Current code skips to parse events after generating data source. The
reason is the data source packets have cache and snooping related info,
the afterwards event packets might contain duplicate info.
This commit changes to continue parsing the events after data source
analysis. If data source does not give out memory level and snooping
types, then the event info is used to synthesize the related fields.
As a result, both the peer snoop option ('-d peer') and hitm options
('-d tot/lcl/rmt') are supported by Arm SPE in 'perf c2c'.
Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Leo Yan <leo.yan@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ali Saidi <alisaidi@amazon.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Since FEAT_SPEv1p4, Arm SPE provides two extra events: "Cache data
modified" and "Data snooped".
Set the snoop mode as:
- If both the "Cache data modified" event and the "Data snooped" event
are set, which indicates a load operation that snooped from a outside
cache and hit a modified copy, set the HITM flag to inspect false
sharing.
- If the snooped event bit is not set, and the snooped event has been
supported by the hardware, set as NONE mode (no snoop operation).
- If the snooped event bit is not set, and the event is not supported or
absent the events info in the meta data, set as NA mode (not
available).
Don't set any mode for only "Cache data modified" event, as it hits a
local modified copy.
Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Leo Yan <leo.yan@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ali Saidi <alisaidi@amazon.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The function parse_events__sort_events_and_fix_groups is needed to fix
uncore events like:
```
$ perf stat -e '{data_read,data_write}' ...
```
so that the multiple uncore PMUs have a group each of data_read and
data_write events.
The same function will perform architecture sorting and group fixing,
in particular for Intel topdown/perf-metric events. Grouping multiple
perf metric events together causes perf_event_open to fail as the
group can only support one. This means command lines like:
```
$ perf stat -e 'slots,slots' ...
```
fail as the slots events are forced into a group together to try to
satisfy the perf-metric event constraints.
As the user may know better than
parse_events__sort_events_and_fix_groups add a 'X' modifier to skip
its regrouping behavior. This allows the following to succeed rather
than fail on the second slots event being opened:
```
$ perf stat -e 'slots,slots:X' -a sleep 1
Performance counter stats for 'system wide':
6,834,154,071 cpu_core/slots/ (50.13%)
5,548,629,453 cpu_core/slots/X (49.87%)
1.002634606 seconds time elapsed
```
Closes: https://lore.kernel.org/lkml/20250822082233.1850417-1-dapeng1.mi@linux.intel.com/
Reported-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Reported-by: Xudong Hao <xudong.hao@intel.com>
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
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: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Yoshihiro Furudera <fj5100bi@fujitsu.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The lzma_is_compressed and gzip_is_compressed functions are declared
to return a "bool" type, but in case of an error (e.g., file open
failure), they incorrectly returned -1.
A bool type is a boolean value that is either true or false.
Returning -1 for a bool return type can lead to unexpected behavior
and may violate strict type-checking in some compilers.
Fix the return value to be false in error cases, ensuring the function
adheres to its declared return type improves for preventing potential
bugs related to type mismatch.
Fixes: 4b57fd44b6 ("perf tools: Add lzma_is_compressed function")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Yunseong Kim <ysk@kzalloc.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephen Brennan <stephen.s.brennan@oracle.com>
Link: https://lore.kernel.org/r/20250822162506.316844-3-ysk@kzalloc.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The second title line which shows symbol and DSO name is broken after
moving to another function at 'callq' instruction.
The ui_browser__show_title() is used for the first line which shows
global sample count and event name so it doesn't change across the
functions.
What it needs after processing 'call' instruction is to update the
second line onlly. Add a comment and call appropriate function.
You can verify the change by pressing ENTER on a 'call' instruction and
then ESC.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The various sample types that are generated are based on the same SPE
sample, just placed into different sample type bins.
The same sample can be in multiple bins if it has flags set that cause
it to be.
Currently we're only applying the --itrace interval downsampling to the
instruction bin, which means that the sample would appear in one bin but
not another if it was skipped due to downsampling.
I don't thing anyone would want or expect this, so make this behave
consistently by applying the downsampling before generating any sample.
You might argue that the "instructions" interval type doesn't make sense
to apply to "memory" sample types because it would be skipping every n
memory samples, rather than every n instructions.
ut the downsampling was already not an instruction interval even for the
instruction samples. SPE has a hardware based sampling interval, and the
instruction interval was just a convenient way to specify further
downsampling.
This is hinted at in the warning message shown for intervals greater
than 1.
This makes SPE diverge from trace technologies like Intel PT and Arm
Coresight.
In those cases instruction samples can be reduced but all branches are
still emitted. This makes sense there, because branches form a complete
execution history, and asking to skip branches every n instructions
doesn't really make sense.
But for SPE, as mentioned above, downsampling the instruction samples
already wasn't consistent with trace technologies so we ended up with
some middle ground that had no benefit.
Now it's possible to reduce the volume of samples in all groups and
samples won't be missing from one group but present in another.
Reviewed-by: Leo Yan <leo.yan@arm.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Tested-by: Leo Yan <leo.yan@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ben Gainey <Ben.Gainey@arm.com>
Cc: George Wort <George.Wort@arm.com>
Cc: Graham Woodward <Graham.Woodward@arm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Williams <Michael.Williams@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
I started seeing this in recent Fedora 42 kernels:
# uname -a
Linux number 6.16.3-200.fc42.x86_64 #1 SMP PREEMPT_DYNAMIC Sat Aug 23 17:02:17 UTC 2025 x86_64 GNU/Linux
#
# perf test vmlinux
1: vmlinux symtab matches kallsyms : FAILED!
#
Rust is enabled and these were the symbols causing the above failure,
i.e. found in vmlinux but not in /proc/kallsyms:
$ grep -w N /proc/kallsyms
0000000000000000 N __pfx__RNCINvNtNtNtCsbDUBuN8AbD4_4core4iter8adapters3map12map_try_foldjNtCs6vVzKs5jPr6_12drm_panic_qr7VersionuINtNtNtBa_3ops12control_flow11ControlFlowB10_ENcB10_0NCINvNvNtNtNtB8_6traits8iterator8Iterator4find5checkB10_NCNvMB12_B10_13from_segments0E0E0B12_
0000000000000000 N _RNCINvNtNtNtCsbDUBuN8AbD4_4core4iter8adapters3map12map_try_foldjNtCs6vVzKs5jPr6_12drm_panic_qr7VersionuINtNtNtBa_3ops12control_flow11ControlFlowB10_ENcB10_0NCINvNvNtNtNtB8_6traits8iterator8Iterator4find5checkB10_NCNvMB12_B10_13from_segments0E0E0B12_
$
So accept those 'N' symbols as well.
About them, from 'man nm':
"N" The symbol is a debugging symbol.
"n" The symbol is in a non-data, non-code, non-debug read-only section.
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
To pick the fixes sent by Namhyung for tools/perf for v6.17-rc5 and get
closer to the other tools code that is used by tools/perf.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Pull vfs fixes from Christian Brauner:
"fuse:
- Prevent opening of non-regular backing files.
Fuse doesn't support non-regular files anyway.
- Check whether copy_file_range() returns a larger size than
requested.
- Prevent overflow in copy_file_range() as fuse currently only
supports 32-bit sized copies.
- Cache the blocksize value if the server returned a new value as
inode->i_blkbits isn't modified directly anymore.
- Fix i_blkbits handling for iomap partial writes.
By default i_blkbits is set to PAGE_SIZE which causes iomap to mark
the whole folio as uptodate even on a partial write. But fuseblk
filesystems support choosing a blocksize smaller than PAGE_SIZE
risking data corruption. Simply enforce PAGE_SIZE as blocksize for
fuseblk's internal inode for now.
- Prevent out-of-bounds acces in fuse_dev_write() when the number of
bytes to be retrieved is truncated to the fc->max_pages limit.
virtiofs:
- Fix page faults for DAX page addresses.
Misc:
- Tighten file handle decoding from userns.
Check that the decoded dentry itself has a valid idmapping in the
user namespace.
- Fix mount-notify selftests.
- Fix some indentation errors.
- Add an FMODE_ flag to indicate IOCB_HAS_METADATA availability.
This will be moved to an FOP_* flag with a bit more rework needed
for that to happen not suitable for a fix.
- Don't silently ignore metadata for sync read/write.
- Don't pointlessly log warning when reading coredump sysctls"
* tag 'vfs-6.17-rc6.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
fuse: virtio_fs: fix page fault for DAX page address
selftests/fs/mount-notify: Fix compilation failure.
fhandle: use more consistent rules for decoding file handle from userns
fuse: Block access to folio overlimit
fuse: fix fuseblk i_blkbits for iomap partial writes
fuse: reflect cached blocksize if blocksize was changed
fuse: prevent overflow in copy_file_range return value
fuse: check if copy_file_range() returns larger than requested size
fuse: do not allow mapping a non-regular backing file
coredump: don't pointlessly check and spew warnings
fs: fix indentation style
block: don't silently ignore metadata for sync read/write
fs: add a FMODE_ flag to indicate IOCB_HAS_METADATA availability
Please enter a commit message to explain why this merge is necessary,
especially if it merges an updated upstream into a topic branch.
Pull i2c fixes from Wolfram Sang:
- i801: drop superfluous WDT entry for Birch
- rtl9300:
- fix channel number check in probe
- check data length boundaries in xfer
- drop broken SMBus quick operation
* tag 'i2c-for-6.17-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux:
i2c: rtl9300: remove broken SMBus Quick operation support
i2c: rtl9300: ensure data length is within supported range
i2c: rtl9300: fix channel number bound check
i2c: i801: Hide Intel Birch Stream SoC TCO WDT
Pull EDAC fix from Borislav Petkov:
- Remove a misplaced dma_free_coherent() call in altera_edac
* tag 'edac_urgent_for_v6.17_rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras:
EDAC/altera: Delete an inappropriate dma_free_coherent() call
Pull timer fix from Ingo Molnar:
"Fix a severe slowdown regression in the timer vDSO code related to the
while() loop in __iter_div_u64_rem(), when the AUX-clock is enabled"
* tag 'timers-urgent-2025-09-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
vdso/vsyscall: Avoid slow division loop in auxiliary clock update
Pull locking fix from Ingo Molnar:
"Fix an 'allocation from atomic context' regression in the futex
vmalloc variant"
* tag 'locking-urgent-2025-09-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
futex: Move futex_hash_free() back to __mmput()
Pull perf event fix from Ingo Molnar:
"Fix regression where PERF_EVENT_IOC_REFRESH counters miss a PMU-stop"
* tag 'perf-urgent-2025-09-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf: Fix the POLL_HUP delivery breakage
Pull RISC-V fixes from Paul Walmsley:
- LTO fix for clang when building with CONFIG_CMODEL_MEDLOW
- Fix for ACPI CPPC CSR read/write return values
- Several fixes for incorrect access widths in thread_info.cpu reads
- Fix an issue in __put_user_nocheck() that was causing the glibc
tst-socket-timestamp test to fail
- Initialize struct kexec_buf records in several kexec-related
functions, which were generating UBSAN warnings
- Two fixes for sparse warnings
* tag 'riscv-for-linus-6.17-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux:
riscv: Fix sparse warning about different address spaces
riscv: Fix sparse warning in __get_user_error()
riscv: kexec: Initialize kexec_buf struct
riscv: use lw when reading int cpu in asm_per_cpu
riscv, bpf: use lw when reading int cpu in bpf_get_smp_processor_id
riscv, bpf: use lw when reading int cpu in BPF_MOV64_PERCPU_REG
riscv: uaccess: fix __put_user_nocheck for unaligned accesses
riscv: use lw when reading int cpu in new_vmalloc_check
ACPI: RISC-V: Fix FFH_CPPC_CSR error handling
riscv: Only allow LTO with CMODEL_MEDANY
Pull rust fixes from Miguel Ojeda:
- Two changes to prepare for the future Rust 1.91.0 release (expected
2025-10-30, currently in nightly): a target specification format
change and a renamed, soon-to-be-stabilized 'core' function.
* tag 'rust-fixes-6.17-2' of git://git.kernel.org/pub/scm/linux/kernel/git/ojeda/linux:
rust: support Rust >= 1.91.0 target spec
rust: use the new name Location::file_as_c_str() in Rust >= 1.91.0
i2c-host-fixes for v6.17-rc5
- i801: fix device IDs
- in rtl9300:
- fix channel number check in probe
- check data length boundaries in xfer
- drop unsupported SMBus quick operation
Pull perf tools fixes from Namhyung Kim:
"Fixes for use-after-free that resulted in segfaults after merging the
bpf tree.
Also a couple of build and test fixes"
* tag 'perf-tools-fixes-for-v6.17-2025-09-05' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools:
perf symbol-elf: Add support for the block argument for libbfd
perf test: Checking BPF metadata collection fails on version string
perf tests: Fix "PE file support" test build
perf bpf-utils: Harden get_bpf_prog_info_linear
perf bpf-utils: Constify bpil_array_desc
perf bpf-event: Fix use-after-free in synthesis
The kexec_buf structure was previously declared without initialization.
commit bf454ec31a ("kexec_file: allow to place kexec_buf randomly")
added a field that is always read but not consistently populated by all
architectures. This un-initialized field will contain garbage.
This is also triggering a UBSAN warning when the uninitialized data was
accessed:
------------[ cut here ]------------
UBSAN: invalid-load in ./include/linux/kexec.h:210:10
load of value 252 is not a valid value for type '_Bool'
Zero-initializing kexec_buf at declaration ensures all fields are
cleanly set, preventing future instances of uninitialized memory being
used.
Fixes: bf454ec31a ("kexec_file: allow to place kexec_buf randomly")
Signed-off-by: Breno Leitao <leitao@debian.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250827-kbuf_all-v1-2-1df9882bb01a@debian.org
Signed-off-by: Paul Walmsley <pjw@kernel.org>
The type of the value to write should be determined by the size of the
destination, not by the value itself, which may be a constant. This
aligns the behavior with x86_64, where __typeof__(*(__gu_ptr)) is used
to infer the correct type.
This fixes an issue in put_cmsg, which was only writing 4 out of 8
bytes to the cmsg_len field, causing the glibc tst-socket-timestamp test
to fail.
Fixes: ca1a66cdd6 ("riscv: uaccess: do not do misaligned accesses in get/put_user()")
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250724220853.1969954-1-aurelien@aurel32.net
Signed-off-by: Paul Walmsley <pjw@kernel.org>
Ilkka Koskinen