aboutsummaryrefslogtreecommitdiff
path: root/fs/ext4/extents.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4/extents.c')
-rw-r--r--fs/ext4/extents.c646
1 files changed, 409 insertions, 237 deletions
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 765a4826b118..377309c1af65 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -107,11 +107,8 @@ static int ext4_ext_truncate_extend_restart(handle_t *handle,
if (err <= 0)
return err;
err = ext4_truncate_restart_trans(handle, inode, needed);
- /*
- * We have dropped i_data_sem so someone might have cached again
- * an extent we are going to truncate.
- */
- ext4_ext_invalidate_cache(inode);
+ if (err == 0)
+ err = -EAGAIN;
return err;
}
@@ -185,18 +182,17 @@ static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
if (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) {
/*
* If there are at least EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME
- * block groups per flexgroup, reserve the first block
- * group for directories and special files. Regular
+ * block groups per flexgroup, reserve the first block
+ * group for directories and special files. Regular
* files will start at the second block group. This
- * tends to speed up directory access and improves
+ * tends to speed up directory access and improves
* fsck times.
*/
block_group &= ~(flex_size-1);
if (S_ISREG(inode->i_mode))
block_group++;
}
- bg_start = (block_group * EXT4_BLOCKS_PER_GROUP(inode->i_sb)) +
- le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_first_data_block);
+ bg_start = ext4_group_first_block_no(inode->i_sb, block_group);
last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1;
/*
@@ -440,10 +436,10 @@ static int __ext4_ext_check(const char *function, struct inode *inode,
return 0;
corrupted:
- ext4_error(inode->i_sb, function,
- "bad header/extent in inode #%lu: %s - magic %x, "
+ ext4_error_inode(function, inode,
+ "bad header/extent: %s - magic %x, "
"entries %u, max %u(%u), depth %u(%u)",
- inode->i_ino, error_msg, le16_to_cpu(eh->eh_magic),
+ error_msg, le16_to_cpu(eh->eh_magic),
le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max),
max, le16_to_cpu(eh->eh_depth), depth);
@@ -703,7 +699,12 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
}
eh = ext_block_hdr(bh);
ppos++;
- BUG_ON(ppos > depth);
+ if (unlikely(ppos > depth)) {
+ put_bh(bh);
+ EXT4_ERROR_INODE(inode,
+ "ppos %d > depth %d", ppos, depth);
+ goto err;
+ }
path[ppos].p_bh = bh;
path[ppos].p_hdr = eh;
i--;
@@ -749,7 +750,12 @@ int ext4_ext_insert_index(handle_t *handle, struct inode *inode,
if (err)
return err;
- BUG_ON(logical == le32_to_cpu(curp->p_idx->ei_block));
+ if (unlikely(logical == le32_to_cpu(curp->p_idx->ei_block))) {
+ EXT4_ERROR_INODE(inode,
+ "logical %d == ei_block %d!",
+ logical, le32_to_cpu(curp->p_idx->ei_block));
+ return -EIO;
+ }
len = EXT_MAX_INDEX(curp->p_hdr) - curp->p_idx;
if (logical > le32_to_cpu(curp->p_idx->ei_block)) {
/* insert after */
@@ -779,9 +785,17 @@ int ext4_ext_insert_index(handle_t *handle, struct inode *inode,
ext4_idx_store_pblock(ix, ptr);
le16_add_cpu(&curp->p_hdr->eh_entries, 1);
- BUG_ON(le16_to_cpu(curp->p_hdr->eh_entries)
- > le16_to_cpu(curp->p_hdr->eh_max));
- BUG_ON(ix > EXT_LAST_INDEX(curp->p_hdr));
+ if (unlikely(le16_to_cpu(curp->p_hdr->eh_entries)
+ > le16_to_cpu(curp->p_hdr->eh_max))) {
+ EXT4_ERROR_INODE(inode,
+ "logical %d == ei_block %d!",
+ logical, le32_to_cpu(curp->p_idx->ei_block));
+ return -EIO;
+ }
+ if (unlikely(ix > EXT_LAST_INDEX(curp->p_hdr))) {
+ EXT4_ERROR_INODE(inode, "ix > EXT_LAST_INDEX!");
+ return -EIO;
+ }
err = ext4_ext_dirty(handle, inode, curp);
ext4_std_error(inode->i_sb, err);
@@ -819,7 +833,10 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
/* if current leaf will be split, then we should use
* border from split point */
- BUG_ON(path[depth].p_ext > EXT_MAX_EXTENT(path[depth].p_hdr));
+ if (unlikely(path[depth].p_ext > EXT_MAX_EXTENT(path[depth].p_hdr))) {
+ EXT4_ERROR_INODE(inode, "p_ext > EXT_MAX_EXTENT!");
+ return -EIO;
+ }
if (path[depth].p_ext != EXT_MAX_EXTENT(path[depth].p_hdr)) {
border = path[depth].p_ext[1].ee_block;
ext_debug("leaf will be split."
@@ -860,7 +877,11 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
/* initialize new leaf */
newblock = ablocks[--a];
- BUG_ON(newblock == 0);
+ if (unlikely(newblock == 0)) {
+ EXT4_ERROR_INODE(inode, "newblock == 0!");
+ err = -EIO;
+ goto cleanup;
+ }
bh = sb_getblk(inode->i_sb, newblock);
if (!bh) {
err = -EIO;
@@ -880,7 +901,14 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
ex = EXT_FIRST_EXTENT(neh);
/* move remainder of path[depth] to the new leaf */
- BUG_ON(path[depth].p_hdr->eh_entries != path[depth].p_hdr->eh_max);
+ if (unlikely(path[depth].p_hdr->eh_entries !=
+ path[depth].p_hdr->eh_max)) {
+ EXT4_ERROR_INODE(inode, "eh_entries %d != eh_max %d!",
+ path[depth].p_hdr->eh_entries,
+ path[depth].p_hdr->eh_max);
+ err = -EIO;
+ goto cleanup;
+ }
/* start copy from next extent */
/* TODO: we could do it by single memmove */
m = 0;
@@ -927,7 +955,11 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
/* create intermediate indexes */
k = depth - at - 1;
- BUG_ON(k < 0);
+ if (unlikely(k < 0)) {
+ EXT4_ERROR_INODE(inode, "k %d < 0!", k);
+ err = -EIO;
+ goto cleanup;
+ }
if (k)
ext_debug("create %d intermediate indices\n", k);
/* insert new index into current index block */
@@ -964,8 +996,14 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
ext_debug("cur 0x%p, last 0x%p\n", path[i].p_idx,
EXT_MAX_INDEX(path[i].p_hdr));
- BUG_ON(EXT_MAX_INDEX(path[i].p_hdr) !=
- EXT_LAST_INDEX(path[i].p_hdr));
+ if (unlikely(EXT_MAX_INDEX(path[i].p_hdr) !=
+ EXT_LAST_INDEX(path[i].p_hdr))) {
+ EXT4_ERROR_INODE(inode,
+ "EXT_MAX_INDEX != EXT_LAST_INDEX ee_block %d!",
+ le32_to_cpu(path[i].p_ext->ee_block));
+ err = -EIO;
+ goto cleanup;
+ }
while (path[i].p_idx <= EXT_MAX_INDEX(path[i].p_hdr)) {
ext_debug("%d: move %d:%llu in new index %llu\n", i,
le32_to_cpu(path[i].p_idx->ei_block),
@@ -1203,7 +1241,10 @@ ext4_ext_search_left(struct inode *inode, struct ext4_ext_path *path,
struct ext4_extent *ex;
int depth, ee_len;
- BUG_ON(path == NULL);
+ if (unlikely(path == NULL)) {
+ EXT4_ERROR_INODE(inode, "path == NULL *logical %d!", *logical);
+ return -EIO;
+ }
depth = path->p_depth;
*phys = 0;
@@ -1217,15 +1258,33 @@ ext4_ext_search_left(struct inode *inode, struct ext4_ext_path *path,
ex = path[depth].p_ext;
ee_len = ext4_ext_get_actual_len(ex);
if (*logical < le32_to_cpu(ex->ee_block)) {
- BUG_ON(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex);
+ if (unlikely(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex)) {
+ EXT4_ERROR_INODE(inode,
+ "EXT_FIRST_EXTENT != ex *logical %d ee_block %d!",
+ *logical, le32_to_cpu(ex->ee_block));
+ return -EIO;
+ }
while (--depth >= 0) {
ix = path[depth].p_idx;
- BUG_ON(ix != EXT_FIRST_INDEX(path[depth].p_hdr));
+ if (unlikely(ix != EXT_FIRST_INDEX(path[depth].p_hdr))) {
+ EXT4_ERROR_INODE(inode,
+ "ix (%d) != EXT_FIRST_INDEX (%d) (depth %d)!",
+ ix != NULL ? ix->ei_block : 0,
+ EXT_FIRST_INDEX(path[depth].p_hdr) != NULL ?
+ EXT_FIRST_INDEX(path[depth].p_hdr)->ei_block : 0,
+ depth);
+ return -EIO;
+ }
}
return 0;
}
- BUG_ON(*logical < (le32_to_cpu(ex->ee_block) + ee_len));
+ if (unlikely(*logical < (le32_to_cpu(ex->ee_block) + ee_len))) {
+ EXT4_ERROR_INODE(inode,
+ "logical %d < ee_block %d + ee_len %d!",
+ *logical, le32_to_cpu(ex->ee_block), ee_len);
+ return -EIO;
+ }
*logical = le32_to_cpu(ex->ee_block) + ee_len - 1;
*phys = ext_pblock(ex) + ee_len - 1;
@@ -1251,7 +1310,10 @@ ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path,
int depth; /* Note, NOT eh_depth; depth from top of tree */
int ee_len;
- BUG_ON(path == NULL);
+ if (unlikely(path == NULL)) {
+ EXT4_ERROR_INODE(inode, "path == NULL *logical %d!", *logical);
+ return -EIO;
+ }
depth = path->p_depth;
*phys = 0;
@@ -1265,17 +1327,32 @@ ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path,
ex = path[depth].p_ext;
ee_len = ext4_ext_get_actual_len(ex);
if (*logical < le32_to_cpu(ex->ee_block)) {
- BUG_ON(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex);
+ if (unlikely(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex)) {
+ EXT4_ERROR_INODE(inode,
+ "first_extent(path[%d].p_hdr) != ex",
+ depth);
+ return -EIO;
+ }
while (--depth >= 0) {
ix = path[depth].p_idx;
- BUG_ON(ix != EXT_FIRST_INDEX(path[depth].p_hdr));
+ if (unlikely(ix != EXT_FIRST_INDEX(path[depth].p_hdr))) {
+ EXT4_ERROR_INODE(inode,
+ "ix != EXT_FIRST_INDEX *logical %d!",
+ *logical);
+ return -EIO;
+ }
}
*logical = le32_to_cpu(ex->ee_block);
*phys = ext_pblock(ex);
return 0;
}
- BUG_ON(*logical < (le32_to_cpu(ex->ee_block) + ee_len));
+ if (unlikely(*logical < (le32_to_cpu(ex->ee_block) + ee_len))) {
+ EXT4_ERROR_INODE(inode,
+ "logical %d < ee_block %d + ee_len %d!",
+ *logical, le32_to_cpu(ex->ee_block), ee_len);
+ return -EIO;
+ }
if (ex != EXT_LAST_EXTENT(path[depth].p_hdr)) {
/* next allocated block in this leaf */
@@ -1414,8 +1491,12 @@ static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode,
eh = path[depth].p_hdr;
ex = path[depth].p_ext;
- BUG_ON(ex == NULL);
- BUG_ON(eh == NULL);
+
+ if (unlikely(ex == NULL || eh == NULL)) {
+ EXT4_ERROR_INODE(inode,
+ "ex %p == NULL or eh %p == NULL", ex, eh);
+ return -EIO;
+ }
if (depth == 0) {
/* there is no tree at all */
@@ -1538,8 +1619,7 @@ int ext4_ext_try_to_merge(struct inode *inode,
merge_done = 1;
WARN_ON(eh->eh_entries == 0);
if (!eh->eh_entries)
- ext4_error(inode->i_sb, "ext4_ext_try_to_merge",
- "inode#%lu, eh->eh_entries = 0!", inode->i_ino);
+ EXT4_ERROR_INODE(inode, "eh->eh_entries = 0!");
}
return merge_done;
@@ -1612,13 +1692,19 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
ext4_lblk_t next;
unsigned uninitialized = 0;
- BUG_ON(ext4_ext_get_actual_len(newext) == 0);
+ if (unlikely(ext4_ext_get_actual_len(newext) == 0)) {
+ EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0");
+ return -EIO;
+ }
depth = ext_depth(inode);
ex = path[depth].p_ext;
- BUG_ON(path[depth].p_hdr == NULL);
+ if (unlikely(path[depth].p_hdr == NULL)) {
+ EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth);
+ return -EIO;
+ }
/* try to insert block into found extent and return */
- if (ex && (flag != EXT4_GET_BLOCKS_DIO_CREATE_EXT)
+ if (ex && !(flag & EXT4_GET_BLOCKS_PRE_IO)
&& ext4_can_extents_be_merged(inode, ex, newext)) {
ext_debug("append [%d]%d block to %d:[%d]%d (from %llu)\n",
ext4_ext_is_uninitialized(newext),
@@ -1739,7 +1825,7 @@ has_space:
merge:
/* try to merge extents to the right */
- if (flag != EXT4_GET_BLOCKS_DIO_CREATE_EXT)
+ if (!(flag & EXT4_GET_BLOCKS_PRE_IO))
ext4_ext_try_to_merge(inode, path, nearex);
/* try to merge extents to the left */
@@ -1787,7 +1873,11 @@ int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block,
}
depth = ext_depth(inode);
- BUG_ON(path[depth].p_hdr == NULL);
+ if (unlikely(path[depth].p_hdr == NULL)) {
+ EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth);
+ err = -EIO;
+ break;
+ }
ex = path[depth].p_ext;
next = ext4_ext_next_allocated_block(path);
@@ -1838,7 +1928,11 @@ int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block,
cbex.ec_type = EXT4_EXT_CACHE_EXTENT;
}
- BUG_ON(cbex.ec_len == 0);
+ if (unlikely(cbex.ec_len == 0)) {
+ EXT4_ERROR_INODE(inode, "cbex.ec_len == 0");
+ err = -EIO;
+ break;
+ }
err = func(inode, path, &cbex, ex, cbdata);
ext4_ext_drop_refs(path);
@@ -1940,7 +2034,7 @@ ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block,
struct ext4_ext_cache *cex;
int ret = EXT4_EXT_CACHE_NO;
- /*
+ /*
* We borrow i_block_reservation_lock to protect i_cached_extent
*/
spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
@@ -1952,7 +2046,7 @@ ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block,
BUG_ON(cex->ec_type != EXT4_EXT_CACHE_GAP &&
cex->ec_type != EXT4_EXT_CACHE_EXTENT);
- if (block >= cex->ec_block && block < cex->ec_block + cex->ec_len) {
+ if (in_range(block, cex->ec_block, cex->ec_len)) {
ex->ee_block = cpu_to_le32(cex->ec_block);
ext4_ext_store_pblock(ex, cex->ec_start);
ex->ee_len = cpu_to_le16(cex->ec_len);
@@ -1981,7 +2075,10 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
/* free index block */
path--;
leaf = idx_pblock(path->p_idx);
- BUG_ON(path->p_hdr->eh_entries == 0);
+ if (unlikely(path->p_hdr->eh_entries == 0)) {
+ EXT4_ERROR_INODE(inode, "path->p_hdr->eh_entries == 0");
+ return -EIO;
+ }
err = ext4_ext_get_access(handle, inode, path);
if (err)
return err;
@@ -2119,8 +2216,10 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
if (!path[depth].p_hdr)
path[depth].p_hdr = ext_block_hdr(path[depth].p_bh);
eh = path[depth].p_hdr;
- BUG_ON(eh == NULL);
-
+ if (unlikely(path[depth].p_hdr == NULL)) {
+ EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth);
+ return -EIO;
+ }
/* find where to start removing */
ex = EXT_LAST_EXTENT(eh);
@@ -2257,7 +2356,7 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
int depth = ext_depth(inode);
struct ext4_ext_path *path;
handle_t *handle;
- int i = 0, err = 0;
+ int i, err;
ext_debug("truncate since %u\n", start);
@@ -2266,23 +2365,26 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
if (IS_ERR(handle))
return PTR_ERR(handle);
+again:
ext4_ext_invalidate_cache(inode);
/*
* We start scanning from right side, freeing all the blocks
* after i_size and walking into the tree depth-wise.
*/
+ depth = ext_depth(inode);
path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1), GFP_NOFS);
if (path == NULL) {
ext4_journal_stop(handle);
return -ENOMEM;
}
+ path[0].p_depth = depth;
path[0].p_hdr = ext_inode_hdr(inode);
if (ext4_ext_check(inode, path[0].p_hdr, depth)) {
err = -EIO;
goto out;
}
- path[0].p_depth = depth;
+ i = err = 0;
while (i >= 0 && err == 0) {
if (i == depth) {
@@ -2376,6 +2478,8 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
out:
ext4_ext_drop_refs(path);
kfree(path);
+ if (err == -EAGAIN)
+ goto again;
ext4_journal_stop(handle);
return err;
@@ -2440,7 +2544,7 @@ static void bi_complete(struct bio *bio, int error)
/* FIXME!! we need to try to merge to left or right after zero-out */
static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
{
- int ret = -EIO;
+ int ret;
struct bio *bio;
int blkbits, blocksize;
sector_t ee_pblock;
@@ -2464,6 +2568,9 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
len = ee_len;
bio = bio_alloc(GFP_NOIO, len);
+ if (!bio)
+ return -ENOMEM;
+
bio->bi_sector = ee_pblock;
bio->bi_bdev = inode->i_sb->s_bdev;
@@ -2491,22 +2598,20 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
submit_bio(WRITE, bio);
wait_for_completion(&event);
- if (test_bit(BIO_UPTODATE, &bio->bi_flags))
- ret = 0;
- else {
- ret = -EIO;
- break;
+ if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) {
+ bio_put(bio);
+ return -EIO;
}
bio_put(bio);
ee_len -= done;
ee_pblock += done << (blkbits - 9);
}
- return ret;
+ return 0;
}
#define EXT4_EXT_ZERO_LEN 7
/*
- * This function is called by ext4_ext_get_blocks() if someone tries to write
+ * This function is called by ext4_ext_map_blocks() if someone tries to write
* to an uninitialized extent. It may result in splitting the uninitialized
* extent into multiple extents (upto three - one initialized and two
* uninitialized).
@@ -2516,39 +2621,55 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
* c> Splits in three extents: Somone is writing in middle of the extent
*/
static int ext4_ext_convert_to_initialized(handle_t *handle,
- struct inode *inode,
- struct ext4_ext_path *path,
- ext4_lblk_t iblock,
- unsigned int max_blocks)
+ struct inode *inode,
+ struct ext4_map_blocks *map,
+ struct ext4_ext_path *path)
{
struct ext4_extent *ex, newex, orig_ex;
struct ext4_extent *ex1 = NULL;
struct ext4_extent *ex2 = NULL;
struct ext4_extent *ex3 = NULL;
struct ext4_extent_header *eh;
- ext4_lblk_t ee_block;
+ ext4_lblk_t ee_block, eof_block;
unsigned int allocated, ee_len, depth;
ext4_fsblk_t newblock;
int err = 0;
int ret = 0;
+ int may_zeroout;
+
+ ext_debug("ext4_ext_convert_to_initialized: inode %lu, logical"
+ "block %llu, max_blocks %u\n", 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;
+ if (eof_block < map->m_lblk + map->m_len)
+ eof_block = map->m_lblk + map->m_len;
depth = ext_depth(inode);
eh = path[depth].p_hdr;
ex = path[depth].p_ext;
ee_block = le32_to_cpu(ex->ee_block);
ee_len = ext4_ext_get_actual_len(ex);
- allocated = ee_len - (iblock - ee_block);
- newblock = iblock - ee_block + ext_pblock(ex);
+ allocated = ee_len - (map->m_lblk - ee_block);
+ newblock = map->m_lblk - ee_block + ext_pblock(ex);
+
ex2 = ex;
orig_ex.ee_block = ex->ee_block;
orig_ex.ee_len = cpu_to_le16(ee_len);
ext4_ext_store_pblock(&orig_ex, ext_pblock(ex));
+ /*
+ * It is safe to convert extent to initialized via explicit
+ * zeroout only if extent is fully insde i_size or new_size.
+ */
+ may_zeroout = ee_block + ee_len <= eof_block;
+
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
goto out;
/* If extent has less than 2*EXT4_EXT_ZERO_LEN zerout directly */
- if (ee_len <= 2*EXT4_EXT_ZERO_LEN) {
+ if (ee_len <= 2*EXT4_EXT_ZERO_LEN && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
@@ -2561,10 +2682,10 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
return allocated;
}
- /* ex1: ee_block to iblock - 1 : uninitialized */
- if (iblock > ee_block) {
+ /* ex1: ee_block to map->m_lblk - 1 : uninitialized */
+ if (map->m_lblk > ee_block) {
ex1 = ex;
- ex1->ee_len = cpu_to_le16(iblock - ee_block);
+ ex1->ee_len = cpu_to_le16(map->m_lblk - ee_block);
ext4_ext_mark_uninitialized(ex1);
ex2 = &newex;
}
@@ -2573,15 +2694,15 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
* we insert ex3, if ex1 is NULL. This is to avoid temporary
* overlap of blocks.
*/
- if (!ex1 && allocated > max_blocks)
- ex2->ee_len = cpu_to_le16(max_blocks);
+ if (!ex1 && allocated > map->m_len)
+ ex2->ee_len = cpu_to_le16(map->m_len);
/* ex3: to ee_block + ee_len : uninitialised */
- if (allocated > max_blocks) {
+ if (allocated > map->m_len) {
unsigned int newdepth;
/* If extent has less than EXT4_EXT_ZERO_LEN zerout directly */
- if (allocated <= EXT4_EXT_ZERO_LEN) {
+ if (allocated <= EXT4_EXT_ZERO_LEN && may_zeroout) {
/*
- * iblock == ee_block is handled by the zerouout
+ * map->m_lblk == ee_block is handled by the zerouout
* at the beginning.
* Mark first half uninitialized.
* Mark second half initialized and zero out the
@@ -2594,7 +2715,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
ext4_ext_dirty(handle, inode, path + depth);
ex3 = &newex;
- ex3->ee_block = cpu_to_le32(iblock);
+ ex3->ee_block = cpu_to_le32(map->m_lblk);
ext4_ext_store_pblock(ex3, newblock);
ex3->ee_len = cpu_to_le16(allocated);
err = ext4_ext_insert_extent(handle, inode, path,
@@ -2607,7 +2728,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
ex->ee_len = orig_ex.ee_len;
ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
ext4_ext_dirty(handle, inode, path + depth);
- /* blocks available from iblock */
+ /* blocks available from map->m_lblk */
return allocated;
} else if (err)
@@ -2629,8 +2750,8 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
*/
depth = ext_depth(inode);
ext4_ext_drop_refs(path);
- path = ext4_ext_find_extent(inode,
- iblock, path);
+ path = ext4_ext_find_extent(inode, map->m_lblk,
+ path);
if (IS_ERR(path)) {
err = PTR_ERR(path);
return err;
@@ -2650,12 +2771,12 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
return allocated;
}
ex3 = &newex;
- ex3->ee_block = cpu_to_le32(iblock + max_blocks);
- ext4_ext_store_pblock(ex3, newblock + max_blocks);
- ex3->ee_len = cpu_to_le16(allocated - max_blocks);
+ ex3->ee_block = cpu_to_le32(map->m_lblk + map->m_len);
+ ext4_ext_store_pblock(ex3, newblock + map->m_len);
+ ex3->ee_len = cpu_to_le16(allocated - map->m_len);
ext4_ext_mark_uninitialized(ex3);
err = ext4_ext_insert_extent(handle, inode, path, ex3, 0);
- if (err == -ENOSPC) {
+ if (err == -ENOSPC && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
@@ -2665,7 +2786,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
ext4_ext_dirty(handle, inode, path + depth);
/* zeroed the full extent */
- /* blocks available from iblock */
+ /* blocks available from map->m_lblk */
return allocated;
} else if (err)
@@ -2679,11 +2800,13 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
* update the extent length after successful insert of the
* split extent
*/
- orig_ex.ee_len = cpu_to_le16(ee_len -
- ext4_ext_get_actual_len(ex3));
+ ee_len -= ext4_ext_get_actual_len(ex3);
+ orig_ex.ee_len = cpu_to_le16(ee_len);
+ may_zeroout = ee_block + ee_len <= eof_block;
+
depth = newdepth;
ext4_ext_drop_refs(path);
- path = ext4_ext_find_extent(inode, iblock, path);
+ path = ext4_ext_find_extent(inode, map->m_lblk, path);
if (IS_ERR(path)) {
err = PTR_ERR(path);
goto out;
@@ -2697,14 +2820,14 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
if (err)
goto out;
- allocated = max_blocks;
+ allocated = map->m_len;
/* If extent has less than EXT4_EXT_ZERO_LEN and we are trying
* to insert a extent in the middle zerout directly
* otherwise give the extent a chance to merge to left
*/
if (le16_to_cpu(orig_ex.ee_len) <= EXT4_EXT_ZERO_LEN &&
- iblock != ee_block) {
+ map->m_lblk != ee_block && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
@@ -2714,7 +2837,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
ext4_ext_dirty(handle, inode, path + depth);
/* zero out the first half */
- /* blocks available from iblock */
+ /* blocks available from map->m_lblk */
return allocated;
}
}
@@ -2725,12 +2848,12 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
*/
if (ex1 && ex1 != ex) {
ex1 = ex;
- ex1->ee_len = cpu_to_le16(iblock - ee_block);
+ ex1->ee_len = cpu_to_le16(map->m_lblk - ee_block);
ext4_ext_mark_uninitialized(ex1);
ex2 = &newex;
}
- /* ex2: iblock to iblock + maxblocks-1 : initialised */
- ex2->ee_block = cpu_to_le32(iblock);
+ /* ex2: map->m_lblk to map->m_lblk + maxblocks-1 : initialised */
+ ex2->ee_block = cpu_to_le32(map->m_lblk);
ext4_ext_store_pblock(ex2, newblock);
ex2->ee_len = cpu_to_le16(allocated);
if (ex2 != ex)
@@ -2773,7 +2896,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
goto out;
insert:
err = ext4_ext_insert_extent(handle, inode, path, &newex, 0);
- if (err == -ENOSPC) {
+ if (err == -ENOSPC && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
@@ -2800,7 +2923,7 @@ fix_extent_len:
}
/*
- * This function is called by ext4_ext_get_blocks() from
+ * This function is called by ext4_ext_map_blocks() from
* ext4_get_blocks_dio_write() when DIO to write
* to an uninitialized extent.
