Skip to content

Instantly share code, notes, and snippets.

@invisiblek

invisiblek/-

Created January 20, 2015 17:28
Show Gist options
  • Save invisiblek/b8d66a41861bfd257169 to your computer and use it in GitHub Desktop.
Save invisiblek/b8d66a41861bfd257169 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
-
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index cb0783f7..d33733e 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -591,7 +591,8 @@ ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb)
if (bitmap_bh == NULL)
continue;
- x = ext4_count_free(bitmap_bh, sb->s_blocksize);
+ x = ext4_count_free(bitmap_bh->b_data,
+ EXT4_BLOCKS_PER_GROUP(sb) / 8);
printk(KERN_DEBUG "group %u: stored = %d, counted = %u\n",
i, ext4_free_group_clusters(sb, gdp), x);
bitmap_count += x;
@@ -599,7 +600,7 @@ ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb)
brelse(bitmap_bh);
printk(KERN_DEBUG "ext4_count_free_clusters: stored = %llu"
", computed = %llu, %llu\n",
- EXT4_B2C(EXT4_SB(sb), ext4_free_blocks_count(es)),
+ EXT4_NUM_B2C(EXT4_SB(sb), ext4_free_blocks_count(es)),
desc_count, bitmap_count);
return bitmap_count;
#else
diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c
index 1e9f47a..bbde5d5 100644
--- a/fs/ext4/bitmap.c
+++ b/fs/ext4/bitmap.c
@@ -13,15 +13,13 @@
static const int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0};
-unsigned int ext4_count_free(struct buffer_head *map, unsigned int numchars)
+unsigned int ext4_count_free(char *bitmap, unsigned int numchars)
{
unsigned int i, sum = 0;
- if (!map)
- return 0;
for (i = 0; i < numchars; i++)
- sum += nibblemap[map->b_data[i] & 0xf] +
- nibblemap[(map->b_data[i] >> 4) & 0xf];
+ sum += nibblemap[bitmap[i] & 0xf] +
+ nibblemap[(bitmap[i] >> 4) & 0xf];
return sum;
}
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 2f8b318..521ba9d 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -316,9 +316,9 @@ struct ext4_group_desc
*/
struct flex_groups {
- atomic_t free_inodes;
- atomic_t free_clusters;
- atomic_t used_dirs;
+ atomic64_t free_clusters;
+ atomic_t free_inodes;
+ atomic_t used_dirs;
};
#define EXT4_BG_INODE_UNINIT 0x0001 /* Inode table/bitmap not in use */
@@ -1784,7 +1784,7 @@ struct mmpd_data {
# define NORET_AND noreturn,
/* bitmap.c */
-extern unsigned int ext4_count_free(struct buffer_head *, unsigned);
+extern unsigned int ext4_count_free(char *bitmap, unsigned numchars);
/* balloc.c */
extern unsigned int ext4_block_group(struct super_block *sb,
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 3c382b5..d0b8f98 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -113,15 +113,6 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
if (WARN_ON_ONCE(err)) {
ext4_journal_abort_handle(where, line, __func__, bh,
handle, err);
- ext4_error_inode(inode, where, line,
- bh->b_blocknr,
- "journal_dirty_metadata failed: "
- "handle type %u started at line %u, "
- "credits %u/%u, errcode %d",
- handle->h_type,
- handle->h_line_no,
- handle->h_requested_credits,
- handle->h_buffer_credits, err);
}
} else {
if (inode)
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 54f9a98..4296a6f 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -52,6 +52,9 @@
#define EXT4_EXT_MARK_UNINIT1 0x2 /* mark first half uninitialized */
#define EXT4_EXT_MARK_UNINIT2 0x4 /* mark second half uninitialized */
+#define EXT4_EXT_DATA_VALID1 0x8 /* first half contains valid data */
+#define EXT4_EXT_DATA_VALID2 0x10 /* second half contains valid data */
+
static int ext4_split_extent(handle_t *handle,
struct inode *inode,
struct ext4_ext_path *path,
@@ -2108,7 +2111,7 @@ static int
ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block,
struct ext4_extent *ex)
{
- struct ext4_ext_cache cex = {0, 0, 0};
+ struct ext4_ext_cache cex;
int ret = 0;
if (ext4_ext_check_cache(inode, block, &cex)) {
@@ -2127,13 +2130,14 @@ ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block,
* removes index from the index block.
*/
static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
- struct ext4_ext_path *path)
+ struct ext4_ext_path *path, int depth)
{
int err;
ext4_fsblk_t leaf;
/* free index block */
- path--;
+ depth--;
+ path = path + depth;
leaf = ext4_idx_pblock(path->p_idx);
if (unlikely(path->p_hdr->eh_entries == 0)) {
EXT4_ERROR_INODE(inode, "path->p_hdr->eh_entries == 0");
@@ -2158,6 +2162,19 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
ext4_free_blocks(handle, inode, NULL, leaf, 1,
EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
+
+ while (--depth >= 0) {
+ if (path->p_idx != EXT_FIRST_INDEX(path->p_hdr))
+ break;
+ path--;
+ err = ext4_ext_get_access(handle, inode, path);
+ if (err)
+ break;
+ path->p_idx->ei_block = (path+1)->p_idx->ei_block;
+ err = ext4_ext_dirty(handle, inode, path);
+ if (err)
+ break;
+ }
return err;
}
@@ -2491,7 +2508,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
/* if this leaf is free, then we should
* remove it from index block above */
if (err == 0 && eh->eh_entries == 0 && path[depth].p_bh != NULL)
- err = ext4_ext_rm_idx(handle, inode, path + depth);
+ err = ext4_ext_rm_idx(handle, inode, path, depth);
out:
return err;
@@ -2523,10 +2540,10 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
{
struct super_block *sb = inode->i_sb;
int depth = ext_depth(inode);
- struct ext4_ext_path *path;
+ struct ext4_ext_path *path = NULL;
ext4_fsblk_t partial_cluster = 0;
handle_t *handle;
- int i, err;
+ int i = 0, err;
ext_debug("truncate since %u to %u\n", start, end);
@@ -2559,8 +2576,12 @@ again:
}
depth = ext_depth(inode);
ex = path[depth].p_ext;
- if (!ex)
+ if (!ex) {
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ path = NULL;
goto cont;
+ }
ee_block = le32_to_cpu(ex->ee_block);
@@ -2590,8 +2611,6 @@ again:
if (err < 0)
goto out;
}
- ext4_ext_drop_refs(path);
- kfree(path);
}
cont:
@@ -2600,19 +2619,28 @@ cont:
* 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 (path) {
+ int k = i = depth;
+ while (--k > 0)
+ path[k].p_block =
+ le16_to_cpu(path[k].p_hdr->eh_entries)+1;
+ } else {
+ 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);
+ i = 0;
- if (ext4_ext_check(inode, path[0].p_hdr, depth)) {
- err = -EIO;
- goto out;
+ if (ext4_ext_check(inode, path[0].p_hdr, depth)) {
+ err = -EIO;
+ goto out;
+ }
}
- i = err = 0;
+ err = 0;
while (i >= 0 && err == 0) {
if (i == depth) {
@@ -2681,7 +2709,7 @@ cont:
/* index is empty, remove it;
* handle must be already prepared by the
* truncatei_leaf() */
- err = ext4_ext_rm_idx(handle, inode, path + i);
+ err = ext4_ext_rm_idx(handle, inode, path, i);
}
/* root level has p_bh == NULL, brelse() eats this */
brelse(path[i].p_bh);
@@ -2726,8 +2754,10 @@ cont:
out:
ext4_ext_drop_refs(path);
kfree(path);
- if (err == -EAGAIN)
+ if (err == -EAGAIN) {
+ path = NULL;
goto again;
+ }
ext4_journal_stop(handle);
return err;
@@ -2836,6 +2866,9 @@ static int ext4_split_extent_at(handle_t *handle,
unsigned int ee_len, depth;
int err = 0;
+ 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);
@@ -2894,7 +2927,14 @@ static int ext4_split_extent_at(handle_t *handle,
err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
- err = ext4_ext_zeroout(inode, &orig_ex);
+ if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) {
+ if (split_flag & EXT4_EXT_DATA_VALID1)
+ err = ext4_ext_zeroout(inode, ex2);
+ else
+ err = ext4_ext_zeroout(inode, ex);
+ } else
+ err = ext4_ext_zeroout(inode, &orig_ex);
+
if (err)
goto fix_extent_len;
/* update the extent length and mark as initialized */
@@ -2939,6 +2979,7 @@ static int ext4_split_extent(handle_t *handle,
int err = 0;
int uninitialized;
int split_flag1, flags1;
+ int allocated = map->m_len;
depth = ext_depth(inode);
ex = path[depth].p_ext;
@@ -2947,16 +2988,19 @@ static int ext4_split_extent(handle_t *handle,
uninitialized = ext4_ext_is_uninitialized(ex);
if (map->m_lblk + map->m_len < ee_block + ee_len) {
- split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT ?
