user/sven/linux.git/tools/perf, branch v6.1.65

perf intel-pt: Fix async branch flags

2023-11-28T17:07:07Z

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

2023-11-20T10:52:12Z

[ 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

2023-11-20T10:52:12Z

[ 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

2023-11-20T10:52:10Z

[ 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 kwork: Set ordered_events to true in 'struct perf_tool'

2023-11-20T10:52:09Z

[ Upstream commit 0c526579a4b2b6ecd540472f2e34c2850cf70f76 ] 'perf kwork' processes data based on timestamps and needs to sort events. Fixes: f98919ec4fccdacf ("perf kwork: Implement 'report' subcommand") Reviewed-by: Ian Rogers Signed-off-by: Yang Jihong Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Yang Jihong Link: https://lore.kernel.org/r/20230812084917.169338-4-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin

perf kwork: Add the supported subcommands to the document

2023-11-20T10:52:09Z

[ Upstream commit 76e0d8c821bbd952730799cc7af841f9de67b7f7 ] Add missing report, latency and timehist subcommands to the document. Fixes: f98919ec4fccdacf ("perf kwork: Implement 'report' subcommand") Fixes: ad3d9f7a929ab2df ("perf kwork: Implement perf kwork latency") Fixes: bcc8b3e88d6fa1a3 ("perf kwork: Implement perf kwork timehist") Reviewed-by: Ian Rogers Signed-off-by: Yang Jihong Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Link: https://lore.kernel.org/r/20230812084917.169338-3-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin

perf kwork: Fix incorrect and missing free atom in work_push_atom()

2023-11-20T10:52:09Z

[ Upstream commit d39710088d82ef100b33cdf4a9de3546fb0bb5df ] 1. Atoms are managed in page mode and should be released using atom_free() instead of free(). 2. When the event does not match, the atom needs to free. Fixes: f98919ec4fccdacf ("perf kwork: Implement 'report' subcommand") Reviewed-by: Ian Rogers Signed-off-by: Yang Jihong Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Yang Jihong Link: https://lore.kernel.org/r/20230812084917.169338-2-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin

perf stat: Fix aggr mode initialization

2023-11-20T10:52:09Z

[ Upstream commit a84fbf205609313594b86065c67e823f09ebe29b ] Generating metrics llc_code_read_mpi_demand_plus_prefetch, llc_data_read_mpi_demand_plus_prefetch, llc_miss_local_memory_bandwidth_read, llc_miss_local_memory_bandwidth_write, nllc_miss_remote_memory_bandwidth_read, memory_bandwidth_read, memory_bandwidth_write, uncore_frequency, upi_data_transmit_bw, C2_Pkg_Residency, C3_Core_Residency, C3_Pkg_Residency, C6_Core_Residency, C6_Pkg_Residency, C7_Core_Residency, C7_Pkg_Residency, UNCORE_FREQ and tma_info_system_socket_clks would trigger an address sanitizer heap-buffer-overflows on a SkylakeX. ``` ==2567752==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x5020003ed098 at pc 0x5621a816654e bp 0x7fffb55d4da0 sp 0x7fffb55d4d98 READ of size 4 at 0x5020003eee78 thread T0 #0 0x558265d6654d in aggr_cpu_id__is_empty tools/perf/util/cpumap.c:694:12 #1 0x558265c914da in perf_stat__get_aggr tools/perf/builtin-stat.c:1490:6 #2 0x558265c914da in perf_stat__get_global_cached tools/perf/builtin-stat.c:1530:9 #3 0x558265e53290 in should_skip_zero_counter tools/perf/util/stat-display.c:947:31 #4 0x558265e53290 in print_counter_aggrdata tools/perf/util/stat-display.c:985:18 #5 0x558265e51931 in print_counter tools/perf/util/stat-display.c:1110:3 #6 0x558265e51931 in evlist__print_counters tools/perf/util/stat-display.c:1571:5 #7 0x558265c8ec87 in print_counters tools/perf/builtin-stat.c:981:2 #8 0x558265c8cc71 in cmd_stat tools/perf/builtin-stat.c:2837:3 #9 0x558265bb9bd4 in run_builtin tools/perf/perf.c:323:11 #10 0x558265bb98eb in handle_internal_command tools/perf/perf.c:377:8 #11 0x558265bb9389 in run_argv tools/perf/perf.c:421:2 #12 0x558265bb9389 in main tools/perf/perf.c:537:3 ``` The issue was the use of testing a cpumap with NULL rather than using empty, as a map containing the dummy value isn't NULL and the -1 results in an empty aggr map being allocated which legitimately overflows when any member is accessed. Fixes: 8a96f454f5668572 ("perf stat: Avoid SEGV if core.cpus isn't set") Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230906003912.3317462-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin

perf evlist: Avoid frequency mode for the dummy event

2023-11-08T13:11:02Z

[ 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

2023-10-06T12:56:58Z

[ 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