| Age | Commit message (Collapse) | Author |
|---|
|
Harden PERF_RECORD_HEADER_ATTR handling against crafted perf.data:
- Validate attr.size: must be >= PERF_ATTR_SIZE_VER0, a multiple
of sizeof(u64), and fit within the event payload.
- Copy only min(attr.size, sizeof(struct perf_event_attr)) bytes
into a local attr, zeroing the rest so legacy files don't leak
adjacent event data into new fields.
- Keep the original attr.size so perf_event__synthesize_attr()
uses it for both allocation and ID-array placement.
Fix perf_event__synthesize_attr() to use attr->size (not the
compiled sizeof) for event allocation and layout, so perf inject
correctly re-synthesizes attrs from files recorded by a different
perf version. Without this, the ID array destination pointer
(computed via perf_record_header_attr_id()) would be inconsistent
with the allocation when attr->size differs from sizeof.
Also fix the parse-no-sample-id-all test to set attr.size, which
is now validated, and improve error handling in read_attr() for
short reads and invalid attr sizes.
Handle ABI0 pipe/inject events where attr.size is 0: use a local
attr_size variable set to PERF_ATTR_SIZE_VER0 for both the bounded
copy and ID array position, instead of writing back to the event.
Native-endian files may be MAP_SHARED (read-only mmap), so writing
to the event buffer would SIGSEGV. The swap path handles ABI0 in
perf_event__attr_swap() which writes to the MAP_PRIVATE copy.
header.size alignment is now validated centrally in
perf_session__process_event() (see "Add minimum event size and
alignment validation").
Reported-by: sashiko-bot@kernel.org # Running on a local machine
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Assisted-by: Claude:claude-opus-4.6-1m
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
session->time_conv = event->time_conv copies sizeof(struct
perf_record_time_conv) bytes unconditionally, but older kernels
emit shorter TIME_CONV events without the time_cycles, time_mask,
cap_user_time_zero, and cap_user_time_short fields.
For a 32-byte event (the original format), this reads 24 bytes
past the event boundary into adjacent mmap'd data. The garbage
values end up in session->time_conv and can cause incorrect TSC
conversion if cap_user_time_zero happens to be non-zero.
Replace the struct assignment with a bounded memcpy capped at
event->header.size, zeroing the remainder so extended fields
default to off when absent.
Reported-by: sashiko-bot@kernel.org # Running on a local machine
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Assisted-by: Claude:claude-opus-4.6-1m
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Change swap callbacks from void to int return so handlers can
propagate errors. All 28 existing handlers are converted to
return 0 on success, -1 on error. Three new handlers (KSYMBOL,
BPF_EVENT, HEADER_FEATURE) are added returning int from the
start, with sample_id_all handling for the kernel event types.
event_swap() propagates the return to its callers (process_event
and peek_event), which skip events that fail to swap.
Add perf_event__check_nul() for null-termination enforcement
on the common event delivery path for MMAP, MMAP2, COMM,
CGROUP, and KSYMBOL events. Events with
unterminated strings are skipped — native-endian files are
mapped read-only, so writing a NUL byte in place would segfault.
Swap handler hardening:
- Use strnlen bounded by event size (instead of strlen) in
COMM/MMAP/MMAP2/CGROUP swap handlers, returning -1 on
unterminated strings.
- Bounds check text_poke old_len+new_len before computing the
sample_id offset, returning -1 on overflow. Use offsetof()
for the native-path check in machines__deliver_event() since
sizeof() includes struct padding past the flexible array.
- Fix PERF_RECORD_SWITCH sample_id_all: non-CPU_WIDE SWITCH
events have sample_id immediately after the 8-byte header,
not at sizeof(struct perf_record_switch) which is the
CPU_WIDE variant size.
- Fix perf_event__time_conv_swap(): decouple time_cycles and
time_mask into independent per-field event_contains() checks,
so each field is only swapped when the event is large enough
to contain it. The original code guarded both fields under
a single time_cycles check, which would swap time_mask on a
short event that contains time_cycles but not time_mask.
- Handle ABI0 (attr.size == 0) in perf_event__attr_swap()
by substituting PERF_ATTR_SIZE_VER0, so bswap_safe()
correctly swaps VER0 fields instead of skipping everything.
- peek_events: on swap failure, advance past the malformed
entry instead of aborting the loop.
Note: the nr-field bounds checks for namespaces, thread_map,
cpu_map, and stat_config arrays are added by a subsequent
patch ("perf session: Validate nr fields against event size
on both swap and common paths"). The HEADER_ATTR attr.size
validation is added by ("perf session: Validate HEADER_ATTR
attr.size before swapping").
By establishing the int-returning swap infrastructure first,
all subsequent hardening patches can use direct error returns
from day one — no poison values, no workarounds for void return.
Changes in v2:
- peek_events: abort instead of skip for AUXTRACE events on
validation failure — skipping only header.size would land
inside the raw trace payload, causing subsequent iterations
to misparse data as events (Reported-by: sashiko-bot@kernel.org)
Fixes: 9aa0bfa370b2 ("perf tools: Handle PERF_RECORD_KSYMBOL")
Fixes: 45178a928a4b ("perf tools: Handle PERF_RECORD_BPF_EVENT")
Fixes: e9def1b2e74e ("perf tools: Add feature header record to pipe-mode")
Reported-by: sashiko-bot@kernel.org # Running on a local machine
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Assisted-by: Claude:claude-opus-4.6-1m
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
swap_sample_id_all() calls BUG_ON(size % sizeof(u64)) which kills
perf on any event where the sample_id_all tail is not 8-byte aligned.
A crafted perf.data can trigger this trivially.
Replace BUG_ON with a bounds check: skip the swap if the data pointer
is past the end of the event, and only swap when there are bytes
remaining.
Note: the strlen calls in string-field swap handlers (comm,
mmap, mmap2, cgroup) are replaced with bounded strnlen by the
next patch in this series ("perf session: Add validated swap
infrastructure with null-termination checks").
