[PATCH 0/7][TAKE6] fallocate system call

@@ -323,3 +323,4 @@ ENTRY(sys_call_table)
 	.long sys_signalfd
 	.long sys_timerfd
 	.long sys_eventfd
+	.long sys_fallocate

@@ -773,6 +773,13 @@ asmlinkage int compat_sys_truncate64(con
 	return sys_truncate(path, (high << 32) | low);
 }
 
+asmlinkage long compat_sys_fallocate(int fd, int mode, u32 offhi, u32 offlo,
+				     u32 lenhi, u32 lenlo)
+{
+	return sys_fallocate(fd, mode, ((loff_t)offhi << 32) | offlo,
+			     ((loff_t)lenhi << 32) | lenlo);
+}
+
 asmlinkage int compat_sys_ftruncate64(unsigned int fd, u32 reg4, unsigned long high,
 				 unsigned long low)
 {

@@ -719,4 +719,5 @@ ia32_sys_call_table:
 	.quad compat_sys_signalfd
 	.quad compat_sys_timerfd
 	.quad sys_eventfd
+	.quad sys32_fallocate
 ia32_syscall_end:

@@ -353,6 +353,92 @@ asmlinkage long sys_ftruncate64(unsigned
 #endif
 
 /*
+ * sys_fallocate - preallocate blocks or free preallocated blocks
+ * @fd: the file descriptor
+ * @mode: mode specifies if fallocate should preallocate blocks OR free
+ *	  (unallocate) preallocated blocks. Currently only FA_ALLOCATE and
+ *	  FA_DEALLOCATE modes are supported.
+ * @offset: The offset within file, from where (un)allocation is being
+ *	    requested. It should not have a negative value.
+ * @len: The amount (in bytes) of space to be (un)allocated, from the offset.
+ *
+ * This system call, depending on the mode, preallocates or unallocates blocks
+ * for a file. The range of blocks depends on the value of offset and len
+ * arguments provided by the user/application. For FA_ALLOCATE mode, if this
+ * system call succeeds, subsequent writes to the file in the given range
+ * (specified by offset & len) should not fail - even if the file system
+ * later becomes full. Hence the preallocation done is persistent (valid
+ * even after reopen of the file and remount/reboot).
+ *
+ * It is expected that the ->fallocate() inode operation implemented by the
+ * individual file systems will update the file size and/or ctime/mtime
+ * depending on the mode and also on the success of the operation.
+ *
+ * Note: Incase the file system does not support preallocation,
+ * posix_fallocate() should fall back to the library implementation (i.e.
+ * allocating zero-filled new blocks to the file).
+ *
+ * Return Values
+ *	0	: On SUCCESS a value of zero is returned.
+ *	error	: On Failure, an error code will be returned.
+ * An error code of -ENOSYS or -EOPNOTSUPP should make posix_fallocate()
+ * fall back on library implementation of fallocate.
+ *
+ * <TBD> Generic fallocate to be added for file systems that do not
+ *	 support fallocate it.
+ */
+asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len)
+{
+	struct file *file;
+	struct inode *inode;
+	long ret = -EINVAL;
+
+	if (offset < 0 || len <= 0)
+		goto out;
+
+	/* Return error if mode is not supported */
+	ret = -EOPNOTSUPP;
+	if (mode != FA_ALLOCATE && mode != FA_DEALLOCATE)
+		goto out;
+
+	ret = -EBADF;
+	file = fget(fd);
+	if (!file)
+		goto out;
+	if (!(file->f_mode & FMODE_WRITE))
+		goto out_fput;
+
+	inode = file->f_path.dentry->d_inode;
+
+	ret = -ESPIPE;
+	if (S_ISFIFO(inode->i_mode))
+		goto out_fput;
+
+	ret = -ENODEV;
+	/*
+	 * Let individual file system decide if it supports preallocation
+	 * for directories or not.
+	 */
+	if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
+		goto out_fput;
+
+	ret = -EFBIG;
+	/* Check for wrap through zero too */
+	if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0))
+		goto out_fput;
+
+	if (inode->i_op && inode->i_op->fallocate)
+		ret = inode->i_op->fallocate(inode, mode, offset, len);
+	else
+		ret = -ENOSYS;
+
+out_fput:
+	fput(file);
+out:
+	return ret;
+}
+
+/*
  * access() needs to use the real uid/gid, not the effective uid/gid.
  * We do this by temporarily clearing all FS-related capabilities and
  * switching the fsuid/fsgid around to the real ones.

