Skip to contentSkip to conversation

bpf, sockmap: fix page_counter underflow in strparser SK_PASS

PATCH In review Junseo Lim 3 participants 3 messages Jul 23 – Jul 29

Subsystems (4)
lore
Share & tools
lore

Junseo Lim

author
#0 lore raw

PATCH 1/1 bpf, sockmap: fix page_counter underflow in strparser SK_PASS

tcp_bpf_strp_read_sock() delays cleanup of SK_PASS bytes by subtracting psock->ingress_bytes from the amount passed to __tcp_cleanup_rbuf(). But when sk_psock_verdict_apply() queues the skb directly through sk_psock_skb_ingress_self(), skb_set_owner_r() is called unconditionally and charges the skb again.

The duplicated charge is later released independently and can trigger a page_counter underflow.

Add a charge_skb argument to sk_psock_skb_ingress_self() and skip skb_set_owner_r() only for the direct strparser SK_PASS path. Keep existing accounting for the other self-ingress caller and for non-strparser SK_PASS.

Fixes 36b62df5683c ("bpf: Fix wrong copied_seq calculation")

---
Crash reproduced on Linux tree 94515f3a7d4256a5062176b7d6ed0471938cd51a with KASAN, MEMCG, panic_on_warn=1, and oops=panic.

Reproducer/log/config: https://gist.github.com/ZirAjs/16c95c89972ace73910d9b5ac78a5807

The reproducer drives the strparser SK_PASS path until teardown reports:

page_counter underflow

  Workqueue: events sk_psock_destroy
  Kernel panic - not syncing: kernel: panic_on_warn set ...
 net/core/skmsg.c | 29 +++++++++++++++++------------
 1 file changed, 17 insertions(+), 12 deletions(-)
net/core/skmsg.c +17 -12
index 2521b643fa05..17260681479a 100644
@@ -586,7 +586,8 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
 }
 
 static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb,
-				     u32 off, u32 len, bool take_ref);
+				     u32 off, u32 len, bool take_ref,
+				     bool charge_skb);
 
 static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
 				u32 off, u32 len)
@@ -595,12 +596,9 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
 	struct sk_msg *msg;
 	int err;
 
-	/* If we are receiving on the same sock skb->sk is already assigned,
-	 * skip memory accounting and owner transition seeing it already set
-	 * correctly.
-	 */
 	if (unlikely(skb->sk == sk))
-		return sk_psock_skb_ingress_self(psock, skb, off, len, true);
+		return sk_psock_skb_ingress_self(psock, skb, off, len, true,
+						 true);
 	msg = sk_psock_create_ingress_msg(sk, skb);
 	if (!msg)
 		return -EAGAIN;
@@ -618,12 +616,14 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
 	return err;
 }
 
-/* Puts an skb on the ingress queue of the socket already assigned to the
- * skb. In this case we do not need to check memory limits or skb_set_owner_r
- * because the skb is already accounted for here.
+/* Puts an skb on the ingress queue for psock->sk.
+ *
+ * When charge_skb is false, the direct strparser SK_PASS path keeps the TCP
+ * receive queue accounting in place and must not call skb_set_owner_r().
  */
 static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb,
-				     u32 off, u32 len, bool take_ref)
+				     u32 off, u32 len, bool take_ref,
+				     bool charge_skb)
 {
 	struct sk_msg *msg = alloc_sk_msg(GFP_ATOMIC);
 	struct sock *sk = psock->sk;
@@ -631,7 +631,8 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb
 
 	if (unlikely(!msg))
 		return -EAGAIN;
-	skb_set_owner_r(skb, sk);
+	if (charge_skb)
+		skb_set_owner_r(skb, sk);
 
 	/* This is used in tcp_bpf_recvmsg_parser() to determine whether the
 	 * data originates from the socket's own protocol stack. No need to
@@ -1017,6 +1018,8 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
 		 * retrying later from workqueue.
 		 */
 		if (skb_queue_empty(&psock->ingress_skb)) {
+			bool charge_skb = true;
+
 			len = skb->len;
 			off = 0;
 			if (skb_bpf_strparser(skb)) {
@@ -1024,8 +1027,10 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
 
 				off = stm->offset;
 				len = stm->full_len;
+				charge_skb = false;
 			}
-			err = sk_psock_skb_ingress_self(psock, skb, off, len, false);
+			err = sk_psock_skb_ingress_self(psock, skb, off, len,
+							false, charge_skb);
 		}
 		if (err < 0) {
 			spin_lock_bh(&psock->ingress_lock);
Signature · 1 line
2.55.0
#1 lore raw
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider: - [Critical] Bypassing memory accounting in strparser SK_PASS path allows remote memory exhaustion (DoS) --

