Merge branch 'perf/urgent' into perf/core

Pick up the latest fixes, refresh the development tree.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

40 files changed, 505 insertions, 319 deletions

diff --git a/fs/aio.c b/fs/aio.c
index 6efb7f6cb22e..062a5f6a1448 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -244,9 +244,14 @@ static void aio_free_ring(struct kioctx *ctx)
 	int i;
 
 	for (i = 0; i < ctx->nr_pages; i++) {
+		struct page *page;
 		pr_debug("pid(%d) [%d] page->count=%d\n", current->pid, i,
 				page_count(ctx->ring_pages[i]));
-		put_page(ctx->ring_pages[i]);
+		page = ctx->ring_pages[i];
+		if (!page)
+			continue;
+		ctx->ring_pages[i] = NULL;
+		put_page(page);
 	}
 
 	put_aio_ring_file(ctx);
@@ -280,18 +285,38 @@ static int aio_migratepage(struct address_space *mapping, struct page *new,
 	unsigned long flags;
 	int rc;
 
+	rc = 0;
+
+	/* Make sure the old page hasn't already been changed */
+	spin_lock(&mapping->private_lock);
+	ctx = mapping->private_data;
+	if (ctx) {
+		pgoff_t idx;
+		spin_lock_irqsave(&ctx->completion_lock, flags);
+		idx = old->index;
+		if (idx < (pgoff_t)ctx->nr_pages) {
+			if (ctx->ring_pages[idx] != old)
+				rc = -EAGAIN;
+		} else
+			rc = -EINVAL;
+		spin_unlock_irqrestore(&ctx->completion_lock, flags);
+	} else
+		rc = -EINVAL;
+	spin_unlock(&mapping->private_lock);
+
+	if (rc != 0)
+		return rc;
+
 	/* Writeback must be complete */
 	BUG_ON(PageWriteback(old));
-	put_page(old);
+	get_page(new);
 
-	rc = migrate_page_move_mapping(mapping, new, old, NULL, mode);
+	rc = migrate_page_move_mapping(mapping, new, old, NULL, mode, 1);
 	if (rc != MIGRATEPAGE_SUCCESS) {
-		get_page(old);
+		put_page(new);
 		return rc;
 	}
 
-	get_page(new);
-
 	/* We can potentially race against kioctx teardown here.  Use the
 	 * address_space's private data lock to protect the mapping's
 	 * private_data.
@@ -303,13 +328,24 @@ static int aio_migratepage(struct address_space *mapping, struct page *new,
 		spin_lock_irqsave(&ctx->completion_lock, flags);
 		migrate_page_copy(new, old);
 		idx = old->index;
-		if (idx < (pgoff_t)ctx->nr_pages)
-			ctx->ring_pages[idx] = new;
+		if (idx < (pgoff_t)ctx->nr_pages) {
+			/* And only do the move if things haven't changed */
+			if (ctx->ring_pages[idx] == old)
+				ctx->ring_pages[idx] = new;
+			else
+				rc = -EAGAIN;
+		} else
+			rc = -EINVAL;
 		spin_unlock_irqrestore(&ctx->completion_lock, flags);
 	} else
 		rc = -EBUSY;
 	spin_unlock(&mapping->private_lock);
 
+	if (rc == MIGRATEPAGE_SUCCESS)
+		put_page(old);
+	else
+		put_page(new);
+
 	return rc;
 }
 #endif
@@ -326,7 +362,7 @@ static int aio_setup_ring(struct kioctx *ctx)
 	struct aio_ring *ring;
 	unsigned nr_events = ctx->max_reqs;
 	struct mm_struct *mm = current->mm;
-	unsigned long size, populate;
+	unsigned long size, unused;
 	int nr_pages;
 	int i;
 	struct file *file;
@@ -347,6 +383,20 @@ static int aio_setup_ring(struct kioctx *ctx)
 		return -EAGAIN;
 	}
 
+	ctx->aio_ring_file = file;
+	nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring))
+			/ sizeof(struct io_event);
+
+	ctx->ring_pages = ctx->internal_pages;
+	if (nr_pages > AIO_RING_PAGES) {
+		ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *),
+					  GFP_KERNEL);
+		if (!ctx->ring_pages) {
+			put_aio_ring_file(ctx);
+			return -ENOMEM;
+		}
+	}
+
 	for (i = 0; i < nr_pages; i++) {
 		struct page *page;
 		page = find_or_create_page(file->f_inode->i_mapping,
@@ -358,19 +408,14 @@ static int aio_setup_ring(struct kioctx *ctx)
 		SetPageUptodate(page);
 		SetPageDirty(page);
 		unlock_page(page);
+
+		ctx->ring_pages[i] = page;
 	}
-	ctx->aio_ring_file = file;
-	nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring))
-			/ sizeof(struct io_event);
+	ctx->nr_pages = i;
 
-	ctx->ring_pages = ctx->internal_pages;
-	if (nr_pages > AIO_RING_PAGES) {
-		ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *),
-					  GFP_KERNEL);
-		if (!ctx->ring_pages) {
-			put_aio_ring_file(ctx);
-			return -ENOMEM;
-		}
+	if (unlikely(i != nr_pages)) {
+		aio_free_ring(ctx);
+		return -EAGAIN;
 	}
 
 	ctx->mmap_size = nr_pages * PAGE_SIZE;
@@ -379,9 +424,9 @@ static int aio_setup_ring(struct kioctx *ctx)
 	down_write(&mm->mmap_sem);
 	ctx->mmap_base = do_mmap_pgoff(ctx->aio_ring_file, 0, ctx->mmap_size,
 				       PROT_READ | PROT_WRITE,
-				       MAP_SHARED | MAP_POPULATE, 0, &populate);
+				       MAP_SHARED, 0, &unused);
+	up_write(&mm->mmap_sem);
 	if (IS_ERR((void *)ctx->mmap_base)) {
-		up_write(&mm->mmap_sem);
 		ctx->mmap_size = 0;
 		aio_free_ring(ctx);
 		return -EAGAIN;
@@ -389,27 +434,6 @@ static int aio_setup_ring(struct kioctx *ctx)
 
 	pr_debug("mmap address: 0x%08lx\n", ctx->mmap_base);
 
-	/* We must do this while still holding mmap_sem for write, as we
-	 * need to be protected against userspace attempting to mremap()
-	 * or munmap() the ring buffer.
-	 */
-	ctx->nr_pages = get_user_pages(current, mm, ctx->mmap_base, nr_pages,
-				       1, 0, ctx->ring_pages, NULL);
-
-	/* Dropping the reference here is safe as the page cache will hold
-	 * onto the pages for us.  It is also required so that page migration
-	 * can unmap the pages and get the right reference count.
-	 */
-	for (i = 0; i < ctx->nr_pages; i++)
-		put_page(ctx->ring_pages[i]);
-
-	up_write(&mm->mmap_sem);
-
-	if (unlikely(ctx->nr_pages != nr_pages)) {
-		aio_free_ring(ctx);
-		return -EAGAIN;
-	}
-
 	ctx->user_id = ctx->mmap_base;
 	ctx->nr_events = nr_events; /* trusted copy */
 
@@ -652,7 +676,8 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 	aio_nr += ctx->max_reqs;
 	spin_unlock(&aio_nr_lock);
 
-	percpu_ref_get(&ctx->users); /* io_setup() will drop this ref */
+	percpu_ref_get(&ctx->users);	/* io_setup() will drop this ref */
+	percpu_ref_get(&ctx->reqs);	/* free_ioctx_users() will drop this */
 
 	err = ioctx_add_table(ctx, mm);
 	if (err)
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 1e561c059539..ec3ba43b9faa 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -210,9 +210,13 @@ static int readpage_nounlock(struct file *filp, struct page *page)
 	if (err < 0) {
 		SetPageError(page);
 		goto out;
-	} else if (err < PAGE_CACHE_SIZE) {
+	} else {
+		if (err < PAGE_CACHE_SIZE) {
 		/* zero fill remainder of page */
-		zero_user_segment(page, err, PAGE_CACHE_SIZE);
+			zero_user_segment(page, err, PAGE_CACHE_SIZE);
+		} else {
+			flush_dcache_page(page);
+		}
 	}
 	SetPageUptodate(page);
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 9a8e396aed89..278fd2891288 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -978,7 +978,6 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 	struct ceph_mds_reply_inode *ininfo;
 	struct ceph_vino vino;
 	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
-	int i = 0;
 	int err = 0;
 
 	dout("fill_trace %p is_dentry %d is_target %d\n", req,
@@ -1039,6 +1038,29 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 		}
 	}
 
+	if (rinfo->head->is_target) {
+		vino.ino = le64_to_cpu(rinfo->targeti.in->ino);
+		vino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
+
+		in = ceph_get_inode(sb, vino);
+		if (IS_ERR(in)) {
+			err = PTR_ERR(in);
+			goto done;
+		}
+		req->r_target_inode = in;
+
+		err = fill_inode(in, &rinfo->targeti, NULL,
+				session, req->r_request_started,
+				(le32_to_cpu(rinfo->head->result) == 0) ?
+				req->r_fmode : -1,
+				&req->r_caps_reservation);
+		if (err < 0) {
+			pr_err("fill_inode badness %p %llx.%llx\n",
+				in, ceph_vinop(in));
+			goto done;
+		}
+	}
+
 	/*
 	 * ignore null lease/binding on snapdir ENOENT, or else we
 	 * will have trouble splicing in the virtual snapdir later
@@ -1108,7 +1130,6 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 			     ceph_dentry(req->r_old_dentry)->offset);
 
 			dn = req->r_old_dentry;  /* use old_dentry */
-			in = dn->d_inode;
 		}
 
 		/* null dentry? */
@@ -1130,44 +1151,28 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 		}
 
