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

Two minor conflicts in virtio_net driver (bug fix overlapping addition
of a helper) and MAINTAINERS (new driver edit overlapping revamp of
PHY entry).

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

28 files changed, 236 insertions, 106 deletions

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 375f8c728d91..e3b0b4196d3d 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4825,10 +4825,6 @@ skip_async:
 		else
 			flush = BTRFS_RESERVE_NO_FLUSH;
 		spin_lock(&space_info->lock);
-		if (can_overcommit(fs_info, space_info, orig, flush, false)) {
-			spin_unlock(&space_info->lock);
-			break;
-		}
 		if (list_empty(&space_info->tickets) &&
 		    list_empty(&space_info->priority_tickets)) {
 			spin_unlock(&space_info->lock);
@@ -7589,6 +7585,10 @@ search:
 		u64 offset;
 		int cached;
 
+		/* If the block group is read-only, we can skip it entirely. */
+		if (unlikely(block_group->ro))
+			continue;
+
 		btrfs_grab_block_group(block_group, delalloc);
 		search_start = block_group->key.objectid;
 
@@ -7624,8 +7624,6 @@ have_block_group:
 
 		if (unlikely(block_group->cached == BTRFS_CACHE_ERROR))
 			goto loop;
-		if (unlikely(block_group->ro))
-			goto loop;
 
 		/*
 		 * Ok we want to try and use the cluster allocator, so
@@ -7839,6 +7837,7 @@ loop:
 		failed_alloc = false;
 		BUG_ON(index != get_block_group_index(block_group));
 		btrfs_release_block_group(block_group, delalloc);
+		cond_resched();
 	}
 	up_read(&space_info->groups_sem);
 
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index f20ef211a73d..3a11ae63676e 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2153,8 +2153,7 @@ process_leaf:
 			u32 this_len = sizeof(*di) + name_len + data_len;
 			char *name;
 
-			ret = verify_dir_item(fs_info, path->nodes[0],
-					      path->slots[0], di);
+			ret = verify_dir_item(fs_info, path->nodes[0], i, di);
 			if (ret) {
 				ret = -EIO;
 				goto out;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 5eb7217738ed..e8b9a269fdde 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2702,7 +2702,7 @@ int btrfs_grow_device(struct btrfs_trans_handle *trans,
 
 	mutex_lock(&fs_info->chunk_mutex);
 	old_total = btrfs_super_total_bytes(super_copy);
-	diff = new_size - device->total_bytes;
+	diff = round_down(new_size - device->total_bytes, fs_info->sectorsize);
 
 	if (new_size <= device->total_bytes ||
 	    device->is_tgtdev_for_dev_replace) {
@@ -4406,7 +4406,7 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size)
 	u64 diff;
 
 	new_size = round_down(new_size, fs_info->sectorsize);
-	diff = old_size - new_size;
+	diff = round_down(old_size - new_size, fs_info->sectorsize);
 
 	if (device->is_tgtdev_for_dev_replace)
 		return -EINVAL;
diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c
index 7bc186f4ed4d..2e71b6e7e646 100644
--- a/fs/jfs/acl.c
+++ b/fs/jfs/acl.c
@@ -77,13 +77,6 @@ static int __jfs_set_acl(tid_t tid, struct inode *inode, int type,
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		ea_name = XATTR_NAME_POSIX_ACL_ACCESS;
-		if (acl) {
-			rc = posix_acl_update_mode(inode, &inode->i_mode, &acl);
-			if (rc)
-				return rc;
-			inode->i_ctime = current_time(inode);
-			mark_inode_dirty(inode);
-		}
 		break;
 	case ACL_TYPE_DEFAULT:
 		ea_name = XATTR_NAME_POSIX_ACL_DEFAULT;
@@ -115,12 +108,27 @@ int jfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
 	int rc;
 	tid_t tid;
+	int update_mode = 0;
+	umode_t mode = inode->i_mode;
 
 	tid = txBegin(inode->i_sb, 0);
 	mutex_lock(&JFS_IP(inode)->commit_mutex);
+	if (type == ACL_TYPE_ACCESS && acl) {
+		rc = posix_acl_update_mode(inode, &mode, &acl);
+		if (rc)
+			goto end_tx;
+		update_mode = 1;
+	}
 	rc = __jfs_set_acl(tid, inode, type, acl);
-	if (!rc)
+	if (!rc) {
+		if (update_mode) {
+			inode->i_mode = mode;
+			inode->i_ctime = current_time(inode);
+			mark_inode_dirty(inode);
+		}
 		rc = txCommit(tid, 1, &inode, 0);
+	}
+end_tx:
 	txEnd(tid);
 	mutex_unlock(&JFS_IP(inode)->commit_mutex);
 	return rc;
diff --git a/fs/jfs/resize.c b/fs/jfs/resize.c
index bd9b641ada2c..7ddcb445a3d9 100644
--- a/fs/jfs/resize.c
+++ b/fs/jfs/resize.c
@@ -98,7 +98,7 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize)
 		goto out;
 	}
 
