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

Pull vfs updates from Al Viro:
 "The first vfs pile, with deep apologies for being very late in this
  window.

  Assorted cleanups and fixes, plus a large preparatory part of iov_iter
  work.  There's a lot more of that, but it'll probably go into the next
  merge window - it *does* shape up nicely, removes a lot of
  boilerplate, gets rid of locking inconsistencie between aio_write and
  splice_write and I hope to get Kent's direct-io rewrite merged into
  the same queue, but some of the stuff after this point is having
  (mostly trivial) conflicts with the things already merged into
  mainline and with some I want more testing.

  This one passes LTP and xfstests without regressions, in addition to
  usual beating.  BTW, readahead02 in ltp syscalls testsuite has started
  giving failures since "mm/readahead.c: fix readahead failure for
  memoryless NUMA nodes and limit readahead pages" - might be a false
  positive, might be a real regression..."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (63 commits)
  missing bits of "splice: fix racy pipe->buffers uses"
  cifs: fix the race in cifs_writev()
  ceph_sync_{,direct_}write: fix an oops on ceph_osdc_new_request() failure
  kill generic_file_buffered_write()
  ocfs2_file_aio_write(): switch to generic_perform_write()
  ceph_aio_write(): switch to generic_perform_write()
  xfs_file_buffered_aio_write(): switch to generic_perform_write()
  export generic_perform_write(), start getting rid of generic_file_buffer_write()
  generic_file_direct_write(): get rid of ppos argument
  btrfs_file_aio_write(): get rid of ppos
  kill the 5th argument of generic_file_buffered_write()
  kill the 4th argument of __generic_file_aio_write()
  lustre: don't open-code kernel_recvmsg()
  ocfs2: don't open-code kernel_recvmsg()
  drbd: don't open-code kernel_recvmsg()
  constify blk_rq_map_user_iov() and friends
  lustre: switch to kernel_sendmsg()
  ocfs2: don't open-code kernel_sendmsg()
  take iov_iter stuff to mm/iov_iter.c
  process_vm_access: tidy up a bit
  ...

Documentation/filesystems/Locking

@@ -202,7 +202,7 @@ prototypes:
 				unsigned long *);
 	int (*migratepage)(struct address_space *, struct page *, struct page *);
 	int (*launder_page)(struct page *);
-	int (*is_partially_uptodate)(struct page *, read_descriptor_t *, unsigned long);
+	int (*is_partially_uptodate)(struct page *, unsigned long, unsigned long);
 	int (*error_remove_page)(struct address_space *, struct page *);
 	int (*swap_activate)(struct file *);
 	int (*swap_deactivate)(struct file *);

Documentation/filesystems/vfs.txt

@@ -596,7 +596,7 @@ struct address_space_operations {
 	/* migrate the contents of a page to the specified target */
 	int (*migratepage) (struct page *, struct page *);
 	int (*launder_page) (struct page *);
-	int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
+	int (*is_partially_uptodate) (struct page *, unsigned long,
 					unsigned long);
 	void (*is_dirty_writeback) (struct page *, bool *, bool *);
 	int (*error_remove_page) (struct mapping *mapping, struct page *page);

arch/mn10300/include/asm/highmem.h

@@ -70,7 +70,7 @@ static inline void kunmap(struct page *page)
  * be used in IRQ contexts, so in some (very limited) cases we need
  * it.
  */
-static inline unsigned long kmap_atomic(struct page *page)
+static inline void *kmap_atomic(struct page *page)
 {
 	unsigned long vaddr;
 	int idx, type;
@@ -89,7 +89,7 @@ static inline unsigned long kmap_atomic(struct page *page)
 	set_pte(kmap_pte - idx, mk_pte(page, kmap_prot));
 	local_flush_tlb_one(vaddr);
 
-	return vaddr;
+	return (void *)vaddr;
 }
 
 static inline void __kunmap_atomic(unsigned long vaddr)

arch/powerpc/configs/ppc6xx_defconfig

@@ -1244,7 +1244,6 @@ CONFIG_DEBUG_SPINLOCK_SLEEP=y
 CONFIG_DEBUG_HIGHMEM=y
 CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_VM=y
-CONFIG_DEBUG_WRITECOUNT=y
 CONFIG_DEBUG_LIST=y
 CONFIG_DEBUG_SG=y
 # CONFIG_RCU_CPU_STALL_DETECTOR is not set

arch/powerpc/configs/ps3_defconfig

@@ -174,7 +174,6 @@ CONFIG_DETECT_HUNG_TASK=y
 CONFIG_PROVE_LOCKING=y
 CONFIG_DEBUG_LOCKDEP=y
 CONFIG_DEBUG_INFO=y
-CONFIG_DEBUG_WRITECOUNT=y
 CONFIG_DEBUG_MEMORY_INIT=y
 CONFIG_DEBUG_LIST=y
 CONFIG_RCU_CPU_STALL_TIMEOUT=60

arch/s390/configs/default_defconfig

@@ -581,7 +581,6 @@ CONFIG_LOCK_STAT=y
 CONFIG_DEBUG_LOCKDEP=y
 CONFIG_DEBUG_ATOMIC_SLEEP=y
 CONFIG_DEBUG_LOCKING_API_SELFTESTS=y
-CONFIG_DEBUG_WRITECOUNT=y
 CONFIG_DEBUG_LIST=y
 CONFIG_DEBUG_SG=y
 CONFIG_DEBUG_NOTIFIERS=y

arch/sh/configs/rsk7203_defconfig

@@ -128,7 +128,6 @@ CONFIG_DEBUG_MUTEXES=y
 CONFIG_DEBUG_SPINLOCK_SLEEP=y
 CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_VM=y
-CONFIG_DEBUG_WRITECOUNT=y
 CONFIG_DEBUG_LIST=y
 CONFIG_DEBUG_SG=y
 CONFIG_FRAME_POINTER=y

arch/xtensa/configs/iss_defconfig

@@ -627,7 +627,6 @@ CONFIG_SCHED_DEBUG=y
 # CONFIG_DEBUG_KOBJECT is not set
 # CONFIG_DEBUG_INFO is not set
 # CONFIG_DEBUG_VM is not set
-# CONFIG_DEBUG_WRITECOUNT is not set
 # CONFIG_DEBUG_MEMORY_INIT is not set
 # CONFIG_DEBUG_LIST is not set
 # CONFIG_DEBUG_SG is not set

arch/xtensa/configs/s6105_defconfig

@@ -569,7 +569,6 @@ CONFIG_DEBUG_SPINLOCK_SLEEP=y
 # CONFIG_DEBUG_INFO is not set
 # CONFIG_DEBUG_VM is not set
 CONFIG_DEBUG_NOMMU_REGIONS=y
-# CONFIG_DEBUG_WRITECOUNT is not set
 # CONFIG_DEBUG_MEMORY_INIT is not set
 # CONFIG_DEBUG_LIST is not set
 # CONFIG_DEBUG_SG is not set

block/blk-map.c

@@ -188,7 +188,7 @@ EXPORT_SYMBOL(blk_rq_map_user);
  *    unmapping.
  */
 int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
-			struct rq_map_data *map_data, struct sg_iovec *iov,
+			struct rq_map_data *map_data, const struct sg_iovec *iov,
 			int iov_count, unsigned int len, gfp_t gfp_mask)
 {
 	struct bio *bio;

drivers/block/drbd/drbd_receiver.c

@@ -469,24 +469,14 @@ static void drbd_wait_ee_list_empty(struct drbd_device *device,
 
 static int drbd_recv_short(struct socket *sock, void *buf, size_t size, int flags)
 {
-	mm_segment_t oldfs;
 	struct kvec iov = {
 		.iov_base = buf,
 		.iov_len = size,
 	};
 	struct msghdr msg = {
-		.msg_iovlen = 1,
-		.msg_iov = (struct iovec *)&iov,
 		.msg_flags = (flags ? flags : MSG_WAITALL | MSG_NOSIGNAL)
 	};
-	int rv;
-
-	oldfs = get_fs();
-	set_fs(KERNEL_DS);
-	rv = sock_recvmsg(sock, &msg, size, msg.msg_flags);
-	set_fs(oldfs);
-
-	return rv;
+	return kernel_recvmsg(sock, &msg, &iov, 1, size, msg.msg_flags);
 }
 
 static int drbd_recv(struct drbd_connection *connection, void *buf, size_t size)

drivers/block/nbd.c

@@ -630,37 +630,29 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 	}
  
 	case NBD_CLEAR_SOCK: {
-		struct file *file;
-
+		struct socket *sock = nbd->sock;
 		nbd->sock = NULL;
-		file = nbd->file;
-		nbd->file = NULL;
 		nbd_clear_que(nbd);
 		BUG_ON(!list_empty(&nbd->queue_head));
 		BUG_ON(!list_empty(&nbd->waiting_queue));
 		kill_bdev(bdev);
-		if (file)
-			fput(file);
+		if (sock)
+			sockfd_put(sock);
 		return 0;
 	}
 
 	case NBD_SET_SOCK: {
-		struct file *file;
-		if (nbd->file)
+		struct socket *sock;
+		int err;
+		if (nbd->sock)
 			return -EBUSY;
-		file = fget(arg);
-		if (file) {
-			struct inode *inode = file_inode(file);
-			if (S_ISSOCK(inode->i_mode)) {
-				nbd->file = file;
-				nbd->sock = SOCKET_I(inode);
-				if (max_part > 0)
-					bdev->bd_invalidated = 1;
-				nbd->disconnect = 0; /* we're connected now */
-				return 0;
-			} else {
-				fput(file);
-			}
+		sock = sockfd_lookup(arg, &err);
+		if (sock) {
+			nbd->sock = sock;
+			if (max_part > 0)
+				bdev->bd_invalidated = 1;
+			nbd->disconnect = 0; /* we're connected now */
+			return 0;
 		}
 		return -EINVAL;
 	}
@@ -697,12 +689,12 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 
 	case NBD_DO_IT: {
 		struct task_struct *thread;
-		struct file *file;
+		struct socket *sock;
 		int error;
 
 		if (nbd->pid)
 			return -EBUSY;
-		if (!nbd->file)
+		if (!nbd->sock)
 			return -EINVAL;
 
 		mutex_unlock(&nbd->tx_lock);
@@ -731,15 +723,15 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 		if (error)
 			return error;
 		sock_shutdown(nbd, 0);
-		file = nbd->file;
-		nbd->file = NULL;
+		sock = nbd->sock;
+		nbd->sock = NULL;
 		nbd_clear_que(nbd);
 		dev_warn(disk_to_dev(nbd->disk), "queue cleared\n");
 		kill_bdev(bdev);
 		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, nbd->disk->queue);
 		set_device_ro(bdev, false);
-		if (file)
-			fput(file);
+		if (sock)
+			sockfd_put(sock);
 		nbd->flags = 0;
 		nbd->bytesize = 0;
 		bdev->bd_inode->i_size = 0;
@@ -875,9 +867,7 @@ static int __init nbd_init(void)
 
 	for (i = 0; i < nbds_max; i++) {
 		struct gendisk *disk = nbd_dev[i].disk;
-		nbd_dev[i].file = NULL;
 		nbd_dev[i].magic = NBD_MAGIC;
-		nbd_dev[i].flags = 0;
 		INIT_LIST_HEAD(&nbd_dev[i].waiting_queue);
 		spin_lock_init(&nbd_dev[i].queue_lock);
 		INIT_LIST_HEAD(&nbd_dev[i].queue_head);

drivers/char/virtio_console.c

@@ -901,9 +901,9 @@ static int pipe_to_sg(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 		if (len + offset > PAGE_SIZE)
 			len = PAGE_SIZE - offset;
 
-		src = buf->ops->map(pipe, buf, 1);
+		src = kmap_atomic(buf->page);
 		memcpy(page_address(page) + offset, src + buf->offset, len);
-		buf->ops->unmap(pipe, buf, src);
+		kunmap_atomic(src);
 
 		sg_set_page(&(sgl->sg[sgl->n]), page, len, offset);
 	}

drivers/staging/lustre/lnet/klnds/socklnd/socklnd_lib-linux.c

@@ -99,16 +99,7 @@ ksocknal_lib_send_iov (ksock_conn_t *conn, ksock_tx_t *tx)
 		struct iovec   *scratchiov = conn->ksnc_scheduler->kss_scratch_iov;
 		unsigned int    niov = tx->tx_niov;
 #endif
-		struct msghdr msg = {
-			.msg_name       = NULL,
-			.msg_namelen    = 0,
-			.msg_iov	= scratchiov,
-			.msg_iovlen     = niov,
-			.msg_control    = NULL,
-			.msg_controllen = 0,
-			.msg_flags      = MSG_DONTWAIT
-		};
-		mm_segment_t oldmm = get_fs();
+		struct msghdr msg = {.msg_flags = MSG_DONTWAIT};
 		int  i;
 
 		for (nob = i = 0; i < niov; i++) {
@@ -120,9 +111,7 @@ ksocknal_lib_send_iov (ksock_conn_t *conn, ksock_tx_t *tx)
 		    nob < tx->tx_resid)
 			msg.msg_flags |= MSG_MORE;
 
-		set_fs (KERNEL_DS);
-		rc = sock_sendmsg(sock, &msg, nob);
-		set_fs (oldmm);
+		rc = kernel_sendmsg(sock, &msg, (struct kvec *)scratchiov, niov, nob);
 	}
 	return rc;
 }
@@ -174,16 +163,7 @@ ksocknal_lib_send_kiov (ksock_conn_t *conn, ksock_tx_t *tx)
 		struct iovec *scratchiov = conn->ksnc_scheduler->kss_scratch_iov;
 		unsigned int  niov = tx->tx_nkiov;
 #endif
-		struct msghdr msg = {
-			.msg_name       = NULL,
-			.msg_namelen    = 0,
-			.msg_iov	= scratchiov,
-			.msg_iovlen     = niov,
-			.msg_control    = NULL,
-			.msg_controllen = 0,
-			.msg_flags      = MSG_DONTWAIT
-		};
-		mm_segment_t  oldmm = get_fs();
+		struct msghdr msg = {.msg_flags = MSG_DONTWAIT};
 		int	   i;
 
 		for (nob = i = 0; i < niov; i++) {
@@ -196,9 +176,7 @@ ksocknal_lib_send_kiov (ksock_conn_t *conn, ksock_tx_t *tx)
 		    nob < tx->tx_resid)
 			msg.msg_flags |= MSG_MORE;
 
-		set_fs (KERNEL_DS);
-		rc = sock_sendmsg(sock, &msg, nob);
-		set_fs (oldmm);
+		rc = kernel_sendmsg(sock, &msg, (struct kvec *)scratchiov, niov, nob);
 
 		for (i = 0; i < niov; i++)
 			kunmap(kiov[i].kiov_page);
@@ -237,15 +215,8 @@ ksocknal_lib_recv_iov (ksock_conn_t *conn)
 #endif
 	struct iovec *iov = conn->ksnc_rx_iov;
 	struct msghdr msg = {
-		.msg_name       = NULL,
-		.msg_namelen    = 0,
-		.msg_iov	= scratchiov,
-		.msg_iovlen     = niov,
-		.msg_control    = NULL,
-		.msg_controllen = 0,
 		.msg_flags      = 0
 	};
-	mm_segment_t oldmm = get_fs();
 	int	  nob;
 	int	  i;
 	int	  rc;
@@ -263,10 +234,8 @@ ksocknal_lib_recv_iov (ksock_conn_t *conn)
 	}
 	LASSERT (nob <= conn->ksnc_rx_nob_wanted);
 
-	set_fs (KERNEL_DS);
-	rc = sock_recvmsg (conn->ksnc_sock, &msg, nob, MSG_DONTWAIT);
-	/* NB this is just a boolean..........................^ */
-	set_fs (oldmm);
+	rc = kernel_recvmsg(conn->ksnc_sock, &msg,
+		(struct kvec *)scratchiov, niov, nob, MSG_DONTWAIT);
 
 	saved_csum = 0;
 	if (conn->ksnc_proto == &ksocknal_protocol_v2x) {
@@ -355,14 +324,8 @@ ksocknal_lib_recv_kiov (ksock_conn_t *conn)
 #endif
 	lnet_kiov_t   *kiov = conn->ksnc_rx_kiov;
 	struct msghdr msg = {
-		.msg_name       = NULL,
-		.msg_namelen    = 0,
-		.msg_iov	= scratchiov,
-		.msg_control    = NULL,
-		.msg_controllen = 0,
 		.msg_flags      = 0
 	};
-	mm_segment_t oldmm = get_fs();
 	int	  nob;
 	int	  i;
 	int	  rc;
@@ -370,13 +333,14 @@ ksocknal_lib_recv_kiov (ksock_conn_t *conn)
 	void	*addr;
 	int	  sum;
 	int	  fragnob;
+	int n;
 
 	/* NB we can't trust socket ops to either consume our iovs
 	 * or leave them alone. */
 	addr = ksocknal_lib_kiov_vmap(kiov, niov, scratchiov, pages);
 	if (addr != NULL) {
 		nob = scratchiov[0].iov_len;
-		msg.msg_iovlen = 1;
+		n = 1;
 
 	} else {
 		for (nob = i = 0; i < niov; i++) {
@@ -384,15 +348,13 @@ ksocknal_lib_recv_kiov (ksock_conn_t *conn)
 			scratchiov[i].iov_base = kmap(kiov[i].kiov_page) +
 						 kiov[i].kiov_offset;
 		}
-		msg.msg_iovlen = niov;
+		n = niov;
 	}
 
 	LASSERT (nob <= conn->ksnc_rx_nob_wanted);
 
-	set_fs (KERNEL_DS);
-	rc = sock_recvmsg (conn->ksnc_sock, &msg, nob, MSG_DONTWAIT);
-	/* NB this is just a boolean.......................^ */
-	set_fs (oldmm);
+	rc = kernel_recvmsg(conn->ksnc_sock, &msg,
+			(struct kvec *)scratchiov, n, nob, MSG_DONTWAIT);
 
 	if (conn->ksnc_msg.ksm_csum != 0) {
 		for (i = 0, sum = rc; sum > 0; i++, sum -= fragnob) {

drivers/staging/lustre/lustre/libcfs/linux/linux-tcpip.c

@@ -265,17 +265,11 @@ libcfs_sock_write (struct socket *sock, void *buffer, int nob, int timeout)
 	 * empty enough to take the whole message immediately */
 
 	for (;;) {
-		struct iovec  iov = {
+		struct kvec  iov = {
 			.iov_base = buffer,
 			.iov_len  = nob
 		};
 		struct msghdr msg = {
-			.msg_name       = NULL,
-			.msg_namelen    = 0,
-			.msg_iov	= &iov,
-			.msg_iovlen     = 1,
-			.msg_control    = NULL,
-			.msg_controllen = 0,
 			.msg_flags      = (timeout == 0) ? MSG_DONTWAIT : 0
 		};
 
@@ -297,11 +291,9 @@ libcfs_sock_write (struct socket *sock, void *buffer, int nob, int timeout)
 			}
 		}
 
-		set_fs (KERNEL_DS);
 		then = jiffies;
-		rc = sock_sendmsg (sock, &msg, iov.iov_len);
+		rc = kernel_sendmsg(sock, &msg, &iov, 1, nob);
 		ticks -= jiffies - then;
-		set_fs (oldmm);
 
 		if (rc == nob)
 			return 0;
@@ -338,17 +330,11 @@ libcfs_sock_read (struct socket *sock, void *buffer, int nob, int timeout)
 	LASSERT (ticks > 0);
 
 	for (;;) {
-		struct iovec  iov = {
+		struct kvec  iov = {
 			.iov_base = buffer,
 			.iov_len  = nob
 		};
 		struct msghdr msg = {
-			.msg_name       = NULL,
-			.msg_namelen    = 0,
-			.msg_iov	= &iov,
-			.msg_iovlen     = 1,
-			.msg_control    = NULL,
-			.msg_controllen = 0,
 			.msg_flags      = 0
 		};
 
@@ -367,11 +353,9 @@ libcfs_sock_read (struct socket *sock, void *buffer, int nob, int timeout)
 			return rc;
 		}
 
-		set_fs(KERNEL_DS);
 		then = jiffies;
-		rc = sock_recvmsg(sock, &msg, iov.iov_len, 0);
+		rc = kernel_recvmsg(sock, &msg, &iov, 1, nob, 0);
 		ticks -= jiffies - then;
-		set_fs(oldmm);
 
 		if (rc < 0)
 			return rc;

drivers/staging/lustre/lustre/llite/symlink.c

@@ -115,27 +115,6 @@ failed:
 	return rc;
 }
 
-static int ll_readlink(struct dentry *dentry, char *buffer, int buflen)
-{
-	struct inode *inode = dentry->d_inode;
-	struct ptlrpc_request *request;
-	char *symname;
-	int rc;
-
-	CDEBUG(D_VFSTRACE, "VFS Op\n");
-
-	ll_inode_size_lock(inode);
-	rc = ll_readlink_internal(inode, &request, &symname);
-	if (rc)
-		GOTO(out, rc);
-
-	rc = vfs_readlink(dentry, buffer, buflen, symname);
- out:
-	ptlrpc_req_finished(request);
-	ll_inode_size_unlock(inode);
-	return rc;
-}
-
 static void *ll_follow_link(struct dentry *dentry, struct nameidata *nd)
 {
 	struct inode *inode = dentry->d_inode;
@@ -175,7 +154,7 @@ static void ll_put_link(struct dentry *dentry, struct nameidata *nd, void *cooki
 }
 
 struct inode_operations ll_fast_symlink_inode_operations = {
-	.readlink	= ll_readlink,
+	.readlink	= generic_readlink,
 	.setattr	= ll_setattr,
 	.follow_link	= ll_follow_link,
 	.put_link	= ll_put_link,

drivers/staging/usbip/stub_dev.c

@@ -86,7 +86,6 @@ static ssize_t store_sockfd(struct device *dev, struct device_attribute *attr,
 	struct stub_device *sdev = dev_get_drvdata(dev);
 	int sockfd = 0;
 	struct socket *socket;
-	ssize_t err = -EINVAL;
 	int rv;
 
 	if (!sdev) {
@@ -99,6 +98,7 @@ static ssize_t store_sockfd(struct device *dev, struct device_attribute *attr,
 		return -EINVAL;
 
 	if (sockfd != -1) {
+		int err;
 		dev_info(dev, "stub up\n");
 
 		spin_lock_irq(&sdev->ud.lock);
@@ -108,7 +108,7 @@ static ssize_t store_sockfd(struct device *dev, struct device_attribute *attr,
 			goto err;
 		}
 
-		socket = sockfd_to_socket(sockfd);
+		socket = sockfd_lookup(sockfd, &err);
 		if (!socket)
 			goto err;
 
@@ -141,7 +141,7 @@ static ssize_t store_sockfd(struct device *dev, struct device_attribute *attr,
 
 err:
 	spin_unlock_irq(&sdev->ud.lock);
-	return err;
+	return -EINVAL;
 }
 static DEVICE_ATTR(usbip_sockfd, S_IWUSR, NULL, store_sockfd);
 
@@ -211,7 +211,7 @@ static void stub_shutdown_connection(struct usbip_device *ud)
 	 * not touch NULL socket.
 	 */
 	if (ud->tcp_socket) {
-		fput(ud->tcp_socket->file);
+		sockfd_put(ud->tcp_socket);
 		ud->tcp_socket = NULL;
 	}
 

drivers/staging/usbip/usbip_common.c

@@ -382,31 +382,6 @@ err:
 }
 EXPORT_SYMBOL_GPL(usbip_recv);
 
-struct socket *sockfd_to_socket(unsigned int sockfd)
-{
-	struct socket *socket;
-	struct file *file;
-	struct inode *inode;
-
-	file = fget(sockfd);
-	if (!file) {
-		pr_err("invalid sockfd\n");
-		return NULL;
-	}
-
-	inode = file_inode(file);
-
-	if (!inode || !S_ISSOCK(inode->i_mode)) {
-		fput(file);
-		return NULL;
-	}
-
-	socket = SOCKET_I(inode);
-
-	return socket;
-}
-EXPORT_SYMBOL_GPL(sockfd_to_socket);
-
 /* there may be more cases to tweak the flags. */
 static unsigned int tweak_transfer_flags(unsigned int flags)
 {

drivers/staging/usbip/usbip_common.h

@@ -299,7 +299,6 @@ void usbip_dump_urb(struct urb *purb);
 void usbip_dump_header(struct usbip_header *pdu);
 
 int usbip_recv(struct socket *sock, void *buf, int size);
-struct socket *sockfd_to_socket(unsigned int sockfd);
 
 void usbip_pack_pdu(struct usbip_header *pdu, struct urb *urb, int cmd,
 		    int pack);

drivers/staging/usbip/vhci_hcd.c

@@ -788,7 +788,7 @@ static void vhci_shutdown_connection(struct usbip_device *ud)
 
 	/* active connection is closed */
 	if (vdev->ud.tcp_socket) {
-		fput(vdev->ud.tcp_socket->file);
+		sockfd_put(vdev->ud.tcp_socket);
 		vdev->ud.tcp_socket = NULL;
 	}
 	pr_info("release socket\n");
@@ -835,7 +835,7 @@ static void vhci_device_reset(struct usbip_device *ud)
 	vdev->udev = NULL;
 
 	if (ud->tcp_socket) {
-		fput(ud->tcp_socket->file);
+		sockfd_put(ud->tcp_socket);
 		ud->tcp_socket = NULL;
 	}
 	ud->status = VDEV_ST_NULL;

drivers/staging/usbip/vhci_sysfs.c

@@ -176,6 +176,7 @@ static ssize_t store_attach(struct device *dev, struct device_attribute *attr,
 	struct socket *socket;
 	int sockfd = 0;
 	__u32 rhport = 0, devid = 0, speed = 0;
+	int err;
 
 	/*
 	 * @rhport: port number of vhci_hcd
@@ -194,8 +195,7 @@ static ssize_t store_attach(struct device *dev, struct device_attribute *attr,
 		return -EINVAL;
 
 	/* Extract socket from fd. */
-	/* The correct way to clean this up is to fput(socket->file). */
-	socket = sockfd_to_socket(sockfd);
+	socket = sockfd_lookup(sockfd, &err);
 	if (!socket)
 		return -EINVAL;
 
@@ -211,7 +211,7 @@ static ssize_t store_attach(struct device *dev, struct device_attribute *attr,
 		spin_unlock(&vdev->ud.lock);
 		spin_unlock(&the_controller->lock);
 
-		fput(socket->file);
+		sockfd_put(socket);
 
 		dev_err(dev, "port %d already used\n", rhport);
 		return -EINVAL;

drivers/vhost/net.c

@@ -818,9 +818,9 @@ static int vhost_net_release(struct inode *inode, struct file *f)
 	vhost_dev_cleanup(&n->dev, false);
 	vhost_net_vq_reset(n);
 	if (tx_sock)
-		fput(tx_sock->file);
+		sockfd_put(tx_sock);
 	if (rx_sock)
-		fput(rx_sock->file);
+		sockfd_put(rx_sock);
 	/* Make sure no callbacks are outstanding */
 	synchronize_rcu_bh();
 	/* We do an extra flush before freeing memory,
@@ -860,7 +860,7 @@ static struct socket *get_raw_socket(int fd)
 	}
 	return sock;
 err:
-	fput(sock->file);
+	sockfd_put(sock);
 	return ERR_PTR(r);
 }
 
@@ -966,7 +966,7 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
 
 	if (oldsock) {
 		vhost_net_flush_vq(n, index);
-		fput(oldsock->file);
+		sockfd_put(oldsock);
 	}
 
 	mutex_unlock(&n->dev.mutex);
@@ -978,7 +978,7 @@ err_used:
 	if (ubufs)
 		vhost_net_ubuf_put_wait_and_free(ubufs);
 err_ubufs:
-	fput(sock->file);
+	sockfd_put(sock);
 err_vq:
 	mutex_unlock(&vq->mutex);
 err:
@@ -1009,9 +1009,9 @@ static long vhost_net_reset_owner(struct vhost_net *n)
 done:
 	mutex_unlock(&n->dev.mutex);
 	if (tx_sock)
-		fput(tx_sock->file);
+		sockfd_put(tx_sock);
 	if (rx_sock)
-		fput(rx_sock->file);
+		sockfd_put(rx_sock);
 	return err;
 }
 

fs/bio.c

@@ -1002,7 +1002,7 @@ struct bio_map_data {
 };
 
 static void bio_set_map_data(struct bio_map_data *bmd, struct bio *bio,
-			     struct sg_iovec *iov, int iov_count,
+			     const struct sg_iovec *iov, int iov_count,
 			     int is_our_pages)
 {
 	memcpy(bmd->sgvecs, iov, sizeof(struct sg_iovec) * iov_count);
@@ -1022,7 +1022,7 @@ static struct bio_map_data *bio_alloc_map_data(int nr_segs,
 		       sizeof(struct sg_iovec) * iov_count, gfp_mask);
 }
 
-static int __bio_copy_iov(struct bio *bio, struct sg_iovec *iov, int iov_count,
+static int __bio_copy_iov(struct bio *bio, const struct sg_iovec *iov, int iov_count,
 			  int to_user, int from_user, int do_free_page)
 {
 	int ret = 0, i;
@@ -1120,7 +1120,7 @@ EXPORT_SYMBOL(bio_uncopy_user);
  */
 struct bio *bio_copy_user_iov(struct request_queue *q,
 			      struct rq_map_data *map_data,
-			      struct sg_iovec *iov, int iov_count,
+			      const struct sg_iovec *iov, int iov_count,
 			      int write_to_vm, gfp_t gfp_mask)
 {
 	struct bio_map_data *bmd;
@@ -1259,7 +1259,7 @@ EXPORT_SYMBOL(bio_copy_user);
 
 static struct bio *__bio_map_user_iov(struct request_queue *q,
 				      struct block_device *bdev,
-				      struct sg_iovec *iov, int iov_count,
+				      const struct sg_iovec *iov, int iov_count,
 				      int write_to_vm, gfp_t gfp_mask)
 {
 	int i, j;
@@ -1407,7 +1407,7 @@ EXPORT_SYMBOL(bio_map_user);
  *	device. Returns an error pointer in case of error.
  */
 struct bio *bio_map_user_iov(struct request_queue *q, struct block_device *bdev,
-			     struct sg_iovec *iov, int iov_count,
+			     const struct sg_iovec *iov, int iov_count,
 			     int write_to_vm, gfp_t gfp_mask)
 {
 	struct bio *bio;

fs/block_dev.c

@@ -1518,7 +1518,7 @@ ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	BUG_ON(iocb->ki_pos != pos);
 
 	blk_start_plug(&plug);
-	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+	ret = __generic_file_aio_write(iocb, iov, nr_segs);
 	if (ret > 0) {
 		ssize_t err;
 

fs/btrfs/file.c

@@ -425,13 +425,8 @@ static noinline int btrfs_copy_from_user(loff_t pos, int num_pages,
 		struct page *page = prepared_pages[pg];
 		/*
 		 * Copy data from userspace to the current page
-		 *
-		 * Disable pagefault to avoid recursive lock since
-		 * the pages are already locked
 		 */
-		pagefault_disable();
 		copied = iov_iter_copy_from_user_atomic(page, i, offset, count);
-		pagefault_enable();
 
 		/* Flush processor's dcache for this page */
 		flush_dcache_page(page);
@@ -1665,7 +1660,7 @@ again:
 static ssize_t __btrfs_direct_write(struct kiocb *iocb,
 				    const struct iovec *iov,
 				    unsigned long nr_segs, loff_t pos,
-				    loff_t *ppos, size_t count, size_t ocount)
+				    size_t count, size_t ocount)
 {
 	struct file *file = iocb->ki_filp;
 	struct iov_iter i;
@@ -1674,7 +1669,7 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb,
 	loff_t endbyte;
 	int err;
 
-	written = generic_file_direct_write(iocb, iov, &nr_segs, pos, ppos,
+	written = generic_file_direct_write(iocb, iov, &nr_segs, pos,
 					    count, ocount);
 
 	if (written < 0 || written == count)
@@ -1693,7 +1688,7 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb,
 	if (err)
 		goto out;
 	written += written_buffered;
-	*ppos = pos + written_buffered;
+	iocb->ki_pos = pos + written_buffered;
 	invalidate_mapping_pages(file->f_mapping, pos >> PAGE_CACHE_SHIFT,
 				 endbyte >> PAGE_CACHE_SHIFT);
 out:
@@ -1725,7 +1720,6 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	loff_t *ppos = &iocb->ki_pos;
 	u64 start_pos;
 	u64 end_pos;
 	ssize_t num_written = 0;
@@ -1796,7 +1790,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 
 	if (unlikely(file->f_flags & O_DIRECT)) {
 		num_written = __btrfs_direct_write(iocb, iov, nr_segs,
-						   pos, ppos, count, ocount);
+						   pos, count, ocount);
 	} else {
 		struct iov_iter i;
 
@@ -1804,7 +1798,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 
 		num_written = __btrfs_buffered_write(file, &i, pos);
 		if (num_written > 0)
-			*ppos = pos + num_written;
+			iocb->ki_pos = pos + num_written;
 	}
 
 	mutex_unlock(&inode->i_mutex);

fs/buffer.c

@@ -2114,8 +2114,8 @@ EXPORT_SYMBOL(generic_write_end);
  * Returns true if all buffers which correspond to a file portion
  * we want to read are uptodate.
  */
-int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
-					unsigned long from)
+int block_is_partially_uptodate(struct page *page, unsigned long from,
+					unsigned long count)
 {
 	unsigned block_start, block_end, blocksize;
 	unsigned to;
@@ -2127,7 +2127,7 @@ int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
 
 	head = page_buffers(page);
 	blocksize = head->b_size;
-	to = min_t(unsigned, PAGE_CACHE_SIZE - from, desc->count);
+	to = min_t(unsigned, PAGE_CACHE_SIZE - from, count);
 	to = from + to;
 	if (from < blocksize && to > PAGE_CACHE_SIZE - blocksize)
 		return 0;

fs/cachefiles/bind.c

@@ -124,7 +124,6 @@ static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache)
 	/* check parameters */
 	ret = -EOPNOTSUPP;
 	if (!root->d_inode ||
-	    !root->d_inode->i_op ||
 	    !root->d_inode->i_op->lookup ||
 	    !root->d_inode->i_op->mkdir ||
 	    !root->d_inode->i_op->setxattr ||

fs/cachefiles/namei.c

@@ -779,8 +779,7 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
 	}
 
 	ret = -EPERM;
-	if (!subdir->d_inode->i_op ||
-	    !subdir->d_inode->i_op->setxattr ||
+	if (!subdir->d_inode->i_op->setxattr ||
 	    !subdir->d_inode->i_op->getxattr ||
 	    !subdir->d_inode->i_op->lookup ||
 	    !subdir->d_inode->i_op->mkdir ||

fs/ceph/file.c

@@ -601,7 +601,7 @@ ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov,
 					    false);
 		if (IS_ERR(req)) {
 			ret = PTR_ERR(req);
-			goto out;
+			break;
 		}
 
 		num_pages = calc_pages_for(page_align, len);
@@ -719,7 +719,7 @@ static ssize_t ceph_sync_write(struct kiocb *iocb, const struct iovec *iov,
 					    false);
 		if (IS_ERR(req)) {
 			ret = PTR_ERR(req);
-			goto out;
+			break;
 		}
 
 		/*
@@ -972,6 +972,7 @@ retry_snap:
 		}
 	} else {
 		loff_t old_size = inode->i_size;
+		struct iov_iter from;
 		/*
 		 * No need to acquire the i_truncate_mutex. Because
 		 * the MDS revokes Fwb caps before sending truncate
@@ -979,9 +980,10 @@ retry_snap:
 		 * are pending vmtruncate. So write and vmtruncate
 		 * can not run at the same time
 		 */
-		written = generic_file_buffered_write(iocb, iov, nr_segs,
-						      pos, &iocb->ki_pos,
-						      count, 0);
+		iov_iter_init(&from, iov, nr_segs, count, 0);
+		written = generic_perform_write(file, &from, pos);
+		if (likely(written >= 0))
+			iocb->ki_pos = pos + written;
 		if (inode->i_size > old_size)
 			ceph_fscache_update_objectsize(inode);
 		mutex_unlock(&inode->i_mutex);

fs/cifs/cifsfs.c

@@ -850,7 +850,6 @@ const struct inode_operations cifs_file_inode_ops = {
 /*	revalidate:cifs_revalidate, */
 	.setattr = cifs_setattr,
 	.getattr = cifs_getattr, /* do we need this anymore? */
-	.rename = cifs_rename,
 	.permission = cifs_permission,
 #ifdef CONFIG_CIFS_XATTR
 	.setxattr = cifs_setxattr,

fs/cifs/file.c

@@ -2579,19 +2579,32 @@ cifs_writev(struct kiocb *iocb, const struct iovec *iov,
 	struct cifsInodeInfo *cinode = CIFS_I(inode);
 	struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server;
 	ssize_t rc = -EACCES;
-	loff_t lock_pos = pos;
+	loff_t lock_pos = iocb->ki_pos;
 
-	if (file->f_flags & O_APPEND)
-		lock_pos = i_size_read(inode);
 	/*
 	 * We need to hold the sem to be sure nobody modifies lock list
 	 * with a brlock that prevents writing.
 	 */
 	down_read(&cinode->lock_sem);
+	mutex_lock(&inode->i_mutex);
+	if (file->f_flags & O_APPEND)
+		lock_pos = i_size_read(inode);
 	if (!cifs_find_lock_conflict(cfile, lock_pos, iov_length(iov, nr_segs),
 				     server->vals->exclusive_lock_type, NULL,
-				     CIFS_WRITE_OP))
-		rc = generic_file_aio_write(iocb, iov, nr_segs, pos);
+				     CIFS_WRITE_OP)) {
+		rc = __generic_file_aio_write(iocb, iov, nr_segs);
+		mutex_unlock(&inode->i_mutex);
+
+		if (rc > 0) {
+			ssize_t err;
+
+			err = generic_write_sync(file, iocb->ki_pos - rc, rc);
+			if (rc < 0)
+				rc = err;
+		}
+	} else {
+		mutex_unlock(&inode->i_mutex);
+	}
 	up_read(&cinode->lock_sem);
 	return rc;
 }
@@ -2727,56 +2740,27 @@ cifs_retry_async_readv(struct cifs_readdata *rdata)
 /**
  * cifs_readdata_to_iov - copy data from pages in response to an iovec
  * @rdata:	the readdata response with list of pages holding data
- * @iov:	vector in which we should copy the data
- * @nr_segs:	number of segments in vector
- * @offset:	offset into file of the first iovec
- * @copied:	used to return the amount of data copied to the iov
+ * @iter:	destination for our data
  *
  * This function copies data from a list of pages in a readdata response into
  * an array of iovecs. It will first calculate where the data should go
  * based on the info in the readdata and then copy the data into that spot.
  */
-static ssize_t
-cifs_readdata_to_iov(struct cifs_readdata *rdata, const struct iovec *iov,
-			unsigned long nr_segs, loff_t offset, ssize_t *copied)
+static int
+cifs_readdata_to_iov(struct cifs_readdata *rdata, struct iov_iter *iter)
 {
-	int rc = 0;
-	struct iov_iter ii;
-	size_t pos = rdata->offset - offset;
-	ssize_t remaining = rdata->bytes;
-	unsigned char *pdata;
+	size_t remaining = rdata->bytes;
 	unsigned int i;
 
-	/* set up iov_iter and advance to the correct offset */
-	iov_iter_init(&ii, iov, nr_segs, iov_length(iov, nr_segs), 0);
-	iov_iter_advance(&ii, pos);
-
-	*copied = 0;
 	for (i = 0; i < rdata->nr_pages; i++) {
-		ssize_t copy;
 		struct page *page = rdata->pages[i];
-
-		/* copy a whole page or whatever's left */
-		copy = min_t(ssize_t, remaining, PAGE_SIZE);
-
-		/* ...but limit it to whatever space is left in the iov */
-		copy = min_t(ssize_t, copy, iov_iter_count(&ii));
-
-		/* go while there's data to be copied and no errors */
-		if (copy && !rc) {
-			pdata = kmap(page);
-			rc = memcpy_toiovecend(ii.iov, pdata, ii.iov_offset,
-						(int)copy);
-			kunmap(page);
-			if (!rc) {
-				*copied += copy;
-				remaining -= copy;
-				iov_iter_advance(&ii, copy);
-			}
-		}
+		size_t copy = min(remaining, PAGE_SIZE);
+		size_t written = copy_page_to_iter(page, 0, copy, iter);
+		remaining -= written;
+		if (written < copy && iov_iter_count(iter) > 0)
+			break;
 	}
-
-	return rc;
+	return remaining ? -EFAULT : 0;
 }
 
 static void
@@ -2837,20 +2821,21 @@ cifs_uncached_read_into_pages(struct TCP_Server_Info *server,
 	return total_read > 0 ? total_read : result;
 }
 
-static ssize_t
-cifs_iovec_read(struct file *file, const struct iovec *iov,
-		 unsigned long nr_segs, loff_t *poffset)
+ssize_t cifs_user_readv(struct kiocb *iocb, const struct iovec *iov,
+			       unsigned long nr_segs, loff_t pos)
 {
+	struct file *file = iocb->ki_filp;
 	ssize_t rc;
 	size_t len, cur_len;
 	ssize_t total_read = 0;
-	loff_t offset = *poffset;
+	loff_t offset = pos;
 	unsigned int npages;
 	struct cifs_sb_info *cifs_sb;
 	struct cifs_tcon *tcon;
 	struct cifsFileInfo *open_file;
 	struct cifs_readdata *rdata, *tmp;
 	struct list_head rdata_list;
+	struct iov_iter to;
 	pid_t pid;
 
 	if (!nr_segs)
@@ -2860,6 +2845,8 @@ cifs_iovec_read(struct file *file, const struct iovec *iov,
 	if (!len)
 		return 0;
 
+	iov_iter_init(&to, iov, nr_segs, len, 0);
+
 	INIT_LIST_HEAD(&rdata_list);
 	cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
 	open_file = file->private_data;
@@ -2917,55 +2904,44 @@ error:
 	if (!list_empty(&rdata_list))
 		rc = 0;
 
+	len = iov_iter_count(&to);
 	/* the loop below should proceed in the order of increasing offsets */
-restart_loop:
 	list_for_each_entry_safe(rdata, tmp, &rdata_list, list) {
+	again:
 		if (!rc) {
-			ssize_t copied;
-
 			/* FIXME: freezable sleep too? */
 			rc = wait_for_completion_killable(&rdata->done);
 			if (rc)
 				rc = -EINTR;
-			else if (rdata->result)
+			else if (rdata->result) {
 				rc = rdata->result;
-			else {
-				rc = cifs_readdata_to_iov(rdata, iov,
-							nr_segs, *poffset,
-							&copied);
-				total_read += copied;
+				/* resend call if it's a retryable error */
+				if (rc == -EAGAIN) {
+					rc = cifs_retry_async_readv(rdata);
+					goto again;
+				}
+			} else {
+				rc = cifs_readdata_to_iov(rdata, &to);
 			}
 
-			/* resend call if it's a retryable error */
-			if (rc == -EAGAIN) {
-				rc = cifs_retry_async_readv(rdata);
-				goto restart_loop;
-			}
 		}
 		list_del_init(&rdata->list);
 		kref_put(&rdata->refcount, cifs_uncached_readdata_release);
 	}
 
+	total_read = len - iov_iter_count(&to);
+
 	cifs_stats_bytes_read(tcon, total_read);
-	*poffset += total_read;
 
 	/* mask nodata case */
 	if (rc == -ENODATA)
 		rc = 0;
 
-	return total_read ? total_read : rc;
-}
-
-ssize_t cifs_user_readv(struct kiocb *iocb, const struct iovec *iov,
-			       unsigned long nr_segs, loff_t pos)
-{
-	ssize_t read;
-
-	read = cifs_iovec_read(iocb->ki_filp, iov, nr_segs, &pos);
-	if (read > 0)
-		iocb->ki_pos = pos;
-
-	return read;
+	if (total_read) {
+		iocb->ki_pos = pos + total_read;
+		return total_read;
+	}
+	return rc;
 }
 
 ssize_t

fs/exec.c

@@ -813,7 +813,7 @@ EXPORT_SYMBOL(kernel_read);
 
 ssize_t read_code(struct file *file, unsigned long addr, loff_t pos, size_t len)
 {
-	ssize_t res = file->f_op->read(file, (void __user *)addr, len, &pos);
+	ssize_t res = vfs_read(file, (void __user *)addr, len, &pos);
 	if (res > 0)
 		flush_icache_range(addr, addr + len);
 	return res;

fs/ext4/file.c

@@ -146,7 +146,7 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
 			overwrite = 1;
 	}
 
-	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+	ret = __generic_file_aio_write(iocb, iov, nr_segs);
 	mutex_unlock(&inode->i_mutex);
 
 	if (ret > 0) {

fs/file.c

@@ -25,7 +25,10 @@
 
 int sysctl_nr_open __read_mostly = 1024*1024;
 int sysctl_nr_open_min = BITS_PER_LONG;
-int sysctl_nr_open_max = 1024 * 1024; /* raised later */
+/* our max() is unusable in constant expressions ;-/ */
+#define __const_max(x, y) ((x) < (y) ? (x) : (y))
+int sysctl_nr_open_max = __const_max(INT_MAX, ~(size_t)0/sizeof(void *)) &
+			 -BITS_PER_LONG;
 
 static void *alloc_fdmem(size_t size)
 {
@@ -429,12 +432,6 @@ void exit_files(struct task_struct *tsk)
 	}
 }
 
-void __init files_defer_init(void)
-{
-	sysctl_nr_open_max = min((size_t)INT_MAX, ~(size_t)0/sizeof(void *)) &
-			     -BITS_PER_LONG;
-}
-
 struct files_struct init_files = {
 	.count		= ATOMIC_INIT(1),
 	.fdt		= &init_files.fdtab,

fs/file_table.c

@@ -52,7 +52,6 @@ static void file_free_rcu(struct rcu_head *head)
 static inline void file_free(struct file *f)
 {
 	percpu_counter_dec(&nr_files);
-	file_check_state(f);
 	call_rcu(&f->f_u.fu_rcuhead, file_free_rcu);
 }
 
@@ -178,47 +177,12 @@ struct file *alloc_file(struct path *path, fmode_t mode,
 	file->f_mapping = path->dentry->d_inode->i_mapping;
 	file->f_mode = mode;
 	file->f_op = fop;
-
-	/*
-	 * These mounts don't really matter in practice
-	 * for r/o bind mounts.  They aren't userspace-
-	 * visible.  We do this for consistency, and so
-	 * that we can do debugging checks at __fput()
-	 */
-	if ((mode & FMODE_WRITE) && !special_file(path->dentry->d_inode->i_mode)) {
-		file_take_write(file);
-		WARN_ON(mnt_clone_write(path->mnt));
-	}
 	if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
 		i_readcount_inc(path->dentry->d_inode);
 	return file;
 }
 EXPORT_SYMBOL(alloc_file);
 
-/**
- * drop_file_write_access - give up ability to write to a file
- * @file: the file to which we will stop writing
- *
- * This is a central place which will give up the ability
- * to write to @file, along with access to write through
- * its vfsmount.
- */
-static void drop_file_write_access(struct file *file)
-{
-	struct vfsmount *mnt = file->f_path.mnt;
-	struct dentry *dentry = file->f_path.dentry;
-	struct inode *inode = dentry->d_inode;
-
-	put_write_access(inode);
-
-	if (special_file(inode->i_mode))
-		return;
-	if (file_check_writeable(file) != 0)
-		return;
-	__mnt_drop_write(mnt);
-	file_release_write(file);
-}
-
 /* the real guts of fput() - releasing the last reference to file
  */
 static void __fput(struct file *file)
@@ -253,8 +217,10 @@ static void __fput(struct file *file)
 	put_pid(file->f_owner.pid);
 	if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
 		i_readcount_dec(inode);
-	if (file->f_mode & FMODE_WRITE)
-		drop_file_write_access(file);
+	if (file->f_mode & FMODE_WRITER) {
+		put_write_access(inode);
+		__mnt_drop_write(mnt);
+	}
 	file->f_path.dentry = NULL;
 	file->f_path.mnt = NULL;
 	file->f_inode = NULL;
@@ -359,6 +325,5 @@ void __init files_init(unsigned long mempages)
 
 	n = (mempages * (PAGE_SIZE / 1024)) / 10;
 	files_stat.max_files = max_t(unsigned long, n, NR_FILE);
-	files_defer_init();
 	percpu_counter_init(&nr_files, 0);
 } 

fs/fuse/dev.c

@@ -667,15 +667,15 @@ static void fuse_copy_finish(struct fuse_copy_state *cs)
 		struct pipe_buffer *buf = cs->currbuf;
 
 		if (!cs->write) {
-			buf->ops->unmap(cs->pipe, buf, cs->mapaddr);
+			kunmap_atomic(cs->mapaddr);
 		} else {
-			kunmap(buf->page);
+			kunmap_atomic(cs->mapaddr);
 			buf->len = PAGE_SIZE - cs->len;
 		}
 		cs->currbuf = NULL;
 		cs->mapaddr = NULL;
 	} else if (cs->mapaddr) {
-		kunmap(cs->pg);
+		kunmap_atomic(cs->mapaddr);
 		if (cs->write) {
 			flush_dcache_page(cs->pg);
 			set_page_dirty_lock(cs->pg);
@@ -706,7 +706,7 @@ static int fuse_copy_fill(struct fuse_copy_state *cs)
 
 			BUG_ON(!cs->nr_segs);
 			cs->currbuf = buf;
-			cs->mapaddr = buf->ops->map(cs->pipe, buf, 0);
+			cs->mapaddr = kmap_atomic(buf->page);
 			cs->len = buf->len;
 			cs->buf = cs->mapaddr + buf->offset;
 			cs->pipebufs++;
@@ -726,7 +726,7 @@ static int fuse_copy_fill(struct fuse_copy_state *cs)
 			buf->len = 0;
 
 			cs->currbuf = buf;
-			cs->mapaddr = kmap(page);
+			cs->mapaddr = kmap_atomic(page);
 			cs->buf = cs->mapaddr;
 			cs->len = PAGE_SIZE;
 			cs->pipebufs++;
@@ -745,7 +745,7 @@ static int fuse_copy_fill(struct fuse_copy_state *cs)
 			return err;
 		BUG_ON(err != 1);
 		offset = cs->addr % PAGE_SIZE;
-		cs->mapaddr = kmap(cs->pg);
+		cs->mapaddr = kmap_atomic(cs->pg);
 		cs->buf = cs->mapaddr + offset;
 		cs->len = min(PAGE_SIZE - offset, cs->seglen);
 		cs->seglen -= cs->len;
@@ -874,7 +874,7 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
 out_fallback_unlock:
 	unlock_page(newpage);
 out_fallback:
-	cs->mapaddr = buf->ops->map(cs->pipe, buf, 1);
+	cs->mapaddr = kmap_atomic(buf->page);
 	cs->buf = cs->mapaddr + buf->offset;
 
 	err = lock_request(cs->fc, cs->req);

fs/fuse/file.c

@@ -1086,9 +1086,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req,
 		if (mapping_writably_mapped(mapping))
 			flush_dcache_page(page);
 
-		pagefault_disable();
 		tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes);
-		pagefault_enable();
 		flush_dcache_page(page);
 
 		mark_page_accessed(page);
@@ -1237,8 +1235,7 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		goto out;
 
 	if (file->f_flags & O_DIRECT) {
-		written = generic_file_direct_write(iocb, iov, &nr_segs,
-						    pos, &iocb->ki_pos,
+		written = generic_file_direct_write(iocb, iov, &nr_segs, pos, 
 						    count, ocount);
 		if (written < 0 || written == count)
 			goto out;

fs/mount.h

@@ -10,7 +10,7 @@ struct mnt_namespace {
 	struct user_namespace	*user_ns;
 	u64			seq;	/* Sequence number to prevent loops */
 	wait_queue_head_t poll;
-	int event;
+	u64 event;
 };
 
 struct mnt_pcp {
@@ -104,6 +104,9 @@ struct proc_mounts {
 	struct mnt_namespace *ns;
 	struct path root;
 	int (*show)(struct seq_file *, struct vfsmount *);
+	void *cached_mount;
+	u64 cached_event;
+	loff_t cached_index;
 };
 
 #define proc_mounts(p) (container_of((p), struct proc_mounts, m))

fs/namei.c

@@ -358,6 +358,7 @@ int generic_permission(struct inode *inode, int mask)
 
 	return -EACCES;
 }
+EXPORT_SYMBOL(generic_permission);
 
 /*
  * We _really_ want to just do "generic_permission()" without
@@ -455,6 +456,7 @@ int inode_permission(struct inode *inode, int mask)
 		return retval;
 	return __inode_permission(inode, mask);
 }
+EXPORT_SYMBOL(inode_permission);
 
 /**
  * path_get - get a reference to a path
@@ -924,6 +926,7 @@ int follow_up(struct path *path)
 	path->mnt = &parent->mnt;
 	return 1;
 }
+EXPORT_SYMBOL(follow_up);
 
 /*
  * Perform an automount
@@ -1085,6 +1088,7 @@ int follow_down_one(struct path *path)
 	}
 	return 0;
 }
+EXPORT_SYMBOL(follow_down_one);
 
 static inline bool managed_dentry_might_block(struct dentry *dentry)
 {
@@ -1223,6 +1227,7 @@ int follow_down(struct path *path)
 	}
 	return 0;
 }
+EXPORT_SYMBOL(follow_down);
 
 /*
  * Skip to top of mountpoint pile in refwalk mode for follow_dotdot()
@@ -2025,6 +2030,7 @@ int kern_path(const char *name, unsigned int flags, struct path *path)
 		*path = nd.path;
 	return res;
 }
+EXPORT_SYMBOL(kern_path);
 
 /**
  * vfs_path_lookup - lookup a file path relative to a dentry-vfsmount pair
@@ -2049,6 +2055,7 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
 		*path = nd.path;
 	return err;
 }
+EXPORT_SYMBOL(vfs_path_lookup);
 
 /*
  * Restricted form of lookup. Doesn't follow links, single-component only,
@@ -2111,6 +2118,7 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
 
 	return __lookup_hash(&this, base, 0);
 }
+EXPORT_SYMBOL(lookup_one_len);
 
 int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
 		 struct path *path, int *empty)
@@ -2135,6 +2143,7 @@ int user_path_at(int dfd, const char __user *name, unsigned flags,
 {
 	return user_path_at_empty(dfd, name, flags, path, NULL);
 }
+EXPORT_SYMBOL(user_path_at);
 
 /*
  * NB: most callers don't do anything directly with the reference to the
@@ -2477,6 +2486,7 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2)
 	mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD);
 	return NULL;
 }
+EXPORT_SYMBOL(lock_rename);
 
 void unlock_rename(struct dentry *p1, struct dentry *p2)
 {
@@ -2486,6 +2496,7 @@ void unlock_rename(struct dentry *p1, struct dentry *p2)
 		mutex_unlock(&p1->d_inode->i_sb->s_vfs_rename_mutex);
 	}
 }
+EXPORT_SYMBOL(unlock_rename);
 
 int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 		bool want_excl)
@@ -2506,6 +2517,7 @@ int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 		fsnotify_create(dir, dentry);
 	return error;
 }
+EXPORT_SYMBOL(vfs_create);
 
 static int may_open(struct path *path, int acc_mode, int flag)
 {
@@ -3375,6 +3387,7 @@ int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
 		fsnotify_create(dir, dentry);
 	return error;
 }
+EXPORT_SYMBOL(vfs_mknod);
 
 static int may_mknod(umode_t mode)
 {
@@ -3464,6 +3477,7 @@ int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 		fsnotify_mkdir(dir, dentry);
 	return error;
 }
+EXPORT_SYMBOL(vfs_mkdir);
 
 SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode)
 {
@@ -3518,6 +3532,7 @@ void dentry_unhash(struct dentry *dentry)
 		__d_drop(dentry);
 	spin_unlock(&dentry->d_lock);
 }
+EXPORT_SYMBOL(dentry_unhash);
 
 int vfs_rmdir(struct inode *dir, struct dentry *dentry)
 {
@@ -3555,6 +3570,7 @@ out:
 		d_delete(dentry);
 	return error;
 }
+EXPORT_SYMBOL(vfs_rmdir);
 
 static long do_rmdir(int dfd, const char __user *pathname)
 {
@@ -3672,6 +3688,7 @@ out:
 
 	return error;
 }
+EXPORT_SYMBOL(vfs_unlink);
 
 /*
  * Make sure that the actual truncation of the file will occur outside its
@@ -3785,6 +3802,7 @@ int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname)
 		fsnotify_create(dir, dentry);
 	return error;
 }
+EXPORT_SYMBOL(vfs_symlink);
 
 SYSCALL_DEFINE3(symlinkat, const char __user *, oldname,
 		int, newdfd, const char __user *, newname)
@@ -3893,6 +3911,7 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de
 		fsnotify_link(dir, inode, new_dentry);
 	return error;
 }
+EXPORT_SYMBOL(vfs_link);
 
 /*
  * Hardlinks are often used in delicate situations.  We avoid
@@ -4152,6 +4171,7 @@ out:
 
 	return error;
 }
+EXPORT_SYMBOL(vfs_rename);
 
 SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
 		int, newdfd, const char __user *, newname, unsigned int, flags)
@@ -4304,11 +4324,9 @@ SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newna
 	return sys_renameat2(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
 }
 
-int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen, const char *link)
+int readlink_copy(char __user *buffer, int buflen, const char *link)
 {
-	int len;
-
-	len = PTR_ERR(link);
+	int len = PTR_ERR(link);
 	if (IS_ERR(link))
 		goto out;
 
@@ -4320,6 +4338,7 @@ int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen, const c
 out:
 	return len;
 }
+EXPORT_SYMBOL(readlink_copy);
 
 /*
  * A helper for ->readlink().  This should be used *ONLY* for symlinks that
@@ -4337,11 +4356,12 @@ int generic_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 	if (IS_ERR(cookie))
 		return PTR_ERR(cookie);
 
-	res = vfs_readlink(dentry, buffer, buflen, nd_get_link(&nd));
+	res = readlink_copy(buffer, buflen, nd_get_link(&nd));
 	if (dentry->d_inode->i_op->put_link)
 		dentry->d_inode->i_op->put_link(dentry, &nd, cookie);
 	return res;
 }
+EXPORT_SYMBOL(generic_readlink);
 
 /* get the link contents into pagecache */
 static char *page_getlink(struct dentry * dentry, struct page **ppage)
@@ -4361,14 +4381,14 @@ static char *page_getlink(struct dentry * dentry, struct page **ppage)
 int page_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 {
 	struct page *page = NULL;
-	char *s = page_getlink(dentry, &page);
-	int res = vfs_readlink(dentry,buffer,buflen,s);
+	int res = readlink_copy(buffer, buflen, page_getlink(dentry, &page));
 	if (page) {
 		kunmap(page);
 		page_cache_release(page);
 	}
 	return res;
 }
+EXPORT_SYMBOL(page_readlink);
 
 void *page_follow_link_light(struct dentry *dentry, struct nameidata *nd)
 {
@@ -4376,6 +4396,7 @@ void *page_follow_link_light(struct dentry *dentry, struct nameidata *nd)
 	nd_set_link(nd, page_getlink(dentry, &page));
 	return page;
 }
+EXPORT_SYMBOL(page_follow_link_light);
 
 void page_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie)
 {
@@ -4386,6 +4407,7 @@ void page_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie)
 		page_cache_release(page);
 	}
 }
+EXPORT_SYMBOL(page_put_link);
 
 /*
  * The nofs argument instructs pagecache_write_begin to pass AOP_FLAG_NOFS
@@ -4423,45 +4445,18 @@ retry:
 fail:
 	return err;
 }
+EXPORT_SYMBOL(__page_symlink);
 
 int page_symlink(struct inode *inode, const char *symname, int len)
 {
 	return __page_symlink(inode, symname, len,
 			!(mapping_gfp_mask(inode->i_mapping) & __GFP_FS));
 }
+EXPORT_SYMBOL(page_symlink);
 
 const struct inode_operations page_symlink_inode_operations = {
 	.readlink	= generic_readlink,
 	.follow_link	= page_follow_link_light,
 	.put_link	= page_put_link,
 };
-
-EXPORT_SYMBOL(user_path_at);
-EXPORT_SYMBOL(follow_down_one);
-EXPORT_SYMBOL(follow_down);
-EXPORT_SYMBOL(follow_up);
-EXPORT_SYMBOL(get_write_access); /* nfsd */
-EXPORT_SYMBOL(lock_rename);
-EXPORT_SYMBOL(lookup_one_len);
-EXPORT_SYMBOL(page_follow_link_light);
-EXPORT_SYMBOL(page_put_link);
-EXPORT_SYMBOL(page_readlink);
-EXPORT_SYMBOL(__page_symlink);
-EXPORT_SYMBOL(page_symlink);
 EXPORT_SYMBOL(page_symlink_inode_operations);
-EXPORT_SYMBOL(kern_path);
-EXPORT_SYMBOL(vfs_path_lookup);
-EXPORT_SYMBOL(inode_permission);
-EXPORT_SYMBOL(unlock_rename);
-EXPORT_SYMBOL(vfs_create);
-EXPORT_SYMBOL(vfs_link);
-EXPORT_SYMBOL(vfs_mkdir);
-EXPORT_SYMBOL(vfs_mknod);
-EXPORT_SYMBOL(generic_permission);
-EXPORT_SYMBOL(vfs_readlink);
-EXPORT_SYMBOL(vfs_rename);
-EXPORT_SYMBOL(vfs_rmdir);
-EXPORT_SYMBOL(vfs_symlink);
-EXPORT_SYMBOL(vfs_unlink);
-EXPORT_SYMBOL(dentry_unhash);
-EXPORT_SYMBOL(generic_readlink);

fs/namespace.c

@@ -52,7 +52,7 @@ static int __init set_mphash_entries(char *str)
 }
 __setup("mphash_entries=", set_mphash_entries);
 
-static int event;
+static u64 event;
 static DEFINE_IDA(mnt_id_ida);
 static DEFINE_IDA(mnt_group_ida);
 static DEFINE_SPINLOCK(mnt_id_lock);
@@ -414,9 +414,7 @@ EXPORT_SYMBOL_GPL(mnt_clone_write);
  */
 int __mnt_want_write_file(struct file *file)
 {
-	struct inode *inode = file_inode(file);
-
-	if (!(file->f_mode & FMODE_WRITE) || special_file(inode->i_mode))
+	if (!(file->f_mode & FMODE_WRITER))
 		return __mnt_want_write(file->f_path.mnt);
 	else
 		return mnt_clone_write(file->f_path.mnt);
@@ -570,13 +568,17 @@ int sb_prepare_remount_readonly(struct super_block *sb)
 static void free_vfsmnt(struct mount *mnt)
 {
 	kfree(mnt->mnt_devname);
-	mnt_free_id(mnt);
 #ifdef CONFIG_SMP
 	free_percpu(mnt->mnt_pcp);
 #endif
 	kmem_cache_free(mnt_cache, mnt);
 }
 
+static void delayed_free_vfsmnt(struct rcu_head *head)
+{
+	free_vfsmnt(container_of(head, struct mount, mnt_rcu));
+}
+
 /* call under rcu_read_lock */
 bool legitimize_mnt(struct vfsmount *bastard, unsigned seq)
 {
@@ -848,6 +850,7 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void
 
 	root = mount_fs(type, flags, name, data);
 	if (IS_ERR(root)) {
+		mnt_free_id(mnt);
 		free_vfsmnt(mnt);
 		return ERR_CAST(root);
 	}
@@ -885,7 +888,7 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 			goto out_free;
 	}
 
-	mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD;
+	mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~(MNT_WRITE_HOLD|MNT_MARKED);
 	/* Don't allow unprivileged users to change mount flags */
 	if ((flag & CL_UNPRIVILEGED) && (mnt->mnt.mnt_flags & MNT_READONLY))
 		mnt->mnt.mnt_flags |= MNT_LOCK_READONLY;
@@ -928,20 +931,11 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 	return mnt;
 
  out_free:
+	mnt_free_id(mnt);
 	free_vfsmnt(mnt);
 	return ERR_PTR(err);
 }
 
-static void delayed_free(struct rcu_head *head)
-{
-	struct mount *mnt = container_of(head, struct mount, mnt_rcu);
-	kfree(mnt->mnt_devname);
-#ifdef CONFIG_SMP
-	free_percpu(mnt->mnt_pcp);
-#endif
-	kmem_cache_free(mnt_cache, mnt);
-}
-
 static void mntput_no_expire(struct mount *mnt)
 {
 put_again:
@@ -991,7 +985,7 @@ put_again:
 	dput(mnt->mnt.mnt_root);
 	deactivate_super(mnt->mnt.mnt_sb);
 	mnt_free_id(mnt);
-	call_rcu(&mnt->mnt_rcu, delayed_free);
+	call_rcu(&mnt->mnt_rcu, delayed_free_vfsmnt);
 }
 
 void mntput(struct vfsmount *mnt)
@@ -1100,14 +1094,29 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 	struct proc_mounts *p = proc_mounts(m);
 
 	down_read(&namespace_sem);
-	return seq_list_start(&p->ns->list, *pos);
+	if (p->cached_event == p->ns->event) {
+		void *v = p->cached_mount;
+		if (*pos == p->cached_index)
+			return v;
+		if (*pos == p->cached_index + 1) {
+			v = seq_list_next(v, &p->ns->list, &p->cached_index);
+			return p->cached_mount = v;
+		}
+	}
+
+	p->cached_event = p->ns->event;
+	p->cached_mount = seq_list_start(&p->ns->list, *pos);
+	p->cached_index = *pos;
+	return p->cached_mount;
 }
 
 static void *m_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct proc_mounts *p = proc_mounts(m);
 
-	return seq_list_next(v, &p->ns->list, pos);
+	p->cached_mount = seq_list_next(v, &p->ns->list, pos);
+	p->cached_index = *pos;
+	return p->cached_mount;
 }
 
 static void m_stop(struct seq_file *m, void *v)
@@ -1661,9 +1670,9 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 		if (err)
 			goto out;
 		err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list);
+		lock_mount_hash();
 		if (err)
 			goto out_cleanup_ids;
-		lock_mount_hash();
 		for (p = source_mnt; p; p = next_mnt(p, source_mnt))
 			set_mnt_shared(p);
 	} else {
@@ -1690,6 +1699,11 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 	return 0;
 
  out_cleanup_ids:
+	while (!hlist_empty(&tree_list)) {
+		child = hlist_entry(tree_list.first, struct mount, mnt_hash);
+		umount_tree(child, 0);
+	}
+	unlock_mount_hash();
 	cleanup_group_ids(source_mnt, NULL);
  out:
 	return err;
@@ -2044,7 +2058,7 @@ static int do_add_mount(struct mount *newmnt, struct path *path, int mnt_flags)
 	struct mount *parent;
 	int err;
 
-	mnt_flags &= ~(MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | MNT_DOOMED | MNT_SYNC_UMOUNT);
+	mnt_flags &= ~MNT_INTERNAL_FLAGS;
 
 	mp = lock_mount(path);
 	if (IS_ERR(mp))

fs/ncpfs/inode.c

@@ -470,9 +470,7 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent)
 {
 	struct ncp_mount_data_kernel data;
 	struct ncp_server *server;
-	struct file *ncp_filp;
 	struct inode *root_inode;
-	struct inode *sock_inode;
 	struct socket *sock;
 	int error;
 	int default_bufsize;
@@ -541,18 +539,10 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent)
 	if (!uid_valid(data.mounted_uid) || !uid_valid(data.uid) ||
 	    !gid_valid(data.gid))
 		goto out;
-	error = -EBADF;
-	ncp_filp = fget(data.ncp_fd);
-	if (!ncp_filp)
-		goto out;
-	error = -ENOTSOCK;
-	sock_inode = file_inode(ncp_filp);
-	if (!S_ISSOCK(sock_inode->i_mode))
-		goto out_fput;
-	sock = SOCKET_I(sock_inode);
+	sock = sockfd_lookup(data.ncp_fd, &error);
 	if (!sock)
-		goto out_fput;
-		
+		goto out;
+
 	if (sock->type == SOCK_STREAM)
 		default_bufsize = 0xF000;
 	else
@@ -574,27 +564,16 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent)
 	if (error)
 		goto out_fput;
 
-	server->ncp_filp = ncp_filp;
 	server->ncp_sock = sock;
 	
 	if (data.info_fd != -1) {
-		struct socket *info_sock;
-
-		error = -EBADF;
-		server->info_filp = fget(data.info_fd);
-		if (!server->info_filp)
-			goto out_bdi;
-		error = -ENOTSOCK;
-		sock_inode = file_inode(server->info_filp);
-		if (!S_ISSOCK(sock_inode->i_mode))
-			goto out_fput2;
-		info_sock = SOCKET_I(sock_inode);
+		struct socket *info_sock = sockfd_lookup(data.info_fd, &error);
 		if (!info_sock)
-			goto out_fput2;
+			goto out_bdi;
+		server->info_sock = info_sock;
 		error = -EBADFD;
 		if (info_sock->type != SOCK_STREAM)
 			goto out_fput2;
-		server->info_sock = info_sock;
 	}
 
 /*	server->lock = 0;	*/
@@ -766,17 +745,12 @@ out_nls:
 	mutex_destroy(&server->root_setup_lock);
 	mutex_destroy(&server->mutex);
 out_fput2:
-	if (server->info_filp)
-		fput(server->info_filp);
+	if (server->info_sock)
+		sockfd_put(server->info_sock);
 out_bdi:
 	bdi_destroy(&server->bdi);
 out_fput:
-	/* 23/12/1998 Marcin Dalecki <dalecki@cs.net.pl>:
-	 * 
-	 * The previously used put_filp(ncp_filp); was bogus, since
-	 * it doesn't perform proper unlocking.
-	 */
-	fput(ncp_filp);
+	sockfd_put(sock);
 out:
 	put_pid(data.wdog_pid);
 	sb->s_fs_info = NULL;
@@ -809,9 +783,9 @@ static void ncp_put_super(struct super_block *sb)
 	mutex_destroy(&server->root_setup_lock);
 	mutex_destroy(&server->mutex);
 
-	if (server->info_filp)
-		fput(server->info_filp);
-	fput(server->ncp_filp);
+	if (server->info_sock)
+		sockfd_put(server->info_sock);
+	sockfd_put(server->ncp_sock);
 	kill_pid(server->m.wdog_pid, SIGTERM, 1);
 	put_pid(server->m.wdog_pid);
 

fs/ncpfs/ncp_fs_sb.h

@@ -45,9 +45,7 @@ struct ncp_server {
 
 	__u8 name_space[NCP_NUMBER_OF_VOLUMES + 2];
 
-	struct file *ncp_filp;	/* File pointer to ncp socket */
 	struct socket *ncp_sock;/* ncp socket */
-	struct file *info_filp;
 	struct socket *info_sock;
 
 	u8 sequence;

fs/ntfs/inode.c

@@ -1704,8 +1704,6 @@ static int ntfs_read_locked_index_inode(struct inode *base_vi, struct inode *vi)
 	iput(bvi);
 skip_large_index_stuff:
 	/* Setup the operations for this index inode. */
-	vi->i_op = NULL;
-	vi->i_fop = NULL;
 	vi->i_mapping->a_ops = &ntfs_mst_aops;
 	vi->i_blocks = ni->allocated_size >> 9;
 	/*

fs/ocfs2/cluster/tcp.c

@@ -916,57 +916,30 @@ static struct o2net_msg_handler *o2net_handler_get(u32 msg_type, u32 key)
 
 static int o2net_recv_tcp_msg(struct socket *sock, void *data, size_t len)
 {
-	int ret;
-	mm_segment_t oldfs;
-	struct kvec vec = {
-		.iov_len = len,
-		.iov_base = data,
-	};
-	struct msghdr msg = {
-		.msg_iovlen = 1,
-		.msg_iov = (struct iovec *)&vec,
-       		.msg_flags = MSG_DONTWAIT,
-	};
-
-	oldfs = get_fs();
-	set_fs(get_ds());
-	ret = sock_recvmsg(sock, &msg, len, msg.msg_flags);
-	set_fs(oldfs);
-
-	return ret;
+	struct kvec vec = { .iov_len = len, .iov_base = data, };
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT, };
+	return kernel_recvmsg(sock, &msg, &vec, 1, len, msg.msg_flags);
 }
 
 static int o2net_send_tcp_msg(struct socket *sock, struct kvec *vec,
 			      size_t veclen, size_t total)
 {
 	int ret;
-	mm_segment_t oldfs;
-	struct msghdr msg = {
-		.msg_iov = (struct iovec *)vec,
-		.msg_iovlen = veclen,
-	};
+	struct msghdr msg;
 
 	if (sock == NULL) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	oldfs = get_fs();
-	set_fs(get_ds());
-	ret = sock_sendmsg(sock, &msg, total);
-	set_fs(oldfs);
-	if (ret != total) {
-		mlog(ML_ERROR, "sendmsg returned %d instead of %zu\n", ret,
-		     total);
-		if (ret >= 0)
-			ret = -EPIPE; /* should be smarter, I bet */
-		goto out;
-	}
-
-	ret = 0;
+	ret = kernel_sendmsg(sock, &msg, vec, veclen, total);
+	if (likely(ret == total))
+		return 0;
+	mlog(ML_ERROR, "sendmsg returned %d instead of %zu\n", ret, total);
+	if (ret >= 0)
+		ret = -EPIPE; /* should be smarter, I bet */
 out:
-	if (ret < 0)
-		mlog(0, "returning error: %d\n", ret);
+	mlog(0, "returning error: %d\n", ret);
 	return ret;
 }
 

fs/ocfs2/file.c

@@ -2367,15 +2367,18 @@ relock:
 
 	if (direct_io) {
 		written = generic_file_direct_write(iocb, iov, &nr_segs, *ppos,
-						    ppos, count, ocount);
+						    count, ocount);
 		if (written < 0) {
 			ret = written;
 			goto out_dio;
 		}
 	} else {
+		struct iov_iter from;
+		iov_iter_init(&from, iov, nr_segs, count, 0);
 		current->backing_dev_info = file->f_mapping->backing_dev_info;
-		written = generic_file_buffered_write(iocb, iov, nr_segs, *ppos,
-						      ppos, count, 0);
+		written = generic_perform_write(file, &from, *ppos);
+		if (likely(written >= 0))
+			iocb->ki_pos = *ppos + written;
 		current->backing_dev_info = NULL;
 	}
 

fs/open.c

@@ -655,35 +655,6 @@ out:
 	return error;
 }
 
-/*
- * You have to be very careful that these write
- * counts get cleaned up in error cases and
- * upon __fput().  This should probably never
- * be called outside of __dentry_open().
- */
-static inline int __get_file_write_access(struct inode *inode,
-					  struct vfsmount *mnt)
-{
-	int error;
-	error = get_write_access(inode);
-	if (error)
-		return error;
-	/*
-	 * Do not take mount writer counts on
-	 * special files since no writes to
-	 * the mount itself will occur.
-	 */
-	if (!special_file(inode->i_mode)) {
-		/*
-		 * Balanced in __fput()
-		 */
-		error = __mnt_want_write(mnt);
-		if (error)
-			put_write_access(inode);
-	}
-	return error;
-}
-
 int open_check_o_direct(struct file *f)
 {
 	/* NB: we're sure to have correct a_ops only after f_op->open */
@@ -708,26 +679,28 @@ static int do_dentry_open(struct file *f,
 	f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK |
 				FMODE_PREAD | FMODE_PWRITE;
 
-	if (unlikely(f->f_flags & O_PATH))
-		f->f_mode = FMODE_PATH;
-
 	path_get(&f->f_path);
 	inode = f->f_inode = f->f_path.dentry->d_inode;
-	if (f->f_mode & FMODE_WRITE) {
-		error = __get_file_write_access(inode, f->f_path.mnt);
-		if (error)
-			goto cleanup_file;
-		if (!special_file(inode->i_mode))
-			file_take_write(f);
-	}
-
 	f->f_mapping = inode->i_mapping;
 
-	if (unlikely(f->f_mode & FMODE_PATH)) {
+	if (unlikely(f->f_flags & O_PATH)) {
+		f->f_mode = FMODE_PATH;
 		f->f_op = &empty_fops;
 		return 0;
 	}
 
+	if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) {
+		error = get_write_access(inode);
+		if (unlikely(error))
+			goto cleanup_file;
+		error = __mnt_want_write(f->f_path.mnt);
+		if (unlikely(error)) {
+			put_write_access(inode);
+			goto cleanup_file;
+		}
+		f->f_mode |= FMODE_WRITER;
+	}
+
 	/* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */
 	if (S_ISREG(inode->i_mode))
 		f->f_mode |= FMODE_ATOMIC_POS;
@@ -764,18 +737,9 @@ static int do_dentry_open(struct file *f,
 
 cleanup_all:
 	fops_put(f->f_op);
-	if (f->f_mode & FMODE_WRITE) {
+	if (f->f_mode & FMODE_WRITER) {
 		put_write_access(inode);
-		if (!special_file(inode->i_mode)) {
-			/*
-			 * We don't consider this a real
-			 * mnt_want/drop_write() pair
-			 * because it all happenend right
-			 * here, so just reset the state.
-			 */
-			file_reset_write(f);
-			__mnt_drop_write(f->f_path.mnt);
-		}
+		__mnt_drop_write(f->f_path.mnt);
 	}
 cleanup_file:
 	path_put(&f->f_path);

fs/pipe.c

@@ -142,55 +142,6 @@ pipe_iov_copy_from_user(void *to, struct iovec *iov, unsigned long len,
 	return 0;
 }
 
-static int
-pipe_iov_copy_to_user(struct iovec *iov, const void *from, unsigned long len,
-		      int atomic)
-{
-	unsigned long copy;
-
-	while (len > 0) {
-		while (!iov->iov_len)
-			iov++;
-		copy = min_t(unsigned long, len, iov->iov_len);
-
-		if (atomic) {
-			if (__copy_to_user_inatomic(iov->iov_base, from, copy))
-				return -EFAULT;
-		} else {
-			if (copy_to_user(iov->iov_base, from, copy))
-				return -EFAULT;
-		}
-		from += copy;
-		len -= copy;
-		iov->iov_base += copy;
-		iov->iov_len -= copy;
-	}
-	return 0;
-}
-
-/*
- * Attempt to pre-fault in the user memory, so we can use atomic copies.
- * Returns the number of bytes not faulted in.
- */
-static int iov_fault_in_pages_write(struct iovec *iov, unsigned long len)
-{
-	while (!iov->iov_len)
-		iov++;
-
-	while (len > 0) {
-		unsigned long this_len;
-
-		this_len = min_t(unsigned long, len, iov->iov_len);
-		if (fault_in_pages_writeable(iov->iov_base, this_len))
-			break;
-
-		len -= this_len;
-		iov++;
-	}
-
-	return len;
-}
-
 /*
  * Pre-fault in the user memory, so we can use atomic copies.
  */
@@ -225,52 +176,6 @@ static void anon_pipe_buf_release(struct pipe_inode_info *pipe,
 		page_cache_release(page);
 }
 
-/**
- * generic_pipe_buf_map - virtually map a pipe buffer
- * @pipe:	the pipe that the buffer belongs to
- * @buf:	the buffer that should be mapped
- * @atomic:	whether to use an atomic map
- *
- * Description:
- *	This function returns a kernel virtual address mapping for the
- *	pipe_buffer passed in @buf. If @atomic is set, an atomic map is provided
- *	and the caller has to be careful not to fault before calling
- *	the unmap function.
- *
- *	Note that this function calls kmap_atomic() if @atomic != 0.
- */
-void *generic_pipe_buf_map(struct pipe_inode_info *pipe,
-			   struct pipe_buffer *buf, int atomic)
-{
-	if (atomic) {
-		buf->flags |= PIPE_BUF_FLAG_ATOMIC;
-		return kmap_atomic(buf->page);
-	}
-
-	return kmap(buf->page);
-}
-EXPORT_SYMBOL(generic_pipe_buf_map);
-
-/**
- * generic_pipe_buf_unmap - unmap a previously mapped pipe buffer
- * @pipe:	the pipe that the buffer belongs to
- * @buf:	the buffer that should be unmapped
- * @map_data:	the data that the mapping function returned
- *
- * Description:
- *	This function undoes the mapping that ->map() provided.
- */
-void generic_pipe_buf_unmap(struct pipe_inode_info *pipe,
-			    struct pipe_buffer *buf, void *map_data)
-{
-	if (buf->flags & PIPE_BUF_FLAG_ATOMIC) {
-		buf->flags &= ~PIPE_BUF_FLAG_ATOMIC;
-		kunmap_atomic(map_data);
-	} else
-		kunmap(buf->page);
-}
-EXPORT_SYMBOL(generic_pipe_buf_unmap);
-
 /**
  * generic_pipe_buf_steal - attempt to take ownership of a &pipe_buffer
  * @pipe:	the pipe that the buffer belongs to
@@ -351,8 +256,6 @@ EXPORT_SYMBOL(generic_pipe_buf_release);
 
 static const struct pipe_buf_operations anon_pipe_buf_ops = {
 	.can_merge = 1,
-	.map = generic_pipe_buf_map,
-	.unmap = generic_pipe_buf_unmap,
 	.confirm = generic_pipe_buf_confirm,
 	.release = anon_pipe_buf_release,
 	.steal = generic_pipe_buf_steal,
@@ -361,8 +264,6 @@ static const struct pipe_buf_operations anon_pipe_buf_ops = {
 
 static const struct pipe_buf_operations packet_pipe_buf_ops = {
 	.can_merge = 0,
-	.map = generic_pipe_buf_map,
-	.unmap = generic_pipe_buf_unmap,
 	.confirm = generic_pipe_buf_confirm,
 	.release = anon_pipe_buf_release,
 	.steal = generic_pipe_buf_steal,
@@ -379,12 +280,15 @@ pipe_read(struct kiocb *iocb, const struct iovec *_iov,
 	ssize_t ret;
 	struct iovec *iov = (struct iovec *)_iov;
 	size_t total_len;
+	struct iov_iter iter;
 
 	total_len = iov_length(iov, nr_segs);
 	/* Null read succeeds. */
 	if (unlikely(total_len == 0))
 		return 0;
 
+	iov_iter_init(&iter, iov, nr_segs, total_len, 0);
+
 	do_wakeup = 0;
 	ret = 0;
 	__pipe_lock(pipe);
@@ -394,9 +298,9 @@ pipe_read(struct kiocb *iocb, const struct iovec *_iov,
 			int curbuf = pipe->curbuf;
 			struct pipe_buffer *buf = pipe->bufs + curbuf;
 			const struct pipe_buf_operations *ops = buf->ops;
-			void *addr;
 			size_t chars = buf->len;
-			int error, atomic;
+			size_t written;
+			int error;
 
 			if (chars > total_len)
 				chars = total_len;
@@ -408,21 +312,10 @@ pipe_read(struct kiocb *iocb, const struct iovec *_iov,
 				break;
 			}
 
-			atomic = !iov_fault_in_pages_write(iov, chars);
-redo:
-			addr = ops->map(pipe, buf, atomic);
-			error = pipe_iov_copy_to_user(iov, addr + buf->offset, chars, atomic);
-			ops->unmap(pipe, buf, addr);
-			if (unlikely(error)) {
-				/*
-				 * Just retry with the slow path if we failed.
-				 */
-				if (atomic) {
-					atomic = 0;
-					goto redo;
-				}
+			written = copy_page_to_iter(buf->page, buf->offset, chars, &iter);
+			if (unlikely(written < chars)) {
 				if (!ret)
-					ret = error;
+					ret = -EFAULT;
 				break;
 			}
 			ret += chars;
@@ -538,10 +431,16 @@ pipe_write(struct kiocb *iocb, const struct iovec *_iov,
 
 			iov_fault_in_pages_read(iov, chars);
 redo1:
-			addr = ops->map(pipe, buf, atomic);
+			if (atomic)
+				addr = kmap_atomic(buf->page);
+			else
+				addr = kmap(buf->page);
 			error = pipe_iov_copy_from_user(offset + addr, iov,
 							chars, atomic);
-			ops->unmap(pipe, buf, addr);
+			if (atomic)
+				kunmap_atomic(addr);
+			else
+				kunmap(buf->page);
 			ret = error;
 			do_wakeup = 1;
 			if (error) {

fs/pnode.c

@@ -164,46 +164,94 @@ static struct mount *propagation_next(struct mount *m,
 	}
 }
 
-/*
- * return the source mount to be used for cloning
- *
- * @dest 	the current destination mount
- * @last_dest  	the last seen destination mount
- * @last_src  	the last seen source mount
- * @type	return CL_SLAVE if the new mount has to be
- * 		cloned as a slave.
- */
-static struct mount *get_source(struct mount *dest,
-				struct mount *last_dest,
-				struct mount *last_src,
-				int *type)
+static struct mount *next_group(struct mount *m, struct mount *origin)
 {
-	struct mount *p_last_src = NULL;
-	struct mount *p_last_dest = NULL;
-
-	while (last_dest != dest->mnt_master) {
-		p_last_dest = last_dest;
-		p_last_src = last_src;
-		last_dest = last_dest->mnt_master;
-		last_src = last_src->mnt_master;
+	while (1) {
+		while (1) {
+			struct mount *next;
+			if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
+				return first_slave(m);
+			next = next_peer(m);
+			if (m->mnt_group_id == origin->mnt_group_id) {
+				if (next == origin)
+					return NULL;
+			} else if (m->mnt_slave.next != &next->mnt_slave)
+				break;
+			m = next;
+		}
+		/* m is the last peer */
+		while (1) {
+			struct mount *master = m->mnt_master;
+			if (m->mnt_slave.next != &master->mnt_slave_list)
+				return next_slave(m);
+			m = next_peer(master);
+			if (master->mnt_group_id == origin->mnt_group_id)
+				break;
+			if (master->mnt_slave.next == &m->mnt_slave)
+				break;
+			m = master;
+		}
+		if (m == origin)
+			return NULL;
 	}
+}
 
-	if (p_last_dest) {
-		do {
-			p_last_dest = next_peer(p_last_dest);
-		} while (IS_MNT_NEW(p_last_dest));
-		/* is that a peer of the earlier? */
-		if (dest == p_last_dest) {
-			*type = CL_MAKE_SHARED;
-			return p_last_src;
+/* all accesses are serialized by namespace_sem */
+static struct user_namespace *user_ns;
+static struct mount *last_dest, *last_source, *dest_master;
+static struct mountpoint *mp;
+static struct hlist_head *list;
+
+static int propagate_one(struct mount *m)
+{
+	struct mount *child;
+	int type;
+	/* skip ones added by this propagate_mnt() */
+	if (IS_MNT_NEW(m))
+		return 0;
+	/* skip if mountpoint isn't covered by it */
+	if (!is_subdir(mp->m_dentry, m->mnt.mnt_root))
+		return 0;
+	if (m->mnt_group_id == last_dest->mnt_group_id) {
+		type = CL_MAKE_SHARED;
+	} else {
+		struct mount *n, *p;
+		for (n = m; ; n = p) {
+			p = n->mnt_master;
+			if (p == dest_master || IS_MNT_MARKED(p)) {
+				while (last_dest->mnt_master != p) {
+					last_source = last_source->mnt_master;
+					last_dest = last_source->mnt_parent;
+				}
+				if (n->mnt_group_id != last_dest->mnt_group_id) {
+					last_source = last_source->mnt_master;
+					last_dest = last_source->mnt_parent;
+				}
+				break;
+			}
 		}
+		type = CL_SLAVE;
+		/* beginning of peer group among the slaves? */
+		if (IS_MNT_SHARED(m))
+			type |= CL_MAKE_SHARED;
 	}
-	/* slave of the earlier, then */
-	*type = CL_SLAVE;
-	/* beginning of peer group among the slaves? */
-	if (IS_MNT_SHARED(dest))
-		*type |= CL_MAKE_SHARED;
-	return last_src;
+		
+	/* Notice when we are propagating across user namespaces */
+	if (m->mnt_ns->user_ns != user_ns)
+		type |= CL_UNPRIVILEGED;
+	child = copy_tree(last_source, last_source->mnt.mnt_root, type);
+	if (IS_ERR(child))
+		return PTR_ERR(child);
+	mnt_set_mountpoint(m, mp, child);
+	last_dest = m;
+	last_source = child;
+	if (m->mnt_master != dest_master) {
+		read_seqlock_excl(&mount_lock);
+		SET_MNT_MARK(m->mnt_master);
+		read_sequnlock_excl(&mount_lock);
+	}
+	hlist_add_head(&child->mnt_hash, list);
+	return 0;
 }
 
 /*
@@ -222,56 +270,48 @@ static struct mount *get_source(struct mount *dest,
 int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp,
 		    struct mount *source_mnt, struct hlist_head *tree_list)
 {
-	struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns;
-	struct mount *m, *child;
+	struct mount *m, *n;
 	int ret = 0;
-	struct mount *prev_dest_mnt = dest_mnt;
-	struct mount *prev_src_mnt  = source_mnt;
-	HLIST_HEAD(tmp_list);
-
-	for (m = propagation_next(dest_mnt, dest_mnt); m;
-			m = propagation_next(m, dest_mnt)) {
-		int type;
-		struct mount *source;
-
-		if (IS_MNT_NEW(m))
-			continue;
-
-		source =  get_source(m, prev_dest_mnt, prev_src_mnt, &type);
-
-		/* Notice when we are propagating across user namespaces */
-		if (m->mnt_ns->user_ns != user_ns)
-			type |= CL_UNPRIVILEGED;
-
-		child = copy_tree(source, source->mnt.mnt_root, type);
-		if (IS_ERR(child)) {
-			ret = PTR_ERR(child);
-			tmp_list = *tree_list;
-			tmp_list.first->pprev = &tmp_list.first;
-			INIT_HLIST_HEAD(tree_list);
+
+	/*
+	 * we don't want to bother passing tons of arguments to
+	 * propagate_one(); everything is serialized by namespace_sem,
+	 * so globals will do just fine.
+	 */
+	user_ns = current->nsproxy->mnt_ns->user_ns;
+	last_dest = dest_mnt;
+	last_source = source_mnt;
+	mp = dest_mp;
+	list = tree_list;
+	dest_master = dest_mnt->mnt_master;
+
+	/* all peers of dest_mnt, except dest_mnt itself */
+	for (n = next_peer(dest_mnt); n != dest_mnt; n = next_peer(n)) {
+		ret = propagate_one(n);
+		if (ret)
 			goto out;
-		}
+	}
 
-		if (is_subdir(dest_mp->m_dentry, m->mnt.mnt_root)) {
-			mnt_set_mountpoint(m, dest_mp, child);
-			hlist_add_head(&child->mnt_hash, tree_list);
-		} else {
-			/*
-			 * This can happen if the parent mount was bind mounted
-			 * on some subdirectory of a shared/slave mount.
-			 */
-			hlist_add_head(&child->mnt_hash, &tmp_list);
-		}
-		prev_dest_mnt = m;
-		prev_src_mnt  = child;
+	/* all slave groups */
+	for (m = next_group(dest_mnt, dest_mnt); m;
+			m = next_group(m, dest_mnt)) {
+		/* everything in that slave group */
+		n = m;
+		do {
+			ret = propagate_one(n);
+			if (ret)
+				goto out;
+			n = next_peer(n);
+		} while (n != m);
 	}
 out:
-	lock_mount_hash();
-	while (!hlist_empty(&tmp_list)) {
-		child = hlist_entry(tmp_list.first, struct mount, mnt_hash);
-		umount_tree(child, 0);
+	read_seqlock_excl(&mount_lock);
+	hlist_for_each_entry(n, tree_list, mnt_hash) {
+		m = n->mnt_parent;
+		if (m->mnt_master != dest_mnt->mnt_master)
+			CLEAR_MNT_MARK(m->mnt_master);
 	}
-	unlock_mount_hash();
+	read_sequnlock_excl(&mount_lock);
 	return ret;
 }
 

fs/pnode.h

@@ -16,6 +16,9 @@
 #define IS_MNT_NEW(m)  (!(m)->mnt_ns)
 #define CLEAR_MNT_SHARED(m) ((m)->mnt.mnt_flags &= ~MNT_SHARED)
 #define IS_MNT_UNBINDABLE(m) ((m)->mnt.mnt_flags & MNT_UNBINDABLE)
+#define IS_MNT_MARKED(m) ((m)->mnt.mnt_flags & MNT_MARKED)
+#define SET_MNT_MARK(m) ((m)->mnt.mnt_flags |= MNT_MARKED)
+#define CLEAR_MNT_MARK(m) ((m)->mnt.mnt_flags &= ~MNT_MARKED)
 
 #define CL_EXPIRE    		0x01
 #define CL_SLAVE     		0x02

fs/proc/namespaces.c

@@ -146,7 +146,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl
 	struct task_struct *task;
 	void *ns;
 	char name[50];
-	int len = -EACCES;
+	int res = -EACCES;
 
 	task = get_proc_task(inode);
 	if (!task)
@@ -155,24 +155,18 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl
 	if (!ptrace_may_access(task, PTRACE_MODE_READ))
 		goto out_put_task;
 
-	len = -ENOENT;
+	res = -ENOENT;
 	ns = ns_ops->get(task);
 	if (!ns)
 		goto out_put_task;
 
 	snprintf(name, sizeof(name), "%s:[%u]", ns_ops->name, ns_ops->inum(ns));
-	len = strlen(name);
-
-	if (len > buflen)
-		len = buflen;
-	if (copy_to_user(buffer, name, len))
-		len = -EFAULT;
-
+	res = readlink_copy(buffer, buflen, name);
 	ns_ops->put(ns);
 out_put_task:
 	put_task_struct(task);
 out:
-	return len;
+	return res;
 }
 
 static const struct inode_operations proc_ns_link_inode_operations = {

fs/proc/self.c

@@ -16,7 +16,7 @@ static int proc_self_readlink(struct dentry *dentry, char __user *buffer,
 	if (!tgid)
 		return -ENOENT;
 	sprintf(tmp, "%d", tgid);
-	return vfs_readlink(dentry,buffer,buflen,tmp);
+	return readlink_copy(buffer, buflen, tmp);
 }
 
 static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd)

fs/proc_namespace.c

@@ -267,6 +267,7 @@ static int mounts_open_common(struct inode *inode, struct file *file,
 	p->root = root;
 	p->m.poll_event = ns->event;
 	p->show = show;
+	p->cached_event = ~0ULL;
 
 	return 0;
 

fs/splice.c

@@ -136,8 +136,6 @@ error:
 
 const struct pipe_buf_operations page_cache_pipe_buf_ops = {
 	.can_merge = 0,
-	.map = generic_pipe_buf_map,
-	.unmap = generic_pipe_buf_unmap,
 	.confirm = page_cache_pipe_buf_confirm,
 	.release = page_cache_pipe_buf_release,
 	.steal = page_cache_pipe_buf_steal,
@@ -156,8 +154,6 @@ static int user_page_pipe_buf_steal(struct pipe_inode_info *pipe,
 
 static const struct pipe_buf_operations user_page_pipe_buf_ops = {
 	.can_merge = 0,
-	.map = generic_pipe_buf_map,
-	.unmap = generic_pipe_buf_unmap,
 	.confirm = generic_pipe_buf_confirm,
 	.release = page_cache_pipe_buf_release,
 	.steal = user_page_pipe_buf_steal,
@@ -547,8 +543,6 @@ EXPORT_SYMBOL(generic_file_splice_read);
 
 static const struct pipe_buf_operations default_pipe_buf_ops = {
 	.can_merge = 0,
-	.map = generic_pipe_buf_map,
-	.unmap = generic_pipe_buf_unmap,
 	.confirm = generic_pipe_buf_confirm,
 	.release = generic_pipe_buf_release,
 	.steal = generic_pipe_buf_steal,
@@ -564,8 +558,6 @@ static int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe,
 /* Pipe buffer operations for a socket and similar. */
 const struct pipe_buf_operations nosteal_pipe_buf_ops = {
 	.can_merge = 0,
-	.map = generic_pipe_buf_map,
-	.unmap = generic_pipe_buf_unmap,
 	.confirm = generic_pipe_buf_confirm,
 	.release = generic_pipe_buf_release,
 	.steal = generic_pipe_buf_nosteal,
@@ -767,13 +759,13 @@ int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 		goto out;
 
 	if (buf->page != page) {
-		char *src = buf->ops->map(pipe, buf, 1);
+		char *src = kmap_atomic(buf->page);
 		char *dst = kmap_atomic(page);
 
 		memcpy(dst + offset, src + buf->offset, this_len);
 		flush_dcache_page(page);
 		kunmap_atomic(dst);
-		buf->ops->unmap(pipe, buf, src);
+		kunmap_atomic(src);
 	}
 	ret = pagecache_write_end(file, mapping, sd->pos, this_len, this_len,
 				page, fsdata);
@@ -1067,9 +1059,9 @@ static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 	void *data;
 	loff_t tmp = sd->pos;
 
-	data = buf->ops->map(pipe, buf, 0);
+	data = kmap(buf->page);
 	ret = __kernel_write(sd->u.file, data + buf->offset, sd->len, &tmp);
-	buf->ops->unmap(pipe, buf, data);
+	kunmap(buf->page);
 
 	return ret;
 }
@@ -1528,116 +1520,48 @@ static int get_iovec_page_array(const struct iovec __user *iov,
 static int pipe_to_user(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 			struct splice_desc *sd)
 {
-	char *src;
-	int ret;
-
-	/*
-	 * See if we can use the atomic maps, by prefaulting in the
-	 * pages and doing an atomic copy
-	 */
-	if (!fault_in_pages_writeable(sd->u.userptr, sd->len)) {
-		src = buf->ops->map(pipe, buf, 1);
-		ret = __copy_to_user_inatomic(sd->u.userptr, src + buf->offset,
-							sd->len);
-		buf->ops->unmap(pipe, buf, src);
-		if (!ret) {
-			ret = sd->len;
-			goto out;
-		}
-	}
-
-	/*
-	 * No dice, use slow non-atomic map and copy
- 	 */
-	src = buf->ops->map(pipe, buf, 0);
-
-	ret = sd->len;
-	if (copy_to_user(sd->u.userptr, src + buf->offset, sd->len))
-		ret = -EFAULT;
-
-	buf->ops->unmap(pipe, buf, src);
-out:
-	if (ret > 0)
-		sd->u.userptr += ret;
-	return ret;
+	int n = copy_page_to_iter(buf->page, buf->offset, sd->len, sd->u.data);
+	return n == sd->len ? n : -EFAULT;
 }
 
 /*
  * For lack of a better implementation, implement vmsplice() to userspace
  * as a simple copy of the pipes pages to the user iov.
  */
-static long vmsplice_to_user(struct file *file, const struct iovec __user *iov,
+static long vmsplice_to_user(struct file *file, const struct iovec __user *uiov,
 			     unsigned long nr_segs, unsigned int flags)
 {
 	struct pipe_inode_info *pipe;
 	struct splice_desc sd;
-	ssize_t size;
-	int error;
 	long ret;
+	struct iovec iovstack[UIO_FASTIOV];
+	struct iovec *iov = iovstack;
+	struct iov_iter iter;
+	ssize_t count = 0;
 
 	pipe = get_pipe_info(file);
 	if (!pipe)
 		return -EBADF;
 
-	pipe_lock(pipe);
-
-	error = ret = 0;
-	while (nr_segs) {
-		void __user *base;
-		size_t len;
-
-		/*
-		 * Get user address base and length for this iovec.
-		 */
-		error = get_user(base, &iov->iov_base);
-		if (unlikely(error))
-			break;
-		error = get_user(len, &iov->iov_len);
-		if (unlikely(error))
-			break;
-
-		/*
-		 * Sanity check this iovec. 0 read succeeds.
-		 */
-		if (unlikely(!len))
-			break;
-		if (unlikely(!base)) {
-			error = -EFAULT;
-			break;
-		}
-
-		if (unlikely(!access_ok(VERIFY_WRITE, base, len))) {
-			error = -EFAULT;
-			break;
-		}
-
-		sd.len = 0;
-		sd.total_len = len;
-		sd.flags = flags;
-		sd.u.userptr = base;
-		sd.pos = 0;
-
-		size = __splice_from_pipe(pipe, &sd, pipe_to_user);
-		if (size < 0) {
-			if (!ret)
-				ret = size;
-
-			break;
-		}
-
-		ret += size;
+	ret = rw_copy_check_uvector(READ, uiov, nr_segs,
+				    ARRAY_SIZE(iovstack), iovstack, &iov);
+	if (ret <= 0)
+		return ret;
 
-		if (size < len)
-			break;
+	iov_iter_init(&iter, iov, nr_segs, count, 0);
 
-		nr_segs--;
-		iov++;
-	}
+	sd.len = 0;
+	sd.total_len = count;
+	sd.flags = flags;
+	sd.u.data = &iter;
+	sd.pos = 0;
 
+	pipe_lock(pipe);
+	ret = __splice_from_pipe(pipe, &sd, pipe_to_user);
 	pipe_unlock(pipe);
 
-	if (!ret)
-		ret = error;
+	if (iov != iovstack)
+		kfree(iov);
 
 	return ret;
 }

fs/udf/file.c

@@ -171,7 +171,7 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	} else
 		up_write(&iinfo->i_data_sem);
 
-	retval = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+	retval = __generic_file_aio_write(iocb, iov, nr_segs);
 	mutex_unlock(&inode->i_mutex);
 
 	if (retval > 0) {

fs/xfs/xfs_file.c

@@ -699,7 +699,7 @@ xfs_file_dio_aio_write(
 
 	trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0);
 	ret = generic_file_direct_write(iocb, iovp,
-			&nr_segs, pos, &iocb->ki_pos, count, ocount);
+			&nr_segs, pos, count, ocount);
 
 out:
 	xfs_rw_iunlock(ip, iolock);
@@ -715,7 +715,7 @@ xfs_file_buffered_aio_write(
 	const struct iovec	*iovp,
 	unsigned long		nr_segs,
 	loff_t			pos,
-	size_t			ocount)
+	size_t			count)
 {
 	struct file		*file = iocb->ki_filp;
 	struct address_space	*mapping = file->f_mapping;
@@ -724,7 +724,7 @@ xfs_file_buffered_aio_write(
 	ssize_t			ret;
 	int			enospc = 0;
 	int			iolock = XFS_IOLOCK_EXCL;
-	size_t			count = ocount;
+	struct iov_iter		from;
 
 	xfs_rw_ilock(ip, iolock);
 
@@ -732,14 +732,15 @@ xfs_file_buffered_aio_write(
 	if (ret)
 		goto out;
 
+	iov_iter_init(&from, iovp, nr_segs, count, 0);
 	/* We can write back this queue in page reclaim */
 	current->backing_dev_info = mapping->backing_dev_info;
 
 write_retry:
 	trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, 0);
-	ret = generic_file_buffered_write(iocb, iovp, nr_segs,
-			pos, &iocb->ki_pos, count, 0);
-
+	ret = generic_perform_write(file, &from, pos);
+	if (likely(ret >= 0))
+		iocb->ki_pos = pos + ret;
 	/*
 	 * If we just got an ENOSPC, try to write back all dirty inodes to
 	 * convert delalloc space to free up some of the excess reserved

fs/xfs/xfs_ioctl.c

@@ -271,32 +271,6 @@ xfs_open_by_handle(
 	return error;
 }
 
-/*
- * This is a copy from fs/namei.c:vfs_readlink(), except for removing it's
- * unused first argument.
- */
-STATIC int
-do_readlink(
-	char __user		*buffer,
-	int			buflen,
-	const char		*link)
-{
-        int len;
-
-	len = PTR_ERR(link);
-	if (IS_ERR(link))
-		goto out;
-
-	len = strlen(link);
-	if (len > (unsigned) buflen)
-		len = buflen;
-	if (copy_to_user(buffer, link, len))
-		len = -EFAULT;
- out:
-	return len;
-}
-
-
 int
 xfs_readlink_by_handle(
 	struct file		*parfilp,
@@ -334,7 +308,7 @@ xfs_readlink_by_handle(
 	error = -xfs_readlink(XFS_I(dentry->d_inode), link);
 	if (error)
 		goto out_kfree;
-	error = do_readlink(hreq->ohandle, olen, link);
+	error = readlink_copy(hreq->ohandle, olen, link);
 	if (error)
 		goto out_kfree;
 

include/linux/bio.h

@@ -388,7 +388,7 @@ struct sg_iovec;
 struct rq_map_data;
 extern struct bio *bio_map_user_iov(struct request_queue *,
 				    struct block_device *,
-				    struct sg_iovec *, int, int, gfp_t);
+				    const struct sg_iovec *, int, int, gfp_t);
 extern void bio_unmap_user(struct bio *);
 extern struct bio *bio_map_kern(struct request_queue *, void *, unsigned int,
 				gfp_t);
@@ -414,7 +414,8 @@ extern int bio_alloc_pages(struct bio *bio, gfp_t gfp);
 extern struct bio *bio_copy_user(struct request_queue *, struct rq_map_data *,
 				 unsigned long, unsigned int, int, gfp_t);
 extern struct bio *bio_copy_user_iov(struct request_queue *,
-				     struct rq_map_data *, struct sg_iovec *,
+				     struct rq_map_data *,
+				     const struct sg_iovec *,
 				     int, int, gfp_t);
 extern int bio_uncopy_user(struct bio *);
 void zero_fill_bio(struct bio *bio);

include/linux/blkdev.h

@@ -835,8 +835,8 @@ extern int blk_rq_map_user(struct request_queue *, struct request *,
 extern int blk_rq_unmap_user(struct bio *);
 extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t);
 extern int blk_rq_map_user_iov(struct request_queue *, struct request *,
-			       struct rq_map_data *, struct sg_iovec *, int,
-			       unsigned int, gfp_t);
+			       struct rq_map_data *, const struct sg_iovec *,
+			       int, unsigned int, gfp_t);
 extern int blk_execute_rq(struct request_queue *, struct gendisk *,
 			  struct request *, int);
 extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,

include/linux/buffer_head.h

@@ -210,8 +210,8 @@ int block_write_full_page(struct page *page, get_block_t *get_block,
 int block_write_full_page_endio(struct page *page, get_block_t *get_block,
 			struct writeback_control *wbc, bh_end_io_t *handler);
 int block_read_full_page(struct page*, get_block_t*);
-int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
-				unsigned long from);
+int block_is_partially_uptodate(struct page *page, unsigned long from,
+				unsigned long count);
 int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
 		unsigned flags, struct page **pagep, get_block_t *get_block);
 int __block_write_begin(struct page *page, loff_t pos, unsigned len,

include/linux/fdtable.h

@@ -63,8 +63,6 @@ struct file_operations;
 struct vfsmount;
 struct dentry;
 
-extern void __init files_defer_init(void);
-
 #define rcu_dereference_check_fdtable(files, fdtfd) \
 	rcu_dereference_check((fdtfd), lockdep_is_held(&(files)->file_lock))
 

include/linux/fs.h

@@ -48,6 +48,7 @@ struct cred;
 struct swap_info_struct;
 struct seq_file;
 struct workqueue_struct;
+struct iov_iter;
 
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);
@@ -125,6 +126,8 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 
 /* File needs atomic accesses to f_pos */
 #define FMODE_ATOMIC_POS	((__force fmode_t)0x8000)
+/* Write access to underlying fs */
+#define FMODE_WRITER		((__force fmode_t)0x10000)
 
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY		((__force fmode_t)0x1000000)
@@ -293,38 +296,6 @@ struct page;
 struct address_space;
 struct writeback_control;
 
-struct iov_iter {
-	const struct iovec *iov;
-	unsigned long nr_segs;
-	size_t iov_offset;
-	size_t count;
-};
-
-size_t iov_iter_copy_from_user_atomic(struct page *page,
-		struct iov_iter *i, unsigned long offset, size_t bytes);
-size_t iov_iter_copy_from_user(struct page *page,
-		struct iov_iter *i, unsigned long offset, size_t bytes);
-void iov_iter_advance(struct iov_iter *i, size_t bytes);
-int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
-size_t iov_iter_single_seg_count(const struct iov_iter *i);
-
-static inline void iov_iter_init(struct iov_iter *i,
-			const struct iovec *iov, unsigned long nr_segs,
-			size_t count, size_t written)
-{
-	i->iov = iov;
-	i->nr_segs = nr_segs;
-	i->iov_offset = 0;
-	i->count = count + written;
-
-	iov_iter_advance(i, written);
-}
-
-static inline size_t iov_iter_count(struct iov_iter *i)
-{
-	return i->count;
-}
-
 /*
  * "descriptor" for what we're up to with a read.
  * This allows us to use the same read code yet
@@ -383,7 +354,7 @@ struct address_space_operations {
 	int (*migratepage) (struct address_space *,
 			struct page *, struct page *, enum migrate_mode);
 	int (*launder_page) (struct page *);
-	int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
+	int (*is_partially_uptodate) (struct page *, unsigned long,
 					unsigned long);
 	void (*is_dirty_writeback) (struct page *, bool *, bool *);
 	int (*error_remove_page)(struct address_space *, struct page *);
@@ -770,9 +741,6 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
 		index <  ra->start + ra->size);
 }
 
-#define FILE_MNT_WRITE_TAKEN	1
-#define FILE_MNT_WRITE_RELEASED	2
-
 struct file {
 	union {
 		struct llist_node	fu_llist;
@@ -810,9 +778,6 @@ struct file {
 	struct list_head	f_tfile_llink;
 #endif /* #ifdef CONFIG_EPOLL */
 	struct address_space	*f_mapping;
-#ifdef CONFIG_DEBUG_WRITECOUNT
-	unsigned long f_mnt_write_state;
-#endif
 } __attribute__((aligned(4)));	/* lest something weird decides that 2 is OK */
 
 struct file_handle {
@@ -830,49 +795,6 @@ static inline struct file *get_file(struct file *f)
 #define fput_atomic(x)	atomic_long_add_unless(&(x)->f_count, -1, 1)
 #define file_count(x)	atomic_long_read(&(x)->f_count)
 
-#ifdef CONFIG_DEBUG_WRITECOUNT
-static inline void file_take_write(struct file *f)
-{
-	WARN_ON(f->f_mnt_write_state != 0);
-	f->f_mnt_write_state = FILE_MNT_WRITE_TAKEN;
-}
-static inline void file_release_write(struct file *f)
-{
-	f->f_mnt_write_state |= FILE_MNT_WRITE_RELEASED;
-}
-static inline void file_reset_write(struct file *f)
-{
-	f->f_mnt_write_state = 0;
-}
-static inline void file_check_state(struct file *f)
-{
-	/*
-	 * At this point, either both or neither of these bits
-	 * should be set.
-	 */
-	WARN_ON(f->f_mnt_write_state == FILE_MNT_WRITE_TAKEN);
-	WARN_ON(f->f_mnt_write_state == FILE_MNT_WRITE_RELEASED);
-}
-static inline int file_check_writeable(struct file *f)
-{
-	if (f->f_mnt_write_state == FILE_MNT_WRITE_TAKEN)
-		return 0;
-	printk(KERN_WARNING "writeable file with no "
-			    "mnt_want_write()\n");
-	WARN_ON(1);
-	return -EINVAL;
-}
-#else /* !CONFIG_DEBUG_WRITECOUNT */
-static inline void file_take_write(struct file *filp) {}
-static inline void file_release_write(struct file *filp) {}
-static inline void file_reset_write(struct file *filp) {}
-static inline void file_check_state(struct file *filp) {}
-static inline int file_check_writeable(struct file *filp)
-{
-	return 0;
-}
-#endif /* CONFIG_DEBUG_WRITECOUNT */
-
 #define	MAX_NON_LFS	((1UL<<31) - 1)
 
 /* Page cache limit. The filesystems should put that into their s_maxbytes 
@@ -2481,16 +2403,13 @@ extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr,
 		unsigned long size, pgoff_t pgoff);
-extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size);
 int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
 extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t);
-extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long,
-		loff_t *);
+extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long);
 extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t);
 extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *,
-		unsigned long *, loff_t, loff_t *, size_t, size_t);
-extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *,
-		unsigned long, loff_t, loff_t *, size_t, ssize_t);
+		unsigned long *, loff_t, size_t, size_t);
+extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t);
 extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos);
 extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos);
 extern int generic_segment_checks(const struct iovec *iov,
@@ -2582,7 +2501,7 @@ extern const struct file_operations generic_ro_fops;
 
 #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m))
 
-extern int vfs_readlink(struct dentry *, char __user *, int, const char *);
+extern int readlink_copy(char __user *, int, const char *);
 extern int page_readlink(struct dentry *, char __user *, int);
 extern void *page_follow_link_light(struct dentry *, struct nameidata *);
 extern void page_put_link(struct dentry *, struct nameidata *, void *);

include/linux/mount.h

@@ -44,6 +44,8 @@ struct mnt_namespace;
 #define MNT_SHARED_MASK	(MNT_UNBINDABLE)
 #define MNT_PROPAGATION_MASK	(MNT_SHARED | MNT_UNBINDABLE)
 
+#define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \
+			    MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED)
 
 #define MNT_INTERNAL	0x4000
 
@@ -51,6 +53,7 @@ struct mnt_namespace;
 #define MNT_LOCKED		0x800000
 #define MNT_DOOMED		0x1000000
 #define MNT_SYNC_UMOUNT		0x2000000
+#define MNT_MARKED		0x4000000
 
 struct vfsmount {
 	struct dentry *mnt_root;	/* root of the mounted tree */

include/linux/nbd.h

@@ -24,8 +24,7 @@ struct request;
 struct nbd_device {
 	int flags;
 	int harderror;		/* Code of hard error			*/
-	struct socket * sock;
-	struct file * file; 	/* If == NULL, device is not ready, yet	*/
+	struct socket * sock;	/* If == NULL, device is not ready, yet	*/
 	int magic;
 
 	spinlock_t queue_lock;

include/linux/pipe_fs_i.h

@@ -82,23 +82,6 @@ struct pipe_buf_operations {
 	 */
 	int can_merge;
 
-	/*
-	 * ->map() returns a virtual address mapping of the pipe buffer.
-	 * The last integer flag reflects whether this should be an atomic
-	 * mapping or not. The atomic map is faster, however you can't take
-	 * page faults before calling ->unmap() again. So if you need to eg
-	 * access user data through copy_to/from_user(), then you must get
-	 * a non-atomic map. ->map() uses the kmap_atomic slot for
-	 * atomic maps, you have to be careful if mapping another page as
-	 * source or destination for a copy.
-	 */
-	void * (*map)(struct pipe_inode_info *, struct pipe_buffer *, int);
-
-	/*
-	 * Undoes ->map(), finishes the virtual mapping of the pipe buffer.
-	 */
-	void (*unmap)(struct pipe_inode_info *, struct pipe_buffer *, void *);
-
 	/*
 	 * ->confirm() verifies that the data in the pipe buffer is there
 	 * and that the contents are good. If the pages in the pipe belong
@@ -150,8 +133,6 @@ struct pipe_inode_info *alloc_pipe_info(void);
 void free_pipe_info(struct pipe_inode_info *);
 
 /* Generic pipe buffer ops functions */
-void *generic_pipe_buf_map(struct pipe_inode_info *, struct pipe_buffer *, int);
-void generic_pipe_buf_unmap(struct pipe_inode_info *, struct pipe_buffer *, void *);
 void generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *);

include/linux/uio.h

@@ -9,14 +9,23 @@
 #ifndef __LINUX_UIO_H
 #define __LINUX_UIO_H
 
+#include <linux/kernel.h>
 #include <uapi/linux/uio.h>
 
+struct page;
 
 struct kvec {
 	void *iov_base; /* and that should *never* hold a userland pointer */
 	size_t iov_len;
 };
 
+struct iov_iter {
+	const struct iovec *iov;
+	unsigned long nr_segs;
+	size_t iov_offset;
+	size_t count;
+};
+
 /*
  * Total number of bytes covered by an iovec.
  *
@@ -34,8 +43,51 @@ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs)
 	return ret;
 }
 
+static inline struct iovec iov_iter_iovec(const struct iov_iter *iter)
+{
+	return (struct iovec) {
+		.iov_base = iter->iov->iov_base + iter->iov_offset,
+		.iov_len = min(iter->count,
+			       iter->iov->iov_len - iter->iov_offset),
+	};
+}
+
+#define iov_for_each(iov, iter, start)				\
+	for (iter = (start);					\
+	     (iter).count &&					\
+	     ((iov = iov_iter_iovec(&(iter))), 1);		\
+	     iov_iter_advance(&(iter), (iov).iov_len))
+
 unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to);
 
+size_t iov_iter_copy_from_user_atomic(struct page *page,
+		struct iov_iter *i, unsigned long offset, size_t bytes);
+size_t iov_iter_copy_from_user(struct page *page,
+		struct iov_iter *i, unsigned long offset, size_t bytes);
+void iov_iter_advance(struct iov_iter *i, size_t bytes);
+int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
+size_t iov_iter_single_seg_count(const struct iov_iter *i);
+size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
+			 struct iov_iter *i);
+
+static inline void iov_iter_init(struct iov_iter *i,
+			const struct iovec *iov, unsigned long nr_segs,
+			size_t count, size_t written)
+{
+	i->iov = iov;
+	i->nr_segs = nr_segs;
+	i->iov_offset = 0;
+	i->count = count + written;
+
+	iov_iter_advance(i, written);
+}
+
+static inline size_t iov_iter_count(struct iov_iter *i)
+{
+	return i->count;
+}
+
 int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len);
 int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len);
+
 #endif

kernel/relay.c

@@ -1195,8 +1195,6 @@ static void relay_pipe_buf_release(struct pipe_inode_info *pipe,
 
 static const struct pipe_buf_operations relay_pipe_buf_ops = {
 	.can_merge = 0,
-	.map = generic_pipe_buf_map,
-	.unmap = generic_pipe_buf_unmap,
 	.confirm = generic_pipe_buf_confirm,
 	.release = relay_pipe_buf_release,
 	.steal = generic_pipe_buf_steal,
@@ -1253,7 +1251,7 @@ static ssize_t subbuf_splice_actor(struct file *in,
 	subbuf_pages = rbuf->chan->alloc_size >> PAGE_SHIFT;
 	pidx = (read_start / PAGE_SIZE) % subbuf_pages;
 	poff = read_start & ~PAGE_MASK;
-	nr_pages = min_t(unsigned int, subbuf_pages, pipe->buffers);
+	nr_pages = min_t(unsigned int, subbuf_pages, spd.nr_pages_max);
 
 	for (total_len = 0; spd.nr_pages < nr_pages; spd.nr_pages++) {
 		unsigned int this_len, this_end, private;

kernel/trace/trace.c

@@ -4392,8 +4392,6 @@ static void tracing_spd_release_pipe(struct splice_pipe_desc *spd,
 
 static const struct pipe_buf_operations tracing_pipe_buf_ops = {
 	.can_merge		= 0,
-	.map			= generic_pipe_buf_map,
-	.unmap			= generic_pipe_buf_unmap,
 	.confirm		= generic_pipe_buf_confirm,
 	.release		= generic_pipe_buf_release,
 	.steal			= generic_pipe_buf_steal,
@@ -4488,7 +4486,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 	trace_access_lock(iter->cpu_file);
 
 	/* Fill as many pages as possible. */
-	for (i = 0, rem = len; i < pipe->buffers && rem; i++) {
+	for (i = 0, rem = len; i < spd.nr_pages_max && rem; i++) {
 		spd.pages[i] = alloc_page(GFP_KERNEL);
 		if (!spd.pages[i])
 			break;
@@ -5281,8 +5279,6 @@ static void buffer_pipe_buf_get(struct pipe_inode_info *pipe,
 /* Pipe buffer operations for a buffer. */
 static const struct pipe_buf_operations buffer_pipe_buf_ops = {
 	.can_merge		= 0,
-	.map			= generic_pipe_buf_map,
-	.unmap			= generic_pipe_buf_unmap,
 	.confirm		= generic_pipe_buf_confirm,
 	.release		= buffer_pipe_buf_release,
 	.steal			= generic_pipe_buf_steal,
@@ -5358,7 +5354,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 	trace_access_lock(iter->cpu_file);
 	entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file);
 
-	for (i = 0; i < pipe->buffers && len && entries; i++, len -= PAGE_SIZE) {
+	for (i = 0; i < spd.nr_pages_max && len && entries; i++, len -= PAGE_SIZE) {
 		struct page *page;
 		int r;
 

lib/Kconfig.debug

@@ -1045,16 +1045,6 @@ config DEBUG_BUGVERBOSE
 	  of the BUG call as well as the EIP and oops trace.  This aids
 	  debugging but costs about 70-100K of memory.
 
-config DEBUG_WRITECOUNT
-	bool "Debug filesystem writers count"
-	depends on DEBUG_KERNEL
-	help
-	  Enable this to catch wrong use of the writers count in struct
-	  vfsmount.  This will increase the size of each file struct by
-	  32 bits.
-
-	  If unsure, say N.
-
 config DEBUG_LIST
 	bool "Debug linked list manipulation"
 	depends on DEBUG_KERNEL

mm/Makefile

@@ -17,7 +17,8 @@ obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
 			   util.o mmzone.o vmstat.o backing-dev.o \
 			   mm_init.o mmu_context.o percpu.o slab_common.o \
 			   compaction.o balloon_compaction.o vmacache.o \
-			   interval_tree.o list_lru.o workingset.o $(mmu-y)
+			   interval_tree.o list_lru.o workingset.o \
+			   iov_iter.o $(mmu-y)
 
 obj-y += init-mm.o
 

mm/filemap.c

@@ -77,7 +77,7 @@
  *  ->mmap_sem
  *    ->lock_page		(access_process_vm)
  *
- *  ->i_mutex			(generic_file_buffered_write)
+ *  ->i_mutex			(generic_perform_write)
  *    ->mmap_sem		(fault_in_pages_readable->do_page_fault)
  *
  *  bdi->wb.list_lock
@@ -1428,7 +1428,8 @@ static void shrink_readahead_size_eio(struct file *filp,
  * do_generic_file_read - generic file read routine
  * @filp:	the file to read
  * @ppos:	current file position
- * @desc:	read_descriptor
+ * @iter:	data destination
+ * @written:	already copied
  *
  * This is a generic file read routine, and uses the
  * mapping->a_ops->readpage() function for the actual low-level stuff.
@@ -1436,8 +1437,8 @@ static void shrink_readahead_size_eio(struct file *filp,
  * This is really ugly. But the goto's actually try to clarify some
  * of the logic when it comes to error handling etc.
  */
-static void do_generic_file_read(struct file *filp, loff_t *ppos,
-		read_descriptor_t *desc)
+static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos,
+		struct iov_iter *iter, ssize_t written)
 {
 	struct address_space *mapping = filp->f_mapping;
 	struct inode *inode = mapping->host;
@@ -1447,12 +1448,12 @@ static void do_generic_file_read(struct file *filp, loff_t *ppos,
 	pgoff_t prev_index;
 	unsigned long offset;      /* offset into pagecache page */
 	unsigned int prev_offset;
-	int error;
+	int error = 0;
 
 	index = *ppos >> PAGE_CACHE_SHIFT;
 	prev_index = ra->prev_pos >> PAGE_CACHE_SHIFT;
 	prev_offset = ra->prev_pos & (PAGE_CACHE_SIZE-1);
-	last_index = (*ppos + desc->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
+	last_index = (*ppos + iter->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
 	offset = *ppos & ~PAGE_CACHE_MASK;
 
 	for (;;) {
@@ -1487,7 +1488,7 @@ find_page:
 			if (!page->mapping)
 				goto page_not_up_to_date_locked;
 			if (!mapping->a_ops->is_partially_uptodate(page,
-								desc, offset))
+							offset, iter->count))
 				goto page_not_up_to_date_locked;
 			unlock_page(page);
 		}
@@ -1537,24 +1538,23 @@ page_ok:
 		/*
 		 * Ok, we have the page, and it's up-to-date, so
 		 * now we can copy it to user space...
-		 *
-		 * The file_read_actor routine returns how many bytes were
-		 * actually used..
-		 * NOTE! This may not be the same as how much of a user buffer
-		 * we filled up (we may be padding etc), so we can only update
-		 * "pos" here (the actor routine has to update the user buffer
-		 * pointers and the remaining count).
 		 */
-		ret = file_read_actor(desc, page, offset, nr);
+
+		ret = copy_page_to_iter(page, offset, nr, iter);
 		offset += ret;
 		index += offset >> PAGE_CACHE_SHIFT;
 		offset &= ~PAGE_CACHE_MASK;
 		prev_offset = offset;
 
 		page_cache_release(page);
-		if (ret == nr && desc->count)
-			continue;
-		goto out;
+		written += ret;
+		if (!iov_iter_count(iter))
+			goto out;
+		if (ret < nr) {
+			error = -EFAULT;
+			goto out;
+		}
+		continue;
 
 page_not_up_to_date:
 		/* Get exclusive access to the page ... */
@@ -1589,6 +1589,7 @@ readpage:
 		if (unlikely(error)) {
 			if (error == AOP_TRUNCATED_PAGE) {
 				page_cache_release(page);
+				error = 0;
 				goto find_page;
 			}
 			goto readpage_error;
@@ -1619,7 +1620,6 @@ readpage:
 
 readpage_error:
 		/* UHHUH! A synchronous read error occurred. Report it */
-		desc->error = error;
 		page_cache_release(page);
 		goto out;
 
@@ -1630,16 +1630,17 @@ no_cached_page:
 		 */
 		page = page_cache_alloc_cold(mapping);
 		if (!page) {
-			desc->error = -ENOMEM;
+			error = -ENOMEM;
 			goto out;
 		}
 		error = add_to_page_cache_lru(page, mapping,
 						index, GFP_KERNEL);
 		if (error) {
 			page_cache_release(page);
-			if (error == -EEXIST)
+			if (error == -EEXIST) {
+				error = 0;
 				goto find_page;
-			desc->error = error;
+			}
 			goto out;
 		}
 		goto readpage;
@@ -1652,44 +1653,7 @@ out:
 
 	*ppos = ((loff_t)index << PAGE_CACHE_SHIFT) + offset;
 	file_accessed(filp);
-}
-
-int file_read_actor(read_descriptor_t *desc, struct page *page,
-			unsigned long offset, unsigned long size)
-{
-	char *kaddr;
-	unsigned long left, count = desc->count;
-
-	if (size > count)
-		size = count;
-
-	/*
-	 * Faults on the destination of a read are common, so do it before
-	 * taking the kmap.
-	 */
-	if (!fault_in_pages_writeable(desc->arg.buf, size)) {
-		kaddr = kmap_atomic(page);
-		left = __copy_to_user_inatomic(desc->arg.buf,
-						kaddr + offset, size);
-		kunmap_atomic(kaddr);
-		if (left == 0)
-			goto success;
-	}
-
-	/* Do it the slow way */
-	kaddr = kmap(page);
-	left = __copy_to_user(desc->arg.buf, kaddr + offset, size);
-	kunmap(page);
-
-	if (left) {
-		size -= left;
-		desc->error = -EFAULT;
-	}
-success:
-	desc->count = count - size;
-	desc->written += size;
-	desc->arg.buf += size;
-	return size;
+	return written ? written : error;
 }
 
 /*
@@ -1747,14 +1711,15 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 {
 	struct file *filp = iocb->ki_filp;
 	ssize_t retval;
-	unsigned long seg = 0;
 	size_t count;
 	loff_t *ppos = &iocb->ki_pos;
+	struct iov_iter i;
 
 	count = 0;
 	retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
 	if (retval)
 		return retval;
+	iov_iter_init(&i, iov, nr_segs, count, 0);
 
 	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
 	if (filp->f_flags & O_DIRECT) {
@@ -1776,6 +1741,11 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 		if (retval > 0) {
 			*ppos = pos + retval;
 			count -= retval;
+			/*
+			 * If we did a short DIO read we need to skip the
+			 * section of the iov that we've already read data into.
+			 */
+			iov_iter_advance(&i, retval);
 		}
 
 		/*
@@ -1792,39 +1762,7 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 		}
 	}
 
-	count = retval;
-	for (seg = 0; seg < nr_segs; seg++) {
-		read_descriptor_t desc;
-		loff_t offset = 0;
-
-		/*
-		 * If we did a short DIO read we need to skip the section of the
-		 * iov that we've already read data into.
-		 */
-		if (count) {
-			if (count > iov[seg].iov_len) {
-				count -= iov[seg].iov_len;
-				continue;
-			}
-			offset = count;
-			count = 0;
-		}
-
-		desc.written = 0;
-		desc.arg.buf = iov[seg].iov_base + offset;
-		desc.count = iov[seg].iov_len - offset;
-		if (desc.count == 0)
-			continue;
-		desc.error = 0;
-		do_generic_file_read(filp, ppos, &desc);
-		retval += desc.written;
-		if (desc.error) {
-			retval = retval ?: desc.error;
-			break;
-		}
-		if (desc.count > 0)
-			break;
-	}
+	retval = do_generic_file_read(filp, ppos, &i, retval);
 out:
 	return retval;
 }
@@ -2335,150 +2273,6 @@ struct page *read_cache_page_gfp(struct address_space *mapping,
 }
 EXPORT_SYMBOL(read_cache_page_gfp);
 
-static size_t __iovec_copy_from_user_inatomic(char *vaddr,
-			const struct iovec *iov, size_t base, size_t bytes)
-{
-	size_t copied = 0, left = 0;
-
-	while (bytes) {
-		char __user *buf = iov->iov_base + base;
-		int copy = min(bytes, iov->iov_len - base);
-
-		base = 0;
-		left = __copy_from_user_inatomic(vaddr, buf, copy);
-		copied += copy;
-		bytes -= copy;
-		vaddr += copy;
-		iov++;
-
-		if (unlikely(left))
-			break;
-	}
-	return copied - left;
-}
-
-/*
- * Copy as much as we can into the page and return the number of bytes which
- * were successfully copied.  If a fault is encountered then return the number of
- * bytes which were copied.
- */
-size_t iov_iter_copy_from_user_atomic(struct page *page,
-		struct iov_iter *i, unsigned long offset, size_t bytes)
-{
-	char *kaddr;
-	size_t copied;
-
-	BUG_ON(!in_atomic());
-	kaddr = kmap_atomic(page);
-	if (likely(i->nr_segs == 1)) {
-		int left;
-		char __user *buf = i->iov->iov_base + i->iov_offset;
-		left = __copy_from_user_inatomic(kaddr + offset, buf, bytes);
-		copied = bytes - left;
-	} else {
-		copied = __iovec_copy_from_user_inatomic(kaddr + offset,
-						i->iov, i->iov_offset, bytes);
-	}
-	kunmap_atomic(kaddr);
-
-	return copied;
-}
-EXPORT_SYMBOL(iov_iter_copy_from_user_atomic);
-
-/*
- * This has the same sideeffects and return value as
- * iov_iter_copy_from_user_atomic().
- * The difference is that it attempts to resolve faults.
- * Page must not be locked.
- */
-size_t iov_iter_copy_from_user(struct page *page,
-		struct iov_iter *i, unsigned long offset, size_t bytes)
-{
-	char *kaddr;
-	size_t copied;
-
-	kaddr = kmap(page);
-	if (likely(i->nr_segs == 1)) {
-		int left;
-		char __user *buf = i->iov->iov_base + i->iov_offset;
-		left = __copy_from_user(kaddr + offset, buf, bytes);
-		copied = bytes - left;
-	} else {
-		copied = __iovec_copy_from_user_inatomic(kaddr + offset,
-						i->iov, i->iov_offset, bytes);
-	}
-	kunmap(page);
-	return copied;
-}
-EXPORT_SYMBOL(iov_iter_copy_from_user);
-
-void iov_iter_advance(struct iov_iter *i, size_t bytes)
-{
-	BUG_ON(i->count < bytes);
-
-	if (likely(i->nr_segs == 1)) {
-		i->iov_offset += bytes;
-		i->count -= bytes;
-	} else {
-		const struct iovec *iov = i->iov;
-		size_t base = i->iov_offset;
-		unsigned long nr_segs = i->nr_segs;
-
-		/*
-		 * The !iov->iov_len check ensures we skip over unlikely
-		 * zero-length segments (without overruning the iovec).
-		 */
-		while (bytes || unlikely(i->count && !iov->iov_len)) {
-			int copy;
-
-			copy = min(bytes, iov->iov_len - base);
-			BUG_ON(!i->count || i->count < copy);
-			i->count -= copy;
-			bytes -= copy;
-			base += copy;
-			if (iov->iov_len == base) {
-				iov++;
-				nr_segs--;
-				base = 0;
-			}
-		}
-		i->iov = iov;
-		i->iov_offset = base;
-		i->nr_segs = nr_segs;
-	}
-}
-EXPORT_SYMBOL(iov_iter_advance);
-
-/*
- * Fault in the first iovec of the given iov_iter, to a maximum length
- * of bytes. Returns 0 on success, or non-zero if the memory could not be
- * accessed (ie. because it is an invalid address).
- *
- * writev-intensive code may want this to prefault several iovecs -- that
- * would be possible (callers must not rely on the fact that _only_ the
- * first iovec will be faulted with the current implementation).
- */
-int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes)
-{
-	char __user *buf = i->iov->iov_base + i->iov_offset;
-	bytes = min(bytes, i->iov->iov_len - i->iov_offset);
-	return fault_in_pages_readable(buf, bytes);
-}
-EXPORT_SYMBOL(iov_iter_fault_in_readable);
-
-/*
- * Return the count of just the current iov_iter segment.
- */
-size_t iov_iter_single_seg_count(const struct iov_iter *i)
-{
-	const struct iovec *iov = i->iov;
-	if (i->nr_segs == 1)
-		return i->count;
-	else
-		return min(i->count, iov->iov_len - i->iov_offset);
-}
-EXPORT_SYMBOL(iov_iter_single_seg_count);
-
 /*
  * Performs necessary checks before doing a write
  *
@@ -2585,7 +2379,7 @@ EXPORT_SYMBOL(pagecache_write_end);
 
 ssize_t
 generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
-		unsigned long *nr_segs, loff_t pos, loff_t *ppos,
+		unsigned long *nr_segs, loff_t pos,
 		size_t count, size_t ocount)
 {
 	struct file	*file = iocb->ki_filp;
@@ -2646,7 +2440,7 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 			i_size_write(inode, pos);
 			mark_inode_dirty(inode);
 		}
-		*ppos = pos;
+		iocb->ki_pos = pos;
 	}
 out:
 	return written;
@@ -2692,7 +2486,7 @@ found:
 }
 EXPORT_SYMBOL(grab_cache_page_write_begin);
 
-static ssize_t generic_perform_write(struct file *file,
+ssize_t generic_perform_write(struct file *file,
 				struct iov_iter *i, loff_t pos)
 {
 	struct address_space *mapping = file->f_mapping;
@@ -2742,9 +2536,7 @@ again:
 		if (mapping_writably_mapped(mapping))
 			flush_dcache_page(page);
 
-		pagefault_disable();
 		copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
-		pagefault_enable();
 		flush_dcache_page(page);
 
 		mark_page_accessed(page);
@@ -2782,27 +2574,7 @@ again:
 
 	return written ? written : status;
 }
-
-ssize_t
-generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
-		unsigned long nr_segs, loff_t pos, loff_t *ppos,
-		size_t count, ssize_t written)
-{
-	struct file *file = iocb->ki_filp;
-	ssize_t status;
-	struct iov_iter i;
-
-	iov_iter_init(&i, iov, nr_segs, count, written);
-	status = generic_perform_write(file, &i, pos);
-
-	if (likely(status >= 0)) {
-		written += status;
-		*ppos = pos + status;
-  	}
-	
-	return written ? written : status;
-}
-EXPORT_SYMBOL(generic_file_buffered_write);
+EXPORT_SYMBOL(generic_perform_write);
 
 /**
  * __generic_file_aio_write - write data to a file
@@ -2824,16 +2596,18 @@ EXPORT_SYMBOL(generic_file_buffered_write);
  * avoid syncing under i_mutex.
  */
 ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
-				 unsigned long nr_segs, loff_t *ppos)
+				 unsigned long nr_segs)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space * mapping = file->f_mapping;
 	size_t ocount;		/* original count */
 	size_t count;		/* after file limit checks */
 	struct inode 	*inode = mapping->host;
-	loff_t		pos;
-	ssize_t		written;
+	loff_t		pos = iocb->ki_pos;
+	ssize_t		written = 0;
 	ssize_t		err;
+	ssize_t		status;
+	struct iov_iter from;
 
 	ocount = 0;
 	err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
@@ -2841,12 +2615,9 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		return err;
 
 	count = ocount;
-	pos = *ppos;
 
 	/* We can write back this queue in page reclaim */
 	current->backing_dev_info = mapping->backing_dev_info;
-	written = 0;
-
 	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
 	if (err)
 		goto out;
@@ -2862,45 +2633,47 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	if (err)
 		goto out;
 
+	iov_iter_init(&from, iov, nr_segs, count, 0);
+
 	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
 	if (unlikely(file->f_flags & O_DIRECT)) {
 		loff_t endbyte;
-		ssize_t written_buffered;
 
-		written = generic_file_direct_write(iocb, iov, &nr_segs, pos,
-							ppos, count, ocount);
+		written = generic_file_direct_write(iocb, iov, &from.nr_segs, pos,
+							count, ocount);
 		if (written < 0 || written == count)
 			goto out;
+		iov_iter_advance(&from, written);
+
 		/*
 		 * direct-io write to a hole: fall through to buffered I/O
 		 * for completing the rest of the request.
 		 */
 		pos += written;
 		count -= written;
-		written_buffered = generic_file_buffered_write(iocb, iov,
-						nr_segs, pos, ppos, count,
-						written);
+
+		status = generic_perform_write(file, &from, pos);
 		/*
-		 * If generic_file_buffered_write() retuned a synchronous error
+		 * If generic_perform_write() returned a synchronous error
 		 * then we want to return the number of bytes which were
 		 * direct-written, or the error code if that was zero.  Note
 		 * that this differs from normal direct-io semantics, which
 		 * will return -EFOO even if some bytes were written.
 		 */
-		if (written_buffered < 0) {
-			err = written_buffered;
+		if (unlikely(status < 0) && !written) {
+			err = status;
 			goto out;
 		}
-
+		iocb->ki_pos = pos + status;
 		/*
 		 * We need to ensure that the page cache pages are written to
 		 * disk and invalidated to preserve the expected O_DIRECT
 		 * semantics.
 		 */
-		endbyte = pos + written_buffered - written - 1;
+		endbyte = pos + status - 1;
 		err = filemap_write_and_wait_range(file->f_mapping, pos, endbyte);
 		if (err == 0) {
-			written = written_buffered;
+			written += status;
 			invalidate_mapping_pages(mapping,
 						 pos >> PAGE_CACHE_SHIFT,
 						 endbyte >> PAGE_CACHE_SHIFT);
@@ -2911,8 +2684,9 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 			 */
 		}
 	} else {
-		written = generic_file_buffered_write(iocb, iov, nr_segs,
-				pos, ppos, count, written);
+		written = generic_perform_write(file, &from, pos);
+		if (likely(written >= 0))
+			iocb->ki_pos = pos + written;
 	}
 out:
 	current->backing_dev_info = NULL;
@@ -2941,7 +2715,7 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	BUG_ON(iocb->ki_pos != pos);
 
 	mutex_lock(&inode->i_mutex);
-	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+	ret = __generic_file_aio_write(iocb, iov, nr_segs);
 	mutex_unlock(&inode->i_mutex);
 
 	if (ret > 0) {

mm/iov_iter.c

@@ -0,0 +1,224 @@
+#include <linux/export.h>
+#include <linux/uio.h>
+#include <linux/pagemap.h>
+
+size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
+			 struct iov_iter *i)
+{
+	size_t skip, copy, left, wanted;
+	const struct iovec *iov;
+	char __user *buf;
+	void *kaddr, *from;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	iov = i->iov;
+	skip = i->iov_offset;
+	buf = iov->iov_base + skip;
+	copy = min(bytes, iov->iov_len - skip);
+
+	if (!fault_in_pages_writeable(buf, copy)) {
+		kaddr = kmap_atomic(page);
+		from = kaddr + offset;
+
+		/* first chunk, usually the only one */
+		left = __copy_to_user_inatomic(buf, from, copy);
+		copy -= left;
+		skip += copy;
+		from += copy;
+		bytes -= copy;
+
+		while (unlikely(!left && bytes)) {
+			iov++;
+			buf = iov->iov_base;
+			copy = min(bytes, iov->iov_len);
+			left = __copy_to_user_inatomic(buf, from, copy);
+			copy -= left;
+			skip = copy;
+			from += copy;
+			bytes -= copy;
+		}
+		if (likely(!bytes)) {
+			kunmap_atomic(kaddr);
+			goto done;
+		}
+		offset = from - kaddr;
+		buf += copy;
+		kunmap_atomic(kaddr);
+		copy = min(bytes, iov->iov_len - skip);
+	}
+	/* Too bad - revert to non-atomic kmap */
+	kaddr = kmap(page);
+	from = kaddr + offset;
+	left = __copy_to_user(buf, from, copy);
+	copy -= left;
+	skip += copy;
+	from += copy;
+	bytes -= copy;
+	while (unlikely(!left && bytes)) {
+		iov++;
+		buf = iov->iov_base;
+		copy = min(bytes, iov->iov_len);
+		left = __copy_to_user(buf, from, copy);
+		copy -= left;
+		skip = copy;
+		from += copy;
+		bytes -= copy;
+	}
+	kunmap(page);
+done:
+	i->count -= wanted - bytes;
+	i->nr_segs -= iov - i->iov;
+	i->iov = iov;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+EXPORT_SYMBOL(copy_page_to_iter);
+
+static size_t __iovec_copy_from_user_inatomic(char *vaddr,
+			const struct iovec *iov, size_t base, size_t bytes)
+{
+	size_t copied = 0, left = 0;
+
+	while (bytes) {
+		char __user *buf = iov->iov_base + base;
+		int copy = min(bytes, iov->iov_len - base);
+
+		base = 0;
+		left = __copy_from_user_inatomic(vaddr, buf, copy);
+		copied += copy;
+		bytes -= copy;
+		vaddr += copy;
+		iov++;
+
+		if (unlikely(left))
+			break;
+	}
+	return copied - left;
+}
+
+/*
+ * Copy as much as we can into the page and return the number of bytes which
+ * were successfully copied.  If a fault is encountered then return the number of
+ * bytes which were copied.
+ */
+size_t iov_iter_copy_from_user_atomic(struct page *page,
+		struct iov_iter *i, unsigned long offset, size_t bytes)
+{
+	char *kaddr;
+	size_t copied;
+
+	kaddr = kmap_atomic(page);
+	if (likely(i->nr_segs == 1)) {
+		int left;
+		char __user *buf = i->iov->iov_base + i->iov_offset;
+		left = __copy_from_user_inatomic(kaddr + offset, buf, bytes);
+		copied = bytes - left;
+	} else {
+		copied = __iovec_copy_from_user_inatomic(kaddr + offset,
+						i->iov, i->iov_offset, bytes);
+	}
+	kunmap_atomic(kaddr);
+
+	return copied;
+}
+EXPORT_SYMBOL(iov_iter_copy_from_user_atomic);
+
+/*
+ * This has the same sideeffects and return value as
+ * iov_iter_copy_from_user_atomic().
+ * The difference is that it attempts to resolve faults.
+ * Page must not be locked.
+ */
+size_t iov_iter_copy_from_user(struct page *page,
+		struct iov_iter *i, unsigned long offset, size_t bytes)
+{
+	char *kaddr;
+	size_t copied;
+
+	kaddr = kmap(page);
+	if (likely(i->nr_segs == 1)) {
+		int left;
+		char __user *buf = i->iov->iov_base + i->iov_offset;
+		left = __copy_from_user(kaddr + offset, buf, bytes);
+		copied = bytes - left;
+	} else {
+		copied = __iovec_copy_from_user_inatomic(kaddr + offset,
+						i->iov, i->iov_offset, bytes);
+	}
+	kunmap(page);
+	return copied;
+}
+EXPORT_SYMBOL(iov_iter_copy_from_user);
+
+void iov_iter_advance(struct iov_iter *i, size_t bytes)
+{
+	BUG_ON(i->count < bytes);
+
+	if (likely(i->nr_segs == 1)) {
+		i->iov_offset += bytes;
+		i->count -= bytes;
+	} else {
+		const struct iovec *iov = i->iov;
+		size_t base = i->iov_offset;
+		unsigned long nr_segs = i->nr_segs;
+
+		/*
+		 * The !iov->iov_len check ensures we skip over unlikely
+		 * zero-length segments (without overruning the iovec).
+		 */
+		while (bytes || unlikely(i->count && !iov->iov_len)) {
+			int copy;
+
+			copy = min(bytes, iov->iov_len - base);
+			BUG_ON(!i->count || i->count < copy);
+			i->count -= copy;
+			bytes -= copy;
+			base += copy;
+			if (iov->iov_len == base) {
+				iov++;
+				nr_segs--;
+				base = 0;
+			}
+		}
+		i->iov = iov;
+		i->iov_offset = base;
+		i->nr_segs = nr_segs;
+	}
+}
+EXPORT_SYMBOL(iov_iter_advance);
+
+/*
+ * Fault in the first iovec of the given iov_iter, to a maximum length
+ * of bytes. Returns 0 on success, or non-zero if the memory could not be
+ * accessed (ie. because it is an invalid address).
+ *
+ * writev-intensive code may want this to prefault several iovecs -- that
+ * would be possible (callers must not rely on the fact that _only_ the
+ * first iovec will be faulted with the current implementation).
+ */
+int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes)
+{
+	char __user *buf = i->iov->iov_base + i->iov_offset;
+	bytes = min(bytes, i->iov->iov_len - i->iov_offset);
+	return fault_in_pages_readable(buf, bytes);
+}
+EXPORT_SYMBOL(iov_iter_fault_in_readable);
+
+/*
+ * Return the count of just the current iov_iter segment.
+ */
+size_t iov_iter_single_seg_count(const struct iov_iter *i)
+{
+	const struct iovec *iov = i->iov;
+	if (i->nr_segs == 1)
+		return i->count;
+	else
+		return min(i->count, iov->iov_len - i->iov_offset);
+}
+EXPORT_SYMBOL(iov_iter_single_seg_count);

mm/process_vm_access.c

@@ -23,129 +23,44 @@
 
 /**
  * process_vm_rw_pages - read/write pages from task specified
- * @task: task to read/write from
- * @mm: mm for task
- * @process_pages: struct pages area that can store at least
- *  nr_pages_to_copy struct page pointers
- * @pa: address of page in task to start copying from/to
+ * @pages: array of pointers to pages we want to copy
  * @start_offset: offset in page to start copying from/to
  * @len: number of bytes to copy
- * @lvec: iovec array specifying where to copy to/from
- * @lvec_cnt: number of elements in iovec array
- * @lvec_current: index in iovec array we are up to
- * @lvec_offset: offset in bytes from current iovec iov_base we are up to
+ * @iter: where to copy to/from locally
  * @vm_write: 0 means copy from, 1 means copy to
- * @nr_pages_to_copy: number of pages to copy
- * @bytes_copied: returns number of bytes successfully copied
  * Returns 0 on success, error code otherwise
  */
-static int process_vm_rw_pages(struct task_struct *task,
-			       struct mm_struct *mm,
-			       struct page **process_pages,
-			       unsigned long pa,
-			       unsigned long start_offset,
-			       unsigned long len,
-			       const struct iovec *lvec,
-			       unsigned long lvec_cnt,
-			       unsigned long *lvec_current,
-			       size_t *lvec_offset,
-			       int vm_write,
-			       unsigned int nr_pages_to_copy,
-			       ssize_t *bytes_copied)
+static int process_vm_rw_pages(struct page **pages,
+			       unsigned offset,
+			       size_t len,
+			       struct iov_iter *iter,
+			       int vm_write)
 {
-	int pages_pinned;
-	void *target_kaddr;
-	int pgs_copied = 0;
-	int j;
-	int ret;
-	ssize_t bytes_to_copy;
-	ssize_t rc = 0;
-
-	*bytes_copied = 0;
-
-	/* Get the pages we're interested in */
-	down_read(&mm->mmap_sem);
-	pages_pinned = get_user_pages(task, mm, pa,
-				      nr_pages_to_copy,
-				      vm_write, 0, process_pages, NULL);
-	up_read(&mm->mmap_sem);
-
-	if (pages_pinned != nr_pages_to_copy) {
-		rc = -EFAULT;
-		goto end;
-	}
-
 	/* Do the copy for each page */
-	for (pgs_copied = 0;
-	     (pgs_copied < nr_pages_to_copy) && (*lvec_current < lvec_cnt);
-	     pgs_copied++) {
-		/* Make sure we have a non zero length iovec */
-		while (*lvec_current < lvec_cnt
-		       && lvec[*lvec_current].iov_len == 0)
-			(*lvec_current)++;
-		if (*lvec_current == lvec_cnt)
-			break;
-
-		/*
-		 * Will copy smallest of:
-		 * - bytes remaining in page
-		 * - bytes remaining in destination iovec
-		 */
-		bytes_to_copy = min_t(ssize_t, PAGE_SIZE - start_offset,
-				      len - *bytes_copied);
-		bytes_to_copy = min_t(ssize_t, bytes_to_copy,
-				      lvec[*lvec_current].iov_len
-				      - *lvec_offset);
-
-		target_kaddr = kmap(process_pages[pgs_copied]) + start_offset;
-
-		if (vm_write)
-			ret = copy_from_user(target_kaddr,
-					     lvec[*lvec_current].iov_base
-					     + *lvec_offset,
-					     bytes_to_copy);
-		else
-			ret = copy_to_user(lvec[*lvec_current].iov_base
-					   + *lvec_offset,
-					   target_kaddr, bytes_to_copy);
-		kunmap(process_pages[pgs_copied]);
-		if (ret) {
-			*bytes_copied += bytes_to_copy - ret;
-			pgs_copied++;
-			rc = -EFAULT;
-			goto end;
-		}
-		*bytes_copied += bytes_to_copy;
-		*lvec_offset += bytes_to_copy;
-		if (*lvec_offset == lvec[*lvec_current].iov_len) {
-			/*
-			 * Need to copy remaining part of page into the
-			 * next iovec if there are any bytes left in page
-			 */
-			(*lvec_current)++;
-			*lvec_offset = 0;
-			start_offset = (start_offset + bytes_to_copy)
-				% PAGE_SIZE;
-			if (start_offset)
-				pgs_copied--;
+	while (len && iov_iter_count(iter)) {
+		struct page *page = *pages++;
+		size_t copy = PAGE_SIZE - offset;
+		size_t copied;
+
+		if (copy > len)
+			copy = len;
+
+		if (vm_write) {
+			if (copy > iov_iter_count(iter))
+				copy = iov_iter_count(iter);
+			copied = iov_iter_copy_from_user(page, iter,
+					offset, copy);
+			iov_iter_advance(iter, copied);
+			set_page_dirty_lock(page);
 		} else {
-			start_offset = 0;
-		}
-	}
-
-end:
-	if (vm_write) {
-		for (j = 0; j < pages_pinned; j++) {
-			if (j < pgs_copied)
-				set_page_dirty_lock(process_pages[j]);
-			put_page(process_pages[j]);
+			copied = copy_page_to_iter(page, offset, copy, iter);
 		}
-	} else {
-		for (j = 0; j < pages_pinned; j++)
-			put_page(process_pages[j]);
+		len -= copied;
+		if (copied < copy && iov_iter_count(iter))
+			return -EFAULT;
+		offset = 0;
 	}
-
-	return rc;
+	return 0;
 }
 
 /* Maximum number of pages kmalloc'd to hold struct page's during copy */
@@ -155,67 +70,60 @@ end:
  * process_vm_rw_single_vec - read/write pages from task specified
  * @addr: start memory address of target process
  * @len: size of area to copy to/from
- * @lvec: iovec array specifying where to copy to/from locally
- * @lvec_cnt: number of elements in iovec array
- * @lvec_current: index in iovec array we are up to
- * @lvec_offset: offset in bytes from current iovec iov_base we are up to
+ * @iter: where to copy to/from locally
  * @process_pages: struct pages area that can store at least
  *  nr_pages_to_copy struct page pointers
  * @mm: mm for task
  * @task: task to read/write from
  * @vm_write: 0 means copy from, 1 means copy to
- * @bytes_copied: returns number of bytes successfully copied
  * Returns 0 on success or on failure error code
  */
 static int process_vm_rw_single_vec(unsigned long addr,
 				    unsigned long len,
-				    const struct iovec *lvec,
-				    unsigned long lvec_cnt,
-				    unsigned long *lvec_current,
-				    size_t *lvec_offset,
+				    struct iov_iter *iter,
 				    struct page **process_pages,
 				    struct mm_struct *mm,
 				    struct task_struct *task,
-				    int vm_write,
-				    ssize_t *bytes_copied)
+				    int vm_write)
 {
 	unsigned long pa = addr & PAGE_MASK;
 	unsigned long start_offset = addr - pa;
 	unsigned long nr_pages;
-	ssize_t bytes_copied_loop;
 	ssize_t rc = 0;
-	unsigned long nr_pages_copied = 0;
-	unsigned long nr_pages_to_copy;
 	unsigned long max_pages_per_loop = PVM_MAX_KMALLOC_PAGES
 		/ sizeof(struct pages *);
 
-	*bytes_copied = 0;
-
 	/* Work out address and page range required */
 	if (len == 0)
 		return 0;
 	nr_pages = (addr + len - 1) / PAGE_SIZE - addr / PAGE_SIZE + 1;
 
-	while ((nr_pages_copied < nr_pages) && (*lvec_current < lvec_cnt)) {
-		nr_pages_to_copy = min(nr_pages - nr_pages_copied,
-				       max_pages_per_loop);
+	while (!rc && nr_pages && iov_iter_count(iter)) {
+		int pages = min(nr_pages, max_pages_per_loop);
+		size_t bytes;
 
-		rc = process_vm_rw_pages(task, mm, process_pages, pa,
-					 start_offset, len,
-					 lvec, lvec_cnt,
-					 lvec_current, lvec_offset,
-					 vm_write, nr_pages_to_copy,
-					 &bytes_copied_loop);
-		start_offset = 0;
-		*bytes_copied += bytes_copied_loop;
+		/* Get the pages we're interested in */
+		down_read(&mm->mmap_sem);
+		pages = get_user_pages(task, mm, pa, pages,
+				      vm_write, 0, process_pages, NULL);
+		up_read(&mm->mmap_sem);
 
-		if (rc < 0) {
-			return rc;
-		} else {
-			len -= bytes_copied_loop;
-			nr_pages_copied += nr_pages_to_copy;
-			pa += nr_pages_to_copy * PAGE_SIZE;
-		}
+		if (pages <= 0)
+			return -EFAULT;
+
+		bytes = pages * PAGE_SIZE - start_offset;
+		if (bytes > len)
+			bytes = len;
+
+		rc = process_vm_rw_pages(process_pages,
+					 start_offset, bytes, iter,
+					 vm_write);
+		len -= bytes;
+		start_offset = 0;
+		nr_pages -= pages;
+		pa += pages * PAGE_SIZE;
+		while (pages)
+			put_page(process_pages[--pages]);
 	}
 
 	return rc;
@@ -228,8 +136,7 @@ static int process_vm_rw_single_vec(unsigned long addr,
 /**
  * process_vm_rw_core - core of reading/writing pages from task specified
  * @pid: PID of process to read/write from/to
- * @lvec: iovec array specifying where to copy to/from locally
- * @liovcnt: size of lvec array
+ * @iter: where to copy to/from locally
  * @rvec: iovec array specifying where to copy to/from in the other process
  * @riovcnt: size of rvec array
  * @flags: currently unused
@@ -238,8 +145,7 @@ static int process_vm_rw_single_vec(unsigned long addr,
  *  return less bytes than expected if an error occurs during the copying
  *  process.
  */
-static ssize_t process_vm_rw_core(pid_t pid, const struct iovec *lvec,
-				  unsigned long liovcnt,
+static ssize_t process_vm_rw_core(pid_t pid, struct iov_iter *iter,
 				  const struct iovec *rvec,
 				  unsigned long riovcnt,
 				  unsigned long flags, int vm_write)
@@ -250,13 +156,10 @@ static ssize_t process_vm_rw_core(pid_t pid, const struct iovec *lvec,
 	struct mm_struct *mm;
 	unsigned long i;
 	ssize_t rc = 0;
-	ssize_t bytes_copied_loop;
-	ssize_t bytes_copied = 0;
 	unsigned long nr_pages = 0;
 	unsigned long nr_pages_iov;
-	unsigned long iov_l_curr_idx = 0;
-	size_t iov_l_curr_offset = 0;
 	ssize_t iov_len;
+	size_t total_len = iov_iter_count(iter);
 
 	/*
 	 * Work out how many pages of struct pages we're going to need
@@ -310,24 +213,20 @@ static ssize_t process_vm_rw_core(pid_t pid, const struct iovec *lvec,
 		goto put_task_struct;
 	}
 
-	for (i = 0; i < riovcnt && iov_l_curr_idx < liovcnt; i++) {
+	for (i = 0; i < riovcnt && iov_iter_count(iter) && !rc; i++)
 		rc = process_vm_rw_single_vec(
 			(unsigned long)rvec[i].iov_base, rvec[i].iov_len,
-			lvec, liovcnt, &iov_l_curr_idx, &iov_l_curr_offset,
-			process_pages, mm, task, vm_write, &bytes_copied_loop);
-		bytes_copied += bytes_copied_loop;
-		if (rc != 0) {
-			/* If we have managed to copy any data at all then
-			   we return the number of bytes copied. Otherwise
-			   we return the error code */
-			if (bytes_copied)
-				rc = bytes_copied;
-			goto put_mm;
-		}
-	}
+			iter, process_pages, mm, task, vm_write);
+
+	/* copied = space before - space after */
+	total_len -= iov_iter_count(iter);
+
+	/* If we have managed to copy any data at all then
+	   we return the number of bytes copied. Otherwise
+	   we return the error code */
+	if (total_len)
+		rc = total_len;
 
-	rc = bytes_copied;
-put_mm:
 	mmput(mm);
 
 put_task_struct:
@@ -363,6 +262,7 @@ static ssize_t process_vm_rw(pid_t pid,
 	struct iovec iovstack_r[UIO_FASTIOV];
 	struct iovec *iov_l = iovstack_l;
 	struct iovec *iov_r = iovstack_r;
+	struct iov_iter iter;
 	ssize_t rc;
 
 	if (flags != 0)
@@ -378,13 +278,14 @@ static ssize_t process_vm_rw(pid_t pid,
 	if (rc <= 0)
 		goto free_iovecs;
 
+	iov_iter_init(&iter, iov_l, liovcnt, rc, 0);
+
 	rc = rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV,
 				   iovstack_r, &iov_r);
 	if (rc <= 0)
 		goto free_iovecs;
 
-	rc = process_vm_rw_core(pid, iov_l, liovcnt, iov_r, riovcnt, flags,
-				vm_write);
+	rc = process_vm_rw_core(pid, &iter, iov_r, riovcnt, flags, vm_write);
 
 free_iovecs:
 	if (iov_r != iovstack_r)
@@ -424,6 +325,7 @@ compat_process_vm_rw(compat_pid_t pid,
 	struct iovec iovstack_r[UIO_FASTIOV];
 	struct iovec *iov_l = iovstack_l;
 	struct iovec *iov_r = iovstack_r;
+	struct iov_iter iter;
 	ssize_t rc = -EFAULT;
 
 	if (flags != 0)
@@ -439,14 +341,14 @@ compat_process_vm_rw(compat_pid_t pid,
 						  &iov_l);
 	if (rc <= 0)
 		goto free_iovecs;
+	iov_iter_init(&iter, iov_l, liovcnt, rc, 0);
 	rc = compat_rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt,
 					  UIO_FASTIOV, iovstack_r,
 					  &iov_r);
 	if (rc <= 0)
 		goto free_iovecs;
 
-	rc = process_vm_rw_core(pid, iov_l, liovcnt, iov_r, riovcnt, flags,
-			   vm_write);
+	rc = process_vm_rw_core(pid, &iter, iov_r, riovcnt, flags, vm_write);
 
 free_iovecs:
 	if (iov_r != iovstack_r)

mm/shmem.c

@@ -1402,13 +1402,25 @@ shmem_write_end(struct file *file, struct address_space *mapping,
 	return copied;
 }
 
-static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_t *desc, read_actor_t actor)
+static ssize_t shmem_file_aio_read(struct kiocb *iocb,
+		const struct iovec *iov, unsigned long nr_segs, loff_t pos)
 {
-	struct inode *inode = file_inode(filp);
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
 	struct address_space *mapping = inode->i_mapping;
 	pgoff_t index;
 	unsigned long offset;
 	enum sgp_type sgp = SGP_READ;
+	int error;
+	ssize_t retval;
+	size_t count;
+	loff_t *ppos = &iocb->ki_pos;
+	struct iov_iter iter;
+
+	retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
+	if (retval)
+		return retval;
+	iov_iter_init(&iter, iov, nr_segs, count, 0);
 
 	/*
 	 * Might this read be for a stacking filesystem?  Then when reading
@@ -1436,10 +1448,10 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_
 				break;
 		}
 
-		desc->error = shmem_getpage(inode, index, &page, sgp, NULL);
-		if (desc->error) {
-			if (desc->error == -EINVAL)
-				desc->error = 0;
+		error = shmem_getpage(inode, index, &page, sgp, NULL);
+		if (error) {
+			if (error == -EINVAL)
+				error = 0;
 			break;
 		}
 		if (page)
@@ -1483,61 +1495,26 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_
 		/*
 		 * Ok, we have the page, and it's up-to-date, so
 		 * now we can copy it to user space...
-		 *
-		 * The actor routine returns how many bytes were actually used..
-		 * NOTE! This may not be the same as how much of a user buffer
-		 * we filled up (we may be padding etc), so we can only update
-		 * "pos" here (the actor routine has to update the user buffer
-		 * pointers and the remaining count).
 		 */
-		ret = actor(desc, page, offset, nr);
+		ret = copy_page_to_iter(page, offset, nr, &iter);
+		retval += ret;
 		offset += ret;
 		index += offset >> PAGE_CACHE_SHIFT;
 		offset &= ~PAGE_CACHE_MASK;
 
 		page_cache_release(page);
-		if (ret != nr || !desc->count)
+		if (!iov_iter_count(&iter))
 			break;
-
+		if (ret < nr) {
+			error = -EFAULT;
+			break;
+		}
 		cond_resched();
 	}
 
 	*ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset;
-	file_accessed(filp);
-}
-
-static ssize_t shmem_file_aio_read(struct kiocb *iocb,
-		const struct iovec *iov, unsigned long nr_segs, loff_t pos)
-{
-	struct file *filp = iocb->ki_filp;
-	ssize_t retval;
-	unsigned long seg;
-	size_t count;
-	loff_t *ppos = &iocb->ki_pos;
-
-	retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
-	if (retval)
-		return retval;
-
-	for (seg = 0; seg < nr_segs; seg++) {
-		read_descriptor_t desc;
-
-		desc.written = 0;
-		desc.arg.buf = iov[seg].iov_base;
-		desc.count = iov[seg].iov_len;
-		if (desc.count == 0)
-			continue;
-		desc.error = 0;
-		do_shmem_file_read(filp, ppos, &desc, file_read_actor);
-		retval += desc.written;
-		if (desc.error) {
-			retval = retval ?: desc.error;
-			break;
-		}
-		if (desc.count > 0)
-			break;
-	}
-	return retval;
+	file_accessed(file);
+	return retval ? retval : error;
 }
 
 static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
@@ -1576,7 +1553,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
 	index = *ppos >> PAGE_CACHE_SHIFT;
 	loff = *ppos & ~PAGE_CACHE_MASK;
 	req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-	nr_pages = min(req_pages, pipe->buffers);
+	nr_pages = min(req_pages, spd.nr_pages_max);
 
 	spd.nr_pages = find_get_pages_contig(mapping, index,
 						nr_pages, spd.pages);

security/integrity/evm/evm_crypto.c

@@ -139,7 +139,7 @@ static int evm_calc_hmac_or_hash(struct dentry *dentry,
 	int error;
 	int size;
 
-	if (!inode->i_op || !inode->i_op->getxattr)
+	if (!inode->i_op->getxattr)
 		return -EOPNOTSUPP;
 	desc = init_desc(type);
 	if (IS_ERR(desc))

security/integrity/evm/evm_main.c

@@ -64,7 +64,7 @@ static int evm_find_protected_xattrs(struct dentry *dentry)
 	int error;
 	int count = 0;
 
-	if (!inode->i_op || !inode->i_op->getxattr)
+	if (!inode->i_op->getxattr)
 		return -EOPNOTSUPP;
 
 	for (xattr = evm_config_xattrnames; *xattr != NULL; xattr++) {

security/tomoyo/realpath.c

@@ -173,7 +173,7 @@ static char *tomoyo_get_local_path(struct dentry *dentry, char * const buffer,
 		 * Use filesystem name if filesystem does not support rename()
 		 * operation.
 		 */
-		if (inode->i_op && !inode->i_op->rename)
+		if (!inode->i_op->rename)
 			goto prepend_filesystem_name;
 	}
 	/* Prepend device name. */
@@ -282,7 +282,7 @@ char *tomoyo_realpath_from_path(struct path *path)
 		 * Get local name for filesystems without rename() operation
 		 * or dentry without vfsmount.
 		 */
-		if (!path->mnt || (inode->i_op && !inode->i_op->rename))
+		if (!path->mnt || !inode->i_op->rename)
 			pos = tomoyo_get_local_path(path->dentry, buf,
 						    buf_len - 1);
 		/* Get absolute name for the rest. */