*
@@ -2823,9 +2946,8 @@ fix_extent_len:
*/
static int ext4_split_unwritten_extents(handle_t *handle,
struct inode *inode,
+ struct ext4_map_blocks *map,
struct ext4_ext_path *path,
- ext4_lblk_t iblock,
- unsigned int max_blocks,
int flags)
{
struct ext4_extent *ex, newex, orig_ex;
@@ -2833,41 +2955,55 @@ static int ext4_split_unwritten_extents(handle_t *handle,
struct ext4_extent *ex2 = NULL;
struct ext4_extent *ex3 = NULL;
struct ext4_extent_header *eh;
- ext4_lblk_t ee_block;
+ ext4_lblk_t ee_block, eof_block;
unsigned int allocated, ee_len, depth;
ext4_fsblk_t newblock;
int err = 0;
+ int may_zeroout;
+
+ 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);
+
+ eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
+ inode->i_sb->s_blocksize_bits;
+ if (eof_block < map->m_lblk + map->m_len)
+ eof_block = map->m_lblk + map->m_len;
- ext_debug("ext4_split_unwritten_extents: inode %lu,"
- "iblock %llu, max_blocks %u\n", inode->i_ino,
- (unsigned long long)iblock, max_blocks);
depth = ext_depth(inode);
eh = path[depth].p_hdr;
ex = path[depth].p_ext;
ee_block = le32_to_cpu(ex->ee_block);
ee_len = ext4_ext_get_actual_len(ex);
- allocated = ee_len - (iblock - ee_block);
- newblock = iblock - ee_block + ext_pblock(ex);
+ allocated = ee_len - (map->m_lblk - ee_block);
+ newblock = map->m_lblk - ee_block + ext_pblock(ex);
+
ex2 = ex;
orig_ex.ee_block = ex->ee_block;
orig_ex.ee_len = cpu_to_le16(ee_len);
ext4_ext_store_pblock(&orig_ex, ext_pblock(ex));
/*
+ * It is safe to convert extent to initialized via explicit
+ * zeroout only if extent is fully insde i_size or new_size.
+ */
+ may_zeroout = ee_block + ee_len <= eof_block;
+
+ /*
* If the uninitialized extent begins at the same logical
* block where the write begins, and the write completely
* covers the extent, then we don't need to split it.
*/
- if ((iblock == ee_block) && (allocated <= max_blocks))
+ if ((map->m_lblk == ee_block) && (allocated <= map->m_len))
return allocated;
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
goto out;
- /* ex1: ee_block to iblock - 1 : uninitialized */
- if (iblock > ee_block) {
+ /* ex1: ee_block to map->m_lblk - 1 : uninitialized */
+ if (map->m_lblk > ee_block) {
ex1 = ex;
- ex1->ee_len = cpu_to_le16(iblock - ee_block);
+ ex1->ee_len = cpu_to_le16(map->m_lblk - ee_block);
ext4_ext_mark_uninitialized(ex1);
ex2 = &newex;
}
@@ -2876,18 +3012,18 @@ static int ext4_split_unwritten_extents(handle_t *handle,
* we insert ex3, if ex1 is NULL. This is to avoid temporary
* overlap of blocks.
*/
- if (!ex1 && allocated > max_blocks)
- ex2->ee_len = cpu_to_le16(max_blocks);
+ if (!ex1 && allocated > map->m_len)
+ ex2->ee_len = cpu_to_le16(map->m_len);
/* ex3: to ee_block + ee_len : uninitialised */
- if (allocated > max_blocks) {
+ if (allocated > map->m_len) {
unsigned int newdepth;
ex3 = &newex;
- ex3->ee_block = cpu_to_le32(iblock + max_blocks);
- ext4_ext_store_pblock(ex3, newblock + max_blocks);
- ex3->ee_len = cpu_to_le16(allocated - max_blocks);
+ ex3->ee_block = cpu_to_le32(map->m_lblk + map->m_len);
+ ext4_ext_store_pblock(ex3, newblock + map->m_len);
+ ex3->ee_len = cpu_to_le16(allocated - map->m_len);
ext4_ext_mark_uninitialized(ex3);
err = ext4_ext_insert_extent(handle, inode, path, ex3, flags);
- if (err == -ENOSPC) {
+ if (err == -ENOSPC && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
@@ -2897,7 +3033,7 @@ static int ext4_split_unwritten_extents(handle_t *handle,
ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
ext4_ext_dirty(handle, inode, path + depth);
/* zeroed the full extent */
- /* blocks available from iblock */
+ /* blocks available from map->m_lblk */
return allocated;
} else if (err)
@@ -2911,11 +3047,13 @@ static int ext4_split_unwritten_extents(handle_t *handle,
* update the extent length after successful insert of the
* split extent
*/
- orig_ex.ee_len = cpu_to_le16(ee_len -
- ext4_ext_get_actual_len(ex3));
+ ee_len -= ext4_ext_get_actual_len(ex3);
+ orig_ex.ee_len = cpu_to_le16(ee_len);
+ may_zeroout = ee_block + ee_len <= eof_block;
+
depth = newdepth;
ext4_ext_drop_refs(path);
- path = ext4_ext_find_extent(inode, iblock, path);
+ path = ext4_ext_find_extent(inode, map->m_lblk, path);
if (IS_ERR(path)) {
err = PTR_ERR(path);
goto out;
@@ -2929,7 +3067,7 @@ static int ext4_split_unwritten_extents(handle_t *handle,
if (err)
goto out;
- allocated = max_blocks;
+ allocated = map->m_len;
}
/*
* If there was a change of depth as part of the
@@ -2938,15 +3076,15 @@ static int ext4_split_unwritten_extents(handle_t *handle,
*/
if (ex1 && ex1 != ex) {
ex1 = ex;
- ex1->ee_len = cpu_to_le16(iblock - ee_block);
+ ex1->ee_len = cpu_to_le16(map->m_lblk - ee_block);
ext4_ext_mark_uninitialized(ex1);
ex2 = &newex;
}
/*
- * ex2: iblock to iblock + maxblocks-1 : to be direct IO written,
- * uninitialised still.
+ * ex2: map->m_lblk to map->m_lblk + map->m_len-1 : to be written
+ * using direct I/O, uninitialised still.
*/
- ex2->ee_block = cpu_to_le32(iblock);
+ ex2->ee_block = cpu_to_le32(map->m_lblk);
ext4_ext_store_pblock(ex2, newblock);
ex2->ee_len = cpu_to_le16(allocated);
ext4_ext_mark_uninitialized(ex2);
@@ -2958,7 +3096,7 @@ static int ext4_split_unwritten_extents(handle_t *handle,
goto out;
insert:
err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
- if (err == -ENOSPC) {
+ if (err == -ENOSPC && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
@@ -2983,7 +3121,7 @@ fix_extent_len:
ext4_ext_dirty(handle, inode, path + depth);
return err;
}
-static int ext4_convert_unwritten_extents_dio(handle_t *handle,
+static int ext4_convert_unwritten_extents_endio(handle_t *handle,
struct inode *inode,
struct ext4_ext_path *path)
{
@@ -3048,10 +3186,9 @@ static void unmap_underlying_metadata_blocks(struct block_device *bdev,
static int
ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
- ext4_lblk_t iblock, unsigned int max_blocks,
+ struct ext4_map_blocks *map,
struct ext4_ext_path *path, int flags,
- unsigned int allocated, struct buffer_head *bh_result,
- ext4_fsblk_t newblock)
+ unsigned int allocated, ext4_fsblk_t newblock)
{
int ret = 0;
int err = 0;
@@ -3059,29 +3196,30 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
ext_debug("ext4_ext_handle_uninitialized_extents: inode %lu, logical"
"block %llu, max_blocks %u, flags %d, allocated %u",
- inode->i_ino, (unsigned long long)iblock, max_blocks,
+ inode->i_ino, (unsigned long long)map->m_lblk, map->m_len,
flags, allocated);
ext4_ext_show_leaf(inode, path);
- /* DIO get_block() before submit the IO, split the extent */
- if (flags == EXT4_GET_BLOCKS_DIO_CREATE_EXT) {
- ret = ext4_split_unwritten_extents(handle,
- inode, path, iblock,
- max_blocks, flags);
+ /* 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);
/*
* Flag the inode(non aio case) or end_io struct (aio case)
* that this IO needs to convertion to written when IO is
* completed
*/
if (io)
- io->flag = DIO_AIO_UNWRITTEN;
+ io->flag = EXT4_IO_UNWRITTEN;
else
- EXT4_I(inode)->i_state |= EXT4_STATE_DIO_UNWRITTEN;
+ ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
+ if (ext4_should_dioread_nolock(inode))
+ map->m_flags |= EXT4_MAP_UNINIT;
goto out;
}
- /* async DIO end_io complete, convert the filled extent to written */
- if (flags == EXT4_GET_BLOCKS_DIO_CONVERT_EXT) {
- ret = ext4_convert_unwritten_extents_dio(handle, inode,
+ /* IO end_io complete, convert the filled extent to written */
+ if ((flags & EXT4_GET_BLOCKS_CONVERT)) {
+ ret = ext4_convert_unwritten_extents_endio(handle, inode,
path);
if (ret >= 0)
ext4_update_inode_fsync_trans(handle, inode, 1);
@@ -3104,14 +3242,12 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
* the buffer head will be unmapped so that
* a read from the block returns 0s.
*/
- set_buffer_unwritten(bh_result);
+ map->m_flags |= EXT4_MAP_UNWRITTEN;
goto out1;
}
/* buffered write, writepage time, convert*/
- ret = ext4_ext_convert_to_initialized(handle, inode,
- path, iblock,
- max_blocks);
+ ret = ext4_ext_convert_to_initialized(handle, inode, map, path);
if (ret >= 0)
ext4_update_inode_fsync_trans(handle, inode, 1);
out:
@@ -3120,7 +3256,7 @@ out:
goto out2;
} else
allocated = ret;
- set_buffer_new(bh_result);
+ map->m_flags |= EXT4_MAP_NEW;
/*
* if we allocated more blocks than requested
* we need to make sure we unmap the extra block
@@ -3128,11 +3264,11 @@ out:
* unmapped later when we find the buffer_head marked
* new.
*/
- if (allocated > max_blocks) {
+ if (allocated > map->m_len) {
unmap_underlying_metadata_blocks(inode->i_sb->s_bdev,
- newblock + max_blocks,
- allocated - max_blocks);
- allocated = max_blocks;
+ newblock + map->m_len,
+ allocated - map->m_len);
+ allocated = map->m_len;
}
/*
@@ -3146,13 +3282,13 @@ out:
ext4_da_update_reserve_space(inode, allocated, 0);
map_out:
- set_buffer_mapped(bh_result);
+ map->m_flags |= EXT4_MAP_MAPPED;
out1:
- if (allocated > max_blocks)
- allocated = max_blocks;
+ if (allocated > map->m_len)
+ allocated = map->m_len;
ext4_ext_show_leaf(inode, path);
- bh_result->b_bdev = inode->i_sb->s_bdev;
- bh_result->b_blocknr = newblock;
+ map->m_pblk = newblock;
+ map->m_len = allocated;
out2:
if (path) {
ext4_ext_drop_refs(path);
@@ -3178,26 +3314,23 @@ out2:
*
* return < 0, error case.
*/
-int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
- ext4_lblk_t iblock,
- unsigned int max_blocks, struct buffer_head *bh_result,
- int flags)
+int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
+ struct ext4_map_blocks *map, int flags)
{
struct ext4_ext_path *path = NULL;
struct ext4_extent_header *eh;
- struct ext4_extent newex, *ex;
+ struct ext4_extent newex, *ex, *last_ex;
ext4_fsblk_t newblock;
- int err = 0, depth, ret, cache_type;
+ int i, err = 0, depth, ret, cache_type;
unsigned int allocated = 0;
struct ext4_allocation_request ar;
ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio;
- __clear_bit(BH_New, &bh_result->b_state);
ext_debug("blocks %u/%u requested for inode %lu\n",
- iblock, max_blocks, inode->i_ino);
+ map->m_lblk, map->m_len, inode->i_ino);
/* check in cache */
- cache_type = ext4_ext_in_cache(inode, iblock, &newex);
+ cache_type = ext4_ext_in_cache(inode, map->m_lblk, &newex);
if (cache_type) {
if (cache_type == EXT4_EXT_CACHE_GAP) {
if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
@@ -3210,12 +3343,12 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
/* we should allocate requested block */
} else if (cache_type == EXT4_EXT_CACHE_EXTENT) {
/* block is already allocated */
- newblock = iblock
+ newblock = map->m_lblk
- le32_to_cpu(newex.ee_block)
+ ext_pblock(&newex);
/* number of remaining blocks in the extent */
allocated = ext4_ext_get_actual_len(&newex) -
- (iblock - le32_to_cpu(newex.ee_block));
+ (map->m_lblk - le32_to_cpu(newex.ee_block));
goto out;
} else {
BUG();
@@ -3223,7 +3356,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
}
/* find extent for this block */
- path = ext4_ext_find_extent(inode, iblock, NULL);
+ path = ext4_ext_find_extent(inode, map->m_lblk, NULL);
if (IS_ERR(path)) {
err = PTR_ERR(path);
path = NULL;
@@ -3237,10 +3370,11 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
* this situation is possible, though, _during_ tree modification;
* this is why assert can't be put in ext4_ext_find_extent()
*/
- if (path[depth].p_ext == NULL && depth != 0) {
- ext4_error(inode->i_sb, __func__, "bad extent address "
- "inode: %lu, iblock: %d, depth: %d",
- inode->i_ino, iblock, depth);
+ if (unlikely(path[depth].p_ext == NULL && depth != 0)) {
+ EXT4_ERROR_INODE(inode, "bad extent address "
+ "lblock: %lu, depth: %d pblock %lld",
+ (unsigned long) map->m_lblk, depth,
+ path[depth].p_block);
err = -EIO;
goto out2;
}
@@ -3258,12 +3392,12 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
*/
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;
+ if (in_range(map->m_lblk, ee_block, ee_len)) {
+ newblock = map->m_lblk - ee_block + ee_start;
/* number of remaining blocks in the extent */
- allocated = ee_len - (iblock - ee_block);
- ext_debug("%u fit into %u:%d -> %llu\n", iblock,
- ee_block, ee_len, newblock);
+ allocated = ee_len - (map->m_lblk - ee_block);
+ ext_debug("%u fit into %u:%d -> %llu\n", map->m_lblk,
+ ee_block, ee_len, newblock);
/* Do not put uninitialized extent in the cache */
if (!ext4_ext_is_uninitialized(ex)) {
@@ -3273,8 +3407,8 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
goto out;
}
ret = ext4_ext_handle_uninitialized_extents(handle,
- inode, iblock, max_blocks, path,
- flags, allocated, bh_result, newblock);
+ inode, map, path, flags, allocated,
+ newblock);
return ret;
}
}
@@ -3288,7 +3422,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
* put just found gap into cache to speed up
* subsequent requests
*/
- ext4_ext_put_gap_in_cache(inode, path, iblock);
+ ext4_ext_put_gap_in_cache(inode, path, map->m_lblk);
goto out2;
}
/*
@@ -3296,11 +3430,11 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
*/
/* find neighbour allocated blocks */
- ar.lleft = iblock;
+ ar.lleft = map->m_lblk;
err = ext4_ext_search_left(inode, path, &ar.lleft, &ar.pleft);
if (err)
goto out2;
- ar.lright = iblock;
+ ar.lright = map->m_lblk;
err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright);
if (err)
goto out2;
@@ -3311,26 +3445,26 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
* EXT_INIT_MAX_LEN and for an uninitialized extent this limit is
* EXT_UNINIT_MAX_LEN.
*/
- if (max_blocks > EXT_INIT_MAX_LEN &&
+ if (map->m_len > EXT_INIT_MAX_LEN &&
!(flags & EXT4_GET_BLOCKS_UNINIT_EXT))
- max_blocks = EXT_INIT_MAX_LEN;
- else if (max_blocks > EXT_UNINIT_MAX_LEN &&
+ map->m_len = EXT_INIT_MAX_LEN;
+ else if (map->m_len > EXT_UNINIT_MAX_LEN &&
(flags & EXT4_GET_BLOCKS_UNINIT_EXT))
- max_blocks = EXT_UNINIT_MAX_LEN;
+ map->m_len = EXT_UNINIT_MAX_LEN;
- /* Check if we can really insert (iblock)::(iblock+max_blocks) extent */
- newex.ee_block = cpu_to_le32(iblock);
- newex.ee_len = cpu_to_le16(max_blocks);
+ /* Check if we can really insert (m_lblk)::(m_lblk + m_len) extent */
+ newex.ee_block = cpu_to_le32(map->m_lblk);
+ newex.ee_len = cpu_to_le16(map->m_len);
err = ext4_ext_check_overlap(inode, &newex, path);
if (err)
allocated = ext4_ext_get_actual_len(&newex);
else
- allocated = max_blocks;
+ allocated = map->m_len;
/* allocate new block */
ar.inode = inode;
- ar.goal = ext4_ext_find_goal(inode, path, iblock);
- ar.logical = iblock;
+ ar.goal = ext4_ext_find_goal(inode, path, map->m_lblk);
+ ar.logical = map->m_lblk;
ar.len = allocated;
if (S_ISREG(inode->i_mode))
ar.flags = EXT4_MB_HINT_DATA;
@@ -3350,21 +3484,47 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
if (flags & EXT4_GET_BLOCKS_UNINIT_EXT){
ext4_ext_mark_uninitialized(&newex);
/*
- * io_end structure was created for every async
- * direct IO write to the middle of the file.
- * To avoid unecessary convertion for every aio dio rewrite
- * to the mid of file, here we flag the IO that is really
- * need the convertion.
+ * io_end structure was created for every IO write to an
+ * uninitialized extent. To avoid unecessary conversion,
+ * here we flag the IO that really needs the conversion.
* For non asycn direct IO case, flag the inode state
* that we need to perform convertion when IO is done.
*/
- if (flags == EXT4_GET_BLOCKS_DIO_CREATE_EXT) {
+ if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
if (io)
- io->flag = DIO_AIO_UNWRITTEN;
+ io->flag = EXT4_IO_UNWRITTEN;
else
- EXT4_I(inode)->i_state |=
- EXT4_STATE_DIO_UNWRITTEN;;
+ ext4_set_inode_state(inode,
+ EXT4_STATE_DIO_UNWRITTEN);
}
+ if (ext4_should_dioread_nolock(inode))
+ map->m_flags |= EXT4_MAP_UNINIT;
+ }
+
+ if (unlikely(ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS))) {
+ if (unlikely(!eh->eh_entries)) {
+ EXT4_ERROR_INODE(inode,
+ "eh->eh_entries == 0 and "
+ "EOFBLOCKS_FL set");
+ err = -EIO;
+ goto out2;
+ }
+ last_ex = EXT_LAST_EXTENT(eh);
+ /*
+ * If the current leaf block was reached by looking at
+ * the last index block all the way down the tree, and
+ * we are extending the inode beyond the last extent
+ * in the current leaf block, then clear the
+ * EOFBLOCKS_FL flag.
+ */
+ for (i = depth-1; i >= 0; i--) {
+ if (path[i].p_idx != EXT_LAST_INDEX(path[i].p_hdr))
+ break;
+ }
+ if ((i < 0) &&
+ (map->m_lblk + ar.len > le32_to_cpu(last_ex->ee_block) +
+ ext4_ext_get_actual_len(last_ex)))
+ ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
}
err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
if (err) {
@@ -3380,9 +3540,9 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
/* previous routine could use block we allocated */
newblock = ext_pblock(&newex);
allocated = ext4_ext_get_actual_len(&newex);
- if (allocated > max_blocks)
- allocated = max_blocks;
- set_buffer_new(bh_result);
+ if (allocated > map->m_len)
+ allocated = map->m_len;
+ map->m_flags |= EXT4_MAP_NEW;
/*
* Update reserved blocks/metadata blocks after successful
@@ -3396,18 +3556,18 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
* when it is _not_ an uninitialized extent.
