1 files changed, 132 insertions, 121 deletions

diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 497649c69..1b73a7f81 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -384,6 +384,17 @@ static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino,
 	struct inode *inode;
 	int err;
 
+	/*
+	 * We have to check for this corruption early as otherwise
+	 * iget_locked() could wait indefinitely for the state of our
+	 * parent inode.
+	 */
+	if (parent->i_ino == ea_ino) {
+		ext4_error(parent->i_sb,
+			   "Parent and EA inode have the same ino %lu", ea_ino);
+		return -EFSCORRUPTED;
+	}
+
 	inode = ext4_iget(parent->i_sb, ea_ino, EXT4_IGET_NORMAL);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
@@ -434,6 +445,21 @@ error:
 	return err;
 }
 
+/* Remove entry from mbcache when EA inode is getting evicted */
+void ext4_evict_ea_inode(struct inode *inode)
+{
+	struct mb_cache_entry *oe;
+
+	if (!EA_INODE_CACHE(inode))
+		return;
+	/* Wait for entry to get unused so that we can remove it */
+	while ((oe = mb_cache_entry_delete_or_get(EA_INODE_CACHE(inode),
+			ext4_xattr_inode_get_hash(inode), inode->i_ino))) {
+		mb_cache_entry_wait_unused(oe);
+		mb_cache_entry_put(EA_INODE_CACHE(inode), oe);
+	}
+}
+
 static int
 ext4_xattr_inode_verify_hashes(struct inode *ea_inode,
 			       struct ext4_xattr_entry *entry, void *buffer,
@@ -1019,10 +1045,8 @@ static int ext4_xattr_ensure_credits(handle_t *handle, struct inode *inode,
 static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode,
 				       int ref_change)
 {
-	struct mb_cache *ea_inode_cache = EA_INODE_CACHE(ea_inode);
 	struct ext4_iloc iloc;
 	s64 ref_count;
-	u32 hash;
 	int ret;
 
 	inode_lock(ea_inode);
@@ -1047,14 +1071,6 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode,
 
 			set_nlink(ea_inode, 1);
 			ext4_orphan_del(handle, ea_inode);
-
-			if (ea_inode_cache) {
-				hash = ext4_xattr_inode_get_hash(ea_inode);
-				mb_cache_entry_create(ea_inode_cache,
-						      GFP_NOFS, hash,
-						      ea_inode->i_ino,
-						      true /* reusable */);
-			}
 		}
 	} else {
 		WARN_ONCE(ref_count < 0, "EA inode %lu ref_count=%lld",
@@ -1067,12 +1083,6 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode,
 
 			clear_nlink(ea_inode);
 			ext4_orphan_add(handle, ea_inode);
-
-			if (ea_inode_cache) {
-				hash = ext4_xattr_inode_get_hash(ea_inode);
-				mb_cache_entry_delete(ea_inode_cache, hash,
-						      ea_inode->i_ino);
-			}
 		}
 	}
 
@@ -1253,6 +1263,7 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 	if (error)
 		goto out;
 
+retry_ref:
 	lock_buffer(bh);
 	hash = le32_to_cpu(BHDR(bh)->h_hash);
 	ref = le32_to_cpu(BHDR(bh)->h_refcount);
@@ -1262,9 +1273,18 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 		 * This must happen under buffer lock for
 		 * ext4_xattr_block_set() to reliably detect freed block
 		 */
-		if (ea_block_cache)
-			mb_cache_entry_delete(ea_block_cache, hash,
-					      bh->b_blocknr);
+		if (ea_block_cache) {
+			struct mb_cache_entry *oe;
+
+			oe = mb_cache_entry_delete_or_get(ea_block_cache, hash,
+							  bh->b_blocknr);
+			if (oe) {
+				unlock_buffer(bh);
+				mb_cache_entry_wait_unused(oe);
+				mb_cache_entry_put(ea_block_cache, oe);
+				goto retry_ref;
+			}
+		}
 		get_bh(bh);
 		unlock_buffer(bh);
 
@@ -1288,7 +1308,7 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 				ce = mb_cache_entry_get(ea_block_cache, hash,
 							bh->b_blocknr);
 				if (ce) {
-					ce->e_reusable = 1;
+					set_bit(MBE_REUSABLE_B, &ce->e_flags);
 					mb_cache_entry_put(ea_block_cache, ce);
 				}
 			}
@@ -1427,6 +1447,13 @@ static struct inode *ext4_xattr_inode_create(handle_t *handle,
 	uid_t owner[2] = { i_uid_read(inode), i_gid_read(inode) };
 	int err;
 
+	if (inode->i_sb->s_root == NULL) {
+		ext4_warning(inode->i_sb,
+			     "refuse to create EA inode when umounting");
+		WARN_ON(1);
+		return ERR_PTR(-EINVAL);
+	}
+
 	/*
 	 * Let the next inode be the goal, so we try and allocate the EA inode
 	 * in the same group, or nearby one.
@@ -1446,6 +1473,9 @@ static struct inode *ext4_xattr_inode_create(handle_t *handle,
 		if (!err)
 			err = ext4_inode_attach_jinode(ea_inode);
 		if (err) {
+			if (ext4_xattr_inode_dec_ref(handle, ea_inode))
+				ext4_warning_inode(ea_inode,
+					"cleanup dec ref error %d", err);
 			iput(ea_inode);
 			return ERR_PTR(err);
 		}
@@ -1872,6 +1902,8 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 #define header(x) ((struct ext4_xattr_header *)(x))
 
 	if (s->base) {
+		int offset = (char *)s->here - bs->bh->b_data;
+
 		BUFFER_TRACE(bs->bh, "get_write_access");
 		error = ext4_journal_get_write_access(handle, bs->bh);
 		if (error)
@@ -1886,9 +1918,20 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 			 * ext4_xattr_block_set() to reliably detect modified
 			 * block
 			 */
-			if (ea_block_cache)
-				mb_cache_entry_delete(ea_block_cache, hash,
-						      bs->bh->b_blocknr);
+			if (ea_block_cache) {
+				struct mb_cache_entry *oe;
+
+				oe = mb_cache_entry_delete_or_get(ea_block_cache,
+					hash, bs->bh->b_blocknr);
+				if (oe) {
+					/*
+					 * Xattr block is getting reused. Leave
+					 * it alone.
+					 */
+					mb_cache_entry_put(ea_block_cache, oe);
+					goto clone_block;
+				}
+			}
 			ea_bdebug(bs->bh, "modifying in-place");
 			error = ext4_xattr_set_entry(i, s, handle, inode,
 						     true /* is_block */);
@@ -1903,50 +1946,47 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 			if (error)
 				goto cleanup;
 			goto inserted;
-		} else {
-			int offset = (char *)s->here - bs->bh->b_data;
+		}
+clone_block:
+		unlock_buffer(bs->bh);
+		ea_bdebug(bs->bh, "cloning");
+		s->base = kmemdup(BHDR(bs->bh), bs->bh->b_size, GFP_NOFS);
+		error = -ENOMEM;
+		if (s->base == NULL)
+			goto cleanup;
+		s->first = ENTRY(header(s->base)+1);
+		header(s->base)->h_refcount = cpu_to_le32(1);
+		s->here = ENTRY(s->base + offset);
+		s->end = s->base + bs->bh->b_size;
 
-			unlock_buffer(bs->bh);
-			ea_bdebug(bs->bh, "cloning");
-			s->base = kmalloc(bs->bh->b_size, GFP_NOFS);
-			error = -ENOMEM;
-			if (s->base == NULL)
+		/*
+		 * If existing entry points to an xattr inode, we need
+		 * to prevent ext4_xattr_set_entry() from decrementing
+		 * ref count on it because the reference belongs to the
+		 * original block. In this case, make the entry look
+		 * like it has an empty value.
+		 */
+		if (!s->not_found && s->here->e_value_inum) {
+			ea_ino = le32_to_cpu(s->here->e_value_inum);
+			error = ext4_xattr_inode_iget(inode, ea_ino,
+				      le32_to_cpu(s->here->e_hash),
+				      &tmp_inode);
+			if (error)
 				goto cleanup;
-			memcpy(s->base, BHDR(bs->bh), bs->bh->b_size);
-			s->first = ENTRY(header(s->base)+1);
-			header(s->base)->h_refcount = cpu_to_le32(1);
-			s->here = ENTRY(s->base + offset);
-			s->end = s->base + bs->bh->b_size;
-
-			/*
-			 * If existing entry points to an xattr inode, we need
-			 * to prevent ext4_xattr_set_entry() from decrementing
-			 * ref count on it because the reference belongs to the
-			 * original block. In this case, make the entry look
-			 * like it has an empty value.
-			 */
-			if (!s->not_found && s->here->e_value_inum) {
-				ea_ino = le32_to_cpu(s->here->e_value_inum);
-				error = ext4_xattr_inode_iget(inode, ea_ino,
-					      le32_to_cpu(s->here->e_hash),
-					      &tmp_inode);
-				if (error)
-					goto cleanup;
 
-				if (!ext4_test_inode_state(tmp_inode,
-						EXT4_STATE_LUSTRE_EA_INODE)) {
-					/*
-					 * Defer quota free call for previous
-					 * inode until success is guaranteed.
-					 */
-					old_ea_inode_quota = le32_to_cpu(
-							s->here->e_value_size);
-				}
-				iput(tmp_inode);
-
-				s->here->e_value_inum = 0;
-				s->here->e_value_size = 0;
+			if (!ext4_test_inode_state(tmp_inode,
+					EXT4_STATE_LUSTRE_EA_INODE)) {
+				/*
+				 * Defer quota free call for previous
+				 * inode until success is guaranteed.
+				 */
+				old_ea_inode_quota = le32_to_cpu(
+						s->here->e_value_size);
 			}
+			iput(tmp_inode);
+
+			s->here->e_value_inum = 0;
+			s->here->e_value_size = 0;
 		}
 	} else {
 		/* Allocate a buffer where we construct the new block. */
@@ -2013,18 +2053,13 @@ inserted:
 				lock_buffer(new_bh);
 				/*
 				 * We have to be careful about races with
-				 * freeing, rehashing or adding references to
-				 * xattr block. Once we hold buffer lock xattr
-				 * block's state is stable so we can check
-				 * whether the block got freed / rehashed or
-				 * not.  Since we unhash mbcache entry under
-				 * buffer lock when freeing / rehashing xattr
-				 * block, checking whether entry is still
-				 * hashed is reliable. Same rules hold for
-				 * e_reusable handling.
+				 * adding references to xattr block. Once we
+				 * hold buffer lock xattr block's state is
+				 * stable so we can check the additional
+				 * reference fits.
 				 */
-				if (hlist_bl_unhashed(&ce->e_hash_list) ||
-				    !ce->e_reusable) {
+				ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1;
+				if (ref > EXT4_XATTR_REFCOUNT_MAX) {
 					/*
 					 * Undo everything and check mbcache
 					 * again.
@@ -2039,10 +2074,9 @@ inserted:
 					new_bh = NULL;
 					goto inserted;
 				}
-				ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1;
 				BHDR(new_bh)->h_refcount = cpu_to_le32(ref);
-				if (ref >= EXT4_XATTR_REFCOUNT_MAX)
-					ce->e_reusable = 0;
+				if (ref == EXT4_XATTR_REFCOUNT_MAX)
+					clear_bit(MBE_REUSABLE_B, &ce->e_flags);
 				ea_bdebug(new_bh, "reusing; refcount now=%d",
 					  ref);
 				ext4_xattr_block_csum_set(inode, new_bh);
@@ -2070,19 +2104,11 @@ inserted:
 
 			goal = ext4_group_first_block_no(sb,
 						EXT4_I(inode)->i_block_group);
-
-			/* non-extent files can't have physical blocks past 2^32 */
-			if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
-				goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
-
 			block = ext4_new_meta_blocks(handle, inode, goal, 0,
 						     NULL, &error);
 			if (error)
 				goto cleanup;
 
-			if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
-				BUG_ON(block > EXT4_MAX_BLOCK_FILE_PHYS);
-
 			ea_idebug(inode, "creating block %llu",
 				  (unsigned long long)block);
 
@@ -2210,7 +2236,7 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
 	return 0;
 }
 
-int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
+int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
 				struct ext4_xattr_info *i,
 				struct ext4_xattr_ibody_find *is)
 {
@@ -2235,30 +2261,6 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
 	return 0;
 }
 
-static int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
-				struct ext4_xattr_info *i,
-				struct ext4_xattr_ibody_find *is)
-{
-	struct ext4_xattr_ibody_header *header;
-	struct ext4_xattr_search *s = &is->s;
-	int error;
-
-	if (EXT4_I(inode)->i_extra_isize == 0)
-		return -ENOSPC;
-	error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */);
-	if (error)
-		return error;
-	header = IHDR(inode, ext4_raw_inode(&is->iloc));
-	if (!IS_LAST_ENTRY(s->first)) {
-		header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
-		ext4_set_inode_state(inode, EXT4_STATE_XATTR);
-	} else {
-		header->h_magic = cpu_to_le32(0);
-		ext4_clear_inode_state(inode, EXT4_STATE_XATTR);
-	}
-	return 0;
-}
-
 static int ext4_xattr_value_same(struct ext4_xattr_search *s,
 				 struct ext4_xattr_info *i)
 {
@@ -2575,9 +2577,8 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode,
 
 	is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS);
 	bs = kzalloc(sizeof(struct ext4_xattr_block_find), GFP_NOFS);
-	buffer = kmalloc(value_size, GFP_NOFS);
 	b_entry_name = kmalloc(entry->e_name_len + 1, GFP_NOFS);
-	if (!is || !bs || !buffer || !b_entry_name) {
+	if (!is || !bs || !b_entry_name) {
 		error = -ENOMEM;
 		goto out;
 	}
@@ -2589,12 +2590,18 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode,
 
 	/* Save the entry name and the entry value */
 	if (entry->e_value_inum) {
+		buffer = kvmalloc(value_size, GFP_NOFS);
+		if (!buffer) {
+			error = -ENOMEM;
+			goto out;
+		}
+
 		error = ext4_xattr_inode_get(inode, entry, buffer, value_size);
 		if (error)
 			goto out;
 	} else {
 		size_t value_offs = le16_to_cpu(entry->e_value_offs);
-		memcpy(buffer, (void *)IFIRST(header) + value_offs, value_size);
+		buffer = (void *)IFIRST(header) + value_offs;
 	}
 
 	memcpy(b_entry_name, entry->e_name, entry->e_name_len);
@@ -2609,25 +2616,26 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode,
 	if (error)
 		goto out;
 
-	/* Remove the chosen entry from the inode */
-	error = ext4_xattr_ibody_set(handle, inode, &i, is);
-	if (error)
-		goto out;
-
 	i.value = buffer;
 	i.value_len = value_size;
 	error = ext4_xattr_block_find(inode, &i, bs);
 	if (error)
 		goto out;
 
-	/* Add entry which was removed from the inode into the block */
+	/* Move ea entry from the inode into the block */
 	error = ext4_xattr_block_set(handle, inode, &i, bs);
 	if (error)
 		goto out;
-	error = 0;
+
+	/* Remove the chosen entry from the inode */
+	i.value = NULL;
+	i.value_len = 0;
+	error = ext4_xattr_ibody_set(handle, inode, &i, is);
+
 out:
 	kfree(b_entry_name);
-	kfree(buffer);
+	if (entry->e_value_inum && buffer)
+		kvfree(buffer);
 	if (is)
 		brelse(is->iloc.bh);
 	if (bs)
@@ -2802,6 +2810,9 @@ shift:
 			(void *)header, total_ino);
 	EXT4_I(inode)->i_extra_isize = new_extra_isize;
 
+	if (ext4_has_inline_data(inode))
+		error = ext4_find_inline_data_nolock(inode);
+
 cleanup:
 	if (error && (mnt_count != le16_to_cpu(sbi->s_es->s_mnt_count))) {
 		ext4_warning(inode->i_sb, "Unable to expand inode %lu. Delete some EAs or run e2fsck.",