summaryrefslogtreecommitdiffstats
path: root/fs/ext4/mballoc.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2010-08-07 13:03:53 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2010-08-07 13:03:53 -0700
commit09dc942c2a767e2d298f1cc9294bc19c7d7208c5 (patch)
treed310c118467c90c264e953bdc320ae08394c662a /fs/ext4/mballoc.c
parent90e0c225968f0878e090c7ff3f88323973476cee (diff)
parent6c7a120ac6c62316ab1fc78dfc0a7b13f3bfcbff (diff)
downloadop-kernel-dev-09dc942c2a767e2d298f1cc9294bc19c7d7208c5.zip
op-kernel-dev-09dc942c2a767e2d298f1cc9294bc19c7d7208c5.tar.gz
Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4
* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (40 commits) ext4: Adding error check after calling ext4_mb_regular_allocator() ext4: Fix dirtying of journalled buffers in data=journal mode ext4: re-inline ext4_rec_len_(to|from)_disk functions jbd2: Remove t_handle_lock from start_this_handle() jbd2: Change j_state_lock to be a rwlock_t jbd2: Use atomic variables to avoid taking t_handle_lock in jbd2_journal_stop ext4: Add mount options in superblock ext4: force block allocation on quota_off ext4: fix freeze deadlock under IO ext4: drop inode from orphan list if ext4_delete_inode() fails ext4: check to make make sure bd_dev is set before dereferencing it jbd2: Make barrier messages less scary ext4: don't print scary messages for allocation failures post-abort ext4: fix EFBIG edge case when writing to large non-extent file ext4: fix ext4_get_blocks references ext4: Always journal quota file modifications ext4: Fix potential memory leak in ext4_fill_super ext4: Don't error out the fs if the user tries to make a file too big ext4: allocate stripe-multiple IOs on stripe boundaries ext4: move aio completion after unwritten extent conversion ... Fix up conflicts in fs/ext4/inode.c as per Ted. Fix up xfs conflicts as per earlier xfs merge.
Diffstat (limited to 'fs/ext4/mballoc.c')
-rw-r--r--fs/ext4/mballoc.c153
1 files changed, 76 insertions, 77 deletions
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 0e83dfd..4b4ad4b 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -446,10 +446,11 @@ static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b,
blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
blocknr += first + i;
ext4_grp_locked_error(sb, e4b->bd_group,
- __func__, "double-free of inode"
- " %lu's block %llu(bit %u in group %u)",
- inode ? inode->i_ino : 0, blocknr,
- first + i, e4b->bd_group);
+ inode ? inode->i_ino : 0,
+ blocknr,
+ "freeing block already freed "
+ "(bit %u)",
+ first + i);
}
mb_clear_bit(first + i, e4b->bd_info->bb_bitmap);
}
@@ -712,9 +713,9 @@ void ext4_mb_generate_buddy(struct super_block *sb,
grp->bb_fragments = fragments;
if (free != grp->bb_free) {
- ext4_grp_locked_error(sb, group, __func__,
- "EXT4-fs: group %u: %u blocks in bitmap, %u in gd",
- group, free, grp->bb_free);
+ ext4_grp_locked_error(sb, group, 0, 0,
+ "%u blocks in bitmap, %u in gd",
+ free, grp->bb_free);
/*
* If we intent to continue, we consider group descritor
* corrupt and update bb_free using bitmap value
@@ -1296,10 +1297,10 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
blocknr += block;
ext4_grp_locked_error(sb, e4b->bd_group,
- __func__, "double-free of inode"
- " %lu's block %llu(bit %u in group %u)",
- inode ? inode->i_ino : 0, blocknr, block,
- e4b->bd_group);
+ inode ? inode->i_ino : 0,
+ blocknr,
+ "freeing already freed block "
+ "(bit %u)", block);
}
mb_clear_bit(block, EXT4_MB_BITMAP(e4b));
e4b->bd_info->bb_counters[order]++;
@@ -1788,8 +1789,8 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
* free blocks even though group info says we
* we have free blocks
*/
- ext4_grp_locked_error(sb, e4b->bd_group,
- __func__, "%d free blocks as per "
+ ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
+ "%d free blocks as per "
"group info. But bitmap says 0",
free);
break;
@@ -1798,8 +1799,8 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
mb_find_extent(e4b, 0, i, ac->ac_g_ex.fe_len, &ex);
BUG_ON(ex.fe_len <= 0);
if (free < ex.fe_len) {
- ext4_grp_locked_error(sb, e4b->bd_group,
- __func__, "%d free blocks as per "
+ ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
+ "%d free blocks as per "
"group info. But got %d blocks",
free, ex.fe_len);
/*
@@ -1821,8 +1822,7 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
/*
* This is a special case for storages like raid5
- * we try to find stripe-aligned chunks for stripe-size requests
- * XXX should do so at least for multiples of stripe size as well
+ * we try to find stripe-aligned chunks for stripe-size-multiple requests
*/
static noinline_for_stack
void ext4_mb_scan_aligned(struct ext4_allocation_context *ac,
@@ -1999,7 +1999,6 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
ext4_group_t ngroups, group, i;
int cr;
int err = 0;
- int bsbits;
struct ext4_sb_info *sbi;
struct super_block *sb;
struct ext4_buddy e4b;
@@ -2041,8 +2040,6 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
ac->ac_2order = i - 1;
}
- bsbits = ac->ac_sb->s_blocksize_bits;
-
/* if stream allocation is enabled, use global goal */
if (ac->ac_flags & EXT4_MB_STREAM_ALLOC) {
/* TBD: may be hot point */
@@ -2094,8 +2091,8 @@ repeat:
ac->ac_groups_scanned++;
if (cr == 0)
ext4_mb_simple_scan_group(ac, &e4b);
- else if (cr == 1 &&
- ac->ac_g_ex.fe_len == sbi->s_stripe)
+ else if (cr == 1 && sbi->s_stripe &&
+ !(ac->ac_g_ex.fe_len % sbi->s_stripe))
ext4_mb_scan_aligned(ac, &e4b);
else
ext4_mb_complex_scan_group(ac, &e4b);
@@ -2221,7 +2218,7 @@ static int ext4_mb_seq_groups_open(struct inode *inode, struct file *file)
rc = seq_open(file, &ext4_mb_seq_groups_ops);
if (rc == 0) {
- struct seq_file *m = (struct seq_file *)file->private_data;
+ struct seq_file *m = file->private_data;
m->private = sb;
}
return rc;
@@ -2560,6 +2557,22 @@ int ext4_mb_release(struct super_block *sb)
return 0;
}
+static inline void ext4_issue_discard(struct super_block *sb,
+ ext4_group_t block_group, ext4_grpblk_t block, int count)
+{
+ int ret;
+ ext4_fsblk_t discard_block;
+
+ discard_block = block + ext4_group_first_block_no(sb, block_group);
+ trace_ext4_discard_blocks(sb,
+ (unsigned long long) discard_block, count);
+ ret = sb_issue_discard(sb, discard_block, count);
+ if (ret == EOPNOTSUPP) {
+ ext4_warning(sb, "discard not supported, disabling");
+ clear_opt(EXT4_SB(sb)->s_mount_opt, DISCARD);
+ }
+}
+
/*
* This function is called by the jbd2 layer once the commit has finished,
* so we know we can free the blocks that were released with that commit.
@@ -2579,22 +2592,9 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
mb_debug(1, "gonna free %u blocks in group %u (0x%p):",
entry->count, entry->group, entry);
- if (test_opt(sb, DISCARD)) {
- int ret;
- ext4_fsblk_t discard_block;
-
- discard_block = entry->start_blk +
- ext4_group_first_block_no(sb, entry->group);
- trace_ext4_discard_blocks(sb,
- (unsigned long long)discard_block,
- entry->count);
- ret = sb_issue_discard(sb, discard_block, entry->count);
- if (ret == EOPNOTSUPP) {
- ext4_warning(sb,
- "discard not supported, disabling");
- clear_opt(EXT4_SB(sb)->s_mount_opt, DISCARD);
- }
- }
+ if (test_opt(sb, DISCARD))
+ ext4_issue_discard(sb, entry->group,
+ entry->start_blk, entry->count);
err = ext4_mb_load_buddy(sb, entry->group, &e4b);
/* we expect to find existing buddy because it's pinned */
@@ -2712,7 +2712,6 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
handle_t *handle, unsigned int reserv_blks)
{
struct buffer_head *bitmap_bh = NULL;
- struct ext4_super_block *es;
struct ext4_group_desc *gdp;
struct buffer_head *gdp_bh;
struct ext4_sb_info *sbi;
@@ -2725,8 +2724,6 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
sb = ac->ac_sb;
sbi = EXT4_SB(sb);
- es = sbi->s_es;
-
err = -EIO;
bitmap_bh = ext4_read_block_bitmap(sb, ac->ac_b_ex.fe_group);
@@ -2812,7 +2809,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
err = ext4_handle_dirty_metadata(handle, NULL, gdp_bh);
out_err:
- sb->s_dirt = 1;
+ ext4_mark_super_dirty(sb);
brelse(bitmap_bh);
return err;
}
@@ -2850,7 +2847,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
int bsbits, max;
ext4_lblk_t end;
loff_t size, orig_size, start_off;
- ext4_lblk_t start, orig_start;
+ ext4_lblk_t start;
struct ext4_inode_info *ei = EXT4_I(ac->ac_inode);
struct ext4_prealloc_space *pa;
@@ -2881,6 +2878,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
size = size << bsbits;
if (size < i_size_read(ac->ac_inode))
size = i_size_read(ac->ac_inode);
+ orig_size = size;
/* max size of free chunks */
max = 2 << bsbits;
@@ -2922,8 +2920,8 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
start_off = (loff_t)ac->ac_o_ex.fe_logical << bsbits;
size = ac->ac_o_ex.fe_len << bsbits;
}
- orig_size = size = size >> bsbits;
- orig_start = start = start_off >> bsbits;
+ size = size >> bsbits;
+ start = start_off >> bsbits;
/* don't cover already allocated blocks in selected range */
if (ar->pleft && start <= ar->lleft) {
@@ -3547,7 +3545,6 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
ext4_group_t group;
ext4_grpblk_t bit;
unsigned long long grp_blk_start;
- sector_t start;
int err = 0;
int free = 0;
@@ -3567,10 +3564,9 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
if (bit >= end)
break;
next = mb_find_next_bit(bitmap_bh->b_data, end, bit);
- start = ext4_group_first_block_no(sb, group) + bit;
mb_debug(1, " free preallocated %u/%u in group %u\n",
- (unsigned) start, (unsigned) next - bit,
- (unsigned) group);
+ (unsigned) ext4_group_first_block_no(sb, group) + bit,
+ (unsigned) next - bit, (unsigned) group);
free += next - bit;
if (ac) {
@@ -3581,7 +3577,7 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
trace_ext4_mballoc_discard(ac);
}
- trace_ext4_mb_release_inode_pa(ac, pa, grp_blk_start + bit,
+ trace_ext4_mb_release_inode_pa(sb, ac, pa, grp_blk_start + bit,
next - bit);
mb_free_blocks(pa->pa_inode, e4b, bit, next - bit);
bit = next + 1;
@@ -3591,8 +3587,7 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
pa, (unsigned long) pa->pa_lstart,
(unsigned long) pa->pa_pstart,
(unsigned long) pa->pa_len);
- ext4_grp_locked_error(sb, group,
- __func__, "free %u, pa_free %u",
+ ext4_grp_locked_error(sb, group, 0, 0, "free %u, pa_free %u",
free, pa->pa_free);
/*
* pa is already deleted so we use the value obtained
@@ -3613,7 +3608,7 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b,
ext4_group_t group;
ext4_grpblk_t bit;
- trace_ext4_mb_release_group_pa(ac, pa);
+ trace_ext4_mb_release_group_pa(sb, ac, pa);
BUG_ON(pa->pa_deleted == 0);
ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit);
BUG_ON(group != e4b->bd_group && pa->pa_len != 0);
@@ -3889,6 +3884,9 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
struct super_block *sb = ac->ac_sb;
ext4_group_t ngroups, i;
+ if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+ return;
+
printk(KERN_ERR "EXT4-fs: Can't allocate:"
" Allocation context details:\n");
printk(KERN_ERR "EXT4-fs: status %d flags %d\n",
@@ -4255,7 +4253,7 @@ static int ext4_mb_discard_preallocations(struct super_block *sb, int needed)
* to usual allocation
*/
ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
- struct ext4_allocation_request *ar, int *errp)
+ struct ext4_allocation_request *ar, int *errp)
{
int freed;
struct ext4_allocation_context *ac = NULL;
@@ -4299,7 +4297,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
inquota = ar->len;
if (ar->len == 0) {
*errp = -EDQUOT;
- goto out3;
+ goto out;
}
}
@@ -4307,13 +4305,13 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
if (!ac) {
ar->len = 0;
*errp = -ENOMEM;
- goto out1;
+ goto out;
}
*errp = ext4_mb_initialize_context(ac, ar);
if (*errp) {
ar->len = 0;
- goto out2;
+ goto out;
}
ac->ac_op = EXT4_MB_HISTORY_PREALLOC;
@@ -4322,7 +4320,9 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
ext4_mb_normalize_request(ac, ar);
repeat:
/* allocate space in core */
- ext4_mb_regular_allocator(ac);
+ *errp = ext4_mb_regular_allocator(ac);
+ if (*errp)
+ goto errout;
/* as we've just preallocated more space than
* user requested orinally, we store allocated
@@ -4333,7 +4333,7 @@ repeat:
}
if (likely(ac->ac_status == AC_STATUS_FOUND)) {
*errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_blks);
- if (*errp == -EAGAIN) {
+ if (*errp == -EAGAIN) {
/*
* drop the reference that we took
* in ext4_mb_use_best_found
@@ -4344,12 +4344,10 @@ repeat:
ac->ac_b_ex.fe_len = 0;
ac->ac_status = AC_STATUS_CONTINUE;
goto repeat;
- } else if (*errp) {
+ } else if (*errp)
+ errout:
ext4_discard_allocated_blocks(ac);
- ac->ac_b_ex.fe_len = 0;
- ar->len = 0;
- ext4_mb_show_ac(ac);
- } else {
+ else {
block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);
ar->len = ac->ac_b_ex.fe_len;
}
@@ -4358,19 +4356,19 @@ repeat:
if (freed)
goto repeat;
*errp = -ENOSPC;
+ }
+
+ if (*errp) {
ac->ac_b_ex.fe_len = 0;
ar->len = 0;
ext4_mb_show_ac(ac);
}
-
ext4_mb_release_context(ac);
-
-out2:
- kmem_cache_free(ext4_ac_cachep, ac);
-out1:
+out:
+ if (ac)
+ kmem_cache_free(ext4_ac_cachep, ac);
if (inquota && ar->len < inquota)
dquot_free_block(ar->inode, inquota - ar->len);
-out3:
if (!ar->len) {
if (!EXT4_I(ar->inode)->i_delalloc_reserved_flag)
/* release all the reserved blocks if non delalloc */
@@ -4402,6 +4400,7 @@ static noinline_for_stack int
ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
struct ext4_free_data *new_entry)
{
+ ext4_group_t group = e4b->bd_group;
ext4_grpblk_t block;
struct ext4_free_data *entry;
struct ext4_group_info *db = e4b->bd_info;
@@ -4434,9 +4433,9 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
else if (block >= (entry->start_blk + entry->count))
n = &(*n)->rb_right;
else {
- ext4_grp_locked_error(sb, e4b->bd_group, __func__,
- "Double free of blocks %d (%d %d)",
- block, entry->start_blk, entry->count);
+ ext4_grp_locked_error(sb, group, 0,
+ ext4_group_first_block_no(sb, group) + block,
+ "Block already on to-be-freed list");
return 0;
}
}
@@ -4494,7 +4493,6 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
struct super_block *sb = inode->i_sb;
struct ext4_allocation_context *ac = NULL;
struct ext4_group_desc *gdp;
- struct ext4_super_block *es;
unsigned long freed = 0;
unsigned int overflow;
ext4_grpblk_t bit;
@@ -4513,7 +4511,6 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
}
sbi = EXT4_SB(sb);
- es = EXT4_SB(sb)->s_es;
if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) &&
!ext4_data_block_valid(sbi, block, count)) {
ext4_error(sb, "Freeing blocks not in datazone - "
@@ -4647,6 +4644,8 @@ do_more:
mb_clear_bits(bitmap_bh->b_data, bit, count);
mb_free_blocks(inode, &e4b, bit, count);
ext4_mb_return_to_preallocation(inode, &e4b, block, count);
+ if (test_opt(sb, DISCARD))
+ ext4_issue_discard(sb, block_group, bit, count);
}
ret = ext4_free_blks_count(sb, gdp) + count;
@@ -4680,7 +4679,7 @@ do_more:
put_bh(bitmap_bh);
goto do_more;
}
- sb->s_dirt = 1;
+ ext4_mark_super_dirty(sb);
error_return:
if (freed)
dquot_free_block(inode, freed);
OpenPOWER on IntegriCloud