| 066ce64c7e867e95e5fee7c5f6b852710486392a |
|
26-Aug-2014 |
Mathias Krause <minipli@googlemail.com> |
perf/x86/intel: Mark initialization code as such
A few of the initialization functions are missing the __init annotation.
Fix this and thereby allow ~680 additional bytes of code to be released
after initialization.
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: x86@kernel.org
Link: http://lkml.kernel.org/r/1409071785-26015-1-git-send-email-minipli@googlemail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| 89cbc76768c2fa4ed95545bf961f3a14ddfeed21 |
|
17-Aug-2014 |
Christoph Lameter <cl@linux.com> |
x86: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One of
them is address calculation via the form &__get_cpu_var(x). This calculates
the address for the instance of the percpu variable of the current processor
based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less registers
are used when code is generated.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
__this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
__this_cpu_inc(y)
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: x86@kernel.org
Acked-by: H. Peter Anvin <hpa@linux.intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
|
| c8aab2e04ac9f442a07abeaf49ddd1703c608f47 |
|
11-Aug-2014 |
Stephane Eranian <eranian@google.com> |
perf/x86: Clean up __intel_pmu_pebs_event() code
This patch makes the code more readable. It also renames
precise_store_data_hsw() to precise_datala_hsw() because
the function is called for both loads and stores on HSW.
The patch also gets rid of the hardcoded store events
codes in that same function.
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1407785233-32193-5-git-send-email-eranian@google.com
Cc: ak@linux.intel.com
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| 770eee1fd38c70a009b321f5dbe64358f42511fd |
|
11-Aug-2014 |
Stephane Eranian <eranian@google.com> |
perf/x86: Fix data source encoding issues for load latency/precise store
This patch fixes issues introuduce by Andi's previous patch 'Revamp PEBS'
series.
This patch fixes the following:
- precise_store_data_hsw() encode the mem op type whenever we can
- precise_store_data_hsw set the default data source correctly
- 0 is not a valid init value for data source. Define PERF_MEM_NA as the
default value
This bug was actually introduced by
commit 722e76e60f2775c21b087ff12c5e678cf0ebcaaf
Author: Stephane Eranian <eranian@google.com>
Date: Thu May 15 17:56:44 2014 +0200
fix Haswell precise store data source encoding
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1407785233-32193-4-git-send-email-eranian@google.com
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: ak@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| f3908b8cfb65ab6e78ac84df3b864eb22d5b6d9e |
|
11-Aug-2014 |
Andi Kleen <ak@linux.intel.com> |
perf/x86: Don't mark DataLA addresses as store
Haswell supports reporting the data address for a range
of PEBS events, including:
UOPS_RETIRED.ALL
MEM_UOPS_RETIRED.STLB_MISS_LOADS
MEM_UOPS_RETIRED.STLB_MISS_STORES
MEM_UOPS_RETIRED.LOCK_LOADS
MEM_UOPS_RETIRED.SPLIT_LOADS
MEM_UOPS_RETIRED.SPLIT_STORES
MEM_UOPS_RETIRED.ALL_LOADS
MEM_UOPS_RETIRED.ALL_STORES
MEM_LOAD_UOPS_RETIRED.L1_HIT
MEM_LOAD_UOPS_RETIRED.L2_HIT
MEM_LOAD_UOPS_RETIRED.L3_HIT
MEM_LOAD_UOPS_RETIRED.L1_MISS
MEM_LOAD_UOPS_RETIRED.L2_MISS
MEM_LOAD_UOPS_RETIRED.L3_MISS
MEM_LOAD_UOPS_RETIRED.HIT_LFB
MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS
MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT
MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM
MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_NONE
MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM
This facility was already enabled earlier with the original Haswell
perf changes.
However these addresses were always reports as stores by perf, which is wrong,
as they could be loads too. The hardware does not distinguish loads and stores
for these instructions, so there's no (cheap) way for the profiler
to find out.
Change the type to PERF_MEM_OP_NA instead.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Reviewed-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Link: http://lkml.kernel.org/r/1407785233-32193-3-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| 86a04461a99fb857bd7d7f87b234cae27df07f8a |
|
11-Aug-2014 |
Andi Kleen <ak@linux.intel.com> |
perf/x86: Revamp PEBS event selection
The basic idea is that it does not make sense to list all PEBS
events individually. The list is very long, sometimes outdated
and the hardware doesn't need it. If an event does not support
PEBS it will just not count, there is no security issue.
We need to only list events that something special, like
supporting load or store addresses.
This vastly simplifies the PEBS event selection. It also
speeds up the scheduling because the scheduler doesn't
have to walk as many constraints.
Bugs fixed:
- We do not allow setting forbidden flags with PEBS anymore
(SDM 18.9.4), except for the special cycle event.
This is done using a new constraint macro that also
matches on the event flags.
- Correct DataLA and load/store/na flags reporting on Haswell
[Requires a followon patch]
- We did not allow all PEBS events on Haswell:
We were missing some valid subevents in d1-d2 (MEM_LOAD_UOPS_RETIRED.*,
MEM_LOAD_UOPS_RETIRED_L3_HIT_RETIRED.*)
This includes the changes proposed by Stephane earlier and obsoletes
his patchkit (except for some changes on pre Sandy Bridge/Silvermont
CPUs)
I only did Sandy Bridge and Silvermont and later so far, mostly because these
are the parts I could directly confirm the hardware behavior with hardware
architects. Also I do not believe the older CPUs have any
missing events in their PEBS list, so there's no pressing
need to change them.
I did not implement the flag proposed by Peter to allow
setting forbidden flags. If really needed this could
be implemented on to of this patch.
v2: Fix broken store events on SNB/IVB (Stephane Eranian)
v3: More fixes. Rename some arguments (Stephane Eranian)
v4: List most Haswell events individually again to report
memory operation type correctly.
Add new flags to describe load/store/na for datala.
