[PATCH bpf v2 3/3] bpf, sockmap: fix memleak on ingress msg enqueue
From: John Fastabend <john.fastabend@gmail.com>
Date: 2021-07-26 17:20:29
Also in:
bpf
Subsystem:
bpf [l7 framework] (sockmap), networking [general], the rest · Maintainers:
John Fastabend, Jakub Sitnicki, Jiayuan Chen, "David S. Miller", Eric Dumazet, Jakub Kicinski, Paolo Abeni, Linus Torvalds
If backlog handler is running during a tear down operation we may enqueue
data on the ingress msg queue while tear down is trying to free it.
sk_psock_backlog()
sk_psock_handle_skb()
skb_psock_skb_ingress()
sk_psock_skb_ingress_enqueue()
sk_psock_queue_msg(psock,msg)
spin_lock(ingress_lock)
sk_psock_zap_ingress()
_sk_psock_purge_ingerss_msg()
_sk_psock_purge_ingress_msg()
-- free ingress_msg list --
spin_unlock(ingress_lock)
spin_lock(ingress_lock)
list_add_tail(msg,ingress_msg) <- entry on list with no one
left to free it.
spin_unlock(ingress_lock)
To fix we only enqueue from backlog if the ENABLED bit is set. The tear
down logic clears the bit with ingress_lock set so we wont enqueue the
msg in the last step.
Fixes: 799aa7f98d53 ("skmsg: Avoid lock_sock() in sk_psock_backlog()")
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
---
include/linux/skmsg.h | 54 ++++++++++++++++++++++++++++---------------
net/core/skmsg.c | 6 -----
2 files changed, 35 insertions(+), 25 deletions(-)
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 96f319099744..94b4b61ba775 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h@@ -285,11 +285,45 @@ static inline struct sk_psock *sk_psock(const struct sock *sk) return rcu_dereference_sk_user_data(sk); } +static inline void sk_psock_set_state(struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + set_bit(bit, &psock->state); +} + +static inline void sk_psock_clear_state(struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + clear_bit(bit, &psock->state); +} + +static inline bool sk_psock_test_state(const struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + return test_bit(bit, &psock->state); +} + +static void sock_drop(struct sock *sk, struct sk_buff *skb) +{ + sk_drops_add(sk, skb); + kfree_skb(skb); +} + +static inline void drop_sk_msg(struct sk_psock *psock, struct sk_msg *msg) +{ + if (msg->skb) + sock_drop(psock->sk, msg->skb); + kfree(msg); +} + static inline void sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { spin_lock_bh(&psock->ingress_lock); - list_add_tail(&msg->list, &psock->ingress_msg); + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + list_add_tail(&msg->list, &psock->ingress_msg); + else + drop_sk_msg(psock, msg); spin_unlock_bh(&psock->ingress_lock); }
@@ -406,24 +440,6 @@ static inline void sk_psock_restore_proto(struct sock *sk, psock->psock_update_sk_prot(sk, psock, true); } -static inline void sk_psock_set_state(struct sk_psock *psock, - enum sk_psock_state_bits bit) -{ - set_bit(bit, &psock->state); -} - -static inline void sk_psock_clear_state(struct sk_psock *psock, - enum sk_psock_state_bits bit) -{ - clear_bit(bit, &psock->state); -} - -static inline bool sk_psock_test_state(const struct sk_psock *psock, - enum sk_psock_state_bits bit) -{ - return test_bit(bit, &psock->state); -} - static inline struct sk_psock *sk_psock_get(struct sock *sk) { struct sk_psock *psock;
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 036cdb33a94a..2d6249b28928 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c@@ -584,12 +584,6 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, return sk_psock_skb_ingress(psock, skb); } -static void sock_drop(struct sock *sk, struct sk_buff *skb) -{ - sk_drops_add(sk, skb); - kfree_skb(skb); -} - static void sk_psock_skb_state(struct sk_psock *psock, struct sk_psock_work_state *state, struct sk_buff *skb,
--
2.25.1