mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson
synced 2025-08-27 06:18:54 +00:00
loongarch-next
272 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Yuzhuo Jing
|
8e63fd1e00 |
tools: Remove libcrypto dependency
Remove all occurrence of libcrypto in the build system. Signed-off-by: Yuzhuo Jing <yuzhuo@google.com> Signed-off-by: Eric Biggers <ebiggers@kernel.org> Reviewed-by: Ian Rogers <irogers@google.com> Link: https://lore.kernel.org/r/20250625202311.23244-5-ebiggers@kernel.org Signed-off-by: Namhyung Kim <namhyung@kernel.org> |
||
|
Arnaldo Carvalho de Melo
|
970ae86307 |
perf build: The bfd features are opt-in, stop testing for them by default
These are leftovers noticed while updating a build container. We don't need those so that test-all.c can build and thus speed up the feature detection. Test for those features only if the user asks for BUILD_NONDISTRO=1 to build with libbfd. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Reviewed-by: James Clark <james.clark@linaro.org> Reviewed-by: Ian Rogers <irogers@google.com> Link: https://lore.kernel.org/r/20250620212435.93846-4-acme@kernel.org Signed-off-by: Namhyung Kim <namhyung@kernel.org> |
||
|
Blake Jones
|
1d0654b7fd |
perf build: detect support for libbpf's emit_strings option
This creates a config option that detects libbpf's ability to display character arrays as strings, which was just added to the BPF tree (https://git.kernel.org/bpf/bpf-next/c/87c9c79a02b4). To test this change, I built perf (from later in this patch set) with: - static libbpf (default, using source from kernel tree) - dynamic libbpf (LIBBPF_DYNAMIC=1 LIBBPF_INCLUDE=/usr/local/include) For both the static and dynamic versions, I used headers with and without the ".emit_strings" option. I verified that of the four resulting binaries, the two with ".emit_strings" would successfully record BPF_METADATA events, and the two without wouldn't. All four binaries would successfully display BPF_METADATA events, because the relevant bit of libbpf code is only used during "perf record". Signed-off-by: Blake Jones <blakejones@google.com> Link: https://lore.kernel.org/r/20250612194939.162730-2-blakejones@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org> |
||
|
Ian Rogers
|
5ae6a303c2 |
tools/build: Remove some unused libbpf pre-1.0 feature test logic
Commit |
||
|
Arnaldo Carvalho de Melo
|
e0eb84cd51 |
tools build: Don't show libbfd build status as it is opt-in
Since |
||
|
Arnaldo Carvalho de Melo
|
a3a4039129 |
tools build: Don't show libunwind build status as it is opt-in
Since |
||
|
Arnaldo Carvalho de Melo
|
6559b83e4e |
tools build: Don't set libunwind as available if test-all.c build succeeds
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:
|
||
|
Linus Torvalds
|
802f0d58d5 |
perf tools changes for v6.15
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
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQSo2x5BnqMqsoHtzsmMstVUGiXMgwUCZ+Y/YQAKCRCMstVUGiXM
g64CAP9sdUgKCe66JilZRAEy9d3Cp835v7KjHSlCXLXkRSoy6wD+KH96Y0OqVtGw
GYON4s9ZoXAoH+J0lKIFSffVL9MhYgY=
=7L7B
-----END PGP SIGNATURE-----
Merge tag 'perf-tools-for-v6.15-2025-03-27' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools
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
...
|
||
|
Linus Torvalds
|
4fa118e5b7 |
tracing tooling updates for 6.15:
- Allow RTLA to collect data via BPF The current implementation of rtla uses libtracefs and libtraceevent to pull sample events generated by the timerlat tracer from the trace buffer. rtla then processes the sample by updating the histogram and summary (current, maximum, minimum, and sum values) as well as checks if tracing has been stopped due to threshold overflow. In use cases where a large number of samples is being generated, that is, with measurements running on many CPUs and with a low interval, this sample processing design causes a significant CPU load on the rtla side. Furthermore, with >100 CPUs and 100us interval, rtla was reported as not being able to keep up with the samples and dropping most of them, leading to it being unusable. Change the way the timerlat trace processes samples by attaching a BPF program to the trace event using the BPF skeleton feature of bpftool. Unlike the current implementation, the BPF implementation does not check whether tracing is stopped (in BPF mode, tracing is always off to improve performance), but waits for a write to a BPF ringbuffer instead. This allows rtla to exit immediately when a threshold is violated, without waiting for the next iteration of the while loop. If the requirements for the BPF implementation are not met, either at build time or at run time, the current implementation is used as fallback. Which implementation is being used can be seen when running rtla timerlat with "-D" option. rtla can be forced to run in non-BPF mode by setting the RTLA_NO_BPF option to 1, for debugging purposes. - Fix LD_FLAGS from being dropped in build - Refactor code to remove duplication of save_trace_to_file - Always set options and do not rely on default settings Do not rely on the default kernel settings of the tracers when starting. They could have been changed by the user which gives inconsistent results. Always set the options that rtla expects. - Add creation of ctags and TAGS for traversing code -----BEGIN PGP SIGNATURE----- iIoEABYIADIWIQRRSw7ePDh/lE+zeZMp5XQQmuv6qgUCZ+WBgRQccm9zdGVkdEBn b29kbWlzLm9yZwAKCRAp5XQQmuv6qg54AQDCOChaSSBiUkD0VoPKIeDMlPfvO5Qz Xvrst5gtopfKFgEA12/9Lll/sh1eoc4saeGBooNY48HBUMjmX3KNFB14PQg= =aHFu -----END PGP SIGNATURE----- Merge tag 'trace-tools-v6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing tooling updates from Steven Rostedt: - Allow RTLA to collect data via BPF The current implementation of rtla uses libtracefs and libtraceevent to pull sample events generated by the timerlat tracer from the trace buffer. rtla then processes the sample by updating the histogram and summary (current, maximum, minimum, and sum values) as well as checks if tracing has been stopped due to threshold overflow. In use cases where a large number of samples is being generated, that is, with measurements running on many CPUs and with a low interval, this sample processing design causes a significant CPU load on the rtla side. Furthermore, with >100 CPUs and 100us interval, rtla was reported as not being able to keep up with the samples and dropping most of them, leading to it being unusable. Change the way the timerlat trace processes samples by attaching a BPF program to the trace event using the BPF skeleton feature of bpftool. Unlike the current implementation, the BPF implementation does not check whether tracing is stopped (in BPF mode, tracing is always off to improve performance), but waits for a write to a BPF ringbuffer instead. This allows rtla to exit immediately when a threshold is violated, without waiting for the next iteration of the while loop. If the requirements for the BPF implementation are not met, either at build time or at run time, the current implementation is used as fallback. Which implementation is being used can be seen when running rtla timerlat with "-D" option. rtla can be forced to run in non-BPF mode by setting the RTLA_NO_BPF option to 1, for debugging purposes. - Fix LD_FLAGS from being dropped in build - Refactor code to remove duplication of save_trace_to_file - Always set options and do not rely on default settings Do not rely on the default kernel settings of the tracers when starting. They could have been changed by the user which gives inconsistent results. Always set the options that rtla expects. - Add creation of ctags and TAGS for traversing code * tag 'trace-tools-v6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: rtla: Add the ability to create ctags and etags rtla/tests: Test setting default options rtla/tests: Reset osnoise options before check rtla: Always set all tracer options rtla/osnoise: Set OSNOISE_WORKLOAD to true rtla: Unify apply_config between top and hist rtla/osnoise: Unify params struct rtla: Fix segfault in save_trace_to_file call tools/build: Use SYSTEM_BPFTOOL for system bpftool rtla: Refactor save_trace_to_file tools/rv: Keep user LDFLAGS in build rtla/timerlat: Test BPF mode rtla/timerlat_top: Use BPF to collect samples rtla/timerlat_top: Move divisor to update rtla/timerlat_hist: Use BPF to collect samples rtla/timerlat: Add BPF skeleton to collect samples rtla: Add optional dependency on BPF tooling tools/build: Add bpftool-skeletons feature test rtla/timerlat: Unify params struct |
||
|
Tomas Glozar
|
814d051ebe |
tools/build: Use SYSTEM_BPFTOOL for system bpftool
The feature test for system bpftool uses BPFTOOL as the variable to set
its path, defaulting to just "bpftool" if not set by the user.
This conflicts with selftests and a few other utilities, which expect
BPFTOOL to be set to the in-tree bpftool path by default. For example,
bpftool selftests fail to build:
$ make -C tools/testing/selftests/bpf/
make: Entering directory '/home/tglozar/dev/linux/tools/testing/selftests/bpf'
make: *** No rule to make target 'bpftool', needed by '/home/tglozar/dev/linux/tools/testing/selftests/bpf/tools/include/vmlinux.h'. Stop.
make: Leaving directory '/home/tglozar/dev/linux/tools/testing/selftests/bpf'
Fix the problem by renaming the variable used for system bpftool from
BPFTOOL to SYSTEM_BPFTOOL, so that the new usage does not conflict with
the existing one of BPFTOOL.
Cc: John Kacur <jkacur@redhat.com>
Cc: Luis Goncalves <lgoncalv@redhat.com>
Link: https://lore.kernel.org/20250326004018.248357-1-tglozar@redhat.com
Fixes:
|
||
|
Ian Rogers
|
935e7cb5bb |
tools/build: Don't pass test log files to linker
Separate test log files from object files. Depend on test log output but don't pass to the linker. Reviewed-by: James Clark <james.clark@linaro.org> Signed-off-by: Ian Rogers <irogers@google.com> Link: https://lore.kernel.org/r/20250311213628.569562-2-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org> |
||
|
Tomas Glozar
|
8a635c3856 |
tools/build: Add bpftool-skeletons feature test
Add bpftool-skeletons feature test, testing the presence of a bpftool capable of generating skeletons. This is to be used for tools that do not require building their own bootstrap bpftool from the kernel source tree. Cc: John Kacur <jkacur@redhat.com> Cc: Luis Goncalves <lgoncalv@redhat.com> Cc: Gabriele Monaco <gmonaco@redhat.com> Cc: Clark Williams <williams@redhat.com> Link: https://lore.kernel.org/20250218145859.27762-3-tglozar@redhat.com Signed-off-by: Tomas Glozar <tglozar@redhat.com> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> |
||
|
Charlie Jenkins
|
293f324ce9 |
tools: Unify top-level quiet infrastructure
Commit |
||
|
Ian Rogers
|
7c1e94f5dc |
tools build: Fix a number of Wconversion warnings
There's some expressed interest in having the compiler flag -Wconversion detect at build time certain kinds of potential problems: https://lore.kernel.org/lkml/20250103182532.GB781381@e132581.arm.com/ As feature detection passes -Wconversion from CFLAGS when set, the feature detection compile tests need to not fail because of -Wconversion as the failure will be interpretted as a missing feature. Switch various types to avoid the -Wconversion issue, the exact meaning of the code is unimportant as it is typically looking for header file definitions. Signed-off-by: Ian Rogers <irogers@google.com> Reviewed-by: James Clark <james.clark@linaro.org> Link: https://lore.kernel.org/r/20250106215443.198633-1-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org> |
||
|
Charlie Jenkins
|
f2868b1a66 |
perf tools: Expose quiet/verbose variables in Makefile.perf
The variables to make builds silent/verbose live inside tools/build/Makefile.build. Move those variables to the top-level Makefile.perf to be generally available. Committer testing: See the SYSCALL lines, now they are consistent with the other operations in other lines: SYSTBL /tmp/build/perf-tools-next/arch/x86/include/generated/asm/syscalls_32.h SYSTBL /tmp/build/perf-tools-next/arch/x86/include/generated/asm/syscalls_64.h GEN /tmp/build/perf-tools-next/common-cmds.h GEN /tmp/build/perf-tools-next/arch/arm64/include/generated/asm/sysreg-defs.h PERF_VERSION = 6.13.rc2.g3d94bb6ed1d0 GEN perf-archive MKDIR /tmp/build/perf-tools-next/jvmti/ MKDIR /tmp/build/perf-tools-next/jvmti/ MKDIR /tmp/build/perf-tools-next/jvmti/ MKDIR /tmp/build/perf-tools-next/jvmti/ GEN perf-iostat CC /tmp/build/perf-tools-next/jvmti/libjvmti.o Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Charlie Jenkins <charlie@rivosinc.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Suzuki K Poulose <suzuki.poulose@arm.com> Cc: James Clark <james.clark@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: linux-arm-kernel@lists.infradead.org Cc: coresight@lists.linaro.org Link: https://lore.kernel.org/r/20250114-perf_make_test-v1-1-decc1c517b11@rivosinc.com Signed-off-by: Namhyung Kim <namhyung@kernel.org> |
||
|
Charlie Jenkins
|
3cc550f5bb |
perf tools: Remove dependency on libaudit
All architectures now support HAVE_SYSCALL_TABLE_SUPPORT, so the flag is no longer needed. With the removal of the flag, the related GENERIC_SYSCALL_TABLE can also be removed. libaudit was only used as a fallback for when HAVE_SYSCALL_TABLE_SUPPORT was not defined, so libaudit is also no longer needed for any architecture. Signed-off-by: Charlie Jenkins <charlie@rivosinc.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Christian Brauner <brauner@kernel.org> Cc: Guo Ren <guoren@kernel.org> Cc: Günther Noack <gnoack@google.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: John Garry <john.g.garry@oracle.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Leo Yan <leo.yan@linux.dev> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mickaël Salaün <mic@digikod.net> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Will Deacon <will@kernel.org> Link: https://lore.kernel.org/r/20250108-perf_syscalltbl-v6-16-7543b5293098@rivosinc.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Charlie Jenkins
|
4a73aff8c5 |
perf tools: Create generic syscall table support
Currently each architecture in perf independently generates syscall headers. Adapt the work that has gone into unifying syscall header implementations in the kernel to work with perf tools. Introduce this framework with riscv at first. riscv previously relied on libaudit, but with this change, perf tools for riscv no longer needs this external dependency. Signed-off-by: Charlie Jenkins <charlie@rivosinc.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Christian Brauner <brauner@kernel.org> Cc: Guo Ren <guoren@kernel.org> Cc: Günther Noack <gnoack@google.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: John Garry <john.g.garry@oracle.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Leo Yan <leo.yan@linux.dev> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mickaël Salaün <mic@digikod.net> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Will Deacon <will@kernel.org> Link: https://lore.kernel.org/r/20250108-perf_syscalltbl-v6-1-7543b5293098@rivosinc.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Leo Yan
|
d557814cdf |
tools build: Add feature test for libelf with ZSTD
The macro ELFCOMPRESS_ZSTD defines the compress algorithm, which was
introduced in the commit ("libelf: Document and make ELFCOMPRESS_ZSTD
usable with old system elf.h") of the repository elfutils-0.188-67.
Therefore, libelf 0.189 and later versions require to link the libzstd
library.
Add a test for checking if libelf supports ZSTD algorithm. Pass the
macro ELFCOMPRESS_ZSTD as an argument to the elf_compress() function.
If the build succeeds, it means the feature is supported.
Reviewed-by: Quentin Monnet <qmo@kernel.org>
Signed-off-by: Leo Yan <leo.yan@arm.com>
Tested-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Quentin Monnet <qmo@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Hao Luo <haoluo@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@linaro.org>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: KP Singh <kpsingh@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Song Liu <song@kernel.org>
Cc: Stanislav Fomichev <sdf@google.com>
Cc: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20241215221223.293205-2-leo.yan@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|
Arnaldo Carvalho de Melo
|
055f0ce7d8 |
tools build: Test for presence of libtraceevent and libtracefs in test-all.c
Since these are so far considered part of the basic set of libraries to be present when building perf, have then in tools/build/features/test-all.c. They were already in the FEATURE_TESTS_BASIC variable of tools/build/Makefile.feature, meaning if test-all.c builds, those features would be set as present, but then we were calling "again" (well, they were not in test-all.c, so were not really being tested) for it to be detected, fix this all up by not calling feature_check for those features but instead have them in test-all.c to be tested together with the the set of basic expected libraries. 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/lkml/20241213195052.914914-3-acme@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Arnaldo Carvalho de Melo
|
701b27403c |
tools build feature: Don't set feature-libslang-include-subdir=1 if test-all.c builds
As it is not really included in tools/build/feature/test-all.c, so any questioning about this feature should really try to build tools/build/feature/test-libslang-include-subdir.c and not set it as detected when test-all.c builds. 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/lkml/20241213195052.914914-2-acme@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Arnaldo Carvalho de Melo
|
b1ef2559d5 |
tools build feature: Don't set feature-libcap=1 if libcap-devel isn't available
libcap isn't tested in the tools/build/feature/test-all.c fast path
feature detection process, so don't set it as available if test-all
manages to build.
There are other users of this feature detection mechanism, and they
explicitely ask for libcap to be tested, so are not affected by this
patch, for instance, with this patch in place:
$ make -C tools/bpf/bpftool/ clean
<SNIP>
make: Leaving directory '/home/acme/git/perf-tools-next/tools/bpf/bpftool'
⬢ [acme@toolbox perf-tools-next]$ make -C tools/bpf/bpftool/
make: Entering directory '/home/acme/git/perf-tools-next/tools/bpf/bpftool'
Auto-detecting system features:
... clang-bpf-co-re: [ on ]
... llvm: [ on ]
... libcap: [ on ]
... libbfd: [ on ]
... libelf-zstd: [ on ]
<SNIP>
LINK bpftool
make: Leaving directory '/home/acme/git/perf-tools-next/tools/bpf/bpftool'
$
$ sudo rpm -e libcap-devel
$ make -C tools/bpf/bpftool/
<SNIP>
make: Entering directory '/home/acme/git/perf-tools-next/tools/bpf/bpftool'
Auto-detecting system features:
... clang-bpf-co-re: [ on ]
... llvm: [ on ]
... libcap: [ OFF ]
... libbfd: [ on ]
... libelf-zstd: [ on ]
$
Reviewed-by: Ian Rogers <irogers@google.com>
Acked-by: Quentin Monnet <qmo@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.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/lkml/20241211224509.797827-3-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|
Arnaldo Carvalho de Melo
|
20ed532554 |
tools build feature: Add some comments to explain the FEATURE_TESTS logic
The tools/build/feature/test-all.c works in conjunction with the tools/build/Makefile.feature FEATURE_TESTS_BASIC and FEATURE_TESTS_EXTRA contents, so that if test-all.c manages to be built, we go on and iterate all entries in FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA setting them to 1. To test this: $ rm -rf /tmp/b ; mkdir /tmp/b ; make -C tools/perf O=/tmp/b feature-dump $ cat /tmp/b/feature/test-all.make.output $ ldd /tmp/b/feature/test-all.bin linux-vdso.so.1 (0x00007f2a47a67000) libdw.so.1 => /lib64/libdw.so.1 (0x00007f2a477cf000) libpython3.12.so.1.0 => /lib64/libpython3.12.so.1.0 (0x00007f2a471fe000) libm.so.6 => /lib64/libm.so.6 (0x00007f2a4711a000) libtraceevent.so.1 => /lib64/libtraceevent.so.1 (0x00007f2a470f2000) libtracefs.so.1 => /lib64/libtracefs.so.1 (0x00007f2a470cb000) libcrypto.so.3 => /lib64/libcrypto.so.3 (0x00007f2a46c1b000) libz.so.1 => /lib64/libz.so.1 (0x00007f2a46bf8000) libbabeltrace-ctf.so.1 => /lib64/libbabeltrace-ctf.so.1 (0x00007f2a46bad000) libcapstone.so.5 => /lib64/libcapstone.so.5 (0x00007f2a464b8000) libopencsd_c_api.so.1 => /lib64/libopencsd_c_api.so.1 (0x00007f2a464a8000) libopencsd.so.1 => /lib64/libopencsd.so.1 (0x00007f2a46422000) libelf.so.1 => /lib64/libelf.so.1 (0x00007f2a46406000) libnuma.so.1 => /lib64/libnuma.so.1 (0x00007f2a463f6000) libslang.so.2 => /lib64/libslang.so.2 (0x00007f2a46113000) libperl.so.5.38 => /lib64/libperl.so.5.38 (0x00007f2a45d74000) libc.so.6 => /lib64/libc.so.6 (0x00007f2a45b83000) liblzma.so.5 => /lib64/liblzma.so.5 (0x00007f2a45b50000) libzstd.so.1 => /lib64/libzstd.so.1 (0x00007f2a45a91000) libbz2.so.1 => /lib64/libbz2.so.1 (0x00007f2a45a7b000) /lib64/ld-linux-x86-64.so.2 (0x00007f2a47a69000) libbabeltrace.so.1 => /lib64/libbabeltrace.so.1 (0x00007f2a45a6b000) libpopt.so.0 => /lib64/libpopt.so.0 (0x00007f2a45a5b000) libuuid.so.1 => /lib64/libuuid.so.1 (0x00007f2a45a51000) libgmodule-2.0.so.0 => /lib64/libgmodule-2.0.so.0 (0x00007f2a45a4a000) libglib-2.0.so.0 => /lib64/libglib-2.0.so.0 (0x00007f2a458fa000) libstdc++.so.6 => /lib64/libstdc++.so.6 (0x00007f2a45696000) libgcc_s.so.1 => /lib64/libgcc_s.so.1 (0x00007f2a45668000) libcrypt.so.2 => /lib64/libcrypt.so.2 (0x00007f2a45630000) libpcre2-8.so.0 => /lib64/libpcre2-8.so.0 (0x00007f2a45590000) $ head /tmp/b/FEATURE-DUMP feature-backtrace=1 feature-libdw=1 feature-eventfd=1 feature-fortify-source=1 feature-get_current_dir_name=1 feature-gettid=1 feature-glibc=1 feature-libbfd=1 feature-libbfd-buildid=1 feature-libcap=1 $ There are inconsistencies that are being audited, as can be seen above with the libcap case, that is not linked with test-all.bin nor is present in test-all.c, so shouldn't be set as present. Further patches are going to address those inconsistencies, but lets document this a bit more to reduce the chances of this happening again. Reviewed-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.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/lkml/20241211224509.797827-2-acme@kernel.org [ Fixed typo pointed out by Ian Rogers ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Arnaldo Carvalho de Melo
|
b40fbeb0b1 |
tools build: Remove the libunwind feature tests from the ones detected when test-all.o builds
We have a tools/build/feature/test-all.c that has the most common set of
features that perf uses and are expected to have its development files
available when building perf.
When we made libwunwind opt-in we forgot to remove them from the list of
features that are assumed to be available when test-all.c builds, remove
them.
Before this patch:
$ rm -rf /tmp/b ; mkdir /tmp/b ; make -C tools/perf O=/tmp/b feature-dump ; grep feature-libunwind-aarch64= /tmp/b/FEATURE-DUMP
feature-libunwind-aarch64=1
$
Even tho this not being test built and those header files being
available:
$ head -5 tools/build/feature/test-libunwind-aarch64.c
// SPDX-License-Identifier: GPL-2.0
#include <libunwind-aarch64.h>
#include <stdlib.h>
extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
$
After this patch:
$ grep feature-libunwind- /tmp/b/FEATURE-DUMP
$
Now an audit on what is being enabled when test-all.c builds will be
performed.
Fixes:
|
||
|
Arnaldo Carvalho de Melo
|
176c9d1e6a |
tools features: Don't check for libunwind devel files by default
Since |
||
|
Linus Torvalds
|
b50ecc5aca |
perf tools changes for v6.13
perf record
-----------
* Enable leader sampling for inherited task events. It was supported
only for system-wide events but the kernel started to support such a
setup since v6.12.
This is to reduce the number of PMU interrupts. The samples of the
leader event will contain counts of other events and no samples will
be generated for the other member events.
$ perf record -e '{cycles,instructions}:S' ${MYPROG}
perf report
-----------
* Fix --branch-history option to display more branch-related information
like prediction, abort and cycles which is available on Intel machines.
$ perf record -bg -- perf test -w brstack
$ perf report --branch-history
...
#
# Overhead Source:Line Symbol Shared Object Predicted Abort Cycles IPC [IPC Coverage]
# ........ ........................ .............. .................... ......... ..... ...... ....................
#
8.17% copy_page_64.S:19 [k] copy_page [kernel.kallsyms] 50.0% 0 5 - -
|
---xas_load xarray.h:171
|
|--5.68%--xas_load xarray.c:245 (cycles:1)
| xas_load xarray.c:242
| xas_load xarray.h:1260 (cycles:1)
| xas_descend xarray.c:146
| xas_load xarray.c:244 (cycles:2)
| xas_load xarray.c:245
| xas_descend xarray.c:218 (cycles:10)
...
perf stat
---------
* Add HWMON PMU support. The HWMON provides various system information
like CPU/GPU temperature, fan speed and so on. Expose them as PMU
events so that users can see the values using perf stat commands.
$ perf stat -e temp_cpu,fan1 true
Performance counter stats for 'true':
60.00 'C temp_cpu
0 rpm fan1
0.000745382 seconds time elapsed
0.000883000 seconds user
0.000000000 seconds sys
* Display metric threshold in JSON output. Some metrics define
thresholds to classify value ranges. It used to be in a different
color but it won't work for JSON. Add "metric-threshold" field to
the JSON that can be one of "good", "less good", "nearly bad" and
"bad".
# perf stat -a -M TopdownL1 -j true
{"counter-value" : "18693525.000000", "unit" : "", "event" : "TOPDOWN.SLOTS", "event-runtime" : 5552708, "pcnt-running" : 100.00, "metric-value" : "43.226002", "metric-unit" : "% tma_backend_bound", "metric-threshold" : "bad"}
{"metric-value" : "29.212267", "metric-unit" : "% tma_frontend_bound", "metric-threshold" : "bad"}
{"metric-value" : "7.138972", "metric-unit" : "% tma_bad_speculation", "metric-threshold" : "good"}
{"metric-value" : "20.422759", "metric-unit" : "% tma_retiring", "metric-threshold" : "good"}
{"counter-value" : "3817732.000000", "unit" : "", "event" : "topdown-retiring", "event-runtime" : 5552708, "pcnt-running" : 100.00, }
{"counter-value" : "5472824.000000", "unit" : "", "event" : "topdown-fe-bound", "event-runtime" : 5552708, "pcnt-running" : 100.00, }
{"counter-value" : "7984780.000000", "unit" : "", "event" : "topdown-be-bound", "event-runtime" : 5552708, "pcnt-running" : 100.00, }
{"counter-value" : "1418181.000000", "unit" : "", "event" : "topdown-bad-spec", "event-runtime" : 5552708, "pcnt-running" : 100.00, }
...
perf sched
----------
* Add -P/--pre-migrations option for 'timehist' sub-command to track
time a task waited on a run-queue before migrating to a different CPU.
