Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "The first major feature for ext4 this merge window is the largedir
  feature, which allows ext4 directories to support over 2 billion
  directory entries (assuming ~64 byte file names; in practice, users
  will run into practical performance limits first.) This feature was
  originally written by the Lustre team, and credit goes to Artem
  Blagodarenko from Seagate for getting this feature upstream.

  The second major major feature allows ext4 to support extended
  attribute values up to 64k. This feature was also originally from
  Lustre, and has been enhanced by Tahsin Erdogan from Google with a
  deduplication feature so that if multiple files have the same xattr
  value (for example, Windows ACL's stored by Samba), only one copy will
  be stored on disk for encoding and caching efficiency.

  We also have the usual set of bug fixes, cleanups, and optimizations"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (47 commits)
  ext4: fix spelling mistake: "prellocated" -> "preallocated"
  ext4: fix __ext4_new_inode() journal credits calculation
  ext4: skip ext4_init_security() and encryption on ea_inodes
  fs: generic_block_bmap(): initialize all of the fields in the temp bh
  ext4: change fast symlink test to not rely on i_blocks
  ext4: require key for truncate(2) of encrypted file
  ext4: don't bother checking for encryption key in ->mmap()
  ext4: check return value of kstrtoull correctly in reserved_clusters_store
  ext4: fix off-by-one fsmap error on 1k block filesystems
  ext4: return EFSBADCRC if a bad checksum error is found in ext4_find_entry()
  ext4: return EIO on read error in ext4_find_entry
  ext4: forbid encrypting root directory
  ext4: send parallel discards on commit completions
  ext4: avoid unnecessary stalls in ext4_evict_inode()
  ext4: add nombcache mount option
  ext4: strong binding of xattr inode references
  ext4: eliminate xattr entry e_hash recalculation for removes
  ext4: reserve space for xattr entries/names
  quota: add get_inode_usage callback to transfer multi-inode charges
  ext4: xattr inode deduplication
  ...

27 files changed, 2071 insertions, 507 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index 5234b15377c2..233e2983c5db 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -3031,11 +3031,11 @@ EXPORT_SYMBOL(block_write_full_page);
 sector_t generic_block_bmap(struct address_space *mapping, sector_t block,
 			    get_block_t *get_block)
 {
-	struct buffer_head tmp;
 	struct inode *inode = mapping->host;
-	tmp.b_state = 0;
-	tmp.b_blocknr = 0;
-	tmp.b_size = i_blocksize(inode);
+	struct buffer_head tmp = {
+		.b_size = i_blocksize(inode),
+	};
+
 	get_block(inode, block, &tmp, 0);
 	return tmp.b_blocknr;
 }
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 9914d51dff86..ce07a86200f3 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -256,6 +256,7 @@ int fscrypt_inherit_context(struct inode *parent, struct inode *child,
 	memcpy(ctx.master_key_descriptor, ci->ci_master_key,
 	       FS_KEY_DESCRIPTOR_SIZE);
 	get_random_bytes(ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE);
+	BUILD_BUG_ON(sizeof(ctx) != FSCRYPT_SET_CONTEXT_MAX_SIZE);
 	res = parent->i_sb->s_cop->set_context(child, &ctx,
 						sizeof(ctx), fs_data);
 	if (res)
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 03f5ce1d3dbe..23ebb92484c6 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -113,7 +113,7 @@ struct ext2_sb_info {
 	 * of the mount options.
 	 */
 	spinlock_t s_lock;
-	struct mb_cache *s_mb_cache;
+	struct mb_cache *s_ea_block_cache;
 };
 
 static inline spinlock_t *
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 9c2028b50e5c..7b1bc9059863 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -147,9 +147,9 @@ static void ext2_put_super (struct super_block * sb)
 
 	ext2_quota_off_umount(sb);
 
-	if (sbi->s_mb_cache) {
-		ext2_xattr_destroy_cache(sbi->s_mb_cache);
-		sbi->s_mb_cache = NULL;
+	if (sbi->s_ea_block_cache) {
+		ext2_xattr_destroy_cache(sbi->s_ea_block_cache);
+		sbi->s_ea_block_cache = NULL;
 	}
 	if (!(sb->s_flags & MS_RDONLY)) {
 		struct ext2_super_block *es = sbi->s_es;
@@ -1131,9 +1131,9 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 #ifdef CONFIG_EXT2_FS_XATTR
-	sbi->s_mb_cache = ext2_xattr_create_cache();
-	if (!sbi->s_mb_cache) {
-		ext2_msg(sb, KERN_ERR, "Failed to create an mb_cache");
+	sbi->s_ea_block_cache = ext2_xattr_create_cache();
+	if (!sbi->s_ea_block_cache) {
+		ext2_msg(sb, KERN_ERR, "Failed to create ea_block_cache");
 		goto failed_mount3;
 	}
 #endif
@@ -1182,8 +1182,8 @@ cantfind_ext2:
 			sb->s_id);
 	goto failed_mount;
 failed_mount3:
-	if (sbi->s_mb_cache)
-		ext2_xattr_destroy_cache(sbi->s_mb_cache);
+	if (sbi->s_ea_block_cache)
+		ext2_xattr_destroy_cache(sbi->s_ea_block_cache);
 	percpu_counter_destroy(&sbi->s_freeblocks_counter);
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c
index fbdb8f171893..1b9b1268d418 100644
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@@ -121,6 +121,8 @@ const struct xattr_handler *ext2_xattr_handlers[] = {
 	NULL
 };
 
+#define EA_BLOCK_CACHE(inode)	(EXT2_SB(inode->i_sb)->s_ea_block_cache)
+
 static inline const struct xattr_handler *
 ext2_xattr_handler(int name_index)
 {
@@ -150,7 +152,7 @@ ext2_xattr_get(struct inode *inode, int name_index, const char *name,
 	size_t name_len, size;
 	char *end;
 	int error;
-	struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
+	struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
 
 	ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld",
 		  name_index, name, buffer, (long)buffer_size);
@@ -195,7 +197,7 @@ bad_block:	ext2_error(inode->i_sb, "ext2_xattr_get",
 			goto found;
 		entry = next;
 	}
-	if (ext2_xattr_cache_insert(ext2_mb_cache, bh))
+	if (ext2_xattr_cache_insert(ea_block_cache, bh))
 		ea_idebug(inode, "cache insert failed");
 	error = -ENODATA;
 	goto cleanup;
@@ -208,7 +210,7 @@ found:
 	    le16_to_cpu(entry->e_value_offs) + size > inode->i_sb->s_blocksize)
 		goto bad_block;
 
-	if (ext2_xattr_cache_insert(ext2_mb_cache, bh))
+	if (ext2_xattr_cache_insert(ea_block_cache, bh))
 		ea_idebug(inode, "cache insert failed");
 	if (buffer) {
 		error = -ERANGE;
@@ -246,7 +248,7 @@ ext2_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size)
 	char *end;
 	size_t rest = buffer_size;
 	int error;
-	struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
+	struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
 
 	ea_idebug(inode, "buffer=%p, buffer_size=%ld",
 		  buffer, (long)buffer_size);
@@ -281,7 +283,7 @@ bad_block:	ext2_error(inode->i_sb, "ext2_xattr_list",
 			goto bad_block;
 		entry = next;
 	}
-	if (ext2_xattr_cache_insert(ext2_mb_cache, bh))
+	if (ext2_xattr_cache_insert(ea_block_cache, bh))
 		ea_idebug(inode, "cache insert failed");
 
 	/* list the attribute names */
@@ -493,8 +495,8 @@ bad_block:		ext2_error(sb, "ext2_xattr_set",
 			 * This must happen under buffer lock for
 			 * ext2_xattr_set2() to reliably detect modified block
 			 */
-			mb_cache_entry_delete_block(EXT2_SB(sb)->s_mb_cache,
-						    hash, bh->b_blocknr);
+			mb_cache_entry_delete(EA_BLOCK_CACHE(inode), hash,
+					      bh->b_blocknr);
 
 			/* keep the buffer locked while modifying it. */
 		} else {
@@ -627,7 +629,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 	struct super_block *sb = inode->i_sb;
 	struct buffer_head *new_bh = NULL;
 	int error;
-	struct mb_cache *ext2_mb_cache = EXT2_SB(sb)->s_mb_cache;
+	struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
 
 	if (header) {
 		new_bh = ext2_xattr_cache_find(inode, header);
@@ -655,7 +657,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 			   don't need to change the reference count. */
 			new_bh = old_bh;
 			get_bh(new_bh);
-			ext2_xattr_cache_insert(ext2_mb_cache, new_bh);
+			ext2_xattr_cache_insert(ea_block_cache, new_bh);
 		} else {
 			/* We need to allocate a new block */
 			ext2_fsblk_t goal = ext2_group_first_block_no(sb,
@@ -676,7 +678,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 			memcpy(new_bh->b_data, header, new_bh->b_size);
 			set_buffer_uptodate(new_bh);
 			unlock_buffer(new_bh);
-			ext2_xattr_cache_insert(ext2_mb_cache, new_bh);
+			ext2_xattr_cache_insert(ea_block_cache, new_bh);
 			
 			ext2_xattr_update_super_block(sb);
 		}
@@ -721,8 +723,8 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 			 * This must happen under buffer lock for
 			 * ext2_xattr_set2() to reliably detect freed block
 			 */
-			mb_cache_entry_delete_block(ext2_mb_cache,
-						    hash, old_bh->b_blocknr);
+			mb_cache_entry_delete(ea_block_cache, hash,
+					      old_bh->b_blocknr);
 			/* Free the old block. */
 			ea_bdebug(old_bh, "freeing");
 			ext2_free_blocks(inode, old_bh->b_blocknr, 1);
@@ -795,8 +797,8 @@ ext2_xattr_delete_inode(struct inode *inode)
 		 * This must happen under buffer lock for ext2_xattr_set2() to
 		 * reliably detect freed block
 		 */
-		mb_cache_entry_delete_block(EXT2_SB(inode->i_sb)->s_mb_cache,
-					    hash, bh->b_blocknr);
+		mb_cache_entry_delete(EA_BLOCK_CACHE(inode), hash,
+				      bh->b_blocknr);
 		ext2_free_blocks(inode, EXT2_I(inode)->i_file_acl, 1);
 		get_bh(bh);
 		bforget(bh);
@@ -897,21 +899,21 @@ ext2_xattr_cache_find(struct inode *inode, struct ext2_xattr_header *header)
 {
 	__u32 hash = le32_to_cpu(header->h_hash);
 	struct mb_cache_entry *ce;
-	struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
+	struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
 
 	if (!header->h_hash)
 		return NULL;  /* never share */
 	ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
 again:
-	ce = mb_cache_entry_find_first(ext2_mb_cache, hash);
+	ce = mb_cache_entry_find_first(ea_block_cache, hash);
 	while (ce) {
 		struct buffer_head *bh;
 
-		bh = sb_bread(inode->i_sb, ce->e_block);
+		bh = sb_bread(inode->i_sb, ce->e_value);
 		if (!bh) {
 			ext2_error(inode->i_sb, "ext2_xattr_cache_find",
 				"inode %ld: block %ld read error",
-				inode->i_ino, (unsigned long) ce->e_block);
+				inode->i_ino, (unsigned long) ce->e_value);
 		} else {
 			lock_buffer(bh);
 			/*
@@ -924,27 +926,27 @@ again:
 			 * entry is still hashed is reliable.
 			 */
 			if (hlist_bl_unhashed(&ce->e_hash_list)) {
-				mb_cache_entry_put(ext2_mb_cache, ce);
+				mb_cache_entry_put(ea_block_cache, ce);
 				unlock_buffer(bh);
 				brelse(bh);
 				goto again;
 			} else if (le32_to_cpu(HDR(bh)->h_refcount) >
 				   EXT2_XATTR_REFCOUNT_MAX) {
 				ea_idebug(inode, "block %ld refcount %d>%d",
-					  (unsigned long) ce->e_block,
+					  (unsigned long) ce->e_value,
 					  le32_to_cpu(HDR(bh)->h_refcount),
 					  EXT2_XATTR_REFCOUNT_MAX);
 			} else if (!ext2_xattr_cmp(header, HDR(bh))) {
 				ea_bdebug(bh, "b_count=%d",
 					  atomic_read(&(bh->b_count)));
-				mb_cache_entry_touch(ext2_mb_cache, ce);
-				mb_cache_entry_put(ext2_mb_cache, ce);
+				mb_cache_entry_touch(ea_block_cache, ce);
+				mb_cache_entry_put(ea_block_cache, ce);
 				return bh;
 			}
 			unlock_buffer(bh);
 			brelse(bh);
 		}
-		ce = mb_cache_entry_find_next(ext2_mb_cache, ce);
+		ce = mb_cache_entry_find_next(ea_block_cache, ce);
 	}
 	return NULL;
 }
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index 3ec0e46de95f..09441ae07a5b 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -183,7 +183,7 @@ ext4_get_acl(struct inode *inode, int type)
  */
 static int
 __ext4_set_acl(handle_t *handle, struct inode *inode, int type,
-	     struct posix_acl *acl)
+	     struct posix_acl *acl, int xattr_flags)
 {
 	int name_index;
 	void *value = NULL;
@@ -218,7 +218,7 @@ __ext4_set_acl(handle_t *handle, struct inode *inode, int type,
 	}
 
 	error = ext4_xattr_set_handle(handle, inode, name_index, "",
-				      value, size, 0);
+				      value, size, xattr_flags);
 
 	kfree(value);
 	if (!error)
@@ -231,18 +231,23 @@ int
 ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
 	handle_t *handle;
-	int error, retries = 0;
+	int error, credits, retries = 0;
+	size_t acl_size = acl ? ext4_acl_size(acl->a_count) : 0;
 
 	error = dquot_initialize(inode);
 	if (error)
 		return error;
 retry:
-	handle = ext4_journal_start(inode, EXT4_HT_XATTR,
-				    ext4_jbd2_credits_xattr(inode));
+	error = ext4_xattr_set_credits(inode, acl_size, false /* is_create */,
+				       &credits);
+	if (error)
+		return error;
+
+	handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits);
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
-	error = __ext4_set_acl(handle, inode, type, acl);
+	error = __ext4_set_acl(handle, inode, type, acl, 0 /* xattr_flags */);
 	ext4_journal_stop(handle);
 	if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
 		goto retry;
@@ -267,13 +272,13 @@ ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
 
 	if (default_acl) {
 		error = __ext4_set_acl(handle, inode, ACL_TYPE_DEFAULT,
-				       default_acl);
+				       default_acl, XATTR_CREATE);
 		posix_acl_release(default_acl);
 	}
 	if (acl) {
 		if (!error)
 			error = __ext4_set_acl(handle, inode, ACL_TYPE_ACCESS,
-					       acl);
+					       acl, XATTR_CREATE);
 		posix_acl_release(acl);
 	}
 	return error;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 32191548abed..9ebde0cd632e 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1114,6 +1114,7 @@ struct ext4_inode_info {
 /*
  * Mount flags set via mount options or defaults
  */
+#define EXT4_MOUNT_NO_MBCACHE		0x00001 /* Do not use mbcache */
 #define EXT4_MOUNT_GRPID		0x00004	/* Create files with directory's group */
 #define EXT4_MOUNT_DEBUG		0x00008	/* Some debugging messages */
 #define EXT4_MOUNT_ERRORS_CONT		0x00010	/* Continue on errors */
@@ -1444,6 +1445,8 @@ struct ext4_sb_info {
 	unsigned int *s_mb_maxs;
 	unsigned int s_group_info_size;
 	unsigned int s_mb_free_pending;
+	struct list_head s_freed_data_list;	/* List of blocks to be freed
+						   after commit completed */
 
 	/* tunables */
 	unsigned long s_stripe;
@@ -1516,7 +1519,8 @@ struct ext4_sb_info {
 	struct list_head s_es_list;	/* List of inodes with reclaimable extents */
 	long s_es_nr_inode;
 	struct ext4_es_stats s_es_stats;
-	struct mb_cache *s_mb_cache;
+	struct mb_cache *s_ea_block_cache;
+	struct mb_cache *s_ea_inode_cache;
 	spinlock_t s_es_lock ____cacheline_aligned_in_smp;
 
 	/* Ratelimit ext4 messages. */
@@ -1797,10 +1801,12 @@ EXT4_FEATURE_INCOMPAT_FUNCS(encrypt,		ENCRYPT)
 					 EXT4_FEATURE_INCOMPAT_EXTENTS| \
 					 EXT4_FEATURE_INCOMPAT_64BIT| \
 					 EXT4_FEATURE_INCOMPAT_FLEX_BG| \
+					 EXT4_FEATURE_INCOMPAT_EA_INODE| \
 					 EXT4_FEATURE_INCOMPAT_MMP | \
 					 EXT4_FEATURE_INCOMPAT_INLINE_DATA | \
 					 EXT4_FEATURE_INCOMPAT_ENCRYPT | \
-					 EXT4_FEATURE_INCOMPAT_CSUM_SEED)
+					 EXT4_FEATURE_INCOMPAT_CSUM_SEED | \
+					 EXT4_FEATURE_INCOMPAT_LARGEDIR)
 #define EXT4_FEATURE_RO_COMPAT_SUPP	(EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
 					 EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
 					 EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \
@@ -2098,6 +2104,12 @@ static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc)
 	return (struct ext4_inode *) (iloc->bh->b_data + iloc->offset);
 }
 
+static inline bool ext4_is_quota_file(struct inode *inode)
+{
+	return IS_NOQUOTA(inode) &&
+	       !(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL);
+}
+
 /*
  * This structure is stuffed into the struct file's private_data field
  * for directories.  It is where we put information so that we can do
@@ -2126,6 +2138,16 @@ ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no)
  */
 #define ERR_BAD_DX_DIR	(-(MAX_ERRNO - 1))
 
+/* htree levels for ext4 */
+#define	EXT4_HTREE_LEVEL_COMPAT	2
+#define	EXT4_HTREE_LEVEL	3
+
+static inline int ext4_dir_htree_level(struct super_block *sb)
+{
+	return ext4_has_feature_largedir(sb) ?
+		EXT4_HTREE_LEVEL : EXT4_HTREE_LEVEL_COMPAT;
+}
+
 /*
  * Timeout and state flag for lazy initialization inode thread.
  */
@@ -2389,16 +2411,17 @@ extern int ext4fs_dirhash(const char *name, int len, struct
 /* ialloc.c */
 extern struct inode *__ext4_new_inode(handle_t *, struct inode *, umode_t,
 				      const struct qstr *qstr, __u32 goal,
-				      uid_t *owner, int handle_type,
-				      unsigned int line_no, int nblocks);
+				      uid_t *owner, __u32 i_flags,
+				      int handle_type, unsigned int line_no,
+				      int nblocks);
 
-#define ext4_new_inode(handle, dir, mode, qstr, goal, owner) \
+#define ext4_new_inode(handle, dir, mode, qstr, goal, owner, i_flags) \
 	__ext4_new_inode((handle), (dir), (mode), (qstr), (goal), (owner), \
-			 0, 0, 0)
+			 i_flags, 0, 0, 0)
 #define ext4_new_inode_start_handle(dir, mode, qstr, goal, owner, \
 				    type, nblocks)		    \
 	__ext4_new_inode(NULL, (dir), (mode), (qstr), (goal), (owner), \
-			 (type), __LINE__, (nblocks))
+			 0, (type), __LINE__, (nblocks))
 
 
 extern void ext4_free_inode(handle_t *, struct inode *);
@@ -2433,6 +2456,7 @@ extern int ext4_mb_add_groupinfo(struct super_block *sb,
 extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
 				ext4_fsblk_t block, unsigned long count);
 extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
+extern void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid);
 
 /* inode.c */
 int ext4_inode_is_fast_symlink(struct inode *inode);
@@ -2704,19 +2728,20 @@ extern void ext4_group_desc_csum_set(struct super_block *sb, __u32 group,
 extern int ext4_register_li_request(struct super_block *sb,
 				    ext4_group_t first_not_zeroed);
 
-static inline int ext4_has_group_desc_csum(struct super_block *sb)
-{
-	return ext4_has_feature_gdt_csum(sb) ||
-	       EXT4_SB(sb)->s_chksum_driver != NULL;
-}
-
 static inline int ext4_has_metadata_csum(struct super_block *sb)
 {
 	WARN_ON_ONCE(ext4_has_feature_metadata_csum(sb) &&
 		     !EXT4_SB(sb)->s_chksum_driver);
 
-	return (EXT4_SB(sb)->s_chksum_driver != NULL);
+	return ext4_has_feature_metadata_csum(sb) &&
+	       (EXT4_SB(sb)->s_chksum_driver != NULL);
 }
+
+static inline int ext4_has_group_desc_csum(struct super_block *sb)
+{
+	return ext4_has_feature_gdt_csum(sb) || ext4_has_metadata_csum(sb);
+}
+
 static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
 {
 	return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) |
@@ -2756,13 +2781,15 @@ static inline void ext4_r_blocks_count_set(struct ext4_super_block *es,
 	es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32);
 }
 
-static inline loff_t ext4_isize(struct ext4_inode *raw_inode)
+static inline loff_t ext4_isize(struct super_block *sb,
+				struct ext4_inode *raw_inode)
 {
-	if (S_ISREG(le16_to_cpu(raw_inode->i_mode)))
+	if (ext4_has_feature_largedir(sb) ||
+	    S_ISREG(le16_to_cpu(raw_inode->i_mode)))
 		return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) |
 			le32_to_cpu(raw_inode->i_size_lo);
-	else
-		return (loff_t) le32_to_cpu(raw_inode->i_size_lo);
+
+	return (loff_t) le32_to_cpu(raw_inode->i_size_lo);
 }
 
 static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size)
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index f97611171023..dabad1bc8617 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -77,7 +77,14 @@
 
 #define EXT4_RESERVE_TRANS_BLOCKS	12U
 
-#define EXT4_INDEX_EXTRA_TRANS_BLOCKS	8
+/*
+ * Number of credits needed if we need to insert an entry into a
+ * directory.  For each new index block, we need 4 blocks (old index
+ * block, new index block, bitmap block, bg summary).  For normal
+ * htree directories there are 2 levels; if the largedir feature
+ * enabled it's 3 levels.
+ */
+#define EXT4_INDEX_EXTRA_TRANS_BLOCKS	12U
 
 #ifdef CONFIG_QUOTA
 /* Amount of blocks needed for quota update - we know that the structure was
@@ -104,20 +111,6 @@
 #define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb))
 #define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb))
 
-static inline int ext4_jbd2_credits_xattr(struct inode *inode)
-{
-	int credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb);
-
-	/*
-	 * In case of inline data, we may push out the data to a block,
-	 * so we need to reserve credits for this eventuality
-	 */
-	if (ext4_has_inline_data(inode))
-		credits += ext4_writepage_trans_blocks(inode) + 1;
-	return credits;
-}
-
-
 /*
  * Ext4 handle operation types -- for logging purposes
  */
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 3e36508610b7..e0a8425ff74d 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2488,7 +2488,8 @@ int ext4_ext_index_trans_blocks(struct inode *inode, int extents)
 
 static inline int get_default_free_blocks_flags(struct inode *inode)
 {
-	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode) ||
+	    ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE))
 		return EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET;
 	else if (ext4_should_journal_data(inode))
 		return EXT4_FREE_BLOCKS_FORGET;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 58e2eeaa0bc4..58294c9a7e1d 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -364,13 +364,6 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
 		return -EIO;
 
-	if (ext4_encrypted_inode(inode)) {
-		int err = fscrypt_get_encryption_info(inode);
-		if (err)
-			return 0;
-		if (!fscrypt_has_encryption_key(inode))
-			return -ENOKEY;
-	}
 	file_accessed(file);
 	if (IS_DAX(file_inode(file))) {
 		vma->vm_ops = &ext4_dax_vm_ops;
diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c
index b19436098837..7ec340898598 100644
--- a/fs/ext4/fsmap.c
+++ b/fs/ext4/fsmap.c
@@ -480,6 +480,7 @@ static int ext4_getfsmap_datadev(struct super_block *sb,
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_fsblk_t start_fsb;
 	ext4_fsblk_t end_fsb;
+	ext4_fsblk_t bofs;
 	ext4_fsblk_t eofs;
 	ext4_group_t start_ag;
 	ext4_group_t end_ag;
@@ -487,9 +488,12 @@ static int ext4_getfsmap_datadev(struct super_block *sb,
 	ext4_grpblk_t last_cluster;
 	int error = 0;
 
+	bofs = le32_to_cpu(sbi->s_es->s_first_data_block);
 	eofs = ext4_blocks_count(sbi->s_es);
 	if (keys[0].fmr_physical >= eofs)
 		return 0;
+	else if (keys[0].fmr_physical < bofs)
+		keys[0].fmr_physical = bofs;
 	if (keys[1].fmr_physical >= eofs)
 		keys[1].fmr_physical = eofs - 1;
 	start_fsb = keys[0].fmr_physical;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 98ac2f1f23b3..507bfb3344d4 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -294,7 +294,6 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 	 * as writing the quota to disk may need the lock as well.
 	 */
 	dquot_initialize(inode);
-	ext4_xattr_delete_inode(handle, inode);
 	dquot_free_inode(inode);
 	dquot_drop(inode);
 
@@ -743,8 +742,9 @@ out:
  */
 struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 			       umode_t mode, const struct qstr *qstr,
-			       __u32 goal, uid_t *owner, int handle_type,
-			       unsigned int line_no, int nblocks)
+			       __u32 goal, uid_t *owner, __u32 i_flags,
+			       int handle_type, unsigned int line_no,
+			       int nblocks)
 {
 	struct super_block *sb;
 	struct buffer_head *inode_bitmap_bh = NULL;
@@ -766,30 +766,69 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 	if (!dir || !dir->i_nlink)
 		return ERR_PTR(-EPERM);
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
+	sb = dir->i_sb;
+	sbi = EXT4_SB(sb);
+
+	if (unlikely(ext4_forced_shutdown(sbi)))
 		return ERR_PTR(-EIO);
 
-	if ((ext4_encrypted_inode(dir) ||
-	     DUMMY_ENCRYPTION_ENABLED(EXT4_SB(dir->i_sb))) &&
-	    (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) {
+	if ((ext4_encrypted_inode(dir) || DUMMY_ENCRYPTION_ENABLED(sbi)) &&
+	    (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) &&
+	    !(i_flags & EXT4_EA_INODE_FL)) {
 		err = fscrypt_get_encryption_info(dir);
 		if (err)
 			return ERR_PTR(err);
 		if (!fscrypt_has_encryption_key(dir))
 			return ERR_PTR(-ENOKEY);
-		if (!handle)
-			nblocks += EXT4_DATA_TRANS_BLOCKS(dir->i_sb);
 		encrypt = 1;
 	}
 
-	sb = dir->i_sb;
+	if (!handle && sbi->s_journal && !(i_flags & EXT4_EA_INODE_FL)) {
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
+		struct posix_acl *p = get_acl(dir, ACL_TYPE_DEFAULT);
+
+		if (p) {
+			int acl_size = p->a_count * sizeof(ext4_acl_entry);
+
+			nblocks += (S_ISDIR(mode) ? 2 : 1) *
+				__ext4_xattr_set_credits(sb, NULL /* inode */,
+					NULL /* block_bh */, acl_size,
+					true /* is_create */);
+			posix_acl_release(p);
+		}
+#endif
+
+#ifdef CONFIG_SECURITY
+		{
+			int num_security_xattrs = 1;
+
+#ifdef CONFIG_INTEGRITY
+			num_security_xattrs++;
+#endif
+			/*
+			 * We assume that security xattrs are never
+			 * more than 1k.  In practice they are under
+			 * 128 bytes.
+			 */
+			nblocks += num_security_xattrs *
+				__ext4_xattr_set_credits(sb, NULL /* inode */,
+					NULL /* block_bh */, 1024,
+					true /* is_create */);
+		}
+#endif
+		if (encrypt)
+			nblocks += __ext4_xattr_set_credits(sb,
+					NULL /* inode */, NULL /* block_bh */,
+					FSCRYPT_SET_CONTEXT_MAX_SIZE,
+					true /* is_create */);
+	}
+
 	ngroups = ext4_get_groups_count(sb);
 	trace_ext4_request_inode(dir, mode);
 	inode = new_inode(sb);
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
 	ei = EXT4_I(inode);
-	sbi = EXT4_SB(sb);
 
 	/*
 	 * Initialize owners and quota early so that we don't have to account
@@ -1053,6 +1092,7 @@ got:
 	/* Don't inherit extent flag from directory, amongst others. */
 	ei->i_flags =
 		ext4_mask_flags(mode, EXT4_I(dir)->i_flags & EXT4_FL_INHERITED);
+	ei->i_flags |= i_flags;
 	ei->i_file_acl = 0;
 	ei->i_dtime = 0;
 	ei->i_block_group = group;
@@ -1109,13 +1149,15 @@ got:
 			goto fail_free_drop;
 	}
 
-	err = ext4_init_acl(handle, inode, dir);
-	if (err)
-		goto fail_free_drop;
+	if (!(ei->i_flags & EXT4_EA_INODE_FL)) {
+		err = ext4_init_acl(handle, inode, dir);
+		if (err)
+			goto fail_free_drop;
 
-	err = ext4_init_security(handle, inode, dir, qstr);
-	if (err)
-		goto fail_free_drop;
+		err = ext4_init_security(handle, inode, dir, qstr);
+		if (err)
+			goto fail_free_drop;
+	}
 
 	if (ext4_has_feature_extents(sb)) {
 		/* set extent flag only for directory, file and normal symlink*/
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index bc15c2c17633..7ffa290cbb8e 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -829,7 +829,8 @@ static int ext4_clear_blocks(handle_t *handle, struct inode *inode,
 	int	flags = EXT4_FREE_BLOCKS_VALIDATED;
 	int	err;
 
-	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode) ||
+	    ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE))
 		flags |= EXT4_FREE_BLOCKS_FORGET | EXT4_FREE_BLOCKS_METADATA;
 	else if (ext4_should_journal_data(inode))
 		flags |= EXT4_FREE_BLOCKS_FORGET;
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 8d141c0c8ff9..28c5c3abddb3 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -61,7 +61,7 @@ static int get_max_inline_xattr_value_size(struct inode *inode,
 
 	/* Compute min_offs. */
 	for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) {
-		if (!entry->e_value_block && entry->e_value_size) {
+		if (!entry->e_value_inum && entry->e_value_size) {
 			size_t offs = le16_to_cpu(entry->e_value_offs);
 			if (offs < min_offs)
 				min_offs = offs;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 5cf82d03968c..3c600f02673f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -144,16 +144,12 @@ static int ext4_meta_trans_blocks(struct inode *inode, int lblocks,
 
 /*
  * Test whether an inode is a fast symlink.
+ * A fast symlink has its symlink data stored in ext4_inode_info->i_data.
  */
 int ext4_inode_is_fast_symlink(struct inode *inode)
 {
-        int ea_blocks = EXT4_I(inode)->i_file_acl ?
-		EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0;
-
-	if (ext4_has_inline_data(inode))
-		return 0;
-
-	return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0);
+	return S_ISLNK(inode->i_mode) && inode->i_size &&
+	       (inode->i_size < EXT4_N_BLOCKS * 4);
 }
 
 /*
@@ -189,6 +185,8 @@ void ext4_evict_inode(struct inode *inode)
 {
 	handle_t *handle;
 	int err;
+	int extra_credits = 3;
+	struct ext4_xattr_inode_array *ea_inode_array = NULL;
 
 	trace_ext4_evict_inode(inode);
 
@@ -213,7 +211,8 @@ void ext4_evict_inode(struct inode *inode)
 		 */
 		if (inode->i_ino != EXT4_JOURNAL_INO &&
 		    ext4_should_journal_data(inode) &&
-		    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) {
+		    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) &&
+		    inode->i_data.nrpages) {
 			journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
 			tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
 
@@ -238,8 +237,12 @@ void ext4_evict_inode(struct inode *inode)
 	 * protection against it
 	 */
 	sb_start_intwrite(inode->i_sb);
+
+	if (!IS_NOQUOTA(inode))
+		extra_c