From: Ian Rogers <irogers@google.com>
To: namhyung@kernel.org
Cc: irogers@google.com, acme@kernel.org, adrian.hunter@intel.com,
ajones@ventanamicro.com, ak@linux.intel.com, alex@ghiti.fr,
alexander.shishkin@linux.intel.com, anup@brainfault.org,
aou@eecs.berkeley.edu, atrajeev@linux.ibm.com,
blakejones@google.com, ctshao@google.com,
dapeng1.mi@linux.intel.com, derek.foreman@collabora.com,
dvyukov@google.com, howardchu95@gmail.com,
hrishikesh123s@gmail.com, james.clark@linaro.org,
jolsa@kernel.org, krzysztof.m.lopatowski@gmail.com,
leo.yan@arm.com, linux-kernel@vger.kernel.org,
linux-perf-users@vger.kernel.org, linux@treblig.org,
mingo@redhat.com, nichen@iscas.ac.cn, palmer@dabbelt.com,
peterz@infradead.org, pjw@kernel.org, ravi.bangoria@amd.com,
swapnil.sapkal@amd.com, tanze@kylinos.cn,
thomas.falcon@intel.com, tianyou.li@intel.com,
yujie.liu@intel.com, zhouquan@iscas.ac.cn
Subject: [PATCH v4 01/25] perf sample: Document struct perf_sample
Date: Fri, 20 Mar 2026 12:26:03 -0700 [thread overview]
Message-ID: <20260320192627.368357-2-irogers@google.com> (raw)
In-Reply-To: <20260320192627.368357-1-irogers@google.com>
Add kernel-doc for struct perf_sample capturing the somewhat unusual
population of fields and lifetime relationships.
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/util/sample.h | 109 +++++++++++++++++++++++++++++++++++++--
1 file changed, 105 insertions(+), 4 deletions(-)
diff --git a/tools/perf/util/sample.h b/tools/perf/util/sample.h
index 3cce8dd202aa..8d4ace0e6594 100644
--- a/tools/perf/util/sample.h
+++ b/tools/perf/util/sample.h
@@ -81,47 +81,148 @@ struct simd_flags {
#define SIMD_OP_FLAGS_PRED_PARTIAL 0x01 /* partial predicate */
#define SIMD_OP_FLAGS_PRED_EMPTY 0x02 /* empty predicate */
+/**
+ * struct perf_sample
+ *
+ * A sample is generally filled in by evlist__parse_sample/evsel__parse_sample
+ * which fills in the variables from a "union perf_event *event" which is data
+ * from a perf ring buffer or perf.data file. The "event" sample is variable in
+ * length as determined by the perf_event_attr (in the evsel) and details within
+ * the sample event itself. A struct perf_sample avoids needing to care about
+ * the variable length nature of the original event.
+ *
+ * To avoid being excessively large parts of the struct perf_sample are pointers
+ * into the original sample event. In general the lifetime of a struct
+ * perf_sample needs to be less than the "union perf_event *event" it was
+ * derived from.
+ *
+ * The struct regs_dump user_regs and intr_regs are lazily allocated again for
+ * size reasons, due to them holding a cache of looked up registers. The
+ * function pair of perf_sample__init and perf_sample__exit correctly initialize
+ * and clean up these values.
+ */
struct perf_sample {
+ /** @ip: The sample event PERF_SAMPLE_IP value. */
u64 ip;
- u32 pid, tid;
+ /** @pid: The sample event PERF_SAMPLE_TID pid value. */
+ u32 pid;
+ /** @tid: The sample event PERF_SAMPLE_TID tid value. */
+ u32 tid;
+ /** @time: The sample event PERF_SAMPLE_TIME value. */
u64 time;
+ /** @addr: The sample event PERF_SAMPLE_ADDR value. */
u64 addr;
+ /** @id: The sample event PERF_SAMPLE_ID value. */
u64 id;
+ /** @stream_id: The sample event PERF_SAMPLE_STREAM_ID value. */
u64 stream_id;
+ /** @period: The sample event PERF_SAMPLE_PERIOD value. */
u64 period;
+ /** @weight: Data determined by PERF_SAMPLE_WEIGHT or PERF_SAMPLE_WEIGHT_STRUCT. */
u64 weight;
+ /** @transaction: The sample event PERF_SAMPLE_TRANSACTION value. */
u64 transaction;
+ /** @insn_cnt: Filled in and used by intel-pt. */
u64 insn_cnt;
+ /** @cyc_cnt: Filled in and used by intel-pt. */
u64 cyc_cnt;
+ /** @cpu: The sample event PERF_SAMPLE_CPU value. */
u32 cpu;
+ /**
+ * @raw_size: The size in bytes of raw data from PERF_SAMPLE_RAW. For
+ * alignment reasons this should always be sizeof(u32)
+ * followed by a multiple of sizeof(u64).
+ */
u32 raw_size;
+ /** @data_src: The sample event PERF_SAMPLE_DATA_SRC value. */
u64 data_src;
+ /** @phys_addr: The sample event PERF_SAMPLE_PHYS_ADDR value. */
u64 phys_addr;
+ /** @data_page_size: The sample event PERF_SAMPLE_DATA_PAGE_SIZE value. */
u64 data_page_size;
+ /** @code_page_size: The sample event PERF_SAMPLE_CODE_PAGE_SIZE value. */
u64 code_page_size;
+ /** @cgroup: The sample event PERF_SAMPLE_CGROUP value. */
u64 cgroup;
+ /** @flags: Extra flag data from auxiliary events like intel-pt. */
u32 flags;
+ /** @machine_pid: The guest machine pid derived from the sample id. */
u32 machine_pid;
+ /** @vcpu: The guest machine vcpu derived from the sample id. */
u32 vcpu;
+ /**
+ * @insn_len: Instruction length from auxiliary events like
+ * intel-pt. The instruction itself is held in insn.
+ */
u16 insn_len;
+ /**
+ * @cpumode: The cpumode from struct perf_event_header misc variable
+ * masked with CPUMODE_MASK. Gives user, kernel and hypervisor
+ * information.
+ */
u8 cpumode;
+ /** @misc: The entire struct perf_event_header misc variable. */
u16 misc;
+ /**
+ * @ins_lat: Instruction latency information from weight2 in
+ * PERF_SAMPLE_WEIGHT_STRUCT or auxiliary events like
+ * intel-pt.
+ */
u16 ins_lat;
- /** @weight3: On x86 holds retire_lat, on powerpc holds p_stage_cyc. */
+ /**
+ * @weight3: From PERF_SAMPLE_WEIGHT_STRUCT. On x86 holds retire_lat, on
+ * powerpc holds p_stage_cyc.
+ */
u16 weight3;
- bool no_hw_idx; /* No hw_idx collected in branch_stack */
- bool deferred_callchain; /* Has deferred user callchains */
+ /**
+ * @no_hw_idx: For PERF_SAMPLE_BRANCH_STACK, true when
+ * PERF_SAMPLE_BRANCH_HW_INDEX isn't set.
+ */
+ bool no_hw_idx;
+ /**
+ * @deferred_callchain: When processing PERF_SAMPLE_CALLCHAIN a deferred
+ * user callchain marker was encountered.
+ */
+ bool deferred_callchain;
+ /**
+ * @deferred_cookie: Identifier of the deferred callchain in the later
+ * PERF_RECORD_CALLCHAIN_DEFERRED event.
+ */
u64 deferred_cookie;
+ /** @insn: A copy of the sampled instruction filled in by perf_sample__fetch_insn. */
char insn[MAX_INSN];
+ /** @raw_data: Pointer into the original event for PERF_SAMPLE_RAW data. */
void *raw_data;
+ /**
+ * @callchain: Pointer into the original event for PERF_SAMPLE_CALLCHAIN
+ * data. For deferred callchains this may be a copy that
+ * needs freeing, see sample__merge_deferred_callchain.