 		/* attach proper inode */
-		ininfo = rinfo->targeti.in;
-		vino.ino = le64_to_cpu(ininfo->ino);
-		vino.snap = le64_to_cpu(ininfo->snapid);
-		in = dn->d_inode;
-		if (!in) {
-			in = ceph_get_inode(sb, vino);
-			if (IS_ERR(in)) {
-				pr_err("fill_trace bad get_inode "
-				       "%llx.%llx\n", vino.ino, vino.snap);
-				err = PTR_ERR(in);
-				d_drop(dn);
-				goto done;
-			}
+		if (!dn->d_inode) {
+			ihold(in);
 			dn = splice_dentry(dn, in, &have_lease, true);
 			if (IS_ERR(dn)) {
 				err = PTR_ERR(dn);
 				goto done;
 			}
 			req->r_dentry = dn;  /* may have spliced */
-			ihold(in);
-		} else if (ceph_ino(in) == vino.ino &&
-			   ceph_snap(in) == vino.snap) {
-			ihold(in);
-		} else {
+		} else if (dn->d_inode && dn->d_inode != in) {
 			dout(" %p links to %p %llx.%llx, not %llx.%llx\n",
-			     dn, in, ceph_ino(in), ceph_snap(in),
-			     vino.ino, vino.snap);
+			     dn, dn->d_inode, ceph_vinop(dn->d_inode),
+			     ceph_vinop(in));
 			have_lease = false;
-			in = NULL;
 		}
 
 		if (have_lease)
 			update_dentry_lease(dn, rinfo->dlease, session,
 					    req->r_request_started);
 		dout(" final dn %p\n", dn);
-		i++;
-	} else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
-		   req->r_op == CEPH_MDS_OP_MKSNAP) && !req->r_aborted) {
+	} else if (!req->r_aborted &&
+		   (req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
+		    req->r_op == CEPH_MDS_OP_MKSNAP)) {
 		struct dentry *dn = req->r_dentry;
 
 		/* fill out a snapdir LOOKUPSNAP dentry */
@@ -1177,52 +1182,15 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 		ininfo = rinfo->targeti.in;
 		vino.ino = le64_to_cpu(ininfo->ino);
 		vino.snap = le64_to_cpu(ininfo->snapid);
-		in = ceph_get_inode(sb, vino);
-		if (IS_ERR(in)) {
-			pr_err("fill_inode get_inode badness %llx.%llx\n",
-			       vino.ino, vino.snap);
-			err = PTR_ERR(in);
-			d_delete(dn);
-			goto done;
-		}
 		dout(" linking snapped dir %p to dn %p\n", in, dn);
+		ihold(in);
 		dn = splice_dentry(dn, in, NULL, true);
 		if (IS_ERR(dn)) {
 			err = PTR_ERR(dn);
 			goto done;
 		}
 		req->r_dentry = dn;  /* may have spliced */
-		ihold(in);
-		rinfo->head->is_dentry = 1;  /* fool notrace handlers */
-	}
-
-	if (rinfo->head->is_target) {
-		vino.ino = le64_to_cpu(rinfo->targeti.in->ino);
-		vino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
-
-		if (in == NULL || ceph_ino(in) != vino.ino ||
-		    ceph_snap(in) != vino.snap) {
-			in = ceph_get_inode(sb, vino);
-			if (IS_ERR(in)) {
-				err = PTR_ERR(in);
-				goto done;
-			}
-		}
-		req->r_target_inode = in;
-
-		err = fill_inode(in,
-				 &rinfo->targeti, NULL,
-				 session, req->r_request_started,
-				 (le32_to_cpu(rinfo->head->result) == 0) ?
-				 req->r_fmode : -1,
-				 &req->r_caps_reservation);
-		if (err < 0) {
-			pr_err("fill_inode badness %p %llx.%llx\n",
-			       in, ceph_vinop(in));
-			goto done;
-		}
 	}
-
 done:
 	dout("fill_trace done err=%d\n", err);
 	return err;
@@ -1272,7 +1240,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 	struct qstr dname;
 	struct dentry *dn;
 	struct inode *in;
-	int err = 0, i;
+	int err = 0, ret, i;
 	struct inode *snapdir = NULL;
 	struct ceph_mds_request_head *rhead = req->r_request->front.iov_base;
 	struct ceph_dentry_info *di;
@@ -1305,6 +1273,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 			ceph_fill_dirfrag(parent->d_inode, rinfo->dir_dir);
 	}
 
+	/* FIXME: release caps/leases if error occurs */
 	for (i = 0; i < rinfo->dir_nr; i++) {
 		struct ceph_vino vino;
 
@@ -1329,9 +1298,10 @@ retry_lookup:
 				err = -ENOMEM;
 				goto out;
 			}
-			err = ceph_init_dentry(dn);
-			if (err < 0) {
+			ret = ceph_init_dentry(dn);
+			if (ret < 0) {
 				dput(dn);
+				err = ret;
 				goto out;
 			}
 		} else if (dn->d_inode &&
@@ -1351,9 +1321,6 @@ retry_lookup:
 			spin_unlock(&parent->d_lock);
 		}
 
-		di = dn->d_fsdata;
-		di->offset = ceph_make_fpos(frag, i + r_readdir_offset);
-
 		/* inode */
 		if (dn->d_inode) {
 			in = dn->d_inode;
@@ -1366,26 +1333,39 @@ retry_lookup:
 				err = PTR_ERR(in);
 				goto out;
 			}
-			dn = splice_dentry(dn, in, NULL, false);
-			if (IS_ERR(dn))
-				dn = NULL;
 		}
 
 		if (fill_inode(in, &rinfo->dir_in[i], NULL, session,
 			       req->r_request_started, -1,
 			       &req->r_caps_reservation) < 0) {
 			pr_err("fill_inode badness on %p\n", in);
+			if (!dn->d_inode)
+				iput(in);
+			d_drop(dn);
 			goto next_item;
 		}
-		if (dn)
-			update_dentry_lease(dn, rinfo->dir_dlease[i],
-					    req->r_session,
-					    req->r_request_started);
+
+		if (!dn->d_inode) {
+			dn = splice_dentry(dn, in, NULL, false);
+			if (IS_ERR(dn)) {
+				err = PTR_ERR(dn);
+				dn = NULL;
+				goto next_item;
+			}
+		}
+
+		di = dn->d_fsdata;
+		di->offset = ceph_make_fpos(frag, i + r_readdir_offset);
+
+		update_dentry_lease(dn, rinfo->dir_dlease[i],
+				    req->r_session,
+				    req->r_request_started);
 next_item:
 		if (dn)
 			dput(dn);
 	}
-	req->r_did_prepopulate = true;
+	if (err == 0)
+		req->r_did_prepopulate = true;
 
 out:
 	if (snapdir) {
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index aa3397620342..2c29db6a247e 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -477,9 +477,10 @@ extern int CIFSGetExtAttr(const unsigned int xid, struct cifs_tcon *tcon,
 			const int netfid, __u64 *pExtAttrBits, __u64 *pMask);
 extern void cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb);
 extern bool CIFSCouldBeMFSymlink(const struct cifs_fattr *fattr);
-extern int CIFSCheckMFSymlink(struct cifs_fattr *fattr,
-		const unsigned char *path,
-		struct cifs_sb_info *cifs_sb, unsigned int xid);
+extern int CIFSCheckMFSymlink(unsigned int xid, struct cifs_tcon *tcon,
+			      struct cifs_sb_info *cifs_sb,
+			      struct cifs_fattr *fattr,
+			      const unsigned char *path);
 extern int mdfour(unsigned char *, unsigned char *, int);
 extern int E_md4hash(const unsigned char *passwd, unsigned char *p16,
 			const struct nls_table *codepage);
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 124aa0230c1b..d707edb6b852 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -4010,7 +4010,7 @@ QFileInfoRetry:
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cifs_dbg(FYI, "Send error in QPathInfo = %d\n", rc);
+		cifs_dbg(FYI, "Send error in QFileInfo = %d", rc);
 	} else {		/* decode response */
 		rc = validate_t2((struct smb_t2_rsp *)pSMBr);
 
@@ -4179,7 +4179,7 @@ UnixQFileInfoRetry:
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cifs_dbg(FYI, "Send error in QPathInfo = %d\n", rc);
+		cifs_dbg(FYI, "Send error in UnixQFileInfo = %d", rc);
 	} else {		/* decode response */
 		rc = validate_t2((struct smb_t2_rsp *)pSMBr);
 
@@ -4263,7 +4263,7 @@ UnixQPathInfoRetry:
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cifs_dbg(FYI, "Send error in QPathInfo = %d\n", rc);
+		cifs_dbg(FYI, "Send error in UnixQPathInfo = %d", rc);
 	} else {		/* decode response */
 		rc = validate_t2((struct smb_t2_rsp *)pSMBr);
 
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 11ff5f116b20..a514e0a65f69 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -193,7 +193,7 @@ check_name(struct dentry *direntry)
 static int
 cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid,
 	       struct tcon_link *tlink, unsigned oflags, umode_t mode,
-	       __u32 *oplock, struct cifs_fid *fid, int *created)
+	       __u32 *oplock, struct cifs_fid *fid)
 {
 	int rc = -ENOENT;
 	int create_options = CREATE_NOT_DIR;
@@ -349,7 +349,6 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid,
 				.device	= 0,
 		};
 
-		*created |= FILE_CREATED;
 		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
 			args.uid = current_fsuid();
 			if (inode->i_mode & S_ISGID)
@@ -480,13 +479,16 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
 	cifs_add_pending_open(&fid, tlink, &open);
 
 	rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode,
-			    &oplock, &fid, opened);
+			    &oplock, &fid);
 
 	if (rc) {
 		cifs_del_pending_open(&open);
 		goto out;
 	}
 
+	if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
+		*opened |= FILE_CREATED;
+
 	rc = finish_open(file, direntry, generic_file_open, opened);
 	if (rc) {
 		if (server->ops->close)
@@ -529,7 +531,6 @@ int cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode,
 	struct TCP_Server_Info *server;
 	struct cifs_fid fid;
 	__u32 oplock;
-	int created = FILE_CREATED;
 
 	cifs_dbg(FYI, "cifs_create parent inode = 0x%p name is: %s and dentry = 0x%p\n",
 		 inode, direntry->d_name.name, direntry);
@@ -546,7 +547,7 @@ int cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode,
 		server->ops->new_lease_key(&fid);
 
 	rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode,
-			    &oplock, &fid, &created);
+			    &oplock, &fid);
 	if (!rc && server->ops->close)
 		server->ops->close(xid, tcon, &fid);
 