$ perf sched timehist -P
time cpu task name wait time sch delay run time pre-mig time
[tid/pid] (msec) (msec) (msec) (msec)
--------------- ------ ------------------------------ --------- --------- --------- ---------
585940.535527 [0000] perf[584885] 0.000 0.000 0.000 0.000
585940.535535 [0000] migration/0[20] 0.000 0.002 0.008 0.000
585940.535559 [0001] perf[584885] 0.000 0.000 0.000 0.000
585940.535563 [0001] migration/1[25] 0.000 0.001 0.004 0.000
585940.535678 [0002] perf[584885] 0.000 0.000 0.000 0.000
585940.535686 [0002] migration/2[31] 0.000 0.002 0.008 0.000
585940.535905 [0001] <idle> 0.000 0.000 0.342 0.000
585940.535938 [0003] perf[584885] 0.000 0.000 0.000 0.000
585940.537048 [0001] sleep[584886] 0.000 0.019 1.142 0.001
585940.537749 [0002] <idle> 0.000 0.000 2.062 0.000
...
Build
-----
* Make libunwind opt-in (LIBUNWIND=1) rather than opt-out. The perf
tools are generally built with libelf and libdw which has unwinder
functionality. The libunwind support predates it and no need to
have duplicate unwinders by default.
* Rename NO_DWARF=1 build option to NO_LIBDW=1 in order to clarify it's
using libdw for handling DWARF information.
Internals
---------
* Do not set exclude_guest bit in the perf_event_attr by default. This
was causing a trouble in AMD IBS PMU as it doesn't support the bit.
The bit will be set when it's needed later by the fallback logic.
Also update the missing feature detection logic to make sure not clear
supported bits unnecessarily.
* Run perf test in parallel by default and mark flaky tests "exclusive"
to run them serially at the end. Some test numbers are changed but
the test can complete in less than half the time.
JSON vendor events
------------------
* Add AMD Zen 5 events and metrics.
* Add i.MX91 and i.MX95 DDR metrics
* Fix HiSilicon HIP08 Topdown metric name.
* Support compat events on PowerPC.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQSo2x5BnqMqsoHtzsmMstVUGiXMgwUCZ0Qi3gAKCRCMstVUGiXM
g6NIAP49eoSmQF40u55sJN0J7RpYd+bTgXZkahv0IUCBX98TLwEA2NrK0oUcB84C
xeanq28/3JxNM/oBpsEvvB8mb/0lGwI=
=FAVF
-----END PGP SIGNATURE-----
Merge tag 'perf-tools-for-v6.13-2024-11-24' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools
Pull perf tools updates from Namhyung Kim:
"perf record:
- Enable leader sampling for inherited task events. It was supported
only for system-wide events but the kernel started to support such
a setup since v6.12.
This is to reduce the number of PMU interrupts. The samples of the
leader event will contain counts of other events and no samples
will be generated for the other member events.
$ perf record -e '{cycles,instructions}:S' ${MYPROG}
perf report:
- Fix --branch-history option to display more branch-related
information like prediction, abort and cycles which is available
on Intel machines.
$ perf record -bg -- perf test -w brstack
$ perf report --branch-history
...
#
# Overhead Source:Line Symbol Shared Object Predicted Abort Cycles IPC [IPC Coverage]
# ........ ........................ .............. .................... ......... ..... ...... ....................
#
8.17% copy_page_64.S:19 [k] copy_page [kernel.kallsyms] 50.0% 0 5 - -
|
---xas_load xarray.h:171
|
|--5.68%--xas_load xarray.c:245 (cycles:1)
| xas_load xarray.c:242
| xas_load xarray.h:1260 (cycles:1)
| xas_descend xarray.c:146
| xas_load xarray.c:244 (cycles:2)
| xas_load xarray.c:245
| xas_descend xarray.c:218 (cycles:10)
...
perf stat:
- Add HWMON PMU support.
The HWMON provides various system information like CPU/GPU
temperature, fan speed and so on. Expose them as PMU events so that
users can see the values using perf stat commands.
$ perf stat -e temp_cpu,fan1 true
Performance counter stats for 'true':
60.00 'C temp_cpu
0 rpm fan1
0.000745382 seconds time elapsed
0.000883000 seconds user
0.000000000 seconds sys
- Display metric threshold in JSON output.
Some metrics define thresholds to classify value ranges. It used to
be in a different color but it won't work for JSON.
Add "metric-threshold" field to the JSON that can be one of "good",
"less good", "nearly bad" and "bad".
# perf stat -a -M TopdownL1 -j true
{"counter-value" : "18693525.000000", "unit" : "", "event" : "TOPDOWN.SLOTS", "event-runtime" : 5552708, "pcnt-running" : 100.00, "metric-value" : "43.226002", "metric-unit" : "% tma_backend_bound", "metric-threshold" : "bad"}
{"metric-value" : "29.212267", "metric-unit" : "% tma_frontend_bound", "metric-threshold" : "bad"}
{"metric-value" : "7.138972", "metric-unit" : "% tma_bad_speculation", "metric-threshold" : "good"}
{"metric-value" : "20.422759", "metric-unit" : "% tma_retiring", "metric-threshold" : "good"}
{"counter-value" : "3817732.000000", "unit" : "", "event" : "topdown-retiring", "event-runtime" : 5552708, "pcnt-running" : 100.00, }
{"counter-value" : "5472824.000000", "unit" : "", "event" : "topdown-fe-bound", "event-runtime" : 5552708, "pcnt-running" : 100.00, }
{"counter-value" : "7984780.000000", "unit" : "", "event" : "topdown-be-bound", "event-runtime" : 5552708, "pcnt-running" : 100.00, }
{"counter-value" : "1418181.000000", "unit" : "", "event" : "topdown-bad-spec", "event-runtime" : 5552708, "pcnt-running" : 100.00, }
...
perf sched:
- Add -P/--pre-migrations option for 'timehist' sub-command to track
time a task waited on a run-queue before migrating to a different
CPU.
$ perf sched timehist -P
time cpu task name wait time sch delay run time pre-mig time
[tid/pid] (msec) (msec) (msec) (msec)
--------------- ------ ------------------------------ --------- --------- --------- ---------
585940.535527 [0000] perf[584885] 0.000 0.000 0.000 0.000
585940.535535 [0000] migration/0[20] 0.000 0.002 0.008 0.000
585940.535559 [0001] perf[584885] 0.000 0.000 0.000 0.000
585940.535563 [0001] migration/1[25] 0.000 0.001 0.004 0.000
585940.535678 [0002] perf[584885] 0.000 0.000 0.000 0.000
585940.535686 [0002] migration/2[31] 0.000 0.002 0.008 0.000
585940.535905 [0001] <idle> 0.000 0.000 0.342 0.000
585940.535938 [0003] perf[584885] 0.000 0.000 0.000 0.000
585940.537048 [0001] sleep[584886] 0.000 0.019 1.142 0.001
585940.537749 [0002] <idle> 0.000 0.000 2.062 0.000
...
Build:
- Make libunwind opt-in (LIBUNWIND=1) rather than opt-out.
The perf tools are generally built with libelf and libdw which has
unwinder functionality. The libunwind support predates it and no
need to have duplicate unwinders by default.
- Rename NO_DWARF=1 build option to NO_LIBDW=1 in order to clarify
it's using libdw for handling DWARF information.
Internals:
- Do not set exclude_guest bit in the perf_event_attr by default.
This was causing a trouble in AMD IBS PMU as it doesn't support the
bit. The bit will be set when it's needed later by the fallback
logic. Also update the missing feature detection logic to make sure
not clear supported bits unnecessarily.
- Run perf test in parallel by default and mark flaky tests
"exclusive" to run them serially at the end. Some test numbers are
changed but the test can complete in less than half the time.
JSON vendor events:
- Add AMD Zen 5 events and metrics.
- Add i.MX91 and i.MX95 DDR metrics
- Fix HiSilicon HIP08 Topdown metric name.
- Support compat events on PowerPC"
* tag 'perf-tools-for-v6.13-2024-11-24' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (232 commits)
perf tests: Fix hwmon parsing with PMU name test
perf hwmon_pmu: Ensure hwmon key union is zeroed before use
perf tests hwmon_pmu: Remove double evlist__delete()
perf/test: fix perf ftrace test on s390
perf bpf-filter: Return -ENOMEM directly when pfi allocation fails
perf test: Correct hwmon test PMU detection
perf: Remove unused del_perf_probe_events()
perf pmu: Move pmu_metrics_table__find and remove ARM override
perf jevents: Add map_for_cpu()
perf header: Pass a perf_cpu rather than a PMU to get_cpuid_str
perf header: Avoid transitive PMU includes
perf arm64 header: Use cpu argument in get_cpuid
perf header: Refactor get_cpuid to take a CPU for ARM
perf header: Move is_cpu_online to numa bench
perf jevents: fix breakage when do perf stat on system metric
perf test: Add missing __exit calls in tool/hwmon tests
perf tests: Make leader sampling test work without branch event
perf util: Remove kernel version deadcode
perf test shell trace_exit_race: Use --no-comm to avoid cases where COMM isn't resolved
perf test shell trace_exit_race: Show what went wrong in verbose mode
...
|
||
|
Linus Torvalds
|
4b01712311 |
tracing/tools: Updates for 6.13
- Add ':' to getopt option 'trace-buffer-size' in timerlat_hist for consistency - Remove unused sched_getattr define - Rename sched_setattr() helper to syscall_sched_setattr() to avoid conflicts - Update counters to long from int to avoid overflow - Add libcpupower dependency detection - Add --deepest-idle-state to timerlat to limit deep idle sleeps - Other minor clean ups and documentation changes -----BEGIN PGP SIGNATURE----- iIoEABYIADIWIQRRSw7ePDh/lE+zeZMp5XQQmuv6qgUCZz5O/hQccm9zdGVkdEBn b29kbWlzLm9yZwAKCRAp5XQQmuv6qkLlAQDAJ0MASrdbJRDrLrfmKX6sja582MLe 3MvevdSkOeXRdQEA0tzm46KOb5/aYNotzpntQVkTjuZiPBHSgn1JzASiaAI= =OZ1w -----END PGP SIGNATURE----- Merge tag 'trace-tools-v6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing tools updates from Steven Rostedt: - Add ':' to getopt option 'trace-buffer-size' in timerlat_hist for consistency - Remove unused sched_getattr define - Rename sched_setattr() helper to syscall_sched_setattr() to avoid conflicts - Update counters to long from int to avoid overflow - Add libcpupower dependency detection - Add --deepest-idle-state to timerlat to limit deep idle sleeps - Other minor clean ups and documentation changes * tag 'trace-tools-v6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: verification/dot2: Improve dot parser robustness tools/rtla: Improve exception handling in timerlat_load.py tools/rtla: Enhance argument parsing in timerlat_load.py tools/rtla: Improve code readability in timerlat_load.py rtla/timerlat: Do not set params->user_workload with -U rtla: Documentation: Mention --deepest-idle-state rtla/timerlat: Add --deepest-idle-state for hist rtla/timerlat: Add --deepest-idle-state for top rtla/utils: Add idle state disabling via libcpupower rtla: Add optional dependency on libcpupower tools/build: Add libcpupower dependency detection rtla/timerlat: Make timerlat_hist_cpu->*_count unsigned long long rtla/timerlat: Make timerlat_top_cpu->*_count unsigned long long tools/rtla: fix collision with glibc sched_attr/sched_set_attr tools/rtla: drop __NR_sched_getattr rtla: Fix consistency in getopt_long for timerlat_hist rv: Fix a typo tools/rv: Correct the grammatical errors in the comments tools/rv: Correct the grammatical errors in the comments rtla: use the definition for stdout fd when calling isatty() |
||
|
Yicong Yang
|
35de42cdfb |
perf build: Include libtraceevent headers directly indicated by pkg-config
Currently the libtraceevent's found by pkg-config, which give the
include path as:
[root@localhost tmp]# pkg-config --cflags libtraceevent
-I/usr/local/include/traceevent
So we should include the libtraceevent headers directly without
"traceevent/" prefix. Update all the users.
Fixes:
|
||
|
Ian Rogers
|
91e81e988f |
perf probe: Move elfutils support check to libdw check
The test _ELFUTILS_PREREQ(0, 142) is false for elfutils before 2009-06-13, but that is 15 years ago and very unlikely. Add a test to test-libdw.c and assume the libdw version is at least 0.142 to simplify the build logic. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Anup Patel <anup@brainfault.org> Cc: Yang Jihong <yangjihong@bytedance.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: David S. Miller <davem@davemloft.net> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Shenlin Liang <liangshenlin@eswincomputing.com> Cc: Nick Terrell <terrelln@fb.com> Cc: Guilherme Amadio <amadio@gentoo.org> Cc: Steinar H. Gunderson <sesse@google.com> Cc: Changbin Du <changbin.du@huawei.com> Cc: Alexander Lobakin <aleksander.lobakin@intel.com> Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Guo Ren <guoren@kernel.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org> Cc: Will Deacon <will@kernel.org> Cc: James Clark <james.clark@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Chen Pei <cp0613@linux.alibaba.com> Cc: Leo Yan <leo.yan@linux.dev> Cc: Oliver Upton <oliver.upton@linux.dev> Cc: Aditya Gupta <adityag@linux.ibm.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-riscv@lists.infradead.org Cc: Bibo Mao <maobibo@loongson.cn> Cc: John Garry <john.g.garry@oracle.com> Cc: Atish Patra <atishp@rivosinc.com> Cc: Dima Kogan <dima@secretsauce.net> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Dr. David Alan Gilbert <linux@treblig.org> Cc: linux-csky@vger.kernel.org Link: https://lore.kernel.org/r/20241017001354.56973-9-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org> |
||
|
Ian Rogers
|
26385fd237 |
perf build: Combine test-dwarf-getcfi into test-libdw
dwarf_getcfi support in libdw is 15 years old. Make libdw imply dwarf_getcfi support and simplify build logic. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Leo Yan <leo.yan@arm.com> Cc: Anup Patel <anup@brainfault.org> Cc: Yang Jihong <yangjihong@bytedance.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: David S. Miller <davem@davemloft.net> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Shenlin Liang <liangshenlin@eswincomputing.com> Cc: Nick Terrell <terrelln@fb.com> Cc: Guilherme Amadio <amadio@gentoo.org> Cc: Steinar H. Gunderson <sesse@google.com> Cc: Changbin Du <changbin.du@huawei.com> Cc: Alexander Lobakin <aleksander.lobakin@intel.com> Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Guo Ren <guoren@kernel.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org> Cc: Will Deacon <will@kernel.org> Cc: James Clark <james.clark@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Chen Pei <cp0613@linux.alibaba.com> Cc: Leo Yan <leo.yan@linux.dev> Cc: Oliver Upton <oliver.upton@linux.dev> Cc: Aditya Gupta <adityag@linux.ibm.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-riscv@lists.infradead.org Cc: Bibo Mao <maobibo@loongson.cn> Cc: John Garry <john.g.garry@oracle.com> Cc: Atish Patra <atishp@rivosinc.com> Cc: Dima Kogan <dima@secretsauce.net> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Dr. David Alan Gilbert <linux@treblig.org> Cc: linux-csky@vger.kernel.org Link: https://lore.kernel.org/r/20241017001354.56973-8-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org> |
||
|
Ian Rogers
|
23580d7bb1 |
perf build: Combine test-dwarf-getlocations into test-libdw
dwarf_getlocations support in libdw is more than 10 years old. Make libdw imply dwarf_getlocations support and simplify build logic. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Leo Yan <leo.yan@arm.com> Cc: Anup Patel <anup@brainfault.org> Cc: Yang Jihong <yangjihong@bytedance.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: David S. Miller <davem@davemloft.net> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Shenlin Liang <liangshenlin@eswincomputing.com> Cc: Nick Terrell <terrelln@fb.com> Cc: Guilherme Amadio <amadio@gentoo.org> Cc: Steinar H. Gunderson <sesse@google.com> Cc: Changbin Du <changbin.du@huawei.com> Cc: Alexander Lobakin <aleksander.lobakin@intel.com> Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Guo Ren <guoren@kernel.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org> Cc: Will Deacon <will@kernel.org> Cc: James Clark <james.clark@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Chen Pei <cp0613@linux.alibaba.com> Cc: Leo Yan <leo.yan@linux.dev> Cc: Oliver Upton <oliver.upton@linux.dev> Cc: Aditya Gupta <adityag@linux.ibm.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-riscv@lists.infradead.org Cc: Bibo Mao <maobibo@loongson.cn> Cc: John Garry <john.g.garry@oracle.com> Cc: Atish Patra <atishp@rivosinc.com> Cc: Dima Kogan <dima@secretsauce.net> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Dr. David Alan Gilbert <linux@treblig.org> Cc: linux-csky@vger.kernel.org Link: https://lore.kernel.org/r/20241017001354.56973-7-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org> |
||
|
Ian Rogers
|
3034b48a4b |
perf build: Combine libdw-dwarf-unwind into libdw feature tests
Support in libdw has been present for 10 years so let's simplify the build logic with a single feature test. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Leo Yan <leo.yan@arm.com> Cc: Anup Patel <anup@brainfault.org> Cc: Yang Jihong <yangjihong@bytedance.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: David S. Miller <davem@davemloft.net> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Shenlin Liang <liangshenlin@eswincomputing.com> Cc: Nick Terrell <terrelln@fb.com> Cc: Guilherme Amadio <amadio@gentoo.org> Cc: Steinar H. Gunderson <sesse@google.com> Cc: Changbin Du <changbin.du@huawei.com> Cc: Alexander Lobakin <aleksander.lobakin@intel.com> Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Guo Ren <guoren@kernel.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org> Cc: Will Deacon <will@kernel.org> Cc: James Clark <james.clark@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Chen Pei <cp0613@linux.alibaba.com> Cc: Leo Yan <leo.yan@linux.dev> Cc: Oliver Upton <oliver.upton@linux.dev> Cc: Aditya Gupta <adityag@linux.ibm.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-riscv@lists.infradead.org Cc: Bibo Mao <maobibo@loongson.cn> Cc: John Garry <john.g.garry@oracle.com> Cc: Atish Patra <atishp@rivosinc.com> Cc: Dima Kogan <dima@secretsauce.net> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Dr. David Alan Gilbert <linux@treblig.org> Cc: linux-csky@vger.kernel.org Link: https://lore.kernel.org/r/20241017001354.56973-6-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org> |
||
|
Ian Rogers
|
7c943261a1 |
perf build: Rename test-dwarf to test-libdw
Be more intention revealing that the dwarf test is actually testing for libdw support. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Anup Patel <anup@brainfault.org> Cc: Yang Jihong <yangjihong@bytedance.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: David S. Miller <davem@davemloft.net> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Shenlin Liang <liangshenlin@eswincomputing.com> Cc: Nick Terrell <terrelln@fb.com> Cc: Guilherme Amadio <amadio@gentoo.org> Cc: Steinar H. Gunderson <sesse@google.com> Cc: Changbin Du <changbin.du@huawei.com> Cc: Alexander Lobakin <aleksander.lobakin@intel.com> Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Guo Ren <guoren@kernel.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org> Cc: Will Deacon <will@kernel.org> Cc: James Clark <james.clark@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Chen Pei <cp0613@linux.alibaba.com> Cc: Leo Yan <leo.yan@linux.dev> Cc: Oliver Upton <oliver.upton@linux.dev> Cc: Aditya Gupta <adityag@linux.ibm.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-riscv@lists.infradead.org Cc: Bibo Mao <maobibo@loongson.cn> Cc: John Garry <john.g.garry@oracle.com> Cc: Atish Patra <atishp@rivosinc.com> Cc: Dima Kogan <dima@secretsauce.net> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Dr. David Alan Gilbert <linux@treblig.org> Cc: linux-csky@vger.kernel.org Link: https://lore.kernel.org/r/20241017001354.56973-5-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org> |
||
|
Tomas Glozar
|
0f59a6c9c4 |
tools/build: Add libcpupower dependency detection
Add the ability to detect the presence of libcpupower on a system to the Makefiles in tools/build. Link: https://lore.kernel.org/20241017140914.3200454-2-tglozar@redhat.com Signed-off-by: Tomas Glozar <tglozar@redhat.com> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> |
||
|
Yang Jihong
|
a530337ba9 |
perf build: Fix build feature-dwarf_getlocations fail for old libdw
For libdw versions below 0.177, need to link libdl.a in addition to
libbebl.a during static compilation, otherwise
feature-dwarf_getlocations compilation will fail.
Before:
$ make LDFLAGS=-static
BUILD: Doing 'make -j20' parallel build
<SNIP>
Makefile.config:483: Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.157
<SNIP>
$ cat ../build/feature/test-dwarf_getlocations.make.output
/usr/bin/ld: /usr/lib/gcc/x86_64-linux-gnu/9/../../../x86_64-linux-gnu/libebl.a(eblclosebackend.o): in function `ebl_closebackend':
(.text+0x20): undefined reference to `dlclose'
collect2: error: ld returned 1 exit status
After:
$ make LDFLAGS=-static
<SNIP>
Auto-detecting system features:
... dwarf: [ on ]
<SNIP>
$ ./perf probe
Usage: perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]
or: perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]
or: perf probe [<options>] --del '[GROUP:]EVENT' ...
or: perf probe --list [GROUP:]EVENT ...
<SNIP>
Fixes:
|
||
|
Yang Jihong
|
43f6564f18 |
perf build: Fix static compilation error when libdw is not installed
If libdw is not installed in build environment, the output of
'pkg-config --modversion libdw' is empty, causing LIBDW_VERSION_2 to be
empty and the shell test will have the following error:
/bin/sh: 1: test: -lt: unexpected operator
Before:
$ pkg-config --modversion libdw
Package libdw was not found in the pkg-config search path.
Perhaps you should add the directory containing `libdw.pc'
to the PKG_CONFIG_PATH environment variable
No package 'libdw' found
$ make LDFLAGS=-static -j16
BUILD: Doing 'make -j20' parallel build
<SNIP>
Package libdw was not found in the pkg-config search path.
Perhaps you should add the directory containing `libdw.pc'
to the PKG_CONFIG_PATH environment variable
No package 'libdw' found
/bin/sh: 1: test: -lt: unexpected operator
After:
1. libdw is not installed:
$ pkg-config --modversion libdw
Package libdw was not found in the pkg-config search path.
Perhaps you should add the directory containing `libdw.pc'
to the PKG_CONFIG_PATH environment variable
No package 'libdw' found
$ make LDFLAGS=-static -j16
BUILD: Doing 'make -j20' parallel build
<SNIP>
Package libdw was not found in the pkg-config search path.
Perhaps you should add the directory containing `libdw.pc'
to the PKG_CONFIG_PATH environment variable
No package 'libdw' found
Makefile.config:473: No libdw DWARF unwind found, Please install elfutils-devel/libdw-dev >= 0.158 and/or set LIBDW_DIR
2. libdw version is lower than 0.177
$ pkg-config --modversion libdw
0.176
$ make LDFLAGS=-static -j16
BUILD: Doing 'make -j20' parallel build
<SNIP>
Auto-detecting system features:
... dwarf: [ on ]
<SNIP>
INSTALL libsubcmd_headers
INSTALL libapi_headers
INSTALL libperf_headers
INSTALL libsymbol_headers
INSTALL libbpf_headers
LINK perf
3. libdw version is higher than 0.177
$ pkg-config --modversion libdw
0.186
$ make LDFLAGS=-static -j16
BUILD: Doing 'make -j20' parallel build
<SNIP>
Auto-detecting system features:
... dwarf: [ on ]
<SNIP>
CC util/bpf-utils.o
CC util/pfm.o
LD util/perf-util-in.o
LD perf-util-in.o
AR libperf-util.a
LINK perf
Fixes:
|
||
|
James Clark
|
332f60ac05 |
perf build: Remove unused feature test target
llvm-version was removed in commit
|
||
|
James Clark
|
206dcfca1f |
perf build: Autodetect minimum required llvm-dev version
The new LLVM addr2line feature requires a minimum version of 13 to
compile. Add a feature check for the version so that NO_LLVM=1 doesn't
need to be explicitly added. Leave the existing llvm feature check
intact because it's used by tools other than Perf.
This fixes the following compilation error when the llvm-dev version
doesn't match:
util/llvm-c-helpers.cpp: In function 'char* llvm_name_for_code(dso*, const char*, u64)':
util/llvm-c-helpers.cpp:178:21: error: 'std::remove_reference_t<llvm::DILineInfo>' {aka 'struct llvm::DILineInfo'} has no member named 'StartAddress'
178 | addr, res_or_err->StartAddress ? *res_or_err->StartAddress : 0);
Fixes:
|
||
|
Steinar H. Gunderson
|
c3f8644c21 |
perf report: Support LLVM for addr2line()
In addition to the existing support for libbfd and calling out to
an external addr2line command, add support for using libllvm directly.
This is both faster than libbfd, and can be enabled in distro builds
(the LLVM license has an explicit provision for GPLv2 compatibility).
Thus, it is set as the primary choice if available.
As an example, running 'perf report' on a medium-size profile with
DWARF-based backtraces took 58 seconds with LLVM, 78 seconds with
libbfd, 153 seconds with external llvm-addr2line, and I got tired and
aborted the test after waiting for 55 minutes with external bfd
addr2line (which is the default for perf as compiled by distributions
today).
Evidently, for this case, the bfd addr2line process needs 18 seconds (on
a 5.2 GHz Zen 3) to load the .debug ELF in question, hits the 1-second
timeout and gets killed during initialization, getting restarted anew
every time. Having an in-process addr2line makes this much more robust.
As future extensions, libllvm can be used in many other places where
we currently use libbfd or other libraries:
- Symbol enumeration (in particular, for PE binaries).
- Demangling (including non-Itanium demangling, e.g. Microsoft
or Rust).
- Disassembling (perf annotate).
However, these are much less pressing; most people don't profile PE
binaries, and perf has non-bfd paths for ELF. The same with demangling;
the default _cxa_demangle path works fine for most users, and while bfd
objdump can be slow on large binaries, it is possible to use
--objdump=llvm-objdump to get the speed benefits. (It appears
LLVM-based demangling is very simple, should we want that.)
Tested with LLVM 14, 15, 16, 18 and 19. For some reason, LLVM 12 was not
correctly detected using feature_check, and thus was not tested.
Committer notes:
Added the name and a __maybe_unused to address:
1 13.50 almalinux:8 : FAIL gcc version 8.5.0 20210514 (Red Hat 8.5.0-22) (GCC)
util/srcline.c: In function 'dso__free_a2l':
util/srcline.c:184:20: error: parameter name omitted
void dso__free_a2l(struct dso *)
^~~~~~~~~~~~
make[3]: *** [/git/perf-6.11.0-rc3/tools/build/Makefile.build:158: util] Error 2
Signed-off-by: Steinar H. Gunderson <sesse@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20240803152008.2818485-1-sesse@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|
Arnaldo Carvalho de Melo
|
0fd77ae4a3 |
Revert "tools build: Remove leftover libcap tests that prevents fast path feature detection from working"
Ian pointed out that the libcap feature test is also used by bpftool, so
we can't remove it just because perf stopped using it, revert the
removal of the feature test.
Since both perf and libcap uses the fast path feature detection
(tools/build/feature/test-all.c), probably the best thing is to keep
libcap-devel when building perf even it not being used there.
This reverts commit
|
||
|
Arnaldo Carvalho de Melo
|
47b3b6435e |
tools build: Remove leftover libcap tests that prevents fast path feature detection from working
I noticed that the fast path feature detection was failing:
$ cat /tmp/build/perf-tools-next/feature/test-all.make.output
/usr/bin/ld: cannot find -lcap: No such file or directory
collect2: error: ld returned 1 exit status
$
The patch removing the dependency (Fixes tag below) didn't remove the
detection of libcap, and as the fast path feature detection (test-all.c)
had -lcap in its Makefile link list of libraries to link, it was failing
when libcap-devel is not available, fix it by removing those leftover
files.
Fixes:
|
||
|
Alexander Gordeev
|
b53f20b323 |
tools build: Provide consistent build options for fixdep
The fixdep binary is being compiled and linked in one step. While the
host linker flags are passed to the compiler the host compiler flags are
missed.
That leads to build errors at least on x86_64, arm64 and s390 as result
of the compiler vs linker flags inconsistency. For example, during RPM
package build redhat-hardened-ld script is provided to gcc, while
redhat-hardened-cc1 script is missed.
Provide both KBUILD_HOSTCFLAGS and KBUILD_HOSTLDFLAGS to avoid that.
Fixes:
|
||
|
Arnaldo Carvalho de Melo
|
4c55560f23 |
perf build: Fix up broken capstone feature detection fast path
The capstone devel headers define 'struct bpf_insn' in a way that clashes with
what is in the libbpf devel headers, so we so far need to avoid including both.
This is happening on the tools/build/feature/test-all.c file, where we try
building all the expected set of libraries to be normally available on a
system:
⬢[acme@toolbox perf-tools-next]$ cat /tmp/build/perf-tools-next/feature/test-all.make.output
In file included from test-bpf.c:3,
from test-all.c:150:
/home/acme/git/perf-tools-next/tools/include/uapi/linux/bpf.h:77:8: error: ‘bpf_insn’ defined as wrong kind of tag
77 | struct bpf_insn {
| ^~~~~~~~
⬢[acme@toolbox perf-tools-next]$ cat /tmp/build/perf-tools-next/feature/test-all.make.output
When doing so there is a trick where we define main to be
main_test_libcapstone, then include the individual
tools/build/feture/test-libcapstone.c capability query test, and then we undef
'main' because we'll do it all over again with the next expected library to
be tested (at this time 'lzma').
To complete this mechanism we need to, in test-all.c 'main' routine, to
call main_test_libcapstone(), which isn't being done, so the effect of
adding references to capstone in test-all.c are not achieved.
The only thing that is happening is that test-all.c is failing to build and thus
all the tests will have to be done individually, which nullifies the test-all.c
single build speedup.
So lets remove references to capstone from test-all.c to see if this makes it
build again so that we get faster builds or go on fixing up whatever is
preventing us to get that benefit.
Nothing: after this fix we get a clean test-all.c build and get the build speedup back:
⬢[acme@toolbox perf-tools-next]$ cat /tmp/build/perf-tools-next/feature/test-all.make.output
⬢[acme@toolbox perf-tools-next]$ cat /tmp/build/perf-tools-next/feature/test-all.
test-all.bin test-all.d test-all.make.output
⬢[acme@toolbox perf-tools-next]$ cat /tmp/build/perf-tools-next/feature/test-all.make.output
⬢[acme@toolbox perf-tools-next]$ ldd /tmp/build/perf-tools-next/feature/test-all.bin
linux-vdso.so.1 (0x00007f13277a1000)
libpython3.12.so.1.0 => /lib64/libpython3.12.so.1.0 (0x00007f1326e00000)
libm.so.6 => /lib64/libm.so.6 (0x00007f13274be000)
libtraceevent.so.1 => /lib64/libtraceevent.so.1 (0x00007f1327496000)
libtracefs.so.1 => /lib64/libtracefs.so.1 (0x00007f132746f000)
libcrypto.so.3 => /lib64/libcrypto.so.3 (0x00007f1326800000)
libunwind-x86_64.so.8 => /lib64/libunwind-x86_64.so.8 (0x00007f1327452000)
libunwind.so.8 => /lib64/libunwind.so.8 (0x00007f1327436000)
liblzma.so.5 => /lib64/liblzma.so.5 (0x00007f1327403000)
libdw.so.1 => /lib64/libdw.so.1 (0x00007f1326d6f000)
libz.so.1 => /lib64/libz.so.1 (0x00007f13273e2000)
libelf.so.1 => /lib64/libelf.so.1 (0x00007f1326d53000)
libnuma.so.1 => /lib64/libnuma.so.1 (0x00007f13273d4000)
libslang.so.2 => /lib64/libslang.so.2 (0x00007f1326400000)
libperl.so.5.38 => /lib64/libperl.so.5.38 (0x00007f1326000000)
libc.so.6 => /lib64/libc.so.6 (0x00007f1325e0f000)
libzstd.so.1 => /lib64/libzstd.so.1 (0x00007f1326741000)
/lib64/ld-linux-x86-64.so.2 (0x00007f13277a3000)
libbz2.so.1 => /lib64/libbz2.so.1 (0x00007f1326d3f000)
libcrypt.so.2 => /lib64/libcrypt.so.2 (0x00007f1326d07000)
⬢[acme@toolbox perf-tools-next]$
And when having capstone-devel installed we get it detected and linked with
perf, allowing us to benefit from the features that it enables:
⬢[acme@toolbox perf-tools-next]$ rpm -q capstone-devel
capstone-devel-5.0.1-3.fc40.x86_64
⬢[acme@toolbox perf-tools-next]$ ldd /tmp/build/perf-tools-next/perf | grep capstone
libcapstone.so.5 => /lib64/libcapstone.so.5 (0x00007fe6a5c00000)
⬢[acme@toolbox perf-tools-next]$ /tmp/build/perf-tools-next/perf -vv | grep cap
libcapstone: [ on ] # HAVE_LIBCAPSTONE_SUPPORT
⬢[acme@toolbox perf-tools-next]$
Fixes:
|
||
|
Brian Norris
|
dbb2a7a986 |
tools build: Correct bpf fixdep dependencies
The dependencies in tools/lib/bpf/Makefile are incorrect. Before we recurse to build $(BPF_IN_STATIC), we need to build its 'fixdep' executable. I can't use the usual shortcut from Makefile.include: <target>: <sources> fixdep because its 'fixdep' target relies on $(OUTPUT), and $(OUTPUT) differs in the parent 'make' versus the child 'make' -- so I imitate it via open-coding. I tweak a few $(MAKE) invocations while I'm at it, because 1. I'm adding a new recursive make; and 2. these recursive 'make's print spurious lines about files that are "up to date" (which isn't normally a feature in Kbuild subtargets) or "jobserver not available" (see [1]) I also need to tweak the assignment of the OUTPUT variable, so that relative path builds work. For example, for 'make tools/lib/bpf', OUTPUT is unset, and is usually treated as "cwd" -- but recursive make will change cwd and so OUTPUT has a new meaning. For consistency, I ensure OUTPUT is always an absolute path. And $(Q) gets a backup definition in tools/build/Makefile.include, because Makefile.include is sometimes included without tools/build/Makefile, so the "quiet command" stuff doesn't actually work consistently without it. After this change, top-level builds result in an empty grep result from: $ grep 'cannot find fixdep' $(find tools/ -name '*.cmd') [1] https://www.gnu.org/software/make/manual/html_node/MAKE-Variable.html If we're not using $(MAKE) directly, then we need to use more '+'. Signed-off-by: Brian Norris <briannorris@chromium.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ian Rogers <irogers@google.com> Cc: Josh Poimboeuf <jpoimboe@kernel.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Richter <tmricht@linux.ibm.com> Link: https://lore.kernel.org/r/20240715203325.3832977-4-briannorris@chromium.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Brian Norris