@@ -329,10 +329,11 @@
 #define __NR_signalfd		321
 #define __NR_timerfd		322
 #define __NR_eventfd		323
+#define __NR_fallocate		324
 
 #ifdef __KERNEL__
 
-#define NR_syscalls 324
+#define NR_syscalls 325
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR

@@ -308,6 +308,7 @@ COMPAT_SYS_SPU(move_pages)
 SYSCALL_SPU(getcpu)
 COMPAT_SYS(epoll_pwait)
 COMPAT_SYS_SPU(utimensat)
+COMPAT_SYS(fallocate)
 COMPAT_SYS_SPU(signalfd)
 COMPAT_SYS_SPU(timerfd)
 SYSCALL_SPU(eventfd)

@@ -331,10 +331,11 @@
 #define __NR_timerfd		306
 #define __NR_eventfd		307
 #define __NR_sync_file_range2	308
+#define __NR_fallocate		309
 
 #ifdef __KERNEL__
 
-#define __NR_syscalls		309
+#define __NR_syscalls		310
 
 #define __NR__exit __NR_exit
 #define NR_syscalls	__NR_syscalls

@@ -630,6 +630,8 @@ __SYSCALL(__NR_signalfd, sys_signalfd)
 __SYSCALL(__NR_timerfd, sys_timerfd)
 #define __NR_eventfd		284
 __SYSCALL(__NR_eventfd, sys_eventfd)
+#define __NR_fallocate		285
+__SYSCALL(__NR_fallocate, sys_fallocate)
 
 #ifndef __NO_STUBS
 #define __ARCH_WANT_OLD_READDIR

@@ -266,6 +266,17 @@ extern int dir_notify_enable;
 #define SYNC_FILE_RANGE_WRITE		2
 #define SYNC_FILE_RANGE_WAIT_AFTER	4
 
+/*
+ * sys_fallocate modes
+ * Currently sys_fallocate supports two modes:
+ * FA_ALLOCATE  : This is the preallocate mode, using which an application/user
+ *		  may request (pre)allocation of blocks.
+ * FA_DEALLOCATE: This is the deallocate mode, which can be used to free
+ *		  the preallocated blocks.
+ */
+#define FA_ALLOCATE	0x1
+#define FA_DEALLOCATE	0x2
+
 #ifdef __KERNEL__
 
 #include <linux/linkage.h>

@@ -1138,6 +1149,8 @@ struct inode_operations {
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	int (*removexattr) (struct dentry *, const char *);
 	void (*truncate_range)(struct inode *, loff_t, loff_t);
+	long (*fallocate)(struct inode *inode, int mode, loff_t offset,
+			  loff_t len);
 };
 
 struct seq_file;

@@ -610,6 +610,7 @@ asmlinkage long sys_signalfd(int ufd, si
 asmlinkage long sys_timerfd(int ufd, int clockid, int flags,
 			    const struct itimerspec __user *utmr);
 asmlinkage long sys_eventfd(unsigned int count);
+asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len);
 
 int kernel_execve(const char *filename, char *const argv[], char *const envp[]);
 

@@ -879,3 +879,11 @@ asmlinkage long sys32_fadvise64(int fd, 
 	return sys_fadvise64_64(fd, ((u64)offset_hi << 32) | offset_lo,
 				len, advice);
 }
+
+asmlinkage long sys32_fallocate(int fd, int mode, unsigned offset_lo,
+				unsigned offset_hi, unsigned len_lo,
+				unsigned len_hi)
+{
+	return sys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo,
+			     ((u64)len_hi << 32) | len_lo);
+}

@@ -267,15 +267,17 @@ extern int dir_notify_enable;
 #define SYNC_FILE_RANGE_WAIT_AFTER	4
 
