arch/x86/events/intel/core.c | 4 +- arch/x86/events/intel/pt.c | 84 +++- arch/x86/events/intel/pt.h | 6 + include/linux/perf_event.h | 28 ++ include/uapi/linux/perf_event.h | 11 +- kernel/events/core.c | 75 +++- kernel/events/internal.h | 1 + tools/include/uapi/linux/perf_event.h | 11 +- tools/perf/Documentation/perf-intel-pt.txt | 596 ++++++++++++++++++----------- tools/perf/Documentation/perf-record.txt | 4 + tools/perf/builtin-record.c | 4 +- tools/perf/tests/shell/test_intel_pt.sh | 28 ++ tools/perf/util/auxtrace.c | 67 +++- tools/perf/util/auxtrace.h | 6 +- tools/perf/util/evsel.c | 15 + tools/perf/util/evsel.h | 1 + tools/perf/util/evsel_config.h | 1 + tools/perf/util/parse-events.c | 10 + tools/perf/util/parse-events.h | 1 + tools/perf/util/parse-events.l | 1 + tools/perf/util/perf_event_attr_fprintf.c | 3 + tools/perf/util/pmu.c | 1 + 22 files changed, 716 insertions(+), 242 deletions(-)
Hi
Note for V14:
KVM patches dropped.
Note for V12:
There was a small conflict between the Intel PT changes in
"KVM: x86: Fix Intel PT Host/Guest mode when host tracing" and the
changes in this patch set, so I have put the patch sets together,
along with outstanding fix "perf/x86/intel/pt: Fix buffer full but
size is 0 case"
Cover letter for KVM changes (patches 2 to 4):
There is a long-standing problem whereby running Intel PT on host and guest
in Host/Guest mode, causes VM-Entry failure.
The motivation for this patch set is to provide a fix for stable kernels
prior to the advent of the "Mediated Passthrough vPMU" patch set:
https://lore.kernel.org/kvm/20240801045907.4010984-1-mizhang@google.com/
which would render a large part of the fix unnecessary but likely not be
suitable for backport to stable due to its size and complexity.
Ideally, this patch set would be applied before "Mediated Passthrough vPMU"
Note that the fix does not conflict with "Mediated Passthrough vPMU", it
is just that "Mediated Passthrough vPMU" will make the code to stop and
restart Intel PT unnecessary.
Note for V11:
Moving aux_paused into a union within struct hw_perf_event caused
a regression because aux_paused was being written unconditionally
even though it is valid only for AUX (e.g. Intel PT) PMUs.
That is fixed in V11.
Hardware traces, such as instruction traces, can produce a vast amount of
trace data, so being able to reduce tracing to more specific circumstances
can be useful.
The ability to pause or resume tracing when another event happens, can do
that.
These patches add such a facilty and show how it would work for Intel
Processor Trace.
Maintainers of other AUX area tracing implementations are requested to
consider if this is something they might employ and then whether or not
the ABI would work for them. Note, thank you to James Clark (ARM) for
evaluating the API for Coresight. Suzuki K Poulose (ARM) also responded
positively to the RFC.
Changes to perf tools are now (since V4) fleshed out.
Please note, Intel® Architecture Instruction Set Extensions and Future
Features Programming Reference March 2024 319433-052, currently:
https://cdrdv2.intel.com/v1/dl/getContent/671368
introduces hardware pause / resume for Intel PT in a feature named
Intel PT Trigger Tracing.
For that more fields in perf_event_attr will be necessary. The main
differences are:
- it can be applied not just to overflows, but optionally to
every event
- a packet is emitted into the trace, optionally with IP
information
- no PMI
- works with PMC and DR (breakpoint) events only
Here are the proposed additions to perf_event_attr, please comment:
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 0c557f0a17b3..05dcc43f11bb 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -369,6 +369,22 @@ enum perf_event_read_format {
PERF_FORMAT_MAX = 1U << 5, /* non-ABI */
};
+enum {
+ PERF_AUX_ACTION_START_PAUSED = 1U << 0,
+ PERF_AUX_ACTION_PAUSE = 1U << 1,
+ PERF_AUX_ACTION_RESUME = 1U << 2,
+ PERF_AUX_ACTION_EMIT = 1U << 3,
+ PERF_AUX_ACTION_NR = 0x1f << 4,
+ PERF_AUX_ACTION_NO_IP = 1U << 9,
+ PERF_AUX_ACTION_PAUSE_ON_EVT = 1U << 10,
+ PERF_AUX_ACTION_RESUME_ON_EVT = 1U << 11,
+ PERF_AUX_ACTION_EMIT_ON_EVT = 1U << 12,
+ PERF_AUX_ACTION_NR_ON_EVT = 0x1f << 13,
+ PERF_AUX_ACTION_NO_IP_ON_EVT = 1U << 18,
+ PERF_AUX_ACTION_MASK = ~PERF_AUX_ACTION_START_PAUSED,
+ PERF_AUX_PAUSE_RESUME_MASK = PERF_AUX_ACTION_PAUSE | PERF_AUX_ACTION_RESUME,
+};
+
#define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */
#define PERF_ATTR_SIZE_VER1 72 /* add: config2 */
#define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */
@@ -515,10 +531,19 @@ struct perf_event_attr {
union {
__u32 aux_action;
struct {
- __u32 aux_start_paused : 1, /* start AUX area tracing paused */
- aux_pause : 1, /* on overflow, pause AUX area tracing */
- aux_resume : 1, /* on overflow, resume AUX area tracing */
- __reserved_3 : 29;
+ __u32 aux_start_paused : 1, /* start AUX area tracing paused */
+ aux_pause : 1, /* on overflow, pause AUX area tracing */
+ aux_resume : 1, /* on overflow, resume AUX area tracing */
+ aux_emit : 1, /* generate AUX records instead of events */
+ aux_nr : 5, /* AUX area tracing reference number */
+ aux_no_ip : 1, /* suppress IP in AUX records */
+ /* Following apply to event occurrence not overflows */
+ aux_pause_on_evt : 1, /* on event, pause AUX area tracing */
+ aux_resume_on_evt : 1, /* on event, resume AUX area tracing */
+ aux_emit_on_evt : 1, /* generate AUX records instead of events */
+ aux_nr_on_evt : 5, /* AUX area tracing reference number */
+ aux_no_ip_on_evt : 1, /* suppress IP in AUX records */
+ __reserved_3 : 13;
};
};
Changes in V14:
Dropped KVM patches
perf/x86/intel/pt: Add support for pause / resume
Set pt->handle_nmi after configuration is completed instead of during
Changes in V13:
perf/core: Add aux_pause, aux_resume, aux_start_paused
Do aux_resume at the end of __perf_event_overflow() so as to trace
less of perf itself
perf tools: Add missing_features for aux_start_paused, aux_pause, aux_resume
Add error message also in EOPNOTSUPP case (Leo)
Changes in V12:
Add previously sent patch "perf/x86/intel/pt: Fix buffer full
but size is 0 case"
Add previously sent patch set "KVM: x86: Fix Intel PT Host/Guest
mode when host tracing"
Rebase on current tip plus patch set "KVM: x86: Fix Intel PT Host/Guest
mode when host tracing"
Changes in V11:
perf/core: Add aux_pause, aux_resume, aux_start_paused
Make assignment to event->hw.aux_paused conditional on
(pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE).
perf/x86/intel: Do not enable large PEBS for events with aux actions or aux sampling
Remove definition of has_aux_action() because it has
already been added as an inline function.
perf/x86/intel/pt: Fix sampling synchronization
perf tools: Enable evsel__is_aux_event() to work for ARM/ARM64
perf tools: Enable evsel__is_aux_event() to work for S390_CPUMSF
Dropped because they have already been applied
Changes in V10:
perf/core: Add aux_pause, aux_resume, aux_start_paused
Move aux_paused into a union within struct hw_perf_event.
Additional comment wrt PERF_EF_PAUSE/PERF_EF_RESUME.
Factor out has_aux_action() as an inline function.
Use scoped_guard for irqsave.
Move calls of perf_event_aux_pause() from __perf_event_output()
to __perf_event_overflow().
Changes in V9:
perf/x86/intel/pt: Fix sampling synchronization
New patch
perf/core: Add aux_pause, aux_resume, aux_start_paused
Move aux_paused to struct hw_perf_event
perf/x86/intel/pt: Add support for pause / resume
Add more comments and barriers for resume_allowed and
pause_allowed
Always use WRITE_ONCE with resume_allowed
Changes in V8:
perf tools: Parse aux-action
Fix clang warning:
util/auxtrace.c:821:7: error: missing field 'aux_action' initializer [-Werror,-Wmissing-field-initializers]
821 | {NULL},
| ^
Changes in V7:
Add Andi's Reviewed-by for patches 2-12
Re-base
Changes in V6:
perf/core: Add aux_pause, aux_resume, aux_start_paused
Removed READ/WRITE_ONCE from __perf_event_aux_pause()
Expanded comment about guarding against NMI
Changes in V5:
perf/core: Add aux_pause, aux_resume, aux_start_paused
Added James' Ack
perf/x86/intel: Do not enable large PEBS for events with aux actions or aux sampling
New patch
perf tools
Added Ian's Ack
Changes in V4:
perf/core: Add aux_pause, aux_resume, aux_start_paused
Rename aux_output_cfg -> aux_action
Reorder aux_action bits from:
aux_pause, aux_resume, aux_start_paused
to:
aux_start_paused, aux_pause, aux_resume
Fix aux_action bits __u64 -> __u32
coresight: Have a stab at support for pause / resume
Dropped
perf tools
All new patches
Changes in RFC V3:
coresight: Have a stab at support for pause / resume
'mode' -> 'flags' so it at least compiles
Changes in RFC V2:
Use ->stop() / ->start() instead of ->pause_resume()
Move aux_start_paused bit into aux_output_cfg
Tighten up when Intel PT pause / resume is allowed
Add an example of how it might work for CoreSight
Adrian Hunter (11):
perf/x86/intel/pt: Fix buffer full but size is 0 case
perf/core: Add aux_pause, aux_resume, aux_start_paused
perf/x86/intel/pt: Add support for pause / resume
perf/x86/intel: Do not enable large PEBS for events with aux actions or aux sampling
perf tools: Add aux_start_paused, aux_pause and aux_resume
perf tools: Add aux-action config term
perf tools: Parse aux-action
perf tools: Add missing_features for aux_start_paused, aux_pause, aux_resume
perf intel-pt: Improve man page format
perf intel-pt: Add documentation for pause / resume
perf intel-pt: Add a test for pause / resume
arch/x86/events/intel/core.c | 4 +-
arch/x86/events/intel/pt.c | 84 +++-
arch/x86/events/intel/pt.h | 6 +
include/linux/perf_event.h | 28 ++
include/uapi/linux/perf_event.h | 11 +-
kernel/events/core.c | 75 +++-
kernel/events/internal.h | 1 +
tools/include/uapi/linux/perf_event.h | 11 +-
tools/perf/Documentation/perf-intel-pt.txt | 596 ++++++++++++++++++-----------
tools/perf/Documentation/perf-record.txt | 4 +
tools/perf/builtin-record.c | 4 +-
tools/perf/tests/shell/test_intel_pt.sh | 28 ++
tools/perf/util/auxtrace.c | 67 +++-
tools/perf/util/auxtrace.h | 6 +-
tools/perf/util/evsel.c | 15 +
tools/perf/util/evsel.h | 1 +
tools/perf/util/evsel_config.h | 1 +
tools/perf/util/parse-events.c | 10 +
tools/perf/util/parse-events.h | 1 +
tools/perf/util/parse-events.l | 1 +
tools/perf/util/perf_event_attr_fprintf.c | 3 +
tools/perf/util/pmu.c | 1 +
22 files changed, 716 insertions(+), 242 deletions(-)
Regards
Adrian
On 22/10/24 18:59, Adrian Hunter wrote:
> Hi
>
> Note for V14:
> KVM patches dropped.
ping
>
> Note for V12:
> There was a small conflict between the Intel PT changes in
> "KVM: x86: Fix Intel PT Host/Guest mode when host tracing" and the
> changes in this patch set, so I have put the patch sets together,
> along with outstanding fix "perf/x86/intel/pt: Fix buffer full but
> size is 0 case"
>
> Cover letter for KVM changes (patches 2 to 4):
>
> There is a long-standing problem whereby running Intel PT on host and guest
> in Host/Guest mode, causes VM-Entry failure.
>
> The motivation for this patch set is to provide a fix for stable kernels
> prior to the advent of the "Mediated Passthrough vPMU" patch set:
>
> https://lore.kernel.org/kvm/20240801045907.4010984-1-mizhang@google.com/
>
> which would render a large part of the fix unnecessary but likely not be
> suitable for backport to stable due to its size and complexity.
>
> Ideally, this patch set would be applied before "Mediated Passthrough vPMU"
>
> Note that the fix does not conflict with "Mediated Passthrough vPMU", it
> is just that "Mediated Passthrough vPMU" will make the code to stop and
> restart Intel PT unnecessary.
>
> Note for V11:
> Moving aux_paused into a union within struct hw_perf_event caused
> a regression because aux_paused was being written unconditionally
> even though it is valid only for AUX (e.g. Intel PT) PMUs.
> That is fixed in V11.
>
> Hardware traces, such as instruction traces, can produce a vast amount of
> trace data, so being able to reduce tracing to more specific circumstances
> can be useful.
>
> The ability to pause or resume tracing when another event happens, can do
> that.
>
> These patches add such a facilty and show how it would work for Intel
> Processor Trace.
>
> Maintainers of other AUX area tracing implementations are requested to
> consider if this is something they might employ and then whether or not
> the ABI would work for them. Note, thank you to James Clark (ARM) for
> evaluating the API for Coresight. Suzuki K Poulose (ARM) also responded
> positively to the RFC.
>
> Changes to perf tools are now (since V4) fleshed out.
>
> Please note, Intel® Architecture Instruction Set Extensions and Future
> Features Programming Reference March 2024 319433-052, currently:
>
> https://cdrdv2.intel.com/v1/dl/getContent/671368
>
> introduces hardware pause / resume for Intel PT in a feature named
> Intel PT Trigger Tracing.
>
> For that more fields in perf_event_attr will be necessary. The main
> differences are:
> - it can be applied not just to overflows, but optionally to
> every event
> - a packet is emitted into the trace, optionally with IP
> information
> - no PMI
> - works with PMC and DR (breakpoint) events only
>
> Here are the proposed additions to perf_event_attr, please comment:
>
> diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
> index 0c557f0a17b3..05dcc43f11bb 100644
> --- a/tools/include/uapi/linux/perf_event.h
> +++ b/tools/include/uapi/linux/perf_event.h
> @@ -369,6 +369,22 @@ enum perf_event_read_format {
> PERF_FORMAT_MAX = 1U << 5, /* non-ABI */
> };
>
> +enum {
> + PERF_AUX_ACTION_START_PAUSED = 1U << 0,
> + PERF_AUX_ACTION_PAUSE = 1U << 1,
> + PERF_AUX_ACTION_RESUME = 1U << 2,
> + PERF_AUX_ACTION_EMIT = 1U << 3,
> + PERF_AUX_ACTION_NR = 0x1f << 4,
> + PERF_AUX_ACTION_NO_IP = 1U << 9,
> + PERF_AUX_ACTION_PAUSE_ON_EVT = 1U << 10,
> + PERF_AUX_ACTION_RESUME_ON_EVT = 1U << 11,
> + PERF_AUX_ACTION_EMIT_ON_EVT = 1U << 12,
> + PERF_AUX_ACTION_NR_ON_EVT = 0x1f << 13,
> + PERF_AUX_ACTION_NO_IP_ON_EVT = 1U << 18,
> + PERF_AUX_ACTION_MASK = ~PERF_AUX_ACTION_START_PAUSED,
> + PERF_AUX_PAUSE_RESUME_MASK = PERF_AUX_ACTION_PAUSE | PERF_AUX_ACTION_RESUME,
> +};
> +
> #define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */
> #define PERF_ATTR_SIZE_VER1 72 /* add: config2 */
> #define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */
> @@ -515,10 +531,19 @@ struct perf_event_attr {
> union {
> __u32 aux_action;
> struct {
> - __u32 aux_start_paused : 1, /* start AUX area tracing paused */
> - aux_pause : 1, /* on overflow, pause AUX area tracing */
> - aux_resume : 1, /* on overflow, resume AUX area tracing */
> - __reserved_3 : 29;
> + __u32 aux_start_paused : 1, /* start AUX area tracing paused */
> + aux_pause : 1, /* on overflow, pause AUX area tracing */
> + aux_resume : 1, /* on overflow, resume AUX area tracing */
> + aux_emit : 1, /* generate AUX records instead of events */
> + aux_nr : 5, /* AUX area tracing reference number */
> + aux_no_ip : 1, /* suppress IP in AUX records */
> + /* Following apply to event occurrence not overflows */
> + aux_pause_on_evt : 1, /* on event, pause AUX area tracing */
> + aux_resume_on_evt : 1, /* on event, resume AUX area tracing */
> + aux_emit_on_evt : 1, /* generate AUX records instead of events */
> + aux_nr_on_evt : 5, /* AUX area tracing reference number */
> + aux_no_ip_on_evt : 1, /* suppress IP in AUX records */
> + __reserved_3 : 13;
> };
> };
>
>
> Changes in V14:
> Dropped KVM patches
>
> perf/x86/intel/pt: Add support for pause / resume
> Set pt->handle_nmi after configuration is completed instead of during
>
> Changes in V13:
> perf/core: Add aux_pause, aux_resume, aux_start_paused
> Do aux_resume at the end of __perf_event_overflow() so as to trace
> less of perf itself
>
> perf tools: Add missing_features for aux_start_paused, aux_pause, aux_resume
> Add error message also in EOPNOTSUPP case (Leo)
>
> Changes in V12:
> Add previously sent patch "perf/x86/intel/pt: Fix buffer full
> but size is 0 case"
>
> Add previously sent patch set "KVM: x86: Fix Intel PT Host/Guest
> mode when host tracing"
>
> Rebase on current tip plus patch set "KVM: x86: Fix Intel PT Host/Guest
> mode when host tracing"
>
> Changes in V11:
> perf/core: Add aux_pause, aux_resume, aux_start_paused
> Make assignment to event->hw.aux_paused conditional on
> (pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE).
>
> perf/x86/intel: Do not enable large PEBS for events with aux actions or aux sampling
> Remove definition of has_aux_action() because it has
> already been added as an inline function.
>
> perf/x86/intel/pt: Fix sampling synchronization
> perf tools: Enable evsel__is_aux_event() to work for ARM/ARM64
> perf tools: Enable evsel__is_aux_event() to work for S390_CPUMSF
> Dropped because they have already been applied
>
> Changes in V10:
> perf/core: Add aux_pause, aux_resume, aux_start_paused
> Move aux_paused into a union within struct hw_perf_event.
> Additional comment wrt PERF_EF_PAUSE/PERF_EF_RESUME.
> Factor out has_aux_action() as an inline function.
> Use scoped_guard for irqsave.
