bpf: Avoid deadlock when using queue and stack maps from NMI

Sysbot discovered that the queue and stack maps can deadlock if they are
being used from a BPF program that can be called from NMI context (such as
one that is attached to a perf HW counter event). To fix this, add an
in_nmi() check and use raw_spin_trylock() in NMI context, erroring out if
grabbing the lock fails.

Fixes: f1a2e44a3aec ("bpf: add queue and stack maps")
Reported-by: Hsin-Wei Hung <hsinweih@uci.edu>
Tested-by: Hsin-Wei Hung <hsinweih@uci.edu>
Co-developed-by: Hsin-Wei Hung <hsinweih@uci.edu>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/r/20230911132815.717240-1-toke@redhat.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index 8d2ddcb7566b7fe262e7571700f1b1ac48dcc782..d869f51ea93a0e918d365729ee5bcd8687a5ce4f 100644 (file)
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -98,7 +98,12 @@ static long __queue_map_get(struct bpf_map *map, void *value, bool delete)
        int err = 0;
        void *ptr;
 
-       raw_spin_lock_irqsave(&qs->lock, flags);
+       if (in_nmi()) {
+               if (!raw_spin_trylock_irqsave(&qs->lock, flags))
+                       return -EBUSY;
+       } else {
+               raw_spin_lock_irqsave(&qs->lock, flags);
+       }
 
        if (queue_stack_map_is_empty(qs)) {
                memset(value, 0, qs->map.value_size);
@@ -128,7 +133,12 @@ static long __stack_map_get(struct bpf_map *map, void *value, bool delete)
        void *ptr;
        u32 index;
 
-       raw_spin_lock_irqsave(&qs->lock, flags);
+       if (in_nmi()) {
+               if (!raw_spin_trylock_irqsave(&qs->lock, flags))
+                       return -EBUSY;
+       } else {
+               raw_spin_lock_irqsave(&qs->lock, flags);
+       }
 
        if (queue_stack_map_is_empty(qs)) {
                memset(value, 0, qs->map.value_size);
@@ -193,7 +203,12 @@ static long queue_stack_map_push_elem(struct bpf_map *map, void *value,
        if (flags & BPF_NOEXIST || flags > BPF_EXIST)
                return -EINVAL;
 
-       raw_spin_lock_irqsave(&qs->lock, irq_flags);
+       if (in_nmi()) {
+               if (!raw_spin_trylock_irqsave(&qs->lock, irq_flags))
+                       return -EBUSY;
+       } else {
+               raw_spin_lock_irqsave(&qs->lock, irq_flags);
+       }
 
        if (queue_stack_map_is_full(qs)) {
                if (!replace) {