+ */
struct ip_callchain *callchain;
+ /** @branch_stack: Pointer into the original event for PERF_SAMPLE_BRANCH_STACK data. */
struct branch_stack *branch_stack;
+ /**
+ * @branch_stack_cntr: Pointer into the original event for
+ * PERF_SAMPLE_BRANCH_COUNTERS data.
+ */
u64 *branch_stack_cntr;
+ /** @user_regs: Values and pointers into the sample for PERF_SAMPLE_REGS_USER. */
struct regs_dump *user_regs;
+ /** @intr_regs: Values and pointers into the sample for PERF_SAMPLE_REGS_INTR. */
struct regs_dump *intr_regs;
+ /** @user_stack: Size and pointer into the sample for PERF_SAMPLE_STACK_USER. */
struct stack_dump user_stack;
+ /**
+ * @read: The sample event PERF_SAMPLE_READ counter values. The valid
+ * values depend on the attr.read_format PERF_FORMAT_ values.
+ */
struct sample_read read;
+ /**
+ * @aux_sample: Similar to raw data but with a 64-bit size and
+ * alignment, PERF_SAMPLE_AUX data.
+ */
struct aux_sample aux_sample;
+ /** @simd_flags: SIMD flag information from ARM SPE auxiliary events. */
struct simd_flags simd_flags;
};
--
2.53.0.959.g497ff81fa9-goog
next prev parent reply other threads:[~2026-03-20 19:28 UTC|newest]
Thread overview: 112+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-02-09 17:40 [PATCH v1 00/25] perf tool: Add evsel to perf_sample Ian Rogers
2026-02-09 17:40 ` [PATCH v1 01/25] perf sample: Document struct perf_sample Ian Rogers
2026-03-03 3:07 ` Namhyung Kim
2026-03-20 4:41 ` Ian Rogers
2026-02-09 17:40 ` [PATCH v1 02/25] perf sample: Make sure perf_sample__init/exit are used Ian Rogers
2026-03-03 22:38 ` Namhyung Kim
2026-02-09 17:40 ` [PATCH v1 03/25] perf sample: Add evsel to struct perf_sample Ian Rogers
2026-02-09 17:40 ` [PATCH v1 04/25] perf tool: Remove evsel from tool APIs that pass the sample Ian Rogers
2026-02-09 17:40 ` [PATCH v1 05/25] perf kvm: Don't pass evsel with sample Ian Rogers
2026-02-09 17:40 ` [PATCH v1 06/25] perf evsel: Refactor evsel__intval to perf_sample__intval Ian Rogers
2026-02-09 17:40 ` [PATCH v1 07/25] perf trace: Don't pass evsel with sample Ian Rogers
2026-02-09 17:40 ` [PATCH v1 08/25] perf callchain: Don't pass evsel and sample Ian Rogers
2026-02-09 17:40 ` [PATCH v1 09/25] perf lock: Only pass sample to handlers Ian Rogers
2026-02-09 17:40 ` [PATCH v1 10/25] perf lock: Constify trace_lock_handler variables Ian Rogers
2026-02-09 17:40 ` [PATCH v1 11/25] perf hist: Remove evsel parameter from inc samples functions Ian Rogers
2026-02-09 17:40 ` [PATCH v1 12/25] perf db-export: Remove evsel from struct export_sample Ian Rogers
2026-02-09 17:40 ` [PATCH v1 13/25] perf hist: Remove evsel from struct hist_entry_iter Ian Rogers
2026-02-09 17:40 ` [PATCH v1 14/25] perf report: Directly use sample->evsel to avoid computing from sample->id Ian Rogers
2026-02-09 17:40 ` [PATCH v1 15/25] perf annotate: Don't pass evsel to add_sample Ian Rogers
2026-02-09 17:40 ` [PATCH v1 16/25] perf inject: Don't pass evsel with sample Ian Rogers
2026-02-09 17:40 ` [PATCH v1 17/25] perf kmem: " Ian Rogers
2026-02-09 17:40 ` [PATCH v1 18/25] perf kwork: " Ian Rogers
2026-02-09 17:40 ` [PATCH v1 19/25] perf sched: " Ian Rogers
2026-02-09 17:40 ` [PATCH v1 20/25] perf timechart: " Ian Rogers
2026-02-09 17:40 ` [PATCH v1 21/25] perf trace: " Ian Rogers
2026-02-09 17:40 ` [PATCH v1 22/25] perf evlist: Try to avoid computing evsel from sample Ian Rogers
2026-02-09 17:40 ` [PATCH v1 23/25] perf script: Don't pass evsel with sample Ian Rogers
2026-02-09 17:40 ` [PATCH v1 24/25] perf s390-sample-raw: " Ian Rogers
2026-02-09 17:40 ` [PATCH v1 25/25] perf evsel: " Ian Rogers
2026-02-23 19:15 ` [PATCH v1 00/25] perf tool: Add evsel to perf_sample Ian Rogers
2026-03-02 17:56 ` Ian Rogers
2026-03-03 1:15 ` Namhyung Kim
2026-03-04 1:02 ` Namhyung Kim
2026-03-04 16:19 ` Ian Rogers
2026-03-19 23:23 ` [PATCH v2 " Ian Rogers
2026-03-19 23:23 ` [PATCH v2 01/25] perf sample: Document struct perf_sample Ian Rogers
2026-03-19 23:23 ` [PATCH v2 02/25] perf sample: Make sure perf_sample__init/exit are used Ian Rogers
2026-03-19 23:23 ` [PATCH v2 03/25] perf sample: Add evsel to struct perf_sample Ian Rogers
2026-03-19 23:23 ` [PATCH v2 04/25] perf tool: Remove evsel from tool APIs that pass the sample Ian Rogers
2026-03-19 23:23 ` [PATCH v2 05/25] perf kvm: Don't pass evsel with sample Ian Rogers
2026-03-19 23:23 ` [PATCH v2 06/25] perf evsel: Refactor evsel__intval to perf_sample__intval Ian Rogers
2026-03-19 23:23 ` [PATCH v2 07/25] perf trace: Don't pass evsel with sample Ian Rogers
2026-03-19 23:23 ` [PATCH v2 08/25] perf callchain: Don't pass evsel and sample Ian Rogers
2026-03-19 23:23 ` [PATCH v2 09/25] perf lock: Only pass sample to handlers Ian Rogers
2026-03-19 23:23 ` [PATCH v2 10/25] perf lock: Constify trace_lock_handler variables Ian Rogers
2026-03-19 23:23 ` [PATCH v2 11/25] perf hist: Remove evsel parameter from inc samples functions Ian Rogers
2026-03-19 23:23 ` [PATCH v2 12/25] perf db-export: Remove evsel from struct export_sample Ian Rogers
2026-03-19 23:23 ` [PATCH v2 13/25] perf hist: Remove evsel from struct hist_entry_iter Ian Rogers
2026-03-19 23:23 ` [PATCH v2 14/25] perf report: Directly use sample->evsel to avoid computing from sample->id Ian Rogers
2026-03-19 23:23 ` [PATCH v2 15/25] perf annotate: Don't pass evsel to add_sample Ian Rogers
2026-03-19 23:23 ` [PATCH v2 16/25] perf inject: Don't pass evsel with sample Ian Rogers
2026-03-19 23:23 ` [PATCH v2 17/25] perf kmem: " Ian Rogers
2026-03-19 23:23 ` [PATCH v2 18/25] perf kwork: " Ian Rogers
2026-03-19 23:23 ` [PATCH v2 19/25] perf sched: " Ian Rogers
2026-03-19 23:23 ` [PATCH v2 20/25] perf timechart: " Ian Rogers
2026-03-19 23:23 ` [PATCH v2 21/25] perf trace: " Ian Rogers
2026-03-19 23:23 ` [PATCH v2 22/25] perf evlist: Try to avoid computing evsel from sample Ian Rogers
2026-03-19 23:23 ` [PATCH v2 23/25] perf script: Don't pass evsel with sample Ian Rogers