> Move calls of perf_event_aux_pause() from __perf_event_output()
> to __perf_event_overflow().
>
> Changes in V9:
> perf/x86/intel/pt: Fix sampling synchronization
> New patch
>
> perf/core: Add aux_pause, aux_resume, aux_start_paused
> Move aux_paused to struct hw_perf_event
>
> perf/x86/intel/pt: Add support for pause / resume
> Add more comments and barriers for resume_allowed and
> pause_allowed
> Always use WRITE_ONCE with resume_allowed
>
>
> Changes in V8:
>
> perf tools: Parse aux-action
> Fix clang warning:
> util/auxtrace.c:821:7: error: missing field 'aux_action' initializer [-Werror,-Wmissing-field-initializers]
> 821 | {NULL},
> | ^
>
> Changes in V7:
>
> Add Andi's Reviewed-by for patches 2-12
> Re-base
>
> Changes in V6:
>
> perf/core: Add aux_pause, aux_resume, aux_start_paused
> Removed READ/WRITE_ONCE from __perf_event_aux_pause()
> Expanded comment about guarding against NMI
>
> Changes in V5:
>
> perf/core: Add aux_pause, aux_resume, aux_start_paused
> Added James' Ack
>
> perf/x86/intel: Do not enable large PEBS for events with aux actions or aux sampling
> New patch
>
> perf tools
> Added Ian's Ack
>
> Changes in V4:
>
> perf/core: Add aux_pause, aux_resume, aux_start_paused
> Rename aux_output_cfg -> aux_action
> Reorder aux_action bits from:
> aux_pause, aux_resume, aux_start_paused
> to:
> aux_start_paused, aux_pause, aux_resume
> Fix aux_action bits __u64 -> __u32
>
> coresight: Have a stab at support for pause / resume
> Dropped
>
> perf tools
> All new patches
>
> Changes in RFC V3:
>
> coresight: Have a stab at support for pause / resume
> 'mode' -> 'flags' so it at least compiles
>
> Changes in RFC V2:
>
> Use ->stop() / ->start() instead of ->pause_resume()
> Move aux_start_paused bit into aux_output_cfg
> Tighten up when Intel PT pause / resume is allowed
> Add an example of how it might work for CoreSight
>
>
> Adrian Hunter (11):
> perf/x86/intel/pt: Fix buffer full but size is 0 case
> perf/core: Add aux_pause, aux_resume, aux_start_paused
> perf/x86/intel/pt: Add support for pause / resume
> perf/x86/intel: Do not enable large PEBS for events with aux actions or aux sampling
> perf tools: Add aux_start_paused, aux_pause and aux_resume
> perf tools: Add aux-action config term
> perf tools: Parse aux-action
> perf tools: Add missing_features for aux_start_paused, aux_pause, aux_resume
> perf intel-pt: Improve man page format
> perf intel-pt: Add documentation for pause / resume
> perf intel-pt: Add a test for pause / resume
>
> arch/x86/events/intel/core.c | 4 +-
> arch/x86/events/intel/pt.c | 84 +++-
> arch/x86/events/intel/pt.h | 6 +
> include/linux/perf_event.h | 28 ++
> include/uapi/linux/perf_event.h | 11 +-
> kernel/events/core.c | 75 +++-
> kernel/events/internal.h | 1 +
> tools/include/uapi/linux/perf_event.h | 11 +-
> tools/perf/Documentation/perf-intel-pt.txt | 596 ++++++++++++++++++-----------
> tools/perf/Documentation/perf-record.txt | 4 +
> tools/perf/builtin-record.c | 4 +-
> tools/perf/tests/shell/test_intel_pt.sh | 28 ++
> tools/perf/util/auxtrace.c | 67 +++-
> tools/perf/util/auxtrace.h | 6 +-
> tools/perf/util/evsel.c | 15 +
> tools/perf/util/evsel.h | 1 +
> tools/perf/util/evsel_config.h | 1 +
> tools/perf/util/parse-events.c | 10 +
> tools/perf/util/parse-events.h | 1 +
> tools/perf/util/parse-events.l | 1 +
> tools/perf/util/perf_event_attr_fprintf.c | 3 +
> tools/perf/util/pmu.c | 1 +
> 22 files changed, 716 insertions(+), 242 deletions(-)
>
>
> Regards
> Adrian
On 30/10/24 15:16, Adrian Hunter wrote:
> On 22/10/24 18:59, Adrian Hunter wrote:
>> Hi
>>
>> Note for V14:
>> KVM patches dropped.
>
> ping
ping
>
>>
>> Note for V12:
>> There was a small conflict between the Intel PT changes in
>> "KVM: x86: Fix Intel PT Host/Guest mode when host tracing" and the
>> changes in this patch set, so I have put the patch sets together,
>> along with outstanding fix "perf/x86/intel/pt: Fix buffer full but
>> size is 0 case"
>>
>> Cover letter for KVM changes (patches 2 to 4):
>>
>> There is a long-standing problem whereby running Intel PT on host and guest
>> in Host/Guest mode, causes VM-Entry failure.
>>
>> The motivation for this patch set is to provide a fix for stable kernels
>> prior to the advent of the "Mediated Passthrough vPMU" patch set:
>>
>> https://lore.kernel.org/kvm/20240801045907.4010984-1-mizhang@google.com/
>>
>> which would render a large part of the fix unnecessary but likely not be
>> suitable for backport to stable due to its size and complexity.
>>
>> Ideally, this patch set would be applied before "Mediated Passthrough vPMU"
>>
>> Note that the fix does not conflict with "Mediated Passthrough vPMU", it
>> is just that "Mediated Passthrough vPMU" will make the code to stop and
>> restart Intel PT unnecessary.
>>
>> Note for V11:
>> Moving aux_paused into a union within struct hw_perf_event caused
>> a regression because aux_paused was being written unconditionally
>> even though it is valid only for AUX (e.g. Intel PT) PMUs.
>> That is fixed in V11.
>>
>> Hardware traces, such as instruction traces, can produce a vast amount of
>> trace data, so being able to reduce tracing to more specific circumstances
>> can be useful.
>>
>> The ability to pause or resume tracing when another event happens, can do
>> that.
>>
>> These patches add such a facilty and show how it would work for Intel
>> Processor Trace.
>>
>> Maintainers of other AUX area tracing implementations are requested to
>> consider if this is something they might employ and then whether or not
>> the ABI would work for them. Note, thank you to James Clark (ARM) for
>> evaluating the API for Coresight. Suzuki K Poulose (ARM) also responded
>> positively to the RFC.
>>
>> Changes to perf tools are now (since V4) fleshed out.
>>
>> Please note, Intel® Architecture Instruction Set Extensions and Future
>> Features Programming Reference March 2024 319433-052, currently:
>>
>> https://cdrdv2.intel.com/v1/dl/getContent/671368
>>
>> introduces hardware pause / resume for Intel PT in a feature named
>> Intel PT Trigger Tracing.
>>
>> For that more fields in perf_event_attr will be necessary. The main
>> differences are:
>> - it can be applied not just to overflows, but optionally to
>> every event
>> - a packet is emitted into the trace, optionally with IP
>> information
>> - no PMI
>> - works with PMC and DR (breakpoint) events only
>>
>> Here are the proposed additions to perf_event_attr, please comment:
>>
>> diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
>> index 0c557f0a17b3..05dcc43f11bb 100644
>> --- a/tools/include/uapi/linux/perf_event.h
>> +++ b/tools/include/uapi/linux/perf_event.h
>> @@ -369,6 +369,22 @@ enum perf_event_read_format {
>> PERF_FORMAT_MAX = 1U << 5, /* non-ABI */
>> };
>>
>> +enum {
>> + PERF_AUX_ACTION_START_PAUSED = 1U << 0,
>> + PERF_AUX_ACTION_PAUSE = 1U << 1,
>> + PERF_AUX_ACTION_RESUME = 1U << 2,
>> + PERF_AUX_ACTION_EMIT = 1U << 3,
>> + PERF_AUX_ACTION_NR = 0x1f << 4,
>> + PERF_AUX_ACTION_NO_IP = 1U << 9,
>> + PERF_AUX_ACTION_PAUSE_ON_EVT = 1U << 10,
>> + PERF_AUX_ACTION_RESUME_ON_EVT = 1U << 11,
>> + PERF_AUX_ACTION_EMIT_ON_EVT = 1U << 12,
>> + PERF_AUX_ACTION_NR_ON_EVT = 0x1f << 13,
>> + PERF_AUX_ACTION_NO_IP_ON_EVT = 1U << 18,
>> + PERF_AUX_ACTION_MASK = ~PERF_AUX_ACTION_START_PAUSED,
>> + PERF_AUX_PAUSE_RESUME_MASK = PERF_AUX_ACTION_PAUSE | PERF_AUX_ACTION_RESUME,
>> +};
>> +
>> #define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */
>> #define PERF_ATTR_SIZE_VER1 72 /* add: config2 */
>> #define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */
>> @@ -515,10 +531,19 @@ struct perf_event_attr {
>> union {
>> __u32 aux_action;
>> struct {
>> - __u32 aux_start_paused : 1, /* start AUX area tracing paused */
>> - aux_pause : 1, /* on overflow, pause AUX area tracing */
>> - aux_resume : 1, /* on overflow, resume AUX area tracing */
>> - __reserved_3 : 29;
>> + __u32 aux_start_paused : 1, /* start AUX area tracing paused */
>> + aux_pause : 1, /* on overflow, pause AUX area tracing */
>> + aux_resume : 1, /* on overflow, resume AUX area tracing */
>> + aux_emit : 1, /* generate AUX records instead of events */
>> + aux_nr : 5, /* AUX area tracing reference number */
>> + aux_no_ip : 1, /* suppress IP in AUX records */
>> + /* Following apply to event occurrence not overflows */
>> + aux_pause_on_evt : 1, /* on event, pause AUX area tracing */
>> + aux_resume_on_evt : 1, /* on event, resume AUX area tracing */
>> + aux_emit_on_evt : 1, /* generate AUX records instead of events */
>> + aux_nr_on_evt : 5, /* AUX area tracing reference number */
>> + aux_no_ip_on_evt : 1, /* suppress IP in AUX records */
>> + __reserved_3 : 13;
>> };
>> };
>>
>>
>> Changes in V14:
>> Dropped KVM patches
>>
>> perf/x86/intel/pt: Add support for pause / resume
>> Set pt->handle_nmi after configuration is completed instead of during
>>
>> Changes in V13:
>> perf/core: Add aux_pause, aux_resume, aux_start_paused
>> Do aux_resume at the end of __perf_event_overflow() so as to trace
>> less of perf itself
>>
>> perf tools: Add missing_features for aux_start_paused, aux_pause, aux_resume
>> Add error message also in EOPNOTSUPP case (Leo)
>>
>> Changes in V12:
>> Add previously sent patch "perf/x86/intel/pt: Fix buffer full
>> but size is 0 case"
>>
>> Add previously sent patch set "KVM: x86: Fix Intel PT Host/Guest
>> mode when host tracing"
>>
>> Rebase on current tip plus patch set "KVM: x86: Fix Intel PT Host/Guest
>> mode when host tracing"
>>
>> Changes in V11:
>> perf/core: Add aux_pause, aux_resume, aux_start_paused
>> Make assignment to event->hw.aux_paused conditional on
>> (pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE).
>>
>> perf/x86/intel: Do not enable large PEBS for events with aux actions or aux sampling
>> Remove definition of has_aux_action() because it has
>> already been added as an inline function.
>>
>> perf/x86/intel/pt: Fix sampling synchronization
>> perf tools: Enable evsel__is_aux_event() to work for ARM/ARM64
>> perf tools: Enable evsel__is_aux_event() to work for S390_CPUMSF
>> Dropped because they have already been applied
>>
>> Changes in V10:
>> perf/core: Add aux_pause, aux_resume, aux_start_paused
>> Move aux_paused into a union within struct hw_perf_event.
>> Additional comment wrt PERF_EF_PAUSE/PERF_EF_RESUME.
>> Factor out has_aux_action() as an inline function.
>> Use scoped_guard for irqsave.
>> Move calls of perf_event_aux_pause() from __perf_event_output()
>> to __perf_event_overflow().
>>
>> Changes in V9:
>> perf/x86/intel/pt: Fix sampling synchronization
>> New patch
>>
>> perf/core: Add aux_pause, aux_resume, aux_start_paused
>> Move aux_paused to struct hw_perf_event
>>
>> perf/x86/intel/pt: Add support for pause / resume
>> Add more comments and barriers for resume_allowed and
>> pause_allowed
>> Always use WRITE_ONCE with resume_allowed
>>
>>
>> Changes in V8:
>>
>> perf tools: Parse aux-action
>> Fix clang warning:
>> util/auxtrace.c:821:7: error: missing field 'aux_action' initializer [-Werror,-Wmissing-field-initializers]
>> 821 | {NULL},
>> | ^
>>
>> Changes in V7:
>>
>> Add Andi's Reviewed-by for patches 2-12
>> Re-base
>>
>> Changes in V6:
>>
>> perf/core: Add aux_pause, aux_resume, aux_start_paused
>> Removed READ/WRITE_ONCE from __perf_event_aux_pause()
>> Expanded comment about guarding against NMI
>>
>> Changes in V5:
>>
>> perf/core: Add aux_pause, aux_resume, aux_start_paused
>> Added James' Ack
>>
>> perf/x86/intel: Do not enable large PEBS for events with aux actions or aux sampling
>> New patch
>>
>> perf tools
>> Added Ian's Ack
>>
>> Changes in V4:
>>
>> perf/core: Add aux_pause, aux_resume, aux_start_paused
>> Rename aux_output_cfg -> aux_action
>> Reorder aux_action bits from:
>> aux_pause, aux_resume, aux_start_paused
>> to:
>> aux_start_paused, aux_pause, aux_resume
>> Fix aux_action bits __u64 -> __u32
>>
>> coresight: Have a stab at support for pause / resume
>> Dropped
>>
>> perf tools
>> All new patches
>>
>> Changes in RFC V3:
>>
>> coresight: Have a stab at support for pause / resume
>> 'mode' -> 'flags' so it at least compiles
>>
>> Changes in RFC V2:
>>
>> Use ->stop() / ->start() instead of ->pause_resume()
>> Move aux_start_paused bit into aux_output_cfg
>> Tighten up when Intel PT pause / resume is allowed
>> Add an example of how it might work for CoreSight
>>
>>
>> Adrian Hunter (11):
>> perf/x86/intel/pt: Fix buffer full but size is 0 case
>> perf/core: Add aux_pause, aux_resume, aux_start_paused
>> perf/x86/intel/pt: Add support for pause / resume
>> perf/x86/intel: Do not enable large PEBS for events with aux actions or aux sampling
>> perf tools: Add aux_start_paused, aux_pause and aux_resume
>> perf tools: Add aux-action config term
>> perf tools: Parse aux-action
>> perf tools: Add missing_features for aux_start_paused, aux_pause, aux_resume
>> perf intel-pt: Improve man page format
>> perf intel-pt: Add documentation for pause / resume
>> perf intel-pt: Add a test for pause / resume
>>
>> arch/x86/events/intel/core.c | 4 +-
>> arch/x86/events/intel/pt.c | 84 +++-
>> arch/x86/events/intel/pt.h | 6 +
>> include/linux/perf_event.h | 28 ++
>> include/uapi/linux/perf_event.h | 11 +-
>> kernel/events/core.c | 75 +++-
>> kernel/events/internal.h | 1 +
>> tools/include/uapi/linux/perf_event.h | 11 +-
>> tools/perf/Documentation/perf-intel-pt.txt | 596 ++++++++++++++++++-----------
>> tools/perf/Documentation/perf-record.txt | 4 +
>> tools/perf/builtin-record.c | 4 +-
>> tools/perf/tests/shell/test_intel_pt.sh | 28 ++
>> tools/perf/util/auxtrace.c | 67 +++-
>> tools/perf/util/auxtrace.h | 6 +-
>> tools/perf/util/evsel.c | 15 +
>> tools/perf/util/evsel.h | 1 +
>> tools/perf/util/evsel_config.h | 1 +
>> tools/perf/util/parse-events.c | 10 +
>> tools/perf/util/parse-events.h | 1 +
>> tools/perf/util/parse-events.l | 1 +
>> tools/perf/util/perf_event_attr_fprintf.c | 3 +
>> tools/perf/util/pmu.c | 1 +
>> 22 files changed, 716 insertions(+), 242 deletions(-)
>>
>>
>> Regards
>> Adrian
>
If the trace data buffer becomes full, a truncated flag [T] is reported
in PERF_RECORD_AUX. In some cases, the size reported is 0, even though
data must have been added to make the buffer full.
That happens when the buffer fills up from empty to full before the
Intel PT driver has updated the buffer position. Then the driver
calculates the new buffer position before calculating the data size.
If the old and new positions are the same, the data size is reported
as 0, even though it is really the whole buffer size.
Fix by detecting when the buffer position is wrapped, and adjust the
data size calculation accordingly.
Example
Use a very small buffer size (8K) and observe the size of truncated [T]
data. Before the fix, it is possible to see records of 0 size.
Before:
$ perf record -m,8K -e intel_pt// uname
Linux
[ perf record: Woken up 2 times to write data ]
[ perf record: Captured and wrote 0.105 MB perf.data ]
$ perf script -D --no-itrace | grep AUX | grep -F '[T]'
Warning:
AUX data lost 2 times out of 3!
5 19462712368111 0x19710 [0x40]: PERF_RECORD_AUX offset: 0 size: 0 flags: 0x1 [T]
5 19462712700046 0x19ba8 [0x40]: PERF_RECORD_AUX offset: 0x170 size: 0xe90 flags: 0x1 [T]
After:
$ perf record -m,8K -e intel_pt// uname
Linux
[ perf record: Woken up 3 times to write data ]
[ perf record: Captured and wrote 0.040 MB perf.data ]
$ perf script -D --no-itrace | grep AUX | grep -F '[T]'
Warning:
AUX data lost 2 times out of 3!