Reported-by: sashiko-bot@kernel.org # Running on a local machine
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Assisted-by: Claude:claude-opus-4.6-1m
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
The kernel dynamically sizes PERF_RECORD_READ based on
attr.read_format: only the fields enabled by PERF_FORMAT_TOTAL_TIME_ENABLED,
PERF_FORMAT_TOTAL_TIME_RUNNING, PERF_FORMAT_ID, and PERF_FORMAT_LOST
are emitted, packed with no gaps.
perf_event__read_swap() unconditionally byte-swapped time_enabled,
time_running, and id at their fixed struct offsets, causing
out-of-bounds access on smaller events and swapping the wrong
bytes when not all format fields are present. It also swapped
sample_id_all at a fixed offset past the full struct, which is
wrong for shorter events.
Replace the individual field swaps with a single mem_bswap_64()
over the entire tail from value onward. Since every field after
pid/tid is u64 regardless of which combination is present, this
correctly handles any read_format combination and any trailing
sample_id_all fields.
Similarly, dump_read() accessed optional fields via fixed struct
offsets, displaying values from wrong positions when not all
format bits are set. Walk the packed u64 array sequentially
instead, with bounds checks against event->header.size.
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Assisted-by: Claude:claude-opus-4.6-1m
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
zstd_decompress_stream() has two bugs in its multi-iteration loop:
1. After each ZSTD_decompressStream() call, the code advances
output.dst by output.pos but doesn't reset output.pos to 0.
ZSTD interprets output.pos relative to output.dst, so the
next iteration writes at (dst + pos) + pos = dst + 2*pos,
skipping a gap and potentially writing out of bounds.
2. On ZSTD_decompressStream() error, the loop executes break
and returns output.pos (which is > 0 if some bytes were
decompressed before the error). The caller checks
!decomp_size and skips the error, silently accepting
truncated or corrupted data.
Fix both by removing the output buffer adjustment — ZSTD
correctly accumulates output.pos across calls without it.
Return 0 on decompression error so the caller detects it.
Add a no-progress guard to prevent infinite loops if the
output buffer fills before all input is consumed.
Note: the compressed event data_size is validated against
header.size by a subsequent patch in this series
("perf tools: Harden compressed event processing").
Reported-by: sashiko-bot@kernel.org # Running on a local machine
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Assisted-by: Claude:claude-opus-4.6-1m
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
The error fallback does memcpy(dst, src, src_size) intending to store
uncompressed data when compression fails, but this has three bugs:
1. dst has been advanced past the record header (and potentially
past earlier compressed records), so the copy writes to the
wrong offset in the output buffer.
2. src still points to the start of the input, not to the
remaining uncompressed data at src + input.pos. On a second
or later iteration, previously compressed data would be
duplicated.
3. No check that dst_size >= src_size — if the remaining output
space is smaller, this is an out-of-bounds write.
Replace with return -1 after resetting the ZSTD compression
context via ZSTD_initCStream(). The -1 propagates through
zstd_compress() -> record__pushfn() -> perf_mmap__push() to the
recording loop, which breaks out and terminates recording.
Add an out_child_no_flush label in __cmd_record() so the
mmap-read failure path skips the final record__mmap_read_all()
flush — retrying the same read that just failed would just fail
again, and the flush is only useful when the mmap data is intact
but the control path (auxtrace, switch_output) had an error.
Consolidate all error paths through a single 'reset' label to
ensure the compression context is always reset on failure —
including the output-buffer-full path, where a bare return
without resetting would leave stale stream state that corrupts
output if the caller retries.
Also guard against process_header() writing the event header
before the buffer-full check: add a sizeof(perf_event_header)
pre-check so the callback never writes past the output buffer.
Guard against ZSTD making no progress: if output.pos is zero
after ZSTD_compressStream(), calling process_header(record, 0)
would re-trigger header initialization, double-subtracting the
header size from dst_size and underflowing the unsigned counter.
Also fix two pre-existing issues in the same function:
- Add a dst_size guard before subtracting the record header
size: if the output buffer is nearly full, the unsigned
dst_size -= size underflows to a huge value, causing
ZSTD_compressStream to write past the buffer boundary.
- Check the ZSTD_initCStream() return value and log an error
if the context reset itself fails.
Reported-by: sashiko-bot@kernel.org # Running on a local machine
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Assisted-by: Claude:claude-opus-4.6-1m
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
event_contains() checked whether a field's start offset was within
the event (header.size > offsetof), but not whether the full field
fit. A crafted event with header.size = offsetof(field) + 1 would
pass the check, but an 8-byte access (bswap_64, direct read) would
overrun the event boundary by up to 7 bytes.
Fix the macro to verify the complete field:
header.size >= offsetof(field) + sizeof(field)
Also update all callers that check event_contains(time_cycles) but
access later fields (time_mask, cap_user_time_zero,
cap_user_time_short) to check for cap_user_time_short — the last
field accessed — so the entire extended block is verified:
tsc.c, arm-spe.c, cs-etm.c, jitdump.c.
Note: session.c's perf_event__time_conv_swap() also guards on
time_cycles but accesses time_mask — a pre-existing issue not
introduced by this macro change. It is fixed by a later patch
in this series ("perf session: Add validated swap
infrastructure with null-termination checks"), which decouples
time_cycles and time_mask into independent per-field
event_contains() checks. The struct assignment overread
(session->time_conv = event->time_conv copies sizeof on a
potentially shorter event) is separately fixed by "perf
session: Use bounded copy for PERF_RECORD_TIME_CONV".
Reported-by: sashiko-bot@kernel.org # Running on a local machine
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Assisted-by: Claude:claude-opus-4.6-1m
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
perf_session__peek_event() computes an event pointer directly from
file_offset when one_mmap is active, without verifying that file_offset
and the subsequent event->header.size fall within the mapped region.
A corrupted perf.data file could cause out-of-bounds memory reads.
Add one_mmap_size to the session struct and validate both the header
and full event fit within the mmap before dereferencing.
Reported-by: sashiko-bot@kernel.org # Running on a local machine
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Assisted-by: Claude:claude-opus-4.6-1m
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Add a per-type minimum size table (perf_event__min_size[]) and
enforce it before swap and processing, so that both cross-endian
and native-endian paths are protected from accessing fields past
the event boundary.
The table uses offsetof() for types with trailing variable-length
fields (filenames, strings, msg arrays) and sizeof() for
fixed-size types. Zero entries mean no minimum beyond the 8-byte
header already enforced by the reader.
Undersized events are skipped with a warning in process_event
and rejected in peek_event — both checked before the swap
handler runs, preventing OOB access on crafted event fields.
