ext4: Introduce FALLOC_FL_ZERO_RANGE flag for fallocate

Introduce new FALLOC_FL_ZERO_RANGE flag for fallocate. This has the same
functionality as xfs ioctl XFS_IOC_ZERO_RANGE.

It can be used to convert a range of file to zeros preferably without
issuing data IO. Blocks should be preallocated for the regions that span
holes in the file, and the entire range is preferable converted to
unwritten extents

This can be also used to preallocate blocks past EOF in the same way as
with fallocate. Flag FALLOC_FL_KEEP_SIZE which should cause the inode
size to remain the same.

Also add appropriate tracepoints.
Signed-off-by: Lukas Czerner <lczerner@redhat.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

fs/ext4/ext4.h

@@ -568,6 +568,8 @@ enum {
 #define EXT4_GET_BLOCKS_NO_LOCK			0x0100
 	/* Do not put hole in extent cache */
 #define EXT4_GET_BLOCKS_NO_PUT_HOLE		0x0200
+	/* Convert written extents to unwritten */
+#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN	0x0400
 
 /*
  * The bit position of these flags must not overlap with any of the

fs/ext4/inode.c

@@ -503,6 +503,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 {
 	struct extent_status es;
 	int retval;
+	int ret = 0;
 #ifdef ES_AGGRESSIVE_TEST
 	struct ext4_map_blocks orig_map;
 
@@ -558,7 +559,6 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 					     EXT4_GET_BLOCKS_KEEP_SIZE);
 	}
 	if (retval > 0) {
-		int ret;
 		unsigned int status;
 
 		if (unlikely(retval != map->m_len)) {
@@ -585,7 +585,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 
 found:
 	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
-		int ret = check_block_validity(inode, map);
+		ret = check_block_validity(inode, map);
 		if (ret != 0)
 			return ret;
 	}
@@ -602,7 +602,13 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 	 * with buffer head unmapped.
 	 */
 	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
-		return retval;
+		/*
+		 * If we need to convert extent to unwritten
+		 * we continue and do the actual work in
+		 * ext4_ext_map_blocks()
+		 */
+		if (!(flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN))
+			return retval;
 
 	/*
 	 * Here we clear m_flags because after allocating an new extent,
@@ -658,7 +664,6 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 		ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
 
 	if (retval > 0) {
-		int ret;
 		unsigned int status;
 
 		if (unlikely(retval != map->m_len)) {
@@ -693,7 +698,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 has_zeroout:
 	up_write((&EXT4_I(inode)->i_data_sem));
 	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
-		int ret = check_block_validity(inode, map);
+		ret = check_block_validity(inode, map);
 		if (ret != 0)
 			return ret;
 	}
@@ -3507,7 +3512,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 	if (!S_ISREG(inode->i_mode))
 		return -EOPNOTSUPP;
 
-	trace_ext4_punch_hole(inode, offset, length);
+	trace_ext4_punch_hole(inode, offset, length, 0);
 
 	/*
 	 * Write out all dirty pages to avoid race conditions

include/trace/events/ext4.h

@@ -21,6 +21,10 @@ struct extent_status;
 #define FALLOC_FL_COLLAPSE_RANGE	0x08
 #endif
 
+#ifndef FALLOC_FL_ZERO_RANGE
+#define FALLOC_FL_ZERO_RANGE           0x10
+#endif
+
 #define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode))
 
 #define show_mballoc_flags(flags) __print_flags(flags, "|",	\
@@ -77,7 +81,8 @@ struct extent_status;
 	{ FALLOC_FL_KEEP_SIZE,		"KEEP_SIZE"},		\
 	{ FALLOC_FL_PUNCH_HOLE,		"PUNCH_HOLE"},		\
 	{ FALLOC_FL_NO_HIDE_STALE,	"NO_HIDE_STALE"},	\
-	{ FALLOC_FL_COLLAPSE_RANGE,	"COLLAPSE_RANGE"})
+	{ FALLOC_FL_COLLAPSE_RANGE,	"COLLAPSE_RANGE"},	\
+	{ FALLOC_FL_ZERO_RANGE,		"ZERO_RANGE"})
 
 
 TRACE_EVENT(ext4_free_inode,
@@ -1339,7 +1344,7 @@ TRACE_EVENT(ext4_direct_IO_exit,
 		  __entry->rw, __entry->ret)
 );
 
-TRACE_EVENT(ext4_fallocate_enter,
+DECLARE_EVENT_CLASS(ext4__fallocate_mode,
 	TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode),
 
 	TP_ARGS(inode, offset, len, mode),
@@ -1347,23 +1352,45 @@ TRACE_EVENT(ext4_fallocate_enter,
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
 		__field(	ino_t,	ino			)
-		__field(	loff_t,	pos			)
-		__field(	loff_t,	len			)
+		__field(	loff_t,	offset			)
+		__field(	loff_t, len			)
 		__field(	int,	mode			)
 	),
 
 	TP_fast_assign(
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
-		__entry->pos	= offset;
+		__entry->offset	= offset;
 		__entry->len	= len;
 		__entry->mode	= mode;
 	),
 
-	TP_printk("dev %d,%d ino %lu pos %lld len %lld mode %s",
+	TP_printk("dev %d,%d ino %lu offset %lld len %lld mode %s",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  (unsigned long) __entry->ino, __entry->pos,
-		  __entry->len, show_falloc_mode(__entry->mode))
+		  (unsigned long) __entry->ino,
+		  __entry->offset, __entry->len,
+		  show_falloc_mode(__entry->mode))
+);
+
+DEFINE_EVENT(ext4__fallocate_mode, ext4_fallocate_enter,
+
+	TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode),
+
+	TP_ARGS(inode, offset, len, mode)
+);
+
+DEFINE_EVENT(ext4__fallocate_mode, ext4_punch_hole,
+
+	TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode),
+
+	TP_ARGS(inode, offset, len, mode)
+);
+
+DEFINE_EVENT(ext4__fallocate_mode, ext4_zero_range,
+
+	TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode),
+
+	TP_ARGS(inode, offset, len, mode)
 );
 
 TRACE_EVENT(ext4_fallocate_exit,
@@ -1395,31 +1422,6 @@ TRACE_EVENT(ext4_fallocate_exit,
 		  __entry->ret)
 );
 
-TRACE_EVENT(ext4_punch_hole,
-	TP_PROTO(struct inode *inode, loff_t offset, loff_t len),
-
-	TP_ARGS(inode, offset, len),
-
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
-		__field(	loff_t,	offset			)
-		__field(	loff_t, len			)
-	),
-
-	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
-		__entry->ino	= inode->i_ino;
-		__entry->offset	= offset;
-		__entry->len	= len;
-	),
-
-	TP_printk("dev %d,%d ino %lu offset %lld len %lld",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  (unsigned long) __entry->ino,
-		  __entry->offset, __entry->len)
-);
-
 TRACE_EVENT(ext4_unlink_enter,
 	TP_PROTO(struct inode *parent, struct dentry *dentry),