1 113720802995 0x4948 [0x40]: PERF_RECORD_AUX offset: 0 size: 0x2000 flags: 0x1 [T]
1 113720979812 0x6b10 [0x40]: PERF_RECORD_AUX offset: 0x2000 size: 0x2000 flags: 0x1 [T]
Fixes: 52ca9ced3f70 ("perf/x86/intel/pt: Add Intel PT PMU driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
arch/x86/events/intel/pt.c | 11 ++++++++---
arch/x86/events/intel/pt.h | 2 ++
2 files changed, 10 insertions(+), 3 deletions(-)
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index fd4670a6694e..a087bc0c5498 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -828,11 +828,13 @@ static void pt_buffer_advance(struct pt_buffer *buf)
buf->cur_idx++;
if (buf->cur_idx == buf->cur->last) {
- if (buf->cur == buf->last)
+ if (buf->cur == buf->last) {
buf->cur = buf->first;
- else
+ buf->wrapped = true;
+ } else {
buf->cur = list_entry(buf->cur->list.next, struct topa,
list);
+ }
buf->cur_idx = 0;
}
}
@@ -846,8 +848,11 @@ static void pt_buffer_advance(struct pt_buffer *buf)
static void pt_update_head(struct pt *pt)
{
struct pt_buffer *buf = perf_get_aux(&pt->handle);
+ bool wrapped = buf->wrapped;
u64 topa_idx, base, old;
+ buf->wrapped = false;
+
if (buf->single) {
local_set(&buf->data_size, buf->output_off);
return;
@@ -865,7 +870,7 @@ static void pt_update_head(struct pt *pt)
} else {
old = (local64_xchg(&buf->head, base) &
((buf->nr_pages << PAGE_SHIFT) - 1));
- if (base < old)
+ if (base < old || (base == old && wrapped))
base += buf->nr_pages << PAGE_SHIFT;
local_add(base - old, &buf->data_size);
diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h
index f5e46c04c145..a1b6c04b7f68 100644
--- a/arch/x86/events/intel/pt.h
+++ b/arch/x86/events/intel/pt.h
@@ -65,6 +65,7 @@ struct pt_pmu {
* @head: logical write offset inside the buffer
* @snapshot: if this is for a snapshot/overwrite counter
* @single: use Single Range Output instead of ToPA
+ * @wrapped: buffer advance wrapped back to the first topa table
* @stop_pos: STOP topa entry index
* @intr_pos: INT topa entry index
* @stop_te: STOP topa entry pointer
@@ -82,6 +83,7 @@ struct pt_buffer {
local64_t head;
bool snapshot;
bool single;
+ bool wrapped;
long stop_pos, intr_pos;
struct topa_entry *stop_te, *intr_te;
void **data_pages;
--
2.43.0The following commit has been merged into the perf/core branch of tip:
Commit-ID: 5b590160d2cf776b304eb054afafea2bd55e3620
Gitweb: https://git.kernel.org/tip/5b590160d2cf776b304eb054afafea2bd55e3620
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Tue, 22 Oct 2024 18:59:07 +03:00
Committer: Peter Zijlstra <peterz@infradead.org>
CommitterDate: Tue, 05 Nov 2024 12:55:43 +01:00
perf/x86/intel/pt: Fix buffer full but size is 0 case
If the trace data buffer becomes full, a truncated flag [T] is reported
in PERF_RECORD_AUX. In some cases, the size reported is 0, even though
data must have been added to make the buffer full.
That happens when the buffer fills up from empty to full before the
Intel PT driver has updated the buffer position. Then the driver
calculates the new buffer position before calculating the data size.
If the old and new positions are the same, the data size is reported
as 0, even though it is really the whole buffer size.
Fix by detecting when the buffer position is wrapped, and adjust the
data size calculation accordingly.
Example
Use a very small buffer size (8K) and observe the size of truncated [T]
data. Before the fix, it is possible to see records of 0 size.
Before:
$ perf record -m,8K -e intel_pt// uname
Linux
[ perf record: Woken up 2 times to write data ]
[ perf record: Captured and wrote 0.105 MB perf.data ]
$ perf script -D --no-itrace | grep AUX | grep -F '[T]'
Warning:
AUX data lost 2 times out of 3!
5 19462712368111 0x19710 [0x40]: PERF_RECORD_AUX offset: 0 size: 0 flags: 0x1 [T]
5 19462712700046 0x19ba8 [0x40]: PERF_RECORD_AUX offset: 0x170 size: 0xe90 flags: 0x1 [T]
After:
$ perf record -m,8K -e intel_pt// uname
Linux
[ perf record: Woken up 3 times to write data ]
[ perf record: Captured and wrote 0.040 MB perf.data ]
$ perf script -D --no-itrace | grep AUX | grep -F '[T]'
Warning:
AUX data lost 2 times out of 3!
1 113720802995 0x4948 [0x40]: PERF_RECORD_AUX offset: 0 size: 0x2000 flags: 0x1 [T]
1 113720979812 0x6b10 [0x40]: PERF_RECORD_AUX offset: 0x2000 size: 0x2000 flags: 0x1 [T]
Fixes: 52ca9ced3f70 ("perf/x86/intel/pt: Add Intel PT PMU driver")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20241022155920.17511-2-adrian.hunter@intel.com
---
arch/x86/events/intel/pt.c | 11 ++++++++---
arch/x86/events/intel/pt.h | 2 ++
2 files changed, 10 insertions(+), 3 deletions(-)
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index fd4670a..a087bc0 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -828,11 +828,13 @@ static void pt_buffer_advance(struct pt_buffer *buf)
buf->cur_idx++;
if (buf->cur_idx == buf->cur->last) {
- if (buf->cur == buf->last)
+ if (buf->cur == buf->last) {
buf->cur = buf->first;
- else
+ buf->wrapped = true;
+ } else {
buf->cur = list_entry(buf->cur->list.next, struct topa,
list);
+ }
buf->cur_idx = 0;
}
}
@@ -846,8 +848,11 @@ static void pt_buffer_advance(struct pt_buffer *buf)
static void pt_update_head(struct pt *pt)
{
struct pt_buffer *buf = perf_get_aux(&pt->handle);
+ bool wrapped = buf->wrapped;
u64 topa_idx, base, old;
+ buf->wrapped = false;
+
if (buf->single) {
local_set(&buf->data_size, buf->output_off);
return;
@@ -865,7 +870,7 @@ static void pt_update_head(struct pt *pt)
} else {
old = (local64_xchg(&buf->head, base) &
((buf->nr_pages << PAGE_SHIFT) - 1));
- if (base < old)
+ if (base < old || (base == old && wrapped))
base += buf->nr_pages << PAGE_SHIFT;
local_add(base - old, &buf->data_size);
diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h
index f5e46c0..a1b6c04 100644
--- a/arch/x86/events/intel/pt.h
+++ b/arch/x86/events/intel/pt.h
@@ -65,6 +65,7 @@ struct pt_pmu {
* @head: logical write offset inside the buffer
* @snapshot: if this is for a snapshot/overwrite counter
* @single: use Single Range Output instead of ToPA
+ * @wrapped: buffer advance wrapped back to the first topa table
* @stop_pos: STOP topa entry index
* @intr_pos: INT topa entry index
* @stop_te: STOP topa entry pointer
@@ -82,6 +83,7 @@ struct pt_buffer {
local64_t head;
bool snapshot;
bool single;
+ bool wrapped;
long stop_pos, intr_pos;
struct topa_entry *stop_te, *intr_te;
void **data_pages;Hardware traces, such as instruction traces, can produce a vast amount of
trace data, so being able to reduce tracing to more specific circumstances
can be useful.
The ability to pause or resume tracing when another event happens, can do
that.
Add ability for an event to "pause" or "resume" AUX area tracing.
Add aux_pause bit to perf_event_attr to indicate that, if the event
happens, the associated AUX area tracing should be paused. Ditto
aux_resume. Do not allow aux_pause and aux_resume to be set together.
Add aux_start_paused bit to perf_event_attr to indicate to an AUX area
event that it should start in a "paused" state.
Add aux_paused to struct hw_perf_event for AUX area events to keep track of
the "paused" state. aux_paused is initialized to aux_start_paused.
Add PERF_EF_PAUSE and PERF_EF_RESUME modes for ->stop() and ->start()
callbacks. Call as needed, during __perf_event_output(). Add
aux_in_pause_resume to struct perf_buffer to prevent races with the NMI
handler. Pause/resume in NMI context will miss out if it coincides with
another pause/resume.
To use aux_pause or aux_resume, an event must be in a group with the AUX
area event as the group leader.
Example (requires Intel PT and tools patches also):
$ perf record --kcore -e intel_pt/aux-action=start-paused/k,syscalls:sys_enter_newuname/aux-action=resume/,syscalls:sys_exit_newuname/aux-action=pause/ uname
Linux
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.043 MB perf.data ]
$ perf script --call-trace
uname 30805 [000] 24001.058782799: name: 0x7ffc9c1865b0
uname 30805 [000] 24001.058784424: psb offs: 0
uname 30805 [000] 24001.058784424: cbr: 39 freq: 3904 MHz (139%)
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) debug_smp_processor_id
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) __x64_sys_newuname
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) down_read
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) __cond_resched
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) preempt_count_add
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) in_lock_functions
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) preempt_count_sub
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) up_read
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) preempt_count_add
uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) in_lock_functions
uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) preempt_count_sub
uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) _copy_to_user
uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) syscall_exit_to_user_mode
uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) syscall_exit_work
uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) perf_syscall_exit
uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) debug_smp_processor_id
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_trace_buf_alloc
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_swevent_get_recursion_context
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) debug_smp_processor_id
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) debug_smp_processor_id
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_tp_event
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_trace_buf_update
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) tracing_gen_ctx_irq_test
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_swevent_event
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __perf_event_account_interrupt
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __this_cpu_preempt_check
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_event_output_forward
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_event_aux_pause
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) ring_buffer_get
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __rcu_read_lock
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __rcu_read_unlock
uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) pt_event_stop
uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) debug_smp_processor_id
uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) debug_smp_processor_id
uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) native_write_msr
uname 30805 [000] 24001.058785463: ([kernel.kallsyms]) native_write_msr
uname 30805 [000] 24001.058785639: 0x0
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: James Clark <james.clark@arm.com>
---
Changes in V13:
Do aux_resume at the end of __perf_event_overflow() so as to trace
less of perf itself
Changes in V12:
Rebase on current tip
Changes in V11:
Make assignment to event->hw.aux_paused conditional on
(pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE).
Changes in V10:
Move aux_paused into a union within struct hw_perf_event.
Additional comment wrt PERF_EF_PAUSE/PERF_EF_RESUME.
Factor out has_aux_action() as an inline function.
Use scoped_guard for irqsave.
Move calls of perf_event_aux_pause() from __perf_event_output()
to __perf_event_overflow().
Changes in V9:
Move aux_paused to struct hw_perf_event
Changes in V6:
Removed READ/WRITE_ONCE from __perf_event_aux_pause()
Expanded comment about guarding against NMI
Changes in V5:
Added James' Ack
Changes in V4:
Rename aux_output_cfg -> aux_action
Reorder aux_action bits from:
aux_pause, aux_resume, aux_start_paused
to:
aux_start_paused, aux_pause, aux_resume
Fix aux_action bits __u64 -> __u32
include/linux/perf_event.h | 28 ++++++++++++
include/uapi/linux/perf_event.h | 11 ++++-
kernel/events/core.c | 75 +++++++++++++++++++++++++++++++--
kernel/events/internal.h | 1 +
4 files changed, 110 insertions(+), 5 deletions(-)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index fb908843f209..91b310052a7c 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -170,6 +170,12 @@ struct hw_perf_event {
};
struct { /* aux / Intel-PT */
u64 aux_config;
+ /*
+ * For AUX area events, aux_paused cannot be a state
+ * flag because it can be updated asynchronously to
+ * state.
+ */
+ unsigned int aux_paused;
};
struct { /* software */
struct hrtimer hrtimer;
@@ -294,6 +300,7 @@ struct perf_event_pmu_context;
#define PERF_PMU_CAP_NO_EXCLUDE 0x0040
#define PERF_PMU_CAP_AUX_OUTPUT 0x0080
#define PERF_PMU_CAP_EXTENDED_HW_TYPE 0x0100
+#define PERF_PMU_CAP_AUX_PAUSE 0x0200
/**
* pmu::scope
@@ -384,6 +391,8 @@ struct pmu {
#define PERF_EF_START 0x01 /* start the counter when adding */
#define PERF_EF_RELOAD 0x02 /* reload the counter when starting */
#define PERF_EF_UPDATE 0x04 /* update the counter when stopping */
+#define PERF_EF_PAUSE 0x08 /* AUX area event, pause tracing */
+#define PERF_EF_RESUME 0x10 /* AUX area event, resume tracing */
/*
* Adds/Removes a counter to/from the PMU, can be done inside a
@@ -423,6 +432,18 @@ struct pmu {
*
* ->start() with PERF_EF_RELOAD will reprogram the counter
* value, must be preceded by a ->stop() with PERF_EF_UPDATE.
+ *
+ * ->stop() with PERF_EF_PAUSE will stop as simply as possible. Will not
+ * overlap another ->stop() with PERF_EF_PAUSE nor ->start() with
+ * PERF_EF_RESUME.
+ *
+ * ->start() with PERF_EF_RESUME will start as simply as possible but
+ * only if the counter is not otherwise stopped. Will not overlap
+ * another ->start() with PERF_EF_RESUME nor ->stop() with
+ * PERF_EF_PAUSE.
+ *
+ * Notably, PERF_EF_PAUSE/PERF_EF_RESUME *can* be concurrent with other
+ * ->stop()/->start() invocations, just not itself.
*/
void (*start) (struct perf_event *event, int flags);
void (*stop) (struct perf_event *event, int flags);
@@ -1679,6 +1700,13 @@ static inline bool has_aux(struct perf_event *event)
return event->pmu->setup_aux;
}
+static inline bool has_aux_action(struct perf_event *event)
+{
+ return event->attr.aux_sample_size ||
+ event->attr.aux_pause ||
+ event->attr.aux_resume;
+}
+
static inline bool is_write_backward(struct perf_event *event)
{
return !!event->attr.write_backward;
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 4842c36fdf80..0524d541d4e3 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -511,7 +511,16 @@ struct perf_event_attr {
__u16 sample_max_stack;
__u16 __reserved_2;
__u32 aux_sample_size;
- __u32 __reserved_3;
+
+ union {
+ __u32 aux_action;
+ struct {
+ __u32 aux_start_paused : 1, /* start AUX area tracing paused */
+ aux_pause : 1, /* on overflow, pause AUX area tracing */
+ aux_resume : 1, /* on overflow, resume AUX area tracing */
+ __reserved_3 : 29;
+ };
+ };
/*
* User provided data if sigtrap=1, passed back to user via
diff --git a/kernel/events/core.c b/kernel/events/core.c
index cdd09769e6c5..daeb65a0e467 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2146,7 +2146,7 @@ static void perf_put_aux_event(struct perf_event *event)
static bool perf_need_aux_event(struct perf_event *event)
{
- return !!event->attr.aux_output || !!event->attr.aux_sample_size;
+ return event->attr.aux_output || has_aux_action(event);
}
static int perf_get_aux_event(struct perf_event *event,
@@ -2171,6 +2171,10 @@ static int perf_get_aux_event(struct perf_event *event,
!perf_aux_output_match(event, group_leader))
return 0;
+ if ((event->attr.aux_pause || event->attr.aux_resume) &&
+ !(group_leader->pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE))
+ return 0;
+
if (event->attr.aux_sample_size && !group_leader->pmu->snapshot_aux)
return 0;
@@ -8016,6 +8020,49 @@ void perf_prepare_header(struct perf_event_header *header,
WARN_ON_ONCE(header->size & 7);
}
+static void __perf_event_aux_pause(struct perf_event *event, bool pause)
+{
+ if (pause) {
+ if (!event->hw.aux_paused) {
+ event->hw.aux_paused = 1;
+ event->pmu->stop(event, PERF_EF_PAUSE);
+ }
+ } else {
+ if (event->hw.aux_paused) {
+ event->hw.aux_paused = 0;
+ event->pmu->start(event, PERF_EF_RESUME);
+ }
+ }
+}
+
+static void perf_event_aux_pause(struct perf_event *event, bool pause)
+{
+ struct perf_buffer *rb;
+
+ if (WARN_ON_ONCE(!event))
+ return;
+
+ rb = ring_buffer_get(event);
+ if (!rb)
+ return;
+
+ scoped_guard (irqsave) {
+ /*
+ * Guard against self-recursion here. Another event could trip
+ * this same from NMI context.
+ */
+ if (READ_ONCE(rb->aux_in_pause_resume))
+ break;
+
+ WRITE_ONCE(rb->aux_in_pause_resume, 1);
+ barrier();
+ __perf_event_aux_pause(event, pause);
+ barrier();
+ WRITE_ONCE(rb->aux_in_pause_resume, 0);
+ }
+ ring_buffer_put(rb);
+}
+
static __always_inline int
__perf_event_output(struct perf_event *event,
struct perf_sample_data *data,
@@ -9818,9 +9865,12 @@ static int __perf_event_overflow(struct perf_event *event,
ret = __perf_event_account_interrupt(event, throttle);
+ if (event->attr.aux_pause)
+ perf_event_aux_pause(event->aux_event, true);
+
if (event->prog && event->prog->type == BPF_PROG_TYPE_PERF_EVENT &&
!bpf_overflow_handler(event, data, regs))
- return ret;
+ goto out;
/*
* XXX event_limit might not quite work as expected on inherited
@@ -9882,6 +9932,9 @@ static int __perf_event_overflow(struct perf_event *event,
event->pending_wakeup = 1;
irq_work_queue(&event->pending_irq);
}
+out:
+ if (event->attr.aux_resume)
+ perf_event_aux_pause(event->aux_event, false);
return ret;
}
@@ -12273,11 +12326,25 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
}
if (event->attr.aux_output &&
- !(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) {
+ (!(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT) ||
+ event->attr.aux_pause || event->attr.aux_resume)) {
err = -EOPNOTSUPP;
goto err_pmu;
}
+ if (event->attr.aux_pause && event->attr.aux_resume) {
+ err = -EINVAL;
+ goto err_pmu;
+ }
+
+ if (event->attr.aux_start_paused) {
+ if (!(pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE)) {
+ err = -EOPNOTSUPP;
+ goto err_pmu;
+ }
+ event->hw.aux_paused = 1;
+ }
+
if (cgroup_fd != -1) {
err = perf_cgroup_connect(cgroup_fd, event, attr, group_leader);
if (err)
@@ -13073,7 +13140,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
* Grouping is not supported for kernel events, neither is 'AUX',
* make sure the caller's intentions are adjusted.
*/
- if (attr->aux_output)
+ if (attr->aux_output || attr->aux_action)
return ERR_PTR(-EINVAL);
event = perf_event_alloc(attr, cpu, task, NULL, NULL,
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index e072d995d670..249288d82b8d 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -52,6 +52,7 @@ struct perf_buffer {
void (*free_aux)(void *);
refcount_t aux_refcount;
int aux_in_sampling;
+ int aux_in_pause_resume;
void **aux_pages;
void *aux_priv;
--
2.43.0On Tue, Oct 22, 2024 at 06:59:08PM +0300, Adrian Hunter wrote:
>
> Hardware traces, such as instruction traces, can produce a vast amount of
> trace data, so being able to reduce tracing to more specific circumstances
> can be useful.
>
> The ability to pause or resume tracing when another event happens, can do
> that.
>
> Add ability for an event to "pause" or "resume" AUX area tracing.
>
> Add aux_pause bit to perf_event_attr to indicate that, if the event
> happens, the associated AUX area tracing should be paused. Ditto
> aux_resume. Do not allow aux_pause and aux_resume to be set together.
>
> Add aux_start_paused bit to perf_event_attr to indicate to an AUX area
> event that it should start in a "paused" state.
>
> Add aux_paused to struct hw_perf_event for AUX area events to keep track of
> the "paused" state. aux_paused is initialized to aux_start_paused.
