From: "Peter Zijlstra (Intel)"
In order to free up the perf_event_read_group() name:
s/perf_event_read_\(one\|group\)/perf_read_\1/g
s/perf_read_hw/__perf_read/g
Signed-off-by: Peter Zijlstra (Intel)
---
kernel/events/core.c | 14 +++---
1 file changed, 7 insertions(+), 7 deletion
en we implement
the ability to read a group of events using the transaction interface,
we would need the two pieces done independently.
Break up perf_event_read() and have it just read/update the counter
and have the callers compute the total count if necessary.
Signed-off-by: Sukadev Bhattiprolu
---
k
'txn_flags'
parameter and use this parameter to ignore any transactions that are
not of type PERF_PMU_TXN_ADD.
Thanks to Peter Zijlstra for his input.
Signed-off-by: Sukadev Bhattiprolu
---
Changelog[v6]
- [Peter Zijlstra]
- Change txn_flags to unsigned int.
xn() calls.
Peter Zijlstra (2):
perf: Add group reads to perf_event_read()
perf: Invert perf_read_group() loops
Peter Zijlstra (Intel) (1):
perf: Rename perf_event_read_{one,group}, perf_read_hw
Sukadev Bhattiprolu (7):
perf/sparc: Remove unnecessary assignment
perf: Add a flags param
In ->commit_txn() 'cpuc' is already initialized when it is
declared, so we can remove the duplicate assignment.
Signed-off-by: Sukadev Bhattiprolu
---
arch/sparc/kernel/perf_event.c |1 -
1 file changed, 1 deletion(-)
diff --git a/arch/sparc/kernel/perf_event.c b/arch
Peter Zijlstra [pet...@infradead.org] wrote:
|
| when looking at this (I almost pressed A for apply) it occurred to me
| that we now keep double state, cpuhw->txn_flags and cpuhw->group_flag
| are basically the same thing.
|
| Would not something like the below avoid this duplication?
Yes, it ma
Sukadev Bhattiprolu [suka...@linux.vnet.ibm.com] wrote:
| CPUs support a large number of performance monitoring events (PMU events)
| and often these events are very specific to an architecture/model of the
| CPU. To use most of these PMU events with perf, we currently have to identify
| them by
Signed-off-by: Sukadev Bhattiprolu
Acked-by: Jiri Olsa
---
tools/perf/pmu-events/README | 122 ++
1 file changed, 122 insertions(+)
create mode 100644 tools/perf/pmu-events/README
diff --git a/tools/perf/pmu-events/README b/tools/perf/pmu-events/README
From: Andi Kleen
To work with existing mapfiles, assume that the first line in
'mapfile.csv' is a header line and skip over it.
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
Acked-by: Jiri Olsa
---
Changelog[v2]
All architectures may not use the "Fami
]
br_inst_exec.all_direct_jmp
[Speculative and retired macro-unconditional branches excluding
calls and indirects]
br_inst_exec.all_direct_near_call
[Speculative and retired direct near calls]
br_inst_exec.all_indirect_jump_non_call_ret
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev
Previously we were dropping the useful longer descriptions that some
events have in the event list completely. Now that jevents provides
support for longer descriptions (see previous patch), add support for
parsing the long descriptions
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev
baclears for any type of branch]
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
Acked-by: Jiri Olsa
---
Changelog[v15]
- [Jir Olsa, Andi Kleen] Fix usage strings; update man page.
Changelog[v14]
- [Jiri Olsa] Break up independent parts of the patch into
Allow assigning categories "Topics" field to the PMU events i.e.
process the topic field from the JSON file and add a corresponding
topic field to the generated C events tables.
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
Acked-by: Jiri Olsa
---
Changelog[v14]
Implement support in jevents to parse long descriptions for events
that may have them in the JSON files. A follow on patch will make this
long description available to user through the 'perf list' command.
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
Acked-by:
Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
Acked-by: Jiri Olsa
---
v2: Rename --quiet to --no-desc. Add option to man page.
---
tools/perf/Documentation/perf-list.txt |8 +++-
tools/perf/builtin-list.c | 12
tools/perf/util/parse-events.c |4 ++--
From: Andi Kleen
Add a PERF_CPUID variable to override the CPUID of the current CPU (within
the current architecture). This is useful for testing, so that all event
lists can be tested on a single system.
