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

fs/ext4/file.c

@@ -21,6 +21,7 @@
 
 #include <linux/time.h>
 #include <linux/fs.h>
+#include <linux/iomap.h>
 #include <linux/mount.h>
 #include <linux/path.h>
 #include <linux/dax.h>
@@ -423,248 +424,6 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 	return dquot_file_open(inode, filp);
 }
 
-/*
- * Here we use ext4_map_blocks() to get a block mapping for a extent-based
- * file rather than ext4_ext_walk_space() because we can introduce
- * SEEK_DATA/SEEK_HOLE for block-mapped and extent-mapped file at the same
- * function.  When extent status tree has been fully implemented, it will
- * track all extent status for a file and we can directly use it to
- * retrieve the offset for SEEK_DATA/SEEK_HOLE.
- */
-
-/*
- * When we retrieve the offset for SEEK_DATA/SEEK_HOLE, we would need to
- * lookup page cache to check whether or not there has some data between
- * [startoff, endoff] because, if this range contains an unwritten extent,
- * we determine this extent as a data or a hole according to whether the
- * page cache has data or not.
- */
-static int ext4_find_unwritten_pgoff(struct inode *inode,
-				     int whence,
-				     ext4_lblk_t end_blk,
-				     loff_t *offset)
-{
-	struct pagevec pvec;
-	unsigned int blkbits;
-	pgoff_t index;
-	pgoff_t end;
-	loff_t endoff;
-	loff_t startoff;
-	loff_t lastoff;
-	int found = 0;
-
-	blkbits = inode->i_sb->s_blocksize_bits;
-	startoff = *offset;
-	lastoff = startoff;
-	endoff = (loff_t)end_blk << blkbits;
-
-	index = startoff >> PAGE_SHIFT;
-	end = (endoff - 1) >> PAGE_SHIFT;
-
-	pagevec_init(&pvec, 0);
-	do {
-		int i;
-		unsigned long nr_pages;
-
-		nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping,
-					&index, end);
-		if (nr_pages == 0)
-			break;
-
-		for (i = 0; i < nr_pages; i++) {
-			struct page *page = pvec.pages[i];
-			struct buffer_head *bh, *head;
-
-			/*
-			 * If current offset is smaller than the page offset,
-			 * there is a hole at this offset.
-			 */
-			if (whence == SEEK_HOLE && lastoff < endoff &&
-			    lastoff < page_offset(pvec.pages[i])) {
-				found = 1;
-				*offset = lastoff;
-				goto out;
-			}
-
-			lock_page(page);
-
-			if (unlikely(page->mapping != inode->i_mapping)) {
-				unlock_page(page);
-				continue;
-			}
-
-			if (!page_has_buffers(page)) {
-				unlock_page(page);
-				continue;
-			}
-
-			if (page_has_buffers(page)) {
-				lastoff = page_offset(page);
-				bh = head = page_buffers(page);
-				do {
-					if (lastoff + bh->b_size <= startoff)
-						goto next;
-					if (buffer_uptodate(bh) ||
-					    buffer_unwritten(bh)) {
-						if (whence == SEEK_DATA)
-							found = 1;
-					} else {
-						if (whence == SEEK_HOLE)
-							found = 1;
-					}
-					if (found) {
-						*offset = max_t(loff_t,
-							startoff, lastoff);
-						unlock_page(page);
-						goto out;
-					}
-next:
-					lastoff += bh->b_size;
-					bh = bh->b_this_page;
-				} while (bh != head);
-			}
-
-			lastoff = page_offset(page) + PAGE_SIZE;
-			unlock_page(page);
-		}
-
-		pagevec_release(&pvec);
-	} while (index <= end);
-
-	/* There are no pages upto endoff - that would be a hole in there. */
-	if (whence == SEEK_HOLE && lastoff < endoff) {
-		found = 1;
-		*offset = lastoff;
-	}
-out:
-	pagevec_release(&pvec);
-	return found;
-}
-
-/*
- * ext4_seek_data() retrieves the offset for SEEK_DATA.
- */
-static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize)
-{
-	struct inode *inode = file->f_mapping->host;
-	struct extent_status es;
-	ext4_lblk_t start, last, end;
-	loff_t dataoff, isize;
-	int blkbits;
-	int ret;
-
-	inode_lock(inode);
-
-	isize = i_size_read(inode);
-	if (offset < 0 || offset >= isize) {
-		inode_unlock(inode);
-		return -ENXIO;
-	}
-
-	blkbits = inode->i_sb->s_blocksize_bits;
-	start = offset >> blkbits;
-	last = start;
-	end = isize >> blkbits;
-	dataoff = offset;
-
-	do {
-		ret = ext4_get_next_extent(inode, last, end - last + 1, &es);
-		if (ret <= 0) {
-			/* No extent found -> no data */
-			if (ret == 0)
-				ret = -ENXIO;
-			inode_unlock(inode);
-			return ret;
-		}
-
-		last = es.es_lblk;
-		if (last != start)
-			dataoff = (loff_t)last << blkbits;
-		if (!ext4_es_is_unwritten(&es))
-			break;
-
-		/*
-		 * If there is a unwritten extent at this offset,
-		 * it will be as a data or a hole according to page
-		 * cache that has data or not.
-		 */
-		if (ext4_find_unwritten_pgoff(inode, SEEK_DATA,
-					      es.es_lblk + es.es_len, &dataoff))
-			break;
-		last += es.es_len;
-		dataoff = (loff_t)last << blkbits;
-		cond_resched();
-	} while (last <= end);
-
-	inode_unlock(inode);
-
-	if (dataoff > isize)
-		return -ENXIO;
-
-	return vfs_setpos(file, dataoff, maxsize);
-}
-
-/*
- * ext4_seek_hole() retrieves the offset for SEEK_HOLE.
- */
-static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize)
-{
-	struct inode *inode = file->f_mapping->host;
-	struct extent_status es;
-	ext4_lblk_t start, last, end;
-	loff_t holeoff, isize;
-	int blkbits;
-	int ret;
-
-	inode_lock(inode);
-
-	isize = i_size_read(inode);
-	if (offset < 0 || offset >= isize) {
-		inode_unlock(inode);
-		return -ENXIO;
-	}
-
-	blkbits = inode->i_sb->s_blocksize_bits;
-	start = offset >> blkbits;
-	last = start;
-	end = isize >> blkbits;
-	holeoff = offset;
-
-	do {
-		ret = ext4_get_next_extent(inode, last, end - last + 1, &es);
-		if (ret < 0) {
-			inode_unlock(inode);
-			return ret;
-		}
-		/* Found a hole? */
-		if (ret == 0 || es.es_lblk > last) {
-			if (last != start)
-				holeoff = (loff_t)last << blkbits;
-			break;
-		}
-		/*
-		 * If there is a unwritten extent at this offset,
-		 * it will be as a data or a hole according to page
-		 * cache that has data or not.
-		 */
-		if (ext4_es_is_unwritten(&es) &&
-		    ext4_find_unwritten_pgoff(inode, SEEK_HOLE,
-					      last + es.es_len, &holeoff))
-			break;
-
-		last += es.es_len;
-		holeoff = (loff_t)last << blkbits;
-		cond_resched();
-	} while (last <= end);
-
-	inode_unlock(inode);
-
-	if (holeoff > isize)
-		holeoff = isize;
-
-	return vfs_setpos(file, holeoff, maxsize);
-}
-
 /*
  * ext4_llseek() handles both block-mapped and extent-mapped maxbytes values
  * by calling generic_file_llseek_size() with the appropriate maxbytes
@@ -681,18 +440,24 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int whence)
 		maxbytes = inode->i_sb->s_maxbytes;
 
 	switch (whence) {
-	case SEEK_SET:
-	case SEEK_CUR:
-	case SEEK_END:
+	default:
 		return generic_file_llseek_size(file, offset, whence,
 						maxbytes, i_size_read(inode));
-	case SEEK_DATA:
-		return ext4_seek_data(file, offset, maxbytes);
 	case SEEK_HOLE:
-		return ext4_seek_hole(file, offset, maxbytes);
+		inode_lock_shared(inode);
+		offset = iomap_seek_hole(inode, offset, &ext4_iomap_ops);
+		inode_unlock_shared(inode);
+		break;
+	case SEEK_DATA:
+		inode_lock_shared(inode);
+		offset = iomap_seek_data(inode, offset, &ext4_iomap_ops);
+		inode_unlock_shared(inode);
+		break;
 	}
 
-	return -EINVAL;
+	if (offset < 0)
+		return offset;
+	return vfs_setpos(file, offset, maxbytes);
 }
 
 const struct file_operations ext4_file_operations = {

fs/ext4/ialloc.c

@@ -1139,9 +1139,7 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 			   inode->i_ino);
 		goto out;
 	}
-	spin_lock(&sbi->s_next_gen_lock);
-	inode->i_generation = sbi->s_next_generation++;
-	spin_unlock(&sbi->s_next_gen_lock);
+	inode->i_generation = prandom_u32();
 
 	/* Precompute checksum seed for inode metadata */
 	if (ext4_has_metadata_csum(sb)) {

fs/ext4/inline.c

@@ -12,6 +12,7 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/iomap.h>
 #include <linux/fiemap.h>
 
 #include "ext4_jbd2.h"
@@ -302,11 +303,6 @@ static int ext4_create_inline_data(handle_t *handle,
 	EXT4_I(inode)->i_inline_size = len + EXT4_MIN_INLINE_DATA_SIZE;
 	ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
 	ext4_set_inode_flag(inode, EXT4_INODE_INLINE_DATA);
-	/*
-	 * Propagate changes to inode->i_flags as well - e.g. S_DAX may
-	 * get cleared
-	 */
-	ext4_set_inode_flags(inode);
 	get_bh(is.iloc.bh);
 	error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
 
@@ -451,11 +447,6 @@ static int ext4_destroy_inline_data_nolock(handle_t *handle,
 		}
 	}
 	ext4_clear_inode_flag(inode, EXT4_INODE_INLINE_DATA);
-	/*
-	 * Propagate changes to inode->i_flags as well - e.g. S_DAX may
-	 * get set.
-	 */
-	ext4_set_inode_flags(inode);
 
 	get_bh(is.iloc.bh);
 	error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
@@ -1827,6 +1818,38 @@ int ext4_destroy_inline_data(handle_t *handle, struct inode *inode)
 	return ret;
 }
 
+int ext4_inline_data_iomap(struct inode *inode, struct iomap *iomap)
+{
+	__u64 addr;
+	int error = -EAGAIN;
+	struct ext4_iloc iloc;
+
+	down_read(&EXT4_I(inode)->xattr_sem);
+	if (!ext4_has_inline_data(inode))
+		goto out;
+
+	error = ext4_get_inode_loc(inode, &iloc);
+	if (error)
+		goto out;
+
+	addr = (__u64)iloc.bh->b_blocknr << inode->i_sb->s_blocksize_bits;
+	addr += (char *)ext4_raw_inode(&iloc) - iloc.bh->b_data;
+	addr += offsetof(struct ext4_inode, i_block);
+
+	brelse(iloc.bh);
+
+	iomap->addr = addr;
+	iomap->offset = 0;
+	iomap->length = min_t(loff_t, ext4_get_inline_size(inode),
+			      i_size_read(inode));
+	iomap->type = 0;
+	iomap->flags = IOMAP_F_DATA_INLINE;
+
+out:
+	up_read(&EXT4_I(inode)->xattr_sem);
+	return error;
+}
+
 int ext4_inline_data_fiemap(struct inode *inode,
 			    struct fiemap_extent_info *fieinfo,
 			    int *has_inline, __u64 start, __u64 len)

fs/ext4/inode.c

@@ -3394,7 +3394,6 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
 		return try_to_free_buffers(page);
 }
 
-#ifdef CONFIG_FS_DAX
 static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 			    unsigned flags, struct iomap *iomap)
 {
@@ -3403,17 +3402,54 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	unsigned long first_block = offset >> blkbits;
 	unsigned long last_block = (offset + length - 1) >> blkbits;
 	struct ext4_map_blocks map;
+	bool delalloc = false;
 	int ret;
 
-	if (WARN_ON_ONCE(ext4_has_inline_data(inode)))
-		return -ERANGE;
+
+	if (flags & IOMAP_REPORT) {
+		if (ext4_has_inline_data(inode)) {
+			ret = ext4_inline_data_iomap(inode, iomap);
+			if (ret != -EAGAIN) {
+				if (ret == 0 && offset >= iomap->length)
+					ret = -ENOENT;
+				return ret;
+			}
+		}
+	} else {
+		if (WARN_ON_ONCE(ext4_has_inline_data(inode)))
+			return -ERANGE;
+	}
 
 	map.m_lblk = first_block;
 	map.m_len = last_block - first_block + 1;
 
