From: Jiri Olsa <jolsa@kernel.org> mainline inclusion from mainline-v7.3-rc1 commit 15b837759a97237d647962f9943afe0d55af615a category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/19054 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- The new stackid_init function stores all the necessary bits for stackid trace and it will be used by other functions in following changes. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/bpf/20260803210149.296496-2-jolsa@kernel.org Conflicts: kernel/bpf/stackmap.c [ctx conflicts] Signed-off-by: Pu Lehui <pulehui@huawei.com> --- kernel/bpf/stackmap.c | 95 +++++++++++++++++++++++++++---------------- 1 file changed, 59 insertions(+), 36 deletions(-) diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 4e4a98a3b8e2..dc22bee0aeba 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -240,33 +240,54 @@ get_callchain_entry_for_task(struct task_struct *task, u32 max_depth) #endif } -static long __bpf_get_stackid(struct bpf_map *map, - struct perf_callchain_entry *trace, u64 flags) +struct stackid { + struct stack_map_bucket *bucket; + u64 *ips; + u32 nr; + u32 len; + u32 hash; + u32 id; +}; + +static int stackid_init(struct stackid *stackid, struct bpf_map *map, + struct perf_callchain_entry *trace, u64 flags) { struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); - struct stack_map_bucket *bucket, *new_bucket, *old_bucket; - u32 hash, id, trace_nr, trace_len, i, max_depth; u32 skip = flags & BPF_F_SKIP_FIELD_MASK; - bool user = flags & BPF_F_USER_STACK; - u64 *ips; - bool hash_matches; + u32 max_depth; if (trace->nr <= skip) /* skipping more than usable stack trace */ return -EFAULT; max_depth = stack_map_calculate_max_depth(map->value_size, stack_map_data_size(map), flags); - trace_nr = min_t(u32, trace->nr - skip, max_depth - skip); - trace_len = trace_nr * sizeof(u64); - ips = trace->ip + skip; - hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0); - id = hash & (smap->n_buckets - 1); - bucket = READ_ONCE(smap->buckets[id]); + stackid->nr = min_t(u32, trace->nr - skip, max_depth - skip); + stackid->len = stackid->nr * sizeof(u64); + stackid->ips = trace->ip + skip; + stackid->hash = jhash2((u32 *)stackid->ips, stackid->len / sizeof(u32), 0); + stackid->id = stackid->hash & (smap->n_buckets - 1); + stackid->bucket = READ_ONCE(smap->buckets[stackid->id]); + return 0; +} - hash_matches = bucket && bucket->hash == hash; +static long __bpf_get_stackid(struct stackid *stackid, struct bpf_map *map, + struct perf_callchain_entry *trace, u64 flags) +{ + struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); + struct stack_map_bucket *new_bucket, *old_bucket; + bool user = flags & BPF_F_USER_STACK; + bool hash_matches; + u32 trace_len, i; + int err; + + err = stackid_init(stackid, map, trace, flags); + if (err) + return err; + + hash_matches = stackid->bucket && stackid->bucket->hash == stackid->hash; /* fast cmp */ if (hash_matches && flags & BPF_F_FAST_STACK_CMP) - return id; + return stackid->id; if (stack_map_use_build_id(map)) { struct bpf_stack_build_id *id_offs; @@ -276,42 +297,42 @@ static long __bpf_get_stackid(struct bpf_map *map, pcpu_freelist_pop(&smap->freelist); if (unlikely(!new_bucket)) return -ENOMEM; - new_bucket->nr = trace_nr; + new_bucket->nr = stackid->nr; id_offs = (struct bpf_stack_build_id *)new_bucket->data; - for (i = 0; i < trace_nr; i++) - id_offs[i].ip = ips[i]; - stack_map_get_build_id_offset(id_offs, trace_nr, user); - trace_len = trace_nr * sizeof(struct bpf_stack_build_id); - if (hash_matches && bucket->nr == trace_nr && - memcmp(bucket->data, new_bucket->data, trace_len) == 0) { + for (i = 0; i < stackid->nr; i++) + id_offs[i].ip = stackid->ips[i]; + stack_map_get_build_id_offset(id_offs, stackid->nr, user); + trace_len = stackid->nr * sizeof(struct bpf_stack_build_id); + if (hash_matches && stackid->bucket->nr == stackid->nr && + memcmp(stackid->bucket->data, new_bucket->data, trace_len) == 0) { pcpu_freelist_push(&smap->freelist, &new_bucket->fnode); - return id; + return stackid->id; } - if (bucket && !(flags & BPF_F_REUSE_STACKID)) { + if (stackid->bucket && !(flags & BPF_F_REUSE_STACKID)) { pcpu_freelist_push(&smap->freelist, &new_bucket->fnode); return -EEXIST; } } else { - if (hash_matches && bucket->nr == trace_nr && - memcmp(bucket->data, ips, trace_len) == 0) - return id; - if (bucket && !(flags & BPF_F_REUSE_STACKID)) + if (hash_matches && stackid->bucket->nr == stackid->nr && + memcmp(stackid->bucket->data, stackid->ips, stackid->len) == 0) + return stackid->id; + if (stackid->bucket && !(flags & BPF_F_REUSE_STACKID)) return -EEXIST; new_bucket = (struct stack_map_bucket *) pcpu_freelist_pop(&smap->freelist); if (unlikely(!new_bucket)) return -ENOMEM; - memcpy(new_bucket->data, ips, trace_len); + memcpy(new_bucket->data, stackid->ips, stackid->len); } - new_bucket->hash = hash; - new_bucket->nr = trace_nr; + new_bucket->hash = stackid->hash; + new_bucket->nr = stackid->nr; - old_bucket = xchg(&smap->buckets[id], new_bucket); + old_bucket = xchg(&smap->buckets[stackid->id], new_bucket); if (old_bucket) pcpu_freelist_push(&smap->freelist, &old_bucket->fnode); - return id; + return stackid->id; } BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, @@ -320,6 +341,7 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, u32 elem_size = stack_map_data_size(map); bool user = flags & BPF_F_USER_STACK; struct perf_callchain_entry *trace; + struct stackid stackid; bool kernel = !user; u32 max_depth; @@ -335,7 +357,7 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, /* couldn't fetch the stack trace */ return -EFAULT; - return __bpf_get_stackid(map, trace, flags); + return __bpf_get_stackid(&stackid, map, trace, flags); } const struct bpf_func_proto bpf_get_stackid_proto = { @@ -364,6 +386,7 @@ BPF_CALL_3(bpf_get_stackid_pe, struct bpf_perf_event_data_kern *, ctx, { struct perf_event *event = ctx->event; struct perf_callchain_entry *trace; + struct stackid stackid; bool kernel, user; __u64 nr_kernel, nr; int ret; @@ -389,7 +412,7 @@ BPF_CALL_3(bpf_get_stackid_pe, struct bpf_perf_event_data_kern *, ctx, if (kernel) { trace->nr = nr_kernel; - ret = __bpf_get_stackid(map, trace, flags); + ret = __bpf_get_stackid(&stackid, map, trace, flags); } else { /* user */ u64 skip = flags & BPF_F_SKIP_FIELD_MASK; @@ -398,7 +421,7 @@ BPF_CALL_3(bpf_get_stackid_pe, struct bpf_perf_event_data_kern *, ctx, return -EFAULT; flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip; - ret = __bpf_get_stackid(map, trace, flags); + ret = __bpf_get_stackid(&stackid, map, trace, flags); } /* restore nr */ -- 2.34.1