ext4: delayed allocation ENOSPC handling

This patch does block reservation for delayed
allocation, to avoid ENOSPC later at page flush time.

Blocks(data and metadata) are reserved at da_write_begin()
time, the freeblocks counter is updated by then, and the number of
reserved blocks is store in per inode counter.
        
At the writepage time, the unused reserved meta blocks are returned
back. At unlink/truncate time, reserved blocks are properly released.

Updated fix from  Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
to fix the oldallocator block reservation accounting with delalloc, added
lock to guard the counters and also fix the reservation for meta blocks.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Mingming Cao <cmm@us.ibm.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

1 files changed, 18 insertions, 2 deletions

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 8d254ca..8d141a2 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2964,7 +2964,15 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 	le16_add_cpu(&gdp->bg_free_blocks_count, -ac->ac_b_ex.fe_len);
 	gdp->bg_checksum = ext4_group_desc_csum(sbi, ac->ac_b_ex.fe_group, gdp);
 	spin_unlock(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group));
-	percpu_counter_sub(&sbi->s_freeblocks_counter, ac->ac_b_ex.fe_len);
+
+	/*
+	 * free blocks account has already be reduced/reserved
+	 * at write_begin() time for delayed allocation
+	 * do not double accounting
+	 */
+	if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED))
+		percpu_counter_sub(&sbi->s_freeblocks_counter,
+					ac->ac_b_ex.fe_len);
 
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi,
@@ -4169,7 +4177,12 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 					    &(ar->len), errp);
 		return block;
 	}
-	ar->len = ext4_has_free_blocks(sbi, ar->len);
+	if (!EXT4_I(ar->inode)->i_delalloc_reserved_flag) {
+		/*
+		 * With delalloc we already reserved the blocks
+		 */
+		ar->len = ext4_has_free_blocks(sbi, ar->len);
+	}
 
 	if (ar->len == 0) {
 		*errp = -ENOSPC;
@@ -4186,6 +4199,9 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 	}
 	inquota = ar->len;
 
+	if (EXT4_I(ar->inode)->i_delalloc_reserved_flag)
+		ar->flags |= EXT4_MB_DELALLOC_RESERVED;
+
 	ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
 	if (!ac) {
 		ar->len = 0;