Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index ae73e67..0fda305 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -28,6 +28,7 @@
#include <linux/uaccess.h>
#include <linux/fiemap.h>
#include <linux/backing-dev.h>
+#include <linux/iomap.h>
#include "ext4_jbd2.h"
#include "ext4_extents.h"
#include "xattr.h"
@@ -83,13 +84,6 @@
et->et_checksum = ext4_extent_block_csum(inode, eh);
}
-static int ext4_split_extent(handle_t *handle,
- struct inode *inode,
- struct ext4_ext_path **ppath,
- struct ext4_map_blocks *map,
- int split_flag,
- int flags);
-
static int ext4_split_extent_at(handle_t *handle,
struct inode *inode,
struct ext4_ext_path **ppath,
@@ -97,32 +91,41 @@
int split_flag,
int flags);
-static int ext4_find_delayed_extent(struct inode *inode,
- struct extent_status *newes);
-
-static int ext4_ext_truncate_extend_restart(handle_t *handle,
- struct inode *inode,
- int needed)
+static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped)
{
- int err;
-
- if (!ext4_handle_valid(handle))
- return 0;
- if (handle->h_buffer_credits >= needed)
- return 0;
/*
- * If we need to extend the journal get a few extra blocks
- * while we're at it for efficiency's sake.
+ * Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this
+ * moment, get_block can be called only for blocks inside i_size since
+ * page cache has been already dropped and writes are blocked by
+ * i_mutex. So we can safely drop the i_data_sem here.
*/
- needed += 3;
- err = ext4_journal_extend(handle, needed - handle->h_buffer_credits);
- if (err <= 0)
- return err;
- err = ext4_truncate_restart_trans(handle, inode, needed);
- if (err == 0)
- err = -EAGAIN;
+ BUG_ON(EXT4_JOURNAL(inode) == NULL);
+ ext4_discard_preallocations(inode, 0);
+ up_write(&EXT4_I(inode)->i_data_sem);
+ *dropped = 1;
+ return 0;
+}
- return err;
+/*
+ * Make sure 'handle' has at least 'check_cred' credits. If not, restart
+ * transaction with 'restart_cred' credits. The function drops i_data_sem
+ * when restarting transaction and gets it after transaction is restarted.
+ *
+ * The function returns 0 on success, 1 if transaction had to be restarted,
+ * and < 0 in case of fatal error.
+ */
+int ext4_datasem_ensure_credits(handle_t *handle, struct inode *inode,
+ int check_cred, int restart_cred,
+ int revoke_cred)
+{
+ int ret;
+ int dropped = 0;
+
+ ret = ext4_journal_ensure_credits_fn(handle, check_cred, restart_cred,
+ revoke_cred, ext4_ext_trunc_restart_fn(inode, &dropped));
+ if (dropped)
+ down_write(&EXT4_I(inode)->i_data_sem);
+ return ret;
}
/*
@@ -133,14 +136,24 @@
static int ext4_ext_get_access(handle_t *handle, struct inode *inode,
struct ext4_ext_path *path)
{
+ int err = 0;
+
if (path->p_bh) {
/* path points to block */
BUFFER_TRACE(path->p_bh, "get_write_access");
- return ext4_journal_get_write_access(handle, path->p_bh);
+ err = ext4_journal_get_write_access(handle, path->p_bh);
+ /*
+ * The extent buffer's verified bit will be set again in
+ * __ext4_ext_dirty(). We could leave an inconsistent
+ * buffer if the extents updating procudure break off du
+ * to some error happens, force to check it again.
+ */
+ if (!err)
+ clear_buffer_verified(path->p_bh);
}
/* path points to leaf/index in inode body */
/* we use in-core data, no need to protect them */
- return 0;
+ return err;
}
/*
@@ -149,8 +162,9 @@
* - ENOMEM
* - EIO
*/
-int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle,
- struct inode *inode, struct ext4_ext_path *path)
+static int __ext4_ext_dirty(const char *where, unsigned int line,
+ handle_t *handle, struct inode *inode,
+ struct ext4_ext_path *path)
{
int err;
@@ -160,6 +174,9 @@
/* path points to block */
err = __ext4_handle_dirty_metadata(where, line, handle,
inode, path->p_bh);
+ /* Extents updating done, re-set verified flag */
+ if (!err)
+ set_buffer_verified(path->p_bh);
} else {
/* path points to leaf/index in inode body */
err = ext4_mark_inode_dirty(handle, inode);
@@ -167,6 +184,9 @@
return err;
}
+#define ext4_ext_dirty(handle, inode, path) \
+ __ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path))
+
static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
struct ext4_ext_path *path,
ext4_lblk_t block)
@@ -290,58 +310,14 @@
{
struct ext4_ext_path *path = *ppath;
int unwritten = ext4_ext_is_unwritten(path[path->p_depth].p_ext);
+ int flags = EXT4_EX_NOCACHE | EXT4_GET_BLOCKS_PRE_IO;
+
+ if (nofail)
+ flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL | EXT4_EX_NOFAIL;
return ext4_split_extent_at(handle, inode, ppath, lblk, unwritten ?
EXT4_EXT_MARK_UNWRIT1|EXT4_EXT_MARK_UNWRIT2 : 0,
- EXT4_EX_NOCACHE | EXT4_GET_BLOCKS_PRE_IO |
- (nofail ? EXT4_GET_BLOCKS_METADATA_NOFAIL:0));
-}
-
-/*
- * Calculate the number of metadata blocks needed
- * to allocate @blocks
- * Worse case is one block per extent
- */
-int ext4_ext_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock)
-{
- struct ext4_inode_info *ei = EXT4_I(inode);
- int idxs;
-
- idxs = ((inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
- / sizeof(struct ext4_extent_idx));
-
- /*
- * If the new delayed allocation block is contiguous with the
- * previous da block, it can share index blocks with the
- * previous block, so we only need to allocate a new index
- * block every idxs leaf blocks. At ldxs**2 blocks, we need
- * an additional index block, and at ldxs**3 blocks, yet
- * another index blocks.
- */
- if (ei->i_da_metadata_calc_len &&
- ei->i_da_metadata_calc_last_lblock+1 == lblock) {
- int num = 0;
-
- if ((ei->i_da_metadata_calc_len % idxs) == 0)
- num++;
- if ((ei->i_da_metadata_calc_len % (idxs*idxs)) == 0)
- num++;
- if ((ei->i_da_metadata_calc_len % (idxs*idxs*idxs)) == 0) {
- num++;
- ei->i_da_metadata_calc_len = 0;
- } else
- ei->i_da_metadata_calc_len++;
- ei->i_da_metadata_calc_last_lblock++;
- return num;
- }
-
- /*
- * In the worst case we need a new set of index blocks at
- * every level of the inode's extent tree.
- */
- ei->i_da_metadata_calc_len = 1;
- ei->i_da_metadata_calc_last_lblock = lblock;
- return ext_depth(inode) + 1;
+ flags);
}
static int
@@ -377,7 +353,7 @@
*/
if (lblock + len <= lblock)
return 0;
- return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
+ return ext4_inode_block_valid(inode, block, len);
}
static int ext4_valid_extent_idx(struct inode *inode,
@@ -385,14 +361,18 @@
{
ext4_fsblk_t block = ext4_idx_pblock(ext_idx);
- return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, 1);
+ return ext4_inode_block_valid(inode, block, 1);
}
static int ext4_valid_extent_entries(struct inode *inode,
- struct ext4_extent_header *eh,
- int depth)
+ struct ext4_extent_header *eh,
+ ext4_lblk_t lblk, ext4_fsblk_t *pblk,
+ int depth)
{
unsigned short entries;
+ ext4_lblk_t lblock = 0;
+ ext4_lblk_t prev = 0;
+
if (eh->eh_entries == 0)
return 1;
@@ -401,34 +381,51 @@
if (depth == 0) {
/* leaf entries */
struct ext4_extent *ext = EXT_FIRST_EXTENT(eh);
- struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
- ext4_fsblk_t pblock = 0;
- ext4_lblk_t lblock = 0;
- ext4_lblk_t prev = 0;
- int len = 0;
+
+ /*
+ * The logical block in the first entry should equal to
+ * the number in the index block.
+ */
+ if (depth != ext_depth(inode) &&
+ lblk != le32_to_cpu(ext->ee_block))
+ return 0;
while (entries) {
if (!ext4_valid_extent(inode, ext))
return 0;
/* Check for overlapping extents */
lblock = le32_to_cpu(ext->ee_block);
- len = ext4_ext_get_actual_len(ext);
if ((lblock <= prev) && prev) {
- pblock = ext4_ext_pblock(ext);
- es->s_last_error_block = cpu_to_le64(pblock);
+ *pblk = ext4_ext_pblock(ext);
return 0;
}
+ prev = lblock + ext4_ext_get_actual_len(ext) - 1;
ext++;
entries--;
- prev = lblock + len - 1;
}
} else {
struct ext4_extent_idx *ext_idx = EXT_FIRST_INDEX(eh);
+
+ /*
+ * The logical block in the first entry should equal to
+ * the number in the parent index block.