 /*
- * sys_fallocate modes
- * Currently sys_fallocate supports two modes:
- * FA_ALLOCATE  : This is the preallocate mode, using which an application/user
- *		  may request (pre)allocation of blocks.
- * FA_DEALLOCATE: This is the deallocate mode, which can be used to free
- *		  the preallocated blocks.
+ * sys_fallocate mode flags and values
  */
-#define FA_ALLOCATE	0x1
-#define FA_DEALLOCATE	0x2
+#define FALLOC_FL_DEALLOC	0x01 /* default is allocate */
+#define FALLOC_FL_KEEP_SIZE	0x02 /* default is extend/shrink size */
+#define FALLOC_FL_DEL_DATA	0x04 /* default is keep written data on DEALLOC */
+
+#define FALLOC_ALLOCATE 	0
+#define FALLOC_DEALLOCATE	FALLOC_FL_DEALLOC
+#define FALLOC_RESV_SPACE	FALLOC_FL_KEEP_SIZE
+#define FALLOC_UNRESV_SPACE	(FALLOC_FL_DEALLOC | FALLOC_FL_KEEP_SIZE | \
+				 FALLOC_FL_DEL_DATA)
 
 #ifdef __KERNEL__
 

@@ -356,23 +356,26 @@ asmlinkage long sys_ftruncate64(unsigned
  * sys_fallocate - preallocate blocks or free preallocated blocks
  * @fd: the file descriptor
  * @mode: mode specifies if fallocate should preallocate blocks OR free
- *	  (unallocate) preallocated blocks. Currently only FA_ALLOCATE and
- *	  FA_DEALLOCATE modes are supported.
+ *	  (unallocate) preallocated blocks.
  * @offset: The offset within file, from where (un)allocation is being
  *	    requested. It should not have a negative value.
  * @len: The amount (in bytes) of space to be (un)allocated, from the offset.
  *
  * This system call, depending on the mode, preallocates or unallocates blocks
  * for a file. The range of blocks depends on the value of offset and len
- * arguments provided by the user/application. For FA_ALLOCATE mode, if this
+ * arguments provided by the user/application. For FALLOC_ALLOCATE and
+ * FALLOC_RESV_SPACE modes, if the sys_fallocate()
  * system call succeeds, subsequent writes to the file in the given range
  * (specified by offset & len) should not fail - even if the file system
  * later becomes full. Hence the preallocation done is persistent (valid
- * even after reopen of the file and remount/reboot).
+ * even after reopen of the file and remount/reboot). If FALLOC_RESV_SPACE mode
+ * is passed, the file size will not be changed even if the preallocation
+ * is beyond EOF.
  *
  * It is expected that the ->fallocate() inode operation implemented by the
  * individual file systems will update the file size and/or ctime/mtime
- * depending on the mode and also on the success of the operation.
+ * depending on the mode (change is visible to user or not - say file size)
+ * and obviously, on the success of the operation.
  *
  * Note: Incase the file system does not support preallocation,
  * posix_fallocate() should fall back to the library implementation (i.e.

@@ -398,7 +401,8 @@ asmlinkage long sys_fallocate(int fd, in
 
 	/* Return error if mode is not supported */
 	ret = -EOPNOTSUPP;
-	if (mode != FA_ALLOCATE && mode != FA_DEALLOCATE)
+	if (!(mode == FALLOC_ALLOCATE || mode == FALLOC_DEALLOCATE ||
+		mode == FALLOC_RESV_SPACE || mode == FALLOC_UNRESV_SPACE))
 		goto out;
 
 	ret = -EBADF;

@@ -282,7 +282,7 @@ static void ext4_ext_show_path(struct in
 		} else if (path->p_ext) {
 			ext_debug("  %d:%d:%llu ",
 				  le32_to_cpu(path->p_ext->ee_block),
-				  le16_to_cpu(path->p_ext->ee_len),
+				  ext4_ext_get_actual_len(path->p_ext),
 				  ext_pblock(path->p_ext));
 		} else
 			ext_debug("  []");

@@ -305,7 +305,7 @@ static void ext4_ext_show_leaf(struct in
 
 	for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) {
 		ext_debug("%d:%d:%llu ", le32_to_cpu(ex->ee_block),
-			  le16_to_cpu(ex->ee_len), ext_pblock(ex));
+			  ext4_ext_get_actual_len(ex), ext_pblock(ex));
 	}
 	ext_debug("\n");
 }

@@ -425,7 +425,7 @@ ext4_ext_binsearch(struct inode *inode, 
 	ext_debug("  -> %d:%llu:%d ",
 			le32_to_cpu(path->p_ext->ee_block),
 			ext_pblock(path->p_ext),
-			le16_to_cpu(path->p_ext->ee_len));
+			ext4_ext_get_actual_len(path->p_ext));
 
