From: Logan Gunthorpe BLK_STS_P2PDMA reflects the peer/member pairing, not member health: retrying the same pages on the same member cannot succeed. Keep WriteErrorSeen so the range stays fenced, but skip WantReplacement and FailFast eviction, as commit f7b24c7b41f2 ("md/raid1,raid10: don't fail devices for invalid IO errors") did for BLK_STS_INVAL. The failure is whole-range and deterministic, so narrow_write_error()'s block-by-block submit_bio_wait() retries are pointless. Record the whole range as a bad block in the completion handler instead. Fixes: 02666132403a ("md: propagate BLK_FEAT_PCI_P2PDMA from member devices to RAID device") Assisted-by: Claude:claude-fable-5 Signed-off-by: Logan Gunthorpe Co-developed-by: Mykola Marzhan Signed-off-by: Mykola Marzhan --- drivers/md/raid1-10.c | 3 +++ drivers/md/raid1.c | 12 +++++++++--- drivers/md/raid10.c | 8 +++++++- 3 files changed, 19 insertions(+), 4 deletions(-) diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c index cee21452e066..89daf8558251 100644 --- a/drivers/md/raid1-10.c +++ b/drivers/md/raid1-10.c @@ -309,6 +309,9 @@ static inline void raid1_write_error(struct mddev *mddev, struct md_rdev *rdev, { set_bit(WriteErrorSeen, &rdev->flags); + if (bio->bi_status == BLK_STS_P2PDMA) + return; + if (!test_and_set_bit(WantReplacement, &rdev->flags)) set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 19c4dec450de..917d694ef401 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -2624,10 +2624,16 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio) * narrow down and record precise write * errors. */ + struct md_rdev *rdev = conf->mirrors[m].rdev; + fail = true; - narrow_write_error(r1_bio, m); - rdev_dec_pending(conf->mirrors[m].rdev, - conf->mddev); + /* Mapping failures are whole-range and deterministic */ + if (r1_bio->bios[m]->bi_status == BLK_STS_P2PDMA) + rdev_set_badblocks(rdev, r1_bio->sector, + r1_bio->sectors, 0); + else + narrow_write_error(r1_bio, m); + rdev_dec_pending(rdev, conf->mddev); } if (fail) { spin_lock_irq(&conf->device_lock); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 428bddddfe71..9045a3f02dae 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -2940,7 +2940,13 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio) rdev_dec_pending(rdev, conf->mddev); } else if (bio != NULL && bio->bi_status) { fail = true; - narrow_write_error(r10_bio, m); + /* Mapping failures are whole-range and deterministic */ + if (bio->bi_status == BLK_STS_P2PDMA) + rdev_set_badblocks(rdev, + r10_bio->devs[m].addr, + r10_bio->sectors, 0); + else + narrow_write_error(r10_bio, m); rdev_dec_pending(rdev, conf->mddev); } bio = r10_bio->devs[m].repl_bio; -- 2.52.0