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
Acked-by: Jiri Olsa
From: Andi Kleen
Automatically adapt the now wider and word wrapped perf list
output to wider terminals. This requires querying the terminal
before the auto pager takes over, and exporting this
information from the pager subsystem.
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
: Sukadev Bhattiprolu
Acked-by: Jiri Olsa
---
v2: Update to new get_cpuid_str() interface
---
tools/perf/arch/x86/util/header.c | 24 +---
1 file changed, 21 insertions(+), 3 deletions(-)
diff --git a/tools/perf/arch/x86/util/header.c
b/tools/perf/arch/x86/util/header.c
index
...
arith.fpu_div
[Divide operations executed]
arith.fpu_div_active
[Cycles when divider is busy executing divide operations]
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
Acked-by: Jiri Olsa
---
Changelog
- Delete a redundant free()
Changelog[v14
Implement code that returns the generic CPU ID string for Powerpc.
This will be used to identify the specific table of PMU events to
parse/compare user specified events against.
Signed-off-by: Sukadev Bhattiprolu
Acked-by: Jiri Olsa
---
Changelog[v14]
- [Jiri Olsa] Move this
he user to specify events using their
aliases rather than raw event codes.
Based on input and some earlier patches from Andi Kleen, Jiri Olsa.
Signed-off-by: Sukadev Bhattiprolu
Acked-by: Jiri Olsa
---
Changelog[v4]
- Split off unrelated code into separate patches.
Changelog[v3]
-
lows parsing Intel style JSON event files. This
allows to use an Intel event list directly with perf. The Intel event lists
can be quite large and are too big to store in unswappable kernel memory.
The conversion from JSON to C-style is straight forward. The parser knows
(very little) Intel spe
ion I added a simple wrapper that mmaps a json
file and provides some straight forward access functions.
Used in follow-on patches to parse event files.
Acked-by: Namhyung Kim
Acked-by: Jiri Olsa
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
---
v2: Address review feedback.
v3: Minor
: Query terminal width and use in perf list
perf, tools: Add a --no-desc flag to perf list
perf, tools: Add override support for event list CPUID
perf, tools: Add support for event list topics
perf, tools: Handle header line in mapfile
Sukadev Bhattiprolu (7):
perf, tools: Use pmu_eve
erf_event and can avoid submitting a new
->read() request to the PMU.
Thanks to input from Peter Zijlstra.
Signed-off-by: Sukadev Bhattiprolu
---
Changelog[v3]
- [Peter Zijlstra] Save the transaction state in ->start_txn() and
remove the flags parameter from ->com
From: Peter Zijlstra
Enable perf_event_read() to update entire groups at once, this will be
useful for read transactions.
Cc: Ingo Molnar
Cc: Arnaldo Carvalho de Melo
Cc: Michael Ellerman
Cc: Sukadev Bhattiprolu
Signed-off-by: Peter Zijlstra (Intel)
Link:
http://lkml.kernel.org/r
nt PERF_PMU_TXN_READ ignore ->start_txn() and
->commit_txn() and continue to read counters one at a time.
Thanks to input from Peter Zijlstra.
Signed-off-by: Sukadev Bhattiprolu
---
Changelog[v4]
- [Peter Zijlstra] Add lockdep_assert_held() in perf_event_read_group().
Make s
child.
Signed-off-by: Peter Zijlstra (Intel)
Signed-off-by: Sukadev Bhattiprolu
---
Changes to Peter's patch:
- Add GFP_KERNEL to kzalloc().
- Pass in address of counter to atomic_read().
- Return event->size rather than leader->size (perf_read_group())
en we implement
the ability to read a group of events using the transaction interface,
we would need the two pieces done independently.
Break up perf_event_read() and have it just read/update the counter
and have the callers compute the total count if necessary.
Signed-off-by: Sukadev Bhattiprolu
---
k
the return
value when 'group' parameter is false.
Signed-off-by: Sukadev Bhattiprolu
---
kernel/events/core.c | 45 ++---
1 file changed, 34 insertions(+), 11 deletions(-)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2221ebe..
