Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Minor conflict in r8169, bug fix had two versions in net
and net-next, take the net-next hunks.

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

34 files changed, 327 insertions, 246 deletions

diff --git a/fs/afs/cell.c b/fs/afs/cell.c
index a2a87117d262..fd5133e26a38 100644
--- a/fs/afs/cell.c
+++ b/fs/afs/cell.c
@@ -74,6 +74,7 @@ struct afs_cell *afs_lookup_cell_rcu(struct afs_net *net,
 			cell = rcu_dereference_raw(net->ws_cell);
 			if (cell) {
 				afs_get_cell(cell);
+				ret = 0;
 				break;
 			}
 			ret = -EDESTADDRREQ;
@@ -108,6 +109,9 @@ struct afs_cell *afs_lookup_cell_rcu(struct afs_net *net,
 
 	done_seqretry(&net->cells_lock, seq);
 
+	if (ret != 0 && cell)
+		afs_put_cell(net, cell);
+
 	return ret == 0 ? cell : ERR_PTR(ret);
 }
 
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 81207dc3c997..139b4e3cc946 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -959,7 +959,8 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
 				 inode ? AFS_FS_I(inode) : NULL);
 	} else {
 		trace_afs_lookup(dvnode, &dentry->d_name,
-				 inode ? AFS_FS_I(inode) : NULL);
+				 IS_ERR_OR_NULL(inode) ? NULL
+				 : AFS_FS_I(inode));
 	}
 	return d;
 }
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index 2575503170fc..ca2452806ebf 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -2171,7 +2171,7 @@ int yfs_fs_store_opaque_acl2(struct afs_fs_cursor *fc, const struct afs_acl *acl
 	       key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode);
 
 	size = round_up(acl->size, 4);
-	call = afs_alloc_flat_call(net, &yfs_RXYFSStoreStatus,
+	call = afs_alloc_flat_call(net, &yfs_RXYFSStoreOpaqueACL2,
 				   sizeof(__be32) * 2 +
 				   sizeof(struct yfs_xdr_YFSFid) +
 				   sizeof(__be32) + size,
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index e078cc55b989..b3c8b886bf64 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -913,8 +913,9 @@ get_more_pages:
 			if (page_offset(page) >= ceph_wbc.i_size) {
 				dout("%p page eof %llu\n",
 				     page, ceph_wbc.i_size);
-				if (ceph_wbc.size_stable ||
-				    page_offset(page) >= i_size_read(inode))
+				if ((ceph_wbc.size_stable ||
+				    page_offset(page) >= i_size_read(inode)) &&
+				    clear_page_dirty_for_io(page))
 					mapping->a_ops->invalidatepage(page,
 								0, PAGE_SIZE);
 				unlock_page(page);
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index d98dcd976c80..ce0f5658720a 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1301,6 +1301,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
 {
 	struct ceph_inode_info *ci = cap->ci;
 	struct inode *inode = &ci->vfs_inode;
+	struct ceph_buffer *old_blob = NULL;
 	struct cap_msg_args arg;
 	int held, revoking;
 	int wake = 0;
@@ -1365,7 +1366,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
 	ci->i_requested_max_size = arg.max_size;
 
 	if (flushing & CEPH_CAP_XATTR_EXCL) {
-		__ceph_build_xattrs_blob(ci);
+		old_blob = __ceph_build_xattrs_blob(ci);
 		arg.xattr_version = ci->i_xattrs.version;
 		arg.xattr_buf = ci->i_xattrs.blob;
 	} else {
@@ -1409,6 +1410,8 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
 
 	spin_unlock(&ci->i_ceph_lock);
 
+	ceph_buffer_put(old_blob);
+
 	ret = send_cap_msg(&arg);
 	if (ret < 0) {
 		dout("error sending cap msg, must requeue %p\n", inode);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 791f84a13bb8..18500edefc56 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -736,6 +736,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 	int issued, new_issued, info_caps;
 	struct timespec64 mtime, atime, ctime;
 	struct ceph_buffer *xattr_blob = NULL;
+	struct ceph_buffer *old_blob = NULL;
 	struct ceph_string *pool_ns = NULL;
 	struct ceph_cap *new_cap = NULL;
 	int err = 0;
@@ -881,7 +882,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 	if ((ci->i_xattrs.version == 0 || !(issued & CEPH_CAP_XATTR_EXCL))  &&
 	    le64_to_cpu(info->xattr_version) > ci->i_xattrs.version) {
 		if (ci->i_xattrs.blob)
-			ceph_buffer_put(ci->i_xattrs.blob);
+			old_blob = ci->i_xattrs.blob;
 		ci->i_xattrs.blob = xattr_blob;
 		if (xattr_blob)
 			memcpy(ci->i_xattrs.blob->vec.iov_base,
@@ -1022,8 +1023,8 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 out:
 	if (new_cap)
 		ceph_put_cap(mdsc, new_cap);
-	if (xattr_blob)
-		ceph_buffer_put(xattr_blob);
+	ceph_buffer_put(old_blob);
+	ceph_buffer_put(xattr_blob);
 	ceph_put_string(pool_ns);
 	return err;
 }
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index ac9b53b89365..5083e238ad15 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -111,8 +111,7 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct inode *inode,
 		req->r_wait_for_completion = ceph_lock_wait_for_completion;
 
 	err = ceph_mdsc_do_request(mdsc, inode, req);
-
-	if (operation == CEPH_MDS_OP_GETFILELOCK) {
+	if (!err && operation == CEPH_MDS_OP_GETFILELOCK) {
 		fl->fl_pid = -le64_to_cpu(req->r_reply_info.filelock_reply->pid);
 		if (CEPH_LOCK_SHARED == req->r_reply_info.filelock_reply->type)
 			fl->fl_type = F_RDLCK;
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 4c6494eb02b5..ccfcc66aaf44 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -465,6 +465,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci)
 	struct inode *inode = &ci->vfs_inode;
 	struct ceph_cap_snap *capsnap;
 	struct ceph_snap_context *old_snapc, *new_snapc;
+	struct ceph_buffer *old_blob = NULL;
 	int used, dirty;
 
 	capsnap = kzalloc(sizeof(*capsnap), GFP_NOFS);
@@ -541,7 +542,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci)
 	capsnap->gid = inode->i_gid;
 
 	if (dirty & CEPH_CAP_XATTR_EXCL) {
-		__ceph_build_xattrs_blob(ci);
+		old_blob = __ceph_build_xattrs_blob(ci);
 		capsnap->xattr_blob =
 			ceph_buffer_get(ci->i_xattrs.blob);
 		capsnap->xattr_version = ci->i_xattrs.version;
@@ -584,6 +585,7 @@ update_snapc:
 	}
 	spin_unlock(&ci->i_ceph_lock);
 
