Merge branch 'master' into for-next

Sync with Linus' tree so that patches against newer codebase can be applied.

Signed-off-by: Jiri Kosina <jkosina@suse.cz>

30 files changed, 1402 insertions, 609 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 161491d0a879..0363cd731320 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -88,6 +88,19 @@ config BLK_DEV_INTEGRITY
 	T10/SCSI Data Integrity Field or the T13/ATA External Path
 	Protection.  If in doubt, say N.
 
+config BLK_DEV_DAX
+	bool "Block device DAX support"
+	depends on FS_DAX
+	depends on BROKEN
+	help
+	  When DAX support is available (CONFIG_FS_DAX) raw block
+	  devices can also support direct userspace access to the
+	  storage capacity via MMAP(2) similar to a file on a
+	  DAX-enabled filesystem.  However, the DAX I/O-path disables
+	  some standard I/O-statistics, and the MMAP(2) path has some
+	  operational differences due to bypassing the page
+	  cache.  If in doubt, say N.
+
 config BLK_DEV_THROTTLING
 	bool "Block layer bio throttling support"
 	depends on BLK_CGROUP=y
diff --git a/block/Makefile b/block/Makefile
index 00ecc97629db..9eda2322b2d4 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -5,10 +5,10 @@
 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-iopoll.o blk-lib.o blk-mq.o blk-mq-tag.o \
+			blk-lib.o blk-mq.o blk-mq-tag.o \
 			blk-mq-sysfs.o blk-mq-cpu.o blk-mq-cpumap.o ioctl.o \
 			genhd.o scsi_ioctl.o partition-generic.o ioprio.o \
-			partitions/
+			badblocks.o partitions/
 
 obj-$(CONFIG_BOUNCE)	+= bounce.o
 obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
diff --git a/block/badblocks.c b/block/badblocks.c
new file mode 100644
index 000000000000..7be53cb1cc3c
--- /dev/null
+++ b/block/badblocks.c
@@ -0,0 +1,585 @@
+/*
+ * Bad block management
+ *
+ * - Heavily based on MD badblocks code from Neil Brown
+ *
+ * Copyright (c) 2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ */
+
+#include <linux/badblocks.h>
+#include <linux/seqlock.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+
+/**
+ * badblocks_check() - check a given range for bad sectors
+ * @bb:		the badblocks structure that holds all badblock information
+ * @s:		sector (start) at which to check for badblocks
+ * @sectors:	number of sectors to check for badblocks
+ * @first_bad:	pointer to store location of the first badblock
+ * @bad_sectors: pointer to store number of badblocks after @first_bad
+ *
+ * We can record which blocks on each device are 'bad' and so just
+ * fail those blocks, or that stripe, rather than the whole device.
+ * Entries in the bad-block table are 64bits wide.  This comprises:
+ * Length of bad-range, in sectors: 0-511 for lengths 1-512
+ * Start of bad-range, sector offset, 54 bits (allows 8 exbibytes)
+ *  A 'shift' can be set so that larger blocks are tracked and
+ *  consequently larger devices can be covered.
+ * 'Acknowledged' flag - 1 bit. - the most significant bit.
+ *
+ * Locking of the bad-block table uses a seqlock so badblocks_check
+ * might need to retry if it is very unlucky.
+ * We will sometimes want to check for bad blocks in a bi_end_io function,
+ * so we use the write_seqlock_irq variant.
+ *
+ * When looking for a bad block we specify a range and want to
+ * know if any block in the range is bad.  So we binary-search
+ * to the last range that starts at-or-before the given endpoint,
+ * (or "before the sector after the target range")
+ * then see if it ends after the given start.
+ *
+ * Return:
+ *  0: there are no known bad blocks in the range
+ *  1: there are known bad block which are all acknowledged
+ * -1: there are bad blocks which have not yet been acknowledged in metadata.
+ * plus the start/length of the first bad section we overlap.
+ */
+int badblocks_check(struct badblocks *bb, sector_t s, int sectors,
+			sector_t *first_bad, int *bad_sectors)
+{
+	int hi;
+	int lo;
+	u64 *p = bb->page;
+	int rv;
+	sector_t target = s + sectors;
+	unsigned seq;
+
+	if (bb->shift > 0) {
+		/* round the start down, and the end up */
+		s >>= bb->shift;
+		target += (1<<bb->shift) - 1;
+		target >>= bb->shift;
+		sectors = target - s;
+	}
+	/* 'target' is now the first block after the bad range */
+
+retry:
+	seq = read_seqbegin(&bb->lock);
+	lo = 0;
+	rv = 0;
+	hi = bb->count;
+
+	/* Binary search between lo and hi for 'target'
+	 * i.e. for the last range that starts before 'target'
+	 */
+	/* INVARIANT: ranges before 'lo' and at-or-after 'hi'
+	 * are known not to be the last range before target.
+	 * VARIANT: hi-lo is the number of possible
+	 * ranges, and decreases until it reaches 1
+	 */
+	while (hi - lo > 1) {
+		int mid = (lo + hi) / 2;
+		sector_t a = BB_OFFSET(p[mid]);
+
+		if (a < target)
+			/* This could still be the one, earlier ranges
+			 * could not.
+			 */
+			lo = mid;
+		else
+			/* This and later ranges are definitely out. */
+			hi = mid;
+	}
+	/* 'lo' might be the last that started before target, but 'hi' isn't */
+	if (hi > lo) {
+		/* need to check all range that end after 's' to see if
+		 * any are unacknowledged.
+		 */
+		while (lo >= 0 &&
+		       BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > s) {
+			if (BB_OFFSET(p[lo]) < target) {
+				/* starts before the end, and finishes after
+				 * the start, so they must overlap
+				 */
+				if (rv != -1 && BB_ACK(p[lo]))
+					rv = 1;
+				else
+					rv = -1;
+				*first_bad = BB_OFFSET(p[lo]);
+				*bad_sectors = BB_LEN(p[lo]);
+			}
+			lo--;
+		}
+	}
+
+	if (read_seqretry(&bb->lock, seq))
+		goto retry;
+
+	return rv;
+}
+EXPORT_SYMBOL_GPL(badblocks_check);
+
+/**
+ * badblocks_set() - Add a range of bad blocks to the table.
+ * @bb:		the badblocks structure that holds all badblock information
+ * @s:		first sector to mark as bad
+ * @sectors:	number of sectors to mark as bad
+ * @acknowledged: weather to mark the bad sectors as acknowledged
+ *
+ * This might extend the table, or might contract it if two adjacent ranges
+ * can be merged. We binary-search to find the 'insertion' point, then
+ * decide how best to handle it.
+ *
+ * Return:
+ *  0: success
+ *  1: failed to set badblocks (out of space)
+ */
+int badblocks_set(struct badblocks *bb, sector_t s, int sectors,
+			int acknowledged)
+{
+	u64 *p;
+	int lo, hi;
+	int rv = 0;
+	unsigned long flags;
+
+	if (bb->shift < 0)
+		/* badblocks are disabled */
+		return 0;
+
+	if (bb->shift) {
+		/* round the start down, and the end up */
+		sector_t next = s + sectors;
+
+		s >>= bb->shift;
+		next += (1<<bb->shift) - 1;
+		next >>= bb->shift;
+		sectors = next - s;
+	}
+
+	write_seqlock_irqsave(&bb->lock, flags);
+
+	p = bb->page;
+	lo = 0;
+	hi = bb->count;
+	/* Find the last range that starts at-or-before 's' */
+	while (hi - lo > 1) {
+		int mid = (lo + hi) / 2;
+		sector_t a = BB_OFFSET(p[mid]);
+
+		if (a <= s)
+			lo = mid;
+		else
+			hi = mid;
+	}
+	if (hi > lo && BB_OFFSET(p[lo]) > s)
+		hi = lo;
+
+	if (hi > lo) {
+		/* we found a range that might merge with the start
+		 * of our new range
+		 */
+		sector_t a = BB_OFFSET(p[lo]);
+		sector_t e = a + BB_LEN(p[lo]);
+		int ack = BB_ACK(p[lo]);
+
+		if (e >= s) {
+			/* Yes, we can merge with a previous range */
+			if (s == a && s + sectors >= e)
+				/* new range covers old */
+				ack = acknowledged;
+			else
+				ack = ack && acknowledged;
+
+			if (e < s + sectors)
+				e = s + sectors;
+			if (e - a <= BB_MAX_LEN) {
+				p[lo] = BB_MAKE(a, e-a, ack);
+				s = e;
+			} else {
+				/* does not all fit in one range,
+				 * make p[lo] maximal
+				 */
+				if (BB_LEN(p[lo]) != BB_MAX_LEN)
+					p[lo] = BB_MAKE(a, BB_MAX_LEN, ack);
+				s = a + BB_MAX_LEN;
+			}
+			sectors = e - s;
+		}
+	}
+	if (sectors && hi < bb->count) {
+		/* 'hi' points to the first range that starts after 's'.
+		 * Maybe we can merge with the start of that range
+		 */
+		sector_t a = BB_OFFSET(p[hi]);
+		sector_t e = a + BB_LEN(p[hi]);
+		int ack = BB_ACK(p[hi]);
+
+		if (a <= s + sectors) {
+			/* merging is possible */
+			if (e <= s + sectors) {
+				/* full overlap */
+				e = s + sectors;
+				ack = acknowledged;
+			} else
+				ack = ack && acknowledged;
+
+			a = s;
+			if (e - a <= BB_MAX_LEN) {
+				p[hi] = BB_MAKE(a, e-a, ack);
+				s = e;
+			} else {
+				p[hi] = BB_MAKE(a, BB_MAX_LEN, ack);
+				s = a + BB_MAX_LEN;
+			}
+			sectors = e - s;
+			lo = hi;
+			hi++;
+		}
+	}
+	if (sectors == 0 && hi < bb->count) {
+		/* we might be able to combine lo and hi */
+		/* Note: 's' is at the end of 'lo' */
+		sector_t a = BB_OFFSET(p[hi]);
+		int lolen = BB_LEN(p[lo]);
+		int hilen = BB_LEN(p[hi]);
+		int newlen = lolen + hilen - (s - a);
+
+		if (s >= a && newlen < BB_MAX_LEN) {
+			/* yes, we can combine them */
+			int ack = BB_ACK(p[lo]) && BB_ACK(p[hi]);
+
+			p[lo] = BB_MAKE(BB_OFFSET(p[lo]), newlen, ack);
+			memmove(p + hi, p + hi + 1,
+				(bb->count - hi - 1) * 8);
+			bb->count--;
+		}
+	}
+	while (sectors) {
+		/* didn't merge (it all).
+		 * Need to add a range just before 'hi'
+		 */
+		if (bb->count >= MAX_BADBLOCKS) {
+			/* No room for more */
+			rv = 1;
+			break;
+		} else {
+			int this_sectors = sectors;
+
+			memmove(p + hi + 1, p + hi,
+				(bb->count - hi) * 8);
+			bb->count++;
+
+			if (this_sectors > BB_MAX_LEN)
+				this_sectors = BB_MAX_LEN;
+			p[hi] = BB_MAKE(s, this_sectors, acknowledged);
+			sectors -= this_sectors;
+			s += this_sectors;
+		}
+	}
+
+	bb->changed = 1;
+	if (!acknowledged)
+		bb->unacked_exist = 1;
+	write_sequnlock_irqrestore(&bb->lock, flags);
+
+	return rv;
+}
+EXPORT_SYMBOL_GPL(badblocks_set);
+
+/**
+ * badblocks_clear() - Remove a range of bad blocks to the table.
+ * @bb:		the badblocks structure that holds all badblock information
+ * @s:		first sector to mark as bad
+ * @sectors:	number of sectors to mark as bad
+ *
+ * This may involve extending the table if we spilt a region,
+ * but it must not fail.  So if the table becomes full, we just
+ * drop the remove request.
+ *
+ * Return:
+ *  0: success
+ *  1: failed to clear badblocks
+ */
+int badblocks_clear(struct badblocks *bb, sector_t s, int sectors)
+{
+	u64 *p;
+	int lo, hi;
+	sector_t target = s + sectors;
+	int rv = 0;
+
+	if (bb->shift > 0) {
+		/* When clearing we round the start up and the end down.
+		 * This should not matter as the shift should align with
+		 * the block size and no rounding should ever be needed.
+		 * However it is better the think a block is bad when it
+		 * isn't than to think a block is not bad when it is.
+		 */
+		s += (1<<bb->shift) - 1;
+		s >>= bb->shift;
+		target >>= bb->shift;
+		sectors = target - s;
+	}
+
+	write_seqlock_irq(&bb->lock);
+
+	p = bb->page;
+	lo = 0;
+	hi = bb->count;
+	/* Find the last range that starts before 'target' */
+	while (hi - lo > 1) {
+		int mid = (lo + hi) / 2;
+		sector_t a = BB_OFFSET(p[mid]);
+
+		if (a < target)
+			lo = mid;
+		else
+			hi = mid;
+	}
+	if (hi > lo) {
+		/* p[lo] is the last range that could overlap the
+		 * current range.  Earlier ranges could also overlap,
+		 * but only this one can overlap the end of the range.
+		 */
+		if (BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > target) {
+			/* Partial overlap, leave the tail of this range */
+			int ack = BB_ACK(p[lo]);
+			sector_t a = BB_OFFSET(p[lo]);
+			sector_t end = a + BB_LEN(p[lo]);
+
+			if (a < s) {
+				/* we need to split this range */
+				if (bb->count >= MAX_BADBLOCKS) {
+					rv = -ENOSPC;
+					goto out;
+				}
+				memmove(p+lo+1, p+lo, (bb->count - lo) * 8);
+				bb->count++;
+				p[lo] = BB_MAKE(a, s-a, ack);
+				lo++;
+			}
+			p[lo] = BB_MAKE(target, end - target, ack);
+			/* there is no longer an overlap */
+			hi = lo;
+			lo--;
+		}
+		while (lo >= 0 &&
+		       BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > s) {
+			/* This range does overlap */
+			if (BB_OFFSET(p[lo]) < s) {
+				/* Keep the early parts of this range. */
+				int ack = BB_ACK(p[lo]);
+				sector_t start = BB_OFFSET(p[lo]);
+
+				p[lo] = BB_MAKE(start, s - start, ack);
+				/* now low doesn't overlap, so.. */
+				break;
+			}
+			lo--;
+		}
+		/* 'lo' is strictly before, 'hi' is strictly after,
+		 * anything between needs to be discarded
+		 */
+		if (hi - lo > 1) {
+			memmove(p+lo+1, p+hi, (bb->count - hi) * 8);
+			bb->count -= (hi - lo - 1);
+		}
+	}
+
+	bb->changed = 1;
+out:
+	write_sequnlock_irq(&bb->lock);
+	return rv;
+}
+EXPORT_SYMBOL_GPL(badblocks_clear);
+
+/**
+ * ack_all_badblocks() - Acknowledge all bad blocks in a list.
+ * @bb:		the badblocks structure that holds all badblock information
+ *
+ * This only succeeds if ->changed is clear.  It is used by
+ * in-kernel metadata updates
+ */
+void ack_all_badblocks(struct badblocks *bb)
+{
+	if (bb->page == NULL || bb->changed)
+		/* no point even trying */
+		return;
+	write_seqlock_irq(&bb->lock);
+
+	if (bb->changed == 0 && bb->unacked_exist) {
+		u64 *p = bb->page;
+		int i;
+
+		for (i = 0; i < bb->count ; i++) {
+			if (!BB_ACK(p[i])) {
+				sector_t start = BB_OFFSET(p[i]);
+				int len = BB_LEN(p[i]);
+
+				p[i] = BB_MAKE(start, len, 1);
+			}
+		}
+		bb->unacked_exist = 0;
+	}
+	write_sequnlock_irq(&bb->lock);
+}
+EXPORT_SYMBOL_GPL(ack_all_badblocks);
+
+/**
+ * badblocks_show() - sysfs access to bad-blocks list
+ * @bb:		the badblocks structure that holds all badblock information
+ * @page:	buffer received from sysfs
+ * @unack:	weather to show unacknowledged badblocks
+ *
+ * Return:
+ *  Length of returned data
+ */
+ssize_t badblocks_show(struct badblocks *bb, char *page, int unack)
+{
+	size_t len;
+	int i;
+	u64 *p = bb->page;
+	unsigned seq;
+
+	if (bb->shift < 0)
+		return 0;
+
+retry:
+	seq = read_seqbegin(&bb->lock);
+
+	len = 0;
+	i = 0;
+
+	while (len < PAGE_SIZE && i < bb->count) {
+		sector_t s = BB_OFFSET(p[i]);
+		unsigned int length = BB_LEN(p[i]);
+		int ack = BB_ACK(p[i]);
+
+		i++;
+
+		if (unack && ack)
+			continue;
+
+		len += snprintf(page+len, PAGE_SIZE-len, "%llu %u\n",
+				(unsigned long long)s << bb->shift,
+				length << bb->shift);
+	}
+	if (unack && len == 0)
+		bb->unacked_exist = 0;
+
+	if (read_seqretry(&bb->lock, seq))
+		goto retry;
+
+	return len;
+}
+EXPORT_SYMBOL_GPL(badblocks_show);
+
+/**
+ * badblocks_store() - sysfs access to bad-blocks list
+ * @bb:		the badblocks structure that holds all badblock information
+ * @page:	buffer received from sysfs
+ * @len:	length of data received from sysfs
+ * @unack:	weather to show unacknowledged badblocks
+ *
+ * Return:
+ *  Length of the buffer processed or -ve error.
+ */
+ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len,
+			int unack)
+{
+	unsigned long long sector;
+	int length;
+	char newline;
+
+	switch (sscanf(page, "%llu %d%c", &sector, &length, &newline)) {
+	case 3:
+		if (newline != '\n')
+			return -EINVAL;
+	case 2:
+		if (length <= 0)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (badblocks_set(bb, sector, length, !unack))
+		return -ENOSPC;
+	else
+		return len;
+}
+EXPORT_SYMBOL_GPL(badblocks_store);
+
+static int __badblocks_init(struct device *dev, struct badblocks *bb,
+		int enable)
+{
+	bb->dev = dev;
+	bb->count = 0;
+	if (enable)
+		bb->shift = 0;
+	else
+		bb->shift = -1;
+	if (dev)
+		bb->page = devm_kzalloc(dev, PAGE_SIZE, GFP_KERNEL);
+	else
+		bb->page = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!bb->page) {
+		bb->shift = -1;
+		return -ENOMEM;
+	}
+	seqlock_init(&bb->lock);
+
+	return 0;
+}
+
+/**
+ * badblocks_init() - initialize the badblocks structure
+ * @bb:		the badblocks structure that holds all badblock information
+ * @enable:	weather to enable badblocks accounting
+ *
+ * Return:
+ *  0: success
+ *  -ve errno: on error
+ */
+int badblocks_init(struct badblocks *bb, int enable)
+{
+	return __badblocks_init(NULL, bb, enable);
+}
+EXPORT_SYMBOL_GPL(badblocks_init);
+
+int devm_init_badblocks(struct device *dev, struct badblocks *bb)
+{
+	if (!bb)
+		return -EINVAL;
+	return __badblocks_init(dev, bb, 1);
+}
+EXPORT_SYMBOL_GPL(devm_init_badblocks);
+
+/**
+ * badblocks_exit() - free the badblocks structure
+ * @bb:		the badblocks structure that holds all badblock information
+ */
+void badblocks_exit(struct badblocks *bb)
+{
+	if (!bb)
+		return;
+	if (bb->dev)
+		devm_kfree(bb->dev, bb->page);
+	else
+		kfree(bb->page);
+	bb->page = NULL;
+}
+EXPORT_SYMBOL_GPL(badblocks_exit);
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index f6325d573c10..711e4d8de6fa 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -66,7 +66,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 	}
 
 	if (unlikely(!bip))
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	memset(bip, 0, sizeof(*bip));
 
@@ -89,7 +89,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 	return bip;
 err:
 	mempool_free(bip, bs->bio_integrity_pool);
-	return NULL;
+	return ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL(bio_integrity_alloc);
 
@@ -298,10 +298,10 @@ int bio_integrity_prep(struct bio *bio)
 
 	/* Allocate bio integrity payload and integrity vectors */
 	bip = bio_integrity_alloc(bio, GFP_NOIO, nr_pages);
-	if (unlikely(bip == NULL)) {
+	if (IS_ERR(bip)) {
 		printk(KERN_ERR "could not allocate data integrity bioset\n");
 		kfree(buf);
-		return -EIO;
+		return PTR_ERR(bip);
 	}
 
 	bip->bip_flags |= BIP_BLOCK_INTEGRITY;
@@ -465,9 +465,8 @@ int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
 	BUG_ON(bip_src == NULL);
 
 	bip = bio_integrity_alloc(bio, gfp_mask, bip_src->bip_vcnt);
-
-	if (bip == NULL)
-		return -EIO;
+	if (IS_ERR(bip))
+		return PTR_ERR(bip);
 
 	memcpy(bip->bip_vec, bip_src->bip_vec,
 	       bip_src->bip_vcnt * sizeof(struct bio_vec));
diff --git a/block/bio.c b/block/bio.c
index ad3f276d74bc..807d25e466ec 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -211,7 +211,7 @@ fallback:
 		bvl = mempool_alloc(pool, gfp_mask);
 	} else {
 		struct biovec_slab *bvs = bvec_slabs + *idx;
-		gfp_t __gfp_mask = gfp_mask & ~(__GFP_WAIT | __GFP_IO);
+		gfp_t __gfp_mask = gfp_mask & ~(__GFP_DIRECT_RECLAIM | __GFP_IO);
 
 		/*
 		 * Make this allocation restricted and don't dump info on
@@ -221,11 +221,11 @@ fallback:
 		__gfp_mask |= __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN;
 
 		/*
-		 * Try a slab allocation. If this fails and __GFP_WAIT
+		 * Try a slab allocation. If this fails and __GFP_DIRECT_RECLAIM
 		 * is set, retry with the 1-entry mempool
 		 */
 		bvl = kmem_cache_alloc(bvs->slab, __gfp_mask);
-		if (unlikely(!bvl && (gfp_mask & __GFP_WAIT))) {
+		if (unlikely(!bvl && (gfp_mask & __GFP_DIRECT_RECLAIM))) {
 			*idx = BIOVEC_MAX_IDX;
 			goto fallback;
 		}
@@ -296,13 +296,19 @@ void bio_reset(struct bio *bio)
 }
 EXPORT_SYMBOL(bio_reset);
 
-static void bio_chain_endio(struct bio *bio)
+static struct bio *__bio_chain_endio(struct bio *bio)
 {
 	struct bio *parent = bio->bi_private;
 
-	parent->bi_error = bio->bi_error;
-	bio_endio(parent);
+	if (!parent->bi_error)
+		parent->bi_error = bio->bi_error;
 	bio_put(bio);
+	return parent;
+}
+
+static void bio_chain_endio(struct bio *bio)
+{
+	bio_endio(__bio_chain_endio(bio));
 }
 
 /*
@@ -395,12 +401,12 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
  *   If @bs is NULL, uses kmalloc() to allocate the bio; else the allocation is
  *   backed by the @bs's mempool.
  *
- *   When @bs is not NULL, if %__GFP_WAIT is set then bio_alloc will always be
- *   able to allocate a bio. This is due to the mempool guarantees. To make this
- *   work, callers must never allocate more than 1 bio at a time from this pool.
- *   Callers that need to allocate more than 1 bio must always submit the
- *   previously allocated bio for IO before attempting to allocate a new one.
- *   Failure to do so can cause deadlocks under memory pressure.
+ *   When @bs is not NULL, if %__GFP_DIRECT_RECLAIM is set then bio_alloc will
+ *   always be able to allocate a bio. This is due to the mempool guarantees.
+ *   To make this work, callers must never allocate more than 1 bio at a time
+ *   from this pool. Callers that need to allocate more than 1 bio must always
+ *   submit the previously allocated bio for IO before attempting to allocate
+ *   a new one. Failure to do so can cause deadlocks under memory pressure.
  *
  *   Note that when running under generic_make_request() (i.e. any block
  *   driver), bios are not submitted until after you return - see the code in
@@ -459,13 +465,13 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 		 * We solve this, and guarantee forward progress, with a rescuer
 		 * workqueue per bio_set. If we go to allocate and there are
 		 * bios on current->bio_list, we first try the allocation
-		 * without __GFP_WAIT; if that fails, we punt those bios we
-		 * would be blocking to the rescuer workqueue before we retry
-		 * with the original gfp_flags.
+		 * without __GFP_DIRECT_RECLAIM; if that fails, we punt those
+		 * bios we would be blocking to the rescuer workqueue before
+		 * we retry with the original gfp_flags.
 		 */
 
 		if (current->bio_list && !bio_list_empty(current->bio_list))
-			gfp_mask &= ~__GFP_WAIT;
+			gfp_mask &= ~__GFP_DIRECT_RECLAIM;
 
 		p = mempool_alloc(bs->bio_pool, gfp_mask);
 		if (!p && gfp_mask != saved_gfp) {
@@ -874,7 +880,7 @@ int submit_bio_wait(int rw, struct bio *bio)
 	bio->bi_private = &ret;
 	bio->bi_end_io = submit_bio_wait_endio;
 	submit_bio(rw, bio);
-	wait_for_completion(&ret.event);
+	wait_for_completion_io(&ret.event);
 
 	return ret.error;
 }
@@ -1090,9 +1096,12 @@ int bio_uncopy_user(struct bio *bio)
 	if (!bio_flagged(bio, BIO_NULL_MAPPED)) {
 		/*
 		 * if we're in a workqueue, the request is orphaned, so
-		 * don't copy into a random user address space, just free.
+		 * don't copy into a random user address space, just free
+		 * and return -EINTR so user space doesn't expect any data.
 		 */
-		if (current->mm && bio_data_dir(bio) == READ)
+		if (!current->mm)
+			ret = -EINTR;
+		else if (bio_data_dir(bio) == READ)
 			ret = bio_copy_to_iter(bio, bmd->iter);
 		if (bmd->is_our_pages)
 			bio_free_pages(bio);
@@ -1125,7 +1134,7 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 	int i, ret;
 	int nr_pages = 0;
 	unsigned int len = iter->count;
-	unsigned int offset = map_data ? map_data->offset & ~PAGE_MASK : 0;
+	unsigned int offset = map_data ? offset_in_page(map_data->offset) : 0;
 
 	for (i = 0; i < iter->nr_segs; i++) {
 		unsigned long uaddr;
@@ -1304,7 +1313,7 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 			goto out_unmap;
 		}
 
-		offset = uaddr & ~PAGE_MASK;
+		offset = offset_in_page(uaddr);
 		for (j = cur_page; j < page_limit; j++) {
 			unsigned int bytes = PAGE_SIZE - offset;
 
@@ -1330,7 +1339,7 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 		 * release the pages we didn't map into the bio, if any
 		 */
 		while (j < page_limit)
-			page_cache_release(pages[j++]);
+			put_page(pages[j++]);
 	}
 
 	kfree(pages);
@@ -1356,7 +1365,7 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 	for (j = 0; j < nr_pages; j++) {
 		if (!pages[j])
 			break;
-		page_cache_release(pages[j]);
+		put_page(pages[j]);
 	}
  out:
 	kfree(pages);
@@ -1376,7 +1385,7 @@ static void __bio_unmap_user(struct bio *bio)
 		if (bio_data_dir(bio) == READ)
 			set_page_dirty_lock(bvec->bv_page);
 
-		page_cache_release(bvec->bv_page);
+		put_page(bvec->bv_page);
 	}
 
 	bio_put(bio);
@@ -1606,8 +1615,8 @@ static void bio_release_pages(struct bio *bio)
  * the BIO and the offending pages and re-dirty the pages in process context.
  *
  * It is expected that bio_check_pages_dirty() will wholly own the BIO from
- * here on.  It will run one page_cache_release() against each page and will
- * run one bio_put() against the BIO.
+ * here on.  It will run one put_page() against each page and will run one
+ * bio_put() against the BIO.
  */
 
 static void bio_dirty_fn(struct work_struct *work);
@@ -1649,7 +1658,7 @@ void bio_check_pages_dirty(struct bio *bio)
 		struct page *page = bvec->bv_page;
 
 		if (PageDirty(page) || PageCompound(page)) {
-			page_cache_release(page);
+			put_page(page);
 			bvec->bv_page = NULL;
 		} else {
 			nr_clean_pages++;
@@ -1739,29 +1748,25 @@ static inline bool bio_remaining_done(struct bio *bio)
  **/
 void bio_endio(struct bio *bio)
 {
-	while (bio) {
-		if (unlikely(!bio_remaining_done(bio)))
-			break;
+again:
+	if (!bio_remaining_done(bio))
+		return;
 
-		/*
-		 * Need to have a real endio function for chained bios,
-		 * otherwise various corner cases will break (like stacking
-		 * block devices that save/restore bi_end_io) - however, we want
-		 * to avoid unbounded recursion and blowing the stack. Tail call
-		 * optimization would handle this, but compiling with frame
-		 * pointers also disables gcc's sibling call optimization.
-		 */
-		if (bio->bi_end_io == bio_chain_endio) {
-			struct bio *parent = bio->bi_private;
-			parent->bi_error = bio->bi_error;
-			bio_put(bio);
-			bio = parent;
-		} else {
-			if (bio->bi_end_io)
-				bio->bi_end_io(bio);
-			bio = NULL;
-		}
+	/*
+	 * Need to have a real endio function for chained bios, otherwise
+	 * various corner cases will break (like stacking block devices that
+	 * save/restore bi_end_io) - however, we want to avoid unbounded
+	 * recursion and blowing the stack. Tail call optimization would
+	 * handle this, but compiling with frame pointers also disables
+	 * gcc's sibling call optimization.
+	 */
+	if (bio->bi_end_io == bio_chain_endio) {
+		bio = __bio_chain_endio(bio);
+		goto again;
 	}
+
+	if (bio->bi_end_io)
+		bio->bi_end_io(bio);
 }
 EXPORT_SYMBOL(bio_endio);
 
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 5bcdfc10c23a..66e6f1aae02e 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -788,6 +788,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 {
 	struct gendisk *disk;
 	struct blkcg_gq *blkg;
+	struct module *owner;
 	unsigned int major, minor;
 	int key_len, part, ret;
 	char *body;
@@ -804,7 +805,9 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	if (!disk)
 		return -ENODEV;
 	if (part) {
+		owner = disk->fops->owner;
 		put_disk(disk);
+		module_put(owner);
 		return -ENODEV;
 	}
 
@@ -820,7 +823,9 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 		ret = PTR_ERR(blkg);
 		rcu_read_unlock();
 		spin_unlock_irq(disk->queue->queue_lock);
+		owner = disk->fops->owner;
 		put_disk(disk);
+		module_put(owner);
 		/*
 		 * If queue was bypassing, we should retry.  Do so after a
 		 * short msleep().  It isn't strictly necessary but queue
@@ -851,9 +856,13 @@ EXPORT_SYMBOL_GPL(blkg_conf_prep);
 void blkg_conf_finish(struct blkg_conf_ctx *ctx)
 	__releases(ctx->disk->queue->queue_lock) __releases(rcu)
 {
+	struct module *owner;
+
 	spin_unlock_irq(ctx->disk->queue->queue_lock);
 	rcu_read_unlock();
+	owner = ctx->disk->fops->owner;
 	put_disk(ctx->disk);
+	module_put(owner);
 }
 EXPORT_SYMBOL_GPL(blkg_conf_finish);
 