+ */
+ if (depth != ext_depth(inode) &&
+ lblk != le32_to_cpu(ext_idx->ei_block))
+ return 0;
while (entries) {
if (!ext4_valid_extent_idx(inode, ext_idx))
return 0;
+
+ /* Check for overlapping index extents */
+ lblock = le32_to_cpu(ext_idx->ei_block);
+ if ((lblock <= prev) && prev) {
+ *pblk = ext4_idx_pblock(ext_idx);
+ return 0;
+ }
ext_idx++;
entries--;
+ prev = lblock;
}
}
return 1;
@@ -436,7 +433,7 @@
static int __ext4_ext_check(const char *function, unsigned int line,
struct inode *inode, struct ext4_extent_header *eh,
- int depth, ext4_fsblk_t pblk)
+ int depth, ext4_fsblk_t pblk, ext4_lblk_t lblk)
{
const char *error_msg;
int max = 0, err = -EFSCORRUPTED;
@@ -462,7 +459,7 @@
error_msg = "invalid eh_entries";
goto corrupted;
}
- if (!ext4_valid_extent_entries(inode, eh, depth)) {
+ if (!ext4_valid_extent_entries(inode, eh, lblk, &pblk, depth)) {
error_msg = "invalid extent entries";
goto corrupted;
}
@@ -480,18 +477,19 @@
return 0;
corrupted:
- ext4_error_inode(inode, function, line, 0,
- "pblk %llu bad header/extent: %s - magic %x, "
- "entries %u, max %u(%u), depth %u(%u)",
- (unsigned long long) pblk, 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);
+ ext4_error_inode_err(inode, function, line, 0, -err,
+ "pblk %llu bad header/extent: %s - magic %x, "
+ "entries %u, max %u(%u), depth %u(%u)",
+ (unsigned long long) pblk, 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);
return err;
}
#define ext4_ext_check(inode, eh, depth, pblk) \
- __ext4_ext_check(__func__, __LINE__, (inode), (eh), (depth), (pblk))
+ __ext4_ext_check(__func__, __LINE__, (inode), (eh), (depth), (pblk), 0)
int ext4_ext_check_inode(struct inode *inode)
{
@@ -524,32 +522,34 @@
static struct buffer_head *
__read_extent_tree_block(const char *function, unsigned int line,
- struct inode *inode, ext4_fsblk_t pblk, int depth,
- int flags)
+ struct inode *inode, struct ext4_extent_idx *idx,
+ int depth, int flags)
{
struct buffer_head *bh;
int err;
+ gfp_t gfp_flags = __GFP_MOVABLE | GFP_NOFS;
+ ext4_fsblk_t pblk;
- bh = sb_getblk_gfp(inode->i_sb, pblk, __GFP_MOVABLE | GFP_NOFS);
+ if (flags & EXT4_EX_NOFAIL)
+ gfp_flags |= __GFP_NOFAIL;
+
+ pblk = ext4_idx_pblock(idx);
+ bh = sb_getblk_gfp(inode->i_sb, pblk, gfp_flags);
if (unlikely(!bh))
return ERR_PTR(-ENOMEM);
if (!bh_uptodate_or_lock(bh)) {
trace_ext4_ext_load_extent(inode, pblk, _RET_IP_);
- err = bh_submit_read(bh);
+ err = ext4_read_bh(bh, 0, NULL);
if (err < 0)
goto errout;
}
if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE))
return bh;
- if (!ext4_has_feature_journal(inode->i_sb) ||
- (inode->i_ino !=
- le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) {
- err = __ext4_ext_check(function, line, inode,
- ext_block_hdr(bh), depth, pblk);
- if (err)
- goto errout;
- }
+ err = __ext4_ext_check(function, line, inode, ext_block_hdr(bh),
+ depth, pblk, le32_to_cpu(idx->ei_block));
+ if (err)
+ goto errout;
set_buffer_verified(bh);
/*
* If this is a leaf block, cache all of its entries
@@ -565,8 +565,8 @@
}
-#define read_extent_tree_block(inode, pblk, depth, flags) \
- __read_extent_tree_block(__func__, __LINE__, (inode), (pblk), \
+#define read_extent_tree_block(inode, idx, depth, flags) \
+ __read_extent_tree_block(__func__, __LINE__, (inode), (idx), \
(depth), (flags))
/*
@@ -586,6 +586,12 @@
down_read(&ei->i_data_sem);
depth = ext_depth(inode);
+ /* Don't cache anything if there are no external extent blocks */
+ if (!depth) {
+ up_read(&ei->i_data_sem);
+ return ret;
+ }
+
path = kcalloc(depth + 1, sizeof(struct ext4_ext_path),
GFP_NOFS);
if (path == NULL) {
@@ -593,9 +599,6 @@
return -ENOMEM;
}
- /* Don't cache anything if there are no external extent blocks */
- if (depth == 0)
- goto out;
path[0].p_hdr = ext_inode_hdr(inode);
ret = ext4_ext_check(inode, path[0].p_hdr, depth, 0);
if (ret)
@@ -613,8 +616,7 @@
i--;
continue;
}
- bh = read_extent_tree_block(inode,
- ext4_idx_pblock(path[i].p_idx++),
+ bh = read_extent_tree_block(inode, path[i].p_idx++,
depth - i - 1,
EXT4_EX_FORCE_CACHE);
if (IS_ERR(bh)) {
@@ -639,21 +641,22 @@
{
int k, l = path->p_depth;
- ext_debug("path:");
+ ext_debug(inode, "path:");
for (k = 0; k <= l; k++, path++) {
if (path->p_idx) {
- ext_debug(" %d->%llu", le32_to_cpu(path->p_idx->ei_block),
- ext4_idx_pblock(path->p_idx));
+ ext_debug(inode, " %d->%llu",
+ le32_to_cpu(path->p_idx->ei_block),
+ ext4_idx_pblock(path->p_idx));
} else if (path->p_ext) {
- ext_debug(" %d:[%d]%d:%llu ",
+ ext_debug(inode, " %d:[%d]%d:%llu ",
le32_to_cpu(path->p_ext->ee_block),
ext4_ext_is_unwritten(path->p_ext),
ext4_ext_get_actual_len(path->p_ext),
ext4_ext_pblock(path->p_ext));
} else
- ext_debug(" []");
+ ext_debug(inode, " []");
}
- ext_debug("\n");
+ ext_debug(inode, "\n");
}
static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path)
@@ -669,14 +672,14 @@
eh = path[depth].p_hdr;
ex = EXT_FIRST_EXTENT(eh);
- ext_debug("Displaying leaf extents for inode %lu\n", inode->i_ino);
+ ext_debug(inode, "Displaying leaf extents\n");
for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) {
- ext_debug("%d:[%d]%d:%llu ", le32_to_cpu(ex->ee_block),
+ ext_debug(inode, "%d:[%d]%d:%llu ", le32_to_cpu(ex->ee_block),
ext4_ext_is_unwritten(ex),
ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex));
}
- ext_debug("\n");
+ ext_debug(inode, "\n");
}
static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path,
@@ -689,10 +692,9 @@
struct ext4_extent_idx *idx;
idx = path[level].p_idx;
while (idx <= EXT_MAX_INDEX(path[level].p_hdr)) {
- ext_debug("%d: move %d:%llu in new index %llu\n", level,
- le32_to_cpu(idx->ei_block),
- ext4_idx_pblock(idx),
- newblock);
+ ext_debug(inode, "%d: move %d:%llu in new index %llu\n",
+ level, le32_to_cpu(idx->ei_block),
+ ext4_idx_pblock(idx), newblock);
idx++;
}
@@ -701,7 +703,7 @@
ex = path[depth].p_ext;
while (ex <= EXT_MAX_EXTENT(path[depth].p_hdr)) {
- ext_debug("move %d:%llu:[%d]%d in new leaf %llu\n",
+ ext_debug(inode, "move %d:%llu:[%d]%d in new leaf %llu\n",
le32_to_cpu(ex->ee_block),
ext4_ext_pblock(ex),
ext4_ext_is_unwritten(ex),
@@ -724,11 +726,10 @@
if (!path)
return;
depth = path->p_depth;
- for (i = 0; i <= depth; i++, path++)
- if (path->p_bh) {
- brelse(path->p_bh);
- path->p_bh = NULL;
- }
+ for (i = 0; i <= depth; i++, path++) {
+ brelse(path->p_bh);
+ path->p_bh = NULL;
+ }
}
/*
@@ -744,7 +745,7 @@
struct ext4_extent_idx *r, *l, *m;
- ext_debug("binsearch for %u(idx): ", block);
+ ext_debug(inode, "binsearch for %u(idx): ", block);
l = EXT_FIRST_INDEX(eh) + 1;
r = EXT_LAST_INDEX(eh);
@@ -754,13 +755,13 @@
r = m - 1;
else
l = m + 1;
- ext_debug("%p(%u):%p(%u):%p(%u) ", l, le32_to_cpu(l->ei_block),
- m, le32_to_cpu(m->ei_block),
- r, le32_to_cpu(r->ei_block));
+ ext_debug(inode, "%p(%u):%p(%u):%p(%u) ", l,
+ le32_to_cpu(l->ei_block), m, le32_to_cpu(m->ei_block),
+ r, le32_to_cpu(r->ei_block));
}
path->p_idx = l - 1;
- ext_debug(" -> %u->%lld ", le32_to_cpu(path->p_idx->ei_block),
+ ext_debug(inode, " -> %u->%lld ", le32_to_cpu(path->p_idx->ei_block),
ext4_idx_pblock(path->p_idx));
#ifdef CHECK_BINSEARCH
@@ -770,8 +771,8 @@
chix = ix = EXT_FIRST_INDEX(eh);
for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ix++) {
- if (k != 0 &&
- le32_to_cpu(ix->ei_block) <= le32_to_cpu(ix[-1].ei_block)) {
+ if (k != 0 && le32_to_cpu(ix->ei_block) <=
+ le32_to_cpu(ix[-1].ei_block)) {
printk(KERN_DEBUG "k=%d, ix=0x%p, "
"first=0x%p\n", k,
ix, EXT_FIRST_INDEX(eh));
@@ -811,7 +812,7 @@
return;
}
- ext_debug("binsearch for %u: ", block);
+ ext_debug(inode, "binsearch for %u: ", block);
l = EXT_FIRST_EXTENT(eh) + 1;
r = EXT_LAST_EXTENT(eh);
@@ -822,13 +823,13 @@
r = m - 1;
else
l = m + 1;
- ext_debug("%p(%u):%p(%u):%p(%u) ", l, le32_to_cpu(l->ee_block),
- m, le32_to_cpu(m->ee_block),
- r, le32_to_cpu(r->ee_block));
+ ext_debug(inode, "%p(%u):%p(%u):%p(%u) ", l,
+ le32_to_cpu(l->ee_block), m, le32_to_cpu(m->ee_block),
+ r, le32_to_cpu(r->ee_block));
}
path->p_ext = l - 1;
- ext_debug(" -> %d:%llu:[%d]%d ",
+ ext_debug(inode, " -> %d:%llu:[%d]%d ",
le32_to_cpu(path->p_ext->ee_block),
ext4_ext_pblock(path->p_ext),
ext4_ext_is_unwritten(path->p_ext),
@@ -853,7 +854,7 @@
}
-int ext4_ext_tree_init(handle_t *handle, struct inode *inode)
+void ext4_ext_tree_init(handle_t *handle, struct inode *inode)
{
struct ext4_extent_header *eh;
@@ -864,7 +865,6 @@
eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0));
eh->eh_generation = 0;
ext4_mark_inode_dirty(handle, inode);
- return 0;
}
struct ext4_ext_path *
@@ -876,6 +876,10 @@
struct ext4_ext_path *path = orig_path ? *orig_path : NULL;
short int depth, i, ppos = 0;
int ret;
+ gfp_t gfp_flags = GFP_NOFS;
+
+ if (flags & EXT4_EX_NOFAIL)
+ gfp_flags |= __GFP_NOFAIL;
eh = ext_inode_hdr(inode);
depth = ext_depth(inode);
@@ -896,7 +900,7 @@
if (!path) {
/* account possible depth increase */
path = kcalloc(depth + 2, sizeof(struct ext4_ext_path),
- GFP_NOFS);
+ gfp_flags);
if (unlikely(!path))
return ERR_PTR(-ENOMEM);
path[0].p_maxdepth = depth + 1;
@@ -909,7 +913,7 @@
ext4_cache_extents(inode, eh);
/* walk through the tree */
while (i) {
- ext_debug("depth %d: num %d, max %d\n",
+ ext_debug(inode, "depth %d: num %d, max %d\n",
ppos, le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max));
ext4_ext_binsearch_idx(inode, path + ppos, block);
@@ -917,8 +921,7 @@
path[ppos].p_depth = i;
path[ppos].p_ext = NULL;
- bh = read_extent_tree_block(inode, path[ppos].p_block, --i,
- flags);
+ bh = read_extent_tree_block(inode, path[ppos].p_idx, --i, flags);
if (IS_ERR(bh)) {
ret = PTR_ERR(bh);
goto err;
@@ -986,18 +989,20 @@
if (logical > le32_to_cpu(curp->p_idx->ei_block)) {
/* insert after */
- ext_debug("insert new index %d after: %llu\n", logical, ptr);
+ ext_debug(inode, "insert new index %d after: %llu\n",
+ logical, ptr);
ix = curp->p_idx + 1;
} else {
/* insert before */
- ext_debug("insert new index %d before: %llu\n", logical, ptr);
+ ext_debug(inode, "insert new index %d before: %llu\n",
+ logical, ptr);
ix = curp->p_idx;
}
len = EXT_LAST_INDEX(curp->p_hdr) - ix + 1;
BUG_ON(len < 0);
if (len > 0) {
- ext_debug("insert new index %d: "
+ ext_debug(inode, "insert new index %d: "
"move %d indices from 0x%p to 0x%p\n",
logical, len, ix, ix + 1);
memmove(ix + 1, ix, len * sizeof(struct ext4_extent_idx));
@@ -1046,9 +1051,13 @@
ext4_fsblk_t newblock, oldblock;
__le32 border;
ext4_fsblk_t *ablocks = NULL; /* array of allocated blocks */
+ gfp_t gfp_flags = GFP_NOFS;
int err = 0;
size_t ext_size = 0;
+ if (flags & EXT4_EX_NOFAIL)
+ gfp_flags |= __GFP_NOFAIL;
+
/* make decision: where to split? */
/* FIXME: now decision is simplest: at current extent */
@@ -1060,12 +1069,12 @@
}
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."
+ ext_debug(inode, "leaf will be split."
" next leaf starts at %d\n",
le32_to_cpu(border));
} else {
border = newext->ee_block;
- ext_debug("leaf will be added."
+ ext_debug(inode, "leaf will be added."
" next leaf starts at %d\n",
le32_to_cpu(border));
}
@@ -1082,12 +1091,12 @@
* We need this to handle errors and free blocks
* upon them.
