diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index cbbd3e0699453391a461bff35431df5f0ee0d53e..5f3bedaf8e35e90dfc92b2cebee16f6caa025986 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -94,28 +94,37 @@ What: /sys/block/<disk>/queue/physical_block_size
Date: May 2009
Contact: Martin K. Petersen <martin.petersen@oracle.com>
Description:
- This is the smallest unit the storage device can write
- without resorting to read-modify-write operation. It is
- usually the same as the logical block size but may be
- bigger. One example is SATA drives with 4KB sectors
- that expose a 512-byte logical block size to the
- operating system.
+ This is the smallest unit a physical storage device can
+ write atomically. It is usually the same as the logical
+ block size but may be bigger. One example is SATA
+ drives with 4KB sectors that expose a 512-byte logical
+ block size to the operating system. For stacked block
+ devices the physical_block_size variable contains the
+ maximum physical_block_size of the component devices.
What: /sys/block/<disk>/queue/minimum_io_size
Date: April 2009
Contact: Martin K. Petersen <martin.petersen@oracle.com>
Description:
- Storage devices may report a preferred minimum I/O size,
- which is the smallest request the device can perform
- without incurring a read-modify-write penalty. For disk
- drives this is often the physical block size. For RAID
- arrays it is often the stripe chunk size.
+ 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.
What: /sys/block/<disk>/queue/optimal_io_size
Date: April 2009
Contact: Martin K. Petersen <martin.petersen@oracle.com>
Description:
Storage devices may report an optimal I/O size, which is
- the device's preferred unit of receiving I/O. This is
- rarely reported for disk drives. For RAID devices it is
- usually the stripe width or the internal block size.
+ 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. If no optimal I/O size is
+ reported this file contains 0.
diff --git a/block/Kconfig b/block/Kconfig
index 95a86adc33a189d9ef2fb31fb12426d62650627e..9be0b56eaee19ee494d388f07cda821ffcc29ba0 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-settings.c b/block/blk-settings.c
index 8a3ea3bba10d6c06a7276a3146864b3c674271b3..476d870650737eda44dc3177675a34afae63fd53 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"
@@ -384,8 +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:
@@ -394,15 +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);
@@ -412,8 +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)
{
@@ -433,27 +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);
@@ -523,6 +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/include/linux/blkdev.h b/include/linux/blkdev.h
index e7cb5dbf6c26a0daa4182c1d9eca0877583113b5..69103e053c9266e65e28eab0a15ae2c273de1094 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -913,6 +913,7 @@ extern void blk_queue_logical_block_size(struct request_queue *, unsigned short)
extern void blk_queue_physical_block_size(struct request_queue *, unsigned short);
extern void blk_queue_alignment_offset(struct request_queue *q,
unsigned int alignment);
+extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min);
extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt);
extern void blk_set_default_limits(struct queue_limits *lim);