From c15227de132f1295f3db6b7df9079956b1020fd8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 30 Sep 2009 13:52:12 +0200 Subject: block: use normal I/O path for discard requests prepare_discard_fn() was being called in a place where memory allocation was effectively impossible. This makes it inappropriate for all but the most trivial translations of Linux's DISCARD operation to the block command set. Additionally adding a payload there makes the ownership of the bio backing unclear as it's now allocated by the device driver and not the submitter as usual. It is replaced with QUEUE_FLAG_DISCARD which is used to indicate whether the queue supports discard operations or not. blkdev_issue_discard now allocates a one-page, sector-length payload which is the right thing for the common ATA and SCSI implementations. The mtd implementation of prepare_discard_fn() is replaced with simply checking for the request being a discard. Largely based on a previous patch from Matthew Wilcox which did the prepare_discard_fn but not the different payload allocation yet. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e23a86cae5ac..f62d45e87618 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -82,7 +82,6 @@ enum rq_cmd_type_bits { enum { REQ_LB_OP_EJECT = 0x40, /* eject request */ REQ_LB_OP_FLUSH = 0x41, /* flush request */ - REQ_LB_OP_DISCARD = 0x42, /* discard sectors */ }; /* @@ -261,7 +260,6 @@ typedef void (request_fn_proc) (struct request_queue *q); typedef int (make_request_fn) (struct request_queue *q, struct bio *bio); typedef int (prep_rq_fn) (struct request_queue *, struct request *); typedef void (unplug_fn) (struct request_queue *); -typedef int (prepare_discard_fn) (struct request_queue *, struct request *); struct bio_vec; struct bvec_merge_data { @@ -340,7 +338,6 @@ struct request_queue make_request_fn *make_request_fn; prep_rq_fn *prep_rq_fn; unplug_fn *unplug_fn; - prepare_discard_fn *prepare_discard_fn; merge_bvec_fn *merge_bvec_fn; prepare_flush_fn *prepare_flush_fn; softirq_done_fn *softirq_done_fn; @@ -460,6 +457,7 @@ struct request_queue #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ #define QUEUE_FLAG_IO_STAT 15 /* do IO stats */ #define QUEUE_FLAG_CQ 16 /* hardware does queuing */ +#define QUEUE_FLAG_DISCARD 17 /* supports DISCARD */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_CLUSTER) | \ @@ -591,6 +589,7 @@ enum { #define blk_queue_flushing(q) ((q)->ordseq) #define blk_queue_stackable(q) \ test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags) +#define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) #define blk_fs_request(rq) ((rq)->cmd_type == REQ_TYPE_FS) #define blk_pc_request(rq) ((rq)->cmd_type == REQ_TYPE_BLOCK_PC) @@ -955,7 +954,6 @@ extern void blk_queue_merge_bvec(struct request_queue *, merge_bvec_fn *); extern void blk_queue_dma_alignment(struct request_queue *, int); extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *); -extern void blk_queue_set_discard(struct request_queue *, prepare_discard_fn *); extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); -- cgit v1.2.3 From 67efc9258010da35b27b3854d0880c7e193004ed Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 30 Sep 2009 13:54:20 +0200 Subject: block: allow large discard requests Currently we set the bio size to the byte equivalent of the blocks to be trimmed when submitting the initial DISCARD ioctl. That means it is subject to the max_hw_sectors limitation of the HBA which is much lower than the size of a DISCARD request we can support. Add a separate max_discard_sectors tunable to limit the size for discard requests. We limit the max discard request size in bytes to 32bit as that is the limit for bio->bi_size. This could be much larger if we had a way to pass that information through the block layer. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f62d45e87618..1a03b715dfad 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -311,6 +311,7 @@ struct queue_limits { unsigned int alignment_offset; unsigned int io_min; unsigned int io_opt; + unsigned int max_discard_sectors; unsigned short logical_block_size; unsigned short max_hw_segments; @@ -928,6 +929,8 @@ extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_phys_segments(struct request_queue *, unsigned short); extern void blk_queue_max_hw_segments(struct request_queue *, unsigned short); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); +extern void blk_queue_max_discard_sectors(struct request_queue *q, + unsigned int max_discard_sectors); 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, -- cgit v1.2.3 From 8e2967555571659d2c8a70dd120710110ed7bba4 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 3 Oct 2009 16:26:03 +0200 Subject: cfq-iosched: implement slower async initiate and queue ramp up This slowly ramps up the async queue depth based on the time passed since the sync IO, and doesn't allow async at all until a sync slice period has passed. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1a03b715dfad..a7323930d2ba 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1147,7 +1147,11 @@ static inline void put_dev_sector(Sector p) } struct work_struct; +struct delayed_work; int kblockd_schedule_work(struct request_queue *q, struct work_struct *work); +int kblockd_schedule_delayed_work(struct request_queue *q, + struct delayed_work *work, + unsigned long delay); #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) -- cgit v1.2.3 From ac481c20ef8f6c6f2be75d581863f40c43874ef7 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Sat, 3 Oct 2009 20:52:01 +0200 Subject: block: Topology ioctls Not all users of the topology information want to use libblkid. Provide the topology information through bdev ioctls. Also clarify sector size comments for existing BLK ioctls. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 35 ++++++++++++++++++++++++++++++----- 1 file changed, 30 insertions(+), 5 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a7323930d2ba..25119041e034 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1081,25 +1081,37 @@ static inline unsigned int queue_physical_block_size(struct request_queue *q) return q->limits.physical_block_size; } +static inline int bdev_physical_block_size(struct block_device *bdev) +{ + return queue_physical_block_size(bdev_get_queue(bdev)); +} + static inline unsigned int queue_io_min(struct request_queue *q) { return q->limits.io_min; } +static inline int bdev_io_min(struct block_device *bdev) +{ + return queue_io_min(bdev_get_queue(bdev)); +} + static inline unsigned int queue_io_opt(struct request_queue *q) { return q->limits.io_opt; } +static inline int bdev_io_opt(struct block_device *bdev) +{ + return queue_io_opt(bdev_get_queue(bdev)); +} + static inline int queue_alignment_offset(struct request_queue *q) { - if (q && q->limits.misaligned) + if (q->limits.misaligned) return -1; - if (q && q->limits.alignment_offset) - return q->limits.alignment_offset; - - return 0; + return q->limits.alignment_offset; } static inline int queue_sector_alignment_offset(struct request_queue *q, @@ -1109,6 +1121,19 @@ static inline int queue_sector_alignment_offset(struct request_queue *q, & (q->limits.io_min - 1); } +static inline int bdev_alignment_offset(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (q->limits.misaligned) + return -1; + + if (bdev != bdev->bd_contains) + return bdev->bd_part->alignment_offset; + + return q->limits.alignment_offset; +} + static inline int queue_dma_alignment(struct request_queue *q) { return q ? q->dma_alignment : 511; -- cgit v1.2.3 From 23e018a1b083ecb4b8bb2fb43d58e7c19b5d7959 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 5 Oct 2009 08:52:35 +0200 Subject: block: get rid of kblock_schedule_delayed_work() It was briefly introduced to allow CFQ to to delayed scheduling, but we ended up removing that feature again. So lets kill the function and export, and just switch CFQ back to the normal work schedule since it is now passing in a '0' delay from all call sites. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 25119041e034..221cecd86bd3 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1172,11 +1172,7 @@ static inline void put_dev_sector(Sector p) } struct work_struct; -struct delayed_work; int kblockd_schedule_work(struct request_queue *q, struct work_struct *work); -int kblockd_schedule_delayed_work(struct request_queue *q, - struct delayed_work *work, - unsigned long delay); #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) -- cgit v1.2.3 From b9d128f1088ea5245109dfc9bbceb128b6371a77 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 29 Oct 2009 13:59:26 +0100 Subject: block: move bdi/address_space unplug functions to backing-dev.h There's nothing block related about them, the backing device is used by things like NFS etc as well. This gets rid of the need to protect such calls by CONFIG_BLOCK. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 221cecd86bd3..39c601f783a0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -823,19 +823,6 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev) return bdev->bd_disk->queue; } -static inline void blk_run_backing_dev(struct backing_dev_info *bdi, - struct page *page) -{ - if (bdi && bdi->unplug_io_fn) - bdi->unplug_io_fn(bdi, page); -} - -static inline void blk_run_address_space(struct address_space *mapping) -{ - if (mapping) - blk_run_backing_dev(mapping->backing_dev_info, NULL); -} - /* * blk_rq_pos() : the current sector * blk_rq_bytes() : bytes left in the entire request -- cgit v1.2.3 From 86b37281411cf1e9bc0a6b5406c45edb7bd9ea5d Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Tue, 10 Nov 2009 11:50:21 +0100 Subject: block: Expose discard granularity While SSDs track block usage on a per-sector basis, RAID arrays often have allocation blocks that are bigger. Allow the discard granularity and alignment to be set and teach the topology stacking logic how to handle them. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 39c601f783a0..1cc02972fbe2 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -312,12 +312,15 @@ struct queue_limits { unsigned int io_min; unsigned int io_opt; unsigned int max_discard_sectors; + unsigned int discard_granularity; + unsigned int discard_alignment; unsigned short logical_block_size; unsigned short max_hw_segments; unsigned short max_phys_segments; unsigned char misaligned; + unsigned char discard_misaligned; unsigned char no_cluster; }; @@ -1121,6 +1124,21 @@ static inline int bdev_alignment_offset(struct block_device *bdev) return q->limits.alignment_offset; } +static inline int queue_discard_alignment(struct request_queue *q) +{ + if (q->limits.discard_misaligned) + return -1; + + return q->limits.discard_alignment; +} + +static inline int queue_sector_discard_alignment(struct request_queue *q, + sector_t sector) +{ + return ((sector << 9) - q->limits.discard_alignment) + & (q->limits.discard_granularity - 1); +} + static inline int queue_dma_alignment(struct request_queue *q) { return q ? q->dma_alignment : 511; -- cgit v1.2.3 From 2d4dc890b5c8fabd818a8586607e6843c4375e62 Mon Sep 17 00:00:00 2001 From: Ilya Loginov Date: Thu, 26 Nov 2009 09:16:19 +0100 Subject: block: add helpers to run flush_dcache_page() against a bio and a request's pages Mtdblock driver doesn't call flush_dcache_page for pages in request. So, this causes problems on architectures where the icache doesn't fill from the dcache or with dcache aliases. The patch fixes this. The ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE symbol was introduced to avoid pointless empty cache-thrashing loops on architectures for which flush_dcache_page() is a no-op. Every architecture was provided with this flush pages on architectires where ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE is equal 1 or do nothing otherwise. See "fix mtd_blkdevs problem with caches on some architectures" discussion on LKML for more information. Signed-off-by: Ilya Loginov Cc: Ingo Molnar Cc: David Woodhouse Cc: Peter Horton Cc: "Ed L. Cashin" Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1cc02972fbe2..e727f6c44c44 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -752,6 +752,17 @@ struct req_iterator { #define rq_iter_last(rq, _iter) \ (_iter.bio->bi_next == NULL && _iter.i == _iter.bio->bi_vcnt-1) +#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +# error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform" +#endif +#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +extern void rq_flush_dcache_pages(struct request *rq); +#else +static inline void rq_flush_dcache_pages(struct request *rq) +{ +} +#endif + extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); extern void register_disk(struct gendisk *dev); -- cgit v1.2.3 From 98262f2762f0067375f83824d81ea929e37e6bfe Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Thu, 3 Dec 2009 09:24:48 +0100 Subject: block: Allow devices to indicate whether discarded blocks are zeroed The discard ioctl is used by mkfs utilities to clear a block device prior to putting metadata down. However, not all devices return zeroed blocks after a discard. Some drives return stale data, potentially containing old superblocks. It is therefore important to know whether discarded blocks are properly zeroed. Both ATA and SCSI drives have configuration bits that indicate whether zeroes are returned after a discard operation. Implement a block level interface that allows this information to be bubbled up the stack and queried via a new block device ioctl. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e727f6c44c44..784a919aa0d0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -322,6 +322,7 @@ struct queue_limits { unsigned char misaligned; unsigned char discard_misaligned; unsigned char no_cluster; + signed char discard_zeroes_data; }; struct request_queue @@ -1150,6 +1151,19 @@ static inline int queue_sector_discard_alignment(struct request_queue *q, & (q->limits.discard_granularity - 1); } +static inline unsigned int queue_discard_zeroes_data(struct request_queue *q) +{ + if (q->limits.discard_zeroes_data == 1) + return 1; + + return 0; +} + +static inline unsigned int bdev_discard_zeroes_data(struct block_device *bdev) +{ + return queue_discard_zeroes_data(bdev_get_queue(bdev)); +} + static inline int queue_dma_alignment(struct request_queue *q) { return q ? q->dma_alignment : 511; -- cgit v1.2.3 From 81744ee44ab2845c16ffd7d6f762f7b4a49a4750 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Tue, 29 Dec 2009 08:35:35 +0100 Subject: block: Fix incorrect alignment offset reporting and update documentation queue_sector_alignment_offset returned the wrong value which caused partitions to report an incorrect alignment_offset. Since offset alignment calculation is needed several places it has been split into a separate helper function. The topology stacking function has been updated accordingly. Furthermore, comments have been added to clarify how the stacking function works. Signed-off-by: Martin K. Petersen Tested-by: Mike Snitzer Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 784a919aa0d0..59b832be3044 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1116,11 +1116,18 @@ static inline int queue_alignment_offset(struct request_queue *q) return q->limits.alignment_offset; } +static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t offset) +{ + unsigned int granularity = max(lim->physical_block_size, lim->io_min); + + offset &= granularity - 1; + return (granularity + lim->alignment_offset - offset) & (granularity - 1); +} + static inline int queue_sector_alignment_offset(struct request_queue *q, sector_t sector) { - return ((sector << 9) - q->limits.alignment_offset) - & (q->limits.io_min - 1); + return queue_limit_alignment_offset(&q->limits, sector << 9); } static inline int bdev_alignment_offset(struct block_device *bdev) -- cgit v1.2.3 From 9bd3f98821a83041e77ee25158b80b535d02d7b4 Mon Sep 17 00:00:00 2001 From: Gui Jianfeng Date: Wed, 30 Dec 2009 08:41:07 +0100 Subject: block: blk_rq_err_sectors cleanup blk_rq_err_sectors() seems useless, get rid of it. Signed-off-by: Gui Jianfeng Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 59b832be3044..9b98173a8184 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -845,7 +845,6 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev) * blk_rq_err_bytes() : bytes left till the next error boundary * blk_rq_sectors() : sectors left in the entire request * blk_rq_cur_sectors() : sectors left in the current segment - * blk_rq_err_sectors() : sectors left till the next error boundary */ static inline sector_t blk_rq_pos(const struct request *rq) { @@ -874,11 +873,6 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq) return blk_rq_cur_bytes(rq) >> 9; } -static inline unsigned int blk_rq_err_sectors(const struct request *rq) -{ - return blk_rq_err_bytes(rq) >> 9; -} - /* * Request issue related functions. */ -- cgit v1.2.3