bpf, sockmap: fix deadlocks in the sockhash and sockmap

BugLink: https://bugs.launchpad.net/bugs/2025067
[ Upstream commit ed17aa92dc56b6d8883e4b7a8f1c6fbf5ed6cd29 ]

When huang uses sched_switch tracepoint, the tracepoint
does only one thing in the mounted ebpf program, which
deletes the fixed elements in sockhash ([0])

It seems that elements in sockhash are rarely actively
deleted by users or ebpf program. Therefore, we do not
pay much attention to their deletion. Compared with hash
maps, sockhash only provides spin_lock_bh protection.
This causes it to appear to have self-locking behavior
in the interrupt context.

  [0]:https://lore.kernel.org/all/CABcoxUayum5oOqFMMqAeWuS8+EzojquSOSyDA3J_2omY=2EeAg@mail.gmail.com/

Reported-by: Hsin-Wei Hung <hsinweih@uci.edu>
Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface")
Signed-off-by: Xin Liu <liuxin350@huawei.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/r/20230406122622.109978-1-liuxin350@huawei.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
Signed-off-by: Stefan Bader <stefan.bader@canonical.com>

diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index a055139f410e2f9bf99aec47e9863a67e79a10d0..dd5d7b1fa3580521ccee65ed989e1779212223c8 100644 (file)
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -414,8 +414,9 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test,
 {
        struct sock *sk;
        int err = 0;
+       unsigned long flags;
 
-       raw_spin_lock_bh(&stab->lock);
+       raw_spin_lock_irqsave(&stab->lock, flags);
        sk = *psk;
        if (!sk_test || sk_test == sk)
                sk = xchg(psk, NULL);
@@ -425,7 +426,7 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test,
        else
                err = -EINVAL;
 
-       raw_spin_unlock_bh(&stab->lock);
+       raw_spin_unlock_irqrestore(&stab->lock, flags);
        return err;
 }
 
@@ -923,11 +924,12 @@ static long sock_hash_delete_elem(struct bpf_map *map, void *key)
        struct bpf_shtab_bucket *bucket;
        struct bpf_shtab_elem *elem;
        int ret = -ENOENT;
+       unsigned long flags;
 
        hash = sock_hash_bucket_hash(key, key_size);
        bucket = sock_hash_select_bucket(htab, hash);
 
-       raw_spin_lock_bh(&bucket->lock);
+       raw_spin_lock_irqsave(&bucket->lock, flags);
        elem = sock_hash_lookup_elem_raw(&bucket->head, hash, key, key_size);
        if (elem) {
                hlist_del_rcu(&elem->node);
@@ -935,7 +937,7 @@ static long sock_hash_delete_elem(struct bpf_map *map, void *key)
                sock_hash_free_elem(htab, elem);
                ret = 0;
        }
-       raw_spin_unlock_bh(&bucket->lock);
+       raw_spin_unlock_irqrestore(&bucket->lock, flags);
        return ret;
 }