Merge tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - Two NVMe pull requests:
     - ana log parse fix from Anton
     - nvme quirks support for Apple devices from Ben
     - fix missing bio completion tracing for multipath stack devices
       from Hannes and Mikhail
     - IP TOS settings for nvme rdma and tcp transports from Israel
     - rq_dma_dir cleanups from Israel
     - tracing for Get LBA Status command from Minwoo
     - Some nvme-tcp cleanups from Minwoo, Potnuri and Myself
     - Some consolidation between the fabrics transports for handling
       the CAP register
     - reset race with ns scanning fix for fabrics (move fabrics
       commands to a dedicated request queue with a different lifetime
       from the admin request queue)."
     - controller reset and namespace scan races fixes
     - nvme discovery log change uevent support
     - naming improvements from Keith
     - multiple discovery controllers reject fix from James
     - some regular cleanups from various people

 - Series fixing (and re-fixing) null_blk debug printing and nr_devices
   checks (André)

 - A few pull requests from Song, with fixes from Andy, Guoqing,
   Guilherme, Neil, Nigel, and Yufen.

 - REQ_OP_ZONE_RESET_ALL support (Chaitanya)

 - Bio merge handling unification (Christoph)

 - Pick default elevator correctly for devices with special needs
   (Damien)

 - Block stats fixes (Hou)

 - Timeout and support devices nbd fixes (Mike)

 - Series fixing races around elevator switching and device add/remove
   (Ming)

 - sed-opal cleanups (Revanth)

 - Per device weight support for BFQ (Fam)

 - Support for blk-iocost, a new model that can properly account cost of
   IO workloads. (Tejun)

 - blk-cgroup writeback fixes (Tejun)

 - paride queue init fixes (zhengbin)

 - blk_set_runtime_active() cleanup (Stanley)

 - Block segment mapping optimizations (Bart)

 - lightnvm fixes (Hans/Minwoo/YueHaibing)

 - Various little fixes and cleanups

* tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block: (186 commits)
  null_blk: format pr_* logs with pr_fmt
  null_blk: match the type of parameter nr_devices
  null_blk: do not fail the module load with zero devices
  block: also check RQF_STATS in blk_mq_need_time_stamp()
  block: make rq sector size accessible for block stats
  bfq: Fix bfq linkage error
  raid5: use bio_end_sector in r5_next_bio
  raid5: remove STRIPE_OPS_REQ_PENDING
  md: add feature flag MD_FEATURE_RAID0_LAYOUT
  md/raid0: avoid RAID0 data corruption due to layout confusion.
  raid5: don't set STRIPE_HANDLE to stripe which is in batch list
  raid5: don't increment read_errors on EILSEQ return
  nvmet: fix a wrong error status returned in error log page
  nvme: send discovery log page change events to userspace
  nvme: add uevent variables for controller devices
  nvme: enable aen regardless of the presence of I/O queues
  nvme-fabrics: allow discovery subsystems accept a kato
  nvmet: Use PTR_ERR_OR_ZERO() in nvmet_init_discovery()
  nvme: Remove redundant assignment of cq vector
  nvme: Assign subsys instance from first ctrl
  ...

1 files changed, 51 insertions, 38 deletions

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 34e26834ad28..0466ee2453b4 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -447,19 +447,21 @@ static void raid1_end_write_request(struct bio *bio)
 		    /* We never try FailFast to WriteMostly devices */
 		    !test_bit(WriteMostly, &rdev->flags)) {
 			md_error(r1_bio->mddev, rdev);
-			if (!test_bit(Faulty, &rdev->flags))
-				/* This is the only remaining device,
-				 * We need to retry the write without
-				 * FailFast
-				 */
-				set_bit(R1BIO_WriteError, &r1_bio->state);
-			else {
-				/* Finished with this branch */
-				r1_bio->bios[mirror] = NULL;
-				to_put = bio;
-			}
-		} else
+		}
+
+		/*
+		 * When the device is faulty, it is not necessary to
+		 * handle write error.
+		 * For failfast, this is the only remaining device,
+		 * We need to retry the write without FailFast.
+		 */
+		if (!test_bit(Faulty, &rdev->flags))
 			set_bit(R1BIO_WriteError, &r1_bio->state);
+		else {
+			/* Finished with this branch */
+			r1_bio->bios[mirror] = NULL;
+			to_put = bio;
+		}
 	} else {
 		/*
 		 * Set R1BIO_Uptodate in our master bio, so that we
@@ -872,8 +874,11 @@ static void flush_pending_writes(struct r1conf *conf)
  * backgroup IO calls must call raise_barrier.  Once that returns
  *    there is no normal IO happeing.  It must arrange to call
  *    lower_barrier when the particular background IO completes.
+ *
+ * If resync/recovery is interrupted, returns -EINTR;
+ * Otherwise, returns 0.
  */
-static sector_t raise_barrier(struct r1conf *conf, sector_t sector_nr)
+static int raise_barrier(struct r1conf *conf, sector_t sector_nr)
 {
 	int idx = sector_to_idx(sector_nr);
 
@@ -1612,12 +1617,12 @@ static void raid1_error(struct mddev *mddev, struct md_rdev *rdev)
 
 	/*
 	 * If it is not operational, then we have already marked it as dead
-	 * else if it is the last working disks, ignore the error, let the
-	 * next level up know.
+	 * else if it is the last working disks with "fail_last_dev == false",
+	 * ignore the error, let the next level up know.
 	 * else mark the drive as failed
 	 */
 	spin_lock_irqsave(&conf->device_lock, flags);
-	if (test_bit(In_sync, &rdev->flags)
+	if (test_bit(In_sync, &rdev->flags) && !mddev->fail_last_dev
 	    && (conf->raid_disks - mddev->degraded) == 1) {
 		/*
 		 * Don't fail the drive, act as though we were just a
@@ -1901,6 +1906,22 @@ static void abort_sync_write(struct mddev *mddev, struct r1bio *r1_bio)
 	} while (sectors_to_go > 0);
 }
 
+static void put_sync_write_buf(struct r1bio *r1_bio, int uptodate)
+{
+	if (atomic_dec_and_test(&r1_bio->remaining)) {
+		struct mddev *mddev = r1_bio->mddev;
+		int s = r1_bio->sectors;
+
+		if (test_bit(R1BIO_MadeGood, &r1_bio->state) ||
+		    test_bit(R1BIO_WriteError, &r1_bio->state))
+			reschedule_retry(r1_bio);
+		else {
+			put_buf(r1_bio);
+			md_done_sync(mddev, s, uptodate);
+		}
+	}
+}
+
 static void end_sync_write(struct bio *bio)
 {
 	int uptodate = !bio->bi_status;
@@ -1927,16 +1948,7 @@ static void end_sync_write(struct bio *bio)
 		)
 		set_bit(R1BIO_MadeGood, &r1_bio->state);
 
-	if (atomic_dec_and_test(&r1_bio->remaining)) {
-		int s = r1_bio->sectors;
-		if (test_bit(R1BIO_MadeGood, &r1_bio->state) ||
-		    test_bit(R1BIO_WriteError, &r1_bio->state))
-			reschedule_retry(r1_bio);
-		else {
-			put_buf(r1_bio);
-			md_done_sync(mddev, s, uptodate);
-		}
-	}
+	put_sync_write_buf(r1_bio, uptodate);
 }
 
 static int r1_sync_page_io(struct md_rdev *rdev, sector_t sector,
@@ -2219,17 +2231,7 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio)
 		generic_make_request(wbio);
 	}
 
-	if (atomic_dec_and_test(&r1_bio->remaining)) {
-		/* if we're here, all write(s) have completed, so clean up */
-		int s = r1_bio->sectors;
-		if (test_bit(R1BIO_MadeGood, &r1_bio->state) ||
-		    test_bit(R1BIO_WriteError, &r1_bio->state))
-			reschedule_retry(r1_bio);
-		else {
-			put_buf(r1_bio);
-			md_done_sync(mddev, s, 1);
-		}
-	}
+	put_sync_write_buf(r1_bio, 1);
 }
 
 /*
@@ -3127,6 +3129,13 @@ static int raid1_run(struct mddev *mddev)
 		    !test_bit(In_sync, &conf->mirrors[i].rdev->flags) ||
 		    test_bit(Faulty, &conf->mirrors[i].rdev->flags))
 			mddev->degraded++;
+	/*
+	 * RAID1 needs at least one disk in active
+	 */
+	if (conf->raid_disks - mddev->degraded < 1) {
+		ret = -EINVAL;
+		goto abort;
+	}
 
 	if (conf->raid_disks - mddev->degraded == 1)
 		mddev->recovery_cp = MaxSector;
@@ -3160,8 +3169,12 @@ static int raid1_run(struct mddev *mddev)
 	ret = md_integrity_register(mddev);
 	if (ret) {
 		md_unregister_thread(&mddev->thread);
-		raid1_free(mddev, conf);
+		goto abort;
 	}
+	return 0;
+
+abort:
+	raid1_free(mddev, conf);
 	return ret;
 }