Merge tag 'for-5.15/drivers-2021-08-30' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "Sitting on top of the core block changes, here are the driver changes
  for the 5.15 merge window:

   - NVMe updates via Christoph:
       - suspend improvements for devices with an HMB (Keith Busch)
       - handle double completions more gacefull (Sagi Grimberg)
       - cleanup the selects for the nvme core code a bit (Sagi Grimberg)
       - don't update queue count when failing to set io queues (Ruozhu Li)
       - various nvmet connect fixes (Amit Engel)
       - cleanup lightnvm leftovers (Keith Busch, me)
       - small cleanups (Colin Ian King, Hou Pu)
       - add tracing for the Set Features command (Hou Pu)
       - CMB sysfs cleanups (Keith Busch)
       - add a mutex_destroy call (Keith Busch)

   - remove lightnvm subsystem. It's served its purpose and ultimately
     led to zoned nvme support, we no longer need it (Christoph)

   - revert floppy O_NDELAY fix (Denis)

   - nbd fixes (Hou, Pavel, Baokun)

   - nbd locking fixes (Tetsuo)

   - nbd device removal fixes (Christoph)

   - raid10 rcu warning fix (Xiao)

   - raid1 write behind fix (Guoqing)

   - rnbd fixes (Gioh, Md Haris)

   - misc fixes (Colin)"

* tag 'for-5.15/drivers-2021-08-30' of git://git.kernel.dk/linux-block: (42 commits)
  Revert "floppy: reintroduce O_NDELAY fix"
  raid1: ensure write behind bio has less than BIO_MAX_VECS sectors
  md/raid10: Remove unnecessary rcu_dereference in raid10_handle_discard
  nbd: remove nbd->destroy_complete
  nbd: only return usable devices from nbd_find_unused
  nbd: set nbd->index before releasing nbd_index_mutex
  nbd: prevent IDR lookups from finding partially initialized devices
  nbd: reset NBD to NULL when restarting in nbd_genl_connect
  nbd: add missing locking to the nbd_dev_add error path
  nvme: remove the unused NVME_NS_* enum
  nvme: remove nvm_ndev from ns
  nvme: Have NVME_FABRICS select NVME_CORE instead of transport drivers
  block: nbd: add sanity check for first_minor
  nvmet: check that host sqsize does not exceed ctrl MQES
  nvmet: avoid duplicate qid in connect cmd
  nvmet: pass back cntlid on successful completion
  nvme-rdma: don't update queue count when failing to set io queues
  nvme-tcp: don't update queue count when failing to set io queues
  nvme-tcp: pair send_mutex init with destroy
  nvme: allow user toggling hmb usage
  ...

Documentation/driver-api/index.rst

@@ -85,7 +85,6 @@ available subsections can be seen below.
    io-mapping
    io_ordering
    generic-counter
-   lightnvm-pblk
    memory-devices/index
    men-chameleon-bus
    ntb

Documentation/driver-api/lightnvm-pblk.rst

-pblk: Physical Block Device Target
-==================================
-
-pblk implements a fully associative, host-based FTL that exposes a traditional
-block I/O interface. Its primary responsibilities are:
-
-  - Map logical addresses onto physical addresses (4KB granularity) in a
-    logical-to-physical (L2P) table.
-  - Maintain the integrity and consistency of the L2P table as well as its
-    recovery from normal tear down and power outage.
-  - Deal with controller- and media-specific constrains.
-  - Handle I/O errors.
-  - Implement garbage collection.
-  - Maintain consistency across the I/O stack during synchronization points.
-
-For more information please refer to:
-
-  http://lightnvm.io
-
-which maintains updated FAQs, manual pages, technical documentation, tools,
-contacts, etc.

Documentation/userspace-api/ioctl/ioctl-number.rst

@@ -160,7 +160,6 @@ Code  Seq#    Include File                                           Comments
 'K'   all    linux/kd.h
 'L'   00-1F  linux/loop.h                                            conflict!
 'L'   10-1F  drivers/scsi/mpt3sas/mpt3sas_ctl.h                      conflict!
-'L'   20-2F  linux/lightnvm.h
 'L'   E0-FF  linux/ppdd.h                                            encrypted disk device driver
                                                                      <http://linux01.gwdg.de/~alatham/ppdd.html>
 'M'   all    linux/soundcard.h                                       conflict!

MAINTAINERS

@@ -10619,15 +10619,6 @@ F:	LICENSES/
 F:	scripts/spdxcheck-test.sh
 F:	scripts/spdxcheck.py
 
-LIGHTNVM PLATFORM SUPPORT
-M:	Matias Bjorling <mb@lightnvm.io>
-L:	linux-block@vger.kernel.org
-S:	Maintained
-W:	http://github/OpenChannelSSD
-F:	drivers/lightnvm/
-F:	include/linux/lightnvm.h
-F:	include/uapi/linux/lightnvm.h
-
 LINEAR RANGES HELPERS
 M:	Mark Brown <broonie@kernel.org>
 R:	Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>

drivers/Kconfig

@@ -51,8 +51,6 @@ source "drivers/net/Kconfig"
 
 source "drivers/isdn/Kconfig"
 
-source "drivers/lightnvm/Kconfig"
-
 # input before char - char/joystick depends on it. As does USB.
 
 source "drivers/input/Kconfig"

drivers/Makefile

@@ -70,7 +70,6 @@ obj-$(CONFIG_FB_I810)           += video/fbdev/i810/
 obj-$(CONFIG_FB_INTEL)          += video/fbdev/intelfb/
 
 obj-$(CONFIG_PARPORT)		+= parport/
-obj-$(CONFIG_NVM)		+= lightnvm/
 obj-y				+= base/ block/ misc/ mfd/ nfc/
 obj-$(CONFIG_LIBNVDIMM)		+= nvdimm/
 obj-$(CONFIG_DAX)		+= dax/

drivers/block/floppy.c

@@ -4029,9 +4029,11 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 	if (fdc_state[FDC(drive)].rawcmd == 1)
 		fdc_state[FDC(drive)].rawcmd = 2;
 
+	if (!(mode & FMODE_NDELAY)) {
 		if (mode & (FMODE_READ|FMODE_WRITE)) {
 			drive_state[drive].last_checked = 0;
-		clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &drive_state[drive].flags);
+			clear_bit(FD_OPEN_SHOULD_FAIL_BIT,
+				  &drive_state[drive].flags);
 			if (bdev_check_media_change(bdev))
 				floppy_revalidate(bdev->bd_disk);
 			if (test_bit(FD_DISK_CHANGED_BIT, &drive_state[drive].flags))
@@ -4039,13 +4041,11 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 			if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &drive_state[drive].flags))
 				goto out;
 		}
-
 		res = -EROFS;
-
 		if ((mode & FMODE_WRITE) &&
 		    !test_bit(FD_DISK_WRITABLE_BIT, &drive_state[drive].flags))
 			goto out;
-
+	}
 	mutex_unlock(&open_lock);
 	mutex_unlock(&floppy_mutex);
 	return 0;

drivers/block/nbd.c

@@ -49,6 +49,7 @@
 
 static DEFINE_IDR(nbd_index_idr);
 static DEFINE_MUTEX(nbd_index_mutex);
+static struct workqueue_struct *nbd_del_wq;
 static int nbd_total_devices = 0;
 
 struct nbd_sock {
@@ -113,12 +114,12 @@ struct nbd_device {
 	struct mutex config_lock;
 	struct gendisk *disk;
 	struct workqueue_struct *recv_workq;
+	struct work_struct remove_work;
 
 	struct list_head list;
 	struct task_struct *task_recv;
 	struct task_struct *task_setup;
 
-	struct completion *destroy_complete;
 	unsigned long flags;
 
 	char *backend;
@@ -237,32 +238,36 @@ static void nbd_dev_remove(struct nbd_device *nbd)
 {
 	struct gendisk *disk = nbd->disk;
 
-	if (disk) {
 	del_gendisk(disk);
 	blk_cleanup_disk(disk);
 	blk_mq_free_tag_set(&nbd->tag_set);
-	}
 
 	/*
-	 * Place this in the last just before the nbd is freed to
-	 * make sure that the disk and the related kobject are also
-	 * totally removed to avoid duplicate creation of the same
-	 * one.
+	 * Remove from idr after del_gendisk() completes, so if the same ID is
+	 * reused, the following add_disk() will succeed.
 	 */
-	if (test_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags) && nbd->destroy_complete)
-		complete(nbd->destroy_complete);
+	mutex_lock(&nbd_index_mutex);
+	idr_remove(&nbd_index_idr, nbd->index);
+	mutex_unlock(&nbd_index_mutex);
 
 	kfree(nbd);
 }
 
+static void nbd_dev_remove_work(struct work_struct *work)
+{
+	nbd_dev_remove(container_of(work, struct nbd_device, remove_work));
+}
+
 static void nbd_put(struct nbd_device *nbd)
 {
-	if (refcount_dec_and_mutex_lock(&nbd->refs,
-					&nbd_index_mutex)) {
-		idr_remove(&nbd_index_idr, nbd->index);
+	if (!refcount_dec_and_test(&nbd->refs))
+		return;
+
+	/* Call del_gendisk() asynchrounously to prevent deadlock */
+	if (test_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags))
+		queue_work(nbd_del_wq, &nbd->remove_work);
+	else
 		nbd_dev_remove(nbd);
-		mutex_unlock(&nbd_index_mutex);
-	}
 }
 
 static int nbd_disconnected(struct nbd_config *config)
@@ -1388,6 +1393,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 		       unsigned int cmd, unsigned long arg)
 {
 	struct nbd_config *config = nbd->config;
+	loff_t bytesize;
 
 	switch (cmd) {
 	case NBD_DISCONNECT:
@@ -1402,8 +1408,9 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 	case NBD_SET_SIZE:
 		return nbd_set_size(nbd, arg, config->blksize);
 	case NBD_SET_SIZE_BLOCKS:
-		return nbd_set_size(nbd, arg * config->blksize,
-				    config->blksize);
+		if (check_mul_overflow((loff_t)arg, config->blksize, &bytesize))
+			return -EINVAL;
+		return nbd_set_size(nbd, bytesize, config->blksize);
 	case NBD_SET_TIMEOUT:
 		nbd_set_cmd_timeout(nbd, arg);
 		return 0;
@@ -1665,7 +1672,7 @@ static const struct blk_mq_ops nbd_mq_ops = {
 	.timeout	= nbd_xmit_timeout,
 };
 
-static int nbd_dev_add(int index)
+static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
 {
 	struct nbd_device *nbd;
 	struct gendisk *disk;
@@ -1683,13 +1690,14 @@ static int nbd_dev_add(int index)
 	nbd->tag_set.flags = BLK_MQ_F_SHOULD_MERGE |
 		BLK_MQ_F_BLOCKING;
 	nbd->tag_set.driver_data = nbd;
-	nbd->destroy_complete = NULL;
+	INIT_WORK(&nbd->remove_work, nbd_dev_remove_work);
 	nbd->backend = NULL;
 
 	err = blk_mq_alloc_tag_set(&nbd->tag_set);
 	if (err)
 		goto out_free_nbd;
 
+	mutex_lock(&nbd_index_mutex);
 	if (index >= 0) {
 		err = idr_alloc(&nbd_index_idr, nbd, index, index + 1,
 				GFP_KERNEL);
@@ -1700,9 +1708,10 @@ static int nbd_dev_add(int index)
 		if (err >= 0)
 			index = err;
 	}
+	nbd->index = index;
+	mutex_unlock(&nbd_index_mutex);
 	if (err < 0)
 		goto out_free_tags;
-	nbd->index = index;
 
 	disk = blk_mq_alloc_disk(&nbd->tag_set, NULL);
 	if (IS_ERR(disk)) {
@@ -1726,38 +1735,65 @@ static int nbd_dev_add(int index)
 
 	mutex_init(&nbd->config_lock);
 	refcount_set(&nbd->config_refs, 0);
-	refcount_set(&nbd->refs, 1);
+	/*
+	 * Start out with a zero references to keep other threads from using
+	 * this device until it is fully initialized.
+	 */
+	refcount_set(&nbd->refs, 0);
 	INIT_LIST_HEAD(&nbd->list);
 	disk->major = NBD_MAJOR;
+
+	/* Too big first_minor can cause duplicate creation of
+	 * sysfs files/links, since first_minor will be truncated to
+	 * byte in __device_add_disk().
+	 */
 	disk->first_minor = index << part_shift;
+	if (disk->first_minor > 0xff) {
+		err = -EINVAL;
+		goto out_free_idr;
+	}
+
 	disk->minors = 1 << part_shift;
 	disk->fops = &nbd_fops;
 	disk->private_data = nbd;
 	sprintf(disk->disk_name, "nbd%d", index);
 	add_disk(disk);
+
+	/*
+	 * Now publish the device.
+	 */
+	refcount_set(&nbd->refs, refs);
 	nbd_total_devices++;
-	return index;
+	return nbd;
 
 out_free_idr:
+	mutex_lock(&nbd_index_mutex);
 	idr_remove(&nbd_index_idr, index);
+	mutex_unlock(&nbd_index_mutex);
 out_free_tags:
 	blk_mq_free_tag_set(&nbd->tag_set);
 out_free_nbd:
 	kfree(nbd);
 out:
-	return err;
+	return ERR_PTR(err);
 }
 
-static int find_free_cb(int id, void *ptr, void *data)
+static struct nbd_device *nbd_find_get_unused(void)
 {
-	struct nbd_device *nbd = ptr;
-	struct nbd_device **found = data;
+	struct nbd_device *nbd;
+	int id;
+
+	lockdep_assert_held(&nbd_index_mutex);
 
-	if (!refcount_read(&nbd->config_refs)) {
-		*found = nbd;
-		return 1;
+	idr_for_each_entry(&nbd_index_idr, nbd, id) {
+		if (refcount_read(&nbd->config_refs) ||
+		    test_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags))
+			continue;
+		if (refcount_inc_not_zero(&nbd->refs))
+			return nbd;
 	}
-	return 0;
+
+	return NULL;
 }
 
 /* Netlink interface. */
@@ -1806,8 +1842,7 @@ static int nbd_genl_size_set(struct genl_info *info, struct nbd_device *nbd)
 
 static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
 {
-	DECLARE_COMPLETION_ONSTACK(destroy_complete);
-	struct nbd_device *nbd = NULL;
+	struct nbd_device *nbd;
 	struct nbd_config *config;
 	int index = -1;
 	int ret;
@@ -1829,55 +1864,29 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
 again:
 	mutex_lock(&nbd_index_mutex);
 	if (index == -1) {
-		ret = idr_for_each(&nbd_index_idr, &find_free_cb, &nbd);
-		if (ret == 0) {
-			int new_index;
-			new_index = nbd_dev_add(-1);
-			if (new_index < 0) {
-				mutex_unlock(&nbd_index_mutex);
-				printk(KERN_ERR "nbd: failed to add new device\n");
-				return new_index;
-			}
-			nbd = idr_find(&nbd_index_idr, new_index);
-		}
+		nbd = nbd_find_get_unused();
 	} else {
 		nbd = idr_find(&nbd_index_idr, index);
-		if (!nbd) {
-			ret = nbd_dev_add(index);
-			if (ret < 0) {
+		if (nbd) {
+			if ((test_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags) &&
+			     test_bit(NBD_DISCONNECT_REQUESTED, &nbd->flags)) ||
+			    !refcount_inc_not_zero(&nbd->refs)) {
 				mutex_unlock(&nbd_index_mutex);
-				printk(KERN_ERR "nbd: failed to add new device\n");
-				return ret;
-			}
-			nbd = idr_find(&nbd_index_idr, index);
-		}
-	}
-	if (!nbd) {
-		printk(KERN_ERR "nbd: couldn't find device at index %d\n",
+				pr_err("nbd: device at index %d is going down\n",
 					index);
-		mutex_unlock(&nbd_index_mutex);
 				return -EINVAL;
 			}
-
-	if (test_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags) &&
-	    test_bit(NBD_DISCONNECT_REQUESTED, &nbd->flags)) {
-		nbd->destroy_complete = &destroy_complete;
+		}
+	}
 	mutex_unlock(&nbd_index_mutex);
 
-		/* Wait untill the the nbd stuff is totally destroyed */
-		wait_for_completion(&destroy_complete);
-		goto again;
+	if (!nbd) {
+		nbd = nbd_dev_add(index, 2);
+		if (IS_ERR(nbd)) {
+			pr_err("nbd: failed to add new device\n");
+			return PTR_ERR(nbd);
 		}
-
-	if (!refcount_inc_not_zero(&nbd->refs)) {
-		mutex_unlock(&nbd_index_mutex);
-		if (index == -1)
-			goto again;
-		printk(KERN_ERR "nbd: device at index %d is going down\n",
-		       index);
-		return -EINVAL;
 	}
-	mutex_unlock(&nbd_index_mutex);
 
 	mutex_lock(&nbd->config_lock);
 	if (refcount_read(&nbd->config_refs)) {
@@ -2424,16 +2433,21 @@ static int __init nbd_init(void)
 	if (register_blkdev(NBD_MAJOR, "nbd"))
 		return -EIO;
 
+	nbd_del_wq = alloc_workqueue("nbd-del", WQ_UNBOUND, 0);
+	if (!nbd_del_wq) {
+		unregister_blkdev(NBD_MAJOR, "nbd");
+		return -ENOMEM;
+	}
+
 	if (genl_register_family(&nbd_genl_family)) {
+		destroy_workqueue(nbd_del_wq);
 		unregister_blkdev(NBD_MAJOR, "nbd");
 		return -EINVAL;
 	}
 	nbd_dbg_init();
 
-	mutex_lock(&nbd_index_mutex);
 	for (i = 0; i < nbds_max; i++)
-		nbd_dev_add(i);
-	mutex_unlock(&nbd_index_mutex);
+		nbd_dev_add(i, 1);
 	return 0;
 }
 
@@ -2442,7 +2456,10 @@ static int nbd_exit_cb(int id, void *ptr, void *data)
 	struct list_head *list = (struct list_head *)data;
 	struct nbd_device *nbd = ptr;
 
+	/* Skip nbd that is being removed asynchronously */
+	if (refcount_read(&nbd->refs))
 		list_add_tail(&nbd->list, list);
+
 	return 0;
 }
 
@@ -2465,6 +2482,9 @@ static void __exit nbd_cleanup(void)
 		nbd_put(nbd);
 	}
 
+	/* Also wait for nbd_dev_remove_work() completes */
+	destroy_workqueue(nbd_del_wq);
+
 	idr_destroy(&nbd_index_idr);
 	genl_unregister_family(&nbd_genl_family);
 	unregister_blkdev(NBD_MAJOR, "nbd");

drivers/block/rnbd/rnbd-clt-sysfs.c

@@ -227,17 +227,17 @@ static ssize_t state_show(struct kobject *kobj,
 
 	switch (dev->dev_state) {
 	case DEV_STATE_INIT:
-		return snprintf(page, PAGE_SIZE, "init\n");
+		return sysfs_emit(page, "init\n");
 	case DEV_STATE_MAPPED:
 		/* TODO fix cli tool before changing to proper state */
-		return snprintf(page, PAGE_SIZE, "open\n");
+		return sysfs_emit(page, "open\n");
 	case DEV_STATE_MAPPED_DISCONNECTED:
 		/* TODO fix cli tool before changing to proper state */
-		return snprintf(page, PAGE_SIZE, "closed\n");
+		return sysfs_emit(page, "closed\n");
 	case DEV_STATE_UNMAPPED:
-		return snprintf(page, PAGE_SIZE, "unmapped\n");
+		return sysfs_emit(page, "unmapped\n");
 	default:
-		return snprintf(page, PAGE_SIZE, "unknown\n");
+		return sysfs_emit(page, "unknown\n");
 	}
 }
 
@@ -263,7 +263,7 @@ static ssize_t mapping_path_show(struct kobject *kobj,
 
 	dev = container_of(kobj, struct rnbd_clt_dev, kobj);
 
-	return scnprintf(page, PAGE_SIZE, "%s\n", dev->pathname);
+	return sysfs_emit(page, "%s\n", dev->pathname);
 }
 
 static struct kobj_attribute rnbd_clt_mapping_path_attr =
@@ -276,8 +276,7 @@ static ssize_t access_mode_show(struct kobject *kobj,
 
 	dev = container_of(kobj, struct rnbd_clt_dev, kobj);
 
-	return snprintf(page, PAGE_SIZE, "%s\n",
-			rnbd_access_mode_str(dev->access_mode));
+	return sysfs_emit(page, "%s\n", rnbd_access_mode_str(dev->access_mode));
 }
 
 static struct kobj_attribute rnbd_clt_access_mode =
@@ -286,7 +285,7 @@ static struct kobj_attribute rnbd_clt_access_mode =
 static ssize_t rnbd_clt_unmap_dev_show(struct kobject *kobj,
 					struct kobj_attribute *attr, char *page)
 {
-	return scnprintf(page, PAGE_SIZE, "Usage: echo <normal|force> > %s\n",
+	return sysfs_emit(page, "Usage: echo <normal|force> > %s\n",
 			  attr->attr.name);
 }
 
@@ -357,8 +356,7 @@ static ssize_t rnbd_clt_resize_dev_show(struct kobject *kobj,
 					 struct kobj_attribute *attr,
 					 char *page)
 {
-	return scnprintf(page, PAGE_SIZE,
-			 "Usage: echo <new size in sectors> > %s\n",
+	return sysfs_emit(page, "Usage: echo <new size in sectors> > %s\n",
 			  attr->attr.name);
 }
 
@@ -390,8 +388,7 @@ static struct kobj_attribute rnbd_clt_resize_dev_attr =
 static ssize_t rnbd_clt_remap_dev_show(struct kobject *kobj,
 					struct kobj_attribute *attr, char *page)
 {
-	return scnprintf(page, PAGE_SIZE, "Usage: echo <1> > %s\n",
-			 attr->attr.name);
+	return sysfs_emit(page, "Usage: echo <1> > %s\n", attr->attr.name);
 }
 
 static ssize_t rnbd_clt_remap_dev_store(struct kobject *kobj,
@@ -436,7 +433,7 @@ static ssize_t session_show(struct kobject *kobj, struct kobj_attribute *attr,
 
 	dev = container_of(kobj, struct rnbd_clt_dev, kobj);
 
-	return scnprintf(page, PAGE_SIZE, "%s\n", dev->sess->sessname);
+	return sysfs_emit(page, "%s\n", dev->sess->sessname);
 }
 
 static struct kobj_attribute rnbd_clt_session_attr =
@@ -499,7 +496,7 @@ static ssize_t rnbd_clt_map_device_show(struct kobject *kobj,
 					 struct kobj_attribute *attr,
 					 char *page)
 {
-	return scnprintf(page, PAGE_SIZE,
+	return sysfs_emit(page,
 			  "Usage: echo \"[dest_port=server port number] sessname=<name of the rtrs session> path=<[srcaddr@]dstaddr> [path=<[srcaddr@]dstaddr>] device_path=<full path on remote side> [access_mode=<ro|rw|migration>] [nr_poll_queues=<number of queues>]\" > %s\n\naddr ::= [ ip:<ipv4> | ip:<ipv6> | gid:<gid> ]\n",
 			 attr->attr.name);
 }

drivers/block/rnbd/rnbd-clt.c

@@ -271,7 +271,7 @@ static bool rnbd_rerun_if_needed(struct rnbd_clt_session *sess)
 	 */
 	if (cpu_q)
 		*cpup = cpu_q->cpu;
-	put_cpu_var(sess->cpu_rr);
+	put_cpu_ptr(sess->cpu_rr);
 
 	if (q)
 		rnbd_clt_dev_requeue(q);

drivers/block/rnbd/rnbd-srv-sysfs.c

@@ -90,7 +90,7 @@ static ssize_t read_only_show(struct kobject *kobj, struct kobj_attribute *attr,
 
 	sess_dev = container_of(kobj, struct rnbd_srv_sess_dev, kobj);
 
-	return scnprintf(page, PAGE_SIZE, "%d\n",
+	return sysfs_emit(page, "%d\n",
 			  !(sess_dev->open_flags & FMODE_WRITE));
 }
 
@@ -105,7 +105,7 @@ static ssize_t access_mode_show(struct kobject *kobj,
 
 	sess_dev = container_of(kobj, struct rnbd_srv_sess_dev, kobj);
 
-	return scnprintf(page, PAGE_SIZE, "%s\n",
+	return sysfs_emit(page, "%s\n",
 			  rnbd_access_mode_str(sess_dev->access_mode));
 }
 
@@ -119,7 +119,7 @@ static ssize_t mapping_path_show(struct kobject *kobj,
 
 	sess_dev = container_of(kobj, struct rnbd_srv_sess_dev, kobj);
 
-	return scnprintf(page, PAGE_SIZE, "%s\n", sess_dev->pathname);
+	return sysfs_emit(page, "%s\n", sess_dev->pathname);
 }
 
 static struct kobj_attribute rnbd_srv_dev_session_mapping_path_attr =
@@ -128,7 +128,7 @@ static struct kobj_attribute rnbd_srv_dev_session_mapping_path_attr =
 static ssize_t rnbd_srv_dev_session_force_close_show(struct kobject *kobj,
 					struct kobj_attribute *attr, char *page)
 {
-	return scnprintf(page, PAGE_SIZE, "Usage: echo 1 > %s\n",
+	return sysfs_emit(page, "Usage: echo 1 > %s\n",
 			  attr->attr.name);
 }
 

drivers/block/xen-blkfront.c

@@ -1092,7 +1092,6 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 	err = xlbd_reserve_minors(minor, nr_minors);
 	if (err)
 		return err;
-	err = -ENODEV;
 
 	memset(&info->tag_set, 0, sizeof(info->tag_set));
 	info->tag_set.ops = &blkfront_mq_ops;

drivers/lightnvm/Kconfig

-# SPDX-License-Identifier: GPL-2.0-only
-#
-# Open-Channel SSD NVM configuration
-#
-
-menuconfig NVM
-	bool "Open-Channel SSD target support (DEPRECATED)"
-	depends on BLOCK
-	help
-	  Say Y here to get to enable Open-channel SSDs.
-
-	  Open-Channel SSDs implement a set of extension to SSDs, that
-	  exposes direct access to the underlying non-volatile memory.
-
-	  If you say N, all options in this submenu will be skipped and disabled
-	  only do this if you know what you are doing.
-
-	  This code is deprecated and will be removed in Linux 5.15.
-
-if NVM
-
-config NVM_PBLK
-	tristate "Physical Block Device Open-Channel SSD target"
-	select CRC32
-	help
-	  Allows an open-channel SSD to be exposed as a block device to the
-	  host. The target assumes the device exposes raw flash and must be
-	  explicitly managed by the host.
-
-	  Please note the disk format is considered EXPERIMENTAL for now.
-
-if NVM_PBLK
-
-config NVM_PBLK_DEBUG
-	bool "PBlk Debug Support"
-	default n
-	help
-	  Enables debug support for pblk. This includes extra checks, more
-	  vocal error messages, and extra tracking fields in the pblk sysfs
-	  entries.
-
-endif # NVM_PBLK_DEBUG
-
-endif # NVM

drivers/lightnvm/Makefile

-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile for Open-Channel SSDs.
-#
-
-obj-$(CONFIG_NVM)		:= core.o
-obj-$(CONFIG_NVM_PBLK)		+= pblk.o
-pblk-y				:= pblk-init.o pblk-core.o pblk-rb.o \
-				   pblk-write.o pblk-cache.o pblk-read.o \
-				   pblk-gc.o pblk-recovery.o pblk-map.o \
-				   pblk-rl.o pblk-sysfs.o

drivers/lightnvm/pblk-cache.c

-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2016 CNEX Labs
- * Initial release: Javier Gonzalez <javier@cnexlabs.com>
- *                  Matias Bjorling <matias@cnexlabs.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version
- * 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * pblk-cache.c - pblk's write cache
- */
-
-#include "pblk.h"
-
-void pblk_write_to_cache(struct pblk *pblk, struct bio *bio,
-				unsigned long flags)
-{
-	struct pblk_w_ctx w_ctx;
-	sector_t lba = pblk_get_lba(bio);
-	unsigned long start_time;
-	unsigned int bpos, pos;
-	int nr_entries = pblk_get_secs(bio);
-	int i, ret;
-
-	start_time = bio_start_io_acct(bio);
-
-	/* Update the write buffer head (mem) with the entries that we can
-	 * write. The write in itself cannot fail, so there is no need to
-	 * rollback from here on.
-	 */
-retry:
-	ret = pblk_rb_may_write_user(&pblk->rwb, bio, nr_entries, &bpos);
-	switch (ret) {
-	case NVM_IO_REQUEUE:
-		io_schedule();
-		goto retry;
-	case NVM_IO_ERR:
-		pblk_pipeline_stop(pblk);
-		bio_io_error(bio);
-		goto out;
-	}
-
-	pblk_ppa_set_empty(&w_ctx.ppa);
-	w_ctx.flags = flags;
-	if (bio->bi_opf & REQ_PREFLUSH) {
-		w_ctx.flags |= PBLK_FLUSH_ENTRY;
-		pblk_write_kick(pblk);
-	}
-
-	if (unlikely(!bio_has_data(bio)))
-		goto out;
-
-	for (i = 0; i < nr_entries; i++) {
-		void *data = bio_data(bio);
-
-		w_ctx.lba = lba + i;
-
-		pos = pblk_rb_wrap_pos(&pblk->rwb, bpos + i);
-		pblk_rb_write_entry_user(&pblk->rwb, data, w_ctx, pos);
-
-		bio_advance(bio, PBLK_EXPOSED_PAGE_SIZE);
-	}
-
-	atomic64_add(nr_entries, &pblk->user_wa);
-
-#ifdef CONFIG_NVM_PBLK_DEBUG
-	atomic_long_add(nr_entries, &pblk->inflight_writes);
-	atomic_long_add(nr_entries, &pblk->req_writes);
-#endif
-
-	pblk_rl_inserted(&pblk->rl, nr_entries);
-
-out:
-	bio_end_io_acct(bio, start_time);
-	pblk_write_should_kick(pblk);
-
-	if (ret == NVM_IO_DONE)
-		bio_endio(bio);
-}
-
-/*
- * On GC the incoming lbas are not necessarily sequential. Also, some of the
- * lbas might not be valid entries, which are marked as empty by the GC thread
- */
-int pblk_write_gc_to_cache(struct pblk *pblk, struct pblk_gc_rq *gc_rq)
-{
-	struct pblk_w_ctx w_ctx;
-	unsigned int bpos, pos;
-	void *data = gc_rq->data;
-	int i, valid_entries;
-
-	/* Update the write buffer head (mem) with the entries that we can
-	 * write. The write in itself cannot fail, so there is no need to
-	 * rollback from here on.
-	 */
-retry:
-	if (!pblk_rb_may_write_gc(&pblk->rwb, gc_rq->secs_to_gc, &bpos)) {
-		io_schedule();
-		goto retry;
-	}
-
-	w_ctx.flags = PBLK_IOTYPE_GC;
-	pblk_ppa_set_empty(&w_ctx.ppa);
-
-	for (i = 0, valid_entries = 0; i < gc_rq->nr_secs; i++) {
-		if (gc_rq->lba_list[i] == ADDR_EMPTY)
-			continue;
-
-		w_ctx.lba = gc_rq->lba_list[i];
-
-		pos = pblk_rb_wrap_pos(&pblk->rwb, bpos + valid_entries);
-		pblk_rb_write_entry_gc(&pblk->rwb, data, w_ctx, gc_rq->line,
-						gc_rq->paddr_list[i], pos);
-
-		data += PBLK_EXPOSED_PAGE_SIZE;
-		valid_entries++;
-	}
-
-	WARN_ONCE(gc_rq->secs_to_gc != valid_entries,
-					"pblk: inconsistent GC write\n");
-
-	atomic64_add(valid_entries, &pblk->gc_wa);
-
-#ifdef CONFIG_NVM_PBLK_DEBUG
-	atomic_long_add(valid_entries, &pblk->inflight_writes);
-	atomic_long_add(valid_entries, &pblk->recov_gc_writes);
-#endif
-
-	pblk_write_should_kick(pblk);
-	return NVM_IO_OK;
-}

drivers/lightnvm/pblk-map.c

-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2016 CNEX Labs
- * Initial release: Javier Gonzalez <javier@cnexlabs.com>
- *                  Matias Bjorling <matias@cnexlabs.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version
- * 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * pblk-map.c - pblk's lba-ppa mapping strategy
- *
- */
-
-#include "pblk.h"
-
-static int pblk_map_page_data(struct pblk *pblk, unsigned int sentry,
-			      struct ppa_addr *ppa_list,
-			      unsigned long *lun_bitmap,
-			      void *meta_list,
-			      unsigned int valid_secs)
-{
-	struct pblk_line *line = pblk_line_get_data(pblk);
-	struct pblk_emeta *emeta;
-	struct pblk_w_ctx *w_ctx;
-	__le64 *lba_list;
-	u64 paddr;
-	int nr_secs = pblk->min_write_pgs;
-	int i;
-
-	if (!line)
-		return -ENOSPC;
-
-	if (pblk_line_is_full(line)) {
-		struct pblk_line *prev_line = line;
-
-		/* If we cannot allocate a new line, make sure to store metadata
-		 * on current line and then fail
-		 */
-		line = pblk_line_replace_data(pblk);
-		pblk_line_close_meta(pblk, prev_line);
-
-		if (!line) {
-			pblk_pipeline_stop(pblk);
-			return -ENOSPC;
-		}
-
-	}
-
-	emeta = line->emeta;
-	lba_list = emeta_to_lbas(pblk, emeta->buf);
-
-	paddr = pblk_alloc_page(pblk, line, nr_secs);
-
-	for (i = 0; i < nr_secs; i++, paddr++) {
-		struct pblk_sec_meta *meta = pblk_get_meta(pblk, meta_list, i);
-		__le64 addr_empty = cpu_to_le64(ADDR_EMPTY);
-
-		/* ppa to be sent to the device */
-		ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line->id);
-
-		/* Write context for target bio completion on write buffer. Note
-		 * that the write buffer is protected by the sync backpointer,
-		 * and a single writer thread have access to each specific entry
-		 * at a time. Thus, it is safe to modify the context for the
-		 * entry we are setting up for submission without taking any
-		 * lock or memory barrier.
-		 */
-		if (i < valid_secs) {
-			kref_get(&line->ref);
-			atomic_inc(&line->sec_to_update);
-			w_ctx = pblk_rb_w_ctx(&pblk->rwb, sentry + i);
-			w_ctx->ppa = ppa_list[i];
-			meta->lba = cpu_to_le64(w_ctx->lba);
-			lba_list[paddr] = cpu_to_le64(w_ctx->lba);
-			if (lba_list[paddr] != addr_empty)
-				line->nr_valid_lbas++;
-			else
-				atomic64_inc(&pblk->pad_wa);
-		} else {
-			lba_list[paddr] = addr_empty;
-			meta->lba = addr_empty;
-			__pblk_map_invalidate(pblk, line, paddr);
-		}
-	}
-
-	pblk_down_rq(pblk, ppa_list[0], lun_bitmap);
-	return 0;
-}
-
-int pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
-		 unsigned long *lun_bitmap, unsigned int valid_secs,
-		 unsigned int off)
-{
-	void *meta_list = pblk_get_meta_for_writes(pblk, rqd);
-	void *meta_buffer;
-	struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd);
-	unsigned int map_secs;
-	int min = pblk->min_write_pgs;
-	int i;
-	int ret;
-
-	for (i = off; i < rqd->nr_ppas; i += min) {
-		map_secs = (i + min > valid_secs) ? (valid_secs % min) : min;
-		meta_buffer = pblk_get_meta(pblk, meta_list, i);
-
-		ret = pblk_map_page_data(pblk, sentry + i, &ppa_list[i],
-					lun_bitmap, meta_buffer, map_secs);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-/* only if erase_ppa is set, acquire erase semaphore */
-int pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd,
-		       unsigned int sentry, unsigned long *lun_bitmap,
-		       unsigned int valid_secs, struct ppa_addr *erase_ppa)
-{
-	struct nvm_tgt_dev *dev = pblk->dev;
-	struct nvm_geo *geo = &dev->geo;
-	struct pblk_line_meta *lm = &pblk->lm;
-	void *meta_list = pblk_get_meta_for_writes(pblk, rqd);
-	void *meta_buffer;
-	struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd);
-	struct pblk_line *e_line, *d_line;
-	unsigned int map_secs;
-	int min = pblk->min_write_pgs;
-	int i, erase_lun;
-	int ret;
-
-
-	for (i = 0; i < rqd->nr_ppas; i += min) {
-		map_secs = (i + min > valid_secs) ? (valid_secs % min) : min;
-		meta_buffer = pblk_get_meta(pblk, meta_list, i);
-
-		ret = pblk_map_page_data(pblk, sentry + i, &ppa_list[i],
-					lun_bitmap, meta_buffer, map_secs);
-		if (ret)
-			return ret;
-
-		erase_lun = pblk_ppa_to_pos(geo, ppa_list[i]);
-
-		/* line can change after page map. We might also be writing the
-		 * last line.
-		 */
-		e_line = pblk_line_get_erase(pblk);
-		if (!e_line)
-			return pblk_map_rq(pblk, rqd, sentry, lun_bitmap,
-							valid_secs, i + min);
-
-		spin_lock(&e_line->lock);
-		if (!test_bit(erase_lun, e_line->erase_bitmap)) {
-			set_bit(erase_lun, e_line->erase_bitmap);
-			atomic_dec(&e_line->left_eblks);
-
-			*erase_ppa = ppa_list[i];
-			erase_ppa->a.blk = e_line->id;
-			erase_ppa->a.reserved = 0;
-
-			spin_unlock(&e_line->lock);
-
-			/* Avoid evaluating e_line->left_eblks */
-			return pblk_map_rq(pblk, rqd, sentry, lun_bitmap,
-							valid_secs, i + min);
-		}
-		spin_unlock(&e_line->lock);
-	}
-
-	d_line = pblk_line_get_data(pblk);
-
-	/* line can change after page map. We might also be writing the
-	 * last line.
-	 */
-	e_line = pblk_line_get_erase(pblk);
-	if (!e_line)
-		return -ENOSPC;
-
-	/* Erase blocks that are bad in this line but might not be in next */
-	if (unlikely(pblk_ppa_empty(*erase_ppa)) &&
-			bitmap_weight(d_line->blk_bitmap, lm->blk_per_line)) {
-		int bit = -1;
-
-retry:
-		bit = find_next_bit(d_line->blk_bitmap,
-						lm->blk_per_line, bit + 1);
-		if (bit >= lm->blk_per_line)
-			return 0;
-
-		spin_lock(&e_line->lock);
-		if (test_bit(bit, e_line->erase_bitmap)) {
-			spin_unlock(&e_line->lock);
-			goto retry;
-		}
-		spin_unlock(&e_line->lock);
-
-		set_bit(bit, e_line->erase_bitmap);
-		atomic_dec(&e_line->left_eblks);
-		*erase_ppa = pblk->luns[bit].bppa; /* set ch and lun */
-		erase_ppa->a.blk = e_line->id;
-	}
-
-	return 0;
-}

drivers/lightnvm/pblk-rl.c

-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2016 CNEX Labs
- * Initial release: Javier Gonzalez <javier@cnexlabs.com>
- *                  Matias Bjorling <matias@cnexlabs.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version
- * 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * pblk-rl.c - pblk's rate limiter for user I/O
- *
- */
-
-#include "pblk.h"
-
-static void pblk_rl_kick_u_timer(struct pblk_rl *rl)
-{
-	mod_timer(&rl->u_timer, jiffies + msecs_to_jiffies(5000));
-}
-
-int pblk_rl_is_limit(struct pblk_rl *rl)
-{
-	int rb_space;
-
-	rb_space = atomic_read(&rl->rb_space);
-
-	return (rb_space == 0);
-}
-
-int pblk_rl_user_may_insert(struct pblk_rl *rl, int nr_entries)
-{
-	int rb_user_cnt = atomic_read(&rl->rb_user_cnt);
-	int rb_space = atomic_read(&rl->rb_space);
-
-	if (unlikely(rb_space >= 0) && (rb_space - nr_entries < 0))
-		return NVM_IO_ERR;
-
-	if (rb_user_cnt >= rl->rb_user_max)
-		return NVM_IO_REQUEUE;
-
-	return NVM_IO_OK;
-}
-
-void pblk_rl_inserted(struct pblk_rl *rl, int nr_entries)
-{
-	int rb_space = atomic_read(&rl->rb_space);
-
-	if (unlikely(rb_space >= 0))
-		atomic_sub(nr_entries, &rl->rb_space);
-}
-
-int pblk_rl_gc_may_insert(struct pblk_rl *rl, int nr_entries)
-{
-	int rb_gc_cnt = atomic_read(&rl->rb_gc_cnt);
-	int rb_user_active;
-
-	/* If there is no user I/O let GC take over space on the write buffer */
-	rb_user_active = READ_ONCE(rl->rb_user_active);
-	return (!(rb_gc_cnt >= rl->rb_gc_max && rb_user_active));
-}
-
-void pblk_rl_user_in(struct pblk_rl *rl, int nr_entries)
-{
-	atomic_add(nr_entries, &rl->rb_user_cnt);
-
-	/* Release user I/O state. Protect from GC */
-	smp_store_release(&rl->rb_user_active, 1);
-	pblk_rl_kick_u_timer(rl);
-}
-
-void pblk_rl_werr_line_in(struct pblk_rl *rl)
-{
-	atomic_inc(&rl->werr_lines);
-}
-
-void pblk_rl_werr_line_out(struct pblk_rl *rl)
-{
-	atomic_dec(&rl->werr_lines);
-}
-
-void pblk_rl_gc_in(struct pblk_rl *rl, int nr_entries)
-{
-	atomic_add(nr_entries, &rl->rb_gc_cnt);
-}
-
-void pblk_rl_out(struct pblk_rl *rl, int nr_user, int nr_gc)
-{
-	atomic_sub(nr_user, &rl->rb_user_cnt);
-	atomic_sub(nr_gc, &rl->rb_gc_cnt);
-}
-
-unsigned long pblk_rl_nr_free_blks(struct pblk_rl *rl)
-{
-	return atomic_read(&rl->free_blocks);
-}
-
-unsigned long pblk_rl_nr_user_free_blks(struct pblk_rl *rl)
-{
-	return atomic_read(&rl->free_user_blocks);
-}
-
-static void __pblk_rl_update_rates(struct pblk_rl *rl,
-				   unsigned long free_blocks)
-{
-	struct pblk *pblk = container_of(rl, struct pblk, rl);
-	int max = rl->rb_budget;
-	int werr_gc_needed = atomic_read(&rl->werr_lines);
-
-	if (free_blocks >= rl->high) {
-		if (werr_gc_needed) {
-			/* Allocate a small budget for recovering
-			 * lines with write errors
-			 */
-			rl->rb_gc_max = 1 << rl->rb_windows_pw;
-			rl->rb_user_max = max - rl->rb_gc_max;
-			rl->rb_state = PBLK_RL_WERR;
-		} else {
-			rl->rb_user_max = max;
-			rl->rb_gc_max = 0;
-			rl->rb_state = PBLK_RL_OFF;
-		}
-	} else if (free_blocks < rl->high) {
-		int shift = rl->high_pw - rl->rb_windows_pw;
-		int user_windows = free_blocks >> shift;
-		int user_max = user_windows << ilog2(NVM_MAX_VLBA);
-
-		rl->rb_user_max = user_max;
-		rl->rb_gc_max = max - user_max;
-
-		if (free_blocks <= rl->rsv_blocks) {
-			rl->rb_user_max = 0;
-			rl->rb_gc_max = max;
-		}
-
-		/* In the worst case, we will need to GC lines in the low list
-		 * (high valid sector count). If there are lines to GC on high
-		 * or mid lists, these will be prioritized
-		 */
-		rl->rb_state = PBLK_RL_LOW;
-	}
-
-	if (rl->rb_state != PBLK_RL_OFF)
-		pblk_gc_should_start(pblk);
-	else
-		pblk_gc_should_stop(pblk);
-}
-
-void pblk_rl_update_rates(struct pblk_rl *rl)
-{
-	__pblk_rl_update_rates(rl, pblk_rl_nr_user_free_blks(rl));
-}
-
-void pblk_rl_free_lines_inc(struct pblk_rl *rl, struct pblk_line *line)
-{
-	int blk_in_line = atomic_read(&line->blk_in_line);
-	int free_blocks;
-
-	atomic_add(blk_in_line, &rl->free_blocks);
-	free_blocks = atomic_add_return(blk_in_line, &rl->free_user_blocks);
-
-	__pblk_rl_update_rates(rl, free_blocks);
-}
-
-void pblk_rl_free_lines_dec(struct pblk_rl *rl, struct pblk_line *line,
-			    bool used)
-{
-	int blk_in_line = atomic_read(&line->blk_in_line);
-	int free_blocks;
-
-	atomic_sub(blk_in_line, &rl->free_blocks);
-
-	if (used)
-		free_blocks = atomic_sub_return(blk_in_line,
-							&rl->free_user_blocks);
-	else
-		free_blocks = atomic_read(&rl->free_user_blocks);
-
-	__pblk_rl_update_rates(rl, free_blocks);
-}
-
-int pblk_rl_high_thrs(struct pblk_rl *rl)
-{
-	return rl->high;
-}
-
-int pblk_rl_max_io(struct pblk_rl *rl)
-{
-	return rl->rb_max_io;
-}
-
-static void pblk_rl_u_timer(struct timer_list *t)
-{
-	struct pblk_rl *rl = from_timer(rl, t, u_timer);
-
-	/* Release user I/O state. Protect from GC */
-	smp_store_release(&rl->rb_user_active, 0);
-}
-
-void pblk_rl_free(struct pblk_rl *rl)
-{
-	del_timer(&rl->u_timer);
-}
-
-void pblk_rl_init(struct pblk_rl *rl, int budget, int threshold)
-{
-	struct pblk *pblk = container_of(rl, struct pblk, rl);
-	struct nvm_tgt_dev *dev = pblk->dev;
-	struct nvm_geo *geo = &dev->geo;
-	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
-	struct pblk_line_meta *lm = &pblk->lm;
-	int sec_meta, blk_meta;
-	unsigned int rb_windows;
-
-	/* Consider sectors used for metadata */
-	sec_meta = (lm->smeta_sec + lm->emeta_sec[0]) * l_mg->nr_free_lines;
-	blk_meta = DIV_ROUND_UP(sec_meta, geo->clba);
-
-	rl->high = pblk->op_blks - blk_meta - lm->blk_per_line;
-	rl->high_pw = get_count_order(rl->high);
-
-	rl->rsv_blocks = pblk_get_min_chks(pblk);
-
-	/* This will always be a power-of-2 */
-	rb_windows = budget / NVM_MAX_VLBA;
-	rl->rb_windows_pw = get_count_order(rb_windows);
-
-	/* To start with, all buffer is available to user I/O writers */
-	rl->rb_budget = budget;
-	rl->rb_user_max = budget;
-	rl->rb_gc_max = 0;
-	rl->rb_state = PBLK_RL_HIGH;
-
-	/* Maximize I/O size and ansure that back threshold is respected */
-	if (threshold)
-		rl->rb_max_io = budget - pblk->min_write_pgs_data - threshold;
-	else
-		rl->rb_max_io = budget - pblk->min_write_pgs_data - 1;
-
-	atomic_set(&rl->rb_user_cnt, 0);
-	atomic_set(&rl->rb_gc_cnt, 0);
-	atomic_set(&rl->rb_space, -1);
-	atomic_set(&rl->werr_lines, 0);
-
-	timer_setup(&rl->u_timer, pblk_rl_u_timer, 0);
-
-	rl->rb_user_active = 0;
-	rl->rb_gc_active = 0;
-}

drivers/lightnvm/pblk-trace.h

-/* SPDX-License-Identifier: GPL-2.0 */
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM pblk
-
-#if !defined(_TRACE_PBLK_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_PBLK_H
-
-#include <linux/tracepoint.h>
-
-struct ppa_addr;
-
-#define show_chunk_flags(state) __print_flags(state, "",	\
-	{ NVM_CHK_ST_FREE,		"FREE",		},	\
-	{ NVM_CHK_ST_CLOSED,		"CLOSED",	},	\
-	{ NVM_CHK_ST_OPEN,		"OPEN",		},	\
-	{ NVM_CHK_ST_OFFLINE,		"OFFLINE",	})
-
-#define show_line_state(state) __print_symbolic(state,		\
-	{ PBLK_LINESTATE_NEW,		"NEW",		},	\
-	{ PBLK_LINESTATE_FREE,		"FREE",		},	\
-	{ PBLK_LINESTATE_OPEN,		"OPEN",		},	\
-	{ PBLK_LINESTATE_CLOSED,	"CLOSED",	},	\
-	{ PBLK_LINESTATE_GC,		"GC",		},	\
-	{ PBLK_LINESTATE_BAD,		"BAD",		},	\
-	{ PBLK_LINESTATE_CORRUPT,	"CORRUPT"	})
-
-
-#define show_pblk_state(state) __print_symbolic(state,		\
-	{ PBLK_STATE_RUNNING,		"RUNNING",	},	\
-	{ PBLK_STATE_STOPPING,		"STOPPING",	},	\
-	{ PBLK_STATE_RECOVERING,	"RECOVERING",	},	\
-	{ PBLK_STATE_STOPPED,		"STOPPED"	})
-
-#define show_chunk_erase_state(state) __print_symbolic(state,	\
-	{ PBLK_CHUNK_RESET_START,	"START",	},	\
-	{ PBLK_CHUNK_RESET_DONE,	"OK",		},	\
-	{ PBLK_CHUNK_RESET_FAILED,	"FAILED"	})
-
-
-TRACE_EVENT(pblk_chunk_reset,
-
-	TP_PROTO(const char *name, struct ppa_addr *ppa, int state),
-
-	TP_ARGS(name, ppa, state),
-
-	TP_STRUCT__entry(
-		__string(name, name)
-		__field(u64, ppa)
-		__field(int, state)
-	),
-
-	TP_fast_assign(
-		__assign_str(name, name);
-		__entry->ppa = ppa->ppa;
-		__entry->state = state;
-	),
-
-	TP_printk("dev=%s grp=%llu pu=%llu chk=%llu state=%s", __get_str(name),
-			(u64)(((struct ppa_addr *)(&__entry->ppa))->m.grp),
-			(u64)(((struct ppa_addr *)(&__entry->ppa))->m.pu),
-			(u64)(((struct ppa_addr *)(&__entry->ppa))->m.chk),
-			show_chunk_erase_state((int)__entry->state))
-
-);
-
-TRACE_EVENT(pblk_chunk_state,
-
-	TP_PROTO(const char *name, struct ppa_addr *ppa, int state),
-
-	TP_ARGS(name, ppa, state),
-
-	TP_STRUCT__entry(
-		__string(name, name)
-		__field(u64, ppa)
-		__field(int, state)
-	),
-
-	TP_fast_assign(
-		__assign_str(name, name);
-		__entry->ppa = ppa->ppa;
-		__entry->state = state;
-	),
-
-	TP_printk("dev=%s grp=%llu pu=%llu chk=%llu state=%s", __get_str(name),
-			(u64)(((struct ppa_addr *)(&__entry->ppa))->m.grp),
-			(u64)(((struct ppa_addr *)(&__entry->ppa))->m.pu),
-			(u64)(((struct ppa_addr *)(&__entry->ppa))->m.chk),
-			show_chunk_flags((int)__entry->state))
-
-);
-
-TRACE_EVENT(pblk_line_state,
-
-	TP_PROTO(const char *name, int line, int state),
-
-	TP_ARGS(name, line, state),
-
-	TP_STRUCT__entry(
-		__string(name, name)
-		__field(int, line)
-		__field(int, state)
-	),
-
-	TP_fast_assign(
-		__assign_str(name, name);
-		__entry->line = line;
-		__entry->state = state;
-	),
-
-	TP_printk("dev=%s line=%d state=%s", __get_str(name),
-			(int)__entry->line,
-			show_line_state((int)__entry->state))
-
-);
-
-TRACE_EVENT(pblk_state,
-
-	TP_PROTO(const char *name, int state),
-
-	TP_ARGS(name, state),
-
-	TP_STRUCT__entry(
-		__string(name, name)
-		__field(int, state)
-	),
-
-	TP_fast_assign(
-		__assign_str(name, name);
-		__entry->state = state;
-	),
-
-	TP_printk("dev=%s state=%s", __get_str(name),
-			show_pblk_state((int)__entry->state))
-
-);
-
-#endif /* !defined(_TRACE_PBLK_H) || defined(TRACE_HEADER_MULTI_READ) */
-
-/* This part must be outside protection */
-
-#undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH ../../drivers/lightnvm
-#undef TRACE_INCLUDE_FILE
-#define TRACE_INCLUDE_FILE pblk-trace
-#include <trace/define_trace.h>

drivers/md/raid1.c

@@ -1329,6 +1329,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	struct raid1_plug_cb *plug = NULL;
 	int first_clone;
 	int max_sectors;
+	bool write_behind = false;
 
 	if (mddev_is_clustered(mddev) &&
 	     md_cluster_ops->area_resyncing(mddev, WRITE,
@@ -1381,6 +1382,15 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	max_sectors = r1_bio->sectors;
 	for (i = 0;  i < disks; i++) {
 		struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
+
+		/*
+		 * The write-behind io is only attempted on drives marked as
+		 * write-mostly, which means we could allocate write behind
+		 * bio later.
+		 */
+		if (rdev && test_bit(WriteMostly, &rdev->flags))
+			write_behind = true;
+
 		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
 			atomic_inc(&rdev->nr_pending);
 			blocked_rdev = rdev;
@@ -1454,6 +1464,15 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		goto retry_write;
 	}
 
+	/*
+	 * When using a bitmap, we may call alloc_behind_master_bio below.
+	 * alloc_behind_master_bio allocates a copy of the data payload a page
+	 * at a time and thus needs a new bio that can fit the whole payload
+	 * this bio in page sized chunks.
+	 */
+	if (write_behind && bitmap)
+		max_sectors = min_t(int, max_sectors,
+				    BIO_MAX_VECS * (PAGE_SIZE >> 9));
 	if (max_sectors < bio_sectors(bio)) {
 		struct bio *split = bio_split(bio, max_sectors,
 					      GFP_NOIO, &conf->bio_split);

drivers/nvme/host/Kconfig

@@ -33,12 +33,12 @@ config NVME_HWMON
 	  in the system.
 
 config NVME_FABRICS
+	select NVME_CORE
 	tristate
 
 config NVME_RDMA
 	tristate "NVM Express over Fabrics RDMA host driver"
 	depends on INFINIBAND && INFINIBAND_ADDR_TRANS && BLOCK
-	select NVME_CORE
 	select NVME_FABRICS
 	select SG_POOL
 	help
@@ -55,7 +55,6 @@ config NVME_FC
 	tristate "NVM Express over Fabrics FC host driver"
 	depends on BLOCK
 	depends on HAS_DMA
-	select NVME_CORE
 	select NVME_FABRICS
 	select SG_POOL
 	help
@@ -72,7 +71,6 @@ config NVME_TCP
 	tristate "NVM Express over Fabrics TCP host driver"
 	depends on INET
 	depends on BLOCK
-	select NVME_CORE
 	select NVME_FABRICS
 	select CRYPTO
 	select CRYPTO_CRC32C

drivers/nvme/host/Makefile

@@ -12,7 +12,6 @@ obj-$(CONFIG_NVME_TCP)			+= nvme-tcp.o
 nvme-core-y				:= core.o ioctl.o
 nvme-core-$(CONFIG_TRACING)		+= trace.o
 nvme-core-$(CONFIG_NVME_MULTIPATH)	+= multipath.o
-nvme-core-$(CONFIG_NVM)			+= lightnvm.o
 nvme-core-$(CONFIG_BLK_DEV_ZONED)	+= zns.o
 nvme-core-$(CONFIG_FAULT_INJECTION_DEBUG_FS)	+= fault_inject.o
 nvme-core-$(CONFIG_NVME_HWMON)		+= hwmon.o