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 36f9ebb93ceb..49719b8228e5 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -383,7 +383,8 @@ int cifs_get_inode_info_unix(struct inode **pinode,
 
 	/* check for Minshall+French symlinks */
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) {
-		int tmprc = CIFSCheckMFSymlink(&fattr, full_path, cifs_sb, xid);
+		int tmprc = CIFSCheckMFSymlink(xid, tcon, cifs_sb, &fattr,
+					       full_path);
 		if (tmprc)
 			cifs_dbg(FYI, "CIFSCheckMFSymlink: %d\n", tmprc);
 	}
@@ -799,7 +800,8 @@ cifs_get_inode_info(struct inode **inode, const char *full_path,
 
 	/* check for Minshall+French symlinks */
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) {
-		tmprc = CIFSCheckMFSymlink(&fattr, full_path, cifs_sb, xid);
+		tmprc = CIFSCheckMFSymlink(xid, tcon, cifs_sb, &fattr,
+					   full_path);
 		if (tmprc)
 			cifs_dbg(FYI, "CIFSCheckMFSymlink: %d\n", tmprc);
 	}
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index cc0234710ddb..92aee08483a5 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -354,34 +354,30 @@ open_query_close_cifs_symlink(const unsigned char *path, char *pbuf,
 
 
 int
-CIFSCheckMFSymlink(struct cifs_fattr *fattr,
-		   const unsigned char *path,
-		   struct cifs_sb_info *cifs_sb, unsigned int xid)
+CIFSCheckMFSymlink(unsigned int xid, struct cifs_tcon *tcon,
+		   struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr,
+		   const unsigned char *path)
 {
-	int rc = 0;
+	int rc;
 	u8 *buf = NULL;
 	unsigned int link_len = 0;
 	unsigned int bytes_read = 0;
-	struct cifs_tcon *ptcon;
 
 	if (!CIFSCouldBeMFSymlink(fattr))
 		/* it's not a symlink */
 		return 0;
 
 	buf = kmalloc(CIFS_MF_SYMLINK_FILE_SIZE, GFP_KERNEL);
-	if (!buf) {
-		rc = -ENOMEM;
-		goto out;
-	}
+	if (!buf)
+		return -ENOMEM;
 
-	ptcon = tlink_tcon(cifs_sb_tlink(cifs_sb));
-	if ((ptcon->ses) && (ptcon->ses->server->ops->query_mf_symlink))
-		rc = ptcon->ses->server->ops->query_mf_symlink(path, buf,
-						 &bytes_read, cifs_sb, xid);
+	if (tcon->ses->server->ops->query_mf_symlink)
+		rc = tcon->ses->server->ops->query_mf_symlink(path, buf,
+						&bytes_read, cifs_sb, xid);
 	else
-		goto out;
+		rc = -ENOSYS;
 
-	if (rc != 0)
+	if (rc)
 		goto out;
 
 	if (bytes_read == 0) /* not a symlink */
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 8b5e2584c840..af903128891c 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1907,10 +1907,6 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 			}
 		}
 	}
-	if (op == EPOLL_CTL_DEL && is_file_epoll(tf.file)) {
-		tep = tf.file->private_data;
-		mutex_lock_nested(&tep->mtx, 1);
-	}
 
 	/*
 	 * Try to lookup the file inside our RB tree, Since we grabbed "mtx"
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 288534920fe5..20d6697bd638 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1493,6 +1493,7 @@ static ssize_t ext2_quota_write(struct super_block *sb, int type,
 				sb->s_blocksize - offset : towrite;
 
 		tmp_bh.b_state = 0;
+		tmp_bh.b_size = sb->s_blocksize;
 		err = ext2_get_block(inode, blk, &tmp_bh, 1);
 		if (err < 0)
 			goto out;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index e6185031c1cc..ece55565b9cd 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -268,6 +268,16 @@ struct ext4_io_submit {
 /* Translate # of blks to # of clusters */
 #define EXT4_NUM_B2C(sbi, blks)	(((blks) + (sbi)->s_cluster_ratio - 1) >> \
 				 (sbi)->s_cluster_bits)
+/* Mask out the low bits to get the starting block of the cluster */
+#define EXT4_PBLK_CMASK(s, pblk) ((pblk) &				\
+				  ~((ext4_fsblk_t) (s)->s_cluster_ratio - 1))
+#define EXT4_LBLK_CMASK(s, lblk) ((lblk) &				\
+				  ~((ext4_lblk_t) (s)->s_cluster_ratio - 1))
+/* Get the cluster offset */
+#define EXT4_PBLK_COFF(s, pblk) ((pblk) &				\
+				 ((ext4_fsblk_t) (s)->s_cluster_ratio - 1))
+#define EXT4_LBLK_COFF(s, lblk) ((lblk) &				\
+				 ((ext4_lblk_t) (s)->s_cluster_ratio - 1))
 
 /*
  * Structure of a blocks group descriptor
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 17ac112ab101..3fe29de832c8 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -259,6 +259,15 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
 		if (WARN_ON_ONCE(err)) {
 			ext4_journal_abort_handle(where, line, __func__, bh,
 						  handle, err);
+			ext4_error_inode(inode, where, line,
+					 bh->b_blocknr,
+					 "journal_dirty_metadata failed: "
+					 "handle type %u started at line %u, "
+					 "credits %u/%u, errcode %d",
+					 handle->h_type,
+					 handle->h_line_no,
+					 handle->h_requested_credits,
+					 handle->h_buffer_credits, err);
 		}
 	} else {
 		if (inode)
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 35f65cf4f318..3384dc4bed40 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -360,8 +360,10 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
 {
 	ext4_fsblk_t block = ext4_ext_pblock(ext);
 	int len = ext4_ext_get_actual_len(ext);
+	ext4_lblk_t lblock = le32_to_cpu(ext->ee_block);
+	ext4_lblk_t last = lblock + len - 1;
 
-	if (len == 0)
+	if (lblock > last)
 		return 0;
 	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
 }
@@ -387,11 +389,26 @@ static int ext4_valid_extent_entries(struct inode *inode,
 	if (depth == 0) {
 		/* leaf entries */
 		struct ext4_extent *ext = EXT_FIRST_EXTENT(eh);
+		struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
+		ext4_fsblk_t pblock = 0;
+		ext4_lblk_t lblock = 0;
+		ext4_lblk_t prev = 0;
+		int len = 0;
 		while (entries) {
 			if (!ext4_valid_extent(inode, ext))
 				return 0;
+
+			/* Check for overlapping extents */
+			lblock = le32_to_cpu(ext->ee_block);
+			len = ext4_ext_get_actual_len(ext);
+			if ((lblock <= prev) && prev) {
+				pblock = ext4_ext_pblock(ext);
+				es->s_last_error_block = cpu_to_le64(pblock);
+				return 0;
+			}
 			ext++;
 			entries--;
+			prev = lblock + len - 1;
 		}
 	} else {
 		struct ext4_extent_idx *ext_idx = EXT_FIRST_INDEX(eh);
@@ -1834,8 +1851,7 @@ static unsigned int ext4_ext_check_overlap(struct ext4_sb_info *sbi,
 	depth = ext_depth(inode);
 	if (!path[depth].p_ext)
 		goto out;
-	b2 = le32_to_cpu(path[depth].p_ext->ee_block);
-	b2 &= ~(sbi->s_cluster_ratio - 1);
+	b2 = EXT4_LBLK_CMASK(sbi, le32_to_cpu(path[depth].p_ext->ee_block));
 
 	/*
 	 * get the next allocated block if the extent in the path
@@ -1845,7 +1861,7 @@ static unsigned int ext4_ext_check_overlap(struct ext4_sb_info *sbi,
 		b2 = ext4_ext_next_allocated_block(path);
 		if (b2 == EXT_MAX_BLOCKS)
 			goto out;
-		b2 &= ~(sbi->s_cluster_ratio - 1);
+		b2 = EXT4_LBLK_CMASK(sbi, b2);
 	}
 
 	/* check for wrap through zero on extent logical start block*/
@@ -2504,7 +2520,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
 		 * extent, we have to mark the cluster as used (store negative
 		 * cluster number in partial_cluster).
 		 */
-		unaligned = pblk & (sbi->s_cluster_ratio - 1);
+		unaligned = EXT4_PBLK_COFF(sbi, pblk);
 		if (unaligned && (ee_len == num) &&
 		    (*partial_cluster != -((long long)EXT4_B2C(sbi, pblk))))
 			*partial_cluster = EXT4_B2C(sbi, pblk);
@@ -2598,7 +2614,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 			 * accidentally freeing it later on
 			 */
 			pblk = ext4_ext_pblock(ex);
-			if (pblk & (sbi->s_cluster_ratio - 1))
+			if (EXT4_PBLK_COFF(sbi, pblk))
 				*partial_cluster =
 					-((long long)EXT4_B2C(sbi, pblk));
 			ex--;
@@ -3753,7 +3769,7 @@ int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	ext4_lblk_t lblk_start, lblk_end;
-	lblk_start = lblk & (~(sbi->s_cluster_ratio - 1));
+	lblk_start = EXT4_LBLK_CMASK(sbi, lblk);
 	lblk_end = lblk_start + sbi->s_cluster_ratio - 1;
 
 	return ext4_find_delalloc_range(inode, lblk_start, lblk_end);
@@ -3812,9 +3828,9 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start,
 	trace_ext4_get_reserved_cluster_alloc(inode, lblk_start, num_blks);
 
 	/* Check towards left side */
-	c_offset = lblk_start & (sbi->s_cluster_ratio - 1);
+	c_offset = EXT4_LBLK_COFF(sbi, lblk_start);
 	if (c_offset) {
-		lblk_from = lblk_start & (~(sbi->s_cluster_ratio - 1));
+		lblk_from = EXT4_LBLK_CMASK(sbi, lblk_start);
 		lblk_to = lblk_from + c_offset - 1;
 
 		if (ext4_find_delalloc_range(inode, lblk_from, lblk_to))
@@ -3822,7 +3838,7 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start,
 	}
 