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Critical] Bypassing memory accounting in strparser SK_PASS path allows remote memory exhaustion (DoS) --

--- Patch [1]: [PATCH bpf] bpf, sockmap: fix page_counter underflow in strparser SK_PASS --- commit 5073ca36b1b9677d098ec43e3f231a7423b5d727
Author: Junseo Lim <[email protected]>

bpf, sockmap: fix page_counter underflow in strparser SK_PASS

This patch adds a charge_skb flag to skip memory accounting in the direct strparser SK_PASS path. It attempts to fix a page_counter underflow by preventing duplicate charges on the cloned SKB.

Quoted 4 lines
net/core/skmsg.c +0 -0
index 2521b643fa05d..17260681479a3 100644

[ ... ]

Quoted 1 line
net/core/skmsg.c +0 -0
@@ -618,12 +616,14 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,

[ ... ]

Quoted 8 lines

static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb,

net/core/skmsg.c +2 -1
-				     u32 off, u32 len, bool take_ref)
+				     u32 off, u32 len, bool take_ref,
+				     bool charge_skb)
 {
 	struct sk_msg *msg = alloc_sk_msg(GFP_ATOMIC);
 	struct sock *sk = psock->sk;

net/core/skmsg.c static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb · line 635

Quoted 6 lines
net/core/skmsg.c +2 -1
@@ -631,7 +631,8 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb
 
 	if (unlikely(!msg))
 		return -EAGAIN;
-	skb_set_owner_r(skb, sk);
+	if (charge_skb)
+		skb_set_owner_r(skb, sk);

[Severity: Critical]
Does skipping skb_set_owner_r() here leave the cloned SKB without an accounted truesize and without a destructor?

When charge_skb is false, the cloned SKB is queued without being charged. At the same time, __tcp_read_sock() unlinks and frees the original SKB via tcp_eat_recv_skb().

This invokes sock_rfree() and immediately subtracts skb->truesize from sk->sk_rmem_alloc.

Because this queued clone lacks a destructor and was never charged, could sk_rmem_alloc artificially drop to 0?

If so, tcp_select_window() might compute free_space as if the buffer is entirely empty, continuously advertising a fully open TCP window and potentially allowing a remote attacker to stream infinite data and exhaust kernel memory.

[ ... ]

Quoted 21 lines
net/core/skmsg.c +5 -1
@@ -1017,6 +1018,8 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
 		 * retrying later from workqueue.
 		 */
 		if (skb_queue_empty(&psock->ingress_skb)) {
+			bool charge_skb = true;
+
 			len = skb->len;
 			off = 0;
 			if (skb_bpf_strparser(skb)) {
@@ -1024,8 +1027,10 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
 
 				off = stm->offset;
 				len = stm->full_len;
+				charge_skb = false;
 			}
-			err = sk_psock_skb_ingress_self(psock, skb, off, len, false);
+			err = sk_psock_skb_ingress_self(psock, skb, off, len,
+							false, charge_skb);
 		}
 		if (err < 0) {
 			spin_lock_bh(&psock->ingress_lock);
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=1
#2 lore raw
In reply to Junseo Lim
Quoted 5 lines · Junseo Lim

tcp_bpf_strp_read_sock() delays cleanup of SK_PASS bytes by subtracting psock->ingress_bytes from the amount passed to __tcp_cleanup_rbuf(). But when sk_psock_verdict_apply() queues the skb directly through sk_psock_skb_ingress_self(), skb_set_owner_r() is called unconditionally and charges the skb again.

Can you specify in the commit that this is about sk_forward_alloc (AFAICT)? The eventual page_counter underflow is a second-order effect even if it's what eventually causes the crash.

Quoted 8 lines

The duplicated charge is later released independently and can trigger a page_counter underflow.

