From: Namhyung Kim Date: Thu, 4 Jun 2026 17:28:39 +0000 (-0700) Subject: perf lock contention: Allow 'mmap_lock' in -L/--lock-filter X-Git-Tag: v7.2-rc1~60^2~125 X-Git-Url: http://git.ipfire.org/gitweb/?a=commitdiff_plain;h=b72ab69175157aac2f3ff1ebc0765e3899ba295b;p=thirdparty%2Fkernel%2Flinux.git perf lock contention: Allow 'mmap_lock' in -L/--lock-filter The -L/--lock-filter option is to specify target locks by name or address. It's basically for global locks where name or address is known and fixed. But 'mmap_lock' is a per-process lock so it cannot be used for the -L option. $ sudo perf lock con -ab -L mmap_lock ignore unknown symbol: mmap_lock libbpf: map 'addr_filter': failed to create: -EINVAL libbpf: failed to load BPF skeleton 'lock_contention_bpf': -EINVAL Failed to load lock-contention BPF skeleton lock contention BPF setup failed However, it's still a common source of contention especially in a large process so we want to use it for the -L/--lock-filter option. As there is check_lock_type() to check mmap_lock at runtime, let's used it to filter mmap_locks as a special case. Of course, this only works with -b/--use-bpf option. $ sudo perf lock con -b -L mmap_lock -- perf bench mem mmap -f demand -t 2 # Running 'mem/mmap' benchmark: # function 'demand' (Demand loaded mmap()) # Copying 1MB bytes ... 2.679184 GB/sec/thread ( +- 1.78% ) contended total wait max wait avg wait type caller 1 15.22 us 15.22 us 15.22 us rwsem:W __vm_munmap+0x7e 1 7.72 us 7.72 us 7.72 us rwsem:R lock_mm_and_find_vma+0x97 Signed-off-by: Namhyung Kim Cc: Adrian Hunter Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Peter Zijlstra Cc: Suchit Karunakaran Signed-off-by: Arnaldo Carvalho de Melo --- diff --git a/tools/perf/tests/shell/lock_contention.sh b/tools/perf/tests/shell/lock_contention.sh index 6dd90519f45ce..52e8b9db9fbd8 100755 --- a/tools/perf/tests/shell/lock_contention.sh +++ b/tools/perf/tests/shell/lock_contention.sh @@ -208,6 +208,17 @@ test_lock_filter() err=1 exit fi + + perf lock con -b -L mmap_lock -q -- perf bench mem mmap -t 2 -l 10 > /dev/null 2> ${result} + + # find out the type of mmap_lock + test_lock_filter_type=$(head -1 "${result}" | awk '{ print $8 }' | sed -e 's/:.*//') + + if [ "$(grep -c -v "${test_lock_filter_type}" "${result}")" != "0" ]; then + echo "[Fail] BPF result should not have non-${test_lock_filter_type} locks:" "$(cat "${result}")" + err=1 + exit + fi } test_stack_filter() diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c index cbd7435579fea..eb8e29b8064b7 100644 --- a/tools/perf/util/bpf_lock_contention.c +++ b/tools/perf/util/bpf_lock_contention.c @@ -186,6 +186,7 @@ int lock_contention_prepare(struct lock_contention *con) int ncpus = 1, ntasks = 1, ntypes = 1, naddrs = 1, ncgrps = 1, nslabs = 1; struct evlist *evlist = con->evlist; struct target *target = con->target; + bool has_mmap_lock = false; /* make sure it loads the kernel map before lookup */ map__load(machine__kernel_map(con->machine)); @@ -244,6 +245,11 @@ int lock_contention_prepare(struct lock_contention *con) unsigned long *addrs; for (i = 0; i < con->filters->nr_syms; i++) { + if (!strcmp(con->filters->syms[i], "mmap_lock")) { + has_mmap_lock = true; + continue; + } + sym = machine__find_kernel_symbol_by_name(con->machine, con->filters->syms[i], &kmap); @@ -263,7 +269,7 @@ int lock_contention_prepare(struct lock_contention *con) addrs[con->filters->nr_addrs++] = map__unmap_ip(kmap, sym->start); con->filters->addrs = addrs; } - naddrs = con->filters->nr_addrs; + naddrs = con->filters->nr_addrs ?: has_mmap_lock; skel->rodata->has_addr = 1; } @@ -298,6 +304,7 @@ int lock_contention_prepare(struct lock_contention *con) skel->rodata->aggr_mode = con->aggr_mode; skel->rodata->needs_callstack = con->save_callstack; skel->rodata->lock_owner = con->owner; + skel->rodata->has_mmap_lock = has_mmap_lock; if (con->aggr_mode == LOCK_AGGR_CGROUP || con->filters->nr_cgrps) { if (cgroup_is_v2("perf_event")) diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index 5c8431be674ac..d4186ae9f85c7 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -191,6 +191,7 @@ const volatile int has_type; const volatile int has_addr; const volatile int has_cgroup; const volatile int has_slab; +const volatile int has_mmap_lock; const volatile int needs_callstack; const volatile int stack_skip; const volatile int lock_owner; @@ -221,6 +222,8 @@ int data_map_full; struct task_struct *bpf_task_from_pid(s32 pid) __ksym __weak; void bpf_task_release(struct task_struct *p) __ksym __weak; +static inline __u32 check_lock_type(__u64 lock, __u32 flags); + static inline __u64 get_current_cgroup_id(void) { struct task_struct *task; @@ -246,6 +249,8 @@ static inline __u64 get_current_cgroup_id(void) static inline int can_record(u64 *ctx) { + bool is_addr_ok = false; + if (has_cpu) { __u32 cpu = bpf_get_smp_processor_id(); __u8 *ok; @@ -278,8 +283,10 @@ static inline int can_record(u64 *ctx) __u64 addr = ctx[0]; ok = bpf_map_lookup_elem(&addr_filter, &addr); - if (!ok && !has_slab) + if (!ok && !has_slab && !has_mmap_lock) return 0; + + is_addr_ok = !!ok; } if (has_cgroup) { @@ -291,6 +298,10 @@ static inline int can_record(u64 *ctx) return 0; } + if (is_addr_ok) + return 1; + + /* slab and mmap_lock are part of the addr_filter */ if (has_slab && bpf_get_kmem_cache) { __u8 *ok; __u64 addr = ctx[0]; @@ -298,7 +309,17 @@ static inline int can_record(u64 *ctx) kmem_cache_addr = (long)bpf_get_kmem_cache(addr); ok = bpf_map_lookup_elem(&slab_filter, &kmem_cache_addr); - if (!ok) + if (ok) + return 1; + else if (!has_mmap_lock) + return 0; + } + + if (has_mmap_lock) { + __u64 lock = ctx[0]; + __u32 flag = ctx[1]; + + if (check_lock_type(lock, flag) != LCD_F_MMAP_LOCK) return 0; }