linux.git/arch/alpha/kernel/perf_event.c, branch v3.14

alpha: perf: fix out-of-bounds array access triggered from raw event

2013-11-17T00:37:10+00:00

Vince's perf fuzzer uncovered the following issue on Alpha:

Unable to handle kernel paging request at virtual address fffffbfe4e46a0e8
CPU 0 perf_fuzzer(1278): Oops 0
pc = []  ra = []  ps = 0007    Not tainted
pc is at alpha_perf_event_set_period+0x60/0xf0
ra is at alpha_pmu_enable+0x1a4/0x1c0
v0 = 0000000000000000  t0 = 00000000000fffff  t1 = fffffc007b3f5800
t2 = fffffbff275faa94  t3 = ffffffffc9b9bd89  t4 = fffffbfe4e46a098
t5 = 0000000000000020  t6 = fffffbfe4e46a0b8  t7 = fffffc007f4c8000
s0 = 0000000000000000  s1 = fffffc0001b0c018  s2 = fffffc0001b0c020
s3 = fffffc007b3f5800  s4 = 0000000000000001  s5 = ffffffffc9b9bd85
s6 = 0000000000000001
a0 = 0000000000000006  a1 = fffffc007b3f5908  a2 = fffffbfe4e46a098
a3 = 00000005000108c0  a4 = 0000000000000000  a5 = 0000000000000000
t8 = 0000000000000001  t9 = 0000000000000001  t10= 0000000027829f6f
t11= 0000000000000020  pv = fffffc000031fb60  at = fffffc0000950900
gp = fffffc0000940900  sp = fffffc007f4cbca8
Disabling lock debugging due to kernel taint
Trace:
[] alpha_pmu_enable+0x1a4/0x1c0
[] perf_pmu_enable+0x48/0x60
[] __perf_install_in_context+0x15c/0x230
[] remote_function+0x80/0xa0
[] __perf_install_in_context+0x0/0x230
[] smp_call_function_single+0x1b4/0x1d0
[] task_function_call+0x60/0x80
[] __perf_install_in_context+0x0/0x230
[] task_function_call+0x34/0x80
[] perf_install_in_context+0x9c/0x150
[] __perf_install_in_context+0x0/0x230
[] SYSC_perf_event_open+0x360/0xac0
[] entSys+0xa4/0xc0

This is due to the raw event encoding being used as an index directly
into the ev67_mapping array, rather than being validated against the
ev67_pmc_event_type enumeration instead. Unlike other architectures,
which allow raw events to propagate into the hardware counters with
little interference, the limited number of events on Alpha and the
strict event <-> counter relationships mean that raw events actually
correspond to the Linux-specific Alpha events, rather than anything
defined by the architecture.

This patch adds a new callback to alpha_pmu_t for validating the raw
event encoding with the Linux event types for the PMU, preventing the
out-of-bounds array access.

Cc: Peter Zijlstra 
Acked-by: Michael Cree 
Acked-by: Matt Turner 
Signed-off-by: Will Deacon

perf: Pass last sampling period to perf_sample_data_init()

2012-05-09T13:23:12+00:00

We always need to pass the last sample period to
perf_sample_data_init(), otherwise the event distribution will be
wrong. Thus, modifiyng the function interface with the required period
as argument. So basically a pattern like this:

        perf_sample_data_init(&data, ~0ULL);
        data.period = event->hw.last_period;

will now be like that:

        perf_sample_data_init(&data, ~0ULL, event->hw.last_period);

Avoids unininitialized data.period and simplifies code.

Signed-off-by: Robert Richter 
Signed-off-by: Peter Zijlstra 
Link: http://lkml.kernel.org/r/1333390758-10893-3-git-send-email-robert.richter@amd.com
Signed-off-by: Ingo Molnar

perf: Disable PERF_SAMPLE_BRANCH_* when not supported

2012-03-05T13:55:42+00:00

PERF_SAMPLE_BRANCH_* is disabled for:

 - SW events (sw counters, tracepoints)
 - HW breakpoints
 - ALL but Intel x86 architecture
 - AMD64 processors

Signed-off-by: Stephane Eranian 
Signed-off-by: Peter Zijlstra 
Link: http://lkml.kernel.org/r/1328826068-11713-10-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar

atomic: use

2011-07-26T23:49:47+00:00

This allows us to move duplicated code in 
(atomic_inc_not_zero() for now) to 

Signed-off-by: Arun Sharma 
Reviewed-by: Eric Dumazet 
Cc: Ingo Molnar 
Cc: David Miller 
Cc: Eric Dumazet 
Acked-by: Mike Frysinger 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

perf: Remove the nmi parameter from the swevent and overflow interface

2011-07-01T09:06:35+00:00

The nmi parameter indicated if we could do wakeups from the current
context, if not, we would set some state and self-IPI and let the
resulting interrupt do the wakeup.

For the various event classes:

  - hardware: nmi=0; PMI is in fact an NMI or we run irq_work_run from
    the PMI-tail (ARM etc.)
  - tracepoint: nmi=0; since tracepoint could be from NMI context.
  - software: nmi=[0,1]; some, like the schedule thing cannot
    perform wakeups, and hence need 0.

As one can see, there is very little nmi=1 usage, and the down-side of
not using it is that on some platforms some software events can have a
jiffy delay in wakeup (when arch_irq_work_raise isn't implemented).

The up-side however is that we can remove the nmi parameter and save a
bunch of conditionals in fast paths.

Signed-off-by: Peter Zijlstra 
Cc: Michael Cree 
Cc: Will Deacon 
Cc: Deng-Cheng Zhu 
Cc: Anton Blanchard 
Cc: Eric B Munson 
Cc: Heiko Carstens 
Cc: Paul Mundt 
Cc: David S. Miller 
Cc: Frederic Weisbecker 
Cc: Jason Wessel 
Cc: Don Zickus 
Link: http://lkml.kernel.org/n/tip-agjev8eu666tvknpb3iaj0fg@git.kernel.org
Signed-off-by: Ingo Molnar

perf: Dynamic pmu types

2010-12-16T10:36:43+00:00

Extend the perf_pmu_register() interface to allow for named and
dynamic pmu types.

Because we need to support the existing static types we cannot use
dynamic types for everything, hence provide a type argument.

If we want to enumerate the PMUs they need a name, provide one.

Signed-off-by: Peter Zijlstra 
LKML-Reference: <20101117222056.259707703@chello.nl>
Signed-off-by: Ingo Molnar

perf, arch: Cleanup perf-pmu init vs lockup-detector

2010-11-26T14:14:56+00:00

The perf hardware pmu got initialized at various points in the boot,
some before early_initcall() some after (notably arch_initcall).

The problem is that the NMI lockup detector is ran from early_initcall()
and expects the hardware pmu to be present.

Sanitize this by moving all architecture hardware pmu implementations to
initialize at early_initcall() and move the lockup detector to an explicit
initcall right after that.

Cc: paulus 
Cc: davem 
Cc: Michael Cree 
Cc: Deng-Cheng Zhu 
Acked-by: Paul Mundt 
Acked-by: Will Deacon 
Signed-off-by: Peter Zijlstra 
LKML-Reference: <1290707759.2145.119.camel@laptop>
Signed-off-by: Ingo Molnar

alpha: Fix HW performance counters to be stopped properly

2010-09-15T08:43:59+00:00

Also fix a few compile errors due to undefined and duplicated
variables.

Signed-off-by: Michael Cree 
Signed-off-by: Peter Zijlstra 
LKML-Reference: <1284269844-23251-1-git-send-email-mcree@orcon.net.nz>
Signed-off-by: Ingo Molnar

Merge branch 'tip/perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into perf/core

2010-09-15T08:27:31+00:00

perf: Remove the sysfs bits

2010-09-09T18:46:31+00:00

Neither the overcommit nor the reservation sysfs parameter were
actually working, remove them as they'll only get in the way.

Signed-off-by: Peter Zijlstra 
Cc: paulus 
LKML-Reference: 
Signed-off-by: Ingo Molnar