-	if (!(flags & IOMAP_WRITE)) {
+	if (flags & IOMAP_REPORT) {
 		ret = ext4_map_blocks(NULL, inode, &map, 0);
-	} else {
+		if (ret < 0)
+			return ret;
+
+		if (ret == 0) {
+			ext4_lblk_t end = map.m_lblk + map.m_len - 1;
+			struct extent_status es;
+
+			ext4_es_find_delayed_extent_range(inode, map.m_lblk, end, &es);
+
+			if (!es.es_len || es.es_lblk > end) {
+				/* entire range is a hole */
+			} else if (es.es_lblk > map.m_lblk) {
+				/* range starts with a hole */
+				map.m_len = es.es_lblk - map.m_lblk;
+			} else {
+				ext4_lblk_t offs = 0;
+
+				if (es.es_lblk < map.m_lblk)
+					offs = map.m_lblk - es.es_lblk;
+				map.m_lblk = es.es_lblk + offs;
+				map.m_len = es.es_len - offs;
+				delalloc = true;
+			}
+		}
+	} else if (flags & IOMAP_WRITE) {
 		int dio_credits;
 		handle_t *handle;
 		int retries = 0;
@@ -3464,17 +3500,21 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 			}
 		}
 		ext4_journal_stop(handle);
+	} else {
+		ret = ext4_map_blocks(NULL, inode, &map, 0);
+		if (ret < 0)
+			return ret;
 	}
 
 	iomap->flags = 0;
 	iomap->bdev = inode->i_sb->s_bdev;
 	iomap->dax_dev = sbi->s_daxdev;
 	iomap->offset = first_block << blkbits;
+	iomap->length = (u64)map.m_len << blkbits;
 
 	if (ret == 0) {
-		iomap->type = IOMAP_HOLE;
-		iomap->blkno = IOMAP_NULL_BLOCK;
-		iomap->length = (u64)map.m_len << blkbits;
+		iomap->type = delalloc ? IOMAP_DELALLOC : IOMAP_HOLE;
+		iomap->addr = IOMAP_NULL_ADDR;
 	} else {
 		if (map.m_flags & EXT4_MAP_MAPPED) {
 			iomap->type = IOMAP_MAPPED;
@@ -3484,12 +3524,12 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 			WARN_ON_ONCE(1);
 			return -EIO;
 		}
-		iomap->blkno = (sector_t)map.m_pblk << (blkbits - 9);
-		iomap->length = (u64)map.m_len << blkbits;
+		iomap->addr = (u64)map.m_pblk << blkbits;
 	}
 
 	if (map.m_flags & EXT4_MAP_NEW)
 		iomap->flags |= IOMAP_F_NEW;
+
 	return 0;
 }
 
@@ -3550,8 +3590,6 @@ const struct iomap_ops ext4_iomap_ops = {
 	.iomap_end		= ext4_iomap_end,
 };
 
-#endif
-
 static int ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
 			    ssize_t size, void *private)
 {
@@ -4573,6 +4611,21 @@ int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc)
 		!ext4_test_inode_state(inode, EXT4_STATE_XATTR));
 }
 
+static bool ext4_should_use_dax(struct inode *inode)
+{
+	if (!test_opt(inode->i_sb, DAX))
+		return false;
+	if (!S_ISREG(inode->i_mode))
+		return false;
+	if (ext4_should_journal_data(inode))
+		return false;
+	if (ext4_has_inline_data(inode))
+		return false;
+	if (ext4_encrypted_inode(inode))
+		return false;
+	return true;
+}
+
 void ext4_set_inode_flags(struct inode *inode)
 {
 	unsigned int flags = EXT4_I(inode)->i_flags;
@@ -4588,9 +4641,7 @@ void ext4_set_inode_flags(struct inode *inode)
 		new_fl |= S_NOATIME;
 	if (flags & EXT4_DIRSYNC_FL)
 		new_fl |= S_DIRSYNC;
-	if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode) &&
-	    !ext4_should_journal_data(inode) && !ext4_has_inline_data(inode) &&
-	    !(flags & EXT4_ENCRYPT_FL))
+	if (ext4_should_use_dax(inode))
 		new_fl |= S_DAX;
 	if (flags & EXT4_ENCRYPT_FL)
 		new_fl |= S_ENCRYPTED;
@@ -5966,11 +6017,6 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 		ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
 	}
 	ext4_set_aops(inode);
-	/*
-	 * Update inode->i_flags after EXT4_INODE_JOURNAL_DATA was updated.
-	 * E.g. S_DAX may get cleared / set.
-	 */
-	ext4_set_inode_flags(inode);
 
