X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=block%2Fblk-settings.c;h=127f825518553de44daada07d7b7aa2624171500;hb=fe0b393f2c0a0d23a9bc9ed7dc51a1ee511098bd;hp=b21dcdb64151abd31a5cc66ff11db955b0e90a80;hpb=ef9e3facdf1fe1228721a7c295a76d1b7a0e57ec;p=safe%2Fjmp%2Flinux-2.6 diff --git a/block/blk-settings.c b/block/blk-settings.c index b21dcdb..127f825 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -7,6 +7,8 @@ #include #include #include /* for max_pfn/max_low_pfn */ +#include +#include #include "blk.h" @@ -33,23 +35,6 @@ void blk_queue_prep_rq(struct request_queue *q, prep_rq_fn *pfn) 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 @@ -96,6 +81,37 @@ void blk_queue_lld_busy(struct request_queue *q, lld_busy_fn *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 @@ -123,29 +139,30 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn) * 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); + 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_hardsect_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; - INIT_WORK(&q->unplug_work, blk_unplug_work); - 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 */ @@ -155,37 +172,39 @@ EXPORT_SYMBOL(blk_queue_make_request); /** * blk_queue_bounce_limit - set bounce buffer limit for queue - * @q: the request queue for the device - * @dma_addr: bus address limit + * @q: the request queue for the device + * @dma_mask: the maximum address the device can handle * * Description: * Different hardware can have different requirements as to what pages * it can do I/O directly to. A low level driver can call * blk_queue_bounce_limit to have lower memory pages allocated as bounce - * buffers for doing I/O to pages residing above @dma_addr. + * buffers for doing I/O to pages residing above @dma_mask. **/ -void blk_queue_bounce_limit(struct request_queue *q, u64 dma_addr) +void blk_queue_bounce_limit(struct request_queue *q, u64 dma_mask) { - unsigned long b_pfn = dma_addr >> PAGE_SHIFT; + unsigned long b_pfn = dma_mask >> PAGE_SHIFT; int dma = 0; q->bounce_gfp = GFP_NOIO; #if BITS_PER_LONG == 64 - /* Assume anything <= 4GB can be handled by IOMMU. - Actually some IOMMUs can handle everything, but I don't - know of a way to test this here. */ - if (b_pfn < (min_t(u64, 0x100000000UL, BLK_BOUNCE_HIGH) >> PAGE_SHIFT)) + /* + * Assume anything <= 4GB can be handled by IOMMU. Actually + * some IOMMUs can handle everything, but I don't know of a + * way to test this here. + */ + if (b_pfn < (min_t(u64, 0xffffffffUL, BLK_BOUNCE_HIGH) >> PAGE_SHIFT)) dma = 1; - q->bounce_pfn = max_low_pfn; + q->limits.bounce_pfn = max_low_pfn; #else if (b_pfn < blk_max_low_pfn) dma = 1; - q->bounce_pfn = b_pfn; + q->limits.bounce_pfn = b_pfn; #endif if (dma) { init_emergency_isa_pool(); q->bounce_gfp = GFP_NOIO | GFP_DMA; - q->bounce_pfn = b_pfn; + q->limits.bounce_pfn = b_pfn; } } EXPORT_SYMBOL(blk_queue_bounce_limit); @@ -208,14 +227,35 @@ void blk_queue_max_sectors(struct request_queue *q, unsigned int max_sectors) } if (BLK_DEF_MAX_SECTORS > max_sectors) - q->max_hw_sectors = q->max_sectors = max_sectors; + q->limits.max_hw_sectors = q->limits.max_sectors = max_sectors; else { - q->max_sectors = BLK_DEF_MAX_SECTORS; - q->max_hw_sectors = max_sectors; + q->limits.max_sectors = BLK_DEF_MAX_SECTORS; + q->limits.max_hw_sectors = max_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; +} +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 @@ -235,7 +275,7 @@ void blk_queue_max_phys_segments(struct request_queue *q, __func__, max_segments); } - q->max_phys_segments = max_segments; + q->limits.max_phys_segments = max_segments; } EXPORT_SYMBOL(blk_queue_max_phys_segments); @@ -259,7 +299,7 @@ void blk_queue_max_hw_segments(struct request_queue *q, __func__, max_segments); } - q->max_hw_segments = max_segments; + q->limits.max_hw_segments = max_segments; } EXPORT_SYMBOL(blk_queue_max_hw_segments); @@ -280,26 +320,153 @@ void blk_queue_max_segment_size(struct request_queue *q, unsigned int max_size) __func__, max_size); } - q->max_segment_size = max_size; + q->limits.max_segment_size = max_size; } EXPORT_SYMBOL(blk_queue_max_segment_size); /** - * blk_queue_hardsect_size - set hardware sector size for the queue + * blk_queue_logical_block_size - set logical block size for the queue * @q: the request queue for the device - * @size: the hardware sector size, in bytes + * @size: the logical block size, in bytes * * Description: - * This should typically be set to the lowest possible sector size - * that the hardware can operate on (possible without reverting to - * even internal read-modify-write operations). Usually the default - * of 512 covers most hardware. + * This should be set to the lowest possible block size that the + * storage device can address. The default of 512 covers most + * hardware. **/ -void blk_queue_hardsect_size(struct request_queue *q, unsigned short size) +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) { - q->hardsect_size = size; + blk_limits_io_opt(&q->limits, opt); } -EXPORT_SYMBOL(blk_queue_hardsect_size); +EXPORT_SYMBOL(blk_queue_io_opt); /* * Returns the minimum that is _not_ zero, unless both are zero. @@ -313,14 +480,8 @@ EXPORT_SYMBOL(blk_queue_hardsect_size); **/ void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b) { - /* zero is "infinity" */ - 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); + blk_stack_limits(&t->limits, &b->limits, 0); - t->max_phys_segments = min(t->max_phys_segments, b->max_phys_segments); - t->max_hw_segments = min(t->max_hw_segments, b->max_hw_segments); - t->max_segment_size = min(t->max_segment_size, b->max_segment_size); - t->hardsect_size = max(t->hardsect_size, b->hardsect_size); if (!t->queue_lock) WARN_ON_ONCE(1); else if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags)) { @@ -332,6 +493,194 @@ void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b) } 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; + + return a; +} + +/** + * blk_stack_limits - adjust queue_limits for stacked devices + * @t: the stacking driver limits (top device) + * @b: the underlying queue limits (bottom, component device) + * @offset: offset to beginning of data within component device + * + * Description: + * 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 alignment; + unsigned int top, bottom, 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_segment_size = min_not_zero(t->max_segment_size, + b->max_segment_size); + + t->misaligned |= b->misaligned; + + alignment = queue_limit_alignment_offset(b, offset); + + /* 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); + + t->physical_block_size = max(t->physical_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; + } + + /* 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; + ret = -1; + } + + /* Find lowest common alignment_offset */ + t->alignment_offset = lcm(t->alignment_offset, alignment) + & (max(t->physical_block_size, t->io_min) - 1); + + /* Verify that new alignment_offset is on a logical block boundary */ + if (t->alignment_offset & (t->logical_block_size - 1)) { + t->misaligned = 1; + ret = -1; + } + + /* Discard alignment and granularity */ + if (b->discard_granularity) { + unsigned int granularity = b->discard_granularity; + offset &= granularity - 1; + + alignment = (granularity + b->discard_alignment - offset) + & (granularity - 1); + + 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); + +/** + * 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); + 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(disk_stack_limits); + /** * blk_queue_dma_pad - set pad mask * @q: the request queue for the device @@ -392,11 +741,11 @@ int blk_queue_dma_drain(struct request_queue *q, dma_drain_needed_fn *dma_drain_needed, void *buf, unsigned int size) { - if (q->max_hw_segments < 2 || q->max_phys_segments < 2) + if (queue_max_hw_segments(q) < 2 || queue_max_phys_segments(q) < 2) return -EINVAL; /* make room for appending the drain */ - --q->max_hw_segments; - --q->max_phys_segments; + blk_queue_max_hw_segments(q, queue_max_hw_segments(q) - 1); + blk_queue_max_phys_segments(q, queue_max_phys_segments(q) - 1); q->dma_drain_needed = dma_drain_needed; q->dma_drain_buffer = buf; q->dma_drain_size = size; @@ -418,7 +767,7 @@ void blk_queue_segment_boundary(struct request_queue *q, unsigned long mask) __func__, mask); } - q->seg_boundary_mask = mask; + q->limits.seg_boundary_mask = mask; } EXPORT_SYMBOL(blk_queue_segment_boundary); @@ -429,7 +778,7 @@ EXPORT_SYMBOL(blk_queue_segment_boundary); * * description: * set required memory and length alignment for direct dma transactions. - * this is used when buiding direct io requests for the queue. + * this is used when building direct io requests for the queue. * **/ void blk_queue_dma_alignment(struct request_queue *q, int mask)