Merge tag 'block-6.5-2023-08-11' of git://git.kernel.dk/linux

Pull block fixes from Jens Axboe:

 - NVMe pull request via Keith:
      - Fixes for request_queue state (Ming)
      - Another uuid quirk (August)

 - RCU poll fix for NVMe (Ming)

 - Fix for an IO stall with polled IO (me)

 - Fix for blk-iocost stats enable/disable accounting (Chengming)

 - Regression fix for large pages for zram (Christoph)

* tag 'block-6.5-2023-08-11' of git://git.kernel.dk/linux:
  nvme: core: don't hold rcu read lock in nvme_ns_chr_uring_cmd_iopoll
  blk-iocost: fix queue stats accounting
  block: don't make REQ_POLLED imply REQ_NOWAIT
  block: get rid of unused plug->nowait flag
  zram: take device and not only bvec offset into account
  nvme-pci: add NVME_QUIRK_BOGUS_NID for Samsung PM9B1 256G and 512G
  nvme-rdma: fix potential unbalanced freeze & unfreeze
  nvme-tcp: fix potential unbalanced freeze & unfreeze
  nvme: fix possible hang when removing a controller during error recovery

block/blk-core.c

@@ -722,14 +722,9 @@ void submit_bio_noacct(struct bio *bio)
 	struct block_device *bdev = bio->bi_bdev;
 	struct request_queue *q = bdev_get_queue(bdev);
 	blk_status_t status = BLK_STS_IOERR;
-	struct blk_plug *plug;
 
 	might_sleep();
 
-	plug = blk_mq_plug(bio);
-	if (plug && plug->nowait)
-		bio->bi_opf |= REQ_NOWAIT;
-
 	/*
 	 * For a REQ_NOWAIT based request, return -EOPNOTSUPP
 	 * if queue does not support NOWAIT.
@@ -1059,7 +1054,6 @@ void blk_start_plug_nr_ios(struct blk_plug *plug, unsigned short nr_ios)
 	plug->rq_count = 0;
 	plug->multiple_queues = false;
 	plug->has_elevator = false;
-	plug->nowait = false;
 	INIT_LIST_HEAD(&plug->cb_list);
 
 	/*

block/blk-iocost.c

@@ -3301,11 +3301,12 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input,
 	if (qos[QOS_MIN] > qos[QOS_MAX])
 		goto einval;
 
-	if (enable) {
+	if (enable && !ioc->enabled) {
 		blk_stat_enable_accounting(disk->queue);
 		blk_queue_flag_set(QUEUE_FLAG_RQ_ALLOC_TIME, disk->queue);
 		ioc->enabled = true;
-	} else {
+	} else if (!enable && ioc->enabled) {
+		blk_stat_disable_accounting(disk->queue);
 		blk_queue_flag_clear(QUEUE_FLAG_RQ_ALLOC_TIME, disk->queue);
 		ioc->enabled = false;
 	}

block/fops.c

@@ -358,13 +358,14 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 		task_io_account_write(bio->bi_iter.bi_size);
 	}
 
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		bio->bi_opf |= REQ_NOWAIT;
+
 	if (iocb->ki_flags & IOCB_HIPRI) {
-		bio->bi_opf |= REQ_POLLED | REQ_NOWAIT;
+		bio->bi_opf |= REQ_POLLED;
 		submit_bio(bio);
 		WRITE_ONCE(iocb->private, bio);
 	} else {
-		if (iocb->ki_flags & IOCB_NOWAIT)
-			bio->bi_opf |= REQ_NOWAIT;
 		submit_bio(bio);
 	}
 	return -EIOCBQUEUED;

drivers/block/zram/zram_drv.c

@@ -1870,15 +1870,16 @@ static void zram_bio_discard(struct zram *zram, struct bio *bio)
 
 static void zram_bio_read(struct zram *zram, struct bio *bio)
 {
-	struct bvec_iter iter;
-	struct bio_vec bv;
-	unsigned long start_time;
+	unsigned long start_time = bio_start_io_acct(bio);
+	struct bvec_iter iter = bio->bi_iter;
 
-	start_time = bio_start_io_acct(bio);
-	bio_for_each_segment(bv, bio, iter) {
+	do {
 		u32 index = iter.bi_sector >> SECTORS_PER_PAGE_SHIFT;
 		u32 offset = (iter.bi_sector & (SECTORS_PER_PAGE - 1)) <<
 				SECTOR_SHIFT;
+		struct bio_vec bv = bio_iter_iovec(bio, iter);
+
+		bv.bv_len = min_t(u32, bv.bv_len, PAGE_SIZE - offset);
 
 		if (zram_bvec_read(zram, &bv, index, offset, bio) < 0) {
 			atomic64_inc(&zram->stats.failed_reads);
@@ -1890,22 +1891,26 @@ static void zram_bio_read(struct zram *zram, struct bio *bio)
 		zram_slot_lock(zram, index);
 		zram_accessed(zram, index);
 		zram_slot_unlock(zram, index);
-	}
+
+		bio_advance_iter_single(bio, &iter, bv.bv_len);
+	} while (iter.bi_size);
+
 	bio_end_io_acct(bio, start_time);
 	bio_endio(bio);
 }
 
 static void zram_bio_write(struct zram *zram, struct bio *bio)
 {
-	struct bvec_iter iter;
-	struct bio_vec bv;
-	unsigned long start_time;
+	unsigned long start_time = bio_start_io_acct(bio);
+	struct bvec_iter iter = bio->bi_iter;
 
-	start_time = bio_start_io_acct(bio);
-	bio_for_each_segment(bv, bio, iter) {
+	do {
 		u32 index = iter.bi_sector >> SECTORS_PER_PAGE_SHIFT;
 		u32 offset = (iter.bi_sector & (SECTORS_PER_PAGE - 1)) <<
 				SECTOR_SHIFT;
+		struct bio_vec bv = bio_iter_iovec(bio, iter);
+
+		bv.bv_len = min_t(u32, bv.bv_len, PAGE_SIZE - offset);
 
 		if (zram_bvec_write(zram, &bv, index, offset, bio) < 0) {
 			atomic64_inc(&zram->stats.failed_writes);
@@ -1916,7 +1921,10 @@ static void zram_bio_write(struct zram *zram, struct bio *bio)
 		zram_slot_lock(zram, index);
 		zram_accessed(zram, index);
 		zram_slot_unlock(zram, index);
-	}
+
+		bio_advance_iter_single(bio, &iter, bv.bv_len);
+	} while (iter.bi_size);
+
 	bio_end_io_acct(bio, start_time);
 	bio_endio(bio);
 }

drivers/nvme/host/core.c

@@ -3933,6 +3933,12 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
 	 */
 	nvme_mpath_clear_ctrl_paths(ctrl);
 
+	/*
+	 * Unquiesce io queues so any pending IO won't hang, especially
+	 * those submitted from scan work
+	 */
+	nvme_unquiesce_io_queues(ctrl);
+
 	/* prevent racing with ns scanning */
 	flush_work(&ctrl->scan_work);
 
@@ -3942,10 +3948,8 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
 	 * removing the namespaces' disks; fail all the queues now to avoid
 	 * potentially having to clean up the failed sync later.
 	 */
-	if (ctrl->state == NVME_CTRL_DEAD) {
+	if (ctrl->state == NVME_CTRL_DEAD)
 		nvme_mark_namespaces_dead(ctrl);
-		nvme_unquiesce_io_queues(ctrl);
-	}
 
 	/* this is a no-op when called from the controller reset handler */
 	nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING_NOIO);

drivers/nvme/host/ioctl.c

@@ -786,11 +786,9 @@ int nvme_ns_chr_uring_cmd_iopoll(struct io_uring_cmd *ioucmd,
 	if (!(ioucmd->flags & IORING_URING_CMD_POLLED))
 		return 0;
 
-	rcu_read_lock();
 	req = READ_ONCE(ioucmd->cookie);
 	if (req && blk_rq_is_poll(req))
 		ret = blk_rq_poll(req, iob, poll_flags);
-	rcu_read_unlock();
 	return ret;
 }
 #ifdef CONFIG_NVME_MULTIPATH

drivers/nvme/host/pci.c

@@ -3402,7 +3402,8 @@ static const struct pci_device_id nvme_id_table[] = {
 	{ PCI_DEVICE(0x1d97, 0x2263),   /* SPCC */
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x144d, 0xa80b),   /* Samsung PM9B1 256G and 512G */
-		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES |
+				NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x144d, 0xa809),   /* Samsung MZALQ256HBJD 256G */
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x144d, 0xa802),   /* Samsung SM953 */

drivers/nvme/host/rdma.c

@@ -883,6 +883,7 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
 		goto out_cleanup_tagset;
 
 	if (!new) {
+		nvme_start_freeze(&ctrl->ctrl);
 		nvme_unquiesce_io_queues(&ctrl->ctrl);
 		if (!nvme_wait_freeze_timeout(&ctrl->ctrl, NVME_IO_TIMEOUT)) {
 			/*
@@ -891,6 +892,7 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
 			 * to be safe.
 			 */
 			ret = -ENODEV;
+			nvme_unfreeze(&ctrl->ctrl);
 			goto out_wait_freeze_timed_out;
 		}
 		blk_mq_update_nr_hw_queues(ctrl->ctrl.tagset,
@@ -940,7 +942,6 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
 	if (ctrl->ctrl.queue_count > 1) {
-		nvme_start_freeze(&ctrl->ctrl);
 		nvme_quiesce_io_queues(&ctrl->ctrl);
 		nvme_sync_io_queues(&ctrl->ctrl);
 		nvme_rdma_stop_io_queues(ctrl);

drivers/nvme/host/tcp.c

@@ -1868,6 +1868,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
 		goto out_cleanup_connect_q;
 
 	if (!new) {
+		nvme_start_freeze(ctrl);
 		nvme_unquiesce_io_queues(ctrl);
 		if (!nvme_wait_freeze_timeout(ctrl, NVME_IO_TIMEOUT)) {
 			/*
@@ -1876,6 +1877,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
 			 * to be safe.
 			 */
 			ret = -ENODEV;
+			nvme_unfreeze(ctrl);
 			goto out_wait_freeze_timed_out;
 		}
 		blk_mq_update_nr_hw_queues(ctrl->tagset,
@@ -1980,7 +1982,6 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 	if (ctrl->queue_count <= 1)
 		return;
 	nvme_quiesce_admin_queue(ctrl);
-	nvme_start_freeze(ctrl);
 	nvme_quiesce_io_queues(ctrl);
 	nvme_sync_io_queues(ctrl);
 	nvme_tcp_stop_io_queues(ctrl);

include/linux/bio.h

@@ -791,7 +791,7 @@ static inline int bio_integrity_add_page(struct bio *bio, struct page *page,
 static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb)
 {
 	bio->bi_opf |= REQ_POLLED;
-	if (!is_sync_kiocb(kiocb))
+	if (kiocb->ki_flags & IOCB_NOWAIT)
 		bio->bi_opf |= REQ_NOWAIT;
 }
 

include/linux/blkdev.h

@@ -969,7 +969,6 @@ struct blk_plug {
 
 	bool multiple_queues;
 	bool has_elevator;
-	bool nowait;
 
 	struct list_head cb_list; /* md requires an unplug callback */
 };