Update description.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Reviewed-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1407785233-32193-2-git-send-email-eranian@google.com
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com>
Cc: Mark Davies <junk@eslaf.co.uk>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Yan, Zheng <zheng.z.yan@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| 4485154138f6ffa5b252cb490aba3e8eb30124e4 |
|
01-Jul-2014 |
David Rientjes <rientjes@google.com> |
perf/x86/intel: Avoid spamming kernel log for BTS buffer failure
It's unnecessary to excessively spam the kernel log anytime the BTS buffer
cannot be allocated, so make this allocation __GFP_NOWARN.
The user probably will want to at least find some artifact that the
allocation has failed in the past, probably due to fragmentation because
of its large size, when it's not allocated at bootstrap. Thus, add a
WARN_ONCE() so something is left behind for them to understand why perf
commnads that require PEBS is not working properly.
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/alpine.DEB.2.02.1406301600460.26302@chino.kir.corp.google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| 722e76e60f2775c21b087ff12c5e678cf0ebcaaf |
|
15-May-2014 |
Stephane Eranian <eranian@google.com> |
fix Haswell precise store data source encoding
This patch fixes a bug in precise_store_data_hsw() whereby
it would set the data source memory level to the wrong value.
As per the the SDM Vol 3b Table 18-41 (Layout of Data Linear
Address Information in PEBS Record), when status bit 0 is set
this is a L1 hit, otherwise this is a L1 miss.
This patch encodes the memory level according to the specification.
In V2, we added the filtering on the store events.
Only the following events produce L1 information:
* MEM_UOPS_RETIRED.STLB_MISS_STORES
* MEM_UOPS_RETIRED.LOCK_STORES
* MEM_UOPS_RETIRED.SPLIT_STORES
* MEM_UOPS_RETIRED.ALL_STORES
Cc: mingo@elte.hu
Cc: acme@ghostprotocols.net
Cc: jolsa@redhat.com
Cc: jmario@redhat.com
Cc: ak@linux.intel.com
Tested-and-Reviewed-by: Don Zickus <dzickus@redhat.com>
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20140515155644.GA3884@quad
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
|
| 0a196848ca365ec582c6d86659be456be6d4ed96 |
|
30-Oct-2013 |
Peter Zijlstra <peterz@infradead.org> |
perf: Fix arch_perf_out_copy_user default
The arch_perf_output_copy_user() default of
__copy_from_user_inatomic() returns bytes not copied, while all other
argument functions given DEFINE_OUTPUT_COPY() return bytes copied.
Since copy_from_user_nmi() is the odd duck out by returning bytes
copied where all other *copy_{to,from}* functions return bytes not
copied, change it over and ammend DEFINE_OUTPUT_COPY() to expect bytes
not copied.
Oddly enough DEFINE_OUTPUT_COPY() already returned bytes not copied
while expecting its worker functions to return bytes copied.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: will.deacon@arm.com
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/r/20131030201622.GR16117@laptop.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| 9536c8d2da8059b00775bd9c5a84816b608cf6f4 |
|
15-Oct-2013 |
Peter Zijlstra <peterz@infradead.org> |
perf/x86: Optimize intel_pmu_pebs_fixup_ip()
There's been reports of high NMI handler overhead, highlighted by
such kernel messages:
[ 3697.380195] perf samples too long (10009 > 10000), lowering kernel.perf_event_max_sample_rate to 13000
[ 3697.389509] INFO: NMI handler (perf_event_nmi_handler) took too long to run: 9.331 msecs
Don Zickus analyzed the source of the overhead and reported:
> While there are a few places that are causing latencies, for now I focused on
> the longest one first. It seems to be 'copy_user_from_nmi'
>
> intel_pmu_handle_irq ->
> intel_pmu_drain_pebs_nhm ->
> __intel_pmu_drain_pebs_nhm ->
> __intel_pmu_pebs_event ->
> intel_pmu_pebs_fixup_ip ->
> copy_from_user_nmi
>
> In intel_pmu_pebs_fixup_ip(), if the while-loop goes over 50, the sum of
> all the copy_from_user_nmi latencies seems to go over 1,000,000 cycles
> (there are some cases where only 10 iterations are needed to go that high
> too, but in generall over 50 or so). At this point copy_user_from_nmi
> seems to account for over 90% of the nmi latency.
The solution to that is to avoid having to call copy_from_user_nmi() for
every instruction.
Since we already limit the max basic block size, we can easily
pre-allocate a piece of memory to copy the entire thing into in one
go.
Don reported this test result:
> Your patch made a huge difference in improvement. The
> copy_from_user_nmi() no longer hits the million of cycles. I still
> have a batch of 100,000-300,000 cycles. My longest NMI paths used
> to be dominated by copy_from_user_nmi, now it is not (I have to dig
> up the new hot path).
Reported-and-tested-by: Don Zickus <dzickus@redhat.com>
Cc: jmario@redhat.com
Cc: acme@infradead.org
Cc: dave.hansen@linux.intel.com
Cc: eranian@google.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131016105755.GX10651@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| a405bad5ad2086766ce320b16a56952e013327f8 |
|
20-Sep-2013 |
Andi Kleen <ak@linux.intel.com> |
perf/x86: Add Haswell specific transaction flag reporting
In the PEBS handler report the transaction flags using the new
generic transaction flags facility. Most of them come from
the "tsx_tuning" field in PEBSv2, but the abort code is derived
from the RAX register reported in the PEBS record.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1379688044-14173-3-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| 92519bbc8af612975410def52bd462ca9af85cdb |
|
20-Sep-2013 |
Peter Zijlstra <peterz@infradead.org> |
perf/x86/intel: Fix build warning in intel_pmu_drain_pebs_nhm()
Fengguang Wu reported this build warning:
arch/x86/kernel/cpu/perf_event_intel_ds.c: In function 'intel_pmu_drain_pebs_nhm':
arch/x86/kernel/cpu/perf_event_intel_ds.c:964:2: warning: format '%ld' expects argument of type 'long int', but argument 4 has type 'int'
Because pointer arithmetics result type is bitness dependent there's no natural
type to use here, cast it to long.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-jbpauwxJqtf24luewcsdFith@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| eb8417aa703eff5ff43d0275f19b0a8e591d818d |
|
16-Sep-2013 |
Peter Zijlstra <peterz@infradead.org> |
perf/x86/intel: Remove division from the intel_pmu_drain_pebs_nhm() hot path
Only do the division in case we have to print the result out in a warning.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-43nl31erfbajwpfj254f6zji@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| 9d8e3f9693245415db0b7c58551a91fa9fd1f9c7 |
|
13-Sep-2013 |
Stephane Eranian <eranian@google.com> |
perf/x86/intel: Mark MEM_LOAD_UOPS_MISS_RETIRED as precise on SNB
On Intel SNB (SNB, SNB-EP), the event MEM_LOAD_UOPS_MISS_RETIRED
supports PEBS. It was missing for the SNB PEBS event constraint
table thereby preventing any measurement with PEBS for it.
This patch adds the event to the PEBS table for SNB.
WARNING: it should be noted that this event like a few others
are subject to the erratum BT241 for Xeon E5 (SNB-EP). As such,
the event may undercount when used with PEBS unless the
workaround is implemented. But without this patch and just the
workaround, the kernel would not allow precise sampling on this
event. BT241 is documented in:
http://www.intel.com/content/dam/www/public/us/en/documents/specification-updates/xeon-e5-family-spec-update.pdf
Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: peterz@infradead.org
Cc: ak@linux.intel.com
Cc: zheng.z.yan@intel.com
Link: http://lkml.kernel.org/r/20130913201646.GA23981@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| d2beea4a3419e63804094e9ac4b6d1518bc17a9b |
|
12-Sep-2013 |
Peter Zijlstra <peterz@infradead.org> |
perf/x86/intel: Clean-up/reduce PEBS code
Get rid of some pointless duplication introduced by the Haswell code.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-8q6y4davda9aawwv5yxe7klp@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| 748e86aa90edfddfa6016f1cf383ff5bc6aada91 |
|
06-Sep-2013 |
Andi Kleen <ak@linux.intel.com> |
perf/x86: Report TSX transaction abort cost as weight
Use the existing weight reporting facility to report the transaction
abort cost, that is the number of cycles wasted in aborts.
Haswell reports this in the PEBS record.
This was in fact the original user for weight.
This is a very useful sort key to concentrate on the most
costly aborts and a good metric for TSX tuning.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1378438661-24765-3-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| 7bfb7e6bdd906f11ee9e751b3fec4f4fc728e818 |
|
29-Aug-2013 |
Joe Perches <joe@perches.com> |
perf: Convert kmalloc_node(...GFP_ZERO...) to kzalloc_node()
Use the convenience function instead of __GFP_ZERO.
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/f58599ae1a8d7b32d37e9cf283e95fba6452f7f6.1377809875.git.joe@perches.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| 1fa64180fbf7a33b7a30636a2f174a5cad68d48f |
|
18-Jul-2013 |
Yan, Zheng <zheng.z.yan@intel.com> |
perf/x86: Add Silvermont (22nm Atom) support
Compared to old atom, Silvermont has offcore and has more events
that support PEBS.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1374138144-17278-2-git-send-email-zheng.z.yan@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| 983433b5812c5cf33a9008fa38c6f9b407fedb76 |
|
21-Jun-2013 |
Stephane Eranian <eranian@google.com> |
perf/x86: Disable PEBS-LL in intel_pmu_pebs_disable()
Make sure intel_pmu_pebs_disable() and intel_pmu_pebs_enable()
are symmetrical w.r.t. PEBS-LL and precise store.
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1371824448-7306-2-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| f9134f36aed59ab55c0ab1a4618dd455f15aef5f |
|
18-Jun-2013 |
Andi Kleen <ak@linux.intel.com> |
perf/x86/intel: Add mem-loads/stores support for Haswell
mem-loads is basically the same as Sandy Bridge,
but we use a separate string for changes later.
Haswell doesn't support the full precise store mode,
so we emulate it using the "DataLA" facility.
This allows to do everything, but for data sources we
can only detect L1 hit or not.
There is no explicit enable bit anymore, so we have
to tie it to a perf internal only flag.
The address is supported for all memory related PEBS
events with DataLA. Instead of only logging for the
load and store events we allow logging it for all
(it will be simply 0 if the current event does not
support it)
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Andi Kleen <ak@linux.jf.intel.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: http://lkml.kernel.org/r/1371515812-9646-7-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| 3044318f1f3a2a0a636b4c751ddb7169cb1b11b2 |
|
18-Jun-2013 |
Andi Kleen <ak@linux.intel.com> |
perf/x86/intel: Add Haswell PEBS support
Add simple PEBS support for Haswell.
The constraints are similar to SandyBridge with a few new
events.
Reviewed-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Andi Kleen <ak@linux.jf.intel.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: http://lkml.kernel.org/r/1371515812-9646-4-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| 130768b8c93cd8d21390a136ec8cef417153ca14 |
|
18-Jun-2013 |
Andi Kleen <ak@linux.intel.com> |
perf/x86/intel: Add Haswell PEBS record support
Add support for the Haswell extended (fmt2) PEBS format.
It has a superset of the nhm (fmt1) PEBS fields, but has a
longer record so we need to adjust the code paths.
The main advantage is the new "EventingRip" support which
directly gives the instruction, not off-by-one instruction. So
with precise == 2 we use that directly and don't try to use LBRs
and walking basic blocks. This lowers the overhead of using
precise significantly.
Some other features are added in later patches.
Reviewed-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Andi Kleen <ak@linux.jf.intel.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: http://lkml.kernel.org/r/1371515812-9646-2-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| 9ad64c0f481c37a63dd39842a0fd264bee44a097 |
|
24-Jan-2013 |
Stephane Eranian <eranian@google.com> |
perf/x86: Add support for PEBS Precise Store
This patch adds support for PEBS Precise Store
which is available on Intel Sandy Bridge and
Ivy Bridge processors.
To use Precise store, the proper PEBS event
must be used: mem_trans_retired:precise_stores.
For the perf tool, the generic mem-stores event
exported via sysfs can be used directly.
Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: peterz@infradead.org
Cc: ak@linux.intel.com
Cc: acme@redhat.com
Cc: jolsa@redhat.com
Cc: namhyung.kim@lge.com
Link: http://lkml.kernel.org/r/1359040242-8269-11-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
| f20093eef5f7843a25adfc0512617d4b1ff1aa6e |
|
24-Jan-2013 |
Stephane Eranian <eranian@google.com> |
perf/x86: Add memory profiling via PEBS Load Latency
This patch adds support for memory profiling using the
PEBS Load Latency facility.
Load accesses are sampled by HW and the instruction
address, data address, load latency, data source, tlb,
locked information can be saved in the sampling buffer
if using the PERF_SAMPLE_COST (for latency),
PERF_SAMPLE_ADDR, PERF_SAMPLE_DATA_SRC types.
To enable PEBS Load Latency, users have to use the
model specific event:
- on NHM/WSM: MEM_INST_RETIRED:LATENCY_ABOVE_THRESHOLD
- on SNB/IVB: MEM_TRANS_RETIRED:LATENCY_ABOVE_THRESHOLD
To make things easier, this patch also exports a generic
alias via sysfs: mem-loads. It export the right event
encoding based on the host CPU and can be used directly
by the perf tool.
Loosely based on Intel's Lin Ming patch posted on LKML
in July 2011.
Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: peterz@infradead.org
Cc: ak@linux.intel.com
Cc: acme@redhat.com
Cc: jolsa@redhat.com
Cc: namhyung.kim@lge.com
Link: http://lkml.kernel.org/r/1359040242-8269-9-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
| 9fac2cf316b070ae43d2ae2525e381ff2d1d68aa |
|
24-Jan-2013 |
Stephane Eranian <eranian@google.com> |
perf/x86: Add flags to event constraints
This patch adds a flags field to each event constraint.
It can be used to store event specific features which can
then later be used by scheduling code or low-level x86 code.
The flags are propagated into event->hw.flags during the
get_event_constraint() call. They are cleared during the
put_event_constraint() call.
This mechanism is going to be used by the PEBS-LL patches.
It avoids defining yet another table to hold event specific
information.
Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: peterz@infradead.org
Cc: ak@linux.intel.com
Cc: jolsa@redhat.com
Cc: namhyung.kim@lge.com
Link: http://lkml.kernel.org/r/1359040242-8269-4-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
| 0e48026ae7abf871e51eaa9183c81ab5bef4c267 |
|
19-Mar-2013 |
Stephane Eranian <eranian@google.com> |
perf/x86: Fix uninitialized pt_regs in intel_pmu_drain_bts_buffer()
This patch fixes an uninitialized pt_regs struct in drain BTS
function. The pt_regs struct is propagated all the way to the
code_get_segment() function from perf_instruction_pointer()
and may get garbage.
We cannot simply inherit the actual pt_regs from the interrupt
because BTS must be flushed on context-switch or when the
associated event is disabled. And there we do not have a pt_regs
handy.
Setting pt_regs to all zeroes may not be the best option but it
is not clear what else to do given where the drain_bts_buffer()
is called from.
In V2, we move the memset() later in the code to avoid doing it
when we end up returning early without doing the actual BTS
processing. Also dropped the reg.val initialization because it
is redundant with the memset() as suggested by PeterZ.
Signed-off-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: peterz@infradead.org
Cc: sqazi@google.com
Cc: ak@linux.intel.com
Cc: jolsa@redhat.com
Link: http://lkml.kernel.org/r/20130319151038.GA25439@quad
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| 2a6e06b2aed6995af401dcd4feb5e79a0c7ea554 |
|
17-Mar-2013 |
Linus Torvalds <torvalds@linux-foundation.org> |
perf,x86: fix wrmsr_on_cpu() warning on suspend/resume
Commit 1d9d8639c063 ("perf,x86: fix kernel crash with PEBS/BTS after
suspend/resume") fixed a crash when doing PEBS performance profiling
after resuming, but in using init_debug_store_on_cpu() to restore the
DS_AREA mtrr it also resulted in a new WARN_ON() triggering.
init_debug_store_on_cpu() uses "wrmsr_on_cpu()", which in turn uses CPU
cross-calls to do the MSR update. Which is not really valid at the
early resume stage, and the warning is quite reasonable. Now, it all
happens to _work_, for the simple reason that smp_call_function_single()
ends up just doing the call directly on the CPU when the CPU number
matches, but we really should just do the wrmsr() directly instead.
This duplicates the wrmsr() logic, but hopefully we can just remove the
wrmsr_on_cpu() version eventually.
Reported-and-tested-by: Parag Warudkar <parag.lkml@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
| 1d9d8639c063caf6efc2447f5f26aa637f844ff6 |
|
15-Mar-2013 |
Stephane Eranian <eranian@google.com> |
perf,x86: fix kernel crash with PEBS/BTS after suspend/resume
This patch fixes a kernel crash when using precise sampling (PEBS)
after a suspend/resume. Turns out the CPU notifier code is not invoked
on CPU0 (BP). Therefore, the DS_AREA (used by PEBS) is not restored properly
by the kernel and keeps it power-on/resume value of 0 causing any PEBS
measurement to crash when running on CPU0.
The workaround is to add a hook in the actual resume code to restore
the DS Area MSR value. It is invoked for all CPUS. So for all but CPU0,
the DS_AREA will be restored twice but this is harmless.
