Skip to content

cloud-kernel
cloud-kernel

openanolis / cloud-kernel
1 年多 前同步成功

通知 160
Star 36
Fork 7
cloud-kernel
cloud-kernel
切换分支/标签
  1. 14 9月, 2016 11 次提交
  3. 12 9月, 2016 2 次提交
    • N
      perf hists browser: Fix event group display · d9ea48bc
      由 Namhyung Kim 提交于 
      Milian reported that the event group on TUI shows duplicated overhead.
This was due to a bug on calculating hpp->buf position.  The
hpp_advance() was called from __hpp__slsmg_color_printf() on TUI but
it's already called from the hpp__call_print_fn macro in __hpp__fmt().
The end result is that the print function returns number of bytes it
printed but the buffer advanced twice of the length.

This is generally not a problem since it doesn't need to access the
buffer again.  But with event group, overhead needs to be printed
multiple times and hist_entry__snprintf_alignment() tries to fill the
space with buffer after it printed.  So it (brokenly) showed the last
overhead again.

The bug was there from the beginning, but I think it's only revealed
when the alignment function was added.
Reported-by: NMilian Wolff <milian.wolff@kdab.com>
Signed-off-by: NNamhyung Kim <namhyung@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Fixes: 89fee709 ("perf hists: Do column alignment on the format iterator")
Link: http://lkml.kernel.org/r/20160912061958.16656-2-namhyung@kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      d9ea48bc
    • A
      perf probe: Fix dwarf regs table for x86_64 · 7a023fd2
      由 Arnaldo Carvalho de Melo 提交于 
      In 293d5b43 ("perf probe: Support probing on offline cross-arch binary")
DWARF register tables were introduced for many architectures, with the one for
the "dx" register being broken for x86_64, which got noticed by the 'perf test
bpf' testcase, that has this difference from a successful run to one that
fails, with the aforementioned patch:

  -Writing event: p:perf_bpf_probe/func _text+5197232 f_mode=+68(%di):x32 offset=%si:s64 orig=dx:s32
  -Failed to write event: Invalid argument
  -bpf_probe: failed to apply perf probe eventsFailed to add events selected by BPF
  +Writing event: p:perf_bpf_probe/func _text+5197232 f_mode=+68(%di):x32 offset=%si:s64 orig=%dx:s32

Add the missing '%' to '%dx' to fix this.
Acked-by: NMasami Hiramatsu <mhiramat@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: 293d5b43 ("perf probe: Support probing on offline cross-arch binary")
Link: https://lkml.kernel.org/r/20160909145955.GC32585@kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      7a023fd2
  5. 10 9月, 2016 10 次提交
    • K
      perf/x86/intel/uncore: Add Skylake server uncore support · cd34cd97
      由 Kan Liang 提交于 
      This patch implements the uncore monitoring driver for Skylake server.
The uncore subsystem in Skylake server is similar to previous
server. There are some differences in config register encoding and pci
device IDs. Besides, Skylake introduces many new boxes to reflect the
MESH architecture changes.

The control registers for IIO and UPI have been extended to 64 bit. This
patch also introduces event_mask_ext to handle the high 32 bit mask.

The CHA box number could vary for different machines. This patch gets
the CHA box number by counting the CHA register space during
initialization at runtime.
Signed-off-by: NKan Liang <kan.liang@intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Link: http://lkml.kernel.org/r/1471378190-17276-3-git-send-email-kan.liang@intel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      cd34cd97
    • H
      perf/x86/rapl: Enable Apollo Lake RAPL support · 2668c619
      由 Harry Pan 提交于 
      This patch enables RAPL counters (energy consumption counters)
support for Intel Apollo Lake (Goldmont) processors (Model 92):

RAPL of Goldmont, unlikes ESU increment of Silvermont/Airmont,
it likes the Haswell microarchitecture in 1/2^ESU joules and
supports power domains in PP0/PP1/PKG/RAM.

ESU and power domains refer to Intel Software Developers' Manual,
Vol. 3C, Order No. 325384, Table 35-12.

Usage example:

  $ perf list
  $ perf stat -a -e power/energy-cores/,power/energy-pkg/ sleep 10
Signed-off-by: NHarry Pan <harry.pan@intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: bp@alien8.de
Cc: gs0622@gmail.com
Cc: hpa@zytor.com
Cc: srinivas.pandruvada@linux.intel.com
Link: http://lkml.kernel.org/r/1473325738-730-1-git-send-email-harry.pan@intel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      2668c619
    • I
      Merge branch 'perf/urgent' into perf/core, to pick up fixes · 50069218
      由 Ingo Molnar 提交于 
      Signed-off-by: NIngo Molnar <mingo@kernel.org>
      50069218
    • P
      perf/x86/intel: Fix PEBSv3 record drain · 8ef9b845
      由 Peter Zijlstra 提交于 
      Alexander hit the WARN_ON_ONCE(!event) on his Skylake while running
the perf fuzzer.

This means the PEBSv3 record included a status bit for an inactive
event, something that _should_ not happen.

Move the code that filters the status bits against our known PEBS
events up a spot to guarantee we only deal with events we know about.

Further add "continue" statements to the WARN_ON_ONCE()s such that
we'll not die nor generate silly events in case we ever do hit them
again.
Reported-by: NAlexander Shishkin <alexander.shishkin@linux.intel.com>
Tested-by: NAlexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vince@deater.net>
Cc: stable@vger.kernel.org
Fixes: a3d86542 ("perf/x86/intel/pebs: Add PEBSv3 decoding")
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      8ef9b845
    • A
      perf/x86/intel/bts: Kill a silly warning · ef9ef3be
      由 Alexander Shishkin 提交于 
      At the moment, intel_bts will WARN() out if there is more than one
event writing to the same ring buffer, via SET_OUTPUT, and will only
send data from one event to a buffer.

There is no reason to have this warning in, so kill it.
Signed-off-by: NAlexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: vince@deater.net
Link: http://lkml.kernel.org/r/20160906132353.19887-6-alexander.shishkin@linux.intel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      ef9ef3be
    • A
      perf/x86/intel/bts: Fix BTS PMI detection · 4d4c4741
      由 Alexander Shishkin 提交于 
      Since BTS doesn't have a dedicated PMI status bit, the driver needs to
take extra care to check for the condition that triggers it to avoid
spurious NMI warnings.

Regardless of the local BTS context state, the only way of knowing that
the NMI is ours is to compare the write pointer against the interrupt
threshold.
Reported-by: NVince Weaver <vincent.weaver@maine.edu>
Signed-off-by: NAlexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: vince@deater.net
Link: http://lkml.kernel.org/r/20160906132353.19887-5-alexander.shishkin@linux.intel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      4d4c4741
    • A
      perf/x86/intel/bts: Fix confused ordering of PMU callbacks · a9a94401
      由 Alexander Shishkin 提交于 
      The intel_bts driver is using a CPU-local 'started' variable to order
callbacks and PMIs and make sure that AUX transactions don't get messed
up. However, the ordering rules in regard to this variable is a complete
mess, which recently resulted in perf_fuzzer-triggered warnings and
panics.

The general ordering rule that is patch is enforcing is that this
cpu-local variable be set only when the cpu-local AUX transaction is
active; consequently, this variable is to be checked before the AUX
related bits can be touched.
Reported-by: NVince Weaver <vincent.weaver@maine.edu>
Signed-off-by: NAlexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: vince@deater.net
Link: http://lkml.kernel.org/r/20160906132353.19887-4-alexander.shishkin@linux.intel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      a9a94401
    • A
      perf/core: Fix aux_mmap_count vs aux_refcount order · b79ccadd
      由 Alexander Shishkin 提交于 
      The order of accesses to ring buffer's aux_mmap_count and aux_refcount
has to be preserved across the users, namely perf_mmap_close() and
perf_aux_output_begin(), otherwise the inversion can result in the latter
holding the last reference to the aux buffer and subsequently free'ing
it in atomic context, triggering a warning.