Also reject events whose header.size is not 8-byte aligned. The
kernel aligns all event sizes to sizeof(u64) — see
perf_event_comm_event() (ALIGN), perf_event_mmap_event(),
perf_event_cgroup(), perf_event_ksymbol() (IS_ALIGNED loops),
and perf_event_text_poke() (ALIGN) in kernel/events/core.c.
An unaligned size means the file is corrupted or crafted; reject
early so downstream code that divides by sizeof(u64) to compute
array element counts gets exact results.
Three legacy user events are exempted from the alignment check:
TRACING_DATA (66) had a 12-byte struct before commit b39c915a4f36
("libperf event: Ensure tracing data is multiple of 8 sized")
added padding, COMPRESSED (81) carries raw ZSTD output (already
superseded by COMPRESSED2 with PERF_ALIGN), and HEADER_FEATURE
(80) uses do_write_string() with a 4-byte length prefix.
Also guard event_swap() against crafted event types >=
PERF_RECORD_HEADER_MAX to prevent OOB reads on the
perf_event__swap_ops[] array.
Changes in v2:
- Fix double-skip for unsupported event types: return 0 instead
of event->header.size in perf_session__process_event() for
HEADER_MAX, since reader__read_event() already advances by
event->header.size (Reported-by: sashiko-bot@kernel.org)
- Exempt TRACING_DATA, COMPRESSED, and HEADER_FEATURE from the
alignment check — these legacy user events predate the 8-byte
alignment rule (Reported-by: sashiko-bot@kernel.org)
- peek_event: return 0 (skip) for unknown event types instead of
-1 (error), consistent with process_event which already skips
unsupported types gracefully (Reported-by: sashiko-bot@kernel.org)
Reported-by: sashiko-bot@kernel.org # Running on a local machine
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Assisted-by: Claude:claude-opus-4.6-1m
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
The only user of msg->msg_iocb was AF_ALG, but that's deprecated.
It can be removed entirely at the cost of only supporting synchronous
operations. This doesn't break userspace, which will silently block
(for a bounded amount of time) in io_submit instead of operating
asynchronously.
This also makes struct msghdr smaller, helping every other caller of
sendmsg().
Signed-off-by: Demi Marie Obenour <demiobenour@gmail.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
more widely
While testing perf with an updated Debian experimental cross compiler
(gcc version 14.2.0 (Debian 14.2.0-13)) this started failing:
In file included from tests/hwmon_pmu.c:12:
tests/hwmon_pmu.c: In function 'do_test':
tests/hwmon_pmu.c:199:34: error: format '%lld' expects argument of type 'long long int', but argument 7 has type '__u64' {aka 'long unsigned int'} [-Werror=format=]
199 | pr_debug("FAILED %s:%d Unexpected config for '%s', %lld != %ld\n",
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/git/perf-7.1.0-rc5/tools/perf/util/debug.h:20:21: note: in definition of macro 'pr_fmt'
20 | #define pr_fmt(fmt) fmt
| ^~~
tests/hwmon_pmu.c:199:25: note: in expansion of macro 'pr_debug'
199 | pr_debug("FAILED %s:%d Unexpected config for '%s', %lld != %ld\n",
| ^~~~~~~~
tests/hwmon_pmu.c:199:79: note: format string is defined here
199 | pr_debug("FAILED %s:%d Unexpected config for '%s', %lld != %ld\n",
| ~~~^
| |
| long long int
| %ld
LD /tmp/build/perf/util/intel-pt-decoder/perf-util-in.o
The usual make that %lld a PRIu64 (since arg7 is
evsel->core.attr.config, which is a __u64) but then on Fedora 44 (gcc
version 16.1.1 20260515 (Red Hat 16.1.1-2)) it ends up with:
In file included from tests/hwmon_pmu.c:13:
tests/hwmon_pmu.c: In function ‘do_test’:
tests/hwmon_pmu.c:200:34: error: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 7 has type ‘__u64’ {aka ‘long long unsigned int’} [-Werror=format=]
200 | pr_debug("FAILED %s:%d Unexpected config for '%s', %" PRIu64 " != %ld\n",
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/acme/git/perf-tools-next2/tools/perf/util/debug.h:20:21: note: in definition of macro ‘pr_fmt’
20 | #define pr_fmt(fmt) fmt
| ^~~
tests/hwmon_pmu.c:200:25: note: in expansion of macro ‘pr_debug’
200 | pr_debug("FAILED %s:%d Unexpected config for '%s', %" PRIu64 " != %ld\n",
| ^~~~~~~~
cc1: all warnings being treated as errors
So the way to satisfy both compilers is to also add a (u64) cast to
arg7.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Fix missing #include of pmu.h found while cleaning the evsel/evlist
header files. Sort the remaining header files for consistency with the
rest of the code. Doing this exposed a missing forward declaration of
addr_location in print_insn.h, add this and sort the forward
declarations.
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alice Rogers <alice.mei.rogers@gmail.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Fix missing #includes found while cleaning the evsel/evlist header
files. Sort the remaining header files for consistency with the rest
of the code.
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alice Rogers <alice.mei.rogers@gmail.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Fix missing #includes found while cleaning the evsel/evlist header
files. Sort the remaining header files for consistency with the rest
of the code.
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alice Rogers <alice.mei.rogers@gmail.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Fix missing #includes found while cleaning the evsel/evlist header
files. Sort the remaining header files for consistency with the rest
of the code.
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alice Rogers <alice.mei.rogers@gmail.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
DSOs
dso__load_sym_internal() had no filtering for .L* and L0* mapping
symbols while the kallsyms path already filters them via
is_ignored_kernel_symbol().
Add the same check gated by dso__kernel() so that kernel ELF objects
(vmlinux, .ko) have mapping symbols filtered across all architectures,
but userspace ELF objects are unaffected -- '$' is a valid prefix in
languages like Java and Scala.
The existing ARM/AArch64 and RISC-V architecture-specific mapping symbol
checks are preserved; the new is_ignored_kernel_symbol() check adds x86
local symbol (.L*, L0*) filtering and provides unified
cross-architecture coverage for kernel DSOs.
