Merge branch 'for-davem' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

More iov_iter work from Al Viro.

Signed-off-by: David S. Miller <davem@davemloft.net>

crypto/af_alg.c

@@ -338,49 +338,31 @@ static const struct net_proto_family alg_family = {
 	.owner	=	THIS_MODULE,
 };
 
-int af_alg_make_sg(struct af_alg_sgl *sgl, void __user *addr, int len,
-		   int write)
+int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len)
 {
-	unsigned long from = (unsigned long)addr;
-	unsigned long npages;
-	unsigned off;
-	int err;
-	int i;
-
-	err = -EFAULT;
-	if (!access_ok(write ? VERIFY_READ : VERIFY_WRITE, addr, len))
-		goto out;
-
-	off = from & ~PAGE_MASK;
-	npages = (off + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	if (npages > ALG_MAX_PAGES)
-		npages = ALG_MAX_PAGES;
+	size_t off;
+	ssize_t n;
+	int npages, i;
 
-	err = get_user_pages_fast(from, npages, write, sgl->pages);
-	if (err < 0)
-		goto out;
+	n = iov_iter_get_pages(iter, sgl->pages, len, ALG_MAX_PAGES, &off);
+	if (n < 0)
+		return n;
 
-	npages = err;
-	err = -EINVAL;
+	npages = PAGE_ALIGN(off + n);
 	if (WARN_ON(npages == 0))
-		goto out;
-
-	err = 0;
+		return -EINVAL;
 
 	sg_init_table(sgl->sg, npages);
 
-	for (i = 0; i < npages; i++) {
+	for (i = 0, len = n; i < npages; i++) {
 		int plen = min_t(int, len, PAGE_SIZE - off);
 
 		sg_set_page(sgl->sg + i, sgl->pages[i], plen, off);
 
 		off = 0;
 		len -= plen;
-		err += plen;
 	}
-
-out:
-	return err;
+	return n;
 }
 EXPORT_SYMBOL_GPL(af_alg_make_sg);
 

crypto/algif_hash.c

@@ -41,8 +41,6 @@ static int hash_sendmsg(struct kiocb *unused, struct socket *sock,
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
 	struct hash_ctx *ctx = ask->private;
-	unsigned long iovlen;
-	const struct iovec *iov;
 	long copied = 0;
 	int err;
 
@@ -58,37 +56,28 @@ static int hash_sendmsg(struct kiocb *unused, struct socket *sock,
 
 	ctx->more = 0;
 
-	for (iov = msg->msg_iter.iov, iovlen = msg->msg_iter.nr_segs; iovlen > 0;
-	     iovlen--, iov++) {
-		unsigned long seglen = iov->iov_len;
-		char __user *from = iov->iov_base;
+	while (iov_iter_count(&msg->msg_iter)) {
+		int len = iov_iter_count(&msg->msg_iter);
 
-		while (seglen) {
-			int len = min_t(unsigned long, seglen, limit);
-			int newlen;
+		if (len > limit)
+			len = limit;
 
-			newlen = af_alg_make_sg(&ctx->sgl, from, len, 0);
-			if (newlen < 0) {
-				err = copied ? 0 : newlen;
-				goto unlock;
-			}
-
-			ahash_request_set_crypt(&ctx->req, ctx->sgl.sg, NULL,
-						newlen);
-
-			err = af_alg_wait_for_completion(
-				crypto_ahash_update(&ctx->req),
-				&ctx->completion);
+		len = af_alg_make_sg(&ctx->sgl, &msg->msg_iter, len);
+		if (len < 0) {
+			err = copied ? 0 : len;
+			goto unlock;
+		}
 
-			af_alg_free_sg(&ctx->sgl);
+		ahash_request_set_crypt(&ctx->req, ctx->sgl.sg, NULL, len);
 
-			if (err)
-				goto unlock;
+		err = af_alg_wait_for_completion(crypto_ahash_update(&ctx->req),
+						 &ctx->completion);
+		af_alg_free_sg(&ctx->sgl);
+		if (err)
+			goto unlock;
 
-			seglen -= newlen;
-			from += newlen;
-			copied += newlen;
-		}
+		copied += len;
+		iov_iter_advance(&msg->msg_iter, len);
 	}
 
 	err = 0;

crypto/algif_skcipher.c

@@ -426,67 +426,59 @@ static int skcipher_recvmsg(struct kiocb *unused, struct socket *sock,
 		&ctx->req));
 	struct skcipher_sg_list *sgl;
 	struct scatterlist *sg;
-	unsigned long iovlen;
-	const struct iovec *iov;
 	int err = -EAGAIN;
 	int used;
 	long copied = 0;
 
 	lock_sock(sk);
-	for (iov = msg->msg_iter.iov, iovlen = msg->msg_iter.nr_segs; iovlen > 0;
-	     iovlen--, iov++) {
-		unsigned long seglen = iov->iov_len;
-		char __user *from = iov->iov_base;
-
-		while (seglen) {
-			sgl = list_first_entry(&ctx->tsgl,
-					       struct skcipher_sg_list, list);
-			sg = sgl->sg;
-
-			while (!sg->length)
-				sg++;
-
-			if (!ctx->used) {
-				err = skcipher_wait_for_data(sk, flags);
-				if (err)
-					goto unlock;
-			}
+	while (iov_iter_count(&msg->msg_iter)) {
+		sgl = list_first_entry(&ctx->tsgl,
+				       struct skcipher_sg_list, list);
+		sg = sgl->sg;
 
-			used = min_t(unsigned long, ctx->used, seglen);
+		while (!sg->length)
+			sg++;
 
-			used = af_alg_make_sg(&ctx->rsgl, from, used, 1);
-			err = used;
-			if (err < 0)
+		used = ctx->used;
+		if (!used) {
+			err = skcipher_wait_for_data(sk, flags);
+			if (err)
 				goto unlock;
+		}
+
+		used = min_t(unsigned long, used, iov_iter_count(&msg->msg_iter));
+
+		used = af_alg_make_sg(&ctx->rsgl, &msg->msg_iter, used);
+		err = used;
+		if (err < 0)
+			goto unlock;
 
-			if (ctx->more || used < ctx->used)
-				used -= used % bs;
+		if (ctx->more || used < ctx->used)
+			used -= used % bs;
 
-			err = -EINVAL;
-			if (!used)
-				goto free;
+		err = -EINVAL;
+		if (!used)
+			goto free;
 
-			ablkcipher_request_set_crypt(&ctx->req, sg,
-						     ctx->rsgl.sg, used,
-						     ctx->iv);
+		ablkcipher_request_set_crypt(&ctx->req, sg,
+					     ctx->rsgl.sg, used,
+					     ctx->iv);
 
-			err = af_alg_wait_for_completion(
+		err = af_alg_wait_for_completion(
 				ctx->enc ?
 					crypto_ablkcipher_encrypt(&ctx->req) :
 					crypto_ablkcipher_decrypt(&ctx->req),
 				&ctx->completion);
 
 free:
-			af_alg_free_sg(&ctx->rsgl);
+		af_alg_free_sg(&ctx->rsgl);
 
-			if (err)
-				goto unlock;
+		if (err)
+			goto unlock;
 
-			copied += used;
-			from += used;
-			seglen -= used;
-			skcipher_pull_sgl(sk, used);
-		}
+		copied += used;
+		skcipher_pull_sgl(sk, used);
+		iov_iter_advance(&msg->msg_iter, used);
 	}
 
 	err = 0;

drivers/misc/vmw_vmci/vmci_queue_pair.c

@@ -370,12 +370,12 @@ static int __qp_memcpy_to_queue(struct vmci_queue *queue,
 			to_copy = size - bytes_copied;
 
 		if (is_iovec) {
-			struct iovec *iov = (struct iovec *)src;
+			struct msghdr *msg = (struct msghdr *)src;
 			int err;
 
 			/* The iovec will track bytes_copied internally. */
-			err = memcpy_fromiovec((u8 *)va + page_offset,
-					       iov, to_copy);
+			err = memcpy_from_msg((u8 *)va + page_offset,
+					      msg, to_copy);
 			if (err != 0) {
 				if (kernel_if->host)
 					kunmap(kernel_if->u.h.page[page_index]);
@@ -580,7 +580,7 @@ static int qp_memcpy_from_queue(void *dest,
  */
 static int qp_memcpy_to_queue_iov(struct vmci_queue *queue,
 				  u64 queue_offset,
-				  const void *src,
+				  const void *msg,
 				  size_t src_offset, size_t size)
 {
 
@@ -588,7 +588,7 @@ static int qp_memcpy_to_queue_iov(struct vmci_queue *queue,
 	 * We ignore src_offset because src is really a struct iovec * and will
 	 * maintain offset internally.
 	 */
-	return __qp_memcpy_to_queue(queue, queue_offset, src, size, true);
+	return __qp_memcpy_to_queue(queue, queue_offset, msg, size, true);
 }
 
 /*
@@ -3223,13 +3223,13 @@ EXPORT_SYMBOL_GPL(vmci_qpair_peek);
  * of bytes enqueued or < 0 on error.
  */
 ssize_t vmci_qpair_enquev(struct vmci_qp *qpair,
-			  void *iov,
+			  struct msghdr *msg,
 			  size_t iov_size,
 			  int buf_type)
 {
 	ssize_t result;
 
-	if (!qpair || !iov)
+	if (!qpair)
 		return VMCI_ERROR_INVALID_ARGS;
 
 	qp_lock(qpair);
@@ -3238,7 +3238,7 @@ ssize_t vmci_qpair_enquev(struct vmci_qp *qpair,
 		result = qp_enqueue_locked(qpair->produce_q,
 					   qpair->consume_q,
 					   qpair->produce_q_size,
-					   iov, iov_size,
+					   msg, iov_size,
 					   qp_memcpy_to_queue_iov);
 
 		if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY &&

drivers/vhost/net.c

@@ -84,10 +84,6 @@ struct vhost_net_ubuf_ref {
 
 struct vhost_net_virtqueue {
 	struct vhost_virtqueue vq;
-	/* hdr is used to store the virtio header.
-	 * Since each iovec has >= 1 byte length, we never need more than
-	 * header length entries to store the header. */
-	struct iovec hdr[sizeof(struct virtio_net_hdr_mrg_rxbuf)];
 	size_t vhost_hlen;
 	size_t sock_hlen;
 	/* vhost zerocopy support fields below: */
@@ -235,44 +231,6 @@ static bool vhost_sock_zcopy(struct socket *sock)
 		sock_flag(sock->sk, SOCK_ZEROCOPY);
 }
 
-/* Pop first len bytes from iovec. Return number of segments used. */
-static int move_iovec_hdr(struct iovec *from, struct iovec *to,
-			  size_t len, int iov_count)
-{
-	int seg = 0;
-	size_t size;
-
-	while (len && seg < iov_count) {
-		size = min(from->iov_len, len);
-		to->iov_base = from->iov_base;
-		to->iov_len = size;
-		from->iov_len -= size;
-		from->iov_base += size;
-		len -= size;
-		++from;
-		++to;
-		++seg;
-	}
-	return seg;
-}
-/* Copy iovec entries for len bytes from iovec. */
-static void copy_iovec_hdr(const struct iovec *from, struct iovec *to,
-			   size_t len, int iovcount)
-{
-	int seg = 0;
-	size_t size;
-
-	while (len && seg < iovcount) {
-		size = min(from->iov_len, len);
-		to->iov_base = from->iov_base;
-		to->iov_len = size;
-		len -= size;
-		++from;
-		++to;
-		++seg;
-	}
-}
-
 /* In case of DMA done not in order in lower device driver for some reason.
  * upend_idx is used to track end of used idx, done_idx is used to track head
  * of used idx. Once lower device DMA done contiguously, we will signal KVM
@@ -336,7 +294,7 @@ static void handle_tx(struct vhost_net *net)
 {
 	struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
 	struct vhost_virtqueue *vq = &nvq->vq;
-	unsigned out, in, s;
+	unsigned out, in;
 	int head;
 	struct msghdr msg = {
 		.msg_name = NULL,
@@ -395,16 +353,17 @@ static void handle_tx(struct vhost_net *net)
 			break;
 		}
 		/* Skip header. TODO: support TSO. */
-		s = move_iovec_hdr(vq->iov, nvq->hdr, hdr_size, out);
 		len = iov_length(vq->iov, out);
 		iov_iter_init(&msg.msg_iter, WRITE, vq->iov, out, len);
+		iov_iter_advance(&msg.msg_iter, hdr_size);
 		/* Sanity check */
-		if (!len) {
+		if (!iov_iter_count(&msg.msg_iter)) {
 			vq_err(vq, "Unexpected header len for TX: "
 			       "%zd expected %zd\n",
-			       iov_length(nvq->hdr, s), hdr_size);
+			       len, hdr_size);
 			break;
 		}
+		len = iov_iter_count(&msg.msg_iter);
 
 		zcopy_used = zcopy && len >= VHOST_GOODCOPY_LEN
 				   && (nvq->upend_idx + 1) % UIO_MAXIOV !=
@@ -569,9 +528,9 @@ static void handle_rx(struct vhost_net *net)
 		.msg_controllen = 0,
 		.msg_flags = MSG_DONTWAIT,
 	};
-	struct virtio_net_hdr_mrg_rxbuf hdr = {
-		.hdr.flags = 0,
-		.hdr.gso_type = VIRTIO_NET_HDR_GSO_NONE
+	struct virtio_net_hdr hdr = {
+		.flags = 0,
+		.gso_type = VIRTIO_NET_HDR_GSO_NONE
 	};
 	size_t total_len = 0;
 	int err, mergeable;
@@ -579,6 +538,7 @@ static void handle_rx(struct vhost_net *net)
 	size_t vhost_hlen, sock_hlen;
 	size_t vhost_len, sock_len;
 	struct socket *sock;
+	struct iov_iter fixup;
 
 	mutex_lock(&vq->mutex);
 	sock = vq->private_data;
@@ -623,14 +583,19 @@ static void handle_rx(struct vhost_net *net)
 			break;
 		}
 		/* We don't need to be notified again. */
-		if (unlikely((vhost_hlen)))
-			/* Skip header. TODO: support TSO. */
-			move_iovec_hdr(vq->iov, nvq->hdr, vhost_hlen, in);
-		else
-			/* Copy the header for use in VIRTIO_NET_F_MRG_RXBUF:
-			 * needed because recvmsg can modify msg_iov. */
-			copy_iovec_hdr(vq->iov, nvq->hdr, sock_hlen, in);
-		iov_iter_init(&msg.msg_iter, READ, vq->iov, in, sock_len);
+		iov_iter_init(&msg.msg_iter, READ, vq->iov, in, vhost_len);
+		fixup = msg.msg_iter;
+		if (unlikely((vhost_hlen))) {
+			/* We will supply the header ourselves
+			 * TODO: support TSO.
+			 */
+			iov_iter_advance(&msg.msg_iter, vhost_hlen);
+		} else {
+			/* It'll come from socket; we'll need to patch
+			 * ->num_buffers over if VIRTIO_NET_F_MRG_RXBUF
+			 */
+			iov_iter_advance(&fixup, sizeof(hdr));
+		}
 		err = sock->ops->recvmsg(NULL, sock, &msg,
 					 sock_len, MSG_DONTWAIT | MSG_TRUNC);
 		/* Userspace might have consumed the packet meanwhile:
@@ -642,18 +607,18 @@ static void handle_rx(struct vhost_net *net)
 			vhost_discard_vq_desc(vq, headcount);
 			continue;
 		}
+		/* Supply virtio_net_hdr if VHOST_NET_F_VIRTIO_NET_HDR */
 		if (unlikely(vhost_hlen) &&
-		    memcpy_toiovecend(nvq->hdr, (unsigned char *)&hdr, 0,
-				      vhost_hlen)) {
+		    copy_to_iter(&hdr, sizeof(hdr), &fixup) != sizeof(hdr)) {
 			vq_err(vq, "Unable to write vnet_hdr at addr %p\n",
 			       vq->iov->iov_base);
 			break;
 		}
-		/* TODO: Should check and handle checksum. */
+		/* Supply (or replace) ->num_buffers if VIRTIO_NET_F_MRG_RXBUF
+		 * TODO: Should check and handle checksum.
+		 */
 		if (likely(mergeable) &&
-		    memcpy_toiovecend(nvq->hdr, (unsigned char *)&headcount,
-				      offsetof(typeof(hdr), num_buffers),
-				      sizeof hdr.num_buffers)) {
+		    copy_to_iter(&headcount, 2, &fixup) != 2) {
 			vq_err(vq, "Failed num_buffers write");
 			vhost_discard_vq_desc(vq, headcount);
 			break;

drivers/vhost/scsi.c

@@ -1079,7 +1079,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 			       req_size, vq->iov[0].iov_len);
 			break;
 		}
-		ret = memcpy_fromiovecend(req, &vq->iov[0], 0, req_size);
+		ret = copy_from_user(req, vq->iov[0].iov_base, req_size);
 		if (unlikely(ret)) {
 			vq_err(vq, "Faulted on virtio_scsi_cmd_req\n");
 			break;

drivers/vhost/vhost.c

@@ -1125,6 +1125,7 @@ static int get_indirect(struct vhost_virtqueue *vq,
 	struct vring_desc desc;
 	unsigned int i = 0, count, found = 0;
 	u32 len = vhost32_to_cpu(vq, indirect->len);
+	struct iov_iter from;
 	int ret;
 
 	/* Sanity check */
@@ -1142,6 +1143,7 @@ static int get_indirect(struct vhost_virtqueue *vq,
 		vq_err(vq, "Translation failure %d in indirect.\n", ret);
 		return ret;
 	}
+	iov_iter_init(&from, READ, vq->indirect, ret, len);
 
 	/* We will use the result as an address to read from, so most
 	 * architectures only need a compiler barrier here. */
@@ -1164,8 +1166,8 @@ static int get_indirect(struct vhost_virtqueue *vq,
 			       i, count);
 			return -EINVAL;
 		}
-		if (unlikely(memcpy_fromiovec((unsigned char *)&desc,
-					      vq->indirect, sizeof desc))) {
+		if (unlikely(copy_from_iter(&desc, sizeof(desc), &from) !=
+			     sizeof(desc))) {
 			vq_err(vq, "Failed indirect descriptor: idx %d, %zx\n",
 			       i, (size_t)vhost64_to_cpu(vq, indirect->addr) + i * sizeof desc);
 			return -EINVAL;

fs/afs/rxrpc.c

@@ -306,8 +306,8 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg,
 
 			_debug("- range %u-%u%s",
 			       offset, to, msg->msg_flags ? " [more]" : "");
-			iov_iter_init(&msg->msg_iter, WRITE,
-				      (struct iovec *) iov, 1, to - offset);
+			iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC,
+				      iov, 1, to - offset);
 
 			/* have to change the state *before* sending the last
 			 * packet as RxRPC might give us the reply before it
@@ -384,7 +384,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
 
 	msg.msg_name		= NULL;
 	msg.msg_namelen		= 0;
-	iov_iter_init(&msg.msg_iter, WRITE, (struct iovec *)iov, 1,
+	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iov, 1,
 		      call->request_size);
 	msg.msg_control		= NULL;
 	msg.msg_controllen	= 0;
@@ -770,7 +770,7 @@ static int afs_deliver_cm_op_id(struct afs_call *call, struct sk_buff *skb,
 void afs_send_empty_reply(struct afs_call *call)
 {
 	struct msghdr msg;
-	struct iovec iov[1];
+	struct kvec iov[1];
 
 	_enter("");
 
@@ -778,7 +778,7 @@ void afs_send_empty_reply(struct afs_call *call)
 	iov[0].iov_len		= 0;
 	msg.msg_name		= NULL;
 	msg.msg_namelen		= 0;
-	iov_iter_init(&msg.msg_iter, WRITE, iov, 0, 0);	/* WTF? */
+	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iov, 0, 0);	/* WTF? */
 	msg.msg_control		= NULL;
 	msg.msg_controllen	= 0;
 	msg.msg_flags		= 0;
@@ -805,7 +805,7 @@ void afs_send_empty_reply(struct afs_call *call)
 void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len)
 {
 	struct msghdr msg;
-	struct iovec iov[1];
+	struct kvec iov[1];
 	int n;
 
 	_enter("");
@@ -814,7 +814,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len)
 	iov[0].iov_len		= len;
 	msg.msg_name		= NULL;
 	msg.msg_namelen		= 0;
-	iov_iter_init(&msg.msg_iter, WRITE, iov, 1, len);
+	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iov, 1, len);
 	msg.msg_control		= NULL;
 	msg.msg_controllen	= 0;
 	msg.msg_flags		= 0;

include/crypto/if_alg.h

@@ -67,8 +67,7 @@ int af_alg_unregister_type(const struct af_alg_type *type);
 int af_alg_release(struct socket *sock);
 int af_alg_accept(struct sock *sk, struct socket *newsock);
 
-int af_alg_make_sg(struct af_alg_sgl *sgl, void __user *addr, int len,
-		   int write);
+int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len);
 void af_alg_free_sg(struct af_alg_sgl *sgl);
 
 int af_alg_cmsg_send(struct msghdr *msg, struct af_alg_control *con);

include/linux/skbuff.h

@@ -2487,19 +2487,18 @@ static inline int skb_put_padto(struct sk_buff *skb, unsigned int len)
 }
 
 static inline int skb_add_data(struct sk_buff *skb,
-			       char __user *from, int copy)
+			       struct iov_iter *from, int copy)
 {
 	const int off = skb->len;
 
 	if (skb->ip_summed == CHECKSUM_NONE) {
-		int err = 0;
-		__wsum csum = csum_and_copy_from_user(from, skb_put(skb, copy),
-							    copy, 0, &err);
-		if (!err) {
+		__wsum csum = 0;
+		if (csum_and_copy_from_iter(skb_put(skb, copy), copy,
+					    &csum, from) == copy) {
 			skb->csum = csum_block_add(skb->csum, csum, off);
 			return 0;
 		}
-	} else if (!copy_from_user(skb_put(skb, copy), from, copy))
+	} else if (copy_from_iter(skb_put(skb, copy), copy, from) == copy)
 		return 0;
 
 	__skb_trim(skb, off);
@@ -2696,8 +2695,7 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci);
 
 static inline int memcpy_from_msg(void *data, struct msghdr *msg, int len)
 {
-	/* XXX: stripping const */
-	return memcpy_fromiovec(data, (struct iovec *)msg->msg_iter.iov, len);
+	return copy_from_iter(data, len, &msg->msg_iter) == len ? 0 : -EFAULT;
 }
 
 static inline int memcpy_to_msg(struct msghdr *msg, void *data, int len)

include/linux/socket.h

@@ -318,13 +318,6 @@ struct ucred {
 /* IPX options */
 #define IPX_TYPE	1
 
-extern int csum_partial_copy_fromiovecend(unsigned char *kdata, 
-					  struct iovec *iov, 
-					  int offset, 
-					  unsigned int len, __wsum *csump);
-extern unsigned long iov_pages(const struct iovec *iov, int offset,
-			       unsigned long nr_segs);
-
 extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr);
 extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data);
 

include/linux/uio.h

@@ -135,10 +135,4 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count)
 size_t csum_and_copy_to_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
 size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
 
-int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len);
-int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
-			int offset, int len);
-int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata,
-		      int offset, int len);
-
 #endif

include/linux/vmw_vmci_api.h

@@ -74,7 +74,7 @@ ssize_t vmci_qpair_dequeue(struct vmci_qp *qpair,
 ssize_t vmci_qpair_peek(struct vmci_qp *qpair, void *buf, size_t buf_size,
 			int mode);
 ssize_t vmci_qpair_enquev(struct vmci_qp *qpair,
-			  void *iov, size_t iov_size, int mode);
+			  struct msghdr *msg, size_t iov_size, int mode);
 ssize_t vmci_qpair_dequev(struct vmci_qp *qpair,
 			  struct msghdr *msg, size_t iov_size, int mode);
 ssize_t vmci_qpair_peekv(struct vmci_qp *qpair, struct msghdr *msg, size_t iov_size,

include/net/ping.h

@@ -59,7 +59,7 @@ extern struct pingv6_ops pingv6_ops;
 
 struct pingfakehdr {
 	struct icmphdr icmph;
-	struct iovec *iov;
+	struct msghdr *msg;
 	sa_family_t family;
 	__wsum wcheck;
 };

include/net/sock.h

@@ -1803,27 +1803,25 @@ static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags)
 }
 
 static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb,
-					   char __user *from, char *to,
+					   struct iov_iter *from, char *to,
 					   int copy, int offset)
 {
 	if (skb->ip_summed == CHECKSUM_NONE) {
-		int err = 0;
-		__wsum csum = csum_and_copy_from_user(from, to, copy, 0, &err);
-		if (err)
-			return err;
+		__wsum csum = 0;
+		if (csum_and_copy_from_iter(to, copy, &csum, from) != copy)
+			return -EFAULT;
 		skb->csum = csum_block_add(skb->csum, csum, offset);
 	} else if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) {
-		if (!access_ok(VERIFY_READ, from, copy) ||
-		    __copy_from_user_nocache(to, from, copy))
+		if (copy_from_iter_nocache(to, copy, from) != copy)
 			return -EFAULT;
-	} else if (copy_from_user(to, from, copy))
+	} else if (copy_from_iter(to, copy, from) != copy)
 		return -EFAULT;
 
 	return 0;
 }
 
 static inline int skb_add_data_nocache(struct sock *sk, struct sk_buff *skb,
-				       char __user *from, int copy)
+				       struct iov_iter *from, int copy)
 {
 	int err, offset = skb->len;
 
@@ -1835,7 +1833,7 @@ static inline int skb_add_data_nocache(struct sock *sk, struct sk_buff *skb,
 	return err;
 }
 
-static inline int skb_copy_to_page_nocache(struct sock *sk, char __user *from,
+static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *from,
 					   struct sk_buff *skb,
 					   struct page *page,
 					   int off, int copy)

include/net/udplite.h

@@ -20,8 +20,7 @@ static __inline__ int udplite_getfrag(void *from, char *to, int  offset,
 				      int len, int odd, struct sk_buff *skb)
 {
 	struct msghdr *msg = from;
-	/* XXX: stripping const */
-	return memcpy_fromiovecend(to, (struct iovec *)msg->msg_iter.iov, offset, len);
+	return copy_from_iter(to, len, &msg->msg_iter) != len ? -EFAULT : 0;
 }
 
 /* Designate sk as UDP-Lite socket */

lib/Makefile

@@ -24,7 +24,7 @@ obj-y	+= lockref.o
 
 obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
 	 bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
-	 gcd.o lcm.o list_sort.o uuid.o flex_array.o iovec.o clz_ctz.o \
+	 gcd.o lcm.o list_sort.o uuid.o flex_array.o clz_ctz.o \
 	 bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o \
 	 percpu-refcount.o percpu_ida.o rhashtable.o reciprocal_div.o
 obj-y += string_helpers.o

lib/iovec.c

@@ -1,87 +0,0 @@
-#include <linux/uaccess.h>
-#include <linux/export.h>
-#include <linux/uio.h>
-
-/*
- *	Copy iovec to kernel. Returns -EFAULT on error.
- *
- *	Note: this modifies the original iovec.
- */
-
-int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len)
-{
-	while (len > 0) {
-		if (iov->iov_len) {
-			int copy = min_t(unsigned int, len, iov->iov_len);
-			if (copy_from_user(kdata, iov->iov_base, copy))
-				return -EFAULT;
-			len -= copy;
-			kdata += copy;
-			iov->iov_base += copy;
-			iov->iov_len -= copy;
-		}
-		iov++;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(memcpy_fromiovec);
-
-/*
- *	Copy kernel to iovec. Returns -EFAULT on error.
- */
-
-int memcpy_toiovecend(const struct iovec *iov, unsigned char *kdata,
-		      int offset, int len)
-{
-	int copy;
-	for (; len > 0; ++iov) {
-		/* Skip over the finished iovecs */
-		if (unlikely(offset >= iov->iov_len)) {
-			offset -= iov->iov_len;
-			continue;
-		}
-		copy = min_t(unsigned int, iov->iov_len - offset, len);
-		if (copy_to_user(iov->iov_base + offset, kdata, copy))
-			return -EFAULT;
-		offset = 0;
-		kdata += copy;
-		len -= copy;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(memcpy_toiovecend);
-
-/*
- *	Copy iovec to kernel. Returns -EFAULT on error.
- */
-
-int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
-			int offset, int len)
-{
-	/* No data? Done! */
-	if (len == 0)
-		return 0;
-
-	/* Skip over the finished iovecs */
-	while (offset >= iov->iov_len) {
-		offset -= iov->iov_len;
-		iov++;
-	}
-
-	while (len > 0) {
-		u8 __user *base = iov->iov_base + offset;
-		int copy = min_t(unsigned int, len, iov->iov_len - offset);
-
-		offset = 0;
-		if (copy_from_user(kdata, base, copy))
-			return -EFAULT;
-		len -= copy;
-		kdata += copy;
-		iov++;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(memcpy_fromiovecend);

net/core/Makefile

@@ -2,7 +2,7 @@
 # Makefile for the Linux networking core.
 #
 
-obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \
+obj-y := sock.o request_sock.o skbuff.o datagram.o stream.o scm.o \
 	 gen_stats.o gen_estimator.o net_namespace.o secure_seq.o flow_dissector.o
 
 obj-$(CONFIG_SYSCTL) += sysctl_net_core.o

net/core/iovec.c

@@ -1,137 +0,0 @@
-/*
- *	iovec manipulation routines.
- *
- *
- *		This program is free software; you can redistribute it and/or
- *		modify it under the terms of the GNU General Public License
- *		as published by the Free Software Foundation; either version
- *		2 of the License, or (at your option) any later version.
- *
- *	Fixes:
- *		Andrew Lunn	:	Errors in iovec copying.
- *		Pedro Roque	:	Added memcpy_fromiovecend and
- *					csum_..._fromiovecend.
- *		Andi Kleen	:	fixed error handling for 2.1
- *		Alexey Kuznetsov:	2.1 optimisations
- *		Andi Kleen	:	Fix csum*fromiovecend for IPv6.
- */
-
-#include <linux/errno.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/net.h>
-#include <linux/in6.h>
-#include <asm/uaccess.h>
-#include <asm/byteorder.h>
-#include <net/checksum.h>
-#include <net/sock.h>
-
-/*
- *	And now for the all-in-one: copy and checksum from a user iovec
- *	directly to a datagram
- *	Calls to csum_partial but the last must be in 32 bit chunks
- *
- *	ip_build_xmit must ensure that when fragmenting only the last
- *	call to this function will be unaligned also.
- */
-int csum_partial_copy_fromiovecend(unsigned char *kdata, struct iovec *iov,
-				 int offset, unsigned int len, __wsum *csump)
-{
-	__wsum csum = *csump;
-	int partial_cnt = 0, err = 0;
-
-	/* Skip over the finished iovecs */
-	while (offset >= iov->iov_len) {
-		offset -= iov->iov_len;
-		iov++;
-	}
-
-	while (len > 0) {
-		u8 __user *base = iov->iov_base + offset;
-		int copy = min_t(unsigned int, len, iov->iov_len - offset);
-
-		offset = 0;
-
-		/* There is a remnant from previous iov. */
-		if (partial_cnt) {
-			int par_len = 4 - partial_cnt;
-
-			/* iov component is too short ... */
-			if (par_len > copy) {
-				if (copy_from_user(kdata, base, copy))
-					goto out_fault;
-				kdata += copy;
-				base += copy;
-				partial_cnt += copy;
-				len -= copy;
-				iov++;
-				if (len)
-					continue;
-				*csump = csum_partial(kdata - partial_cnt,
-							 partial_cnt, csum);
-				goto out;
-			}
-			if (copy_from_user(kdata, base, par_len))
-				goto out_fault;
-			csum = csum_partial(kdata - partial_cnt, 4, csum);
-			kdata += par_len;
-			base  += par_len;
-			copy  -= par_len;
-			len   -= par_len;
-			partial_cnt = 0;
-		}
-
-		if (len > copy) {
-			partial_cnt = copy % 4;
-			if (partial_cnt) {
-				copy -= partial_cnt;
-				if (copy_from_user(kdata + copy, base + copy,
-						partial_cnt))
-					goto out_fault;
-			}
-		}
-
-		if (copy) {
-			csum = csum_and_copy_from_user(base, kdata, copy,
-							csum, &err);
-			if (err)
-				goto out;
-		}
-		len   -= copy + partial_cnt;
-		kdata += copy + partial_cnt;
-		iov++;
-	}
-	*csump = csum;
-out:
-	return err;
-
-out_fault:
-	err = -EFAULT;
-	goto out;
-}
-EXPORT_SYMBOL(csum_partial_copy_fromiovecend);
-
-unsigned long iov_pages(const struct iovec *iov, int offset,
-			unsigned long nr_segs)
-{
-	unsigned long seg, base;
-	int pages = 0, len, size;
-
-	while (nr_segs && (offset >= iov->iov_len)) {
-		offset -= iov->iov_len;
-		++iov;
-		--nr_segs;
-	}
-
-	for (seg = 0; seg < nr_segs; seg++) {
-		base = (unsigned long)iov[seg].iov_base + offset;
-		len = iov[seg].iov_len - offset;
-		size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
-		pages += size;
-		offset = 0;
-	}
-
-	return pages;
-}
-EXPORT_SYMBOL(iov_pages);

net/ipv4/ip_output.c

@@ -755,13 +755,11 @@ ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk
 	struct msghdr *msg = from;
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		/* XXX: stripping const */
-		if (memcpy_fromiovecend(to, (struct iovec *)msg->msg_iter.iov, offset, len) < 0)
+		if (copy_from_iter(to, len, &msg->msg_iter) != len)
 			return -EFAULT;
 	} else {
 		__wsum csum = 0;
-		/* XXX: stripping const */
-		if (csum_partial_copy_fromiovecend(to, (struct iovec *)msg->msg_iter.iov, offset, len, &csum) < 0)
+		if (csum_and_copy_from_iter(to, len, &csum, &msg->msg_iter) != len)
 			return -EFAULT;
 		skb->csum = csum_block_add(skb->csum, csum, odd);
 	}

net/ipv4/ping.c

@@ -599,18 +599,18 @@ int ping_getfrag(void *from, char *to,
 	struct pingfakehdr *pfh = (struct pingfakehdr *)from;
 
 	if (offset == 0) {
-		if (fraglen < sizeof(struct icmphdr))
+		fraglen -= sizeof(struct icmphdr);
+		if (fraglen < 0)
 			BUG();
-		if (csum_partial_copy_fromiovecend(to + sizeof(struct icmphdr),
-			    pfh->iov, 0, fraglen - sizeof(struct icmphdr),
-			    &pfh->wcheck))
+		if (csum_and_copy_from_iter(to + sizeof(struct icmphdr),
+			    fraglen, &pfh->wcheck,
+			    &pfh->msg->msg_iter) != fraglen)
 			return -EFAULT;
 	} else if (offset < sizeof(struct icmphdr)) {
 			BUG();
 	} else {
-		if (csum_partial_copy_fromiovecend
-				(to, pfh->iov, offset - sizeof(struct icmphdr),
-				 fraglen, &pfh->wcheck))
+		if (csum_and_copy_from_iter(to, fraglen, &pfh->wcheck,
+					    &pfh->msg->msg_iter) != fraglen)
 			return -EFAULT;
 	}
 
@@ -811,8 +811,7 @@ back_from_confirm:
 	pfh.icmph.checksum = 0;
 	pfh.icmph.un.echo.id = inet->inet_sport;
 	pfh.icmph.un.echo.sequence = user_icmph.un.echo.sequence;
-	/* XXX: stripping const */
-	pfh.iov = (struct iovec *)msg->msg_iter.iov;
+	pfh.msg = msg;
 	pfh.wcheck = 0;
 	pfh.family = AF_INET;
 

net/ipv4/raw.c

@@ -337,7 +337,7 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb)
 }
 
 static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
-			   void *from, size_t length,
+			   struct msghdr *msg, size_t length,
 			   struct rtable **rtp,
 			   unsigned int flags)
 {
@@ -382,7 +382,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 
 	skb->transport_header = skb->network_header;
 	err = -EFAULT;
-	if (memcpy_fromiovecend((void *)iph, from, 0, length))
+	if (memcpy_from_msg(iph, msg, length))
 		goto error_free;
 
 	iphlen = iph->ihl * 4;
@@ -625,8 +625,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 back_from_confirm:
 
 	if (inet->hdrincl)
-		/* XXX: stripping const */
-		err = raw_send_hdrinc(sk, &fl4, (struct iovec *)msg->msg_iter.iov, len,
+		err = raw_send_hdrinc(sk, &fl4, msg, len,
 				      &rt, msg->msg_flags);
 
 	 else {

net/ipv4/tcp.c

@@ -1067,11 +1067,10 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		size_t size)
 {
-	const struct iovec *iov;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
-	int iovlen, flags, err, copied = 0;
-	int mss_now = 0, size_goal, copied_syn = 0, offset = 0;
+	int flags, err, copied = 0;
+	int mss_now = 0, size_goal, copied_syn = 0;
 	bool sg;
 	long timeo;
 
@@ -1084,7 +1083,6 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			goto out;
 		else if (err)
 			goto out_err;
-		offset = copied_syn;
 	}
 
 	timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
@@ -1118,8 +1116,6 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	mss_now = tcp_send_mss(sk, &size_goal, flags);
 
 	/* Ok commence sending. */
-	iovlen = msg->msg_iter.nr_segs;
-	iov = msg->msg_iter.iov;
 	copied = 0;
 
 	err = -EPIPE;
@@ -1128,151 +1124,134 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 	sg = !!(sk->sk_route_caps & NETIF_F_SG);
 
-	while (--iovlen >= 0) {
-		size_t seglen = iov->iov_len;
-		unsigned char __user *from = iov->iov_base;
+	while (iov_iter_count(&msg->msg_iter)) {
+		int copy = 0;
+		int max = size_goal;
 
-		iov++;
-		if (unlikely(offset > 0)) {  /* Skip bytes copied in SYN */
-			if (offset >= seglen) {
-				offset -= seglen;
-				continue;
-			}
-			seglen -= offset;
-			from += offset;
-			offset = 0;
+		skb = tcp_write_queue_tail(sk);
+		if (tcp_send_head(sk)) {
+			if (skb->ip_summed == CHECKSUM_NONE)
+				max = mss_now;
+			copy = max - skb->len;
 		}
 
-		while (seglen > 0) {
-			int copy = 0;
-			int max = size_goal;
-
-			skb = tcp_write_queue_tail(sk);
-			if (tcp_send_head(sk)) {
-				if (skb->ip_summed == CHECKSUM_NONE)
-					max = mss_now;
-				copy = max - skb->len;
-			}
-
-			if (copy <= 0) {
+		if (copy <= 0) {
 new_segment:
-				/* Allocate new segment. If the interface is SG,
-				 * allocate skb fitting to single page.
-				 */
-				if (!sk_stream_memory_free(sk))
-					goto wait_for_sndbuf;
+			/* Allocate new segment. If the interface is SG,
+			 * allocate skb fitting to single page.
+			 */
+			if (!sk_stream_memory_free(sk))
+				goto wait_for_sndbuf;
 
-				skb = sk_stream_alloc_skb(sk,
-							  select_size(sk, sg),
-							  sk->sk_allocation);
-				if (!skb)
-					goto wait_for_memory;
+			skb = sk_stream_alloc_skb(sk,
+						  select_size(sk, sg),
+						  sk->sk_allocation);
+			if (!skb)
+				goto wait_for_memory;
 
-				/*
-				 * Check whether we can use HW checksum.
-				 */
-				if (sk->sk_route_caps & NETIF_F_ALL_CSUM)
-					skb->ip_summed = CHECKSUM_PARTIAL;
+			/*
+			 * Check whether we can use HW checksum.
+			 */
+			if (sk->sk_route_caps & NETIF_F_ALL_CSUM)
+				skb->ip_summed = CHECKSUM_PARTIAL;
 
-				skb_entail(sk, skb);
-				copy = size_goal;
-				max = size_goal;
+			skb_entail(sk, skb);
+			copy = size_goal;
+			max = size_goal;
 
-				/* All packets are restored as if they have
-				 * already been sent. skb_mstamp isn't set to
-				 * avoid wrong rtt estimation.
-				 */
-				if (tp->repair)
-					TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED;
-			}
+			/* All packets are restored as if they have
+			 * already been sent. skb_mstamp isn't set to
+			 * avoid wrong rtt estimation.
+			 */
+			if (tp->repair)
+				TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED;
+		}
 
-			/* Try to append data to the end of skb. */
-			if (copy > seglen)
-				copy = seglen;
-
-			/* Where to copy to? */
-			if (skb_availroom(skb) > 0) {
-				/* We have some space in skb head. Superb! */
-				copy = min_t(int, copy, skb_availroom(skb));
-				err = skb_add_data_nocache(sk, skb, from, copy);
-				if (err)
-					goto do_fault;
-			} else {
-				bool merge = true;
-				int i = skb_shinfo(skb)->nr_frags;
-				struct page_frag *pfrag = sk_page_frag(sk);
-
-				if (!sk_page_frag_refill(sk, pfrag))
-					goto wait_for_memory;
-
-				if (!skb_can_coalesce(skb, i, pfrag->page,
-						      pfrag->offset)) {
-					if (i == MAX_SKB_FRAGS || !sg) {
-						tcp_mark_push(tp, skb);
-						goto new_segment;
-					}
-					merge = false;
-				}
+		/* Try to append data to the end of skb. */
+		if (copy > iov_iter_count(&msg->msg_iter))
+			copy = iov_iter_count(&msg->msg_iter);
+
+		/* Where to copy to? */
+		if (skb_availroom(skb) > 0) {
+			/* We have some space in skb head. Superb! */
+			copy = min_t(int, copy, skb_availroom(skb));
+			err = skb_add_data_nocache(sk, skb, &msg->msg_iter, copy);
+			if (err)
+				goto do_fault;
+		} else {
+			bool merge = true;
+			int i = skb_shinfo(skb)->nr_frags;
+			struct page_frag *pfrag = sk_page_frag(sk);
+
+			if (!sk_page_frag_refill(sk, pfrag))
+				goto wait_for_memory;
 
-				copy = min_t(int, copy, pfrag->size - pfrag->offset);
-
-				if (!sk_wmem_schedule(sk, copy))
-					goto wait_for_memory;
-
-				err = skb_copy_to_page_nocache(sk, from, skb,
-							       pfrag->page,
-							       pfrag->offset,
-							       copy);
-				if (err)
-					goto do_error;
-
-				/* Update the skb. */
-				if (merge) {
-					skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
-				} else {
-					skb_fill_page_desc(skb, i, pfrag->page,
-							   pfrag->offset, copy);
-					get_page(pfrag->page);
+			if (!skb_can_coalesce(skb, i, pfrag->page,
+					      pfrag->offset)) {
+				if (i == MAX_SKB_FRAGS || !sg) {
+					tcp_mark_push(tp, skb);
+					goto new_segment;
 				}
-				pfrag->offset += copy;
+				merge = false;
 			}
 
-			if (!copied)
-				TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
+			copy = min_t(int, copy, pfrag->size - pfrag->offset);
 
-			tp->write_seq += copy;
-			TCP_SKB_CB(skb)->end_seq += copy;
-			tcp_skb_pcount_set(skb, 0);
+			if (!sk_wmem_schedule(sk, copy))
+				goto wait_for_memory;
 
-			from += copy;
-			copied += copy;
-			if ((seglen -= copy) == 0 && iovlen == 0) {
-				tcp_tx_timestamp(sk, skb);
-				goto out;
+			err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb,
+						       pfrag->page,
+						       pfrag->offset,
+						       copy);
+			if (err)
+				goto do_error;
+
+			/* Update the skb. */
+			if (merge) {
+				skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
+			} else {
+				skb_fill_page_desc(skb, i, pfrag->page,
+						   pfrag->offset, copy);
+				get_page(pfrag->page);
 			}
+			pfrag->offset += copy;
+		}
 
-			if (skb->len < max || (flags & MSG_OOB) || unlikely(tp->repair))
-				continue;
+		if (!copied)
+			TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
+
+		tp->write_seq += copy;
+		TCP_SKB_CB(skb)->end_seq += copy;
+		tcp_skb_pcount_set(skb, 0);
+
+		copied += copy;
+		if (!iov_iter_count(&msg->msg_iter)) {
+			tcp_tx_timestamp(sk, skb);
+			goto out;
+		}
 
-			if (forced_push(tp)) {
-				tcp_mark_push(tp, skb);
-				__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH);
-			} else if (skb == tcp_send_head(sk))
-				tcp_push_one(sk, mss_now);
+		if (skb->len < max || (flags & MSG_OOB) || unlikely(tp->repair))
 			continue;
 
+		if (forced_push(tp)) {
+			tcp_mark_push(tp, skb);
+			__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH);
+		} else if (skb == tcp_send_head(sk))
+			tcp_push_one(sk, mss_now);
+		continue;
+
 wait_for_sndbuf:
-			set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 wait_for_memory:
-			if (copied)
-				tcp_push(sk, flags & ~MSG_MORE, mss_now,
-					 TCP_NAGLE_PUSH, size_goal);
+		if (copied)
+			tcp_push(sk, flags & ~MSG_MORE, mss_now,
+				 TCP_NAGLE_PUSH, size_goal);
 
-			if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
-				goto do_error;
+		if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
+			goto do_error;
 
-			mss_now = tcp_send_mss(sk, &size_goal, flags);
-		}
+		mss_now = tcp_send_mss(sk, &size_goal, flags);
 	}
 
 out:

net/ipv4/tcp_output.c

@@ -3055,7 +3055,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_fastopen_request *fo = tp->fastopen_req;
-	int syn_loss = 0, space, err = 0;
+	int syn_loss = 0, space, err = 0, copied;
 	unsigned long last_syn_loss = 0;
 	struct sk_buff *syn_data;
 
@@ -3093,11 +3093,16 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 		goto fallback;
 	syn_data->ip_summed = CHECKSUM_PARTIAL;
 	memcpy(syn_data->cb, syn->cb, sizeof(syn->cb));
-	if (unlikely(memcpy_fromiovecend(skb_put(syn_data, space),
-					 fo->data->msg_iter.iov, 0, space))) {
+	copied = copy_from_iter(skb_put(syn_data, space), space,
+				&fo->data->msg_iter);
+	if (unlikely(!copied)) {
 		kfree_skb(syn_data);
 		goto fallback;
 	}
+	if (copied != space) {
+		skb_trim(syn_data, copied);
+		space = copied;
+	}
 
 	/* No more data pending in inet_wait_for_connect() */
 	if (space == fo->size)

net/ipv6/ping.c

@@ -163,8 +163,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	pfh.icmph.checksum = 0;
 	pfh.icmph.un.echo.id = inet->inet_sport;
 	pfh.icmph.un.echo.sequence = user_icmph.icmp6_sequence;
-	/* XXX: stripping const */
-	pfh.iov = (struct iovec *)msg->msg_iter.iov;
+	pfh.msg = msg;
 	pfh.wcheck = 0;
 	pfh.family = AF_INET6;
 

net/ipv6/raw.c

@@ -609,7 +609,7 @@ out:
 	return err;
 }
 
-static int rawv6_send_hdrinc(struct sock *sk, void *from, int length,
+static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 			struct flowi6 *fl6, struct dst_entry **dstp,
 			unsigned int flags)
 {
@@ -648,7 +648,7 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length,
 	skb->ip_summed = CHECKSUM_NONE;
 
 	skb->transport_header = skb->network_header;
-	err = memcpy_fromiovecend((void *)iph, from, 0, length);
+	err = memcpy_from_msg(iph, msg, length);
 	if (err)
 		goto error_fault;
 
@@ -886,8 +886,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 
 back_from_confirm:
 	if (inet->hdrincl)
-		/* XXX: stripping const */
-		err = rawv6_send_hdrinc(sk, (struct iovec *)msg->msg_iter.iov, len, &fl6, &dst, msg->msg_flags);
+		err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst, msg->msg_flags);
 	else {
 		lock_sock(sk);
 		err = ip6_append_data(sk, raw6_getfrag, &rfv,

net/netlink/af_netlink.c

@@ -2298,7 +2298,12 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 			goto out;
 	}
 
+	/* It's a really convoluted way for userland to ask for mmaped
+	 * sendmsg(), but that's what we've got...
+	 */
 	if (netlink_tx_is_mmaped(sk) &&
+	    msg->msg_iter.type == ITER_IOVEC &&
+	    msg->msg_iter.nr_segs == 1 &&
 	    msg->msg_iter.iov->iov_base == NULL) {
 		err = netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group,
 					   &scm);

net/rxrpc/ar-output.c

@@ -232,10 +232,7 @@ int rxrpc_kernel_send_data(struct rxrpc_call *call, struct msghdr *msg,
 		   call->state != RXRPC_CALL_SERVER_SEND_REPLY) {
 		ret = -EPROTO; /* request phase complete for this client call */
 	} else {
-		mm_segment_t oldfs = get_fs();
-		set_fs(KERNEL_DS);
 		ret = rxrpc_send_data(NULL, call->socket, call, msg, len);
-		set_fs(oldfs);
 	}
 
 	release_sock(&call->socket->sk);
@@ -529,13 +526,11 @@ static int rxrpc_send_data(struct kiocb *iocb,
 			   struct msghdr *msg, size_t len)
 {
 	struct rxrpc_skb_priv *sp;
-	unsigned char __user *from;
 	struct sk_buff *skb;
-	const struct iovec *iov;
 	struct sock *sk = &rx->sk;
 	long timeo;
 	bool more;
-	int ret, ioc, segment, copied;
+	int ret, copied;
 
 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 
@@ -545,25 +540,17 @@ static int rxrpc_send_data(struct kiocb *iocb,
 	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
 		return -EPIPE;
 
-	iov = msg->msg_iter.iov;
-	ioc = msg->msg_iter.nr_segs - 1;
-	from = iov->iov_base;
-	segment = iov->iov_len;
-	iov++;
 	more = msg->msg_flags & MSG_MORE;
 
 	skb = call->tx_pending;
 	call->tx_pending = NULL;
 
 	copied = 0;
-	do {
+	if (len > iov_iter_count(&msg->msg_iter))
+		len = iov_iter_count(&msg->msg_iter);
+	while (len) {
 		int copy;
 
-		if (segment > len)
-			segment = len;
-
-		_debug("SEGMENT %d @%p", segment, from);
-
 		if (!skb) {
 			size_t size, chunk, max, space;
 
@@ -631,13 +618,13 @@ static int rxrpc_send_data(struct kiocb *iocb,
 		/* append next segment of data to the current buffer */
 		copy = skb_tailroom(skb);
 		ASSERTCMP(copy, >, 0);
-		if (copy > segment)
-			copy = segment;
+		if (copy > len)
+			copy = len;
 		if (copy > sp->remain)
 			copy = sp->remain;
 
 		_debug("add");
-		ret = skb_add_data(skb, from, copy);
+		ret = skb_add_data(skb, &msg->msg_iter, copy);
 		_debug("added");
 		if (ret < 0)
 			goto efault;
@@ -646,18 +633,6 @@ static int rxrpc_send_data(struct kiocb *iocb,
 		copied += copy;
 
 		len -= copy;
-		segment -= copy;
-		from += copy;
-		while (segment == 0 && ioc > 0) {
-			from = iov->iov_base;
-			segment = iov->iov_len;
-			iov++;
-			ioc--;
-		}
-		if (len == 0) {
-			segment = 0;
-			ioc = 0;
-		}
 
 		/* check for the far side aborting the call or a network error
 		 * occurring */
@@ -665,7 +640,7 @@ static int rxrpc_send_data(struct kiocb *iocb,
 			goto call_aborted;
 
 		/* add the packet to the send queue if it's now full */
-		if (sp->remain <= 0 || (segment == 0 && !more)) {
+		if (sp->remain <= 0 || (!len && !more)) {
 			struct rxrpc_connection *conn = call->conn;
 			uint32_t seq;
 			size_t pad;
@@ -711,11 +686,10 @@ static int rxrpc_send_data(struct kiocb *iocb,
 
 			memcpy(skb->head, &sp->hdr,
 			       sizeof(struct rxrpc_header));
-			rxrpc_queue_packet(call, skb, segment == 0 && !more);
+			rxrpc_queue_packet(call, skb, !iov_iter_count(&msg->msg_iter) && !more);
 			skb = NULL;
 		}
-
-	} while (segment > 0);
+	}
 
 success:
 	ret = copied;

net/socket.c

@@ -113,10 +113,8 @@ unsigned int sysctl_net_busy_read __read_mostly;
 unsigned int sysctl_net_busy_poll __read_mostly;
 #endif
 
-static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov,
-			 unsigned long nr_segs, loff_t pos);
-static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov,
-			  unsigned long nr_segs, loff_t pos);
+static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to);
+static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from);
 static int sock_mmap(struct file *file, struct vm_area_struct *vma);
 
 static int sock_close(struct inode *inode, struct file *file);
@@ -142,8 +140,10 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
 static const struct file_operations socket_file_ops = {
 	.owner =	THIS_MODULE,
 	.llseek =	no_llseek,
-	.aio_read =	sock_aio_read,
-	.aio_write =	sock_aio_write,
+	.read =		new_sync_read,
+	.write =	new_sync_write,
+	.read_iter =	sock_read_iter,
+	.write_iter =	sock_write_iter,
 	.poll =		sock_poll,
 	.unlocked_ioctl = sock_ioctl,
 #ifdef CONFIG_COMPAT
@@ -845,63 +845,47 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
 	return sock->ops->splice_read(sock, ppos, pipe, len, flags);
 }
 
-static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb,
-		struct file *file, const struct iovec *iov,
-		unsigned long nr_segs)
+static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
+	struct file *file = iocb->ki_filp;
 	struct socket *sock = file->private_data;
+	struct msghdr msg = {.msg_iter = *to};
+	ssize_t res;
 
-	msg->msg_name = NULL;
-	msg->msg_namelen = 0;
-	msg->msg_control = NULL;
-	msg->msg_controllen = 0;
-	iov_iter_init(&msg->msg_iter, READ, iov, nr_segs, iocb->ki_nbytes);
-	msg->msg_flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0;
+	if (file->f_flags & O_NONBLOCK)
+		msg.msg_flags = MSG_DONTWAIT;
 
-	return __sock_recvmsg(iocb, sock, msg, iocb->ki_nbytes, msg->msg_flags);
-}
-
-static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos)
-{
-	struct msghdr msg;
-
-	if (pos != 0)
+	if (iocb->ki_pos != 0)
 		return -ESPIPE;
 
 	if (iocb->ki_nbytes == 0)	/* Match SYS5 behaviour */
 		return 0;
 
-	return do_sock_read(&msg, iocb, iocb->ki_filp, iov, nr_segs);
+	res = __sock_recvmsg(iocb, sock, &msg,
+			     iocb->ki_nbytes, msg.msg_flags);
+	*to = msg.msg_iter;
+	return res;
 }
 
-static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb,
-			struct file *file, const struct iovec *iov,
-			unsigned long nr_segs)
+static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
+	struct file *file = iocb->ki_filp;
 	struct socket *sock = file->private_data;
+	struct msghdr msg = {.msg_iter = *from};
+	ssize_t res;
 
-	msg->msg_name = NULL;
-	msg->msg_namelen = 0;
-	msg->msg_control = NULL;
-	msg->msg_controllen = 0;
-	iov_iter_init(&msg->msg_iter, WRITE, iov, nr_segs, iocb->ki_nbytes);
-	msg->msg_flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0;
-	if (sock->type == SOCK_SEQPACKET)
-		msg->msg_flags |= MSG_EOR;
-
-	return __sock_sendmsg(iocb, sock, msg, iocb->ki_nbytes);
-}
+	if (iocb->ki_pos != 0)
+		return -ESPIPE;
 
-static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov,
-			  unsigned long nr_segs, loff_t pos)
-{
-	struct msghdr msg;
+	if (file->f_flags & O_NONBLOCK)
+		msg.msg_flags = MSG_DONTWAIT;
 
-	if (pos != 0)
-		return -ESPIPE;
+	if (sock->type == SOCK_SEQPACKET)
+		msg.msg_flags |= MSG_EOR;
 
-	return do_sock_write(&msg, iocb, iocb->ki_filp, iov, nr_segs);
+	res = __sock_sendmsg(iocb, sock, &msg, iocb->ki_nbytes);
+	*from = msg.msg_iter;
+	return res;
 }
 
 /*

net/tipc/msg.c

@@ -189,7 +189,6 @@ err:
  * tipc_msg_build - create buffer chain containing specified header and data
  * @mhdr: Message header, to be prepended to data
  * @m: User message
- * @offset: Posision in iov to start copying from
  * @dsz: Total length of user data
  * @pktmax: Max packet size that can be used
  * @list: Buffer or chain of buffers to be returned to caller
@@ -221,8 +220,7 @@ int tipc_msg_build(struct net *net, struct tipc_msg *mhdr, struct msghdr *m,
 		__skb_queue_tail(list, skb);
 		skb_copy_to_linear_data(skb, mhdr, mhsz);
 		pktpos = skb->data + mhsz;
-		if (!dsz || !memcpy_fromiovecend(pktpos, m->msg_iter.iov, offset,
-						 dsz))
+		if (copy_from_iter(pktpos, dsz, &m->msg_iter) == dsz)
 			return dsz;
 		rc = -EFAULT;
 		goto error;
@@ -252,12 +250,11 @@ int tipc_msg_build(struct net *net, struct tipc_msg *mhdr, struct msghdr *m,
 		if (drem < pktrem)
 			pktrem = drem;
 
-		if (memcpy_fromiovecend(pktpos, m->msg_iter.iov, offset, pktrem)) {
+		if (copy_from_iter(pktpos, pktrem, &m->msg_iter) != pktrem) {
 			rc = -EFAULT;
 			goto error;
 		}
 		drem -= pktrem;
-		offset += pktrem;
 
 		if (!drem)
 			break;

net/tipc/socket.c

@@ -733,6 +733,7 @@ static int tipc_sendmcast(struct  socket *sock, struct tipc_name_seq *seq,
 	struct net *net = sock_net(sk);
 	struct tipc_msg *mhdr = &tipc_sk(sk)->phdr;
 	struct sk_buff_head head;
+	struct iov_iter save = msg->msg_iter;
 	uint mtu;
 	int rc;
 
@@ -758,8 +759,10 @@ new_mtu:
 			rc = dsz;
 			break;
 		}
-		if (rc == -EMSGSIZE)
+		if (rc == -EMSGSIZE) {
+			msg->msg_iter = save;
 			goto new_mtu;
+		}
 		if (rc != -ELINKCONG)
 			break;
 		tipc_sk(sk)->link_cong = 1;
@@ -895,6 +898,7 @@ static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock,
 	struct sk_buff_head head;
 	struct sk_buff *skb;
 	struct tipc_name_seq *seq = &dest->addr.nameseq;
+	struct iov_iter save;
 	u32 mtu;
 	long timeo;
 	int rc;
@@ -963,6 +967,7 @@ static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock,
 		msg_set_hdr_sz(mhdr, BASIC_H_SIZE);
 	}
 
+	save = m->msg_iter;
 new_mtu:
 	mtu = tipc_node_get_mtu(net, dnode, tsk->portid);
 	__skb_queue_head_init(&head);
@@ -980,8 +985,10 @@ new_mtu:
 			rc = dsz;
 			break;
 		}
-		if (rc == -EMSGSIZE)
+		if (rc == -EMSGSIZE) {
+			m->msg_iter = save;
 			goto new_mtu;
+		}
 		if (rc != -ELINKCONG)
 			break;
 		tsk->link_cong = 1;
@@ -1052,6 +1059,7 @@ static int tipc_send_stream(struct kiocb *iocb, struct socket *sock,
 	long timeo;
 	u32 dnode;
 	uint mtu, send, sent = 0;
+	struct iov_iter save;
 
 	/* Handle implied connection establishment */
 	if (unlikely(dest)) {
@@ -1078,6 +1086,7 @@ static int tipc_send_stream(struct kiocb *iocb, struct socket *sock,
 	dnode = tsk_peer_node(tsk);
 
 next:
+	save = m->msg_iter;
 	mtu = tsk->max_pkt;
 	send = min_t(uint, dsz - sent, TIPC_MAX_USER_MSG_SIZE);
 	__skb_queue_head_init(&head);
@@ -1097,6 +1106,7 @@ next:
 			if (rc == -EMSGSIZE) {
 				tsk->max_pkt = tipc_node_get_mtu(net, dnode,
 								 portid);
+				m->msg_iter = save;
 				goto next;
 			}
 			if (rc != -ELINKCONG)

net/vmw_vsock/vmci_transport.c

@@ -1850,8 +1850,7 @@ static ssize_t vmci_transport_stream_enqueue(
 	struct msghdr *msg,
 	size_t len)
 {
-	/* XXX: stripping const */
-	return vmci_qpair_enquev(vmci_trans(vsk)->qpair, (struct iovec *)msg->msg_iter.iov, len, 0);
+	return vmci_qpair_enquev(vmci_trans(vsk)->qpair, msg, len, 0);
 }
 
 static s64 vmci_transport_stream_has_data(struct vsock_sock *vsk)