> ------------[ cut here ]------------
> WARNING: CPU: 0 PID: 257 at kernel/events/ring_buffer.c:541 __rb_free_aux+0x11a/0x130
> CPU: 0 PID: 257 Comm: stopbug Not tainted 4.8.0-rc1+ #2596
> Call Trace:
>  [<ffffffff810f3e0b>] __warn+0xcb/0xf0
>  [<ffffffff810f3f3d>] warn_slowpath_null+0x1d/0x20
>  [<ffffffff8121182a>] __rb_free_aux+0x11a/0x130
>  [<ffffffff812127a8>] rb_free_aux+0x18/0x20
>  [<ffffffff81212913>] perf_aux_output_begin+0x163/0x1e0
>  [<ffffffff8100c33a>] bts_event_start+0x3a/0xd0
>  [<ffffffff8100c42d>] bts_event_add+0x5d/0x80
>  [<ffffffff81203646>] event_sched_in.isra.104+0xf6/0x2f0
>  [<ffffffff8120652e>] group_sched_in+0x6e/0x190
>  [<ffffffff8120694e>] ctx_sched_in+0x2fe/0x5f0
>  [<ffffffff81206ca0>] perf_event_sched_in+0x60/0x80
>  [<ffffffff81206d1b>] ctx_resched+0x5b/0x90
>  [<ffffffff81207281>] __perf_event_enable+0x1e1/0x240
>  [<ffffffff81200639>] event_function+0xa9/0x180
>  [<ffffffff81202000>] ? perf_cgroup_attach+0x70/0x70
>  [<ffffffff8120203f>] remote_function+0x3f/0x50
>  [<ffffffff811971f3>] flush_smp_call_function_queue+0x83/0x150
>  [<ffffffff81197bd3>] generic_smp_call_function_single_interrupt+0x13/0x60
>  [<ffffffff810a6477>] smp_call_function_single_interrupt+0x27/0x40
>  [<ffffffff81a26ea9>] call_function_single_interrupt+0x89/0x90
>  [<ffffffff81120056>] finish_task_switch+0xa6/0x210
>  [<ffffffff81120017>] ? finish_task_switch+0x67/0x210
>  [<ffffffff81a1e83d>] __schedule+0x3dd/0xb50
>  [<ffffffff81a1efe5>] schedule+0x35/0x80
>  [<ffffffff81128031>] sys_sched_yield+0x61/0x70
>  [<ffffffff81a25be5>] entry_SYSCALL_64_fastpath+0x18/0xa8
> ---[ end trace 6235f556f5ea83a9 ]---

This patch puts the checks in perf_aux_output_begin() in the same order
as that of perf_mmap_close().
Reported-by: NVince Weaver <vincent.weaver@maine.edu>
Signed-off-by: NAlexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: vince@deater.net
Link: http://lkml.kernel.org/r/20160906132353.19887-3-alexander.shishkin@linux.intel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      b79ccadd
    • A
      perf/core: Fix a race between mmap_close() and set_output() of AUX events · 767ae086
      由 Alexander Shishkin 提交于 
      In the mmap_close() path we need to stop all the AUX events that are
writing data to the AUX area that we are unmapping, before we can
safely free the pages. To determine if an event needs to be stopped,
we're comparing its ->rb against the one that's getting unmapped.
However, a SET_OUTPUT ioctl may turn up inside an AUX transaction
and swizzle event::rb to some other ring buffer, but the transaction
will keep writing data to the old ring buffer until the event gets
scheduled out. At this point, mmap_close() will skip over such an
event and will proceed to free the AUX area, while it's still being
used by this event, which will set off a warning in the mmap_close()
path and cause a memory corruption.

To avoid this, always stop an AUX event before its ->rb is updated;
this will release the (potentially) last reference on the AUX area
of the buffer. If the event gets restarted, its new ring buffer will
be used. If another SET_OUTPUT comes and switches it back to the
old ring buffer that's getting unmapped, it's also fine: this
ring buffer's aux_mmap_count will be zero and AUX transactions won't
start any more.
Reported-by: NVince Weaver <vincent.weaver@maine.edu>
Signed-off-by: NAlexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: vince@deater.net
Link: http://lkml.kernel.org/r/20160906132353.19887-2-alexander.shishkin@linux.intel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      767ae086
    • S
      perf/x86/amd/uncore: Prevent use after free · 7d762e49
      由 Sebastian Andrzej Siewior 提交于 
      The resent conversion of the cpu hotplug support in the uncore driver
introduced a regression due to the way the callbacks are invoked at
initialization time.

The old code called the prepare/starting/online function on each online cpu
as a block. The new code registers the hotplug callbacks in the core for
each state. The core invokes the callbacks at each registration on all
online cpus.

The code implicitely relied on the prepare/starting/online callbacks being
called as combo on a particular cpu, which was not obvious and completely
undocumented.

The resulting subtle wreckage happens due to the way how the uncore code
manages shared data structures for cpus which share an uncore resource in
hardware. The sharing is determined in the cpu starting callback, but the
prepare callback allocates per cpu data for the upcoming cpu because
potential sharing is unknown at this point. If the starting callback finds
a online cpu which shares the hardware resource it takes a refcount on the
percpu data of that cpu and puts the own data structure into a
'free_at_online' pointer of that shared data structure. The online callback
frees that.

With the old model this worked because in a starting callback only one non
unused structure (the one of the starting cpu) was available. The new code
allocates the data structures for all cpus when the prepare callback is
registered.

Now the starting function iterates through all online cpus and looks for a
data structure (skipping its own) which has a matching hardware id. The id
member of the data structure is initialized to 0, but the hardware id can
be 0 as well. The resulting wreckage is:

  CPU0 finds a matching id on CPU1, takes a refcount on CPU1 data and puts
  its own data structure into CPU1s data structure to be freed.

  CPU1 skips CPU0 because the data structure is its allegedly unsued own.
  It finds a matching id on CPU2, takes a refcount on CPU1 data and puts
  its own data structure into CPU2s data structure to be freed.

  ....

Now the online callbacks are invoked.

  CPU0 has a pointer to CPU1s data and frees the original CPU0 data. So
  far so good.

  CPU1 has a pointer to CPU2s data and frees the original CPU1 data, which
  is still referenced by CPU0 ---> Booom

So there are two issues to be solved here:

1) The id field must be initialized at allocation time to a value which
   cannot be a valid hardware id, i.e. -1

   This prevents the above scenario, but now CPU1 and CPU2 both stick their
   own data structure into the free_at_online pointer of CPU0. So we leak
   CPU1s data structure.

2) Fix the memory leak described in #1

   Instead of having a single pointer, use a hlist to enqueue the
   superflous data structures which are then freed by the first cpu
   invoking the online callback.

Ideally we should know the sharing _before_ invoking the prepare callback,
but that's way beyond the scope of this bug fix.

[ tglx: Rewrote changelog ]

Fixes: 96b2bd38 ("perf/x86/amd/uncore: Convert to hotplug state machine")
Reported-and-tested-by: NEric Sandeen <sandeen@sandeen.net>
Signed-off-by: NSebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Borislav Petkov <bp@suse.de>
Link: http://lkml.kernel.org/r/20160909160822.lowgmkdwms2dheyv@linutronix.deSigned-off-by: NThomas Gleixner <tglx@linutronix.de>
      7d762e49
  7. 09 9月, 2016 5 次提交
    • I
      Merge tag 'perf-core-for-mingo-20160908' of... · 14520d63
      由 Ingo Molnar 提交于 
      Merge tag 'perf-core-for-mingo-20160908' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

- Add branch stack / basic block info to 'perf annotate --stdio', where for
  each branch, we add an asm comment after the instruction with information on
  how often it was taken and predicted. See example with color output at:

    http://vger.kernel.org/~acme/perf/annotate_basic_blocks.png

  (Peter Zijlstra)

- Only open an evsel in CPUs in its cpu map, fixing some use cases in
  systems with multiple PMUs with different CPU maps (Mark Rutland)

- Fix handling of huge TLB maps, recognizing it as anonymous (Wang Nan)

Infrastructure changes:

- Remove the symbol filtering code, i.e. the callbacks passed to all functions
  that could end up loading a DSO symtab, simplifying the code, eventually
  allowing what we should have had since day one: removing the 'map' parameter
  from dso__load() functions (Arnaldo Carvalho de Melo)

Arch specific build fixes:

- Fix detached tarball build on powerpc, where we were still accessing a
  file outside tools/ (Ravi Bangoria)
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      14520d63
    • R
      perf powerpc: Fix build-test failure · 25b8592e
      由 Ravi Bangoria 提交于 
      'make -C tools/perf build-test' is failing with below log for poewrpc.

  In file included from /tmp/tmp.3eEwmGlYaF/perf-4.8.0-rc4/tools/perf/perf.h:15:0,
                   from util/cpumap.h:8,
                   from util/env.c:1:
  /tmp/tmp.3eEwmGlYaF/perf-4.8.0-rc4/tools/perf/perf-sys.h:23:56:
  fatal error: ../../arch/powerpc/include/uapi/asm/unistd.h: No such file or directory
  compilation terminated.

I bisected it and found it's failing from commit ad430729 ("Remove:
kernel unistd*h files from perf's MANIFEST, not used").

Header file '../../arch/powerpc/include/uapi/asm/unistd.h' is included
only for powerpc in tools/perf/perf-sys.h.

By looking closly at commit history, I found little weird thing:

Commit f2d9cae9 ("perf powerpc: Use uapi/unistd.h to fix build
error") replaced 'asm/unistd.h' with 'uapi/asm/unistd.h'

Commit d2709c7c ("perf: Make perf build for x86 with UAPI
disintegration applied") removes all arch specific 'uapi/asm/unistd.h'
for all archs and adds generic <asm/unistd.h>.

Commit f0b9abfb ("Merge branch 'linus' into perf/core") again
includes 'uapi/asm/unistd.h' for powerpc. Don't know how exactly this
happened as this change is not part of commit also.
Signed-off-by: NRavi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1472630591-5089-1-git-send-email-ravi.bangoria@linux.vnet.ibm.com
Fixes: ad430729 ("Remove: kernel unistd*h files from perf's MANIFEST, not used")
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      25b8592e
    • M
      perf pmu: Support alternative sysfs cpumask · 7e3fcffe
      由 Mark Rutland 提交于 
      The perf tools can read a cpumask file for a PMU, describing a subset of
CPUs which that PMU covers. So far this has only been used to cater for
uncore PMUs, which in practice happen to only have a single CPU
described in the mask.

Until recently, the perf tools only correctly handled cpumask containing
a single CPU, and only when monitoring in system-wide mode. For example,
prior to commit 00e727bb ("perf stat: Balance opening and
reading events"), a mask with more than a single CPU could cause perf
stat to hang. When a CPU PMU covers a subset of CPUs, but lacks a
cpumask, perf record will fail to open events (on the cores the PMU does
not support), and gives up.

For systems with heterogeneous CPUs such as ARM big.LITTLE systems, this
presents a problem. We have a PMU for each microarchitecture (e.g. a big
PMU and a little PMU), and would like to expose a cpumask for each (so
as to allow perf record and other tools to do the right thing). However,
doing so kernel-side will cause old perf binaries to not function (e.g.
hitting the issue solved by 00e727bb), and thus commits the
cardinal sin of breaking (existing) userspace.

To address this chicken-and-egg problem, this patch adds support got a
new file, cpus, which is largely identical to the existing cpumask file.
A kernel can expose this file, knowing that new perf binaries will
correctly support it, while old perf binaries will not look for it (and
thus will not be broken).
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will.deacon@arm.com>
Link: http://lkml.kernel.org/r/1473330112-28528-8-git-send-email-mark.rutland@arm.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      7e3fcffe
    • M
      perf evlist: Only open events on CPUs an evsel permits · 9f21b815
      由 Mark Rutland 提交于 
      In systems with heterogeneous CPU PMUs, it's possible for each evsel to
cover a distinct set of CPUs, and hence the cpu_map associated with each
evsel may have a distinct idx<->id mapping. Any of these may be distinct
from the evlist's cpu map.

Events can be tied to the same fd so long as they use the same per-cpu
ringbuffer (i.e. so long as they are on the same CPU). To acquire the
correct FDs, we must compare the Linux logical IDs rather than the evsel
or evlist indices.

This path adds logic to perf_evlist__mmap_per_evsel to handle this,
translating IDs as required. As PMUs may cover a subset of CPUs from the
evlist, we skip the CPUs a PMU cannot handle.

Without this patch, perf record may try to mmap erroneous FDs on
heterogeneous systems, and will bail out early rather than running the
workload.
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Acked-by: NJiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will.deacon@arm.com>
Link: http://lkml.kernel.org/r/1473330112-28528-7-git-send-email-mark.rutland@arm.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      9f21b815
    • P
      perf annotate: Add branch stack / basic block · 70fbe057
      由 Peter Zijlstra 提交于 
      I wanted to know the hottest path through a function and figured the
branch-stack (LBR) information should be able to help out with that.

The below uses the branch-stack to create basic blocks and generate
statistics from them.

        from    to              branch_i
        * ----> *
                |
                | block
                v
                * ----> *
                from    to      branch_i+1

The blocks are broken down into non-overlapping ranges, while tracking
if the start of each range is an entry point and/or the end of a range
is a branch.

Each block iterates all ranges it covers (while splitting where required
to exactly match the block) and increments the 'coverage' count.

For the range including the branch we increment the taken counter, as
well as the pred counter if flags.predicted.

Using these number we can find if an instruction:

 - had coverage; given by:

        br->coverage / br->sym->max_coverage

   This metric ensures each symbol has a 100% spot, which reflects the
   observation that each symbol must have a most covered/hottest
   block.

 - is a branch target: br->is_target && br->start == add

 - for targets, how much of a branch's coverages comes from it:

	target->entry / branch->coverage

 - is a branch: br->is_branch && br->end == addr

 - for branches, how often it was taken:

        br->taken / br->coverage

   after all, all execution that didn't take the branch would have
   incremented the coverage and continued onward to a later branch.

 - for branches, how often it was predicted:

        br->pred / br->taken

The coverage percentage is used to color the address and asm sections;
for low (<1%) coverage we use NORMAL (uncolored), indicating that these
instructions are not 'important'. For high coverage (>75%) we color the
address RED.

For each branch, we add an asm comment after the instruction with
information on how often it was taken and predicted.

Output looks like (sans color, which does loose a lot of the
information :/)

$ perf record --branch-filter u,any -e cycles:p ./branches 27
$ perf annotate branches

 Percent |	Source code & Disassembly of branches for cycles:pu (217 samples)
---------------------------------------------------------------------------------
         :	branches():
    0.00 :	  40057a:       push   %rbp
    0.00 :	  40057b:       mov    %rsp,%rbp
    0.00 :	  40057e:       sub    $0x20,%rsp
    0.00 :	  400582:       mov    %rdi,-0x18(%rbp)
    0.00 :	  400586:       mov    %rsi,-0x20(%rbp)
    0.00 :	  40058a:       mov    -0x18(%rbp),%rax
    0.00 :	  40058e:       mov    %rax,-0x10(%rbp)
    0.00 :	  400592:       movq   $0x0,-0x8(%rbp)
    0.00 :	  40059a:       jmpq   400656 <branches+0xdc>
    1.84 :	  40059f:       mov    -0x10(%rbp),%rax	# +100.00%
    3.23 :	  4005a3:       and    $0x1,%eax
    1.84 :	  4005a6:       test   %rax,%rax
    0.00 :	  4005a9:       je     4005bf <branches+0x45>	# -54.50% (p:42.00%)
    0.46 :	  4005ab:       mov    0x200bbe(%rip),%rax        # 601170 <acc>
   12.90 :	  4005b2:       add    $0x1,%rax
    2.30 :	  4005b6:       mov    %rax,0x200bb3(%rip)        # 601170 <acc>
    0.46 :	  4005bd:       jmp    4005d1 <branches+0x57>	# -100.00% (p:100.00%)
    0.92 :	  4005bf:       mov    0x200baa(%rip),%rax        # 601170 <acc>	# +49.54%
   13.82 :	  4005c6:       sub    $0x1,%rax
    0.46 :	  4005ca:       mov    %rax,0x200b9f(%rip)        # 601170 <acc>
    2.30 :	  4005d1:       mov    -0x10(%rbp),%rax	# +50.46%
    0.46 :	  4005d5:       mov    %rax,%rdi
    0.46 :	  4005d8:       callq  400526 <lfsr>	# -100.00% (p:100.00%)
    0.00 :	  4005dd:       mov    %rax,-0x10(%rbp)	# +100.00%
    0.92 :	  4005e1:       mov    -0x18(%rbp),%rax
    0.00 :	  4005e5:       and    $0x1,%eax
    0.00 :	  4005e8:       test   %rax,%rax
    0.00 :	  4005eb:       je     4005ff <branches+0x85>	# -100.00% (p:100.00%)
    0.00 :	  4005ed:       mov    0x200b7c(%rip),%rax        # 601170 <acc>
    0.00 :	  4005f4:       shr    $0x2,%rax
    0.00 :	  4005f8:       mov    %rax,0x200b71(%rip)        # 601170 <acc>
    0.00 :	  4005ff:       mov    -0x10(%rbp),%rax	# +100.00%
    7.37 :	  400603:       and    $0x1,%eax
    3.69 :	  400606:       test   %rax,%rax
    0.00 :	  400609:       jne    400612 <branches+0x98>	# -59.25% (p:42.99%)
    1.84 :	  40060b:       mov    $0x1,%eax
   14.29 :	  400610:       jmp    400617 <branches+0x9d>	# -100.00% (p:100.00%)
    1.38 :	  400612:       mov    $0x0,%eax	# +57.65%
   10.14 :	  400617:       test   %al,%al	# +42.35%
    0.00 :	  400619:       je     40062f <branches+0xb5>	# -57.65% (p:100.00%)
    0.46 :	  40061b:       mov    0x200b4e(%rip),%rax        # 601170 <acc>
    2.76 :	  400622:       sub    $0x1,%rax
    0.00 :	  400626:       mov    %rax,0x200b43(%rip)        # 601170 <acc>
    0.46 :	  40062d:       jmp    400641 <branches+0xc7>	# -100.00% (p:100.00%)
    0.92 :	  40062f:       mov    0x200b3a(%rip),%rax        # 601170 <acc>	# +56.13%
    2.30 :	  400636:       add    $0x1,%rax
    0.92 :	  40063a:       mov    %rax,0x200b2f(%rip)        # 601170 <acc>
    0.92 :	  400641:       mov    -0x10(%rbp),%rax	# +43.87%
    2.30 :	  400645:       mov    %rax,%rdi
    0.00 :	  400648:       callq  400526 <lfsr>	# -100.00% (p:100.00%)
    0.00 :	  40064d:       mov    %rax,-0x10(%rbp)	# +100.00%
    1.84 :	  400651:       addq   $0x1,-0x8(%rbp)
    0.92 :	  400656:       mov    -0x8(%rbp),%rax
    5.07 :	  40065a:       cmp    -0x20(%rbp),%rax
    0.00 :	  40065e:       jb     40059f <branches+0x25>	# -100.00% (p:100.00%)
    0.00 :	  400664:       nop
    0.00 :	  400665:       leaveq
    0.00 :	  400666:       retq

(Note: the --branch-filter u,any was used to avoid spurious target and
branch points due to interrupts/faults, they show up as very small -/+
annotations on 'weird' locations)

Committer note:

Please take a look at:

  http://vger.kernel.org/~acme/perf/annotate_basic_blocks.png

To see the colors.
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
[ Moved sym->max_coverage to 'struct annotate', aka symbol__annotate(sym) ]
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      70fbe057
  9. 08 9月, 2016 3 次提交
  11. 06 9月, 2016 1 次提交
  13. 05 9月, 2016 8 次提交