Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kern…

…el/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:

 - Add support for online resizing of file systems with bigalloc

 - Fix a two data corruption bugs involving DAX, as well as a corruption
   bug after a crash during a racing fallocate and delayed allocation.

 - Finally, a number of cleanups and optimizations.

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: improve smp scalability for inode generation
  ext4: add support for online resizing with bigalloc
  ext4: mention noload when recovering on read-only device
  Documentation: fix little inconsistencies
  ext4: convert timers to use timer_setup()
  jbd2: convert timers to use timer_setup()
  ext4: remove duplicate extended attributes defs
  ext4: add ext4_should_use_dax()
  ext4: add sanity check for encryption + DAX
  ext4: prevent data corruption with journaling + DAX
  ext4: prevent data corruption with inline data + DAX
  ext4: fix interaction between i_size, fallocate, and delalloc after a crash
  ext4: retry allocations conservatively
  ext4: Switch to iomap for SEEK_HOLE / SEEK_DATA
  ext4: Add iomap support for inline data
  iomap: Add IOMAP_F_DATA_INLINE flag
  iomap: Switch from blkno to disk offset

fs/buffer.c

@@ -1979,8 +1979,8 @@ iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh,
 	case IOMAP_MAPPED:
 		if (offset >= i_size_read(inode))
 			set_buffer_new(bh);
-		bh->b_blocknr = (iomap->blkno >> (inode->i_blkbits - 9)) +
-				((offset - iomap->offset) >> inode->i_blkbits);
+		bh->b_blocknr = (iomap->addr + offset - iomap->offset) >>
+				inode->i_blkbits;
 		set_buffer_mapped(bh);
 		break;
 	}

fs/dax.c

@@ -938,7 +938,7 @@ EXPORT_SYMBOL_GPL(__dax_zero_page_range);
 
 static sector_t dax_iomap_sector(struct iomap *iomap, loff_t pos)
 {
-	return iomap->blkno + (((pos & PAGE_MASK) - iomap->offset) >> 9);
+	return (iomap->addr + (pos & PAGE_MASK) - iomap->offset) >> 9;
 }
 
 static loff_t

fs/ext2/inode.c

@@ -821,11 +821,11 @@ static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 
 	if (ret == 0) {
 		iomap->type = IOMAP_HOLE;
-		iomap->blkno = IOMAP_NULL_BLOCK;
+		iomap->addr = IOMAP_NULL_ADDR;
 		iomap->length = 1 << blkbits;
 	} else {
 		iomap->type = IOMAP_MAPPED;
-		iomap->blkno = (sector_t)bno << (blkbits - 9);
+		iomap->addr = (u64)bno << blkbits;
 		iomap->length = (u64)ret << blkbits;
 		iomap->flags |= IOMAP_F_MERGED;
 	}

fs/ext4/Kconfig

@@ -37,6 +37,7 @@ config EXT4_FS
 	select CRC16
 	select CRYPTO
 	select CRYPTO_CRC32C
+	select FS_IOMAP
 	help
 	  This is the next generation of the ext3 filesystem.
 

fs/ext4/balloc.c

@@ -601,22 +601,21 @@ int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
  * ext4_should_retry_alloc() is called when ENOSPC is returned, and if
  * it is profitable to retry the operation, this function will wait
  * for the current or committing transaction to complete, and then
- * return TRUE.
- *
- * if the total number of retries exceed three times, return FALSE.
+ * return TRUE.  We will only retry once.
  */
 int ext4_should_retry_alloc(struct super_block *sb, int *retries)
 {
 	if (!ext4_has_free_clusters(EXT4_SB(sb), 1, 0) ||
-	    (*retries)++ > 3 ||
+	    (*retries)++ > 1 ||
 	    !EXT4_SB(sb)->s_journal)
 		return 0;
 
-	jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id);
-
 	smp_mb();
-	if (EXT4_SB(sb)->s_mb_free_pending)
-		jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
+	if (EXT4_SB(sb)->s_mb_free_pending == 0)
+		return 0;
+
+	jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id);
+	jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
 	return 1;
 }
 

fs/ext4/ext4.h

@@ -544,8 +544,8 @@ struct ext4_new_group_data {
 	__u64 inode_table;
 	__u32 blocks_count;
 	__u16 reserved_blocks;
-	__u16 unused;
-	__u32 free_blocks_count;
+	__u16 mdata_blocks;
+	__u32 free_clusters_count;
 };
 
 /* Indexes used to index group tables in ext4_new_group_data */
@@ -643,43 +643,6 @@ enum {
 #define EXT4_IOC_GET_ENCRYPTION_PWSALT	FS_IOC_GET_ENCRYPTION_PWSALT
 #define EXT4_IOC_GET_ENCRYPTION_POLICY	FS_IOC_GET_ENCRYPTION_POLICY
 
-#ifndef FS_IOC_FSGETXATTR
-/* Until the uapi changes get merged for project quota... */
-
-#define FS_IOC_FSGETXATTR		_IOR('X', 31, struct fsxattr)
-#define FS_IOC_FSSETXATTR		_IOW('X', 32, struct fsxattr)
-
-/*
- * Structure for FS_IOC_FSGETXATTR and FS_IOC_FSSETXATTR.
- */
-struct fsxattr {
-	__u32		fsx_xflags;	/* xflags field value (get/set) */
-	__u32		fsx_extsize;	/* extsize field value (get/set)*/
-	__u32		fsx_nextents;	/* nextents field value (get)	*/
-	__u32		fsx_projid;	/* project identifier (get/set) */
-	unsigned char	fsx_pad[12];
-};
-
-/*
- * Flags for the fsx_xflags field
- */
-#define FS_XFLAG_REALTIME	0x00000001	/* data in realtime volume */
-#define FS_XFLAG_PREALLOC	0x00000002	/* preallocated file extents */
-#define FS_XFLAG_IMMUTABLE	0x00000008	/* file cannot be modified */
-#define FS_XFLAG_APPEND		0x00000010	/* all writes append */
-#define FS_XFLAG_SYNC		0x00000020	/* all writes synchronous */
-#define FS_XFLAG_NOATIME	0x00000040	/* do not update access time */
-#define FS_XFLAG_NODUMP		0x00000080	/* do not include in backups */
-#define FS_XFLAG_RTINHERIT	0x00000100	/* create with rt bit set */
-#define FS_XFLAG_PROJINHERIT	0x00000200	/* create with parents projid */
-#define FS_XFLAG_NOSYMLINKS	0x00000400	/* disallow symlink creation */
-#define FS_XFLAG_EXTSIZE	0x00000800	/* extent size allocator hint */
-#define FS_XFLAG_EXTSZINHERIT	0x00001000	/* inherit inode extent size */
-#define FS_XFLAG_NODEFRAG	0x00002000  	/* do not defragment */
-#define FS_XFLAG_FILESTREAM	0x00004000	/* use filestream allocator */
-#define FS_XFLAG_HASATTR	0x80000000	/* no DIFLAG for this */
-#endif /* !defined(FS_IOC_FSGETXATTR) */
-
 #define EXT4_IOC_FSGETXATTR		FS_IOC_FSGETXATTR
 #define EXT4_IOC_FSSETXATTR		FS_IOC_FSSETXATTR
 
@@ -1391,8 +1354,6 @@ struct ext4_sb_info {
 	int s_first_ino;
 	unsigned int s_inode_readahead_blks;
 	unsigned int s_inode_goal;
-	spinlock_t s_next_gen_lock;
-	u32 s_next_generation;
 	u32 s_hash_seed[4];
 	int s_def_hash_version;
 	int s_hash_unsigned;	/* 3 if hash should be signed, 0 if not */
@@ -2514,9 +2475,6 @@ extern void ext4_da_update_reserve_space(struct inode *inode,
 					int used, int quota_claim);
 extern int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk,
 			      ext4_fsblk_t pblk, ext4_lblk_t len);
-extern int ext4_get_next_extent(struct inode *inode, ext4_lblk_t lblk,
-				unsigned int map_len,
-				struct extent_status *result);
 
 /* indirect.c */
 extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
@@ -3047,6 +3005,10 @@ extern struct buffer_head *ext4_get_first_inline_block(struct inode *inode,
 extern int ext4_inline_data_fiemap(struct inode *inode,
 				   struct fiemap_extent_info *fieinfo,
 				   int *has_inline, __u64 start, __u64 len);
+
+struct iomap;
+extern int ext4_inline_data_iomap(struct inode *inode, struct iomap *iomap);
+
 extern int ext4_try_to_evict_inline_data(handle_t *handle,
 					 struct inode *inode,
 					 int needed);

fs/ext4/extents.c

@@ -4794,7 +4794,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	}
 
 	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
-	     offset + len > i_size_read(inode)) {
+	    (offset + len > i_size_read(inode) ||
+	     offset + len > EXT4_I(inode)->i_disksize)) {
 		new_size = offset + len;
 		ret = inode_newsize_ok(inode, new_size);
 		if (ret)
@@ -4965,7 +4966,8 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	}
 
 	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
-	     offset + len > i_size_read(inode)) {
+	    (offset + len > i_size_read(inode) ||
+	     offset + len > EXT4_I(inode)->i_disksize)) {
 		new_size = offset + len;
 		ret = inode_newsize_ok(inode, new_size);
 		if (ret)