|
ea974028a0 |
tools build: Avoid circular .fixdep-in.o.cmd issues
The 'fixdep' tool is used to post-process dependency files for various reasons, and it runs after every object file generation command. This even includes 'fixdep' itself. In Kbuild, this isn't actually a problem, because it uses a single command to generate fixdep (a compile-and-link command on fixdep.c), and afterward runs the fixdep command on the accompanying .fixdep.cmd file. In tools/ builds (which notably is maintained separately from Kbuild), fixdep is generated in several phases: 1. fixdep.c -> fixdep-in.o 2. fixdep-in.o -> fixdep Thus, fixdep is not available in the post-processing for step 1, and instead, we generate .cmd files that look like: ## from tools/objtool/libsubcmd/.fixdep.o.cmd # cannot find fixdep (/path/to/linux/tools/objtool/libsubcmd//fixdep) [...] These invalid .cmd files are benign in some respects, but cause problems in others (such as the linked reports). Because the tools/ build system is rather complicated in its own right (and pointedly different than Kbuild), I choose to simply open-code the rule for building fixdep, and avoid the recursive-make indirection that produces the problem in the first place. Signed-off-by: Brian Norris <briannorris@chromium.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ian Rogers <irogers@google.com> Cc: Josh Poimboeuf <jpoimboe@kernel.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Richter <tmricht@linux.ibm.com> Link: https://lore.kernel.org/all/Zk-C5Eg84yt6_nml@google.com/ Link: https://lore.kernel.org/r/20240715203325.3832977-3-briannorris@chromium.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Linus Torvalds
|
e254e0c5ba |
Another perf tools fixes for v6.11
Some more fixes about the build and a random crash: * Fix cross-build by setting pkg-config env according to the arch * Fix static build for missing library dependencies * Fix Segfault when callchain has no symbols Signed-off-by: Namhyung Kim <namhyung@kernel.org> -----BEGIN PGP SIGNATURE----- iHUEABYIAB0WIQSo2x5BnqMqsoHtzsmMstVUGiXMgwUCZqls2wAKCRCMstVUGiXM g12aAQCovAOO6jC5GrzCS8KlBoHXplyGL1rscI2uZfOttotBnQEA875Ov6FNL9Ux u9oxHZOpN/U4Xnyeoj9c43ibae/urAQ= =LTu1 -----END PGP SIGNATURE----- Merge tag 'perf-tools-fixes-for-v6.11-2024-07-30' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools Pull perf tools fixes from Namhyung Kim: "Some more build fixes and a random crash fix: - Fix cross-build by setting pkg-config env according to the arch - Fix static build for missing library dependencies - Fix Segfault when callchain has no symbols" * tag 'perf-tools-fixes-for-v6.11-2024-07-30' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: perf docs: Document cross compilation perf: build: Link lib 'zstd' for static build perf: build: Link lib 'lzma' for static build perf: build: Only link libebl.a for old libdw perf: build: Set Python configuration for cross compilation perf: build: Setup PKG_CONFIG_LIBDIR for cross compilation perf tool: fix dereferencing NULL al->maps |
||
|
Leo Yan
|
f42596c738 |
perf: build: Link lib 'zstd' for static build
When build static perf, Makefile reports the error: Makefile.config:480: No libdw DWARF unwind found, Please install elfutils-devel/libdw-dev >= 0.158 and/or set LIBDW_DIR The libdw has been installed on the system, but the build system fails to build the feature detecting binary 'test-libdw-dwarf-unwind'. The failure is caused by missing to link the lib 'zstd'. Link lib 'zstd' for the static build, in the end, the dwarf feature can be enabled in the static perf. Signed-off-by: Leo Yan <leo.yan@arm.com> Tested-by: Ian Rogers <irogers@google.com> Cc: amadio@gentoo.org Cc: James Clark <james.clark@linaro.org> Cc: Thomas Richter <tmricht@linux.ibm.com> Link: https://lore.kernel.org/r/20240717082211.524826-6-leo.yan@arm.com Signed-off-by: Namhyung Kim <namhyung@kernel.org> |
||
|
Leo Yan
|
91b6a536b4 |
perf: build: Link lib 'lzma' for static build
The libunwind feature test failed with the static linkage. This is due to the 'lzma' lib is missed, so link it to dismiss building failure. Signed-off-by: Leo Yan <leo.yan@arm.com> Tested-by: Ian Rogers <irogers@google.com> Cc: amadio@gentoo.org Cc: James Clark <james.clark@linaro.org> Cc: Thomas Richter <tmricht@linux.ibm.com> Link: https://lore.kernel.org/r/20240717082211.524826-5-leo.yan@arm.com Signed-off-by: Namhyung Kim <namhyung@kernel.org> |
||
|
Leo Yan
|
536661da6e |
perf: build: Only link libebl.a for old libdw
Since libdw version 0.177, elfutils has merged libebl.a into libdw (see the commit "libebl: Don't install libebl.a, libebl.h and remove backends from spec." in the elfutils repository). As a result, libebl.a does not exist on Debian Bullseye and newer releases, causing static perf builds to fail on these distributions. This commit checks the libdw version and only links libebl.a if it detects that the libdw version is older than 0.177. Signed-off-by: Leo Yan <leo.yan@arm.com> Tested-by: Ian Rogers <irogers@google.com> Cc: amadio@gentoo.org Cc: James Clark <james.clark@linaro.org> Cc: Thomas Richter <tmricht@linux.ibm.com> Link: https://lore.kernel.org/r/20240717082211.524826-4-leo.yan@arm.com Signed-off-by: Namhyung Kim <namhyung@kernel.org> |
||
|
Leo Yan
|
440cf77625 |
perf: build: Setup PKG_CONFIG_LIBDIR for cross compilation
On recent Linux distros like Ubuntu Noble and Debian Bookworm, the 'pkg-config-aarch64-linux-gnu' package is missing. As a result, the aarch64-linux-gnu-pkg-config command is not available, which causes build failures. When a build passes the environment variables PKG_CONFIG_LIBDIR or PKG_CONFIG_PATH, like a user uses make command or a build system (like Yocto, Buildroot, etc) prepares the variables and passes to the Perf's Makefile, the commit keeps these variables for package configuration. Otherwise, this commit sets the PKG_CONFIG_LIBDIR variable to use the Multiarch libs for the cross compilation. Signed-off-by: Leo Yan <leo.yan@arm.com> Tested-by: Ian Rogers <irogers@google.com> Cc: amadio@gentoo.org Cc: Thomas Richter <tmricht@linux.ibm.com> Link: https://lore.kernel.org/r/20240717082211.524826-2-leo.yan@arm.com Signed-off-by: Namhyung Kim <namhyung@kernel.org> |
||
|
Linus Torvalds
|
786c8248db |
perf tools fixes for v6.11
Two fixes about building perf and other tools:
* Fix breakage in tracing tools due to pkg-config for libtrace{event,fs}
* Fix build of perf when libunwind is used
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
-----BEGIN PGP SIGNATURE-----
iHQEABYIAB0WIQSo2x5BnqMqsoHtzsmMstVUGiXMgwUCZqA1SAAKCRCMstVUGiXM
g3TfAQDXLi+XcSDE/u5JcDN3H6+bXvavDn2k8Gsd6vWZQc5LEQD3X1E+GbtWTQsE
ruk5ZT3voy8qBPgmrUg72NJwmRxYAQ==
=0RKR
-----END PGP SIGNATURE-----
Merge tag 'perf-tools-fixes-for-v6.11-2024-07-23' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools
Pull perf tools fixes from Namhyung Kim:
"Two fixes for building perf and other tools:
- Fix breakage in tracing tools due to pkg-config for
libtrace{event,fs}
- Fix build of perf when libunwind is used"
* tag 'perf-tools-fixes-for-v6.11-2024-07-23' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools:
perf dso: Fix build when libunwind is enabled
tools/latency: Use pkg-config in lib_setup of Makefile.config
tools/rtla: Use pkg-config in lib_setup of Makefile.config
tools/verification: Use pkg-config in lib_setup of Makefile.config
tools: Make pkg-config dependency checks usable by other tools
perf build: Warn if libtracefs is not found
|