*/
if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0) {
- ext4_ext_put_in_cache(inode, iblock, allocated, newblock,
+ ext4_ext_put_in_cache(inode, map->m_lblk, allocated, newblock,
EXT4_EXT_CACHE_EXTENT);
ext4_update_inode_fsync_trans(handle, inode, 1);
} else
ext4_update_inode_fsync_trans(handle, inode, 0);
out:
- if (allocated > max_blocks)
- allocated = max_blocks;
+ if (allocated > map->m_len)
+ allocated = map->m_len;
ext4_ext_show_leaf(inode, path);
- set_buffer_mapped(bh_result);
- bh_result->b_bdev = inode->i_sb->s_bdev;
- bh_result->b_blocknr = newblock;
+ map->m_flags |= EXT4_MAP_MAPPED;
+ map->m_pblk = newblock;
+ map->m_len = allocated;
out2:
if (path) {
ext4_ext_drop_refs(path);
@@ -3499,6 +3659,13 @@ static void ext4_falloc_update_inode(struct inode *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))
+ ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
}
}
@@ -3513,55 +3680,57 @@ static void ext4_falloc_update_inode(struct inode *inode,
long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
{
handle_t *handle;
- ext4_lblk_t block;
loff_t new_size;
unsigned int max_blocks;
int ret = 0;
int ret2 = 0;
int retries = 0;
- struct buffer_head map_bh;
+ struct ext4_map_blocks map;
unsigned int credits, blkbits = inode->i_blkbits;
/*
* currently supporting (pre)allocate mode for extent-based
* files _only_
*/
- if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return -EOPNOTSUPP;
/* preallocation to directories is currently not supported */
if (S_ISDIR(inode->i_mode))
return -ENODEV;
- block = offset >> blkbits;
+ map.m_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)
- - block;
+ - 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);
+ return ret;
+ }
retry:
while (ret >= 0 && ret < max_blocks) {
- block = block + ret;
- max_blocks = max_blocks - ret;
+ map.m_lblk = map.m_lblk + ret;
+ map.m_len = max_blocks = max_blocks - ret;
handle = ext4_journal_start(inode, credits);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
break;
}
- map_bh.b_state = 0;
- ret = ext4_get_blocks(handle, inode, block,
- max_blocks, &map_bh,
+ ret = ext4_map_blocks(handle, inode, &map,
EXT4_GET_BLOCKS_CREATE_UNINIT_EXT);
if (ret <= 0) {
#ifdef EXT4FS_DEBUG
WARN_ON(ret <= 0);
- printk(KERN_ERR "%s: ext4_ext_get_blocks "
+ printk(KERN_ERR "%s: ext4_ext_map_blocks "
"returned error inode#%lu, block=%u, "
"max_blocks=%u", __func__,
inode->i_ino, block, max_blocks);
@@ -3570,14 +3739,14 @@ retry:
ret2 = ext4_journal_stop(handle);
break;
}
- if ((block + ret) >= (EXT4_BLOCK_ALIGN(offset + len,
+ if ((map.m_lblk + ret) >= (EXT4_BLOCK_ALIGN(offset + len,
blkbits) >> blkbits))
new_size = offset + len;
else
- new_size = (block + ret) << blkbits;
+ new_size = (map.m_lblk + ret) << blkbits;
ext4_falloc_update_inode(inode, mode, new_size,
- buffer_new(&map_bh));
+ (map.m_flags & EXT4_MAP_NEW));
ext4_mark_inode_dirty(handle, inode);
ret2 = ext4_journal_stop(handle);
if (ret2)
@@ -3603,45 +3772,42 @@ retry:
* Returns 0 on success.
*/
int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
- loff_t len)
+ ssize_t len)
{
handle_t *handle;
- ext4_lblk_t block;
unsigned int max_blocks;
int ret = 0;
int ret2 = 0;
- struct buffer_head map_bh;
+ struct ext4_map_blocks map;
unsigned int credits, blkbits = inode->i_blkbits;
- block = offset >> blkbits;
+ map.m_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)
- - block;
+ 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);
while (ret >= 0 && ret < max_blocks) {
- block = block + ret;
- max_blocks = max_blocks - ret;
+ map.m_lblk += ret;
+ map.m_len = (max_blocks -= ret);
handle = ext4_journal_start(inode, credits);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
break;
}
- map_bh.b_state = 0;
- ret = ext4_get_blocks(handle, inode, block,
- max_blocks, &map_bh,
- EXT4_GET_BLOCKS_DIO_CONVERT_EXT);
+ ret = ext4_map_blocks(handle, inode, &map,
+ EXT4_GET_BLOCKS_IO_CONVERT_EXT);
if (ret <= 0) {
WARN_ON(ret <= 0);
- printk(KERN_ERR "%s: ext4_ext_get_blocks "
+ printk(KERN_ERR "%s: ext4_ext_map_blocks "
"returned error inode#%lu, block=%u, "
"max_blocks=%u", __func__,
- inode->i_ino, block, max_blocks);
+ inode->i_ino, map.m_lblk, map.m_len);
}
ext4_mark_inode_dirty(handle, inode);
ret2 = ext4_journal_stop(handle);
@@ -3739,7 +3905,7 @@ static int ext4_xattr_fiemap(struct inode *inode,
int error = 0;
/* in-inode? */
- if (EXT4_I(inode)->i_state & EXT4_STATE_XATTR) {
+ if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
struct ext4_iloc iloc;
int offset; /* offset of xattr in inode */
@@ -3752,6 +3918,7 @@ static int ext4_xattr_fiemap(struct inode *inode,
physical += offset;
length = EXT4_SB(inode->i_sb)->s_inode_size - offset;
flags |= FIEMAP_EXTENT_DATA_INLINE;
+ brelse(iloc.bh);
} else { /* external block */
physical = EXT4_I(inode)->i_file_acl << blockbits;
length = inode->i_sb->s_blocksize;
@@ -3767,11 +3934,10 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len)
{
ext4_lblk_t start_blk;
- ext4_lblk_t len_blks;
int error = 0;
/* fallback to generic here if not in extents fmt */
- if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return generic_block_fiemap(inode, fieinfo, start, len,
ext4_get_block);
@@ -3781,8 +3947,14 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) {
error = ext4_xattr_fiemap(inode, fieinfo);
} else {
+ ext4_lblk_t len_blks;
+ __u64 last_blk;
+
start_blk = start >> inode->i_sb->s_blocksize_bits;
- len_blks = len >> inode->i_sb->s_blocksize_bits;
+ last_blk = (start + len - 1) >> inode->i_sb->s_blocksize_bits;
+ if (last_blk >= EXT_MAX_BLOCK)
+ last_blk = EXT_MAX_BLOCK-1;
+ len_blks = ((ext4_lblk_t) last_blk) - start_blk + 1;
/*
* Walk the extent tree gathering extent information.
Powered by cgit, Gruvboxed by Blaster4385.