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
| 20a36e39d59757252edbbdcf9574ae2998733ce9 |
|
11-Sep-2012 |
Stephane Eranian <eranian@google.com> |
perf/x86: Fix Intel Ivy Bridge support
This patch updates the existing Intel IvyBridge (model 58)
support with proper PEBS event constraints. It cannot reuse
the same as SandyBridge because some events (0xd3) are
specific to IvyBridge.
Also there is no UOPS_DISPATCHED.THREAD on IVB, so do not
populate the PERF_COUNT_HW_STALLED_CYCLES_BACKEND mapping.
Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: peterz@infradead.org
Cc: ak@linux.intel.com
Link: http://lkml.kernel.org/r/20120910230701.GA5898@quad
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| d07bdfd322d307789f15b427dbcc39257665356f |
|
10-Jul-2012 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf/x86: Fix USER/KERNEL tagging of samples properly
Some PMUs don't provide a full register set for their sample,
specifically 'advanced' PMUs like AMD IBS and Intel PEBS which provide
'better' than regular interrupt accuracy.
In this case we use the interrupt regs as basis and over-write some
fields (typically IP) with different information.
The perf core however uses user_mode() to distinguish user/kernel
samples, user_mode() relies on regs->cs. If the interrupt skid pushed
us over a boundary the new IP might not be in the same domain as the
interrupt.
Commit ce5c1fe9a9e ("perf/x86: Fix USER/KERNEL tagging of samples")
tried to fix this by making the perf core use kernel_ip(). This
however is wrong (TM), as pointed out by Linus, since it doesn't allow
for VM86 and non-zero based segments in IA32 mode.
Therefore, provide a new helper to set the regs->ip field,
set_linear_ip(), which massages the regs into a suitable state
assuming the provided IP is in fact a linear address.
Also modify perf_instruction_pointer() and perf_callchain_user() to
deal with segments base offsets.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1341910954.3462.102.camel@twins
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| 15c7ad51ad58cbd3b46112c1840bc7228bd354bf |
|
20-Jun-2012 |
Robert Richter <robert.richter@amd.com> |
perf/x86: Rename Intel specific macros
There are macros that are Intel specific and not x86 generic. Rename
them into INTEL_*.
This patch removes X86_PMC_IDX_GENERIC and does:
$ sed -i -e 's/X86_PMC_MAX_/INTEL_PMC_MAX_/g' \
arch/x86/include/asm/kvm_host.h \
arch/x86/include/asm/perf_event.h \
arch/x86/kernel/cpu/perf_event.c \
arch/x86/kernel/cpu/perf_event_p4.c \
arch/x86/kvm/pmu.c
$ sed -i -e 's/X86_PMC_IDX_FIXED/INTEL_PMC_IDX_FIXED/g' \
arch/x86/include/asm/perf_event.h \
arch/x86/kernel/cpu/perf_event.c \
arch/x86/kernel/cpu/perf_event_intel.c \
arch/x86/kernel/cpu/perf_event_intel_ds.c \
arch/x86/kvm/pmu.c
$ sed -i -e 's/X86_PMC_MSK_/INTEL_PMC_MSK_/g' \
arch/x86/include/asm/perf_event.h \
arch/x86/kernel/cpu/perf_event.c
Signed-off-by: Robert Richter <robert.richter@amd.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1340217996-2254-2-git-send-email-robert.richter@amd.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| 70ab7003dec58afeae7f5d681dfa309b3a259f03 |
|
06-Jun-2012 |
Andi Kleen <ak@linux.intel.com> |
perf/x86: Don't assume there can be only 4 PEBS events
On Sandy Bridge in non HT mode there are 8 counters available.
Since every counter can write a PEBS record assuming there are
4 max is incorrect. Use the reported counter number -- with an
upper limit for a static array -- instead.
Also I made the warning messages a bit more informational.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1338944211-28275-2-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| 212d95dfdb66e5c81879b08e4f7fbfc8498b1ab5 |
|
05-Jun-2012 |
Peter Zijlstra <peterz@infradead.org> |
perf/x86: Update SNB PEBS constraints
Afaict there's no need to (incompletely) iterate the
MEM_UOPS_RETIRED.* umask state.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1338884803.28282.153.camel@twins
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| 8440ccb43fc0ecffcf1acee0273d766e6a8cd51d |
|
05-Jun-2012 |
Peter Zijlstra <peterz@infradead.org> |
perf/x86: Update SNB PEBS constraints
Afaict there's no need to (incompletely) iterate the
MEM_UOPS_RETIRED.* umask state.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1338884803.28282.153.camel@twins
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| fd0d000b2c34aa43d4e92dcf0dfaeda7e123008a |
|
02-Apr-2012 |
Robert Richter <robert.richter@amd.com> |
perf: Pass last sampling period to perf_sample_data_init()
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 <robert.richter@amd.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1333390758-10893-3-git-send-email-robert.richter@amd.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
| 3e702ff6d1ea12dcf1c798ecb61e7f3a1579df42 |
|
09-Feb-2012 |
Stephane Eranian <eranian@google.com> |
perf/x86: Add LBR software filter support for Intel CPUs
This patch adds an internal sofware filter to complement
the (optional) LBR hardware filter.
The software filter is necessary:
- as a substitute when there is no HW LBR filter (e.g., Atom, Core)
- to complement HW LBR filter in case of errata (e.g., Nehalem/Westmere)
- to provide finer grain filtering (e.g., all processors)
Sometimes the LBR HW filter cannot distinguish between two types
of branches. For instance, to capture syscall as CALLS, it is necessary
to enable the LBR_FAR filter which will also capture JMP instructions.
Thus, a second pass is necessary to filter those out, this is what the
SW filter can do.
The SW filter is built on top of the internal x86 disassembler. It
is a best effort filter especially for user level code. It is subject
to the availability of the text page of the program.
The SW filter is enabled on all Intel processors. It is bypassed
when the user is capturing all branches at all priv levels.
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1328826068-11713-9-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| 60ce0fbd072695866cb27b729690ab59dce705a5 |
|
09-Feb-2012 |
Stephane Eranian <eranian@google.com> |
perf/x86: Implement PERF_SAMPLE_BRANCH for Intel CPUs
This patch implements PERF_SAMPLE_BRANCH support for Intel
x86processors. It connects PERF_SAMPLE_BRANCH to the actual LBR.
The patch adds the hooks in the PMU irq handler to save the LBR
on counter overflow for both regular and PEBS modes.
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1328826068-11713-8-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| 84f2b9b2edc09595569c7397cc3c888764ffd78b |
|
02-Feb-2012 |
Stephane Eranian <eranian@google.com> |
perf: Remove deprecated WARN_ON_ONCE()
With the new throttling/unthrottling code introduced with
commit:
e050e3f0a71b ("perf: Fix broken interrupt rate throttling")
we occasionally hit two WARN_ON_ONCE() checks in:
- intel_pmu_pebs_enable()
- intel_pmu_lbr_enable()
- x86_pmu_start()
The assertions are no longer problematic. There is a valid
path where they can trigger but it is harmless.
The assertion can be triggered with:
$ perf record -e instructions:pp ....
Leading to paths:
intel_pmu_pebs_enable
intel_pmu_enable_event
x86_perf_event_set_period
x86_pmu_start
perf_adjust_freq_unthr_context
perf_event_task_tick
scheduler_tick
And:
intel_pmu_lbr_enable
intel_pmu_enable_event
x86_perf_event_set_period
x86_pmu_start
perf_adjust_freq_unthr_context.
perf_event_task_tick
scheduler_tick
cpuc->enabled is always on because when we get to
perf_adjust_freq_unthr_context() the PMU is not totally
disabled. Furthermore when we need to adjust a period,
we only stop the event we need to change and not the
entire PMU. Thus, when we re-enable, cpuc->enabled is
already set. Note that when we stop the event, both
pebs and lbr are stopped if necessary (and possible).
Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: peterz@infradead.org
Link: http://lkml.kernel.org/r/20120202110401.GA30911@quad
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| 57d1c0c03c6b48b2b96870d831b9ce6b917f53ac |
|
07-Oct-2011 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf/x86: Fix PEBS instruction unwind
Masami spotted that we always try to decode the instruction stream as
64bit instructions when running a 64bit kernel, this doesn't work for
ia32-compat proglets.
Use TIF_IA32 to detect if we need to use the 32bit instruction
decoder.
Reported-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: stable@kernel.org
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| de0428a7ad4856c7b5b8a2792488ac893e6f3faa |
|
31-Aug-2011 |
Kevin Winchester <kjwinchester@gmail.com> |
x86, perf: Clean up perf_event cpu code
The CPU support for perf events on x86 was implemented via included C files
with #ifdefs. Clean this up by creating a new header file and compiling
the vendor-specific files as needed.
Signed-off-by: Kevin Winchester <kjwinchester@gmail.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1314747665-2090-1-git-send-email-kjwinchester@gmail.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| a7ac67ea021b4603095d2aa458bc41641238f22c |
|
27-Jun-2011 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf: Remove the perf_output_begin(.sample) argument
Since only samples call perf_output_sample() its much saner (and more
correct) to put the sample logic in there than in the
perf_output_begin()/perf_output_end() pair.
Saves a useless argument, reduces conditionals and shrinks
struct perf_output_handle, win!
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-2crpvsx3cqu67q3zqjbnlpsc@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| a8b0ca17b80e92faab46ee7179ba9e99ccb61233 |
|
27-Jun-2011 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf: Remove the nmi parameter from the swevent and overflow interface
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 <a.p.zijlstra@chello.nl>
Cc: Michael Cree <mcree@orcon.net.nz>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: Anton Blanchard <anton@samba.org>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jason Wessel <jason.wessel@windriver.com>
Cc: Don Zickus <dzickus@redhat.com>
Link: http://lkml.kernel.org/n/tip-agjev8eu666tvknpb3iaj0fg@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| 7d5d02dadd43db7f829775e404e82019c5d5586f |
|
09-Mar-2011 |
Lin Ming <ming.m.lin@intel.com> |
perf, x86: Use INTEL_*_CONSTRAINT() for all PEBS event constraints
PEBS_EVENT_CONSTRAINT() is just a duplicate of INTEL_UEVENT_CONSTRAINT().
Remove it and use INTEL_UEVENT_CONSTRAINT() instead.
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1299684089-22835-3-git-send-email-ming.m.lin@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| eefaaac46470d105f58cff93c8176cfadc75b857 |
|
09-Mar-2011 |
Lin Ming <ming.m.lin@intel.com> |
perf, x86: Clean up SandyBridge PEBS events
Use INTEL_EVENT_CONSTRAINT() for the events where all umasks support PEBS.
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1299684089-22835-2-git-send-email-ming.m.lin@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| 17e3162972cbb9796035fff1e2fd30669b0eef65 |
|
02-Mar-2011 |
Stephane Eranian <eranian@google.com> |
perf_events: Update PEBS event constraints
This patch updates PEBS event constraints for Intel Atom, Nehalem, Westmere.
This patch also reorganizes the PEBS format/constraint detection code. It is
now based on processor model and not PEBS format. Two processors may use the
same PEBS format without have the same list of PEBS events.
In this second version, we simplified the initialization of the PEBS
constraints by leveraging the existing switch() statement in perf_event_intel.c.
We also renamed the constraint tables to be more consistent with regular
constraints.
In this 3rd version, we drop BR_INST_RETIRED.MISPRED from Intel Atom as it does
not seem to work. Use MISPREDICTED_BRANCH_RETIRED instead. Also add FP_ASSIST.*
o both Intel Nehalem and Westmere. I misssed those in the earlier patches.
Events were tested using libpfm4 perf_examples.
