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
...
Pull non-MM updates from Andrew Morton:
- The series "resource: A couple of cleanups" from Andy Shevchenko
performs some cleanups in the resource management code
- The series "Improve the copy of task comm" from Yafang Shao addresses
possible race-induced overflows in the management of
task_struct.comm[]
- The series "Remove unnecessary header includes from
{tools/}lib/list_sort.c" from Kuan-Wei Chiu adds some cleanups and a
small fix to the list_sort library code and to its selftest
- The series "Enhance min heap API with non-inline functions and
optimizations" also from Kuan-Wei Chiu optimizes and cleans up the
min_heap library code
- The series "nilfs2: Finish folio conversion" from Ryusuke Konishi
finishes off nilfs2's folioification
- The series "add detect count for hung tasks" from Lance Yang adds
more userspace visibility into the hung-task detector's activity
- Apart from that, singelton patches in many places - please see the
individual changelogs for details
* tag 'mm-nonmm-stable-2024-11-24-02-05' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (71 commits)
gdb: lx-symbols: do not error out on monolithic build
kernel/reboot: replace sprintf() with sysfs_emit()
lib: util_macros_kunit: add kunit test for util_macros.h
util_macros.h: fix/rework find_closest() macros
Improve consistency of '#error' directive messages
ocfs2: fix uninitialized value in ocfs2_file_read_iter()
hung_task: add docs for hung_task_detect_count
hung_task: add detect count for hung tasks
dma-buf: use atomic64_inc_return() in dma_buf_getfile()
fs/proc/kcore.c: fix coccinelle reported ERROR instances
resource: avoid unnecessary resource tree walking in __region_intersects()
ocfs2: remove unused errmsg function and table
ocfs2: cluster: fix a typo
lib/scatterlist: use sg_phys() helper
checkpatch: always parse orig_commit in fixes tag
nilfs2: convert metadata aops from writepage to writepages
nilfs2: convert nilfs_recovery_copy_block() to take a folio
nilfs2: convert nilfs_page_count_clean_buffers() to take a folio
nilfs2: remove nilfs_writepage
nilfs2: convert checkpoint file to be folio-based
...
Pull bpf updates from Alexei Starovoitov:
- Add BPF uprobe session support (Jiri Olsa)
- Optimize uprobe performance (Andrii Nakryiko)
- Add bpf_fastcall support to helpers and kfuncs (Eduard Zingerman)
- Avoid calling free_htab_elem() under hash map bucket lock (Hou Tao)
- Prevent tailcall infinite loop caused by freplace (Leon Hwang)
- Mark raw_tracepoint arguments as nullable (Kumar Kartikeya Dwivedi)
- Introduce uptr support in the task local storage map (Martin KaFai
Lau)
- Stringify errno log messages in libbpf (Mykyta Yatsenko)
- Add kmem_cache BPF iterator for perf's lock profiling (Namhyung Kim)
- Support BPF objects of either endianness in libbpf (Tony Ambardar)
- Add ksym to struct_ops trampoline to fix stack trace (Xu Kuohai)
- Introduce private stack for eligible BPF programs (Yonghong Song)
- Migrate samples/bpf tests to selftests/bpf test_progs (Daniel T. Lee)
- Migrate test_sock to selftests/bpf test_progs (Jordan Rife)
* tag 'bpf-next-6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (152 commits)
libbpf: Change hash_combine parameters from long to unsigned long
selftests/bpf: Fix build error with llvm 19
libbpf: Fix memory leak in bpf_program__attach_uprobe_multi
bpf: use common instruction history across all states
bpf: Add necessary migrate_disable to range_tree.
bpf: Do not alloc arena on unsupported arches
selftests/bpf: Set test path for token/obj_priv_implicit_token_envvar
selftests/bpf: Add a test for arena range tree algorithm
bpf: Introduce range_tree data structure and use it in bpf arena
samples/bpf: Remove unused variable in xdp2skb_meta_kern.c
samples/bpf: Remove unused variables in tc_l2_redirect_kern.c
bpftool: Cast variable `var` to long long
bpf, x86: Propagate tailcall info only for subprogs
bpf: Add kernel symbol for struct_ops trampoline
bpf: Use function pointers count as struct_ops links count
bpf: Remove unused member rcu from bpf_struct_ops_map
selftests/bpf: Add struct_ops prog private stack tests
bpf: Support private stack for struct_ops progs
selftests/bpf: Add tracing prog private stack tests
bpf, x86: Support private stack in jit
...