 #ifdef CHECK_BINSEARCH
 	{

@@ -686,7 +686,7 @@ static int ext4_ext_split(handle_t *hand
 		ext_debug("move %d:%llu:%d in new leaf %llu\n",
 				le32_to_cpu(path[depth].p_ext->ee_block),
 				ext_pblock(path[depth].p_ext),
-				le16_to_cpu(path[depth].p_ext->ee_len),
+				ext4_ext_get_actual_len(path[depth].p_ext),
 				newblock);
 		/*memmove(ex++, path[depth].p_ext++,
 				sizeof(struct ext4_extent));

@@ -1106,7 +1106,19 @@ static int
 ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
 				struct ext4_extent *ex2)
 {
-	if (le32_to_cpu(ex1->ee_block) + le16_to_cpu(ex1->ee_len) !=
+	unsigned short ext1_ee_len, ext2_ee_len;
+
+	/*
+	 * Make sure that either both extents are uninitialized, or
+	 * both are _not_.
+	 */
+	if (ext4_ext_is_uninitialized(ex1) ^ ext4_ext_is_uninitialized(ex2))
+		return 0;
+
+	ext1_ee_len = ext4_ext_get_actual_len(ex1);
+	ext2_ee_len = ext4_ext_get_actual_len(ex2);
+
+	if (le32_to_cpu(ex1->ee_block) + ext1_ee_len !=
 			le32_to_cpu(ex2->ee_block))
 		return 0;
 

@@ -1115,14 +1127,14 @@ ext4_can_extents_be_merged(struct inode 
 	 * as an RO_COMPAT feature, refuse to merge to extents if
 	 * this can result in the top bit of ee_len being set.
 	 */
-	if (le16_to_cpu(ex1->ee_len) + le16_to_cpu(ex2->ee_len) > EXT_MAX_LEN)
+	if (ext1_ee_len + ext2_ee_len > EXT_MAX_LEN)
 		return 0;
 #ifdef AGGRESSIVE_TEST
 	if (le16_to_cpu(ex1->ee_len) >= 4)
 		return 0;
 #endif
 
-	if (ext_pblock(ex1) + le16_to_cpu(ex1->ee_len) == ext_pblock(ex2))
+	if (ext_pblock(ex1) + ext1_ee_len == ext_pblock(ex2))
 		return 1;
 	return 0;
 }

@@ -1144,7 +1156,7 @@ unsigned int ext4_ext_check_overlap(stru
 	unsigned int ret = 0;
 
 	b1 = le32_to_cpu(newext->ee_block);
-	len1 = le16_to_cpu(newext->ee_len);
+	len1 = ext4_ext_get_actual_len(newext);
 	depth = ext_depth(inode);
 	if (!path[depth].p_ext)
 		goto out;

@@ -1191,8 +1203,9 @@ int ext4_ext_insert_extent(handle_t *han
 	struct ext4_extent *nearex; /* nearest extent */
 	struct ext4_ext_path *npath = NULL;
 	int depth, len, err, next;
+	unsigned uninitialized = 0;
 
-	BUG_ON(newext->ee_len == 0);
+	BUG_ON(ext4_ext_get_actual_len(newext) == 0);
 	depth = ext_depth(inode);
 	ex = path[depth].p_ext;
 	BUG_ON(path[depth].p_hdr == NULL);

@@ -1200,14 +1213,24 @@ int ext4_ext_insert_extent(handle_t *han
 	/* try to insert block into found extent and return */
 	if (ex && ext4_can_extents_be_merged(inode, ex, newext)) {
 		ext_debug("append %d block to %d:%d (from %llu)\n",
-				le16_to_cpu(newext->ee_len),
+				ext4_ext_get_actual_len(newext),
 				le32_to_cpu(ex->ee_block),
-				le16_to_cpu(ex->ee_len), ext_pblock(ex));
+				ext4_ext_get_actual_len(ex), ext_pblock(ex));
 		err = ext4_ext_get_access(handle, inode, path + depth);
 		if (err)
 			return err;
-		ex->ee_len = cpu_to_le16(le16_to_cpu(ex->ee_len)
-					 + le16_to_cpu(newext->ee_len));
+
+		/*
+		 * ext4_can_extents_be_merged should have checked that either
+		 * both extents are uninitialized, or both aren't. Thus we
+		 * need to check only one of them here.
+		 */
+		if (ext4_ext_is_uninitialized(ex))
+			uninitialized = 1;
+		ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
+					+ ext4_ext_get_actual_len(newext));
+		if (uninitialized)
+			ext4_ext_mark_uninitialized(ex);
 		eh = path[depth].p_hdr;
 		nearex = ex;
 		goto merge;

@@ -1263,7 +1286,7 @@ has_space:
 		ext_debug("first extent in the leaf: %d:%llu:%d\n",
 				le32_to_cpu(newext->ee_block),
 				ext_pblock(newext),
-				le16_to_cpu(newext->ee_len));
+				ext4_ext_get_actual_len(newext));
 		path[depth].p_ext = EXT_FIRST_EXTENT(eh);
 	} else if (le32_to_cpu(newext->ee_block)
 			   > le32_to_cpu(nearex->ee_block)) {

@@ -1276,7 +1299,7 @@ has_space:
 					"move %d from 0x%p to 0x%p\n",
 					le32_to_cpu(newext->ee_block),
 					ext_pblock(newext),
-					le16_to_cpu(newext->ee_len),
+					ext4_ext_get_actual_len(newext),
 					nearex, len, nearex + 1, nearex + 2);
 			memmove(nearex + 2, nearex + 1, len);
 		}

@@ -1289,7 +1312,7 @@ has_space:
 				"move %d from 0x%p to 0x%p\n",
 				le32_to_cpu(newext->ee_block),
 				ext_pblock(newext),
-				le16_to_cpu(newext->ee_len),
+				ext4_ext_get_actual_len(newext),
 				nearex, len, nearex + 1, nearex + 2);
 		memmove(nearex + 1, nearex, len);
 		path[depth].p_ext = nearex;

@@ -1308,8 +1331,13 @@ merge:
 		if (!ext4_can_extents_be_merged(inode, nearex, nearex + 1))
 			break;
 		/* merge with next extent! */
-		nearex->ee_len = cpu_to_le16(le16_to_cpu(nearex->ee_len)
-					     + le16_to_cpu(nearex[1].ee_len));
+		if (ext4_ext_is_uninitialized(nearex))
+			uninitialized = 1;
+		nearex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(nearex)
+					+ ext4_ext_get_actual_len(nearex + 1));
+		if (uninitialized)
+			ext4_ext_mark_uninitialized(nearex);
+
 		if (nearex + 1 < EXT_LAST_EXTENT(eh)) {
 			len = (EXT_LAST_EXTENT(eh) - nearex - 1)
 					* sizeof(struct ext4_extent);

@@ -1379,8 +1407,8 @@ int ext4_ext_walk_space(struct inode *in
 			end = le32_to_cpu(ex->ee_block);
 			if (block + num < end)
 				end = block + num;
-		} else if (block >=
-			     le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len)) {
+		} else if (block >= le32_to_cpu(ex->ee_block)
+					+ ext4_ext_get_actual_len(ex)) {
 			/* need to allocate space after found extent */
 			start = block;
 			end = block + num;

@@ -1392,7 +1420,8 @@ int ext4_ext_walk_space(struct inode *in
 			 * by found extent
 			 */
 			start = block;
-			end = le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len);
+			end = le32_to_cpu(ex->ee_block)
+				+ ext4_ext_get_actual_len(ex);
 			if (block + num < end)
 				end = block + num;
 			exists = 1;

@@ -1408,7 +1437,7 @@ int ext4_ext_walk_space(struct inode *in
 			cbex.ec_type = EXT4_EXT_CACHE_GAP;
 		} else {
 			cbex.ec_block = le32_to_cpu(ex->ee_block);
-			cbex.ec_len = le16_to_cpu(ex->ee_len);
+			cbex.ec_len = ext4_ext_get_actual_len(ex);
 			cbex.ec_start = ext_pblock(ex);
 			cbex.ec_type = EXT4_EXT_CACHE_EXTENT;
 		}

@@ -1481,15 +1510,15 @@ ext4_ext_put_gap_in_cache(struct inode *
 		ext_debug("cache gap(before): %lu [%lu:%lu]",
 				(unsigned long) block,
 				(unsigned long) le32_to_cpu(ex->ee_block),
-				(unsigned long) le16_to_cpu(ex->ee_len));
+				(unsigned long) ext4_ext_get_actual_len(ex));
 	} else if (block >= le32_to_cpu(ex->ee_block)
-			    + le16_to_cpu(ex->ee_len)) {
+			+ ext4_ext_get_actual_len(ex)) {
 		lblock = le32_to_cpu(ex->ee_block)
-			 + le16_to_cpu(ex->ee_len);
+			+ ext4_ext_get_actual_len(ex);
 		len = ext4_ext_next_allocated_block(path);
 		ext_debug("cache gap(after): [%lu:%lu] %lu",
 				(unsigned long) le32_to_cpu(ex->ee_block),
-				(unsigned long) le16_to_cpu(ex->ee_len),
+				(unsigned long) ext4_ext_get_actual_len(ex),
 				(unsigned long) block);
 		BUG_ON(len == lblock);
 		len = len - lblock;

@@ -1619,12 +1648,12 @@ static int ext4_remove_blocks(handle_t *
 				unsigned long from, unsigned long to)
 {
 	struct buffer_head *bh;
+	unsigned short ee_len =  ext4_ext_get_actual_len(ex);
 	int i;
 
 #ifdef EXTENTS_STATS
 	{
 		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-		unsigned short ee_len =  le16_to_cpu(ex->ee_len);
 		spin_lock(&sbi->s_ext_stats_lock);
 		sbi->s_ext_blocks += ee_len;
 		sbi->s_ext_extents++;

@@ -1638,12 +1667,12 @@ static int ext4_remove_blocks(handle_t *
 	}
 #endif
 	if (from >= le32_to_cpu(ex->ee_block)
-	    && to == le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len) - 1) {
+	    && to == le32_to_cpu(ex->ee_block) + ee_len - 1) {
 		/* tail removal */
 		unsigned long num;
 		ext4_fsblk_t start;
-		num = le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len) - from;
-		start = ext_pblock(ex) + le16_to_cpu(ex->ee_len) - num;
+		num = le32_to_cpu(ex->ee_block) + ee_len - from;
+		start = ext_pblock(ex) + ee_len - num;
 		ext_debug("free last %lu blocks starting %llu\n", num, start);
 		for (i = 0; i < num; i++) {
 			bh = sb_find_get_block(inode->i_sb, start + i);

@@ -1651,12 +1680,12 @@ static int ext4_remove_blocks(handle_t *
 		}
 		ext4_free_blocks(handle, inode, start, num);
 	} else if (from == le32_to_cpu(ex->ee_block)
-		   && to <= le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len) - 1) {
+		   && to <= le32_to_cpu(ex->ee_block) + ee_len - 1) {
 		printk("strange request: removal %lu-%lu from %u:%u\n",
-		       from, to, le32_to_cpu(ex->ee_block), le16_to_cpu(ex->ee_len));
+			from, to, le32_to_cpu(ex->ee_block), ee_len);
 	} else {
 		printk("strange request: removal(2) %lu-%lu from %u:%u\n",
-		       from, to, le32_to_cpu(ex->ee_block), le16_to_cpu(ex->ee_len));
+			from, to, le32_to_cpu(ex->ee_block), ee_len);
 	}
 	return 0;
 }

@@ -1671,6 +1700,7 @@ ext4_ext_rm_leaf(handle_t *handle, struc
 	unsigned a, b, block, num;
 	unsigned long ex_ee_block;
 	unsigned short ex_ee_len;
+	unsigned uninitialized = 0;
 	struct ext4_extent *ex;
 
 	ext_debug("truncate since %lu in leaf\n", start);

@@ -1685,7 +1715,9 @@ ext4_ext_rm_leaf(handle_t *handle, struc
 	ex = EXT_LAST_EXTENT(eh);
 
 	ex_ee_block = le32_to_cpu(ex->ee_block);
-	ex_ee_len = le16_to_cpu(ex->ee_len);
+	if (ext4_ext_is_uninitialized(ex))
+		uninitialized = 1;
+	ex_ee_len = ext4_ext_get_actual_len(ex);
 
 	while (ex >= EXT_FIRST_EXTENT(eh) &&
 			ex_ee_block + ex_ee_len > start) {

@@ -1753,6 +1785,8 @@ ext4_ext_rm_leaf(handle_t *handle, struc
 
 		ex->ee_block = cpu_to_le32(block);
 		ex->ee_len = cpu_to_le16(num);
+		if (uninitialized)
+			ext4_ext_mark_uninitialized(ex);
 
 		err = ext4_ext_dirty(handle, inode, path + depth);
 		if (err)