 	/* Now check towards right. */
-	c_offset = (lblk_start + num_blks) & (sbi->s_cluster_ratio - 1);
+	c_offset = EXT4_LBLK_COFF(sbi, lblk_start + num_blks);
 	if (allocated_clusters && c_offset) {
 		lblk_from = lblk_start + num_blks;
 		lblk_to = lblk_from + (sbi->s_cluster_ratio - c_offset) - 1;
@@ -4030,7 +4046,7 @@ static int get_implied_cluster_alloc(struct super_block *sb,
 				     struct ext4_ext_path *path)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	ext4_lblk_t c_offset = map->m_lblk & (sbi->s_cluster_ratio-1);
+	ext4_lblk_t c_offset = EXT4_LBLK_COFF(sbi, map->m_lblk);
 	ext4_lblk_t ex_cluster_start, ex_cluster_end;
 	ext4_lblk_t rr_cluster_start;
 	ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block);
@@ -4048,8 +4064,7 @@ static int get_implied_cluster_alloc(struct super_block *sb,
 	    (rr_cluster_start == ex_cluster_start)) {
 		if (rr_cluster_start == ex_cluster_end)
 			ee_start += ee_len - 1;
-		map->m_pblk = (ee_start & ~(sbi->s_cluster_ratio - 1)) +
-			c_offset;
+		map->m_pblk = EXT4_PBLK_CMASK(sbi, ee_start) + c_offset;
 		map->m_len = min(map->m_len,
 				 (unsigned) sbi->s_cluster_ratio - c_offset);
 		/*
@@ -4203,7 +4218,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	 */
 	map->m_flags &= ~EXT4_MAP_FROM_CLUSTER;
 	newex.ee_block = cpu_to_le32(map->m_lblk);
-	cluster_offset = map->m_lblk & (sbi->s_cluster_ratio-1);
+	cluster_offset = EXT4_LBLK_COFF(sbi, map->m_lblk);
 
 	/*
 	 * If we are doing bigalloc, check to see if the extent returned
@@ -4271,7 +4286,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	 * needed so that future calls to get_implied_cluster_alloc()
 	 * work correctly.
 	 */
-	offset = map->m_lblk & (sbi->s_cluster_ratio - 1);
+	offset = EXT4_LBLK_COFF(sbi, map->m_lblk);
 	ar.len = EXT4_NUM_B2C(sbi, offset+allocated);
 	ar.goal -= offset;
 	ar.logical -= offset;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 075763474118..61d49ff22c81 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1206,7 +1206,6 @@ static int ext4_journalled_write_end(struct file *file,
  */
 static int ext4_da_reserve_metadata(struct inode *inode, ext4_lblk_t lblock)
 {
-	int retries = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	unsigned int md_needed;
@@ -1218,7 +1217,6 @@ static int ext4_da_reserve_metadata(struct inode *inode, ext4_lblk_t lblock)
 	 * in order to allocate nrblocks
 	 * worse case is one extent per block
 	 */
-repeat:
 	spin_lock(&ei->i_block_reservation_lock);
 	/*
 	 * ext4_calc_metadata_amount() has side effects, which we have
@@ -1238,10 +1236,6 @@ repeat:
 		ei->i_da_metadata_calc_len = save_len;
 		ei->i_da_metadata_calc_last_lblock = save_last_lblock;
 		spin_unlock(&ei->i_block_reservation_lock);
-		if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
-			cond_resched();
-			goto repeat;
-		}
 		return -ENOSPC;
 	}
 	ei->i_reserved_meta_blocks += md_needed;
@@ -1255,7 +1249,6 @@ repeat:
  */
 static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
 {
-	int retries = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	unsigned int md_needed;
@@ -1277,7 +1270,6 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
 	 * in order to allocate nrblocks
 	 * worse case is one extent per block
 	 */
-repeat:
 	spin_lock(&ei->i_block_reservation_lock);
 	/*
 	 * ext4_calc_metadata_amount() has side effects, which we have
@@ -1297,10 +1289,6 @@ repeat:
 		ei->i_da_metadata_calc_len = save_len;
 		ei->i_da_metadata_calc_last_lblock = save_last_lblock;
 		spin_unlock(&ei->i_block_reservation_lock);
-		if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
-			cond_resched();
-			goto repeat;
-		}
 		dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
 		return -ENOSPC;
 	}
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 4d113efa024c..04a5c7504be9 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3442,6 +3442,9 @@ static void ext4_mb_pa_callback(struct rcu_head *head)
 {
 	struct ext4_prealloc_space *pa;
 	pa = container_of(head, struct ext4_prealloc_space, u.pa_rcu);
+
+	BUG_ON(atomic_read(&pa->pa_count));
+	BUG_ON(pa->pa_deleted == 0);
 	kmem_cache_free(ext4_pspace_cachep, pa);
 }
 
@@ -3455,11 +3458,13 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac,
 	ext4_group_t grp;
 	ext4_fsblk_t grp_blk;
 
-	if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0)
-		return;
-
 	/* in this short window concurrent discard can set pa_deleted */
 	spin_lock(&pa->pa_lock);
+	if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0) {
+		spin_unlock(&pa->pa_lock);
+		return;
+	}
+
 	if (pa->pa_deleted == 1) {
 		spin_unlock(&pa->pa_lock);
 		return;
@@ -4121,7 +4126,7 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac,
 	ext4_get_group_no_and_offset(sb, goal, &group, &block);
 
 	/* set up allocation goals */
-	ac->ac_b_ex.fe_logical = ar->logical & ~(sbi->s_cluster_ratio - 1);
+	ac->ac_b_ex.fe_logical = EXT4_LBLK_CMASK(sbi, ar->logical);
 	ac->ac_status = AC_STATUS_CONTINUE;
 	ac->ac_sb = sb;
 	ac->ac_inode = ar->inode;
@@ -4663,7 +4668,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 	 * blocks at the beginning or the end unless we are explicitly
 	 * requested to avoid doing so.
 	 */
-	overflow = block & (sbi->s_cluster_ratio - 1);
+	overflow = EXT4_PBLK_COFF(sbi, block);
 	if (overflow) {
 		if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) {
 			overflow = sbi->s_cluster_ratio - overflow;
@@ -4677,7 +4682,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 			count += overflow;
 		}
 	}
-	overflow = count & (sbi->s_cluster_ratio - 1);
+	overflow = EXT4_LBLK_COFF(sbi, count);
 	if (overflow) {
 		if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) {
 			if (count > overflow)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index c977f4e4e63b..1f7784de05b6 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -792,7 +792,7 @@ static void ext4_put_super(struct super_block *sb)
 	}
 
 	ext4_es_unregister_shrinker(sbi);
-	del_timer(&sbi->s_err_report);
+	del_timer_sync(&sbi->s_err_report);
 	ext4_release_system_zone(sb);
 	ext4_mb_release(sb);
 	ext4_ext_release(sb);
@@ -3316,11 +3316,19 @@ int ext4_calculate_overhead(struct super_block *sb)
 }
 
 
-static ext4_fsblk_t ext4_calculate_resv_clusters(struct ext4_sb_info *sbi)
+static ext4_fsblk_t ext4_calculate_resv_clusters(struct super_block *sb)
 {
 	ext4_fsblk_t resv_clusters;
 
 	/*
+	 * There's no need to reserve anything when we aren't using extents.
+	 * The space estimates are exact, there are no unwritten extents,
+	 * hole punching doesn't need new metadata... This is needed especially
+	 * to keep ext2/3 backward compatibility.
+	 */
+	if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS))
+		return 0;
+	/*
 	 * By default we reserve 2% or 4096 clusters, whichever is smaller.
 	 * This should cover the situations where we can not afford to run
 	 * out of space like for example punch hole, or converting
@@ -3328,7 +3336,8 @@ static ext4_fsblk_t ext4_calculate_resv_clusters(struct ext4_sb_info *sbi)
 	 * allocation would require 1, or 2 blocks, higher numbers are
 	 * very rare.
 	 */
-	resv_clusters = ext4_blocks_count(sbi->s_es) >> sbi->s_cluster_bits;
+	resv_clusters = ext4_blocks_count(EXT4_SB(sb)->s_es) >>
+			EXT4_SB(sb)->s_cluster_bits;
 
 	do_div(resv_clusters, 50);
 	resv_clusters = min_t(ext4_fsblk_t, resv_clusters, 4096);
@@ -4071,10 +4080,10 @@ no_journal:
 			 "available");
 	}
 
-	err = ext4_reserve_clusters(sbi, ext4_calculate_resv_clusters(sbi));
+	err = ext4_reserve_clusters(sbi, ext4_calculate_resv_clusters(sb));
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "failed to reserve %llu clusters for "
-			 "reserved pool", ext4_calculate_resv_clusters(sbi));
+			 "reserved pool", ext4_calculate_resv_clusters(sb));
 		goto failed_mount4a;
 	}
 
@@ -4184,7 +4193,7 @@ failed_mount_wq:
 	}
 failed_mount3:
 	ext4_es_unregister_shrinker(sbi);
-	del_timer(&sbi->s_err_report);
+	del_timer_sync(&sbi->s_err_report);
 	if (sbi->s_flex_groups)
 		ext4_kvfree(sbi->s_flex_groups);
 	percpu_counter_destroy(&sbi->s_freeclusters_counter);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 1f4a10ece2f1..e0259a163f98 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -516,13 +516,16 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 	}
 	WARN_ON(inode->i_state & I_SYNC);
 	/*
-	 * Skip inode if it is clean. We don't want to mess with writeback
-	 * lists in this function since flusher thread may be doing for example
-	 * sync in parallel and if we move the inode, it could get skipped. So
-	 * here we make sure inode is on some writeback list and leave it there
-	 * unless we have completely cleaned the inode.
+	 * Skip inode if it is clean and we have no outstanding writeback in
+	 * WB_SYNC_ALL mode. We don't want to mess with writeback lists in this
+	 * function since flusher thread may be doing for example sync in
+	 * parallel and if we move the inode, it could get skipped. So here we
+	 * make sure inode is on some writeback list and leave it there unless
+	 * we have completely cleaned the inode.
 	 */
-	if (!(inode->i_state & I_DIRTY))
+	if (!(inode->i_state & I_DIRTY) &&
+	    (wbc->sync_mode != WB_SYNC_ALL ||
+	     !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK)))
 		goto out;
 	inode->i_state |= I_SYNC;
 	spin_unlock(&inode->i_lock);
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index b7fc035a6943..73f3e4ee4037 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -986,6 +986,7 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
+	struct address_space *mapping = inode->i_mapping;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder gh;
 	int rv;
@@ -1006,6 +1007,35 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
 	if (rv != 1)
 		goto out; /* dio not valid, fall back to buffered i/o */
 
+	/*
+	 * Now since we are holding a deferred (CW) lock at this point, you
+	 * might be wondering why this is ever needed. There is a case however
+	 * where we've granted a deferred local lock against a cached exclusive
+	 * glock. That is ok provided all granted local locks are deferred, but
+	 * it also means that it is possible to encounter pages which are
+	 * cached and possibly also mapped. So here we check for that and sort
+	 * them out ahead of the dio. The glock state machine will take care of
+	 * everything else.
+	 *
+	 * If in fact the cached glock state (gl->gl_state) is deferred (CW) in
+	 * the first place, mapping->nr_pages will always be zero.
+	 */
+	if (mapping->nrpages) {
+		loff_t lstart = offset & (PAGE_CACHE_SIZE - 1);
+		loff_t len = iov_length(iov, nr_segs);
+		loff_t end = PAGE_ALIGN(offset + len) - 1;
+
+		rv = 0;
+		if (len == 0)
+			goto out;
+		if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
+			unmap_shared_mapping_range(ip->i_inode.i_mapping, offset, len);
+		rv = filemap_write_and_wait_range(mapping, lstart, end);
+		if (rv)
+			return rv;
+		truncate_inode_pages_range(mapping, lstart, end);
+	}
+
 	rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
 				  offset, nr_segs, gfs2_get_block_direct,
 				  NULL, NULL, 0);
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index c8420f7e4db6..6f7a47c05259 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1655,6 +1655,7 @@ static int dump_holder(struct seq_file *seq, const struct gfs2_holder *gh)
 	struct task_struct *gh_owner = NULL;
 	char flags_buf[32];
 
+	rcu_read_lock();
 	if (gh->gh_owner_pid)
 		gh_owner = pid_task(gh->gh_owner_pid, PIDTYPE_PID);
 	gfs2_print_dbg(seq, " H: s:%s f:%s e:%d p:%ld [%s] %pS\n",
@@ -1664,6 +1665,7 @@ static int dump_holder(struct seq_file *seq, const struct gfs2_holder *gh)
 		       gh->gh_owner_pid ? (long)pid_nr(gh->gh_owner_pid) : -1,
 		       gh_owner ? gh_owner->comm : "(ended)",
 		       (void *)gh->gh_ip);
+	rcu_read_unlock();
 	return 0;
 }
 
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index db908f697139..f88dcd925010 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -192,8 +192,11 @@ static void inode_go_sync(struct gfs2_glock *gl)
 
 	if (ip && !S_ISREG(ip->i_inode.i_mode))
 		ip = NULL;
-	if (ip && test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
-		unmap_shared_mapping_range(ip->i_inode.i_mapping, 0, 0);
+	if (ip) {
+		if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
+			unmap_shared_mapping_range(ip->i_inode.i_mapping, 0, 0);
+		inode_dio_wait(&ip->i_inode);
+	}
 	if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
 		return;
 
@@ -410,6 +413,9 @@ static int inode_go_lock(struct gfs2_holder *gh)
 			return error;
 	}
 
+	if (gh->gh_state != LM_ST_DEFERRED)
+		inode_dio_wait(&ip->i_inode);
+
 	if ((ip->i_diskflags & GFS2_DIF_TRUNC_IN_PROG) &&
 	    (gl->gl_state == LM_ST_EXCLUSIVE) &&
 	    (gh->gh_state == LM_ST_EXCLUSIVE)) {
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 610613fb65b5..9dcb9777a5f8 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -551,10 +551,10 @@ void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
 	struct buffer_head *bh = bd->bd_bh;
 	struct gfs2_glock *gl = bd->bd_gl;
 
-	gfs2_remove_from_ail(bd);
-	bd->bd_bh = NULL;
 	bh->b_private = NULL;
 	bd->bd_blkno = bh->b_blocknr;
+	gfs2_remove_from_ail(bd); /* drops ref on bh */
+	bd->bd_bh = NULL;
 	bd->bd_ops = &gfs2_revoke_lops;
 	sdp->sd_log_num_revoke++;
 	atomic_inc(&gl->gl_revokes);
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 932415050540..52f177be3bf8 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -258,6 +258,7 @@ void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int
 	struct address_space *mapping = bh->b_page->mapping;
 	struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping);
 	struct gfs2_bufdata *bd = bh->b_private;
+	int was_pinned = 0;
 
 	if (test_clear_buffer_pinned(bh)) {
 		trace_gfs2_pin(bd, 0);
@@ -273,12 +274,16 @@ void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int
 			tr->tr_num_databuf_rm++;
 		}
 		tr->tr_touched = 1;
+		was_pinned = 1;
 		brelse(bh);
 	}
 	if (bd) {
 		spin_lock(&sdp->sd_ail_lock);
 		if (bd->bd_tr) {
 			gfs2_trans_add_revoke(sdp, bd);
+		} else if (was_pinned) {
+			bh->b_private = NULL;
+			kmem_cache_free(gfs2_bufdata_cachep, bd);
 		}
 		spin_unlock(&sdp->sd_ail_lock);
 	}
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 82303b474958..52fa88314f5c 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1366,8 +1366,18 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags,
 	if (IS_ERR(s))
 		goto error_bdev;
 
-	if (s->s_root)
+	if (s->s_root) {
+		/*
+		 * s_umount nests inside bd_mutex during
+		 * __invalidate_device().  blkdev_put() acquires
+		 * bd_mutex and can't be called under s_umount.  Drop
+		 * s_umount temporarily.  This is safe as we're
+		 * holding an active reference.
+		 */
+		up_write(&s->s_umount);
 		blkdev_put(bdev, mode);
+		down_write(&s->s_umount);
+	}
 
 	memset(&args, 0, sizeof(args));
 	args.ar_quota = GFS2_QUOTA_DEFAULT;
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 52032647dd4a..5fa344afb49a 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -702,7 +702,7 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
 	read_lock(&journal->j_state_lock);
 #ifdef CONFIG_JBD2_DEBUG
 	if (!tid_geq(journal->j_commit_request, tid)) {
-		printk(KERN_EMERG
+		printk(KERN_ERR
 		       "%s: error: j_commit_request=%d, tid=%d\n",
 		       __func__, journal->j_commit_request, tid);
 	}
@@ -718,10 +718,8 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
 	}
 	read_unlock(&journal->j_state_lock);
 
-	if (unlikely(is_journal_aborted(journal))) {
-		printk(KERN_EMERG "journal commit I/O error\n");
+	if (unlikely(is_journal_aborted(journal)))
 		err = -EIO;
-	}
 	return err;
 }
 
@@ -1527,13 +1525,13 @@ static int journal_get_superblock(journal_t *journal)
 	if (JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM) &&
 	    JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
 		/* Can't have checksum v1 and v2 on at the same time! */
-		printk(KERN_ERR "JBD: Can't enable checksumming v1 and v2 "
+		printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2 "
 		       "at the same time!\n");
 		goto out;
 	}
 
 	if (!jbd2_verify_csum_type(journal, sb)) {
-		printk(KERN_ERR "JBD: Unknown checksum type\n");
+		printk(KERN_ERR "JBD2: Unknown checksum type\n");
 		goto out;
 	}
 
@@ -1541,7 +1539,7 @@ static int journal_get_superblock(journal_t *journal)
 	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
 		journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0);
 		if (IS_ERR(journal->j_chksum_driver)) {
-			printk(KERN_ERR "JBD: Cannot load crc32c driver.\n");
+			printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n");
 			err = PTR_ERR(journal->j_chksum_driver);
 			journal->j_chksum_driver = NULL;
 			goto out;
@@ -1550,7 +1548,7 @@ static int journal_get_superblock(journal_t *journal)
 
 	/* Check superblock checksum */
 	if (!jbd2_superblock_csum_verify(journal, sb)) {
-		printk(KERN_ERR "JBD: journal checksum error\n");
+		printk(KERN_ERR "JBD2: journal checksum error\n");
 		goto out;
 	}
 