Cross-merge bpf fixes after downstream PR.
In particular to bring the fix in
commit aa30eb3260 ("bpf: Force checkpoint when jmp history is too long").
The follow up verifier work depends on it.
And the fix in
commit 6801cf7890 ("selftests/bpf: Use -4095 as the bad address for bits iterator").
It's fixing instability of BPF CI on s390 arch.
No conflicts.
Adjacent changes in:
Auto-merging arch/Kconfig
Auto-merging kernel/bpf/helpers.c
Auto-merging kernel/bpf/memalloc.c
Auto-merging kernel/bpf/verifier.c
Auto-merging mm/slab_common.c
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Adding support to attach program in uprobe session mode
with bpf_program__attach_uprobe_multi function.
Adding session bool to bpf_uprobe_multi_opts struct that allows
to load and attach the bpf program via uprobe session.
the attachment to create uprobe multi session.
Also adding new program loader section that allows:
SEC("uprobe.session/bpf_fentry_test*")
and loads/attaches uprobe program as uprobe session.
Adding sleepable hook (uprobe.session.s) as well.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20241108134544.480660-6-jolsa@kernel.org
Adding support to attach BPF program for entry and return probe
of the same function. This is common use case which at the moment
requires to create two uprobe multi links.
Adding new BPF_TRACE_UPROBE_SESSION attach type that instructs
kernel to attach single link program to both entry and exit probe.
It's possible to control execution of the BPF program on return
probe simply by returning zero or non zero from the entry BPF
program execution to execute or not the BPF program on return
probe respectively.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20241108134544.480660-4-jolsa@kernel.org
The sampling handler, provided by the user alongside a void* context,
was invoked with an internal structure instead of the user context.
Correct the invocation of the sampling handler to pass the user context
pointer instead.
Note that the approach taken is similar to that in events.c, and will
reduce the chances of this mistake happening if additional sampling
callbacks are added.
Fixes: 47c4b0de08 ("tools/lib/thermal: Add a thermal library")
Signed-off-by: Emil Dahl Juhl <emdj@bang-olufsen.dk>
Link: https://lore.kernel.org/r/20241015171826.170154-1-emdj@bang-olufsen.dk
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
The thermal netlink has been extended with more commands which require
an encoding with more information. The generic encoding function puts
the thermal zone id with the command name. It is the unique
parameters.
The next changes will provide more parameters to the command. Set the
scene for those new parameters by making the encoding function more
generic.
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://patch.msgid.link/20241022155147.463475-4-daniel.lezcano@linaro.org
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Since BPF skeleton inception libbpf has been doing mmap()'ing of global
data ARRAY maps in bpf_object__load_skeleton() API, which is used by
code generated .skel.h files (i.e., by BPF skeletons only).
This is wrong because if BPF object is loaded through generic
bpf_object__load() API, global data maps won't be re-mmap()'ed after
load step, and memory pointers returned from bpf_map__initial_value()
would be wrong and won't reflect the actual memory shared between BPF
program and user space.
bpf_map__initial_value() return result is rarely used after load, so
this went unnoticed for a really long time, until bpftrace project
attempted to load BPF object through generic bpf_object__load() API and
then used BPF subskeleton instantiated from such bpf_object. It turned
out that .data/.rodata/.bss data updates through such subskeleton was
"blackholed", all because libbpf wouldn't re-mmap() those maps during
bpf_object__load() phase.
Long story short, this step should be done by libbpf regardless of BPF
skeleton usage, right after BPF map is created in the kernel. This patch
moves this functionality into bpf_object__populate_internal_map() to
achieve this. And bpf_object__load_skeleton() is now simple and almost
trivial, only propagating these mmap()'ed pointers into user-supplied
skeleton structs.
We also do trivial adjustments to error reporting inside
bpf_object__populate_internal_map() for consistency with the rest of
libbpf's map-handling code.
Reported-by: Alastair Robertson <ajor@meta.com>
Reported-by: Jonathan Wiepert <jwiepert@meta.com>
Fixes: d66562fba1 ("libbpf: Add BPF object skeleton support")
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20241023043908.3834423-3-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