*/
- ablocks = kcalloc(depth, sizeof(ext4_fsblk_t), GFP_NOFS);
+ ablocks = kcalloc(depth, sizeof(ext4_fsblk_t), gfp_flags);
if (!ablocks)
return -ENOMEM;
/* allocate all needed blocks */
- ext_debug("allocate %d blocks for indexes/leaf\n", depth - at);
+ ext_debug(inode, "allocate %d blocks for indexes/leaf\n", depth - at);
for (a = 0; a < depth - at; a++) {
newblock = ext4_ext_new_meta_block(handle, inode, path,
newext, &err, flags);
@@ -1174,7 +1183,7 @@
goto cleanup;
}
if (k)
- ext_debug("create %d intermediate indices\n", k);
+ ext_debug(inode, "create %d intermediate indices\n", k);
/* insert new index into current index block */
/* current depth stored in i var */
i = depth - 1;
@@ -1202,7 +1211,7 @@
fidx->ei_block = border;
ext4_idx_store_pblock(fidx, oldblock);
- ext_debug("int.index at %d (block %llu): %u -> %llu\n",
+ ext_debug(inode, "int.index at %d (block %llu): %u -> %llu\n",
i, newblock, le32_to_cpu(border), oldblock);
/* move remainder of path[i] to the new index block */
@@ -1216,7 +1225,7 @@
}
/* start copy indexes */
m = EXT_MAX_INDEX(path[i].p_hdr) - path[i].p_idx++;
- ext_debug("cur 0x%p, last 0x%p\n", path[i].p_idx,
+ ext_debug(inode, "cur 0x%p, last 0x%p\n", path[i].p_idx,
EXT_MAX_INDEX(path[i].p_hdr));
ext4_ext_show_move(inode, path, newblock, i);
if (m) {
@@ -1353,13 +1362,13 @@
EXT_FIRST_INDEX(neh)->ei_block =
EXT_FIRST_EXTENT(neh)->ee_block;
}
- ext_debug("new root: num %d(%d), lblock %d, ptr %llu\n",
+ ext_debug(inode, "new root: num %d(%d), lblock %d, ptr %llu\n",
le16_to_cpu(neh->eh_entries), le16_to_cpu(neh->eh_max),
le32_to_cpu(EXT_FIRST_INDEX(neh)->ei_block),
ext4_idx_pblock(EXT_FIRST_INDEX(neh)));
le16_add_cpu(&neh->eh_depth, 1);
- ext4_mark_inode_dirty(handle, inode);
+ err = ext4_mark_inode_dirty(handle, inode);
out:
brelse(bh);
@@ -1502,22 +1511,21 @@
}
/*
- * search the closest allocated block to the right for *logical
- * and returns it at @logical + it's physical address at @phys
- * if *logical is the largest allocated block, the function
- * returns 0 at @phys
- * return value contains 0 (success) or error code
+ * Search the closest allocated block to the right for *logical
+ * and returns it at @logical + it's physical address at @phys.
+ * If not exists, return 0 and @phys is set to 0. We will return
+ * 1 which means we found an allocated block and ret_ex is valid.
+ * Or return a (< 0) error code.
*/
static int ext4_ext_search_right(struct inode *inode,
struct ext4_ext_path *path,
ext4_lblk_t *logical, ext4_fsblk_t *phys,
- struct ext4_extent **ret_ex)
+ struct ext4_extent *ret_ex)
{
struct buffer_head *bh = NULL;
struct ext4_extent_header *eh;
struct ext4_extent_idx *ix;
struct ext4_extent *ex;
- ext4_fsblk_t block;
int depth; /* Note, NOT eh_depth; depth from top of tree */
int ee_len;
@@ -1584,20 +1592,17 @@
* follow it and find the closest allocated
* block to the right */
ix++;
- block = ext4_idx_pblock(ix);
while (++depth < path->p_depth) {
/* subtract from p_depth to get proper eh_depth */
- bh = read_extent_tree_block(inode, block,
- path->p_depth - depth, 0);
+ bh = read_extent_tree_block(inode, ix, path->p_depth - depth, 0);
if (IS_ERR(bh))
return PTR_ERR(bh);
eh = ext_block_hdr(bh);
ix = EXT_FIRST_INDEX(eh);
- block = ext4_idx_pblock(ix);
put_bh(bh);
}
- bh = read_extent_tree_block(inode, block, path->p_depth - depth, 0);
+ bh = read_extent_tree_block(inode, ix, path->p_depth - depth, 0);
if (IS_ERR(bh))
return PTR_ERR(bh);
eh = ext_block_hdr(bh);
@@ -1605,10 +1610,11 @@
found_extent:
*logical = le32_to_cpu(ex->ee_block);
*phys = ext4_ext_pblock(ex);
- *ret_ex = ex;
+ if (ret_ex)
+ *ret_ex = *ex;
if (bh)
put_bh(bh);
- return 0;
+ return 1;
}
/*
@@ -1630,17 +1636,16 @@
return EXT_MAX_BLOCKS;
while (depth >= 0) {
+ struct ext4_ext_path *p = &path[depth];
+
if (depth == path->p_depth) {
/* leaf */
- if (path[depth].p_ext &&
- path[depth].p_ext !=
- EXT_LAST_EXTENT(path[depth].p_hdr))
- return le32_to_cpu(path[depth].p_ext[1].ee_block);
+ if (p->p_ext && p->p_ext != EXT_LAST_EXTENT(p->p_hdr))
+ return le32_to_cpu(p->p_ext[1].ee_block);
} else {
/* index */
- if (path[depth].p_idx !=
- EXT_LAST_INDEX(path[depth].p_hdr))
- return le32_to_cpu(path[depth].p_idx[1].ei_block);
+ if (p->p_idx != EXT_LAST_INDEX(p->p_hdr))
+ return le32_to_cpu(p->p_idx[1].ei_block);
}
depth--;
}
@@ -1740,9 +1745,9 @@
return err;
}
-int
-ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
- struct ext4_extent *ex2)
+static int ext4_can_extents_be_merged(struct inode *inode,
+ struct ext4_extent *ex1,
+ struct ext4_extent *ex2)
{
unsigned short ext1_ee_len, ext2_ee_len;
@@ -1756,23 +1761,11 @@
le32_to_cpu(ex2->ee_block))
return 0;
- /*
- * To allow future support for preallocated extents to be added
- * as an RO_COMPAT feature, refuse to merge to extents if
- * this can result in the top bit of ee_len being set.
- */
if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN)
return 0;
- /*
- * The check for IO to unwritten extent is somewhat racy as we
- * increment i_unwritten / set EXT4_STATE_DIO_UNWRITTEN only after
- * dropping i_data_sem. But reserved blocks should save us in that
- * case.
- */
+
if (ext4_ext_is_unwritten(ex1) &&
- (ext4_test_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN) ||
- atomic_read(&EXT4_I(inode)->i_unwritten) ||
- (ext1_ee_len + ext2_ee_len > EXT_UNWRITTEN_MAX_LEN)))
+ ext1_ee_len + ext2_ee_len > EXT_UNWRITTEN_MAX_LEN)
return 0;
#ifdef AGGRESSIVE_TEST
if (ext1_ee_len >= 4)
@@ -1850,7 +1843,8 @@
* group descriptor to release the extent tree block. If we
* can't get the journal credits, give up.
*/
- if (ext4_journal_extend(handle, 2))
+ if (ext4_journal_extend(handle, 2,
+ ext4_free_metadata_revoke_credits(inode->i_sb, 1)))
return;
/*
@@ -1874,13 +1868,14 @@
}
/*
- * This function tries to merge the @ex extent to neighbours in the tree.
- * return 1 if merge left else 0.
+ * This function tries to merge the @ex extent to neighbours in the tree, then
+ * tries to collapse the extent tree into the inode.
*/
static void ext4_ext_try_to_merge(handle_t *handle,
struct inode *inode,
struct ext4_ext_path *path,
- struct ext4_extent *ex) {
+ struct ext4_extent *ex)
+{
struct ext4_extent_header *eh;
unsigned int depth;
int merge_done = 0;
@@ -1951,7 +1946,7 @@
/*
* ext4_ext_insert_extent:
- * tries to merge requsted extent into the existing extent or
+ * tries to merge requested extent into the existing extent or
* inserts requested extent as new one into the tree,
* creating new leaf in the no-space case.
*/
@@ -2006,7 +2001,7 @@
/* Try to append newex to the ex */
if (ext4_can_extents_be_merged(inode, ex, newext)) {
- ext_debug("append [%d]%d block to %u:[%d]%d"
+ ext_debug(inode, "append [%d]%d block to %u:[%d]%d"
"(from %llu)\n",
ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
@@ -2031,7 +2026,7 @@
prepend:
/* Try to prepend newex to the ex */
if (ext4_can_extents_be_merged(inode, newext, ex)) {
- ext_debug("prepend %u[%d]%d block to %u:[%d]%d"
+ ext_debug(inode, "prepend %u[%d]%d block to %u:[%d]%d"
"(from %llu)\n",
le32_to_cpu(newext->ee_block),
ext4_ext_is_unwritten(newext),
@@ -2069,20 +2064,20 @@
if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block))
next = ext4_ext_next_leaf_block(path);
if (next != EXT_MAX_BLOCKS) {
- ext_debug("next leaf block - %u\n", next);
+ ext_debug(inode, "next leaf block - %u\n", next);
BUG_ON(npath != NULL);
- npath = ext4_find_extent(inode, next, NULL, 0);
+ npath = ext4_find_extent(inode, next, NULL, gb_flags);
if (IS_ERR(npath))
return PTR_ERR(npath);
BUG_ON(npath->p_depth != path->p_depth);
eh = npath[depth].p_hdr;
if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max)) {
- ext_debug("next leaf isn't full(%d)\n",
+ ext_debug(inode, "next leaf isn't full(%d)\n",
le16_to_cpu(eh->eh_entries));
path = npath;
goto has_space;
}
- ext_debug("next leaf has no free space(%d,%d)\n",
+ ext_debug(inode, "next leaf has no free space(%d,%d)\n",
le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max));
}
@@ -2108,7 +2103,7 @@
if (!nearex) {
/* there is no extent in this leaf, create first one */
- ext_debug("first extent in the leaf: %u:%llu:[%d]%d\n",
+ ext_debug(inode, "first extent in the leaf: %u:%llu:[%d]%d\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
ext4_ext_is_unwritten(newext),
@@ -2118,7 +2113,7 @@
if (le32_to_cpu(newext->ee_block)
> le32_to_cpu(nearex->ee_block)) {
/* Insert after */
- ext_debug("insert %u:%llu:[%d]%d before: "
+ ext_debug(inode, "insert %u:%llu:[%d]%d before: "
"nearest %p\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
@@ -2129,7 +2124,7 @@
} else {
/* Insert before */
BUG_ON(newext->ee_block == nearex->ee_block);
- ext_debug("insert %u:%llu:[%d]%d after: "
+ ext_debug(inode, "insert %u:%llu:[%d]%d after: "
"nearest %p\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
@@ -2139,7 +2134,7 @@
}
len = EXT_LAST_EXTENT(eh) - nearex + 1;
if (len > 0) {
- ext_debug("insert %u:%llu:[%d]%d: "
+ ext_debug(inode, "insert %u:%llu:[%d]%d: "
"move %d extents from 0x%p to 0x%p\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
@@ -2176,155 +2171,6 @@
return err;
}
-static int ext4_fill_fiemap_extents(struct inode *inode,
- ext4_lblk_t block, ext4_lblk_t num,
- struct fiemap_extent_info *fieinfo)
-{
- struct ext4_ext_path *path = NULL;
- struct ext4_extent *ex;
- struct extent_status es;
- ext4_lblk_t next, next_del, start = 0, end = 0;
- ext4_lblk_t last = block + num;
- int exists, depth = 0, err = 0;
- unsigned int flags = 0;
- unsigned char blksize_bits = inode->i_sb->s_blocksize_bits;
-
- while (block < last && block != EXT_MAX_BLOCKS) {
- num = last - block;
- /* find extent for this block */
- down_read(&EXT4_I(inode)->i_data_sem);
-
- path = ext4_find_extent(inode, block, &path, 0);
- if (IS_ERR(path)) {
- up_read(&EXT4_I(inode)->i_data_sem);
- err = PTR_ERR(path);
- path = NULL;
- break;
- }
-
- depth = ext_depth(inode);
- if (unlikely(path[depth].p_hdr == NULL)) {
- up_read(&EXT4_I(inode)->i_data_sem);
- EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth);
- err = -EFSCORRUPTED;
- break;
- }
- ex = path[depth].p_ext;
- next = ext4_ext_next_allocated_block(path);
-
- flags = 0;
- exists = 0;
- if (!ex) {
- /* there is no extent yet, so try to allocate
- * all requested space */
- start = block;
- end = block + num;
- } else if (le32_to_cpu(ex->ee_block) > block) {
- /* need to allocate space before found extent */
- start = block;
- end = le32_to_cpu(ex->ee_block);
- if (block + num < end)
- end = block + num;
- } 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;
- if (end >= next)
- end = next;
- } else if (block >= le32_to_cpu(ex->ee_block)) {
- /*
- * some part of requested space is covered
- * by found extent
- */
- start = block;
- end = le32_to_cpu(ex->ee_block)
- + ext4_ext_get_actual_len(ex);
- if (block + num < end)
- end = block + num;
- exists = 1;
- } else {
- BUG();
- }
- BUG_ON(end <= start);
-
- if (!exists) {
- es.es_lblk = start;
- es.es_len = end - start;
- es.es_pblk = 0;
- } else {
- es.es_lblk = le32_to_cpu(ex->ee_block);
- es.es_len = ext4_ext_get_actual_len(ex);
- es.es_pblk = ext4_ext_pblock(ex);
- if (ext4_ext_is_unwritten(ex))
- flags |= FIEMAP_EXTENT_UNWRITTEN;
- }
-
- /*
- * Find delayed extent and update es accordingly. We call
- * it even in !exists case to find out whether es is the
- * last existing extent or not.