@@ -1836,7 +1834,7 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
 			journal->j_chksum_driver = crypto_alloc_shash("crc32c",
 								      0, 0);
 			if (IS_ERR(journal->j_chksum_driver)) {
-				printk(KERN_ERR "JBD: Cannot load crc32c "
+				printk(KERN_ERR "JBD2: Cannot load crc32c "
 				       "driver.\n");
 				journal->j_chksum_driver = NULL;
 				return 0;
@@ -2645,7 +2643,7 @@ static void __exit journal_exit(void)
 #ifdef CONFIG_JBD2_DEBUG
 	int n = atomic_read(&nr_journal_heads);
 	if (n)
-		printk(KERN_EMERG "JBD2: leaked %d journal_heads!\n", n);
+		printk(KERN_ERR "JBD2: leaked %d journal_heads!\n", n);
 #endif
 	jbd2_remove_jbd_stats_proc_entry();
 	jbd2_journal_destroy_caches();
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 3929c50428b1..3b6bb19d60b1 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -594,7 +594,7 @@ static int do_one_pass(journal_t *journal,
 						be32_to_cpu(tmp->h_sequence))) {
 						brelse(obh);
 						success = -EIO;
-						printk(KERN_ERR "JBD: Invalid "
+						printk(KERN_ERR "JBD2: Invalid "
 						       "checksum recovering "
 						       "block %llu in log\n",
 						       blocknr);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 7aa9a32573bb..8360674c85bc 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -932,7 +932,7 @@ repeat:
 					jbd2_alloc(jh2bh(jh)->b_size,
 							 GFP_NOFS);
 				if (!frozen_buffer) {
-					printk(KERN_EMERG
+					printk(KERN_ERR
 					       "%s: OOM for frozen_buffer\n",
 					       __func__);
 					JBUFFER_TRACE(jh, "oom!");
@@ -1166,7 +1166,7 @@ repeat:
 	if (!jh->b_committed_data) {
 		committed_data = jbd2_alloc(jh2bh(jh)->b_size, GFP_NOFS);
 		if (!committed_data) {
-			printk(KERN_EMERG "%s: No memory for committed data\n",
+			printk(KERN_ERR "%s: No memory for committed data\n",
 				__func__);
 			err = -ENOMEM;
 			goto out;
@@ -1290,7 +1290,10 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 		 * once a transaction -bzzz
 		 */
 		jh->b_modified = 1;
-		J_ASSERT_JH(jh, handle->h_buffer_credits > 0);
+		if (handle->h_buffer_credits <= 0) {
+			ret = -ENOSPC;
+			goto out_unlock_bh;
+		}
 		handle->h_buffer_credits--;
 	}
 
@@ -1305,7 +1308,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 		JBUFFER_TRACE(jh, "fastpath");
 		if (unlikely(jh->b_transaction !=
 			     journal->j_running_transaction)) {
-			printk(KERN_EMERG "JBD: %s: "
+			printk(KERN_ERR "JBD2: %s: "
 			       "jh->b_transaction (%llu, %p, %u) != "
 			       "journal->j_running_transaction (%p, %u)",
 			       journal->j_devname,
@@ -1332,7 +1335,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 		JBUFFER_TRACE(jh, "already on other transaction");
 		if (unlikely(jh->b_transaction !=
 			     journal->j_committing_transaction)) {
-			printk(KERN_EMERG "JBD: %s: "
+			printk(KERN_ERR "JBD2: %s: "
 			       "jh->b_transaction (%llu, %p, %u) != "
 			       "journal->j_committing_transaction (%p, %u)",
 			       journal->j_devname,
@@ -1345,7 +1348,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 			ret = -EINVAL;
 		}
 		if (unlikely(jh->b_next_transaction != transaction)) {
-			printk(KERN_EMERG "JBD: %s: "
+			printk(KERN_ERR "JBD2: %s: "
 			       "jh->b_next_transaction (%llu, %p, %u) != "
 			       "transaction (%p, %u)",
 			       journal->j_devname,
@@ -1373,7 +1376,6 @@ out_unlock_bh:
 	jbd2_journal_put_journal_head(jh);
 out:
 	JBUFFER_TRACE(jh, "exit");
-	WARN_ON(ret);	/* All errors are bugs, so dump the stack */
 	return ret;
 }
 
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 9f6b486b6c01..a1a191634abc 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -1440,17 +1440,19 @@ static int nilfs_segctor_collect(struct nilfs_sc_info *sci,
 
 		nilfs_clear_logs(&sci->sc_segbufs);
 
-		err = nilfs_segctor_extend_segments(sci, nilfs, nadd);
-		if (unlikely(err))
-			return err;
-
 		if (sci->sc_stage.flags & NILFS_CF_SUFREED) {
 			err = nilfs_sufile_cancel_freev(nilfs->ns_sufile,
 							sci->sc_freesegs,
 							sci->sc_nfreesegs,
 							NULL);
 			WARN_ON(err); /* do not happen */
+			sci->sc_stage.flags &= ~NILFS_CF_SUFREED;
 		}
+
+		err = nilfs_segctor_extend_segments(sci, nilfs, nadd);
+		if (unlikely(err))
+			return err;
+
 		nadd = min_t(int, nadd << 1, SC_MAX_SEGDELTA);
 		sci->sc_stage = prev_stage;
 	}
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index b8e93a40a5d3..78c3c2097787 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -443,8 +443,11 @@ int pstore_register(struct pstore_info *psi)
 		pstore_get_records(0);
 
 	kmsg_dump_register(&pstore_dumper);
-	pstore_register_console();
-	pstore_register_ftrace();
+
+	if ((psi->flags & PSTORE_FLAGS_FRAGILE) == 0) {
+		pstore_register_console();
+		pstore_register_ftrace();
+	}
 
 	if (pstore_update_ms >= 0) {
 		pstore_timer.expires = jiffies +
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index b94f93685093..35e7d08fe629 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -609,7 +609,7 @@ static int sysfs_open_file(struct inode *inode, struct file *file)
 	struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
 	struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
 	struct sysfs_open_file *of;
-	bool has_read, has_write, has_mmap;
+	bool has_read, has_write;
 	int error = -EACCES;
 
 	/* need attr_sd for attr and ops, its parent for kobj */
@@ -621,7 +621,6 @@ static int sysfs_open_file(struct inode *inode, struct file *file)
 
 		has_read = battr->read || battr->mmap;
 		has_write = battr->write || battr->mmap;
-		has_mmap = battr->mmap;
 	} else {
 		const struct sysfs_ops *ops = sysfs_file_ops(attr_sd);
 
@@ -633,7 +632,6 @@ static int sysfs_open_file(struct inode *inode, struct file *file)
 
 		has_read = ops->show;
 		has_write = ops->store;
-		has_mmap = false;
 	}
 
 	/* check perms and supported operations */
@@ -661,9 +659,9 @@ static int sysfs_open_file(struct inode *inode, struct file *file)
 	 * open file has a separate mutex, it's okay as long as those don't
 	 * happen on the same file.  At this point, we can't easily give
 	 * each file a separate locking class.  Let's differentiate on
-	 * whether the file has mmap or not for now.
+	 * whether the file is bin or not for now.
 	 */
-	if (has_mmap)
+	if (sysfs_is_bin(attr_sd))
 		mutex_init(&of->mutex);
 	else
 		mutex_init(&of->mutex);
diff --git a/fs/xfs/xfs_attr_remote.c b/fs/xfs/xfs_attr_remote.c
index 739e0a52deda..5549d69ddb45 100644
--- a/fs/xfs/xfs_attr_remote.c
+++ b/fs/xfs/xfs_attr_remote.c
@@ -110,7 +110,7 @@ xfs_attr3_rmt_verify(
 	if (be32_to_cpu(rmt->rm_bytes) > fsbsize - sizeof(*rmt))
 		return false;
 	if (be32_to_cpu(rmt->rm_offset) +
-				be32_to_cpu(rmt->rm_bytes) >= XATTR_SIZE_MAX)
+				be32_to_cpu(rmt->rm_bytes) > XATTR_SIZE_MAX)
 		return false;
 	if (rmt->rm_owner == 0)
 		return false;
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 3ef11b22e750..3b2c14b6f0fb 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -1635,7 +1635,7 @@ xfs_bmap_last_extent(
  * blocks at the end of the file which do not start at the previous data block,
  * we will try to align the new blocks at stripe unit boundaries.
  *
- * Returns 0 in bma->aeof if the file (fork) is empty as any new write will be
+ * Returns 1 in bma->aeof if the file (fork) is empty as any new write will be
  * at, or past the EOF.
  */
 STATIC int
@@ -1650,9 +1650,14 @@ xfs_bmap_isaeof(
 	bma->aeof = 0;
 	error = xfs_bmap_last_extent(NULL, bma->ip, whichfork, &rec,
 				     &is_empty);
-	if (error || is_empty)
+	if (error)
 		return error;
 
+	if (is_empty) {
+		bma->aeof = 1;
+		return 0;
+	}
+
 	/*
 	 * Check if we are allocation or past the last extent, or at least into
 	 * the last delayed allocated extent.
@@ -3643,10 +3648,19 @@ xfs_bmap_btalloc(
 	int		isaligned;
 	int		tryagain;
 	int		error;
+	int		stripe_align;
 
 	ASSERT(ap->length);
 
 	mp = ap->ip->i_mount;
+
+	/* stripe alignment for allocation is determined by mount parameters */
+	stripe_align = 0;
+	if (mp->m_swidth && (mp->m_flags & XFS_MOUNT_SWALLOC))
+		stripe_align = mp->m_swidth;
+	else if (mp->m_dalign)
+		stripe_align = mp->m_dalign;
+
 	align = ap->userdata ? xfs_get_extsz_hint(ap->ip) : 0;
 	if (unlikely(align)) {
 		error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev,
@@ -3655,6 +3669,8 @@ xfs_bmap_btalloc(
 		ASSERT(!error);
 		ASSERT(ap->length);
 	}
+
+
 	nullfb = *ap->firstblock == NULLFSBLOCK;
 	fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, *ap->firstblock);
 	if (nullfb) {
@@ -3730,7 +3746,7 @@ xfs_bmap_btalloc(
 	 */
 	if (!ap->flist->xbf_low && ap->aeof) {
 		if (!ap->offset) {
-			args.alignment = mp->m_dalign;
+			args.alignment = stripe_align;
 			atype = args.type;
 			isaligned = 1;
 			/*
@@ -3755,13 +3771,13 @@ xfs_bmap_btalloc(
 			 * of minlen+alignment+slop doesn't go up
 			 * between the calls.
 			 */
-			if (blen > mp->m_dalign && blen <= args.maxlen)
-				nextminlen = blen - mp->m_dalign;
+			if (blen > stripe_align && blen <= args.maxlen)
+				nextminlen = blen - stripe_align;
 			else
 				nextminlen = args.minlen;
-			if (nextminlen + mp->m_dalign > args.minlen + 1)
+			if (nextminlen + stripe_align > args.minlen + 1)
 				args.minalignslop =
-					nextminlen + mp->m_dalign -
+					nextminlen + stripe_align -
 					args.minlen - 1;
 			else
 				args.minalignslop = 0;
@@ -3783,7 +3799,7 @@ xfs_bmap_btalloc(
 		 */
 		args.type = atype;
 		args.fsbno = ap->blkno;
-		args.alignment = mp->m_dalign;
+		args.alignment = stripe_align;
 		args.minlen = nextminlen;
 		args.minalignslop = 0;
 		isaligned = 1;
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 5887e41c0323..82e0dab46ee5 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -287,6 +287,7 @@ xfs_bmapi_allocate(
 	INIT_WORK_ONSTACK(&args->work, xfs_bmapi_allocate_worker);
 	queue_work(xfs_alloc_wq, &args->work);
 	wait_for_completion(&done);
+	destroy_work_on_stack(&args->work);
 	return args->result;
 }
 
