bpf: enable program stats

JITed BPF programs are indistinguishable from kernel functions, but unlike
kernel code BPF code can be changed often.
Typical approach of "perf record" + "perf report" profiling and tuning of
kernel code works just as well for BPF programs, but kernel code doesn't
need to be monitored whereas BPF programs do.
Users load and run large amount of BPF programs.
These BPF stats allow tools monitor the usage of BPF on the server.
The monitoring tools will turn sysctl kernel.bpf_stats_enabled
on and off for few seconds to sample average cost of the programs.
Aggregated data over hours and days will provide an insight into cost of BPF
and alarms can trigger in case given program suddenly gets more expensive.

The cost of two sched_clock() per program invocation adds ~20 nsec.
Fast BPF progs (like selftests/bpf/progs/test_pkt_access.c) will slow down
from ~10 nsec to ~30 nsec.
static_key minimizes the cost of the stats collection.
There is no measurable difference before/after this patch
with kernel.bpf_stats_enabled=0

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

1 files changed, 32 insertions, 2 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ec7c552af76b..31cf66fc3f5c 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1283,24 +1283,54 @@ static int bpf_prog_release(struct inode *inode, struct file *filp)
         return 0;
 }
 
+static void bpf_prog_get_stats(const struct bpf_prog *prog,
+                               struct bpf_prog_stats *stats)
+{
+        u64 nsecs = 0, cnt = 0;
+        int cpu;
+
+        for_each_possible_cpu(cpu) {
+                const struct bpf_prog_stats *st;
+                unsigned int start;
+                u64 tnsecs, tcnt;
+
+                st = per_cpu_ptr(prog->aux->stats, cpu);
+                do {
+                        start = u64_stats_fetch_begin_irq(&st->syncp);
+                        tnsecs = st->nsecs;
+                        tcnt = st->cnt;
+                } while (u64_stats_fetch_retry_irq(&st->syncp, start));
+                nsecs += tnsecs;
+                cnt += tcnt;
+        }
+        stats->nsecs = nsecs;
+        stats->cnt = cnt;
+}
+
 #ifdef CONFIG_PROC_FS
 static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp)
 {
         const struct bpf_prog *prog = filp->private_data;
         char prog_tag[sizeof(prog->tag) * 2 + 1] = { };
+        struct bpf_prog_stats stats;
 
+        bpf_prog_get_stats(prog, &stats);
         bin2hex(prog_tag, prog->tag, sizeof(prog->tag));
         seq_printf(m,
                    "prog_type:\t%u\n"
                    "prog_jited:\t%u\n"
                    "prog_tag:\t%s\n"
                    "memlock:\t%llu\n"
-                   "prog_id:\t%u\n",
+                   "prog_id:\t%u\n"
+                   "run_time_ns:\t%llu\n"
+                   "run_cnt:\t%llu\n",
                    prog->type,
                    prog->jited,
                    prog_tag,
                    prog->pages * 1ULL << PAGE_SHIFT,
-                   prog->aux->id);
+                   prog->aux->id,
+                   stats.nsecs,
+                   stats.cnt);
 }
 #endif