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) {
@@ -355,44 +324,37 @@ 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;
 	void	*base;
 	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++) {
 			nob += scratchiov[i].iov_len = kiov[i].kiov_len;
 			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) {