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <4d6e6b02.815bdf0a.637b.07a7@mx.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| b06b3d49699a52e8f9ca056c4f96e81b1987d78e |
|
02-Mar-2011 |
Lin Ming <ming.m.lin@intel.com> |
perf, x86: Add Intel SandyBridge CPU support
This patch adds basic SandyBridge support, including hardware
cache events and PEBS events support.
It has been tested on SandyBridge CPUs with perf stat and also
with PEBS based profiling - both work fine.
The patch does not affect other models.
v2 -> v3:
- fix PEBS event 0xd0 with right umask combinations
- move snb pebs constraint assignment to intel_pmu_init
v1 -> v2:
- add more raw and PEBS events constraints
- use offcore events for LLC-* cache events
- remove the call to Nehalem workaround enable_all function
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Cc: Andi Kleen <andi@firstfloor.org>
LKML-Reference: <1299072424.2175.24.camel@localhost>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| 96681fc3c9e7d1f89ab64e5eec40b6467c97680f |
|
19-Oct-2010 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf, x86: Use NUMA aware allocations for PEBS/BTS/DS allocations
For performance reasons its best to use memory node local memory for
per-cpu buffers.
This logic comes from a much larger patch proposed by Stephane.
Suggested-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Stephane Eranian <eranian@google.com>
LKML-Reference: <20101019134808.514465326@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| f80c9e304b8e8062230b0cda2c2fdd586149c771 |
|
19-Oct-2010 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf, x86: Clean up reserve_ds_buffers() signature
Now that reserve_ds_buffers() never fails, change it to return
void and remove all code dealing with the error return.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Stephane Eranian <eranian@google.com>
LKML-Reference: <20101019134808.462621937@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| 6809b6ea73f7291f2e495d40397f1172c9caa77e |
|
19-Oct-2010 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf, x86: Less disastrous PEBS/BTS buffer allocation failure
Currently PEBS/BTS buffers are allocated when we instantiate the first
event, when this fails everything fails.
This is a problem because esp. BTS tries to allocate a rather large
buffer (64K), which can easily fail.
This patch changes the logic such that when either buffer allocation
fails, we simply don't allow events that would use these facilities,
but continue functioning for all other events.
This logic comes from a much larger patch proposed by Stephane.
Suggested-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Stephane Eranian <eranian@google.com>
LKML-Reference: <20101019134808.354429461@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| 65af94baca56beb3514d6cfce782634db9cf676d |
|
19-Oct-2010 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf, x86: Extract DS alloc/free functions
Again, mostly a cleanup to unclutter the reserve_ds_buffer() code.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Stephane Eranian <eranian@google.com>
LKML-Reference: <20101019134808.304495776@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| 5ee25c87318fa3722026fd77089fa7ba0db8d447 |
|
19-Oct-2010 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf, x86: Extract PEBS/BTS allocation functions
Mostly a cleanup.. it reduces code indentation and makes the code flow
of reserve_ds_buffers() clearer.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Stephane Eranian <eranian@google.com>
LKML-Reference: <20101019134808.253453452@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| b39f88acd7d989b6b247ba87c480fc24ed71d9c5 |
|
19-Oct-2010 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf, x86: Extract PEBS/BTS buffer free routines
So that we may grow additional call-sites..
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Stephane Eranian <eranian@google.com>
LKML-Reference: <20101019134808.196793164@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| b0b2072df3b544f56b90173c2cde7a374c51546b |
|
10-Sep-2010 |
Stephane Eranian <eranian@google.com> |
perf_events: Fix BTS interrupt handling to avoid being dazed by NMI (v2)
Fix a bug introduced with commit de725de and the change in the
meaning of the return value of intel_pmu_handle_irq(). With the
current code, when you are using the BTS, you get 'dazed by NMI'
each time the BTS buffer fills up.
BTS does interrupt on the PMU vector, thus NMI. You need to take
this into account in the return value of the function.
This version fixes initial patch which was missing changes to
perf_event_intel_ds.c.
Signed-off-by: Stephane Eranian <eranian@google.com>
Acked-by: Don Zickus <dzickus@redhat.com>
Cc: peterz@infradead.org
Cc: paulus@samba.org
Cc: davem@davemloft.net
Cc: fweisbec@gmail.com
Cc: perfmon2-devel@lists.sf.net
Cc: eranian@gmail.com
Cc: robert.richter@amd.com
LKML-Reference: <4c8a1686.aae9d80a.5aa4.5e35@mx.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| a4eaf7f14675cb512d69f0c928055e73d0c6d252 |
|
16-Jun-2010 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| ab608344bcbde4f55ec4cd911b686b0ce3eae076 |
|
08-Apr-2010 |
Peter Zijlstra <peterz@infradead.org> |
perf, x86: Improve the PEBS ABI
Rename perf_event_attr::precise to perf_event_attr::precise_ip and
widen it to 2 bits. This new field describes the required precision of
the PERF_SAMPLE_IP field:
0 - SAMPLE_IP can have arbitrary skid
1 - SAMPLE_IP must have constant skid
2 - SAMPLE_IP requested to have 0 skid
3 - SAMPLE_IP must have 0 skid
And modify the Intel PEBS code accordingly. The PEBS implementation
now supports up to precise_ip == 2, where we perform the IP fixup.
Also s/PERF_RECORD_MISC_EXACT/&_IP/ to clarify its meaning, this bit
should be set for each PERF_SAMPLE_IP field known to match the actual
instruction triggering the event.
This new scheme allows for a PEBS mode that uses the buffer for more
than a single event.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Stephane Eranian <eranian@google.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| 2b0b5c6fe9b383f3cf35a0a6371c9d577bd523ff |
|
08-Apr-2010 |
Peter Zijlstra <peterz@infradead.org> |
perf, x86: Consolidate some code repetition
Remove some duplicated logic.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| 1e9a6d8d44cb6dcd2799b36ceb23007e6a423bfe |
|
04-May-2010 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf, x86: Remove PEBS SAMPLE_RAW support
Its broken, we really should get PERF_SAMPLE_REGS sorted.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| 7c5ecaf7666617889f337296c610815b519abfa9 |
|
25-Mar-2010 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf, x86: Clean up debugctlmsr bit definitions
Move all debugctlmsr thingies into msr-index.h
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20100325135413.861425293@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| caa0142d84ceb0fc83e28f0475d0a7316cb6df77 |
|
06-Jun-2009 |
Ingo Molnar <mingo@elte.hu> |
perf, x86: Fix the !CONFIG_CPU_SUP_INTEL build
Fix typo. But the modularization here is ugly and should be improved.
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| d80c7502ff63aa0d99d8c0c5803d28bbef67a74e |
|
09-Mar-2010 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf, x86: Fixup the PEBS handler for Core2 cpus
Pull the core handler in line with the nhm one, also make sure we always
drain the buffer.
Signed-off-by: Peter 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: Ingo Molnar <mingo@elte.hu>
|
| ad0e6cfe2a2a61d7b5530188e571d508146cb43b |
|
06-Mar-2010 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf, x86: Fix silly bug in intel_pmu_pebs_{enable,disable}
We need to use the actual cpuc->pebs_enabled value, not a local copy for
the changes to take effect.
Signed-off-by: Peter 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: Ingo Molnar <mingo@elte.hu>
|
| 12ab854d744f04bfc5c6c4db723b7e31fc03eb29 |
|
06-Mar-2010 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf, x86: Deal with multiple state bits for pebs-fmt1
Its unclear if the PEBS state record will have only a single bit set, in
case it does not and accumulates bits, deal with that by only processing
each event once.
Also, robustify some of the code.
Signed-off-by: Peter 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: Ingo Molnar <mingo@elte.hu>
|
| 4807e3d5dc7bb7057dd6ca3abb09f3da2eb8c323 |
|
06-Mar-2010 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf, x86: Fix PEBS enable/disable vs cpuc->enabled
We should never call ->enable with the pmu enabled, and we _can_ have
->disable called with the pmu enabled.
Signed-off-by: Peter 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: Ingo Molnar <mingo@elte.hu>
|
| 8f4aebd2be9892bf8fb79a2d8576d3f3ee7f00f6 |
|
06-Mar-2010 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf, x86: Fix pebs drains
I overlooked the perf_disable()/perf_enable() calls in
intel_pmu_handle_irq(), (pointed out by Markus) so we should not
explicitly disable_all/enable_all pebs counters in the drain functions,
these are already disabled and enabling them early is confusing.
Signed-off-by: Peter 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: Ingo Molnar <mingo@elte.hu>
|
| cc7f00820b2f3be656569c41158d9323e425bcfe |
|
08-Mar-2010 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf, x86: Avoid double disable on throttle vs ioctl(PERF_IOC_DISABLE)
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: Peter 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: Ingo Molnar <mingo@elte.hu>
|
| a562b1871f7f7d2f3a835c3c1e07fa58d473cfb7 |
|
05-Mar-2010 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf, x86: Robustify PEBS fixup
It turns out the LBR is massively unreliable on certain CPUs, so code the
fixup a little more defensive to avoid crashing the kernel.
Signed-off-by: Peter 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: <20100305154129.042271287@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| 3adaebd69557615c1bf0365ce5e32d93ac7d82af |
|
05-Mar-2010 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf, x86: Fix silly bug in data store buffer allocation
Fix up the ds allocation error path, where we could free @buffer before
we used it.
Signed-off-by: Peter 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: <20100305154128.813452402@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| 30a813ae035d3e220a89609adce878e045c49547 |
|
04-Mar-2010 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
x86: Move MAX_INSN_SIZE into asm/insn.h
Since there's now two users for this, place it in a common header.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.923774125@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| 7e1a40dda619b0483fbe0740494ed2c2a1f05289 |
|
04-Mar-2010 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf, x86: Expose the full PEBS record using PERF_SAMPLE_RAW
Expose the full PEBS record using PERF_SAMPLE_RAW
Signed-off-by: Peter 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: <20100304140100.847218224@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| 8db909a7e3c888b5d45aef7650d74ccebe3ce725 |
|
03-Mar-2010 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf, x86: Clean up IA32_PERF_CAPABILITIES usage
Saner PERF_CAPABILITIES support, which also exposes pebs_trap. Use that
latter to make PEBS's use of LBR conditional since a fault-like pebs
should already report the correct IP.
( As of this writing there is no known hardware that implements
!pebs_trap )
Signed-off-by: Peter 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: <20100304140100.770650663@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| ef21f683a045a79b6aa86ad81e5fdfc0d5ddd250 |
|
03-Mar-2010 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf, x86: use LBR for PEBS IP+1 fixup
Use the LBR to fix up the PEBS IP+1 issue.
As said, PEBS reports the next instruction, here we use the LBR to find
the last branch and from that construct the actual IP. If the IP matches
the LBR-TO, we use LBR-FROM, otherwise we use the LBR-TO address as the
beginning of the last basic block and decode forward.
Once we find a match to the current IP, we use the previous location.
This patch introduces a new ABI element: PERF_RECORD_MISC_EXACT, which
conveys that the reported IP (PERF_SAMPLE_IP) is the exact instruction
that caused the event (barring CPU errata).
The fixup can fail due to various reasons:
1) LBR contains invalid data (quite possible)
2) part of the basic block got paged out
3) the reported IP isn't part of the basic block (see 1)
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: "Zhang, Yanmin" <yanmin_zhang@linux.intel.com>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.619375431@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
| ca037701a025334e724e5c61b3b1082940c8b981 |
|
02-Mar-2010 |
Peter Zijlstra <a.p.zijlstra@chello.nl> |
perf, x86: Add PEBS infrastructure
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: Peter 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: Ingo Molnar <mingo@elte.hu>
|