>
> Add PERF_EF_PAUSE and PERF_EF_RESUME modes for ->stop() and ->start()
> callbacks. Call as needed, during __perf_event_output(). Add
> aux_in_pause_resume to struct perf_buffer to prevent races with the NMI
> handler. Pause/resume in NMI context will miss out if it coincides with
> another pause/resume.
>
> To use aux_pause or aux_resume, an event must be in a group with the AUX
> area event as the group leader.
>
> Example (requires Intel PT and tools patches also):
>
> $ perf record --kcore -e intel_pt/aux-action=start-paused/k,syscalls:sys_enter_newuname/aux-action=resume/,syscalls:sys_exit_newuname/aux-action=pause/ uname
> Linux
> [ perf record: Woken up 1 times to write data ]
> [ perf record: Captured and wrote 0.043 MB perf.data ]
> $ perf script --call-trace
> uname 30805 [000] 24001.058782799: name: 0x7ffc9c1865b0
> uname 30805 [000] 24001.058784424: psb offs: 0
> uname 30805 [000] 24001.058784424: cbr: 39 freq: 3904 MHz (139%)
> uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) debug_smp_processor_id
> uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) __x64_sys_newuname
> uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) down_read
> uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) __cond_resched
> uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) preempt_count_add
> uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) in_lock_functions
> uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) preempt_count_sub
> uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) up_read
> uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) preempt_count_add
> uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) in_lock_functions
> uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) preempt_count_sub
> uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) _copy_to_user
> uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) syscall_exit_to_user_mode
> uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) syscall_exit_work
> uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) perf_syscall_exit
> uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) debug_smp_processor_id
> uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_trace_buf_alloc
> uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_swevent_get_recursion_context
> uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) debug_smp_processor_id
> uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) debug_smp_processor_id
> uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_tp_event
> uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_trace_buf_update
> uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) tracing_gen_ctx_irq_test
> uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_swevent_event
> uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __perf_event_account_interrupt
> uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __this_cpu_preempt_check
> uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_event_output_forward
> uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_event_aux_pause
> uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) ring_buffer_get
> uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __rcu_read_lock
> uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __rcu_read_unlock
> uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) pt_event_stop
> uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) debug_smp_processor_id
> uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) debug_smp_processor_id
> uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) native_write_msr
> uname 30805 [000] 24001.058785463: ([kernel.kallsyms]) native_write_msr
> uname 30805 [000] 24001.058785639: 0x0
>
> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
> Acked-by: James Clark <james.clark@arm.com>
FWIW, I verified this patch with Arm CoreSight:
Tested-by: Leo Yan <leo.yan@arm.com>
> ---
>
>
> Changes in V13:
> Do aux_resume at the end of __perf_event_overflow() so as to trace
> less of perf itself
>
> Changes in V12:
> Rebase on current tip
>
> Changes in V11:
> Make assignment to event->hw.aux_paused conditional on
> (pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE).
>
> Changes in V10:
> Move aux_paused into a union within struct hw_perf_event.
> Additional comment wrt PERF_EF_PAUSE/PERF_EF_RESUME.
> Factor out has_aux_action() as an inline function.
> Use scoped_guard for irqsave.
> Move calls of perf_event_aux_pause() from __perf_event_output()
> to __perf_event_overflow().
>
> Changes in V9:
> Move aux_paused to struct hw_perf_event
>
> Changes in V6:
> Removed READ/WRITE_ONCE from __perf_event_aux_pause()
> Expanded comment about guarding against NMI
>
> Changes in V5:
> Added James' Ack
>
> Changes in V4:
> Rename aux_output_cfg -> aux_action
> Reorder aux_action bits from:
> aux_pause, aux_resume, aux_start_paused
> to:
> aux_start_paused, aux_pause, aux_resume
> Fix aux_action bits __u64 -> __u32
>
>
> include/linux/perf_event.h | 28 ++++++++++++
> include/uapi/linux/perf_event.h | 11 ++++-
> kernel/events/core.c | 75 +++++++++++++++++++++++++++++++--
> kernel/events/internal.h | 1 +
> 4 files changed, 110 insertions(+), 5 deletions(-)
>
> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
> index fb908843f209..91b310052a7c 100644
> --- a/include/linux/perf_event.h
> +++ b/include/linux/perf_event.h
> @@ -170,6 +170,12 @@ struct hw_perf_event {
> };
> struct { /* aux / Intel-PT */
> u64 aux_config;
> + /*
> + * For AUX area events, aux_paused cannot be a state
> + * flag because it can be updated asynchronously to
> + * state.
> + */
> + unsigned int aux_paused;
> };
> struct { /* software */
> struct hrtimer hrtimer;
> @@ -294,6 +300,7 @@ struct perf_event_pmu_context;
> #define PERF_PMU_CAP_NO_EXCLUDE 0x0040
> #define PERF_PMU_CAP_AUX_OUTPUT 0x0080
> #define PERF_PMU_CAP_EXTENDED_HW_TYPE 0x0100
> +#define PERF_PMU_CAP_AUX_PAUSE 0x0200
>
> /**
> * pmu::scope
> @@ -384,6 +391,8 @@ struct pmu {
> #define PERF_EF_START 0x01 /* start the counter when adding */
> #define PERF_EF_RELOAD 0x02 /* reload the counter when starting */
> #define PERF_EF_UPDATE 0x04 /* update the counter when stopping */
> +#define PERF_EF_PAUSE 0x08 /* AUX area event, pause tracing */
> +#define PERF_EF_RESUME 0x10 /* AUX area event, resume tracing */
>
> /*
> * Adds/Removes a counter to/from the PMU, can be done inside a
> @@ -423,6 +432,18 @@ struct pmu {
> *
> * ->start() with PERF_EF_RELOAD will reprogram the counter
> * value, must be preceded by a ->stop() with PERF_EF_UPDATE.
> + *
> + * ->stop() with PERF_EF_PAUSE will stop as simply as possible. Will not
> + * overlap another ->stop() with PERF_EF_PAUSE nor ->start() with
> + * PERF_EF_RESUME.
> + *
> + * ->start() with PERF_EF_RESUME will start as simply as possible but
> + * only if the counter is not otherwise stopped. Will not overlap
> + * another ->start() with PERF_EF_RESUME nor ->stop() with
> + * PERF_EF_PAUSE.
> + *
> + * Notably, PERF_EF_PAUSE/PERF_EF_RESUME *can* be concurrent with other
> + * ->stop()/->start() invocations, just not itself.
> */
> void (*start) (struct perf_event *event, int flags);
> void (*stop) (struct perf_event *event, int flags);
> @@ -1679,6 +1700,13 @@ static inline bool has_aux(struct perf_event *event)
> return event->pmu->setup_aux;
> }
>
> +static inline bool has_aux_action(struct perf_event *event)
> +{
> + return event->attr.aux_sample_size ||
> + event->attr.aux_pause ||
> + event->attr.aux_resume;
> +}
> +
> static inline bool is_write_backward(struct perf_event *event)
> {
> return !!event->attr.write_backward;
> diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
> index 4842c36fdf80..0524d541d4e3 100644
> --- a/include/uapi/linux/perf_event.h
> +++ b/include/uapi/linux/perf_event.h
> @@ -511,7 +511,16 @@ struct perf_event_attr {
> __u16 sample_max_stack;
> __u16 __reserved_2;
> __u32 aux_sample_size;
> - __u32 __reserved_3;
> +
> + union {
> + __u32 aux_action;
> + struct {
> + __u32 aux_start_paused : 1, /* start AUX area tracing paused */
> + aux_pause : 1, /* on overflow, pause AUX area tracing */
> + aux_resume : 1, /* on overflow, resume AUX area tracing */
> + __reserved_3 : 29;
> + };
> + };
>
> /*
> * User provided data if sigtrap=1, passed back to user via
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index cdd09769e6c5..daeb65a0e467 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -2146,7 +2146,7 @@ static void perf_put_aux_event(struct perf_event *event)
>
> static bool perf_need_aux_event(struct perf_event *event)
> {
> - return !!event->attr.aux_output || !!event->attr.aux_sample_size;
> + return event->attr.aux_output || has_aux_action(event);
> }
>
> static int perf_get_aux_event(struct perf_event *event,
> @@ -2171,6 +2171,10 @@ static int perf_get_aux_event(struct perf_event *event,
> !perf_aux_output_match(event, group_leader))
> return 0;
>
> + if ((event->attr.aux_pause || event->attr.aux_resume) &&
> + !(group_leader->pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE))
> + return 0;
> +
> if (event->attr.aux_sample_size && !group_leader->pmu->snapshot_aux)
> return 0;
>
> @@ -8016,6 +8020,49 @@ void perf_prepare_header(struct perf_event_header *header,
> WARN_ON_ONCE(header->size & 7);
> }
>
> +static void __perf_event_aux_pause(struct perf_event *event, bool pause)
> +{
> + if (pause) {
> + if (!event->hw.aux_paused) {
> + event->hw.aux_paused = 1;
> + event->pmu->stop(event, PERF_EF_PAUSE);
> + }
> + } else {
> + if (event->hw.aux_paused) {
> + event->hw.aux_paused = 0;
> + event->pmu->start(event, PERF_EF_RESUME);
> + }
> + }
> +}
> +
> +static void perf_event_aux_pause(struct perf_event *event, bool pause)
> +{
> + struct perf_buffer *rb;
> +
> + if (WARN_ON_ONCE(!event))
> + return;
> +
> + rb = ring_buffer_get(event);
> + if (!rb)
> + return;
> +
> + scoped_guard (irqsave) {
> + /*
> + * Guard against self-recursion here. Another event could trip
> + * this same from NMI context.
> + */
> + if (READ_ONCE(rb->aux_in_pause_resume))
> + break;
> +
> + WRITE_ONCE(rb->aux_in_pause_resume, 1);
> + barrier();
> + __perf_event_aux_pause(event, pause);
> + barrier();
> + WRITE_ONCE(rb->aux_in_pause_resume, 0);
> + }
> + ring_buffer_put(rb);
> +}
> +
> static __always_inline int
> __perf_event_output(struct perf_event *event,
> struct perf_sample_data *data,
> @@ -9818,9 +9865,12 @@ static int __perf_event_overflow(struct perf_event *event,
>
> ret = __perf_event_account_interrupt(event, throttle);
>
> + if (event->attr.aux_pause)
> + perf_event_aux_pause(event->aux_event, true);
> +
> if (event->prog && event->prog->type == BPF_PROG_TYPE_PERF_EVENT &&
> !bpf_overflow_handler(event, data, regs))
> - return ret;
> + goto out;
>
> /*
> * XXX event_limit might not quite work as expected on inherited
> @@ -9882,6 +9932,9 @@ static int __perf_event_overflow(struct perf_event *event,
> event->pending_wakeup = 1;
> irq_work_queue(&event->pending_irq);
> }
> +out:
> + if (event->attr.aux_resume)
> + perf_event_aux_pause(event->aux_event, false);
>
> return ret;
> }
> @@ -12273,11 +12326,25 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
> }
>
> if (event->attr.aux_output &&
> - !(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) {
> + (!(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT) ||
> + event->attr.aux_pause || event->attr.aux_resume)) {
> err = -EOPNOTSUPP;
> goto err_pmu;
> }
>
> + if (event->attr.aux_pause && event->attr.aux_resume) {
> + err = -EINVAL;
> + goto err_pmu;
> + }
> +
> + if (event->attr.aux_start_paused) {
> + if (!(pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE)) {
> + err = -EOPNOTSUPP;
> + goto err_pmu;
> + }
> + event->hw.aux_paused = 1;
> + }
> +
> if (cgroup_fd != -1) {
> err = perf_cgroup_connect(cgroup_fd, event, attr, group_leader);
> if (err)
> @@ -13073,7 +13140,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
> * Grouping is not supported for kernel events, neither is 'AUX',
> * make sure the caller's intentions are adjusted.
> */
> - if (attr->aux_output)
> + if (attr->aux_output || attr->aux_action)
> return ERR_PTR(-EINVAL);
>
> event = perf_event_alloc(attr, cpu, task, NULL, NULL,
> diff --git a/kernel/events/internal.h b/kernel/events/internal.h
> index e072d995d670..249288d82b8d 100644
> --- a/kernel/events/internal.h
> +++ b/kernel/events/internal.h
> @@ -52,6 +52,7 @@ struct perf_buffer {
> void (*free_aux)(void *);
> refcount_t aux_refcount;
> int aux_in_sampling;
> + int aux_in_pause_resume;
> void **aux_pages;
> void *aux_priv;
>
> --
> 2.43.0
>
>
The following commit has been merged into the perf/core branch of tip:
Commit-ID: 18d92bb57c39504d9da11c6ef604f58eb1d5a117
Gitweb: https://git.kernel.org/tip/18d92bb57c39504d9da11c6ef604f58eb1d5a117
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Tue, 22 Oct 2024 18:59:08 +03:00
Committer: Peter Zijlstra <peterz@infradead.org>
CommitterDate: Tue, 05 Nov 2024 12:55:43 +01:00
perf/core: Add aux_pause, aux_resume, aux_start_paused
Hardware traces, such as instruction traces, can produce a vast amount of
trace data, so being able to reduce tracing to more specific circumstances
can be useful.
The ability to pause or resume tracing when another event happens, can do
that.
Add ability for an event to "pause" or "resume" AUX area tracing.
Add aux_pause bit to perf_event_attr to indicate that, if the event
happens, the associated AUX area tracing should be paused. Ditto
aux_resume. Do not allow aux_pause and aux_resume to be set together.
Add aux_start_paused bit to perf_event_attr to indicate to an AUX area
event that it should start in a "paused" state.
Add aux_paused to struct hw_perf_event for AUX area events to keep track of
the "paused" state. aux_paused is initialized to aux_start_paused.
Add PERF_EF_PAUSE and PERF_EF_RESUME modes for ->stop() and ->start()
callbacks. Call as needed, during __perf_event_output(). Add
aux_in_pause_resume to struct perf_buffer to prevent races with the NMI
handler. Pause/resume in NMI context will miss out if it coincides with
another pause/resume.
To use aux_pause or aux_resume, an event must be in a group with the AUX
area event as the group leader.
Example (requires Intel PT and tools patches also):
$ perf record --kcore -e intel_pt/aux-action=start-paused/k,syscalls:sys_enter_newuname/aux-action=resume/,syscalls:sys_exit_newuname/aux-action=pause/ uname
Linux
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.043 MB perf.data ]
$ perf script --call-trace
uname 30805 [000] 24001.058782799: name: 0x7ffc9c1865b0
uname 30805 [000] 24001.058784424: psb offs: 0
uname 30805 [000] 24001.058784424: cbr: 39 freq: 3904 MHz (139%)
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) debug_smp_processor_id
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) __x64_sys_newuname
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) down_read
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) __cond_resched
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) preempt_count_add
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) in_lock_functions
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) preempt_count_sub
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) up_read
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) preempt_count_add
uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) in_lock_functions
uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) preempt_count_sub
uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) _copy_to_user
uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) syscall_exit_to_user_mode
uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) syscall_exit_work
uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) perf_syscall_exit
uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) debug_smp_processor_id
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_trace_buf_alloc
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_swevent_get_recursion_context
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) debug_smp_processor_id
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) debug_smp_processor_id
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_tp_event
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_trace_buf_update
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) tracing_gen_ctx_irq_test
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_swevent_event
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __perf_event_account_interrupt
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __this_cpu_preempt_check
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_event_output_forward
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_event_aux_pause
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) ring_buffer_get
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __rcu_read_lock
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __rcu_read_unlock
uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) pt_event_stop
uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) debug_smp_processor_id
uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) debug_smp_processor_id
uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) native_write_msr
uname 30805 [000] 24001.058785463: ([kernel.kallsyms]) native_write_msr
uname 30805 [000] 24001.058785639: 0x0
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: James Clark <james.clark@arm.com>
Link: https://lkml.kernel.org/r/20241022155920.17511-3-adrian.hunter@intel.com
---
include/linux/perf_event.h | 28 ++++++++++++-
include/uapi/linux/perf_event.h | 11 ++++-
kernel/events/core.c | 75 ++++++++++++++++++++++++++++++--
kernel/events/internal.h | 1 +-
4 files changed, 110 insertions(+), 5 deletions(-)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index fb90884..91b3100 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -170,6 +170,12 @@ struct hw_perf_event {
};
struct { /* aux / Intel-PT */
u64 aux_config;
+ /*
+ * For AUX area events, aux_paused cannot be a state
+ * flag because it can be updated asynchronously to
+ * state.
+ */
+ unsigned int aux_paused;
};
struct { /* software */
struct hrtimer hrtimer;
@@ -294,6 +300,7 @@ struct perf_event_pmu_context;
#define PERF_PMU_CAP_NO_EXCLUDE 0x0040
#define PERF_PMU_CAP_AUX_OUTPUT 0x0080
#define PERF_PMU_CAP_EXTENDED_HW_TYPE 0x0100
+#define PERF_PMU_CAP_AUX_PAUSE 0x0200
/**
* pmu::scope
@@ -384,6 +391,8 @@ struct pmu {
#define PERF_EF_START 0x01 /* start the counter when adding */
#define PERF_EF_RELOAD 0x02 /* reload the counter when starting */
#define PERF_EF_UPDATE 0x04 /* update the counter when stopping */
+#define PERF_EF_PAUSE 0x08 /* AUX area event, pause tracing */
+#define PERF_EF_RESUME 0x10 /* AUX area event, resume tracing */
/*
* Adds/Removes a counter to/from the PMU, can be done inside a
@@ -423,6 +432,18 @@ struct pmu {
*
* ->start() with PERF_EF_RELOAD will reprogram the counter
* value, must be preceded by a ->stop() with PERF_EF_UPDATE.
+ *
+ * ->stop() with PERF_EF_PAUSE will stop as simply as possible. Will not
+ * overlap another ->stop() with PERF_EF_PAUSE nor ->start() with
+ * PERF_EF_RESUME.
+ *
+ * ->start() with PERF_EF_RESUME will start as simply as possible but
+ * only if the counter is not otherwise stopped. Will not overlap
+ * another ->start() with PERF_EF_RESUME nor ->stop() with
+ * PERF_EF_PAUSE.
+ *
+ * Notably, PERF_EF_PAUSE/PERF_EF_RESUME *can* be concurrent with other
+ * ->stop()/->start() invocations, just not itself.