- EXT4_EXT_MAY_ZEROOUT : 0;
+ split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT;
flags1 = flags | EXT4_GET_BLOCKS_PRE_IO;
if (uninitialized)
split_flag1 |= EXT4_EXT_MARK_UNINIT1 |
EXT4_EXT_MARK_UNINIT2;
+ if (split_flag & EXT4_EXT_DATA_VALID2)
+ split_flag1 |= EXT4_EXT_DATA_VALID1;
err = ext4_split_extent_at(handle, inode, path,
map->m_lblk + map->m_len, split_flag1, flags1);
if (err)
goto out;
+ } else {
+ allocated = ee_len - (map->m_lblk - ee_block);
}
ext4_ext_drop_refs(path);
@@ -2965,8 +3009,8 @@ static int ext4_split_extent(handle_t *handle,
return PTR_ERR(path);
if (map->m_lblk >= ee_block) {
- split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT ?
- EXT4_EXT_MAY_ZEROOUT : 0;
+ split_flag1 = split_flag & (EXT4_EXT_MAY_ZEROOUT |
+ EXT4_EXT_DATA_VALID2);
if (uninitialized)
split_flag1 |= EXT4_EXT_MARK_UNINIT1;
if (split_flag & EXT4_EXT_MARK_UNINIT2)
@@ -2979,7 +3023,7 @@ static int ext4_split_extent(handle_t *handle,
ext4_ext_show_leaf(inode, path);
out:
- return err ? err : map->m_len;
+ return err ? err : allocated;
}
#define EXT4_EXT_ZERO_LEN 7
@@ -3244,26 +3288,47 @@ static int ext4_split_unwritten_extents(handle_t *handle,
split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0;
split_flag |= EXT4_EXT_MARK_UNINIT2;
-
+ if (flags & EXT4_GET_BLOCKS_CONVERT)
+ split_flag |= EXT4_EXT_DATA_VALID2;
flags |= EXT4_GET_BLOCKS_PRE_IO;
return ext4_split_extent(handle, inode, path, map, split_flag, flags);
}
static int ext4_convert_unwritten_extents_endio(handle_t *handle,
- struct inode *inode,
- struct ext4_ext_path *path)
+ struct inode *inode,
+ struct ext4_map_blocks *map,
+ struct ext4_ext_path *path)
{
struct ext4_extent *ex;
+ ext4_lblk_t ee_block;
+ unsigned int ee_len;
int depth;
int err = 0;
depth = ext_depth(inode);
ex = path[depth].p_ext;
+ ee_block = le32_to_cpu(ex->ee_block);
+ ee_len = ext4_ext_get_actual_len(ex);
ext_debug("ext4_convert_unwritten_extents_endio: inode %lu, logical"
"block %llu, max_blocks %u\n", inode->i_ino,
- (unsigned long long)le32_to_cpu(ex->ee_block),
- ext4_ext_get_actual_len(ex));
+ (unsigned long long)ee_block, ee_len);
+
+ /* If extent is larger than requested then split is required */
+ if (ee_block != map->m_lblk || ee_len > map->m_len) {
+ err = ext4_split_unwritten_extents(handle, inode, map, path,
+ EXT4_GET_BLOCKS_CONVERT);
+ if (err < 0)
+ goto out;
+ ext4_ext_drop_refs(path);
+ path = ext4_ext_find_extent(inode, map->m_lblk, path);
+ if (IS_ERR(path)) {
+ err = PTR_ERR(path);
+ goto out;
+ }
+ depth = ext_depth(inode);
+ ex = path[depth].p_ext;
+ }
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
@@ -3571,7 +3636,7 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *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,
+ ret = ext4_convert_unwritten_extents_endio(handle, inode, map,
path);
if (ret >= 0) {
ext4_update_inode_fsync_trans(handle, inode, 1);
@@ -3626,6 +3691,7 @@ out:
allocated - map->m_len);
allocated = map->m_len;
}
+ map->m_len = allocated;
/*
* If we have done fallocate with the offset that is already
@@ -4667,7 +4733,7 @@ static int ext4_xattr_fiemap(struct inode *inode,
error = ext4_get_inode_loc(inode, &iloc);
if (error)
return error;
- physical = iloc.bh->b_blocknr << blockbits;
+ physical = (__u64)iloc.bh->b_blocknr << blockbits;
offset = EXT4_GOOD_OLD_INODE_SIZE +
EXT4_I(inode)->i_extra_isize;
physical += offset;
@@ -4675,7 +4741,7 @@ static int ext4_xattr_fiemap(struct inode *inode,
flags |= FIEMAP_EXTENT_DATA_INLINE;
brelse(iloc.bh);
} else { /* external block */
- physical = EXT4_I(inode)->i_file_acl << blockbits;
+ physical = (__u64)EXT4_I(inode)->i_file_acl << blockbits;
length = inode->i_sb->s_blocksize;
}
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index f155f42..75c4f36 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -305,8 +305,8 @@ error_return:
}
struct orlov_stats {
+ __u64 free_clusters;
__u32 free_inodes;
- __u32 free_clusters;
__u32 used_dirs;
};
@@ -323,7 +323,7 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g,
if (flex_size > 1) {
stats->free_inodes = atomic_read(&flex_group[g].free_inodes);
- stats->free_clusters = atomic_read(&flex_group[g].free_clusters);
+ stats->free_clusters = atomic64_read(&flex_group[g].free_clusters);
stats->used_dirs = atomic_read(&flex_group[g].used_dirs);
return;
}
@@ -488,10 +488,12 @@ fallback_retry:
for (i = 0; i < ngroups; i++) {
grp = (parent_group + i) % ngroups;
desc = ext4_get_group_desc(sb, grp, NULL);
- grp_free = ext4_free_inodes_count(sb, desc);
- if (desc && grp_free && grp_free >= avefreei) {
- *group = grp;
- return 0;
+ if (desc) {
+ grp_free = ext4_free_inodes_count(sb, desc);
+ if (grp_free && grp_free >= avefreei) {
+ *group = grp;
+ return 0;
+ }
}
}
@@ -685,11 +687,8 @@ repeat_in_this_group:
ino = ext4_find_next_zero_bit((unsigned long *)
inode_bitmap_bh->b_data,
EXT4_INODES_PER_GROUP(sb), ino);
- if (ino >= EXT4_INODES_PER_GROUP(sb)) {
- if (++group == ngroups)
- group = 0;
- continue;
- }
+ if (ino >= EXT4_INODES_PER_GROUP(sb))
+ goto next_group;
if (group == 0 && (ino+1) < EXT4_FIRST_INO(sb)) {
ext4_error(sb, "reserved inode found cleared - "
