hugetlbfs: don't delete error page from pagecache

This change is very similar to the change that was made for shmem [1], and
it solves the same problem but for HugeTLBFS instead.

Currently, when poison is found in a HugeTLB page, the page is removed
from the page cache.  That means that attempting to map or read that
hugepage in the future will result in a new hugepage being allocated
instead of notifying the user that the page was poisoned.  As [1] states,
this is effectively memory corruption.

The fix is to leave the page in the page cache.  If the user attempts to
use a poisoned HugeTLB page with a syscall, the syscall will fail with
EIO, the same error code that shmem uses.  For attempts to map the page,
the thread will get a BUS_MCEERR_AR SIGBUS.

[1]: commit a7605426 ("mm: shmem: don't truncate page if memory failure happens")

Link: https://lkml.kernel.org/r/20221018200125.848471-1-jthoughton@google.comSigned-off-by: James Houghton <jthoughton@google.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Tested-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: James Houghton <jthoughton@google.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

fs/hugetlbfs/inode.c

@@ -328,6 +328,12 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		} else {
 			unlock_page(page);
 
+			if (PageHWPoison(page)) {
+				put_page(page);
+				retval = -EIO;
+				break;
+			}
+
 			/*
 			 * We have the page, copy it to user space buffer.
 			 */
@@ -1111,13 +1117,6 @@ static int hugetlbfs_migrate_folio(struct address_space *mapping,
 static int hugetlbfs_error_remove_page(struct address_space *mapping,
 				struct page *page)
 {
-	struct inode *inode = mapping->host;
-	pgoff_t index = page->index;
-
-	hugetlb_delete_from_page_cache(page);
-	if (unlikely(hugetlb_unreserve_pages(inode, index, index + 1, 1)))
-		hugetlb_fix_reserve_counts(inode);
-
 	return 0;
 }
 

mm/hugetlb.c

@@ -6111,6 +6111,10 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 
 	ptl = huge_pte_lock(h, dst_mm, dst_pte);
 
+	ret = -EIO;
+	if (PageHWPoison(page))
+		goto out_release_unlock;
+
 	/*
 	 * We allow to overwrite a pte marker: consider when both MISSING|WP
 	 * registered, we firstly wr-protect a none pte which has no page cache

mm/memory-failure.c

@@ -1080,6 +1080,7 @@ static int me_huge_page(struct page_state *ps, struct page *p)
 	int res;
 	struct page *hpage = compound_head(p);
 	struct address_space *mapping;
+	bool extra_pins = false;
 
 	if (!PageHuge(hpage))
 		return MF_DELAYED;
@@ -1087,6 +1088,8 @@ static int me_huge_page(struct page_state *ps, struct page *p)
 	mapping = page_mapping(hpage);
 	if (mapping) {
 		res = truncate_error_page(hpage, page_to_pfn(p), mapping);
+		/* The page is kept in page cache. */
+		extra_pins = true;
 		unlock_page(hpage);
 	} else {
 		unlock_page(hpage);
@@ -1104,7 +1107,7 @@ static int me_huge_page(struct page_state *ps, struct page *p)
 		}
 	}
 
-	if (has_extra_refcount(ps, p, false))
+	if (has_extra_refcount(ps, p, extra_pins))
 		res = MF_FAILED;
 
 	return res;