2026-03-19 23:23 ` [PATCH v2 24/25] perf s390-sample-raw: " Ian Rogers
2026-03-19 23:23 ` [PATCH v2 25/25] perf evsel: " Ian Rogers
2026-03-20 8:08 ` [PATCH v3 00/25] perf tool: Add evsel to perf_sample Ian Rogers
2026-03-20 8:08 ` [PATCH v3 01/25] perf sample: Document struct perf_sample Ian Rogers
2026-03-20 8:08 ` [PATCH v3 02/25] perf sample: Make sure perf_sample__init/exit are used Ian Rogers
2026-03-20 8:08 ` [PATCH v3 03/25] perf sample: Add evsel to struct perf_sample Ian Rogers
2026-03-20 8:08 ` [PATCH v3 04/25] perf tool: Remove evsel from tool APIs that pass the sample Ian Rogers
2026-03-20 8:08 ` [PATCH v3 05/25] perf kvm: Don't pass evsel with sample Ian Rogers
2026-03-20 8:08 ` [PATCH v3 06/25] perf evsel: Refactor evsel__intval to perf_sample__intval Ian Rogers
2026-03-20 8:08 ` [PATCH v3 07/25] perf trace: Don't pass evsel with sample Ian Rogers
2026-03-20 8:08 ` [PATCH v3 08/25] perf callchain: Don't pass evsel and sample Ian Rogers
2026-03-20 8:08 ` [PATCH v3 09/25] perf lock: Only pass sample to handlers Ian Rogers
2026-03-20 8:08 ` [PATCH v3 10/25] perf lock: Constify trace_lock_handler variables Ian Rogers
2026-03-20 8:08 ` [PATCH v3 11/25] perf hist: Remove evsel parameter from inc samples functions Ian Rogers
2026-03-20 8:08 ` [PATCH v3 12/25] perf db-export: Remove evsel from struct export_sample Ian Rogers
2026-03-20 8:08 ` [PATCH v3 13/25] perf hist: Remove evsel from struct hist_entry_iter Ian Rogers
2026-03-20 8:08 ` [PATCH v3 14/25] perf report: Directly use sample->evsel to avoid computing from sample->id Ian Rogers
2026-03-20 8:08 ` [PATCH v3 15/25] perf annotate: Don't pass evsel to add_sample Ian Rogers
2026-03-20 8:08 ` [PATCH v3 16/25] perf inject: Don't pass evsel with sample Ian Rogers
2026-03-20 8:08 ` [PATCH v3 17/25] perf kmem: " Ian Rogers
2026-03-20 8:08 ` [PATCH v3 18/25] perf kwork: " Ian Rogers
2026-03-20 8:08 ` [PATCH v3 19/25] perf sched: " Ian Rogers
2026-03-20 8:08 ` [PATCH v3 20/25] perf timechart: " Ian Rogers
2026-03-20 8:08 ` [PATCH v3 21/25] perf trace: " Ian Rogers
2026-03-20 8:08 ` [PATCH v3 22/25] perf evlist: Try to avoid computing evsel from sample Ian Rogers
2026-03-20 8:08 ` [PATCH v3 23/25] perf script: Don't pass evsel with sample Ian Rogers
2026-03-20 8:08 ` [PATCH v3 24/25] perf s390-sample-raw: " Ian Rogers
2026-03-20 8:08 ` [PATCH v3 25/25] perf evsel: " Ian Rogers
2026-03-20 19:26 ` [PATCH v4 00/25] perf tool: Add evsel to perf_sample Ian Rogers
2026-03-20 19:26 ` Ian Rogers [this message]
2026-03-20 19:26 ` [PATCH v4 02/25] perf sample: Make sure perf_sample__init/exit are used Ian Rogers
2026-03-20 19:26 ` [PATCH v4 03/25] perf sample: Add evsel to struct perf_sample Ian Rogers
2026-03-20 19:26 ` [PATCH v4 04/25] perf tool: Remove evsel from tool APIs that pass the sample Ian Rogers
2026-03-20 19:26 ` [PATCH v4 05/25] perf kvm: Don't pass evsel with sample Ian Rogers
2026-03-20 19:26 ` [PATCH v4 06/25] perf evsel: Refactor evsel__intval to perf_sample__intval Ian Rogers
2026-03-20 19:26 ` [PATCH v4 07/25] perf trace: Don't pass evsel with sample Ian Rogers
2026-03-20 19:26 ` [PATCH v4 08/25] perf callchain: Don't pass evsel and sample Ian Rogers
2026-03-20 19:26 ` [PATCH v4 09/25] perf lock: Only pass sample to handlers Ian Rogers
2026-03-20 19:26 ` [PATCH v4 10/25] perf lock: Constify trace_lock_handler variables Ian Rogers
2026-03-20 19:26 ` [PATCH v4 11/25] perf hist: Remove evsel parameter from inc samples functions Ian Rogers
2026-03-20 19:26 ` [PATCH v4 12/25] perf db-export: Remove evsel from struct export_sample Ian Rogers
2026-03-20 19:26 ` [PATCH v4 13/25] perf hist: Remove evsel from struct hist_entry_iter Ian Rogers
2026-03-20 19:26 ` [PATCH v4 14/25] perf report: Directly use sample->evsel to avoid computing from sample->id Ian Rogers
2026-03-20 19:26 ` [PATCH v4 15/25] perf annotate: Don't pass evsel to add_sample Ian Rogers
2026-03-20 19:26 ` [PATCH v4 16/25] perf inject: Don't pass evsel with sample Ian Rogers
2026-03-20 19:26 ` [PATCH v4 17/25] perf kmem: " Ian Rogers
2026-03-20 19:26 ` [PATCH v4 18/25] perf kwork: " Ian Rogers
2026-03-20 19:26 ` [PATCH v4 19/25] perf sched: " Ian Rogers
2026-03-20 19:26 ` [PATCH v4 20/25] perf timechart: " Ian Rogers
2026-03-20 19:26 ` [PATCH v4 21/25] perf trace: " Ian Rogers
2026-03-20 19:26 ` [PATCH v4 22/25] perf evlist: Try to avoid computing evsel from sample Ian Rogers
2026-03-20 19:26 ` [PATCH v4 23/25] perf script: Don't pass evsel with sample Ian Rogers
2026-03-20 19:26 ` [PATCH v4 24/25] perf s390-sample-raw: Don't pass evsel or its PMU " Ian Rogers
2026-03-20 19:26 ` [PATCH v4 25/25] perf evsel: Don't pass evsel " Ian Rogers
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260320192627.368357-2-irogers@google.com \
--to=irogers@google.com \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=ajones@ventanamicro.com \
--cc=ak@linux.intel.com \
--cc=alex@ghiti.fr \
--cc=alexander.shishkin@linux.intel.com \
--cc=anup@brainfault.org \
--cc=aou@eecs.berkeley.edu \
--cc=atrajeev@linux.ibm.com \
--cc=blakejones@google.com \
--cc=ctshao@google.com \
--cc=dapeng1.mi@linux.intel.com \
--cc=derek.foreman@collabora.com \
--cc=dvyukov@google.com \
--cc=howardchu95@gmail.com \
--cc=hrishikesh123s@gmail.com \
--cc=james.clark@linaro.org \
--cc=jolsa@kernel.org \
--cc=krzysztof.m.lopatowski@gmail.com \
--cc=leo.yan@arm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=linux@treblig.org \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=nichen@iscas.ac.cn \
--cc=palmer@dabbelt.com \
--cc=peterz@infradead.org \
--cc=pjw@kernel.org \
--cc=ravi.bangoria@amd.com \
--cc=swapnil.sapkal@amd.com \
--cc=tanze@kylinos.cn \
--cc=thomas.falcon@intel.com \
--cc=tianyou.li@intel.com \
--cc=yujie.liu@intel.com \
--cc=zhouquan@iscas.ac.cn \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox