diff options
| author | Stephen Rothwell <sfr@canb.auug.org.au> | 2014-08-04 17:00:40 +1000 |
|---|---|---|
| committer | Stephen Rothwell <sfr@canb.auug.org.au> | 2014-08-04 17:00:40 +1000 |
| commit | 1d42fcfe774211af917889db5bfff7ccb6b226fa (patch) | |
| tree | 51bda16f752c893aba2aedb36dd314768401b59f | |
| parent | 189da3b9ff1fa12056be78d769970410b11e83c9 (diff) | |
| parent | 30e8e851f9c57d4710754438c296fe3e92a525a1 (diff) | |
Merge remote-tracking branch 'tip/auto-latest'
Conflicts:
arch/x86/Kconfig
drivers/acpi/acpi_extlog.c
drivers/net/wireless/ath/ath9k/hw.c
fs/nfs/pagelist.c
543 files changed, 14497 insertions, 7024 deletions
diff --git a/Documentation/ABI/testing/sysfs-platform-ts5500 b/Documentation/ABI/testing/sysfs-platform-ts5500 index c88375a537a1..e685957caa12 100644 --- a/Documentation/ABI/testing/sysfs-platform-ts5500 +++ b/Documentation/ABI/testing/sysfs-platform-ts5500 @@ -30,6 +30,13 @@ Description: the corresponding bit is set. For instance, 0x0e means jumpers 2, 3 and 4 are set. +What: /sys/devices/platform/ts5500/name +Date: July 2014 +KernelVersion: 3.16 +Contact: "Savoir-faire Linux Inc." <kernel@savoirfairelinux.com> +Description: + Model name of the TS board, e.g. "TS-5500". + What: /sys/devices/platform/ts5500/rs485 Date: January 2013 KernelVersion: 3.7 diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl index cc63f30de166..6e06ebdbe0c7 100644 --- a/Documentation/DocBook/device-drivers.tmpl +++ b/Documentation/DocBook/device-drivers.tmpl @@ -54,7 +54,7 @@ !Ikernel/sched/cpupri.c !Ikernel/sched/fair.c !Iinclude/linux/completion.h -!Ekernel/timer.c +!Ekernel/time/timer.c </sect1> <sect1><title>Wait queues and Wake events</title> !Iinclude/linux/wait.h @@ -63,7 +63,7 @@ <sect1><title>High-resolution timers</title> !Iinclude/linux/ktime.h !Iinclude/linux/hrtimer.h -!Ekernel/hrtimer.c +!Ekernel/time/hrtimer.c </sect1> <sect1><title>Workqueues and Kevents</title> !Ekernel/workqueue.c diff --git a/Documentation/RCU/rcuref.txt b/Documentation/RCU/rcuref.txt index 141d531aa14b..613033ff2b9b 100644 --- a/Documentation/RCU/rcuref.txt +++ b/Documentation/RCU/rcuref.txt @@ -1,5 +1,14 @@ Reference-count design for elements of lists/arrays protected by RCU. + +Please note that the percpu-ref feature is likely your first +stop if you need to combine reference counts and RCU. Please see +include/linux/percpu-refcount.h for more information. However, in +those unusual cases where percpu-ref would consume too much memory, +please read on. + +------------------------------------------------------------------------ + Reference counting on elements of lists which are protected by traditional reader/writer spinlocks or semaphores are straightforward: diff --git a/Documentation/devicetree/bindings/arm/atmel-aic.txt b/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt index 2742e9cfd6b1..2742e9cfd6b1 100644 --- a/Documentation/devicetree/bindings/arm/atmel-aic.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt diff --git a/Documentation/devicetree/bindings/interrupt-controller/opencores,or1k-pic.txt b/Documentation/devicetree/bindings/interrupt-controller/opencores,or1k-pic.txt new file mode 100644 index 000000000000..55c04faa3f3f --- /dev/null +++ b/Documentation/devicetree/bindings/interrupt-controller/opencores,or1k-pic.txt @@ -0,0 +1,23 @@ +OpenRISC 1000 Programmable Interrupt Controller + +Required properties: + +- compatible : should be "opencores,or1k-pic-level" for variants with + level triggered interrupt lines, "opencores,or1k-pic-edge" for variants with + edge triggered interrupt lines or "opencores,or1200-pic" for machines + with the non-spec compliant or1200 type implementation. + + "opencores,or1k-pic" is also provided as an alias to "opencores,or1200-pic", + but this is only for backwards compatibility. + +- interrupt-controller : Identifies the node as an interrupt controller +- #interrupt-cells : Specifies the number of cells needed to encode an + interrupt source. The value shall be 1. + +Example: + +intc: interrupt-controller { + compatible = "opencores,or1k-pic-level"; + interrupt-controller; + #interrupt-cells = <1>; +}; diff --git a/Documentation/devicetree/bindings/timer/cirrus,clps711x-timer.txt b/Documentation/devicetree/bindings/timer/cirrus,clps711x-timer.txt new file mode 100644 index 000000000000..cd55b52548e4 --- /dev/null +++ b/Documentation/devicetree/bindings/timer/cirrus,clps711x-timer.txt @@ -0,0 +1,29 @@ +* Cirrus Logic CLPS711X Timer Counter + +Required properties: +- compatible: Shall contain "cirrus,clps711x-timer". +- reg : Address and length of the register set. +- interrupts: The interrupt number of the timer. +- clocks : phandle of timer reference clock. + +Note: Each timer should have an alias correctly numbered in "aliases" node. + +Example: + aliases { + timer0 = &timer1; + timer1 = &timer2; + }; + + timer1: timer@80000300 { + compatible = "cirrus,ep7312-timer", "cirrus,clps711x-timer"; + reg = <0x80000300 0x4>; + interrupts = <8>; + clocks = <&clks 5>; + }; + + timer2: timer@80000340 { + compatible = "cirrus,ep7312-timer", "cirrus,clps711x-timer"; + reg = <0x80000340 0x4>; + interrupts = <9>; + clocks = <&clks 6>; + }; diff --git a/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt b/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt new file mode 100644 index 000000000000..7c4408ff4b83 --- /dev/null +++ b/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt @@ -0,0 +1,17 @@ +Mediatek MT6577, MT6572 and MT6589 Timers +--------------------------------------- + +Required properties: +- compatible: Should be "mediatek,mt6577-timer" +- reg: Should contain location and length for timers register. +- clocks: Clocks driving the timer hardware. This list should include two + clocks. The order is system clock and as second clock the RTC clock. + +Examples: + + timer@10008000 { + compatible = "mediatek,mt6577-timer"; + reg = <0x10008000 0x80>; + interrupts = <GIC_SPI 113 IRQ_TYPE_LEVEL_LOW>; + clocks = <&system_clk>, <&rtc_clk>; + }; diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt index 2ae59e41a8bd..ac7269f90764 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.txt +++ b/Documentation/devicetree/bindings/vendor-prefixes.txt @@ -80,6 +80,7 @@ lsi LSI Corp. (LSI Logic) lltc Linear Technology Corporation marvell Marvell Technology Group Ltd. maxim Maxim Integrated Products +mediatek MediaTek Inc. micrel Micrel Inc. microchip Microchip Technology Inc. mosaixtech Mosaix Technologies, Inc. diff --git a/Documentation/filesystems/caching/operations.txt b/Documentation/filesystems/caching/operations.txt index bee2a5f93d60..a1c052cbba35 100644 --- a/Documentation/filesystems/caching/operations.txt +++ b/Documentation/filesystems/caching/operations.txt @@ -90,7 +90,7 @@ operations: to be cleared before proceeding: wait_on_bit(&op->flags, FSCACHE_OP_WAITING, - fscache_wait_bit, TASK_UNINTERRUPTIBLE); + TASK_UNINTERRUPTIBLE); (2) The operation may be fast asynchronous (FSCACHE_OP_FAST), in which case it diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index ddc531a74d04..eb8a10e22f7c 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -1743,6 +1743,25 @@ pair provide additional information particular to the objects they represent. While the first three lines are mandatory and always printed, the rest is optional and may be omitted if no marks created yet. + Timerfd files + ~~~~~~~~~~~~~ + + pos: 0 + flags: 02 + mnt_id: 9 + clockid: 0 + ticks: 0 + settime flags: 01 + it_value: (0, 49406829) + it_interval: (1, 0) + + where 'clockid' is the clock type and 'ticks' is the number of the timer expirations + that have occurred [see timerfd_create(2) for details]. 'settime flags' are + flags in octal form been used to setup the timer [see timerfd_settime(2) for + details]. 'it_value' is remaining time until the timer exiration. + 'it_interval' is the interval for the timer. Note the timer might be set up + with TIMER_ABSTIME option which will be shown in 'settime flags', but 'it_value' + still exhibits timer's remaining time. ------------------------------------------------------------------------------ Configuring procfs diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 355d9f3db813..676930e7b6bd 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2188,6 +2188,21 @@ bytes respectively. Such letter suffixes can also be entirely omitted. and restore using xsave. The kernel will fallback to enabling legacy floating-point and sse state. + noxsaveopt [X86] Disables xsaveopt used in saving x86 extended + register states. The kernel will fall back to use + xsave to save the states. By using this parameter, + performance of saving the states is degraded because + xsave doesn't support modified optimization while + xsaveopt supports it on xsaveopt enabled systems. + + noxsaves [X86] Disables xsaves and xrstors used in saving and + restoring x86 extended register state in compacted + form of xsave area. The kernel will fall back to use + xsaveopt and xrstor to save and restore the states + in standard form of xsave area. By using this + parameter, xsave area per process might occupy more + memory on xsaves enabled systems. + eagerfpu= [X86] on enable eager fpu restore off disable eager fpu restore @@ -2829,6 +2844,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted. quiescent states. Units are jiffies, minimum value is one, and maximum value is HZ. + rcutree.rcu_nocb_leader_stride= [KNL] + Set the number of NOCB kthread groups, which + defaults to the square root of the number of + CPUs. Larger numbers reduces the wakeup overhead + on the per-CPU grace-period kthreads, but increases + that same overhead on each group's leader. + rcutree.qhimark= [KNL] Set threshold of queued RCU callbacks beyond which batch limiting is disabled. diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index f1dc4a215593..a4de88fb55f0 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -757,10 +757,14 @@ SMP BARRIER PAIRING When dealing with CPU-CPU interactions, certain types of memory barrier should always be paired. A lack of appropriate pairing is almost certainly an error. -A write barrier should always be paired with a data dependency barrier or read -barrier, though a general barrier would also be viable. Similarly a read -barrier or a data dependency barrier should always be paired with at least an -write barrier, though, again, a general barrier is viable: +General barriers pair with each other, though they also pair with +most other types of barriers, albeit without transitivity. An acquire +barrier pairs with a release barrier, but both may also pair with other +barriers, including of course general barriers. A write barrier pairs +with a data dependency barrier, an acquire barrier, a release barrier, +a read barrier, or a general barrier. Similarly a read barrier or a +data dependency barrier pairs with a write barrier, an acquire barrier, +a release barrier, or a general barrier: CPU 1 CPU 2 =============== =============== @@ -1893,6 +1897,21 @@ between the STORE to indicate the event and the STORE to set TASK_RUNNING: <general barrier> STORE current->state LOAD event_indicated +To repeat, this write memory barrier is present if and only if something +is actually awakened. To see this, consider the following sequence of +events, where X and Y are both initially zero: + + CPU 1 CPU 2 + =============================== =============================== + X = 1; STORE event_indicated + smp_mb(); wake_up(); + Y = 1; wait_event(wq, Y == 1); + wake_up(); load from Y sees 1, no memory barrier + load from X might see 0 + +In contrast, if a wakeup does occur, CPU 2's load from X would be guaranteed +to see 1. + The available waker functions include: complete(); diff --git a/Documentation/timers/00-INDEX b/Documentation/timers/00-INDEX index 6d042dc1cce0..ee212a27772f 100644 --- a/Documentation/timers/00-INDEX +++ b/Documentation/timers/00-INDEX @@ -12,6 +12,8 @@ Makefile - Build and link hpet_example NO_HZ.txt - Summary of the different methods for the scheduler clock-interrupts management. +timekeeping.txt + - Clock sources, clock events, sched_clock() and delay timer notes timers-howto.txt - how to insert delays in the kernel the right (tm) way. timer_stats.txt diff --git a/Documentation/timers/timekeeping.txt b/Documentation/timers/timekeeping.txt new file mode 100644 index 000000000000..f3a8cf28f802 --- /dev/null +++ b/Documentation/timers/timekeeping.txt @@ -0,0 +1,179 @@ +Clock sources, Clock events, sched_clock() and delay timers +----------------------------------------------------------- + +This document tries to briefly explain some basic kernel timekeeping +abstractions. It partly pertains to the drivers usually found in +drivers/clocksource in the kernel tree, but the code may be spread out +across the kernel. + +If you grep through the kernel source you will find a number of architecture- +specific implementations of clock sources, clockevents and several likewise +architecture-specific overrides of the sched_clock() function and some +delay timers. + +To provide timekeeping for your platform, the clock source provides +the basic timeline, whereas clock events shoot interrupts on certain points +on this timeline, providing facilities such as high-resolution timers. +sched_clock() is used for scheduling and timestamping, and delay timers +provide an accurate delay source using hardware counters. + + +Clock sources +------------- + +The purpose of the clock source is to provide a timeline for the system that +tells you where you are in time. For example issuing the command 'date' on +a Linux system will eventually read the clock source to determine exactly +what time it is. + +Typically the clock source is a monotonic, atomic counter which will provide +n bits which count from 0 to 2^(n-1) and then wraps around to 0 and start over. +It will ideally NEVER stop ticking as long as the system is running. It +may stop during system suspend. + +The clock source shall have as high resolution as possible, and the frequency +shall be as stable and correct as possible as compared to a real-world wall +clock. It should not move unpredictably back and forth in time or miss a few +cycles here and there. + +It must be immune to the kind of effects that occur in hardware where e.g. +the counter register is read in two phases on the bus lowest 16 bits first +and the higher 16 bits in a second bus cycle with the counter bits +potentially being updated in between leading to the risk of very strange +values from the counter. + +When the wall-clock accuracy of the clock source isn't satisfactory, there +are various quirks and layers in the timekeeping code for e.g. synchronizing +the user-visible time to RTC clocks in the system or against networked time +servers using NTP, but all they do basically is update an offset against +the clock source, which provides the fundamental timeline for the system. +These measures does not affect the clock source per se, they only adapt the +system to the shortcomings of it. + +The clock source struct shall provide means to translate the provided counter +into a nanosecond value as an unsigned long long (unsigned 64 bit) number. +Since this operation may be invoked very often, doing this in a strict +mathematical sense is not desirable: instead the number is taken as close as +possible to a nanosecond value using only the arithmetic operations +multiply and shift, so in clocksource_cyc2ns() you find: + + ns ~= (clocksource * mult) >> shift + +You will find a number of helper functions in the clock source code intended +to aid in providing these mult and shift values, such as +clocksource_khz2mult(), clocksource_hz2mult() that help determine the +mult factor from a fixed shift, and clocksource_register_hz() and +clocksource_register_khz() which will help out assigning both shift and mult +factors using the frequency of the clock source as the only input. + +For real simple clock sources accessed from a single I/O memory location +there is nowadays even clocksource_mmio_init() which will take a memory +location, bit width, a parameter telling whether the counter in the +register counts up or down, and the timer clock rate, and then conjure all +necessary parameters. + +Since a 32-bit counter at say 100 MHz will wrap around to zero after some 43 +seconds, the code handling the clock source will have to compensate for this. +That is the reason why the clock source struct also contains a 'mask' +member telling how many bits of the source are valid. This way the timekeeping +code knows when the counter will wrap around and can insert the necessary +compensation code on both sides of the wrap point so that the system timeline +remains monotonic. + + +Clock events +------------ + +Clock events are the conceptual reverse of clock sources: they take a +desired time specification value and calculate the values to poke into +hardware timer registers. + +Clock events are orthogonal to clock sources. The same hardware +and register range may be used for the clock event, but it is essentially +a different thing. The hardware driving clock events has to be able to +fire interrupts, so as to trigger events on the system timeline. On an SMP +system, it is ideal (and customary) to have one such event driving timer per +CPU core, so that each core can trigger events independently of any other +core. + +You will notice that the clock event device code is based on the same basic +idea about translating counters to nanoseconds using mult and shift +arithmetic, and you find the same family of helper functions again for +assigning these values. The clock event driver does not need a 'mask' +attribute however: the system will not try to plan events beyond the time +horizon of the clock event. + + +sched_clock() +------------- + +In addition to the clock sources and clock events there is a special weak +function in the kernel called sched_clock(). This function shall return the +number of nanoseconds since the system was started. An architecture may or +may not provide an implementation of sched_clock() on its own. If a local +implementation is not provided, the system jiffy counter will be used as +sched_clock(). + +As the name suggests, sched_clock() is used for scheduling the system, +determining the absolute timeslice for a certain process in the CFS scheduler +for example. It is also used for printk timestamps when you have selected to +include time information in printk for things like bootcharts. + +Compared to clock sources, sched_clock() has to be very fast: it is called +much more often, especially by the scheduler. If you have to do trade-offs +between accuracy compared to the clock source, you may sacrifice accuracy +for speed in sched_clock(). It however requires some of the same basic +characteristics as the clock source, i.e. it should be monotonic. + +The sched_clock() function may wrap only on unsigned long long boundaries, +i.e. after 64 bits. Since this is a nanosecond value this will mean it wraps +after circa 585 years. (For most practical systems this means "never".) + +If an architecture does not provide its own implementation of this function, +it will fall back to using jiffies, making its maximum resolution 1/HZ of the +jiffy frequency for the architecture. This will affect scheduling accuracy +and will likely show up in system benchmarks. + +The clock driving sched_clock() may stop or reset to zero during system +suspend/sleep. This does not matter to the function it serves of scheduling +events on the system. However it may result in interesting timestamps in +printk(). + +The sched_clock() function should be callable in any context, IRQ- and +NMI-safe and return a sane value in any context. + +Some architectures may have a limited set of time sources and lack a nice +counter to derive a 64-bit nanosecond value, so for example on the ARM +architecture, special helper functions have been created to provide a +sched_clock() nanosecond base from a 16- or 32-bit counter. Sometimes the +same counter that is also used as clock source is used for this purpose. + +On SMP systems, it is crucial for performance that sched_clock() can be called +independently on each CPU without any synchronization performance hits. +Some hardware (such as the x86 TSC) will cause the sched_clock() function to +drift between the CPUs on the system. The kernel can work around this by +enabling the CONFIG_HAVE_UNSTABLE_SCHED_CLOCK option. This is another aspect +that makes sched_clock() different from the ordinary clock source. + + +Delay timers (some architectures only) +-------------------------------------- + +On systems with variable CPU frequency, the various kernel delay() functions +will sometimes behave strangely. Basically these delays usually use a hard +loop to delay a certain number of jiffy fractions using a "lpj" (loops per +jiffy) value, calibrated on boot. + +Let's hope that your system is running on maximum frequency when this value +is calibrated: as an effect when the frequency is geared down to half the +full frequency, any delay() will be twice as long. Usually this does not +hurt, as you're commonly requesting that amount of delay *or more*. But +basically the semantics are quite unpredictable on such systems. + +Enter timer-based delays. Using these, a timer read may be used instead of +a hard-coded loop for providing the desired delay. + +This is done by declaring a struct delay_timer and assigning the appropriate +function pointers and rate settings for this delay timer. + +This is available on some architectures like OpenRISC or ARM. diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt index 2479b2a0c77c..4da42616939f 100644 --- a/Documentation/trace/ftrace.txt +++ b/Documentation/trace/ftrace.txt @@ -1515,7 +1515,7 @@ Doing the same with chrt -r 5 and function-trace set. <idle>-0 3d.h4 1us+: 0:120:R + [003] 2448: 94:R sleep <idle>-0 3d.h4 2us : ttwu_do_activate.constprop.87 <-try_to_wake_up <idle>-0 3d.h3 3us : check_preempt_curr <-ttwu_do_wakeup - <idle>-0 3d.h3 3us : resched_task <-check_preempt_curr + <idle>-0 3d.h3 3us : resched_curr <-check_preempt_curr <idle>-0 3dNh3 4us : task_woken_rt <-ttwu_do_wakeup <idle>-0 3dNh3 4us : _raw_spin_unlock <-try_to_wake_up <idle>-0 3dNh3 4us : sub_preempt_count <-_raw_spin_unlock diff --git a/Documentation/x86/tlb.txt b/Documentation/x86/tlb.txt new file mode 100644 index 000000000000..2b3a82e69151 --- /dev/null +++ b/Documentation/x86/tlb.txt @@ -0,0 +1,75 @@ +When the kernel unmaps or modified the attributes of a range of +memory, it has two choices: + 1. Flush the entire TLB with a two-instruction sequence. This is + a quick operation, but it causes collateral damage: TLB entries + from areas other than the one we are trying to flush will be + destroyed and must be refilled later, at some cost. + 2. Use the invlpg instruction to invalidate a single page at a + time. This could potentialy cost many more instructions, but + it is a much more precise operation, causing no collateral + damage to other TLB entries. + +Which method to do depends on a few things: + 1. The size of the flush being performed. A flush of the entire + address space is obviously better performed by flushing the + entire TLB than doing 2^48/PAGE_SIZE individual flushes. + 2. The contents of the TLB. If the TLB is empty, then there will + be no collateral damage caused by doing the global flush, and + all of the individual flush will have ended up being wasted + work. + 3. The size of the TLB. The larger the TLB, the more collateral + damage we do with a full flush. So, the larger the TLB, the + more attrative an individual flush looks. Data and + instructions have separate TLBs, as do different page sizes. + 4. The microarchitecture. The TLB has become a multi-level + cache on modern CPUs, and the global flushes have become more + expensive relative to single-page flushes. + +There is obviously no way the kernel can know all these things, +especially the contents of the TLB during a given flush. The +sizes of the flush will vary greatly depending on the workload as +well. There is essentially no "right" point to choose. + +You may be doing too many individual invalidations if you see the +invlpg instruction (or instructions _near_ it) show up high in +profiles. If you believe that individual invalidations being +called too often, you can lower the tunable: + + /sys/debug/kernel/x86/tlb_single_page_flush_ceiling + +This will cause us to do the global flush for more cases. +Lowering it to 0 will disable the use of the individual flushes. +Setting it to 1 is a very conservative setting and it should +never need to be 0 under normal circumstances. + +Despite the fact that a single individual flush on x86 is +guaranteed to flush a full 2MB [1], hugetlbfs always uses the full +flushes. THP is treated exactly the same as normal memory. + +You might see invlpg inside of flush_tlb_mm_range() show up in +profiles, or you can use the trace_tlb_flush() tracepoints. to +determine how long the flush operations are taking. + +Essentially, you are balancing the cycles you spend doing invlpg +with the cycles that you spend refilling the TLB later. + +You can measure how expensive TLB refills are by using +performance counters and 'perf stat', like this: + +perf stat -e + cpu/event=0x8,umask=0x84,name=dtlb_load_misses_walk_duration/, + cpu/event=0x8,umask=0x82,name=dtlb_load_misses_walk_completed/, + cpu/event=0x49,umask=0x4,name=dtlb_store_misses_walk_duration/, + cpu/event=0x49,umask=0x2,name=dtlb_store_misses_walk_completed/, + cpu/event=0x85,umask=0x4,name=itlb_misses_walk_duration/, + cpu/event=0x85,umask=0x2,name=itlb_misses_walk_completed/ + +That works on an IvyBridge-era CPU (i5-3320M). Different CPUs +may have differently-named counters, but they should at least +be there in some form. You can use pmu-tools 'ocperf list' +(https://github.com/andikleen/pmu-tools) to find the right +counters for a given CPU. + +1. A footnote in Intel's SDM "4.10.4.2 Recommended Invalidation" + says: "One execution of INVLPG is sufficient even for a page + with size greater than 4 KBytes." diff --git a/MAINTAINERS b/MAINTAINERS index 08ce5efc2f37..1c9a3ab09091 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -70,6 +70,8 @@ Descriptions of section entries: P: Person (obsolete) M: Mail patches to: FullName <address@domain> + R: Designated reviewer: FullName <address@domain> + These reviewers should be CCed on patches. L: Mailing list that is relevant to this area W: Web-page with status/info Q: Patchwork web based patch tracking system site @@ -4252,7 +4254,7 @@ L: linux-kernel@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core S: Maintained F: Documentation/timers/ -F: kernel/hrtimer.c +F: kernel/time/hrtimer.c F: kernel/time/clockevents.c F: kernel/time/tick*.* F: kernel/time/timer_*.c @@ -7081,10 +7083,10 @@ POSIX CLOCKS and TIMERS M: Thomas Gleixner <tglx@linutronix.de> L: linux-kernel@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core -S: Supported +S: Maintained F: fs/timerfd.c F: include/linux/timer* -F: kernel/*timer* +F: kernel/time/*timer* POWER SUPPLY CLASS/SUBSYSTEM and DRIVERS M: Sebastian Reichel <sre@kernel.org> @@ -7493,10 +7495,14 @@ L: linux-kernel@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git F: Documentation/RCU/torture.txt -F: kernel/rcu/torture.c +F: kernel/rcu/rcutorture.c RCUTORTURE TEST FRAMEWORK M: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> +M: Josh Triplett <josh@joshtriplett.org> +R: Steven Rostedt <rostedt@goodmis.org> +R: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> +R: Lai Jiangshan <laijs@cn.fujitsu.com> L: linux-kernel@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git @@ -7519,8 +7525,11 @@ S: Supported F: net/rds/ READ-COPY UPDATE (RCU) -M: Dipankar Sarma <dipankar@in.ibm.com> M: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> +M: Josh Triplett <josh@joshtriplett.org> +R: Steven Rostedt <rostedt@goodmis.org> +R: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> +R: Lai Jiangshan <laijs@cn.fujitsu.com> L: linux-kernel@vger.kernel.org W: http://www.rdrop.com/users/paulmck/RCU/ S: Supported @@ -7530,7 +7539,7 @@ X: Documentation/RCU/torture.txt F: include/linux/rcu* X: include/linux/srcu.h F: kernel/rcu/ -X: kernel/rcu/torture.c +X: kernel/torture.c REAL TIME CLOCK (RTC) SUBSYSTEM M: Alessandro Zummo <a.zummo@towertech.it> @@ -8330,6 +8339,9 @@ F: mm/sl?b* SLEEPABLE READ-COPY UPDATE (SRCU) M: Lai Jiangshan <laijs@cn.fujitsu.com> M: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> +M: Josh Triplett <josh@joshtriplett.org> +R: Steven Rostedt <rostedt@goodmis.org> +R: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> L: linux-kernel@vger.kernel.org W: http://www.rdrop.com/users/paulmck/RCU/ S: Supported diff --git a/arch/alpha/include/asm/processor.h b/arch/alpha/include/asm/processor.h index 6cb7fe85c4b5..b4cf03690394 100644 --- a/arch/alpha/include/asm/processor.h +++ b/arch/alpha/include/asm/processor.h @@ -57,6 +57,7 @@ unsigned long get_wchan(struct task_struct *p); ((tsk) == current ? rdusp() : task_thread_info(tsk)->pcb.usp) #define cpu_relax() barrier() +#define cpu_relax_lowlatency() cpu_relax() #define ARCH_HAS_PREFETCH #define ARCH_HAS_PREFETCHW diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h index d99f9b37cd15..82588f3ba77f 100644 --- a/arch/arc/include/asm/processor.h +++ b/arch/arc/include/asm/processor.h @@ -62,6 +62,8 @@ unsigned long thread_saved_pc(struct task_struct *t); #define cpu_relax() do { } while (0) #endif +#define cpu_relax_lowlatency() cpu_relax() + #define copy_segments(tsk, mm) do { } while (0) #define release_segments(mm) do { } while (0) diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c index 63177e4cb66d..b9a5685a990e 100644 --- a/arch/arc/kernel/perf_event.c +++ b/arch/arc/kernel/perf_event.c @@ -99,10 +99,6 @@ static int arc_pmu_event_init(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; int ret; - /* ARC 700 PMU does not support sampling events */ - if (is_sampling_event(event)) - return -ENOENT; - switch (event->attr.type) { case PERF_TYPE_HARDWARE: if (event->attr.config >= PERF_COUNT_HW_MAX) @@ -298,6 +294,9 @@ static int arc_pmu_device_probe(struct platform_device *pdev) .read = arc_pmu_read, }; + /* ARC 700 PMU does not support sampling events */ + arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; + ret = perf_pmu_register(&arc_pmu->pmu, pdev->name, PERF_TYPE_RAW); return ret; diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index e24b16a1fa29..916cedbd7a67 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -65,7 +65,6 @@ config ARM select HAVE_UID16 select HAVE_VIRT_CPU_ACCOUNTING_GEN select IRQ_FORCED_THREADING - select KTIME_SCALAR select MODULES_USE_ELF_REL select NO_BOOTMEM select OLD_SIGACTION @@ -623,6 +622,7 @@ config ARCH_PXA select AUTO_ZRELADDR select CLKDEV_LOOKUP select CLKSRC_MMIO + select CLKSRC_OF select GENERIC_CLOCKEVENTS select GPIO_PXA select HAVE_IDE diff --git a/arch/arm/common/bL_switcher.c b/arch/arm/common/bL_switcher.c index 490f3dced749..6eaddc47c43d 100644 --- a/arch/arm/common/bL_switcher.c +++ b/arch/arm/common/bL_switcher.c @@ -58,16 +58,6 @@ static int read_mpidr(void) } /* - * Get a global nanosecond time stamp for tracing. - */ -static s64 get_ns(void) -{ - struct timespec ts; - getnstimeofday(&ts); - return timespec_to_ns(&ts); -} - -/* * bL switcher core code. */ @@ -224,7 +214,7 @@ static int bL_switch_to(unsigned int new_cluster_id) */ local_irq_disable(); local_fiq_disable(); - trace_cpu_migrate_begin(get_ns(), ob_mpidr); + trace_cpu_migrate_begin(ktime_get_real_ns(), ob_mpidr); /* redirect GIC's SGIs to our counterpart */ gic_migrate_target(bL_gic_id[ib_cpu][ib_cluster]); @@ -267,7 +257,7 @@ static int bL_switch_to(unsigned int new_cluster_id) tdev->evtdev->next_event, 1); } - trace_cpu_migrate_finish(get_ns(), ib_mpidr); + trace_cpu_migrate_finish(ktime_get_real_ns(), ib_mpidr); local_fiq_enable(); local_irq_enable(); @@ -558,7 +548,7 @@ int bL_switcher_get_logical_index(u32 mpidr) static void bL_switcher_trace_trigger_cpu(void *__always_unused info) { - trace_cpu_migrate_current(get_ns(), read_mpidr()); + trace_cpu_migrate_current(ktime_get_real_ns(), read_mpidr()); } int bL_switcher_trace_trigger(void) diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h index c3d5fc124a05..8a1e8e995dae 100644 --- a/arch/arm/include/asm/processor.h +++ b/arch/arm/include/asm/processor.h @@ -82,6 +82,8 @@ unsigned long get_wchan(struct task_struct *p); #define cpu_relax() barrier() #endif +#define cpu_relax_lowlatency() cpu_relax() + #define task_pt_regs(p) \ ((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1) diff --git a/arch/arm/mach-pxa/Makefile b/arch/arm/mach-pxa/Makefile index 648867a8caa8..2fe1824c6dcb 100644 --- a/arch/arm/mach-pxa/Makefile +++ b/arch/arm/mach-pxa/Makefile @@ -4,7 +4,7 @@ # Common support (must be linked before board specific support) obj-y += clock.o devices.o generic.o irq.o \ - time.o reset.o + reset.o obj-$(CONFIG_PM) += pm.o sleep.o standby.o # Generic drivers that other drivers may depend upon diff --git a/arch/arm/mach-pxa/generic.c b/arch/arm/mach-pxa/generic.c index b31e101cad9b..630fa916bbc6 100644 --- a/arch/arm/mach-pxa/generic.c +++ b/arch/arm/mach-pxa/generic.c @@ -25,11 +25,13 @@ #include <asm/mach/map.h> #include <asm/mach-types.h> +#include <mach/irqs.h> #include <mach/reset.h> #include <mach/smemc.h> #include <mach/pxa3xx-regs.h> #include "generic.h" +#include <clocksource/pxa.h> void clear_reset_status(unsigned int mask) { @@ -57,6 +59,15 @@ unsigned long get_clock_tick_rate(void) EXPORT_SYMBOL(get_clock_tick_rate); /* + * For non device-tree builds, keep legacy timer init + */ +void pxa_timer_init(void) +{ + pxa_timer_nodt_init(IRQ_OST0, io_p2v(0x40a00000), + get_clock_tick_rate()); +} + +/* * Get the clock frequency as reflected by CCCR and the turbo flag. * We assume these values have been applied via a fcs. * If info is not 0 we also display the current settings. diff --git a/arch/arm/mach-pxa/time.c b/arch/arm/mach-pxa/time.c deleted file mode 100644 index fca174e3865d..000000000000 --- a/arch/arm/mach-pxa/time.c +++ /dev/null @@ -1,162 +0,0 @@ -/* - * arch/arm/mach-pxa/time.c - * - * PXA clocksource, clockevents, and OST interrupt handlers. - * Copyright (c) 2007 by Bill Gatliff <bgat@billgatliff.com>. - * - * Derived from Nicolas Pitre's PXA timer handler Copyright (c) 2001 - * by MontaVista Software, Inc. (Nico, your code rocks!) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/clockchips.h> -#include <linux/sched_clock.h> - -#include <asm/div64.h> -#include <asm/mach/irq.h> -#include <asm/mach/time.h> -#include <mach/regs-ost.h> -#include <mach/irqs.h> - -/* - * This is PXA's sched_clock implementation. This has a resolution - * of at least 308 ns and a maximum value of 208 days. - * - * The return value is guaranteed to be monotonic in that range as - * long as there is always less than 582 seconds between successive - * calls to sched_clock() which should always be the case in practice. - */ - -static u64 notrace pxa_read_sched_clock(void) -{ - return readl_relaxed(OSCR); -} - - -#define MIN_OSCR_DELTA 16 - -static irqreturn_t -pxa_ost0_interrupt(int irq, void *dev_id) -{ - struct clock_event_device *c = dev_id; - - /* Disarm the compare/match, signal the event. */ - writel_relaxed(readl_relaxed(OIER) & ~OIER_E0, OIER); - writel_relaxed(OSSR_M0, OSSR); - c->event_handler(c); - - return IRQ_HANDLED; -} - -static int -pxa_osmr0_set_next_event(unsigned long delta, struct clock_event_device *dev) -{ - unsigned long next, oscr; - - writel_relaxed(readl_relaxed(OIER) | OIER_E0, OIER); - next = readl_relaxed(OSCR) + delta; - writel_relaxed(next, OSMR0); - oscr = readl_relaxed(OSCR); - - return (signed)(next - oscr) <= MIN_OSCR_DELTA ? -ETIME : 0; -} - -static void -pxa_osmr0_set_mode(enum clock_event_mode mode, struct clock_event_device *dev) -{ - switch (mode) { - case CLOCK_EVT_MODE_ONESHOT: - writel_relaxed(readl_relaxed(OIER) & ~OIER_E0, OIER); - writel_relaxed(OSSR_M0, OSSR); - break; - - case CLOCK_EVT_MODE_UNUSED: - case CLOCK_EVT_MODE_SHUTDOWN: - /* initializing, released, or preparing for suspend */ - writel_relaxed(readl_relaxed(OIER) & ~OIER_E0, OIER); - writel_relaxed(OSSR_M0, OSSR); - break; - - case CLOCK_EVT_MODE_RESUME: - case CLOCK_EVT_MODE_PERIODIC: - break; - } -} - -#ifdef CONFIG_PM -static unsigned long osmr[4], oier, oscr; - -static void pxa_timer_suspend(struct clock_event_device *cedev) -{ - osmr[0] = readl_relaxed(OSMR0); - osmr[1] = readl_relaxed(OSMR1); - osmr[2] = readl_relaxed(OSMR2); - osmr[3] = readl_relaxed(OSMR3); - oier = readl_relaxed(OIER); - oscr = readl_relaxed(OSCR); -} - -static void pxa_timer_resume(struct clock_event_device *cedev) -{ - /* - * Ensure that we have at least MIN_OSCR_DELTA between match - * register 0 and the OSCR, to guarantee that we will receive - * the one-shot timer interrupt. We adjust OSMR0 in preference - * to OSCR to guarantee that OSCR is monotonically incrementing. - */ - if (osmr[0] - oscr < MIN_OSCR_DELTA) - osmr[0] += MIN_OSCR_DELTA; - - writel_relaxed(osmr[0], OSMR0); - writel_relaxed(osmr[1], OSMR1); - writel_relaxed(osmr[2], OSMR2); - writel_relaxed(osmr[3], OSMR3); - writel_relaxed(oier, OIER); - writel_relaxed(oscr, OSCR); -} -#else -#define pxa_timer_suspend NULL -#define pxa_timer_resume NULL -#endif - -static struct clock_event_device ckevt_pxa_osmr0 = { - .name = "osmr0", - .features = CLOCK_EVT_FEAT_ONESHOT, - .rating = 200, - .set_next_event = pxa_osmr0_set_next_event, - .set_mode = pxa_osmr0_set_mode, - .suspend = pxa_timer_suspend, - .resume = pxa_timer_resume, -}; - -static struct irqaction pxa_ost0_irq = { - .name = "ost0", - .flags = IRQF_TIMER | IRQF_IRQPOLL, - .handler = pxa_ost0_interrupt, - .dev_id = &ckevt_pxa_osmr0, -}; - -void __init pxa_timer_init(void) -{ - unsigned long clock_tick_rate = get_clock_tick_rate(); - - writel_relaxed(0, OIER); - writel_relaxed(OSSR_M0 | OSSR_M1 | OSSR_M2 | OSSR_M3, OSSR); - - sched_clock_register(pxa_read_sched_clock, 32, clock_tick_rate); - - ckevt_pxa_osmr0.cpumask = cpumask_of(0); - - setup_irq(IRQ_OST0, &pxa_ost0_irq); - - clocksource_mmio_init(OSCR, "oscr0", clock_tick_rate, 200, 32, - clocksource_mmio_readl_up); - clockevents_config_and_register(&ckevt_pxa_osmr0, clock_tick_rate, - MIN_OSCR_DELTA * 2, 0x7fffffff); -} diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index f3b584be76d7..b0f9c9db9590 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -347,12 +347,18 @@ config CMDLINE_FORCE This is useful if you cannot or don't want to change the command-line options your boot loader passes to the kernel. +config EFI_STUB + bool + config EFI bool "UEFI runtime support" depends on OF && !CPU_BIG_ENDIAN select LIBFDT select UCS2_STRING select EFI_PARAMS_FROM_FDT + select EFI_RUNTIME_WRAPPERS + select EFI_STUB + select EFI_ARMSTUB default y help This option provides support for runtime services provided diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index e8d025c1459e..57833546bf00 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -52,6 +52,7 @@ core-$(CONFIG_XEN) += arch/arm64/xen/ core-$(CONFIG_CRYPTO) += arch/arm64/crypto/ libs-y := arch/arm64/lib/ $(libs-y) libs-y += $(LIBGCC) +libs-$(CONFIG_EFI_STUB) += drivers/firmware/efi/libstub/ # Default target when executing plain make KBUILD_IMAGE := Image.gz diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 5a46c4e7f539..a34fd3b12e2b 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -2,6 +2,7 @@ #define _ASM_EFI_H #include <asm/io.h> +#include <asm/neon.h> #ifdef CONFIG_EFI extern void efi_init(void); @@ -11,4 +12,36 @@ extern void efi_idmap_init(void); #define efi_idmap_init() #endif +#define efi_call_virt(f, ...) \ +({ \ + efi_##f##_t *__f = efi.systab->runtime->f; \ + efi_status_t __s; \ + \ + kernel_neon_begin(); \ + __s = __f(__VA_ARGS__); \ + kernel_neon_end(); \ + __s; \ +}) + +#define __efi_call_virt(f, ...) \ +({ \ + efi_##f##_t *__f = efi.systab->runtime->f; \ + \ + kernel_neon_begin(); \ + __f(__VA_ARGS__); \ + kernel_neon_end(); \ +}) + +/* arch specific definitions used by the stub code */ + +/* + * AArch64 requires the DTB to be 8-byte aligned in the first 512MiB from + * start of kernel and may not cross a 2MiB boundary. We set alignment to + * 2MiB so we know it won't cross a 2MiB boundary. + */ +#define EFI_FDT_ALIGN SZ_2M /* used by allocate_new_fdt_and_exit_boot() */ +#define MAX_FDT_OFFSET SZ_512M + +#define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__) + #endif /* _ASM_EFI_H */ diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 77712454486b..3df21feeabdd 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -129,6 +129,7 @@ extern void release_thread(struct task_struct *); unsigned long get_wchan(struct task_struct *p); #define cpu_relax() barrier() +#define cpu_relax_lowlatency() cpu_relax() /* Thread switching */ extern struct task_struct *cpu_switch_to(struct task_struct *prev, diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 27c72ef4fd7a..df7ef8768fc2 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -4,8 +4,7 @@ CPPFLAGS_vmlinux.lds := -DTEXT_OFFSET=$(TEXT_OFFSET) AFLAGS_head.o := -DTEXT_OFFSET=$(TEXT_OFFSET) -CFLAGS_efi-stub.o := -DTEXT_OFFSET=$(TEXT_OFFSET) \ - -I$(src)/../../../scripts/dtc/libfdt +CFLAGS_efi-stub.o := -DTEXT_OFFSET=$(TEXT_OFFSET) CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_insn.o = -pg diff --git a/arch/arm64/kernel/efi-stub.c b/arch/arm64/kernel/efi-stub.c index e786e6cdc400..1317fef8dde9 100644 --- a/arch/arm64/kernel/efi-stub.c +++ b/arch/arm64/kernel/efi-stub.c @@ -10,46 +10,16 @@ * */ #include <linux/efi.h> -#include <linux/libfdt.h> +#include <asm/efi.h> #include <asm/sections.h> -/* - * AArch64 requires the DTB to be 8-byte aligned in the first 512MiB from - * start of kernel and may not cross a 2MiB boundary. We set alignment to - * 2MiB so we know it won't cross a 2MiB boundary. - */ -#define EFI_FDT_ALIGN SZ_2M /* used by allocate_new_fdt_and_exit_boot() */ -#define MAX_FDT_OFFSET SZ_512M - -#define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__) - -static void efi_char16_printk(efi_system_table_t *sys_table_arg, - efi_char16_t *str); - -static efi_status_t efi_open_volume(efi_system_table_t *sys_table, - void *__image, void **__fh); -static efi_status_t efi_file_close(void *handle); - -static efi_status_t -efi_file_read(void *handle, unsigned long *size, void *addr); - -static efi_status_t -efi_file_size(efi_system_table_t *sys_table, void *__fh, - efi_char16_t *filename_16, void **handle, u64 *file_sz); - -/* Include shared EFI stub code */ -#include "../../../drivers/firmware/efi/efi-stub-helper.c" -#include "../../../drivers/firmware/efi/fdt.c" -#include "../../../drivers/firmware/efi/arm-stub.c" - - -static 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 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; @@ -69,7 +39,7 @@ static efi_status_t handle_kernel_image(efi_system_table_t *sys_table, if (*image_addr != (dram_base + TEXT_OFFSET)) { pr_efi_err(sys_table, "Failed to alloc kernel memory\n"); efi_free(sys_table, kernel_memsize, *image_addr); - return EFI_ERROR; + return EFI_LOAD_ERROR; } *image_size = kernel_memsize; } diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 14db1f6e8d7f..e72f3100958f 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -414,13 +414,24 @@ static int __init arm64_enter_virtual_mode(void) for_each_efi_memory_desc(&memmap, md) { if (!(md->attribute & EFI_MEMORY_RUNTIME)) continue; - if (remap_region(md, &virt_md)) - ++count; + if (!remap_region(md, &virt_md)) + goto err_unmap; + ++count; } efi.systab = (__force void *)efi_lookup_mapped_addr(efi_system_table); - if (efi.systab) - set_bit(EFI_SYSTEM_TABLES, &efi.flags); + if (!efi.systab) { + /* + * If we have no virtual mapping for the System Table at this + * point, the memory map doesn't cover the physical offset where + * it resides. This means the System Table will be inaccessible + * to Runtime Services themselves once the virtual mapping is + * installed. + */ + pr_err("Failed to remap EFI System Table -- buggy firmware?\n"); + goto err_unmap; + } + set_bit(EFI_SYSTEM_TABLES, &efi.flags); local_irq_save(flags); cpu_switch_mm(idmap_pg_dir, &init_mm); @@ -449,21 +460,18 @@ static int __init arm64_enter_virtual_mode(void) /* Set up runtime services function pointers */ runtime = efi.systab->runtime; - efi.get_time = runtime->get_time; - efi.set_time = runtime->set_time; - efi.get_wakeup_time = runtime->get_wakeup_time; - efi.set_wakeup_time = runtime->set_wakeup_time; - efi.get_variable = runtime->get_variable; - efi.get_next_variable = runtime->get_next_variable; - efi.set_variable = runtime->set_variable; - efi.query_variable_info = runtime->query_variable_info; - efi.update_capsule = runtime->update_capsule; - efi.query_capsule_caps = runtime->query_capsule_caps; - efi.get_next_high_mono_count = runtime->get_next_high_mono_count; - efi.reset_system = runtime->reset_system; - + efi_native_runtime_setup(); set_bit(EFI_RUNTIME_SERVICES, &efi.flags); return 0; + +err_unmap: + /* unmap all mappings that succeeded: there are 'count' of those */ + for (virt_md = virtmap; count--; virt_md += memmap.desc_size) { + md = virt_md; + iounmap((__force void __iomem *)md->virt_addr); + } + kfree(virtmap); + return -1; } early_initcall(arm64_enter_virtual_mode); diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 24f2e8c62479..a81a446a5786 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -219,7 +219,7 @@ struct vm_area_struct *get_gate_vma(struct mm_struct *mm) void update_vsyscall(struct timekeeper *tk) { struct timespec xtime_coarse; - u32 use_syscall = strcmp(tk->clock->name, "arch_sys_counter"); + u32 use_syscall = strcmp(tk->tkr.clock->name, "arch_sys_counter"); ++vdso_data->tb_seq_count; smp_wmb(); @@ -232,11 +232,11 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->wtm_clock_nsec = tk->wall_to_monotonic.tv_nsec; if (!use_syscall) { - vdso_data->cs_cycle_last = tk->clock->cycle_last; + vdso_data->cs_cycle_last = tk->tkr.cycle_last; vdso_data->xtime_clock_sec = tk->xtime_sec; - vdso_data->xtime_clock_nsec = tk->xtime_nsec; - vdso_data->cs_mult = tk->mult; - vdso_data->cs_shift = tk->shift; + vdso_data->xtime_clock_nsec = tk->tkr.xtime_nsec; + vdso_data->cs_mult = tk->tkr.mult; + vdso_data->cs_shift = tk->tkr.shift; } smp_wmb(); diff --git a/arch/avr32/include/asm/processor.h b/arch/avr32/include/asm/processor.h index 972adcc1e8f4..941593c7d9f3 100644 --- a/arch/avr32/include/asm/processor.h +++ b/arch/avr32/include/asm/processor.h @@ -92,6 +92,7 @@ extern struct avr32_cpuinfo boot_cpu_data; #define TASK_UNMAPPED_BASE (PAGE_ALIGN(TASK_SIZE / 3)) #define cpu_relax() barrier() +#define cpu_relax_lowlatency() cpu_relax() #define cpu_sync_pipeline() asm volatile("sub pc, -2" : : : "memory") struct cpu_context { diff --git a/arch/blackfin/include/asm/processor.h b/arch/blackfin/include/asm/processor.h index d0e72e9475a6..7acd46653df3 100644 --- a/arch/blackfin/include/asm/processor.h +++ b/arch/blackfin/include/asm/processor.h @@ -99,7 +99,7 @@ unsigned long get_wchan(struct task_struct *p); #define KSTK_ESP(tsk) ((tsk) == current ? rdusp() : (tsk)->thread.usp) #define cpu_relax() smp_mb() - +#define cpu_relax_lowlatency() cpu_relax() /* Get the Silicon Revision of the chip */ static inline uint32_t __pure bfin_revid(void) diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c index 974e55496db3..ea2032013cc2 100644 --- a/arch/blackfin/kernel/perf_event.c +++ b/arch/blackfin/kernel/perf_event.c @@ -389,14 +389,6 @@ static int bfin_pmu_event_init(struct perf_event *event) if (attr->exclude_hv || attr->exclude_idle) return -EPERM; - /* - * All of the on-chip counters are "limited", in that they have - * no interrupts, and are therefore unable to do sampling without - * further work and timer assistance. - */ - if (hwc->sample_period) - return -EINVAL; - ret = 0; switch (attr->type) { case PERF_TYPE_RAW: @@ -490,6 +482,13 @@ static int __init bfin_pmu_init(void) { int ret; + /* + * All of the on-chip counters are "limited", in that they have + * no interrupts, and are therefore unable to do sampling without + * further work and timer assistance. + */ + pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; + ret = perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW); if (!ret) perf_cpu_notifier(bfin_pmu_notifier); diff --git a/arch/c6x/include/asm/processor.h b/arch/c6x/include/asm/processor.h index b9eb3da7f278..f2ef31be2f8b 100644 --- a/arch/c6x/include/asm/processor.h +++ b/arch/c6x/include/asm/processor.h @@ -121,6 +121,7 @@ extern unsigned long get_wchan(struct task_struct *p); #define KSTK_ESP(task) (task_pt_regs(task)->sp) #define cpu_relax() do { } while (0) +#define cpu_relax_lowlatency() cpu_relax() extern const struct seq_operations cpuinfo_op; diff --git a/arch/cris/include/asm/processor.h b/arch/cris/include/asm/processor.h index 15b815df29c1..862126b58116 100644 --- a/arch/cris/include/asm/processor.h +++ b/arch/cris/include/asm/processor.h @@ -63,6 +63,7 @@ static inline void release_thread(struct task_struct *dead_task) #define init_stack (init_thread_union.stack) #define cpu_relax() barrier() +#define cpu_relax_lowlatency() cpu_relax() void default_idle(void); diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig index 0fd6138f6203..4dc89d1f9c48 100644 --- a/arch/hexagon/Kconfig +++ b/arch/hexagon/Kconfig @@ -23,7 +23,6 @@ config HEXAGON select GENERIC_IOMAP select GENERIC_SMP_IDLE_THREAD select STACKTRACE_SUPPORT - select KTIME_SCALAR select GENERIC_CLOCKEVENTS select GENERIC_CLOCKEVENTS_BROADCAST select MODULES_USE_ELF_RELA diff --git a/arch/hexagon/include/asm/processor.h b/arch/hexagon/include/asm/processor.h index 45a825402f63..d8501137c8d0 100644 --- a/arch/hexagon/include/asm/processor.h +++ b/arch/hexagon/include/asm/processor.h @@ -56,6 +56,7 @@ struct thread_struct { } #define cpu_relax() __vmyield() +#define cpu_relax_lowlatency() cpu_relax() /* * Decides where the kernel will search for a free chunk of vm space during diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h index 0d2bcb37ec35..bee0acd52f7e 100644 --- a/arch/ia64/include/asm/io.h +++ b/arch/ia64/include/asm/io.h @@ -426,6 +426,7 @@ extern void iounmap (volatile void __iomem *addr); extern void __iomem * early_ioremap (unsigned long phys_addr, unsigned long size); #define early_memremap(phys_addr, size) early_ioremap(phys_addr, size) extern void early_iounmap (volatile void __iomem *addr, unsigned long size); +#define early_memunmap(addr, size) early_iounmap(addr, size) static inline void __iomem * ioremap_cache (unsigned long phys_addr, unsigned long size) { return ioremap(phys_addr, size); diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h index efd1b927ccb7..c7367130ab14 100644 --- a/arch/ia64/include/asm/processor.h +++ b/arch/ia64/include/asm/processor.h @@ -548,6 +548,7 @@ ia64_eoi (void) } #define cpu_relax() ia64_hint(ia64_hint_pause) +#define cpu_relax_lowlatency() cpu_relax() static inline int ia64_get_irr(unsigned int vector) diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 55d4ba47a907..deed6fa96bb0 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -662,7 +662,7 @@ void machine_restart (char *restart_cmd) { (void) notify_die(DIE_MACHINE_RESTART, restart_cmd, NULL, 0, 0, 0); - (*efi.reset_system)(EFI_RESET_WARM, 0, 0, NULL); + efi_reboot(REBOOT_WARM, NULL); } void diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index 71c52bc7c28d..3e71ef85e439 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -441,7 +441,7 @@ void update_vsyscall_tz(void) } void update_vsyscall_old(struct timespec *wall, struct timespec *wtm, - struct clocksource *c, u32 mult) + struct clocksource *c, u32 mult, cycle_t cycle_last) { write_seqcount_begin(&fsyscall_gtod_data.seq); @@ -450,7 +450,7 @@ void update_vsyscall_old(struct timespec *wall, struct timespec *wtm, fsyscall_gtod_data.clk_mult = mult; fsyscall_gtod_data.clk_shift = c->shift; fsyscall_gtod_data.clk_fsys_mmio = c->archdata.fsys_mmio; - fsyscall_gtod_data.clk_cycle_last = c->cycle_last; + fsyscall_gtod_data.clk_cycle_last = cycle_last; /* copy kernel time structures */ fsyscall_gtod_data.wall_time.tv_sec = wall->tv_sec; diff --git a/arch/m32r/include/asm/processor.h b/arch/m32r/include/asm/processor.h index 5767367550c6..9f8fd9bef70f 100644 --- a/arch/m32r/include/asm/processor.h +++ b/arch/m32r/include/asm/processor.h @@ -133,5 +133,6 @@ unsigned long get_wchan(struct task_struct *p); #define KSTK_ESP(tsk) ((tsk)->thread.sp) #define cpu_relax() barrier() +#define cpu_relax_lowlatency() cpu_relax() #endif /* _ASM_M32R_PROCESSOR_H */ diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h index b0768a657920..20dda1d4b860 100644 --- a/arch/m68k/include/asm/processor.h +++ b/arch/m68k/include/asm/processor.h @@ -176,5 +176,6 @@ unsigned long get_wchan(struct task_struct *p); #define task_pt_regs(tsk) ((struct pt_regs *) ((tsk)->thread.esp0)) #define cpu_relax() barrier() +#define cpu_relax_lowlatency() cpu_relax() #endif diff --git a/arch/metag/include/asm/processor.h b/arch/metag/include/asm/processor.h index a8a37477c66e..881071c07942 100644 --- a/arch/metag/include/asm/processor.h +++ b/arch/metag/include/asm/processor.h @@ -155,6 +155,7 @@ unsigned long get_wchan(struct task_struct *p); #define user_stack_pointer(regs) ((regs)->ctx.AX[0].U0) #define cpu_relax() barrier() +#define cpu_relax_lowlatency() cpu_relax() extern void setup_priv(void); diff --git a/arch/metag/kernel/perf/perf_event.c b/arch/metag/kernel/perf/perf_event.c index 5cc4d4dcf3cf..02c08737f6aa 100644 --- a/arch/metag/kernel/perf/perf_event.c +++ b/arch/metag/kernel/perf/perf_event.c @@ -568,16 +568,6 @@ static int _hw_perf_event_init(struct perf_event *event) return -EINVAL; /* - * Early cores have "limited" counters - they have no overflow - * interrupts - and so are unable to do sampling without extra work - * and timer assistance. - */ - if (metag_pmu->max_period == 0) { - if (hwc->sample_period) - return -EINVAL; - } - - /* * Don't assign an index until the event is placed into the hardware. * -1 signifies that we're still deciding where to put it. On SMP * systems each core has its own set of counters, so we can't do any @@ -866,6 +856,15 @@ static int __init init_hw_perf_events(void) pr_info("enabled with %s PMU driver, %d counters available\n", metag_pmu->name, metag_pmu->max_events); + /* + * Early cores have "limited" counters - they have no overflow + * interrupts - and so are unable to do sampling without extra work + * and timer assistance. + */ + if (metag_pmu->max_period == 0) { + metag_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; + } + /* Initialise the active events and reservation mutex */ atomic_set(&metag_pmu->active_events, 0); mutex_init(&metag_pmu->reserve_mutex); diff --git a/arch/microblaze/include/asm/processor.h b/arch/microblaze/include/asm/processor.h index 9d31b057c355..497a988d79c2 100644 --- a/arch/microblaze/include/asm/processor.h +++ b/arch/microblaze/include/asm/processor.h @@ -22,6 +22,7 @@ extern const struct seq_operations cpuinfo_op; # define cpu_relax() barrier() +# define cpu_relax_lowlatency() cpu_relax() #define task_pt_regs(tsk) \ (((struct pt_regs *)(THREAD_SIZE + task_stack_page(tsk))) - 1) diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h index ad70cba8daff..d5098bc554f4 100644 --- a/arch/mips/include/asm/processor.h +++ b/arch/mips/include/asm/processor.h @@ -367,6 +367,7 @@ unsigned long get_wchan(struct task_struct *p); #define KSTK_STATUS(tsk) (task_pt_regs(tsk)->cp0_status) #define cpu_relax() barrier() +#define cpu_relax_lowlatency() cpu_relax() /* * Return_address is a replacement for __builtin_return_address(count) diff --git a/arch/mn10300/include/asm/processor.h b/arch/mn10300/include/asm/processor.h index 8b80b19d0c8a..769d5ed8e992 100644 --- a/arch/mn10300/include/asm/processor.h +++ b/arch/mn10300/include/asm/processor.h @@ -68,7 +68,9 @@ extern struct mn10300_cpuinfo cpu_data[]; extern void identify_cpu(struct mn10300_cpuinfo *); extern void print_cpu_info(struct mn10300_cpuinfo *); extern void dodgy_tsc(void); + #define cpu_relax() barrier() +#define cpu_relax_lowlatency() cpu_relax() /* * User space process size: 1.75GB (default). diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig index e71d712afb79..88e83368bbf5 100644 --- a/arch/openrisc/Kconfig +++ b/arch/openrisc/Kconfig @@ -22,6 +22,7 @@ config OPENRISC select GENERIC_STRNLEN_USER select MODULES_USE_ELF_RELA select HAVE_DEBUG_STACKOVERFLOW + select OR1K_PIC config MMU def_bool y diff --git a/arch/openrisc/include/asm/irq.h b/arch/openrisc/include/asm/irq.h index eb612b1865d2..b84634cc95eb 100644 --- a/arch/openrisc/include/asm/irq.h +++ b/arch/openrisc/include/asm/irq.h @@ -24,4 +24,7 @@ #define NO_IRQ (-1) +void handle_IRQ(unsigned int, struct pt_regs *); +extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); + #endif /* __ASM_OPENRISC_IRQ_H__ */ diff --git a/arch/openrisc/include/asm/processor.h b/arch/openrisc/include/asm/processor.h index cab746fa9e87..4d235e3d2534 100644 --- a/arch/openrisc/include/asm/processor.h +++ b/arch/openrisc/include/asm/processor.h @@ -101,6 +101,7 @@ extern unsigned long thread_saved_pc(struct task_struct *t); #define init_stack (init_thread_union.stack) #define cpu_relax() barrier() +#define cpu_relax_lowlatency() cpu_relax() #endif /* __ASSEMBLY__ */ #endif /* __ASM_OPENRISC_PROCESSOR_H */ diff --git a/arch/openrisc/kernel/irq.c b/arch/openrisc/kernel/irq.c index 8ec77bc9f1e7..967eb1430203 100644 --- a/arch/openrisc/kernel/irq.c +++ b/arch/openrisc/kernel/irq.c @@ -16,11 +16,10 @@ #include <linux/interrupt.h> #include <linux/init.h> -#include <linux/of.h> #include <linux/ftrace.h> #include <linux/irq.h> +#include <linux/irqchip.h> #include <linux/export.h> -#include <linux/irqdomain.h> #include <linux/irqflags.h> /* read interrupt enabled status */ @@ -37,150 +36,31 @@ void arch_local_irq_restore(unsigned long flags) } EXPORT_SYMBOL(arch_local_irq_restore); - -/* OR1K PIC implementation */ - -/* We're a couple of cycles faster than the generic implementations with - * these 'fast' versions. - */ - -static void or1k_pic_mask(struct irq_data *data) -{ - mtspr(SPR_PICMR, mfspr(SPR_PICMR) & ~(1UL << data->hwirq)); -} - -static void or1k_pic_unmask(struct irq_data *data) -{ - mtspr(SPR_PICMR, mfspr(SPR_PICMR) | (1UL << data->hwirq)); -} - -static void or1k_pic_ack(struct irq_data *data) -{ - /* EDGE-triggered interrupts need to be ack'ed in order to clear - * the latch. - * LEVEL-triggered interrupts do not need to be ack'ed; however, - * ack'ing the interrupt has no ill-effect and is quicker than - * trying to figure out what type it is... - */ - - /* The OpenRISC 1000 spec says to write a 1 to the bit to ack the - * interrupt, but the OR1200 does this backwards and requires a 0 - * to be written... - */ - -#ifdef CONFIG_OR1K_1200 - /* There are two oddities with the OR1200 PIC implementation: - * i) LEVEL-triggered interrupts are latched and need to be cleared - * ii) the interrupt latch is cleared by writing a 0 to the bit, - * as opposed to a 1 as mandated by the spec - */ - - mtspr(SPR_PICSR, mfspr(SPR_PICSR) & ~(1UL << data->hwirq)); -#else - WARN(1, "Interrupt handling possibly broken\n"); - mtspr(SPR_PICSR, (1UL << data->hwirq)); -#endif -} - -static void or1k_pic_mask_ack(struct irq_data *data) -{ - /* Comments for pic_ack apply here, too */ - -#ifdef CONFIG_OR1K_1200 - mtspr(SPR_PICMR, mfspr(SPR_PICMR) & ~(1UL << data->hwirq)); - mtspr(SPR_PICSR, mfspr(SPR_PICSR) & ~(1UL << data->hwirq)); -#else - WARN(1, "Interrupt handling possibly broken\n"); - mtspr(SPR_PICMR, (1UL << data->hwirq)); - mtspr(SPR_PICSR, (1UL << data->hwirq)); -#endif -} - -#if 0 -static int or1k_pic_set_type(struct irq_data *data, unsigned int flow_type) -{ - /* There's nothing to do in the PIC configuration when changing - * flow type. Level and edge-triggered interrupts are both - * supported, but it's PIC-implementation specific which type - * is handled. */ - - return irq_setup_alt_chip(data, flow_type); -} -#endif - -static struct irq_chip or1k_dev = { - .name = "or1k-PIC", - .irq_unmask = or1k_pic_unmask, - .irq_mask = or1k_pic_mask, - .irq_ack = or1k_pic_ack, - .irq_mask_ack = or1k_pic_mask_ack, -}; - -static struct irq_domain *root_domain; - -static inline int pic_get_irq(int first) -{ - int hwirq; - - hwirq = ffs(mfspr(SPR_PICSR) >> first); - if (!hwirq) - return NO_IRQ; - else - hwirq = hwirq + first -1; - - return irq_find_mapping(root_domain, hwirq); -} - - -static int or1k_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw) +void __init init_IRQ(void) { - irq_set_chip_and_handler_name(irq, &or1k_dev, - handle_level_irq, "level"); - irq_set_status_flags(irq, IRQ_LEVEL | IRQ_NOPROBE); - - return 0; + irqchip_init(); } -static const struct irq_domain_ops or1k_irq_domain_ops = { - .xlate = irq_domain_xlate_onecell, - .map = or1k_map, -}; - -/* - * This sets up the IRQ domain for the PIC built in to the OpenRISC - * 1000 CPU. This is the "root" domain as these are the interrupts - * that directly trigger an exception in the CPU. - */ -static void __init or1k_irq_init(void) -{ - struct device_node *intc = NULL; - - /* The interrupt controller device node is mandatory */ - intc = of_find_compatible_node(NULL, NULL, "opencores,or1k-pic"); - BUG_ON(!intc); - - /* Disable all interrupts until explicitly requested */ - mtspr(SPR_PICMR, (0UL)); - - root_domain = irq_domain_add_linear(intc, 32, - &or1k_irq_domain_ops, NULL); -} +static void (*handle_arch_irq)(struct pt_regs *); -void __init init_IRQ(void) +void __init set_handle_irq(void (*handle_irq)(struct pt_regs *)) { - or1k_irq_init(); + handle_arch_irq = handle_irq; } -void __irq_entry do_IRQ(struct pt_regs *regs) +void handle_IRQ(unsigned int irq, struct pt_regs *regs) { - int irq = -1; struct pt_regs *old_regs = set_irq_regs(regs); irq_enter(); - while ((irq = pic_get_irq(irq + 1)) != NO_IRQ) - generic_handle_irq(irq); + generic_handle_irq(irq); irq_exit(); set_irq_regs(old_regs); } + +void __irq_entry do_IRQ(struct pt_regs *regs) +{ + handle_arch_irq(regs); +} diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h index d951c9681ab3..689a8ade3606 100644 --- a/arch/parisc/include/asm/processor.h +++ b/arch/parisc/include/asm/processor.h @@ -338,6 +338,7 @@ extern unsigned long get_wchan(struct task_struct *p); #define KSTK_ESP(tsk) ((tsk)->thread.regs.gr[30]) #define cpu_relax() barrier() +#define cpu_relax_lowlatency() cpu_relax() /* Used as a macro to identify the combined VIPT/PIPT cached * CPUs which require a guarantee of coherency (no inequivalent diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 6d59072e13a7..dda7ac4c80bd 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -400,6 +400,8 @@ static inline unsigned long __pack_fe01(unsigned int fpmode) #define cpu_relax() barrier() #endif +#define cpu_relax_lowlatency() cpu_relax() + /* Check that a certain kernel stack pointer is valid in task_struct p */ int validate_sp(unsigned long sp, struct task_struct *p, unsigned long nbytes); diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 9fff9cdcc519..368ab374d33c 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -741,7 +741,7 @@ static cycle_t timebase_read(struct clocksource *cs) } void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm, - struct clocksource *clock, u32 mult) + struct clocksource *clock, u32 mult, cycle_t cycle_last) { u64 new_tb_to_xs, new_stamp_xsec; u32 frac_sec; @@ -774,7 +774,7 @@ void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm, * We expect the caller to have done the first increment of * vdso_data->tb_update_count already. */ - vdso_data->tb_orig_stamp = clock->cycle_last; + vdso_data->tb_orig_stamp = cycle_last; vdso_data->stamp_xsec = new_stamp_xsec; vdso_data->tb_to_xs = new_tb_to_xs; vdso_data->wtom_clock_sec = wtm->tv_sec; diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index e0766b82e165..66d0f179650f 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -387,8 +387,7 @@ static int h_24x7_event_init(struct perf_event *event) event->attr.exclude_hv || event->attr.exclude_idle || event->attr.exclude_host || - event->attr.exclude_guest || - is_sampling_event(event)) /* no sampling */ + event->attr.exclude_guest) return -EINVAL; /* no branch sampling */ @@ -513,6 +512,9 @@ static int hv_24x7_init(void) if (!hv_page_cache) return -ENOMEM; + /* sampling not supported */ + h_24x7_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; + r = perf_pmu_register(&h_24x7_pmu, h_24x7_pmu.name, -1); if (r) return r; diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c index c9d399a2df82..15fc76c93022 100644 --- a/arch/powerpc/perf/hv-gpci.c +++ b/arch/powerpc/perf/hv-gpci.c @@ -210,8 +210,7 @@ static int h_gpci_event_init(struct perf_event *event) event->attr.exclude_hv || event->attr.exclude_idle || event->attr.exclude_host || - event->attr.exclude_guest || - is_sampling_event(event)) /* no sampling */ + event->attr.exclude_guest) return -EINVAL; /* no branch sampling */ @@ -284,6 +283,9 @@ static int hv_gpci_init(void) return -ENODEV; } + /* sampling not supported */ + h_gpci_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; + r = perf_pmu_register(&h_gpci_pmu, h_gpci_pmu.name, -1); if (r) return r; diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c index f85db3a69b4a..2930d1e81a05 100644 --- a/arch/powerpc/platforms/cell/spu_base.c +++ b/arch/powerpc/platforms/cell/spu_base.c @@ -611,7 +611,6 @@ static int __init create_spu(void *data) int ret; static int number; unsigned long flags; - struct timespec ts; ret = -ENOMEM; spu = kzalloc(sizeof (*spu), GFP_KERNEL); @@ -652,8 +651,7 @@ static int __init create_spu(void *data) mutex_unlock(&spu_full_list_mutex); spu->stats.util_state = SPU_UTIL_IDLE_LOADED; - ktime_get_ts(&ts); - spu->stats.tstamp = timespec_to_ns(&ts); + spu->stats.tstamp = ktime_get_ns(); INIT_LIST_HEAD(&spu->aff_list); @@ -676,7 +674,6 @@ static const char *spu_state_names[] = { static unsigned long long spu_acct_time(struct spu *spu, enum spu_utilization_state state) { - struct timespec ts; unsigned long long time = spu->stats.times[state]; /* @@ -684,10 +681,8 @@ static unsigned long long spu_acct_time(struct spu *spu, * statistics are not updated. Apply the time delta from the * last recorded state of the spu. */ - if (spu->stats.util_state == state) { - ktime_get_ts(&ts); - time += timespec_to_ns(&ts) - spu->stats.tstamp; - } + if (spu->stats.util_state == state) + time += ktime_get_ns() - spu->stats.tstamp; return time / NSEC_PER_MSEC; } diff --git a/arch/powerpc/platforms/cell/spufs/context.c b/arch/powerpc/platforms/cell/spufs/context.c index 9c6790d17eda..3b4152faeb1f 100644 --- a/arch/powerpc/platforms/cell/spufs/context.c +++ b/arch/powerpc/platforms/cell/spufs/context.c @@ -36,7 +36,6 @@ atomic_t nr_spu_contexts = ATOMIC_INIT(0); struct spu_context *alloc_spu_context(struct spu_gang *gang) { struct spu_context *ctx; - struct timespec ts; ctx = kzalloc(sizeof *ctx, GFP_KERNEL); if (!ctx) @@ -67,8 +66,7 @@ struct spu_context *alloc_spu_context(struct spu_gang *gang) __spu_update_sched_info(ctx); spu_set_timeslice(ctx); ctx->stats.util_state = SPU_UTIL_IDLE_LOADED; - ktime_get_ts(&ts); - ctx->stats.tstamp = timespec_to_ns(&ts); + ctx->stats.tstamp = ktime_get_ns(); atomic_inc(&nr_spu_contexts); goto out; diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 90986923a53a..d966bbe58b8f 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -2338,7 +2338,6 @@ static const char *ctx_state_names[] = { static unsigned long long spufs_acct_time(struct spu_context *ctx, enum spu_utilization_state state) { - struct timespec ts; unsigned long long time = ctx->stats.times[state]; /* @@ -2351,8 +2350,7 @@ static unsigned long long spufs_acct_time(struct spu_context *ctx, * of the spu context. */ if (ctx->spu && ctx->stats.util_state == state) { - ktime_get_ts(&ts); - time += timespec_to_ns(&ts) - ctx->stats.tstamp; + time += ktime_get_ns() - ctx->stats.tstamp; } return time / NSEC_PER_MSEC; diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c index 4a0a64fe25df..998f632e7cce 100644 --- a/arch/powerpc/platforms/cell/spufs/sched.c +++ b/arch/powerpc/platforms/cell/spufs/sched.c @@ -1039,13 +1039,11 @@ void spuctx_switch_state(struct spu_context *ctx, { unsigned long long curtime; signed long long delta; - struct timespec ts; struct spu *spu; enum spu_utilization_state old_state; int node; - ktime_get_ts(&ts); - curtime = timespec_to_ns(&ts); + curtime = ktime_get_ns(); delta = curtime - ctx->stats.tstamp; WARN_ON(!mutex_is_locked(&ctx->state_mutex)); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index bb63499fc5d3..1afc7a686702 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -137,7 +137,6 @@ config S390 select HAVE_SYSCALL_TRACEPOINTS select HAVE_UID16 if 32BIT select HAVE_VIRT_CPU_ACCOUNTING - select KTIME_SCALAR if 32BIT select MODULES_USE_ELF_RELA select NO_BOOTMEM select OLD_SIGACTION diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 6f02d452bbee..e568fc8a7250 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -217,7 +217,7 @@ static inline void cpu_relax(void) barrier(); } -#define arch_mutex_cpu_relax() barrier() +#define cpu_relax_lowlatency() barrier() static inline void psw_set_key(unsigned int key) { diff --git a/arch/s390/include/uapi/asm/Kbuild b/arch/s390/include/uapi/asm/Kbuild index 736637363d31..08fe6dad9026 100644 --- a/arch/s390/include/uapi/asm/Kbuild +++ b/arch/s390/include/uapi/asm/Kbuild @@ -16,6 +16,7 @@ header-y += ioctls.h header-y += ipcbuf.h header-y += kvm.h header-y += kvm_para.h +header-y += kvm_perf.h header-y += kvm_virtio.h header-y += mman.h header-y += monwriter.h diff --git a/arch/s390/include/uapi/asm/kvm_perf.h b/arch/s390/include/uapi/asm/kvm_perf.h new file mode 100644 index 000000000000..397282727e21 --- /dev/null +++ b/arch/s390/include/uapi/asm/kvm_perf.h @@ -0,0 +1,25 @@ +/* + * Definitions for perf-kvm on s390 + * + * Copyright 2014 IBM Corp. + * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.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 only) + * as published by the Free Software Foundation. + */ + +#ifndef __LINUX_KVM_PERF_S390_H +#define __LINUX_KVM_PERF_S390_H + +#include <asm/sie.h> + +#define DECODE_STR_LEN 40 + +#define VCPU_ID "id" + +#define KVM_ENTRY_TRACE "kvm:kvm_s390_sie_enter" +#define KVM_EXIT_TRACE "kvm:kvm_s390_sie_exit" +#define KVM_EXIT_REASON "icptcode" + +#endif diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index ea75d011a6fc..d3194de7ae1e 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -411,12 +411,6 @@ static int cpumf_pmu_event_init(struct perf_event *event) case PERF_TYPE_HARDWARE: case PERF_TYPE_HW_CACHE: case PERF_TYPE_RAW: - /* The CPU measurement counter facility does not have overflow - * interrupts to do sampling. Sampling must be provided by - * external means, for example, by timers. - */ - if (is_sampling_event(event)) - return -ENOENT; err = __hw_perf_event_init(event); break; default: @@ -681,6 +675,12 @@ static int __init cpumf_pmu_init(void) goto out; } + /* The CPU measurement counter facility does not have overflow + * interrupts to do sampling. Sampling must be provided by + * external means, for example, by timers. + */ + cpumf_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; + cpumf_pmu.attr_groups = cpumf_cf_event_group(); rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW); if (rc) { diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 0931b110c826..4cef607f3711 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -214,26 +214,26 @@ void update_vsyscall(struct timekeeper *tk) { u64 nsecps; - if (tk->clock != &clocksource_tod) + if (tk->tkr.clock != &clocksource_tod) return; /* Make userspace gettimeofday spin until we're done. */ ++vdso_data->tb_update_count; smp_wmb(); - vdso_data->xtime_tod_stamp = tk->clock->cycle_last; + vdso_data->xtime_tod_stamp = tk->tkr.cycle_last; vdso_data->xtime_clock_sec = tk->xtime_sec; - vdso_data->xtime_clock_nsec = tk->xtime_nsec; + vdso_data->xtime_clock_nsec = tk->tkr.xtime_nsec; vdso_data->wtom_clock_sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; - vdso_data->wtom_clock_nsec = tk->xtime_nsec + - + ((u64) tk->wall_to_monotonic.tv_nsec << tk->shift); - nsecps = (u64) NSEC_PER_SEC << tk->shift; + vdso_data->wtom_clock_nsec = tk->tkr.xtime_nsec + + + ((u64) tk->wall_to_monotonic.tv_nsec << tk->tkr.shift); + nsecps = (u64) NSEC_PER_SEC << tk->tkr.shift; while (vdso_data->wtom_clock_nsec >= nsecps) { vdso_data->wtom_clock_nsec -= nsecps; vdso_data->wtom_clock_sec++; } - vdso_data->tk_mult = tk->mult; - vdso_data->tk_shift = tk->shift; + vdso_data->tk_mult = tk->tkr.mult; + vdso_data->tk_shift = tk->tkr.shift; smp_wmb(); ++vdso_data->tb_update_count; } diff --git a/arch/score/include/asm/processor.h b/arch/score/include/asm/processor.h index d9a922d8711b..851f441991d2 100644 --- a/arch/score/include/asm/processor.h +++ b/arch/score/include/asm/processor.h @@ -24,6 +24,7 @@ extern unsigned long get_wchan(struct task_struct *p); #define current_text_addr() ({ __label__ _l; _l: &&_l; }) #define cpu_relax() barrier() +#define cpu_relax_lowlatency() cpu_relax() #define release_thread(thread) do {} while (0) /* diff --git a/arch/sh/include/asm/processor.h b/arch/sh/include/asm/processor.h index 5448f9bbf4ab..1506897648aa 100644 --- a/arch/sh/include/asm/processor.h +++ b/arch/sh/include/asm/processor.h @@ -97,6 +97,7 @@ extern struct sh_cpuinfo cpu_data[]; #define cpu_sleep() __asm__ __volatile__ ("sleep" : : : "memory") #define cpu_relax() barrier() +#define cpu_relax_lowlatency() cpu_relax() void default_idle(void); void stop_this_cpu(void *); diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c index 02331672b6db..7cfd7f153966 100644 --- a/arch/sh/kernel/perf_event.c +++ b/arch/sh/kernel/perf_event.c @@ -129,14 +129,6 @@ static int __hw_perf_event_init(struct perf_event *event) return -ENODEV; /* - * All of the on-chip counters are "limited", in that they have - * no interrupts, and are therefore unable to do sampling without - * further work and timer assistance. - */ - if (hwc->sample_period) - return -EINVAL; - - /* * See if we need to reserve the counter. * * If no events are currently in use, then we have to take a @@ -392,6 +384,13 @@ int register_sh_pmu(struct sh_pmu *_pmu) pr_info("Performance Events: %s support registered\n", _pmu->name); + /* + * All of the on-chip counters are "limited", in that they have + * no interrupts, and are therefore unable to do sampling without + * further work and timer assistance. + */ + pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; + WARN_ON(_pmu->num_events > MAX_HWEVENTS); perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW); diff --git a/arch/sparc/include/asm/processor_32.h b/arch/sparc/include/asm/processor_32.h index a564817bbc2e..812fd08f3e62 100644 --- a/arch/sparc/include/asm/processor_32.h +++ b/arch/sparc/include/asm/processor_32.h @@ -119,6 +119,8 @@ extern struct task_struct *last_task_used_math; int do_mathemu(struct pt_regs *regs, struct task_struct *fpt); #define cpu_relax() barrier() +#define cpu_relax_lowlatency() cpu_relax() + extern void (*sparc_idle)(void); #endif diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h index 7028fe1a7c04..6924bdefe148 100644 --- a/arch/sparc/include/asm/processor_64.h +++ b/arch/sparc/include/asm/processor_64.h @@ -216,6 +216,7 @@ unsigned long get_wchan(struct task_struct *task); "nop\n\t" \ ".previous" \ ::: "memory") +#define cpu_relax_lowlatency() cpu_relax() /* Prefetch support. This is tuned for UltraSPARC-III and later. * UltraSPARC-I will treat these as nops, and UltraSPARC-II has diff --git a/arch/tile/include/asm/processor.h b/arch/tile/include/asm/processor.h index 42323636c459..dd4f9f17e30a 100644 --- a/arch/tile/include/asm/processor.h +++ b/arch/tile/include/asm/processor.h @@ -266,6 +266,8 @@ static inline void cpu_relax(void) barrier(); } +#define cpu_relax_lowlatency() cpu_relax() + /* Info on this processor (see fs/proc/cpuinfo.c) */ struct seq_operations; extern const struct seq_operations cpuinfo_op; diff --git a/arch/tile/kernel/time.c b/arch/tile/kernel/time.c index 462dcd0c1700..d8fbc289e680 100644 --- a/arch/tile/kernel/time.c +++ b/arch/tile/kernel/time.c @@ -260,9 +260,8 @@ void update_vsyscall_tz(void) void update_vsyscall(struct timekeeper *tk) { - struct timespec wall_time = tk_xtime(tk); struct timespec *wtm = &tk->wall_to_monotonic; - struct clocksource *clock = tk->clock; + struct clocksource *clock = tk->tkr.clock; if (clock != &cycle_counter_cs) return; @@ -270,13 +269,13 @@ void update_vsyscall(struct timekeeper *tk) /* Userspace gettimeofday will spin while this value is odd. */ ++vdso_data->tb_update_count; smp_wmb(); - vdso_data->xtime_tod_stamp = clock->cycle_last; - vdso_data->xtime_clock_sec = wall_time.tv_sec; - vdso_data->xtime_clock_nsec = wall_time.tv_nsec; + vdso_data->xtime_tod_stamp = tk->tkr.cycle_last; + vdso_data->xtime_clock_sec = tk->xtime_sec; + vdso_data->xtime_clock_nsec = tk->tkr.xtime_nsec; vdso_data->wtom_clock_sec = wtm->tv_sec; vdso_data->wtom_clock_nsec = wtm->tv_nsec; - vdso_data->mult = clock->mult; - vdso_data->shift = clock->shift; + vdso_data->mult = tk->tkr.mult; + vdso_data->shift = tk->tkr.shift; smp_wmb(); ++vdso_data->tb_update_count; } diff --git a/arch/tile/kernel/vdso/vgettimeofday.c b/arch/tile/kernel/vdso/vgettimeofday.c index 51ec8e46f5f9..e933fb9fbf5c 100644 --- a/arch/tile/kernel/vdso/vgettimeofday.c +++ b/arch/tile/kernel/vdso/vgettimeofday.c @@ -83,10 +83,11 @@ int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) if (count & 1) continue; - cycles = (get_cycles() - vdso_data->xtime_tod_stamp); - ns = (cycles * vdso_data->mult) >> vdso_data->shift; sec = vdso_data->xtime_clock_sec; - ns += vdso_data->xtime_clock_nsec; + cycles = get_cycles() - vdso_data->xtime_tod_stamp; + ns = (cycles * vdso_data->mult) + vdso_data->xtime_clock_nsec; + ns >>= vdso_data->shift; + if (ns >= NSEC_PER_SEC) { ns -= NSEC_PER_SEC; sec += 1; diff --git a/arch/unicore32/include/asm/processor.h b/arch/unicore32/include/asm/processor.h index 4eaa42167667..8d21b7adf26b 100644 --- a/arch/unicore32/include/asm/processor.h +++ b/arch/unicore32/include/asm/processor.h @@ -71,6 +71,7 @@ extern void release_thread(struct task_struct *); unsigned long get_wchan(struct task_struct *p); #define cpu_relax() barrier() +#define cpu_relax_lowlatency() cpu_relax() #define task_pt_regs(p) \ ((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ac5a788d2432..727d1adf6f03 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -110,9 +110,9 @@ config X86 select CLOCKSOURCE_WATCHDOG select GENERIC_CLOCKEVENTS select ARCH_CLOCKSOURCE_DATA + select CLOCKSOURCE_VALIDATE_LAST_CYCLE select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC) select GENERIC_TIME_VSYSCALL - select KTIME_SCALAR if X86_32 select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER select HAVE_CONTEXT_TRACKING if X86_64 @@ -134,6 +134,8 @@ config X86 select HAVE_ARCH_AUDITSYSCALL select ARCH_SUPPORTS_ATOMIC_RMW select ACPI_LEGACY_TABLES_LOOKUP if ACPI + select HAVE_ACPI_APEI if ACPI + select HAVE_ACPI_APEI_NMI if ACPI config INSTRUCTION_DECODER def_bool y @@ -432,6 +434,7 @@ config X86_INTEL_CE bool "CE4100 TV platform" depends on PCI depends on PCI_GODIRECT + depends on X86_IO_APIC depends on X86_32 depends on X86_EXTENDED_PLATFORM select X86_REBOOTFIXUPS @@ -838,6 +841,7 @@ config X86_IO_APIC def_bool y depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC || PCI_MSI select GENERIC_IRQ_LEGACY_ALLOC_HWIRQ + select IRQ_DOMAIN config X86_REROUTE_FOR_BROKEN_BOOT_IRQS bool "Reroute for broken boot IRQs" @@ -1525,6 +1529,7 @@ config EFI bool "EFI runtime service support" depends on ACPI select UCS2_STRING + select EFI_RUNTIME_WRAPPERS ---help--- This enables the kernel to use EFI runtime services that are available (such as the EFI variable services). @@ -2406,6 +2411,10 @@ config IOSF_MBI default m depends on PCI +config PMC_ATOM + def_bool y + depends on PCI + source "net/Kconfig" source "drivers/Kconfig" diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 33f71b01fd22..c65fd9650467 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -15,12 +15,9 @@ endif # that way we can complain to the user if the CPU is insufficient. # # The -m16 option is supported by GCC >= 4.9 and clang >= 3.5. For -# older versions of GCC, we need to play evil and unreliable tricks to -# attempt to ensure that our asm(".code16gcc") is first in the asm -# output. -CODE16GCC_CFLAGS := -m32 -include $(srctree)/arch/x86/boot/code16gcc.h \ - $(call cc-option, -fno-toplevel-reorder,\ - $(call cc-option, -fno-unit-at-a-time)) +# older versions of GCC, include an *assembly* header to make sure that +# gcc doesn't play any games behind our back. +CODE16GCC_CFLAGS := -m32 -Wa,$(srctree)/arch/x86/boot/code16gcc.h M16_CFLAGS := $(call cc-option, -m16, $(CODE16GCC_CFLAGS)) REALMODE_CFLAGS := $(M16_CFLAGS) -g -Os -D__KERNEL__ \ diff --git a/arch/x86/boot/code16gcc.h b/arch/x86/boot/code16gcc.h index d93e48010b61..5ff426535397 100644 --- a/arch/x86/boot/code16gcc.h +++ b/arch/x86/boot/code16gcc.h @@ -1,15 +1,11 @@ -/* - * code16gcc.h - * - * This file is -include'd when compiling 16-bit C code. - * Note: this asm() needs to be emitted before gcc emits any code. - * Depending on gcc version, this requires -fno-unit-at-a-time or - * -fno-toplevel-reorder. - * - * Hopefully gcc will eventually have a real -m16 option so we can - * drop this hack long term. - */ +# +# code16gcc.h +# +# This file is added to the assembler via -Wa when compiling 16-bit C code. +# This is done this way instead via asm() to make sure gcc does not reorder +# things around us. +# +# gcc 4.9+ has a real -m16 option so we can drop this hack long term. +# -#ifndef __ASSEMBLY__ -asm(".code16gcc"); -#endif + .code16gcc diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 0fcd9133790c..7a801a310e37 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -33,7 +33,8 @@ VMLINUX_OBJS = $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \ $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone ifeq ($(CONFIG_EFI_STUB), y) - VMLINUX_OBJS += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o + VMLINUX_OBJS += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o \ + $(objtree)/drivers/firmware/efi/libstub/lib.a endif $(obj)/vmlinux: $(VMLINUX_OBJS) FORCE diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 0331d765c2bb..f277184e2ac1 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -19,10 +19,7 @@ static efi_system_table_t *sys_table; -static struct efi_config *efi_early; - -#define efi_call_early(f, ...) \ - efi_early->call(efi_early->f, __VA_ARGS__); +struct efi_config *efi_early; #define BOOT_SERVICES(bits) \ static void setup_boot_services##bits(struct efi_config *c) \ @@ -48,8 +45,7 @@ static void setup_boot_services##bits(struct efi_config *c) \ BOOT_SERVICES(32); BOOT_SERVICES(64); -static void efi_printk(efi_system_table_t *, char *); -static void efi_char16_printk(efi_system_table_t *, efi_char16_t *); +void efi_char16_printk(efi_system_table_t *, efi_char16_t *); static efi_status_t __file_size32(void *__fh, efi_char16_t *filename_16, @@ -156,7 +152,7 @@ grow: return status; } -static efi_status_t +efi_status_t efi_file_size(efi_system_table_t *sys_table, void *__fh, efi_char16_t *filename_16, void **handle, u64 *file_sz) { @@ -166,7 +162,7 @@ efi_file_size(efi_system_table_t *sys_table, void *__fh, return __file_size32(__fh, filename_16, handle, file_sz); } -static inline efi_status_t +efi_status_t efi_file_read(void *handle, unsigned long *size, void *addr) { unsigned long func; @@ -184,7 +180,7 @@ efi_file_read(void *handle, unsigned long *size, void *addr) } } -static inline efi_status_t efi_file_close(void *handle) +efi_status_t efi_file_close(void *handle) { if (efi_early->is64) { efi_file_handle_64_t *fh = handle; @@ -249,7 +245,7 @@ static inline efi_status_t __open_volume64(void *__image, void **__fh) return status; } -static inline efi_status_t +efi_status_t efi_open_volume(efi_system_table_t *sys_table, void *__image, void **__fh) { if (efi_early->is64) @@ -258,7 +254,7 @@ efi_open_volume(efi_system_table_t *sys_table, void *__image, void **__fh) return __open_volume32(__image, __fh); } -static void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str) +void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str) { unsigned long output_string; size_t offset; @@ -284,8 +280,6 @@ static void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str) } } -#include "../../../../drivers/firmware/efi/efi-stub-helper.c" - static void find_bits(unsigned long mask, u8 *pos, u8 *size) { u8 first, len; @@ -1038,6 +1032,7 @@ struct boot_params *make_boot_params(struct efi_config *c) int i; unsigned long ramdisk_addr; unsigned long ramdisk_size; + unsigned long initrd_addr_max; efi_early = c; sys_table = (efi_system_table_t *)(unsigned long)efi_early->table; @@ -1100,14 +1095,21 @@ struct boot_params *make_boot_params(struct efi_config *c) memset(sdt, 0, sizeof(*sdt)); + if (hdr->xloadflags & XLF_CAN_BE_LOADED_ABOVE_4G) + initrd_addr_max = -1UL; + else + initrd_addr_max = hdr->initrd_addr_max; + status = handle_cmdline_files(sys_table, image, (char *)(unsigned long)hdr->cmd_line_ptr, - "initrd=", hdr->initrd_addr_max, + "initrd=", initrd_addr_max, &ramdisk_addr, &ramdisk_size); if (status != EFI_SUCCESS) goto fail2; - hdr->ramdisk_image = ramdisk_addr; - hdr->ramdisk_size = ramdisk_size; + hdr->ramdisk_image = ramdisk_addr & 0xffffffff; + hdr->ramdisk_size = ramdisk_size & 0xffffffff; + boot_params->ext_ramdisk_image = (u64)ramdisk_addr >> 32; + boot_params->ext_ramdisk_size = (u64)ramdisk_size >> 32; return boot_params; fail2: @@ -1374,7 +1376,10 @@ struct boot_params *efi_main(struct efi_config *c, setup_graphics(boot_params); - setup_efi_pci(boot_params); + status = setup_efi_pci(boot_params); + if (status != EFI_SUCCESS) { + efi_printk(sys_table, "setup_efi_pci() failed!\n"); + } status = efi_call_early(allocate_pool, EFI_LOADER_DATA, sizeof(*gdt), (void **)&gdt); @@ -1401,16 +1406,20 @@ struct boot_params *efi_main(struct efi_config *c, hdr->init_size, hdr->init_size, hdr->pref_address, hdr->kernel_alignment); - if (status != EFI_SUCCESS) + if (status != EFI_SUCCESS) { + efi_printk(sys_table, "efi_relocate_kernel() failed!\n"); goto fail; + } hdr->pref_address = hdr->code32_start; hdr->code32_start = bzimage_addr; } status = exit_boot(boot_params, handle, is64); - if (status != EFI_SUCCESS) + if (status != EFI_SUCCESS) { + efi_printk(sys_table, "exit_boot() failed!\n"); goto fail; + } memset((char *)gdt->address, 0x0, gdt->size); desc = (struct desc_struct *)gdt->address; @@ -1470,5 +1479,6 @@ struct boot_params *efi_main(struct efi_config *c, return boot_params; fail: + efi_printk(sys_table, "efi_main() failed!\n"); return NULL; } diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h index c88c31ecad12..d487e727f1ec 100644 --- a/arch/x86/boot/compressed/eboot.h +++ b/arch/x86/boot/compressed/eboot.h @@ -103,20 +103,4 @@ struct efi_uga_draw_protocol { void *blt; }; -struct efi_config { - u64 image_handle; - u64 table; - u64 allocate_pool; - u64 allocate_pages; - u64 get_memory_map; - u64 free_pool; - u64 free_pages; - u64 locate_handle; - u64 handle_protocol; - u64 exit_boot_services; - u64 text_output; - efi_status_t (*call)(unsigned long, ...); - bool is64; -} __packed; - #endif /* BOOT_COMPRESSED_EBOOT_H */ diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 7a6d43a554d7..16ef02596db2 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -154,7 +154,7 @@ extra_header_fields: #else .quad 0 # ImageBase #endif - .long 0x20 # SectionAlignment + .long CONFIG_PHYSICAL_ALIGN # SectionAlignment .long 0x20 # FileAlignment .word 0 # MajorOperatingSystemVersion .word 0 # MinorOperatingSystemVersion diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 0a3f9c9f98d5..473bdbee378a 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -161,6 +161,20 @@ static inline int alternatives_text_reserved(void *start, void *end) asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) \ : : "i" (0), ## input) +/* + * This is similar to alternative_input. But it has two features and + * respective instructions. + * + * If CPU has feature2, newinstr2 is used. + * Otherwise, if CPU has feature1, newinstr1 is used. + * Otherwise, oldinstr is used. + */ +#define alternative_input_2(oldinstr, newinstr1, feature1, newinstr2, \ + feature2, input...) \ + asm volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, \ + newinstr2, feature2) \ + : : "i" (0), ## input) + /* Like alternative_input, but with a single output argument */ #define alternative_io(oldinstr, newinstr, feature, output, input...) \ asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) \ diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 19b0ebafcd3e..465b309af254 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -85,21 +85,13 @@ static inline bool apic_from_smp_config(void) #include <asm/paravirt.h> #endif -#ifdef CONFIG_X86_64 -extern int is_vsmp_box(void); -#else -static inline int is_vsmp_box(void) -{ - return 0; -} -#endif extern int setup_profiling_timer(unsigned int); static inline void native_apic_mem_write(u32 reg, u32 v) { volatile u32 *addr = (volatile u32 *)(APIC_BASE + reg); - alternative_io("movl %0, %1", "xchgl %0, %1", X86_FEATURE_11AP, + alternative_io("movl %0, %1", "xchgl %0, %1", X86_BUG_11AP, ASM_OUTPUT2("=r" (v), "=m" (*addr)), ASM_OUTPUT2("0" (v), "m" (*addr))); } @@ -300,7 +292,6 @@ struct apic { int dest_logical; unsigned long (*check_apicid_used)(physid_mask_t *map, int apicid); - unsigned long (*check_apicid_present)(int apicid); void (*vector_allocation_domain)(int cpu, struct cpumask *retmask, const struct cpumask *mask); @@ -309,21 +300,11 @@ struct apic { void (*ioapic_phys_id_map)(physid_mask_t *phys_map, physid_mask_t *retmap); void (*setup_apic_routing)(void); - int (*multi_timer_check)(int apic, int irq); int (*cpu_present_to_apicid)(int mps_cpu); void (*apicid_to_cpu_present)(int phys_apicid, physid_mask_t *retmap); - void (*setup_portio_remap)(void); int (*check_phys_apicid_present)(int phys_apicid); - void (*enable_apic_mode)(void); int (*phys_pkg_id)(int cpuid_apic, int index_msb); - /* - * When one of the next two hooks returns 1 the apic - * is switched to this. Essentially they are additional - * probe functions: - */ - int (*mps_oem_check)(struct mpc_table *mpc, char *oem, char *productid); - unsigned int (*get_apic_id)(unsigned long x); unsigned long (*set_apic_id)(unsigned int id); unsigned long apic_id_mask; @@ -343,11 +324,7 @@ struct apic { /* wakeup_secondary_cpu */ int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip); - int trampoline_phys_low; - int trampoline_phys_high; - bool wait_for_init_deassert; - void (*smp_callin_clear_local_apic)(void); void (*inquire_remote_apic)(int apicid); /* apic ops */ @@ -378,14 +355,6 @@ struct apic { * won't be applied properly during early boot in this case. */ int (*x86_32_early_logical_apicid)(int cpu); - - /* - * Optional method called from setup_local_APIC() after logical - * apicid is guaranteed to be known to initialize apicid -> node - * mapping if NUMA initialization hasn't done so already. Don't - * add new users. - */ - int (*x86_32_numa_cpu_node)(int cpu); #endif }; @@ -496,14 +465,12 @@ static inline unsigned default_get_apic_id(unsigned long x) } /* - * Warm reset vector default position: + * Warm reset vector position: */ -#define DEFAULT_TRAMPOLINE_PHYS_LOW 0x467 -#define DEFAULT_TRAMPOLINE_PHYS_HIGH 0x469 +#define TRAMPOLINE_PHYS_LOW 0x467 +#define TRAMPOLINE_PHYS_HIGH 0x469 #ifdef CONFIG_X86_64 -extern int default_acpi_madt_oem_check(char *, char *); - extern void apic_send_IPI_self(int vector); DECLARE_PER_CPU(int, x2apic_extra_bits); @@ -552,6 +519,8 @@ static inline int default_apic_id_valid(int apicid) return (apicid < 255); } +extern int default_acpi_madt_oem_check(char *, char *); + extern void default_setup_apic_routing(void); extern struct apic apic_noop; @@ -635,11 +604,6 @@ static inline unsigned long default_check_apicid_used(physid_mask_t *map, int ap return physid_isset(apicid, *map); } -static inline unsigned long default_check_apicid_present(int bit) -{ - return physid_isset(bit, phys_cpu_present_map); -} - static inline void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap) { *retmap = *phys_map; diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 5c7198cca5ed..0f4460b5636d 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -99,7 +99,7 @@ #if defined(CONFIG_X86_PPRO_FENCE) /* - * For either of these options x86 doesn't have a strong TSO memory + * For this option x86 doesn't have a strong TSO memory * model and we should fall back to full barriers. */ diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index d47786acb016..99c105d78b7e 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -4,6 +4,8 @@ #include <linux/compiler.h> #include <asm/alternative.h> /* Provides LOCK_PREFIX */ +#define __HAVE_ARCH_CMPXCHG 1 + /* * Non-existant functions to indicate usage errors at link time * (or compile-time if the compiler implements __compiletime_error(). @@ -143,7 +145,6 @@ extern void __add_wrong_size(void) # include <asm/cmpxchg_64.h> #endif -#ifdef __HAVE_ARCH_CMPXCHG #define cmpxchg(ptr, old, new) \ __cmpxchg(ptr, old, new, sizeof(*(ptr))) @@ -152,7 +153,6 @@ extern void __add_wrong_size(void) #define cmpxchg_local(ptr, old, new) \ __cmpxchg_local(ptr, old, new, sizeof(*(ptr))) -#endif /* * xadd() adds "inc" to "*ptr" and atomically returns the previous diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h index f8bf2eecab86..f7e142926481 100644 --- a/arch/x86/include/asm/cmpxchg_32.h +++ b/arch/x86/include/asm/cmpxchg_32.h @@ -34,8 +34,6 @@ static inline void set_64bit(volatile u64 *ptr, u64 value) : "memory"); } -#define __HAVE_ARCH_CMPXCHG 1 - #ifdef CONFIG_X86_CMPXCHG64 #define cmpxchg64(ptr, o, n) \ ((__typeof__(*(ptr)))__cmpxchg64((ptr), (unsigned long long)(o), \ diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index 614be87f1a9b..1af94697aae5 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -6,8 +6,6 @@ static inline void set_64bit(volatile u64 *ptr, u64 val) *ptr = val; } -#define __HAVE_ARCH_CMPXCHG 1 - #define cmpxchg64(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index e265ff95d16d..bb9b258d60e7 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -8,7 +8,7 @@ #include <asm/required-features.h> #endif -#define NCAPINTS 10 /* N 32-bit words worth of info */ +#define NCAPINTS 11 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* @@ -18,213 +18,218 @@ */ /* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */ -#define X86_FEATURE_FPU (0*32+ 0) /* Onboard FPU */ -#define X86_FEATURE_VME (0*32+ 1) /* Virtual Mode Extensions */ -#define X86_FEATURE_DE (0*32+ 2) /* Debugging Extensions */ -#define X86_FEATURE_PSE (0*32+ 3) /* Page Size Extensions */ -#define X86_FEATURE_TSC (0*32+ 4) /* Time Stamp Counter */ -#define X86_FEATURE_MSR (0*32+ 5) /* Model-Specific Registers */ -#define X86_FEATURE_PAE (0*32+ 6) /* Physical Address Extensions */ -#define X86_FEATURE_MCE (0*32+ 7) /* Machine Check Exception */ -#define X86_FEATURE_CX8 (0*32+ 8) /* CMPXCHG8 instruction */ -#define X86_FEATURE_APIC (0*32+ 9) /* Onboard APIC */ -#define X86_FEATURE_SEP (0*32+11) /* SYSENTER/SYSEXIT */ -#define X86_FEATURE_MTRR (0*32+12) /* Memory Type Range Registers */ -#define X86_FEATURE_PGE (0*32+13) /* Page Global Enable */ -#define X86_FEATURE_MCA (0*32+14) /* Machine Check Architecture */ -#define X86_FEATURE_CMOV (0*32+15) /* CMOV instructions */ +#define X86_FEATURE_FPU ( 0*32+ 0) /* Onboard FPU */ +#define X86_FEATURE_VME ( 0*32+ 1) /* Virtual Mode Extensions */ +#define X86_FEATURE_DE ( 0*32+ 2) /* Debugging Extensions */ +#define X86_FEATURE_PSE ( 0*32+ 3) /* Page Size Extensions */ +#define X86_FEATURE_TSC ( 0*32+ 4) /* Time Stamp Counter */ +#define X86_FEATURE_MSR ( 0*32+ 5) /* Model-Specific Registers */ +#define X86_FEATURE_PAE ( 0*32+ 6) /* Physical Address Extensions */ +#define X86_FEATURE_MCE ( 0*32+ 7) /* Machine Check Exception */ +#define X86_FEATURE_CX8 ( 0*32+ 8) /* CMPXCHG8 instruction */ +#define X86_FEATURE_APIC ( 0*32+ 9) /* Onboard APIC */ +#define X86_FEATURE_SEP ( 0*32+11) /* SYSENTER/SYSEXIT */ +#define X86_FEATURE_MTRR ( 0*32+12) /* Memory Type Range Registers */ +#define X86_FEATURE_PGE ( 0*32+13) /* Page Global Enable */ +#define X86_FEATURE_MCA ( 0*32+14) /* Machine Check Architecture */ +#define X86_FEATURE_CMOV ( 0*32+15) /* CMOV instructions */ /* (plus FCMOVcc, FCOMI with FPU) */ -#define X86_FEATURE_PAT (0*32+16) /* Page Attribute Table */ -#define X86_FEATURE_PSE36 (0*32+17) /* 36-bit PSEs */ -#define X86_FEATURE_PN (0*32+18) /* Processor serial number */ -#define X86_FEATURE_CLFLUSH (0*32+19) /* CLFLUSH instruction */ -#define X86_FEATURE_DS (0*32+21) /* "dts" Debug Store */ -#define X86_FEATURE_ACPI (0*32+22) /* ACPI via MSR */ -#define X86_FEATURE_MMX (0*32+23) /* Multimedia Extensions */ -#define X86_FEATURE_FXSR (0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */ -#define X86_FEATURE_XMM (0*32+25) /* "sse" */ -#define X86_FEATURE_XMM2 (0*32+26) /* "sse2" */ -#define X86_FEATURE_SELFSNOOP (0*32+27) /* "ss" CPU self snoop */ -#define X86_FEATURE_HT (0*32+28) /* Hyper-Threading */ -#define X86_FEATURE_ACC (0*32+29) /* "tm" Automatic clock control */ -#define X86_FEATURE_IA64 (0*32+30) /* IA-64 processor */ -#define X86_FEATURE_PBE (0*32+31) /* Pending Break Enable */ +#define X86_FEATURE_PAT ( 0*32+16) /* Page Attribute Table */ +#define X86_FEATURE_PSE36 ( 0*32+17) /* 36-bit PSEs */ +#define X86_FEATURE_PN ( 0*32+18) /* Processor serial number */ +#define X86_FEATURE_CLFLUSH ( 0*32+19) /* CLFLUSH instruction */ +#define X86_FEATURE_DS ( 0*32+21) /* "dts" Debug Store */ +#define X86_FEATURE_ACPI ( 0*32+22) /* ACPI via MSR */ +#define X86_FEATURE_MMX ( 0*32+23) /* Multimedia Extensions */ +#define X86_FEATURE_FXSR ( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */ +#define X86_FEATURE_XMM ( 0*32+25) /* "sse" */ +#define X86_FEATURE_XMM2 ( 0*32+26) /* "sse2" */ +#define X86_FEATURE_SELFSNOOP ( 0*32+27) /* "ss" CPU self snoop */ +#define X86_FEATURE_HT ( 0*32+28) /* Hyper-Threading */ +#define X86_FEATURE_ACC ( 0*32+29) /* "tm" Automatic clock control */ +#define X86_FEATURE_IA64 ( 0*32+30) /* IA-64 processor */ +#define X86_FEATURE_PBE ( 0*32+31) /* Pending Break Enable */ /* AMD-defined CPU features, CPUID level 0x80000001, word 1 */ /* Don't duplicate feature flags which are redundant with Intel! */ -#define X86_FEATURE_SYSCALL (1*32+11) /* SYSCALL/SYSRET */ -#define X86_FEATURE_MP (1*32+19) /* MP Capable. */ -#define X86_FEATURE_NX (1*32+20) /* Execute Disable */ -#define X86_FEATURE_MMXEXT (1*32+22) /* AMD MMX extensions */ -#define X86_FEATURE_FXSR_OPT (1*32+25) /* FXSAVE/FXRSTOR optimizations */ -#define X86_FEATURE_GBPAGES (1*32+26) /* "pdpe1gb" GB pages */ -#define X86_FEATURE_RDTSCP (1*32+27) /* RDTSCP */ -#define X86_FEATURE_LM (1*32+29) /* Long Mode (x86-64) */ -#define X86_FEATURE_3DNOWEXT (1*32+30) /* AMD 3DNow! extensions */ -#define X86_FEATURE_3DNOW (1*32+31) /* 3DNow! */ +#define X86_FEATURE_SYSCALL ( 1*32+11) /* SYSCALL/SYSRET */ +#define X86_FEATURE_MP ( 1*32+19) /* MP Capable. */ +#define X86_FEATURE_NX ( 1*32+20) /* Execute Disable */ +#define X86_FEATURE_MMXEXT ( 1*32+22) /* AMD MMX extensions */ +#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* FXSAVE/FXRSTOR optimizations */ +#define X86_FEATURE_GBPAGES ( 1*32+26) /* "pdpe1gb" GB pages */ +#define X86_FEATURE_RDTSCP ( 1*32+27) /* RDTSCP */ +#define X86_FEATURE_LM ( 1*32+29) /* Long Mode (x86-64) */ +#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* AMD 3DNow! extensions */ +#define X86_FEATURE_3DNOW ( 1*32+31) /* 3DNow! */ /* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */ -#define X86_FEATURE_RECOVERY (2*32+ 0) /* CPU in recovery mode */ -#define X86_FEATURE_LONGRUN (2*32+ 1) /* Longrun power control */ -#define X86_FEATURE_LRTI (2*32+ 3) /* LongRun table interface */ +#define X86_FEATURE_RECOVERY ( 2*32+ 0) /* CPU in recovery mode */ +#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* Longrun power control */ +#define X86_FEATURE_LRTI ( 2*32+ 3) /* LongRun table interface */ /* Other features, Linux-defined mapping, word 3 */ /* This range is used for feature bits which conflict or are synthesized */ -#define X86_FEATURE_CXMMX (3*32+ 0) /* Cyrix MMX extensions */ -#define X86_FEATURE_K6_MTRR (3*32+ 1) /* AMD K6 nonstandard MTRRs */ -#define X86_FEATURE_CYRIX_ARR (3*32+ 2) /* Cyrix ARRs (= MTRRs) */ -#define X86_FEATURE_CENTAUR_MCR (3*32+ 3) /* Centaur MCRs (= MTRRs) */ +#define X86_FEATURE_CXMMX ( 3*32+ 0) /* Cyrix MMX extensions */ +#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */ +#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */ +#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */ /* cpu types for specific tunings: */ -#define X86_FEATURE_K8 (3*32+ 4) /* "" Opteron, Athlon64 */ -#define X86_FEATURE_K7 (3*32+ 5) /* "" Athlon */ -#define X86_FEATURE_P3 (3*32+ 6) /* "" P3 */ -#define X86_FEATURE_P4 (3*32+ 7) /* "" P4 */ -#define X86_FEATURE_CONSTANT_TSC (3*32+ 8) /* TSC ticks at a constant rate */ -#define X86_FEATURE_UP (3*32+ 9) /* smp kernel running on up */ -#define X86_FEATURE_FXSAVE_LEAK (3*32+10) /* "" FXSAVE leaks FOP/FIP/FOP */ -#define X86_FEATURE_ARCH_PERFMON (3*32+11) /* Intel Architectural PerfMon */ -#define X86_FEATURE_PEBS (3*32+12) /* Precise-Event Based Sampling */ -#define X86_FEATURE_BTS (3*32+13) /* Branch Trace Store */ -#define X86_FEATURE_SYSCALL32 (3*32+14) /* "" syscall in ia32 userspace */ -#define X86_FEATURE_SYSENTER32 (3*32+15) /* "" sysenter in ia32 userspace */ -#define X86_FEATURE_REP_GOOD (3*32+16) /* rep microcode works well */ -#define X86_FEATURE_MFENCE_RDTSC (3*32+17) /* "" Mfence synchronizes RDTSC */ -#define X86_FEATURE_LFENCE_RDTSC (3*32+18) /* "" Lfence synchronizes RDTSC */ -#define X86_FEATURE_11AP (3*32+19) /* "" Bad local APIC aka 11AP */ -#define X86_FEATURE_NOPL (3*32+20) /* The NOPL (0F 1F) instructions */ -#define X86_FEATURE_ALWAYS (3*32+21) /* "" Always-present feature */ -#define X86_FEATURE_XTOPOLOGY (3*32+22) /* cpu topology enum extensions */ -#define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */ -#define X86_FEATURE_NONSTOP_TSC (3*32+24) /* TSC does not stop in C states */ -#define X86_FEATURE_CLFLUSH_MONITOR (3*32+25) /* "" clflush reqd with monitor */ -#define X86_FEATURE_EXTD_APICID (3*32+26) /* has extended APICID (8 bits) */ -#define X86_FEATURE_AMD_DCM (3*32+27) /* multi-node processor */ -#define X86_FEATURE_APERFMPERF (3*32+28) /* APERFMPERF */ -#define X86_FEATURE_EAGER_FPU (3*32+29) /* "eagerfpu" Non lazy FPU restore */ -#define X86_FEATURE_NONSTOP_TSC_S3 (3*32+30) /* TSC doesn't stop in S3 state */ +#define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */ +#define X86_FEATURE_K7 ( 3*32+ 5) /* "" Athlon */ +#define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */ +#define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */ +#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */ +#define X86_FEATURE_UP ( 3*32+ 9) /* smp kernel running on up */ +/* free, was #define X86_FEATURE_FXSAVE_LEAK ( 3*32+10) * "" FXSAVE leaks FOP/FIP/FOP */ +#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */ +#define X86_FEATURE_PEBS ( 3*32+12) /* Precise-Event Based Sampling */ +#define X86_FEATURE_BTS ( 3*32+13) /* Branch Trace Store */ +#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in ia32 userspace */ +#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in ia32 userspace */ +#define X86_FEATURE_REP_GOOD ( 3*32+16) /* rep microcode works well */ +#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" Mfence synchronizes RDTSC */ +#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" Lfence synchronizes RDTSC */ +/* free, was #define X86_FEATURE_11AP ( 3*32+19) * "" Bad local APIC aka 11AP */ +#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ +#define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ +#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* cpu topology enum extensions */ +#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */ +#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */ +/* free, was #define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) * "" clflush reqd with monitor */ +#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* has extended APICID (8 bits) */ +#define X86_FEATURE_AMD_DCM ( 3*32+27) /* multi-node processor */ +#define X86_FEATURE_APERFMPERF ( 3*32+28) /* APERFMPERF */ +#define X86_FEATURE_EAGER_FPU ( 3*32+29) /* "eagerfpu" Non lazy FPU restore */ +#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */ /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */ -#define X86_FEATURE_XMM3 (4*32+ 0) /* "pni" SSE-3 */ -#define X86_FEATURE_PCLMULQDQ (4*32+ 1) /* PCLMULQDQ instruction */ -#define X86_FEATURE_DTES64 (4*32+ 2) /* 64-bit Debug Store */ -#define X86_FEATURE_MWAIT (4*32+ 3) /* "monitor" Monitor/Mwait support */ -#define X86_FEATURE_DSCPL (4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */ -#define X86_FEATURE_VMX (4*32+ 5) /* Hardware virtualization */ -#define X86_FEATURE_SMX (4*32+ 6) /* Safer mode */ -#define X86_FEATURE_EST (4*32+ 7) /* Enhanced SpeedStep */ -#define X86_FEATURE_TM2 (4*32+ 8) /* Thermal Monitor 2 */ -#define X86_FEATURE_SSSE3 (4*32+ 9) /* Supplemental SSE-3 */ -#define X86_FEATURE_CID (4*32+10) /* Context ID */ -#define X86_FEATURE_FMA (4*32+12) /* Fused multiply-add */ -#define X86_FEATURE_CX16 (4*32+13) /* CMPXCHG16B */ -#define X86_FEATURE_XTPR (4*32+14) /* Send Task Priority Messages */ -#define X86_FEATURE_PDCM (4*32+15) /* Performance Capabilities */ -#define X86_FEATURE_PCID (4*32+17) /* Process Context Identifiers */ -#define X86_FEATURE_DCA (4*32+18) /* Direct Cache Access */ -#define X86_FEATURE_XMM4_1 (4*32+19) /* "sse4_1" SSE-4.1 */ -#define X86_FEATURE_XMM4_2 (4*32+20) /* "sse4_2" SSE-4.2 */ -#define X86_FEATURE_X2APIC (4*32+21) /* x2APIC */ -#define X86_FEATURE_MOVBE (4*32+22) /* MOVBE instruction */ -#define X86_FEATURE_POPCNT (4*32+23) /* POPCNT instruction */ -#define X86_FEATURE_TSC_DEADLINE_TIMER (4*32+24) /* Tsc deadline timer */ -#define X86_FEATURE_AES (4*32+25) /* AES instructions */ -#define X86_FEATURE_XSAVE (4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */ -#define X86_FEATURE_OSXSAVE (4*32+27) /* "" XSAVE enabled in the OS */ -#define X86_FEATURE_AVX (4*32+28) /* Advanced Vector Extensions */ -#define X86_FEATURE_F16C (4*32+29) /* 16-bit fp conversions */ -#define X86_FEATURE_RDRAND (4*32+30) /* The RDRAND instruction */ -#define X86_FEATURE_HYPERVISOR (4*32+31) /* Running on a hypervisor */ +#define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */ +#define X86_FEATURE_PCLMULQDQ ( 4*32+ 1) /* PCLMULQDQ instruction */ +#define X86_FEATURE_DTES64 ( 4*32+ 2) /* 64-bit Debug Store */ +#define X86_FEATURE_MWAIT ( 4*32+ 3) /* "monitor" Monitor/Mwait support */ +#define X86_FEATURE_DSCPL ( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */ +#define X86_FEATURE_VMX ( 4*32+ 5) /* Hardware virtualization */ +#define X86_FEATURE_SMX ( 4*32+ 6) /* Safer mode */ +#define X86_FEATURE_EST ( 4*32+ 7) /* Enhanced SpeedStep */ +#define X86_FEATURE_TM2 ( 4*32+ 8) /* Thermal Monitor 2 */ +#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* Supplemental SSE-3 */ +#define X86_FEATURE_CID ( 4*32+10) /* Context ID */ +#define X86_FEATURE_FMA ( 4*32+12) /* Fused multiply-add */ +#define X86_FEATURE_CX16 ( 4*32+13) /* CMPXCHG16B */ +#define X86_FEATURE_XTPR ( 4*32+14) /* Send Task Priority Messages */ +#define X86_FEATURE_PDCM ( 4*32+15) /* Performance Capabilities */ +#define X86_FEATURE_PCID ( 4*32+17) /* Process Context Identifiers */ +#define X86_FEATURE_DCA ( 4*32+18) /* Direct Cache Access */ +#define X86_FEATURE_XMM4_1 ( 4*32+19) /* "sse4_1" SSE-4.1 */ +#define X86_FEATURE_XMM4_2 ( 4*32+20) /* "sse4_2" SSE-4.2 */ +#define X86_FEATURE_X2APIC ( 4*32+21) /* x2APIC */ +#define X86_FEATURE_MOVBE ( 4*32+22) /* MOVBE instruction */ +#define X86_FEATURE_POPCNT ( 4*32+23) /* POPCNT instruction */ +#define X86_FEATURE_TSC_DEADLINE_TIMER ( 4*32+24) /* Tsc deadline timer */ +#define X86_FEATURE_AES ( 4*32+25) /* AES instructions */ +#define X86_FEATURE_XSAVE ( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */ +#define X86_FEATURE_OSXSAVE ( 4*32+27) /* "" XSAVE enabled in the OS */ +#define X86_FEATURE_AVX ( 4*32+28) /* Advanced Vector Extensions */ +#define X86_FEATURE_F16C ( 4*32+29) /* 16-bit fp conversions */ +#define X86_FEATURE_RDRAND ( 4*32+30) /* The RDRAND instruction */ +#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* Running on a hypervisor */ /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */ -#define X86_FEATURE_XSTORE (5*32+ 2) /* "rng" RNG present (xstore) */ -#define X86_FEATURE_XSTORE_EN (5*32+ 3) /* "rng_en" RNG enabled */ -#define X86_FEATURE_XCRYPT (5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */ -#define X86_FEATURE_XCRYPT_EN (5*32+ 7) /* "ace_en" on-CPU crypto enabled */ -#define X86_FEATURE_ACE2 (5*32+ 8) /* Advanced Cryptography Engine v2 */ -#define X86_FEATURE_ACE2_EN (5*32+ 9) /* ACE v2 enabled */ -#define X86_FEATURE_PHE (5*32+10) /* PadLock Hash Engine */ -#define X86_FEATURE_PHE_EN (5*32+11) /* PHE enabled */ -#define X86_FEATURE_PMM (5*32+12) /* PadLock Montgomery Multiplier */ -#define X86_FEATURE_PMM_EN (5*32+13) /* PMM enabled */ +#define X86_FEATURE_XSTORE ( 5*32+ 2) /* "rng" RNG present (xstore) */ +#define X86_FEATURE_XSTORE_EN ( 5*32+ 3) /* "rng_en" RNG enabled */ +#define X86_FEATURE_XCRYPT ( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */ +#define X86_FEATURE_XCRYPT_EN ( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */ +#define X86_FEATURE_ACE2 ( 5*32+ 8) /* Advanced Cryptography Engine v2 */ +#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* ACE v2 enabled */ +#define X86_FEATURE_PHE ( 5*32+10) /* PadLock Hash Engine */ +#define X86_FEATURE_PHE_EN ( 5*32+11) /* PHE enabled */ +#define X86_FEATURE_PMM ( 5*32+12) /* PadLock Montgomery Multiplier */ +#define X86_FEATURE_PMM_EN ( 5*32+13) /* PMM enabled */ /* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */ -#define X86_FEATURE_LAHF_LM (6*32+ 0) /* LAHF/SAHF in long mode */ -#define X86_FEATURE_CMP_LEGACY (6*32+ 1) /* If yes HyperThreading not valid */ -#define X86_FEATURE_SVM (6*32+ 2) /* Secure virtual machine */ -#define X86_FEATURE_EXTAPIC (6*32+ 3) /* Extended APIC space */ -#define X86_FEATURE_CR8_LEGACY (6*32+ 4) /* CR8 in 32-bit mode */ -#define X86_FEATURE_ABM (6*32+ 5) /* Advanced bit manipulation */ -#define X86_FEATURE_SSE4A (6*32+ 6) /* SSE-4A */ -#define X86_FEATURE_MISALIGNSSE (6*32+ 7) /* Misaligned SSE mode */ -#define X86_FEATURE_3DNOWPREFETCH (6*32+ 8) /* 3DNow prefetch instructions */ -#define X86_FEATURE_OSVW (6*32+ 9) /* OS Visible Workaround */ -#define X86_FEATURE_IBS (6*32+10) /* Instruction Based Sampling */ -#define X86_FEATURE_XOP (6*32+11) /* extended AVX instructions */ -#define X86_FEATURE_SKINIT (6*32+12) /* SKINIT/STGI instructions */ -#define X86_FEATURE_WDT (6*32+13) /* Watchdog timer */ -#define X86_FEATURE_LWP (6*32+15) /* Light Weight Profiling */ -#define X86_FEATURE_FMA4 (6*32+16) /* 4 operands MAC instructions */ -#define X86_FEATURE_TCE (6*32+17) /* translation cache extension */ -#define X86_FEATURE_NODEID_MSR (6*32+19) /* NodeId MSR */ -#define X86_FEATURE_TBM (6*32+21) /* trailing bit manipulations */ -#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_PERFCTR_L2 (6*32+28) /* L2 performance counter extensions */ +#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* LAHF/SAHF in long mode */ +#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* If yes HyperThreading not valid */ +#define X86_FEATURE_SVM ( 6*32+ 2) /* Secure virtual machine */ +#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* Extended APIC space */ +#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* CR8 in 32-bit mode */ +#define X86_FEATURE_ABM ( 6*32+ 5) /* Advanced bit manipulation */ +#define X86_FEATURE_SSE4A ( 6*32+ 6) /* SSE-4A */ +#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */ +#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */ +#define X86_FEATURE_OSVW ( 6*32+ 9) /* OS Visible Workaround */ +#define X86_FEATURE_IBS ( 6*32+10) /* Instruction Based Sampling */ +#define X86_FEATURE_XOP ( 6*32+11) /* extended AVX instructions */ +#define X86_FEATURE_SKINIT ( 6*32+12) /* SKINIT/STGI instructions */ +#define X86_FEATURE_WDT ( 6*32+13) /* Watchdog timer */ +#define X86_FEATURE_LWP ( 6*32+15) /* Light Weight Profiling */ +#define X86_FEATURE_FMA4 ( 6*32+16) /* 4 operands MAC instructions */ +#define X86_FEATURE_TCE ( 6*32+17) /* translation cache extension */ +#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* NodeId MSR */ +#define X86_FEATURE_TBM ( 6*32+21) /* trailing bit manipulations */ +#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_PERFCTR_L2 ( 6*32+28) /* L2 performance counter extensions */ /* * Auxiliary flags: Linux defined - For features scattered in various * CPUID levels like 0x6, 0xA etc, word 7 */ -#define X86_FEATURE_IDA (7*32+ 0) /* Intel Dynamic Acceleration */ -#define X86_FEATURE_ARAT (7*32+ 1) /* Always Running APIC Timer */ -#define X86_FEATURE_CPB (7*32+ 2) /* AMD Core Performance Boost */ -#define X86_FEATURE_EPB (7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ -#define X86_FEATURE_XSAVEOPT (7*32+ 4) /* Optimized Xsave */ -#define X86_FEATURE_PLN (7*32+ 5) /* Intel Power Limit Notification */ -#define X86_FEATURE_PTS (7*32+ 6) /* Intel Package Thermal Status */ -#define X86_FEATURE_DTHERM (7*32+ 7) /* Digital Thermal Sensor */ -#define X86_FEATURE_HW_PSTATE (7*32+ 8) /* AMD HW-PState */ -#define X86_FEATURE_PROC_FEEDBACK (7*32+ 9) /* AMD ProcFeedbackInterface */ +#define X86_FEATURE_IDA ( 7*32+ 0) /* Intel Dynamic Acceleration */ +#define X86_FEATURE_ARAT ( 7*32+ 1) /* Always Running APIC Timer */ +#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ +#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ +#define X86_FEATURE_PLN ( 7*32+ 5) /* Intel Power Limit Notification */ +#define X86_FEATURE_PTS ( 7*32+ 6) /* Intel Package Thermal Status */ +#define X86_FEATURE_DTHERM ( 7*32+ 7) /* Digital Thermal Sensor */ +#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ +#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ /* Virtualization flags: Linux defined, word 8 */ -#define X86_FEATURE_TPR_SHADOW (8*32+ 0) /* Intel TPR Shadow */ -#define X86_FEATURE_VNMI (8*32+ 1) /* Intel Virtual NMI */ -#define X86_FEATURE_FLEXPRIORITY (8*32+ 2) /* Intel FlexPriority */ -#define X86_FEATURE_EPT (8*32+ 3) /* Intel Extended Page Table */ -#define X86_FEATURE_VPID (8*32+ 4) /* Intel Virtual Processor ID */ -#define X86_FEATURE_NPT (8*32+ 5) /* AMD Nested Page Table support */ -#define X86_FEATURE_LBRV (8*32+ 6) /* AMD LBR Virtualization support */ -#define X86_FEATURE_SVML (8*32+ 7) /* "svm_lock" AMD SVM locking MSR */ -#define X86_FEATURE_NRIPS (8*32+ 8) /* "nrip_save" AMD SVM next_rip save */ -#define X86_FEATURE_TSCRATEMSR (8*32+ 9) /* "tsc_scale" AMD TSC scaling support */ -#define X86_FEATURE_VMCBCLEAN (8*32+10) /* "vmcb_clean" AMD VMCB clean bits support */ -#define X86_FEATURE_FLUSHBYASID (8*32+11) /* AMD flush-by-ASID support */ -#define X86_FEATURE_DECODEASSISTS (8*32+12) /* AMD Decode Assists support */ -#define X86_FEATURE_PAUSEFILTER (8*32+13) /* AMD filtered pause intercept */ -#define X86_FEATURE_PFTHRESHOLD (8*32+14) /* AMD pause filter threshold */ +#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ +#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ +#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */ +#define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */ +#define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ +#define X86_FEATURE_NPT ( 8*32+ 5) /* AMD Nested Page Table support */ +#define X86_FEATURE_LBRV ( 8*32+ 6) /* AMD LBR Virtualization support */ +#define X86_FEATURE_SVML ( 8*32+ 7) /* "svm_lock" AMD SVM locking MSR */ +#define X86_FEATURE_NRIPS ( 8*32+ 8) /* "nrip_save" AMD SVM next_rip save */ +#define X86_FEATURE_TSCRATEMSR ( 8*32+ 9) /* "tsc_scale" AMD TSC scaling support */ +#define X86_FEATURE_VMCBCLEAN ( 8*32+10) /* "vmcb_clean" AMD VMCB clean bits support */ +#define X86_FEATURE_FLUSHBYASID ( 8*32+11) /* AMD flush-by-ASID support */ +#define X86_FEATURE_DECODEASSISTS ( 8*32+12) /* AMD Decode Assists support */ +#define X86_FEATURE_PAUSEFILTER ( 8*32+13) /* AMD filtered pause intercept */ +#define X86_FEATURE_PFTHRESHOLD ( 8*32+14) /* AMD pause filter threshold */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ -#define X86_FEATURE_FSGSBASE (9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/ -#define X86_FEATURE_TSC_ADJUST (9*32+ 1) /* TSC adjustment MSR 0x3b */ -#define X86_FEATURE_BMI1 (9*32+ 3) /* 1st group bit manipulation extensions */ -#define X86_FEATURE_HLE (9*32+ 4) /* Hardware Lock Elision */ -#define X86_FEATURE_AVX2 (9*32+ 5) /* AVX2 instructions */ -#define X86_FEATURE_SMEP (9*32+ 7) /* Supervisor Mode Execution Protection */ -#define X86_FEATURE_BMI2 (9*32+ 8) /* 2nd group bit manipulation extensions */ -#define X86_FEATURE_ERMS (9*32+ 9) /* Enhanced REP MOVSB/STOSB */ -#define X86_FEATURE_INVPCID (9*32+10) /* Invalidate Processor Context ID */ -#define X86_FEATURE_RTM (9*32+11) /* Restricted Transactional Memory */ -#define X86_FEATURE_MPX (9*32+14) /* Memory Protection Extension */ -#define X86_FEATURE_AVX512F (9*32+16) /* AVX-512 Foundation */ -#define X86_FEATURE_RDSEED (9*32+18) /* The RDSEED instruction */ -#define X86_FEATURE_ADX (9*32+19) /* The ADCX and ADOX instructions */ -#define X86_FEATURE_SMAP (9*32+20) /* Supervisor Mode Access Prevention */ -#define X86_FEATURE_CLFLUSHOPT (9*32+23) /* CLFLUSHOPT instruction */ -#define X86_FEATURE_AVX512PF (9*32+26) /* AVX-512 Prefetch */ -#define X86_FEATURE_AVX512ER (9*32+27) /* AVX-512 Exponential and Reciprocal */ -#define X86_FEATURE_AVX512CD (9*32+28) /* AVX-512 Conflict Detection */ +#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/ +#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* TSC adjustment MSR 0x3b */ +#define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */ +#define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */ +#define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */ +#define X86_FEATURE_SMEP ( 9*32+ 7) /* Supervisor Mode Execution Protection */ +#define X86_FEATURE_BMI2 ( 9*32+ 8) /* 2nd group bit manipulation extensions */ +#define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */ +#define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */ +#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */ +#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */ +#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */ +#define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */ +#define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */ +#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */ +#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ +#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ +#define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ +#define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ + +/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */ +#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* XSAVEOPT */ +#define X86_FEATURE_XSAVEC (10*32+ 1) /* XSAVEC */ +#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 */ +#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS */ /* * BUG word(s) @@ -234,8 +239,11 @@ #define X86_BUG_F00F X86_BUG(0) /* Intel F00F */ #define X86_BUG_FDIV X86_BUG(1) /* FPU FDIV */ #define X86_BUG_COMA X86_BUG(2) /* Cyrix 6x86 coma */ -#define X86_BUG_AMD_TLB_MMATCH X86_BUG(3) /* AMD Erratum 383 */ -#define X86_BUG_AMD_APIC_C1E X86_BUG(4) /* AMD Erratum 400 */ +#define X86_BUG_AMD_TLB_MMATCH X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */ +#define X86_BUG_AMD_APIC_C1E X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */ +#define X86_BUG_11AP X86_BUG(5) /* Bad local APIC aka 11AP */ +#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ +#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ #if defined(__KERNEL__) && !defined(__ASSEMBLY__) @@ -245,6 +253,12 @@ extern const char * const x86_cap_flags[NCAPINTS*32]; extern const char * const x86_power_flags[32]; +/* + * In order to save room, we index into this array by doing + * X86_BUG_<name> - NCAPINTS*32. + */ +extern const char * const x86_bug_flags[NBUGINTS*32]; + #define test_cpu_cap(c, bit) \ test_bit(bit, (unsigned long *)((c)->x86_capability)) @@ -301,7 +315,6 @@ extern const char * const x86_power_flags[32]; #define cpu_has_avx boot_cpu_has(X86_FEATURE_AVX) #define cpu_has_avx2 boot_cpu_has(X86_FEATURE_AVX2) #define cpu_has_ht boot_cpu_has(X86_FEATURE_HT) -#define cpu_has_mp boot_cpu_has(X86_FEATURE_MP) #define cpu_has_nx boot_cpu_has(X86_FEATURE_NX) #define cpu_has_k6_mtrr boot_cpu_has(X86_FEATURE_K6_MTRR) #define cpu_has_cyrix_arr boot_cpu_has(X86_FEATURE_CYRIX_ARR) @@ -328,6 +341,7 @@ extern const char * const x86_power_flags[32]; #define cpu_has_x2apic boot_cpu_has(X86_FEATURE_X2APIC) #define cpu_has_xsave boot_cpu_has(X86_FEATURE_XSAVE) #define cpu_has_xsaveopt boot_cpu_has(X86_FEATURE_XSAVEOPT) +#define cpu_has_xsaves boot_cpu_has(X86_FEATURE_XSAVES) #define cpu_has_osxsave boot_cpu_has(X86_FEATURE_OSXSAVE) #define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR) #define cpu_has_pclmulqdq boot_cpu_has(X86_FEATURE_PCLMULQDQ) @@ -347,9 +361,6 @@ extern const char * const x86_power_flags[32]; #undef cpu_has_pae #define cpu_has_pae ___BUG___ -#undef cpu_has_mp -#define cpu_has_mp 1 - #undef cpu_has_k6_mtrr #define cpu_has_k6_mtrr 0 @@ -539,20 +550,20 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit) #define static_cpu_has_safe(bit) boot_cpu_has(bit) #endif -#define cpu_has_bug(c, bit) cpu_has(c, (bit)) -#define set_cpu_bug(c, bit) set_cpu_cap(c, (bit)) -#define clear_cpu_bug(c, bit) clear_cpu_cap(c, (bit)); +#define cpu_has_bug(c, bit) cpu_has(c, (bit)) +#define set_cpu_bug(c, bit) set_cpu_cap(c, (bit)) +#define clear_cpu_bug(c, bit) clear_cpu_cap(c, (bit)) -#define static_cpu_has_bug(bit) static_cpu_has((bit)) -#define boot_cpu_has_bug(bit) cpu_has_bug(&boot_cpu_data, (bit)) +#define static_cpu_has_bug(bit) static_cpu_has((bit)) +#define static_cpu_has_bug_safe(bit) static_cpu_has_safe((bit)) +#define boot_cpu_has_bug(bit) cpu_has_bug(&boot_cpu_data, (bit)) -#define MAX_CPU_FEATURES (NCAPINTS * 32) -#define cpu_have_feature boot_cpu_has +#define MAX_CPU_FEATURES (NCAPINTS * 32) +#define cpu_have_feature boot_cpu_has -#define CPU_FEATURE_TYPEFMT "x86,ven%04Xfam%04Xmod%04X" -#define CPU_FEATURE_TYPEVAL boot_cpu_data.x86_vendor, boot_cpu_data.x86, \ - boot_cpu_data.x86_model +#define CPU_FEATURE_TYPEFMT "x86,ven%04Xfam%04Xmod%04X" +#define CPU_FEATURE_TYPEVAL boot_cpu_data.x86_vendor, boot_cpu_data.x86, \ + boot_cpu_data.x86_model #endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */ - #endif /* _ASM_X86_CPUFEATURE_H */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 1eb5f6433ad8..044a2fd3c5fe 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -104,6 +104,8 @@ extern void __init runtime_code_page_mkexec(void); extern void __init efi_runtime_mkexec(void); extern void __init efi_dump_pagetable(void); extern void __init efi_apply_memmap_quirks(void); +extern int __init efi_reuse_config(u64 tables, int nr_tables); +extern void efi_delete_dummy_variable(void); struct efi_setup_data { u64 fw_vendor; @@ -156,6 +158,33 @@ static inline efi_status_t efi_thunk_set_virtual_address_map( return EFI_SUCCESS; } #endif /* CONFIG_EFI_MIXED */ + + +/* arch specific definitions used by the stub code */ + +struct efi_config { + u64 image_handle; + u64 table; + u64 allocate_pool; + u64 allocate_pages; + u64 get_memory_map; + u64 free_pool; + u64 free_pages; + u64 locate_handle; + u64 handle_protocol; + u64 exit_boot_services; + u64 text_output; + efi_status_t (*call)(unsigned long, ...); + bool is64; +} __packed; + +extern struct efi_config *efi_early; + +#define efi_call_early(f, ...) \ + efi_early->call(efi_early->f, __VA_ARGS__); + +extern bool efi_reboot_required(void); + #else /* * IF EFI is not configured, have the EFI calls return -ENOSYS. @@ -168,6 +197,10 @@ static inline efi_status_t efi_thunk_set_virtual_address_map( #define efi_call5(_f, _a1, _a2, _a3, _a4, _a5) (-ENOSYS) #define efi_call6(_f, _a1, _a2, _a3, _a4, _a5, _a6) (-ENOSYS) static inline void parse_efi_setup(u64 phys_addr, u32 data_len) {} +static inline bool efi_reboot_required(void) +{ + return false; +} #endif /* CONFIG_EFI */ #endif /* _ASM_X86_EFI_H */ diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h index 115e3689cd53..412ececa00b9 100644 --- a/arch/x86/include/asm/fpu-internal.h +++ b/arch/x86/include/asm/fpu-internal.h @@ -293,7 +293,7 @@ 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 */ - if (unlikely(static_cpu_has_safe(X86_FEATURE_FXSAVE_LEAK))) { + if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) { asm volatile( "fnclex\n\t" "emms\n\t" @@ -508,9 +508,12 @@ static inline void user_fpu_begin(void) static inline void __save_fpu(struct task_struct *tsk) { - if (use_xsave()) - xsave_state(&tsk->thread.fpu.state->xsave, -1); - else + if (use_xsave()) { + if (unlikely(system_state == SYSTEM_BOOTING)) + xsave_state_booting(&tsk->thread.fpu.state->xsave, -1); + else + xsave_state(&tsk->thread.fpu.state->xsave, -1); + } else fpu_fxsave(&tsk->thread.fpu); } diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 230853da4ec0..0f5fb6b6567e 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -40,9 +40,6 @@ typedef struct { DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); -/* We can have at most NR_VECTORS irqs routed to a cpu at a time */ -#define MAX_HARDIRQS_PER_CPU NR_VECTORS - #define __ARCH_IRQ_STAT #define inc_irq_stat(member) this_cpu_inc(irq_stat.member) diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h index a20365953bf8..ccffa53750a8 100644 --- a/arch/x86/include/asm/i8259.h +++ b/arch/x86/include/asm/i8259.h @@ -67,4 +67,9 @@ struct legacy_pic { extern struct legacy_pic *legacy_pic; extern struct legacy_pic null_legacy_pic; +static inline int nr_legacy_irqs(void) +{ + return legacy_pic->nr_legacy_irqs; +} + #endif /* _ASM_X86_I8259_H */ diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 90f97b4b9347..0aeed5ca356e 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -98,6 +98,8 @@ struct IR_IO_APIC_route_entry { #define IOAPIC_AUTO -1 #define IOAPIC_EDGE 0 #define IOAPIC_LEVEL 1 +#define IOAPIC_MAP_ALLOC 0x1 +#define IOAPIC_MAP_CHECK 0x2 #ifdef CONFIG_X86_IO_APIC @@ -118,9 +120,6 @@ extern int mp_irq_entries; /* MP IRQ source entries */ extern struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES]; -/* non-0 if default (table-less) MP configuration */ -extern int mpc_default_type; - /* Older SiS APIC requires we rewrite the index register */ extern int sis_apic_bug; @@ -133,9 +132,6 @@ extern int noioapicquirk; /* -1 if "noapic" boot option passed */ extern int noioapicreroute; -/* 1 if the timer IRQ uses the '8259A Virtual Wire' mode */ -extern int timer_through_8259; - /* * If we use the IO-APIC for IRQ routing, disable automatic * assignment of PCI IRQ's. @@ -145,24 +141,17 @@ extern int timer_through_8259; struct io_apic_irq_attr; struct irq_cfg; -extern int io_apic_set_pci_routing(struct device *dev, int irq, - struct io_apic_irq_attr *irq_attr); -void setup_IO_APIC_irq_extra(u32 gsi); extern void ioapic_insert_resources(void); extern int native_setup_ioapic_entry(int, struct IO_APIC_route_entry *, unsigned int, int, struct io_apic_irq_attr *); -extern int native_setup_ioapic_entry(int, struct IO_APIC_route_entry *, - unsigned int, int, - struct io_apic_irq_attr *); extern void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg); extern void native_compose_msi_msg(struct pci_dev *pdev, unsigned int irq, unsigned int dest, struct msi_msg *msg, u8 hpet_id); extern void native_eoi_ioapic_pin(int apic, int pin, int vector); -int io_apic_setup_irq_pin_once(unsigned int irq, int node, struct io_apic_irq_attr *attr); extern int save_ioapic_entries(void); extern void mask_ioapic_entries(void); @@ -171,15 +160,40 @@ extern int restore_ioapic_entries(void); extern void setup_ioapic_ids_from_mpc(void); extern void setup_ioapic_ids_from_mpc_nocheck(void); +enum ioapic_domain_type { + IOAPIC_DOMAIN_INVALID, + IOAPIC_DOMAIN_LEGACY, + IOAPIC_DOMAIN_STRICT, + IOAPIC_DOMAIN_DYNAMIC, +}; + +struct device_node; +struct irq_domain; +struct irq_domain_ops; + +struct ioapic_domain_cfg { + enum ioapic_domain_type type; + const struct irq_domain_ops *ops; + struct device_node *dev; +}; + struct mp_ioapic_gsi{ u32 gsi_base; u32 gsi_end; }; -extern struct mp_ioapic_gsi mp_gsi_routing[]; extern u32 gsi_top; -int mp_find_ioapic(u32 gsi); -int mp_find_ioapic_pin(int ioapic, u32 gsi); -void __init mp_register_ioapic(int id, u32 address, u32 gsi_base); + +extern int mp_find_ioapic(u32 gsi); +extern int mp_find_ioapic_pin(int ioapic, u32 gsi); +extern u32 mp_pin_to_gsi(int ioapic, int pin); +extern int mp_map_gsi_to_irq(u32 gsi, unsigned int flags); +extern void mp_unmap_irq(int irq); +extern void __init mp_register_ioapic(int id, u32 address, u32 gsi_base, + struct ioapic_domain_cfg *cfg); +extern int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq); +extern void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq); +extern int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node); extern void __init pre_init_apic_IRQ0(void); extern void mp_save_irq(struct mpc_intsrc *m); @@ -217,14 +231,12 @@ extern void io_apic_eoi(unsigned int apic, unsigned int vector); #define io_apic_assign_pci_irqs 0 #define setup_ioapic_ids_from_mpc x86_init_noop -static const int timer_through_8259 = 0; static inline void ioapic_insert_resources(void) { } #define gsi_top (NR_IRQS_LEGACY) static inline int mp_find_ioapic(u32 gsi) { return 0; } - -struct io_apic_irq_attr; -static inline int io_apic_set_pci_routing(struct device *dev, int irq, - struct io_apic_irq_attr *irq_attr) { return 0; } +static inline u32 mp_pin_to_gsi(int ioapic, int pin) { return UINT_MAX; } +static inline int mp_map_gsi_to_irq(u32 gsi, unsigned int flags) { return gsi; } +static inline void mp_unmap_irq(int irq) { } static inline int save_ioapic_entries(void) { diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h index a55c7efcc4ed..0f555cc31984 100644 --- a/arch/x86/include/asm/mc146818rtc.h +++ b/arch/x86/include/asm/mc146818rtc.h @@ -13,7 +13,7 @@ #define RTC_ALWAYS_BCD 1 /* RTC operates in binary mode */ #endif -#if defined(CONFIG_X86_32) && defined(__HAVE_ARCH_CMPXCHG) +#if defined(CONFIG_X86_32) /* * This lock provides nmi access to the CMOS/RTC registers. It has some * special properties. It is owned by a CPU and stores the index register diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index be12c534fd59..166af2a8e865 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -3,6 +3,10 @@ #include <asm/desc.h> #include <linux/atomic.h> +#include <linux/mm_types.h> + +#include <trace/events/tlb.h> + #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm/paravirt.h> @@ -44,6 +48,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, /* Re-load page tables */ load_cr3(next->pgd); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); /* Stop flush ipis for the previous mm */ cpumask_clear_cpu(cpu, mm_cpumask(prev)); @@ -71,6 +76,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * to make sure to use no freed page tables. */ load_cr3(next->pgd); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); load_LDT_nolock(&next->context); } } diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index f5a617956735..b07233b64578 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -40,8 +40,6 @@ extern int mp_bus_id_to_type[MAX_MP_BUSSES]; extern DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES); extern unsigned int boot_cpu_physical_apicid; -extern unsigned int max_physical_apicid; -extern int mpc_default_type; extern unsigned long mp_lapic_addr; #ifdef CONFIG_X86_LOCAL_APIC @@ -88,15 +86,6 @@ static inline void early_reserve_e820_mpc_new(void) { } #endif int generic_processor_info(int apicid, int version); -#ifdef CONFIG_ACPI -extern void mp_register_ioapic(int id, u32 address, u32 gsi_base); -extern void mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, - u32 gsi); -extern void mp_config_acpi_legacy_irqs(void); -struct device; -extern int mp_register_gsi(struct device *dev, u32 gsi, int edge_level, - int active_high_low); -#endif /* CONFIG_ACPI */ #define PHYSID_ARRAY_SIZE BITS_TO_LONGS(MAX_LOCAL_APIC) @@ -161,8 +150,4 @@ static inline void physid_set_mask_of_physid(int physid, physid_mask_t *map) extern physid_mask_t phys_cpu_present_map; -extern int generic_mps_oem_check(struct mpc_table *, char *, char *); - -extern int default_acpi_madt_oem_check(char *, char *); - #endif /* _ASM_X86_MPSPEC_H */ diff --git a/arch/x86/include/asm/mutex_32.h b/arch/x86/include/asm/mutex_32.h index 0208c3c2cbc6..85e6cda45a02 100644 --- a/arch/x86/include/asm/mutex_32.h +++ b/arch/x86/include/asm/mutex_32.h @@ -100,23 +100,11 @@ do { \ static inline int __mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *)) { - /* - * We have two variants here. The cmpxchg based one is the best one - * because it never induce a false contention state. It is included - * here because architectures using the inc/dec algorithms over the - * xchg ones are much more likely to support cmpxchg natively. - * - * If not we fall back to the spinlock based variant - that is - * just as efficient (and simpler) as a 'destructive' probing of - * the mutex state would be. - */ -#ifdef __HAVE_ARCH_CMPXCHG + /* cmpxchg because it never induces a false contention state. */ if (likely(atomic_cmpxchg(count, 1, 0) == 1)) return 1; + return 0; -#else - return fail_fn(count); -#endif } #endif /* _ASM_X86_MUTEX_32_H */ diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index 1da25a5f96f9..a1410db38a1a 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -43,7 +43,7 @@ static inline void __mwait(unsigned long eax, unsigned long ecx) static inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx) { if (!current_set_polling_and_test()) { - if (static_cpu_has(X86_FEATURE_CLFLUSH_MONITOR)) { + if (static_cpu_has_bug(X86_BUG_CLFLUSH_MONITOR)) { mb(); clflush((void *)¤t_thread_info()->flags); mb(); diff --git a/arch/x86/include/asm/pmc_atom.h b/arch/x86/include/asm/pmc_atom.h new file mode 100644 index 000000000000..fc7a17c05d35 --- /dev/null +++ b/arch/x86/include/asm/pmc_atom.h @@ -0,0 +1,107 @@ +/* + * Intel Atom SOC Power Management Controller Header File + * Copyright (c) 2014, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + */ + +#ifndef PMC_ATOM_H +#define PMC_ATOM_H + +/* ValleyView Power Control Unit PCI Device ID */ +#define PCI_DEVICE_ID_VLV_PMC 0x0F1C + +/* PMC Memory mapped IO registers */ +#define PMC_BASE_ADDR_OFFSET 0x44 +#define PMC_BASE_ADDR_MASK 0xFFFFFE00 +#define PMC_MMIO_REG_LEN 0x100 +#define PMC_REG_BIT_WIDTH 32 + +/* BIOS uses FUNC_DIS to disable specific function */ +#define PMC_FUNC_DIS 0x34 +#define PMC_FUNC_DIS_2 0x38 + +/* S0ix wake event control */ +#define PMC_S0IX_WAKE_EN 0x3C + +#define BIT_LPC_CLOCK_RUN BIT(4) +#define BIT_SHARED_IRQ_GPSC BIT(5) +#define BIT_ORED_DEDICATED_IRQ_GPSS BIT(18) +#define BIT_ORED_DEDICATED_IRQ_GPSC BIT(19) +#define BIT_SHARED_IRQ_GPSS BIT(20) + +#define PMC_WAKE_EN_SETTING ~(BIT_LPC_CLOCK_RUN | \ + BIT_SHARED_IRQ_GPSC | \ + BIT_ORED_DEDICATED_IRQ_GPSS | \ + BIT_ORED_DEDICATED_IRQ_GPSC | \ + BIT_SHARED_IRQ_GPSS) + +/* The timers acumulate time spent in sleep state */ +#define PMC_S0IR_TMR 0x80 +#define PMC_S0I1_TMR 0x84 +#define PMC_S0I2_TMR 0x88 +#define PMC_S0I3_TMR 0x8C +#define PMC_S0_TMR 0x90 +/* Sleep state counter is in units of of 32us */ +#define PMC_TMR_SHIFT 5 + +/* These registers reflect D3 status of functions */ +#define PMC_D3_STS_0 0xA0 + +#define BIT_LPSS1_F0_DMA BIT(0) +#define BIT_LPSS1_F1_PWM1 BIT(1) +#define BIT_LPSS1_F2_PWM2 BIT(2) +#define BIT_LPSS1_F3_HSUART1 BIT(3) +#define BIT_LPSS1_F4_HSUART2 BIT(4) +#define BIT_LPSS1_F5_SPI BIT(5) +#define BIT_LPSS1_F6_XXX BIT(6) +#define BIT_LPSS1_F7_XXX BIT(7) +#define BIT_SCC_EMMC BIT(8) +#define BIT_SCC_SDIO BIT(9) +#define BIT_SCC_SDCARD BIT(10) +#define BIT_SCC_MIPI BIT(11) +#define BIT_HDA BIT(12) +#define BIT_LPE BIT(13) +#define BIT_OTG BIT(14) +#define BIT_USH BIT(15) +#define BIT_GBE BIT(16) +#define BIT_SATA BIT(17) +#define BIT_USB_EHCI BIT(18) +#define BIT_SEC BIT(19) +#define BIT_PCIE_PORT0 BIT(20) +#define BIT_PCIE_PORT1 BIT(21) +#define BIT_PCIE_PORT2 BIT(22) +#define BIT_PCIE_PORT3 BIT(23) +#define BIT_LPSS2_F0_DMA BIT(24) +#define BIT_LPSS2_F1_I2C1 BIT(25) +#define BIT_LPSS2_F2_I2C2 BIT(26) +#define BIT_LPSS2_F3_I2C3 BIT(27) +#define BIT_LPSS2_F4_I2C4 BIT(28) +#define BIT_LPSS2_F5_I2C5 BIT(29) +#define BIT_LPSS2_F6_I2C6 BIT(30) +#define BIT_LPSS2_F7_I2C7 BIT(31) + +#define PMC_D3_STS_1 0xA4 +#define BIT_SMB BIT(0) +#define BIT_OTG_SS_PHY BIT(1) +#define BIT_USH_SS_PHY BIT(2) +#define BIT_DFX BIT(3) + +/* PMC I/O Registers */ +#define ACPI_BASE_ADDR_OFFSET 0x40 +#define ACPI_BASE_ADDR_MASK 0xFFFFFE00 +#define ACPI_MMIO_REG_LEN 0x100 + +#define PM1_CNT 0x4 +#define SLEEP_TYPE_MASK 0xFFFFECFF +#define SLEEP_TYPE_S5 0x1C00 +#define SLEEP_ENABLE 0x2000 +#endif /* PMC_ATOM_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index a4ea02351f4d..eb71ec794732 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -72,7 +72,6 @@ extern u16 __read_mostly tlb_lld_4k[NR_INFO]; extern u16 __read_mostly tlb_lld_2m[NR_INFO]; extern u16 __read_mostly tlb_lld_4m[NR_INFO]; extern u16 __read_mostly tlb_lld_1g[NR_INFO]; -extern s8 __read_mostly tlb_flushall_shift; /* * CPU type and hardware bug flags. Kept separately for each CPU. @@ -386,8 +385,8 @@ struct bndcsr_struct { struct xsave_hdr_struct { u64 xstate_bv; - u64 reserved1[2]; - u64 reserved2[5]; + u64 xcomp_bv; + u64 reserved[6]; } __attribute__((packed)); struct xsave_struct { @@ -696,6 +695,8 @@ static inline void cpu_relax(void) rep_nop(); } +#define cpu_relax_lowlatency() cpu_relax() + /* Stop speculative execution and prefetching of modified code. */ static inline void sync_core(void) { diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h index fbeb06ed0eaa..1d081ac1cd69 100644 --- a/arch/x86/include/asm/prom.h +++ b/arch/x86/include/asm/prom.h @@ -26,12 +26,10 @@ extern int of_ioapic; extern u64 initial_dtb; extern void add_dtb(u64 data); -extern void x86_add_irq_domains(void); void x86_of_pci_init(void); void x86_dtb_init(void); #else static inline void add_dtb(u64 data) { } -static inline void x86_add_irq_domains(void) { } static inline void x86_of_pci_init(void) { } static inline void x86_dtb_init(void) { } #define of_ioapic 0 diff --git a/arch/x86/include/asm/qrwlock.h b/arch/x86/include/asm/qrwlock.h index 70f46f07f94e..ae0e241e228b 100644 --- a/arch/x86/include/asm/qrwlock.h +++ b/arch/x86/include/asm/qrwlock.h @@ -3,7 +3,7 @@ #include <asm-generic/qrwlock_types.h> -#if !defined(CONFIG_X86_OOSTORE) && !defined(CONFIG_X86_PPRO_FENCE) +#ifndef CONFIG_X86_PPRO_FENCE #define queue_write_unlock queue_write_unlock static inline void queue_write_unlock(struct qrwlock *lock) { diff --git a/arch/x86/include/asm/smpboot_hooks.h b/arch/x86/include/asm/smpboot_hooks.h index 49adfd7bb4a4..0da7409f0bec 100644 --- a/arch/x86/include/asm/smpboot_hooks.h +++ b/arch/x86/include/asm/smpboot_hooks.h @@ -17,11 +17,11 @@ static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip) spin_unlock_irqrestore(&rtc_lock, flags); local_flush_tlb(); pr_debug("1.