1 files changed, 706 insertions, 112 deletions

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 74bc2d549c58..82df3ce9874a 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -37,7 +37,6 @@
 #include <linux/quotaops.h>
 #include <linux/string.h>
 #include <linux/slab.h>
-#include <linux/falloc.h>
 #include <asm/uaccess.h>
 #include <linux/fiemap.h>
 #include "ext4_jbd2.h"
@@ -1691,7 +1690,7 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
          * the extent that was written properly split out and conversion to
          * initialized is trivial.
          */
-        if (ext4_ext_is_uninitialized(ex1) || ext4_ext_is_uninitialized(ex2))
+        if (ext4_ext_is_uninitialized(ex1) != ext4_ext_is_uninitialized(ex2))
                 return 0;
 
         ext1_ee_len = ext4_ext_get_actual_len(ex1);
@@ -1708,6 +1707,11 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
          */
         if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN)
                 return 0;
+        if (ext4_ext_is_uninitialized(ex1) &&
+            (ext4_test_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN) ||
+             atomic_read(&EXT4_I(inode)->i_unwritten) ||
+             (ext1_ee_len + ext2_ee_len > EXT_UNINIT_MAX_LEN)))
+                return 0;
 #ifdef AGGRESSIVE_TEST
         if (ext1_ee_len >= 4)
                 return 0;
@@ -1731,7 +1735,7 @@ static int ext4_ext_try_to_merge_right(struct inode *inode,
 {
         struct ext4_extent_header *eh;
         unsigned int depth, len;
-        int merge_done = 0;
+        int merge_done = 0, uninit;
 
         depth = ext_depth(inode);
         BUG_ON(path[depth].p_hdr == NULL);
@@ -1741,8 +1745,11 @@ static int ext4_ext_try_to_merge_right(struct inode *inode,
                 if (!ext4_can_extents_be_merged(inode, ex, ex + 1))
                         break;
                 /* merge with next extent! */
+                uninit = ext4_ext_is_uninitialized(ex);
                 ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
                                 + ext4_ext_get_actual_len(ex + 1));
+                if (uninit)
+                        ext4_ext_mark_uninitialized(ex);
 
                 if (ex + 1 < EXT_LAST_EXTENT(eh)) {
                         len = (EXT_LAST_EXTENT(eh) - ex - 1)
@@ -1896,7 +1903,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
         struct ext4_ext_path *npath = NULL;
         int depth, len, err;
         ext4_lblk_t next;
-        int mb_flags = 0;
+        int mb_flags = 0, uninit;
 
         if (unlikely(ext4_ext_get_actual_len(newext) == 0)) {
                 EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0");
@@ -1946,9 +1953,11 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
                                                   path + depth);
                         if (err)
                                 return err;
-
+                        uninit = ext4_ext_is_uninitialized(ex);
                         ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
                                         + ext4_ext_get_actual_len(newext));
+                        if (uninit)
+                                ext4_ext_mark_uninitialized(ex);
                         eh = path[depth].p_hdr;
                         nearex = ex;
                         goto merge;
@@ -1971,10 +1980,13 @@ prepend:
                         if (err)
                                 return err;
 
+                        uninit = ext4_ext_is_uninitialized(ex);
                         ex->ee_block = newext->ee_block;
                         ext4_ext_store_pblock(ex, ext4_ext_pblock(newext));
                         ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
                                         + ext4_ext_get_actual_len(newext));
+                        if (uninit)
+                                ext4_ext_mark_uninitialized(ex);
                         eh = path[depth].p_hdr;
                         nearex = ex;
                         goto merge;
@@ -2585,6 +2597,27 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
         ex_ee_block = le32_to_cpu(ex->ee_block);
         ex_ee_len = ext4_ext_get_actual_len(ex);
 
+        /*
+         * If we're starting with an extent other than the last one in the
+         * node, we need to see if it shares a cluster with the extent to
+         * the right (towards the end of the file). If its leftmost cluster
+         * is this extent's rightmost cluster and it is not cluster aligned,
+         * we'll mark it as a partial that is not to be deallocated.
+         */
+
+        if (ex != EXT_LAST_EXTENT(eh)) {
+                ext4_fsblk_t current_pblk, right_pblk;
+                long long current_cluster, right_cluster;
+
+                current_pblk = ext4_ext_pblock(ex) + ex_ee_len - 1;
+                current_cluster = (long long)EXT4_B2C(sbi, current_pblk);
+                right_pblk = ext4_ext_pblock(ex + 1);
+                right_cluster = (long long)EXT4_B2C(sbi, right_pblk);
+                if (current_cluster == right_cluster &&
+                        EXT4_PBLK_COFF(sbi, right_pblk))
+                        *partial_cluster = -right_cluster;
+        }
+
         trace_ext4_ext_rm_leaf(inode, start, ex, *partial_cluster);
 
         while (ex >= EXT_FIRST_EXTENT(eh) &&
@@ -2710,10 +2743,15 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
                 err = ext4_ext_correct_indexes(handle, inode, path);
 
         /*
-         * Free the partial cluster only if the current extent does not
-         * reference it. Otherwise we might free used cluster.
+         * If there's a partial cluster and at least one extent remains in
+         * the leaf, free the partial cluster if it isn't shared with the
+         * current extent.  If there's a partial cluster and no extents
+         * remain in the leaf, it can't be freed here.  It can only be
+         * freed when it's possible to determine if it's not shared with
+         * any other extent - when the next leaf is processed or when space
+         * removal is complete.
          */
-        if (*partial_cluster > 0 &&
+        if (*partial_cluster > 0 && eh->eh_entries &&
             (EXT4_B2C(sbi, ext4_ext_pblock(ex) + ex_ee_len - 1) !=
              *partial_cluster)) {
                 int flags = get_default_free_blocks_flags(inode);
@@ -3569,6 +3607,8 @@ out:
  *   b> Splits in two extents: Write is happening at either end of the extent
  *   c> Splits in three extents: Somone is writing in middle of the extent
  *
+ * This works the same way in the case of initialized -> unwritten conversion.
+ *
  * One of more index blocks maybe needed if the extent tree grow after
  * the uninitialized extent split. To prevent ENOSPC occur at the IO
  * complete, we need to split the uninitialized extent before DIO submit
@@ -3579,7 +3619,7 @@ out:
  *
  * Returns the size of uninitialized extent to be written on success.
  */
-static int ext4_split_unwritten_extents(handle_t *handle,
+static int ext4_split_convert_extents(handle_t *handle,
                                         struct inode *inode,
                                         struct ext4_map_blocks *map,
                                         struct ext4_ext_path *path,
@@ -3591,9 +3631,9 @@ static int ext4_split_unwritten_extents(handle_t *handle,
         unsigned int ee_len;
         int split_flag = 0, depth;
 
-        ext_debug("ext4_split_unwritten_extents: inode %lu, logical"
-                "block %llu, max_blocks %u\n", inode->i_ino,
-                (unsigned long long)map->m_lblk, map->m_len);
+        ext_debug("%s: inode %lu, logical block %llu, max_blocks %u\n",
+                  __func__, inode->i_ino,
+                  (unsigned long long)map->m_lblk, map->m_len);
 
         eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
                 inode->i_sb->s_blocksize_bits;
@@ -3608,14 +3648,73 @@ static int ext4_split_unwritten_extents(handle_t *handle,
         ee_block = le32_to_cpu(ex->ee_block);
         ee_len = ext4_ext_get_actual_len(ex);
 
-        split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0;
-        split_flag |= EXT4_EXT_MARK_UNINIT2;
-        if (flags & EXT4_GET_BLOCKS_CONVERT)
-                split_flag |= EXT4_EXT_DATA_VALID2;
+        /* Convert to unwritten */
+        if (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN) {
+                split_flag |= EXT4_EXT_DATA_VALID1;
+        /* Convert to initialized */
+        } else if (flags & EXT4_GET_BLOCKS_CONVERT) {
+                split_flag |= ee_block + ee_len <= eof_block ?
+                              EXT4_EXT_MAY_ZEROOUT : 0;
+                split_flag |= (EXT4_EXT_MARK_UNINIT2 | EXT4_EXT_DATA_VALID2);
+        }
         flags |= EXT4_GET_BLOCKS_PRE_IO;
         return ext4_split_extent(handle, inode, path, map, split_flag, flags);
 }
 