-	VolumeSize = sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits;
+	VolumeSize = i_size_read(sb->s_bdev->bd_inode) >> sb->s_blocksize_bits;
 
 	if (VolumeSize) {
 		if (newLVSize > VolumeSize) {
@@ -211,7 +211,7 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize)
 	txQuiesce(sb);
 
 	/* Reset size of direct inode */
-	sbi->direct_inode->i_size =  sb->s_bdev->bd_inode->i_size;
+	sbi->direct_inode->i_size =  i_size_read(sb->s_bdev->bd_inode);
 
 	if (sbi->mntflag & JFS_INLINELOG) {
 		/*
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index e8aad7d87b8c..78b41e1d5c67 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -313,7 +313,7 @@ static int parse_options(char *options, struct super_block *sb, s64 *newLVSize,
 		}
 		case Opt_resize_nosize:
 		{
-			*newLVSize = sb->s_bdev->bd_inode->i_size >>
+			*newLVSize = i_size_read(sb->s_bdev->bd_inode) >>
 				sb->s_blocksize_bits;
 			if (*newLVSize == 0)
 				pr_err("JFS: Cannot determine volume size\n");
@@ -579,7 +579,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
 		goto out_unload;
 	}
 	inode->i_ino = 0;
-	inode->i_size = sb->s_bdev->bd_inode->i_size;
+	inode->i_size = i_size_read(sb->s_bdev->bd_inode);
 	inode->i_mapping->a_ops = &jfs_metapage_aops;
 	hlist_add_fake(&inode->i_hash);
 	mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index ee5ddbd36088..efebe6cf4378 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -820,6 +820,7 @@ void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_server *sour
 	target->caps = source->caps;
 	target->options = source->options;
 	target->auth_info = source->auth_info;
+	target->port = source->port;
 }
 EXPORT_SYMBOL_GPL(nfs_server_copy_userdata);
 
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 5ac484fe0dee..3522b1249019 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2372,16 +2372,40 @@ void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set)
 }
 EXPORT_SYMBOL_GPL(nfs_access_add_cache);
 
+#define NFS_MAY_READ (NFS4_ACCESS_READ)
+#define NFS_MAY_WRITE (NFS4_ACCESS_MODIFY | \
+		NFS4_ACCESS_EXTEND | \
+		NFS4_ACCESS_DELETE)
+#define NFS_FILE_MAY_WRITE (NFS4_ACCESS_MODIFY | \
+		NFS4_ACCESS_EXTEND)
+#define NFS_DIR_MAY_WRITE NFS_MAY_WRITE
+#define NFS_MAY_LOOKUP (NFS4_ACCESS_LOOKUP)
+#define NFS_MAY_EXECUTE (NFS4_ACCESS_EXECUTE)
+static int
+nfs_access_calc_mask(u32 access_result, umode_t umode)
+{
+	int mask = 0;
+
+	if (access_result & NFS_MAY_READ)
+		mask |= MAY_READ;
+	if (S_ISDIR(umode)) {
+		if ((access_result & NFS_DIR_MAY_WRITE) == NFS_DIR_MAY_WRITE)
+			mask |= MAY_WRITE;
+		if ((access_result & NFS_MAY_LOOKUP) == NFS_MAY_LOOKUP)
+			mask |= MAY_EXEC;
+	} else if (S_ISREG(umode)) {
+		if ((access_result & NFS_FILE_MAY_WRITE) == NFS_FILE_MAY_WRITE)
+			mask |= MAY_WRITE;
+		if ((access_result & NFS_MAY_EXECUTE) == NFS_MAY_EXECUTE)
+			mask |= MAY_EXEC;
+	} else if (access_result & NFS_MAY_WRITE)
+			mask |= MAY_WRITE;
+	return mask;
+}
+
 void nfs_access_set_mask(struct nfs_access_entry *entry, u32 access_result)
 {
-	entry->mask = 0;
-	if (access_result & NFS4_ACCESS_READ)
-		entry->mask |= MAY_READ;
-	if (access_result &
-	    (NFS4_ACCESS_MODIFY | NFS4_ACCESS_EXTEND | NFS4_ACCESS_DELETE))
-		entry->mask |= MAY_WRITE;
-	if (access_result & (NFS4_ACCESS_LOOKUP|NFS4_ACCESS_EXECUTE))
-		entry->mask |= MAY_EXEC;
+	entry->mask = access_result;
 }
 EXPORT_SYMBOL_GPL(nfs_access_set_mask);
 
@@ -2389,6 +2413,7 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
 {
 	struct nfs_access_entry cache;
 	bool may_block = (mask & MAY_NOT_BLOCK) == 0;
+	int cache_mask;
 	int status;
 
 	trace_nfs_access_enter(inode);
@@ -2404,7 +2429,8 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
 		goto out;
 
