bpf stackmap with build-id lookup (BPF_F_STACK_BUILD_ID) can trigger A-A deadlock on rq_lock():
rcu: INFO: rcu_sched detected stalls on CPUs/tasks: [...] Call Trace: try_to_wake_up+0x1ad/0x590 wake_up_q+0x54/0x80 rwsem_wake+0x8a/0xb0 bpf_get_stack+0x13c/0x150 bpf_prog_fbdaf42eded9fe46_on_event+0x5e3/0x1000 bpf_overflow_handler+0x60/0x100 __perf_event_overflow+0x4f/0xf0 perf_swevent_overflow+0x99/0xc0 ___perf_sw_event+0xe7/0x120 __schedule+0x47d/0x620 schedule+0x29/0x90 futex_wait_queue_me+0xb9/0x110 futex_wait+0x139/0x230 do_futex+0x2ac/0xa50 __x64_sys_futex+0x13c/0x180 do_syscall_64+0x42/0x100 entry_SYSCALL_64_after_hwframe+0x44/0xa9
This can be reproduced by: 1. Start a multi-thread program that does parallel mmap() and malloc(); 2. taskset the program to 2 CPUs; 3. Attach bpf program to trace_sched_switch and gather stackmap with build-id, e.g. with trace.py from bcc tools: trace.py -U -p <pid> -s <some-bin,some-lib> t:sched:sched_switch
A sample reproducer is attached at the end.
Fix this by checking whether rq_lock is already locked. If so, postpone the up_read() to irq_work, just like the in_nmi() case.
Fixes: commit 615755a77b24 ("bpf: extend stackmap to save binary_build_id+offset instead of address") Cc: stable@vger.kernel.org # v4.17+ Cc: Peter Zijlstra peterz@infradead.org Cc: Alexei Starovoitov ast@kernel.org Cc: Daniel Borkmann daniel@iogearbox.net Reported-by: Tejun Heo tj@kernel.org Signed-off-by: Song Liu songliubraving@fb.com
Reproducer: ============================ 8< ============================
char *filename;
void *worker(void *p) { void *ptr; int fd; char *pptr;
fd = open(filename, O_RDONLY); if (fd < 0) return NULL; while (1) { struct timespec ts = {0, 1000 + rand() % 2000};
ptr = mmap(NULL, 4096 * 64, PROT_READ, MAP_PRIVATE, fd, 0); usleep(1); if (ptr == MAP_FAILED) { printf("failed to mmap\n"); break; } munmap(ptr, 4096 * 64); usleep(1); pptr = malloc(1); usleep(1); pptr[0] = 1; usleep(1); free(pptr); usleep(1); nanosleep(&ts, NULL); } close(fd); return NULL; }
int main(int argc, char *argv[]) { void *ptr; int i; pthread_t threads[THREAD_COUNT];
if (argc < 2) return 0;
filename = argv[1];
for (i = 0; i < THREAD_COUNT; i++) { if (pthread_create(threads + i, NULL, worker, NULL)) { fprintf(stderr, "Error creating thread\n"); return 0; } }
for (i = 0; i < THREAD_COUNT; i++) pthread_join(threads[i], NULL); return 0; } ============================ 8< ============================ --- kernel/bpf/stackmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 052580c33d26..3b278f6b0c3e 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -287,7 +287,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, bool irq_work_busy = false; struct stack_map_irq_work *work = NULL;
- if (in_nmi()) { + if (in_nmi() || this_rq_is_locked()) { work = this_cpu_ptr(&up_read_work); if (work->irq_work.flags & IRQ_WORK_BUSY) /* cannot queue more up_read, fallback */ -- 2.17.1