+static int ext4_convert_initialized_extents(handle_t *handle,
+                                            struct inode *inode,
+                                            struct ext4_map_blocks *map,
+                                            struct ext4_ext_path *path)
+{
+        struct ext4_extent *ex;
+        ext4_lblk_t ee_block;
+        unsigned int ee_len;
+        int depth;
+        int err = 0;
+
+        depth = ext_depth(inode);
+        ex = path[depth].p_ext;
+        ee_block = le32_to_cpu(ex->ee_block);
+        ee_len = ext4_ext_get_actual_len(ex);
+
+        ext_debug("%s: inode %lu, logical"
+                "block %llu, max_blocks %u\n", __func__, inode->i_ino,
+                  (unsigned long long)ee_block, ee_len);
+
+        if (ee_block != map->m_lblk || ee_len > map->m_len) {
+                err = ext4_split_convert_extents(handle, inode, map, path,
+                                EXT4_GET_BLOCKS_CONVERT_UNWRITTEN);
+                if (err < 0)
+                        goto out;
+                ext4_ext_drop_refs(path);
+                path = ext4_ext_find_extent(inode, map->m_lblk, path, 0);
+                if (IS_ERR(path)) {
+                        err = PTR_ERR(path);
+                        goto out;
+                }
+                depth = ext_depth(inode);
+                ex = path[depth].p_ext;
+        }
+
+        err = ext4_ext_get_access(handle, inode, path + depth);
+        if (err)
+                goto out;
+        /* first mark the extent as uninitialized */
+        ext4_ext_mark_uninitialized(ex);
+
+        /* note: ext4_ext_correct_indexes() isn't needed here because
+         * borders are not changed
+         */
+        ext4_ext_try_to_merge(handle, inode, path, ex);
+
+        /* Mark modified extent as dirty */
+        err = ext4_ext_dirty(handle, inode, path + path->p_depth);
+out:
+        ext4_ext_show_leaf(inode, path);
+        return err;
+}
+
+
 static int ext4_convert_unwritten_extents_endio(handle_t *handle,
                                                 struct inode *inode,
                                                 struct ext4_map_blocks *map,
@@ -3649,8 +3748,8 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle,
                              inode->i_ino, (unsigned long long)ee_block, ee_len,
                              (unsigned long long)map->m_lblk, map->m_len);
 #endif
-                err = ext4_split_unwritten_extents(handle, inode, map, path,
-                                                   EXT4_GET_BLOCKS_CONVERT);
+                err = ext4_split_convert_extents(handle, inode, map, path,
+                                                 EXT4_GET_BLOCKS_CONVERT);
                 if (err < 0)
                         goto out;
                 ext4_ext_drop_refs(path);
@@ -3851,6 +3950,38 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start,
 }
 
 static int
+ext4_ext_convert_initialized_extent(handle_t *handle, struct inode *inode,
+                        struct ext4_map_blocks *map,
+                        struct ext4_ext_path *path, int flags,
+                        unsigned int allocated, ext4_fsblk_t newblock)
+{
+        int ret = 0;
+        int err = 0;
+
+        /*
+         * Make sure that the extent is no bigger than we support with
+         * uninitialized extent
+         */
+        if (map->m_len > EXT_UNINIT_MAX_LEN)
+                map->m_len = EXT_UNINIT_MAX_LEN / 2;
+
+        ret = ext4_convert_initialized_extents(handle, inode, map,
+                                                path);
+        if (ret >= 0) {
+                ext4_update_inode_fsync_trans(handle, inode, 1);
+                err = check_eofblocks_fl(handle, inode, map->m_lblk,
+                                         path, map->m_len);
+        } else
+                err = ret;
+        map->m_flags |= EXT4_MAP_UNWRITTEN;
+        if (allocated > map->m_len)
+                allocated = map->m_len;
+        map->m_len = allocated;
+
+        return err ? err : allocated;
+}
+
+static int
 ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
                         struct ext4_map_blocks *map,
                         struct ext4_ext_path *path, int flags,
@@ -3877,8 +4008,8 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 
         /* get_block() before submit the IO, split the extent */
         if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
-                ret = ext4_split_unwritten_extents(handle, inode, map,
-                                                   path, flags);
+                ret = ext4_split_convert_extents(handle, inode, map,
+                                         path, flags | EXT4_GET_BLOCKS_CONVERT);
                 if (ret <= 0)
                         goto out;
                 /*
@@ -3993,10 +4124,6 @@ out1:
         map->m_pblk = newblock;
         map->m_len = allocated;
 out2:
-        if (path) {
-                ext4_ext_drop_refs(path);
-                kfree(path);
-        }
         return err ? err : allocated;
 }
 
@@ -4128,7 +4255,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
         struct ext4_extent newex, *ex, *ex2;
         struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
         ext4_fsblk_t newblock = 0;
-        int free_on_err = 0, err = 0, depth;
+        int free_on_err = 0, err = 0, depth, ret;
         unsigned int allocated = 0, offset = 0;
         unsigned int allocated_clusters = 0;
         struct ext4_allocation_request ar;
@@ -4170,6 +4297,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
                 ext4_fsblk_t ee_start = ext4_ext_pblock(ex);
                 unsigned short ee_len;
 
+
                 /*
                  * Uninitialized extents are treated as holes, except that
                  * we split out initialized portions during a write.
@@ -4186,13 +4314,27 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
                         ext_debug("%u fit into %u:%d -> %llu\n", map->m_lblk,
                                   ee_block, ee_len, newblock);
 
-                        if (!ext4_ext_is_uninitialized(ex))
+                        /*
+                         * If the extent is initialized check whether the
+                         * caller wants to convert it to unwritten.
+                         */
+                        if ((!ext4_ext_is_uninitialized(ex)) &&
+                            (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) {
+                                allocated = ext4_ext_convert_initialized_extent(
+                                                handle, inode, map, path, flags,
+                                                allocated, newblock);
+                                goto out2;
+                        } else if (!ext4_ext_is_uninitialized(ex))
                                 goto out;
 
-                        allocated = ext4_ext_handle_uninitialized_extents(
+                        ret = ext4_ext_handle_uninitialized_extents(
                                 handle, inode, map, path, flags,
                                 allocated, newblock);
-                        goto out3;
+                        if (ret < 0)
+                                err = ret;
+                        else
+                                allocated = ret;
+                        goto out2;
                 }
         }
 
@@ -4473,7 +4615,6 @@ out2:
                 kfree(path);
         }
 
-out3:
         trace_ext4_ext_map_blocks_exit(inode, flags, map,
                                        err ? err : allocated);
         ext4_es_lru_add(inode);
@@ -4514,34 +4655,200 @@ retry:
         ext4_std_error(inode->i_sb, err);
 }
 
-static void ext4_falloc_update_inode(struct inode *inode,
-                                int mode, loff_t new_size, int update_ctime)
+static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
+                                  ext4_lblk_t len, int flags, int mode)
 {
-        struct timespec now;
+        struct inode *inode = file_inode(file);
+        handle_t *handle;
+        int ret = 0;
+        int ret2 = 0;
+        int retries = 0;
+        struct ext4_map_blocks map;
+        unsigned int credits;
 
-        if (update_ctime) {
-                now = current_fs_time(inode->i_sb);
-                if (!timespec_equal(&inode->i_ctime, &now))
-                        inode->i_ctime = now;
+        map.m_lblk = offset;
+        /*
+         * Don't normalize the request if it can fit in one extent so
+         * that it doesn't get unnecessarily split into multiple
+         * extents.
+         */
+        if (len <= EXT_UNINIT_MAX_LEN)
+                flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
+
+        /*
+         * credits to insert 1 extent into extent tree
+         */
+        credits = ext4_chunk_trans_blocks(inode, len);
+
+retry:
+        while (ret >= 0 && ret < len) {
+                map.m_lblk = map.m_lblk + ret;
+                map.m_len = len = len - ret;
+                handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
+                                            credits);
+                if (IS_ERR(handle)) {
+                        ret = PTR_ERR(handle);
+                        break;
+                }
+                ret = ext4_map_blocks(handle, inode, &map, flags);
+                if (ret <= 0) {
+                        ext4_debug("inode #%lu: block %u: len %u: "
+                                   "ext4_ext_map_blocks returned %d",
+                                   inode->i_ino, map.m_lblk,
+                                   map.m_len, ret);
+                        ext4_mark_inode_dirty(handle, inode);
+                        ret2 = ext4_journal_stop(handle);
+                        break;
+                }
+                ret2 = ext4_journal_stop(handle);
+                if (ret2)
+                        break;
+        }
+        if (ret == -ENOSPC &&
+                        ext4_should_retry_alloc(inode->i_sb, &retries)) {
+                ret = 0;
+                goto retry;
         }
+
+        return ret > 0 ? ret2 : ret;
+}
+
+static long ext4_zero_range(struct file *file, loff_t offset,
+                            loff_t len, int mode)
+{
+        struct inode *inode = file_inode(file);
+        handle_t *handle = NULL;
+        unsigned int max_blocks;
+        loff_t new_size = 0;
+        int ret = 0;
+        int flags;
+        int partial;
+        loff_t start, end;
+        ext4_lblk_t lblk;
+        struct address_space *mapping = inode->i_mapping;
+        unsigned int blkbits = inode->i_blkbits;
+
+        trace_ext4_zero_range(inode, offset, len, mode);
+
+        /*
+         * Write out all dirty pages to avoid race conditions
+         * Then release them.
+         */
+        if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
+                ret = filemap_write_and_wait_range(mapping, offset,
+                                                   offset + len - 1);
+                if (ret)
+                        return ret;
+        }
+
         /*
-         * Update only when preallocation was requested beyond
-         * the file size.
+         * Round up offset. This is not fallocate, we neet to zero out
+         * blocks, so convert interior block aligned part of the range to
+         * unwritten and possibly manually zero out unaligned parts of the
+         * range.
          */
-        if (!(mode & FALLOC_FL_KEEP_SIZE)) {
+        start = round_up(offset, 1 << blkbits);
+        end = round_down((offset + len), 1 << blkbits);
+
+        if (start < offset || end > offset + len)
+                return -EINVAL;
+        partial = (offset + len) & ((1 << blkbits) - 1);
+
+        lblk = start >> blkbits;
+        max_blocks = (end >> blkbits);
+        if (max_blocks < lblk)
+                max_blocks = 0;
+        else
+                max_blocks -= lblk;
+
+        flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT |
+                EXT4_GET_BLOCKS_CONVERT_UNWRITTEN;
+        if (mode & FALLOC_FL_KEEP_SIZE)
+                flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
+
+        mutex_lock(&inode->i_mutex);
+
+        /*
+         * Indirect files do not support unwritten extnets
+         */
+        if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
+                ret = -EOPNOTSUPP;
+                goto out_mutex;
+        }
+
+        if (!(mode & FALLOC_FL_KEEP_SIZE) &&
+             offset + len > i_size_read(inode)) {
+                new_size = offset + len;
+                ret = inode_newsize_ok(inode, new_size);
+                if (ret)
+                        goto out_mutex;
+                /*
+                 * If we have a partial block after EOF we have to allocate
+                 * the entire block.
+                 */
+                if (partial)
+                        max_blocks += 1;
+        }
+
+        if (max_blocks > 0) {
+
+                /* Now release the pages and zero block aligned part of pages*/
+                truncate_pagecache_range(inode, start, end - 1);
+
+                /* Wait all existing dio workers, newcomers will block on i_mutex */
+                ext4_inode_block_unlocked_dio(inode);
+                inode_dio_wait(inode);
+
+                /*
+                 * Remove entire range from the extent status tree.
+                 */
+                ret = ext4_es_remove_extent(inode, lblk, max_blocks);
+                if (ret)
+                        goto out_dio;
+
+                ret = ext4_alloc_file_blocks(file, lblk, max_blocks, flags,
+                                             mode);
+                if (ret)
+                        goto out_dio;
+        }
+
+        handle = ext4_journal_start(inode, EXT4_HT_MISC, 4);
+        if (IS_ERR(handle)) {
+                ret = PTR_ERR(handle);
+                ext4_std_error(inode->i_sb, ret);
+                goto out_dio;
+        }
+
+        inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+
+        if (new_size) {
                 if (new_size > i_size_read(inode))
                         i_size_write(inode, new_size);
                 if (new_size > EXT4_I(inode)->i_disksize)
                         ext4_update_i_disksize(inode, new_size);
         } else {
                 /*
-                 * Mark that we allocate beyond EOF so the subsequent truncate
-                 * can proceed even if the new size is the same as i_size.
-                 */
-                if (new_size > i_size_read(inode))
+                * Mark that we allocate beyond EOF so the subsequent truncate
+                * can proceed even if the new size is the same as i_size.
+                */
+                if ((offset + len) > i_size_read(inode))
                         ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
         }
 