@@ -1127,15 +1136,15 @@ void blkcg_exit_queue(struct request_queue *q)
  * of the main cic data structures.  For now we allow a task to change
  * its cgroup only if it's the only owner of its ioc.
  */
-static int blkcg_can_attach(struct cgroup_subsys_state *css,
-			    struct cgroup_taskset *tset)
+static int blkcg_can_attach(struct cgroup_taskset *tset)
 {
 	struct task_struct *task;
+	struct cgroup_subsys_state *dst_css;
 	struct io_context *ioc;
 	int ret = 0;
 
 	/* task_lock() is needed to avoid races with exit_io_context() */
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, dst_css, tset) {
 		task_lock(task);
 		ioc = task->io_context;
 		if (ioc && atomic_read(&ioc->nr_tasks) > 1)
diff --git a/block/blk-core.c b/block/blk-core.c
index 89eec7965870..b60537b2c35b 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -51,7 +51,7 @@ DEFINE_IDA(blk_queue_ida);
 /*
  * For the allocated request tables
  */
-struct kmem_cache *request_cachep = NULL;
+struct kmem_cache *request_cachep;
 
 /*
  * For queue allocation
@@ -207,6 +207,22 @@ void blk_delay_queue(struct request_queue *q, unsigned long msecs)
 EXPORT_SYMBOL(blk_delay_queue);
 
 /**
+ * blk_start_queue_async - asynchronously restart a previously stopped queue
+ * @q:    The &struct request_queue in question
+ *
+ * Description:
+ *   blk_start_queue_async() will clear the stop flag on the queue, and
+ *   ensure that the request_fn for the queue is run from an async
+ *   context.
+ **/
+void blk_start_queue_async(struct request_queue *q)
+{
+	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
+	blk_run_queue_async(q);
+}
+EXPORT_SYMBOL(blk_start_queue_async);
+
+/**
  * blk_start_queue - restart a previously stopped queue
  * @q:    The &struct request_queue in question
  *
@@ -630,7 +646,7 @@ struct request_queue *blk_alloc_queue(gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(blk_alloc_queue);
 
-int blk_queue_enter(struct request_queue *q, gfp_t gfp)
+int blk_queue_enter(struct request_queue *q, bool nowait)
 {
 	while (true) {
 		int ret;
@@ -638,7 +654,7 @@ int blk_queue_enter(struct request_queue *q, gfp_t gfp)
 		if (percpu_ref_tryget_live(&q->q_usage_counter))
 			return 0;
 
-		if (!(gfp & __GFP_WAIT))
+		if (nowait)
 			return -EBUSY;
 
 		ret = wait_event_interruptible(q->mq_freeze_wq,
@@ -664,6 +680,13 @@ static void blk_queue_usage_counter_release(struct percpu_ref *ref)
 	wake_up_all(&q->mq_freeze_wq);
 }
 
+static void blk_rq_timed_out_timer(unsigned long data)
+{
+	struct request_queue *q = (struct request_queue *)data;
+
+	kblockd_schedule_work(&q->timeout_work);
+}
+
 struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 {
 	struct request_queue *q;
@@ -683,7 +706,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 		goto fail_id;
 
 	q->backing_dev_info.ra_pages =
-			(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
+			(VM_MAX_READAHEAD * 1024) / PAGE_SIZE;
 	q->backing_dev_info.capabilities = BDI_CAP_CGROUP_WRITEBACK;
 	q->backing_dev_info.name = "block";
 	q->node = node_id;
@@ -809,7 +832,7 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
 }
 EXPORT_SYMBOL(blk_init_queue_node);
 
-static void blk_queue_bio(struct request_queue *q, struct bio *bio);
+static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio);
 
 struct request_queue *
 blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
@@ -825,6 +848,7 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 	if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
 		goto fail;
 
+	INIT_WORK(&q->timeout_work, blk_timeout_work);
 	q->request_fn		= rfn;
 	q->prep_rq_fn		= NULL;
 	q->unprep_rq_fn		= NULL;
@@ -1206,8 +1230,8 @@ rq_starved:
  * @bio: bio to allocate request for (can be %NULL)
  * @gfp_mask: allocation mask
  *
- * Get a free request from @q.  If %__GFP_WAIT is set in @gfp_mask, this
- * function keeps retrying under memory pressure and fails iff @q is dead.
+ * Get a free request from @q.  If %__GFP_DIRECT_RECLAIM is set in @gfp_mask,
+ * this function keeps retrying under memory pressure and fails iff @q is dead.
  *
  * Must be called with @q->queue_lock held and,
  * Returns ERR_PTR on failure, with @q->queue_lock held.
@@ -1227,7 +1251,7 @@ retry:
 	if (!IS_ERR(rq))
 		return rq;
 
-	if (!(gfp_mask & __GFP_WAIT) || unlikely(blk_queue_dying(q))) {
+	if (!gfpflags_allow_blocking(gfp_mask) || unlikely(blk_queue_dying(q))) {
 		blk_put_rl(rl);
 		return rq;
 	}
@@ -1276,7 +1300,9 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw,
 struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
 {
 	if (q->mq_ops)
-		return blk_mq_alloc_request(q, rw, gfp_mask, false);
+		return blk_mq_alloc_request(q, rw,
+			(gfp_mask & __GFP_DIRECT_RECLAIM) ?
+				0 : BLK_MQ_REQ_NOWAIT);
 	else
 		return blk_old_get_request(q, rw, gfp_mask);
 }
@@ -1305,11 +1331,11 @@ EXPORT_SYMBOL(blk_get_request);
  * BUG.
  *
  * WARNING: When allocating/cloning a bio-chain, careful consideration should be
- * given to how you allocate bios. In particular, you cannot use __GFP_WAIT for
- * anything but the first bio in the chain. Otherwise you risk waiting for IO
- * completion of a bio that hasn't been submitted yet, thus resulting in a
- * deadlock. Alternatively bios should be allocated using bio_kmalloc() instead
- * of bio_alloc(), as that avoids the mempool deadlock.
+ * given to how you allocate bios. In particular, you cannot use
+ * __GFP_DIRECT_RECLAIM for anything but the first bio in the chain. Otherwise
+ * you risk waiting for IO completion of a bio that hasn't been submitted yet,
+ * thus resulting in a deadlock. Alternatively bios should be allocated using
+ * bio_kmalloc() instead of bio_alloc(), as that avoids the mempool deadlock.
  * If possible a big IO should be split into smaller parts when allocation
  * fails. Partial allocation should not be an error, or you risk a live-lock.
  */
@@ -1575,6 +1601,9 @@ bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
  * @q: request_queue new bio is being queued at
  * @bio: new bio being queued
  * @request_count: out parameter for number of traversed plugged requests
+ * @same_queue_rq: pointer to &struct request that gets filled in when
+ * another request associated with @q is found on the plug list
+ * (optional, may be %NULL)
  *
  * Determine whether @bio being queued on @q can be merged with a request
  * on %current's plugged list.  Returns %true if merge was successful,
@@ -1678,7 +1707,7 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 	blk_rq_bio_prep(req->q, req, bio);
 }
 
-static void blk_queue_bio(struct request_queue *q, struct bio *bio)
+static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 {
 	const bool sync = !!(bio->bi_rw & REQ_SYNC);
 	struct blk_plug *plug;
@@ -1686,8 +1715,6 @@ static void blk_queue_bio(struct request_queue *q, struct bio *bio)
 	struct request *req;
 	unsigned int request_count = 0;
 
-	blk_queue_split(q, &bio, q->bio_split);
-
 	/*
 	 * low level driver can indicate that it wants pages above a
 	 * certain limit bounced to low memory (ie for highmem, or even
@@ -1695,10 +1722,12 @@ static void blk_queue_bio(struct request_queue *q, struct bio *bio)
 	 */
 	blk_queue_bounce(q, &bio);
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
 		bio->bi_error = -EIO;
 		bio_endio(bio);
-		return;
+		return BLK_QC_T_NONE;
 	}
 
 	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
@@ -1713,7 +1742,7 @@ static void blk_queue_bio(struct request_queue *q, struct bio *bio)
 	 */
 	if (!blk_queue_nomerges(q)) {
 		if (blk_attempt_plug_merge(q, bio, &request_count, NULL))
-			return;
+			return BLK_QC_T_NONE;
 	} else
 		request_count = blk_plug_queued_count(q);
 
@@ -1791,6 +1820,8 @@ get_rq:
 out_unlock:
 		spin_unlock_irq(q->queue_lock);
 	}
+
+	return BLK_QC_T_NONE;
 }
 
 /*
@@ -1996,12 +2027,13 @@ end_io:
  * a lower device by calling into generic_make_request recursively, which
  * means the bio should NOT be touched after the call to ->make_request_fn.
  */
-void generic_make_request(struct bio *bio)
+blk_qc_t generic_make_request(struct bio *bio)
 {
 	struct bio_list bio_list_on_stack;
+	blk_qc_t ret = BLK_QC_T_NONE;
 
 	if (!generic_make_request_checks(bio))
-		return;
+		goto out;
 
 	/*
 	 * We only want one ->make_request_fn to be active at a time, else
@@ -2015,7 +2047,7 @@ void generic_make_request(struct bio *bio)
 	 */
 	if (current->bio_list) {
 		bio_list_add(current->bio_list, bio);
-		return;
+		goto out;
 	}
 
 	/* following loop may be a bit non-obvious, and so deserves some
@@ -2038,9 +2070,8 @@ void generic_make_request(struct bio *bio)
 	do {
 		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 
-		if (likely(blk_queue_enter(q, __GFP_WAIT) == 0)) {
-
-			q->make_request_fn(q, bio);
+		if (likely(blk_queue_enter(q, false) == 0)) {
+			ret = q->make_request_fn(q, bio);
 
 			blk_queue_exit(q);
 
@@ -2053,6 +2084,9 @@ void generic_make_request(struct bio *bio)
 		}
 	} while (bio);
 	current->bio_list = NULL; /* deactivate */
+
+out:
+	return ret;
 }
 EXPORT_SYMBOL(generic_make_request);
 
@@ -2066,7 +2100,7 @@ EXPORT_SYMBOL(generic_make_request);
  * interfaces; @bio must be presetup and ready for I/O.
  *
  */
-void submit_bio(int rw, struct bio *bio)
+blk_qc_t submit_bio(int rw, struct bio *bio)
 {
 	bio->bi_rw |= rw;
 
@@ -2100,12 +2134,13 @@ void submit_bio(int rw, struct bio *bio)
 		}
 	}
 
-	generic_make_request(bio);
+	return generic_make_request(bio);
 }
 EXPORT_SYMBOL(submit_bio);
 
 /**
- * blk_rq_check_limits - Helper function to check a request for the queue limit
+ * blk_cloned_rq_check_limits - Helper function to check a cloned request
+ *                              for new the queue limits
  * @q:  the queue
  * @rq: the request being checked
  *
@@ -2116,20 +2151,13 @@ EXPORT_SYMBOL(submit_bio);
  *    after it is inserted to @q, it should be checked against @q before
  *    the insertion using this generic function.
  *
- *    This function should also be useful for request stacking drivers
- *    in some cases below, so export this function.
  *    Request stacking drivers like request-based dm may change the queue
- *    limits while requests are in the queue (e.g. dm's table swapping).
- *    Such request stacking drivers should check those requests against
- *    the new queue limits again when they dispatch those requests,
- *    although such checkings are also done against the old queue limits
- *    when submitting requests.
+ *    limits when retrying requests on other queues. Those requests need
+ *    to be checked against the new queue limits again during dispatch.
  */
-int blk_rq_check_limits(struct request_queue *q, struct request *rq)
+static int blk_cloned_rq_check_limits(struct request_queue *q,
+				      struct request *rq)
 {
-	if (!rq_mergeable(rq))
-		return 0;
-
 	if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q, rq->cmd_flags)) {
 		printk(KERN_ERR "%s: over max size limit.\n", __func__);
 		return -EIO;
@@ -2149,7 +2177,6 @@ int blk_rq_check_limits(struct request_queue *q, struct request *rq)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(blk_rq_check_limits);
 
 /**
  * blk_insert_cloned_request - Helper for stacking drivers to submit a request
@@ -2161,7 +2188,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 	unsigned long flags;
 	int where = ELEVATOR_INSERT_BACK;
 
-	if (blk_rq_check_limits(q, rq))
+	if (blk_cloned_rq_check_limits(q, rq))
 		return -EIO;
 
 	if (rq->rq_disk &&
@@ -2171,7 +2198,7 @@ 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, true);
+		blk_mq_insert_request(rq, false, true, false);
 		return 0;
 	}
 
@@ -2428,14 +2455,16 @@ struct request *blk_peek_request(struct request_queue *q)
 
 			rq = NULL;
 			break;
-		} else if (ret == BLKPREP_KILL) {
+		} else if (ret == BLKPREP_KILL || ret == BLKPREP_INVALID) {
+			int err = (ret == BLKPREP_INVALID) ? -EREMOTEIO : -EIO;
+
 			rq->cmd_flags |= REQ_QUIET;
 			/*
 			 * Mark this request as started so we don't trigger
 			 * any debug logic in the end I/O path.
 			 */
 			blk_start_request(rq);
-			__blk_end_request_all(rq, -EIO);
+			__blk_end_request_all(rq, err);
 		} else {
 			printk(KERN_ERR "%s: bad return=%d\n", __func__, ret);
 			break;
@@ -3306,6 +3335,47 @@ void blk_finish_plug(struct blk_plug *plug)
 }
 EXPORT_SYMBOL(blk_finish_plug);
 
+bool blk_poll(struct request_queue *q, blk_qc_t cookie)
+{
+	struct blk_plug *plug;
+	long state;
+
+	if (!q->mq_ops || !q->mq_ops->poll || !blk_qc_t_valid(cookie) ||
+	    !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
+		return false;
+
+	plug = current->plug;
+	if (plug)
+		blk_flush_plug_list(plug, false);
+
+	state = current->state;
+	while (!need_resched()) {
+		unsigned int queue_num = blk_qc_t_to_queue_num(cookie);
+		struct blk_mq_hw_ctx *hctx = q->queue_hw_ctx[queue_num];
+		int ret;
+
+		hctx->poll_invoked++;
+
+		ret = q->mq_ops->poll(hctx, blk_qc_t_to_tag(cookie));
+		if (ret > 0) {
+			hctx->poll_success++;
+			set_current_state(TASK_RUNNING);
+			return true;
+		}
+
+		if (signal_pending_state(state, current))
+			set_current_state(TASK_RUNNING);
+
+		if (current->state == TASK_RUNNING)
+			return true;
+		if (ret < 0)
+			break;
+		cpu_relax();
+	}
+
+	return false;
+}
+
 #ifdef CONFIG_PM
 /**
  * blk_pm_runtime_init - Block layer runtime PM initialization routine
@@ -3362,6 +3432,9 @@ int blk_pre_runtime_suspend(struct request_queue *q)
 {
 	int ret = 0;
 
+	if (!q->dev)
+		return ret;
+
 	spin_lock_irq(q->queue_lock);
 	if (q->nr_pending) {
 		ret = -EBUSY;
@@ -3389,6 +3462,9 @@ EXPORT_SYMBOL(blk_pre_runtime_suspend);
  */
 void blk_post_runtime_suspend(struct request_queue *q, int err)
 {
+	if (!q->dev)
+		return;
+
 	spin_lock_irq(q->queue_lock);
 	if (!err) {
 		q->rpm_status = RPM_SUSPENDED;
@@ -3413,6 +3489,9 @@ EXPORT_SYMBOL(blk_post_runtime_suspend);
  */
 void blk_pre_runtime_resume(struct request_queue *q)
 {
+	if (!q->dev)
+		return;
+
 	spin_lock_irq(q->queue_lock);
 	q->rpm_status = RPM_RESUMING;
 	spin_unlock_irq(q->queue_lock);
@@ -3435,6 +3514,9 @@ EXPORT_SYMBOL(blk_pre_runtime_resume);
  */
 void blk_post_runtime_resume(struct request_queue *q, int err)
 {
+	if (!q->dev)
+		return;
+
 	spin_lock_irq(q->queue_lock);
 	if (!err) {
 		q->rpm_status = RPM_ACTIVE;
@@ -3447,6 +3529,30 @@ void blk_post_runtime_resume(struct request_queue *q, int err)
 	spin_unlock_irq(q->queue_lock);
 }
 EXPORT_SYMBOL(blk_post_runtime_resume);
+
+/**
+ * blk_set_runtime_active - Force runtime status of the queue to be active
+ * @q: the queue of the device
+ *
+ * If the device is left runtime suspended during system suspend the resume
+ * hook typically resumes the device and corrects runtime status
+ * accordingly. However, that does not affect the queue runtime PM status
+ * which is still "suspended". This prevents processing requests from the
+ * queue.
+ *
+ * This function can be used in driver's resume hook to correct queue
+ * runtime PM status and re-enable peeking requests from the queue. It
+ * should be called before first request is added to the queue.
+ */
+void blk_set_runtime_active(struct request_queue *q)
+{
+	spin_lock_irq(q->queue_lock);
+	q->rpm_status = RPM_ACTIVE;
+	pm_runtime_mark_last_busy(q->dev);
+	pm_request_autosuspend(q->dev);
+	spin_unlock_irq(q->queue_lock);
+}
+EXPORT_SYMBOL(blk_set_runtime_active);
 #endif
 
 int __init blk_dev_init(void)
@@ -3463,7 +3569,7 @@ int __init blk_dev_init(void)
 	request_cachep = kmem_cache_create("blkdev_requests",
 			sizeof(struct request), 0, SLAB_PANIC, NULL);
 
-	blk_requestq_cachep = kmem_cache_create("blkdev_queue",
+	blk_requestq_cachep = kmem_cache_create("request_queue",
 			sizeof(struct request_queue), 0, SLAB_PANIC, NULL);
 
 	return 0;
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 1a27f45ec776..381cb50a673c 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -289,7 +289,7 @@ struct io_context *get_task_io_context(struct task_struct *task,
 {
 	struct io_context *ioc;
 
-	might_sleep_if(gfp_flags & __GFP_WAIT);
+	might_sleep_if(gfpflags_allow_blocking(gfp_flags));
 
 	do {
 		task_lock(task);
diff --git a/block/blk-iopoll.c b/block/blk-iopoll.c
deleted file mode 100644
index 0736729d6494..000000000000
--- a/block/blk-iopoll.c
+++ /dev/null
@@ -1,224 +0,0 @@
-/*
- * Functions related to interrupt-poll handling in the block layer. This
- * is similar to NAPI for network devices.
- */
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/bio.h>
-#include <linux/blkdev.h>
-#include <linux/interrupt.h>
-#include <linux/cpu.h>
-#include <linux/blk-iopoll.h>
-#include <linux/delay.h>
-
-#include "blk.h"
-
-static unsigned int blk_iopoll_budget __read_mostly = 256;
-
-static DEFINE_PER_CPU(struct list_head, blk_cpu_iopoll);
-
-/**
- * blk_iopoll_sched - Schedule a run of the iopoll handler
- * @iop:      The parent iopoll structure
- *
- * Description:
- *     Add this blk_iopoll structure to the pending poll list and trigger the
- *     raise of the blk iopoll softirq. The driver must already have gotten a
- *     successful return from blk_iopoll_sched_prep() before calling this.
- **/
-void blk_iopoll_sched(struct blk_iopoll *iop)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	list_add_tail(&iop->list, this_cpu_ptr(&blk_cpu_iopoll));
-	__raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL(blk_iopoll_sched);
-
-/**
- * __blk_iopoll_complete - Mark this @iop as un-polled again
- * @iop:      The parent iopoll structure
- *
- * Description:
- *     See blk_iopoll_complete(). This function must be called with interrupts
- *     disabled.
- **/
-void __blk_iopoll_complete(struct blk_iopoll *iop)
-{
-	list_del(&iop->list);
-	smp_mb__before_atomic();
-	clear_bit_unlock(IOPOLL_F_SCHED, &iop->state);
-}
-EXPORT_SYMBOL(__blk_iopoll_complete);
-
-/**
- * blk_iopoll_complete - Mark this @iop as un-polled again
- * @iop:      The parent iopoll structure
- *
- * Description:
- *     If a driver consumes less than the assigned budget in its run of the
- *     iopoll handler, it'll end the polled mode by calling this function. The
- *     iopoll handler will not be invoked again before blk_iopoll_sched_prep()
- *     is called.
- **/
-void blk_iopoll_complete(struct blk_iopoll *iop)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__blk_iopoll_complete(iop);
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL(blk_iopoll_complete);
-
-static void blk_iopoll_softirq(struct softirq_action *h)
-{
-	struct list_head *list = this_cpu_ptr(&blk_cpu_iopoll);
-	int rearm = 0, budget = blk_iopoll_budget;
-	unsigned long start_time = jiffies;
-
-	local_irq_disable();
-
-	while (!list_empty(list)) {
-		struct blk_iopoll *iop;
-		int work, weight;
-
-		/*
-		 * If softirq window is exhausted then punt.
-		 */
-		if (budget <= 0 || time_after(jiffies, start_time)) {
-			rearm = 1;
-			break;
-		}
-
-		local_irq_enable();
-
-		/* Even though interrupts have been re-enabled, this
-		 * access is safe because interrupts can only add new
-		 * entries to the tail of this list, and only ->poll()
-		 * calls can remove this head entry from the list.
-		 */
-		iop = list_entry(list->next, struct blk_iopoll, list);
-
-		weight = iop->weight;
-		work = 0;
-		if (test_bit(IOPOLL_F_SCHED, &iop->state))
-			work = iop->poll(iop, weight);
-
-		budget -= work;
-
-		local_irq_disable();
-
-		/*
-		 * Drivers must not modify the iopoll state, if they
-		 * consume their assigned weight (or more, some drivers can't
-		 * easily just stop processing, they have to complete an
-		 * entire mask of commands).In such cases this code
-		 * still "owns" the iopoll instance and therefore can
-		 * move the instance around on the list at-will.
-		 */
-		if (work >= weight) {
-			if (blk_iopoll_disable_pending(iop))
-				__blk_iopoll_complete(iop);
-			else
-				list_move_tail(&iop->list, list);
-		}
-	}
-
-	if (rearm)
-		__raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
-
-	local_irq_enable();
-}
-
-/**
- * blk_iopoll_disable - Disable iopoll on this @iop
- * @iop:      The parent iopoll structure
- *
- * Description:
- *     Disable io polling and wait for any pending callbacks to have completed.
- **/
-void blk_iopoll_disable(struct blk_iopoll *iop)
-{
-	set_bit(IOPOLL_F_DISABLE, &iop->state);
-	while (test_and_set_bit(IOPOLL_F_SCHED, &iop->state))
-		msleep(1);
-	clear_bit(IOPOLL_F_DISABLE, &iop->state);
-}
-EXPORT_SYMBOL(blk_iopoll_disable);
-
-/**
- * blk_iopoll_enable - Enable iopoll on this @iop
- * @iop:      The parent iopoll structure
- *
- * Description:
- *     Enable iopoll on this @iop. Note that the handler run will not be
- *     scheduled, it will only mark it as active.
- **/
-void blk_iopoll_enable(struct blk_iopoll *iop)
-{
-	BUG_ON(!test_bit(IOPOLL_F_SCHED, &iop->state));
-	smp_mb__before_atomic();
-	clear_bit_unlock(IOPOLL_F_SCHED, &iop->state);
-}
-EXPORT_SYMBOL(blk_iopoll_enable);
-
-/**
- * blk_iopoll_init - Initialize this @iop
- * @iop:      The parent iopoll structure
- * @weight:   The default weight (or command completion budget)
- * @poll_fn:  The handler to invoke
- *
- * Description:
- *     Initialize this blk_iopoll structure. Before being actively used, the
- *     driver must call blk_iopoll_enable().
- **/
-void blk_iopoll_init(struct blk_iopoll *iop, int weight, blk_iopoll_fn *poll_fn)
-{
-	memset(iop, 0, sizeof(*iop));
-	INIT_LIST_HEAD(&iop->list);
-	iop->weight = weight;
-	iop->poll = poll_fn;
-	set_bit(IOPOLL_F_SCHED, &iop->state);
-}
-EXPORT_SYMBOL(blk_iopoll_init);
-
-static int blk_iopoll_cpu_notify(struct notifier_block *self,
-				 unsigned long action, void *hcpu)
-{
-	/*
-	 * If a CPU goes away, splice its entries to the current CPU
-	 * and trigger a run of the softirq
-	 */
-	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
-		int cpu = (unsigned long) hcpu;
-
-		local_irq_disable();
-		list_splice_init(&per_cpu(blk_cpu_iopoll, cpu),
-				 this_cpu_ptr(&blk_cpu_iopoll));
-		__raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
-		local_irq_enable();
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block blk_iopoll_cpu_notifier = {
-	.notifier_call	= blk_iopoll_cpu_notify,
-};
-
-static __init int blk_iopoll_setup(void)
-{
-	int i;
-
-	for_each_possible_cpu(i)
-		INIT_LIST_HEAD(&per_cpu(blk_cpu_iopoll, i));
-
-	open_softirq(BLOCK_IOPOLL_SOFTIRQ, blk_iopoll_softirq);
-	register_hotcpu_notifier(&blk_iopoll_cpu_notifier);
-	return 0;
-}
-subsys_initcall(blk_iopoll_setup);
diff --git a/block/blk-map.c b/block/blk-map.c
index f565e11f465a..a54f0543b956 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -57,6 +57,49 @@ static int __blk_rq_unmap_user(struct bio *bio)
 	return ret;
 }
 
+static int __blk_rq_map_user_iov(struct request *rq,
+		struct rq_map_data *map_data, struct iov_iter *iter,
+		gfp_t gfp_mask, bool copy)
+{
+	struct request_queue *q = rq->q;
+	struct bio *bio, *orig_bio;
+	int ret;
+
+	if (copy)
+		bio = bio_copy_user_iov(q, map_data, iter, gfp_mask);
+	else
+		bio = bio_map_user_iov(q, iter, gfp_mask);
+
+	if (IS_ERR(bio))
+		return PTR_ERR(bio);
+
+	if (map_data && map_data->null_mapped)
+		bio_set_flag(bio, BIO_NULL_MAPPED);
+
+	iov_iter_advance(iter, bio->bi_iter.bi_size);
+	if (map_data)
+		map_data->offset += bio->bi_iter.bi_size;
+
+	orig_bio = bio;
+	blk_queue_bounce(q, &bio);
+
+	/*
+	 * We link the bounce buffer in and could have to traverse it
+	 * later so we have to get a ref to prevent it from being freed
+	 */
+	bio_get(bio);
+
+	ret = blk_rq_append_bio(q, rq, bio);
+	if (ret) {
+		bio_endio(bio);
+		__blk_rq_unmap_user(orig_bio);
+		bio_put(bio);
+		return ret;
+	}
+
+	return 0;
+}
+
 /**
  * blk_rq_map_user_iov - map user data to a request, for REQ_TYPE_BLOCK_PC usage
  * @q:		request queue where request should be inserted
@@ -82,10 +125,11 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 			struct rq_map_data *map_data,
 			const struct iov_iter *iter, gfp_t gfp_mask)
 {
-	struct bio *bio;
-	int unaligned = 0;
-	struct iov_iter i;
 	struct iovec iov, prv = {.iov_base = NULL, .iov_len = 0};
+	bool copy = (q->dma_pad_mask & iter->count) || map_data;
+	struct bio *bio = NULL;
+	struct iov_iter i;
+	int ret;
 
 	if (!iter || !iter->count)
 		return -EINVAL;
@@ -101,42 +145,29 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 		 */
 		if ((uaddr & queue_dma_alignment(q)) ||
 		    iovec_gap_to_prv(q, &prv, &iov))
-			unaligned = 1;
+			copy = true;
 
 		prv.iov_base = iov.iov_base;
 		prv.iov_len = iov.iov_len;
 	}
 
-	if (unaligned || (q->dma_pad_mask & iter->count) || map_data)
-		bio = bio_copy_user_iov(q, map_data, iter, gfp_mask);
-	else
-		bio = bio_map_user_iov(q, iter, gfp_mask);
-
-	if (IS_ERR(bio))
-		return PTR_ERR(bio);
-
-	if (map_data && map_data->null_mapped)
-		bio_set_flag(bio, BIO_NULL_MAPPED);
-
-	if (bio->bi_iter.bi_size != iter->count) {
-		/*
-		 * Grab an extra reference to this bio, as bio_unmap_user()
-		 * expects to be able to drop it twice as it happens on the
-		 * normal IO completion path
-		 */
-		bio_get(bio);
-		bio_endio(bio);
-		__blk_rq_unmap_user(bio);
-		return -EINVAL;
-	}
+	i = *iter;
+	do {
+		ret =__blk_rq_map_user_iov(rq, map_data, &i, gfp_mask, copy);
+		if (ret)
+			goto unmap_rq;
+		if (!bio)
+			bio = rq->bio;
+	} while (iov_iter_count(&i));
 
 	if (!bio_flagged(bio, BIO_USER_MAPPED))
 		rq->cmd_flags |= REQ_COPY_USER;
-
-	blk_queue_bounce(q, &bio);
-	bio_get(bio);
-	blk_rq_bio_prep(q, rq, bio);
 	return 0;
+
+unmap_rq:
+	__blk_rq_unmap_user(bio);
+	rq->bio = NULL;
+	return -EINVAL;
 }
 EXPORT_SYMBOL(blk_rq_map_user_iov);
 
diff --git a/block/blk-merge.c b/block/blk-merge.c
index de5716d8e525..261353166dcf 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -7,6 +7,8 @@
 #include <linux/blkdev.h>
 #include <linux/scatterlist.h>
 
+#include <trace/events/block.h>
+
 #include "blk.h"
 
 static struct bio *blk_bio_discard_split(struct request_queue *q,
@@ -68,6 +70,18 @@ static struct bio *blk_bio_write_same_split(struct request_queue *q,
 	return bio_split(bio, q->limits.max_write_same_sectors, GFP_NOIO, bs);
 }
 
+static inline unsigned get_max_io_size(struct request_queue *q,
+				       struct bio *bio)
+{
+	unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector);
+	unsigned mask = queue_logical_block_size(q) - 1;
+
+	/* aligned to logical block size */
+	sectors &= ~(mask >> 9);
+
+	return sectors;
+}
+
 static struct bio *blk_bio_segment_split(struct request_queue *q,
 					 struct bio *bio,
 					 struct bio_set *bs,
@@ -76,11 +90,12 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 	struct bio_vec bv, bvprv, *bvprvp = NULL;
 	struct bvec_iter iter;
 	unsigned seg_size = 0, nsegs = 0, sectors = 0;
+	unsigned front_seg_size = bio->bi_seg_front_size;
+	bool do_split = true;
+	struct bio *new = NULL;
+	const unsigned max_sectors = get_max_io_size(q, bio);
 
 	bio_for_each_segment(bv, bio, iter) {
-		if (sectors + (bv.bv_len >> 9) > queue_max_sectors(q))
-			goto split;
-
 		/*
 		 * If the queue doesn't support SG gaps and adding this
 		 * offset would create a gap, disallow it.
@@ -88,6 +103,21 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 		if (bvprvp && bvec_gap_to_prev(q, bvprvp, bv.bv_offset))
 			goto split;
 
+		if (sectors + (bv.bv_len >> 9) > max_sectors) {
+			/*
+			 * Consider this a new segment if we're splitting in
+			 * the middle of this vector.
+			 */
+			if (nsegs < queue_max_segments(q) &&
+			    sectors < max_sectors) {
+				nsegs++;
+				sectors = max_sectors;
+			}
+			if (sectors)
+				goto split;
+			/* Make this single bvec as the 1st segment */
+		}
+
 		if (bvprvp && blk_queue_cluster(q)) {
 			if (seg_size + bv.bv_len > queue_max_segment_size(q))
 				goto new_segment;
@@ -98,8 +128,11 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 
 			seg_size += bv.bv_len;
 			bvprv = bv;
-			bvprvp = &bv;
+			bvprvp = &bvprv;
 			sectors += bv.bv_len >> 9;
+
+			if (nsegs == 1 && seg_size > front_seg_size)
+				front_seg_size = seg_size;
 			continue;
 		}
 new_segment:
@@ -108,16 +141,29 @@ new_segment:
 
 		nsegs++;
 		bvprv = bv;
-		bvprvp = &bv;
+		bvprvp = &bvprv;
 		seg_size = bv.bv_len;
 		sectors += bv.bv_len >> 9;
+
+		if (nsegs == 1 && seg_size > front_seg_size)
+			front_seg_size = seg_size;
 	}
 
-	*segs = nsegs;
-	return NULL;
+	do_split = false;
 split:
 	*segs = nsegs;
-	return bio_split(bio, sectors, GFP_NOIO, bs);
+
+	if (do_split) {
+		new = bio_split(bio, sectors, GFP_NOIO, bs);
+		if (new)
+			bio = new;
+	}
+
+	bio->bi_seg_front_size = front_seg_size;
+	if (seg_size > bio->bi_seg_back_size)
+		bio->bi_seg_back_size = seg_size;
+
+	return do_split ? new : NULL;
 }
 
 void blk_queue_split(struct request_queue *q, struct bio **bio,
@@ -143,6 +189,7 @@ void blk_queue_split(struct request_queue *q, struct bio **bio,
 		split->bi_rw |= REQ_NOMERGE;
 
 		bio_chain(split, *bio);
+		trace_block_split(q, split, (*bio)->bi_iter.bi_sector);
 		generic_make_request(*bio);
 		*bio = split;
 	}
@@ -257,7 +304,6 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
 				   struct bio *nxt)
 {
 	struct bio_vec end_bv = { NULL }, nxt_bv;
-	struct bvec_iter iter;
 
 	if (!blk_queue_cluster(q))
 		return 0;
@@ -269,11 +315,8 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
 	if (!bio_has_data(bio))
 		return 1;
 
-	bio_for_each_segment(end_bv, bio, iter)
-		if (end_bv.bv_len == iter.bi_size)
-			break;
-
-	nxt_bv = bio_iovec(nxt);
+	bio_get_last_bvec(bio, &end_bv);
+	bio_get_first_bvec(nxt, &nxt_bv);
 
 	if (!BIOVEC_PHYS_MERGEABLE(&end_bv, &nxt_bv))
 		return 0;
@@ -412,6 +455,12 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 	if (sg)
 		sg_mark_end(sg);
 
+	/*
+	 * Something must have been wrong if the figured number of
+	 * segment is bigger than number of req's physical segments
+	 */
+	WARN_ON(nsegs > rq->nr_phys_segments);
+
 	return nsegs;
 }
 EXPORT_SYMBOL(blk_rq_map_sg);
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index 8764c241e5bb..d0634bcf322f 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -113,7 +113,7 @@ int blk_mq_hw_queue_to_node(unsigned int *mq_map, unsigned int index)
 
 	for_each_possible_cpu(i) {
 		if (index == mq_map[i])
-			return cpu_to_node(i);
+			return local_memory_node(cpu_to_node(i));
 	}
 
 	return NUMA_NO_NODE;
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 6f57a110289c..4ea4dd8a1eed 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -174,6 +174,11 @@ static ssize_t blk_mq_sysfs_rq_list_show(struct blk_mq_ctx *ctx, char *page)
 	return ret;
 }
 
+static ssize_t blk_mq_hw_sysfs_poll_show(struct blk_mq_hw_ctx *hctx, char *page)
+{
+	return sprintf(page, "invoked=%lu, success=%lu\n", hctx->poll_invoked, hctx->poll_success);
+}
+
 static ssize_t blk_mq_hw_sysfs_queued_show(struct blk_mq_hw_ctx *hctx,
 					   char *page)
 {
@@ -295,6 +300,10 @@ static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_cpus = {
 	.attr = {.name = "cpu_list", .mode = S_IRUGO },
 	.show = blk_mq_hw_sysfs_cpus_show,
 };
+static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_poll = {
+	.attr = {.name = "io_poll", .mode = S_IRUGO },
+	.show = blk_mq_hw_sysfs_poll_show,
+};
 
 static struct attribute *default_hw_ctx_attrs[] = {
 	&blk_mq_hw_sysfs_queued.attr,
@@ -304,6 +313,7 @@ static struct attribute *default_hw_ctx_attrs[] = {
 	&blk_mq_hw_sysfs_tags.attr,
 	&blk_mq_hw_sysfs_cpus.attr,
 	&blk_mq_hw_sysfs_active.attr,
+	&blk_mq_hw_sysfs_poll.attr,
 	NULL,
 };
 
@@ -398,19 +408,22 @@ void blk_mq_unregister_disk(struct gendisk *disk)
 	blk_mq_enable_hotplug();
 }
 
+void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx)
+{
+	kobject_init(&hctx->kobj, &blk_mq_hw_ktype);
+}
+
 static void blk_mq_sysfs_init(struct request_queue *q)
 {
-	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
-	int i;
+	int cpu;
 
 	kobject_init(&q->mq_kobj, &blk_mq_ktype);
 
-	queue_for_each_hw_ctx(q, hctx, i)
-		kobject_init(&hctx->kobj, &blk_mq_hw_ktype);
-
-	queue_for_each_ctx(q, ctx, i)
+	for_each_possible_cpu(cpu) {
+		ctx = per_cpu_ptr(q->queue_ctx, cpu);
 		kobject_init(&ctx->kobj, &blk_mq_ctx_ktype);
+	}
 }
 
 int blk_mq_register_disk(struct gendisk *disk)
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 60ac684c8b8c..abdbb47405cb 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -268,7 +268,7 @@ static int bt_get(struct blk_mq_alloc_data *data,
 	if (tag != -1)
 		return tag;
 
-	if (!(data->gfp & __GFP_WAIT))
+	if (data->flags & BLK_MQ_REQ_NOWAIT)
 		return -1;
 
 	bs = bt_wait_ptr(bt, hctx);
@@ -303,7 +303,7 @@ static int bt_get(struct blk_mq_alloc_data *data,
 		data->ctx = blk_mq_get_ctx(data->q);
 		data->hctx = data->q->mq_ops->map_queue(data->q,
 				data->ctx->cpu);
-		if (data->reserved) {
+		if (data->flags & BLK_MQ_REQ_RESERVED) {
 			bt = &data->hctx->tags->breserved_tags;
 		} else {
 			last_tag = &data->ctx->last_tag;
@@ -349,10 +349,9 @@ static unsigned int __blk_mq_get_reserved_tag(struct blk_mq_alloc_data *data)
 
 unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 {
-	if (!data->reserved)
-		return __blk_mq_get_tag(data);
-
-	return __blk_mq_get_reserved_tag(data);
+	if (data->flags & BLK_MQ_REQ_RESERVED)
+		return __blk_mq_get_reserved_tag(data);
+	return __blk_mq_get_tag(data);
 }
 
 static struct bt_wait_state *bt_wake_ptr(struct blk_mq_bitmap_tags *bt)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 1c27b3eaef64..1699baf39b78 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -229,8 +229,8 @@ __blk_mq_alloc_request(struct blk_mq_alloc_data *data, int rw)
 	return NULL;
 }
 
-struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp,
-		bool reserved)
+struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
+		unsigned int flags)
 {
 	struct blk_mq_ctx *ctx;
 	struct blk_mq_hw_ctx *hctx;
@@ -238,24 +238,22 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp,
 	struct blk_mq_alloc_data alloc_data;
 	int ret;
 
-	ret = blk_queue_enter(q, gfp);
+	ret = blk_queue_enter(q, flags & BLK_MQ_REQ_NOWAIT);
 	if (ret)
 		return ERR_PTR(ret);
 
 	ctx = blk_mq_get_ctx(q);
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
-	blk_mq_set_alloc_data(&alloc_data, q, gfp & ~__GFP_WAIT,
-			reserved, ctx, hctx);
+	blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
 
 	rq = __blk_mq_alloc_request(&alloc_data, rw);
-	if (!rq && (gfp & __GFP_WAIT)) {
+	if (!rq && !(flags & BLK_MQ_REQ_NOWAIT)) {
 		__blk_mq_run_hw_queue(hctx);
 		blk_mq_put_ctx(ctx);
 
 		ctx = blk_mq_get_ctx(q);
 		hctx = q->mq_ops->map_queue(q, ctx->cpu);
-		blk_mq_set_alloc_data(&alloc_data, q, gfp, reserved, ctx,
-				hctx);
+		blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
 		rq =  __blk_mq_alloc_request(&alloc_data, rw);
 		ctx = alloc_data.ctx;
 	}
@@ -358,7 +356,7 @@ static void blk_mq_ipi_complete_request(struct request *rq)
 	put_cpu();
 }
 
-void __blk_mq_complete_request(struct request *rq)
+static void __blk_mq_complete_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
@@ -546,7 +544,10 @@ EXPORT_SYMBOL(blk_mq_abort_requeue_list);
 
 struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag)
 {
-	return tags->rqs[tag];
+	if (tag < tags->nr_tags)
+		return tags->rqs[tag];
+
+	return NULL;
 }
 EXPORT_SYMBOL(blk_mq_tag_to_rq);
 
@@ -601,12 +602,12 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 		 * If a request wasn't started before the queue was
 		 * marked dying, kill it here or it'll go unnoticed.
 		 */
-		if (unlikely(blk_queue_dying(rq->q)))
-			blk_mq_complete_request(rq, -EIO);
+		if (unlikely(blk_queue_dying(rq->q))) {
+			rq->errors = -EIO;
+			blk_mq_end_request(rq, rq->errors);
+		}
 		return;
 	}
-	if (rq->cmd_flags & REQ_NO_TIMEOUT)
-		return;
 
 	if (time_after_eq(jiffies, rq->deadline)) {
 		if (!blk_mark_rq_complete(rq))
@@ -617,15 +618,19 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 	}
 }
 
-static void blk_mq_rq_timer(unsigned long priv)
+static void blk_mq_timeout_work(struct work_struct *work)
 {
-	struct request_queue *q = (struct request_queue *)priv;
+	struct request_queue *q =
+		container_of(work, struct request_queue, timeout_work);
 	struct blk_mq_timeout_data data = {
 		.next		= 0,
 		.next_set	= 0,
 	};
 	int i;
 
+	if (blk_queue_enter(q, true))
+		return;
+
 	blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &data);
 
 	if (data.next_set) {
@@ -640,6 +645,7 @@ static void blk_mq_rq_timer(unsigned long priv)
 				blk_mq_tag_idle(hctx);
 		}
 	}
+	blk_queue_exit(q);
 }
 
 /*
@@ -1175,8 +1181,7 @@ static struct request *blk_mq_map_request(struct request_queue *q,
 		rw |= REQ_SYNC;
 
 	trace_block_getrq(q, bio, rw);
-	blk_mq_set_alloc_data(&alloc_data, q, GFP_ATOMIC, false, ctx,
-			hctx);
+	blk_mq_set_alloc_data(&alloc_data, q, BLK_MQ_REQ_NOWAIT, ctx, hctx);
 	rq = __blk_mq_alloc_request(&alloc_data, rw);
 	if (unlikely(!rq)) {
 		__blk_mq_run_hw_queue(hctx);
@@ -1185,8 +1190,7 @@ static struct request *blk_mq_map_request(struct request_queue *q,
 
 		ctx = blk_mq_get_ctx(q);
 		hctx = q->mq_ops->map_queue(q, ctx->cpu);
-		blk_mq_set_alloc_data(&alloc_data, q,
-				__GFP_WAIT|GFP_ATOMIC, false, ctx, hctx);
+		blk_mq_set_alloc_data(&alloc_data, q, 0, ctx, hctx);
 		rq = __blk_mq_alloc_request(&alloc_data, rw);
 		ctx = alloc_data.ctx;
 		hctx = alloc_data.hctx;
@@ -1198,7 +1202,7 @@ static struct request *blk_mq_map_request(struct request_queue *q,
 	return rq;
 }
 
-static int blk_mq_direct_issue_request(struct request *rq)
+static int blk_mq_direct_issue_request(struct request *rq, blk_qc_t *cookie)
 {
 	int ret;
 	struct request_queue *q = rq->q;
@@ -1209,6 +1213,7 @@ static int blk_mq_direct_issue_request(struct request *rq)
 		.list = NULL,
 		.last = 1
 	};
+	blk_qc_t new_cookie = blk_tag_to_qc_t(rq->tag, hctx->queue_num);
 
 	/*
 	 * For OK queue, we are done. For error, kill it. Any other
@@ -1216,18 +1221,21 @@ static int blk_mq_direct_issue_request(struct request *rq)
 	 * would have done
 	 */
 	ret = q->mq_ops->queue_rq(hctx, &bd);
-	if (ret == BLK_MQ_RQ_QUEUE_OK)
+	if (ret == BLK_MQ_RQ_QUEUE_OK) {
+		*cookie = new_cookie;
 		return 0;
-	else {
-		__blk_mq_requeue_request(rq);
+	}
 
-		if (ret == BLK_MQ_RQ_QUEUE_ERROR) {
-			rq->errors = -EIO;
-			blk_mq_end_request(rq, rq->errors);
-			return 0;
-		}
-		return -1;
+	__blk_mq_requeue_request(rq);
+
+	if (ret == BLK_MQ_RQ_QUEUE_ERROR) {
+		*cookie = BLK_QC_T_NONE;
+		rq->errors = -EIO;
+		blk_mq_end_request(rq, rq->errors);
+		return 0;
 	}
+
+	return -1;
 }
 
 /*
@@ -1235,7 +1243,7 @@ static int blk_mq_direct_issue_request(struct request *rq)
  * but will attempt to bypass the hctx queueing if we can go straight to
  * hardware for SYNC IO.
  */
-static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int is_sync = rw_is_sync(bio->bi_rw);
 	const int is_flush_fua = bio->bi_rw & (REQ_FLUSH | REQ_FUA);
@@ -1244,12 +1252,13 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	unsigned int request_count = 0;
 	struct blk_plug *plug;
 	struct request *same_queue_rq = NULL;
+	blk_qc_t cookie;
 
 	blk_queue_bounce(q, &bio);
 
 	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
 		bio_io_error(bio);
-		return;
+		return BLK_QC_T_NONE;
 	}
 
 	blk_queue_split(q, &bio, q->bio_split);
@@ -1257,13 +1266,15 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	if (!is_flush_fua && !blk_queue_nomerges(q)) {
 		if (blk_attempt_plug_merge(q, bio, &request_count,
 					   &same_queue_rq))
-			return;
+			return BLK_QC_T_NONE;
 	} else
 		request_count = blk_plug_queued_count(q);
 
 	rq = blk_mq_map_request(q, bio, &data);
 	if (unlikely(!rq))
-		return;
+		return BLK_QC_T_NONE;
+
+	cookie = blk_tag_to_qc_t(rq->tag, data.hctx->queue_num);
 
 	if (unlikely(is_flush_fua)) {
 		blk_mq_bio_to_request(rq, bio);
@@ -1284,15 +1295,16 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		blk_mq_bio_to_request(rq, bio);
 
 		/*
-		 * we do limited pluging. If bio can be merged, do merge.
+		 * We do limited pluging. If the bio can be merged, do that.
 		 * Otherwise the existing request in the plug list will be
 		 * issued. So the plug list will have one request at most
 		 */
 		if (plug) {
 			/*
 			 * The plug list might get flushed before this. If that
-			 * happens, same_queue_rq is invalid and plug list is empty
-			 **/
+			 * happens, same_queue_rq is invalid and plug list is
+			 * empty
+			 */
 			if (same_queue_rq && !list_empty(&plug->mq_list)) {
 				old_rq = same_queue_rq;
 				list_del_init(&old_rq->queuelist);
@@ -1302,11 +1314,11 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 			old_rq = rq;
 		blk_mq_put_ctx(data.ctx);
 		if (!old_rq)
-			return;
-		if (!blk_mq_direct_issue_request(old_rq))
-			return;
+			goto done;
+		if (!blk_mq_direct_issue_request(old_rq, &cookie))
+			goto done;
 		blk_mq_insert_request(old_rq, false, true, true);
-		return;
+		goto done;
 	}
 
 	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
@@ -1320,13 +1332,15 @@ run_queue:
 		blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
 	}
 	blk_mq_put_ctx(data.ctx);
+done:
+	return cookie;
 }
 
 /*
  * Single hardware queue variant. This will attempt to use any per-process
  * plug for merging and IO deferral.
  */
-static void blk_sq_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int is_sync = rw_is_sync(bio->bi_rw);
 	const int is_flush_fua = bio->bi_rw & (REQ_FLUSH | REQ_FUA);
@@ -1334,23 +1348,26 @@ static void blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	unsigned int request_count = 0;
 	struct blk_map_ctx data;
 	struct request *rq;
+	blk_qc_t cookie;
 
 	blk_queue_bounce(q, &bio);
 
 	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
 		bio_io_error(bio);
-		return;
+		return BLK_QC_T_NONE;
 	}
 
 	blk_queue_split(q, &bio, q->bio_split);
 
 	if (!is_flush_fua && !blk_queue_nomerges(q) &&
 	    blk_attempt_plug_merge(q, bio, &request_count, NULL))
-		return;
+		return BLK_QC_T_NONE;
 
 	rq = blk_mq_map_request(q, bio, &data);
 	if (unlikely(!rq))
-		return;
+		return BLK_QC_T_NONE;
+
+	cookie = blk_tag_to_qc_t(rq->tag, data.hctx->queue_num);
 
 	if (unlikely(is_flush_fua)) {
 		blk_mq_bio_to_request(rq, bio);
@@ -1368,13 +1385,16 @@ static void blk_sq_make_request(struct request_queue *q, struct bio *bio)
 		blk_mq_bio_to_request(rq, bio);
 		if (!request_count)
 			trace_block_plug(q);
-		else if (request_count >= BLK_MAX_REQUEST_COUNT) {
+
+		blk_mq_put_ctx(data.ctx);
+
+		if (request_count >= BLK_MAX_REQUEST_COUNT) {
 			blk_flush_plug_list(plug, false);
 			trace_block_plug(q);
 		}
+
 		list_add_tail(&rq->queuelist, &plug->mq_list);
-		blk_mq_put_ctx(data.ctx);
-		return;
+		return cookie;
 	}
 
 	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
@@ -1389,6 +1409,7 @@ run_queue:
 	}
 
 	blk_mq_put_ctx(data.ctx);
+	return cookie;
 }
 
 /*
@@ -1726,31 +1747,6 @@ static int blk_mq_init_hctx(struct request_queue *q,
 	return -1;
 }
 
-static int blk_mq_init_hw_queues(struct request_queue *q,
-		struct blk_mq_tag_set *set)
-{
-	struct blk_mq_hw_ctx *hctx;
-	unsigned int i;
-
-	/*
-	 * Initialize hardware queues
-	 */
-	queue_for_each_hw_ctx(q, hctx, i) {
-		if (blk_mq_init_hctx(q, set, hctx, i))
-			break;
-	}
-
-	if (i == q->nr_hw_queues)
-		return 0;
-
-	/*
-	 * Init failed
-	 */
-	blk_mq_exit_hw_queues(q, set, i);
-
-	return 1;
-}
-
 static void blk_mq_init_cpu_queues(struct request_queue *q,
 				   unsigned int nr_hw_queues)
 {
@@ -1777,7 +1773,7 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
 		 * not, we remain on the home node of the device
 		 */
 		if (nr_hw_queues > 1 && hctx->numa_node == NUMA_NO_NODE)
-			hctx->numa_node = cpu_to_node(i);
+			hctx->numa_node = local_memory_node(cpu_to_node(i));
 	}
 }
 
@@ -1802,12 +1798,14 @@ static void blk_mq_map_swqueue(struct request_queue *q,
 	/*
 	 * Map software to hardware queues
 	 */
-	queue_for_each_ctx(q, ctx, i) {
+	for_each_possible_cpu(i) {
 		/* If the cpu isn't online, the cpu is mapped to first hctx */
 		if (!cpumask_test_cpu(i, online_mask))
 			continue;
 
+		ctx = per_cpu_ptr(q->queue_ctx, i);
 		hctx = q->mq_ops->map_queue(q, i);
+
 		cpumask_set_cpu(i, hctx->cpumask);
 		ctx->index_hw = hctx->nr_ctx;
 		hctx->ctxs[hctx->nr_ctx++] = ctx;
@@ -1837,6 +1835,7 @@ static void blk_mq_map_swqueue(struct request_queue *q,
 		hctx->tags = set->tags[i];
 		WARN_ON(!hctx->tags);
 
+		cpumask_copy(hctx->tags->cpumask, hctx->cpumask);
 		/*
 		 * Set the map size to the number of mapped software queues.
 		 * This is more accurate and more efficient than looping
@@ -1850,14 +1849,6 @@ static void blk_mq_map_swqueue(struct request_queue *q,
 		hctx->next_cpu = cpumask_first(hctx->cpumask);
 		hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
 	}
-
-	queue_for_each_ctx(q, ctx, i) {
-		if (!cpumask_test_cpu(i, online_mask))
-			continue;
-
-		hctx = q->mq_ops->map_queue(q, i);
-		cpumask_set_cpu(i, hctx->tags->cpumask);
-	}
 }
 
 static void queue_set_hctx_shared(struct request_queue *q, bool shared)
@@ -1963,56 +1954,93 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 }
 EXPORT_SYMBOL(blk_mq_init_queue);
 
-struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
-						  struct request_queue *q)
+static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
+						struct request_queue *q)
 {
-	struct blk_mq_hw_ctx **hctxs;
-	struct blk_mq_ctx __percpu *ctx;
-	unsigned int *map;
-	int i;
-
-	ctx = alloc_percpu(struct blk_mq_ctx);
-	if (!ctx)
-		return ERR_PTR(-ENOMEM);
-
-	hctxs = kmalloc_node(set->nr_hw_queues * sizeof(*hctxs), GFP_KERNEL,
-			set->numa_node);
-
-	if (!hctxs)
-		goto err_percpu;
-
-	map = blk_mq_make_queue_map(set);
-	if (!map)
-		goto err_map;
+	int i, j;
+	struct blk_mq_hw_ctx **hctxs = q->queue_hw_ctx;
 
+	blk_mq_sysfs_unregister(q);
 	for (i = 0; i < set->nr_hw_queues; i++) {
-		int node = blk_mq_hw_queue_to_node(map, i);
+		int node;
 
+		if (hctxs[i])
+			continue;
+
+		node = blk_mq_hw_queue_to_node(q->mq_map, i);
 		hctxs[i] = kzalloc_node(sizeof(struct blk_mq_hw_ctx),
 					GFP_KERNEL, node);
 		if (!hctxs[i])
-			goto err_hctxs;
+			break;
 
 		if (!zalloc_cpumask_var_node(&hctxs[i]->cpumask, GFP_KERNEL,
-						node))
-			goto err_hctxs;
+						node)) {
+			kfree(hctxs[i]);
+			hctxs[i] = NULL;
+			break;
+		}
 
 		atomic_set(&hctxs[i]->nr_active, 0);
 		hctxs[i]->numa_node = node;
 		hctxs[i]->queue_num = i;
+
+		if (blk_mq_init_hctx(q, set, hctxs[i], i)) {
+			free_cpumask_var(hctxs[i]->cpumask);
+			kfree(hctxs[i]);
+			hctxs[i] = NULL;
+			break;
+		}
+		blk_mq_hctx_kobj_init(hctxs[i]);
+	}
+	for (j = i; j < q->nr_hw_queues; j++) {
+		struct blk_mq_hw_ctx *hctx = hctxs[j];
+
+		if (hctx) {
+			if (hctx->tags) {
+				blk_mq_free_rq_map(set, hctx->tags, j);
+				set->tags[j] = NULL;
+			}
+			blk_mq_exit_hctx(q, set, hctx, j);
+			free_cpumask_var(hctx->cpumask);
+			kobject_put(&hctx->kobj);
+			kfree(hctx->ctxs);
+			kfree(hctx);
+			hctxs[j] = NULL;
+
+		}
 	}
+	q->nr_hw_queues = i;
+	blk_mq_sysfs_register(q);
+}
+
+struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
+						  struct request_queue *q)
+{
+	/* mark the queue as mq asap */
+	q->mq_ops = set->ops;
+
+	q->queue_ctx = alloc_percpu(struct blk_mq_ctx);
+	if (!q->queue_ctx)
+		return ERR_PTR(-ENOMEM);
+
+	q->queue_hw_ctx = kzalloc_node(nr_cpu_ids * sizeof(*(q->queue_hw_ctx)),
+						GFP_KERNEL, set->numa_node);
+	if (!q->queue_hw_ctx)
+		goto err_percpu;
+
+	q->mq_map = blk_mq_make_queue_map(set);
+	if (!q->mq_map)
+		goto err_map;
 
-	setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q);
+	blk_mq_realloc_hw_ctxs(set, q);
+	if (!q->nr_hw_queues)
+		goto err_hctxs;
+
+	INIT_WORK(&q->timeout_work, blk_mq_timeout_work);
 	blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ);
 
 	q->nr_queues = nr_cpu_ids;
-	q->nr_hw_queues = set->nr_hw_queues;
-	q->mq_map = map;
-
-	q->queue_ctx = ctx;
-	q->queue_hw_ctx = hctxs;
 
-	q->mq_ops = set->ops;
 	q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT;
 
 	if (!(set->flags & BLK_MQ_F_SG_MERGE))
@@ -2039,9 +2067,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 
 	blk_mq_init_cpu_queues(q, set->nr_hw_queues);
 
-	if (blk_mq_init_hw_queues(q, set))
-		goto err_hctxs;
-
 	get_online_cpus();
 	mutex_lock(&all_q_mutex);
 
@@ -2055,17 +2080,11 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	return q;
 
 err_hctxs:
-	kfree(map);
-	for (i = 0; i < set->nr_hw_queues; i++) {
-		if (!hctxs[i])
-			break;
-		free_cpumask_var(hctxs[i]->cpumask);
-		kfree(hctxs[i]);
-	}
+	kfree(q->mq_map);
 err_map:
-	kfree(hctxs);
+	kfree(q->queue_hw_ctx);
 err_percpu:
-	free_percpu(ctx);
+	free_percpu(q->queue_ctx);
 	return ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL(blk_mq_init_allocated_queue);
@@ -2273,9 +2292,13 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 		set->nr_hw_queues = 1;
 		set->queue_depth = min(64U, set->queue_depth);
 	}
+	/*
+	 * There is no use for more h/w queues than cpus.
+	 */
+	if (set->nr_hw_queues > nr_cpu_ids)
+		set->nr_hw_queues = nr_cpu_ids;
 
-	set->tags = kmalloc_node(set->nr_hw_queues *
-				 sizeof(struct blk_mq_tags *),
+	set->tags = kzalloc_node(nr_cpu_ids * sizeof(struct blk_mq_tags *),
 				 GFP_KERNEL, set->numa_node);
 	if (!set->tags)
 		return -ENOMEM;
@@ -2298,7 +2321,7 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
 {
 	int i;
 
-	for (i = 0; i < set->nr_hw_queues; i++) {
+	for (i = 0; i < nr_cpu_ids; i++) {
 		if (set->tags[i])
 			blk_mq_free_rq_map(set, set->tags[i], i);
 	}
@@ -2319,6 +2342,8 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 
 	ret = 0;
 	queue_for_each_hw_ctx(q, hctx, i) {
+		if (!hctx->tags)
+			continue;
 		ret = blk_mq_tag_update_depth(hctx->tags, nr);
 		if (ret)
 			break;
@@ -2330,6 +2355,35 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 	return ret;
 }
 
+void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
+{
+	struct request_queue *q;
+
+	if (nr_hw_queues > nr_cpu_ids)
+		nr_hw_queues = nr_cpu_ids;
+	if (nr_hw_queues < 1 || nr_hw_queues == set->nr_hw_queues)
+		return;
+
+	list_for_each_entry(q, &set->tag_list, tag_set_list)
+		blk_mq_freeze_queue(q);
+
+	set->nr_hw_queues = nr_hw_queues;
+	list_for_each_entry(q, &set->tag_list, tag_set_list) {
+		blk_mq_realloc_hw_ctxs(set, q);
+
+		if (q->nr_hw_queues > 1)
+			blk_queue_make_request(q, blk_mq_make_request);
+		else
+			blk_queue_make_request(q, blk_sq_make_request);
+
+		blk_mq_queue_reinit(q, cpu_online_mask);
+	}
+
+	list_for_each_entry(q, &set->tag_list, tag_set_list)
+		blk_mq_unfreeze_queue(q);
+}
+EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues);
+
 void blk_mq_disable_hotplug(void)
 {
 	mutex_lock(&all_q_mutex);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index b44dce165761..9087b11037b7 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -25,7 +25,6 @@ struct blk_mq_ctx {
 	struct kobject		kobj;
 } ____cacheline_aligned_in_smp;
 
-void __blk_mq_complete_request(struct request *rq);
 void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
 void blk_mq_freeze_queue(struct request_queue *q);
 void blk_mq_free_queue(struct request_queue *q);
@@ -58,6 +57,7 @@ extern int blk_mq_hw_queue_to_node(unsigned int *map, unsigned int);
  */
 extern int blk_mq_sysfs_register(struct request_queue *q);
 extern void blk_mq_sysfs_unregister(struct request_queue *q);
+extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
 
 extern void blk_mq_rq_timed_out(struct request *req, bool reserved);
 
@@ -97,8 +97,7 @@ static inline void blk_mq_put_ctx(struct blk_mq_ctx *ctx)
 struct blk_mq_alloc_data {
 	/* input parameter */
 	struct request_queue *q;
-	gfp_t gfp;
-	bool reserved;
+	unsigned int flags;
 
 	/* input & output parameter */
 	struct blk_mq_ctx *ctx;
@@ -106,13 +105,11 @@ struct blk_mq_alloc_data {
 };
 
 static inline void blk_mq_set_alloc_data(struct blk_mq_alloc_data *data,
-		struct request_queue *q, gfp_t gfp, bool reserved,
-		struct blk_mq_ctx *ctx,
-		struct blk_mq_hw_ctx *hctx)
+		struct request_queue *q, unsigned int flags,
+		struct blk_mq_ctx *ctx, struct blk_mq_hw_ctx *hctx)
 {
 	data->q = q;
-	data->gfp = gfp;
-	data->reserved = reserved;
+	data->flags = flags;
 	data->ctx = ctx;
 	data->hctx = hctx;
 }
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 7d8f129a1516..331e4eee0dda 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -92,6 +92,7 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->virt_boundary_mask = 0;
 	lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
 	lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
+	lim->max_dev_sectors = 0;
 	lim->chunk_sectors = 0;
 	lim->max_write_same_sectors = 0;
 	lim->max_discard_sectors = 0;
@@ -127,6 +128,7 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 	lim->max_hw_sectors = UINT_MAX;
 	lim->max_segment_size = UINT_MAX;
 	lim->max_sectors = UINT_MAX;
+	lim->max_dev_sectors = UINT_MAX;
 	lim->max_write_same_sectors = UINT_MAX;
 }
 EXPORT_SYMBOL(blk_set_stacking_limits);
@@ -214,8 +216,8 @@ void blk_queue_bounce_limit(struct request_queue *q, u64 max_addr)
 EXPORT_SYMBOL(blk_queue_bounce_limit);
 
 /**
- * blk_limits_max_hw_sectors - set hard and soft limit of max sectors for request
- * @limits: the queue limits
+ * blk_queue_max_hw_sectors - set max sectors for a request for this queue
+ * @q:  the request queue for the device
  * @max_hw_sectors:  max hardware sectors in the usual 512b unit
  *
  * Description:
@@ -224,36 +226,29 @@ EXPORT_SYMBOL(blk_queue_bounce_limit);
  *    the device driver based upon the capabilities of the I/O
  *    controller.
  *
+ *    max_dev_sectors is a hard limit imposed by the storage device for
+ *    READ/WRITE requests. It is set by the disk driver.
+ *
  *    max_sectors is a soft limit imposed by the block layer for
  *    filesystem type requests.  This value can be overridden on a
  *    per-device basis in /sys/block/<device>/queue/max_sectors_kb.
  *    The soft limit can not exceed max_hw_sectors.
  **/
-void blk_limits_max_hw_sectors(struct queue_limits *limits, unsigned int max_hw_sectors)
+void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors)
 {
-	if ((max_hw_sectors << 9) < PAGE_CACHE_SIZE) {
-		max_hw_sectors = 1 << (PAGE_CACHE_SHIFT - 9);
+	struct queue_limits *limits = &q->limits;
+	unsigned int max_sectors;
+
+	if ((max_hw_sectors << 9) < PAGE_SIZE) {
+		max_hw_sectors = 1 << (PAGE_SHIFT - 9);
 		printk(KERN_INFO "%s: set to minimum %d\n",
 		       __func__, max_hw_sectors);
 	}
 
 	limits->max_hw_sectors = max_hw_sectors;
-	limits->max_sectors = min_t(unsigned int, max_hw_sectors,
-				    BLK_DEF_MAX_SECTORS);
-}
-EXPORT_SYMBOL(blk_limits_max_hw_sectors);
-
-/**
- * blk_queue_max_hw_sectors - set max sectors for a request for this queue
- * @q:  the request queue for the device
- * @max_hw_sectors:  max hardware sectors in the usual 512b unit
- *
- * Description:
- *    See description for blk_limits_max_hw_sectors().
- **/
-void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors)
-{
-	blk_limits_max_hw_sectors(&q->limits, max_hw_sectors);
+	max_sectors = min_not_zero(max_hw_sectors, limits->max_dev_sectors);
+	max_sectors = min_t(unsigned int, max_sectors, BLK_DEF_MAX_SECTORS);
+	limits->max_sectors = max_sectors;
 }
 EXPORT_SYMBOL(blk_queue_max_hw_sectors);
 
@@ -334,8 +329,8 @@ EXPORT_SYMBOL(blk_queue_max_segments);
  **/
 void blk_queue_max_segment_size(struct request_queue *q, unsigned int max_size)
 {
-	if (max_size < PAGE_CACHE_SIZE) {
-		max_size = PAGE_CACHE_SIZE;
+	if (max_size < PAGE_SIZE) {
+		max_size = PAGE_SIZE;
 		printk(KERN_INFO "%s: set to minimum %d\n",
 		       __func__, max_size);
 	}
@@ -527,6 +522,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 
 	t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
 	t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
+	t->max_dev_sectors = min_not_zero(t->max_dev_sectors, b->max_dev_sectors);
 	t->max_write_same_sectors = min(t->max_write_same_sectors,
 					b->max_write_same_sectors);
 	t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn);
@@ -764,8 +760,8 @@ EXPORT_SYMBOL_GPL(blk_queue_dma_drain);
  **/
 void blk_queue_segment_boundary(struct request_queue *q, unsigned long mask)
 {
-	if (mask < PAGE_CACHE_SIZE - 1) {
-		mask = PAGE_CACHE_SIZE - 1;
+	if (mask < PAGE_SIZE - 1) {
+		mask = PAGE_SIZE - 1;
 		printk(KERN_INFO "%s: set to minimum %lx\n",
 		       __func__, mask);
 	}
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 31849e328b45..995b58d46ed1 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -76,7 +76,7 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count)
 static ssize_t queue_ra_show(struct request_queue *q, char *page)
 {
 	unsigned long ra_kb = q->backing_dev_info.ra_pages <<
-					(PAGE_CACHE_SHIFT - 10);
+					(PAGE_SHIFT - 10);
 
 	return queue_var_show(ra_kb, (page));
 }
@@ -90,7 +90,7 @@ queue_ra_store(struct request_queue *q, const char *page, size_t count)
 	if (ret < 0)
 		return ret;
 
-	q->backing_dev_info.ra_pages = ra_kb >> (PAGE_CACHE_SHIFT - 10);
+	q->backing_dev_info.ra_pages = ra_kb >> (PAGE_SHIFT - 10);
 
 	return ret;
 }
@@ -117,7 +117,7 @@ static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page)
 	if (blk_queue_cluster(q))
 		return queue_var_show(queue_max_segment_size(q), (page));
 
-	return queue_var_show(PAGE_CACHE_SIZE, (page));
+	return queue_var_show(PAGE_SIZE, (page));
 }
 
 static ssize_t queue_logical_block_size_show(struct request_queue *q, char *page)
@@ -147,10 +147,9 @@ static ssize_t queue_discard_granularity_show(struct request_queue *q, char *pag
 
 static ssize_t queue_discard_max_hw_show(struct request_queue *q, char *page)
 {
-	unsigned long long val;
 
-	val = q->limits.max_hw_discard_sectors << 9;
-	return sprintf(page, "%llu\n", val);
+	return sprintf(page, "%llu\n",
+		(unsigned long long)q->limits.max_hw_discard_sectors << 9);
 }
 
 static ssize_t queue_discard_max_show(struct request_queue *q, char *page)
@@ -199,12 +198,15 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 {
 	unsigned long max_sectors_kb,
 		max_hw_sectors_kb = queue_max_hw_sectors(q) >> 1,
-			page_kb = 1 << (PAGE_CACHE_SHIFT - 10);
+			page_kb = 1 << (PAGE_SHIFT - 10);
 	ssize_t ret = queue_var_store(&max_sectors_kb, page, count);
 
 	if (ret < 0)
 		return ret;
 
+	max_hw_sectors_kb = min_not_zero(max_hw_sectors_kb, (unsigned long)
+					 q->limits.max_dev_sectors >> 1);
+
 	if (max_sectors_kb > max_hw_sectors_kb || max_sectors_kb < page_kb)
 		return -EINVAL;
 
@@ -317,6 +319,34 @@ queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count)
 	return ret;
 }
 
+static ssize_t queue_poll_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(test_bit(QUEUE_FLAG_POLL, &q->queue_flags), page);
+}
+
+static ssize_t queue_poll_store(struct request_queue *q, const char *page,
+				size_t count)
+{
+	unsigned long poll_on;
+	ssize_t ret;
+
+	if (!q->mq_ops || !q->mq_ops->poll)
+		return -EINVAL;
+
+	ret = queue_var_store(&poll_on, page, count);
+	if (ret < 0)
+		return ret;
+
+	spin_lock_irq(q->queue_lock);
+	if (poll_on)
+		queue_flag_set(QUEUE_FLAG_POLL, q);
+	else
+		queue_flag_clear(QUEUE_FLAG_POLL, q);
+	spin_unlock_irq(q->queue_lock);
+
+	return ret;
+}
+
 static struct queue_sysfs_entry queue_requests_entry = {
 	.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_requests_show,
@@ -442,6 +472,12 @@ static struct queue_sysfs_entry queue_random_entry = {
 	.store = queue_store_random,
 };
 
+static struct queue_sysfs_entry queue_poll_entry = {
+	.attr = {.name = "io_poll", .mode = S_IRUGO | S_IWUSR },
+	.show = queue_poll_show,
+	.store = queue_poll_store,
+};
+
 static struct attribute *default_attrs[] = {
 	&queue_requests_entry.attr,
 	&queue_ra_entry.attr,
@@ -466,6 +502,7 @@ static struct attribute *default_attrs[] = {
 	&queue_rq_affinity_entry.attr,
 	&queue_iostats_entry.attr,
 	&queue_random_entry.attr,
+	&queue_poll_entry.attr,
 	NULL,
 };
 
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 246dfb16c3d9..a30441a200c0 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -127,13 +127,16 @@ static void blk_rq_check_expired(struct request *rq, unsigned long *next_timeout
 	}
 }
 
-void blk_rq_timed_out_timer(unsigned long data)
+void blk_timeout_work(struct work_struct *work)
 {
-	struct request_queue *q = (struct request_queue *) data;
+	struct request_queue *q =
+		container_of(work, struct request_queue, timeout_work);
 	unsigned long flags, next = 0;
 	struct request *rq, *tmp;
 	int next_set = 0;
 
+	if (blk_queue_enter(q, true))
+		return;
 	spin_lock_irqsave(q->queue_lock, flags);
 
 	list_for_each_entry_safe(rq, tmp, &q->timeout_list, timeout_list)
@@ -143,6 +146,7 @@ void blk_rq_timed_out_timer(unsigned long data)
 		mod_timer(&q->timeout, round_jiffies_up(next));
 
 	spin_unlock_irqrestore(q->queue_lock, flags);
+	blk_queue_exit(q);
 }
 
 /**
@@ -158,11 +162,13 @@ void blk_abort_request(struct request *req)
 {
 	if (blk_mark_rq_complete(req))
 		return;
-	blk_delete_timer(req);
-	if (req->q->mq_ops)
+
+	if (req->q->mq_ops) {
 		blk_mq_rq_timed_out(req, false);
-	else
+	} else {
+		blk_delete_timer(req);
 		blk_rq_timed_out(req);
+	}
 }
 EXPORT_SYMBOL_GPL(blk_abort_request);
 
@@ -184,15 +190,13 @@ unsigned long blk_rq_timeout(unsigned long timeout)
  * Notes:
  *    Each request has its own timer, and as it is added to the queue, we
  *    set up the timer. When the request completes, we cancel the timer.
+ *    Queue lock must be held for the non-mq case, mq case doesn't care.
  */
 void blk_add_timer(struct request *req)
 {
 	struct request_queue *q = req->q;
 	unsigned long expiry;
 
-	if (req->cmd_flags & REQ_NO_TIMEOUT)
-		return;
-
 	/* blk-mq has its own handler, so we don't need ->rq_timed_out_fn */
 	if (!q->mq_ops && !q->rq_timed_out_fn)
 		return;
@@ -207,6 +211,11 @@ void blk_add_timer(struct request *req)
 		req->timeout = q->rq_timeout;
 
 	req->deadline = jiffies + req->timeout;
+
+	/*
+	 * Only the non-mq case needs to add the request to a protected list.
+	 * For the mq case we simply scan the tag map.
+	 */
 	if (!q->mq_ops)
 		list_add_tail(&req->timeout_list, &req->q->timeout_list);
 
diff --git a/block/blk.h b/block/blk.h
index da722eb786df..70e4aee9cdcb 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -72,8 +72,6 @@ void blk_dequeue_request(struct request *rq);
 void __blk_queue_free_tags(struct request_queue *q);
 bool __blk_end_bidi_request(struct request *rq, int error,
 			    unsigned int nr_bytes, unsigned int bidi_bytes);
-int blk_queue_enter(struct request_queue *q, gfp_t gfp);
-void blk_queue_exit(struct request_queue *q);
 void blk_freeze_queue(struct request_queue *q);
 
 static inline void blk_queue_enter_live(struct request_queue *q)
@@ -95,7 +93,7 @@ static inline void blk_flush_integrity(void)
 }
 #endif
 
-void blk_rq_timed_out_timer(unsigned long data);
+void blk_timeout_work(struct work_struct *work);
 unsigned long blk_rq_timeout(unsigned long timeout);
 void blk_add_timer(struct request *req);
 void blk_delete_timer(struct request *);
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 1f9093e901da..4a349787bc62 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -632,6 +632,13 @@ static inline struct cfq_group *cfqg_parent(struct cfq_group *cfqg)
 	return pblkg ? blkg_to_cfqg(pblkg) : NULL;
 }
 
+static inline bool cfqg_is_descendant(struct cfq_group *cfqg,
+				      struct cfq_group *ancestor)
+{
+	return cgroup_is_descendant(cfqg_to_blkg(cfqg)->blkcg->css.cgroup,
+				    cfqg_to_blkg(ancestor)->blkcg->css.cgroup);
+}
+
 static inline void cfqg_get(struct cfq_group *cfqg)
 {
 	return blkg_get(cfqg_to_blkg(cfqg));
@@ -758,6 +765,11 @@ static void cfqg_stats_xfer_dead(struct cfq_group *cfqg)
 #else	/* CONFIG_CFQ_GROUP_IOSCHED */
 
 static inline struct cfq_group *cfqg_parent(struct cfq_group *cfqg) { return NULL; }
+static inline bool cfqg_is_descendant(struct cfq_group *cfqg,
+				      struct cfq_group *ancestor)
+{
+	return true;
+}
 static inline void cfqg_get(struct cfq_group *cfqg) { }
 static inline void cfqg_put(struct cfq_group *cfqg) { }
 
@@ -2897,6 +2909,7 @@ static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 {
 	struct cfq_queue *cfqq = cfqd->active_queue;
+	struct cfq_rb_root *st = cfqq->service_tree;
 	struct cfq_io_cq *cic;
 	unsigned long sl, group_idle = 0;
 
@@ -2947,8 +2960,13 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 		return;
 	}
 
-	/* There are other queues in the group, don't do group idle */
-	if (group_idle && cfqq->cfqg->nr_cfqq > 1)
+	/*
+	 * There are other queues in the group or this is the only group and
+	 * it has too big thinktime, don't do group idle.
+	 */
+	if (group_idle &&
+	    (cfqq->cfqg->nr_cfqq > 1 ||
+	     cfq_io_thinktime_big(cfqd, &st->ttime, true)))
 		return;
 
 	cfq_mark_cfqq_wait_request(cfqq);
@@ -3947,16 +3965,27 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	if (rq_is_sync(rq) && !cfq_cfqq_sync(cfqq))
 		return true;
 
-	if (new_cfqq->cfqg != cfqq->cfqg)
+	/*
+	 * Treat ancestors of current cgroup the same way as current cgroup.
+	 * For anybody else we disallow preemption to guarantee service
+	 * fairness among cgroups.
+	 */
+	if (!cfqg_is_descendant(cfqq->cfqg, new_cfqq->cfqg))
 		return false;
 
 	if (cfq_slice_used(cfqq))
 		return true;
 
+	/*
+	 * Allow an RT request to pre-empt an ongoing non-RT cfqq timeslice.
+	 */
+	if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq))
+		return true;
+
+	WARN_ON_ONCE(cfqq->ioprio_class != new_cfqq->ioprio_class);
 	/* Allow preemption only if we are idling on sync-noidle tree */
 	if (cfqd->serving_wl_type == SYNC_NOIDLE_WORKLOAD &&
 	    cfqq_type(new_cfqq) == SYNC_NOIDLE_WORKLOAD &&
-	    new_cfqq->service_tree->count == 2 &&
 	    RB_EMPTY_ROOT(&cfqq->sort_list))
 		return true;
 
@@ -3967,12 +3996,6 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	if ((rq->cmd_flags & REQ_PRIO) && !cfqq->prio_pending)
 		return true;
 
-	/*
-	 * Allow an RT request to pre-empt an ongoing non-RT cfqq timeslice.
-	 */
-	if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq))
-		return true;
-
 	/* An idle queue should not be idle now for some reason */
 	if (RB_EMPTY_ROOT(&cfqq->sort_list) && !cfq_should_idle(cfqd, cfqq))
 		return true;
@@ -4052,7 +4075,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		 * idle timer unplug to continue working.
 		 */
 		if (cfq_cfqq_wait_request(cfqq)) {
-			if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE ||
+			if (blk_rq_bytes(rq) > PAGE_SIZE ||
 			    cfqd->busy_queues > 1) {
 				cfq_del_timer(cfqd, cfqq);
 				cfq_clear_cfqq_wait_request(cfqq);
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index f678c733df40..556826ac7cb4 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -710,7 +710,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 			return -EINVAL;
 		bdi = blk_get_backing_dev_info(bdev);
 		return compat_put_long(arg,
-				       (bdi->ra_pages * PAGE_CACHE_SIZE) / 512);
+				       (bdi->ra_pages * PAGE_SIZE) / 512);
 	case BLKROGET: /* compatible */
 		return compat_put_int(arg, bdev_read_only(bdev) != 0);
 	case BLKBSZGET_32: /* get the logical block size (cf. BLKSSZGET) */
@@ -729,7 +729,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 		if (!capable(CAP_SYS_ADMIN))
 			return -EACCES;
 		bdi = blk_get_backing_dev_info(bdev);
-		bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE;
+		bdi->ra_pages = (arg * 512) / PAGE_SIZE;
 		return 0;
 	case BLKGETSIZE:
 		size = i_size_read(bdev->bd_inode);
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index a753df2b3fc2..d0dd7882d8c7 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -39,7 +39,6 @@ struct deadline_data {
 	 */
 	struct request *next_rq[2];
 	unsigned int batching;		/* number of sequential requests made */
-	sector_t last_sector;		/* head position */
 	unsigned int starved;		/* times reads have starved writes */
 
 	/*
@@ -210,8 +209,6 @@ deadline_move_request(struct deadline_data *dd, struct request *rq)
 	dd->next_rq[WRITE] = NULL;
 	dd->next_rq[data_dir] = deadline_latter_request(rq);
 
-	dd->last_sector = rq_end_sector(rq);
-
 	/*
 	 * take it off the sort and fifo list, move
 	 * to dispatch queue
diff --git a/block/genhd.c b/block/genhd.c
index e5cafa51567c..9f42526b4d62 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -20,6 +20,7 @@
 #include <linux/idr.h>
 #include <linux/log2.h>
 #include <linux/pm_runtime.h>
+#include <linux/badblocks.h>
 
 #include "blk.h"
 
@@ -664,7 +665,6 @@ void del_gendisk(struct gendisk *disk)
 
 	kobject_put(disk->part0.holder_dir);
 	kobject_put(disk->slave_dir);
-	disk->driverfs_dev = NULL;
 	if (!sysfs_deprecated)
 		sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
 	pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
@@ -672,6 +672,31 @@ void del_gendisk(struct gendisk *disk)
 }
 EXPORT_SYMBOL(del_gendisk);
 
+/* sysfs access to bad-blocks list. */
+static ssize_t disk_badblocks_show(struct device *dev,
+					struct device_attribute *attr,
+					char *page)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	if (!disk->bb)
+		return sprintf(page, "\n");
+
+	return badblocks_show(disk->bb, page, 0);
+}
+
+static ssize_t disk_badblocks_store(struct device *dev,
+					struct device_attribute *attr,
+					const char *page, size_t len)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	if (!disk->bb)
+		return -ENXIO;
+
+	return badblocks_store(disk->bb, page, len, 0);
+}
+
 /**
  * get_gendisk - get partitioning information for a given device
  * @devt: device to get partitioning information for
@@ -990,6 +1015,8 @@ static DEVICE_ATTR(discard_alignment, S_IRUGO, disk_discard_alignment_show,
 static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL);
 static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
 static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL);
+static DEVICE_ATTR(badblocks, S_IRUGO | S_IWUSR, disk_badblocks_show,
+		disk_badblocks_store);
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 static struct device_attribute dev_attr_fail =
 	__ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store);
@@ -1011,6 +1038,7 @@ static struct attribute *disk_attrs[] = {
 	&dev_attr_capability.attr,
 	&dev_attr_stat.attr,
 	&dev_attr_inflight.attr,
+	&dev_attr_badblocks.attr,
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	&dev_attr_fail.attr,
 #endif
@@ -1421,7 +1449,7 @@ static DEFINE_MUTEX(disk_events_mutex);
 static LIST_HEAD(disk_events);
 
 /* disable in-kernel polling by default */
-static unsigned long disk_events_dfl_poll_msecs	= 0;
+static unsigned long disk_events_dfl_poll_msecs;
 
 static unsigned long disk_events_poll_jiffies(struct gendisk *disk)
 {
diff --git a/block/ioctl.c b/block/ioctl.c
index 0918aed2d847..4ff1f92f89ca 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -4,6 +4,7 @@
 #include <linux/gfp.h>
 #include <linux/blkpg.h>
 #include <linux/hdreg.h>
+#include <linux/badblocks.h>
 #include <linux/backing-dev.h>
 #include <linux/fs.h>
 #include <linux/blktrace_api.h>
@@ -406,6 +407,35 @@ static inline int is_unrecognized_ioctl(int ret)
 		ret == -ENOIOCTLCMD;
 }
 
+#ifdef CONFIG_FS_DAX
+bool blkdev_dax_capable(struct block_device *bdev)
+{
+	struct gendisk *disk = bdev->bd_disk;
+
+	if (!disk->fops->direct_access)
+		return false;
+
+	/*
+	 * If the partition is not aligned on a page boundary, we can't
+	 * do dax I/O to it.
+	 */
+	if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512))
+			|| (bdev->bd_part->nr_sects % (PAGE_SIZE / 512)))
+		return false;
+
+	/*
+	 * If the device has known bad blocks, force all I/O through the
+	 * driver / page cache.
+	 *
+	 * TODO: support finer grained dax error handling
+	 */
+	if (disk->bb && disk->bb->count)
+		return false;
+
+	return true;
+}
+#endif
+
 static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode,
 		unsigned cmd, unsigned long arg)
 {
@@ -520,7 +550,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 		if (!arg)
 			return -EINVAL;
 		bdi = blk_get_backing_dev_info(bdev);
-		return put_long(arg, (bdi->ra_pages * PAGE_CACHE_SIZE) / 512);
+		return put_long(arg, (bdi->ra_pages * PAGE_SIZE) / 512);
 	case BLKROGET:
 		return put_int(arg, bdev_read_only(bdev) != 0);
 	case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */
@@ -548,7 +578,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 		if(!capable(CAP_SYS_ADMIN))
 			return -EACCES;
 		bdi = blk_get_backing_dev_info(bdev);
-		bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE;
+		bdi->ra_pages = (arg * 512) / PAGE_SIZE;
 		return 0;
 	case BLKBSZSET:
 		return blkdev_bszset(bdev, mode, argp);
@@ -568,6 +598,9 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case BLKTRACESETUP:
 	case BLKTRACETEARDOWN:
 		return blk_trace_ioctl(bdev, cmd, argp);
+	case BLKDAXGET:
+		return put_int(arg, !!(bdev->bd_inode->i_flags & S_DAX));
+		break;
 	case IOC_PR_REGISTER:
 		return blkdev_pr_register(bdev, argp);
 	case IOC_PR_RESERVE:
diff --git a/block/ioprio.c b/block/ioprio.c
index 31666c92b46a..cc7800e9eb44 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -123,7 +123,8 @@ SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio)
 				break;
 
 			do_each_thread(g, p) {
-				if (!uid_eq(task_uid(p), uid))
+				if (!uid_eq(task_uid(p), uid) ||
+				    !task_pid_vnr(p))
 					continue;
 				ret = set_task_ioprio(p, ioprio);
 				if (ret)
@@ -220,7 +221,8 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who)
 				break;
 
 			do_each_thread(g, p) {
-				if (!uid_eq(task_uid(p), user->uid))
+				if (!uid_eq(task_uid(p), user->uid) ||
+				    !task_pid_vnr(p))
 					continue;
 				tmpio = get_task_ioprio(p);
 				if (tmpio < 0)
diff --git a/block/noop-iosched.c b/block/noop-iosched.c
index 3de89d4690f3..a163c487cf38 100644
--- a/block/noop-iosched.c
+++ b/block/noop-iosched.c
@@ -21,10 +21,10 @@ static void noop_merged_requests(struct request_queue *q, struct request *rq,
 static int noop_dispatch(struct request_queue *q, int force)
 {
 	struct noop_data *nd = q->elevator->elevator_data;
+	struct request *rq;
 
-	if (!list_empty(&nd->queue)) {
-		struct request *rq;
-		rq = list_entry(nd->queue.next, struct request, queuelist);
+	rq = list_first_entry_or_null(&nd->queue, struct request, queuelist);
+	if (rq) {
 		list_del_init(&rq->queuelist);
 		elv_dispatch_sort(q, rq);
 		return 1;
@@ -46,7 +46,7 @@ noop_former_request(struct request_queue *q, struct request *rq)
 
 	if (rq->queuelist.prev == &nd->queue)
 		return NULL;
-	return list_entry(rq->queuelist.prev, struct request, queuelist);
+	return list_prev_entry(rq, queuelist);
 }
 
 static struct request *
@@ -56,7 +56,7 @@ noop_latter_request(struct request_queue *q, struct request *rq)
 
 	if (rq->queuelist.next == &nd->queue)
 		return NULL;
-	return list_entry(rq->queuelist.next, struct request, queuelist);
+	return list_next_entry(rq, queuelist);
 }
 
 static int noop_init_queue(struct request_queue *q, struct elevator_type *e)
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 3b030157ec85..d7eb77e1e3a8 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -16,6 +16,7 @@
 #include <linux/kmod.h>
 #include <linux/ctype.h>
 #include <linux/genhd.h>
+#include <linux/dax.h>
 #include <linux/blktrace_api.h>
 
 #include "partitions/check.h"
@@ -216,10 +217,21 @@ static void part_release(struct device *dev)
 	kfree(p);
 }
 
+static int part_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	struct hd_struct *part = dev_to_part(dev);
+
+	add_uevent_var(env, "PARTN=%u", part->partno);
+	if (part->info && part->info->volname[0])
+		add_uevent_var(env, "PARTNAME=%s", part->info->volname);
+	return 0;
+}
+
 struct device_type part_type = {
 	.name		= "partition",
 	.groups		= part_attr_groups,
 	.release	= part_release,
+	.uevent		= part_uevent,
 };
 
 static void delete_partition_rcu_cb(struct rcu_head *head)
@@ -349,15 +361,20 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
 			goto out_del;
 	}
 
+	err = hd_ref_init(p);
+	if (err) {
+		if (flags & ADDPART_FLAG_WHOLEDISK)
+			goto out_remove_file;
+		goto out_del;
+	}
+
 	/* everything is up and running, commence */
 	rcu_assign_pointer(ptbl->part[partno], p);
 
 	/* suppress uevent if the disk suppresses it */
 	if (!dev_get_uevent_suppress(ddev))
 		kobject_uevent(&pdev->kobj, KOBJ_ADD);
-
-	if (!hd_ref_init(p))
-		return p;
+	return p;
 
 out_free_info:
 	free_part_info(p);
@@ -366,6 +383,8 @@ out_free_stats:
 out_free:
 	kfree(p);
 	return ERR_PTR(err);
+out_remove_file:
+	device_remove_file(pdev, &dev_attr_whole_disk);
 out_del:
 	kobject_put(p->holder_dir);
 	device_del(pdev);
@@ -397,7 +416,7 @@ static int drop_partitions(struct gendisk *disk, struct block_device *bdev)
 	struct hd_struct *part;
 	int res;
 
-	if (bdev->bd_part_count)
+	if (bdev->bd_part_count || bdev->bd_super)
 		return -EBUSY;
 	res = invalidate_partition(disk, 0);
 	if (res)
@@ -550,20 +569,31 @@ int invalidate_partitions(struct gendisk *disk, struct block_device *bdev)
 	return 0;
 }
 
-unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p)
+static struct page *read_pagecache_sector(struct block_device *bdev, sector_t n)
 {
 	struct address_space *mapping = bdev->bd_inode->i_mapping;
-	struct page *page;
 
-	page = read_mapping_page(mapping, (pgoff_t)(n >> (PAGE_CACHE_SHIFT-9)),
+	return read_mapping_page(mapping, (pgoff_t)(n >> (PAGE_SHIFT-9)),
 				 NULL);
+}
+
+unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p)
+{
+	struct page *page;
+
+	/* don't populate page cache for dax capable devices */
+	if (IS_DAX(bdev->bd_inode))
+		page = read_dax_sector(bdev, n);
+	else
+		page = read_pagecache_sector(bdev, n);
+
 	if (!IS_ERR(page)) {
 		if (PageError(page))
 			goto fail;
 		p->v = page;
-		return (unsigned char *)page_address(page) +  ((n & ((1 << (PAGE_CACHE_SHIFT - 9)) - 1)) << 9);
+		return (unsigned char *)page_address(page) +  ((n & ((1 << (PAGE_SHIFT - 9)) - 1)) << 9);
 fail:
-		page_cache_release(page);
+		put_page(page);
 	}
 	p->v = NULL;
 	return NULL;
diff --git a/block/partitions/mac.c b/block/partitions/mac.c
index c2c48ec64b27..621317ac4d59 100644
--- a/block/partitions/mac.c
+++ b/block/partitions/mac.c
@@ -32,7 +32,7 @@ int mac_partition(struct parsed_partitions *state)
 	Sector sect;
 	unsigned char *data;
 	int slot, blocks_in_map;
-	unsigned secsize;
+	unsigned secsize, datasize, partoffset;
 #ifdef CONFIG_PPC_PMAC
 	int found_root = 0;
 	int found_root_goodness = 0;
@@ -50,10 +50,14 @@ int mac_partition(struct parsed_partitions *state)
 	}
 	secsize = be16_to_cpu(md->block_size);
 	put_dev_sector(sect);
-	data = read_part_sector(state, secsize/512, &sect);
+	datasize = round_down(secsize, 512);
+	data = read_part_sector(state, datasize / 512, &sect);
 	if (!data)
 		return -1;
-	part = (struct mac_partition *) (data + secsize%512);
+	partoffset = secsize % 512;
+	if (partoffset + sizeof(*part) > datasize)
+		return -1;
+	part = (struct mac_partition *) (data + partoffset);
 	if (be16_to_cpu(part->signature) != MAC_PARTITION_MAGIC) {
 		put_dev_sector(sect);
 		return 0;		/* not a MacOS disk */
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index dda653ce7b24..0774799942e0 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -444,7 +444,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 
 	}
 
-	rq = blk_get_request(q, in_len ? WRITE : READ, __GFP_WAIT);
+	rq = blk_get_request(q, in_len ? WRITE : READ, __GFP_RECLAIM);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto error_free_buffer;
@@ -495,7 +495,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 		break;
 	}
 
-	if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, __GFP_WAIT)) {
+	if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, __GFP_RECLAIM)) {
 		err = DRIVER_ERROR << 24;
 		goto error;
 	}
@@ -536,7 +536,7 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
 	struct request *rq;
 	int err;
 
-	rq = blk_get_request(q, WRITE, __GFP_WAIT);
+	rq = blk_get_request(q, WRITE, __GFP_RECLAIM);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 	blk_rq_set_block_pc(rq);