+	ceph_buffer_put(old_blob);
 	kfree(capsnap);
 	ceph_put_snap_context(old_snapc);
 }
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index d2352fd95dbc..6b9f1ee7de85 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -926,7 +926,7 @@ extern int ceph_getattr(const struct path *path, struct kstat *stat,
 int __ceph_setxattr(struct inode *, const char *, const void *, size_t, int);
 ssize_t __ceph_getxattr(struct inode *, const char *, void *, size_t);
 extern ssize_t ceph_listxattr(struct dentry *, char *, size_t);
-extern void __ceph_build_xattrs_blob(struct ceph_inode_info *ci);
+extern struct ceph_buffer *__ceph_build_xattrs_blob(struct ceph_inode_info *ci);
 extern void __ceph_destroy_xattrs(struct ceph_inode_info *ci);
 extern const struct xattr_handler *ceph_xattr_handlers[];
 
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 37b458a9af3a..939eab7aa219 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -754,12 +754,15 @@ static int __get_required_blob_size(struct ceph_inode_info *ci, int name_size,
 
 /*
  * If there are dirty xattrs, reencode xattrs into the prealloc_blob
- * and swap into place.
+ * and swap into place.  It returns the old i_xattrs.blob (or NULL) so
+ * that it can be freed by the caller as the i_ceph_lock is likely to be
+ * held.
  */
-void __ceph_build_xattrs_blob(struct ceph_inode_info *ci)
+struct ceph_buffer *__ceph_build_xattrs_blob(struct ceph_inode_info *ci)
 {
 	struct rb_node *p;
 	struct ceph_inode_xattr *xattr = NULL;
+	struct ceph_buffer *old_blob = NULL;
 	void *dest;
 
 	dout("__build_xattrs_blob %p\n", &ci->vfs_inode);
@@ -790,12 +793,14 @@ void __ceph_build_xattrs_blob(struct ceph_inode_info *ci)
 			dest - ci->i_xattrs.prealloc_blob->vec.iov_base;
 
 		if (ci->i_xattrs.blob)
-			ceph_buffer_put(ci->i_xattrs.blob);
+			old_blob = ci->i_xattrs.blob;
 		ci->i_xattrs.blob = ci->i_xattrs.prealloc_blob;
 		ci->i_xattrs.prealloc_blob = NULL;
 		ci->i_xattrs.dirty = false;
 		ci->i_xattrs.version++;
 	}
+
+	return old_blob;
 }
 
 static inline int __get_request_mask(struct inode *in) {
@@ -1036,6 +1041,7 @@ int __ceph_setxattr(struct inode *inode, const char *name,
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 	struct ceph_cap_flush *prealloc_cf = NULL;
+	struct ceph_buffer *old_blob = NULL;
 	int issued;
 	int err;
 	int dirty = 0;
@@ -1109,13 +1115,15 @@ retry:
 		struct ceph_buffer *blob;
 
 		spin_unlock(&ci->i_ceph_lock);
-		dout(" preaallocating new blob size=%d\n", required_blob_size);
+		ceph_buffer_put(old_blob); /* Shouldn't be required */
+		dout(" pre-allocating new blob size=%d\n", required_blob_size);
 		blob = ceph_buffer_new(required_blob_size, GFP_NOFS);
 		if (!blob)
 			goto do_sync_unlocked;
 		spin_lock(&ci->i_ceph_lock);
+		/* prealloc_blob can't be released while holding i_ceph_lock */
 		if (ci->i_xattrs.prealloc_blob)
-			ceph_buffer_put(ci->i_xattrs.prealloc_blob);
+			old_blob = ci->i_xattrs.prealloc_blob;
 		ci->i_xattrs.prealloc_blob = blob;
 		goto retry;
 	}
@@ -1131,6 +1139,7 @@ retry:
 	}
 
 	spin_unlock(&ci->i_ceph_lock);
+	ceph_buffer_put(old_blob);
 	if (lock_snap_rwsem)
 		up_read(&mdsc->snap_rwsem);
 	if (dirty)
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index a15a6e738eb5..1795e80cbdf7 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1113,7 +1113,7 @@ cifs_demultiplex_thread(void *p)
 		mempool_resize(cifs_req_poolp, length + cifs_min_rcv);
 
 	set_freezable();
-	allow_signal(SIGKILL);
+	allow_kernel_signal(SIGKILL);
 	while (server->tcpStatus != CifsExiting) {
 		if (try_to_freeze())
 			continue;
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 24bbe3cb7ad4..cfb48bd088e1 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -679,6 +679,13 @@ static void io_put_req(struct io_kiocb *req)
 		io_free_req(req);
 }
 
+static unsigned io_cqring_events(struct io_cq_ring *ring)
+{
+	/* See comment at the top of this file */
+	smp_rmb();
+	return READ_ONCE(ring->r.tail) - READ_ONCE(ring->r.head);
+}
+
 /*
  * Find and free completed poll iocbs
  */
@@ -771,7 +778,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
 static int io_iopoll_getevents(struct io_ring_ctx *ctx, unsigned int *nr_events,
 				long min)
 {
-	while (!list_empty(&ctx->poll_list)) {
+	while (!list_empty(&ctx->poll_list) && !need_resched()) {
 		int ret;
 
 		ret = io_do_iopoll(ctx, nr_events, min);
@@ -798,6 +805,12 @@ static void io_iopoll_reap_events(struct io_ring_ctx *ctx)
 		unsigned int nr_events = 0;
 
 		io_iopoll_getevents(ctx, &nr_events, 1);
+
+		/*
+		 * Ensure we allow local-to-the-cpu processing to take place,
+		 * in this case we need to ensure that we reap all events.
+		 */
+		cond_resched();
 	}
 	mutex_unlock(&ctx->uring_lock);
 }
@@ -805,11 +818,42 @@ static void io_iopoll_reap_events(struct io_ring_ctx *ctx)
 static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
 			   long min)
 {
-	int ret = 0;
+	int iters, ret = 0;
 
+	/*
+	 * We disallow the app entering submit/complete with polling, but we
+	 * still need to lock the ring to prevent racing with polled issue
+	 * that got punted to a workqueue.
+	 */
+	mutex_lock(&ctx->uring_lock);
+
+	iters = 0;
 	do {
 		int tmin = 0;
 
+		/*
+		 * Don't enter poll loop if we already have events pending.
+		 * If we do, we can potentially be spinning for commands that
+		 * already triggered a CQE (eg in error).
+		 */
+		if (io_cqring_events(ctx->cq_ring))
+			break;
+
+		/*
+		 * If a submit got punted to a workqueue, we can have the
+		 * application entering polling for a command before it gets
+		 * issued. That app will hold the uring_lock for the duration
+		 * of the poll right here, so we need to take a breather every
+		 * now and then to ensure that the issue has a chance to add
+		 * the poll to the issued list. Otherwise we can spin here
+		 * forever, while the workqueue is stuck trying to acquire the
+		 * very same mutex.
+		 */
+		if (!(++iters & 7)) {
+			mutex_unlock(&ctx->uring_lock);
+			mutex_lock(&ctx->uring_lock);
+		}
+
 		if (*nr_events < min)
 			tmin = min - *nr_events;
 
