diff options
| author | Andrii Nakryiko <andriin@fb.com> | 2020-05-13 22:51:37 -0700 |
|---|---|---|
| committer | Alexei Starovoitov <ast@kernel.org> | 2020-05-14 18:37:32 -0700 |
| commit | c70f34a8ac66c2cb05593ef5760142e5f862a9b4 (patch) | |
| tree | 8c0045ceb528c231cc94e10534e305f9d196cc3c /kernel/bpf/task_iter.c | |
| parent | 0645f7eb6f6af78aba2bdd37ae776bd8754bc8f0 (diff) | |
bpf: Fix bpf_iter's task iterator logic
task_seq_get_next might stop prematurely if get_pid_task() fails to get
task_struct. Failure to do so doesn't mean that there are no more tasks with
higher pids. Procfs's iteration algorithm (see next_tgid in fs/proc/base.c)
does a retry in such case. After this fix, instead of stopping prematurely
after about 300 tasks on my server, bpf_iter program now returns >4000, which
sounds much closer to reality.
Fixes: eaaacd23910f ("bpf: Add task and task/file iterator targets")
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20200514055137.1564581-1-andriin@fb.com
Diffstat (limited to 'kernel/bpf/task_iter.c')
| -rw-r--r-- | kernel/bpf/task_iter.c | 8 |
1 files changed, 7 insertions, 1 deletions
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index a9b7264dda08..4dbf2b6035f8 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -27,9 +27,15 @@ static struct task_struct *task_seq_get_next(struct pid_namespace *ns, struct pid *pid; rcu_read_lock(); +retry: pid = idr_get_next(&ns->idr, tid); - if (pid) + if (pid) { task = get_pid_task(pid, PIDTYPE_PID); + if (!task) { + ++*tid; + goto retry; + } + } rcu_read_unlock(); return task; |