"inode=%lu", ino + 1);
@@ -707,6 +706,9 @@ repeat_in_this_group:
goto got; /* we grabbed the inode! */
if (ino < EXT4_INODES_PER_GROUP(sb))
goto repeat_in_this_group;
+next_group:
+ if (++group == ngroups)
+ group = 0;
}
err = -ENOSPC;
goto out;
@@ -732,7 +734,6 @@ got:
BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap");
err = ext4_handle_dirty_metadata(handle, NULL, block_bitmap_bh);
- brelse(block_bitmap_bh);
/* recheck and clear flag under lock if we still need to */
ext4_lock_group(sb, group);
@@ -744,6 +745,7 @@ got:
gdp);
}
ext4_unlock_group(sb, group);
+ brelse(block_bitmap_bh);
if (err)
goto fail;
@@ -1012,7 +1014,8 @@ unsigned long ext4_count_free_inodes(struct super_block *sb)
if (!bitmap_bh)
continue;
- x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8);
+ x = ext4_count_free(bitmap_bh->b_data,
+ EXT4_INODES_PER_GROUP(sb) / 8);
printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n",
(unsigned long) i, ext4_free_inodes_count(sb, gdp), x);
bitmap_count += x;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 756fab6..5b6dcba 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -145,7 +145,8 @@ void ext4_evict_inode(struct inode *inode)
* don't use page cache.
*/
if (ext4_should_journal_data(inode) &&
- (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) {
+ (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) &&
+ inode->i_ino != EXT4_JOURNAL_INO) {
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
@@ -279,6 +280,15 @@ void ext4_da_update_reserve_space(struct inode *inode,
used = ei->i_reserved_data_blocks;
}
+ if (unlikely(ei->i_allocated_meta_blocks > ei->i_reserved_meta_blocks)) {
+ ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, allocated %d "
+ "with only %d reserved metadata blocks\n", __func__,
+ inode->i_ino, ei->i_allocated_meta_blocks,
+ ei->i_reserved_meta_blocks);
+ WARN_ON(1);
+ ei->i_allocated_meta_blocks = ei->i_reserved_meta_blocks;
+ }
+
/* Update per-inode reservations */
ei->i_reserved_data_blocks -= used;
ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks;
@@ -1104,6 +1114,17 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int md_needed;
int ret;
+ ext4_lblk_t save_last_lblock;
+ int save_len;
+
+ /*
+ * We will charge metadata quota at writeout time; this saves
+ * us from metadata over-estimation, though we may go over by
+ * a small amount in the end. Here we just reserve for data.
+ */
+ ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1));
+ if (ret)
+ return ret;
/*
* recalculate the amount of metadata blocks to reserve
@@ -1112,32 +1133,31 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
*/
repeat:
spin_lock(&ei->i_block_reservation_lock);
+ /*
+ * ext4_calc_metadata_amount() has side effects, which we have
+ * to be prepared undo if we fail to claim space.
+ */
+ save_len = ei->i_da_metadata_calc_len;
+ save_last_lblock = ei->i_da_metadata_calc_last_lblock;
md_needed = EXT4_NUM_B2C(sbi,
ext4_calc_metadata_amount(inode, lblock));
trace_ext4_da_reserve_space(inode, md_needed);
- spin_unlock(&ei->i_block_reservation_lock);
/*
- * We will charge metadata quota at writeout time; this saves
- * us from metadata over-estimation, though we may go over by
- * a small amount in the end. Here we just reserve for data.
- */
- ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1));
- if (ret)
- return ret;
- /*
* We do still charge estimated metadata to the sb though;
* we cannot afford to run out of free blocks.
*/
if (ext4_claim_free_clusters(sbi, md_needed + 1, 0)) {
- dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
+ ei->i_da_metadata_calc_len = save_len;
+ ei->i_da_metadata_calc_last_lblock = save_last_lblock;
+ spin_unlock(&ei->i_block_reservation_lock);
if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
yield();
goto repeat;
}
+ dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
return -ENOSPC;
}
- spin_lock(&ei->i_block_reservation_lock);
ei->i_reserved_data_blocks++;
ei->i_reserved_meta_blocks += md_needed;
spin_unlock(&ei->i_block_reservation_lock);
@@ -1405,6 +1425,8 @@ static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd)
index = mpd->first_page;
end = mpd->next_page - 1;
+
+ pagevec_init(&pvec, 0);
while (index <= end) {
nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
if (nr_pages == 0)
@@ -2367,6 +2389,16 @@ static int ext4_nonda_switch(struct super_block *sb)
free_blocks = EXT4_C2B(sbi,
percpu_counter_read_positive(&sbi->s_freeclusters_counter));
dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyclusters_counter);
+ /*
+ * Start pushing delalloc when 1/2 of free blocks are dirty.
+ */
+ if (dirty_blocks && (free_blocks < 2 * dirty_blocks) &&
+ !writeback_in_progress(sb->s_bdi) &&
+ down_read_trylock(&sb->s_umount)) {
+ writeback_inodes_sb(sb, WB_REASON_FS_FREE_SPACE);
+ up_read(&sb->s_umount);
+ }
+
if (2 * free_blocks < 3 * dirty_blocks ||
free_blocks < (dirty_blocks + EXT4_FREECLUSTERS_WATERMARK)) {
/*
@@ -2375,13 +2407,6 @@ static int ext4_nonda_switch(struct super_block *sb)
*/
return 1;
}
- /*
- * Even if we don't switch but are nearing capacity,
- * start pushing delalloc when 1/2 of free blocks are dirty.
- */
- if (free_blocks < 2 * dirty_blocks)
- writeback_inodes_sb_if_idle(sb, WB_REASON_FS_FREE_SPACE);
-
return 0;
}
@@ -3869,6 +3894,7 @@ static int ext4_do_update_inode(handle_t *handle,
struct ext4_inode_info *ei = EXT4_I(inode);
struct buffer_head *bh = iloc->bh;
int err = 0, rc, block;
+ int need_datasync = 0;
/* For fields not not tracking in the in-memory inode,
* initialise them to zero for new inodes. */
@@ -3917,7 +3943,10 @@ static int ext4_do_update_inode(handle_t *handle,
raw_inode->i_file_acl_high =
cpu_to_le16(ei->i_file_acl >> 32);
raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl);
- ext4_isize_set(raw_inode, ei->i_disksize);
+ if (ei->i_disksize != ext4_isize(raw_inode)) {
+ ext4_isize_set(raw_inode, ei->i_disksize);
+ need_datasync = 1;
+ }
if (ei->i_disksize > 0x7fffffffULL) {
struct super_block *sb = inode->i_sb;
if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
@@ -3968,7 +3997,7 @@ static int ext4_do_update_inode(handle_t *handle,
err = rc;
ext4_clear_inode_state(inode, EXT4_STATE_NEW);
- ext4_update_inode_fsync_trans(handle, inode, 0);
+ ext4_update_inode_fsync_trans(handle, inode, need_datasync);
out_brelse:
brelse(bh);
ext4_std_error(inode->i_sb, err);
@@ -4191,7 +4220,7 @@ int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat)
{
struct inode *inode;
- unsigned long delalloc_blocks;
+ unsigned long long delalloc_blocks;
inode = dentry->d_inode;
generic_fillattr(inode, stat);
@@ -4208,7 +4237,7 @@ int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
*/
delalloc_blocks = EXT4_I(inode)->i_reserved_data_blocks;
- stat->blocks += (delalloc_blocks << inode->i_sb->s_blocksize_bits)>>9;
+ stat->blocks += delalloc_blocks << (inode->i_sb->s_blocksize_bits-9);
return 0;
}
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 6eee255..9727522 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -38,7 +38,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
handle_t *handle = NULL;
int err, migrate = 0;
struct ext4_iloc iloc;
- unsigned int oldflags;
+ unsigned int oldflags, mask, i;
unsigned int jflag;
if (!inode_owner_or_capable(inode))
@@ -115,9 +115,14 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
if (err)
goto flags_err;
- flags = flags & EXT4_FL_USER_MODIFIABLE;
- flags |= oldflags & ~EXT4_FL_USER_MODIFIABLE;
- ei->i_flags = flags;
+ for (i = 0, mask = 1; i < 32; i++, mask <<= 1) {
+ if (!(mask & EXT4_FL_USER_MODIFIABLE))
+ continue;
+ if (mask & flags)
+ ext4_set_inode_flag(inode, i);
+ else
+ ext4_clear_inode_flag(inode, i);
+ }
ext4_set_inode_flags(inode);
inode->i_ctime = ext4_current_time(inode);
@@ -256,7 +261,6 @@ group_extend_out:
err = ext4_move_extents(filp, donor_filp, me.orig_start,
me.donor_start, me.len, &me.moved_len);
mnt_drop_write_file(filp);
- mnt_drop_write(filp->f_path.mnt);
if (copy_to_user((struct move_extent __user *)arg,
&me, sizeof(me)))
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 5e60c3b..cdfc763 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1980,7 +1980,11 @@ repeat:
group = ac->ac_g_ex.fe_group;
for (i = 0; i < ngroups; group++, i++) {
- if (group == ngroups)
+ /*
+ * Artificially restricted ngroups for non-extent
+ * files makes group > ngroups possible on first loop.
+ */
+ if (group >= ngroups)
group = 0;
/* This now checks without needing the buddy page */
@@ -2517,6 +2521,9 @@ int ext4_mb_release(struct super_block *sb)
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits);
+ if (sbi->s_proc)
+ remove_proc_entry("mb_groups", sbi->s_proc);
+
if (sbi->s_group_info) {
for (i = 0; i < ngroups; i++) {
grinfo = ext4_get_group_info(sb, i);
@@ -2564,8 +2571,6 @@ int ext4_mb_release(struct super_block *sb)
}
free_percpu(sbi->s_locality_groups);
- if (sbi->s_proc)
- remove_proc_entry("mb_groups", sbi->s_proc);
return 0;
}
@@ -2812,8 +2817,8 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi,
ac->ac_b_ex.fe_group);
- atomic_sub(ac->ac_b_ex.fe_len,
- &sbi->s_flex_groups[flex_group].free_clusters);
+ atomic64_sub(ac->ac_b_ex.fe_len,
+ &sbi->s_flex_groups[flex_group].free_clusters);
}
err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
@@ -3437,7 +3442,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
win = offs;
ac->ac_b_ex.fe_logical = ac->ac_o_ex.fe_logical -
- EXT4_B2C(sbi, win);
+ EXT4_NUM_B2C(sbi, win);
BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical);
BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len);
}
@@ -4130,7 +4135,7 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac)
/* The max size of hash table is PREALLOC_TB_SIZE */
order = PREALLOC_TB_SIZE - 1;
/* Add the prealloc space to lg */
- rcu_read_lock();
+ spin_lock(&lg->lg_prealloc_lock);
list_for_each_entry_rcu(tmp_pa, &lg->lg_prealloc_list[order],
pa_inode_list) {
spin_lock(&tmp_pa->pa_lock);
@@ -4154,12 +4159,12 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac)
if (!added)
list_add_tail_rcu(&pa->pa_inode_list,
&lg->lg_prealloc_list[order]);
- rcu_read_unlock();
+ spin_unlock(&lg->lg_prealloc_lock);
/* Now trim the list to be not more than 8 elements */
if (lg_prealloc_count > 8) {
ext4_mb_discard_lg_preallocations(sb, lg,
- order, lg_prealloc_count);
+ order, lg_prealloc_count);
return;
}
return ;
@@ -4581,7 +4586,7 @@ do_more:
EXT4_BLOCKS_PER_GROUP(sb);
count -= overflow;
}
- count_clusters = EXT4_B2C(sbi, count);
+ count_clusters = EXT4_NUM_B2C(sbi, count);
bitmap_bh = ext4_read_block_bitmap(sb, block_group);
if (!bitmap_bh) {
err = -EIO;
@@ -4639,10 +4644,16 @@ do_more:
* blocks being freed are metadata. these blocks shouldn't
* be used until this transaction is committed
*/
+ retry:
new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS);
if (!new_entry) {
- err = -ENOMEM;
- goto error_return;
+ /*
+ * We use a retry loop because
+ * ext4_free_blocks() is not allowed to fail.
+ */
+ cond_resched();
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ goto retry;
}
new_entry->efd_start_cluster = bit;
new_entry->efd_group = block_group;
@@ -4670,8 +4681,8 @@ do_more:
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
- atomic_add(count_clusters,
- &sbi->s_flex_groups[flex_group].free_clusters);
+ atomic64_add(count_clusters,
+ &sbi->s_flex_groups[flex_group].free_clusters);
}
ext4_mb_unload_buddy(&e4b);
@@ -4811,12 +4822,12 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
ext4_unlock_group(sb, block_group);
percpu_counter_add(&sbi->s_freeclusters_counter,
- EXT4_B2C(sbi, blocks_freed));
+ EXT4_NUM_B2C(sbi, blocks_freed));
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
- atomic_add(EXT4_B2C(sbi, blocks_freed),
- &sbi->s_flex_groups[flex_group].free_clusters);
+ atomic64_add(EXT4_NUM_B2C(sbi, blocks_freed),
+ &sbi->s_flex_groups[flex_group].free_clusters);
}
ext4_mb_unload_buddy(&e4b);
@@ -4987,8 +4998,9 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
end = start + (range->len >> sb->s_blocksize_bits) - 1;
minlen = range->minlen >> sb->s_blocksize_bits;
- if (unlikely(minlen > EXT4_CLUSTERS_PER_GROUP(sb)) ||
- unlikely(start >= max_blks))
+ if (minlen > EXT4_CLUSTERS_PER_GROUP(sb) ||
+ start >= max_blks ||
+ range->len < sb->s_blocksize)
return -EINVAL;
if (end >= max_blks)
end = max_blks - 1;
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index c5826c6..e2016f3 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -141,55 +141,21 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
}
/**
- * mext_check_null_inode - NULL check for two inodes
- *
- * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0.
- */
-static int
-mext_check_null_inode(struct inode *inode1, struct inode *inode2,
- const char *function, unsigned int line)
-{
- int ret = 0;
-
- if (inode1 == NULL) {
- __ext4_error(inode2->i_sb, function, line,
- "Both inodes should not be NULL: "
- "inode1 NULL inode2 %lu", inode2->i_ino);
- ret = -EIO;
- } else if (inode2 == NULL) {
- __ext4_error(inode1->i_sb, function, line,
- "Both inodes should not be NULL: "
- "inode1 %lu inode2 NULL", inode1->i_ino);
- ret = -EIO;
- }
- return ret;
-}
-
-/**
* double_down_write_data_sem - Acquire two inodes' write lock of i_data_sem
*
- * @orig_inode: original inode structure
- * @donor_inode: donor inode structure
- * Acquire write lock of i_data_sem of the two inodes (orig and donor) by
- * i_ino order.
+ * Acquire write lock of i_data_sem of the two inodes
*/
static void
-double_down_write_data_sem(struct inode *orig_inode, struct inode *donor_inode)
+double_down_write_data_sem(struct inode *first, struct inode *second)
{
- struct inode *first = orig_inode, *second = donor_inode;
+ if (first < second) {
+ down_write(&EXT4_I(first)->i_data_sem);
+ down_write_nested(&EXT4_I(second)->i_data_sem, SINGLE_DEPTH_NESTING);
+ } else {
+ down_write(&EXT4_I(second)->i_data_sem);
+ down_write_nested(&EXT4_I(first)->i_data_sem, SINGLE_DEPTH_NESTING);
- /*
- * Use the inode number to provide the stable locking order instead
- * of its address, because the C language doesn't guarantee you can
- * compare pointers that don't come from the same array.
- */
- if (donor_inode->i_ino < orig_inode->i_ino) {
- first = donor_inode;
- second = orig_inode;
}
-
- down_write(&EXT4_I(first)->i_data_sem);
- down_write_nested(&EXT4_I(second)->i_data_sem, SINGLE_DEPTH_NESTING);
}
/**
@@ -969,14 +935,6 @@ mext_check_arguments(struct inode *orig_inode,
return -EINVAL;
}
- /* Files should be in the same ext4 FS */
- if (orig_inode->i_sb != donor_inode->i_sb) {
- ext4_debug("ext4 move extent: The argument files "
- "should be in same FS [ino:orig %lu, donor %lu]\n",
- orig_inode->i_ino, donor_inode->i_ino);
- return -EINVAL;
- }
-
/* Ext4 move extent supports only extent based file */
if (!(ext4_test_inode_flag(orig_inode, EXT4_INODE_EXTENTS))) {
ext4_debug("ext4 move extent: orig file is not extents "
@@ -1072,35 +1030,19 @@ mext_check_arguments(struct inode *orig_inode,
* @inode1: the inode structure
* @inode2: the inode structure
*
- * Lock two inodes' i_mutex by i_ino order.
- * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0.
+ * Lock two inodes' i_mutex
*/
-static int
+static void
mext_inode_double_lock(struct inode *inode1, struct inode *inode2)
{
- int ret = 0;
-
- BUG_ON(inode1 == NULL && inode2 == NULL);
-
- ret = mext_check_null_inode(inode1, inode2, __func__, __LINE__);
- if (ret < 0)
- goto out;
-
- if (inode1 == inode2) {
- mutex_lock(&inode1->i_mutex);
- goto out;
- }
-
- if (inode1->i_ino < inode2->i_ino) {
+ BUG_ON(inode1 == inode2);
+ if (inode1 < inode2) {
mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
} else {
mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT);
mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD);
}
-
-out:
- return ret;
}
/**
@@ -1109,28 +1051,13 @@ out:
* @inode1: the inode that is released first
* @inode2: the inode that is released second
*
- * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0.
*/
-static int
+static void
mext_inode_double_unlock(struct inode *inode1, struct inode *inode2)
{
- int ret = 0;
-
- BUG_ON(inode1 == NULL && inode2 == NULL);
-
- ret = mext_check_null_inode(inode1, inode2, __func__, __LINE__);
- if (ret < 0)
- goto out;
-
- if (inode1)
- mutex_unlock(&inode1->i_mutex);
-
- if (inode2 && inode2 != inode1)
- mutex_unlock(&inode2->i_mutex);
-
-out:
- return ret;
+ mutex_unlock(&inode1->i_mutex);
+ mutex_unlock(&inode2->i_mutex);
}
/**
@@ -1187,16 +1114,23 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
ext4_lblk_t block_end, seq_start, add_blocks, file_end, seq_blocks = 0;
ext4_lblk_t rest_blocks;
pgoff_t orig_page_offset = 0, seq_end_page;
- int ret1, ret2, depth, last_extent = 0;
+ int ret, depth, last_extent = 0;
int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
int data_offset_in_page;
int block_len_in_page;
int uninit;
- /* orig and donor should be different file */
- if (orig_inode->i_ino == donor_inode->i_ino) {
+ if (orig_inode->i_sb != donor_inode->i_sb) {
+ ext4_debug("ext4 move extent: The argument files "
+ "should be in same FS [ino:orig %lu, donor %lu]\n",
+ orig_inode->i_ino, donor_inode->i_ino);
+ return -EINVAL;
+ }
+
+ /* orig and donor should be different inodes */
+ if (orig_inode == donor_inode) {
ext4_debug("ext4 move extent: The argument files should not "
- "be same file [ino:orig %lu, donor %lu]\n",
+ "be same inode [ino:orig %lu, donor %lu]\n",
orig_inode->i_ino, donor_inode->i_ino);
return -EINVAL;
}
@@ -1208,18 +1142,21 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
orig_inode->i_ino, donor_inode->i_ino);
return -EINVAL;
}
-
+ /* TODO: This is non obvious task to swap blocks for inodes with full
+ jornaling enabled */
+ if (ext4_should_journal_data(orig_inode) ||
+ ext4_should_journal_data(donor_inode)) {
+ return -EINVAL;
+ }
/* Protect orig and donor inodes against a truncate */
- ret1 = mext_inode_double_lock(orig_inode, donor_inode);
- if (ret1 < 0)
- return ret1;
+ mext_inode_double_lock(orig_inode, donor_inode);
/* Protect extent tree against block allocations via delalloc */
double_down_write_data_sem(orig_inode, donor_inode);
/* Check the filesystem environment whether move_extent can be done */
- ret1 = mext_check_arguments(orig_inode, donor_inode, orig_start,
+ ret = mext_check_arguments(orig_inode, donor_inode, orig_start,
donor_start, &len);
- if (ret1)
+ if (ret)
goto out;
file_end = (i_size_read(orig_inode) - 1) >> orig_inode->i_blkbits;
@@ -1227,13 +1164,13 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
if (file_end < block_end)
len -= block_end - file_end;
- ret1 = get_ext_path(orig_inode, block_start, &orig_path);
- if (ret1)
+ ret = get_ext_path(orig_inode, block_start, &orig_path);
+ if (ret)
goto out;
/* Get path structure to check the hole */
- ret1 = get_ext_path(orig_inode, block_start, &holecheck_path);
- if (ret1)
+ ret = get_ext_path(orig_inode, block_start, &holecheck_path);
+ if (ret)
goto out;
depth = ext_depth(orig_inode);
@@ -1252,13 +1189,13 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
last_extent = mext_next_extent(orig_inode,
holecheck_path, &ext_cur);
if (last_extent < 0) {
- ret1 = last_extent;
+ ret = last_extent;
goto out;
}
last_extent = mext_next_extent(orig_inode, orig_path,
&ext_dummy);
if (last_extent < 0) {
- ret1 = last_extent;
+ ret = last_extent;
goto out;
}
seq_start = le32_to_cpu(ext_cur->ee_block);
@@ -1272,7 +1209,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
if (le32_to_cpu(ext_cur->ee_block) > block_end) {
ext4_debug("ext4 move extent: The specified range of file "
"may be the hole\n");
- ret1 = -EINVAL;
+ ret = -EINVAL;
goto out;
}
@@ -1292,7 +1229,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
last_extent = mext_next_extent(orig_inode, holecheck_path,
&ext_cur);
if (last_extent < 0) {
- ret1 = last_extent;
+ ret = last_extent;
break;
}
add_blocks = ext4_ext_get_actual_len(ext_cur);
@@ -1349,18 +1286,18 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
orig_page_offset,
data_offset_in_page,
block_len_in_page, uninit,
- &ret1);
+ &ret);
/* Count how many blocks we have exchanged */
*moved_len += block_len_in_page;
- if (ret1 < 0)
+ if (ret < 0)
break;
if (*moved_len > len) {
EXT4_ERROR_INODE(orig_inode,
"We replaced blocks too much! "
"sum of replaced: %llu requested: %llu",
*moved_len, len);
- ret1 = -EIO;
+ ret = -EIO;
break;
}
@@ -1374,22 +1311,22 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
}
double_down_write_data_sem(orig_inode, donor_inode);
- if (ret1 < 0)
+ if (ret < 0)
break;
/* Decrease buffer counter */
if (holecheck_path)
ext4_ext_drop_refs(holecheck_path);
- ret1 = get_ext_path(orig_inode, seq_start, &holecheck_path);
- if (ret1)
+ ret = get_ext_path(orig_inode, seq_start, &holecheck_path);
+ if (ret)
break;
depth = holecheck_path->p_depth;
/* Decrease buffer counter */
if (orig_path)
ext4_ext_drop_refs(orig_path);
- ret1 = get_ext_path(orig_inode, seq_start, &orig_path);
- if (ret1)
+ ret = get_ext_path(orig_inode, seq_start, &orig_path);
+ if (ret)
break;
ext_cur = holecheck_path[depth].p_ext;
@@ -1412,12 +1349,7 @@ out:
kfree(holecheck_path);
}
double_up_write_data_sem(orig_inode, donor_inode);
- ret2 = mext_inode_double_unlock(orig_inode, donor_inode);
-
- if (ret1)
- return ret1;
- else if (ret2)
- return ret2;
+ mext_inode_double_unlock(orig_inode, donor_inode);
- return 0;
+ return ret;
}
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 6832a51..665e55c 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -585,11 +585,8 @@ static int htree_dirblock_to_tree(struct file *dir_file,
if (ext4_check_dir_entry(dir, NULL, de, bh,
(block<<EXT4_BLOCK_SIZE_BITS(dir->i_sb))
+ ((char *)de - bh->b_data))) {
- /* On error, skip the f_pos to the next block. */
- dir_file->f_pos = (dir_file->f_pos |
- (dir->i_sb->s_blocksize - 1)) + 1;
- brelse(bh);
- return count;
+ /* silently ignore the rest of the block */
+ break;
}
ext4fs_dirhash(de->name, de->name_len, hinfo);
if ((hinfo->hash < start_hash) ||
@@ -1048,6 +1045,12 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, stru
EXT4_ERROR_INODE(dir, "bad inode number: %u", ino);
return ERR_PTR(-EIO);
}
+ if (unlikely(ino == dir->i_ino)) {
+ EXT4_ERROR_INODE(dir, "'%.*s' linked to parent dir",
+ dentry->d_name.len,
+ dentry->d_name.name);
+ return ERR_PTR(-EIO);
+ }
inode = ext4_iget(dir->i_sb, ino);
if (inode == ERR_PTR(-ESTALE)) {
EXT4_ERROR_INODE(dir,
@@ -1808,9 +1811,7 @@ retry:
err = PTR_ERR(inode);
if (!IS_ERR(inode)) {
init_special_inode(inode, inode->i_mode, rdev);
-#ifdef CONFIG_EXT4_FS_XATTR
inode->i_op = &ext4_special_inode_operations;
-#endif
err = ext4_add_nondir(handle, dentry, inode);
}
ext4_journal_stop(handle);
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 21227d83..a43e43c 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -161,6 +161,8 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size)
if (flex_gd == NULL)
goto out3;
+ if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_flex_group_data))
+ goto out2;
flex_gd->count = flexbg_size;
flex_gd->groups = kmalloc(sizeof(struct ext4_new_group_data) *
@@ -198,8 +200,11 @@ static void free_flex_gd(struct ext4_new_flex_group_data *flex_gd)
* be a partial of a flex group.
*
* @sb: super block of fs to which the groups belongs
+ *
+ * Returns 0 on a successful allocation of the metadata blocks in the
+ * block group.
*/
-static void ext4_alloc_group_tables(struct super_block *sb,
+static int ext4_alloc_group_tables(struct super_block *sb,
struct ext4_new_flex_group_data *flex_gd,
int flexbg_size)
{
@@ -224,6 +229,8 @@ static void ext4_alloc_group_tables(struct super_block *sb,
(last_group & ~(flexbg_size - 1))));
next_group:
group = group_data[0].group;
+ if (src_group >= group_data[0].group + flex_gd->count)
+ return -ENOSPC;
start_blk = ext4_group_first_block_no(sb, src_group);
last_blk = start_blk + group_data[src_group - group].blocks_count;
@@ -233,7 +240,6 @@ next_group:
start_blk += overhead;
- BUG_ON(src_group >= group_data[0].group + flex_gd->count);
/* We collect contiguous blocks as much as possible. */
src_group++;
for (; src_group <= last_group; src_group++)
@@ -298,6 +304,7 @@ next_group:
group_data[i].free_blocks_count);
}
}
+ return 0;
}
static struct buffer_head *bclean(handle_t *handle, struct super_block *sb,
@@ -449,6 +456,9 @@ static int setup_new_flex_group_blocks(struct super_block *sb,
gdblocks = ext4_bg_num_gdb(sb, group);
start = ext4_group_first_block_no(sb, group);
+ if (!ext4_bg_has_super(sb, group))
+ goto handle_itb;
+
/* Copy all of the GDT blocks into the backup in this group */
for (j = 0, block = start + 1; j < gdblocks; j++, block++) {
struct buffer_head *gdb;
@@ -491,6 +501,7 @@ static int setup_new_flex_group_blocks(struct super_block *sb,
goto out;
}
+handle_itb:
/* Initialize group tables of the grop @group */
if (!(bg_flags[i] & EXT4_BG_INODE_ZEROED))
goto handle_bb;
@@ -1103,7 +1114,7 @@ static int ext4_setup_new_descs(handle_t *handle, struct super_block *sb,
ext4_inode_bitmap_set(sb, gdp, group_data->inode_bitmap);
ext4_inode_table_set(sb, gdp, group_data->inode_table);
ext4_free_group_clusters_set(sb, gdp,
- EXT4_B2C(sbi, group_data->free_blocks_count));
+ EXT4_NUM_B2C(sbi, group_data->free_blocks_count));
ext4_free_inodes_set(sb, gdp, EXT4_INODES_PER_GROUP(sb));
gdp->bg_flags = cpu_to_le16(*bg_flags);
gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
@@ -1193,6 +1204,8 @@ static void ext4_update_super(struct super_block *sb,
/* Update the global fs size fields */
sbi->s_groups_count += flex_gd->count;
+ sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count,
+ (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb)));
/* Update the reserved block counts only once the new group is
* active. */
@@ -1201,7 +1214,7 @@ static void ext4_update_super(struct super_block *sb,
/* Update the free space counts */
percpu_counter_add(&sbi->s_freeclusters_counter,
- EXT4_B2C(sbi, free_blocks));
+ EXT4_NUM_B2C(sbi, free_blocks));
percpu_counter_add(&sbi->s_freeinodes_counter,
EXT4_INODES_PER_GROUP(sb) * flex_gd->count);
@@ -1210,8 +1223,8 @@ static void ext4_update_super(struct super_block *sb,
sbi->s_log_groups_per_flex) {
ext4_group_t flex_group;
flex_group = ext4_flex_group(sbi, group_data[0].group);
- atomic_add(EXT4_B2C(sbi, free_blocks),
- &sbi->s_flex_groups[flex_group].free_clusters);
+ atomic64_add(EXT4_NUM_B2C(sbi, free_blocks),
+ &sbi->s_flex_groups[flex_group].free_clusters);
atomic_add(EXT4_INODES_PER_GROUP(sb) * flex_gd->count,
&sbi->s_flex_groups[flex_group].free_inodes);
}
@@ -1293,13 +1306,15 @@ exit_journal:
err = err2;
if (!err) {
- int i;
+ int gdb_num = group / EXT4_DESC_PER_BLOCK(sb);
+ int gdb_num_end = ((group + flex_gd->count - 1) /
+ EXT4_DESC_PER_BLOCK(sb));
+
update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es,
sizeof(struct ext4_super_block));
- for (i = 0; i < flex_gd->count; i++, group++) {
+ for (; gdb_num <= gdb_num_end; gdb_num++) {
struct buffer_head *gdb_bh;
- int gdb_num;
- gdb_num = group / EXT4_BLOCKS_PER_GROUP(sb);
+
gdb_bh = sbi->s_group_desc[gdb_num];
update_backups(sb, gdb_bh->b_blocknr, gdb_bh->b_data,
gdb_bh->b_size);
@@ -1617,6 +1632,10 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
return 0;
ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &offset);
+ if (n_group > (0xFFFFFFFFUL / EXT4_INODES_PER_GROUP(sb))) {
+ ext4_warning(sb, "resize would cause inodes_count overflow");
+ return -EINVAL;
+ }
ext4_get_group_no_and_offset(sb, o_blocks_count - 1, &o_group, &offset);
n_desc_blocks = (n_group + EXT4_DESC_PER_BLOCK(sb)) /
@@ -1676,7 +1695,8 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
*/
while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count,
flexbg_size)) {
- ext4_alloc_group_tables(sb, flex_gd, flexbg_size);
+ if (ext4_alloc_group_tables(sb, flex_gd, flexbg_size) != 0)
+ break;
err = ext4_flex_group_add(sb, resize_inode, flex_gd);
if (unlikely(err))
break;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 734d744..f0e4e46 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -500,6 +500,7 @@ void __ext4_error(struct super_block *sb, const char *function,
printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: comm %s: %pV\n",
sb->s_id, function, line, current->comm, &vaf);
va_end(args);
+ save_error_info(sb, function, line);
ext4_handle_error(sb);
}
@@ -657,14 +658,6 @@ void __ext4_abort(struct super_block *sb, const char *function,
if (EXT4_SB(sb)->s_journal)
jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
save_error_info(sb, function, line);
- #ifdef CONFIG_MACH_LGE
- /* LGE_CHANGE
- * put panic when ext4 partition is remounted as Read Only
- * 2014-04-15, [email protected]
- */
- panic("EXT4-fs panic from previous error. remounted as RO \n");
- #endif
-
}
if (test_opt(sb, ERRORS_PANIC))
panic("EXT4-fs panic from previous error\n");
@@ -942,6 +935,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
ei->i_reserved_meta_blocks = 0;
ei->i_allocated_meta_blocks = 0;
ei->i_da_metadata_calc_len = 0;
+ ei->i_da_metadata_calc_last_lblock = 0;
spin_lock_init(&(ei->i_block_reservation_lock));
#ifdef CONFIG_QUOTA
ei->i_reserved_quota = 0;
@@ -1012,11 +1006,6 @@ static int init_inodecache(void)
static void destroy_inodecache(void)
{
- /*
- * Make sure all delayed rcu free inodes are flushed before we
- * destroy cache.
- */
- rcu_barrier();
kmem_cache_destroy(ext4_inode_cachep);
}
@@ -1613,9 +1602,7 @@ static int parse_options(char *options, struct super_block *sb,
unsigned int *journal_ioprio,
int is_remount)
{
-#ifdef CONFIG_QUOTA
struct ext4_sb_info *sbi = EXT4_SB(sb);
-#endif
char *p;
substring_t args[MAX_OPT_ARGS];
int token;
@@ -1664,6 +1651,16 @@ static int parse_options(char *options, struct super_block *sb,
}
}
#endif
+ if (test_opt(sb, DIOREAD_NOLOCK)) {
+ int blocksize =
+ BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
+
+ if (blocksize < PAGE_CACHE_SIZE) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "dioread_nolock if block size != PAGE_SIZE");
+ return 0;
+ }
+ }
return 1;
}
@@ -1706,7 +1703,7 @@ static inline void ext4_show_quota_options(struct seq_file *seq,
static const char *token2str(int token)
{
- static const struct match_token *t;
+ const struct match_token *t;
for (t = tokens; t->token != Opt_err; t++)
if (t->token == token && !strchr(t->pattern, '='))
@@ -1913,8 +1910,8 @@ static int ext4_fill_flex_info(struct super_block *sb)
flex_group = ext4_flex_group(sbi, i);
atomic_add(ext4_free_inodes_count(sb, gdp),
&sbi->s_flex_groups[flex_group].free_inodes);
- atomic_add(ext4_free_group_clusters(sb, gdp),
- &sbi->s_flex_groups[flex_group].free_clusters);
+ atomic64_add(ext4_free_group_clusters(sb, gdp),
+ &sbi->s_flex_groups[flex_group].free_clusters);
atomic_add(ext4_used_dirs_count(sb, gdp),
&sbi->s_flex_groups[flex_group].used_dirs);
}
@@ -2126,7 +2123,9 @@ static void ext4_orphan_cleanup(struct super_block *sb,
__func__, inode->i_ino, inode->i_size);
jbd_debug(2, "truncating inode %lu to %lld bytes\n",
inode->i_ino, inode->i_size);
+ mutex_lock(&inode->i_mutex);
ext4_truncate(inode);
+ mutex_unlock(&inode->i_mutex);
nr_truncates++;
} else {
ext4_msg(sb, KERN_DEBUG,
@@ -2984,6 +2983,10 @@ static int count_overhead(struct super_block *sb, ext4_group_t grp,
ext4_group_t i, ngroups = ext4_get_groups_count(sb);
int s, j, count = 0;
+ if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC))
+ return (ext4_bg_has_super(sb, grp) + ext4_bg_num_gdb(sb, grp) +
+ sbi->s_itb_per_group + 2);
+
first_block = le32_to_cpu(sbi->s_es->s_first_data_block) +
(grp * EXT4_BLOCKS_PER_GROUP(sb));
last_block = first_block + EXT4_BLOCKS_PER_GROUP(sb) - 1;
@@ -3230,22 +3233,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
}
if (test_opt(sb, DIOREAD_NOLOCK)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
- "both data=journal and delalloc");
+ "both data=journal and dioread_nolock");
goto failed_mount;
}
if (test_opt(sb, DELALLOC))
clear_opt(sb, DELALLOC);
}
- blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
- if (test_opt(sb, DIOREAD_NOLOCK)) {
- if (blocksize < PAGE_SIZE) {
- ext4_msg(sb, KERN_ERR, "can't mount with "
- "dioread_nolock if block size != PAGE_SIZE");
- goto failed_mount;
- }
- }
-
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
(test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0);
@@ -3287,6 +3281,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
if (!ext4_feature_set_ok(sb, (sb->s_flags & MS_RDONLY)))
goto failed_mount;
+ blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
if (blocksize < EXT4_MIN_BLOCK_SIZE ||
blocksize > EXT4_MAX_BLOCK_SIZE) {
ext4_msg(sb, KERN_ERR,
@@ -3735,7 +3730,8 @@ no_journal:
goto failed_mount4;
}
- ext4_setup_super(sb, es, sb->s_flags & MS_RDONLY);
+ if (ext4_setup_super(sb, es, sb->s_flags & MS_RDONLY))
+ sb->s_flags |= MS_RDONLY;
/* determine the minimum size of new large inodes, if present */
if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) {
@@ -3818,55 +3814,27 @@ no_journal:
cantfind_ext4:
if (!silent)
ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem");
-#ifdef CONFIG_MACH_LGE
-/* LGE_CHANGE
- * add return code if ext4 superblock is damaged
- * 2014-01-16, [email protected]
- */
- ret = -ESUPER;
-#endif
goto failed_mount;
failed_mount7:
-#ifdef CONFIG_MACH_LGE
- printk(KERN_ERR "EXT4-fs: failed_mount7\n");
-#endif
ext4_unregister_li_request(sb);
failed_mount6:
-#ifdef CONFIG_MACH_LGE
- printk(KERN_ERR "EXT4-fs: failed_mount6\n");
-#endif
ext4_mb_release(sb);
failed_mount5:
-#ifdef CONFIG_MACH_LGE
- printk(KERN_ERR "EXT4-fs: failed_mount5\n");
-#endif
ext4_ext_release(sb);
ext4_release_system_zone(sb);
failed_mount4a:
-#ifdef CONFIG_MACH_LGE
- printk(KERN_ERR "EXT4-fs: failed_mount4a\n");
-#endif
dput(sb->s_root);
sb->s_root = NULL;
failed_mount4:
-#ifdef CONFIG_MACH_LGE
- printk(KERN_ERR "EXT4-fs: failed_mount4\n");
-#endif
ext4_msg(sb, KERN_ERR, "mount failed");
destroy_workqueue(EXT4_SB(sb)->dio_unwritten_wq);
failed_mount_wq:
-#ifdef CONFIG_MACH_LGE
- printk(KERN_ERR "EXT4-fs: failed_mount_wq\n");
-#endif
if (sbi->s_journal) {
jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
}
failed_mount3:
-#ifdef CONFIG_MACH_LGE
- printk(KERN_ERR "EXT4-fs: failed_mount3\n");
-#endif
del_timer(&sbi->s_err_report);
if (sbi->s_flex_groups)
ext4_kvfree(sbi->s_flex_groups);
@@ -3877,17 +3845,10 @@ failed_mount3:
if (sbi->s_mmp_tsk)
kthread_stop(sbi->s_mmp_tsk);
failed_mount2:
-#ifdef CONFIG_MACH_LGE
- printk(KERN_ERR "EXT4-fs: failed_mount2\n");
- ret = -ESUPER;
-#endif
for (i = 0; i < db_count; i++)
brelse(sbi->s_group_desc[i]);
ext4_kvfree(sbi->s_group_desc);
failed_mount:
-#ifdef CONFIG_MACH_LGE
- printk(KERN_ERR "EXT4-fs: failed_mount\n");
-#endif
if (sbi->s_proc) {
remove_proc_entry("options", sbi->s_proc);
remove_proc_entry(sb->s_id, ext4_proc_root);
@@ -4443,6 +4404,21 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
goto restore_opts;
}
+ if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
+ if (test_opt2(sb, EXPLICIT_DELALLOC)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "both data=journal and delalloc");
+ err = -EINVAL;
+ goto restore_opts;
+ }
+ if (test_opt(sb, DIOREAD_NOLOCK)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "both data=journal and dioread_nolock");
+ err = -EINVAL;
+ goto restore_opts;
+ }
+ }
+
if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
ext4_abort(sb, "Abort forced by user");
@@ -4557,7 +4533,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
}
ext4_setup_system_zone(sb);
- if (sbi->s_journal == NULL)
+ if (sbi->s_journal == NULL && !(old_sb_flags & MS_RDONLY))
ext4_commit_super(sb, 1);
#ifdef CONFIG_QUOTA
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index a37f317..5743e9d 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -495,7 +495,7 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
error = ext4_handle_dirty_metadata(handle, inode, bh);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
- dquot_free_block(inode, 1);
+ dquot_free_block(inode, EXT4_C2B(EXT4_SB(inode->i_sb), 1));
ea_bdebug(bh, "refcount now=%d; releasing",
le32_to_cpu(BHDR(bh)->h_refcount));
}
@@ -784,7 +784,8 @@ inserted:
else {
/* The old block is released after updating
the inode. */
- error = dquot_alloc_block(inode, 1);
+ error = dquot_alloc_block(inode,
+ EXT4_C2B(EXT4_SB(sb), 1));
if (error)
goto cleanup;
error = ext4_journal_get_write_access(handle,
@@ -881,7 +882,7 @@ cleanup:
return error;
cleanup_dquot:
- dquot_free_block(inode, 1);
+ dquot_free_block(inode, EXT4_C2B(EXT4_SB(sb), 1));
goto cleanup;
bad_block:
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment