#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/bootmem.h> /* for max_pfn/max_low_pfn */
+#include <linux/gcd.h>
+#include <linux/jiffies.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_phys_segments = MAX_PHYS_SEGMENTS;
+ lim->max_hw_segments = MAX_HW_SEGMENTS;
+ lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
+ lim->max_segment_size = 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_sectors(q, 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_max_hw_sectors);
/**
+ * blk_queue_max_discard_sectors - set max sectors for a single discard
+ * @q: the request queue for the device
+ * @max_discard_sectors: maximum number of sectors to discard
+ **/
+void blk_queue_max_discard_sectors(struct request_queue *q,
+ unsigned int max_discard_sectors)
+{
+ q->limits.max_discard_sectors = max_discard_sectors;
+}
+EXPORT_SYMBOL(blk_queue_max_discard_sectors);
+
+/**
* blk_queue_max_phys_segments - set max phys segments for a request for this queue
* @q: the request queue for the device
* @max_segments: max number of segments
void blk_queue_logical_block_size(struct request_queue *q, unsigned short size)
{
q->limits.logical_block_size = size;
+
+ if (q->limits.physical_block_size < size)
+ q->limits.physical_block_size = size;
+
+ if (q->limits.io_min < q->limits.physical_block_size)
+ q->limits.io_min = q->limits.physical_block_size;
}
EXPORT_SYMBOL(blk_queue_logical_block_size);
+/**
+ * blk_queue_physical_block_size - set physical block size for the queue
+ * @q: the request queue for the device
+ * @size: the physical block size, in bytes
+ *
+ * Description:
+ * This should be set to the lowest possible sector size that the
+ * hardware can operate on without reverting to read-modify-write
+ * operations.
+ */
+void blk_queue_physical_block_size(struct request_queue *q, unsigned short size)
+{
+ q->limits.physical_block_size = size;
+
+ if (q->limits.physical_block_size < q->limits.logical_block_size)
+ q->limits.physical_block_size = q->limits.logical_block_size;
+
+ if (q->limits.io_min < q->limits.physical_block_size)
+ q->limits.io_min = q->limits.physical_block_size;
+}
+EXPORT_SYMBOL(blk_queue_physical_block_size);
+
+/**
+ * blk_queue_alignment_offset - set physical block alignment offset
+ * @q: the request queue for the device
+ * @offset: alignment offset in bytes
+ *
+ * Description:
+ * Some devices are naturally misaligned to compensate for things like
+ * the legacy DOS partition table 63-sector offset. Low-level drivers
+ * should call this function for devices whose first sector is not
+ * naturally aligned.
+ */
+void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset)
+{
+ q->limits.alignment_offset =
+ offset & (q->limits.physical_block_size - 1);
+ q->limits.misaligned = 0;
+}
+EXPORT_SYMBOL(blk_queue_alignment_offset);
+
+/**
+ * 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
+ * hardware sector size. This function can be used to signal the
+ * smallest I/O the device can perform without incurring a performance
+ * penalty.
+ */
+void blk_limits_io_min(struct queue_limits *limits, unsigned int min)
+{
+ limits->io_min = min;
+
+ if (limits->io_min < limits->logical_block_size)
+ limits->io_min = limits->logical_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
+ * @opt: optimal request 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_queue_io_opt(struct request_queue *q, unsigned int opt)
+{
+ blk_limits_io_opt(&q->limits, opt);
+}
+EXPORT_SYMBOL(blk_queue_io_opt);
+
/*
* Returns the minimum that is _not_ zero, unless both are zero.
*/
**/
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));
+ blk_stack_limits(&t->limits, &b->limits, 0);
+
+ if (!t->queue_lock)
+ WARN_ON_ONCE(1);
+ else if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags)) {
+ unsigned long flags;
+ spin_lock_irqsave(t->queue_lock, flags);
+ queue_flag_clear(QUEUE_FLAG_CLUSTER, t);
+ spin_unlock_irqrestore(t->queue_lock, flags);
+ }
+}
+EXPORT_SYMBOL(blk_queue_stack_limits);
+
+static unsigned int lcm(unsigned int a, unsigned int b)
+{
+ if (a && b)
+ return (a * b) / gcd(a, b);
+ else if (b)
+ return b;
- t->limits.max_hw_sectors = min_not_zero(queue_max_hw_sectors(t),
- queue_max_hw_sectors(b));
+ return a;
+}
- t->limits.seg_boundary_mask = min_not_zero(queue_segment_boundary(t),
- queue_segment_boundary(b));
+/**
+ * blk_stack_limits - adjust queue_limits for stacked devices
+ * @t: the stacking driver limits (top)
+ * @b: the underlying queue limits (bottom)
+ * @offset: offset to beginning of data 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.
+ */
+int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
+ sector_t offset)
+{
+ int ret;
- t->limits.max_phys_segments = min_not_zero(queue_max_phys_segments(t),
- queue_max_phys_segments(b));
+ ret = 0;
- t->limits.max_hw_segments = min_not_zero(queue_max_hw_segments(t),
- queue_max_hw_segments(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->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn);
- t->limits.max_segment_size = min_not_zero(queue_max_segment_size(t),
- queue_max_segment_size(b));
+ t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
+ b->seg_boundary_mask);
- t->limits.logical_block_size = max(queue_logical_block_size(t),
- queue_logical_block_size(b));
+ 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_segment_size = min_not_zero(t->max_segment_size,
+ b->max_segment_size);
+
+ t->logical_block_size = max(t->logical_block_size,
+ b->logical_block_size);
+
+ t->physical_block_size = max(t->physical_block_size,
+ b->physical_block_size);
+
+ t->io_min = max(t->io_min, b->io_min);
+ t->no_cluster |= b->no_cluster;
+ t->discard_zeroes_data &= b->discard_zeroes_data;
+
+ /* Bottom device offset aligned? */
+ if (offset &&
+ (offset & (b->physical_block_size - 1)) != b->alignment_offset) {
+ t->misaligned = 1;
+ ret = -1;
+ }
+
+ if (offset &&
+ (offset & (b->discard_granularity - 1)) != b->discard_alignment) {
+ t->discard_misaligned = 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);
+
+ if (!t->discard_alignment)
+ t->discard_alignment =
+ b->discard_alignment & (b->discard_granularity - 1);
+
+ /* Top device aligned on logical block boundary? */
+ if (t->alignment_offset & (t->logical_block_size - 1)) {
+ t->misaligned = 1;
+ ret = -1;
+ }
+
+ /* Find lcm() of optimal I/O size and granularity */
+ t->io_opt = lcm(t->io_opt, b->io_opt);
+ t->discard_granularity = lcm(t->discard_granularity,
+ b->discard_granularity);
+
+ /* Verify that optimal I/O size is a multiple of io_min */
+ if (t->io_min && t->io_opt % t->io_min)
+ ret = -1;
+
+ return ret;
+}
+EXPORT_SYMBOL(blk_stack_limits);
+
+/**
+ * disk_stack_limits - adjust queue limits for stacked drivers
+ * @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.
+ */
+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) {
+ char top[BDEVNAME_SIZE], bottom[BDEVNAME_SIZE];
+
+ disk_name(disk, 0, top);
+ bdevname(bdev, bottom);
+
+ printk(KERN_NOTICE "%s: Warning: Device %s is misaligned\n",
+ top, bottom);
+ }
if (!t->queue_lock)
WARN_ON_ONCE(1);
else if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags)) {
unsigned long flags;
+
spin_lock_irqsave(t->queue_lock, flags);
- queue_flag_clear(QUEUE_FLAG_CLUSTER, t);
+ if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags))
+ queue_flag_clear(QUEUE_FLAG_CLUSTER, t);
spin_unlock_irqrestore(t->queue_lock, flags);
}
}
-EXPORT_SYMBOL(blk_queue_stack_limits);
+EXPORT_SYMBOL(disk_stack_limits);
/**
* blk_queue_dma_pad - set pad mask
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff