mm/shmem: fix infinite loop when swap in shmem error at swapoff time

When swap in shmem error at swapoff time, there would be a infinite loop
in the while loop in shmem_unuse_inode().  It's because swapin error is
deliberately ignored now and thus info->swapped will never reach 0.  So we
can't escape the loop in shmem_unuse().

In order to fix the issue, swapin_error entry is stored in the mapping
when swapin error occurs.  So the swapcache page can be freed and the user
won't end up with a permanently mounted swap because a sector is bad.  If
the page is accessed later, the user process will be killed so that
corrupted data is never consumed.  On the other hand, if the page is never
accessed, the user won't even notice it.

Link: https://lkml.kernel.org/r/20220519125030.21486-5-linmiaohe@huawei.com
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Reported-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Reviewed-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: NeilBrown <neilb@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/shmem.c b/mm/shmem.c
index b8169beff226d1dc3833727f64bf0fa880d94e74..54149ce679be4f7d4b3ed556b3118c9a0c84bad6 100644 (file)
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1174,6 +1174,10 @@ static int shmem_find_swap_entries(struct address_space *mapping,
                        continue;
 
                entry = radix_to_swp_entry(folio);
+               /*
+                * swapin error entries can be found in the mapping. But they're
+                * deliberately ignored here as we've done everything we can do.
+                */
                if (swp_type(entry) != type)
                        continue;
 
@@ -1671,6 +1675,36 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
        return error;
 }
 
+static void shmem_set_folio_swapin_error(struct inode *inode, pgoff_t index,
+                                        struct folio *folio, swp_entry_t swap)
+{
+       struct address_space *mapping = inode->i_mapping;
+       struct shmem_inode_info *info = SHMEM_I(inode);
+       swp_entry_t swapin_error;
+       void *old;
+
+       swapin_error = make_swapin_error_entry(&folio->page);
+       old = xa_cmpxchg_irq(&mapping->i_pages, index,
+                            swp_to_radix_entry(swap),
+                            swp_to_radix_entry(swapin_error), 0);
+       if (old != swp_to_radix_entry(swap))
+               return;
+
+       folio_wait_writeback(folio);
+       delete_from_swap_cache(&folio->page);
+       spin_lock_irq(&info->lock);
+       /*
+        * Don't treat swapin error folio as alloced. Otherwise inode->i_blocks won't
+        * be 0 when inode is released and thus trigger WARN_ON(inode->i_blocks) in
+        * shmem_evict_inode.
+        */
+       info->alloced--;
+       info->swapped--;
+       shmem_recalc_inode(inode);
+       spin_unlock_irq(&info->lock);
+       swap_free(swap);
+}
+
 /*
  * Swap in the page pointed to by *pagep.
  * Caller has to make sure that *pagep contains a valid swapped page.
@@ -1694,6 +1728,9 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
        swap = radix_to_swp_entry(*foliop);
        *foliop = NULL;
 
+       if (is_swapin_error_entry(swap))
+               return -EIO;
+
        /* Look it up and read it in.. */
        page = lookup_swap_cache(swap, NULL, 0);
        if (!page) {
@@ -1761,6 +1798,8 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 failed:
        if (!shmem_confirm_swap(mapping, index, swap))
                error = -EEXIST;
+       if (error == -EIO)
+               shmem_set_folio_swapin_error(inode, index, folio, swap);
 unlock:
        if (folio) {
                folio_unlock(folio);