 	jbd2_journal_unlock_updates(journal);
 	percpu_up_write(&sbi->s_journal_flag_rwsem);
@@ -6106,70 +6152,3 @@ int ext4_filemap_fault(struct vm_fault *vmf)
 
 	return err;
 }
-
-/*
- * Find the first extent at or after @lblk in an inode that is not a hole.
- * Search for @map_len blocks at most. The extent is returned in @result.
- *
- * The function returns 1 if we found an extent. The function returns 0 in
- * case there is no extent at or after @lblk and in that case also sets
- * @result->es_len to 0. In case of error, the error code is returned.
- */
-int ext4_get_next_extent(struct inode *inode, ext4_lblk_t lblk,
-			 unsigned int map_len, struct extent_status *result)
-{
-	struct ext4_map_blocks map;
-	struct extent_status es = {};
-	int ret;
-
-	map.m_lblk = lblk;
-	map.m_len = map_len;
-
-	/*
-	 * For non-extent based files this loop may iterate several times since
-	 * we do not determine full hole size.
-	 */
-	while (map.m_len > 0) {
-		ret = ext4_map_blocks(NULL, inode, &map, 0);
-		if (ret < 0)
-			return ret;
-		/* There's extent covering m_lblk? Just return it. */
-		if (ret > 0) {
-			int status;
-
-			ext4_es_store_pblock(result, map.m_pblk);
-			result->es_lblk = map.m_lblk;
-			result->es_len = map.m_len;
-			if (map.m_flags & EXT4_MAP_UNWRITTEN)
-				status = EXTENT_STATUS_UNWRITTEN;
-			else
-				status = EXTENT_STATUS_WRITTEN;
-			ext4_es_store_status(result, status);
-			return 1;
-		}
-		ext4_es_find_delayed_extent_range(inode, map.m_lblk,
-						  map.m_lblk + map.m_len - 1,
-						  &es);
-		/* Is delalloc data before next block in extent tree? */
-		if (es.es_len && es.es_lblk < map.m_lblk + map.m_len) {
-			ext4_lblk_t offset = 0;
-
-			if (es.es_lblk < lblk)
-				offset = lblk - es.es_lblk;
-			result->es_lblk = es.es_lblk + offset;
-			ext4_es_store_pblock(result,
-					     ext4_es_pblock(&es) + offset);
-			result->es_len = es.es_len - offset;
-			ext4_es_store_status(result, ext4_es_status(&es));
-
-			return 1;
-		}
-		/* There's a hole at m_lblk, advance us after it */
-		map.m_lblk += map.m_len;
-		map_len -= map.m_len;
-		map.m_len = map_len;
-		cond_resched();
-	}
-	result->es_len = 0;
-	return 0;
-}

fs/ext4/ioctl.c

@@ -15,6 +15,7 @@
 #include <linux/mount.h>
 #include <linux/file.h>
 #include <linux/quotaops.h>
+#include <linux/random.h>
 #include <linux/uuid.h>
 #include <linux/uaccess.h>
 #include <linux/delay.h>
@@ -99,7 +100,6 @@ static long swap_inode_boot_loader(struct super_block *sb,
 	int err;
 	struct inode *inode_bl;
 	struct ext4_inode_info *ei_bl;
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode))
 		return -EINVAL;
@@ -158,10 +158,8 @@ static long swap_inode_boot_loader(struct super_block *sb,
 
 	inode->i_ctime = inode_bl->i_ctime = current_time(inode);
 
-	spin_lock(&sbi->s_next_gen_lock);
-	inode->i_generation = sbi->s_next_generation++;
-	inode_bl->i_generation = sbi->s_next_generation++;
-	spin_unlock(&sbi->s_next_gen_lock);
+	inode->i_generation = prandom_u32();
+	inode_bl->i_generation = prandom_u32();
 
 	ext4_discard_preallocations(inode);
 
@@ -291,10 +289,20 @@ static int ext4_ioctl_setflags(struct inode *inode,
 	if (err)
 		goto flags_out;
 
-	if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL))
+	if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
+		/*
+		 * Changes to the journaling mode can cause unsafe changes to
+		 * S_DAX if we are using the DAX mount option.
+		 */
+		if (test_opt(inode->i_sb, DAX)) {
+			err = -EBUSY;
+			goto flags_out;
+		}
+
 		err = ext4_change_inode_journal_flag(inode, jflag);
-	if (err)
-		goto flags_out;
+		if (err)
+			goto flags_out;
+	}
 	if (migrate) {
 		if (flags & EXT4_EXTENTS_FL)
 			err = ext4_ext_migrate(inode);
@@ -862,12 +870,6 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		int err = 0, err2 = 0;
 		ext4_group_t o_group = EXT4_SB(sb)->s_groups_count;
 