+        ext4_mark_inode_dirty(handle, inode);
+
+        /* Zero out partial block at the edges of the range */
+        ret = ext4_zero_partial_blocks(handle, inode, offset, len);
+
+        if (file->f_flags & O_SYNC)
+                ext4_handle_sync(handle);
+
+        ext4_journal_stop(handle);
+out_dio:
+        ext4_inode_resume_unlocked_dio(inode);
+out_mutex:
+        mutex_unlock(&inode->i_mutex);
+        return ret;
 }
 
 /*
@@ -4555,22 +4862,25 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 {
         struct inode *inode = file_inode(file);
         handle_t *handle;
-        loff_t new_size;
+        loff_t new_size = 0;
         unsigned int max_blocks;
         int ret = 0;
-        int ret2 = 0;
-        int retries = 0;
         int flags;
-        struct ext4_map_blocks map;
-        unsigned int credits, blkbits = inode->i_blkbits;
+        ext4_lblk_t lblk;
+        struct timespec tv;
+        unsigned int blkbits = inode->i_blkbits;
 
         /* Return error if mode is not supported */
-        if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+        if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
+                     FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE))
                 return -EOPNOTSUPP;
 
         if (mode & FALLOC_FL_PUNCH_HOLE)
                 return ext4_punch_hole(inode, offset, len);
 
+        if (mode & FALLOC_FL_COLLAPSE_RANGE)
+                return ext4_collapse_range(inode, offset, len);
+
         ret = ext4_convert_inline_data(inode);
         if (ret)
                 return ret;
@@ -4582,83 +4892,66 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
         if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
                 return -EOPNOTSUPP;
 
