#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/bootmem.h> /* for max_pfn/max_low_pfn */
+#include <linux/gcd.h>
+#include <linux/lcm.h>
+#include <linux/jiffies.h>
+#include <linux/gfp.h>
#include "blk.h"
EXPORT_SYMBOL(blk_queue_prep_rq);
/**
- * blk_queue_set_discard - set a discard_sectors function for queue
- * @q: queue
- * @dfn: prepare_discard function
- *
- * It's possible for a queue to register a discard callback which is used
- * to transform a discard request into the appropriate type for the
- * hardware. If none is registered, then discard requests are failed
- * with %EOPNOTSUPP.
- *
- */
-void blk_queue_set_discard(struct request_queue *q, prepare_discard_fn *dfn)
-{
- q->prepare_discard_fn = dfn;
-}
-EXPORT_SYMBOL(blk_queue_set_discard);
-
-/**
* blk_queue_merge_bvec - set a merge_bvec function for queue
* @q: queue
* @mbfn: merge_bvec_fn
EXPORT_SYMBOL_GPL(blk_queue_lld_busy);
/**
+ * blk_set_default_limits - reset limits to default values
+ * @lim: the queue_limits structure to reset
+ *
+ * Description:
+ * Returns a queue_limit struct to its default state. Can be used by
+ * stacking drivers like DM that stage table swaps and reuse an
+ * existing device queue.
+ */
+void blk_set_default_limits(struct queue_limits *lim)
+{
+ lim->max_segments = BLK_MAX_SEGMENTS;
+ lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
+ lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
+ lim->max_sectors = BLK_DEF_MAX_SECTORS;
+ lim->max_hw_sectors = INT_MAX;
+ lim->max_discard_sectors = 0;
+ lim->discard_granularity = 0;
+ lim->discard_alignment = 0;
+ lim->discard_misaligned = 0;
+ lim->discard_zeroes_data = -1;
+ lim->logical_block_size = lim->physical_block_size = lim->io_min = 512;
+ lim->bounce_pfn = (unsigned long)(BLK_BOUNCE_ANY >> PAGE_SHIFT);
+ lim->alignment_offset = 0;
+ lim->io_opt = 0;
+ lim->misaligned = 0;
+ lim->no_cluster = 0;
+}
+EXPORT_SYMBOL(blk_set_default_limits);
+
+/**
* blk_queue_make_request - define an alternate make_request function for a device
* @q: the request queue for the device to be affected
* @mfn: the alternate make_request function
* set defaults
*/
q->nr_requests = BLKDEV_MAX_RQ;
- blk_queue_max_phys_segments(q, MAX_PHYS_SEGMENTS);
- blk_queue_max_hw_segments(q, MAX_HW_SEGMENTS);
- blk_queue_segment_boundary(q, BLK_SEG_BOUNDARY_MASK);
- blk_queue_max_segment_size(q, MAX_SEGMENT_SIZE);
q->make_request_fn = mfn;
- q->backing_dev_info.ra_pages =
- (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
- q->backing_dev_info.state = 0;
- q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
- blk_queue_max_sectors(q, SAFE_MAX_SECTORS);
- blk_queue_logical_block_size(q, 512);
blk_queue_dma_alignment(q, 511);
blk_queue_congestion_threshold(q);
q->nr_batching = BLK_BATCH_REQ;
q->unplug_thresh = 4; /* hmm */
- q->unplug_delay = (3 * HZ) / 1000; /* 3 milliseconds */
+ q->unplug_delay = msecs_to_jiffies(3); /* 3 milliseconds */
if (q->unplug_delay == 0)
q->unplug_delay = 1;
q->unplug_timer.function = blk_unplug_timeout;
q->unplug_timer.data = (unsigned long)q;
+ blk_set_default_limits(&q->limits);
+ blk_queue_max_hw_sectors(q, BLK_SAFE_MAX_SECTORS);
+
+ /*
+ * 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
*/
EXPORT_SYMBOL(blk_queue_bounce_limit);
/**
- * blk_queue_max_sectors - set max sectors for a request for this queue
+ * blk_queue_max_hw_sectors - set max sectors for a request for this queue
* @q: the request queue for the device
- * @max_sectors: max sectors in the usual 512b unit
+ * @max_hw_sectors: max hardware sectors in the usual 512b unit
*
* Description:
- * Enables a low level driver to set an upper limit on the size of
- * received requests.
+ * Enables a low level driver to set a hard upper limit,
+ * max_hw_sectors, on the size of requests. max_hw_sectors is set by
+ * the device driver based upon the combined capabilities of I/O
+ * controller and storage device.
+ *
+ * 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_queue_max_sectors(struct request_queue *q, unsigned int max_sectors)
+void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors)
{
- if ((max_sectors << 9) < PAGE_CACHE_SIZE) {
- max_sectors = 1 << (PAGE_CACHE_SHIFT - 9);
+ if ((max_hw_sectors << 9) < PAGE_CACHE_SIZE) {
+ max_hw_sectors = 1 << (PAGE_CACHE_SHIFT - 9);
printk(KERN_INFO "%s: set to minimum %d\n",
- __func__, max_sectors);
- }
-
- if (BLK_DEF_MAX_SECTORS > max_sectors)
- q->limits.max_hw_sectors = q->limits.max_sectors = max_sectors;
- else {
- q->limits.max_sectors = BLK_DEF_MAX_SECTORS;
- q->limits.max_hw_sectors = max_sectors;
+ __func__, max_hw_sectors);
}
-}
-EXPORT_SYMBOL(blk_queue_max_sectors);
-void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_sectors)
-{
- if (BLK_DEF_MAX_SECTORS > max_sectors)
- q->limits.max_hw_sectors = BLK_DEF_MAX_SECTORS;
- else
- q->limits.max_hw_sectors = max_sectors;
+ q->limits.max_hw_sectors = max_hw_sectors;
+ q->limits.max_sectors = min_t(unsigned int, max_hw_sectors,
+ BLK_DEF_MAX_SECTORS);
}
EXPORT_SYMBOL(blk_queue_max_hw_sectors);
/**
- * blk_queue_max_phys_segments - set max phys segments for a request for this queue
+ * blk_queue_max_discard_sectors - set max sectors for a single discard
* @q: the request queue for the device
- * @max_segments: max number of segments
- *
- * Description:
- * Enables a low level driver to set an upper limit on the number of
- * physical data segments in a request. This would be the largest sized
- * scatter list the driver could handle.
+ * @max_discard_sectors: maximum number of sectors to discard
**/
-void blk_queue_max_phys_segments(struct request_queue *q,
- unsigned short max_segments)
+void blk_queue_max_discard_sectors(struct request_queue *q,
+ unsigned int max_discard_sectors)
{
- if (!max_segments) {
- max_segments = 1;
- printk(KERN_INFO "%s: set to minimum %d\n",
- __func__, max_segments);
- }
-
- q->limits.max_phys_segments = max_segments;
+ q->limits.max_discard_sectors = max_discard_sectors;
}
-EXPORT_SYMBOL(blk_queue_max_phys_segments);
+EXPORT_SYMBOL(blk_queue_max_discard_sectors);
/**
- * blk_queue_max_hw_segments - set max hw segments for a request for this queue
+ * blk_queue_max_segments - set max hw segments for a request for this queue
* @q: the request queue for the device
* @max_segments: max number of segments
*
* Description:
* Enables a low level driver to set an upper limit on the number of
- * hw data segments in a request. This would be the largest number of
- * address/length pairs the host adapter can actually give at once
- * to the device.
+ * hw data segments in a request.
**/
-void blk_queue_max_hw_segments(struct request_queue *q,
- unsigned short max_segments)
+void blk_queue_max_segments(struct request_queue *q, unsigned short max_segments)
{
if (!max_segments) {
max_segments = 1;
__func__, max_segments);
}
- q->limits.max_hw_segments = max_segments;
+ q->limits.max_segments = max_segments;
}
-EXPORT_SYMBOL(blk_queue_max_hw_segments);
+EXPORT_SYMBOL(blk_queue_max_segments);
/**
* blk_queue_max_segment_size - set max segment size for blk_rq_map_sg
/**
* blk_queue_alignment_offset - set physical block alignment offset
* @q: the request queue for the device
- * @alignment: alignment offset in bytes
+ * @offset: alignment offset in bytes
*
* Description:
* Some devices are naturally misaligned to compensate for things like
EXPORT_SYMBOL(blk_queue_alignment_offset);
/**
- * blk_queue_io_min - set minimum request size for the queue
- * @q: the request queue for the device
- * @io_min: smallest I/O size in bytes
+ * blk_limits_io_min - set minimum request size for a device
+ * @limits: the queue limits
+ * @min: smallest I/O size in bytes
*
* Description:
* Some devices have an internal block size bigger than the reported
* 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);
/**
+ * blk_limits_io_opt - set optimal request size for a device
+ * @limits: the queue limits
+ * @opt: smallest I/O size in bytes
+ *
+ * Description:
+ * 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_limits_io_opt(struct queue_limits *limits, unsigned int opt)
+{
+ limits->io_opt = opt;
+}
+EXPORT_SYMBOL(blk_limits_io_opt);
+
+/**
* blk_queue_io_opt - set optimal request size for the queue
* @q: the request queue for the device
- * @io_opt: optimal request size in bytes
+ * @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)
{
- q->limits.io_opt = opt;
+ blk_limits_io_opt(&q->limits, opt);
}
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);
/**
* blk_stack_limits - adjust queue_limits for stacked devices
- * @t: the stacking driver limits (top)
- * @bdev: the underlying queue limits (bottom)
- * @offset: offset to beginning of data within component device
+ * @t: the stacking driver limits (top device)
+ * @b: the underlying queue limits (bottom, component device)
+ * @start: first data sector within component device
*
* Description:
- * Merges two queue_limit structs. Returns 0 if alignment didn't
- * change. Returns -1 if adding the bottom device caused
- * misalignment.
