According to the perf_event_map_fd and key, the function bpf_perf_event_read() can convert the corresponding map value to the pointer to struct perf_event and return the Hardware PMU counter value.
The key can't be passed to bpf_perf_event_read() directly because the function argument constraint is lacked. Signed-off-by: Kaixu Xia <[email protected]> --- include/linux/bpf.h | 1 + include/linux/perf_event.h | 3 ++- include/uapi/linux/bpf.h | 2 ++ kernel/bpf/helpers.c | 42 ++++++++++++++++++++++++++++++++++++++++++ kernel/events/core.c | 4 ++-- kernel/trace/bpf_trace.c | 2 ++ 6 files changed, 51 insertions(+), 3 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 257149c..0fbff67 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -197,5 +197,6 @@ extern const struct bpf_func_proto bpf_ktime_get_ns_proto; extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; +extern const struct bpf_func_proto bpf_perf_event_read_proto; #endif /* _LINUX_BPF_H */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 2ea4067..899abcb 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -662,7 +662,8 @@ extern void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); - +extern void __perf_event_read(void *info); +extern u64 perf_event_count(struct perf_event *event); struct perf_sample_data { /* diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 69a1f6b..e3bb181 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -250,6 +250,8 @@ enum bpf_func_id { * Return: 0 on success */ BPF_FUNC_get_current_comm, + + BPF_FUNC_perf_event_read, /* u64 bpf_perf_event_read(&map, &key) */ __BPF_FUNC_MAX_ID, }; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 1447ec0..aef2640 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -16,6 +16,7 @@ #include <linux/ktime.h> #include <linux/sched.h> #include <linux/uidgid.h> +#include <linux/perf_event.h> /* If kernel subsystem is allowing eBPF programs to call this function, * inside its own verifier_ops->get_func_proto() callback it should return @@ -182,3 +183,44 @@ const struct bpf_func_proto bpf_get_current_comm_proto = { .arg1_type = ARG_PTR_TO_STACK, .arg2_type = ARG_CONST_STACK_SIZE, }; + +static u64 bpf_perf_event_read(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + struct bpf_map *map = (struct bpf_map *) (unsigned long) r1; + void *key = (void *) (unsigned long) r2; + struct perf_event *event; + void *ptr; + + if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) + return -EINVAL; + + rcu_read_lock(); + ptr = map->ops->map_lookup_elem(map, key); + rcu_read_unlock(); + if (!ptr || !(*(unsigned long *)ptr)) + return -EBADF; + + event = (struct perf_event *)(*(unsigned long *)ptr); + + if (event->state != PERF_EVENT_STATE_ACTIVE) + return -ENOENT; + + if (event->oncpu != raw_smp_processor_id() && + event->ctx->task != current) + return -EINVAL; + + if (event->attr.inherit) + return -EINVAL; + + __perf_event_read(event); + + return perf_event_count(event); +} + +const struct bpf_func_proto bpf_perf_event_read_proto = { + .func = bpf_perf_event_read, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_MAP_KEY, +}; diff --git a/kernel/events/core.c b/kernel/events/core.c index 14a9924..b4bde27 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3177,7 +3177,7 @@ void perf_event_exec(void) /* * Cross CPU call to read the hardware event */ -static void __perf_event_read(void *info) +void __perf_event_read(void *info) { struct perf_event *event = info; struct perf_event_context *ctx = event->ctx; @@ -3204,7 +3204,7 @@ static void __perf_event_read(void *info) raw_spin_unlock(&ctx->lock); } -static inline u64 perf_event_count(struct perf_event *event) +u64 perf_event_count(struct perf_event *event) { if (event->pmu->count) return event->pmu->count(event); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 88a041a..9cf094f 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -183,6 +183,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func return bpf_get_trace_printk_proto(); case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; + case BPF_FUNC_perf_event_read: + return &bpf_perf_event_read_proto; default: return NULL; } -- 1.8.3.4 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