+        if (mode & FALLOC_FL_ZERO_RANGE)
+                return ext4_zero_range(file, offset, len, mode);
+
         trace_ext4_fallocate_enter(inode, offset, len, mode);
-        map.m_lblk = offset >> blkbits;
+        lblk = offset >> blkbits;
         /*
          * We can't just convert len to max_blocks because
          * If blocksize = 4096 offset = 3072 and len = 2048
          */
         max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits)
-                - map.m_lblk;
-        /*
-         * credits to insert 1 extent into extent tree
-         */
-        credits = ext4_chunk_trans_blocks(inode, max_blocks);
-        mutex_lock(&inode->i_mutex);
-        ret = inode_newsize_ok(inode, (len + offset));
-        if (ret) {
-                mutex_unlock(&inode->i_mutex);
-                trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
-                return ret;
-        }
+                - lblk;
+
         flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT;
         if (mode & FALLOC_FL_KEEP_SIZE)
                 flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
-        /*
-         * Don't normalize the request if it can fit in one extent so
-         * that it doesn't get unnecessarily split into multiple
-         * extents.
-         */
-        if (len <= EXT_UNINIT_MAX_LEN << blkbits)
-                flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
 
-retry:
-        while (ret >= 0 && ret < max_blocks) {
-                map.m_lblk = map.m_lblk + ret;
-                map.m_len = max_blocks = max_blocks - ret;
-                handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
-                                            credits);
-                if (IS_ERR(handle)) {
-                        ret = PTR_ERR(handle);
-                        break;
-                }
-                ret = ext4_map_blocks(handle, inode, &map, flags);
-                if (ret <= 0) {
-#ifdef EXT4FS_DEBUG
-                        ext4_warning(inode->i_sb,
-                                     "inode #%lu: block %u: len %u: "
-                                     "ext4_ext_map_blocks returned %d",
-                                     inode->i_ino, map.m_lblk,
-                                     map.m_len, ret);
-#endif
-                        ext4_mark_inode_dirty(handle, inode);
-                        ret2 = ext4_journal_stop(handle);
-                        break;
-                }
-                if ((map.m_lblk + ret) >= (EXT4_BLOCK_ALIGN(offset + len,
-                                                blkbits) >> blkbits))
-                        new_size = offset + len;
-                else
-                        new_size = ((loff_t) map.m_lblk + ret) << blkbits;
+        mutex_lock(&inode->i_mutex);
 
-                ext4_falloc_update_inode(inode, mode, new_size,
-                                         (map.m_flags & EXT4_MAP_NEW));
-                ext4_mark_inode_dirty(handle, inode);
-                if ((file->f_flags & O_SYNC) && ret >= max_blocks)
-                        ext4_handle_sync(handle);
-                ret2 = ext4_journal_stop(handle);
-                if (ret2)
-                        break;
+        if (!(mode & FALLOC_FL_KEEP_SIZE) &&
+             offset + len > i_size_read(inode)) {
+                new_size = offset + len;
+                ret = inode_newsize_ok(inode, new_size);
+                if (ret)
+                        goto out;
         }
-        if (ret == -ENOSPC &&
-                        ext4_should_retry_alloc(inode->i_sb, &retries)) {
-                ret = 0;
-                goto retry;
+
+        ret = ext4_alloc_file_blocks(file, lblk, max_blocks, flags, mode);
+        if (ret)
+                goto out;
+
+        handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+        if (IS_ERR(handle))
+                goto out;
+
+        tv = inode->i_ctime = ext4_current_time(inode);
+
+        if (new_size) {
+                if (new_size > i_size_read(inode)) {
+                        i_size_write(inode, new_size);
+                        inode->i_mtime = tv;
+                }
+                if (new_size > EXT4_I(inode)->i_disksize)
+                        ext4_update_i_disksize(inode, new_size);
+        } else {
+                /*
+                * Mark that we allocate beyond EOF so the subsequent truncate
+                * can proceed even if the new size is the same as i_size.
+                */
+                if ((offset + len) > i_size_read(inode))
+                        ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
         }
+        ext4_mark_inode_dirty(handle, inode);
+        if (file->f_flags & O_SYNC)
+                ext4_handle_sync(handle);
+
+        ext4_journal_stop(handle);
+out:
         mutex_unlock(&inode->i_mutex);
-        trace_ext4_fallocate_exit(inode, offset, max_blocks,
-                                ret > 0 ? ret2 : ret);
-        return ret > 0 ? ret2 : ret;
+        trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
+        return ret;
 }
 
 /*
@@ -4869,3 +5162,304 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
         ext4_es_lru_add(inode);
         return error;
 }
+
+/*
+ * ext4_access_path:
+ * Function to access the path buffer for marking it dirty.
+ * It also checks if there are sufficient credits left in the journal handle
+ * to update path.
+ */
+static int
+ext4_access_path(handle_t *handle, struct inode *inode,
+                struct ext4_ext_path *path)
+{
+        int credits, err;
+
+        if (!ext4_handle_valid(handle))
+                return 0;
+
+        /*
+         * Check if need to extend journal credits
+         * 3 for leaf, sb, and inode plus 2 (bmap and group
+         * descriptor) for each block group; assume two block
+         * groups
+         */
+        if (handle->h_buffer_credits < 7) {
+                credits = ext4_writepage_trans_blocks(inode);
+                err = ext4_ext_truncate_extend_restart(handle, inode, credits);
+                /* EAGAIN is success */
+                if (err && err != -EAGAIN)
+                        return err;
+        }
+
+        err = ext4_ext_get_access(handle, inode, path);
+        return err;
+}
+
+/*
+ * ext4_ext_shift_path_extents:
+ * Shift the extents of a path structure lying between path[depth].p_ext
+ * and EXT_LAST_EXTENT(path[depth].p_hdr) downwards, by subtracting shift
+ * from starting block for each extent.
+ */
+static int
+ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift,
+                            struct inode *inode, handle_t *handle,
+                            ext4_lblk_t *start)
+{
+        int depth, err = 0;
+        struct ext4_extent *ex_start, *ex_last;
+        bool update = 0;
+        depth = path->p_depth;
+
+        while (depth >= 0) {
+                if (depth == path->p_depth) {
+                        ex_start = path[depth].p_ext;
+                        if (!ex_start)
+                                return -EIO;
+
+                        ex_last = EXT_LAST_EXTENT(path[depth].p_hdr);
+                        if (!ex_last)
+                                return -EIO;
+
+                        err = ext4_access_path(handle, inode, path + depth);
+                        if (err)
+                                goto out;
+
+                        if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr))
+                                update = 1;
+
+                        *start = ex_last->ee_block +
+                                ext4_ext_get_actual_len(ex_last);
+
+                        while (ex_start <= ex_last) {
+                                ex_start->ee_block -= shift;
+                                if (ex_start >
+                                        EXT_FIRST_EXTENT(path[depth].p_hdr)) {
+                                        if (ext4_ext_try_to_merge_right(inode,
+                                                path, ex_start - 1))
+                                                ex_last--;
+                                }
+                                ex_start++;
+                        }
+                        err = ext4_ext_dirty(handle, inode, path + depth);
+                        if (err)
+                                goto out;
+
+                        if (--depth < 0 || !update)
+                                break;
+                }
+
+                /* Update index too */
+                err = ext4_access_path(handle, inode, path + depth);
+                if (err)
+                        goto out;
+
+                path[depth].p_idx->ei_block -= shift;
+                err = ext4_ext_dirty(handle, inode, path + depth);
+                if (err)
+                        goto out;
+
+                /* we are done if current index is not a starting index */
+                if (path[depth].p_idx != EXT_FIRST_INDEX(path[depth].p_hdr))
+                        break;
+
+                depth--;
+        }
+
+out:
+        return err;
+}
+
+/*
+ * ext4_ext_shift_extents:
+ * All the extents which lies in the range from start to the last allocated
+ * block for the file are shifted downwards by shift blocks.
+ * On success, 0 is returned, error otherwise.
+ */
+static int
+ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
+                       ext4_lblk_t start, ext4_lblk_t shift)
+{
+        struct ext4_ext_path *path;
+        int ret = 0, depth;
+        struct ext4_extent *extent;
+        ext4_lblk_t stop_block, current_block;
+        ext4_lblk_t ex_start, ex_end;
+
+        /* Let path point to the last extent */
+        path = ext4_ext_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, 0);
+        if (IS_ERR(path))
+                return PTR_ERR(path);
+
+        depth = path->p_depth;
+        extent = path[depth].p_ext;
+        if (!extent) {
+                ext4_ext_drop_refs(path);
+                kfree(path);
+                return ret;
+        }
+
+        stop_block = extent->ee_block + ext4_ext_get_actual_len(extent);
+        ext4_ext_drop_refs(path);
+        kfree(path);
+
+        /* Nothing to shift, if hole is at the end of file */
+        if (start >= stop_block)
+                return ret;
+
+        /*
