summaryrefslogtreecommitdiffstats
path: root/fs/hugetlbfs
diff options
context:
space:
mode:
authorJiaqi Yan <jiaqiyan@google.com>2023-07-13 00:18:32 +0000
committerAndrew Morton <akpm@linux-foundation.org>2023-08-18 10:12:26 -0700
commit38c1ddbde6c6593e7c4bc17bde87232b7c577e7b (patch)
treee7a65730f83ee6dbf81c6788bdb48e62987a9454 /fs/hugetlbfs
parentb79f8eb408d0468df0d6082ed958b67d94adce65 (diff)
downloadlinux-38c1ddbde6c6593e7c4bc17bde87232b7c577e7b.tar.gz
linux-38c1ddbde6c6593e7c4bc17bde87232b7c577e7b.tar.bz2
linux-38c1ddbde6c6593e7c4bc17bde87232b7c577e7b.zip
hugetlbfs: improve read HWPOISON hugepage
When a hugepage contains HWPOISON pages, read() fails to read any byte of the hugepage and returns -EIO, although many bytes in the HWPOISON hugepage are readable. Improve this by allowing hugetlbfs_read_iter returns as many bytes as possible. For a requested range [offset, offset + len) that contains HWPOISON page, return [offset, first HWPOISON page addr); the next read attempt will fail and return -EIO. Link: https://lkml.kernel.org/r/20230713001833.3778937-4-jiaqiyan@google.com Signed-off-by: Jiaqi Yan <jiaqiyan@google.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: James Houghton <jthoughton@google.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Muchun Song <songmuchun@bytedance.com> Cc: Yang Shi <shy828301@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'fs/hugetlbfs')
-rw-r--r--fs/hugetlbfs/inode.c57
1 files changed, 51 insertions, 6 deletions
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 7b17ccfa039d..e7611ae1e612 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -283,6 +283,41 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
#endif
/*
+ * Someone wants to read @bytes from a HWPOISON hugetlb @page from @offset.
+ * Returns the maximum number of bytes one can read without touching the 1st raw
+ * HWPOISON subpage.
+ *
+ * The implementation borrows the iteration logic from copy_page_to_iter*.
+ */
+static size_t adjust_range_hwpoison(struct page *page, size_t offset, size_t bytes)
+{
+ size_t n = 0;
+ size_t res = 0;
+
+ /* First subpage to start the loop. */
+ page += offset / PAGE_SIZE;
+ offset %= PAGE_SIZE;
+ while (1) {
+ if (is_raw_hwpoison_page_in_hugepage(page))
+ break;
+
+ /* Safe to read n bytes without touching HWPOISON subpage. */
+ n = min(bytes, (size_t)PAGE_SIZE - offset);
+ res += n;
+ bytes -= n;
+ if (!bytes || !n)
+ break;
+ offset += n;
+ if (offset == PAGE_SIZE) {
+ page++;
+ offset = 0;
+ }
+ }
+
+ return res;
+}
+
+/*
* Support for read() - Find the page attached to f_mapping and copy out the
* data. This provides functionality similar to filemap_read().
*/
@@ -300,7 +335,7 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
while (iov_iter_count(to)) {
struct page *page;
- size_t nr, copied;
+ size_t nr, copied, want;
/* nr is the maximum number of bytes to copy from this page */
nr = huge_page_size(h);
@@ -328,16 +363,26 @@ 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;
+ if (!PageHWPoison(page))
+ want = nr;
+ else {
+ /*
+ * Adjust how many bytes safe to read without
+ * touching the 1st raw HWPOISON subpage after
+ * offset.
+ */
+ want = adjust_range_hwpoison(page, offset, nr);
+ if (want == 0) {
+ put_page(page);
+ retval = -EIO;
+ break;
+ }
}
/*
* We have the page, copy it to user space buffer.
*/
- copied = copy_page_to_iter(page, offset, nr, to);
+ copied = copy_page_to_iter(page, offset, want, to);
put_page(page);
}
offset += copied;