[PATCH bpf-next 2/2] bpf/stackmap: fix A-A deadlock in bpf_get_stack()

[Song Liu <songliubraving@xxxxxx>]

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@xxxxxxxxxxxxxxx # v4.17+
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Alexei Starovoitov <ast@xxxxxxxxxx>
Cc: Daniel Borkmann <daniel@xxxxxxxxxxxxx>
Reported-by: Tejun Heo <tj@xxxxxxxxxx>
Signed-off-by: Song Liu <songliubraving@xxxxxx>

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