*/
void (*start) (struct perf_event *event, int flags);
void (*stop) (struct perf_event *event, int flags);
@@ -1679,6 +1700,13 @@ static inline bool has_aux(struct perf_event *event)
return event->pmu->setup_aux;
}
+static inline bool has_aux_action(struct perf_event *event)
+{
+ return event->attr.aux_sample_size ||
+ event->attr.aux_pause ||
+ event->attr.aux_resume;
+}
+
static inline bool is_write_backward(struct perf_event *event)
{
return !!event->attr.write_backward;
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 4842c36..0524d54 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -511,7 +511,16 @@ struct perf_event_attr {
__u16 sample_max_stack;
__u16 __reserved_2;
__u32 aux_sample_size;
- __u32 __reserved_3;
+
+ union {
+ __u32 aux_action;
+ struct {
+ __u32 aux_start_paused : 1, /* start AUX area tracing paused */
+ aux_pause : 1, /* on overflow, pause AUX area tracing */
+ aux_resume : 1, /* on overflow, resume AUX area tracing */
+ __reserved_3 : 29;
+ };
+ };
/*
* User provided data if sigtrap=1, passed back to user via
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e3589c4..0e9cfe6 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2146,7 +2146,7 @@ static void perf_put_aux_event(struct perf_event *event)
static bool perf_need_aux_event(struct perf_event *event)
{
- return !!event->attr.aux_output || !!event->attr.aux_sample_size;
+ return event->attr.aux_output || has_aux_action(event);
}
static int perf_get_aux_event(struct perf_event *event,
@@ -2171,6 +2171,10 @@ static int perf_get_aux_event(struct perf_event *event,
!perf_aux_output_match(event, group_leader))
return 0;
+ if ((event->attr.aux_pause || event->attr.aux_resume) &&
+ !(group_leader->pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE))
+ return 0;
+
if (event->attr.aux_sample_size && !group_leader->pmu->snapshot_aux)
return 0;
@@ -8016,6 +8020,49 @@ void perf_prepare_header(struct perf_event_header *header,
WARN_ON_ONCE(header->size & 7);
}
+static void __perf_event_aux_pause(struct perf_event *event, bool pause)
+{
+ if (pause) {
+ if (!event->hw.aux_paused) {
+ event->hw.aux_paused = 1;
+ event->pmu->stop(event, PERF_EF_PAUSE);
+ }
+ } else {
+ if (event->hw.aux_paused) {
+ event->hw.aux_paused = 0;
+ event->pmu->start(event, PERF_EF_RESUME);
+ }
+ }
+}
+
+static void perf_event_aux_pause(struct perf_event *event, bool pause)
+{
+ struct perf_buffer *rb;
+
+ if (WARN_ON_ONCE(!event))
+ return;
+
+ rb = ring_buffer_get(event);
+ if (!rb)
+ return;
+
+ scoped_guard (irqsave) {
+ /*
+ * Guard against self-recursion here. Another event could trip
+ * this same from NMI context.
+ */
+ if (READ_ONCE(rb->aux_in_pause_resume))
+ break;
+
+ WRITE_ONCE(rb->aux_in_pause_resume, 1);
+ barrier();
+ __perf_event_aux_pause(event, pause);
+ barrier();
+ WRITE_ONCE(rb->aux_in_pause_resume, 0);
+ }
+ ring_buffer_put(rb);
+}
+
static __always_inline int
__perf_event_output(struct perf_event *event,
struct perf_sample_data *data,
@@ -9818,9 +9865,12 @@ static int __perf_event_overflow(struct perf_event *event,
ret = __perf_event_account_interrupt(event, throttle);
+ if (event->attr.aux_pause)
+ perf_event_aux_pause(event->aux_event, true);
+
if (event->prog && event->prog->type == BPF_PROG_TYPE_PERF_EVENT &&
!bpf_overflow_handler(event, data, regs))
- return ret;
+ goto out;
/*
* XXX event_limit might not quite work as expected on inherited
@@ -9882,6 +9932,9 @@ static int __perf_event_overflow(struct perf_event *event,
event->pending_wakeup = 1;
irq_work_queue(&event->pending_irq);
}
+out:
+ if (event->attr.aux_resume)
+ perf_event_aux_pause(event->aux_event, false);
return ret;
}
@@ -12273,11 +12326,25 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
}
if (event->attr.aux_output &&
- !(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) {
+ (!(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT) ||
+ event->attr.aux_pause || event->attr.aux_resume)) {
err = -EOPNOTSUPP;
goto err_pmu;
}
+ if (event->attr.aux_pause && event->attr.aux_resume) {
+ err = -EINVAL;
+ goto err_pmu;
+ }
+
+ if (event->attr.aux_start_paused) {
+ if (!(pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE)) {
+ err = -EOPNOTSUPP;
+ goto err_pmu;
+ }
+ event->hw.aux_paused = 1;
+ }
+
if (cgroup_fd != -1) {
err = perf_cgroup_connect(cgroup_fd, event, attr, group_leader);
if (err)
@@ -13073,7 +13140,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
* Grouping is not supported for kernel events, neither is 'AUX',
* make sure the caller's intentions are adjusted.
*/
- if (attr->aux_output)
+ if (attr->aux_output || attr->aux_action)
return ERR_PTR(-EINVAL);
event = perf_event_alloc(attr, cpu, task, NULL, NULL,
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index e072d99..249288d 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -52,6 +52,7 @@ struct perf_buffer {
void (*free_aux)(void *);
refcount_t aux_refcount;
int aux_in_sampling;
+ int aux_in_pause_resume;
void **aux_pages;
void *aux_priv;Prevent tracing to start if aux_paused.
Implement support for PERF_EF_PAUSE / PERF_EF_RESUME. When aux_paused, stop
tracing. When not aux_paused, only start tracing if it isn't currently
meant to be stopped.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
---
Changes in V14:
Set pt->handle_nmi after configuration is completed instead of during
Changes in V12:
Rebase on current tip plus patch set "KVM: x86: Fix Intel PT Host/Guest
mode when host tracing"
Changes in V9:
Add more comments and barriers for resume_allowed and
pause_allowed
Always use WRITE_ONCE with resume_allowed
arch/x86/events/intel/pt.c | 73 ++++++++++++++++++++++++++++++++++++--
arch/x86/events/intel/pt.h | 4 +++
2 files changed, 74 insertions(+), 3 deletions(-)
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index a087bc0c5498..4b0373bc8ab4 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -418,6 +418,9 @@ static void pt_config_start(struct perf_event *event)
struct pt *pt = this_cpu_ptr(&pt_ctx);
u64 ctl = event->hw.aux_config;
+ if (READ_ONCE(event->hw.aux_paused))
+ return;
+
ctl |= RTIT_CTL_TRACEEN;
if (READ_ONCE(pt->vmx_on))
perf_aux_output_flag(&pt->handle, PERF_AUX_FLAG_PARTIAL);
@@ -534,7 +537,24 @@ static void pt_config(struct perf_event *event)
reg |= (event->attr.config & PT_CONFIG_MASK);
event->hw.aux_config = reg;
+
+ /*
+ * Allow resume before starting so as not to overwrite a value set by a
+ * PMI.
+ */
+ barrier();
+ WRITE_ONCE(pt->resume_allowed, 1);
+ /* Configuration is complete, it is now OK to handle an NMI */
+ barrier();
+ WRITE_ONCE(pt->handle_nmi, 1);
+ barrier();
pt_config_start(event);
+ barrier();
+ /*
+ * Allow pause after starting so its pt_config_stop() doesn't race with
+ * pt_config_start().
+ */
+ WRITE_ONCE(pt->pause_allowed, 1);
}
static void pt_config_stop(struct perf_event *event)
@@ -1516,6 +1536,7 @@ void intel_pt_interrupt(void)
buf = perf_aux_output_begin(&pt->handle, event);
if (!buf) {
event->hw.state = PERF_HES_STOPPED;
+ WRITE_ONCE(pt->resume_allowed, 0);
return;
}
@@ -1524,6 +1545,7 @@ void intel_pt_interrupt(void)
ret = pt_buffer_reset_markers(buf, &pt->handle);
if (ret) {
perf_aux_output_end(&pt->handle, 0);
+ WRITE_ONCE(pt->resume_allowed, 0);
return;
}
@@ -1578,6 +1600,26 @@ static void pt_event_start(struct perf_event *event, int mode)
struct pt *pt = this_cpu_ptr(&pt_ctx);
struct pt_buffer *buf;
+ if (mode & PERF_EF_RESUME) {
+ if (READ_ONCE(pt->resume_allowed)) {
+ u64 status;
+
+ /*
+ * Only if the trace is not active and the error and
+ * stopped bits are clear, is it safe to start, but a
+ * PMI might have just cleared these, so resume_allowed
+ * must be checked again also.
+ */
+ rdmsrl(MSR_IA32_RTIT_STATUS, status);
+ if (!(status & (RTIT_STATUS_TRIGGEREN |
+ RTIT_STATUS_ERROR |
+ RTIT_STATUS_STOPPED)) &&
+ READ_ONCE(pt->resume_allowed))
+ pt_config_start(event);
+ }
+ return;
+ }
+
buf = perf_aux_output_begin(&pt->handle, event);
if (!buf)
goto fail_stop;
@@ -1588,7 +1630,6 @@ static void pt_event_start(struct perf_event *event, int mode)
goto fail_end_stop;
}
- WRITE_ONCE(pt->handle_nmi, 1);
hwc->state = 0;
pt_config_buffer(buf);
@@ -1606,6 +1647,12 @@ static void pt_event_stop(struct perf_event *event, int mode)
{
struct pt *pt = this_cpu_ptr(&pt_ctx);
+ if (mode & PERF_EF_PAUSE) {
+ if (READ_ONCE(pt->pause_allowed))
+ pt_config_stop(event);
+ return;
+ }
+
/*
* Protect against the PMI racing with disabling wrmsr,
* see comment in intel_pt_interrupt().
@@ -1613,6 +1660,15 @@ static void pt_event_stop(struct perf_event *event, int mode)
WRITE_ONCE(pt->handle_nmi, 0);
barrier();
+ /*
+ * Prevent a resume from attempting to restart tracing, or a pause
+ * during a subsequent start. Do this after clearing handle_nmi so that
+ * pt_event_snapshot_aux() will not re-allow them.
+ */
+ WRITE_ONCE(pt->pause_allowed, 0);
+ WRITE_ONCE(pt->resume_allowed, 0);
+ barrier();
+
pt_config_stop(event);
if (event->hw.state == PERF_HES_STOPPED)
@@ -1662,6 +1718,10 @@ static long pt_event_snapshot_aux(struct perf_event *event,
if (WARN_ON_ONCE(!buf->snapshot))
return 0;
+ /* Prevent pause/resume from attempting to start/stop tracing */
+ WRITE_ONCE(pt->pause_allowed, 0);
+ WRITE_ONCE(pt->resume_allowed, 0);
+ barrier();
/*
* There is no PT interrupt in this mode, so stop the trace and it will
* remain stopped while the buffer is copied.
@@ -1681,8 +1741,13 @@ static long pt_event_snapshot_aux(struct perf_event *event,
* Here, handle_nmi tells us if the tracing was on.
* If the tracing was on, restart it.
*/
- if (READ_ONCE(pt->handle_nmi))
+ if (READ_ONCE(pt->handle_nmi)) {
+ WRITE_ONCE(pt->resume_allowed, 1);
+ barrier();
pt_config_start(event);
+ barrier();
+ WRITE_ONCE(pt->pause_allowed, 1);
+ }
return ret;
}
@@ -1798,7 +1863,9 @@ static __init int pt_init(void)
if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries))
pt_pmu.pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG;
- pt_pmu.pmu.capabilities |= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE;
+ pt_pmu.pmu.capabilities |= PERF_PMU_CAP_EXCLUSIVE |
+ PERF_PMU_CAP_ITRACE |
+ PERF_PMU_CAP_AUX_PAUSE;
pt_pmu.pmu.attr_groups = pt_attr_groups;
pt_pmu.pmu.task_ctx_nr = perf_sw_context;
pt_pmu.pmu.event_init = pt_event_init;
diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h
index a1b6c04b7f68..7ee94fc6d7cb 100644
--- a/arch/x86/events/intel/pt.h
+++ b/arch/x86/events/intel/pt.h
@@ -119,6 +119,8 @@ struct pt_filters {
* @filters: last configured filters
* @handle_nmi: do handle PT PMI on this cpu, there's an active event
* @vmx_on: 1 if VMX is ON on this cpu
+ * @pause_allowed: PERF_EF_PAUSE is allowed to stop tracing
+ * @resume_allowed: PERF_EF_RESUME is allowed to start tracing
* @output_base: cached RTIT_OUTPUT_BASE MSR value
* @output_mask: cached RTIT_OUTPUT_MASK MSR value
*/
@@ -127,6 +129,8 @@ struct pt {
struct pt_filters filters;
int handle_nmi;
int vmx_on;
+ int pause_allowed;
+ int resume_allowed;
u64 output_base;
u64 output_mask;
};
--
2.43.0The following commit has been merged into the perf/core branch of tip:
Commit-ID: 08c7454ceb948d773fcd0ff7b6fb9c315e2f801a
Gitweb: https://git.kernel.org/tip/08c7454ceb948d773fcd0ff7b6fb9c315e2f801a
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Tue, 22 Oct 2024 18:59:09 +03:00
Committer: Peter Zijlstra <peterz@infradead.org>
CommitterDate: Tue, 05 Nov 2024 12:55:44 +01:00
perf/x86/intel/pt: Add support for pause / resume
Prevent tracing to start if aux_paused.
Implement support for PERF_EF_PAUSE / PERF_EF_RESUME. When aux_paused, stop
tracing. When not aux_paused, only start tracing if it isn't currently
meant to be stopped.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Link: https://lkml.kernel.org/r/20241022155920.17511-4-adrian.hunter@intel.com
---
arch/x86/events/intel/pt.c | 73 +++++++++++++++++++++++++++++++++++--
arch/x86/events/intel/pt.h | 4 ++-
2 files changed, 74 insertions(+), 3 deletions(-)
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index a087bc0..4b0373b 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -418,6 +418,9 @@ static void pt_config_start(struct perf_event *event)
struct pt *pt = this_cpu_ptr(&pt_ctx);
u64 ctl = event->hw.aux_config;
+ if (READ_ONCE(event->hw.aux_paused))
+ return;
+
ctl |= RTIT_CTL_TRACEEN;
if (READ_ONCE(pt->vmx_on))
perf_aux_output_flag(&pt->handle, PERF_AUX_FLAG_PARTIAL);
@@ -534,7 +537,24 @@ static void pt_config(struct perf_event *event)
reg |= (event->attr.config & PT_CONFIG_MASK);
event->hw.aux_config = reg;
+
+ /*
+ * Allow resume before starting so as not to overwrite a value set by a
+ * PMI.
+ */
+ barrier();
+ WRITE_ONCE(pt->resume_allowed, 1);
+ /* Configuration is complete, it is now OK to handle an NMI */
+ barrier();
+ WRITE_ONCE(pt->handle_nmi, 1);
+ barrier();
pt_config_start(event);
+ barrier();
+ /*
+ * Allow pause after starting so its pt_config_stop() doesn't race with
+ * pt_config_start().
+ */
+ WRITE_ONCE(pt->pause_allowed, 1);
}
static void pt_config_stop(struct perf_event *event)
@@ -1516,6 +1536,7 @@ void intel_pt_interrupt(void)
buf = perf_aux_output_begin(&pt->handle, event);
if (!buf) {
event->hw.state = PERF_HES_STOPPED;
+ WRITE_ONCE(pt->resume_allowed, 0);
return;
}
@@ -1524,6 +1545,7 @@ void intel_pt_interrupt(void)
ret = pt_buffer_reset_markers(buf, &pt->handle);
if (ret) {
perf_aux_output_end(&pt->handle, 0);
+ WRITE_ONCE(pt->resume_allowed, 0);
return;
}
@@ -1578,6 +1600,26 @@ static void pt_event_start(struct perf_event *event, int mode)
struct pt *pt = this_cpu_ptr(&pt_ctx);
struct pt_buffer *buf;
+ if (mode & PERF_EF_RESUME) {
+ if (READ_ONCE(pt->resume_allowed)) {
+ u64 status;
+
+ /*
+ * Only if the trace is not active and the error and
+ * stopped bits are clear, is it safe to start, but a
+ * PMI might have just cleared these, so resume_allowed
+ * must be checked again also.
+ */
+ rdmsrl(MSR_IA32_RTIT_STATUS, status);
+ if (!(status & (RTIT_STATUS_TRIGGEREN |
+ RTIT_STATUS_ERROR |
+ RTIT_STATUS_STOPPED)) &&
+ READ_ONCE(pt->resume_allowed))
+ pt_config_start(event);
+ }
+ return;
+ }
+
buf = perf_aux_output_begin(&pt->handle, event);
if (!buf)
goto fail_stop;
@@ -1588,7 +1630,6 @@ static void pt_event_start(struct perf_event *event, int mode)
goto fail_end_stop;
}
- WRITE_ONCE(pt->handle_nmi, 1);
hwc->state = 0;
pt_config_buffer(buf);
@@ -1606,6 +1647,12 @@ static void pt_event_stop(struct perf_event *event, int mode)
{
struct pt *pt = this_cpu_ptr(&pt_ctx);
+ if (mode & PERF_EF_PAUSE) {
+ if (READ_ONCE(pt->pause_allowed))
+ pt_config_stop(event);
+ return;
+ }
+
/*
* Protect against the PMI racing with disabling wrmsr,
* see comment in intel_pt_interrupt().
@@ -1613,6 +1660,15 @@ static void pt_event_stop(struct perf_event *event, int mode)
WRITE_ONCE(pt->handle_nmi, 0);
barrier();
+ /*
+ * Prevent a resume from attempting to restart tracing, or a pause
+ * during a subsequent start. Do this after clearing handle_nmi so that
+ * pt_event_snapshot_aux() will not re-allow them.
+ */
+ WRITE_ONCE(pt->pause_allowed, 0);
+ WRITE_ONCE(pt->resume_allowed, 0);
+ barrier();
+
pt_config_stop(event);
if (event->hw.state == PERF_HES_STOPPED)
@@ -1662,6 +1718,10 @@ static long pt_event_snapshot_aux(struct perf_event *event,
if (WARN_ON_ONCE(!buf->snapshot))
return 0;
+ /* Prevent pause/resume from attempting to start/stop tracing */
+ WRITE_ONCE(pt->pause_allowed, 0);
+ WRITE_ONCE(pt->resume_allowed, 0);
+ barrier();
/*
* There is no PT interrupt in this mode, so stop the trace and it will
* remain stopped while the buffer is copied.
@@ -1681,8 +1741,13 @@ static long pt_event_snapshot_aux(struct perf_event *event,
* Here, handle_nmi tells us if the tracing was on.
* If the tracing was on, restart it.
*/
- if (READ_ONCE(pt->handle_nmi))
+ if (READ_ONCE(pt->handle_nmi)) {
+ WRITE_ONCE(pt->resume_allowed, 1);
+ barrier();
pt_config_start(event);
+ barrier();
+ WRITE_ONCE(pt->pause_allowed, 1);
+ }
return ret;
}
@@ -1798,7 +1863,9 @@ static __init int pt_init(void)
if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries))
pt_pmu.pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG;
- pt_pmu.pmu.capabilities |= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE;
+ pt_pmu.pmu.capabilities |= PERF_PMU_CAP_EXCLUSIVE |
+ PERF_PMU_CAP_ITRACE |
+ PERF_PMU_CAP_AUX_PAUSE;
pt_pmu.pmu.attr_groups = pt_attr_groups;
pt_pmu.pmu.task_ctx_nr = perf_sw_context;
pt_pmu.pmu.event_init = pt_event_init;
diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h
index a1b6c04..7ee94fc 100644
--- a/arch/x86/events/intel/pt.h
+++ b/arch/x86/events/intel/pt.h
@@ -119,6 +119,8 @@ struct pt_filters {
* @filters: last configured filters
* @handle_nmi: do handle PT PMI on this cpu, there's an active event
* @vmx_on: 1 if VMX is ON on this cpu
+ * @pause_allowed: PERF_EF_PAUSE is allowed to stop tracing
+ * @resume_allowed: PERF_EF_RESUME is allowed to start tracing
* @output_base: cached RTIT_OUTPUT_BASE MSR value
* @output_mask: cached RTIT_OUTPUT_MASK MSR value
*/
@@ -127,6 +129,8 @@ struct pt {
struct pt_filters filters;
int handle_nmi;
int vmx_on;
+ int pause_allowed;
+ int resume_allowed;
u64 output_base;
u64 output_mask;
};Events with aux actions or aux sampling expect the PMI to coincide with the
event, which does not happen for large PEBS, so do not enable large PEBS in
that case.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
---
Changes in V11:
Remove definition of has_aux_action() because it has
already been added as an inline function.
arch/x86/events/intel/core.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 7ca40002a19b..bb284aff7bfd 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3962,8 +3962,8 @@ static int intel_pmu_hw_config(struct perf_event *event)
if (!(event->attr.freq || (event->attr.wakeup_events && !event->attr.watermark))) {
event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
- if (!(event->attr.sample_type &
- ~intel_pmu_large_pebs_flags(event))) {
+ if (!(event->attr.sample_type & ~intel_pmu_large_pebs_flags(event)) &&
+ !has_aux_action(event)) {
event->hw.flags |= PERF_X86_EVENT_LARGE_PEBS;
event->attach_state |= PERF_ATTACH_SCHED_CB;
}
--
2.43.0The following commit has been merged into the perf/core branch of tip:
Commit-ID: 0d5eb14c1e2ed4a8413458cb3b779f215ff214aa
Gitweb: https://git.kernel.org/tip/0d5eb14c1e2ed4a8413458cb3b779f215ff214aa
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Tue, 22 Oct 2024 18:59:10 +03:00
Committer: Peter Zijlstra <peterz@infradead.org>
CommitterDate: Tue, 05 Nov 2024 12:55:44 +01:00
perf/x86/intel: Do not enable large PEBS for events with aux actions or aux sampling
Events with aux actions or aux sampling expect the PMI to coincide with the
event, which does not happen for large PEBS, so do not enable large PEBS in
that case.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Link: https://lkml.kernel.org/r/20241022155920.17511-5-adrian.hunter@intel.com
---
arch/x86/events/intel/core.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 7ca4000..bb284af 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3962,8 +3962,8 @@ static int intel_pmu_hw_config(struct perf_event *event)
if (!(event->attr.freq || (event->attr.wakeup_events && !event->attr.watermark))) {
event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
- if (!(event->attr.sample_type &
- ~intel_pmu_large_pebs_flags(event))) {
+ if (!(event->attr.sample_type & ~intel_pmu_large_pebs_flags(event)) &&
+ !has_aux_action(event)) {
event->hw.flags |= PERF_X86_EVENT_LARGE_PEBS;
event->attach_state |= PERF_ATTACH_SCHED_CB;
}Add struct perf_event_attr members to support pause and resume of AUX area
tracing.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
---
tools/include/uapi/linux/perf_event.h | 11 ++++++++++-
tools/perf/util/perf_event_attr_fprintf.c | 3 +++
2 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 4842c36fdf80..0524d541d4e3 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -511,7 +511,16 @@ struct perf_event_attr {
__u16 sample_max_stack;
__u16 __reserved_2;
__u32 aux_sample_size;
- __u32 __reserved_3;
+
+ union {
+ __u32 aux_action;
+ struct {
+ __u32 aux_start_paused : 1, /* start AUX area tracing paused */
+ aux_pause : 1, /* on overflow, pause AUX area tracing */
+ aux_resume : 1, /* on overflow, resume AUX area tracing */
+ __reserved_3 : 29;
+ };
+ };
/*
* User provided data if sigtrap=1, passed back to user via
diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c
index 59fbbba79697..29db0aef9a74 100644
--- a/tools/perf/util/perf_event_attr_fprintf.c
+++ b/tools/perf/util/perf_event_attr_fprintf.c
@@ -335,6 +335,9 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
PRINT_ATTRf(sample_max_stack, p_unsigned);
PRINT_ATTRf(aux_sample_size, p_unsigned);
PRINT_ATTRf(sig_data, p_unsigned);
+ PRINT_ATTRf(aux_start_paused, p_unsigned);
+ PRINT_ATTRf(aux_pause, p_unsigned);
+ PRINT_ATTRf(aux_resume, p_unsigned);
return ret;
}
--
2.43.0Add a new common config term "aux-action" to use for configuring AUX area
trace pause / resume. The value is a string that will be parsed in a
subsequent patch.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
---
Changes in V7:
Add aux-action to perf_pmu__for_each_format
tools/perf/util/evsel.c | 2 ++
tools/perf/util/evsel_config.h | 1 +
tools/perf/util/parse-events.c | 10 ++++++++++
tools/perf/util/parse-events.h | 1 +
tools/perf/util/parse-events.l | 1 +
tools/perf/util/pmu.c | 1 +
6 files changed, 16 insertions(+)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 14663ad14c53..8f7932cd5550 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1104,6 +1104,8 @@ static void evsel__apply_config_terms(struct evsel *evsel,
case EVSEL__CONFIG_TERM_AUX_OUTPUT:
attr->aux_output = term->val.aux_output ? 1 : 0;
break;
+ case EVSEL__CONFIG_TERM_AUX_ACTION:
+ break;
case EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE:
/* Already applied by auxtrace */
break;
diff --git a/tools/perf/util/evsel_config.h b/tools/perf/util/evsel_config.h
index aee6f808b512..af52a1516d0b 100644
--- a/tools/perf/util/evsel_config.h
+++ b/tools/perf/util/evsel_config.h
@@ -25,6 +25,7 @@ enum evsel_term_type {
EVSEL__CONFIG_TERM_BRANCH,
EVSEL__CONFIG_TERM_PERCORE,
EVSEL__CONFIG_TERM_AUX_OUTPUT,
+ EVSEL__CONFIG_TERM_AUX_ACTION,
EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE,
EVSEL__CONFIG_TERM_CFG_CHG,
};
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 4507ae68198b..e01e13cfc403 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -795,6 +795,7 @@ const char *parse_events__term_type_str(enum parse_events__term_type term_type)
[PARSE_EVENTS__TERM_TYPE_DRV_CFG] = "driver-config",
[PARSE_EVENTS__TERM_TYPE_PERCORE] = "percore",
[PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT] = "aux-output",
+ [PARSE_EVENTS__TERM_TYPE_AUX_ACTION] = "aux-action",
[PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE] = "aux-sample-size",
[PARSE_EVENTS__TERM_TYPE_METRIC_ID] = "metric-id",
[PARSE_EVENTS__TERM_TYPE_RAW] = "raw",
@@ -844,6 +845,7 @@ config_term_avail(enum parse_events__term_type term_type, struct parse_events_er
case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
case PARSE_EVENTS__TERM_TYPE_DRV_CFG:
case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
+ case PARSE_EVENTS__TERM_TYPE_AUX_ACTION:
case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE:
case PARSE_EVENTS__TERM_TYPE_RAW:
case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE:
@@ -963,6 +965,9 @@ do { \
case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
CHECK_TYPE_VAL(NUM);
break;
+ case PARSE_EVENTS__TERM_TYPE_AUX_ACTION:
+ CHECK_TYPE_VAL(STR);
+ break;
case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE:
CHECK_TYPE_VAL(NUM);
if (term->val.num > UINT_MAX) {
@@ -1081,6 +1086,7 @@ static int config_term_tracepoint(struct perf_event_attr *attr,
case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
+ case PARSE_EVENTS__TERM_TYPE_AUX_ACTION:
case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE:
return config_term_common(attr, term, err);
case PARSE_EVENTS__TERM_TYPE_USER:
@@ -1217,6 +1223,9 @@ do { \
ADD_CONFIG_TERM_VAL(AUX_OUTPUT, aux_output,
term->val.num ? 1 : 0, term->weak);
break;
+ case PARSE_EVENTS__TERM_TYPE_AUX_ACTION:
+ ADD_CONFIG_TERM_STR(AUX_ACTION, term->val.str, term->weak);
+ break;
case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE:
ADD_CONFIG_TERM_VAL(AUX_SAMPLE_SIZE, aux_sample_size,
term->val.num, term->weak);
@@ -1279,6 +1288,7 @@ static int get_config_chgs(struct perf_pmu *pmu, struct parse_events_terms *head
case PARSE_EVENTS__TERM_TYPE_DRV_CFG:
case PARSE_EVENTS__TERM_TYPE_PERCORE:
case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
+ case PARSE_EVENTS__TERM_TYPE_AUX_ACTION:
case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE:
case PARSE_EVENTS__TERM_TYPE_METRIC_ID:
case PARSE_EVENTS__TERM_TYPE_RAW:
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 3f4334ec6231..e176a34ab088 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -74,6 +74,7 @@ enum parse_events__term_type {
PARSE_EVENTS__TERM_TYPE_DRV_CFG,
PARSE_EVENTS__TERM_TYPE_PERCORE,
PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT,
+ PARSE_EVENTS__TERM_TYPE_AUX_ACTION,
PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE,
PARSE_EVENTS__TERM_TYPE_METRIC_ID,
PARSE_EVENTS__TERM_TYPE_RAW,
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 14e5bd856a18..bf7f73548605 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -321,6 +321,7 @@ overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_OVERWRITE); }
no-overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE); }
percore { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); }
aux-output { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); }
+aux-action { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_ACTION); }
aux-sample-size { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE); }
metric-id { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_METRIC_ID); }
cpu-cycles|cycles { return hw_term(yyscanner, PERF_COUNT_HW_CPU_CYCLES); }
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 0789758598c0..a9b680479290 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1779,6 +1779,7 @@ int perf_pmu__for_each_format(struct perf_pmu *pmu, void *state, pmu_format_call
"no-overwrite",
"percore",
"aux-output",
+ "aux-action=(pause|resume|start-paused)",
"aux-sample-size=number",
};
struct perf_pmu_format *format;
--
2.43.0Add parsing for aux-action to accept "pause", "resume" or "start-paused"
values.
"start-paused" is valid only for AUX area events.
"pause" and "resume" are valid only for events grouped with an AUX area
event as the group leader. However, like with aux-output, the events
will be automatically grouped if they are not currently in a group, and
the AUX area event precedes the other events.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
---
Changes in V8:
Fix clang warning:
util/auxtrace.c:821:7: error: missing field 'aux_action' initializer [-Werror,-Wmissing-field-initializers]
821 | {NULL},
| ^
tools/perf/Documentation/perf-record.txt | 4 ++
tools/perf/builtin-record.c | 4 +-
tools/perf/util/auxtrace.c | 67 ++++++++++++++++++++++--
tools/perf/util/auxtrace.h | 6 ++-
tools/perf/util/evsel.c | 1 +
5 files changed, 74 insertions(+), 8 deletions(-)
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 242223240a08..80686d590de2 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -68,6 +68,10 @@ OPTIONS
like this: name=\'CPU_CLK_UNHALTED.THREAD:cmask=0x1\'.
- 'aux-output': Generate AUX records instead of events. This requires
that an AUX area event is also provided.
+ - 'aux-action': "pause" or "resume" to pause or resume an AUX
+ area event (the group leader) when this event occurs.
+ "start-paused" on an AUX area event itself, will
+ start in a paused state.
- 'aux-sample-size': Set sample size for AUX area sampling. If the
'--aux-sample' option has been used, set aux-sample-size=0 to disable
AUX area sampling for the event.
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index adbaf80b398c..a7afde2fbebc 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -860,7 +860,9 @@ static int record__auxtrace_init(struct record *rec)
if (err)
return err;
- auxtrace_regroup_aux_output(rec->evlist);
+ err = auxtrace_parse_aux_action(rec->evlist);
+ if (err)
+ return err;
return auxtrace_parse_filters(rec->evlist);
}
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index ca8682966fae..4d1633d87eff 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -810,19 +810,76 @@ int auxtrace_parse_sample_options(struct auxtrace_record *itr,
return auxtrace_validate_aux_sample_size(evlist, opts);
}
-void auxtrace_regroup_aux_output(struct evlist *evlist)
+static struct aux_action_opt {
+ const char *str;
+ u32 aux_action;
+ bool aux_event_opt;
+} aux_action_opts[] = {
+ {"start-paused", BIT(0), true},
+ {"pause", BIT(1), false},
+ {"resume", BIT(2), false},
+ {.str = NULL},
+};
+
+static const struct aux_action_opt *auxtrace_parse_aux_action_str(const char *str)
+{
+ const struct aux_action_opt *opt;
+
+ if (!str)
+ return NULL;
+
+ for (opt = aux_action_opts; opt->str; opt++)
+ if (!strcmp(str, opt->str))
+ return opt;
+
+ return NULL;
+}
+
+int auxtrace_parse_aux_action(struct evlist *evlist)
{
- struct evsel *evsel, *aux_evsel = NULL;
struct evsel_config_term *term;
+ struct evsel *aux_evsel = NULL;
+ struct evsel *evsel;
evlist__for_each_entry(evlist, evsel) {
- if (evsel__is_aux_event(evsel))
+ bool is_aux_event = evsel__is_aux_event(evsel);
+ const struct aux_action_opt *opt;
+
+ if (is_aux_event)
aux_evsel = evsel;
- term = evsel__get_config_term(evsel, AUX_OUTPUT);
+ term = evsel__get_config_term(evsel, AUX_ACTION);
+ if (!term) {
+ if (evsel__get_config_term(evsel, AUX_OUTPUT))
+ goto regroup;
+ continue;
+ }
+ opt = auxtrace_parse_aux_action_str(term->val.str);
+ if (!opt) {
+ pr_err("Bad aux-action '%s'\n", term->val.str);
+ return -EINVAL;
+ }
+ if (opt->aux_event_opt && !is_aux_event) {
+ pr_err("aux-action '%s' can only be used with AUX area event\n",
+ term->val.str);
+ return -EINVAL;
+ }
+ if (!opt->aux_event_opt && is_aux_event) {
+ pr_err("aux-action '%s' cannot be used for AUX area event itself\n",
+ term->val.str);
+ return -EINVAL;
+ }
+ evsel->core.attr.aux_action = opt->aux_action;
+regroup:
/* If possible, group with the AUX event */
- if (term && aux_evsel)
+ if (aux_evsel)
evlist__regroup(evlist, aux_evsel, evsel);
+ if (!evsel__is_aux_event(evsel__leader(evsel))) {
+ pr_err("Events with aux-action must have AUX area event group leader\n");
+ return -EINVAL;
+ }
}
+
+ return 0;
}
struct auxtrace_record *__weak
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index a1895a4f530b..208c15be9221 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -579,7 +579,7 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
int auxtrace_parse_sample_options(struct auxtrace_record *itr,
struct evlist *evlist,
struct record_opts *opts, const char *str);
-void auxtrace_regroup_aux_output(struct evlist *evlist);
+int auxtrace_parse_aux_action(struct evlist *evlist);
int auxtrace_record__options(struct auxtrace_record *itr,
struct evlist *evlist,
struct record_opts *opts);
@@ -800,8 +800,10 @@ int auxtrace_parse_sample_options(struct auxtrace_record *itr __maybe_unused,
}
static inline
-void auxtrace_regroup_aux_output(struct evlist *evlist __maybe_unused)
+int auxtrace_parse_aux_action(struct evlist *evlist __maybe_unused)
{
+ pr_err("AUX area tracing not supported\n");
+ return -EINVAL;
}
static inline
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 8f7932cd5550..95593b55d9a7 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1105,6 +1105,7 @@ static void evsel__apply_config_terms(struct evsel *evsel,
attr->aux_output = term->val.aux_output ? 1 : 0;
break;
case EVSEL__CONFIG_TERM_AUX_ACTION:
+ /* Already applied by auxtrace */
break;
case EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE:
/* Already applied by auxtrace */
--
2.43.0Display "feature is not supported" error message if aux_start_paused,
aux_pause or aux_resume result in a perf_event_open() error.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
---
Changes in V13:
Add error message also in EOPNOTSUPP case (Leo)
tools/perf/util/evsel.c | 12 ++++++++++++
tools/perf/util/evsel.h | 1 +
2 files changed, 13 insertions(+)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 95593b55d9a7..88b31a005ac6 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2102,6 +2102,12 @@ bool evsel__detect_missing_features(struct evsel *evsel)
perf_missing_features.inherit_sample_read = true;
pr_debug2("Using PERF_SAMPLE_READ / :S modifier is not compatible with inherit, falling back to no-inherit.\n");
return true;
+ } else if (!perf_missing_features.aux_pause_resume &&
+ (evsel->core.attr.aux_pause || evsel->core.attr.aux_resume ||
+ evsel->core.attr.aux_start_paused)) {
+ perf_missing_features.aux_pause_resume = true;
+ pr_debug2_peo("Kernel has no aux_pause/aux_resume support, bailing out\n");
+ return false;
} else if (!perf_missing_features.branch_counters &&
(evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS)) {
perf_missing_features.branch_counters = true;
@@ -3279,6 +3285,10 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target,
return scnprintf(msg, size,
"%s: PMU Hardware doesn't support 'aux_output' feature",
evsel__name(evsel));
+ if (evsel->core.attr.aux_action)
+ return scnprintf(msg, size,
+ "%s: PMU Hardware doesn't support 'aux_action' feature",
+ evsel__name(evsel));
if (evsel->core.attr.sample_period != 0)
return scnprintf(msg, size,
"%s: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat'",
@@ -3309,6 +3319,8 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target,
return scnprintf(msg, size, "clockid feature not supported.");
if (perf_missing_features.clockid_wrong)
return scnprintf(msg, size, "wrong clockid (%d).", clockid);
+ if (perf_missing_features.aux_pause_resume)
+ return scnprintf(msg, size, "The 'aux_pause / aux_resume' feature is not supported, update the kernel.");
if (perf_missing_features.aux_output)
return scnprintf(msg, size, "The 'aux_output' feature is not supported, update the kernel.");
if (!target__has_cpu(target))
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 9fcaf417b277..87135012217d 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -205,6 +205,7 @@ struct perf_missing_features {
bool weight_struct;
bool read_lost;
bool branch_counters;
+ bool aux_pause_resume;
bool inherit_sample_read;
};
--
2.43.0Hi Adrian,
On Tue, Oct 22, 2024 at 06:59:14PM +0300, Adrian Hunter wrote:
>
> Display "feature is not supported" error message if aux_start_paused,
> aux_pause or aux_resume result in a perf_event_open() error.
>
> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
> Acked-by: Ian Rogers <irogers@google.com>
> Reviewed-by: Andi Kleen <ak@linux.intel.com>
> ---
>
>
> Changes in V13:
> Add error message also in EOPNOTSUPP case (Leo)
>
>
> tools/perf/util/evsel.c | 12 ++++++++++++
> tools/perf/util/evsel.h | 1 +
> 2 files changed, 13 insertions(+)
>
> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> index 95593b55d9a7..88b31a005ac6 100644
> --- a/tools/perf/util/evsel.c
> +++ b/tools/perf/util/evsel.c
> @@ -2102,6 +2102,12 @@ bool evsel__detect_missing_features(struct evsel *evsel)
> perf_missing_features.inherit_sample_read = true;
> pr_debug2("Using PERF_SAMPLE_READ / :S modifier is not compatible with inherit, falling back to no-inherit.\n");
> return true;
> + } else if (!perf_missing_features.aux_pause_resume &&
> + (evsel->core.attr.aux_pause || evsel->core.attr.aux_resume ||
> + evsel->core.attr.aux_start_paused)) {
> + perf_missing_features.aux_pause_resume = true;
> + pr_debug2_peo("Kernel has no aux_pause/aux_resume support, bailing out\n");
> + return false;
This patch fails to apply on the latest perf-tools-next branch due to
conflict:
https://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next.git
branch: perf-tools-next
You might need to rebase it on the latest code base.
Thanks,
Leo
> } else if (!perf_missing_features.branch_counters &&
> (evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS)) {
> perf_missing_features.branch_counters = true;
> @@ -3279,6 +3285,10 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target,
> return scnprintf(msg, size,
> "%s: PMU Hardware doesn't support 'aux_output' feature",
> evsel__name(evsel));
> + if (evsel->core.attr.aux_action)
> + return scnprintf(msg, size,
> + "%s: PMU Hardware doesn't support 'aux_action' feature",
> + evsel__name(evsel));
> if (evsel->core.attr.sample_period != 0)
> return scnprintf(msg, size,
> "%s: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat'",
> @@ -3309,6 +3319,8 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target,
> return scnprintf(msg, size, "clockid feature not supported.");
> if (perf_missing_features.clockid_wrong)
> return scnprintf(msg, size, "wrong clockid (%d).", clockid);
> + if (perf_missing_features.aux_pause_resume)
> + return scnprintf(msg, size, "The 'aux_pause / aux_resume' feature is not supported, update the kernel.");
> if (perf_missing_features.aux_output)
> return scnprintf(msg, size, "The 'aux_output' feature is not supported, update the kernel.");
> if (!target__has_cpu(target))
> diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
> index 9fcaf417b277..87135012217d 100644
> --- a/tools/perf/util/evsel.h
> +++ b/tools/perf/util/evsel.h
> @@ -205,6 +205,7 @@ struct perf_missing_features {
> bool weight_struct;
> bool read_lost;
> bool branch_counters;
> + bool aux_pause_resume;
> bool inherit_sample_read;
> };
>
> --
> 2.43.0
>
>
Hello,
On Fri, Nov 08, 2024 at 03:41:52PM +0000, Leo Yan wrote:
> Hi Adrian,
>
> On Tue, Oct 22, 2024 at 06:59:14PM +0300, Adrian Hunter wrote:
> >
> > Display "feature is not supported" error message if aux_start_paused,
> > aux_pause or aux_resume result in a perf_event_open() error.
> >
> > Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
> > Acked-by: Ian Rogers <irogers@google.com>
> > Reviewed-by: Andi Kleen <ak@linux.intel.com>
> > ---
> >
> >
> > Changes in V13:
> > Add error message also in EOPNOTSUPP case (Leo)
> >
> >
> > tools/perf/util/evsel.c | 12 ++++++++++++
> > tools/perf/util/evsel.h | 1 +
> > 2 files changed, 13 insertions(+)
> >
> > diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> > index 95593b55d9a7..88b31a005ac6 100644
> > --- a/tools/perf/util/evsel.c
> > +++ b/tools/perf/util/evsel.c
> > @@ -2102,6 +2102,12 @@ bool evsel__detect_missing_features(struct evsel *evsel)
> > perf_missing_features.inherit_sample_read = true;
> > pr_debug2("Using PERF_SAMPLE_READ / :S modifier is not compatible with inherit, falling back to no-inherit.\n");
> > return true;
> > + } else if (!perf_missing_features.aux_pause_resume &&
> > + (evsel->core.attr.aux_pause || evsel->core.attr.aux_resume ||
> > + evsel->core.attr.aux_start_paused)) {
> > + perf_missing_features.aux_pause_resume = true;
> > + pr_debug2_peo("Kernel has no aux_pause/aux_resume support, bailing out\n");
> > + return false;
>
> This patch fails to apply on the latest perf-tools-next branch due to
> conflict:
>
> https://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next.git
> branch: perf-tools-next
>
> You might need to rebase it on the latest code base.
Yep, please do for the tooling patches.
Thanks,
Namhyung
On 8/11/24 19:39, Namhyung Kim wrote:
> Hello,
>
> On Fri, Nov 08, 2024 at 03:41:52PM +0000, Leo Yan wrote:
>> Hi Adrian,
>>
>> On Tue, Oct 22, 2024 at 06:59:14PM +0300, Adrian Hunter wrote:
>>>
>>> Display "feature is not supported" error message if aux_start_paused,
>>> aux_pause or aux_resume result in a perf_event_open() error.
>>>
>>> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
>>> Acked-by: Ian Rogers <irogers@google.com>
>>> Reviewed-by: Andi Kleen <ak@linux.intel.com>
>>> ---
>>>
>>>
>>> Changes in V13:
>>> Add error message also in EOPNOTSUPP case (Leo)
>>>
>>>
>>> tools/perf/util/evsel.c | 12 ++++++++++++
>>> tools/perf/util/evsel.h | 1 +
>>> 2 files changed, 13 insertions(+)
>>>
>>> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
>>> index 95593b55d9a7..88b31a005ac6 100644
>>> --- a/tools/perf/util/evsel.c
>>> +++ b/tools/perf/util/evsel.c
>>> @@ -2102,6 +2102,12 @@ bool evsel__detect_missing_features(struct evsel *evsel)
>>> perf_missing_features.inherit_sample_read = true;
>>> pr_debug2("Using PERF_SAMPLE_READ / :S modifier is not compatible with inherit, falling back to no-inherit.\n");
>>> return true;
>>> + } else if (!perf_missing_features.aux_pause_resume &&
>>> + (evsel->core.attr.aux_pause || evsel->core.attr.aux_resume ||
>>> + evsel->core.attr.aux_start_paused)) {
>>> + perf_missing_features.aux_pause_resume = true;
>>> + pr_debug2_peo("Kernel has no aux_pause/aux_resume support, bailing out\n");
>>> + return false;
>>
>> This patch fails to apply on the latest perf-tools-next branch due to
>> conflict:
>>
>> https://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next.git
>> branch: perf-tools-next
>>
>> You might need to rebase it on the latest code base.
>
> Yep, please do for the tooling patches.
I'd noticed that, but there is more work to sort it out.
The probing simply won't work when there are dependencies
on other events, or other attr members. But there is no
point in trying to "fallback" in that case either. It is
just a failure, but what *is* still needed is a sensible
error message.
The other patches, including the ones that come after,
still apply by the way, or they did the other day, so
they could be applied anyway.
On Fri, Nov 08, 2024 at 08:01:02PM +0200, Adrian Hunter wrote:
> On 8/11/24 19:39, Namhyung Kim wrote:
> > Hello,
> >
> > On Fri, Nov 08, 2024 at 03:41:52PM +0000, Leo Yan wrote:
> >> Hi Adrian,
> >>
> >> On Tue, Oct 22, 2024 at 06:59:14PM +0300, Adrian Hunter wrote:
> >>>
> >>> Display "feature is not supported" error message if aux_start_paused,
> >>> aux_pause or aux_resume result in a perf_event_open() error.
> >>>
> >>> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
> >>> Acked-by: Ian Rogers <irogers@google.com>
> >>> Reviewed-by: Andi Kleen <ak@linux.intel.com>
> >>> ---
> >>>
> >>>
> >>> Changes in V13:
> >>> Add error message also in EOPNOTSUPP case (Leo)
> >>>
> >>>
> >>> tools/perf/util/evsel.c | 12 ++++++++++++
> >>> tools/perf/util/evsel.h | 1 +
> >>> 2 files changed, 13 insertions(+)
> >>>
> >>> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> >>> index 95593b55d9a7..88b31a005ac6 100644
> >>> --- a/tools/perf/util/evsel.c
> >>> +++ b/tools/perf/util/evsel.c
> >>> @@ -2102,6 +2102,12 @@ bool evsel__detect_missing_features(struct evsel *evsel)
> >>> perf_missing_features.inherit_sample_read = true;
> >>> pr_debug2("Using PERF_SAMPLE_READ / :S modifier is not compatible with inherit, falling back to no-inherit.\n");
> >>> return true;
> >>> + } else if (!perf_missing_features.aux_pause_resume &&
> >>> + (evsel->core.attr.aux_pause || evsel->core.attr.aux_resume ||
> >>> + evsel->core.attr.aux_start_paused)) {
> >>> + perf_missing_features.aux_pause_resume = true;
> >>> + pr_debug2_peo("Kernel has no aux_pause/aux_resume support, bailing out\n");
> >>> + return false;
> >>
> >> This patch fails to apply on the latest perf-tools-next branch due to
> >> conflict:
> >>
> >> https://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next.git
> >> branch: perf-tools-next
> >>
> >> You might need to rebase it on the latest code base.
> >
> > Yep, please do for the tooling patches.
>
> I'd noticed that, but there is more work to sort it out.
> The probing simply won't work when there are dependencies
> on other events, or other attr members. But there is no
> point in trying to "fallback" in that case either. It is
> just a failure, but what *is* still needed is a sensible
> error message.
Do you need to probe with two or more events? I guess we can extend
evsel__detect_missing_pmu_features to check more complicated setups.
For now, it only checks exclude_guest attribute.
>
> The other patches, including the ones that come after,
> still apply by the way, or they did the other day, so
> they could be applied anyway.
Do you want me to process the series without this patch? I think
this is needed to support old kernels and I'd like to have it together.
Would be hard for you to update this change in the current form and work
on improving it later?
Thanks,
Namhyung
Improve format of config terms and section references.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
---
tools/perf/Documentation/perf-intel-pt.txt | 486 +++++++++++----------
1 file changed, 267 insertions(+), 219 deletions(-)
diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt
index 59ab1ff9d75f..ad39bf20f862 100644
--- a/tools/perf/Documentation/perf-intel-pt.txt
+++ b/tools/perf/Documentation/perf-intel-pt.txt
@@ -151,7 +151,7 @@ displayed as follows:
There are two ways that instructions-per-cycle (IPC) can be calculated depending
on the recording.
-If the 'cyc' config term (see config terms section below) was used, then IPC
+If the 'cyc' config term (see <<_config_terms,config terms>> section below) was used, then IPC
and cycle events are calculated using the cycle count from CYC packets, otherwise
MTC packets are used - refer to the 'mtc' config term. When MTC is used, however,
the values are less accurate because the timing is less accurate.
@@ -239,7 +239,7 @@ which is the same as
-e intel_pt/tsc=1,noretcomp=0/
-Note there are now new config terms - see section 'config terms' further below.
+Note there are other config terms - see section <<_config_terms,config terms>> further below.
The config terms are listed in /sys/devices/intel_pt/format. They are bit
fields within the config member of the struct perf_event_attr which is
@@ -311,217 +311,264 @@ perf_event_attr is displayed if the -vv option is used e.g.
config terms
~~~~~~~~~~~~
-The June 2015 version of Intel 64 and IA-32 Architectures Software Developer
-Manuals, Chapter 36 Intel Processor Trace, defined new Intel PT features.
-Some of the features are reflect in new config terms. All the config terms are
-described below.
-
-tsc Always supported. Produces TSC timestamp packets to provide
- timing information. In some cases it is possible to decode
- without timing information, for example a per-thread context
- that does not overlap executable memory maps.
-
- The default config selects tsc (i.e. tsc=1).
-
-noretcomp Always supported. Disables "return compression" so a TIP packet
- is produced when a function returns. Causes more packets to be
- produced but might make decoding more reliable.
-
- The default config does not select noretcomp (i.e. noretcomp=0).
-
-psb_period Allows the frequency of PSB packets to be specified.
-
- The PSB packet is a synchronization packet that provides a
- starting point for decoding or recovery from errors.
-
- Support for psb_period is indicated by:
-
- /sys/bus/event_source/devices/intel_pt/caps/psb_cyc
-
- which contains "1" if the feature is supported and "0"
- otherwise.
-
- Valid values are given by:
-
- /sys/bus/event_source/devices/intel_pt/caps/psb_periods
-
- which contains a hexadecimal value, the bits of which represent
- valid values e.g. bit 2 set means value 2 is valid.
-
- The psb_period value is converted to the approximate number of
- trace bytes between PSB packets as:
-
- 2 ^ (value + 11)
-
- e.g. value 3 means 16KiB bytes between PSBs
-
- If an invalid value is entered, the error message
- will give a list of valid values e.g.
-
- $ perf record -e intel_pt/psb_period=15/u uname
- Invalid psb_period for intel_pt. Valid values are: 0-5
-
- If MTC packets are selected, the default config selects a value
- of 3 (i.e. psb_period=3) or the nearest lower value that is
- supported (0 is always supported). Otherwise the default is 0.
-
- If decoding is expected to be reliable and the buffer is large
- then a large PSB period can be used.
-
- Because a TSC packet is produced with PSB, the PSB period can
- also affect the granularity to timing information in the absence
- of MTC or CYC.
-
-mtc Produces MTC timing packets.
-
- MTC packets provide finer grain timestamp information than TSC
- packets. MTC packets record time using the hardware crystal
- clock (CTC) which is related to TSC packets using a TMA packet.
-
- Support for this feature is indicated by:
-
- /sys/bus/event_source/devices/intel_pt/caps/mtc
-
- which contains "1" if the feature is supported and
- "0" otherwise.
-
- The frequency of MTC packets can also be specified - see
- mtc_period below.
-
-mtc_period Specifies how frequently MTC packets are produced - see mtc
- above for how to determine if MTC packets are supported.
-
- Valid values are given by:
-
- /sys/bus/event_source/devices/intel_pt/caps/mtc_periods
-
- which contains a hexadecimal value, the bits of which represent
- valid values e.g. bit 2 set means value 2 is valid.
-
- The mtc_period value is converted to the MTC frequency as:
-
- CTC-frequency / (2 ^ value)
-
- e.g. value 3 means one eighth of CTC-frequency
-
- Where CTC is the hardware crystal clock, the frequency of which
- can be related to TSC via values provided in cpuid leaf 0x15.
-
- If an invalid value is entered, the error message
- will give a list of valid values e.g.
-
- $ perf record -e intel_pt/mtc_period=15/u uname
- Invalid mtc_period for intel_pt. Valid values are: 0,3,6,9
-
- The default value is 3 or the nearest lower value
- that is supported (0 is always supported).
-
-cyc Produces CYC timing packets.
-
- CYC packets provide even finer grain timestamp information than
- MTC and TSC packets. A CYC packet contains the number of CPU
- cycles since the last CYC packet. Unlike MTC and TSC packets,
- CYC packets are only sent when another packet is also sent.
-
- Support for this feature is indicated by:
-
- /sys/bus/event_source/devices/intel_pt/caps/psb_cyc
-
- which contains "1" if the feature is supported and
- "0" otherwise.
-
- The number of CYC packets produced can be reduced by specifying
- a threshold - see cyc_thresh below.
-
-cyc_thresh Specifies how frequently CYC packets are produced - see cyc
- above for how to determine if CYC packets are supported.
-
- Valid cyc_thresh values are given by:
-
- /sys/bus/event_source/devices/intel_pt/caps/cycle_thresholds
-
- which contains a hexadecimal value, the bits of which represent
- valid values e.g. bit 2 set means value 2 is valid.
-
- The cyc_thresh value represents the minimum number of CPU cycles
- that must have passed before a CYC packet can be sent. The
- number of CPU cycles is:
-
- 2 ^ (value - 1)
-
- e.g. value 4 means 8 CPU cycles must pass before a CYC packet
- can be sent. Note a CYC packet is still only sent when another
- packet is sent, not at, e.g. every 8 CPU cycles.
-
- If an invalid value is entered, the error message
- will give a list of valid values e.g.
-
- $ perf record -e intel_pt/cyc,cyc_thresh=15/u uname
- Invalid cyc_thresh for intel_pt. Valid values are: 0-12
-
- CYC packets are not requested by default.
-
-pt Specifies pass-through which enables the 'branch' config term.
-
- The default config selects 'pt' if it is available, so a user will
- never need to specify this term.
-
-branch Enable branch tracing. Branch tracing is enabled by default so to
- disable branch tracing use 'branch=0'.
-
- The default config selects 'branch' if it is available.
-
-ptw Enable PTWRITE packets which are produced when a ptwrite instruction
- is executed.
-
- Support for this feature is indicated by:
-
- /sys/bus/event_source/devices/intel_pt/caps/ptwrite
-
- which contains "1" if the feature is supported and
- "0" otherwise.
-
- As an alternative, refer to "Emulated PTWRITE" further below.
-
-fup_on_ptw Enable a FUP packet to follow the PTWRITE packet. The FUP packet
- provides the address of the ptwrite instruction. In the absence of
- fup_on_ptw, the decoder will use the address of the previous branch
- if branch tracing is enabled, otherwise the address will be zero.
- Note that fup_on_ptw will work even when branch tracing is disabled.
-
-pwr_evt Enable power events. The power events provide information about
- changes to the CPU C-state.
-
- Support for this feature is indicated by:
-
- /sys/bus/event_source/devices/intel_pt/caps/power_event_trace
-
- which contains "1" if the feature is supported and
- "0" otherwise.
-
-event Enable Event Trace. The events provide information about asynchronous
- events.
-
- Support for this feature is indicated by:
-
- /sys/bus/event_source/devices/intel_pt/caps/event_trace
-
- which contains "1" if the feature is supported and
- "0" otherwise.
-
-notnt Disable TNT packets. Without TNT packets, it is not possible to walk
- executable code to reconstruct control flow, however FUP, TIP, TIP.PGE
- and TIP.PGD packets still indicate asynchronous control flow, and (if
- return compression is disabled - see noretcomp) return statements.
- The advantage of eliminating TNT packets is reducing the size of the
- trace and corresponding tracing overhead.
-
- Support for this feature is indicated by:
-
- /sys/bus/event_source/devices/intel_pt/caps/tnt_disable
-
- which contains "1" if the feature is supported and
- "0" otherwise.
