From d46edd671a147032e22cfeb271a5734703093649 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 30 Apr 2020 00:15:04 -0700 Subject: bpf: Sharing bpf runtime stats with BPF_ENABLE_STATS Currently, sysctl kernel.bpf_stats_enabled controls BPF runtime stats. Typical userspace tools use kernel.bpf_stats_enabled as follows: 1. Enable kernel.bpf_stats_enabled; 2. Check program run_time_ns; 3. Sleep for the monitoring period; 4. Check program run_time_ns again, calculate the difference; 5. Disable kernel.bpf_stats_enabled. The problem with this approach is that only one userspace tool can toggle this sysctl. If multiple tools toggle the sysctl at the same time, the measurement may be inaccurate. To fix this problem while keep backward compatibility, introduce a new bpf command BPF_ENABLE_STATS. On success, this command enables stats and returns a valid fd. BPF_ENABLE_STATS takes argument "type". Currently, only one type, BPF_STATS_RUN_TIME, is supported. We can extend the command to support other types of stats in the future. With BPF_ENABLE_STATS, user space tool would have the following flow: 1. Get a fd with BPF_ENABLE_STATS, and make sure it is valid; 2. Check program run_time_ns; 3. Sleep for the monitoring period; 4. Check program run_time_ns again, calculate the difference; 5. Close the fd. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200430071506.1408910-2-songliubraving@fb.com --- kernel/sysctl.c | 36 +++++++++++++++++++++++++++++++++++- 1 file changed, 35 insertions(+), 1 deletion(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index e961286d0e14..7adfe5dbce9d 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -201,6 +201,40 @@ static int max_extfrag_threshold = 1000; #endif /* CONFIG_SYSCTL */ +#ifdef CONFIG_BPF_SYSCALL +static int bpf_stats_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + struct static_key *key = (struct static_key *)table->data; + static int saved_val; + int val, ret; + struct ctl_table tmp = { + .data = &val, + .maxlen = sizeof(val), + .mode = table->mode, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + mutex_lock(&bpf_stats_enabled_mutex); + val = saved_val; + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + if (write && !ret && val != saved_val) { + if (val) + static_key_slow_inc(key); + else + static_key_slow_dec(key); + saved_val = val; + } + mutex_unlock(&bpf_stats_enabled_mutex); + return ret; +} +#endif + /* * /proc/sys support */ @@ -2549,7 +2583,7 @@ static struct ctl_table kern_table[] = { .data = &bpf_stats_enabled_key.key, .maxlen = sizeof(bpf_stats_enabled_key), .mode = 0644, - .proc_handler = proc_do_static_key, + .proc_handler = bpf_stats_handler, }, #endif #if defined(CONFIG_TREE_RCU) -- cgit v1.2.3