Signed-off-by: Rui Qi <qirui.001@bytedance.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Mapping symbol filtering is scattered across multiple files with
inconsistent checks. The kernel's own is_mapping_symbol() covers x86
local symbols ('.L*' and 'L0*') on top of the '$' prefix used by
ARM/AArch64/RISC-V, but the perf tool only checks '$'.
Extract is_ignored_kernel_symbol() into symbol.h matching the kernel
definition, and convert the kallsyms and ksymbol event paths to use it.
Add ksymbol event name validation and early mapping symbol filtering
before any state mutation.
Signed-off-by: Rui Qi <qirui.001@bytedance.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Add documentation comment describing the parameters
and return code for auxtrace_record__init() in util/auxtrace.c
Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Athira Rajeev <atrajeev@linux.ibm.com>
Cc: Hari Bathini <hbathini@linux.vnet.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Shivani Nittor <shivani@linux.ibm.com>
Cc: Tanushree.Shah@ibm.com
Cc: Tejas.Manhas1@ibm.com
Cc: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
perf trace record fails some cases in powerpc
# perf test "perf trace record and replay"
128: perf trace record and replay : FAILED!
# perf trace record sleep 1
# echo $?
32
This is happening because of non-zero err value from
auxtrace_record__init() function.
static int record__auxtrace_init(struct record *rec)
{
int err;
if ((rec->opts.auxtrace_snapshot_opts || rec->opts.auxtrace_sample_opts)
&& record__threads_enabled(rec)) {
pr_err("AUX area tracing options are not available in parallel streaming mode.\n");
return -EINVAL;
}
if (!rec->itr) {
rec->itr = auxtrace_record__init(rec->evlist, &err);
if (err)
return err;
}
Here "int err" is not initialised. The code expects "err" to be set from
auxtrace_record__init() function.
Update auxtrace_record__init() in arch/powerpc/util/auxtrace.c to clear
err value in the beginning.
- Clear err value in beginning of function. Any fail later will
set appropriate return code to err.
- Even if we haven't found any event for auxtrace, perf record
should continue for other events. NULL return
will indicate that there is no auxtrace record initialized.
- Not having "err" set here will affect monitoring of other events
also because perf record will fail seeing random value in err.
Set err to -EINVAL before invoking auxtrace_record__init() in
builtin-record.c
With the fix,
# perf trace record sleep 1
[ perf record: Woken up 2 times to write data ]
[ perf record: Captured and wrote 0.033 MB perf.data (228 samples) ]
Fixes: 1dbfaf94cf66ec4b ("perf powerpc: Add basic CONFIG_AUXTRACE support for VPA pmu on powerpc")
Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Athira Rajeev <atrajeev@linux.ibm.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Athira Rajeev <atrajeev@linux.ibm.com>
Cc: Hari Bathini <hbathini@linux.vnet.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Shivani Nittor <shivani@linux.ibm.com>
Cc: Tanushree Shah <tanushree.shah@ibm.com>
Cc: Tejas Manhas <tejas.manhas1@ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Add a new shell test `stat_metrics_cgrp.sh` to verify metric reporting
with `--for-each-cgroup`, both with and without `--bpf-counters`.
The test:
- Checks if system-wide monitoring is supported (skips if not).
- Finds cgroups to test.
- Runs `perf stat` with `insn_per_cycle` metric and verifies that the
metric is reported for each cgroup.
- Dynamically pairs and verifies instructions and cycles counts to
avoid false failures on idle cgroups.
- Tests both standard mode and BPF counters mode (if supported).
Assisted-by: Antigravity:gemini-3-flash
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Svilen Kanev <skanev@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
When using BPF counters with cgroups, follower events (for cgroups
other than the first one) are not opened. Because they are not opened,
their `supported` flag was left as `false`.
During metric calculation, `prepare_metric` checks if the event is
supported. If it is not supported (like the follower events), it
explicitly sets the value to `NAN`, which eventually causes the metric
to be reported as `nan %`.
Fix this by propagating the `supported` flag from the "leader" events
(the ones opened for the first cgroup) to the "follower" events.
Also add a validation check to `bperf_load_program` to ensure `nr_cgroups`
is not zero and the number of events is a multiple of `nr_cgroups`,
preventing a potential division-by-zero (SIGFPE) exception when
`num_events` evaluates to 0 (e.g., with a trailing comma in cgroups list).
Reported-by: Svilen Kanev <skanev@google.com>
Assisted-by: Antigravity:gemini-3-flash
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
The assignment of strrchr() return values to non-const char * variables
triggers a -Werror=discarded-qualifiers warning when building with GCC
14.
This happens because in newer glibc versions, strrchr() returns a 'const
char *' if the input string is const.
Properly declare 'line2' and 'nl' as const char * to match the glibc
function signature and ensure type safety. This avoids the need for
explicit type casting and aligns with the design pattern of not
modifying read-only memory in the perf tool.
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Li Guan <guanli.oerv@isrc.iscas.ac.cn>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <pjw@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Add a new test case `test_stat_delay` to `stat.sh` to verify that
`duration_time` correctly excludes the delay period when using the
delay option (-D).
The test runs `perf stat -D 1000 -e duration_time sleep 2` and
verifies that `duration_time` is ~1s (excluding the 1s delay), not
~2s.
Assisted-by: Antigravity:gemini-3-flash
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Francesco Nigro <nigro.fra@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Tool PMU events (duration_time, user_time, system_time) currently
count from when the event is opened to when it is read. This causes
issues with features like the delay option (-D) or control fd, where
events are opened but should not start counting immediately.
Make these events behave more like regular counters by implementing
proper enable and disable support. Add accumulated_time to struct
evsel to track time while enabled, and implement enable/disable CPU
callbacks to start/stop counting.
Also generalize userspace PMU mixed group handling. Userspace synthetic
PMUs (type > PERF_PMU_TYPE_PE_END) do not have kernel implementations and
cannot be grouped in the kernel (opened with group_fd = -1), and are
skipped by kernel enable/disable calls. Iterate over group members in
userspace and manually enable/disable any members if the leader or the
member is a non-perf-event open PMU, and synchronize their disabled flags.
Closes: https://lore.kernel.org/linux-perf-users/20260517093650.2540920-1-nigro.fra@gmail.com/
Fixes: b71f46a6a7086175 ("perf stat: Remove hard coded shadow metrics")
Reported-by: Francesco Nigro <nigro.fra@gmail.com>
Assisted-by: Antigravity:gemini-3-flash
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Include examples of:
o Privilege filter with Fetch and Op PMUs, including swfilt approach on
Zen5 and older platforms and hardware assisted filter on Zen6 and newer
platforms
o Streaming store filter with Op PMU
o Fetch latency filter with Fetch PMU
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Ananth Narayan <ananth.narayan@amd.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Manali Shukla <manali.shukla@amd.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Santosh Shukla <santosh.shukla@amd.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
IBS OP on Zen6 and future platform can tag IBS samples that originate from
streaming-store instruction. When the PMU advertises this feature,
interpret IBS_OP_DATA2[8] bit as the streaming store indicator and show
it in the raw dump output.
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Ananth Narayan <ananth.narayan@amd.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Manali Shukla <manali.shukla@amd.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Santosh Shukla <santosh.shukla@amd.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
IBS OP on Zen6 and future platform can mark a data source as coming from
a remote socket. When the PMU advertises this feature, interpret
IBS_OP_DATA2[9] bit as the Remote-Socket indicator and show it in the
raw dump output.
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Ananth Narayan <ananth.narayan@amd.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Manali Shukla <manali.shukla@amd.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Santosh Shukla <santosh.shukla@amd.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
platforms
On Zen6 and future platforms, IBS_FETCH_CTL status fields are valid only
if IBS_FETCH_CTL[IbsPhyAddrValid] is set. Same for IBS_FETCH_CTL_EXT.
Add these checks while decoding IBS MSRs.
Unfortunately, there is no CPUID bit to indicate the change. Fallback
to Family/Model check.
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Ananth Narayan <ananth.narayan@amd.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Manali Shukla <manali.shukla@amd.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Santosh Shukla <santosh.shukla@amd.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
On Zen4 (and future) CPUs, IBS_OP_DATA3[TlbRefillLat] is valid only if
IBS_OP_DATA3[DcPhyAddrValid] is set. Similarly, IBS_DC_PHYSADDR is valid
if IBS_OP_DATA3[DcLinAddrValid] is _also_ set. Add these checks while
decoding IBS MSRs.
When IBS is triggered by an unprivileged user, the kernel now zeroes
PhysAddr before storing raw IBS register values in the perf sample. The
perf tool, however, still outputs these zero physical addresses, which
serves no purpose. So avoid printing zero physical addresses.
Instead of explicit family/model checks use the !zen4_ibs_extensions as
a proxy flag to cover Zen 3 and earlier revisions.
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Ananth Narayan <ananth.narayan@amd.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Manali Shukla <manali.shukla@amd.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Santosh Shukla <santosh.shukla@amd.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
IBS on pre-Zen6 platforms lacked a hardware privilege filter, so the
kernel enabled swfilt=1. Zen6 and newer platforms provides privilege
filtering via the RIP[63] bit, making swfilt redundant. Skip the perf
unit test that assumes IBS has no hardware-assisted privilege filter
on Zen6 and newer platforms.
swfilt is ignored by kernel on platforms that support RIP[63] bit filter
i.e. all amd-ibs-swfilt.sh tests will test hardware assisted privilege
filter.
Without the patch on Zen6:
# sudo ./perf test -vv 77
77: AMD IBS software filtering:
--- start ---
test child forked, pid 30813
check availability of IBS swfilt
run perf record with modifier and swfilt
[FAIL] IBS PMU should not accept exclude_kernel
---- end(-1) ----
77: AMD IBS software filtering : FAILED!
With the patch:
# ./perf test -vv 77
77: AMD IBS software filtering:
--- start ---
test child forked, pid 30903
check availability of IBS swfilt
run perf record with modifier and swfilt
[ perf record: Woken up 2 times to write data ]
[ perf record: Captured and wrote 0.000 MB /dev/null ]
[ perf record: Woken up 3 times to write data ]
[ perf record: Captured and wrote 0.000 MB /dev/null ]
[ perf record: Woken up 3 times to write data ]
[ perf record: Captured and wrote 0.000 MB /dev/null ]
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.000 MB /dev/null ]
check number of samples with swfilt
[ perf record: Woken up 4 times to write data ]
[ perf record: Captured and wrote 0.051 MB - ]
[ perf record: Woken up 4 times to write data ]
[ perf record: Captured and wrote 0.063 MB - ]
---- end(0) ----
77: AMD IBS software filtering : Ok
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Ananth Narayan <ananth.narayan@amd.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Manali Shukla <manali.shukla@amd.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Santosh Shukla <santosh.shukla@amd.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
"AMD IBS sample period" unit test is getting skipped on kernel v7.x. Fix
the kernel version >= v6.15 check.
Fixes: 21fb366b2f457611 ("perf test amd: Skip amd-ibs-period test on kernel < v6.15")
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Ananth Narayan <ananth.narayan@amd.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Manali Shukla <manali.shukla@amd.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Santosh Shukla <santosh.shukla@amd.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
This commit addresses several memory management issues in builtin-kwork.c:
1. Implements a global cleanup function perf_kwork__exit to free all
kwork_work and kwork_atom_page objects at the end of the command.
2. Ensures all 'name' fields in struct kwork_work are malloc-ed (or NULL)
and properly freed by using strdup and zfree.
3. Fixes memory leaks in top_merge_tasks where kwork_work objects were
dropped without being freed.
4. Adds robustness with NULL checks for name fields.
5. Fixes workqueue_work_init to correctly resolve and strdup kernel
function names, preventing bad-free errors.
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
There is a double free in the record array due to how parse_options
will mutate the array. Fix by keeping an array that isn't
mutated. Ensure kwork_usage is freed on all paths.
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
A "make feature-dump" build does not specify LIBUNWIND=1 because it is
run with the default configuration to detect system-wide capabilities.
This sets NO_LIBUNWIND := 1, causing Makefile.config to skip setting
LIBUNWIND_LIBS and FEATURE_CHECK_LDFLAGS-libunwind.
Consequently, when Makefile.feature is included and attempts to run
all feature checks (via FEATURE_TESTS := all), the local feature test
test-libunwind.bin compiles without the required architecture-specific
library flags (-lunwind-x86_64) and fails to link on x86_64. This
results in a corrupted cached BUILD_TEST_FEATURE_DUMP showing
feature-libunwind=0 even when the host supports it.
Subsequent test builds (like make_libunwind_O in the build-test suite)
which reuse the feature dump and specify LIBUNWIND=1 will fail to
compile due to a mismatch where CONFIG_LIBUNWIND is set (via remote
architecture checks which are self-contained) but HAVE_LIBUNWIND_SUPPORT
is disabled, causing compiler errors due to missing maps__e_machine
definitions in maps.h.
Fix this by unconditionally setting up the libunwind library lists
and feature check LDFLAGS in Makefile.config so they are always
populated and available to the feature detection engine regardless
of whether LIBUNWIND=1 is opted-in for the current run.
Fixes: 444508cd7c7b4f05 ("perf build: Be more programmatic when setting up libunwind variables")
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Since some time the metric-only output columns are messed up and do not
line up with the header, which makes it hard to read. I haven't bisected
it, but presumably it was broken for some time.
There were multiple problems:
- The dummy pm invocation at the beginning did print a bogus field
- The column computation in pm did not agree with the header length
- The color escape strings from highlighting confuse printf's field
length computation
Fix all those. I simplified the column width computation significantly,
ignoring EVNAME_LEN, MGROUP_LEN, config->unit_width which don't
seem to be useful in the metric only context. It now only uses
the actual unit width as well as config->metric_only_len. The result
is more code removed than added.
Before:
% perf stat --topdown -a -I 1000
+ time % tma_backend_bound % tma_frontend_bound % tma_bad_speculation % tma_retiring
1.000190386 45.5 40.0 5.3 9.2
2.005185654 45.3 40.1 5.6 9.0
3.009193207 45.4 39.9 5.6 9.1
After:
% perf stat --topdown -a -I 1000
+ time % tma_backend_bound % tma_frontend_bound % tma_bad_speculation % tma_retiring
1.000810024 46.3 39.7 5.3 8.7
2.004800656 45.8 39.8 5.4 8.9
3.008804783 46.0 39.6 5.4 9.0
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Fixup clash of:
552636b9317c8a84 ("perf trace: Add beautifier script for fsmount flags")
That went via Namhyung upstream and the following ones in the
perf-tools-next tree:
32969ef6e3e1979a ("perf build: Pre-generate BPF skeleton tooling during umbrella prepare phase")
537609924c43715e ("perf trace beauty: Make beauty generated C code standalone .o files")
This complements f8d0db39bcc536ef ("perf build: Fix fsmount.o build")
sent by Ian Rogers.
Acked-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Ian Rogers <irogers@google.com>
Cc: Mark Brown <broonie@kernel.org>
Cc: Thorsten Leemhuis <linux@leemhuis.info>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
A merge conflict between:
commit 552636b9317c8a84 ("perf trace: Add beautifier script for fsmount flags")
commit 32969ef6e3e1979a ("perf build: Pre-generate BPF skeleton tooling during umbrella prepare phase")
Resulted in a missed build dependency in the linux-next merge:
commit 61da860eee0798d3 ("Merge branch 'perf-tools-next' of https://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next.git")
Fix the build by adding the necessary build dependencies.
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Mark Brown <broonie@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
In Makefile.perf, ALL_PROGRAMS includes SCRIPTS (perf-archive,
perf-iostat). However, unlike PROGRAMS and DLFILTERS, SCRIPTS was not
prefixed with $(OUTPUT).
During out-of-tree builds (or when O= is specified), Make checked for the
unprefixed target 'tools/perf/perf-archive'. Since the actual script was
installed into $(OUTPUT)perf-archive, Make concluded the target was
missing and continuously re-executed the script installation rule on every
single incremental build.
Prefix SCRIPTS with $(OUTPUT) and update the static pattern rule to ensure
Kbuild correctly tracks generated script prerequisites during incremental
builds.
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: James Clark <james.clark@linaro.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Chartre <alexandre.chartre@oracle.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Ankur Arora <ankur.a.arora@oracle.com>
Cc: Collin Funk <collin.funk1@gmail.com>
Cc: Costa Shulyupin <costa.shul@redhat.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: David Sterba <dsterba@suse.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Markus Mayer <mmayer@broadcom.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <pjw@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Monnet <qmo@kernel.org>
Cc: Ricky Ringler <ricky.ringler@proton.me>
Cc: Song Liu <song@kernel.org>
Cc: Swapnil Sapkal <swapnil.sapkal@amd.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Tomas Glozar <tglozar@redhat.com>
Cc: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Add a test to capture the comment in tools/perf/arch/x86/util/evlist.c.
Test that slots and topdown-retiring get appropriately sorted with
respect to instructions when they're all specified together.
When the PMU requires topdown event grouping (indicated by the pressence
of the slots event) metric events should be after slots, which should be
the group leader.
Add a related test that when the slots event isn't given it is injected
into the appropriate group.
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Zide Chen <zide.chen@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Collin Funk <collin.funk1@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Add a test for uncore event sorting matching multiple PMUs.
Uncore PMUs may have a common prefix, like the PMUs
uncore_imc_free_running_0 and uncore_imc_free_running_1 have a prefix of
uncore_imc_free_running.
Parsing an event group like "{data_read,data_write}" for those PMUs
should result with two groups:
"{uncore_imc_free_running_0/data_read/,uncore_imc_free_running_0/data_write/},
{uncore_imc_free_running_1/data_read/,uncore_imc_free_running_1/data_write/}"
which means the evsels need resorting as when initially parsed the
evsels are ordered with mixed PMUs:
"{uncore_imc_free_running_0/data_read/,uncore_imc_free_running_1/data_read/,
uncore_imc_free_running_0/data_write/,uncore_imc_free_running_1/data_write/}".
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Zide Chen <zide.chen@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Collin Funk <collin.funk1@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
In Makefile.config, CFLAGS, CXXFLAGS, LIBLLVM, and EXTLIBS were assigned
using recursive expansion or appended with raw $(shell $(LLVM_CONFIG) ...)
calls. Because these variables were expanded during dependency evaluation
across every single object file compilation rule, Kbuild continuously
re-executed llvm-config forks nearly 200 times during incremental builds.
Convert llvm-config shell queries to simply expanded variables (:=) to
ensure Make evaluates LLVM compiler flags and library paths exactly once
when Makefile.config is parsed, eliminating ~185 redundant sub-processes
during build startup.
