Merge branch 'percpu-for-linus' into percpu-for-next

Conflicts:
	arch/sparc/kernel/smp_64.c
	arch/x86/kernel/cpu/perf_counter.c
	arch/x86/kernel/setup_percpu.c
	drivers/cpufreq/cpufreq_ondemand.c
	mm/percpu.c

Conflicts in core and arch percpu codes are mostly from commit
ed78e1e078dd44249f88b1dd8c76dafb39567161 which substituted many
num_possible_cpus() with nr_cpu_ids.  As for-next branch has moved all
the first chunk allocators into mm/percpu.c, the changes are moved
from arch code to mm/percpu.c.

Signed-off-by: Tejun Heo <tj@kernel.org>

9 files changed, 94 insertions, 54 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 95a86adc33a..9be0b56eaee 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -48,9 +48,9 @@ config LBDAF
 	  If unsure, say Y.
 
 config BLK_DEV_BSG
-	bool "Block layer SG support v4 (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
-	---help---
+	bool "Block layer SG support v4"
+	default y
+	help
 	  Saying Y here will enable generic SG (SCSI generic) v4 support
 	  for any block device.
 
@@ -60,7 +60,10 @@ config BLK_DEV_BSG
 	  protocols (e.g. Task Management Functions and SMP in Serial
 	  Attached SCSI).
 
-	  If unsure, say N.
+	  This option is required by recent UDEV versions to properly
+	  access device serial numbers, etc.
+
+	  If unsure, say Y.
 
 config BLK_DEV_INTEGRITY
 	bool "Block layer data integrity support"
diff --git a/block/blk-core.c b/block/blk-core.c
index 4b45435c6ea..e3299a77a0d 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -575,13 +575,6 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
 		return NULL;
 	}
 
-	/*
-	 * if caller didn't supply a lock, they get per-queue locking with
-	 * our embedded lock
-	 */
-	if (!lock)
-		lock = &q->__queue_lock;
-
 	q->request_fn		= rfn;
 	q->prep_rq_fn		= NULL;
 	q->unplug_fn		= generic_unplug_device;
@@ -2143,7 +2136,7 @@ bool blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
 {
 	return blk_end_bidi_request(rq, error, nr_bytes, 0);
 }
-EXPORT_SYMBOL_GPL(blk_end_request);
+EXPORT_SYMBOL(blk_end_request);
 
 /**
  * blk_end_request_all - Helper function for drives to finish the request.
@@ -2164,7 +2157,7 @@ void blk_end_request_all(struct request *rq, int error)
 	pending = blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes);
 	BUG_ON(pending);
 }
-EXPORT_SYMBOL_GPL(blk_end_request_all);
+EXPORT_SYMBOL(blk_end_request_all);
 
 /**
  * blk_end_request_cur - Helper function to finish the current request chunk.
@@ -2182,7 +2175,7 @@ bool blk_end_request_cur(struct request *rq, int error)
 {
 	return blk_end_request(rq, error, blk_rq_cur_bytes(rq));
 }
-EXPORT_SYMBOL_GPL(blk_end_request_cur);
+EXPORT_SYMBOL(blk_end_request_cur);
 
 /**
  * __blk_end_request - Helper function for drivers to complete the request.
@@ -2201,7 +2194,7 @@ bool __blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
 {
 	return __blk_end_bidi_request(rq, error, nr_bytes, 0);
 }
-EXPORT_SYMBOL_GPL(__blk_end_request);
+EXPORT_SYMBOL(__blk_end_request);
 
 /**
  * __blk_end_request_all - Helper function for drives to finish the request.
@@ -2222,7 +2215,7 @@ void __blk_end_request_all(struct request *rq, int error)
 	pending = __blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes);
 	BUG_ON(pending);
 }
-EXPORT_SYMBOL_GPL(__blk_end_request_all);
+EXPORT_SYMBOL(__blk_end_request_all);
 
 /**
  * __blk_end_request_cur - Helper function to finish the current request chunk.
@@ -2241,7 +2234,7 @@ bool __blk_end_request_cur(struct request *rq, int error)
 {
 	return __blk_end_request(rq, error, blk_rq_cur_bytes(rq));
 }
-EXPORT_SYMBOL_GPL(__blk_end_request_cur);
+EXPORT_SYMBOL(__blk_end_request_cur);
 
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 		     struct bio *bio)
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 73e28d35568..15c630813b1 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -379,6 +379,7 @@ void blk_integrity_unregister(struct gendisk *disk)
 
 	kobject_uevent(&bi->kobj, KOBJ_REMOVE);
 	kobject_del(&bi->kobj);
+	kobject_put(&bi->kobj);
 	kmem_cache_free(integrity_cachep, bi);
 	disk->integrity = NULL;
 }
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 39ce64432ba..e1999679a4d 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -350,6 +350,12 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	if (blk_integrity_rq(req) != blk_integrity_rq(next))
 		return 0;
 
+	/* don't merge requests of different failfast settings */
+	if (blk_failfast_dev(req)	!= blk_failfast_dev(next)	||
+	    blk_failfast_transport(req)	!= blk_failfast_transport(next)	||
+	    blk_failfast_driver(req)	!= blk_failfast_driver(next))
+		return 0;
+
 	/*
 	 * If we are allowed to merge, then append bio list
 	 * from next to rq and release next. merge_requests_fn
diff --git a/block/blk-settings.c b/block/blk-settings.c
index bd582a7f531..476d8706507 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -7,6 +7,7 @@
 #include <linux/bio.h>
 #include <linux/blkdev.h>
 #include <linux/bootmem.h>	/* for max_pfn/max_low_pfn */
+#include <linux/gcd.h>
 
 #include "blk.h"
 
@@ -165,6 +166,13 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn)
 	blk_set_default_limits(&q->limits);
 
 	/*
+	 * If the caller didn't supply a lock, fall back to our embedded
+	 * per-queue locks
+	 */
+	if (!q->queue_lock)
+		q->queue_lock = &q->__queue_lock;
+
+	/*
 	 * by default assume old behaviour and bounce for any highmem page
 	 */
 	blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
@@ -377,8 +385,8 @@ void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset)
 EXPORT_SYMBOL(blk_queue_alignment_offset);
 
 /**
- * blk_queue_io_min - set minimum request size for the queue
- * @q:	the request queue for the device
+ * blk_limits_io_min - set minimum request size for a device
+ * @limits: the queue limits
  * @min:  smallest I/O size in bytes
  *
  * Description:
@@ -387,15 +395,35 @@ EXPORT_SYMBOL(blk_queue_alignment_offset);
  *   smallest I/O the device can perform without incurring a performance
  *   penalty.
  */
-void blk_queue_io_min(struct request_queue *q, unsigned int min)
+void blk_limits_io_min(struct queue_limits *limits, unsigned int min)
 {
-	q->limits.io_min = min;
+	limits->io_min = min;
 
-	if (q->limits.io_min < q->limits.logical_block_size)
-		q->limits.io_min = q->limits.logical_block_size;
+	if (limits->io_min < limits->logical_block_size)
+		limits->io_min = limits->logical_block_size;
 
-	if (q->limits.io_min < q->limits.physical_block_size)
-		q->limits.io_min = q->limits.physical_block_size;
+	if (limits->io_min < limits->physical_block_size)
+		limits->io_min = limits->physical_block_size;
+}
+EXPORT_SYMBOL(blk_limits_io_min);
+
+/**
+ * blk_queue_io_min - set minimum request size for the queue
+ * @q:	the request queue for the device
+ * @min:  smallest I/O size in bytes
+ *
+ * Description:
+ *   Storage devices may report a granularity or preferred minimum I/O
+ *   size which is the smallest request the device can perform without
+ *   incurring a performance penalty.  For disk drives this is often the
+ *   physical block size.  For RAID arrays it is often the stripe chunk
+ *   size.  A properly aligned multiple of minimum_io_size is the
+ *   preferred request size for workloads where a high number of I/O
+ *   operations is desired.
+ */
+void blk_queue_io_min(struct request_queue *q, unsigned int min)
+{
+	blk_limits_io_min(&q->limits, min);
 }
 EXPORT_SYMBOL(blk_queue_io_min);
 
@@ -405,8 +433,12 @@ EXPORT_SYMBOL(blk_queue_io_min);
  * @opt:  optimal request size in bytes
  *
  * Description:
- *   Drivers can call this function to set the preferred I/O request
- *   size for devices that report such a value.
+ *   Storage devices may report an optimal I/O size, which is the
+ *   device's preferred unit for sustained I/O.  This is rarely reported
+ *   for disk drives.  For RAID arrays it is usually the stripe width or
+ *   the internal track size.  A properly aligned multiple of
+ *   optimal_io_size is the preferred request size for workloads where
+ *   sustained throughput is desired.
  */
 void blk_queue_io_opt(struct request_queue *q, unsigned int opt)
 {
@@ -426,27 +458,7 @@ EXPORT_SYMBOL(blk_queue_io_opt);
  **/
 void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
 {
-	/* zero is "infinity" */
-	t->limits.max_sectors = min_not_zero(queue_max_sectors(t),
-					     queue_max_sectors(b));
-
-	t->limits.max_hw_sectors = min_not_zero(queue_max_hw_sectors(t),
-						queue_max_hw_sectors(b));
-
-	t->limits.seg_boundary_mask = min_not_zero(queue_segment_boundary(t),
-						   queue_segment_boundary(b));
-
-	t->limits.max_phys_segments = min_not_zero(queue_max_phys_segments(t),
-						   queue_max_phys_segments(b));
-
-	t->limits.max_hw_segments = min_not_zero(queue_max_hw_segments(t),
-						 queue_max_hw_segments(b));
-
-	t->limits.max_segment_size = min_not_zero(queue_max_segment_size(t),
-						  queue_max_segment_size(b));
-
-	t->limits.logical_block_size = max(queue_logical_block_size(t),
-					   queue_logical_block_size(b));
+	blk_stack_limits(&t->limits, &b->limits, 0);
 
 	if (!t->queue_lock)
 		WARN_ON_ONCE(1);
@@ -516,6 +528,16 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 		return -1;
 	}
 
+	/* Find lcm() of optimal I/O size */
+	if (t->io_opt && b->io_opt)
+		t->io_opt = (t->io_opt * b->io_opt) / gcd(t->io_opt, b->io_opt);
+	else if (b->io_opt)
+		t->io_opt = b->io_opt;
+
+	/* Verify that optimal I/O size is a multiple of io_min */
+	if (t->io_min && t->io_opt % t->io_min)
+		return -1;
+
 	return 0;
 }
 EXPORT_SYMBOL(blk_stack_limits);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index b1cd04087d6..418d6361968 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -16,9 +16,9 @@ struct queue_sysfs_entry {
 };
 
 static ssize_t
-queue_var_show(unsigned int var, char *page)
+queue_var_show(unsigned long var, char *page)
 {
-	return sprintf(page, "%d\n", var);
+	return sprintf(page, "%lu\n", var);
 }
 
 static ssize_t
@@ -77,7 +77,8 @@ 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)
 {
-	int ra_kb = q->backing_dev_info.ra_pages << (PAGE_CACHE_SHIFT - 10);
+	unsigned long ra_kb = q->backing_dev_info.ra_pages <<
+					(PAGE_CACHE_SHIFT - 10);
 
 	return queue_var_show(ra_kb, (page));
 }
@@ -189,9 +190,9 @@ static ssize_t queue_nomerges_store(struct request_queue *q, const char *page,
 
 static ssize_t queue_rq_affinity_show(struct request_queue *q, char *page)
 {
-	unsigned int set = test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags);
+	bool set = test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags);
 
-	return queue_var_show(set != 0, page);
+	return queue_var_show(set, page);
 }
 
 static ssize_t
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 85208dd1d05..1b2d12cda43 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -2311,7 +2311,7 @@ cfq_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask)
 		goto queue_fail;
 
 	cfqq = cic_to_cfqq(cic, is_sync);
-	if (!cfqq) {
+	if (!cfqq || cfqq == &cfqd->oom_cfqq) {
 		cfqq = cfq_get_queue(cfqd, is_sync, cic->ioc, gfp_mask);
 		cic_set_cfqq(cic, cfqq, is_sync);
 	}
diff --git a/block/elevator.c b/block/elevator.c
index ca861927ba4..2d511f9105e 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -100,6 +100,19 @@ int elv_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (bio_integrity(bio) != blk_integrity_rq(rq))
 		return 0;
 
+	/*
+	 * Don't merge if failfast settings don't match.
+	 *
+	 * FIXME: The negation in front of each condition is necessary
+	 * because bio and request flags use different bit positions
+	 * and the accessors return those bits directly.  This
+	 * ugliness will soon go away.
+	 */
+	if (!bio_failfast_dev(bio)	 != !blk_failfast_dev(rq)	||
+	    !bio_failfast_transport(bio) != !blk_failfast_transport(rq)	||
+	    !bio_failfast_driver(bio)	 != !blk_failfast_driver(rq))
+		return 0;
+
 	if (!elv_iosched_allow_merge(rq, bio))
 		return 0;
 
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index f0e0ce0a607..e5b10017a50 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -680,3 +680,4 @@ int __init blk_scsi_ioctl_init(void)
 	blk_set_cmd_filter_defaults(&blk_default_cmd_filter);
 	return 0;
 }
+fs_initcall(blk_scsi_ioctl_init);