From: "Peter Zijlstra (Intel)"
In order to free up the perf_event_read_group() name:
s/perf_event_read_\(one\|group\)/perf_read_\1/g
s/perf_read_hw/__perf_read/g
Signed-off-by: Peter Zijlstra (Intel)
---
kernel/events/core.c | 14 +++---
1 file changed, 7 insertions(+), 7 deletion
'txn_flags'
parameter and use this parameter to ignore any transactions that are
not of type PERF_PMU_TXN_ADD.
Thanks to Peter Zijlstra for his input.
Signed-off-by: Sukadev Bhattiprolu
---
Changelog[v4]
- [Peter Zijlstra] Fix an copy-paste error in power_pmu_cancel_txn().
.
Peter Zijlstra (2):
perf: Add group reads to perf_event_read()
perf: Invert perf_read_group() loops
Peter Zijlstra (Intel) (1):
perf: Rename perf_event_read_{one,group}, perf_read_hw
Sukadev Bhattiprolu (5):
perf: Add a flags parameter to pmu txn interfaces
perf: Split perf_event_read()
Peter Zijlstra [pet...@infradead.org] wrote:
| On Tue, Aug 11, 2015 at 09:14:00PM -0700, Sukadev Bhattiprolu wrote:
| > | +static void __perf_read_group_add(struct perf_event *leader, u64
read_format, u64 *values)
| > | {
| > | + struct perf_event *sub;
| > | + int n = 1;
Peter Zijlstra [pet...@infradead.org] wrote:
| On Sun, Jul 26, 2015 at 10:40:37PM -0700, Sukadev Bhattiprolu wrote:
| > @@ -3743,7 +3762,13 @@ static u64 perf_event_aggregate(struct perf_event
*event, u64 *enabled,
| > lockdep_assert_held(&event-&g
Sukadev Bhattiprolu [suka...@linux.vnet.ibm.com] wrote:
| CPUs support a large number of performance monitoring events (PMU events)
| and often these events are very specific to an architecture/model of the
| CPU. To use most of these PMU events with perf, we currently have to identify
| them by
Peter Zijlstra [pet...@infradead.org] wrote:
| On Tue, Jul 14, 2015 at 08:01:52PM -0700, Sukadev Bhattiprolu wrote:
| > Move the part of perf_event_read_value() that computes the event
| > counts and event times into a new function, perf_event_compute().
| >
| > This would allo
erf_event and can avoid submitting a new
->read() request to the PMU.
Thanks to input from Peter Zijlstra.
Signed-off-by: Sukadev Bhattiprolu
---
Changelog[v3]
[Peter Zijlstra] Save the transaction state in ->start_txn() and
remove the flags parameter from ->commit_txn() and
nt PERF_PMU_TXN_READ ignore ->start_txn() and
->commit_txn() and continue to read counters one at a time.
Thanks to input from Peter Zijlstra.
Signed-off-by: Sukadev Bhattiprolu
---
Changelog[v4]
[Peter Zijlstra] Add lockdep_assert_held() in perf_event_read_group().
Make s
Add a return value to __perf_event_read(). The return value will be
needed later in perf_read_group() implements ability to read several
counters in a PERF_PMU_TXN_READ transaction.
Signed-off-by: Sukadev Bhattiprolu
---
kernel/events/core.c | 22 +++---
1 file changed, 19
Add a 'group' parameter to perf_event_read(). It will be used (set
to true) in a follow-on patch to update event times of the group.
Signed-off-by: Sukadev Bhattiprolu
---
kernel/events/core.c | 17 +++--
1 file changed, 11 insertions(+), 6 deletions(-)
diff --git a/ker
Add a return value to perf_event_read(). The return value will be
needed later in perf_read_group() implements ability to read several
counters in a PERF_PMU_TXN_READ transaction.
Signed-off-by: Sukadev Bhattiprolu
---
kernel/events/core.c | 19 +--
1 file changed, 13
Unroll the calls to perf_event_read_value() in perf_read_group()
so we can later optimize out parts we don't need for group events.
Signed-off-by: Sukadev Bhattiprolu
---
kernel/events/core.c | 17 +++--
1 file changed, 15 insertions(+), 2 deletions(-)
diff --git a/kernel/e
Move the part of perf_event_read_value() that aggregates the event
counts and event times into a new function, perf_event_aggregate().
