1 files changed, 186 insertions, 122 deletions

diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 8eb671c827f9..2ac7731e1e0a 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -8,6 +8,7 @@
 #include <net/sock.h>
 #include <net/tcp.h>
 #include <net/tls.h>
+#include <trace/events/sock.h>
 
 static bool sk_msg_try_coalesce_ok(struct sk_msg *msg, int elem_first_coalesce)
 {
@@ -27,6 +28,7 @@ int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len,
 		 int elem_first_coalesce)
 {
 	struct page_frag *pfrag = sk_page_frag(sk);
+	u32 osize = msg->sg.size;
 	int ret = 0;
 
 	len -= msg->sg.size;
@@ -35,13 +37,17 @@ int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len,
 		u32 orig_offset;
 		int use, i;
 
-		if (!sk_page_frag_refill(sk, pfrag))
-			return -ENOMEM;
+		if (!sk_page_frag_refill(sk, pfrag)) {
+			ret = -ENOMEM;
+			goto msg_trim;
+		}
 
 		orig_offset = pfrag->offset;
 		use = min_t(int, len, pfrag->size - orig_offset);
-		if (!sk_wmem_schedule(sk, use))
-			return -ENOMEM;
+		if (!sk_wmem_schedule(sk, use)) {
+			ret = -ENOMEM;
+			goto msg_trim;
+		}
 
 		i = msg->sg.end;
 		sk_msg_iter_var_prev(i);
@@ -71,6 +77,10 @@ int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len,
 	}
 
 	return ret;
+
+msg_trim:
+	sk_msg_trim(sk, msg, osize);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(sk_msg_alloc);
 
@@ -283,7 +293,7 @@ out:
 	/* If we trim data a full sg elem before curr pointer update
 	 * copybreak and current so that any future copy operations
 	 * start at new copy location.
-	 * However trimed data that has not yet been used in a copy op
+	 * However trimmed data that has not yet been used in a copy op
 	 * does not require an update.
 	 */
 	if (!msg->sg.size) {
@@ -315,14 +325,13 @@ int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from,
 			goto out;
 		}
 
-		copied = iov_iter_get_pages(from, pages, bytes, maxpages,
+		copied = iov_iter_get_pages2(from, pages, bytes, maxpages,
 					    &offset);
 		if (copied <= 0) {
 			ret = -EFAULT;
 			goto out;
 		}
 
-		iov_iter_advance(from, copied);
 		bytes -= copied;
 		msg->sg.size += copied;
 
@@ -360,8 +369,8 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
 			     struct sk_msg *msg, u32 bytes)
 {
 	int ret = -ENOSPC, i = msg->sg.curr;
+	u32 copy, buf_size, copied = 0;
 	struct scatterlist *sge;
-	u32 copy, buf_size;
 	void *to;
 
 	do {
@@ -388,6 +397,7 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
 			goto out;
 		}
 		bytes -= copy;
+		copied += copy;
 		if (!bytes)
 			break;
 		msg->sg.copybreak = 0;
@@ -395,7 +405,7 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
 	} while (i != msg->sg.end);
 out:
 	msg->sg.curr = i;
-	return ret;
+	return (ret < 0) ? ret : copied;
 }
 EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter);
 
@@ -425,16 +435,21 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 			page = sg_page(sge);
 			if (copied + copy > len)
 				copy = len - copied;
-			copy = copy_page_to_iter(page, sge->offset, copy, iter);
-			if (!copy)
-				return copied ? copied : -EFAULT;
+			if (copy)
+				copy = copy_page_to_iter(page, sge->offset, copy, iter);
+			if (!copy) {
+				copied = copied ? copied : -EFAULT;
+				goto out;
+			}
 
 			copied += copy;
 			if (likely(!peek)) {
 				sge->offset += copy;
 				sge->length -= copy;
-				if (!msg_rx->skb)
+				if (!msg_rx->skb) {
 					sk_mem_uncharge(sk, copy);
+					atomic_sub(copy, &sk->sk_rmem_alloc);
+				}
 				msg_rx->sg.size -= copy;
 
 				if (!sge->length) {
@@ -447,13 +462,13 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 				 * didn't copy the entire length lets just break.
 				 */
 				if (copy != sge->length)
-					return copied;
+					goto out;
 				sk_msg_iter_var_next(i);
 			}
 
 			if (copied == len)
 				break;
-		} while (i != msg_rx->sg.end);
+		} while ((i != msg_rx->sg.end) && !sg_is_last(sge));
 
 		if (unlikely(peek)) {
 			msg_rx = sk_psock_next_msg(psock, msg_rx);
@@ -463,13 +478,13 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 		}
 
 		msg_rx->sg.start = i;
-		if (!sge->length && msg_rx->sg.start == msg_rx->sg.end) {
+		if (!sge->length && (i == msg_rx->sg.end || sg_is_last(sge))) {
 			msg_rx = sk_psock_dequeue_msg(psock);
 			kfree_sk_msg(msg_rx);
 		}
 		msg_rx = sk_psock_peek_msg(psock);
 	}
-
+out:
 	return copied;
 }
 EXPORT_SYMBOL_GPL(sk_msg_recvmsg);
@@ -488,49 +503,66 @@ bool sk_msg_is_readable(struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(sk_msg_is_readable);
 
-static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk,
-						  struct sk_buff *skb)
+static struct sk_msg *alloc_sk_msg(gfp_t gfp)
 {
 	struct sk_msg *msg;
 
-	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
+	msg = kzalloc(sizeof(*msg), gfp | __GFP_NOWARN);
+	if (unlikely(!msg))
 		return NULL;
+	sg_init_marker(msg->sg.data, NR_MSG_FRAG_IDS);
+	return msg;
+}
 
-	if (!sk_rmem_schedule(sk, skb, skb->truesize))
+static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk,
+						  struct sk_buff *skb)
+{
+	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
 		return NULL;
 
-	msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_KERNEL);
-	if (unlikely(!msg))
+	if (!sk_rmem_schedule(sk, skb, skb->truesize))
 		return NULL;
 
-	sk_msg_init(msg);
-	return msg;
+	return alloc_sk_msg(GFP_KERNEL);
 }
 
 static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
 					u32 off, u32 len,
 					struct sk_psock *psock,
 					struct sock *sk,
-					struct sk_msg *msg)
+					struct sk_msg *msg,
+					bool take_ref)
 {
 	int num_sge, copied;
 
-	/* skb linearize may fail with ENOMEM, but lets simply try again
-	 * later if this happens. Under memory pressure we don't want to
-	 * drop the skb. We need to linearize the skb so that the mapping
-	 * in skb_to_sgvec can not error.
+	/* skb_to_sgvec will fail when the total number of fragments in
+	 * frag_list and frags exceeds MAX_MSG_FRAGS. For example, the
+	 * caller may aggregate multiple skbs.
 	 */
-	if (skb_linearize(skb))
-		return -EAGAIN;
 	num_sge = skb_to_sgvec(skb, msg->sg.data, off, len);
-	if (unlikely(num_sge < 0))
-		return num_sge;
+	if (num_sge < 0) {
+		/* skb linearize may fail with ENOMEM, but lets simply try again
+		 * later if this happens. Under memory pressure we don't want to
+		 * drop the skb. We need to linearize the skb so that the mapping
+		 * in skb_to_sgvec can not error.
+		 * Note that skb_linearize requires the skb not to be shared.
+		 */
+		if (skb_linearize(skb))
+			return -EAGAIN;
+
+		num_sge = skb_to_sgvec(skb, msg->sg.data, off, len);
+		if (unlikely(num_sge < 0))
+			return num_sge;
+	}
 
+#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
+	psock->ingress_bytes += len;
+#endif
 	copied = len;
 	msg->sg.start = 0;
 	msg->sg.size = copied;
 	msg->sg.end = num_sge;
-	msg->skb = skb;
+	msg->skb = take_ref ? skb_get(skb) : skb;
 
 	sk_psock_queue_msg(psock, msg);
 	sk_psock_data_ready(sk, psock);
@@ -538,7 +570,7 @@ 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);
+				     u32 off, u32 len, bool take_ref);
 
 static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
 				u32 off, u32 len)
@@ -552,7 +584,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
 	 * correctly.
 	 */
 	if (unlikely(skb->sk == sk))
-		return sk_psock_skb_ingress_self(psock, skb, off, len);
+		return sk_psock_skb_ingress_self(psock, skb, off, len, true);
 	msg = sk_psock_create_ingress_msg(sk, skb);
 	if (!msg)
 		return -EAGAIN;
@@ -564,7 +596,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
 	 * into user buffers.
 	 */
 	skb_set_owner_r(skb, sk);
-	err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg);
+	err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg, true);
 	if (err < 0)
 		kfree(msg);
 	return err;
@@ -575,17 +607,16 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
  * because the skb is already accounted for here.
  */
 static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb,
-				     u32 off, u32 len)
+				     u32 off, u32 len, bool take_ref)
 {
-	struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC);
+	struct sk_msg *msg = alloc_sk_msg(GFP_ATOMIC);
 	struct sock *sk = psock->sk;
 	int err;
 
 	if (unlikely(!msg))
 		return -EAGAIN;
-	sk_msg_init(msg);
 	skb_set_owner_r(skb, sk);
-	err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg);
+	err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg, take_ref);
 	if (err < 0)
 		kfree(msg);
 	return err;
@@ -599,47 +630,48 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
 			return -EAGAIN;
 		return skb_send_sock(psock->sk, skb, off, len);
 	}
+
 	return sk_psock_skb_ingress(psock, skb, off, len);
 }
 
 static void sk_psock_skb_state(struct sk_psock *psock,
 			       struct sk_psock_work_state *state,
-			       struct sk_buff *skb,
 			       int len, int off)
 {
 	spin_lock_bh(&psock->ingress_lock);
 	if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
-		state->skb = skb;
 		state->len = len;
 		state->off = off;
-	} else {
-		sock_drop(psock->sk, skb);
 	}
 	spin_unlock_bh(&psock->ingress_lock);
 }
 
 static void sk_psock_backlog(struct work_struct *work)
 {
-	struct sk_psock *psock = container_of(work, struct sk_psock, work);
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct sk_psock *psock = container_of(dwork, struct sk_psock, work);
 	struct sk_psock_work_state *state = &psock->work_state;
 	struct sk_buff *skb = NULL;
+	u32 len = 0, off = 0;
 	bool ingress;
-	u32 len, off;
 	int ret;
 
-	mutex_lock(&psock->work_mutex);
-	if (unlikely(state->skb)) {
-		spin_lock_bh(&psock->ingress_lock);
-		skb = state->skb;
-		len = state->len;
-		off = state->off;
-		state->skb = NULL;
-		spin_unlock_bh(&psock->ingress_lock);
-	}
-	if (skb)
-		goto start;
+	/* If sk is quickly removed from the map and then added back, the old
+	 * psock should not be scheduled, because there are now two psocks
+	 * pointing to the same sk.
+	 */
+	if (!sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
+		return;
 
-	while ((skb = skb_dequeue(&psock->ingress_skb))) {
+	/* Increment the psock refcnt to synchronize with close(fd) path in
+	 * sock_map_close(), ensuring we wait for backlog thread completion
+	 * before sk_socket freed. If refcnt increment fails, it indicates
+	 * sock_map_close() completed with sk_socket potentially already freed.
+	 */
+	if (!sk_psock_get(psock->sk))
+		return;
+	mutex_lock(&psock->work_mutex);
+	while ((skb = skb_peek(&psock->ingress_skb))) {
 		len = skb->len;
 		off = 0;
 		if (skb_bpf_strparser(skb)) {
@@ -648,7 +680,13 @@ static void sk_psock_backlog(struct work_struct *work)
 			off = stm->offset;
 			len = stm->full_len;
 		}
-start:
+
+		/* Resume processing from previous partial state */
+		if (unlikely(state->len)) {
+			len = state->len;
+			off = state->off;
+		}
+
 		ingress = skb_bpf_ingress(skb);
 		skb_bpf_redirect_clear(skb);
 		do {
@@ -658,25 +696,33 @@ start:
 							  len, ingress);
 			if (ret <= 0) {
 				if (ret == -EAGAIN) {
-					sk_psock_skb_state(psock, state, skb,
-							   len, off);
+					sk_psock_skb_state(psock, state, len, off);
+					/* Restore redir info we cleared before */
+					skb_bpf_set_redir(skb, psock->sk, ingress);
+					/* Delay slightly to prioritize any
+					 * other work that might be here.
+					 */
+					if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
+						schedule_delayed_work(&psock->work, 1);
 					goto end;
 				}
 				/* Hard errors break pipe and stop xmit. */
 				sk_psock_report_error(psock, ret ? -ret : EPIPE);
 				sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
-				sock_drop(psock->sk, skb);
 				goto end;
 			}
 			off += ret;
 			len -= ret;
 		} while (len);
 
-		if (!ingress)
-			kfree_skb(skb);
+		/* The entire skb sent, clear state */
+		sk_psock_skb_state(psock, state, 0, 0);
+		skb = skb_dequeue(&psock->ingress_skb);
+		kfree_skb(skb);
 	}
 end:
 	mutex_unlock(&psock->work_mutex);
+	sk_psock_put(psock->sk, psock);
 }
 
 struct sk_psock *sk_psock_init(struct sock *sk, int node)
@@ -686,6 +732,11 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node)
 
 	write_lock_bh(&sk->sk_callback_lock);
 
+	if (sk_is_inet(sk) && inet_csk_has_ulp(sk)) {
+		psock = ERR_PTR(-EINVAL);
+		goto out;
+	}
+
 	if (sk->sk_user_data) {
 		psock = ERR_PTR(-EBUSY);
 		goto out;
@@ -702,13 +753,14 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node)
 	psock->eval = __SK_NONE;
 	psock->sk_proto = prot;
 	psock->saved_unhash = prot->unhash;
+	psock->saved_destroy = prot->destroy;
 	psock->saved_close = prot->close;
 	psock->saved_write_space = sk->sk_write_space;
 
 	INIT_LIST_HEAD(&psock->link);
 	spin_lock_init(&psock->link_lock);
 
-	INIT_WORK(&psock->work, sk_psock_backlog);
+	INIT_DELAYED_WORK(&psock->work, sk_psock_backlog);
 	mutex_init(&psock->work_mutex);
 	INIT_LIST_HEAD(&psock->ingress_msg);
 	spin_lock_init(&psock->ingress_lock);
@@ -717,7 +769,9 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node)
 	sk_psock_set_state(psock, SK_PSOCK_TX_ENABLED);
 	refcount_set(&psock->refcnt, 1);
 
-	rcu_assign_sk_user_data_nocopy(sk, psock);
+	__rcu_assign_sk_user_data_with_flags(sk, psock,
+					     SK_USER_DATA_NOCOPY |
+					     SK_USER_DATA_PSOCK);
 	sock_hold(sk);
 
 out:
@@ -745,6 +799,8 @@ static void __sk_psock_purge_ingress_msg(struct sk_psock *psock)
 
 	list_for_each_entry_safe(msg, tmp, &psock->ingress_msg, list) {
 		list_del(&msg->list);
+		if (!msg->skb)
+			atomic_sub(msg->sg.size, &psock->sk->sk_rmem_alloc);
 		sk_msg_free(psock->sk, msg);
 		kfree(msg);
 	}
@@ -758,11 +814,6 @@ static void __sk_psock_zap_ingress(struct sk_psock *psock)
 		skb_bpf_redirect_clear(skb);
 		sock_drop(psock->sk, skb);
 	}
-	kfree_skb(psock->work_state.skb);
-	/* We null the skb here to ensure that calls to sk_psock_backlog
-	 * do not pick up the free'd skb.
-	 */
-	psock->work_state.skb = NULL;
 	__sk_psock_purge_ingress_msg(psock);
 }
 
@@ -776,16 +827,12 @@ static void sk_psock_link_destroy(struct sk_psock *psock)
 	}
 }
 
-void sk_psock_stop(struct sk_psock *psock, bool wait)
+void sk_psock_stop(struct sk_psock *psock)
 {
 	spin_lock_bh(&psock->ingress_lock);
 	sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
 	sk_psock_cork_free(psock);
-	__sk_psock_zap_ingress(psock);
 	spin_unlock_bh(&psock->ingress_lock);
-
-	if (wait)
-		cancel_work_sync(&psock->work);
 }
 
 static void sk_psock_done_strp(struct sk_psock *psock);
@@ -798,7 +845,8 @@ static void sk_psock_destroy(struct work_struct *work)
 
 	sk_psock_done_strp(psock);
 
-	cancel_work_sync(&psock->work);
+	cancel_delayed_work_sync(&psock->work);
+	__sk_psock_zap_ingress(psock);
 	mutex_destroy(&psock->work_mutex);
 
 	psock_progs_drop(&psock->progs);
@@ -808,6 +856,8 @@ static void sk_psock_destroy(struct work_struct *work)
 
 	if (psock->sk_redir)
 		sock_put(psock->sk_redir);
+	if (psock->sk_pair)
+		sock_put(psock->sk_pair);
 	sock_put(psock->sk);
 	kfree(psock);
 }
@@ -823,10 +873,10 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
 		sk_psock_stop_verdict(sk, psock);
 	write_unlock_bh(&sk->sk_callback_lock);
 
-	sk_psock_stop(psock, false);
+	sk_psock_stop(psock);
 
 	INIT_RCU_WORK(&psock->rwork, sk_psock_destroy);
-	queue_rcu_work(system_wq, &psock->rwork);
+	queue_rcu_work(system_percpu_wq, &psock->rwork);
 }
 EXPORT_SYMBOL_GPL(sk_psock_drop);
 
@@ -862,13 +912,16 @@ int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock,
 	ret = sk_psock_map_verd(ret, msg->sk_redir);
 	psock->apply_bytes = msg->apply_bytes;
 	if (ret == __SK_REDIRECT) {
-		if (psock->sk_redir)
+		if (psock->sk_redir) {
 			sock_put(psock->sk_redir);
-		psock->sk_redir = msg->sk_redir;
-		if (!psock->sk_redir) {
+			psock->sk_redir = NULL;
+		}
+		if (!msg->sk_redir) {
 			ret = __SK_DROP;
 			goto out;
 		}
+		psock->redir_ingress = sk_msg_to_ingress(msg);
+		psock->sk_redir = msg->sk_redir;
 		sock_hold(psock->sk_redir);
 	}
 out:
@@ -910,7 +963,7 @@ static int sk_psock_skb_redirect(struct sk_psock *from, struct sk_buff *skb)
 	}
 
 	skb_queue_tail(&psock_other->ingress_skb, skb);
-	schedule_work(&psock_other->work);
+	schedule_delayed_work(&psock_other->work, 0);
 	spin_unlock_bh(&psock_other->ingress_lock);
 	return 0;
 }
@@ -962,10 +1015,8 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
 		err = -EIO;
 		sk_other = psock->sk;
 		if (sock_flag(sk_other, SOCK_DEAD) ||
-		    !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
-			skb_bpf_redirect_clear(skb);
+		    !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
 			goto out_free;
-		}
 
 		skb_bpf_set_ingress(skb);
 
@@ -984,28 +1035,29 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
 				off = stm->offset;
 				len = stm->full_len;
 			}
-			err = sk_psock_skb_ingress_self(psock, skb, off, len);
+			err = sk_psock_skb_ingress_self(psock, skb, off, len, false);
 		}
 		if (err < 0) {
 			spin_lock_bh(&psock->ingress_lock);
 			if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
 				skb_queue_tail(&psock->ingress_skb, skb);
-				schedule_work(&psock->work);
+				schedule_delayed_work(&psock->work, 0);
 				err = 0;
 			}
 			spin_unlock_bh(&psock->ingress_lock);
-			if (err < 0) {
-				skb_bpf_redirect_clear(skb);
+			if (err < 0)
 				goto out_free;
-			}
 		}
 		break;
 	case __SK_REDIRECT:
+		tcp_eat_skb(psock->sk, skb);
 		err = sk_psock_skb_redirect(psock, skb);
 		break;
 	case __SK_DROP:
 	default:
 out_free:
+		skb_bpf_redirect_clear(skb);
+		tcp_eat_skb(psock->sk, skb);
 		sock_drop(psock->sk, skb);
 	}
 
@@ -1021,7 +1073,7 @@ static void sk_psock_write_space(struct sock *sk)
 	psock = sk_psock(sk);
 	if (likely(psock)) {
 		if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
-			schedule_work(&psock->work);
+			schedule_delayed_work(&psock->work, 0);
 		write_space = psock->saved_write_space;
 	}
 	rcu_read_unlock();
@@ -1050,8 +1102,7 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
 		skb_dst_drop(skb);
 		skb_bpf_redirect_clear(skb);
 		ret = bpf_prog_run_pin_on_cpu(prog, skb);
-		if (ret == SK_PASS)
-			skb_bpf_set_strparser(skb);
+		skb_bpf_set_strparser(skb);
 		ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
 		skb->sk = NULL;
 	}
@@ -1087,15 +1138,17 @@ static void sk_psock_strp_data_ready(struct sock *sk)
 {
 	struct sk_psock *psock;
 
+	trace_sk_data_ready(sk);
+
 	rcu_read_lock();
 	psock = sk_psock(sk);
 	if (likely(psock)) {
 		if (tls_sw_has_ctx_rx(sk)) {
 			psock->saved_data_ready(sk);
 		} else {
-			write_lock_bh(&sk->sk_callback_lock);
+			read_lock_bh(&sk->sk_callback_lock);
 			strp_data_ready(&psock->strp);
-			write_unlock_bh(&sk->sk_callback_lock);
+			read_unlock_bh(&sk->sk_callback_lock);
 		}
 	}
 	rcu_read_unlock();
@@ -1103,13 +1156,23 @@ static void sk_psock_strp_data_ready(struct sock *sk)
 
 int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock)
 {
+	int ret;
+
 	static const struct strp_callbacks cb = {
 		.rcv_msg	= sk_psock_strp_read,
 		.read_sock_done	= sk_psock_strp_read_done,
 		.parse_msg	= sk_psock_strp_parse,
 	};
 
-	return strp_init(&psock->strp, sk, &cb);
+	ret = strp_init(&psock->strp, sk, &cb);
+	if (!ret)
+		sk_psock_set_state(psock, SK_PSOCK_RX_STRP_ENABLED);
+
+	if (sk_is_tcp(sk)) {
+		psock->strp.cb.read_sock = tcp_bpf_strp_read_sock;
+		psock->copied_seq = tcp_sk(sk)->copied_seq;
+	}
+	return ret;
 }
 
 void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
@@ -1137,7 +1200,7 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
 static void sk_psock_done_strp(struct sk_psock *psock)
 {
 	/* Parser has been stopped */
-	if (psock->progs.stream_parser)
+	if (sk_psock_test_state(psock, SK_PSOCK_RX_STRP_ENABLED))
 		strp_done(&psock->strp);
 }
 #else
@@ -1146,26 +1209,18 @@ static void sk_psock_done_strp(struct sk_psock *psock)
 }
 #endif /* CONFIG_BPF_STREAM_PARSER */
 
-static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb,
-				 unsigned int offset, size_t orig_len)
+static int sk_psock_verdict_recv(struct sock *sk, struct sk_buff *skb)
 {
-	struct sock *sk = (struct sock *)desc->arg.data;
 	struct sk_psock *psock;
 	struct bpf_prog *prog;
 	int ret = __SK_DROP;
 	int len = skb->len;
 
-	/* clone here so sk_eat_skb() in tcp_read_sock does not drop our data */
-	skb = skb_clone(skb, GFP_ATOMIC);
-	if (!skb) {
-		desc->error = -ENOMEM;
-		return 0;
-	}
-
 	rcu_read_lock();
 	psock = sk_psock(sk);
 	if (unlikely(!psock)) {
 		len = 0;
+		tcp_eat_skb(sk, skb);
 		sock_drop(sk, skb);
 		goto out;
 	}
@@ -1173,15 +1228,14 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb,
 	if (!prog)
 		prog = READ_ONCE(psock->progs.skb_verdict);
 	if (likely(prog)) {
-		skb->sk = sk;
 		skb_dst_drop(skb);
 		skb_bpf_redirect_clear(skb);
 		ret = bpf_prog_run_pin_on_cpu(prog, skb);
 		ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
-		skb->sk = NULL;
 	}
-	if (sk_psock_verdict_apply(psock, skb, ret) < 0)
-		len = 0;
+	ret = sk_psock_verdict_apply(psock, skb, ret);
+	if (ret < 0)
+		len = ret;
 out:
 	rcu_read_unlock();
 	return len;
@@ -1190,16 +1244,26 @@ out:
 static void sk_psock_verdict_data_ready(struct sock *sk)
 {
 	struct socket *sock = sk->sk_socket;
-	read_descriptor_t desc;
+	const struct proto_ops *ops;
+	int copied;
 
-	if (unlikely(!sock || !sock->ops || !sock->ops->read_sock))
-		return;
+	trace_sk_data_ready(sk);
 
-	desc.arg.data = sk;
-	desc.error = 0;
-	desc.count = 1;
-
-	sock->ops->read_sock(sk, &desc, sk_psock_verdict_recv);
+	if (unlikely(!sock))
+		return;
+	ops = READ_ONCE(sock->ops);
+	if (!ops || !ops->read_skb)
+		return;
+	copied = ops->read_skb(sk, sk_psock_verdict_recv);
+	if (copied >= 0) {
+		struct sk_psock *psock;
+
+		rcu_read_lock();
+		psock = sk_psock(sk);
+		if (psock)
+			sk_psock_data_ready(sk, psock);
+		rcu_read_unlock();
+	}
 }
 
 void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock)