- 03 Nov, 2023 2 commits
-
-
Arnaldo Carvalho de Melo authored
As libelf is a requirement for libbpf if it is not available, as in some container build tests where NO_LIBELF=1 is used, then better warn about the most basic library first. Ditto for libz, check its availability before libbpf too. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/lkml/ZUEehyDk0FkPnvMR@kernel.orgSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
Arnaldo Carvalho de Melo authored
One last case, caught while testing with amazonlinux:2, centos:stream, etc: 4 7.28 amazonlinux:2 : FAIL egrep: warning: egrep is obsolescent; using grep -E gcc version 7.3.1 20180712 (Red Hat 7.3.1-17) (GCC) 8 13.87 centos:stream : FAIL egrep: warning: egrep is obsolescent; using grep -E Reviewed-by:
Guilherme Amadio <amadio@gentoo.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/lkml/ZUEdtblE8qDAQkBK@kernel.orgSigned-off-by:
-
- 31 Oct, 2023 1 commit
-
-
Arnaldo Carvalho de Melo authored
Noticed on fedora 38, the extended regexp that so far was ok for both grep and sed now gets complaints by grep, that says '/' doesn't need to be escaped with '\'. So stop using '/' in sed, use '%' instead and remove the \ before / in the common extended regexp. Link: https://x.com/SMT_Solvers/status/1710380010098344192?s=20 Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/lkml/ZUEddFPTJHVLhH%2F6@kernel.orgSigned-off-by:
-
- 30 Oct, 2023 1 commit
-
-
Namhyung Kim authored
To get the latest fixes in the perf tools including perf stat output, dlfilter and LLVM feature detection. Signed-off-by:Namhyung Kim <namhyung@kernel.org>
-
- 28 Oct, 2023 13 commits
-
-
Ian Rogers authored
Update tsx_cycles_per_elision as per: https://github.com/intel/perfmon/pull/116 Prefer the el-start event rather than cycles-t for detecting whether the metric will work as HLE may be disabled. Remove the metric from sapphirerapids that has no el-start event. Signed-off-by:
Ian Rogers <irogers@google.com> Reviewed-by:
Kan Liang <kan.liang@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Edward Baker <edward.baker@intel.com> Cc: Zhengjun Xing <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20231026003149.3287633-9-irogers@google.comSigned-off-by:
-
Ian Rogers authored
Spelling fixes were already incorporated in the Linux perf tree, update the version number to reflect this. Signed-off-by:
-
Ian Rogers authored
Update westmereex events from v3 to v4 fixing a spelling issue. Signed-off-by:
-
Ian Rogers authored
Update meteorlake from v1.04 to v1.06 adding the changes from: https://github.com/intel/perfmon/commit/bc84df043091ec7c98c0629f3d074d9d7a108194 https://github.com/intel/perfmon/commit/405d3ee987d756b5b5d9a64d8a8fa77559822ecfSigned-off-by:
-
Ian Rogers authored
Update knightslanding from v10 to v16 adding the changes from: https://github.com/intel/perfmon/commit/6c1f169f6ed63ee1fd75ebb303d0fd06d71196f5 https://github.com/intel/perfmon/commit/b22ca587ec8b5ac20471ea2f14924f63e63afe9d https://github.com/intel/perfmon/commit/e685286f083ee81cb7dafd0cd8546c79ee433187Signed-off-by:
-
Ian Rogers authored
Add a missed space. Signed-off-by:
-
Ian Rogers authored
The spelling of "in-flight" was switched to "inflight". Signed-off-by:
-
Ian Rogers authored
Update emeraldrapids to v1.01 from v1.00 adding the changes from: https://github.com/intel/perfmon/commit/3993b600e032a9fd443ffd828aab73de7cb167e5Signed-off-by:
-
Ian Rogers authored
Update alderlake and alderlaken events from v1.21 to v1.23 adding the changes from: https://github.com/intel/perfmon/commit/8df4db9433a2aab59dbbac1a70281032d1af7734 https://github.com/intel/perfmon/commit/846bd247c6e04acc572ca56c992e9e65852bbe63 The tsx_cycles_per_elision metric is updated from PR: https://github.com/intel/perfmon/pull/116Signed-off-by:
-
Arnaldo Carvalho de Melo authored
While building on a wide range of distros and clang versions it was noticed that at least version 12.0.1 (noticed on Alpine 3.15 with "Alpine clang version 12.0.1") is needed to not fail with BTF generation errors such as: Debian:10 Debian clang version 11.0.1-2~deb10u1: CLANG /tmp/build/perf/util/bpf_skel/.tmp/sample_filter.bpf.o <SNIP> GENSKEL /tmp/build/perf/util/bpf_skel/sample_filter.skel.h libbpf: failed to find BTF for extern 'bpf_cast_to_kern_ctx' [21] section: -2 Error: failed to open BPF object file: No such file or directory make[2]: *** [Makefile.perf:1121: /tmp/build/perf/util/bpf_skel/sample_filter.skel.h] Error 254 make[2]: *** Deleting file '/tmp/build/perf/util/bpf_skel/sample_filter.skel.h' Amazon Linux 2: clang version 11.1.0 (Amazon Linux 2 11.1.0-1.amzn2.0.2) GENSKEL /tmp/build/perf/util/bpf_skel/sample_filter.skel.h libbpf: elf: skipping unrecognized data section(18) .eh_frame libbpf: elf: skipping relo section(19) .rel.eh_frame for section(18) .eh_frame libbpf: failed to find BTF for extern 'bpf_cast_to_kern_ctx' [21] section: -2 Error: failed to open BPF object file: No such file or directory make[2]: *** [/tmp/build/perf/util/bpf_skel/sample_filter.skel.h] Error 254 make[2]: *** Deleting file `/tmp/build/perf/util/bpf_skel/sample_filter.skel.h' Ubuntu 20.04: clang version 10.0.0-4ubuntu1 CLANG /tmp/build/perf/util/bpf_skel/.tmp/augmented_raw_syscalls.bpf.o GENSKEL /tmp/build/perf/util/bpf_skel/bench_uprobe.skel.h GENSKEL /tmp/build/perf/util/bpf_skel/bperf_leader.skel.h libbpf: sec '.reluprobe': corrupted symbol #27 pointing to invalid section #65522 for relo #0 GENSKEL /tmp/build/perf/util/bpf_skel/bperf_follower.skel.h Error: failed to open BPF object file: BPF object format invalid make[2]: *** [Makefile.perf:1121: /tmp/build/perf/util/bpf_skel/bench_uprobe.skel.h] Error 95 make[2]: *** Deleting file '/tmp/build/perf/util/bpf_skel/bench_uprobe.skel.h' So check if the version is at least 12.0.1 otherwise disable building BPF skels and provide a message about it, continuing the build. The message, when running on amazonlinux:2: Makefile.config:698: Warning: Disabled BPF skeletons as reliable BTF generation needs at least clang version 12.0.1 Signed-off-by: -
Colin Ian King authored
There are a couple of spelling mistakes in perror messages. Fix them. Signed-off-by:
Colin Ian King <colin.i.king@gmail.com> Cc: kernel-janitors@vger.kernel.org Link: https://lore.kernel.org/r/20231027084633.1167530-1-colin.i.king@gmail.comSigned-off-by:
-
Colin Ian King authored
There is a spelling mistake in a ui error message. Fix it. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
The changes in ("perf evsel: Rename evsel__increase_rlimit to rlimit__increase_nofile") ended up breaking the python binding that now references the rlimit__increase_nofile function, add the util/rlimit.o to the tools/perf/util/python-ext-sources to cure that. This was detected by the 'perf test python' regression test: $ perf test python 14: 'import perf' in python : FAILED! $ perf test -v python Couldn't bump rlimit(MEMLOCK), failures may take place when creating BPF maps, etc 14: 'import perf' in python : --- start --- test child forked, pid 2912462 python usage test: "echo "import sys ; sys.path.insert(0, '/tmp/build/perf-tools-next/python'); import perf" | '/usr/bin/python3' " Traceback (most recent call last): File "<stdin>", line 1, in <module> ImportError: /tmp/build/perf-tools-next/python/perf.cpython-311-x86_64-linux-gnu.so: undefined symbol: rlimit__increase_nofile test child finished with -1 ---- end ---- 'import perf' in python: FAILED! $ Fixes: e093a222 ("perf evsel: Rename evsel__increase_rlimit to rlimit__increase_nofile") Acked-by:Yang Jihong <yangjihong1@huawei.com> Link: https://lore.kernel.org/lkml/ZTrCS5Z3PZAmfPdV@kernel.orgSigned-off-by:
-
- 26 Oct, 2023 3 commits
-
-
James Clark authored
There are two reasons to do this, firstly there is a shellcheck warning in cs_etm_dev_name(), which can be completely deleted. And secondly the current iteration method doesn't support systems with both ETE and ETM because it picks one or the other. There isn't a known system with this configuration, but it could happen in the future. Iterating over all the sources for each CPU can be done by going through /sys/bus/event_source/devices/cs_etm/cpu* and following the symlink back to the Coresight device in /sys/bus/coresight/devices. This will work whether the device is ETE, ETM or any future name, and is much simpler and doesn't require any hard coded version numbers Suggested-by:
Suzuki K Poulose <suzuki.poulose@arm.com> Signed-off-by:
James Clark <james.clark@arm.com> Acked-by:
Leo Yan <leo.yan@linaro.org> Cc: tianruidong@linux.alibaba.com Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Anushree Mathur <anushree.mathur@linux.vnet.ibm.com> Cc: Tiezhu Yang <yangtiezhu@loongson.cn> Cc: atrajeev@linux.vnet.ibm.com Cc: coresight@lists.linaro.org Link: https://lore.kernel.org/r/20231023131550.487760-1-james.clark@arm.comSigned-off-by:
-
Ian Rogers authored
Add tma_info_system_socket_clks and uncore_freq metrics. The associated converter script fix is in: https://github.com/intel/perfmon/pull/112Signed-off-by:
-
Ian Rogers authored
Add tma_info_system_socket_clks and uncore_freq metrics that require a broadwellx style uncore event for UNC_CLOCK. The associated converter script fix is in: https://github.com/intel/perfmon/pull/112 Fixes: 7d124303 ("perf vendor events intel: Update broadwell variant events/metrics") Signed-off-by:
-
- 25 Oct, 2023 20 commits
-
-
Ian Rogers authored
Broadwell-de has a consumer core and server uncore. The uncore_arb PMU isn't present and the broadwellx style cbox PMU should be used instead. Fix the tma_info_system_dram_bw_use metric to use the server metric rather than client. The associated converter script fix is in: https://github.com/intel/perfmon/pull/111 Fixes: 7d124303 ("perf vendor events intel: Update broadwell variant events/metrics") Signed-off-by:
-
Ian Rogers authored
Fix leak where mem_info__put wouldn't release the maps/map as used by perf mem. Add exit functions and use elsewhere that the maps and map are released. Signed-off-by:
-
Ian Rogers authored
Avoid 6 byte hole for padding. Place more frequently used fields first in an attempt to use just 1 cacheline in the common case. Before: ``` struct callchain_list { u64 ip; /* 0 8 */ struct map_symbol ms; /* 8 24 */ struct { _Bool unfolded; /* 32 1 */ _Bool has_children; /* 33 1 */ }; /* 32 2 */ /* XXX 6 bytes hole, try to pack */ u64 branch_count; /* 40 8 */ u64 from_count; /* 48 8 */ u64 predicted_count; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ u64 abort_count; /* 64 8 */ u64 cycles_count; /* 72 8 */ u64 iter_count; /* 80 8 */ u64 iter_cycles; /* 88 8 */ struct branch_type_stat * brtype_stat; /* 96 8 */ const char * srcline; /* 104 8 */ struct list_head list; /* 112 16 */ /* size: 128, cachelines: 2, members: 13 */ /* sum members: 122, holes: 1, sum holes: 6 */ }; ``` After: ``` struct callchain_list { struct list_head list; /* 0 16 */ u64 ip; /* 16 8 */ struct map_symbol ms; /* 24 24 */ const char * srcline; /* 48 8 */ u64 branch_count; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ u64 from_count; /* 64 8 */ u64 cycles_count; /* 72 8 */ u64 iter_count; /* 80 8 */ u64 iter_cycles; /* 88 8 */ struct branch_type_stat * brtype_stat; /* 96 8 */ u64 predicted_count; /* 104 8 */ u64 abort_count; /* 112 8 */ struct { _Bool unfolded; /* 120 1 */ _Bool has_children; /* 121 1 */ }; /* 120 2 */ /* size: 128, cachelines: 2, members: 13 */ /* padding: 6 */ }; ``` Signed-off-by: -
Ian Rogers authored
struct callchain_list is 352bytes in size, 232 of which are brtype_stat. brtype_stat is only used for certain callchain_list items so make it optional, allocating when necessary. So that printing doesn't need to deal with an optional brtype_stat, pass an empty/zero version. Before: ``` struct callchain_list { u64 ip; /* 0 8 */ struct map_symbol ms; /* 8 24 */ struct { _Bool unfolded; /* 32 1 */ _Bool has_children; /* 33 1 */ }; /* 32 2 */ /* XXX 6 bytes hole, try to pack */ u64 branch_count; /* 40 8 */ u64 from_count; /* 48 8 */ u64 predicted_count; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ u64 abort_count; /* 64 8 */ u64 cycles_count; /* 72 8 */ u64 iter_count; /* 80 8 */ u64 iter_cycles; /* 88 8 */ struct branch_type_stat brtype_stat; /* 96 232 */ /* --- cacheline 5 boundary (320 bytes) was 8 bytes ago --- */ const char * srcline; /* 328 8 */ struct list_head list; /* 336 16 */ /* size: 352, cachelines: 6, members: 13 */ /* sum members: 346, holes: 1, sum holes: 6 */ /* last cacheline: 32 bytes */ }; ``` After: ``` struct callchain_list { u64 ip; /* 0 8 */ struct map_symbol ms; /* 8 24 */ struct { _Bool unfolded; /* 32 1 */ _Bool has_children; /* 33 1 */ }; /* 32 2 */ /* XXX 6 bytes hole, try to pack */ u64 branch_count; /* 40 8 */ u64 from_count; /* 48 8 */ u64 predicted_count; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ u64 abort_count; /* 64 8 */ u64 cycles_count; /* 72 8 */ u64 iter_count; /* 80 8 */ u64 iter_cycles; /* 88 8 */ struct branch_type_stat * brtype_stat; /* 96 8 */ const char * srcline; /* 104 8 */ struct list_head list; /* 112 16 */ /* size: 128, cachelines: 2, members: 13 */ /* sum members: 122, holes: 1, sum holes: 6 */ }; ``` Signed-off-by: -
Ian Rogers authored
Display code doesn't modify the branch_type_stat so switch uses to const. This is done to aid refactoring struct callchain_list where current the branch_type_stat is embedded even if not used. Signed-off-by:
-
Ian Rogers authored
Caught by address/leak sanitizer. Signed-off-by:
-
Ian Rogers authored
Commit 40826c45 ("perf thread: Remove notion of dead threads") removed dead threads but the list head wasn't removed. Remove it here. Signed-off-by:
-
Ian Rogers authored
Caught using reference count checking on perf top with "--call-graph=lbr". After this no memory leaks were detected. Fixes: 57849998 ("perf report: Add processing for cycle histograms") Signed-off-by:
-
Ian Rogers authored
Comparing pointers with reference count checking is tricky to avoid a SEGV. Add a convenience macro to simplify and use. Signed-off-by:
-
Ian Rogers authored
Make the implicit REFCOUNT_CHECKING robust to when building with GCC. Fixes: 9be6ab18 ("libperf rc_check: Enable implicitly with sanitizers") Signed-off-by:
-
Ian Rogers authored
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: e2b23483 ("perf machine: Factor out lbr_callchain_add_lbr_ip()") Signed-off-by:
-
Ian Rogers authored
Mutex error check will capture trying to take the lock recursively and other problems that rwlock won't. At the expense of concurrency, adda debug mode that uses a mutex in place of a rwsem. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
To address this grep 3.8 warning: grep: warning: stray \ before # We needed to remove the '' around the grep expression and keep the \ before # so that it is escaped by the $(shell grep ...) and thus doesn't get to grep. We need that \ before the #, otherwise we get this: Makefile.perf:364: *** unterminated call to function 'shell': missing ')'. Stop. As everything after the # will be considered a comment. Removing the single quotes needs some more escaping so that _some_ of the escaped chars gets to grep, like the '\|' that becomes '\\\|´. Running on debian:10, where there is no libtraceevent-devel available, we get: Makefile.perf:367: *** PYTHON_EXT_SRCS= util/python.c ../lib/ctype.c util/cap.c util/evlist.c util/evsel.c util/evsel_fprintf.c util/perf_event_attr_fprintf.c util/cpumap.c util/memswap.c util/mmap.c util/namespaces.c ../lib/bitmap.c ../lib/find_bit.c ../lib/list_sort.c ../lib/hweight.c ../lib/string.c ../lib/vsprintf.c util/thread_map.c util/util.c util/cgroup.c util/parse-branch-options.c util/rblist.c util/counts.c util/print_binary.c util/strlist.c ../lib/rbtree.c util/string.c util/symbol_fprintf.c util/units.c util/affinity.c util/rwsem.c util/hashmap.c util/perf_regs.c util/fncache.c util/perf-regs-arch/perf_regs_aarch64.c util/perf-regs-arch/perf_regs_arm.c util/perf-regs-arch/perf_regs_csky.c util/perf-regs-arch/perf_regs_loongarch.c util/perf-regs-arch/perf_regs_mips.c util/perf-regs-arch/perf_regs_powerpc.c util/perf-regs-arch/perf_regs_riscv.c util/perf-regs-arch/perf_regs_s390.c util/perf-regs-arch/perf_regs_x86.c. Stop. make[1]: *** [Makefile.perf:242: sub-make] Error 2 I.e. both the comments and the util/trace-event.c were removed. When using: msg := $(error PYTHON_EXT_SRCS=$(PYTHON_EXT_SRCS)) While on the more recent fedora:38, with the new grep and make packages and libtraceevent-devel installed: Makefile.perf:367: *** PYTHON_EXT_SRCS= util/python.c ../lib/ctype.c util/cap.c util/evlist.c util/evsel.c util/evsel_fprintf.c util/perf_event_attr_fprintf.c util/cpumap.c util/memswap.c util/mmap.c util/namespaces.c ../lib/bitmap.c ../lib/find_bit.c ../lib/list_sort.c ../lib/hweight.c ../lib/string.c ../lib/vsprintf.c util/thread_map.c util/util.c util/cgroup.c util/parse-branch-options.c util/rblist.c util/counts.c util/print_binary.c util/strlist.c util/trace-event.c ../lib/rbtree.c util/string.c util/symbol_fprintf.c util/units.c util/affinity.c util/rwsem.c util/hashmap.c util/perf_regs.c util/fncache.c util/perf-regs-arch/perf_regs_aarch64.c util/perf-regs-arch/perf_regs_arm.c util/perf-regs-arch/perf_regs_csky.c util/perf-regs-arch/perf_regs_loongarch.c util/perf-regs-arch/perf_regs_mips.c util/perf-regs-arch/perf_regs_powerpc.c util/perf-regs-arch/perf_regs_riscv.c util/perf-regs-arch/perf_regs_s390.c util/perf-regs-arch/perf_regs_x86.c. Stop. make[1]: *** [Makefile.perf:242: sub-make] Error 2 make: *** [Makefile:113: install-bin] Error 2 make: Leaving directory '/home/acme/git/perf-tools-next/tools/perf' $ I.e. only the comments were removed. If we build it on the same fedora:38 system, but using NO_LIBTRACEEVENT=1 $ make NO_LIBTRACEEVENT=1 CORESIGHT=1 O=/tmp/build/$(basename $PWD) -C tools/perf install-bin Makefile.perf:367: *** PYTHON_EXT_SRCS= util/python.c ../lib/ctype.c util/cap.c util/evlist.c util/evsel.c util/evsel_fprintf.c util/perf_event_attr_fprintf.c util/cpumap.c util/memswap.c util/mmap.c util/namespaces.c ../lib/bitmap.c ../lib/find_bit.c ../lib/list_sort.c ../lib/hweight.c ../lib/string.c ../lib/vsprintf.c util/thread_map.c util/util.c util/cgroup.c util/parse-branch-options.c util/rblist.c util/counts.c util/print_binary.c util/strlist.c ../lib/rbtree.c util/string.c util/symbol_fprintf.c util/units.c util/affinity.c util/rwsem.c util/hashmap.c util/perf_regs.c util/fncache.c util/perf-regs-arch/perf_regs_aarch64.c util/perf-regs-arch/perf_regs_arm.c util/perf-regs-arch/perf_regs_csky.c util/perf-regs-arch/perf_regs_loongarch.c util/perf-regs-arch/perf_regs_mips.c util/perf-regs-arch/perf_regs_powerpc.c util/perf-regs-arch/perf_regs_riscv.c util/perf-regs-arch/perf_regs_s390.c util/perf-regs-arch/perf_regs_x86.c. Stop. make[1]: *** [Makefile.perf:242: sub-make] Error 2 make: *** [Makefile:113: install-bin] Error 2 make: Leaving directory '/home/acme/git/perf-tools-next/tools/perf' $ Both comments and the util/trace-event.c file removed. Signed-off-by:
-
Namhyung Kim authored
The hierarchy mode needs to setup output formats for each evsel. Normally setup_sorting() handles this at the beginning, but it cannot do that if data comes from a pipe since there's no evsel info before reading the data. And then perf report cannot process the samples in hierarchy mode and think as if there's no sample. Let's check the condition and setup the output formats after reading data so that it can find evsels. Before: $ ./perf record -o- true | ./perf report -i- --hierarchy -q [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.000 MB - ] Error: The - data has no samples! After: $ ./perf record -o- true | ./perf report -i- --hierarchy -q [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.000 MB - ] 94.76% true 94.76% [kernel.kallsyms] 94.76% [k] filemap_fault 5.24% perf-ex 5.24% [kernel.kallsyms] 5.06% [k] __memset 0.18% [k] native_write_msr Acked-by: -
Namhyung Kim authored
Currently lock contention timestamp is maintained in a hash map keyed by pid. That means it needs to get and release a map element (which is proctected by spinlock!) on each contention begin and end pair. This can impact on performance if there are a lot of contention (usually from spinlocks). It used to go with task local storage but it had an issue on memory allocation in some critical paths. Although it's addressed in recent kernels IIUC, the tool should support old kernels too. So it cannot simply switch to the task local storage at least for now. As spinlocks create lots of contention and they disabled preemption during the spinning, it can use per-cpu array to keep the timestamp to avoid overhead in hashmap update and delete. In contention_begin, it's easy to check the lock types since it can see the flags. But contention_end cannot see it. So let's try to per-cpu array first (unconditionally) if it has an active element (lock != 0). Then it should be used and per-task tstamp map should not be used until the per-cpu array element is cleared which means nested spinlock contention (if any) was finished and it nows see (the outer) lock. Signed-off-by:
-
Namhyung Kim authored
When pelem is NULL, it'd create a new entry with zero data. But it might be preempted by IRQ/NMI just before calling bpf_map_update_elem() then there's a chance to call it twice for the same pid. So it'd be better to use BPF_NOEXIST flag and check the return value to prevent the race. Signed-off-by:
-
Namhyung Kim authored
It checks the current lock to calculated the delta of contention time. The address is saved in the tstamp map which is allocated at begining of contention and released at end of contention. But it's possible for bpf_map_delete_elem() to fail. In that case, the element in the tstamp map kept for the current lock and it makes the next contention for the same lock tracked incorrectly. Specificially the next contention begin will see the existing element for the task and it'd just return. Then the next contention end will see the element and calculate the time using the timestamp for the previous begin. This can result in a large value for two small contentions happened from time to time. Let's clear the lock address so that it can be updated next time even if the bpf_map_delete_elem() failed. Signed-off-by:
-
Yang Jihong authored
evsel__increase_rlimit() helper does nothing with evsel, and description of the functionality is inaccurate, rename it and move to util/rlimit.c. By the way, fix a checkppatch warning about misplaced license tag: WARNING: Misplaced SPDX-License-Identifier tag - use line 1 instead #160: FILE: tools/perf/util/rlimit.h:3: /* SPDX-License-Identifier: LGPL-2.1 */ No functional change. Signed-off-by:
-
Namhyung Kim authored
The -G/--cgroups option is to put sender and receiver in different cgroups in order to measure cgroup context switch overheads. Users need to make sure the cgroups exist and accessible. The following example should the effect of this change. Please don't forget taskset before the perf bench to measure cgroup switches properly. Otherwise each task would run on a different CPU and generate cgroup switches regardless of this change. # perf stat -e context-switches,cgroup-switches \ > taskset -c 0 perf bench sched pipe -l 10000 > /dev/null Performance counter stats for 'taskset -c 0 perf bench sched pipe -l 10000': 20,001 context-switches 2 cgroup-switches 0.053449651 seconds time elapsed 0.011286000 seconds user 0.041869000 seconds sys # perf stat -e context-switches,cgroup-switches \ > taskset -c 0 perf bench sched pipe -l 10000 -G AAA,BBB > /dev/null Performance counter stats for 'taskset -c 0 perf bench sched pipe -l 10000 -G AAA,BBB': 20,001 context-switches 20,001 cgroup-switches 0.052768627 seconds time elapsed 0.006284000 seconds user 0.046266000 seconds sys Signed-off-by: -
Michael Petlan authored
CoreSight might be not available, in such case, skip the tests. Signed-off-by:
Michael Petlan <mpetlan@redhat.com> Reviewed-by:
Carsten Haitzler <carsten.haitzler@arm.com> Cc: vmolnaro@redhat.com Link: https://lore.kernel.org/r/20231019091137.22525-1-mpetlan@redhat.comSigned-off-by:
-