- */
- next_del = ext4_find_delayed_extent(inode, &es);
- if (!exists && next_del) {
- exists = 1;
- flags |= (FIEMAP_EXTENT_DELALLOC |
- FIEMAP_EXTENT_UNKNOWN);
- }
- up_read(&EXT4_I(inode)->i_data_sem);
-
- if (unlikely(es.es_len == 0)) {
- EXT4_ERROR_INODE(inode, "es.es_len == 0");
- err = -EFSCORRUPTED;
- break;
- }
-
- /*
- * This is possible iff next == next_del == EXT_MAX_BLOCKS.
- * we need to check next == EXT_MAX_BLOCKS because it is
- * possible that an extent is with unwritten and delayed
- * status due to when an extent is delayed allocated and
- * is allocated by fallocate status tree will track both of
- * them in a extent.
- *
- * So we could return a unwritten and delayed extent, and
- * its block is equal to 'next'.
- */
- if (next == next_del && next == EXT_MAX_BLOCKS) {
- flags |= FIEMAP_EXTENT_LAST;
- if (unlikely(next_del != EXT_MAX_BLOCKS ||
- next != EXT_MAX_BLOCKS)) {
- EXT4_ERROR_INODE(inode,
- "next extent == %u, next "
- "delalloc extent = %u",
- next, next_del);
- err = -EFSCORRUPTED;
- break;
- }
- }
-
- if (exists) {
- err = fiemap_fill_next_extent(fieinfo,
- (__u64)es.es_lblk << blksize_bits,
- (__u64)es.es_pblk << blksize_bits,
- (__u64)es.es_len << blksize_bits,
- flags);
- if (err < 0)
- break;
- if (err == 1) {
- err = 0;
- break;
- }
- }
-
- block = es.es_lblk + es.es_len;
- }
-
- ext4_ext_drop_refs(path);
- kfree(path);
- return err;
-}
-
static int ext4_fill_es_cache_info(struct inode *inode,
ext4_lblk_t block, ext4_lblk_t num,
struct fiemap_extent_info *fieinfo)
@@ -2432,7 +2278,7 @@
return;
hole_len = min(es.es_lblk - hole_start, hole_len);
}
- ext_debug(" -> %u:%u\n", hole_start, hole_len);
+ ext_debug(inode, " -> %u:%u\n", hole_start, hole_len);
ext4_es_insert_extent(inode, hole_start, hole_len, ~0,
EXTENT_STATUS_HOLE);
}
@@ -2469,7 +2315,7 @@
err = ext4_ext_dirty(handle, inode, path);
if (err)
return err;
- ext_debug("index is empty, remove it, free block %llu\n", leaf);
+ ext_debug(inode, "index is empty, remove it, free block %llu\n", leaf);
trace_ext4_ext_rm_idx(inode, leaf);
ext4_free_blocks(handle, inode, NULL, leaf, 1,
@@ -2737,7 +2583,7 @@
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
int err = 0, correct_index = 0;
- int depth = ext_depth(inode), credits;
+ int depth = ext_depth(inode), credits, revoke_credits;
struct ext4_extent_header *eh;
ext4_lblk_t a, b;
unsigned num;
@@ -2748,7 +2594,7 @@
ext4_fsblk_t pblk;
/* the header must be checked already in ext4_ext_remove_space() */
- ext_debug("truncate since %u in leaf to %u\n", start, end);
+ ext_debug(inode, "truncate since %u in leaf to %u\n", start, end);
if (!path[depth].p_hdr)
path[depth].p_hdr = ext_block_hdr(path[depth].p_bh);
eh = path[depth].p_hdr;
@@ -2774,7 +2620,7 @@
else
unwritten = 0;
- ext_debug("remove ext %u:[%d]%d\n", ex_ee_block,
+ ext_debug(inode, "remove ext %u:[%d]%d\n", ex_ee_block,
unwritten, ex_ee_len);
path[depth].p_ext = ex;
@@ -2782,7 +2628,7 @@
b = ex_ee_block+ex_ee_len - 1 < end ?
ex_ee_block+ex_ee_len - 1 : end;
- ext_debug(" border %u:%u\n", a, b);
+ ext_debug(inode, " border %u:%u\n", a, b);
/* If this extent is beyond the end of the hole, skip it */
if (end < ex_ee_block) {
@@ -2829,10 +2675,23 @@
credits += (ext_depth(inode)) + 1;
}
credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb);
+ /*
+ * We may end up freeing some index blocks and data from the
+ * punched range. Note that partial clusters are accounted for
+ * by ext4_free_data_revoke_credits().
+ */
+ revoke_credits =
+ ext4_free_metadata_revoke_credits(inode->i_sb,
+ ext_depth(inode)) +
+ ext4_free_data_revoke_credits(inode, b - a + 1);
- err = ext4_ext_truncate_extend_restart(handle, inode, credits);
- if (err)
+ err = ext4_datasem_ensure_credits(handle, inode, credits,
+ credits, revoke_credits);
+ if (err) {
+ if (err > 0)
+ err = -EAGAIN;
goto out;
+ }
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
@@ -2878,7 +2737,7 @@
if (err)
goto out;
- ext_debug("new extent: %u:%u:%llu\n", ex_ee_block, num,
+ ext_debug(inode, "new extent: %u:%u:%llu\n", ex_ee_block, num,
ext4_ext_pblock(ex));
ex--;
ex_ee_block = le32_to_cpu(ex->ee_block);
@@ -2955,10 +2814,12 @@
partial.lblk = 0;
partial.state = initial;
- ext_debug("truncate since %u to %u\n", start, end);
+ ext_debug(inode, "truncate since %u to %u\n", start, end);
/* probably first extent we're gonna free will be last in block */
- handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, depth + 1);
+ handle = ext4_journal_start_with_revoke(inode, EXT4_HT_TRUNCATE,
+ depth + 1,
+ ext4_free_metadata_revoke_credits(inode->i_sb, depth));
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -2978,7 +2839,8 @@
ext4_fsblk_t pblk;
/* find extent for or closest extent to this block */
- path = ext4_find_extent(inode, end, NULL, EXT4_EX_NOCACHE);
+ path = ext4_find_extent(inode, end, NULL,
+ EXT4_EX_NOCACHE | EXT4_EX_NOFAIL);
if (IS_ERR(path)) {
ext4_journal_stop(handle);
return PTR_ERR(path);
@@ -3043,8 +2905,8 @@
*/
lblk = ex_end + 1;
err = ext4_ext_search_right(inode, path, &lblk, &pblk,
- &ex);
- if (err)
+ NULL);
+ if (err < 0)
goto out;
if (pblk) {
partial.pclu = EXT4_B2C(sbi, pblk);
@@ -3064,7 +2926,7 @@
le16_to_cpu(path[k].p_hdr->eh_entries)+1;
} else {
path = kcalloc(depth + 1, sizeof(struct ext4_ext_path),
- GFP_NOFS);
+ GFP_NOFS | __GFP_NOFAIL);
if (path == NULL) {
ext4_journal_stop(handle);
return -ENOMEM;
@@ -3094,7 +2956,7 @@
/* this is index block */
if (!path[i].p_hdr) {
- ext_debug("initialize header\n");
+ ext_debug(inode, "initialize header\n");
path[i].p_hdr = ext_block_hdr(path[i].p_bh);
}
@@ -3102,7 +2964,7 @@
/* this level hasn't been touched yet */
path[i].p_idx = EXT_LAST_INDEX(path[i].p_hdr);
path[i].p_block = le16_to_cpu(path[i].p_hdr->eh_entries)+1;
- ext_debug("init index ptr: hdr 0x%p, num %d\n",
+ ext_debug(inode, "init index ptr: hdr 0x%p, num %d\n",
path[i].p_hdr,
le16_to_cpu(path[i].p_hdr->eh_entries));
} else {
@@ -3110,18 +2972,18 @@
path[i].p_idx--;
}
- ext_debug("level %d - index, first 0x%p, cur 0x%p\n",
+ ext_debug(inode, "level %d - index, first 0x%p, cur 0x%p\n",
i, EXT_FIRST_INDEX(path[i].p_hdr),
path[i].p_idx);
if (ext4_ext_more_to_rm(path + i)) {
struct buffer_head *bh;
/* go to the next level */
- ext_debug("move to level %d (block %llu)\n",
+ ext_debug(inode, "move to level %d (block %llu)\n",
i + 1, ext4_idx_pblock(path[i].p_idx));
memset(path + i + 1, 0, sizeof(*path));
- bh = read_extent_tree_block(inode,
- ext4_idx_pblock(path[i].p_idx), depth - i - 1,
- EXT4_EX_NOCACHE);
+ bh = read_extent_tree_block(inode, path[i].p_idx,
+ depth - i - 1,
+ EXT4_EX_NOCACHE);
if (IS_ERR(bh)) {
/* should we reset i_size? */
err = PTR_ERR(bh);
@@ -3152,7 +3014,7 @@
brelse(path[i].p_bh);
path[i].p_bh = NULL;
i--;
- ext_debug("return to level %d\n", i);
+ ext_debug(inode, "return to level %d\n", i);
}
}
@@ -3294,7 +3156,7 @@
*
*
* Splits extent [a, b] into two extents [a, @split) and [@split, b], states
- * of which are deterimined by split_flag.
+ * of which are determined by split_flag.
*
* There are two cases:
* a> the extent are splitted into two extent.
@@ -3320,8 +3182,7 @@
BUG_ON((split_flag & (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2)) ==
(EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2));
- ext_debug("ext4_split_extents_at: inode %lu, logical"
- "block %llu\n", inode->i_ino, (unsigned long long)split);
+ ext_debug(inode, "logical block %llu\n", (unsigned long long)split);
ext4_ext_show_leaf(inode, path);
@@ -3429,6 +3290,10 @@
fix_extent_len:
ex->ee_len = orig_ex.ee_len;
+ /*
+ * Ignore ext4_ext_dirty return value since we are already in error path
+ * and err is a non-zero error code.
+ */
ext4_ext_dirty(handle, inode, path + path->p_depth);
return err;
out:
@@ -3488,7 +3353,7 @@
* Update path is required because previous ext4_split_extent_at() may
* result in split of original leaf or extent zeroout.
*/
- path = ext4_find_extent(inode, map->m_lblk, ppath, 0);
+ path = ext4_find_extent(inode, map->m_lblk, ppath, flags);
if (IS_ERR(path))
return PTR_ERR(path);
depth = ext_depth(inode);
@@ -3557,9 +3422,8 @@
int err = 0;
int split_flag = EXT4_EXT_DATA_VALID2;
- 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_len);
+ ext_debug(inode, "logical block %llu, max_blocks %u\n",
+ (unsigned long long)map->m_lblk, map_len);
sbi = EXT4_SB(inode->i_sb);
eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1)
@@ -3691,7 +3555,7 @@
}
if (allocated) {
/* Mark the block containing both extents as dirty */
- ext4_ext_dirty(handle, inode, path + depth);
+ err = ext4_ext_dirty(handle, inode, path + depth);
/* Update path to point to the right extent */
path[depth].p_ext = abut_ex;
@@ -3710,9 +3574,6 @@
max_zeroout = sbi->s_extent_max_zeroout_kb >>
(inode->i_sb->s_blocksize_bits - 10);
- if (IS_ENCRYPTED(inode))
- max_zeroout = 0;
-
/*
* five cases:
* 1. split the extent into three extents.
@@ -3814,8 +3675,7 @@
unsigned int ee_len;
int split_flag = 0, depth;
- ext_debug("%s: inode %lu, logical block %llu, max_blocks %u\n",
- __func__, inode->i_ino,
+ ext_debug(inode, "logical block %llu, max_blocks %u\n",
(unsigned long long)map->m_lblk, map->m_len);
eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1)
@@ -3824,7 +3684,7 @@
eof_block = map->m_lblk + map->m_len;
/*
* It is safe to convert extent to initialized via explicit
- * zeroout only if extent is fully insde i_size or new_size.
+ * zeroout only if extent is fully inside i_size or new_size.
*/
depth = ext_depth(inode);
ex = path[depth].p_ext;
@@ -3861,8 +3721,7 @@
ee_block = le32_to_cpu(ex->ee_block);
ee_len = ext4_ext_get_actual_len(ex);
- ext_debug("ext4_convert_unwritten_extents_endio: inode %lu, logical"
- "block %llu, max_blocks %u\n", inode->i_ino,
+ ext_debug(inode, "logical block %llu, max_blocks %u\n",
(unsigned long long)ee_block, ee_len);
/* If extent is larger than requested it is a clear sign that we still
@@ -3907,64 +3766,11 @@
return err;
}
-/*
- * Handle EOFBLOCKS_FL flag, clearing it if necessary
- */
-static int check_eofblocks_fl(handle_t *handle, struct inode *inode,
- ext4_lblk_t lblk,
- struct ext4_ext_path *path,
- unsigned int len)
-{
- int i, depth;
- struct ext4_extent_header *eh;
- struct ext4_extent *last_ex;
-
- if (!ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS))
- return 0;
-
- depth = ext_depth(inode);
- eh = path[depth].p_hdr;
-
- /*
- * We're going to remove EOFBLOCKS_FL entirely in future so we
- * do not care for this case anymore. Simply remove the flag
- * if there are no extents.
- */
- if (unlikely(!eh->eh_entries))
- goto out;
- last_ex = EXT_LAST_EXTENT(eh);
- /*
- * We should clear the EOFBLOCKS_FL flag if we are writing the
- * last block in the last extent in the file. We test this by
- * first checking to see if the caller to
- * ext4_ext_get_blocks() was interested in the last block (or
- * a block beyond the last block) in the current extent. If
- * this turns out to be false, we can bail out from this
- * function immediately.
- */
- if (lblk + len < le32_to_cpu(last_ex->ee_block) +
- ext4_ext_get_actual_len(last_ex))
- return 0;
- /*
- * If the caller does appear to be planning to write at or
- * beyond the end of the current extent, we then test to see
- * if the current extent is the last extent in the file, by
- * checking to make sure it was reached via the rightmost node
- * at each level of the tree.
- */
- for (i = depth-1; i >= 0; i--)
- if (path[i].p_idx != EXT_LAST_INDEX(path[i].p_hdr))
- return 0;
-out:
- ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
- return ext4_mark_inode_dirty(handle, inode);
-}
-
static int
convert_initialized_extent(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map,
struct ext4_ext_path **ppath,
- unsigned int allocated)
+ unsigned int *allocated)
{
struct ext4_ext_path *path = *ppath;
struct ext4_extent *ex;
@@ -3985,8 +3791,7 @@
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,
+ ext_debug(inode, "logical block %llu, max_blocks %u\n",
(unsigned long long)ee_block, ee_len);
if (ee_block != map->m_lblk || ee_len > map->m_len) {
@@ -4024,14 +3829,12 @@
ext4_ext_show_leaf(inode, path);
ext4_update_inode_fsync_trans(handle, inode, 1);
- err = check_eofblocks_fl(handle, inode, map->m_lblk, path, map->m_len);
- if (err)
- return err;
+
map->m_flags |= EXT4_MAP_UNWRITTEN;
- if (allocated > map->m_len)
- allocated = map->m_len;
- map->m_len = allocated;
- return allocated;
+ if (*allocated > map->m_len)
+ *allocated = map->m_len;
+ map->m_len = *allocated;
+ return 0;
}
static int
@@ -4040,14 +3843,13 @@
struct ext4_ext_path **ppath, int flags,
unsigned int allocated, ext4_fsblk_t newblock)
{
- struct ext4_ext_path *path = *ppath;
+ struct ext4_ext_path __maybe_unused *path = *ppath;
int ret = 0;
int err = 0;
- ext_debug("ext4_ext_handle_unwritten_extents: inode %lu, logical "
- "block %llu, max_blocks %u, flags %x, allocated %u\n",
- inode->i_ino, (unsigned long long)map->m_lblk, map->m_len,
- flags, allocated);
+ ext_debug(inode, "logical block %llu, max_blocks %u, flags 0x%x, allocated %u\n",
+ (unsigned long long)map->m_lblk, map->m_len, flags,
+ allocated);
ext4_ext_show_leaf(inode, path);
/*
@@ -4059,41 +3861,38 @@
trace_ext4_ext_handle_unwritten_extents(inode, map, flags,
allocated, newblock);
- /* get_block() before submit the IO, split the extent */
+ /* get_block() before submitting IO, split the extent */
if (flags & EXT4_GET_BLOCKS_PRE_IO) {
ret = ext4_split_convert_extents(handle, inode, map, ppath,
flags | EXT4_GET_BLOCKS_CONVERT);
- if (ret <= 0)
- goto out;
+ if (ret < 0) {
+ err = ret;
+ goto out2;
+ }
+ /*
+ * shouldn't get a 0 return when splitting an extent unless
+ * m_len is 0 (bug) or extent has been corrupted
+ */
+ if (unlikely(ret == 0)) {
+ EXT4_ERROR_INODE(inode,
+ "unexpected ret == 0, m_len = %u",
+ map->m_len);
+ err = -EFSCORRUPTED;
+ goto out2;
+ }
map->m_flags |= EXT4_MAP_UNWRITTEN;
goto out;
}
/* IO end_io complete, convert the filled extent to written */
if (flags & EXT4_GET_BLOCKS_CONVERT) {
- if (flags & EXT4_GET_BLOCKS_ZERO) {
- if (allocated > map->m_len)
- allocated = map->m_len;
- err = ext4_issue_zeroout(inode, map->m_lblk, newblock,
- allocated);
- if (err < 0)
- goto out2;
- }
- ret = ext4_convert_unwritten_extents_endio(handle, inode, map,
+ err = ext4_convert_unwritten_extents_endio(handle, inode, map,
ppath);
- 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_MAPPED;
- map->m_pblk = newblock;
- if (allocated > map->m_len)
- allocated = map->m_len;
- map->m_len = allocated;
- goto out2;
+ if (err < 0)
+ goto out2;
+ ext4_update_inode_fsync_trans(handle, inode, 1);
+ goto map_out;
}
- /* buffered IO case */
+ /* buffered IO cases */
/*
* repeat fallocate creation request
* we already have an unwritten extent
@@ -4116,35 +3915,39 @@
goto out1;
}
- /* buffered write, writepage time, convert*/
+ /*
+ * Default case when (flags & EXT4_GET_BLOCKS_CREATE) == 1.
+ * For buffered writes, at writepage time, etc. Convert a
+ * discovered unwritten extent to written.
+ */
ret = ext4_ext_convert_to_initialized(handle, inode, map, ppath, flags);
- if (ret >= 0)
- ext4_update_inode_fsync_trans(handle, inode, 1);
-out:
- if (ret <= 0) {
+ if (ret < 0) {
err = ret;
goto out2;
- } else
- allocated = ret;
- map->m_flags |= EXT4_MAP_NEW;
- if (allocated > map->m_len)
- allocated = map->m_len;
- map->m_len = allocated;
+ }
+ ext4_update_inode_fsync_trans(handle, inode, 1);
+ /*
+ * shouldn't get a 0 return when converting an unwritten extent
+ * unless m_len is 0 (bug) or extent has been corrupted
+ */
+ if (unlikely(ret == 0)) {
+ EXT4_ERROR_INODE(inode, "unexpected ret == 0, m_len = %u",
+ map->m_len);
+ err = -EFSCORRUPTED;
+ goto out2;
+ }
+out:
+ allocated = ret;
+ map->m_flags |= EXT4_MAP_NEW;
map_out:
map->m_flags |= EXT4_MAP_MAPPED;
- if ((flags & EXT4_GET_BLOCKS_KEEP_SIZE) == 0) {
- err = check_eofblocks_fl(handle, inode, map->m_lblk, path,
- map->m_len);
- if (err < 0)
- goto out2;
- }
out1:
+ map->m_pblk = newblock;
if (allocated > map->m_len)
allocated = map->m_len;
- ext4_ext_show_leaf(inode, path);
- map->m_pblk = newblock;
map->m_len = allocated;
+ ext4_ext_show_leaf(inode, path);
out2:
return err ? err : allocated;
}
@@ -4260,7 +4063,7 @@
* down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block
* (ie, create is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem)
*
- * return > 0, number of of blocks already mapped/allocated
+ * return > 0, number of blocks already mapped/allocated
* if create == 0 and these are pre-allocated blocks
* buffer head is unmapped
* otherwise blocks are mapped
@@ -4274,18 +4077,16 @@
struct ext4_map_blocks *map, int flags)
{
struct ext4_ext_path *path = NULL;
- struct ext4_extent newex, *ex, *ex2;
+ 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, ret;
+ ext4_fsblk_t newblock = 0, pblk;
+ int err = 0, depth, ret;
unsigned int allocated = 0, offset = 0;
unsigned int allocated_clusters = 0;
struct ext4_allocation_request ar;
ext4_lblk_t cluster_offset;
- bool map_from_cluster = false;
- ext_debug("blocks %u/%u requested for inode %lu\n",
- map->m_lblk, map->m_len, inode->i_ino);
+ ext_debug(inode, "blocks %u/%u requested\n", map->m_lblk, map->m_len);
trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
/* find extent for this block */
@@ -4293,7 +4094,7 @@
if (IS_ERR(path)) {
err = PTR_ERR(path);
path = NULL;
- goto out2;
+ goto out;
}
depth = ext_depth(inode);
@@ -4309,7 +4110,7 @@
(unsigned long) map->m_lblk, depth,
path[depth].p_block);
err = -EFSCORRUPTED;
- goto out2;
+ goto out;
}
ex = path[depth].p_ext;
@@ -4332,8 +4133,8 @@
newblock = map->m_lblk - ee_block + ee_start;
/* number of remaining blocks in the extent */
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);
+ ext_debug(inode, "%u fit into %u:%d -> %llu\n",
+ map->m_lblk, ee_block, ee_len, newblock);
/*
* If the extent is initialized check whether the
@@ -4341,12 +4142,18 @@
*/
if ((!ext4_ext_is_unwritten(ex)) &&
(flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) {
- allocated = convert_initialized_extent(
- handle, inode, map, &path,
- allocated);
- goto out2;
- } else if (!ext4_ext_is_unwritten(ex))
+ err = convert_initialized_extent(handle,
+ inode, map, &path, &allocated);
goto out;
+ } else if (!ext4_ext_is_unwritten(ex)) {
+ map->m_flags |= EXT4_MAP_MAPPED;
+ map->m_pblk = newblock;
+ if (allocated > map->m_len)
+ allocated = map->m_len;
+ map->m_len = allocated;
+ ext4_ext_show_leaf(inode, path);
+ goto out;
+ }
ret = ext4_ext_handle_unwritten_extents(
handle, inode, map, &path, flags,
@@ -4355,7 +4162,7 @@
err = ret;
else
allocated = ret;
- goto out2;
+ goto out;
}
}
@@ -4380,7 +4187,7 @@
map->m_pblk = 0;
map->m_len = min_t(unsigned int, map->m_len, hole_len);
- goto out2;
+ goto out;
}
/*
@@ -4397,7 +4204,6 @@
get_implied_cluster_alloc(inode->i_sb, map, ex, path)) {
ar.len = allocated = map->m_len;
newblock = map->m_pblk;
- map_from_cluster = true;
goto got_allocated_blocks;
}
@@ -4405,20 +4211,18 @@
ar.lleft = map->m_lblk;
err = ext4_ext_search_left(inode, path, &ar.lleft, &ar.pleft);
if (err)
- goto out2;
+ goto out;
ar.lright = map->m_lblk;
- ex2 = NULL;
err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright, &ex2);
- if (err)
- goto out2;
+ if (err < 0)
+ goto out;
/* Check if the extent after searching to the right implies a
* cluster we can use. */
- if ((sbi->s_cluster_ratio > 1) && ex2 &&
- get_implied_cluster_alloc(inode->i_sb, map, ex2, path)) {
+ if ((sbi->s_cluster_ratio > 1) && err &&
+ get_implied_cluster_alloc(inode->i_sb, map, &ex2, path)) {
ar.len = allocated = map->m_len;
newblock = map->m_pblk;
- map_from_cluster = true;
goto got_allocated_blocks;
}
@@ -4472,59 +4276,52 @@
ar.flags |= EXT4_MB_USE_RESERVED;
newblock = ext4_mb_new_blocks(handle, &ar, &err);
if (!newblock)
- goto out2;
- ext_debug("allocate new block: goal %llu, found %llu/%u\n",
- ar.goal, newblock, allocated);
- free_on_err = 1;
+ goto out;
allocated_clusters = ar.len;
ar.len = EXT4_C2B(sbi, ar.len) - offset;
+ ext_debug(inode, "allocate new block: goal %llu, found %llu/%u, requested %u\n",
+ ar.goal, newblock, ar.len, allocated);
if (ar.len > allocated)
ar.len = allocated;
got_allocated_blocks:
/* try to insert new extent into found leaf and return */
- ext4_ext_store_pblock(&newex, newblock + offset);
+ pblk = newblock + offset;
+ ext4_ext_store_pblock(&newex, pblk);
newex.ee_len = cpu_to_le16(ar.len);
/* Mark unwritten */
- if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT){
+ if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT) {
ext4_ext_mark_unwritten(&newex);
map->m_flags |= EXT4_MAP_UNWRITTEN;
}
- err = 0;
- if ((flags & EXT4_GET_BLOCKS_KEEP_SIZE) == 0)
- err = check_eofblocks_fl(handle, inode, map->m_lblk,
- path, ar.len);
- if (!err)
- err = ext4_ext_insert_extent(handle, inode, &path,
- &newex, flags);
+ err = ext4_ext_insert_extent(handle, inode, &path, &newex, flags);
+ if (err) {
+ if (allocated_clusters) {
+ int fb_flags = 0;
- if (err && free_on_err) {
- int fb_flags = flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE ?
- EXT4_FREE_BLOCKS_NO_QUOT_UPDATE : 0;
- /* free data blocks we just allocated */
- /* not a good idea to call discard here directly,
- * but otherwise we'd need to call it every free() */
- ext4_discard_preallocations(inode);
- ext4_free_blocks(handle, inode, NULL, newblock,
- EXT4_C2B(sbi, allocated_clusters), fb_flags);
- goto out2;
+ /*
+ * free data blocks we just allocated.
+ * not a good idea to call discard here directly,
+ * but otherwise we'd need to call it every free().
+ */
+ ext4_discard_preallocations(inode, 0);
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+ fb_flags = EXT4_FREE_BLOCKS_NO_QUOT_UPDATE;
+ ext4_free_blocks(handle, inode, NULL, newblock,
+ EXT4_C2B(sbi, allocated_clusters),
+ fb_flags);
+ }
+ goto out;
}
- /* previous routine could use block we allocated */
- newblock = ext4_ext_pblock(&newex);
- allocated = ext4_ext_get_actual_len(&newex);
- if (allocated > map->m_len)
- allocated = map->m_len;
- map->m_flags |= EXT4_MAP_NEW;
-
/*
* Reduce the reserved cluster count to reflect successful deferred
* allocation of delayed allocated clusters or direct allocation of
* clusters discovered to be delayed allocated. Once allocated, a
* cluster is not included in the reserved count.
*/
- if (test_opt(inode->i_sb, DELALLOC) && !map_from_cluster) {
+ if (test_opt(inode->i_sb, DELALLOC) && allocated_clusters) {
if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
/*
* When allocating delayed allocated clusters, simply
@@ -4563,14 +4360,13 @@
ext4_update_inode_fsync_trans(handle, inode, 1);
else
ext4_update_inode_fsync_trans(handle, inode, 0);
-out:
- if (allocated > map->m_len)
- allocated = map->m_len;
+
+ map->m_flags |= (EXT4_MAP_NEW | EXT4_MAP_MAPPED);
+ map->m_pblk = pblk;
+ map->m_len = ar.len;
+ allocated = map->m_len;
ext4_ext_show_leaf(inode, path);
- map->m_flags |= EXT4_MAP_MAPPED;
- map->m_pblk = newblock;
- map->m_len = allocated;
-out2:
+out:
ext4_ext_drop_refs(path);
kfree(path);
@@ -4609,7 +4405,14 @@
}
if (err)
return err;
- return ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1);
+retry_remove_space:
+ err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1);
+ if (err == -ENOMEM) {
+ cond_resched();
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ goto retry_remove_space;
+ }
+ return err;
}
static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
@@ -4619,7 +4422,7 @@
struct inode *inode = file_inode(file);
handle_t *handle;
int ret = 0;
- int ret2 = 0;
+ int ret2 = 0, ret3 = 0;
int retries = 0;
int depth = 0;
struct ext4_map_blocks map;
@@ -4678,15 +4481,12 @@
epos = new_size;
if (ext4_update_inode_size(inode, epos) & 0x1)
inode->i_mtime = inode->i_ctime;
- } else {
- if (epos > inode->i_size)
- ext4_set_inode_flag(inode,
- EXT4_INODE_EOFBLOCKS);
}
- ext4_mark_inode_dirty(handle, inode);
+ ret2 = ext4_mark_inode_dirty(handle, inode);
ext4_update_inode_fsync_trans(handle, inode, 1);
- ret2 = ext4_journal_stop(handle);
- if (ret2)
+ ret3 = ext4_journal_stop(handle);
+ ret2 = ret3 ? ret3 : ret2;
+ if (unlikely(ret2))
break;
}
if (ret == -ENOSPC &&
@@ -4698,6 +4498,10 @@
return ret > 0 ? ret2 : ret;
}
+static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len);
+
+static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len);
+
static long ext4_zero_range(struct file *file, loff_t offset,
loff_t len, int mode)
{
@@ -4715,9 +4519,6 @@
trace_ext4_zero_range(inode, offset, len, mode);
- if (!S_ISREG(inode->i_mode))
- return -EINVAL;
-
/* Call ext4_force_commit to flush all data in case of data=journal. */
if (ext4_should_journal_data(inode)) {
ret = ext4_force_commit(inode->i_sb);
@@ -4726,7 +4527,7 @@
}
/*
- * Round up offset. This is not fallocate, we neet to zero out
+ * Round up offset. This is not fallocate, we need 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.
@@ -4749,7 +4550,7 @@
inode_lock(inode);
/*
- * Indirect files do not support unwritten extnets
+ * Indirect files do not support unwritten extents
*/
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
ret = -EOPNOTSUPP;
@@ -4757,7 +4558,7 @@
}
if (!(mode & FALLOC_FL_KEEP_SIZE) &&
- (offset + len > i_size_read(inode) ||
+ (offset + len > inode->i_size ||
offset + len > EXT4_I(inode)->i_disksize)) {
new_size = offset + len;
ret = inode_newsize_ok(inode, new_size);
@@ -4766,8 +4567,6 @@
}
flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT;
- if (mode & FALLOC_FL_KEEP_SIZE)
- flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
/* Wait all existing dio workers, newcomers will block on i_mutex */
inode_dio_wait(inode);
@@ -4834,18 +4633,11 @@
}
inode->i_mtime = inode->i_ctime = current_time(inode);
- if (new_size) {
+ if (new_size)
ext4_update_inode_size(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);
-
+ ret = ext4_mark_inode_dirty(handle, inode);
+ if (unlikely(ret))
+ goto out_handle;
/* Zero out partial block at the edges of the range */
ret = ext4_zero_partial_blocks(handle, inode, offset, len);
if (ret >= 0)
@@ -4854,6 +4646,7 @@
if (file->f_flags & O_SYNC)
ext4_handle_sync(handle);
+out_handle:
ext4_journal_stop(handle);
out_mutex:
inode_unlock(inode);
@@ -4882,14 +4675,9 @@
* range since we would need to re-encrypt blocks with a
* different IV or XTS tweak (which are based on the logical
* block number).
- *
- * XXX It's not clear why zero range isn't working, but we'll
- * leave it disabled for encrypted inodes for now. This is a
- * bug we should fix....
*/
if (IS_ENCRYPTED(inode) &&
- (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE |
- FALLOC_FL_ZERO_RANGE)))
+ (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE)))
return -EOPNOTSUPP;
/* Return error if mode is not supported */
@@ -4898,29 +4686,36 @@
FALLOC_FL_INSERT_RANGE))
return -EOPNOTSUPP;
- if (mode & FALLOC_FL_PUNCH_HOLE)
- return ext4_punch_hole(inode, offset, len);
+ ext4_fc_start_update(inode);
+
+ if (mode & FALLOC_FL_PUNCH_HOLE) {
+ ret = ext4_punch_hole(inode, offset, len);
+ goto exit;
+ }
ret = ext4_convert_inline_data(inode);
if (ret)
- return ret;
+ goto exit;
- if (mode & FALLOC_FL_COLLAPSE_RANGE)
- return ext4_collapse_range(inode, offset, len);
+ if (mode & FALLOC_FL_COLLAPSE_RANGE) {
+ ret = ext4_collapse_range(inode, offset, len);
+ goto exit;
+ }
- if (mode & FALLOC_FL_INSERT_RANGE)
- return ext4_insert_range(inode, offset, len);
+ if (mode & FALLOC_FL_INSERT_RANGE) {
+ ret = ext4_insert_range(inode, offset, len);
+ goto exit;
+ }
- if (mode & FALLOC_FL_ZERO_RANGE)
- return ext4_zero_range(file, offset, len, mode);
-
+ if (mode & FALLOC_FL_ZERO_RANGE) {
+ ret = ext4_zero_range(file, offset, len, mode);
+ goto exit;
+ }
trace_ext4_fallocate_enter(inode, offset, len, mode);
lblk = offset >> blkbits;
max_blocks = EXT4_MAX_BLOCKS(len, offset, blkbits);
flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT;
- if (mode & FALLOC_FL_KEEP_SIZE)
- flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
inode_lock(inode);
@@ -4933,7 +4728,7 @@
}
if (!(mode & FALLOC_FL_KEEP_SIZE) &&
- (offset + len > i_size_read(inode) ||
+ (offset + len > inode->i_size ||
offset + len > EXT4_I(inode)->i_disksize)) {
new_size = offset + len;
ret = inode_newsize_ok(inode, new_size);
@@ -4949,12 +4744,14 @@
goto out;
if (file->f_flags & O_SYNC && EXT4_SB(inode->i_sb)->s_journal) {
- ret = jbd2_complete_transaction(EXT4_SB(inode->i_sb)->s_journal,
- EXT4_I(inode)->i_sync_tid);
+ ret = ext4_fc_commit(EXT4_SB(inode->i_sb)->s_journal,
+ EXT4_I(inode)->i_sync_tid);
}
out:
inode_unlock(inode);
trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
+exit:
+ ext4_fc_stop_update(inode);
return ret;
}
@@ -4972,26 +4769,15 @@
loff_t offset, ssize_t len)
{
unsigned int max_blocks;
- int ret = 0;
- int ret2 = 0;
+ int ret = 0, ret2 = 0, ret3 = 0;
struct ext4_map_blocks map;
- unsigned int credits, blkbits = inode->i_blkbits;
+ unsigned int blkbits = inode->i_blkbits;
+ unsigned int credits = 0;
map.m_lblk = offset >> blkbits;
max_blocks = EXT4_MAX_BLOCKS(len, offset, blkbits);
- /*
- * This is somewhat ugly but the idea is clear: When transaction is
- * reserved, everything goes into it. Otherwise we rather start several
- * smaller transactions for conversion of each extent separately.
- */
- if (handle) {
- handle = ext4_journal_start_reserved(handle,
- EXT4_HT_EXT_CONVERT);
- if (IS_ERR(handle))
- return PTR_ERR(handle);
- credits = 0;
- } else {
+ if (!handle) {
/*
* credits to insert 1 extent into extent tree
*/
@@ -5016,75 +4802,57 @@
"ext4_ext_map_blocks returned %d",
inode->i_ino, map.m_lblk,
map.m_len, ret);
- ext4_mark_inode_dirty(handle, inode);
- if (credits)
- ret2 = ext4_journal_stop(handle);
+ ret2 = ext4_mark_inode_dirty(handle, inode);
+ if (credits) {
+ ret3 = ext4_journal_stop(handle);
+ if (unlikely(ret3))
+ ret2 = ret3;
+ }
+
if (ret <= 0 || ret2)
break;
}
- if (!credits)
- ret2 = ext4_journal_stop(handle);
return ret > 0 ? ret2 : ret;
}
-/*
- * If newes is not existing extent (newes->ec_pblk equals zero) find
- * delayed extent at start of newes and update newes accordingly and
- * return start of the next delayed extent.
- *
- * If newes is existing extent (newes->ec_pblk is not equal zero)
- * return start of next delayed extent or EXT_MAX_BLOCKS if no delayed
- * extent found. Leave newes unmodified.
- */
-static int ext4_find_delayed_extent(struct inode *inode,
- struct extent_status *newes)
+int ext4_convert_unwritten_io_end_vec(handle_t *handle, ext4_io_end_t *io_end)
{
- struct extent_status es;
- ext4_lblk_t block, next_del;
+ int ret = 0, err = 0;
+ struct ext4_io_end_vec *io_end_vec;
- if (newes->es_pblk == 0) {
- ext4_es_find_extent_range(inode, &ext4_es_is_delayed,
- newes->es_lblk,
- newes->es_lblk + newes->es_len - 1,
- &es);
-
- /*
- * No extent in extent-tree contains block @newes->es_pblk,
- * then the block may stay in 1)a hole or 2)delayed-extent.
- */
- if (es.es_len == 0)
- /* A hole found. */
- return 0;
-
- if (es.es_lblk > newes->es_lblk) {
- /* A hole found. */
- newes->es_len = min(es.es_lblk - newes->es_lblk,
- newes->es_len);
- return 0;
- }
-
- newes->es_len = es.es_lblk + es.es_len - newes->es_lblk;
+ /*
+ * This is somewhat ugly but the idea is clear: When transaction is
+ * reserved, everything goes into it. Otherwise we rather start several
+ * smaller transactions for conversion of each extent separately.
+ */
+ if (handle) {
+ handle = ext4_journal_start_reserved(handle,
+ EXT4_HT_EXT_CONVERT);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
}
- block = newes->es_lblk + newes->es_len;
- ext4_es_find_extent_range(inode, &ext4_es_is_delayed, block,
- EXT_MAX_BLOCKS, &es);
- if (es.es_len == 0)
- next_del = EXT_MAX_BLOCKS;
- else
- next_del = es.es_lblk;
+ list_for_each_entry(io_end_vec, &io_end->list_vec, list) {
+ ret = ext4_convert_unwritten_extents(handle, io_end->inode,
+ io_end_vec->offset,
+ io_end_vec->size);
+ if (ret)
+ break;
+ }
- return next_del;
+ if (handle)
+ err = ext4_journal_stop(handle);
+
+ return ret < 0 ? ret : err;
}
-static int ext4_xattr_fiemap(struct inode *inode,
- struct fiemap_extent_info *fieinfo)
+static int ext4_iomap_xattr_fiemap(struct inode *inode, struct iomap *iomap)
{
__u64 physical = 0;
- __u64 length;
- __u32 flags = FIEMAP_EXTENT_LAST;
+ __u64 length = 0;
int blockbits = inode->i_sb->s_blocksize_bits;
int error = 0;
+ u16 iomap_type;
/* in-inode? */
if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
@@ -5099,41 +4867,70 @@
EXT4_I(inode)->i_extra_isize;
physical += offset;
length = EXT4_SB(inode->i_sb)->s_inode_size - offset;
- flags |= FIEMAP_EXTENT_DATA_INLINE;
brelse(iloc.bh);
- } else { /* external block */
+ iomap_type = IOMAP_INLINE;
+ } else if (EXT4_I(inode)->i_file_acl) { /* external block */
physical = (__u64)EXT4_I(inode)->i_file_acl << blockbits;
length = inode->i_sb->s_blocksize;
+ iomap_type = IOMAP_MAPPED;
+ } else {
+ /* no in-inode or external block for xattr, so return -ENOENT */
+ error = -ENOENT;
+ goto out;
}
- if (physical)
- error = fiemap_fill_next_extent(fieinfo, 0, physical,
- length, flags);
- return (error < 0 ? error : 0);
+ iomap->addr = physical;
+ iomap->offset = 0;
+ iomap->length = length;
+ iomap->type = iomap_type;
+ iomap->flags = 0;
+out:
+ return error;
}
-static int _ext4_fiemap(struct inode *inode,
- struct fiemap_extent_info *fieinfo,
- __u64 start, __u64 len,
- int (*fill)(struct inode *, ext4_lblk_t,
- ext4_lblk_t,
- struct fiemap_extent_info *))
+static int ext4_iomap_xattr_begin(struct inode *inode, loff_t offset,
+ loff_t length, unsigned flags,
+ struct iomap *iomap, struct iomap *srcmap)
{
- ext4_lblk_t start_blk;
- u32 ext4_fiemap_flags = FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR;
+ int error;
+ error = ext4_iomap_xattr_fiemap(inode, iomap);
+ if (error == 0 && (offset >= iomap->length))
+ error = -ENOENT;
+ return error;
+}
+
+static const struct iomap_ops ext4_iomap_xattr_ops = {
+ .iomap_begin = ext4_iomap_xattr_begin,
+};
+
+static int ext4_fiemap_check_ranges(struct inode *inode, u64 start, u64 *len)
+{
+ u64 maxbytes;
+
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+ maxbytes = inode->i_sb->s_maxbytes;
+ else
+ maxbytes = EXT4_SB(inode->i_sb)->s_bitmap_maxbytes;
+
+ if (*len == 0)
+ return -EINVAL;
+ if (start > maxbytes)
+ return -EFBIG;
+
+ /*
+ * Shrink request scope to what the fs can actually handle.
+ */
+ if (*len > maxbytes || (maxbytes - *len) < start)
+ *len = maxbytes - start;
+ return 0;
+}
+
+int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len)
+{
int error = 0;
- if (ext4_has_inline_data(inode)) {
- int has_inline = 1;
-
- error = ext4_inline_data_fiemap(inode, fieinfo, &has_inline,
- start, len);
-
- if (has_inline)
- return error;
- }
-
if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) {
error = ext4_ext_precache(inode);
if (error)
@@ -5141,48 +4938,31 @@
fieinfo->fi_flags &= ~FIEMAP_FLAG_CACHE;
}
- /* fallback to generic here if not in extents fmt */
- if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) &&
- fill == ext4_fill_fiemap_extents)
- return generic_block_fiemap(inode, fieinfo, start, len,
- ext4_get_block);
-
- if (fill == ext4_fill_es_cache_info)
- ext4_fiemap_flags &= FIEMAP_FLAG_XATTR;
- if (fiemap_check_flags(fieinfo, ext4_fiemap_flags))
- return -EBADR;
+ /*
+ * For bitmap files the maximum size limit could be smaller than
+ * s_maxbytes, so check len here manually instead of just relying on the
+ * generic check.
+ */
+ error = ext4_fiemap_check_ranges(inode, start, &len);
+ if (error)
+ return error;
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;
- last_blk = (start + len - 1) >> inode->i_sb->s_blocksize_bits;
- if (last_blk >= EXT_MAX_BLOCKS)
- last_blk = EXT_MAX_BLOCKS-1;
- len_blks = ((ext4_lblk_t) last_blk) - start_blk + 1;
-
- /*
- * Walk the extent tree gathering extent information
- * and pushing extents back to the user.
- */
- error = fill(inode, start_blk, len_blks, fieinfo);
+ fieinfo->fi_flags &= ~FIEMAP_FLAG_XATTR;
+ return iomap_fiemap(inode, fieinfo, start, len,
+ &ext4_iomap_xattr_ops);
}
- return error;
-}
-int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
- __u64 start, __u64 len)
-{
- return _ext4_fiemap(inode, fieinfo, start, len,
- ext4_fill_fiemap_extents);
+ return iomap_fiemap(inode, fieinfo, start, len, &ext4_iomap_report_ops);
}
int ext4_get_es_cache(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len)
{
+ ext4_lblk_t start_blk, len_blks;
+ __u64 last_blk;
+ int error = 0;
+
if (ext4_has_inline_data(inode)) {
int has_inline;
@@ -5193,42 +4973,32 @@
return 0;
}
- return _ext4_fiemap(inode, fieinfo, start, len,
- ext4_fill_es_cache_info);
-}
-
-
-/*
- * 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;
+ if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) {
+ error = ext4_ext_precache(inode);
+ if (error)
+ return error;
+ fieinfo->fi_flags &= ~FIEMAP_FLAG_CACHE;
}
- err = ext4_ext_get_access(handle, inode, path);
- return err;
+ error = fiemap_prep(inode, fieinfo, start, &len, 0);
+ if (error)
+ return error;
+
+ error = ext4_fiemap_check_ranges(inode, start, &len);
+ if (error)
+ return error;
+
+ start_blk = start >> inode->i_sb->s_blocksize_bits;
+ last_blk = (start + len - 1) >> inode->i_sb->s_blocksize_bits;
+ if (last_blk >= EXT_MAX_BLOCKS)
+ last_blk = EXT_MAX_BLOCKS-1;
+ len_blks = ((ext4_lblk_t) last_blk) - start_blk + 1;
+
+ /*
+ * Walk the extent tree gathering extent information
+ * and pushing extents back to the user.
+ */
+ return ext4_fill_es_cache_info(inode, start_blk, len_blks, fieinfo);
}
/*
@@ -5244,7 +5014,8 @@
{
int depth, err = 0;
struct ext4_extent *ex_start, *ex_last;
- bool update = 0;
+ bool update = false;
+ int credits, restart_credits;
depth = path->p_depth;
while (depth >= 0) {
@@ -5254,14 +5025,27 @@
return -EFSCORRUPTED;
ex_last = EXT_LAST_EXTENT(path[depth].p_hdr);
+ /* leaf + sb + inode */
+ credits = 3;
+ if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr)) {
+ update = true;
+ /* extent tree + sb + inode */
+ credits = depth + 2;
+ }
- err = ext4_access_path(handle, inode, path + depth);
+ restart_credits = ext4_writepage_trans_blocks(inode);
+ err = ext4_datasem_ensure_credits(handle, inode, credits,
+ restart_credits, 0);
+ if (err) {
+ if (err > 0)
+ err = -EAGAIN;
+ goto out;
+ }
+
+ err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
goto out;
- if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr))
- update = 1;
-
while (ex_start <= ex_last) {
if (SHIFT == SHIFT_LEFT) {
le32_add_cpu(&ex_start->ee_block,
@@ -5291,7 +5075,7 @@
}
/* Update index too */
- err = ext4_access_path(handle, inode, path + depth);
+ err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
goto out;
@@ -5330,6 +5114,7 @@
int ret = 0, depth;
struct ext4_extent *extent;
ext4_lblk_t stop, *iterator, ex_start, ex_end;
+ ext4_lblk_t tmp = EXT_MAX_BLOCKS;
/* Let path point to the last extent */
path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL,
@@ -5383,11 +5168,15 @@
* till we reach stop. In case of right shift, iterator points to stop
* and it is decreased till we reach start.
*/
+again:
if (SHIFT == SHIFT_LEFT)
iterator = &start;
else
iterator = &stop;
+ if (tmp != EXT_MAX_BLOCKS)
+ *iterator = tmp;
+
/*
* Its safe to start updating extents. Start and stop are unsigned, so
* in case of right shift if extent with 0 block is reached, iterator
@@ -5416,6 +5205,7 @@
}
}
+ tmp = *iterator;
if (SHIFT == SHIFT_LEFT) {
extent = EXT_LAST_EXTENT(path[depth].p_hdr);
*iterator = le32_to_cpu(extent->ee_block) +
@@ -5434,6 +5224,9 @@
}
ret = ext4_ext_shift_path_extents(path, shift, inode,
handle, SHIFT);
+ /* iterator can be NULL which means we should break */
+ if (ret == -EAGAIN)
+ goto again;
if (ret)
break;
}
@@ -5448,7 +5241,7 @@
* 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)
+static 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;
@@ -5465,12 +5258,8 @@
if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
return -EOPNOTSUPP;
- /* Collapse range works only on fs block size aligned offsets. */
- if (offset & (EXT4_CLUSTER_SIZE(sb) - 1) ||
- len & (EXT4_CLUSTER_SIZE(sb) - 1))
- return -EINVAL;
-
- if (!S_ISREG(inode->i_mode))
+ /* Collapse range works only on fs cluster size aligned regions. */
+ if (!IS_ALIGNED(offset | len, EXT4_CLUSTER_SIZE(sb)))
return -EINVAL;
trace_ext4_collapse_range(inode, offset, len);
@@ -5490,7 +5279,7 @@
* There is no need to overlap collapse range with EOF, in which case
* it is effectively a truncate operation
*/
- if (offset + len >= i_size_read(inode)) {
+ if (offset + len >= inode->i_size) {
ret = -EINVAL;
goto out_mutex;
}
@@ -5543,9 +5332,10 @@
ret = PTR_ERR(handle);
goto out_mmap;
}
+ ext4_fc_start_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE);
down_write(&EXT4_I(inode)->i_data_sem);
- ext4_discard_preallocations(inode);
+ ext4_discard_preallocations(inode, 0);
ret = ext4_es_remove_extent(inode, punch_start,
EXT_MAX_BLOCKS - punch_start);
@@ -5559,7 +5349,7 @@
up_write(&EXT4_I(inode)->i_data_sem);
goto out_stop;
}
- ext4_discard_preallocations(inode);
+ ext4_discard_preallocations(inode, 0);
ret = ext4_ext_shift_extents(inode, handle, punch_stop,
punch_stop - punch_start, SHIFT_LEFT);
@@ -5568,7 +5358,7 @@
goto out_stop;
}
- new_size = i_size_read(inode) - len;
+ new_size = inode->i_size - len;
i_size_write(inode, new_size);
EXT4_I(inode)->i_disksize = new_size;
@@ -5576,11 +5366,12 @@
if (IS_SYNC(inode))
ext4_handle_sync(handle);
inode->i_mtime = inode->i_ctime = current_time(inode);
- ext4_mark_inode_dirty(handle, inode);
+ ret = ext4_mark_inode_dirty(handle, inode);
ext4_update_inode_fsync_trans(handle, inode, 1);
out_stop:
ext4_journal_stop(handle);
+ ext4_fc_stop_ineligible(sb);
out_mmap:
up_write(&EXT4_I(inode)->i_mmap_sem);
out_mutex:
@@ -5596,7 +5387,7 @@
* by len bytes.
* Returns 0 on success, error otherwise.
*/
-int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
+static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
{
struct super_block *sb = inode->i_sb;
handle_t *handle;
@@ -5615,14 +5406,10 @@
if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
return -EOPNOTSUPP;
- /* Insert range works only on fs block size aligned offsets. */
- if (offset & (EXT4_CLUSTER_SIZE(sb) - 1) ||
- len & (EXT4_CLUSTER_SIZE(sb) - 1))
+ /* Insert range works only on fs cluster size aligned regions. */
+ if (!IS_ALIGNED(offset | len, EXT4_CLUSTER_SIZE(sb)))
return -EINVAL;
- if (!S_ISREG(inode->i_mode))
- return -EOPNOTSUPP;
-
trace_ext4_insert_range(inode, offset, len);
offset_lblk = offset >> EXT4_BLOCK_SIZE_BITS(sb);
@@ -5642,14 +5429,14 @@
goto out_mutex;
}
- /* Check for wrap through zero */
- if (inode->i_size + len > inode->i_sb->s_maxbytes) {
+ /* Check whether the maximum file size would be exceeded */
+ if (len > inode->i_sb->s_maxbytes - inode->i_size) {
ret = -EFBIG;
goto out_mutex;
}
- /* Offset should be less than i_size */
- if (offset >= i_size_read(inode)) {
+ /* Offset must be less than i_size */
+ if (offset >= inode->i_size) {
ret = -EINVAL;
goto out_mutex;
}
@@ -5685,6 +5472,7 @@
ret = PTR_ERR(handle);
goto out_mmap;
}
+ ext4_fc_start_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE);
/* Expand file to avoid data loss if there is error while shifting */
inode->i_size += len;
@@ -5695,7 +5483,7 @@
goto out_stop;
down_write(&EXT4_I(inode)->i_data_sem);
- ext4_discard_preallocations(inode);
+ ext4_discard_preallocations(inode, 0);
path = ext4_find_extent(inode, offset_lblk, NULL, 0);
if (IS_ERR(path)) {
@@ -5759,6 +5547,7 @@
out_stop:
ext4_journal_stop(handle);
+ ext4_fc_stop_ineligible(sb);
out_mmap:
up_write(&EXT4_I(inode)->i_mmap_sem);
out_mutex:
@@ -5829,7 +5618,7 @@
}
ex1 = path1[path1->p_depth].p_ext;
ex2 = path2[path2->p_depth].p_ext;
- /* Do we have somthing to swap ? */
+ /* Do we have something to swap ? */
if (unlikely(!ex2 || !ex1))
goto finish;
@@ -6040,3 +5829,277 @@
return err ? err : mapped;
}
+
+/*
+ * Updates physical block address and unwritten status of extent
+ * starting at lblk start and of len. If such an extent doesn't exist,
+ * this function splits the extent tree appropriately to create an
+ * extent like this. This function is called in the fast commit
+ * replay path. Returns 0 on success and error on failure.
+ */
+int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start,
+ int len, int unwritten, ext4_fsblk_t pblk)
+{
+ struct ext4_ext_path *path = NULL, *ppath;
+ struct ext4_extent *ex;
+ int ret;
+
+ path = ext4_find_extent(inode, start, NULL, 0);
+ if (IS_ERR(path))
+ return PTR_ERR(path);
+ ex = path[path->p_depth].p_ext;
+ if (!ex) {
+ ret = -EFSCORRUPTED;
+ goto out;
+ }
+
+ if (le32_to_cpu(ex->ee_block) != start ||
+ ext4_ext_get_actual_len(ex) != len) {
+ /* We need to split this extent to match our extent first */
+ ppath = path;
+ down_write(&EXT4_I(inode)->i_data_sem);
+ ret = ext4_force_split_extent_at(NULL, inode, &ppath, start, 1);
+ up_write(&EXT4_I(inode)->i_data_sem);
+ if (ret)
+ goto out;
+ kfree(path);
+ path = ext4_find_extent(inode, start, NULL, 0);
+ if (IS_ERR(path))
+ return -1;
+ ppath = path;
+ ex = path[path->p_depth].p_ext;
+ WARN_ON(le32_to_cpu(ex->ee_block) != start);
+ if (ext4_ext_get_actual_len(ex) != len) {
+ down_write(&EXT4_I(inode)->i_data_sem);
+ ret = ext4_force_split_extent_at(NULL, inode, &ppath,
+ start + len, 1);
+ up_write(&EXT4_I(inode)->i_data_sem);
+ if (ret)
+ goto out;
+ kfree(path);
+ path = ext4_find_extent(inode, start, NULL, 0);
+ if (IS_ERR(path))
+ return -EINVAL;
+ ex = path[path->p_depth].p_ext;
+ }
+ }
+ if (unwritten)
+ ext4_ext_mark_unwritten(ex);
+ else
+ ext4_ext_mark_initialized(ex);
+ ext4_ext_store_pblock(ex, pblk);
+ down_write(&EXT4_I(inode)->i_data_sem);
+ ret = ext4_ext_dirty(NULL, inode, &path[path->p_depth]);
+ up_write(&EXT4_I(inode)->i_data_sem);
+out:
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ ext4_mark_inode_dirty(NULL, inode);
+ return ret;
+}
+
+/* Try to shrink the extent tree */
+void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end)
+{
+ struct ext4_ext_path *path = NULL;
+ struct ext4_extent *ex;
+ ext4_lblk_t old_cur, cur = 0;
+
+ while (cur < end) {
+ path = ext4_find_extent(inode, cur, NULL, 0);
+ if (IS_ERR(path))
+ return;
+ ex = path[path->p_depth].p_ext;
+ if (!ex) {
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ ext4_mark_inode_dirty(NULL, inode);
+ return;
+ }
+ old_cur = cur;
+ cur = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex);
+ if (cur <= old_cur)
+ cur = old_cur + 1;
+ ext4_ext_try_to_merge(NULL, inode, path, ex);
+ down_write(&EXT4_I(inode)->i_data_sem);
+ ext4_ext_dirty(NULL, inode, &path[path->p_depth]);
+ up_write(&EXT4_I(inode)->i_data_sem);
+ ext4_mark_inode_dirty(NULL, inode);
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ }
+}
+
+/* Check if *cur is a hole and if it is, skip it */
+static int skip_hole(struct inode *inode, ext4_lblk_t *cur)
+{
+ int ret;
+ struct ext4_map_blocks map;
+
+ map.m_lblk = *cur;
+ map.m_len = ((inode->i_size) >> inode->i_sb->s_blocksize_bits) - *cur;
+
+ ret = ext4_map_blocks(NULL, inode, &map, 0);
+ if (ret < 0)
+ return ret;
+ if (ret != 0)
+ return 0;
+ *cur = *cur + map.m_len;
+ return 0;
+}
+
+/* Count number of blocks used by this inode and update i_blocks */
+int ext4_ext_replay_set_iblocks(struct inode *inode)
+{
+ struct ext4_ext_path *path = NULL, *path2 = NULL;
+ struct ext4_extent *ex;
+ ext4_lblk_t cur = 0, end;
+ int numblks = 0, i, ret = 0;
+ ext4_fsblk_t cmp1, cmp2;
+ struct ext4_map_blocks map;
+
+ /* Determin the size of the file first */
+ path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL,
+ EXT4_EX_NOCACHE);
+ if (IS_ERR(path))
+ return PTR_ERR(path);
+ ex = path[path->p_depth].p_ext;
+ if (!ex) {
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ goto out;
+ }
+ end = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex);
+ ext4_ext_drop_refs(path);
+ kfree(path);
+
+ /* Count the number of data blocks */
+ cur = 0;
+ while (cur < end) {
+ map.m_lblk = cur;
+ map.m_len = end - cur;
+ ret = ext4_map_blocks(NULL, inode, &map, 0);
+ if (ret < 0)
+ break;
+ if (ret > 0)
+ numblks += ret;
+ cur = cur + map.m_len;
+ }
+
+ /*
+ * Count the number of extent tree blocks. We do it by looking up
+ * two successive extents and determining the difference between
+ * their paths. When path is different for 2 successive extents
+ * we compare the blocks in the path at each level and increment
+ * iblocks by total number of differences found.
+ */
+ cur = 0;
+ ret = skip_hole(inode, &cur);
+ if (ret < 0)
+ goto out;
+ path = ext4_find_extent(inode, cur, NULL, 0);
+ if (IS_ERR(path))
+ goto out;
+ numblks += path->p_depth;
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ while (cur < end) {
+ path = ext4_find_extent(inode, cur, NULL, 0);
+ if (IS_ERR(path))
+ break;
+ ex = path[path->p_depth].p_ext;
+ if (!ex) {
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ return 0;
+ }
+ cur = max(cur + 1, le32_to_cpu(ex->ee_block) +
+ ext4_ext_get_actual_len(ex));
+ ret = skip_hole(inode, &cur);
+ if (ret < 0) {
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ break;
+ }
+ path2 = ext4_find_extent(inode, cur, NULL, 0);
+ if (IS_ERR(path2)) {
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ break;
+ }
+ ex = path2[path2->p_depth].p_ext;
+ for (i = 0; i <= max(path->p_depth, path2->p_depth); i++) {
+ cmp1 = cmp2 = 0;
+ if (i <= path->p_depth)
+ cmp1 = path[i].p_bh ?
+ path[i].p_bh->b_blocknr : 0;
+ if (i <= path2->p_depth)
+ cmp2 = path2[i].p_bh ?
+ path2[i].p_bh->b_blocknr : 0;
+ if (cmp1 != cmp2 && cmp2 != 0)
+ numblks++;
+ }
+ ext4_ext_drop_refs(path);
+ ext4_ext_drop_refs(path2);
+ kfree(path);
+ kfree(path2);
+ }
+
+out:
+ inode->i_blocks = numblks << (inode->i_sb->s_blocksize_bits - 9);
+ ext4_mark_inode_dirty(NULL, inode);
+ return 0;
+}
+
+int ext4_ext_clear_bb(struct inode *inode)
+{
+ struct ext4_ext_path *path = NULL;
+ struct ext4_extent *ex;
+ ext4_lblk_t cur = 0, end;
+ int j, ret = 0;
+ struct ext4_map_blocks map;
+
+ /* Determin the size of the file first */
+ path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL,
+ EXT4_EX_NOCACHE);
+ if (IS_ERR(path))
+ return PTR_ERR(path);
+ ex = path[path->p_depth].p_ext;
+ if (!ex) {
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ return 0;
+ }
+ end = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex);
+ ext4_ext_drop_refs(path);
+ kfree(path);
+
+ cur = 0;
+ while (cur < end) {
+ map.m_lblk = cur;
+ map.m_len = end - cur;
+ ret = ext4_map_blocks(NULL, inode, &map, 0);
+ if (ret < 0)
+ break;
+ if (ret > 0) {
+ path = ext4_find_extent(inode, map.m_lblk, NULL, 0);
+ if (!IS_ERR_OR_NULL(path)) {
+ for (j = 0; j < path->p_depth; j++) {
+
+ ext4_mb_mark_bb(inode->i_sb,
+ path[j].p_block, 1, 0);
+ ext4_fc_record_regions(inode->i_sb, inode->i_ino,
+ 0, path[j].p_block, 1, 1);
+ }
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ }
+ ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0);
+ ext4_fc_record_regions(inode->i_sb, inode->i_ino,
+ map.m_lblk, map.m_pblk, map.m_len, 1);
+ }
+ cur = cur + map.m_len;
+ }
+
+ return 0;
+}