ext4: Retry block allocation if new blocks are allocated from system zone.

If the block allocator gets blocks out of system zone ext4 calls
ext4_error. But if the file system is mounted with errors=continue
retry block allocation. We need to mark the system zone blocks as
in use to make sure retry don't pick them again

System zone is the block range mapping block bitmap, inode bitmap and inode
table.

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>

2 files changed, 47 insertions, 17 deletions

diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index da994374ec3b..30494c5da843 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -287,11 +287,11 @@ read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
                             (int)block_group, (unsigned long long)bitmap_blk);
                 return NULL;
         }
-        if (!ext4_valid_block_bitmap(sb, desc, block_group, bh)) {
-                put_bh(bh);
-                return NULL;
-        }
-
+        ext4_valid_block_bitmap(sb, desc, block_group, bh);
+        /*
+         * file system mounted not to panic on error,
+         * continue with corrupt bitmap
+         */
         return bh;
 }
 /*
@@ -1770,7 +1770,12 @@ allocated:
                             "Allocating block in system zone - "
                             "blocks from %llu, length %lu",
                              ret_block, num);
-                goto out;
+                /*
+                 * claim_block marked the blocks we allocated
+                 * as in use. So we may want to selectively
+                 * mark some of the blocks as free
+                 */
+                goto retry_alloc;
         }
 
         performed_allocation = 1;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 1d7fde994521..873ad9b3418c 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2736,7 +2736,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
         struct ext4_sb_info *sbi;
         struct super_block *sb;
         ext4_fsblk_t block;
-        int err;
+        int err, len;
 
         BUG_ON(ac->ac_status != AC_STATUS_FOUND);
         BUG_ON(ac->ac_b_ex.fe_len <= 0);
@@ -2770,14 +2770,27 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
                 + ac->ac_b_ex.fe_start
                 + le32_to_cpu(es->s_first_data_block);
 
-        if (block == ext4_block_bitmap(sb, gdp) ||
-                        block == ext4_inode_bitmap(sb, gdp) ||
-                        in_range(block, ext4_inode_table(sb, gdp),
-                                EXT4_SB(sb)->s_itb_per_group)) {
-
+        len = ac->ac_b_ex.fe_len;
+        if (in_range(ext4_block_bitmap(sb, gdp), block, len) ||
+            in_range(ext4_inode_bitmap(sb, gdp), block, len) ||
+            in_range(block, ext4_inode_table(sb, gdp),
+                     EXT4_SB(sb)->s_itb_per_group) ||
+            in_range(block + len - 1, ext4_inode_table(sb, gdp),
+                     EXT4_SB(sb)->s_itb_per_group)) {
                 ext4_error(sb, __func__,
                            "Allocating block in system zone - block = %llu",
                            block);
+                /* File system mounted not to panic on error
+                 * Fix the bitmap and repeat the block allocation
+                 * We leak some of the blocks here.
+                 */
+                mb_set_bits(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group),
+                                bitmap_bh->b_data, ac->ac_b_ex.fe_start,
+                                ac->ac_b_ex.fe_len);
+                err = ext4_journal_dirty_metadata(handle, bitmap_bh);
+                if (!err)
+                        err = -EAGAIN;
+                goto out_err;
         }
 #ifdef AGGRESSIVE_CHECK
         {
@@ -4032,7 +4045,6 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 
                 ac->ac_op = EXT4_MB_HISTORY_ALLOC;
                 ext4_mb_normalize_request(ac, ar);
-
 repeat:
                 /* allocate space in core */
                 ext4_mb_regular_allocator(ac);
@@ -4046,10 +4058,21 @@ repeat:
         }
 
         if (likely(ac->ac_status == AC_STATUS_FOUND)) {
-                ext4_mb_mark_diskspace_used(ac, handle);
-                *errp = 0;
-                block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);
-                ar->len = ac->ac_b_ex.fe_len;
+                *errp = ext4_mb_mark_diskspace_used(ac, handle);
+                if (*errp ==  -EAGAIN) {
+                        ac->ac_b_ex.fe_group = 0;
+                        ac->ac_b_ex.fe_start = 0;
+                        ac->ac_b_ex.fe_len = 0;
+                        ac->ac_status = AC_STATUS_CONTINUE;
+                        goto repeat;
+                } else if (*errp) {
+                        ac->ac_b_ex.fe_len = 0;
+                        ar->len = 0;
+                        ext4_mb_show_ac(ac);
+                } else {
+                        block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);
+                        ar->len = ac->ac_b_ex.fe_len;
+                }
         } else {
                 freed  = ext4_mb_discard_preallocations(sb, ac->ac_o_ex.fe_len);
                 if (freed)
@@ -4236,6 +4259,8 @@ do_more:
                 ext4_error(sb, __func__,
                            "Freeing blocks in system zone - "
                            "Block = %lu, count = %lu", block, count);
+                /* err = 0. ext4_std_error should be a no op */
+                goto error_return;
         }
 
         BUFFER_TRACE(bitmap_bh, "getting write access");