+         * Don't start shifting extents until we make sure the hole is big
+         * enough to accomodate the shift.
+         */
+        path = ext4_ext_find_extent(inode, start - 1, NULL, 0);
+        depth = path->p_depth;
+        extent =  path[depth].p_ext;
+        ex_start = extent->ee_block;
+        ex_end = extent->ee_block + ext4_ext_get_actual_len(extent);
+        ext4_ext_drop_refs(path);
+        kfree(path);
+
+        if ((start == ex_start && shift > ex_start) ||
+            (shift > start - ex_end))
+                return -EINVAL;
+
+        /* Its safe to start updating extents */
+        while (start < stop_block) {
+                path = ext4_ext_find_extent(inode, start, NULL, 0);
+                if (IS_ERR(path))
+                        return PTR_ERR(path);
+                depth = path->p_depth;
+                extent = path[depth].p_ext;
+                current_block = extent->ee_block;
+                if (start > current_block) {
+                        /* Hole, move to the next extent */
+                        ret = mext_next_extent(inode, path, &extent);
+                        if (ret != 0) {
+                                ext4_ext_drop_refs(path);
+                                kfree(path);
+                                if (ret == 1)
+                                        ret = 0;
+                                break;
+                        }
+                }
+                ret = ext4_ext_shift_path_extents(path, shift, inode,
+                                handle, &start);
+                ext4_ext_drop_refs(path);
+                kfree(path);
+                if (ret)
+                        break;
+        }
+
+        return ret;
+}
+
+/*
+ * ext4_collapse_range:
+ * This implements the fallocate's collapse range functionality for ext4
+ * Returns: 0 and non-zero on error.
+ */
+int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
+{
+        struct super_block *sb = inode->i_sb;
+        ext4_lblk_t punch_start, punch_stop;
+        handle_t *handle;
+        unsigned int credits;
+        loff_t new_size;
+        int ret;
+
+        BUG_ON(offset + len > i_size_read(inode));
+
+        /* Collapse range works only on fs block size aligned offsets. */
+        if (offset & (EXT4_BLOCK_SIZE(sb) - 1) ||
+            len & (EXT4_BLOCK_SIZE(sb) - 1))
+                return -EINVAL;
+
+        if (!S_ISREG(inode->i_mode))
+                return -EOPNOTSUPP;
+
+        trace_ext4_collapse_range(inode, offset, len);
+
+        punch_start = offset >> EXT4_BLOCK_SIZE_BITS(sb);
+        punch_stop = (offset + len) >> EXT4_BLOCK_SIZE_BITS(sb);
+
+        /* Write out all dirty pages */
+        ret = filemap_write_and_wait_range(inode->i_mapping, offset, -1);
+        if (ret)
+                return ret;
+
+        /* Take mutex lock */
+        mutex_lock(&inode->i_mutex);
+
+        /* It's not possible punch hole on append only file */
+        if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) {
+                ret = -EPERM;
+                goto out_mutex;
+        }
+
+        if (IS_SWAPFILE(inode)) {
+                ret = -ETXTBSY;
+                goto out_mutex;
+        }
+
+        /* Currently just for extent based files */
+        if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+                ret = -EOPNOTSUPP;
+                goto out_mutex;
+        }
+
+        truncate_pagecache_range(inode, offset, -1);
+
+        /* Wait for existing dio to complete */
+        ext4_inode_block_unlocked_dio(inode);
+        inode_dio_wait(inode);
+
+        credits = ext4_writepage_trans_blocks(inode);
+        handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
+        if (IS_ERR(handle)) {
+                ret = PTR_ERR(handle);
+                goto out_dio;
+        }
+
+        down_write(&EXT4_I(inode)->i_data_sem);
+        ext4_discard_preallocations(inode);
+
+        ret = ext4_es_remove_extent(inode, punch_start,
+                                    EXT_MAX_BLOCKS - punch_start - 1);
+        if (ret) {
+                up_write(&EXT4_I(inode)->i_data_sem);
+                goto out_stop;
+        }
+
+        ret = ext4_ext_remove_space(inode, punch_start, punch_stop - 1);
+        if (ret) {
+                up_write(&EXT4_I(inode)->i_data_sem);
+                goto out_stop;
+        }
+
+        ret = ext4_ext_shift_extents(inode, handle, punch_stop,
+                                     punch_stop - punch_start);
+        if (ret) {
+                up_write(&EXT4_I(inode)->i_data_sem);
+                goto out_stop;
+        }
+
+        new_size = i_size_read(inode) - len;
+        truncate_setsize(inode, new_size);
+        EXT4_I(inode)->i_disksize = new_size;
+
+        ext4_discard_preallocations(inode);
+        up_write(&EXT4_I(inode)->i_data_sem);
+        if (IS_SYNC(inode))
+                ext4_handle_sync(handle);
+        inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+        ext4_mark_inode_dirty(handle, inode);
+
+out_stop:
+        ext4_journal_stop(handle);
+out_dio:
+        ext4_inode_resume_unlocked_dio(inode);
+out_mutex:
+        mutex_unlock(&inode->i_mutex);
+        return ret;
+}