From 729204ef49ec00b788ce23deb9eb922a5769f55d Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Sat, 17 Dec 2016 18:49:09 +0800 Subject: block: relax check on sg gap If the last bvec of the 1st bio and the 1st bvec of the next bio are physically contigious, and the latter can be merged to last segment of the 1st bio, we should think they don't violate sg gap(or virt boundary) limit. Both Vitaly and Dexuan reported lots of unmergeable small bios are observed when running mkfs on Hyper-V virtual storage, and performance becomes quite low. This patch fixes that performance issue. The same issue should exist on NVMe, since it sets virt boundary too. Reported-by: Vitaly Kuznetsov Reported-by: Dexuan Cui Tested-by: Dexuan Cui Cc: Keith Busch Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 83695641bd5e..b20da8dfa7ec 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1607,6 +1607,25 @@ 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 bio *prev, struct bio *next) { @@ -1616,7 +1635,8 @@ static inline bool bio_will_gap(struct request_queue *q, struct bio *prev, bio_get_last_bvec(prev, &pb); bio_get_first_bvec(next, &nb); - return __bvec_gap_to_prev(q, &pb, nb.bv_offset); + if (!bios_segs_mergeable(q, prev, &pb, &nb)) + return __bvec_gap_to_prev(q, &pb, nb.bv_offset); } return false; -- cgit v1.2.3 From f8a5b12247fe18f7fed801ad262a7ab190e1f848 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 13 Dec 2016 09:24:51 -0700 Subject: blk-mq: make mq_ops a const pointer We never change it, make that clear. Signed-off-by: Jens Axboe Reviewed-by: Bart Van Assche --- 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 b20da8dfa7ec..2e99d659b0f1 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -407,7 +407,7 @@ struct request_queue { dma_drain_needed_fn *dma_drain_needed; lld_busy_fn *lld_busy_fn; - struct blk_mq_ops *mq_ops; + const struct blk_mq_ops *mq_ops; unsigned int *mq_map; -- cgit v1.2.3 From bd166ef183c263c5ced656d49ef19c7da4adc774 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 17 Jan 2017 06:03:22 -0700 Subject: blk-mq-sched: add framework for MQ capable IO schedulers This adds a set of hooks that intercepts the blk-mq path of allocating/inserting/issuing/completing requests, allowing us to develop a scheduler within that framework. We reuse the existing elevator scheduler API on the registration side, but augment that with the scheduler flagging support for the blk-mq interfce, and with a separate set of ops hooks for MQ devices. We split driver and scheduler tags, so we can run the scheduling independently of device queue depth. Signed-off-by: Jens Axboe Reviewed-by: Bart Van Assche Reviewed-by: Omar Sandoval --- include/linux/blkdev.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2e99d659b0f1..25564857f5f8 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -154,6 +154,7 @@ struct request { /* the following two fields are internal, NEVER access directly */ unsigned int __data_len; /* total data len */ + int tag; sector_t __sector; /* sector cursor */ struct bio *bio; @@ -220,9 +221,10 @@ struct request { unsigned short ioprio; + int internal_tag; + void *special; /* opaque pointer available for LLD use */ - int tag; int errors; /* -- cgit v1.2.3 From 07e4fead45e6e1932f0b960655ab554b6aab6a08 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Wed, 25 Jan 2017 08:06:40 -0800 Subject: blk-mq: create debugfs directory tree In preparation for putting blk-mq debugging information in debugfs, create a directory tree mirroring the one in sysfs: # tree -d /sys/kernel/debug/block /sys/kernel/debug/block |-- nvme0n1 | `-- mq | |-- 0 | | `-- cpu0 | |-- 1 | | `-- cpu1 | |-- 2 | | `-- cpu2 | `-- 3 | `-- cpu3 `-- vda `-- mq `-- 0 |-- cpu0 |-- cpu1 |-- cpu2 `-- cpu3 Also add the scaffolding for the actual files that will go in here, either under the hardware queue or software queue directories. Reviewed-by: Hannes Reinecke Signed-off-by: Omar Sandoval 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 25564857f5f8..0ee283f3cffe 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -571,6 +571,11 @@ struct request_queue { struct list_head tag_set_list; struct bio_set *bio_split; +#ifdef CONFIG_DEBUG_FS + struct dentry *debugfs_dir; + struct dentry *mq_debugfs_dir; +#endif + bool mq_sysfs_init_done; }; -- cgit v1.2.3 From 50e1dab86aa2c10cbca2f754aae9542169403141 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 26 Jan 2017 14:42:34 -0700 Subject: blk-mq-sched: fix starvation for multiple hardware