ext4: restart handle if credits are insufficient during allocating blocks

After large folios are supported on ext4, writing back a sufficiently
large and discontinuous folio may consume a significant number of
journal credits, placing considerable strain on the journal. For
example, in a 20GB filesystem with 1K block size and 1MB journal size,
writing back a 2MB folio could require thousands of credits in the
worst-case scenario (when each block is discontinuous and distributed
across different block groups), potentially exceeding the journal size.
This issue can also occur in ext4_write_begin() and ext4_page_mkwrite()
when delalloc is not enabled.

Fix this by ensuring that there are sufficient journal credits before
allocating an extent in mpage_map_one_extent() and
ext4_block_write_begin(). If there are not enough credits, return
-EAGAIN, exit the current mapping loop, restart a new handle and a new
transaction, and allocating blocks on this folio again in the next
iteration.

Suggested-by: Jan Kara <jack@suse.cz>
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20250707140814.542883-6-yi.zhang@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index f8946430304c95edd239586a59d697523e624a7f..74b7ba2afb67994bf0d660d3162ce15b88eddae1 100644 (file)
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -875,6 +875,26 @@ static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags)
        } while (unlikely(!try_cmpxchg(&bh->b_state, &old_state, new_state)));
 }
 
+/*
+ * Make sure that the current journal transaction has enough credits to map
+ * one extent. Return -EAGAIN if it cannot extend the current running
+ * transaction.
+ */
+static inline int ext4_journal_ensure_extent_credits(handle_t *handle,
+                                                    struct inode *inode)
+{
+       int credits;
+       int ret;
+
+       /* Called from ext4_da_write_begin() which has no handle started? */
+       if (!handle)
+               return 0;
+
+       credits = ext4_chunk_trans_blocks(inode, 1);
+       ret = __ext4_journal_ensure_credits(handle, credits, credits, 0);
+       return ret <= 0 ? ret : -EAGAIN;
+}
+
 static int _ext4_get_block(struct inode *inode, sector_t iblock,
                           struct buffer_head *bh, int flags)
 {
@@ -1173,7 +1193,9 @@ int ext4_block_write_begin(handle_t *handle, struct folio *folio,
                        clear_buffer_new(bh);
                if (!buffer_mapped(bh)) {
                        WARN_ON(bh->b_size != blocksize);
-                       err = get_block(inode, block, bh, 1);
+                       err = ext4_journal_ensure_extent_credits(handle, inode);
+                       if (!err)
+                               err = get_block(inode, block, bh, 1);
                        if (err)
                                break;
                        if (buffer_new(bh)) {
@@ -1372,8 +1394,9 @@ retry_journal:
                                ext4_orphan_del(NULL, inode);
                }
 
-               if (ret == -ENOSPC &&
-                   ext4_should_retry_alloc(inode->i_sb, &retries))
+               if (ret == -EAGAIN ||
+                   (ret == -ENOSPC &&
+                    ext4_should_retry_alloc(inode->i_sb, &retries)))
                        goto retry_journal;
                folio_put(folio);
                return ret;
@@ -2321,6 +2344,11 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
        int get_blocks_flags;
        int err, dioread_nolock;
 
+       /* Make sure transaction has enough credits for this extent */
+       err = ext4_journal_ensure_extent_credits(handle, inode);
+       if (err < 0)
+               return err;
+
        trace_ext4_da_write_pages_extent(inode, map);
        /*
         * Call ext4_map_blocks() to allocate any delayed allocation blocks, or
@@ -2448,7 +2476,7 @@ static int mpage_map_and_submit_extent(handle_t *handle,
                         * In the case of ENOSPC, if ext4_count_free_blocks()
                         * is non-zero, a commit should free up blocks.
                         */
-                       if ((err == -ENOMEM) ||
+                       if ((err == -ENOMEM) || (err == -EAGAIN) ||
                            (err == -ENOSPC && ext4_count_free_clusters(sb))) {
                                /*
                                 * We may have already allocated extents for
@@ -2954,6 +2982,8 @@ retry:
                        ret = 0;
                        continue;
                }
+               if (ret == -EAGAIN)
+                       ret = 0;
                /* Fatal error - ENOMEM, EIO... */
                if (ret)
                        break;
@@ -6732,7 +6762,8 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
 retry_alloc:
        /* Start journal and allocate blocks */
        err = ext4_block_page_mkwrite(inode, folio, get_block);
-       if (err == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+       if (err == -EAGAIN ||
+           (err == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)))
                goto retry_alloc;
 out_ret:
        ret = vmf_fs_error(err);