[PATCH 1/1] nfs: keep PG_UPTODATE clear after read errors in page groups

[xiaoning . wang]

From: Clark Wang <xiaoning.wang@xxxxxxx>

When a read request is split into multiple subrequests, earlier
completions may advance PG_UPTODATE state for the page group once
their bytes fall within hdr->good_bytes. If a later subrequest in
the same group then completes with NFS_IOHDR_ERROR, the read path
needs to clear any accumulated PG_UPTODATE state and keep later
completions from rebuilding it.

Otherwise, a subsequent successful subrequest can re-enter
nfs_page_group_set_uptodate(), restore the page-group sync state,
and leave stale PG_UPTODATE behind for nfs_page_group_destroy()
to trip over in nfs_free_request().

Add a sticky page-group read-failed flag. Once any subrequest in
the group is known to be bad, mark the group failed, clear any
accumulated PG_UPTODATE state, and refuse further PG_UPTODATE
synchronization for the rest of the completion walk.

Fixes: 67d0338edd71 ("nfs: page group syncing in read path")
Signed-off-by: Clark Wang <xiaoning.wang@xxxxxxx>
---
 fs/nfs/read.c            | 25 ++++++++++++++++++++++++-
 include/linux/nfs_page.h |  1 +
 2 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index e1fe78d7b8d0..2b70bd2b934b 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -132,10 +132,32 @@ static void nfs_readpage_release(struct nfs_page *req, int error)
 
 static void nfs_page_group_set_uptodate(struct nfs_page *req)
 {
-	if (nfs_page_group_sync_on_bit(req, PG_UPTODATE))
+	bool uptodate = false;
+
+	nfs_page_group_lock(req);
+	if (!test_bit(PG_READ_FAILED, &req->wb_head->wb_flags) &&
+	    nfs_page_group_sync_on_bit_locked(req, PG_UPTODATE))
+		uptodate = true;
+	nfs_page_group_unlock(req);
+
+	if (uptodate)
 		folio_mark_uptodate(nfs_page_to_folio(req));
 }
 
+static void nfs_page_group_mark_read_failed(struct nfs_page *req)
+{
+	struct nfs_page *tmp;
+
+	nfs_page_group_lock(req);
+	set_bit(PG_READ_FAILED, &req->wb_head->wb_flags);
+	tmp = req;
+	do {
+		clear_bit(PG_UPTODATE, &tmp->wb_flags);
+		tmp = tmp->wb_this_page;
+	} while (tmp != req);
+	nfs_page_group_unlock(req);
+}
+
 static void nfs_read_completion(struct nfs_pgio_header *hdr)
 {
 	unsigned long bytes = 0;
@@ -172,6 +194,7 @@ static void nfs_read_completion(struct nfs_pgio_header *hdr)
 			if (bytes <= hdr->good_bytes)
 				nfs_page_group_set_uptodate(req);
 			else {
+				nfs_page_group_mark_read_failed(req);
 				error = hdr->error;
 				xchg(&nfs_req_openctx(req)->error, error);
 			}
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index afe1d8f09d89..4b9a35dbc062 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -33,6 +33,7 @@ enum {
 	PG_TEARDOWN,		/* page group sync for destroy */
 	PG_UNLOCKPAGE,		/* page group sync bit in read path */
 	PG_UPTODATE,		/* page group sync bit in read path */
+	PG_READ_FAILED,		/* page group saw a read error */
 	PG_WB_END,		/* page group sync bit in write path */
 	PG_REMOVE,		/* page group sync bit in write path */
 	PG_CONTENDED1,		/* Is someone waiting for a lock? */
-- 
2.34.1