erofs: fix unexpected EIO under memory pressure

erofs readahead could fail with ENOMEM under the memory pressure because
it tries to alloc_page with GFP_NOWAIT | GFP_NORETRY, while GFP_KERNEL
for a regular read. And if readahead fails (with non-uptodate folios),
the original request will then fall back to synchronous read, and
`.read_folio()` should return appropriate errnos.

However, in scenarios where readahead and read operations compete,
read operation could return an unintended EIO because of an incorrect
error propagation.

To resolve this, this patch modifies the behavior so that, when the
PCL is for read(which means pcl.besteffort is true), it attempts actual
decompression instead of propagating the privios error except initial EIO.

- Page size: 4K
- The original size of FileA: 16K
- Compress-ratio per PCL: 50% (Uncompressed 8K -> Compressed 4K)
[page0, page1] [page2, page3]
[PCL0]---------[PCL1]

- functions declaration:
  . pread(fd, buf, count, offset)
  . readahead(fd, offset, count)
- Thread A tries to read the last 4K
- Thread B tries to do readahead 8K from 4K
- RA, besteffort == false
- R, besteffort == true

        <process A>                   <process B>

pread(FileA, buf, 4K, 12K)
  do readahead(page3) // failed with ENOMEM
  wait_lock(page3)
    if (!uptodate(page3))
      goto do_read
                               readahead(FileA, 4K, 8K)
                               // Here create PCL-chain like below:
                               // [null, page1] [page2, null]
                               //   [PCL0:RA]-----[PCL1:RA]
...
  do read(page3)        // found [PCL1:RA] and add page3 into it,
                        // and then, change PCL1 from RA to R
...
                               // Now, PCL-chain is as below:
                               // [null, page1] [page2, page3]
                               //   [PCL0:RA]-----[PCL1:R]

                                 // try to decompress PCL-chain...
                                 z_erofs_decompress_queue
                                   err = 0;

                                   // failed with ENOMEM, so page 1
                                   // only for RA will not be uptodated.
                                   // it's okay.
                                   err = decompress([PCL0:RA], err)

                                   // However, ENOMEM propagated to next
                                   // PCL, even though PCL is not only
                                   // for RA but also for R. As a result,
                                   // it just failed with ENOMEM without
                                   // trying any decompression, so page2
                                   // and page3 will not be uptodated.
                ** BUG HERE ** --> err = decompress([PCL1:R], err)

                                   return err as ENOMEM
...
    wait_lock(page3)
      if (!uptodate(page3))
        return EIO      <-- Return an unexpected EIO!
...

Fixes: 2349d2fa02db ("erofs: sunset unneeded NOFAILs")
Cc: stable@vger.kernel.org
Reviewed-by: Jaewook Kim <jw5454.kim@samsung.com>
Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
Signed-off-by: Junbeom Yeom <junbeom.yeom@samsung.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>

diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 65da215046320a9a088c58676b3db8628ee98dff..3d31f7840ca04de30e137735886aaade190e99d4 100644 (file)
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -1262,7 +1262,7 @@ static int z_erofs_parse_in_bvecs(struct z_erofs_backend *be, bool *overlapped)
        return err;
 }
 
-static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err)
+static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, bool eio)
 {
        struct erofs_sb_info *const sbi = EROFS_SB(be->sb);
        struct z_erofs_pcluster *pcl = be->pcl;
@@ -1270,7 +1270,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err)
        const struct z_erofs_decompressor *alg =
                                z_erofs_decomp[pcl->algorithmformat];
        bool try_free = true;
-       int i, j, jtop, err2;
+       int i, j, jtop, err2, err = eio ? -EIO : 0;
        struct page *page;
        bool overlapped;
        const char *reason;
@@ -1413,12 +1413,12 @@ static int z_erofs_decompress_queue(const struct z_erofs_decompressqueue *io,
                .pcl = io->head,
        };
        struct z_erofs_pcluster *next;
-       int err = io->eio ? -EIO : 0;
+       int err = 0;
 
        for (; be.pcl != Z_EROFS_PCLUSTER_TAIL; be.pcl = next) {
                DBG_BUGON(!be.pcl);
                next = READ_ONCE(be.pcl->next);
-               err = z_erofs_decompress_pcluster(&be, err) ?: err;
+               err = z_erofs_decompress_pcluster(&be, io->eio) ?: err;
        }
        return err;
 }