ext4: ENOSPC error handling for writing to an uninitialized extent

This patch handles possible ENOSPC errors when writing to an
uninitialized extent in case the filesystem is full.

A write to a prealloc area causes the split of an unititalized extent
into initialized and uninitialized extents.  If we don't have
space to add new extent information, instead of returning error,
convert the existing uninitialized extent to initialized one.  We
need to zero out the blocks corresponding to the entire extent to
prevent uninitialized data reaching userspace.

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>

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index a38f324278267c7f8f534934c1360588b7b4b29d..d279ea8c4661fd4fa574bf00d49e637be2cea2d2 100644 (file)
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2138,6 +2138,80 @@ void ext4_ext_release(struct super_block *sb)
 #endif
 }
 
+static void bi_complete(struct bio *bio, int error)
+{
+       complete((struct completion *)bio->bi_private);
+}
+
+/* FIXME!! we need to try to merge to left or right after zero-out  */
+static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
+{
+       int ret = -EIO;
+       struct bio *bio;
+       int blkbits, blocksize;
+       sector_t ee_pblock;
+       struct completion event;
+       unsigned int ee_len, len, done, offset;
+
+
+       blkbits   = inode->i_blkbits;
+       blocksize = inode->i_sb->s_blocksize;
+       ee_len    = ext4_ext_get_actual_len(ex);
+       ee_pblock = ext_pblock(ex);
+
+       /* convert ee_pblock to 512 byte sectors */
+       ee_pblock = ee_pblock << (blkbits - 9);
+
+       while (ee_len > 0) {
+
+               if (ee_len > BIO_MAX_PAGES)
+                       len = BIO_MAX_PAGES;
+               else
+                       len = ee_len;
+
+               bio = bio_alloc(GFP_NOIO, len);
+               if (!bio)
+                       return -ENOMEM;
+               bio->bi_sector = ee_pblock;
+               bio->bi_bdev   = inode->i_sb->s_bdev;
+
+               done = 0;
+               offset = 0;
+               while (done < len) {
+                       ret = bio_add_page(bio, ZERO_PAGE(0),
+                                                       blocksize, offset);
+                       if (ret != blocksize) {
+                               /*
+                                * We can't add any more pages because of
+                                * hardware limitations.  Start a new bio.
+                                */
+                               break;
+                       }
+                       done++;
+                       offset += blocksize;
+                       if (offset >= PAGE_CACHE_SIZE)
+                               offset = 0;
+               }
+
+               init_completion(&event);
+               bio->bi_private = &event;
+               bio->bi_end_io = bi_complete;
+               submit_bio(WRITE, bio);
+               wait_for_completion(&event);
+
+               if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+                       ret = 0;
+               else {
+                       ret = -EIO;
+                       break;
+               }
+               bio_put(bio);
+               ee_len    -= done;
+               ee_pblock += done  << (blkbits - 9);
+       }
+       return ret;
+}
+
 /*
  * This function is called by ext4_ext_get_blocks() if someone tries to write
  * to an uninitialized extent. It may result in splitting the uninitialized
@@ -2204,14 +2278,19 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
                ex3->ee_len = cpu_to_le16(allocated - max_blocks);
                ext4_ext_mark_uninitialized(ex3);
                err = ext4_ext_insert_extent(handle, inode, path, ex3);
-               if (err) {
+               if (err == -ENOSPC) {
+                       err =  ext4_ext_zeroout(inode, &orig_ex);
+                       if (err)
+                               goto fix_extent_len;
+                       /* update the extent length and mark as initialized */
                        ex->ee_block = orig_ex.ee_block;
                        ex->ee_len   = orig_ex.ee_len;
                        ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
-                       ext4_ext_mark_uninitialized(ex);
                        ext4_ext_dirty(handle, inode, path + depth);
-                       goto out;
-               }
+                       return le16_to_cpu(ex->ee_len);
+
+               } else if (err)
+                       goto fix_extent_len;
                /*
                 * The depth, and hence eh & ex might change
                 * as part of the insert above.
@@ -2297,15 +2376,28 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
        goto out;
 insert:
        err = ext4_ext_insert_extent(handle, inode, path, &newex);
-       if (err) {
+       if (err == -ENOSPC) {
+               err =  ext4_ext_zeroout(inode, &orig_ex);
+               if (err)
+                       goto fix_extent_len;
+               /* update the extent length and mark as initialized */
                ex->ee_block = orig_ex.ee_block;
                ex->ee_len   = orig_ex.ee_len;
                ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
-               ext4_ext_mark_uninitialized(ex);
                ext4_ext_dirty(handle, inode, path + depth);
-       }
+               return le16_to_cpu(ex->ee_len);
+       } else if (err)
+               goto fix_extent_len;
 out:
        return err ? err : allocated;
+
+fix_extent_len:
+       ex->ee_block = orig_ex.ee_block;
+       ex->ee_len   = orig_ex.ee_len;
+       ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+       ext4_ext_mark_uninitialized(ex);
+       ext4_ext_dirty(handle, inode, path + depth);
+       return err;
 }
 
 /*