\n"); - *((volatile unsigned short *)phys_to_virt(apic->trampoline_phys_high)) = - start_eip >> 4; + *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) = + start_eip >> 4; pr_debug("2.\n"); - *((volatile unsigned short *)phys_to_virt(apic->trampoline_phys_low)) = - start_eip & 0xf; + *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = + start_eip & 0xf; pr_debug("3.\n"); } @@ -42,7 +42,7 @@ static inline void smpboot_restore_warm_reset_vector(void) CMOS_WRITE(0, 0xf); spin_unlock_irqrestore(&rtc_lock, flags); - *((volatile u32 *)phys_to_virt(apic->trampoline_phys_low)) = 0; + *((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0; } static inline void __init smpboot_setup_io_apic(void) diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h index 0b46ef261c77..2d60a7813dfe 100644 --- a/arch/x86/include/asm/uv/uv_bau.h +++ b/arch/x86/include/asm/uv/uv_bau.h @@ -73,6 +73,7 @@ #define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD (is_uv1_hub() ? \ UV1_INTD_SOFT_ACK_TIMEOUT_PERIOD : \ UV2_INTD_SOFT_ACK_TIMEOUT_PERIOD) +/* assuming UV3 is the same */ #define BAU_MISC_CONTROL_MULT_MASK 3 @@ -93,6 +94,8 @@ #define SOFTACK_MSHIFT UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT #define SOFTACK_PSHIFT UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT #define SOFTACK_TIMEOUT_PERIOD UV_INTD_SOFT_ACK_TIMEOUT_PERIOD +#define PREFETCH_HINT_SHFT UV3H_LB_BAU_MISC_CONTROL_ENABLE_INTD_PREFETCH_HINT_SHFT +#define SB_STATUS_SHFT UV3H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_SHFT #define write_gmmr uv_write_global_mmr64 #define write_lmmr uv_write_local_mmr #define read_lmmr uv_read_local_mmr @@ -322,8 +325,9 @@ struct uv1_bau_msg_header { /* * UV2 Message header: 16 bytes (128 bits) (bytes 0x30-0x3f of descriptor) * see figure 9-2 of harp_sys.pdf + * assuming UV3 is the same */ -struct uv2_bau_msg_header { +struct uv2_3_bau_msg_header { unsigned int base_dest_nasid:15; /* nasid of the first bit */ /* bits 14:0 */ /* in uvhub map */ unsigned int dest_subnodeid:5; /* must be 0x10, for the LB */ @@ -395,7 +399,7 @@ struct bau_desc { */ union bau_msg_header { struct uv1_bau_msg_header uv1_hdr; - struct uv2_bau_msg_header uv2_hdr; + struct uv2_3_bau_msg_header uv2_3_hdr; } header; struct bau_msg_payload payload; @@ -631,11 +635,6 @@ struct bau_control { struct hub_and_pnode *thp; }; -static inline unsigned long read_mmr_uv2_status(void) -{ - return read_lmmr(UV2H_LB_BAU_SB_ACTIVATION_STATUS_2); -} - static inline void write_mmr_data_broadcast(int pnode, unsigned long mmr_image) { write_gmmr(pnode, UVH_BAU_DATA_BROADCAST, mmr_image); @@ -760,7 +759,11 @@ static inline int atomic_read_short(const struct atomic_short *v) */ static inline int atom_asr(short i, struct atomic_short *v) { - return i + xadd(&v->counter, i); + short __i = i; + asm volatile(LOCK_PREFIX "xaddw %0, %1" + : "+r" (i), "+m" (v->counter) + : : "memory"); + return i + __i; } /* diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index 30be253dd283..8021bd28c0f1 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -18,15 +18,15 @@ struct vdso_image { unsigned long alt, alt_len; - unsigned long sym_end_mapping; /* Total size of the mapping */ - - unsigned long sym_vvar_page; - unsigned long sym_hpet_page; - unsigned long sym_VDSO32_NOTE_MASK; - unsigned long sym___kernel_sigreturn; - unsigned long sym___kernel_rt_sigreturn; - unsigned long sym___kernel_vsyscall; - unsigned long sym_VDSO32_SYSENTER_RETURN; + long sym_vvar_start; /* Negative offset to the vvar area */ + + long sym_vvar_page; + long sym_hpet_page; + long sym_VDSO32_NOTE_MASK; + long sym___kernel_sigreturn; + long sym___kernel_rt_sigreturn; + long sym___kernel_vsyscall; + long sym_VDSO32_SYSENTER_RETURN; }; #ifdef CONFIG_X86_64 diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h index d949ef28c48b..7e7a79ada658 100644 --- a/arch/x86/include/asm/xsave.h +++ b/arch/x86/include/asm/xsave.h @@ -52,24 +52,170 @@ extern void xsave_init(void); extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask); extern int init_fpu(struct task_struct *child); -static inline int fpu_xrstor_checking(struct xsave_struct *fx) +/* These macros all use (%edi)/(%rdi) as the single memory argument. */ +#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" +#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" +#define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f" +#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" +#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" + +#define xstate_fault ".section .fixup,\"ax\"\n" \ + "3: movl $-1,%[err]\n" \ + " jmp 2b\n" \ + ".previous\n" \ + _ASM_EXTABLE(1b, 3b) \ + : [err] "=r" (err) + +/* + * This function is called only during boot time when x86 caps are not set + * up and alternative can not be used yet. + */ +static inline int xsave_state_booting(struct xsave_struct *fx, u64 mask) { - int err; + u32 lmask = mask; + u32 hmask = mask >> 32; + int err = 0; + + WARN_ON(system_state != SYSTEM_BOOTING); + + if (boot_cpu_has(X86_FEATURE_XSAVES)) + asm volatile("1:"XSAVES"\n\t" + "2:\n\t" + : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) + : "memory"); + else + asm volatile("1:"XSAVE"\n\t" + "2:\n\t" + : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) + : "memory"); + + asm volatile(xstate_fault + : "0" (0) + : "memory"); + + return err; +} + +/* + * This function is called only during boot time when x86 caps are not set + * up and alternative can not be used yet. + */ +static inline int xrstor_state_booting(struct xsave_struct *fx, u64 mask) +{ + u32 lmask = mask; + u32 hmask = mask >> 32; + int err = 0; + + WARN_ON(system_state != SYSTEM_BOOTING); - asm volatile("1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n\t" - "2:\n" - ".section .fixup,\"ax\"\n" - "3: movl $-1,%[err]\n" - " jmp 2b\n" - ".previous\n" - _ASM_EXTABLE(1b, 3b) - : [err] "=r" (err) - : "D" (fx), "m" (*fx), "a" (-1), "d" (-1), "0" (0) + if (boot_cpu_has(X86_FEATURE_XSAVES)) + asm volatile("1:"XRSTORS"\n\t" + "2:\n\t" + : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) + : "memory"); + else + asm volatile("1:"XRSTOR"\n\t" + "2:\n\t" + : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) + : "memory"); + + asm volatile(xstate_fault + : "0" (0) + : "memory"); + + return err; +} + +/* + * Save processor xstate to xsave area. + */ +static inline int xsave_state(struct xsave_struct *fx, u64 mask) +{ + u32 lmask = mask; + u32 hmask = mask >> 32; + int err = 0; + + /* + * If xsaves is enabled, xsaves replaces xsaveopt because + * it supports compact format and supervisor states in addition to + * modified optimization in xsaveopt. + * + * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave + * because xsaveopt supports modified optimization which is not + * supported by xsave. + * + * If none of xsaves and xsaveopt is enabled, use xsave. + */ + alternative_input_2( + "1:"XSAVE, + "1:"XSAVEOPT, + X86_FEATURE_XSAVEOPT, + "1:"XSAVES, + X86_FEATURE_XSAVES, + [fx] "D" (fx), "a" (lmask), "d" (hmask) : + "memory"); + asm volatile("2:\n\t" + xstate_fault + : "0" (0) : "memory"); return err; } +/* + * Restore processor xstate from xsave area. + */ +static inline int xrstor_state(struct xsave_struct *fx, u64 mask) +{ + int err = 0; + u32 lmask = mask; + u32 hmask = mask >> 32; + + /* + * Use xrstors to restore context if it is enabled. xrstors supports + * compacted format of xsave area which is not supported by xrstor. + */ + alternative_input( + "1: " XRSTOR, + "1: " XRSTORS, + X86_FEATURE_XSAVES, + "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) + : "memory"); + + asm volatile("2:\n" + xstate_fault + : "0" (0) + : "memory"); + + return err; +} + +/* + * Save xstate context for old process during context switch. + */ +static inline void fpu_xsave(struct fpu *fpu) +{ + xsave_state(&fpu->state->xsave, -1); +} + +/* + * Restore xstate context for new process during context switch. + */ +static inline int fpu_xrstor_checking(struct xsave_struct *fx) +{ + return xrstor_state(fx, -1); +} + +/* + * Save xstate to user space xsave area. + * + * We don't use modified optimization because xrstor/xrstors might track + * a different application. + * + * We don't use compacted format xsave area for + * backward compatibility for old applications which don't understand + * compacted format of xsave area. + */ static inline int xsave_user(struct xsave_struct __user *buf) { int err; @@ -83,69 +229,34 @@ static inline int xsave_user(struct xsave_struct __user *buf) return -EFAULT; __asm__ __volatile__(ASM_STAC "\n" - "1: .byte " REX_PREFIX "0x0f,0xae,0x27\n" + "1:"XSAVE"\n" "2: " ASM_CLAC "\n" - ".section .fixup,\"ax\"\n" - "3: movl $-1,%[err]\n" - " jmp 2b\n" - ".previous\n" - _ASM_EXTABLE(1b,3b) - : [err] "=r" (err) + xstate_fault : "D" (buf), "a" (-1), "d" (-1), "0" (0) : "memory"); return err; } +/* + * Restore xstate from user space xsave area. + */ static inline int xrestore_user(struct xsave_struct __user *buf, u64 mask) { - int err; + int err = 0; struct xsave_struct *xstate = ((__force struct xsave_struct *)buf); u32 lmask = mask; u32 hmask = mask >> 32; __asm__ __volatile__(ASM_STAC "\n" - "1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n" + "1:"XRSTOR"\n" "2: " ASM_CLAC "\n" - ".section .fixup,\"ax\"\n" - "3: movl $-1,%[err]\n" - " jmp 2b\n" - ".previous\n" - _ASM_EXTABLE(1b,3b) - : [err] "=r" (err) + xstate_fault : "D" (xstate), "a" (lmask), "d" (hmask), "0" (0) : "memory"); /* memory required? */ return err; } -static inline void xrstor_state(struct xsave_struct *fx, u64 mask) -{ - u32 lmask = mask; - u32 hmask = mask >> 32; - - asm volatile(".byte " REX_PREFIX "0x0f,0xae,0x2f\n\t" - : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) - : "memory"); -} - -static inline void xsave_state(struct xsave_struct *fx, u64 mask) -{ - u32 lmask = mask; - u32 hmask = mask >> 32; +void *get_xsave_addr(struct xsave_struct *xsave, int xstate); +void setup_xstate_comp(void); - asm volatile(".byte " REX_PREFIX "0x0f,0xae,0x27\n\t" - : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) - : "memory"); -} - -static inline void fpu_xsave(struct fpu *fpu) -{ - /* This, however, we can work around by forcing the compiler to select - an addressing mode that doesn't require extended registers. */ - alternative_input( - ".byte " REX_PREFIX "0x0f,0xae,0x27", - ".byte " REX_PREFIX "0x0f,0xae,0x37", - X86_FEATURE_XSAVEOPT, - [fx] "D" (&fpu->state->xsave), "a" (-1), "d" (-1) : - "memory"); -} #endif diff --git a/arch/x86/include/uapi/asm/Kbuild b/arch/x86/include/uapi/asm/Kbuild index 09409c44f9a5..3dec769cadf7 100644 --- a/arch/x86/include/uapi/asm/Kbuild +++ b/arch/x86/include/uapi/asm/Kbuild @@ -22,6 +22,7 @@ header-y += ipcbuf.h header-y += ist.h header-y += kvm.h header-y += kvm_para.h +header-y += kvm_perf.h header-y += ldt.h header-y += mce.h header-y += mman.h diff --git a/arch/x86/include/uapi/asm/kvm_perf.h b/arch/x86/include/uapi/asm/kvm_perf.h new file mode 100644 index 000000000000..3bb964f88aa1 --- /dev/null +++ b/arch/x86/include/uapi/asm/kvm_perf.h @@ -0,0 +1,16 @@ +#ifndef _ASM_X86_KVM_PERF_H +#define _ASM_X86_KVM_PERF_H + +#include <asm/svm.h> +#include <asm/vmx.h> +#include <asm/kvm.h> + +#define DECODE_STR_LEN 20 + +#define VCPU_ID "vcpu_id" + +#define KVM_ENTRY_TRACE "kvm:kvm_entry" +#define KVM_EXIT_TRACE "kvm:kvm_exit" +#define KVM_EXIT_REASON "exit_reason" + +#endif /* _ASM_X86_KVM_PERF_H */ diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h index 4a7aecd2ea13..c3f1ce4e249d 100644 --- a/arch/x86/include/uapi/asm/msr-index.h +++ b/arch/x86/include/uapi/asm/msr-index.h @@ -300,6 +300,8 @@ #define MSR_IA32_TSC_ADJUST 0x0000003b #define MSR_IA32_BNDCFGS 0x00000d90 +#define MSR_IA32_XSS 0x00000da0 + #define FEATURE_CONTROL_LOCKED (1<<0) #define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX (1<<1) #define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX (1<<2) diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 047f9ff2e36c..bde3993624f1 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -106,6 +106,7 @@ obj-$(CONFIG_EFI) += sysfb_efi.o obj-$(CONFIG_PERF_EVENTS) += perf_regs.o obj-$(CONFIG_TRACING) += tracepoint.o obj-$(CONFIG_IOSF_MBI) += iosf_mbi.o +obj-$(CONFIG_PMC_ATOM) += pmc_atom.o ### # 64 bit specific files diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile index 163b22581472..3242e591fa82 100644 --- a/arch/x86/kernel/acpi/Makefile +++ b/arch/x86/kernel/acpi/Makefile @@ -1,5 +1,6 @@ obj-$(CONFIG_ACPI) += boot.o obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup_$(BITS).o +obj-$(CONFIG_ACPI_APEI) += apei.o ifneq ($(CONFIG_ACPI_PROCESSOR),) obj-y += cstate.o diff --git a/arch/x86/kernel/acpi/apei.c b/arch/x86/kernel/acpi/apei.c new file mode 100644 index 000000000000..c280df6b2aa2 --- /dev/null +++ b/arch/x86/kernel/acpi/apei.c @@ -0,0 +1,62 @@ +/* + * Arch-specific APEI-related functions. + * + * 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. + */ + +#include <acpi/apei.h> + +#include <asm/mce.h> +#include <asm/tlbflush.h> + +int arch_apei_enable_cmcff(struct acpi_hest_header *hest_hdr, void *data) +{ +#ifdef CONFIG_X86_MCE + int i; + struct acpi_hest_ia_corrected *cmc; + struct acpi_hest_ia_error_bank *mc_bank; + + if (hest_hdr->type != ACPI_HEST_TYPE_IA32_CORRECTED_CHECK) + return 0; + + cmc = (struct acpi_hest_ia_corrected *)hest_hdr; + if (!cmc->enabled) + return 0; + + /* + * We expect HEST to provide a list of MC banks that report errors + * in firmware first mode. Otherwise, return non-zero value to + * indicate that we are done parsing HEST. + */ + if (!(cmc->flags & ACPI_HEST_FIRMWARE_FIRST) || + !cmc->num_hardware_banks) + return 1; + + pr_info("HEST: Enabling Firmware First mode for corrected errors.\n"); + + mc_bank = (struct acpi_hest_ia_error_bank *)(cmc + 1); + for (i = 0; i < cmc->num_hardware_banks; i++, mc_bank++) + mce_disable_bank(mc_bank->bank_number); +#endif + return 1; +} + +void arch_apei_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) +{ +#ifdef CONFIG_X86_MCE + apei_mce_report_mem_error(sev, mem_err); +#endif +} + +void arch_apei_flush_tlb_one(unsigned long addr) +{ + __flush_tlb_one(addr); +} diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 86281ffb96d6..b436fc735aa4 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -31,6 +31,7 @@ #include <linux/module.h> #include <linux/dmi.h> #include <linux/irq.h> +#include <linux/irqdomain.h> #include <linux/slab.h> #include <linux/bootmem.h> #include <linux/ioport.h> @@ -43,6 +44,7 @@ #include <asm/io.h> #include <asm/mpspec.h> #include <asm/smp.h> +#include <asm/i8259.h> #include "sleep.h" /* To include x86_acpi_suspend_lowlevel */ static int __initdata acpi_force = 0; @@ -74,10 +76,6 @@ int acpi_fix_pin2_polarity __initdata; static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; #endif -#ifndef __HAVE_ARCH_CMPXCHG -#warning ACPI uses CMPXCHG, i486 and later hardware -#endif - /* -------------------------------------------------------------------------- Boot-time Configuration -------------------------------------------------------------------------- */ @@ -97,44 +95,7 @@ static u32 isa_irq_to_gsi[NR_IRQS_LEGACY] __read_mostly = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 }; -static unsigned int gsi_to_irq(unsigned int gsi) -{ - unsigned int irq = gsi + NR_IRQS_LEGACY; - unsigned int i; - - for (i = 0; i < NR_IRQS_LEGACY; i++) { - if (isa_irq_to_gsi[i] == gsi) { - return i; - } - } - - /* Provide an identity mapping of gsi == irq - * except on truly weird platforms that have - * non isa irqs in the first 16 gsis. - */ - if (gsi >= NR_IRQS_LEGACY) - irq = gsi; - else - irq = gsi_top + gsi; - - return irq; -} - -static u32 irq_to_gsi(int irq) -{ - unsigned int gsi; - - if (irq < NR_IRQS_LEGACY) - gsi = isa_irq_to_gsi[irq]; - else if (irq < gsi_top) - gsi = irq; - else if (irq < (gsi_top + NR_IRQS_LEGACY)) - gsi = irq - gsi_top; - else - gsi = 0xffffffff; - - return gsi; -} +#define ACPI_INVALID_GSI INT_MIN /* * This is just a simple wrapper around early_ioremap(), @@ -345,11 +306,145 @@ acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long e #endif /*CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_IO_APIC +#define MP_ISA_BUS 0 + +static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, + u32 gsi) +{ + int ioapic; + int pin; + struct mpc_intsrc mp_irq; + + /* + * Convert 'gsi' to 'ioapic.pin'. + */ + ioapic = mp_find_ioapic(gsi); + if (ioapic < 0) + return; + pin = mp_find_ioapic_pin(ioapic, gsi); + + /* + * TBD: This check is for faulty timer entries, where the override + * erroneously sets the trigger to level, resulting in a HUGE + * increase of timer interrupts! + */ + if ((bus_irq == 0) && (trigger == 3)) + trigger = 1; + + mp_irq.type = MP_INTSRC; + mp_irq.irqtype = mp_INT; + mp_irq.irqflag = (trigger << 2) | polarity; + mp_irq.srcbus = MP_ISA_BUS; + mp_irq.srcbusirq = bus_irq; /* IRQ */ + mp_irq.dstapic = mpc_ioapic_id(ioapic); /* APIC ID */ + mp_irq.dstirq = pin; /* INTIN# */ + + mp_save_irq(&mp_irq); + + /* + * Reset default identity mapping if gsi is also an legacy IRQ, + * otherwise there will be more than one entry with the same GSI + * and acpi_isa_irq_to_gsi() may give wrong result. + */ + if (gsi < nr_legacy_irqs() && isa_irq_to_gsi[gsi] == gsi) + isa_irq_to_gsi[gsi] = ACPI_INVALID_GSI; + isa_irq_to_gsi[bus_irq] = gsi; +} + +static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger, + int polarity) +{ +#ifdef CONFIG_X86_MPPARSE + struct mpc_intsrc mp_irq; + struct pci_dev *pdev; + unsigned char number; + unsigned int devfn; + int ioapic; + u8 pin; + + if (!acpi_ioapic) + return 0; + if (!dev || !dev_is_pci(dev)) + return 0; + + pdev = to_pci_dev(dev); + number = pdev->bus->number; + devfn = pdev->devfn; + pin = pdev->pin; + /* print the entry should happen on mptable identically */ + mp_irq.type = MP_INTSRC; + mp_irq.irqtype = mp_INT; + mp_irq.irqflag = (trigger == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) | + (polarity == ACPI_ACTIVE_HIGH ? 1 : 3); + mp_irq.srcbus = number; + mp_irq.srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3); + ioapic = mp_find_ioapic(gsi); + mp_irq.dstapic = mpc_ioapic_id(ioapic); + mp_irq.dstirq = mp_find_ioapic_pin(ioapic, gsi); + + mp_save_irq(&mp_irq); +#endif + return 0; +} + +static int mp_register_gsi(struct device *dev, u32 gsi, int trigger, + int polarity) +{ + int irq, node; + + if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC) + return gsi; + + /* Don't set up the ACPI SCI because it's already set up */ + if (acpi_gbl_FADT.sci_interrupt == gsi) + return gsi; + + trigger = trigger == ACPI_EDGE_SENSITIVE ? 0 : 1; + polarity = polarity == ACPI_ACTIVE_HIGH ? 0 : 1; + node = dev ? dev_to_node(dev) : NUMA_NO_NODE; + if (mp_set_gsi_attr(gsi, trigger, polarity, node)) { + pr_warn("Failed to set pin attr for GSI%d\n", gsi); + return -1; + } + + irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC); + if (irq < 0) + return irq; + + if (enable_update_mptable) + mp_config_acpi_gsi(dev, gsi, trigger, polarity); + + return irq; +} + +static void mp_unregister_gsi(u32 gsi) +{ + int irq; + + if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC) + return; + + if (acpi_gbl_FADT.sci_interrupt == gsi) + return; + + irq = mp_map_gsi_to_irq(gsi, 0); + if (irq > 0) + mp_unmap_irq(irq); +} + +static struct irq_domain_ops acpi_irqdomain_ops = { + .map = mp_irqdomain_map, + .unmap = mp_irqdomain_unmap, +}; static int __init acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end) { struct acpi_madt_io_apic *ioapic = NULL; + struct ioapic_domain_cfg cfg = { + .type = IOAPIC_DOMAIN_DYNAMIC, + .ops = &acpi_irqdomain_ops, + }; ioapic = (struct acpi_madt_io_apic *)header; @@ -358,8 +453,12 @@ acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end) acpi_table_print_madt_entry(header); - mp_register_ioapic(ioapic->id, - ioapic->address, ioapic->global_irq_base); + /* Statically assign IRQ numbers for IOAPICs hosting legacy IRQs */ + if (ioapic->global_irq_base < nr_legacy_irqs()) + cfg.type = IOAPIC_DOMAIN_LEGACY; + + mp_register_ioapic(ioapic->id, ioapic->address, ioapic->global_irq_base, + &cfg); return 0; } @@ -382,11 +481,6 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger, if (acpi_sci_flags & ACPI_MADT_POLARITY_MASK) polarity = acpi_sci_flags & ACPI_MADT_POLARITY_MASK; - /* - * mp_config_acpi_legacy_irqs() already setup IRQs < 16 - * If GSI is < 16, this will update its flags, - * else it will create a new mp_irqs[] entry. - */ mp_override_legacy_irq(bus_irq, polarity, trigger, gsi); /* @@ -508,25 +602,28 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger) outb(new >> 8, 0x4d1); } -int acpi_gsi_to_irq(u32 gsi, unsigned int *irq) +int acpi_gsi_to_irq(u32 gsi, unsigned int *irqp) { - *irq = gsi_to_irq(gsi); + int irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC | IOAPIC_MAP_CHECK); -#ifdef CONFIG_X86_IO_APIC - if (acpi_irq_model == ACPI_IRQ_MODEL_IOAPIC) - setup_IO_APIC_irq_extra(gsi); -#endif + if (irq >= 0) { + *irqp = irq; + return 0; + } - return 0; + return -1; } EXPORT_SYMBOL_GPL(acpi_gsi_to_irq); int acpi_isa_irq_to_gsi(unsigned isa_irq, u32 *gsi) { - if (isa_irq >= 16) - return -1; - *gsi = irq_to_gsi(isa_irq); - return 0; + if (isa_irq < nr_legacy_irqs() && + isa_irq_to_gsi[isa_irq] != ACPI_INVALID_GSI) { + *gsi = isa_irq_to_gsi[isa_irq]; + return 0; + } + + return -1; } static int acpi_register_gsi_pic(struct device *dev, u32 gsi, @@ -546,15 +643,25 @@ static int acpi_register_gsi_pic(struct device *dev, u32 gsi, static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi, int trigger, int polarity) { + int irq = gsi; + #ifdef CONFIG_X86_IO_APIC - gsi = mp_register_gsi(dev, gsi, trigger, polarity); + irq = mp_register_gsi(dev, gsi, trigger, polarity); #endif - return gsi; + return irq; +} + +static void acpi_unregister_gsi_ioapic(u32 gsi) +{ +#ifdef CONFIG_X86_IO_APIC + mp_unregister_gsi(gsi); +#endif } int (*__acpi_register_gsi)(struct device *dev, u32 gsi, int trigger, int polarity) = acpi_register_gsi_pic; +void (*__acpi_unregister_gsi)(u32 gsi) = NULL; #ifdef CONFIG_ACPI_SLEEP int (*acpi_suspend_lowlevel)(void) = x86_acpi_suspend_lowlevel; @@ -568,32 +675,22 @@ int (*acpi_suspend_lowlevel)(void); */ int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity) { - unsigned int irq; - unsigned int plat_gsi = gsi; - - plat_gsi = (*__acpi_register_gsi)(dev, gsi, trigger, polarity); - irq = gsi_to_irq(plat_gsi); - - return irq; + return __acpi_register_gsi(dev, gsi, trigger, polarity); } EXPORT_SYMBOL_GPL(acpi_register_gsi); void acpi_unregister_gsi(u32 gsi) { + if (__acpi_unregister_gsi) + __acpi_unregister_gsi(gsi); } EXPORT_SYMBOL_GPL(acpi_unregister_gsi); -void __init acpi_set_irq_model_pic(void) -{ - acpi_irq_model = ACPI_IRQ_MODEL_PIC; - __acpi_register_gsi = acpi_register_gsi_pic; - acpi_ioapic = 0; -} - -void __init acpi_set_irq_model_ioapic(void) +static void __init acpi_set_irq_model_ioapic(void) { acpi_irq_model = ACPI_IRQ_MODEL_IOAPIC; __acpi_register_gsi = acpi_register_gsi_ioapic; + __acpi_unregister_gsi = acpi_unregister_gsi_ioapic; acpi_ioapic = 1; } @@ -829,9 +926,8 @@ static int __init early_acpi_parse_madt_lapic_addr_ovr(void) * and (optionally) overriden by a LAPIC_ADDR_OVR entry (64-bit value). */ - count = - acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_OVERRIDE, - acpi_parse_lapic_addr_ovr, 0); + count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_OVERRIDE, + acpi_parse_lapic_addr_ovr, 0); if (count < 0) { printk(KERN_ERR PREFIX "Error parsing LAPIC address override entry\n"); @@ -856,9 +952,8 @@ static int __init acpi_parse_madt_lapic_entries(void) * and (optionally) overriden by a LAPIC_ADDR_OVR entry (64-bit value). */ - count = - acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_OVERRIDE, - acpi_parse_lapic_addr_ovr, 0); + count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_OVERRIDE, + acpi_parse_lapic_addr_ovr, 0); if (count < 0) { printk(KERN_ERR PREFIX "Error parsing LAPIC address override entry\n"); @@ -886,11 +981,10 @@ static int __init acpi_parse_madt_lapic_entries(void) return count; } - x2count = - acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC_NMI, - acpi_parse_x2apic_nmi, 0); - count = - acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_NMI, acpi_parse_lapic_nmi, 0); + x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC_NMI, + acpi_parse_x2apic_nmi, 0); + count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_NMI, + acpi_parse_lapic_nmi, 0); if (count < 0 || x2count < 0) { printk(KERN_ERR PREFIX "Error parsing LAPIC NMI entry\n"); /* TBD: Cleanup to allow fallback to MPS */ @@ -901,44 +995,7 @@ static int __init acpi_parse_madt_lapic_entries(void) #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_IO_APIC -#define MP_ISA_BUS 0 - -void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi) -{ - int ioapic; - int pin; - struct mpc_intsrc mp_irq; - - /* - * Convert 'gsi' to 'ioapic.pin'. - */ - ioapic = mp_find_ioapic(gsi); - if (ioapic < 0) - return; - pin = mp_find_ioapic_pin(ioapic, gsi); - - /* - * TBD: This check is for faulty timer entries, where the override - * erroneously sets the trigger to level, resulting in a HUGE - * increase of timer interrupts! - */ - if ((bus_irq == 0) && (trigger == 3)) - trigger = 1; - - mp_irq.type = MP_INTSRC; - mp_irq.irqtype = mp_INT; - mp_irq.irqflag = (trigger << 2) | polarity; - mp_irq.srcbus = MP_ISA_BUS; - mp_irq.srcbusirq = bus_irq; /* IRQ */ - mp_irq.dstapic = mpc_ioapic_id(ioapic); /* APIC ID */ - mp_irq.dstirq = pin; /* INTIN# */ - - mp_save_irq(&mp_irq); - - isa_irq_to_gsi[bus_irq] = gsi; -} - -void __init mp_config_acpi_legacy_irqs(void) +static void __init mp_config_acpi_legacy_irqs(void) { int i; struct mpc_intsrc mp_irq; @@ -956,7 +1013,7 @@ void __init mp_config_acpi_legacy_irqs(void) * Use the default configuration for the IRQs 0-15. Unless * overridden by (MADT) interrupt source override entries. */ - for (i = 0; i < 16; i++) { + for (i = 0; i < nr_legacy_irqs(); i++) { int ioapic, pin; unsigned int dstapic; int idx; @@ -1004,84 +1061,6 @@ void __init mp_config_acpi_legacy_irqs(void) } } -static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger, - int polarity) -{ -#ifdef CONFIG_X86_MPPARSE - struct mpc_intsrc mp_irq; - struct pci_dev *pdev; - unsigned char number; - unsigned int devfn; - int ioapic; - u8 pin; - - if (!acpi_ioapic) - return 0; - if (!dev || !dev_is_pci(dev)) - return 0; - - pdev = to_pci_dev(dev); - number = pdev->bus->number; - devfn = pdev->devfn; - pin = pdev->pin; - /* print the entry should happen on mptable identically */ - mp_irq.type = MP_INTSRC; - mp_irq.irqtype = mp_INT; - mp_irq.irqflag = (trigger == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) | - (polarity == ACPI_ACTIVE_HIGH ? 1 : 3); - mp_irq.srcbus = number; - mp_irq.srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3); - ioapic = mp_find_ioapic(gsi); - mp_irq.dstapic = mpc_ioapic_id(ioapic); - mp_irq.dstirq = mp_find_ioapic_pin(ioapic, gsi); - - mp_save_irq(&mp_irq); -#endif - return 0; -} - -int mp_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity) -{ - int ioapic; - int ioapic_pin; - struct io_apic_irq_attr irq_attr; - int ret; - - if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC) - return gsi; - - /* Don't set up the ACPI SCI because it's already set up */ - if (acpi_gbl_FADT.sci_interrupt == gsi) - return gsi; - - ioapic = mp_find_ioapic(gsi); - if (ioapic < 0) { - printk(KERN_WARNING "No IOAPIC for GSI %u\n", gsi); - return gsi; - } - - ioapic_pin = mp_find_ioapic_pin(ioapic, gsi); - - if (ioapic_pin > MP_MAX_IOAPIC_PIN) { - printk(KERN_ERR "Invalid reference to IOAPIC pin " - "%d-%d\n", mpc_ioapic_id(ioapic), - ioapic_pin); - return gsi; - } - - if (enable_update_mptable) - mp_config_acpi_gsi(dev, gsi, trigger, polarity); - - set_io_apic_irq_attr(&irq_attr, ioapic, ioapic_pin, - trigger == ACPI_EDGE_SENSITIVE ? 0 : 1, - polarity == ACPI_ACTIVE_HIGH ? 0 : 1); - ret = io_apic_set_pci_routing(dev, gsi_to_irq(gsi), &irq_attr); - if (ret < 0) - gsi = INT_MIN; - - return gsi; -} - /* * Parse IOAPIC related entries in MADT * returns 0 on success, < 0 on error @@ -1111,9 +1090,8 @@ static int __init acpi_parse_madt_ioapic_entries(void) return -ENODEV; } - count = - acpi_table_parse_madt(ACPI_MADT_TYPE_IO_APIC, acpi_parse_ioapic, - MAX_IO_APICS); + count = acpi_table_parse_madt(ACPI_MADT_TYPE_IO_APIC, acpi_parse_ioapic, + MAX_IO_APICS); if (!count) { printk(KERN_ERR PREFIX "No IOAPIC entries present\n"); return -ENODEV; @@ -1122,9 +1100,8 @@ static int __init acpi_parse_madt_ioapic_entries(void) return count; } - count = - acpi_table_parse_madt(ACPI_MADT_TYPE_INTERRUPT_OVERRIDE, acpi_parse_int_src_ovr, - nr_irqs); + count = acpi_table_parse_madt(ACPI_MADT_TYPE_INTERRUPT_OVERRIDE, + acpi_parse_int_src_ovr, nr_irqs); if (count < 0) { printk(KERN_ERR PREFIX "Error parsing interrupt source overrides entry\n"); @@ -1143,9 +1120,8 @@ static int __init acpi_parse_madt_ioapic_entries(void) /* Fill in identity legacy mappings where no override */ mp_config_acpi_legacy_irqs(); - count = - acpi_table_parse_madt(ACPI_MADT_TYPE_NMI_SOURCE, acpi_parse_nmi_src, - nr_irqs); + count = acpi_table_parse_madt(ACPI_MADT_TYPE_NMI_SOURCE, + acpi_parse_nmi_src, nr_irqs); if (count < 0) { printk(KERN_ERR PREFIX "Error parsing NMI SRC entry\n"); /* TBD: Cleanup to allow fallback to MPS */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index ad28db7e6bde..67760275544b 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -67,7 +67,7 @@ EXPORT_SYMBOL_GPL(boot_cpu_physical_apicid); /* * The highest APIC ID seen during enumeration. */ -unsigned int max_physical_apicid; +static unsigned int max_physical_apicid; /* * Bitmask of physically existing CPUs: @@ -1342,17 +1342,6 @@ void setup_local_APIC(void) /* always use the value from LDR */ early_per_cpu(x86_cpu_to_logical_apicid, cpu) = logical_smp_processor_id(); - - /* - * Some NUMA implementations (NUMAQ) don't initialize apicid to - * node mapping during NUMA init. Now that logical apicid is - * guaranteed to be known, give it another chance. This is already - * a bit too late - percpu allocation has already happened without - * proper NUMA affinity. - */ - if (apic->x86_32_numa_cpu_node) - set_apicid_to_node(early_per_cpu(x86_cpu_to_apicid, cpu), - apic->x86_32_numa_cpu_node(cpu)); #endif /* @@ -2053,8 +2042,6 @@ void __init connect_bsp_APIC(void) imcr_pic_to_apic(); } #endif - if (apic->enable_apic_mode) - apic->enable_apic_mode(); } /** @@ -2451,51 +2438,6 @@ static void apic_pm_activate(void) { } #ifdef CONFIG_X86_64 -static int apic_cluster_num(void) -{ - int i, clusters, zeros; - unsigned id; - u16 *bios_cpu_apicid; - DECLARE_BITMAP(clustermap, NUM_APIC_CLUSTERS); - - bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid); - bitmap_zero(clustermap, NUM_APIC_CLUSTERS); - - for (i = 0; i < nr_cpu_ids; i++) { - /* are we being called early in kernel startup? */ - if (bios_cpu_apicid) { - id = bios_cpu_apicid[i]; - } else if (i < nr_cpu_ids) { - if (cpu_present(i)) - id = per_cpu(x86_bios_cpu_apicid, i); - else - continue; - } else - break; - - if (id != BAD_APICID) - __set_bit(APIC_CLUSTERID(id), clustermap); - } - - /* Problem: Partially populated chassis may not have CPUs in some of - * the APIC clusters they have been allocated. Only present CPUs have - * x86_bios_cpu_apicid entries, thus causing zeroes in the bitmap. - * Since clusters are allocated sequentially, count zeros only if - * they are bounded by ones. - */ - clusters = 0; - zeros = 0; - for (i = 0; i < NUM_APIC_CLUSTERS; i++) { - if (test_bit(i, clustermap)) { - clusters += 1 + zeros; - zeros = 0; - } else - ++zeros; - } - - return clusters; -} - static int multi_checked; static int multi; @@ -2540,20 +2482,7 @@ static void dmi_check_multi(void) int apic_is_clustered_box(void) { dmi_check_multi(); - if (multi) - return 1; - - if (!is_vsmp_box()) - return 0; - - /* - * ScaleMP vSMPowered boxes have one cluster per board and TSCs are - * not guaranteed to be synced between boards - */ - if (apic_cluster_num() > 1) - return 1; - - return 0; + return multi; } #endif diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index 7c1b29479513..de918c410eae 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -168,21 +168,16 @@ static struct apic apic_flat = { .disable_esr = 0, .dest_logical = APIC_DEST_LOGICAL, .check_apicid_used = NULL, - .check_apicid_present = NULL, .vector_allocation_domain = flat_vector_allocation_domain, .init_apic_ldr = flat_init_apic_ldr, .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, - .multi_timer_check = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, .apicid_to_cpu_present = NULL, - .setup_portio_remap = NULL, .check_phys_apicid_present = default_check_phys_apicid_present, - .enable_apic_mode = NULL, .phys_pkg_id = flat_phys_pkg_id, - .mps_oem_check = NULL, .get_apic_id = flat_get_apic_id, .set_apic_id = set_apic_id, @@ -196,10 +191,7 @@ static struct apic apic_flat = { .send_IPI_all = flat_send_IPI_all, .send_IPI_self = apic_send_IPI_self, - .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, - .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, .wait_for_init_deassert = false, - .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = default_inquire_remote_apic, .read = native_apic_mem_read, @@ -283,7 +275,6 @@ static struct apic apic_physflat = { .disable_esr = 0, .dest_logical = 0, .check_apicid_used = NULL, - .check_apicid_present = NULL, .vector_allocation_domain = default_vector_allocation_domain, /* not needed, but shouldn't hurt: */ @@ -291,14 +282,10 @@ static struct apic apic_physflat = { .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, - .multi_timer_check = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, .apicid_to_cpu_present = NULL, - .setup_portio_remap = NULL, .check_phys_apicid_present = default_check_phys_apicid_present, - .enable_apic_mode = NULL, .phys_pkg_id = flat_phys_pkg_id, - .mps_oem_check = NULL, .get_apic_id = flat_get_apic_id, .set_apic_id = set_apic_id, @@ -312,10 +299,7 @@ static struct apic apic_physflat = { .send_IPI_all = physflat_send_IPI_all, .send_IPI_self = apic_send_IPI_self, - .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, - .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, .wait_for_init_deassert = false, - .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = default_inquire_remote_apic, .read = native_apic_mem_read, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 8c7c98249c20..b205cdbdbe6a 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -89,16 +89,6 @@ static const struct cpumask *noop_target_cpus(void) return cpumask_of(0); } -static unsigned long noop_check_apicid_used(physid_mask_t *map, int apicid) -{ - return physid_isset(apicid, *map); -} - -static unsigned long noop_check_apicid_present(int bit) -{ - return physid_isset(bit, phys_cpu_present_map); -} - static void noop_vector_allocation_domain(int cpu, struct cpumask *retmask, const struct cpumask *mask) { @@ -133,27 +123,21 @@ struct apic apic_noop = { .target_cpus = noop_target_cpus, .disable_esr = 0, .dest_logical = APIC_DEST_LOGICAL, - .check_apicid_used = noop_check_apicid_used, - .check_apicid_present = noop_check_apicid_present, + .check_apicid_used = default_check_apicid_used, .vector_allocation_domain = noop_vector_allocation_domain, .init_apic_ldr = noop_init_apic_ldr, .ioapic_phys_id_map = default_ioapic_phys_id_map, .setup_apic_routing = NULL, - .multi_timer_check = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, .apicid_to_cpu_present = physid_set_mask_of_physid, - .setup_portio_remap = NULL, .check_phys_apicid_present = default_check_phys_apicid_present, - .enable_apic_mode = NULL, .phys_pkg_id = noop_phys_pkg_id, - .mps_oem_check = NULL, - .get_apic_id = noop_get_apic_id, .set_apic_id = NULL, .apic_id_mask = 0x0F << 24, @@ -168,12 +152,7 @@ struct apic apic_noop = { .wakeup_secondary_cpu = noop_wakeup_secondary_cpu, - /* should be safe */ - .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, - .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = false, - .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = NULL, .read = noop_apic_read, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index a5b45df8bc88..ae915391ebec 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -217,21 +217,16 @@ static const struct apic apic_numachip __refconst = { .disable_esr = 0, .dest_logical = 0, .check_apicid_used = NULL, - .check_apicid_present = NULL, .vector_allocation_domain = default_vector_allocation_domain, .init_apic_ldr = flat_init_apic_ldr, .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, - .multi_timer_check = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, .apicid_to_cpu_present = NULL, - .setup_portio_remap = NULL, .check_phys_apicid_present = default_check_phys_apicid_present, - .enable_apic_mode = NULL, .phys_pkg_id = numachip_phys_pkg_id, - .mps_oem_check = NULL, .get_apic_id = get_apic_id, .set_apic_id = set_apic_id, @@ -246,10 +241,7 @@ static const struct apic apic_numachip __refconst = { .send_IPI_self = numachip_send_IPI_self, .wakeup_secondary_cpu = numachip_wakeup_secondary, - .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, - .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, .wait_for_init_deassert = false, - .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = NULL, /* REMRD not supported */ .read = native_apic_mem_read, diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index e4840aa7a255..c4a8d63f8220 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -31,11 +31,6 @@ static unsigned long bigsmp_check_apicid_used(physid_mask_t *map, int apicid) return 0; } -static unsigned long bigsmp_check_apicid_present(int bit) -{ - return 1; -} - static int bigsmp_early_logical_apicid(int cpu) { /* on bigsmp, logical apicid is the same as physical */ @@ -168,21 +163,16 @@ static struct apic apic_bigsmp = { .disable_esr = 1, .dest_logical = 0, .check_apicid_used = bigsmp_check_apicid_used, - .check_apicid_present = bigsmp_check_apicid_present, .vector_allocation_domain = default_vector_allocation_domain, .init_apic_ldr = bigsmp_init_apic_ldr, .ioapic_phys_id_map = bigsmp_ioapic_phys_id_map, .setup_apic_routing = bigsmp_setup_apic_routing, - .multi_timer_check = NULL, .cpu_present_to_apicid = bigsmp_cpu_present_to_apicid, .apicid_to_cpu_present = physid_set_mask_of_physid, - .setup_portio_remap = NULL, .check_phys_apicid_present = bigsmp_check_phys_apicid_present, - .enable_apic_mode = NULL, .phys_pkg_id = bigsmp_phys_pkg_id, - .mps_oem_check = NULL, .get_apic_id = bigsmp_get_apic_id, .set_apic_id = NULL, @@ -196,11 +186,7 @@ static struct apic apic_bigsmp = { .send_IPI_all = bigsmp_send_IPI_all, .send_IPI_self = default_send_IPI_self, - .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, - .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = true, - .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = default_inquire_remote_apic, .read = native_apic_mem_read, diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 81e08eff05ee..29290f554e79 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -31,6 +31,7 @@ #include <linux/acpi.h> #include <linux/module.h> #include <linux/syscore_ops.h> +#include <linux/irqdomain.h> #include <linux/msi.h> #include <linux/htirq.h> #include <linux/freezer.h> @@ -62,6 +63,16 @@ #define __apicdebuginit(type) static type __init +#define for_each_ioapic(idx) \ + for ((idx) = 0; (idx) < nr_ioapics; (idx)++) +#define for_each_ioapic_reverse(idx) \ + for ((idx) = nr_ioapics - 1; (idx) >= 0; (idx)--) +#define for_each_pin(idx, pin) \ + for ((pin) = 0; (pin) < ioapics[(idx)].nr_registers; (pin)++) +#define for_each_ioapic_pin(idx, pin) \ + for_each_ioapic((idx)) \ + for_each_pin((idx), (pin)) + #define for_each_irq_pin(entry, head) \ for (entry = head; entry; entry = entry->next) @@ -73,6 +84,17 @@ int sis_apic_bug = -1; static DEFINE_RAW_SPINLOCK(ioapic_lock); static DEFINE_RAW_SPINLOCK(vector_lock); +static DEFINE_MUTEX(ioapic_mutex); +static unsigned int ioapic_dynirq_base; +static int ioapic_initialized; + +struct mp_pin_info { + int trigger; + int polarity; + int node; + int set; + u32 count; +}; static struct ioapic { /* @@ -87,7 +109,9 @@ static struct ioapic { struct mpc_ioapic mp_config; /* IO APIC gsi routing info */ struct mp_ioapic_gsi gsi_config; - DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1); + struct ioapic_domain_cfg irqdomain_cfg; + struct irq_domain *irqdomain; + struct mp_pin_info *pin_info; } ioapics[MAX_IO_APICS]; #define mpc_ioapic_ver(ioapic_idx) ioapics[ioapic_idx].mp_config.apicver @@ -107,6 +131,41 @@ struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic_idx) return &ioapics[ioapic_idx].gsi_config; } +static inline int mp_ioapic_pin_count(int ioapic) +{ + struct mp_ioapic_gsi *gsi_cfg = mp_ioapic_gsi_routing(ioapic); + + return gsi_cfg->gsi_end - gsi_cfg->gsi_base + 1; +} + +u32 mp_pin_to_gsi(int ioapic, int pin) +{ + return mp_ioapic_gsi_routing(ioapic)->gsi_base + pin; +} + +/* + * Initialize all legacy IRQs and all pins on the first IOAPIC + * if we have legacy interrupt controller. Kernel boot option "pirq=" + * may rely on non-legacy pins on the first IOAPIC. + */ +static inline int mp_init_irq_at_boot(int ioapic, int irq) +{ + if (!nr_legacy_irqs()) + return 0; + + return ioapic == 0 || (irq >= 0 && irq < nr_legacy_irqs()); +} + +static inline struct mp_pin_info *mp_pin_info(int ioapic_idx, int pin) +{ + return ioapics[ioapic_idx].pin_info + pin; +} + +static inline struct irq_domain *mp_ioapic_irqdomain(int ioapic) +{ + return ioapics[ioapic].irqdomain; +} + int nr_ioapics; /* The one past the highest gsi number used */ @@ -118,9 +177,6 @@ struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES]; /* # of MP IRQ source entries */ int mp_irq_entries; -/* GSI interrupts */ -static int nr_irqs_gsi = NR_IRQS_LEGACY; - #ifdef CONFIG_EISA int mp_bus_id_to_type[MAX_MP_BUSSES]; #endif @@ -149,8 +205,7 @@ static int __init parse_noapic(char *str) } early_param("noapic", parse_noapic); -static int io_apic_setup_irq_pin(unsigned int irq, int node, - struct io_apic_irq_attr *attr); +static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node); /* Will be called in mpparse/acpi/sfi codes for saving IRQ info */ void mp_save_irq(struct mpc_intsrc *m) @@ -182,19 +237,15 @@ static struct irq_pin_list *alloc_irq_pin_list(int node) return kzalloc_node(sizeof(struct irq_pin_list), GFP_KERNEL, node); } - -/* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */ -static struct irq_cfg irq_cfgx[NR_IRQS_LEGACY]; - int __init arch_early_irq_init(void) { struct irq_cfg *cfg; - int count, node, i; + int i, node = cpu_to_node(0); - if (!legacy_pic->nr_legacy_irqs) + if (!nr_legacy_irqs()) io_apic_irqs = ~0UL; - for (i = 0; i < nr_ioapics; i++) { + for_each_ioapic(i) { ioapics[i].saved_registers = kzalloc(sizeof(struct IO_APIC_route_entry) * ioapics[i].nr_registers, GFP_KERNEL); @@ -202,28 +253,20 @@ int __init arch_early_irq_init(void) pr_err("IOAPIC %d: suspend/resume impossible!\n", i); } - cfg = irq_cfgx; - count = ARRAY_SIZE(irq_cfgx); - node = cpu_to_node(0); - - for (i = 0; i < count; i++) { - irq_set_chip_data(i, &cfg[i]); - zalloc_cpumask_var_node(&cfg[i].domain, GFP_KERNEL, node); - zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_KERNEL, node); - /* - * For legacy IRQ's, start with assigning irq0 to irq15 to - * IRQ0_VECTOR to IRQ15_VECTOR for all cpu's. - */ - if (i < legacy_pic->nr_legacy_irqs) { - cfg[i].vector = IRQ0_VECTOR + i; - cpumask_setall(cfg[i].domain); - } + /* + * For legacy IRQ's, start with assigning irq0 to irq15 to + * IRQ0_VECTOR to IRQ15_VECTOR for all cpu's. + */ + for (i = 0; i < nr_legacy_irqs(); i++) { + cfg = alloc_irq_and_cfg_at(i, node); + cfg->vector = IRQ0_VECTOR + i; + cpumask_setall(cfg->domain); } return 0; } -static struct irq_cfg *irq_cfg(unsigned int irq) +static inline struct irq_cfg *irq_cfg(unsigned int irq) { return irq_get_chip_data(irq); } @@ -265,7 +308,7 @@ static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node) if (res < 0) { if (res != -EEXIST) return NULL; - cfg = irq_get_chip_data(at); + cfg = irq_cfg(at); if (cfg) return cfg; } @@ -425,6 +468,21 @@ static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pi return 0; } +static void __remove_pin_from_irq(struct irq_cfg *cfg, int apic, int pin) +{ + struct irq_pin_list **last, *entry; + + last = &cfg->irq_2_pin; + for_each_irq_pin(entry, cfg->irq_2_pin) + if (entry->apic == apic && entry->pin == pin) { + *last = entry->next; + kfree(entry); + return; + } else { + last = &entry->next; + } +} + static void add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin) { if (__add_pin_to_irq_node(cfg, node, apic, pin)) @@ -627,9 +685,8 @@ static void clear_IO_APIC (void) { int apic, pin; - for (apic = 0; apic < nr_ioapics; apic++) - for (pin = 0; pin < ioapics[apic].nr_registers; pin++) - clear_IO_APIC_pin(apic, pin); + for_each_ioapic_pin(apic, pin) + clear_IO_APIC_pin(apic, pin); } #ifdef CONFIG_X86_32 @@ -678,13 +735,13 @@ int save_ioapic_entries(void) int apic, pin; int err = 0; - for (apic = 0; apic < nr_ioapics; apic++) { + for_each_ioapic(apic) { if (!ioapics[apic].saved_registers) { err = -ENOMEM; continue; } - for (pin = 0; pin < ioapics[apic].nr_registers; pin++) + for_each_pin(apic, pin) ioapics[apic].saved_registers[pin] = ioapic_read_entry(apic, pin); } @@ -699,11 +756,11 @@ void mask_ioapic_entries(void) { int apic, pin; - for (apic = 0; apic < nr_ioapics; apic++) { + for_each_ioapic(apic) { if (!ioapics[apic].saved_registers) continue; - for (pin = 0; pin < ioapics[apic].nr_registers; pin++) { + for_each_pin(apic, pin) { struct IO_APIC_route_entry entry; entry = ioapics[apic].saved_registers[pin]; @@ -722,11 +779,11 @@ int restore_ioapic_entries(void) { int apic, pin; - for (apic = 0; apic < nr_ioapics; apic++) { + for_each_ioapic(apic) { if (!ioapics[apic].saved_registers) continue; - for (pin = 0; pin < ioapics[apic].nr_registers; pin++) + for_each_pin(apic, pin) ioapic_write_entry(apic, pin, ioapics[apic].saved_registers[pin]); } @@ -785,7 +842,7 @@ static int __init find_isa_irq_apic(int irq, int type) if (i < mp_irq_entries) { int ioapic_idx; - for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++) + for_each_ioapic(ioapic_idx) if (mpc_ioapic_id(ioapic_idx) == mp_irqs[i].dstapic) return ioapic_idx; } @@ -799,7 +856,7 @@ static int __init find_isa_irq_apic(int irq, int type) */ static int EISA_ELCR(unsigned int irq) { - if (irq < legacy_pic->nr_legacy_irqs) { + if (irq < nr_legacy_irqs()) { unsigned int port = 0x4d0 + (irq >> 3); return (inb(port) >> (irq & 7)) & 1; } @@ -939,29 +996,101 @@ static int irq_trigger(int idx) return trigger; } -static int pin_2_irq(int idx, int apic, int pin) +static int alloc_irq_from_domain(struct irq_domain *domain, u32 gsi, int pin) +{ + int irq = -1; + int ioapic = (int)(long)domain->host_data; + int type = ioapics[ioapic].irqdomain_cfg.type; + + switch (type) { + case IOAPIC_DOMAIN_LEGACY: + /* + * Dynamically allocate IRQ number for non-ISA IRQs in the first 16 + * GSIs on some weird platforms. + */ + if (gsi < nr_legacy_irqs()) + irq = irq_create_mapping(domain, pin); + else if (irq_create_strict_mappings(domain, gsi, pin, 1) == 0) + irq = gsi; + break; + case IOAPIC_DOMAIN_STRICT: + if (irq_create_strict_mappings(domain, gsi, pin, 1) == 0) + irq = gsi; + break; + case IOAPIC_DOMAIN_DYNAMIC: + irq = irq_create_mapping(domain, pin); + break; + default: + WARN(1, "ioapic: unknown irqdomain type %d\n", type); + break; + } + + return irq > 0 ? irq : -1; +} + +static int mp_map_pin_to_irq(u32 gsi, int idx, int ioapic, int pin, + unsigned int flags) { int irq; - int bus = mp_irqs[idx].srcbus; - struct mp_ioapic_gsi *gsi_cfg = mp_ioapic_gsi_routing(apic); + struct irq_domain *domain = mp_ioapic_irqdomain(ioapic); + struct mp_pin_info *info = mp_pin_info(ioapic, pin); + + if (!domain) + return -1; + + mutex_lock(&ioapic_mutex); /* - * Debugging check, we are in big trouble if this message pops up! + * Don't use irqdomain to manage ISA IRQs because there may be + * multiple IOAPIC pins sharing the same ISA IRQ number and + * irqdomain only supports 1:1 mapping between IOAPIC pin and + * IRQ number. A typical IOAPIC has 24 pins, pin 0-15 are used + * for legacy IRQs and pin 16-23 are used for PCI IRQs (PIRQ A-H). + * When ACPI is disabled, only legacy IRQ numbers (IRQ0-15) are + * available, and some BIOSes may use MP Interrupt Source records + * to override IRQ numbers for PIRQs instead of reprogramming + * the interrupt routing logic. Thus there may be multiple pins + * sharing the same legacy IRQ number when ACPI is disabled. */ - if (mp_irqs[idx].dstirq != pin) - pr_err("broken BIOS or MPTABLE parser, ayiee!!\n"); - - if (test_bit(bus, mp_bus_not_pci)) { + if (idx >= 0 && test_bit(mp_irqs[idx].srcbus, mp_bus_not_pci)) { irq = mp_irqs[idx].srcbusirq; + if (flags & IOAPIC_MAP_ALLOC) { + if (info->count == 0 && + mp_irqdomain_map(domain, irq, pin) != 0) + irq = -1; + + /* special handling for timer IRQ0 */ + if (irq == 0) + info->count++; + } } else { - u32 gsi = gsi_cfg->gsi_base + pin; + irq = irq_find_mapping(domain, pin); + if (irq <= 0 && (flags & IOAPIC_MAP_ALLOC)) + irq = alloc_irq_from_domain(domain, gsi, pin); + } - if (gsi >= NR_IRQS_LEGACY) - irq = gsi; - else - irq = gsi_top + gsi; + if (flags & IOAPIC_MAP_ALLOC) { + if (irq > 0) + info->count++; + else if (info->count == 0) + info->set = 0; } + mutex_unlock(&ioapic_mutex); + + return irq > 0 ? irq : -1; +} + +static int pin_2_irq(int idx, int ioapic, int pin, unsigned int flags) +{ + u32 gsi = mp_pin_to_gsi(ioapic, pin); + + /* + * Debugging check, we are in big trouble if this message pops up! + */ + if (mp_irqs[idx].dstirq != pin) + pr_err("broken BIOS or MPTABLE parser, ayiee!!\n"); + #ifdef CONFIG_X86_32 /* * PCI IRQ command line redirection. Yes, limits are hardcoded. @@ -972,16 +1101,58 @@ static int pin_2_irq(int idx, int apic, int pin) apic_printk(APIC_VERBOSE, KERN_DEBUG "disabling PIRQ%d\n", pin-16); } else { - irq = pirq_entries[pin-16]; + int irq = pirq_entries[pin-16]; apic_printk(APIC_VERBOSE, KERN_DEBUG "using PIRQ%d -> IRQ %d\n", pin-16, irq); + return irq; } } } #endif - return irq; + return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags); +} + +int mp_map_gsi_to_irq(u32 gsi, unsigned int flags) +{ + int ioapic, pin, idx; + + ioapic = mp_find_ioapic(gsi); + if (ioapic < 0) + return -1; + + pin = mp_find_ioapic_pin(ioapic, gsi); + idx = find_irq_entry(ioapic, pin, mp_INT); + if ((flags & IOAPIC_MAP_CHECK) && idx < 0) + return -1; + + return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags); +} + +void mp_unmap_irq(int irq) +{ + struct irq_data *data = irq_get_irq_data(irq); + struct mp_pin_info *info; + int ioapic, pin; + + if (!data || !data->domain) + return; + + ioapic = (int)(long)data->domain->host_data; + pin = (int)data->hwirq; + info = mp_pin_info(ioapic, pin); + + mutex_lock(&ioapic_mutex); + if (--info->count == 0) { + info->set = 0; + if (irq < nr_legacy_irqs() && + ioapics[ioapic].irqdomain_cfg.type == IOAPIC_DOMAIN_LEGACY) + mp_irqdomain_unmap(data->domain, irq); + else + irq_dispose_mapping(irq); + } + mutex_unlock(&ioapic_mutex); } /* @@ -991,7 +1162,7 @@ static int pin_2_irq(int idx, int apic, int pin) int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin, struct io_apic_irq_attr *irq_attr) { - int ioapic_idx, i, best_guess = -1; + int irq, i, best_ioapic = -1, best_idx = -1; apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n", @@ -1001,44 +1172,56 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin, "PCI BIOS passed nonexistent PCI bus %d!\n", bus); return -1; } + for (i = 0; i < mp_irq_entries; i++) { int lbus = mp_irqs[i].srcbus; + int ioapic_idx, found = 0; - for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++) + if (bus != lbus || mp_irqs[i].irqtype != mp_INT || + slot != ((mp_irqs[i].srcbusirq >> 2) & 0x1f)) + continue; + + for_each_ioapic(ioapic_idx) if (mpc_ioapic_id(ioapic_idx) == mp_irqs[i].dstapic || - mp_irqs[i].dstapic == MP_APIC_ALL) + mp_irqs[i].dstapic == MP_APIC_ALL) { + found = 1; break; + } + if (!found) + continue; - if (!test_bit(lbus, mp_bus_not_pci) && - !mp_irqs[i].irqtype && - (bus == lbus) && - (slot == ((mp_irqs[i].srcbusirq >> 2) & 0x1f))) { - int irq = pin_2_irq(i, ioapic_idx, mp_irqs[i].dstirq); + /* Skip ISA IRQs */ + irq = pin_2_irq(i, ioapic_idx, mp_irqs[i].dstirq, 0); + if (irq > 0 && !IO_APIC_IRQ(irq)) + continue; - if (!(ioapic_idx || IO_APIC_IRQ(irq))) - continue; + if (pin == (mp_irqs[i].srcbusirq & 3)) { + best_idx = i; + best_ioapic = ioapic_idx; + goto out; + } - if (pin == (mp_irqs[i].srcbusirq & 3)) { - set_io_apic_irq_attr(irq_attr, ioapic_idx, - mp_irqs[i].dstirq, - irq_trigger(i), - irq_polarity(i)); - return irq; - } - /* - * Use the first all-but-pin matching entry as a - * best-guess fuzzy result for broken mptables. - */ - if (best_guess < 0) { - set_io_apic_irq_attr(irq_attr, ioapic_idx, - mp_irqs[i].dstirq, - irq_trigger(i), - irq_polarity(i)); - best_guess = irq; - } + /* + * Use the first all-but-pin matching entry as a + * best-guess fuzzy result for broken mptables. + */ + if (best_idx < 0) { + best_idx = i; + best_ioapic = ioapic_idx; } } - return best_guess; + if (best_idx < 0) + return -1; + +out: + irq = pin_2_irq(best_idx, best_ioapic, mp_irqs[best_idx].dstirq, + IOAPIC_MAP_ALLOC); + if (irq > 0) + set_io_apic_irq_attr(irq_attr, best_ioapic, + mp_irqs[best_idx].dstirq, + irq_trigger(best_idx), + irq_polarity(best_idx)); + return irq; } EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector); @@ -1198,7 +1381,7 @@ void __setup_vector_irq(int cpu) raw_spin_lock(&vector_lock); /* Mark the inuse vectors */ for_each_active_irq(irq) { - cfg = irq_get_chip_data(irq); + cfg = irq_cfg(irq); if (!cfg) continue; @@ -1227,12 +1410,10 @@ static inline int IO_APIC_irq_trigger(int irq) { int apic, idx, pin; - for (apic = 0; apic < nr_ioapics; apic++) { - for (pin = 0; pin < ioapics[apic].nr_registers; pin++) { - idx = find_irq_entry(apic, pin, mp_INT); - if ((idx != -1) && (irq == pin_2_irq(idx, apic, pin))) - return irq_trigger(idx); - } + for_each_ioapic_pin(apic, pin) { + idx = find_irq_entry(apic, pin, mp_INT); + if ((idx != -1) && (irq == pin_2_irq(idx, apic, pin, 0))) + return irq_trigger(idx); } /* * nonexistent IRQs are edge default @@ -1330,95 +1511,29 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg, } ioapic_register_intr(irq, cfg, attr->trigger); - if (irq < legacy_pic->nr_legacy_irqs) + if (irq < nr_legacy_irqs()) legacy_pic->mask(irq); ioapic_write_entry(attr->ioapic, attr->ioapic_pin, entry); } -static bool __init io_apic_pin_not_connected(int idx, int ioapic_idx, int pin) -{ - if (idx != -1) - return false; - - apic_printk(APIC_VERBOSE, KERN_DEBUG " apic %d pin %d not connected\n", - mpc_ioapic_id(ioapic_idx), pin); - return true; -} - -static void __init __io_apic_setup_irqs(unsigned int ioapic_idx) -{ - int idx, node = cpu_to_node(0); - struct io_apic_irq_attr attr; - unsigned int pin, irq; - - for (pin = 0; pin < ioapics[ioapic_idx].nr_registers; pin++) { - idx = find_irq_entry(ioapic_idx, pin, mp_INT); - if (io_apic_pin_not_connected(idx, ioapic_idx, pin)) - continue; - - irq = pin_2_irq(idx, ioapic_idx, pin); - - if ((ioapic_idx > 0) && (irq > 16)) - continue; - - /* - * Skip the timer IRQ if there's a quirk handler - * installed and if it returns 1: - */ - if (apic->multi_timer_check && - apic->multi_timer_check(ioapic_idx, irq)) - continue; - - set_io_apic_irq_attr(&attr, ioapic_idx, pin, irq_trigger(idx), - irq_polarity(idx)); - - io_apic_setup_irq_pin(irq, node, &attr); - } -} - static void __init setup_IO_APIC_irqs(void) { - unsigned int ioapic_idx; + unsigned int ioapic, pin; + int idx; apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n"); - for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++) - __io_apic_setup_irqs(ioapic_idx); -} - -/* - * for the gsit that is not in first ioapic - * but could not use acpi_register_gsi() - * like some special sci in IBM x3330 - */ -void setup_IO_APIC_irq_extra(u32 gsi) -{ - int ioapic_idx = 0, pin, idx, irq, node = cpu_to_node(0); - struct io_apic_irq_attr attr; - - /* - * Convert 'gsi' to 'ioapic.pin'. - */ - ioapic_idx = mp_find_ioapic(gsi); - if (ioapic_idx < 0) - return; - - pin = mp_find_ioapic_pin(ioapic_idx, gsi); - idx = find_irq_entry(ioapic_idx, pin, mp_INT); - if (idx == -1) - return; - - irq = pin_2_irq(idx, ioapic_idx, pin); - - /* Only handle the non legacy irqs on secondary ioapics */ - if (ioapic_idx == 0 || irq < NR_IRQS_LEGACY) - return; - - set_io_apic_irq_attr(&attr, ioapic_idx, pin, irq_trigger(idx), - irq_polarity(idx)); - - io_apic_setup_irq_pin_once(irq, node, &attr); + for_each_ioapic_pin(ioapic, pin) { + idx = find_irq_entry(ioapic, pin, mp_INT); + if (idx < 0) + apic_printk(APIC_VERBOSE, + KERN_DEBUG " apic %d pin %d not connected\n", + mpc_ioapic_id(ioapic), pin); + else + pin_2_irq(idx, ioapic, pin, + ioapic ? 0 : IOAPIC_MAP_ALLOC); + } } /* @@ -1586,7 +1701,7 @@ __apicdebuginit(void) print_IO_APICs(void) struct irq_chip *chip; printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries); - for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++) + for_each_ioapic(ioapic_idx) printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n", mpc_ioapic_id(ioapic_idx), ioapics[ioapic_idx].nr_registers); @@ -1597,7 +1712,7 @@ __apicdebuginit(void) print_IO_APICs(void) */ printk(KERN_INFO "testing the IO APIC.......................\n"); - for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++) + for_each_ioapic(ioapic_idx) print_IO_APIC(ioapic_idx); printk(KERN_DEBUG "IRQ to pin mappings:\n"); @@ -1608,7 +1723,7 @@ __apicdebuginit(void) print_IO_APICs(void) if (chip != &ioapic_chip) continue; - cfg = irq_get_chip_data(irq); + cfg = irq_cfg(irq); if (!cfg) continue; entry = cfg->irq_2_pin; @@ -1758,7 +1873,7 @@ __apicdebuginit(void) print_PIC(void) unsigned int v; unsigned long flags; - if (!legacy_pic->nr_legacy_irqs) + if (!nr_legacy_irqs()) return; printk(KERN_DEBUG "\nprinting PIC contents\n"); @@ -1828,26 +1943,22 @@ static struct { int pin, apic; } ioapic_i8259 = { -1, -1 }; void __init enable_IO_APIC(void) { int i8259_apic, i8259_pin; - int apic; + int apic, pin; - if (!legacy_pic->nr_legacy_irqs) + if (!nr_legacy_irqs()) return; - for(apic = 0; apic < nr_ioapics; apic++) { - int pin; + for_each_ioapic_pin(apic, pin) { /* See if any of the pins is in ExtINT mode */ - for (pin = 0; pin < ioapics[apic].nr_registers; pin++) { - struct IO_APIC_route_entry entry; - entry = ioapic_read_entry(apic, pin); + struct IO_APIC_route_entry entry = ioapic_read_entry(apic, pin); - /* If the interrupt line is enabled and in ExtInt mode - * I have found the pin where the i8259 is connected. - */ - if ((entry.mask == 0) && (entry.delivery_mode == dest_ExtINT)) { - ioapic_i8259.apic = apic; - ioapic_i8259.pin = pin; - goto found_i8259; - } + /* If the interrupt line is enabled and in ExtInt mode + * I have found the pin where the i8259 is connected. + */ + if ((entry.mask == 0) && (entry.delivery_mode == dest_ExtINT)) { + ioapic_i8259.apic = apic; + ioapic_i8259.pin = pin; + goto found_i8259; } } found_i8259: @@ -1919,7 +2030,7 @@ void disable_IO_APIC(void) */ clear_IO_APIC(); - if (!legacy_pic->nr_legacy_irqs) + if (!nr_legacy_irqs()) return; x86_io_apic_ops.disable(); @@ -1950,7 +2061,7 @@ void __init setup_ioapic_ids_from_mpc_nocheck(void) /* * Set the IOAPIC ID to the value stored in the MPC table. */ - for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++) { + for_each_ioapic(ioapic_idx) { /* Read the register 0 value */ raw_spin_lock_irqsave(&ioapic_lock, flags); reg_00.raw = io_apic_read(ioapic_idx, 0); @@ -2123,7 +2234,7 @@ static unsigned int startup_ioapic_irq(struct irq_data *data) unsigned long flags; raw_spin_lock_irqsave(&ioapic_lock, flags); - if (irq < legacy_pic->nr_legacy_irqs) { + if (irq < nr_legacy_irqs()) { legacy_pic->mask(irq); if (legacy_pic->irq_pending(irq)) was_pending = 1; @@ -2225,7 +2336,7 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) apic->send_IPI_self(IRQ_MOVE_CLEANUP_VECTOR); goto unlock; } - __this_cpu_write(vector_irq[vector], -1); + __this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED); unlock: raw_spin_unlock(&desc->lock); } @@ -2253,7 +2364,7 @@ static void irq_complete_move(struct irq_cfg *cfg) void irq_force_complete_move(int irq) { - struct irq_cfg *cfg = irq_get_chip_data(irq); + struct irq_cfg *cfg = irq_cfg(irq); if (!cfg) return; @@ -2514,26 +2625,15 @@ static inline void init_IO_APIC_traps(void) struct irq_cfg *cfg; unsigned int irq; - /* - * NOTE! The local APIC isn't very good at handling - * multiple interrupts at the same interrupt level. - * As the interrupt level is determined by taking the - * vector number and shifting that right by 4, we - * want to spread these out a bit so that they don't - * all fall in the same interrupt level. - * - * Also, we've got to be careful not to trash gate - * 0x80, because int 0x80 is hm, kind of importantish. ;) - */ for_each_active_irq(irq) { - cfg = irq_get_chip_data(irq); + cfg = irq_cfg(irq); if (IO_APIC_IRQ(irq) && cfg && !cfg->vector) { /* * Hmm.. We don't have an entry for this, * so default to an old-fashioned 8259 * interrupt if we can.. */ - if (irq < legacy_pic->nr_legacy_irqs) + if (irq < nr_legacy_irqs()) legacy_pic->make_irq(irq); else /* Strange. Oh, well.. */ @@ -2649,8 +2749,6 @@ static int __init disable_timer_pin_setup(char *arg) } early_param("disable_timer_pin_1", disable_timer_pin_setup); -int timer_through_8259 __initdata; - /* * This code may look a bit paranoid, but it's supposed to cooperate with * a wide range of boards and BIOS bugs. Fortunately only the timer IRQ @@ -2661,7 +2759,7 @@ int timer_through_8259 __initdata; */ static inline void __init check_timer(void) { - struct irq_cfg *cfg = irq_get_chip_data(0); + struct irq_cfg *cfg = irq_cfg(0); int node = cpu_to_node(0); int apic1, pin1, apic2, pin2; unsigned long flags; @@ -2755,7 +2853,6 @@ static inline void __init check_timer(void) legacy_pic->unmask(0); if (timer_irq_works()) { apic_printk(APIC_QUIET, KERN_INFO "....... works.\n"); - timer_through_8259 = 1; goto out; } /* @@ -2827,15 +2924,54 @@ out: */ #define PIC_IRQS (1UL << PIC_CASCADE_IR) +static int mp_irqdomain_create(int ioapic) +{ + size_t size; + int hwirqs = mp_ioapic_pin_count(ioapic); + struct ioapic *ip = &ioapics[ioapic]; + struct ioapic_domain_cfg *cfg = &ip->irqdomain_cfg; + struct mp_ioapic_gsi *gsi_cfg = mp_ioapic_gsi_routing(ioapic); + + size = sizeof(struct mp_pin_info) * mp_ioapic_pin_count(ioapic); + ip->pin_info = kzalloc(size, GFP_KERNEL); + if (!ip->pin_info) + return -ENOMEM; + + if (cfg->type == IOAPIC_DOMAIN_INVALID) + return 0; + + ip->irqdomain = irq_domain_add_linear(cfg->dev, hwirqs, cfg->ops, + (void *)(long)ioapic); + if(!ip->irqdomain) { + kfree(ip->pin_info); + ip->pin_info = NULL; + return -ENOMEM; + } + + if (cfg->type == IOAPIC_DOMAIN_LEGACY || + cfg->type == IOAPIC_DOMAIN_STRICT) + ioapic_dynirq_base = max(ioapic_dynirq_base, + gsi_cfg->gsi_end + 1); + + if (gsi_cfg->gsi_base == 0) + irq_set_default_host(ip->irqdomain); + + return 0; +} + void __init setup_IO_APIC(void) { + int ioapic; /* * calling enable_IO_APIC() is moved to setup_local_APIC for BP */ - io_apic_irqs = legacy_pic->nr_legacy_irqs ? ~PIC_IRQS : ~0UL; + io_apic_irqs = nr_legacy_irqs() ? ~PIC_IRQS : ~0UL; apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n"); + for_each_ioapic(ioapic) + BUG_ON(mp_irqdomain_create(ioapic)); + /* * Set up IO-APIC IRQ routing. */ @@ -2844,8 +2980,10 @@ void __init setup_IO_APIC(void) sync_Arb_IDs(); setup_IO_APIC_irqs(); init_IO_APIC_traps(); - if (legacy_pic->nr_legacy_irqs) + if (nr_legacy_irqs()) check_timer(); + + ioapic_initialized = 1; } /* @@ -2880,7 +3018,7 @@ static void ioapic_resume(void) { int ioapic_idx; - for (ioapic_idx = nr_ioapics - 1; ioapic_idx >= 0; ioapic_idx--) + for_each_ioapic_reverse(ioapic_idx) resume_ioapic_id(ioapic_idx); restore_ioapic_entries(); @@ -2926,7 +3064,7 @@ int arch_setup_hwirq(unsigned int irq, int node) void arch_teardown_hwirq(unsigned int irq) { - struct irq_cfg *cfg = irq_get_chip_data(irq); + struct irq_cfg *cfg = irq_cfg(irq); unsigned long flags; free_remapped_irq(irq); @@ -3053,7 +3191,7 @@ int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, if (!irq_offset) write_msi_msg(irq, &msg); - setup_remapped_irq(irq, irq_get_chip_data(irq), chip); + setup_remapped_irq(irq, irq_cfg(irq), chip); irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge"); @@ -3192,7 +3330,7 @@ int default_setup_hpet_msi(unsigned int irq, unsigned int id) hpet_msi_write(irq_get_handler_data(irq), &msg); irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - setup_remapped_irq(irq, irq_get_chip_data(irq), chip); + setup_remapped_irq(irq, irq_cfg(irq), chip); irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge"); return 0; @@ -3303,27 +3441,6 @@ io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr) return ret; } -int io_apic_setup_irq_pin_once(unsigned int irq, int node, - struct io_apic_irq_attr *attr) -{ - unsigned int ioapic_idx = attr->ioapic, pin = attr->ioapic_pin; - int ret; - struct IO_APIC_route_entry orig_entry; - - /* Avoid redundant programming */ - if (test_bit(pin, ioapics[ioapic_idx].pin_programmed)) { - pr_debug("Pin %d-%d already programmed\n", mpc_ioapic_id(ioapic_idx), pin); - orig_entry = ioapic_read_entry(attr->ioapic, pin); - if (attr->trigger == orig_entry.trigger && attr->polarity == orig_entry.polarity) - return 0; - return -EBUSY; - } - ret = io_apic_setup_irq_pin(irq, node, attr); - if (!ret) - set_bit(pin, ioapics[ioapic_idx].pin_programmed); - return ret; -} - static int __init io_apic_get_redir_entries(int ioapic) { union IO_APIC_reg_01 reg_01; @@ -3340,20 +3457,13 @@ static int __init io_apic_get_redir_entries(int ioapic) return reg_01.bits.entries + 1; } -static void __init probe_nr_irqs_gsi(void) -{ - int nr; - - nr = gsi_top + NR_IRQS_LEGACY; - if (nr > nr_irqs_gsi) - nr_irqs_gsi = nr; - - printk(KERN_DEBUG "nr_irqs_gsi: %d\n", nr_irqs_gsi); -} - unsigned int arch_dynirq_lower_bound(unsigned int from) { - return from < nr_irqs_gsi ? nr_irqs_gsi : from; + /* + * dmar_alloc_hwirq() may be called before setup_IO_APIC(), so use + * gsi_top if ioapic_dynirq_base hasn't been initialized yet. + */ + return ioapic_initialized ? ioapic_dynirq_base : gsi_top; } int __init arch_probe_nr_irqs(void) @@ -3363,33 +3473,17 @@ int __init arch_probe_nr_irqs(void) if (nr_irqs > (NR_VECTORS * nr_cpu_ids)) nr_irqs = NR_VECTORS * nr_cpu_ids; - nr = nr_irqs_gsi + 8 * nr_cpu_ids; + nr = (gsi_top + nr_legacy_irqs()) + 8 * nr_cpu_ids; #if defined(CONFIG_PCI_MSI) || defined(CONFIG_HT_IRQ) /* * for MSI and HT dyn irq */ - nr += nr_irqs_gsi * 16; + nr += gsi_top * 16; #endif if (nr < nr_irqs) nr_irqs = nr; - return NR_IRQS_LEGACY; -} - -int io_apic_set_pci_routing(struct device *dev, int irq, - struct io_apic_irq_attr *irq_attr) -{ - int node; - - if (!IO_APIC_IRQ(irq)) { - apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n", - irq_attr->ioapic); - return -EINVAL; - } - - node = dev ? dev_to_node(dev) : cpu_to_node(0); - - return io_apic_setup_irq_pin_once(irq, node, irq_attr); + return 0; } #ifdef CONFIG_X86_32 @@ -3483,9 +3577,8 @@ static u8 __init io_apic_unique_id(u8 id) DECLARE_BITMAP(used, 256); bitmap_zero(used, 256); - for (i = 0; i < nr_ioapics; i++) { + for_each_ioapic(i) __set_bit(mpc_ioapic_id(i), used); - } if (!test_bit(id, used)) return id; return find_first_zero_bit(used, 256); @@ -3543,14 +3636,13 @@ void __init setup_ioapic_dest(void) if (skip_ioapic_setup == 1) return; - for (ioapic = 0; ioapic < nr_ioapics; ioapic++) - for (pin = 0; pin < ioapics[ioapic].nr_registers; pin++) { + for_each_ioapic_pin(ioapic, pin) { irq_entry = find_irq_entry(ioapic, pin, mp_INT); if (irq_entry == -1) continue; - irq = pin_2_irq(irq_entry, ioapic, pin); - if ((ioapic > 0) && (irq > 16)) + irq = pin_2_irq(irq_entry, ioapic, pin, 0); + if (irq < 0 || !mp_init_irq_at_boot(ioapic, irq)) continue; idata = irq_get_irq_data(irq); @@ -3573,29 +3665,33 @@ void __init setup_ioapic_dest(void) static struct resource *ioapic_resources; -static struct resource * __init ioapic_setup_resources(int nr_ioapics) +static struct resource * __init ioapic_setup_resources(void) { unsigned long n; struct resource *res; char *mem; - int i; + int i, num = 0; - if (nr_ioapics <= 0) + for_each_ioapic(i) + num++; + if (num == 0) return NULL; n = IOAPIC_RESOURCE_NAME_SIZE + sizeof(struct resource); - n *= nr_ioapics; + n *= num; mem = alloc_bootmem(n); res = (void *)mem; - mem += sizeof(struct resource) * nr_ioapics; + mem += sizeof(struct resource) * num; - for (i = 0; i < nr_ioapics; i++) { - res[i].name = mem; - res[i].flags = IORESOURCE_MEM | IORESOURCE_BUSY; + num = 0; + for_each_ioapic(i) { + res[num].name = mem; + res[num].flags = IORESOURCE_MEM | IORESOURCE_BUSY; snprintf(mem, IOAPIC_RESOURCE_NAME_SIZE, "IOAPIC %u", i); mem += IOAPIC_RESOURCE_NAME_SIZE; + num++; } ioapic_resources = res; @@ -3609,8 +3705,8 @@ void __init native_io_apic_init_mappings(void) struct resource *ioapic_res; int i; - ioapic_res = ioapic_setup_resources(nr_ioapics); - for (i = 0; i < nr_ioapics; i++) { + ioapic_res = ioapic_setup_resources(); + for_each_ioapic(i) { if (smp_found_config) { ioapic_phys = mpc_ioapic_addr(i); #ifdef CONFIG_X86_32 @@ -3641,8 +3737,6 @@ fake_ioapic_page: ioapic_res->end = ioapic_phys + IO_APIC_SLOT_SIZE - 1; ioapic_res++; } - - probe_nr_irqs_gsi(); } void __init ioapic_insert_resources(void) @@ -3657,7 +3751,7 @@ void __init ioapic_insert_resources(void) return; } - for (i = 0; i < nr_ioapics; i++) { + for_each_ioapic(i) { insert_resource(&iomem_resource, r); r++; } @@ -3665,16 +3759,15 @@ void __init ioapic_insert_resources(void) int mp_find_ioapic(u32 gsi) { - int i = 0; + int i; if (nr_ioapics == 0) return -1; /* Find the IOAPIC that manages this GSI. */ - for (i = 0; i < nr_ioapics; i++) { + for_each_ioapic(i) { struct mp_ioapic_gsi *gsi_cfg = mp_ioapic_gsi_routing(i); - if ((gsi >= gsi_cfg->gsi_base) - && (gsi <= gsi_cfg->gsi_end)) + if (gsi >= gsi_cfg->gsi_base && gsi <= gsi_cfg->gsi_end) return i; } @@ -3686,7 +3779,7 @@ int mp_find_ioapic_pin(int ioapic, u32 gsi) { struct mp_ioapic_gsi *gsi_cfg; - if (WARN_ON(ioapic == -1)) + if (WARN_ON(ioapic < 0)) return -1; gsi_cfg = mp_ioapic_gsi_routing(ioapic); @@ -3729,7 +3822,8 @@ static __init int bad_ioapic_register(int idx) return 0; } -void __init mp_register_ioapic(int id, u32 address, u32 gsi_base) +void __init mp_register_ioapic(int id, u32 address, u32 gsi_base, + struct ioapic_domain_cfg *cfg) { int idx = 0; int entries; @@ -3743,6 +3837,8 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base) ioapics[idx].mp_config.type = MP_IOAPIC; ioapics[idx].mp_config.flags = MPC_APIC_USABLE; ioapics[idx].mp_config.apicaddr = address; + ioapics[idx].irqdomain = NULL; + ioapics[idx].irqdomain_cfg = *cfg; set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address); @@ -3779,6 +3875,77 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base) nr_ioapics++; } +int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq) +{ + int ioapic = (int)(long)domain->host_data; + struct mp_pin_info *info = mp_pin_info(ioapic, hwirq); + struct io_apic_irq_attr attr; + + /* Get default attribute if not set by caller yet */ + if (!info->set) { + u32 gsi = mp_pin_to_gsi(ioapic, hwirq); + + if (acpi_get_override_irq(gsi, &info->trigger, + &info->polarity) < 0) { + /* + * PCI interrupts are always polarity one level + * triggered. + */ + info->trigger = 1; + info->polarity = 1; + } + info->node = NUMA_NO_NODE; + info->set = 1; + } + set_io_apic_irq_attr(&attr, ioapic, hwirq, info->trigger, + info->polarity); + + return io_apic_setup_irq_pin(virq, info->node, &attr); +} + +void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq) +{ + struct irq_data *data = irq_get_irq_data(virq); + struct irq_cfg *cfg = irq_cfg(virq); + int ioapic = (int)(long)domain->host_data; + int pin = (int)data->hwirq; + + ioapic_mask_entry(ioapic, pin); + __remove_pin_from_irq(cfg, ioapic, pin); + WARN_ON(cfg->irq_2_pin != NULL); + arch_teardown_hwirq(virq); +} + +int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node) +{ + int ret = 0; + int ioapic, pin; + struct mp_pin_info *info; + + ioapic = mp_find_ioapic(gsi); + if (ioapic < 0) + return -ENODEV; + + pin = mp_find_ioapic_pin(ioapic, gsi); + info = mp_pin_info(ioapic, pin); + trigger = trigger ? 1 : 0; + polarity = polarity ? 1 : 0; + + mutex_lock(&ioapic_mutex); + if (!info->set) { + info->trigger = trigger; + info->polarity = polarity; + info->node = node; + info->set = 1; + } else if (info->trigger != trigger || info->polarity != polarity) { + ret = -EBUSY; + } + mutex_unlock(&ioapic_mutex); + + return ret; +} + /* Enable IOAPIC early just for system timer */ void __init pre_init_apic_IRQ0(void) { diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index cceb352c968c..bda488680dbc 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -88,21 +88,16 @@ static struct apic apic_default = { .disable_esr = 0, .dest_logical = APIC_DEST_LOGICAL, .check_apicid_used = default_check_apicid_used, - .check_apicid_present = default_check_apicid_present, .vector_allocation_domain = flat_vector_allocation_domain, .init_apic_ldr = default_init_apic_ldr, .ioapic_phys_id_map = default_ioapic_phys_id_map, .setup_apic_routing = setup_apic_flat_routing, - .multi_timer_check = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, .apicid_to_cpu_present = physid_set_mask_of_physid, - .setup_portio_remap = NULL, .check_phys_apicid_present = default_check_phys_apicid_present, - .enable_apic_mode = NULL, .phys_pkg_id = default_phys_pkg_id, - .mps_oem_check = NULL, .get_apic_id = default_get_apic_id, .set_apic_id = NULL, @@ -116,11 +111,7 @@ static struct apic apic_default = { .send_IPI_all = default_send_IPI_all, .send_IPI_self = default_send_IPI_self, - .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, - .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = true, - .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = default_inquire_remote_apic, .read = native_apic_mem_read, @@ -214,29 +205,7 @@ void __init generic_apic_probe(void) printk(KERN_INFO "Using APIC driver %s\n", apic->name); } -/* These functions can switch the APIC even after the initial ->probe() */ - -int __init -generic_mps_oem_check(struct mpc_table *mpc, char *oem, char *productid) -{ - struct apic **drv; - - for (drv = __apicdrivers; drv < __apicdrivers_end; drv++) { - if (!((*drv)->mps_oem_check)) - continue; - if (!(*drv)->mps_oem_check(mpc, oem, productid)) - continue; - - if (!cmdline_apic) { - apic = *drv; - printk(KERN_INFO "Switched to APIC driver `%s'.\n", - apic->name); - } - return 1; - } - return 0; -} - +/* This function can switch the APIC even after the initial ->probe() */ int __init default_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { struct apic **drv; diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index e66766bf1641..6ce600f9bc78 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -249,21 +249,16 @@ static struct apic apic_x2apic_cluster = { .disable_esr = 0, .dest_logical = APIC_DEST_LOGICAL, .check_apicid_used = NULL, - .check_apicid_present = NULL, .vector_allocation_domain = cluster_vector_allocation_domain, .init_apic_ldr = init_x2apic_ldr, .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, - .multi_timer_check = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, .apicid_to_cpu_present = NULL, - .setup_portio_remap = NULL, .check_phys_apicid_present = default_check_phys_apicid_present, - .enable_apic_mode = NULL, .phys_pkg_id = x2apic_phys_pkg_id, - .mps_oem_check = NULL, .get_apic_id = x2apic_get_apic_id, .set_apic_id = x2apic_set_apic_id, @@ -277,10 +272,7 @@ static struct apic apic_x2apic_cluster = { .send_IPI_all = x2apic_send_IPI_all, .send_IPI_self = x2apic_send_IPI_self, - .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, - .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, .wait_for_init_deassert = false, - .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = NULL, .read = native_apic_msr_read, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 6d600ebf6c12..6fae733e9194 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -103,21 +103,16 @@ static struct apic apic_x2apic_phys = { .disable_esr = 0, .dest_logical = 0, .check_apicid_used = NULL, - .check_apicid_present = NULL, .vector_allocation_domain = default_vector_allocation_domain, .init_apic_ldr = init_x2apic_ldr, .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, - .multi_timer_check = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, .apicid_to_cpu_present = NULL, - .setup_portio_remap = NULL, .check_phys_apicid_present = default_check_phys_apicid_present, - .enable_apic_mode = NULL, .phys_pkg_id = x2apic_phys_pkg_id, - .mps_oem_check = NULL, .get_apic_id = x2apic_get_apic_id, .set_apic_id = x2apic_set_apic_id, @@ -131,10 +126,7 @@ static struct apic apic_x2apic_phys = { .send_IPI_all = x2apic_send_IPI_all, .send_IPI_self = x2apic_send_IPI_self, - .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, - .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, .wait_for_init_deassert = false, - .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = NULL, .read = native_apic_msr_read, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 293b41df54ef..004f017aa7b9 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -365,21 +365,16 @@ static struct apic __refdata apic_x2apic_uv_x = { .disable_esr = 0, .dest_logical = APIC_DEST_LOGICAL, .check_apicid_used = NULL, - .check_apicid_present = NULL, .vector_allocation_domain = default_vector_allocation_domain, .init_apic_ldr = uv_init_apic_ldr, .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, - .multi_timer_check = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, .apicid_to_cpu_present = NULL, - .setup_portio_remap = NULL, .check_phys_apicid_present = default_check_phys_apicid_present, - .enable_apic_mode = NULL, .phys_pkg_id = uv_phys_pkg_id, - .mps_oem_check = NULL, .get_apic_id = x2apic_get_apic_id, .set_apic_id = set_apic_id, @@ -394,10 +389,7 @@ static struct apic __refdata apic_x2apic_uv_x = { .send_IPI_self = uv_send_IPI_self, .wakeup_secondary_cpu = uv_wakeup_secondary, - .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, - .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, .wait_for_init_deassert = false, - .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = NULL, .read = native_apic_msr_read, diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index ce8b8ff0e0ef..60e5497681f5 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -8,6 +8,7 @@ #include <asm/processor.h> #include <asm/apic.h> #include <asm/cpu.h> +#include <asm/smp.h> #include <asm/pci-direct.h> #ifdef CONFIG_X86_64 @@ -50,7 +51,6 @@ static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val) return wrmsr_safe_regs(gprs); } -#ifdef CONFIG_X86_32 /* * B step AMD K6 before B 9730xxxx have hardware bugs that can cause * misexecution of code under Linux. Owners of such processors should @@ -70,6 +70,7 @@ __asm__(".globl vide\n\t.align 4\nvide: ret"); static void init_amd_k5(struct cpuinfo_x86 *c) { +#ifdef CONFIG_X86_32 /* * General Systems BIOSen alias the cpu frequency registers * of the Elan at 0x000df000. Unfortuantly, one of the Linux @@ -83,11 +84,12 @@ static void init_amd_k5(struct cpuinfo_x86 *c) if (inl(CBAR) & CBAR_ENB) outl(0 | CBAR_KEY, CBAR); } +#endif } - static void init_amd_k6(struct cpuinfo_x86 *c) { +#ifdef CONFIG_X86_32 u32 l, h; int mbytes = get_num_physpages() >> (20-PAGE_SHIFT); @@ -176,10 +178,44 @@ static void init_amd_k6(struct cpuinfo_x86 *c) /* placeholder for any needed mods */ return; } +#endif } -static void amd_k7_smp_check(struct cpuinfo_x86 *c) +static void init_amd_k7(struct cpuinfo_x86 *c) { +#ifdef CONFIG_X86_32 + u32 l, h; + + /* + * Bit 15 of Athlon specific MSR 15, needs to be 0 + * to enable SSE on Palomino/Morgan/Barton CPU's. + * If the BIOS didn't enable it already, enable it here. + */ + if (c->x86_model >= 6 && c->x86_model <= 10) { + if (!cpu_has(c, X86_FEATURE_XMM)) { + printk(KERN_INFO "Enabling disabled K7/SSE Support.\n"); + msr_clear_bit(MSR_K7_HWCR, 15); + set_cpu_cap(c, X86_FEATURE_XMM); + } + } + + /* + * It's been determined by AMD that Athlons since model 8 stepping 1 + * are more robust with CLK_CTL set to 200xxxxx instead of 600xxxxx + * As per AMD technical note 27212 0.2 + */ + if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) { + rdmsr(MSR_K7_CLK_CTL, l, h); + if ((l & 0xfff00000) != 0x20000000) { + printk(KERN_INFO + "CPU: CLK_CTL MSR was %x. Reprogramming to %x\n", + l, ((l & 0x000fffff)|0x20000000)); + wrmsr(MSR_K7_CLK_CTL, (l & 0x000fffff)|0x20000000, h); + } + } + + set_cpu_cap(c, X86_FEATURE_K7); + /* calling is from identify_secondary_cpu() ? */ if (!c->cpu_index) return; @@ -207,7 +243,7 @@ static void amd_k7_smp_check(struct cpuinfo_x86 *c) if (((c->x86_model == 6) && (c->x86_mask >= 2)) || ((c->x86_model == 7) && (c->x86_mask >= 1)) || (c->x86_model > 7)) - if (cpu_has_mp) + if (cpu_has(c, X86_FEATURE_MP)) return; /* If we get here, not a certified SMP capable AMD system. */ @@ -219,45 +255,8 @@ static void amd_k7_smp_check(struct cpuinfo_x86 *c) WARN_ONCE(1, "WARNING: This combination of AMD" " processors is not suitable for SMP.\n"); add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_NOW_UNRELIABLE); -} - -static void init_amd_k7(struct cpuinfo_x86 *c) -{ - u32 l, h; - - /* - * Bit 15 of Athlon specific MSR 15, needs to be 0 - * to enable SSE on Palomino/Morgan/Barton CPU's. - * If the BIOS didn't enable it already, enable it here. - */ - if (c->x86_model >= 6 && c->x86_model <= 10) { - if (!cpu_has(c, X86_FEATURE_XMM)) { - printk(KERN_INFO "Enabling disabled K7/SSE Support.\n"); - msr_clear_bit(MSR_K7_HWCR, 15); - set_cpu_cap(c, X86_FEATURE_XMM); - } - } - - /* - * It's been determined by AMD that Athlons since model 8 stepping 1 - * are more robust with CLK_CTL set to 200xxxxx instead of 600xxxxx - * As per AMD technical note 27212 0.2 - */ - if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) { - rdmsr(MSR_K7_CLK_CTL, l, h); - if ((l & 0xfff00000) != 0x20000000) { - printk(KERN_INFO - "CPU: CLK_CTL MSR was %x. Reprogramming to %x\n", - l, ((l & 0x000fffff)|0x20000000)); - wrmsr(MSR_K7_CLK_CTL, (l & 0x000fffff)|0x20000000, h); - } - } - - set_cpu_cap(c, X86_FEATURE_K7); - - amd_k7_smp_check(c); -} #endif +} #ifdef CONFIG_NUMA /* @@ -446,6 +445,26 @@ static void early_init_amd_mc(struct cpuinfo_x86 *c) static void bsp_init_amd(struct cpuinfo_x86 *c) { + +#ifdef CONFIG_X86_64 + if (c->x86 >= 0xf) { + unsigned long long tseg; + + /* + * Split up direct mapping around the TSEG SMM area. + * Don't do it for gbpages because there seems very little + * benefit in doing so. + */ + if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) { + unsigned long pfn = tseg >> PAGE_SHIFT; + + printk(KERN_DEBUG "tseg: %010llx\n", tseg); + if (pfn_range_is_mapped(pfn, pfn + 1)) + set_memory_4k((unsigned long)__va(tseg), 1); + } + } +#endif + if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { if (c->x86 > 0x10 || @@ -515,101 +534,74 @@ static const int amd_erratum_383[]; static const int amd_erratum_400[]; static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum); -static void init_amd(struct cpuinfo_x86 *c) +static void init_amd_k8(struct cpuinfo_x86 *c) { - u32 dummy; - unsigned long long value; + u32 level; + u64 value; -#ifdef CONFIG_SMP - /* - * Disable TLB flush filter by setting HWCR.FFDIS on K8 - * bit 6 of msr C001_0015 - * - * Errata 63 for SH-B3 steppings - * Errata 122 for all steppings (F+ have it disabled by default) - */ - if (c->x86 == 0xf) - msr_set_bit(MSR_K7_HWCR, 6); -#endif - - early_init_amd(c); + /* On C+ stepping K8 rep microcode works well for copy/memset */ + level = cpuid_eax(1); + if ((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58) + set_cpu_cap(c, X86_FEATURE_REP_GOOD); /* - * Bit 31 in normal CPUID used for nonstandard 3DNow ID; - * 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway + * Some BIOSes incorrectly force this feature, but only K8 revision D + * (model = 0x14) and later actually support it. + * (AMD Erratum #110, docId: 25759). */ - clear_cpu_cap(c, 0*32+31); - -#ifdef CONFIG_X86_64 - /* On C+ stepping K8 rep microcode works well for copy/memset */ - if (c->x86 == 0xf) { - u32 level; - - level = cpuid_eax(1); - if ((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58) - set_cpu_cap(c, X86_FEATURE_REP_GOOD); - - /* - * Some BIOSes incorrectly force this feature, but only K8 - * revision D (model = 0x14) and later actually support it. - * (AMD Erratum #110, docId: 25759). - */ - if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM)) { - clear_cpu_cap(c, X86_FEATURE_LAHF_LM); - if (!rdmsrl_amd_safe(0xc001100d, &value)) { - value &= ~(1ULL << 32); - wrmsrl_amd_safe(0xc001100d, value); - } + if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM)) { + clear_cpu_cap(c, X86_FEATURE_LAHF_LM); + if (!rdmsrl_amd_safe(0xc001100d, &value)) { + value &= ~BIT_64(32); + wrmsrl_amd_safe(0xc001100d, value); } - } - if (c->x86 >= 0x10) - set_cpu_cap(c, X86_FEATURE_REP_GOOD); - /* get apicid instead of initial apic id from cpuid */ - c->apicid = hard_smp_processor_id(); -#else + if (!c->x86_model_id[0]) + strcpy(c->x86_model_id, "Hammer"); +} + +static void init_amd_gh(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_X86_64 + /* do this for boot cpu */ + if (c == &boot_cpu_data) + check_enable_amd_mmconf_dmi(); + + fam10h_check_enable_mmcfg(); +#endif /* - * FIXME: We should handle the K5 here. Set up the write - * range and also turn on MSR 83 bits 4 and 31 (write alloc, - * no bus pipeline) + * Disable GART TLB Walk Errors on Fam10h. We do this here because this + * is always needed when GART is enabled, even in a kernel which has no + * MCE support built in. BIOS should disable GartTlbWlk Errors already. + * If it doesn't, we do it here as suggested by the BKDG. + * + * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012 */ + msr_set_bit(MSR_AMD64_MCx_MASK(4), 10); - switch (c->x86) { - case 4: - init_amd_k5(c); - break; - case 5: - init_amd_k6(c); - break; - case 6: /* An Athlon/Duron */ - init_amd_k7(c); - break; - } + /* + * On family 10h BIOS may not have properly enabled WC+ support, causing + * it to be converted to CD memtype. This may result in performance + * degradation for certain nested-paging guests. Prevent this conversion + * by clearing bit 24 in MSR_AMD64_BU_CFG2. + * + * NOTE: we want to use the _safe accessors so as not to #GP kvm + * guests on older kvm hosts. + */ + msr_clear_bit(MSR_AMD64_BU_CFG2, 24); - /* K6s reports MCEs but don't actually have all the MSRs */ - if (c->x86 < 6) - clear_cpu_cap(c, X86_FEATURE_MCE); -#endif + if (cpu_has_amd_erratum(c, amd_erratum_383)) + set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH); +} - /* Enable workaround for FXSAVE leak */ - if (c->x86 >= 6) - set_cpu_cap(c, X86_FEATURE_FXSAVE_LEAK); - - if (!c->x86_model_id[0]) { - switch (c->x86) { - case 0xf: - /* Should distinguish Models here, but this is only - a fallback anyways. */ - strcpy(c->x86_model_id, "Hammer"); - break; - } - } +static void init_amd_bd(struct cpuinfo_x86 *c) +{ + u64 value; /* re-enable TopologyExtensions if switched off by BIOS */ - if ((c->x86 == 0x15) && - (c->x86_model >= 0x10) && (c->x86_model <= 0x1f) && + if ((c->x86_model >= 0x10) && (c->x86_model <= 0x1f) && !cpu_has(c, X86_FEATURE_TOPOEXT)) { if (msr_set_bit(0xc0011005, 54) > 0) { @@ -625,14 +617,60 @@ static void init_amd(struct cpuinfo_x86 *c) * The way access filter has a performance penalty on some workloads. * Disable it on the affected CPUs. */ - if ((c->x86 == 0x15) && - (c->x86_model >= 0x02) && (c->x86_model < 0x20)) { - + if ((c->x86_model >= 0x02) && (c->x86_model < 0x20)) { if (!rdmsrl_safe(0xc0011021, &value) && !(value & 0x1E)) { value |= 0x1E; wrmsrl_safe(0xc0011021, value); } } +} + +static void init_amd(struct cpuinfo_x86 *c) +{ + u32 dummy; + +#ifdef CONFIG_SMP + /* + * Disable TLB flush filter by setting HWCR.FFDIS on K8 + * bit 6 of msr C001_0015 + * + * Errata 63 for SH-B3 steppings + * Errata 122 for all steppings (F+ have it disabled by default) + */ + if (c->x86 == 0xf) + msr_set_bit(MSR_K7_HWCR, 6); +#endif + + early_init_amd(c); + + /* + * Bit 31 in normal CPUID used for nonstandard 3DNow ID; + * 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway + */ + clear_cpu_cap(c, 0*32+31); + + if (c->x86 >= 0x10) + set_cpu_cap(c, X86_FEATURE_REP_GOOD); + + /* get apicid instead of initial apic id from cpuid */ + c->apicid = hard_smp_processor_id(); + + /* K6s reports MCEs but don't actually have all the MSRs */ + if (c->x86 < 6) + clear_cpu_cap(c, X86_FEATURE_MCE); + + switch (c->x86) { + case 4: init_amd_k5(c); break; + case 5: init_amd_k6(c); break; + case 6: init_amd_k7(c); break; + case 0xf: init_amd_k8(c); break; + case 0x10: init_amd_gh(c); break; + case 0x15: init_amd_bd(c); break; + } + + /* Enable workaround for FXSAVE leak */ + if (c->x86 >= 6) + set_cpu_bug(c, X86_BUG_FXSAVE_LEAK); cpu_detect_cache_sizes(c); @@ -656,33 +694,6 @@ static void init_amd(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); } -#ifdef CONFIG_X86_64 - if (c->x86 == 0x10) { - /* do this for boot cpu */ - if (c == &boot_cpu_data) - check_enable_amd_mmconf_dmi(); - - fam10h_check_enable_mmcfg(); - } - - if (c == &boot_cpu_data && c->x86 >= 0xf) { - unsigned long long tseg; - - /* - * Split up direct mapping around the TSEG SMM area. - * Don't do it for gbpages because there seems very little - * benefit in doing so. - */ - if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) { - unsigned long pfn = tseg >> PAGE_SHIFT; - - printk(KERN_DEBUG "tseg: %010llx\n", tseg); - if (pfn_range_is_mapped(pfn, pfn + 1)) - set_memory_4k((unsigned long)__va(tseg), 1); - } - } -#endif - /* * Family 0x12 and above processors have APIC timer * running in deep C states. @@ -690,34 +701,6 @@ static void init_amd(struct cpuinfo_x86 *c) if (c->x86 > 0x11) set_cpu_cap(c, X86_FEATURE_ARAT); - if (c->x86 == 0x10) { - /* - * Disable GART TLB Walk Errors on Fam10h. We do this here - * because this is always needed when GART is enabled, even in a - * kernel which has no MCE support built in. - * BIOS should disable GartTlbWlk Errors already. If - * it doesn't, do it here as suggested by the BKDG. - * - * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012 - */ - msr_set_bit(MSR_AMD64_MCx_MASK(4), 10); - - /* - * On family 10h BIOS may not have properly enabled WC+ support, - * causing it to be converted to CD memtype. This may result in - * performance degradation for certain nested-paging guests. - * Prevent this conversion by clearing bit 24 in - * MSR_AMD64_BU_CFG2. - * - * NOTE: we want to use the _safe accessors so as not to #GP kvm - * guests on older kvm hosts. - */ - msr_clear_bit(MSR_AMD64_BU_CFG2, 24); - - if (cpu_has_amd_erratum(c, amd_erratum_383)) - set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH); - } - if (cpu_has_amd_erratum(c, amd_erratum_400)) set_cpu_bug(c, X86_BUG_AMD_APIC_C1E); @@ -741,11 +724,6 @@ static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size) } #endif -static void cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c) -{ - tlb_flushall_shift = 6; -} - static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c) { u32 ebx, eax, ecx, edx; @@ -793,8 +771,6 @@ static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c) tlb_lli_2m[ENTRIES] = eax & mask; tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1; - - cpu_set_tlb_flushall_shift(c); } static const struct cpu_dev amd_cpu_dev = { diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index ef1b93f18ed1..e4ab2b42bd6f 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -148,6 +148,7 @@ static int __init x86_xsave_setup(char *s) { setup_clear_cpu_cap(X86_FEATURE_XSAVE); setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); + setup_clear_cpu_cap(X86_FEATURE_XSAVES); setup_clear_cpu_cap(X86_FEATURE_AVX); setup_clear_cpu_cap(X86_FEATURE_AVX2); return 1; @@ -161,6 +162,13 @@ static int __init x86_xsaveopt_setup(char *s) } __setup("noxsaveopt", x86_xsaveopt_setup); +static int __init x86_xsaves_setup(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_XSAVES); + return 1; +} +__setup("noxsaves", x86_xsaves_setup); + #ifdef CONFIG_X86_32 static int cachesize_override = -1; static int disable_x86_serial_nr = 1; @@ -481,26 +489,17 @@ u16 __read_mostly tlb_lld_2m[NR_INFO]; u16 __read_mostly tlb_lld_4m[NR_INFO]; u16 __read_mostly tlb_lld_1g[NR_INFO]; -/* - * tlb_flushall_shift shows the balance point in replacing cr3 write - * with multiple 'invlpg'. It will do this replacement when - * flush_tlb_lines <= active_lines/2^tlb_flushall_shift. - * If tlb_flushall_shift is -1, means the replacement will be disabled. - */ -s8 __read_mostly tlb_flushall_shift = -1; - 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" - "tlb_flushall_shift: %d\n", + "Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d, 1GB %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_flushall_shift); + tlb_lld_1g[ENTRIES]); } void detect_ht(struct cpuinfo_x86 *c) @@ -634,6 +633,15 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[9] = ebx; } + /* Extended state features: level 0x0000000d */ + if (c->cpuid_level >= 0x0000000d) { + u32 eax, ebx, ecx, edx; + + cpuid_count(0x0000000d, 1, &eax, &ebx, &ecx, &edx); + + c->x86_capability[10] = eax; + } + /* AMD-defined flags: level 0x80000001 */ xlvl = cpuid_eax(0x80000000); c->extended_cpuid_level = xlvl; diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index f9e4fdd3b877..74e804ddc5c7 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -253,7 +253,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) */ if (cpu_has_apic && (c->x86<<8 | c->x86_model<<4) == 0x520 && (c->x86_mask < 0x6 || c->x86_mask == 0xb)) - set_cpu_cap(c, X86_FEATURE_11AP); + set_cpu_bug(c, X86_BUG_11AP); #ifdef CONFIG_X86_INTEL_USERCOPY @@ -402,7 +402,7 @@ static void init_intel(struct cpuinfo_x86 *c) if (c->x86 == 6 && cpu_has_clflush && (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47)) - set_cpu_cap(c, X86_FEATURE_CLFLUSH_MONITOR); + set_cpu_bug(c, X86_BUG_CLFLUSH_MONITOR); #ifdef CONFIG_X86_64 if (c->x86 == 15) @@ -634,31 +634,6 @@ static void intel_tlb_lookup(const unsigned char desc) } } -static void intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c) -{ - switch ((c->x86 << 8) + c->x86_model) { - case 0x60f: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */ - case 0x616: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */ - case 0x617: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */ - case 0x61d: /* six-core 45 nm xeon "Dunnington" */ - tlb_flushall_shift = -1; - break; - case 0x63a: /* Ivybridge */ - tlb_flushall_shift = 2; - break; - case 0x61a: /* 45 nm nehalem, "Bloomfield" */ - case 0x61e: /* 45 nm nehalem, "Lynnfield" */ - case 0x625: /* 32 nm nehalem, "Clarkdale" */ - case 0x62c: /* 32 nm nehalem, "Gulftown" */ - case 0x62e: /* 45 nm nehalem-ex, "Beckton" */ - case 0x62f: /* 32 nm Xeon E7 */ - case 0x62a: /* SandyBridge */ - case 0x62d: /* SandyBridge, "Romely-EP" */ - default: - tlb_flushall_shift = 6; - } -} - static void intel_detect_tlb(struct cpuinfo_x86 *c) { int i, j, n; @@ -683,7 +658,6 @@ static void intel_detect_tlb(struct cpuinfo_x86 *c) for (j = 1 ; j < 16 ; j++) intel_tlb_lookup(desc[j]); } - intel_tlb_flushall_shift_set(c); } static const struct cpu_dev intel_cpu_dev = { diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 9a79c8dbd8e8..4fc57975acc1 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -2385,6 +2385,10 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) threshold_cpu_callback(action, cpu); mce_device_remove(cpu); mce_intel_hcpu_update(cpu); + + /* intentionally ignoring frozen here */ + if (!(action & CPU_TASKS_FROZEN)) + cmci_rediscover(); break; case CPU_DOWN_PREPARE: smp_call_function_single(cpu, mce_disable_cpu, &action, 1); @@ -2396,11 +2400,6 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) break; } - if (action == CPU_POST_DEAD) { - /* intentionally ignoring frozen here */ - cmci_rediscover(); - } - return NOTIFY_OK; } diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh index 2bf616505499..e2b22df964cd 100644 --- a/arch/x86/kernel/cpu/mkcapflags.sh +++ b/arch/x86/kernel/cpu/mkcapflags.sh @@ -1,23 +1,25 @@ #!/bin/sh # -# Generate the x86_cap_flags[] array from include/asm/cpufeature.h +# Generate the x86_cap/bug_flags[] arrays from include/asm/cpufeature.h # IN=$1 OUT=$2 -TABS="$(printf '\t\t\t\t\t')" -trap 'rm "$OUT"' EXIT +function dump_array() +{ + ARRAY=$1 + SIZE=$2 + PFX=$3 + POSTFIX=$4 -( - echo "#ifndef _ASM_X86_CPUFEATURE_H" - echo "#include <asm/cpufeature.h>" - echo "#endif" - echo "" - echo "const char * const x86_cap_flags[NCAPINTS*32] = {" + PFX_SZ=$(echo $PFX | wc -c) + TABS="$(printf '\t\t\t\t\t')" + + echo "const char * const $ARRAY[$SIZE] = {" - # Iterate through any input lines starting with #define X86_FEATURE_ - sed -n -e 's/\t/ /g' -e 's/^ *# *define *X86_FEATURE_//p' $IN | + # Iterate through any input lines starting with #define $PFX + sed -n -e 's/\t/ /g' -e "s/^ *# *define *$PFX//p" $IN | while read i do # Name is everything up to the first whitespace @@ -31,11 +33,32 @@ trap 'rm "$OUT"' EXIT # Name is uppercase, VALUE is all lowercase VALUE="$(echo "$VALUE" | tr A-Z a-z)" - TABCOUNT=$(( ( 5*8 - 14 - $(echo "$NAME" | wc -c) ) / 8 )) - printf "\t[%s]%.*s = %s,\n" \ - "X86_FEATURE_$NAME" "$TABCOUNT" "$TABS" "$VALUE" + if [ -n "$POSTFIX" ]; then + T=$(( $PFX_SZ + $(echo $POSTFIX | wc -c) + 2 )) + TABS="$(printf '\t\t\t\t\t\t')" + TABCOUNT=$(( ( 6*8 - ($T + 1) - $(echo "$NAME" | wc -c) ) / 8 )) + printf "\t[%s - %s]%.*s = %s,\n" "$PFX$NAME" "$POSTFIX" "$TABCOUNT" "$TABS" "$VALUE" + else + TABCOUNT=$(( ( 5*8 - ($PFX_SZ + 1) - $(echo "$NAME" | wc -c) ) / 8 )) + printf "\t[%s]%.*s = %s,\n" "$PFX$NAME" "$TABCOUNT" "$TABS" "$VALUE" + fi done echo "};" +} + +trap 'rm "$OUT"' EXIT + +( + echo "#ifndef _ASM_X86_CPUFEATURE_H" + echo "#include <asm/cpufeature.h>" + echo "#endif" + echo "" + + dump_array "x86_cap_flags" "NCAPINTS*32" "X86_FEATURE_" "" + echo "" + + dump_array "x86_bug_flags" "NBUGINTS*32" "X86_BUG_" "NCAPINTS*32" + ) > $OUT trap - EXIT diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c index 3bbdf4cd38b9..30790d798e6b 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c @@ -294,31 +294,41 @@ static struct amd_uncore *amd_uncore_alloc(unsigned int cpu) cpu_to_node(cpu)); } -static void amd_uncore_cpu_up_prepare(unsigned int cpu) +static int amd_uncore_cpu_up_prepare(unsigned int cpu) { - struct amd_uncore *uncore; + struct amd_uncore *uncore_nb = NULL, *uncore_l2; if (amd_uncore_nb) { - uncore = amd_uncore_alloc(cpu); - uncore->cpu = cpu; - uncore->num_counters = NUM_COUNTERS_NB; - uncore->rdpmc_base = RDPMC_BASE_NB; - uncore->msr_base = MSR_F15H_NB_PERF_CTL; - uncore->active_mask = &amd_nb_active_mask; - uncore->pmu = &amd_nb_pmu; - *per_cpu_ptr(amd_uncore_nb, cpu) = uncore; + uncore_nb = amd_uncore_alloc(cpu); + if (!uncore_nb) + goto fail; + uncore_nb->cpu = cpu; + uncore_nb->num_counters = NUM_COUNTERS_NB; + uncore_nb->rdpmc_base = RDPMC_BASE_NB; + uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL; + uncore_nb->active_mask = &amd_nb_active_mask; + uncore_nb->pmu = &amd_nb_pmu; + *per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb; } if (amd_uncore_l2) { - uncore = amd_uncore_alloc(cpu); - uncore->cpu = cpu; - uncore->num_counters = NUM_COUNTERS_L2; - uncore->rdpmc_base = RDPMC_BASE_L2; - uncore->msr_base = MSR_F16H_L2I_PERF_CTL; - uncore->active_mask = &amd_l2_active_mask; - uncore->pmu = &amd_l2_pmu; - *per_cpu_ptr(amd_uncore_l2, cpu) = uncore; + uncore_l2 = amd_uncore_alloc(cpu); + if (!uncore_l2) + goto fail; + uncore_l2->cpu = cpu; + uncore_l2->num_counters = NUM_COUNTERS_L2; + uncore_l2->rdpmc_base = RDPMC_BASE_L2; + uncore_l2->msr_base = MSR_F16H_L2I_PERF_CTL; + uncore_l2->active_mask = &amd_l2_active_mask; + uncore_l2->pmu = &amd_l2_pmu; + *per_cpu_ptr(amd_uncore_l2, cpu) = uncore_l2; } + + return 0; + +fail: + kfree(uncore_nb); + return -ENOMEM; } static struct amd_uncore * @@ -441,7 +451,7 @@ static void uncore_dead(unsigned int cpu, struct amd_uncore * __percpu *uncores) if (!--uncore->refcnt) kfree(uncore); - *per_cpu_ptr(amd_uncore_nb, cpu) = NULL; + *per_cpu_ptr(uncores, cpu) = NULL; } static void amd_uncore_cpu_dead(unsigned int cpu) @@ -461,7 +471,8 @@ amd_uncore_cpu_notifier(struct notifier_block *self, unsigned long action, switch (action & ~CPU_TASKS_FROZEN) { case CPU_UP_PREPARE: - amd_uncore_cpu_up_prepare(cpu); + if (amd_uncore_cpu_up_prepare(cpu)) + return notifier_from_errno(-ENOMEM); break; case CPU_STARTING: @@ -501,20 +512,33 @@ static void __init init_cpu_already_online(void *dummy) amd_uncore_cpu_online(cpu); } +static void cleanup_cpu_online(void *dummy) +{ + unsigned int cpu = smp_processor_id(); + + amd_uncore_cpu_dead(cpu); +} + static int __init amd_uncore_init(void) { - unsigned int cpu; + unsigned int cpu, cpu2; int ret = -ENODEV; if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) - return -ENODEV; + goto fail_nodev; if (!cpu_has_topoext) - return -ENODEV; + goto fail_nodev; if (cpu_has_perfctr_nb) { amd_uncore_nb = alloc_percpu(struct amd_uncore *); - perf_pmu_register(&amd_nb_pmu, amd_nb_pmu.name, -1); + if (!amd_uncore_nb) { + ret = -ENOMEM; + goto fail_nb; + } + ret = perf_pmu_register(&amd_nb_pmu, amd_nb_pmu.name, -1); + if (ret) + goto fail_nb; printk(KERN_INFO "perf: AMD NB counters detected\n"); ret = 0; @@ -522,20 +546,28 @@ static int __init amd_uncore_init(void) if (cpu_has_perfctr_l2) { amd_uncore_l2 = alloc_percpu(struct amd_uncore *); - perf_pmu_register(&amd_l2_pmu, amd_l2_pmu.name, -1); + if (!amd_uncore_l2) { + ret = -ENOMEM; + goto fail_l2; + } + ret = perf_pmu_register(&amd_l2_pmu, amd_l2_pmu.name, -1); + if (ret) + goto fail_l2; printk(KERN_INFO "perf: AMD L2I counters detected\n"); ret = 0; } if (ret) - return -ENODEV; + goto fail_nodev; cpu_notifier_register_begin(); /* init cpus already online before registering for hotplug notifier */ for_each_online_cpu(cpu) { - amd_uncore_cpu_up_prepare(cpu); + ret = amd_uncore_cpu_up_prepare(cpu); + if (ret) + goto fail_online; smp_call_function_single(cpu, init_cpu_already_online, NULL, 1); } @@ -543,5 +575,30 @@ static int __init amd_uncore_init(void) cpu_notifier_register_done(); return 0; + + +fail_online: + for_each_online_cpu(cpu2) { + if (cpu2 == cpu) + break; + smp_call_function_single(cpu, cleanup_cpu_online, NULL, 1); + } + cpu_notifier_register_done(); + + /* amd_uncore_nb/l2 should have been freed by cleanup_cpu_online */ + amd_uncore_nb = amd_uncore_l2 = NULL; + if (cpu_has_perfctr_l2) + perf_pmu_unregister(&amd_l2_pmu); +fail_l2: + if (cpu_has_perfctr_nb) + perf_pmu_unregister(&amd_nb_pmu); + if (amd_uncore_l2) + free_percpu(amd_uncore_l2); +fail_nb: + if (amd_uncore_nb) + free_percpu(amd_uncore_nb); + +fail_nodev: + return ret; } device_initcall(amd_uncore_init); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index ae6552a0701f..cfc6f9dfcd90 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -2947,10 +2947,7 @@ again: * extra registers. If we failed to take an extra * register, try the alternative. */ - if (idx % 2) - idx--; - else - idx++; + idx ^= 1; if (idx != reg1->idx % 6) { if (idx == 2) config1 >>= 8; diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 06fe3ed8b851..5433658e598d 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -97,6 +97,14 @@ static int show_cpuinfo(struct seq_file *m, void *v) if (cpu_has(c, i) && x86_cap_flags[i] != NULL) seq_printf(m, " %s", x86_cap_flags[i]); + seq_printf(m, "\nbugs\t\t:"); + for (i = 0; i < 32*NBUGINTS; i++) { + unsigned int bug_bit = 32*NCAPINTS + i; + + if (cpu_has_bug(c, bug_bit) && x86_bug_flags[i]) + seq_printf(m, " %s", x86_bug_flags[i]); + } + seq_printf(m, "\nbogomips\t: %lu.%02lu\n", c->loops_per_jiffy/(500000/HZ), (c->loops_per_jiffy/(5000/HZ)) % 100); diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index b6f794aa1693..4a8013d55947 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -38,7 +38,6 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c) { X86_FEATURE_PTS, CR_EAX, 6, 0x00000006, 0 }, { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 }, - { X86_FEATURE_XSAVEOPT, CR_EAX, 0, 0x0000000d, 1 }, { X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 }, { X86_FEATURE_CPB, CR_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CR_EDX,11, 0x80000007, 0 }, diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 7db54b5d5f86..3d3503351242 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -21,6 +21,7 @@ #include <asm/apic.h> #include <asm/pci_x86.h> #include <asm/setup.h> +#include <asm/i8259.h> __initdata u64 initial_dtb; char __initdata cmd_line[COMMAND_LINE_SIZE]; @@ -165,82 +166,6 @@ static void __init dtb_lapic_setup(void) #ifdef CONFIG_X86_IO_APIC static unsigned int ioapic_id; -static void __init dtb_add_ioapic(struct device_node *dn) -{ - struct resource r; - int ret; - - ret = of_address_to_resource(dn, 0, &r); - if (ret) { - printk(KERN_ERR "Can't obtain address from node %s.\n", - dn->full_name); - return; - } - mp_register_ioapic(++ioapic_id, r.start, gsi_top); -} - -static void __init dtb_ioapic_setup(void) -{ - struct device_node *dn; - - for_each_compatible_node(dn, NULL, "intel,ce4100-ioapic") - dtb_add_ioapic(dn); - - if (nr_ioapics) { - of_ioapic = 1; - return; - } - printk(KERN_ERR "Error: No information about IO-APIC in OF.\n"); -} -#else -static void __init dtb_ioapic_setup(void) {} -#endif - -static void __init dtb_apic_setup(void) -{ - dtb_lapic_setup(); - dtb_ioapic_setup(); -} - -#ifdef CONFIG_OF_FLATTREE -static void __init x86_flattree_get_config(void) -{ - u32 size, map_len; - void *dt; - - if (!initial_dtb) - return; - - map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), (u64)128); - - initial_boot_params = dt = early_memremap(initial_dtb, map_len); - size = of_get_flat_dt_size(); - if (map_len < size) { - early_iounmap(dt, map_len); - initial_boot_params = dt = early_memremap(initial_dtb, size); - map_len = size; - } - - unflatten_and_copy_device_tree(); - early_iounmap(dt, map_len); -} -#else -static inline void x86_flattree_get_config(void) { } -#endif - -void __init x86_dtb_init(void) -{ - x86_flattree_get_config(); - - if (!of_have_populated_dt()) - return; - - dtb_setup_hpet(); - dtb_apic_setup(); -} - -#ifdef CONFIG_X86_IO_APIC - struct of_ioapic_type { u32 out_type; u32 trigger; @@ -276,10 +201,8 @@ static int ioapic_xlate(struct irq_domain *domain, const u32 *intspec, u32 intsize, irq_hw_number_t *out_hwirq, u32 *out_type) { - struct io_apic_irq_attr attr; struct of_ioapic_type *it; - u32 line, idx; - int rc; + u32 line, idx, gsi; if (WARN_ON(intsize < 2)) return -EINVAL; @@ -291,13 +214,10 @@ static int ioapic_xlate(struct irq_domain *domain, it = &of_ioapic_type[intspec[1]]; - idx = (u32) domain->host_data; - set_io_apic_irq_attr(&attr, idx, line, it->trigger, it->polarity); - - rc = io_apic_setup_irq_pin_once(irq_find_mapping(domain, line), - cpu_to_node(0), &attr); - if (rc) - return rc; + idx = (u32)(long)domain->host_data; + gsi = mp_pin_to_gsi(idx, line); + if (mp_set_gsi_attr(gsi, it->trigger, it->polarity, cpu_to_node(0))) + return -EBUSY; *out_hwirq = line; *out_type = it->out_type; @@ -305,81 +225,86 @@ static int ioapic_xlate(struct irq_domain *domain, } const struct irq_domain_ops ioapic_irq_domain_ops = { + .map = mp_irqdomain_map, + .unmap = mp_irqdomain_unmap, .xlate = ioapic_xlate, }; -static void dt_add_ioapic_domain(unsigned int ioapic_num, - struct device_node *np) +static void __init dtb_add_ioapic(struct device_node *dn) { - struct irq_domain *id; - struct mp_ioapic_gsi *gsi_cfg; + struct resource r; int ret; - int num; - - gsi_cfg = mp_ioapic_gsi_routing(ioapic_num); - num = gsi_cfg->gsi_end - gsi_cfg->gsi_base + 1; - - id = irq_domain_add_linear(np, num, &ioapic_irq_domain_ops, - (void *)ioapic_num); - BUG_ON(!id); - if (gsi_cfg->gsi_base == 0) { - /* - * The first NR_IRQS_LEGACY irq descs are allocated in - * early_irq_init() and need just a mapping. The - * remaining irqs need both. All of them are preallocated - * and assigned so we can keep the 1:1 mapping which the ioapic - * is having. - */ - irq_domain_associate_many(id, 0, 0, NR_IRQS_LEGACY); - - if (num > NR_IRQS_LEGACY) { - ret = irq_create_strict_mappings(id, NR_IRQS_LEGACY, - NR_IRQS_LEGACY, num - NR_IRQS_LEGACY); - if (ret) - pr_err("Error creating mapping for the " - "remaining IRQs: %d\n", ret); - } - irq_set_default_host(id); - } else { - ret = irq_create_strict_mappings(id, gsi_cfg->gsi_base, 0, num); - if (ret) - pr_err("Error creating IRQ mapping: %d\n", ret); + struct ioapic_domain_cfg cfg = { + .type = IOAPIC_DOMAIN_DYNAMIC, + .ops = &ioapic_irq_domain_ops, + .dev = dn, + }; + + ret = of_address_to_resource(dn, 0, &r); + if (ret) { + printk(KERN_ERR "Can't obtain address from node %s.\n", + dn->full_name); + return; } + mp_register_ioapic(++ioapic_id, r.start, gsi_top, &cfg); } -static void __init ioapic_add_ofnode(struct device_node *np) +static void __init dtb_ioapic_setup(void) { - struct resource r; - int i, ret; + struct device_node *dn; - ret = of_address_to_resource(np, 0, &r); - if (ret) { - printk(KERN_ERR "Failed to obtain address for %s\n", - np->full_name); + for_each_compatible_node(dn, NULL, "intel,ce4100-ioapic") + dtb_add_ioapic(dn); + + if (nr_ioapics) { + of_ioapic = 1; return; } + printk(KERN_ERR "Error: No information about IO-APIC in OF.\n"); +} +#else +static void __init dtb_ioapic_setup(void) {} +#endif - for (i = 0; i < nr_ioapics; i++) { - if (r.start == mpc_ioapic_addr(i)) { - dt_add_ioapic_domain(i, np); - return; - } - } - printk(KERN_ERR "IOxAPIC at %s is not registered.\n", np->full_name); +static void __init dtb_apic_setup(void) +{ + dtb_lapic_setup(); + dtb_ioapic_setup(); } -void __init x86_add_irq_domains(void) +#ifdef CONFIG_OF_FLATTREE +static void __init x86_flattree_get_config(void) { - struct device_node *dp; + u32 size, map_len; + void *dt; - if (!of_have_populated_dt()) + if (!initial_dtb) return; - for_each_node_with_property(dp, "interrupt-controller") { - if (of_device_is_compatible(dp, "intel,ce4100-ioapic")) - ioapic_add_ofnode(dp); + map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), (u64)128); + + initial_boot_params = dt = early_memremap(initial_dtb, map_len); + size = of_get_flat_dt_size(); + if (map_len < size) { + early_iounmap(dt, map_len); + initial_boot_params = dt = early_memremap(initial_dtb, size); + map_len = size; } + + unflatten_and_copy_device_tree(); + early_iounmap(dt, map_len); } #else -void __init x86_add_irq_domains(void) { } +static inline void x86_flattree_get_config(void) { } #endif + +void __init x86_dtb_init(void) +{ + x86_flattree_get_config(); + + if (!of_have_populated_dt()) + return; + + dtb_setup_hpet(); + dtb_apic_setup(); +} diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 5e8cb2ad9fb3..c0a712bedd05 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -207,7 +207,6 @@ ENDPROC(native_usergs_sysret64) */ .macro XCPT_FRAME start=1 offset=0 INTR_FRAME \start, RIP+\offset-ORIG_RAX - /*CFI_REL_OFFSET orig_rax, ORIG_RAX-ORIG_RAX*/ .endm /* @@ -287,21 +286,21 @@ ENDPROC(native_usergs_sysret64) ENTRY(save_paranoid) XCPT_FRAME 1 RDI+8 cld - movq_cfi rdi, RDI+8 - movq_cfi rsi, RSI+8 + movq %rdi, RDI+8(%rsp) + movq %rsi, RSI+8(%rsp) movq_cfi rdx, RDX+8 movq_cfi rcx, RCX+8 movq_cfi rax, RAX+8 - movq_cfi r8, R8+8 - movq_cfi r9, R9+8 - movq_cfi r10, R10+8 - movq_cfi r11, R11+8 + movq %r8, R8+8(%rsp) + movq %r9, R9+8(%rsp) + movq %r10, R10+8(%rsp) + movq %r11, R11+8(%rsp) movq_cfi rbx, RBX+8 - movq_cfi rbp, RBP+8 - movq_cfi r12, R12+8 - movq_cfi r13, R13+8 - movq_cfi r14, R14+8 - movq_cfi r15, R15+8 + movq %rbp, RBP+8(%rsp) + movq %r12, R12+8(%rsp) + movq %r13, R13+8(%rsp) + movq %r14, R14+8(%rsp) + movq %r15, R15+8(%rsp) movl $1,%ebx movl $MSR_GS_BASE,%ecx rdmsr @@ -1386,21 +1385,21 @@ ENTRY(error_entry) CFI_ADJUST_CFA_OFFSET 15*8 /* oldrax contains error code */ cld - movq_cfi rdi, RDI+8 - movq_cfi rsi, RSI+8 - movq_cfi rdx, RDX+8 - movq_cfi rcx, RCX+8 - movq_cfi rax, RAX+8 - movq_cfi r8, R8+8 - movq_cfi r9, R9+8 - movq_cfi r10, R10+8 - movq_cfi r11, R11+8 + movq %rdi, RDI+8(%rsp) + movq %rsi, RSI+8(%rsp) + movq %rdx, RDX+8(%rsp) + movq %rcx, RCX+8(%rsp) + movq %rax, RAX+8(%rsp) + movq %r8, R8+8(%rsp) + movq %r9, R9+8(%rsp) + movq %r10, R10+8(%rsp) + movq %r11, R11+8(%rsp) movq_cfi rbx, RBX+8 - movq_cfi rbp, RBP+8 - movq_cfi r12, R12+8 - movq_cfi r13, R13+8 - movq_cfi r14, R14+8 - movq_cfi r15, R15+8 + movq %rbp, RBP+8(%rsp) + movq %r12, R12+8(%rsp) + movq %r13, R13+8(%rsp) + movq %r14, R14+8(%rsp) + movq %r15, R15+8(%rsp) xorl %ebx,%ebx testl $3,CS+8(%rsp) je error_kernelspace @@ -1418,6 +1417,7 @@ error_sti: * compat mode. Check for these here too. */ error_kernelspace: + CFI_REL_OFFSET rcx, RCX+8 incl %ebx leaq native_irq_return_iret(%rip),%rcx cmpq %rcx,RIP+8(%rsp) diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index d5dd80814419..a9a4229f6161 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -375,7 +375,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, /* * These bits must be zero. */ - xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0; + memset(xsave_hdr->reserved, 0, 48); return ret; } diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 7f50156542fb..1e6cff5814fa 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -78,7 +78,7 @@ void __init init_ISA_irqs(void) #endif legacy_pic->init(0); - for (i = 0; i < legacy_pic->nr_legacy_irqs; i++) + for (i = 0; i < nr_legacy_irqs(); i++) irq_set_chip_and_handler_name(i, chip, handle_level_irq, name); } @@ -87,12 +87,6 @@ void __init init_IRQ(void) int i; /* - * We probably need a better place for this, but it works for - * now ... - */ - x86_add_irq_domains(); - - /* * On cpu 0, Assign IRQ0_VECTOR..IRQ15_VECTOR's to IRQ 0..15. * If these IRQ's are handled by legacy interrupt-controllers like PIC, * then this configuration will likely be static after the boot. If @@ -100,7 +94,7 @@ void __init init_IRQ(void) * then this vector space can be freed and re-used dynamically as the * irq's migrate etc. */ - for (i = 0; i < legacy_pic->nr_legacy_irqs; i++) + for (i = 0; i < nr_legacy_irqs(); i++) per_cpu(vector_irq, 0)[IRQ0_VECTOR + i] = i; x86_init.irqs.intr_init(); @@ -121,7 +115,7 @@ void setup_vector_irq(int cpu) * legacy PIC, for the new cpu that is coming online, setup the static * legacy vector to irq mapping: */ - for (irq = 0; irq < legacy_pic->nr_legacy_irqs; irq++) + for (irq = 0; irq < nr_legacy_irqs(); irq++) per_cpu(vector_irq, cpu)[IRQ0_VECTOR + irq] = irq; #endif diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index d2b56489d70f..2d2a237f2c73 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -19,6 +19,7 @@ #include <linux/module.h> #include <linux/smp.h> #include <linux/pci.h> +#include <linux/irqdomain.h> #include <asm/mtrr.h> #include <asm/mpspec.h> @@ -67,7 +68,7 @@ static void __init MP_processor_info(struct mpc_cpu *m) boot_cpu_physical_apicid = m->apicid; } - printk(KERN_INFO "Processor #%d%s\n", m->apicid, bootup_cpu); + pr_info("Processor #%d%s\n", m->apicid, bootup_cpu); generic_processor_info(apicid, m->apicver); } @@ -87,9 +88,8 @@ static void __init MP_bus_info(struct mpc_bus *m) #if MAX_MP_BUSSES < 256 if (m->busid >= MAX_MP_BUSSES) { - printk(KERN_WARNING "MP table busid value (%d) for bustype %s " - " is too large, max. supported is %d\n", - m->busid, str, MAX_MP_BUSSES - 1); + pr_warn("MP table busid value (%d) for bustype %s is too large, max. supported is %d\n", + m->busid, str, MAX_MP_BUSSES - 1); return; } #endif @@ -110,19 +110,29 @@ static void __init MP_bus_info(struct mpc_bus *m) mp_bus_id_to_type[m->busid] = MP_BUS_EISA; #endif } else - printk(KERN_WARNING "Unknown bustype %s - ignoring\n", str); + pr_warn("Unknown bustype %s - ignoring\n", str); } +static struct irq_domain_ops mp_ioapic_irqdomain_ops = { + .map = mp_irqdomain_map, + .unmap = mp_irqdomain_unmap, +}; + static void __init MP_ioapic_info(struct mpc_ioapic *m) { + struct ioapic_domain_cfg cfg = { + .type = IOAPIC_DOMAIN_LEGACY, + .ops = &mp_ioapic_irqdomain_ops, + }; + if (m->flags & MPC_APIC_USABLE) - mp_register_ioapic(m->apicid, m->apicaddr, gsi_top); + mp_register_ioapic(m->apicid, m->apicaddr, gsi_top, &cfg); } static void __init print_mp_irq_info(struct mpc_intsrc *mp_irq) { - apic_printk(APIC_VERBOSE, "Int: type %d, pol %d, trig %d, bus %02x," - " IRQ %02x, APIC ID %x, APIC INT %02x\n", + apic_printk(APIC_VERBOSE, + "Int: type %d, pol %d, trig %d, bus %02x, IRQ %02x, APIC ID %x, APIC INT %02x\n", mp_irq->irqtype, mp_irq->irqflag & 3, (mp_irq->irqflag >> 2) & 3, mp_irq->srcbus, mp_irq->srcbusirq, mp_irq->dstapic, mp_irq->dstirq); @@ -135,8 +145,8 @@ static inline void __init MP_ioapic_info(struct mpc_ioapic *m) {} static void __init MP_lintsrc_info(struct mpc_lintsrc *m) { - apic_printk(APIC_VERBOSE, "Lint: type %d, pol %d, trig %d, bus %02x," - " IRQ %02x, APIC ID %x, APIC LINT %02x\n", + apic_printk(APIC_VERBOSE, + "Lint: type %d, pol %d, trig %d, bus %02x, IRQ %02x, APIC ID %x, APIC LINT %02x\n", m->irqtype, m->irqflag & 3, (m->irqflag >> 2) & 3, m->srcbusid, m->srcbusirq, m->destapic, m->destapiclint); } @@ -148,34 +158,33 @@ static int __init smp_check_mpc(struct mpc_table *mpc, char *oem, char *str) { if (memcmp(mpc->signature, MPC_SIGNATURE, 4)) { - printk(KERN_ERR "MPTABLE: bad signature [%c%c%c%c]!\n", + pr_err("MPTABLE: bad signature [%c%c%c%c]!\n", mpc->signature[0], mpc->signature[1], mpc->signature[2], mpc->signature[3]); return 0; } if (mpf_checksum((unsigned char *)mpc, mpc->length)) { - printk(KERN_ERR "MPTABLE: checksum error!\n"); + pr_err("MPTABLE: checksum error!\n"); return 0; } if (mpc->spec != 0x01 && mpc->spec != 0x04) { - printk(KERN_ERR "MPTABLE: bad table version (%d)!!\n", - mpc->spec); + pr_err("MPTABLE: bad table version (%d)!!\n", mpc->spec); return 0; } if (!mpc->lapic) { - printk(KERN_ERR "MPTABLE: null local APIC address!\n"); + pr_err("MPTABLE: null local APIC address!\n"); return 0; } memcpy(oem, mpc->oem, 8); oem[8] = 0; - printk(KERN_INFO "MPTABLE: OEM ID: %s\n", oem); + pr_info("MPTABLE: OEM ID: %s\n", oem); memcpy(str, mpc->productid, 12); str[12] = 0; - printk(KERN_INFO "MPTABLE: Product ID: %s\n", str); + pr_info("MPTABLE: Product ID: %s\n", str); - printk(KERN_INFO "MPTABLE: APIC at: 0x%X\n", mpc->lapic); + pr_info("MPTABLE: APIC at: 0x%X\n", mpc->lapic); return 1; } @@ -188,8 +197,8 @@ static void skip_entry(unsigned char **ptr, int *count, int size) static void __init smp_dump_mptable(struct mpc_table *mpc, unsigned char *mpt) { - printk(KERN_ERR "Your mptable is wrong, contact your HW vendor!\n" - "type %x\n", *mpt); + pr_err("Your mptable is wrong, contact your HW vendor!\n"); + pr_cont("type %x\n", *mpt); print_hex_dump(KERN_ERR, " ", DUMP_PREFIX_ADDRESS, 16, 1, mpc, mpc->length, 1); } @@ -207,9 +216,6 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early) if (!smp_check_mpc(mpc, oem, str)) return 0; -#ifdef CONFIG_X86_32 - generic_mps_oem_check(mpc, oem, str); -#endif /* Initialize the lapic mapping */ if (!acpi_lapic) register_lapic_address(mpc->lapic); @@ -259,7 +265,7 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early) } if (!num_processors) - printk(KERN_ERR "MPTABLE: no processors registered!\n"); + pr_err("MPTABLE: no processors registered!\n"); return num_processors; } @@ -295,16 +301,13 @@ static void __init construct_default_ioirq_mptable(int mpc_default_type) * If it does, we assume it's valid. */ if (mpc_default_type == 5) { - printk(KERN_INFO "ISA/PCI bus type with no IRQ information... " - "falling back to ELCR\n"); + pr_info("ISA/PCI bus type with no IRQ information... falling back to ELCR\n"); if (ELCR_trigger(0) || ELCR_trigger(1) || ELCR_trigger(2) || ELCR_trigger(13)) - printk(KERN_ERR "ELCR contains invalid data... " - "not using ELCR\n"); + pr_err("ELCR contains invalid data... not using ELCR\n"); else { - printk(KERN_INFO - "Using ELCR to identify PCI interrupts\n"); + pr_info("Using ELCR to identify PCI interrupts\n"); ELCR_fallback = 1; } } @@ -353,7 +356,7 @@ static void __init construct_ioapic_table(int mpc_default_type) bus.busid = 0; switch (mpc_default_type) { default: - printk(KERN_ERR "???\nUnknown standard configuration %d\n", + pr_err("???\nUnknown standard configuration %d\n", mpc_default_type); /* fall through */ case 1: @@ -462,8 +465,8 @@ static int __init check_physptr(struct mpf_intel *mpf, unsigned int early) #ifdef CONFIG_X86_LOCAL_APIC smp_found_config = 0; #endif - printk(KERN_ERR "BIOS bug, MP table errors detected!...\n" - "... disabling SMP support. (tell your hw vendor)\n"); + pr_err("BIOS bug, MP table errors detected!...\n"); + pr_cont("... disabling SMP support. (tell your hw vendor)\n"); early_iounmap(mpc, size); return -1; } @@ -481,8 +484,7 @@ static int __init check_physptr(struct mpf_intel *mpf, unsigned int early) if (!mp_irq_entries) { struct mpc_bus bus; - printk(KERN_ERR "BIOS bug, no explicit IRQ entries, " - "using default mptable. (tell your hw vendor)\n"); + pr_err("BIOS bug, no explicit IRQ entries, using default mptable. (tell your hw vendor)\n"); bus.type = MP_BUS; bus.busid = 0; @@ -516,14 +518,14 @@ void __init default_get_smp_config(unsigned int early) if (acpi_lapic && acpi_ioapic) return; - printk(KERN_INFO "Intel MultiProcessor Specification v1.%d\n", - mpf->specification); + pr_info("Intel MultiProcessor Specification v1.%d\n", + mpf->specification); #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32) if (mpf->feature2 & (1 << 7)) { - printk(KERN_INFO " IMCR and PIC compatibility mode.\n"); + pr_info(" IMCR and PIC compatibility mode.\n"); pic_mode = 1; } else { - printk(KERN_INFO " Virtual Wire compatibility mode.\n"); + pr_info(" Virtual Wire compatibility mode.\n"); pic_mode = 0; } #endif @@ -539,8 +541,7 @@ void __init default_get_smp_config(unsigned int early) return; } - printk(KERN_INFO "Default MP configuration #%d\n", - mpf->feature1); + pr_info("Default MP configuration #%d\n", mpf->feature1); construct_default_ISA_mptable(mpf->feature1); } else if (mpf->physptr) { @@ -550,7 +551,7 @@ void __init default_get_smp_config(unsigned int early) BUG(); if (!early) - printk(KERN_INFO "Processors: %d\n", num_processors); + pr_info("Processors: %d\n", num_processors); /* * Only use the first configuration found. */ @@ -583,10 +584,10 @@ static int __init smp_scan_config(unsigned long base, unsigned long length) #endif mpf_found = mpf; - printk(KERN_INFO "found SMP MP-table at [mem %#010llx-%#010llx] mapped at [%p]\n", - (unsigned long long) virt_to_phys(mpf), - (unsigned long long) virt_to_phys(mpf) + - sizeof(*mpf) - 1, mpf); + pr_info("found SMP MP-table at [mem %#010llx-%#010llx] mapped at [%p]\n", + (unsigned long long) virt_to_phys(mpf), + (unsigned long long) virt_to_phys(mpf) + + sizeof(*mpf) - 1, mpf); mem = virt_to_phys(mpf); memblock_reserve(mem, sizeof(*mpf)); @@ -735,7 +736,7 @@ static int __init replace_intsrc_all(struct mpc_table *mpc, int nr_m_spare = 0; unsigned char *mpt = ((unsigned char *)mpc) + count; - printk(KERN_INFO "mpc_length %x\n", mpc->length); + pr_info("mpc_length %x\n", mpc->length); while (count < mpc->length) { switch (*mpt) { case MP_PROCESSOR: @@ -862,13 +863,13 @@ static int __init update_mp_table(void) if (!smp_check_mpc(mpc, oem, str)) return 0; - printk(KERN_INFO "mpf: %llx\n", (u64)virt_to_phys(mpf)); - printk(KERN_INFO "physptr: %x\n", mpf->physptr); + pr_info("mpf: %llx\n", (u64)virt_to_phys(mpf)); + pr_info("physptr: %x\n", mpf->physptr); if (mpc_new_phys && mpc->length > mpc_new_length) { mpc_new_phys = 0; - printk(KERN_INFO "mpc_new_length is %ld, please use alloc_mptable=8k\n", - mpc_new_length); + pr_info("mpc_new_length is %ld, please use alloc_mptable=8k\n", + mpc_new_length); } if (!mpc_new_phys) { @@ -879,10 +880,10 @@ static int __init update_mp_table(void) mpc->checksum = 0xff; new = mpf_checksum((unsigned char *)mpc, mpc->length); if (old == new) { - printk(KERN_INFO "mpc is readonly, please try alloc_mptable instead\n"); + pr_info("mpc is readonly, please try alloc_mptable instead\n"); return 0; } - printk(KERN_INFO "use in-position replacing\n"); + pr_info("use in-position replacing\n"); } else { mpf->physptr = mpc_new_phys; mpc_new = phys_to_virt(mpc_new_phys); @@ -892,7 +893,7 @@ static int __init update_mp_table(void) if (mpc_new_phys - mpf->physptr) { struct mpf_intel *mpf_new; /* steal 16 bytes from [0, 1k) */ - printk(KERN_INFO "mpf new: %x\n", 0x400 - 16); + pr_info("mpf new: %x\n", 0x400 - 16); mpf_new = phys_to_virt(0x400 - 16); memcpy(mpf_new, mpf, 16); mpf = mpf_new; @@ -900,7 +901,7 @@ static int __init update_mp_table(void) } mpf->checksum = 0; mpf->checksum -= mpf_checksum((unsigned char *)mpf, 16); - printk(KERN_INFO "physptr new: %x\n", mpf->physptr); + pr_info("physptr new: %x\n", mpf->physptr); } /* diff --git a/arch/x86/kernel/pmc_atom.c b/arch/x86/kernel/pmc_atom.c new file mode 100644 index 000000000000..0d92ef6b5860 --- /dev/null +++ b/arch/x86/kernel/pmc_atom.c @@ -0,0 +1,321 @@ +/* + * Intel Atom SOC Power Management Controller Driver + * Copyright (c) 2014, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/pci.h> +#include <linux/device.h> +#include <linux/debugfs.h> +#include <linux/seq_file.h> +#include <linux/io.h> + +#include <asm/pmc_atom.h> + +#define DRIVER_NAME KBUILD_MODNAME + +struct pmc_dev { + u32 base_addr; + void __iomem *regmap; +#ifdef CONFIG_DEBUG_FS + struct dentry *dbgfs_dir; +#endif /* CONFIG_DEBUG_FS */ +}; + +static struct pmc_dev pmc_device; +static u32 acpi_base_addr; + +struct pmc_dev_map { + const char *name; + u32 bit_mask; +}; + +static const struct pmc_dev_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}, + {"3 - LPSS1_F3_HSUART1", BIT_LPSS1_F3_HSUART1}, + {"4 - LPSS1_F4_HSUART2", BIT_LPSS1_F4_HSUART2}, + {"5 - LPSS1_F5_SPI", BIT_LPSS1_F5_SPI}, + {"6 - LPSS1_F6_Reserved", BIT_LPSS1_F6_XXX}, + {"7 - LPSS1_F7_Reserved", BIT_LPSS1_F7_XXX}, + {"8 - SCC_EMMC", BIT_SCC_EMMC}, + {"9 - SCC_SDIO", BIT_SCC_SDIO}, + {"10 - SCC_SDCARD", BIT_SCC_SDCARD}, + {"11 - SCC_MIPI", BIT_SCC_MIPI}, + {"12 - HDA", BIT_HDA}, + {"13 - LPE", BIT_LPE}, + {"14 - OTG", BIT_OTG}, + {"15 - USH", BIT_USH}, + {"16 - GBE", BIT_GBE}, + {"17 - SATA", BIT_SATA}, + {"18 - USB_EHCI", BIT_USB_EHCI}, + {"19 - SEC", BIT_SEC}, + {"20 - PCIE_PORT0", BIT_PCIE_PORT0}, + {"21 - PCIE_PORT1", BIT_PCIE_PORT1}, + {"22 - PCIE_PORT2", BIT_PCIE_PORT2}, + {"23 - PCIE_PORT3", BIT_PCIE_PORT3}, + {"24 - LPSS2_F0_DMA", BIT_LPSS2_F0_DMA}, + {"25 - LPSS2_F1_I2C1", BIT_LPSS2_F1_I2C1}, + {"26 - LPSS2_F2_I2C2", BIT_LPSS2_F2_I2C2}, + {"27 - LPSS2_F3_I2C3", BIT_LPSS2_F3_I2C3}, + {"28 - LPSS2_F3_I2C4", BIT_LPSS2_F4_I2C4}, + {"29 - LPSS2_F5_I2C5", BIT_LPSS2_F5_I2C5}, + {"30 - LPSS2_F6_I2C6", BIT_LPSS2_F6_I2C6}, + {"31 - LPSS2_F7_I2C7", BIT_LPSS2_F7_I2C7}, + {"32 - SMB", BIT_SMB}, + {"33 - OTG_SS_PHY", BIT_OTG_SS_PHY}, + {"34 - USH_SS_PHY", BIT_USH_SS_PHY}, + {"35 - DFX", BIT_DFX}, +}; + +static inline u32 pmc_reg_read(struct pmc_dev *pmc, int reg_offset) +{ + return readl(pmc->regmap + reg_offset); +} + +static inline void pmc_reg_write(struct pmc_dev *pmc, int reg_offset, u32 val) +{ + writel(val, pmc->regmap + reg_offset); +} + +static void pmc_power_off(void) +{ + u16 pm1_cnt_port; + u32 pm1_cnt_value; + + pr_info("Preparing to enter system sleep state S5\n"); + + pm1_cnt_port = acpi_base_addr + PM1_CNT; + + pm1_cnt_value = inl(pm1_cnt_port); + pm1_cnt_value &= SLEEP_TYPE_MASK; + pm1_cnt_value |= SLEEP_TYPE_S5; + pm1_cnt_value |= SLEEP_ENABLE; + + outl(pm1_cnt_value, pm1_cnt_port); +} + +static void pmc_hw_reg_setup(struct pmc_dev *pmc) +{ + /* + * Disable PMC S0IX_WAKE_EN events coming from: + * - LPC clock run + * - GPIO_SUS ored dedicated IRQs + * - GPIO_SCORE ored dedicated IRQs + * - GPIO_SUS shared IRQ + * - GPIO_SCORE shared IRQ + */ + pmc_reg_write(pmc, PMC_S0IX_WAKE_EN, (u32)PMC_WAKE_EN_SETTING); +} + +#ifdef CONFIG_DEBUG_FS +static int pmc_dev_state_show(struct seq_file *s, void *unused) +{ + struct pmc_dev *pmc = s->private; + u32 func_dis, func_dis_2, func_dis_index; + u32 d3_sts_0, d3_sts_1, d3_sts_index; + int dev_num, dev_index, reg_index; + + func_dis = pmc_reg_read(pmc, PMC_FUNC_DIS); + func_dis_2 = pmc_reg_read(pmc, PMC_FUNC_DIS_2); + d3_sts_0 = pmc_reg_read(pmc, PMC_D3_STS_0); + d3_sts_1 = pmc_reg_read(pmc, PMC_D3_STS_1); + + dev_num = ARRAY_SIZE(dev_map); + + for (dev_index = 0; dev_index < dev_num; dev_index++) { + reg_index = dev_index / PMC_REG_BIT_WIDTH; + if (reg_index) { + func_dis_index = func_dis_2; + d3_sts_index = d3_sts_1; + } else { + func_dis_index = func_dis; + d3_sts_index = d3_sts_0; + } + + seq_printf(s, "Dev: %-32s\tState: %s [%s]\n", + dev_map[dev_index].name, + dev_map[dev_index].bit_mask & func_dis_index ? + "Disabled" : "Enabled ", + dev_map[dev_index].bit_mask & d3_sts_index ? + "D3" : "D0"); + } + return 0; +} + +static int pmc_dev_state_open(struct inode *inode, struct file *file) +{ + return single_open(file, pmc_dev_state_show, inode->i_private); +} + +static const struct file_operations pmc_dev_state_ops = { + .open = pmc_dev_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; + u64 s0ir_tmr, s0i1_tmr, s0i2_tmr, s0i3_tmr, s0_tmr; + + s0ir_tmr = pmc_reg_read(pmc, PMC_S0IR_TMR) << PMC_TMR_SHIFT; + s0i1_tmr = pmc_reg_read(pmc, PMC_S0I1_TMR) << PMC_TMR_SHIFT; + s0i2_tmr = pmc_reg_read(pmc, PMC_S0I2_TMR) << PMC_TMR_SHIFT; + s0i3_tmr = pmc_reg_read(pmc, PMC_S0I3_TMR) << PMC_TMR_SHIFT; + s0_tmr = pmc_reg_read(pmc, PMC_S0_TMR) << PMC_TMR_SHIFT; + + seq_printf(s, "S0IR Residency:\t%lldus\n", s0ir_tmr); + seq_printf(s, "S0I1 Residency:\t%lldus\n", s0i1_tmr); + seq_printf(s, "S0I2 Residency:\t%lldus\n", s0i2_tmr); + seq_printf(s, "S0I3 Residency:\t%lldus\n", s0i3_tmr); + seq_printf(s, "S0 Residency:\t%lldus\n", s0_tmr); + return 0; +} + +static int pmc_sleep_tmr_open(struct inode *inode, struct file *file) +{ + return single_open(file, pmc_sleep_tmr_show, inode->i_private); +} + +static const struct file_operations pmc_sleep_tmr_ops = { + .open = pmc_sleep_tmr_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +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) +{ + struct dentry *dir, *f; + + dir = debugfs_create_dir("pmc_atom", NULL); + if (!dir) + return -ENOMEM; + + 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"); + 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); + return -ENODEV; +} +#endif /* CONFIG_DEBUG_FS */ + +static int pmc_setup_dev(struct pci_dev *pdev) +{ + struct pmc_dev *pmc = &pmc_device; + int ret; + + /* Obtain ACPI base address */ + pci_read_config_dword(pdev, ACPI_BASE_ADDR_OFFSET, &acpi_base_addr); + acpi_base_addr &= ACPI_BASE_ADDR_MASK; + + /* Install power off function */ + if (acpi_base_addr != 0 && pm_power_off == NULL) + pm_power_off = pmc_power_off; + + pci_read_config_dword(pdev, PMC_BASE_ADDR_OFFSET, &pmc->base_addr); + pmc->base_addr &= PMC_BASE_ADDR_MASK; + + pmc->regmap = ioremap_nocache(pmc->base_addr, PMC_MMIO_REG_LEN); + if (!pmc->regmap) { + dev_err(&pdev->dev, "error: ioremap failed\n"); + return -ENOMEM; + } + + /* PMC hardware registers setup */ + pmc_hw_reg_setup(pmc); + +#ifdef CONFIG_DEBUG_FS + ret = pmc_dbgfs_register(pmc, pdev); + if (ret) { + iounmap(pmc->regmap); + return ret; + } +#endif /* CONFIG_DEBUG_FS */ + return 0; +} + +/* + * Data for PCI driver interface + * + * This data only exists for exporting the supported + * PCI ids via MODULE_DEVICE_TABLE. We do not actually + * register a pci_driver, because lpc_ich will register + * a driver on the same PCI id. + */ +static const struct pci_device_id pmc_pci_ids[] = { + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_VLV_PMC) }, + { 0, }, +}; + +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; + + /* We look for our device - PCU PMC + * we assume that there is max. one device. + * + * We can't use plain pci_driver mechanism, + * as the device is really a multiple function device, + * main driver that binds to the pci_device is lpc_ich + * and have to find & bind to the device this way. + */ + for_each_pci_dev(pdev) { + ent = pci_match_id(pmc_pci_ids, pdev); + if (ent) { + err = pmc_setup_dev(pdev); + goto out; + } + } + /* Device not found. */ +out: + return err; +} + +module_init(pmc_atom_init); +/* no module_exit, this driver shouldn't be unloaded */ + +MODULE_AUTHOR("Aubrey Li <aubrey.li@linux.intel.com>"); +MODULE_DESCRIPTION("Intel Atom SOC Power Management Controller Interface"); +MODULE_LICENSE("GPL v2"); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 4505e2a950d8..f804dc935d2a 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -93,6 +93,7 @@ void arch_task_cache_init(void) kmem_cache_create("task_xstate", xstate_size, __alignof__(union thread_xstate), SLAB_PANIC | SLAB_NOTRACK, NULL); + setup_xstate_comp(); } /* diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 52b1157c53eb..17962e667a91 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -28,6 +28,7 @@ #include <linux/mc146818rtc.h> #include <asm/realmode.h> #include <asm/x86_init.h> +#include <asm/efi.h> /* * Power off function, if any @@ -401,12 +402,25 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { static int __init reboot_init(void) { + int rv; + /* * Only do the DMI check if reboot_type hasn't been overridden * on the command line */ - if (reboot_default) - dmi_check_system(reboot_dmi_table); + if (!reboot_default) + return 0; + + /* + * The DMI quirks table takes precedence. If no quirks entry + * matches and the ACPI Hardware Reduced bit is set, force EFI + * reboot. + */ + rv = dmi_check_system(reboot_dmi_table); + + if (!rv && efi_reboot_required()) + reboot_type = BOOT_EFI; + return 0; } core_initcall(reboot_init); @@ -528,11 +542,7 @@ static void native_machine_emergency_restart(void) break; case BOOT_EFI: - if (efi_enabled(EFI_RUNTIME_SERVICES)) - efi.reset_system(reboot_mode == REBOOT_WARM ? - EFI_RESET_WARM : - EFI_RESET_COLD, - EFI_SUCCESS, 0, NULL); + efi_reboot(reboot_mode, NULL); reboot_type = BOOT_BIOS; break; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 78a0e6298922..41ead8d3bc0b 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -924,10 +924,10 @@ void __init setup_arch(char **cmdline_p) #endif #ifdef CONFIG_EFI if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, - "EL32", 4)) { + EFI32_LOADER_SIGNATURE, 4)) { set_bit(EFI_BOOT, &efi.flags); } else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, - "EL64", 4)) { + EFI64_LOADER_SIGNATURE, 4)) { set_bit(EFI_BOOT, &efi.flags); set_bit(EFI_64BIT, &efi.flags); } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 5492798930ef..2d872e08fab9 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -168,10 +168,6 @@ static void smp_callin(void) * CPU, first the APIC. (this is probably redundant on most * boards) */ - - pr_debug("CALLIN, before setup_local_APIC()\n"); - if (apic->smp_callin_clear_local_apic) - apic->smp_callin_clear_local_apic(); setup_local_APIC(); end_local_APIC_setup(); @@ -1143,10 +1139,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) enable_IO_APIC(); bsp_end_local_APIC_setup(); - - if (apic->setup_portio_remap) - apic->setup_portio_remap(); - smpboot_setup_io_apic(); /* * Set up local APIC timer on boot CPU. diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index ea030319b321..b6025f9e36c6 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -234,9 +234,6 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc) return ns; } -/* XXX surely we already have this someplace in the kernel?! */ -#define DIV_ROUND(n, d) (((n) + ((d) / 2)) / (d)) - static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) { unsigned long long tsc_now, ns_now; @@ -259,7 +256,9 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) * time function is continuous; see the comment near struct * cyc2ns_data. */ - data->cyc2ns_mul = DIV_ROUND(NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR, cpu_khz); + data->cyc2ns_mul = + DIV_ROUND_CLOSEST(NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR, + cpu_khz); data->cyc2ns_shift = CYC2NS_SCALE_FACTOR; data->cyc2ns_offset = ns_now - mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR); @@ -951,7 +950,7 @@ core_initcall(cpufreq_tsc); static struct clocksource clocksource_tsc; /* - * We compare the TSC to the cycle_last value in the clocksource + * We used to compare the TSC to the cycle_last value in the clocksource * structure to avoid a nasty time-warp. This can be observed in a * very small window right after one CPU updated cycle_last under * xtime/vsyscall_gtod lock and the other CPU reads a TSC value which @@ -961,26 +960,23 @@ static struct clocksource clocksource_tsc; * due to the unsigned delta calculation of the time keeping core * code, which is necessary to support wrapping clocksources like pm * timer. + * + * This sanity check is now done in the core timekeeping code. + * checking the result of read_tsc() - cycle_last for being negative. + * That works because CLOCKSOURCE_MASK(64) does not mask out any bit. */ static cycle_t read_tsc(struct clocksource *cs) { - cycle_t ret = (cycle_t)get_cycles(); - - return ret >= clocksource_tsc.cycle_last ? - ret : clocksource_tsc.cycle_last; -} - -static void resume_tsc(struct clocksource *cs) -{ - if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3)) - clocksource_tsc.cycle_last = 0; + return (cycle_t)get_cycles(); } +/* + * .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc() + */ static struct clocksource clocksource_tsc = { .name = "tsc", .rating = 300, .read = read_tsc, - .resume = resume_tsc, .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_MUST_VERIFY, diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index ea5b5709aa76..e1e1e80fc6a6 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -81,10 +81,10 @@ static void warn_bad_vsyscall(const char *level, struct pt_regs *regs, if (!show_unhandled_signals) return; - pr_notice_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", - level, current->comm, task_pid_nr(current), - message, regs->ip, regs->cs, - regs->sp, regs->ax, regs->si, regs->di); + printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", + level, current->comm, task_pid_nr(current), + message, regs->ip, regs->cs, + regs->sp, regs->ax, regs->si, regs->di); } static int addr_to_vsyscall_nr(unsigned long addr) diff --git a/arch/x86/kernel/vsyscall_gtod.c b/arch/x86/kernel/vsyscall_gtod.c index 9531fbb123ba..c7d791f32b98 100644 --- a/arch/x86/kernel/vsyscall_gtod.c +++ b/arch/x86/kernel/vsyscall_gtod.c @@ -31,29 +31,30 @@ void update_vsyscall(struct timekeeper *tk) gtod_write_begin(vdata); /* copy vsyscall data */ - vdata->vclock_mode = tk->clock->archdata.vclock_mode; - vdata->cycle_last = tk->clock->cycle_last; - vdata->mask = tk->clock->mask; - vdata->mult = tk->mult; - vdata->shift = tk->shift; + vdata->vclock_mode = tk->tkr.clock->archdata.vclock_mode; + vdata->cycle_last = tk->tkr.cycle_last; + vdata->mask = tk->tkr.mask; + vdata->mult = tk->tkr.mult; + vdata->shift = tk->tkr.shift; vdata->wall_time_sec = tk->xtime_sec; - vdata->wall_time_snsec = tk->xtime_nsec; + vdata->wall_time_snsec = tk->tkr.xtime_nsec; vdata->monotonic_time_sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; - vdata->monotonic_time_snsec = tk->xtime_nsec + vdata->monotonic_time_snsec = tk->tkr.xtime_nsec + ((u64)tk->wall_to_monotonic.tv_nsec - << tk->shift); + << tk->tkr.shift); while (vdata->monotonic_time_snsec >= - (((u64)NSEC_PER_SEC) << tk->shift)) { + (((u64)NSEC_PER_SEC) << tk->tkr.shift)) { vdata->monotonic_time_snsec -= - ((u64)NSEC_PER_SEC) << tk->shift; + ((u64)NSEC_PER_SEC) << tk->tkr.shift; vdata->monotonic_time_sec++; } vdata->wall_time_coarse_sec = tk->xtime_sec; - vdata->wall_time_coarse_nsec = (long)(tk->xtime_nsec >> tk->shift); + vdata->wall_time_coarse_nsec = (long)(tk->tkr.xtime_nsec >> + tk->tkr.shift); vdata->monotonic_time_coarse_sec = vdata->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec; diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index a4b451c6addf..940b142cc11f 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -8,6 +8,7 @@ #include <linux/bootmem.h> #include <linux/compat.h> +#include <linux/cpu.h> #include <asm/i387.h> #include <asm/fpu-internal.h> #include <asm/sigframe.h> @@ -24,7 +25,9 @@ u64 pcntxt_mask; struct xsave_struct *init_xstate_buf; static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32; -static unsigned int *xstate_offsets, *xstate_sizes, xstate_features; +static unsigned int *xstate_offsets, *xstate_sizes; +static unsigned int xstate_comp_offsets[sizeof(pcntxt_mask)*8]; +static unsigned int xstate_features; /* * If a processor implementation discern that a processor state component is @@ -283,7 +286,7 @@ sanitize_restored_xstate(struct task_struct *tsk, if (use_xsave()) { /* These bits must be zero. */ - xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0; + memset(xsave_hdr->reserved, 0, 48); /* * Init the state that is not present in the memory @@ -479,6 +482,52 @@ static void __init setup_xstate_features(void) } /* + * This function sets up offsets and sizes of all extended states in + * xsave area. This supports both standard format and compacted format + * of the xsave aread. + * + * Input: void + * Output: void + */ +void setup_xstate_comp(void) +{ + unsigned int xstate_comp_sizes[sizeof(pcntxt_mask)*8]; + int i; + + /* + * The FP xstates and SSE xstates are legacy states. They are always + * in the fixed offsets in the xsave area in either compacted form + * or standard form. + */ + xstate_comp_offsets[0] = 0; + xstate_comp_offsets[1] = offsetof(struct i387_fxsave_struct, xmm_space); + + if (!cpu_has_xsaves) { + for (i = 2; i < xstate_features; i++) { + if (test_bit(i, (unsigned long *)&pcntxt_mask)) { + xstate_comp_offsets[i] = xstate_offsets[i]; + xstate_comp_sizes[i] = xstate_sizes[i]; + } + } + return; + } + + xstate_comp_offsets[2] = FXSAVE_SIZE + XSAVE_HDR_SIZE; + + for (i = 2; i < xstate_features; i++) { + if (test_bit(i, (unsigned long *)&pcntxt_mask)) + xstate_comp_sizes[i] = xstate_sizes[i]; + else + xstate_comp_sizes[i] = 0; + + if (i > 2) + xstate_comp_offsets[i] = xstate_comp_offsets[i-1] + + xstate_comp_sizes[i-1]; + + } +} + +/* * setup the xstate image representing the init state */ static void __init setup_init_fpu_buf(void) @@ -496,15 +545,21 @@ static void __init setup_init_fpu_buf(void) setup_xstate_features(); + if (cpu_has_xsaves) { + init_xstate_buf->xsave_hdr.xcomp_bv = + (u64)1 << 63 | pcntxt_mask; + init_xstate_buf->xsave_hdr.xstate_bv = pcntxt_mask; + } + /* * Init all the features state with header_bv being 0x0 */ - xrstor_state(init_xstate_buf, -1); + xrstor_state_booting(init_xstate_buf, -1); /* * Dump the init state again. This is to identify the init state * of any feature which is not represented by all zero's. */ - xsave_state(init_xstate_buf, -1); + xsave_state_booting(init_xstate_buf, -1); } static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO; @@ -520,6 +575,30 @@ static int __init eager_fpu_setup(char *s) } __setup("eagerfpu=", eager_fpu_setup); + +/* + * Calculate total size of enabled xstates in XCR0/pcntxt_mask. + */ +static void __init init_xstate_size(void) +{ + unsigned int eax, ebx, ecx, edx; + int i; + + if (!cpu_has_xsaves) { + cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); + xstate_size = ebx; + return; + } + + xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE; + for (i = 2; i < 64; i++) { + if (test_bit(i, (unsigned long *)&pcntxt_mask)) { + cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); + xstate_size += eax; + } + } +} + /* * Enable and initialize the xsave feature. */ @@ -551,8 +630,7 @@ static void __init xstate_enable_boot_cpu(void) /* * Recompute the context size for enabled features */ - cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); - xstate_size = ebx; + init_xstate_size(); update_regset_xstate_info(xstate_size, pcntxt_mask); prepare_fx_sw_frame(); @@ -572,8 +650,9 @@ static void __init xstate_enable_boot_cpu(void) } } - pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x\n", - pcntxt_mask, xstate_size); + pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x using %s\n", + pcntxt_mask, xstate_size, + cpu_has_xsaves ? "compacted form" : "standard form"); } /* @@ -635,3 +714,26 @@ void eager_fpu_init(void) else fxrstor_checking(&init_xstate_buf->i387); } + +/* + * Given the xsave area and a state inside, this function returns the + * address of the state. + * + * This is the API that is called to get xstate address in either + * standard format or compacted format of xsave area. + * + * Inputs: + * xsave: base address of the xsave area; + * xstate: state which is defined in xsave.h (e.g. XSTATE_FP, XSTATE_SSE, + * etc.) + * Output: + * address of the state in the xsave area. + */ +void *get_xsave_addr(struct xsave_struct *xsave, int xstate) +{ + int feature = fls64(xstate) - 1; + if (!test_bit(feature, (unsigned long *)&pcntxt_mask)) + return NULL; + + return (void *)xsave + xstate_comp_offsets[feature]; +} diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ef432f891d30..f169f8bbd5aa 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -984,9 +984,8 @@ struct pvclock_gtod_data { u32 shift; } clock; - /* open coded 'struct timespec' */ - u64 monotonic_time_snsec; - time_t monotonic_time_sec; + u64 boot_ns; + u64 nsec_base; }; static struct pvclock_gtod_data pvclock_gtod_data; @@ -994,27 +993,21 @@ static struct pvclock_gtod_data pvclock_gtod_data; static void update_pvclock_gtod(struct timekeeper *tk) { struct pvclock_gtod_data *vdata = &pvclock_gtod_data; + u64 boot_ns; + + boot_ns = ktime_to_ns(ktime_add(tk->tkr.base_mono, tk->offs_boot)); write_seqcount_begin(&vdata->seq); /* copy pvclock gtod data */ - vdata->clock.vclock_mode = tk->clock->archdata.vclock_mode; - vdata->clock.cycle_last = tk->clock->cycle_last; - vdata->clock.mask = tk->clock->mask; - vdata->clock.mult = tk->mult; - vdata->clock.shift = tk->shift; - - vdata->monotonic_time_sec = tk->xtime_sec - + tk->wall_to_monotonic.tv_sec; - vdata->monotonic_time_snsec = tk->xtime_nsec - + (tk->wall_to_monotonic.tv_nsec - << tk->shift); - while (vdata->monotonic_time_snsec >= - (((u64)NSEC_PER_SEC) << tk->shift)) { - vdata->monotonic_time_snsec -= - ((u64)NSEC_PER_SEC) << tk->shift; - vdata->monotonic_time_sec++; - } + vdata->clock.vclock_mode = tk->tkr.clock->archdata.vclock_mode; + vdata->clock.cycle_last = tk->tkr.cycle_last; + vdata->clock.mask = tk->tkr.mask; + vdata->clock.mult = tk->tkr.mult; + vdata->clock.shift = tk->tkr.shift; + + vdata->boot_ns = boot_ns; + vdata->nsec_base = tk->tkr.xtime_nsec; write_seqcount_end(&vdata->seq); } @@ -1109,11 +1102,7 @@ static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz, static inline u64 get_kernel_ns(void) { - struct timespec ts; - - ktime_get_ts(&ts); - monotonic_to_bootbased(&ts); - return timespec_to_ns(&ts); + return ktime_get_boot_ns(); } #ifdef CONFIG_X86_64 @@ -1375,23 +1364,22 @@ static inline u64 vgettsc(cycle_t *cycle_now) return v * gtod->clock.mult; } -static int do_monotonic(struct timespec *ts, cycle_t *cycle_now) +static int do_monotonic_boot(s64 *t, cycle_t *cycle_now) { + struct pvclock_gtod_data *gtod = &pvclock_gtod_data; unsigned long seq; - u64 ns; int mode; - struct pvclock_gtod_data *gtod = &pvclock_gtod_data; + u64 ns; - ts->tv_nsec = 0; do { seq = read_seqcount_begin(>od->seq); mode = gtod->clock.vclock_mode; - ts->tv_sec = gtod->monotonic_time_sec; - ns = gtod->monotonic_time_snsec; + ns = gtod->nsec_base; ns += vgettsc(cycle_now); ns >>= gtod->clock.shift; + ns += gtod->boot_ns; } while (unlikely(read_seqcount_retry(>od->seq, seq))); - timespec_add_ns(ts, ns); + *t = ns; return mode; } @@ -1399,19 +1387,11 @@ static int do_monotonic(struct timespec *ts, cycle_t *cycle_now) /* returns true if host is using tsc clocksource */ static bool kvm_get_time_and_clockread(s64 *kernel_ns, cycle_t *cycle_now) { - struct timespec ts; - /* checked again under seqlock below */ if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC) return false; - if (do_monotonic(&ts, cycle_now) != VCLOCK_TSC) - return false; - - monotonic_to_bootbased(&ts); - *kernel_ns = timespec_to_ns(&ts); - - return true; + return do_monotonic_boot(kernel_ns, cycle_now) == VCLOCK_TSC; } #endif diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 36642793e315..1dbade870f90 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -577,6 +577,8 @@ static int is_f00f_bug(struct pt_regs *regs, unsigned long address) static const char nx_warning[] = KERN_CRIT "kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n"; +static const char smep_warning[] = KERN_CRIT +"unable to execute userspace code (SMEP?) (uid: %d)\n"; static void show_fault_oops(struct pt_regs *regs, unsigned long error_code, @@ -597,6 +599,10 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, if (pte && pte_present(*pte) && !pte_exec(*pte)) printk(nx_warning, from_kuid(&init_user_ns, current_uid())); + if (pte && pte_present(*pte) && pte_exec(*pte) && + (pgd_flags(*pgd) & _PAGE_USER) && + (read_cr4() & X86_CR4_SMEP)) + printk(smep_warning, from_kuid(&init_user_ns, current_uid())); } printk(KERN_ALERT "BUG: unable to handle kernel "); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index f97130618113..66dba36f2343 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -18,6 +18,13 @@ #include <asm/dma.h> /* for MAX_DMA_PFN */ #include <asm/microcode.h> +/* + * We need to define the tracepoints somewhere, and tlb.c + * is only compied when SMP=y. + */ +#define CREATE_TRACE_POINTS +#include <trace/events/tlb.h> + #include "mm_internal.h" static unsigned long __initdata pgt_buf_start; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index dd8dda167a24..1fe33987de02 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -49,6 +49,7 @@ void leave_mm(int cpu) if (cpumask_test_cpu(cpu, mm_cpumask(active_mm))) { cpumask_clear_cpu(cpu, mm_cpumask(active_mm)); load_cr3(swapper_pg_dir); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); } } EXPORT_SYMBOL_GPL(leave_mm); @@ -102,20 +103,24 @@ static void flush_tlb_func(void *info) if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm)) return; + if (!f->flush_end) + f->flush_end = f->flush_start + PAGE_SIZE; count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) { - if (f->flush_end == TLB_FLUSH_ALL) + if (f->flush_end == TLB_FLUSH_ALL) { local_flush_tlb(); - else if (!f->flush_end) - __flush_tlb_single(f->flush_start); - else { + trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, TLB_FLUSH_ALL); + } else { unsigned long addr; + unsigned long nr_pages = + f->flush_end - f->flush_start / PAGE_SIZE; addr = f->flush_start; while (addr < f->flush_end) { __flush_tlb_single(addr); addr += PAGE_SIZE; } + trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, nr_pages); } } else leave_mm(smp_processor_id()); @@ -153,46 +158,45 @@ void flush_tlb_current_task(void) count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); local_flush_tlb(); + trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL); if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL); preempt_enable(); } +/* + * See Documentation/x86/tlb.txt for details. We choose 33 + * because it is large enough to cover the vast majority (at + * least 95%) of allocations, and is small enough that we are + * confident it will not cause too much overhead. Each single + * flush is about 100 ns, so this caps the maximum overhead at + * _about_ 3,000 ns. + * + * This is in units of pages. + */ +unsigned long tlb_single_page_flush_ceiling = 33; + void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long vmflag) { unsigned long addr; - unsigned act_entries, tlb_entries = 0; - unsigned long nr_base_pages; + /* do a global flush by default */ + unsigned long base_pages_to_flush = TLB_FLUSH_ALL; preempt_disable(); if (current->active_mm != mm) - goto flush_all; + goto out; if (!current->mm) { leave_mm(smp_processor_id()); - goto flush_all; + goto out; } - if (end == TLB_FLUSH_ALL || tlb_flushall_shift == -1 - || vmflag & VM_HUGETLB) { - local_flush_tlb(); - goto flush_all; - } - - /* In modern CPU, last level tlb used for both data/ins */ - if (vmflag & VM_EXEC) - tlb_entries = tlb_lli_4k[ENTRIES]; - else - tlb_entries = tlb_lld_4k[ENTRIES]; + if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB)) + base_pages_to_flush = (end - start) >> PAGE_SHIFT; - /* Assume all of TLB entries was occupied by this task */ - act_entries = tlb_entries >> tlb_flushall_shift; - act_entries = mm->total_vm > act_entries ? act_entries : mm->total_vm; - nr_base_pages = (end - start) >> PAGE_SHIFT; - - /* tlb_flushall_shift is on balance point, details in commit log */ - if (nr_base_pages > act_entries) { + if (base_pages_to_flush > tlb_single_page_flush_ceiling) { + base_pages_to_flush = TLB_FLUSH_ALL; count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); local_flush_tlb(); } else { @@ -201,17 +205,15 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); __flush_tlb_single(addr); } - - if (cpumask_any_but(mm_cpumask(mm), - smp_processor_id()) < nr_cpu_ids) - flush_tlb_others(mm_cpumask(mm), mm, start, end); - preempt_enable(); - return; } - -flush_all: + trace_tlb_flush(TLB_LOCAL_MM_SHOOTDOWN, base_pages_to_flush); +out: + if (base_pages_to_flush == TLB_FLUSH_ALL) { + start = 0UL; + end = TLB_FLUSH_ALL; + } if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) - flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL); + flush_tlb_others(mm_cpumask(mm), mm, start, end); preempt_enable(); } @@ -260,32 +262,26 @@ static void do_kernel_range_flush(void *info) void flush_tlb_kernel_range(unsigned long start, unsigned long end) { - unsigned act_entries; - struct flush_tlb_info info; - - /* In modern CPU, last level tlb used for both data/ins */ - act_entries = tlb_lld_4k[ENTRIES]; /* Balance as user space task's flush, a bit conservative */ - if (end == TLB_FLUSH_ALL || tlb_flushall_shift == -1 || - (end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) - + if (end == TLB_FLUSH_ALL || + (end - start) > tlb_single_page_flush_ceiling * PAGE_SIZE) { on_each_cpu(do_flush_tlb_all, NULL, 1); - else { + } else { + struct flush_tlb_info info; info.flush_start = start; info.flush_end = end; on_each_cpu(do_kernel_range_flush, &info, 1); } } -#ifdef CONFIG_DEBUG_TLBFLUSH static ssize_t tlbflush_read_file(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { char buf[32]; unsigned int len; - len = sprintf(buf, "%hd\n", tlb_flushall_shift); + len = sprintf(buf, "%ld\n", tlb_single_page_flush_ceiling); return simple_read_from_buffer(user_buf, count, ppos, buf, len); } @@ -294,20 +290,20 @@ static ssize_t tlbflush_write_file(struct file *file, { char buf[32]; ssize_t len; - s8 shift; + int ceiling; len = min(count, sizeof(buf) - 1); if (copy_from_user(buf, user_buf, len)) return -EFAULT; buf[len] = '\0'; - if (kstrtos8(buf, 0, &shift)) + if (kstrtoint(buf, 0, &ceiling)) return -EINVAL; - if (shift < -1 || shift >= BITS_PER_LONG) + if (ceiling < 0) return -EINVAL; - tlb_flushall_shift = shift; + tlb_single_page_flush_ceiling = ceiling; return count; } @@ -317,11 +313,10 @@ static const struct file_operations fops_tlbflush = { .llseek = default_llseek, }; -static int __init create_tlb_flushall_shift(void) +static int __init create_tlb_single_page_flush_ceiling(void) { - debugfs_create_file("tlb_flushall_shift", S_IRUSR | S_IWUSR, + debugfs_create_file("tlb_single_page_flush_ceiling", S_IRUSR | S_IWUSR, arch_debugfs_dir, NULL, &fops_tlbflush); return 0; } -late_initcall(create_tlb_flushall_shift); -#endif +late_initcall(create_tlb_single_page_flush_ceiling); diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 5075371ab593..cfd1b132b8e3 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -448,7 +448,7 @@ static void probe_pci_root_info(struct pci_root_info *info, return; size = sizeof(*info->res) * info->res_num; - info->res = kzalloc(size, GFP_KERNEL); + info->res = kzalloc_node(size, GFP_KERNEL, info->sd.node); if (!info->res) { info->res_num = 0; return; @@ -456,7 +456,7 @@ static void probe_pci_root_info(struct pci_root_info *info, size = sizeof(*info->res_offset) * info->res_num; info->res_num = 0; - info->res_offset = kzalloc(size, GFP_KERNEL); + info->res_offset = kzalloc_node(size, GFP_KERNEL, info->sd.node); if (!info->res_offset) { kfree(info->res); info->res = NULL; @@ -499,7 +499,7 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) if (node != NUMA_NO_NODE && !node_online(node)) node = NUMA_NO_NODE; - info = kzalloc(sizeof(*info), GFP_KERNEL); + info = kzalloc_node(sizeof(*info), GFP_KERNEL, node); if (!info) { printk(KERN_WARNING "pci_bus %04x:%02x: " "ignored (out of memory)\n", domain, busnum); diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 84b9d672843d..09fece368592 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -208,27 +208,31 @@ static int pci_write(struct pci_bus *bus, unsigned int devfn, int where, static int intel_mid_pci_irq_enable(struct pci_dev *dev) { - u8 pin; - struct io_apic_irq_attr irq_attr; + int polarity; - pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); + if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_TANGIER) + polarity = 0; /* active high */ + else + polarity = 1; /* active low */ /* * MRST only have IOAPIC, the PCI irq lines are 1:1 mapped to * IOAPIC RTE entries, so we just enable RTE for the device. */ - irq_attr.ioapic = mp_find_ioapic(dev->irq); - irq_attr.ioapic_pin = dev->irq; - irq_attr.trigger = 1; /* level */ - if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_TANGIER) - irq_attr.polarity = 0; /* active high */ - else - irq_attr.polarity = 1; /* active low */ - io_apic_set_pci_routing(&dev->dev, dev->irq, &irq_attr); + if (mp_set_gsi_attr(dev->irq, 1, polarity, dev_to_node(&dev->dev))) + return -EBUSY; + if (mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC) < 0) + return -EBUSY; return 0; } +static void intel_mid_pci_irq_disable(struct pci_dev *dev) +{ + if (dev->irq > 0) + mp_unmap_irq(dev->irq); +} + struct pci_ops intel_mid_pci_ops = { .read = pci_read, .write = pci_write, @@ -245,6 +249,7 @@ int __init intel_mid_pci_init(void) pr_info("Intel MID platform detected, using MID PCI ops\n"); pci_mmcfg_late_init(); pcibios_enable_irq = intel_mid_pci_irq_enable; + pcibios_disable_irq = intel_mid_pci_irq_disable; pci_root_ops = intel_mid_pci_ops; pci_soc_mode = 1; /* Continue with standard init */ diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 84112f55dd7a..748cfe8ab322 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -26,6 +26,7 @@ static int acer_tm360_irqrouting; static struct irq_routing_table *pirq_table; static int pirq_enable_irq(struct pci_dev *dev); +static void pirq_disable_irq(struct pci_dev *dev); /* * Never use: 0, 1, 2 (timer, keyboard, and cascade) @@ -53,7 +54,7 @@ struct irq_router_handler { }; int (*pcibios_enable_irq)(struct pci_dev *dev) = pirq_enable_irq; -void (*pcibios_disable_irq)(struct pci_dev *dev) = NULL; +void (*pcibios_disable_irq)(struct pci_dev *dev) = pirq_disable_irq; /* * Check passed address for the PCI IRQ Routing Table signature @@ -1186,7 +1187,7 @@ void pcibios_penalize_isa_irq(int irq, int active) static int pirq_enable_irq(struct pci_dev *dev) { - u8 pin; + u8 pin = 0; pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); if (pin && !pcibios_lookup_irq(dev, 1)) { @@ -1227,8 +1228,6 @@ static int pirq_enable_irq(struct pci_dev *dev) } dev = temp_dev; if (irq >= 0) { - io_apic_set_pci_routing(&dev->dev, irq, - &irq_attr); dev->irq = irq; dev_info(&dev->dev, "PCI->APIC IRQ transform: " "INT %c -> IRQ %d\n", 'A' + pin - 1, irq); @@ -1254,3 +1253,11 @@ static int pirq_enable_irq(struct pci_dev *dev) } return 0; } + +static void pirq_disable_irq(struct pci_dev *dev) +{ + if (io_apic_assign_pci_irqs && dev->irq) { + mp_unmap_irq(dev->irq); + dev->irq = 0; + } +} diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 905956f16465..093f5f4272d3 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -23,6 +23,7 @@ #include <xen/features.h> #include <xen/events.h> #include <asm/xen/pci.h> +#include <asm/i8259.h> static int xen_pcifront_enable_irq(struct pci_dev *dev) { @@ -40,7 +41,7 @@ static int xen_pcifront_enable_irq(struct pci_dev *dev) /* In PV DomU the Xen PCI backend puts the PIRQ in the interrupt line.*/ pirq = gsi; - if (gsi < NR_IRQS_LEGACY) + if (gsi < nr_legacy_irqs()) share = 0; rc = xen_bind_pirq_gsi_to_irq(gsi, pirq, share, "pcifront"); @@ -511,7 +512,7 @@ int __init pci_xen_initial_domain(void) xen_setup_acpi_sci(); __acpi_register_gsi = acpi_register_gsi_xen; /* Pre-allocate legacy irqs */ - for (irq = 0; irq < NR_IRQS_LEGACY; irq++) { + for (irq = 0; irq < nr_legacy_irqs(); irq++) { int trigger, polarity; if (acpi_get_override_irq(irq, &trigger, &polarity) == -1) @@ -522,7 +523,7 @@ int __init pci_xen_initial_domain(void) true /* Map GSI to PIRQ */); } if (0 == nr_ioapics) { - for (irq = 0; irq < NR_IRQS_LEGACY; irq++) + for (irq = 0; irq < nr_legacy_irqs(); irq++) xen_bind_pirq_gsi_to_irq(irq, irq, 0, "xt-pic"); } return 0; diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c index 8244f5ec2f4c..701fd5843c87 100644 --- a/arch/x86/platform/ce4100/ce4100.c +++ b/arch/x86/platform/ce4100/ce4100.c @@ -135,14 +135,10 @@ static void __init sdv_arch_setup(void) sdv_serial_fixup(); } -#ifdef CONFIG_X86_IO_APIC static void sdv_pci_init(void) { x86_of_pci_init(); - /* We can't set this earlier, because we need to calibrate the timer */ - legacy_pic = &null_legacy_pic; } -#endif /* * CE4100 specific x86_init function overrides and early setup @@ -155,7 +151,9 @@ void __init x86_ce4100_early_setup(void) x86_init.resources.probe_roms = x86_init_noop; x86_init.mpparse.get_smp_config = x86_init_uint_noop; x86_init.mpparse.find_smp_config = x86_init_noop; + x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc_nocheck; x86_init.pci.init = ce4100_pci_init; + x86_init.pci.init_irq = sdv_pci_init; /* * By default, the reboot method is ACPI which is supported by the @@ -166,10 +164,5 @@ void __init x86_ce4100_early_setup(void) */ reboot_type = BOOT_KBD; -#ifdef CONFIG_X86_IO_APIC - x86_init.pci.init_irq = sdv_pci_init; - x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc_nocheck; -#endif - pm_power_off = ce4100_power_off; } diff --git a/arch/x86/platform/efi/Makefile b/arch/x86/platform/efi/Makefile index d51045afcaaf..2846aaab5103 100644 --- a/arch/x86/platform/efi/Makefile +++ b/arch/x86/platform/efi/Makefile @@ -1,4 +1,4 @@ -obj-$(CONFIG_EFI) += efi.o efi_$(BITS).o efi_stub_$(BITS).o +obj-$(CONFIG_EFI) += quirks.o efi.o efi_$(BITS).o efi_stub_$(BITS).o obj-$(CONFIG_ACPI_BGRT) += efi-bgrt.o obj-$(CONFIG_EARLY_PRINTK_EFI) += early_printk.o obj-$(CONFIG_EFI_MIXED) += efi_thunk_$(BITS).o diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 87fc96bcc13c..850da94fef30 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -56,13 +56,6 @@ #define EFI_DEBUG -#define EFI_MIN_RESERVE 5120 - -#define EFI_DUMMY_GUID \ - EFI_GUID(0x4424ac57, 0xbe4b, 0x47dd, 0x9e, 0x97, 0xed, 0x50, 0xf0, 0x9f, 0x92, 0xa9) - -static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 }; - struct efi_memory_map memmap; static struct efi efi_phys __initdata; @@ -95,139 +88,6 @@ static int __init setup_add_efi_memmap(char *arg) } early_param("add_efi_memmap", setup_add_efi_memmap); -static bool efi_no_storage_paranoia; - -static int __init setup_storage_paranoia(char *arg) -{ - efi_no_storage_paranoia = true; - return 0; -} -early_param("efi_no_storage_paranoia", setup_storage_paranoia); - -static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) -{ - unsigned long flags; - efi_status_t status; - - spin_lock_irqsave(&rtc_lock, flags); - status = efi_call_virt(get_time, tm, tc); - spin_unlock_irqrestore(&rtc_lock, flags); - return status; -} - -static efi_status_t virt_efi_set_time(efi_time_t *tm) -{ - unsigned long flags; - efi_status_t status; - - spin_lock_irqsave(&rtc_lock, flags); - status = efi_call_virt(set_time, tm); - spin_unlock_irqrestore(&rtc_lock, flags); - return status; -} - -static efi_status_t virt_efi_get_wakeup_time(efi_bool_t *enabled, - efi_bool_t *pending, - efi_time_t *tm) -{ - unsigned long flags; - efi_status_t status; - - spin_lock_irqsave(&rtc_lock, flags); - status = efi_call_virt(get_wakeup_time, enabled, pending, tm); - spin_unlock_irqrestore(&rtc_lock, flags); - return status; -} - -static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) -{ - unsigned long flags; - efi_status_t status; - - spin_lock_irqsave(&rtc_lock, flags); - status = efi_call_virt(set_wakeup_time, enabled, tm); - spin_unlock_irqrestore(&rtc_lock, flags); - return status; -} - -static efi_status_t virt_efi_get_variable(efi_char16_t *name, - efi_guid_t *vendor, - u32 *attr, - unsigned long *data_size, - void *data) -{ - return efi_call_virt(get_variable, - name, vendor, attr, - data_size, data); -} - -static efi_status_t virt_efi_get_next_variable(unsigned long *name_size, - efi_char16_t *name, - efi_guid_t *vendor) -{ - return efi_call_virt(get_next_variable, - name_size, name, vendor); -} - -static efi_status_t virt_efi_set_variable(efi_char16_t *name, - efi_guid_t *vendor, - u32 attr, - unsigned long data_size, - void *data) -{ - return efi_call_virt(set_variable, - name, vendor, attr, - data_size, data); -} - -static efi_status_t virt_efi_query_variable_info(u32 attr, - u64 *storage_space, - u64 *remaining_space, - u64 *max_variable_size) -{ - if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) - return EFI_UNSUPPORTED; - - return efi_call_virt(query_variable_info, attr, storage_space, - remaining_space, max_variable_size); -} - -static efi_status_t virt_efi_get_next_high_mono_count(u32 *count) -{ - return efi_call_virt(get_next_high_mono_count, count); -} - -static void virt_efi_reset_system(int reset_type, - efi_status_t status, - unsigned long data_size, - efi_char16_t *data) -{ - __efi_call_virt(reset_system, reset_type, status, - data_size, data); -} - -static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules, - unsigned long count, - unsigned long sg_list) -{ - if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) - return EFI_UNSUPPORTED; - - return efi_call_virt(update_capsule, capsules, count, sg_list); -} - -static efi_status_t virt_efi_query_capsule_caps(efi_capsule_header_t **capsules, - unsigned long count, - u64 *max_size, - int *reset_type) -{ - if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) - return EFI_UNSUPPORTED; - - return efi_call_virt(query_capsule_caps, capsules, count, max_size, - reset_type); -} - static efi_status_t __init phys_efi_set_virtual_address_map( unsigned long memory_map_size, unsigned long descriptor_size, @@ -244,42 +104,6 @@ static efi_status_t __init phys_efi_set_virtual_address_map( return status; } -int efi_set_rtc_mmss(const struct timespec *now) -{ - unsigned long nowtime = now->tv_sec; - efi_status_t status; - efi_time_t eft; - efi_time_cap_t cap; - struct rtc_time tm; - - status = efi.get_time(&eft, &cap); - if (status != EFI_SUCCESS) { - pr_err("Oops: efitime: can't read time!\n"); - return -1; - } - - rtc_time_to_tm(nowtime, &tm); - if (!rtc_valid_tm(&tm)) { - eft.year = tm.tm_year + 1900; - eft.month = tm.tm_mon + 1; - eft.day = tm.tm_mday; - eft.minute = tm.tm_min; - eft.second = tm.tm_sec; - eft.nanosecond = 0; - } else { - pr_err("%s: Invalid EFI RTC value: write of %lx to EFI RTC failed\n", - __func__, nowtime); - return -1; - } - - status = efi.set_time(&eft); - if (status != EFI_SUCCESS) { - pr_err("Oops: efitime: can't write time!\n"); - return -1; - } - return 0; -} - void efi_get_time(struct timespec *now) { efi_status_t status; @@ -350,6 +174,9 @@ int __init efi_memblock_x86_reserve_range(void) struct efi_info *e = &boot_params.efi_info; unsigned long pmap; + if (efi_enabled(EFI_PARAVIRT)) + return 0; + #ifdef CONFIG_X86_32 /* Can't handle data above 4GB at this time */ if (e->efi_memmap_hi) { @@ -392,69 +219,15 @@ static void __init print_efi_memmap(void) #endif /* EFI_DEBUG */ } -void __init efi_reserve_boot_services(void) -{ - void *p; - - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - efi_memory_desc_t *md = p; - u64 start = md->phys_addr; - u64 size = md->num_pages << EFI_PAGE_SHIFT; - - if (md->type != EFI_BOOT_SERVICES_CODE && - md->type != EFI_BOOT_SERVICES_DATA) - continue; - /* Only reserve where possible: - * - Not within any already allocated areas - * - Not over any memory area (really needed, if above?) - * - Not within any part of the kernel - * - Not the bios reserved area - */ - if ((start + size > __pa_symbol(_text) - && start <= __pa_symbol(_end)) || - !e820_all_mapped(start, start+size, E820_RAM) || - memblock_is_region_reserved(start, size)) { - /* Could not reserve, skip it */ - md->num_pages = 0; - memblock_dbg("Could not reserve boot range [0x%010llx-0x%010llx]\n", - start, start+size-1); - } else - memblock_reserve(start, size); - } -} - void __init efi_unmap_memmap(void) { clear_bit(EFI_MEMMAP, &efi.flags); if (memmap.map) { - early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size); + early_memunmap(memmap.map, memmap.nr_map * memmap.desc_size); memmap.map = NULL; } } -void __init efi_free_boot_services(void) -{ - void *p; - - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - efi_memory_desc_t *md = p; - unsigned long long start = md->phys_addr; - unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; - - if (md->type != EFI_BOOT_SERVICES_CODE && - md->type != EFI_BOOT_SERVICES_DATA) - continue; - - /* Could not reserve boot area */ - if (!size) - continue; - - free_bootmem_late(start, size); - } - - efi_unmap_memmap(); -} - static int __init efi_systab_init(void *phys) { if (efi_enabled(EFI_64BIT)) { @@ -467,12 +240,12 @@ static int __init efi_systab_init(void *phys) if (!data) return -ENOMEM; } - systab64 = early_ioremap((unsigned long)phys, + systab64 = early_memremap((unsigned long)phys, sizeof(*systab64)); if (systab64 == NULL) { pr_err("Couldn't map the system table!\n"); if (data) - early_iounmap(data, sizeof(*data)); + early_memunmap(data, sizeof(*data)); return -ENOMEM; } @@ -504,9 +277,9 @@ static int __init efi_systab_init(void *phys) systab64->tables; tmp |= data ? data->tables : systab64->tables; - early_iounmap(systab64, sizeof(*systab64)); + early_memunmap(systab64, sizeof(*systab64)); if (data) - early_iounmap(data, sizeof(*data)); + early_memunmap(data, sizeof(*data)); #ifdef CONFIG_X86_32 if (tmp >> 32) { pr_err("EFI data located above 4GB, disabling EFI.\n"); @@ -516,7 +289,7 @@ static int __init efi_systab_init(void *phys) } else { efi_system_table_32_t *systab32; - systab32 = early_ioremap((unsigned long)phys, + systab32 = early_memremap((unsigned long)phys, sizeof(*systab32)); if (systab32 == NULL) { pr_err("Couldn't map the system table!\n"); @@ -537,7 +310,7 @@ static int __init efi_systab_init(void *phys) efi_systab.nr_tables = systab32->nr_tables; efi_systab.tables = systab32->tables; - early_iounmap(systab32, sizeof(*systab32)); + early_memunmap(systab32, sizeof(*systab32)); } efi.systab = &efi_systab; @@ -563,7 +336,7 @@ static int __init efi_runtime_init32(void) { efi_runtime_services_32_t *runtime; - runtime = early_ioremap((unsigned long)efi.systab->runtime, + runtime = early_memremap((unsigned long)efi.systab->runtime, sizeof(efi_runtime_services_32_t)); if (!runtime) { pr_err("Could not map the runtime service table!\n"); @@ -578,7 +351,7 @@ static int __init efi_runtime_init32(void) efi_phys.set_virtual_address_map = (efi_set_virtual_address_map_t *) (unsigned long)runtime->set_virtual_address_map; - early_iounmap(runtime, sizeof(efi_runtime_services_32_t)); + early_memunmap(runtime, sizeof(efi_runtime_services_32_t)); return 0; } @@ -587,7 +360,7 @@ static int __init efi_runtime_init64(void) { efi_runtime_services_64_t *runtime; - runtime = early_ioremap((unsigned long)efi.systab->runtime, + runtime = early_memremap((unsigned long)efi.systab->runtime, sizeof(efi_runtime_services_64_t)); if (!runtime) { pr_err("Could not map the runtime service table!\n"); @@ -602,7 +375,7 @@ static int __init efi_runtime_init64(void) efi_phys.set_virtual_address_map = (efi_set_virtual_address_map_t *) (unsigned long)runtime->set_virtual_address_map; - early_iounmap(runtime, sizeof(efi_runtime_services_64_t)); + early_memunmap(runtime, sizeof(efi_runtime_services_64_t)); return 0; } @@ -616,14 +389,24 @@ static int __init efi_runtime_init(void) * the runtime services table so that we can grab the physical * address of several of the EFI runtime functions, needed to * set the firmware into virtual mode. + * + * When EFI_PARAVIRT is in force then we could not map runtime + * service memory region because we do not have direct access to it. + * However, runtime services are available through proxy functions + * (e.g. in case of Xen dom0 EFI implementation they call special + * hypercall which executes relevant EFI functions) and that is why + * they are always enabled. */ - if (efi_enabled(EFI_64BIT)) - rv = efi_runtime_init64(); - else - rv = efi_runtime_init32(); - if (rv) - return rv; + if (!efi_enabled(EFI_PARAVIRT)) { + if (efi_enabled(EFI_64BIT)) + rv = efi_runtime_init64(); + else + rv = efi_runtime_init32(); + + if (rv) + return rv; + } set_bit(EFI_RUNTIME_SERVICES, &efi.flags); @@ -632,8 +415,11 @@ static int __init efi_runtime_init(void) static int __init efi_memmap_init(void) { + if (efi_enabled(EFI_PARAVIRT)) + return 0; + /* Map the EFI memory map */ - memmap.map = early_ioremap((unsigned long)memmap.phys_map, + memmap.map = early_memremap((unsigned long)memmap.phys_map, memmap.nr_map * memmap.desc_size); if (memmap.map == NULL) { pr_err("Could not map the memory map!\n"); @@ -649,62 +435,6 @@ static int __init efi_memmap_init(void) return 0; } -/* - * A number of config table entries get remapped to virtual addresses - * after entering EFI virtual mode. However, the kexec kernel requires - * their physical addresses therefore we pass them via setup_data and - * correct those entries to their respective physical addresses here. - * - * Currently only handles smbios which is necessary for some firmware - * implementation. - */ -static int __init efi_reuse_config(u64 tables, int nr_tables) -{ - int i, sz, ret = 0; - void *p, *tablep; - struct efi_setup_data *data; - - if (!efi_setup) - return 0; - - if (!efi_enabled(EFI_64BIT)) - return 0; - - data = early_memremap(efi_setup, sizeof(*data)); - if (!data) { - ret = -ENOMEM; - goto out; - } - - if (!data->smbios) - goto out_memremap; - - sz = sizeof(efi_config_table_64_t); - - p = tablep = early_memremap(tables, nr_tables * sz); - if (!p) { - pr_err("Could not map Configuration table!\n"); - ret = -ENOMEM; - goto out_memremap; - } - - for (i = 0; i < efi.systab->nr_tables; i++) { - efi_guid_t guid; - - guid = ((efi_config_table_64_t *)p)->guid; - - if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID)) - ((efi_config_table_64_t *)p)->table = data->smbios; - p += sz; - } - early_iounmap(tablep, nr_tables * sz); - -out_memremap: - early_iounmap(data, sizeof(*data)); -out: - return ret; -} - void __init efi_init(void) { efi_char16_t *c16; @@ -728,8 +458,6 @@ void __init efi_init(void) if (efi_systab_init(efi_phys.systab)) return; - set_bit(EFI_SYSTEM_TABLES, &efi.flags); - efi.config_table = (unsigned long)efi.systab->tables; efi.fw_vendor = (unsigned long)efi.systab->fw_vendor; efi.runtime = (unsigned long)efi.systab->runtime; @@ -737,14 +465,14 @@ void __init efi_init(void) /* * Show what we know for posterity */ - c16 = tmp = early_ioremap(efi.systab->fw_vendor, 2); + c16 = tmp = early_memremap(efi.systab->fw_vendor, 2); if (c16) { for (i = 0; i < sizeof(vendor) - 1 && *c16; ++i) vendor[i] = *c16++; vendor[i] = '\0'; } else pr_err("Could not map the firmware vendor!\n"); - early_iounmap(tmp, 2); + early_memunmap(tmp, 2); pr_info("EFI v%u.%.02u by %s\n", efi.systab->hdr.revision >> 16, @@ -770,8 +498,6 @@ void __init efi_init(void) if (efi_memmap_init()) return; - set_bit(EFI_MEMMAP, &efi.flags); - print_efi_memmap(); } @@ -847,22 +573,6 @@ void __init old_map_region(efi_memory_desc_t *md) (unsigned long long)md->phys_addr); } -static void native_runtime_setup(void) -{ - efi.get_time = virt_efi_get_time; - efi.set_time = virt_efi_set_time; - efi.get_wakeup_time = virt_efi_get_wakeup_time; - efi.set_wakeup_time = virt_efi_set_wakeup_time; - efi.get_variable = virt_efi_get_variable; - efi.get_next_variable = virt_efi_get_next_variable; - efi.set_variable = virt_efi_set_variable; - efi.get_next_high_mono_count = virt_efi_get_next_high_mono_count; - efi.reset_system = virt_efi_reset_system; - efi.query_variable_info = virt_efi_query_variable_info; - efi.update_capsule = virt_efi_update_capsule; - efi.query_capsule_caps = virt_efi_query_capsule_caps; -} - /* Merge contiguous regions of the same type and attribute */ static void __init efi_merge_regions(void) { @@ -1049,7 +759,7 @@ static void __init kexec_enter_virtual_mode(void) */ efi.runtime_version = efi_systab.hdr.revision; - native_runtime_setup(); + efi_native_runtime_setup(); efi.set_virtual_address_map = NULL; @@ -1057,11 +767,7 @@ static void __init kexec_enter_virtual_mode(void) runtime_code_page_mkexec(); /* clean DUMMY object */ - efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID, - EFI_VARIABLE_NON_VOLATILE | - EFI_VARIABLE_BOOTSERVICE_ACCESS | - EFI_VARIABLE_RUNTIME_ACCESS, - 0, NULL); + efi_delete_dummy_variable(); #endif } @@ -1142,7 +848,7 @@ static void __init __efi_enter_virtual_mode(void) efi.runtime_version = efi_systab.hdr.revision; if (efi_is_native()) - native_runtime_setup(); + efi_native_runtime_setup(); else efi_thunk_runtime_setup(); @@ -1179,15 +885,14 @@ static void __init __efi_enter_virtual_mode(void) free_pages((unsigned long)new_memmap, pg_shift); /* clean DUMMY object */ - efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID, - EFI_VARIABLE_NON_VOLATILE | - EFI_VARIABLE_BOOTSERVICE_ACCESS | - EFI_VARIABLE_RUNTIME_ACCESS, - 0, NULL); + efi_delete_dummy_variable(); } void __init efi_enter_virtual_mode(void) { + if (efi_enabled(EFI_PARAVIRT)) + return; + if (efi_setup) kexec_enter_virtual_mode(); else @@ -1220,6 +925,9 @@ u64 efi_mem_attributes(unsigned long phys_addr) efi_memory_desc_t *md; void *p; + if (!efi_enabled(EFI_MEMMAP)) + return 0; + for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { md = p; if ((md->phys_addr <= phys_addr) && @@ -1230,86 +938,6 @@ u64 efi_mem_attributes(unsigned long phys_addr) return 0; } -/* - * Some firmware implementations refuse to boot if there's insufficient space - * in the variable store. Ensure that we never use more than a safe limit. - * - * Return EFI_SUCCESS if it is safe to write 'size' bytes to the variable - * store. - */ -efi_status_t efi_query_variable_store(u32 attributes, unsigned long size) -{ - efi_status_t status; - u64 storage_size, remaining_size, max_size; - - if (!(attributes & EFI_VARIABLE_NON_VOLATILE)) - return 0; - - status = efi.query_variable_info(attributes, &storage_size, - &remaining_size, &max_size); - if (status != EFI_SUCCESS) - return status; - - /* - * We account for that by refusing the write if permitting it would - * reduce the available space to under 5KB. This figure was provided by - * Samsung, so should be safe. - */ - if ((remaining_size - size < EFI_MIN_RESERVE) && - !efi_no_storage_paranoia) { - - /* - * Triggering garbage collection may require that the firmware - * generate a real EFI_OUT_OF_RESOURCES error. We can force - * that by attempting to use more space than is available. - */ - unsigned long dummy_size = remaining_size + 1024; - void *dummy = kzalloc(dummy_size, GFP_ATOMIC); - - if (!dummy) - return EFI_OUT_OF_RESOURCES; - - status = efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID, - EFI_VARIABLE_NON_VOLATILE | - EFI_VARIABLE_BOOTSERVICE_ACCESS | - EFI_VARIABLE_RUNTIME_ACCESS, - dummy_size, dummy); - - if (status == EFI_SUCCESS) { - /* - * This should have failed, so if it didn't make sure - * that we delete it... - */ - efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID, - EFI_VARIABLE_NON_VOLATILE | - EFI_VARIABLE_BOOTSERVICE_ACCESS | - EFI_VARIABLE_RUNTIME_ACCESS, - 0, dummy); - } - - kfree(dummy); - - /* - * The runtime code may now have triggered a garbage collection - * run, so check the variable info again - */ - status = efi.query_variable_info(attributes, &storage_size, - &remaining_size, &max_size); - - if (status != EFI_SUCCESS) - return status; - - /* - * There still isn't enough room, so return an error - */ - if (remaining_size - size < EFI_MIN_RESERVE) - return EFI_OUT_OF_RESOURCES; - } - - return EFI_SUCCESS; -} -EXPORT_SYMBOL_GPL(efi_query_variable_store); - static int __init parse_efi_cmdline(char *str) { if (*str == '=') @@ -1321,22 +949,3 @@ static int __init parse_efi_cmdline(char *str) return 0; } early_param("efi", parse_efi_cmdline); - -void __init efi_apply_memmap_quirks(void) -{ - /* - * Once setup is done earlier, unmap the EFI memory map on mismatched - * firmware/kernel architectures since there is no support for runtime - * services. - */ - if (!efi_runtime_supported()) { - pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n"); - efi_unmap_memmap(); - } - - /* - * UV doesn't support the new EFI pagetable mapping yet. - */ - if (is_uv_system()) - set_bit(EFI_OLD_MEMMAP, &efi.flags); -} diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c new file mode 100644 index 000000000000..1c7380da65ff --- /dev/null +++ b/arch/x86/platform/efi/quirks.c @@ -0,0 +1,290 @@ +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/time.h> +#include <linux/types.h> +#include <linux/efi.h> +#include <linux/slab.h> +#include <linux/memblock.h> +#include <linux/bootmem.h> +#include <linux/acpi.h> +#include <asm/efi.h> +#include <asm/uv/uv.h> + +#define EFI_MIN_RESERVE 5120 + +#define EFI_DUMMY_GUID \ + EFI_GUID(0x4424ac57, 0xbe4b, 0x47dd, 0x9e, 0x97, 0xed, 0x50, 0xf0, 0x9f, 0x92, 0xa9) + +static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 }; + +static bool efi_no_storage_paranoia; + +/* + * Some firmware implementations refuse to boot if there's insufficient + * space in the variable store. The implementation of garbage collection + * in some FW versions causes stale (deleted) variables to take up space + * longer than intended and space is only freed once the store becomes + * almost completely full. + * + * Enabling this option disables the space checks in + * efi_query_variable_store() and forces garbage collection. + * + * Only enable this option if deleting EFI variables does not free up + * space in your variable store, e.g. if despite deleting variables + * you're unable to create new ones. + */ +static int __init setup_storage_paranoia(char *arg) +{ + efi_no_storage_paranoia = true; + return 0; +} +early_param("efi_no_storage_paranoia", setup_storage_paranoia); + +/* + * Deleting the dummy variable which kicks off garbage collection +*/ +void efi_delete_dummy_variable(void) +{ + efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID, + EFI_VARIABLE_NON_VOLATILE | + EFI_VARIABLE_BOOTSERVICE_ACCESS | + EFI_VARIABLE_RUNTIME_ACCESS, + 0, NULL); +} + +/* + * Some firmware implementations refuse to boot if there's insufficient space + * in the variable store. Ensure that we never use more than a safe limit. + * + * Return EFI_SUCCESS if it is safe to write 'size' bytes to the variable + * store. + */ +efi_status_t efi_query_variable_store(u32 attributes, unsigned long size) +{ + efi_status_t status; + u64 storage_size, remaining_size, max_size; + + if (!(attributes & EFI_VARIABLE_NON_VOLATILE)) + return 0; + + status = efi.query_variable_info(attributes, &storage_size, + &remaining_size, &max_size); + if (status != EFI_SUCCESS) + return status; + + /* + * We account for that by refusing the write if permitting it would + * reduce the available space to under 5KB. This figure was provided by + * Samsung, so should be safe. + */ + if ((remaining_size - size < EFI_MIN_RESERVE) && + !efi_no_storage_paranoia) { + + /* + * Triggering garbage collection may require that the firmware + * generate a real EFI_OUT_OF_RESOURCES error. We can force + * that by attempting to use more space than is available. + */ + unsigned long dummy_size = remaining_size + 1024; + void *dummy = kzalloc(dummy_size, GFP_ATOMIC); + + if (!dummy) + return EFI_OUT_OF_RESOURCES; + + status = efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID, + EFI_VARIABLE_NON_VOLATILE | + EFI_VARIABLE_BOOTSERVICE_ACCESS | + EFI_VARIABLE_RUNTIME_ACCESS, + dummy_size, dummy); + + if (status == EFI_SUCCESS) { + /* + * This should have failed, so if it didn't make sure + * that we delete it... + */ + efi_delete_dummy_variable(); + } + + kfree(dummy); + + /* + * The runtime code may now have triggered a garbage collection + * run, so check the variable info again + */ + status = efi.query_variable_info(attributes, &storage_size, + &remaining_size, &max_size); + + if (status != EFI_SUCCESS) + return status; + + /* + * There still isn't enough room, so return an error + */ + if (remaining_size - size < EFI_MIN_RESERVE) + return EFI_OUT_OF_RESOURCES; + } + + return EFI_SUCCESS; +} +EXPORT_SYMBOL_GPL(efi_query_variable_store); + +/* + * The UEFI specification makes it clear that the operating system is free to do + * whatever it wants with boot services code after ExitBootServices() has been + * called. Ignoring this recommendation a significant bunch of EFI implementations + * continue calling into boot services code (SetVirtualAddressMap). In order to + * work around such buggy implementations we reserve boot services region during + * EFI init and make sure it stays executable. Then, after SetVirtualAddressMap(), it +* is discarded. +*/ +void __init efi_reserve_boot_services(void) +{ + void *p; + + for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { + efi_memory_desc_t *md = p; + u64 start = md->phys_addr; + u64 size = md->num_pages << EFI_PAGE_SHIFT; + + if (md->type != EFI_BOOT_SERVICES_CODE && + md->type != EFI_BOOT_SERVICES_DATA) + continue; + /* Only reserve where possible: + * - Not within any already allocated areas + * - Not over any memory area (really needed, if above?) + * - Not within any part of the kernel + * - Not the bios reserved area + */ + if ((start + size > __pa_symbol(_text) + && start <= __pa_symbol(_end)) || + !e820_all_mapped(start, start+size, E820_RAM) || + memblock_is_region_reserved(start, size)) { + /* Could not reserve, skip it */ + md->num_pages = 0; + memblock_dbg("Could not reserve boot range [0x%010llx-0x%010llx]\n", + start, start+size-1); + } else + memblock_reserve(start, size); + } +} + +void __init efi_free_boot_services(void) +{ + void *p; + + for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { + efi_memory_desc_t *md = p; + unsigned long long start = md->phys_addr; + unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; + + if (md->type != EFI_BOOT_SERVICES_CODE && + md->type != EFI_BOOT_SERVICES_DATA) + continue; + + /* Could not reserve boot area */ + if (!size) + continue; + + free_bootmem_late(start, size); + } + + efi_unmap_memmap(); +} + +/* + * A number of config table entries get remapped to virtual addresses + * after entering EFI virtual mode. However, the kexec kernel requires + * their physical addresses therefore we pass them via setup_data and + * correct those entries to their respective physical addresses here. + * + * Currently only handles smbios which is necessary for some firmware + * implementation. + */ +int __init efi_reuse_config(u64 tables, int nr_tables) +{ + int i, sz, ret = 0; + void *p, *tablep; + struct efi_setup_data *data; + + if (!efi_setup) + return 0; + + if (!efi_enabled(EFI_64BIT)) + return 0; + + data = early_memremap(efi_setup, sizeof(*data)); + if (!data) { + ret = -ENOMEM; + goto out; + } + + if (!data->smbios) + goto out_memremap; + + sz = sizeof(efi_config_table_64_t); + + p = tablep = early_memremap(tables, nr_tables * sz); + if (!p) { + pr_err("Could not map Configuration table!\n"); + ret = -ENOMEM; + goto out_memremap; + } + + for (i = 0; i < efi.systab->nr_tables; i++) { + efi_guid_t guid; + + guid = ((efi_config_table_64_t *)p)->guid; + + if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID)) + ((efi_config_table_64_t *)p)->table = data->smbios; + p += sz; + } + early_memunmap(tablep, nr_tables * sz); + +out_memremap: + early_memunmap(data, sizeof(*data)); +out: + return ret; +} + +void __init efi_apply_memmap_quirks(void) +{ + /* + * Once setup is done earlier, unmap the EFI memory map on mismatched + * firmware/kernel architectures since there is no support for runtime + * services. + */ + if (!efi_runtime_supported()) { + pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n"); + efi_unmap_memmap(); + } + + /* + * UV doesn't support the new EFI pagetable mapping yet. + */ + if (is_uv_system()) + set_bit(EFI_OLD_MEMMAP, &efi.flags); +} + +/* + * For most modern platforms the preferred method of powering off is via + * ACPI. However, there are some that are known to require the use of + * EFI runtime services and for which ACPI does not work at all. + * + * Using EFI is a last resort, to be used only if no other option + * exists. + */ +bool efi_reboot_required(void) +{ + if (!acpi_gbl_reduced_hardware) + return false; + + efi_reboot_quirk_mode = EFI_RESET_WARM; + return true; +} + +bool efi_poweroff_required(void) +{ + return !!acpi_gbl_reduced_hardware; +} diff --git a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c index 973cf3bfa9fd..0b283d4d0ad7 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c @@ -26,28 +26,18 @@ static struct platform_device wdt_dev = { static int tangier_probe(struct platform_device *pdev) { - int ioapic; - int irq; + int gsi; struct intel_mid_wdt_pdata *pdata = pdev->dev.platform_data; - struct io_apic_irq_attr irq_attr = { 0 }; if (!pdata) return -EINVAL; - irq = pdata->irq; - ioapic = mp_find_ioapic(irq); - if (ioapic >= 0) { - int ret; - irq_attr.ioapic = ioapic; - irq_attr.ioapic_pin = irq; - irq_attr.trigger = 1; - /* irq_attr.polarity = 0; -> Active high */ - ret = io_apic_set_pci_routing(NULL, irq, &irq_attr); - if (ret) - return ret; - } else { + /* IOAPIC builds identity mapping between GSI and IRQ on MID */ + gsi = pdata->irq; + if (mp_set_gsi_attr(gsi, 1, 0, cpu_to_node(0)) || + mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC) <= 0) { dev_warn(&pdev->dev, "cannot find interrupt %d in ioapic\n", - irq); + gsi); return -EINVAL; } diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c index 994c40bd7cb7..3c53a90fdb18 100644 --- a/arch/x86/platform/intel-mid/sfi.c +++ b/arch/x86/platform/intel-mid/sfi.c @@ -432,9 +432,8 @@ static int __init sfi_parse_devs(struct sfi_table_header *table) struct sfi_table_simple *sb; struct sfi_device_table_entry *pentry; struct devs_id *dev = NULL; - int num, i; - int ioapic; - struct io_apic_irq_attr irq_attr; + int num, i, ret; + int polarity; sb = (struct sfi_table_simple *)table; num = SFI_GET_NUM_ENTRIES(sb, struct sfi_device_table_entry); @@ -448,35 +447,30 @@ static int __init sfi_parse_devs(struct sfi_table_header *table) * devices, but they have separate RTE entry in IOAPIC * so we have to enable them one by one here */ - ioapic = mp_find_ioapic(irq); - if (ioapic >= 0) { - irq_attr.ioapic = ioapic; - irq_attr.ioapic_pin = irq; - irq_attr.trigger = 1; - if (intel_mid_identify_cpu() == - INTEL_MID_CPU_CHIP_TANGIER) { - if (!strncmp(pentry->name, - "r69001-ts-i2c", 13)) - /* active low */ - irq_attr.polarity = 1; - else if (!strncmp(pentry->name, - "synaptics_3202", 14)) - /* active low */ - irq_attr.polarity = 1; - else if (irq == 41) - /* fast_int_1 */ - irq_attr.polarity = 1; - else - /* active high */ - irq_attr.polarity = 0; - } else { - /* PNW and CLV go with active low */ - irq_attr.polarity = 1; - } - io_apic_set_pci_routing(NULL, irq, &irq_attr); + if (intel_mid_identify_cpu() == + INTEL_MID_CPU_CHIP_TANGIER) { + if (!strncmp(pentry->name, "r69001-ts-i2c", 13)) + /* active low */ + polarity = 1; + else if (!strncmp(pentry->name, + "synaptics_3202", 14)) + /* active low */ + polarity = 1; + else if (irq == 41) + /* fast_int_1 */ + polarity = 1; + else + /* active high */ + polarity = 0; + } else { + /* PNW and CLV go with active low */ + polarity = 1; } - } else { - irq = 0; /* No irq */ + + ret = mp_set_gsi_attr(irq, 1, polarity, NUMA_NO_NODE); + if (ret == 0) + ret = mp_map_gsi_to_irq(irq, IOAPIC_MAP_ALLOC); + WARN_ON(ret < 0); } dev = get_device_id(pentry->type, pentry->name); diff --git a/arch/x86/platform/sfi/sfi.c b/arch/x86/platform/sfi/sfi.c index bcd1a703e3e6..2a8a74f3bd76 100644 --- a/arch/x86/platform/sfi/sfi.c +++ b/arch/x86/platform/sfi/sfi.c @@ -25,6 +25,7 @@ #include <linux/init.h> #include <linux/sfi.h> #include <linux/io.h> +#include <linux/irqdomain.h> #include <asm/io_apic.h> #include <asm/mpspec.h> @@ -70,19 +71,26 @@ static int __init sfi_parse_cpus(struct sfi_table_header *table) #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_IO_APIC +static struct irq_domain_ops sfi_ioapic_irqdomain_ops = { + .map = mp_irqdomain_map, +}; static int __init sfi_parse_ioapic(struct sfi_table_header *table) { struct sfi_table_simple *sb; struct sfi_apic_table_entry *pentry; int i, num; + struct ioapic_domain_cfg cfg = { + .type = IOAPIC_DOMAIN_STRICT, + .ops = &sfi_ioapic_irqdomain_ops, + }; sb = (struct sfi_table_simple *)table; num = SFI_GET_NUM_ENTRIES(sb, struct sfi_apic_table_entry); pentry = (struct sfi_apic_table_entry *)sb->pentry; for (i = 0; i < num; i++) { - mp_register_ioapic(i, pentry->phys_addr, gsi_top); + mp_register_ioapic(i, pentry->phys_addr, gsi_top, &cfg); pentry++; } diff --git a/arch/x86/platform/ts5500/ts5500.c b/arch/x86/platform/ts5500/ts5500.c index 9471b9456f25..baf16e72e668 100644 --- a/arch/x86/platform/ts5500/ts5500.c +++ b/arch/x86/platform/ts5500/ts5500.c @@ -1,7 +1,7 @@ /* * Technologic Systems TS-5500 Single Board Computer support * - * Copyright (C) 2013 Savoir-faire Linux Inc. + * Copyright (C) 2013-2014 Savoir-faire Linux Inc. * Vivien Didelot <vivien.didelot@savoirfairelinux.com> * * This program is free software; you can redistribute it and/or modify it under @@ -15,8 +15,8 @@ * state or available options. For further information about sysfs entries, see * Documentation/ABI/testing/sysfs-platform-ts5500. * - * This code actually supports the TS-5500 platform, but it may be extended to - * support similar Technologic Systems x86-based platforms, such as the TS-5600. + * This code may be extended to support similar x86-based platforms. + * Actually, the TS-5500 and TS-5400 are supported. */ #include <linux/delay.h> @@ -32,6 +32,7 @@ /* Product code register */ #define TS5500_PRODUCT_CODE_ADDR 0x74 #define TS5500_PRODUCT_CODE 0x60 /* TS-5500 product code */ +#define TS5400_PRODUCT_CODE 0x40 /* TS-5400 product code */ /* SRAM/RS-485/ADC options, and RS-485 RTS/Automatic RS-485 flags register */ #define TS5500_SRAM_RS485_ADC_ADDR 0x75 @@ -66,6 +67,7 @@ /** * struct ts5500_sbc - TS-5500 board description + * @name: Board model name. * @id: Board product ID. * @sram: Flag for SRAM option. * @rs485: Flag for RS-485 option. @@ -75,6 +77,7 @@ * @jumpers: Bitfield for jumpers' state. */ struct ts5500_sbc { + const char *name; int id; bool sram; bool rs485; @@ -122,13 +125,16 @@ static int __init ts5500_detect_config(struct ts5500_sbc *sbc) if (!request_region(TS5500_PRODUCT_CODE_ADDR, 4, "ts5500")) return -EBUSY; - tmp = inb(TS5500_PRODUCT_CODE_ADDR); - if (tmp != TS5500_PRODUCT_CODE) { - pr_err("This platform is not a TS-5500 (found ID 0x%x)\n", tmp); + sbc->id = inb(TS5500_PRODUCT_CODE_ADDR); + if (sbc->id == TS5500_PRODUCT_CODE) { + sbc->name = "TS-5500"; + } else if (sbc->id == TS5400_PRODUCT_CODE) { + sbc->name = "TS-5400"; + } else { + pr_err("ts5500: unknown product code 0x%x\n", sbc->id); ret = -ENODEV; goto cleanup; } - sbc->id = tmp; tmp = inb(TS5500_SRAM_RS485_ADC_ADDR); sbc->sram = tmp & TS5500_SRAM; @@ -147,48 +153,52 @@ cleanup: return ret; } -static ssize_t ts5500_show_id(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t name_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct ts5500_sbc *sbc = dev_get_drvdata(dev); - return sprintf(buf, "0x%.2x\n", sbc->id); + return sprintf(buf, "%s\n", sbc->name); } +static DEVICE_ATTR_RO(name); -static ssize_t ts5500_show_jumpers(struct device *dev, - struct device_attribute *attr, - char *buf) +static ssize_t id_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct ts5500_sbc *sbc = dev_get_drvdata(dev); - return sprintf(buf, "0x%.2x\n", sbc->jumpers >> 1); + return sprintf(buf, "0x%.2x\n", sbc->id); } +static DEVICE_ATTR_RO(id); -#define TS5500_SHOW(field) \ - static ssize_t ts5500_show_##field(struct device *dev, \ - struct device_attribute *attr, \ - char *buf) \ - { \ - struct ts5500_sbc *sbc = dev_get_drvdata(dev); \ - return sprintf(buf, "%d\n", sbc->field); \ - } - -TS5500_SHOW(sram) -TS5500_SHOW(rs485) -TS5500_SHOW(adc) -TS5500_SHOW(ereset) -TS5500_SHOW(itr) +static ssize_t jumpers_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct ts5500_sbc *sbc = dev_get_drvdata(dev); -static DEVICE_ATTR(id, S_IRUGO, ts5500_show_id, NULL); -static DEVICE_ATTR(jumpers, S_IRUGO, ts5500_show_jumpers, NULL); -static DEVICE_ATTR(sram, S_IRUGO, ts5500_show_sram, NULL); -static DEVICE_ATTR(rs485, S_IRUGO, ts5500_show_rs485, NULL); -static DEVICE_ATTR(adc, S_IRUGO, ts5500_show_adc, NULL); -static DEVICE_ATTR(ereset, S_IRUGO, ts5500_show_ereset, NULL); -static DEVICE_ATTR(itr, S_IRUGO, ts5500_show_itr, NULL); + return sprintf(buf, "0x%.2x\n", sbc->jumpers >> 1); +} +static DEVICE_ATTR_RO(jumpers); + +#define TS5500_ATTR_BOOL(_field) \ + static ssize_t _field##_show(struct device *dev, \ + struct device_attribute *attr, char *buf) \ + { \ + struct ts5500_sbc *sbc = dev_get_drvdata(dev); \ + \ + return sprintf(buf, "%d\n", sbc->_field); \ + } \ + static DEVICE_ATTR_RO(_field) + +TS5500_ATTR_BOOL(sram); +TS5500_ATTR_BOOL(rs485); +TS5500_ATTR_BOOL(adc); +TS5500_ATTR_BOOL(ereset); +TS5500_ATTR_BOOL(itr); static struct attribute *ts5500_attributes[] = { &dev_attr_id.attr, + &dev_attr_name.attr, &dev_attr_jumpers.attr, &dev_attr_sram.attr, &dev_attr_rs485.attr, @@ -311,12 +321,14 @@ static int __init ts5500_init(void) if (err) goto error; - ts5500_dio1_pdev.dev.parent = &pdev->dev; - if (platform_device_register(&ts5500_dio1_pdev)) - dev_warn(&pdev->dev, "DIO1 block registration failed\n"); - ts5500_dio2_pdev.dev.parent = &pdev->dev; - if (platform_device_register(&ts5500_dio2_pdev)) - dev_warn(&pdev->dev, "DIO2 block registration failed\n"); + if (sbc->id == TS5500_PRODUCT_CODE) { + ts5500_dio1_pdev.dev.parent = &pdev->dev; + if (platform_device_register(&ts5500_dio1_pdev)) + dev_warn(&pdev->dev, "DIO1 block registration failed\n"); + ts5500_dio2_pdev.dev.parent = &pdev->dev; + if (platform_device_register(&ts5500_dio2_pdev)) + dev_warn(&pdev->dev, "DIO2 block registration failed\n"); + } if (led_classdev_register(&pdev->dev, &ts5500_led_cdev)) dev_warn(&pdev->dev, "LED registration failed\n"); diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index dfe605ac1bcd..ed161c6e278b 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -1,7 +1,7 @@ /* * SGI UltraViolet TLB flush routines. * - * (c) 2008-2012 Cliff Wickman <cpw@sgi.com>, SGI. + * (c) 2008-2014 Cliff Wickman <cpw@sgi.com>, SGI. * * This code is released under the GNU General Public License version 2 or * later. @@ -451,7 +451,7 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc) /* * The reverse of the above; converts a duration in ns to a duration in cycles. - */ + */ static inline unsigned long long ns_2_cycles(unsigned long long ns) { struct cyc2ns_data *data = cyc2ns_read_begin(); @@ -563,7 +563,7 @@ static int uv1_wait_completion(struct bau_desc *bau_desc, * UV2 could have an extra bit of status in the ACTIVATION_STATUS_2 register. * But not currently used. */ -static unsigned long uv2_read_status(unsigned long offset, int rshft, int desc) +static unsigned long uv2_3_read_status(unsigned long offset, int rshft, int desc) { unsigned long descriptor_status; @@ -606,7 +606,7 @@ int handle_uv2_busy(struct bau_control *bcp) return FLUSH_GIVEUP; } -static int uv2_wait_completion(struct bau_desc *bau_desc, +static int uv2_3_wait_completion(struct bau_desc *bau_desc, unsigned long mmr_offset, int right_shift, struct bau_control *bcp, long try) { @@ -616,7 +616,7 @@ static int uv2_wait_completion(struct bau_desc *bau_desc, long busy_reps = 0; struct ptc_stats *stat = bcp->statp; - descriptor_stat = uv2_read_status(mmr_offset, right_shift, desc); + descriptor_stat = uv2_3_read_status(mmr_offset, right_shift, desc); /* spin on the status MMR, waiting for it to go idle */ while (descriptor_stat != UV2H_DESC_IDLE) { @@ -658,8 +658,7 @@ static int uv2_wait_completion(struct bau_desc *bau_desc, /* not to hammer on the clock */ busy_reps = 0; ttm = get_cycles(); - if ((ttm - bcp->send_message) > - bcp->timeout_interval) + if ((ttm - bcp->send_message) > bcp->timeout_interval) return handle_uv2_busy(bcp); } /* @@ -667,8 +666,7 @@ static int uv2_wait_completion(struct bau_desc *bau_desc, */ cpu_relax(); } - descriptor_stat = uv2_read_status(mmr_offset, right_shift, - desc); + descriptor_stat = uv2_3_read_status(mmr_offset, right_shift, desc); } bcp->conseccompletes++; return FLUSH_COMPLETE; @@ -679,8 +677,7 @@ static int uv2_wait_completion(struct bau_desc *bau_desc, * which register to read and position in that register based on cpu in * current hub. */ -static int wait_completion(struct bau_desc *bau_desc, - struct bau_control *bcp, long try) +static int wait_completion(struct bau_desc *bau_desc, struct bau_control *bcp, long try) { int right_shift; unsigned long mmr_offset; @@ -695,11 +692,9 @@ static int wait_completion(struct bau_desc *bau_desc, } if (bcp->uvhub_version == 1) - return uv1_wait_completion(bau_desc, mmr_offset, right_shift, - bcp, try); + return uv1_wait_completion(bau_desc, mmr_offset, right_shift, bcp, try); else - return uv2_wait_completion(bau_desc, mmr_offset, right_shift, - bcp, try); + return uv2_3_wait_completion(bau_desc, mmr_offset, right_shift, bcp, try); } /* @@ -888,7 +883,7 @@ int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp, struct ptc_stats *stat = bcp->statp; struct bau_control *hmaster = bcp->uvhub_master; struct uv1_bau_msg_header *uv1_hdr = NULL; - struct uv2_bau_msg_header *uv2_hdr = NULL; + struct uv2_3_bau_msg_header *uv2_3_hdr = NULL; if (bcp->uvhub_version == 1) { uv1 = 1; @@ -902,27 +897,28 @@ int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp, if (uv1) uv1_hdr = &bau_desc->header.uv1_hdr; else - uv2_hdr = &bau_desc->header.uv2_hdr; + /* uv2 and uv3 */ + uv2_3_hdr = &bau_desc->header.uv2_3_hdr; do { if (try == 0) { if (uv1) uv1_hdr->msg_type = MSG_REGULAR; else - uv2_hdr->msg_type = MSG_REGULAR; + uv2_3_hdr->msg_type = MSG_REGULAR; seq_number = bcp->message_number++; } else { if (uv1) uv1_hdr->msg_type = MSG_RETRY; else - uv2_hdr->msg_type = MSG_RETRY; + uv2_3_hdr->msg_type = MSG_RETRY; stat->s_retry_messages++; } if (uv1) uv1_hdr->sequence = seq_number; else - uv2_hdr->sequence = seq_number; + uv2_3_hdr->sequence = seq_number; index = (1UL << AS_PUSH_SHIFT) | bcp->uvhub_cpu; bcp->send_message = get_cycles(); @@ -1080,8 +1076,10 @@ static int set_distrib_bits(struct cpumask *flush_mask, struct bau_control *bcp, * done. The returned pointer is valid till preemption is re-enabled. */ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, - struct mm_struct *mm, unsigned long start, - unsigned long end, unsigned int cpu) + struct mm_struct *mm, + unsigned long start, + unsigned long end, + unsigned int cpu) { int locals = 0; int remotes = 0; @@ -1268,6 +1266,7 @@ void uv_bau_message_interrupt(struct pt_regs *regs) if (bcp->uvhub_version == 2) process_uv2_message(&msgdesc, bcp); else + /* no error workaround for uv1 or uv3 */ bau_process_message(&msgdesc, bcp, 1); msg++; @@ -1325,8 +1324,12 @@ static void __init enable_timeouts(void) */ mmr_image |= (1L << SOFTACK_MSHIFT); if (is_uv2_hub()) { + /* do not touch the legacy mode bit */ /* hw bug workaround; do not use extended status */ mmr_image &= ~(1L << UV2_EXT_SHFT); + } else if (is_uv3_hub()) { + mmr_image &= ~(1L << PREFETCH_HINT_SHFT); + mmr_image |= (1L << SB_STATUS_SHFT); } write_mmr_misc_control(pnode, mmr_image); } @@ -1692,7 +1695,7 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode) struct bau_desc *bau_desc; struct bau_desc *bd2; struct uv1_bau_msg_header *uv1_hdr; - struct uv2_bau_msg_header *uv2_hdr; + struct uv2_3_bau_msg_header *uv2_3_hdr; struct bau_control *bcp; /* @@ -1739,15 +1742,15 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode) */ } else { /* - * BIOS uses legacy mode, but UV2 hardware always + * BIOS uses legacy mode, but uv2 and uv3 hardware always * uses native mode for selective broadcasts. */ - uv2_hdr = &bd2->header.uv2_hdr; - uv2_hdr->swack_flag = 1; - uv2_hdr->base_dest_nasid = + uv2_3_hdr = &bd2->header.uv2_3_hdr; + uv2_3_hdr->swack_flag = 1; + uv2_3_hdr->base_dest_nasid = UV_PNODE_TO_NASID(base_pnode); - uv2_hdr->dest_subnodeid = UV_LB_SUBNODEID; - uv2_hdr->command = UV_NET_ENDPOINT_INTD; + uv2_3_hdr->dest_subnodeid = UV_LB_SUBNODEID; + uv2_3_hdr->command = UV_NET_ENDPOINT_INTD; } } for_each_present_cpu(cpu) { @@ -1858,6 +1861,7 @@ static int calculate_destination_timeout(void) ts_ns *= (mult1 * mult2); ret = ts_ns / 1000; } else { + /* same destination timeout for uv2 and uv3 */ /* 4 bits 0/1 for 10/80us base, 3 bits of multiplier */ mmr_image = uv_read_local_mmr(UVH_LB_BAU_MISC_CONTROL); mmr_image = (mmr_image & UV_SA_MASK) >> UV_SA_SHFT; @@ -2012,8 +2016,10 @@ static int scan_sock(struct socket_desc *sdp, struct uvhub_desc *bdp, bcp->uvhub_version = 1; else if (is_uv2_hub()) bcp->uvhub_version = 2; + else if (is_uv3_hub()) + bcp->uvhub_version = 3; else { - printk(KERN_EMERG "uvhub version not 1 or 2\n"); + printk(KERN_EMERG "uvhub version not 1, 2 or 3\n"); return 1; } bcp->uvhub_master = *hmasterp; @@ -2138,9 +2144,10 @@ static int __init uv_bau_init(void) } vector = UV_BAU_MESSAGE; - for_each_possible_blade(uvhub) + for_each_possible_blade(uvhub) { if (uv_blade_nr_possible_cpus(uvhub)) init_uvhub(uvhub, vector, uv_base_pnode); + } alloc_intr_gate(vector, uv_bau_message_intr1); diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h index 04f82e020f2b..2a206d2b14ab 100644 --- a/arch/x86/um/asm/processor.h +++ b/arch/x86/um/asm/processor.h @@ -25,7 +25,8 @@ static inline void rep_nop(void) __asm__ __volatile__("rep;nop": : :"memory"); } -#define cpu_relax() rep_nop() +#define cpu_relax() rep_nop() +#define cpu_relax_lowlatency() cpu_relax() #include <asm/processor-generic.h> diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index 61b04fe36e66..5a4affe025e8 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -10,7 +10,7 @@ VDSO32-$(CONFIG_X86_32) := y VDSO32-$(CONFIG_COMPAT) := y # files to link into the vdso -vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o vdso-fakesections.o +vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o # files to link into kernel obj-y += vma.o @@ -37,7 +37,8 @@ vdso_img_sodbg := $(vdso_img-y:%=vdso%.so.dbg) obj-y += $(vdso_img_objs) targets += $(vdso_img_cfiles) targets += $(vdso_img_sodbg) -.SECONDARY: $(vdso_img-y:%=$(obj)/vdso-image-%.c) +.SECONDARY: $(vdso_img-y:%=$(obj)/vdso-image-%.c) \ + $(vdso_img-y:%=$(obj)/vdso%.so) export CPPFLAGS_vdso.lds += -P -C @@ -54,10 +55,10 @@ hostprogs-y += vdso2c quiet_cmd_vdso2c = VDSO2C $@ define cmd_vdso2c - $(obj)/vdso2c $< $@ + $(obj)/vdso2c $< $(<:%.dbg=%) $@ endef -$(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso2c FORCE +$(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE $(call if_changed,vdso2c) # @@ -113,6 +114,10 @@ $(obj)/%-x32.o: $(obj)/%.o FORCE targets += vdsox32.lds $(vobjx32s-y) +$(obj)/%.so: OBJCOPYFLAGS := -S +$(obj)/%.so: $(obj)/%.so.dbg + $(call if_changed,objcopy) + $(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE $(call if_changed,vdso) @@ -134,7 +139,7 @@ override obj-dirs = $(dir $(obj)) $(obj)/vdso32/ targets += vdso32/vdso32.lds targets += vdso32/note.o vdso32/vclock_gettime.o $(vdso32.so-y:%=vdso32/%.o) -targets += vdso32/vclock_gettime.o vdso32/vdso-fakesections.o +targets += vdso32/vclock_gettime.o $(obj)/vdso32.o: $(vdso32-images:%=$(obj)/%) @@ -156,7 +161,6 @@ $(vdso32-images:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32) $(vdso32-images:%=$(obj)/%.dbg): $(obj)/vdso32-%.so.dbg: FORCE \ $(obj)/vdso32/vdso32.lds \ $(obj)/vdso32/vclock_gettime.o \ - $(obj)/vdso32/vdso-fakesections.o \ $(obj)/vdso32/note.o \ $(obj)/vdso32/%.o $(call if_changed,vdso) diff --git a/arch/x86/vdso/vdso-fakesections.c b/arch/x86/vdso/vdso-fakesections.c deleted file mode 100644 index aa5fbfab20a5..000000000000 --- a/arch/x86/vdso/vdso-fakesections.c +++ /dev/null @@ -1,21 +0,0 @@ -/* - * Copyright 2014 Andy Lutomirski - * Subject to the GNU Public License, v.2 - * - * String table for loadable section headers. See vdso2c.h for why - * this exists. - */ - -const char fake_shstrtab[] __attribute__((section(".fake_shstrtab"))) = - ".hash\0" - ".dynsym\0" - ".dynstr\0" - ".gnu.version\0" - ".gnu.version_d\0" - ".dynamic\0" - ".rodata\0" - ".fake_shstrtab\0" /* Yay, self-referential code. */ - ".note\0" - ".eh_frame_hdr\0" - ".eh_frame\0" - ".text"; diff --git a/arch/x86/vdso/vdso-layout.lds.S b/arch/x86/vdso/vdso-layout.lds.S index 9197544eea9a..de2c921025f5 100644 --- a/arch/x86/vdso/vdso-layout.lds.S +++ b/arch/x86/vdso/vdso-layout.lds.S @@ -18,6 +18,25 @@ SECTIONS { + /* + * User/kernel shared data is before the vDSO. This may be a little + * uglier than putting it after the vDSO, but it avoids issues with + * non-allocatable things that dangle past the end of the PT_LOAD + * segment. + */ + + vvar_start = . - 2 * PAGE_SIZE; + vvar_page = vvar_start; + + /* Place all vvars at the offsets in asm/vvar.h. */ +#define EMIT_VVAR(name, offset) vvar_ ## name = vvar_page + offset; +#define __VVAR_KERNEL_LDS +#include <asm/vvar.h> +#undef __VVAR_KERNEL_LDS +#undef EMIT_VVAR + + hpet_page = vvar_start + PAGE_SIZE; + . = SIZEOF_HEADERS; .hash : { *(.hash) } :text @@ -74,31 +93,6 @@ SECTIONS .altinstructions : { *(.altinstructions) } :text .altinstr_replacement : { *(.altinstr_replacement) } :text - /* - * The remainder of the vDSO consists of special pages that are - * shared between the kernel and userspace. It needs to be at the - * end so that it doesn't overlap the mapping of the actual - * vDSO image. - */ - - . = ALIGN(PAGE_SIZE); - vvar_page = .; - - /* Place all vvars at the offsets in asm/vvar.h. */ -#define EMIT_VVAR(name, offset) vvar_ ## name = vvar_page + offset; -#define __VVAR_KERNEL_LDS -#include <asm/vvar.h> -#undef __VVAR_KERNEL_LDS -#undef EMIT_VVAR - - . = vvar_page + PAGE_SIZE; - - hpet_page = .; - . = . + PAGE_SIZE; - - . = ALIGN(PAGE_SIZE); - end_mapping = .; - /DISCARD/ : { *(.discard) *(.discard.*) diff --git a/arch/x86/vdso/vdso2c.c b/arch/x86/vdso/vdso2c.c index 238dbe82776e..8627db24a7f6 100644 --- a/arch/x86/vdso/vdso2c.c +++ b/arch/x86/vdso/vdso2c.c @@ -1,3 +1,53 @@ +/* + * vdso2c - A vdso image preparation tool + * Copyright (c) 2014 Andy Lutomirski and others + * Licensed under the GPL v2 + * + * vdso2c requires stripped and unstripped input. It would be trivial + * to fully strip the input in here, but, for reasons described below, + * we need to write a section table. Doing this is more or less + * equivalent to dropping all non-allocatable sections, but it's + * easier to let objcopy handle that instead of doing it ourselves. + * If we ever need to do something fancier than what objcopy provides, + * it would be straightforward to add here. + * + * We're keep a section table for a few reasons: + * + * The Go runtime had a couple of bugs: it would read the section + * table to try to figure out how many dynamic symbols there were (it + * shouldn't have looked at the section table at all) and, if there + * were no SHT_SYNDYM section table entry, it would use an + * uninitialized value for the number of symbols. An empty DYNSYM + * table would work, but I see no reason not to write a valid one (and + * keep full performance for old Go programs). This hack is only + * needed on x86_64. + * + * The bug was introduced on 2012-08-31 by: + * https://code.google.com/p/go/source/detail?r=56ea40aac72b + * and was fixed on 2014-06-13 by: + * https://code.google.com/p/go/source/detail?r=fc1cd5e12595 + * + * Binutils has issues debugging the vDSO: it reads the section table to + * find SHT_NOTE; it won't look at PT_NOTE for the in-memory vDSO, which + * would break build-id if we removed the section table. Binutils + * also requires that shstrndx != 0. See: + * https://sourceware.org/bugzilla/show_bug.cgi?id=17064 + * + * elfutils might not look for PT_NOTE if there is a section table at + * all. I don't know whether this matters for any practical purpose. + * + * For simplicity, rather than hacking up a partial section table, we + * just write a mostly complete one. We omit non-dynamic symbols, + * though, since they're rather large. + * + * Once binutils gets fixed, we might be able to drop this for all but + * the 64-bit vdso, since build-id only works in kernel RPMs, and + * systems that update to new enough kernel RPMs will likely update + * binutils in sync. build-id has never worked for home-built kernel + * RPMs without manual symlinking, and I suspect that no one ever does + * that. + */ + #include <inttypes.h> #include <stdint.h> #include <unistd.h> @@ -20,9 +70,9 @@ const char *outfilename; /* Symbols that we need in vdso2c. */ enum { + sym_vvar_start, sym_vvar_page, sym_hpet_page, - sym_end_mapping, sym_VDSO_FAKE_SECTION_TABLE_START, sym_VDSO_FAKE_SECTION_TABLE_END, }; @@ -38,9 +88,9 @@ struct vdso_sym { }; struct vdso_sym required_syms[] = { + [sym_vvar_start] = {"vvar_start", true}, [sym_vvar_page] = {"vvar_page", true}, [sym_hpet_page] = {"hpet_page", true}, - [sym_end_mapping] = {"end_mapping", true}, [sym_VDSO_FAKE_SECTION_TABLE_START] = { "VDSO_FAKE_SECTION_TABLE_START", false }, @@ -61,7 +111,8 @@ static void fail(const char *format, ...) va_start(ap, format); fprintf(stderr, "Error: "); vfprintf(stderr, format, ap); - unlink(outfilename); + if (outfilename) + unlink(outfilename); exit(1); va_end(ap); } @@ -96,9 +147,11 @@ extern void bad_put_le(void); #define NSYMS (sizeof(required_syms) / sizeof(required_syms[0])) -#define BITSFUNC3(name, bits) name##bits -#define BITSFUNC2(name, bits) BITSFUNC3(name, bits) -#define BITSFUNC(name) BITSFUNC2(name, ELF_BITS) +#define BITSFUNC3(name, bits, suffix) name##bits##suffix +#define BITSFUNC2(name, bits, suffix) BITSFUNC3(name, bits, suffix) +#define BITSFUNC(name) BITSFUNC2(name, ELF_BITS, ) + +#define INT_BITS BITSFUNC2(int, ELF_BITS, _t) #define ELF_BITS_XFORM2(bits, x) Elf##bits##_##x #define ELF_BITS_XFORM(bits, x) ELF_BITS_XFORM2(bits, x) @@ -112,30 +165,53 @@ extern void bad_put_le(void); #include "vdso2c.h" #undef ELF_BITS -static void go(void *addr, size_t len, FILE *outfile, const char *name) +static void go(void *raw_addr, size_t raw_len, + void *stripped_addr, size_t stripped_len, + FILE *outfile, const char *name) { - Elf64_Ehdr *hdr = (Elf64_Ehdr *)addr; + Elf64_Ehdr *hdr = (Elf64_Ehdr *)raw_addr; if (hdr->e_ident[EI_CLASS] == ELFCLASS64) { - go64(addr, len, outfile, name); + go64(raw_addr, raw_len, stripped_addr, stripped_len, + outfile, name); } else if (hdr->e_ident[EI_CLASS] == ELFCLASS32) { - go32(addr, len, outfile, name); + go32(raw_addr, raw_len, stripped_addr, stripped_len, + outfile, name); } else { fail("unknown ELF class\n"); } } +static void map_input(const char *name, void **addr, size_t *len, int prot) +{ + off_t tmp_len; + + int fd = open(name, O_RDONLY); + if (fd == -1) + err(1, "%s", name); + + tmp_len = lseek(fd, 0, SEEK_END); + if (tmp_len == (off_t)-1) + err(1, "lseek"); + *len = (size_t)tmp_len; + + *addr = mmap(NULL, tmp_len, prot, MAP_PRIVATE, fd, 0); + if (*addr == MAP_FAILED) + err(1, "mmap"); + + close(fd); +} + int main(int argc, char **argv) { - int fd; - off_t len; - void *addr; + size_t raw_len, stripped_len; + void *raw_addr, *stripped_addr; FILE *outfile; char *name, *tmp; int namelen; - if (argc != 3) { - printf("Usage: vdso2c INPUT OUTPUT\n"); + if (argc != 4) { + printf("Usage: vdso2c RAW_INPUT STRIPPED_INPUT OUTPUT\n"); return 1; } @@ -143,7 +219,7 @@ int main(int argc, char **argv) * Figure out the struct name. If we're writing to a .so file, * generate raw output insted. */ - name = strdup(argv[2]); + name = strdup(argv[3]); namelen = strlen(name); if (namelen >= 3 && !strcmp(name + namelen - 3, ".so")) { name = NULL; @@ -159,26 +235,18 @@ int main(int argc, char **argv) *tmp = '_'; } - fd = open(argv[1], O_RDONLY); - if (fd == -1) - err(1, "%s", argv[1]); - - len = lseek(fd, 0, SEEK_END); - if (len == (off_t)-1) - err(1, "lseek"); - - addr = mmap(NULL, len, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); - if (addr == MAP_FAILED) - err(1, "mmap"); + map_input(argv[1], &raw_addr, &raw_len, PROT_READ); + map_input(argv[2], &stripped_addr, &stripped_len, PROT_READ); - outfilename = argv[2]; + outfilename = argv[3]; outfile = fopen(outfilename, "w"); if (!outfile) err(1, "%s", argv[2]); - go(addr, (size_t)len, outfile, name); + go(raw_addr, raw_len, stripped_addr, stripped_len, outfile, name); - munmap(addr, len); + munmap(raw_addr, raw_len); + munmap(stripped_addr, stripped_len); fclose(outfile); return 0; diff --git a/arch/x86/vdso/vdso2c.h b/arch/x86/vdso/vdso2c.h index 11b65d4f9414..fd57829b30d8 100644 --- a/arch/x86/vdso/vdso2c.h +++ b/arch/x86/vdso/vdso2c.h @@ -4,139 +4,23 @@ * are built for 32-bit userspace. */ -/* - * We're writing a section table for a few reasons: - * - * The Go runtime had a couple of bugs: it would read the section - * table to try to figure out how many dynamic symbols there were (it - * shouldn't have looked at the section table at all) and, if there - * were no SHT_SYNDYM section table entry, it would use an - * uninitialized value for the number of symbols. An empty DYNSYM - * table would work, but I see no reason not to write a valid one (and - * keep full performance for old Go programs). This hack is only - * needed on x86_64. - * - * The bug was introduced on 2012-08-31 by: - * https://code.google.com/p/go/source/detail?r=56ea40aac72b - * and was fixed on 2014-06-13 by: - * https://code.google.com/p/go/source/detail?r=fc1cd5e12595 - * - * Binutils has issues debugging the vDSO: it reads the section table to - * find SHT_NOTE; it won't look at PT_NOTE for the in-memory vDSO, which - * would break build-id if we removed the section table. Binutils - * also requires that shstrndx != 0. See: - * https://sourceware.org/bugzilla/show_bug.cgi?id=17064 - * - * elfutils might not look for PT_NOTE if there is a section table at - * all. I don't know whether this matters for any practical purpose. - * - * For simplicity, rather than hacking up a partial section table, we - * just write a mostly complete one. We omit non-dynamic symbols, - * though, since they're rather large. - * - * Once binutils gets fixed, we might be able to drop this for all but - * the 64-bit vdso, since build-id only works in kernel RPMs, and - * systems that update to new enough kernel RPMs will likely update - * binutils in sync. build-id has never worked for home-built kernel - * RPMs without manual symlinking, and I suspect that no one ever does - * that. - */ -struct BITSFUNC(fake_sections) -{ - ELF(Shdr) *table; - unsigned long table_offset; - int count, max_count; - - int in_shstrndx; - unsigned long shstr_offset; - const char *shstrtab; - size_t shstrtab_len; - - int out_shstrndx; -}; - -static unsigned int BITSFUNC(find_shname)(struct BITSFUNC(fake_sections) *out, - const char *name) -{ - const char *outname = out->shstrtab; - while (outname - out->shstrtab < out->shstrtab_len) { - if (!strcmp(name, outname)) - return (outname - out->shstrtab) + out->shstr_offset; - outname += strlen(outname) + 1; - } - - if (*name) - printf("Warning: could not find output name \"%s\"\n", name); - return out->shstr_offset + out->shstrtab_len - 1; /* Use a null. */ -} - -static void BITSFUNC(init_sections)(struct BITSFUNC(fake_sections) *out) -{ - if (!out->in_shstrndx) - fail("didn't find the fake shstrndx\n"); - - memset(out->table, 0, out->max_count * sizeof(ELF(Shdr))); - - if (out->max_count < 1) - fail("we need at least two fake output sections\n"); - - PUT_LE(&out->table[0].sh_type, SHT_NULL); - PUT_LE(&out->table[0].sh_name, BITSFUNC(find_shname)(out, "")); - - out->count = 1; -} - -static void BITSFUNC(copy_section)(struct BITSFUNC(fake_sections) *out, - int in_idx, const ELF(Shdr) *in, - const char *name) -{ - uint64_t flags = GET_LE(&in->sh_flags); - - bool copy = flags & SHF_ALLOC && - (GET_LE(&in->sh_size) || - (GET_LE(&in->sh_type) != SHT_RELA && - GET_LE(&in->sh_type) != SHT_REL)) && - strcmp(name, ".altinstructions") && - strcmp(name, ".altinstr_replacement"); - - if (!copy) - return; - - if (out->count >= out->max_count) - fail("too many copied sections (max = %d)\n", out->max_count); - - if (in_idx == out->in_shstrndx) - out->out_shstrndx = out->count; - - out->table[out->count] = *in; - PUT_LE(&out->table[out->count].sh_name, - BITSFUNC(find_shname)(out, name)); - - /* elfutils requires that a strtab have the correct type. */ - if (!strcmp(name, ".fake_shstrtab")) - PUT_LE(&out->table[out->count].sh_type, SHT_STRTAB); - - out->count++; -} - -static void BITSFUNC(go)(void *addr, size_t len, +static void BITSFUNC(go)(void *raw_addr, size_t raw_len, + void *stripped_addr, size_t stripped_len, FILE *outfile, const char *name) { int found_load = 0; unsigned long load_size = -1; /* Work around bogus warning */ - unsigned long data_size; - ELF(Ehdr) *hdr = (ELF(Ehdr) *)addr; + unsigned long mapping_size; + ELF(Ehdr) *hdr = (ELF(Ehdr) *)raw_addr; int i; unsigned long j; ELF(Shdr) *symtab_hdr = NULL, *strtab_hdr, *secstrings_hdr, *alt_sec = NULL; ELF(Dyn) *dyn = 0, *dyn_end = 0; const char *secstrings; - uint64_t syms[NSYMS] = {}; - - struct BITSFUNC(fake_sections) fake_sections = {}; + INT_BITS syms[NSYMS] = {}; - ELF(Phdr) *pt = (ELF(Phdr) *)(addr + GET_LE(&hdr->e_phoff)); + ELF(Phdr) *pt = (ELF(Phdr) *)(raw_addr + GET_LE(&hdr->e_phoff)); /* Walk the segment table. */ for (i = 0; i < GET_LE(&hdr->e_phnum); i++) { @@ -154,14 +38,16 @@ static void BITSFUNC(go)(void *addr, size_t len, load_size = GET_LE(&pt[i].p_memsz); found_load = 1; } else if (GET_LE(&pt[i].p_type) == PT_DYNAMIC) { - dyn = addr + GET_LE(&pt[i].p_offset); - dyn_end = addr + GET_LE(&pt[i].p_offset) + + dyn = raw_addr + GET_LE(&pt[i].p_offset); + dyn_end = raw_addr + GET_LE(&pt[i].p_offset) + GET_LE(&pt[i].p_memsz); } } if (!found_load) fail("no PT_LOAD seg\n"); - data_size = (load_size + 4095) / 4096 * 4096; + + if (stripped_len < load_size) + fail("stripped input is too short\n"); /* Walk the dynamic table */ for (i = 0; dyn + i < dyn_end && @@ -173,11 +59,11 @@ static void BITSFUNC(go)(void *addr, size_t len, } /* Walk the section table */ - secstrings_hdr = addr + GET_LE(&hdr->e_shoff) + + secstrings_hdr = raw_addr + GET_LE(&hdr->e_shoff) + GET_LE(&hdr->e_shentsize)*GET_LE(&hdr->e_shstrndx); - secstrings = addr + GET_LE(&secstrings_hdr->sh_offset); + secstrings = raw_addr + GET_LE(&secstrings_hdr->sh_offset); for (i = 0; i < GET_LE(&hdr->e_shnum); i++) { - ELF(Shdr) *sh = addr + GET_LE(&hdr->e_shoff) + + ELF(Shdr) *sh = raw_addr + GET_LE(&hdr->e_shoff) + GET_LE(&hdr->e_shentsize) * i; if (GET_LE(&sh->sh_type) == SHT_SYMTAB) symtab_hdr = sh; @@ -190,7 +76,7 @@ static void BITSFUNC(go)(void *addr, size_t len, if (!symtab_hdr) fail("no symbol table\n"); - strtab_hdr = addr + GET_LE(&hdr->e_shoff) + + strtab_hdr = raw_addr + GET_LE(&hdr->e_shoff) + GET_LE(&hdr->e_shentsize) * GET_LE(&symtab_hdr->sh_link); /* Walk the symbol table */ @@ -198,9 +84,9 @@ static void BITSFUNC(go)(void *addr, size_t len, i < GET_LE(&symtab_hdr->sh_size) / GET_LE(&symtab_hdr->sh_entsize); i++) { int k; - ELF(Sym) *sym = addr + GET_LE(&symtab_hdr->sh_offset) + + ELF(Sym) *sym = raw_addr + GET_LE(&symtab_hdr->sh_offset) + GET_LE(&symtab_hdr->sh_entsize) * i; - const char *name = addr + GET_LE(&strtab_hdr->sh_offset) + + const char *name = raw_addr + GET_LE(&strtab_hdr->sh_offset) + GET_LE(&sym->st_name); for (k = 0; k < NSYMS; k++) { @@ -209,51 +95,17 @@ static void BITSFUNC(go)(void *addr, size_t len, fail("duplicate symbol %s\n", required_syms[k].name); } + + /* + * Careful: we use negative addresses, but + * st_value is unsigned, so we rely + * on syms[k] being a signed type of the + * correct width. + */ syms[k] = GET_LE(&sym->st_value); } } - - if (!strcmp(name, "fake_shstrtab")) { - ELF(Shdr) *sh; - - fake_sections.in_shstrndx = GET_LE(&sym->st_shndx); - fake_sections.shstrtab = addr + GET_LE(&sym->st_value); - fake_sections.shstrtab_len = GET_LE(&sym->st_size); - sh = addr + GET_LE(&hdr->e_shoff) + - GET_LE(&hdr->e_shentsize) * - fake_sections.in_shstrndx; - fake_sections.shstr_offset = GET_LE(&sym->st_value) - - GET_LE(&sh->sh_addr); - } - } - - /* Build the output section table. */ - if (!syms[sym_VDSO_FAKE_SECTION_TABLE_START] || - !syms[sym_VDSO_FAKE_SECTION_TABLE_END]) - fail("couldn't find fake section table\n"); - if ((syms[sym_VDSO_FAKE_SECTION_TABLE_END] - - syms[sym_VDSO_FAKE_SECTION_TABLE_START]) % sizeof(ELF(Shdr))) - fail("fake section table size isn't a multiple of sizeof(Shdr)\n"); - fake_sections.table = addr + syms[sym_VDSO_FAKE_SECTION_TABLE_START]; - fake_sections.table_offset = syms[sym_VDSO_FAKE_SECTION_TABLE_START]; - fake_sections.max_count = (syms[sym_VDSO_FAKE_SECTION_TABLE_END] - - syms[sym_VDSO_FAKE_SECTION_TABLE_START]) / - sizeof(ELF(Shdr)); - - BITSFUNC(init_sections)(&fake_sections); - for (i = 0; i < GET_LE(&hdr->e_shnum); i++) { - ELF(Shdr) *sh = addr + GET_LE(&hdr->e_shoff) + - GET_LE(&hdr->e_shentsize) * i; - BITSFUNC(copy_section)(&fake_sections, i, sh, - secstrings + GET_LE(&sh->sh_name)); } - if (!fake_sections.out_shstrndx) - fail("didn't generate shstrndx?!?\n"); - - PUT_LE(&hdr->e_shoff, fake_sections.table_offset); - PUT_LE(&hdr->e_shentsize, sizeof(ELF(Shdr))); - PUT_LE(&hdr->e_shnum, fake_sections.count); - PUT_LE(&hdr->e_shstrndx, fake_sections.out_shstrndx); /* Validate mapping addresses. */ for (i = 0; i < sizeof(special_pages) / sizeof(special_pages[0]); i++) { @@ -263,21 +115,23 @@ static void BITSFUNC(go)(void *addr, size_t len, if (syms[i] % 4096) fail("%s must be a multiple of 4096\n", required_syms[i].name); - if (syms[i] < data_size) - fail("%s must be after the text mapping\n", + if (syms[sym_vvar_start] > syms[i] + 4096) + fail("%s underruns begin_vvar\n", required_syms[i].name); - if (syms[sym_end_mapping] < syms[i] + 4096) - fail("%s overruns end_mapping\n", + if (syms[i] + 4096 > 0) + fail("%s is on the wrong side of the vdso text\n", required_syms[i].name); } - if (syms[sym_end_mapping] % 4096) - fail("end_mapping must be a multiple of 4096\n"); + if (syms[sym_vvar_start] % 4096) + fail("vvar_begin must be a multiple of 4096\n"); if (!name) { - fwrite(addr, load_size, 1, outfile); + fwrite(stripped_addr, stripped_len, 1, outfile); return; } + mapping_size = (stripped_len + 4095) / 4096 * 4096; + fprintf(outfile, "/* AUTOMATICALLY GENERATED -- DO NOT EDIT */\n\n"); fprintf(outfile, "#include <linux/linkage.h>\n"); fprintf(outfile, "#include <asm/page_types.h>\n"); @@ -285,20 +139,21 @@ static void BITSFUNC(go)(void *addr, size_t len, fprintf(outfile, "\n"); fprintf(outfile, "static unsigned char raw_data[%lu] __page_aligned_data = {", - data_size); - for (j = 0; j < load_size; j++) { + mapping_size); + for (j = 0; j < stripped_len; j++) { if (j % 10 == 0) fprintf(outfile, "\n\t"); - fprintf(outfile, "0x%02X, ", (int)((unsigned char *)addr)[j]); + fprintf(outfile, "0x%02X, ", + (int)((unsigned char *)stripped_addr)[j]); } fprintf(outfile, "\n};\n\n"); fprintf(outfile, "static struct page *pages[%lu];\n\n", - data_size / 4096); + mapping_size / 4096); fprintf(outfile, "const struct vdso_image %s = {\n", name); fprintf(outfile, "\t.data = raw_data,\n"); - fprintf(outfile, "\t.size = %lu,\n", data_size); + fprintf(outfile, "\t.size = %lu,\n", mapping_size); fprintf(outfile, "\t.text_mapping = {\n"); fprintf(outfile, "\t\t.name = \"[vdso]\",\n"); fprintf(outfile, "\t\t.pages = pages,\n"); @@ -311,8 +166,8 @@ static void BITSFUNC(go)(void *addr, size_t len, } for (i = 0; i < NSYMS; i++) { if (required_syms[i].export && syms[i]) - fprintf(outfile, "\t.sym_%s = 0x%" PRIx64 ",\n", - required_syms[i].name, syms[i]); + fprintf(outfile, "\t.sym_%s = %" PRIi64 ",\n", + required_syms[i].name, (int64_t)syms[i]); } fprintf(outfile, "};\n"); } diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c index 5a5176de8d0a..970463b566cf 100644 --- a/arch/x86/vdso/vma.c +++ b/arch/x86/vdso/vma.c @@ -93,7 +93,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; - unsigned long addr; + unsigned long addr, text_start; int ret = 0; static struct page *no_pages[] = {NULL}; static struct vm_special_mapping vvar_mapping = { @@ -103,26 +103,28 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) if (calculate_addr) { addr = vdso_addr(current->mm->start_stack, - image->sym_end_mapping); + image->size - image->sym_vvar_start); } else { addr = 0; } down_write(&mm->mmap_sem); - addr = get_unmapped_area(NULL, addr, image->sym_end_mapping, 0, 0); + addr = get_unmapped_area(NULL, addr, + image->size - image->sym_vvar_start, 0, 0); if (IS_ERR_VALUE(addr)) { ret = addr; goto up_fail; } - current->mm->context.vdso = (void __user *)addr; + text_start = addr - image->sym_vvar_start; + current->mm->context.vdso = (void __user *)text_start; /* * MAYWRITE to allow gdb to COW and set breakpoints */ vma = _install_special_mapping(mm, - addr, + text_start, image->size, VM_READ|VM_EXEC| VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, @@ -134,9 +136,9 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) } vma = _install_special_mapping(mm, - addr + image->size, - image->sym_end_mapping - image->size, - VM_READ, + addr, + -image->sym_vvar_start, + VM_READ|VM_MAYREAD, &vvar_mapping); if (IS_ERR(vma)) { @@ -146,7 +148,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) if (image->sym_vvar_page) ret = remap_pfn_range(vma, - addr + image->sym_vvar_page, + text_start + image->sym_vvar_page, __pa_symbol(&__vvar_page) >> PAGE_SHIFT, PAGE_SIZE, PAGE_READONLY); @@ -157,7 +159,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) #ifdef CONFIG_HPET_TIMER if (hpet_address && image->sym_hpet_page) { ret = io_remap_pfn_range(vma, - addr + image->sym_hpet_page, + text_start + image->sym_hpet_page, hpet_address >> PAGE_SHIFT, PAGE_SIZE, pgprot_noncached(PAGE_READONLY)); diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 96ab2c09cb68..7322755f337a 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -22,3 +22,4 @@ obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o obj-$(CONFIG_XEN_DOM0) += apic.o vga.o obj-$(CONFIG_SWIOTLB_XEN) += pci-swiotlb-xen.o +obj-$(CONFIG_XEN_EFI) += efi.o diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c new file mode 100644 index 000000000000..a02e09e18f57 --- /dev/null +++ b/arch/x86/xen/efi.c @@ -0,0 +1,43 @@ +/* + * Copyright (c) 2014 Oracle Co., Daniel Kiper + * + * 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/efi.h> +#include <linux/init.h> +#include <linux/string.h> + +#include <xen/xen-ops.h> + +#include <asm/setup.h> + +void __init xen_efi_init(void) +{ + efi_system_table_t *efi_systab_xen; + + efi_systab_xen = xen_efi_probe(); + + if (efi_systab_xen == NULL) + return; + + strncpy((char *)&boot_params.efi_info.efi_loader_signature, "Xen", + sizeof(boot_params.efi_info.efi_loader_signature)); + boot_params.efi_info.efi_systab = (__u32)__pa(efi_systab_xen); + boot_params.efi_info.efi_systab_hi = (__u32)(__pa(efi_systab_xen) >> 32); + + set_bit(EFI_BOOT, &efi.flags); + set_bit(EFI_PARAVIRT, &efi.flags); + set_bit(EFI_64BIT, &efi.flags); +} diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index ffb101e45731..94813515fdd6 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1718,6 +1718,8 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_setup_runstate_info(0); + xen_efi_init(); + /* Start the world */ #ifdef CONFIG_X86_32 i386_start_kernel(); diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 97d87659f779..28c7e0be56e4 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -105,6 +105,14 @@ static inline void __init xen_init_apic(void) } #endif +#ifdef CONFIG_XEN_EFI +extern void xen_efi_init(void); +#else +static inline void __init xen_efi_init(void) +{ +} +#endif + /* Declare an asm function, along with symbols needed to make it inlineable */ #define DECL_ASM(ret, name, ...) \ diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index abb59708a3b7..b61bdf0eea25 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -182,6 +182,7 @@ extern unsigned long get_wchan(struct task_struct *p); #define KSTK_ESP(tsk) (task_pt_regs(tsk)->areg[1]) #define cpu_relax() barrier() +#define cpu_relax_lowlatency() cpu_relax() /* Special register access. */ diff --git a/drivers/Kconfig b/drivers/Kconfig index 0e87a34b6472..4e6e66c3c8d6 100644 --- a/drivers/Kconfig +++ b/drivers/Kconfig @@ -176,4 +176,6 @@ source "drivers/powercap/Kconfig" source "drivers/mcb/Kconfig" +source "drivers/ras/Kconfig" + endmenu diff --git a/drivers/Makefile b/drivers/Makefile index f98b50d8251d..65c32b1cea3d 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -158,3 +158,4 @@ obj-$(CONFIG_NTB) += ntb/ obj-$(CONFIG_FMC) += fmc/ obj-$(CONFIG_POWERCAP) += powercap/ obj-$(CONFIG_MCB) += mcb/ +obj-$(CONFIG_RAS) += ras/ diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index 3f5f745bbbea..d0f3265fb85d 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -376,6 +376,7 @@ config ACPI_EXTLOG tristate "Extended Error Log support" depends on X86_MCE && X86_LOCAL_APIC select UEFI_CPER + select RAS default n help Certain usages such as Predictive Failure Analysis (PFA) require @@ -390,6 +391,7 @@ config ACPI_EXTLOG Enhanced MCA Logging allows firmware to provide additional error information to system software, synchronous with MCE or CMCI. This - driver adds support for that functionality. + driver adds support for that functionality with corresponding + tracepoint which carries that information to userspace. endif # ACPI diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c index 340d09518f8e..b3842ffc19ba 100644 --- a/drivers/acpi/acpi_extlog.c +++ b/drivers/acpi/acpi_extlog.c @@ -12,10 +12,12 @@ #include <linux/cper.h> #include <linux/ratelimit.h> #include <linux/edac.h> +#include <linux/ras.h> #include <asm/cpu.h> #include <asm/mce.h> #include "apei/apei-internal.h" +#include <ras/ras_event.h> #define EXT_ELOG_ENTRY_MASK GENMASK_ULL(51, 0) /* elog entry address mask */ @@ -137,8 +139,12 @@ static int extlog_print(struct notifier_block *nb, unsigned long val, struct mce *mce = (struct mce *)data; int bank = mce->bank; int cpu = mce->extcpu; - struct acpi_hest_generic_status *estatus; - int rc; + struct acpi_hest_generic_status *estatus, *tmp; + struct acpi_hest_generic_data *gdata; + const uuid_le *fru_id = &NULL_UUID_LE; + char *fru_text = ""; + uuid_le *sec_type; + static u32 err_seq; estatus = extlog_elog_entry_check(cpu, bank); if (estatus == NULL) @@ -148,8 +154,29 @@ static int extlog_print(struct notifier_block *nb, unsigned long val, /* clear record status to enable BIOS to update it again */ estatus->block_status = 0; - rc = print_extlog_rcd(NULL, (struct acpi_hest_generic_status *)elog_buf, cpu); + tmp = (struct acpi_hest_generic_status *)elog_buf; + + if (!ras_userspace_consumers()) { + print_extlog_rcd(NULL, tmp, cpu); + goto out; + } + + /* log event via trace */ + err_seq++; + gdata = (struct acpi_hest_generic_data *)(tmp + 1); + if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID) + fru_id = (uuid_le *)gdata->fru_id; + if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT) + fru_text = gdata->fru_text; + sec_type = (uuid_le *)gdata->section_type; + if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) { + struct cper_sec_mem_err *mem = (void *)(gdata + 1); + if (gdata->error_data_length >= sizeof(*mem)) + trace_extlog_mem_event(mem, err_seq, fru_id, fru_text, + (u8)gdata->error_severity); + } +out: return NOTIFY_STOP; } @@ -196,19 +223,16 @@ static int __init extlog_init(void) u64 cap; int rc; + rdmsrl(MSR_IA32_MCG_CAP, cap); + + if (!(cap & MCG_ELOG_P) || !extlog_get_l1addr()) + return -ENODEV; + if (get_edac_report_status() == EDAC_REPORTING_FORCE) { pr_warn("Not loading eMCA, error reporting force-enabled through EDAC.\n"); return -EPERM; } - rc = -ENODEV; - rdmsrl(MSR_IA32_MCG_CAP, cap); - if (!(cap & MCG_ELOG_P)) - return rc; - - if (!extlog_get_l1addr()) - return rc; - rc = -EINVAL; /* get L1 header to fetch necessary information */ l1_hdr_size = sizeof(struct extlog_l1_head); diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig index c4dac7150960..b0140c8fc733 100644 --- a/drivers/acpi/apei/Kconfig +++ b/drivers/acpi/apei/Kconfig @@ -1,9 +1,15 @@ +config HAVE_ACPI_APEI + bool + +config HAVE_ACPI_APEI_NMI + bool + config ACPI_APEI bool "ACPI Platform Error Interface (APEI)" select MISC_FILESYSTEMS select PSTORE select UEFI_CPER - depends on X86 + depends on HAVE_ACPI_APEI help APEI allows to report errors (for example from the chipset) to the operating system. This improves NMI handling diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c index 8678dfe5366b..2cd7bdd6c8b3 100644 --- a/drivers/acpi/apei/apei-base.c +++ b/drivers/acpi/apei/apei-base.c @@ -745,6 +745,19 @@ struct dentry *apei_get_debugfs_dir(void) } EXPORT_SYMBOL_GPL(apei_get_debugfs_dir); +int __weak arch_apei_enable_cmcff(struct acpi_hest_header *hest_hdr, + void *data) +{ + return 1; +} +EXPORT_SYMBOL_GPL(arch_apei_enable_cmcff); + +void __weak arch_apei_report_mem_error(int sev, + struct cper_sec_mem_err *mem_err) +{ +} +EXPORT_SYMBOL_GPL(arch_apei_report_mem_error); + int apei_osc_setup(void) { static u8 whea_uuid_str[] = "ed855e0c-6c90-47bf-a62a-26de0fc5ad5c"; diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 7a38d1465b61..fc5f780bb61d 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -47,11 +47,11 @@ #include <linux/genalloc.h> #include <linux/pci.h> #include <linux/aer.h> +#include <linux/nmi.h> #include <acpi/ghes.h> -#include <asm/mce.h> +#include <acpi/apei.h> #include <asm/tlbflush.h> -#include <asm/nmi.h> #include "apei-internal.h" @@ -86,8 +86,6 @@ bool ghes_disable; module_param_named(disable, ghes_disable, bool, 0); -static int ghes_panic_timeout __read_mostly = 30; - /* * All error sources notified with SCI shares one notifier function, * so they need to be linked and checked one by one. This is applied @@ -97,16 +95,9 @@ static int ghes_panic_timeout __read_mostly = 30; * list changing, not for traversing. */ static LIST_HEAD(ghes_sci); -static LIST_HEAD(ghes_nmi); static DEFINE_MUTEX(ghes_list_mutex); /* - * NMI may be triggered on any CPU, so ghes_nmi_lock is used for - * mutual exclusion. - */ -static DEFINE_RAW_SPINLOCK(ghes_nmi_lock); - -/* * Because the memory area used to transfer hardware error information * from BIOS to Linux can be determined only in NMI, IRQ or timer * handler, but general ioremap can not be used in atomic context, so @@ -114,12 +105,16 @@ static DEFINE_RAW_SPINLOCK(ghes_nmi_lock); */ /* - * Two virtual pages are used, one for NMI context, the other for - * IRQ/PROCESS context + * Two virtual pages are used, one for IRQ/PROCESS context, the other for + * NMI context (optionally). */ -#define GHES_IOREMAP_PAGES 2 -#define GHES_IOREMAP_NMI_PAGE(base) (base) -#define GHES_IOREMAP_IRQ_PAGE(base) ((base) + PAGE_SIZE) +#ifdef CONFIG_HAVE_ACPI_APEI_NMI +#define GHES_IOREMAP_PAGES 2 +#else +#define GHES_IOREMAP_PAGES 1 +#endif +#define GHES_IOREMAP_IRQ_PAGE(base) (base) +#define GHES_IOREMAP_NMI_PAGE(base) ((base) + PAGE_SIZE) /* virtual memory area for atomic ioremap */ static struct vm_struct *ghes_ioremap_area; @@ -130,18 +125,8 @@ static struct vm_struct *ghes_ioremap_area; static DEFINE_RAW_SPINLOCK(ghes_ioremap_lock_nmi); static DEFINE_SPINLOCK(ghes_ioremap_lock_irq); -/* - * printk is not safe in NMI context. So in NMI handler, we allocate - * required memory from lock-less memory allocator - * (ghes_estatus_pool), save estatus into it, put them into lock-less - * list (ghes_estatus_llist), then delay printk into IRQ context via - * irq_work (ghes_proc_irq_work). ghes_estatus_size_request record - * required pool size by all NMI error source. - */ static struct gen_pool *ghes_estatus_pool; static unsigned long ghes_estatus_pool_size_request; -static struct llist_head ghes_estatus_llist; -static struct irq_work ghes_proc_irq_work; struct ghes_estatus_cache *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE]; static atomic_t ghes_estatus_cache_alloced; @@ -192,7 +177,7 @@ static void ghes_iounmap_nmi(void __iomem *vaddr_ptr) BUG_ON(vaddr != (unsigned long)GHES_IOREMAP_NMI_PAGE(base)); unmap_kernel_range_noflush(vaddr, PAGE_SIZE); - __flush_tlb_one(vaddr); + arch_apei_flush_tlb_one(vaddr); } static void ghes_iounmap_irq(void __iomem *vaddr_ptr) @@ -202,7 +187,7 @@ static void ghes_iounmap_irq(void __iomem *vaddr_ptr) BUG_ON(vaddr != (unsigned long)GHES_IOREMAP_IRQ_PAGE(base)); unmap_kernel_range_noflush(vaddr, PAGE_SIZE); - __flush_tlb_one(vaddr); + arch_apei_flush_tlb_one(vaddr); } static int ghes_estatus_pool_init(void) @@ -249,11 +234,6 @@ static int ghes_estatus_pool_expand(unsigned long len) return 0; } -static void ghes_estatus_pool_shrink(unsigned long len) -{ - ghes_estatus_pool_size_request -= PAGE_ALIGN(len); -} - static struct ghes *ghes_new(struct acpi_hest_generic *generic) { struct ghes *ghes; @@ -455,9 +435,7 @@ static void ghes_do_proc(struct ghes *ghes, mem_err = (struct cper_sec_mem_err *)(gdata+1); ghes_edac_report_mem_error(ghes, sev, mem_err); -#ifdef CONFIG_X86_MCE - apei_mce_report_mem_error(sev, mem_err); -#endif + arch_apei_report_mem_error(sev, mem_err); ghes_handle_memory_failure(gdata, sev); } #ifdef CONFIG_ACPI_APEI_PCIEAER @@ -734,6 +712,32 @@ static int ghes_notify_sci(struct notifier_block *this, return ret; } +static struct notifier_block ghes_notifier_sci = { + .notifier_call = ghes_notify_sci, +}; + +#ifdef CONFIG_HAVE_ACPI_APEI_NMI +/* + * printk is not safe in NMI context. So in NMI handler, we allocate + * required memory from lock-less memory allocator + * (ghes_estatus_pool), save estatus into it, put them into lock-less + * list (ghes_estatus_llist), then delay printk into IRQ context via + * irq_work (ghes_proc_irq_work). ghes_estatus_size_request record + * required pool size by all NMI error source. + */ +static struct llist_head ghes_estatus_llist; +static struct irq_work ghes_proc_irq_work; + +/* + * NMI may be triggered on any CPU, so ghes_nmi_lock is used for + * mutual exclusion. + */ +static DEFINE_RAW_SPINLOCK(ghes_nmi_lock); + +static LIST_HEAD(ghes_nmi); + +static int ghes_panic_timeout __read_mostly = 30; + static struct llist_node *llist_nodes_reverse(struct llist_node *llnode) { struct llist_node *next, *tail = NULL; @@ -877,10 +881,6 @@ out: return ret; } -static struct notifier_block ghes_notifier_sci = { - .notifier_call = ghes_notify_sci, -}; - static unsigned long ghes_esource_prealloc_size( const struct acpi_hest_generic *generic) { @@ -896,11 +896,71 @@ static unsigned long ghes_esource_prealloc_size( return prealloc_size; } +static void ghes_estatus_pool_shrink(unsigned long len) +{ + ghes_estatus_pool_size_request -= PAGE_ALIGN(len); +} + +static void ghes_nmi_add(struct ghes *ghes) +{ + unsigned long len; + + len = ghes_esource_prealloc_size(ghes->generic); + ghes_estatus_pool_expand(len); + mutex_lock(&ghes_list_mutex); + if (list_empty(&ghes_nmi)) + register_nmi_handler(NMI_LOCAL, ghes_notify_nmi, 0, "ghes"); + list_add_rcu(&ghes->list, &ghes_nmi); + mutex_unlock(&ghes_list_mutex); +} + +static void ghes_nmi_remove(struct ghes *ghes) +{ + unsigned long len; + + mutex_lock(&ghes_list_mutex); + list_del_rcu(&ghes->list); + if (list_empty(&ghes_nmi)) + unregister_nmi_handler(NMI_LOCAL, "ghes"); + mutex_unlock(&ghes_list_mutex); + /* + * To synchronize with NMI handler, ghes can only be + * freed after NMI handler finishes. + */ + synchronize_rcu(); + len = ghes_esource_prealloc_size(ghes->generic); + ghes_estatus_pool_shrink(len); +} + +static void ghes_nmi_init_cxt(void) +{ + init_irq_work(&ghes_proc_irq_work, ghes_proc_in_irq); +} +#else /* CONFIG_HAVE_ACPI_APEI_NMI */ +static inline void ghes_nmi_add(struct ghes *ghes) +{ + pr_err(GHES_PFX "ID: %d, trying to add NMI notification which is not supported!\n", + ghes->generic->header.source_id); + BUG(); +} + +static inline void ghes_nmi_remove(struct ghes *ghes) +{ + pr_err(GHES_PFX "ID: %d, trying to remove NMI notification which is not supported!\n", + ghes->generic->header.source_id); + BUG(); +} + +static inline void ghes_nmi_init_cxt(void) +{ +} +#endif /* CONFIG_HAVE_ACPI_APEI_NMI */ + static int ghes_probe(struct platform_device *ghes_dev) { struct acpi_hest_generic *generic; struct ghes *ghes = NULL; - unsigned long len; + int rc = -EINVAL; generic = *(struct acpi_hest_generic **)ghes_dev->dev.platform_data; @@ -911,7 +971,13 @@ static int ghes_probe(struct platform_device *ghes_dev) case ACPI_HEST_NOTIFY_POLLED: case ACPI_HEST_NOTIFY_EXTERNAL: case ACPI_HEST_NOTIFY_SCI: + break; case ACPI_HEST_NOTIFY_NMI: + if (!IS_ENABLED(CONFIG_HAVE_ACPI_APEI_NMI)) { + pr_warn(GHES_PFX "Generic hardware error source: %d notified via NMI interrupt is not supported!\n", + generic->header.source_id); + goto err; + } break; case ACPI_HEST_NOTIFY_LOCAL: pr_warning(GHES_PFX "Generic hardware error source: %d notified via local interrupt is not supported!\n", @@ -972,14 +1038,7 @@ static int ghes_probe(struct platform_device *ghes_dev) mutex_unlock(&ghes_list_mutex); break; case ACPI_HEST_NOTIFY_NMI: - len = ghes_esource_prealloc_size(generic); - ghes_estatus_pool_expand(len); - mutex_lock(&ghes_list_mutex); - if (list_empty(&ghes_nmi)) - register_nmi_handler(NMI_LOCAL, ghes_notify_nmi, 0, - "ghes"); - list_add_rcu(&ghes->list, &ghes_nmi); - mutex_unlock(&ghes_list_mutex); + ghes_nmi_add(ghes); break; default: BUG(); @@ -1001,7 +1060,6 @@ static int ghes_remove(struct platform_device *ghes_dev) { struct ghes *ghes; struct acpi_hest_generic *generic; - unsigned long len; ghes = platform_get_drvdata(ghes_dev); generic = ghes->generic; @@ -1022,18 +1080,7 @@ static int ghes_remove(struct platform_device *ghes_dev) mutex_unlock(&ghes_list_mutex); break; case ACPI_HEST_NOTIFY_NMI: - mutex_lock(&ghes_list_mutex); - list_del_rcu(&ghes->list); - if (list_empty(&ghes_nmi)) - unregister_nmi_handler(NMI_LOCAL, "ghes"); - mutex_unlock(&ghes_list_mutex); - /* - * To synchronize with NMI handler, ghes can only be - * freed after NMI handler finishes. - */ - synchronize_rcu(); - len = ghes_esource_prealloc_size(generic); - ghes_estatus_pool_shrink(len); + ghes_nmi_remove(ghes); break; default: BUG(); @@ -1077,7 +1124,7 @@ static int __init ghes_init(void) return -EINVAL; } - init_irq_work(&ghes_proc_irq_work, ghes_proc_in_irq); + ghes_nmi_init_cxt(); rc = ghes_ioremap_init(); if (rc) diff --git a/drivers/acpi/apei/hest.c b/drivers/acpi/apei/hest.c index f5e37f32c71f..06e9b411a0a2 100644 --- a/drivers/acpi/apei/hest.c +++ b/drivers/acpi/apei/hest.c @@ -36,7 +36,6 @@ #include <linux/io.h> #include <linux/platform_device.h> #include <acpi/apei.h> -#include <asm/mce.h> #include "apei-internal.h" @@ -128,33 +127,7 @@ EXPORT_SYMBOL_GPL(apei_hest_parse); */ static int __init hest_parse_cmc(struct acpi_hest_header *hest_hdr, void *data) { -#ifdef CONFIG_X86_MCE - int i; - struct acpi_hest_ia_corrected *cmc; - struct acpi_hest_ia_error_bank *mc_bank; - - if (hest_hdr->type != ACPI_HEST_TYPE_IA32_CORRECTED_CHECK) - return 0; - - cmc = (struct acpi_hest_ia_corrected *)hest_hdr; - if (!cmc->enabled) - return 0; - - /* - * We expect HEST to provide a list of MC banks that report errors - * in firmware first mode. Otherwise, return non-zero value to - * indicate that we are done parsing HEST. - */ - if (!(cmc->flags & ACPI_HEST_FIRMWARE_FIRST) || !cmc->num_hardware_banks) - return 1; - - pr_info(HEST_PFX "Enabling Firmware First mode for corrected errors.\n"); - - mc_bank = (struct acpi_hest_ia_error_bank *)(cmc + 1); - for (i = 0; i < cmc->num_hardware_banks; i++, mc_bank++) - mce_disable_bank(mc_bank->bank_number); -#endif - return 1; + return arch_apei_enable_cmcff(hest_hdr, data); } struct ghes_arr { diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index 9c62340c2360..6ba463ceccc6 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -498,5 +498,6 @@ void acpi_pci_irq_disable(struct pci_dev *dev) */ dev_dbg(&dev->dev, "PCI INT %c disabled\n", pin_name(pin)); - acpi_unregister_gsi(gsi); + if (gsi >= 0 && dev->irq > 0) + acpi_unregister_gsi(gsi); } diff --git a/drivers/char/hangcheck-timer.c b/drivers/char/hangcheck-timer.c index f953c96efc86..ebc4c73d8ca4 100644 --- a/drivers/char/hangcheck-timer.c +++ b/drivers/char/hangcheck-timer.c @@ -49,7 +49,7 @@ #include <asm/uaccess.h> #include <linux/sysrq.h> #include <linux/timer.h> -#include <linux/time.h> +#include <linux/hrtimer.h> #define VERSION_STR "0.9.1" @@ -117,24 +117,7 @@ __setup("hcheck_reboot", hangcheck_parse_reboot); __setup("hcheck_dump_tasks", hangcheck_parse_dump_tasks); #endif /* not MODULE */ -#if defined(CONFIG_S390) -# define HAVE_MONOTONIC -# define TIMER_FREQ 1000000000ULL -#else -# define TIMER_FREQ 1000000000ULL -#endif - -#ifdef HAVE_MONOTONIC -extern unsigned long long monotonic_clock(void); -#else -static inline unsigned long long monotonic_clock(void) -{ - struct timespec ts; - getrawmonotonic(&ts); - return timespec_to_ns(&ts); -} -#endif /* HAVE_MONOTONIC */ - +#define TIMER_FREQ 1000000000ULL /* Last time scheduled */ static unsigned long long hangcheck_tsc, hangcheck_tsc_margin; @@ -143,12 +126,11 @@ static void hangcheck_fire(unsigned long); static DEFINE_TIMER(hangcheck_ticktock, hangcheck_fire, 0, 0); - static void hangcheck_fire(unsigned long data) { unsigned long long cur_tsc, tsc_diff; - cur_tsc = monotonic_clock(); + cur_tsc = ktime_get_ns(); if (cur_tsc > hangcheck_tsc) tsc_diff = cur_tsc - hangcheck_tsc; @@ -177,7 +159,7 @@ static void hangcheck_fire(unsigned long data) tsc_diff, tsc_diff - hangcheck_tick*TIMER_FREQ); #endif mod_timer(&hangcheck_ticktock, jiffies + (hangcheck_tick*HZ)); - hangcheck_tsc = monotonic_clock(); + hangcheck_tsc = ktime_get_ns(); } @@ -185,16 +167,11 @@ static int __init hangcheck_init(void) { printk("Hangcheck: starting hangcheck timer %s (tick is %d seconds, margin is %d seconds).\n", VERSION_STR, hangcheck_tick, hangcheck_margin); -#if defined (HAVE_MONOTONIC) - printk("Hangcheck: Using monotonic_clock().\n"); -#else - printk("Hangcheck: Using getrawmonotonic().\n"); -#endif /* HAVE_MONOTONIC */ hangcheck_tsc_margin = (unsigned long long)(hangcheck_margin + hangcheck_tick); hangcheck_tsc_margin *= (unsigned long long)TIMER_FREQ; - hangcheck_tsc = monotonic_clock(); + hangcheck_tsc = ktime_get_ns(); mod_timer(&hangcheck_ticktock, jiffies + (hangcheck_tick*HZ)); return 0; diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 065131cbfcc0..cfd6519df661 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -1,3 +1,5 @@ +menu "Clock Source drivers" + config CLKSRC_OF bool @@ -125,6 +127,7 @@ config CLKSRC_METAG_GENERIC config CLKSRC_EXYNOS_MCT def_bool y if ARCH_EXYNOS + depends on !ARM64 help Support for Multi Core Timer controller on Exynos SoCs. @@ -149,6 +152,11 @@ config VF_PIT_TIMER config SYS_SUPPORTS_SH_CMT bool +config MTK_TIMER + select CLKSRC_OF + select CLKSRC_MMIO + bool + config SYS_SUPPORTS_SH_MTU2 bool @@ -173,7 +181,7 @@ config SH_TIMER_MTU2 default SYS_SUPPORTS_SH_MTU2 help This enables build of a clockevent driver for the Multi-Function - Timer Pulse Unit 2 (TMU2) hardware available on SoCs from Renesas. + Timer Pulse Unit 2 (MTU2) hardware available on SoCs from Renesas. This hardware comes with 16 bit-timer registers. config SH_TIMER_TMU @@ -187,7 +195,7 @@ config SH_TIMER_TMU config EM_TIMER_STI bool "Renesas STI timer driver" if COMPILE_TEST - depends on GENERIC_CLOCKEVENTS + depends on GENERIC_CLOCKEVENTS && HAS_IOMEM default SYS_SUPPORTS_EM_STI help This enables build of a clocksource and clockevent driver for @@ -207,3 +215,5 @@ config CLKSRC_VERSATILE counter available in the "System Registers" block of ARM Versatile, RealView and Versatile Express reference platforms. + +endmenu diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile index 800b1303c236..7fd9fd1dff42 100644 --- a/drivers/clocksource/Makefile +++ b/drivers/clocksource/Makefile @@ -16,9 +16,11 @@ obj-$(CONFIG_CLKSRC_DBX500_PRCMU) += clksrc-dbx500-prcmu.o obj-$(CONFIG_ARMADA_370_XP_TIMER) += time-armada-370-xp.o obj-$(CONFIG_ORION_TIMER) += time-orion.o obj-$(CONFIG_ARCH_BCM2835) += bcm2835_timer.o +obj-$(CONFIG_ARCH_CLPS711X) += clps711x-timer.o obj-$(CONFIG_ARCH_MARCO) += timer-marco.o obj-$(CONFIG_ARCH_MOXART) += moxart_timer.o obj-$(CONFIG_ARCH_MXS) += mxs_timer.o +obj-$(CONFIG_ARCH_PXA) += pxa_timer.o obj-$(CONFIG_ARCH_PRIMA2) += timer-prima2.o obj-$(CONFIG_ARCH_U300) += timer-u300.o obj-$(CONFIG_SUN4I_TIMER) += sun4i_timer.o @@ -34,6 +36,7 @@ obj-$(CONFIG_CLKSRC_SAMSUNG_PWM) += samsung_pwm_timer.o obj-$(CONFIG_FSL_FTM_TIMER) += fsl_ftm_timer.o obj-$(CONFIG_VF_PIT_TIMER) += vf_pit_timer.o obj-$(CONFIG_CLKSRC_QCOM) += qcom-timer.o +obj-$(CONFIG_MTK_TIMER) += mtk_timer.o obj-$(CONFIG_ARM_ARCH_TIMER) += arm_arch_timer.o obj-$(CONFIG_ARM_GLOBAL_TIMER) += arm_global_timer.o diff --git a/drivers/clocksource/clps711x-timer.c b/drivers/clocksource/clps711x-timer.c new file mode 100644 index 000000000000..d83ec1f2fddc --- /dev/null +++ b/drivers/clocksource/clps711x-timer.c @@ -0,0 +1,131 @@ +/* + * Cirrus Logic CLPS711X clocksource driver + * + * Copyright (C) 2014 Alexander Shiyan <shc_work@mail.ru> + * + * 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/clk.h> +#include <linux/clockchips.h> +#include <linux/clocksource.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/sched_clock.h> +#include <linux/slab.h> + +enum { + CLPS711X_CLKSRC_CLOCKSOURCE, + CLPS711X_CLKSRC_CLOCKEVENT, +}; + +static void __iomem *tcd; + +static u64 notrace clps711x_sched_clock_read(void) +{ + return ~readw(tcd); +} + +static int __init _clps711x_clksrc_init(struct clk *clock, void __iomem *base) +{ + unsigned long rate; + + if (!base) + return -ENOMEM; + if (IS_ERR(clock)) + return PTR_ERR(clock); + + rate = clk_get_rate(clock); + + tcd = base; + + clocksource_mmio_init(tcd, "clps711x-clocksource", rate, 300, 16, + clocksource_mmio_readw_down); + + sched_clock_register(clps711x_sched_clock_read, 16, rate); + + return 0; +} + +static irqreturn_t clps711x_timer_interrupt(int irq, void *dev_id) +{ + struct clock_event_device *evt = dev_id; + + evt->event_handler(evt); + + return IRQ_HANDLED; +} + +static void clps711x_clockevent_set_mode(enum clock_event_mode mode, + struct clock_event_device *evt) +{ +} + +static int __init _clps711x_clkevt_init(struct clk *clock, void __iomem *base, + unsigned int irq) +{ + struct clock_event_device *clkevt; + unsigned long rate; + + if (!irq) + return -EINVAL; + if (!base) + return -ENOMEM; + if (IS_ERR(clock)) + return PTR_ERR(clock); + + clkevt = kzalloc(sizeof(*clkevt), GFP_KERNEL); + if (!clkevt) + return -ENOMEM; + + rate = clk_get_rate(clock); + + /* Set Timer prescaler */ + writew(DIV_ROUND_CLOSEST(rate, HZ), base); + + clkevt->name = "clps711x-clockevent"; + clkevt->rating = 300; + clkevt->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_C3STOP; + clkevt->set_mode = clps711x_clockevent_set_mode; + clkevt->cpumask = cpumask_of(0); + clockevents_config_and_register(clkevt, HZ, 0, 0); + + return request_irq(irq, clps711x_timer_interrupt, IRQF_TIMER, + "clps711x-timer", clkevt); +} + +void __init clps711x_clksrc_init(void __iomem *tc1_base, void __iomem *tc2_base, + unsigned int irq) +{ + struct clk *tc1 = clk_get_sys("clps711x-timer.0", NULL); + struct clk *tc2 = clk_get_sys("clps711x-timer.1", NULL); + + BUG_ON(_clps711x_clksrc_init(tc1, tc1_base)); + BUG_ON(_clps711x_clkevt_init(tc2, tc2_base, irq)); +} + +#ifdef CONFIG_CLKSRC_OF +static void __init clps711x_timer_init(struct device_node *np) +{ + unsigned int irq = irq_of_parse_and_map(np, 0); + struct clk *clock = of_clk_get(np, 0); + void __iomem *base = of_iomap(np, 0); + + switch (of_alias_get_id(np, "timer")) { + case CLPS711X_CLKSRC_CLOCKSOURCE: + BUG_ON(_clps711x_clksrc_init(clock, base)); + break; + case CLPS711X_CLKSRC_CLOCKEVENT: + BUG_ON(_clps711x_clkevt_init(clock, base, irq)); + break; + default: + break; + } +} +CLOCKSOURCE_OF_DECLARE(clps711x, "cirrus,clps711x-timer", clps711x_timer_init); +#endif diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c index ab51bf20a3ed..9403061a2acc 100644 --- a/drivers/clocksource/exynos_mct.c +++ b/drivers/clocksource/exynos_mct.c @@ -94,7 +94,7 @@ static void exynos4_mct_write(unsigned int value, unsigned long offset) u32 mask; u32 i; - __raw_writel(value, reg_base + offset); + writel_relaxed(value, reg_base + offset); if (likely(offset >= EXYNOS4_MCT_L_BASE(0))) { stat_addr = (offset & ~EXYNOS4_MCT_L_MASK) + MCT_L_WSTAT_OFFSET; @@ -144,8 +144,8 @@ static void exynos4_mct_write(unsigned int value, unsigned long offset) /* Wait maximum 1 ms until written values are applied */ for (i = 0; i < loops_per_jiffy / 1000 * HZ; i++) - if (__raw_readl(reg_base + stat_addr) & mask) { - __raw_writel(mask, reg_base + stat_addr); + if (readl_relaxed(reg_base + stat_addr) & mask) { + writel_relaxed(mask, reg_base + stat_addr); return; } @@ -157,28 +157,51 @@ static void exynos4_mct_frc_start(void) { u32 reg; - reg = __raw_readl(reg_base + EXYNOS4_MCT_G_TCON); + reg = readl_relaxed(reg_base + EXYNOS4_MCT_G_TCON); reg |= MCT_G_TCON_START; exynos4_mct_write(reg, EXYNOS4_MCT_G_TCON); } -static cycle_t notrace _exynos4_frc_read(void) +/** + * exynos4_read_count_64 - Read all 64-bits of the global counter + * + * This will read all 64-bits of the global counter taking care to make sure + * that the upper and lower half match. Note that reading the MCT can be quite + * slow (hundreds of nanoseconds) so you should use the 32-bit (lower half + * only) version when possible. + * + * Returns the number of cycles in the global counter. + */ +static u64 exynos4_read_count_64(void) { unsigned int lo, hi; - u32 hi2 = __raw_readl(reg_base + EXYNOS4_MCT_G_CNT_U); + u32 hi2 = readl_relaxed(reg_base + EXYNOS4_MCT_G_CNT_U); do { hi = hi2; - lo = __raw_readl(reg_base + EXYNOS4_MCT_G_CNT_L); - hi2 = __raw_readl(reg_base + EXYNOS4_MCT_G_CNT_U); + lo = readl_relaxed(reg_base + EXYNOS4_MCT_G_CNT_L); + hi2 = readl_relaxed(reg_base + EXYNOS4_MCT_G_CNT_U); } while (hi != hi2); return ((cycle_t)hi << 32) | lo; } +/** + * exynos4_read_count_32 - Read the lower 32-bits of the global counter + * + * This will read just the lower 32-bits of the global counter. This is marked + * as notrace so it can be used by the scheduler clock. + * + * Returns the number of cycles in the global counter (lower 32 bits). + */ +static u32 notrace exynos4_read_count_32(void) +{ + return readl_relaxed(reg_base + EXYNOS4_MCT_G_CNT_L); +} + static cycle_t exynos4_frc_read(struct clocksource *cs) { - return _exynos4_frc_read(); + return exynos4_read_count_32(); } static void exynos4_frc_resume(struct clocksource *cs) @@ -190,21 +213,23 @@ struct clocksource mct_frc = { .name = "mct-frc", .rating = 400, .read = exynos4_frc_read, - .mask = CLOCKSOURCE_MASK(64), + .mask = CLOCKSOURCE_MASK(32), .flags = CLOCK_SOURCE_IS_CONTINUOUS, .resume = exynos4_frc_resume, }; static u64 notrace exynos4_read_sched_clock(void) { - return _exynos4_frc_read(); + return exynos4_read_count_32(); } static struct delay_timer exynos4_delay_timer; static cycles_t exynos4_read_current_timer(void) { - return _exynos4_frc_read(); + BUILD_BUG_ON_MSG(sizeof(cycles_t) != sizeof(u32), + "cycles_t needs to move to 32-bit for ARM64 usage"); + return exynos4_read_count_32(); } static void __init exynos4_clocksource_init(void) @@ -218,14 +243,14 @@ static void __init exynos4_clocksource_init(void) if (clocksource_register_hz(&mct_frc, clk_rate)) panic("%s: can't register clocksource\n", mct_frc.name); - sched_clock_register(exynos4_read_sched_clock, 64, clk_rate); + sched_clock_register(exynos4_read_sched_clock, 32, clk_rate); } static void exynos4_mct_comp0_stop(void) { unsigned int tcon; - tcon = __raw_readl(reg_base + EXYNOS4_MCT_G_TCON); + tcon = readl_relaxed(reg_base + EXYNOS4_MCT_G_TCON); tcon &= ~(MCT_G_TCON_COMP0_ENABLE | MCT_G_TCON_COMP0_AUTO_INC); exynos4_mct_write(tcon, EXYNOS4_MCT_G_TCON); @@ -238,14 +263,14 @@ static void exynos4_mct_comp0_start(enum clock_event_mode mode, unsigned int tcon; cycle_t comp_cycle; - tcon = __raw_readl(reg_base + EXYNOS4_MCT_G_TCON); + tcon = readl_relaxed(reg_base + EXYNOS4_MCT_G_TCON); if (mode == CLOCK_EVT_MODE_PERIODIC) { tcon |= MCT_G_TCON_COMP0_AUTO_INC; exynos4_mct_write(cycles, EXYNOS4_MCT_G_COMP0_ADD_INCR); } - comp_cycle = exynos4_frc_read(&mct_frc) + cycles; + comp_cycle = exynos4_read_count_64() + cycles; exynos4_mct_write((u32)comp_cycle, EXYNOS4_MCT_G_COMP0_L); exynos4_mct_write((u32)(comp_cycle >> 32), EXYNOS4_MCT_G_COMP0_U); @@ -327,7 +352,7 @@ static void exynos4_mct_tick_stop(struct mct_clock_event_device *mevt) unsigned long mask = MCT_L_TCON_INT_START | MCT_L_TCON_TIMER_START; unsigned long offset = mevt->base + MCT_L_TCON_OFFSET; - tmp = __raw_readl(reg_base + offset); + tmp = readl_relaxed(reg_base + offset); if (tmp & mask) { tmp &= ~mask; exynos4_mct_write(tmp, offset); @@ -349,7 +374,7 @@ static void exynos4_mct_tick_start(unsigned long cycles, /* enable MCT tick interrupt */ exynos4_mct_write(0x1, mevt->base + MCT_L_INT_ENB_OFFSET); - tmp = __raw_readl(reg_base + mevt->base + MCT_L_TCON_OFFSET); + tmp = readl_relaxed(reg_base + mevt->base + MCT_L_TCON_OFFSET); tmp |= MCT_L_TCON_INT_START | MCT_L_TCON_TIMER_START | MCT_L_TCON_INTERVAL_MODE; exynos4_mct_write(tmp, mevt->base + MCT_L_TCON_OFFSET); @@ -401,7 +426,7 @@ static int exynos4_mct_tick_clear(struct mct_clock_event_device *mevt) exynos4_mct_tick_stop(mevt); /* Clear the MCT tick interrupt */ - if (__raw_readl(reg_base + mevt->base + MCT_L_INT_CSTAT_OFFSET) & 1) { + if (readl_relaxed(reg_base + mevt->base + MCT_L_INT_CSTAT_OFFSET) & 1) { exynos4_mct_write(0x1, mevt->base + MCT_L_INT_CSTAT_OFFSET); return 1; } else { diff --git a/drivers/clocksource/mtk_timer.c b/drivers/clocksource/mtk_timer.c new file mode 100644 index 000000000000..32a3d25795d3 --- /dev/null +++ b/drivers/clocksource/mtk_timer.c @@ -0,0 +1,261 @@ +/* + * Mediatek SoCs General-Purpose Timer handling. + * + * Copyright (C) 2014 Matthias Brugger + * + * Matthias Brugger <matthias.bgg@gmail.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. + */ + +#include <linux/clk.h> +#include <linux/clockchips.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/irqreturn.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/slab.h> + +#define GPT_IRQ_EN_REG 0x00 +#define GPT_IRQ_ENABLE(val) BIT((val) - 1) +#define GPT_IRQ_ACK_REG 0x08 +#define GPT_IRQ_ACK(val) BIT((val) - 1) + +#define TIMER_CTRL_REG(val) (0x10 * (val)) +#define TIMER_CTRL_OP(val) (((val) & 0x3) << 4) +#define TIMER_CTRL_OP_ONESHOT (0) +#define TIMER_CTRL_OP_REPEAT (1) +#define TIMER_CTRL_OP_FREERUN (3) +#define TIMER_CTRL_CLEAR (2) +#define TIMER_CTRL_ENABLE (1) +#define TIMER_CTRL_DISABLE (0) + +#define TIMER_CLK_REG(val) (0x04 + (0x10 * (val))) +#define TIMER_CLK_SRC(val) (((val) & 0x1) << 4) +#define TIMER_CLK_SRC_SYS13M (0) +#define TIMER_CLK_SRC_RTC32K (1) +#define TIMER_CLK_DIV1 (0x0) +#define TIMER_CLK_DIV2 (0x1) + +#define TIMER_CNT_REG(val) (0x08 + (0x10 * (val))) +#define TIMER_CMP_REG(val) (0x0C + (0x10 * (val))) + +#define GPT_CLK_EVT 1 +#define GPT_CLK_SRC 2 + +struct mtk_clock_event_device { + void __iomem *gpt_base; + u32 ticks_per_jiffy; + struct clock_event_device dev; +}; + +static inline struct mtk_clock_event_device *to_mtk_clk( + struct clock_event_device *c) +{ + return container_of(c, struct mtk_clock_event_device, dev); +} + +static void mtk_clkevt_time_stop(struct mtk_clock_event_device *evt, u8 timer) +{ + u32 val; + + val = readl(evt->gpt_base + TIMER_CTRL_REG(timer)); + writel(val & ~TIMER_CTRL_ENABLE, evt->gpt_base + + TIMER_CTRL_REG(timer)); +} + +static void mtk_clkevt_time_setup(struct mtk_clock_event_device *evt, + unsigned long delay, u8 timer) +{ + writel(delay, evt->gpt_base + TIMER_CMP_REG(timer)); +} + +static void mtk_clkevt_time_start(struct mtk_clock_event_device *evt, + bool periodic, u8 timer) +{ + u32 val; + + /* Acknowledge interrupt */ + writel(GPT_IRQ_ACK(timer), evt->gpt_base + GPT_IRQ_ACK_REG); + + val = readl(evt->gpt_base + TIMER_CTRL_REG(timer)); + + /* Clear 2 bit timer operation mode field */ + val &= ~TIMER_CTRL_OP(0x3); + + if (periodic) + val |= TIMER_CTRL_OP(TIMER_CTRL_OP_REPEAT); + else + val |= TIMER_CTRL_OP(TIMER_CTRL_OP_ONESHOT); + + writel(val | TIMER_CTRL_ENABLE | TIMER_CTRL_CLEAR, + evt->gpt_base + TIMER_CTRL_REG(timer)); +} + +static void mtk_clkevt_mode(enum clock_event_mode mode, + struct clock_event_device *clk) +{ + struct mtk_clock_event_device *evt = to_mtk_clk(clk); + + mtk_clkevt_time_stop(evt, GPT_CLK_EVT); + + switch (mode) { + case CLOCK_EVT_MODE_PERIODIC: + mtk_clkevt_time_setup(evt, evt->ticks_per_jiffy, GPT_CLK_EVT); + mtk_clkevt_time_start(evt, true, GPT_CLK_EVT); + break; + case CLOCK_EVT_MODE_ONESHOT: + /* Timer is enabled in set_next_event */ + break; + case CLOCK_EVT_MODE_UNUSED: + case CLOCK_EVT_MODE_SHUTDOWN: + default: + /* No more interrupts will occur as source is disabled */ + break; + } +} + +static int mtk_clkevt_next_event(unsigned long event, + struct clock_event_device *clk) +{ + struct mtk_clock_event_device *evt = to_mtk_clk(clk); + + mtk_clkevt_time_stop(evt, GPT_CLK_EVT); + mtk_clkevt_time_setup(evt, event, GPT_CLK_EVT); + mtk_clkevt_time_start(evt, false, GPT_CLK_EVT); + + return 0; +} + +static irqreturn_t mtk_timer_interrupt(int irq, void *dev_id) +{ + struct mtk_clock_event_device *evt = dev_id; + + /* Acknowledge timer0 irq */ + writel(GPT_IRQ_ACK(GPT_CLK_EVT), evt->gpt_base + GPT_IRQ_ACK_REG); + evt->dev.event_handler(&evt->dev); + + return IRQ_HANDLED; +} + +static void mtk_timer_global_reset(struct mtk_clock_event_device *evt) +{ + /* Disable all interrupts */ + writel(0x0, evt->gpt_base + GPT_IRQ_EN_REG); + /* Acknowledge all interrupts */ + writel(0x3f, evt->gpt_base + GPT_IRQ_ACK_REG); +} + +static void +mtk_timer_setup(struct mtk_clock_event_device *evt, u8 timer, u8 option) +{ + writel(TIMER_CTRL_CLEAR | TIMER_CTRL_DISABLE, + evt->gpt_base + TIMER_CTRL_REG(timer)); + + writel(TIMER_CLK_SRC(TIMER_CLK_SRC_SYS13M) | TIMER_CLK_DIV1, + evt->gpt_base + TIMER_CLK_REG(timer)); + + writel(0x0, evt->gpt_base + TIMER_CMP_REG(timer)); + + writel(TIMER_CTRL_OP(option) | TIMER_CTRL_ENABLE, + evt->gpt_base + TIMER_CTRL_REG(timer)); +} + +static void mtk_timer_enable_irq(struct mtk_clock_event_device *evt, u8 timer) +{ + u32 val; + + val = readl(evt->gpt_base + GPT_IRQ_EN_REG); + writel(val | GPT_IRQ_ENABLE(timer), + evt->gpt_base + GPT_IRQ_EN_REG); +} + +static void __init mtk_timer_init(struct device_node *node) +{ + struct mtk_clock_event_device *evt; + struct resource res; + unsigned long rate = 0; + struct clk *clk; + + evt = kzalloc(sizeof(*evt), GFP_KERNEL); + if (!evt) { + pr_warn("Can't allocate mtk clock event driver struct"); + return; + } + + evt->dev.name = "mtk_tick"; + evt->dev.rating = 300; + evt->dev.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT; + evt->dev.set_mode = mtk_clkevt_mode; + evt->dev.set_next_event = mtk_clkevt_next_event; + evt->dev.cpumask = cpu_possible_mask; + + evt->gpt_base = of_io_request_and_map(node, 0, "mtk-timer"); + if (IS_ERR(evt->gpt_base)) { + pr_warn("Can't get resource\n"); + return; + } + + evt->dev.irq = irq_of_parse_and_map(node, 0); + if (evt->dev.irq <= 0) { + pr_warn("Can't parse IRQ"); + goto err_mem; + } + + clk = of_clk_get(node, 0); + if (IS_ERR(clk)) { + pr_warn("Can't get timer clock"); + goto err_irq; + } + + if (clk_prepare_enable(clk)) { + pr_warn("Can't prepare clock"); + goto err_clk_put; + } + rate = clk_get_rate(clk); + + if (request_irq(evt->dev.irq, mtk_timer_interrupt, + IRQF_TIMER | IRQF_IRQPOLL, "mtk_timer", evt)) { + pr_warn("failed to setup irq %d\n", evt->dev.irq); + goto err_clk_disable; + } + + evt->ticks_per_jiffy = DIV_ROUND_UP(rate, HZ); + + mtk_timer_global_reset(evt); + + /* Configure clock source */ + mtk_timer_setup(evt, GPT_CLK_SRC, TIMER_CTRL_OP_FREERUN); + clocksource_mmio_init(evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC), + node->name, rate, 300, 32, clocksource_mmio_readl_up); + + /* Configure clock event */ + mtk_timer_setup(evt, GPT_CLK_EVT, TIMER_CTRL_OP_REPEAT); + mtk_timer_enable_irq(evt, GPT_CLK_EVT); + + clockevents_config_and_register(&evt->dev, rate, 0x3, + 0xffffffff); + return; + +err_clk_disable: + clk_disable_unprepare(clk); +err_clk_put: + clk_put(clk); +err_irq: + irq_dispose_mapping(evt->dev.irq); +err_mem: + iounmap(evt->gpt_base); + of_address_to_resource(node, 0, &res); + release_mem_region(res.start, resource_size(&res)); +} +CLOCKSOURCE_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_timer_init); diff --git a/drivers/clocksource/pxa_timer.c b/drivers/clocksource/pxa_timer.c new file mode 100644 index 000000000000..941f3f344e08 --- /dev/null +++ b/drivers/clocksource/pxa_timer.c @@ -0,0 +1,227 @@ +/* + * arch/arm/mach-pxa/time.c + * + * PXA clocksource, clockevents, and OST interrupt handlers. + * Copyright (c) 2007 by Bill Gatliff <bgat@billgatliff.com>. + * + * Derived from Nicolas Pitre's PXA timer handler Copyright (c) 2001 + * by MontaVista Software, Inc. (Nico, your code rocks!) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/clk.h> +#include <linux/clockchips.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/sched_clock.h> + +#include <asm/div64.h> + +#define OSMR0 0x00 /* OS Timer 0 Match Register */ +#define OSMR1 0x04 /* OS Timer 1 Match Register */ +#define OSMR2 0x08 /* OS Timer 2 Match Register */ +#define OSMR3 0x0C /* OS Timer 3 Match Register */ + +#define OSCR 0x10 /* OS Timer Counter Register */ +#define OSSR 0x14 /* OS Timer Status Register */ +#define OWER 0x18 /* OS Timer Watchdog Enable Register */ +#define OIER 0x1C /* OS Timer Interrupt Enable Register */ + +#define OSSR_M3 (1 << 3) /* Match status channel 3 */ +#define OSSR_M2 (1 << 2) /* Match status channel 2 */ +#define OSSR_M1 (1 << 1) /* Match status channel 1 */ +#define OSSR_M0 (1 << 0) /* Match status channel 0 */ + +#define OIER_E0 (1 << 0) /* Interrupt enable channel 0 */ + +/* + * This is PXA's sched_clock implementation. This has a resolution + * of at least 308 ns and a maximum value of 208 days. + * + * The return value is guaranteed to be monotonic in that range as + * long as there is always less than 582 seconds between successive + * calls to sched_clock() which should always be the case in practice. + */ + +#define timer_readl(reg) readl_relaxed(timer_base + (reg)) +#define timer_writel(val, reg) writel_relaxed((val), timer_base + (reg)) + +static void __iomem *timer_base; + +static u64 notrace pxa_read_sched_clock(void) +{ + return timer_readl(OSCR); +} + + +#define MIN_OSCR_DELTA 16 + +static irqreturn_t +pxa_ost0_interrupt(int irq, void *dev_id) +{ + struct clock_event_device *c = dev_id; + + /* Disarm the compare/match, signal the event. */ + timer_writel(timer_readl(OIER) & ~OIER_E0, OIER); + timer_writel(OSSR_M0, OSSR); + c->event_handler(c); + + return IRQ_HANDLED; +} + +static int +pxa_osmr0_set_next_event(unsigned long delta, struct clock_event_device *dev) +{ + unsigned long next, oscr; + + timer_writel(timer_readl(OIER) | OIER_E0, OIER); + next = timer_readl(OSCR) + delta; + timer_writel(next, OSMR0); + oscr = timer_readl(OSCR); + + return (signed)(next - oscr) <= MIN_OSCR_DELTA ? -ETIME : 0; +} + +static void +pxa_osmr0_set_mode(enum clock_event_mode mode, struct clock_event_device *dev) +{ + switch (mode) { + case CLOCK_EVT_MODE_ONESHOT: + timer_writel(timer_readl(OIER) & ~OIER_E0, OIER); + timer_writel(OSSR_M0, OSSR); + break; + + case CLOCK_EVT_MODE_UNUSED: + case CLOCK_EVT_MODE_SHUTDOWN: + /* initializing, released, or preparing for suspend */ + timer_writel(timer_readl(OIER) & ~OIER_E0, OIER); + timer_writel(OSSR_M0, OSSR); + break; + + case CLOCK_EVT_MODE_RESUME: + case CLOCK_EVT_MODE_PERIODIC: + break; + } +} + +#ifdef CONFIG_PM +static unsigned long osmr[4], oier, oscr; + +static void pxa_timer_suspend(struct clock_event_device *cedev) +{ + osmr[0] = timer_readl(OSMR0); + osmr[1] = timer_readl(OSMR1); + osmr[2] = timer_readl(OSMR2); + osmr[3] = timer_readl(OSMR3); + oier = timer_readl(OIER); + oscr = timer_readl(OSCR); +} + +static void pxa_timer_resume(struct clock_event_device *cedev) +{ + /* + * Ensure that we have at least MIN_OSCR_DELTA between match + * register 0 and the OSCR, to guarantee that we will receive + * the one-shot timer interrupt. We adjust OSMR0 in preference + * to OSCR to guarantee that OSCR is monotonically incrementing. + */ + if (osmr[0] - oscr < MIN_OSCR_DELTA) + osmr[0] += MIN_OSCR_DELTA; + + timer_writel(osmr[0], OSMR0); + timer_writel(osmr[1], OSMR1); + timer_writel(osmr[2], OSMR2); + timer_writel(osmr[3], OSMR3); + timer_writel(oier, OIER); + timer_writel(oscr, OSCR); +} +#else +#define pxa_timer_suspend NULL +#define pxa_timer_resume NULL +#endif + +static struct clock_event_device ckevt_pxa_osmr0 = { + .name = "osmr0", + .features = CLOCK_EVT_FEAT_ONESHOT, + .rating = 200, + .set_next_event = pxa_osmr0_set_next_event, + .set_mode = pxa_osmr0_set_mode, + .suspend = pxa_timer_suspend, + .resume = pxa_timer_resume, +}; + +static struct irqaction pxa_ost0_irq = { + .name = "ost0", + .flags = IRQF_TIMER | IRQF_IRQPOLL, + .handler = pxa_ost0_interrupt, + .dev_id = &ckevt_pxa_osmr0, +}; + +static void pxa_timer_common_init(int irq, unsigned long clock_tick_rate) +{ + timer_writel(0, OIER); + timer_writel(OSSR_M0 | OSSR_M1 | OSSR_M2 | OSSR_M3, OSSR); + + sched_clock_register(pxa_read_sched_clock, 32, clock_tick_rate); + + ckevt_pxa_osmr0.cpumask = cpumask_of(0); + + setup_irq(irq, &pxa_ost0_irq); + + clocksource_mmio_init(timer_base + OSCR, "oscr0", clock_tick_rate, 200, + 32, clocksource_mmio_readl_up); + clockevents_config_and_register(&ckevt_pxa_osmr0, clock_tick_rate, + MIN_OSCR_DELTA * 2, 0x7fffffff); +} + +static void __init pxa_timer_dt_init(struct device_node *np) +{ + struct clk *clk; + int irq; + + /* timer registers are shared with watchdog timer */ + timer_base = of_iomap(np, 0); + if (!timer_base) + panic("%s: unable to map resource\n", np->name); + + clk = of_clk_get(np, 0); + if (IS_ERR(clk)) { + pr_crit("%s: unable to get clk\n", np->name); + return; + } + clk_prepare_enable(clk); + + /* we are only interested in OS-timer0 irq */ + irq = irq_of_parse_and_map(np, 0); + if (irq <= 0) { + pr_crit("%s: unable to parse OS-timer0 irq\n", np->name); + return; + } + + pxa_timer_common_init(irq, clk_get_rate(clk)); +} +CLOCKSOURCE_OF_DECLARE(pxa_timer, "marvell,pxa-timer", pxa_timer_dt_init); + +/* + * Legacy timer init for non device-tree boards. + */ +void __init pxa_timer_nodt_init(int irq, void __iomem *base, + unsigned long clock_tick_rate) +{ + struct clk *clk; + + timer_base = base; + clk = clk_get(NULL, "OSTIMER0"); + if (clk && !IS_ERR(clk)) + clk_prepare_enable(clk); + else + pr_crit("%s: unable to get clk\n", __func__); + + pxa_timer_common_init(irq, clock_tick_rate); +} diff --git a/drivers/clocksource/timer-marco.c b/drivers/clocksource/timer-marco.c index dbd30398222a..330e93064692 100644 --- a/drivers/clocksource/timer-marco.c +++ b/drivers/clocksource/timer-marco.c @@ -260,6 +260,9 @@ static void __init sirfsoc_marco_timer_init(struct device_node *np) clk = of_clk_get(np, 0); BUG_ON(IS_ERR(clk)); + + BUG_ON(clk_prepare_enable(clk)); + rate = clk_get_rate(clk); BUG_ON(rate < MARCO_CLOCK_FREQ); diff --git a/drivers/clocksource/timer-prima2.c b/drivers/clocksource/timer-prima2.c index a722aac7ac02..ce18d570e1cd 100644 --- a/drivers/clocksource/timer-prima2.c +++ b/drivers/clocksource/timer-prima2.c @@ -200,6 +200,9 @@ static void __init sirfsoc_prima2_timer_init(struct device_node *np) clk = of_clk_get(np, 0); BUG_ON(IS_ERR(clk)); + + BUG_ON(clk_prepare_enable(clk)); + rate = clk_get_rate(clk); BUG_ON(rate < PRIMA2_CLOCK_FREQ); diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c index ccdd4c7e748b..15d06fcf0b50 100644 --- a/drivers/connector/cn_proc.c +++ b/drivers/connector/cn_proc.c @@ -69,7 +69,6 @@ void proc_fork_connector(struct task_struct *task) struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); - struct timespec ts; struct task_struct *parent; if (atomic_read(&proc_event_num_listeners) < 1) @@ -79,8 +78,7 @@ void proc_fork_connector(struct task_struct *task) ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); - ktime_get_ts(&ts); /* get high res monotonic timestamp */ - ev->timestamp_ns = timespec_to_ns(&ts); + ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_FORK; rcu_read_lock(); parent = rcu_dereference(task->real_parent); @@ -102,7 +100,6 @@ void proc_exec_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; - struct timespec ts; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) @@ -112,8 +109,7 @@ void proc_exec_connector(struct task_struct *task) ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); - ktime_get_ts(&ts); /* get high res monotonic timestamp */ - ev->timestamp_ns = timespec_to_ns(&ts); + ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_EXEC; ev->event_data.exec.process_pid = task->pid; ev->event_data.exec.process_tgid = task->tgid; @@ -130,7 +126,6 @@ void proc_id_connector(struct task_struct *task, int which_id) struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); - struct timespec ts; const struct cred *cred; if (atomic_read(&proc_event_num_listeners) < 1) @@ -156,8 +151,7 @@ void proc_id_connector(struct task_struct *task, int which_id) } rcu_read_unlock(); get_seq(&msg->seq, &ev->cpu); - ktime_get_ts(&ts); /* get high res monotonic timestamp */ - ev->timestamp_ns = timespec_to_ns(&ts); + ev->timestamp_ns = ktime_get_ns(); memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ @@ -170,7 +164,6 @@ void proc_sid_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; - struct timespec ts; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) @@ -180,8 +173,7 @@ void proc_sid_connector(struct task_struct *task) ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); - ktime_get_ts(&ts); /* get high res monotonic timestamp */ - ev->timestamp_ns = timespec_to_ns(&ts); + ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_SID; ev->event_data.sid.process_pid = task->pid; ev->event_data.sid.process_tgid = task->tgid; @@ -197,7 +189,6 @@ void proc_ptrace_connector(struct task_struct *task, int ptrace_id) { struct cn_msg *msg; struct proc_event *ev; - struct timespec ts; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) @@ -207,8 +198,7 @@ void proc_ptrace_connector(struct task_struct *task, int ptrace_id) ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); - ktime_get_ts(&ts); /* get high res monotonic timestamp */ - ev->timestamp_ns = timespec_to_ns(&ts); + ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_PTRACE; ev->event_data.ptrace.process_pid = task->pid; ev->event_data.ptrace.process_tgid = task->tgid; @@ -232,7 +222,6 @@ void proc_comm_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; - struct timespec ts; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) @@ -242,8 +231,7 @@ void proc_comm_connector(struct task_struct *task) ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); - ktime_get_ts(&ts); /* get high res monotonic timestamp */ - ev->timestamp_ns = timespec_to_ns(&ts); + ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_COMM; ev->event_data.comm.process_pid = task->pid; ev->event_data.comm.process_tgid = task->tgid; @@ -261,7 +249,6 @@ void proc_coredump_connector(struct task_struct *task) struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); - struct timespec ts; if (atomic_read(&proc_event_num_listeners) < 1) return; @@ -270,8 +257,7 @@ void proc_coredump_connector(struct task_struct *task) ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); - ktime_get_ts(&ts); /* get high res monotonic timestamp */ - ev->timestamp_ns = timespec_to_ns(&ts); + ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_COREDUMP; ev->event_data.coredump.process_pid = task->pid; ev->event_data.coredump.process_tgid = task->tgid; @@ -288,7 +274,6 @@ void proc_exit_connector(struct task_struct *task) struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); - struct timespec ts; if (atomic_read(&proc_event_num_listeners) < 1) return; @@ -297,8 +282,7 @@ void proc_exit_connector(struct task_struct *task) ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); - ktime_get_ts(&ts); /* get high res monotonic timestamp */ - ev->timestamp_ns = timespec_to_ns(&ts); + ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_EXIT; ev->event_data.exit.process_pid = task->pid; ev->event_data.exit.process_tgid = task->tgid; @@ -325,7 +309,6 @@ static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack) struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); - struct timespec ts; if (atomic_read(&proc_event_num_listeners) < 1) return; @@ -334,8 +317,7 @@ static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack) ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); msg->seq = rcvd_seq; - ktime_get_ts(&ts); /* get high res monotonic timestamp */ - ev->timestamp_ns = timespec_to_ns(&ts); + ev->timestamp_ns = ktime_get_ns(); ev->cpu = -1; ev->what = PROC_EVENT_NONE; ev->event_data.ack.err = err; diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 878f09005fad..d3c0465ba456 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -72,6 +72,7 @@ config EDAC_MCE_INJ config EDAC_MM_EDAC tristate "Main Memory EDAC (Error Detection And Correction) reporting" + select RAS help Some systems are able to detect and correct errors in main memory. EDAC can report statistics on memory error diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index 2c694b5297cc..9f134823fa75 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -33,9 +33,6 @@ #include <asm/edac.h> #include "edac_core.h" #include "edac_module.h" - -#define CREATE_TRACE_POINTS -#define TRACE_INCLUDE_PATH ../../include/ras #include <ras/ras_event.h> /* lock to memory controller's control array */ diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index d7d5c8af92b9..5d997a33907e 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -1214,9 +1214,9 @@ static int ioctl_get_cycle_timer2(struct client *client, union ioctl_arg *arg) cycle_time = card->driver->read_csr(card, CSR_CYCLE_TIME); switch (a->clk_id) { - case CLOCK_REALTIME: getnstimeofday(&ts); break; - case CLOCK_MONOTONIC: do_posix_clock_monotonic_gettime(&ts); break; - case CLOCK_MONOTONIC_RAW: getrawmonotonic(&ts); break; + case CLOCK_REALTIME: getnstimeofday(&ts); break; + case CLOCK_MONOTONIC: ktime_get_ts(&ts); break; + case CLOCK_MONOTONIC_RAW: getrawmonotonic(&ts); break; default: ret = -EINVAL; } diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig index d420ae2d3413..f712d47f30d8 100644 --- a/drivers/firmware/efi/Kconfig +++ b/drivers/firmware/efi/Kconfig @@ -54,6 +54,12 @@ config EFI_PARAMS_FROM_FDT the EFI runtime support gets system table address, memory map address, and other parameters from the device tree. +config EFI_RUNTIME_WRAPPERS + bool + +config EFI_ARMSTUB + bool + endmenu config UEFI_CPER diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile index 9553496b0f43..d8be608a9f3b 100644 --- a/drivers/firmware/efi/Makefile +++ b/drivers/firmware/efi/Makefile @@ -1,8 +1,10 @@ # # Makefile for linux kernel # -obj-$(CONFIG_EFI) += efi.o vars.o +obj-$(CONFIG_EFI) += efi.o vars.o reboot.o obj-$(CONFIG_EFI_VARS) += efivars.o obj-$(CONFIG_EFI_VARS_PSTORE) += efi-pstore.o obj-$(CONFIG_UEFI_CPER) += cper.o obj-$(CONFIG_EFI_RUNTIME_MAP) += runtime-map.o +obj-$(CONFIG_EFI_RUNTIME_WRAPPERS) += runtime-wrappers.o +obj-$(CONFIG_EFI_STUB) += libstub/ diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c index 65f2f3fdde24..5b53d6183b6b 100644 --- a/drivers/firmware/efi/cper.c +++ b/drivers/firmware/efi/cper.c @@ -34,6 +34,9 @@ #include <linux/aer.h> #define INDENT_SP " " + +static char rcd_decode_str[CPER_REC_LEN]; + /* * CPER record ID need to be unique even after reboot, because record * ID is used as index for ERST storage, while CPER records from @@ -50,18 +53,19 @@ u64 cper_next_record_id(void) } EXPORT_SYMBOL_GPL(cper_next_record_id); -static const char *cper_severity_strs[] = { +static const char * const severity_strs[] = { "recoverable", "fatal", "corrected", "info", }; -static const char *cper_severity_str(unsigned int severity) +const char *cper_severity_str(unsigned int severity) { - return severity < ARRAY_SIZE(cper_severity_strs) ? - cper_severity_strs[severity] : "unknown"; + return severity < ARRAY_SIZE(severity_strs) ? + severity_strs[severity] : "unknown"; } +EXPORT_SYMBOL_GPL(cper_severity_str); /* * cper_print_bits - print strings for set bits @@ -100,32 +104,32 @@ void cper_print_bits(const char *pfx, unsigned int bits, printk("%s\n", buf); } -static const char * const cper_proc_type_strs[] = { +static const char * const proc_type_strs[] = { "IA32/X64", "IA64", }; -static const char * const cper_proc_isa_strs[] = { +static const char * const proc_isa_strs[] = { "IA32", "IA64", "X64", }; -static const char * const cper_proc_error_type_strs[] = { +static const char * const proc_error_type_strs[] = { "cache error", "TLB error", "bus error", "micro-architectural error", }; -static const char * const cper_proc_op_strs[] = { +static const char * const proc_op_strs[] = { "unknown or generic", "data read", "data write", "instruction execution", }; -static const char * const cper_proc_flag_strs[] = { +static const char * const proc_flag_strs[] = { "restartable", "precise IP", "overflow", @@ -137,26 +141,26 @@ static void cper_print_proc_generic(const char *pfx, { if (proc->validation_bits & CPER_PROC_VALID_TYPE) printk("%s""processor_type: %d, %s\n", pfx, proc->proc_type, - proc->proc_type < ARRAY_SIZE(cper_proc_type_strs) ? - cper_proc_type_strs[proc->proc_type] : "unknown"); + proc->proc_type < ARRAY_SIZE(proc_type_strs) ? + proc_type_strs[proc->proc_type] : "unknown"); if (proc->validation_bits & CPER_PROC_VALID_ISA) printk("%s""processor_isa: %d, %s\n", pfx, proc->proc_isa, - proc->proc_isa < ARRAY_SIZE(cper_proc_isa_strs) ? - cper_proc_isa_strs[proc->proc_isa] : "unknown"); + proc->proc_isa < ARRAY_SIZE(proc_isa_strs) ? + proc_isa_strs[proc->proc_isa] : "unknown"); if (proc->validation_bits & CPER_PROC_VALID_ERROR_TYPE) { printk("%s""error_type: 0x%02x\n", pfx, proc->proc_error_type); cper_print_bits(pfx, proc->proc_error_type, - cper_proc_error_type_strs, - ARRAY_SIZE(cper_proc_error_type_strs)); + proc_error_type_strs, + ARRAY_SIZE(proc_error_type_strs)); } if (proc->validation_bits & CPER_PROC_VALID_OPERATION) printk("%s""operation: %d, %s\n", pfx, proc->operation, - proc->operation < ARRAY_SIZE(cper_proc_op_strs) ? - cper_proc_op_strs[proc->operation] : "unknown"); + proc->operation < ARRAY_SIZE(proc_op_strs) ? + proc_op_strs[proc->operation] : "unknown"); if (proc->validation_bits & CPER_PROC_VALID_FLAGS) { printk("%s""flags: 0x%02x\n", pfx, proc->flags); - cper_print_bits(pfx, proc->flags, cper_proc_flag_strs, - ARRAY_SIZE(cper_proc_flag_strs)); + cper_print_bits(pfx, proc->flags, proc_flag_strs, + ARRAY_SIZE(proc_flag_strs)); } if (proc->validation_bits & CPER_PROC_VALID_LEVEL) printk("%s""level: %d\n", pfx, proc->level); @@ -177,7 +181,7 @@ static void cper_print_proc_generic(const char *pfx, printk("%s""IP: 0x%016llx\n", pfx, proc->ip); } -static const char *cper_mem_err_type_strs[] = { +static const char * const mem_err_type_strs[] = { "unknown", "no error", "single-bit ECC", @@ -196,58 +200,136 @@ static const char *cper_mem_err_type_strs[] = { "physical memory map-out event", }; -static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem) +const char *cper_mem_err_type_str(unsigned int etype) { - if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS) - printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status); - if (mem->validation_bits & CPER_MEM_VALID_PA) - printk("%s""physical_address: 0x%016llx\n", - pfx, mem->physical_addr); - if (mem->validation_bits & CPER_MEM_VALID_PA_MASK) - printk("%s""physical_address_mask: 0x%016llx\n", - pfx, mem->physical_addr_mask); + return etype < ARRAY_SIZE(mem_err_type_strs) ? + mem_err_type_strs[etype] : "unknown"; +} +EXPORT_SYMBOL_GPL(cper_mem_err_type_str); + +static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg) +{ + u32 len, n; + + if (!msg) + return 0; + + n = 0; + len = CPER_REC_LEN - 1; if (mem->validation_bits & CPER_MEM_VALID_NODE) - pr_debug("node: %d\n", mem->node); + n += scnprintf(msg + n, len - n, "node: %d ", mem->node); if (mem->validation_bits & CPER_MEM_VALID_CARD) - pr_debug("card: %d\n", mem->card); + n += scnprintf(msg + n, len - n, "card: %d ", mem->card); if (mem->validation_bits & CPER_MEM_VALID_MODULE) - pr_debug("module: %d\n", mem->module); + n += scnprintf(msg + n, len - n, "module: %d ", mem->module); if (mem->validation_bits & CPER_MEM_VALID_RANK_NUMBER) - pr_debug("rank: %d\n", mem->rank); + n += scnprintf(msg + n, len - n, "rank: %d ", mem->rank); if (mem->validation_bits & CPER_MEM_VALID_BANK) - pr_debug("bank: %d\n", mem->bank); + n += scnprintf(msg + n, len - n, "bank: %d ", mem->bank); if (mem->validation_bits & CPER_MEM_VALID_DEVICE) - pr_debug("device: %d\n", mem->device); + n += scnprintf(msg + n, len - n, "device: %d ", mem->device); if (mem->validation_bits & CPER_MEM_VALID_ROW) - pr_debug("row: %d\n", mem->row); + n += scnprintf(msg + n, len - n, "row: %d ", mem->row); if (mem->validation_bits & CPER_MEM_VALID_COLUMN) - pr_debug("column: %d\n", mem->column); + n += scnprintf(msg + n, len - n, "column: %d ", mem->column); if (mem->validation_bits & CPER_MEM_VALID_BIT_POSITION) - pr_debug("bit_position: %d\n", mem->bit_pos); + n += scnprintf(msg + n, len - n, "bit_position: %d ", + mem->bit_pos); if (mem->validation_bits & CPER_MEM_VALID_REQUESTOR_ID) - pr_debug("requestor_id: 0x%016llx\n", mem->requestor_id); + n += scnprintf(msg + n, len - n, "requestor_id: 0x%016llx ", + mem->requestor_id); if (mem->validation_bits & CPER_MEM_VALID_RESPONDER_ID) - pr_debug("responder_id: 0x%016llx\n", mem->responder_id); + n += scnprintf(msg + n, len - n, "responder_id: 0x%016llx ", + mem->responder_id); if (mem->validation_bits & CPER_MEM_VALID_TARGET_ID) - pr_debug("target_id: 0x%016llx\n", mem->target_id); + scnprintf(msg + n, len - n, "target_id: 0x%016llx ", + mem->target_id); + + msg[n] = '\0'; + return n; +} + +static int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg) +{ + u32 len, n; + const char *bank = NULL, *device = NULL; + + if (!msg || !(mem->validation_bits & CPER_MEM_VALID_MODULE_HANDLE)) + return 0; + + n = 0; + len = CPER_REC_LEN - 1; + dmi_memdev_name(mem->mem_dev_handle, &bank, &device); + if (bank && device) + n = snprintf(msg, len, "DIMM location: %s %s ", bank, device); + else + n = snprintf(msg, len, + "DIMM location: not present. DMI handle: 0x%.4x ", + mem->mem_dev_handle); + + msg[n] = '\0'; + return n; +} + +void cper_mem_err_pack(const struct cper_sec_mem_err *mem, + struct cper_mem_err_compact *cmem) +{ + cmem->validation_bits = mem->validation_bits; + cmem->node = mem->node; + cmem->card = mem->card; + cmem->module = mem->module; + cmem->bank = mem->bank; + cmem->device = mem->device; + cmem->row = mem->row; + cmem->column = mem->column; + cmem->bit_pos = mem->bit_pos; + cmem->requestor_id = mem->requestor_id; + cmem->responder_id = mem->responder_id; + cmem->target_id = mem->target_id; + cmem->rank = mem->rank; + cmem->mem_array_handle = mem->mem_array_handle; + cmem->mem_dev_handle = mem->mem_dev_handle; +} + +const char *cper_mem_err_unpack(struct trace_seq *p, + struct cper_mem_err_compact *cmem) +{ + const char *ret = p->buffer + p->len; + + if (cper_mem_err_location(cmem, rcd_decode_str)) + trace_seq_printf(p, "%s", rcd_decode_str); + if (cper_dimm_err_location(cmem, rcd_decode_str)) + trace_seq_printf(p, "%s", rcd_decode_str); + trace_seq_putc(p, '\0'); + + return ret; +} + +static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem) +{ + struct cper_mem_err_compact cmem; + + if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS) + printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status); + if (mem->validation_bits & CPER_MEM_VALID_PA) + printk("%s""physical_address: 0x%016llx\n", + pfx, mem->physical_addr); + if (mem->validation_bits & CPER_MEM_VALID_PA_MASK) + printk("%s""physical_address_mask: 0x%016llx\n", + pfx, mem->physical_addr_mask); + cper_mem_err_pack(mem, &cmem); + if (cper_mem_err_location(&cmem, rcd_decode_str)) + printk("%s%s\n", pfx, rcd_decode_str); if (mem->validation_bits & CPER_MEM_VALID_ERROR_TYPE) { u8 etype = mem->error_type; printk("%s""error_type: %d, %s\n", pfx, etype, - etype < ARRAY_SIZE(cper_mem_err_type_strs) ? - cper_mem_err_type_strs[etype] : "unknown"); - } - if (mem->validation_bits & CPER_MEM_VALID_MODULE_HANDLE) { - const char *bank = NULL, *device = NULL; - dmi_memdev_name(mem->mem_dev_handle, &bank, &device); - if (bank != NULL && device != NULL) - printk("%s""DIMM location: %s %s", pfx, bank, device); - else - printk("%s""DIMM DMI handle: 0x%.4x", - pfx, mem->mem_dev_handle); + cper_mem_err_type_str(etype)); } + if (cper_dimm_err_location(&cmem, rcd_decode_str)) + printk("%s%s\n", pfx, rcd_decode_str); } -static const char *cper_pcie_port_type_strs[] = { +static const char * const pcie_port_type_strs[] = { "PCIe end point", "legacy PCI end point", "unknown", @@ -266,8 +348,8 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie, { if (pcie->validation_bits & CPER_PCIE_VALID_PORT_TYPE) printk("%s""port_type: %d, %s\n", pfx, pcie->port_type, - pcie->port_type < ARRAY_SIZE(cper_pcie_port_type_strs) ? - cper_pcie_port_type_strs[pcie->port_type] : "unknown"); + pcie->port_type < ARRAY_SIZE(pcie_port_type_strs) ? + pcie_port_type_strs[pcie->port_type] : "unknown"); if (pcie->validation_bits & CPER_PCIE_VALID_VERSION) printk("%s""version: %d.%d\n", pfx, pcie->version.major, pcie->version.minor); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index dc79346689e6..64ecbb501c50 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -23,6 +23,7 @@ #include <linux/of.h> #include <linux/of_fdt.h> #include <linux/io.h> +#include <linux/platform_device.h> struct efi __read_mostly efi = { .mps = EFI_INVALID_TABLE_ADDR, @@ -104,16 +105,19 @@ static struct attribute *efi_subsys_attrs[] = { static umode_t efi_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n) { - umode_t mode = attr->mode; - - if (attr == &efi_attr_fw_vendor.attr) - return (efi.fw_vendor == EFI_INVALID_TABLE_ADDR) ? 0 : mode; - else if (attr == &efi_attr_runtime.attr) - return (efi.runtime == EFI_INVALID_TABLE_ADDR) ? 0 : mode; - else if (attr == &efi_attr_config_table.attr) - return (efi.config_table == EFI_INVALID_TABLE_ADDR) ? 0 : mode; + if (attr == &efi_attr_fw_vendor.attr) { + if (efi_enabled(EFI_PARAVIRT) || + efi.fw_vendor == EFI_INVALID_TABLE_ADDR) + return 0; + } else if (attr == &efi_attr_runtime.attr) { + if (efi.runtime == EFI_INVALID_TABLE_ADDR) + return 0; + } else if (attr == &efi_attr_config_table.attr) { + if (efi.config_table == EFI_INVALID_TABLE_ADDR) + return 0; + } - return mode; + return attr->mode; } static struct attribute_group efi_subsys_attr_group = { @@ -298,7 +302,7 @@ int __init efi_config_init(efi_config_table_type_t *arch_tables) if (table64 >> 32) { pr_cont("\n"); pr_err("Table located above 4GB, disabling EFI.\n"); - early_iounmap(config_tables, + early_memunmap(config_tables, efi.systab->nr_tables * sz); return -EINVAL; } @@ -314,13 +318,27 @@ int __init efi_config_init(efi_config_table_type_t *arch_tables) tablep += sz; } pr_cont("\n"); - early_iounmap(config_tables, efi.systab->nr_tables * sz); + early_memunmap(config_tables, efi.systab->nr_tables * sz); set_bit(EFI_CONFIG_TABLES, &efi.flags); return 0; } +#ifdef CONFIG_EFI_VARS_MODULE +static int __init efi_load_efivars(void) +{ + struct platform_device *pdev; + + if (!efi_enabled(EFI_RUNTIME_SERVICES)) + return 0; + + pdev = platform_device_register_simple("efivars", 0, NULL, 0); + return IS_ERR(pdev) ? PTR_ERR(pdev) : 0; +} +device_initcall(efi_load_efivars); +#endif + #ifdef CONFIG_EFI_PARAMS_FROM_FDT #define UEFI_PARAM(name, prop, field) \ diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c index 463c56545ae8..f256ecd8a176 100644 --- a/drivers/firmware/efi/efivars.c +++ b/drivers/firmware/efi/efivars.c @@ -78,6 +78,7 @@ MODULE_AUTHOR("Matt Domsch <Matt_Domsch@Dell.com>"); MODULE_DESCRIPTION("sysfs interface to EFI Variables"); MODULE_LICENSE("GPL"); MODULE_VERSION(EFIVARS_VERSION); +MODULE_ALIAS("platform:efivars"); LIST_HEAD(efivar_sysfs_list); EXPORT_SYMBOL_GPL(efivar_sysfs_list); diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile new file mode 100644 index 000000000000..b14bc2b9fb4d --- /dev/null +++ b/drivers/firmware/efi/libstub/Makefile @@ -0,0 +1,26 @@ +# +# The stub may be linked into the kernel proper or into a separate boot binary, +# but in either case, it executes before the kernel does (with MMU disabled) so +# things like ftrace and stack-protector are likely to cause trouble if left +# enabled, even if doing so doesn't break the build. +# +cflags-$(CONFIG_X86_32) := -march=i386 +cflags-$(CONFIG_X86_64) := -mcmodel=small +cflags-$(CONFIG_X86) += -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 \ + -fPIC -fno-strict-aliasing -mno-red-zone \ + -mno-mmx -mno-sse -DDISABLE_BRANCH_PROFILING + +cflags-$(CONFIG_ARM64) := $(subst -pg,,$(KBUILD_CFLAGS)) +cflags-$(CONFIG_ARM) := $(subst -pg,,$(KBUILD_CFLAGS)) \ + -fno-builtin -fpic -mno-single-pic-base + +KBUILD_CFLAGS := $(cflags-y) \ + $(call cc-option,-ffreestanding) \ + $(call cc-option,-fno-stack-protector) + +GCOV_PROFILE := n + +lib-y := efi-stub-helper.o +lib-$(CONFIG_EFI_ARMSTUB) += arm-stub.o fdt.o + +CFLAGS_fdt.o += -I$(srctree)/scripts/dtc/libfdt/ diff --git a/drivers/firmware/efi/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c index 41114ce03b01..480339b6b110 100644 --- a/drivers/firmware/efi/arm-stub.c +++ b/drivers/firmware/efi/libstub/arm-stub.c @@ -12,6 +12,11 @@ * */ +#include <linux/efi.h> +#include <asm/efi.h> + +#include "efistub.h" + static int __init efi_secureboot_enabled(efi_system_table_t *sys_table_arg) { static efi_guid_t const var_guid __initconst = EFI_GLOBAL_VARIABLE_GUID; @@ -36,8 +41,8 @@ static int __init efi_secureboot_enabled(efi_system_table_t *sys_table_arg) } } -static efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, - void *__image, void **__fh) +efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, + void *__image, void **__fh) { efi_file_io_interface_t *io; efi_loaded_image_t *image = __image; @@ -60,14 +65,15 @@ static efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, *__fh = fh; return status; } -static efi_status_t efi_file_close(void *handle) + +efi_status_t efi_file_close(void *handle) { efi_file_handle_t *fh = handle; return fh->close(handle); } -static efi_status_t +efi_status_t efi_file_read(void *handle, unsigned long *size, void *addr) { efi_file_handle_t *fh = handle; @@ -76,7 +82,7 @@ efi_file_read(void *handle, unsigned long *size, void *addr) } -static efi_status_t +efi_status_t efi_file_size(efi_system_table_t *sys_table_arg, void *__fh, efi_char16_t *filename_16, void **handle, u64 *file_sz) { @@ -129,7 +135,7 @@ grow: -static void efi_char16_printk(efi_system_table_t *sys_table_arg, +void efi_char16_printk(efi_system_table_t *sys_table_arg, efi_char16_t *str) { struct efi_simple_text_output_protocol *out; @@ -145,13 +151,13 @@ static void efi_char16_printk(efi_system_table_t *sys_table_arg, * must be reserved. On failure it is required to free all * all allocations it has made. */ -static 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 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 entry point for the arm/arm64 EFI stubs. This is the entrypoint * that is described in the PE/COFF header. Most of the code is the same diff --git a/drivers/firmware/efi/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index eb6d4be9e722..32d5cca30f49 100644 --- a/drivers/firmware/efi/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -9,18 +9,20 @@ * under the terms of the GNU General Public License version 2. * */ -#define EFI_READ_CHUNK_SIZE (1024 * 1024) -/* error code which can't be mistaken for valid address */ -#define EFI_ERROR (~0UL) +#include <linux/efi.h> +#include <asm/efi.h> + +#include "efistub.h" +#define EFI_READ_CHUNK_SIZE (1024 * 1024) struct file_info { efi_file_handle_t *handle; u64 size; }; -static void efi_printk(efi_system_table_t *sys_table_arg, char *str) +void efi_printk(efi_system_table_t *sys_table_arg, char *str) { char *s8; @@ -37,16 +39,12 @@ static void efi_printk(efi_system_table_t *sys_table_arg, char *str) } } -#define pr_efi(sys_table, msg) efi_printk(sys_table, "EFI stub: "msg) -#define pr_efi_err(sys_table, msg) efi_printk(sys_table, "EFI stub: ERROR: "msg) - - -static efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg, - efi_memory_desc_t **map, - unsigned long *map_size, - unsigned long *desc_size, - u32 *desc_ver, - unsigned long *key_ptr) +efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg, + efi_memory_desc_t **map, + unsigned long *map_size, + unsigned long *desc_size, + u32 *desc_ver, + unsigned long *key_ptr) { efi_memory_desc_t *m = NULL; efi_status_t status; @@ -88,7 +86,7 @@ fail: } -static unsigned long __init get_dram_base(efi_system_table_t *sys_table_arg) +unsigned long __init get_dram_base(efi_system_table_t *sys_table_arg) { efi_status_t status; unsigned long map_size; @@ -116,9 +114,9 @@ static unsigned long __init get_dram_base(efi_system_table_t *sys_table_arg) /* * Allocate at the highest possible address that is not above 'max'. */ -static efi_status_t efi_high_alloc(efi_system_table_t *sys_table_arg, - unsigned long size, unsigned long align, - unsigned long *addr, unsigned long max) +efi_status_t efi_high_alloc(efi_system_table_t *sys_table_arg, + unsigned long size, unsigned long align, + unsigned long *addr, unsigned long max) { unsigned long map_size, desc_size; efi_memory_desc_t *map; @@ -202,9 +200,9 @@ fail: /* * Allocate at the lowest possible address. */ -static efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg, - unsigned long size, unsigned long align, - unsigned long *addr) +efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg, + unsigned long size, unsigned long align, + unsigned long *addr) { unsigned long map_size, desc_size; efi_memory_desc_t *map; @@ -271,8 +269,8 @@ fail: return status; } -static void efi_free(efi_system_table_t *sys_table_arg, unsigned long size, - unsigned long addr) +void efi_free(efi_system_table_t *sys_table_arg, unsigned long size, + unsigned long addr) { unsigned long nr_pages; @@ -290,12 +288,12 @@ static void efi_free(efi_system_table_t *sys_table_arg, unsigned long size, * We only support loading a file from the same filesystem as * the kernel image. */ -static efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg, - efi_loaded_image_t *image, - char *cmd_line, char *option_string, - unsigned long max_addr, - unsigned long *load_addr, - unsigned long *load_size) +efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg, + efi_loaded_image_t *image, + char *cmd_line, char *option_string, + unsigned long max_addr, + unsigned long *load_addr, + unsigned long *load_size) { struct file_info *files; unsigned long file_addr; @@ -477,12 +475,12 @@ fail: * address is not available the lowest available address will * be used. */ -static efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg, - unsigned long *image_addr, - unsigned long image_size, - unsigned long alloc_size, - unsigned long preferred_addr, - unsigned long alignment) +efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg, + unsigned long *image_addr, + unsigned long image_size, + unsigned long alloc_size, + unsigned long preferred_addr, + unsigned long alignment) { unsigned long cur_image_addr; unsigned long new_addr = 0; @@ -589,9 +587,9 @@ static u8 *efi_utf16_to_utf8(u8 *dst, const u16 *src, int n) * Size of memory allocated return in *cmd_line_len. * Returns NULL on error. */ -static char *efi_convert_cmdline(efi_system_table_t *sys_table_arg, - efi_loaded_image_t *image, - int *cmd_line_len) +char *efi_convert_cmdline(efi_system_table_t *sys_table_arg, + efi_loaded_image_t *image, + int *cmd_line_len) { const u16 *s2; u8 *s1 = NULL; diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h new file mode 100644 index 000000000000..304ab295ca1a --- /dev/null +++ b/drivers/firmware/efi/libstub/efistub.h @@ -0,0 +1,42 @@ + +#ifndef _DRIVERS_FIRMWARE_EFI_EFISTUB_H +#define _DRIVERS_FIRMWARE_EFI_EFISTUB_H + +/* error code which can't be mistaken for valid address */ +#define EFI_ERROR (~0UL) + +void efi_char16_printk(efi_system_table_t *, efi_char16_t *); + +efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, void *__image, + void **__fh); + +efi_status_t efi_file_size(efi_system_table_t *sys_table_arg, void *__fh, + efi_char16_t *filename_16, void **handle, + u64 *file_sz); + +efi_status_t efi_file_read(void *handle, unsigned long *size, void *addr); + +efi_status_t efi_file_close(void *handle); + +unsigned long get_dram_base(efi_system_table_t *sys_table_arg); + +efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt, + unsigned long orig_fdt_size, + void *fdt, int new_fdt_size, char *cmdline_ptr, + u64 initrd_addr, u64 initrd_size, + efi_memory_desc_t *memory_map, + unsigned long map_size, unsigned long desc_size, + u32 desc_ver); + +efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table, + void *handle, + unsigned long *new_fdt_addr, + unsigned long max_addr, + u64 initrd_addr, u64 initrd_size, + char *cmdline_ptr, + unsigned long fdt_addr, + unsigned long fdt_size); + +void *get_fdt(efi_system_table_t *sys_table); + +#endif diff --git a/drivers/firmware/efi/fdt.c b/drivers/firmware/efi/libstub/fdt.c index 507a3df46a5d..a56bb3528755 100644 --- a/drivers/firmware/efi/fdt.c +++ b/drivers/firmware/efi/libstub/fdt.c @@ -10,13 +10,17 @@ * */ -static efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt, - unsigned long orig_fdt_size, - void *fdt, int new_fdt_size, char *cmdline_ptr, - u64 initrd_addr, u64 initrd_size, - efi_memory_desc_t *memory_map, - unsigned long map_size, unsigned long desc_size, - u32 desc_ver) +#include <linux/efi.h> +#include <linux/libfdt.h> +#include <asm/efi.h> + +efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt, + unsigned long orig_fdt_size, + void *fdt, int new_fdt_size, char *cmdline_ptr, + u64 initrd_addr, u64 initrd_size, + efi_memory_desc_t *memory_map, + unsigned long map_size, unsigned long desc_size, + u32 desc_ver) { int node, prev; int status; @@ -255,7 +259,7 @@ fail: return EFI_LOAD_ERROR; } -static void *get_fdt(efi_system_table_t *sys_table) +void *get_fdt(efi_system_table_t *sys_table) { efi_guid_t fdt_guid = DEVICE_TREE_GUID; efi_config_table_t *tables; diff --git a/drivers/firmware/efi/reboot.c b/drivers/firmware/efi/reboot.c new file mode 100644 index 000000000000..9c59d1c795d1 --- /dev/null +++ b/drivers/firmware/efi/reboot.c @@ -0,0 +1,56 @@ +/* + * Copyright (C) 2014 Intel Corporation; author Matt Fleming + * Copyright (c) 2014 Red Hat, Inc., Mark Salter <msalter@redhat.com> + */ +#include <linux/efi.h> +#include <linux/reboot.h> + +int efi_reboot_quirk_mode = -1; + +void efi_reboot(enum reboot_mode reboot_mode, const char *__unused) +{ + int efi_mode; + + if (!efi_enabled(EFI_RUNTIME_SERVICES)) + return; + + switch (reboot_mode) { + case REBOOT_WARM: + case REBOOT_SOFT: + efi_mode = EFI_RESET_WARM; + break; + default: + efi_mode = EFI_RESET_COLD; + break; + } + + /* + * If a quirk forced an EFI reset mode, always use that. + */ + if (efi_reboot_quirk_mode != -1) + efi_mode = efi_reboot_quirk_mode; + + efi.reset_system(efi_mode, EFI_SUCCESS, 0, NULL); +} + +bool __weak efi_poweroff_required(void) +{ + return false; +} + +static void efi_power_off(void) +{ + efi.reset_system(EFI_RESET_SHUTDOWN, EFI_SUCCESS, 0, NULL); +} + +static int __init efi_shutdown_init(void) +{ + if (!efi_enabled(EFI_RUNTIME_SERVICES)) + return -ENODEV; + + if (efi_poweroff_required()) + pm_power_off = efi_power_off; + + return 0; +} +late_initcall(efi_shutdown_init); diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c new file mode 100644 index 000000000000..10daa4bbb258 --- /dev/null +++ b/drivers/firmware/efi/runtime-wrappers.c @@ -0,0 +1,161 @@ +/* + * runtime-wrappers.c - Runtime Services function call wrappers + * + * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org> + * + * Split off from arch/x86/platform/efi/efi.c + * + * Copyright (C) 1999 VA Linux Systems + * Copyright (C) 1999 Walt Drummond <drummond@valinux.com> + * Copyright (C) 1999-2002 Hewlett-Packard Co. + * Copyright (C) 2005-2008 Intel Co. + * Copyright (C) 2013 SuSE Labs + * + * This file is released under the GPLv2. + */ + +#include <linux/efi.h> +#include <linux/spinlock.h> /* spinlock_t */ +#include <asm/efi.h> + +/* + * As per commit ef68c8f87ed1 ("x86: Serialize EFI time accesses on rtc_lock"), + * the EFI specification requires that callers of the time related runtime + * functions serialize with other CMOS accesses in the kernel, as the EFI time + * functions may choose to also use the legacy CMOS RTC. + */ +__weak DEFINE_SPINLOCK(rtc_lock); + +static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) +{ + unsigned long flags; + efi_status_t status; + + spin_lock_irqsave(&rtc_lock, flags); + status = efi_call_virt(get_time, tm, tc); + spin_unlock_irqrestore(&rtc_lock, flags); + return status; +} + +static efi_status_t virt_efi_set_time(efi_time_t *tm) +{ + unsigned long flags; + efi_status_t status; + + spin_lock_irqsave(&rtc_lock, flags); + status = efi_call_virt(set_time, tm); + spin_unlock_irqrestore(&rtc_lock, flags); + return status; +} + +static efi_status_t virt_efi_get_wakeup_time(efi_bool_t *enabled, + efi_bool_t *pending, + efi_time_t *tm) +{ + unsigned long flags; + efi_status_t status; + + spin_lock_irqsave(&rtc_lock, flags); + status = efi_call_virt(get_wakeup_time, enabled, pending, tm); + spin_unlock_irqrestore(&rtc_lock, flags); + return status; +} + +static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) +{ + unsigned long flags; + efi_status_t status; + + spin_lock_irqsave(&rtc_lock, flags); + status = efi_call_virt(set_wakeup_time, enabled, tm); + spin_unlock_irqrestore(&rtc_lock, flags); + return status; +} + +static efi_status_t virt_efi_get_variable(efi_char16_t *name, + efi_guid_t *vendor, + u32 *attr, + unsigned long *data_size, + void *data) +{ + return efi_call_virt(get_variable, name, vendor, attr, data_size, data); +} + +static efi_status_t virt_efi_get_next_variable(unsigned long *name_size, + efi_char16_t *name, + efi_guid_t *vendor) +{ + return efi_call_virt(get_next_variable, name_size, name, vendor); +} + +static efi_status_t virt_efi_set_variable(efi_char16_t *name, + efi_guid_t *vendor, + u32 attr, + unsigned long data_size, + void *data) +{ + return efi_call_virt(set_variable, name, vendor, attr, data_size, data); +} + +static efi_status_t virt_efi_query_variable_info(u32 attr, + u64 *storage_space, + u64 *remaining_space, + u64 *max_variable_size) +{ + if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) + return EFI_UNSUPPORTED; + + return efi_call_virt(query_variable_info, attr, storage_space, + remaining_space, max_variable_size); +} + +static efi_status_t virt_efi_get_next_high_mono_count(u32 *count) +{ + return efi_call_virt(get_next_high_mono_count, count); +} + +static void virt_efi_reset_system(int reset_type, + efi_status_t status, + unsigned long data_size, + efi_char16_t *data) +{ + __efi_call_virt(reset_system, reset_type, status, data_size, data); +} + +static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules, + unsigned long count, + unsigned long sg_list) +{ + if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) + return EFI_UNSUPPORTED; + + return efi_call_virt(update_capsule, capsules, count, sg_list); +} + +static efi_status_t virt_efi_query_capsule_caps(efi_capsule_header_t **capsules, + unsigned long count, + u64 *max_size, + int *reset_type) +{ + if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) + return EFI_UNSUPPORTED; + + return efi_call_virt(query_capsule_caps, capsules, count, max_size, + reset_type); +} + +void efi_native_runtime_setup(void) +{ + efi.get_time = virt_efi_get_time; + efi.set_time = virt_efi_set_time; + efi.get_wakeup_time = virt_efi_get_wakeup_time; + efi.set_wakeup_time = virt_efi_set_wakeup_time; + efi.get_variable = virt_efi_get_variable; + efi.get_next_variable = virt_efi_get_next_variable; + efi.set_variable = virt_efi_set_variable; + efi.get_next_high_mono_count = virt_efi_get_next_high_mono_count; + efi.reset_system = virt_efi_reset_system; + efi.query_variable_info = virt_efi_query_variable_info; + efi.update_capsule = virt_efi_update_capsule; + efi.query_capsule_caps = virt_efi_query_capsule_caps; +} diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index 0de123afdb34..08ba1209228e 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -542,8 +542,8 @@ int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, int crtc, const struct drm_crtc *refcrtc, const struct drm_display_mode *mode) { - ktime_t stime, etime, mono_time_offset; struct timeval tv_etime; + ktime_t stime, etime; int vbl_status; int vpos, hpos, i; int framedur_ns, linedur_ns, pixeldur_ns, delta_ns, duration_ns; @@ -588,13 +588,6 @@ int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, int crtc, vbl_status = dev->driver->get_scanout_position(dev, crtc, flags, &vpos, &hpos, &stime, &etime); - /* - * Get correction for CLOCK_MONOTONIC -> CLOCK_REALTIME if - * CLOCK_REALTIME is requested. - */ - if (!drm_timestamp_monotonic) - mono_time_offset = ktime_get_monotonic_offset(); - /* Return as no-op if scanout query unsupported or failed. */ if (!(vbl_status & DRM_SCANOUTPOS_VALID)) { DRM_DEBUG("crtc %d : scanoutpos query failed [%d].\n", @@ -633,7 +626,7 @@ int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, int crtc, delta_ns = vpos * linedur_ns + hpos * pixeldur_ns; if (!drm_timestamp_monotonic) - etime = ktime_sub(etime, mono_time_offset); + etime = ktime_mono_to_real(etime); /* save this only for debugging purposes */ tv_etime = ktime_to_timeval(etime); @@ -664,10 +657,7 @@ static struct timeval get_drm_timestamp(void) { ktime_t now; - now = ktime_get(); - if (!drm_timestamp_monotonic) - now = ktime_sub(now, ktime_get_monotonic_offset()); - + now = drm_timestamp_monotonic ? ktime_get() : ktime_get_real(); return ktime_to_timeval(now); } diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index d604f4f27a14..53c100eca961 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -975,7 +975,7 @@ struct intel_ilk_power_mgmt { unsigned long last_time1; unsigned long chipset_power; u64 last_count2; - struct timespec last_time2; + u64 last_time2; unsigned long gfx_power; u8 corr; diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index dcd8d7b42552..215185050ff1 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1149,16 +1149,16 @@ static bool can_wait_boost(struct drm_i915_file_private *file_priv) static int __wait_seqno(struct intel_engine_cs *ring, u32 seqno, unsigned reset_counter, bool interruptible, - struct timespec *timeout, + s64 *timeout, struct drm_i915_file_private *file_priv) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; const bool irq_test_in_progress = ACCESS_ONCE(dev_priv->gpu_error.test_irq_rings) & intel_ring_flag(ring); - struct timespec before, now; DEFINE_WAIT(wait); unsigned long timeout_expire; + s64 before, now; int ret; WARN(!intel_irqs_enabled(dev_priv), "IRQs disabled"); @@ -1166,7 +1166,7 @@ static int __wait_seqno(struct intel_engine_cs *ring, u32 seqno, if (i915_seqno_passed(ring->get_seqno(ring, true), seqno)) return 0; - timeout_expire = timeout ? jiffies + timespec_to_jiffies_timeout(timeout) : 0; + timeout_expire = timeout ? jiffies + nsecs_to_jiffies((u64)*timeout) : 0; if (INTEL_INFO(dev)->gen >= 6 && ring->id == RCS && can_wait_boost(file_priv)) { gen6_rps_boost(dev_priv); @@ -1181,7 +1181,7 @@ static int __wait_seqno(struct intel_engine_cs *ring, u32 seqno, /* Record current time in case interrupted by signal, or wedged */ trace_i915_gem_request_wait_begin(ring, seqno); - getrawmonotonic(&before); + before = ktime_get_raw_ns(); for (;;) { struct timer_list timer; @@ -1230,7 +1230,7 @@ static int __wait_seqno(struct intel_engine_cs *ring, u32 seqno, destroy_timer_on_stack(&timer); } } - getrawmonotonic(&now); + now = ktime_get_raw_ns(); trace_i915_gem_request_wait_end(ring, seqno); if (!irq_test_in_progress) @@ -1239,10 +1239,9 @@ static int __wait_seqno(struct intel_engine_cs *ring, u32 seqno, finish_wait(&ring->irq_queue, &wait); if (timeout) { - struct timespec sleep_time = timespec_sub(now, before); - *timeout = timespec_sub(*timeout, sleep_time); - if (!timespec_valid(timeout)) /* i.e. negative time remains */ - set_normalized_timespec(timeout, 0, 0); + s64 tres = *timeout - (now - before); + + *timeout = tres < 0 ? 0 : tres; } return ret; @@ -2757,16 +2756,10 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file) struct drm_i915_gem_wait *args = data; struct drm_i915_gem_object *obj; struct intel_engine_cs *ring = NULL; - struct timespec timeout_stack, *timeout = NULL; unsigned reset_counter; u32 seqno = 0; int ret = 0; - if (args->timeout_ns >= 0) { - timeout_stack = ns_to_timespec(args->timeout_ns); - timeout = &timeout_stack; - } - ret = i915_mutex_lock_interruptible(dev); if (ret) return ret; @@ -2791,9 +2784,9 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file) goto out; /* Do this after OLR check to make sure we make forward progress polling - * on this IOCTL with a 0 timeout (like busy ioctl) + * on this IOCTL with a timeout <=0 (like busy ioctl) */ - if (!args->timeout_ns) { + if (args->timeout_ns <= 0) { ret = -ETIME; goto out; } @@ -2802,10 +2795,8 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file) reset_counter = atomic_read(&dev_priv->gpu_error.reset_counter); mutex_unlock(&dev->struct_mutex); - ret = __wait_seqno(ring, seqno, reset_counter, true, timeout, file->driver_priv); - if (timeout) - args->timeout_ns = timespec_to_ns(timeout); - return ret; + return __wait_seqno(ring, seqno, reset_counter, true, &args->timeout_ns, + file->driver_priv); out: drm_gem_object_unreference(&obj->base); diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 1ddd4df41261..852b9933d85f 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -3036,7 +3036,7 @@ static void ironlake_enable_drps(struct drm_device *dev) I915_READ(0x112e0); dev_priv->ips.last_time1 = jiffies_to_msecs(jiffies); dev_priv->ips.last_count2 = I915_READ(0x112f4); - getrawmonotonic(&dev_priv->ips.last_time2); + dev_priv->ips.last_time2 = ktime_get_raw_ns(); spin_unlock_irq(&mchdev_lock); } @@ -4597,18 +4597,16 @@ static u16 pvid_to_extvid(struct drm_i915_private *dev_priv, u8 pxvid) static void __i915_update_gfx_val(struct drm_i915_private *dev_priv) { - struct timespec now, diff1; - u64 diff; - unsigned long diffms; + u64 now, diff, diffms; u32 count; assert_spin_locked(&mchdev_lock); - getrawmonotonic(&now); - diff1 = timespec_sub(now, dev_priv->ips.last_time2); + now = ktime_get_raw_ns(); + diffms = now - dev_priv->ips.last_time2; + do_div(diffms, NSEC_PER_MSEC); /* Don't divide by 0 */ - diffms = diff1.tv_sec * 1000 + diff1.tv_nsec / 1000000; if (!diffms) return; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index c1811750cc8d..99f731757c4b 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -169,8 +169,8 @@ struct vmw_surface { struct vmw_marker_queue { struct list_head head; - struct timespec lag; - struct timespec lag_time; + u64 lag; + u64 lag_time; spinlock_t lock; }; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_marker.c b/drivers/gpu/drm/vmwgfx/vmwgfx_marker.c index 8a8725c2716c..efd1ffd68185 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_marker.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_marker.c @@ -31,14 +31,14 @@ struct vmw_marker { struct list_head head; uint32_t seqno; - struct timespec submitted; + u64 submitted; }; void vmw_marker_queue_init(struct vmw_marker_queue *queue) { INIT_LIST_HEAD(&queue->head); - queue->lag = ns_to_timespec(0); - getrawmonotonic(&queue->lag_time); + queue->lag = 0; + queue->lag_time = ktime_get_raw_ns(); spin_lock_init(&queue->lock); } @@ -62,7 +62,7 @@ int vmw_marker_push(struct vmw_marker_queue *queue, return -ENOMEM; marker->seqno = seqno; - getrawmonotonic(&marker->submitted); + marker->submitted = ktime_get_raw_ns(); spin_lock(&queue->lock); list_add_tail(&marker->head, &queue->head); spin_unlock(&queue->lock); @@ -74,14 +74,14 @@ int vmw_marker_pull(struct vmw_marker_queue *queue, uint32_t signaled_seqno) { struct vmw_marker *marker, *next; - struct timespec now; bool updated = false; + u64 now; spin_lock(&queue->lock); - getrawmonotonic(&now); + now = ktime_get_raw_ns(); if (list_empty(&queue->head)) { - queue->lag = ns_to_timespec(0); + queue->lag = 0; queue->lag_time = now; updated = true; goto out_unlock; @@ -91,7 +91,7 @@ int vmw_marker_pull(struct vmw_marker_queue *queue, if (signaled_seqno - marker->seqno > (1 << 30)) continue; - queue->lag = timespec_sub(now, marker->submitted); + queue->lag = now - marker->submitted; queue->lag_time = now; updated = true; list_del(&marker->head); @@ -104,27 +104,13 @@ out_unlock: return (updated) ? 0 : -EBUSY; } -static struct timespec vmw_timespec_add(struct timespec t1, - struct timespec t2) +static u64 vmw_fifo_lag(struct vmw_marker_queue *queue) { - t1.tv_sec += t2.tv_sec; - t1.tv_nsec += t2.tv_nsec; - if (t1.tv_nsec >= 1000000000L) { - t1.tv_sec += 1; - t1.tv_nsec -= 1000000000L; - } - - return t1; -} - -static struct timespec vmw_fifo_lag(struct vmw_marker_queue *queue) -{ - struct timespec now; + u64 now; spin_lock(&queue->lock); - getrawmonotonic(&now); - queue->lag = vmw_timespec_add(queue->lag, - timespec_sub(now, queue->lag_time)); + now = ktime_get_raw_ns(); + queue->lag += now - queue->lag_time; queue->lag_time = now; spin_unlock(&queue->lock); return queue->lag; @@ -134,11 +120,9 @@ static struct timespec vmw_fifo_lag(struct vmw_marker_queue *queue) static bool vmw_lag_lt(struct vmw_marker_queue *queue, uint32_t us) { - struct timespec lag, cond; + u64 cond = (u64) us * NSEC_PER_USEC; - cond = ns_to_timespec((s64) us * 1000); - lag = vmw_fifo_lag(queue); - return (timespec_compare(&lag, &cond) < 1); + return vmw_fifo_lag(queue) <= cond; } int vmw_wait_lag(struct vmw_private *dev_priv, diff --git a/drivers/hwmon/ibmaem.c b/drivers/hwmon/ibmaem.c index 632f1dc0fe1f..7a8a6fbf11ff 100644 --- a/drivers/hwmon/ibmaem.c +++ b/drivers/hwmon/ibmaem.c @@ -842,11 +842,10 @@ static ssize_t aem_show_power(struct device *dev, struct aem_data *data = dev_get_drvdata(dev); u64 before, after, delta, time; signed long leftover; - struct timespec b, a; mutex_lock(&data->lock); update_aem_energy_one(data, attr->index); - getnstimeofday(&b); + time = ktime_get_ns(); before = data->energy[attr->index]; leftover = schedule_timeout_interruptible( @@ -858,11 +857,10 @@ static ssize_t aem_show_power(struct device *dev, } update_aem_energy_one(data, attr->index); - getnstimeofday(&a); + time = ktime_get_ns() - time; after = data->energy[attr->index]; mutex_unlock(&data->lock); - time = timespec_to_ns(&a) - timespec_to_ns(&b); delta = (after - before) * UJ_PER_MJ; return sprintf(buf, "%llu\n", diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index fd325ec9f064..de055451d1af 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -108,9 +108,8 @@ static void evdev_queue_syn_dropped(struct evdev_client *client) struct input_event ev; ktime_t time; - time = ktime_get(); - if (client->clkid != CLOCK_MONOTONIC) - time = ktime_sub(time, ktime_get_monotonic_offset()); + time = (client->clkid == CLOCK_MONOTONIC) ? + ktime_get() : ktime_get_real(); ev.time = ktime_to_timeval(time); ev.type = EV_SYN; @@ -202,7 +201,7 @@ static void evdev_events(struct input_handle *handle, ktime_t time_mono, time_real; time_mono = ktime_get(); - time_real = ktime_sub(time_mono, ktime_get_monotonic_offset()); + time_real = ktime_mono_to_real(time_mono); rcu_read_lock(); diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index 113cc8ac1d6a..b8632bf9a7f3 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -34,6 +34,20 @@ config ARM_VIC_NR The maximum number of VICs available in the system, for power management. +config ATMEL_AIC_IRQ + bool + select GENERIC_IRQ_CHIP + select IRQ_DOMAIN + select MULTI_IRQ_HANDLER + select SPARSE_IRQ + +config ATMEL_AIC5_IRQ + bool + select GENERIC_IRQ_CHIP + select IRQ_DOMAIN + select MULTI_IRQ_HANDLER + select SPARSE_IRQ + config BRCMSTB_L2_IRQ bool depends on ARM @@ -57,6 +71,10 @@ config CLPS711X_IRQCHIP select SPARSE_IRQ default y +config OR1K_PIC + bool + select IRQ_DOMAIN + config ORION_IRQCHIP bool select IRQ_DOMAIN diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile index c57e642700d4..73052ba9ca62 100644 --- a/drivers/irqchip/Makefile +++ b/drivers/irqchip/Makefile @@ -11,6 +11,7 @@ obj-$(CONFIG_METAG) += irq-metag-ext.o obj-$(CONFIG_METAG_PERFCOUNTER_IRQS) += irq-metag.o obj-$(CONFIG_ARCH_MOXART) += irq-moxart.o obj-$(CONFIG_CLPS711X_IRQCHIP) += irq-clps711x.o +obj-$(CONFIG_OR1K_PIC) += irq-or1k-pic.o obj-$(CONFIG_ORION_IRQCHIP) += irq-orion.o obj-$(CONFIG_ARCH_SUNXI) += irq-sun4i.o obj-$(CONFIG_ARCH_SUNXI) += irq-sunxi-nmi.o @@ -19,6 +20,8 @@ obj-$(CONFIG_ARM_GIC) += irq-gic.o irq-gic-common.o obj-$(CONFIG_ARM_GIC_V3) += irq-gic-v3.o irq-gic-common.o obj-$(CONFIG_ARM_NVIC) += irq-nvic.o obj-$(CONFIG_ARM_VIC) += irq-vic.o +obj-$(CONFIG_ATMEL_AIC_IRQ) += irq-atmel-aic-common.o irq-atmel-aic.o +obj-$(CONFIG_ATMEL_AIC5_IRQ) += irq-atmel-aic-common.o irq-atmel-aic5.o obj-$(CONFIG_IMGPDC_IRQ) += irq-imgpdc.o obj-$(CONFIG_SIRF_IRQ) += irq-sirfsoc.o obj-$(CONFIG_RENESAS_INTC_IRQPIN) += irq-renesas-intc-irqpin.o diff --git a/drivers/irqchip/irq-atmel-aic-common.c b/drivers/irqchip/irq-atmel-aic-common.c new file mode 100644 index 000000000000..6ae3cdee0681 --- /dev/null +++ b/drivers/irqchip/irq-atmel-aic-common.c @@ -0,0 +1,254 @@ +/* + * Atmel AT91 common AIC (Advanced Interrupt Controller) code shared by + * irq-atmel-aic and irq-atmel-aic5 drivers + * + * Copyright (C) 2004 SAN People + * Copyright (C) 2004 ATMEL + * Copyright (C) Rick Bronson + * Copyright (C) 2014 Free Electrons + * + * Author: Boris BREZILLON <boris.brezillon@free-electrons.com> + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +#include <linux/errno.h> +#include <linux/io.h> +#include <linux/irq.h> +#include <linux/irqdomain.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/slab.h> + +#include "irq-atmel-aic-common.h" + +#define AT91_AIC_PRIOR GENMASK(2, 0) +#define AT91_AIC_IRQ_MIN_PRIORITY 0 +#define AT91_AIC_IRQ_MAX_PRIORITY 7 + +#define AT91_AIC_SRCTYPE GENMASK(7, 6) +#define AT91_AIC_SRCTYPE_LOW (0 << 5) +#define AT91_AIC_SRCTYPE_FALLING (1 << 5) +#define AT91_AIC_SRCTYPE_HIGH (2 << 5) +#define AT91_AIC_SRCTYPE_RISING (3 << 5) + +struct aic_chip_data { + u32 ext_irqs; +}; + +static void aic_common_shutdown(struct irq_data *d) +{ + struct irq_chip_type *ct = irq_data_get_chip_type(d); + + ct->chip.irq_mask(d); +} + +int aic_common_set_type(struct irq_data *d, unsigned type, unsigned *val) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + struct aic_chip_data *aic = gc->private; + unsigned aic_type; + + switch (type) { + case IRQ_TYPE_LEVEL_HIGH: + aic_type = AT91_AIC_SRCTYPE_HIGH; + break; + case IRQ_TYPE_EDGE_RISING: + aic_type = AT91_AIC_SRCTYPE_RISING; + break; + case IRQ_TYPE_LEVEL_LOW: + if (!(d->mask & aic->ext_irqs)) + return -EINVAL; + + aic_type = AT91_AIC_SRCTYPE_LOW; + break; + case IRQ_TYPE_EDGE_FALLING: + if (!(d->mask & aic->ext_irqs)) + return -EINVAL; + + aic_type = AT91_AIC_SRCTYPE_FALLING; + break; + default: + return -EINVAL; + } + + *val &= AT91_AIC_SRCTYPE; + *val |= aic_type; + + return 0; +} + +int aic_common_set_priority(int priority, unsigned *val) +{ + if (priority < AT91_AIC_IRQ_MIN_PRIORITY || + priority > AT91_AIC_IRQ_MAX_PRIORITY) + return -EINVAL; + + *val &= AT91_AIC_PRIOR; + *val |= priority; + + return 0; +} + +int aic_common_irq_domain_xlate(struct irq_domain *d, + struct device_node *ctrlr, + const u32 *intspec, + unsigned int intsize, + irq_hw_number_t *out_hwirq, + unsigned int *out_type) +{ + if (WARN_ON(intsize < 3)) + return -EINVAL; + + if (WARN_ON((intspec[2] < AT91_AIC_IRQ_MIN_PRIORITY) || + (intspec[2] > AT91_AIC_IRQ_MAX_PRIORITY))) + return -EINVAL; + + *out_hwirq = intspec[0]; + *out_type = intspec[1] & IRQ_TYPE_SENSE_MASK; + + return 0; +} + +static void __init aic_common_ext_irq_of_init(struct irq_domain *domain) +{ + struct device_node *node = domain->of_node; + struct irq_chip_generic *gc; + struct aic_chip_data *aic; + struct property *prop; + const __be32 *p; + u32 hwirq; + + gc = irq_get_domain_generic_chip(domain, 0); + + aic = gc->private; + aic->ext_irqs |= 1; + + of_property_for_each_u32(node, "atmel,external-irqs", prop, p, hwirq) { + gc = irq_get_domain_generic_chip(domain, hwirq); + if (!gc) { + pr_warn("AIC: external irq %d >= %d skip it\n", + hwirq, domain->revmap_size); + continue; + } + + aic = gc->private; + aic->ext_irqs |= (1 << (hwirq % 32)); + } +} + +#define AT91_RTC_IDR 0x24 +#define AT91_RTC_IMR 0x28 +#define AT91_RTC_IRQ_MASK 0x1f + +void __init aic_common_rtc_irq_fixup(struct device_node *root) +{ + struct device_node *np; + void __iomem *regs; + + np = of_find_compatible_node(root, NULL, "atmel,at91rm9200-rtc"); + if (!np) + np = of_find_compatible_node(root, NULL, + "atmel,at91sam9x5-rtc"); + + if (!np) + return; + + regs = of_iomap(np, 0); + of_node_put(np); + + if (!regs) + return; + + writel(AT91_RTC_IRQ_MASK, regs + AT91_RTC_IDR); + + iounmap(regs); +} + +void __init aic_common_irq_fixup(const struct of_device_id *matches) +{ + struct device_node *root = of_find_node_by_path("/"); + const struct of_device_id *match; + + if (!root) + return; + + match = of_match_node(matches, root); + of_node_put(root); + + if (match) { + void (*fixup)(struct device_node *) = match->data; + fixup(root); + } + + of_node_put(root); +} + +struct irq_domain *__init aic_common_of_init(struct device_node *node, + const struct irq_domain_ops *ops, + const char *name, int nirqs) +{ + struct irq_chip_generic *gc; + struct irq_domain *domain; + struct aic_chip_data *aic; + void __iomem *reg_base; + int nchips; + int ret; + int i; + + nchips = DIV_ROUND_UP(nirqs, 32); + + reg_base = of_iomap(node, 0); + if (!reg_base) + return ERR_PTR(-ENOMEM); + + aic = kcalloc(nchips, sizeof(*aic), GFP_KERNEL); + if (!aic) { + ret = -ENOMEM; + goto err_iounmap; + } + + domain = irq_domain_add_linear(node, nchips * 32, ops, aic); + if (!domain) { + ret = -ENOMEM; + goto err_free_aic; + } + + ret = irq_alloc_domain_generic_chips(domain, 32, 1, name, + handle_level_irq, 0, 0, + IRQCHIP_SKIP_SET_WAKE); + if (ret) + goto err_domain_remove; + + for (i = 0; i < nchips; i++) { + gc = irq_get_domain_generic_chip(domain, i * 32); + + gc->reg_base = reg_base; + + gc->unused = 0; + gc->wake_enabled = ~0; + gc->chip_types[0].type = IRQ_TYPE_SENSE_MASK; + gc->chip_types[0].handler = handle_fasteoi_irq; + gc->chip_types[0].chip.irq_eoi = irq_gc_eoi; + gc->chip_types[0].chip.irq_set_wake = irq_gc_set_wake; + gc->chip_types[0].chip.irq_shutdown = aic_common_shutdown; + gc->private = &aic[i]; + } + + aic_common_ext_irq_of_init(domain); + + return domain; + +err_domain_remove: + irq_domain_remove(domain); + +err_free_aic: + kfree(aic); + +err_iounmap: + iounmap(reg_base); + + return ERR_PTR(ret); +} diff --git a/drivers/irqchip/irq-atmel-aic-common.h b/drivers/irqchip/irq-atmel-aic-common.h new file mode 100644 index 000000000000..90aa00e918d6 --- /dev/null +++ b/drivers/irqchip/irq-atmel-aic-common.h @@ -0,0 +1,39 @@ +/* + * Atmel AT91 common AIC (Advanced Interrupt Controller) header file + * + * Copyright (C) 2004 SAN People + * Copyright (C) 2004 ATMEL + * Copyright (C) Rick Bronson + * Copyright (C) 2014 Free Electrons + * + * Author: Boris BREZILLON <boris.brezillon@free-electrons.com> + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +#ifndef __IRQ_ATMEL_AIC_COMMON_H +#define __IRQ_ATMEL_AIC_COMMON_H + + +int aic_common_set_type(struct irq_data *d, unsigned type, unsigned *val); + +int aic_common_set_priority(int priority, unsigned *val); + +int aic_common_irq_domain_xlate(struct irq_domain *d, + struct device_node *ctrlr, + const u32 *intspec, + unsigned int intsize, + irq_hw_number_t *out_hwirq, + unsigned int *out_type); + +struct irq_domain *__init aic_common_of_init(struct device_node *node, + const struct irq_domain_ops *ops, + const char *name, int nirqs); + +void __init aic_common_rtc_irq_fixup(struct device_node *root); + +void __init aic_common_irq_fixup(const struct of_device_id *matches); + +#endif /* __IRQ_ATMEL_AIC_COMMON_H */ diff --git a/drivers/irqchip/irq-atmel-aic.c b/drivers/irqchip/irq-atmel-aic.c new file mode 100644 index 000000000000..a82869e9fb26 --- /dev/null +++ b/drivers/irqchip/irq-atmel-aic.c @@ -0,0 +1,262 @@ +/* + * Atmel AT91 AIC (Advanced Interrupt Controller) driver + * + * Copyright (C) 2004 SAN People + * Copyright (C) 2004 ATMEL + * Copyright (C) Rick Bronson + * Copyright (C) 2014 Free Electrons + * + * Author: Boris BREZILLON <boris.brezillon@free-electrons.com> + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/mm.h> +#include <linux/bitmap.h> +#include <linux/types.h> +#include <linux/irq.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/irqdomain.h> +#include <linux/err.h> +#include <linux/slab.h> +#include <linux/io.h> + +#include <asm/exception.h> +#include <asm/mach/irq.h> + +#include "irq-atmel-aic-common.h" +#include "irqchip.h" + +/* Number of irq lines managed by AIC */ +#define NR_AIC_IRQS 32 + +#define AT91_AIC_SMR(n) ((n) * 4) + +#define AT91_AIC_SVR(n) (0x80 + ((n) * 4)) +#define AT91_AIC_IVR 0x100 +#define AT91_AIC_FVR 0x104 +#define AT91_AIC_ISR 0x108 + +#define AT91_AIC_IPR 0x10c +#define AT91_AIC_IMR 0x110 +#define AT91_AIC_CISR 0x114 + +#define AT91_AIC_IECR 0x120 +#define AT91_AIC_IDCR 0x124 +#define AT91_AIC_ICCR 0x128 +#define AT91_AIC_ISCR 0x12c +#define AT91_AIC_EOICR 0x130 +#define AT91_AIC_SPU 0x134 +#define AT91_AIC_DCR 0x138 + +static struct irq_domain *aic_domain; + +static asmlinkage void __exception_irq_entry +aic_handle(struct pt_regs *regs) +{ + struct irq_domain_chip_generic *dgc = aic_domain->gc; + struct irq_chip_generic *gc = dgc->gc[0]; + u32 irqnr; + u32 irqstat; + + irqnr = irq_reg_readl(gc->reg_base + AT91_AIC_IVR); + irqstat = irq_reg_readl(gc->reg_base + AT91_AIC_ISR); + + irqnr = irq_find_mapping(aic_domain, irqnr); + + if (!irqstat) + irq_reg_writel(0, gc->reg_base + AT91_AIC_EOICR); + else + handle_IRQ(irqnr, regs); +} + +static int aic_retrigger(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + + /* Enable interrupt on AIC5 */ + irq_gc_lock(gc); + irq_reg_writel(d->mask, gc->reg_base + AT91_AIC_ISCR); + irq_gc_unlock(gc); + + return 0; +} + +static int aic_set_type(struct irq_data *d, unsigned type) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + unsigned int smr; + int ret; + + smr = irq_reg_readl(gc->reg_base + AT91_AIC_SMR(d->hwirq)); + ret = aic_common_set_type(d, type, &smr); + if (ret) + return ret; + + irq_reg_writel(smr, gc->reg_base + AT91_AIC_SMR(d->hwirq)); + + return 0; +} + +#ifdef CONFIG_PM +static void aic_suspend(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + + irq_gc_lock(gc); + irq_reg_writel(gc->mask_cache, gc->reg_base + AT91_AIC_IDCR); + irq_reg_writel(gc->wake_active, gc->reg_base + AT91_AIC_IECR); + irq_gc_unlock(gc); +} + +static void aic_resume(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + + irq_gc_lock(gc); + irq_reg_writel(gc->wake_active, gc->reg_base + AT91_AIC_IDCR); + irq_reg_writel(gc->mask_cache, gc->reg_base + AT91_AIC_IECR); + irq_gc_unlock(gc); +} + +static void aic_pm_shutdown(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + + irq_gc_lock(gc); + irq_reg_writel(0xffffffff, gc->reg_base + AT91_AIC_IDCR); + irq_reg_writel(0xffffffff, gc->reg_base + AT91_AIC_ICCR); + irq_gc_unlock(gc); +} +#else +#define aic_suspend NULL +#define aic_resume NULL +#define aic_pm_shutdown NULL +#endif /* CONFIG_PM */ + +static void __init aic_hw_init(struct irq_domain *domain) +{ + struct irq_chip_generic *gc = irq_get_domain_generic_chip(domain, 0); + int i; + + /* + * Perform 8 End Of Interrupt Command to make sure AIC + * will not Lock out nIRQ + */ + for (i = 0; i < 8; i++) + irq_reg_writel(0, gc->reg_base + AT91_AIC_EOICR); + + /* + * Spurious Interrupt ID in Spurious Vector Register. + * When there is no current interrupt, the IRQ Vector Register + * reads the value stored in AIC_SPU + */ + irq_reg_writel(0xffffffff, gc->reg_base + AT91_AIC_SPU); + + /* No debugging in AIC: Debug (Protect) Control Register */ + irq_reg_writel(0, gc->reg_base + AT91_AIC_DCR); + + /* Disable and clear all interrupts initially */ + irq_reg_writel(0xffffffff, gc->reg_base + AT91_AIC_IDCR); + irq_reg_writel(0xffffffff, gc->reg_base + AT91_AIC_ICCR); + + for (i = 0; i < 32; i++) + irq_reg_writel(i, gc->reg_base + AT91_AIC_SVR(i)); +} + +static int aic_irq_domain_xlate(struct irq_domain *d, + struct device_node *ctrlr, + const u32 *intspec, unsigned int intsize, + irq_hw_number_t *out_hwirq, + unsigned int *out_type) +{ + struct irq_domain_chip_generic *dgc = d->gc; + struct irq_chip_generic *gc; + unsigned smr; + int idx; + int ret; + + if (!dgc) + return -EINVAL; + + ret = aic_common_irq_domain_xlate(d, ctrlr, intspec, intsize, + out_hwirq, out_type); + if (ret) + return ret; + + idx = intspec[0] / dgc->irqs_per_chip; + if (idx >= dgc->num_chips) + return -EINVAL; + + gc = dgc->gc[idx]; + + irq_gc_lock(gc); + smr = irq_reg_readl(gc->reg_base + AT91_AIC_SMR(*out_hwirq)); + ret = aic_common_set_priority(intspec[2], &smr); + if (!ret) + irq_reg_writel(smr, gc->reg_base + AT91_AIC_SMR(*out_hwirq)); + irq_gc_unlock(gc); + + return ret; +} + +static const struct irq_domain_ops aic_irq_ops = { + .map = irq_map_generic_chip, + .xlate = aic_irq_domain_xlate, +}; + +static void __init at91sam9_aic_irq_fixup(struct device_node *root) +{ + aic_common_rtc_irq_fixup(root); +} + +static const struct of_device_id __initdata aic_irq_fixups[] = { + { .compatible = "atmel,at91sam9g45", .data = at91sam9_aic_irq_fixup }, + { .compatible = "atmel,at91sam9n12", .data = at91sam9_aic_irq_fixup }, + { .compatible = "atmel,at91sam9rl", .data = at91sam9_aic_irq_fixup }, + { .compatible = "atmel,at91sam9x5", .data = at91sam9_aic_irq_fixup }, + { /* sentinel */ }, +}; + +static int __init aic_of_init(struct device_node *node, + struct device_node *parent) +{ + struct irq_chip_generic *gc; + struct irq_domain *domain; + + if (aic_domain) + return -EEXIST; + + domain = aic_common_of_init(node, &aic_irq_ops, "atmel-aic", + NR_AIC_IRQS); + if (IS_ERR(domain)) + return PTR_ERR(domain); + + aic_common_irq_fixup(aic_irq_fixups); + + aic_domain = domain; + gc = irq_get_domain_generic_chip(domain, 0); + + gc->chip_types[0].regs.eoi = AT91_AIC_EOICR; + gc->chip_types[0].regs.enable = AT91_AIC_IECR; + gc->chip_types[0].regs.disable = AT91_AIC_IDCR; + gc->chip_types[0].chip.irq_mask = irq_gc_mask_disable_reg; + gc->chip_types[0].chip.irq_unmask = irq_gc_unmask_enable_reg; + gc->chip_types[0].chip.irq_retrigger = aic_retrigger; + gc->chip_types[0].chip.irq_set_type = aic_set_type; + gc->chip_types[0].chip.irq_suspend = aic_suspend; + gc->chip_types[0].chip.irq_resume = aic_resume; + gc->chip_types[0].chip.irq_pm_shutdown = aic_pm_shutdown; + + aic_hw_init(domain); + set_handle_irq(aic_handle); + + return 0; +} +IRQCHIP_DECLARE(at91rm9200_aic, "atmel,at91rm9200-aic", aic_of_init); diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c new file mode 100644 index 000000000000..edb227081524 --- /dev/null +++ b/drivers/irqchip/irq-atmel-aic5.c @@ -0,0 +1,353 @@ +/* + * Atmel AT91 AIC5 (Advanced Interrupt Controller) driver + * + * Copyright (C) 2004 SAN People + * Copyright (C) 2004 ATMEL + * Copyright (C) Rick Bronson + * Copyright (C) 2014 Free Electrons + * + * Author: Boris BREZILLON <boris.brezillon@free-electrons.com> + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/mm.h> +#include <linux/bitmap.h> +#include <linux/types.h> +#include <linux/irq.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/irqdomain.h> +#include <linux/err.h> +#include <linux/slab.h> +#include <linux/io.h> + +#include <asm/exception.h> +#include <asm/mach/irq.h> + +#include "irq-atmel-aic-common.h" +#include "irqchip.h" + +/* Number of irq lines managed by AIC */ +#define NR_AIC5_IRQS 128 + +#define AT91_AIC5_SSR 0x0 +#define AT91_AIC5_INTSEL_MSK (0x7f << 0) + +#define AT91_AIC5_SMR 0x4 + +#define AT91_AIC5_SVR 0x8 +#define AT91_AIC5_IVR 0x10 +#define AT91_AIC5_FVR 0x14 +#define AT91_AIC5_ISR 0x18 + +#define AT91_AIC5_IPR0 0x20 +#define AT91_AIC5_IPR1 0x24 +#define AT91_AIC5_IPR2 0x28 +#define AT91_AIC5_IPR3 0x2c +#define AT91_AIC5_IMR 0x30 +#define AT91_AIC5_CISR 0x34 + +#define AT91_AIC5_IECR 0x40 +#define AT91_AIC5_IDCR 0x44 +#define AT91_AIC5_ICCR 0x48 +#define AT91_AIC5_ISCR 0x4c +#define AT91_AIC5_EOICR 0x38 +#define AT91_AIC5_SPU 0x3c +#define AT91_AIC5_DCR 0x6c + +#define AT91_AIC5_FFER 0x50 +#define AT91_AIC5_FFDR 0x54 +#define AT91_AIC5_FFSR 0x58 + +static struct irq_domain *aic5_domain; + +static asmlinkage void __exception_irq_entry +aic5_handle(struct pt_regs *regs) +{ + struct irq_domain_chip_generic *dgc = aic5_domain->gc; + struct irq_chip_generic *gc = dgc->gc[0]; + u32 irqnr; + u32 irqstat; + + irqnr = irq_reg_readl(gc->reg_base + AT91_AIC5_IVR); + irqstat = irq_reg_readl(gc->reg_base + AT91_AIC5_ISR); + + irqnr = irq_find_mapping(aic5_domain, irqnr); + + if (!irqstat) + irq_reg_writel(0, gc->reg_base + AT91_AIC5_EOICR); + else + handle_IRQ(irqnr, regs); +} + +static void aic5_mask(struct irq_data *d) +{ + struct irq_domain *domain = d->domain; + struct irq_domain_chip_generic *dgc = domain->gc; + struct irq_chip_generic *gc = dgc->gc[0]; + + /* Disable interrupt on AIC5 */ + irq_gc_lock(gc); + irq_reg_writel(d->hwirq, gc->reg_base + AT91_AIC5_SSR); + irq_reg_writel(1, gc->reg_base + AT91_AIC5_IDCR); + gc->mask_cache &= ~d->mask; + irq_gc_unlock(gc); +} + +static void aic5_unmask(struct irq_data *d) +{ + struct irq_domain *domain = d->domain; + struct irq_domain_chip_generic *dgc = domain->gc; + struct irq_chip_generic *gc = dgc->gc[0]; + + /* Enable interrupt on AIC5 */ + irq_gc_lock(gc); + irq_reg_writel(d->hwirq, gc->reg_base + AT91_AIC5_SSR); + irq_reg_writel(1, gc->reg_base + AT91_AIC5_IECR); + gc->mask_cache |= d->mask; + irq_gc_unlock(gc); +} + +static int aic5_retrigger(struct irq_data *d) +{ + struct irq_domain *domain = d->domain; + struct irq_domain_chip_generic *dgc = domain->gc; + struct irq_chip_generic *gc = dgc->gc[0]; + + /* Enable interrupt on AIC5 */ + irq_gc_lock(gc); + irq_reg_writel(d->hwirq, gc->reg_base + AT91_AIC5_SSR); + irq_reg_writel(1, gc->reg_base + AT91_AIC5_ISCR); + irq_gc_unlock(gc); + + return 0; +} + +static int aic5_set_type(struct irq_data *d, unsigned type) +{ + struct irq_domain *domain = d->domain; + struct irq_domain_chip_generic *dgc = domain->gc; + struct irq_chip_generic *gc = dgc->gc[0]; + unsigned int smr; + int ret; + + irq_gc_lock(gc); + irq_reg_writel(d->hwirq, gc->reg_base + AT91_AIC5_SSR); + smr = irq_reg_readl(gc->reg_base + AT91_AIC5_SMR); + ret = aic_common_set_type(d, type, &smr); + if (!ret) + irq_reg_writel(smr, gc->reg_base + AT91_AIC5_SMR); + irq_gc_unlock(gc); + + return ret; +} + +#ifdef CONFIG_PM +static void aic5_suspend(struct irq_data *d) +{ + struct irq_domain *domain = d->domain; + struct irq_domain_chip_generic *dgc = domain->gc; + struct irq_chip_generic *bgc = dgc->gc[0]; + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + int i; + u32 mask; + + irq_gc_lock(bgc); + for (i = 0; i < dgc->irqs_per_chip; i++) { + mask = 1 << i; + if ((mask & gc->mask_cache) == (mask & gc->wake_active)) + continue; + + irq_reg_writel(i + gc->irq_base, + bgc->reg_base + AT91_AIC5_SSR); + if (mask & gc->wake_active) + irq_reg_writel(1, bgc->reg_base + AT91_AIC5_IECR); + else + irq_reg_writel(1, bgc->reg_base + AT91_AIC5_IDCR); + } + irq_gc_unlock(bgc); +} + +static void aic5_resume(struct irq_data *d) +{ + struct irq_domain *domain = d->domain; + struct irq_domain_chip_generic *dgc = domain->gc; + struct irq_chip_generic *bgc = dgc->gc[0]; + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + int i; + u32 mask; + + irq_gc_lock(bgc); + for (i = 0; i < dgc->irqs_per_chip; i++) { + mask = 1 << i; + if ((mask & gc->mask_cache) == (mask & gc->wake_active)) + continue; + + irq_reg_writel(i + gc->irq_base, + bgc->reg_base + AT91_AIC5_SSR); + if (mask & gc->mask_cache) + irq_reg_writel(1, bgc->reg_base + AT91_AIC5_IECR); + else + irq_reg_writel(1, bgc->reg_base + AT91_AIC5_IDCR); + } + irq_gc_unlock(bgc); +} + +static void aic5_pm_shutdown(struct irq_data *d) +{ + struct irq_domain *domain = d->domain; + struct irq_domain_chip_generic *dgc = domain->gc; + struct irq_chip_generic *bgc = dgc->gc[0]; + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + int i; + + irq_gc_lock(bgc); + for (i = 0; i < dgc->irqs_per_chip; i++) { + irq_reg_writel(i + gc->irq_base, + bgc->reg_base + AT91_AIC5_SSR); + irq_reg_writel(1, bgc->reg_base + AT91_AIC5_IDCR); + irq_reg_writel(1, bgc->reg_base + AT91_AIC5_ICCR); + } + irq_gc_unlock(bgc); +} +#else +#define aic5_suspend NULL +#define aic5_resume NULL +#define aic5_pm_shutdown NULL +#endif /* CONFIG_PM */ + +static void __init aic5_hw_init(struct irq_domain *domain) +{ + struct irq_chip_generic *gc = irq_get_domain_generic_chip(domain, 0); + int i; + + /* + * Perform 8 End Of Interrupt Command to make sure AIC + * will not Lock out nIRQ + */ + for (i = 0; i < 8; i++) + irq_reg_writel(0, gc->reg_base + AT91_AIC5_EOICR); + + /* + * Spurious Interrupt ID in Spurious Vector Register. + * When there is no current interrupt, the IRQ Vector Register + * reads the value stored in AIC_SPU + */ + irq_reg_writel(0xffffffff, gc->reg_base + AT91_AIC5_SPU); + + /* No debugging in AIC: Debug (Protect) Control Register */ + irq_reg_writel(0, gc->reg_base + AT91_AIC5_DCR); + + /* Disable and clear all interrupts initially */ + for (i = 0; i < domain->revmap_size; i++) { + irq_reg_writel(i, gc->reg_base + AT91_AIC5_SSR); + irq_reg_writel(i, gc->reg_base + AT91_AIC5_SVR); + irq_reg_writel(1, gc->reg_base + AT91_AIC5_IDCR); + irq_reg_writel(1, gc->reg_base + AT91_AIC5_ICCR); + } +} + +static int aic5_irq_domain_xlate(struct irq_domain *d, + struct device_node *ctrlr, + const u32 *intspec, unsigned int intsize, + irq_hw_number_t *out_hwirq, + unsigned int *out_type) +{ + struct irq_domain_chip_generic *dgc = d->gc; + struct irq_chip_generic *gc; + unsigned smr; + int ret; + + if (!dgc) + return -EINVAL; + + ret = aic_common_irq_domain_xlate(d, ctrlr, intspec, intsize, + out_hwirq, out_type); + if (ret) + return ret; + + gc = dgc->gc[0]; + + irq_gc_lock(gc); + irq_reg_writel(*out_hwirq, gc->reg_base + AT91_AIC5_SSR); + smr = irq_reg_readl(gc->reg_base + AT91_AIC5_SMR); + ret = aic_common_set_priority(intspec[2], &smr); + if (!ret) + irq_reg_writel(intspec[2] | smr, gc->reg_base + AT91_AIC5_SMR); + irq_gc_unlock(gc); + + return ret; +} + +static const struct irq_domain_ops aic5_irq_ops = { + .map = irq_map_generic_chip, + .xlate = aic5_irq_domain_xlate, +}; + +static void __init sama5d3_aic_irq_fixup(struct device_node *root) +{ + aic_common_rtc_irq_fixup(root); +} + +static const struct of_device_id __initdata aic5_irq_fixups[] = { + { .compatible = "atmel,sama5d3", .data = sama5d3_aic_irq_fixup }, + { /* sentinel */ }, +}; + +static int __init aic5_of_init(struct device_node *node, + struct device_node *parent, + int nirqs) +{ + struct irq_chip_generic *gc; + struct irq_domain *domain; + int nchips; + int i; + + if (nirqs > NR_AIC5_IRQS) + return -EINVAL; + + if (aic5_domain) + return -EEXIST; + + domain = aic_common_of_init(node, &aic5_irq_ops, "atmel-aic5", + nirqs); + if (IS_ERR(domain)) + return PTR_ERR(domain); + + aic_common_irq_fixup(aic5_irq_fixups); + + aic5_domain = domain; + nchips = aic5_domain->revmap_size / 32; + for (i = 0; i < nchips; i++) { + gc = irq_get_domain_generic_chip(domain, i * 32); + + gc->chip_types[0].regs.eoi = AT91_AIC5_EOICR; + gc->chip_types[0].chip.irq_mask = aic5_mask; + gc->chip_types[0].chip.irq_unmask = aic5_unmask; + gc->chip_types[0].chip.irq_retrigger = aic5_retrigger; + gc->chip_types[0].chip.irq_set_type = aic5_set_type; + gc->chip_types[0].chip.irq_suspend = aic5_suspend; + gc->chip_types[0].chip.irq_resume = aic5_resume; + gc->chip_types[0].chip.irq_pm_shutdown = aic5_pm_shutdown; + } + + aic5_hw_init(domain); + set_handle_irq(aic5_handle); + + return 0; +} + +#define NR_SAMA5D3_IRQS 50 + +static int __init sama5d3_aic5_of_init(struct device_node *node, + struct device_node *parent) +{ + return aic5_of_init(node, parent, NR_SAMA5D3_IRQS); +} +IRQCHIP_DECLARE(sama5d3_aic5, "atmel,sama5d3-aic", sama5d3_aic5_of_init); diff --git a/drivers/irqchip/irq-nvic.c b/drivers/irqchip/irq-nvic.c index 70bdf6edb7bb..4ff0805fca01 100644 --- a/drivers/irqchip/irq-nvic.c +++ b/drivers/irqchip/irq-nvic.c @@ -49,14 +49,6 @@ nvic_handle_irq(irq_hw_number_t hwirq, struct pt_regs *regs) handle_IRQ(irq, regs); } -static void nvic_eoi(struct irq_data *d) -{ - /* - * This is a no-op as end of interrupt is signaled by the exception - * return sequence. - */ -} - static int __init nvic_of_init(struct device_node *node, struct device_node *parent) { @@ -102,7 +94,10 @@ static int __init nvic_of_init(struct device_node *node, gc->chip_types[0].regs.disable = NVIC_ICER; gc->chip_types[0].chip.irq_mask = irq_gc_mask_disable_reg; gc->chip_types[0].chip.irq_unmask = irq_gc_unmask_enable_reg; - gc->chip_types[0].chip.irq_eoi = nvic_eoi; + /* This is a no-op as end of interrupt is signaled by the + * exception return sequence. + */ + gc->chip_types[0].chip.irq_eoi = irq_gc_noop; /* disable interrupts */ writel_relaxed(~0, gc->reg_base + NVIC_ICER); diff --git a/drivers/irqchip/irq-or1k-pic.c b/drivers/irqchip/irq-or1k-pic.c new file mode 100644 index 000000000000..17ff033d9925 --- /dev/null +++ b/drivers/irqchip/irq-or1k-pic.c @@ -0,0 +1,182 @@ +/* + * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se> + * Copyright (C) 2014 Stefan Kristansson <stefan.kristiansson@saunalahti.fi> + * + * 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/irq.h> +#include <linux/of.h> +#include <linux/of_irq.h> +#include <linux/of_address.h> + +#include "irqchip.h" + +/* OR1K PIC implementation */ + +struct or1k_pic_dev { + struct irq_chip chip; + irq_flow_handler_t handle; + unsigned long flags; +}; + +/* + * We're a couple of cycles faster than the generic implementations with + * these 'fast' versions. + */ + +static void or1k_pic_mask(struct irq_data *data) +{ + mtspr(SPR_PICMR, mfspr(SPR_PICMR) & ~(1UL << data->hwirq)); +} + +static void or1k_pic_unmask(struct irq_data *data) +{ + mtspr(SPR_PICMR, mfspr(SPR_PICMR) | (1UL << data->hwirq)); +} + +static void or1k_pic_ack(struct irq_data *data) +{ + mtspr(SPR_PICSR, (1UL << data->hwirq)); +} + +static void or1k_pic_mask_ack(struct irq_data *data) +{ + mtspr(SPR_PICMR, mfspr(SPR_PICMR) & ~(1UL << data->hwirq)); + mtspr(SPR_PICSR, (1UL << data->hwirq)); +} + +/* + * There are two oddities with the OR1200 PIC implementation: + * i) LEVEL-triggered interrupts are latched and need to be cleared + * ii) the interrupt latch is cleared by writing a 0 to the bit, + * as opposed to a 1 as mandated by the spec + */ +static void or1k_pic_or1200_ack(struct irq_data *data) +{ + mtspr(SPR_PICSR, mfspr(SPR_PICSR) & ~(1UL << data->hwirq)); +} + +static void or1k_pic_or1200_mask_ack(struct irq_data *data) +{ + mtspr(SPR_PICMR, mfspr(SPR_PICMR) & ~(1UL << data->hwirq)); + mtspr(SPR_PICSR, mfspr(SPR_PICSR) & ~(1UL << data->hwirq)); +} + +static struct or1k_pic_dev or1k_pic_level = { + .chip = { + .name = "or1k-PIC-level", + .irq_unmask = or1k_pic_unmask, + .irq_mask = or1k_pic_mask, + .irq_mask_ack = or1k_pic_mask, + }, + .handle = handle_level_irq, + .flags = IRQ_LEVEL | IRQ_NOPROBE, +}; + +static struct or1k_pic_dev or1k_pic_edge = { + .chip = { + .name = "or1k-PIC-edge", + .irq_unmask = or1k_pic_unmask, + .irq_mask = or1k_pic_mask, + .irq_ack = or1k_pic_ack, + .irq_mask_ack = or1k_pic_mask_ack, + }, + .handle = handle_edge_irq, + .flags = IRQ_LEVEL | IRQ_NOPROBE, +}; + +static struct or1k_pic_dev or1k_pic_or1200 = { + .chip = { + .name = "or1200-PIC", + .irq_unmask = or1k_pic_unmask, + .irq_mask = or1k_pic_mask, + .irq_ack = or1k_pic_or1200_ack, + .irq_mask_ack = or1k_pic_or1200_mask_ack, + }, + .handle = handle_level_irq, + .flags = IRQ_LEVEL | IRQ_NOPROBE, +}; + +static struct irq_domain *root_domain; + +static inline int pic_get_irq(int first) +{ + int hwirq; + + hwirq = ffs(mfspr(SPR_PICSR) >> first); + if (!hwirq) + return NO_IRQ; + else + hwirq = hwirq + first - 1; + + return irq_find_mapping(root_domain, hwirq); +} + +static void or1k_pic_handle_irq(struct pt_regs *regs) +{ + int irq = -1; + + while ((irq = pic_get_irq(irq + 1)) != NO_IRQ) + handle_IRQ(irq, regs); +} + +static int or1k_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw) +{ + struct or1k_pic_dev *pic = d->host_data; + + irq_set_chip_and_handler(irq, &pic->chip, pic->handle); + irq_set_status_flags(irq, pic->flags); + + return 0; +} + +static const struct irq_domain_ops or1k_irq_domain_ops = { + .xlate = irq_domain_xlate_onecell, + .map = or1k_map, +}; + +/* + * This sets up the IRQ domain for the PIC built in to the OpenRISC + * 1000 CPU. This is the "root" domain as these are the interrupts + * that directly trigger an exception in the CPU. + */ +static int __init or1k_pic_init(struct device_node *node, + struct or1k_pic_dev *pic) +{ + /* Disable all interrupts until explicitly requested */ + mtspr(SPR_PICMR, (0UL)); + + root_domain = irq_domain_add_linear(node, 32, &or1k_irq_domain_ops, + pic); + + set_handle_irq(or1k_pic_handle_irq); + + return 0; +} + +static int __init or1k_pic_or1200_init(struct device_node *node, + struct device_node *parent) +{ + return or1k_pic_init(node, &or1k_pic_or1200); +} +IRQCHIP_DECLARE(or1k_pic_or1200, "opencores,or1200-pic", or1k_pic_or1200_init); +IRQCHIP_DECLARE(or1k_pic, "opencores,or1k-pic", or1k_pic_or1200_init); + +static int __init or1k_pic_level_init(struct device_node *node, + struct device_node *parent) +{ + return or1k_pic_init(node, &or1k_pic_level); +} +IRQCHIP_DECLARE(or1k_pic_level, "opencores,or1k-pic-level", + or1k_pic_level_init); + +static int __init or1k_pic_edge_init(struct device_node *node, + struct device_node *parent) +{ + return or1k_pic_init(node, &or1k_pic_edge); +} +IRQCHIP_DECLARE(or1k_pic_edge, "opencores,or1k-pic-edge", or1k_pic_edge_init); diff --git a/drivers/irqchip/spear-shirq.c b/drivers/irqchip/spear-shirq.c index 6ce6bd3441bf..9c145a7cb056 100644 --- a/drivers/irqchip/spear-shirq.c +++ b/drivers/irqchip/spear-shirq.c @@ -19,7 +19,6 @@ #include <linux/io.h> #include <linux/irq.h> #include <linux/irqdomain.h> -#include <linux/irqchip/spear-shirq.h> #include <linux/of.h> #include <linux/of_address.h> #include <linux/of_irq.h> @@ -27,20 +26,73 @@ #include "irqchip.h" -static DEFINE_SPINLOCK(lock); +/* + * struct spear_shirq: shared irq structure + * + * base: Base register address + * status_reg: Status register offset for chained interrupt handler + * mask_reg: Mask register offset for irq chip + * mask: Mask to apply to the status register + * virq_base: Base virtual interrupt number + * nr_irqs: Number of interrupts handled by this block + * offset: Bit offset of the first interrupt + * irq_chip: Interrupt controller chip used for this instance, + * if NULL group is disabled, but accounted + */ +struct spear_shirq { + void __iomem *base; + u32 status_reg; + u32 mask_reg; + u32 mask; + u32 virq_base; + u32 nr_irqs; + u32 offset; + struct irq_chip *irq_chip; +}; /* spear300 shared irq registers offsets and masks */ #define SPEAR300_INT_ENB_MASK_REG 0x54 #define SPEAR300_INT_STS_MASK_REG 0x58 +static DEFINE_RAW_SPINLOCK(shirq_lock); + +static void shirq_irq_mask(struct irq_data *d) +{ + struct spear_shirq *shirq = irq_data_get_irq_chip_data(d); + u32 val, shift = d->irq - shirq->virq_base + shirq->offset; + u32 __iomem *reg = shirq->base + shirq->mask_reg; + + raw_spin_lock(&shirq_lock); + val = readl(reg) & ~(0x1 << shift); + writel(val, reg); + raw_spin_unlock(&shirq_lock); +} + +static void shirq_irq_unmask(struct irq_data *d) +{ + struct spear_shirq *shirq = irq_data_get_irq_chip_data(d); + u32 val, shift = d->irq - shirq->virq_base + shirq->offset; + u32 __iomem *reg = shirq->base + shirq->mask_reg; + + raw_spin_lock(&shirq_lock); + val = readl(reg) | (0x1 << shift); + writel(val, reg); + raw_spin_unlock(&shirq_lock); +} + +static struct irq_chip shirq_chip = { + .name = "spear-shirq", + .irq_mask = shirq_irq_mask, + .irq_unmask = shirq_irq_unmask, +}; + static struct spear_shirq spear300_shirq_ras1 = { - .irq_nr = 9, - .irq_bit_off = 0, - .regs = { - .enb_reg = SPEAR300_INT_ENB_MASK_REG, - .status_reg = SPEAR300_INT_STS_MASK_REG, - .clear_reg = -1, - }, + .offset = 0, + .nr_irqs = 9, + .mask = ((0x1 << 9) - 1) << 0, + .irq_chip = &shirq_chip, + .status_reg = SPEAR300_INT_STS_MASK_REG, + .mask_reg = SPEAR300_INT_ENB_MASK_REG, }; static struct spear_shirq *spear300_shirq_blocks[] = { @@ -51,43 +103,35 @@ static struct spear_shirq *spear300_shirq_blocks[] = { #define SPEAR310_INT_STS_MASK_REG 0x04 static struct spear_shirq spear310_shirq_ras1 = { - .irq_nr = 8, - .irq_bit_off = 0, - .regs = { - .enb_reg = -1, - .status_reg = SPEAR310_INT_STS_MASK_REG, - .clear_reg = -1, - }, + .offset = 0, + .nr_irqs = 8, + .mask = ((0x1 << 8) - 1) << 0, + .irq_chip = &dummy_irq_chip, + .status_reg = SPEAR310_INT_STS_MASK_REG, }; static struct spear_shirq spear310_shirq_ras2 = { - .irq_nr = 5, - .irq_bit_off = 8, - .regs = { - .enb_reg = -1, - .status_reg = SPEAR310_INT_STS_MASK_REG, - .clear_reg = -1, - }, + .offset = 8, + .nr_irqs = 5, + .mask = ((0x1 << 5) - 1) << 8, + .irq_chip = &dummy_irq_chip, + .status_reg = SPEAR310_INT_STS_MASK_REG, }; static struct spear_shirq spear310_shirq_ras3 = { - .irq_nr = 1, - .irq_bit_off = 13, - .regs = { - .enb_reg = -1, - .status_reg = SPEAR310_INT_STS_MASK_REG, - .clear_reg = -1, - }, + .offset = 13, + .nr_irqs = 1, + .mask = ((0x1 << 1) - 1) << 13, + .irq_chip = &dummy_irq_chip, + .status_reg = SPEAR310_INT_STS_MASK_REG, }; static struct spear_shirq spear310_shirq_intrcomm_ras = { - .irq_nr = 3, - .irq_bit_off = 14, - .regs = { - .enb_reg = -1, - .status_reg = SPEAR310_INT_STS_MASK_REG, - .clear_reg = -1, - }, + .offset = 14, + .nr_irqs = 3, + .mask = ((0x1 << 3) - 1) << 14, + .irq_chip = &dummy_irq_chip, + .status_reg = SPEAR310_INT_STS_MASK_REG, }; static struct spear_shirq *spear310_shirq_blocks[] = { @@ -102,50 +146,34 @@ static struct spear_shirq *spear310_shirq_blocks[] = { #define SPEAR320_INT_CLR_MASK_REG 0x04 #define SPEAR320_INT_ENB_MASK_REG 0x08 -static struct spear_shirq spear320_shirq_ras1 = { - .irq_nr = 3, - .irq_bit_off = 7, - .regs = { - .enb_reg = -1, - .status_reg = SPEAR320_INT_STS_MASK_REG, - .clear_reg = SPEAR320_INT_CLR_MASK_REG, - .reset_to_clear = 1, - }, +static struct spear_shirq spear320_shirq_ras3 = { + .offset = 0, + .nr_irqs = 7, + .mask = ((0x1 << 7) - 1) << 0, }; -static struct spear_shirq spear320_shirq_ras2 = { - .irq_nr = 1, - .irq_bit_off = 10, - .regs = { - .enb_reg = -1, - .status_reg = SPEAR320_INT_STS_MASK_REG, - .clear_reg = SPEAR320_INT_CLR_MASK_REG, - .reset_to_clear = 1, - }, +static struct spear_shirq spear320_shirq_ras1 = { + .offset = 7, + .nr_irqs = 3, + .mask = ((0x1 << 3) - 1) << 7, + .irq_chip = &dummy_irq_chip, + .status_reg = SPEAR320_INT_STS_MASK_REG, }; -static struct spear_shirq spear320_shirq_ras3 = { - .irq_nr = 7, - .irq_bit_off = 0, - .invalid_irq = 1, - .regs = { - .enb_reg = SPEAR320_INT_ENB_MASK_REG, - .reset_to_enb = 1, - .status_reg = SPEAR320_INT_STS_MASK_REG, - .clear_reg = SPEAR320_INT_CLR_MASK_REG, - .reset_to_clear = 1, - }, +static struct spear_shirq spear320_shirq_ras2 = { + .offset = 10, + .nr_irqs = 1, + .mask = ((0x1 << 1) - 1) << 10, + .irq_chip = &dummy_irq_chip, + .status_reg = SPEAR320_INT_STS_MASK_REG, }; static struct spear_shirq spear320_shirq_intrcomm_ras = { - .irq_nr = 11, - .irq_bit_off = 11, - .regs = { - .enb_reg = -1, - .status_reg = SPEAR320_INT_STS_MASK_REG, - .clear_reg = SPEAR320_INT_CLR_MASK_REG, - .reset_to_clear = 1, - }, + .offset = 11, + .nr_irqs = 11, + .mask = ((0x1 << 11) - 1) << 11, + .irq_chip = &dummy_irq_chip, + .status_reg = SPEAR320_INT_STS_MASK_REG, }; static struct spear_shirq *spear320_shirq_blocks[] = { @@ -155,104 +183,46 @@ static struct spear_shirq *spear320_shirq_blocks[] = { &spear320_shirq_intrcomm_ras, }; -static void shirq_irq_mask_unmask(struct irq_data *d, bool mask) -{ - struct spear_shirq *shirq = irq_data_get_irq_chip_data(d); - u32 val, offset = d->irq - shirq->irq_base; - unsigned long flags; - - if (shirq->regs.enb_reg == -1) - return; - - spin_lock_irqsave(&lock, flags); - val = readl(shirq->base + shirq->regs.enb_reg); - - if (mask ^ shirq->regs.reset_to_enb) - val &= ~(0x1 << shirq->irq_bit_off << offset); - else - val |= 0x1 << shirq->irq_bit_off << offset; - - writel(val, shirq->base + shirq->regs.enb_reg); - spin_unlock_irqrestore(&lock, flags); - -} - -static void shirq_irq_mask(struct irq_data *d) -{ - shirq_irq_mask_unmask(d, 1); -} - -static void shirq_irq_unmask(struct irq_data *d) -{ - shirq_irq_mask_unmask(d, 0); -} - -static struct irq_chip shirq_chip = { - .name = "spear-shirq", - .irq_ack = shirq_irq_mask, - .irq_mask = shirq_irq_mask, - .irq_unmask = shirq_irq_unmask, -}; - static void shirq_handler(unsigned irq, struct irq_desc *desc) { - u32 i, j, val, mask, tmp; - struct irq_chip *chip; struct spear_shirq *shirq = irq_get_handler_data(irq); + u32 pend; - chip = irq_get_chip(irq); - chip->irq_ack(&desc->irq_data); - - mask = ((0x1 << shirq->irq_nr) - 1) << shirq->irq_bit_off; - while ((val = readl(shirq->base + shirq->regs.status_reg) & - mask)) { - - val >>= shirq->irq_bit_off; - for (i = 0, j = 1; i < shirq->irq_nr; i++, j <<= 1) { - - if (!(j & val)) - continue; + pend = readl(shirq->base + shirq->status_reg) & shirq->mask; + pend >>= shirq->offset; - generic_handle_irq(shirq->irq_base + i); + while (pend) { + int irq = __ffs(pend); - /* clear interrupt */ - if (shirq->regs.clear_reg == -1) - continue; - - tmp = readl(shirq->base + shirq->regs.clear_reg); - if (shirq->regs.reset_to_clear) - tmp &= ~(j << shirq->irq_bit_off); - else - tmp |= (j << shirq->irq_bit_off); - writel(tmp, shirq->base + shirq->regs.clear_reg); - } + pend &= ~(0x1 << irq); + generic_handle_irq(shirq->virq_base + irq); } - chip->irq_unmask(&desc->irq_data); } -static void __init spear_shirq_register(struct spear_shirq *shirq) +static void __init spear_shirq_register(struct spear_shirq *shirq, + int parent_irq) { int i; - if (shirq->invalid_irq) + if (!shirq->irq_chip) return; - irq_set_chained_handler(shirq->irq, shirq_handler); - for (i = 0; i < shirq->irq_nr; i++) { - irq_set_chip_and_handler(shirq->irq_base + i, - &shirq_chip, handle_simple_irq); - set_irq_flags(shirq->irq_base + i, IRQF_VALID); - irq_set_chip_data(shirq->irq_base + i, shirq); - } + irq_set_chained_handler(parent_irq, shirq_handler); + irq_set_handler_data(parent_irq, shirq); - irq_set_handler_data(shirq->irq, shirq); + for (i = 0; i < shirq->nr_irqs; i++) { + irq_set_chip_and_handler(shirq->virq_base + i, + shirq->irq_chip, handle_simple_irq); + set_irq_flags(shirq->virq_base + i, IRQF_VALID); + irq_set_chip_data(shirq->virq_base + i, shirq); + } } static int __init shirq_init(struct spear_shirq **shirq_blocks, int block_nr, struct device_node *np) { - int i, irq_base, hwirq = 0, irq_nr = 0; - static struct irq_domain *shirq_domain; + int i, parent_irq, virq_base, hwirq = 0, nr_irqs = 0; + struct irq_domain *shirq_domain; void __iomem *base; base = of_iomap(np, 0); @@ -262,15 +232,15 @@ static int __init shirq_init(struct spear_shirq **shirq_blocks, int block_nr, } for (i = 0; i < block_nr; i++) - irq_nr += shirq_blocks[i]->irq_nr; + nr_irqs += shirq_blocks[i]->nr_irqs; - irq_base = irq_alloc_descs(-1, 0, irq_nr, 0); - if (IS_ERR_VALUE(irq_base)) { + virq_base = irq_alloc_descs(-1, 0, nr_irqs, 0); + if (IS_ERR_VALUE(virq_base)) { pr_err("%s: irq desc alloc failed\n", __func__); goto err_unmap; } - shirq_domain = irq_domain_add_legacy(np, irq_nr, irq_base, 0, + shirq_domain = irq_domain_add_legacy(np, nr_irqs, virq_base, 0, &irq_domain_simple_ops, NULL); if (WARN_ON(!shirq_domain)) { pr_warn("%s: irq domain init failed\n", __func__); @@ -279,41 +249,41 @@ static int __init shirq_init(struct spear_shirq **shirq_blocks, int block_nr, for (i = 0; i < block_nr; i++) { shirq_blocks[i]->base = base; - shirq_blocks[i]->irq_base = irq_find_mapping(shirq_domain, + shirq_blocks[i]->virq_base = irq_find_mapping(shirq_domain, hwirq); - shirq_blocks[i]->irq = irq_of_parse_and_map(np, i); - spear_shirq_register(shirq_blocks[i]); - hwirq += shirq_blocks[i]->irq_nr; + parent_irq = irq_of_parse_and_map(np, i); + spear_shirq_register(shirq_blocks[i], parent_irq); + hwirq += shirq_blocks[i]->nr_irqs; } return 0; err_free_desc: - irq_free_descs(irq_base, irq_nr); + irq_free_descs(virq_base, nr_irqs); err_unmap: iounmap(base); return -ENXIO; } -int __init spear300_shirq_of_init(struct device_node *np, - struct device_node *parent) +static int __init spear300_shirq_of_init(struct device_node *np, + struct device_node *parent) { return shirq_init(spear300_shirq_blocks, ARRAY_SIZE(spear300_shirq_blocks), np); } IRQCHIP_DECLARE(spear300_shirq, "st,spear300-shirq", spear300_shirq_of_init); -int __init spear310_shirq_of_init(struct device_node *np, - struct device_node *parent) +static int __init spear310_shirq_of_init(struct device_node *np, + struct device_node *parent) { return shirq_init(spear310_shirq_blocks, ARRAY_SIZE(spear310_shirq_blocks), np); } IRQCHIP_DECLARE(spear310_shirq, "st,spear310-shirq", spear310_shirq_of_init); -int __init spear320_shirq_of_init(struct device_node *np, - struct device_node *parent) +static int __init spear320_shirq_of_init(struct device_node *np, + struct device_node *parent) { return shirq_init(spear320_shirq_blocks, ARRAY_SIZE(spear320_shirq_blocks), np); diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index d724459860d9..ab472c557d18 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -615,16 +615,6 @@ static void write_endio(struct bio *bio, int error) } /* - * This function is called when wait_on_bit is actually waiting. - */ -static int do_io_schedule(void *word) -{ - io_schedule(); - - return 0; -} - -/* * Initiate a write on a dirty buffer, but don't wait for it. * * - If the buffer is not dirty, exit. @@ -640,8 +630,7 @@ static void __write_dirty_buffer(struct dm_buffer *b, return; clear_bit(B_DIRTY, &b->state); - wait_on_bit_lock(&b->state, B_WRITING, - do_io_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit_lock_io(&b->state, B_WRITING, TASK_UNINTERRUPTIBLE); if (!write_list) submit_io(b, WRITE, b->block, write_endio); @@ -675,9 +664,9 @@ static void __make_buffer_clean(struct dm_buffer *b) if (!b->state) /* fast case */ return; - wait_on_bit(&b->state, B_READING, do_io_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE); __write_dirty_buffer(b, NULL); - wait_on_bit(&b->state, B_WRITING, do_io_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&b->state, B_WRITING, TASK_UNINTERRUPTIBLE); } /* @@ -1030,7 +1019,7 @@ static void *new_read(struct dm_bufio_client *c, sector_t block, if (need_submit) submit_io(b, READ, b->block, read_endio); - wait_on_bit(&b->state, B_READING, do_io_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE); if (b->read_error) { int error = b->read_error; @@ -1209,15 +1198,13 @@ again: dropped_lock = 1; b->hold_count++; dm_bufio_unlock(c); - wait_on_bit(&b->state, B_WRITING, - do_io_schedule, - TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&b->state, B_WRITING, + TASK_UNINTERRUPTIBLE); dm_bufio_lock(c); b->hold_count--; } else - wait_on_bit(&b->state, B_WRITING, - do_io_schedule, - TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&b->state, B_WRITING, + TASK_UNINTERRUPTIBLE); } if (!test_bit(B_DIRTY, &b->state) && @@ -1321,15 +1308,15 @@ retry: __write_dirty_buffer(b, NULL); if (b->hold_count == 1) { - wait_on_bit(&b->state, B_WRITING, - do_io_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&b->state, B_WRITING, + TASK_UNINTERRUPTIBLE); set_bit(B_DIRTY, &b->state); __unlink_buffer(b); __link_buffer(b, new_block, LIST_DIRTY); } else { sector_t old_block; - wait_on_bit_lock(&b->state, B_WRITING, - do_io_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit_lock_io(&b->state, B_WRITING, + TASK_UNINTERRUPTIBLE); /* * Relink buffer to "new_block" so that write_callback * sees "new_block" as a block number. @@ -1341,8 +1328,8 @@ retry: __unlink_buffer(b); __link_buffer(b, new_block, b->list_mode); submit_io(b, WRITE, new_block, write_endio); - wait_on_bit(&b->state, B_WRITING, - do_io_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&b->state, B_WRITING, + TASK_UNINTERRUPTIBLE); __unlink_buffer(b); __link_buffer(b, old_block, b->list_mode); } diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index 5bd2290cfb1e..864b03f47727 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -1032,21 +1032,13 @@ static void start_merge(struct dm_snapshot *s) snapshot_merge_next_chunks(s); } -static int wait_schedule(void *ptr) -{ - schedule(); - - return 0; -} - /* * Stop the merging process and wait until it finishes. */ static void stop_merge(struct dm_snapshot *s) { set_bit(SHUTDOWN_MERGE, &s->state_bits); - wait_on_bit(&s->state_bits, RUNNING_MERGE, wait_schedule, - TASK_UNINTERRUPTIBLE); + wait_on_bit(&s->state_bits, RUNNING_MERGE, TASK_UNINTERRUPTIBLE); clear_bit(SHUTDOWN_MERGE, &s->state_bits); } diff --git a/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c b/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c index 45f5ee9f46fc..2e90310be2af 100644 --- a/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c +++ b/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c @@ -253,13 +253,6 @@ static int dvb_usbv2_adapter_stream_exit(struct dvb_usb_adapter *adap) return usb_urb_exitv2(&adap->stream); } -static int wait_schedule(void *ptr) -{ - schedule(); - - return 0; -} - static int dvb_usb_start_feed(struct dvb_demux_feed *dvbdmxfeed) { struct dvb_usb_adapter *adap = dvbdmxfeed->demux->priv; @@ -273,8 +266,7 @@ static int dvb_usb_start_feed(struct dvb_demux_feed *dvbdmxfeed) dvbdmxfeed->pid, dvbdmxfeed->index); /* wait init is done */ - wait_on_bit(&adap->state_bits, ADAP_INIT, wait_schedule, - TASK_UNINTERRUPTIBLE); + wait_on_bit(&adap->state_bits, ADAP_INIT, TASK_UNINTERRUPTIBLE); if (adap->active_fe == -1) return -EINVAL; @@ -568,7 +560,7 @@ static int dvb_usb_fe_sleep(struct dvb_frontend *fe) if (!adap->suspend_resume_active) { set_bit(ADAP_SLEEP, &adap->state_bits); - wait_on_bit(&adap->state_bits, ADAP_STREAMING, wait_schedule, + wait_on_bit(&adap->state_bits, ADAP_STREAMING, TASK_UNINTERRUPTIBLE); } diff --git a/drivers/mfd/cros_ec_spi.c b/drivers/mfd/cros_ec_spi.c index ac52e3653e90..588c700af39c 100644 --- a/drivers/mfd/cros_ec_spi.c +++ b/drivers/mfd/cros_ec_spi.c @@ -225,7 +225,6 @@ static int cros_ec_cmd_xfer_spi(struct cros_ec_device *ec_dev, u8 *ptr; int sum; int ret = 0, final_ret; - struct timespec ts; /* * We have the shared ec_dev buffer plus we do lots of separate spi_sync @@ -239,11 +238,9 @@ static int cros_ec_cmd_xfer_spi(struct cros_ec_device *ec_dev, /* If it's too soon to do another transaction, wait */ if (ec_spi->last_transfer_ns) { - struct timespec ts; unsigned long delay; /* The delay completed so far */ - ktime_get_ts(&ts); - delay = timespec_to_ns(&ts) - ec_spi->last_transfer_ns; + delay = ktime_get_ns() - ec_spi->last_transfer_ns; if (delay < EC_SPI_RECOVERY_TIME_NS) ndelay(EC_SPI_RECOVERY_TIME_NS - delay); } @@ -276,8 +273,7 @@ static int cros_ec_cmd_xfer_spi(struct cros_ec_device *ec_dev, spi_message_add_tail(&trans, &msg); final_ret = spi_sync(ec_spi->spi, &msg); - ktime_get_ts(&ts); - ec_spi->last_transfer_ns = timespec_to_ns(&ts); + ec_spi->last_transfer_ns = ktime_get_ns(); if (!ret) ret = final_ret; if (ret < 0) { diff --git a/drivers/misc/ioc4.c b/drivers/misc/ioc4.c index 06f6ad29ceff..3336ddca45ac 100644 --- a/drivers/misc/ioc4.c +++ b/drivers/misc/ioc4.c @@ -145,7 +145,6 @@ ioc4_clock_calibrate(struct ioc4_driver_data *idd) union ioc4_int_out int_out; union ioc4_gpcr gpcr; unsigned int state, last_state = 1; - struct timespec start_ts, end_ts; uint64_t start, end, period; unsigned int count = 0; @@ -174,10 +173,10 @@ ioc4_clock_calibrate(struct ioc4_driver_data *idd) if (!last_state && state) { count++; if (count == IOC4_CALIBRATE_END) { - ktime_get_ts(&end_ts); + end = ktime_get_ns(); break; } else if (count == IOC4_CALIBRATE_DISCARD) - ktime_get_ts(&start_ts); + start = ktime_get_ns(); } last_state = state; } while (1); @@ -192,8 +191,6 @@ ioc4_clock_calibrate(struct ioc4_driver_data *idd) * by which the IOC4 generates the square wave, to get the * period of an IOC4 INT_OUT count. */ - end = end_ts.tv_sec * NSEC_PER_SEC + end_ts.tv_nsec; - start = start_ts.tv_sec * NSEC_PER_SEC + start_ts.tv_nsec; period = (end - start) / (IOC4_CALIBRATE_CYCLES * 2 * (IOC4_CALIBRATE_COUNT + 1)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 4671747dd365..65a7da69e2ac 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -548,7 +548,7 @@ static void cmd_work_handler(struct work_struct *work) lay->status_own = CMD_OWNER_HW; set_signature(ent, !cmd->checksum_disabled); dump_command(dev, ent, 1); - ktime_get_ts(&ent->ts1); + ent->ts1 = ktime_get_ns(); /* ring doorbell after the descriptor is valid */ wmb(); @@ -637,7 +637,6 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, { struct mlx5_cmd *cmd = &dev->cmd; struct mlx5_cmd_work_ent *ent; - ktime_t t1, t2, delta; struct mlx5_cmd_stats *stats; int err = 0; s64 ds; @@ -668,10 +667,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, if (err == -ETIMEDOUT) goto out; - t1 = timespec_to_ktime(ent->ts1); - t2 = timespec_to_ktime(ent->ts2); - delta = ktime_sub(t2, t1); - ds = ktime_to_ns(delta); + ds = ent->ts2 - ent->ts1; op = be16_to_cpu(((struct mlx5_inbox_hdr *)in->first.data)->opcode); if (op < ARRAY_SIZE(cmd->stats)) { stats = &cmd->stats[op]; @@ -1135,7 +1131,6 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, unsigned long vector) void *context; int err; int i; - ktime_t t1, t2, delta; s64 ds; struct mlx5_cmd_stats *stats; unsigned long flags; @@ -1149,7 +1144,7 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, unsigned long vector) sem = &cmd->pages_sem; else sem = &cmd->sem; - ktime_get_ts(&ent->ts2); + ent->ts2 = ktime_get_ns(); memcpy(ent->out->first.data, ent->lay->out, sizeof(ent->lay->out)); dump_command(dev, ent, 0); if (!ent->ret) { @@ -1163,10 +1158,7 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, unsigned long vector) } free_ent(cmd, ent->idx); if (ent->callback) { - t1 = timespec_to_ktime(ent->ts1); - t2 = timespec_to_ktime(ent->ts2); - delta = ktime_sub(t2, t1); - ds = ktime_to_ns(delta); + ds = ent->ts2 - ent->ts1; if (ent->op < ARRAY_SIZE(cmd->stats)) { stats = &cmd->stats[ent->op]; spin_lock_irqsave(&stats->lock, flags); diff --git a/drivers/of/address.c b/drivers/of/address.c index 5edfcb0da37d..e3718250d66e 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -702,6 +702,42 @@ void __iomem *of_iomap(struct device_node *np, int index) } EXPORT_SYMBOL(of_iomap); +/* + * of_io_request_and_map - Requests a resource and maps the memory mapped IO + * for a given device_node + * @device: the device whose io range will be mapped + * @index: index of the io range + * @name: name of the resource + * + * Returns a pointer to the requested and mapped memory or an ERR_PTR() encoded + * error code on failure. Usage example: + * + * base = of_io_request_and_map(node, 0, "foo"); + * if (IS_ERR(base)) + * return PTR_ERR(base); + */ +void __iomem *of_io_request_and_map(struct device_node *np, int index, + char *name) +{ + struct resource res; + void __iomem *mem; + + if (of_address_to_resource(np, index, &res)) + return IOMEM_ERR_PTR(-EINVAL); + + if (!request_mem_region(res.start, resource_size(&res), name)) + return IOMEM_ERR_PTR(-EBUSY); + + mem = ioremap(res.start, resource_size(&res)); + if (!mem) { + release_mem_region(res.start, resource_size(&res)); + return IOMEM_ERR_PTR(-ENOMEM); + } + + return mem; +} +EXPORT_SYMBOL(of_io_request_and_map); + /** * of_dma_get_range - Get DMA range info * @np: device node to get DMA range info diff --git a/drivers/pci/pcie/aer/Kconfig b/drivers/pci/pcie/aer/Kconfig index 50e94e02378a..389440228c1d 100644 --- a/drivers/pci/pcie/aer/Kconfig +++ b/drivers/pci/pcie/aer/Kconfig @@ -5,6 +5,7 @@ config PCIEAER boolean "Root Port Advanced Error Reporting support" depends on PCIEPORTBUS + select RAS default y help This enables PCI Express Root Port Advanced Error Reporting diff --git a/drivers/pci/pcie/aer/aerdrv_errprint.c b/drivers/pci/pcie/aer/aerdrv_errprint.c index 36ed31b52198..35d06e177917 100644 --- a/drivers/pci/pcie/aer/aerdrv_errprint.c +++ b/drivers/pci/pcie/aer/aerdrv_errprint.c @@ -22,9 +22,7 @@ #include <linux/cper.h> #include "aerdrv.h" - -#define CREATE_TRACE_POINTS -#include <trace/events/ras.h> +#include <ras/ras_event.h> #define AER_AGENT_RECEIVER 0 #define AER_AGENT_REQUESTER 1 diff --git a/drivers/ras/Kconfig b/drivers/ras/Kconfig new file mode 100644 index 000000000000..f9da613052c2 --- /dev/null +++ b/drivers/ras/Kconfig @@ -0,0 +1,2 @@ +config RAS + bool diff --git a/drivers/ras/Makefile b/drivers/ras/Makefile new file mode 100644 index 000000000000..d7f73341ced3 --- /dev/null +++ b/drivers/ras/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_RAS) += ras.o debugfs.o diff --git a/drivers/ras/debugfs.c b/drivers/ras/debugfs.c new file mode 100644 index 000000000000..0322acf67ea5 --- /dev/null +++ b/drivers/ras/debugfs.c @@ -0,0 +1,56 @@ +#include <linux/debugfs.h> + +static struct dentry *ras_debugfs_dir; + +static atomic_t trace_count = ATOMIC_INIT(0); + +int ras_userspace_consumers(void) +{ + return atomic_read(&trace_count); +} +EXPORT_SYMBOL_GPL(ras_userspace_consumers); + +static int trace_show(struct seq_file *m, void *v) +{ + return atomic_read(&trace_count); +} + +static int trace_open(struct inode *inode, struct file *file) +{ + atomic_inc(&trace_count); + return single_open(file, trace_show, NULL); +} + +static int trace_release(struct inode *inode, struct file *file) +{ + atomic_dec(&trace_count); + return single_release(inode, file); +} + +static const struct file_operations trace_fops = { + .open = trace_open, + .read = seq_read, + .llseek = seq_lseek, + .release = trace_release, +}; + +int __init ras_add_daemon_trace(void) +{ + struct dentry *fentry; + + if (!ras_debugfs_dir) + return -ENOENT; + + fentry = debugfs_create_file("daemon_active", S_IRUSR, ras_debugfs_dir, + NULL, &trace_fops); + if (!fentry) + return -ENODEV; + + return 0; + +} + +void __init ras_debugfs_init(void) +{ + ras_debugfs_dir = debugfs_create_dir("ras", NULL); +} diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c new file mode 100644 index 000000000000..b67dd362b7b6 --- /dev/null +++ b/drivers/ras/ras.c @@ -0,0 +1,29 @@ +/* + * Copyright (C) 2014 Intel Corporation + * + * Authors: + * Chen, Gong <gong.chen@linux.intel.com> + */ + +#include <linux/init.h> +#include <linux/ras.h> + +#define CREATE_TRACE_POINTS +#define TRACE_INCLUDE_PATH ../../include/ras +#include <ras/ras_event.h> + +static int __init ras_init(void) +{ + int rc = 0; + + ras_debugfs_init(); + rc = ras_add_daemon_trace(); + + return rc; +} +subsys_initcall(ras_init); + +#if defined(CONFIG_ACPI_EXTLOG) || defined(CONFIG_ACPI_EXTLOG_MODULE) +EXPORT_TRACEPOINT_SYMBOL_GPL(extlog_mem_event); +#endif +EXPORT_TRACEPOINT_SYMBOL_GPL(mc_event); diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index 38fb36e1c592..8bc01838daf9 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -240,4 +240,8 @@ config XEN_MCE_LOG config XEN_HAVE_PVMMU bool +config XEN_EFI + def_bool y + depends on X86_64 && EFI + endmenu diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index 45e00afa7f2d..84044b554e33 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -9,6 +9,8 @@ obj-y += xenbus/ nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_features.o := $(nostackp) +CFLAGS_efi.o += -fshort-wchar + dom0-$(CONFIG_PCI) += pci.o dom0-$(CONFIG_USB_SUPPORT) += dbgp.o dom0-$(CONFIG_ACPI) += acpi.o $(xen-pad-y) @@ -33,6 +35,7 @@ obj-$(CONFIG_XEN_STUB) += xen-stub.o obj-$(CONFIG_XEN_ACPI_HOTPLUG_MEMORY) += xen-acpi-memhotplug.o obj-$(CONFIG_XEN_ACPI_HOTPLUG_CPU) += xen-acpi-cpuhotplug.o obj-$(CONFIG_XEN_ACPI_PROCESSOR) += xen-acpi-processor.o +obj-$(CONFIG_XEN_EFI) += efi.o xen-evtchn-y := evtchn.o xen-gntdev-y := gntdev.o xen-gntalloc-y := gntalloc.o diff --git a/drivers/xen/efi.c b/drivers/xen/efi.c new file mode 100644 index 000000000000..31f618a49661 --- /dev/null +++ b/drivers/xen/efi.c @@ -0,0 +1,368 @@ +/* + * EFI support for Xen. + * + * Copyright (C) 1999 VA Linux Systems + * Copyright (C) 1999 Walt Drummond <drummond@valinux.com> + * Copyright (C) 1999-2002 Hewlett-Packard Co. + * David Mosberger-Tang <davidm@hpl.hp.com> + * Stephane Eranian <eranian@hpl.hp.com> + * Copyright (C) 2005-2008 Intel Co. + * Fenghua Yu <fenghua.yu@intel.com> + * Bibo Mao <bibo.mao@intel.com> + * Chandramouli Narayanan <mouli@linux.intel.com> + * Huang Ying <ying.huang@intel.com> + * Copyright (C) 2011 Novell Co. + * Jan Beulich <JBeulich@suse.com> + * Copyright (C) 2011-2012 Oracle Co. + * Liang Tang <liang.tang@oracle.com> + * Copyright (c) 2014 Oracle Co., Daniel Kiper + */ + +#include <linux/bug.h> +#include <linux/efi.h> +#include <linux/init.h> +#include <linux/string.h> + +#include <xen/interface/xen.h> +#include <xen/interface/platform.h> +#include <xen/xen.h> + +#include <asm/xen/hypercall.h> + +#define INIT_EFI_OP(name) \ + {.cmd = XENPF_efi_runtime_call, \ + .u.efi_runtime_call.function = XEN_EFI_##name, \ + .u.efi_runtime_call.misc = 0} + +#define efi_data(op) (op.u.efi_runtime_call) + +static efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) +{ + struct xen_platform_op op = INIT_EFI_OP(get_time); + + if (HYPERVISOR_dom0_op(&op) < 0) + return EFI_UNSUPPORTED; + + if (tm) { + BUILD_BUG_ON(sizeof(*tm) != sizeof(efi_data(op).u.get_time.time)); + memcpy(tm, &efi_data(op).u.get_time.time, sizeof(*tm)); + } + + if (tc) { + tc->resolution = efi_data(op).u.get_time.resolution; + tc->accuracy = efi_data(op).u.get_time.accuracy; + tc->sets_to_zero = !!(efi_data(op).misc & + XEN_EFI_GET_TIME_SET_CLEARS_NS); + } + + return efi_data(op).status; +} + +static efi_status_t xen_efi_set_time(efi_time_t *tm) +{ + struct xen_platform_op op = INIT_EFI_OP(set_time); + + BUILD_BUG_ON(sizeof(*tm) != sizeof(efi_data(op).u.set_time)); + memcpy(&efi_data(op).u.set_time, tm, sizeof(*tm)); + + if (HYPERVISOR_dom0_op(&op) < 0) + return EFI_UNSUPPORTED; + + return efi_data(op).status; +} + +static efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled, + efi_bool_t *pending, + efi_time_t *tm) +{ + struct xen_platform_op op = INIT_EFI_OP(get_wakeup_time); + + if (HYPERVISOR_dom0_op(&op) < 0) + return EFI_UNSUPPORTED; + + if (tm) { + BUILD_BUG_ON(sizeof(*tm) != sizeof(efi_data(op).u.get_wakeup_time)); + memcpy(tm, &efi_data(op).u.get_wakeup_time, sizeof(*tm)); + } + + if (enabled) + *enabled = !!(efi_data(op).misc & XEN_EFI_GET_WAKEUP_TIME_ENABLED); + + if (pending) + *pending = !!(efi_data(op).misc & XEN_EFI_GET_WAKEUP_TIME_PENDING); + + return efi_data(op).status; +} + +static efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) +{ + struct xen_platform_op op = INIT_EFI_OP(set_wakeup_time); + + BUILD_BUG_ON(sizeof(*tm) != sizeof(efi_data(op).u.set_wakeup_time)); + if (enabled) + efi_data(op).misc = XEN_EFI_SET_WAKEUP_TIME_ENABLE; + if (tm) + memcpy(&efi_data(op).u.set_wakeup_time, tm, sizeof(*tm)); + else + efi_data(op).misc |= XEN_EFI_SET_WAKEUP_TIME_ENABLE_ONLY; + + if (HYPERVISOR_dom0_op(&op) < 0) + return EFI_UNSUPPORTED; + + return efi_data(op).status; +} + +static efi_status_t xen_efi_get_variable(efi_char16_t *name, + efi_guid_t *vendor, + u32 *attr, + unsigned long *data_size, + void *data) +{ + struct xen_platform_op op = INIT_EFI_OP(get_variable); + + set_xen_guest_handle(efi_data(op).u.get_variable.name, name); + BUILD_BUG_ON(sizeof(*vendor) != + sizeof(efi_data(op).u.get_variable.vendor_guid)); + memcpy(&efi_data(op).u.get_variable.vendor_guid, vendor, sizeof(*vendor)); + efi_data(op).u.get_variable.size = *data_size; + set_xen_guest_handle(efi_data(op).u.get_variable.data, data); + + if (HYPERVISOR_dom0_op(&op) < 0) + return EFI_UNSUPPORTED; + + *data_size = efi_data(op).u.get_variable.size; + if (attr) + *attr = efi_data(op).misc; + + return efi_data(op).status; +} + +static efi_status_t xen_efi_get_next_variable(unsigned long *name_size, + efi_char16_t *name, + efi_guid_t *vendor) +{ + struct xen_platform_op op = INIT_EFI_OP(get_next_variable_name); + + efi_data(op).u.get_next_variable_name.size = *name_size; + set_xen_guest_handle(efi_data(op).u.get_next_variable_name.name, name); + BUILD_BUG_ON(sizeof(*vendor) != + sizeof(efi_data(op).u.get_next_variable_name.vendor_guid)); + memcpy(&efi_data(op).u.get_next_variable_name.vendor_guid, vendor, + sizeof(*vendor)); + + if (HYPERVISOR_dom0_op(&op) < 0) + return EFI_UNSUPPORTED; + + *name_size = efi_data(op).u.get_next_variable_name.size; + memcpy(vendor, &efi_data(op).u.get_next_variable_name.vendor_guid, + sizeof(*vendor)); + + return efi_data(op).status; +} + +static efi_status_t xen_efi_set_variable(efi_char16_t *name, + efi_guid_t *vendor, + u32 attr, + unsigned long data_size, + void *data) +{ + struct xen_platform_op op = INIT_EFI_OP(set_variable); + + set_xen_guest_handle(efi_data(op).u.set_variable.name, name); + efi_data(op).misc = attr; + BUILD_BUG_ON(sizeof(*vendor) != + sizeof(efi_data(op).u.set_variable.vendor_guid)); + memcpy(&efi_data(op).u.set_variable.vendor_guid, vendor, sizeof(*vendor)); + efi_data(op).u.set_variable.size = data_size; + set_xen_guest_handle(efi_data(op).u.set_variable.data, data); + + if (HYPERVISOR_dom0_op(&op) < 0) + return EFI_UNSUPPORTED; + + return efi_data(op).status; +} + +static efi_status_t xen_efi_query_variable_info(u32 attr, + u64 *storage_space, + u64 *remaining_space, + u64 *max_variable_size) +{ + struct xen_platform_op op = INIT_EFI_OP(query_variable_info); + + if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) + return EFI_UNSUPPORTED; + + efi_data(op).u.query_variable_info.attr = attr; + + if (HYPERVISOR_dom0_op(&op) < 0) + return EFI_UNSUPPORTED; + + *storage_space = efi_data(op).u.query_variable_info.max_store_size; + *remaining_space = efi_data(op).u.query_variable_info.remain_store_size; + *max_variable_size = efi_data(op).u.query_variable_info.max_size; + + return efi_data(op).status; +} + +static efi_status_t xen_efi_get_next_high_mono_count(u32 *count) +{ + struct xen_platform_op op = INIT_EFI_OP(get_next_high_monotonic_count); + + if (HYPERVISOR_dom0_op(&op) < 0) + return EFI_UNSUPPORTED; + + *count = efi_data(op).misc; + + return efi_data(op).status; +} + +static efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules, + unsigned long count, + unsigned long sg_list) +{ + struct xen_platform_op op = INIT_EFI_OP(update_capsule); + + if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) + return EFI_UNSUPPORTED; + + set_xen_guest_handle(efi_data(op).u.update_capsule.capsule_header_array, + capsules); + efi_data(op).u.update_capsule.capsule_count = count; + efi_data(op).u.update_capsule.sg_list = sg_list; + + if (HYPERVISOR_dom0_op(&op) < 0) + return EFI_UNSUPPORTED; + + return efi_data(op).status; +} + +static efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules, + unsigned long count, + u64 *max_size, + int *reset_type) +{ + struct xen_platform_op op = INIT_EFI_OP(query_capsule_capabilities); + + if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) + return EFI_UNSUPPORTED; + + set_xen_guest_handle(efi_data(op).u.query_capsule_capabilities.capsule_header_array, + capsules); + efi_data(op).u.query_capsule_capabilities.capsule_count = count; + + if (HYPERVISOR_dom0_op(&op) < 0) + return EFI_UNSUPPORTED; + + *max_size = efi_data(op).u.query_capsule_capabilities.max_capsule_size; + *reset_type = efi_data(op).u.query_capsule_capabilities.reset_type; + + return efi_data(op).status; +} + +static efi_char16_t vendor[100] __initdata; + +static efi_system_table_t efi_systab_xen __initdata = { + .hdr = { + .signature = EFI_SYSTEM_TABLE_SIGNATURE, + .revision = 0, /* Initialized later. */ + .headersize = 0, /* Ignored by Linux Kernel. */ + .crc32 = 0, /* Ignored by Linux Kernel. */ + .reserved = 0 + }, + .fw_vendor = EFI_INVALID_TABLE_ADDR, /* Initialized later. */ + .fw_revision = 0, /* Initialized later. */ + .con_in_handle = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */ + .con_in = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */ + .con_out_handle = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */ + .con_out = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */ + .stderr_handle = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */ + .stderr = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */ + .runtime = (efi_runtime_services_t *)EFI_INVALID_TABLE_ADDR, + /* Not used under Xen. */ + .boottime = (efi_boot_services_t *)EFI_INVALID_TABLE_ADDR, + /* Not used under Xen. */ + .nr_tables = 0, /* Initialized later. */ + .tables = EFI_INVALID_TABLE_ADDR /* Initialized later. */ +}; + +static const struct efi efi_xen __initconst = { + .systab = NULL, /* Initialized later. */ + .runtime_version = 0, /* Initialized later. */ + .mps = EFI_INVALID_TABLE_ADDR, + .acpi = EFI_INVALID_TABLE_ADDR, + .acpi20 = EFI_INVALID_TABLE_ADDR, + .smbios = EFI_INVALID_TABLE_ADDR, + .sal_systab = EFI_INVALID_TABLE_ADDR, + .boot_info = EFI_INVALID_TABLE_ADDR, + .hcdp = EFI_INVALID_TABLE_ADDR, + .uga = EFI_INVALID_TABLE_ADDR, + .uv_systab = EFI_INVALID_TABLE_ADDR, + .fw_vendor = EFI_INVALID_TABLE_ADDR, + .runtime = EFI_INVALID_TABLE_ADDR, + .config_table = EFI_INVALID_TABLE_ADDR, + .get_time = xen_efi_get_time, + .set_time = xen_efi_set_time, + .get_wakeup_time = xen_efi_get_wakeup_time, + .set_wakeup_time = xen_efi_set_wakeup_time, + .get_variable = xen_efi_get_variable, + .get_next_variable = xen_efi_get_next_variable, + .set_variable = xen_efi_set_variable, + .query_variable_info = xen_efi_query_variable_info, + .update_capsule = xen_efi_update_capsule, + .query_capsule_caps = xen_efi_query_capsule_caps, + .get_next_high_mono_count = xen_efi_get_next_high_mono_count, + .reset_system = NULL, /* Functionality provided by Xen. */ + .set_virtual_address_map = NULL, /* Not used under Xen. */ + .memmap = NULL, /* Not used under Xen. */ + .flags = 0 /* Initialized later. */ +}; + +efi_system_table_t __init *xen_efi_probe(void) +{ + struct xen_platform_op op = { + .cmd = XENPF_firmware_info, + .u.firmware_info = { + .type = XEN_FW_EFI_INFO, + .index = XEN_FW_EFI_CONFIG_TABLE + } + }; + union xenpf_efi_info *info = &op.u.firmware_info.u.efi_info; + + if (!xen_initial_domain() || HYPERVISOR_dom0_op(&op) < 0) + return NULL; + + /* Here we know that Xen runs on EFI platform. */ + + efi = efi_xen; + + efi_systab_xen.tables = info->cfg.addr; + efi_systab_xen.nr_tables = info->cfg.nent; + + op.cmd = XENPF_firmware_info; + op.u.firmware_info.type = XEN_FW_EFI_INFO; + op.u.firmware_info.index = XEN_FW_EFI_VENDOR; + info->vendor.bufsz = sizeof(vendor); + set_xen_guest_handle(info->vendor.name, vendor); + + if (HYPERVISOR_dom0_op(&op) == 0) { + efi_systab_xen.fw_vendor = __pa_symbol(vendor); + efi_systab_xen.fw_revision = info->vendor.revision; + } else + efi_systab_xen.fw_vendor = __pa_symbol(L"UNKNOWN"); + + op.cmd = XENPF_firmware_info; + op.u.firmware_info.type = XEN_FW_EFI_INFO; + op.u.firmware_info.index = XEN_FW_EFI_VERSION; + + if (HYPERVISOR_dom0_op(&op) == 0) + efi_systab_xen.hdr.revision = info->version; + + op.cmd = XENPF_firmware_info; + op.u.firmware_info.type = XEN_FW_EFI_INFO; + op.u.firmware_info.index = XEN_FW_EFI_RT_VERSION; + + if (HYPERVISOR_dom0_op(&op) == 0) + efi.runtime_version = info->version; + + return &efi_systab_xen; +} diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index a389820d158b..3e11aab9f391 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3437,16 +3437,10 @@ done_unlocked: return 0; } -static int eb_wait(void *word) -{ - io_schedule(); - return 0; -} - void wait_on_extent_buffer_writeback(struct extent_buffer *eb) { - wait_on_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK, eb_wait, - TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_WRITEBACK, + TASK_UNINTERRUPTIBLE); } static noinline_for_stack int diff --git a/fs/buffer.c b/fs/buffer.c index eba6e4f621ce..8f05111bbb8b 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -61,16 +61,9 @@ inline void touch_buffer(struct buffer_head *bh) } EXPORT_SYMBOL(touch_buffer); -static int sleep_on_buffer(void *word) -{ - io_schedule(); - return 0; -} - void __lock_buffer(struct buffer_head *bh) { - wait_on_bit_lock(&bh->b_state, BH_Lock, sleep_on_buffer, - TASK_UNINTERRUPTIBLE); + wait_on_bit_lock_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__lock_buffer); @@ -123,7 +116,7 @@ EXPORT_SYMBOL(buffer_check_dirty_writeback); */ void __wait_on_buffer(struct buffer_head * bh) { - wait_on_bit(&bh->b_state, BH_Lock, sleep_on_buffer, TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__wait_on_buffer); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index b0427f6ea971..03ed8a09581c 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -3934,13 +3934,6 @@ cifs_sb_master_tcon(struct cifs_sb_info *cifs_sb) return tlink_tcon(cifs_sb_master_tlink(cifs_sb)); } -static int -cifs_sb_tcon_pending_wait(void *unused) -{ - schedule(); - return signal_pending(current) ? -ERESTARTSYS : 0; -} - /* find and return a tlink with given uid */ static struct tcon_link * tlink_rb_search(struct rb_root *root, kuid_t uid) @@ -4039,11 +4032,10 @@ cifs_sb_tlink(struct cifs_sb_info *cifs_sb) } else { wait_for_construction: ret = wait_on_bit(&tlink->tl_flags, TCON_LINK_PENDING, - cifs_sb_tcon_pending_wait, TASK_INTERRUPTIBLE); if (ret) { cifs_put_tlink(tlink); - return ERR_PTR(ret); + return ERR_PTR(-ERESTARTSYS); } /* if it's good, return it */ diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 12b64e02eee1..4ab2f79ffa7a 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3812,13 +3812,6 @@ static int cifs_launder_page(struct page *page) return rc; } -static int -cifs_pending_writers_wait(void *unused) -{ - schedule(); - return 0; -} - void cifs_oplock_break(struct work_struct *work) { struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo, @@ -3830,7 +3823,7 @@ void cifs_oplock_break(struct work_struct *work) int rc = 0; wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, - cifs_pending_writers_wait, TASK_UNINTERRUPTIBLE); + TASK_UNINTERRUPTIBLE); server->ops->downgrade_oplock(server, cinode, test_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags)); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index bec0a0831be6..426d6c6ad8bf 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1790,7 +1790,7 @@ cifs_invalidate_mapping(struct inode *inode) * @word: long word containing the bit lock */ static int -cifs_wait_bit_killable(void *word) +cifs_wait_bit_killable(struct wait_bit_key *key) { if (fatal_signal_pending(current)) return -ERESTARTSYS; @@ -1804,8 +1804,8 @@ cifs_revalidate_mapping(struct inode *inode) int rc; unsigned long *flags = &CIFS_I(inode)->flags; - rc = wait_on_bit_lock(flags, CIFS_INO_LOCK, cifs_wait_bit_killable, - TASK_KILLABLE); + rc = wait_on_bit_lock_action(flags, CIFS_INO_LOCK, cifs_wait_bit_killable, + TASK_KILLABLE); if (rc) return rc; diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index e65e17b3d484..81340c6253eb 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -591,7 +591,7 @@ int cifs_get_writer(struct cifsInodeInfo *cinode) start: rc = wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_OPLOCK_BREAK, - cifs_oplock_break_wait, TASK_KILLABLE); + TASK_KILLABLE); if (rc) return rc; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index be568b7311d6..ef9bef118342 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -342,7 +342,8 @@ static void __inode_wait_for_writeback(struct inode *inode) wqh = bit_waitqueue(&inode->i_state, __I_SYNC); while (inode->i_state & I_SYNC) { spin_unlock(&inode->i_lock); - __wait_on_bit(wqh, &wq, inode_wait, TASK_UNINTERRUPTIBLE); + __wait_on_bit(wqh, &wq, bit_wait, + TASK_UNINTERRUPTIBLE); spin_lock(&inode->i_lock); } } diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index aec01be91b0a..89acec742e0b 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -160,7 +160,7 @@ void __fscache_enable_cookie(struct fscache_cookie *cookie, _enter("%p", cookie); wait_on_bit_lock(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK, - fscache_wait_bit, TASK_UNINTERRUPTIBLE); + TASK_UNINTERRUPTIBLE); if (test_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags)) goto out_unlock; @@ -255,7 +255,7 @@ static int fscache_acquire_non_index_cookie(struct fscache_cookie *cookie) if (!fscache_defer_lookup) { _debug("non-deferred lookup %p", &cookie->flags); wait_on_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP, - fscache_wait_bit, TASK_UNINTERRUPTIBLE); + TASK_UNINTERRUPTIBLE); _debug("complete"); if (test_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags)) goto unavailable; @@ -463,7 +463,6 @@ void __fscache_wait_on_invalidate(struct fscache_cookie *cookie) _enter("%p", cookie); wait_on_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING, - fscache_wait_bit_interruptible, TASK_UNINTERRUPTIBLE); _leave(""); @@ -525,7 +524,7 @@ void __fscache_disable_cookie(struct fscache_cookie *cookie, bool invalidate) } wait_on_bit_lock(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK, - fscache_wait_bit, TASK_UNINTERRUPTIBLE); + TASK_UNINTERRUPTIBLE); if (!test_and_clear_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags)) goto out_unlock_enable; diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index bc6c08fcfddd..7872a62ef30c 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -97,8 +97,6 @@ static inline bool fscache_object_congested(void) return workqueue_congested(WORK_CPU_UNBOUND, fscache_object_wq); } -extern int fscache_wait_bit(void *); -extern int fscache_wait_bit_interruptible(void *); extern int fscache_wait_atomic_t(atomic_t *); /* diff --git a/fs/fscache/main.c b/fs/fscache/main.c index 63f868e869b9..a31b83c5cbd9 100644 --- a/fs/fscache/main.c +++ b/fs/fscache/main.c @@ -197,24 +197,6 @@ static void __exit fscache_exit(void) module_exit(fscache_exit); /* - * wait_on_bit() sleep function for uninterruptible waiting - */ -int fscache_wait_bit(void *flags) -{ - schedule(); - return 0; -} - -/* - * wait_on_bit() sleep function for interruptible waiting - */ -int fscache_wait_bit_interruptible(void *flags) -{ - schedule(); - return signal_pending(current); -} - -/* * wait_on_atomic_t() sleep function for uninterruptible waiting */ int fscache_wait_atomic_t(atomic_t *p) diff --git a/fs/fscache/page.c b/fs/fscache/page.c index ed70714503fa..85332b9d19d1 100644 --- a/fs/fscache/page.c +++ b/fs/fscache/page.c @@ -298,7 +298,6 @@ int fscache_wait_for_deferred_lookup(struct fscache_cookie *cookie) jif = jiffies; if (wait_on_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP, - fscache_wait_bit_interruptible, TASK_INTERRUPTIBLE) != 0) { fscache_stat(&fscache_n_retrievals_intr); _leave(" = -ERESTARTSYS"); @@ -342,7 +341,6 @@ int fscache_wait_for_operation_activation(struct fscache_object *object, if (stat_op_waits) fscache_stat(stat_op_waits); if (wait_on_bit(&op->flags, FSCACHE_OP_WAITING, - fscache_wait_bit_interruptible, TASK_INTERRUPTIBLE) != 0) { ret = fscache_cancel_op(op, do_cancel); if (ret == 0) @@ -351,7 +349,7 @@ int fscache_wait_for_operation_activation(struct fscache_object *object, /* it's been removed from the pending queue by another party, * so we should get to run shortly */ wait_on_bit(&op->flags, FSCACHE_OP_WAITING, - fscache_wait_bit, TASK_UNINTERRUPTIBLE); + TASK_UNINTERRUPTIBLE); } _debug("<<< GO"); diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index ee4e04fe60fc..7f513b1ceb2c 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -856,27 +856,6 @@ void gfs2_holder_uninit(struct gfs2_holder *gh) } /** - * gfs2_glock_holder_wait - * @word: unused - * - * This function and gfs2_glock_demote_wait both show up in the WCHAN - * field. Thus I've separated these otherwise identical functions in - * order to be more informative to the user. - */ - -static int gfs2_glock_holder_wait(void *word) -{ - schedule(); - return 0; -} - -static int gfs2_glock_demote_wait(void *word) -{ - schedule(); - return 0; -} - -/** * gfs2_glock_wait - wait on a glock acquisition * @gh: the glock holder * @@ -888,7 +867,7 @@ int gfs2_glock_wait(struct gfs2_holder *gh) unsigned long time1 = jiffies; might_sleep(); - wait_on_bit(&gh->gh_iflags, HIF_WAIT, gfs2_glock_holder_wait, TASK_UNINTERRUPTIBLE); + wait_on_bit(&gh->gh_iflags, HIF_WAIT, TASK_UNINTERRUPTIBLE); if (time_after(jiffies, time1 + HZ)) /* have we waited > a second? */ /* Lengthen the minimum hold time. */ gh->gh_gl->gl_hold_time = min(gh->gh_gl->gl_hold_time + @@ -1128,7 +1107,7 @@ void gfs2_glock_dq_wait(struct gfs2_holder *gh) struct gfs2_glock *gl = gh->gh_gl; gfs2_glock_dq(gh); might_sleep(); - wait_on_bit(&gl->gl_flags, GLF_DEMOTE, gfs2_glock_demote_wait, TASK_UNINTERRUPTIBLE); + wait_on_bit(&gl->gl_flags, GLF_DEMOTE, TASK_UNINTERRUPTIBLE); } /** diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index 4fafea1c9ecf..641383a9c1bb 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -936,12 +936,6 @@ fail: return error; } -static int dlm_recovery_wait(void *word) -{ - schedule(); - return 0; -} - static int control_first_done(struct gfs2_sbd *sdp) { struct lm_lockstruct *ls = &sdp->sd_lockstruct; @@ -976,7 +970,7 @@ restart: fs_info(sdp, "control_first_done wait gen %u\n", start_gen); wait_on_bit(&ls->ls_recover_flags, DFL_DLM_RECOVERY, - dlm_recovery_wait, TASK_UNINTERRUPTIBLE); + TASK_UNINTERRUPTIBLE); goto restart; } diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index bc564c0d6d16..d3eae244076e 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -1024,20 +1024,13 @@ void gfs2_lm_unmount(struct gfs2_sbd *sdp) lm->lm_unmount(sdp); } -static int gfs2_journalid_wait(void *word) -{ - if (signal_pending(current)) - return -EINTR; - schedule(); - return 0; -} - static int wait_on_journal(struct gfs2_sbd *sdp) { if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL) return 0; - return wait_on_bit(&sdp->sd_flags, SDF_NOJOURNALID, gfs2_journalid_wait, TASK_INTERRUPTIBLE); + return wait_on_bit(&sdp->sd_flags, SDF_NOJOURNALID, TASK_INTERRUPTIBLE) + ? -EINTR : 0; } void gfs2_online_uevent(struct gfs2_sbd *sdp) diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 94555d4c5698..573bd3b758fa 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -591,12 +591,6 @@ done: wake_up_bit(&jd->jd_flags, JDF_RECOVERY); } -static int gfs2_recovery_wait(void *word) -{ - schedule(); - return 0; -} - int gfs2_recover_journal(struct gfs2_jdesc *jd, bool wait) { int rv; @@ -609,7 +603,7 @@ int gfs2_recover_journal(struct gfs2_jdesc *jd, bool wait) BUG_ON(!rv); if (wait) - wait_on_bit(&jd->jd_flags, JDF_RECOVERY, gfs2_recovery_wait, + wait_on_bit(&jd->jd_flags, JDF_RECOVERY, TASK_UNINTERRUPTIBLE); return wait ? jd->jd_recover_error : 0; diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 669e92e405ec..a346f56c4c6d 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -864,12 +864,6 @@ static int gfs2_make_fs_ro(struct gfs2_sbd *sdp) return error; } -static int gfs2_umount_recovery_wait(void *word) -{ - schedule(); - return 0; -} - /** * gfs2_put_super - Unmount the filesystem * @sb: The VFS superblock @@ -894,7 +888,7 @@ restart: continue; spin_unlock(&sdp->sd_jindex_spin); wait_on_bit(&jd->jd_flags, JDF_RECOVERY, - gfs2_umount_recovery_wait, TASK_UNINTERRUPTIBLE); + TASK_UNINTERRUPTIBLE); goto restart; } spin_unlock(&sdp->sd_jindex_spin); diff --git a/fs/inode.c b/fs/inode.c index 6eecb7ff0b9a..5938f3928944 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1695,13 +1695,6 @@ int inode_needs_sync(struct inode *inode) } EXPORT_SYMBOL(inode_needs_sync); -int inode_wait(void *word) -{ - schedule(); - return 0; -} -EXPORT_SYMBOL(inode_wait); - /* * If we try to find an inode in the inode hash while it is being * deleted, we have to wait until the filesystem completes its diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 6f0f590cc5a3..5f09370c90a8 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -763,12 +763,6 @@ static void warn_dirty_buffer(struct buffer_head *bh) bdevname(bh->b_bdev, b), (unsigned long long)bh->b_blocknr); } -static int sleep_on_shadow_bh(void *word) -{ - io_schedule(); - return 0; -} - /* * If the buffer is already part of the current transaction, then there * is nothing we need to do. If it is already part of a prior @@ -906,8 +900,8 @@ repeat: if (buffer_shadow(bh)) { JBUFFER_TRACE(jh, "on shadow: sleep"); jbd_unlock_bh_state(bh); - wait_on_bit(&bh->b_state, BH_Shadow, - sleep_on_shadow_bh, TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&bh->b_state, BH_Shadow, + TASK_UNINTERRUPTIBLE); goto repeat; } diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 1812f026960c..daa8e7514eae 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -306,11 +306,9 @@ static struct nsm_handle *nsm_lookup_priv(const struct nsm_private *priv) static void nsm_init_private(struct nsm_handle *nsm) { u64 *p = (u64 *)&nsm->sm_priv.data; - struct timespec ts; s64 ns; - ktime_get_ts(&ts); - ns = timespec_to_ns(&ts); + ns = ktime_get_ns(); put_unaligned(ns, p); put_unaligned((unsigned long)nsm, p + 1); } diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 4042ff58fe3f..524dd80d1898 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -361,8 +361,8 @@ start: * Prevent starvation issues if someone is doing a consistency * sync-to-disk */ - ret = wait_on_bit(&NFS_I(mapping->host)->flags, NFS_INO_FLUSHING, - nfs_wait_bit_killable, TASK_KILLABLE); + ret = wait_on_bit_action(&NFS_I(mapping->host)->flags, NFS_INO_FLUSHING, + nfs_wait_bit_killable, TASK_KILLABLE); if (ret) return ret; diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c index 48f8dcdb75db..8540516f4d71 100644 --- a/fs/nfs/filelayout/filelayoutdev.c +++ b/fs/nfs/filelayout/filelayoutdev.c @@ -783,8 +783,8 @@ nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j) static void nfs4_wait_ds_connect(struct nfs4_pnfs_ds *ds) { might_sleep(); - wait_on_bit(&ds->ds_state, NFS4DS_CONNECTING, - nfs_wait_bit_killable, TASK_KILLABLE); + wait_on_bit_action(&ds->ds_state, NFS4DS_CONNECTING, + nfs_wait_bit_killable, TASK_KILLABLE); } static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 147fd17e7920..432b6c4bea47 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -75,7 +75,7 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr) * nfs_wait_bit_killable - helper for functions that are sleeping on bit locks * @word: long word containing the bit lock */ -int nfs_wait_bit_killable(void *word) +int nfs_wait_bit_killable(struct wait_bit_key *key) { if (fatal_signal_pending(current)) return -ERESTARTSYS; @@ -1083,8 +1083,8 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping) * the bit lock here if it looks like we're going to be doing that. */ for (;;) { - ret = wait_on_bit(bitlock, NFS_INO_INVALIDATING, - nfs_wait_bit_killable, TASK_KILLABLE); + ret = wait_on_bit_action(bitlock, NFS_INO_INVALIDATING, + nfs_wait_bit_killable, TASK_KILLABLE); if (ret) goto out; spin_lock(&inode->i_lock); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 2f19e8392eb3..c2d6cf17b58d 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -348,7 +348,7 @@ extern int nfs_drop_inode(struct inode *); extern void nfs_clear_inode(struct inode *); extern void nfs_evict_inode(struct inode *); void nfs_zap_acl_cache(struct inode *inode); -extern int nfs_wait_bit_killable(void *word); +extern int nfs_wait_bit_killable(struct wait_bit_key *key); /* super.c */ extern const struct super_operations nfs_sops; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index a770c8e469a7..a043f618cd5a 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1236,8 +1236,8 @@ int nfs4_wait_clnt_recover(struct nfs_client *clp) might_sleep(); atomic_inc(&clp->cl_count); - res = wait_on_bit(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING, - nfs_wait_bit_killable, TASK_KILLABLE); + res = wait_on_bit_action(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING, + nfs_wait_bit_killable, TASK_KILLABLE); if (res) goto out; if (clp->cl_cons_state < 0) diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 9425118e91d7..ba491926df5f 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -115,7 +115,7 @@ __nfs_iocounter_wait(struct nfs_io_counter *c) set_bit(NFS_IO_INPROGRESS, &c->flags); if (atomic_read(&c->io_count) == 0) break; - ret = nfs_wait_bit_killable(&c->flags); + ret = nfs_wait_bit_killable(&q.key); } while (atomic_read(&c->io_count) != 0); finish_wait(wq, &q.wait); return ret; @@ -136,12 +136,6 @@ nfs_iocounter_wait(struct nfs_io_counter *c) return __nfs_iocounter_wait(c); } -static int nfs_wait_bit_uninterruptible(void *word) -{ - io_schedule(); - return 0; -} - /* * nfs_page_group_lock - lock the head of the page group * @req - request in group that is to be locked @@ -160,7 +154,6 @@ nfs_page_group_lock(struct nfs_page *req, bool wait) do { ret = wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK, - nfs_wait_bit_uninterruptible, TASK_UNINTERRUPTIBLE); } while (wait && ret != 0); @@ -443,9 +436,8 @@ void nfs_release_request(struct nfs_page *req) int nfs_wait_on_request(struct nfs_page *req) { - return wait_on_bit(&req->wb_flags, PG_BUSY, - nfs_wait_bit_uninterruptible, - TASK_UNINTERRUPTIBLE); + return wait_on_bit_io(&req->wb_flags, PG_BUSY, + TASK_UNINTERRUPTIBLE); } /* diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 4e853157fecc..a3851debf8a2 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1831,7 +1831,7 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync) if (test_and_set_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags)) { if (!sync) goto out; - status = wait_on_bit_lock(&nfsi->flags, + status = wait_on_bit_lock_action(&nfsi->flags, NFS_INO_LAYOUTCOMMITTING, nfs_wait_bit_killable, TASK_KILLABLE); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 1065de26190b..e3b5cf28bdc5 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -644,7 +644,7 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc) int err; /* Stop dirtying of new pages while we sync */ - err = wait_on_bit_lock(bitlock, NFS_INO_FLUSHING, + err = wait_on_bit_lock_action(bitlock, NFS_INO_FLUSHING, nfs_wait_bit_killable, TASK_KILLABLE); if (err) goto out_err; @@ -1711,7 +1711,7 @@ int nfs_commit_inode(struct inode *inode, int how) return error; if (!may_wait) goto out_mark_dirty; - error = wait_on_bit(&NFS_I(inode)->flags, + error = wait_on_bit_action(&NFS_I(inode)->flags, NFS_INO_COMMIT, nfs_wait_bit_killable, TASK_KILLABLE); diff --git a/fs/proc/array.c b/fs/proc/array.c index 3e1290b0492e..cd3653e4f35c 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -464,13 +464,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, priority = task_prio(task); nice = task_nice(task); - /* Temporary variable needed for gcc-2.96 */ - /* convert timespec -> nsec*/ - start_time = - (unsigned long long)task->real_start_time.tv_sec * NSEC_PER_SEC - + task->real_start_time.tv_nsec; /* convert nsec -> ticks */ - start_time = nsec_to_clock_t(start_time); + start_time = nsec_to_clock_t(task->real_start_time); seq_printf(m, "%d (%s) %c", pid_nr_ns(pid, ns), tcomm, state); seq_put_decimal_ll(m, ' ', ppid); diff --git a/fs/timerfd.c b/fs/timerfd.c index 0013142c0475..80c350216ea8 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -35,8 +35,9 @@ struct timerfd_ctx { ktime_t moffs; wait_queue_head_t wqh; u64 ticks; - int expired; int clockid; + short unsigned expired; + short unsigned settime_flags; /* to show in fdinfo */ struct rcu_head rcu; struct list_head clist; bool might_cancel; @@ -92,7 +93,7 @@ static enum alarmtimer_restart timerfd_alarmproc(struct alarm *alarm, */ void timerfd_clock_was_set(void) { - ktime_t moffs = ktime_get_monotonic_offset(); + ktime_t moffs = ktime_mono_to_real((ktime_t){ .tv64 = 0 }); struct timerfd_ctx *ctx; unsigned long flags; @@ -125,7 +126,7 @@ static bool timerfd_canceled(struct timerfd_ctx *ctx) { if (!ctx->might_cancel || ctx->moffs.tv64 != KTIME_MAX) return false; - ctx->moffs = ktime_get_monotonic_offset(); + ctx->moffs = ktime_mono_to_real((ktime_t){ .tv64 = 0 }); return true; } @@ -196,6 +197,8 @@ static int timerfd_setup(struct timerfd_ctx *ctx, int flags, if (timerfd_canceled(ctx)) return -ECANCELED; } + + ctx->settime_flags = flags & TFD_SETTIME_FLAGS; return 0; } @@ -284,11 +287,77 @@ static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count, return res; } +#ifdef CONFIG_PROC_FS +static int timerfd_show(struct seq_file *m, struct file *file) +{ + struct timerfd_ctx *ctx = file->private_data; + struct itimerspec t; + + spin_lock_irq(&ctx->wqh.lock); + t.it_value = ktime_to_timespec(timerfd_get_remaining(ctx)); + t.it_interval = ktime_to_timespec(ctx->tintv); + spin_unlock_irq(&ctx->wqh.lock); + + return seq_printf(m, + "clockid: %d\n" + "ticks: %llu\n" + "settime flags: 0%o\n" + "it_value: (%llu, %llu)\n" + "it_interval: (%llu, %llu)\n", + ctx->clockid, (unsigned long long)ctx->ticks, + ctx->settime_flags, + (unsigned long long)t.it_value.tv_sec, + (unsigned long long)t.it_value.tv_nsec, + (unsigned long long)t.it_interval.tv_sec, + (unsigned long long)t.it_interval.tv_nsec); +} +#else +#define timerfd_show NULL +#endif + +#ifdef CONFIG_CHECKPOINT_RESTORE +static long timerfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct timerfd_ctx *ctx = file->private_data; + int ret = 0; + + switch (cmd) { + case TFD_IOC_SET_TICKS: { + u64 ticks; + + if (copy_from_user(&ticks, (u64 __user *)arg, sizeof(ticks))) + return -EFAULT; + if (!ticks) + return -EINVAL; + + spin_lock_irq(&ctx->wqh.lock); + if (!timerfd_canceled(ctx)) { + ctx->ticks = ticks; + if (ticks) + wake_up_locked(&ctx->wqh); + } else + ret = -ECANCELED; + spin_unlock_irq(&ctx->wqh.lock); + break; + } + default: + ret = -ENOTTY; + break; + } + + return ret; +} +#else +#define timerfd_ioctl NULL +#endif + static const struct file_operations timerfd_fops = { .release = timerfd_release, .poll = timerfd_poll, .read = timerfd_read, .llseek = noop_llseek, + .show_fdinfo = timerfd_show, + .unlocked_ioctl = timerfd_ioctl, }; static int timerfd_fget(int fd, struct fd *p) @@ -336,7 +405,7 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags) else hrtimer_init(&ctx->t.tmr, clockid, HRTIMER_MODE_ABS); - ctx->moffs = ktime_get_monotonic_offset(); + ctx->moffs = ktime_mono_to_real((ktime_t){ .tv64 = 0 }); ufd = anon_inode_getfd("[timerfd]", &timerfd_fops, ctx, O_RDWR | (flags & TFD_SHARED_FCNTL_FLAGS)); diff --git a/include/acpi/apei.h b/include/acpi/apei.h index 04f349d8da73..76284bb560a6 100644 --- a/include/acpi/apei.h +++ b/include/acpi/apei.h @@ -42,5 +42,9 @@ ssize_t erst_read(u64 record_id, struct cper_record_header *record, size_t buflen); int erst_clear(u64 record_id); +int arch_apei_enable_cmcff(struct acpi_hest_header *hest_hdr, void *data); +void arch_apei_report_mem_error(int sev, struct cper_sec_mem_err *mem_err); +void arch_apei_flush_tlb_one(unsigned long addr); + #endif #endif diff --git a/include/clocksource/pxa.h b/include/clocksource/pxa.h new file mode 100644 index 000000000000..1efbe5a66958 --- /dev/null +++ b/include/clocksource/pxa.h @@ -0,0 +1,18 @@ +/* + * PXA clocksource, clockevents, and OST interrupt handlers. + * + * Copyright (C) 2014 Robert Jarzmik + * + * 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 of the License. + * + */ + +#ifndef _CLOCKSOURCE_PXA_H +#define _CLOCKSOURCE_PXA_H + +extern void pxa_timer_nodt_init(int irq, void __iomem *base, + unsigned long clock_tick_rate); + +#endif diff --git a/include/linux/aer.h b/include/linux/aer.h index 4dbaa7081530..c826d1c28f9c 100644 --- a/include/linux/aer.h +++ b/include/linux/aer.h @@ -11,6 +11,8 @@ #define AER_FATAL 1 #define AER_CORRECTABLE 2 +struct pci_dev; + struct aer_header_log_regs { unsigned int dw0; unsigned int dw1; diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index a16b497d5159..653f0e2b6ca9 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -162,7 +162,6 @@ extern u64 timecounter_cyc2time(struct timecounter *tc, * @archdata: arch-specific data * @suspend: suspend function for the clocksource, if necessary * @resume: resume function for the clocksource, if necessary - * @cycle_last: most recent cycle counter value seen by ::read() * @owner: module reference, must be set by clocksource in modules */ struct clocksource { @@ -171,7 +170,6 @@ struct clocksource { * clocksource itself is cacheline aligned. */ cycle_t (*read)(struct clocksource *cs); - cycle_t cycle_last; cycle_t mask; u32 mult; u32 shift; diff --git a/include/linux/cper.h b/include/linux/cper.h index 2fc0ec3d89cc..76abba4b238e 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -22,6 +22,7 @@ #define LINUX_CPER_H #include <linux/uuid.h> +#include <linux/trace_seq.h> /* CPER record signature and the size */ #define CPER_SIG_RECORD "CPER" @@ -36,6 +37,13 @@ #define CPER_RECORD_REV 0x0100 /* + * CPER record length contains the CPER fields which are relevant for further + * handling of a memory error in userspace (we don't carry all the fields + * defined in the UEFI spec because some of them don't make any sense.) + * Currently, a length of 256 should be more than enough. + */ +#define CPER_REC_LEN 256 +/* * Severity difinition for error_severity in struct cper_record_header * and section_severity in struct cper_section_descriptor */ @@ -356,6 +364,24 @@ struct cper_sec_mem_err { __u16 mem_dev_handle; /* module handle in UEFI 2.4 */ }; +struct cper_mem_err_compact { + __u64 validation_bits; + __u16 node; + __u16 card; + __u16 module; + __u16 bank; + __u16 device; + __u16 row; + __u16 column; + __u16 bit_pos; + __u64 requestor_id; + __u64 responder_id; + __u64 target_id; + __u16 rank; + __u16 mem_array_handle; + __u16 mem_dev_handle; +}; + struct cper_sec_pcie { __u64 validation_bits; __u32 port_type; @@ -395,7 +421,13 @@ struct cper_sec_pcie { #pragma pack() u64 cper_next_record_id(void); +const char *cper_severity_str(unsigned int); +const char *cper_mem_err_type_str(unsigned int); void cper_print_bits(const char *prefix, unsigned int bits, const char * const strs[], unsigned int strs_size); +void cper_mem_err_pack(const struct cper_sec_mem_err *, + struct cper_mem_err_compact *); +const char *cper_mem_err_unpack(struct trace_seq *, + struct cper_mem_err_compact *); #endif diff --git a/include/linux/efi.h b/include/linux/efi.h index 41bbf8ba4ba8..efc681fd5895 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -20,6 +20,7 @@ #include <linux/ioport.h> #include <linux/pfn.h> #include <linux/pstore.h> +#include <linux/reboot.h> #include <asm/page.h> @@ -521,6 +522,8 @@ typedef efi_status_t efi_query_capsule_caps_t(efi_capsule_header_t **capsules, int *reset_type); typedef efi_status_t efi_query_variable_store_t(u32 attributes, unsigned long size); +void efi_native_runtime_setup(void); + /* * EFI Configuration Table and GUID definitions */ @@ -870,11 +873,13 @@ extern int __init efi_uart_console_only (void); extern void efi_initialize_iomem_resources(struct resource *code_resource, struct resource *data_resource, struct resource *bss_resource); extern void efi_get_time(struct timespec *now); -extern int efi_set_rtc_mmss(const struct timespec *now); extern void efi_reserve_boot_services(void); extern int efi_get_fdt_params(struct efi_fdt_params *params, int verbose); extern struct efi_memory_map memmap; +extern int efi_reboot_quirk_mode; +extern bool efi_poweroff_required(void); + /* Iterate through an efi_memory_map */ #define for_each_efi_memory_desc(m, md) \ for ((md) = (m)->map; \ @@ -916,7 +921,8 @@ extern int __init efi_setup_pcdp_console(char *); #define EFI_RUNTIME_SERVICES 3 /* Can we use runtime services? */ #define EFI_MEMMAP 4 /* Can we use EFI memory map? */ #define EFI_64BIT 5 /* Is the firmware 64-bit? */ -#define EFI_ARCH_1 6 /* First arch-specific bit */ +#define EFI_PARAVIRT 6 /* Access is via a paravirt interface */ +#define EFI_ARCH_1 7 /* First arch-specific bit */ #ifdef CONFIG_EFI /* @@ -926,11 +932,14 @@ static inline bool efi_enabled(int feature) { return test_bit(feature, &efi.flags) != 0; } +extern void efi_reboot(enum reboot_mode reboot_mode, const char *__unused); #else static inline bool efi_enabled(int feature) { return false; } +static inline void +efi_reboot(enum reboot_mode reboot_mode, const char *__unused) {} #endif /* @@ -1031,12 +1040,8 @@ struct efivar_operations { struct efivars { /* * ->lock protects two things: - * 1) ->list - adds, removals, reads, writes - * 2) ops.[gs]et_variable() calls. - * It must not be held when creating sysfs entries or calling kmalloc. - * ops.get_next_variable() is only called from register_efivars() - * or efivar_update_sysfs_entries(), - * which is protected by the BKL, so that path is safe. + * 1) efivarfs_list and efivars_sysfs_list + * 2) ->ops calls */ spinlock_t lock; struct kset *kset; @@ -1161,4 +1166,46 @@ static inline void efi_runtime_map_setup(void *map, int nr_entries, u32 desc_size) {} #endif +/* prototypes shared between arch specific and generic stub code */ + +#define pr_efi(sys_table, msg) efi_printk(sys_table, "EFI stub: "msg) +#define pr_efi_err(sys_table, msg) efi_printk(sys_table, "EFI stub: ERROR: "msg) + +void efi_printk(efi_system_table_t *sys_table_arg, char *str); + +void efi_free(efi_system_table_t *sys_table_arg, unsigned long size, + unsigned long addr); + +char *efi_convert_cmdline(efi_system_table_t *sys_table_arg, + efi_loaded_image_t *image, int *cmd_line_len); + +efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg, + efi_memory_desc_t **map, + unsigned long *map_size, + unsigned long *desc_size, + u32 *desc_ver, + unsigned long *key_ptr); + +efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg, + unsigned long size, unsigned long align, + unsigned long *addr); + +efi_status_t efi_high_alloc(efi_system_table_t *sys_table_arg, + unsigned long size, unsigned long align, + unsigned long *addr, unsigned long max); + +efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg, + unsigned long *image_addr, + unsigned long image_size, + unsigned long alloc_size, + unsigned long preferred_addr, + unsigned long alignment); + +efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg, + efi_loaded_image_t *image, + char *cmd_line, char *option_string, + unsigned long max_addr, + unsigned long *load_addr, + unsigned long *load_size); + #endif /* _LINUX_EFI_H */ diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index e7a8d3fa91d5..a036d058a249 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -165,6 +165,7 @@ enum hrtimer_base_type { * struct hrtimer_cpu_base - the per cpu clock bases * @lock: lock protecting the base and associated clock bases * and timers + * @cpu: cpu number * @active_bases: Bitfield to mark bases with active timers * @clock_was_set: Indicates that clock was set from irq context. * @expires_next: absolute time of the next event which was scheduled @@ -179,6 +180,7 @@ enum hrtimer_base_type { */ struct hrtimer_cpu_base { raw_spinlock_t lock; + unsigned int cpu; unsigned int active_bases; unsigned int clock_was_set; #ifdef CONFIG_HIGH_RES_TIMERS @@ -324,14 +326,6 @@ static inline void timerfd_clock_was_set(void) { } #endif extern void hrtimers_resume(void); -extern ktime_t ktime_get(void); -extern ktime_t ktime_get_real(void); -extern ktime_t ktime_get_boottime(void); -extern ktime_t ktime_get_monotonic_offset(void); -extern ktime_t ktime_get_clocktai(void); -extern ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot, - ktime_t *offs_tai); - DECLARE_PER_CPU(struct tick_device, tick_cpu_device); @@ -452,12 +446,6 @@ extern void hrtimer_run_pending(void); /* Bootup initialization: */ extern void __init hrtimers_init(void); -#if BITS_PER_LONG < 64 -extern u64 ktime_divns(const ktime_t kt, s64 div); -#else /* BITS_PER_LONG < 64 */ -# define ktime_divns(kt, div) (u64)((kt).tv64 / (div)) -#endif - /* Show pending timers: */ extern void sysrq_timer_list_show(void); diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index ccde91725f98..15dc6bc2bdd2 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -277,14 +277,7 @@ static inline bool iio_channel_has_info(const struct iio_chan_spec *chan, **/ static inline s64 iio_get_time_ns(void) { - struct timespec ts; - /* - * calls getnstimeofday. - * If hrtimers then up to ns accurate, if not microsecond. - */ - ktime_get_real_ts(&ts); - - return timespec_to_ns(&ts); + return ktime_get_real_ns(); } /* Device operating modes */ diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 6df7f9fe0d01..2bb4c4f3531a 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -102,12 +102,6 @@ extern struct group_info init_groups; #define INIT_IDS #endif -#ifdef CONFIG_RCU_BOOST -#define INIT_TASK_RCU_BOOST() \ - .rcu_boost_mutex = NULL, -#else -#define INIT_TASK_RCU_BOOST() -#endif #ifdef CONFIG_TREE_PREEMPT_RCU #define INIT_TASK_RCU_TREE_PREEMPT() \ .rcu_blocked_node = NULL, @@ -119,8 +113,7 @@ extern struct group_info init_groups; .rcu_read_lock_nesting = 0, \ .rcu_read_unlock_special = 0, \ .rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry), \ - INIT_TASK_RCU_TREE_PREEMPT() \ - INIT_TASK_RCU_BOOST() + INIT_TASK_RCU_TREE_PREEMPT() #else #define INIT_TASK_RCU_PREEMPT(tsk) #endif diff --git a/include/linux/io.h b/include/linux/io.h index b76e6e545806..d5fc9b8d8b03 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -58,6 +58,8 @@ static inline void devm_ioport_unmap(struct device *dev, void __iomem *addr) } #endif +#define IOMEM_ERR_PTR(err) (__force void __iomem *)ERR_PTR(err) + void __iomem *devm_ioremap(struct device *dev, resource_size_t offset, unsigned long size); void __iomem *devm_ioremap_nocache(struct device *dev, resource_size_t offset, diff --git a/include/linux/irq.h b/include/linux/irq.h index 0d998d8b01d8..62af59242ddc 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -771,6 +771,8 @@ void irq_gc_eoi(struct irq_data *d); int irq_gc_set_wake(struct irq_data *d, unsigned int on); /* Setup functions for irq_chip_generic */ +int irq_map_generic_chip(struct irq_domain *d, unsigned int virq, + irq_hw_number_t hw_irq); struct irq_chip_generic * irq_alloc_generic_chip(const char *name, int nr_ct, unsigned int irq_base, void __iomem *reg_base, irq_flow_handler_t handler); diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index 19ae05d4b8ec..bf9422c3aefe 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -33,6 +33,11 @@ void init_irq_work(struct irq_work *work, void (*func)(struct irq_work *)) #define DEFINE_IRQ_WORK(name, _f) struct irq_work name = { .func = (_f), } bool irq_work_queue(struct irq_work *work); + +#ifdef CONFIG_SMP +bool irq_work_queue_on(struct irq_work *work, int cpu); +#endif + void irq_work_run(void); void irq_work_sync(struct irq_work *work); diff --git a/include/linux/irqchip/spear-shirq.h b/include/linux/irqchip/spear-shirq.h deleted file mode 100644 index c8be16d213a3..000000000000 --- a/include/linux/irqchip/spear-shirq.h +++ /dev/null @@ -1,64 +0,0 @@ -/* - * SPEAr platform shared irq layer header file - * - * Copyright (C) 2009-2012 ST Microelectronics - * Viresh Kumar <viresh.linux@gmail.com> - * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. - */ - -#ifndef __SPEAR_SHIRQ_H -#define __SPEAR_SHIRQ_H - -#include <linux/irq.h> -#include <linux/types.h> - -/* - * struct shirq_regs: shared irq register configuration - * - * enb_reg: enable register offset - * reset_to_enb: val 1 indicates, we need to clear bit for enabling interrupt - * status_reg: status register offset - * status_reg_mask: status register valid mask - * clear_reg: clear register offset - * reset_to_clear: val 1 indicates, we need to clear bit for clearing interrupt - */ -struct shirq_regs { - u32 enb_reg; - u32 reset_to_enb; - u32 status_reg; - u32 clear_reg; - u32 reset_to_clear; -}; - -/* - * struct spear_shirq: shared irq structure - * - * irq: hardware irq number - * irq_base: base irq in linux domain - * irq_nr: no. of shared interrupts in a particular block - * irq_bit_off: starting bit offset in the status register - * invalid_irq: irq group is currently disabled - * base: base address of shared irq register - * regs: register configuration for shared irq block - */ -struct spear_shirq { - u32 irq; - u32 irq_base; - u32 irq_nr; - u32 irq_bit_off; - int invalid_irq; - void __iomem *base; - struct shirq_regs regs; -}; - -int __init spear300_shirq_of_init(struct device_node *np, - struct device_node *parent); -int __init spear310_shirq_of_init(struct device_node *np, - struct device_node *parent); -int __init spear320_shirq_of_init(struct device_node *np, - struct device_node *parent); - -#endif /* __SPEAR_SHIRQ_H */ diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index c983ed18c332..b0f9d16e48f6 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -172,6 +172,8 @@ extern int irq_domain_associate(struct irq_domain *domain, unsigned int irq, extern void irq_domain_associate_many(struct irq_domain *domain, unsigned int irq_base, irq_hw_number_t hwirq_base, int count); +extern void irq_domain_disassociate(struct irq_domain *domain, + unsigned int irq); extern unsigned int irq_create_mapping(struct irq_domain *host, irq_hw_number_t hwirq); diff --git a/include/linux/ktime.h b/include/linux/ktime.h index de9e46e6bcc9..c9d645ad98ff 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -27,43 +27,19 @@ /* * ktime_t: * - * On 64-bit CPUs a single 64-bit variable is used to store the hrtimers + * A single 64-bit variable is used to store the hrtimers * internal representation of time values in scalar nanoseconds. The * design plays out best on 64-bit CPUs, where most conversions are * NOPs and most arithmetic ktime_t operations are plain arithmetic * operations. * - * On 32-bit CPUs an optimized representation of the timespec structure - * is used to avoid expensive conversions from and to timespecs. The - * endian-aware order of the tv struct members is chosen to allow - * mathematical operations on the tv64 member of the union too, which - * for certain operations produces better code. - * - * For architectures with efficient support for 64/32-bit conversions the - * plain scalar nanosecond based representation can be selected by the - * config switch CONFIG_KTIME_SCALAR. */ union ktime { s64 tv64; -#if BITS_PER_LONG != 64 && !defined(CONFIG_KTIME_SCALAR) - struct { -# ifdef __BIG_ENDIAN - s32 sec, nsec; -# else - s32 nsec, sec; -# endif - } tv; -#endif }; typedef union ktime ktime_t; /* Kill this */ -/* - * ktime_t definitions when using the 64-bit scalar representation: - */ - -#if (BITS_PER_LONG == 64) || defined(CONFIG_KTIME_SCALAR) - /** * ktime_set - Set a ktime_t variable from a seconds/nanoseconds value * @secs: seconds to set @@ -71,13 +47,12 @@ typedef union ktime ktime_t; /* Kill this */ * * Return: The ktime_t representation of the value. */ -static inline ktime_t ktime_set(const long secs, const unsigned long nsecs) +static inline ktime_t ktime_set(const s64 secs, const unsigned long nsecs) { -#if (BITS_PER_LONG == 64) if (unlikely(secs >= KTIME_SEC_MAX)) return (ktime_t){ .tv64 = KTIME_MAX }; -#endif - return (ktime_t) { .tv64 = (s64)secs * NSEC_PER_SEC + (s64)nsecs }; + + return (ktime_t) { .tv64 = secs * NSEC_PER_SEC + (s64)nsecs }; } /* Subtract two ktime_t variables. rem = lhs -rhs: */ @@ -108,6 +83,12 @@ static inline ktime_t timespec_to_ktime(struct timespec ts) return ktime_set(ts.tv_sec, ts.tv_nsec); } +/* convert a timespec64 to ktime_t format: */ +static inline ktime_t timespec64_to_ktime(struct timespec64 ts) +{ + return ktime_set(ts.tv_sec, ts.tv_nsec); +} + /* convert a timeval to ktime_t format: */ static inline ktime_t timeval_to_ktime(struct timeval tv) { @@ -117,159 +98,15 @@ static inline ktime_t timeval_to_ktime(struct timeval tv) /* Map the ktime_t to timespec conversion to ns_to_timespec function */ #define ktime_to_timespec(kt) ns_to_timespec((kt).tv64) +/* Map the ktime_t to timespec conversion to ns_to_timespec function */ +#define ktime_to_timespec64(kt) ns_to_timespec64((kt).tv64) + /* Map the ktime_t to timeval conversion to ns_to_timeval function */ #define ktime_to_timeval(kt) ns_to_timeval((kt).tv64) /* Convert ktime_t to nanoseconds - NOP in the scalar storage format: */ #define ktime_to_ns(kt) ((kt).tv64) -#else /* !((BITS_PER_LONG == 64) || defined(CONFIG_KTIME_SCALAR)) */ - -/* - * Helper macros/inlines to get the ktime_t math right in the timespec - * representation. The macros are sometimes ugly - their actual use is - * pretty okay-ish, given the circumstances. We do all this for - * performance reasons. The pure scalar nsec_t based code was nice and - * simple, but created too many 64-bit / 32-bit conversions and divisions. - * - * Be especially aware that negative values are represented in a way - * that the tv.sec field is negative and the tv.nsec field is greater - * or equal to zero but less than nanoseconds per second. This is the - * same representation which is used by timespecs. - * - * tv.sec < 0 and 0 >= tv.nsec < NSEC_PER_SEC - */ - -/* Set a ktime_t variable to a value in sec/nsec representation: */ -static inline ktime_t ktime_set(const long secs, const unsigned long nsecs) -{ - return (ktime_t) { .tv = { .sec = secs, .nsec = nsecs } }; -} - -/** - * ktime_sub - subtract two ktime_t variables - * @lhs: minuend - * @rhs: subtrahend - * - * Return: The remainder of the subtraction. - */ -static inline ktime_t ktime_sub(const ktime_t lhs, const ktime_t rhs) -{ - ktime_t res; - - res.tv64 = lhs.tv64 - rhs.tv64; - if (res.tv.nsec < 0) - res.tv.nsec += NSEC_PER_SEC; - - return res; -} - -/** - * ktime_add - add two ktime_t variables - * @add1: addend1 - * @add2: addend2 - * - * Return: The sum of @add1 and @add2. - */ -static inline ktime_t ktime_add(const ktime_t add1, const ktime_t add2) -{ - ktime_t res; - - res.tv64 = add1.tv64 + add2.tv64; - /* - * performance trick: the (u32) -NSEC gives 0x00000000Fxxxxxxx - * so we subtract NSEC_PER_SEC and add 1 to the upper 32 bit. - * - * it's equivalent to: - * tv.nsec -= NSEC_PER_SEC - * tv.sec ++; - */ - if (res.tv.nsec >= NSEC_PER_SEC) - res.tv64 += (u32)-NSEC_PER_SEC; - - return res; -} - -/** - * ktime_add_ns - Add a scalar nanoseconds value to a ktime_t variable - * @kt: addend - * @nsec: the scalar nsec value to add - * - * Return: The sum of @kt and @nsec in ktime_t format. - */ -extern ktime_t ktime_add_ns(const ktime_t kt, u64 nsec); - -/** - * ktime_sub_ns - Subtract a scalar nanoseconds value from a ktime_t variable - * @kt: minuend - * @nsec: the scalar nsec value to subtract - * - * Return: The subtraction of @nsec from @kt in ktime_t format. - */ -extern ktime_t ktime_sub_ns(const ktime_t kt, u64 nsec); - -/** - * timespec_to_ktime - convert a timespec to ktime_t format - * @ts: the timespec variable to convert - * - * Return: A ktime_t variable with the converted timespec value. - */ -static inline ktime_t timespec_to_ktime(const struct timespec ts) -{ - return (ktime_t) { .tv = { .sec = (s32)ts.tv_sec, - .nsec = (s32)ts.tv_nsec } }; -} - -/** - * timeval_to_ktime - convert a timeval to ktime_t format - * @tv: the timeval variable to convert - * - * Return: A ktime_t variable with the converted timeval value. - */ -static inline ktime_t timeval_to_ktime(const struct timeval tv) -{ - return (ktime_t) { .tv = { .sec = (s32)tv.tv_sec, - .nsec = (s32)(tv.tv_usec * - NSEC_PER_USEC) } }; -} - -/** - * ktime_to_timespec - convert a ktime_t variable to timespec format - * @kt: the ktime_t variable to convert - * - * Return: The timespec representation of the ktime value. - */ -static inline struct timespec ktime_to_timespec(const ktime_t kt) -{ - return (struct timespec) { .tv_sec = (time_t) kt.tv.sec, - .tv_nsec = (long) kt.tv.nsec }; -} - -/** - * ktime_to_timeval - convert a ktime_t variable to timeval format - * @kt: the ktime_t variable to convert - * - * Return: The timeval representation of the ktime value. - */ -static inline struct timeval ktime_to_timeval(const ktime_t kt) -{ - return (struct timeval) { - .tv_sec = (time_t) kt.tv.sec, - .tv_usec = (suseconds_t) (kt.tv.nsec / NSEC_PER_USEC) }; -} - -/** - * ktime_to_ns - convert a ktime_t variable to scalar nanoseconds - * @kt: the ktime_t variable to convert - * - * Return: The scalar nanoseconds representation of @kt. - */ -static inline s64 ktime_to_ns(const ktime_t kt) -{ - return (s64) kt.tv.sec * NSEC_PER_SEC + kt.tv.nsec; -} - -#endif /* !((BITS_PER_LONG == 64) || defined(CONFIG_KTIME_SCALAR)) */ /** * ktime_equal - Compares two ktime_t variables to see if they are equal @@ -328,16 +165,20 @@ static inline bool ktime_before(const ktime_t cmp1, const ktime_t cmp2) return ktime_compare(cmp1, cmp2) < 0; } +#if BITS_PER_LONG < 64 +extern u64 ktime_divns(const ktime_t kt, s64 div); +#else /* BITS_PER_LONG < 64 */ +# define ktime_divns(kt, div) (u64)((kt).tv64 / (div)) +#endif + static inline s64 ktime_to_us(const ktime_t kt) { - struct timeval tv = ktime_to_timeval(kt); - return (s64) tv.tv_sec * USEC_PER_SEC + tv.tv_usec; + return ktime_divns(kt, NSEC_PER_USEC); } static inline s64 ktime_to_ms(const ktime_t kt) { - struct timeval tv = ktime_to_timeval(kt); - return (s64) tv.tv_sec * MSEC_PER_SEC + tv.tv_usec / USEC_PER_MSEC; + return ktime_divns(kt, NSEC_PER_MSEC); } static inline s64 ktime_us_delta(const ktime_t later, const ktime_t earlier) @@ -381,6 +222,25 @@ static inline __must_check bool ktime_to_timespec_cond(const ktime_t kt, } } +/** + * ktime_to_timespec64_cond - convert a ktime_t variable to timespec64 + * format only if the variable contains data + * @kt: the ktime_t variable to convert + * @ts: the timespec variable to store the result in + * + * Return: %true if there was a successful conversion, %false if kt was 0. + */ +static inline __must_check bool ktime_to_timespec64_cond(const ktime_t kt, + struct timespec64 *ts) +{ + if (kt.tv64) { + *ts = ktime_to_timespec64(kt); + return true; + } else { + return false; + } +} + /* * The resolution of the clocks. The resolution value is returned in * the clock_getres() system call to give application programmers an @@ -390,12 +250,6 @@ static inline __must_check bool ktime_to_timespec_cond(const ktime_t kt, #define LOW_RES_NSEC TICK_NSEC #define KTIME_LOW_RES (ktime_t){ .tv64 = LOW_RES_NSEC } -/* Get the monotonic time in timespec format: */ -extern void ktime_get_ts(struct timespec *ts); - -/* Get the real (wall-) time in timespec format: */ -#define ktime_get_real_ts(ts) getnstimeofday(ts) - static inline ktime_t ns_to_ktime(u64 ns) { static const ktime_t ktime_zero = { .tv64 = 0 }; @@ -410,4 +264,6 @@ static inline ktime_t ms_to_ktime(u64 ms) return ktime_add_ms(ktime_zero, ms); } +# include <linux/timekeeping.h> + #endif diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 9f3a5476bb71..b88e9b46d957 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -608,8 +608,8 @@ struct mlx5_cmd_work_ent { int page_queue; u8 status; u8 token; - struct timespec ts1; - struct timespec ts2; + u64 ts1; + u64 ts2; u16 op; }; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 96c5750e3110..796deac19fcf 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -516,4 +516,12 @@ struct vm_special_mapping struct page **pages; }; +enum tlb_flush_reason { + TLB_FLUSH_ON_TASK_SWITCH, + TLB_REMOTE_SHOOTDOWN, + TLB_LOCAL_SHOOTDOWN, + TLB_LOCAL_MM_SHOOTDOWN, + NR_TLB_FLUSH_REASONS, +}; + #endif /* _LINUX_MM_TYPES_H */ diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 42aa9b9ecd5f..8d5535c58cc2 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -176,8 +176,4 @@ extern void mutex_unlock(struct mutex *lock); extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); -#ifndef arch_mutex_cpu_relax -# define arch_mutex_cpu_relax() cpu_relax() -#endif - #endif /* __LINUX_MUTEX_H */ diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 447775ee2c4b..1d2a6ab6b8bb 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -63,4 +63,8 @@ extern int proc_dowatchdog(struct ctl_table *, int , void __user *, size_t *, loff_t *); #endif +#ifdef CONFIG_HAVE_ACPI_APEI_NMI +#include <asm/nmi.h> +#endif + #endif diff --git a/include/linux/of_address.h b/include/linux/of_address.h index c13b8782a4eb..fb7b7221e063 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -109,7 +109,12 @@ static inline bool of_dma_is_coherent(struct device_node *np) extern int of_address_to_resource(struct device_node *dev, int index, struct resource *r); void __iomem *of_iomap(struct device_node *node, int index); +void __iomem *of_io_request_and_map(struct device_node *device, + int index, char *name); #else + +#include <linux/io.h> + static inline int of_address_to_resource(struct device_node *dev, int index, struct resource *r) { @@ -120,6 +125,12 @@ static inline void __iomem *of_iomap(struct device_node *device, int index) { return NULL; } + +static inline void __iomem *of_io_request_and_map(struct device_node *device, + int index, char *name) +{ + return IOMEM_ERR_PTR(-EINVAL); +} #endif #if defined(CONFIG_OF_ADDRESS) && defined(CONFIG_PCI) diff --git a/include/linux/ras.h b/include/linux/ras.h new file mode 100644 index 000000000000..2aceeafd6fe5 --- /dev/null +++ b/include/linux/ras.h @@ -0,0 +1,14 @@ +#ifndef __RAS_H__ +#define __RAS_H__ + +#ifdef CONFIG_DEBUG_FS +int ras_userspace_consumers(void); +void ras_debugfs_init(void); +int ras_add_daemon_trace(void); +#else +static inline int ras_userspace_consumers(void) { return 0; } +static inline void ras_debugfs_init(void) { return; } +static inline int ras_add_daemon_trace(void) { return 0; } +#endif + +#endif diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 6a94cc8b1ca0..d231aa17b1d7 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -826,15 +826,14 @@ static inline void rcu_preempt_sleep_check(void) * read-side critical section that would block in a !PREEMPT kernel. * But if you want the full story, read on! * - * In non-preemptible RCU implementations (TREE_RCU and TINY_RCU), it - * is illegal to block while in an RCU read-side critical section. In - * preemptible RCU implementations (TREE_PREEMPT_RCU and TINY_PREEMPT_RCU) - * in CONFIG_PREEMPT kernel builds, RCU read-side critical sections may - * be preempted, but explicit blocking is illegal. Finally, in preemptible - * RCU implementations in real-time (with -rt patchset) kernel builds, - * RCU read-side critical sections may be preempted and they may also - * block, but only when acquiring spinlocks that are subject to priority - * inheritance. + * In non-preemptible RCU implementations (TREE_RCU and TINY_RCU), + * it is illegal to block while in an RCU read-side critical section. + * In preemptible RCU implementations (TREE_PREEMPT_RCU) in CONFIG_PREEMPT + * kernel builds, RCU read-side critical sections may be preempted, + * but explicit blocking is illegal. Finally, in preemptible RCU + * implementations in real-time (with -rt patchset) kernel builds, RCU + * read-side critical sections may be preempted and they may also block, but + * only when acquiring spinlocks that are subject to priority inheritance. */ static inline void rcu_read_lock(void) { @@ -858,6 +857,34 @@ static inline void rcu_read_lock(void) /** * rcu_read_unlock() - marks the end of an RCU read-side critical section. * + * In most situations, rcu_read_unlock() is immune from deadlock. + * However, in kernels built with CONFIG_RCU_BOOST, rcu_read_unlock() + * is responsible for deboosting, which it does via rt_mutex_unlock(). + * Unfortunately, this function acquires the scheduler's runqueue and + * priority-inheritance spinlocks. This means that deadlock could result + * if the caller of rcu_read_unlock() already holds one of these locks or + * any lock that is ever acquired while holding them. + * + * That said, RCU readers are never priority boosted unless they were + * preempted. Therefore, one way to avoid deadlock is to make sure + * that preemption never happens within any RCU read-side critical + * section whose outermost rcu_read_unlock() is called with one of + * rt_mutex_unlock()'s locks held. Such preemption can be avoided in + * a number of ways, for example, by invoking preempt_disable() before + * critical section's outermost rcu_read_lock(). + * + * Given that the set of locks acquired by rt_mutex_unlock() might change + * at any time, a somewhat more future-proofed approach is to make sure + * that that preemption never happens within any RCU read-side critical + * section whose outermost rcu_read_unlock() is called with irqs disabled. + * This approach relies on the fact that rt_mutex_unlock() currently only + * acquires irq-disabled locks. + * + * The second of these two approaches is best in most situations, + * however, the first approach can also be useful, at least to those + * developers willing to keep abreast of the set of locks acquired by + * rt_mutex_unlock(). + * * See rcu_read_lock() for more information. */ static inline void rcu_read_unlock(void) diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 3aed8d737e1a..1abba5ce2a2f 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -90,11 +90,9 @@ extern void __rt_mutex_init(struct rt_mutex *lock, const char *name); extern void rt_mutex_destroy(struct rt_mutex *lock); extern void rt_mutex_lock(struct rt_mutex *lock); -extern int rt_mutex_lock_interruptible(struct rt_mutex *lock, - int detect_deadlock); +extern int rt_mutex_lock_interruptible(struct rt_mutex *lock); extern int rt_mutex_timed_lock(struct rt_mutex *lock, - struct hrtimer_sleeper *timeout, - int detect_deadlock); + struct hrtimer_sleeper *timeout); extern int rt_mutex_trylock(struct rt_mutex *lock); diff --git a/include/linux/sched.h b/include/linux/sched.h index 45cec6b70eaf..7c19d552dc3f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -813,7 +813,7 @@ struct task_delay_info { * associated with the operation is added to XXX_delay. * XXX_delay contains the accumulated delay time in nanoseconds. */ - struct timespec blkio_start, blkio_end; /* Shared by blkio, swapin */ + u64 blkio_start; /* Shared by blkio, swapin */ u64 blkio_delay; /* wait for sync block io completion */ u64 swapin_delay; /* wait for swapin block io completion */ u32 blkio_count; /* total count of the number of sync block */ @@ -821,7 +821,7 @@ struct task_delay_info { u32 swapin_count; /* total count of the number of swapin block */ /* io operations performed */ - struct timespec freepages_start, freepages_end; + u64 freepages_start; u64 freepages_delay; /* wait for memory reclaim */ u32 freepages_count; /* total count of memory reclaim */ }; @@ -1270,9 +1270,6 @@ struct task_struct { #ifdef CONFIG_TREE_PREEMPT_RCU struct rcu_node *rcu_blocked_node; #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ -#ifdef CONFIG_RCU_BOOST - struct rt_mutex *rcu_boost_mutex; -#endif /* #ifdef CONFIG_RCU_BOOST */ #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) struct sched_info sched_info; @@ -1366,8 +1363,8 @@ struct task_struct { } vtime_snap_whence; #endif unsigned long nvcsw, nivcsw; /* context switch counts */ - struct timespec start_time; /* monotonic time */ - struct timespec real_start_time; /* boot based time */ + u64 start_time; /* monotonic time in nsec */ + u64 real_start_time; /* boot based time in nsec */ /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */ unsigned long min_flt, maj_flt; @@ -1439,8 +1436,6 @@ struct task_struct { struct rb_node *pi_waiters_leftmost; /* Deadlock detection and priority inheritance handling */ struct rt_mutex_waiter *pi_blocked_on; - /* Top pi_waiters task */ - struct task_struct *pi_top_task; #endif #ifdef CONFIG_DEBUG_MUTEXES @@ -2021,9 +2016,6 @@ static inline void rcu_copy_process(struct task_struct *p) #ifdef CONFIG_TREE_PREEMPT_RCU p->rcu_blocked_node = NULL; #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ -#ifdef CONFIG_RCU_BOOST - p->rcu_boost_mutex = NULL; -#endif /* #ifdef CONFIG_RCU_BOOST */ INIT_LIST_HEAD(&p->rcu_node_entry); } @@ -2800,7 +2792,7 @@ static inline bool __must_check current_set_polling_and_test(void) /* * Polling state must be visible before we test NEED_RESCHED, - * paired by resched_task() + * paired by resched_curr() */ smp_mb__after_atomic(); @@ -2818,7 +2810,7 @@ static inline bool __must_check current_clr_polling_and_test(void) /* * Polling state must be visible before we test NEED_RESCHED, - * paired by resched_task() + * paired by resched_curr() */ smp_mb__after_atomic(); @@ -2850,7 +2842,7 @@ static inline void current_clr_polling(void) * TIF_NEED_RESCHED and the IPI handler, scheduler_ipi(), will also * fold. */ - smp_mb(); /* paired with resched_task() */ + smp_mb(); /* paired with resched_curr() */ preempt_fold_need_resched(); } diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 535f158977b9..cc359636cfa3 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -117,6 +117,22 @@ repeat: } /** + * raw_read_seqcount - Read the raw seqcount + * @s: pointer to seqcount_t + * Returns: count to be passed to read_seqcount_retry + * + * raw_read_seqcount opens a read critical section of the given + * seqcount without any lockdep checking and without checking or + * masking the LSB. Calling code is responsible for handling that. + */ +static inline unsigned raw_read_seqcount(const seqcount_t *s) +{ + unsigned ret = ACCESS_ONCE(s->sequence); + smp_rmb(); + return ret; +} + +/** * raw_read_seqcount_begin - start seq-read critical section w/o lockdep * @s: pointer to seqcount_t * Returns: count to be passed to read_seqcount_retry @@ -164,8 +180,6 @@ static inline unsigned read_seqcount_begin(const seqcount_t *s) static inline unsigned raw_seqcount_begin(const seqcount_t *s) { unsigned ret = ACCESS_ONCE(s->sequence); - - seqcount_lockdep_reader_access(s); smp_rmb(); return ret & ~1; } @@ -220,6 +234,17 @@ static inline void raw_write_seqcount_end(seqcount_t *s) } /* + * raw_write_seqcount_latch - redirect readers to even/odd copy + * @s: pointer to seqcount_t + */ +static inline void raw_write_seqcount_latch(seqcount_t *s) +{ + smp_wmb(); /* prior stores before incrementing "sequence" */ + s->sequence++; + smp_wmb(); /* increment "sequence" before following stores */ +} + +/* * Sequence counter only version assumes that callers are using their * own mutexing. */ diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index ad7dbe2cfecd..1a8959944c5f 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -236,7 +236,7 @@ void * rpc_malloc(struct rpc_task *, size_t); void rpc_free(void *); int rpciod_up(void); void rpciod_down(void); -int __rpc_wait_for_completion_task(struct rpc_task *task, int (*)(void *)); +int __rpc_wait_for_completion_task(struct rpc_task *task, wait_bit_action_f *); #ifdef RPC_DEBUG struct net; void rpc_show_tasks(struct net *); diff --git a/include/linux/tick.h b/include/linux/tick.h index b84773cb9f4c..059052306831 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -12,6 +12,7 @@ #include <linux/hrtimer.h> #include <linux/context_tracking_state.h> #include <linux/cpumask.h> +#include <linux/sched.h> #ifdef CONFIG_GENERIC_CLOCKEVENTS @@ -162,6 +163,7 @@ static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } #ifdef CONFIG_NO_HZ_FULL extern bool tick_nohz_full_running; extern cpumask_var_t tick_nohz_full_mask; +extern cpumask_var_t housekeeping_mask; static inline bool tick_nohz_full_enabled(void) { @@ -181,7 +183,13 @@ static inline bool tick_nohz_full_cpu(int cpu) extern void tick_nohz_init(void); extern void __tick_nohz_full_check(void); -extern void tick_nohz_full_kick(void); +extern void tick_nohz_full_kick_cpu(int cpu); + +static inline void tick_nohz_full_kick(void) +{ + tick_nohz_full_kick_cpu(smp_processor_id()); +} + extern void tick_nohz_full_kick_all(void); extern void __tick_nohz_task_switch(struct task_struct *tsk); #else @@ -189,11 +197,30 @@ static inline void tick_nohz_init(void) { } static inline bool tick_nohz_full_enabled(void) { return false; } static inline bool tick_nohz_full_cpu(int cpu) { return false; } static inline void __tick_nohz_full_check(void) { } +static inline void tick_nohz_full_kick_cpu(int cpu) { } static inline void tick_nohz_full_kick(void) { } static inline void tick_nohz_full_kick_all(void) { } static inline void __tick_nohz_task_switch(struct task_struct *tsk) { } #endif +static inline bool is_housekeeping_cpu(int cpu) +{ +#ifdef CONFIG_NO_HZ_FULL + if (tick_nohz_full_enabled()) + return cpumask_test_cpu(cpu, housekeeping_mask); +#endif + return true; +} + +static inline void housekeeping_affine(struct task_struct *t) +{ +#ifdef CONFIG_NO_HZ_FULL + if (tick_nohz_full_enabled()) + set_cpus_allowed_ptr(t, housekeeping_mask); + +#endif +} + static inline void tick_nohz_full_check(void) { if (tick_nohz_full_enabled()) diff --git a/include/linux/time.h b/include/linux/time.h index d5d229b2e5af..8c42cf8d2444 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -4,19 +4,10 @@ # include <linux/cache.h> # include <linux/seqlock.h> # include <linux/math64.h> -#include <uapi/linux/time.h> +# include <linux/time64.h> extern struct timezone sys_tz; -/* Parameters used to convert the timespec values: */ -#define MSEC_PER_SEC 1000L -#define USEC_PER_MSEC 1000L -#define NSEC_PER_USEC 1000L -#define NSEC_PER_MSEC 1000000L -#define USEC_PER_SEC 1000000L -#define NSEC_PER_SEC 1000000000L -#define FSEC_PER_SEC 1000000000000000LL - #define TIME_T_MAX (time_t)((1UL << ((sizeof(time_t) << 3) - 1)) - 1) static inline int timespec_equal(const struct timespec *a, @@ -84,13 +75,6 @@ static inline struct timespec timespec_sub(struct timespec lhs, return ts_delta; } -#define KTIME_MAX ((s64)~((u64)1 << 63)) -#if (BITS_PER_LONG == 64) -# define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) -#else -# define KTIME_SEC_MAX LONG_MAX -#endif - /* * Returns true if the timespec is norm, false if denorm: */ @@ -115,27 +99,7 @@ static inline bool timespec_valid_strict(const struct timespec *ts) return true; } -extern bool persistent_clock_exist; - -static inline bool has_persistent_clock(void) -{ - return persistent_clock_exist; -} - -extern void read_persistent_clock(struct timespec *ts); -extern void read_boot_clock(struct timespec *ts); -extern int persistent_clock_is_local; -extern int update_persistent_clock(struct timespec now); -void timekeeping_init(void); -extern int timekeeping_suspended; - -unsigned long get_seconds(void); -struct timespec current_kernel_time(void); -struct timespec __current_kernel_time(void); /* does not take xtime_lock */ -struct timespec get_monotonic_coarse(void); -void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim, - struct timespec *wtom, struct timespec *sleep); -void timekeeping_inject_sleeptime(struct timespec *delta); +extern struct timespec timespec_trunc(struct timespec t, unsigned gran); #define CURRENT_TIME (current_kernel_time()) #define CURRENT_TIME_SEC ((struct timespec) { get_seconds(), 0 }) @@ -153,33 +117,14 @@ void timekeeping_inject_sleeptime(struct timespec *delta); extern u32 (*arch_gettimeoffset)(void); #endif -extern void do_gettimeofday(struct timeval *tv); -extern int do_settimeofday(const struct timespec *tv); -extern int do_sys_settimeofday(const struct timespec *tv, - const struct timezone *tz); -#define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts) -extern long do_utimes(int dfd, const char __user *filename, struct timespec *times, int flags); struct itimerval; extern int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue); -extern unsigned int alarm_setitimer(unsigned int seconds); extern int do_getitimer(int which, struct itimerval *value); -extern int __getnstimeofday(struct timespec *tv); -extern void getnstimeofday(struct timespec *tv); -extern void getrawmonotonic(struct timespec *ts); -extern void getnstime_raw_and_real(struct timespec *ts_raw, - struct timespec *ts_real); -extern void getboottime(struct timespec *ts); -extern void monotonic_to_bootbased(struct timespec *ts); -extern void get_monotonic_boottime(struct timespec *ts); -extern struct timespec timespec_trunc(struct timespec t, unsigned gran); -extern int timekeeping_valid_for_hres(void); -extern u64 timekeeping_max_deferment(void); -extern int timekeeping_inject_offset(struct timespec *ts); -extern s32 timekeeping_get_tai_offset(void); -extern void timekeeping_set_tai_offset(s32 tai_offset); -extern void timekeeping_clocktai(struct timespec *ts); +extern unsigned int alarm_setitimer(unsigned int seconds); + +extern long do_utimes(int dfd, const char __user *filename, struct timespec *times, int flags); struct tms; extern void do_sys_times(struct tms *); diff --git a/include/linux/time64.h b/include/linux/time64.h new file mode 100644 index 000000000000..a3831478d9cf --- /dev/null +++ b/include/linux/time64.h @@ -0,0 +1,190 @@ +#ifndef _LINUX_TIME64_H +#define _LINUX_TIME64_H + +#include <uapi/linux/time.h> + +typedef __s64 time64_t; + +/* + * This wants to go into uapi/linux/time.h once we agreed about the + * userspace interfaces. + */ +#if __BITS_PER_LONG == 64 +# define timespec64 timespec +#else +struct timespec64 { + time64_t tv_sec; /* seconds */ + long tv_nsec; /* nanoseconds */ +}; +#endif + +/* Parameters used to convert the timespec values: */ +#define MSEC_PER_SEC 1000L +#define USEC_PER_MSEC 1000L +#define NSEC_PER_USEC 1000L +#define NSEC_PER_MSEC 1000000L +#define USEC_PER_SEC 1000000L +#define NSEC_PER_SEC 1000000000L +#define FSEC_PER_SEC 1000000000000000LL + +/* Located here for timespec[64]_valid_strict */ +#define KTIME_MAX ((s64)~((u64)1 << 63)) +#define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) + +#if __BITS_PER_LONG == 64 + +static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64) +{ + return ts64; +} + +static inline struct timespec64 timespec_to_timespec64(const struct timespec ts) +{ + return ts; +} + +# define timespec64_equal timespec_equal +# define timespec64_compare timespec_compare +# define set_normalized_timespec64 set_normalized_timespec +# define timespec64_add_safe timespec_add_safe +# define timespec64_add timespec_add +# define timespec64_sub timespec_sub +# define timespec64_valid timespec_valid +# define timespec64_valid_strict timespec_valid_strict +# define timespec64_to_ns timespec_to_ns +# define ns_to_timespec64 ns_to_timespec +# define timespec64_add_ns timespec_add_ns + +#else + +static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64) +{ + struct timespec ret; + + ret.tv_sec = (time_t)ts64.tv_sec; + ret.tv_nsec = ts64.tv_nsec; + return ret; +} + +static inline struct timespec64 timespec_to_timespec64(const struct timespec ts) +{ + struct timespec64 ret; + + ret.tv_sec = ts.tv_sec; + ret.tv_nsec = ts.tv_nsec; + return ret; +} + +static inline int timespec64_equal(const struct timespec64 *a, + const struct timespec64 *b) +{ + return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec); +} + +/* + * lhs < rhs: return <0 + * lhs == rhs: return 0 + * lhs > rhs: return >0 + */ +static inline int timespec64_compare(const struct timespec64 *lhs, const struct timespec64 *rhs) +{ + if (lhs->tv_sec < rhs->tv_sec) + return -1; + if (lhs->tv_sec > rhs->tv_sec) + return 1; + return lhs->tv_nsec - rhs->tv_nsec; +} + +extern void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec); + +/* + * timespec64_add_safe assumes both values are positive and checks for + * overflow. It will return TIME_T_MAX if the returned value would be + * smaller then either of the arguments. + */ +extern struct timespec64 timespec64_add_safe(const struct timespec64 lhs, + const struct timespec64 rhs); + + +static inline struct timespec64 timespec64_add(struct timespec64 lhs, + struct timespec64 rhs) +{ + struct timespec64 ts_delta; + set_normalized_timespec64(&ts_delta, lhs.tv_sec + rhs.tv_sec, + lhs.tv_nsec + rhs.tv_nsec); + return ts_delta; +} + +/* + * sub = lhs - rhs, in normalized form + */ +static inline struct timespec64 timespec64_sub(struct timespec64 lhs, + struct timespec64 rhs) +{ + struct timespec64 ts_delta; + set_normalized_timespec64(&ts_delta, lhs.tv_sec - rhs.tv_sec, + lhs.tv_nsec - rhs.tv_nsec); + return ts_delta; +} + +/* + * Returns true if the timespec64 is norm, false if denorm: + */ +static inline bool timespec64_valid(const struct timespec64 *ts) +{ + /* Dates before 1970 are bogus */ + if (ts->tv_sec < 0) + return false; + /* Can't have more nanoseconds then a second */ + if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) + return false; + return true; +} + +static inline bool timespec64_valid_strict(const struct timespec64 *ts) +{ + if (!timespec64_valid(ts)) + return false; + /* Disallow values that could overflow ktime_t */ + if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) + return false; + return true; +} + +/** + * timespec64_to_ns - Convert timespec64 to nanoseconds + * @ts: pointer to the timespec64 variable to be converted + * + * Returns the scalar nanosecond representation of the timespec64 + * parameter. + */ +static inline s64 timespec64_to_ns(const struct timespec64 *ts) +{ + return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; +} + +/** + * ns_to_timespec64 - Convert nanoseconds to timespec64 + * @nsec: the nanoseconds value to be converted + * + * Returns the timespec64 representation of the nsec parameter. + */ +extern struct timespec64 ns_to_timespec64(const s64 nsec); + +/** + * timespec64_add_ns - Adds nanoseconds to a timespec64 + * @a: pointer to timespec64 to be incremented + * @ns: unsigned nanoseconds value to be added + * + * This must always be inlined because its used from the x86-64 vdso, + * which cannot call other kernel functions. + */ +static __always_inline void timespec64_add_ns(struct timespec64 *a, u64 ns) +{ + a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns); + a->tv_nsec = ns; +} + +#endif + +#endif /* _LINUX_TIME64_H */ diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index c1825eb436ed..95640dcd1899 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -10,77 +10,100 @@ #include <linux/jiffies.h> #include <linux/time.h> -/* Structure holding internal timekeeping values. */ -struct timekeeper { - /* Current clocksource used for timekeeping. */ +/** + * struct tk_read_base - base structure for timekeeping readout + * @clock: Current clocksource used for timekeeping. + * @read: Read function of @clock + * @mask: Bitmask for two's complement subtraction of non 64bit clocks + * @cycle_last: @clock cycle value at last update + * @mult: NTP adjusted multiplier for scaled math conversion + * @shift: Shift value for scaled math conversion + * @xtime_nsec: Shifted (fractional) nano seconds offset for readout + * @base_mono: ktime_t (nanoseconds) base time for readout + * + * This struct has size 56 byte on 64 bit. Together with a seqcount it + * occupies a single 64byte cache line. + * + * The struct is separate from struct timekeeper as it is also used + * for a fast NMI safe accessor to clock monotonic. + */ +struct tk_read_base { struct clocksource *clock; - /* NTP adjusted clock multiplier */ + cycle_t (*read)(struct clocksource *cs); + cycle_t mask; + cycle_t cycle_last; u32 mult; - /* The shift value of the current clocksource. */ u32 shift; - /* Number of clock cycles in one NTP interval. */ + u64 xtime_nsec; + ktime_t base_mono; +}; + +/** + * struct timekeeper - Structure holding internal timekeeping values. + * @tkr: The readout base structure + * @xtime_sec: Current CLOCK_REALTIME time in seconds + * @wall_to_monotonic: CLOCK_REALTIME to CLOCK_MONOTONIC offset + * @offs_real: Offset clock monotonic -> clock realtime + * @offs_boot: Offset clock monotonic -> clock boottime + * @offs_tai: Offset clock monotonic -> clock tai + * @tai_offset: The current UTC to TAI offset in seconds + * @base_raw: Monotonic raw base time in ktime_t format + * @raw_time: Monotonic raw base time in timespec64 format + * @cycle_interval: Number of clock cycles in one NTP interval + * @xtime_interval: Number of clock shifted nano seconds in one NTP + * interval. + * @xtime_remainder: Shifted nano seconds left over when rounding + * @cycle_interval + * @raw_interval: Raw nano seconds accumulated per NTP interval. + * @ntp_error: Difference between accumulated time and NTP time in ntp + * shifted nano seconds. + * @ntp_error_shift: Shift conversion between clock shifted nano seconds and + * ntp shifted nano seconds. + * + * Note: For timespec(64) based interfaces wall_to_monotonic is what + * we need to add to xtime (or xtime corrected for sub jiffie times) + * to get to monotonic time. Monotonic is pegged at zero at system + * boot time, so wall_to_monotonic will be negative, however, we will + * ALWAYS keep the tv_nsec part positive so we can use the usual + * normalization. + * + * wall_to_monotonic is moved after resume from suspend for the + * monotonic time not to jump. We need to add total_sleep_time to + * wall_to_monotonic to get the real boot based time offset. + * + * wall_to_monotonic is no longer the boot time, getboottime must be + * used instead. + */ +struct timekeeper { + struct tk_read_base tkr; + u64 xtime_sec; + struct timespec64 wall_to_monotonic; + ktime_t offs_real; + ktime_t offs_boot; + ktime_t offs_tai; + s32 tai_offset; + ktime_t base_raw; + struct timespec64 raw_time; + + /* The following members are for timekeeping internal use */ cycle_t cycle_interval; - /* Last cycle value (also stored in clock->cycle_last) */ - cycle_t cycle_last; - /* Number of clock shifted nano seconds in one NTP interval. */ u64 xtime_interval; - /* shifted nano seconds left over when rounding cycle_interval */ s64 xtime_remainder; - /* Raw nano seconds accumulated per NTP interval. */ u32 raw_interval; - - /* Current CLOCK_REALTIME time in seconds */ - u64 xtime_sec; - /* Clock shifted nano seconds */ - u64 xtime_nsec; - + /* The ntp_tick_length() value currently being used. + * This cached copy ensures we consistently apply the tick + * length for an entire tick, as ntp_tick_length may change + * mid-tick, and we don't want to apply that new value to + * the tick in progress. + */ + u64 ntp_tick; /* Difference between accumulated time and NTP time in ntp * shifted nano seconds. */ s64 ntp_error; - /* Shift conversion between clock shifted nano seconds and - * ntp shifted nano seconds. */ u32 ntp_error_shift; - - /* - * wall_to_monotonic is what we need to add to xtime (or xtime corrected - * for sub jiffie times) to get to monotonic time. Monotonic is pegged - * at zero at system boot time, so wall_to_monotonic will be negative, - * however, we will ALWAYS keep the tv_nsec part positive so we can use - * the usual normalization. - * - * wall_to_monotonic is moved after resume from suspend for the - * monotonic time not to jump. We need to add total_sleep_time to - * wall_to_monotonic to get the real boot based time offset. - * - * - wall_to_monotonic is no longer the boot time, getboottime must be - * used instead. - */ - struct timespec wall_to_monotonic; - /* Offset clock monotonic -> clock realtime */ - ktime_t offs_real; - /* time spent in suspend */ - struct timespec total_sleep_time; - /* Offset clock monotonic -> clock boottime */ - ktime_t offs_boot; - /* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */ - struct timespec raw_time; - /* The current UTC to TAI offset in seconds */ - s32 tai_offset; - /* Offset clock monotonic -> clock tai */ - ktime_t offs_tai; - + u32 ntp_err_mult; }; -static inline struct timespec tk_xtime(struct timekeeper *tk) -{ - struct timespec ts; - - ts.tv_sec = tk->xtime_sec; - ts.tv_nsec = (long)(tk->xtime_nsec >> tk->shift); - return ts; -} - - #ifdef CONFIG_GENERIC_TIME_VSYSCALL extern void update_vsyscall(struct timekeeper *tk); @@ -89,17 +112,10 @@ extern void update_vsyscall_tz(void); #elif defined(CONFIG_GENERIC_TIME_VSYSCALL_OLD) extern void update_vsyscall_old(struct timespec *ts, struct timespec *wtm, - struct clocksource *c, u32 mult); + struct clocksource *c, u32 mult, + cycle_t cycle_last); extern void update_vsyscall_tz(void); -static inline void update_vsyscall(struct timekeeper *tk) -{ - struct timespec xt; - - xt = tk_xtime(tk); - update_vsyscall_old(&xt, &tk->wall_to_monotonic, tk->clock, tk->mult); -} - #else static inline void update_vsyscall(struct timekeeper *tk) diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h new file mode 100644 index 000000000000..1caa6b04fdc5 --- /dev/null +++ b/include/linux/timekeeping.h @@ -0,0 +1,209 @@ +#ifndef _LINUX_TIMEKEEPING_H +#define _LINUX_TIMEKEEPING_H + +/* Included from linux/ktime.h */ + +void timekeeping_init(void); +extern int timekeeping_suspended; + +/* + * Get and set timeofday + */ +extern void do_gettimeofday(struct timeval *tv); +extern int do_settimeofday(const struct timespec *tv); +extern int do_sys_settimeofday(const struct timespec *tv, + const struct timezone *tz); + +/* + * Kernel time accessors + */ +unsigned long get_seconds(void); +struct timespec current_kernel_time(void); +/* does not take xtime_lock */ +struct timespec __current_kernel_time(void); + +/* + * timespec based interfaces + */ +struct timespec get_monotonic_coarse(void); +extern void getrawmonotonic(struct timespec *ts); +extern void ktime_get_ts64(struct timespec64 *ts); + +extern int __getnstimeofday64(struct timespec64 *tv); +extern void getnstimeofday64(struct timespec64 *tv); + +#if BITS_PER_LONG == 64 +static inline int __getnstimeofday(struct timespec *ts) +{ + return __getnstimeofday64(ts); +} + +static inline void getnstimeofday(struct timespec *ts) +{ + getnstimeofday64(ts); +} + +static inline void ktime_get_ts(struct timespec *ts) +{ + ktime_get_ts64(ts); +} + +static inline void ktime_get_real_ts(struct timespec *ts) +{ + getnstimeofday64(ts); +} + +#else +static inline int __getnstimeofday(struct timespec *ts) +{ + struct timespec64 ts64; + int ret = __getnstimeofday64(&ts64); + + *ts = timespec64_to_timespec(ts64); + return ret; +} + +static inline void getnstimeofday(struct timespec *ts) +{ + struct timespec64 ts64; + + getnstimeofday64(&ts64); + *ts = timespec64_to_timespec(ts64); +} + +static inline void ktime_get_ts(struct timespec *ts) +{ + struct timespec64 ts64; + + ktime_get_ts64(&ts64); + *ts = timespec64_to_timespec(ts64); +} + +static inline void ktime_get_real_ts(struct timespec *ts) +{ + struct timespec64 ts64; + + getnstimeofday64(&ts64); + *ts = timespec64_to_timespec(ts64); +} +#endif + +extern void getboottime(struct timespec *ts); + +#define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts) +#define ktime_get_real_ts64(ts) getnstimeofday64(ts) + +/* + * ktime_t based interfaces + */ + +enum tk_offsets { + TK_OFFS_REAL, + TK_OFFS_BOOT, + TK_OFFS_TAI, + TK_OFFS_MAX, +}; + +extern ktime_t ktime_get(void); +extern ktime_t ktime_get_with_offset(enum tk_offsets offs); +extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs); +extern ktime_t ktime_get_raw(void); + +/** + * ktime_get_real - get the real (wall-) time in ktime_t format + */ +static inline ktime_t ktime_get_real(void) +{ + return ktime_get_with_offset(TK_OFFS_REAL); +} + +/** + * ktime_get_boottime - Returns monotonic time since boot in ktime_t format + * + * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the + * time spent in suspend. + */ +static inline ktime_t ktime_get_boottime(void) +{ + return ktime_get_with_offset(TK_OFFS_BOOT); +} + +/** + * ktime_get_clocktai - Returns the TAI time of day in ktime_t format + */ +static inline ktime_t ktime_get_clocktai(void) +{ + return ktime_get_with_offset(TK_OFFS_TAI); +} + +/** + * ktime_mono_to_real - Convert monotonic time to clock realtime + */ +static inline ktime_t ktime_mono_to_real(ktime_t mono) +{ + return ktime_mono_to_any(mono, TK_OFFS_REAL); +} + +static inline u64 ktime_get_ns(void) +{ + return ktime_to_ns(ktime_get()); +} + +static inline u64 ktime_get_real_ns(void) +{ + return ktime_to_ns(ktime_get_real()); +} + +static inline u64 ktime_get_boot_ns(void) +{ + return ktime_to_ns(ktime_get_boottime()); +} + +static inline u64 ktime_get_raw_ns(void) +{ + return ktime_to_ns(ktime_get_raw()); +} + +extern u64 ktime_get_mono_fast_ns(void); + +/* + * Timespec interfaces utilizing the ktime based ones + */ +static inline void get_monotonic_boottime(struct timespec *ts) +{ + *ts = ktime_to_timespec(ktime_get_boottime()); +} + +static inline void timekeeping_clocktai(struct timespec *ts) +{ + *ts = ktime_to_timespec(ktime_get_clocktai()); +} + +/* + * RTC specific + */ +extern void timekeeping_inject_sleeptime(struct timespec *delta); + +/* + * PPS accessor + */ +extern void getnstime_raw_and_real(struct timespec *ts_raw, + struct timespec *ts_real); + +/* + * Persistent clock related interfaces + */ +extern bool persistent_clock_exist; +extern int persistent_clock_is_local; + +static inline bool has_persistent_clock(void) +{ + return persistent_clock_exist; +} + +extern void read_persistent_clock(struct timespec *ts); +extern void read_boot_clock(struct timespec *ts); +extern int update_persistent_clock(struct timespec now); + + +#endif diff --git a/include/linux/timerfd.h b/include/linux/timerfd.h index d3b57fa12225..bd36ce431e32 100644 --- a/include/linux/timerfd.h +++ b/include/linux/timerfd.h @@ -11,6 +11,9 @@ /* For O_CLOEXEC and O_NONBLOCK */ #include <linux/fcntl.h> +/* For _IO helpers */ +#include <linux/ioctl.h> + /* * CAREFUL: Check include/asm-generic/fcntl.h when defining * new flags, since they might collide with O_* ones. We want @@ -29,4 +32,6 @@ /* Flags for timerfd_settime. */ #define TFD_SETTIME_FLAGS (TFD_TIMER_ABSTIME | TFD_TIMER_CANCEL_ON_SET) +#define TFD_IOC_SET_TICKS _IOW('T', 0, u64) + #endif /* _LINUX_TIMERFD_H */ diff --git a/include/linux/wait.h b/include/linux/wait.h index bd68819f0815..6fb1ba5f9b2f 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -25,6 +25,7 @@ struct wait_bit_key { void *flags; int bit_nr; #define WAIT_ATOMIC_T_BIT_NR -1 + unsigned long private; }; struct wait_bit_queue { @@ -141,18 +142,19 @@ __remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old) list_del(&old->task_list); } +typedef int wait_bit_action_f(struct wait_bit_key *); void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key); void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key); void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key); void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr); void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr); void __wake_up_bit(wait_queue_head_t *, void *, int); -int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned); -int __wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned); +int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_action_f *, unsigned); +int __wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_action_f *, unsigned); void wake_up_bit(void *, int); void wake_up_atomic_t(atomic_t *); -int out_of_line_wait_on_bit(void *, int, int (*)(void *), unsigned); -int out_of_line_wait_on_bit_lock(void *, int, int (*)(void *), unsigned); +int out_of_line_wait_on_bit(void *, int, wait_bit_action_f *, unsigned); +int out_of_line_wait_on_bit_lock(void *, int, wait_bit_action_f *, unsigned); int out_of_line_wait_on_atomic_t(atomic_t *, int (*)(atomic_t *), unsigned); wait_queue_head_t *bit_waitqueue(void *, int); @@ -854,11 +856,14 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key); (wait)->flags = 0; \ } while (0) + +extern int bit_wait(struct wait_bit_key *); +extern int bit_wait_io(struct wait_bit_key *); + /** * wait_on_bit - 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 - * @action: the function used to sleep, which may take special actions * @mode: the task state to sleep in * * There is a standard hashed waitqueue table for generic use. This @@ -867,9 +872,62 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key); * call wait_on_bit() in threads waiting for the bit to clear. * One uses wait_on_bit() where one is waiting for the bit to clear, * but has no intention of setting it. + * Returned value will be zero if the bit was cleared, or non-zero + * if the process received a signal and the mode permitted wakeup + * on that signal. + */ +static inline int +wait_on_bit(void *word, int bit, unsigned mode) +{ + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit(word, bit, + bit_wait, + mode); +} + +/** + * wait_on_bit_io - 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 + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared. This is similar to wait_on_bit(), but calls + * io_schedule() instead of schedule() for the actual waiting. + * + * Returned value will be zero if the bit was cleared, or non-zero + * if the process received a signal and the mode permitted wakeup + * on that signal. + */ +static inline int +wait_on_bit_io(void *word, int bit, unsigned mode) +{ + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit(word, bit, + bit_wait_io, + mode); +} + +/** + * 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 + * @action: the function used to sleep, which may take special actions + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared, and allow the waiting action to be specified. + * This is like wait_on_bit() but allows fine control of how the waiting + * is done. + * + * Returned value will be zero if the bit was cleared, or non-zero + * if the process received a signal and the mode permitted wakeup + * on that signal. */ static inline int -wait_on_bit(void *word, int bit, int (*action)(void *), unsigned mode) +wait_on_bit_action(void *word, int bit, wait_bit_action_f *action, unsigned mode) { if (!test_bit(bit, word)) return 0; @@ -880,7 +938,6 @@ wait_on_bit(void *word, int bit, int (*action)(void *), unsigned mode) * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on - * @action: the function used to sleep, which may take special actions * @mode: the task state to sleep in * * There is a standard hashed waitqueue table for generic use. This @@ -891,9 +948,61 @@ wait_on_bit(void *word, int bit, int (*action)(void *), unsigned mode) * wait_on_bit() in threads waiting to be able to set the bit. * One uses wait_on_bit_lock() where one is waiting for the bit to * clear with the intention of setting it, and when done, clearing it. + * + * Returns zero if the bit was (eventually) found to be clear and was + * set. Returns non-zero if a signal was delivered to the process and + * the @mode allows that signal to wake the process. + */ +static inline int +wait_on_bit_lock(void *word, int bit, unsigned mode) +{ + if (!test_and_set_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode); +} + +/** + * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it + * @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 + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared and then to atomically set it. This is similar + * to wait_on_bit(), but calls io_schedule() instead of schedule() + * for the actual waiting. + * + * Returns zero if the bit was (eventually) found to be clear and was + * set. Returns non-zero if a signal was delivered to the process and + * the @mode allows that signal to wake the process. + */ +static inline int +wait_on_bit_lock_io(void *word, int bit, unsigned mode) +{ + if (!test_and_set_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode); +} + +/** + * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @action: the function used to sleep, which may take special actions + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared and then to set it, and allow the waiting action + * to be specified. + * This is like wait_on_bit() but allows fine control of how the waiting + * is done. + * + * Returns zero if the bit was (eventually) found to be clear and was + * set. Returns non-zero if a signal was delivered to the process and + * the @mode allows that signal to wake the process. */ static inline int -wait_on_bit_lock(void *word, int bit, int (*action)(void *), unsigned mode) +wait_on_bit_lock_action(void *word, int bit, wait_bit_action_f *action, unsigned mode) { if (!test_and_set_bit(bit, word)) return 0; diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 5777c13849ba..a219be961c0a 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -90,7 +90,6 @@ struct writeback_control { * fs/fs-writeback.c */ struct bdi_writeback; -int inode_wait(void *); void writeback_inodes_sb(struct super_block *, enum wb_reason reason); void writeback_inodes_sb_nr(struct super_block *, unsigned long nr, enum wb_reason reason); @@ -105,7 +104,7 @@ void inode_wait_for_writeback(struct inode *inode); static inline void wait_on_inode(struct inode *inode) { might_sleep(); - wait_on_bit(&inode->i_state, __I_NEW, inode_wait, TASK_UNINTERRUPTIBLE); + wait_on_bit(&inode->i_state, __I_NEW, TASK_UNINTERRUPTIBLE); } /* diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h index 21cdb0b7b0fb..47da53c27ffa 100644 --- a/include/ras/ras_event.h +++ b/include/ras/ras_event.h @@ -8,6 +8,71 @@ #include <linux/tracepoint.h> #include <linux/edac.h> #include <linux/ktime.h> +#include <linux/aer.h> +#include <linux/cper.h> + +/* + * MCE Extended Error Log trace event + * + * These events are generated when hardware detects a corrected or + * uncorrected event. + */ + +/* memory trace event */ + +#if defined(CONFIG_ACPI_EXTLOG) || defined(CONFIG_ACPI_EXTLOG_MODULE) +TRACE_EVENT(extlog_mem_event, + TP_PROTO(struct cper_sec_mem_err *mem, + u32 err_seq, + const uuid_le *fru_id, + const char *fru_text, + u8 sev), + + TP_ARGS(mem, err_seq, fru_id, fru_text, sev), + + TP_STRUCT__entry( + __field(u32, err_seq) + __field(u8, etype) + __field(u8, sev) + __field(u64, pa) + __field(u8, pa_mask_lsb) + __field_struct(uuid_le, fru_id) + __string(fru_text, fru_text) + __field_struct(struct cper_mem_err_compact, data) + ), + + TP_fast_assign( + __entry->err_seq = err_seq; + if (mem->validation_bits & CPER_MEM_VALID_ERROR_TYPE) + __entry->etype = mem->error_type; + else + __entry->etype = ~0; + __entry->sev = sev; + if (mem->validation_bits & CPER_MEM_VALID_PA) + __entry->pa = mem->physical_addr; + else + __entry->pa = ~0ull; + + if (mem->validation_bits & CPER_MEM_VALID_PA_MASK) + __entry->pa_mask_lsb = (u8)__ffs64(mem->physical_addr_mask); + else + __entry->pa_mask_lsb = ~0; + __entry->fru_id = *fru_id; + __assign_str(fru_text, fru_text); + cper_mem_err_pack(mem, &__entry->data); + ), + + TP_printk("{%d} %s error: %s physical addr: %016llx (mask lsb: %x) %sFRU: %pUl %.20s", + __entry->err_seq, + cper_severity_str(__entry->sev), + cper_mem_err_type_str(__entry->etype), + __entry->pa, + __entry->pa_mask_lsb, + cper_mem_err_unpack(p, &__entry->data), + &__entry->fru_id, + __get_str(fru_text)) +); +#endif /* * Hardware Events Report @@ -94,6 +159,69 @@ TRACE_EVENT(mc_event, __get_str(driver_detail)) ); +/* + * PCIe AER Trace event + * + * These events are generated when hardware detects a corrected or + * uncorrected event on a PCIe device. The event report has + * the following structure: + * + * char * dev_name - The name of the slot where the device resides + * ([domain:]bus:device.function). + * u32 status - Either the correctable or uncorrectable register + * indicating what error or errors have been seen + * u8 severity - error severity 0:NONFATAL 1:FATAL 2:CORRECTED + */ + +#define aer_correctable_errors \ + {BIT(0), "Receiver Error"}, \ + {BIT(6), "Bad TLP"}, \ + {BIT(7), "Bad DLLP"}, \ + {BIT(8), "RELAY_NUM Rollover"}, \ + {BIT(12), "Replay Timer Timeout"}, \ + {BIT(13), "Advisory Non-Fatal"} + +#define aer_uncorrectable_errors \ + {BIT(4), "Data Link Protocol"}, \ + {BIT(12), "Poisoned TLP"}, \ + {BIT(13), "Flow Control Protocol"}, \ + {BIT(14), "Completion Timeout"}, \ + {BIT(15), "Completer Abort"}, \ + {BIT(16), "Unexpected Completion"}, \ + {BIT(17), "Receiver Overflow"}, \ + {BIT(18), "Malformed TLP"}, \ + {BIT(19), "ECRC"}, \ + {BIT(20), "Unsupported Request"} + +TRACE_EVENT(aer_event, + TP_PROTO(const char *dev_name, + const u32 status, + const u8 severity), + + TP_ARGS(dev_name, status, severity), + + TP_STRUCT__entry( + __string( dev_name, dev_name ) + __field( u32, status ) + __field( u8, severity ) + ), + + TP_fast_assign( + __assign_str(dev_name, dev_name); + __entry->status = status; + __entry->severity = severity; + ), + + TP_printk("%s PCIe Bus Error: severity=%s, %s\n", + __get_str(dev_name), + __entry->severity == AER_CORRECTABLE ? "Corrected" : + __entry->severity == AER_FATAL ? + "Fatal" : "Uncorrected, non-fatal", + __entry->severity == AER_CORRECTABLE ? + __print_flags(__entry->status, "|", aer_correctable_errors) : + __print_flags(__entry->status, "|", aer_uncorrectable_errors)) +); + #endif /* _TRACE_HW_EVENT_MC_H */ /* This part must be outside protection */ diff --git a/include/trace/events/ras.h b/include/trace/events/ras.h deleted file mode 100644 index 1c875ad1ee5f..000000000000 --- a/include/trace/events/ras.h +++ /dev/null @@ -1,77 +0,0 @@ -#undef TRACE_SYSTEM -#define TRACE_SYSTEM ras - -#if !defined(_TRACE_AER_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_AER_H - -#include <linux/tracepoint.h> -#include <linux/aer.h> - - -/* - * PCIe AER Trace event - * - * These events are generated when hardware detects a corrected or - * uncorrected event on a PCIe device. The event report has - * the following structure: - * - * char * dev_name - The name of the slot where the device resides - * ([domain:]bus:device.function). - * u32 status - Either the correctable or uncorrectable register - * indicating what error or errors have been seen - * u8 severity - error severity 0:NONFATAL 1:FATAL 2:CORRECTED - */ - -#define aer_correctable_errors \ - {BIT(0), "Receiver Error"}, \ - {BIT(6), "Bad TLP"}, \ - {BIT(7), "Bad DLLP"}, \ - {BIT(8), "RELAY_NUM Rollover"}, \ - {BIT(12), "Replay Timer Timeout"}, \ - {BIT(13), "Advisory Non-Fatal"} - -#define aer_uncorrectable_errors \ - {BIT(4), "Data Link Protocol"}, \ - {BIT(12), "Poisoned TLP"}, \ - {BIT(13), "Flow Control Protocol"}, \ - {BIT(14), "Completion Timeout"}, \ - {BIT(15), "Completer Abort"}, \ - {BIT(16), "Unexpected Completion"}, \ - {BIT(17), "Receiver Overflow"}, \ - {BIT(18), "Malformed TLP"}, \ - {BIT(19), "ECRC"}, \ - {BIT(20), "Unsupported Request"} - -TRACE_EVENT(aer_event, - TP_PROTO(const char *dev_name, - const u32 status, - const u8 severity), - - TP_ARGS(dev_name, status, severity), - - TP_STRUCT__entry( - __string( dev_name, dev_name ) - __field( u32, status ) - __field( u8, severity ) - ), - - TP_fast_assign( - __assign_str(dev_name, dev_name); - __entry->status = status; - __entry->severity = severity; - ), - - TP_printk("%s PCIe Bus Error: severity=%s, %s\n", - __get_str(dev_name), - __entry->severity == AER_CORRECTABLE ? "Corrected" : - __entry->severity == AER_FATAL ? - "Fatal" : "Uncorrected, non-fatal", - __entry->severity == AER_CORRECTABLE ? - __print_flags(__entry->status, "|", aer_correctable_errors) : - __print_flags(__entry->status, "|", aer_uncorrectable_errors)) -); - -#endif /* _TRACE_AER_H */ - -/* This part must be outside protection */ -#include <trace/define_trace.h> diff --git a/include/trace/events/tlb.h b/include/trace/events/tlb.h new file mode 100644 index 000000000000..13391d288107 --- /dev/null +++ b/include/trace/events/tlb.h @@ -0,0 +1,40 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM tlb + +#if !defined(_TRACE_TLB_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_TLB_H + +#include <linux/mm_types.h> +#include <linux/tracepoint.h> + +#define TLB_FLUSH_REASON \ + { TLB_FLUSH_ON_TASK_SWITCH, "flush on task switch" }, \ + { TLB_REMOTE_SHOOTDOWN, "remote shootdown" }, \ + { TLB_LOCAL_SHOOTDOWN, "local shootdown" }, \ + { TLB_LOCAL_MM_SHOOTDOWN, "local mm shootdown" } + +TRACE_EVENT(tlb_flush, + + TP_PROTO(int reason, unsigned long pages), + TP_ARGS(reason, pages), + + TP_STRUCT__entry( + __field( int, reason) + __field(unsigned long, pages) + ), + + TP_fast_assign( + __entry->reason = reason; + __entry->pages = pages; + ), + + TP_printk("pages:%ld reason:%s (%d)", + __entry->pages, + __print_symbolic(__entry->reason, TLB_FLUSH_REASON), + __entry->reason) +); + +#endif /* _TRACE_TLB_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/xen/interface/platform.h b/include/xen/interface/platform.h index f1331e3e7271..5cc49ea8d840 100644 --- a/include/xen/interface/platform.h +++ b/include/xen/interface/platform.h @@ -108,11 +108,113 @@ struct xenpf_platform_quirk { }; DEFINE_GUEST_HANDLE_STRUCT(xenpf_platform_quirk_t); +#define XENPF_efi_runtime_call 49 +#define XEN_EFI_get_time 1 +#define XEN_EFI_set_time 2 +#define XEN_EFI_get_wakeup_time 3 +#define XEN_EFI_set_wakeup_time 4 +#define XEN_EFI_get_next_high_monotonic_count 5 +#define XEN_EFI_get_variable 6 +#define XEN_EFI_set_variable 7 +#define XEN_EFI_get_next_variable_name 8 +#define XEN_EFI_query_variable_info 9 +#define XEN_EFI_query_capsule_capabilities 10 +#define XEN_EFI_update_capsule 11 + +struct xenpf_efi_runtime_call { + uint32_t function; + /* + * This field is generally used for per sub-function flags (defined + * below), except for the XEN_EFI_get_next_high_monotonic_count case, + * where it holds the single returned value. + */ + uint32_t misc; + xen_ulong_t status; + union { +#define XEN_EFI_GET_TIME_SET_CLEARS_NS 0x00000001 + struct { + struct xenpf_efi_time { + uint16_t year; + uint8_t month; + uint8_t day; + uint8_t hour; + uint8_t min; + uint8_t sec; + uint32_t ns; + int16_t tz; + uint8_t daylight; + } time; + uint32_t resolution; + uint32_t accuracy; + } get_time; + + struct xenpf_efi_time set_time; + +#define XEN_EFI_GET_WAKEUP_TIME_ENABLED 0x00000001 +#define XEN_EFI_GET_WAKEUP_TIME_PENDING 0x00000002 + struct xenpf_efi_time get_wakeup_time; + +#define XEN_EFI_SET_WAKEUP_TIME_ENABLE 0x00000001 +#define XEN_EFI_SET_WAKEUP_TIME_ENABLE_ONLY 0x00000002 + struct xenpf_efi_time set_wakeup_time; + +#define XEN_EFI_VARIABLE_NON_VOLATILE 0x00000001 +#define XEN_EFI_VARIABLE_BOOTSERVICE_ACCESS 0x00000002 +#define XEN_EFI_VARIABLE_RUNTIME_ACCESS 0x00000004 + struct { + GUEST_HANDLE(void) name; /* UCS-2/UTF-16 string */ + xen_ulong_t size; + GUEST_HANDLE(void) data; + struct xenpf_efi_guid { + uint32_t data1; + uint16_t data2; + uint16_t data3; + uint8_t data4[8]; + } vendor_guid; + } get_variable, set_variable; + + struct { + xen_ulong_t size; + GUEST_HANDLE(void) name; /* UCS-2/UTF-16 string */ + struct xenpf_efi_guid vendor_guid; + } get_next_variable_name; + + struct { + uint32_t attr; + uint64_t max_store_size; + uint64_t remain_store_size; + uint64_t max_size; + } query_variable_info; + + struct { + GUEST_HANDLE(void) capsule_header_array; + xen_ulong_t capsule_count; + uint64_t max_capsule_size; + uint32_t reset_type; + } query_capsule_capabilities; + + struct { + GUEST_HANDLE(void) capsule_header_array; + xen_ulong_t capsule_count; + uint64_t sg_list; /* machine address */ + } update_capsule; + } u; +}; +DEFINE_GUEST_HANDLE_STRUCT(xenpf_efi_runtime_call); + +#define XEN_FW_EFI_VERSION 0 +#define XEN_FW_EFI_CONFIG_TABLE 1 +#define XEN_FW_EFI_VENDOR 2 +#define XEN_FW_EFI_MEM_INFO 3 +#define XEN_FW_EFI_RT_VERSION 4 + #define XENPF_firmware_info 50 #define XEN_FW_DISK_INFO 1 /* from int 13 AH=08/41/48 */ #define XEN_FW_DISK_MBR_SIGNATURE 2 /* from MBR offset 0x1b8 */ #define XEN_FW_VBEDDC_INFO 3 /* from int 10 AX=4f15 */ +#define XEN_FW_EFI_INFO 4 /* from EFI */ #define XEN_FW_KBD_SHIFT_FLAGS 5 /* Int16, Fn02: Get keyboard shift flags. */ + struct xenpf_firmware_info { /* IN variables. */ uint32_t type; @@ -144,6 +246,26 @@ struct xenpf_firmware_info { GUEST_HANDLE(uchar) edid; } vbeddc_info; /* XEN_FW_VBEDDC_INFO */ + union xenpf_efi_info { + uint32_t version; + struct { + uint64_t addr; /* EFI_CONFIGURATION_TABLE */ + uint32_t nent; + } cfg; + struct { + uint32_t revision; + uint32_t bufsz; /* input, in bytes */ + GUEST_HANDLE(void) name; + /* UCS-2/UTF-16 string */ + } vendor; + struct { + uint64_t addr; + uint64_t size; + uint64_t attr; + uint32_t type; + } mem; + } efi_info; /* XEN_FW_EFI_INFO */ + uint8_t kbd_shift_flags; /* XEN_FW_KBD_SHIFT_FLAGS */ } u; }; @@ -362,6 +484,7 @@ struct xen_platform_op { struct xenpf_read_memtype read_memtype; struct xenpf_microcode_update microcode; struct xenpf_platform_quirk platform_quirk; + struct xenpf_efi_runtime_call efi_runtime_call; struct xenpf_firmware_info firmware_info; struct xenpf_enter_acpi_sleep enter_acpi_sleep; struct xenpf_change_freq change_freq; diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 0b3149ed7eaa..7491ee5d8164 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -3,6 +3,7 @@ #include <linux/percpu.h> #include <linux/notifier.h> +#include <linux/efi.h> #include <asm/xen/interface.h> DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu); @@ -35,4 +36,14 @@ int xen_unmap_domain_mfn_range(struct vm_area_struct *vma, int numpgs, struct page **pages); bool xen_running_on_version_or_later(unsigned int major, unsigned int minor); + +#ifdef CONFIG_XEN_EFI +extern efi_system_table_t *xen_efi_probe(void); +#else +static inline efi_system_table_t __init *xen_efi_probe(void) +{ + return NULL; +} +#endif + #endif /* INCLUDE_XEN_OPS_H */ diff --git a/init/Kconfig b/init/Kconfig index 8cd4343456f8..85fb9851b326 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -505,7 +505,7 @@ config PREEMPT_RCU def_bool TREE_PREEMPT_RCU help This option enables preemptible-RCU code that is common between - the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations. + TREE_PREEMPT_RCU and, in the old days, TINY_PREEMPT_RCU. config RCU_STALL_COMMON def_bool ( TREE_RCU || TREE_PREEMPT_RCU || RCU_TRACE ) @@ -737,7 +737,7 @@ choice config RCU_NOCB_CPU_NONE bool "No build_forced no-CBs CPUs" - depends on RCU_NOCB_CPU && !NO_HZ_FULL + depends on RCU_NOCB_CPU && !NO_HZ_FULL_ALL help This option does not force any of the CPUs to be no-CBs CPUs. Only CPUs designated by the rcu_nocbs= boot parameter will be @@ -751,7 +751,7 @@ config RCU_NOCB_CPU_NONE config RCU_NOCB_CPU_ZERO bool "CPU 0 is a build_forced no-CBs CPU" - depends on RCU_NOCB_CPU && !NO_HZ_FULL + depends on RCU_NOCB_CPU && !NO_HZ_FULL_ALL help This option forces CPU 0 to be a no-CBs CPU, so that its RCU callbacks are invoked by a per-CPU kthread whose name begins diff --git a/kernel/Makefile b/kernel/Makefile index e7360b7c2c0e..0026cf531769 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -3,12 +3,11 @@ # obj-y = fork.o exec_domain.o panic.o \ - cpu.o exit.o itimer.o time.o softirq.o resource.o \ - sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \ + cpu.o exit.o softirq.o resource.o \ + sysctl.o sysctl_binary.o capability.o ptrace.o user.o \ signal.o sys.o kmod.o workqueue.o pid.o task_work.o \ - extable.o params.o posix-timers.o \ - kthread.o sys_ni.o posix-cpu-timers.o \ - hrtimer.o nsproxy.o \ + extable.o params.o \ + kthread.o sys_ni.o nsproxy.o \ notifier.o ksysfs.o cred.o reboot.o \ async.o range.o groups.o smpboot.o @@ -111,22 +110,6 @@ targets += config_data.h $(obj)/config_data.h: $(obj)/config_data.gz FORCE $(call filechk,ikconfiggz) -$(obj)/time.o: $(obj)/timeconst.h - -quiet_cmd_hzfile = HZFILE $@ - cmd_hzfile = echo "hz=$(CONFIG_HZ)" > $@ - -targets += hz.bc -$(obj)/hz.bc: $(objtree)/include/config/hz.h FORCE - $(call if_changed,hzfile) - -quiet_cmd_bc = BC $@ - cmd_bc = bc -q $(filter-out FORCE,$^) > $@ - -targets += timeconst.h -$(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE - $(call if_changed,bc) - ############################################################################### # # Roll all the X.509 certificates that we can find together and pull them into diff --git a/kernel/acct.c b/kernel/acct.c index 808a86ff229d..a1844f14c6d6 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -458,9 +458,7 @@ static void do_acct_process(struct bsd_acct_struct *acct, acct_t ac; mm_segment_t fs; unsigned long flim; - u64 elapsed; - u64 run_time; - struct timespec uptime; + u64 elapsed, run_time; struct tty_struct *tty; const struct cred *orig_cred; @@ -484,10 +482,8 @@ static void do_acct_process(struct bsd_acct_struct *acct, strlcpy(ac.ac_comm, current->comm, sizeof(ac.ac_comm)); /* calculate run_time in nsec*/ - do_posix_clock_monotonic_gettime(&uptime); - run_time = (u64)uptime.tv_sec*NSEC_PER_SEC + uptime.tv_nsec; - run_time -= (u64)current->group_leader->start_time.tv_sec * NSEC_PER_SEC - + current->group_leader->start_time.tv_nsec; + run_time = ktime_get_ns(); + run_time -= current->group_leader->start_time; /* convert nsec -> AHZ */ elapsed = nsec_to_AHZ(run_time); #if ACCT_VERSION==3 diff --git a/kernel/cpu.c b/kernel/cpu.c index a343bde710b1..81e2a388a0f6 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -274,21 +274,28 @@ void clear_tasks_mm_cpumask(int cpu) rcu_read_unlock(); } -static inline void check_for_tasks(int cpu) +static inline void check_for_tasks(int dead_cpu) { - struct task_struct *p; - cputime_t utime, stime; + struct task_struct *g, *p; - write_lock_irq(&tasklist_lock); - for_each_process(p) { - task_cputime(p, &utime, &stime); - if (task_cpu(p) == cpu && p->state == TASK_RUNNING && - (utime || stime)) - pr_warn("Task %s (pid = %d) is on cpu %d (state = %ld, flags = %x)\n", - p->comm, task_pid_nr(p), cpu, - p->state, p->flags); - } - write_unlock_irq(&tasklist_lock); + read_lock_irq(&tasklist_lock); + do_each_thread(g, p) { + if (!p->on_rq) + continue; + /* + * We do the check with unlocked task_rq(p)->lock. + * Order the reading to do not warn about a task, + * which was running on this cpu in the past, and + * it's just been woken on another cpu. + */ + rmb(); + if (task_cpu(p) != dead_cpu) + continue; + + pr_warn("Task %s (pid=%d) is on cpu %d (state=%ld, flags=%x)\n", + p->comm, task_pid_nr(p), dead_cpu, p->state, p->flags); + } while_each_thread(g, p); + read_unlock_irq(&tasklist_lock); } struct take_cpu_down_param { diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 2f7c760305ca..379650b984f8 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2472,7 +2472,7 @@ static void kdb_gmtime(struct timespec *tv, struct kdb_tm *tm) static void kdb_sysinfo(struct sysinfo *val) { struct timespec uptime; - do_posix_clock_monotonic_gettime(&uptime); + ktime_get_ts(&uptime); memset(val, 0, sizeof(*val)); val->uptime = uptime.tv_sec; val->loads[0] = avenrun[0]; diff --git a/kernel/delayacct.c b/kernel/delayacct.c index 54996b71e66d..ef90b04d783f 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -46,42 +46,25 @@ void __delayacct_tsk_init(struct task_struct *tsk) } /* - * Start accounting for a delay statistic using - * its starting timestamp (@start) + * Finish delay accounting for a statistic using its timestamps (@start), + * accumalator (@total) and @count */ - -static inline void delayacct_start(struct timespec *start) +static void delayacct_end(u64 *start, u64 *total, u32 *count) { - do_posix_clock_monotonic_gettime(start); -} - -/* - * Finish delay accounting for a statistic using - * its timestamps (@start, @end), accumalator (@total) and @count - */ - -static void delayacct_end(struct timespec *start, struct timespec *end, - u64 *total, u32 *count) -{ - struct timespec ts; - s64 ns; + s64 ns = ktime_get_ns() - *start; unsigned long flags; - do_posix_clock_monotonic_gettime(end); - ts = timespec_sub(*end, *start); - ns = timespec_to_ns(&ts); - if (ns < 0) - return; - - spin_lock_irqsave(¤t->delays->lock, flags); - *total += ns; - (*count)++; - spin_unlock_irqrestore(¤t->delays->lock, flags); + if (ns > 0) { + spin_lock_irqsave(¤t->delays->lock, flags); + *total += ns; + (*count)++; + spin_unlock_irqrestore(¤t->delays->lock, flags); + } } void __delayacct_blkio_start(void) { - delayacct_start(¤t->delays->blkio_start); + current->delays->blkio_start = ktime_get_ns(); } void __delayacct_blkio_end(void) @@ -89,35 +72,29 @@ void __delayacct_blkio_end(void) if (current->delays->flags & DELAYACCT_PF_SWAPIN) /* Swapin block I/O */ delayacct_end(¤t->delays->blkio_start, - ¤t->delays->blkio_end, ¤t->delays->swapin_delay, ¤t->delays->swapin_count); else /* Other block I/O */ delayacct_end(¤t->delays->blkio_start, - ¤t->delays->blkio_end, ¤t->delays->blkio_delay, ¤t->delays->blkio_count); } int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) { - s64 tmp; - unsigned long t1; - unsigned long long t2, t3; - unsigned long flags; - struct timespec ts; cputime_t utime, stime, stimescaled, utimescaled; + unsigned long long t2, t3; + unsigned long flags, t1; + s64 tmp; - tmp = (s64)d->cpu_run_real_total; task_cputime(tsk, &utime, &stime); - cputime_to_timespec(utime + stime, &ts); - tmp += timespec_to_ns(&ts); + tmp = (s64)d->cpu_run_real_total; + tmp += cputime_to_nsecs(utime + stime); d->cpu_run_real_total = (tmp < (s64)d->cpu_run_real_total) ? 0 : tmp; - tmp = (s64)d->cpu_scaled_run_real_total; task_cputime_scaled(tsk, &utimescaled, &stimescaled); - cputime_to_timespec(utimescaled + stimescaled, &ts); - tmp += timespec_to_ns(&ts); + tmp = (s64)d->cpu_scaled_run_real_total; + tmp += cputime_to_nsecs(utimescaled + stimescaled); d->cpu_scaled_run_real_total = (tmp < (s64)d->cpu_scaled_run_real_total) ? 0 : tmp; @@ -169,13 +146,12 @@ __u64 __delayacct_blkio_ticks(struct task_struct *tsk) void __delayacct_freepages_start(void) { - delayacct_start(¤t->delays->freepages_start); + current->delays->freepages_start = ktime_get_ns(); } void __delayacct_freepages_end(void) { delayacct_end(¤t->delays->freepages_start, - ¤t->delays->freepages_end, ¤t->delays->freepages_delay, ¤t->delays->freepages_count); } diff --git a/kernel/events/core.c b/kernel/events/core.c index 6b17ac1b0c2a..1cf24b3e42ec 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5266,6 +5266,12 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event) goto got_name; } else { + if (vma->vm_ops && vma->vm_ops->name) { + name = (char *) vma->vm_ops->name(vma); + if (name) + goto cpy_name; + } + name = (char *)arch_vma_name(vma); if (name) goto cpy_name; @@ -7804,7 +7810,7 @@ inherit_task_group(struct perf_event *event, struct task_struct *parent, /* * Initialize the perf_event context in task_struct */ -int perf_event_init_context(struct task_struct *child, int ctxn) +static int perf_event_init_context(struct task_struct *child, int ctxn) { struct perf_event_context *child_ctx, *parent_ctx; struct perf_event_context *cloned_ctx; diff --git a/kernel/fork.c b/kernel/fork.c index ed4bc339c9dc..fbd3497b221f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1137,7 +1137,6 @@ static void rt_mutex_init_task(struct task_struct *p) p->pi_waiters = RB_ROOT; p->pi_waiters_leftmost = NULL; p->pi_blocked_on = NULL; - p->pi_top_task = NULL; #endif } @@ -1303,9 +1302,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, posix_cpu_timers_init(p); - do_posix_clock_monotonic_gettime(&p->start_time); - p->real_start_time = p->start_time; - monotonic_to_bootbased(&p->real_start_time); + p->start_time = ktime_get_ns(); + p->real_start_time = ktime_get_boot_ns(); p->io_context = NULL; p->audit_context = NULL; if (clone_flags & CLONE_THREAD) diff --git a/kernel/futex.c b/kernel/futex.c index b632b5f3f094..d3a9d946d0b7 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -792,94 +792,91 @@ void exit_pi_state_list(struct task_struct *curr) * [10] There is no transient state which leaves owner and user space * TID out of sync. */ -static int -lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, - union futex_key *key, struct futex_pi_state **ps) + +/* + * Validate that the existing waiter has a pi_state and sanity check + * the pi_state against the user space value. If correct, attach to + * it. + */ +static int attach_to_pi_state(u32 uval, struct futex_pi_state *pi_state, + struct futex_pi_state **ps) { - struct futex_pi_state *pi_state = NULL; - struct futex_q *this, *next; - struct task_struct *p; pid_t pid = uval & FUTEX_TID_MASK; - plist_for_each_entry_safe(this, next, &hb->chain, list) { - if (match_futex(&this->key, key)) { - /* - * Sanity check the waiter before increasing - * the refcount and attaching to it. - */ - pi_state = this->pi_state; - /* - * Userspace might have messed up non-PI and - * PI futexes [3] - */ - if (unlikely(!pi_state)) - return -EINVAL; + /* + * Userspace might have messed up non-PI and PI futexes [3] + */ + if (unlikely(!pi_state)) + return -EINVAL; - WARN_ON(!atomic_read(&pi_state->refcount)); + WARN_ON(!atomic_read(&pi_state->refcount)); + /* + * Handle the owner died case: + */ + if (uval & FUTEX_OWNER_DIED) { + /* + * exit_pi_state_list sets owner to NULL and wakes the + * topmost waiter. The task which acquires the + * pi_state->rt_mutex will fixup owner. + */ + if (!pi_state->owner) { /* - * Handle the owner died case: + * No pi state owner, but the user space TID + * is not 0. Inconsistent state. [5] */ - if (uval & FUTEX_OWNER_DIED) { - /* - * exit_pi_state_list sets owner to NULL and - * wakes the topmost waiter. The task which - * acquires the pi_state->rt_mutex will fixup - * owner. - */ - if (!pi_state->owner) { - /* - * No pi state owner, but the user - * space TID is not 0. Inconsistent - * state. [5] - */ - if (pid) - return -EINVAL; - /* - * Take a ref on the state and - * return. [4] - */ - goto out_state; - } - - /* - * If TID is 0, then either the dying owner - * has not yet executed exit_pi_state_list() - * or some waiter acquired the rtmutex in the - * pi state, but did not yet fixup the TID in - * user space. - * - * Take a ref on the state and return. [6] - */ - if (!pid) - goto out_state; - } else { - /* - * If the owner died bit is not set, - * then the pi_state must have an - * owner. [7] - */ - if (!pi_state->owner) - return -EINVAL; - } - + if (pid) + return -EINVAL; /* - * Bail out if user space manipulated the - * futex value. If pi state exists then the - * owner TID must be the same as the user - * space TID. [9/10] + * Take a ref on the state and return success. [4] */ - if (pid != task_pid_vnr(pi_state->owner)) - return -EINVAL; - - out_state: - atomic_inc(&pi_state->refcount); - *ps = pi_state; - return 0; + goto out_state; } + + /* + * If TID is 0, then either the dying owner has not + * yet executed exit_pi_state_list() or some waiter + * acquired the rtmutex in the pi state, but did not + * yet fixup the TID in user space. + * + * Take a ref on the state and return success. [6] + */ + if (!pid) + goto out_state; + } else { + /* + * If the owner died bit is not set, then the pi_state + * must have an owner. [7] + */ + if (!pi_state->owner) + return -EINVAL; } /* + * Bail out if user space manipulated the futex value. If pi + * state exists then the owner TID must be the same as the + * user space TID. [9/10] + */ + if (pid != task_pid_vnr(pi_state->owner)) + return -EINVAL; +out_state: + atomic_inc(&pi_state->refcount); + *ps = pi_state; + return 0; +} + +/* + * Lookup the task for the TID provided from user space and attach to + * it after doing proper sanity checks. + */ +static int attach_to_pi_owner(u32 uval, union futex_key *key, + struct futex_pi_state **ps) +{ + pid_t pid = uval & FUTEX_TID_MASK; + struct futex_pi_state *pi_state; + struct task_struct *p; + + /* * We are the first waiter - try to look up the real owner and attach * the new pi_state to it, but bail out when TID = 0 [1] */ @@ -920,7 +917,7 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, pi_state = alloc_pi_state(); /* - * Initialize the pi_mutex in locked state and make 'p' + * Initialize the pi_mutex in locked state and make @p * the owner of it: */ rt_mutex_init_proxy_locked(&pi_state->pi_mutex, p); @@ -940,6 +937,36 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, return 0; } +static int lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, + union futex_key *key, struct futex_pi_state **ps) +{ + struct futex_q *match = futex_top_waiter(hb, key); + + /* + * If there is a waiter on that futex, validate it and + * attach to the pi_state when the validation succeeds. + */ + if (match) + return attach_to_pi_state(uval, match->pi_state, ps); + + /* + * We are the first waiter - try to look up the owner based on + * @uval and attach to it. + */ + return attach_to_pi_owner(uval, key, ps); +} + +static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval) +{ + u32 uninitialized_var(curval); + + if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))) + return -EFAULT; + + /*If user space value changed, let the caller retry */ + return curval != uval ? -EAGAIN : 0; +} + /** * futex_lock_pi_atomic() - Atomic work required to acquire a pi aware futex * @uaddr: the pi futex user address @@ -963,113 +990,69 @@ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb, struct futex_pi_state **ps, struct task_struct *task, int set_waiters) { - int lock_taken, ret, force_take = 0; - u32 uval, newval, curval, vpid = task_pid_vnr(task); - -retry: - ret = lock_taken = 0; + u32 uval, newval, vpid = task_pid_vnr(task); + struct futex_q *match; + int ret; /* - * To avoid races, we attempt to take the lock here again - * (by doing a 0 -> TID atomic cmpxchg), while holding all - * the locks. It will most likely not succeed. + * Read the user space value first so we can validate a few + * things before proceeding further. */ - newval = vpid; - if (set_waiters) - newval |= FUTEX_WAITERS; - - if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, 0, newval))) + if (get_futex_value_locked(&uval, uaddr)) return -EFAULT; /* * Detect deadlocks. */ - if ((unlikely((curval & FUTEX_TID_MASK) == vpid))) + if ((unlikely((uval & FUTEX_TID_MASK) == vpid))) return -EDEADLK; /* - * Surprise - we got the lock, but we do not trust user space at all. - */ - if (unlikely(!curval)) { - /* - * We verify whether there is kernel state for this - * futex. If not, we can safely assume, that the 0 -> - * TID transition is correct. If state exists, we do - * not bother to fixup the user space state as it was - * corrupted already. - */ - return futex_top_waiter(hb, key) ? -EINVAL : 1; - } - - uval = curval; - - /* - * Set the FUTEX_WAITERS flag, so the owner will know it has someone - * to wake at the next unlock. + * Lookup existing state first. If it exists, try to attach to + * its pi_state. */ - newval = curval | FUTEX_WAITERS; + match = futex_top_waiter(hb, key); + if (match) + return attach_to_pi_state(uval, match->pi_state, ps); /* - * Should we force take the futex? See below. + * No waiter and user TID is 0. We are here because the + * waiters or the owner died bit is set or called from + * requeue_cmp_pi or for whatever reason something took the + * syscall. */ - if (unlikely(force_take)) { + if (!(uval & FUTEX_TID_MASK)) { /* - * Keep the OWNER_DIED and the WAITERS bit and set the - * new TID value. + * We take over the futex. No other waiters and the user space + * TID is 0. We preserve the owner died bit. */ - newval = (curval & ~FUTEX_TID_MASK) | vpid; - force_take = 0; - lock_taken = 1; - } + newval = uval & FUTEX_OWNER_DIED; + newval |= vpid; - if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))) - return -EFAULT; - if (unlikely(curval != uval)) - goto retry; + /* The futex requeue_pi code can enforce the waiters bit */ + if (set_waiters) + newval |= FUTEX_WAITERS; + + ret = lock_pi_update_atomic(uaddr, uval, newval); + /* If the take over worked, return 1 */ + return ret < 0 ? ret : 1; + } /* - * We took the lock due to forced take over. + * First waiter. Set the waiters bit before attaching ourself to + * the owner. If owner tries to unlock, it will be forced into + * the kernel and blocked on hb->lock. */ - if (unlikely(lock_taken)) - return 1; - + newval = uval | FUTEX_WAITERS; + ret = lock_pi_update_atomic(uaddr, uval, newval); + if (ret) + return ret; /* - * We dont have the lock. Look up the PI state (or create it if - * we are the first waiter): + * If the update of the user space value succeeded, we try to + * attach to the owner. If that fails, no harm done, we only + * set the FUTEX_WAITERS bit in the user space variable. */ - ret = lookup_pi_state(uval, hb, key, ps); - - if (unlikely(ret)) { - switch (ret) { - case -ESRCH: - /* - * We failed to find an owner for this - * futex. So we have no pi_state to block - * on. This can happen in two cases: - * - * 1) The owner died - * 2) A stale FUTEX_WAITERS bit - * - * Re-read the futex value. - */ - if (get_futex_value_locked(&curval, uaddr)) - return -EFAULT; - - /* - * If the owner died or we have a stale - * WAITERS bit the owner TID in the user space - * futex is 0. - */ - if (!(curval & FUTEX_TID_MASK)) { - force_take = 1; - goto retry; - } - default: - break; - } - } - - return ret; + return attach_to_pi_owner(uval, key, ps); } /** @@ -1186,22 +1169,6 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this) return 0; } -static int unlock_futex_pi(u32 __user *uaddr, u32 uval) -{ - u32 uninitialized_var(oldval); - - /* - * There is no waiter, so we unlock the futex. The owner died - * bit has not to be preserved here. We are the owner: - */ - if (cmpxchg_futex_value_locked(&oldval, uaddr, uval, 0)) - return -EFAULT; - if (oldval != uval) - return -EAGAIN; - - return 0; -} - /* * Express the locking dependencies for lockdep: */ @@ -1659,7 +1626,12 @@ retry_private: goto retry; goto out; case -EAGAIN: - /* The owner was exiting, try again. */ + /* + * Two reasons for this: + * - Owner is exiting and we just wait for the + * exit to complete. + * - The user space value changed. + */ double_unlock_hb(hb1, hb2); hb_waiters_dec(hb2); put_futex_key(&key2); @@ -1718,7 +1690,7 @@ retry_private: this->pi_state = pi_state; ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex, this->rt_waiter, - this->task, 1); + this->task); if (ret == 1) { /* We got the lock. */ requeue_pi_wake_futex(this, &key2, hb2); @@ -2316,8 +2288,10 @@ retry_private: goto uaddr_faulted; case -EAGAIN: /* - * Task is exiting and we just wait for the - * exit to complete. + * Two reasons for this: + * - Task is exiting and we just wait for the + * exit to complete. + * - The user space value changed. */ queue_unlock(hb); put_futex_key(&q.key); @@ -2337,9 +2311,9 @@ retry_private: /* * Block on the PI mutex: */ - if (!trylock) - ret = rt_mutex_timed_lock(&q.pi_state->pi_mutex, to, 1); - else { + if (!trylock) { + ret = rt_mutex_timed_futex_lock(&q.pi_state->pi_mutex, to); + } else { ret = rt_mutex_trylock(&q.pi_state->pi_mutex); /* Fixup the trylock return value: */ ret = ret ? 0 : -EWOULDBLOCK; @@ -2401,10 +2375,10 @@ uaddr_faulted: */ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) { - struct futex_hash_bucket *hb; - struct futex_q *this, *next; + u32 uninitialized_var(curval), uval, vpid = task_pid_vnr(current); union futex_key key = FUTEX_KEY_INIT; - u32 uval, vpid = task_pid_vnr(current); + struct futex_hash_bucket *hb; + struct futex_q *match; int ret; retry: @@ -2417,57 +2391,47 @@ retry: return -EPERM; ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, VERIFY_WRITE); - if (unlikely(ret != 0)) - goto out; + if (ret) + return ret; hb = hash_futex(&key); spin_lock(&hb->lock); /* - * To avoid races, try to do the TID -> 0 atomic transition - * again. If it succeeds then we can return without waking - * anyone else up. We only try this if neither the waiters nor - * the owner died bit are set. - */ - if (!(uval & ~FUTEX_TID_MASK) && - cmpxchg_futex_value_locked(&uval, uaddr, vpid, 0)) - goto pi_faulted; - /* - * Rare case: we managed to release the lock atomically, - * no need to wake anyone else up: - */ - if (unlikely(uval == vpid)) - goto out_unlock; - - /* - * Ok, other tasks may need to be woken up - check waiters - * and do the wakeup if necessary: + * Check waiters first. We do not trust user space values at + * all and we at least want to know if user space fiddled + * with the futex value instead of blindly unlocking. */ - plist_for_each_entry_safe(this, next, &hb->chain, list) { - if (!match_futex (&this->key, &key)) - continue; - ret = wake_futex_pi(uaddr, uval, this); + match = futex_top_waiter(hb, &key); + if (match) { + ret = wake_futex_pi(uaddr, uval, match); /* - * The atomic access to the futex value - * generated a pagefault, so retry the - * user-access and the wakeup: + * The atomic access to the futex value generated a + * pagefault, so retry the user-access and the wakeup: */ if (ret == -EFAULT) goto pi_faulted; goto out_unlock; } + /* - * No waiters - kernel unlocks the futex: + * We have no kernel internal state, i.e. no waiters in the + * kernel. Waiters which are about to queue themselves are stuck + * on hb->lock. So we can safely ignore them. We do neither + * preserve the WAITERS bit not the OWNER_DIED one. We are the + * owner. */ - ret = unlock_futex_pi(uaddr, uval); - if (ret == -EFAULT) + if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0)) goto pi_faulted; + /* + * If uval has changed, let user space handle it. + */ + ret = (curval == uval) ? 0 : -EAGAIN; + out_unlock: spin_unlock(&hb->lock); put_futex_key(&key); - -out: return ret; pi_faulted: @@ -2669,7 +2633,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, */ WARN_ON(!q.pi_state); pi_mutex = &q.pi_state->pi_mutex; - ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter, 1); + ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter); debug_rt_mutex_free_waiter(&rt_waiter); spin_lock(q.lock_ptr); diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index 452d6f2ba21d..cf80e7b0ddab 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -341,8 +341,8 @@ static struct lock_class_key irq_nested_lock_class; /* * irq_map_generic_chip - Map a generic chip for an irq domain */ -static int irq_map_generic_chip(struct irq_domain *d, unsigned int virq, - irq_hw_number_t hw_irq) +int irq_map_generic_chip(struct irq_domain *d, unsigned int virq, + irq_hw_number_t hw_irq) { struct irq_data *data = irq_get_irq_data(virq); struct irq_domain_chip_generic *dgc = d->gc; @@ -394,6 +394,7 @@ static int irq_map_generic_chip(struct irq_domain *d, unsigned int virq, irq_modify_status(virq, dgc->irq_flags_to_clear, dgc->irq_flags_to_set); return 0; } +EXPORT_SYMBOL_GPL(irq_map_generic_chip); struct irq_domain_ops irq_generic_chip_ops = { .map = irq_map_generic_chip, diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index eb5e10e32e05..6534ff6ce02e 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -231,7 +231,7 @@ void irq_set_default_host(struct irq_domain *domain) } EXPORT_SYMBOL_GPL(irq_set_default_host); -static void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq) +void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq) { struct irq_data *irq_data = irq_get_irq_data(irq); irq_hw_number_t hwirq; diff --git a/kernel/irq_work.c b/kernel/irq_work.c index a82170e2fa78..e6bcbe756663 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -16,11 +16,12 @@ #include <linux/tick.h> #include <linux/cpu.h> #include <linux/notifier.h> +#include <linux/smp.h> #include <asm/processor.h> -static DEFINE_PER_CPU(struct llist_head, irq_work_list); -static DEFINE_PER_CPU(int, irq_work_raised); +static DEFINE_PER_CPU(struct llist_head, raised_list); +static DEFINE_PER_CPU(struct llist_head, lazy_list); /* * Claim the entry so that no one else will poke at it. @@ -55,12 +56,34 @@ void __weak arch_irq_work_raise(void) */ } +#ifdef CONFIG_SMP /* - * Enqueue the irq_work @entry unless it's already pending + * Enqueue the irq_work @work on @cpu unless it's already pending * somewhere. * * Can be re-enqueued while the callback is still in progress. */ +bool irq_work_queue_on(struct irq_work *work, int cpu) +{ + /* All work should have been flushed before going offline */ + WARN_ON_ONCE(cpu_is_offline(cpu)); + + /* Arch remote IPI send/receive backend aren't NMI safe */ + WARN_ON_ONCE(in_nmi()); + + /* Only queue if not already pending */ + if (!irq_work_claim(work)) + return false; + + if (llist_add(&work->llnode, &per_cpu(raised_list, cpu))) + arch_send_call_function_single_ipi(cpu); + + return true; +} +EXPORT_SYMBOL_GPL(irq_work_queue_on); +#endif + +/* Enqueue the irq work @work on the current CPU */ bool irq_work_queue(struct irq_work *work) { /* Only queue if not already pending */ @@ -70,15 +93,13 @@ bool irq_work_queue(struct irq_work *work) /* Queue the entry and raise the IPI if needed. */ preempt_disable(); - llist_add(&work->llnode, &__get_cpu_var(irq_work_list)); - - /* - * If the work is not "lazy" or the tick is stopped, raise the irq - * work interrupt (if supported by the arch), otherwise, just wait - * for the next tick. - */ - if (!(work->flags & IRQ_WORK_LAZY) || tick_nohz_tick_stopped()) { - if (!this_cpu_cmpxchg(irq_work_raised, 0, 1)) + /* If the work is "lazy", handle it from next tick if any */ + if (work->flags & IRQ_WORK_LAZY) { + if (llist_add(&work->llnode, &__get_cpu_var(lazy_list)) && + tick_nohz_tick_stopped()) + arch_irq_work_raise(); + } else { + if (llist_add(&work->llnode, &__get_cpu_var(raised_list))) arch_irq_work_raise(); } @@ -90,10 +111,11 @@ EXPORT_SYMBOL_GPL(irq_work_queue); bool irq_work_needs_cpu(void) { - struct llist_head *this_list; + struct llist_head *raised, *lazy; - this_list = &__get_cpu_var(irq_work_list); - if (llist_empty(this_list)) + raised = &__get_cpu_var(raised_list); + lazy = &__get_cpu_var(lazy_list); + if (llist_empty(raised) && llist_empty(lazy)) return false; /* All work should have been flushed before going offline */ @@ -102,28 +124,18 @@ bool irq_work_needs_cpu(void) return true; } -static void __irq_work_run(void) +static void irq_work_run_list(struct llist_head *list) { unsigned long flags; struct irq_work *work; - struct llist_head *this_list; struct llist_node *llnode; + BUG_ON(!irqs_disabled()); - /* - * Reset the "raised" state right before we check the list because - * an NMI may enqueue after we find the list empty from the runner. - */ - __this_cpu_write(irq_work_raised, 0); - barrier(); - - this_list = &__get_cpu_var(irq_work_list); - if (llist_empty(this_list)) + if (llist_empty(list)) return; - BUG_ON(!irqs_disabled()); - - llnode = llist_del_all(this_list); + llnode = llist_del_all(list); while (llnode != NULL) { work = llist_entry(llnode, struct irq_work, llnode); @@ -149,13 +161,13 @@ static void __irq_work_run(void) } /* - * Run the irq_work entries on this cpu. Requires to be ran from hardirq - * context with local IRQs disabled. + * hotplug calls this through: + * hotplug_cfd() -> flush_smp_call_function_queue() */ void irq_work_run(void) { - BUG_ON(!in_irq()); - __irq_work_run(); + irq_work_run_list(&__get_cpu_var(raised_list)); + irq_work_run_list(&__get_cpu_var(lazy_list)); } EXPORT_SYMBOL_GPL(irq_work_run); @@ -171,35 +183,3 @@ void irq_work_sync(struct irq_work *work) cpu_relax(); } EXPORT_SYMBOL_GPL(irq_work_sync); - -#ifdef CONFIG_HOTPLUG_CPU -static int irq_work_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) -{ - long cpu = (long)hcpu; - - switch (action) { - case CPU_DYING: - /* Called from stop_machine */ - if (WARN_ON_ONCE(cpu != smp_processor_id())) - break; - __irq_work_run(); - break; - default: - break; - } - return NOTIFY_OK; -} - -static struct notifier_block cpu_notify; - -static __init int irq_work_init_cpu_notifier(void) -{ - cpu_notify.notifier_call = irq_work_cpu_notify; - cpu_notify.priority = 0; - register_cpu_notifier(&cpu_notify); - return 0; -} -device_initcall(irq_work_init_cpu_notifier); - -#endif /* CONFIG_HOTPLUG_CPU */ diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index d24e4339b46d..88d0d4420ad2 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -384,7 +384,9 @@ static void print_lockdep_off(const char *bug_msg) { printk(KERN_DEBUG "%s\n", bug_msg); printk(KERN_DEBUG "turning off the locking correctness validator.\n"); +#ifdef CONFIG_LOCK_STAT printk(KERN_DEBUG "Please attach the output of /proc/lock_stat to the bug report\n"); +#endif } static int save_trace(struct stack_trace *trace) diff --git a/kernel/locking/mcs_spinlock.c b/kernel/locking/mcs_spinlock.c index be9ee1559fca..9887a905a762 100644 --- a/kernel/locking/mcs_spinlock.c +++ b/kernel/locking/mcs_spinlock.c @@ -1,6 +1,4 @@ - #include <linux/percpu.h> -#include <linux/mutex.h> #include <linux/sched.h> #include "mcs_spinlock.h" @@ -79,7 +77,7 @@ osq_wait_next(struct optimistic_spin_queue *lock, break; } - arch_mutex_cpu_relax(); + cpu_relax_lowlatency(); } return next; @@ -120,7 +118,7 @@ bool osq_lock(struct optimistic_spin_queue *lock) if (need_resched()) goto unqueue; - arch_mutex_cpu_relax(); + cpu_relax_lowlatency(); } return true; @@ -146,7 +144,7 @@ unqueue: if (smp_load_acquire(&node->locked)) return true; - arch_mutex_cpu_relax(); + cpu_relax_lowlatency(); /* * Or we race against a concurrent unqueue()'s step-B, in which diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h index 74356dc0ce29..23e89c5930e9 100644 --- a/kernel/locking/mcs_spinlock.h +++ b/kernel/locking/mcs_spinlock.h @@ -27,7 +27,7 @@ struct mcs_spinlock { #define arch_mcs_spin_lock_contended(l) \ do { \ while (!(smp_load_acquire(l))) \ - arch_mutex_cpu_relax(); \ + cpu_relax_lowlatency(); \ } while (0) #endif @@ -104,7 +104,7 @@ void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node) return; /* Wait until the next pointer is set */ while (!(next = ACCESS_ONCE(node->next))) - arch_mutex_cpu_relax(); + cpu_relax_lowlatency(); } /* Pass lock to next waiter. */ diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index acca2c1a3c5e..ae712b25e492 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -46,12 +46,6 @@ # include <asm/mutex.h> #endif -/* - * A negative mutex count indicates that waiters are sleeping waiting for the - * mutex. - */ -#define MUTEX_SHOW_NO_WAITER(mutex) (atomic_read(&(mutex)->count) >= 0) - void __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key) { @@ -152,7 +146,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) if (need_resched()) break; - arch_mutex_cpu_relax(); + cpu_relax_lowlatency(); } rcu_read_unlock(); @@ -388,12 +382,10 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, /* * Optimistic spinning. * - * We try to spin for acquisition when we find that there are no - * pending waiters and the lock owner is currently running on a - * (different) CPU. - * - * The rationale is that if the lock owner is running, it is likely to - * release the lock soon. + * We try to spin for acquisition when we find that the lock owner + * is currently running on a (different) CPU and while we don't + * need to reschedule. The rationale is that if the lock owner is + * running, it is likely to release the lock soon. * * Since this needs the lock owner, and this mutex implementation * doesn't track the owner atomically in the lock field, we need to @@ -440,7 +432,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, if (owner && !mutex_spin_on_owner(lock, owner)) break; - if ((atomic_read(&lock->count) == 1) && + /* Try to acquire the mutex if it is unlocked. */ + if (!mutex_is_locked(lock) && (atomic_cmpxchg(&lock->count, 1, 0) == 1)) { lock_acquired(&lock->dep_map, ip); if (use_ww_ctx) { @@ -471,7 +464,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, * memory barriers as we'll eventually observe the right * values at the cost of a few extra spins. */ - arch_mutex_cpu_relax(); + cpu_relax_lowlatency(); } osq_unlock(&lock->osq); slowpath: @@ -485,8 +478,11 @@ slowpath: #endif spin_lock_mutex(&lock->wait_lock, flags); - /* once more, can we acquire the lock? */ - if (MUTEX_SHOW_NO_WAITER(lock) && (atomic_xchg(&lock->count, 0) == 1)) + /* + * Once more, try to acquire the lock. Only try-lock the mutex if + * it is unlocked to reduce unnecessary xchg() operations. + */ + if (!mutex_is_locked(lock) && (atomic_xchg(&lock->count, 0) == 1)) goto skip_wait; debug_mutex_lock_common(lock, &waiter); @@ -506,9 +502,10 @@ slowpath: * it's unlocked. Later on, if we sleep, this is the * operation that gives us the lock. We xchg it to -1, so * that when we release the lock, we properly wake up the - * other waiters: + * other waiters. We only attempt the xchg if the count is + * non-negative in order to avoid unnecessary xchg operations: */ - if (MUTEX_SHOW_NO_WAITER(lock) && + if (atomic_read(&lock->count) >= 0 && (atomic_xchg(&lock->count, -1) == 1)) break; @@ -823,6 +820,10 @@ static inline int __mutex_trylock_slowpath(atomic_t *lock_count) unsigned long flags; int prev; + /* No need to trylock if the mutex is locked. */ + if (mutex_is_locked(lock)) + return 0; + spin_lock_mutex(&lock->wait_lock, flags); prev = atomic_xchg(&lock->count, -1); diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c index fb5b8ac411a5..f956ede7f90d 100644 --- a/kernel/locking/qrwlock.c +++ b/kernel/locking/qrwlock.c @@ -20,7 +20,6 @@ #include <linux/cpumask.h> #include <linux/percpu.h> #include <linux/hardirq.h> -#include <linux/mutex.h> #include <asm/qrwlock.h> /** @@ -35,7 +34,7 @@ static __always_inline void rspin_until_writer_unlock(struct qrwlock *lock, u32 cnts) { while ((cnts & _QW_WMASK) == _QW_LOCKED) { - arch_mutex_cpu_relax(); + cpu_relax_lowlatency(); cnts = smp_load_acquire((u32 *)&lock->cnts); } } @@ -75,7 +74,7 @@ void queue_read_lock_slowpath(struct qrwlock *lock) * to make sure that the write lock isn't taken. */ while (atomic_read(&lock->cnts) & _QW_WMASK) - arch_mutex_cpu_relax(); + cpu_relax_lowlatency(); cnts = atomic_add_return(_QR_BIAS, &lock->cnts) - _QR_BIAS; rspin_until_writer_unlock(lock, cnts); @@ -114,7 +113,7 @@ void queue_write_lock_slowpath(struct qrwlock *lock) cnts | _QW_WAITING) == cnts)) break; - arch_mutex_cpu_relax(); + cpu_relax_lowlatency(); } /* When no more readers, set the locked flag */ @@ -125,7 +124,7 @@ void queue_write_lock_slowpath(struct qrwlock *lock) _QW_LOCKED) == _QW_WAITING)) break; - arch_mutex_cpu_relax(); + cpu_relax_lowlatency(); } unlock: arch_spin_unlock(&lock->lock); diff --git a/kernel/locking/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c index 49b2ed3dced8..62b6cee8ea7f 100644 --- a/kernel/locking/rtmutex-debug.c +++ b/kernel/locking/rtmutex-debug.c @@ -66,12 +66,13 @@ void rt_mutex_debug_task_free(struct task_struct *task) * the deadlock. We print when we return. act_waiter can be NULL in * case of a remove waiter operation. */ -void debug_rt_mutex_deadlock(int detect, struct rt_mutex_waiter *act_waiter, +void debug_rt_mutex_deadlock(enum rtmutex_chainwalk chwalk, + struct rt_mutex_waiter *act_waiter, struct rt_mutex *lock) { struct task_struct *task; - if (!debug_locks || detect || !act_waiter) + if (!debug_locks || chwalk == RT_MUTEX_FULL_CHAINWALK || !act_waiter) return; task = rt_mutex_owner(act_waiter->lock); diff --git a/kernel/locking/rtmutex-debug.h b/kernel/locking/rtmutex-debug.h index ab29b6a22669..d0519c3432b6 100644 --- a/kernel/locking/rtmutex-debug.h +++ b/kernel/locking/rtmutex-debug.h @@ -20,14 +20,15 @@ extern void debug_rt_mutex_unlock(struct rt_mutex *lock); extern void debug_rt_mutex_proxy_lock(struct rt_mutex *lock, struct task_struct *powner); extern void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock); -extern void debug_rt_mutex_deadlock(int detect, struct rt_mutex_waiter *waiter, +extern void debug_rt_mutex_deadlock(enum rtmutex_chainwalk chwalk, + struct rt_mutex_waiter *waiter, struct rt_mutex *lock); extern void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter); # define debug_rt_mutex_reset_waiter(w) \ do { (w)->deadlock_lock = NULL; } while (0) -static inline int debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter, - int detect) +static inline bool debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter, + enum rtmutex_chainwalk walk) { return (waiter != NULL); } diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index fc605941b9b8..a0ea2a141b3b 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -308,6 +308,32 @@ static void rt_mutex_adjust_prio(struct task_struct *task) } /* + * Deadlock detection is conditional: + * + * If CONFIG_DEBUG_RT_MUTEXES=n, deadlock detection is only conducted + * if the detect argument is == RT_MUTEX_FULL_CHAINWALK. + * + * If CONFIG_DEBUG_RT_MUTEXES=y, deadlock detection is always + * conducted independent of the detect argument. + * + * If the waiter argument is NULL this indicates the deboost path and + * deadlock detection is disabled independent of the detect argument + * and the config settings. + */ +static bool rt_mutex_cond_detect_deadlock(struct rt_mutex_waiter *waiter, + enum rtmutex_chainwalk chwalk) +{ + /* + * This is just a wrapper function for the following call, + * because debug_rt_mutex_detect_deadlock() smells like a magic + * debug feature and I wanted to keep the cond function in the + * main source file along with the comments instead of having + * two of the same in the headers. + */ + return debug_rt_mutex_detect_deadlock(waiter, chwalk); +} + +/* * Max number of times we'll walk the boosting chain: */ int max_lock_depth = 1024; @@ -337,21 +363,65 @@ static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p) * @top_task: the current top waiter * * Returns 0 or -EDEADLK. + * + * Chain walk basics and protection scope + * + * [R] refcount on task + * [P] task->pi_lock held + * [L] rtmutex->wait_lock held + * + * Step Description Protected by + * function arguments: + * @task [R] + * @orig_lock if != NULL @top_task is blocked on it + * @next_lock Unprotected. Cannot be + * dereferenced. Only used for + * comparison. + * @orig_waiter if != NULL @top_task is blocked on it + * @top_task current, or in case of proxy + * locking protected by calling + * code + * again: + * loop_sanity_check(); + * retry: + * [1] lock(task->pi_lock); [R] acquire [P] + * [2] waiter = task->pi_blocked_on; [P] + * [3] check_exit_conditions_1(); [P] + * [4] lock = waiter->lock; [P] + * [5] if (!try_lock(lock->wait_lock)) { [P] try to acquire [L] + * unlock(task->pi_lock); release [P] + * goto retry; + * } + * [6] check_exit_conditions_2(); [P] + [L] + * [7] requeue_lock_waiter(lock, waiter); [P] + [L] + * [8] unlock(task->pi_lock); release [P] + * put_task_struct(task); release [R] + * [9] check_exit_conditions_3(); [L] + * [10] task = owner(lock); [L] + * get_task_struct(task); [L] acquire [R] + * lock(task->pi_lock); [L] acquire [P] + * [11] requeue_pi_waiter(tsk, waiters(lock));[P] + [L] + * [12] check_exit_conditions_4(); [P] + [L] + * [13] unlock(task->pi_lock); release [P] + * unlock(lock->wait_lock); release [L] + * goto again; */ static int rt_mutex_adjust_prio_chain(struct task_struct *task, - int deadlock_detect, + enum rtmutex_chainwalk chwalk, struct rt_mutex *orig_lock, struct rt_mutex *next_lock, struct rt_mutex_waiter *orig_waiter, struct task_struct *top_task) { - struct rt_mutex *lock; struct rt_mutex_waiter *waiter, *top_waiter = orig_waiter; - int detect_deadlock, ret = 0, depth = 0; + struct rt_mutex_waiter *prerequeue_top_waiter; + int ret = 0, depth = 0; + struct rt_mutex *lock; + bool detect_deadlock; unsigned long flags; + bool requeue = true; - detect_deadlock = debug_rt_mutex_detect_deadlock(orig_waiter, - deadlock_detect); + detect_deadlock = rt_mutex_cond_detect_deadlock(orig_waiter, chwalk); /* * The (de)boosting is a step by step approach with a lot of @@ -360,6 +430,9 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * carefully whether things change under us. */ again: + /* + * We limit the lock chain length for each invocation. + */ if (++depth > max_lock_depth) { static int prev_max; @@ -377,13 +450,28 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, return -EDEADLK; } + + /* + * We are fully preemptible here and only hold the refcount on + * @task. So everything can have changed under us since the + * caller or our own code below (goto retry/again) dropped all + * locks. + */ retry: /* - * Task can not go away as we did a get_task() before ! + * [1] Task cannot go away as we did a get_task() before ! */ raw_spin_lock_irqsave(&task->pi_lock, flags); + /* + * [2] Get the waiter on which @task is blocked on. + */ waiter = task->pi_blocked_on; + + /* + * [3] check_exit_conditions_1() protected by task->pi_lock. + */ + /* * Check whether the end of the boosting chain has been * reached or the state of the chain has changed while we @@ -421,20 +509,41 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, goto out_unlock_pi; /* * If deadlock detection is off, we stop here if we - * are not the top pi waiter of the task. + * are not the top pi waiter of the task. If deadlock + * detection is enabled we continue, but stop the + * requeueing in the chain walk. */ - if (!detect_deadlock && top_waiter != task_top_pi_waiter(task)) - goto out_unlock_pi; + if (top_waiter != task_top_pi_waiter(task)) { + if (!detect_deadlock) + goto out_unlock_pi; + else + requeue = false; + } } /* - * When deadlock detection is off then we check, if further - * priority adjustment is necessary. + * If the waiter priority is the same as the task priority + * then there is no further priority adjustment necessary. If + * deadlock detection is off, we stop the chain walk. If its + * enabled we continue, but stop the requeueing in the chain + * walk. */ - if (!detect_deadlock && waiter->prio == task->prio) - goto out_unlock_pi; + if (waiter->prio == task->prio) { + if (!detect_deadlock) + goto out_unlock_pi; + else + requeue = false; + } + /* + * [4] Get the next lock + */ lock = waiter->lock; + /* + * [5] We need to trylock here as we are holding task->pi_lock, + * which is the reverse lock order versus the other rtmutex + * operations. + */ if (!raw_spin_trylock(&lock->wait_lock)) { raw_spin_unlock_irqrestore(&task->pi_lock, flags); cpu_relax(); @@ -442,79 +551,180 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, } /* + * [6] check_exit_conditions_2() protected by task->pi_lock and + * lock->wait_lock. + * * Deadlock detection. If the lock is the same as the original * lock which caused us to walk the lock chain or if the * current lock is owned by the task which initiated the chain * walk, we detected a deadlock. */ if (lock == orig_lock || rt_mutex_owner(lock) == top_task) { - debug_rt_mutex_deadlock(deadlock_detect, orig_waiter, lock); + debug_rt_mutex_deadlock(chwalk, orig_waiter, lock); raw_spin_unlock(&lock->wait_lock); ret = -EDEADLK; goto out_unlock_pi; } - top_waiter = rt_mutex_top_waiter(lock); + /* + * If we just follow the lock chain for deadlock detection, no + * need to do all the requeue operations. To avoid a truckload + * of conditionals around the various places below, just do the + * minimum chain walk checks. + */ + if (!requeue) { + /* + * No requeue[7] here. Just release @task [8] + */ + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + put_task_struct(task); + + /* + * [9] check_exit_conditions_3 protected by lock->wait_lock. + * If there is no owner of the lock, end of chain. + */ + if (!rt_mutex_owner(lock)) { + raw_spin_unlock(&lock->wait_lock); + return 0; + } + + /* [10] Grab the next task, i.e. owner of @lock */ + task = rt_mutex_owner(lock); + get_task_struct(task); + raw_spin_lock_irqsave(&task->pi_lock, flags); + + /* + * No requeue [11] here. We just do deadlock detection. + * + * [12] Store whether owner is blocked + * itself. Decision is made after dropping the locks + */ + next_lock = task_blocked_on_lock(task); + /* + * Get the top waiter for the next iteration + */ + top_waiter = rt_mutex_top_waiter(lock); + + /* [13] Drop locks */ + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + raw_spin_unlock(&lock->wait_lock); + + /* If owner is not blocked, end of chain. */ + if (!next_lock) + goto out_put_task; + goto again; + } - /* Requeue the waiter */ + /* + * Store the current top waiter before doing the requeue + * operation on @lock. We need it for the boost/deboost + * decision below. + */ + prerequeue_top_waiter = rt_mutex_top_waiter(lock); + + /* [7] Requeue the waiter in the lock waiter list. */ rt_mutex_dequeue(lock, waiter); waiter->prio = task->prio; rt_mutex_enqueue(lock, waiter); - /* Release the task */ + /* [8] Release the task */ raw_spin_unlock_irqrestore(&task->pi_lock, flags); + put_task_struct(task); + + /* + * [9] check_exit_conditions_3 protected by lock->wait_lock. + * + * We must abort the chain walk if there is no lock owner even + * in the dead lock detection case, as we have nothing to + * follow here. This is the end of the chain we are walking. + */ if (!rt_mutex_owner(lock)) { /* - * If the requeue above changed the top waiter, then we need - * to wake the new top waiter up to try to get the lock. + * If the requeue [7] above changed the top waiter, + * then we need to wake the new top waiter up to try + * to get the lock. */ - - if (top_waiter != rt_mutex_top_waiter(lock)) + if (prerequeue_top_waiter != rt_mutex_top_waiter(lock)) wake_up_process(rt_mutex_top_waiter(lock)->task); raw_spin_unlock(&lock->wait_lock); - goto out_put_task; + return 0; } - put_task_struct(task); - /* Grab the next task */ + /* [10] Grab the next task, i.e. the owner of @lock */ task = rt_mutex_owner(lock); get_task_struct(task); raw_spin_lock_irqsave(&task->pi_lock, flags); + /* [11] requeue the pi waiters if necessary */ if (waiter == rt_mutex_top_waiter(lock)) { - /* Boost the owner */ - rt_mutex_dequeue_pi(task, top_waiter); + /* + * The waiter became the new top (highest priority) + * waiter on the lock. Replace the previous top waiter + * in the owner tasks pi waiters list with this waiter + * and adjust the priority of the owner. + */ + rt_mutex_dequeue_pi(task, prerequeue_top_waiter); rt_mutex_enqueue_pi(task, waiter); __rt_mutex_adjust_prio(task); - } else if (top_waiter == waiter) { - /* Deboost the owner */ + } else if (prerequeue_top_waiter == waiter) { + /* + * The waiter was the top waiter on the lock, but is + * no longer the top prority waiter. Replace waiter in + * the owner tasks pi waiters list with the new top + * (highest priority) waiter and adjust the priority + * of the owner. + * The new top waiter is stored in @waiter so that + * @waiter == @top_waiter evaluates to true below and + * we continue to deboost the rest of the chain. + */ rt_mutex_dequeue_pi(task, waiter); waiter = rt_mutex_top_waiter(lock); rt_mutex_enqueue_pi(task, waiter); __rt_mutex_adjust_prio(task); + } else { + /* + * Nothing changed. No need to do any priority + * adjustment. + */ } /* + * [12] check_exit_conditions_4() protected by task->pi_lock + * and lock->wait_lock. The actual decisions are made after we + * dropped the locks. + * * Check whether the task which owns the current lock is pi * blocked itself. If yes we store a pointer to the lock for * the lock chain change detection above. After we dropped * task->pi_lock next_lock cannot be dereferenced anymore. */ next_lock = task_blocked_on_lock(task); + /* + * Store the top waiter of @lock for the end of chain walk + * decision below. + */ + top_waiter = rt_mutex_top_waiter(lock); + /* [13] Drop the locks */ raw_spin_unlock_irqrestore(&task->pi_lock, flags); - - top_waiter = rt_mutex_top_waiter(lock); raw_spin_unlock(&lock->wait_lock); /* + * Make the actual exit decisions [12], based on the stored + * values. + * * We reached the end of the lock chain. Stop right here. No * point to go back just to figure that out. */ if (!next_lock) goto out_put_task; + /* + * If the current waiter is not the top waiter on the lock, + * then we can stop the chain walk here if we are not in full + * deadlock detection mode. + */ if (!detect_deadlock && waiter != top_waiter) goto out_put_task; @@ -533,76 +743,119 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * * Must be called with lock->wait_lock held. * - * @lock: the lock to be acquired. - * @task: the task which wants to acquire the lock - * @waiter: the waiter that is queued to the lock's wait list. (could be NULL) + * @lock: The lock to be acquired. + * @task: The task which wants to acquire the lock + * @waiter: The waiter that is queued to the lock's wait list if the + * callsite called task_blocked_on_lock(), otherwise NULL */ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, - struct rt_mutex_waiter *waiter) + struct rt_mutex_waiter *waiter) { + unsigned long flags; + /* - * We have to be careful here if the atomic speedups are - * enabled, such that, when - * - no other waiter is on the lock - * - the lock has been released since we did the cmpxchg - * the lock can be released or taken while we are doing the - * checks and marking the lock with RT_MUTEX_HAS_WAITERS. + * Before testing whether we can acquire @lock, we set the + * RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all + * other tasks which try to modify @lock into the slow path + * and they serialize on @lock->wait_lock. + * + * The RT_MUTEX_HAS_WAITERS bit can have a transitional state + * as explained at the top of this file if and only if: * - * The atomic acquire/release aware variant of - * mark_rt_mutex_waiters uses a cmpxchg loop. After setting - * the WAITERS bit, the atomic release / acquire can not - * happen anymore and lock->wait_lock protects us from the - * non-atomic case. + * - There is a lock owner. The caller must fixup the + * transient state if it does a trylock or leaves the lock + * function due to a signal or timeout. * - * Note, that this might set lock->owner = - * RT_MUTEX_HAS_WAITERS in the case the lock is not contended - * any more. This is fixed up when we take the ownership. - * This is the transitional state explained at the top of this file. + * - @task acquires the lock and there are no other + * waiters. This is undone in rt_mutex_set_owner(@task) at + * the end of this function. */ mark_rt_mutex_waiters(lock); + /* + * If @lock has an owner, give up. + */ if (rt_mutex_owner(lock)) return 0; /* - * It will get the lock because of one of these conditions: - * 1) there is no waiter - * 2) higher priority than waiters - * 3) it is top waiter + * If @waiter != NULL, @task has already enqueued the waiter + * into @lock waiter list. If @waiter == NULL then this is a + * trylock attempt. */ - if (rt_mutex_has_waiters(lock)) { - if (task->prio >= rt_mutex_top_waiter(lock)->prio) { - if (!waiter || waiter != rt_mutex_top_waiter(lock)) - return 0; - } - } - - if (waiter || rt_mutex_has_waiters(lock)) { - unsigned long flags; - struct rt_mutex_waiter *top; - - raw_spin_lock_irqsave(&task->pi_lock, flags); + if (waiter) { + /* + * If waiter is not the highest priority waiter of + * @lock, give up. + */ + if (waiter != rt_mutex_top_waiter(lock)) + return 0; - /* remove the queued waiter. */ - if (waiter) { - rt_mutex_dequeue(lock, waiter); - task->pi_blocked_on = NULL; - } + /* + * We can acquire the lock. Remove the waiter from the + * lock waiters list. + */ + rt_mutex_dequeue(lock, waiter); + } else { /* - * We have to enqueue the top waiter(if it exists) into - * task->pi_waiters list. + * If the lock has waiters already we check whether @task is + * eligible to take over the lock. + * + * If there are no other waiters, @task can acquire + * the lock. @task->pi_blocked_on is NULL, so it does + * not need to be dequeued. */ if (rt_mutex_has_waiters(lock)) { - top = rt_mutex_top_waiter(lock); - rt_mutex_enqueue_pi(task, top); + /* + * If @task->prio is greater than or equal to + * the top waiter priority (kernel view), + * @task lost. + */ + if (task->prio >= rt_mutex_top_waiter(lock)->prio) + return 0; + + /* + * The current top waiter stays enqueued. We + * don't have to change anything in the lock + * waiters order. + */ + } else { + /* + * No waiters. Take the lock without the + * pi_lock dance.@task->pi_blocked_on is NULL + * and we have no waiters to enqueue in @task + * pi waiters list. + */ + goto takeit; } - raw_spin_unlock_irqrestore(&task->pi_lock, flags); } + /* + * Clear @task->pi_blocked_on. Requires protection by + * @task->pi_lock. Redundant operation for the @waiter == NULL + * case, but conditionals are more expensive than a redundant + * store. + */ + raw_spin_lock_irqsave(&task->pi_lock, flags); + task->pi_blocked_on = NULL; + /* + * Finish the lock acquisition. @task is the new owner. If + * other waiters exist we have to insert the highest priority + * waiter into @task->pi_waiters list. + */ + if (rt_mutex_has_waiters(lock)) + rt_mutex_enqueue_pi(task, rt_mutex_top_waiter(lock)); + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + +takeit: /* We got the lock. */ debug_rt_mutex_lock(lock); + /* + * This either preserves the RT_MUTEX_HAS_WAITERS bit if there + * are still waiters or clears it. + */ rt_mutex_set_owner(lock, task); rt_mutex_deadlock_account_lock(lock, task); @@ -620,7 +873,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, static int task_blocks_on_rt_mutex(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, struct task_struct *task, - int detect_deadlock) + enum rtmutex_chainwalk chwalk) { struct task_struct *owner = rt_mutex_owner(lock); struct rt_mutex_waiter *top_waiter = waiter; @@ -666,7 +919,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, __rt_mutex_adjust_prio(owner); if (owner->pi_blocked_on) chain_walk = 1; - } else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock)) { + } else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) { chain_walk = 1; } @@ -691,7 +944,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, raw_spin_unlock(&lock->wait_lock); - res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, + res = rt_mutex_adjust_prio_chain(owner, chwalk, lock, next_lock, waiter, task); raw_spin_lock(&lock->wait_lock); @@ -753,9 +1006,9 @@ static void wakeup_next_waiter(struct rt_mutex *lock) static void remove_waiter(struct rt_mutex *lock, struct rt_mutex_waiter *waiter) { - int first = (waiter == rt_mutex_top_waiter(lock)); + bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock)); struct task_struct *owner = rt_mutex_owner(lock); - struct rt_mutex *next_lock = NULL; + struct rt_mutex *next_lock; unsigned long flags; raw_spin_lock_irqsave(¤t->pi_lock, flags); @@ -763,29 +1016,31 @@ static void remove_waiter(struct rt_mutex *lock, current->pi_blocked_on = NULL; raw_spin_unlock_irqrestore(¤t->pi_lock, flags); - if (!owner) + /* + * Only update priority if the waiter was the highest priority + * waiter of the lock and there is an owner to update. + */ + if (!owner || !is_top_waiter) return; - if (first) { - - raw_spin_lock_irqsave(&owner->pi_lock, flags); + raw_spin_lock_irqsave(&owner->pi_lock, flags); - rt_mutex_dequeue_pi(owner, waiter); + rt_mutex_dequeue_pi(owner, waiter); - if (rt_mutex_has_waiters(lock)) { - struct rt_mutex_waiter *next; + if (rt_mutex_has_waiters(lock)) + rt_mutex_enqueue_pi(owner, rt_mutex_top_waiter(lock)); - next = rt_mutex_top_waiter(lock); - rt_mutex_enqueue_pi(owner, next); - } - __rt_mutex_adjust_prio(owner); + __rt_mutex_adjust_prio(owner); - /* Store the lock on which owner is blocked or NULL */ - next_lock = task_blocked_on_lock(owner); + /* Store the lock on which owner is blocked or NULL */ + next_lock = task_blocked_on_lock(owner); - raw_spin_unlock_irqrestore(&owner->pi_lock, flags); - } + raw_spin_unlock_irqrestore(&owner->pi_lock, flags); + /* + * Don't walk the chain, if the owner task is not blocked + * itself. + */ if (!next_lock) return; @@ -794,7 +1049,8 @@ static void remove_waiter(struct rt_mutex *lock, raw_spin_unlock(&lock->wait_lock); - rt_mutex_adjust_prio_chain(owner, 0, lock, next_lock, NULL, current); + rt_mutex_adjust_prio_chain(owner, RT_MUTEX_MIN_CHAINWALK, lock, + next_lock, NULL, current); raw_spin_lock(&lock->wait_lock); } @@ -824,7 +1080,8 @@ void rt_mutex_adjust_pi(struct task_struct *task) /* gets dropped in rt_mutex_adjust_prio_chain()! */ get_task_struct(task); - rt_mutex_adjust_prio_chain(task, 0, NULL, next_lock, NULL, task); + rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL, + next_lock, NULL, task); } /** @@ -902,7 +1159,7 @@ static void rt_mutex_handle_deadlock(int res, int detect_deadlock, static int __sched rt_mutex_slowlock(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, - int detect_deadlock) + enum rtmutex_chainwalk chwalk) { struct rt_mutex_waiter waiter; int ret = 0; @@ -928,7 +1185,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, timeout->task = NULL; } - ret = task_blocks_on_rt_mutex(lock, &waiter, current, detect_deadlock); + ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk); if (likely(!ret)) ret = __rt_mutex_slowlock(lock, state, timeout, &waiter); @@ -937,7 +1194,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, if (unlikely(ret)) { remove_waiter(lock, &waiter); - rt_mutex_handle_deadlock(ret, detect_deadlock, &waiter); + rt_mutex_handle_deadlock(ret, chwalk, &waiter); } /* @@ -960,22 +1217,31 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, /* * Slow path try-lock function: */ -static inline int -rt_mutex_slowtrylock(struct rt_mutex *lock) +static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) { - int ret = 0; + int ret; + + /* + * If the lock already has an owner we fail to get the lock. + * This can be done without taking the @lock->wait_lock as + * it is only being read, and this is a trylock anyway. + */ + if (rt_mutex_owner(lock)) + return 0; + /* + * The mutex has currently no owner. Lock the wait lock and + * try to acquire the lock. + */ raw_spin_lock(&lock->wait_lock); - if (likely(rt_mutex_owner(lock) != current)) { + ret = try_to_take_rt_mutex(lock, current, NULL); - ret = try_to_take_rt_mutex(lock, current, NULL); - /* - * try_to_take_rt_mutex() sets the lock waiters - * bit unconditionally. Clean this up. - */ - fixup_rt_mutex_waiters(lock); - } + /* + * try_to_take_rt_mutex() sets the lock waiters bit + * unconditionally. Clean this up. + */ + fixup_rt_mutex_waiters(lock); raw_spin_unlock(&lock->wait_lock); @@ -1053,30 +1319,31 @@ rt_mutex_slowunlock(struct rt_mutex *lock) */ static inline int rt_mutex_fastlock(struct rt_mutex *lock, int state, - int detect_deadlock, int (*slowfn)(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, - int detect_deadlock)) + enum rtmutex_chainwalk chwalk)) { - if (!detect_deadlock && likely(rt_mutex_cmpxchg(lock, NULL, current))) { + if (likely(rt_mutex_cmpxchg(lock, NULL, current))) { rt_mutex_deadlock_account_lock(lock, current); return 0; } else - return slowfn(lock, state, NULL, detect_deadlock); + return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK); } static inline int rt_mutex_timed_fastlock(struct rt_mutex *lock, int state, - struct hrtimer_sleeper *timeout, int detect_deadlock, + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, int (*slowfn)(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, - int detect_deadlock)) + enum rtmutex_chainwalk chwalk)) { - if (!detect_deadlock && likely(rt_mutex_cmpxchg(lock, NULL, current))) { + if (chwalk == RT_MUTEX_MIN_CHAINWALK && + likely(rt_mutex_cmpxchg(lock, NULL, current))) { rt_mutex_deadlock_account_lock(lock, current); return 0; } else - return slowfn(lock, state, timeout, detect_deadlock); + return slowfn(lock, state, timeout, chwalk); } static inline int @@ -1109,54 +1376,61 @@ void __sched rt_mutex_lock(struct rt_mutex *lock) { might_sleep(); - rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, 0, rt_mutex_slowlock); + rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock); } EXPORT_SYMBOL_GPL(rt_mutex_lock); /** * rt_mutex_lock_interruptible - lock a rt_mutex interruptible * - * @lock: the rt_mutex to be locked - * @detect_deadlock: deadlock detection on/off + * @lock: the rt_mutex to be locked * * Returns: - * 0 on success - * -EINTR when interrupted by a signal - * -EDEADLK when the lock would deadlock (when deadlock detection is on) + * 0 on success + * -EINTR when interrupted by a signal */ -int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock, - int detect_deadlock) +int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock) { might_sleep(); - return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, - detect_deadlock, rt_mutex_slowlock); + return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock); } EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible); +/* + * Futex variant with full deadlock detection. + */ +int rt_mutex_timed_futex_lock(struct rt_mutex *lock, + struct hrtimer_sleeper *timeout) +{ + might_sleep(); + + return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, + RT_MUTEX_FULL_CHAINWALK, + rt_mutex_slowlock); +} + /** * rt_mutex_timed_lock - lock a rt_mutex interruptible * the timeout structure is provided * by the caller * - * @lock: the rt_mutex to be locked + * @lock: the rt_mutex to be locked * @timeout: timeout structure or NULL (no timeout) - * @detect_deadlock: deadlock detection on/off * * Returns: - * 0 on success - * -EINTR when interrupted by a signal + * 0 on success + * -EINTR when interrupted by a signal * -ETIMEDOUT when the timeout expired - * -EDEADLK when the lock would deadlock (when deadlock detection is on) */ int -rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout, - int detect_deadlock) +rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout) { might_sleep(); return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, - detect_deadlock, rt_mutex_slowlock); + RT_MUTEX_MIN_CHAINWALK, + rt_mutex_slowlock); } EXPORT_SYMBOL_GPL(rt_mutex_timed_lock); @@ -1262,7 +1536,6 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock, * @lock: the rt_mutex to take * @waiter: the pre-initialized rt_mutex_waiter * @task: the task to prepare - * @detect_deadlock: perform deadlock detection (1) or not (0) * * Returns: * 0 - task blocked on lock @@ -1273,7 +1546,7 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock, */ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, - struct task_struct *task, int detect_deadlock) + struct task_struct *task) { int ret; @@ -1285,7 +1558,8 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, } /* We enforce deadlock detection for futexes */ - ret = task_blocks_on_rt_mutex(lock, waiter, task, 1); + ret = task_blocks_on_rt_mutex(lock, waiter, task, + RT_MUTEX_FULL_CHAINWALK); if (ret && !rt_mutex_owner(lock)) { /* @@ -1331,22 +1605,20 @@ struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock) * rt_mutex_finish_proxy_lock() - Complete lock acquisition * @lock: the rt_mutex we were woken on * @to: the timeout, null if none. hrtimer should already have - * been started. + * been started. * @waiter: the pre-initialized rt_mutex_waiter - * @detect_deadlock: perform deadlock detection (1) or not (0) * * Complete the lock acquisition started our behalf by another thread. * * Returns: * 0 - success - * <0 - error, one of -EINTR, -ETIMEDOUT, or -EDEADLK + * <0 - error, one of -EINTR, -ETIMEDOUT * * Special API call for PI-futex requeue support */ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, struct hrtimer_sleeper *to, - struct rt_mutex_waiter *waiter, - int detect_deadlock) + struct rt_mutex_waiter *waiter) { int ret; diff --git a/kernel/locking/rtmutex.h b/kernel/locking/rtmutex.h index f6a1f3c133b1..c4060584c407 100644 --- a/kernel/locking/rtmutex.h +++ b/kernel/locking/rtmutex.h @@ -22,10 +22,15 @@ #define debug_rt_mutex_init(m, n) do { } while (0) #define debug_rt_mutex_deadlock(d, a ,l) do { } while (0) #define debug_rt_mutex_print_deadlock(w) do { } while (0) -#define debug_rt_mutex_detect_deadlock(w,d) (d) #define debug_rt_mutex_reset_waiter(w) do { } while (0) static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w) { WARN(1, "rtmutex deadlock detected\n"); } + +static inline bool debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *w, + enum rtmutex_chainwalk walk) +{ + return walk == RT_MUTEX_FULL_CHAINWALK; +} diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index 7431a9c86f35..855212501407 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -102,6 +102,21 @@ static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock) } /* + * Constants for rt mutex functions which have a selectable deadlock + * detection. + * + * RT_MUTEX_MIN_CHAINWALK: Stops the lock chain walk when there are + * no further PI adjustments to be made. + * + * RT_MUTEX_FULL_CHAINWALK: Invoke deadlock detection with a full + * walk of the lock chain. + */ +enum rtmutex_chainwalk { + RT_MUTEX_MIN_CHAINWALK, + RT_MUTEX_FULL_CHAINWALK, +}; + +/* * PI-futex support (proxy locking functions, etc.): */ extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); @@ -111,12 +126,11 @@ extern void rt_mutex_proxy_unlock(struct rt_mutex *lock, struct task_struct *proxy_owner); extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, - struct task_struct *task, - int detect_deadlock); + struct task_struct *task); extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, struct hrtimer_sleeper *to, - struct rt_mutex_waiter *waiter, - int detect_deadlock); + struct rt_mutex_waiter *waiter); +extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to); #ifdef CONFIG_DEBUG_RT_MUTEXES # include "rtmutex-debug.h" diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index a2391ac135c8..d6203faf2eb1 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -329,7 +329,7 @@ bool rwsem_spin_on_owner(struct rw_semaphore *sem, struct task_struct *owner) if (need_resched()) break; - arch_mutex_cpu_relax(); + cpu_relax_lowlatency(); } rcu_read_unlock(); @@ -381,7 +381,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem) * memory barriers as we'll eventually observe the right * values at the cost of a few extra spins. */ - arch_mutex_cpu_relax(); + cpu_relax_lowlatency(); } osq_unlock(&sem->osq); done: diff --git a/kernel/ptrace.c b/kernel/ptrace.c index adf98622cb32..54e75226c2c4 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -28,12 +28,6 @@ #include <linux/compat.h> -static int ptrace_trapping_sleep_fn(void *flags) -{ - schedule(); - return 0; -} - /* * ptrace a task: make the debugger its new parent and * move it to the ptrace list. @@ -371,7 +365,7 @@ unlock_creds: out: if (!retval) { wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, - ptrace_trapping_sleep_fn, TASK_UNINTERRUPTIBLE); + TASK_UNINTERRUPTIBLE); proc_ptrace_connector(task, PTRACE_ATTACH); } diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index bfda2726ca45..ff1a6de62f17 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -99,6 +99,10 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head) void kfree(const void *); +/* + * Reclaim the specified callback, either by invoking it (non-lazy case) + * or freeing it directly (lazy case). Return true if lazy, false otherwise. + */ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head) { unsigned long offset = (unsigned long)head->func; @@ -108,12 +112,12 @@ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head) RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset)); kfree((void *)head - offset); rcu_lock_release(&rcu_callback_map); - return 1; + return true; } else { RCU_TRACE(trace_rcu_invoke_callback(rn, head)); head->func(head); rcu_lock_release(&rcu_callback_map); - return 0; + return false; } } diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c index c639556f3fa0..e037f3eb2f7b 100644 --- a/kernel/rcu/srcu.c +++ b/kernel/rcu/srcu.c @@ -298,9 +298,9 @@ int __srcu_read_lock(struct srcu_struct *sp) idx = ACCESS_ONCE(sp->completed) & 0x1; preempt_disable(); - ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->c[idx]) += 1; + __this_cpu_inc(sp->per_cpu_ref->c[idx]); smp_mb(); /* B */ /* Avoid leaking the critical section. */ - ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->seq[idx]) += 1; + __this_cpu_inc(sp->per_cpu_ref->seq[idx]); preempt_enable(); return idx; } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 625d0b0cd75a..1b70cb6fbe3c 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1013,10 +1013,7 @@ static void record_gp_stall_check_time(struct rcu_state *rsp) } /* - * Dump stacks of all tasks running on stalled CPUs. This is a fallback - * for architectures that do not implement trigger_all_cpu_backtrace(). - * The NMI-triggered stack traces are more accurate because they are - * printed by the target CPU. + * Dump stacks of all tasks running on stalled CPUs. */ static void rcu_dump_cpu_stacks(struct rcu_state *rsp) { @@ -1094,7 +1091,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp) (long)rsp->gpnum, (long)rsp->completed, totqlen); if (ndetected == 0) pr_err("INFO: Stall ended before state dump start\n"); - else if (!trigger_all_cpu_backtrace()) + else rcu_dump_cpu_stacks(rsp); /* Complain about tasks blocking the grace period. */ @@ -1125,8 +1122,7 @@ 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); - if (!trigger_all_cpu_backtrace()) - dump_stack(); + rcu_dump_cpu_stacks(rsp); raw_spin_lock_irqsave(&rnp->lock, flags); if (ULONG_CMP_GE(jiffies, ACCESS_ONCE(rsp->jiffies_stall))) @@ -1305,10 +1301,16 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp, * believe that a grace period is in progress, then we must wait * for the one following, which is in "c". Because our request * will be noticed at the end of the current grace period, we don't - * need to explicitly start one. + * need to explicitly start one. We only do the lockless check + * of rnp_root's fields if the current rcu_node structure thinks + * there is no grace period in flight, and because we hold rnp->lock, + * the only possible change is when rnp_root's two fields are + * equal, in which case rnp_root->gpnum might be concurrently + * incremented. But that is OK, as it will just result in our + * doing some extra useless work. */ if (rnp->gpnum != rnp->completed || - ACCESS_ONCE(rnp->gpnum) != ACCESS_ONCE(rnp->completed)) { + ACCESS_ONCE(rnp_root->gpnum) != ACCESS_ONCE(rnp_root->completed)) { rnp->need_future_gp[c & 0x1]++; trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleaf")); goto out; @@ -1645,11 +1647,6 @@ static int rcu_gp_init(struct rcu_state *rsp) rnp->level, rnp->grplo, rnp->grphi, rnp->qsmask); raw_spin_unlock_irq(&rnp->lock); -#ifdef CONFIG_PROVE_RCU_DELAY - if ((prandom_u32() % (rcu_num_nodes + 1)) == 0 && - system_state == SYSTEM_RUNNING) - udelay(200); -#endif /* #ifdef CONFIG_PROVE_RCU_DELAY */ cond_resched(); } @@ -2347,7 +2344,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) } smp_mb(); /* List handling before counting for rcu_barrier(). */ rdp->qlen_lazy -= count_lazy; - ACCESS_ONCE(rdp->qlen) -= count; + ACCESS_ONCE(rdp->qlen) = rdp->qlen - count; rdp->n_cbs_invoked += count; /* Reinstate batch limit if we have worked down the excess. */ @@ -2485,14 +2482,14 @@ static void force_quiescent_state(struct rcu_state *rsp) struct rcu_node *rnp_old = NULL; /* Funnel through hierarchy to reduce memory contention. */ - rnp = per_cpu_ptr(rsp->rda, raw_smp_processor_id())->mynode; + rnp = __this_cpu_read(rsp->rda->mynode); for (; rnp != NULL; rnp = rnp->parent) { ret = (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) || !raw_spin_trylock(&rnp->fqslock); if (rnp_old != NULL) raw_spin_unlock(&rnp_old->fqslock); if (ret) { - ACCESS_ONCE(rsp->n_force_qs_lh)++; + rsp->n_force_qs_lh++; return; } rnp_old = rnp; @@ -2504,7 +2501,7 @@ static void force_quiescent_state(struct rcu_state *rsp) smp_mb__after_unlock_lock(); raw_spin_unlock(&rnp_old->fqslock); if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { - ACCESS_ONCE(rsp->n_force_qs_lh)++; + rsp->n_force_qs_lh++; raw_spin_unlock_irqrestore(&rnp_old->lock, flags); return; /* Someone beat us to it. */ } @@ -2662,7 +2659,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), unsigned long flags; struct rcu_data *rdp; - WARN_ON_ONCE((unsigned long)head & 0x3); /* Misaligned rcu_head! */ + WARN_ON_ONCE((unsigned long)head & 0x1); /* Misaligned rcu_head! */ if (debug_rcu_head_queue(head)) { /* Probable double call_rcu(), so leak the callback. */ ACCESS_ONCE(head->func) = rcu_leak_callback; @@ -2693,7 +2690,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), local_irq_restore(flags); return; } - ACCESS_ONCE(rdp->qlen)++; + ACCESS_ONCE(rdp->qlen) = rdp->qlen + 1; if (lazy) rdp->qlen_lazy++; else @@ -3257,7 +3254,7 @@ static void _rcu_barrier(struct rcu_state *rsp) * ACCESS_ONCE() to prevent the compiler from speculating * the increment to precede the early-exit check. */ - ACCESS_ONCE(rsp->n_barrier_done)++; + ACCESS_ONCE(rsp->n_barrier_done) = rsp->n_barrier_done + 1; WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 1); _rcu_barrier_trace(rsp, "Inc1", -1, rsp->n_barrier_done); smp_mb(); /* Order ->n_barrier_done increment with below mechanism. */ @@ -3307,7 +3304,7 @@ static void _rcu_barrier(struct rcu_state *rsp) /* Increment ->n_barrier_done to prevent duplicate work. */ smp_mb(); /* Keep increment after above mechanism. */ - ACCESS_ONCE(rsp->n_barrier_done)++; + ACCESS_ONCE(rsp->n_barrier_done) = rsp->n_barrier_done + 1; WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 0); _rcu_barrier_trace(rsp, "Inc2", -1, rsp->n_barrier_done); smp_mb(); /* Keep increment before caller's subsequent code. */ @@ -3564,14 +3561,16 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp) static void __init rcu_init_one(struct rcu_state *rsp, struct rcu_data __percpu *rda) { - static char *buf[] = { "rcu_node_0", - "rcu_node_1", - "rcu_node_2", - "rcu_node_3" }; /* Match MAX_RCU_LVLS */ - static char *fqs[] = { "rcu_node_fqs_0", - "rcu_node_fqs_1", - "rcu_node_fqs_2", - "rcu_node_fqs_3" }; /* Match MAX_RCU_LVLS */ + static const char * const buf[] = { + "rcu_node_0", + "rcu_node_1", + "rcu_node_2", + "rcu_node_3" }; /* Match MAX_RCU_LVLS */ + static const char * const fqs[] = { + "rcu_node_fqs_0", + "rcu_node_fqs_1", + "rcu_node_fqs_2", + "rcu_node_fqs_3" }; /* Match MAX_RCU_LVLS */ static u8 fl_mask = 0x1; int cpustride = 1; int i; diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 0f69a79c5b7d..71e64c718f75 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -172,6 +172,14 @@ 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. */ unsigned long boost_time; /* When to start boosting (jiffies). */ struct task_struct *boost_kthread_task; @@ -334,11 +342,29 @@ struct rcu_data { struct rcu_head **nocb_tail; atomic_long_t nocb_q_count; /* # CBs waiting for kthread */ atomic_long_t nocb_q_count_lazy; /* (approximate). */ + 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; bool nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */ + + /* The following fields are used by the leader, hence own cacheline. */ + 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_wake; /* Is the nocb leader thread awake? */ + struct rcu_data *nocb_next_follower; + /* Next follower in wakeup chain. */ + + /* The following fields are used by the follower, hence new cachline. */ + struct rcu_data *nocb_leader ____cacheline_internodealigned_in_smp; + /* Leader CPU takes GP-end wakeups. */ #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ /* 8) RCU CPU stall data. */ @@ -587,8 +613,14 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp); /* Sum up 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; - *qll = atomic_long_read(&rdp->nocb_q_count_lazy) + rdp->nocb_p_count_lazy; + *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; } #else /* #ifdef CONFIG_RCU_NOCB_CPU */ static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll) diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 02ac0fb186b8..00dc411e9676 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -33,6 +33,7 @@ #define RCU_KTHREAD_PRIO 1 #ifdef CONFIG_RCU_BOOST +#include "../locking/rtmutex_common.h" #define RCU_BOOST_PRIO CONFIG_RCU_BOOST_PRIO #else #define RCU_BOOST_PRIO RCU_KTHREAD_PRIO @@ -336,7 +337,7 @@ void rcu_read_unlock_special(struct task_struct *t) unsigned long flags; struct list_head *np; #ifdef CONFIG_RCU_BOOST - struct rt_mutex *rbmp = NULL; + bool drop_boost_mutex = false; #endif /* #ifdef CONFIG_RCU_BOOST */ struct rcu_node *rnp; int special; @@ -398,11 +399,8 @@ void rcu_read_unlock_special(struct task_struct *t) #ifdef CONFIG_RCU_BOOST if (&t->rcu_node_entry == rnp->boost_tasks) rnp->boost_tasks = np; - /* Snapshot/clear ->rcu_boost_mutex with rcu_node lock held. */ - if (t->rcu_boost_mutex) { - rbmp = t->rcu_boost_mutex; - t->rcu_boost_mutex = NULL; - } + /* Snapshot ->boost_mtx ownership with rcu_node lock held. */ + drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t; #endif /* #ifdef CONFIG_RCU_BOOST */ /* @@ -427,8 +425,10 @@ void rcu_read_unlock_special(struct task_struct *t) #ifdef CONFIG_RCU_BOOST /* Unboost if we were boosted. */ - if (rbmp) - rt_mutex_unlock(rbmp); + if (drop_boost_mutex) { + rt_mutex_unlock(&rnp->boost_mtx); + complete(&rnp->boost_completion); + } #endif /* #ifdef CONFIG_RCU_BOOST */ /* @@ -988,6 +988,7 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp) /* 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) { raw_spin_unlock_irqrestore(&rnp->lock, flags); } @@ -1149,7 +1150,6 @@ static void rcu_wake_cond(struct task_struct *t, int status) static int rcu_boost(struct rcu_node *rnp) { unsigned long flags; - struct rt_mutex mtx; struct task_struct *t; struct list_head *tb; @@ -1200,11 +1200,15 @@ static int rcu_boost(struct rcu_node *rnp) * section. */ t = container_of(tb, struct task_struct, rcu_node_entry); - rt_mutex_init_proxy_locked(&mtx, t); - t->rcu_boost_mutex = &mtx; + rt_mutex_init_proxy_locked(&rnp->boost_mtx, t); + init_completion(&rnp->boost_completion); raw_spin_unlock_irqrestore(&rnp->lock, flags); - rt_mutex_lock(&mtx); /* Side effect: boosts task t's priority. */ - rt_mutex_unlock(&mtx); /* Keep lockdep happy. */ + /* 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; @@ -1256,6 +1260,7 @@ static int rcu_boost_kthread(void *arg) * about it going away. */ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) + __releases(rnp->lock) { struct task_struct *t; @@ -1491,6 +1496,7 @@ static void rcu_prepare_kthreads(int cpu) #else /* #ifdef CONFIG_RCU_BOOST */ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) + __releases(rnp->lock) { raw_spin_unlock_irqrestore(&rnp->lock, flags); } @@ -2060,6 +2066,22 @@ bool rcu_is_nocb_cpu(int cpu) #endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ /* + * Kick the leader kthread for this NOCB group. + */ +static void wake_nocb_leader(struct rcu_data *rdp, bool force) +{ + struct rcu_data *rdp_leader = rdp->nocb_leader; + + if (!ACCESS_ONCE(rdp_leader->nocb_kthread)) + return; + if (!ACCESS_ONCE(rdp_leader->nocb_leader_wake) || force) { + /* Prior xchg orders against prior callback enqueue. */ + ACCESS_ONCE(rdp_leader->nocb_leader_wake) = true; + wake_up(&rdp_leader->nocb_wq); + } +} + +/* * Enqueue the specified string of rcu_head structures onto the specified * CPU's no-CBs lists. The CPU is specified by rdp, the head of the * string by rhp, and the tail of the string by rhtp. The non-lazy/lazy @@ -2093,7 +2115,8 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, len = atomic_long_read(&rdp->nocb_q_count); if (old_rhpp == &rdp->nocb_head) { if (!irqs_disabled_flags(flags)) { - wake_up(&rdp->nocb_wq); /* ... if queue was empty ... */ + /* ... if queue was empty ... */ + wake_nocb_leader(rdp, false); trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeEmpty")); } else { @@ -2103,7 +2126,8 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, } rdp->qlen_last_fqs_check = 0; } else if (len > rdp->qlen_last_fqs_check + qhimark) { - wake_up_process(t); /* ... or if many callbacks queued. */ + /* ... or if many callbacks queued. */ + wake_nocb_leader(rdp, true); rdp->qlen_last_fqs_check = LONG_MAX / 2; trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeOvf")); } else { @@ -2213,13 +2237,150 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) } /* + * Leaders come here to wait for additional callbacks to show up. + * This function does not return until callbacks appear. + */ +static void nocb_leader_wait(struct rcu_data *my_rdp) +{ + bool firsttime = true; + bool gotcbs; + struct rcu_data *rdp; + struct rcu_head **tail; + +wait_again: + + /* Wait for callbacks to appear. */ + if (!rcu_nocb_poll) { + trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Sleep"); + wait_event_interruptible(my_rdp->nocb_wq, + ACCESS_ONCE(my_rdp->nocb_leader_wake)); + /* Memory barrier handled by smp_mb() calls below and repoll. */ + } else if (firsttime) { + firsttime = false; /* Don't drown trace log with "Poll"! */ + trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Poll"); + } + + /* + * Each pass through the following loop checks a follower for CBs. + * We are our own first follower. Any CBs found are moved to + * nocb_gp_head, where they await a grace period. + */ + gotcbs = false; + for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) { + rdp->nocb_gp_head = ACCESS_ONCE(rdp->nocb_head); + if (!rdp->nocb_gp_head) + continue; /* No CBs here, try next follower. */ + + /* 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; + } + + /* + * If there were no callbacks, sleep a bit, rescan after a + * memory barrier, and go retry. + */ + if (unlikely(!gotcbs)) { + if (!rcu_nocb_poll) + trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, + "WokeEmpty"); + flush_signals(current); + schedule_timeout_interruptible(1); + + /* Rescan in case we were a victim of memory ordering. */ + my_rdp->nocb_leader_wake = false; + smp_mb(); /* Ensure _wake false before scan. */ + for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) + if (ACCESS_ONCE(rdp->nocb_head)) { + /* Found CB, so short-circuit next wait. */ + my_rdp->nocb_leader_wake = true; + break; + } + goto wait_again; + } + + /* Wait for one grace period. */ + rcu_nocb_wait_gp(my_rdp); + + /* + * We left ->nocb_leader_wake set to reduce cache thrashing. + * We clear it now, but recheck for new callbacks while + * traversing our follower list. + */ + my_rdp->nocb_leader_wake = false; + smp_mb(); /* Ensure _wake false before scan of ->nocb_head. */ + + /* Each pass through the following loop wakes a follower, if needed. */ + for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) { + if (ACCESS_ONCE(rdp->nocb_head)) + my_rdp->nocb_leader_wake = true; /* No need to wait. */ + if (!rdp->nocb_gp_head) + continue; /* No CBs, so no need to wake follower. */ + + /* 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); + if (rdp != my_rdp && tail == &rdp->nocb_follower_head) { + /* + * List was empty, wake up the follower. + * Memory barriers supplied by atomic_long_add(). + */ + wake_up(&rdp->nocb_wq); + } + } + + /* If we (the leader) don't have CBs, go wait some more. */ + if (!my_rdp->nocb_follower_head) + goto wait_again; +} + +/* + * Followers come here to wait for additional callbacks to show up. + * This function does not return until callbacks appear. + */ +static void nocb_follower_wait(struct rcu_data *rdp) +{ + bool firsttime = true; + + for (;;) { + if (!rcu_nocb_poll) { + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + "FollowerSleep"); + wait_event_interruptible(rdp->nocb_wq, + ACCESS_ONCE(rdp->nocb_follower_head)); + } else if (firsttime) { + /* Don't drown trace log with "Poll"! */ + firsttime = false; + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, "Poll"); + } + if (smp_load_acquire(&rdp->nocb_follower_head)) { + /* ^^^ Ensure CB invocation follows _head test. */ + return; + } + if (!rcu_nocb_poll) + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + "WokeEmpty"); + flush_signals(current); + schedule_timeout_interruptible(1); + } +} + +/* * Per-rcu_data kthread, but only for no-CBs CPUs. Each kthread invokes - * callbacks queued by the corresponding no-CBs CPU. + * callbacks queued by the corresponding no-CBs CPU, however, there is + * an optional leader-follower relationship so that the grace-period + * kthreads don't have to do quite so many wakeups. */ static int rcu_nocb_kthread(void *arg) { int c, cl; - bool firsttime = 1; struct rcu_head *list; struct rcu_head *next; struct rcu_head **tail; @@ -2227,41 +2388,22 @@ static int rcu_nocb_kthread(void *arg) /* Each pass through this loop invokes one batch of callbacks */ for (;;) { - /* If not polling, wait for next batch of callbacks. */ - if (!rcu_nocb_poll) { - trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, - TPS("Sleep")); - wait_event_interruptible(rdp->nocb_wq, rdp->nocb_head); - /* Memory barrier provide by xchg() below. */ - } else if (firsttime) { - firsttime = 0; - trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, - TPS("Poll")); - } - list = ACCESS_ONCE(rdp->nocb_head); - if (!list) { - if (!rcu_nocb_poll) - trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, - TPS("WokeEmpty")); - schedule_timeout_interruptible(1); - flush_signals(current); - continue; - } - firsttime = 1; - trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, - TPS("WokeNonEmpty")); - - /* - * Extract queued callbacks, update counts, and wait - * for a grace period to elapse. - */ - ACCESS_ONCE(rdp->nocb_head) = NULL; - tail = xchg(&rdp->nocb_tail, &rdp->nocb_head); - c = atomic_long_xchg(&rdp->nocb_q_count, 0); - cl = atomic_long_xchg(&rdp->nocb_q_count_lazy, 0); - ACCESS_ONCE(rdp->nocb_p_count) += c; - ACCESS_ONCE(rdp->nocb_p_count_lazy) += cl; - rcu_nocb_wait_gp(rdp); + /* Wait for callbacks. */ + if (rdp->nocb_leader == rdp) + nocb_leader_wait(rdp); + else + nocb_follower_wait(rdp); + + /* Pull the ready-to-invoke callbacks onto local list. */ + list = ACCESS_ONCE(rdp->nocb_follower_head); + BUG_ON(!list); + 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); @@ -2305,7 +2447,7 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp) if (!rcu_nocb_need_deferred_wakeup(rdp)) return; ACCESS_ONCE(rdp->nocb_defer_wakeup) = false; - wake_up(&rdp->nocb_wq); + wake_nocb_leader(rdp, false); trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWakeEmpty")); } @@ -2314,19 +2456,57 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) { rdp->nocb_tail = &rdp->nocb_head; init_waitqueue_head(&rdp->nocb_wq); + rdp->nocb_follower_tail = &rdp->nocb_follower_head; } -/* Create a kthread for each RCU flavor for each no-CBs CPU. */ +/* How many follower CPU IDs per leader? Default of -1 for sqrt(nr_cpu_ids). */ +static int rcu_nocb_leader_stride = -1; +module_param(rcu_nocb_leader_stride, int, 0444); + +/* + * Create a kthread for each RCU flavor for each no-CBs CPU. + * Also initialize leader-follower relationships. + */ static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp) { int cpu; + int ls = rcu_nocb_leader_stride; + int nl = 0; /* Next leader. */ struct rcu_data *rdp; + struct rcu_data *rdp_leader = NULL; /* Suppress misguided gcc warn. */ + struct rcu_data *rdp_prev = NULL; struct task_struct *t; if (rcu_nocb_mask == NULL) return; +#if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL) + if (tick_nohz_full_running) + cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask); +#endif /* #if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL) */ + if (ls == -1) { + ls = int_sqrt(nr_cpu_ids); + rcu_nocb_leader_stride = ls; + } + + /* + * Each pass through this loop sets up one rcu_data structure and + * spawns one rcu_nocb_kthread(). + */ for_each_cpu(cpu, rcu_nocb_mask) { rdp = per_cpu_ptr(rsp->rda, cpu); + if (rdp->cpu >= nl) { + /* New leader, set up for followers & next leader. */ + nl = DIV_ROUND_UP(rdp->cpu + 1, ls) * ls; + rdp->nocb_leader = rdp; + rdp_leader = rdp; + } else { + /* Another follower, link to previous leader. */ + rdp->nocb_leader = rdp_leader; + rdp_prev->nocb_next_follower = rdp; + } + rdp_prev = rdp; + + /* Spawn the kthread for this CPU. */ t = kthread_run(rcu_nocb_kthread, rdp, "rcuo%c/%d", rsp->abbr, cpu); BUG_ON(IS_ERR(t)); @@ -2843,12 +3023,16 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp) */ static void rcu_bind_gp_kthread(void) { -#ifdef CONFIG_NO_HZ_FULL - int cpu = ACCESS_ONCE(tick_do_timer_cpu); + int __maybe_unused cpu; - if (cpu < 0 || cpu >= nr_cpu_ids) + if (!tick_nohz_full_enabled()) return; - if (raw_smp_processor_id() != cpu) +#ifdef CONFIG_NO_HZ_FULL_SYSIDLE + cpu = tick_do_timer_cpu; + if (cpu >= 0 && cpu < nr_cpu_ids && raw_smp_processor_id() != cpu) set_cpus_allowed_ptr(current, cpumask_of(cpu)); -#endif /* #ifdef CONFIG_NO_HZ_FULL */ +#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ + if (!is_housekeeping_cpu(raw_smp_processor_id())) + housekeeping_affine(current); +#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ } diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index bc7883570530..4056d7992a6c 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -90,9 +90,6 @@ void __rcu_read_unlock(void) } else { barrier(); /* critical section before exit code. */ t->rcu_read_lock_nesting = INT_MIN; -#ifdef CONFIG_PROVE_RCU_DELAY - udelay(10); /* Make preemption more probable. */ -#endif /* #ifdef CONFIG_PROVE_RCU_DELAY */ barrier(); /* assign before ->rcu_read_unlock_special load */ if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) rcu_read_unlock_special(t); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index bc1638b33449..2676866b4394 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -139,6 +139,8 @@ void update_rq_clock(struct rq *rq) return; delta = sched_clock_cpu(cpu_of(rq)) - rq->clock; + if (delta < 0) + return; rq->clock += delta; update_rq_clock_task(rq, delta); } @@ -243,6 +245,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf, char buf[64]; char *cmp; int i; + struct inode *inode; if (cnt > 63) cnt = 63; @@ -253,7 +256,11 @@ sched_feat_write(struct file *filp, const char __user *ubuf, buf[cnt] = 0; cmp = strstrip(buf); + /* Ensure the static_key remains in a consistent state */ + inode = file_inode(filp); + mutex_lock(&inode->i_mutex); i = sched_feat_set(cmp); + mutex_unlock(&inode->i_mutex); if (i == __SCHED_FEAT_NR) return -EINVAL; @@ -587,30 +594,31 @@ static bool set_nr_if_polling(struct task_struct *p) #endif /* - * resched_task - mark a task 'to be rescheduled now'. + * resched_curr - mark rq's current task 'to be rescheduled now'. * * On UP this means the setting of the need_resched flag, on SMP it * might also involve a cross-CPU call to trigger the scheduler on * the target CPU. */ -void resched_task(struct task_struct *p) +void resched_curr(struct rq *rq) { + struct task_struct *curr = rq->curr; int cpu; - lockdep_assert_held(&task_rq(p)->lock); + lockdep_assert_held(&rq->lock); - if (test_tsk_need_resched(p)) + if (test_tsk_need_resched(curr)) return; - cpu = task_cpu(p); + cpu = cpu_of(rq); if (cpu == smp_processor_id()) { - set_tsk_need_resched(p); + set_tsk_need_resched(curr); set_preempt_need_resched(); return; } - if (set_nr_and_not_polling(p)) + if (set_nr_and_not_polling(curr)) smp_send_reschedule(cpu); else trace_sched_wake_idle_without_ipi(cpu); @@ -623,7 +631,7 @@ void resched_cpu(int cpu) if (!raw_spin_trylock_irqsave(&rq->lock, flags)) return; - resched_task(cpu_curr(cpu)); + resched_curr(rq); raw_spin_unlock_irqrestore(&rq->lock, flags); } @@ -684,10 +692,16 @@ static void wake_up_idle_cpu(int cpu) static bool wake_up_full_nohz_cpu(int cpu) { + /* + * We just need the target to call irq_exit() and re-evaluate + * the next tick. The nohz full kick at least implies that. + * If needed we can still optimize that later with an + * empty IRQ. + */ if (tick_nohz_full_cpu(cpu)) { if (cpu != smp_processor_id() || tick_nohz_tick_stopped()) - smp_send_reschedule(cpu); + tick_nohz_full_kick_cpu(cpu); return true; } @@ -730,18 +744,15 @@ static inline bool got_nohz_idle_kick(void) #ifdef CONFIG_NO_HZ_FULL bool sched_can_stop_tick(void) { - struct rq *rq; - - rq = this_rq(); - - /* Make sure rq->nr_running update is visible after the IPI */ - smp_rmb(); - - /* More than one running task need preemption */ - if (rq->nr_running > 1) - return false; + /* + * More than one running task need preemption. + * nr_running update is assumed to be visible + * after IPI is sent from wakers. + */ + if (this_rq()->nr_running > 1) + return false; - return true; + return true; } #endif /* CONFIG_NO_HZ_FULL */ @@ -1022,7 +1033,7 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) if (class == rq->curr->sched_class) break; if (class == p->sched_class) { - resched_task(rq->curr); + resched_curr(rq); break; } } @@ -1568,9 +1579,7 @@ void scheduler_ipi(void) */ preempt_fold_need_resched(); - if (llist_empty(&this_rq()->wake_list) - && !tick_nohz_full_cpu(smp_processor_id()) - && !got_nohz_idle_kick()) + if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick()) return; /* @@ -1587,7 +1596,6 @@ void scheduler_ipi(void) * somewhat pessimize the simple resched case. */ irq_enter(); - tick_nohz_full_check(); sched_ttwu_pending(); /* @@ -2431,7 +2439,12 @@ static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq) { u64 ns = 0; - if (task_current(rq, p)) { + /* + * Must be ->curr _and_ ->on_rq. If dequeued, we would + * project cycles that may never be accounted to this + * thread, breaking clock_gettime(). + */ + if (task_current(rq, p) && p->on_rq) { update_rq_clock(rq); ns = rq_clock_task(rq) - p->se.exec_start; if ((s64)ns < 0) @@ -2474,8 +2487,10 @@ unsigned long long task_sched_runtime(struct task_struct *p) * If we race with it leaving cpu, we'll take a lock. So we're correct. * If we race with it entering cpu, unaccounted time is 0. This is * indistinguishable from the read occurring a few cycles earlier. + * If we see ->on_cpu without ->on_rq, the task is leaving, and has + * been accounted, so we're correct here as well. */ - if (!p->on_cpu) + if (!p->on_cpu || !p->on_rq) return p->se.sum_exec_runtime; #endif @@ -2971,7 +2986,6 @@ void rt_mutex_setprio(struct task_struct *p, int prio) } trace_sched_pi_setprio(p, prio); - p->pi_top_task = rt_mutex_get_top_task(p); oldprio = p->prio; prev_class = p->sched_class; on_rq = p->on_rq; @@ -2991,8 +3005,9 @@ void rt_mutex_setprio(struct task_struct *p, int prio) * running task */ if (dl_prio(prio)) { - if (!dl_prio(p->normal_prio) || (p->pi_top_task && - dl_entity_preempt(&p->pi_top_task->dl, &p->dl))) { + struct task_struct *pi_task = rt_mutex_get_top_task(p); + if (!dl_prio(p->normal_prio) || + (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) { p->dl.dl_boosted = 1; p->dl.dl_throttled = 0; enqueue_flag = ENQUEUE_REPLENISH; @@ -3064,7 +3079,7 @@ void set_user_nice(struct task_struct *p, long nice) * lowered its priority, then reschedule its CPU: */ if (delta < 0 || (delta > 0 && task_running(rq, p))) - resched_task(rq->curr); + resched_curr(rq); } out_unlock: task_rq_unlock(rq, p, &flags); @@ -3203,12 +3218,18 @@ __setparam_dl(struct task_struct *p, const struct sched_attr *attr) dl_se->dl_yielded = 0; } +/* + * sched_setparam() passes in -1 for its policy, to let the functions + * it calls know not to change it. + */ +#define SETPARAM_POLICY -1 + static void __setscheduler_params(struct task_struct *p, const struct sched_attr *attr) { int policy = attr->sched_policy; - if (policy == -1) /* setparam */ + if (policy == SETPARAM_POLICY) policy = p->policy; p->policy = policy; @@ -3557,10 +3578,8 @@ static int _sched_setscheduler(struct task_struct *p, int policy, .sched_nice = PRIO_TO_NICE(p->static_prio), }; - /* - * Fixup the legacy SCHED_RESET_ON_FORK hack - */ - if (policy & SCHED_RESET_ON_FORK) { + /* Fixup the legacy SCHED_RESET_ON_FORK hack. */ + if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) { attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; policy &= ~SCHED_RESET_ON_FORK; attr.sched_policy = policy; @@ -3730,7 +3749,7 @@ SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, */ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) { - return do_sched_setscheduler(pid, -1, param); + return do_sched_setscheduler(pid, SETPARAM_POLICY, param); } /** @@ -4285,7 +4304,7 @@ again: * fairness. */ if (preempt && rq != p_rq) - resched_task(p_rq->curr); + resched_curr(p_rq); } out_unlock: @@ -6465,6 +6484,20 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, sched_domain_level_max = max(sched_domain_level_max, sd->level); child->parent = sd; sd->child = child; + + if (!cpumask_subset(sched_domain_span(child), + sched_domain_span(sd))) { + pr_err("BUG: arch topology borken\n"); +#ifdef CONFIG_SCHED_DEBUG + pr_err(" the %s domain not a subset of the %s domain\n", + child->name, sd->name); +#endif + /* Fixup, ensure @sd has at least @child cpus. */ + cpumask_or(sched_domain_span(sd), + sched_domain_span(sd), + sched_domain_span(child)); + } + } set_domain_attribute(sd, attr); @@ -7092,7 +7125,7 @@ static void normalize_task(struct rq *rq, struct task_struct *p) __setscheduler(rq, p, &attr); if (on_rq) { enqueue_task(rq, p, 0); - resched_task(rq->curr); + resched_curr(rq); } check_class_changed(rq, p, prev_class, old_prio); @@ -7803,6 +7836,11 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) if (period > max_cfs_quota_period) return -EINVAL; + /* + * Prevent race between setting of cfs_rq->runtime_enabled and + * unthrottle_offline_cfs_rqs(). + */ + get_online_cpus(); mutex_lock(&cfs_constraints_mutex); ret = __cfs_schedulable(tg, period, quota); if (ret) @@ -7828,7 +7866,7 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) } raw_spin_unlock_irq(&cfs_b->lock); - for_each_possible_cpu(i) { + for_each_online_cpu(i) { struct cfs_rq *cfs_rq = tg->cfs_rq[i]; struct rq *rq = cfs_rq->rq; @@ -7844,6 +7882,7 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) cfs_bandwidth_usage_dec(); out_unlock: mutex_unlock(&cfs_constraints_mutex); + put_online_cpus(); return ret; } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index fc4f98b1258f..255ce138b652 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -306,7 +306,7 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se, * the overrunning entity can't interfere with other entity in the system and * can't make them miss their deadlines. Reasons why this kind of overruns * could happen are, typically, a entity voluntarily trying to overcome its - * runtime, or it just underestimated it during sched_setscheduler_ex(). + * runtime, or it just underestimated it during sched_setattr(). */ static void replenish_dl_entity(struct sched_dl_entity *dl_se, struct sched_dl_entity *pi_se) @@ -535,7 +535,7 @@ again: if (task_has_dl_policy(rq->curr)) check_preempt_curr_dl(rq, p, 0); else - resched_task(rq->curr); + resched_curr(rq); #ifdef CONFIG_SMP /* * Queueing this task back might have overloaded rq, @@ -634,7 +634,7 @@ static void update_curr_dl(struct rq *rq) enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH); if (!is_leftmost(curr, &rq->dl)) - resched_task(curr); + resched_curr(rq); } /* @@ -964,7 +964,7 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p) cpudl_find(&rq->rd->cpudl, p, NULL) != -1) return; - resched_task(rq->curr); + resched_curr(rq); } static int pull_dl_task(struct rq *this_rq); @@ -979,7 +979,7 @@ static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p, int flags) { if (dl_entity_preempt(&p->dl, &rq->curr->dl)) { - resched_task(rq->curr); + resched_curr(rq); return; } @@ -1333,7 +1333,7 @@ retry: if (dl_task(rq->curr) && dl_time_before(next_task->dl.deadline, rq->curr->dl.deadline) && rq->curr->nr_cpus_allowed > 1) { - resched_task(rq->curr); + resched_curr(rq); return 0; } @@ -1373,7 +1373,7 @@ retry: set_task_cpu(next_task, later_rq->cpu); activate_task(later_rq, next_task, 0); - resched_task(later_rq->curr); + resched_curr(later_rq); double_unlock_balance(rq, later_rq); @@ -1632,14 +1632,14 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p, */ if (dl_time_before(rq->dl.earliest_dl.curr, p->dl.deadline) && rq->curr == p) - resched_task(p); + resched_curr(rq); #else /* * Again, we don't know if p has a earlier * or later deadline, so let's blindly set a * (maybe not needed) rescheduling point. */ - resched_task(p); + resched_curr(rq); #endif /* CONFIG_SMP */ } else switched_to_dl(rq, p); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index fea7d3335e1f..bfa3c86d0d68 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1062,7 +1062,6 @@ static void update_numa_stats(struct numa_stats *ns, int nid) if (!cpus) return; - ns->load = (ns->load * SCHED_CAPACITY_SCALE) / ns->compute_capacity; ns->task_capacity = DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE); ns->has_free_capacity = (ns->nr_running < ns->task_capacity); @@ -1096,18 +1095,30 @@ static void task_numa_assign(struct task_numa_env *env, env->best_cpu = env->dst_cpu; } -static bool load_too_imbalanced(long orig_src_load, long orig_dst_load, - long src_load, long dst_load, +static bool load_too_imbalanced(long src_load, long dst_load, struct task_numa_env *env) { long imb, old_imb; + long orig_src_load, orig_dst_load; + long src_capacity, dst_capacity; + + /* + * The load is corrected for the CPU capacity available on each node. + * + * src_load dst_load + * ------------ vs --------- + * src_capacity dst_capacity + */ + src_capacity = env->src_stats.compute_capacity; + dst_capacity = env->dst_stats.compute_capacity; /* We care about the slope of the imbalance, not the direction. */ if (dst_load < src_load) swap(dst_load, src_load); /* Is the difference below the threshold? */ - imb = dst_load * 100 - src_load * env->imbalance_pct; + imb = dst_load * src_capacity * 100 - + src_load * dst_capacity * env->imbalance_pct; if (imb <= 0) return false; @@ -1115,10 +1126,14 @@ static bool load_too_imbalanced(long orig_src_load, long orig_dst_load, * The imbalance is above the allowed threshold. * Compare it with the old imbalance. */ + orig_src_load = env->src_stats.load; + orig_dst_load = env->dst_stats.load; + if (orig_dst_load < orig_src_load) swap(orig_dst_load, orig_src_load); - old_imb = orig_dst_load * 100 - orig_src_load * env->imbalance_pct; + old_imb = orig_dst_load * src_capacity * 100 - + orig_src_load * dst_capacity * env->imbalance_pct; /* Would this change make things worse? */ return (imb > old_imb); @@ -1136,10 +1151,10 @@ static void task_numa_compare(struct task_numa_env *env, struct rq *src_rq = cpu_rq(env->src_cpu); struct rq *dst_rq = cpu_rq(env->dst_cpu); struct task_struct *cur; - long orig_src_load, src_load; - long orig_dst_load, dst_load; + long src_load, dst_load; long load; - long imp = (groupimp > 0) ? groupimp : taskimp; + long imp = env->p->numa_group ? groupimp : taskimp; + long moveimp = imp; rcu_read_lock(); cur = ACCESS_ONCE(dst_rq->curr); @@ -1177,11 +1192,6 @@ static void task_numa_compare(struct task_numa_env *env, * itself (not part of a group), use the task weight * instead. */ - if (env->p->numa_group) - imp = groupimp; - else - imp = taskimp; - if (cur->numa_group) imp += group_weight(cur, env->src_nid) - group_weight(cur, env->dst_nid); @@ -1191,7 +1201,7 @@ static void task_numa_compare(struct task_numa_env *env, } } - if (imp < env->best_imp) + if (imp <= env->best_imp && moveimp <= env->best_imp) goto unlock; if (!cur) { @@ -1204,20 +1214,34 @@ static void task_numa_compare(struct task_numa_env *env, } /* Balance doesn't matter much if we're running a task per cpu */ - if (src_rq->nr_running == 1 && dst_rq->nr_running == 1) + if (imp > env->best_imp && src_rq->nr_running == 1 && + dst_rq->nr_running == 1) goto assign; /* * In the overloaded case, try and keep the load balanced. */ balance: - orig_dst_load = env->dst_stats.load; - orig_src_load = env->src_stats.load; - - /* XXX missing capacity terms */ load = task_h_load(env->p); - dst_load = orig_dst_load + load; - src_load = orig_src_load - load; + dst_load = env->dst_stats.load + load; + src_load = env->src_stats.load - load; + + if (moveimp > imp && moveimp > env->best_imp) { + /* + * If the improvement from just moving env->p direction is + * better than swapping tasks around, check if a move is + * possible. Store a slightly smaller score than moveimp, + * so an actually idle CPU will win. + */ + if (!load_too_imbalanced(src_load, dst_load, env)) { + imp = moveimp - 1; + cur = NULL; + goto assign; + } + } + + if (imp <= env->best_imp) + goto unlock; if (cur) { load = task_h_load(cur); @@ -1225,8 +1249,7 @@ balance: src_load += load; } - if (load_too_imbalanced(orig_src_load, orig_dst_load, - src_load, dst_load, env)) + if (load_too_imbalanced(src_load, dst_load, env)) goto unlock; assign: @@ -1302,9 +1325,8 @@ static int task_numa_migrate(struct task_struct *p) groupimp = group_weight(p, env.dst_nid) - groupweight; update_numa_stats(&env.dst_stats, env.dst_nid); - /* If the preferred nid has free capacity, try to use it. */ - if (env.dst_stats.has_free_capacity) - task_numa_find_cpu(&env, taskimp, groupimp); + /* Try to find a spot on the preferred nid. */ + task_numa_find_cpu(&env, taskimp, groupimp); /* No space available on the preferred nid. Look elsewhere. */ if (env.best_cpu == -1) { @@ -1324,10 +1346,6 @@ static int task_numa_migrate(struct task_struct *p) } } - /* No better CPU than the current one was found. */ - if (env.best_cpu == -1) - return -EAGAIN; - /* * If the task is part of a workload that spans multiple NUMA nodes, * and is migrating into one of the workload's active nodes, remember @@ -1336,8 +1354,19 @@ static int task_numa_migrate(struct task_struct *p) * A task that migrated to a second choice node will be better off * trying for a better one later. Do not set the preferred node here. */ - if (p->numa_group && node_isset(env.dst_nid, p->numa_group->active_nodes)) - sched_setnuma(p, env.dst_nid); + if (p->numa_group) { + if (env.best_cpu == -1) + nid = env.src_nid; + else + nid = env.dst_nid; + + if (node_isset(nid, p->numa_group->active_nodes)) + sched_setnuma(p, env.dst_nid); + } + + /* No better CPU than the current one was found. */ + if (env.best_cpu == -1) + return -EAGAIN; /* * Reset the scan period if the task is being rescheduled on an @@ -1415,12 +1444,12 @@ static void update_numa_active_node_mask(struct numa_group *numa_group) /* * When adapting the scan rate, the period is divided into NUMA_PERIOD_SLOTS * increments. The more local the fault statistics are, the higher the scan - * period will be for the next scan window. If local/remote ratio is below - * NUMA_PERIOD_THRESHOLD (where range of ratio is 1..NUMA_PERIOD_SLOTS) the - * scan period will decrease + * period will be for the next scan window. If local/(local+remote) ratio is + * below NUMA_PERIOD_THRESHOLD (where range of ratio is 1..NUMA_PERIOD_SLOTS) + * the scan period will decrease. Aim for 70% local accesses. */ #define NUMA_PERIOD_SLOTS 10 -#define NUMA_PERIOD_THRESHOLD 3 +#define NUMA_PERIOD_THRESHOLD 7 /* * Increase the scan period (slow down scanning) if the majority of @@ -1595,30 +1624,17 @@ static void task_numa_placement(struct task_struct *p) if (p->numa_group) { update_numa_active_node_mask(p->numa_group); - /* - * If the preferred task and group nids are different, - * iterate over the nodes again to find the best place. - */ - if (max_nid != max_group_nid) { - unsigned long weight, max_weight = 0; - - for_each_online_node(nid) { - weight = task_weight(p, nid) + group_weight(p, nid); - if (weight > max_weight) { - max_weight = weight; - max_nid = nid; - } - } - } - spin_unlock_irq(group_lock); + max_nid = max_group_nid; } - /* Preferred node as the node with the most faults */ - if (max_faults && max_nid != p->numa_preferred_nid) { - /* Update the preferred nid and migrate task if possible */ - sched_setnuma(p, max_nid); - numa_migrate_preferred(p); + if (max_faults) { + /* Set the new preferred node */ + if (max_nid != p->numa_preferred_nid) + sched_setnuma(p, max_nid); + + if (task_node(p) != p->numa_preferred_nid) + numa_migrate_preferred(p); } } @@ -2899,7 +2915,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) ideal_runtime = sched_slice(cfs_rq, curr); delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; if (delta_exec > ideal_runtime) { - resched_task(rq_of(cfs_rq)->curr); + resched_curr(rq_of(cfs_rq)); /* * The current task ran long enough, ensure it doesn't get * re-elected due to buddy favours. @@ -2923,7 +2939,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) return; if (delta > ideal_runtime) - resched_task(rq_of(cfs_rq)->curr); + resched_curr(rq_of(cfs_rq)); } static void @@ -3063,7 +3079,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) * validating it and just reschedule. */ if (queued) { - resched_task(rq_of(cfs_rq)->curr); + resched_curr(rq_of(cfs_rq)); return; } /* @@ -3254,7 +3270,7 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) * hierarchy can be throttled */ if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr)) - resched_task(rq_of(cfs_rq)->curr); + resched_curr(rq_of(cfs_rq)); } static __always_inline @@ -3360,7 +3376,11 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq) cfs_rq->throttled = 1; cfs_rq->throttled_clock = rq_clock(rq); raw_spin_lock(&cfs_b->lock); - list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq); + /* + * Add to the _head_ of the list, so that an already-started + * distribute_cfs_runtime will not see us + */ + list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq); if (!cfs_b->timer_active) __start_cfs_bandwidth(cfs_b, false); raw_spin_unlock(&cfs_b->lock); @@ -3410,14 +3430,15 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) /* determine whether we need to wake up potentially idle cpu */ if (rq->curr == rq->idle && rq->cfs.nr_running) - resched_task(rq->curr); + resched_curr(rq); } static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining, u64 expires) { struct cfs_rq *cfs_rq; - u64 runtime = remaining; + u64 runtime; + u64 starting_runtime = remaining; rcu_read_lock(); list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq, @@ -3448,7 +3469,7 @@ next: } rcu_read_unlock(); - return remaining; + return starting_runtime - remaining; } /* @@ -3494,22 +3515,17 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) /* account preceding periods in which throttling occurred */ cfs_b->nr_throttled += overrun; - /* - * There are throttled entities so we must first use the new bandwidth - * to unthrottle them before making it generally available. This - * ensures that all existing debts will be paid before a new cfs_rq is - * allowed to run. - */ - runtime = cfs_b->runtime; runtime_expires = cfs_b->runtime_expires; - cfs_b->runtime = 0; /* - * This check is repeated as we are holding onto the new bandwidth - * while we unthrottle. This can potentially race with an unthrottled - * group trying to acquire new bandwidth from the global pool. + * This check is repeated as we are holding onto the new bandwidth while + * we unthrottle. This can potentially race with an unthrottled group + * trying to acquire new bandwidth from the global pool. This can result + * in us over-using our runtime if it is all used during this loop, but + * only by limited amounts in that extreme case. */ - while (throttled && runtime > 0) { + while (throttled && cfs_b->runtime > 0) { + runtime = cfs_b->runtime; raw_spin_unlock(&cfs_b->lock); /* we can't nest cfs_b->lock while distributing bandwidth */ runtime = distribute_cfs_runtime(cfs_b, runtime, @@ -3517,10 +3533,10 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) raw_spin_lock(&cfs_b->lock); throttled = !list_empty(&cfs_b->throttled_cfs_rq); + + cfs_b->runtime -= min(runtime, cfs_b->runtime); } - /* return (any) remaining runtime */ - cfs_b->runtime = runtime; /* * While we are ensured activity in the period following an * unthrottle, this also covers the case in which the new bandwidth is @@ -3631,10 +3647,9 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) return; } - if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) { + if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) runtime = cfs_b->runtime; - cfs_b->runtime = 0; - } + expires = cfs_b->runtime_expires; raw_spin_unlock(&cfs_b->lock); @@ -3645,7 +3660,7 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) raw_spin_lock(&cfs_b->lock); if (expires == cfs_b->runtime_expires) - cfs_b->runtime = runtime; + cfs_b->runtime -= min(runtime, cfs_b->runtime); raw_spin_unlock(&cfs_b->lock); } @@ -3775,6 +3790,19 @@ static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) hrtimer_cancel(&cfs_b->slack_timer); } +static void __maybe_unused update_runtime_enabled(struct rq *rq) +{ + struct cfs_rq *cfs_rq; + + for_each_leaf_cfs_rq(rq, cfs_rq) { + struct cfs_bandwidth *cfs_b = &cfs_rq->tg->cfs_bandwidth; + + raw_spin_lock(&cfs_b->lock); + cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF; + raw_spin_unlock(&cfs_b->lock); + } +} + static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) { struct cfs_rq *cfs_rq; @@ -3788,6 +3816,12 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) * there's some valid quota amount */ cfs_rq->runtime_remaining = 1; + /* + * Offline rq is schedulable till cpu is completely disabled + * in take_cpu_down(), so we prevent new cfs throttling here. + */ + cfs_rq->runtime_enabled = 0; + if (cfs_rq_throttled(cfs_rq)) unthrottle_cfs_rq(cfs_rq); } @@ -3831,6 +3865,7 @@ static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) return NULL; } static inline void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {} +static inline void update_runtime_enabled(struct rq *rq) {} static inline void unthrottle_offline_cfs_rqs(struct rq *rq) {} #endif /* CONFIG_CFS_BANDWIDTH */ @@ -3854,7 +3889,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p) if (delta < 0) { if (rq->curr == p) - resched_task(p); + resched_curr(rq); return; } @@ -4723,7 +4758,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ return; preempt: - resched_task(curr); + resched_curr(rq); /* * Only set the backward buddy when the current task is still * on the rq. This can happen when a wakeup gets interleaved @@ -5094,8 +5129,7 @@ static void move_task(struct task_struct *p, struct lb_env *env) /* * Is this task likely cache-hot: */ -static int -task_hot(struct task_struct *p, u64 now) +static int task_hot(struct task_struct *p, struct lb_env *env) { s64 delta; @@ -5108,7 +5142,7 @@ task_hot(struct task_struct *p, u64 now) /* * Buddy candidates are cache hot: */ - if (sched_feat(CACHE_HOT_BUDDY) && this_rq()->nr_running && + if (sched_feat(CACHE_HOT_BUDDY) && env->dst_rq->nr_running && (&p->se == cfs_rq_of(&p->se)->next || &p->se == cfs_rq_of(&p->se)->last)) return 1; @@ -5118,7 +5152,7 @@ task_hot(struct task_struct *p, u64 now) if (sysctl_sched_migration_cost == 0) return 0; - delta = now - p->se.exec_start; + delta = rq_clock_task(env->src_rq) - p->se.exec_start; return delta < (s64)sysctl_sched_migration_cost; } @@ -5272,7 +5306,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) * 2) task is cache cold, or * 3) too many balance attempts have failed. */ - tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq)); + tsk_cache_hot = task_hot(p, env); if (!tsk_cache_hot) tsk_cache_hot = migrate_degrades_locality(p, env); @@ -5864,10 +5898,12 @@ static inline int sg_capacity_factor(struct lb_env *env, struct sched_group *gro * @load_idx: Load index of sched_domain of this_cpu for load calc. * @local_group: Does group contain this_cpu. * @sgs: variable to hold the statistics for this group. + * @overload: Indicate more than one runnable task for any CPU. */ static inline void update_sg_lb_stats(struct lb_env *env, struct sched_group *group, int load_idx, - int local_group, struct sg_lb_stats *sgs) + int local_group, struct sg_lb_stats *sgs, + bool *overload) { unsigned long load; int i; @@ -5885,6 +5921,10 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->group_load += load; sgs->sum_nr_running += rq->nr_running; + + if (rq->nr_running > 1) + *overload = true; + #ifdef CONFIG_NUMA_BALANCING sgs->nr_numa_running += rq->nr_numa_running; sgs->nr_preferred_running += rq->nr_preferred_running; @@ -5995,6 +6035,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd struct sched_group *sg = env->sd->groups; struct sg_lb_stats tmp_sgs; int load_idx, prefer_sibling = 0; + bool overload = false; if (child && child->flags & SD_PREFER_SIBLING) prefer_sibling = 1; @@ -6015,7 +6056,8 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd update_group_capacity(env->sd, env->dst_cpu); } - update_sg_lb_stats(env, sg, load_idx, local_group, sgs); + update_sg_lb_stats(env, sg, load_idx, local_group, sgs, + &overload); if (local_group) goto next_group; @@ -6049,6 +6091,13 @@ next_group: if (env->sd->flags & SD_NUMA) env->fbq_type = fbq_classify_group(&sds->busiest_stat); + + if (!env->sd->parent) { + /* update overload indicator if we are at root domain */ + if (env->dst_rq->rd->overload != overload) + env->dst_rq->rd->overload = overload; + } + } /** @@ -6767,7 +6816,8 @@ static int idle_balance(struct rq *this_rq) */ this_rq->idle_stamp = rq_clock(this_rq); - if (this_rq->avg_idle < sysctl_sched_migration_cost) { + if (this_rq->avg_idle < sysctl_sched_migration_cost || + !this_rq->rd->overload) { rcu_read_lock(); sd = rcu_dereference_check_sched_domain(this_rq->sd); if (sd) @@ -7325,6 +7375,8 @@ void trigger_load_balance(struct rq *rq) static void rq_online_fair(struct rq *rq) { update_sysctl(); + + update_runtime_enabled(rq); } static void rq_offline_fair(struct rq *rq) @@ -7398,7 +7450,7 @@ static void task_fork_fair(struct task_struct *p) * 'current' within the tree based on its new key value. */ swap(curr->vruntime, se->vruntime); - resched_task(rq->curr); + resched_curr(rq); } se->vruntime -= cfs_rq->min_vruntime; @@ -7423,7 +7475,7 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio) */ if (rq->curr == p) { if (p->prio > oldprio) - resched_task(rq->curr); + resched_curr(rq); } else check_preempt_curr(rq, p, 0); } @@ -7486,7 +7538,7 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p) * if we can still preempt the current task. */ if (rq->curr == p) - resched_task(rq->curr); + resched_curr(rq); else check_preempt_curr(rq, p, 0); } diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 658a58dc30f4..11e7bc434f43 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -79,7 +79,7 @@ static void cpuidle_idle_call(void) struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices); struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); int next_state, entered_state; - bool broadcast; + unsigned int broadcast; /* * Check if the idle task must be rescheduled. If it is the @@ -135,7 +135,7 @@ use_default: goto exit_idle; } - broadcast = !!(drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP); + broadcast = drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP; /* * Tell the time framework to switch to a broadcast timer diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c index 879f2b75266a..67ad4e7f506a 100644 --- a/kernel/sched/idle_task.c +++ b/kernel/sched/idle_task.c @@ -20,7 +20,7 @@ select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags) */ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int flags) { - resched_task(rq->idle); + resched_curr(rq); } static struct task_struct * diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index a49083192c64..5f6edca4fafd 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -463,9 +463,10 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se); static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) { struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr; + struct rq *rq = rq_of_rt_rq(rt_rq); struct sched_rt_entity *rt_se; - int cpu = cpu_of(rq_of_rt_rq(rt_rq)); + int cpu = cpu_of(rq); rt_se = rt_rq->tg->rt_se[cpu]; @@ -476,7 +477,7 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) enqueue_rt_entity(rt_se, false); if (rt_rq->highest_prio.curr < curr->prio) - resched_task(curr); + resched_curr(rq); } } @@ -566,7 +567,7 @@ static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq) return; enqueue_top_rt_rq(rt_rq); - resched_task(rq->curr); + resched_curr(rq); } static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq) @@ -740,6 +741,9 @@ balanced: rt_rq->rt_throttled = 0; raw_spin_unlock(&rt_rq->rt_runtime_lock); raw_spin_unlock(&rt_b->rt_runtime_lock); + + /* Make rt_rq available for pick_next_task() */ + sched_rt_rq_enqueue(rt_rq); } } @@ -948,7 +952,7 @@ static void update_curr_rt(struct rq *rq) raw_spin_lock(&rt_rq->rt_runtime_lock); rt_rq->rt_time += delta_exec; if (sched_rt_runtime_exceeded(rt_rq)) - resched_task(curr); + resched_curr(rq); raw_spin_unlock(&rt_rq->rt_runtime_lock); } } @@ -1363,7 +1367,7 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) * to try and push current away: */ requeue_task_rt(rq, p, 1); - resched_task(rq->curr); + resched_curr(rq); } #endif /* CONFIG_SMP */ @@ -1374,7 +1378,7 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flags) { if (p->prio < rq->curr->prio) { - resched_task(rq->curr); + resched_curr(rq); return; } @@ -1690,7 +1694,7 @@ retry: * just reschedule current. */ if (unlikely(next_task->prio < rq->curr->prio)) { - resched_task(rq->curr); + resched_curr(rq); return 0; } @@ -1737,7 +1741,7 @@ retry: activate_task(lowest_rq, next_task, 0); ret = 1; - resched_task(lowest_rq->curr); + resched_curr(lowest_rq); double_unlock_balance(rq, lowest_rq); @@ -1936,7 +1940,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p) return; if (pull_rt_task(rq)) - resched_task(rq->curr); + resched_curr(rq); } void __init init_sched_rt_class(void) @@ -1974,7 +1978,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) check_resched = 0; #endif /* CONFIG_SMP */ if (check_resched && p->prio < rq->curr->prio) - resched_task(rq->curr); + resched_curr(rq); } } @@ -2003,11 +2007,11 @@ prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio) * Only reschedule if p is still on the same runqueue. */ if (p->prio > rq->rt.highest_prio.curr && rq->curr == p) - resched_task(p); + resched_curr(rq); #else /* For UP simply resched on drop of prio */ if (oldprio < p->prio) - resched_task(p); + resched_curr(rq); #endif /* CONFIG_SMP */ } else { /* @@ -2016,7 +2020,7 @@ prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio) * then reschedule. */ if (p->prio < rq->curr->prio) - resched_task(rq->curr); + resched_curr(rq); } } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 31cc02ebc54e..579712f4e9d5 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -477,6 +477,9 @@ struct root_domain { cpumask_var_t span; cpumask_var_t online; + /* Indicate more than one runnable task for any CPU */ + bool overload; + /* * The bit corresponding to a CPU gets set here if such CPU has more * than one runnable -deadline task (as it is below for RT tasks). @@ -884,20 +887,10 @@ enum { #undef SCHED_FEAT #if defined(CONFIG_SCHED_DEBUG) && defined(HAVE_JUMP_LABEL) -static __always_inline bool static_branch__true(struct static_key *key) -{ - return static_key_true(key); /* Not out of line branch. */ -} - -static __always_inline bool static_branch__false(struct static_key *key) -{ - return static_key_false(key); /* Out of line branch. */ -} - #define SCHED_FEAT(name, enabled) \ static __always_inline bool static_branch_##name(struct static_key *key) \ { \ - return static_branch__##enabled(key); \ + return static_key_##enabled(key); \ } #include "features.h" @@ -1196,7 +1189,7 @@ extern void init_sched_rt_class(void); extern void init_sched_fair_class(void); extern void init_sched_dl_class(void); -extern void resched_task(struct task_struct *p); +extern void resched_curr(struct rq *rq); extern void resched_cpu(int cpu); extern struct rt_bandwidth def_rt_bandwidth; @@ -1218,15 +1211,26 @@ static inline void add_nr_running(struct rq *rq, unsigned count) rq->nr_running = prev_nr + count; -#ifdef CONFIG_NO_HZ_FULL if (prev_nr < 2 && rq->nr_running >= 2) { +#ifdef CONFIG_SMP + if (!rq->rd->overload) + rq->rd->overload = true; +#endif + +#ifdef CONFIG_NO_HZ_FULL if (tick_nohz_full_cpu(rq->cpu)) { - /* Order rq->nr_running write against the IPI */ - smp_wmb(); - smp_send_reschedule(rq->cpu); + /* + * Tick is needed if more than one task runs on a CPU. + * Send the target an IPI to kick it out of nohz mode. + * + * We assume that IPI implies full memory barrier and the + * new value of rq->nr_running is visible on reception + * from the target. + */ + tick_nohz_full_kick_cpu(rq->cpu); } - } #endif + } } static inline void sub_nr_running(struct rq *rq, unsigned count) diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 0ffa20ae657b..15cab1a4f84e 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -319,14 +319,14 @@ EXPORT_SYMBOL(wake_bit_function); */ int __sched __wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q, - int (*action)(void *), unsigned mode) + wait_bit_action_f *action, unsigned mode) { int ret = 0; do { prepare_to_wait(wq, &q->wait, mode); if (test_bit(q->key.bit_nr, q->key.flags)) - ret = (*action)(q->key.flags); + ret = (*action)(&q->key); } while (test_bit(q->key.bit_nr, q->key.flags) && !ret); finish_wait(wq, &q->wait); return ret; @@ -334,7 +334,7 @@ __wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q, EXPORT_SYMBOL(__wait_on_bit); int __sched out_of_line_wait_on_bit(void *word, int bit, - int (*action)(void *), unsigned mode) + wait_bit_action_f *action, unsigned mode) { wait_queue_head_t *wq = bit_waitqueue(word, bit); DEFINE_WAIT_BIT(wait, word, bit); @@ -345,7 +345,7 @@ EXPORT_SYMBOL(out_of_line_wait_on_bit); int __sched __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q, - int (*action)(void *), unsigned mode) + wait_bit_action_f *action, unsigned mode) { do { int ret; @@ -353,7 +353,7 @@ __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q, prepare_to_wait_exclusive(wq, &q->wait, mode); if (!test_bit(q->key.bit_nr, q->key.flags)) continue; - ret = action(q->key.flags); + ret = action(&q->key); if (!ret) continue; abort_exclusive_wait(wq, &q->wait, mode, &q->key); @@ -365,7 +365,7 @@ __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q, EXPORT_SYMBOL(__wait_on_bit_lock); int __sched out_of_line_wait_on_bit_lock(void *word, int bit, - int (*action)(void *), unsigned mode) + wait_bit_action_f *action, unsigned mode) { wait_queue_head_t *wq = bit_waitqueue(word, bit); DEFINE_WAIT_BIT(wait, word, bit); @@ -502,3 +502,21 @@ void wake_up_atomic_t(atomic_t *p) __wake_up_bit(atomic_t_waitqueue(p), p, WAIT_ATOMIC_T_BIT_NR); } EXPORT_SYMBOL(wake_up_atomic_t); + +__sched int bit_wait(struct wait_bit_key *word) +{ + if (signal_pending_state(current->state, current)) + return 1; + schedule(); + return 0; +} +EXPORT_SYMBOL(bit_wait); + +__sched int bit_wait_io(struct wait_bit_key *word) +{ + if (signal_pending_state(current->state, current)) + return 1; + io_schedule(); + return 0; +} +EXPORT_SYMBOL(bit_wait_io); diff --git a/kernel/signal.c b/kernel/signal.c index a4077e90f19f..40b76e351e64 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1263,6 +1263,10 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, struct sighand_struct *sighand; for (;;) { + /* + * Disable interrupts early to avoid deadlocks. + * See rcu_read_unlock() comment header for details. + */ local_irq_save(*flags); rcu_read_lock(); sighand = rcu_dereference(tsk->sighand); diff --git a/kernel/smp.c b/kernel/smp.c index 80c33f8de14f..487653b5844f 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -3,6 +3,7 @@ * * (C) Jens Axboe <jens.axboe@oracle.com> 2008 */ +#include <linux/irq_work.h> #include <linux/rcupdate.h> #include <linux/rculist.h> #include <linux/kernel.h> @@ -251,6 +252,14 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline) csd->func(csd->info); csd_unlock(csd); } + + /* + * Handle irq works queued remotely by irq_work_queue_on(). + * Smp functions above are typically synchronous so they + * better run first since some other CPUs may be busy waiting + * for them. + */ + irq_work_run(); } /* diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index f448513a45ed..d626dc98e8df 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -12,6 +12,11 @@ config CLOCKSOURCE_WATCHDOG config ARCH_CLOCKSOURCE_DATA bool +# Clocksources require validation of the clocksource against the last +# cycle update - x86/TSC misfeature +config CLOCKSOURCE_VALIDATE_LAST_CYCLE + bool + # Timekeeping vsyscall support config GENERIC_TIME_VSYSCALL bool @@ -20,10 +25,6 @@ config GENERIC_TIME_VSYSCALL config GENERIC_TIME_VSYSCALL_OLD bool -# ktime_t scalar 64bit nsec representation -config KTIME_SCALAR - bool - # Old style timekeeping config ARCH_USES_GETTIMEOFFSET bool diff --git a/kernel/time/Makefile b/kernel/time/Makefile index 57a413fd0ebf..7347426fa68d 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -1,3 +1,4 @@ +obj-y += time.o timer.o hrtimer.o itimer.o posix-timers.o posix-cpu-timers.o obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o obj-y += timeconv.o posix-clock.o alarmtimer.o @@ -12,3 +13,21 @@ obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o obj-$(CONFIG_TICK_ONESHOT) += tick-sched.o obj-$(CONFIG_TIMER_STATS) += timer_stats.o obj-$(CONFIG_DEBUG_FS) += timekeeping_debug.o +obj-$(CONFIG_TEST_UDELAY) += udelay_test.o + +$(obj)/time.o: $(obj)/timeconst.h + +quiet_cmd_hzfile = HZFILE $@ + cmd_hzfile = echo "hz=$(CONFIG_HZ)" > $@ + +targets += hz.bc +$(obj)/hz.bc: $(objtree)/include/config/hz.h FORCE + $(call if_changed,hzfile) + +quiet_cmd_bc = BC $@ + cmd_bc = bc -q $(filter-out FORCE,$^) > $@ + +targets += timeconst.h +$(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE + $(call if_changed,bc) + diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index ba3e502c955a..2e949cc9c9f1 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -32,6 +32,7 @@ #include <linux/kthread.h> #include "tick-internal.h" +#include "timekeeping_internal.h" void timecounter_init(struct timecounter *tc, const struct cyclecounter *cc, @@ -249,7 +250,7 @@ void clocksource_mark_unstable(struct clocksource *cs) static void clocksource_watchdog(unsigned long data) { struct clocksource *cs; - cycle_t csnow, wdnow; + cycle_t csnow, wdnow, delta; int64_t wd_nsec, cs_nsec; int next_cpu, reset_pending; @@ -282,11 +283,12 @@ static void clocksource_watchdog(unsigned long data) continue; } - wd_nsec = clocksource_cyc2ns((wdnow - cs->wd_last) & watchdog->mask, - watchdog->mult, watchdog->shift); + delta = clocksource_delta(wdnow, cs->wd_last, watchdog->mask); + wd_nsec = clocksource_cyc2ns(delta, watchdog->mult, + watchdog->shift); - cs_nsec = clocksource_cyc2ns((csnow - cs->cs_last) & - cs->mask, cs->mult, cs->shift); + delta = clocksource_delta(csnow, cs->cs_last, cs->mask); + cs_nsec = clocksource_cyc2ns(delta, cs->mult, cs->shift); cs->cs_last = csnow; cs->wd_last = wdnow; diff --git a/kernel/hrtimer.c b/kernel/time/hrtimer.c index 3ab28993f6e0..1c2fe7de2842 100644 --- a/kernel/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -54,6 +54,8 @@ #include <trace/events/timer.h> +#include "timekeeping.h" + /* * The timer bases: * @@ -114,21 +116,18 @@ static inline int hrtimer_clockid_to_base(clockid_t clock_id) */ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base) { - ktime_t xtim, mono, boot; - struct timespec xts, tom, slp; - s32 tai_offset; + ktime_t xtim, mono, boot, tai; + ktime_t off_real, off_boot, off_tai; - get_xtime_and_monotonic_and_sleep_offset(&xts, &tom, &slp); - tai_offset = timekeeping_get_tai_offset(); + 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); - xtim = timespec_to_ktime(xts); - mono = ktime_add(xtim, timespec_to_ktime(tom)); - boot = ktime_add(mono, timespec_to_ktime(slp)); base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim; base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono; base->clock_base[HRTIMER_BASE_BOOTTIME].softirq_time = boot; - base->clock_base[HRTIMER_BASE_TAI].softirq_time = - ktime_add(xtim, ktime_set(tai_offset, 0)); + base->clock_base[HRTIMER_BASE_TAI].softirq_time = tai; } /* @@ -264,60 +263,6 @@ lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) * too large for inlining: */ #if BITS_PER_LONG < 64 -# ifndef CONFIG_KTIME_SCALAR -/** - * ktime_add_ns - Add a scalar nanoseconds value to a ktime_t variable - * @kt: addend - * @nsec: the scalar nsec value to add - * - * Returns the sum of kt and nsec in ktime_t format - */ -ktime_t ktime_add_ns(const ktime_t kt, u64 nsec) -{ - ktime_t tmp; - - if (likely(nsec < NSEC_PER_SEC)) { - tmp.tv64 = nsec; - } else { - unsigned long rem = do_div(nsec, NSEC_PER_SEC); - - /* Make sure nsec fits into long */ - if (unlikely(nsec > KTIME_SEC_MAX)) - return (ktime_t){ .tv64 = KTIME_MAX }; - - tmp = ktime_set((long)nsec, rem); - } - - return ktime_add(kt, tmp); -} - -EXPORT_SYMBOL_GPL(ktime_add_ns); - -/** - * ktime_sub_ns - Subtract a scalar nanoseconds value from a ktime_t variable - * @kt: minuend - * @nsec: the scalar nsec value to subtract - * - * Returns the subtraction of @nsec from @kt in ktime_t format - */ -ktime_t ktime_sub_ns(const ktime_t kt, u64 nsec) -{ - ktime_t tmp; - - if (likely(nsec < NSEC_PER_SEC)) { - tmp.tv64 = nsec; - } else { - unsigned long rem = do_div(nsec, NSEC_PER_SEC); - - tmp = ktime_set((long)nsec, rem); - } - - return ktime_sub(kt, tmp); -} - -EXPORT_SYMBOL_GPL(ktime_sub_ns); -# endif /* !CONFIG_KTIME_SCALAR */ - /* * Divide a ktime value by a nanosecond value */ @@ -337,6 +282,7 @@ u64 ktime_divns(const ktime_t kt, s64 div) return dclc; } +EXPORT_SYMBOL_GPL(ktime_divns); #endif /* BITS_PER_LONG >= 64 */ /* @@ -602,6 +548,11 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) * timers, we have to check, whether it expires earlier than the timer for * which the clock event device was armed. * + * Note, that in case the state has HRTIMER_STATE_CALLBACK set, no reprogramming + * and no expiry check happens. The timer gets enqueued into the rbtree. The + * reprogramming and expiry check is done in the hrtimer_interrupt or in the + * softirq. + * * Called with interrupts disabled and base->cpu_base.lock held */ static int hrtimer_reprogram(struct hrtimer *timer, @@ -662,25 +613,13 @@ static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) base->hres_active = 0; } -/* - * When High resolution timers are active, try to reprogram. Note, that in case - * the state has HRTIMER_STATE_CALLBACK set, no reprogramming and no expiry - * check happens. The timer gets enqueued into the rbtree. The reprogramming - * and expiry check is done in the hrtimer_interrupt or in the softirq. - */ -static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, - struct hrtimer_clock_base *base) -{ - return base->cpu_base->hres_active && hrtimer_reprogram(timer, base); -} - static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) { ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset; ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset; ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset; - return ktime_get_update_offsets(offs_real, offs_boot, offs_tai); + return ktime_get_update_offsets_now(offs_real, offs_boot, offs_tai); } /* @@ -755,8 +694,8 @@ static inline int hrtimer_is_hres_enabled(void) { return 0; } static inline int hrtimer_switch_to_hres(void) { return 0; } static inline void hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { } -static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, - struct hrtimer_clock_base *base) +static inline int hrtimer_reprogram(struct hrtimer *timer, + struct hrtimer_clock_base *base) { return 0; } @@ -1013,14 +952,25 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, leftmost = enqueue_hrtimer(timer, new_base); - /* - * Only allow reprogramming if the new base is on this CPU. - * (it might still be on another CPU if the timer was pending) - * - * XXX send_remote_softirq() ? - */ - if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases) - && hrtimer_enqueue_reprogram(timer, new_base)) { + if (!leftmost) { + unlock_hrtimer_base(timer, &flags); + return ret; + } + + if (!hrtimer_is_hres_active(timer)) { + /* + * Kick to reschedule the next tick to handle the new timer + * on dynticks target. + */ + wake_up_nohz_cpu(new_base->cpu_base->cpu); + } else if (new_base->cpu_base == &__get_cpu_var(hrtimer_bases) && + hrtimer_reprogram(timer, new_base)) { + /* + * Only allow reprogramming if the new base is on this CPU. + * (it might still be on another CPU if the timer was pending) + * + * XXX send_remote_softirq() ? + */ if (wakeup) { /* * We need to drop cpu_base->lock to avoid a @@ -1680,6 +1630,7 @@ static void init_hrtimers_cpu(int cpu) timerqueue_init_head(&cpu_base->clock_base[i].active); } + cpu_base->cpu = cpu; hrtimer_init_hres(cpu_base); } diff --git a/kernel/itimer.c b/kernel/time/itimer.c index 8d262b467573..8d262b467573 100644 --- a/kernel/itimer.c +++ b/kernel/time/itimer.c diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 33db43a39515..87a346fd6d61 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -466,7 +466,8 @@ static DECLARE_DELAYED_WORK(sync_cmos_work, sync_cmos_clock); static void sync_cmos_clock(struct work_struct *work) { - struct timespec now, next; + struct timespec64 now; + struct timespec next; int fail = 1; /* @@ -485,9 +486,9 @@ static void sync_cmos_clock(struct work_struct *work) return; } - getnstimeofday(&now); + getnstimeofday64(&now); if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec * 5) { - struct timespec adjust = now; + struct timespec adjust = timespec64_to_timespec(now); fail = -ENODEV; if (persistent_clock_is_local) @@ -531,7 +532,7 @@ void ntp_notify_cmos_timer(void) { } /* * Propagate a new txc->status value into the NTP state: */ -static inline void process_adj_status(struct timex *txc, struct timespec *ts) +static inline void process_adj_status(struct timex *txc, struct timespec64 *ts) { if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) { time_state = TIME_OK; @@ -554,7 +555,7 @@ static inline void process_adj_status(struct timex *txc, struct timespec *ts) static inline void process_adjtimex_modes(struct timex *txc, - struct timespec *ts, + struct timespec64 *ts, s32 *time_tai) { if (txc->modes & ADJ_STATUS) @@ -640,7 +641,7 @@ int ntp_validate_timex(struct timex *txc) * adjtimex mainly allows reading (and writing, if superuser) of * kernel time-keeping variables. used by xntpd. */ -int __do_adjtimex(struct timex *txc, struct timespec *ts, s32 *time_tai) +int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai) { int result; @@ -684,7 +685,7 @@ int __do_adjtimex(struct timex *txc, struct timespec *ts, s32 *time_tai) /* fill PPS status fields */ pps_fill_timex(txc); - txc->time.tv_sec = ts->tv_sec; + txc->time.tv_sec = (time_t)ts->tv_sec; txc->time.tv_usec = ts->tv_nsec; if (!(time_status & STA_NANO)) txc->time.tv_usec /= NSEC_PER_USEC; diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h index 1950cb4ca2a4..bbd102ad9df7 100644 --- a/kernel/time/ntp_internal.h +++ b/kernel/time/ntp_internal.h @@ -7,6 +7,6 @@ extern void ntp_clear(void); extern u64 ntp_tick_length(void); extern int second_overflow(unsigned long secs); extern int ntp_validate_timex(struct timex *); -extern int __do_adjtimex(struct timex *, struct timespec *, s32 *); +extern int __do_adjtimex(struct timex *, struct timespec64 *, s32 *); extern void __hardpps(const struct timespec *, const struct timespec *); #endif /* _LINUX_NTP_INTERNAL_H */ diff --git a/kernel/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 3b8946416a5f..3b8946416a5f 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c diff --git a/kernel/posix-timers.c b/kernel/time/posix-timers.c index 424c2d4265c9..42b463ad90f2 100644 --- a/kernel/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -49,6 +49,8 @@ #include <linux/export.h> #include <linux/hashtable.h> +#include "timekeeping.h" + /* * Management arrays for POSIX timers. Timers are now kept in static hash table * with 512 entries. diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 7ab92b19965a..c19c1d84b6f3 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -4,6 +4,8 @@ #include <linux/hrtimer.h> #include <linux/tick.h> +#include "timekeeping.h" + extern seqlock_t jiffies_lock; #define CS_NAME_LEN 32 diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 6558b7ac112d..99aa6ee3908f 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -154,6 +154,7 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) #ifdef CONFIG_NO_HZ_FULL cpumask_var_t tick_nohz_full_mask; +cpumask_var_t housekeeping_mask; bool tick_nohz_full_running; static bool can_stop_full_tick(void) @@ -224,13 +225,15 @@ static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { }; /* - * Kick the current CPU if it's full dynticks in order to force it to + * Kick the CPU if it's full dynticks in order to force it to * re-evaluate its dependency on the tick and restart it if necessary. */ -void tick_nohz_full_kick(void) +void tick_nohz_full_kick_cpu(int cpu) { - if (tick_nohz_full_cpu(smp_processor_id())) - irq_work_queue(&__get_cpu_var(nohz_full_kick_work)); + if (!tick_nohz_full_cpu(cpu)) + return; + + irq_work_queue_on(&per_cpu(nohz_full_kick_work, cpu), cpu); } static void nohz_full_kick_ipi(void *info) @@ -281,6 +284,7 @@ static int __init tick_nohz_full_setup(char *str) int cpu; alloc_bootmem_cpumask_var(&tick_nohz_full_mask); + alloc_bootmem_cpumask_var(&housekeeping_mask); if (cpulist_parse(str, tick_nohz_full_mask) < 0) { pr_warning("NOHZ: Incorrect nohz_full cpumask\n"); return 1; @@ -291,6 +295,8 @@ static int __init tick_nohz_full_setup(char *str) pr_warning("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", cpu); cpumask_clear_cpu(cpu, tick_nohz_full_mask); } + cpumask_andnot(housekeeping_mask, + cpu_possible_mask, tick_nohz_full_mask); tick_nohz_full_running = true; return 1; @@ -332,9 +338,15 @@ static int tick_nohz_init_all(void) pr_err("NO_HZ: Can't allocate full dynticks cpumask\n"); return err; } + if (!alloc_cpumask_var(&housekeeping_mask, GFP_KERNEL)) { + pr_err("NO_HZ: Can't allocate not-full dynticks cpumask\n"); + return err; + } err = 0; cpumask_setall(tick_nohz_full_mask); cpumask_clear_cpu(smp_processor_id(), tick_nohz_full_mask); + cpumask_clear(housekeeping_mask); + cpumask_set_cpu(smp_processor_id(), housekeeping_mask); tick_nohz_full_running = true; #endif return err; diff --git a/kernel/time.c b/kernel/time/time.c index 7c7964c33ae7..f0294ba14634 100644 --- a/kernel/time.c +++ b/kernel/time/time.c @@ -42,6 +42,7 @@ #include <asm/unistd.h> #include "timeconst.h" +#include "timekeeping.h" /* * The timezone where the local system is located. Used as a default by some @@ -420,6 +421,68 @@ struct timeval ns_to_timeval(const s64 nsec) } EXPORT_SYMBOL(ns_to_timeval); +#if BITS_PER_LONG == 32 +/** + * set_normalized_timespec - set timespec sec and nsec parts and normalize + * + * @ts: pointer to timespec variable to be set + * @sec: seconds to set + * @nsec: nanoseconds to set + * + * Set seconds and nanoseconds field of a timespec variable and + * normalize to the timespec storage format + * + * Note: The tv_nsec part is always in the range of + * 0 <= tv_nsec < NSEC_PER_SEC + * For negative values only the tv_sec field is negative ! + */ +void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec) +{ + while (nsec >= NSEC_PER_SEC) { + /* + * The following asm() prevents the compiler from + * optimising this loop into a modulo operation. See + * also __iter_div_u64_rem() in include/linux/time.h + */ + asm("" : "+rm"(nsec)); + nsec -= NSEC_PER_SEC; + ++sec; + } + while (nsec < 0) { + asm("" : "+rm"(nsec)); + nsec += NSEC_PER_SEC; + --sec; + } + ts->tv_sec = sec; + ts->tv_nsec = nsec; +} +EXPORT_SYMBOL(set_normalized_timespec64); + +/** + * ns_to_timespec64 - Convert nanoseconds to timespec64 + * @nsec: the nanoseconds value to be converted + * + * Returns the timespec64 representation of the nsec parameter. + */ +struct timespec64 ns_to_timespec64(const s64 nsec) +{ + struct timespec64 ts; + s32 rem; + + if (!nsec) + return (struct timespec64) {0, 0}; + + ts.tv_sec = div_s64_rem(nsec, NSEC_PER_SEC, &rem); + if (unlikely(rem < 0)) { + ts.tv_sec--; + rem += NSEC_PER_SEC; + } + ts.tv_nsec = rem; + + return ts; +} +EXPORT_SYMBOL(ns_to_timespec64); +#endif /* * When we convert to jiffies then we interpret incoming values * the following way: @@ -694,6 +757,7 @@ unsigned long nsecs_to_jiffies(u64 n) { return (unsigned long)nsecs_to_jiffies64(n); } +EXPORT_SYMBOL_GPL(nsecs_to_jiffies); /* * Add two timespec values and do a safety check for overflow. diff --git a/kernel/timeconst.bc b/kernel/time/timeconst.bc index 511bdf2cafda..511bdf2cafda 100644 --- a/kernel/timeconst.bc +++ b/kernel/time/timeconst.bc diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 32d8d6aaedb8..f36b02838a47 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -32,11 +32,34 @@ #define TK_MIRROR (1 << 1) #define TK_CLOCK_WAS_SET (1 << 2) -static struct timekeeper timekeeper; +/* + * The most important data for readout fits into a single 64 byte + * cache line. + */ +static struct { + seqcount_t seq; + struct timekeeper timekeeper; +} tk_core ____cacheline_aligned; + static DEFINE_RAW_SPINLOCK(timekeeper_lock); -static seqcount_t timekeeper_seq; static struct timekeeper shadow_timekeeper; +/** + * struct tk_fast - NMI safe timekeeper + * @seq: Sequence counter for protecting updates. The lowest bit + * is the index for the tk_read_base array + * @base: tk_read_base array. Access is indexed by the lowest bit of + * @seq. + * + * See @update_fast_timekeeper() below. + */ +struct tk_fast { + seqcount_t seq; + struct tk_read_base base[2]; +}; + +static struct tk_fast tk_fast_mono ____cacheline_aligned; + /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; @@ -45,49 +68,54 @@ bool __read_mostly persistent_clock_exist = false; static inline void tk_normalize_xtime(struct timekeeper *tk) { - while (tk->xtime_nsec >= ((u64)NSEC_PER_SEC << tk->shift)) { - tk->xtime_nsec -= (u64)NSEC_PER_SEC << tk->shift; + while (tk->tkr.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr.shift)) { + tk->tkr.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr.shift; tk->xtime_sec++; } } -static void tk_set_xtime(struct timekeeper *tk, const struct timespec *ts) +static inline struct timespec64 tk_xtime(struct timekeeper *tk) +{ + struct timespec64 ts; + + ts.tv_sec = tk->xtime_sec; + ts.tv_nsec = (long)(tk->tkr.xtime_nsec >> tk->tkr.shift); + return ts; +} + +static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec = ts->tv_sec; - tk->xtime_nsec = (u64)ts->tv_nsec << tk->shift; + tk->tkr.xtime_nsec = (u64)ts->tv_nsec << tk->tkr.shift; } -static void tk_xtime_add(struct timekeeper *tk, const struct timespec *ts) +static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec += ts->tv_sec; - tk->xtime_nsec += (u64)ts->tv_nsec << tk->shift; + tk->tkr.xtime_nsec += (u64)ts->tv_nsec << tk->tkr.shift; tk_normalize_xtime(tk); } -static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec wtm) +static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) { - struct timespec tmp; + struct timespec64 tmp; /* * Verify consistency of: offset_real = -wall_to_monotonic * before modifying anything */ - set_normalized_timespec(&tmp, -tk->wall_to_monotonic.tv_sec, + set_normalized_timespec64(&tmp, -tk->wall_to_monotonic.tv_sec, -tk->wall_to_monotonic.tv_nsec); - WARN_ON_ONCE(tk->offs_real.tv64 != timespec_to_ktime(tmp).tv64); + WARN_ON_ONCE(tk->offs_real.tv64 != timespec64_to_ktime(tmp).tv64); tk->wall_to_monotonic = wtm; - set_normalized_timespec(&tmp, -wtm.tv_sec, -wtm.tv_nsec); - tk->offs_real = timespec_to_ktime(tmp); + set_normalized_timespec64(&tmp, -wtm.tv_sec, -wtm.tv_nsec); + tk->offs_real = timespec64_to_ktime(tmp); tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0)); } -static void tk_set_sleep_time(struct timekeeper *tk, struct timespec t) +static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) { - /* Verify consistency before modifying */ - WARN_ON_ONCE(tk->offs_boot.tv64 != timespec_to_ktime(tk->total_sleep_time).tv64); - - tk->total_sleep_time = t; - tk->offs_boot = timespec_to_ktime(t); + tk->offs_boot = ktime_add(tk->offs_boot, delta); } /** @@ -107,9 +135,11 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) u64 tmp, ntpinterval; struct clocksource *old_clock; - old_clock = tk->clock; - tk->clock = clock; - tk->cycle_last = clock->cycle_last = clock->read(clock); + old_clock = tk->tkr.clock; + tk->tkr.clock = clock; + tk->tkr.read = clock->read; + tk->tkr.mask = clock->mask; + tk->tkr.cycle_last = tk->tkr.read(clock); /* Do the ns -> cycle conversion first, using original mult */ tmp = NTP_INTERVAL_LENGTH; @@ -133,78 +163,212 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) if (old_clock) { int shift_change = clock->shift - old_clock->shift; if (shift_change < 0) - tk->xtime_nsec >>= -shift_change; + tk->tkr.xtime_nsec >>= -shift_change; else - tk->xtime_nsec <<= shift_change; + tk->tkr.xtime_nsec <<= shift_change; } - tk->shift = clock->shift; + tk->tkr.shift = clock->shift; tk->ntp_error = 0; tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; + tk->ntp_tick = ntpinterval << tk->ntp_error_shift; /* * The timekeeper keeps its own mult values for the currently * active clocksource. These value will be adjusted via NTP * to counteract clock drifting. */ - tk->mult = clock->mult; + tk->tkr.mult = clock->mult; + tk->ntp_err_mult = 0; } /* Timekeeper helper functions. */ #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET -u32 (*arch_gettimeoffset)(void); - -u32 get_arch_timeoffset(void) -{ - if (likely(arch_gettimeoffset)) - return arch_gettimeoffset(); - return 0; -} +static u32 default_arch_gettimeoffset(void) { return 0; } +u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset; #else -static inline u32 get_arch_timeoffset(void) { return 0; } +static inline u32 arch_gettimeoffset(void) { return 0; } #endif -static inline s64 timekeeping_get_ns(struct timekeeper *tk) +static inline s64 timekeeping_get_ns(struct tk_read_base *tkr) { - cycle_t cycle_now, cycle_delta; - struct clocksource *clock; + cycle_t cycle_now, delta; s64 nsec; /* read clocksource: */ - clock = tk->clock; - cycle_now = clock->read(clock); + cycle_now = tkr->read(tkr->clock); /* calculate the delta since the last update_wall_time: */ - cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; + delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask); - nsec = cycle_delta * tk->mult + tk->xtime_nsec; - nsec >>= tk->shift; + nsec = delta * tkr->mult + tkr->xtime_nsec; + nsec >>= tkr->shift; /* If arch requires, add in get_arch_timeoffset() */ - return nsec + get_arch_timeoffset(); + return nsec + arch_gettimeoffset(); } static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk) { - cycle_t cycle_now, cycle_delta; - struct clocksource *clock; + struct clocksource *clock = tk->tkr.clock; + cycle_t cycle_now, delta; s64 nsec; /* read clocksource: */ - clock = tk->clock; - cycle_now = clock->read(clock); + cycle_now = tk->tkr.read(clock); /* calculate the delta since the last update_wall_time: */ - cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; + delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, tk->tkr.mask); /* convert delta to nanoseconds. */ - nsec = clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift); + nsec = clocksource_cyc2ns(delta, clock->mult, clock->shift); /* If arch requires, add in get_arch_timeoffset() */ - return nsec + get_arch_timeoffset(); + return nsec + arch_gettimeoffset(); +} + +/** + * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper. + * @tk: The timekeeper from which we take the update + * @tkf: The fast timekeeper to update + * @tbase: The time base for the fast timekeeper (mono/raw) + * + * We want to use this from any context including NMI and tracing / + * instrumenting the timekeeping code itself. + * + * So we handle this differently than the other timekeeping accessor + * functions which retry when the sequence count has changed. The + * update side does: + * + * smp_wmb(); <- Ensure that the last base[1] update is visible + * tkf->seq++; + * smp_wmb(); <- Ensure that the seqcount update is visible + * update(tkf->base[0], tk); + * smp_wmb(); <- Ensure that the base[0] update is visible + * tkf->seq++; + * smp_wmb(); <- Ensure that the seqcount update is visible + * update(tkf->base[1], tk); + * + * The reader side does: + * + * do { + * seq = tkf->seq; + * smp_rmb(); + * idx = seq & 0x01; + * now = now(tkf->base[idx]); + * smp_rmb(); + * } while (seq != tkf->seq) + * + * As long as we update base[0] readers are forced off to + * base[1]. Once base[0] is updated readers are redirected to base[0] + * and the base[1] update takes place. + * + * So if a NMI hits the update of base[0] then it will use base[1] + * which is still consistent. In the worst case this can result is a + * slightly wrong timestamp (a few nanoseconds). See + * @ktime_get_mono_fast_ns. + */ +static void update_fast_timekeeper(struct timekeeper *tk) +{ + struct tk_read_base *base = tk_fast_mono.base; + + /* Force readers off to base[1] */ + raw_write_seqcount_latch(&tk_fast_mono.seq); + + /* Update base[0] */ + memcpy(base, &tk->tkr, sizeof(*base)); + + /* Force readers back to base[0] */ + raw_write_seqcount_latch(&tk_fast_mono.seq); + + /* Update base[1] */ + memcpy(base + 1, base, sizeof(*base)); } +/** + * ktime_get_mono_fast_ns - Fast NMI safe access to clock monotonic + * + * This timestamp is not guaranteed to be monotonic across an update. + * The timestamp is calculated by: + * + * now = base_mono + clock_delta * slope + * + * So if the update lowers the slope, readers who are forced to the + * not yet updated second array are still using the old steeper slope. + * + * tmono + * ^ + * | o n + * | o n + * | u + * | o + * |o + * |12345678---> reader order + * + * o = old slope + * u = update + * n = new slope + * + * So reader 6 will observe time going backwards versus reader 5. + * + * While other CPUs are likely to be able observe that, the only way + * for a CPU local observation is when an NMI hits in the middle of + * the update. Timestamps taken from that NMI context might be ahead + * of the following timestamps. Callers need to be aware of that and + * deal with it. + */ +u64 notrace ktime_get_mono_fast_ns(void) +{ + struct tk_read_base *tkr; + unsigned int seq; + u64 now; + + do { + seq = raw_read_seqcount(&tk_fast_mono.seq); + tkr = tk_fast_mono.base + (seq & 0x01); + now = ktime_to_ns(tkr->base_mono) + timekeeping_get_ns(tkr); + + } while (read_seqcount_retry(&tk_fast_mono.seq, seq)); + return now; +} +EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns); + +#ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD + +static inline void update_vsyscall(struct timekeeper *tk) +{ + struct timespec xt; + + xt = timespec64_to_timespec(tk_xtime(tk)); + update_vsyscall_old(&xt, &tk->wall_to_monotonic, tk->tkr.clock, tk->tkr.mult, + tk->tkr.cycle_last); +} + +static inline void old_vsyscall_fixup(struct timekeeper *tk) +{ + s64 remainder; + + /* + * Store only full nanoseconds into xtime_nsec after rounding + * it up and add the remainder to the error difference. + * XXX - This is necessary to avoid small 1ns inconsistnecies caused + * by truncating the remainder in vsyscalls. However, it causes + * additional work to be done in timekeeping_adjust(). Once + * the vsyscall implementations are converted to use xtime_nsec + * (shifted nanoseconds), and CONFIG_GENERIC_TIME_VSYSCALL_OLD + * users are removed, this can be killed. + */ + remainder = tk->tkr.xtime_nsec & ((1ULL << tk->tkr.shift) - 1); + tk->tkr.xtime_nsec -= remainder; + tk->tkr.xtime_nsec += 1ULL << tk->tkr.shift; + tk->ntp_error += remainder << tk->ntp_error_shift; + tk->ntp_error -= (1ULL << tk->tkr.shift) << tk->ntp_error_shift; +} +#else +#define old_vsyscall_fixup(tk) +#endif + static RAW_NOTIFIER_HEAD(pvclock_gtod_chain); static void update_pvclock_gtod(struct timekeeper *tk, bool was_set) @@ -217,7 +381,7 @@ static void update_pvclock_gtod(struct timekeeper *tk, bool was_set) */ int pvclock_gtod_register_notifier(struct notifier_block *nb) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; int ret; @@ -247,6 +411,29 @@ int pvclock_gtod_unregister_notifier(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier); +/* + * Update the ktime_t based scalar nsec members of the timekeeper + */ +static inline void tk_update_ktime_data(struct timekeeper *tk) +{ + s64 nsec; + + /* + * The xtime based monotonic readout is: + * nsec = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec + now(); + * The ktime based monotonic readout is: + * nsec = base_mono + now(); + * ==> base_mono = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec + */ + nsec = (s64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec); + nsec *= NSEC_PER_SEC; + nsec += tk->wall_to_monotonic.tv_nsec; + tk->tkr.base_mono = ns_to_ktime(nsec); + + /* Update the monotonic raw base */ + tk->base_raw = timespec64_to_ktime(tk->raw_time); +} + /* must hold timekeeper_lock */ static void timekeeping_update(struct timekeeper *tk, unsigned int action) { @@ -257,8 +444,13 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) update_vsyscall(tk); update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); + tk_update_ktime_data(tk); + if (action & TK_MIRROR) - memcpy(&shadow_timekeeper, &timekeeper, sizeof(timekeeper)); + memcpy(&shadow_timekeeper, &tk_core.timekeeper, + sizeof(tk_core.timekeeper)); + + update_fast_timekeeper(tk); } /** @@ -270,49 +462,48 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) */ static void timekeeping_forward_now(struct timekeeper *tk) { - cycle_t cycle_now, cycle_delta; - struct clocksource *clock; + struct clocksource *clock = tk->tkr.clock; + cycle_t cycle_now, delta; s64 nsec; - clock = tk->clock; - cycle_now = clock->read(clock); - cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; - tk->cycle_last = clock->cycle_last = cycle_now; + cycle_now = tk->tkr.read(clock); + delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, tk->tkr.mask); + tk->tkr.cycle_last = cycle_now; - tk->xtime_nsec += cycle_delta * tk->mult; + tk->tkr.xtime_nsec += delta * tk->tkr.mult; /* If arch requires, add in get_arch_timeoffset() */ - tk->xtime_nsec += (u64)get_arch_timeoffset() << tk->shift; + tk->tkr.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr.shift; tk_normalize_xtime(tk); - nsec = clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift); - timespec_add_ns(&tk->raw_time, nsec); + nsec = clocksource_cyc2ns(delta, clock->mult, clock->shift); + timespec64_add_ns(&tk->raw_time, nsec); } /** - * __getnstimeofday - Returns the time of day in a timespec. + * __getnstimeofday64 - Returns the time of day in a timespec64. * @ts: pointer to the timespec to be set * * Updates the time of day in the timespec. * Returns 0 on success, or -ve when suspended (timespec will be undefined). */ -int __getnstimeofday(struct timespec *ts) +int __getnstimeofday64(struct timespec64 *ts) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long seq; s64 nsecs = 0; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; - nsecs = timekeeping_get_ns(tk); + nsecs = timekeeping_get_ns(&tk->tkr); - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; - timespec_add_ns(ts, nsecs); + timespec64_add_ns(ts, nsecs); /* * Do not bail out early, in case there were callers still using @@ -322,116 +513,138 @@ int __getnstimeofday(struct timespec *ts) return -EAGAIN; return 0; } -EXPORT_SYMBOL(__getnstimeofday); +EXPORT_SYMBOL(__getnstimeofday64); /** - * getnstimeofday - Returns the time of day in a timespec. + * getnstimeofday64 - Returns the time of day in a timespec64. * @ts: pointer to the timespec to be set * * Returns the time of day in a timespec (WARN if suspended). */ -void getnstimeofday(struct timespec *ts) +void getnstimeofday64(struct timespec64 *ts) { - WARN_ON(__getnstimeofday(ts)); + WARN_ON(__getnstimeofday64(ts)); } -EXPORT_SYMBOL(getnstimeofday); +EXPORT_SYMBOL(getnstimeofday64); ktime_t ktime_get(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; - s64 secs, nsecs; + ktime_t base; + s64 nsecs; WARN_ON(timekeeping_suspended); do { - seq = read_seqcount_begin(&timekeeper_seq); - secs = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; - nsecs = timekeeping_get_ns(tk) + tk->wall_to_monotonic.tv_nsec; + seq = read_seqcount_begin(&tk_core.seq); + base = tk->tkr.base_mono; + nsecs = timekeeping_get_ns(&tk->tkr); - } while (read_seqcount_retry(&timekeeper_seq, seq)); - /* - * Use ktime_set/ktime_add_ns to create a proper ktime on - * 32-bit architectures without CONFIG_KTIME_SCALAR. - */ - return ktime_add_ns(ktime_set(secs, 0), nsecs); + } while (read_seqcount_retry(&tk_core.seq, seq)); + + return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get); -/** - * ktime_get_ts - get the monotonic clock in timespec format - * @ts: pointer to timespec variable - * - * The function calculates the monotonic clock from the realtime - * clock and the wall_to_monotonic offset and stores the result - * in normalized timespec format in the variable pointed to by @ts. - */ -void ktime_get_ts(struct timespec *ts) +static ktime_t *offsets[TK_OFFS_MAX] = { + [TK_OFFS_REAL] = &tk_core.timekeeper.offs_real, + [TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot, + [TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai, +}; + +ktime_t ktime_get_with_offset(enum tk_offsets offs) { - struct timekeeper *tk = &timekeeper; - struct timespec tomono; - s64 nsec; + struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; + ktime_t base, *offset = offsets[offs]; + s64 nsecs; WARN_ON(timekeeping_suspended); do { - seq = read_seqcount_begin(&timekeeper_seq); - ts->tv_sec = tk->xtime_sec; - nsec = timekeeping_get_ns(tk); - tomono = tk->wall_to_monotonic; + seq = read_seqcount_begin(&tk_core.seq); + base = ktime_add(tk->tkr.base_mono, *offset); + nsecs = timekeeping_get_ns(&tk->tkr); - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); - ts->tv_sec += tomono.tv_sec; - ts->tv_nsec = 0; - timespec_add_ns(ts, nsec + tomono.tv_nsec); -} -EXPORT_SYMBOL_GPL(ktime_get_ts); + return ktime_add_ns(base, nsecs); +} +EXPORT_SYMBOL_GPL(ktime_get_with_offset); /** - * timekeeping_clocktai - Returns the TAI time of day in a timespec - * @ts: pointer to the timespec to be set - * - * Returns the time of day in a timespec. + * ktime_mono_to_any() - convert mononotic time to any other time + * @tmono: time to convert. + * @offs: which offset to use */ -void timekeeping_clocktai(struct timespec *ts) +ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs) { - struct timekeeper *tk = &timekeeper; + ktime_t *offset = offsets[offs]; unsigned long seq; - u64 nsecs; - - WARN_ON(timekeeping_suspended); + ktime_t tconv; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); + tconv = ktime_add(tmono, *offset); + } while (read_seqcount_retry(&tk_core.seq, seq)); - ts->tv_sec = tk->xtime_sec + tk->tai_offset; - nsecs = timekeeping_get_ns(tk); + return tconv; +} +EXPORT_SYMBOL_GPL(ktime_mono_to_any); - } while (read_seqcount_retry(&timekeeper_seq, seq)); +/** + * ktime_get_raw - Returns the raw monotonic time in ktime_t format + */ +ktime_t ktime_get_raw(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned int seq; + ktime_t base; + s64 nsecs; - ts->tv_nsec = 0; - timespec_add_ns(ts, nsecs); + do { + seq = read_seqcount_begin(&tk_core.seq); + base = tk->base_raw; + nsecs = timekeeping_get_ns_raw(tk); -} -EXPORT_SYMBOL(timekeeping_clocktai); + } while (read_seqcount_retry(&tk_core.seq, seq)); + return ktime_add_ns(base, nsecs); +} +EXPORT_SYMBOL_GPL(ktime_get_raw); /** - * ktime_get_clocktai - Returns the TAI time of day in a ktime + * ktime_get_ts64 - get the monotonic clock in timespec64 format + * @ts: pointer to timespec variable * - * Returns the time of day in a ktime. + * The function calculates the monotonic clock from the realtime + * clock and the wall_to_monotonic offset and stores the result + * in normalized timespec format in the variable pointed to by @ts. */ -ktime_t ktime_get_clocktai(void) +void ktime_get_ts64(struct timespec64 *ts) { - struct timespec ts; + struct timekeeper *tk = &tk_core.timekeeper; + struct timespec64 tomono; + s64 nsec; + unsigned int seq; + + WARN_ON(timekeeping_suspended); - timekeeping_clocktai(&ts); - return timespec_to_ktime(ts); + do { + seq = read_seqcount_begin(&tk_core.seq); + ts->tv_sec = tk->xtime_sec; + nsec = timekeeping_get_ns(&tk->tkr); + tomono = tk->wall_to_monotonic; + + } while (read_seqcount_retry(&tk_core.seq, seq)); + + ts->tv_sec += tomono.tv_sec; + ts->tv_nsec = 0; + timespec64_add_ns(ts, nsec + tomono.tv_nsec); } -EXPORT_SYMBOL(ktime_get_clocktai); +EXPORT_SYMBOL_GPL(ktime_get_ts64); #ifdef CONFIG_NTP_PPS @@ -446,23 +659,23 @@ EXPORT_SYMBOL(ktime_get_clocktai); */ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long seq; s64 nsecs_raw, nsecs_real; WARN_ON_ONCE(timekeeping_suspended); do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); - *ts_raw = tk->raw_time; + *ts_raw = timespec64_to_timespec(tk->raw_time); ts_real->tv_sec = tk->xtime_sec; ts_real->tv_nsec = 0; nsecs_raw = timekeeping_get_ns_raw(tk); - nsecs_real = timekeeping_get_ns(tk); + nsecs_real = timekeeping_get_ns(&tk->tkr); - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); timespec_add_ns(ts_raw, nsecs_raw); timespec_add_ns(ts_real, nsecs_real); @@ -479,9 +692,9 @@ EXPORT_SYMBOL(getnstime_raw_and_real); */ void do_gettimeofday(struct timeval *tv) { - struct timespec now; + struct timespec64 now; - getnstimeofday(&now); + getnstimeofday64(&now); tv->tv_sec = now.tv_sec; tv->tv_usec = now.tv_nsec/1000; } @@ -495,15 +708,15 @@ EXPORT_SYMBOL(do_gettimeofday); */ int do_settimeofday(const struct timespec *tv) { - struct timekeeper *tk = &timekeeper; - struct timespec ts_delta, xt; + struct timekeeper *tk = &tk_core.timekeeper; + struct timespec64 ts_delta, xt, tmp; unsigned long flags; if (!timespec_valid_strict(tv)) return -EINVAL; raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); @@ -511,13 +724,14 @@ int do_settimeofday(const struct timespec *tv) ts_delta.tv_sec = tv->tv_sec - xt.tv_sec; ts_delta.tv_nsec = tv->tv_nsec - xt.tv_nsec; - tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, ts_delta)); + tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts_delta)); - tk_set_xtime(tk, tv); + tmp = timespec_to_timespec64(*tv); + tk_set_xtime(tk, &tmp); timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* signal hrtimers about time change */ @@ -535,33 +749,35 @@ EXPORT_SYMBOL(do_settimeofday); */ int timekeeping_inject_offset(struct timespec *ts) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; - struct timespec tmp; + struct timespec64 ts64, tmp; int ret = 0; if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) return -EINVAL; + ts64 = timespec_to_timespec64(*ts); + raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); /* Make sure the proposed value is valid */ - tmp = timespec_add(tk_xtime(tk), *ts); - if (!timespec_valid_strict(&tmp)) { + tmp = timespec64_add(tk_xtime(tk), ts64); + if (!timespec64_valid_strict(&tmp)) { ret = -EINVAL; goto error; } - tk_xtime_add(tk, ts); - tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *ts)); + tk_xtime_add(tk, &ts64); + tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts64)); error: /* even if we error out, we forwarded the time, so call update */ timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* signal hrtimers about time change */ @@ -578,14 +794,14 @@ EXPORT_SYMBOL(timekeeping_inject_offset); */ s32 timekeeping_get_tai_offset(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; s32 ret; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); ret = tk->tai_offset; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } @@ -606,14 +822,14 @@ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) */ void timekeeping_set_tai_offset(s32 tai_offset) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); __timekeeping_set_tai_offset(tk, tai_offset); timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); clock_was_set(); } @@ -625,14 +841,14 @@ void timekeeping_set_tai_offset(s32 tai_offset) */ static int change_clocksource(void *data) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *new, *old; unsigned long flags; new = (struct clocksource *) data; raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); /* @@ -641,7 +857,7 @@ static int change_clocksource(void *data) */ if (try_module_get(new->owner)) { if (!new->enable || new->enable(new) == 0) { - old = tk->clock; + old = tk->tkr.clock; tk_setup_internals(tk, new); if (old->disable) old->disable(old); @@ -652,7 +868,7 @@ static int change_clocksource(void *data) } timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return 0; @@ -667,29 +883,14 @@ static int change_clocksource(void *data) */ int timekeeping_notify(struct clocksource *clock) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; - if (tk->clock == clock) + if (tk->tkr.clock == clock) return 0; stop_machine(change_clocksource, clock, NULL); tick_clock_notify(); - return tk->clock == clock ? 0 : -1; -} - -/** - * ktime_get_real - get the real (wall-) time in ktime_t format - * - * returns the time in ktime_t format - */ -ktime_t ktime_get_real(void) -{ - struct timespec now; - - getnstimeofday(&now); - - return timespec_to_ktime(now); + return tk->tkr.clock == clock ? 0 : -1; } -EXPORT_SYMBOL_GPL(ktime_get_real); /** * getrawmonotonic - Returns the raw monotonic time in a timespec @@ -699,18 +900,20 @@ EXPORT_SYMBOL_GPL(ktime_get_real); */ void getrawmonotonic(struct timespec *ts) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; + struct timespec64 ts64; unsigned long seq; s64 nsecs; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); nsecs = timekeeping_get_ns_raw(tk); - *ts = tk->raw_time; + ts64 = tk->raw_time; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); - timespec_add_ns(ts, nsecs); + timespec64_add_ns(&ts64, nsecs); + *ts = timespec64_to_timespec(ts64); } EXPORT_SYMBOL(getrawmonotonic); @@ -719,16 +922,16 @@ EXPORT_SYMBOL(getrawmonotonic); */ int timekeeping_valid_for_hres(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long seq; int ret; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); - ret = tk->clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; + ret = tk->tkr.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } @@ -738,16 +941,16 @@ int timekeeping_valid_for_hres(void) */ u64 timekeeping_max_deferment(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long seq; u64 ret; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); - ret = tk->clock->max_idle_ns; + ret = tk->tkr.clock->max_idle_ns; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } @@ -787,14 +990,15 @@ void __weak read_boot_clock(struct timespec *ts) */ void __init timekeeping_init(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *clock; unsigned long flags; - struct timespec now, boot, tmp; - - read_persistent_clock(&now); + struct timespec64 now, boot, tmp; + struct timespec ts; - if (!timespec_valid_strict(&now)) { + read_persistent_clock(&ts); + now = timespec_to_timespec64(ts); + if (!timespec64_valid_strict(&now)) { pr_warn("WARNING: Persistent clock returned invalid value!\n" " Check your CMOS/BIOS settings.\n"); now.tv_sec = 0; @@ -802,8 +1006,9 @@ void __init timekeeping_init(void) } else if (now.tv_sec || now.tv_nsec) persistent_clock_exist = true; - read_boot_clock(&boot); - if (!timespec_valid_strict(&boot)) { + read_boot_clock(&ts); + boot = timespec_to_timespec64(ts); + if (!timespec64_valid_strict(&boot)) { pr_warn("WARNING: Boot clock returned invalid value!\n" " Check your CMOS/BIOS settings.\n"); boot.tv_sec = 0; @@ -811,7 +1016,7 @@ void __init timekeeping_init(void) } raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); ntp_init(); clock = clocksource_default_clock(); @@ -822,24 +1027,21 @@ void __init timekeeping_init(void) tk_set_xtime(tk, &now); tk->raw_time.tv_sec = 0; tk->raw_time.tv_nsec = 0; + tk->base_raw.tv64 = 0; if (boot.tv_sec == 0 && boot.tv_nsec == 0) boot = tk_xtime(tk); - set_normalized_timespec(&tmp, -boot.tv_sec, -boot.tv_nsec); + set_normalized_timespec64(&tmp, -boot.tv_sec, -boot.tv_nsec); tk_set_wall_to_mono(tk, tmp); - tmp.tv_sec = 0; - tmp.tv_nsec = 0; - tk_set_sleep_time(tk, tmp); - - memcpy(&shadow_timekeeper, &timekeeper, sizeof(timekeeper)); + timekeeping_update(tk, TK_MIRROR); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); } /* time in seconds when suspend began */ -static struct timespec timekeeping_suspend_time; +static struct timespec64 timekeeping_suspend_time; /** * __timekeeping_inject_sleeptime - Internal function to add sleep interval @@ -849,17 +1051,17 @@ static struct timespec timekeeping_suspend_time; * adds the sleep offset to the timekeeping variables. */ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, - struct timespec *delta) + struct timespec64 *delta) { - if (!timespec_valid_strict(delta)) { + if (!timespec64_valid_strict(delta)) { printk_deferred(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid " "sleep delta value!\n"); return; } tk_xtime_add(tk, delta); - tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *delta)); - tk_set_sleep_time(tk, timespec_add(tk->total_sleep_time, *delta)); + tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta)); + tk_update_sleep_time(tk, timespec64_to_ktime(*delta)); tk_debug_account_sleep_time(delta); } @@ -875,7 +1077,8 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, */ void timekeeping_inject_sleeptime(struct timespec *delta) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; + struct timespec64 tmp; unsigned long flags; /* @@ -886,15 +1089,16 @@ void timekeeping_inject_sleeptime(struct timespec *delta) return; raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); - __timekeeping_inject_sleeptime(tk, delta); + tmp = timespec_to_timespec64(*delta); + __timekeeping_inject_sleeptime(tk, &tmp); timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* signal hrtimers about time change */ @@ -910,20 +1114,22 @@ void timekeeping_inject_sleeptime(struct timespec *delta) */ static void timekeeping_resume(void) { - struct timekeeper *tk = &timekeeper; - struct clocksource *clock = tk->clock; + struct timekeeper *tk = &tk_core.timekeeper; + struct clocksource *clock = tk->tkr.clock; unsigned long flags; - struct timespec ts_new, ts_delta; + struct timespec64 ts_new, ts_delta; + struct timespec tmp; cycle_t cycle_now, cycle_delta; bool suspendtime_found = false; - read_persistent_clock(&ts_new); + read_persistent_clock(&tmp); + ts_new = timespec_to_timespec64(tmp); clockevents_resume(); clocksource_resume(); raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); /* * After system resumes, we need to calculate the suspended time and @@ -937,15 +1143,16 @@ static void timekeeping_resume(void) * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ - cycle_now = clock->read(clock); + cycle_now = tk->tkr.read(clock); if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) && - cycle_now > clock->cycle_last) { + cycle_now > tk->tkr.cycle_last) { u64 num, max = ULLONG_MAX; u32 mult = clock->mult; u32 shift = clock->shift; s64 nsec = 0; - cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; + cycle_delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, + tk->tkr.mask); /* * "cycle_delta * mutl" may cause 64 bits overflow, if the @@ -960,10 +1167,10 @@ static void timekeeping_resume(void) } nsec += ((u64) cycle_delta * mult) >> shift; - ts_delta = ns_to_timespec(nsec); + ts_delta = ns_to_timespec64(nsec); suspendtime_found = true; - } else if (timespec_compare(&ts_new, &timekeeping_suspend_time) > 0) { - ts_delta = timespec_sub(ts_new, timekeeping_suspend_time); + } else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) { + ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time); suspendtime_found = true; } @@ -971,11 +1178,11 @@ static void timekeeping_resume(void) __timekeeping_inject_sleeptime(tk, &ts_delta); /* Re-base the last cycle value */ - tk->cycle_last = clock->cycle_last = cycle_now; + tk->tkr.cycle_last = cycle_now; tk->ntp_error = 0; timekeeping_suspended = 0; timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); touch_softlockup_watchdog(); @@ -988,12 +1195,14 @@ static void timekeeping_resume(void) static int timekeeping_suspend(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; - struct timespec delta, delta_delta; - static struct timespec old_delta; + struct timespec64 delta, delta_delta; + static struct timespec64 old_delta; + struct timespec tmp; - read_persistent_clock(&timekeeping_suspend_time); + read_persistent_clock(&tmp); + timekeeping_suspend_time = timespec_to_timespec64(tmp); /* * On some systems the persistent_clock can not be detected at @@ -1004,7 +1213,7 @@ static int timekeeping_suspend(void) persistent_clock_exist = true; raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); timekeeping_suspended = 1; @@ -1014,8 +1223,8 @@ static int timekeeping_suspend(void) * try to compensate so the difference in system time * and persistent_clock time stays close to constant. */ - delta = timespec_sub(tk_xtime(tk), timekeeping_suspend_time); - delta_delta = timespec_sub(delta, old_delta); + delta = timespec64_sub(tk_xtime(tk), timekeeping_suspend_time); + delta_delta = timespec64_sub(delta, old_delta); if (abs(delta_delta.tv_sec) >= 2) { /* * if delta_delta is too large, assume time correction @@ -1025,11 +1234,11 @@ static int timekeeping_suspend(void) } else { /* Otherwise try to adjust old_system to compensate */ timekeeping_suspend_time = - timespec_add(timekeeping_suspend_time, delta_delta); + timespec64_add(timekeeping_suspend_time, delta_delta); } timekeeping_update(tk, TK_MIRROR); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL); @@ -1050,125 +1259,34 @@ static int __init timekeeping_init_ops(void) register_syscore_ops(&timekeeping_syscore_ops); return 0; } - device_initcall(timekeeping_init_ops); /* - * If the error is already larger, we look ahead even further - * to compensate for late or lost adjustments. + * Apply a multiplier adjustment to the timekeeper */ -static __always_inline int timekeeping_bigadjust(struct timekeeper *tk, - s64 error, s64 *interval, - s64 *offset) +static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk, + s64 offset, + bool negative, + int adj_scale) { - s64 tick_error, i; - u32 look_ahead, adj; - s32 error2, mult; - - /* - * Use the current error value to determine how much to look ahead. - * The larger the error the slower we adjust for it to avoid problems - * with losing too many ticks, otherwise we would overadjust and - * produce an even larger error. The smaller the adjustment the - * faster we try to adjust for it, as lost ticks can do less harm - * here. This is tuned so that an error of about 1 msec is adjusted - * within about 1 sec (or 2^20 nsec in 2^SHIFT_HZ ticks). - */ - error2 = tk->ntp_error >> (NTP_SCALE_SHIFT + 22 - 2 * SHIFT_HZ); - error2 = abs(error2); - for (look_ahead = 0; error2 > 0; look_ahead++) - error2 >>= 2; + s64 interval = tk->cycle_interval; + s32 mult_adj = 1; - /* - * Now calculate the error in (1 << look_ahead) ticks, but first - * remove the single look ahead already included in the error. - */ - tick_error = ntp_tick_length() >> (tk->ntp_error_shift + 1); - tick_error -= tk->xtime_interval >> 1; - error = ((error - tick_error) >> look_ahead) + tick_error; - - /* Finally calculate the adjustment shift value. */ - i = *interval; - mult = 1; - if (error < 0) { - error = -error; - *interval = -*interval; - *offset = -*offset; - mult = -1; + if (negative) { + mult_adj = -mult_adj; + interval = -interval; + offset = -offset; } - for (adj = 0; error > i; adj++) - error >>= 1; - - *interval <<= adj; - *offset <<= adj; - return mult << adj; -} - -/* - * Adjust the multiplier to reduce the error value, - * this is optimized for the most common adjustments of -1,0,1, - * for other values we can do a bit more work. - */ -static void timekeeping_adjust(struct timekeeper *tk, s64 offset) -{ - s64 error, interval = tk->cycle_interval; - int adj; + mult_adj <<= adj_scale; + interval <<= adj_scale; + offset <<= adj_scale; /* - * The point of this is to check if the error is greater than half - * an interval. - * - * First we shift it down from NTP_SHIFT to clocksource->shifted nsecs. - * - * Note we subtract one in the shift, so that error is really error*2. - * This "saves" dividing(shifting) interval twice, but keeps the - * (error > interval) comparison as still measuring if error is - * larger than half an interval. - * - * Note: It does not "save" on aggravation when reading the code. - */ - error = tk->ntp_error >> (tk->ntp_error_shift - 1); - if (error > interval) { - /* - * We now divide error by 4(via shift), which checks if - * the error is greater than twice the interval. - * If it is greater, we need a bigadjust, if its smaller, - * we can adjust by 1. - */ - error >>= 2; - if (likely(error <= interval)) - adj = 1; - else - adj = timekeeping_bigadjust(tk, error, &interval, &offset); - } else { - if (error < -interval) { - /* See comment above, this is just switched for the negative */ - error >>= 2; - if (likely(error >= -interval)) { - adj = -1; - interval = -interval; - offset = -offset; - } else { - adj = timekeeping_bigadjust(tk, error, &interval, &offset); - } - } else { - goto out_adjust; - } - } - - if (unlikely(tk->clock->maxadj && - (tk->mult + adj > tk->clock->mult + tk->clock->maxadj))) { - printk_deferred_once(KERN_WARNING - "Adjusting %s more than 11%% (%ld vs %ld)\n", - tk->clock->name, (long)tk->mult + adj, - (long)tk->clock->mult + tk->clock->maxadj); - } - /* * So the following can be confusing. * - * To keep things simple, lets assume adj == 1 for now. + * To keep things simple, lets assume mult_adj == 1 for now. * - * When adj != 1, remember that the interval and offset values + * When mult_adj != 1, remember that the interval and offset values * have been appropriately scaled so the math is the same. * * The basic idea here is that we're increasing the multiplier @@ -1212,12 +1330,78 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) * * XXX - TODO: Doc ntp_error calculation. */ - tk->mult += adj; + tk->tkr.mult += mult_adj; tk->xtime_interval += interval; - tk->xtime_nsec -= offset; + tk->tkr.xtime_nsec -= offset; tk->ntp_error -= (interval - offset) << tk->ntp_error_shift; +} + +/* + * Calculate the multiplier adjustment needed to match the frequency + * specified by NTP + */ +static __always_inline void timekeeping_freqadjust(struct timekeeper *tk, + s64 offset) +{ + s64 interval = tk->cycle_interval; + s64 xinterval = tk->xtime_interval; + s64 tick_error; + bool negative; + u32 adj; + + /* Remove any current error adj from freq calculation */ + if (tk->ntp_err_mult) + xinterval -= tk->cycle_interval; + + tk->ntp_tick = ntp_tick_length(); + + /* Calculate current error per tick */ + tick_error = ntp_tick_length() >> tk->ntp_error_shift; + tick_error -= (xinterval + tk->xtime_remainder); + + /* Don't worry about correcting it if its small */ + if (likely((tick_error >= 0) && (tick_error <= interval))) + return; + + /* preserve the direction of correction */ + negative = (tick_error < 0); + + /* Sort out the magnitude of the correction */ + tick_error = abs(tick_error); + for (adj = 0; tick_error > interval; adj++) + tick_error >>= 1; + + /* scale the corrections */ + timekeeping_apply_adjustment(tk, offset, negative, adj); +} + +/* + * Adjust the timekeeper's multiplier to the correct frequency + * and also to reduce the accumulated error value. + */ +static void timekeeping_adjust(struct timekeeper *tk, s64 offset) +{ + /* Correct for the current frequency error */ + timekeeping_freqadjust(tk, offset); + + /* Next make a small adjustment to fix any cumulative error */ + if (!tk->ntp_err_mult && (tk->ntp_error > 0)) { + tk->ntp_err_mult = 1; + timekeeping_apply_adjustment(tk, offset, 0, 0); + } else if (tk->ntp_err_mult && (tk->ntp_error <= 0)) { + /* Undo any existing error adjustment */ + timekeeping_apply_adjustment(tk, offset, 1, 0); + tk->ntp_err_mult = 0; + } + + if (unlikely(tk->tkr.clock->maxadj && + (tk->tkr.mult > tk->tkr.clock->mult + tk->tkr.clock->maxadj))) { + printk_once(KERN_WARNING + "Adjusting %s more than 11%% (%ld vs %ld)\n", + tk->tkr.clock->name, (long)tk->tkr.mult, + (long)tk->tkr.clock->mult + tk->tkr.clock->maxadj); + } -out_adjust: /* * It may be possible that when we entered this function, xtime_nsec * was very small. Further, if we're slightly speeding the clocksource @@ -1232,12 +1416,11 @@ out_adjust: * We'll correct this error next time through this function, when * xtime_nsec is not as small. */ - if (unlikely((s64)tk->xtime_nsec < 0)) { - s64 neg = -(s64)tk->xtime_nsec; - tk->xtime_nsec = 0; + if (unlikely((s64)tk->tkr.xtime_nsec < 0)) { + s64 neg = -(s64)tk->tkr.xtime_nsec; + tk->tkr.xtime_nsec = 0; tk->ntp_error += neg << tk->ntp_error_shift; } - } /** @@ -1250,26 +1433,26 @@ out_adjust: */ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk) { - u64 nsecps = (u64)NSEC_PER_SEC << tk->shift; + u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr.shift; unsigned int clock_set = 0; - while (tk->xtime_nsec >= nsecps) { + while (tk->tkr.xtime_nsec >= nsecps) { int leap; - tk->xtime_nsec -= nsecps; + tk->tkr.xtime_nsec -= nsecps; tk->xtime_sec++; /* Figure out if its a leap sec and apply if needed */ leap = second_overflow(tk->xtime_sec); if (unlikely(leap)) { - struct timespec ts; + struct timespec64 ts; tk->xtime_sec += leap; ts.tv_sec = leap; ts.tv_nsec = 0; tk_set_wall_to_mono(tk, - timespec_sub(tk->wall_to_monotonic, ts)); + timespec64_sub(tk->wall_to_monotonic, ts)); __timekeeping_set_tai_offset(tk, tk->tai_offset - leap); @@ -1301,9 +1484,9 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset, /* Accumulate one shifted interval */ offset -= interval; - tk->cycle_last += interval; + tk->tkr.cycle_last += interval; - tk->xtime_nsec += tk->xtime_interval << shift; + tk->tkr.xtime_nsec += tk->xtime_interval << shift; *clock_set |= accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ @@ -1317,48 +1500,20 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset, tk->raw_time.tv_nsec = raw_nsecs; /* Accumulate error between NTP and clock interval */ - tk->ntp_error += ntp_tick_length() << shift; + tk->ntp_error += tk->ntp_tick << shift; tk->ntp_error -= (tk->xtime_interval + tk->xtime_remainder) << (tk->ntp_error_shift + shift); return offset; } -#ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD -static inline void old_vsyscall_fixup(struct timekeeper *tk) -{ - s64 remainder; - - /* - * Store only full nanoseconds into xtime_nsec after rounding - * it up and add the remainder to the error difference. - * XXX - This is necessary to avoid small 1ns inconsistnecies caused - * by truncating the remainder in vsyscalls. However, it causes - * additional work to be done in timekeeping_adjust(). Once - * the vsyscall implementations are converted to use xtime_nsec - * (shifted nanoseconds), and CONFIG_GENERIC_TIME_VSYSCALL_OLD - * users are removed, this can be killed. - */ - remainder = tk->xtime_nsec & ((1ULL << tk->shift) - 1); - tk->xtime_nsec -= remainder; - tk->xtime_nsec += 1ULL << tk->shift; - tk->ntp_error += remainder << tk->ntp_error_shift; - tk->ntp_error -= (1ULL << tk->shift) << tk->ntp_error_shift; -} -#else -#define old_vsyscall_fixup(tk) -#endif - - - /** * update_wall_time - Uses the current clocksource to increment the wall time * */ void update_wall_time(void) { - struct clocksource *clock; - struct timekeeper *real_tk = &timekeeper; + struct timekeeper *real_tk = &tk_core.timekeeper; struct timekeeper *tk = &shadow_timekeeper; cycle_t offset; int shift = 0, maxshift; @@ -1371,12 +1526,11 @@ void update_wall_time(void) if (unlikely(timekeeping_suspended)) goto out; - clock = real_tk->clock; - #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET offset = real_tk->cycle_interval; #else - offset = (clock->read(clock) - clock->cycle_last) & clock->mask; + offset = clocksource_delta(tk->tkr.read(tk->tkr.clock), + tk->tkr.cycle_last, tk->tkr.mask); #endif /* Check if there's really nothing to do */ @@ -1418,9 +1572,7 @@ void update_wall_time(void) */ clock_set |= accumulate_nsecs_to_secs(tk); - write_seqcount_begin(&timekeeper_seq); - /* Update clock->cycle_last with the new value */ - clock->cycle_last = tk->cycle_last; + write_seqcount_begin(&tk_core.seq); /* * Update the real timekeeper. * @@ -1428,12 +1580,12 @@ void update_wall_time(void) * requires changes to all other timekeeper usage sites as * well, i.e. move the timekeeper pointer getter into the * spinlocked/seqcount protected sections. And we trade this - * memcpy under the timekeeper_seq against one before we start + * memcpy under the tk_core.seq against one before we start * updating. */ memcpy(real_tk, tk, sizeof(*tk)); timekeeping_update(real_tk, clock_set); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); out: raw_spin_unlock_irqrestore(&timekeeper_lock, flags); if (clock_set) @@ -1454,83 +1606,16 @@ out: */ void getboottime(struct timespec *ts) { - struct timekeeper *tk = &timekeeper; - struct timespec boottime = { - .tv_sec = tk->wall_to_monotonic.tv_sec + - tk->total_sleep_time.tv_sec, - .tv_nsec = tk->wall_to_monotonic.tv_nsec + - tk->total_sleep_time.tv_nsec - }; - - set_normalized_timespec(ts, -boottime.tv_sec, -boottime.tv_nsec); -} -EXPORT_SYMBOL_GPL(getboottime); - -/** - * get_monotonic_boottime - Returns monotonic time since boot - * @ts: pointer to the timespec to be set - * - * Returns the monotonic time since boot in a timespec. - * - * This is similar to CLOCK_MONTONIC/ktime_get_ts, but also - * includes the time spent in suspend. - */ -void get_monotonic_boottime(struct timespec *ts) -{ - struct timekeeper *tk = &timekeeper; - struct timespec tomono, sleep; - s64 nsec; - unsigned int seq; - - WARN_ON(timekeeping_suspended); - - do { - seq = read_seqcount_begin(&timekeeper_seq); - ts->tv_sec = tk->xtime_sec; - nsec = timekeeping_get_ns(tk); - tomono = tk->wall_to_monotonic; - sleep = tk->total_sleep_time; - - } while (read_seqcount_retry(&timekeeper_seq, seq)); - - ts->tv_sec += tomono.tv_sec + sleep.tv_sec; - ts->tv_nsec = 0; - timespec_add_ns(ts, nsec + tomono.tv_nsec + sleep.tv_nsec); -} -EXPORT_SYMBOL_GPL(get_monotonic_boottime); - -/** - * ktime_get_boottime - Returns monotonic time since boot in a ktime - * - * Returns the monotonic time since boot in a ktime - * - * This is similar to CLOCK_MONTONIC/ktime_get, but also - * includes the time spent in suspend. - */ -ktime_t ktime_get_boottime(void) -{ - struct timespec ts; - - get_monotonic_boottime(&ts); - return timespec_to_ktime(ts); -} -EXPORT_SYMBOL_GPL(ktime_get_boottime); - -/** - * monotonic_to_bootbased - Convert the monotonic time to boot based. - * @ts: pointer to the timespec to be converted - */ -void monotonic_to_bootbased(struct timespec *ts) -{ - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; + ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot); - *ts = timespec_add(*ts, tk->total_sleep_time); + *ts = ktime_to_timespec(t); } -EXPORT_SYMBOL_GPL(monotonic_to_bootbased); +EXPORT_SYMBOL_GPL(getboottime); unsigned long get_seconds(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; return tk->xtime_sec; } @@ -1538,43 +1623,44 @@ EXPORT_SYMBOL(get_seconds); struct timespec __current_kernel_time(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; - return tk_xtime(tk); + return timespec64_to_timespec(tk_xtime(tk)); } struct timespec current_kernel_time(void) { - struct timekeeper *tk = &timekeeper; - struct timespec now; + struct timekeeper *tk = &tk_core.timekeeper; + struct timespec64 now; unsigned long seq; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); now = tk_xtime(tk); - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); - return now; + return timespec64_to_timespec(now); } EXPORT_SYMBOL(current_kernel_time); struct timespec get_monotonic_coarse(void) { - struct timekeeper *tk = &timekeeper; - struct timespec now, mono; + struct timekeeper *tk = &tk_core.timekeeper; + struct timespec64 now, mono; unsigned long seq; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); now = tk_xtime(tk); mono = tk->wall_to_monotonic; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); - set_normalized_timespec(&now, now.tv_sec + mono.tv_sec, + set_normalized_timespec64(&now, now.tv_sec + mono.tv_sec, now.tv_nsec + mono.tv_nsec); - return now; + + return timespec64_to_timespec(now); } /* @@ -1587,29 +1673,38 @@ void do_timer(unsigned long ticks) } /** - * get_xtime_and_monotonic_and_sleep_offset() - get xtime, wall_to_monotonic, - * and sleep offsets. - * @xtim: pointer to timespec to be set with xtime - * @wtom: pointer to timespec to be set with wall_to_monotonic - * @sleep: pointer to timespec to be set with time in suspend + * ktime_get_update_offsets_tick - hrtimer helper + * @offs_real: pointer to storage for monotonic -> realtime offset + * @offs_boot: pointer to storage for monotonic -> boottime offset + * @offs_tai: pointer to storage for monotonic -> clock tai offset + * + * Returns monotonic time at last tick and various offsets */ -void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim, - struct timespec *wtom, struct timespec *sleep) +ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, ktime_t *offs_boot, + ktime_t *offs_tai) { - struct timekeeper *tk = &timekeeper; - unsigned long seq; + struct timekeeper *tk = &tk_core.timekeeper; + unsigned int seq; + ktime_t base; + u64 nsecs; do { - seq = read_seqcount_begin(&timekeeper_seq); - *xtim = tk_xtime(tk); - *wtom = tk->wall_to_monotonic; - *sleep = tk->total_sleep_time; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + seq = read_seqcount_begin(&tk_core.seq); + + base = tk->tkr.base_mono; + nsecs = tk->tkr.xtime_nsec >> tk->tkr.shift; + + *offs_real = tk->offs_real; + *offs_boot = tk->offs_boot; + *offs_tai = tk->offs_tai; + } while (read_seqcount_retry(&tk_core.seq, seq)); + + return ktime_add_ns(base, nsecs); } #ifdef CONFIG_HIGH_RES_TIMERS /** - * ktime_get_update_offsets - hrtimer helper + * ktime_get_update_offsets_now - hrtimer helper * @offs_real: pointer to storage for monotonic -> realtime offset * @offs_boot: pointer to storage for monotonic -> boottime offset * @offs_tai: pointer to storage for monotonic -> clock tai offset @@ -1617,57 +1712,37 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim, * Returns current monotonic time and updates the offsets * Called from hrtimer_interrupt() or retrigger_next_event() */ -ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot, +ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot, ktime_t *offs_tai) { - struct timekeeper *tk = &timekeeper; - ktime_t now; + struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; - u64 secs, nsecs; + ktime_t base; + u64 nsecs; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); - secs = tk->xtime_sec; - nsecs = timekeeping_get_ns(tk); + base = tk->tkr.base_mono; + nsecs = timekeeping_get_ns(&tk->tkr); *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; *offs_tai = tk->offs_tai; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); - now = ktime_add_ns(ktime_set(secs, 0), nsecs); - now = ktime_sub(now, *offs_real); - return now; + return ktime_add_ns(base, nsecs); } #endif /** - * ktime_get_monotonic_offset() - get wall_to_monotonic in ktime_t format - */ -ktime_t ktime_get_monotonic_offset(void) -{ - struct timekeeper *tk = &timekeeper; - unsigned long seq; - struct timespec wtom; - - do { - seq = read_seqcount_begin(&timekeeper_seq); - wtom = tk->wall_to_monotonic; - } while (read_seqcount_retry(&timekeeper_seq, seq)); - - return timespec_to_ktime(wtom); -} -EXPORT_SYMBOL_GPL(ktime_get_monotonic_offset); - -/** * do_adjtimex() - Accessor function to NTP __do_adjtimex function */ int do_adjtimex(struct timex *txc) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; - struct timespec ts; + struct timespec64 ts; s32 orig_tai, tai; int ret; @@ -1687,10 +1762,10 @@ int do_adjtimex(struct timex *txc) return ret; } - getnstimeofday(&ts); + getnstimeofday64(&ts); raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); orig_tai = tai = tk->tai_offset; ret = __do_adjtimex(txc, &ts, &tai); @@ -1699,7 +1774,7 @@ int do_adjtimex(struct timex *txc) __timekeeping_set_tai_offset(tk, tai); timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); } - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); if (tai != orig_tai) @@ -1719,11 +1794,11 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); __hardpps(phase_ts, raw_ts); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); } EXPORT_SYMBOL(hardpps); diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h new file mode 100644 index 000000000000..adc1fc98bde3 --- /dev/null +++ b/kernel/time/timekeeping.h @@ -0,0 +1,20 @@ +#ifndef _KERNEL_TIME_TIMEKEEPING_H +#define _KERNEL_TIME_TIMEKEEPING_H +/* + * Internal interfaces for kernel/time/ + */ +extern ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, + ktime_t *offs_boot, + ktime_t *offs_tai); +extern ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, + ktime_t *offs_boot, + ktime_t *offs_tai); + +extern int timekeeping_valid_for_hres(void); +extern u64 timekeeping_max_deferment(void); +extern int timekeeping_inject_offset(struct timespec *ts); +extern s32 timekeeping_get_tai_offset(void); +extern void timekeeping_set_tai_offset(s32 tai_offset); +extern void timekeeping_clocktai(struct timespec *ts); + +#endif diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c index 4d54f97558df..f6bd65236712 100644 --- a/kernel/time/timekeeping_debug.c +++ b/kernel/time/timekeeping_debug.c @@ -67,7 +67,7 @@ static int __init tk_debug_sleep_time_init(void) } late_initcall(tk_debug_sleep_time_init); -void tk_debug_account_sleep_time(struct timespec *t) +void tk_debug_account_sleep_time(struct timespec64 *t) { sleep_time_bin[fls(t->tv_sec)]++; } diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h index 13323ea08ffa..4ea005a7f9da 100644 --- a/kernel/time/timekeeping_internal.h +++ b/kernel/time/timekeeping_internal.h @@ -3,12 +3,27 @@ /* * timekeeping debug functions */ +#include <linux/clocksource.h> #include <linux/time.h> #ifdef CONFIG_DEBUG_FS -extern void tk_debug_account_sleep_time(struct timespec *t); +extern void tk_debug_account_sleep_time(struct timespec64 *t); #else #define tk_debug_account_sleep_time(x) #endif +#ifdef CONFIG_CLOCKSOURCE_VALIDATE_LAST_CYCLE +static inline cycle_t clocksource_delta(cycle_t now, cycle_t last, cycle_t mask) +{ + cycle_t ret = (now - last) & mask; + + return (s64) ret > 0 ? ret : 0; +} +#else +static inline cycle_t clocksource_delta(cycle_t now, cycle_t last, cycle_t mask) +{ + return (now - last) & mask; +} +#endif + #endif /* _TIMEKEEPING_INTERNAL_H */ diff --git a/kernel/timer.c b/kernel/time/timer.c index 3bb01a323b2a..aca5dfe2fa3d 100644 --- a/kernel/timer.c +++ b/kernel/time/timer.c @@ -82,6 +82,7 @@ struct tvec_base { unsigned long next_timer; unsigned long active_timers; unsigned long all_timers; + int cpu; struct tvec_root tv1; struct tvec tv2; struct tvec tv3; @@ -409,6 +410,22 @@ static void internal_add_timer(struct tvec_base *base, struct timer_list *timer) base->next_timer = timer->expires; } base->all_timers++; + + /* + * Check whether the other CPU is in dynticks mode and needs + * to be triggered to reevaluate the timer wheel. + * We are protected against the other CPU fiddling + * with the timer by holding the timer base lock. This also + * makes sure that a CPU on the way to stop its tick can not + * evaluate the timer wheel. + * + * Spare the IPI for deferrable timers on idle targets though. + * The next busy ticks will take care of it. Except full dynticks + * require special care against races with idle_cpu(), lets deal + * with that later. + */ + if (!tbase_get_deferrable(base) || tick_nohz_full_cpu(base->cpu)) + wake_up_nohz_cpu(base->cpu); } #ifdef CONFIG_TIMER_STATS @@ -948,22 +965,6 @@ void add_timer_on(struct timer_list *timer, int cpu) timer_set_base(timer, base); debug_activate(timer, timer->expires); internal_add_timer(base, timer); - /* - * Check whether the other CPU is in dynticks mode and needs - * to be triggered to reevaluate the timer wheel. - * We are protected against the other CPU fiddling - * with the timer by holding the timer base lock. This also - * makes sure that a CPU on the way to stop its tick can not - * evaluate the timer wheel. - * - * Spare the IPI for deferrable timers on idle targets though. - * The next busy ticks will take care of it. Except full dynticks - * require special care against races with idle_cpu(), lets deal - * with that later. - */ - if (!tbase_get_deferrable(timer->base) || tick_nohz_full_cpu(cpu)) - wake_up_nohz_cpu(cpu); - spin_unlock_irqrestore(&base->lock, flags); } EXPORT_SYMBOL_GPL(add_timer_on); @@ -1568,6 +1569,7 @@ static int init_timers_cpu(int cpu) } spin_lock_init(&base->lock); tvec_base_done[cpu] = 1; + base->cpu = cpu; } else { base = per_cpu(tvec_bases, cpu); } diff --git a/kernel/time/udelay_test.c b/kernel/time/udelay_test.c new file mode 100644 index 000000000000..e622ba365a13 --- /dev/null +++ b/kernel/time/udelay_test.c @@ -0,0 +1,168 @@ +/* + * udelay() test kernel module + * + * Test is executed by writing and reading to /sys/kernel/debug/udelay_test + * Tests are configured by writing: USECS ITERATIONS + * Tests are executed by reading from the same file. + * Specifying usecs of 0 or negative values will run multiples tests. + * + * Copyright (C) 2014 Google, Inc. + * + * 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. + */ + +#include <linux/debugfs.h> +#include <linux/delay.h> +#include <linux/ktime.h> +#include <linux/module.h> +#include <linux/uaccess.h> + +#define DEFAULT_ITERATIONS 100 + +#define DEBUGFS_FILENAME "udelay_test" + +static DEFINE_MUTEX(udelay_test_lock); +static struct dentry *udelay_test_debugfs_file; +static int udelay_test_usecs; +static int udelay_test_iterations = DEFAULT_ITERATIONS; + +static int udelay_test_single(struct seq_file *s, int usecs, uint32_t iters) +{ + int min = 0, max = 0, fail_count = 0; + uint64_t sum = 0; + uint64_t avg; + int i; + /* Allow udelay to be up to 0.5% fast */ + int allowed_error_ns = usecs * 5; + + for (i = 0; i < iters; ++i) { + struct timespec ts1, ts2; + int time_passed; + + ktime_get_ts(&ts1); + udelay(usecs); + ktime_get_ts(&ts2); + time_passed = timespec_to_ns(&ts2) - timespec_to_ns(&ts1); + + if (i == 0 || time_passed < min) + min = time_passed; + if (i == 0 || time_passed > max) + max = time_passed; + if ((time_passed + allowed_error_ns) / 1000 < usecs) + ++fail_count; + WARN_ON(time_passed < 0); + sum += time_passed; + } + + avg = sum; + do_div(avg, iters); + seq_printf(s, "%d usecs x %d: exp=%d allowed=%d min=%d avg=%lld max=%d", + usecs, iters, usecs * 1000, + (usecs * 1000) - allowed_error_ns, min, avg, max); + if (fail_count) + seq_printf(s, " FAIL=%d", fail_count); + seq_puts(s, "\n"); + + return 0; +} + +static int udelay_test_show(struct seq_file *s, void *v) +{ + int usecs; + int iters; + int ret = 0; + + mutex_lock(&udelay_test_lock); + usecs = udelay_test_usecs; + iters = udelay_test_iterations; + mutex_unlock(&udelay_test_lock); + + if (usecs > 0 && iters > 0) { + return udelay_test_single(s, usecs, iters); + } else if (usecs == 0) { + struct timespec ts; + + ktime_get_ts(&ts); + seq_printf(s, "udelay() test (lpj=%ld kt=%ld.%09ld)\n", + loops_per_jiffy, ts.tv_sec, ts.tv_nsec); + seq_puts(s, "usage:\n"); + seq_puts(s, "echo USECS [ITERS] > " DEBUGFS_FILENAME "\n"); + seq_puts(s, "cat " DEBUGFS_FILENAME "\n"); + } + + return ret; +} + +static int udelay_test_open(struct inode *inode, struct file *file) +{ + return single_open(file, udelay_test_show, inode->i_private); +} + +static ssize_t udelay_test_write(struct file *file, const char __user *buf, + size_t count, loff_t *pos) +{ + char lbuf[32]; + int ret; + int usecs; + int iters; + + if (count >= sizeof(lbuf)) + return -EINVAL; + + if (copy_from_user(lbuf, buf, count)) + return -EFAULT; + lbuf[count] = '\0'; + + ret = sscanf(lbuf, "%d %d", &usecs, &iters); + if (ret < 1) + return -EINVAL; + else if (ret < 2) + iters = DEFAULT_ITERATIONS; + + mutex_lock(&udelay_test_lock); + udelay_test_usecs = usecs; + udelay_test_iterations = iters; + mutex_unlock(&udelay_test_lock); + + return count; +} + +static const struct file_operations udelay_test_debugfs_ops = { + .owner = THIS_MODULE, + .open = udelay_test_open, + .read = seq_read, + .write = udelay_test_write, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init udelay_test_init(void) +{ + mutex_lock(&udelay_test_lock); + udelay_test_debugfs_file = debugfs_create_file(DEBUGFS_FILENAME, + S_IRUSR, NULL, NULL, &udelay_test_debugfs_ops); + mutex_unlock(&udelay_test_lock); + + return 0; +} + +module_init(udelay_test_init); + +static void __exit udelay_test_exit(void) +{ + mutex_lock(&udelay_test_lock); + debugfs_remove(udelay_test_debugfs_file); + mutex_unlock(&udelay_test_lock); +} + +module_exit(udelay_test_exit); + +MODULE_AUTHOR("David Riley <davidriley@chromium.org>"); +MODULE_LICENSE("GPL"); diff --git a/kernel/torture.c b/kernel/torture.c index 40bb511cca48..d600af21f022 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -708,7 +708,7 @@ int _torture_create_kthread(int (*fn)(void *arg), void *arg, char *s, char *m, int ret = 0; VERBOSE_TOROUT_STRING(m); - *tp = kthread_run(fn, arg, s); + *tp = kthread_run(fn, arg, "%s", s); if (IS_ERR(*tp)) { ret = PTR_ERR(*tp); VERBOSE_TOROUT_ERRSTRING(f); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 291397e66669..f19f0d81e738 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -820,11 +820,12 @@ static struct { const char *name; int in_ns; /* is this clock in nanoseconds? */ } trace_clocks[] = { - { trace_clock_local, "local", 1 }, - { trace_clock_global, "global", 1 }, - { trace_clock_counter, "counter", 0 }, + { trace_clock_local, "local", 1 }, + { trace_clock_global, "global", 1 }, + { trace_clock_counter, "counter", 0 }, { trace_clock_jiffies, "uptime", 0 }, - { trace_clock, "perf", 1 }, + { trace_clock, "perf", 1 }, + { ktime_get_mono_fast_ns, "mono", 1 }, ARCH_TRACE_CLOCKS }; diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 5d12bb407b44..4b9c114ee9de 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -30,6 +30,18 @@ static int perf_trace_event_perm(struct ftrace_event_call *tp_event, return ret; } + /* + * We checked and allowed to create parent, + * allow children without checking. + */ + if (p_event->parent) + return 0; + + /* + * It's ok to check current process (owner) permissions in here, + * because code below is called only via perf_event_open syscall. + */ + /* The ftrace function trace is allowed only for root. */ if (ftrace_event_is_function(tp_event)) { if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN)) diff --git a/kernel/tsacct.c b/kernel/tsacct.c index a1dd9a1b1327..975cb49e32bf 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -31,20 +31,19 @@ void bacct_add_tsk(struct user_namespace *user_ns, struct taskstats *stats, struct task_struct *tsk) { const struct cred *tcred; - struct timespec uptime, ts; cputime_t utime, stime, utimescaled, stimescaled; - u64 ac_etime; + u64 delta; BUILD_BUG_ON(TS_COMM_LEN < TASK_COMM_LEN); - /* calculate task elapsed time in timespec */ - do_posix_clock_monotonic_gettime(&uptime); - ts = timespec_sub(uptime, tsk->start_time); - /* rebase elapsed time to usec (should never be negative) */ - ac_etime = timespec_to_ns(&ts); - do_div(ac_etime, NSEC_PER_USEC); - stats->ac_etime = ac_etime; - stats->ac_btime = get_seconds() - ts.tv_sec; + /* calculate task elapsed time in nsec */ + delta = ktime_get_ns() - tsk->start_time; + /* Convert to micro seconds */ + do_div(delta, NSEC_PER_USEC); + stats->ac_etime = delta; + /* Convert to seconds for btime */ + do_div(delta, USEC_PER_SEC); + stats->ac_btime = get_seconds() - delta; if (thread_group_leader(tsk)) { stats->ac_exitcode = tsk->exit_code; if (tsk->flags & PF_FORKNOEXEC) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c7b8cfbfcc7e..cd536d403e56 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -859,7 +859,7 @@ config DEBUG_RT_MUTEXES config RT_MUTEX_TESTER bool "Built-in scriptable tester for rt-mutexes" - depends on DEBUG_KERNEL && RT_MUTEXES + depends on DEBUG_KERNEL && RT_MUTEXES && BROKEN help This option enables a rt-mutex tester. @@ -1155,20 +1155,6 @@ config PROVE_RCU_REPEATEDLY Say N if you are unsure. -config PROVE_RCU_DELAY - bool "RCU debugging: preemptible RCU race provocation" - depends on DEBUG_KERNEL && PREEMPT_RCU - default n - help - There is a class of races that involve an unlikely preemption - of __rcu_read_unlock() just after ->rcu_read_lock_nesting has - been set to INT_MIN. This feature inserts a delay at that - point to increase the probability of these races. - - Say Y to increase probability of preemption of __rcu_read_unlock(). - - Say N if you are unsure. - config SPARSE_RCU_POINTER bool "RCU debugging: sparse-based checks for pointer usage" default n @@ -1681,6 +1667,15 @@ config TEST_BPF If unsure, say N. +config TEST_UDELAY + tristate "udelay test driver" + default n + help + This builds the "udelay_test" module that helps to make sure + that udelay() is working properly. + + If unsure, say N. + source "samples/Kconfig" source "lib/Kconfig.kgdb" diff --git a/lib/devres.c b/lib/devres.c index f562bf6ff71d..bb632484a860 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -86,8 +86,6 @@ void devm_iounmap(struct device *dev, void __iomem *addr) } EXPORT_SYMBOL(devm_iounmap); -#define IOMEM_ERR_PTR(err) (__force void __iomem *)ERR_PTR(err) - /** * devm_ioremap_resource() - check, request region, and ioremap resource * @dev: generic device to handle the resource for diff --git a/lib/lockref.c b/lib/lockref.c index f07a40d33871..d2233de9a86e 100644 --- a/lib/lockref.c +++ b/lib/lockref.c @@ -1,6 +1,5 @@ #include <linux/export.h> #include <linux/lockref.h> -#include <linux/mutex.h> #if USE_CMPXCHG_LOCKREF @@ -29,7 +28,7 @@ if (likely(old.lock_count == prev.lock_count)) { \ SUCCESS; \ } \ - arch_mutex_cpu_relax(); \ + cpu_relax_lowlatency(); \ } \ } while (0) diff --git a/mm/filemap.c b/mm/filemap.c index 900edfaf6df5..65d44fd88c78 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -241,18 +241,6 @@ void delete_from_page_cache(struct page *page) } EXPORT_SYMBOL(delete_from_page_cache); -static int sleep_on_page(void *word) -{ - io_schedule(); - return 0; -} - -static int sleep_on_page_killable(void *word) -{ - sleep_on_page(word); - return fatal_signal_pending(current) ? -EINTR : 0; -} - static int filemap_check_errors(struct address_space *mapping) { int ret = 0; @@ -692,7 +680,7 @@ void wait_on_page_bit(struct page *page, int bit_nr) DEFINE_WAIT_BIT(wait, &page->flags, bit_nr); if (test_bit(bit_nr, &page->flags)) - __wait_on_bit(page_waitqueue(page), &wait, sleep_on_page, + __wait_on_bit(page_waitqueue(page), &wait, bit_wait_io, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(wait_on_page_bit); @@ -705,7 +693,7 @@ int wait_on_page_bit_killable(struct page *page, int bit_nr) return 0; return __wait_on_bit(page_waitqueue(page), &wait, - sleep_on_page_killable, TASK_KILLABLE); + bit_wait_io, TASK_KILLABLE); } /** @@ -806,7 +794,7 @@ void __lock_page(struct page *page) { DEFINE_WAIT_BIT(wait, &page->flags, PG_locked); - __wait_on_bit_lock(page_waitqueue(page), &wait, sleep_on_page, + __wait_on_bit_lock(page_waitqueue(page), &wait, bit_wait_io, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__lock_page); @@ -816,7 +804,7 @@ int __lock_page_killable(struct page *page) DEFINE_WAIT_BIT(wait, &page->flags, PG_locked); return __wait_on_bit_lock(page_waitqueue(page), &wait, - sleep_on_page_killable, TASK_KILLABLE); + bit_wait_io, TASK_KILLABLE); } EXPORT_SYMBOL_GPL(__lock_page_killable); @@ -1978,18 +1978,12 @@ void ksm_migrate_page(struct page *newpage, struct page *oldpage) #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_MEMORY_HOTREMOVE -static int just_wait(void *word) -{ - schedule(); - return 0; -} - static void wait_while_offlining(void) { while (ksm_run & KSM_RUN_OFFLINE) { mutex_unlock(&ksm_thread_mutex); wait_on_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE), - just_wait, TASK_UNINTERRUPTIBLE); + TASK_UNINTERRUPTIBLE); mutex_lock(&ksm_thread_mutex); } } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 32b96f1aaf42..c32d361c0cf7 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2235,12 +2235,6 @@ static void hci_inq_req(struct hci_request *req, unsigned long opt) hci_req_add(req, HCI_OP_INQUIRY, sizeof(cp), &cp); } -static int wait_inquiry(void *word) -{ - schedule(); - return signal_pending(current); -} - int hci_inquiry(void __user *arg) { __u8 __user *ptr = arg; @@ -2296,7 +2290,7 @@ int hci_inquiry(void __user *arg) /* Wait until Inquiry procedure finishes (HCI_INQUIRY flag is * cleared). If it is interrupted by a signal, return -EINTR. */ - if (wait_on_bit(&hdev->flags, HCI_INQUIRY, wait_inquiry, + if (wait_on_bit(&hdev->flags, HCI_INQUIRY, TASK_INTERRUPTIBLE)) return -EINTR; } diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index c0365c14b858..9358c79fd589 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -250,7 +250,7 @@ void rpc_destroy_wait_queue(struct rpc_wait_queue *queue) } EXPORT_SYMBOL_GPL(rpc_destroy_wait_queue); -static int rpc_wait_bit_killable(void *word) +static int rpc_wait_bit_killable(struct wait_bit_key *key) { if (fatal_signal_pending(current)) return -ERESTARTSYS; @@ -309,7 +309,7 @@ static int rpc_complete_task(struct rpc_task *task) * to enforce taking of the wq->lock and hence avoid races with * rpc_complete_task(). */ -int __rpc_wait_for_completion_task(struct rpc_task *task, int (*action)(void *)) +int __rpc_wait_for_completion_task(struct rpc_task *task, wait_bit_action_f *action) { if (action == NULL) action = rpc_wait_bit_killable; diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 41987885bd31..d7016279ec2b 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -21,6 +21,7 @@ my $lk_path = "./"; my $email = 1; my $email_usename = 1; my $email_maintainer = 1; +my $email_reviewer = 1; my $email_list = 1; my $email_subscriber_list = 0; my $email_git_penguin_chiefs = 0; @@ -202,6 +203,7 @@ if (!GetOptions( 'remove-duplicates!' => \$email_remove_duplicates, 'mailmap!' => \$email_use_mailmap, 'm!' => \$email_maintainer, + 'r!' => \$email_reviewer, 'n!' => \$email_usename, 'l!' => \$email_list, 's!' => \$email_subscriber_list, @@ -260,7 +262,8 @@ if ($sections) { } if ($email && - ($email_maintainer + $email_list + $email_subscriber_list + + ($email_maintainer + $email_reviewer + + $email_list + $email_subscriber_list + $email_git + $email_git_penguin_chiefs + $email_git_blame) == 0) { die "$P: Please select at least 1 email option\n"; } @@ -750,6 +753,7 @@ MAINTAINER field selection options: --hg-since => hg history to use (default: $email_hg_since) --interactive => display a menu (mostly useful if used with the --git option) --m => include maintainer(s) if any + --r => include reviewer(s) if any --n => include name 'Full Name <addr\@domain.tld>' --l => include list(s) if any --s => include subscriber only list(s) if any @@ -1064,6 +1068,22 @@ sub add_categories { my $role = get_maintainer_role($i); push_email_addresses($pvalue, $role); } + } elsif ($ptype eq "R") { + my ($name, $address) = parse_email($pvalue); + if ($name eq "") { + if ($i > 0) { + my $tv = $typevalue[$i - 1]; + if ($tv =~ m/^(\C):\s*(.*)/) { + if ($1 eq "P") { + $name = $2; + $pvalue = format_email($name, $address, $email_usename); + } + } + } + } + if ($email_reviewer) { + push_email_addresses($pvalue, 'reviewer'); + } } elsif ($ptype eq "T") { push(@scm, $pvalue); } elsif ($ptype eq "W") { diff --git a/security/keys/gc.c b/security/keys/gc.c index d3222b6d7d59..9609a7f0faea 100644 --- a/security/keys/gc.c +++ b/security/keys/gc.c @@ -92,15 +92,6 @@ static void key_gc_timer_func(unsigned long data) } /* - * wait_on_bit() sleep function for uninterruptible waiting - */ -static int key_gc_wait_bit(void *flags) -{ - schedule(); - return 0; -} - -/* * Reap keys of dead type. * * We use three flags to make sure we see three complete cycles of the garbage @@ -123,7 +114,7 @@ void key_gc_keytype(struct key_type *ktype) schedule_work(&key_gc_work); kdebug("sleep"); - wait_on_bit(&key_gc_flags, KEY_GC_REAPING_KEYTYPE, key_gc_wait_bit, + wait_on_bit(&key_gc_flags, KEY_GC_REAPING_KEYTYPE, TASK_UNINTERRUPTIBLE); key_gc_dead_keytype = NULL; diff --git a/security/keys/request_key.c b/security/keys/request_key.c index 381411941cc1..26a94f18af94 100644 --- a/security/keys/request_key.c +++ b/security/keys/request_key.c @@ -21,24 +21,6 @@ #define key_negative_timeout 60 /* default timeout on a negative key's existence */ -/* - * wait_on_bit() sleep function for uninterruptible waiting - */ -static int key_wait_bit(void *flags) -{ - schedule(); - return 0; -} - -/* - * wait_on_bit() sleep function for interruptible waiting - */ -static int key_wait_bit_intr(void *flags) -{ - schedule(); - return signal_pending(current) ? -ERESTARTSYS : 0; -} - /** * complete_request_key - Complete the construction of a key. * @cons: The key construction record. @@ -592,10 +574,9 @@ int wait_for_key_construction(struct key *key, bool intr) int ret; ret = wait_on_bit(&key->flags, KEY_FLAG_USER_CONSTRUCT, - intr ? key_wait_bit_intr : key_wait_bit, intr ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE); - if (ret < 0) - return ret; + if (ret) + return -ERESTARTSYS; if (test_bit(KEY_FLAG_NEGATIVE, &key->flags)) { smp_rmb(); return key->type_data.reject_error; diff --git a/security/tomoyo/audit.c b/security/tomoyo/audit.c index c1b00375c9ad..3ffa4f5509d8 100644 --- a/security/tomoyo/audit.c +++ b/security/tomoyo/audit.c @@ -155,11 +155,9 @@ static char *tomoyo_print_header(struct tomoyo_request_info *r) u8 i; if (!buffer) return NULL; - { - struct timeval tv; - do_gettimeofday(&tv); - tomoyo_convert_time(tv.tv_sec, &stamp); - } + + tomoyo_convert_time(get_seconds(), &stamp); + pos = snprintf(buffer, tomoyo_buffer_len - 1, "#%04u/%02u/%02u %02u:%02u:%02u# profile=%u mode=%s " "granted=%s (global-pid=%u) task={ pid=%u ppid=%u " diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c index 283862aebdc8..e0fb75052550 100644 --- a/security/tomoyo/common.c +++ b/security/tomoyo/common.c @@ -2267,13 +2267,11 @@ static unsigned int tomoyo_stat_modified[TOMOYO_MAX_POLICY_STAT]; */ void tomoyo_update_stat(const u8 index) { - struct timeval tv; - do_gettimeofday(&tv); /* * I don't use atomic operations because race condition is not fatal. */ tomoyo_stat_updated[index]++; - tomoyo_stat_modified[index] = tv.tv_sec; + tomoyo_stat_modified[index] = get_seconds(); } /** diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 93825a17dcce..cf3a44bf1ec3 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -2395,7 +2395,7 @@ process_flags(struct event_format *event, struct print_arg *arg, char **tok) { struct print_arg *field; enum event_type type; - char *token; + char *token = NULL; memset(arg, 0, sizeof(*arg)); arg->type = PRINT_FLAGS; @@ -2448,7 +2448,7 @@ process_symbols(struct event_format *event, struct print_arg *arg, char **tok) { struct print_arg *field; enum event_type type; - char *token; + char *token = NULL; memset(arg, 0, sizeof(*arg)); arg->type = PRINT_SYMBOL; @@ -2487,7 +2487,7 @@ process_hex(struct event_format *event, struct print_arg *arg, char **tok) { struct print_arg *field; enum event_type type; - char *token; + char *token = NULL; memset(arg, 0, sizeof(*arg)); arg->type = PRINT_HEX; diff --git a/tools/lib/traceevent/plugin_cfg80211.c b/tools/lib/traceevent/plugin_cfg80211.c index c066b25905f8..4592d8438318 100644 --- a/tools/lib/traceevent/plugin_cfg80211.c +++ b/tools/lib/traceevent/plugin_cfg80211.c @@ -5,8 +5,7 @@ #include "event-parse.h" static unsigned long long -process___le16_to_cpup(struct trace_seq *s, - unsigned long long *args) +process___le16_to_cpup(struct trace_seq *s, unsigned long long *args) { uint16_t *val = (uint16_t *) (unsigned long) args[0]; return val ? (long long) le16toh(*val) : 0; diff --git a/tools/lib/traceevent/plugin_jbd2.c b/tools/lib/traceevent/plugin_jbd2.c index 0db714c721be..5c23d5bd27ce 100644 --- a/tools/lib/traceevent/plugin_jbd2.c +++ b/tools/lib/traceevent/plugin_jbd2.c @@ -30,8 +30,7 @@ #define MINOR(dev) ((unsigned int) ((dev) & MINORMASK)) static unsigned long long -process_jbd2_dev_to_name(struct trace_seq *s, - unsigned long long *args) +process_jbd2_dev_to_name(struct trace_seq *s, unsigned long long *args) { unsigned int dev = args[0]; @@ -40,8 +39,7 @@ process_jbd2_dev_to_name(struct trace_seq *s, } static unsigned long long -process_jiffies_to_msecs(struct trace_seq *s, - unsigned long long *args) +process_jiffies_to_msecs(struct trace_seq *s, unsigned long long *args) { unsigned long long jiffies = args[0]; diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugin_kvm.c index 9e0e8c61b43b..88fe83dff7cd 100644 --- a/tools/lib/traceevent/plugin_kvm.c +++ b/tools/lib/traceevent/plugin_kvm.c @@ -240,25 +240,38 @@ static const char *find_exit_reason(unsigned isa, int val) for (i = 0; strings[i].val >= 0; i++) if (strings[i].val == val) break; - if (strings[i].str) - return strings[i].str; - return "UNKNOWN"; + + return strings[i].str; } -static int kvm_exit_handler(struct trace_seq *s, struct pevent_record *record, - struct event_format *event, void *context) +static int print_exit_reason(struct trace_seq *s, struct pevent_record *record, + struct event_format *event, const char *field) { unsigned long long isa; unsigned long long val; - unsigned long long info1 = 0, info2 = 0; + const char *reason; - if (pevent_get_field_val(s, event, "exit_reason", record, &val, 1) < 0) + if (pevent_get_field_val(s, event, field, record, &val, 1) < 0) return -1; if (pevent_get_field_val(s, event, "isa", record, &isa, 0) < 0) isa = 1; - trace_seq_printf(s, "reason %s", find_exit_reason(isa, val)); + reason = find_exit_reason(isa, val); + if (reason) + trace_seq_printf(s, "reason %s", reason); + else + trace_seq_printf(s, "reason UNKNOWN (%llu)", val); + return 0; +} + +static int kvm_exit_handler(struct trace_seq *s, struct pevent_record *record, + struct event_format *event, void *context) +{ + unsigned long long info1 = 0, info2 = 0; + + if (print_exit_reason(s, record, event, "exit_reason") < 0) + return -1; pevent_print_num_field(s, " rip 0x%lx", event, "guest_rip", record, 1); @@ -313,6 +326,29 @@ static int kvm_emulate_insn_handler(struct trace_seq *s, return 0; } + +static int kvm_nested_vmexit_inject_handler(struct trace_seq *s, struct pevent_record *record, + struct event_format *event, void *context) +{ + if (print_exit_reason(s, record, event, "exit_code") < 0) + return -1; + + pevent_print_num_field(s, " info1 %llx", event, "exit_info1", record, 1); + pevent_print_num_field(s, " info2 %llx", event, "exit_info2", record, 1); + pevent_print_num_field(s, " int_info %llx", event, "exit_int_info", record, 1); + pevent_print_num_field(s, " int_info_err %llx", event, "exit_int_info_err", record, 1); + + return 0; +} + +static int kvm_nested_vmexit_handler(struct trace_seq *s, struct pevent_record *record, + struct event_format *event, void *context) +{ + pevent_print_num_field(s, "rip %llx ", event, "rip", record, 1); + + return kvm_nested_vmexit_inject_handler(s, record, event, context); +} + union kvm_mmu_page_role { unsigned word; struct { @@ -409,6 +445,12 @@ int PEVENT_PLUGIN_LOADER(struct pevent *pevent) pevent_register_event_handler(pevent, -1, "kvm", "kvm_emulate_insn", kvm_emulate_insn_handler, NULL); + pevent_register_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit", + kvm_nested_vmexit_handler, NULL); + + pevent_register_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit_inject", + kvm_nested_vmexit_inject_handler, NULL); + pevent_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page", kvm_mmu_get_page_handler, NULL); @@ -443,6 +485,12 @@ void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent) pevent_unregister_event_handler(pevent, -1, "kvm", "kvm_emulate_insn", kvm_emulate_insn_handler, NULL); + pevent_unregister_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit", + kvm_nested_vmexit_handler, NULL); + + pevent_unregister_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit_inject", + kvm_nested_vmexit_inject_handler, NULL); + pevent_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page", kvm_mmu_get_page_handler, NULL); diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt index 4464ad770d51..f6480cbf309b 100644 --- a/tools/perf/Documentation/perf-bench.txt +++ b/tools/perf/Documentation/perf-bench.txt @@ -16,6 +16,10 @@ This 'perf bench' command is a general framework for benchmark suites. COMMON OPTIONS -------------- +-r:: +--repeat=:: +Specify amount of times to repeat the run (default 10). + -f:: --format=:: Specify format style. diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt index a00a34276c54..dc7442cf3d7f 100644 --- a/tools/perf/Documentation/perf-inject.txt +++ b/tools/perf/Documentation/perf-inject.txt @@ -41,6 +41,9 @@ OPTIONS tasks slept. sched_switch contains a callchain where a task slept and sched_stat contains a timeslice how long a task slept. +--kallsyms=<file>:: + kallsyms pathname + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1] diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt index 52276a6d2b75..6e689dc89a2f 100644 --- a/tools/perf/Documentation/perf-kvm.txt +++ b/tools/perf/Documentation/perf-kvm.txt @@ -51,9 +51,9 @@ There are a couple of variants of perf kvm: 'perf kvm stat <command>' to run a command and gather performance counter statistics. Especially, perf 'kvm stat record/report' generates a statistical analysis - of KVM events. Currently, vmexit, mmio and ioport events are supported. - 'perf kvm stat record <command>' records kvm events and the events between - start and end <command>. + of KVM events. Currently, vmexit, mmio (x86 only) and ioport (x86 only) + events are supported. 'perf kvm stat record <command>' records kvm events + and the events between start and end <command>. And this command produces a file which contains tracing results of kvm events. @@ -103,8 +103,8 @@ STAT REPORT OPTIONS analyze events which occures on this vcpu. (default: all vcpus) --event=<value>:: - event to be analyzed. Possible values: vmexit, mmio, ioport. - (default: vmexit) + event to be analyzed. Possible values: vmexit, mmio (x86 only), + ioport (x86 only). (default: vmexit) -k:: --key=<value>:: Sorting key. Possible values: sample (default, sort by samples @@ -138,7 +138,8 @@ STAT LIVE OPTIONS --event=<value>:: - event to be analyzed. Possible values: vmexit, mmio, ioport. + event to be analyzed. Possible values: vmexit, + mmio (x86 only), ioport (x86 only). (default: vmexit) -k:: @@ -147,7 +148,8 @@ STAT LIVE OPTIONS number), time (sort by average time). --duration=<value>:: - Show events other than HLT that take longer than duration usecs. + Show events other than HLT (x86 only) or Wait state (s390 only) + that take longer than duration usecs. SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt index 5e0f986dff38..df98d1c82688 100644 --- a/tools/perf/Documentation/perf-timechart.txt +++ b/tools/perf/Documentation/perf-timechart.txt @@ -15,10 +15,20 @@ DESCRIPTION There are two variants of perf timechart: 'perf timechart record <command>' to record the system level events - of an arbitrary workload. + of an arbitrary workload. By default timechart records only scheduler + and CPU events (task switches, running times, CPU power states, etc), + but it's possible to record IO (disk, network) activity using -I argument. 'perf timechart' to turn a trace into a Scalable Vector Graphics file, - that can be viewed with popular SVG viewers such as 'Inkscape'. + that can be viewed with popular SVG viewers such as 'Inkscape'. Depending + on the events in the perf.data file, timechart will contain scheduler/cpu + events or IO events. + + In IO mode, every bar has two charts: upper and lower. + Upper bar shows incoming events (disk reads, ingress network packets). + Lower bar shows outgoing events (disk writes, egress network packets). + There are also poll bars which show how much time application spent + in poll/epoll/select syscalls. TIMECHART OPTIONS ----------------- @@ -54,6 +64,19 @@ TIMECHART OPTIONS duration or tasks with given name. If number is given it's interpreted as number of nanoseconds. If non-numeric string is given it's interpreted as task name. +--io-skip-eagain:: + Don't draw EAGAIN IO events. +--io-min-time=<nsecs>:: + Draw small events as if they lasted min-time. Useful when you need + to see very small and fast IO. It's possible to specify ms or us + suffix to specify time in milliseconds or microseconds. + Default value is 1ms. +--io-merge-dist=<nsecs>:: + Merge events that are merge-dist nanoseconds apart. + Reduces number of figures on the SVG and makes it more render-friendly. + It's possible to specify ms or us suffix to specify time in + milliseconds or microseconds. + Default value is 1us. RECORD OPTIONS -------------- @@ -63,6 +86,9 @@ RECORD OPTIONS -T:: --tasks-only:: Record only tasks-related events +-I:: +--io-only:: + Record only io-related events -g:: --callchain:: Do call-graph (stack chain/backtrace) recording @@ -87,6 +113,14 @@ Record system-wide timechart: $ perf timechart --highlight gcc +Record system-wide IO events: + + $ perf timechart record -I + + then generate timechart: + + $ perf timechart + SEE ALSO -------- linkperf:perf-record[1] diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index fae38d9a44a4..02aac831bdd9 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -107,6 +107,52 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs. Show tool stats such as number of times fd->pathname was discovered thru hooking the open syscall return + vfs_getname or via reading /proc/pid/fd, etc. +-F=[all|min|maj]:: +--pf=[all|min|maj]:: + Trace pagefaults. Optionally, you can specify whether you want minor, + major or all pagefaults. Default value is maj. + +--syscalls:: + Trace system calls. This options is enabled by default. + +PAGEFAULTS +---------- + +When tracing pagefaults, the format of the trace is as follows: + +<min|maj>fault [<ip.symbol>+<ip.offset>] => <addr.dso@addr.offset> (<map type><addr level>). + +- min/maj indicates whether fault event is minor or major; +- ip.symbol shows symbol for instruction pointer (the code that generated the + fault); if no debug symbols available, perf trace will print raw IP; +- addr.dso shows DSO for the faulted address; +- map type is either 'd' for non-executable maps or 'x' for executable maps; +- addr level is either 'k' for kernel dso or '.' for user dso. + +For symbols resolution you may need to install debugging symbols. + +Please be aware that duration is currently always 0 and doesn't reflect actual +time it took for fault to be handled! + +When --verbose specified, perf trace tries to print all available information +for both IP and fault address in the form of dso@symbol+offset. + +EXAMPLES +-------- + +Trace only major pagefaults: + + $ perf trace --no-syscalls -F + +Trace syscalls, major and minor pagefaults: + + $ perf trace -F all + + 1416.547 ( 0.000 ms): python/20235 majfault [CRYPTO_push_info_+0x0] => /lib/x86_64-linux-gnu/libcrypto.so.1.0.0@0x61be0 (x.) + + As you can see, there was major pagefault in python process, from + CRYPTO_push_info_ routine which faulted somewhere in libcrypto.so. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-script[1] diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt index 0eeb247dc7d2..d240bb2e5b22 100644 --- a/tools/perf/Documentation/perf.txt +++ b/tools/perf/Documentation/perf.txt @@ -8,7 +8,15 @@ perf - Performance analysis tools for Linux SYNOPSIS -------- [verse] -'perf' [--version] [--help] COMMAND [ARGS] +'perf' [--version] [--help] [OPTIONS] COMMAND [ARGS] + +OPTIONS +------- +--debug:: + Setup debug variable (just verbose for now) in value + range (0, 10). Use like: + --debug verbose # sets verbose = 1 + --debug verbose=2 # sets verbose = 2 DESCRIPTION ----------- diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 45da209b6ed3..344c4d3d0a4a 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -37,3 +37,6 @@ arch/x86/include/asm/kvm_host.h arch/x86/include/uapi/asm/svm.h arch/x86/include/uapi/asm/vmx.h arch/x86/include/uapi/asm/kvm.h +arch/x86/include/uapi/asm/kvm_perf.h +arch/s390/include/uapi/asm/sie.h +arch/s390/include/uapi/asm/kvm_perf.h diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 9670a16fa577..2240974b7745 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -295,11 +295,13 @@ LIB_H += util/intlist.h LIB_H += util/perf_regs.h LIB_H += util/unwind.h LIB_H += util/vdso.h +LIB_H += util/tsc.h LIB_H += ui/helpline.h LIB_H += ui/progress.h LIB_H += ui/util.h LIB_H += ui/ui.h LIB_H += util/data.h +LIB_H += util/kvm-stat.h LIB_OBJS += $(OUTPUT)util/abspath.o LIB_OBJS += $(OUTPUT)util/alias.o @@ -373,6 +375,8 @@ LIB_OBJS += $(OUTPUT)util/stat.o LIB_OBJS += $(OUTPUT)util/record.o LIB_OBJS += $(OUTPUT)util/srcline.o LIB_OBJS += $(OUTPUT)util/data.o +LIB_OBJS += $(OUTPUT)util/tsc.o +LIB_OBJS += $(OUTPUT)util/cloexec.o LIB_OBJS += $(OUTPUT)ui/setup.o LIB_OBJS += $(OUTPUT)ui/helpline.o diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile index 744e629797be..b92219b1900d 100644 --- a/tools/perf/arch/powerpc/Makefile +++ b/tools/perf/arch/powerpc/Makefile @@ -3,3 +3,4 @@ PERF_HAVE_DWARF_REGS := 1 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o endif LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o +LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/skip-callchain-idx.o diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c index 2f7073d107fd..6c1b8a75db09 100644 --- a/tools/perf/arch/powerpc/util/header.c +++ b/tools/perf/arch/powerpc/util/header.c @@ -5,9 +5,7 @@ #include <string.h> #include "../../util/header.h" - -#define __stringify_1(x) #x -#define __stringify(x) __stringify_1(x) +#include "../../util/util.h" #define mfspr(rn) ({unsigned long rval; \ asm volatile("mfspr %0," __stringify(rn) \ diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c new file mode 100644 index 000000000000..a7c23a4b3778 --- /dev/null +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -0,0 +1,266 @@ +/* + * Use DWARF Debug information to skip unnecessary callchain entries. + * + * Copyright (C) 2014 Sukadev Bhattiprolu, IBM Corporation. + * Copyright (C) 2014 Ulrich Weigand, IBM 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; either version + * 2 of the License, or (at your option) any later version. + */ +#include <inttypes.h> +#include <dwarf.h> +#include <elfutils/libdwfl.h> + +#include "util/thread.h" +#include "util/callchain.h" + +/* + * When saving the callchain on Power, the kernel conservatively saves + * excess entries in the callchain. A few of these entries are needed + * in some cases but not others. If the unnecessary entries are not + * ignored, we end up with duplicate arcs in the call-graphs. Use + * DWARF debug information to skip over any unnecessary callchain + * entries. + * + * See function header for arch_adjust_callchain() below for more details. + * + * The libdwfl code in this file is based on code from elfutils + * (libdwfl/argp-std.c, libdwfl/tests/addrcfi.c, etc). + */ +static char *debuginfo_path; + +static const Dwfl_Callbacks offline_callbacks = { + .debuginfo_path = &debuginfo_path, + .find_debuginfo = dwfl_standard_find_debuginfo, + .section_address = dwfl_offline_section_address, +}; + + +/* + * Use the DWARF expression for the Call-frame-address and determine + * if return address is in LR and if a new frame was allocated. + */ +static int check_return_reg(int ra_regno, Dwarf_Frame *frame) +{ + Dwarf_Op ops_mem[2]; + Dwarf_Op dummy; + Dwarf_Op *ops = &dummy; + size_t nops; + int result; + + result = dwarf_frame_register(frame, ra_regno, ops_mem, &ops, &nops); + if (result < 0) { + pr_debug("dwarf_frame_register() %s\n", dwarf_errmsg(-1)); + return -1; + } + + /* + * Check if return address is on the stack. + */ + if (nops != 0 || ops != NULL) + return 0; + + /* + * Return address is in LR. Check if a frame was allocated + * but not-yet used. + */ + result = dwarf_frame_cfa(frame, &ops, &nops); + if (result < 0) { + pr_debug("dwarf_frame_cfa() returns %d, %s\n", result, + dwarf_errmsg(-1)); + return -1; + } + + /* + * If call frame address is in r1, no new frame was allocated. + */ + if (nops == 1 && ops[0].atom == DW_OP_bregx && ops[0].number == 1 && + ops[0].number2 == 0) + return 1; + + /* + * A new frame was allocated but has not yet been used. + */ + return 2; +} + +/* + * Get the DWARF frame from the .eh_frame section. + */ +static Dwarf_Frame *get_eh_frame(Dwfl_Module *mod, Dwarf_Addr pc) +{ + int result; + Dwarf_Addr bias; + Dwarf_CFI *cfi; + Dwarf_Frame *frame; + + cfi = dwfl_module_eh_cfi(mod, &bias); + if (!cfi) { + pr_debug("%s(): no CFI - %s\n", __func__, dwfl_errmsg(-1)); + return NULL; + } + + result = dwarf_cfi_addrframe(cfi, pc, &frame); + if (result) { + pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1)); + return NULL; + } + + return frame; +} + +/* + * Get the DWARF frame from the .debug_frame section. + */ +static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc) +{ + Dwarf_CFI *cfi; + Dwarf_Addr bias; + Dwarf_Frame *frame; + int result; + + cfi = dwfl_module_dwarf_cfi(mod, &bias); + if (!cfi) { + pr_debug("%s(): no CFI - %s\n", __func__, dwfl_errmsg(-1)); + return NULL; + } + + result = dwarf_cfi_addrframe(cfi, pc, &frame); + if (result) { + pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1)); + return NULL; + } + + return frame; +} + +/* + * Return: + * 0 if return address for the program counter @pc is on stack + * 1 if return address is in LR and no new stack frame was allocated + * 2 if return address is in LR and a new frame was allocated (but not + * yet used) + * -1 in case of errors + */ +static int check_return_addr(const char *exec_file, Dwarf_Addr pc) +{ + int rc = -1; + Dwfl *dwfl; + Dwfl_Module *mod; + Dwarf_Frame *frame; + int ra_regno; + Dwarf_Addr start = pc; + Dwarf_Addr end = pc; + bool signalp; + + dwfl = dwfl_begin(&offline_callbacks); + if (!dwfl) { + pr_debug("dwfl_begin() failed: %s\n", dwarf_errmsg(-1)); + return -1; + } + + if (dwfl_report_offline(dwfl, "", exec_file, -1) == NULL) { + pr_debug("dwfl_report_offline() failed %s\n", dwarf_errmsg(-1)); + goto out; + } + + mod = dwfl_addrmodule(dwfl, pc); + if (!mod) { + pr_debug("dwfl_addrmodule() failed, %s\n", dwarf_errmsg(-1)); + goto out; + } + + /* + * To work with split debug info files (eg: glibc), check both + * .eh_frame and .debug_frame sections of the ELF header. + */ + frame = get_eh_frame(mod, pc); + if (!frame) { + frame = get_dwarf_frame(mod, pc); + if (!frame) + goto out; + } + + ra_regno = dwarf_frame_info(frame, &start, &end, &signalp); + if (ra_regno < 0) { + pr_debug("Return address register unavailable: %s\n", + dwarf_errmsg(-1)); + goto out; + } + + rc = check_return_reg(ra_regno, frame); + +out: + dwfl_end(dwfl); + return rc; +} + +/* + * The callchain saved by the kernel always includes the link register (LR). + * + * 0: PERF_CONTEXT_USER + * 1: Program counter (Next instruction pointer) + * 2: LR value + * 3: Caller's caller + * 4: ... + * + * The value in LR is only needed when it holds a return address. If the + * return address is on the stack, we should ignore the LR value. + * + * Further, when the return address is in the LR, if a new frame was just + * allocated but the LR was not saved into it, then the LR contains the + * caller, slot 4: contains the caller's caller and the contents of slot 3: + * (chain->ips[3]) is undefined and must be ignored. + * + * Use DWARF debug information to determine if any entries need to be skipped. + * + * Return: + * index: of callchain entry that needs to be ignored (if any) + * -1 if no entry needs to be ignored or in case of errors + */ +int arch_skip_callchain_idx(struct machine *machine, struct thread *thread, + struct ip_callchain *chain) +{ + struct addr_location al; + struct dso *dso = NULL; + int rc; + u64 ip; + u64 skip_slot = -1; + + if (chain->nr < 3) + return skip_slot; + + ip = chain->ips[2]; + + thread__find_addr_location(thread, machine, PERF_RECORD_MISC_USER, + MAP__FUNCTION, ip, &al); + + if (al.map) + dso = al.map->dso; + + if (!dso) { + pr_debug("%" PRIx64 " dso is NULL\n", ip); + return skip_slot; + } + + rc = check_return_addr(dso->long_name, ip); + + pr_debug("DSO %s, nr %" PRIx64 ", ip 0x%" PRIx64 "rc %d\n", + dso->long_name, chain->nr, ip, rc); + + if (rc == 0) { + /* + * Return address on stack. Ignore LR value in callchain + */ + skip_slot = 2; + } else if (rc == 2) { + /* + * New frame allocated but return address still in LR. + * Ignore the caller's caller entry in callchain. + */ + skip_slot = 3; + } + return skip_slot; +} diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile index 15130b50dfe3..798ac7379c5f 100644 --- a/tools/perf/arch/s390/Makefile +++ b/tools/perf/arch/s390/Makefile @@ -2,3 +2,6 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o endif +LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o +HAVE_KVM_STAT_SUPPORT := 1 +LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/kvm-stat.o diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c new file mode 100644 index 000000000000..9fa6c3e5782c --- /dev/null +++ b/tools/perf/arch/s390/util/header.c @@ -0,0 +1,28 @@ +/* + * Implementation of get_cpuid(). + * + * Copyright 2014 IBM Corp. + * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.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 only) + * as published by the Free Software Foundation. + */ + +#include <sys/types.h> +#include <unistd.h> +#include <stdio.h> +#include <string.h> + +#include "../../util/header.h" + +int get_cpuid(char *buffer, size_t sz) +{ + const char *cpuid = "IBM/S390"; + + if (strlen(cpuid) + 1 > sz) + return -1; + + strcpy(buffer, cpuid); + return 0; +} diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c new file mode 100644 index 000000000000..a5dbc07ec9dc --- /dev/null +++ b/tools/perf/arch/s390/util/kvm-stat.c @@ -0,0 +1,105 @@ +/* + * Arch specific functions for perf kvm stat. + * + * Copyright 2014 IBM Corp. + * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.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 only) + * as published by the Free Software Foundation. + */ + +#include "../../util/kvm-stat.h" +#include <asm/kvm_perf.h> + +define_exit_reasons_table(sie_exit_reasons, sie_intercept_code); +define_exit_reasons_table(sie_icpt_insn_codes, icpt_insn_codes); +define_exit_reasons_table(sie_sigp_order_codes, sigp_order_codes); +define_exit_reasons_table(sie_diagnose_codes, diagnose_codes); +define_exit_reasons_table(sie_icpt_prog_codes, icpt_prog_codes); + +static void event_icpt_insn_get_key(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + unsigned long insn; + + insn = perf_evsel__intval(evsel, sample, "instruction"); + key->key = icpt_insn_decoder(insn); + key->exit_reasons = sie_icpt_insn_codes; +} + +static void event_sigp_get_key(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->key = perf_evsel__intval(evsel, sample, "order_code"); + key->exit_reasons = sie_sigp_order_codes; +} + +static void event_diag_get_key(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->key = perf_evsel__intval(evsel, sample, "code"); + key->exit_reasons = sie_diagnose_codes; +} + +static void event_icpt_prog_get_key(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->key = perf_evsel__intval(evsel, sample, "code"); + key->exit_reasons = sie_icpt_prog_codes; +} + +static struct child_event_ops child_events[] = { + { .name = "kvm:kvm_s390_intercept_instruction", + .get_key = event_icpt_insn_get_key }, + { .name = "kvm:kvm_s390_handle_sigp", + .get_key = event_sigp_get_key }, + { .name = "kvm:kvm_s390_handle_diag", + .get_key = event_diag_get_key }, + { .name = "kvm:kvm_s390_intercept_prog", + .get_key = event_icpt_prog_get_key }, + { NULL, NULL }, +}; + +static struct kvm_events_ops exit_events = { + .is_begin_event = exit_event_begin, + .is_end_event = exit_event_end, + .child_ops = child_events, + .decode_key = exit_event_decode_key, + .name = "VM-EXIT" +}; + +const char * const kvm_events_tp[] = { + "kvm:kvm_s390_sie_enter", + "kvm:kvm_s390_sie_exit", + "kvm:kvm_s390_intercept_instruction", + "kvm:kvm_s390_handle_sigp", + "kvm:kvm_s390_handle_diag", + "kvm:kvm_s390_intercept_prog", + NULL, +}; + +struct kvm_reg_events_ops kvm_reg_events_ops[] = { + { .name = "vmexit", .ops = &exit_events }, + { NULL, NULL }, +}; + +const char * const kvm_skip_events[] = { + "Wait state", + NULL, +}; + +int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid) +{ + if (strstr(cpuid, "IBM/S390")) { + kvm->exit_reasons = sie_exit_reasons; + kvm->exit_reasons_isa = "SIE"; + } else + return -ENOTSUP; + + return 0; +} diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile index 1641542e3636..9b21881db52f 100644 --- a/tools/perf/arch/x86/Makefile +++ b/tools/perf/arch/x86/Makefile @@ -15,3 +15,5 @@ endif LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/tsc.o LIB_H += arch/$(ARCH)/util/tsc.h +HAVE_KVM_STAT_SUPPORT := 1 +LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/kvm-stat.o diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c index 9f89f899ccc7..d8bbf7ad1681 100644 --- a/tools/perf/arch/x86/tests/dwarf-unwind.c +++ b/tools/perf/arch/x86/tests/dwarf-unwind.c @@ -3,6 +3,7 @@ #include "thread.h" #include "map.h" #include "event.h" +#include "debug.h" #include "tests/tests.h" #define STACK_SIZE 8192 diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c new file mode 100644 index 000000000000..14e4e668fad7 --- /dev/null +++ b/tools/perf/arch/x86/util/kvm-stat.c @@ -0,0 +1,156 @@ +#include "../../util/kvm-stat.h" +#include <asm/kvm_perf.h> + +define_exit_reasons_table(vmx_exit_reasons, VMX_EXIT_REASONS); +define_exit_reasons_table(svm_exit_reasons, SVM_EXIT_REASONS); + +static struct kvm_events_ops exit_events = { + .is_begin_event = exit_event_begin, + .is_end_event = exit_event_end, + .decode_key = exit_event_decode_key, + .name = "VM-EXIT" +}; + +/* + * For the mmio events, we treat: + * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry + * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...). + */ +static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample, + struct event_key *key) +{ + key->key = perf_evsel__intval(evsel, sample, "gpa"); + key->info = perf_evsel__intval(evsel, sample, "type"); +} + +#define KVM_TRACE_MMIO_READ_UNSATISFIED 0 +#define KVM_TRACE_MMIO_READ 1 +#define KVM_TRACE_MMIO_WRITE 2 + +static bool mmio_event_begin(struct perf_evsel *evsel, + struct perf_sample *sample, struct event_key *key) +{ + /* MMIO read begin event in kernel. */ + if (kvm_exit_event(evsel)) + return true; + + /* MMIO write begin event in kernel. */ + if (!strcmp(evsel->name, "kvm:kvm_mmio") && + perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) { + mmio_event_get_key(evsel, sample, key); + return true; + } + + return false; +} + +static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample, + struct event_key *key) +{ + /* MMIO write end event in kernel. */ + if (kvm_entry_event(evsel)) + return true; + + /* MMIO read end event in kernel.*/ + if (!strcmp(evsel->name, "kvm:kvm_mmio") && + perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) { + mmio_event_get_key(evsel, sample, key); + return true; + } + + return false; +} + +static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, + struct event_key *key, + char *decode) +{ + scnprintf(decode, DECODE_STR_LEN, "%#lx:%s", + (unsigned long)key->key, + key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R"); +} + +static struct kvm_events_ops mmio_events = { + .is_begin_event = mmio_event_begin, + .is_end_event = mmio_event_end, + .decode_key = mmio_event_decode_key, + .name = "MMIO Access" +}; + + /* The time of emulation pio access is from kvm_pio to kvm_entry. */ +static void ioport_event_get_key(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->key = perf_evsel__intval(evsel, sample, "port"); + key->info = perf_evsel__intval(evsel, sample, "rw"); +} + +static bool ioport_event_begin(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + if (!strcmp(evsel->name, "kvm:kvm_pio")) { + ioport_event_get_key(evsel, sample, key); + return true; + } + + return false; +} + +static bool ioport_event_end(struct perf_evsel *evsel, + struct perf_sample *sample __maybe_unused, + struct event_key *key __maybe_unused) +{ + return kvm_entry_event(evsel); +} + +static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, + struct event_key *key, + char *decode) +{ + scnprintf(decode, DECODE_STR_LEN, "%#llx:%s", + (unsigned long long)key->key, + key->info ? "POUT" : "PIN"); +} + +static struct kvm_events_ops ioport_events = { + .is_begin_event = ioport_event_begin, + .is_end_event = ioport_event_end, + .decode_key = ioport_event_decode_key, + .name = "IO Port Access" +}; + +const char * const kvm_events_tp[] = { + "kvm:kvm_entry", + "kvm:kvm_exit", + "kvm:kvm_mmio", + "kvm:kvm_pio", + NULL, +}; + +struct kvm_reg_events_ops kvm_reg_events_ops[] = { + { .name = "vmexit", .ops = &exit_events }, + { .name = "mmio", .ops = &mmio_events }, + { .name = "ioport", .ops = &ioport_events }, + { NULL, NULL }, +}; + +const char * const kvm_skip_events[] = { + "HLT", + NULL, +}; + +int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid) +{ + if (strstr(cpuid, "Intel")) { + kvm->exit_reasons = vmx_exit_reasons; + kvm->exit_reasons_isa = "VMX"; + } else if (strstr(cpuid, "AMD")) { + kvm->exit_reasons = svm_exit_reasons; + kvm->exit_reasons_isa = "SVM"; + } else + return -ENOTSUP; + + return 0; +} diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c index 40021fa3129b..fd2868490d00 100644 --- a/tools/perf/arch/x86/util/tsc.c +++ b/tools/perf/arch/x86/util/tsc.c @@ -6,29 +6,9 @@ #include "../../perf.h" #include <linux/types.h> #include "../../util/debug.h" +#include "../../util/tsc.h" #include "tsc.h" -u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc) -{ - u64 t, quot, rem; - - t = ns - tc->time_zero; - quot = t / tc->time_mult; - rem = t % tc->time_mult; - return (quot << tc->time_shift) + - (rem << tc->time_shift) / tc->time_mult; -} - -u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc) -{ - u64 quot, rem; - - quot = cyc >> tc->time_shift; - rem = cyc & ((1 << tc->time_shift) - 1); - return tc->time_zero + quot * tc->time_mult + - ((rem * tc->time_mult) >> tc->time_shift); -} - int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, struct perf_tsc_conversion *tc) { @@ -57,3 +37,12 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, return 0; } + +u64 rdtsc(void) +{ + unsigned int low, high; + + asm volatile("rdtsc" : "=a" (low), "=d" (high)); + + return low | ((u64)high) << 32; +} diff --git a/tools/perf/arch/x86/util/tsc.h b/tools/perf/arch/x86/util/tsc.h index 2affe0366b59..2edc4d31065c 100644 --- a/tools/perf/arch/x86/util/tsc.h +++ b/tools/perf/arch/x86/util/tsc.h @@ -14,7 +14,4 @@ struct perf_event_mmap_page; int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, struct perf_tsc_conversion *tc); -u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc); -u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc); - #endif /* TOOLS_PERF_ARCH_X86_UTIL_TSC_H__ */ diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c index 3261f68c6a7c..db25e93d989c 100644 --- a/tools/perf/arch/x86/util/unwind-libunwind.c +++ b/tools/perf/arch/x86/util/unwind-libunwind.c @@ -3,6 +3,7 @@ #include <libunwind.h> #include "perf_regs.h" #include "../../util/unwind.h" +#include "../../util/debug.h" #ifdef HAVE_ARCH_X86_64_SUPPORT int libunwind__arch_reg_id(int regnum) diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h index eba46709b279..3c4dd44d45cb 100644 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -43,5 +43,6 @@ extern int bench_futex_requeue(int argc, const char **argv, const char *prefix); #define BENCH_FORMAT_UNKNOWN -1 extern int bench_format; +extern unsigned int bench_repeat; #endif diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index a16255876f1d..732403bfd31a 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -29,13 +29,6 @@ static u_int32_t futex1 = 0, futex2 = 0; */ static unsigned int nrequeue = 1; -/* - * There can be significant variance from run to run, - * the more repeats, the more exact the overall avg and - * the better idea of the futex latency. - */ -static unsigned int repeat = 10; - static pthread_t *worker; static bool done = 0, silent = 0; static pthread_mutex_t thread_lock; @@ -46,7 +39,6 @@ static unsigned int ncpus, threads_starting, nthreads = 0; static const struct option options[] = { OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"), OPT_UINTEGER('q', "nrequeue", &nrequeue, "Specify amount of threads to requeue at once"), - OPT_UINTEGER('r', "repeat", &repeat, "Specify amount of times to repeat the run"), OPT_BOOLEAN( 's', "silent", &silent, "Silent mode: do not display data/details"), OPT_END() }; @@ -146,7 +138,7 @@ int bench_futex_requeue(int argc, const char **argv, pthread_cond_init(&thread_parent, NULL); pthread_cond_init(&thread_worker, NULL); - for (j = 0; j < repeat && !done; j++) { + for (j = 0; j < bench_repeat && !done; j++) { unsigned int nrequeued = 0; struct timeval start, end, runtime; diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index d096169b161e..50022cbce87e 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -30,15 +30,8 @@ static u_int32_t futex1 = 0; */ static unsigned int nwakes = 1; -/* - * There can be significant variance from run to run, - * the more repeats, the more exact the overall avg and - * the better idea of the futex latency. - */ -static unsigned int repeat = 10; - pthread_t *worker; -static bool done = 0, silent = 0; +static bool done = false, silent = false; static pthread_mutex_t thread_lock; static pthread_cond_t thread_parent, thread_worker; static struct stats waketime_stats, wakeup_stats; @@ -47,7 +40,6 @@ static unsigned int ncpus, threads_starting, nthreads = 0; static const struct option options[] = { OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"), OPT_UINTEGER('w', "nwakes", &nwakes, "Specify amount of threads to wake at once"), - OPT_UINTEGER('r', "repeat", &repeat, "Specify amount of times to repeat the run"), OPT_BOOLEAN( 's', "silent", &silent, "Silent mode: do not display data/details"), OPT_END() }; @@ -149,7 +141,7 @@ int bench_futex_wake(int argc, const char **argv, pthread_cond_init(&thread_parent, NULL); pthread_cond_init(&thread_worker, NULL); - for (j = 0; j < repeat && !done; j++) { + for (j = 0; j < bench_repeat && !done; j++) { unsigned int nwoken = 0; struct timeval start, end, runtime; diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c index 5ce71d3b72cf..2465141b554b 100644 --- a/tools/perf/bench/mem-memcpy.c +++ b/tools/perf/bench/mem-memcpy.c @@ -10,6 +10,7 @@ #include "../util/util.h" #include "../util/parse-options.h" #include "../util/header.h" +#include "../util/cloexec.h" #include "bench.h" #include "mem-memcpy-arch.h" @@ -83,7 +84,8 @@ static struct perf_event_attr cycle_attr = { static void init_cycle(void) { - cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, 0); + cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, + perf_event_open_cloexec_flag()); if (cycle_fd < 0 && errno == ENOSYS) die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); @@ -189,6 +191,11 @@ int bench_mem_memcpy(int argc, const char **argv, argc = parse_options(argc, argv, options, bench_mem_memcpy_usage, 0); + if (no_prefault && only_prefault) { + fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n"); + return 1; + } + if (use_cycle) init_cycle(); diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c index 9af79d2b18e5..75fc3e65fb2a 100644 --- a/tools/perf/bench/mem-memset.c +++ b/tools/perf/bench/mem-memset.c @@ -10,6 +10,7 @@ #include "../util/util.h" #include "../util/parse-options.h" #include "../util/header.h" +#include "../util/cloexec.h" #include "bench.h" #include "mem-memset-arch.h" @@ -83,7 +84,8 @@ static struct perf_event_attr cycle_attr = { static void init_cycle(void) { - cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, 0); + cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, + perf_event_open_cloexec_flag()); if (cycle_fd < 0 && errno == ENOSYS) die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); @@ -181,6 +183,11 @@ int bench_mem_memset(int argc, const char **argv, argc = parse_options(argc, argv, options, bench_mem_memset_usage, 0); + if (no_prefault && only_prefault) { + fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n"); + return 1; + } + if (use_cycle) init_cycle(); diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c index cc1190a0849b..52a56599a543 100644 --- a/tools/perf/bench/sched-messaging.c +++ b/tools/perf/bench/sched-messaging.c @@ -28,6 +28,7 @@ #include <sys/time.h> #include <sys/poll.h> #include <limits.h> +#include <err.h> #define DATASIZE 100 @@ -50,12 +51,6 @@ struct receiver_context { int wakefd; }; -static void barf(const char *msg) -{ - fprintf(stderr, "%s (error: %s)\n", msg, strerror(errno)); - exit(1); -} - static void fdpair(int fds[2]) { if (use_pipes) { @@ -66,7 +61,7 @@ static void fdpair(int fds[2]) return; } - barf(use_pipes ? "pipe()" : "socketpair()"); + err(EXIT_FAILURE, use_pipes ? "pipe()" : "socketpair()"); } /* Block until we're ready to go */ @@ -77,11 +72,11 @@ static void ready(int ready_out, int wakefd) /* Tell them we're ready. */ if (write(ready_out, &dummy, 1) != 1) - barf("CLIENT: ready write"); + err(EXIT_FAILURE, "CLIENT: ready write"); /* Wait for "GO" signal */ if (poll(&pollfd, 1, -1) != 1) - barf("poll"); + err(EXIT_FAILURE, "poll"); } /* Sender sprays loops messages down each file descriptor */ @@ -101,7 +96,7 @@ again: ret = write(ctx->out_fds[j], data + done, sizeof(data)-done); if (ret < 0) - barf("SENDER: write"); + err(EXIT_FAILURE, "SENDER: write"); done += ret; if (done < DATASIZE) goto again; @@ -131,7 +126,7 @@ static void *receiver(struct receiver_context* ctx) again: ret = read(ctx->in_fds[0], data + done, DATASIZE - done); if (ret < 0) - barf("SERVER: read"); + err(EXIT_FAILURE, "SERVER: read"); done += ret; if (done < DATASIZE) goto again; @@ -144,14 +139,14 @@ static pthread_t create_worker(void *ctx, void *(*func)(void *)) { pthread_attr_t attr; pthread_t childid; - int err; + int ret; if (!thread_mode) { /* process mode */ /* Fork the receiver. */ switch (fork()) { case -1: - barf("fork()"); + err(EXIT_FAILURE, "fork()"); break; case 0: (*func) (ctx); @@ -165,19 +160,17 @@ static pthread_t create_worker(void *ctx, void *(*func)(void *)) } if (pthread_attr_init(&attr) != 0) - barf("pthread_attr_init:"); + err(EXIT_FAILURE, "pthread_attr_init:"); #ifndef __ia64__ if (pthread_attr_setstacksize(&attr, PTHREAD_STACK_MIN) != 0) - barf("pthread_attr_setstacksize"); + err(EXIT_FAILURE, "pthread_attr_setstacksize"); #endif - err = pthread_create(&childid, &attr, func, ctx); - if (err != 0) { - fprintf(stderr, "pthread_create failed: %s (%d)\n", - strerror(err), err); - exit(-1); - } + ret = pthread_create(&childid, &attr, func, ctx); + if (ret != 0) + err(EXIT_FAILURE, "pthread_create failed"); + return childid; } @@ -207,14 +200,14 @@ static unsigned int group(pthread_t *pth, + num_fds * sizeof(int)); if (!snd_ctx) - barf("malloc()"); + err(EXIT_FAILURE, "malloc()"); for (i = 0; i < num_fds; i++) { int fds[2]; struct receiver_context *ctx = malloc(sizeof(*ctx)); if (!ctx) - barf("malloc()"); + err(EXIT_FAILURE, "malloc()"); /* Create the pipe between client and server */ @@ -281,7 +274,7 @@ int bench_sched_messaging(int argc, const char **argv, pth_tab = malloc(num_fds * 2 * num_groups * sizeof(pthread_t)); if (!pth_tab) - barf("main:malloc()"); + err(EXIT_FAILURE, "main:malloc()"); fdpair(readyfds); fdpair(wakefds); @@ -294,13 +287,13 @@ int bench_sched_messaging(int argc, const char **argv, /* Wait for everyone to be ready */ for (i = 0; i < total_children; i++) if (read(readyfds[0], &dummy, 1) != 1) - barf("Reading for readyfds"); + err(EXIT_FAILURE, "Reading for readyfds"); gettimeofday(&start, NULL); /* Kick them off */ if (write(wakefds[1], &dummy, 1) != 1) - barf("Writing to start them"); + err(EXIT_FAILURE, "Writing to start them"); /* Reap them all */ for (i = 0; i < total_children; i++) @@ -332,5 +325,7 @@ int bench_sched_messaging(int argc, const char **argv, break; } + free(pth_tab); + return 0; } diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index 1e6e77710545..b9a56fa83330 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -104,9 +104,11 @@ static const char *bench_format_str; /* Output/formatting style, exported to benchmark modules: */ int bench_format = BENCH_FORMAT_DEFAULT; +unsigned int bench_repeat = 10; /* default number of times to repeat the run */ static const struct option bench_options[] = { OPT_STRING('f', "format", &bench_format_str, "default", "Specify format style"), + OPT_UINTEGER('r', "repeat", &bench_repeat, "Specify amount of times to repeat the run"), OPT_END() }; @@ -226,6 +228,11 @@ int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused) goto end; } + if (bench_repeat == 0) { + printf("Invalid repeat option: Must specify a positive value\n"); + goto end; + } + if (argc < 1) { print_usage(); goto end; diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index b22dbb16f877..2a2c78f80876 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -125,7 +125,8 @@ static int build_id_cache__kcore_existing(const char *from_dir, char *to_dir, return ret; } -static int build_id_cache__add_kcore(const char *filename, const char *debugdir) +static int build_id_cache__add_kcore(const char *filename, const char *debugdir, + bool force) { char dir[32], sbuildid[BUILD_ID_SIZE * 2 + 1]; char from_dir[PATH_MAX], to_dir[PATH_MAX]; @@ -144,7 +145,8 @@ static int build_id_cache__add_kcore(const char *filename, const char *debugdir) scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s", debugdir, sbuildid); - if (!build_id_cache__kcore_existing(from_dir, to_dir, sizeof(to_dir))) { + if (!force && + !build_id_cache__kcore_existing(from_dir, to_dir, sizeof(to_dir))) { pr_debug("same kcore found in %s\n", to_dir); return 0; } @@ -389,7 +391,7 @@ int cmd_buildid_cache(int argc, const char **argv, } if (kcore_filename && - build_id_cache__add_kcore(kcore_filename, debugdir)) + build_id_cache__add_kcore(kcore_filename, debugdir, force)) pr_warning("Couldn't add %s\n", kcore_filename); return ret; diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c index c99e0de7e54a..66e12f55c052 100644 --- a/tools/perf/builtin-evlist.c +++ b/tools/perf/builtin-evlist.c @@ -15,6 +15,7 @@ #include "util/parse-options.h" #include "util/session.h" #include "util/data.h" +#include "util/debug.h" static int __cmd_evlist(const char *file_name, struct perf_attr_details *details) { diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index 178b88ae3d2f..0384d930480b 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -11,6 +11,7 @@ #include "util/parse-options.h" #include "util/run-command.h" #include "util/help.h" +#include "util/debug.h" static struct man_viewer_list { struct man_viewer_list *next; diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 16c7c11ad06e..9a02807387d6 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -389,6 +389,9 @@ static int __cmd_inject(struct perf_inject *inject) ret = perf_session__process_events(session, &inject->tool); if (!file_out->is_pipe) { + if (inject->build_ids) + 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); } @@ -436,6 +439,8 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) "where and how long tasks slept"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show build ids, etc)"), + OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file", + "kallsyms pathname"), OPT_END() }; const char * const inject_usage[] = { diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 0f1e5a2f6ad7..43367eb00510 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -29,114 +29,25 @@ #include <pthread.h> #include <math.h> -#if defined(__i386__) || defined(__x86_64__) -#include <asm/svm.h> -#include <asm/vmx.h> -#include <asm/kvm.h> - -struct event_key { - #define INVALID_KEY (~0ULL) - u64 key; - int info; -}; - -struct kvm_event_stats { - u64 time; - struct stats stats; -}; - -struct kvm_event { - struct list_head hash_entry; - struct rb_node rb; - - struct event_key key; - - struct kvm_event_stats total; - - #define DEFAULT_VCPU_NUM 8 - int max_vcpu; - struct kvm_event_stats *vcpu; -}; - -typedef int (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int); - -struct kvm_event_key { - const char *name; - key_cmp_fun key; -}; - - -struct perf_kvm_stat; - -struct kvm_events_ops { - bool (*is_begin_event)(struct perf_evsel *evsel, - struct perf_sample *sample, - struct event_key *key); - bool (*is_end_event)(struct perf_evsel *evsel, - struct perf_sample *sample, struct event_key *key); - void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key, - char decode[20]); - const char *name; -}; - -struct exit_reasons_table { - unsigned long exit_code; - const char *reason; -}; +#ifdef HAVE_KVM_STAT_SUPPORT +#include <asm/kvm_perf.h> +#include "util/kvm-stat.h" -#define EVENTS_BITS 12 -#define EVENTS_CACHE_SIZE (1UL << EVENTS_BITS) - -struct perf_kvm_stat { - struct perf_tool tool; - struct record_opts opts; - struct perf_evlist *evlist; - struct perf_session *session; - - const char *file_name; - const char *report_event; - const char *sort_key; - int trace_vcpu; - - struct exit_reasons_table *exit_reasons; - int exit_reasons_size; - const char *exit_reasons_isa; - - struct kvm_events_ops *events_ops; - key_cmp_fun compare; - struct list_head kvm_events_cache[EVENTS_CACHE_SIZE]; - - u64 total_time; - u64 total_count; - u64 lost_events; - u64 duration; - - const char *pid_str; - struct intlist *pid_list; - - struct rb_root result; - - int timerfd; - unsigned int display_time; - bool live; -}; - - -static void exit_event_get_key(struct perf_evsel *evsel, - struct perf_sample *sample, - struct event_key *key) +void exit_event_get_key(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key) { key->info = 0; - key->key = perf_evsel__intval(evsel, sample, "exit_reason"); + key->key = perf_evsel__intval(evsel, sample, KVM_EXIT_REASON); } -static bool kvm_exit_event(struct perf_evsel *evsel) +bool kvm_exit_event(struct perf_evsel *evsel) { - return !strcmp(evsel->name, "kvm:kvm_exit"); + return !strcmp(evsel->name, KVM_EXIT_TRACE); } -static bool exit_event_begin(struct perf_evsel *evsel, - struct perf_sample *sample, struct event_key *key) +bool exit_event_begin(struct perf_evsel *evsel, + struct perf_sample *sample, struct event_key *key) { if (kvm_exit_event(evsel)) { exit_event_get_key(evsel, sample, key); @@ -146,32 +57,23 @@ static bool exit_event_begin(struct perf_evsel *evsel, return false; } -static bool kvm_entry_event(struct perf_evsel *evsel) +bool kvm_entry_event(struct perf_evsel *evsel) { - return !strcmp(evsel->name, "kvm:kvm_entry"); + return !strcmp(evsel->name, KVM_ENTRY_TRACE); } -static bool exit_event_end(struct perf_evsel *evsel, - struct perf_sample *sample __maybe_unused, - struct event_key *key __maybe_unused) +bool exit_event_end(struct perf_evsel *evsel, + struct perf_sample *sample __maybe_unused, + struct event_key *key __maybe_unused) { return kvm_entry_event(evsel); } -static struct exit_reasons_table vmx_exit_reasons[] = { - VMX_EXIT_REASONS -}; - -static struct exit_reasons_table svm_exit_reasons[] = { - SVM_EXIT_REASONS -}; - -static const char *get_exit_reason(struct perf_kvm_stat *kvm, u64 exit_code) +static const char *get_exit_reason(struct perf_kvm_stat *kvm, + struct exit_reasons_table *tbl, + u64 exit_code) { - int i = kvm->exit_reasons_size; - struct exit_reasons_table *tbl = kvm->exit_reasons; - - while (i--) { + while (tbl->reason != NULL) { if (tbl->exit_code == exit_code) return tbl->reason; tbl++; @@ -182,148 +84,30 @@ static const char *get_exit_reason(struct perf_kvm_stat *kvm, u64 exit_code) return "UNKNOWN"; } -static void exit_event_decode_key(struct perf_kvm_stat *kvm, - struct event_key *key, - char decode[20]) +void exit_event_decode_key(struct perf_kvm_stat *kvm, + struct event_key *key, + char *decode) { - const char *exit_reason = get_exit_reason(kvm, key->key); + const char *exit_reason = get_exit_reason(kvm, key->exit_reasons, + key->key); - scnprintf(decode, 20, "%s", exit_reason); + scnprintf(decode, DECODE_STR_LEN, "%s", exit_reason); } -static struct kvm_events_ops exit_events = { - .is_begin_event = exit_event_begin, - .is_end_event = exit_event_end, - .decode_key = exit_event_decode_key, - .name = "VM-EXIT" -}; - -/* - * For the mmio events, we treat: - * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry - * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...). - */ -static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample, - struct event_key *key) -{ - key->key = perf_evsel__intval(evsel, sample, "gpa"); - key->info = perf_evsel__intval(evsel, sample, "type"); -} - -#define KVM_TRACE_MMIO_READ_UNSATISFIED 0 -#define KVM_TRACE_MMIO_READ 1 -#define KVM_TRACE_MMIO_WRITE 2 - -static bool mmio_event_begin(struct perf_evsel *evsel, - struct perf_sample *sample, struct event_key *key) -{ - /* MMIO read begin event in kernel. */ - if (kvm_exit_event(evsel)) - return true; - - /* MMIO write begin event in kernel. */ - if (!strcmp(evsel->name, "kvm:kvm_mmio") && - perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) { - mmio_event_get_key(evsel, sample, key); - return true; - } - - return false; -} - -static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample, - struct event_key *key) -{ - /* MMIO write end event in kernel. */ - if (kvm_entry_event(evsel)) - return true; - - /* MMIO read end event in kernel.*/ - if (!strcmp(evsel->name, "kvm:kvm_mmio") && - perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) { - mmio_event_get_key(evsel, sample, key); - return true; - } - - return false; -} - -static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, - struct event_key *key, - char decode[20]) -{ - scnprintf(decode, 20, "%#lx:%s", (unsigned long)key->key, - key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R"); -} - -static struct kvm_events_ops mmio_events = { - .is_begin_event = mmio_event_begin, - .is_end_event = mmio_event_end, - .decode_key = mmio_event_decode_key, - .name = "MMIO Access" -}; - - /* The time of emulation pio access is from kvm_pio to kvm_entry. */ -static void ioport_event_get_key(struct perf_evsel *evsel, - struct perf_sample *sample, - struct event_key *key) +static bool register_kvm_events_ops(struct perf_kvm_stat *kvm) { - key->key = perf_evsel__intval(evsel, sample, "port"); - key->info = perf_evsel__intval(evsel, sample, "rw"); -} + struct kvm_reg_events_ops *events_ops = kvm_reg_events_ops; -static bool ioport_event_begin(struct perf_evsel *evsel, - struct perf_sample *sample, - struct event_key *key) -{ - if (!strcmp(evsel->name, "kvm:kvm_pio")) { - ioport_event_get_key(evsel, sample, key); - return true; + for (events_ops = kvm_reg_events_ops; events_ops->name; events_ops++) { + if (!strcmp(events_ops->name, kvm->report_event)) { + kvm->events_ops = events_ops->ops; + return true; + } } return false; } -static bool ioport_event_end(struct perf_evsel *evsel, - struct perf_sample *sample __maybe_unused, - struct event_key *key __maybe_unused) -{ - return kvm_entry_event(evsel); -} - -static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, - struct event_key *key, - char decode[20]) -{ - scnprintf(decode, 20, "%#llx:%s", (unsigned long long)key->key, - key->info ? "POUT" : "PIN"); -} - -static struct kvm_events_ops ioport_events = { - .is_begin_event = ioport_event_begin, - .is_end_event = ioport_event_end, - .decode_key = ioport_event_decode_key, - .name = "IO Port Access" -}; - -static bool register_kvm_events_ops(struct perf_kvm_stat *kvm) -{ - bool ret = true; - - if (!strcmp(kvm->report_event, "vmexit")) - kvm->events_ops = &exit_events; - else if (!strcmp(kvm->report_event, "mmio")) - kvm->events_ops = &mmio_events; - else if (!strcmp(kvm->report_event, "ioport")) - kvm->events_ops = &ioport_events; - else { - pr_err("Unknown report event:%s\n", kvm->report_event); - ret = false; - } - - return ret; -} - struct vcpu_event_record { int vcpu_id; u64 start_time; @@ -477,6 +261,54 @@ static bool update_kvm_event(struct kvm_event *event, int vcpu_id, return true; } +static bool is_child_event(struct perf_kvm_stat *kvm, + struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + struct child_event_ops *child_ops; + + child_ops = kvm->events_ops->child_ops; + + if (!child_ops) + return false; + + for (; child_ops->name; child_ops++) { + if (!strcmp(evsel->name, child_ops->name)) { + child_ops->get_key(evsel, sample, key); + return true; + } + } + + return false; +} + +static bool handle_child_event(struct perf_kvm_stat *kvm, + struct vcpu_event_record *vcpu_record, + struct event_key *key, + struct perf_sample *sample __maybe_unused) +{ + struct kvm_event *event = NULL; + + if (key->key != INVALID_KEY) + event = find_create_kvm_event(kvm, key); + + vcpu_record->last_event = event; + + return true; +} + +static bool skip_event(const char *event) +{ + const char * const *skip_events; + + for (skip_events = kvm_skip_events; *skip_events; skip_events++) + if (!strcmp(event, *skip_events)) + return true; + + return false; +} + static bool handle_end_event(struct perf_kvm_stat *kvm, struct vcpu_event_record *vcpu_record, struct event_key *key, @@ -525,10 +357,10 @@ static bool handle_end_event(struct perf_kvm_stat *kvm, time_diff = sample->time - time_begin; if (kvm->duration && time_diff > kvm->duration) { - char decode[32]; + char decode[DECODE_STR_LEN]; kvm->events_ops->decode_key(kvm, &event->key, decode); - if (strcmp(decode, "HLT")) { + if (!skip_event(decode)) { pr_info("%" PRIu64 " VM %d, vcpu %d: %s event took %" PRIu64 "usec\n", sample->time, sample->pid, vcpu_record->vcpu_id, decode, time_diff/1000); @@ -553,7 +385,7 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread, return NULL; } - vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, "vcpu_id"); + vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, VCPU_ID); thread->priv = vcpu_record; } @@ -566,7 +398,8 @@ static bool handle_kvm_event(struct perf_kvm_stat *kvm, struct perf_sample *sample) { struct vcpu_event_record *vcpu_record; - struct event_key key = {.key = INVALID_KEY}; + struct event_key key = { .key = INVALID_KEY, + .exit_reasons = kvm->exit_reasons }; vcpu_record = per_vcpu_record(thread, evsel, sample); if (!vcpu_record) @@ -580,6 +413,9 @@ static bool handle_kvm_event(struct perf_kvm_stat *kvm, if (kvm->events_ops->is_begin_event(evsel, sample, &key)) return handle_begin_event(kvm, vcpu_record, &key, sample->time); + if (is_child_event(kvm, evsel, sample, &key)) + return handle_child_event(kvm, vcpu_record, &key, sample); + if (kvm->events_ops->is_end_event(evsel, sample, &key)) return handle_end_event(kvm, vcpu_record, &key, sample); @@ -740,7 +576,7 @@ static void show_timeofday(void) static void print_result(struct perf_kvm_stat *kvm) { - char decode[20]; + char decode[DECODE_STR_LEN]; struct kvm_event *event; int vcpu = kvm->trace_vcpu; @@ -751,7 +587,7 @@ static void print_result(struct perf_kvm_stat *kvm) pr_info("\n\n"); print_vcpu_info(kvm); - pr_info("%20s ", kvm->events_ops->name); + pr_info("%*s ", DECODE_STR_LEN, kvm->events_ops->name); pr_info("%10s ", "Samples"); pr_info("%9s ", "Samples%"); @@ -770,7 +606,7 @@ static void print_result(struct perf_kvm_stat *kvm) min = get_event_min(event, vcpu); kvm->events_ops->decode_key(kvm, &event->key, decode); - pr_info("%20s ", decode); + pr_info("%*s ", DECODE_STR_LEN, decode); pr_info("%10llu ", (unsigned long long)ecount); pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100); pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100); @@ -839,34 +675,28 @@ static int process_sample_event(struct perf_tool *tool, static int cpu_isa_config(struct perf_kvm_stat *kvm) { char buf[64], *cpuid; - int err, isa; + int err; if (kvm->live) { err = get_cpuid(buf, sizeof(buf)); if (err != 0) { - pr_err("Failed to look up CPU type (Intel or AMD)\n"); + pr_err("Failed to look up CPU type\n"); return err; } cpuid = buf; } else cpuid = kvm->session->header.env.cpuid; - if (strstr(cpuid, "Intel")) - isa = 1; - else if (strstr(cpuid, "AMD")) - isa = 0; - else { - pr_err("CPU %s is not supported.\n", cpuid); - return -ENOTSUP; + if (!cpuid) { + pr_err("Failed to look up CPU type\n"); + return -EINVAL; } - if (isa == 1) { - kvm->exit_reasons = vmx_exit_reasons; - kvm->exit_reasons_size = ARRAY_SIZE(vmx_exit_reasons); - kvm->exit_reasons_isa = "VMX"; - } + err = cpu_isa_init(kvm, cpuid); + if (err == -ENOTSUP) + pr_err("CPU %s is not supported.\n", cpuid); - return 0; + return err; } static bool verify_vcpu(int vcpu) @@ -1300,13 +1130,6 @@ exit: return ret; } -static const char * const kvm_events_tp[] = { - "kvm:kvm_entry", - "kvm:kvm_exit", - "kvm:kvm_mmio", - "kvm:kvm_pio", -}; - #define STRDUP_FAIL_EXIT(s) \ ({ char *_p; \ _p = strdup(s); \ @@ -1318,7 +1141,7 @@ static const char * const kvm_events_tp[] = { static int kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv) { - unsigned int rec_argc, i, j; + unsigned int rec_argc, i, j, events_tp_size; const char **rec_argv; const char * const record_args[] = { "record", @@ -1326,9 +1149,14 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv) "-m", "1024", "-c", "1", }; + const char * const *events_tp; + events_tp_size = 0; + + for (events_tp = kvm_events_tp; *events_tp; events_tp++) + events_tp_size++; rec_argc = ARRAY_SIZE(record_args) + argc + 2 + - 2 * ARRAY_SIZE(kvm_events_tp); + 2 * events_tp_size; rec_argv = calloc(rec_argc + 1, sizeof(char *)); if (rec_argv == NULL) @@ -1337,7 +1165,7 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv) for (i = 0; i < ARRAY_SIZE(record_args); i++) rec_argv[i] = STRDUP_FAIL_EXIT(record_args[i]); - for (j = 0; j < ARRAY_SIZE(kvm_events_tp); j++) { + for (j = 0; j < events_tp_size; j++) { rec_argv[i++] = "-e"; rec_argv[i++] = STRDUP_FAIL_EXIT(kvm_events_tp[j]); } @@ -1356,7 +1184,8 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv) { const struct option kvm_events_report_options[] = { OPT_STRING(0, "event", &kvm->report_event, "report event", - "event for reporting: vmexit, mmio, ioport"), + "event for reporting: vmexit, " + "mmio (x86 only), ioport (x86 only)"), OPT_INTEGER(0, "vcpu", &kvm->trace_vcpu, "vcpu id to report"), OPT_STRING('k', "key", &kvm->sort_key, "sort-key", @@ -1391,16 +1220,16 @@ static struct perf_evlist *kvm_live_event_list(void) { struct perf_evlist *evlist; char *tp, *name, *sys; - unsigned int j; int err = -1; + const char * const *events_tp; evlist = perf_evlist__new(); if (evlist == NULL) return NULL; - for (j = 0; j < ARRAY_SIZE(kvm_events_tp); j++) { + for (events_tp = kvm_events_tp; *events_tp; events_tp++) { - tp = strdup(kvm_events_tp[j]); + tp = strdup(*events_tp); if (tp == NULL) goto out; @@ -1409,7 +1238,7 @@ static struct perf_evlist *kvm_live_event_list(void) name = strchr(tp, ':'); if (name == NULL) { pr_err("Error parsing %s tracepoint: subsystem delimiter not found\n", - kvm_events_tp[j]); + *events_tp); free(tp); goto out; } @@ -1417,7 +1246,7 @@ static struct perf_evlist *kvm_live_event_list(void) name++; if (perf_evlist__add_newtp(evlist, sys, name, NULL)) { - pr_err("Failed to add %s tracepoint to the list\n", kvm_events_tp[j]); + pr_err("Failed to add %s tracepoint to the list\n", *events_tp); free(tp); goto out; } @@ -1462,7 +1291,9 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, "key for sorting: sample(sort by samples number)" " time (sort by avg time)"), OPT_U64(0, "duration", &kvm->duration, - "show events other than HALT that take longer than duration usecs"), + "show events other than" + " HLT (x86 only) or Wait state (s390 only)" + " that take longer than duration usecs"), OPT_END() }; const char * const live_usage[] = { @@ -1585,9 +1416,6 @@ static int kvm_cmd_stat(const char *file_name, int argc, const char **argv) .report_event = "vmexit", .sort_key = "sample", - .exit_reasons = svm_exit_reasons, - .exit_reasons_size = ARRAY_SIZE(svm_exit_reasons), - .exit_reasons_isa = "SVM", }; if (argc == 1) { @@ -1609,7 +1437,7 @@ static int kvm_cmd_stat(const char *file_name, int argc, const char **argv) perf_stat: return cmd_stat(argc, argv, NULL); } -#endif +#endif /* HAVE_KVM_STAT_SUPPORT */ static int __cmd_record(const char *file_name, int argc, const char **argv) { @@ -1726,7 +1554,7 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused) return cmd_top(argc, argv, NULL); else if (!strncmp(argv[0], "buildid-list", 12)) return __cmd_buildid_list(file_name, argc, argv); -#if defined(__i386__) || defined(__x86_64__) +#ifdef HAVE_KVM_STAT_SUPPORT else if (!strncmp(argv[0], "stat", 4)) return kvm_cmd_stat(file_name, argc, argv); #endif diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 378b85b731a7..4869050e7194 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -238,6 +238,7 @@ static struct perf_event_header finished_round_event = { static int record__mmap_read_all(struct record *rec) { + u64 bytes_written = rec->bytes_written; int i; int rc = 0; @@ -250,7 +251,11 @@ static int record__mmap_read_all(struct record *rec) } } - if (perf_header__has_feat(&rec->session->header, HEADER_TRACING_DATA)) + /* + * Mark the round finished in case we wrote + * at least one event. + */ + if (bytes_written != rec->bytes_written) rc = record__write(rec, &finished_round_event, sizeof(finished_round_event)); out: diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index c38d06c04775..f83c08c0dd87 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -10,6 +10,7 @@ #include "util/header.h" #include "util/session.h" #include "util/tool.h" +#include "util/cloexec.h" #include "util/parse-options.h" #include "util/trace-event.h" @@ -434,7 +435,8 @@ static int self_open_counters(void) attr.type = PERF_TYPE_SOFTWARE; attr.config = PERF_COUNT_SW_TASK_CLOCK; - fd = sys_perf_event_open(&attr, 0, -1, -1, 0); + fd = sys_perf_event_open(&attr, 0, -1, -1, + perf_event_open_cloexec_flag()); if (fd < 0) pr_err("Error: sys_perf_event_open() syscall returned " @@ -935,8 +937,8 @@ static int latency_switch_event(struct perf_sched *sched, return -1; } - sched_out = machine__findnew_thread(machine, 0, prev_pid); - sched_in = machine__findnew_thread(machine, 0, next_pid); + sched_out = machine__findnew_thread(machine, -1, prev_pid); + sched_in = machine__findnew_thread(machine, -1, next_pid); out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid); if (!out_events) { @@ -979,7 +981,7 @@ static int latency_runtime_event(struct perf_sched *sched, { const u32 pid = perf_evsel__intval(evsel, sample, "pid"); const u64 runtime = perf_evsel__intval(evsel, sample, "runtime"); - struct thread *thread = machine__findnew_thread(machine, 0, pid); + struct thread *thread = machine__findnew_thread(machine, -1, pid); struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid); u64 timestamp = sample->time; int cpu = sample->cpu; @@ -1012,7 +1014,7 @@ static int latency_wakeup_event(struct perf_sched *sched, struct thread *wakee; u64 timestamp = sample->time; - wakee = machine__findnew_thread(machine, 0, pid); + wakee = machine__findnew_thread(machine, -1, pid); atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid); if (!atoms) { if (thread_atoms_insert(sched, wakee)) @@ -1072,7 +1074,7 @@ static int latency_migrate_task_event(struct perf_sched *sched, if (sched->profile_cpu == -1) return 0; - migrant = machine__findnew_thread(machine, 0, pid); + migrant = machine__findnew_thread(machine, -1, pid); atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid); if (!atoms) { if (thread_atoms_insert(sched, migrant)) @@ -1290,7 +1292,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, return -1; } - sched_in = machine__findnew_thread(machine, 0, next_pid); + sched_in = machine__findnew_thread(machine, -1, next_pid); sched->curr_thread[this_cpu] = sched_in; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 9e9c91f5b7fa..f57035b89c15 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -358,27 +358,6 @@ static void print_sample_start(struct perf_sample *sample, } } -static bool is_bts_event(struct perf_event_attr *attr) -{ - return ((attr->type == PERF_TYPE_HARDWARE) && - (attr->config & PERF_COUNT_HW_BRANCH_INSTRUCTIONS) && - (attr->sample_period == 1)); -} - -static bool sample_addr_correlates_sym(struct perf_event_attr *attr) -{ - if ((attr->type == PERF_TYPE_SOFTWARE) && - ((attr->config == PERF_COUNT_SW_PAGE_FAULTS) || - (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MIN) || - (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MAJ))) - return true; - - if (is_bts_event(attr)) - return true; - - return false; -} - static void print_sample_addr(union perf_event *event, struct perf_sample *sample, struct machine *machine, @@ -386,24 +365,13 @@ static void print_sample_addr(union perf_event *event, struct perf_event_attr *attr) { struct addr_location al; - u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; printf("%16" PRIx64, sample->addr); if (!sample_addr_correlates_sym(attr)) return; - thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, - sample->addr, &al); - if (!al.map) - thread__find_addr_map(thread, machine, cpumode, MAP__VARIABLE, - sample->addr, &al); - - al.cpu = sample->cpu; - al.sym = NULL; - - if (al.map) - al.sym = map__find_symbol(al.map, al.addr, NULL); + perf_event__preprocess_sample_addr(event, sample, machine, thread, &al); if (PRINT_FIELD(SYM)) { printf(" "); @@ -427,25 +395,35 @@ static void print_sample_bts(union perf_event *event, struct addr_location *al) { struct perf_event_attr *attr = &evsel->attr; + bool print_srcline_last = false; /* print branch_from information */ if (PRINT_FIELD(IP)) { - if (!symbol_conf.use_callchain) - printf(" "); - else + unsigned int print_opts = output[attr->type].print_ip_opts; + + if (symbol_conf.use_callchain && sample->callchain) { printf("\n"); - perf_evsel__print_ip(evsel, sample, al, - output[attr->type].print_ip_opts, + } else { + printf(" "); + if (print_opts & PRINT_IP_OPT_SRCLINE) { + print_srcline_last = true; + print_opts &= ~PRINT_IP_OPT_SRCLINE; + } + } + perf_evsel__print_ip(evsel, sample, al, print_opts, PERF_MAX_STACK_DEPTH); } - printf(" => "); - /* print branch_to information */ if (PRINT_FIELD(ADDR) || ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) && - !output[attr->type].user_set)) + !output[attr->type].user_set)) { + printf(" => "); print_sample_addr(event, sample, al->machine, thread, attr); + } + + if (print_srcline_last) + map__fprintf_srcline(al->map, al->addr, "\n ", stdout); printf("\n"); } diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 65a151e36067..3e80aa10cfd8 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -184,7 +184,7 @@ static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) { evsel->priv = zalloc(sizeof(struct perf_stat)); - if (evsel == NULL) + if (evsel->priv == NULL) return -ENOMEM; perf_evsel__reset_stat_priv(evsel); return 0; diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index 74db2568b867..2f1a5220c090 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -37,6 +37,7 @@ #include "util/svghelper.h" #include "util/tool.h" #include "util/data.h" +#include "util/debug.h" #define SUPPORT_OLD_POWER_EVENTS 1 #define PWR_EVENT_EXIT -1 @@ -60,10 +61,17 @@ struct timechart { tasks_only, with_backtrace, topology; + /* IO related settings */ + u64 io_events; + bool io_only, + skip_eagain; + u64 min_time, + merge_dist; }; struct per_pidcomm; struct cpu_sample; +struct io_sample; /* * Datastructure layout: @@ -84,6 +92,7 @@ struct per_pid { u64 start_time; u64 end_time; u64 total_time; + u64 total_bytes; int display; struct per_pidcomm *all; @@ -97,6 +106,8 @@ struct per_pidcomm { u64 start_time; u64 end_time; u64 total_time; + u64 max_bytes; + u64 total_bytes; int Y; int display; @@ -107,6 +118,7 @@ struct per_pidcomm { char *comm; struct cpu_sample *samples; + struct io_sample *io_samples; }; struct sample_wrapper { @@ -131,6 +143,27 @@ struct cpu_sample { const char *backtrace; }; +enum { + IOTYPE_READ, + IOTYPE_WRITE, + IOTYPE_SYNC, + IOTYPE_TX, + IOTYPE_RX, + IOTYPE_POLL, +}; + +struct io_sample { + struct io_sample *next; + + u64 start_time; + u64 end_time; + u64 bytes; + int type; + int fd; + int err; + int merges; +}; + #define CSTATE 1 #define PSTATE 2 @@ -213,7 +246,7 @@ static void pid_fork(struct timechart *tchart, int pid, int ppid, u64 timestamp) pid_set_comm(tchart, pid, pp->current->comm); p->start_time = timestamp; - if (p->current) { + if (p->current && !p->current->start_time) { p->current->start_time = timestamp; p->current->state_since = timestamp; } @@ -682,6 +715,249 @@ static void end_sample_processing(struct timechart *tchart) } } +static int pid_begin_io_sample(struct timechart *tchart, int pid, int type, + u64 start, int fd) +{ + struct per_pid *p = find_create_pid(tchart, pid); + struct per_pidcomm *c = p->current; + struct io_sample *sample; + struct io_sample *prev; + + if (!c) { + c = zalloc(sizeof(*c)); + if (!c) + return -ENOMEM; + p->current = c; + c->next = p->all; + p->all = c; + } + + prev = c->io_samples; + + if (prev && prev->start_time && !prev->end_time) { + pr_warning("Skip invalid start event: " + "previous event already started!\n"); + + /* remove previous event that has been started, + * we are not sure we will ever get an end for it */ + c->io_samples = prev->next; + free(prev); + return 0; + } + + sample = zalloc(sizeof(*sample)); + if (!sample) + return -ENOMEM; + sample->start_time = start; + sample->type = type; + sample->fd = fd; + sample->next = c->io_samples; + c->io_samples = sample; + + if (c->start_time == 0 || c->start_time > start) + c->start_time = start; + + return 0; +} + +static int pid_end_io_sample(struct timechart *tchart, int pid, int type, + u64 end, long ret) +{ + struct per_pid *p = find_create_pid(tchart, pid); + struct per_pidcomm *c = p->current; + struct io_sample *sample, *prev; + + if (!c) { + pr_warning("Invalid pidcomm!\n"); + return -1; + } + + sample = c->io_samples; + + if (!sample) /* skip partially captured events */ + return 0; + + if (sample->end_time) { + pr_warning("Skip invalid end event: " + "previous event already ended!\n"); + return 0; + } + + if (sample->type != type) { + pr_warning("Skip invalid end event: invalid event type!\n"); + return 0; + } + + sample->end_time = end; + prev = sample->next; + + /* we want to be able to see small and fast transfers, so make them + * at least min_time long, but don't overlap them */ + if (sample->end_time - sample->start_time < tchart->min_time) + sample->end_time = sample->start_time + tchart->min_time; + if (prev && sample->start_time < prev->end_time) { + if (prev->err) /* try to make errors more visible */ + sample->start_time = prev->end_time; + else + prev->end_time = sample->start_time; + } + + if (ret < 0) { + sample->err = ret; + } else if (type == IOTYPE_READ || type == IOTYPE_WRITE || + type == IOTYPE_TX || type == IOTYPE_RX) { + + if ((u64)ret > c->max_bytes) + c->max_bytes = ret; + + c->total_bytes += ret; + p->total_bytes += ret; + sample->bytes = ret; + } + + /* merge two requests to make svg smaller and render-friendly */ + if (prev && + prev->type == sample->type && + prev->err == sample->err && + prev->fd == sample->fd && + prev->end_time + tchart->merge_dist >= sample->start_time) { + + sample->bytes += prev->bytes; + sample->merges += prev->merges + 1; + + sample->start_time = prev->start_time; + sample->next = prev->next; + free(prev); + + if (!sample->err && sample->bytes > c->max_bytes) + c->max_bytes = sample->bytes; + } + + tchart->io_events++; + + return 0; +} + +static int +process_enter_read(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long fd = perf_evsel__intval(evsel, sample, "fd"); + return pid_begin_io_sample(tchart, sample->tid, IOTYPE_READ, + sample->time, fd); +} + +static int +process_exit_read(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long ret = perf_evsel__intval(evsel, sample, "ret"); + return pid_end_io_sample(tchart, sample->tid, IOTYPE_READ, + sample->time, ret); +} + +static int +process_enter_write(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long fd = perf_evsel__intval(evsel, sample, "fd"); + return pid_begin_io_sample(tchart, sample->tid, IOTYPE_WRITE, + sample->time, fd); +} + +static int +process_exit_write(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long ret = perf_evsel__intval(evsel, sample, "ret"); + return pid_end_io_sample(tchart, sample->tid, IOTYPE_WRITE, + sample->time, ret); +} + +static int +process_enter_sync(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long fd = perf_evsel__intval(evsel, sample, "fd"); + return pid_begin_io_sample(tchart, sample->tid, IOTYPE_SYNC, + sample->time, fd); +} + +static int +process_exit_sync(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long ret = perf_evsel__intval(evsel, sample, "ret"); + return pid_end_io_sample(tchart, sample->tid, IOTYPE_SYNC, + sample->time, ret); +} + +static int +process_enter_tx(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long fd = perf_evsel__intval(evsel, sample, "fd"); + return pid_begin_io_sample(tchart, sample->tid, IOTYPE_TX, + sample->time, fd); +} + +static int +process_exit_tx(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long ret = perf_evsel__intval(evsel, sample, "ret"); + return pid_end_io_sample(tchart, sample->tid, IOTYPE_TX, + sample->time, ret); +} + +static int +process_enter_rx(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long fd = perf_evsel__intval(evsel, sample, "fd"); + return pid_begin_io_sample(tchart, sample->tid, IOTYPE_RX, + sample->time, fd); +} + +static int +process_exit_rx(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long ret = perf_evsel__intval(evsel, sample, "ret"); + return pid_end_io_sample(tchart, sample->tid, IOTYPE_RX, + sample->time, ret); +} + +static int +process_enter_poll(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long fd = perf_evsel__intval(evsel, sample, "fd"); + return pid_begin_io_sample(tchart, sample->tid, IOTYPE_POLL, + sample->time, fd); +} + +static int +process_exit_poll(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long ret = perf_evsel__intval(evsel, sample, "ret"); + return pid_end_io_sample(tchart, sample->tid, IOTYPE_POLL, + sample->time, ret); +} + /* * Sort the pid datastructure */ @@ -852,6 +1128,121 @@ static void draw_cpu_usage(struct timechart *tchart) } } +static void draw_io_bars(struct timechart *tchart) +{ + const char *suf; + double bytes; + char comm[256]; + struct per_pid *p; + struct per_pidcomm *c; + struct io_sample *sample; + int Y = 1; + + p = tchart->all_data; + while (p) { + c = p->all; + while (c) { + if (!c->display) { + c->Y = 0; + c = c->next; + continue; + } + + svg_box(Y, c->start_time, c->end_time, "process3"); + sample = c->io_samples; + for (sample = c->io_samples; sample; sample = sample->next) { + double h = (double)sample->bytes / c->max_bytes; + + if (tchart->skip_eagain && + sample->err == -EAGAIN) + continue; + + if (sample->err) + h = 1; + + if (sample->type == IOTYPE_SYNC) + svg_fbox(Y, + sample->start_time, + sample->end_time, + 1, + sample->err ? "error" : "sync", + sample->fd, + sample->err, + sample->merges); + else if (sample->type == IOTYPE_POLL) + svg_fbox(Y, + sample->start_time, + sample->end_time, + 1, + sample->err ? "error" : "poll", + sample->fd, + sample->err, + sample->merges); + else if (sample->type == IOTYPE_READ) + svg_ubox(Y, + sample->start_time, + sample->end_time, + h, + sample->err ? "error" : "disk", + sample->fd, + sample->err, + sample->merges); + else if (sample->type == IOTYPE_WRITE) + svg_lbox(Y, + sample->start_time, + sample->end_time, + h, + sample->err ? "error" : "disk", + sample->fd, + sample->err, + sample->merges); + else if (sample->type == IOTYPE_RX) + svg_ubox(Y, + sample->start_time, + sample->end_time, + h, + sample->err ? "error" : "net", + sample->fd, + sample->err, + sample->merges); + else if (sample->type == IOTYPE_TX) + svg_lbox(Y, + sample->start_time, + sample->end_time, + h, + sample->err ? "error" : "net", + sample->fd, + sample->err, + sample->merges); + } + + suf = ""; + bytes = c->total_bytes; + if (bytes > 1024) { + bytes = bytes / 1024; + suf = "K"; + } + if (bytes > 1024) { + bytes = bytes / 1024; + suf = "M"; + } + if (bytes > 1024) { + bytes = bytes / 1024; + suf = "G"; + } + + + sprintf(comm, "%s:%i (%3.1f %sbytes)", c->comm ?: "", p->pid, bytes, suf); + svg_text(Y, c->start_time, comm); + + c->Y = Y; + Y++; + c = c->next; + } + p = p->next; + } +} + static void draw_process_bars(struct timechart *tchart) { struct per_pid *p; @@ -987,9 +1378,6 @@ static int determine_display_tasks(struct timechart *tchart, u64 threshold) struct per_pidcomm *c; int count = 0; - if (process_filter) - return determine_display_tasks_filtered(tchart); - p = tchart->all_data; while (p) { p->display = 0; @@ -1025,15 +1413,46 @@ static int determine_display_tasks(struct timechart *tchart, u64 threshold) return count; } +static int determine_display_io_tasks(struct timechart *timechart, u64 threshold) +{ + struct per_pid *p; + struct per_pidcomm *c; + int count = 0; + + p = timechart->all_data; + while (p) { + /* no exit marker, task kept running to the end */ + if (p->end_time == 0) + p->end_time = timechart->last_time; + c = p->all; + while (c) { + c->display = 0; + + if (c->total_bytes >= threshold) { + c->display = 1; + count++; + } + + if (c->end_time == 0) + c->end_time = timechart->last_time; + + c = c->next; + } + p = p->next; + } + return count; +} + +#define BYTES_THRESH (1 * 1024 * 1024) #define TIME_THRESH 10000000 static void write_svg_file(struct timechart *tchart, const char *filename) { u64 i; int count; - int thresh = TIME_THRESH; + int thresh = tchart->io_events ? BYTES_THRESH : TIME_THRESH; if (tchart->power_only) tchart->proc_num = 0; @@ -1041,28 +1460,43 @@ static void write_svg_file(struct timechart *tchart, const char *filename) /* We'd like to show at least proc_num tasks; * be less picky if we have fewer */ do { - count = determine_display_tasks(tchart, thresh); + if (process_filter) + count = determine_display_tasks_filtered(tchart); + else if (tchart->io_events) + count = determine_display_io_tasks(tchart, thresh); + else + count = determine_display_tasks(tchart, thresh); thresh /= 10; } while (!process_filter && thresh && count < tchart->proc_num); if (!tchart->proc_num) count = 0; - open_svg(filename, tchart->numcpus, count, tchart->first_time, tchart->last_time); + if (tchart->io_events) { + open_svg(filename, 0, count, tchart->first_time, tchart->last_time); - svg_time_grid(); - svg_legenda(); + svg_time_grid(0.5); + svg_io_legenda(); + + draw_io_bars(tchart); + } else { + open_svg(filename, tchart->numcpus, count, tchart->first_time, tchart->last_time); - for (i = 0; i < tchart->numcpus; i++) - svg_cpu_box(i, tchart->max_freq, tchart->turbo_frequency); + svg_time_grid(0); - draw_cpu_usage(tchart); - if (tchart->proc_num) - draw_process_bars(tchart); - if (!tchart->tasks_only) - draw_c_p_states(tchart); - if (tchart->proc_num) - draw_wakeups(tchart); + svg_legenda(); + + for (i = 0; i < tchart->numcpus; i++) + svg_cpu_box(i, tchart->max_freq, tchart->turbo_frequency); + + draw_cpu_usage(tchart); + if (tchart->proc_num) + draw_process_bars(tchart); + if (!tchart->tasks_only) + draw_c_p_states(tchart); + if (tchart->proc_num) + draw_wakeups(tchart); + } svg_close(); } @@ -1110,6 +1544,56 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name) { "power:power_end", process_sample_power_end }, { "power:power_frequency", process_sample_power_frequency }, #endif + + { "syscalls:sys_enter_read", process_enter_read }, + { "syscalls:sys_enter_pread64", process_enter_read }, + { "syscalls:sys_enter_readv", process_enter_read }, + { "syscalls:sys_enter_preadv", process_enter_read }, + { "syscalls:sys_enter_write", process_enter_write }, + { "syscalls:sys_enter_pwrite64", process_enter_write }, + { "syscalls:sys_enter_writev", process_enter_write }, + { "syscalls:sys_enter_pwritev", process_enter_write }, + { "syscalls:sys_enter_sync", process_enter_sync }, + { "syscalls:sys_enter_sync_file_range", process_enter_sync }, + { "syscalls:sys_enter_fsync", process_enter_sync }, + { "syscalls:sys_enter_msync", process_enter_sync }, + { "syscalls:sys_enter_recvfrom", process_enter_rx }, + { "syscalls:sys_enter_recvmmsg", process_enter_rx }, + { "syscalls:sys_enter_recvmsg", process_enter_rx }, + { "syscalls:sys_enter_sendto", process_enter_tx }, + { "syscalls:sys_enter_sendmsg", process_enter_tx }, + { "syscalls:sys_enter_sendmmsg", process_enter_tx }, + { "syscalls:sys_enter_epoll_pwait", process_enter_poll }, + { "syscalls:sys_enter_epoll_wait", process_enter_poll }, + { "syscalls:sys_enter_poll", process_enter_poll }, + { "syscalls:sys_enter_ppoll", process_enter_poll }, + { "syscalls:sys_enter_pselect6", process_enter_poll }, + { "syscalls:sys_enter_select", process_enter_poll }, + + { "syscalls:sys_exit_read", process_exit_read }, + { "syscalls:sys_exit_pread64", process_exit_read }, + { "syscalls:sys_exit_readv", process_exit_read }, + { "syscalls:sys_exit_preadv", process_exit_read }, + { "syscalls:sys_exit_write", process_exit_write }, + { "syscalls:sys_exit_pwrite64", process_exit_write }, + { "syscalls:sys_exit_writev", process_exit_write }, + { "syscalls:sys_exit_pwritev", process_exit_write }, + { "syscalls:sys_exit_sync", process_exit_sync }, + { "syscalls:sys_exit_sync_file_range", process_exit_sync }, + { "syscalls:sys_exit_fsync", process_exit_sync }, + { "syscalls:sys_exit_msync", process_exit_sync }, + { "syscalls:sys_exit_recvfrom", process_exit_rx }, + { "syscalls:sys_exit_recvmmsg", process_exit_rx }, + { "syscalls:sys_exit_recvmsg", process_exit_rx }, + { "syscalls:sys_exit_sendto", process_exit_tx }, + { "syscalls:sys_exit_sendmsg", process_exit_tx }, + { "syscalls:sys_exit_sendmmsg", process_exit_tx }, + { "syscalls:sys_exit_epoll_pwait", process_exit_poll }, + { "syscalls:sys_exit_epoll_wait", process_exit_poll }, + { "syscalls:sys_exit_poll", process_exit_poll }, + { "syscalls:sys_exit_ppoll", process_exit_poll }, + { "syscalls:sys_exit_pselect6", process_exit_poll }, + { "syscalls:sys_exit_select", process_exit_poll }, }; struct perf_data_file file = { .path = input_name, @@ -1154,6 +1638,139 @@ out_delete: return ret; } +static int timechart__io_record(int argc, const char **argv) +{ + unsigned int rec_argc, i; + const char **rec_argv; + const char **p; + char *filter = NULL; + + const char * const common_args[] = { + "record", "-a", "-R", "-c", "1", + }; + unsigned int common_args_nr = ARRAY_SIZE(common_args); + + const char * const disk_events[] = { + "syscalls:sys_enter_read", + "syscalls:sys_enter_pread64", + "syscalls:sys_enter_readv", + "syscalls:sys_enter_preadv", + "syscalls:sys_enter_write", + "syscalls:sys_enter_pwrite64", + "syscalls:sys_enter_writev", + "syscalls:sys_enter_pwritev", + "syscalls:sys_enter_sync", + "syscalls:sys_enter_sync_file_range", + "syscalls:sys_enter_fsync", + "syscalls:sys_enter_msync", + + "syscalls:sys_exit_read", + "syscalls:sys_exit_pread64", + "syscalls:sys_exit_readv", + "syscalls:sys_exit_preadv", + "syscalls:sys_exit_write", + "syscalls:sys_exit_pwrite64", + "syscalls:sys_exit_writev", + "syscalls:sys_exit_pwritev", + "syscalls:sys_exit_sync", + "syscalls:sys_exit_sync_file_range", + "syscalls:sys_exit_fsync", + "syscalls:sys_exit_msync", + }; + unsigned int disk_events_nr = ARRAY_SIZE(disk_events); + + const char * const net_events[] = { + "syscalls:sys_enter_recvfrom", + "syscalls:sys_enter_recvmmsg", + "syscalls:sys_enter_recvmsg", + "syscalls:sys_enter_sendto", + "syscalls:sys_enter_sendmsg", + "syscalls:sys_enter_sendmmsg", + + "syscalls:sys_exit_recvfrom", + "syscalls:sys_exit_recvmmsg", + "syscalls:sys_exit_recvmsg", + "syscalls:sys_exit_sendto", + "syscalls:sys_exit_sendmsg", + "syscalls:sys_exit_sendmmsg", + }; + unsigned int net_events_nr = ARRAY_SIZE(net_events); + + const char * const poll_events[] = { + "syscalls:sys_enter_epoll_pwait", + "syscalls:sys_enter_epoll_wait", + "syscalls:sys_enter_poll", + "syscalls:sys_enter_ppoll", + "syscalls:sys_enter_pselect6", + "syscalls:sys_enter_select", + + "syscalls:sys_exit_epoll_pwait", + "syscalls:sys_exit_epoll_wait", + "syscalls:sys_exit_poll", + "syscalls:sys_exit_ppoll", + "syscalls:sys_exit_pselect6", + "syscalls:sys_exit_select", + }; + unsigned int poll_events_nr = ARRAY_SIZE(poll_events); + + rec_argc = common_args_nr + + disk_events_nr * 4 + + net_events_nr * 4 + + poll_events_nr * 4 + + argc; + rec_argv = calloc(rec_argc + 1, sizeof(char *)); + + if (rec_argv == NULL) + return -ENOMEM; + + if (asprintf(&filter, "common_pid != %d", getpid()) < 0) + return -ENOMEM; + + p = rec_argv; + for (i = 0; i < common_args_nr; i++) + *p++ = strdup(common_args[i]); + + for (i = 0; i < disk_events_nr; i++) { + if (!is_valid_tracepoint(disk_events[i])) { + rec_argc -= 4; + continue; + } + + *p++ = "-e"; + *p++ = strdup(disk_events[i]); + *p++ = "--filter"; + *p++ = filter; + } + for (i = 0; i < net_events_nr; i++) { + if (!is_valid_tracepoint(net_events[i])) { + rec_argc -= 4; + continue; + } + + *p++ = "-e"; + *p++ = strdup(net_events[i]); + *p++ = "--filter"; + *p++ = filter; + } + for (i = 0; i < poll_events_nr; i++) { + if (!is_valid_tracepoint(poll_events[i])) { + rec_argc -= 4; + continue; + } + + *p++ = "-e"; + *p++ = strdup(poll_events[i]); + *p++ = "--filter"; + *p++ = filter; + } + + for (i = 0; i < (unsigned int)argc; i++) + *p++ = argv[i]; + + return cmd_record(rec_argc, rec_argv, NULL); +} + + static int timechart__record(struct timechart *tchart, int argc, const char **argv) { unsigned int rec_argc, i, j; @@ -1270,6 +1887,30 @@ parse_highlight(const struct option *opt __maybe_unused, const char *arg, return 0; } +static int +parse_time(const struct option *opt, const char *arg, int __maybe_unused unset) +{ + char unit = 'n'; + u64 *value = opt->value; + + if (sscanf(arg, "%" PRIu64 "%cs", value, &unit) > 0) { + switch (unit) { + case 'm': + *value *= 1000000; + break; + case 'u': + *value *= 1000; + break; + case 'n': + break; + default: + return -1; + } + } + + return 0; +} + int cmd_timechart(int argc, const char **argv, const char *prefix __maybe_unused) { @@ -1282,6 +1923,8 @@ int cmd_timechart(int argc, const char **argv, .ordered_samples = true, }, .proc_num = 15, + .min_time = 1000000, + .merge_dist = 1000, }; const char *output_name = "output.svg"; const struct option timechart_options[] = { @@ -1303,6 +1946,14 @@ int cmd_timechart(int argc, const char **argv, "min. number of tasks to print"), OPT_BOOLEAN('t', "topology", &tchart.topology, "sort CPUs according to topology"), + OPT_BOOLEAN(0, "io-skip-eagain", &tchart.skip_eagain, + "skip EAGAIN errors"), + OPT_CALLBACK(0, "io-min-time", &tchart.min_time, "time", + "all IO faster than min-time will visually appear longer", + parse_time), + OPT_CALLBACK(0, "io-merge-dist", &tchart.merge_dist, "time", + "merge events that are merge-dist us apart", + parse_time), OPT_END() }; const char * const timechart_usage[] = { @@ -1314,6 +1965,8 @@ int cmd_timechart(int argc, const char **argv, OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"), OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only, "output processes data only"), + OPT_BOOLEAN('I', "io-only", &tchart.io_only, + "record only IO data"), OPT_BOOLEAN('g', "callchain", &tchart.with_backtrace, "record callchain"), OPT_END() }; @@ -1340,7 +1993,10 @@ int cmd_timechart(int argc, const char **argv, return -1; } - return timechart__record(&tchart, argc, argv); + if (tchart.io_only) + return timechart__io_record(argc, argv); + else + return timechart__record(&tchart, argc, argv); } else if (argc) usage_with_options(timechart_usage, timechart_options); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index f954c26de231..a6c375224f46 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1108,6 +1108,7 @@ struct syscall { struct event_format *tp_format; const char *name; bool filtered; + bool is_exit; struct syscall_fmt *fmt; size_t (**arg_scnprintf)(char *bf, size_t size, struct syscall_arg *arg); void **arg_parm; @@ -1132,6 +1133,7 @@ struct thread_trace { u64 exit_time; bool entry_pending; unsigned long nr_events; + unsigned long pfmaj, pfmin; char *entry_str; double runtime_ms; struct { @@ -1177,6 +1179,9 @@ fail: return NULL; } +#define TRACE_PFMAJ (1 << 0) +#define TRACE_PFMIN (1 << 1) + struct trace { struct perf_tool tool; struct { @@ -1211,6 +1216,8 @@ struct trace { bool summary_only; bool show_comm; bool show_tool_stats; + bool trace_syscalls; + int trace_pgfaults; }; static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname) @@ -1276,11 +1283,11 @@ static const char *thread__fd_path(struct thread *thread, int fd, if (fd < 0) return NULL; - if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL)) + if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL)) { if (!trace->live) return NULL; ++trace->stats.proc_getname; - if (thread__read_fd_path(thread, fd)) { + if (thread__read_fd_path(thread, fd)) return NULL; } @@ -1473,6 +1480,8 @@ static int trace__read_syscall_info(struct trace *trace, int id) if (sc->tp_format == NULL) return -1; + sc->is_exit = !strcmp(name, "exit_group") || !strcmp(name, "exit"); + return syscall__set_arg_fmts(sc); } @@ -1535,6 +1544,7 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, } typedef int (*tracepoint_handler)(struct trace *trace, struct perf_evsel *evsel, + union perf_event *event, struct perf_sample *sample); static struct syscall *trace__syscall_info(struct trace *trace, @@ -1607,6 +1617,7 @@ static void thread__update_stats(struct thread_trace *ttrace, } static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, + union perf_event *event __maybe_unused, struct perf_sample *sample) { char *msg; @@ -1629,7 +1640,6 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, return -1; args = perf_evsel__sc_tp_ptr(evsel, args, sample); - ttrace = thread->priv; if (ttrace->entry_str == NULL) { ttrace->entry_str = malloc(1024); @@ -1644,7 +1654,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, printed += syscall__scnprintf_args(sc, msg + printed, 1024 - printed, args, trace, thread); - if (!strcmp(sc->name, "exit_group") || !strcmp(sc->name, "exit")) { + if (sc->is_exit) { if (!trace->duration_filter && !trace->summary_only) { trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output); fprintf(trace->output, "%-70s\n", ttrace->entry_str); @@ -1656,6 +1666,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, } static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, + union perf_event *event __maybe_unused, struct perf_sample *sample) { int ret; @@ -1687,8 +1698,6 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, ++trace->stats.vfs_getname; } - ttrace = thread->priv; - ttrace->exit_time = sample->time; if (ttrace->entry_time) { @@ -1735,6 +1744,7 @@ out: } static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel, + union perf_event *event __maybe_unused, struct perf_sample *sample) { trace->last_vfs_getname = perf_evsel__rawptr(evsel, sample, "pathname"); @@ -1742,6 +1752,7 @@ static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel, } static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evsel, + union perf_event *event __maybe_unused, struct perf_sample *sample) { u64 runtime = perf_evsel__intval(evsel, sample, "runtime"); @@ -1768,6 +1779,80 @@ out_dump: return 0; } +static void print_location(FILE *f, struct perf_sample *sample, + struct addr_location *al, + bool print_dso, bool print_sym) +{ + + if ((verbose || print_dso) && al->map) + fprintf(f, "%s@", al->map->dso->long_name); + + if ((verbose || print_sym) && al->sym) + fprintf(f, "%s+0x%" PRIx64, al->sym->name, + al->addr - al->sym->start); + else if (al->map) + fprintf(f, "0x%" PRIx64, al->addr); + else + fprintf(f, "0x%" PRIx64, sample->addr); +} + +static int trace__pgfault(struct trace *trace, + struct perf_evsel *evsel, + union perf_event *event, + struct perf_sample *sample) +{ + struct thread *thread; + u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + struct addr_location al; + char map_type = 'd'; + struct thread_trace *ttrace; + + thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); + ttrace = thread__trace(thread, trace->output); + if (ttrace == NULL) + return -1; + + if (evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ) + ttrace->pfmaj++; + else + ttrace->pfmin++; + + if (trace->summary_only) + return 0; + + thread__find_addr_location(thread, trace->host, cpumode, MAP__FUNCTION, + sample->ip, &al); + + trace__fprintf_entry_head(trace, thread, 0, sample->time, trace->output); + + fprintf(trace->output, "%sfault [", + evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ? + "maj" : "min"); + + print_location(trace->output, sample, &al, false, true); + + fprintf(trace->output, "] => "); + + thread__find_addr_location(thread, trace->host, cpumode, MAP__VARIABLE, + sample->addr, &al); + + if (!al.map) { + thread__find_addr_location(thread, trace->host, cpumode, + MAP__FUNCTION, sample->addr, &al); + + if (al.map) + map_type = 'x'; + else + map_type = '?'; + } + + print_location(trace->output, sample, &al, true, false); + + fprintf(trace->output, " (%c%c)\n", map_type, al.level); + + return 0; +} + static bool skip_sample(struct trace *trace, struct perf_sample *sample) { if ((trace->pid_list && intlist__find(trace->pid_list, sample->pid)) || @@ -1781,7 +1866,7 @@ static bool skip_sample(struct trace *trace, struct perf_sample *sample) } static int trace__process_sample(struct perf_tool *tool, - union perf_event *event __maybe_unused, + union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine __maybe_unused) @@ -1799,7 +1884,7 @@ static int trace__process_sample(struct perf_tool *tool, if (handler) { ++trace->nr_events; - handler(trace, evsel, sample); + handler(trace, evsel, event, sample); } return err; @@ -1826,7 +1911,7 @@ static int parse_target_str(struct trace *trace) return 0; } -static int trace__record(int argc, const char **argv) +static int trace__record(struct trace *trace, int argc, const char **argv) { unsigned int rec_argc, i, j; const char **rec_argv; @@ -1835,34 +1920,54 @@ static int trace__record(int argc, const char **argv) "-R", "-m", "1024", "-c", "1", - "-e", }; + const char * const sc_args[] = { "-e", }; + unsigned int sc_args_nr = ARRAY_SIZE(sc_args); + const char * const majpf_args[] = { "-e", "major-faults" }; + unsigned int majpf_args_nr = ARRAY_SIZE(majpf_args); + const char * const minpf_args[] = { "-e", "minor-faults" }; + unsigned int minpf_args_nr = ARRAY_SIZE(minpf_args); + /* +1 is for the event string below */ - rec_argc = ARRAY_SIZE(record_args) + 1 + argc; + rec_argc = ARRAY_SIZE(record_args) + sc_args_nr + 1 + + majpf_args_nr + minpf_args_nr + argc; rec_argv = calloc(rec_argc + 1, sizeof(char *)); if (rec_argv == NULL) return -ENOMEM; + j = 0; for (i = 0; i < ARRAY_SIZE(record_args); i++) - rec_argv[i] = record_args[i]; - - /* event string may be different for older kernels - e.g., RHEL6 */ - if (is_valid_tracepoint("raw_syscalls:sys_enter")) - rec_argv[i] = "raw_syscalls:sys_enter,raw_syscalls:sys_exit"; - else if (is_valid_tracepoint("syscalls:sys_enter")) - rec_argv[i] = "syscalls:sys_enter,syscalls:sys_exit"; - else { - pr_err("Neither raw_syscalls nor syscalls events exist.\n"); - return -1; + rec_argv[j++] = record_args[i]; + + if (trace->trace_syscalls) { + for (i = 0; i < sc_args_nr; i++) + rec_argv[j++] = sc_args[i]; + + /* event string may be different for older kernels - e.g., RHEL6 */ + if (is_valid_tracepoint("raw_syscalls:sys_enter")) + rec_argv[j++] = "raw_syscalls:sys_enter,raw_syscalls:sys_exit"; + else if (is_valid_tracepoint("syscalls:sys_enter")) + rec_argv[j++] = "syscalls:sys_enter,syscalls:sys_exit"; + else { + pr_err("Neither raw_syscalls nor syscalls events exist.\n"); + return -1; + } } - i++; - for (j = 0; j < (unsigned int)argc; j++, i++) - rec_argv[i] = argv[j]; + if (trace->trace_pgfaults & TRACE_PFMAJ) + for (i = 0; i < majpf_args_nr; i++) + rec_argv[j++] = majpf_args[i]; + + if (trace->trace_pgfaults & TRACE_PFMIN) + for (i = 0; i < minpf_args_nr; i++) + rec_argv[j++] = minpf_args[i]; + + for (i = 0; i < (unsigned int)argc; i++) + rec_argv[j++] = argv[i]; - return cmd_record(i, rec_argv, NULL); + return cmd_record(j, rec_argv, NULL); } static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp); @@ -1882,6 +1987,30 @@ static void perf_evlist__add_vfs_getname(struct perf_evlist *evlist) perf_evlist__add(evlist, evsel); } +static int perf_evlist__add_pgfault(struct perf_evlist *evlist, + u64 config) +{ + struct perf_evsel *evsel; + struct perf_event_attr attr = { + .type = PERF_TYPE_SOFTWARE, + .mmap_data = 1, + }; + + attr.config = config; + attr.sample_period = 1; + + event_attr_init(&attr); + + evsel = perf_evsel__new(&attr); + if (!evsel) + return -ENOMEM; + + evsel->handler = trace__pgfault; + perf_evlist__add(evlist, evsel); + + return 0; +} + static int trace__run(struct trace *trace, int argc, const char **argv) { struct perf_evlist *evlist = perf_evlist__new(); @@ -1897,10 +2026,21 @@ static int trace__run(struct trace *trace, int argc, const char **argv) goto out; } - if (perf_evlist__add_syscall_newtp(evlist, trace__sys_enter, trace__sys_exit)) + if (trace->trace_syscalls && + perf_evlist__add_syscall_newtp(evlist, trace__sys_enter, + trace__sys_exit)) goto out_error_tp; - perf_evlist__add_vfs_getname(evlist); + 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; + + if ((trace->trace_pgfaults & TRACE_PFMIN) && + perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MIN)) + goto out_error_tp; if (trace->sched && perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime", @@ -1982,7 +2122,8 @@ again: goto next_event; } - if (sample.raw_data == NULL) { + if (evsel->attr.type == PERF_TYPE_TRACEPOINT && + sample.raw_data == NULL) { fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n", perf_evsel__name(evsel), sample.tid, sample.cpu, sample.raw_size); @@ -1990,7 +2131,7 @@ again: } handler = evsel->handler; - handler(trace, evsel, &sample); + handler(trace, evsel, event, &sample); next_event: perf_evlist__mmap_consume(evlist, i); @@ -2093,13 +2234,10 @@ static int trace__replay(struct trace *trace) if (evsel == NULL) evsel = perf_evlist__find_tracepoint_by_name(session->evlist, "syscalls:sys_enter"); - if (evsel == NULL) { - pr_err("Data file does not have raw_syscalls:sys_enter event\n"); - goto out; - } - if (perf_evsel__init_syscall_tp(evsel, trace__sys_enter) < 0 || - perf_evsel__init_sc_tp_ptr_field(evsel, args)) { + if (evsel && + (perf_evsel__init_syscall_tp(evsel, trace__sys_enter) < 0 || + perf_evsel__init_sc_tp_ptr_field(evsel, args))) { pr_err("Error during initialize raw_syscalls:sys_enter event\n"); goto out; } @@ -2109,15 +2247,19 @@ static int trace__replay(struct trace *trace) if (evsel == NULL) evsel = perf_evlist__find_tracepoint_by_name(session->evlist, "syscalls:sys_exit"); - if (evsel == NULL) { - pr_err("Data file does not have raw_syscalls:sys_exit event\n"); + if (evsel && + (perf_evsel__init_syscall_tp(evsel, trace__sys_exit) < 0 || + perf_evsel__init_sc_tp_uint_field(evsel, ret))) { + pr_err("Error during initialize raw_syscalls:sys_exit event\n"); goto out; } - if (perf_evsel__init_syscall_tp(evsel, trace__sys_exit) < 0 || - perf_evsel__init_sc_tp_uint_field(evsel, ret)) { - pr_err("Error during initialize raw_syscalls:sys_exit event\n"); - goto out; + evlist__for_each(session->evlist, evsel) { + if (evsel->attr.type == PERF_TYPE_SOFTWARE && + (evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ || + evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MIN || + evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS)) + evsel->handler = trace__pgfault; } err = parse_target_str(trace); @@ -2217,6 +2359,10 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv) printed += fprintf(fp, " %s (%d), ", thread__comm_str(thread), thread->tid); printed += fprintf(fp, "%lu events, ", ttrace->nr_events); printed += fprintf(fp, "%.1f%%", ratio); + if (ttrace->pfmaj) + printed += fprintf(fp, ", %lu majfaults", ttrace->pfmaj); + if (ttrace->pfmin) + printed += fprintf(fp, ", %lu minfaults", ttrace->pfmin); printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms); printed += thread__dump_stats(ttrace, trace, fp); @@ -2264,6 +2410,23 @@ static int trace__open_output(struct trace *trace, const char *filename) return trace->output == NULL ? -errno : 0; } +static int parse_pagefaults(const struct option *opt, const char *str, + int unset __maybe_unused) +{ + int *trace_pgfaults = opt->value; + + if (strcmp(str, "all") == 0) + *trace_pgfaults |= TRACE_PFMAJ | TRACE_PFMIN; + else if (strcmp(str, "maj") == 0) + *trace_pgfaults |= TRACE_PFMAJ; + else if (strcmp(str, "min") == 0) + *trace_pgfaults |= TRACE_PFMIN; + else + return -1; + + return 0; +} + int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) { const char * const trace_usage[] = { @@ -2293,6 +2456,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) }, .output = stdout, .show_comm = true, + .trace_syscalls = true, }; const char *output_name = NULL; const char *ev_qualifier_str = NULL; @@ -2330,20 +2494,34 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) "Show only syscall summary with statistics"), OPT_BOOLEAN('S', "with-summary", &trace.summary, "Show all syscalls and summary with statistics"), + OPT_CALLBACK_DEFAULT('F', "pf", &trace.trace_pgfaults, "all|maj|min", + "Trace pagefaults", parse_pagefaults, "maj"), + OPT_BOOLEAN(0, "syscalls", &trace.trace_syscalls, "Trace syscalls"), OPT_END() }; int err; char bf[BUFSIZ]; - if ((argc > 1) && (strcmp(argv[1], "record") == 0)) - return trace__record(argc-2, &argv[2]); + argc = parse_options(argc, argv, trace_options, trace_usage, + PARSE_OPT_STOP_AT_NON_OPTION); - argc = parse_options(argc, argv, trace_options, trace_usage, 0); + if (trace.trace_pgfaults) { + trace.opts.sample_address = true; + trace.opts.sample_time = true; + } + + if ((argc >= 1) && (strcmp(argv[0], "record") == 0)) + return trace__record(&trace, argc-1, &argv[1]); /* summary_only implies summary option, but don't overwrite summary if set */ if (trace.summary_only) trace.summary = trace.summary_only; + if (!trace.trace_syscalls && !trace.trace_pgfaults) { + pr_err("Please specify something to trace.\n"); + return -1; + } + if (output_name != NULL) { err = trace__open_output(&trace, output_name); if (err < 0) { diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index f30ac5e5d271..1f67aa02d240 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -48,6 +48,10 @@ ifneq ($(ARCH),$(filter $(ARCH),x86 arm)) NO_LIBDW_DWARF_UNWIND := 1 endif +ifeq ($(ARCH),powerpc) + CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX +endif + ifeq ($(LIBUNWIND_LIBS),) NO_LIBUNWIND := 1 else @@ -160,6 +164,7 @@ CORE_FEATURE_TESTS = \ backtrace \ dwarf \ fortify-source \ + sync-compare-and-swap \ glibc \ gtk2 \ gtk2-infobar \ @@ -195,6 +200,7 @@ LIB_FEATURE_TESTS = \ VF_FEATURE_TESTS = \ backtrace \ fortify-source \ + sync-compare-and-swap \ gtk2-infobar \ libelf-getphdrnum \ libelf-mmap \ @@ -268,6 +274,10 @@ CFLAGS += -I$(LIB_INCLUDE) CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE +ifeq ($(feature-sync-compare-and-swap), 1) + CFLAGS += -DHAVE_SYNC_COMPARE_AND_SWAP_SUPPORT +endif + ifndef NO_BIONIC $(call feature_check,bionic) ifeq ($(feature-bionic), 1) @@ -590,6 +600,10 @@ ifndef NO_LIBNUMA endif endif +ifdef HAVE_KVM_STAT_SUPPORT + CFLAGS += -DHAVE_KVM_STAT_SUPPORT +endif + # Among the variables below, these: # perfexecdir # template_dir diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile index 64c84e5f0514..6088f8d8a434 100644 --- a/tools/perf/config/feature-checks/Makefile +++ b/tools/perf/config/feature-checks/Makefile @@ -5,6 +5,7 @@ FILES= \ test-bionic.bin \ test-dwarf.bin \ test-fortify-source.bin \ + test-sync-compare-and-swap.bin \ test-glibc.bin \ test-gtk2.bin \ test-gtk2-infobar.bin \ @@ -141,6 +142,9 @@ test-timerfd.bin: test-libdw-dwarf-unwind.bin: $(BUILD) +test-sync-compare-and-swap.bin: + $(BUILD) -Werror + -include *.d ############################### diff --git a/tools/perf/config/feature-checks/test-all.c b/tools/perf/config/feature-checks/test-all.c index fe5c1e5c952f..a7d022e161c0 100644 --- a/tools/perf/config/feature-checks/test-all.c +++ b/tools/perf/config/feature-checks/test-all.c @@ -89,6 +89,10 @@ # include "test-libdw-dwarf-unwind.c" #undef main +#define main main_test_sync_compare_and_swap +# include "test-sync-compare-and-swap.c" +#undef main + int main(int argc, char *argv[]) { main_test_libpython(); @@ -111,6 +115,7 @@ int main(int argc, char *argv[]) main_test_timerfd(); main_test_stackprotector_all(); main_test_libdw_dwarf_unwind(); + main_test_sync_compare_and_swap(argc, argv); return 0; } diff --git a/tools/perf/config/feature-checks/test-sync-compare-and-swap.c b/tools/perf/config/feature-checks/test-sync-compare-and-swap.c new file mode 100644 index 000000000000..c34d4ca4af56 --- /dev/null +++ b/tools/perf/config/feature-checks/test-sync-compare-and-swap.c @@ -0,0 +1,14 @@ +#include <stdint.h> + +volatile uint64_t x; + +int main(int argc, char *argv[]) +{ + uint64_t old, new = argc; + + argv = argv; + do { + old = __sync_val_compare_and_swap(&x, 0, 0); + } while (!__sync_bool_compare_and_swap(&x, old, new)); + return old == new; +} diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h index 5268a1481d23..937e4324ad94 100644 --- a/tools/perf/perf-sys.h +++ b/tools/perf/perf-sys.h @@ -54,6 +54,7 @@ #define mb() asm volatile("bcr 15,0" ::: "memory") #define wmb() asm volatile("bcr 15,0" ::: "memory") #define rmb() asm volatile("bcr 15,0" ::: "memory") +#define CPUINFO_PROC "vendor_id" #endif #ifdef __sh__ diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 95c58fc15284..2282d41879a2 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -13,11 +13,12 @@ #include "util/quote.h" #include "util/run-command.h" #include "util/parse-events.h" +#include "util/debug.h" #include <api/fs/debugfs.h> #include <pthread.h> const char perf_usage_string[] = - "perf [--version] [--help] COMMAND [ARGS]"; + "perf [--version] [--help] [OPTIONS] COMMAND [ARGS]"; const char perf_more_info_string[] = "See 'perf help COMMAND' for more information on a specific command."; @@ -212,6 +213,16 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) printf("%s ", p->cmd); } exit(0); + } else if (!strcmp(cmd, "--debug")) { + if (*argc < 2) { + fprintf(stderr, "No variable specified for --debug.\n"); + usage(perf_usage_string); + } + if (perf_debug_option((*argv)[1])) + usage(perf_usage_string); + + (*argv)++; + (*argc)--; } else { fprintf(stderr, "Unknown option: %s\n", cmd); usage(perf_usage_string); diff --git a/tools/perf/scripts/perl/bin/failed-syscalls-record b/tools/perf/scripts/perl/bin/failed-syscalls-record index 8104895a7b67..74685f318379 100644 --- a/tools/perf/scripts/perl/bin/failed-syscalls-record +++ b/tools/perf/scripts/perl/bin/failed-syscalls-record @@ -1,2 +1,3 @@ #!/bin/bash -perf record -e raw_syscalls:sys_exit $@ +(perf record -e raw_syscalls:sys_exit $@ || \ + perf record -e syscalls:sys_exit $@) 2> /dev/null diff --git a/tools/perf/scripts/perl/failed-syscalls.pl b/tools/perf/scripts/perl/failed-syscalls.pl index 94bc25a347eb..55e7ae4c5c88 100644 --- a/tools/perf/scripts/perl/failed-syscalls.pl +++ b/tools/perf/scripts/perl/failed-syscalls.pl @@ -26,6 +26,11 @@ sub raw_syscalls::sys_exit } } +sub syscalls::sys_exit +{ + raw_syscalls::sys_exit(@_) +} + sub trace_end { printf("\nfailed syscalls by comm:\n\n"); diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py index de7211e4fa47..38dfb720fb6f 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py +++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py @@ -107,12 +107,13 @@ def taskState(state): class EventHeaders: def __init__(self, common_cpu, common_secs, common_nsecs, - common_pid, common_comm): + common_pid, common_comm, common_callchain): self.cpu = common_cpu self.secs = common_secs self.nsecs = common_nsecs self.pid = common_pid self.comm = common_comm + self.callchain = common_callchain def ts(self): return (self.secs * (10 ** 9)) + self.nsecs diff --git a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record index 8104895a7b67..74685f318379 100644 --- a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record +++ b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record @@ -1,2 +1,3 @@ #!/bin/bash -perf record -e raw_syscalls:sys_exit $@ +(perf record -e raw_syscalls:sys_exit $@ || \ + perf record -e syscalls:sys_exit $@) 2> /dev/null diff --git a/tools/perf/scripts/python/bin/sctop-record b/tools/perf/scripts/python/bin/sctop-record index 4efbfaa7f6a5..d6940841e54f 100644 --- a/tools/perf/scripts/python/bin/sctop-record +++ b/tools/perf/scripts/python/bin/sctop-record @@ -1,2 +1,3 @@ #!/bin/bash -perf record -e raw_syscalls:sys_enter $@ +(perf record -e raw_syscalls:sys_enter $@ || \ + perf record -e syscalls:sys_enter $@) 2> /dev/null diff --git a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record index 4efbfaa7f6a5..d6940841e54f 100644 --- a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record +++ b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record @@ -1,2 +1,3 @@ #!/bin/bash -perf record -e raw_syscalls:sys_enter $@ +(perf record -e raw_syscalls:sys_enter $@ || \ + perf record -e syscalls:sys_enter $@) 2> /dev/null diff --git a/tools/perf/scripts/python/bin/syscall-counts-record b/tools/perf/scripts/python/bin/syscall-counts-record index 4efbfaa7f6a5..d6940841e54f 100644 --- a/tools/perf/scripts/python/bin/syscall-counts-record +++ b/tools/perf/scripts/python/bin/syscall-counts-record @@ -1,2 +1,3 @@ #!/bin/bash -perf record -e raw_syscalls:sys_enter $@ +(perf record -e raw_syscalls:sys_enter $@ || \ + perf record -e syscalls:sys_enter $@) 2> /dev/null diff --git a/tools/perf/scripts/python/check-perf-trace.py b/tools/perf/scripts/python/check-perf-trace.py index 4647a7694cf6..334599c6032c 100644 --- a/tools/perf/scripts/python/check-perf-trace.py +++ b/tools/perf/scripts/python/check-perf-trace.py @@ -27,7 +27,7 @@ def trace_end(): def irq__softirq_entry(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - vec): + common_callchain, vec): print_header(event_name, common_cpu, common_secs, common_nsecs, common_pid, common_comm) @@ -38,7 +38,7 @@ def irq__softirq_entry(event_name, context, common_cpu, def kmem__kmalloc(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - call_site, ptr, bytes_req, bytes_alloc, + common_callchain, call_site, ptr, bytes_req, bytes_alloc, gfp_flags): print_header(event_name, common_cpu, common_secs, common_nsecs, common_pid, common_comm) diff --git a/tools/perf/scripts/python/failed-syscalls-by-pid.py b/tools/perf/scripts/python/failed-syscalls-by-pid.py index 85805fac4116..cafeff3d74db 100644 --- a/tools/perf/scripts/python/failed-syscalls-by-pid.py +++ b/tools/perf/scripts/python/failed-syscalls-by-pid.py @@ -39,7 +39,7 @@ def trace_end(): def raw_syscalls__sys_exit(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - id, ret): + common_callchain, id, ret): if (for_comm and common_comm != for_comm) or \ (for_pid and common_pid != for_pid ): return @@ -50,6 +50,11 @@ def raw_syscalls__sys_exit(event_name, context, common_cpu, except TypeError: syscalls[common_comm][common_pid][id][ret] = 1 +def syscalls__sys_exit(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + id, ret): + raw_syscalls__sys_exit(**locals()) + def print_error_totals(): if for_comm is not None: print "\nsyscall errors for %s:\n\n" % (for_comm), diff --git a/tools/perf/scripts/python/futex-contention.py b/tools/perf/scripts/python/futex-contention.py index 11e70a388d41..0f5cf437b602 100644 --- a/tools/perf/scripts/python/futex-contention.py +++ b/tools/perf/scripts/python/futex-contention.py @@ -21,7 +21,7 @@ thread_blocktime = {} lock_waits = {} # long-lived stats on (tid,lock) blockage elapsed time process_names = {} # long-lived pid-to-execname mapping -def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm, +def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm, callchain, nr, uaddr, op, val, utime, uaddr2, val3): cmd = op & FUTEX_CMD_MASK if cmd != FUTEX_WAIT: @@ -31,7 +31,7 @@ def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm, thread_thislock[tid] = uaddr thread_blocktime[tid] = nsecs(s, ns) -def syscalls__sys_exit_futex(event, ctxt, cpu, s, ns, tid, comm, +def syscalls__sys_exit_futex(event, ctxt, cpu, s, ns, tid, comm, callchain, nr, ret): if thread_blocktime.has_key(tid): elapsed = nsecs(s, ns) - thread_blocktime[tid] diff --git a/tools/perf/scripts/python/net_dropmonitor.py b/tools/perf/scripts/python/net_dropmonitor.py index b5740599aabd..0b6ce8c253e8 100755 --- a/tools/perf/scripts/python/net_dropmonitor.py +++ b/tools/perf/scripts/python/net_dropmonitor.py @@ -66,7 +66,7 @@ def trace_end(): print_drop_table() # called from perf, when it finds a correspoinding event -def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, +def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, location, protocol): slocation = str(location) try: diff --git a/tools/perf/scripts/python/netdev-times.py b/tools/perf/scripts/python/netdev-times.py index 9aa0a32972e8..4d21ef2d601d 100644 --- a/tools/perf/scripts/python/netdev-times.py +++ b/tools/perf/scripts/python/netdev-times.py @@ -224,75 +224,75 @@ def trace_end(): (len(rx_skb_list), of_count_rx_skb_list) # called from perf, when it finds a correspoinding event -def irq__softirq_entry(name, context, cpu, sec, nsec, pid, comm, vec): +def irq__softirq_entry(name, context, cpu, sec, nsec, pid, comm, callchain, vec): if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX": return event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec) all_event_list.append(event_info) -def irq__softirq_exit(name, context, cpu, sec, nsec, pid, comm, vec): +def irq__softirq_exit(name, context, cpu, sec, nsec, pid, comm, callchain, vec): if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX": return event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec) all_event_list.append(event_info) -def irq__softirq_raise(name, context, cpu, sec, nsec, pid, comm, vec): +def irq__softirq_raise(name, context, cpu, sec, nsec, pid, comm, callchain, vec): if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX": return event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec) all_event_list.append(event_info) def irq__irq_handler_entry(name, context, cpu, sec, nsec, pid, comm, - irq, irq_name): + callchain, irq, irq_name): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, irq, irq_name) all_event_list.append(event_info) -def irq__irq_handler_exit(name, context, cpu, sec, nsec, pid, comm, irq, ret): +def irq__irq_handler_exit(name, context, cpu, sec, nsec, pid, comm, callchain, irq, ret): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, irq, ret) all_event_list.append(event_info) -def napi__napi_poll(name, context, cpu, sec, nsec, pid, comm, napi, dev_name): +def napi__napi_poll(name, context, cpu, sec, nsec, pid, comm, callchain, napi, dev_name): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, napi, dev_name) all_event_list.append(event_info) -def net__netif_receive_skb(name, context, cpu, sec, nsec, pid, comm, skbaddr, +def net__netif_receive_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, skblen, dev_name): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, skbaddr, skblen, dev_name) all_event_list.append(event_info) -def net__netif_rx(name, context, cpu, sec, nsec, pid, comm, skbaddr, +def net__netif_rx(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, skblen, dev_name): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, skbaddr, skblen, dev_name) all_event_list.append(event_info) -def net__net_dev_queue(name, context, cpu, sec, nsec, pid, comm, +def net__net_dev_queue(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, skblen, dev_name): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, skbaddr, skblen, dev_name) all_event_list.append(event_info) -def net__net_dev_xmit(name, context, cpu, sec, nsec, pid, comm, +def net__net_dev_xmit(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, skblen, rc, dev_name): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, skbaddr, skblen, rc ,dev_name) all_event_list.append(event_info) -def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, +def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, protocol, location): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, skbaddr, protocol, location) all_event_list.append(event_info) -def skb__consume_skb(name, context, cpu, sec, nsec, pid, comm, skbaddr): +def skb__consume_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, skbaddr) all_event_list.append(event_info) -def skb__skb_copy_datagram_iovec(name, context, cpu, sec, nsec, pid, comm, +def skb__skb_copy_datagram_iovec(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, skblen): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, skbaddr, skblen) diff --git a/tools/perf/scripts/python/sched-migration.py b/tools/perf/scripts/python/sched-migration.py index 74d55ec08aed..de66cb3b72c9 100644 --- a/tools/perf/scripts/python/sched-migration.py +++ b/tools/perf/scripts/python/sched-migration.py @@ -369,93 +369,92 @@ def trace_end(): def sched__sched_stat_runtime(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, runtime, vruntime): + common_callchain, comm, pid, runtime, vruntime): pass def sched__sched_stat_iowait(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, delay): + common_callchain, comm, pid, delay): pass def sched__sched_stat_sleep(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, delay): + common_callchain, comm, pid, delay): pass def sched__sched_stat_wait(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, delay): + common_callchain, comm, pid, delay): pass def sched__sched_process_fork(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - parent_comm, parent_pid, child_comm, child_pid): + common_callchain, parent_comm, parent_pid, child_comm, child_pid): pass def sched__sched_process_wait(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, prio): + common_callchain, comm, pid, prio): pass def sched__sched_process_exit(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, prio): + common_callchain, comm, pid, prio): pass def sched__sched_process_free(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, prio): + common_callchain, comm, pid, prio): pass def sched__sched_migrate_task(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, prio, orig_cpu, + common_callchain, comm, pid, prio, orig_cpu, dest_cpu): headers = EventHeaders(common_cpu, common_secs, common_nsecs, - common_pid, common_comm) + common_pid, common_comm, common_callchain) parser.migrate(headers, pid, prio, orig_cpu, dest_cpu) def sched__sched_switch(event_name, context, common_cpu, - common_secs, common_nsecs, common_pid, common_comm, + common_secs, common_nsecs, common_pid, common_comm, common_callchain, prev_comm, prev_pid, prev_prio, prev_state, next_comm, next_pid, next_prio): headers = EventHeaders(common_cpu, common_secs, common_nsecs, - common_pid, common_comm) + common_pid, common_comm, common_callchain) parser.sched_switch(headers, prev_comm, prev_pid, prev_prio, prev_state, next_comm, next_pid, next_prio) def sched__sched_wakeup_new(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, prio, success, + common_callchain, comm, pid, prio, success, target_cpu): headers = EventHeaders(common_cpu, common_secs, common_nsecs, - common_pid, common_comm) + common_pid, common_comm, common_callchain) parser.wake_up(headers, comm, pid, success, target_cpu, 1) def sched__sched_wakeup(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, prio, success, + common_callchain, comm, pid, prio, success, target_cpu): headers = EventHeaders(common_cpu, common_secs, common_nsecs, - common_pid, common_comm) + common_pid, common_comm, common_callchain) parser.wake_up(headers, comm, pid, success, target_cpu, 0) def sched__sched_wait_task(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, prio): + common_callchain, comm, pid, prio): pass def sched__sched_kthread_stop_ret(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - ret): + common_callchain, ret): pass def sched__sched_kthread_stop(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid): + common_callchain, comm, pid): pass -def trace_unhandled(event_name, context, common_cpu, common_secs, common_nsecs, - common_pid, common_comm): +def trace_unhandled(event_name, context, event_fields_dict): pass diff --git a/tools/perf/scripts/python/sctop.py b/tools/perf/scripts/python/sctop.py index 42c267e292fa..61621b93affb 100644 --- a/tools/perf/scripts/python/sctop.py +++ b/tools/perf/scripts/python/sctop.py @@ -44,7 +44,7 @@ def trace_begin(): def raw_syscalls__sys_enter(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - id, args): + common_callchain, id, args): if for_comm is not None: if common_comm != for_comm: return @@ -53,6 +53,11 @@ def raw_syscalls__sys_enter(event_name, context, common_cpu, except TypeError: syscalls[id] = 1 +def syscalls__sys_enter(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + id, args): + raw_syscalls__sys_enter(**locals()) + def print_syscall_totals(interval): while 1: clear_term() diff --git a/tools/perf/scripts/python/syscall-counts-by-pid.py b/tools/perf/scripts/python/syscall-counts-by-pid.py index c64d1c55d745..daf314cc5dd3 100644 --- a/tools/perf/scripts/python/syscall-counts-by-pid.py +++ b/tools/perf/scripts/python/syscall-counts-by-pid.py @@ -38,7 +38,7 @@ def trace_end(): def raw_syscalls__sys_enter(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - id, args): + common_callchain, id, args): if (for_comm and common_comm != for_comm) or \ (for_pid and common_pid != for_pid ): @@ -48,6 +48,11 @@ def raw_syscalls__sys_enter(event_name, context, common_cpu, except TypeError: syscalls[common_comm][common_pid][id] = 1 +def syscalls__sys_enter(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + id, args): + raw_syscalls__sys_enter(**locals()) + def print_syscall_totals(): if for_comm is not None: print "\nsyscall events for %s:\n\n" % (for_comm), diff --git a/tools/perf/scripts/python/syscall-counts.py b/tools/perf/scripts/python/syscall-counts.py index b435d3f188e8..e66a7730aeb5 100644 --- a/tools/perf/scripts/python/syscall-counts.py +++ b/tools/perf/scripts/python/syscall-counts.py @@ -35,7 +35,7 @@ def trace_end(): def raw_syscalls__sys_enter(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - id, args): + common_callchain, id, args): if for_comm is not None: if common_comm != for_comm: return @@ -44,6 +44,11 @@ def raw_syscalls__sys_enter(event_name, context, common_cpu, except TypeError: syscalls[id] = 1 +def syscalls__sys_enter(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + id, args): + raw_syscalls__sys_enter(**locals()) + def print_syscall_totals(): if for_comm is not None: print "\nsyscall events for %s:\n\n" % (for_comm), diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record index e9bd6391f2ae..f710b92ccff6 100644 --- a/tools/perf/tests/attr/base-record +++ b/tools/perf/tests/attr/base-record @@ -1,7 +1,8 @@ [event] fd=1 group_fd=-1 -flags=0 +# 0 or PERF_FLAG_FD_CLOEXEC flag +flags=0|8 cpu=* type=0|1 size=96 diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat index 91cd48b399f3..dc3ada2470c0 100644 --- a/tools/perf/tests/attr/base-stat +++ b/tools/perf/tests/attr/base-stat @@ -1,7 +1,8 @@ [event] fd=1 group_fd=-1 -flags=0 +# 0 or PERF_FLAG_FD_CLOEXEC flag +flags=0|8 cpu=* type=0 size=96 diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c index aba095489193..a02b035fd5aa 100644 --- a/tools/perf/tests/bp_signal.c +++ b/tools/perf/tests/bp_signal.c @@ -25,6 +25,7 @@ #include "tests.h" #include "debug.h" #include "perf.h" +#include "cloexec.h" static int fd1; static int fd2; @@ -78,7 +79,8 @@ static int bp_event(void *fn, int setup_signal) pe.exclude_kernel = 1; pe.exclude_hv = 1; - fd = sys_perf_event_open(&pe, 0, -1, -1, 0); + fd = sys_perf_event_open(&pe, 0, -1, -1, + perf_event_open_cloexec_flag()); if (fd < 0) { pr_debug("failed opening event %llx\n", pe.config); return TEST_FAIL; diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c index 44ac82179708..e76537724491 100644 --- a/tools/perf/tests/bp_signal_overflow.c +++ b/tools/perf/tests/bp_signal_overflow.c @@ -24,6 +24,7 @@ #include "tests.h" #include "debug.h" #include "perf.h" +#include "cloexec.h" static int overflows; @@ -91,7 +92,8 @@ int test__bp_signal_overflow(void) pe.exclude_kernel = 1; pe.exclude_hv = 1; - fd = sys_perf_event_open(&pe, 0, -1, -1, 0); + fd = sys_perf_event_open(&pe, 0, -1, -1, + perf_event_open_cloexec_flag()); if (fd < 0) { pr_debug("failed opening event %llx\n", pe.config); return TEST_FAIL; diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c index 630808cd7cc2..caaf37f079b1 100644 --- a/tools/perf/tests/dso-data.c +++ b/tools/perf/tests/dso-data.c @@ -10,6 +10,7 @@ #include "machine.h" #include "symbol.h" #include "tests.h" +#include "debug.h" static char *test_file(int size) { diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c index 465cdbc345cf..b8d8341b383e 100644 --- a/tools/perf/tests/evsel-roundtrip-name.c +++ b/tools/perf/tests/evsel-roundtrip-name.c @@ -2,6 +2,7 @@ #include "evsel.h" #include "parse-events.h" #include "tests.h" +#include "debug.h" static int perf_evsel__roundtrip_cache_name_test(void) { diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c index 35d7fdb2328d..52162425c969 100644 --- a/tools/perf/tests/evsel-tp-sched.c +++ b/tools/perf/tests/evsel-tp-sched.c @@ -1,6 +1,7 @@ #include <traceevent/event-parse.h> #include "evsel.h" #include "tests.h" +#include "debug.h" static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name, int size, bool should_be_signed) diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c index c505ef2af245..0785b64ffd6c 100644 --- a/tools/perf/tests/open-syscall-tp-fields.c +++ b/tools/perf/tests/open-syscall-tp-fields.c @@ -3,6 +3,7 @@ #include "evsel.h" #include "thread_map.h" #include "tests.h" +#include "debug.h" int test__syscall_open_tp_fields(void) { diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index deba66955f8c..5941927a4b7f 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -5,6 +5,7 @@ #include <api/fs/fs.h> #include <api/fs/debugfs.h> #include "tests.h" +#include "debug.h" #include <linux/hw_breakpoint.h> #define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \ diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c index 905019f9b740..2c63ea658541 100644 --- a/tools/perf/tests/parse-no-sample-id-all.c +++ b/tools/perf/tests/parse-no-sample-id-all.c @@ -7,6 +7,7 @@ #include "evlist.h" #include "header.h" #include "util.h" +#include "debug.h" static int process_event(struct perf_evlist **pevlist, union perf_event *event) { diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index 3b7cd4d32dcb..f238442b238a 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -8,10 +8,9 @@ #include "evsel.h" #include "thread_map.h" #include "cpumap.h" +#include "tsc.h" #include "tests.h" -#include "../arch/x86/util/tsc.h" - #define CHECK__(x) { \ while ((x) < 0) { \ pr_debug(#x " failed!\n"); \ @@ -26,15 +25,6 @@ } \ } -static u64 rdtsc(void) -{ - unsigned int low, high; - - asm volatile("rdtsc" : "=a" (low), "=d" (high)); - - return low | ((u64)high) << 32; -} - /** * test__perf_time_to_tsc - test converting perf time to TSC. * diff --git a/tools/perf/tests/rdpmc.c b/tools/perf/tests/rdpmc.c index e59143fd9e71..c04d1f268576 100644 --- a/tools/perf/tests/rdpmc.c +++ b/tools/perf/tests/rdpmc.c @@ -6,6 +6,7 @@ #include "perf.h" #include "debug.h" #include "tests.h" +#include "cloexec.h" #if defined(__x86_64__) || defined(__i386__) @@ -104,7 +105,8 @@ static int __test__rdpmc(void) sa.sa_sigaction = segfault_handler; sigaction(SIGSEGV, &sa, NULL); - fd = sys_perf_event_open(&attr, 0, -1, -1, 0); + fd = sys_perf_event_open(&attr, 0, -1, -1, + perf_event_open_cloexec_flag()); if (fd < 0) { pr_err("Error: sys_perf_event_open() syscall returned " "with %d (%s)\n", fd, strerror(errno)); diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index 7ae8d17db3d9..ca292f9a4ae2 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -4,6 +4,7 @@ #include "util.h" #include "event.h" #include "evsel.h" +#include "debug.h" #include "tests.h" diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c index 2b2e0dbe114f..b028499dd3cf 100644 --- a/tools/perf/tests/thread-mg-share.c +++ b/tools/perf/tests/thread-mg-share.c @@ -2,6 +2,7 @@ #include "machine.h" #include "thread.h" #include "map.h" +#include "debug.h" int test__thread_mg_share(void) { diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index 3ccf6e14f89b..6680fa5cb9dd 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -150,7 +150,7 @@ unsigned int ui_browser__rb_tree_refresh(struct ui_browser *browser) while (nd != NULL) { ui_browser__gotorc(browser, row, 0); browser->write(browser, nd, row); - if (++row == browser->height) + if (++row == browser->rows) break; nd = rb_next(nd); } @@ -166,7 +166,7 @@ bool ui_browser__is_current_entry(struct ui_browser *browser, unsigned row) void ui_browser__refresh_dimensions(struct ui_browser *browser) { browser->width = SLtt_Screen_Cols - 1; - browser->height = SLtt_Screen_Rows - 2; + browser->height = browser->rows = SLtt_Screen_Rows - 2; browser->y = 1; browser->x = 0; } @@ -250,7 +250,10 @@ int ui_browser__show(struct ui_browser *browser, const char *title, int err; va_list ap; - ui_browser__refresh_dimensions(browser); + if (browser->refresh_dimensions == NULL) + browser->refresh_dimensions = ui_browser__refresh_dimensions; + + browser->refresh_dimensions(browser); pthread_mutex_lock(&ui__lock); __ui_browser__show_title(browser, title); @@ -279,7 +282,7 @@ static void ui_browser__scrollbar_set(struct ui_browser *browser) { int height = browser->height, h = 0, pct = 0, col = browser->width, - row = browser->y - 1; + row = 0; if (browser->nr_entries > 1) { pct = ((browser->index * (browser->height - 1)) / @@ -367,7 +370,7 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs) if (key == K_RESIZE) { ui__refresh_dimensions(false); - ui_browser__refresh_dimensions(browser); + browser->refresh_dimensions(browser); __ui_browser__show_title(browser, browser->title); ui_helpline__puts(browser->helpline); continue; @@ -389,7 +392,7 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs) if (browser->index == browser->nr_entries - 1) break; ++browser->index; - if (browser->index == browser->top_idx + browser->height) { + if (browser->index == browser->top_idx + browser->rows) { ++browser->top_idx; browser->seek(browser, +1, SEEK_CUR); } @@ -405,10 +408,10 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs) break; case K_PGDN: case ' ': - if (browser->top_idx + browser->height > browser->nr_entries - 1) + if (browser->top_idx + browser->rows > browser->nr_entries - 1) break; - offset = browser->height; + offset = browser->rows; if (browser->index + offset > browser->nr_entries - 1) offset = browser->nr_entries - 1 - browser->index; browser->index += offset; @@ -419,10 +422,10 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs) if (browser->top_idx == 0) break; - if (browser->top_idx < browser->height) + if (browser->top_idx < browser->rows) offset = browser->top_idx; else - offset = browser->height; + offset = browser->rows; browser->index -= offset; browser->top_idx -= offset; @@ -432,7 +435,7 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs) ui_browser__reset_index(browser); break; case K_END: - offset = browser->height - 1; + offset = browser->rows - 1; if (offset >= browser->nr_entries) offset = browser->nr_entries - 1; @@ -462,7 +465,7 @@ unsigned int ui_browser__list_head_refresh(struct ui_browser *browser) if (!browser->filter || !browser->filter(browser, pos)) { ui_browser__gotorc(browser, row, 0); browser->write(browser, pos, row); - if (++row == browser->height) + if (++row == browser->rows) break; } } @@ -587,7 +590,7 @@ unsigned int ui_browser__argv_refresh(struct ui_browser *browser) if (!browser->filter || !browser->filter(browser, *pos)) { ui_browser__gotorc(browser, row, 0); browser->write(browser, pos, row); - if (++row == browser->height) + if (++row == browser->rows) break; } @@ -623,7 +626,7 @@ static void __ui_browser__line_arrow_up(struct ui_browser *browser, SLsmg_set_char_set(1); - if (start < browser->top_idx + browser->height) { + if (start < browser->top_idx + browser->rows) { row = start - browser->top_idx; ui_browser__gotorc(browser, row, column); SLsmg_write_char(SLSMG_LLCORN_CHAR); @@ -633,7 +636,7 @@ static void __ui_browser__line_arrow_up(struct ui_browser *browser, if (row-- == 0) goto out; } else - row = browser->height - 1; + row = browser->rows - 1; if (end > browser->top_idx) end_row = end - browser->top_idx; @@ -675,8 +678,8 @@ static void __ui_browser__line_arrow_down(struct ui_browser *browser, } else row = 0; - if (end >= browser->top_idx + browser->height) - end_row = browser->height - 1; + if (end >= browser->top_idx + browser->rows) + end_row = browser->rows - 1; else end_row = end - browser->top_idx; @@ -684,7 +687,7 @@ static void __ui_browser__line_arrow_down(struct ui_browser *browser, SLsmg_draw_vline(end_row - row + 1); ui_browser__gotorc(browser, end_row, column); - if (end < browser->top_idx + browser->height) { + if (end < browser->top_idx + browser->rows) { SLsmg_write_char(SLSMG_LLCORN_CHAR); ui_browser__gotorc(browser, end_row, column + 1); SLsmg_write_char(SLSMG_HLINE_CHAR); diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h index 03d4d6295f10..92ae72113965 100644 --- a/tools/perf/ui/browser.h +++ b/tools/perf/ui/browser.h @@ -14,11 +14,12 @@ struct ui_browser { u64 index, top_idx; void *top, *entries; - u16 y, x, width, height; + u16 y, x, width, height, rows; int current_color; void *priv; const char *title; char *helpline; + void (*refresh_dimensions)(struct ui_browser *browser); unsigned int (*refresh)(struct ui_browser *browser); void (*write)(struct ui_browser *browser, void *entry, int row); void (*seek)(struct ui_browser *browser, off_t offset, int whence); diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 04a229aa5c0f..a94b11fc5e00 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -26,6 +26,7 @@ struct hist_browser { struct map_symbol *selection; int print_seq; bool show_dso; + bool show_headers; float min_pcnt; u64 nr_non_filtered_entries; u64 nr_callchain_rows; @@ -33,8 +34,7 @@ struct hist_browser { extern void hist_browser__init_hpp(void); -static int hists__browser_title(struct hists *hists, char *bf, size_t size, - const char *ev_name); +static int hists__browser_title(struct hists *hists, char *bf, size_t size); static void hist_browser__update_nr_entries(struct hist_browser *hb); static struct rb_node *hists__filter_entries(struct rb_node *nd, @@ -57,11 +57,42 @@ static u32 hist_browser__nr_entries(struct hist_browser *hb) return nr_entries + hb->nr_callchain_rows; } -static void hist_browser__refresh_dimensions(struct hist_browser *browser) +static void hist_browser__update_rows(struct hist_browser *hb) { + struct ui_browser *browser = &hb->b; + u16 header_offset = hb->show_headers ? 1 : 0, index_row; + + browser->rows = browser->height - header_offset; + /* + * Verify if we were at the last line and that line isn't + * visibe because we now show the header line(s). + */ + index_row = browser->index - browser->top_idx; + if (index_row >= browser->rows) + browser->index -= index_row - browser->rows + 1; +} + +static void hist_browser__refresh_dimensions(struct ui_browser *browser) +{ + struct hist_browser *hb = container_of(browser, struct hist_browser, b); + /* 3 == +/- toggle symbol before actual hist_entry rendering */ - browser->b.width = 3 + (hists__sort_list_width(browser->hists) + - sizeof("[k]")); + browser->width = 3 + (hists__sort_list_width(hb->hists) + sizeof("[k]")); + /* + * FIXME: Just keeping existing behaviour, but this really should be + * before updating browser->width, as it will invalidate the + * calculation above. Fix this and the fallout in another + * changeset. + */ + ui_browser__refresh_dimensions(browser); + hist_browser__update_rows(hb); +} + +static void hist_browser__gotorc(struct hist_browser *browser, int row, int column) +{ + u16 header_offset = browser->show_headers ? 1 : 0; + + ui_browser__gotorc(&browser->b, row + header_offset, column); } static void hist_browser__reset(struct hist_browser *browser) @@ -74,7 +105,7 @@ static void hist_browser__reset(struct hist_browser *browser) hist_browser__update_nr_entries(browser); browser->b.nr_entries = hist_browser__nr_entries(browser); - hist_browser__refresh_dimensions(browser); + hist_browser__refresh_dimensions(&browser->b); ui_browser__reset_index(&browser->b); } @@ -346,7 +377,7 @@ static void ui_browser__warn_lost_events(struct ui_browser *browser) "Or reduce the sampling frequency."); } -static int hist_browser__run(struct hist_browser *browser, const char *ev_name, +static int hist_browser__run(struct hist_browser *browser, struct hist_browser_timer *hbt) { int key; @@ -356,8 +387,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name, browser->b.entries = &browser->hists->entries; browser->b.nr_entries = hist_browser__nr_entries(browser); - hist_browser__refresh_dimensions(browser); - hists__browser_title(browser->hists, title, sizeof(title), ev_name); + hists__browser_title(browser->hists, title, sizeof(title)); if (ui_browser__show(&browser->b, title, "Press '?' for help on key bindings") < 0) @@ -384,7 +414,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name, ui_browser__warn_lost_events(&browser->b); } - hists__browser_title(browser->hists, title, sizeof(title), ev_name); + hists__browser_title(browser->hists, title, sizeof(title)); ui_browser__show_title(&browser->b, title); continue; } @@ -393,10 +423,10 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name, struct hist_entry *h = rb_entry(browser->b.top, struct hist_entry, rb_node); ui_helpline__pop(); - ui_helpline__fpush("%d: nr_ent=(%d,%d), height=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d", + ui_helpline__fpush("%d: nr_ent=(%d,%d), rows=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d", seq++, browser->b.nr_entries, browser->hists->nr_entries, - browser->b.height, + browser->b.rows, browser->b.index, browser->b.top_idx, h->row_offset, h->nr_rows); @@ -410,6 +440,10 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name, /* Expand the whole world. */ hist_browser__set_folding(browser, true); break; + case 'H': + browser->show_headers = !browser->show_headers; + hist_browser__update_rows(browser); + break; case K_ENTER: if (hist_browser__toggle_fold(browser)) break; @@ -509,13 +543,13 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *browse } ui_browser__set_color(&browser->b, color); - ui_browser__gotorc(&browser->b, row, 0); + hist_browser__gotorc(browser, row, 0); slsmg_write_nstring(" ", offset + extra_offset); slsmg_printf("%c ", folded_sign); slsmg_write_nstring(str, width); free(alloc_str); - if (++row == browser->b.height) + if (++row == browser->b.rows) goto out; do_next: if (folded_sign == '+') @@ -528,7 +562,7 @@ do_next: new_level, row, row_offset, is_current_entry); } - if (row == browser->b.height) + if (row == browser->b.rows) goto out; node = next; } @@ -568,13 +602,13 @@ static int hist_browser__show_callchain_node(struct hist_browser *browser, s = callchain_list__sym_name(chain, bf, sizeof(bf), browser->show_dso); - ui_browser__gotorc(&browser->b, row, 0); + hist_browser__gotorc(browser, row, 0); ui_browser__set_color(&browser->b, color); slsmg_write_nstring(" ", offset); slsmg_printf("%c ", folded_sign); slsmg_write_nstring(s, width - 2); - if (++row == browser->b.height) + if (++row == browser->b.rows) goto out; } @@ -603,7 +637,7 @@ static int hist_browser__show_callchain(struct hist_browser *browser, row += hist_browser__show_callchain_node(browser, node, level, row, row_offset, is_current_entry); - if (row == browser->b.height) + if (row == browser->b.rows) break; } @@ -733,7 +767,7 @@ static int hist_browser__show_entry(struct hist_browser *browser, .ptr = &arg, }; - ui_browser__gotorc(&browser->b, row, 0); + hist_browser__gotorc(browser, row, 0); perf_hpp__for_each_format(fmt) { if (perf_hpp__should_skip(fmt)) @@ -777,7 +811,7 @@ static int hist_browser__show_entry(struct hist_browser *browser, } else --row_offset; - if (folded_sign == '-' && row != browser->b.height) { + if (folded_sign == '-' && row != browser->b.rows) { printed += hist_browser__show_callchain(browser, &entry->sorted_chain, 1, row, &row_offset, ¤t_entry); @@ -788,6 +822,56 @@ static int hist_browser__show_entry(struct hist_browser *browser, return printed; } +static int advance_hpp_check(struct perf_hpp *hpp, int inc) +{ + advance_hpp(hpp, inc); + return hpp->size <= 0; +} + +static int hists__scnprintf_headers(char *buf, size_t size, struct hists *hists) +{ + struct perf_hpp dummy_hpp = { + .buf = buf, + .size = size, + }; + struct perf_hpp_fmt *fmt; + size_t ret = 0; + + if (symbol_conf.use_callchain) { + ret = scnprintf(buf, size, " "); + if (advance_hpp_check(&dummy_hpp, ret)) + return ret; + } + + perf_hpp__for_each_format(fmt) { + if (perf_hpp__should_skip(fmt)) + continue; + + /* We need to add the length of the columns header. */ + perf_hpp__reset_width(fmt, hists); + + ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists)); + if (advance_hpp_check(&dummy_hpp, ret)) + break; + + ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, " "); + if (advance_hpp_check(&dummy_hpp, ret)) + break; + } + + return ret; +} + +static void hist_browser__show_headers(struct hist_browser *browser) +{ + char headers[1024]; + + hists__scnprintf_headers(headers, sizeof(headers), browser->hists); + ui_browser__gotorc(&browser->b, 0, 0); + ui_browser__set_color(&browser->b, HE_COLORSET_ROOT); + slsmg_write_nstring(headers, browser->b.width + 1); +} + static void ui_browser__hists_init_top(struct ui_browser *browser) { if (browser->top == NULL) { @@ -801,9 +885,15 @@ static void ui_browser__hists_init_top(struct ui_browser *browser) static unsigned int hist_browser__refresh(struct ui_browser *browser) { unsigned row = 0; + u16 header_offset = 0; struct rb_node *nd; struct hist_browser *hb = container_of(browser, struct hist_browser, b); + if (hb->show_headers) { + hist_browser__show_headers(hb); + header_offset = 1; + } + ui_browser__hists_init_top(browser); for (nd = browser->top; nd; nd = rb_next(nd)) { @@ -818,11 +908,11 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser) continue; row += hist_browser__show_entry(hb, h, row); - if (row == browser->height) + if (row == browser->rows) break; } - return row; + return row + header_offset; } static struct rb_node *hists__filter_entries(struct rb_node *nd, @@ -1191,8 +1281,10 @@ static struct hist_browser *hist_browser__new(struct hists *hists) if (browser) { browser->hists = hists; browser->b.refresh = hist_browser__refresh; + browser->b.refresh_dimensions = hist_browser__refresh_dimensions; browser->b.seek = ui_browser__hists_seek; browser->b.use_navkeypressed = true; + browser->show_headers = symbol_conf.show_hist_headers; } return browser; @@ -1213,8 +1305,7 @@ static struct thread *hist_browser__selected_thread(struct hist_browser *browser return browser->he_selection->thread; } -static int hists__browser_title(struct hists *hists, char *bf, size_t size, - const char *ev_name) +static int hists__browser_title(struct hists *hists, char *bf, size_t size) { char unit; int printed; @@ -1223,6 +1314,7 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size, unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE]; u64 nr_events = hists->stats.total_period; struct perf_evsel *evsel = hists_to_evsel(hists); + const char *ev_name = perf_evsel__name(evsel); char buf[512]; size_t buflen = sizeof(buf); @@ -1390,7 +1482,7 @@ static void hist_browser__update_nr_entries(struct hist_browser *hb) } static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, - const char *helpline, const char *ev_name, + const char *helpline, bool left_exits, struct hist_browser_timer *hbt, float min_pcnt, @@ -1422,6 +1514,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, "d Zoom into current DSO\n" \ "E Expand all callchains\n" \ "F Toggle percentage of filtered entries\n" \ + "H Display column headers\n" \ /* help messages are sorted by lexical order of the hotkey */ const char report_help[] = HIST_BROWSER_HELP_COMMON @@ -1465,7 +1558,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, nr_options = 0; - key = hist_browser__run(browser, ev_name, hbt); + key = hist_browser__run(browser, hbt); if (browser->he_selection != NULL) { thread = hist_browser__selected_thread(browser); @@ -1843,7 +1936,7 @@ static int perf_evsel_menu__run(struct perf_evsel_menu *menu, { struct perf_evlist *evlist = menu->b.priv; struct perf_evsel *pos; - const char *ev_name, *title = "Available samples"; + const char *title = "Available samples"; int delay_secs = hbt ? hbt->refresh : 0; int key; @@ -1876,9 +1969,8 @@ browse_hists: */ if (hbt) hbt->timer(hbt->arg); - ev_name = perf_evsel__name(pos); key = perf_evsel__hists_browse(pos, nr_events, help, - ev_name, true, hbt, + true, hbt, menu->min_pcnt, menu->env); ui_browser__show_title(&menu->b, title); @@ -1982,10 +2074,9 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, single_entry: if (nr_entries == 1) { struct perf_evsel *first = perf_evlist__first(evlist); - const char *ev_name = perf_evsel__name(first); return perf_evsel__hists_browse(first, nr_entries, help, - ev_name, false, hbt, min_pcnt, + false, hbt, min_pcnt, env); } diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 90122abd3721..40af0acb4fe9 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -479,7 +479,7 @@ print_entries: if (h->ms.map == NULL && verbose > 1) { __map_groups__fprintf_maps(h->thread->mg, - MAP__FUNCTION, verbose, fp); + MAP__FUNCTION, fp); fprintf(fp, "%.10s end\n", graph_dotted_line); } } diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 48b6d3f50012..437ee09727e6 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -626,7 +626,7 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample) { - if (!symbol_conf.use_callchain) + if (!symbol_conf.use_callchain || sample->callchain == NULL) return 0; return callchain_append(he->callchain, &callchain_cursor, sample->period); } diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 8f84423a75da..da43619d6173 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -176,4 +176,17 @@ static inline void callchain_cursor_snapshot(struct callchain_cursor *dest, dest->first = src->curr; dest->nr -= src->pos; } + +#ifdef HAVE_SKIP_CALLCHAIN_IDX +extern int arch_skip_callchain_idx(struct machine *machine, + struct thread *thread, struct ip_callchain *chain); +#else +static inline int arch_skip_callchain_idx(struct machine *machine __maybe_unused, + struct thread *thread __maybe_unused, + struct ip_callchain *chain __maybe_unused) +{ + return -1; +} +#endif + #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c new file mode 100644 index 000000000000..c5d05ec17220 --- /dev/null +++ b/tools/perf/util/cloexec.c @@ -0,0 +1,57 @@ +#include "util.h" +#include "../perf.h" +#include "cloexec.h" +#include "asm/bug.h" + +static unsigned long flag = PERF_FLAG_FD_CLOEXEC; + +static int perf_flag_probe(void) +{ + /* use 'safest' configuration as used in perf_evsel__fallback() */ + struct perf_event_attr attr = { + .type = PERF_COUNT_SW_CPU_CLOCK, + .config = PERF_COUNT_SW_CPU_CLOCK, + }; + int fd; + int err; + + /* check cloexec flag */ + fd = sys_perf_event_open(&attr, 0, -1, -1, + PERF_FLAG_FD_CLOEXEC); + err = errno; + + if (fd >= 0) { + close(fd); + return 1; + } + + WARN_ONCE(err != EINVAL, + "perf_event_open(..., PERF_FLAG_FD_CLOEXEC) failed with unexpected error %d (%s)\n", + err, strerror(err)); + + /* not supported, confirm error related to PERF_FLAG_FD_CLOEXEC */ + fd = sys_perf_event_open(&attr, 0, -1, -1, 0); + err = errno; + + if (WARN_ONCE(fd < 0, + "perf_event_open(..., 0) failed unexpectedly with error %d (%s)\n", + err, strerror(err))) + return -1; + + close(fd); + + return 0; +} + +unsigned long perf_event_open_cloexec_flag(void) +{ + static bool probed; + + if (!probed) { + if (perf_flag_probe() <= 0) + flag = 0; + probed = true; + } + + return flag; +} diff --git a/tools/perf/util/cloexec.h b/tools/perf/util/cloexec.h new file mode 100644 index 000000000000..94a5a7d829d5 --- /dev/null +++ b/tools/perf/util/cloexec.h @@ -0,0 +1,6 @@ +#ifndef __PERF_CLOEXEC_H +#define __PERF_CLOEXEC_H + +unsigned long perf_event_open_cloexec_flag(void); + +#endif /* __PERF_CLOEXEC_H */ diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 24519e14ac56..1e5e2e5af6b1 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -350,6 +350,16 @@ static int perf_default_core_config(const char *var __maybe_unused, return 0; } +static int perf_ui_config(const char *var, const char *value) +{ + /* Add other config variables here. */ + if (!strcmp(var, "ui.show-headers")) { + symbol_conf.show_hist_headers = perf_config_bool(var, value); + return 0; + } + return 0; +} + int perf_default_config(const char *var, const char *value, void *dummy __maybe_unused) { @@ -359,6 +369,9 @@ int perf_default_config(const char *var, const char *value, if (!prefixcmp(var, "hist.")) return perf_hist_config(var, value); + if (!prefixcmp(var, "ui.")) + return perf_ui_config(var, value); + /* Add other config variables here. */ return 0; } diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 55de44ecebef..29d720cf5844 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -7,6 +7,7 @@ #include "data.h" #include "util.h" +#include "debug.h" static bool check_pipe(struct perf_data_file *file) { @@ -65,7 +66,7 @@ static int open_file_read(struct perf_data_file *file) goto out_close; if (!file->force && st.st_uid && (st.st_uid != geteuid())) { - pr_err("file %s not owned by current user or root\n", + pr_err("File %s not owned by current user or root (use -f to override)\n", file->path); goto out_close; } diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 299b55586502..71d419362634 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -16,11 +16,11 @@ int verbose; bool dump_trace = false, quiet = false; -static int _eprintf(int level, const char *fmt, va_list args) +static int _eprintf(int level, int var, const char *fmt, va_list args) { int ret = 0; - if (verbose >= level) { + if (var >= level) { if (use_browser >= 1) ui_helpline__vshow(fmt, args); else @@ -30,13 +30,13 @@ static int _eprintf(int level, const char *fmt, va_list args) return ret; } -int eprintf(int level, const char *fmt, ...) +int eprintf(int level, int var, const char *fmt, ...) { va_list args; int ret; va_start(args, fmt); - ret = _eprintf(level, fmt, args); + ret = _eprintf(level, var, fmt, args); va_end(args); return ret; @@ -51,9 +51,9 @@ void pr_stat(const char *fmt, ...) va_list args; va_start(args, fmt); - _eprintf(1, fmt, args); + _eprintf(1, verbose, fmt, args); va_end(args); - eprintf(1, "\n"); + eprintf(1, verbose, "\n"); } int dump_printf(const char *fmt, ...) @@ -105,3 +105,47 @@ void trace_event(union perf_event *event) } printf(".\n"); } + +static struct debug_variable { + const char *name; + int *ptr; +} debug_variables[] = { + { .name = "verbose", .ptr = &verbose }, + { .name = NULL, } +}; + +int perf_debug_option(const char *str) +{ + struct debug_variable *var = &debug_variables[0]; + char *vstr, *s = strdup(str); + int v = 1; + + vstr = strchr(s, '='); + if (vstr) + *vstr++ = 0; + + while (var->name) { + if (!strcmp(s, var->name)) + break; + var++; + } + + if (!var->name) { + pr_err("Unknown debug variable name '%s'\n", s); + free(s); + return -1; + } + + if (vstr) { + v = atoi(vstr); + /* + * Allow only values in range (0, 10), + * otherwise set 0. + */ + v = (v < 0) || (v > 10) ? 0 : v; + } + + *var->ptr = v; + free(s); + return 0; +} diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index 443694c36b03..89fb6b0f7ab2 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -11,6 +11,24 @@ extern int verbose; extern bool quiet, dump_trace; +#ifndef pr_fmt +#define pr_fmt(fmt) fmt +#endif + +#define pr_err(fmt, ...) \ + eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_warning(fmt, ...) \ + eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_info(fmt, ...) \ + eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_debug(fmt, ...) \ + eprintf(1, verbose, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_debugN(n, fmt, ...) \ + eprintf(n, verbose, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__) + int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2))); void trace_event(union perf_event *event); @@ -19,4 +37,8 @@ int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2))); void pr_stat(const char *fmt, ...); +int eprintf(int level, int var, const char *fmt, ...) __attribute__((format(printf, 3, 4))); + +int perf_debug_option(const char *str); + #endif /* __PERF_DEBUG_H */ diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 819f10414f08..90d02c661dd4 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -216,7 +216,7 @@ static int open_dso(struct dso *dso, struct machine *machine) { int fd = __open_dso(dso, machine); - if (fd > 0) { + if (fd >= 0) { dso__list_add(dso); /* * Check if we crossed the allowed number @@ -331,26 +331,44 @@ int dso__data_fd(struct dso *dso, struct machine *machine) }; int i = 0; + if (dso->data.status == DSO_DATA_STATUS_ERROR) + return -1; + if (dso->data.fd >= 0) - return dso->data.fd; + goto out; if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) { dso->data.fd = open_dso(dso, machine); - return dso->data.fd; + goto out; } do { - int fd; - dso->binary_type = binary_type_data[i++]; - fd = open_dso(dso, machine); - if (fd >= 0) - return dso->data.fd = fd; + dso->data.fd = open_dso(dso, machine); + if (dso->data.fd >= 0) + goto out; } while (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND); +out: + if (dso->data.fd >= 0) + dso->data.status = DSO_DATA_STATUS_OK; + else + dso->data.status = DSO_DATA_STATUS_ERROR; - return -EINVAL; + return dso->data.fd; +} + +bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by) +{ + u32 flag = 1 << by; + + if (dso->data.status_seen & flag) + return true; + + dso->data.status_seen |= flag; + + return false; } static void @@ -526,6 +544,28 @@ static int data_file_size(struct dso *dso) return 0; } +/** + * dso__data_size - Return dso data size + * @dso: dso object + * @machine: machine object + * + * Return: dso data size + */ +off_t dso__data_size(struct dso *dso, struct machine *machine) +{ + int fd; + + fd = dso__data_fd(dso, machine); + if (fd < 0) + return fd; + + if (data_file_size(dso)) + return -1; + + /* For now just estimate dso data size is close to file size */ + return dso->data.file_size; +} + static ssize_t data_read_offset(struct dso *dso, u64 offset, u8 *data, ssize_t size) { @@ -701,8 +741,10 @@ struct dso *dso__new(const char *name) dso->symbols[i] = dso->symbol_names[i] = RB_ROOT; dso->data.cache = RB_ROOT; dso->data.fd = -1; + dso->data.status = DSO_DATA_STATUS_UNKNOWN; dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND; dso->binary_type = DSO_BINARY_TYPE__NOT_FOUND; + dso->is_64_bit = (sizeof(void *) == 8); dso->loaded = 0; dso->rel = 0; dso->sorted_by_name = 0; @@ -898,3 +940,14 @@ size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp) return ret; } + +enum dso_type dso__type(struct dso *dso, struct machine *machine) +{ + int fd; + + fd = dso__data_fd(dso, machine); + if (fd < 0) + return DSO__TYPE_UNKNOWN; + + return dso__type_fd(fd); +} diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index ad553ba257bf..5e463c0964d4 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -5,6 +5,7 @@ #include <linux/rbtree.h> #include <stdbool.h> #include <linux/types.h> +#include <linux/bitops.h> #include "map.h" #include "build-id.h" @@ -40,6 +41,23 @@ enum dso_swap_type { DSO_SWAP__YES, }; +enum dso_data_status { + DSO_DATA_STATUS_ERROR = -1, + DSO_DATA_STATUS_UNKNOWN = 0, + DSO_DATA_STATUS_OK = 1, +}; + +enum dso_data_status_seen { + DSO_DATA_STATUS_SEEN_ITRACE, +}; + +enum dso_type { + DSO__TYPE_UNKNOWN, + DSO__TYPE_64BIT, + DSO__TYPE_32BIT, + DSO__TYPE_X32BIT, +}; + #define DSO__SWAP(dso, type, val) \ ({ \ type ____r = val; \ @@ -90,6 +108,7 @@ struct dso { u8 annotate_warned:1; u8 short_name_allocated:1; u8 long_name_allocated:1; + u8 is_64_bit:1; u8 sorted_by_name; u8 loaded; u8 rel; @@ -103,6 +122,8 @@ struct dso { struct { struct rb_root cache; int fd; + int status; + u32 status_seen; size_t file_size; struct list_head open_entry; } data; @@ -153,6 +174,7 @@ int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type t * The dso__data_* external interface provides following functions: * dso__data_fd * dso__data_close + * dso__data_size * dso__data_read_offset * dso__data_read_addr * @@ -190,11 +212,13 @@ int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type t int dso__data_fd(struct dso *dso, struct machine *machine); void dso__data_close(struct dso *dso); +off_t dso__data_size(struct dso *dso, struct machine *machine); ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, u64 offset, u8 *data, ssize_t size); ssize_t dso__data_read_addr(struct dso *dso, struct map *map, struct machine *machine, u64 addr, u8 *data, ssize_t size); +bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by); struct map *dso__new_map(const char *name); struct dso *dso__kernel_findnew(struct machine *machine, const char *name, @@ -229,4 +253,6 @@ static inline bool dso__is_kcore(struct dso *dso) void dso__free_a2l(struct dso *dso); +enum dso_type dso__type(struct dso *dso, struct machine *machine); + #endif /* __PERF_DSO */ diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index d0281bdfa582..1398c83d896d 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -603,7 +603,14 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp) { - return fprintf(fp, ": %s:%d\n", event->comm.comm, event->comm.tid); + const char *s; + + if (event->header.misc & PERF_RECORD_MISC_COMM_EXEC) + s = " exec"; + else + s = ""; + + return fprintf(fp, "%s: %s:%d\n", s, event->comm.comm, event->comm.tid); } int perf_event__process_comm(struct perf_tool *tool __maybe_unused, @@ -781,6 +788,7 @@ try_again: cpumode == PERF_RECORD_MISC_USER && machine && mg != &machine->kmaps) { mg = &machine->kmaps; + load_map = true; goto try_again; } } else { @@ -866,3 +874,45 @@ int perf_event__preprocess_sample(const union perf_event *event, return 0; } + +bool is_bts_event(struct perf_event_attr *attr) +{ + return attr->type == PERF_TYPE_HARDWARE && + (attr->config & PERF_COUNT_HW_BRANCH_INSTRUCTIONS) && + attr->sample_period == 1; +} + +bool sample_addr_correlates_sym(struct perf_event_attr *attr) +{ + if (attr->type == PERF_TYPE_SOFTWARE && + (attr->config == PERF_COUNT_SW_PAGE_FAULTS || + attr->config == PERF_COUNT_SW_PAGE_FAULTS_MIN || + attr->config == PERF_COUNT_SW_PAGE_FAULTS_MAJ)) + return true; + + if (is_bts_event(attr)) + return true; + + return false; +} + +void perf_event__preprocess_sample_addr(union perf_event *event, + struct perf_sample *sample, + struct machine *machine, + struct thread *thread, + struct addr_location *al) +{ + u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + + thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, + sample->addr, al); + if (!al->map) + thread__find_addr_map(thread, machine, cpumode, MAP__VARIABLE, + sample->addr, al); + + al->cpu = sample->cpu; + al->sym = NULL; + + if (al->map) + al->sym = map__find_symbol(al->map, al->addr, NULL); +} diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index e5dd40addb30..94d6976180da 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -288,6 +288,16 @@ int perf_event__preprocess_sample(const union perf_event *event, struct addr_location *al, struct perf_sample *sample); +struct thread; + +bool is_bts_event(struct perf_event_attr *attr); +bool sample_addr_correlates_sym(struct perf_event_attr *attr); +void perf_event__preprocess_sample_addr(union perf_event *event, + struct perf_sample *sample, + struct machine *machine, + struct thread *thread, + struct addr_location *al); + const char *perf_event__name(unsigned int id); size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 59ef2802fcf6..814e954c1318 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -606,12 +606,17 @@ static int perf_evlist__alloc_mmap(struct perf_evlist *evlist) return evlist->mmap != NULL ? 0 : -ENOMEM; } -static int __perf_evlist__mmap(struct perf_evlist *evlist, - int idx, int prot, int mask, int fd) +struct mmap_params { + int prot; + int mask; +}; + +static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx, + struct mmap_params *mp, int fd) { evlist->mmap[idx].prev = 0; - evlist->mmap[idx].mask = mask; - evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot, + evlist->mmap[idx].mask = mp->mask; + evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot, MAP_SHARED, fd, 0); if (evlist->mmap[idx].base == MAP_FAILED) { pr_debug2("failed to mmap perf event ring buffer, error %d\n", @@ -625,8 +630,8 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, } static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, - int prot, int mask, int cpu, int thread, - int *output) + struct mmap_params *mp, int cpu, + int thread, int *output) { struct perf_evsel *evsel; @@ -635,8 +640,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, if (*output == -1) { *output = fd; - if (__perf_evlist__mmap(evlist, idx, prot, mask, - *output) < 0) + if (__perf_evlist__mmap(evlist, idx, mp, *output) < 0) return -1; } else { if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0) @@ -651,8 +655,8 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, return 0; } -static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, - int mask) +static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, + struct mmap_params *mp) { int cpu, thread; int nr_cpus = cpu_map__nr(evlist->cpus); @@ -663,8 +667,8 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int output = -1; for (thread = 0; thread < nr_threads; thread++) { - if (perf_evlist__mmap_per_evsel(evlist, cpu, prot, mask, - cpu, thread, &output)) + if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu, + thread, &output)) goto out_unmap; } } @@ -677,8 +681,8 @@ out_unmap: return -1; } -static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, - int mask) +static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, + struct mmap_params *mp) { int thread; int nr_threads = thread_map__nr(evlist->threads); @@ -687,8 +691,8 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, for (thread = 0; thread < nr_threads; thread++) { int output = -1; - if (perf_evlist__mmap_per_evsel(evlist, thread, prot, mask, 0, - thread, &output)) + if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread, + &output)) goto out_unmap; } @@ -793,7 +797,9 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, struct perf_evsel *evsel; const struct cpu_map *cpus = evlist->cpus; const struct thread_map *threads = evlist->threads; - int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE), mask; + struct mmap_params mp = { + .prot = PROT_READ | (overwrite ? 0 : PROT_WRITE), + }; if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0) return -ENOMEM; @@ -804,7 +810,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, evlist->overwrite = overwrite; evlist->mmap_len = perf_evlist__mmap_size(pages); pr_debug("mmap size %zuB\n", evlist->mmap_len); - mask = evlist->mmap_len - page_size - 1; + mp.mask = evlist->mmap_len - page_size - 1; evlist__for_each(evlist, evsel) { if ((evsel->attr.read_format & PERF_FORMAT_ID) && @@ -814,9 +820,9 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, } if (cpu_map__empty(cpus)) - return perf_evlist__mmap_per_thread(evlist, prot, mask); + return perf_evlist__mmap_per_thread(evlist, &mp); - return perf_evlist__mmap_per_cpu(evlist, prot, mask); + return perf_evlist__mmap_per_cpu(evlist, &mp); } int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) @@ -1214,10 +1220,11 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused, "For your workloads it needs to be <= 1\nHint:\t"); } printed += scnprintf(buf + printed, size - printed, - "For system wide tracing it needs to be set to -1"); + "For system wide tracing it needs to be set to -1.\n"); printed += scnprintf(buf + printed, size - printed, - ".\nHint:\tThe current value is %d.", value); + "Hint:\tTry: 'sudo sh -c \"echo -1 > /proc/sys/kernel/perf_event_paranoid\"'\n" + "Hint:\tThe current value is %d.", value); break; default: scnprintf(buf, size, "%s", emsg); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 8606175fe1e8..21a373ebea22 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -29,6 +29,7 @@ static struct { bool sample_id_all; bool exclude_guest; bool mmap2; + bool cloexec; } perf_missing_features; #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) @@ -623,7 +624,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) attr->mmap_data = track; } - if (opts->call_graph_enabled) + if (opts->call_graph_enabled && !evsel->no_aux_samples) perf_evsel__config_callgraph(evsel, opts); if (target__has_cpu(&opts->target)) @@ -637,7 +638,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) target__has_cpu(&opts->target) || per_cpu)) perf_evsel__set_sample_bit(evsel, TIME); - if (opts->raw_samples) { + if (opts->raw_samples && !evsel->no_aux_samples) { perf_evsel__set_sample_bit(evsel, TIME); perf_evsel__set_sample_bit(evsel, RAW); perf_evsel__set_sample_bit(evsel, CPU); @@ -650,7 +651,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) attr->watermark = 0; attr->wakeup_events = 1; } - if (opts->branch_stack) { + if (opts->branch_stack && !evsel->no_aux_samples) { perf_evsel__set_sample_bit(evsel, BRANCH_STACK); attr->branch_sample_type = opts->branch_stack; } @@ -681,6 +682,11 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel) && !opts->initial_delay) attr->enable_on_exec = 1; + + if (evsel->immediate) { + attr->disabled = 0; + attr->enable_on_exec = 0; + } } int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) @@ -960,6 +966,7 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp) ret += PRINT_ATTR2(exclude_user, exclude_kernel); ret += PRINT_ATTR2(exclude_hv, exclude_idle); ret += PRINT_ATTR2(mmap, comm); + ret += PRINT_ATTR2(mmap2, comm_exec); ret += PRINT_ATTR2(freq, inherit_stat); ret += PRINT_ATTR2(enable_on_exec, task); ret += PRINT_ATTR2(watermark, precise_ip); @@ -967,7 +974,6 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp) ret += PRINT_ATTR2(exclude_host, exclude_guest); ret += PRINT_ATTR2N("excl.callchain_kern", exclude_callchain_kernel, "excl.callchain_user", exclude_callchain_user); - ret += PRINT_ATTR_U32(mmap2); ret += PRINT_ATTR_U32(wakeup_events); ret += PRINT_ATTR_U32(wakeup_watermark); @@ -989,7 +995,7 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, struct thread_map *threads) { int cpu, thread; - unsigned long flags = 0; + unsigned long flags = PERF_FLAG_FD_CLOEXEC; int pid = -1, err; enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE; @@ -998,11 +1004,13 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, return -ENOMEM; if (evsel->cgrp) { - flags = PERF_FLAG_PID_CGROUP; + flags |= PERF_FLAG_PID_CGROUP; pid = evsel->cgrp->fd; } fallback_missing_features: + if (perf_missing_features.cloexec) + flags &= ~(unsigned long)PERF_FLAG_FD_CLOEXEC; if (perf_missing_features.mmap2) evsel->attr.mmap2 = 0; if (perf_missing_features.exclude_guest) @@ -1071,7 +1079,10 @@ try_fallback: if (err != -EINVAL || cpu > 0 || thread > 0) goto out_close; - if (!perf_missing_features.mmap2 && evsel->attr.mmap2) { + if (!perf_missing_features.cloexec && (flags & PERF_FLAG_FD_CLOEXEC)) { + perf_missing_features.cloexec = true; + goto fallback_missing_features; + } else if (!perf_missing_features.mmap2 && evsel->attr.mmap2) { perf_missing_features.mmap2 = true; goto fallback_missing_features; } else if (!perf_missing_features.exclude_guest && @@ -1940,6 +1951,7 @@ int perf_evsel__fprintf(struct perf_evsel *evsel, if_print(mmap); if_print(mmap2); if_print(comm); + if_print(comm_exec); if_print(freq); if_print(inherit_stat); if_print(enable_on_exec); diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index a52e9a5bb2d0..d7f93ce0ebc1 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -83,6 +83,8 @@ struct perf_evsel { int is_pos; bool supported; bool needs_swap; + bool no_aux_samples; + bool immediate; /* parse modifier helper */ int exclude_GH; int nr_members; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 893f8e2df928..158c787ce0c4 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -200,6 +200,47 @@ static int write_buildid(const char *name, size_t name_len, u8 *build_id, return write_padded(fd, name, name_len + 1, len); } +static int __dsos__hit_all(struct list_head *head) +{ + struct dso *pos; + + list_for_each_entry(pos, head, node) + pos->hit = true; + + return 0; +} + +static int machine__hit_all_dsos(struct machine *machine) +{ + int err; + + err = __dsos__hit_all(&machine->kernel_dsos); + if (err) + return err; + + return __dsos__hit_all(&machine->user_dsos); +} + +int dsos__hit_all(struct perf_session *session) +{ + struct rb_node *nd; + int err; + + err = machine__hit_all_dsos(&session->machines.host); + if (err) + return err; + + for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { + struct machine *pos = rb_entry(nd, struct machine, rb_node); + + err = machine__hit_all_dsos(pos); + if (err) + return err; + } + + return 0; +} + static int __dsos__write_buildid_table(struct list_head *head, struct machine *machine, pid_t pid, u16 misc, int fd) @@ -215,9 +256,9 @@ static int __dsos__write_buildid_table(struct list_head *head, if (!pos->hit) continue; - if (is_vdso_map(pos->short_name)) { - name = (char *) VDSO__MAP_NAME; - name_len = sizeof(VDSO__MAP_NAME) + 1; + if (dso__is_vdso(pos)) { + name = pos->short_name; + name_len = pos->short_name_len + 1; } else if (dso__is_kcore(pos)) { machine__mmap_name(machine, nm, sizeof(nm)); name = nm; @@ -298,7 +339,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, len = scnprintf(filename, size, "%s%s%s", debugdir, slash ? "/" : "", - is_vdso ? VDSO__MAP_NAME : realname); + is_vdso ? DSO__NAME_VDSO : realname); if (mkdir_p(filename, 0755)) goto out_free; @@ -386,7 +427,7 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine, const char *debugdir) { bool is_kallsyms = dso->kernel && dso->long_name[0] != '/'; - bool is_vdso = is_vdso_map(dso->short_name); + bool is_vdso = dso__is_vdso(dso); const char *name = dso->long_name; char nm[PATH_MAX]; diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index d08cfe499404..8f5cbaea64a5 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -151,6 +151,8 @@ int perf_event__process_build_id(struct perf_tool *tool, struct perf_session *session); bool is_perf_magic(u64 magic); +int dsos__hit_all(struct perf_session *session); + /* * arch specific callback */ diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h index 9844c31b7c2b..09e8e7aea7c6 100644 --- a/tools/perf/util/include/linux/kernel.h +++ b/tools/perf/util/include/linux/kernel.h @@ -94,27 +94,6 @@ static inline int scnprintf(char * buf, size_t size, const char * fmt, ...) return (i >= ssize) ? (ssize - 1) : i; } -int eprintf(int level, - const char *fmt, ...) __attribute__((format(printf, 2, 3))); - -#ifndef pr_fmt -#define pr_fmt(fmt) fmt -#endif - -#define pr_err(fmt, ...) \ - eprintf(0, pr_fmt(fmt), ##__VA_ARGS__) -#define pr_warning(fmt, ...) \ - eprintf(0, pr_fmt(fmt), ##__VA_ARGS__) -#define pr_info(fmt, ...) \ - eprintf(0, pr_fmt(fmt), ##__VA_ARGS__) -#define pr_debug(fmt, ...) \ - eprintf(1, pr_fmt(fmt), ##__VA_ARGS__) -#define pr_debugN(n, fmt, ...) \ - eprintf(n, pr_fmt(fmt), ##__VA_ARGS__) -#define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__) -#define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__) -#define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__) - /* * This looks more complex than it should be. But we need to * get the type for the ~ right in round_down (it needs to be diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h new file mode 100644 index 000000000000..0b5a8cd2ee79 --- /dev/null +++ b/tools/perf/util/kvm-stat.h @@ -0,0 +1,140 @@ +#ifndef __PERF_KVM_STAT_H +#define __PERF_KVM_STAT_H + +#include "../perf.h" +#include "evsel.h" +#include "evlist.h" +#include "session.h" +#include "tool.h" +#include "stat.h" + +struct event_key { + #define INVALID_KEY (~0ULL) + u64 key; + int info; + struct exit_reasons_table *exit_reasons; +}; + +struct kvm_event_stats { + u64 time; + struct stats stats; +}; + +struct kvm_event { + struct list_head hash_entry; + struct rb_node rb; + + struct event_key key; + + struct kvm_event_stats total; + + #define DEFAULT_VCPU_NUM 8 + int max_vcpu; + struct kvm_event_stats *vcpu; +}; + +typedef int (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int); + +struct kvm_event_key { + const char *name; + key_cmp_fun key; +}; + +struct perf_kvm_stat; + +struct child_event_ops { + void (*get_key)(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key); + const char *name; +}; + +struct kvm_events_ops { + bool (*is_begin_event)(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key); + bool (*is_end_event)(struct perf_evsel *evsel, + struct perf_sample *sample, struct event_key *key); + struct child_event_ops *child_ops; + void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key, + char *decode); + const char *name; +}; + +struct exit_reasons_table { + unsigned long exit_code; + const char *reason; +}; + +#define EVENTS_BITS 12 +#define EVENTS_CACHE_SIZE (1UL << EVENTS_BITS) + +struct perf_kvm_stat { + struct perf_tool tool; + struct record_opts opts; + struct perf_evlist *evlist; + struct perf_session *session; + + const char *file_name; + const char *report_event; + const char *sort_key; + int trace_vcpu; + + struct exit_reasons_table *exit_reasons; + const char *exit_reasons_isa; + + struct kvm_events_ops *events_ops; + key_cmp_fun compare; + struct list_head kvm_events_cache[EVENTS_CACHE_SIZE]; + + u64 total_time; + u64 total_count; + u64 lost_events; + u64 duration; + + const char *pid_str; + struct intlist *pid_list; + + struct rb_root result; + + int timerfd; + unsigned int display_time; + bool live; +}; + +struct kvm_reg_events_ops { + const char *name; + struct kvm_events_ops *ops; +}; + +void exit_event_get_key(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key); +bool exit_event_begin(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key); +bool exit_event_end(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key); +void exit_event_decode_key(struct perf_kvm_stat *kvm, + struct event_key *key, + char *decode); + +bool kvm_exit_event(struct perf_evsel *evsel); +bool kvm_entry_event(struct perf_evsel *evsel); + +#define define_exit_reasons_table(name, symbols) \ + static struct exit_reasons_table name[] = { \ + symbols, { -1, NULL } \ + } + +/* + * arch specific callbacks and data structures + */ +int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid); + +extern const char * const kvm_events_tp[]; +extern struct kvm_reg_events_ops kvm_reg_events_ops[]; +extern const char * const kvm_skip_events[]; + +#endif /* __PERF_KVM_STAT_H */ diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index c73e1fc12e53..16bba9fff2c8 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -8,6 +8,7 @@ #include "sort.h" #include "strlist.h" #include "thread.h" +#include "vdso.h" #include <stdbool.h> #include <symbol/kallsyms.h> #include "unwind.h" @@ -23,6 +24,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) INIT_LIST_HEAD(&machine->dead_threads); machine->last_match = NULL; + machine->vdso_info = NULL; + machine->kmaps.machine = machine; machine->pid = pid; @@ -34,7 +37,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) return -ENOMEM; if (pid != HOST_KERNEL_ID) { - struct thread *thread = machine__findnew_thread(machine, 0, + struct thread *thread = machine__findnew_thread(machine, -1, pid); char comm[64]; @@ -45,6 +48,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) thread__set_comm(thread, comm, 0); } + machine->current_tid = NULL; + return 0; } @@ -103,7 +108,9 @@ void machine__exit(struct machine *machine) map_groups__exit(&machine->kmaps); dsos__delete(&machine->user_dsos); dsos__delete(&machine->kernel_dsos); + vdso__exit(machine); zfree(&machine->root_dir); + zfree(&machine->current_tid); } void machine__delete(struct machine *machine) @@ -272,6 +279,52 @@ void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size) return; } +static void machine__update_thread_pid(struct machine *machine, + struct thread *th, pid_t pid) +{ + struct thread *leader; + + if (pid == th->pid_ || pid == -1 || th->pid_ != -1) + return; + + th->pid_ = pid; + + if (th->pid_ == th->tid) + return; + + leader = machine__findnew_thread(machine, th->pid_, th->pid_); + if (!leader) + goto out_err; + + if (!leader->mg) + leader->mg = map_groups__new(); + + if (!leader->mg) + goto out_err; + + if (th->mg == leader->mg) + return; + + if (th->mg) { + /* + * Maps are created from MMAP events which provide the pid and + * tid. Consequently there never should be any maps on a thread + * with an unknown pid. Just print an error if there are. + */ + if (!map_groups__empty(th->mg)) + pr_err("Discarding thread maps for %d:%d\n", + th->pid_, th->tid); + map_groups__delete(th->mg); + } + + th->mg = map_groups__get(leader->mg); + + return; + +out_err: + pr_err("Failed to join map groups for %d:%d\n", th->pid_, th->tid); +} + static struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid, bool create) @@ -285,10 +338,10 @@ static struct thread *__machine__findnew_thread(struct machine *machine, * so most of the time we dont have to look up * the full rbtree: */ - if (machine->last_match && machine->last_match->tid == tid) { - if (pid && pid != machine->last_match->pid_) - machine->last_match->pid_ = pid; - return machine->last_match; + th = machine->last_match; + if (th && th->tid == tid) { + machine__update_thread_pid(machine, th, pid); + return th; } while (*p != NULL) { @@ -297,8 +350,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine, if (th->tid == tid) { machine->last_match = th; - if (pid && pid != th->pid_) - th->pid_ = pid; + machine__update_thread_pid(machine, th, pid); return th; } @@ -325,8 +377,10 @@ static struct thread *__machine__findnew_thread(struct machine *machine, * within thread__init_map_groups to find the thread * leader and that would screwed the rb tree. */ - if (thread__init_map_groups(th, machine)) + if (thread__init_map_groups(th, machine)) { + thread__delete(th); return NULL; + } } return th; @@ -1045,14 +1099,14 @@ int machine__process_mmap2_event(struct machine *machine, else type = MAP__FUNCTION; - map = map__new(&machine->user_dsos, event->mmap2.start, + map = map__new(machine, event->mmap2.start, event->mmap2.len, event->mmap2.pgoff, event->mmap2.pid, event->mmap2.maj, event->mmap2.min, event->mmap2.ino, event->mmap2.ino_generation, event->mmap2.prot, event->mmap2.flags, - event->mmap2.filename, type); + event->mmap2.filename, type, thread); if (map == NULL) goto out_problem; @@ -1095,11 +1149,11 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event else type = MAP__FUNCTION; - map = map__new(&machine->user_dsos, event->mmap.start, + map = map__new(machine, event->mmap.start, event->mmap.len, event->mmap.pgoff, event->mmap.pid, 0, 0, 0, 0, 0, 0, event->mmap.filename, - type); + type, thread); if (map == NULL) goto out_problem; @@ -1281,7 +1335,9 @@ static int machine__resolve_callchain_sample(struct machine *machine, u8 cpumode = PERF_RECORD_MISC_USER; int chain_nr = min(max_stack, (int)chain->nr); int i; + int j; int err; + int skip_idx __maybe_unused; callchain_cursor_reset(&callchain_cursor); @@ -1290,14 +1346,26 @@ static int machine__resolve_callchain_sample(struct machine *machine, return 0; } + /* + * Based on DWARF debug information, some architectures skip + * a callchain entry saved by the kernel. + */ + skip_idx = arch_skip_callchain_idx(machine, thread, chain); + for (i = 0; i < chain_nr; i++) { u64 ip; struct addr_location al; if (callchain_param.order == ORDER_CALLEE) - ip = chain->ips[i]; + j = i; else - ip = chain->ips[chain->nr - i - 1]; + j = chain->nr - i - 1; + +#ifdef HAVE_SKIP_CALLCHAIN_IDX + if (j == skip_idx) + continue; +#endif + ip = chain->ips[j]; if (ip >= PERF_CONTEXT_MAX) { switch (ip) { @@ -1420,3 +1488,46 @@ int __machine__synthesize_threads(struct machine *machine, struct perf_tool *too /* command specified */ return 0; } + +pid_t machine__get_current_tid(struct machine *machine, int cpu) +{ + if (cpu < 0 || cpu >= MAX_NR_CPUS || !machine->current_tid) + return -1; + + return machine->current_tid[cpu]; +} + +int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid, + pid_t tid) +{ + struct thread *thread; + + if (cpu < 0) + return -EINVAL; + + if (!machine->current_tid) { + int i; + + machine->current_tid = calloc(MAX_NR_CPUS, sizeof(pid_t)); + if (!machine->current_tid) + return -ENOMEM; + for (i = 0; i < MAX_NR_CPUS; i++) + machine->current_tid[i] = -1; + } + + if (cpu >= MAX_NR_CPUS) { + pr_err("Requested CPU %d too large. ", cpu); + pr_err("Consider raising MAX_NR_CPUS\n"); + return -EINVAL; + } + + machine->current_tid[cpu] = tid; + + thread = machine__findnew_thread(machine, pid, tid); + if (!thread) + return -ENOMEM; + + thread->cpu = cpu; + + return 0; +} diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index c8c74a119398..b972824e6294 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -20,6 +20,8 @@ union perf_event; extern const char *ref_reloc_sym_names[]; +struct vdso_info; + struct machine { struct rb_node rb_node; pid_t pid; @@ -28,11 +30,13 @@ struct machine { struct rb_root threads; struct list_head dead_threads; struct thread *last_match; + struct vdso_info *vdso_info; struct list_head user_dsos; struct list_head kernel_dsos; struct map_groups kmaps; struct map *vmlinux_maps[MAP__NR_TYPES]; symbol_filter_t symbol_filter; + pid_t *current_tid; }; static inline @@ -191,4 +195,8 @@ int machine__synthesize_threads(struct machine *machine, struct target *target, perf_event__process, data_mmap); } +pid_t machine__get_current_tid(struct machine *machine, int cpu); +int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid, + pid_t tid); + #endif /* __PERF_MACHINE_H */ diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 25c571f4cba6..31b8905dd863 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -12,6 +12,8 @@ #include "vdso.h" #include "build-id.h" #include "util.h" +#include "debug.h" +#include "machine.h" #include <linux/string.h> const char *map_type__name[MAP__NR_TYPES] = { @@ -136,10 +138,10 @@ void map__init(struct map *map, enum map_type type, map->erange_warned = false; } -struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, +struct map *map__new(struct machine *machine, u64 start, u64 len, u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino, u64 ino_gen, u32 prot, u32 flags, char *filename, - enum map_type type) + enum map_type type, struct thread *thread) { struct map *map = malloc(sizeof(*map)); @@ -172,9 +174,9 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, if (vdso) { pgoff = 0; - dso = vdso__dso_findnew(dsos__list); + dso = vdso__dso_findnew(machine, thread); } else - dso = __dsos__findnew(dsos__list, filename); + dso = __dsos__findnew(&machine->user_dsos, filename); if (dso == NULL) goto out_delete; @@ -454,6 +456,20 @@ void map_groups__exit(struct map_groups *mg) } } +bool map_groups__empty(struct map_groups *mg) +{ + int i; + + for (i = 0; i < MAP__NR_TYPES; ++i) { + if (maps__first(&mg->maps[i])) + return false; + if (!list_empty(&mg->removed_maps[i])) + return false; + } + + return true; +} + struct map_groups *map_groups__new(void) { struct map_groups *mg = malloc(sizeof(*mg)); @@ -554,8 +570,8 @@ int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter) return ams->sym ? 0 : -1; } -size_t __map_groups__fprintf_maps(struct map_groups *mg, - enum map_type type, int verbose, FILE *fp) +size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type, + FILE *fp) { size_t printed = fprintf(fp, "%s:\n", map_type__name[type]); struct rb_node *nd; @@ -573,17 +589,16 @@ size_t __map_groups__fprintf_maps(struct map_groups *mg, return printed; } -size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp) +static size_t map_groups__fprintf_maps(struct map_groups *mg, FILE *fp) { size_t printed = 0, i; for (i = 0; i < MAP__NR_TYPES; ++i) - printed += __map_groups__fprintf_maps(mg, i, verbose, fp); + printed += __map_groups__fprintf_maps(mg, i, fp); return printed; } static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg, - enum map_type type, - int verbose, FILE *fp) + enum map_type type, FILE *fp) { struct map *pos; size_t printed = 0; @@ -600,23 +615,23 @@ static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg, } static size_t map_groups__fprintf_removed_maps(struct map_groups *mg, - int verbose, FILE *fp) + FILE *fp) { size_t printed = 0, i; for (i = 0; i < MAP__NR_TYPES; ++i) - printed += __map_groups__fprintf_removed_maps(mg, i, verbose, fp); + printed += __map_groups__fprintf_removed_maps(mg, i, fp); return printed; } -size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp) +size_t map_groups__fprintf(struct map_groups *mg, FILE *fp) { - size_t printed = map_groups__fprintf_maps(mg, verbose, fp); + size_t printed = map_groups__fprintf_maps(mg, fp); printed += fprintf(fp, "Removed maps:\n"); - return printed + map_groups__fprintf_removed_maps(mg, verbose, fp); + return printed + map_groups__fprintf_removed_maps(mg, fp); } int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, - int verbose, FILE *fp) + FILE *fp) { struct rb_root *root = &mg->maps[map->type]; struct rb_node *next = rb_first(root); diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 7758c72522ef..2f83954af050 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -66,6 +66,7 @@ struct map_groups { struct map_groups *map_groups__new(void); void map_groups__delete(struct map_groups *mg); +bool map_groups__empty(struct map_groups *mg); static inline struct map_groups *map_groups__get(struct map_groups *mg) { @@ -103,6 +104,7 @@ u64 map__rip_2objdump(struct map *map, u64 rip); u64 map__objdump_2mem(struct map *map, u64 ip); struct symbol; +struct thread; /* map__for_each_symbol - iterate over the symbols in the given map * @@ -118,10 +120,10 @@ typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym); void map__init(struct map *map, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso); -struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, +struct map *map__new(struct machine *machine, u64 start, u64 len, u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino, u64 ino_gen, u32 prot, u32 flags, - char *filename, enum map_type type); + char *filename, enum map_type type, struct thread *thread); struct map *map__new2(u64 start, struct dso *dso, enum map_type type); void map__delete(struct map *map); struct map *map__clone(struct map *map); @@ -141,8 +143,8 @@ void map__fixup_end(struct map *map); void map__reloc_vmlinux(struct map *map); -size_t __map_groups__fprintf_maps(struct map_groups *mg, - enum map_type type, int verbose, FILE *fp); +size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type, + FILE *fp); void maps__insert(struct rb_root *maps, struct map *map); void maps__remove(struct rb_root *maps, struct map *map); struct map *maps__find(struct rb_root *maps, u64 addr); @@ -152,8 +154,7 @@ void map_groups__init(struct map_groups *mg); void map_groups__exit(struct map_groups *mg); int map_groups__clone(struct map_groups *mg, struct map_groups *parent, enum map_type type); -size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp); -size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp); +size_t map_groups__fprintf(struct map_groups *mg, FILE *fp); int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name, u64 addr); @@ -210,7 +211,7 @@ struct symbol *map_groups__find_function_by_name(struct map_groups *mg, } int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, - int verbose, FILE *fp); + FILE *fp); struct map *map_groups__find_by_name(struct map_groups *mg, enum map_type type, const char *name); diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h index d8dac8ac5f37..b59ba858e73d 100644 --- a/tools/perf/util/parse-options.h +++ b/tools/perf/util/parse-options.h @@ -98,6 +98,7 @@ struct option { parse_opt_cb *callback; intptr_t defval; bool *set; + void *data; }; #define check_vtype(v, type) ( BUILD_BUG_ON_ZERO(!__builtin_types_compatible_p(typeof(v), type)) + v ) @@ -131,6 +132,10 @@ struct option { { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l),\ .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\ .flags = PARSE_OPT_LASTARG_DEFAULT | PARSE_OPT_NOARG} +#define OPT_CALLBACK_OPTARG(s, l, v, d, a, h, f) \ + { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), \ + .value = (v), (a), .help = (h), .callback = (f), \ + .flags = PARSE_OPT_OPTARG, .data = (d) } /* parse_options() will filter out the processed options and leave the * non-option argments in argv[]. diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 98e304766416..dca9145d704c 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -26,7 +26,6 @@ #include <errno.h> #include <stdio.h> #include <unistd.h> -#include <getopt.h> #include <stdlib.h> #include <string.h> #include <stdarg.h> diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c index daa17aeb6c63..a126e6cc6e73 100644 --- a/tools/perf/util/pstack.c +++ b/tools/perf/util/pstack.c @@ -6,6 +6,7 @@ #include "util.h" #include "pstack.h" +#include "debug.h" #include <linux/kernel.h> #include <stdlib.h> diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 122669c18ff4..12aa9b0d0ba1 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -14,12 +14,12 @@ */ int verbose; -int eprintf(int level, const char *fmt, ...) +int eprintf(int level, int var, const char *fmt, ...) { va_list args; int ret = 0; - if (verbose >= level) { + if (var >= level) { va_start(args, fmt); ret = vfprintf(stderr, fmt, args); va_end(args); diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 049e0a09ccd3..fe8079edbdc1 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -4,6 +4,7 @@ #include "parse-events.h" #include <api/fs/fs.h> #include "util.h" +#include "cloexec.h" typedef void (*setup_probe_fn_t)(struct perf_evsel *evsel); @@ -11,6 +12,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) { struct perf_evlist *evlist; struct perf_evsel *evsel; + unsigned long flags = perf_event_open_cloexec_flag(); int err = -EAGAIN, fd; evlist = perf_evlist__new(); @@ -22,14 +24,14 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) evsel = perf_evlist__first(evlist); - fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0); + fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, flags); if (fd < 0) goto out_delete; close(fd); fn(evsel); - fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0); + fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, flags); if (fd < 0) { if (errno == EINVAL) err = -EINVAL; @@ -69,15 +71,26 @@ static void perf_probe_sample_identifier(struct perf_evsel *evsel) evsel->attr.sample_type |= PERF_SAMPLE_IDENTIFIER; } +static void perf_probe_comm_exec(struct perf_evsel *evsel) +{ + evsel->attr.comm_exec = 1; +} + bool perf_can_sample_identifier(void) { return perf_probe_api(perf_probe_sample_identifier); } +static bool perf_can_comm_exec(void) +{ + return perf_probe_api(perf_probe_comm_exec); +} + void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts) { struct perf_evsel *evsel; bool use_sample_identifier = false; + bool use_comm_exec; /* * Set the evsel leader links before we configure attributes, @@ -89,8 +102,13 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts) if (evlist->cpus->map[0] < 0) opts->no_inherit = true; - evlist__for_each(evlist, evsel) + use_comm_exec = perf_can_comm_exec(); + + evlist__for_each(evlist, evsel) { perf_evsel__config(evsel, opts); + if (!evsel->idx && use_comm_exec) + evsel->attr.comm_exec = 1; + } if (evlist->nr_entries > 1) { struct perf_evsel *first = perf_evlist__first(evlist); @@ -203,7 +221,8 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str) cpu = evlist->cpus->map[0]; } - fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0); + fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, + perf_event_open_cloexec_flag()); if (fd >= 0) { close(fd); ret = true; diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index af7da565a750..b2dba9c0a3a1 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -34,6 +34,7 @@ #include "../event.h" #include "../trace-event.h" #include "../evsel.h" +#include "../debug.h" void boot_Perf__Trace__Context(pTHX_ CV *cv); void boot_DynaLoader(pTHX_ CV *cv); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 1c419321f707..cbce2545da45 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -27,11 +27,13 @@ #include <errno.h> #include "../../perf.h" +#include "../debug.h" #include "../evsel.h" #include "../util.h" #include "../event.h" #include "../thread.h" #include "../trace-event.h" +#include "../machine.h" PyMODINIT_FUNC initperf_trace_context(void); @@ -50,10 +52,14 @@ static int zero_flag_atom; static PyObject *main_module, *main_dict; +static void handler_call_die(const char *handler_name) NORETURN; static void handler_call_die(const char *handler_name) { PyErr_Print(); Py_FatalError("problem in Python trace event handler"); + // Py_FatalError does not return + // but we have to make the compiler happy + abort(); } /* @@ -97,6 +103,7 @@ static void define_value(enum print_arg_type field_type, retval = PyObject_CallObject(handler, t); if (retval == NULL) handler_call_die(handler_name); + Py_DECREF(retval); } Py_DECREF(t); @@ -143,6 +150,7 @@ static void define_field(enum print_arg_type field_type, retval = PyObject_CallObject(handler, t); if (retval == NULL) handler_call_die(handler_name); + Py_DECREF(retval); } Py_DECREF(t); @@ -231,15 +239,133 @@ static inline struct event_format *find_cache_event(struct perf_evsel *evsel) return event; } +static PyObject *get_field_numeric_entry(struct event_format *event, + struct format_field *field, void *data) +{ + bool is_array = field->flags & FIELD_IS_ARRAY; + PyObject *obj, *list = NULL; + unsigned long long val; + unsigned int item_size, n_items, i; + + if (is_array) { + list = PyList_New(field->arraylen); + item_size = field->size / field->arraylen; + n_items = field->arraylen; + } else { + item_size = field->size; + n_items = 1; + } + + for (i = 0; i < n_items; i++) { + + val = read_size(event, data + field->offset + i * item_size, + item_size); + if (field->flags & FIELD_IS_SIGNED) { + if ((long long)val >= LONG_MIN && + (long long)val <= LONG_MAX) + obj = PyInt_FromLong(val); + else + obj = PyLong_FromLongLong(val); + } else { + if (val <= LONG_MAX) + obj = PyInt_FromLong(val); + else + obj = PyLong_FromUnsignedLongLong(val); + } + if (is_array) + PyList_SET_ITEM(list, i, obj); + } + if (is_array) + obj = list; + return obj; +} + + +static PyObject *python_process_callchain(struct perf_sample *sample, + struct perf_evsel *evsel, + struct addr_location *al) +{ + PyObject *pylist; + + pylist = PyList_New(0); + if (!pylist) + Py_FatalError("couldn't create Python list"); + + if (!symbol_conf.use_callchain || !sample->callchain) + goto exit; + + if (machine__resolve_callchain(al->machine, evsel, al->thread, + sample, NULL, NULL, + PERF_MAX_STACK_DEPTH) != 0) { + pr_err("Failed to resolve callchain. Skipping\n"); + goto exit; + } + callchain_cursor_commit(&callchain_cursor); + + + while (1) { + PyObject *pyelem; + struct callchain_cursor_node *node; + node = callchain_cursor_current(&callchain_cursor); + if (!node) + break; + + pyelem = PyDict_New(); + if (!pyelem) + Py_FatalError("couldn't create Python dictionary"); + + + pydict_set_item_string_decref(pyelem, "ip", + PyLong_FromUnsignedLongLong(node->ip)); + + if (node->sym) { + PyObject *pysym = PyDict_New(); + if (!pysym) + Py_FatalError("couldn't create Python dictionary"); + pydict_set_item_string_decref(pysym, "start", + PyLong_FromUnsignedLongLong(node->sym->start)); + pydict_set_item_string_decref(pysym, "end", + PyLong_FromUnsignedLongLong(node->sym->end)); + pydict_set_item_string_decref(pysym, "binding", + PyInt_FromLong(node->sym->binding)); + pydict_set_item_string_decref(pysym, "name", + PyString_FromStringAndSize(node->sym->name, + node->sym->namelen)); + pydict_set_item_string_decref(pyelem, "sym", pysym); + } + + if (node->map) { + struct map *map = node->map; + const char *dsoname = "[unknown]"; + if (map && map->dso && (map->dso->name || map->dso->long_name)) { + if (symbol_conf.show_kernel_path && map->dso->long_name) + dsoname = map->dso->long_name; + else if (map->dso->name) + dsoname = map->dso->name; + } + pydict_set_item_string_decref(pyelem, "dso", + PyString_FromString(dsoname)); + } + + callchain_cursor_advance(&callchain_cursor); + PyList_Append(pylist, pyelem); + Py_DECREF(pyelem); + } + +exit: + return pylist; +} + + static void python_process_tracepoint(struct perf_sample *sample, struct perf_evsel *evsel, struct thread *thread, struct addr_location *al) { - PyObject *handler, *retval, *context, *t, *obj, *dict = NULL; + PyObject *handler, *retval, *context, *t, *obj, *callchain; + PyObject *dict = NULL; static char handler_name[256]; struct format_field *field; - unsigned long long val; unsigned long s, ns; struct event_format *event; unsigned n = 0; @@ -280,18 +406,23 @@ static void python_process_tracepoint(struct perf_sample *sample, PyTuple_SetItem(t, n++, PyString_FromString(handler_name)); PyTuple_SetItem(t, n++, context); + /* ip unwinding */ + callchain = python_process_callchain(sample, evsel, al); + if (handler) { PyTuple_SetItem(t, n++, PyInt_FromLong(cpu)); PyTuple_SetItem(t, n++, PyInt_FromLong(s)); PyTuple_SetItem(t, n++, PyInt_FromLong(ns)); PyTuple_SetItem(t, n++, PyInt_FromLong(pid)); PyTuple_SetItem(t, n++, PyString_FromString(comm)); + PyTuple_SetItem(t, n++, callchain); } else { pydict_set_item_string_decref(dict, "common_cpu", PyInt_FromLong(cpu)); pydict_set_item_string_decref(dict, "common_s", PyInt_FromLong(s)); pydict_set_item_string_decref(dict, "common_ns", PyInt_FromLong(ns)); pydict_set_item_string_decref(dict, "common_pid", PyInt_FromLong(pid)); pydict_set_item_string_decref(dict, "common_comm", PyString_FromString(comm)); + pydict_set_item_string_decref(dict, "common_callchain", callchain); } for (field = event->format.fields; field; field = field->next) { if (field->flags & FIELD_IS_STRING) { @@ -303,20 +434,7 @@ static void python_process_tracepoint(struct perf_sample *sample, offset = field->offset; obj = PyString_FromString((char *)data + offset); } else { /* FIELD_IS_NUMERIC */ - val = read_size(event, data + field->offset, - field->size); - if (field->flags & FIELD_IS_SIGNED) { - if ((long long)val >= LONG_MIN && - (long long)val <= LONG_MAX) - obj = PyInt_FromLong(val); - else - obj = PyLong_FromLongLong(val); - } else { - if (val <= LONG_MAX) - obj = PyInt_FromLong(val); - else - obj = PyLong_FromUnsignedLongLong(val); - } + obj = get_field_numeric_entry(event, field, data); } if (handler) PyTuple_SetItem(t, n++, obj); @@ -324,6 +442,7 @@ static void python_process_tracepoint(struct perf_sample *sample, pydict_set_item_string_decref(dict, field->name, obj); } + if (!handler) PyTuple_SetItem(t, n++, dict); @@ -334,6 +453,7 @@ static void python_process_tracepoint(struct perf_sample *sample, retval = PyObject_CallObject(handler, t); if (retval == NULL) handler_call_die(handler_name); + Py_DECREF(retval); } else { handler = PyDict_GetItemString(main_dict, "trace_unhandled"); if (handler && PyCallable_Check(handler)) { @@ -341,6 +461,7 @@ static void python_process_tracepoint(struct perf_sample *sample, retval = PyObject_CallObject(handler, t); if (retval == NULL) handler_call_die("trace_unhandled"); + Py_DECREF(retval); } Py_DECREF(dict); } @@ -353,7 +474,7 @@ static void python_process_general_event(struct perf_sample *sample, struct thread *thread, struct addr_location *al) { - PyObject *handler, *retval, *t, *dict; + PyObject *handler, *retval, *t, *dict, *callchain, *dict_sample; static char handler_name[64]; unsigned n = 0; @@ -369,6 +490,10 @@ static void python_process_general_event(struct perf_sample *sample, if (!dict) Py_FatalError("couldn't create Python dictionary"); + dict_sample = PyDict_New(); + if (!dict_sample) + Py_FatalError("couldn't create Python dictionary"); + snprintf(handler_name, sizeof(handler_name), "%s", "process_event"); handler = PyDict_GetItemString(main_dict, handler_name); @@ -378,8 +503,21 @@ static void python_process_general_event(struct perf_sample *sample, pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel))); pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize( (const char *)&evsel->attr, sizeof(evsel->attr))); - pydict_set_item_string_decref(dict, "sample", PyString_FromStringAndSize( - (const char *)sample, sizeof(*sample))); + + pydict_set_item_string_decref(dict_sample, "pid", + PyInt_FromLong(sample->pid)); + pydict_set_item_string_decref(dict_sample, "tid", + PyInt_FromLong(sample->tid)); + pydict_set_item_string_decref(dict_sample, "cpu", + PyInt_FromLong(sample->cpu)); + pydict_set_item_string_decref(dict_sample, "ip", + PyLong_FromUnsignedLongLong(sample->ip)); + pydict_set_item_string_decref(dict_sample, "time", + PyLong_FromUnsignedLongLong(sample->time)); + pydict_set_item_string_decref(dict_sample, "period", + PyLong_FromUnsignedLongLong(sample->period)); + pydict_set_item_string_decref(dict, "sample", dict_sample); + pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize( (const char *)sample->raw_data, sample->raw_size)); pydict_set_item_string_decref(dict, "comm", @@ -393,6 +531,10 @@ static void python_process_general_event(struct perf_sample *sample, PyString_FromString(al->sym->name)); } + /* ip unwinding */ + callchain = python_process_callchain(sample, evsel, al); + pydict_set_item_string_decref(dict, "callchain", callchain); + PyTuple_SetItem(t, n++, dict); if (_PyTuple_Resize(&t, n) == -1) Py_FatalError("error resizing Python tuple"); @@ -400,6 +542,7 @@ static void python_process_general_event(struct perf_sample *sample, retval = PyObject_CallObject(handler, t); if (retval == NULL) handler_call_die(handler_name); + Py_DECREF(retval); exit: Py_DECREF(dict); Py_DECREF(t); @@ -521,8 +664,7 @@ static int python_stop_script(void) retval = PyObject_CallObject(handler, NULL); if (retval == NULL) handler_call_die("trace_end"); - else - Py_DECREF(retval); + Py_DECREF(retval); out: Py_XDECREF(main_dict); Py_XDECREF(main_module); @@ -589,6 +731,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "common_nsecs, "); fprintf(ofp, "common_pid, "); fprintf(ofp, "common_comm,\n\t"); + fprintf(ofp, "common_callchain, "); not_first = 0; count = 0; @@ -632,7 +775,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "%%u"); } - fprintf(ofp, "\\n\" %% \\\n\t\t("); + fprintf(ofp, "\" %% \\\n\t\t("); not_first = 0; count = 0; @@ -668,7 +811,15 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "%s", f->name); } - fprintf(ofp, "),\n\n"); + fprintf(ofp, ")\n\n"); + + fprintf(ofp, "\t\tfor node in common_callchain:"); + fprintf(ofp, "\n\t\t\tif 'sym' in node:"); + fprintf(ofp, "\n\t\t\t\tprint \"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name'])"); + fprintf(ofp, "\n\t\t\telse:"); + fprintf(ofp, "\n\t\t\t\tprint \"\t[%%x]\" %% (node['ip'])\n\n"); + fprintf(ofp, "\t\tprint \"\\n\"\n\n"); + } fprintf(ofp, "def trace_unhandled(event_name, context, " diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 64a186edc7be..88dfef70c13d 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -14,7 +14,6 @@ #include "util.h" #include "cpumap.h" #include "perf_regs.h" -#include "vdso.h" static int perf_session__open(struct perf_session *session) { @@ -156,7 +155,6 @@ void perf_session__delete(struct perf_session *session) if (session->file) perf_data_file__close(session->file); free(session); - vdso__exit(); } static int process_event_synth_tracing_data_stub(struct perf_tool *tool @@ -511,6 +509,7 @@ static int flush_sample_queue(struct perf_session *s, os->last_flush = iter->timestamp; list_del(&iter->list); list_add(&iter->list, &os->sample_cache); + os->nr_samples--; if (show_progress) ui_progress__update(&prog, 1); @@ -523,8 +522,6 @@ static int flush_sample_queue(struct perf_session *s, list_entry(head->prev, struct sample_queue, list); } - os->nr_samples = 0; - return 0; } @@ -994,8 +991,10 @@ static int perf_session_deliver_event(struct perf_session *session, } } -static int perf_session__process_user_event(struct perf_session *session, union perf_event *event, - struct perf_tool *tool, u64 file_offset) +static s64 perf_session__process_user_event(struct perf_session *session, + union perf_event *event, + struct perf_tool *tool, + u64 file_offset) { int fd = perf_data_file__fd(session->file); int err; @@ -1037,7 +1036,7 @@ static void event_swap(union perf_event *event, bool sample_id_all) swap(event, sample_id_all); } -static int perf_session__process_event(struct perf_session *session, +static s64 perf_session__process_event(struct perf_session *session, union perf_event *event, struct perf_tool *tool, u64 file_offset) @@ -1083,13 +1082,14 @@ void perf_event_header__bswap(struct perf_event_header *hdr) struct thread *perf_session__findnew(struct perf_session *session, pid_t pid) { - return machine__findnew_thread(&session->machines.host, 0, pid); + return machine__findnew_thread(&session->machines.host, -1, pid); } static struct thread *perf_session__register_idle_thread(struct perf_session *session) { - struct thread *thread = perf_session__findnew(session, 0); + struct thread *thread; + thread = machine__findnew_thread(&session->machines.host, 0, 0); if (thread == NULL || thread__set_comm(thread, "swapper", 0)) { pr_err("problem inserting idle task.\n"); thread = NULL; @@ -1147,7 +1147,7 @@ static int __perf_session__process_pipe_events(struct perf_session *session, union perf_event *event; uint32_t size, cur_size = 0; void *buf = NULL; - int skip = 0; + s64 skip = 0; u64 head; ssize_t err; void *p; @@ -1276,13 +1276,13 @@ int __perf_session__process_events(struct perf_session *session, u64 file_size, struct perf_tool *tool) { int fd = perf_data_file__fd(session->file); - u64 head, page_offset, file_offset, file_pos; + u64 head, page_offset, file_offset, file_pos, size; int err, mmap_prot, mmap_flags, map_idx = 0; size_t mmap_size; char *buf, *mmaps[NUM_MMAPS]; union perf_event *event; - uint32_t size; struct ui_progress prog; + s64 skip; perf_tool__fill_defaults(tool); @@ -1296,8 +1296,10 @@ int __perf_session__process_events(struct perf_session *session, ui_progress__init(&prog, file_size, "Processing events..."); mmap_size = MMAP_SIZE; - if (mmap_size > file_size) + if (mmap_size > file_size) { mmap_size = file_size; + session->one_mmap = true; + } memset(mmaps, 0, sizeof(mmaps)); @@ -1319,6 +1321,10 @@ remap: mmaps[map_idx] = buf; map_idx = (map_idx + 1) & (ARRAY_SIZE(mmaps) - 1); file_pos = file_offset + head; + if (session->one_mmap) { + session->one_mmap_addr = buf; + session->one_mmap_offset = file_offset; + } more: event = fetch_mmaped_event(session, head, mmap_size, buf); @@ -1337,7 +1343,8 @@ more: size = event->header.size; if (size < sizeof(struct perf_event_header) || - perf_session__process_event(session, event, tool, file_pos) < 0) { + (skip = perf_session__process_event(session, event, tool, file_pos)) + < 0) { pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", file_offset + head, event->header.size, event->header.type); @@ -1345,6 +1352,9 @@ more: goto out_err; } + if (skip) + size += skip; + head += size; file_pos += size; @@ -1364,6 +1374,7 @@ out_err: ui_progress__finish(); perf_session__warn_about_errors(session, tool); perf_session_free_sample_buffers(session); + session->one_mmap = false; return err; } diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 3140f8ae6148..0321013bd9fd 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -36,6 +36,9 @@ struct perf_session { struct trace_event tevent; struct events_stats stats; bool repipe; + bool one_mmap; + void *one_mmap_addr; + u64 one_mmap_offset; struct ordered_samples ordered_samples; struct perf_data_file *file; }; diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 1ec57dd82284..14e5a039bc45 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1215,7 +1215,7 @@ static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, hse = container_of(fmt, struct hpp_sort_entry, hpp); len = hists__col_len(&evsel->hists, hse->se->se_width_idx); - return scnprintf(hpp->buf, hpp->size, "%*s", len, hse->se->se_header); + return scnprintf(hpp->buf, hpp->size, "%-*s", len, hse->se->se_header); } static int __sort__hpp_width(struct perf_hpp_fmt *fmt, diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c index 6a0a13d07a28..283d3e73e2f2 100644 --- a/tools/perf/util/svghelper.c +++ b/tools/perf/util/svghelper.c @@ -30,6 +30,7 @@ static u64 turbo_frequency, max_freq; #define SLOT_MULT 30.0 #define SLOT_HEIGHT 25.0 +#define SLOT_HALF (SLOT_HEIGHT / 2) int svg_page_width = 1000; u64 svg_highlight; @@ -114,8 +115,14 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end) fprintf(svgfile, " rect { stroke-width: 1; }\n"); fprintf(svgfile, " rect.process { fill:rgb(180,180,180); fill-opacity:0.9; stroke-width:1; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.process2 { fill:rgb(180,180,180); fill-opacity:0.9; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); + fprintf(svgfile, " rect.process3 { fill:rgb(180,180,180); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.sample { fill:rgb( 0, 0,255); fill-opacity:0.8; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.sample_hi{ fill:rgb(255,128, 0); fill-opacity:0.8; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); + fprintf(svgfile, " rect.error { fill:rgb(255, 0, 0); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); + fprintf(svgfile, " rect.net { fill:rgb( 0,128, 0); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); + fprintf(svgfile, " rect.disk { fill:rgb( 0, 0,255); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); + fprintf(svgfile, " rect.sync { fill:rgb(128,128, 0); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); + fprintf(svgfile, " rect.poll { fill:rgb( 0,128,128); fill-opacity:0.2; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.blocked { fill:rgb(255, 0, 0); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.waiting { fill:rgb(224,214, 0); fill-opacity:0.8; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.WAITING { fill:rgb(255,214, 48); fill-opacity:0.6; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); @@ -132,12 +139,81 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end) fprintf(svgfile, " ]]>\n </style>\n</defs>\n"); } +static double normalize_height(double height) +{ + if (height < 0.25) + return 0.25; + else if (height < 0.50) + return 0.50; + else if (height < 0.75) + return 0.75; + else + return 0.100; +} + +void svg_ubox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges) +{ + double w = time2pixels(end) - time2pixels(start); + height = normalize_height(height); + + if (!svgfile) + return; + + fprintf(svgfile, "<g>\n"); + fprintf(svgfile, "<title>fd=%d error=%d merges=%d</title>\n", fd, err, merges); + fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n", + time2pixels(start), + w, + Yslot * SLOT_MULT, + SLOT_HALF * height, + type); + fprintf(svgfile, "</g>\n"); +} + +void svg_lbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges) +{ + double w = time2pixels(end) - time2pixels(start); + height = normalize_height(height); + + if (!svgfile) + return; + + fprintf(svgfile, "<g>\n"); + fprintf(svgfile, "<title>fd=%d error=%d merges=%d</title>\n", fd, err, merges); + fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n", + time2pixels(start), + w, + Yslot * SLOT_MULT + SLOT_HEIGHT - SLOT_HALF * height, + SLOT_HALF * height, + type); + fprintf(svgfile, "</g>\n"); +} + +void svg_fbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges) +{ + double w = time2pixels(end) - time2pixels(start); + height = normalize_height(height); + + if (!svgfile) + return; + + fprintf(svgfile, "<g>\n"); + fprintf(svgfile, "<title>fd=%d error=%d merges=%d</title>\n", fd, err, merges); + fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n", + time2pixels(start), + w, + Yslot * SLOT_MULT + SLOT_HEIGHT - SLOT_HEIGHT * height, + SLOT_HEIGHT * height, + type); + fprintf(svgfile, "</g>\n"); +} + void svg_box(int Yslot, u64 start, u64 end, const char *type) { if (!svgfile) return; - fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"%s\"/>\n", + fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n", time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT, type); } @@ -174,7 +250,7 @@ void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace) cpu, time_to_string(end - start)); if (backtrace) fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace); - fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"%s\"/>\n", + fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n", time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT, type); @@ -186,7 +262,7 @@ void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace) text_size = round_text_size(text_size); if (text_size > MIN_TEXT_SIZE) - fprintf(svgfile, "<text x=\"%1.8f\" y=\"%1.8f\" font-size=\"%1.8fpt\">%i</text>\n", + fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\" font-size=\"%.8fpt\">%i</text>\n", time2pixels(start), Yslot * SLOT_MULT + SLOT_HEIGHT - 1, text_size, cpu + 1); fprintf(svgfile, "</g>\n"); @@ -202,10 +278,10 @@ static char *time_to_string(u64 duration) return text; if (duration < 1000 * 1000) { /* less than 1 msec */ - sprintf(text, "%4.1f us", duration / 1000.0); + sprintf(text, "%.1f us", duration / 1000.0); return text; } - sprintf(text, "%4.1f ms", duration / 1000.0 / 1000); + sprintf(text, "%.1f ms", duration / 1000.0 / 1000); return text; } @@ -233,14 +309,14 @@ void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace) font_size = round_text_size(font_size); - fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), Yslot * SLOT_MULT); + fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\">\n", time2pixels(start), Yslot * SLOT_MULT); fprintf(svgfile, "<title>#%d waiting %s</title>\n", cpu, time_to_string(end - start)); if (backtrace) fprintf(svgfile, "<desc>Waiting on:\n%s</desc>\n", backtrace); - fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n", + fprintf(svgfile, "<rect x=\"0\" width=\"%.8f\" y=\"0\" height=\"%.1f\" class=\"%s\"/>\n", time2pixels(end)-time2pixels(start), SLOT_HEIGHT, style); if (font_size > MIN_TEXT_SIZE) - fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%1.8fpt\"> %s</text>\n", + fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%.8fpt\"> %s</text>\n", font_size, text); fprintf(svgfile, "</g>\n"); } @@ -289,16 +365,16 @@ void svg_cpu_box(int cpu, u64 __max_freq, u64 __turbo_freq) fprintf(svgfile, "<g>\n"); - fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"cpu\"/>\n", + fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"cpu\"/>\n", time2pixels(first_time), time2pixels(last_time)-time2pixels(first_time), cpu2y(cpu), SLOT_MULT+SLOT_HEIGHT); sprintf(cpu_string, "CPU %i", (int)cpu); - fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\">%s</text>\n", + fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\">%s</text>\n", 10+time2pixels(first_time), cpu2y(cpu) + SLOT_HEIGHT/2, cpu_string); - fprintf(svgfile, "<text transform=\"translate(%4.8f,%4.8f)\" font-size=\"1.25pt\">%s</text>\n", + fprintf(svgfile, "<text transform=\"translate(%.8f,%.8f)\" font-size=\"1.25pt\">%s</text>\n", 10+time2pixels(first_time), cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - 4, cpu_model()); fprintf(svgfile, "</g>\n"); @@ -319,11 +395,11 @@ void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const c else type = "sample"; - fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), cpu2y(cpu)); + fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\">\n", time2pixels(start), cpu2y(cpu)); fprintf(svgfile, "<title>%d %s running %s</title>\n", pid, name, time_to_string(end - start)); if (backtrace) fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace); - fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n", + fprintf(svgfile, "<rect x=\"0\" width=\"%.8f\" y=\"0\" height=\"%.1f\" class=\"%s\"/>\n", time2pixels(end)-time2pixels(start), SLOT_MULT+SLOT_HEIGHT, type); width = time2pixels(end)-time2pixels(start); if (width > 6) @@ -332,7 +408,7 @@ void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const c width = round_text_size(width); if (width > MIN_TEXT_SIZE) - fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%3.8fpt\">%s</text>\n", + fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%.8fpt\">%s</text>\n", width, name); fprintf(svgfile, "</g>\n"); @@ -353,7 +429,7 @@ void svg_cstate(int cpu, u64 start, u64 end, int type) type = 6; sprintf(style, "c%i", type); - fprintf(svgfile, "<rect class=\"%s\" x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\"/>\n", + fprintf(svgfile, "<rect class=\"%s\" x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\"/>\n", style, time2pixels(start), time2pixels(end)-time2pixels(start), cpu2y(cpu), SLOT_MULT+SLOT_HEIGHT); @@ -365,7 +441,7 @@ void svg_cstate(int cpu, u64 start, u64 end, int type) width = round_text_size(width); if (width > MIN_TEXT_SIZE) - fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"%3.8fpt\">C%i</text>\n", + fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\" font-size=\"%.8fpt\">C%i</text>\n", time2pixels(start), cpu2y(cpu)+width, width, type); fprintf(svgfile, "</g>\n"); @@ -407,9 +483,9 @@ void svg_pstate(int cpu, u64 start, u64 end, u64 freq) if (max_freq) height = freq * 1.0 / max_freq * (SLOT_HEIGHT + SLOT_MULT); height = 1 + cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - height; - fprintf(svgfile, "<line x1=\"%4.8f\" x2=\"%4.8f\" y1=\"%4.1f\" y2=\"%4.1f\" class=\"pstate\"/>\n", + fprintf(svgfile, "<line x1=\"%.8f\" x2=\"%.8f\" y1=\"%.1f\" y2=\"%.1f\" class=\"pstate\"/>\n", time2pixels(start), time2pixels(end), height, height); - fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"0.25pt\">%s</text>\n", + fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\" font-size=\"0.25pt\">%s</text>\n", time2pixels(start), height+0.9, HzToHuman(freq)); fprintf(svgfile, "</g>\n"); @@ -435,32 +511,32 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc if (row1 < row2) { if (row1) { - fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", + fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT, time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT + SLOT_MULT/32); if (desc2) - fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s ></text></g>\n", + fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s ></text></g>\n", time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT + SLOT_HEIGHT/48, desc2); } if (row2) { - fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", + fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", time2pixels(start), row2 * SLOT_MULT - SLOT_MULT/32, time2pixels(start), row2 * SLOT_MULT); if (desc1) - fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s ></text></g>\n", + fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s ></text></g>\n", time2pixels(start), row2 * SLOT_MULT - SLOT_MULT/32, desc1); } } else { if (row2) { - fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", + fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT, time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT + SLOT_MULT/32); if (desc1) - fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s <</text></g>\n", + fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s <</text></g>\n", time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT + SLOT_MULT/48, desc1); } if (row1) { - fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", + fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", time2pixels(start), row1 * SLOT_MULT - SLOT_MULT/32, time2pixels(start), row1 * SLOT_MULT); if (desc2) - fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s <</text></g>\n", + fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s <</text></g>\n", time2pixels(start), row1 * SLOT_MULT - SLOT_HEIGHT/32, desc2); } } @@ -468,7 +544,7 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc if (row2 > row1) height += SLOT_HEIGHT; if (row1) - fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(32,255,32)\"/>\n", + fprintf(svgfile, "<circle cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\" style=\"fill:rgb(32,255,32)\"/>\n", time2pixels(start), height); fprintf(svgfile, "</g>\n"); @@ -488,16 +564,16 @@ void svg_wakeline(u64 start, int row1, int row2, const char *backtrace) fprintf(svgfile, "<desc>%s</desc>\n", backtrace); if (row1 < row2) - fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", + fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT, time2pixels(start), row2 * SLOT_MULT); else - fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", + fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT, time2pixels(start), row1 * SLOT_MULT); height = row1 * SLOT_MULT; if (row2 > row1) height += SLOT_HEIGHT; - fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(32,255,32)\"/>\n", + fprintf(svgfile, "<circle cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\" style=\"fill:rgb(32,255,32)\"/>\n", time2pixels(start), height); fprintf(svgfile, "</g>\n"); @@ -515,9 +591,9 @@ void svg_interrupt(u64 start, int row, const char *backtrace) if (backtrace) fprintf(svgfile, "<desc>%s</desc>\n", backtrace); - fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(255,128,128)\"/>\n", + fprintf(svgfile, "<circle cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\" style=\"fill:rgb(255,128,128)\"/>\n", time2pixels(start), row * SLOT_MULT); - fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(255,128,128)\"/>\n", + fprintf(svgfile, "<circle cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\" style=\"fill:rgb(255,128,128)\"/>\n", time2pixels(start), row * SLOT_MULT + SLOT_HEIGHT); fprintf(svgfile, "</g>\n"); @@ -528,7 +604,7 @@ void svg_text(int Yslot, u64 start, const char *text) if (!svgfile) return; - fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\">%s</text>\n", + fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\">%s</text>\n", time2pixels(start), Yslot * SLOT_MULT+SLOT_HEIGHT/2, text); } @@ -537,12 +613,26 @@ static void svg_legenda_box(int X, const char *text, const char *style) double boxsize; boxsize = SLOT_HEIGHT / 2; - fprintf(svgfile, "<rect x=\"%i\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n", + fprintf(svgfile, "<rect x=\"%i\" width=\"%.8f\" y=\"0\" height=\"%.1f\" class=\"%s\"/>\n", X, boxsize, boxsize, style); - fprintf(svgfile, "<text transform=\"translate(%4.8f, %4.8f)\" font-size=\"%4.8fpt\">%s</text>\n", + fprintf(svgfile, "<text transform=\"translate(%.8f, %.8f)\" font-size=\"%.8fpt\">%s</text>\n", X + boxsize + 5, boxsize, 0.8 * boxsize, text); } +void svg_io_legenda(void) +{ + if (!svgfile) + return; + + fprintf(svgfile, "<g>\n"); + svg_legenda_box(0, "Disk", "disk"); + svg_legenda_box(100, "Network", "net"); + svg_legenda_box(200, "Sync", "sync"); + svg_legenda_box(300, "Poll", "poll"); + svg_legenda_box(400, "Error", "error"); + fprintf(svgfile, "</g>\n"); +} + void svg_legenda(void) { if (!svgfile) @@ -559,7 +649,7 @@ void svg_legenda(void) fprintf(svgfile, "</g>\n"); } -void svg_time_grid(void) +void svg_time_grid(double min_thickness) { u64 i; @@ -579,8 +669,10 @@ void svg_time_grid(void) color = 128; } - fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%" PRIu64 "\" style=\"stroke:rgb(%i,%i,%i);stroke-width:%1.3f\"/>\n", - time2pixels(i), SLOT_MULT/2, time2pixels(i), total_height, color, color, color, thickness); + if (thickness >= min_thickness) + fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%" PRIu64 "\" style=\"stroke:rgb(%i,%i,%i);stroke-width:%.3f\"/>\n", + time2pixels(i), SLOT_MULT/2, time2pixels(i), + total_height, color, color, color, thickness); i += 10000000; } diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h index e3aff5332e30..9292a5291445 100644 --- a/tools/perf/util/svghelper.h +++ b/tools/perf/util/svghelper.h @@ -4,6 +4,9 @@ #include <linux/types.h> extern void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end); +extern void svg_ubox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges); +extern void svg_lbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges); +extern void svg_fbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges); extern void svg_box(int Yslot, u64 start, u64 end, const char *type); extern void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace); extern void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace); @@ -16,7 +19,8 @@ extern void svg_cstate(int cpu, u64 start, u64 end, int type); extern void svg_pstate(int cpu, u64 start, u64 end, u64 freq); -extern void svg_time_grid(void); +extern void svg_time_grid(double min_thickness); +extern void svg_io_legenda(void); extern void svg_legenda(void); extern void svg_wakeline(u64 start, int row1, int row2, const char *backtrace); extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 6864661a79dd..d75349979e65 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -49,7 +49,8 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym) static inline int elf_sym__is_function(const GElf_Sym *sym) { - return elf_sym__type(sym) == STT_FUNC && + return (elf_sym__type(sym) == STT_FUNC || + elf_sym__type(sym) == STT_GNU_IFUNC) && sym->st_name != 0 && sym->st_shndx != SHN_UNDEF; } @@ -598,6 +599,8 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, goto out_elf_end; } + ss->is_64_bit = (gelf_getclass(elf) == ELFCLASS64); + ss->symtab = elf_section_by_name(elf, &ehdr, &ss->symshdr, ".symtab", NULL); if (ss->symshdr.sh_type != SHT_SYMTAB) @@ -619,7 +622,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, GElf_Shdr shdr; ss->adjust_symbols = (ehdr.e_type == ET_EXEC || ehdr.e_type == ET_REL || - is_vdso_map(dso->short_name) || + dso__is_vdso(dso) || elf_section_by_name(elf, &ehdr, &shdr, ".gnu.prelink_undo", NULL) != NULL); @@ -698,6 +701,7 @@ int dso__load_sym(struct dso *dso, struct map *map, bool remap_kernel = false, adjust_kernel_syms = false; dso->symtab_type = syms_ss->type; + dso->is_64_bit = syms_ss->is_64_bit; dso->rel = syms_ss->ehdr.e_type == ET_REL; /* @@ -1024,6 +1028,39 @@ int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data, return err; } +enum dso_type dso__type_fd(int fd) +{ + enum dso_type dso_type = DSO__TYPE_UNKNOWN; + GElf_Ehdr ehdr; + Elf_Kind ek; + Elf *elf; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) + goto out; + + ek = elf_kind(elf); + if (ek != ELF_K_ELF) + goto out_end; + + if (gelf_getclass(elf) == ELFCLASS64) { + dso_type = DSO__TYPE_64BIT; + goto out_end; + } + + if (gelf_getehdr(elf, &ehdr) == NULL) + goto out_end; + + if (ehdr.e_machine == EM_X86_64) + dso_type = DSO__TYPE_X32BIT; + else + dso_type = DSO__TYPE_32BIT; +out_end: + elf_end(elf); +out: + return dso_type; +} + static int copy_bytes(int from, off_t from_offs, int to, off_t to_offs, u64 len) { ssize_t r; diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index bd15f490d04f..c9541fea9514 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -288,6 +288,44 @@ int dso__synthesize_plt_symbols(struct dso *dso __maybe_unused, return 0; } +static int fd__is_64_bit(int fd) +{ + u8 e_ident[EI_NIDENT]; + + if (lseek(fd, 0, SEEK_SET)) + return -1; + + if (readn(fd, e_ident, sizeof(e_ident)) != sizeof(e_ident)) + return -1; + + if (memcmp(e_ident, ELFMAG, SELFMAG) || + e_ident[EI_VERSION] != EV_CURRENT) + return -1; + + return e_ident[EI_CLASS] == ELFCLASS64; +} + +enum dso_type dso__type_fd(int fd) +{ + Elf64_Ehdr ehdr; + int ret; + + ret = fd__is_64_bit(fd); + if (ret < 0) + return DSO__TYPE_UNKNOWN; + + if (ret) + return DSO__TYPE_64BIT; + + if (readn(fd, &ehdr, sizeof(ehdr)) != sizeof(ehdr)) + return DSO__TYPE_UNKNOWN; + + if (ehdr.e_machine == EM_X86_64) + return DSO__TYPE_X32BIT; + + return DSO__TYPE_32BIT; +} + int dso__load_sym(struct dso *dso, struct map *map __maybe_unused, struct symsrc *ss, struct symsrc *runtime_ss __maybe_unused, @@ -295,6 +333,11 @@ int dso__load_sym(struct dso *dso, struct map *map __maybe_unused, int kmodule __maybe_unused) { unsigned char *build_id[BUILD_ID_SIZE]; + int ret; + + ret = fd__is_64_bit(ss->fd); + if (ret >= 0) + dso->is_64_bit = ret; if (filename__read_build_id(ss->name, build_id, BUILD_ID_SIZE) > 0) { dso__set_build_id(dso, build_id); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 7b9096f29cdb..eb06746b06b2 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -34,6 +34,7 @@ struct symbol_conf symbol_conf = { .annotate_src = true, .demangle = true, .cumulate_callchain = true, + .show_hist_headers = true, .symfs = "", }; @@ -341,6 +342,16 @@ static struct symbol *symbols__first(struct rb_root *symbols) return NULL; } +static struct symbol *symbols__next(struct symbol *sym) +{ + struct rb_node *n = rb_next(&sym->rb_node); + + if (n) + return rb_entry(n, struct symbol, rb_node); + + return NULL; +} + struct symbol_name_rb_node { struct rb_node rb_node; struct symbol sym; @@ -411,11 +422,16 @@ struct symbol *dso__find_symbol(struct dso *dso, return symbols__find(&dso->symbols[type], addr); } -static struct symbol *dso__first_symbol(struct dso *dso, enum map_type type) +struct symbol *dso__first_symbol(struct dso *dso, enum map_type type) { return symbols__first(&dso->symbols[type]); } +struct symbol *dso__next_symbol(struct symbol *sym) +{ + return symbols__next(sym); +} + struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, const char *name) { @@ -1064,6 +1080,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, &is_64_bit); if (err) goto out_err; + dso->is_64_bit = is_64_bit; if (list_empty(&md.maps)) { err = -EINVAL; @@ -1662,6 +1679,7 @@ do_kallsyms: free(kallsyms_allocated_filename); if (err > 0 && !dso__is_kcore(dso)) { + dso->binary_type = DSO_BINARY_TYPE__KALLSYMS; dso__set_long_name(dso, "[kernel.kallsyms]", false); map__fixup_start(map); map__fixup_end(map); @@ -1709,6 +1727,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map, if (err > 0) pr_debug("Using %s for symbols\n", kallsyms_filename); if (err > 0 && !dso__is_kcore(dso)) { + dso->binary_type = DSO_BINARY_TYPE__GUEST_KALLSYMS; machine__mmap_name(machine, path, sizeof(path)); dso__set_long_name(dso, strdup(path), true); map__fixup_start(map); diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 615c752dd767..e7295e93cff9 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -118,7 +118,8 @@ struct symbol_conf { annotate_src, event_group, demangle, - filter_relative; + filter_relative, + show_hist_headers; const char *vmlinux_name, *kallsyms_name, *source_prefix, @@ -215,6 +216,7 @@ struct symsrc { GElf_Shdr dynshdr; bool adjust_symbols; + bool is_64_bit; #endif }; @@ -238,6 +240,11 @@ struct symbol *dso__find_symbol(struct dso *dso, enum map_type type, struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, const char *name); +struct symbol *dso__first_symbol(struct dso *dso, enum map_type type); +struct symbol *dso__next_symbol(struct symbol *sym); + +enum dso_type dso__type_fd(int fd); + int filename__read_build_id(const char *filename, void *bf, size_t size); int sysfs__read_build_id(const char *filename, void *bf, size_t size); int modules__parse(const char *filename, void *arg, diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 2fde0d5e40b5..12c7a253a63c 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -13,7 +13,7 @@ int thread__init_map_groups(struct thread *thread, struct machine *machine) struct thread *leader; pid_t pid = thread->pid_; - if (pid == thread->tid) { + if (pid == thread->tid || pid == -1) { thread->mg = map_groups__new(); } else { leader = machine__findnew_thread(machine, pid, pid); @@ -34,6 +34,7 @@ struct thread *thread__new(pid_t pid, pid_t tid) thread->pid_ = pid; thread->tid = tid; thread->ppid = -1; + thread->cpu = -1; INIT_LIST_HEAD(&thread->comm_list); comm_str = malloc(32); @@ -60,8 +61,10 @@ void thread__delete(struct thread *thread) { struct comm *comm, *tmp; - map_groups__put(thread->mg); - thread->mg = NULL; + if (thread->mg) { + map_groups__put(thread->mg); + thread->mg = NULL; + } list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) { list_del(&comm->list); comm__free(comm); @@ -127,12 +130,12 @@ int thread__comm_len(struct thread *thread) size_t thread__fprintf(struct thread *thread, FILE *fp) { return fprintf(fp, "Thread %d %s\n", thread->tid, thread__comm_str(thread)) + - map_groups__fprintf(thread->mg, verbose, fp); + map_groups__fprintf(thread->mg, fp); } void thread__insert_map(struct thread *thread, struct map *map) { - map_groups__fixup_overlappings(thread->mg, map, verbose, stderr); + map_groups__fixup_overlappings(thread->mg, map, stderr); map_groups__insert(thread->mg, map); } diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 3c0c2724f82c..716b7723cce2 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -17,6 +17,7 @@ struct thread { pid_t pid_; /* Not all tools update this */ pid_t tid; pid_t ppid; + int cpu; char shortname[3]; bool comm_set; bool dead; /* if set thread has exited */ diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index 7e6fcfe8b438..eb72716017ac 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -40,6 +40,7 @@ #include "trace-event.h" #include <api/fs/debugfs.h> #include "evsel.h" +#include "debug.h" #define VERSION "0.5" @@ -191,12 +192,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps) strcmp(dent->d_name, "..") == 0 || !name_in_tp_list(dent->d_name, tps)) continue; - format = malloc(strlen(sys) + strlen(dent->d_name) + 10); - if (!format) { + if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) { err = -ENOMEM; goto out; } - sprintf(format, "%s/%s/format", sys, dent->d_name); ret = stat(format, &st); free(format); if (ret < 0) @@ -217,12 +216,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps) strcmp(dent->d_name, "..") == 0 || !name_in_tp_list(dent->d_name, tps)) continue; - format = malloc(strlen(sys) + strlen(dent->d_name) + 10); - if (!format) { + if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) { err = -ENOMEM; goto out; } - sprintf(format, "%s/%s/format", sys, dent->d_name); ret = stat(format, &st); if (ret >= 0) { @@ -317,12 +314,10 @@ static int record_event_files(struct tracepoint_path *tps) strcmp(dent->d_name, "ftrace") == 0 || !system_in_tp_list(dent->d_name, tps)) continue; - sys = malloc(strlen(path) + strlen(dent->d_name) + 2); - if (!sys) { + if (asprintf(&sys, "%s/%s", path, dent->d_name) < 0) { err = -ENOMEM; goto out; } - sprintf(sys, "%s/%s", path, dent->d_name); ret = stat(sys, &st); if (ret >= 0) { ssize_t size = strlen(dent->d_name) + 1; diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index e113e180c48f..54d9e9b548a8 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -22,7 +22,6 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> -#include <getopt.h> #include <stdarg.h> #include <sys/types.h> #include <sys/stat.h> @@ -36,6 +35,7 @@ #include "../perf.h" #include "util.h" #include "trace-event.h" +#include "debug.h" static int input_fd; diff --git a/tools/perf/util/tsc.c b/tools/perf/util/tsc.c new file mode 100644 index 000000000000..4d4210d4e13d --- /dev/null +++ b/tools/perf/util/tsc.c @@ -0,0 +1,30 @@ +#include <linux/compiler.h> +#include <linux/types.h> + +#include "tsc.h" + +u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc) +{ + u64 t, quot, rem; + + t = ns - tc->time_zero; + quot = t / tc->time_mult; + rem = t % tc->time_mult; + return (quot << tc->time_shift) + + (rem << tc->time_shift) / tc->time_mult; +} + +u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc) +{ + u64 quot, rem; + + quot = cyc >> tc->time_shift; + rem = cyc & ((1 << tc->time_shift) - 1); + return tc->time_zero + quot * tc->time_mult + + ((rem * tc->time_mult) >> tc->time_shift); +} + +u64 __weak rdtsc(void) +{ + return 0; +} diff --git a/tools/perf/util/tsc.h b/tools/perf/util/tsc.h new file mode 100644 index 000000000000..a8b78f1b3243 --- /dev/null +++ b/tools/perf/util/tsc.h @@ -0,0 +1,12 @@ +#ifndef __PERF_TSC_H +#define __PERF_TSC_H + +#include <linux/types.h> + +#include "../arch/x86/util/tsc.h" + +u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc); +u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc); +u64 rdtsc(void); + +#endif diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 5ec80a575b50..7419768c38b1 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -3,6 +3,7 @@ #include <elfutils/libdwfl.h> #include <inttypes.h> #include <errno.h> +#include "debug.h" #include "unwind.h" #include "unwind-libdw.h" #include "machine.h" diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index 25578b98f5c5..92b56db52471 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -30,6 +30,7 @@ #include "unwind.h" #include "symbol.h" #include "util.h" +#include "debug.h" extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 95aefa78bb07..e52e7461911b 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -1,5 +1,6 @@ #include "../perf.h" #include "util.h" +#include "debug.h" #include <api/fs/fs.h> #include <sys/mman.h> #ifdef HAVE_BACKTRACE_SUPPORT @@ -333,12 +334,9 @@ const char *find_tracing_dir(void) if (!debugfs) return NULL; - tracing = malloc(strlen(debugfs) + 9); - if (!tracing) + if (asprintf(&tracing, "%s/tracing", debugfs) < 0) return NULL; - sprintf(tracing, "%s/tracing", debugfs); - tracing_found = 1; return tracing; } @@ -352,11 +350,9 @@ char *get_tracing_file(const char *name) if (!tracing) return NULL; - file = malloc(strlen(tracing) + strlen(name) + 2); - if (!file) + if (asprintf(&file, "%s/%s", tracing, name) < 0) return NULL; - sprintf(file, "%s/%s", tracing, name); return file; } diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c index 0ddb3b8a89ec..adca69384fcc 100644 --- a/tools/perf/util/vdso.c +++ b/tools/perf/util/vdso.c @@ -11,10 +11,34 @@ #include "vdso.h" #include "util.h" #include "symbol.h" +#include "machine.h" #include "linux/string.h" +#include "debug.h" -static bool vdso_found; -static char vdso_file[] = "/tmp/perf-vdso.so-XXXXXX"; +#define VDSO__TEMP_FILE_NAME "/tmp/perf-vdso.so-XXXXXX" + +struct vdso_file { + bool found; + bool error; + char temp_file_name[sizeof(VDSO__TEMP_FILE_NAME)]; + const char *dso_name; +}; + +struct vdso_info { + struct vdso_file vdso; +}; + +static struct vdso_info *vdso_info__new(void) +{ + static const struct vdso_info vdso_info_init = { + .vdso = { + .temp_file_name = VDSO__TEMP_FILE_NAME, + .dso_name = DSO__NAME_VDSO, + }, + }; + + return memdup(&vdso_info_init, sizeof(vdso_info_init)); +} static int find_vdso_map(void **start, void **end) { @@ -47,7 +71,7 @@ static int find_vdso_map(void **start, void **end) return !found; } -static char *get_file(void) +static char *get_file(struct vdso_file *vdso_file) { char *vdso = NULL; char *buf = NULL; @@ -55,10 +79,10 @@ static char *get_file(void) size_t size; int fd; - if (vdso_found) - return vdso_file; + if (vdso_file->found) + return vdso_file->temp_file_name; - if (find_vdso_map(&start, &end)) + if (vdso_file->error || find_vdso_map(&start, &end)) return NULL; size = end - start; @@ -67,45 +91,78 @@ static char *get_file(void) if (!buf) return NULL; - fd = mkstemp(vdso_file); + fd = mkstemp(vdso_file->temp_file_name); if (fd < 0) goto out; if (size == (size_t) write(fd, buf, size)) - vdso = vdso_file; + vdso = vdso_file->temp_file_name; close(fd); out: free(buf); - vdso_found = (vdso != NULL); + vdso_file->found = (vdso != NULL); + vdso_file->error = !vdso_file->found; return vdso; } -void vdso__exit(void) +void vdso__exit(struct machine *machine) { - if (vdso_found) - unlink(vdso_file); + struct vdso_info *vdso_info = machine->vdso_info; + + if (!vdso_info) + return; + + if (vdso_info->vdso.found) + unlink(vdso_info->vdso.temp_file_name); + + zfree(&machine->vdso_info); } -struct dso *vdso__dso_findnew(struct list_head *head) +static struct dso *vdso__new(struct machine *machine, const char *short_name, + const char *long_name) { - struct dso *dso = dsos__find(head, VDSO__MAP_NAME, true); + struct dso *dso; + dso = dso__new(short_name); + if (dso != NULL) { + dsos__add(&machine->user_dsos, dso); + dso__set_long_name(dso, long_name, false); + } + + return dso; +} + +struct dso *vdso__dso_findnew(struct machine *machine, + struct thread *thread __maybe_unused) +{ + struct vdso_info *vdso_info; + struct dso *dso; + + if (!machine->vdso_info) + machine->vdso_info = vdso_info__new(); + + vdso_info = machine->vdso_info; + if (!vdso_info) + return NULL; + + dso = dsos__find(&machine->user_dsos, DSO__NAME_VDSO, true); if (!dso) { char *file; - file = get_file(); + file = get_file(&vdso_info->vdso); if (!file) return NULL; - dso = dso__new(VDSO__MAP_NAME); - if (dso != NULL) { - dsos__add(head, dso); - dso__set_long_name(dso, file, false); - } + dso = vdso__new(machine, DSO__NAME_VDSO, file); } return dso; } + +bool dso__is_vdso(struct dso *dso) +{ + return !strcmp(dso->short_name, DSO__NAME_VDSO); +} diff --git a/tools/perf/util/vdso.h b/tools/perf/util/vdso.h index 0f76e7caf6f8..af9d6929a215 100644 --- a/tools/perf/util/vdso.h +++ b/tools/perf/util/vdso.h @@ -7,12 +7,21 @@ #define VDSO__MAP_NAME "[vdso]" +#define DSO__NAME_VDSO "[vdso]" + static inline bool is_vdso_map(const char *filename) { return !strcmp(filename, VDSO__MAP_NAME); } -struct dso *vdso__dso_findnew(struct list_head *head); -void vdso__exit(void); +struct dso; + +bool dso__is_vdso(struct dso *dso); + +struct machine; +struct thread; + +struct dso *vdso__dso_findnew(struct machine *machine, struct thread *thread); +void vdso__exit(struct machine *machine); #endif /* __PERF_VDSO__ */ diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh index ee1f6cae3d70..3f6c9b78d177 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh @@ -54,10 +54,16 @@ do if test -f "$i/qemu-cmd" then print_bug qemu failed + echo " $i" + elif test -f "$i/buildonly" + then + echo Build-only run, no boot/test + configcheck.sh $i/.config $i/ConfigFragment + parse-build.sh $i/Make.out $configfile else print_bug Build failed + echo " $i" fi - echo " $i" fi done done 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 27e544e29510..0f69dcbf9def 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -42,6 +42,7 @@ grace=120 T=/tmp/kvm-test-1-run.sh.$$ trap 'rm -rf $T' 0 +touch $T . $KVM/bin/functions.sh . $KVPATH/ver_functions.sh @@ -131,7 +132,10 @@ boot_args=$6 cd $KVM kstarttime=`awk 'BEGIN { print systime() }' < /dev/null` -echo ' ---' `date`: Starting kernel +if test -z "$TORTURE_BUILDONLY" +then + echo ' ---' `date`: Starting kernel +fi # Generate -smp qemu argument. qemu_args="-nographic $qemu_args" @@ -157,12 +161,13 @@ boot_args="`configfrag_boot_params "$boot_args" "$config_template"`" # Generate kernel-version-specific boot parameters boot_args="`per_version_boot_params "$boot_args" $builddir/.config $seconds`" -echo $QEMU $qemu_args -m 512 -kernel $builddir/$BOOT_IMAGE -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd if test -n "$TORTURE_BUILDONLY" then echo Build-only run specified, boot/test omitted. + touch $resdir/buildonly exit 0 fi +echo $QEMU $qemu_args -m 512 -kernel $builddir/$BOOT_IMAGE -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd ( $QEMU $qemu_args -m 512 -kernel $builddir/$BOOT_IMAGE -append "$qemu_append $boot_args"; echo $? > $resdir/qemu-retval ) & qemu_pid=$! commandcompleted=0 diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index 40285c58653e..589e9c38413b 100644 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -340,12 +340,18 @@ function dump(first, pastlast) for (j = 1; j < jn; j++) { builddir=KVM "/b" j print "rm -f " builddir ".ready" - print "echo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date`"; - print "echo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date` >> " rd "/log"; + print "if test -z \"$TORTURE_BUILDONLY\"" + print "then" + print "\techo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date`"; + print "\techo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date` >> " rd "/log"; + print "fi" } print "wait" - print "echo ---- All kernel runs complete. `date`"; - print "echo ---- All kernel runs complete. `date` >> " rd "/log"; + print "if test -z \"$TORTURE_BUILDONLY\"" + print "then" + print "\techo ---- All kernel runs complete. `date`"; + print "\techo ---- All kernel runs complete. `date` >> " rd "/log"; + print "fi" for (j = 1; j < jn; j++) { builddir=KVM "/b" j print "echo ----", cfr[j], cpusr[j] ovf ": Build/run results:"; @@ -385,10 +391,7 @@ echo echo echo " --- `date` Test summary:" echo Results directory: $resdir/$ds -if test -z "$TORTURE_BUILDONLY" -then - kvm-recheck.sh $resdir/$ds -fi +kvm-recheck.sh $resdir/$ds ___EOF___ if test "$dryrun" = script @@ -403,7 +406,7 @@ then sed -e 's/:.*$//' -e 's/^echo //' exit 0 else - # Not a dryru, so run the script. + # Not a dryrun, so run the script. sh $T/script fi diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 index 9c827ec59a97..063b7079c621 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 @@ -15,7 +15,6 @@ CONFIG_RCU_FANOUT_EXACT=n CONFIG_RCU_NOCB_CPU=y CONFIG_RCU_NOCB_CPU_ZERO=y CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_PROVE_RCU_DELAY=n CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_RCU_BOOST=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 b/tools/testing/selftests/rcutorture/configs/rcu/TREE02 index 1a777b5f68b5..ea119ba2f7d4 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02 @@ -18,7 +18,6 @@ CONFIG_RCU_FANOUT_EXACT=n CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=n -CONFIG_PROVE_RCU_DELAY=n CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_CPU_STALL_VERBOSE=y CONFIG_RCU_BOOST=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T index 61c8d9ce5bb2..19cf9485f48a 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T @@ -18,7 +18,6 @@ CONFIG_RCU_FANOUT_EXACT=n CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=n -CONFIG_PROVE_RCU_DELAY=n CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_CPU_STALL_VERBOSE=y CONFIG_RCU_BOOST=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 b/tools/testing/selftests/rcutorture/configs/rcu/TREE03 index c1f111c1561b..f4567fb3e332 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03 @@ -14,7 +14,6 @@ CONFIG_RCU_FANOUT_LEAF=4 CONFIG_RCU_FANOUT_EXACT=n CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_PROVE_RCU_DELAY=n CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_RCU_BOOST=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 index 7dbd27ce17a4..0a262fbb0c12 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 @@ -18,7 +18,6 @@ CONFIG_RCU_FANOUT_LEAF=2 CONFIG_RCU_FANOUT_EXACT=n CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_PROVE_RCU_DELAY=n CONFIG_RCU_CPU_STALL_INFO=y CONFIG_RCU_CPU_STALL_VERBOSE=y CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 index d0f32e574743..3a06b97e9a73 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 @@ -18,7 +18,6 @@ CONFIG_RCU_NOCB_CPU_NONE=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y CONFIG_PROVE_RCU=y -CONFIG_PROVE_RCU_DELAY=y CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 index 2e477dfb9c57..8f084cca91bf 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 @@ -19,7 +19,6 @@ CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y CONFIG_PROVE_RCU=y -CONFIG_PROVE_RCU_DELAY=n CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 index 042f86ef362a..ab6225506909 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 @@ -17,7 +17,6 @@ CONFIG_RCU_FANOUT_LEAF=2 CONFIG_RCU_FANOUT_EXACT=n CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_PROVE_RCU_DELAY=n CONFIG_RCU_CPU_STALL_INFO=y CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 b/tools/testing/selftests/rcutorture/configs/rcu/TREE08 index 3438cee1e3c5..69a2e255bf98 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08 @@ -18,7 +18,6 @@ CONFIG_RCU_FANOUT_LEAF=2 CONFIG_RCU_NOCB_CPU=y CONFIG_RCU_NOCB_CPU_ALL=y CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_PROVE_RCU_DELAY=n CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_RCU_BOOST=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T index bf4523d3e44c..a0f32fb8f17e 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T @@ -18,7 +18,6 @@ CONFIG_RCU_FANOUT_LEAF=2 CONFIG_RCU_NOCB_CPU=y CONFIG_RCU_NOCB_CPU_ALL=y CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_PROVE_RCU_DELAY=n CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_RCU_BOOST=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE09 b/tools/testing/selftests/rcutorture/configs/rcu/TREE09 index 81e4f7c0bf0b..b7a62a540ad1 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE09 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE09 @@ -13,7 +13,6 @@ CONFIG_SUSPEND=n CONFIG_HIBERNATION=n CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_PROVE_RCU_DELAY=n CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_RCU_BOOST=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp index ef624ce73d8e..a55c00877fe4 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp @@ -13,7 +13,6 @@ CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=y #CHECK#CONFIG_TREE_PREEMPT_RCU=y CONFIG_DEBUG_KERNEL=y -CONFIG_PROVE_RCU_DELAY=y CONFIG_DEBUG_OBJECTS=y CONFIG_DEBUG_OBJECTS_RCU_HEAD=y CONFIG_RT_MUTEXES=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp index ef624ce73d8e..a55c00877fe4 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp @@ -13,7 +13,6 @@ CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=y #CHECK#CONFIG_TREE_PREEMPT_RCU=y CONFIG_DEBUG_KERNEL=y -CONFIG_PROVE_RCU_DELAY=y CONFIG_DEBUG_OBJECTS=y CONFIG_DEBUG_OBJECTS_RCU_HEAD=y CONFIG_RT_MUTEXES=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp index ef624ce73d8e..a55c00877fe4 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp @@ -13,7 +13,6 @@ CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=y #CHECK#CONFIG_TREE_PREEMPT_RCU=y CONFIG_DEBUG_KERNEL=y -CONFIG_PROVE_RCU_DELAY=y CONFIG_DEBUG_OBJECTS=y CONFIG_DEBUG_OBJECTS_RCU_HEAD=y CONFIG_RT_MUTEXES=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp index ef624ce73d8e..a55c00877fe4 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp @@ -13,7 +13,6 @@ CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=y #CHECK#CONFIG_TREE_PREEMPT_RCU=y CONFIG_DEBUG_KERNEL=y -CONFIG_PROVE_RCU_DELAY=y CONFIG_DEBUG_OBJECTS=y CONFIG_DEBUG_OBJECTS_RCU_HEAD=y CONFIG_RT_MUTEXES=y diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt index adbb76cffb49..3e588db86a17 100644 --- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt +++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt @@ -14,7 +14,6 @@ CONFIG_NO_HZ_FULL_SYSIDLE -- Do one. CONFIG_PREEMPT -- Do half. (First three and #8.) CONFIG_PROVE_LOCKING -- Do all but two, covering CONFIG_PROVE_RCU and not. CONFIG_PROVE_RCU -- Do all but one under CONFIG_PROVE_LOCKING. -CONFIG_PROVE_RCU_DELAY -- Do one. CONFIG_RCU_BOOST -- one of TREE_PREEMPT_RCU. CONFIG_RCU_BOOST_PRIO -- set to 2 for _BOOST testing. CONFIG_RCU_CPU_STALL_INFO -- do one with and without _VERBOSE. diff --git a/tools/time/udelay_test.sh b/tools/time/udelay_test.sh new file mode 100755 index 000000000000..12d46b926917 --- /dev/null +++ b/tools/time/udelay_test.sh @@ -0,0 +1,66 @@ +#!/bin/bash + +# udelay() test script +# +# Test is executed by writing and reading to /sys/kernel/debug/udelay_test +# and exercises a variety of delays to ensure that udelay() is delaying +# at least as long as requested (as compared to ktime). +# +# Copyright (C) 2014 Google, Inc. +# +# 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. + +MODULE_NAME=udelay_test +UDELAY_PATH=/sys/kernel/debug/udelay_test + +setup() +{ + /sbin/modprobe -q $MODULE_NAME + tmp_file=`mktemp` +} + +test_one() +{ + delay=$1 + echo $delay > $UDELAY_PATH + tee -a $tmp_file < $UDELAY_PATH +} + +cleanup() +{ + if [ -f $tmp_file ]; then + rm $tmp_file + fi + /sbin/modprobe -q -r $MODULE_NAME +} + +trap cleanup EXIT +setup + +# Delay for a variety of times. +# 1..200, 200..500 (by 10), 500..2000 (by 100) +for (( delay = 1; delay < 200; delay += 1 )); do + test_one $delay +done +for (( delay = 200; delay < 500; delay += 10 )); do + test_one $delay +done +for (( delay = 500; delay <= 2000; delay += 100 )); do + test_one $delay +done + +# Search for failures +count=`grep -c FAIL $tmp_file` +if [ $? -eq "0" ]; then + echo "ERROR: $count delays failed to delay long enough" + retcode=1 +fi + +exit $retcode |