Merge branch 'for-4.3/drivers' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "On top of the 4.3 core block IO changes, here are the driver related
  changes for 4.3.  Basically just NVMe and nbd this time around:

   - NVMe:
      - PRACT PI improvement from Alok Pandey.
      - Cleanups and improvements on submission queue doorbell and
        writing, using CMB if available.  From Jon Derrick.
      - From Keith, support for setting queue maximum segments, and
        reset support.
      - Also from Jon, fixup of u64 division issue on 32-bit archs and
        wiring up of the reset support through and ioctl.
      - Two small cleanups from Matias and Sunad

  - Various code cleanups and fixes from Markus Pargmann"

* 'for-4.3/drivers' of git://git.kernel.dk/linux-block:
  NVMe: Using PRACT bit to generate and verify PI by controller
  NVMe:Remove unreachable code in nvme_abort_req
  NVMe: Add nvme subsystem reset IOCTL
  NVMe: Add nvme subsystem reset support
  NVMe: removed unused nn var from nvme_dev_add
  NVMe: Set queue max segments
  nbd: flags is a u32 variable
  nbd: Rename functions for clearness of recv/send path
  nbd: Change 'disconnect' to be boolean
  nbd: Add debugfs entries
  nbd: Remove variable 'pid'
  nbd: Move clear queue debug message
  nbd: Remove 'harderror' and propagate error properly
  nbd: restructure sock_shutdown
  nbd: sock_shutdown, remove conditional lock
  nbd: Fix timeout detection
  nvme: Fixes u64 division which breaks i386 builds
  NVMe: Use CMB for the IO SQes if available
  NVMe: Unify SQ entry writing and doorbell ringing

2 files changed, 484 insertions, 145 deletions

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index f169faf9838a..293495a75d3d 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -33,6 +33,7 @@
 #include <linux/net.h>
 #include <linux/kthread.h>
 #include <linux/types.h>
+#include <linux/debugfs.h>
 
 #include <asm/uaccess.h>
 #include <asm/types.h>
@@ -40,8 +41,7 @@
 #include <linux/nbd.h>
 
 struct nbd_device {
-	int flags;
-	int harderror;		/* Code of hard error			*/
+	u32 flags;
 	struct socket * sock;	/* If == NULL, device is not ready, yet	*/
 	int magic;
 
@@ -56,11 +56,24 @@ struct nbd_device {
 	struct gendisk *disk;
 	int blksize;
 	loff_t bytesize;
-	pid_t pid; /* pid of nbd-client, if attached */
 	int xmit_timeout;
-	int disconnect; /* a disconnect has been requested by user */
+	bool disconnect; /* a disconnect has been requested by user */
+
+	struct timer_list timeout_timer;
+	struct task_struct *task_recv;
+	struct task_struct *task_send;
+
+#if IS_ENABLED(CONFIG_DEBUG_FS)
+	struct dentry *dbg_dir;
+#endif
 };
 
+#if IS_ENABLED(CONFIG_DEBUG_FS)
+static struct dentry *nbd_dbg_dir;
+#endif
+
+#define nbd_name(nbd) ((nbd)->disk->disk_name)
+
 #define NBD_MAGIC 0x68797548
 
 static unsigned int nbds_max = 16;
@@ -113,26 +126,36 @@ static void nbd_end_request(struct nbd_device *nbd, struct request *req)
 /*
  * Forcibly shutdown the socket causing all listeners to error
  */
-static void sock_shutdown(struct nbd_device *nbd, int lock)
+static void sock_shutdown(struct nbd_device *nbd)
 {
-	if (lock)
-		mutex_lock(&nbd->tx_lock);
-	if (nbd->sock) {
-		dev_warn(disk_to_dev(nbd->disk), "shutting down socket\n");
-		kernel_sock_shutdown(nbd->sock, SHUT_RDWR);
-		nbd->sock = NULL;
-	}
-	if (lock)
-		mutex_unlock(&nbd->tx_lock);
+	if (!nbd->sock)
+		return;
+
+	dev_warn(disk_to_dev(nbd->disk), "shutting down socket\n");
+	kernel_sock_shutdown(nbd->sock, SHUT_RDWR);
+	nbd->sock = NULL;
+	del_timer_sync(&nbd->timeout_timer);
 }
 
 static void nbd_xmit_timeout(unsigned long arg)
 {
-	struct task_struct *task = (struct task_struct *)arg;
+	struct nbd_device *nbd = (struct nbd_device *)arg;
+	struct task_struct *task;
+
+	if (list_empty(&nbd->queue_head))
+		return;
+
+	nbd->disconnect = true;
+
+	task = READ_ONCE(nbd->task_recv);
+	if (task)
+		force_sig(SIGKILL, task);
 
-	printk(KERN_WARNING "nbd: killing hung xmit (%s, pid: %d)\n",
-		task->comm, task->pid);
-	force_sig(SIGKILL, task);
+	task = READ_ONCE(nbd->task_send);
+	if (task)
+		force_sig(SIGKILL, nbd->task_send);
+
+	dev_err(nbd_to_dev(nbd), "Connection timed out, killed receiver and sender, shutting down connection\n");
 }
 
 /*
@@ -171,33 +194,12 @@ static int sock_xmit(struct nbd_device *nbd, int send, void *buf, int size,
 		msg.msg_controllen = 0;
 		msg.msg_flags = msg_flags | MSG_NOSIGNAL;
 
-		if (send) {
-			struct timer_list ti;
-
-			if (nbd->xmit_timeout) {
-				init_timer(&ti);
-				ti.function = nbd_xmit_timeout;
-				ti.data = (unsigned long)current;
-				ti.expires = jiffies + nbd->xmit_timeout;
-				add_timer(&ti);
-			}
+		if (send)
 			result = kernel_sendmsg(sock, &msg, &iov, 1, size);
-			if (nbd->xmit_timeout)
-				del_timer_sync(&ti);
-		} else
+		else
 			result = kernel_recvmsg(sock, &msg, &iov, 1, size,
 						msg.msg_flags);
 
-		if (signal_pending(current)) {
-			siginfo_t info;
-			printk(KERN_WARNING "nbd (pid %d: %s) got signal %d\n",
-				task_pid_nr(current), current->comm,
-				dequeue_signal_lock(current, &current->blocked, &info));
-			result = -EINTR;
-			sock_shutdown(nbd, !send);
-			break;
-		}
-
 		if (result <= 0) {
 			if (result == 0)
 				result = -EPIPE; /* short read */
@@ -210,6 +212,9 @@ static int sock_xmit(struct nbd_device *nbd, int send, void *buf, int size,
 	sigprocmask(SIG_SETMASK, &oldset, NULL);
 	tsk_restore_flags(current, pflags, PF_MEMALLOC);
 
+	if (!send && nbd->xmit_timeout)
+		mod_timer(&nbd->timeout_timer, jiffies + nbd->xmit_timeout);
+
 	return result;
 }
 
@@ -333,26 +338,24 @@ static struct request *nbd_read_stat(struct nbd_device *nbd)
 	if (result <= 0) {
 		dev_err(disk_to_dev(nbd->disk),
 			"Receive control failed (result %d)\n", result);
-		goto harderror;
+		return ERR_PTR(result);
 	}
 
 	if (ntohl(reply.magic) != NBD_REPLY_MAGIC) {
 		dev_err(disk_to_dev(nbd->disk), "Wrong magic (0x%lx)\n",
 				(unsigned long)ntohl(reply.magic));
-		result = -EPROTO;
-		goto harderror;
+		return ERR_PTR(-EPROTO);
 	}
 
 	req = nbd_find_request(nbd, *(struct request **)reply.handle);
 	if (IS_ERR(req)) {
 		result = PTR_ERR(req);
 		if (result != -ENOENT)
-			goto harderror;
+			return ERR_PTR(result);
 
 		dev_err(disk_to_dev(nbd->disk), "Unexpected reply (%p)\n",
 			reply.handle);
-		result = -EBADR;
-		goto harderror;
+		return ERR_PTR(-EBADR);
 	}
 
 	if (ntohl(reply.error)) {
@@ -380,18 +383,15 @@ static struct request *nbd_read_stat(struct nbd_device *nbd)
 		}
 	}
 	return req;
-harderror:
-	nbd->harderror = result;
-	return NULL;
 }
 
 static ssize_t pid_show(struct device *dev,
 			struct device_attribute *attr, char *buf)
 {
 	struct gendisk *disk = dev_to_disk(dev);
+	struct nbd_device *nbd = (struct nbd_device *)disk->private_data;
 
-	return sprintf(buf, "%ld\n",
-		(long) ((struct nbd_device *)disk->private_data)->pid);
+	return sprintf(buf, "%d\n", task_pid_nr(nbd->task_recv));
 }
 
 static struct device_attribute pid_attr = {
@@ -399,7 +399,7 @@ static struct device_attribute pid_attr = {
 	.show = pid_show,
 };
 
-static int nbd_do_it(struct nbd_device *nbd)
+static int nbd_thread_recv(struct nbd_device *nbd)
 {
 	struct request *req;
 	int ret;
@@ -407,20 +407,43 @@ static int nbd_do_it(struct nbd_device *nbd)
 	BUG_ON(nbd->magic != NBD_MAGIC);
 
 	sk_set_memalloc(nbd->sock->sk);
-	nbd->pid = task_pid_nr(current);
+
+	nbd->task_recv = current;
+
 	ret = device_create_file(disk_to_dev(nbd->disk), &pid_attr);
 	if (ret) {
 		dev_err(disk_to_dev(nbd->disk), "device_create_file failed!\n");
-		nbd->pid = 0;
+		nbd->task_recv = NULL;
 		return ret;
 	}
 
-	while ((req = nbd_read_stat(nbd)) != NULL)
+	while (1) {
+		req = nbd_read_stat(nbd);
+		if (IS_ERR(req)) {
+			ret = PTR_ERR(req);
+			break;
+		}
+
 		nbd_end_request(nbd, req);
+	}
 
 	device_remove_file(disk_to_dev(nbd->disk), &pid_attr);
-	nbd->pid = 0;
-	return 0;
+
+	nbd->task_recv = NULL;
+
+	if (signal_pending(current)) {
+		siginfo_t info;
+
+		ret = dequeue_signal_lock(current, &current->blocked, &info);
+		dev_warn(nbd_to_dev(nbd), "pid %d, %s, got signal %d\n",
+			 task_pid_nr(current), current->comm, ret);
+		mutex_lock(&nbd->tx_lock);
+		sock_shutdown(nbd);
+		mutex_unlock(&nbd->tx_lock);
+		ret = -ETIMEDOUT;
+	}
+
+	return ret;
 }
 
 static void nbd_clear_que(struct nbd_device *nbd)
@@ -455,6 +478,7 @@ static void nbd_clear_que(struct nbd_device *nbd)
 		req->errors++;
 		nbd_end_request(nbd, req);
 	}
+	dev_dbg(disk_to_dev(nbd->disk), "queue cleared\n");
 }
 
 
@@ -482,6 +506,9 @@ static void nbd_handle_req(struct nbd_device *nbd, struct request *req)
 
 	nbd->active_req = req;
 
+	if (nbd->xmit_timeout && list_empty_careful(&nbd->queue_head))
+		mod_timer(&nbd->timeout_timer, jiffies + nbd->xmit_timeout);
+
 	if (nbd_send_req(nbd, req) != 0) {
 		dev_err(disk_to_dev(nbd->disk), "Request send failed\n");
 		req->errors++;
@@ -503,11 +530,13 @@ error_out:
 	nbd_end_request(nbd, req);
 }
 
-static int nbd_thread(void *data)
+static int nbd_thread_send(void *data)
 {
 	struct nbd_device *nbd = data;
 	struct request *req;
 
+	nbd->task_send = current;
+
 	set_user_nice(current, MIN_NICE);
 	while (!kthread_should_stop() || !list_empty(&nbd->waiting_queue)) {
 		/* wait for something to do */
@@ -515,6 +544,20 @@ static int nbd_thread(void *data)
 					 kthread_should_stop() ||
 					 !list_empty(&nbd->waiting_queue));
 
+		if (signal_pending(current)) {
+			siginfo_t info;
+			int ret;
+
+			ret = dequeue_signal_lock(current, &current->blocked,
+						  &info);
+			dev_warn(nbd_to_dev(nbd), "pid %d, %s, got signal %d\n",
+				 task_pid_nr(current), current->comm, ret);
+			mutex_lock(&nbd->tx_lock);
+			sock_shutdown(nbd);
+			mutex_unlock(&nbd->tx_lock);
+			break;
+		}
+
 		/* extract request */
 		if (list_empty(&nbd->waiting_queue))
 			continue;
@@ -528,6 +571,9 @@ static int nbd_thread(void *data)
 		/* handle request */
 		nbd_handle_req(nbd, req);
 	}
+
+	nbd->task_send = NULL;
+
 	return 0;
 }
 
@@ -538,7 +584,7 @@ static int nbd_thread(void *data)
  *   { printk( "Warning: Ignoring result!\n"); nbd_end_request( req ); }
  */
 
-static void do_nbd_request(struct request_queue *q)
+static void nbd_request_handler(struct request_queue *q)
 		__releases(q->queue_lock) __acquires(q->queue_lock)
 {
 	struct request *req;
@@ -574,6 +620,9 @@ static void do_nbd_request(struct request_queue *q)
 	}
 }
 
+static int nbd_dev_dbg_init(struct nbd_device *nbd);
+static void nbd_dev_dbg_close(struct nbd_device *nbd);
+
 /* Must be called with tx_lock held */
 
 static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
@@ -597,7 +646,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 		if (!nbd->sock)
 			return -EINVAL;
 
-		nbd->disconnect = 1;
+		nbd->disconnect = true;
 
 		nbd_send_req(nbd, &sreq);
 		return 0;
@@ -625,7 +674,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 			nbd->sock = sock;
 			if (max_part > 0)
 				bdev->bd_invalidated = 1;
-			nbd->disconnect = 0; /* we're connected now */
+			nbd->disconnect = false; /* we're connected now */
 			return 0;
 		}
 		return -EINVAL;
@@ -648,6 +697,12 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 
 	case NBD_SET_TIMEOUT:
 		nbd->xmit_timeout = arg * HZ;
+		if (arg)
+			mod_timer(&nbd->timeout_timer,
+				  jiffies + nbd->xmit_timeout);
+		else
+			del_timer_sync(&nbd->timeout_timer);
+
 		return 0;
 
 	case NBD_SET_FLAGS:
@@ -666,7 +721,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 		struct socket *sock;
 		int error;
 
-		if (nbd->pid)
+		if (nbd->task_recv)
 			return -EBUSY;
 		if (!nbd->sock)
 			return -EINVAL;
@@ -683,24 +738,24 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 		else
 			blk_queue_flush(nbd->disk->queue, 0);
 
-		thread = kthread_run(nbd_thread, nbd, "%s",
-				     nbd->disk->disk_name);
+		thread = kthread_run(nbd_thread_send, nbd, "%s",
+				     nbd_name(nbd));
 		if (IS_ERR(thread)) {
 			mutex_lock(&nbd->tx_lock);
 			return PTR_ERR(thread);
 		}
 
-		error = nbd_do_it(nbd);
+		nbd_dev_dbg_init(nbd);
+		error = nbd_thread_recv(nbd);
+		nbd_dev_dbg_close(nbd);
 		kthread_stop(thread);
 
 		mutex_lock(&nbd->tx_lock);
-		if (error)
-			return error;
-		sock_shutdown(nbd, 0);
+
+		sock_shutdown(nbd);
 		sock = nbd->sock;
 		nbd->sock = NULL;
 		nbd_clear_que(nbd);
-		dev_warn(disk_to_dev(nbd->disk), "queue cleared\n");
 		kill_bdev(bdev);
 		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, nbd->disk->queue);
 		set_device_ro(bdev, false);
@@ -714,7 +769,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 			blkdev_reread_part(bdev);
 		if (nbd->disconnect) /* user requested, ignore socket errors */
 			return 0;
-		return nbd->harderror;
+		return error;
 	}
 
 	case NBD_CLEAR_QUE:
@@ -758,6 +813,161 @@ static const struct block_device_operations nbd_fops =
 	.ioctl =	nbd_ioctl,
 };
 
+#if IS_ENABLED(CONFIG_DEBUG_FS)
+
+static int nbd_dbg_tasks_show(struct seq_file *s, void *unused)
+{
+	struct nbd_device *nbd = s->private;
+
+	if (nbd->task_recv)
+		seq_printf(s, "recv: %d\n", task_pid_nr(nbd->task_recv));
+	if (nbd->task_send)
+		seq_printf(s, "send: %d\n", task_pid_nr(nbd->task_send));
+
+	return 0;
+}
+
+static int nbd_dbg_tasks_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, nbd_dbg_tasks_show, inode->i_private);
+}
+
+static const struct file_operations nbd_dbg_tasks_ops = {
+	.open = nbd_dbg_tasks_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int nbd_dbg_flags_show(struct seq_file *s, void *unused)
+{
+	struct nbd_device *nbd = s->private;
+	u32 flags = nbd->flags;
+
+	seq_printf(s, "Hex: 0x%08x\n\n", flags);
+
+	seq_puts(s, "Known flags:\n");
+
+	if (flags & NBD_FLAG_HAS_FLAGS)
+		seq_puts(s, "NBD_FLAG_HAS_FLAGS\n");
+	if (flags & NBD_FLAG_READ_ONLY)
+		seq_puts(s, "NBD_FLAG_READ_ONLY\n");
+	if (flags & NBD_FLAG_SEND_FLUSH)
+		seq_puts(s, "NBD_FLAG_SEND_FLUSH\n");
+	if (flags & NBD_FLAG_SEND_TRIM)
+		seq_puts(s, "NBD_FLAG_SEND_TRIM\n");
+
+	return 0;
+}
+
+static int nbd_dbg_flags_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, nbd_dbg_flags_show, inode->i_private);
+}
+
+static const struct file_operations nbd_dbg_flags_ops = {
+	.open = nbd_dbg_flags_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int nbd_dev_dbg_init(struct nbd_device *nbd)
+{
+	struct dentry *dir;
+	struct dentry *f;
+
+	dir = debugfs_create_dir(nbd_name(nbd), nbd_dbg_dir);
+	if (IS_ERR_OR_NULL(dir)) {
+		dev_err(nbd_to_dev(nbd), "Failed to create debugfs dir for '%s' (%ld)\n",
+			nbd_name(nbd), PTR_ERR(dir));
+		return PTR_ERR(dir);
+	}
+	nbd->dbg_dir = dir;
+
+	f = debugfs_create_file("tasks", 0444, dir, nbd, &nbd_dbg_tasks_ops);
+	if (IS_ERR_OR_NULL(f)) {
+		dev_err(nbd_to_dev(nbd), "Failed to create debugfs file 'tasks', %ld\n",
+			PTR_ERR(f));
+		return PTR_ERR(f);
+	}
+
+	f = debugfs_create_u64("size_bytes", 0444, dir, &nbd->bytesize);
+	if (IS_ERR_OR_NULL(f)) {
+		dev_err(nbd_to_dev(nbd), "Failed to create debugfs file 'size_bytes', %ld\n",
+			PTR_ERR(f));
+		return PTR_ERR(f);
+	}
+
+	f = debugfs_create_u32("timeout", 0444, dir, &nbd->xmit_timeout);
+	if (IS_ERR_OR_NULL(f)) {
+		dev_err(nbd_to_dev(nbd), "Failed to create debugfs file 'timeout', %ld\n",
+			PTR_ERR(f));
+		return PTR_ERR(f);
+	}
+
+	f = debugfs_create_u32("blocksize", 0444, dir, &nbd->blksize);
+	if (IS_ERR_OR_NULL(f)) {
+		dev_err(nbd_to_dev(nbd), "Failed to create debugfs file 'blocksize', %ld\n",
+			PTR_ERR(f));
+		return PTR_ERR(f);
+	}
+
+	f = debugfs_create_file("flags", 0444, dir, &nbd, &nbd_dbg_flags_ops);
+	if (IS_ERR_OR_NULL(f)) {
+		dev_err(nbd_to_dev(nbd), "Failed to create debugfs file 'flags', %ld\n",
+			PTR_ERR(f));
+		return PTR_ERR(f);
+	}
+
+	return 0;
+}
+
+static void nbd_dev_dbg_close(struct nbd_device *nbd)
+{
+	debugfs_remove_recursive(nbd->dbg_dir);
+}
+
+static int nbd_dbg_init(void)
+{
+	struct dentry *dbg_dir;
+
+	dbg_dir = debugfs_create_dir("nbd", NULL);
+	if (IS_ERR(dbg_dir))
+		return PTR_ERR(dbg_dir);
+
+	nbd_dbg_dir = dbg_dir;
+
+	return 0;
+}
+
+static void nbd_dbg_close(void)
+{
+	debugfs_remove_recursive(nbd_dbg_dir);
+}
+
+#else  /* IS_ENABLED(CONFIG_DEBUG_FS) */
+
+static int nbd_dev_dbg_init(struct nbd_device *nbd)
+{
+	return 0;
+}
+
+static void nbd_dev_dbg_close(struct nbd_device *nbd)
+{
+}
+
+static int nbd_dbg_init(void)
+{
+	return 0;
+}
+
+static void nbd_dbg_close(void)
+{
+}
+
+#endif
+
 /*
  * And here should be modules and kernel interface 
  *  (Just smiley confuses emacs :-)
@@ -811,7 +1021,7 @@ static int __init nbd_init(void)
 		 * every gendisk to have its very own request_queue struct.
 		 * These structs are big so we dynamically allocate them.
 		 */
-		disk->queue = blk_init_queue(do_nbd_request, &nbd_lock);
+		disk->queue = blk_init_queue(nbd_request_handler, &nbd_lock);
 		if (!disk->queue) {
 			put_disk(disk);
 			goto out;
@@ -835,6 +1045,8 @@ static int __init nbd_init(void)
 
 	printk(KERN_INFO "nbd: registered device at major %d\n", NBD_MAJOR);
 
+	nbd_dbg_init();
+
 	for (i = 0; i < nbds_max; i++) {
 		struct gendisk *disk = nbd_dev[i].disk;
 		nbd_dev[i].magic = NBD_MAGIC;
@@ -842,6 +1054,9 @@ static int __init nbd_init(void)
 		spin_lock_init(&nbd_dev[i].queue_lock);
 		INIT_LIST_HEAD(&nbd_dev[i].queue_head);
 		mutex_init(&nbd_dev[i].tx_lock);
+		init_timer(&nbd_dev[i].timeout_timer);
+		nbd_dev[i].timeout_timer.function = nbd_xmit_timeout;
+		nbd_dev[i].timeout_timer.data = (unsigned long)&nbd_dev[i];
 		init_waitqueue_head(&nbd_dev[i].active_wq);
 		init_waitqueue_head(&nbd_dev[i].waiting_wq);
 		nbd_dev[i].blksize = 1024;
@@ -868,6 +1083,9 @@ out:
 static void __exit nbd_cleanup(void)
 {
 	int i;
+
+	nbd_dbg_close();
+
 	for (i = 0; i < nbds_max; i++) {
 		struct gendisk *disk = nbd_dev[i].disk;
 		nbd_dev[i].magic = 0;
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index 2f694d78da55..b97fc3fe0916 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -72,6 +72,10 @@ module_param(nvme_char_major, int, 0);
 static int use_threaded_interrupts;
 module_param(use_threaded_interrupts, int, 0);
 
+static bool use_cmb_sqes = true;
+module_param(use_cmb_sqes, bool, 0644);
+MODULE_PARM_DESC(use_cmb_sqes, "use controller's memory buffer for I/O SQes");
+
 static DEFINE_SPINLOCK(dev_list_lock);
 static LIST_HEAD(dev_list);
 static struct task_struct *nvme_thread;
@@ -103,6 +107,7 @@ struct nvme_queue {
 	char irqname[24];	/* nvme4294967295-65535\0 */
 	spinlock_t q_lock;
 	struct nvme_command *sq_cmds;
+	struct nvme_command __iomem *sq_cmds_io;
 	volatile struct nvme_completion *cqes;
 	struct blk_mq_tags **tags;
 	dma_addr_t sq_dma_addr;
@@ -379,27 +384,28 @@ static void *nvme_finish_cmd(struct nvme_queue *nvmeq, int tag,
  *
  * Safe to use from interrupt context
  */
-static int __nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
+static void __nvme_submit_cmd(struct nvme_queue *nvmeq,
+						struct nvme_command *cmd)
 {
 	u16 tail = nvmeq->sq_tail;
 
-	memcpy(&nvmeq->sq_cmds[tail], cmd, sizeof(*cmd));
+	if (nvmeq->sq_cmds_io)
+		memcpy_toio(&nvmeq->sq_cmds_io[tail], cmd, sizeof(*cmd));
+	else
+		memcpy(&nvmeq->sq_cmds[tail], cmd, sizeof(*cmd));
+
 	if (++tail == nvmeq->q_depth)
 		tail = 0;
 	writel(tail, nvmeq->q_db);
 	nvmeq->sq_tail = tail;
-
-	return 0;
 }
 
-static int nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
+static void nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
 {
 	unsigned long flags;
-	int ret;
 	spin_lock_irqsave(&nvmeq->q_lock, flags);
-	ret = __nvme_submit_cmd(nvmeq, cmd);
+	__nvme_submit_cmd(nvmeq, cmd);
 	spin_unlock_irqrestore(&nvmeq->q_lock, flags);
-	return ret;
 }
 
 static __le64 **iod_list(struct nvme_iod *iod)
@@ -730,18 +736,16 @@ static int nvme_setup_prps(struct nvme_dev *dev, struct nvme_iod *iod,
 static void nvme_submit_priv(struct nvme_queue *nvmeq, struct request *req,
 		struct nvme_iod *iod)
 {
-	struct nvme_command *cmnd = &nvmeq->sq_cmds[nvmeq->sq_tail];
+	struct nvme_command cmnd;
 
-	memcpy(cmnd, req->cmd, sizeof(struct nvme_command));
-	cmnd->rw.command_id = req->tag;
+	memcpy(&cmnd, req->cmd, sizeof(cmnd));
+	cmnd.rw.command_id = req->tag;
 	if (req->nr_phys_segments) {
-		cmnd->rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
-		cmnd->rw.prp2 = cpu_to_le64(iod->first_dma);
+		cmnd.rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
+		cmnd.rw.prp2 = cpu_to_le64(iod->first_dma);
 	}
 
-	if (++nvmeq->sq_tail == nvmeq->q_depth)
-		nvmeq->sq_tail = 0;
-	writel(nvmeq->sq_tail, nvmeq->q_db);
+	__nvme_submit_cmd(nvmeq, &cmnd);
 }
 
 /*
@@ -754,45 +758,41 @@ static void nvme_submit_discard(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 {
 	struct nvme_dsm_range *range =
 				(struct nvme_dsm_range *)iod_list(iod)[0];
-	struct nvme_command *cmnd = &nvmeq->sq_cmds[nvmeq->sq_tail];
+	struct nvme_command cmnd;
 
 	range->cattr = cpu_to_le32(0);
 	range->nlb = cpu_to_le32(blk_rq_bytes(req) >> ns->lba_shift);
 	range->slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
 
-	memset(cmnd, 0, sizeof(*cmnd));
-	cmnd->dsm.opcode = nvme_cmd_dsm;
-	cmnd->dsm.command_id = req->tag;
-	cmnd->dsm.nsid = cpu_to_le32(ns->ns_id);
-	cmnd->dsm.prp1 = cpu_to_le64(iod->first_dma);
-	cmnd->dsm.nr = 0;
-	cmnd->dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
+	memset(&cmnd, 0, sizeof(cmnd));
+	cmnd.dsm.opcode = nvme_cmd_dsm;
+	cmnd.dsm.command_id = req->tag;
+	cmnd.dsm.nsid = cpu_to_le32(ns->ns_id);
+	cmnd.dsm.prp1 = cpu_to_le64(iod->first_dma);
+	cmnd.dsm.nr = 0;
+	cmnd.dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
 
-	if (++nvmeq->sq_tail == nvmeq->q_depth)
-		nvmeq->sq_tail = 0;
-	writel(nvmeq->sq_tail, nvmeq->q_db);
+	__nvme_submit_cmd(nvmeq, &cmnd);
 }
 
 static void nvme_submit_flush(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 								int cmdid)
 {
-	struct nvme_command *cmnd = &nvmeq->sq_cmds[nvmeq->sq_tail];
+	struct nvme_command cmnd;
 
-	memset(cmnd, 0, sizeof(*cmnd));
-	cmnd->common.opcode = nvme_cmd_flush;
-	cmnd->common.command_id = cmdid;
-	cmnd->common.nsid = cpu_to_le32(ns->ns_id);
+	memset(&cmnd, 0, sizeof(cmnd));
+	cmnd.common.opcode = nvme_cmd_flush;
+	cmnd.common.command_id = cmdid;
+	cmnd.common.nsid = cpu_to_le32(ns->ns_id);
 
-	if (++nvmeq->sq_tail == nvmeq->q_depth)
-		nvmeq->sq_tail = 0;
-	writel(nvmeq->sq_tail, nvmeq->q_db);
+	__nvme_submit_cmd(nvmeq, &cmnd);
 }
 
 static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod,
 							struct nvme_ns *ns)
 {
 	struct request *req = iod_get_private(iod);
-	struct nvme_command *cmnd;
+	struct nvme_command cmnd;
 	u16 control = 0;
 	u32 dsmgmt = 0;
 
@@ -804,19 +804,16 @@ static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod,
 	if (req->cmd_flags & REQ_RAHEAD)
 		dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;
 
-	cmnd = &nvmeq->sq_cmds[nvmeq->sq_tail];
-	memset(cmnd, 0, sizeof(*cmnd));
+	memset(&cmnd, 0, sizeof(cmnd));
+	cmnd.rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read);
+	cmnd.rw.command_id = req->tag;
+	cmnd.rw.nsid = cpu_to_le32(ns->ns_id);
+	cmnd.rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
+	cmnd.rw.prp2 = cpu_to_le64(iod->first_dma);
+	cmnd.rw.slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
+	cmnd.rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
 
-	cmnd->rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read);
-	cmnd->rw.command_id = req->tag;
-	cmnd->rw.nsid = cpu_to_le32(ns->ns_id);
-	cmnd->rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
-	cmnd->rw.prp2 = cpu_to_le64(iod->first_dma);
-	cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
-	cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
-
-	if (blk_integrity_rq(req)) {
-		cmnd->rw.metadata = cpu_to_le64(sg_dma_address(iod->meta_sg));
+	if (ns->ms) {
 		switch (ns->pi_type) {
 		case NVME_NS_DPS_PI_TYPE3:
 			control |= NVME_RW_PRINFO_PRCHK_GUARD;
@@ -825,19 +822,21 @@ static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod,
 		case NVME_NS_DPS_PI_TYPE2:
 			control |= NVME_RW_PRINFO_PRCHK_GUARD |
 					NVME_RW_PRINFO_PRCHK_REF;
-			cmnd->rw.reftag = cpu_to_le32(
+			cmnd.rw.reftag = cpu_to_le32(
 					nvme_block_nr(ns, blk_rq_pos(req)));
 			break;
 		}
-	} else if (ns->ms)
-		control |= NVME_RW_PRINFO_PRACT;
+		if (blk_integrity_rq(req))
+			cmnd.rw.metadata =
+				cpu_to_le64(sg_dma_address(iod->meta_sg));
+		else
+			control |= NVME_RW_PRINFO_PRACT;
+	}
 
-	cmnd->rw.control = cpu_to_le16(control);
-	cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt);
+	cmnd.rw.control = cpu_to_le16(control);
+	cmnd.rw.dsmgmt = cpu_to_le32(dsmgmt);
 
-	if (++nvmeq->sq_tail == nvmeq->q_depth)
-		nvmeq->sq_tail = 0;
-	writel(nvmeq->sq_tail, nvmeq->q_db);
+	__nvme_submit_cmd(nvmeq, &cmnd);
 
 	return 0;
 }
@@ -1080,7 +1079,8 @@ static int nvme_submit_async_admin_req(struct nvme_dev *dev)
 	c.common.command_id = req->tag;
 
 	blk_mq_free_request(req);
-	return __nvme_submit_cmd(nvmeq, &c);
+	__nvme_submit_cmd(nvmeq, &c);
+	return 0;
 }
 
 static int nvme_submit_admin_async_cmd(struct nvme_dev *dev,
@@ -1103,7 +1103,8 @@ static int nvme_submit_admin_async_cmd(struct nvme_dev *dev,
 
 	cmd->common.command_id = req->tag;
 
-	return nvme_submit_cmd(nvmeq, cmd);
+	nvme_submit_cmd(nvmeq, cmd);
+	return 0;
 }
 
 static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
@@ -1315,12 +1316,7 @@ static void nvme_abort_req(struct request *req)
 
 	dev_warn(nvmeq->q_dmadev, "Aborting I/O %d QID %d\n", req->tag,
 							nvmeq->qid);
-	if (nvme_submit_cmd(dev->queues[0], &cmd) < 0) {
-		dev_warn(nvmeq->q_dmadev,
-				"Could not abort I/O %d QID %d",
-				req->tag, nvmeq->qid);
-		blk_mq_free_request(abort_req);
-	}
+	nvme_submit_cmd(dev->queues[0], &cmd);
 }
 
 static void nvme_cancel_queue_ios(struct request *req, void *data, bool reserved)
@@ -1374,7 +1370,8 @@ static void nvme_free_queue(struct nvme_queue *nvmeq)
 {
 	dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
 				(void *)nvmeq->cqes, nvmeq->cq_dma_addr);
-	dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth),
+	if (nvmeq->sq_cmds)
+		dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth),
 					nvmeq->sq_cmds, nvmeq->sq_dma_addr);
 	kfree(nvmeq);
 }
@@ -1447,6 +1444,47 @@ static void nvme_disable_queue(struct nvme_dev *dev, int qid)
 	spin_unlock_irq(&nvmeq->q_lock);
 }
 
+static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
+				int entry_size)
+{
+	int q_depth = dev->q_depth;
+	unsigned q_size_aligned = roundup(q_depth * entry_size, dev->page_size);
+
+	if (q_size_aligned * nr_io_queues > dev->cmb_size) {
+		u64 mem_per_q = div_u64(dev->cmb_size, nr_io_queues);
+		mem_per_q = round_down(mem_per_q, dev->page_size);
+		q_depth = div_u64(mem_per_q, entry_size);
+
+		/*
+		 * Ensure the reduced q_depth is above some threshold where it
+		 * would be better to map queues in system memory with the
+		 * original depth
+		 */
+		if (q_depth < 64)
+			return -ENOMEM;
+	}
+
+	return q_depth;
+}
+
+static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq,
+				int qid, int depth)
+{
+	if (qid && dev->cmb && use_cmb_sqes && NVME_CMB_SQS(dev->cmbsz)) {
+		unsigned offset = (qid - 1) *
+					roundup(SQ_SIZE(depth), dev->page_size);
+		nvmeq->sq_dma_addr = dev->cmb_dma_addr + offset;
+		nvmeq->sq_cmds_io = dev->cmb + offset;
+	} else {
+		nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth),
+					&nvmeq->sq_dma_addr, GFP_KERNEL);
+		if (!nvmeq->sq_cmds)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
 static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 							int depth)
 {
@@ -1459,9 +1497,7 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 	if (!nvmeq->cqes)
 		goto free_nvmeq;
 
-	nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth),
-					&nvmeq->sq_dma_addr, GFP_KERNEL);
-	if (!nvmeq->sq_cmds)
+	if (nvme_alloc_sq_cmds(dev, nvmeq, qid, depth))
 		goto free_cqdma;
 
 	nvmeq->q_dmadev = dev->dev;
@@ -1696,6 +1732,12 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 		page_shift = dev_page_max;
 	}
 
+	dev->subsystem = readl(&dev->bar->vs) >= NVME_VS(1, 1) ?
+						NVME_CAP_NSSRC(cap) : 0;
+
+	if (dev->subsystem && (readl(&dev->bar->csts) & NVME_CSTS_NSSRO))
+		writel(NVME_CSTS_NSSRO, &dev->bar->csts);
+
 	result = nvme_disable_ctrl(dev, cap);
 	if (result < 0)
 		return result;
@@ -1856,6 +1898,15 @@ static int nvme_user_cmd(struct nvme_dev *dev, struct nvme_ns *ns,
 	return status;
 }
 
+static int nvme_subsys_reset(struct nvme_dev *dev)
+{
+	if (!dev->subsystem)
+		return -ENOTTY;
+
+	writel(0x4E564D65, &dev->bar->nssr); /* "NVMe" */
+	return 0;
+}
+
 static int nvme_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd,
 							unsigned long arg)
 {
@@ -1989,7 +2040,7 @@ static int nvme_revalidate_disk(struct gendisk *disk)
 								!ns->ext)
 		nvme_init_integrity(ns);
 
-	if (ns->ms && !blk_get_integrity(disk))
+	if (ns->ms && !(ns->ms == 8 && ns->pi_type) && !blk_get_integrity(disk))
 		set_capacity(disk, 0);
 	else
 		set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9));
@@ -2020,7 +2071,10 @@ static int nvme_kthread(void *data)
 		spin_lock(&dev_list_lock);
 		list_for_each_entry_safe(dev, next, &dev_list, node) {
 			int i;
-			if (readl(&dev->bar->csts) & NVME_CSTS_CFS) {
+			u32 csts = readl(&dev->bar->csts);
+
+			if ((dev->subsystem && (csts & NVME_CSTS_NSSRO)) ||
+							csts & NVME_CSTS_CFS) {
 				if (work_busy(&dev->reset_work))
 					continue;
 				list_del_init(&dev->node);
@@ -2080,8 +2134,11 @@ static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid)
 	list_add_tail(&ns->list, &dev->namespaces);
 
 	blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
-	if (dev->max_hw_sectors)
+	if (dev->max_hw_sectors) {
 		blk_queue_max_hw_sectors(ns->queue, dev->max_hw_sectors);
+		blk_queue_max_segments(ns->queue,
+			((dev->max_hw_sectors << 9) / dev->page_size) + 1);
+	}
 	if (dev->stripe_size)
 		blk_queue_chunk_sectors(ns->queue, dev->stripe_size >> 9);
 	if (dev->vwc & NVME_CTRL_VWC_PRESENT)
@@ -2159,6 +2216,58 @@ static int set_queue_count(struct nvme_dev *dev, int count)
 	return min(result & 0xffff, result >> 16) + 1;
 }
 
+static void __iomem *nvme_map_cmb(struct nvme_dev *dev)
+{
+	u64 szu, size, offset;
+	u32 cmbloc;
+	resource_size_t bar_size;
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
+	void __iomem *cmb;
+	dma_addr_t dma_addr;
+
+	if (!use_cmb_sqes)
+		return NULL;
+
+	dev->cmbsz = readl(&dev->bar->cmbsz);
+	if (!(NVME_CMB_SZ(dev->cmbsz)))
+		return NULL;
+
+	cmbloc = readl(&dev->bar->cmbloc);
+
+	szu = (u64)1 << (12 + 4 * NVME_CMB_SZU(dev->cmbsz));
+	size = szu * NVME_CMB_SZ(dev->cmbsz);
+	offset = szu * NVME_CMB_OFST(cmbloc);
+	bar_size = pci_resource_len(pdev, NVME_CMB_BIR(cmbloc));
+
+	if (offset > bar_size)
+		return NULL;
+
+	/*
+	 * Controllers may support a CMB size larger than their BAR,
+	 * for example, due to being behind a bridge. Reduce the CMB to
+	 * the reported size of the BAR
+	 */
+	if (size > bar_size - offset)
+		size = bar_size - offset;
+
+	dma_addr = pci_resource_start(pdev, NVME_CMB_BIR(cmbloc)) + offset;
+	cmb = ioremap_wc(dma_addr, size);
+	if (!cmb)
+		return NULL;
+
+	dev->cmb_dma_addr = dma_addr;
+	dev->cmb_size = size;
+	return cmb;
+}
+
+static inline void nvme_release_cmb(struct nvme_dev *dev)
+{
+	if (dev->cmb) {
+		iounmap(dev->cmb);
+		dev->cmb = NULL;
+	}
+}
+
 static size_t db_bar_size(struct nvme_dev *dev, unsigned nr_io_queues)
 {
 	return 4096 + ((nr_io_queues + 1) * 8 * dev->db_stride);
@@ -2177,6 +2286,15 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	if (result < nr_io_queues)
 		nr_io_queues = result;
 
+	if (dev->cmb && NVME_CMB_SQS(dev->cmbsz)) {
+		result = nvme_cmb_qdepth(dev, nr_io_queues,
+				sizeof(struct nvme_command));
+		if (result > 0)
+			dev->q_depth = result;
+		else
+			nvme_release_cmb(dev);
+	}
+
 	size = db_bar_size(dev, nr_io_queues);
 	if (size > 8192) {
 		iounmap(dev->bar);
@@ -2344,7 +2462,6 @@ static int nvme_dev_add(struct nvme_dev *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 	int res;
-	unsigned nn;
 	struct nvme_id_ctrl *ctrl;
 	int shift = NVME_CAP_MPSMIN(readq(&dev->bar->cap)) + 12;
 
@@ -2354,7 +2471,6 @@ static int nvme_dev_add(struct nvme_dev *dev)
 		return -EIO;
 	}
 
-	nn = le32_to_cpup(&ctrl->nn);
 	dev->oncs = le16_to_cpup(&ctrl->oncs);
 	dev->abort_limit = ctrl->acl + 1;
 	dev->vwc = ctrl->vwc;
@@ -2440,6 +2556,8 @@ static int nvme_dev_map(struct nvme_dev *dev)
 	dev->q_depth = min_t(int, NVME_CAP_MQES(cap) + 1, NVME_Q_DEPTH);
 	dev->db_stride = 1 << NVME_CAP_STRIDE(cap);
 	dev->dbs = ((void __iomem *)dev->bar) + 4096;
+	if (readl(&dev->bar->vs) >= NVME_VS(1, 2))
+		dev->cmb = nvme_map_cmb(dev);
 
 	return 0;
 
@@ -2820,6 +2938,8 @@ static long nvme_dev_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 	case NVME_IOCTL_RESET:
 		dev_warn(dev->dev, "resetting controller\n");
 		return nvme_reset(dev);
+	case NVME_IOCTL_SUBSYS_RESET:
+		return nvme_subsys_reset(dev);
 	default:
 		return -ENOTTY;
 	}
@@ -3145,6 +3265,7 @@ static void nvme_remove(struct pci_dev *pdev)
 	nvme_dev_remove_admin(dev);
 	device_destroy(nvme_class, MKDEV(nvme_char_major, dev->instance));
 	nvme_free_queues(dev, 0);
+	nvme_release_cmb(dev);
 	nvme_release_prp_pools(dev);
 	kref_put(&dev->kref, nvme_free_dev);
 }