 	/* Be clever: ask server to check for all possible rights */
-	cache.mask = MAY_EXEC | MAY_WRITE | MAY_READ;
+	cache.mask = NFS_MAY_LOOKUP | NFS_MAY_EXECUTE
+		     | NFS_MAY_WRITE | NFS_MAY_READ;
 	cache.cred = cred;
 	cache.jiffies = jiffies;
 	status = NFS_PROTO(inode)->access(inode, &cache);
@@ -2418,7 +2444,8 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
 	}
 	nfs_access_add_cache(inode, &cache);
 out_cached:
-	if ((mask & ~cache.mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) != 0)
+	cache_mask = nfs_access_calc_mask(cache.mask, inode->i_mode);
+	if ((mask & ~cache_mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) != 0)
 		status = -EACCES;
 out:
 	trace_nfs_access_exit(inode, status);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 5713eb32a45e..af330c31f627 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -617,6 +617,8 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 		if (result)
 			goto out;
 	}
+	if (iocb->ki_pos > i_size_read(inode))
+		nfs_revalidate_mapping(inode, file->f_mapping);
 
 	nfs_start_io_write(inode);
 	result = generic_write_checks(iocb, from);
@@ -750,7 +752,7 @@ do_setlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 	 */
 	nfs_sync_mapping(filp->f_mapping);
 	if (!NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
-		nfs_zap_mapping(inode, filp->f_mapping);
+		nfs_zap_caches(inode);
 out:
 	return status;
 }
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 080fc6b278bd..44c638b7876c 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -542,6 +542,10 @@ filelayout_check_deviceid(struct pnfs_layout_hdr *lo,
 	struct nfs4_file_layout_dsaddr *dsaddr;
 	int status = -EINVAL;
 
+	/* Is the deviceid already set? If so, we're good. */
+	if (fl->dsaddr != NULL)
+		return 0;
+
 	/* find and reference the deviceid */
 	d = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode), &fl->deviceid,
 			lo->plh_lc_cred, gfp_flags);
@@ -553,8 +557,6 @@ filelayout_check_deviceid(struct pnfs_layout_hdr *lo,
 	if (filelayout_test_devid_unavailable(&dsaddr->id_node))
 		goto out_put;
 
-	fl->dsaddr = dsaddr;
-
 	if (fl->first_stripe_index >= dsaddr->stripe_count) {
 		dprintk("%s Bad first_stripe_index %u\n",
 				__func__, fl->first_stripe_index);
@@ -570,6 +572,13 @@ filelayout_check_deviceid(struct pnfs_layout_hdr *lo,
 		goto out_put;
 	}
 	status = 0;
+
+	/*
+	 * Atomic compare and xchange to ensure we don't scribble
+	 * over a non-NULL pointer.
+	 */
+	if (cmpxchg(&fl->dsaddr, NULL, dsaddr) != NULL)
+		goto out_put;
 out:
 	return status;
 out_put:
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 1f2ac3dd0fe5..b0fa83a60754 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1842,6 +1842,10 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
 	int vers, ret;
 	struct nfs_fh *fh;
 
+	if (!lseg || !(pnfs_is_valid_lseg(lseg) ||
+	    test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags)))
+		goto out_err;
+
 	idx = calc_ds_index_from_commit(lseg, data->ds_commit_index);
 	ds = nfs4_ff_layout_prepare_ds(lseg, idx, true);
 	if (!ds)
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index 3efe946672be..60bad882c123 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -512,7 +512,7 @@ static const struct rpc_version mnt_version1 = {
 	.counts		= mnt_counts,
 };
 
-static unsigned int mnt3_counts[ARRAY_SIZE(mnt_procedures)];
+static unsigned int mnt3_counts[ARRAY_SIZE(mnt3_procedures)];
 static const struct rpc_version mnt_version3 = {
 	.number		= 3,
 	.nrprocs	= ARRAY_SIZE(mnt3_procedures),
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index df4a7d3ab915..d1e87ec0df84 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -220,15 +220,8 @@ static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry)
 
 	status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
 	nfs_refresh_inode(inode, res.fattr);
-	if (status == 0) {
-		entry->mask = 0;
-		if (res.access & NFS3_ACCESS_READ)
-			entry->mask |= MAY_READ;
-		if (res.access & (NFS3_ACCESS_MODIFY | NFS3_ACCESS_EXTEND | NFS3_ACCESS_DELETE))
-			entry->mask |= MAY_WRITE;
-		if (res.access & (NFS3_ACCESS_LOOKUP|NFS3_ACCESS_EXECUTE))
-			entry->mask |= MAY_EXEC;
-	}
+	if (status == 0)
+		nfs_access_set_mask(entry, res.access);
 	nfs_free_fattr(res.fattr);
 out:
 	dprintk("NFS reply access: %d\n", status);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index a0b4e1091340..18ca6879d8de 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2236,7 +2236,7 @@ static int nfs4_opendata_access(struct rpc_cred *cred,
 				int openflags)
 {
 	struct nfs_access_entry cache;
-	u32 mask;
+	u32 mask, flags;
 