@@ -1187,7 +1188,12 @@ xfs_zero_remaining_bytes(
 		XFS_BUF_UNWRITE(bp);
 		XFS_BUF_READ(bp);
 		XFS_BUF_SET_ADDR(bp, xfs_fsb_to_db(ip, imap.br_startblock));
-		xfsbdstrat(mp, bp);
+
+		if (XFS_FORCED_SHUTDOWN(mp)) {
+			error = XFS_ERROR(EIO);
+			break;
+		}
+		xfs_buf_iorequest(bp);
 		error = xfs_buf_iowait(bp);
 		if (error) {
 			xfs_buf_ioerror_alert(bp,
@@ -1200,7 +1206,12 @@ xfs_zero_remaining_bytes(
 		XFS_BUF_UNDONE(bp);
 		XFS_BUF_UNREAD(bp);
 		XFS_BUF_WRITE(bp);
-		xfsbdstrat(mp, bp);
+
+		if (XFS_FORCED_SHUTDOWN(mp)) {
+			error = XFS_ERROR(EIO);
+			break;
+		}
+		xfs_buf_iorequest(bp);
 		error = xfs_buf_iowait(bp);
 		if (error) {
 			xfs_buf_ioerror_alert(bp,
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index c7f0b77dcb00..afe7645e4b2b 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -698,7 +698,11 @@ xfs_buf_read_uncached(
 	bp->b_flags |= XBF_READ;
 	bp->b_ops = ops;
 
-	xfsbdstrat(target->bt_mount, bp);
+	if (XFS_FORCED_SHUTDOWN(target->bt_mount)) {
+		xfs_buf_relse(bp);
+		return NULL;
+	}
+	xfs_buf_iorequest(bp);
 	xfs_buf_iowait(bp);
 	return bp;
 }
@@ -1089,7 +1093,7 @@ xfs_bioerror(
  * This is meant for userdata errors; metadata bufs come with
  * iodone functions attached, so that we can track down errors.
  */
-STATIC int
+int
 xfs_bioerror_relse(
 	struct xfs_buf	*bp)
 {
@@ -1152,7 +1156,7 @@ xfs_bwrite(
 	ASSERT(xfs_buf_islocked(bp));
 
 	bp->b_flags |= XBF_WRITE;
-	bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q);
+	bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q | XBF_WRITE_FAIL);
 
 	xfs_bdstrat_cb(bp);
 
@@ -1164,25 +1168,6 @@ xfs_bwrite(
 	return error;
 }
 
-/*
- * Wrapper around bdstrat so that we can stop data from going to disk in case
- * we are shutting down the filesystem.  Typically user data goes thru this
- * path; one of the exceptions is the superblock.
- */
-void
-xfsbdstrat(
-	struct xfs_mount	*mp,
-	struct xfs_buf		*bp)
-{
-	if (XFS_FORCED_SHUTDOWN(mp)) {
-		trace_xfs_bdstrat_shut(bp, _RET_IP_);
-		xfs_bioerror_relse(bp);
-		return;
-	}
-
-	xfs_buf_iorequest(bp);
-}
-
 STATIC void
 _xfs_buf_ioend(
 	xfs_buf_t		*bp,
@@ -1516,6 +1501,12 @@ xfs_wait_buftarg(
 			struct xfs_buf *bp;
 			bp = list_first_entry(&dispose, struct xfs_buf, b_lru);
 			list_del_init(&bp->b_lru);
+			if (bp->b_flags & XBF_WRITE_FAIL) {
+				xfs_alert(btp->bt_mount,
+"Corruption Alert: Buffer at block 0x%llx had permanent write failures!\n"
+"Please run xfs_repair to determine the extent of the problem.",
+					(long long)bp->b_bn);
+			}
 			xfs_buf_rele(bp);
 		}
 		if (loop++ != 0)
@@ -1799,7 +1790,7 @@ __xfs_buf_delwri_submit(
 
 	blk_start_plug(&plug);
 	list_for_each_entry_safe(bp, n, io_list, b_list) {
-		bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC);
+		bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC | XBF_WRITE_FAIL);
 		bp->b_flags |= XBF_WRITE;
 
 		if (!wait) {
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index e65683361017..1cf21a4a9f22 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -45,6 +45,7 @@ typedef enum {
 #define XBF_ASYNC	 (1 << 4) /* initiator will not wait for completion */
 #define XBF_DONE	 (1 << 5) /* all pages in the buffer uptodate */
 #define XBF_STALE	 (1 << 6) /* buffer has been staled, do not find it */
+#define XBF_WRITE_FAIL	 (1 << 24)/* async writes have failed on this buffer */
 
 /* I/O hints for the BIO layer */
 #define XBF_SYNCIO	 (1 << 10)/* treat this buffer as synchronous I/O */
@@ -70,6 +71,7 @@ typedef unsigned int xfs_buf_flags_t;
 	{ XBF_ASYNC,		"ASYNC" }, \
 	{ XBF_DONE,		"DONE" }, \
 	{ XBF_STALE,		"STALE" }, \
+	{ XBF_WRITE_FAIL,	"WRITE_FAIL" }, \
 	{ XBF_SYNCIO,		"SYNCIO" }, \
 	{ XBF_FUA,		"FUA" }, \
 	{ XBF_FLUSH,		"FLUSH" }, \
@@ -80,6 +82,7 @@ typedef unsigned int xfs_buf_flags_t;
 	{ _XBF_DELWRI_Q,	"DELWRI_Q" }, \
 	{ _XBF_COMPOUND,	"COMPOUND" }
 
+
 /*
  * Internal state flags.
  */
@@ -269,9 +272,6 @@ extern void xfs_buf_unlock(xfs_buf_t *);
 
 /* Buffer Read and Write Routines */
 extern int xfs_bwrite(struct xfs_buf *bp);
-
-extern void xfsbdstrat(struct xfs_mount *, struct xfs_buf *);
-
 extern void xfs_buf_ioend(xfs_buf_t *,	int);
 extern void xfs_buf_ioerror(xfs_buf_t *, int);
 extern void xfs_buf_ioerror_alert(struct xfs_buf *, const char *func);
@@ -282,6 +282,8 @@ extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
 #define xfs_buf_zero(bp, off, len) \
 	    xfs_buf_iomove((bp), (off), (len), NULL, XBRW_ZERO)
 
+extern int xfs_bioerror_relse(struct xfs_buf *);
+
 static inline int xfs_buf_geterror(xfs_buf_t *bp)
 {
 	return bp ? bp->b_error : ENOMEM;
@@ -301,7 +303,8 @@ extern void xfs_buf_terminate(void);
 
 #define XFS_BUF_ZEROFLAGS(bp) \
 	((bp)->b_flags &= ~(XBF_READ|XBF_WRITE|XBF_ASYNC| \
-			    XBF_SYNCIO|XBF_FUA|XBF_FLUSH))
+			    XBF_SYNCIO|XBF_FUA|XBF_FLUSH| \
+			    XBF_WRITE_FAIL))
 
 void xfs_buf_stale(struct xfs_buf *bp);
 #define XFS_BUF_UNSTALE(bp)	((bp)->b_flags &= ~XBF_STALE)
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index a64f67ba25d3..2227b9b050bb 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -496,6 +496,14 @@ xfs_buf_item_unpin(
 	}
 }
 
+/*
+ * Buffer IO error rate limiting. Limit it to no more than 10 messages per 30
+ * seconds so as to not spam logs too much on repeated detection of the same
+ * buffer being bad..
+ */
+
+DEFINE_RATELIMIT_STATE(xfs_buf_write_fail_rl_state, 30 * HZ, 10);
+
 STATIC uint
 xfs_buf_item_push(
 	struct xfs_log_item	*lip,
@@ -524,6 +532,14 @@ xfs_buf_item_push(
 
 	trace_xfs_buf_item_push(bip);
 
+	/* has a previous flush failed due to IO errors? */
+	if ((bp->b_flags & XBF_WRITE_FAIL) &&
+	    ___ratelimit(&xfs_buf_write_fail_rl_state, "XFS:")) {
+		xfs_warn(bp->b_target->bt_mount,
+"Detected failing async write on buffer block 0x%llx. Retrying async write.\n",
+			 (long long)bp->b_bn);
+	}
+
 	if (!xfs_buf_delwri_queue(bp, buffer_list))
 		rval = XFS_ITEM_FLUSHING;
 	xfs_buf_unlock(bp);
@@ -1096,8 +1112,9 @@ xfs_buf_iodone_callbacks(
 
 		xfs_buf_ioerror(bp, 0); /* errno of 0 unsets the flag */
 
-		if (!XFS_BUF_ISSTALE(bp)) {
-			bp->b_flags |= XBF_WRITE | XBF_ASYNC | XBF_DONE;
+		if (!(bp->b_flags & (XBF_STALE|XBF_WRITE_FAIL))) {
+			bp->b_flags |= XBF_WRITE | XBF_ASYNC |
+				       XBF_DONE | XBF_WRITE_FAIL;
 			xfs_buf_iorequest(bp);
 		} else {
 			xfs_buf_relse(bp);
diff --git a/fs/xfs/xfs_dir2_node.c b/fs/xfs/xfs_dir2_node.c
index 56369d4509d5..48c7d18f68c3 100644
--- a/fs/xfs/xfs_dir2_node.c
+++ b/fs/xfs/xfs_dir2_node.c
@@ -2067,12 +2067,12 @@ xfs_dir2_node_lookup(
  */
 int						/* error */
 xfs_dir2_node_removename(
-	xfs_da_args_t		*args)		/* operation arguments */
+	struct xfs_da_args	*args)		/* operation arguments */
 {
-	xfs_da_state_blk_t	*blk;		/* leaf block */
+	struct xfs_da_state_blk	*blk;		/* leaf block */
 	int			error;		/* error return value */
 	int			rval;		/* operation return value */
-	xfs_da_state_t		*state;		/* btree cursor */
+	struct xfs_da_state	*state;		/* btree cursor */
 
 	trace_xfs_dir2_node_removename(args);
 