@@ -819,6 +863,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
 		ret = 0;
 	} while (min && !*nr_events && !need_resched());
 
+	mutex_unlock(&ctx->uring_lock);
 	return ret;
 }
 
@@ -2280,15 +2325,7 @@ static int io_sq_thread(void *data)
 			unsigned nr_events = 0;
 
 			if (ctx->flags & IORING_SETUP_IOPOLL) {
-				/*
-				 * We disallow the app entering submit/complete
-				 * with polling, but we still need to lock the
-				 * ring to prevent racing with polled issue
-				 * that got punted to a workqueue.
-				 */
-				mutex_lock(&ctx->uring_lock);
 				io_iopoll_check(ctx, &nr_events, 0);
-				mutex_unlock(&ctx->uring_lock);
 			} else {
 				/*
 				 * Normal IO, just pretend everything completed.
@@ -2433,13 +2470,6 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 	return submit;
 }
 
-static unsigned io_cqring_events(struct io_cq_ring *ring)
-{
-	/* See comment at the top of this file */
-	smp_rmb();
-	return READ_ONCE(ring->r.tail) - READ_ONCE(ring->r.head);
-}
-
 /*
  * Wait until events become available, if we don't already have some. The
  * application must reap them itself, as they reside on the shared cq ring.
@@ -3190,9 +3220,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 		min_complete = min(min_complete, ctx->cq_entries);
 
 		if (ctx->flags & IORING_SETUP_IOPOLL) {
-			mutex_lock(&ctx->uring_lock);
 			ret = io_iopoll_check(ctx, &nr_events, min_complete);
-			mutex_unlock(&ctx->uring_lock);
 		} else {
 			ret = io_cqring_wait(ctx, min_complete, sig, sigsz);
 		}
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 8d501093660f..0adfd8840110 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1487,7 +1487,7 @@ static int nfs_finish_open(struct nfs_open_context *ctx,
 	if (S_ISREG(file->f_path.dentry->d_inode->i_mode))
 		nfs_file_set_open_context(file, ctx);
 	else
-		err = -ESTALE;
+		err = -EOPENSTALE;
 out:
 	return err;
 }
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 0cb442406168..222d7115db71 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -401,15 +401,21 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
 	unsigned long bytes = 0;
 	struct nfs_direct_req *dreq = hdr->dreq;
 
-	if (test_bit(NFS_IOHDR_REDO, &hdr->flags))
-		goto out_put;
-
 	spin_lock(&dreq->lock);
-	if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes == 0))
+	if (test_bit(NFS_IOHDR_ERROR, &hdr->flags))
 		dreq->error = hdr->error;
-	else
+
+	if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+		spin_unlock(&dreq->lock);
+		goto out_put;
+	}
+
+	if (hdr->good_bytes != 0)
 		nfs_direct_good_bytes(dreq, hdr);
 
+	if (test_bit(NFS_IOHDR_EOF, &hdr->flags))
+		dreq->error = 0;
+
 	spin_unlock(&dreq->lock);
 
 	while (!list_empty(&hdr->pages)) {
@@ -782,16 +788,19 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 	bool request_commit = false;
 	struct nfs_page *req = nfs_list_entry(hdr->pages.next);
 
-	if (test_bit(NFS_IOHDR_REDO, &hdr->flags))
-		goto out_put;
-
 	nfs_init_cinfo_from_dreq(&cinfo, dreq);
 
 	spin_lock(&dreq->lock);
 
 	if (test_bit(NFS_IOHDR_ERROR, &hdr->flags))
 		dreq->error = hdr->error;
-	if (dreq->error == 0) {
+
+	if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+		spin_unlock(&dreq->lock);
+		goto out_put;
+	}
+
+	if (hdr->good_bytes != 0) {
 		nfs_direct_good_bytes(dreq, hdr);
 		if (nfs_write_need_commit(hdr)) {
 			if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES)
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index b04e20d28162..5657b7f2611f 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/nfs_fs.h>
+#include <linux/nfs_mount.h>
 #include <linux/nfs_page.h>
 #include <linux/module.h>
 #include <linux/sched/mm.h>
@@ -928,7 +929,9 @@ retry:
 	pgm = &pgio->pg_mirrors[0];
 	pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize;
 
-	pgio->pg_maxretrans = io_maxretrans;
+	if (NFS_SERVER(pgio->pg_inode)->flags &
+			(NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR))
+		pgio->pg_maxretrans = io_maxretrans;
 	return;
 out_nolseg:
 	if (pgio->pg_error < 0)
@@ -940,6 +943,7 @@ out_mds:
 			pgio->pg_lseg);
 	pnfs_put_lseg(pgio->pg_lseg);
 	pgio->pg_lseg = NULL;
+	pgio->pg_maxretrans = 0;
 	nfs_pageio_reset_read_mds(pgio);
 }
 
@@ -1000,7 +1004,9 @@ retry:
 		pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].wsize;
 	}
 
-	pgio->pg_maxretrans = io_maxretrans;
+	if (NFS_SERVER(pgio->pg_inode)->flags &
+			(NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR))
+		pgio->pg_maxretrans = io_maxretrans;
 	return;
 
 out_mds:
@@ -1010,6 +1016,7 @@ out_mds:
 			pgio->pg_lseg);
 	pnfs_put_lseg(pgio->pg_lseg);
 	pgio->pg_lseg = NULL;
+	pgio->pg_maxretrans = 0;
 	nfs_pageio_reset_write_mds(pgio);
 }
 
@@ -1148,8 +1155,6 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
 		break;
 	case -NFS4ERR_RETRY_UNCACHED_REP:
 		break;
-	case -EAGAIN:
-		return -NFS4ERR_RESET_TO_PNFS;
 	/* Invalidate Layout errors */
 	case -NFS4ERR_PNFS_NO_LAYOUT:
 	case -ESTALE:           /* mapped NFS4ERR_STALE */
@@ -1210,7 +1215,6 @@ static int ff_layout_async_handle_error_v3(struct rpc_task *task,
 	case -EBADHANDLE:
 	case -ELOOP:
 	case -ENOSPC:
-	case -EAGAIN:
 		break;
 	case -EJUKEBOX:
 		nfs_inc_stats(lseg->pls_layout->plh_inode, NFSIOS_DELAY);
@@ -1445,16 +1449,6 @@ static void ff_layout_read_prepare_v4(struct rpc_task *task, void *data)
 	ff_layout_read_prepare_common(task, hdr);
 }
 
