Skip to content

L
linux
Switch branch/tag
  1. 10 Mar, 2010 15 commits
    • Peter Zijlstra's avatar
      perf, x86: Add PEBS infrastructure · ca037701
      Peter Zijlstra authored 
      This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.

This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.

With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.

This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).

It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      ca037701
    • Peter Zijlstra's avatar
      perf: Provide better condition for event rotation · d4944a06
      Peter Zijlstra authored 
      Try to avoid useless rotation and PMU disables.

[ Could be improved by keeping a nr_runnable count to better account
  for the < PERF_STAT_INACTIVE counters ]
Signed-off-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <new-submission>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      d4944a06
    • Peter Zijlstra's avatar
      perf, x86: Fix double enable calls · f3d46b2e
      Peter Zijlstra authored 
      hw_perf_enable() would enable already enabled events.

This causes problems with code that assumes that ->enable/->disable calls
are balanced (like the LBR code does).

What happens is that events that were already running and left in place
would get enabled again.

Avoid this by only enabling new events that match their previous
assignment.
Signed-off-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <new-submission>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      f3d46b2e
    • Peter Zijlstra's avatar
      perf, x86: Fix double disable calls · 19925ce7
      Peter Zijlstra authored 
      hw_perf_enable() would disable events that were not yet enabled.

This causes problems with code that assumes that ->enable/->disable calls
are balanced (like the LBR code does).

What happens is that we disable newly added counters that match their
previous assignment, even though they are not yet programmed on the
hardware.

Avoid this by only doing the first pass over the existing events.
Signed-off-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <new-submission>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      19925ce7
    • Peter Zijlstra's avatar
      perf, x86: Properly account n_added · 356e1f2e
      Peter Zijlstra authored 
      Make sure n_added is properly accounted so that we can rely on the value
to reflect the number of added counters. This is needed if its going to
be used for more than a boolean check.
Signed-off-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <new-submission>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      356e1f2e
    • Peter Zijlstra's avatar
      perf, x86: Avoid double disable on throttle vs ioctl(PERF_IOC_DISABLE) · 71e2d282
      Peter Zijlstra authored 
      Calling ioctl(PERF_EVENT_IOC_DISABLE) on a thottled counter would result
in a double disable, cure this by using x86_pmu_{start,stop} for
throttle/unthrottle and teach x86_pmu_stop() to check ->active_mask.
Signed-off-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <new-submission>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      71e2d282
    • Peter Zijlstra's avatar
      perf, x86: Fix x86_pmu_start · c08053e6
      Peter Zijlstra authored 
      pmu::start should undo pmu::stop, make it so.
Signed-off-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <new-submission>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      c08053e6
    • Peter Zijlstra's avatar
      perf, x86: Use unlocked bitops · 34538ee7
      Peter Zijlstra authored 
      There is no concurrency on these variables, so don't use LOCK'ed ops.

As to the intel_pmu_handle_irq() status bit clean, nobody uses that so
remove it all together.
Signed-off-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
LKML-Reference: <20100304140100.240023029@chello.nl>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      34538ee7
    • Peter Zijlstra's avatar
      perf, x86: Change x86_pmu.{enable,disable} calling convention · aff3d91a
      Peter Zijlstra authored 
      Pass the full perf_event into the x86_pmu functions so that those may
make use of more than the hw_perf_event, and while doing this, remove the
superfluous second argument.
Signed-off-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
LKML-Reference: <20100304140100.165166129@chello.nl>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      aff3d91a
    • Peter Zijlstra's avatar
      perf, x86: Remove superfluous arguments to x86_perf_event_update() · cc2ad4ba
      Peter Zijlstra authored 
      The second and third argument to x86_perf_event_update() are superfluous
since they are simple expressions of the first argument. Hence remove
them.
Signed-off-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
LKML-Reference: <20100304140100.089468871@chello.nl>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      cc2ad4ba
    • Peter Zijlstra's avatar
      perf, x86: Remove superfluous arguments to x86_perf_event_set_period() · 07088edb
      Peter Zijlstra authored 
      The second and third argument to x86_perf_event_set_period() are
superfluous since they are simple expressions of the first argument.
Hence remove them.
Signed-off-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
LKML-Reference: <20100304140100.006500906@chello.nl>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      07088edb
    • Peter Zijlstra's avatar
      perf, x86, Do not user perf_disable from NMI context · 3fb2b8dd
      Peter Zijlstra authored 
      Explicitly use intel_pmu_{disable,enable}_all() in intel_pmu_handle_irq()
to avoid the NMI race conditions in perf_{disable,enable}
Signed-off-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <new-submission>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      3fb2b8dd
    • Peter Zijlstra's avatar
      perf: Optimize perf_disable · 32975a4f
      Peter Zijlstra authored 
      Currently we always call hw_perf_disable(), even if its already disabled,
this seems superflous, esp. since it cannot be made NMI safe (see further
patches).
Signed-off-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
LKML-Reference: <new-submission>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      32975a4f
    • Peter Zijlstra's avatar
      perf: Rework and fix the arch CPU-hotplug hooks · 3f6da390
      Peter Zijlstra authored 
      Remove the hw_perf_event_*() hotplug hooks in favour of per PMU hotplug
notifiers. This has the advantage of reducing the static weak interface
as well as exposing all hotplug actions to the PMU.

Use this to fix x86 hotplug usage where we did things in ONLINE which
should have been done in UP_PREPARE or STARTING.
Signed-off-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
LKML-Reference: <20100305154128.736225361@chello.nl>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      3f6da390
    • Peter Zijlstra's avatar
      perf: Provide generic perf_sample_data initialization · dc1d628a
      Peter Zijlstra authored 
      This makes it easier to extend perf_sample_data and fixes a bug on arm
and sparc, which failed to set ->raw to NULL, which can cause crashes
when combined with PERF_SAMPLE_RAW.

It also optimizes PowerPC and tracepoint, because the struct
initialization is forced to zero out the whole structure.
Signed-off-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: default avatarJean Pihet <jpihet@mvista.com>
Reviewed-by: default avatarFrederic Weisbecker <fweisbec@gmail.com>
Acked-by: default avatarDavid S. Miller <davem@davemloft.net>
Cc: Jamie Iles <jamie.iles@picochip.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: stable@kernel.org
LKML-Reference: <20100304140100.315416040@chello.nl>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      dc1d628a
  3. 09 Mar, 2010 2 commits
  5. 08 Mar, 2010 23 commits
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7