-		if (ext4_has_feature_bigalloc(sb)) {
-			ext4_msg(sb, KERN_ERR,
-				 "Online resizing not (yet) supported with bigalloc");
-			return -EOPNOTSUPP;
-		}
-
 		if (copy_from_user(&n_blocks_count, (__u64 __user *)arg,
 				   sizeof(__u64))) {
 			return -EFAULT;

fs/ext4/mballoc.c

@@ -4994,8 +4994,11 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
 	struct ext4_group_desc *desc;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_buddy e4b;
-	int err = 0, ret, blk_free_count;
-	ext4_grpblk_t blocks_freed;
+	int err = 0, ret, free_clusters_count;
+	ext4_grpblk_t clusters_freed;
+	ext4_fsblk_t first_cluster = EXT4_B2C(sbi, block);
+	ext4_fsblk_t last_cluster = EXT4_B2C(sbi, block + count - 1);
+	unsigned long cluster_count = last_cluster - first_cluster + 1;
 
 	ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1);
 
@@ -5007,8 +5010,8 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
 	 * Check to see if we are freeing blocks across a group
 	 * boundary.
 	 */
-	if (bit + count > EXT4_BLOCKS_PER_GROUP(sb)) {
-		ext4_warning(sb, "too much blocks added to group %u",
+	if (bit + cluster_count > EXT4_CLUSTERS_PER_GROUP(sb)) {
+		ext4_warning(sb, "too many blocks added to group %u",
 			     block_group);
 		err = -EINVAL;
 		goto error_return;
@@ -5054,14 +5057,14 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
 	if (err)
 		goto error_return;
 
-	for (i = 0, blocks_freed = 0; i < count; i++) {
+	for (i = 0, clusters_freed = 0; i < cluster_count; i++) {
 		BUFFER_TRACE(bitmap_bh, "clear bit");
 		if (!mb_test_bit(bit + i, bitmap_bh->b_data)) {
 			ext4_error(sb, "bit already cleared for block %llu",
 				   (ext4_fsblk_t)(block + i));
 			BUFFER_TRACE(bitmap_bh, "bit already cleared");
 		} else {
-			blocks_freed++;
+			clusters_freed++;
 		}
 	}
 
@@ -5075,19 +5078,20 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
 	 * them with group lock_held
 	 */
 	ext4_lock_group(sb, block_group);
-	mb_clear_bits(bitmap_bh->b_data, bit, count);
-	mb_free_blocks(NULL, &e4b, bit, count);
-	blk_free_count = blocks_freed + ext4_free_group_clusters(sb, desc);
-	ext4_free_group_clusters_set(sb, desc, blk_free_count);
+	mb_clear_bits(bitmap_bh->b_data, bit, cluster_count);
+	mb_free_blocks(NULL, &e4b, bit, cluster_count);
+	free_clusters_count = clusters_freed +
+		ext4_free_group_clusters(sb, desc);
+	ext4_free_group_clusters_set(sb, desc, free_clusters_count);
 	ext4_block_bitmap_csum_set(sb, block_group, desc, bitmap_bh);
 	ext4_group_desc_csum_set(sb, block_group, desc);
 	ext4_unlock_group(sb, block_group);
 	percpu_counter_add(&sbi->s_freeclusters_counter,
-			   EXT4_NUM_B2C(sbi, blocks_freed));
+			   clusters_freed);
 
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
-		atomic64_add(EXT4_NUM_B2C(sbi, blocks_freed),
+		atomic64_add(clusters_freed,
 			     &sbi->s_flex_groups[flex_group].free_clusters);
 	}
 

fs/ext4/super.c

@@ -1159,6 +1159,9 @@ static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
 	if (inode->i_ino == EXT4_ROOT_INO)
 		return -EPERM;
 
+	if (WARN_ON_ONCE(IS_DAX(inode) && i_size_read(inode)))
+		return -EINVAL;
+
 	res = ext4_convert_inline_data(inode);
 	if (res)
 		return res;
@@ -2790,14 +2793,11 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly)
  * This function is called once a day if we have errors logged
  * on the file system
  */
-static void print_daily_error_info(unsigned long arg)
+static void print_daily_error_info(struct timer_list *t)
 {
-	struct super_block *sb = (struct super_block *) arg;
-	struct ext4_sb_info *sbi;
-	struct ext4_super_block *es;
-
-	sbi = EXT4_SB(sb);
-	es = sbi->s_es;
+	struct ext4_sb_info *sbi = from_timer(sbi, t, s_err_report);
+	struct super_block *sb = sbi->s_sb;
+	struct ext4_super_block *es = sbi->s_es;
 
 	if (es->s_error_count)
 		/* fsck newer than v1.41.13 is needed to clean this condition. */
@@ -3707,6 +3707,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	if (sbi->s_mount_opt & EXT4_MOUNT_DAX) {
+		if (ext4_has_feature_inline_data(sb)) {
+			ext4_msg(sb, KERN_ERR, "Cannot use DAX on a filesystem"
+					" that may contain inline data");
+			goto failed_mount;
+		}
 		err = bdev_dax_supported(sb, blocksize);
 		if (err)
 			goto failed_mount;
@@ -3976,11 +3981,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	sbi->s_gdb_count = db_count;
-	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
-	spin_lock_init(&sbi->s_next_gen_lock);
 
-	setup_timer(&sbi->s_err_report, print_daily_error_info,
-		(unsigned long) sb);
+	timer_setup(&sbi->s_err_report, print_daily_error_info, 0);
 
 	/* Register extent status tree shrinker */
 	if (ext4_es_register_shrinker(sbi))
@@ -4613,7 +4615,8 @@ static int ext4_load_journal(struct super_block *sb,
 					"required on readonly filesystem");
 			if (really_read_only) {
 				ext4_msg(sb, KERN_ERR, "write access "
-					"unavailable, cannot proceed");
+					"unavailable, cannot proceed "
+					"(try mounting with noload)");
 				return -EROFS;
 			}
 			ext4_msg(sb, KERN_INFO, "write access will "

fs/iomap.c

@@ -350,8 +350,8 @@ static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
 static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes,
 		struct iomap *iomap)
 {
-	sector_t sector = iomap->blkno +
-		(((pos & ~(PAGE_SIZE - 1)) - iomap->offset) >> 9);
+	sector_t sector = (iomap->addr +
+			   (pos & PAGE_MASK) - iomap->offset) >> 9;
 
 	return __dax_zero_page_range(iomap->bdev, iomap->dax_dev, sector,
 			offset, bytes);
@@ -510,11 +510,12 @@ static int iomap_to_fiemap(struct fiemap_extent_info *fi,
 		flags |= FIEMAP_EXTENT_MERGED;
 	if (iomap->flags & IOMAP_F_SHARED)
 		flags |= FIEMAP_EXTENT_SHARED;
+	if (iomap->flags & IOMAP_F_DATA_INLINE)
+		flags |= FIEMAP_EXTENT_DATA_INLINE;
 
 	return fiemap_fill_next_extent(fi, iomap->offset,
-			iomap->blkno != IOMAP_NULL_BLOCK ? iomap->blkno << 9: 0,
+			iomap->addr != IOMAP_NULL_ADDR ? iomap->addr : 0,
 			iomap->length, flags);
-
 }
 
 static loff_t
@@ -830,7 +831,7 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
 	bio = bio_alloc(GFP_KERNEL, 1);
 	bio_set_dev(bio, iomap->bdev);
 	bio->bi_iter.bi_sector =
-		iomap->blkno + ((pos - iomap->offset) >> 9);
+		(iomap->addr + pos - iomap->offset) >> 9;
 	bio->bi_private = dio;
 	bio->bi_end_io = iomap_dio_bio_end_io;
 
@@ -909,7 +910,7 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 		bio = bio_alloc(GFP_KERNEL, nr_pages);
 		bio_set_dev(bio, iomap->bdev);
 		bio->bi_iter.bi_sector =
-			iomap->blkno + ((pos - iomap->offset) >> 9);
+			(iomap->addr + pos - iomap->offset) >> 9;
 		bio->bi_write_hint = dio->iocb->ki_hint;
 		bio->bi_private = dio;
 		bio->bi_end_io = iomap_dio_bio_end_io;

fs/jbd2/journal.c

@@ -165,11 +165,11 @@ static void jbd2_superblock_csum_set(journal_t *j, journal_superblock_t *sb)
  * Helper function used to manage commit timeouts
  */
 
-static void commit_timeout(unsigned long __data)
+static void commit_timeout(struct timer_list *t)
 {
-	struct task_struct * p = (struct task_struct *) __data;
+	journal_t *journal = from_timer(journal, t, j_commit_timer);
 
-	wake_up_process(p);
+	wake_up_process(journal->j_task);
 }
 
 /*
@@ -197,8 +197,7 @@ static int kjournald2(void *arg)
 	 * Set up an interval timer which can be used to trigger a commit wakeup
 	 * after the commit interval expires
 	 */
-	setup_timer(&journal->j_commit_timer, commit_timeout,
-			(unsigned long)current);
+	timer_setup(&journal->j_commit_timer, commit_timeout, 0);
 
 	set_freezable();
 

fs/nfsd/blocklayout.c

@@ -66,7 +66,7 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
 			bex->es = PNFS_BLOCK_READ_DATA;
 		else
 			bex->es = PNFS_BLOCK_READWRITE_DATA;
-		bex->soff = (iomap.blkno << 9);
+		bex->soff = iomap.addr;
 		break;
 	case IOMAP_UNWRITTEN:
 		if (seg->iomode & IOMODE_RW) {
@@ -79,7 +79,7 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
 			}
 
 			bex->es = PNFS_BLOCK_INVALID_DATA;
-			bex->soff = (iomap.blkno << 9);
+			bex->soff = iomap.addr;
 			break;
 		}
 		/*FALLTHRU*/

fs/xfs/xfs_iomap.c

@@ -54,13 +54,13 @@ xfs_bmbt_to_iomap(
 	struct xfs_mount	*mp = ip->i_mount;
 
 	if (imap->br_startblock == HOLESTARTBLOCK) {
-		iomap->blkno = IOMAP_NULL_BLOCK;
+		iomap->addr = IOMAP_NULL_ADDR;
 		iomap->type = IOMAP_HOLE;
 	} else if (imap->br_startblock == DELAYSTARTBLOCK) {
-		iomap->blkno = IOMAP_NULL_BLOCK;
+		iomap->addr = IOMAP_NULL_ADDR;
 		iomap->type = IOMAP_DELALLOC;
 	} else {
-		iomap->blkno = xfs_fsb_to_db(ip, imap->br_startblock);
+		iomap->addr = BBTOB(xfs_fsb_to_db(ip, imap->br_startblock));
 		if (imap->br_state == XFS_EXT_UNWRITTEN)
 			iomap->type = IOMAP_UNWRITTEN;
 		else

include/linux/iomap.h

@@ -16,8 +16,8 @@ struct vm_fault;
  */
 #define IOMAP_HOLE	0x01	/* no blocks allocated, need allocation */
 #define IOMAP_DELALLOC	0x02	/* delayed allocation blocks */
-#define IOMAP_MAPPED	0x03	/* blocks allocated @blkno */
-#define IOMAP_UNWRITTEN	0x04	/* blocks allocated @blkno in unwritten state */
+#define IOMAP_MAPPED	0x03	/* blocks allocated at @addr */
+#define IOMAP_UNWRITTEN	0x04	/* blocks allocated at @addr in unwritten state */
 
 /*
  * Flags for all iomap mappings:
@@ -27,16 +27,17 @@ struct vm_fault;
 /*
  * Flags that only need to be reported for IOMAP_REPORT requests:
  */
-#define IOMAP_F_MERGED	0x10	/* contains multiple blocks/extents */
-#define IOMAP_F_SHARED	0x20	/* block shared with another file */
+#define IOMAP_F_MERGED		0x10	/* contains multiple blocks/extents */
+#define IOMAP_F_SHARED		0x20	/* block shared with another file */
+#define IOMAP_F_DATA_INLINE	0x40	/* data inline in the inode */
 
 /*
- * Magic value for blkno:
+ * Magic value for addr:
  */
-#define IOMAP_NULL_BLOCK -1LL	/* blkno is not valid */
+#define IOMAP_NULL_ADDR -1ULL	/* addr is not valid */
 
 struct iomap {
-	sector_t		blkno;	/* 1st sector of mapping, 512b units */
+	u64			addr; /* disk offset of mapping, bytes */
 	loff_t			offset;	/* file offset of mapping, bytes */
 	u64			length;	/* length of mapping, bytes */
 	u16			type;	/* type of mapping */