Merge branch 'for-4.11/block' into for-4.11/linus-merge

Signed-off-by: Jens Axboe <axboe@fb.com>

68 files changed, 7340 insertions, 2832 deletions

diff --git a/Documentation/cdrom/cdrom-standard.tex b/Documentation/cdrom/cdrom-standard.tex
index c06233fe52ac..8f85b0e41046 100644
--- a/Documentation/cdrom/cdrom-standard.tex
+++ b/Documentation/cdrom/cdrom-standard.tex
@@ -249,7 +249,6 @@ struct& cdrom_device_ops\ \{ \hidewidth\cr
         unsigned\ long);\cr
 \noalign{\medskip}
   &const\ int& capability;& capability flags \cr
-  &int& n_minors;& number of active minor devices \cr
 \};\cr
 }
 $$
@@ -258,13 +257,7 @@ it should add a function pointer to this $struct$. When a particular
 function is not implemented, however, this $struct$ should contain a
 NULL instead. The $capability$ flags specify the capabilities of the
 \cdrom\ hardware and/or low-level \cdrom\ driver when a \cdrom\ drive
-is registered with the \UCD. The value $n_minors$ should be a positive
-value indicating the number of minor devices that are supported by
-the low-level device driver, normally~1. Although these two variables
-are `informative' rather than `operational,' they are included in
-$cdrom_device_ops$ because they describe the capability of the {\em
-driver\/} rather than the {\em drive}. Nomenclature has always been
-difficult in computer programming.
+is registered with the \UCD.
 
 Note that most functions have fewer parameters than their
 $blkdev_fops$ counterparts. This is because very little of the
diff --git a/MAINTAINERS b/MAINTAINERS
index 527d13759ecc..864e1fd31f0c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8612,10 +8612,10 @@ S:	Maintained
 F:	drivers/net/ethernet/netronome/
 
 NETWORK BLOCK DEVICE (NBD)
-M:	Markus Pargmann <mpa@pengutronix.de>
+M:	Josef Bacik <jbacik@fb.com>
 S:	Maintained
+L:	linux-block@vger.kernel.org
 L:	nbd-general@lists.sourceforge.net
-T:	git git://git.pengutronix.de/git/mpa/linux-nbd.git
 F:	Documentation/blockdev/nbd.txt
 F:	drivers/block/nbd.c
 F:	include/uapi/linux/nbd.h
@@ -11089,6 +11089,17 @@ L:	linux-mmc@vger.kernel.org
 S:	Maintained
 F:	drivers/mmc/host/sdhci-spear.c
 
+SECURE ENCRYPTING DEVICE (SED) OPAL DRIVER
+M:	Scott Bauer <scott.bauer@intel.com>
+M:	Jonathan Derrick <jonathan.derrick@intel.com>
+M:	Rafael Antognolli <rafael.antognolli@intel.com>
+L:	linux-block@vger.kernel.org
+S:	Supported
+F:	block/sed*
+F:	block/opal_proto.h
+F:	include/linux/sed*
+F:	include/uapi/linux/sed*
+
 SECURITY SUBSYSTEM
 M:	James Morris <james.l.morris@oracle.com>
 M:	"Serge E. Hallyn" <serge@hallyn.com>
diff --git a/block/Kconfig b/block/Kconfig
index 8bf114a3858a..1aef809affae 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -147,6 +147,25 @@ config BLK_WBT_MQ
 	Multiqueue currently doesn't have support for IO scheduling,
 	enabling this option is recommended.
 
+config BLK_DEBUG_FS
+	bool "Block layer debugging information in debugfs"
+	default y
+	depends on DEBUG_FS
+	---help---
+	Include block layer debugging information in debugfs. This information
+	is mostly useful for kernel developers, but it doesn't incur any cost
+	at runtime.
+
+	Unless you are building a kernel for a tiny system, you should
+	say Y here.
+
+config BLK_SED_OPAL
+	bool "Logic for interfacing with Opal enabled SEDs"
+	---help---
+	Builds Logic for interfacing with Opal enabled controllers.
+	Enabling this option enables users to setup/unlock/lock
+	Locking ranges for SED devices using the Opal protocol.
+
 menu "Partition Types"
 
 source "block/partitions/Kconfig"
diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index 421bef9c4c48..0715ce93daef 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -63,6 +63,56 @@ config DEFAULT_IOSCHED
 	default "cfq" if DEFAULT_CFQ
 	default "noop" if DEFAULT_NOOP
 
+config MQ_IOSCHED_DEADLINE
+	tristate "MQ deadline I/O scheduler"
+	default y
+	---help---
+	  MQ version of the deadline IO scheduler.
+
+config MQ_IOSCHED_NONE
+	bool
+	default y
+
+choice
+	prompt "Default single-queue blk-mq I/O scheduler"
+	default DEFAULT_SQ_NONE
+	help
+	  Select the I/O scheduler which will be used by default for blk-mq
+	  managed block devices with a single queue.
+
+	config DEFAULT_SQ_DEADLINE
+		bool "MQ Deadline" if MQ_IOSCHED_DEADLINE=y
+
+	config DEFAULT_SQ_NONE
+		bool "None"
+
+endchoice
+
+config DEFAULT_SQ_IOSCHED
+	string
+	default "mq-deadline" if DEFAULT_SQ_DEADLINE
+	default "none" if DEFAULT_SQ_NONE
+
+choice
+	prompt "Default multi-queue blk-mq I/O scheduler"
+	default DEFAULT_MQ_NONE
+	help
+	  Select the I/O scheduler which will be used by default for blk-mq
+	  managed block devices with multiple queues.
+
+	config DEFAULT_MQ_DEADLINE
+		bool "MQ Deadline" if MQ_IOSCHED_DEADLINE=y
+
+	config DEFAULT_MQ_NONE
+		bool "None"
+
+endchoice
+
+config DEFAULT_MQ_IOSCHED
+	string
+	default "mq-deadline" if DEFAULT_MQ_DEADLINE
+	default "none" if DEFAULT_MQ_NONE
+
 endmenu
 
 endif
diff --git a/block/Makefile b/block/Makefile
index a827f988c4e6..6ba1b1bc9529 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -6,7 +6,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
 			blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
-			blk-mq-sysfs.o blk-mq-cpumap.o ioctl.o \
+			blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
 			genhd.o scsi_ioctl.o partition-generic.o ioprio.o \
 			badblocks.o partitions/
 
@@ -18,6 +18,7 @@ obj-$(CONFIG_BLK_DEV_THROTTLING)	+= blk-throttle.o
 obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
 obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
 obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
+obj-$(CONFIG_MQ_IOSCHED_DEADLINE)	+= mq-deadline.o
 
 obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
 obj-$(CONFIG_BLK_CMDLINE_PARSER)	+= cmdline-parser.o
@@ -25,3 +26,5 @@ obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o
 obj-$(CONFIG_BLK_MQ_PCI)	+= blk-mq-pci.o
 obj-$(CONFIG_BLK_DEV_ZONED)	+= blk-zoned.o
 obj-$(CONFIG_BLK_WBT)		+= blk-wbt.o
+obj-$(CONFIG_BLK_DEBUG_FS)	+= blk-mq-debugfs.o
+obj-$(CONFIG_BLK_SED_OPAL)	+= sed-opal.o
diff --git a/block/bio.c b/block/bio.c
index 2b375020fc49..d3c26d1cb1da 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1403,7 +1403,7 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 	bio_set_flag(bio, BIO_USER_MAPPED);
 
 	/*
-	 * subtle -- if __bio_map_user() ended up bouncing a bio,
+	 * subtle -- if bio_map_user_iov() ended up bouncing a bio,
 	 * it would normally disappear when its bi_end_io is run.
 	 * however, we need it for the unmap, so grab an extra
 	 * reference to it
@@ -1445,8 +1445,8 @@ static void __bio_unmap_user(struct bio *bio)
  *	bio_unmap_user	-	unmap a bio
  *	@bio:		the bio being unmapped
  *
- *	Unmap a bio previously mapped by bio_map_user(). Must be called with
- *	a process context.
+ *	Unmap a bio previously mapped by bio_map_user_iov(). Must be called from
+ *	process context.
  *
  *	bio_unmap_user() may sleep.
  */
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 8ba0af780e88..fb59a3edc778 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1223,7 +1223,10 @@ int blkcg_activate_policy(struct request_queue *q,
 	if (blkcg_policy_enabled(q, pol))
 		return 0;
 
-	blk_queue_bypass_start(q);
+	if (q->mq_ops)
+		blk_mq_freeze_queue(q);
+	else
+		blk_queue_bypass_start(q);
 pd_prealloc:
 	if (!pd_prealloc) {
 		pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q->node);
@@ -1261,7 +1264,10 @@ pd_prealloc:
 
 	spin_unlock_irq(q->queue_lock);
 out_bypass_end:
-	blk_queue_bypass_end(q);
+	if (q->mq_ops)
+		blk_mq_unfreeze_queue(q);
+	else
+		blk_queue_bypass_end(q);
 	if (pd_prealloc)
 		pol->pd_free_fn(pd_prealloc);
 	return ret;
@@ -1284,7 +1290,11 @@ void blkcg_deactivate_policy(struct request_queue *q,
 	if (!blkcg_policy_enabled(q, pol))
 		return;
 
-	blk_queue_bypass_start(q);
+	if (q->mq_ops)
+		blk_mq_freeze_queue(q);
+	else
+		blk_queue_bypass_start(q);
+
 	spin_lock_irq(q->queue_lock);
 
 	__clear_bit(pol->plid, q->blkcg_pols);
@@ -1304,7 +1314,11 @@ void blkcg_deactivate_policy(struct request_queue *q,
 	}
 
 	spin_unlock_irq(q->queue_lock);
-	blk_queue_bypass_end(q);
+
+	if (q->mq_ops)
+		blk_mq_unfreeze_queue(q);
+	else
+		blk_queue_bypass_end(q);
 }
 EXPORT_SYMBOL_GPL(blkcg_deactivate_policy);
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 61ba08c58b64..b2df55a65250 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -39,6 +39,7 @@
 
 #include "blk.h"
 #include "blk-mq.h"
+#include "blk-mq-sched.h"
 #include "blk-wbt.h"
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
@@ -134,6 +135,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	rq->cmd = rq->__cmd;
 	rq->cmd_len = BLK_MAX_CDB;
 	rq->tag = -1;
+	rq->internal_tag = -1;
 	rq->start_time = jiffies;
 	set_start_time_ns(rq);
 	rq->part = NULL;
@@ -525,12 +527,14 @@ void blk_set_queue_dying(struct request_queue *q)
 	else {
 		struct request_list *rl;
 
+		spin_lock_irq(q->queue_lock);
 		blk_queue_for_each_rl(rl, q) {
 			if (rl->rq_pool) {
 				wake_up(&rl->wait[BLK_RW_SYNC]);
 				wake_up(&rl->wait[BLK_RW_ASYNC]);
 			}
 		}
+		spin_unlock_irq(q->queue_lock);
 	}
 }
 EXPORT_SYMBOL_GPL(blk_set_queue_dying);
@@ -1033,29 +1037,13 @@ static bool blk_rq_should_init_elevator(struct bio *bio)
 	 * Flush requests do not use the elevator so skip initialization.
 	 * This allows a request to share the flush and elevator data.
 	 */
-	if (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA))
+	if (op_is_flush(bio->bi_opf))
 		return false;
 
 	return true;
 }
 
 /**
- * rq_ioc - determine io_context for request allocation
- * @bio: request being allocated is for this bio (can be %NULL)
- *
- * Determine io_context to use for request allocation for @bio.  May return
- * %NULL if %current->io_context doesn't exist.
- */
-static struct io_context *rq_ioc(struct bio *bio)
-{
-#ifdef CONFIG_BLK_CGROUP
-	if (bio && bio->bi_ioc)
-		return bio->bi_ioc;
-#endif
-	return current->io_context;
-}
-
-/**
  * __get_request - get a free request
  * @rl: request list to allocate from
  * @op: operation and flags
@@ -1655,7 +1643,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 		return BLK_QC_T_NONE;
 	}
 
-	if (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA)) {
+	if (op_is_flush(bio->bi_opf)) {
 		spin_lock_irq(q->queue_lock);
 		where = ELEVATOR_INSERT_FLUSH;
 		goto get_rq;
@@ -1894,7 +1882,7 @@ generic_make_request_checks(struct bio *bio)
 	 * drivers without flush support don't have to worry
 	 * about them.
 	 */
-	if ((bio->bi_opf & (REQ_PREFLUSH | REQ_FUA)) &&
+	if (op_is_flush(bio->bi_opf) &&
 	    !test_bit(QUEUE_FLAG_WC, &q->queue_flags)) {
 		bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA);
 		if (!nr_sectors) {
@@ -2143,7 +2131,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 	if (q->mq_ops) {
 		if (blk_queue_io_stat(q))
 			blk_account_io_start(rq, true);
-		blk_mq_insert_request(rq, false, true, false);
+		blk_mq_sched_insert_request(rq, false, true, false, false);
 		return 0;
 	}
 
@@ -2159,7 +2147,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 	 */
 	BUG_ON(blk_queued_rq(rq));
 
-	if (rq->cmd_flags & (REQ_PREFLUSH | REQ_FUA))
+	if (op_is_flush(rq->cmd_flags))
 		where = ELEVATOR_INSERT_FLUSH;
 
 	add_acct_request(q, rq, where);
@@ -3270,7 +3258,7 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 		/*
 		 * rq is already accounted, so use raw insert
 		 */
-		if (rq->cmd_flags & (REQ_PREFLUSH | REQ_FUA))
+		if (op_is_flush(rq->cmd_flags))
 			__elv_add_request(q, rq, ELEVATOR_INSERT_FLUSH);
 		else
 			__elv_add_request(q, rq, ELEVATOR_INSERT_SORT_MERGE);
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 3ecb00a6cf45..ed1f10165268 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -9,6 +9,7 @@
 #include <linux/sched/sysctl.h>
 
 #include "blk.h"
+#include "blk-mq-sched.h"
 
 /*
  * for max sense size
@@ -65,7 +66,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	 * be reused after dying flag is set
 	 */
 	if (q->mq_ops) {
-		blk_mq_insert_request(rq, at_head, true, false);
+		blk_mq_sched_insert_request(rq, at_head, true, false, false);
 		return;
 	}
 
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 20b7c7a02f1c..4427896641ac 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -74,6 +74,7 @@
 #include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-tag.h"
+#include "blk-mq-sched.h"
 
 /* FLUSH/FUA sequences */
 enum {
@@ -391,9 +392,10 @@ static void mq_flush_data_end_io(struct request *rq, int error)
 	 * the comment in flush_end_io().
 	 */
 	spin_lock_irqsave(&fq->mq_flush_lock, flags);
-	if (blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error))
-		blk_mq_run_hw_queue(hctx, true);
+	blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error);
 	spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
+
+	blk_mq_run_hw_queue(hctx, true);
 }
 
 /**
@@ -453,9 +455,9 @@ void blk_insert_flush(struct request *rq)
 	 */
 	if ((policy & REQ_FSEQ_DATA) &&
 	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
-		if (q->mq_ops) {
-			blk_mq_insert_request(rq, false, true, false);
-		} else
+		if (q->mq_ops)
+			blk_mq_sched_insert_request(rq, false, true, false, false);
+		else
 			list_add_tail(&rq->queuelist, &q->queue_head);
 		return;
 	}
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 381cb50a673c..fe186a9eade9 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -43,8 +43,10 @@ static void ioc_exit_icq(struct io_cq *icq)
 	if (icq->flags & ICQ_EXITED)
 		return;
 
-	if (et->ops.elevator_exit_icq_fn)
-		et->ops.elevator_exit_icq_fn(icq);
+	if (et->uses_mq && et->ops.mq.exit_icq)
+		et->ops.mq.exit_icq(icq);
+	else if (!et->uses_mq && et->ops.sq.elevator_exit_icq_fn)
+		et->ops.sq.elevator_exit_icq_fn(icq);
 
 	icq->flags |= ICQ_EXITED;
 }
@@ -383,8 +385,10 @@ struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q,
 	if (likely(!radix_tree_insert(&ioc->icq_tree, q->id, icq))) {
 		hlist_add_head(&icq->ioc_node, &ioc->icq_list);
 		list_add(&icq->q_node, &q->icq_list);
-		if (et->ops.elevator_init_icq_fn)
-			et->ops.elevator_init_icq_fn(icq);
+		if (et->uses_mq && et->ops.mq.init_icq)
+			et->ops.mq.init_icq(icq);
+		else if (!et->uses_mq && et->ops.sq.elevator_init_icq_fn)
+			et->ops.sq.elevator_init_icq_fn(icq);
 	} else {
 		kmem_cache_free(et->icq_cache, icq);
 		icq = ioc_lookup_icq(ioc, q);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 182398cb1524..6aa43dec5af4 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -763,8 +763,8 @@ int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_allow_rq_merge_fn)
-		if (!e->type->ops.elevator_allow_rq_merge_fn(q, rq, next))
+	if (!e->uses_mq && e->type->ops.sq.elevator_allow_rq_merge_fn)
+		if (!e->type->ops.sq.elevator_allow_rq_merge_fn(q, rq, next))
 			return 0;
 
 	return attempt_merge(q, rq, next);
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
new file mode 100644
index 000000000000..5cd2b435a9f5
--- /dev/null
+++ b/block/blk-mq-debugfs.c
@@ -0,0 +1,756 @@
+/*
+ * Copyright (C) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/debugfs.h>
+
+#include <linux/blk-mq.h>
+#include "blk-mq.h"
+#include "blk-mq-tag.h"
+
+struct blk_mq_debugfs_attr {
+	const char *name;
+	umode_t mode;
+	const struct file_operations *fops;
+};
+
+static struct dentry *block_debugfs_root;
+
+static int blk_mq_debugfs_seq_open(struct inode *inode, struct file *file,
+				   const struct seq_operations *ops)
+{
+	struct seq_file *m;
+	int ret;
+
+	ret = seq_open(file, ops);
+	if (!ret) {
+		m = file->private_data;
+		m->private = inode->i_private;
+	}
+	return ret;
+}
+
+static int hctx_state_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	seq_printf(m, "0x%lx\n", hctx->state);
+	return 0;
+}
+
+static int hctx_state_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_state_show, inode->i_private);
+}
+
+static const struct file_operations hctx_state_fops = {
+	.open		= hctx_state_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int hctx_flags_show(struct seq_file *m, void