From ff9ea323816dc1c8ac7144afd4eab3ac97704430 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 8 Sep 2014 08:03:56 +0900 Subject: block, bdi: an active gendisk always has a request_queue associated with it bdev_get_queue() returns the request_queue associated with the specified block_device. blk_get_backing_dev_info() makes use of bdev_get_queue() to determine the associated bdi given a block_device. All the callers of bdev_get_queue() including blk_get_backing_dev_info() assume that bdev_get_queue() may return NULL and implement NULL handling; however, bdev_get_queue() requires the passed in block_device is opened and attached to its gendisk. Because an active gendisk always has a valid request_queue associated with it, bdev_get_queue() can never return NULL and neither can blk_get_backing_dev_info(). Make it clear that neither of the two functions can return NULL and remove NULL handling from all the callers. Signed-off-by: Tejun Heo Cc: Chris Mason Cc: Dave Chinner Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 518b46555b80..e267bf0db559 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -865,7 +865,7 @@ extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *, static inline struct request_queue *bdev_get_queue(struct block_device *bdev) { - return bdev->bd_disk->queue; + return bdev->bd_disk->queue; /* this is never NULL */ } /* -- cgit v1.2.3 From 7c94e1c157a227837b04f02f5edeff8301410ba2 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 25 Sep 2014 23:23:43 +0800 Subject: block: introduce blk_flush_queue to drive flush machinery This patch introduces 'struct blk_flush_queue' and puts all flush machinery related fields into this structure, so that - flush implementation details aren't exposed to driver - it is easy to convert to per dispatch-queue flush machinery This patch is basically a mechanical replacement. Reviewed-by: Christoph Hellwig Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e267bf0db559..49f3461e4272 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -36,6 +36,7 @@ struct request; struct sg_io_hdr; struct bsg_job; struct blkcg_gq; +struct blk_flush_queue; #define BLKDEV_MIN_RQ 4 #define BLKDEV_MAX_RQ 128 /* Default maximum */ @@ -455,14 +456,7 @@ struct request_queue { */ unsigned int flush_flags; unsigned int flush_not_queueable:1; - unsigned int flush_queue_delayed:1; - unsigned int flush_pending_idx:1; - unsigned int flush_running_idx:1; - unsigned long flush_pending_since; - struct list_head flush_queue[2]; - struct list_head flush_data_in_flight; - struct request *flush_rq; - spinlock_t mq_flush_lock; + struct blk_flush_queue *fq; struct list_head requeue_list; spinlock_t requeue_lock; -- cgit v1.2.3 From 180b2f95dd331010a9930a65c8a18d6d81b94dc1 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 26 Sep 2014 19:19:56 -0400 Subject: block: Replace bi_integrity with bi_special For commands like REQ_COPY we need a way to pass extra information along with each bio. Like integrity metadata this information must be available at the bottom of the stack so bi_private does not suffice. Rename the existing bi_integrity field to bi_special and make it a union so we can have different bio extensions for each class of command. We previously used bi_integrity != NULL as a way to identify whether a bio had integrity metadata or not. Introduce a REQ_INTEGRITY to be the indicator now that bi_special can contain different things. In addition, bio_integrity(bio) will now return a pointer to the integrity payload (when applicable). Signed-off-by: Martin K. Petersen Reviewed-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 49f3461e4272..7fcb2caef559 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1514,12 +1514,9 @@ static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) return disk->integrity; } -static inline int blk_integrity_rq(struct request *rq) +static inline bool blk_integrity_rq(struct request *rq) { - if (rq->bio == NULL) - return 0; - - return bio_integrity(rq->bio); + return rq->cmd_flags & REQ_INTEGRITY; } static inline void blk_queue_max_integrity_segments(struct request_queue *q, -- cgit v1.2.3 From 8492b68bc4025e7bce1d57761bd7c047efda2f81 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 26 Sep 2014 19:19:57 -0400 Subject: block: Remove integrity tagging functions None of the filesystems appear interested in using the integrity tagging feature. Potentially because very few storage devices actually permit using the application tag space. Remove the tagging functions. Signed-off-by: Martin K. Petersen Reviewed-by: Christoph Hellwig Reviewed-by: Sagi Grimberg 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 7fcb2caef559..0bf5d79d9ba0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1472,14 +1472,10 @@ struct blk_integrity_exchg { typedef void (integrity_gen_fn) (struct blk_integrity_exchg *); typedef int (integrity_vrfy_fn) (struct blk_integrity_exchg *); -typedef void (integrity_set_tag_fn) (void *, void *, unsigned int); -typedef void (integrity_get_tag_fn) (void *, void *, unsigned int); struct blk_integrity { integrity_gen_fn *generate_fn; integrity_vrfy_fn *verify_fn; - integrity_set_tag_fn *set_tag_fn; - integrity_get_tag_fn *get_tag_fn; unsigned short flags; unsigned short tuple_size; -- cgit v1.2.3 From 3be91c4a3d090bd700bd6ee5bf457c1bbf189a4f Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 26 Sep 2014 19:19:59 -0400 Subject: block: Deprecate the use of the term sector in the context of block integrity The protection interval is not necessarily tied to the logical block size of a block device. Stop using the terms "sector" and "sectors". Going forward we will use the term "seed" to describe the initial reference tag value for a given I/O. "Interval" will be used to describe the portion of the data buffer that a given piece of protection information is associated with. Signed-off-by: Martin K. Petersen Reviewed-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0bf5d79d9ba0..d364c42dbf17 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1464,9 +1464,9 @@ static inline uint64_t rq_io_start_time_ns(struct request *req) struct blk_integrity_exchg { void *prot_buf; void *data_buf; - sector_t sector; + sector_t seed; unsigned int data_size; - unsigned short sector_size; + unsigned short interval; const char *disk_name; }; @@ -1479,7 +1479,7 @@ struct blk_integrity { unsigned short flags; unsigned short tuple_size; - unsigned short sector_size; + unsigned short interval; unsigned short tag_size; const char *name; -- cgit v1.2.3 From 1859308853b19c4daf4afaab910d3d52ac1ec2ff Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 26 Sep 2014 19:20:01 -0400 Subject: block: Clean up the code used to generate and verify integrity metadata Instead of the "operate" parameter we pass in a seed value and a pointer to a function that can be used to process the integrity metadata. The generation function is changed to have a return value to fit into this scheme. Signed-off-by: Martin K. Petersen Reviewed-by: Sagi Grimberg Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d364c42dbf17..24c1e055b8a7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1461,7 +1461,7 @@ static inline uint64_t rq_io_start_time_ns(struct request *req) #define INTEGRITY_FLAG_READ 2 /* verify data integrity on read */ #define INTEGRITY_FLAG_WRITE 4 /* generate data integrity on write */ -struct blk_integrity_exchg { +struct blk_integrity_iter { void *prot_buf; void *data_buf; sector_t seed; @@ -1470,12 +1470,11 @@ struct blk_integrity_exchg { const char *disk_name; }; -typedef void (integrity_gen_fn) (struct blk_integrity_exchg *); -typedef int (integrity_vrfy_fn) (struct blk_integrity_exchg *); +typedef int (integrity_processing_fn) (struct blk_integrity_iter *); struct blk_integrity { - integrity_gen_fn *generate_fn; - integrity_vrfy_fn *verify_fn; + integrity_processing_fn *generate_fn; + integrity_processing_fn *verify_fn; unsigned short flags; unsigned short tuple_size; -- cgit v1.2.3 From 8288f496eb1b1905c425e92eaf1abbb29119217b Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 26 Sep 2014 19:20:02 -0400 Subject: block: Add prefix to block integrity profile flags Add a BLK_ prefix to the integrity profile flags. Also rename the flags to be more consistent with the generate/verify terminology in the rest of the integrity code. Signed-off-by: Martin K. Petersen Reviewed-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 24c1e055b8a7..cf92eb031ae9 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1458,8 +1458,10 @@ static inline uint64_t rq_io_start_time_ns(struct request *req) #if defined(CONFIG_BLK_DEV_INTEGRITY) -#define INTEGRITY_FLAG_READ 2 /* verify data integrity on read */ -#define INTEGRITY_FLAG_WRITE 4 /* generate data integrity on write */ +enum blk_integrity_flags { + BLK_INTEGRITY_VERIFY = 1 << 0, + BLK_INTEGRITY_GENERATE = 1 << 1, +}; struct blk_integrity_iter { void *prot_buf; -- cgit v1.2.3 From 3aec2f41a8baeb70aa77556a4e4dcec7d9d70b4d Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 26 Sep 2014 19:20:03 -0400 Subject: block: Add a disk flag to block integrity profile So far we have relied on the app tag size to determine whether a disk has been formatted with T10 protection information or not. However, not all target devices provide application tag storage. Add a flag to the block integrity profile that indicates whether the disk has been formatted with protection information. Signed-off-by: Martin K. Petersen Reviewed-by: Sagi Grimberg Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index cf92eb031ae9..4600fc63e3fc 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1461,6 +1461,7 @@ static inline uint64_t rq_io_start_time_ns(struct request *req) enum blk_integrity_flags { BLK_INTEGRITY_VERIFY = 1 << 0, BLK_INTEGRITY_GENERATE = 1 << 1, + BLK_INTEGRITY_DEVICE_CAPABLE = 1 << 2, }; struct blk_integrity_iter { -- cgit v1.2.3 From aae7df50190a640e51bfe11c93f94741ac82ff0b Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 26 Sep 2014 19:20:05 -0400 Subject: block: Integrity checksum flag Make the choice of checksum a per-I/O property by introducing a flag that can be inspected by the SCSI layer. There are several reasons for this: 1. It allows us to switch choice of checksum without unloading and reloading the HBA driver. 2. During error recovery we need to be able to tell the HBA that checksums read from disk should not be verified and converted to IP checksums. 3. For error injection purposes we need to be able to write a bad guard tag to storage. Since the storage device only supports T10 CRC we need to be able to disable IP checksum conversion on the HBA. Signed-off-by: Martin K. Petersen Reviewed-by: Sagi Grimberg Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4600fc63e3fc..773df190a4ee 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1462,6 +1462,7 @@ enum blk_integrity_flags { BLK_INTEGRITY_VERIFY = 1 << 0, BLK_INTEGRITY_GENERATE = 1 << 1, BLK_INTEGRITY_DEVICE_CAPABLE = 1 << 2, + BLK_INTEGRITY_IP_CHECKSUM = 1 << 3, }; struct blk_integrity_iter { -- cgit v1.2.3 From 4eaf99beadcefbf126fa05e66fb40fca999e09fd Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 26 Sep 2014 19:20:06 -0400 Subject: block: Don't merge requests if integrity flags differ We'd occasionally merge requests with conflicting integrity flags. Introduce a merge helper which checks that the requests have compatible integrity payloads. Signed-off-by: Martin K. Petersen Reviewed-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 773df190a4ee..038b40f84c7a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1497,10 +1497,10 @@ extern int blk_integrity_compare(struct gendisk *, struct gendisk *); extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *, struct scatterlist *); extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); -extern int blk_integrity_merge_rq(struct request_queue *, struct request *, - struct request *); -extern int blk_integrity_merge_bio(struct request_queue *, struct request *, - struct bio *); +extern bool blk_integrity_merge_rq(struct request_queue *, struct request *, + struct request *); +extern bool blk_integrity_merge_bio(struct request_queue *, struct request *, + struct bio *); static inline struct blk_integrity *bdev_get_integrity(struct block_device *bdev) @@ -1580,15 +1580,15 @@ static inline unsigned short queue_max_integrity_segments(struct request_queue * { return 0; } -static inline int blk_integrity_merge_rq(struct request_queue *rq, - struct request *r1, - struct request *r2) +static inline bool blk_integrity_merge_rq(struct request_queue *rq, + struct request *r1, + struct request *r2) { return 0; } -static inline int blk_integrity_merge_bio(struct request_queue *rq, - struct request *r, - struct bio *b) +static inline bool blk_integrity_merge_bio(struct request_queue *rq, + struct request *r, + struct bio *b) { return 0; } -- cgit v1.2.3 From b8839b8c55f3fdd60dc36abcda7e0266aff7985c Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 8 Oct 2014 18:26:13 -0400 Subject: block: fix alignment_offset math that assumes io_min is a power-of-2 The math in both blk_stack_limits() and queue_limit_alignment_offset() assume that a block device's io_min (aka minimum_io_size) is always a power-of-2. Fix the math such that it works for non-power-of-2 io_min. This issue (of alignment_offset != 0) became apparent when testing dm-thinp with a thinp blocksize that matches a RAID6 stripesize of 1280K. Commit fdfb4c8c1 ("dm thin: set minimum_io_size to pool's data block size") unlocked the potential for alignment_offset != 0 due to the dm-thin-pool's io_min possibly being a non-power-of-2. Signed-off-by: Mike Snitzer Cc: stable@vger.kernel.org Acked-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 038b40f84c7a..554639249fd6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1279,10 +1279,9 @@ static inline int queue_alignment_offset(struct request_queue *q) static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector) { unsigned int granularity = max(lim->physical_block_size, lim->io_min); - unsigned int alignment = (sector << 9) & (granularity - 1); + unsigned int alignment = sector_div(sector, granularity >> 9) << 9; - return (granularity + lim->alignment_offset - alignment) - & (granularity - 1); + return (granularity + lim->alignment_offset - alignment) % granularity; } static inline int bdev_alignment_offset(struct block_device *bdev) -- cgit v1.2.3