Add a struct and few bpf maps in order to tracing owner stack. `struct owner_tracing_data`: Contains owner's pid, stack id, timestamp for when the owner acquires lock, and the count of lock waiters. `stack_buf`: Percpu buffer for retrieving owner stacktrace. `owner_stacks`: For tracing owner stacktrace to customized owner stack id. `owner_data`: For tracing lock_address to `struct owner_tracing_data` in bpf program. `owner_stat`: For reporting owner stacktrace in usermode. Signed-off-by: Chun-Tse Shao <ctshao@xxxxxxxxxx> --- tools/perf/util/bpf_lock_contention.c | 16 +++++-- .../perf/util/bpf_skel/lock_contention.bpf.c | 42 ++++++++++++++++--- tools/perf/util/bpf_skel/lock_data.h | 7 ++++ 3 files changed, 57 insertions(+), 8 deletions(-) diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c index fc8666222399..795e2374facc 100644 --- a/tools/perf/util/bpf_lock_contention.c +++ b/tools/perf/util/bpf_lock_contention.c @@ -131,9 +131,19 @@ int lock_contention_prepare(struct lock_contention *con) else bpf_map__set_max_entries(skel->maps.task_data, 1); - if (con->save_callstack) - bpf_map__set_max_entries(skel->maps.stacks, con->map_nr_entries); - else + if (con->save_callstack) { + bpf_map__set_max_entries(skel->maps.stacks, + con->map_nr_entries); + if (con->owner) { + bpf_map__set_value_size(skel->maps.stack_buf, con->max_stack * sizeof(u64)); + bpf_map__set_key_size(skel->maps.owner_stacks, + con->max_stack * sizeof(u64)); + bpf_map__set_max_entries(skel->maps.owner_stacks, con->map_nr_entries); + bpf_map__set_max_entries(skel->maps.owner_data, con->map_nr_entries); + bpf_map__set_max_entries(skel->maps.owner_stat, con->map_nr_entries); + skel->rodata->max_stack = con->max_stack; + } + } else bpf_map__set_max_entries(skel->maps.stacks, 1); if (target__has_cpu(target)) { diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index 6533ea9b044c..b4961dd86222 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -19,13 +19,37 @@ #define LCB_F_PERCPU (1U << 4) #define LCB_F_MUTEX (1U << 5) -/* callstack storage */ + /* buffer for owner stacktrace */ struct { - __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); __uint(key_size, sizeof(__u32)); __uint(value_size, sizeof(__u64)); - __uint(max_entries, MAX_ENTRIES); -} stacks SEC(".maps"); + __uint(max_entries, 1); +} stack_buf SEC(".maps"); + +/* a map for tracing owner stacktrace to owner stack id */ +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u64)); // owner stacktrace + __uint(value_size, sizeof(__u64)); // owner stack id + __uint(max_entries, 1); +} owner_stacks SEC(".maps"); + +/* a map for tracing lock address to owner data */ +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u64)); // lock address + __uint(value_size, sizeof(struct owner_tracing_data)); + __uint(max_entries, 1); +} owner_data SEC(".maps"); + +/* a map for contention_key (stores owner stack id) to contention data */ +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(struct contention_key)); + __uint(value_size, sizeof(struct contention_data)); + __uint(max_entries, 1); +} owner_stat SEC(".maps"); /* maintain timestamp at the beginning of contention */ struct { @@ -43,6 +67,14 @@ struct { __uint(max_entries, 1); } tstamp_cpu SEC(".maps"); +/* callstack storage */ +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u64)); + __uint(max_entries, MAX_ENTRIES); +} stacks SEC(".maps"); + /* actual lock contention statistics */ struct { __uint(type, BPF_MAP_TYPE_HASH); @@ -143,6 +175,7 @@ const volatile int needs_callstack; const volatile int stack_skip; const volatile int lock_owner; const volatile int use_cgroup_v2; +const volatile int max_stack; /* determine the key of lock stat */ const volatile int aggr_mode; @@ -466,7 +499,6 @@ int contention_end(u64 *ctx) return 0; need_delete = true; } - duration = bpf_ktime_get_ns() - pelem->timestamp; if ((__s64)duration < 0) { __sync_fetch_and_add(&time_fail, 1); diff --git a/tools/perf/util/bpf_skel/lock_data.h b/tools/perf/util/bpf_skel/lock_data.h index c15f734d7fc4..15f5743bd409 100644 --- a/tools/perf/util/bpf_skel/lock_data.h +++ b/tools/perf/util/bpf_skel/lock_data.h @@ -3,6 +3,13 @@ #ifndef UTIL_BPF_SKEL_LOCK_DATA_H #define UTIL_BPF_SKEL_LOCK_DATA_H +struct owner_tracing_data { + u32 pid; // Who has the lock. + u32 count; // How many waiters for this lock. + u64 timestamp; // The time while the owner acquires lock and contention is going on. + s32 stack_id; // Identifier for `owner_stat`, which stores as value in `owner_stacks` +}; + struct tstamp_data { u64 timestamp; u64 lock; -- 2.48.1.262.g85cc9f2d1e-goog