@@ -1762,7 +1796,7 @@ ext4_ext_rm_leaf(handle_t *handle, struc
 				ext_pblock(ex));
 		ex--;
 		ex_ee_block = le32_to_cpu(ex->ee_block);
-		ex_ee_len = le16_to_cpu(ex->ee_len);
+		ex_ee_len = ext4_ext_get_actual_len(ex);
 	}
 
 	if (correct_index && eh->eh_entries)

@@ -2038,7 +2072,7 @@ int ext4_ext_get_blocks(handle_t *handle
 	if (ex) {
 		unsigned long ee_block = le32_to_cpu(ex->ee_block);
 		ext4_fsblk_t ee_start = ext_pblock(ex);
-		unsigned short ee_len  = le16_to_cpu(ex->ee_len);
+		unsigned short ee_len;
 
 		/*
 		 * Allow future support for preallocated extents to be added

@@ -2046,8 +2080,9 @@ int ext4_ext_get_blocks(handle_t *handle
 		 * Uninitialized extents are treated as holes, except that
 		 * we avoid (fail) allocating new blocks during a write.
 		 */
-		if (ee_len > EXT_MAX_LEN)
+		if (le16_to_cpu(ex->ee_len) > EXT_MAX_LEN)
 			goto out2;
+		ee_len = ext4_ext_get_actual_len(ex);
 		/* if found extent covers block, simply return it */
 		if (iblock >= ee_block && iblock < ee_block + ee_len) {
 			newblock = iblock - ee_block + ee_start;

@@ -2055,8 +2090,11 @@ int ext4_ext_get_blocks(handle_t *handle
 			allocated = ee_len - (iblock - ee_block);
 			ext_debug("%d fit into %lu:%d -> %llu\n", (int) iblock,
 					ee_block, ee_len, newblock);
-			ext4_ext_put_in_cache(inode, ee_block, ee_len,
-						ee_start, EXT4_EXT_CACHE_EXTENT);
+			/* Do not put uninitialized extent in the cache */
+			if (!ext4_ext_is_uninitialized(ex))
+				ext4_ext_put_in_cache(inode, ee_block,
+							ee_len, ee_start,
+							EXT4_EXT_CACHE_EXTENT);
 			goto out;
 		}
 	}

@@ -2098,6 +2136,8 @@ int ext4_ext_get_blocks(handle_t *handle
 	/* try to insert new extent into found leaf and return */
 	ext4_ext_store_pblock(&newex, newblock);
 	newex.ee_len = cpu_to_le16(allocated);
+	if (create == EXT4_CREATE_UNINITIALIZED_EXT)  /* Mark uninitialized */
+		ext4_ext_mark_uninitialized(&newex);
 	err = ext4_ext_insert_extent(handle, inode, path, &newex);
 	if (err) {
 		/* free data blocks we just allocated */

@@ -2113,8 +2153,10 @@ int ext4_ext_get_blocks(handle_t *handle
 	newblock = ext_pblock(&newex);
 	__set_bit(BH_New, &bh_result->b_state);
 
-	ext4_ext_put_in_cache(inode, iblock, allocated, newblock,
-				EXT4_EXT_CACHE_EXTENT);
+	/* Cache only when it is _not_ an uninitialized extent */
+	if (create != EXT4_CREATE_UNINITIALIZED_EXT)
+		ext4_ext_put_in_cache(inode, iblock, allocated, newblock,
+						EXT4_EXT_CACHE_EXTENT);
 out:
 	if (allocated > max_blocks)
 		allocated = max_blocks;

@@ -2217,3 +2259,129 @@ int ext4_ext_writepage_trans_blocks(stru
 
 	return needed;
 }
+
+/*
+ * preallocate space for a file. This implements ext4's fallocate inode
+ * operation, which gets called from sys_fallocate system call.
+ * Currently only FA_ALLOCATE mode is supported on extent based files.
+ * We may have more modes supported in future - like FA_DEALLOCATE, which
+ * tells fallocate to unallocate previously (pre)allocated blocks.
+ * For block-mapped files, posix_fallocate should fall back to the method
+ * of writing zeroes to the required new blocks (the same behavior which is
+ * expected for file systems which do not support fallocate() system call).
+ */
+long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
+{
+	handle_t *handle;
+	ext4_fsblk_t block, max_blocks;
+	ext4_fsblk_t nblocks = 0;
+	int ret = 0;
+	int ret2 = 0;
+	int retries = 0;
+	struct buffer_head map_bh;
+	unsigned int credits, blkbits = inode->i_blkbits;
+
+	/*
+	 * currently supporting (pre)allocate mode for extent-based
+	 * files _only_
+	 */
+	if (mode != FA_ALLOCATE || !(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+		return -EOPNOTSUPP;
+
+	/* preallocation to directories is currently not supported */
+	if (S_ISDIR(inode->i_mode))
+		return -ENODEV;
+
+	block = offset >> blkbits;
+	max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits)
+			- block;
+
+	/*
+	 * credits to insert 1 extent into extent tree + buffers to be able to
+	 * modify 1 super block, 1 block bitmap and 1 group descriptor.
+	 */
+	credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + 3;
+retry:
+	while (ret >= 0 && ret < max_blocks) {
+		block = block + ret;
+		max_blocks = max_blocks - ret;
+		handle = ext4_journal_start(inode, credits);
+		if (IS_ERR(handle)) {
+			ret = PTR_ERR(handle);
+			break;
+		}
+
+		ret = ext4_ext_get_blocks(handle, inode, block,
+					  max_blocks, &map_bh,
+					  EXT4_CREATE_UNINITIALIZED_EXT, 0);
+		WARN_ON(!ret);
+		if (!ret) {
+			ext4_error(inode->i_sb, "ext4_fallocate",
+				   "ext4_ext_get_blocks returned 0! inode#%lu"
+				   ", block=%llu, max_blocks=%llu",
+				   inode->i_ino, block, max_blocks);
+			ret = -EIO;
+			ext4_mark_inode_dirty(handle, inode);
+			ret2 = ext4_journal_stop(handle);
+			break;
+		}
+		if (ret > 0) {
+			/* check wrap through sign-bit/zero here */
+			if ((block + ret) < 0 || (block + ret) < block) {
+				ret = -EIO;
+				ext4_mark_inode_dirty(handle, inode);
+				ret2 = ext4_journal_stop(handle);
+				break;
+			}
+			if (buffer_new(&map_bh) && ((block + ret) >
+			    (EXT4_BLOCK_ALIGN(i_size_read(inode), blkbits)
+			    >> blkbits)))
+					nblocks = nblocks + ret;
+		}
+
+		/* Update ctime if new blocks get allocated */
+		if (nblocks) {
+			struct timespec now;
+			now = current_fs_time(inode->i_sb);
+			if (!timespec_equal(&inode->i_ctime, &now))
+				inode->i_ctime = now;
+		}
+
+		ext4_mark_inode_dirty(handle, inode);
+		ret2 = ext4_journal_stop(handle);
+		if (ret2)
+			break;
+	}
+
+	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+		goto retry;
+
+	/*
+	 * Time to update the file size.
+	 * Update only when preallocation was requested beyond the file size.
+	 */
+	if ((offset + len) > i_size_read(inode)) {
+		if (ret > 0) {
+			/*
+			 * if no error, we assume preallocation succeeded
+			 * completely
+			 */
+			mutex_lock(&inode->i_mutex);
+			i_size_write(inode, offset + len);
+			EXT4_I(inode)->i_disksize = i_size_read(inode);
+			mutex_unlock(&inode->i_mutex);
+		} else if (ret < 0 && nblocks) {
+			/* Handle partial allocation scenario */
+			loff_t newsize;
+
+			mutex_lock(&inode->i_mutex);
+			newsize  = (nblocks << blkbits) + i_size_read(inode);
+			i_size_write(inode, EXT4_BLOCK_ALIGN(newsize, blkbits));
+			EXT4_I(inode)->i_disksize = i_size_read(inode);
+			mutex_unlock(&inode->i_mutex);
+		}
+	}
+
+	return ret > 0 ? ret2 : ret;
+}
+