linux-stable.git/tools/perf/util, branch v6.1.78

perf env: Avoid recursively taking env->bpf_progs.lock

2024-01-25T23:27:48+00:00

[ Upstream commit 9c51f8788b5d4e9f46afbcf563255cfd355690b3 ]

Add variants of perf_env__insert_bpf_prog_info(), perf_env__insert_btf()
and perf_env__find_btf prefixed with __ to indicate the
env->bpf_progs.lock is assumed held.

Call these variants when the lock is held to avoid recursively taking it
and potentially having a thread deadlock with itself.

Fixes: f8dfeae009effc0b ("perf bpf: Show more BPF program info in print_bpf_prog_info()")
Signed-off-by: Ian Rogers 
Acked-by: Jiri Olsa 
Acked-by: Song Liu 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Huacai Chen 
Cc: Ingo Molnar 
Cc: K Prateek Nayak 
Cc: Kan Liang 
Cc: Mark Rutland 
Cc: Ming Wang 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Ravi Bangoria 
Link: https://lore.kernel.org/r/20231207014655.1252484-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Sasha Levin

perf genelf: Set ELF program header addresses properly

2024-01-25T23:27:47+00:00

[ Upstream commit 1af478903fc48c1409a8dd6b698383b62387adf1 ]

The text section starts after the ELF headers so PHDR.p_vaddr and
others should have the correct addresses.

Fixes: babd04386b1df8c3 ("perf jit: Include program header in ELF files")
Reviewed-by: Ian Rogers 
Signed-off-by: Namhyung Kim 
Cc: Adrian Hunter 
Cc: Fangrui Song 
Cc: Ingo Molnar 
Cc: Jiri Olsa 
Cc: Lieven Hey 
Cc: Milian Wolff 
Cc: Pablo Galindo 
Cc: Peter Zijlstra 
Link: https://lore.kernel.org/r/20231212070547.612536-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Sasha Levin

perf hisi-ptt: Fix one memory leakage in hisi_ptt_process_auxtrace_event()

2024-01-25T23:27:47+00:00

[ Upstream commit 1bc479d665bc25a9a4e8168d5b400a47491511f9 ]

ASan complains a memory leakage in hisi_ptt_process_auxtrace_event()
that the data buffer is not freed. Since currently we only support the
raw dump trace mode, the data buffer is used only within this function.
So fix this by freeing the data buffer before going out.

Fixes: 5e91e57e68090c0e ("perf auxtrace arm64: Add support for parsing HiSilicon PCIe Trace packet")
Reviewed-by: Ian Rogers 
Signed-off-by: Yicong Yang 
Acked-by: Namhyung Kim 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Ingo Molnar 
Cc: Jiri Olsa 
Cc: Jonathan Cameron 
Cc: Junhao He 
Cc: Mark Rutland 
Cc: Peter Zijlstra 
Cc: Qi Liu 
Link: https://lore.kernel.org/r/20231207081635.8427-3-yangyicong@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Sasha Levin

perf header: Fix one memory leakage in perf_event__fprintf_event_update()

2024-01-25T23:27:47+00:00

[ Upstream commit 813900d19b923fc1b241c1ce292472f68066092b ]

When dump the raw trace by `perf report -D` ASan reports a memory
leakage in perf_event__fprintf_event_update().

It shows that we allocated a temporary cpumap for dumping the CPUs but
doesn't release it and it's not used elsewhere. Fix this by free the
cpumap after the dumping.

Fixes: c853f9394b7bc189 ("perf tools: Add perf_event__fprintf_event_update function")
Reviewed-by: Ian Rogers 
Signed-off-by: Yicong Yang 
Acked-by: Namhyung Kim 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Ingo Molnar 
Cc: Jiri Olsa 
Cc: Jonathan Cameron 
Cc: Junhao He 
Cc: Mark Rutland 
Cc: Peter Zijlstra 
Cc: linuxarm@huawei.com
Link: https://lore.kernel.org/r/20231207081635.8427-2-yangyicong@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Sasha Levin

perf intel-pt: Fix async branch flags

2023-11-28T17:07:07+00:00

commit f2d87895cbc4af80649850dcf5da36de6b2ed3dd upstream.

Ensure PERF_IP_FLAG_ASYNC is set always for asynchronous branches (i.e.
interrupts etc).

Fixes: 90e457f7be08 ("perf tools: Add Intel PT support")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter 
Acked-by: Namhyung Kim 
Link: https://lore.kernel.org/r/20230928072953.19369-1-adrian.hunter@intel.com
Signed-off-by: Namhyung Kim 
Signed-off-by: Greg Kroah-Hartman

perf hist: Add missing puts to hist__account_cycles

2023-11-20T10:52:12+00:00

[ Upstream commit c1149037f65bcf0334886180ebe3d5efcf214912 ]

Caught using reference count checking on perf top with
"--call-graph=lbr". After this no memory leaks were detected.

Fixes: 57849998e2cd ("perf report: Add processing for cycle histograms")
Signed-off-by: Ian Rogers 
Cc: K Prateek Nayak 
Cc: Ravi Bangoria 
Cc: Sandipan Das 
Cc: Anshuman Khandual 
Cc: German Gomez 
Cc: James Clark 
Cc: Nick Terrell 
Cc: Sean Christopherson 
Cc: Changbin Du 
Cc: liuwenyu 
Cc: Yang Jihong 
Cc: Masami Hiramatsu 
Cc: Miguel Ojeda 
Cc: Song Liu 
Cc: Leo Yan 
Cc: Kajol Jain 
Cc: Andi Kleen 
Cc: Kan Liang 
Cc: Athira Rajeev 
Cc: Yanteng Si 
Cc: Liam Howlett 
Cc: Paolo Bonzini 
Link: https://lore.kernel.org/r/20231024222353.3024098-6-irogers@google.com
Signed-off-by: Namhyung Kim 
Signed-off-by: Sasha Levin

perf machine: Avoid out of bounds LBR memory read

2023-11-20T10:52:12+00:00

[ Upstream commit ab8ce150781d326c6bfbe1e09f175ffde1186f80 ]

Running perf top with address sanitizer and "--call-graph=lbr" fails
due to reading sample 0 when no samples exist. Add a guard to prevent
this.

Fixes: e2b23483eb1d ("perf machine: Factor out lbr_callchain_add_lbr_ip()")
Signed-off-by: Ian Rogers 
Cc: K Prateek Nayak 
Cc: Ravi Bangoria 
Cc: Sandipan Das 
Cc: Anshuman Khandual 
Cc: German Gomez 
Cc: James Clark 
Cc: Nick Terrell 
Cc: Sean Christopherson 
Cc: Changbin Du 
Cc: liuwenyu 
Cc: Yang Jihong 
Cc: Masami Hiramatsu 
Cc: Miguel Ojeda 
Cc: Song Liu 
Cc: Leo Yan 
Cc: Kajol Jain 
Cc: Andi Kleen 
Cc: Kan Liang 
Cc: Athira Rajeev 
Cc: Yanteng Si 
Cc: Liam Howlett 
Cc: Paolo Bonzini 
Link: https://lore.kernel.org/r/20231024222353.3024098-3-irogers@google.com
Signed-off-by: Namhyung Kim 
Signed-off-by: Sasha Levin

perf record: Fix BTF type checks in the off-cpu profiling

2023-11-20T10:52:10+00:00

[ Upstream commit 0e501a65d35bf72414379fed0e31a0b6b81ab57d ]

The BTF func proto for a tracepoint has one more argument than the
actual tracepoint function since it has a context argument at the
begining.  So it should compare to 5 when the tracepoint has 4
arguments.

  typedef void (*btf_trace_sched_switch)(void *, bool, struct task_struct *, struct task_struct *, unsigned int);

Also, recent change in the perf tool would use a hand-written minimal
vmlinux.h to generate BTF in the skeleton.  So it won't have the info
of the tracepoint.  Anyway it should use the kernel's vmlinux BTF to
check the type in the kernel.

Fixes: b36888f71c85 ("perf record: Handle argument change in sched_switch")
Reviewed-by: Ian Rogers 
Acked-by: Song Liu 
Cc: Hao Luo 
CC: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230922234444.3115821-1-namhyung@kernel.org
Signed-off-by: Namhyung Kim 
Signed-off-by: Sasha Levin

perf evlist: Avoid frequency mode for the dummy event

2023-11-08T13:11:02+00:00

[ Upstream commit f9cdeb58a9cf46c09b56f5f661ea8da24b6458c3 ]

Dummy events are created with an attribute where the period and freq
are zero. evsel__config will then see the uninitialized values and
initialize them in evsel__default_freq_period. As fequency mode is
used by default the dummy event would be set to use frequency
mode. However, this has no effect on the dummy event but does cause
unnecessary timers/interrupts. Avoid this overhead by setting the
period to 1 for dummy events.

evlist__add_aux_dummy calls evlist__add_dummy then sets freq=0 and
period=1. This isn't necessary after this change and so the setting is
removed.

From Stephane:

The dummy event is not counting anything. It is used to collect mmap
records and avoid a race condition during the synthesize mmap phase of
perf record. As such, it should not cause any overhead during active
profiling. Yet, it did. Because of a bug the dummy event was
programmed as a sampling event in frequency mode. Events in that mode
incur more kernel overheads because on timer tick, the kernel has to
look at the number of samples for each event and potentially adjust
the sampling period to achieve the desired frequency. The dummy event
was therefore adding a frequency event to task and ctx contexts we may
otherwise not have any, e.g.,

  perf record -a -e cpu/event=0x3c,period=10000000/.

On each timer tick the perf_adjust_freq_unthr_context() is invoked and
if ctx->nr_freq is non-zero, then the kernel will loop over ALL the
events of the context looking for frequency mode ones. In doing, so it
locks the context, and enable/disable the PMU of each hw event. If all
the events of the context are in period mode, the kernel will have to
traverse the list for nothing incurring overhead. The overhead is
multiplied by a very large factor when this happens in a guest kernel.
There is no need for the dummy event to be in frequency mode, it does
not count anything and therefore should not cause extra overhead for
no reason.

Fixes: 5bae0250237f ("perf evlist: Introduce perf_evlist__new_dummy constructor")
Reported-by: Stephane Eranian 
Signed-off-by: Ian Rogers 
Acked-by: Adrian Hunter 
Cc: Yang Jihong 
Cc: Kan Liang 
Link: https://lore.kernel.org/r/20230916035640.1074422-1-irogers@google.com
Signed-off-by: Namhyung Kim 
Signed-off-by: Sasha Levin

perf build: Define YYNOMEM as YYNOABORT for bison < 3.81

2023-10-06T12:56:58+00:00

[ Upstream commit 88cc47e24597971b05b6e94c28a2fc81d2a8d61a ]

YYNOMEM was introduced in bison 3.81, so define it as YYABORT for older
versions, which should provide the previous perf behaviour.

Cc: Adrian Hunter 
Cc: Ian Rogers 
Cc: Jiri Olsa 
Cc: Namhyung Kim 
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Sasha Levin