queues and shared tags If we have both multiple hardware queues and shared tag map between devices, we need to ensure that we propagate the hardware queue restart bit higher up. This is because we can get into a situation where we don't have any IO pending on a hardware queue, yet we fail getting a tag to start new IO. If that happens, it's not enough to mark the hardware queue as needing a restart, we need to bubble that up to the higher level queue as well. Signed-off-by: Jens Axboe Reviewed-by: Omar Sandoval Tested-by: Hannes Reinecke --- 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 0ee283f3cffe..883b8abe4305 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -607,6 +607,7 @@ struct request_queue { #define QUEUE_FLAG_FLUSH_NQ 25 /* flush not queueuable */ #define QUEUE_FLAG_DAX 26 /* device supports DAX */ #define QUEUE_FLAG_STATS 27 /* track rq completion times */ +#define QUEUE_FLAG_RESTART 28 /* queue needs restart at completion */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_STACKABLE) | \ -- cgit v1.2.3 From 5ea708d15a928f7a479987704203616d3274c03b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 3 Jan 2017 14:52:44 +0300 Subject: block: simplify blk_init_allocated_queue Return an errno value instead of the passed in queue so that the callers don't have to keep track of two queues, and move the assignment of the request_fn and lock to the caller as passing them as argument doesn't simplify anything. While we're at it also remove two pointless NULL assignments, given that the request structure is zeroed on allocation. Signed-off-by: Christoph Hellwig Reviewed-by: Bart Van Assche Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 05675b1dfd20..6b1efc5760ea 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1137,8 +1137,7 @@ extern void blk_unprep_request(struct request *); extern struct request_queue *blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id); extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *); -extern struct request_queue *blk_init_allocated_queue(struct request_queue *, - request_fn_proc *, spinlock_t *); +extern int blk_init_allocated_queue(struct request_queue *); extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); -- cgit v1.2.3 From 6d247d7f71d1fa4b66a5f4da7b1daa21510d529b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 27 Jan 2017 09:51:45 -0700 Subject: block: allow specifying size for extra command data This mirrors the blk-mq capabilities to allocate extra drivers-specific data behind struct request by setting a cmd_size field, as well as having a constructor / destructor for it. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke 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 6b1efc5760ea..461b7cf6af1d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -273,6 +273,8 @@ typedef void (softirq_done_fn)(struct request *); typedef int (dma_drain_needed_fn)(struct request *); typedef int (lld_busy_fn) (struct request_queue *q); typedef int (bsg_job_fn) (struct bsg_job *); +typedef int (init_rq_fn)(struct request_queue *, struct request *, gfp_t); +typedef void (exit_rq_fn)(struct request_queue *, struct request *); enum blk_eh_timer_return { BLK_EH_NOT_HANDLED, @@ -408,6 +410,8 @@ struct request_queue { rq_timed_out_fn *rq_timed_out_fn; dma_drain_needed_fn *dma_drain_needed; lld_busy_fn *lld_busy_fn; + init_rq_fn *init_rq_fn; + exit_rq_fn *exit_rq_fn; const struct blk_mq_ops *mq_ops; @@ -577,6 +581,9 @@ struct request_queue { #endif bool mq_sysfs_init_done; + + size_t cmd_size; + void *rq_alloc_data; }; #define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */ -- cgit v1.2.3 From 82ed4db499b8598f16f8871261bff088d6b0597f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 27 Jan 2017 09:46:29 +0100 Subject: block: split scsi_request out of struct request And require all drivers that want to support BLOCK_PC to allocate it as the first thing of their private data. To support this the legacy IDE and BSG code is switched to set cmd_size on their queues to let the block layer allocate the additional space. Signed-off-by: Christoph Hellwig 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 461b7cf6af1d..e4c5f284fe2d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -128,8 +128,6 @@ typedef __u32 __bitwise req_flags_t; #define RQF_NOMERGE_FLAGS \ (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) -#define BLK_MAX_CDB 16 - /* * Try to put the fields that are referenced together in the same cacheline. * @@ -227,17 +225,7 @@ struct request { int errors; - /* - * when request is used as a packet command carrier - */ - unsigned char __cmd[BLK_MAX_CDB]; - unsigned char *cmd; - unsigned short cmd_len; - unsigned int extra_len; /* length of alignment and padding */ - unsigned int sense_len; - unsigned int resid_len; /* residual count */ - void *sense; unsigned long deadline; struct list_head timeout_list; @@ -925,7 +913,6 @@ extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_put_request(struct request *); extern void __blk_put_request(struct request_queue *, struct request *); extern struct request *blk_get_request(struct request_queue *, int, gfp_t); -extern void blk_rq_set_block_pc(struct request *); extern void blk_requeue_request(struct request_queue *, struct request *); extern int blk_lld_busy(struct request_queue *q); extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, -- cgit v1.2.3 From 57292b58ddb58689e8c3b4c6eadbef10d9ca44dd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 31 Jan 2017 16:57:29 +0100 Subject: block: introduce blk_rq_is_passthrough This can be used to check for fs vs non-fs requests and basically removes all knowledge of BLOCK_PC specific from the block layer, as well as preparing for removing the cmd_type field in struct request. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e4c5f284fe2d..7121be081517 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -242,6 +242,11 @@ struct request { struct request *next_rq; }; +static inline bool blk_rq_is_passthrough(struct request *rq) +{ + return rq->cmd_type != REQ_TYPE_FS; +} + static inline unsigned short req_get_ioprio(struct request *req) { return req->ioprio; @@ -698,9 +703,10 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ REQ_FAILFAST_DRIVER)) -#define blk_account_rq(rq) \ - (((rq)->rq_flags & RQF_STARTED) && \ - ((rq)->cmd_type == REQ_TYPE_FS)) +static inline bool blk_account_rq(struct request *rq) +{ + return (rq->rq_flags & RQF_STARTED) && !blk_rq_is_passthrough(rq); +} #define blk_rq_cpu_valid(rq) ((rq)->cpu != -1) #define blk_bidi_rq(rq) ((rq)->next_rq != NULL) @@ -775,7 +781,7 @@ static inline void blk_clear_rl_full(struct request_list *rl, bool sync) static inline bool rq_mergeable(struct request *rq) { - if (rq->cmd_type != REQ_TYPE_FS) + if (blk_rq_is_passthrough(rq)) return false; if (req_op(rq) == REQ_OP_FLUSH) @@ -1049,7 +1055,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq, { struct request_queue *q = rq->q; - if (unlikely(rq->cmd_type != REQ_TYPE_FS)) + if (blk_rq_is_passthrough(rq)) return q->limits.max_hw_sectors; if (!q->limits.chunk_sectors || -- cgit v1.2.3 From aebf526b53aea164508730427597d45f3e06b376 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 31 Jan 2017 16:57:31 +0100 Subject: block: fold cmd_type into the REQ_OP_ space Instead of keeping two levels of indirection for requests types, fold it all into the operations. The little caveat here is that previously cmd_type only applied to struct request, while the request and bio op fields were set to plain REQ_OP_READ/WRITE even for passthrough operations. Instead this patch adds new REQ_OP_* for SCSI passthrough and driver private requests, althought it has to add two for each so that we can communicate the data in/out nature of the request. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7121be081517..1e947e725528 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -70,15 +70,6 @@ struct request_list { unsigned int flags; }; -/* - * request command types - */ -enum rq_cmd_type_bits { - REQ_TYPE_FS = 1, /* fs request */ - REQ_TYPE_BLOCK_PC, /* scsi command */ - REQ_TYPE_DRV_PRIV, /* driver defined types from here */ -}; - /* * request flags */ typedef __u32 __bitwise req_flags_t; @@ -145,7 +136,6 @@ struct request { struct blk_mq_ctx *mq_ctx; int cpu; - unsigned cmd_type; unsigned int cmd_flags; /* op and common flags */ req_flags_t rq_flags; unsigned long atomic_flags; @@ -242,9 +232,19 @@ struct request { struct request *next_rq; }; +static inline bool blk_rq_is_scsi(struct request *rq) +{ + return req_op(rq) == REQ_OP_SCSI_IN || req_op(rq) == REQ_OP_SCSI_OUT; +} + +static inline bool blk_rq_is_private(struct request *rq) +{ + return req_op(rq) == REQ_OP_DRV_IN || req_op(rq) == REQ_OP_DRV_OUT; +} + static inline bool blk_rq_is_passthrough(struct request *rq) { - return rq->cmd_type != REQ_TYPE_FS; + return blk_rq_is_scsi(rq) || blk_rq_is_private(rq); } static inline unsigned short req_get_ioprio(struct request *req) -- cgit v1.2.3 From d486f1f204382557b5fbcb3ddbb5845cd4ba4e2c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 31 Jan 2017 12:34:41 -0700 Subject: block: move internal_tag to same cache line as tag Since we removed cmd_type, we now have a hole in the struct. Move the internal_tag member to the same cacheline as tag, since we use them at the same time. This doesn't fix the hole, just moves it elsewhere. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1e947e725528..11f7a8e86a89 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -138,6 +138,9 @@ struct request { int cpu; unsigned int cmd_flags; /* op and common flags */ req_flags_t rq_flags; + + int internal_tag; + unsigned long atomic_flags; /* the following two fields are internal, NEVER access directly */ @@ -209,8 +212,6 @@ struct request { unsigned short ioprio; - int internal_tag; - void *special; /* opaque pointer available for LLD use */ int errors; -- cgit v1.2.3 From dc3b17cc8bf21307c7e076e7c778d5db756f7871 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 2 Feb 2017 15:56:50 +0100 Subject: block: Use pointer to backing_dev_info from request_queue We will want to have struct backing_dev_info allocated separately from struct request_queue. As the first step add pointer to backing_dev_info to request_queue and convert all users touching it. No functional changes in this patch. Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 11f7a8e86a89..a75e42de34ab 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -432,7 +432,8 @@ struct request_queue { */ struct delayed_work delay_work; - struct backing_dev_info backing_dev_info; + struct backing_dev_info *backing_dev_info; + struct backing_dev_info _backing_dev_info; /* * The queue owner gets to use this for whatever they like. -- cgit v1.2.3 From d03f6cdc1fc422accb734c7c07a661a0018d8631 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 2 Feb 2017 15:56:51 +0100 Subject: block: Dynamically allocate and refcount backing_dev_info Instead of storing backing_dev_info inside struct request_queue, allocate it dynamically, reference count it, and free it when the last reference is dropped. Currently only request_queue holds the reference but in the following patch we add other users referencing backing_dev_info. Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a75e42de34ab..e77c1039fd0e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -433,7 +433,6 @@ struct request_queue { struct delayed_work delay_work; struct backing_dev_info *backing_dev_info; - struct backing_dev_info _backing_dev_info; /* * The queue owner gets to use this for whatever they like. -- cgit v1.2.3 From efa7c9f97e3ef624e9a398bf69c15f58eea9f0e8 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 2 Feb 2017 15:56:53 +0100 Subject: block: Get rid of blk_get_backing_dev_info() blk_get_backing_dev_info() is now a simple dereference. Remove that function and simplify some code around that. Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e77c1039fd0e..b31137e2afd0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1187,7 +1187,6 @@ 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 void blk_queue_flush_queueable(struct request_queue *q, bool queueable); extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); -extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); static inline unsigned short blk_rq_nr_phys_segments(struct request *rq) { -- cgit v1.2.3 From 0dba1314d4f81115dce711292ec7981d17231064 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 1 Feb 2017 14:05:23 -0800 Subject: scsi, block: fix duplicate bdi name registration crashes Warnings of the following form occur because scsi reuses a devt number while the block layer still has it referenced as the name of the bdi [1]: WARNING: CPU: 1 PID: 93 at fs/sysfs/dir.c:31 sysfs_warn_dup+0x62/0x80 sysfs: cannot create duplicate filename '/devices/virtual/bdi/8:192' [..] Call Trace: dump_stack+0x86/0xc3 __warn+0xcb/0xf0 warn_slowpath_fmt+0x5f/0x80 ? kernfs_path_from_node+0x4f/0x60 sysfs_warn_dup+0x62/0x80 sysfs_create_dir_ns+0x77/0x90 kobject_add_internal+0xb2/0x350 kobject_add+0x75/0xd0 device_add+0x15a/0x650 device_create_groups_vargs+0xe0/0xf0 device_create_vargs+0x1c/0x20 bdi_register+0x90/0x240 ? lockdep_init_map+0x57/0x200 bdi_register_owner+0x36/0x60 device_add_disk+0x1bb/0x4e0 ? __pm_runtime_use_autosuspend+0x5c/0x70 sd_probe_async+0x10d/0x1c0 async_run_entry_fn+0x39/0x170 This is a brute-force fix to pass the devt release information from sd_probe() to the locations where we register the bdi, device_add_disk(), and unregister the bdi, blk_cleanup_queue(). Thanks to Omar for the quick reproducer script [2]. This patch survives where an unmodified kernel fails in a few seconds. [1]: https://marc.info/?l=linux-scsi&m=147116857810716&w=4 [2]: http://marc.info/?l=linux-block&m=148554717109098&w=2 Cc: James Bottomley Cc: Bart Van Assche Cc: "Martin K. Petersen" Cc: Jan Kara Reported-by: Omar Sandoval Tested-by: Omar Sandoval Signed-off-by: Dan Williams Reviewed-by: Christoph Hellwig Reviewed-by: Bart Van Assche 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 b31137e2afd0..f84fbe55d3b3 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -433,6 +433,7 @@ struct request_queue { struct delayed_work delay_work; struct backing_dev_info *backing_dev_info; + struct disk_devt *disk_devt; /* * The queue owner gets to use this for whatever they like. -- cgit v1.2.3 From 03796c149a99e14506db9de3adba710c26f83ba9 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Tue, 31 Jan 2017 14:53:18 -0800 Subject: block: fix debugfs config conditional in struct request_queue The debugfs dentries are only used for CONFIG_BLK_DEBUG_FS, so make them conditional on that instead of CONFIG_DEBUG_FS. Signed-off-by: Omar Sandoval 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 f84fbe55d3b3..e0bac14347e6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -570,7 +570,7 @@ struct request_queue { struct list_head tag_set_list; struct bio_set *bio_split; -#ifdef CONFIG_DEBUG_FS +#ifdef CONFIG_BLK_DEBUG_FS struct dentry *debugfs_dir; struct dentry *mq_debugfs_dir; #endif -- cgit v1.2.3 From 1e739730c5b9ea80a2f25e9cf6e1025d47e3d8ed Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 8 Feb 2017 14:46:49 +0100 Subject: block: optionally merge discontiguous discard bios into a single request Add a new merge strategy that merges discard bios into a request until the maximum number of discard ranges (or the maximum discard size) is reached from the plug merging code. I/O scheduler merging is not wired up yet but might also be useful, although not for fast devices like NVMe which are the only user for now. Note that for now we don't support limiting the size of each discard range, but if needed that can be added later. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e0bac14347e6..aecca0e7d9ca 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -331,6 +331,7 @@ struct queue_limits { unsigned short logical_block_size; unsigned short max_segments; unsigned short max_integrity_segments; + unsigned short max_discard_segments; unsigned char misaligned; unsigned char discard_misaligned; @@ -1146,6 +1147,8 @@ extern void blk_queue_bounce_limit(struct request_queue *, u64); extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_segments(struct request_queue *, unsigned short); +extern void blk_queue_max_discard_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); @@ -1189,6 +1192,15 @@ extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable); extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); +/* + * Number of physical segments as sent to the device. + * + * Normally this is the number of discontiguous data segments sent by the + * submitter. But for data-less command like discard we might have no + * actual data segments submitted, but the driver might have to add it's + * own special payload. In that case we still return 1 here so that this + * special payload will be mapped. + */ static inline unsigned short blk_rq_nr_phys_segments(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) @@ -1196,6 +1208,15 @@ static inline unsigned short blk_rq_nr_phys_segments(struct request *rq) return rq->nr_phys_segments; } +/* + * Number of discard segments (or ranges) the driver needs to fill in. + * Each discard bio merged into a request is counted as one segment. + */ +static inline unsigned short blk_rq_nr_discard_segments(struct request *rq) +{ + return max_t(unsigned short, rq->nr_phys_segments, 1); +} + extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *); extern void blk_dump_rq_flags(struct request *, char *); extern long nr_blockdev_pages(void); @@ -1384,6 +1405,11 @@ static inline unsigned short queue_max_segments(struct request_queue *q) return q->limits.max_segments; } +static inline unsigned short queue_max_discard_segments(struct request_queue *q) +{ + return q->limits.max_discard_segments; +} + static inline unsigned int queue_max_segment_size(struct request_queue *q) { return q->limits.max_segment_size; -- cgit v1.2.3