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Chartre <alexandre.chartre@oracle.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Ankur Arora <ankur.a.arora@oracle.com>
Cc: Collin Funk <collin.funk1@gmail.com>
Cc: Costa Shulyupin <costa.shul@redhat.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: David Sterba <dsterba@suse.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Markus Mayer <mmayer@broadcom.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <pjw@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Monnet <qmo@kernel.org>
Cc: Ricky Ringler <ricky.ringler@proton.me>
Cc: Song Liu <song@kernel.org>
Cc: Swapnil Sapkal <swapnil.sapkal@amd.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Tomas Glozar <tglozar@redhat.com>
Cc: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
built-ins
In pmu-events/Build, ZENS, ARMS, and INTELS were assigned using recursive
assignment (=), and model_name/vendor_name were evaluated using shell
macros (echo ... | sed ...).
Because these variables were expanded inside the COPY_RULE dependency
evaluation loop across hundreds of PMU JSON files and inside every metric
generation recipe, Kbuild continuously re-executed 'ls', 'grep', and 'sed'
shell forks thousands of times during AST parsing and execution.
Convert ZENS, ARMS, and INTELS to simply expanded variables (:=) and
replace model_name/vendor_name with pure GNU Make string functions. This
guarantees Make executes directory probing shell forks exactly once when
the Build file is parsed and evaluates path macros purely in memory,
completely eliminating over 7,800 redundant sub-processes during build
startup.
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Chartre <alexandre.chartre@oracle.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Ankur Arora <ankur.a.arora@oracle.com>
Cc: Collin Funk <collin.funk1@gmail.com>
Cc: Costa Shulyupin <costa.shul@redhat.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: David Sterba <dsterba@suse.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Markus Mayer <mmayer@broadcom.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <pjw@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Monnet <qmo@kernel.org>
Cc: Ricky Ringler <ricky.ringler@proton.me>
Cc: Song Liu <song@kernel.org>
Cc: Swapnil Sapkal <swapnil.sapkal@amd.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Tomas Glozar <tglozar@redhat.com>
Cc: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Currently, jevents.py emits both the massive 2.8 MB big_c_string literal
and tens of thousands of compact_pmu_event struct arrays into a single
pmu-events.c compilation unit. Compiling this giant file takes ~2.2 seconds
on a single CPU core during Kbuild startup.
Refactor jevents.py to emit big_c_string into a dedicated
pmu-events-string.c compilation unit. This allows Kbuild to compile
pmu-events.o and pmu-events-string.o simultaneously in parallel across
two separate CPU cores, preserving 100% string deduplication and zero
dynamic ELF relocations while cutting C compilation latency in half.
Add pmu-events-string.c to tools/perf/.gitignore to ensure in-tree Kbuild
runs do not leave untracked generated files in the working directory.
To guarantee 100% backward compatibility with GNU Make 4.0+ (avoiding the
Make 4.3+ grouped target &: syntax which causes older Make versions like
4.2.1 to spawn multiple concurrent jevents.py processes during parallel
builds), implement a robust dependency chaining pattern:
$(PMU_EVENTS_C): $(JEVENTS_DEPS)
$(PMU_EVENTS_STRING_C): $(PMU_EVENTS_C)
@:
This ensures jevents.py is invoked exactly once. If jevents.py aborts
early, Make's .DELETE_ON_ERROR: purges pmu-events.c, guaranteeing that
subsequent Make invocations correctly re-execute the script and overwrite
pmu-events-string.c. In jevents.py, explicitly close output_file first
and output_string_file second at the tail of main() to guarantee that
pmu-events-string.c receives a filesystem timestamp greater than or equal
to pmu-events.c, completely avoiding redundant incremental rebuilds.
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: James Clark <james.clark@linaro.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Chartre <alexandre.chartre@oracle.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Ankur Arora <ankur.a.arora@oracle.com>
Cc: Collin Funk <collin.funk1@gmail.com>
Cc: Costa Shulyupin <costa.shul@redhat.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: David Sterba <dsterba@suse.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Markus Mayer <mmayer@broadcom.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <pjw@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Monnet <qmo@kernel.org>
Cc: Ricky Ringler <ricky.ringler@proton.me>
Cc: Song Liu <song@kernel.org>
Cc: Swapnil Sapkal <swapnil.sapkal@amd.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Tomas Glozar <tglozar@redhat.com>
Cc: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
By default, the perf tool compiles and statically links against its own
internal copy of libbpf (tools/lib/bpf/libbpf.a), setting LIBBPF_STATIC=1.
Despite this static linkage, Makefile.config unconditionally executed
$(call feature_check,libbpf), which forced a synchronous sub-make fork
during AST parsing to detect dynamic system libbpf libraries.
As noted in the internal Makefile comments, this check was executed purely
so that running `make VF=1` would display the detection status of system
libbpf. During standard builds without LIBBPF_DYNAMIC=1, the detection
result was entirely ignored.
Wrap the libbpf feature check inside LIBBPF_DYNAMIC=1 so Make avoids the
redundant sub-make fork overhead during standard static builds.
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: James Clark <james.clark@linaro.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Chartre <alexandre.chartre@oracle.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Ankur Arora <ankur.a.arora@oracle.com>
Cc: Collin Funk <collin.funk1@gmail.com>
Cc: Costa Shulyupin <costa.shul@redhat.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: David Sterba <dsterba@suse.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Markus Mayer <mmayer@broadcom.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <pjw@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Monnet <qmo@kernel.org>
Cc: Ricky Ringler <ricky.ringler@proton.me>
Cc: Song Liu <song@kernel.org>
Cc: Swapnil Sapkal <swapnil.sapkal@amd.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Tomas Glozar <tglozar@redhat.com>
Cc: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
The prepare step is a large serialization point before parallel
sub-makes build the perf tool. The libsymbol headers are used in the
bench and util libraries. Move the libsymbol dependency out of the
prepare step and into the dependencies for those targets to avoid it
being a source of serialization in the prepare step.
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: James Clark <james.clark@linaro.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Chartre <alexandre.chartre@oracle.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Ankur Arora <ankur.a.arora@oracle.com>
Cc: Collin Funk <collin.funk1@gmail.com>
Cc: Costa Shulyupin <costa.shul@redhat.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: David Sterba <dsterba@suse.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Markus Mayer <mmayer@broadcom.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <pjw@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Monnet <qmo@kernel.org>
Cc: Ricky Ringler <ricky.ringler@proton.me>
Cc: Song Liu <song@kernel.org>
Cc: Swapnil Sapkal <swapnil.sapkal@amd.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Tomas Glozar <tglozar@redhat.com>
Cc: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Currently, BPF skeleton generation rules (bpf_skel.mak) are evaluated as
part of util/Build. However, because LIBPERF_UTIL_IN explicitly depends
on the top-level static libbpf archive, Make completely blocked the
execution of bpftool bootstrap and skeleton generation until libbpf
finished compiling midway through the build.
Since bpftool bootstrap compiles its own independent copy of libbpf.a, it
does not depend on the top-level libbpf target.
Decouple early skeleton tooling generation by attaching bpf-skel-prepare
to the umbrella prepare target, exporting CONFIG_PERF_BPF_SKEL to ensure
accurate feature propagation. This allows Make to compile bpftool and
dump vmlinux.h in the background at build startup, eliminating the initial
sub-make startup bottleneck before BPF object compilation while keeping
100% of tooling rules perfectly encapsulated in bpf_skel.mak. Provide an
empty fallback target to ensure builds succeed when BPF skeletons are
disabled.
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: James Clark <james.clark@linaro.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Chartre <alexandre.chartre@oracle.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Ankur Arora <ankur.a.arora@oracle.com>
Cc: Collin Funk <collin.funk1@gmail.com>
Cc: Costa Shulyupin <costa.shul@redhat.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: David Sterba <dsterba@suse.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Markus Mayer <mmayer@broadcom.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <pjw@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Monnet <qmo@kernel.org>
Cc: Ricky Ringler <ricky.ringler@proton.me>
Cc: Song Liu <song@kernel.org>
Cc: Swapnil Sapkal <swapnil.sapkal@amd.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Tomas Glozar <tglozar@redhat.com>
Cc: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Currently, bpftool and vmlinux.h are prerequisites of the top-level
prepare target in Makefile.perf. This unnecessarily blocks the massive
parallel C compilation of libraries (perf-util, perf-ui, pmu-events) during
the initial startup phase.
Move all bpftool and vmlinux.h generation rules down into
tools/perf/bpf_skel.mak to encapsulate BPF tooling completely within the
skeleton framework. Remove them entirely from prepare to unblock immediate
parallel build execution.
To prevent parallel sub-makes (perf-util and perf-bench) from racing to
build shared prerequisites concurrently, while maintaining strict directory
encapsulation without top-level inclusions, serialize bench after the util
static archive finishes using an order-only prerequisite:
$(LIBPERF_BENCH_IN): FORCE prepare | $(LIBPERF_UTIL)
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: James Clark <james.clark@linaro.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Chartre <alexandre.chartre@oracle.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Ankur Arora <ankur.a.arora@oracle.com>
Cc: Collin Funk <collin.funk1@gmail.com>
Cc: Costa Shulyupin <costa.shul@redhat.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: David Sterba <dsterba@suse.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Markus Mayer <mmayer@broadcom.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <pjw@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Monnet <qmo@kernel.org>
Cc: Ricky Ringler <ricky.ringler@proton.me>
Cc: Song Liu <song@kernel.org>
Cc: Swapnil Sapkal <swapnil.sapkal@amd.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Tomas Glozar <tglozar@redhat.com>
Cc: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Currently, the top-level Makefile.perf defines a massive global bpf-skel
umbrella target that pre-compiles all 12+ BPF skeletons (%.skel.h) upfront
before launching sub-makes. This forces unrelated sub-makes to serialize
behind bpftool and clang BPF target evaluations, causing parallel build
bottlenecks.
Furthermore, bench_uprobe.bpf.c lived inside util/bpf_skel/, breaking
conceptual directory encapsulation since it is consumed purely by
bench/uprobe.c.
Refactor the BPF skeletons to better achieve directory isolation:
1. Move tools/perf/util/bpf_skel/bench_uprobe.bpf.c directly into
tools/perf/bench/bpf_skel/.
2. Extract the skeleton generation infrastructure out of Makefile.perf into
a shared inclusion file tools/perf/bpf_skel.mak.
3. Include bpf_skel.mak locally inside tools/perf/util/Build and
tools/perf/bench/Build and bind precise local prerequisites.
4. Safely synchronize the shared bpftool bootstrap and vmlinux.h targets
via the conditional prepare: umbrella to avoid parallel sub-make races,
while evaluating the actual skeletons completely locally on demand. A
later patch will move these targets into bpf_skel.mak.
5. Export CLANG from the global Makefile to ensure accurate tool
propagation.
6. Clean up Makefile.perf by stripping the global bpf-skel umbrella target
and its SKELETONS list.
While removing code from Makefile.perf generally helps build
performance, the impact here is minimal. The main motivation for the
change is to better encapsulate things in the build and simplify
Makefile.perf that has around 50 lines removed.
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: James Clark <james.clark@linaro.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Chartre <alexandre.chartre@oracle.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Ankur Arora <ankur.a.arora@oracle.com>
Cc: Collin Funk <collin.funk1@gmail.com>
Cc: Costa Shulyupin <costa.shul@redhat.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: David Sterba <dsterba@suse.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Markus Mayer <mmayer@broadcom.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <pjw@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Monnet <qmo@kernel.org>
Cc: Ricky Ringler <ricky.ringler@proton.me>
Cc: Song Liu <song@kernel.org>
Cc: Swapnil Sapkal <swapnil.sapkal@amd.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Tomas Glozar <tglozar@redhat.com>
Cc: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Remove empty target that doesn't do anything.
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: James Clark <james.clark@linaro.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Chartre <alexandre.chartre@oracle.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Ankur Arora <ankur.a.arora@oracle.com>
Cc: Collin Funk <collin.funk1@gmail.com>
Cc: Costa Shulyupin <costa.shul@redhat.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: David Sterba <dsterba@suse.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Markus Mayer <mmayer@broadcom.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <pjw@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Monnet <qmo@kernel.org>
Cc: Ricky Ringler <ricky.ringler@proton.me>
Cc: Song Liu <song@kernel.org>
Cc: Swapnil Sapkal <swapnil.sapkal@amd.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Tomas Glozar <tglozar@redhat.com>
Cc: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
