From 01c5f85aebaaddfd7e6051fb2ec80c1d4b463554 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 11 Sep 2018 10:59:53 -0600 Subject: blk-cgroup: increase number of supported policies After merging the iolatency policy, we potentially now have 4 policies being registered, but only support 3. This causes one of them to fail loading. Takashi reports that BFQ no longer works for him, because it fails to load due to policy registration failure. Bump to 5 policies, and also add a warning for when we have exceeded the global amount. If we have to touch this again, we should switch to a dynamic scheme instead. Reported-by: Takashi Iwai Reviewed-by: Jeff Moyer Tested-by: Takashi Iwai 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 d6869e0e2b64..6980014357d4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -54,7 +54,7 @@ struct blk_stat_callback; * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. */ -#define BLKCG_MAX_POLS 3 +#define BLKCG_MAX_POLS 5 typedef void (rq_end_io_fn)(struct request *, blk_status_t); -- cgit v1.2.3 From 43b729bfe9cf30ad11499a66e3b7bd300c716d44 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Sep 2018 09:43:47 +0200 Subject: block: move integrity_req_gap_{back,front}_merge to blk.h No need to expose these to drivers. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 31 ------------------------------- 1 file changed, 31 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d6869e0e2b64..bc534c857344 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1843,26 +1843,6 @@ queue_max_integrity_segments(struct request_queue *q) return q->limits.max_integrity_segments; } -static inline bool integrity_req_gap_back_merge(struct request *req, - struct bio *next) -{ - struct bio_integrity_payload *bip = bio_integrity(req->bio); - struct bio_integrity_payload *bip_next = bio_integrity(next); - - return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1], - bip_next->bip_vec[0].bv_offset); -} - -static inline bool integrity_req_gap_front_merge(struct request *req, - struct bio *bio) -{ - struct bio_integrity_payload *bip = bio_integrity(bio); - struct bio_integrity_payload *bip_next = bio_integrity(req->bio); - - return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1], - bip_next->bip_vec[0].bv_offset); -} - /** * bio_integrity_intervals - Return number of integrity intervals for a bio * @bi: blk_integrity profile for device @@ -1947,17 +1927,6 @@ static inline bool blk_integrity_merge_bio(struct request_queue *rq, return true; } -static inline bool integrity_req_gap_back_merge(struct request *req, - struct bio *next) -{ - return false; -} -static inline bool integrity_req_gap_front_merge(struct request *req, - struct bio *bio) -{ - return false; -} - static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, unsigned int sectors) { -- cgit v1.2.3 From e9907009cbfc0c93d987d5a8fdf3d6c3c7b89717 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Sep 2018 09:43:48 +0200 Subject: block: move req_gap_{back,front}_merge to blk-merge.c Keep it close to the actual users instead of exposing the function to all drivers. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 69 -------------------------------------------------- 1 file changed, 69 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bc534c857344..b7e676bb01bc 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1695,75 +1695,6 @@ static inline bool bvec_gap_to_prev(struct request_queue *q, return __bvec_gap_to_prev(q, bprv, offset); } -/* - * Check if the two bvecs from two bios can be merged to one segment. - * If yes, no need to check gap between the two bios since the 1st bio - * and the 1st bvec in the 2nd bio can be handled in one segment. - */ -static inline bool bios_segs_mergeable(struct request_queue *q, - struct bio *prev, struct bio_vec *prev_last_bv, - struct bio_vec *next_first_bv) -{ - if (!BIOVEC_PHYS_MERGEABLE(prev_last_bv, next_first_bv)) - return false; - if (!BIOVEC_SEG_BOUNDARY(q, prev_last_bv, next_first_bv)) - return false; - if (prev->bi_seg_back_size + next_first_bv->bv_len > - queue_max_segment_size(q)) - return false; - return true; -} - -static inline bool bio_will_gap(struct request_queue *q, - struct request *prev_rq, - struct bio *prev, - struct bio *next) -{ - if (bio_has_data(prev) && queue_virt_boundary(q)) { - struct bio_vec pb, nb; - - /* - * don't merge if the 1st bio starts with non-zero - * offset, otherwise it is quite difficult to respect - * sg gap limit. We work hard to merge a huge number of small - * single bios in case of mkfs. - */ - if (prev_rq) - bio_get_first_bvec(prev_rq->bio, &pb); - else - bio_get_first_bvec(prev, &pb); - if (pb.bv_offset) - return true; - - /* - * We don't need to worry about the situation that the - * merged segment ends in unaligned virt boundary: - * - * - if 'pb' ends aligned, the merged segment ends aligned - * - if 'pb' ends unaligned, the next bio must include - * one single bvec of 'nb', otherwise the 'nb' can't - * merge with 'pb' - */ - bio_get_last_bvec(prev, &pb); - bio_get_first_bvec(next, &nb); - - if (!bios_segs_mergeable(q, prev, &pb, &nb)) - return __bvec_gap_to_prev(q, &pb, nb.bv_offset); - } - - return false; -} - -static inline bool req_gap_back_merge(struct request *req, struct bio *bio) -{ - return bio_will_gap(req->q, req, req->biotail, bio); -} - -static inline bool req_gap_front_merge(struct request *req, struct bio *bio) -{ - return bio_will_gap(req->q, NULL, bio, req->bio); -} - int kblockd_schedule_work(struct work_struct *work); int kblockd_schedule_work_on(int cpu, struct work_struct *work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); -- cgit v1.2.3 From 27ca1d4ed04ea29dc77b47190a3cc82697023e76 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Sep 2018 09:43:49 +0200 Subject: block: move req_gap_back_merge to blk.h No need to expose these helpers outside the block layer. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b7e676bb01bc..1d5e14139795 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1676,25 +1676,6 @@ static inline void put_dev_sector(Sector p) put_page(p.v); } -static inline bool __bvec_gap_to_prev(struct request_queue *q, - struct bio_vec *bprv, unsigned int offset) -{ - return offset || - ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); -} - -/* - * Check if adding a bio_vec after bprv with offset would create a gap in - * the SG list. Most drivers don't care about this, but some do. - */ -static inline bool bvec_gap_to_prev(struct request_queue *q, - struct bio_vec *bprv, unsigned int offset) -{ - if (!queue_virt_boundary(q)) - return false; - return __bvec_gap_to_prev(q, bprv, offset); -} - int kblockd_schedule_work(struct work_struct *work); int kblockd_schedule_work_on(int cpu, struct work_struct *work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); -- cgit v1.2.3 From bca6b067b0b269a7b8ba129e2a918309ca8b4a55 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 26 Sep 2018 14:01:03 -0700 Subject: block: Move power management code into a new source file Move the code for runtime power management from blk-core.c into the new source file blk-pm.c. Move the corresponding declarations from into . For CONFIG_PM=n, leave out the declarations of the functions that are not used in that mode. This patch not only reduces the number of #ifdefs in the block layer core code but also reduces the size of header file and hence should help to reduce the build time of the Linux kernel if CONFIG_PM is not defined. Signed-off-by: Bart Van Assche Reviewed-by: Ming Lei Reviewed-by: Christoph Hellwig Cc: Jianchao Wang Cc: Hannes Reinecke Cc: Johannes Thumshirn Cc: Alan Stern Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 23 ----------------------- 1 file changed, 23 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1d5e14139795..cd863511dedb 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1280,29 +1280,6 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id, extern void blk_put_queue(struct request_queue *); extern void blk_set_queue_dying(struct request_queue *); -/* - * block layer runtime pm functions - */ -#ifdef CONFIG_PM -extern void blk_pm_runtime_init(struct request_queue *q, struct device *dev); -extern int blk_pre_runtime_suspend(struct request_queue *q); -extern void blk_post_runtime_suspend(struct request_queue *q, int err); -extern void blk_pre_runtime_resume(struct request_queue *q); -extern void blk_post_runtime_resume(struct request_queue *q, int err); -extern void blk_set_runtime_active(struct request_queue *q); -#else -static inline void blk_pm_runtime_init(struct request_queue *q, - struct device *dev) {} -static inline int blk_pre_runtime_suspend(struct request_queue *q) -{ - return -ENOSYS; -} -static inline void blk_post_runtime_suspend(struct request_queue *q, int err) {} -static inline void blk_pre_runtime_resume(struct request_queue *q) {} -static inline void blk_post_runtime_resume(struct request_queue *q, int err) {} -static inline void blk_set_runtime_active(struct request_queue *q) {} -#endif - /* * blk_plug permits building a queue of related requests by holding the I/O * fragments for a short period. This allows merging of sequential requests -- cgit v1.2.3 From cd84a62e0078dce09f4ed349bec84f86c9d54b30 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 26 Sep 2018 14:01:04 -0700 Subject: block, scsi: Change the preempt-only flag into a counter The RQF_PREEMPT flag is used for three purposes: - In the SCSI core, for making sure that power management requests are executed even if a device is in the "quiesced" state. - For domain validation by SCSI drivers that use the parallel port. - In the IDE driver, for IDE preempt requests. Rename "preempt-only" into "pm-only" because the primary purpose of this mode is power management. Since the power management core may but does not have to resume a runtime suspended device before performing system-wide suspend and since a later patch will set "pm-only" mode as long as a block device is runtime suspended, make it possible to set "pm-only" mode from more than one context. Since with this change scsi_device_quiesce() is no longer idempotent, make that function return early if it is called for a quiesced queue. Signed-off-by: Bart Van Assche Acked-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Reviewed-by: Ming Lei Cc: Jianchao Wang Cc: Johannes Thumshirn Cc: Alan Stern Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index cd863511dedb..13bb54f26736 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -504,6 +504,12 @@ struct request_queue { * various queue flags, see QUEUE_* below */ unsigned long queue_flags; + /* + * Number of contexts that have called blk_set_pm_only(). If this + * counter is above zero then only RQF_PM and RQF_PREEMPT requests are + * processed. + */ + atomic_t pm_only; /* * ida allocated id for this queue. Used to index queues from @@ -698,7 +704,6 @@ struct request_queue { #define QUEUE_FLAG_REGISTERED 26 /* queue has been registered to a disk */ #define QUEUE_FLAG_SCSI_PASSTHROUGH 27 /* queue supports SCSI commands */ #define QUEUE_FLAG_QUIESCED 28 /* queue has been quiesced */ -#define QUEUE_FLAG_PREEMPT_ONLY 29 /* only process REQ_PREEMPT requests */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_SAME_COMP) | \ @@ -736,12 +741,11 @@ bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q); ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ REQ_FAILFAST_DRIVER)) #define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) -#define blk_queue_preempt_only(q) \ - test_bit(QUEUE_FLAG_PREEMPT_ONLY, &(q)->queue_flags) +#define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) #define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags) -extern int blk_set_preempt_only(struct request_queue *q); -extern void blk_clear_preempt_only(struct request_queue *q); +extern void blk_set_pm_only(struct request_queue *q); +extern void blk_clear_pm_only(struct request_queue *q); static inline int queue_in_flight(struct request_queue *q) { -- cgit v1.2.3 From 4822e902f9bdffaea2817471365e000966f0d1a1 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Thu, 11 Oct 2018 10:07:06 +0300 Subject: block: describe difference between flags IO_STAT and STATS This adds reasonable comments, but they definitely needs better names. Signed-off-by: Konstantin Khlebnikov Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index dee46c20701b..61207560e826 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -108,7 +108,7 @@ typedef __u32 __bitwise req_flags_t; #define RQF_QUIET ((__force req_flags_t)(1 << 11)) /* elevator private data attached */ #define RQF_ELVPRIV ((__force req_flags_t)(1 << 12)) -/* account I/O stat */ +/* account into disk and partition IO statistics */ #define RQF_IO_STAT ((__force req_flags_t)(1 << 13)) /* request came from our alloc pool */ #define RQF_ALLOCED ((__force req_flags_t)(1 << 14)) @@ -116,7 +116,7 @@ typedef __u32 __bitwise req_flags_t; #define RQF_PM ((__force req_flags_t)(1 << 15)) /* on IO scheduler merge hash */ #define RQF_HASHED ((__force req_flags_t)(1 << 16)) -/* IO stats tracking on */ +/* track IO completion time */ #define RQF_STATS ((__force req_flags_t)(1 << 17)) /* Look at ->special_vec for the actual data payload instead of the bio chain. */ @@ -685,7 +685,7 @@ struct request_queue { #define QUEUE_FLAG_FAIL_IO 7 /* fake timeout */ #define QUEUE_FLAG_NONROT 9 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ -#define QUEUE_FLAG_IO_STAT 10 /* do IO stats */ +#define QUEUE_FLAG_IO_STAT 10 /* do disk/partitions IO accounting */ #define QUEUE_FLAG_DISCARD 11 /* supports DISCARD */ #define QUEUE_FLAG_NOXMERGES 12 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 13 /* Contributes to random pool */ @@ -699,7 +699,7 @@ struct request_queue { #define QUEUE_FLAG_FUA 21 /* device supports FUA writes */ #define QUEUE_FLAG_FLUSH_NQ 22 /* flush not queueuable */ #define QUEUE_FLAG_DAX 23 /* device supports DAX */ -#define QUEUE_FLAG_STATS 24 /* track rq completion times */ +#define QUEUE_FLAG_STATS 24 /* track IO start and completion times */ #define QUEUE_FLAG_POLL_STATS 25 /* collecting stats for hybrid polling */ #define QUEUE_FLAG_REGISTERED 26 /* queue has been registered to a disk */ #define QUEUE_FLAG_SCSI_PASSTHROUGH 27 /* queue supports SCSI commands */ -- cgit v1.2.3 From 49d92c0dd64ae769c2d67fe27ac260ae31259ba6 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 4 Oct 2018 15:27:41 -0600 Subject: block: Add PCI P2P flag for request queue Add QUEUE_FLAG_PCI_P2P, meaning a driver's request queue supports targeting P2P memory. This will be used by P2P providers and orchestrators (in subsequent patches) to ensure block devices can support P2P memory before submitting P2P-backed pages to submit_bio(). Signed-off-by: Logan Gunthorpe Signed-off-by: Bjorn Helgaas Reviewed-by: Christoph Hellwig Acked-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 6980014357d4..c32f7171899b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -699,6 +699,7 @@ struct request_queue { #define QUEUE_FLAG_SCSI_PASSTHROUGH 27 /* queue supports SCSI commands */ #define QUEUE_FLAG_QUIESCED 28 /* queue has been quiesced */ #define QUEUE_FLAG_PREEMPT_ONLY 29 /* only process REQ_PREEMPT requests */ +#define QUEUE_FLAG_PCI_P2PDMA 30 /* device supports PCI p2p requests */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_SAME_COMP) | \ @@ -731,6 +732,8 @@ bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q); #define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) #define blk_queue_scsi_passthrough(q) \ test_bit(QUEUE_FLAG_SCSI_PASSTHROUGH, &(q)->queue_flags) +#define blk_queue_pci_p2pdma(q) \ + test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags) #define blk_noretry_request(rq) \ ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ -- cgit v1.2.3 From a91e138022bc29b5d2bbc56b41de3e0db6261e28 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 12 Oct 2018 19:08:43 +0900 Subject: block: Introduce blkdev_nr_zones() helper Introduce the blkdev_nr_zones() helper function to get the total number of zones of a zoned block device. This number is always 0 for a regular block device (q->limits.zoned == BLK_ZONED_NONE case). Replace hard-coded number of zones calculation in dmz_get_zoned_device() with a call to this helper. Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7d423721b327..ca5fdc1b7745 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -401,6 +401,7 @@ struct blk_zone_report_hdr { u8 padding[60]; }; +extern unsigned int blkdev_nr_zones(struct block_device *bdev); extern int blkdev_report_zones(struct block_device *bdev, sector_t sector, struct blk_zone *zones, unsigned int *nr_zones, gfp_t gfp_mask); @@ -414,6 +415,10 @@ extern int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode, #else /* CONFIG_BLK_DEV_ZONED */ +static inline unsigned int blkdev_nr_zones(struct block_device *bdev) +{ + return 0; +} static inline int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) -- cgit v1.2.3 From 965b652e901886ea54f93c60027b5be76328d958 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 12 Oct 2018 19:08:48 +0900 Subject: block: Expose queue nr_zones in sysfs Expose through sysfs the nr_zones field of struct request_queue. Exposing this value helps in debugging disk issues as well as facilitating scripts based use of the disk (e.g. blktests). For zoned block devices, the nr_zones field indicates the total number of zones of the device calculated using the known disk capacity and zone size. This number of zones is always 0 for regular block devices. Since nr_zones is defined conditionally with CONFIG_BLK_DEV_ZONED, introduce the blk_queue_nr_zones() function to return the correct value for any device, regardless if CONFIG_BLK_DEV_ZONED is set. Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ca5fdc1b7745..6bb845f9601a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -811,6 +811,11 @@ static inline unsigned int blk_queue_zone_sectors(struct request_queue *q) } #ifdef CONFIG_BLK_DEV_ZONED +static inline unsigned int blk_queue_nr_zones(struct request_queue *q) +{ + return blk_queue_is_zoned(q) ? q->nr_zones : 0; +} + static inline unsigned int blk_queue_zone_no(struct request_queue *q, sector_t sector) { @@ -826,6 +831,11 @@ static inline bool blk_queue_zone_is_seq(struct request_queue *q, return false; return test_bit(blk_queue_zone_no(q, sector), q->seq_zones_bitmap); } +#else /* CONFIG_BLK_DEV_ZONED */ +static inline unsigned int blk_queue_nr_zones(struct request_queue *q) +{ + return 0; +} #endif /* CONFIG_BLK_DEV_ZONED */ static inline bool rq_is_sync(struct request *rq) -- cgit v1.2.3 From e76239a3748c90a8b0e197f8f4544a8ce52f126e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 12 Oct 2018 19:08:49 +0900 Subject: block: add a report_zones method Dispatching a report zones command through the request queue is a major pain due to the command reply payload rewriting necessary. Given that blkdev_report_zones() is executing everything synchronously, implement report zones as a block device file operation instead, allowing major simplification of the code in many places. sd, null-blk, dm-linear and dm-flakey being the only block device drivers supporting exposing zoned block devices, these drivers are modified to provide the device side implementation of the report_zones() block device file operation. For device mappers, a new report_zones() target type operation is defined so that the upper block layer calls blkdev_report_zones() can be propagated down to the underlying devices of the dm targets. Implementation for this new operation is added to the dm-linear and dm-flakey targets. Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig [Damien] * Changed method block_device argument to gendisk * Various bug fixes and improvements * Added support for null_blk, dm-linear and dm-flakey. Reviewed-by: Martin K. Petersen Reviewed-by: Mike Snitzer Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6bb845f9601a..51fe6472ce02 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -396,11 +396,6 @@ struct queue_limits { #ifdef CONFIG_BLK_DEV_ZONED -struct blk_zone_report_hdr { - unsigned int nr_zones; - u8 padding[60]; -}; - extern unsigned int blkdev_nr_zones(struct block_device *bdev); extern int blkdev_report_zones(struct block_device *bdev, sector_t sector, struct blk_zone *zones, @@ -1867,6 +1862,9 @@ struct block_device_operations { int (*getgeo)(struct block_device *, struct hd_geometry *); /* this callback is with swap_lock and sometimes page table lock held */ void (*swap_slot_free_notify) (struct block_device *, unsigned long); + int (*report_zones)(struct gendisk *, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask); struct module *owner; const struct pr_ops *pr_ops; }; -- cgit v1.2.3 From bf5054569653c491ece544cc7ee333ae53b47121 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 12 Oct 2018 19:08:50 +0900 Subject: block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Mike Snitzer Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 51fe6472ce02..4293dc1cd160 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -402,6 +402,7 @@ extern int blkdev_report_zones(struct block_device *bdev, unsigned int *nr_zones, gfp_t gfp_mask); extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask); +extern int blk_revalidate_disk_zones(struct gendisk *disk); extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); @@ -414,6 +415,12 @@ static inline unsigned int blkdev_nr_zones(struct block_device *bdev) { return 0; } + +static inline int blk_revalidate_disk_zones(struct gendisk *disk) +{ + return 0; +} + static inline int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) -- cgit v1.2.3