Add a charge_skb argument to sk_psock_skb_ingress_self() and skip skb_set_owner_r() only for the direct strparser SK_PASS path. Keep existing accounting for the other self-ingress caller and for non-strparser SK_PASS.

Quoted 5 lines
Fixes 36b62df5683c ("bpf: Fix wrong copied_seq calculation")

---
Crash reproduced on Linux tree 94515f3a7d4256a5062176b7d6ed0471938cd51a with KASAN, MEMCG, panic_on_warn=1, and oops=panic.

Can you make a selftest out of the reproducer?

Quoted 61 lines

Reproducer/log/config: https://gist.github.com/ZirAjs/16c95c89972ace73910d9b5ac78a5807

The reproducer drives the strparser SK_PASS path until teardown reports:

page_counter underflow

  Workqueue: events sk_psock_destroy
  Kernel panic - not syncing: kernel: panic_on_warn set ...
 net/core/skmsg.c | 29 +++++++++++++++++------------
 1 file changed, 17 insertions(+), 12 deletions(-)
net/core/skmsg.c +10 -10
index 2521b643fa05..17260681479a 100644
@@ -586,7 +586,8 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
 }
 
 static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb,
-				     u32 off, u32 len, bool take_ref);
+				     u32 off, u32 len, bool take_ref,
+				     bool charge_skb);
 
 static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
 				u32 off, u32 len)
@@ -595,12 +596,9 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
 	struct sk_msg *msg;
 	int err;
 
-	/* If we are receiving on the same sock skb->sk is already assigned,
-	 * skip memory accounting and owner transition seeing it already set
-	 * correctly.
-	 */
 	if (unlikely(skb->sk == sk))
-		return sk_psock_skb_ingress_self(psock, skb, off, len, true);
+		return sk_psock_skb_ingress_self(psock, skb, off, len, true,
+						 true);
 	msg = sk_psock_create_ingress_msg(sk, skb);
 	if (!msg)
 		return -EAGAIN;
@@ -618,12 +616,14 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
 	return err;
 }
 
-/* Puts an skb on the ingress queue of the socket already assigned to the
- * skb. In this case we do not need to check memory limits or skb_set_owner_r
- * because the skb is already accounted for here.
+/* Puts an skb on the ingress queue for psock->sk.
+ *
+ * When charge_skb is false, the direct strparser SK_PASS path keeps the TCP
+ * receive queue accounting in place and must not call skb_set_owner_r().
  */
 static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb,
-				     u32 off, u32 len, bool take_ref)
+				     u32 off, u32 len, bool take_ref,
+				     bool charge_skb)
 {
 	struct sk_msg *msg = alloc_sk_msg(GFP_ATOMIC);
 	struct sock *sk = psock->sk;

net/core/skmsg.c static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb · line 635

Quoted 6 lines
net/core/skmsg.c +2 -1
@@ -631,7 +631,8 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb
 
 	if (unlikely(!msg))
 		return -EAGAIN;
-	skb_set_owner_r(skb, sk);
+	if (charge_skb)
+		skb_set_owner_r(skb, sk);

Sashiko's right that skipping this leaves the skb half-configured. Since the point is to not double-count sk_forward_alloc but we still have to account truesize, can you try something like:

if (!skb_charge)

	sk_rmem_schedule(sk, skb, 0);

skb_set_owner_r(skb, sk);

to just ajust the sk_forward_alloc?

pw-bot: cr

Quoted 24 lines
net/core/skmsg.c +5 -1
 	/* This is used in tcp_bpf_recvmsg_parser() to determine whether the
 	 * data originates from the socket's own protocol stack. No need to
@@ -1017,6 +1018,8 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
 		 * retrying later from workqueue.
 		 */
 		if (skb_queue_empty(&psock->ingress_skb)) {
+			bool charge_skb = true;
+
 			len = skb->len;
 			off = 0;
 			if (skb_bpf_strparser(skb)) {
@@ -1024,8 +1027,10 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
 
 				off = stm->offset;
 				len = stm->full_len;
+				charge_skb = false;
 			}
-			err = sk_psock_skb_ingress_self(psock, skb, off, len, false);
+			err = sk_psock_skb_ingress_self(psock, skb, off, len,
+							false, charge_skb);
 		}
 		if (err < 0) {
 			spin_lock_bh(&psock->ingress_lock);