 	/* access call failed or for some reason the server doesn't
 	 * support any access modes -- defer access call until later */
@@ -2250,16 +2250,20 @@ static int nfs4_opendata_access(struct rpc_cred *cred,
 	 */
 	if (openflags & __FMODE_EXEC) {
 		/* ONLY check for exec rights */
-		mask = MAY_EXEC;
+		if (S_ISDIR(state->inode->i_mode))
+			mask = NFS4_ACCESS_LOOKUP;
+		else
+			mask = NFS4_ACCESS_EXECUTE;
 	} else if ((fmode & FMODE_READ) && !opendata->file_created)
-		mask = MAY_READ;
+		mask = NFS4_ACCESS_READ;
 
 	cache.cred = cred;
 	cache.jiffies = jiffies;
 	nfs_access_set_mask(&cache, opendata->o_res.access_result);
 	nfs_access_add_cache(state->inode, &cache);
 
-	if ((mask & ~cache.mask & (MAY_READ | MAY_EXEC)) == 0)
+	flags = NFS4_ACCESS_READ | NFS4_ACCESS_EXECUTE | NFS4_ACCESS_LOOKUP;
+	if ((mask & ~cache.mask & flags) == 0)
 		return 0;
 
 	return -EACCES;
@@ -6492,7 +6496,7 @@ nfs4_retry_setlk(struct nfs4_state *state, int cmd, struct file_lock *request)
 		set_current_state(TASK_INTERRUPTIBLE);
 		spin_unlock_irqrestore(&q->lock, flags);
 
-		freezable_schedule_timeout_interruptible(NFS4_LOCK_MAXTIMEOUT);
+		freezable_schedule_timeout(NFS4_LOCK_MAXTIMEOUT);
 	}
 
 	finish_wait(q, &wait);
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index d40755a0984b..25f28fa64c57 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -159,13 +159,18 @@ void pnfs_generic_recover_commit_reqs(struct list_head *dst,
 {
 	struct pnfs_commit_bucket *b;
 	struct pnfs_layout_segment *freeme;
+	int nwritten;
 	int i;
 
 	lockdep_assert_held(&cinfo->inode->i_lock);
 restart:
 	for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) {
-		if (pnfs_generic_transfer_commit_list(&b->written, dst,
-						      cinfo, 0)) {
+		nwritten = pnfs_generic_transfer_commit_list(&b->written,
+				dst, cinfo, 0);
+		if (!nwritten)
+			continue;
+		cinfo->ds->nwritten -= nwritten;
+		if (list_empty(&b->written)) {
 			freeme = b->wlseg;
 			b->wlseg = NULL;
 			spin_unlock(&cinfo->inode->i_lock);
@@ -174,7 +179,6 @@ restart:
 			goto restart;
 		}
 	}
-	cinfo->ds->nwritten = 0;
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_recover_commit_reqs);
 
@@ -183,6 +187,7 @@ static void pnfs_generic_retry_commit(struct nfs_commit_info *cinfo, int idx)
 	struct pnfs_ds_commit_info *fl_cinfo = cinfo->ds;
 	struct pnfs_commit_bucket *bucket;
 	struct pnfs_layout_segment *freeme;
+	struct list_head *pos;
 	LIST_HEAD(pages);
 	int i;
 
@@ -193,6 +198,8 @@ static void pnfs_generic_retry_commit(struct nfs_commit_info *cinfo, int idx)
 			continue;
 		freeme = bucket->clseg;
 		bucket->clseg = NULL;
+		list_for_each(pos, &bucket->committing)
+			cinfo->ds->ncommitting--;
 		list_splice_init(&bucket->committing, &pages);
 		spin_unlock(&cinfo->inode->i_lock);
 		nfs_retry_commit(&pages, freeme, cinfo, i);
@@ -217,13 +224,6 @@ pnfs_generic_alloc_ds_commits(struct nfs_commit_info *cinfo,
 	for (i = 0; i < fl_cinfo->nbuckets; i++, bucket++) {
 		if (list_empty(&bucket->committing))
 			continue;
-		/*
-		 * If the layout segment is invalid, then let
-		 * pnfs_generic_retry_commit() clean up the bucket.
-		 */
-		if (bucket->clseg && !pnfs_is_valid_lseg(bucket->clseg) &&
-		    !test_bit(NFS_LSEG_LAYOUTRETURN, &bucket->clseg->pls_flags))
-			break;
 		data = nfs_commitdata_alloc(false);
 		if (!data)
 			break;
@@ -243,9 +243,12 @@ void pnfs_fetch_commit_bucket_list(struct list_head *pages,
 		struct nfs_commit_info *cinfo)
 {
 	struct pnfs_commit_bucket *bucket;
+	struct list_head *pos;
 
 	bucket = &cinfo->ds->buckets[data->ds_commit_index];
 	spin_lock(&cinfo->inode->i_lock);
+	list_for_each(pos, &bucket->committing)
+		cinfo->ds->ncommitting--;
 	list_splice_init(&bucket->committing, pages);
 	data->lseg = bucket->clseg;
 	bucket->clseg = NULL;
@@ -330,7 +333,6 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
 		}
 	}
 out:
-	cinfo->ds->ncommitting = 0;
 	return PNFS_ATTEMPTED;
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_commit_pagelist);
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 641d9ee97f91..48b70e6490f3 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -481,17 +481,30 @@ out_cleanup:
 }
 
 static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
-			      struct cattr *attr, struct dentry *hardlink)
+			      struct cattr *attr, struct dentry *hardlink,
+			      bool origin)
 {
 	int err;
 	const struct cred *old_cred;
 	struct cred *override_cred;
+	struct dentry *parent = dentry->d_parent;
 
-	err = ovl_copy_up(dentry->d_parent);
+	err = ovl_copy_up(parent);
 	if (err)
 		return err;
 
 	old_cred = ovl_override_creds(dentry->d_sb);
+
+	/*
+	 * When linking a file with copy up origin into a new parent, mark the
+	 * new parent dir "impure".
+	 */
+	if (origin) {
+		err = ovl_set_impure(parent, ovl_dentry_upper(parent));
+		if (err)
+			goto out_revert_creds;
+	}
+
 	err = -ENOMEM;
 	override_cred = prepare_creds();
 	if (override_cred) {
@@ -550,7 +563,7 @@ static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev,
 	inode_init_owner(inode, dentry->d_parent->d_inode, mode);
 	attr.mode = inode->i_mode;
 
-	err = ovl_create_or_link(dentry, inode, &attr, NULL);
+	err = ovl_create_or_link(dentry, inode, &attr, NULL, false);
 	if (err)
 		iput(inode);
 
@@ -609,7 +622,8 @@ static int ovl_link(struct dentry *old, struct inode *newdir,
 	inode = d_inode(old);
 	ihold(inode);
 
-	err = ovl_create_or_link(new, inode, NULL, ovl_dentry_upper(old));
+	err = ovl_create_or_link(new, inode, NULL, ovl_dentry_upper(old),
+				 ovl_type_origin(old));
 	if (err)
 		iput(inode);
 
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 69f4fc26ee39..5bc71642b226 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -202,37 +202,38 @@ bool ovl_is_private_xattr(const char *name)
 		       sizeof(OVL_XATTR_PREFIX) - 1) == 0;
 }
 
-int ovl_xattr_set(struct dentry *dentry, const char *name, const void *value,
-		  size_t size, int flags)
+int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name,
+		  const void *value, size_t size, int flags)
 {
 	int err;
-	struct path realpath;
-	enum ovl_path_type type = ovl_path_real(dentry, &realpath);
+	struct dentry *upperdentry = ovl_i_dentry_upper(inode);
+	struct dentry *realdentry = upperdentry ?: ovl_dentry_lower(dentry);
 	const struct cred *old_cred;
 
 	err = ovl_want_write(dentry);
 	if (err)
 		goto out;
 
-	if (!value && !OVL_TYPE_UPPER(type)) {
-		err = vfs_getxattr(realpath.dentry, name, NULL, 0);
+	if (!value && !upperdentry) {
+		err = vfs_getxattr(realdentry, name, NULL, 0);
 		if (err < 0)
 			goto out_drop_write;
 	}
 
-	err = ovl_copy_up(dentry);
-	if (err)
-		goto out_drop_write;
+	if (!upperdentry) {
+		err = ovl_copy_up(dentry);
+		if (err)
+			goto out_drop_write;
 
-	if (!OVL_TYPE_UPPER(type))
-		ovl_path_upper(dentry, &realpath);
+		realdentry = ovl_dentry_upper(dentry);
+	}
 
 	old_cred = ovl_override_creds(dentry->d_sb);
 	if (value)
-		err = vfs_setxattr(realpath.dentry, name, value, size, flags);
+		err = vfs_setxattr(realdentry, name, value, size, flags);
 	else {
 		WARN_ON(flags != XATTR_REPLACE);
-		err = vfs_removexattr(realpath.dentry, name);
+		err = vfs_removexattr(realdentry, name);
 	}
 	revert_creds(old_cred);
 
