Skip to contentSkip to conversation

FAILED: patch "[PATCH] packet: synchronize pressure clearing with ring" failed to apply to 5.15-stable tree

PATCH New [email protected] 2 participants 2 messages Aug 17 – Aug 21

Subsystems (3)
lore
Share & tools
lore

[email protected]

author maintainer
#0 lore raw

The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <[email protected]>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x 1a35da325cac4d5bcad76a2aa943408a6f1d9000
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<[email protected]>' --in-reply-to '2026081735-transpire-shining-9653@gregkh' --subject-prefix 'PATCH 5.15.y' 'HEAD^..'

Possible dependencies:

thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From 1a35da325cac4d5bcad76a2aa943408a6f1d9000 Mon Sep 17 00:00:00 2001
From: Zihan Xi <[email protected]>
Date: Wed, 29 Jul 2026 09:16:53 +0000
Subject: [PATCH] packet: synchronize pressure clearing with ring
reconfiguration

packet_set_ring() updates the RX ring state under sk_receive_queue.lock, but used to publish the tpacket receive mode through po->prot_hook.func after releasing that lock. packet_poll() and packet_recvmsg() can then run the pressure clearing path after the ring has been cleared while still seeing tpacket_rcv, causing __packet_rcv_has_room() to dereference stale or NULL ring storage.

Move the existing receive hook assignment into the same sk_receive_queue.lock section as the ring state update. Keep the assignment otherwise unchanged, including on TX ring reconfiguration, to avoid adding behavior changes that are not required for the fix.

Serialize packet_recvmsg() pressure clearing with the same queue lock only after PACKET_SOCK_PRESSURE has been observed. If the flag is clear and the socket has moved away from tpacket_rcv, packet_set_ring() has already detached the socket and waited for synchronize_net(), so no new packet input can set the flag again.

packet_poll() already holds sk_receive_queue.lock, so it uses the new unlocked helper directly.

net/packet/af_packet.c +16 -4
index 5ae0511e89e3..0e1355be89f6 100644
@@ -1315,13 +1315,25 @@ static int packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb)
 	return ret;
 }
 
-static void packet_rcv_try_clear_pressure(struct packet_sock *po)
+static void __packet_rcv_try_clear_pressure(struct packet_sock *po)
 {
 	if (packet_sock_flag(po, PACKET_SOCK_PRESSURE) &&
 	    __packet_rcv_has_room(po, NULL) == ROOM_NORMAL)
 		packet_sock_flag_set(po, PACKET_SOCK_PRESSURE, false);
 }
 
+static void packet_rcv_try_clear_pressure(struct packet_sock *po)
+{
+	struct sock *sk = &po->sk;
+
+	if (!packet_sock_flag(po, PACKET_SOCK_PRESSURE))
+		return;
+
+	spin_lock_bh(&sk->sk_receive_queue.lock);
+	__packet_rcv_try_clear_pressure(po);
+	spin_unlock_bh(&sk->sk_receive_queue.lock);
+}
+
 static void packet_sock_destruct(struct sock *sk)
 {
 	skb_queue_purge(&sk->sk_error_queue);
@@ -4305,7 +4317,7 @@ static __poll_t packet_poll(struct file *file, struct socket *sock,
 			TP_STATUS_KERNEL))
 			mask |= EPOLLIN | EPOLLRDNORM;
 	}
-	packet_rcv_try_clear_pressure(po);
+	__packet_rcv_try_clear_pressure(po);
 	spin_unlock_bh(&sk->sk_receive_queue.lock);
 	spin_lock_bh(&sk->sk_write_queue.lock);
 	if (po->tx_ring.pg_vec) {
@@ -4545,14 +4557,14 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		rb->frame_max = (req->tp_frame_nr - 1);
 		rb->head = 0;
 		rb->frame_size = req->tp_frame_size;
+		po->prot_hook.func = (po->rx_ring.pg_vec) ?
+						tpacket_rcv : packet_rcv;
 		spin_unlock_bh(&rb_queue->lock);
 
 		swap(rb->pg_vec_order, order);
 		swap(rb->pg_vec_len, req->tp_block_nr);
 
 		rb->pg_vec_pages = req->tp_block_size/PAGE_SIZE;
-		po->prot_hook.func = (po->rx_ring.pg_vec) ?
-						tpacket_rcv : packet_rcv;
 		skb_queue_purge(rb_queue);
 		if (atomic_long_read(&po->mapped))
 			pr_err("packet_mmap: vma is busy: %ld\n",
maintainer
#1 lore raw

PATCH 1/1 packet: synchronize pressure clearing with ring reconfiguration

From: Zihan Xi <[email protected]>

[ Upstream commit 1a35da325cac4d5bcad76a2aa943408a6f1d9000 ]

packet_set_ring() updates the RX ring state under sk_receive_queue.lock, but used to publish the tpacket receive mode through po->prot_hook.func after releasing that lock. packet_poll() and packet_recvmsg() can then run the pressure clearing path after the ring has been cleared while still seeing tpacket_rcv, causing __packet_rcv_has_room() to dereference stale or NULL ring storage.

Move the existing receive hook assignment into the same sk_receive_queue.lock section as the ring state update. Keep the assignment otherwise unchanged, including on TX ring reconfiguration, to avoid adding behavior changes that are not required for the fix.

Serialize packet_recvmsg() pressure clearing with the same queue lock only after PACKET_SOCK_PRESSURE has been observed. If the flag is clear and the socket has moved away from tpacket_rcv, packet_set_ring() has already detached the socket and waited for synchronize_net(), so no new packet input can set the flag again.

packet_poll() already holds sk_receive_queue.lock, so it uses the new unlocked helper directly.

Fixes 2ccdbaa6d55b ("packet: rollover lock contention avoidance")
Assisted-by Codex:gpt-5.4
[ Replaced `packet_sock_flag(po, PACKET_SOCK_PRESSURE)` with `READ_ONCE(po->pressure)` since the flag conversion isn't in this tree. ]
---
 net/packet/af_packet.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)
net/packet/af_packet.c +16 -4
index 2c1a0c5e6df1f..95c46c15219a2 100644
@@ -1333,13 +1333,25 @@ static int packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb)
 	return ret;
 }
 
-static void packet_rcv_try_clear_pressure(struct packet_sock *po)
+static void __packet_rcv_try_clear_pressure(struct packet_sock *po)
 {
 	if (READ_ONCE(po->pressure) &&
 	    __packet_rcv_has_room(po, NULL) == ROOM_NORMAL)
 		WRITE_ONCE(po->pressure,  0);
 }
 
+static void packet_rcv_try_clear_pressure(struct packet_sock *po)
+{
+	struct sock *sk = &po->sk;
+
+	if (!READ_ONCE(po->pressure))
+		return;
+
+	spin_lock_bh(&sk->sk_receive_queue.lock);
+	__packet_rcv_try_clear_pressure(po);
+	spin_unlock_bh(&sk->sk_receive_queue.lock);
+}
+
 static void packet_sock_destruct(struct sock *sk)
 {
 	skb_queue_purge(&sk->sk_error_queue);
@@ -4292,7 +4304,7 @@ static __poll_t packet_poll(struct file *file, struct socket *sock,
 			TP_STATUS_KERNEL))
 			mask |= EPOLLIN | EPOLLRDNORM;
 	}
-	packet_rcv_try_clear_pressure(po);
+	__packet_rcv_try_clear_pressure(po);
 	spin_unlock_bh(&sk->sk_receive_queue.lock);
 	spin_lock_bh(&sk->sk_write_queue.lock);
 	if (po->tx_ring.pg_vec) {
@@ -4532,14 +4544,14 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		rb->frame_max = (req->tp_frame_nr - 1);
 		rb->head = 0;
 		rb->frame_size = req->tp_frame_size;
+		po->prot_hook.func = (po->rx_ring.pg_vec) ?
+						tpacket_rcv : packet_rcv;
 		spin_unlock_bh(&rb_queue->lock);
 
 		swap(rb->pg_vec_order, order);
 		swap(rb->pg_vec_len, req->tp_block_nr);
 
 		rb->pg_vec_pages = req->tp_block_size/PAGE_SIZE;
-		po->prot_hook.func = (po->rx_ring.pg_vec) ?
-						tpacket_rcv : packet_rcv;
 		skb_queue_purge(rb_queue);
 		if (atomic_long_read(&po->mapped))
 			pr_err("packet_mmap: vma is busy: %ld\n",
Signature · 1 line
2.53.0