Merge branch 'for-5.18/drivers' into for-5.18/write-streams

* for-5.18/drivers: (51 commits)
  bcache: fixup multiple threads crash
  bcache: fixup bcache_dev_sectors_dirty_add() multithreaded CPU false sharing
  floppy: use memcpy_{to,from}_bvec
  drbd: use bvec_kmap_local in recv_dless_read
  drbd: use bvec_kmap_local in drbd_csum_bio
  bcache: use bvec_kmap_local in bio_csum
  nvdimm-btt: use bvec_kmap_local in btt_rw_integrity
  nvdimm-blk: use bvec_kmap_local in nd_blk_rw_integrity
  zram: use memcpy_from_bvec in zram_bvec_write
  zram: use memcpy_to_bvec in zram_bvec_read
  aoe: use bvec_kmap_local in bvcpy
  iss-simdisk: use bvec_kmap_local in simdisk_submit_bio
  nvme: check that EUI/GUID/UUID are globally unique
  nvme: check for duplicate identifiers earlier
  nvme: fix the check for duplicate unique identifiers
  nvme: cleanup __nvme_check_ids
  nvme: remove nssa from struct nvme_ctrl
  nvme: explicitly set non-error for directives
  nvme: expose cntrltype and dctype through sysfs
  nvme: send uevent on connection up
  ...

Author: axboe

arch/xtensa/platforms/iss/simdisk.c

@@ -108,13 +108,13 @@ static void simdisk_submit_bio(struct bio *bio)
 	sector_t sector = bio->bi_iter.bi_sector;
 
 	bio_for_each_segment(bvec, bio, iter) {
-		char *buffer = kmap_atomic(bvec.bv_page) + bvec.bv_offset;
+		char *buffer = bvec_kmap_local(&bvec);
 		unsigned len = bvec.bv_len >> SECTOR_SHIFT;
 
 		simdisk_transfer(dev, sector, len, buffer,
 				bio_data_dir(bio) == WRITE);
 		sector += len;
-		kunmap_atomic(buffer);
+		kunmap_local(buffer);
 	}
 
 	bio_endio(bio);

drivers/block/aoe/aoecmd.c

@@ -1018,9 +1018,9 @@ bvcpy(struct sk_buff *skb, struct bio *bio, struct bvec_iter iter, long cnt)
 	iter.bi_size = cnt;
 
 	__bio_for_each_segment(bv, bio, iter, iter) {
-		char *p = kmap_atomic(bv.bv_page) + bv.bv_offset;
+		char *p = bvec_kmap_local(&bv);
 		skb_copy_bits(skb, soff, p, bv.bv_len);
-		kunmap_atomic(p);
+		kunmap_local(p);
 		soff += bv.bv_len;
 	}
 }

drivers/block/drbd/drbd_receiver.c

@@ -2017,10 +2017,10 @@ static int recv_dless_read(struct drbd_peer_device *peer_device, struct drbd_req
 	D_ASSERT(peer_device->device, sector == bio->bi_iter.bi_sector);
 
 	bio_for_each_segment(bvec, bio, iter) {
-		void *mapped = kmap(bvec.bv_page) + bvec.bv_offset;
+		void *mapped = bvec_kmap_local(&bvec);
 		expect = min_t(int, data_size, bvec.bv_len);
 		err = drbd_recv_all_warn(peer_device->connection, mapped, expect);
-		kunmap(bvec.bv_page);
+		kunmap_local(mapped);
 		if (err)
 			return err;
 		data_size -= expect;

drivers/block/drbd/drbd_worker.c

@@ -326,9 +326,9 @@ void drbd_csum_bio(struct crypto_shash *tfm, struct bio *bio, void *digest)
 	bio_for_each_segment(bvec, bio, iter) {
 		u8 *src;
 
-		src = kmap_atomic(bvec.bv_page);
-		crypto_shash_update(desc, src + bvec.bv_offset, bvec.bv_len);
-		kunmap_atomic(src);
+		src = bvec_kmap_local(&bvec);
+		crypto_shash_update(desc, src, bvec.bv_len);
+		kunmap_local(src);
 
 		/* REQ_OP_WRITE_SAME has only one segment,
 		 * checksum the payload only once. */

drivers/block/floppy.c

@@ -2485,11 +2485,9 @@ static void copy_buffer(int ssize, int max_sector, int max_sector_2)
 		}
 
 		if (CT(raw_cmd->cmd[COMMAND]) == FD_READ)
-			memcpy_to_page(bv.bv_page, bv.bv_offset, dma_buffer,
-				       size);
+			memcpy_to_bvec(&bv, dma_buffer);
 		else
-			memcpy_from_page(dma_buffer, bv.bv_page, bv.bv_offset,
-					 size);
+			memcpy_from_bvec(dma_buffer, &bv);
 
 		remaining -= size;
 		dma_buffer += size;

drivers/block/loop.c

@@ -86,6 +86,7 @@
 #include <linux/uaccess.h>
 
 #define LOOP_IDLE_WORKER_TIMEOUT (60 * HZ)
+#define LOOP_DEFAULT_HW_Q_DEPTH (128)
 
 static DEFINE_IDR(loop_index_idr);
 static DEFINE_MUTEX(loop_ctl_mutex);
@@ -309,12 +310,11 @@ static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos,
 	 * a.k.a. discard/zerorange.
 	 */
 	struct file *file = lo->lo_backing_file;
-	struct request_queue *q = lo->lo_queue;
 	int ret;
 
 	mode |= FALLOC_FL_KEEP_SIZE;
 
-	if (!blk_queue_discard(q)) {
+	if (!blk_queue_discard(lo->lo_queue)) {
 		ret = -EOPNOTSUPP;
 		goto out;
 	}
@@ -328,8 +328,7 @@ static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos,
 
 static int lo_req_flush(struct loop_device *lo, struct request *rq)
 {
-	struct file *file = lo->lo_backing_file;
-	int ret = vfs_fsync(file, 0);
+	int ret = vfs_fsync(lo->lo_backing_file, 0);
 	if (unlikely(ret && ret != -EINVAL))
 		ret = -EIO;
 
@@ -681,33 +680,33 @@ static ssize_t loop_attr_backing_file_show(struct loop_device *lo, char *buf)
 
 static ssize_t loop_attr_offset_show(struct loop_device *lo, char *buf)
 {
-	return sprintf(buf, "%llu\n", (unsigned long long)lo->lo_offset);
+	return sysfs_emit(buf, "%llu\n", (unsigned long long)lo->lo_offset);
 }
 
 static ssize_t loop_attr_sizelimit_show(struct loop_device *lo, char *buf)
 {
-	return sprintf(buf, "%llu\n", (unsigned long long)lo->lo_sizelimit);
+	return sysfs_emit(buf, "%llu\n", (unsigned long long)lo->lo_sizelimit);
 }
 
 static ssize_t loop_attr_autoclear_show(struct loop_device *lo, char *buf)
 {
 	int autoclear = (lo->lo_flags & LO_FLAGS_AUTOCLEAR);
 
-	return sprintf(buf, "%s\n", autoclear ? "1" : "0");
+	return sysfs_emit(buf, "%s\n", autoclear ? "1" : "0");
 }
 
 static ssize_t loop_attr_partscan_show(struct loop_device *lo, char *buf)
 {
 	int partscan = (lo->lo_flags & LO_FLAGS_PARTSCAN);
 
-	return sprintf(buf, "%s\n", partscan ? "1" : "0");
+	return sysfs_emit(buf, "%s\n", partscan ? "1" : "0");
 }
 
 static ssize_t loop_attr_dio_show(struct loop_device *lo, char *buf)
 {
 	int dio = (lo->lo_flags & LO_FLAGS_DIRECT_IO);
 
-	return sprintf(buf, "%s\n", dio ? "1" : "0");
+	return sysfs_emit(buf, "%s\n", dio ? "1" : "0");
 }
 
 LOOP_ATTR_RO(backing_file);
@@ -1261,7 +1260,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	if (size_changed && lo->lo_device->bd_inode->i_mapping->nrpages) {
 		/* If any pages were dirtied after invalidate_bdev(), try again */
 		err = -EAGAIN;
-		pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n",
+		pr_warn("%s: loop%d (%s) still has dirty pages (nrpages=%lu)\n",
 			__func__, lo->lo_number, lo->lo_file_name,
 			lo->lo_device->bd_inode->i_mapping->nrpages);
 		goto out_unfreeze;
@@ -1481,7 +1480,7 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
 	/* invalidate_bdev should have truncated all the pages */
 	if (lo->lo_device->bd_inode->i_mapping->nrpages) {
 		err = -EAGAIN;
-		pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n",
+		pr_warn("%s: loop%d (%s) still has dirty pages (nrpages=%lu)\n",
 			__func__, lo->lo_number, lo->lo_file_name,
 			lo->lo_device->bd_inode->i_mapping->nrpages);
 		goto out_unfreeze;
@@ -1786,6 +1785,24 @@ module_param(max_loop, int, 0444);
 MODULE_PARM_DESC(max_loop, "Maximum number of loop devices");
 module_param(max_part, int, 0444);
 MODULE_PARM_DESC(max_part, "Maximum number of partitions per loop device");
+
+static int hw_queue_depth = LOOP_DEFAULT_HW_Q_DEPTH;
+
+static int loop_set_hw_queue_depth(const char *s, const struct kernel_param *p)
+{
+	int ret = kstrtoint(s, 10, &hw_queue_depth);
+
+	return (ret || (hw_queue_depth < 1)) ? -EINVAL : 0;
+}
+
+static const struct kernel_param_ops loop_hw_qdepth_param_ops = {
+	.set	= loop_set_hw_queue_depth,
+	.get	= param_get_int,
+};
+
+device_param_cb(hw_queue_depth, &loop_hw_qdepth_param_ops, &hw_queue_depth, 0444);
+MODULE_PARM_DESC(hw_queue_depth, "Queue depth for each hardware queue. Default: 128");
+
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR);
 
@@ -1980,7 +1997,7 @@ static int loop_add(int i)
 
 	lo->tag_set.ops = &loop_mq_ops;
 	lo->tag_set.nr_hw_queues = 1;
-	lo->tag_set.queue_depth = 128;
+	lo->tag_set.queue_depth = hw_queue_depth;
 	lo->tag_set.numa_node = NUMA_NO_NODE;
 	lo->tag_set.cmd_size = sizeof(struct loop_cmd);
 	lo->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_STACKING |

drivers/block/null_blk/main.c

@@ -431,9 +431,10 @@ static ssize_t nullb_device_power_store(struct config_item *item,
 	if (!dev->power && newp) {
 		if (test_and_set_bit(NULLB_DEV_FL_UP, &dev->flags))
 			return count;
-		if (null_add_dev(dev)) {
+		ret = null_add_dev(dev);
+		if (ret) {
 			clear_bit(NULLB_DEV_FL_UP, &dev->flags);
-			return -ENOMEM;
+			return ret;
 		}
 
 		set_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags);
@@ -719,26 +720,25 @@ static struct nullb_cmd *__alloc_cmd(struct nullb_queue *nq)
 	return NULL;
 }
 
-static struct nullb_cmd *alloc_cmd(struct nullb_queue *nq, int can_wait)
+static struct nullb_cmd *alloc_cmd(struct nullb_queue *nq, struct bio *bio)
 {
 	struct nullb_cmd *cmd;
 	DEFINE_WAIT(wait);
 
-	cmd = __alloc_cmd(nq);
-	if (cmd || !can_wait)
-		return cmd;
-
 	do {
-		prepare_to_wait(&nq->wait, &wait, TASK_UNINTERRUPTIBLE);
+		/*
+		 * This avoids multiple return statements, multiple calls to
+		 * __alloc_cmd() and a fast path call to prepare_to_wait().
+		 */
 		cmd = __alloc_cmd(nq);
-		if (cmd)
-			break;
-
+		if (cmd) {
+			cmd->bio = bio;
+			return cmd;
+		}
+		prepare_to_wait(&nq->wait, &wait, TASK_UNINTERRUPTIBLE);
 		io_schedule();
+		finish_wait(&nq->wait, &wait);
 	} while (1);
-
-	finish_wait(&nq->wait, &wait);
-	return cmd;
 }
 
 static void end_cmd(struct nullb_cmd *cmd)
@@ -777,24 +777,22 @@ static void null_complete_rq(struct request *rq)
 	end_cmd(blk_mq_rq_to_pdu(rq));
 }
 
-static struct nullb_page *null_alloc_page(gfp_t gfp_flags)
+static struct nullb_page *null_alloc_page(void)
 {
 	struct nullb_page *t_page;
 
-	t_page = kmalloc(sizeof(struct nullb_page), gfp_flags);
+	t_page = kmalloc(sizeof(struct nullb_page), GFP_NOIO);
 	if (!t_page)
-		goto out;
+		return NULL;
 
-	t_page->page = alloc_pages(gfp_flags, 0);
-	if (!t_page->page)
-		goto out_freepage;
+	t_page->page = alloc_pages(GFP_NOIO, 0);
+	if (!t_page->page) {
+		kfree(t_page);
+		return NULL;
+	}
 
 	memset(t_page->bitmap, 0, sizeof(t_page->bitmap));
 	return t_page;
-out_freepage:
-	kfree(t_page);
-out:
-	return NULL;
 }
 
 static void null_free_page(struct nullb_page *t_page)
@@ -932,7 +930,7 @@ static struct nullb_page *null_insert_page(struct nullb *nullb,
 
 	spin_unlock_irq(&nullb->lock);
 
-	t_page = null_alloc_page(GFP_NOIO);
+	t_page = null_alloc_page();
 	if (!t_page)
 		goto out_lock;
 
@@ -1476,12 +1474,8 @@ static void null_submit_bio(struct bio *bio)
 	sector_t nr_sectors = bio_sectors(bio);
 	struct nullb *nullb = bio->bi_bdev->bd_disk->private_data;
 	struct nullb_queue *nq = nullb_to_queue(nullb);
-	struct nullb_cmd *cmd;
-
-	cmd = alloc_cmd(nq, 1);
-	cmd->bio = bio;
 
-	null_handle_cmd(cmd, sector, nr_sectors, bio_op(bio));
+	null_handle_cmd(alloc_cmd(nq, bio), sector, nr_sectors, bio_op(bio));
 }
 
 static bool should_timeout_request(struct request *rq)

drivers/block/rnbd/rnbd-clt.c

@@ -23,7 +23,6 @@ MODULE_LICENSE("GPL");
 
 static int rnbd_client_major;
 static DEFINE_IDA(index_ida);
-static DEFINE_MUTEX(ida_lock);
 static DEFINE_MUTEX(sess_lock);
 static LIST_HEAD(sess_list);
 
@@ -55,9 +54,7 @@ static void rnbd_clt_put_dev(struct rnbd_clt_dev *dev)
 	if (!refcount_dec_and_test(&dev->refcount))
 		return;
 
-	mutex_lock(&ida_lock);
-	ida_simple_remove(&index_ida, dev->clt_device_id);
-	mutex_unlock(&ida_lock);
+	ida_free(&index_ida, dev->clt_device_id);
 	kfree(dev->hw_queues);
 	kfree(dev->pathname);
 	rnbd_clt_put_sess(dev->sess);
@@ -87,7 +84,6 @@ static int rnbd_clt_set_dev_attr(struct rnbd_clt_dev *dev,
 	dev->discard_granularity    = le32_to_cpu(rsp->discard_granularity);
 	dev->discard_alignment	    = le32_to_cpu(rsp->discard_alignment);
 	dev->secure_discard	    = le16_to_cpu(rsp->secure_discard);
-	dev->rotational		    = rsp->rotational;
 	dev->wc			    = !!(rsp->cache_policy & RNBD_WRITEBACK);
 	dev->fua		    = !!(rsp->cache_policy & RNBD_FUA);
 
@@ -1262,9 +1258,9 @@ find_and_get_or_create_sess(const char *sessname,
 	struct rtrs_clt_ops rtrs_ops;
 
 	sess = find_or_create_sess(sessname, &first);
-	if (sess == ERR_PTR(-ENOMEM))
+	if (sess == ERR_PTR(-ENOMEM)) {
 		return ERR_PTR(-ENOMEM);
-	else if ((nr_poll_queues && !first) ||  (!nr_poll_queues && sess->nr_poll_queues)) {
+	} else if ((nr_poll_queues && !first) ||  (!nr_poll_queues && sess->nr_poll_queues)) {
 		/*
 		 * A device MUST have its own session to use the polling-mode.
 		 * It must fail to map new device with the same session.
@@ -1410,8 +1406,10 @@ static int rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, int idx)
 		dev->read_only = false;
 	}
 
-	if (!dev->rotational)
-		blk_queue_flag_set(QUEUE_FLAG_NONROT, dev->queue);
+	/*
+	 * Network device does not need rotational
+	 */
+	blk_queue_flag_set(QUEUE_FLAG_NONROT, dev->queue);
 	err = add_disk(dev->gd);
 	if (err)
 		blk_cleanup_disk(dev->gd);
@@ -1459,10 +1457,8 @@ static struct rnbd_clt_dev *init_dev(struct rnbd_clt_session *sess,
 		goto out_alloc;
 	}
 
-	mutex_lock(&ida_lock);
-	ret = ida_simple_get(&index_ida, 0, 1 << (MINORBITS - RNBD_PART_BITS),
-			     GFP_KERNEL);
-	mutex_unlock(&ida_lock);
+	ret = ida_alloc_max(&index_ida, 1 << (MINORBITS - RNBD_PART_BITS),
+			    GFP_KERNEL);
 	if (ret < 0) {
 		pr_err("Failed to initialize device '%s' from session %s, allocating idr failed, err: %d\n",
 		       pathname, sess->sessname, ret);
@@ -1610,13 +1606,13 @@ struct rnbd_clt_dev *rnbd_clt_map_device(const char *sessname,
 	}
 
 	rnbd_clt_info(dev,
-		       "map_device: Device mapped as %s (nsectors: %zu, logical_block_size: %d, physical_block_size: %d, max_write_same_sectors: %d, max_discard_sectors: %d, discard_granularity: %d, discard_alignment: %d, secure_discard: %d, max_segments: %d, max_hw_sectors: %d, rotational: %d, wc: %d, fua: %d)\n",
+		       "map_device: Device mapped as %s (nsectors: %zu, logical_block_size: %d, physical_block_size: %d, max_write_same_sectors: %d, max_discard_sectors: %d, discard_granularity: %d, discard_alignment: %d, secure_discard: %d, max_segments: %d, max_hw_sectors: %d, wc: %d, fua: %d)\n",
 		       dev->gd->disk_name, dev->nsectors,
 		       dev->logical_block_size, dev->physical_block_size,
 		       dev->max_write_same_sectors, dev->max_discard_sectors,
 		       dev->discard_granularity, dev->discard_alignment,
 		       dev->secure_discard, dev->max_segments,
-		       dev->max_hw_sectors, dev->rotational, dev->wc, dev->fua);
+		       dev->max_hw_sectors, dev->wc, dev->fua);
 
 	mutex_unlock(&dev->lock);
 	rnbd_clt_put_sess(sess);

drivers/block/rnbd/rnbd-clt.h

@@ -118,7 +118,6 @@ struct rnbd_clt_dev {
 	enum rnbd_access_mode	access_mode;
 	u32			nr_poll_queues;
 	bool			read_only;
-	bool			rotational;
 	bool			wc;
 	bool			fua;
 	u32			max_hw_sectors;