@@ -242,12 +243,13 @@ out:
 	return err;
 }
 
-int ovl_xattr_get(struct dentry *dentry, const char *name,
+int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name,
 		  void *value, size_t size)
 {
-	struct dentry *realdentry = ovl_dentry_real(dentry);
 	ssize_t res;
 	const struct cred *old_cred;
+	struct dentry *realdentry =
+		ovl_i_dentry_upper(inode) ?: ovl_dentry_lower(dentry);
 
 	old_cred = ovl_override_creds(dentry->d_sb);
 	res = vfs_getxattr(realdentry, name, value, size);
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index 9bc0e580a5b3..8aef2b304b2d 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -397,8 +397,19 @@ int ovl_verify_index(struct dentry *index, struct path *lowerstack,
 	if (!d_inode(index))
 		return 0;
 
-	err = -EISDIR;
-	if (d_is_dir(index))
+	/*
+	 * Directory index entries are going to be used for looking up
+	 * redirected upper dirs by lower dir fh when decoding an overlay
+	 * file handle of a merge dir. Whiteout index entries are going to be
+	 * used as an indication that an exported overlay file handle should
+	 * be treated as stale (i.e. after unlink of the overlay inode).
+	 * We don't know the verification rules for directory and whiteout
+	 * index entries, because they have not been implemented yet, so return
+	 * EROFS if those entries are found to avoid corrupting an index that
+	 * was created by a newer kernel.
+	 */
+	err = -EROFS;
+	if (d_is_dir(index) || ovl_is_whiteout(index))
 		goto fail;
 
 	err = -EINVAL;
@@ -436,8 +447,8 @@ out:
 	return err;
 
 fail:
-	pr_warn_ratelimited("overlayfs: failed to verify index (%pd2, err=%i)\n",
-			    index, err);
+	pr_warn_ratelimited("overlayfs: failed to verify index (%pd2, ftype=%x, err=%i)\n",
+			    index, d_inode(index)->i_mode & S_IFMT, err);
 	goto out;
 }
 
@@ -502,6 +513,7 @@ static struct dentry *ovl_lookup_index(struct dentry *dentry,
 		goto out;
 	}
 
+	inode = d_inode(index);
 	if (d_is_negative(index)) {
 		if (upper && d_inode(origin)->i_nlink > 1) {
 			pr_warn_ratelimited("overlayfs: hard link with origin but no index (ino=%lu).\n",
@@ -511,11 +523,22 @@ static struct dentry *ovl_lookup_index(struct dentry *dentry,
 
 		dput(index);
 		index = NULL;
-	} else if (upper && d_inode(index) != d_inode(upper)) {
-		inode = d_inode(index);
-		pr_warn_ratelimited("overlayfs: wrong index found (index ino: %lu, upper ino: %lu).\n",
-				    d_inode(index)->i_ino,
-				    d_inode(upper)->i_ino);
+	} else if (upper && d_inode(upper) != inode) {
+		pr_warn_ratelimited("overlayfs: wrong index found (index=%pd2, ino=%lu, upper ino=%lu).\n",
+				    index, inode->i_ino, d_inode(upper)->i_ino);
+		goto fail;
+	} else if (ovl_dentry_weird(index) || ovl_is_whiteout(index) ||
+		   ((inode->i_mode ^ d_inode(origin)->i_mode) & S_IFMT)) {
+		/*
+		 * Index should always be of the same file type as origin
+		 * except for the case of a whiteout index. A whiteout
+		 * index should only exist if all lower aliases have been
+		 * unlinked, which means that finding a lower origin on lookup
+		 * whose index is a whiteout should be treated as an error.
+		 */
+		pr_warn_ratelimited("overlayfs: bad index found (index=%pd2, ftype=%x, origin ftype=%x).\n",
+				    index, d_inode(index)->i_mode & S_IFMT,
+				    d_inode(origin)->i_mode & S_IFMT);
 		goto fail;
 	}
 
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 60d26605e039..e927a62c97ae 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -47,7 +47,8 @@ enum ovl_flag {
 /* Is the real inode encoded in fid an upper inode? */
 #define OVL_FH_FLAG_PATH_UPPER	(1 << 2)
 
-#define OVL_FH_FLAG_ALL (OVL_FH_FLAG_BIG_ENDIAN | OVL_FH_FLAG_ANY_ENDIAN)
+#define OVL_FH_FLAG_ALL (OVL_FH_FLAG_BIG_ENDIAN | OVL_FH_FLAG_ANY_ENDIAN | \
+			 OVL_FH_FLAG_PATH_UPPER)
 
 #if defined(__LITTLE_ENDIAN)
 #define OVL_FH_FLAG_CPU_ENDIAN 0
@@ -199,6 +200,7 @@ enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path);
 struct dentry *ovl_dentry_upper(struct dentry *dentry);
 struct dentry *ovl_dentry_lower(struct dentry *dentry);
 struct dentry *ovl_dentry_real(struct dentry *dentry);
+struct dentry *ovl_i_dentry_upper(struct inode *inode);
 struct inode *ovl_inode_upper(struct inode *inode);
 struct inode *ovl_inode_lower(struct inode *inode);
 struct inode *ovl_inode_real(struct inode *inode);
@@ -270,9 +272,9 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr);
 int ovl_getattr(const struct path *path, struct kstat *stat,
 		u32 request_mask, unsigned int flags);
 int ovl_permission(struct inode *inode, int mask);
-int ovl_xattr_set(struct dentry *dentry, const char *name, const void *value,
-		  size_t size, int flags);
-int ovl_xattr_get(struct dentry *dentry, const char *name,
+int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name,
+		  const void *value, size_t size, int flags);
+int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name,
 		  void *value, size_t size);
 ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size);
 struct posix_acl *ovl_get_acl(struct inode *inode, int type);
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 0298463cf9c3..3d424a51cabb 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -703,7 +703,10 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt,
 			err = PTR_ERR(index);
 			break;
 		}
-		if (ovl_verify_index(index, lowerstack, numlower)) {
+		err = ovl_verify_index(index, lowerstack, numlower);
+		if (err) {
+			if (err == -EROFS)
+				break;
 			err = ovl_cleanup(dir, index);
 			if (err)
 				break;
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 44dc2d6ffe0f..d86e89f97201 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -692,7 +692,7 @@ ovl_posix_acl_xattr_get(const struct xattr_handler *handler,
 			struct dentry *dentry, struct inode *inode,
 			const char *name, void *buffer, size_t size)
 {
-	return ovl_xattr_get(dentry, handler->name, buffer, size);
+	return ovl_xattr_get(dentry, inode, handler->name, buffer, size);
 }
 
 static int __maybe_unused
@@ -742,7 +742,7 @@ ovl_posix_acl_xattr_set(const struct xattr_handler *handler,
 			return err;
 	}
 
-	err = ovl_xattr_set(dentry, handler->name, value, size, flags);
+	err = ovl_xattr_set(dentry, inode, handler->name, value, size, flags);
 	if (!err)
 		ovl_copyattr(ovl_inode_real(inode), inode);
 
@@ -772,7 +772,7 @@ static int ovl_other_xattr_get(const struct xattr_handler *handler,
 			       struct dentry *dentry, struct inode *inode,
 			       const char *name, void *buffer, size_t size)
 {
-	return ovl_xattr_get(dentry, name, buffer, size);
+	return ovl_xattr_get(dentry, inode, name, buffer, size);
 }
 
 static int ovl_other_xattr_set(const struct xattr_handler *handler,
@@ -780,7 +780,7 @@ static int ovl_other_xattr_set(const struct xattr_handler *handler,
 			       const char *name, const void *value,
 			       size_t size, int flags)
 {
-	return ovl_xattr_set(dentry, name, value, size, flags);
+	return ovl_xattr_set(dentry, inode, name, value, size, flags);
 }
 
 static const struct xattr_handler __maybe_unused
@@ -1058,10 +1058,6 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 
 		ufs->indexdir = ovl_workdir_create(sb, ufs, workpath.dentry,
 						   OVL_INDEXDIR_NAME, true);
-		err = PTR_ERR(ufs->indexdir);
-		if (IS_ERR(ufs->indexdir))
-			goto out_put_lower_mnt;
-
 		if (ufs->indexdir) {
 			/* Verify upper root is index dir origin */
 			err = ovl_verify_origin(ufs->indexdir, ufs->upper_mnt,
@@ -1090,6 +1086,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	else
 		sb->s_d_op = &ovl_dentry_operations;
 
+	err = -ENOMEM;
 	ufs->creator_cred = cred = prepare_creds();
 	if (!cred)
 		goto out_put_indexdir;
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index c492ba75c659..f46ad75dc96a 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -157,9 +157,14 @@ struct dentry *ovl_dentry_real(struct dentry *dentry)
 	return ovl_dentry_upper(dentry) ?: ovl_dentry_lower(dentry);
 }
 
+struct dentry *ovl_i_dentry_upper(struct inode *inode)
+{
+	return ovl_upperdentry_dereference(OVL_I(inode));
+}
+
 struct inode *ovl_inode_upper(struct inode *inode)
 {
-	struct dentry *upperdentry = ovl_upperdentry_dereference(OVL_I(inode));
+	struct dentry *upperdentry = ovl_i_dentry_upper(inode);
 
 	return upperdentry ? d_inode(upperdentry) : NULL;
 }
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 0a9880777c9c..c09c16b1ad3b 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -5435,6 +5435,7 @@ __xfs_bunmapi(
 	xfs_fsblock_t		sum;
 	xfs_filblks_t		len = *rlen;	/* length to unmap in file */
 	xfs_fileoff_t		max_len;
+	xfs_agnumber_t		prev_agno = NULLAGNUMBER, agno;
 
 	trace_xfs_bunmap(ip, bno, len, flags, _RET_IP_);
 
@@ -5534,6 +5535,17 @@ __xfs_bunmapi(
 		 */
 		del = got;
 		wasdel = isnullstartblock(del.br_startblock);
+
+		/*
+		 * Make sure we don't touch multiple AGF headers out of order
+		 * in a single transaction, as that could cause AB-BA deadlocks.
+		 */
+		if (!wasdel) {
+			agno = XFS_FSB_TO_AGNO(mp, del.br_startblock);
+			if (prev_agno != NULLAGNUMBER && prev_agno > agno)
+				break;
+			prev_agno = agno;
+		}
 		if (got.br_startoff < start) {
 			del.br_startoff = start;
 			del.br_blockcount -= start - got.br_startoff;
@@ -6499,6 +6511,15 @@ xfs_bmap_finish_one(
 	xfs_fsblock_t			firstfsb;
 	int				error = 0;
 
+	/*
+	 * firstfsb is tied to the transaction lifetime and is used to
+	 * ensure correct AG locking order and schedule work item
+	 * continuations.  XFS_BUI_MAX_FAST_EXTENTS (== 1) restricts us
+	 * to only making one bmap call per transaction, so it should
+	 * be safe to have it as a local variable here.
+	 */
+	firstfsb = NULLFSBLOCK;
+
 	trace_xfs_bmap_deferred(tp->t_mountp,
 			XFS_FSB_TO_AGNO(tp->t_mountp, startblock), type,
 			XFS_FSB_TO_AGBNO(tp->t_mountp, startblock),
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 4da85fff69ad..e0bcc4a59efd 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -728,7 +728,8 @@ xfs_btree_firstrec(
 	 * Get the block pointer for this level.
 	 */
 	block = xfs_btree_get_block(cur, level, &bp);
-	xfs_btree_check_block(cur, block, level, bp);
+	if (xfs_btree_check_block(cur, block, level, bp))
+		return 0;
 	/*
 	 * It's empty, there is no such record.
 	 */
@@ -757,7 +758,8 @@ xfs_btree_lastrec(
 	 * Get the block pointer for this level.
 	 */
 	block = xfs_btree_get_block(cur, level, &bp);
-	xfs_btree_check_block(cur, block, level, bp);
+	if (xfs_btree_check_block(cur, block, level, bp))
+		return 0;
 	/*
 	 * It's empty, there is no such record.
 	 */
diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c
index d478065b9544..8727a43115ef 100644
--- a/fs/xfs/libxfs/xfs_dir2_data.c
+++ b/fs/xfs/libxfs/xfs_dir2_data.c
@@ -136,6 +136,8 @@ __xfs_dir3_data_check(
 		 */
 		if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
 			XFS_WANT_CORRUPTED_RETURN(mp, lastfree == 0);
+			XFS_WANT_CORRUPTED_RETURN(mp, endp >=
+					p + be16_to_cpu(dup->length));
 			XFS_WANT_CORRUPTED_RETURN(mp,
 				be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup)) ==
 					       (char *)dup - (char *)hdr);
@@ -164,6 +166,8 @@ __xfs_dir3_data_check(
 		XFS_WANT_CORRUPTED_RETURN(mp, dep->namelen != 0);
 		XFS_WANT_CORRUPTED_RETURN(mp,
 			!xfs_dir_ino_validate(mp, be64_to_cpu(dep->inumber)));
+		XFS_WANT_CORRUPTED_RETURN(mp, endp >=
+				p + ops->data_entsize(dep->namelen));
 		XFS_WANT_CORRUPTED_RETURN(mp,
 			be16_to_cpu(*ops->data_entry_tag_p(dep)) ==
 					       (char *)dep - (char *)hdr);
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 900ea231f9a3..45b1c3b4e047 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -1638,6 +1638,10 @@ xfs_refcount_recover_cow_leftovers(
 	error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
 	if (error)
 		goto out_trans;
+	if (!agbp) {
+		error = -ENOMEM;
+		goto out_trans;
+	}
 	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, NULL);
 
 	/* Find all the leftover CoW staging extents. */
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 6ce948c436d5..15751dc2a27d 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -111,6 +111,9 @@ restart:
 			skipped = 0;
 			break;
 		}
+		/* we're done if id overflows back to zero */
+		if (!next_index)
+			break;
 	}
 
 	if (skipped) {
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index ab2270a87196..f45fbf0db9bb 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -170,6 +170,8 @@ xfs_reflink_find_shared(
 	error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
 	if (error)
 		return error;
+	if (!agbp)
+		return -ENOMEM;
 
 	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, NULL);
 
@@ -329,7 +331,7 @@ xfs_reflink_convert_cow_extent(
 	xfs_filblks_t			count_fsb,
 	struct xfs_defer_ops		*dfops)
 {
-	xfs_fsblock_t			first_block;
+	xfs_fsblock_t			first_block = NULLFSBLOCK;
 	int				nimaps = 1;
 
 	if (imap->br_state == XFS_EXT_NORM)