While testing building with libunwind (using LIBUNWIND=1) in various
arches I noticed a problem on arm64, on an rpi5 system, a missing close
parens in a change related to dso__data_get_fd() usage, fix it.
Fixes: 5ac22c35aa ("perf dso: Use lock annotations to fix asan deadlock")
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: https://lore.kernel.org/r/Z_Z3o8KvB2i5c6ab@x1
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
To pick up the changes in:
2981557cb0 x86,kcfi: Fix EXPORT_SYMBOL vs kCFI
That required adding a copy of include/linux/cfi_types.h and its checking
in tools/perf/check-headers.h.
Addressing this perf tools build warning:
Warning: Kernel ABI header differences:
diff -u tools/arch/x86/lib/memset_64.S arch/x86/lib/memset_64.S
Please see tools/include/uapi/README for further details.
Acked-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Cc: x86@kernel.org
Link: https://lore.kernel.org/r/20250410001125.391820-11-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
To pick up the changes in:
c4a16820d9 fs: add open_tree_attr()
2df1ad0d25 x86/arch_prctl: Simplify sys_arch_prctl()
e632bca07c arm64: generate 64-bit syscall.tbl
This is basically to support the new open_tree_attr syscall. But it
also needs to update asm-generic unistd.h header to get the new syscall
number. And arm64 unistd.h header was converted to use the generic
64-bit header.
Addressing this perf tools build warning:
Warning: Kernel ABI header differences:
diff -u tools/scripts/syscall.tbl scripts/syscall.tbl
diff -u tools/perf/arch/x86/entry/syscalls/syscall_32.tbl arch/x86/entry/syscalls/syscall_32.tbl
diff -u tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl
diff -u tools/perf/arch/powerpc/entry/syscalls/syscall.tbl arch/powerpc/kernel/syscalls/syscall.tbl
diff -u tools/perf/arch/s390/entry/syscalls/syscall.tbl arch/s390/kernel/syscalls/syscall.tbl
diff -u tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl arch/mips/kernel/syscalls/syscall_n64.tbl
diff -u tools/perf/arch/arm/entry/syscalls/syscall.tbl arch/arm/tools/syscall.tbl
diff -u tools/perf/arch/sh/entry/syscalls/syscall.tbl arch/sh/kernel/syscalls/syscall.tbl
diff -u tools/perf/arch/sparc/entry/syscalls/syscall.tbl arch/sparc/kernel/syscalls/syscall.tbl
diff -u tools/perf/arch/xtensa/entry/syscalls/syscall.tbl arch/xtensa/kernel/syscalls/syscall.tbl
diff -u tools/arch/arm64/include/uapi/asm/unistd.h arch/arm64/include/uapi/asm/unistd.h
diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h
Please see tools/include/uapi/README for further details.
Acked-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Cc: linux-arch@vger.kernel.org
Link: https://lore.kernel.org/r/20250410001125.391820-6-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
To pick up the changes in:
64e844505b include: uapi: protocol number and packet structs for AGGFRAG in ESP
18912c5206 tcp: devmem: don't write truncated dmabuf CMSGs to userspace
Addressing this perf tools build warning:
Warning: Kernel ABI header differences:
diff -u tools/include/uapi/linux/in.h include/uapi/linux/in.h
diff -u tools/perf/trace/beauty/include/linux/socket.h include/linux/socket.h
Please see tools/include/uapi/README for further details.
Acked-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Cc: netdev@vger.kernel.org
Link: https://lore.kernel.org/r/20250410001125.391820-3-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
In 7cecb7fe83 ("perf hists: Move sort__has_comm into struct
perf_hpp_list") it assumes that act->thread is set prior to calling
do_zoom_thread().
This doesn't happen when we use ESC or the Left arrow key to Zoom out of
a specific thread, making this operation not to work and we get stuck
into the thread zoom.
In 6422184b08 ("perf hists browser: Simplify zooming code using
pstack_peek()") it says no need to set actions->thread, and at that
point that was true, but in 7cecb7fe83 a actions->thread == NULL
check was added before the zoom out of thread could kick in.
We can zoom out using the alternative 't' thread zoom toggle hotkey to
finally set actions->thread before calling do_zoom_thread() and zoom
out, but lets also fix the ESC/Zoom out of thread case.
Fixes: 7cecb7fe83 ("perf hists: Move sort__has_comm into struct perf_hpp_list")
Reported-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Ingo Molnar <mingo@kernel.org>
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: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/Z_TYux5fUg2pW-pF@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
In the past (like before 2015) we had the familiar workflow of using
ENTER to get the menu and then zoom on a pid or DSO, kernel, etc and
then use UP and DOWN to navigate further, etc, and then when wanting to
go to the previous level, i.e. to Zoom out, use the LEFT arrow key.
This way the right hand stays in the arrow keys block that is near the
enter and we can go around real quickly.
But then, when we started supporting horizontal scrolling by columns to
support things like 'perf c2c report' that has lots of columns, we
switched to using the LEFT key exclusively for that, horizontal
scrolling, requiring the user to press 'm' to get a "context menu" that
then would allow users to select the Zoom out operation.
Ingo recently reported this as not intuitive, which is true, so lets
overload the LEFT key with both meanings, by doing a Zoom out operation
if the LEFT key is pressed when we're on the first column, but use it
also for horizontal scrolling if it is pressed when the cursor is on
column > 1.
Reported-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Ingo Molnar <mingo@kernel.org>
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: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/Z_TYux5fUg2pW-pF@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Ingo reported that having a visual cue if the source code view is
enabled will help in noticing a bug when no source is presented.
Change the title scnprintf routine for the annotation browser to do
that.
More work is needed to have the capabilities of the existing
disassemblers listed somehow and start using the fastest one but switch
to another that provides features only made available by some particular
one, like the first one, the objdump output parsing one.
Suggested-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Ingo Molnar <mingo@kernel.org>
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: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/Z_TYux5fUg2pW-pF@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
There are still some cases, for instance to disassembly BPF code that
needs this, so until someone works on supporting that, we're keeping the
code but it is opt-in.
Make that clear on the 'perf version --build-options' and other ways to
query if a feature is present:
$ perf check feature libbfd
libbfd: [ OFF ] # HAVE_LIBBFD_SUPPORT ( tip: Deprecated, license incompatibility, use BUILD_NONDISTRO=1 and install binutils-dev[el] )
$ perf -vv | grep bfd
libbfd: [ OFF ] # HAVE_LIBBFD_SUPPORT ( tip: Deprecated, license incompatibility, use BUILD_NONDISTRO=1 and install binutils-dev[el] )
$
Tested-by: Ingo Molnar <mingo@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/Z_dkNDj9EPFwPqq1@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
While working on 'perf version --build-options' I noticed that:
$ perf version --build-options
perf version 6.15.rc1.g312a07a00d31
aio: [ on ] # HAVE_AIO_SUPPORT
bpf: [ on ] # HAVE_LIBBPF_SUPPORT
bpf_skeletons: [ on ] # HAVE_BPF_SKEL
debuginfod: [ OFF ] # HAVE_DEBUGINFOD_SUPPORT
<SNIP>
And looking at tools/perf/Makefile.config I also noticed that it is not
opt-in, meaning we will attempt to build with it in all normal cases.
So add the usual warning at build time to let the user know that
something recommended is missing, now we see:
Makefile.config:563: No elfutils/debuginfod.h found, no debuginfo server support, please install elfutils-debuginfod-client-devel or equivalent
And after following the recommendation:
$ perf check feature debuginfod
debuginfod: [ on ] # HAVE_DEBUGINFOD_SUPPORT
$ ldd ~/bin/perf | grep debuginfo
libdebuginfod.so.1 => /lib64/libdebuginfod.so.1 (0x00007fee5cf5f000)
$
With this feature on several perf tools will fetch what is needed and
not require all the contents of the debuginfo packages, for instance:
# rpm -qa | grep kernel-debuginfo
# pahole --running_kernel_vmlinux
pahole: couldn't find a vmlinux that matches the running kernel
HINT: Maybe you're inside a container or missing a debuginfo package?
#
# perf trace -e open* perf probe --vars icmp_rcv
0.000 ( 0.005 ms): perf/97391 openat(dfd: CWD, filename: "/etc/ld.so.cache", flags: RDONLY|CLOEXEC) = 3
0.014 ( 0.004 ms): perf/97391 openat(dfd: CWD, filename: "/lib64/libm.so.6", flags: RDONLY|CLOEXEC) = 3
<SNIP>
32130.100 ( 0.008 ms): perf/97391 openat(dfd: CWD, filename: "/root/.cache/debuginfod_client/aa3c82b4a13f9c0e0301bebb20fe958c4db6f362/debuginfo") = 3
<SNIP>
Available variables at icmp_rcv
@<icmp_rcv+0>
struct sk_buff* skb
<SNIP>
#
# pahole --running_kernel_vmlinux
/root/.cache/debuginfod_client/aa3c82b4a13f9c0e0301bebb20fe958c4db6f362/debuginfo
# file /root/.cache/debuginfod_client/aa3c82b4a13f9c0e0301bebb20fe958c4db6f362/debuginfo
/root/.cache/debuginfod_client/aa3c82b4a13f9c0e0301bebb20fe958c4db6f362/debuginfo: ELF 64-bit LSB executable, x86-64, version 1 (SYSV), statically linked, BuildID[sha1]=aa3c82b4a13f9c0e0301bebb20fe958c4db6f362, with debug_info, not stripped
# ls -la /root/.cache/debuginfod_client/aa3c82b4a13f9c0e0301bebb20fe958c4db6f362/debuginfo
-r--------. 1 root root 475401512 Mar 27 21:00 /root/.cache/debuginfod_client/aa3c82b4a13f9c0e0301bebb20fe958c4db6f362/debuginfo
#
Then, cached:
# perf stat --null perf probe --vars icmp_rcv
Available variables at icmp_rcv
@<icmp_rcv+0>
struct sk_buff* skb
Performance counter stats for 'perf probe --vars icmp_rcv':
0.671389041 seconds time elapsed
0.519176000 seconds user
0.150860000 seconds sys
Fixes: c7a14fdcb3 ("perf build-ids: Fall back to debuginfod query if debuginfo not found")
Tested-by: Ingo Molnar <mingo@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Link: https://lore.kernel.org/r/Z_dkNDj9EPFwPqq1@gmail.com
[ Folded patch from Ingo to have the debian/ubuntu devel package added build warning message ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Ingo reported that it was difficult to understand why libunwind support
didn't link even when he had the usual libunwind-dev files installed in
his machine.
This is because libunwind became opt-in, the user has to use
LIBUNWIND=1, as it was deemed stalled in its development/unsuitable for
use with perf, IIRC, and so we better use the elfutils equivalent
routine that we also supported for ages.
But the build message still printed:
Auto-detecting system features:
... libdw: [ on ]
... glibc: [ on ]
<SNIP>
... libcrypto: [ on ]
... libunwind: [ OFF ]
<SNIP>
Which is confusing, so allow for having a tip when 'perf version
--build-options' is used, and variants with 'perf check feature':
$ perf version --build-options | grep libunwind
libunwind: [ OFF ] # HAVE_LIBUNWIND_SUPPORT ( tip: Deprecated, use LIBUNWIND=1 and install libunwind-dev[el] to build with it )
$
$ perf check feature libunwind
libunwind: [ OFF ] # HAVE_LIBUNWIND_SUPPORT ( tip: Deprecated, use LIBUNWIND=1 and install libunwind-dev[el] to build with it )
$
The next patches will remove the opt-in libunwind FEATURES_DISPLAY.
Reported-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Ingo Molnar <mingo@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Howard Chu <howardchu95@gmail.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: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/Z--pWmTHGb62_83e@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Both had the same open coded functions, share them so that we can add
tips for opt-in features such as libunwind, coresight, etc.
Examples of use:
$ perf check feature libcapstone
libcapstone: [ on ] # HAVE_LIBCAPSTONE_SUPPORT
$ perf check feature libunwind
libunwind: [ OFF ] # HAVE_LIBUNWIND_SUPPORT
$ perf version --build-options
perf version 6.15.rc1.g113e3df8ccc5
aio: [ on ] # HAVE_AIO_SUPPORT
bpf: [ on ] # HAVE_LIBBPF_SUPPORT
bpf_skeletons: [ on ] # HAVE_BPF_SKEL
debuginfod: [ OFF ] # HAVE_DEBUGINFOD_SUPPORT
dwarf: [ on ] # HAVE_LIBDW_SUPPORT
dwarf_getlocations: [ on ] # HAVE_LIBDW_SUPPORT
dwarf-unwind: [ on ] # HAVE_DWARF_UNWIND_SUPPORT
auxtrace: [ on ] # HAVE_AUXTRACE_SUPPORT
libbfd: [ OFF ] # HAVE_LIBBFD_SUPPORT
libcapstone: [ on ] # HAVE_LIBCAPSTONE_SUPPORT
libcrypto: [ on ] # HAVE_LIBCRYPTO_SUPPORT
libdw-dwarf-unwind: [ on ] # HAVE_LIBDW_SUPPORT
libelf: [ on ] # HAVE_LIBELF_SUPPORT
libnuma: [ on ] # HAVE_LIBNUMA_SUPPORT
libopencsd: [ on ] # HAVE_CSTRACE_SUPPORT
libperl: [ on ] # HAVE_LIBPERL_SUPPORT
libpfm4: [ on ] # HAVE_LIBPFM
libpython: [ on ] # HAVE_LIBPYTHON_SUPPORT
libslang: [ on ] # HAVE_SLANG_SUPPORT
libtraceevent: [ on ] # HAVE_LIBTRACEEVENT
libunwind: [ OFF ] # HAVE_LIBUNWIND_SUPPORT
lzma: [ on ] # HAVE_LZMA_SUPPORT
numa_num_possible_cpus: [ on ] # HAVE_LIBNUMA_SUPPORT
zlib: [ on ] # HAVE_ZLIB_SUPPORT
zstd: [ on ] # HAVE_ZSTD_SUPPORT
$
Tested-by: Ingo Molnar <mingo@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/Z_Rz10stoLzBocIO@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The tools/build/feature/test-all.c file tries to detect the expected,
most common set of libraries/features we expect to have available to
build perf with.
At some point libunwind was deemed not to be part of that set of
libries, but the patches making it to be opt-in ended up forgetting some
details, fix one more.
Testing it:
$ rm -rf /tmp/build/$(basename $PWD)/ ; mkdir -p /tmp/build/$(basename $PWD)/
$ rpm -q libunwind-devel
libunwind-devel-1.8.0-3.fc40.x86_64
$ make -k LIBUNWIND=1 CORESIGHT=1 O=/tmp/build/$(basename $PWD)/ -C tools/perf install-bin |& grep unwind && ldd ~/bin/perf | grep unwind
... libunwind: [ on ]
CC /tmp/build/perf-tools-next/arch/x86/tests/dwarf-unwind.o
CC /tmp/build/perf-tools-next/arch/x86/util/unwind-libunwind.o
CC /tmp/build/perf-tools-next/util/arm64-frame-pointer-unwind-support.o
CC /tmp/build/perf-tools-next/tests/dwarf-unwind.o
CC /tmp/build/perf-tools-next/util/unwind-libunwind-local.o
CC /tmp/build/perf-tools-next/util/unwind-libunwind.o
libunwind-x86_64.so.8 => /lib64/libunwind-x86_64.so.8 (0x00007f615a549000)
libunwind.so.8 => /lib64/libunwind.so.8 (0x00007f615a52f000)
$ sudo rpm -e libunwind-devel
$ rm -rf /tmp/build/$(basename $PWD)/ ; mkdir -p /tmp/build/$(basename $PWD)/
$ make -k LIBUNWIND=1 CORESIGHT=1 O=/tmp/build/$(basename $PWD)/ -C tools/perf install-bin |& grep unwind && ldd ~/bin/perf | grep unwind
Makefile.config:653: No libunwind found. Please install libunwind-dev[el] >= 1.1 and/or set LIBUNWIND_DIR
... libunwind: [ OFF ]
CC /tmp/build/perf-tools-next/arch/x86/tests/dwarf-unwind.o
CC /tmp/build/perf-tools-next/arch/x86/util/unwind-libdw.o
CC /tmp/build/perf-tools-next/util/arm64-frame-pointer-unwind-support.o
CC /tmp/build/perf-tools-next/tests/dwarf-unwind.o
CC /tmp/build/perf-tools-next/util/unwind-libdw.o
$
Should be in a separate patch, but tired now, so also adding a message
about the need to use LIBUNWIND=1 in the output when its not available,
so done here as well.
So, now when the devel files are not available we get:
$ make -k LIBUNWIND=1 CORESIGHT=1 O=/tmp/build/$(basename $PWD)/ -C tools/perf install-bin |& grep unwind && ldd ~/bin/perf | grep unwind
Makefile.config:653: No libunwind found. Please install libunwind-dev[el] >= 1.1 and/or set LIBUNWIND_DIR and set LIBUNWIND=1 in the make command line as it is opt-in now
... libunwind: [ OFF ]
$
Fixes: 13e17c9ff4 ("perf build: Make libunwind opt-in rather than opt-out")
Reported-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Ingo Molnar <mingo@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Ian Rogers <irogers@google.com>
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>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/Z_AnsW9oJzFbhIFC@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Pull perf tools updates from Namhyung Kim:
"perf record:
- Introduce latency profiling using scheduler information.
The latency profiling is to show impacts on wall-time rather than
cpu-time. By tracking context switches, it can weight samples and
find which part of the code contributed more to the execution
latency.
The value (period) of the sample is weighted by dividing it by the
number of parallel execution at the moment. The parallelism is
tracked in perf report with sched-switch records. This will reduce
the portion that are run in parallel and in turn increase the
portion of serial executions.
For now, it's limited to profile processes, IOW system-wide
profiling is not supported. You can add --latency option to enable
this.
$ perf record --latency -- make -C tools/perf
I've run the above command for perf build which adds -j option to
make with the number of CPUs in the system internally. Normally
it'd show something like below:
$ perf report -F overhead,comm
...
#
# Overhead Command
# ........ ...............
#
78.97% cc1
6.54% python3
4.21% shellcheck
3.28% ld
1.80% as
1.37% cc1plus
0.80% sh
0.62% clang
0.56% gcc
0.44% perl
0.39% make
...
The cc1 takes around 80% of the overhead as it's the actual
compiler. However it runs in parallel so its contribution to
latency may be less than that. Now, perf report will show both
overhead and latency (if --latency was given at record time) like
below:
$ perf report -s comm
...
#
# Overhead Latency Command
# ........ ........ ...............
#
78.97% 48.66% cc1
6.54% 25.68% python3
4.21% 0.39% shellcheck
3.28% 13.70% ld
1.80% 2.56% as
1.37% 3.08% cc1plus
0.80% 0.98% sh
0.62% 0.61% clang
0.56% 0.33% gcc
0.44% 1.71% perl
0.39% 0.83% make
...
You can see latency of cc1 goes down to around 50% and python3 and
ld contribute a lot more than their overhead. You can use --latency
option in perf report to get the same result but ordered by
latency.
$ perf report --latency -s comm
perf report:
- As a side effect of the latency profiling work, it adds a new
output field 'latency' and a sort key 'parallelism'. The below is a
result from my system with 64 CPUs. The build was well-parallelized
but contained some serial portions.
$ perf report -s parallelism
...
#
# Overhead Latency Parallelism
# ........ ........ ...........
#
16.95% 1.54% 62
13.38% 1.24% 61
12.50% 70.47% 1
11.81% 1.06% 63
7.59% 0.71% 60
4.33% 12.20% 2
3.41% 0.33% 59
2.05% 0.18% 64
1.75% 1.09% 9
1.64% 1.85% 5
...
- Support Feodra mini-debuginfo which is a LZMA compressed symbol
table inside ".gnu_debugdata" ELF section.
perf annotate:
- Add --code-with-type option to enable data-type profiling with the
usual annotate output.
Instead of focusing on data structure, it shows code annotation
together with data type it accesses in case the instruction refers
to a memory location (and it was able to resolve the target data
type). Currently it only works with --stdio.
$ perf annotate --stdio --code-with-type
...
Percent | Source code & Disassembly of vmlinux for cpu/mem-loads,ldlat=30/pp (18 samples, percent: local period)
----------------------------------------------------------------------------------------------------------------------
: 0 0xffffffff81050610 <__fdget>:
0.00 : ffffffff81050610: callq 0xffffffff81c01b80 <__fentry__> # data-type: (stack operation)
0.00 : ffffffff81050615: pushq %rbp # data-type: (stack operation)
0.00 : ffffffff81050616: movq %rsp, %rbp
0.00 : ffffffff81050619: pushq %r15 # data-type: (stack operation)
0.00 : ffffffff8105061b: pushq %r14 # data-type: (stack operation)
0.00 : ffffffff8105061d: pushq %rbx # data-type: (stack operation)
0.00 : ffffffff8105061e: subq $0x10, %rsp
0.00 : ffffffff81050622: movl %edi, %ebx
0.00 : ffffffff81050624: movq %gs:0x7efc4814(%rip), %rax # 0x14e40 <current_task> # data-type: struct task_struct* +0
0.00 : ffffffff8105062c: movq 0x8d0(%rax), %r14 # data-type: struct task_struct +0x8d0 (files)
0.00 : ffffffff81050633: movl (%r14), %eax # data-type: struct files_struct +0 (count.counter)
0.00 : ffffffff81050636: cmpl $0x1, %eax
0.00 : ffffffff81050639: je 0xffffffff810506a9 <__fdget+0x99>
0.00 : ffffffff8105063b: movq 0x20(%r14), %rcx # data-type: struct files_struct +0x20 (fdt)
0.00 : ffffffff8105063f: movl (%rcx), %eax # data-type: struct fdtable +0 (max_fds)
0.00 : ffffffff81050641: cmpl %ebx, %eax
0.00 : ffffffff81050643: jbe 0xffffffff810506ef <__fdget+0xdf>
0.00 : ffffffff81050649: movl %ebx, %r15d
5.56 : ffffffff8105064c: movq 0x8(%rcx), %rdx # data-type: struct fdtable +0x8 (fd)
...
The "# data-type:" part was added with this change. The first few
entries are not very interesting. But later you can it accesses a
couple of fields in the task_struct, files_struct and fdtable.
perf trace:
- Support syscall tracing for different ABI. For example it can trace
system calls for 32-bit applications on 64-bit kernel
transparently.
- Add --summary-mode=total option to show global syscall summary. The
default is 'thread' to show per-thread syscall summary.
Python support:
- Add more interfaces to 'perf' module to parse events, and config,
enable or disable the event list properly so that it can implement
basic functionalities purely in Python. There is an example code
for these new interfaces in python/tracepoint.py.
- Add mypy and pylint support to enable build time checking. Fix some
code based on the findings from these tools.
Internals:
- Introduce io_dir__readdir() API to make directory traveral (usually
for proc or sysfs) efficient with less memory footprint.
JSON vendor events:
- Add events and metrics for ARM Neoverse N3 and V3
- Update events and metrics on various Intel CPUs
- Add/update events for a number of SiFive processors"
* tag 'perf-tools-for-v6.15-2025-03-27' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (229 commits)
perf bpf-filter: Fix a parsing error with comma
perf report: Fix a memory leak for perf_env on AMD
perf trace: Fix wrong size to bpf_map__update_elem call
perf tools: annotate asm_pure_loop.S
perf python: Fix setup.py mypy errors
perf test: Address attr.py mypy error
perf build: Add pylint build tests
perf build: Add mypy build tests
perf build: Rename TEST_LOGS to SHELL_TEST_LOGS
tools/build: Don't pass test log files to linker
perf bench sched pipe: fix enforced blocking reads in worker_thread
perf tools: Fix is_compat_mode build break in ppc64
perf build: filter all combinations of -flto for libperl
perf vendor events arm64 AmpereOneX: Fix frontend_bound calculation
perf vendor events arm64: AmpereOne/AmpereOneX: Mark LD_RETIRED impacted by errata
perf trace: Fix evlist memory leak
perf trace: Fix BTF memory leak
perf trace: Make syscall table stable
perf syscalltbl: Mask off ABI type for MIPS system calls
perf build: Remove Makefile.syscalls
...
The previous change to support cgroup filters introduced a bug that
pathname can include commas. It confused the lexer to treat an item and
the trailing comma as a single token. And it resulted in a parse error:
$ sudo perf record -e cycles:P --filter 'period > 0, ip > 64' -- true
perf_bpf_filter: Error: Unexpected item: 0,
perf_bpf_filter: syntax error, unexpected BFT_ERROR, expecting BFT_NUM
Usage: perf record [<options>] [<command>]
or: perf record [<options>] -- <command> [<options>]
--filter <filter>
event filter
It should get "0" and "," separately.
An easiest fix would be to remove "," from the possible pathname
characters. As it's for cgroup names, probably ok to assume it won't
have commas in the pathname.
I found that the existing BPF filtering test didn't have any complex
filter condition with commas. Let's update the group filter test which
is supposed to test filter combinations like this.
Link: https://lore.kernel.org/r/20250307220922.434319-1-namhyung@kernel.org
Fixes: 91e88437d5 ("perf bpf-filter: Support filtering on cgroups")
Reported-by: Sally Shi <sshii@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
The env.pmu_mapping can be leaked when it reads data from a pipe on AMD.
For a pipe data, it reads the header data including pmu_mapping from
PERF_RECORD_HEADER_FEATURE runtime. But it's already set in:
perf_session__new()
__perf_session__new()
evlist__init_trace_event_sample_raw()
evlist__has_amd_ibs()
perf_env__nr_pmu_mappings()
Then it'll overwrite that when it processes the HEADER_FEATURE record.
Here's a report from address sanitizer.
Direct leak of 2689 byte(s) in 1 object(s) allocated from:
#0 0x7fed8f814596 in realloc ../../../../src/libsanitizer/lsan/lsan_interceptors.cpp:98
#1 0x5595a7d416b1 in strbuf_grow util/strbuf.c:64
#2 0x5595a7d414ef in strbuf_init util/strbuf.c:25
#3 0x5595a7d0f4b7 in perf_env__read_pmu_mappings util/env.c:362
#4 0x5595a7d12ab7 in perf_env__nr_pmu_mappings util/env.c:517
#5 0x5595a7d89d2f in evlist__has_amd_ibs util/amd-sample-raw.c:315
#6 0x5595a7d87fb2 in evlist__init_trace_event_sample_raw util/sample-raw.c:23
#7 0x5595a7d7f893 in __perf_session__new util/session.c:179
#8 0x5595a7b79572 in perf_session__new util/session.h:115
#9 0x5595a7b7e9dc in cmd_report builtin-report.c:1603
#10 0x5595a7c019eb in run_builtin perf.c:351
#11 0x5595a7c01c92 in handle_internal_command perf.c:404
#12 0x5595a7c01deb in run_argv perf.c:448
#13 0x5595a7c02134 in main perf.c:556
#14 0x7fed85833d67 in __libc_start_call_main ../sysdeps/nptl/libc_start_call_main.h:58
Let's free the existing pmu_mapping data if any.
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20250311000416.817631-1-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
In linux-next
commit c760174401 ("perf cpumap: Reduce cpu size from int to int16_t")
causes the perf tests 100 126 to fail on s390:
Output before:
# ./perf test 100
100: perf trace BTF general tests : FAILED!
#
The root cause is the change from int to int16_t for the
cpu maps. The size of the CPU key value pair changes from
four bytes to two bytes. However a two byte key size is
not supported for bpf_map__update_elem().
Note: validate_map_op() in libbpf.c emits warning
libbpf: map '__augmented_syscalls__': \
unexpected key size 2 provided, expected 4
when key size is set to int16_t.
Therefore change to variable size back to 4 bytes for
invocation of bpf_map__update_elem().
Output after:
# ./perf test 100
100: perf trace BTF general tests : Ok
#
Fixes: c760174401 ("perf cpumap: Reduce cpu size from int to int16_t")
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Acked-by: Howard Chu <howardchu95@gmail.com>
Cc: James Clark <james.clark@linaro.org>
Link: https://lore.kernel.org/r/20250324152756.3879571-1-tmricht@linux.ibm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
If PYLINT=1 is passed to the build then run pylint over python code in
perf. Unlike shellcheck this isn't default on as there are currently
too many errors.
An example of an error:
```
************* Module setup
util/setup.py:19:0: C0301: Line too long (127/100) (line-too-long)
util/setup.py:20:0: C0301: Line too long (138/100) (line-too-long)
util/setup.py:63:0: C0301: Line too long (106/100) (line-too-long)
util/setup.py:1:0: C0114: Missing module docstring (missing-module-docstring)
util/setup.py:24:4: W0622: Redefining built-in 'vars' (redefined-builtin)
util/setup.py:11:4: C0103: Constant name "cc_options" doesn't conform to UPPER_CASE naming style (invalid-name)
util/setup.py:13:4: C0103: Constant name "cc_options" doesn't conform to UPPER_CASE naming style (invalid-name)
util/setup.py:15:34: R1732: Consider using 'with' for resource-allocating operations (consider-using-with)
util/setup.py:18:0: C0116: Missing function or method docstring (missing-function-docstring)
util/setup.py:19:16: R1732: Consider using 'with' for resource-allocating operations (consider-using-with)
util/setup.py:44:0: C0413: Import "from setuptools import setup, Extension" should be placed at the top of the module (wrong-import-position)
util/setup.py:46:0: C0413: Import "from setuptools.command.build_ext import build_ext as _build_ext" should be placed at the top of the module (wrong-import-position)
util/setup.py:47:0: C0413: Import "from setuptools.command.install_lib import install_lib as _install_lib" should be placed at the top of the module (wrong-import-position)
util/setup.py:49:0: C0115: Missing class docstring (missing-class-docstring)
util/setup.py:49:0: C0103: Class name "build_ext" doesn't conform to PascalCase naming style (invalid-name)
util/setup.py:52:8: W0201: Attribute 'build_lib' defined outside __init__ (attribute-defined-outside-init)
util/setup.py:53:8: W0201: Attribute 'build_temp' defined outside __init__ (attribute-defined-outside-init)
util/setup.py:55:0: C0115: Missing class docstring (missing-class-docstring)
util/setup.py:55:0: C0103: Class name "install_lib" doesn't conform to PascalCase naming style (invalid-name)
util/setup.py:58:8: W0201: Attribute 'build_dir' defined outside __init__ (attribute-defined-outside-init)
*-----------------------------------------------------------------
Your code has been rated at 6.67/10 (previous run: 6.51/10, +0.16)
make[4]: *** [util/Build:442: util/setup.py.pylint_log] Error 1
```
Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250311213628.569562-5-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
If MYPY=1 is passed to the build then run mypy over python code in
perf. Unlike shellcheck this isn't default on as there are currently
too many errors.
An example of an error:
```
util/setup.py:8: error: Item "None" of "str | None" has no attribute "split" [union-attr]
util/setup.py:15: error: Item "None" of "IO[bytes] | None" has no attribute "readline" [union-attr]
util/setup.py:15: error: List item 0 has incompatible type "str | None"; expected "str | bytes | PathLike[str] | PathLike[bytes]" [list-item]
util/setup.py:16: error: Unsupported left operand type for + ("None") [operator]
util/setup.py:16: note: Left operand is of type "str | None"
util/setup.py:74: error: Unsupported left operand type for + ("None") [operator]
util/setup.py:74: note: Left operand is of type "str | None"
Found 5 errors in 1 file (checked 1 source file)
make[4]: *** [util/Build:430: util/setup.py.mypy_log] Error 1
```
Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250311213628.569562-4-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
The function worker_thread() is programmed in a way that roughly
doubles the number of expectable context switches, because it enforces
blocking reads:
Performance counter stats for 'perf bench sched pipe':
2,000,004 context-switches
11.859548321 seconds time elapsed
0.674871000 seconds user
8.076890000 seconds sys
The result of this behavior is that the blocking reads by far dominate
the performance analysis of 'perf bench sched pipe':
Samples: 78K of event 'cycles:P', Event count (approx.): 27964965844
Overhead Command Shared Object Symbol
25.28% sched-pipe [kernel.kallsyms] [k] read_hpet
8.11% sched-pipe [kernel.kallsyms] [k] retbleed_untrain_ret
2.82% sched-pipe [kernel.kallsyms] [k] pipe_write
From the code, it is unclear if that behavior is wanted but the log
says that at least Ingo Molnar aims to mimic lmbench's lat_ctx, that
doesn't handle the pipe ends that way
(https://sourceforge.net/p/lmbench/code/HEAD/tree/trunk/lmbench2/src/lat_ctx.c)
Fix worker_thread() by always first feeding the write ends of the pipes
and then trying to read.
This roughly halves the context switches and runtime of pure
'perf bench sched pipe':
Performance counter stats for 'perf bench sched pipe':
1,005,770 context-switches
6.033448041 seconds time elapsed
0.423142000 seconds user
4.519829000 seconds sys
And the blocking reads do no longer dominate the analysis at the above
extreme:
Samples: 40K of event 'cycles:P', Event count (approx.): 14309364879
Overhead Command Shared Object Symbol
12.20% sched-pipe [kernel.kallsyms] [k] read_hpet
9.23% sched-pipe [kernel.kallsyms] [k] retbleed_untrain_ret
3.68% sched-pipe [kernel.kallsyms] [k] pipe_write
Signed-off-by: Dirk Gouders <dirk@gouders.net>
Acked-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250323140316.19027-2-dirk@gouders.net
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Commit 54f9aa1092 ("tools/perf/powerpc/util: Add support to
handle compatible mode PVR for perf json events") introduced
to select proper JSON events in case of compat mode using
auxiliary vector. But this caused a compilation error in ppc64
Big Endian.
arch/powerpc/util/header.c: In function 'is_compat_mode':
arch/powerpc/util/header.c:20:21: error: cast to pointer from
integer of different size [-Werror=int-to-pointer-cast]
20 | if (!strcmp((char *)platform, (char *)base_platform))
| ^
arch/powerpc/util/header.c:20:39: error: cast to pointer from
integer of different size [-Werror=int-to-pointer-cast]
20 | if (!strcmp((char *)platform, (char *)base_platform))
|
Commit saved the getauxval(AT_BASE_PLATFORM) and getauxval(AT_PLATFORM)
return values in u64 which causes the compilation error.
Patch fixes this issue by changing u64 to "unsigned long".
Fixes: 54f9aa1092 ("tools/perf/powerpc/util: Add support to handle compatible mode PVR for perf json events")
Signed-off-by: Likhitha Korrapati <likhitha@linux.ibm.com>
Reviewed-by: Athira Rajeev <atrajeev@linux.ibm.com>
Link: https://lore.kernel.org/r/20250321100726.699956-1-likhitha@linux.ibm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
When enabling the libperl feature the build uses perl's build flags
(ccopts) but filters out various flags, e.g. for LTO.
While this is conceptually correct, it is insufficient in practice,
since only "-flto=auto" is filtered out. When perl itself is built with
"-flto" this can cause parts of perf being built with LTO and others
without, giving exciting build errors like e.g.:
../tools/perf/pmu-events/pmu-events.c:72851:(.text+0xb79): undefined
reference to `strcmp_cpuid_str' collect2: error: ld returned 1 exit status
Fix this by filtering all matching flag values of -flto{=n,auto,..}.
Signed-off-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Link: https://lore.kernel.org/r/20250321082038.27901-2-holger@applied-asynchrony.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Rather than generating individual syscall header files generate a
single trace/beauty/generated/syscalltbl.c. In a syscalltbls array
have references to each architectures tables along with the
corresponding e_machine. When the 32-bit or 64-bit table is ambiguous,
match the perf binary's type. For ARM32 don't use the arm64 32-bit
table which is smaller. EM_NONE is present for is no machine matches.
Conditionally compile the tables, only having the appropriate 32 and
64-bit table. If ALL_SYSCALLTBL is defined all tables can be
compiled.
Add comment for noreturn column suggested by Arnd Bergmann:
https://lore.kernel.org/lkml/d47c35dd-9c52-48e7-a00d-135572f11fbb@app.fastmail.com/
and added in commit 9142be9e64 ("x86/syscall: Mark exit[_group]
syscall handlers __noreturn").
Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: Howard Chu <howardchu95@gmail.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Link: https://lore.kernel.org/r/20250319050741.269828-9-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
First try to read the e_machine from the dsos associated with the
thread's maps. If live use the executable from /proc/pid/exe and read
the e_machine from the ELF header. On failure use EM_HOST. Change
builtin-trace syscall functions to pass e_machine from the thread
rather than EM_HOST, so that in later patches when syscalltbl can use
the e_machine the system calls are specific to the architecture.
Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Link: https://lore.kernel.org/r/20250319050741.269828-8-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
