Merge tag 'for-5.20/io_uring-zerocopy-send-2022-07-29' of git://git.kernel.dk/linux-block

Pull io_uring zerocopy support from Jens Axboe:
 "This adds support for efficient support for zerocopy sends through
  io_uring. Both ipv4 and ipv6 is supported, as well as both TCP and
  UDP.

  The core network changes to support this is in a stable branch from
  Jakub that both io_uring and net-next has pulled in, and the io_uring
  changes are layered on top of that.

  All of the work has been done by Pavel"

* tag 'for-5.20/io_uring-zerocopy-send-2022-07-29' of git://git.kernel.dk/linux-block: (34 commits)
  io_uring: notification completion optimisation
  io_uring: export req alloc from core
  io_uring/net: use unsigned for flags
  io_uring/net: make page accounting more consistent
  io_uring/net: checks errors of zc mem accounting
  io_uring/net: improve io_get_notif_slot types
  selftests/io_uring: test zerocopy send
  io_uring: enable managed frags with register buffers
  io_uring: add zc notification flush requests
  io_uring: rename IORING_OP_FILES_UPDATE
  io_uring: flush notifiers after sendzc
  io_uring: sendzc with fixed buffers
  io_uring: allow to pass addr into sendzc
  io_uring: account locked pages for non-fixed zc
  io_uring: wire send zc request type
  io_uring: add notification slot registration
  io_uring: add rsrc referencing for notifiers
  io_uring: complete notifiers in tw
  io_uring: cache struct io_notif
  io_uring: add zc notification infrastructure
  ...

7 files changed, 140 insertions, 46 deletions

diff --git a/net/compat.c b/net/compat.c
index ed880729d159..fe9be3c56ef7 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -75,6 +75,7 @@ int __get_compat_msghdr(struct msghdr *kmsg,
 		return -EMSGSIZE;
 
 	kmsg->msg_iocb = NULL;
+	kmsg->msg_ubuf = NULL;
 	return 0;
 }
 
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 50f4faeea76c..ecbc0f471089 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -613,10 +613,16 @@ fault:
 }
 EXPORT_SYMBOL(skb_copy_datagram_from_iter);
 
-int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb,
-			    struct iov_iter *from, size_t length)
+int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
+			    struct sk_buff *skb, struct iov_iter *from,
+			    size_t length)
 {
-	int frag = skb_shinfo(skb)->nr_frags;
+	int frag;
+
+	if (msg && msg->msg_ubuf && msg->sg_from_iter)
+		return msg->sg_from_iter(sk, skb, from, length);
+
+	frag = skb_shinfo(skb)->nr_frags;
 
 	while (length && iov_iter_count(from)) {
 		struct page *pages[MAX_SKB_FRAGS];
@@ -702,7 +708,7 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from)
 	if (skb_copy_datagram_from_iter(skb, 0, from, copy))
 		return -EFAULT;
 
-	return __zerocopy_sg_from_iter(NULL, skb, from, ~0U);
+	return __zerocopy_sg_from_iter(NULL, NULL, skb, from, ~0U);
 }
 EXPORT_SYMBOL(zerocopy_sg_from_iter);
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 5b3559cb1d82..cf4107d80bc4 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -666,11 +666,18 @@ static void skb_release_data(struct sk_buff *skb)
 			      &shinfo->dataref))
 		goto exit;
 
-	skb_zcopy_clear(skb, true);
+	if (skb_zcopy(skb)) {
+		bool skip_unref = shinfo->flags & SKBFL_MANAGED_FRAG_REFS;
+
+		skb_zcopy_clear(skb, true);
+		if (skip_unref)
+			goto free_head;
+	}
 
 	for (i = 0; i < shinfo->nr_frags; i++)
 		__skb_frag_unref(&shinfo->frags[i], skb->pp_recycle);
 
+free_head:
 	if (shinfo->frag_list)
 		kfree_skb_list(shinfo->frag_list);
 
@@ -895,7 +902,10 @@ EXPORT_SYMBOL(skb_dump);
  */
 void skb_tx_error(struct sk_buff *skb)
 {
-	skb_zcopy_clear(skb, true);
+	if (skb) {
+		skb_zcopy_downgrade_managed(skb);
+		skb_zcopy_clear(skb, true);
+	}
 }
 EXPORT_SYMBOL(skb_tx_error);
 
@@ -1193,7 +1203,7 @@ static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size)
 	uarg->len = 1;
 	uarg->bytelen = size;
 	uarg->zerocopy = 1;
-	uarg->flags = SKBFL_ZEROCOPY_FRAG;
+	uarg->flags = SKBFL_ZEROCOPY_FRAG | SKBFL_DONT_ORPHAN;
 	refcount_set(&uarg->refcnt, 1);
 	sock_hold(sk);
 
@@ -1212,6 +1222,10 @@ struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
 		const u32 byte_limit = 1 << 19;		/* limit to a few TSO */
 		u32 bytelen, next;
 
+		/* there might be non MSG_ZEROCOPY users */
+		if (uarg->callback != msg_zerocopy_callback)
+			return NULL;
+
 		/* realloc only when socket is locked (TCP, UDP cork),
 		 * so uarg->len and sk_zckey access is serialized
 		 */
@@ -1354,7 +1368,7 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
 	if (orig_uarg && uarg != orig_uarg)
 		return -EEXIST;
 
-	err = __zerocopy_sg_from_iter(sk, skb, &msg->msg_iter, len);
+	err = __zerocopy_sg_from_iter(msg, sk, skb, &msg->msg_iter, len);
 	if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) {
 		struct sock *save_sk = skb->sk;
 
@@ -1371,6 +1385,16 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
 }
 EXPORT_SYMBOL_GPL(skb_zerocopy_iter_stream);
 
+void __skb_zcopy_downgrade_managed(struct sk_buff *skb)
+{
+	int i;
+
+	skb_shinfo(skb)->flags &= ~SKBFL_MANAGED_FRAG_REFS;
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
+		skb_frag_ref(skb, i);
+}
+EXPORT_SYMBOL_GPL(__skb_zcopy_downgrade_managed);
+
 static int skb_zerocopy_clone(struct sk_buff *nskb, struct sk_buff *orig,
 			      gfp_t gfp_mask)
 {
@@ -1688,6 +1712,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
 
 	BUG_ON(skb_shared(skb));
 
+	skb_zcopy_downgrade_managed(skb);
+
 	size = SKB_DATA_ALIGN(size);
 
 	if (skb_pfmemalloc(skb))
@@ -3484,6 +3510,8 @@ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len)
 	int pos = skb_headlen(skb);
 	const int zc_flags = SKBFL_SHARED_FRAG | SKBFL_PURE_ZEROCOPY;
 
+	skb_zcopy_downgrade_managed(skb);
+
 	skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & zc_flags;
 	skb_zerocopy_clone(skb1, skb, 0);
 	if (len < pos)	/* Split line is inside header. */
@@ -3837,6 +3865,7 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page,
 	if (skb_can_coalesce(skb, i, page, offset)) {
 		skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], size);
 	} else if (i < MAX_SKB_FRAGS) {
+		skb_zcopy_downgrade_managed(skb);
 		get_page(page);
 		skb_fill_page_desc(skb, i, page, offset, size);
 	} else {
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 00b4bf26fd93..df7f9dfbe8be 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -969,7 +969,6 @@ static int __ip_append_data(struct sock *sk,
 	struct inet_sock *inet = inet_sk(sk);
 	struct ubuf_info *uarg = NULL;
 	struct sk_buff *skb;
-
 	struct ip_options *opt = cork->opt;
 	int hh_len;
 	int exthdrlen;
@@ -977,6 +976,7 @@ static int __ip_append_data(struct sock *sk,
 	int copy;
 	int err;
 	int offset = 0;
+	bool zc = false;
 	unsigned int maxfraglen, fragheaderlen, maxnonfragsize;
 	int csummode = CHECKSUM_NONE;
 	struct rtable *rt = (struct rtable *)cork->dst;
@@ -1017,17 +1017,35 @@ static int __ip_append_data(struct sock *sk,
 	    (!exthdrlen || (rt->dst.dev->features & NETIF_F_HW_ESP_TX_CSUM)))
 		csummode = CHECKSUM_PARTIAL;
 
-	if (flags & MSG_ZEROCOPY && length && sock_flag(sk, SOCK_ZEROCOPY)) {
-		uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb));
-		if (!uarg)
-			return -ENOBUFS;
-		extra_uref = !skb_zcopy(skb);	/* only ref on new uarg */
-		if (rt->dst.dev->features & NETIF_F_SG &&
-		    csummode == CHECKSUM_PARTIAL) {
-			paged = true;
-		} else {
-			uarg->zerocopy = 0;
-			skb_zcopy_set(skb, uarg, &extra_uref);
+	if ((flags & MSG_ZEROCOPY) && length) {
+		struct msghdr *msg = from;
+
+		if (getfrag == ip_generic_getfrag && msg->msg_ubuf) {
+			if (skb_zcopy(skb) && msg->msg_ubuf != skb_zcopy(skb))
+				return -EINVAL;
+
+			/* Leave uarg NULL if can't zerocopy, callers should
+			 * be able to handle it.
+			 */
+			if ((rt->dst.dev->features & NETIF_F_SG) &&
+			    csummode == CHECKSUM_PARTIAL) {
+				paged = true;
+				zc = true;
+				uarg = msg->msg_ubuf;
+			}
+		} else if (sock_flag(sk, SOCK_ZEROCOPY)) {
+			uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb));
+			if (!uarg)
+				return -ENOBUFS;
+			extra_uref = !skb_zcopy(skb);	/* only ref on new uarg */
+			if (rt->dst.dev->features & NETIF_F_SG &&
+			    csummode == CHECKSUM_PARTIAL) {
+				paged = true;
+				zc = true;
+			} else {
+				uarg->zerocopy = 0;
+				skb_zcopy_set(skb, uarg, &extra_uref);
+			}
 		}
 	}
 
@@ -1091,9 +1109,12 @@ alloc_new_skb:
 				 (fraglen + alloc_extra < SKB_MAX_ALLOC ||
 				  !(rt->dst.dev->features & NETIF_F_SG)))
 				alloclen = fraglen;
-			else {
+			else if (!zc) {
 				alloclen = min_t(int, fraglen, MAX_HEADER);
 				pagedlen = fraglen - alloclen;
+			} else {
+				alloclen = fragheaderlen + transhdrlen;
+				pagedlen = datalen - transhdrlen;
 			}
 
 			alloclen += alloc_extra;
@@ -1188,13 +1209,14 @@ alloc_new_skb:
 				err = -EFAULT;
 				goto error;
 			}
-		} else if (!uarg || !uarg->zerocopy) {
+		} else if (!zc) {
 			int i = skb_shinfo(skb)->nr_frags;
 
 			err = -ENOMEM;
 			if (!sk_page_frag_refill(sk, pfrag))
 				goto error;
 
+			skb_zcopy_downgrade_managed(skb);
 			if (!skb_can_coalesce(skb, i, pfrag->page,
 					      pfrag->offset)) {
 				err = -EMSGSIZE;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 766881775abb..a628daa51113 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1203,17 +1203,23 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 
 	flags = msg->msg_flags;
 
-	if (flags & MSG_ZEROCOPY && size && sock_flag(sk, SOCK_ZEROCOPY)) {
+	if ((flags & MSG_ZEROCOPY) && size) {
 		skb = tcp_write_queue_tail(sk);
-		uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb));
-		if (!uarg) {
-			err = -ENOBUFS;
-			goto out_err;
-		}
 
-		zc = sk->sk_route_caps & NETIF_F_SG;
-		if (!zc)
-			uarg->zerocopy = 0;
+		if (msg->msg_ubuf) {
+			uarg = msg->msg_ubuf;
+			net_zcopy_get(uarg);
+			zc = sk->sk_route_caps & NETIF_F_SG;
+		} else if (sock_flag(sk, SOCK_ZEROCOPY)) {
+			uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb));
+			if (!uarg) {
+				err = -ENOBUFS;
+				goto out_err;
+			}
+			zc = sk->sk_route_caps & NETIF_F_SG;
+			if (!zc)
+				uarg->zerocopy = 0;
+		}
 	}
 
 	if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) &&
@@ -1336,8 +1342,13 @@ new_segment:
 
 			copy = min_t(int, copy, pfrag->size - pfrag->offset);
 
-			if (tcp_downgrade_zcopy_pure(sk, skb) ||
-			    !sk_wmem_schedule(sk, copy))
+			if (unlikely(skb_zcopy_pure(skb) || skb_zcopy_managed(skb))) {
+				if (tcp_downgrade_zcopy_pure(sk, skb))
+					goto wait_for_space;
+				skb_zcopy_downgrade_managed(skb);
+			}
+
+			if (!sk_wmem_schedule(sk, copy))
 				goto wait_for_space;
 
 			err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb,
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 77e3f5970ce4..897ca4f9b791 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1464,6 +1464,7 @@ static int __ip6_append_data(struct sock *sk,
 	int copy;
 	int err;
 	int offset = 0;
+	bool zc = false;
 	u32 tskey = 0;
 	struct rt6_info *rt = (struct rt6_info *)cork->dst;
 	struct ipv6_txoptions *opt = v6_cork->opt;
@@ -1541,17 +1542,35 @@ emsgsize:
 	    rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM))
 		csummode = CHECKSUM_PARTIAL;
 
-	if (flags & MSG_ZEROCOPY && length && sock_flag(sk, SOCK_ZEROCOPY)) {
-		uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb));
-		if (!uarg)
-			return -ENOBUFS;
-		extra_uref = !skb_zcopy(skb);	/* only ref on new uarg */
-		if (rt->dst.dev->features & NETIF_F_SG &&
-		    csummode == CHECKSUM_PARTIAL) {
-			paged = true;
-		} else {
-			uarg->zerocopy = 0;
-			skb_zcopy_set(skb, uarg, &extra_uref);
+	if ((flags & MSG_ZEROCOPY) && length) {
+		struct msghdr *msg = from;
+
+		if (getfrag == ip_generic_getfrag && msg->msg_ubuf) {
+			if (skb_zcopy(skb) && msg->msg_ubuf != skb_zcopy(skb))
+				return -EINVAL;
+
+			/* Leave uarg NULL if can't zerocopy, callers should
+			 * be able to handle it.
+			 */
+			if ((rt->dst.dev->features & NETIF_F_SG) &&
+			    csummode == CHECKSUM_PARTIAL) {
+				paged = true;
+				zc = true;
+				uarg = msg->msg_ubuf;
+			}
+		} else if (sock_flag(sk, SOCK_ZEROCOPY)) {
+			uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb));
+			if (!uarg)
+				return -ENOBUFS;
+			extra_uref = !skb_zcopy(skb);	/* only ref on new uarg */
+			if (rt->dst.dev->features & NETIF_F_SG &&
+			    csummode == CHECKSUM_PARTIAL) {
+				paged = true;
+				zc = true;
+			} else {
+				uarg->zerocopy = 0;
+				skb_zcopy_set(skb, uarg, &extra_uref);
+			}
 		}
 	}
 
@@ -1630,9 +1649,12 @@ alloc_new_skb:
 				 (fraglen + alloc_extra < SKB_MAX_ALLOC ||
 				  !(rt->dst.dev->features & NETIF_F_SG)))
 				alloclen = fraglen;
-			else {
+			else if (!zc) {
 				alloclen = min_t(int, fraglen, MAX_HEADER);
 				pagedlen = fraglen - alloclen;
+			} else {
+				alloclen = fragheaderlen + transhdrlen;
+				pagedlen = datalen - transhdrlen;
 			}
 			alloclen += alloc_extra;
 
@@ -1742,13 +1764,14 @@ alloc_new_skb:
 				err = -EFAULT;
 				goto error;
 			}
-		} else if (!uarg || !uarg->zerocopy) {
+		} else if (!zc) {
 			int i = skb_shinfo(skb)->nr_frags;
 
 			err = -ENOMEM;
 			if (!sk_page_frag_refill(sk, pfrag))
 				goto error;
 
+			skb_zcopy_downgrade_managed(skb);
 			if (!skb_can_coalesce(skb, i, pfrag->page,
 					      pfrag->offset)) {
 				err = -EMSGSIZE;
diff --git a/net/socket.c b/net/socket.c
index 843545c21ec2..ec9ef13a702e 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2106,6 +2106,7 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags,
 	msg.msg_control = NULL;
 	msg.msg_controllen = 0;
 	msg.msg_namelen = 0;
+	msg.msg_ubuf = NULL;
 	if (addr) {
 		err = move_addr_to_kernel(addr, addr_len, &address);
 		if (err < 0)
@@ -2400,6 +2401,7 @@ int __copy_msghdr(struct msghdr *kmsg,
 		return -EMSGSIZE;
 
 	kmsg->msg_iocb = NULL;
+	kmsg->msg_ubuf = NULL;
 	return 0;
 }