-static void
-ff_layout_io_prepare_transmit(struct rpc_task *task,
-		void *data)
-{
-	struct nfs_pgio_header *hdr = data;
-
-	if (!pnfs_is_valid_lseg(hdr->lseg))
-		rpc_exit(task, -EAGAIN);
-}
-
 static void ff_layout_read_call_done(struct rpc_task *task, void *data)
 {
 	struct nfs_pgio_header *hdr = data;
@@ -1740,7 +1734,6 @@ static void ff_layout_commit_release(void *data)
 
 static const struct rpc_call_ops ff_layout_read_call_ops_v3 = {
 	.rpc_call_prepare = ff_layout_read_prepare_v3,
-	.rpc_call_prepare_transmit = ff_layout_io_prepare_transmit,
 	.rpc_call_done = ff_layout_read_call_done,
 	.rpc_count_stats = ff_layout_read_count_stats,
 	.rpc_release = ff_layout_read_release,
@@ -1748,7 +1741,6 @@ static const struct rpc_call_ops ff_layout_read_call_ops_v3 = {
 
 static const struct rpc_call_ops ff_layout_read_call_ops_v4 = {
 	.rpc_call_prepare = ff_layout_read_prepare_v4,
-	.rpc_call_prepare_transmit = ff_layout_io_prepare_transmit,
 	.rpc_call_done = ff_layout_read_call_done,
 	.rpc_count_stats = ff_layout_read_count_stats,
 	.rpc_release = ff_layout_read_release,
@@ -1756,7 +1748,6 @@ static const struct rpc_call_ops ff_layout_read_call_ops_v4 = {
 
 static const struct rpc_call_ops ff_layout_write_call_ops_v3 = {
 	.rpc_call_prepare = ff_layout_write_prepare_v3,
-	.rpc_call_prepare_transmit = ff_layout_io_prepare_transmit,
 	.rpc_call_done = ff_layout_write_call_done,
 	.rpc_count_stats = ff_layout_write_count_stats,
 	.rpc_release = ff_layout_write_release,
@@ -1764,7 +1755,6 @@ static const struct rpc_call_ops ff_layout_write_call_ops_v3 = {
 
 static const struct rpc_call_ops ff_layout_write_call_ops_v4 = {
 	.rpc_call_prepare = ff_layout_write_prepare_v4,
-	.rpc_call_prepare_transmit = ff_layout_io_prepare_transmit,
 	.rpc_call_done = ff_layout_write_call_done,
 	.rpc_count_stats = ff_layout_write_count_stats,
 	.rpc_release = ff_layout_write_release,
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 8a1758200b57..c764cfe456e5 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1403,12 +1403,21 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
 	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
 		return 0;
 
+	/* No fileid? Just exit */
+	if (!(fattr->valid & NFS_ATTR_FATTR_FILEID))
+		return 0;
 	/* Has the inode gone and changed behind our back? */
-	if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid)
+	if (nfsi->fileid != fattr->fileid) {
+		/* Is this perhaps the mounted-on fileid? */
+		if ((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) &&
+		    nfsi->fileid == fattr->mounted_on_fileid)
+			return 0;
 		return -ESTALE;
+	}
 	if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT))
 		return -ESTALE;
 
+
 	if (!nfs_file_has_buffered_writers(nfsi)) {
 		/* Verify a few of the more important attributes */
 		if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && !inode_eq_iversion_raw(inode, fattr->change_attr))
@@ -1768,18 +1777,6 @@ int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fa
 EXPORT_SYMBOL_GPL(nfs_post_op_update_inode_force_wcc);
 
 
-static inline bool nfs_fileid_valid(struct nfs_inode *nfsi,
-				    struct nfs_fattr *fattr)
-{
-	bool ret1 = true, ret2 = true;
-
-	if (fattr->valid & NFS_ATTR_FATTR_FILEID)
-		ret1 = (nfsi->fileid == fattr->fileid);
-	if (fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID)
-		ret2 = (nfsi->fileid == fattr->mounted_on_fileid);
-	return ret1 || ret2;
-}
-
 /*
  * Many nfs protocol calls return the new file attributes after
  * an operation.  Here we update the inode to reflect the state
@@ -1810,7 +1807,15 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			nfs_display_fhandle_hash(NFS_FH(inode)),
 			atomic_read(&inode->i_count), fattr->valid);
 
-	if (!nfs_fileid_valid(nfsi, fattr)) {
+	/* No fileid? Just exit */
+	if (!(fattr->valid & NFS_ATTR_FATTR_FILEID))
+		return 0;
+	/* Has the inode gone and changed behind our back? */
+	if (nfsi->fileid != fattr->fileid) {
+		/* Is this perhaps the mounted-on fileid? */
+		if ((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) &&
+		    nfsi->fileid == fattr->mounted_on_fileid)
+			return 0;
 		printk(KERN_ERR "NFS: server %s error: fileid changed\n"
 			"fsid %s: expected fileid 0x%Lx, got 0x%Lx\n",
 			NFS_SERVER(inode)->nfs_client->cl_hostname,
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index a2346a2f8361..e64f810223be 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -775,3 +775,13 @@ static inline bool nfs_error_is_fatal(int err)
 	}
 }
 
+static inline bool nfs_error_is_fatal_on_server(int err)
+{
+	switch (err) {
+	case 0:
+	case -ERESTARTSYS:
+	case -EINTR:
+		return false;
+	}
+	return nfs_error_is_fatal(err);
+}
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 96db471ca2e5..339663d04bf8 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -73,13 +73,13 @@ nfs4_file_open(struct inode *inode, struct file *filp)
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		switch (err) {
-		case -EPERM:
-		case -EACCES:
-		case -EDQUOT:
-		case -ENOSPC:
-		case -EROFS:
-			goto out_put_ctx;
 		default:
+			goto out_put_ctx;
+		case -ENOENT:
+		case -ESTALE:
+		case -EISDIR:
+		case -ENOTDIR:
+		case -ELOOP:
 			goto out_drop;
 		}
 	}
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index ed4e1b07447b..20b3717cd7ca 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -590,7 +590,7 @@ static void nfs_pgio_rpcsetup(struct nfs_pgio_header *hdr,
 	}
 
 	hdr->res.fattr   = &hdr->fattr;
-	hdr->res.count   = count;
+	hdr->res.count   = 0;
 	hdr->res.eof     = 0;
 	hdr->res.verf    = &hdr->verf;
 	nfs_fattr_init(&hdr->fattr);
@@ -1251,20 +1251,23 @@ static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc,
 int nfs_pageio_resend(struct nfs_pageio_descriptor *desc,
 		      struct nfs_pgio_header *hdr)
 {
-	LIST_HEAD(failed);
+	LIST_HEAD(pages);
 
 	desc->pg_io_completion = hdr->io_completion;
 	desc->pg_dreq = hdr->dreq;
-	while (!list_empty(&hdr->pages)) {
-		struct nfs_page *req = nfs_list_entry(hdr->pages.next);
+	list_splice_init(&hdr->pages, &pages);
+	while (!list_empty(&pages)) {
+		struct nfs_page *req = nfs_list_entry(pages.next);
 
 		if (!nfs_pageio_add_request(desc, req))
-			nfs_list_move_request(req, &failed);
+			break;
 	}
 	nfs_pageio_complete(desc);
-	if (!list_empty(&failed)) {
-		list_move(&failed, &hdr->pages);
-		return desc->pg_error < 0 ? desc->pg_error : -EIO;
+	if (!list_empty(&pages)) {
+		int err = desc->pg_error < 0 ? desc->pg_error : -EIO;
+		hdr->completion_ops->error_cleanup(&pages, err);
+		nfs_set_pgio_error(hdr, err, hdr->io_start);
+		return err;
 	}
 	return 0;
 }
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index c0046c348910..82af4809b869 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -627,11 +627,16 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
 			/* Add this address as an alias */
 			rpc_clnt_add_xprt(clp->cl_rpcclient, &xprt_args,
 					rpc_clnt_test_and_add_xprt, NULL);
-		} else
-			clp = get_v3_ds_connect(mds_srv,
-					(struct sockaddr *)&da->da_addr,
-					da->da_addrlen, IPPROTO_TCP,
-					timeo, retrans);
+			continue;
+		}
+		clp = get_v3_ds_connect(mds_srv,
+				(struct sockaddr *)&da->da_addr,
+				da->da_addrlen, IPPROTO_TCP,
+				timeo, retrans);
+		if (IS_ERR(clp))
+			continue;
+		clp->cl_rpcclient->cl_softerr = 0;
+		clp->cl_rpcclient->cl_softrtry = 0;
 	}
 
 	if (IS_ERR(clp)) {
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index 5552fa8b6e12..0f7288b94633 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -594,7 +594,8 @@ static int nfs_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 		/* Emulate the eof flag, which isn't normally needed in NFSv2
 		 * as it is guaranteed to always return the file attributes
 		 */
-		if (hdr->args.offset + hdr->res.count >= hdr->res.fattr->size)
+		if ((hdr->res.count == 0 && hdr->args.count > 0) ||
+		    hdr->args.offset + hdr->res.count >= hdr->res.fattr->size)
 			hdr->res.eof = 1;
 	}
 	return 0;
@@ -615,8 +616,10 @@ static int nfs_proc_pgio_rpc_prepare(struct rpc_task *task,
 
 static int nfs_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 {
-	if (task->tk_status >= 0)
+	if (task->tk_status >= 0) {
+		hdr->res.count = hdr->args.count;
 		nfs_writeback_update_inode(hdr);
+	}
 	return 0;
 }
 
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index c19841c82b6a..cfe0b586eadd 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -91,19 +91,25 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio)
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds);
 
-static void nfs_readpage_release(struct nfs_page *req)
+static void nfs_readpage_release(struct nfs_page *req, int error)
 {
 	struct inode *inode = d_inode(nfs_req_openctx(req)->dentry);
+	struct page *page = req->wb_page;
 
 	dprintk("NFS: read done (%s/%llu %d@%lld)\n", inode->i_sb->s_id,
 		(unsigned long long)NFS_FILEID(inode), req->wb_bytes,
 		(long long)req_offset(req));
 
+	if (nfs_error_is_fatal_on_server(error) && error != -ETIMEDOUT)
+		SetPageError(page);
 	if (nfs_page_group_sync_on_bit(req, PG_UNLOCKPAGE)) {
-		if (PageUptodate(req->wb_page))
-			nfs_readpage_to_fscache(inode, req->wb_page, 0);
+		struct address_space *mapping = page_file_mapping(page);
 
-		unlock_page(req->wb_page);
+		if (PageUptodate(page))
+			nfs_readpage_to_fscache(inode, page, 0);
+		else if (!PageError(page) && !PagePrivate(page))
+			generic_error_remove_page(mapping, page);
+		unlock_page(page);
 	}
 	nfs_release_request(req);
 }
@@ -131,7 +137,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 			     &nfs_async_read_completion_ops);
 	if (!nfs_pageio_add_request(&pgio, new)) {
 		nfs_list_remove_request(new);
-		nfs_readpage_release(new);
+		nfs_readpage_release(new, pgio.pg_error);
 	}
 	nfs_pageio_complete(&pgio);
 
@@ -153,6 +159,7 @@ static void nfs_page_group_set_uptodate(struct nfs_page *req)
 static void nfs_read_completion(struct nfs_pgio_header *hdr)
 {
 	unsigned long bytes = 0;
+	int error;
 
 	if (test_bit(NFS_IOHDR_REDO, &hdr->flags))
 		goto out;
@@ -179,14 +186,19 @@ static void nfs_read_completion(struct nfs_pgio_header *hdr)
 				zero_user_segment(page, start, end);
 			}
 		}
+		error = 0;
 		bytes += req->wb_bytes;
 		if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) {
 			if (bytes <= hdr->good_bytes)
 				nfs_page_group_set_uptodate(req);
+			else {
+				error = hdr->error;
+				xchg(&nfs_req_openctx(req)->error, error);
+			}
 		} else
 			nfs_page_group_set_uptodate(req);
 		nfs_list_remove_request(req);
-		nfs_readpage_release(req);
+		nfs_readpage_release(req, error);
 	}
 out:
 	hdr->release(hdr);
@@ -213,7 +225,7 @@ nfs_async_read_error(struct list_head *head, int error)
 	while (!list_empty(head)) {
 		req = nfs_list_entry(head->next);
 		nfs_list_remove_request(req);
-		nfs_readpage_release(req);
+		nfs_readpage_release(req, error);
 	}
 }
 
@@ -337,8 +349,13 @@ int nfs_readpage(struct file *file, struct page *page)
 			goto out;
 	}
 
+	xchg(&ctx->error, 0);
 	error = nfs_readpage_async(ctx, inode, page);
-
+	if (!error) {
+		error = wait_on_page_locked_killable(page);
+		if (!PageUptodate(page) && !error)
+			error = xchg(&ctx->error, 0);
+	}
 out:
 	put_nfs_open_context(ctx);
 	return error;
@@ -372,8 +389,8 @@ readpage_async_filler(void *data, struct page *page)
 		zero_user_segment(page, len, PAGE_SIZE);
 	if (!nfs_pageio_add_request(desc->pgio, new)) {
 		nfs_list_remove_request(new);
-		nfs_readpage_release(new);
 		error = desc->pgio->pg_error;
+		nfs_readpage_release(new, error);
 		goto out;
 	}
 	return 0;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 92d9cadc6102..85ca49549b39 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -57,6 +57,7 @@ static const struct rpc_call_ops nfs_commit_ops;
 static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops;
 static const struct nfs_commit_completion_ops nfs_commit_completion_ops;
 static const struct nfs_rw_ops nfs_rw_write_ops;
+static void nfs_inode_remove_request(struct nfs_page *req);
 static void nfs_clear_request_commit(struct nfs_page *req);
 static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo,
 				      struct inode *inode);
@@ -591,23 +592,13 @@ release_request:
 
 static void nfs_write_error(struct nfs_page *req, int error)
 {
+	nfs_set_pageerror(page_file_mapping(req->wb_page));
 	nfs_mapping_set_error(req->wb_page, error);
+	nfs_inode_remove_request(req);
 	nfs_end_page_writeback(req);
 	nfs_release_request(req);
 }
 
-static bool
-nfs_error_is_fatal_on_server(int err)
-{
-	switch (err) {
-	case 0:
-	case -ERESTARTSYS:
-	case -EINTR:
-		return false;
-	}
-	return nfs_error_is_fatal(err);
-}
-
 /*
  * Find an associated nfs write request, and prepare to flush it out
  * May return an error if the user signalled nfs_wait_on_request().
@@ -615,7 +606,6 @@ nfs_error_is_fatal_on_server(int err)
 static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
 				struct page *page)
 {
-	struct address_space *mapping;
 	struct nfs_page *req;
 	int ret = 0;
 
@@ -630,12 +620,11 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
 	WARN_ON_ONCE(test_bit(PG_CLEAN, &req->wb_flags));
 
 	/* If there is a fatal error that covers this write, just exit */
-	ret = 0;
-	mapping = page_file_mapping(page);
-	if (test_bit(AS_ENOSPC, &mapping->flags) ||
-	    test_bit(AS_EIO, &mapping->flags))
+	ret = pgio->pg_error;
+	if (nfs_error_is_fatal_on_server(ret))
 		goto out_launder;
 
+	ret = 0;
 	if (!nfs_pageio_add_request(pgio, req)) {
 		ret = pgio->pg_error;
 		/*
@@ -647,6 +636,7 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
 		} else
 			ret = -EAGAIN;
 		nfs_redirty_request(req);
+		pgio->pg_error = 0;
 	} else
 		nfs_add_stats(page_file_mapping(page)->host,
 				NFSIOS_WRITEPAGES, 1);
@@ -666,7 +656,7 @@ static int nfs_do_writepage(struct page *page, struct writeback_control *wbc,
 	ret = nfs_page_async_flush(pgio, page);
 	if (ret == -EAGAIN) {
 		redirty_page_for_writepage(wbc, page);
-		ret = 0;
+		ret = AOP_WRITEPAGE_ACTIVATE;
 	}
 	return ret;
 }
@@ -685,10 +675,11 @@ static int nfs_writepage_locked(struct page *page,
 	nfs_pageio_init_write(&pgio, inode, 0,
 				false, &nfs_async_write_completion_ops);
 	err = nfs_do_writepage(page, wbc, &pgio);
+	pgio.pg_error = 0;
 	nfs_pageio_complete(&pgio);
 	if (err < 0)
 		return err;
-	if (pgio.pg_error < 0)
+	if (nfs_error_is_fatal(pgio.pg_error))
 		return pgio.pg_error;
 	return 0;
 }
@@ -698,7 +689,8 @@ int nfs_writepage(struct page *page, struct writeback_control *wbc)
 	int ret;
 
 	ret = nfs_writepage_locked(page, wbc);
-	unlock_page(page);
+	if (ret != AOP_WRITEPAGE_ACTIVATE)
+		unlock_page(page);
 	return ret;
 }
 
@@ -707,7 +699,8 @@ static int nfs_writepages_callback(struct page *page, struct writeback_control *
 	int ret;
 
 	ret = nfs_do_writepage(page, wbc, data);
-	unlock_page(page);
+	if (ret != AOP_WRITEPAGE_ACTIVATE)
+		unlock_page(page);
 	return ret;
 }
 
@@ -733,13 +726,14 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 				&nfs_async_write_completion_ops);
 	pgio.pg_io_completion = ioc;
 	err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio);
+	pgio.pg_error = 0;
 	nfs_pageio_complete(&pgio);
 	nfs_io_completion_put(ioc);
 
 	if (err < 0)
 		goto out_err;
 	err = pgio.pg_error;
-	if (err < 0)
+	if (nfs_error_is_fatal(err))
 		goto out_err;
 	return 0;
 out_err:
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 26ad75ae2be0..96352ab7bd81 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -571,7 +571,7 @@ nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *data)
  */
 static int nfsd_reply_cache_stats_show(struct seq_file *m, void *v)
 {
-	struct nfsd_net *nn = v;
+	struct nfsd_net *nn = m->private;
 
 	seq_printf(m, "max entries:           %u\n", nn->max_drc_entries);
 	seq_printf(m, "num entries:           %u\n",
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 13c548733860..3cf4f6aa48d6 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1171,13 +1171,17 @@ static struct inode *nfsd_get_inode(struct super_block *sb, umode_t mode)
 	return inode;
 }
 
-static int __nfsd_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int __nfsd_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode, struct nfsdfs_client *ncl)
 {
 	struct inode *inode;
 
 	inode = nfsd_get_inode(dir->i_sb, mode);
 	if (!inode)
 		return -ENOMEM;
+	if (ncl) {
+		inode->i_private = ncl;
+		kref_get(&ncl->cl_ref);
+	}
 	d_add(dentry, inode);
 	inc_nlink(dir);
 	fsnotify_mkdir(dir, dentry);
@@ -1194,17 +1198,14 @@ static struct dentry *nfsd_mkdir(struct dentry *parent, struct nfsdfs_client *nc
 	dentry = d_alloc_name(parent, name);
 	if (!dentry)
 		goto out_err;
-	ret = __nfsd_mkdir(d_inode(parent), dentry, S_IFDIR | 0600);
+	ret = __nfsd_mkdir(d_inode(parent), dentry, S_IFDIR | 0600, ncl);
 	if (ret)
 		goto out_err;
-	if (ncl) {
-		d_inode(dentry)->i_private = ncl;
-		kref_get(&ncl->cl_ref);
-	}
 out:
 	inode_unlock(dir);
 	return dentry;
 out_err:
+	dput(dentry);
 	dentry = ERR_PTR(ret);
 	goto out;
 }
@@ -1214,11 +1215,9 @@ static void clear_ncl(struct inode *inode)
 	struct nfsdfs_client *ncl = inode->i_private;
 
 	inode->i_private = NULL;
-	synchronize_rcu();
 	kref_put(&ncl->cl_ref, ncl->cl_release);
 }
 
-
 static struct nfsdfs_client *__get_nfsdfs_client(struct inode *inode)
 {
 	struct nfsdfs_client *nc = inode->i_private;
@@ -1232,9 +1231,9 @@ struct nfsdfs_client *get_nfsdfs_client(struct inode *inode)
 {
 	struct nfsdfs_client *nc;
 
-	rcu_read_lock();
+	inode_lock_shared(inode);
 	nc = __get_nfsdfs_client(inode);
-	rcu_read_unlock();
+	inode_unlock_shared(inode);
 	return nc;
 }
 /* from __rpc_unlink */
diff --git a/fs/read_write.c b/fs/read_write.c
index 1f5088dec566..5bbf587f5bc1 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1811,10 +1811,7 @@ static int generic_remap_check_len(struct inode *inode_in,
 	return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL;
 }
 
-/*
- * Read a page's worth of file data into the page cache.  Return the page
- * locked.
- */
+/* Read a page's worth of file data into the page cache. */
 static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset)
 {
 	struct page *page;
@@ -1826,11 +1823,33 @@ static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset)
 		put_page(page);
 		return ERR_PTR(-EIO);
 	}
-	lock_page(page);
 	return page;
 }
 
 /*
+ * Lock two pages, ensuring that we lock in offset order if the pages are from
+ * the same file.
+ */
+static void vfs_lock_two_pages(struct page *page1, struct page *page2)
+{
+	/* Always lock in order of increasing index. */
+	if (page1->index > page2->index)
+		swap(page1, page2);
+
+	lock_page(page1);
+	if (page1 != page2)
+		lock_page(page2);
+}
+
+/* Unlock two pages, being careful not to unlock the same page twice. */
+static void vfs_unlock_two_pages(struct page *page1, struct page *page2)
+{
+	unlock_page(page1);
+	if (page1 != page2)
+		unlock_page(page2);
+}
+
+/*
  * Compare extents of two files to see if they are the same.
  * Caller must have locked both inodes to prevent write races.
  */
@@ -1867,10 +1886,24 @@ static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
 		dest_page = vfs_dedupe_get_page(dest, destoff);
 		if (IS_ERR(dest_page)) {
 			error = PTR_ERR(dest_page);
-			unlock_page(src_page);
 			put_page(src_page);
 			goto out_error;
 		}
+
+		vfs_lock_two_pages(src_page, dest_page);
+
+		/*
+		 * Now that we've locked both pages, make sure they're still
+		 * mapped to the file data we're interested in.  If not,
+		 * someone is invalidating pages on us and we lose.
+		 */
+		if (!PageUptodate(src_page) || !PageUptodate(dest_page) ||
+		    src_page->mapping != src->i_mapping ||
+		    dest_page->mapping != dest->i_mapping) {
+			same = false;
+			goto unlock;
+		}
+
 		src_addr = kmap_atomic(src_page);
 		dest_addr = kmap_atomic(dest_page);
 
@@ -1882,8 +1915,8 @@ static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
 
 		kunmap_atomic(dest_addr);
 		kunmap_atomic(src_addr);
-		unlock_page(dest_page);
-		unlock_page(src_page);
+unlock:
+		vfs_unlock_two_pages(src_page, dest_page);
 		put_page(dest_page);
 		put_page(src_page);
 
diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c
index 80d7301ab76d..c0b84e960b20 100644
--- a/fs/ubifs/budget.c
+++ b/fs/ubifs/budget.c
@@ -51,7 +51,7 @@
 static void shrink_liability(struct ubifs_info *c, int nr_to_write)
 {
 	down_read(&c->vfs_sb->s_umount);
-	writeback_inodes_sb(c->vfs_sb, WB_REASON_FS_FREE_SPACE);
+	writeback_inodes_sb_nr(c->vfs_sb, nr_to_write, WB_REASON_FS_FREE_SPACE);
 	up_read(&c->vfs_sb->s_umount);
 }
 
diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c
index b52624e28fa1..3b4b4114f208 100644
--- a/fs/ubifs/orphan.c
+++ b/fs/ubifs/orphan.c
@@ -129,7 +129,6 @@ static void __orphan_drop(struct ubifs_info *c, struct ubifs_orphan *o)
 static void orphan_delete(struct ubifs_info *c, struct ubifs_orphan *orph)
 {
 	if (orph->del) {
-		spin_unlock(&c->orphan_lock);
 		dbg_gen("deleted twice ino %lu", orph->inum);
 		return;
 	}
@@ -138,7 +137,6 @@ static void orphan_delete(struct ubifs_info *c, struct ubifs_orphan *orph)
 		orph->del = 1;
 		orph->dnext = c->orph_dnext;
 		c->orph_dnext = orph;
-		spin_unlock(&c->orphan_lock);
 		dbg_gen("delete later ino %lu", orph->inum);
 		return;
 	}
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 2c0803b0ac3a..8c1d571334bc 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -609,6 +609,10 @@ static int init_constants_early(struct ubifs_info *c)
 	c->max_bu_buf_len = UBIFS_MAX_BULK_READ * UBIFS_MAX_DATA_NODE_SZ;
 	if (c->max_bu_buf_len > c->leb_size)
 		c->max_bu_buf_len = c->leb_size;
+
+	/* Log is ready, preserve one LEB for commits. */
+	c->min_log_bytes = c->leb_size;
+
 	return 0;
 }
 
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index ccbdbd62f0d8..fe6d804a38dc 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -880,6 +880,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 	/* len == 0 means wake all */
 	struct userfaultfd_wake_range range = { .len = 0, };
 	unsigned long new_flags;
+	bool still_valid;
 
 	WRITE_ONCE(ctx->released, true);
 
@@ -895,8 +896,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 	 * taking the mmap_sem for writing.
 	 */
 	down_write(&mm->mmap_sem);
-	if (!mmget_still_valid(mm))
-		goto skip_mm;
+	still_valid = mmget_still_valid(mm);
 	prev = NULL;
 	for (vma = mm->mmap; vma; vma = vma->vm_next) {
 		cond_resched();
@@ -907,19 +907,20 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 			continue;
 		}
 		new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
-		prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
-				 new_flags, vma->anon_vma,
-				 vma->vm_file, vma->vm_pgoff,
-				 vma_policy(vma),
-				 NULL_VM_UFFD_CTX);
-		if (prev)
-			vma = prev;
-		else
-			prev = vma;
+		if (still_valid) {
+			prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
+					 new_flags, vma->anon_vma,
+					 vma->vm_file, vma->vm_pgoff,
+					 vma_policy(vma),
+					 NULL_VM_UFFD_CTX);
+			if (prev)
+				vma = prev;
+			else
+				prev = vma;
+		}
 		vma->vm_flags = new_flags;
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
 	}
-skip_mm:
 	up_write(&mm->mmap_sem);
 	mmput(mm);
 wakeup:
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index 7fcf7569743f..7bd7534f5051 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -547,63 +547,12 @@ xfs_file_compat_ioctl(
 	struct inode		*inode = file_inode(filp);
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
-	void			__user *arg = (void __user *)p;
+	void			__user *arg = compat_ptr(p);
 	int			error;
 
 	trace_xfs_file_compat_ioctl(ip);
 