+Config terms are parameters specified with the -e intel_pt// event option,
+for example:
+
+ -e intel_pt/cyc/
+
+which selects cycle accurate mode. Each config term can have a value which
+defaults to 1, so the above is the same as:
+
+ -e intel_pt/cyc=1/
+
+Some terms are set by default, so must be set to 0 to turn them off. For
+example, to turn off branch tracing:
+
+ -e intel_pt/branch=0/
+
+Multiple config terms are separated by commas, for example:
+
+ -e intel_pt/cyc,mtc_period=9/
+
+There are also common config terms, see linkperf:perf-record[1] documentation.
+
+Intel PT config terms are described below.
+
+*tsc*::
+Always supported. Produces TSC timestamp packets to provide
+timing information. In some cases it is possible to decode
+without timing information, for example a per-thread context
+that does not overlap executable memory maps.
++
+The default config selects tsc (i.e. tsc=1).
+
+*noretcomp*::
+Always supported. Disables "return compression" so a TIP packet
+is produced when a function returns. Causes more packets to be
+produced but might make decoding more reliable.
++
+The default config does not select noretcomp (i.e. noretcomp=0).
+
+*psb_period*::
+Allows the frequency of PSB packets to be specified.
++
+The PSB packet is a synchronization packet that provides a
+starting point for decoding or recovery from errors.
++
+Support for psb_period is indicated by:
++
+ /sys/bus/event_source/devices/intel_pt/caps/psb_cyc
++
+which contains "1" if the feature is supported and "0"
+otherwise.
++
+Valid values are given by:
++
+ /sys/bus/event_source/devices/intel_pt/caps/psb_periods
++
+which contains a hexadecimal value, the bits of which represent
+valid values e.g. bit 2 set means value 2 is valid.
++
+The psb_period value is converted to the approximate number of
+trace bytes between PSB packets as:
++
+ 2 ^ (value + 11)
++
+e.g. value 3 means 16KiB bytes between PSBs
++
+If an invalid value is entered, the error message
+will give a list of valid values e.g.
++
+ $ perf record -e intel_pt/psb_period=15/u uname
+ Invalid psb_period for intel_pt. Valid values are: 0-5
++
+If MTC packets are selected, the default config selects a value
+of 3 (i.e. psb_period=3) or the nearest lower value that is
+supported (0 is always supported). Otherwise the default is 0.
++
+If decoding is expected to be reliable and the buffer is large
+then a large PSB period can be used.
++
+Because a TSC packet is produced with PSB, the PSB period can
+also affect the granularity to timing information in the absence
+of MTC or CYC.
+
+*mtc*::
+Produces MTC timing packets.
++
+MTC packets provide finer grain timestamp information than TSC
+packets. MTC packets record time using the hardware crystal
+clock (CTC) which is related to TSC packets using a TMA packet.
++
+Support for this feature is indicated by:
++
+ /sys/bus/event_source/devices/intel_pt/caps/mtc
++
+which contains "1" if the feature is supported and
+"0" otherwise.
++
+The frequency of MTC packets can also be specified - see
+mtc_period below.
+
+*mtc_period*::
+Specifies how frequently MTC packets are produced - see mtc
+above for how to determine if MTC packets are supported.
++
+Valid values are given by:
++
+ /sys/bus/event_source/devices/intel_pt/caps/mtc_periods
++
+which contains a hexadecimal value, the bits of which represent
+valid values e.g. bit 2 set means value 2 is valid.
++
+The mtc_period value is converted to the MTC frequency as:
+
+ CTC-frequency / (2 ^ value)
++
+e.g. value 3 means one eighth of CTC-frequency
++
+Where CTC is the hardware crystal clock, the frequency of which
+can be related to TSC via values provided in cpuid leaf 0x15.
++
+If an invalid value is entered, the error message
+will give a list of valid values e.g.
++
+ $ perf record -e intel_pt/mtc_period=15/u uname
+ Invalid mtc_period for intel_pt. Valid values are: 0,3,6,9
++
+The default value is 3 or the nearest lower value
+that is supported (0 is always supported).
+
+*cyc*::
+Produces CYC timing packets.
++
+CYC packets provide even finer grain timestamp information than
+MTC and TSC packets. A CYC packet contains the number of CPU
+cycles since the last CYC packet. Unlike MTC and TSC packets,
+CYC packets are only sent when another packet is also sent.
++
+Support for this feature is indicated by:
++
+ /sys/bus/event_source/devices/intel_pt/caps/psb_cyc
++
+which contains "1" if the feature is supported and
+"0" otherwise.
++
+The number of CYC packets produced can be reduced by specifying
+a threshold - see cyc_thresh below.
+
+*cyc_thresh*::
+Specifies how frequently CYC packets are produced - see cyc
+above for how to determine if CYC packets are supported.
++
+Valid cyc_thresh values are given by:
++
+ /sys/bus/event_source/devices/intel_pt/caps/cycle_thresholds
++
+which contains a hexadecimal value, the bits of which represent
+valid values e.g. bit 2 set means value 2 is valid.
++
+The cyc_thresh value represents the minimum number of CPU cycles
+that must have passed before a CYC packet can be sent. The
+number of CPU cycles is:
++
+ 2 ^ (value - 1)
++
+e.g. value 4 means 8 CPU cycles must pass before a CYC packet
+can be sent. Note a CYC packet is still only sent when another
+packet is sent, not at, e.g. every 8 CPU cycles.
++
+If an invalid value is entered, the error message
+will give a list of valid values e.g.
++
+ $ perf record -e intel_pt/cyc,cyc_thresh=15/u uname
+ Invalid cyc_thresh for intel_pt. Valid values are: 0-12
++
+CYC packets are not requested by default.
+
+*pt*::
+Specifies pass-through which enables the 'branch' config term.
++
+The default config selects 'pt' if it is available, so a user will
+never need to specify this term.
+
+*branch*::
+Enable branch tracing. Branch tracing is enabled by default so to
+disable branch tracing use 'branch=0'.
++
+The default config selects 'branch' if it is available.
+
+*ptw*::
+Enable PTWRITE packets which are produced when a ptwrite instruction
+is executed.
++
+Support for this feature is indicated by:
++
+ /sys/bus/event_source/devices/intel_pt/caps/ptwrite
++
+which contains "1" if the feature is supported and
+"0" otherwise.
++
+As an alternative, refer to "Emulated PTWRITE" further below.
+
+*fup_on_ptw*::
+Enable a FUP packet to follow the PTWRITE packet. The FUP packet
+provides the address of the ptwrite instruction. In the absence of
+fup_on_ptw, the decoder will use the address of the previous branch
+if branch tracing is enabled, otherwise the address will be zero.
+Note that fup_on_ptw will work even when branch tracing is disabled.
+
+*pwr_evt*::
+Enable power events. The power events provide information about
+changes to the CPU C-state.
++
+Support for this feature is indicated by:
++
+ /sys/bus/event_source/devices/intel_pt/caps/power_event_trace
++
+which contains "1" if the feature is supported and
+"0" otherwise.
+
+*event*::
+Enable Event Trace. The events provide information about asynchronous
+events.
++
+Support for this feature is indicated by:
++
+ /sys/bus/event_source/devices/intel_pt/caps/event_trace
++
+which contains "1" if the feature is supported and
+"0" otherwise.
+
+*notnt*::
+Disable TNT packets. Without TNT packets, it is not possible to walk
+executable code to reconstruct control flow, however FUP, TIP, TIP.PGE
+and TIP.PGD packets still indicate asynchronous control flow, and (if
+return compression is disabled - see noretcomp) return statements.
+The advantage of eliminating TNT packets is reducing the size of the
+trace and corresponding tracing overhead.
++
+Support for this feature is indicated by:
++
+ /sys/bus/event_source/devices/intel_pt/caps/tnt_disable
++
+which contains "1" if the feature is supported and
+"0" otherwise.
+
+
+config terms on other events
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Some Intel PT features work with other events, features such as AUX area sampling
+and PEBS-via-PT. In those cases, the other events can have config terms below:
+
+*aux-sample-size*::
+ Used to set the AUX area sample size, refer to the section
+ <<_aux_area_sampling_option,AUX area sampling option>>
+
+*aux-output*::
+ Used to select PEBS-via-PT, refer to the
+ section <<_pebs_via_intel_pt,PEBS via Intel PT>>
AUX area sampling option
@@ -596,7 +643,8 @@ The default snapshot size is the auxtrace mmap size. If neither auxtrace mmap s
nor snapshot size is specified, then the default is 4MiB for privileged users
(or if /proc/sys/kernel/perf_event_paranoid < 0), 128KiB for unprivileged users.
If an unprivileged user does not specify mmap pages, the mmap pages will be
-reduced as described in the 'new auxtrace mmap size option' section below.
+reduced as described in the <<_new_auxtrace_mmap_size_option,new auxtrace mmap size option>>
+section below.
The snapshot size is displayed if the option -vv is used e.g.
@@ -952,11 +1000,11 @@ transaction start, commit or abort.
Note that "instructions", "cycles", "branches" and "transactions" events
depend on code flow packets which can be disabled by using the config term
-"branch=0". Refer to the config terms section above.
+"branch=0". Refer to the <<_config_terms,config terms>> section above.
"ptwrite" events record the payload of the ptwrite instruction and whether
"fup_on_ptw" was used. "ptwrite" events depend on PTWRITE packets which are
-recorded only if the "ptw" config term was used. Refer to the config terms
+recorded only if the "ptw" config term was used. Refer to the <<_config_terms,config terms>>
section above. perf script "synth" field displays "ptwrite" information like
this: "ip: 0 payload: 0x123456789abcdef0" where "ip" is 1 if "fup_on_ptw" was
used.
@@ -964,7 +1012,7 @@ used.
"Power" events correspond to power event packets and CBR (core-to-bus ratio)
packets. While CBR packets are always recorded when tracing is enabled, power
event packets are recorded only if the "pwr_evt" config term was used. Refer to
-the config terms section above. The power events record information about
+the <<_config_terms,config terms>> section above. The power events record information about
C-state changes, whereas CBR is indicative of CPU frequency. perf script
"event,synth" fields display information like this:
@@ -1120,7 +1168,7 @@ What *will* be decoded with the (single) q option:
- asynchronous branches such as interrupts
- indirect branches
- function return target address *if* the noretcomp config term (refer
- config terms section) was used
+ <<_config_terms,config terms>> section) was used
- start of (control-flow) tracing
- end of (control-flow) tracing, if it is not out of context
- power events, ptwrite, transaction start and abort
@@ -1133,7 +1181,7 @@ Repeating the q option (double-q i.e. qq) results in even faster decoding and ev
less detail. The decoder decodes only extended PSB (PSB+) packets, getting the
instruction pointer if there is a FUP packet within PSB+ (i.e. between PSB and
PSBEND). Note PSB packets occur regularly in the trace based on the psb_period
-config term (refer config terms section). There will be a FUP packet if the
+config term (refer <<_config_terms,config terms>> section). There will be a FUP packet if the
PSB+ occurs while control flow is being traced.
What will *not* be decoded with the qq option:
--
2.43.0Document the use of aux-action config term and provide a simple example.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
---
Changes in V5:
Added more examples
tools/perf/Documentation/perf-intel-pt.txt | 108 +++++++++++++++++++++
1 file changed, 108 insertions(+)
diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt
index ad39bf20f862..cc0f37f0fa5a 100644
--- a/tools/perf/Documentation/perf-intel-pt.txt
+++ b/tools/perf/Documentation/perf-intel-pt.txt
@@ -555,6 +555,9 @@ Support for this feature is indicated by:
which contains "1" if the feature is supported and
"0" otherwise.
+*aux-action=start-paused*::
+Start tracing paused, refer to the section <<_pause_or_resume_tracing,Pause or Resume Tracing>>
+
config terms on other events
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -570,6 +573,9 @@ and PEBS-via-PT. In those cases, the other events can have config terms below:
Used to select PEBS-via-PT, refer to the
section <<_pebs_via_intel_pt,PEBS via Intel PT>>
+*aux-action*::
+ Used to pause or resume tracing, refer to the section
+ <<_pause_or_resume_tracing,Pause or Resume Tracing>>
AUX area sampling option
~~~~~~~~~~~~~~~~~~~~~~~~
@@ -1915,6 +1921,108 @@ For pipe mode, the order of events and timestamps can presumably
be messed up.
+Pause or Resume Tracing
+-----------------------
+
+With newer Kernels, it is possible to use other selected events to pause
+or resume Intel PT tracing. This is configured by using the "aux-action"
+config term:
+
+"aux-action=pause" is used with events that are to pause Intel PT tracing.
+
+"aux-action=resume" is used with events that are to resume Intel PT tracing.
+
+"aux-action=start-paused" is used with the Intel PT event to start in a
+paused state.
+
+For example, to trace only the uname system call (sys_newuname) when running the
+command line utility uname:
+
+ $ perf record --kcore -e intel_pt/aux-action=start-paused/k,syscalls:sys_enter_newuname/aux-action=resume/,syscalls:sys_exit_newuname/aux-action=pause/ uname
+ Linux
+ [ perf record: Woken up 1 times to write data ]
+ [ perf record: Captured and wrote 0.043 MB perf.data ]
+ $ perf script --call-trace
+ uname 30805 [000] 24001.058782799: name: 0x7ffc9c1865b0
+ uname 30805 [000] 24001.058784424: psb offs: 0
+ uname 30805 [000] 24001.058784424: cbr: 39 freq: 3904 MHz (139%)
+ uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) debug_smp_processor_id
+ uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) __x64_sys_newuname
+ uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) down_read
+ uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) __cond_resched
+ uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) preempt_count_add
+ uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) in_lock_functions
+ uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) preempt_count_sub
+ uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) up_read
+ uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) preempt_count_add
+ uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) in_lock_functions
+ uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) preempt_count_sub
+ uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) _copy_to_user
+ uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) syscall_exit_to_user_mode
+ uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) syscall_exit_work
+ uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) perf_syscall_exit
+ uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) debug_smp_processor_id
+ uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_trace_buf_alloc
+ uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_swevent_get_recursion_context
+ uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) debug_smp_processor_id
+ uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) debug_smp_processor_id
+ uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_tp_event
+ uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_trace_buf_update
+ uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) tracing_gen_ctx_irq_test
+ uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_swevent_event
+ uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __perf_event_account_interrupt
+ uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __this_cpu_preempt_check
+ uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_event_output_forward
+ uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_event_aux_pause
+ uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) ring_buffer_get
+ uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __rcu_read_lock
+ uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __rcu_read_unlock
+ uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) pt_event_stop
+ uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) debug_smp_processor_id
+ uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) debug_smp_processor_id
+ uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) native_write_msr
+ uname 30805 [000] 24001.058785463: ([kernel.kallsyms]) native_write_msr
+ uname 30805 [000] 24001.058785639: 0x0
+
+The example above uses tracepoints, but any kind of sampled event can be used.
+
+For example:
+
+ Tracing between arch_cpu_idle_enter() and arch_cpu_idle_exit() using breakpoint events:
+
+ $ sudo cat /proc/kallsyms | sort | grep ' arch_cpu_idle_enter\| arch_cpu_idle_exit'
+ ffffffffb605bf60 T arch_cpu_idle_enter
+ ffffffffb614d8a0 W arch_cpu_idle_exit
+ $ sudo perf record --kcore -a -e intel_pt/aux-action=start-paused/k -e mem:0xffffffffb605bf60:x/aux-action=resume/ -e mem:0xffffffffb614d8a0:x/aux-action=pause/ -- sleep 1
+ [ perf record: Woken up 1 times to write data ]
+ [ perf record: Captured and wrote 1.387 MB perf.data ]
+
+ Tracing __alloc_pages() using kprobes:
+
+ $ sudo perf probe --add '__alloc_pages order'
+ Added new event: probe:__alloc_pages (on __alloc_pages with order)
+ $ sudo perf probe --add __alloc_pages%return
+ Added new event: probe:__alloc_pages__return (on __alloc_pages%return)
+ $ sudo perf record --kcore -aR -e intel_pt/aux-action=start-paused/k -e probe:__alloc_pages/aux-action=resume/ -e probe:__alloc_pages__return/aux-action=pause/ -- sleep 1
+ [ perf record: Woken up 1 times to write data ]
+ [ perf record: Captured and wrote 1.490 MB perf.data ]
+
+ Tracing starting at main() using a uprobe event:
+
+ $ sudo perf probe -x /usr/bin/uname main
+ Added new event: probe_uname:main (on main in /usr/bin/uname)
+ $ sudo perf record -e intel_pt/-aux-action=start-paused/u -e probe_uname:main/aux-action=resume/ -- uname
+ Linux
+ [ perf record: Woken up 1 times to write data ]
+ [ perf record: Captured and wrote 0.031 MB perf.data ]
+
+ Tracing occasionally using cycles events with different periods:
+
+ $ perf record --kcore -a -m,64M -e intel_pt/aux-action=start-paused/k -e cycles/aux-action=pause,period=1000000/Pk -e cycles/aux-action=resume,period=10500000/Pk -- firefox
+ [ perf record: Woken up 19 times to write data ]
+ [ perf record: Captured and wrote 16.561 MB perf.data ]
+
+
EXAMPLE
-------
--
2.43.0Add a simple sub-test to the "Miscellaneous Intel PT testing" test to
check pause / resume.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
---
tools/perf/tests/shell/test_intel_pt.sh | 28 +++++++++++++++++++++++++
1 file changed, 28 insertions(+)
diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh
index bf9017b812aa..bce579f4f447 100755
--- a/tools/perf/tests/shell/test_intel_pt.sh
+++ b/tools/perf/tests/shell/test_intel_pt.sh
@@ -644,6 +644,33 @@ test_pipe()
return 0
}
+test_pause_resume()
+{
+ echo "--- Test with pause / resume ---"
+ if ! perf_record_no_decode -o "${perfdatafile}" -e intel_pt/aux-action=start-paused/u uname ; then
+ echo "SKIP: pause / resume is not supported"
+ return 2
+ fi
+ if ! perf_record_no_bpf -o "${perfdatafile}" \
+ -e intel_pt/aux-action=start-paused/u \
+ -e instructions/period=50000,aux-action=resume,name=Resume/u \
+ -e instructions/period=100000,aux-action=pause,name=Pause/u uname ; then
+ echo "perf record with pause / resume failed"
+ return 1
+ fi
+ if ! perf script -i "${perfdatafile}" --itrace=b -Fperiod,event | \
+ awk 'BEGIN {paused=1;branches=0}
+ /Resume/ {paused=0}
+ /branches/ {if (paused) exit 1;branches=1}
+ /Pause/ {paused=1}
+ END {if (!branches) exit 1}' ; then
+ echo "perf record with pause / resume failed"
+ return 1
+ fi
+ echo OK
+ return 0
+}
+
count_result()
{
if [ "$1" -eq 2 ] ; then
@@ -672,6 +699,7 @@ test_power_event || ret=$? ; count_result $ret ; ret=0
test_no_tnt || ret=$? ; count_result $ret ; ret=0
test_event_trace || ret=$? ; count_result $ret ; ret=0
test_pipe || ret=$? ; count_result $ret ; ret=0
+test_pause_resume || ret=$? ; count_result $ret ; ret=0
cleanup
--
2.43.0© 2016 - 2024 Red Hat, Inc.