This would allow us to call perf_event_aggregate() independently.
Signed-off-by: Sukadev Bhattiprolu
---
Changelog[v4]
[Peter Zijlstra] Add missing
From: "Peter Zijlstra (Intel)"
In order to free up the perf_event_read_group() name:
s/perf_event_read_\(one\|group\)/perf_read_\1/g
s/perf_read_hw/__perf_read/g
Signed-off-by: Peter Zijlstra (Intel)
---
kernel/events/core.c | 14 +++---
1 file changed, 7 insertions(+), 7 deletion
en we implement
the ability to read a group of events using the transaction interface,
we would need the two pieces done independently.
Break up perf_event_read() and have it just read/update the counter
and have the callers compute the total count if necessary.
Signed-off-by: Sukadev Bhattiprolu
---
k
tectures/PMUs that don't need the READ transaction types
simply ignore the ->start_txn() and ->commit_txn() calls.
Peter Zijlstra (Intel) (1):
perf: Rename perf_event_read_{one,group}, perf_read_hw
Sukadev Bhattiprolu (9):
perf: Add a flags parameter to pmu txn interfaces
'txn_flags'
parameter and use this parameter to ignore any transactions that are
not of type PERF_PMU_TXN_ADD.
Thanks to Peter Zijlstra for his input.
Signed-off-by: Sukadev Bhattiprolu
---
Changelog[v4]
- [Peter Zijlstra] Fix an copy-paste error in power_pmu_cancel_txn().
Peter Zijlstra [pet...@infradead.org] wrote:
| On Wed, Jul 22, 2015 at 04:19:16PM -0700, Sukadev Bhattiprolu wrote:
| > Peter Zijlstra [pet...@infradead.org] wrote:
| > | I've not woken up yet, and not actually fully read the email, but can
| > | you stuff the entire above chunk
same context, so no point in
| calling update_*time*() for every event or so.
|
Do you mean something like this (will move the rename to a separate
patch before posting):
--
From e8eddb5d3877ebdb3b71213a00aaa980f4010dd0 Mon Sep 17 00:00:00 2001
From: Sukadev Bhattiprolu
Date: Tue, 7 Jul 2015 21:45:23
Peter Zijlstra [pet...@infradead.org] wrote:
| On Tue, Jul 14, 2015 at 08:01:54PM -0700, Sukadev Bhattiprolu wrote:
| > +/*
| > + * Use the transaction interface to read the group of events in @leader.
| > + * PMUs like the 24x7 counters in Power, can use this to queue the events
| >
Herrenschmidt
| Cc: Paul Mackerras
| Cc: Anton Blanchard
| Cc: Sukadev Bhattiprolu
| Cc: Anshuman Khandual
| Cc: Stephane Eranian
| Signed-off-by: Madhavan Srinivasan
Thanks for addressing my comments from earlier version.
Reviewed-by: Sukadev Bhattiprolu
Zumeng Chen [zumeng.c...@gmail.com] wrote:
| 3. What I have seen in 3.14.x kernel,
| ==
| And so far, no more difference to 4.x kernel from me about this part if
| I'm right.
|
| *) With 1028ccf5
|
| perf list|grep -i syscall got me nothing.
|
|
| *) Without 1028ccf5
| root@
Peter Zijlstra [pet...@infradead.org] wrote:
| On Tue, Jul 14, 2015 at 08:01:52PM -0700, Sukadev Bhattiprolu wrote:
| > Move the part of perf_event_read_value() that computes the event
| > counts and event times into a new function, perf_event_compute().
| >
| > This would allo
Peter Zijlstra [pet...@infradead.org] wrote:
| On Tue, Jul 14, 2015 at 08:01:50PM -0700, Sukadev Bhattiprolu wrote:
| > @@ -1604,6 +1613,12 @@ static void power_pmu_start_txn(struct pmu *pmu)
| > static void power_pmu_cancel_txn(struct pmu *pmu)
| > {
| > struct cpu_hw_e
From: "Peter Zijlstra (Intel)"
In order to free up the perf_event_read_group() name:
s/perf_event_read_\(one\|group\)/perf_read_\1/g
s/perf_read_hw/__perf_read/g
Signed-off-by: Peter Zijlstra (Intel)
---
kernel/events/core.c | 14 +++---
1 file changed, 7 insertions(+), 7 deletion
erf_event and can avoid submitting a new
->read() request to the PMU.
Thanks to input from Peter Zijlstra.
Signed-off-by: Sukadev Bhattiprolu
Changelog[v3]
[Peter Zijlstra] Save the transaction state in ->start_txn() and
drop the flags parameter from ->commit_txn() and ->
t once.
PMUs that don't implement PERF_PMU_TXN_READ ignore ->start_txn() and
->commit_txn() and continue to read counters one at a time.
Thanks to input from Peter Zijlstra.
Signed-off-by: Sukadev Bhattiprolu
---
include/linux/perf_event.h |1 +
kernel/events/co
Move the part of perf_event_read_value() that computes the event
counts and event times into a new function, perf_event_compute().
This would allow us to call perf_event_compute() independently.
Signed-off-by: Sukadev Bhattiprolu
Changelog[v3]
Rather than move perf_event_read() into
'txn_flags'
parameter and use this parameter to ignore any transactions that are
not of type PERF_PMU_TXN_ADD.
Thanks to Peter Zijlstra for his input.
Signed-off-by: Sukadev Bhattiprolu
Changelog[v3]
- [Peter Zijlstra] Ensure the nop_txn interfaces disable/enable
en we implement
the ability to read a group of events using the transaction interface,
we would need the two pieces done independently.
Break up perf_event_read() and have it just read/update the counter
and have the callers compute the total count if necessary.
Signed-off-by: Sukadev Bhattiprolu
---
k
Simplify code that extracts a 24x7 counter from the HCALL's result buffer.
Suggested-by: Joe Perches
Signed-off-by: Sukadev Bhattiprolu
---
arch/powerpc/perf/hv-24x7.c |6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc
Fix parameter alignment to be consistent with coding style.
Signed-off-by: Sukadev Bhattiprolu
---
arch/powerpc/perf/hv-24x7.c | 20 ++--
1 file changed, 10 insertions(+), 10 deletions(-)
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index df95629
nsaction interface unconditionally to avoid special-case
code. Architectures/PMUs that don't need the READ transaction types
simply ignore the ->start_txn() and ->commit_txn() calls.
Peter Zijlstra (Intel) (1):
perf: Rename perf_event_read_{one,group}, perf_read_hw
Sukadev
Madhavan Srinivasan [ma...@linux.vnet.ibm.com] wrote:
|
| > Are the 'start.*' and 'unit.*' files events by themselves or just attributes
| > of events?
|
| These are attributes needed for computation. unit and scale attributes
| will be used by perf tool in post-processing the counter data. These
Sukadev Bhattiprolu [suka...@linux.vnet.ibm.com] wrote:
| | @@ -50,6 +163,15 @@ static int nest_ima_dt_parser(void)
| | p8ni->vbase = (uint64_t) phys_to_virt(p8ni->pbase);
| | }
| |
| | + /* Look for supported Nest PMU units */
| | + idx = 0;
| | + for_each_node_by_ty
Madhavan Srinivasan [ma...@linux.vnet.ibm.com] wrote:
| Add code to create event/format attributes and attribute groups for
| each nest pmu.
|
| Cc: Michael Ellerman
| Cc: Benjamin Herrenschmidt
| Cc: Paul Mackerras
| Cc: Anton Blanchard
| Cc: Sukadev Bhattiprolu
| Cc: Anshuman Khandual
: Michael Ellerman
| Cc: Benjamin Herrenschmidt
| Cc: Paul Mackerras
| Cc: Anton Blanchard
| Cc: Sukadev Bhattiprolu
| Cc: Anshuman Khandual
| Cc: Stephane Eranian
| Signed-off-by: Madhavan Srinivasan
| ---
| arch/powerpc/perf/nest-pmu.c | 124
++-
| 1
From 370152d9427e57cd9632b00189f71099f8e85544 Mon Sep 17 00:00:00 2001
From: Sukadev Bhattiprolu
Date: Tue, 7 Jul 2015 12:21:10 -0400
Subject: [PATCH 1/1] powerpc/perf/24x7: Fix lockdep warning
The sysfs attributes for the 24x7 counters are dynamically allocated.
Initialize the attributes using
nest pmus.
|
| Cc: Michael Ellerman
| Cc: Benjamin Herrenschmidt
| Cc: Paul Mackerras
| Cc: Anton Blanchard
| Cc: Sukadev Bhattiprolu
| Cc: Anshuman Khandual
| Cc: Stephane Eranian
| Signed-off-by: Madhavan Srinivasan
| ---
| arch/powerpc/perf/nest-pmu.c | 109
Signed-off-by: Sukadev Bhattiprolu
Acked-by: Jiri Olsa
---
tools/perf/pmu-events/README | 122 +++
1 file changed, 122 insertions(+)
create mode 100644 tools/perf/pmu-events/README
diff --git a/tools/perf/pmu-events/README b/tools/perf/pmu-events/README
From: Andi Kleen
To work with existing mapfiles, assume that the first line in
'mapfile.csv' is a header line and skip over it.
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
Acked-by: Jiri Olsa
---
Changelog[v2]
All architectures may not use the "Fami
]
br_inst_exec.all_direct_jmp
[Speculative and retired macro-unconditional branches excluding
calls and indirects]
br_inst_exec.all_direct_near_call
[Speculative and retired direct near calls]
br_inst_exec.all_indirect_jump_non_call_ret
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev
Allow assigning categories "Topics" field to the PMU events i.e.
process the topic field from the JSON file and add a corresponding
topic field to the generated C events tables.
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
Acked-by: Jiri Olsa
---
Changelog[v14]
baclears for any type of branch]
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
Acked-by: Jiri Olsa
---
Changelog[v15]
- [Jir Olsa, Andi Kleen] Fix usage strings; update man page.
Changelog[v14]
- [Jiri Olsa] Break up independent parts of the patch into
Previously we were dropping the useful longer descriptions that some
events have in the event list completely. Now that jevents provides
support for longer descriptions (see previous patch), add support for
parsing the long descriptions
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev
Implement support in jevents to parse long descriptions for events
that may have them in the JSON files. A follow on patch will make this
long description available to user through the 'perf list' command.
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
Acked-by:
From: Andi Kleen
Add a PERF_CPUID variable to override the CPUID of the current CPU (within
the current architecture). This is useful for testing, so that all event
lists can be tested on a single system.
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
Acked-by: Jiri Olsa
Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
Acked-by: Jiri Olsa
---
v2: Rename --quiet to --no-desc. Add option to man page.
---
tools/perf/Documentation/perf-list.txt | 8 +++-
tools/perf/builtin-list.c | 12
tools/perf/util/parse-events.c | 4 ++--
tools
From: Andi Kleen
Automatically adapt the now wider and word wrapped perf list
output to wider terminals. This requires querying the terminal
before the auto pager takes over, and exporting this
information from the pager subsystem.
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
: Sukadev Bhattiprolu
Acked-by: Jiri Olsa
---
v2: Update to new get_cpuid_str() interface
---
tools/perf/arch/x86/util/header.c | 24 +---
1 file changed, 21 insertions(+), 3 deletions(-)
diff --git a/tools/perf/arch/x86/util/header.c
b/tools/perf/arch/x86/util/header.c
index
...
arith.fpu_div
[Divide operations executed]
arith.fpu_div_active
[Cycles when divider is busy executing divide operations]
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
Acked-by: Jiri Olsa
---
Changelog
- Delete a redundant free()
Changelog[v14
m not fully sure this change to the scanner is correct
(what was the dot special case good for?), but I haven't
found anything that breaks with it so far at least.
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
Acked-by: Namhyung Kim
Acked-by: Jiri Olsa
---
V2: Add the dot t
Implement code that returns the generic CPU ID string for Powerpc.
This will be used to identify the specific table of PMU events to
parse/compare user specified events against.
Signed-off-by: Sukadev Bhattiprolu
Acked-by: Jiri Olsa
---
Changelog[v14]
- [Jiri Olsa] Move this
Separate the event parsing code in perf_pmu__new_alias() out into
a separate function __perf_pmu__new_alias() so that code can be
called indepdently.
This is based on an earlier patch from Andi Kleen.
Signed-off-by: Sukadev Bhattiprolu
Acked-by: Jiri Olsa
---
tools/perf/util/pmu.c | 42
he user to specify events using their
aliases rather than raw event codes.
Based on input and some earlier patches from Andi Kleen, Jiri Olsa.
Signed-off-by: Sukadev Bhattiprolu
Acked-by: Jiri Olsa
---
Changelog[v4]
- Split off unrelated code into separate patches.
Changelog[v3]
-
Jiri Olsa pointed out, that the defines the
attribute '__weak'. We might as well use that.
Signed-off-by: Sukadev Bhattiprolu
Acked-by: Jiri Olsa
---
tools/perf/util/pmu.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/p
lows parsing Intel style JSON event files. This
allows to use an Intel event list directly with perf. The Intel event lists
can be quite large and are too big to store in unswappable kernel memory.
The conversion from JSON to C-style is straight forward. The parser knows
(very little) Intel spe
ion I added a simple wrapper that mmaps a json
file and provides some straight forward access functions.
Used in follow-on patches to parse event files.
Acked-by: Namhyung Kim
Acked-by: Jiri Olsa
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
---
v2: Address review feedback.
v3: Minor
ag to perf list
perf, tools: Add override support for event list CPUID
perf, tools: Add support for event list topics
perf, tools: Handle header line in mapfile
Sukadev Bhattiprolu (9):
Use __weak definition from
perf, tools: Split perf_pmu__new_alias()
perf, tools: Use pmu_events table to
Andi Kleen [a...@linux.intel.com] wrote:
| On Fri, Jun 05, 2015 at 12:21:38PM +0200, Jiri Olsa wrote:
| > On Thu, Jun 04, 2015 at 11:27:23PM -0700, Sukadev Bhattiprolu wrote:
| >
| > SNIP
| >
| > > ---
| > > tools/perf/builtin-list.c | 11 ---
| > > 1 fi
Signed-off-by: Sukadev Bhattiprolu
---
tools/perf/pmu-events/README | 122 ++
1 file changed, 122 insertions(+)
create mode 100644 tools/perf/pmu-events/README
diff --git a/tools/perf/pmu-events/README b/tools/perf/pmu-events/README
new file mode 100644
From: Andi Kleen
To work with existing mapfiles, assume that the first line in
'mapfile.csv' is a header line and skip over it.
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
Changelog[v2]
All architectures may not use the "Family" to identify. So,
]
br_inst_exec.all_direct_jmp
[Speculative and retired macro-unconditional branches excluding
calls and indirects]
br_inst_exec.all_direct_near_call
[Speculative and retired direct near calls]
br_inst_exec.all_indirect_jump_non_call_ret
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev
baclears for any type of branch]
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
Changelog[v14]
- [Jiri Olsa] Break up independent parts of the patch into
separate patches.
---
tools/perf/builtin-list.c | 11 ---
1 file changed, 8 insertions(+), 3
Allow assigning categories "Topics" field to the PMU events i.e.
process the topic field from the JSON file and add a corresponding
topic field to the generated C events tables.
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
Changelog[v14]
[Jiri Olsa]
Implement support in jevents to parse long descriptions for events
that may have them in the JSON files. A follow on patch will make this
long description available to user through the 'perf list' command.
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
Cha
Previously we were dropping the useful longer descriptions that some
events have in the event list completely. Now that jevents provides
support for longer descriptions (see previous patch), add support for
parsing the long descriptions
Signed-off-by: Andi Kleen
Signed-off-by: Sukadev
-by: Sukadev Bhattiprolu
---
tools/perf/util/cache.h |1 +
tools/perf/util/pager.c | 15 +++
tools/perf/util/pmu.c |3 ++-
3 files changed, 18 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index c861373..8e0d4b8 100644
--- a
Andi Kleen
Signed-off-by: Sukadev Bhattiprolu
v2: Rename --quiet to --no-desc. Add option to man page.
---
tools/perf/Documentation/perf-list.txt |8 +++-
tools/perf/builtin-list.c | 12
tools/perf/util/parse-events.c |4 ++--
tools/perf/util/parse-eve
401 - 500 of 893 matches
Mail list logo