@@ -2084,19 +2084,18 @@ xfs_dir2_node_removename(
 	state->mp = args->dp->i_mount;
 	state->blocksize = state->mp->m_dirblksize;
 	state->node_ents = state->mp->m_dir_node_ents;
-	/*
-	 * Look up the entry we're deleting, set up the cursor.
-	 */
+
+	/* Look up the entry we're deleting, set up the cursor. */
 	error = xfs_da3_node_lookup_int(state, &rval);
 	if (error)
-		rval = error;
-	/*
-	 * Didn't find it, upper layer screwed up.
-	 */
+		goto out_free;
+
+	/* Didn't find it, upper layer screwed up. */
 	if (rval != EEXIST) {
-		xfs_da_state_free(state);
-		return rval;
+		error = rval;
+		goto out_free;
 	}
+
 	blk = &state->path.blk[state->path.active - 1];
 	ASSERT(blk->magic == XFS_DIR2_LEAFN_MAGIC);
 	ASSERT(state->extravalid);
@@ -2107,7 +2106,7 @@ xfs_dir2_node_removename(
 	error = xfs_dir2_leafn_remove(args, blk->bp, blk->index,
 		&state->extrablk, &rval);
 	if (error)
-		return error;
+		goto out_free;
 	/*
 	 * Fix the hash values up the btree.
 	 */
@@ -2122,6 +2121,7 @@ xfs_dir2_node_removename(
 	 */
 	if (!error)
 		error = xfs_dir2_node_to_leaf(state);
+out_free:
 	xfs_da_state_free(state);
 	return error;
 }
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 27e0e544e963..104455b8046c 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -618,7 +618,8 @@ xfs_setattr_nonsize(
 		}
 		if (!gid_eq(igid, gid)) {
 			if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_GQUOTA_ON(mp)) {
-				ASSERT(!XFS_IS_PQUOTA_ON(mp));
+				ASSERT(xfs_sb_version_has_pquotino(&mp->m_sb) ||
+				       !XFS_IS_PQUOTA_ON(mp));
 				ASSERT(mask & ATTR_GID);
 				ASSERT(gdqp);
 				olddquot2 = xfs_qm_vop_chown(tp, ip,
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index b6b669df40f3..eae16920655b 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -193,7 +193,10 @@ xlog_bread_noalign(
 	bp->b_io_length = nbblks;
 	bp->b_error = 0;
 
-	xfsbdstrat(log->l_mp, bp);
+	if (XFS_FORCED_SHUTDOWN(log->l_mp))
+		return XFS_ERROR(EIO);
+
+	xfs_buf_iorequest(bp);
 	error = xfs_buf_iowait(bp);
 	if (error)
 		xfs_buf_ioerror_alert(bp, __func__);
@@ -4397,7 +4400,13 @@ xlog_do_recover(
 	XFS_BUF_READ(bp);
 	XFS_BUF_UNASYNC(bp);
 	bp->b_ops = &xfs_sb_buf_ops;
-	xfsbdstrat(log->l_mp, bp);
+
+	if (XFS_FORCED_SHUTDOWN(log->l_mp)) {
+		xfs_buf_relse(bp);
+		return XFS_ERROR(EIO);
+	}
+
+	xfs_buf_iorequest(bp);
 	error = xfs_buf_iowait(bp);
 	if (error) {
 		xfs_buf_ioerror_alert(bp, __func__);
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 14a4996cfec6..dd88f0e27bd8 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -134,8 +134,6 @@ xfs_qm_dqpurge(
 {
 	struct xfs_mount	*mp = dqp->q_mount;
 	struct xfs_quotainfo	*qi = mp->m_quotainfo;
-	struct xfs_dquot	*gdqp = NULL;
-	struct xfs_dquot	*pdqp = NULL;
 
 	xfs_dqlock(dqp);
 	if ((dqp->dq_flags & XFS_DQ_FREEING) || dqp->q_nrefs != 0) {
@@ -143,21 +141,6 @@ xfs_qm_dqpurge(
 		return EAGAIN;
 	}
 
-	/*
-	 * If this quota has a hint attached, prepare for releasing it now.
-	 */
-	gdqp = dqp->q_gdquot;
-	if (gdqp) {
-		xfs_dqlock(gdqp);
-		dqp->q_gdquot = NULL;
-	}
-
-	pdqp = dqp->q_pdquot;
-	if (pdqp) {
-		xfs_dqlock(pdqp);
-		dqp->q_pdquot = NULL;
-	}
-
 	dqp->dq_flags |= XFS_DQ_FREEING;
 
 	xfs_dqflock(dqp);
@@ -206,11 +189,47 @@ xfs_qm_dqpurge(
 	XFS_STATS_DEC(xs_qm_dquot_unused);
 
 	xfs_qm_dqdestroy(dqp);
+	return 0;
+}
+
+/*
+ * Release the group or project dquot pointers the user dquots maybe carrying
+ * around as a hint, and proceed to purge the user dquot cache if requested.
+*/
+STATIC int
+xfs_qm_dqpurge_hints(
+	struct xfs_dquot	*dqp,
+	void			*data)
+{
+	struct xfs_dquot	*gdqp = NULL;
+	struct xfs_dquot	*pdqp = NULL;
+	uint			flags = *((uint *)data);
+
+	xfs_dqlock(dqp);
+	if (dqp->dq_flags & XFS_DQ_FREEING) {
+		xfs_dqunlock(dqp);
+		return EAGAIN;
+	}
+
+	/* If this quota has a hint attached, prepare for releasing it now */
+	gdqp = dqp->q_gdquot;
+	if (gdqp)
+		dqp->q_gdquot = NULL;
+
+	pdqp = dqp->q_pdquot;
+	if (pdqp)
+		dqp->q_pdquot = NULL;
+
+	xfs_dqunlock(dqp);
 
 	if (gdqp)
-		xfs_qm_dqput(gdqp);
+		xfs_qm_dqrele(gdqp);
 	if (pdqp)
-		xfs_qm_dqput(pdqp);
+		xfs_qm_dqrele(pdqp);
+
+	if (flags & XFS_QMOPT_UQUOTA)
+		return xfs_qm_dqpurge(dqp, NULL);
+
 	return 0;
 }
 
@@ -222,8 +241,18 @@ xfs_qm_dqpurge_all(
 	struct xfs_mount	*mp,
 	uint			flags)
 {
-	if (flags & XFS_QMOPT_UQUOTA)
-		xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge, NULL);
+	/*
+	 * We have to release group/project dquot hint(s) from the user dquot
+	 * at first if they are there, otherwise we would run into an infinite
+	 * loop while walking through radix tree to purge other type of dquots
+	 * since their refcount is not zero if the user dquot refers to them
+	 * as hint.
+	 *
+	 * Call the special xfs_qm_dqpurge_hints() will end up go through the
+	 * general xfs_qm_dqpurge() against user dquot cache if requested.
+	 */
+	xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge_hints, &flags);
+
 	if (flags & XFS_QMOPT_GQUOTA)
 		xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_dqpurge, NULL);
 	if (flags & XFS_QMOPT_PQUOTA)
@@ -2082,24 +2111,21 @@ xfs_qm_vop_create_dqattach(
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 	ASSERT(XFS_IS_QUOTA_RUNNING(mp));
 
-	if (udqp) {
+	if (udqp && XFS_IS_UQUOTA_ON(mp)) {
 		ASSERT(ip->i_udquot == NULL);
-		ASSERT(XFS_IS_UQUOTA_ON(mp));
 		ASSERT(ip->i_d.di_uid == be32_to_cpu(udqp->q_core.d_id));
 
 		ip->i_udquot = xfs_qm_dqhold(udqp);
 		xfs_trans_mod_dquot(tp, udqp, XFS_TRANS_DQ_ICOUNT, 1);
 	}
-	if (gdqp) {
+	if (gdqp && XFS_IS_GQUOTA_ON(mp)) {
 		ASSERT(ip->i_gdquot == NULL);
-		ASSERT(XFS_IS_GQUOTA_ON(mp));
 		ASSERT(ip->i_d.di_gid == be32_to_cpu(gdqp->q_core.d_id));
 		ip->i_gdquot = xfs_qm_dqhold(gdqp);
 		xfs_trans_mod_dquot(tp, gdqp, XFS_TRANS_DQ_ICOUNT, 1);
 	}
-	if (pdqp) {
+	if (pdqp && XFS_IS_PQUOTA_ON(mp)) {
 		ASSERT(ip->i_pdquot == NULL);
-		ASSERT(XFS_IS_PQUOTA_ON(mp));
 		ASSERT(xfs_get_projid(ip) == be32_to_cpu(pdqp->q_core.d_id));
 
 		ip->i_pdquot = xfs_qm_dqhold(pdqp);
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index c035d11b7734..647b6f1d8923 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -314,7 +314,18 @@ xfs_trans_read_buf_map(
 			ASSERT(bp->b_iodone == NULL);
 			XFS_BUF_READ(bp);
 			bp->b_ops = ops;
-			xfsbdstrat(tp->t_mountp, bp);
+
+			/*
+			 * XXX(hch): clean up the error handling here to be less
+			 * of a mess..
+			 */
+			if (XFS_FORCED_SHUTDOWN(mp)) {
+				trace_xfs_bdstrat_shut(bp, _RET_IP_);
+				xfs_bioerror_relse(bp);
+			} else {
+				xfs_buf_iorequest(bp);
+			}
+
 			error = xfs_buf_iowait(bp);
 			if (error) {
 				xfs_buf_ioerror_alert(bp, __func__);