 	switch (cmd) {
-	/* No size or alignment issues on any arch */
-	case XFS_IOC_DIOINFO:
-	case XFS_IOC_FSGEOMETRY_V4:
-	case XFS_IOC_FSGEOMETRY:
-	case XFS_IOC_AG_GEOMETRY:
-	case XFS_IOC_FSGETXATTR:
-	case XFS_IOC_FSSETXATTR:
-	case XFS_IOC_FSGETXATTRA:
-	case XFS_IOC_FSSETDM:
-	case XFS_IOC_GETBMAP:
-	case XFS_IOC_GETBMAPA:
-	case XFS_IOC_GETBMAPX:
-	case XFS_IOC_FSCOUNTS:
-	case XFS_IOC_SET_RESBLKS:
-	case XFS_IOC_GET_RESBLKS:
-	case XFS_IOC_FSGROWFSLOG:
-	case XFS_IOC_GOINGDOWN:
-	case XFS_IOC_ERROR_INJECTION:
-	case XFS_IOC_ERROR_CLEARALL:
-	case FS_IOC_GETFSMAP:
-	case XFS_IOC_SCRUB_METADATA:
-	case XFS_IOC_BULKSTAT:
-	case XFS_IOC_INUMBERS:
-		return xfs_file_ioctl(filp, cmd, p);
-#if !defined(BROKEN_X86_ALIGNMENT) || defined(CONFIG_X86_X32)
-	/*
-	 * These are handled fine if no alignment issues.  To support x32
-	 * which uses native 64-bit alignment we must emit these cases in
-	 * addition to the ia-32 compat set below.
-	 */
-	case XFS_IOC_ALLOCSP:
-	case XFS_IOC_FREESP:
-	case XFS_IOC_RESVSP:
-	case XFS_IOC_UNRESVSP:
-	case XFS_IOC_ALLOCSP64:
-	case XFS_IOC_FREESP64:
-	case XFS_IOC_RESVSP64:
-	case XFS_IOC_UNRESVSP64:
-	case XFS_IOC_FSGEOMETRY_V1:
-	case XFS_IOC_FSGROWFSDATA:
-	case XFS_IOC_FSGROWFSRT:
-	case XFS_IOC_ZERO_RANGE:
-#ifdef CONFIG_X86_X32
-	/*
-	 * x32 special: this gets a different cmd number from the ia-32 compat
-	 * case below; the associated data will match native 64-bit alignment.
-	 */
-	case XFS_IOC_SWAPEXT:
-#endif
-		return xfs_file_ioctl(filp, cmd, p);
-#endif
 #if defined(BROKEN_X86_ALIGNMENT)
 	case XFS_IOC_ALLOCSP_32:
 	case XFS_IOC_FREESP_32:
@@ -705,6 +654,7 @@ xfs_file_compat_ioctl(
 	case XFS_IOC_FSSETDM_BY_HANDLE_32:
 		return xfs_compat_fssetdm_by_handle(filp, arg);
 	default:
-		return -ENOIOCTLCMD;
+		/* try the native version */
+		return xfs_file_ioctl(filp, cmd, (unsigned long)arg);
 	}
 }
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index ff3c1fae5357..fe285d123d69 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -793,6 +793,7 @@ xfs_setattr_nonsize(
 
 out_cancel:
 	xfs_trans_cancel(tp);
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 out_dqrele:
 	xfs_qm_dqrele(udqp);
 	xfs_qm_dqrele(gdqp);
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index 0c954cad7449..a339bd5fa260 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -32,7 +32,7 @@ xfs_break_leased_layouts(
 	struct xfs_inode	*ip = XFS_I(inode);
 	int			error;
 
-	while ((error = break_layout(inode, false) == -EWOULDBLOCK)) {
+	while ((error = break_layout(inode, false)) == -EWOULDBLOCK) {
 		xfs_iunlock(ip, *iolock);
 		*did_unlock = true;
 		error = break_layout(inode, true);
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index c4ec7afd1170..edbe37b7f636 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1190,11 +1190,11 @@ xfs_reflink_remap_blocks(
 }
 
 /*
- * Grab the exclusive iolock for a data copy from src to dest, making
- * sure to abide vfs locking order (lowest pointer value goes first) and
- * breaking the pnfs layout leases on dest before proceeding.  The loop
- * is needed because we cannot call the blocking break_layout() with the
- * src iolock held, and therefore have to back out both locks.
+ * Grab the exclusive iolock for a data copy from src to dest, making sure to
+ * abide vfs locking order (lowest pointer value goes first) and breaking the
+ * layout leases before proceeding.  The loop is needed because we cannot call
+ * the blocking break_layout() with the iolocks held, and therefore have to
+ * back out both locks.
  */
 static int
 xfs_iolock_two_inodes_and_break_layout(
@@ -1203,33 +1203,44 @@ xfs_iolock_two_inodes_and_break_layout(
 {
 	int			error;
 
-retry:
-	if (src < dest) {
-		inode_lock_shared(src);
-		inode_lock_nested(dest, I_MUTEX_NONDIR2);
-	} else {
-		/* src >= dest */
-		inode_lock(dest);
-	}
+	if (src > dest)
+		swap(src, dest);
 
-	error = break_layout(dest, false);
-	if (error == -EWOULDBLOCK) {
-		inode_unlock(dest);
-		if (src < dest)
-			inode_unlock_shared(src);
+retry:
+	/* Wait to break both inodes' layouts before we start locking. */
+	error = break_layout(src, true);
+	if (error)
+		return error;
+	if (src != dest) {
 		error = break_layout(dest, true);
 		if (error)
 			return error;
-		goto retry;
 	}
+
+	/* Lock one inode and make sure nobody got in and leased it. */
+	inode_lock(src);
+	error = break_layout(src, false);
 	if (error) {
+		inode_unlock(src);
+		if (error == -EWOULDBLOCK)
+			goto retry;
+		return error;
+	}
+
+	if (src == dest)
+		return 0;
+
+	/* Lock the other inode and make sure nobody got in and leased it. */
+	inode_lock_nested(dest, I_MUTEX_NONDIR2);
+	error = break_layout(dest, false);
+	if (error) {
+		inode_unlock(src);
 		inode_unlock(dest);
-		if (src < dest)
-			inode_unlock_shared(src);
+		if (error == -EWOULDBLOCK)
+			goto retry;
 		return error;
 	}
-	if (src > dest)
-		inode_lock_shared_nested(src, I_MUTEX_NONDIR2);
+
 	return 0;
 }
 
@@ -1247,10 +1258,10 @@ xfs_reflink_remap_unlock(
 
 	xfs_iunlock(dest, XFS_MMAPLOCK_EXCL);
 	if (!same_inode)
-		xfs_iunlock(src, XFS_MMAPLOCK_SHARED);
+		xfs_iunlock(src, XFS_MMAPLOCK_EXCL);
 	inode_unlock(inode_out);
 	if (!same_inode)
-		inode_unlock_shared(inode_in);
+		inode_unlock(inode_in);
 }
 
 /*
@@ -1325,7 +1336,7 @@ xfs_reflink_remap_prep(
 	if (same_inode)
 		xfs_ilock(src, XFS_MMAPLOCK_EXCL);
 	else
-		xfs_lock_two_inodes(src, XFS_MMAPLOCK_SHARED, dest,
+		xfs_lock_two_inodes(src, XFS_MMAPLOCK_EXCL, dest,
 				XFS_MMAPLOCK_EXCL);
 
 	/* Check file eligibility and prepare for block sharing. */