+ * This function is used by stacking drivers like MD and DM to ensure
+ * that all component devices have compatible block sizes and
+ * alignments. The stacking driver must provide a queue_limits
+ * struct (top) and then iteratively call the stacking function for
+ * all component (bottom) devices. The stacking function will
+ * attempt to combine the values and ensure proper alignment.
+ *
+ * Returns 0 if the top and bottom queue_limits are compatible. The
+ * top device's block sizes and alignment offsets may be adjusted to
+ * ensure alignment with the bottom device. If no compatible sizes
+ * and alignments exist, -1 is returned and the resulting top
+ * queue_limits will have the misaligned flag set to indicate that
+ * the alignment_offset is undefined.
*/
int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
- sector_t offset)
+ sector_t start)
{
+ unsigned int top, bottom, alignment, ret = 0;
+
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->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn);
t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
b->seg_boundary_mask);
- t->max_phys_segments = min_not_zero(t->max_phys_segments,
- b->max_phys_segments);
-
- t->max_hw_segments = min_not_zero(t->max_hw_segments,
- b->max_hw_segments);
+ t->max_segments = min_not_zero(t->max_segments, b->max_segments);
t->max_segment_size = min_not_zero(t->max_segment_size,
b->max_segment_size);
+ t->misaligned |= b->misaligned;
+
+ alignment = queue_limit_alignment_offset(b, start);
+
+ /* Bottom device has different alignment. Check that it is
+ * compatible with the current top alignment.
+ */
+ if (t->alignment_offset != alignment) {
+
+ top = max(t->physical_block_size, t->io_min)
+ + t->alignment_offset;
+ bottom = max(b->physical_block_size, b->io_min) + alignment;
+
+ /* Verify that top and bottom intervals line up */
+ if (max(top, bottom) & (min(top, bottom) - 1)) {
+ t->misaligned = 1;
+ ret = -1;
+ }
+ }
+
t->logical_block_size = max(t->logical_block_size,
b->logical_block_size);
b->physical_block_size);
t->io_min = max(t->io_min, b->io_min);
+ t->io_opt = lcm(t->io_opt, b->io_opt);
+
t->no_cluster |= b->no_cluster;
+ t->discard_zeroes_data &= b->discard_zeroes_data;
+
+ /* Physical block size a multiple of the logical block size? */
+ if (t->physical_block_size & (t->logical_block_size - 1)) {
+ t->physical_block_size = t->logical_block_size;
+ t->misaligned = 1;
+ ret = -1;
+ }
+
+ /* Minimum I/O a multiple of the physical block size? */
+ if (t->io_min & (t->physical_block_size - 1)) {
+ t->io_min = t->physical_block_size;
+ t->misaligned = 1;
+ ret = -1;
+ }
- /* Bottom device offset aligned? */
- if (offset &&
- (offset & (b->physical_block_size - 1)) != b->alignment_offset) {
+ /* Optimal I/O a multiple of the physical block size? */
+ if (t->io_opt & (t->physical_block_size - 1)) {
+ t->io_opt = 0;
t->misaligned = 1;
- return -1;
+ ret = -1;
}
- /* If top has no alignment offset, inherit from bottom */
- if (!t->alignment_offset)
- t->alignment_offset =
- b->alignment_offset & (b->physical_block_size - 1);
+ /* Find lowest common alignment_offset */
+ t->alignment_offset = lcm(t->alignment_offset, alignment)
+ & (max(t->physical_block_size, t->io_min) - 1);
- /* Top device aligned on logical block boundary? */
+ /* Verify that new alignment_offset is on a logical block boundary */
if (t->alignment_offset & (t->logical_block_size - 1)) {
t->misaligned = 1;
- return -1;
+ ret = -1;
}
- return 0;
+ /* Discard alignment and granularity */
+ if (b->discard_granularity) {
+ alignment = queue_limit_discard_alignment(b, start);
+
+ if (t->discard_granularity != 0 &&
+ t->discard_alignment != alignment) {
+ top = t->discard_granularity + t->discard_alignment;
+ bottom = b->discard_granularity + alignment;
+
+ /* Verify that top and bottom intervals line up */
+ if (max(top, bottom) & (min(top, bottom) - 1))
+ t->discard_misaligned = 1;
+ }
+
+ t->max_discard_sectors = min_not_zero(t->max_discard_sectors,
+ b->max_discard_sectors);
+ t->discard_granularity = max(t->discard_granularity,
+ b->discard_granularity);
+ t->discard_alignment = lcm(t->discard_alignment, alignment) &
+ (t->discard_granularity - 1);
+ }
+
+ return ret;
}
+EXPORT_SYMBOL(blk_stack_limits);
+
+/**
+ * bdev_stack_limits - adjust queue limits for stacked drivers
+ * @t: the stacking driver limits (top device)
+ * @bdev: the component block_device (bottom)
+ * @start: first data sector within component device
+ *
+ * Description:
+ * Merges queue limits for a top device and a block_device. Returns
+ * 0 if alignment didn't change. Returns -1 if adding the bottom
+ * device caused misalignment.
+ */
+int bdev_stack_limits(struct queue_limits *t, struct block_device *bdev,
+ sector_t start)
+{
+ struct request_queue *bq = bdev_get_queue(bdev);
+
+ start += get_start_sect(bdev);
+
+ return blk_stack_limits(t, &bq->limits, start);
+}
+EXPORT_SYMBOL(bdev_stack_limits);
/**
* disk_stack_limits - adjust queue limits for stacked drivers
- * @t: MD/DM gendisk (top)
+ * @disk: MD/DM gendisk (top)
* @bdev: the underlying block device (bottom)
* @offset: offset to beginning of data within component device
*
* Description:
- * Merges the limits for two queues. Returns 0 if alignment
- * didn't change. Returns -1 if adding the bottom device caused
- * misalignment.
+ * Merges the limits for a top level gendisk and a bottom level
+ * block_device.
*/
void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
sector_t offset)
struct request_queue *t = disk->queue;
struct request_queue *b = bdev_get_queue(bdev);
- offset += get_start_sect(bdev) << 9;
-
- if (blk_stack_limits(&t->limits, &b->limits, offset) < 0) {
+ if (bdev_stack_limits(&t->limits, bdev, offset >> 9) < 0) {
char top[BDEVNAME_SIZE], bottom[BDEVNAME_SIZE];
disk_name(disk, 0, top);
* does is adjust the queue so that the buf is always appended
* silently to the scatterlist.
*
- * Note: This routine adjusts max_hw_segments to make room for
- * appending the drain buffer. If you call
- * blk_queue_max_hw_segments() or blk_queue_max_phys_segments() after
- * calling this routine, you must set the limit to one fewer than your
- * device can support otherwise there won't be room for the drain
- * buffer.
+ * Note: This routine adjusts max_hw_segments to make room for appending
+ * the drain buffer. If you call blk_queue_max_segments() after calling
+ * this routine, you must set the limit to one fewer than your device
+ * can support otherwise there won't be room for the drain buffer.
*/
int blk_queue_dma_drain(struct request_queue *q,
dma_drain_needed_fn *dma_drain_needed,
void *buf, unsigned int size)
{
- if (queue_max_hw_segments(q) < 2 || queue_max_phys_segments(q) < 2)
+ if (queue_max_segments(q) < 2)
return -EINVAL;
/* make room for appending the drain */
- blk_queue_max_hw_segments(q, queue_max_hw_segments(q) - 1);
- blk_queue_max_phys_segments(q, queue_max_phys_segments(q) - 1);
+ blk_queue_max_segments(q, queue_max_segments(q) - 1);
q->dma_drain_needed = dma_drain_needed;
q->dma_drain_buffer = buf;
q->dma_drain_size = size;