Merge branch 'iov_iter'

Herbert Xu says:

====================
Replace skb_copy_datagram_const_iovec with iterator version

This patch series adds the helper skb_copy_datagram_iter, which
is meant to replace both skb_copy_datagram_iovec and its evil
twin skb_copy_datagram_const_iovec.

It then converts tun and macvtap over to the new helper and finally
removes skb_copy_datagram_const_iovec which is only used by tun
and macvtap.

The copy_to_iter return value issue pointed out by Al has now been
fixed.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

drivers/net/macvtap.c

@@ -15,6 +15,7 @@
 #include <linux/cdev.h>
 #include <linux/idr.h>
 #include <linux/fs.h>
+#include <linux/uio.h>
 
 #include <net/ipv6.h>
 #include <net/net_namespace.h>
@@ -778,31 +779,29 @@ static ssize_t macvtap_aio_write(struct kiocb *iocb, const struct iovec *iv,
 /* Put packet to the user space buffer */
 static ssize_t macvtap_put_user(struct macvtap_queue *q,
 				const struct sk_buff *skb,
-				const struct iovec *iv, int len)
+				struct iov_iter *iter)
 {
 	int ret;
 	int vnet_hdr_len = 0;
 	int vlan_offset = 0;
-	int copied, total;
+	int total;
 
 	if (q->flags & IFF_VNET_HDR) {
 		struct virtio_net_hdr vnet_hdr;
 		vnet_hdr_len = q->vnet_hdr_sz;
-		if ((len -= vnet_hdr_len) < 0)
+		if (iov_iter_count(iter) < vnet_hdr_len)
 			return -EINVAL;
 
 		macvtap_skb_to_vnet_hdr(skb, &vnet_hdr);
 
-		if (memcpy_toiovecend(iv, (void *)&vnet_hdr, 0, sizeof(vnet_hdr)))
+		if (copy_to_iter(&vnet_hdr, sizeof(vnet_hdr), iter) !=
+		    sizeof(vnet_hdr))
 			return -EFAULT;
 	}
-	total = copied = vnet_hdr_len;
+	total = vnet_hdr_len;
 	total += skb->len;
 
-	if (!vlan_tx_tag_present(skb))
-		len = min_t(int, skb->len, len);
-	else {
-		int copy;
+	if (vlan_tx_tag_present(skb)) {
 		struct {
 			__be16 h_vlan_proto;
 			__be16 h_vlan_TCI;
@@ -811,37 +810,33 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
 		veth.h_vlan_TCI = htons(vlan_tx_tag_get(skb));
 
 		vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto);
-		len = min_t(int, skb->len + VLAN_HLEN, len);
 		total += VLAN_HLEN;
 
-		copy = min_t(int, vlan_offset, len);
-		ret = skb_copy_datagram_const_iovec(skb, 0, iv, copied, copy);
-		len -= copy;
-		copied += copy;
-		if (ret || !len)
+		ret = skb_copy_datagram_iter(skb, 0, iter, vlan_offset);
+		if (ret || !iov_iter_count(iter))
 			goto done;
 
-		copy = min_t(int, sizeof(veth), len);
-		ret = memcpy_toiovecend(iv, (void *)&veth, copied, copy);
-		len -= copy;
-		copied += copy;
-		if (ret || !len)
+		ret = copy_to_iter(&veth, sizeof(veth), iter);
+		if (ret != sizeof(veth) || !iov_iter_count(iter))
 			goto done;
 	}
 
-	ret = skb_copy_datagram_const_iovec(skb, vlan_offset, iv, copied, len);
+	ret = skb_copy_datagram_iter(skb, vlan_offset, iter,
+				     skb->len - vlan_offset);
 
 done:
 	return ret ? ret : total;
 }
 
 static ssize_t macvtap_do_read(struct macvtap_queue *q,
-			       const struct iovec *iv, unsigned long len,
+			       const struct iovec *iv, unsigned long segs,
+			       unsigned long len,
 			       int noblock)
 {
 	DEFINE_WAIT(wait);
 	struct sk_buff *skb;
 	ssize_t ret = 0;
+	struct iov_iter iter;
 
 	while (len) {
 		if (!noblock)
@@ -863,7 +858,8 @@ static ssize_t macvtap_do_read(struct macvtap_queue *q,
 			schedule();
 			continue;
 		}
-		ret = macvtap_put_user(q, skb, iv, len);
+		iov_iter_init(&iter, READ, iv, segs, len);
+		ret = macvtap_put_user(q, skb, &iter);
 		kfree_skb(skb);
 		break;
 	}
@@ -886,7 +882,7 @@ static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv,
 		goto out;
 	}
 
-	ret = macvtap_do_read(q, iv, len, file->f_flags & O_NONBLOCK);
+	ret = macvtap_do_read(q, iv, count, len, file->f_flags & O_NONBLOCK);
 	ret = min_t(ssize_t, ret, len);
 	if (ret > 0)
 		iocb->ki_pos = ret;
@@ -1117,7 +1113,7 @@ static int macvtap_recvmsg(struct kiocb *iocb, struct socket *sock,
 	int ret;
 	if (flags & ~(MSG_DONTWAIT|MSG_TRUNC))
 		return -EINVAL;
-	ret = macvtap_do_read(q, m->msg_iov, total_len,
+	ret = macvtap_do_read(q, m->msg_iov, m->msg_iovlen, total_len,
 			  flags & MSG_DONTWAIT);
 	if (ret > total_len) {
 		m->msg_flags |= MSG_TRUNC;

drivers/net/tun.c

@@ -71,6 +71,7 @@
 #include <net/rtnetlink.h>
 #include <net/sock.h>
 #include <linux/seq_file.h>
+#include <linux/uio.h>
 
 #include <asm/uaccess.h>
 
@@ -1230,11 +1231,11 @@ static ssize_t tun_chr_aio_write(struct kiocb *iocb, const struct iovec *iv,
 static ssize_t tun_put_user(struct tun_struct *tun,
 			    struct tun_file *tfile,
 			    struct sk_buff *skb,
-			    const struct iovec *iv, int len)
+			    struct iov_iter *iter)
 {
 	struct tun_pi pi = { 0, skb->protocol };
-	ssize_t total = 0;
-	int vlan_offset = 0, copied;
+	ssize_t total;
+	int vlan_offset;
 	int vlan_hlen = 0;
 	int vnet_hdr_sz = 0;
 
@@ -1244,23 +1245,25 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 	if (tun->flags & TUN_VNET_HDR)
 		vnet_hdr_sz = tun->vnet_hdr_sz;
 
+	total = skb->len + vlan_hlen + vnet_hdr_sz;
+
 	if (!(tun->flags & TUN_NO_PI)) {
-		if ((len -= sizeof(pi)) < 0)
+		if (iov_iter_count(iter) < sizeof(pi))
 			return -EINVAL;
 
-		if (len < skb->len + vlan_hlen + vnet_hdr_sz) {
+		total += sizeof(pi);
+		if (iov_iter_count(iter) < total) {
 			/* Packet will be striped */
 			pi.flags |= TUN_PKT_STRIP;
 		}
 
-		if (memcpy_toiovecend(iv, (void *) &pi, 0, sizeof(pi)))
+		if (copy_to_iter(&pi, sizeof(pi), iter) != sizeof(pi))
 			return -EFAULT;
-		total += sizeof(pi);
 	}
 
 	if (vnet_hdr_sz) {
 		struct virtio_net_hdr gso = { 0 }; /* no info leak */
-		if ((len -= vnet_hdr_sz) < 0)
+		if (iov_iter_count(iter) < vnet_hdr_sz)
 			return -EINVAL;
 
 		if (skb_is_gso(skb)) {
@@ -1299,17 +1302,12 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 			gso.flags = VIRTIO_NET_HDR_F_DATA_VALID;
 		} /* else everything is zero */
 
-		if (unlikely(memcpy_toiovecend(iv, (void *)&gso, total,
-					       sizeof(gso))))
+		if (copy_to_iter(&gso, sizeof(gso), iter) != sizeof(gso))
 			return -EFAULT;
-		total += vnet_hdr_sz;
 	}
 
-	copied = total;
-	len = min_t(int, skb->len + vlan_hlen, len);
-	total += skb->len + vlan_hlen;
 	if (vlan_hlen) {
-		int copy, ret;
+		int ret;
 		struct {
 			__be16 h_vlan_proto;
 			__be16 h_vlan_TCI;
@@ -1320,36 +1318,32 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 
 		vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto);
 
-		copy = min_t(int, vlan_offset, len);
-		ret = skb_copy_datagram_const_iovec(skb, 0, iv, copied, copy);
-		len -= copy;
-		copied += copy;
-		if (ret || !len)
+		ret = skb_copy_datagram_iter(skb, 0, iter, vlan_offset);
+		if (ret || !iov_iter_count(iter))
 			goto done;
 
-		copy = min_t(int, sizeof(veth), len);
-		ret = memcpy_toiovecend(iv, (void *)&veth, copied, copy);
-		len -= copy;
-		copied += copy;
-		if (ret || !len)
+		ret = copy_to_iter(&veth, sizeof(veth), iter);
+		if (ret != sizeof(veth) || !iov_iter_count(iter))
 			goto done;
 	}
 
-	skb_copy_datagram_const_iovec(skb, vlan_offset, iv, copied, len);
+	skb_copy_datagram_iter(skb, vlan_offset, iter, skb->len - vlan_offset);
 
 done:
 	tun->dev->stats.tx_packets++;
-	tun->dev->stats.tx_bytes += len;
+	tun->dev->stats.tx_bytes += skb->len + vlan_hlen;
 
 	return total;
 }
 
 static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile,
-			   const struct iovec *iv, ssize_t len, int noblock)
+			   const struct iovec *iv, unsigned long segs,
+			   ssize_t len, int noblock)
 {
 	struct sk_buff *skb;
 	ssize_t ret = 0;
 	int peeked, err, off = 0;
+	struct iov_iter iter;
 
 	tun_debug(KERN_INFO, tun, "tun_do_read\n");
 
@@ -1362,11 +1356,12 @@ static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile,
 	/* Read frames from queue */
 	skb = __skb_recv_datagram(tfile->socket.sk, noblock ? MSG_DONTWAIT : 0,
 				  &peeked, &off, &err);
-	if (skb) {
-		ret = tun_put_user(tun, tfile, skb, iv, len);
-		kfree_skb(skb);
-	} else
-		ret = err;
+	if (!skb)
+		return ret;
+
+	iov_iter_init(&iter, READ, iv, segs, len);
+	ret = tun_put_user(tun, tfile, skb, &iter);
+	kfree_skb(skb);
 
 	return ret;
 }
@@ -1387,7 +1382,7 @@ static ssize_t tun_chr_aio_read(struct kiocb *iocb, const struct iovec *iv,
 		goto out;
 	}
 
-	ret = tun_do_read(tun, tfile, iv, len,
+	ret = tun_do_read(tun, tfile, iv, count, len,
 			  file->f_flags & O_NONBLOCK);
 	ret = min_t(ssize_t, ret, len);
 	if (ret > 0)
@@ -1488,7 +1483,7 @@ static int tun_recvmsg(struct kiocb *iocb, struct socket *sock,
 					 SOL_PACKET, TUN_TX_TIMESTAMP);
 		goto out;
 	}
-	ret = tun_do_read(tun, tfile, m->msg_iov, total_len,
+	ret = tun_do_read(tun, tfile, m->msg_iov, m->msg_iovlen, total_len,
 			  flags & MSG_DONTWAIT);
 	if (ret > total_len) {
 		m->msg_flags |= MSG_TRUNC;

include/linux/skbuff.h

@@ -150,6 +150,7 @@
 struct net_device;
 struct scatterlist;
 struct pipe_inode_info;
+struct iov_iter;
 
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 struct nf_conntrack {
@@ -2650,9 +2651,8 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
 				 int len);
 int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *frm,
 			   int offset, size_t count);
-int skb_copy_datagram_const_iovec(const struct sk_buff *from, int offset,
-				  const struct iovec *to, int to_offset,
-				  int size);
+int skb_copy_datagram_iter(const struct sk_buff *from, int offset,
+			   struct iov_iter *to, int size);
 void skb_free_datagram(struct sock *sk, struct sk_buff *skb);
 void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb);
 int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags);

net/core/datagram.c

@@ -49,6 +49,7 @@
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/pagemap.h>
+#include <linux/uio.h>
 
 #include <net/protocol.h>
 #include <linux/skbuff.h>
@@ -393,34 +394,30 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset,
 EXPORT_SYMBOL(skb_copy_datagram_iovec);
 
 /**
- *	skb_copy_datagram_const_iovec - Copy a datagram to an iovec.
+ *	skb_copy_datagram_iter - Copy a datagram to an iovec iterator.
  *	@skb: buffer to copy
  *	@offset: offset in the buffer to start copying from
- *	@to: io vector to copy to
- *	@to_offset: offset in the io vector to start copying to
+ *	@to: iovec iterator to copy to
  *	@len: amount of data to copy from buffer to iovec
- *
- *	Returns 0 or -EFAULT.
- *	Note: the iovec is not modified during the copy.
  */
-int skb_copy_datagram_const_iovec(const struct sk_buff *skb, int offset,
-				  const struct iovec *to, int to_offset,
-				  int len)
+int skb_copy_datagram_iter(const struct sk_buff *skb, int offset,
+			   struct iov_iter *to, int len)
 {
 	int start = skb_headlen(skb);
 	int i, copy = start - offset;
 	struct sk_buff *frag_iter;
 
+	trace_skb_copy_datagram_iovec(skb, len);
+
 	/* Copy header. */
 	if (copy > 0) {
 		if (copy > len)
 			copy = len;
-		if (memcpy_toiovecend(to, skb->data + offset, to_offset, copy))
-			goto fault;
+		if (copy_to_iter(skb->data + offset, copy, to) != copy)
+			goto short_copy;
 		if ((len -= copy) == 0)
 			return 0;
 		offset += copy;
-		to_offset += copy;
 	}
 
 	/* Copy paged appendix. Hmm... why does this look so complicated? */
@@ -432,22 +429,15 @@ int skb_copy_datagram_const_iovec(const struct sk_buff *skb, int offset,
 
 		end = start + skb_frag_size(frag);
 		if ((copy = end - offset) > 0) {
-			int err;
-			u8  *vaddr;
-			struct page *page = skb_frag_page(frag);
-
 			if (copy > len)
 				copy = len;
-			vaddr = kmap(page);
-			err = memcpy_toiovecend(to, vaddr + frag->page_offset +
-						offset - start, to_offset, copy);
-			kunmap(page);
-			if (err)
-				goto fault;
+			if (copy_page_to_iter(skb_frag_page(frag),
+					      frag->page_offset + offset -
+					      start, copy, to) != copy)
+				goto short_copy;
 			if (!(len -= copy))
 				return 0;
 			offset += copy;
-			to_offset += copy;
 		}
 		start = end;
 	}
@@ -461,25 +451,33 @@ int skb_copy_datagram_const_iovec(const struct sk_buff *skb, int offset,
 		if ((copy = end - offset) > 0) {
 			if (copy > len)
 				copy = len;
-			if (skb_copy_datagram_const_iovec(frag_iter,
-							  offset - start,
-							  to, to_offset,
-							  copy))
+			if (skb_copy_datagram_iter(frag_iter, offset - start,
+						   to, copy))
 				goto fault;
 			if ((len -= copy) == 0)
 				return 0;
 			offset += copy;
-			to_offset += copy;
 		}
 		start = end;
 	}
 	if (!len)
 		return 0;
 
+	/* This is not really a user copy fault, but rather someone
+	 * gave us a bogus length on the skb.  We should probably
+	 * print a warning here as it may indicate a kernel bug.
+	 */
+
 fault:
 	return -EFAULT;
+
+short_copy:
+	if (iov_iter_count(to))
+		goto fault;
+
+	return 0;
 }
-EXPORT_SYMBOL(skb_copy_datagram_const_iovec);
+EXPORT_SYMBOL(skb_copy_datagram_iter);
 
 /**
  *	skb_copy_datagram_from_iovec - Copy a datagram from an iovec.