From 8fa72d234da9b6b473bbb1f74d533663e4996e6b Mon Sep 17 00:00:00 2001 From: Jeff Moyer Date: Wed, 5 Dec 2012 20:17:21 +0100 Subject: bdi: add a user-tunable cpu_list for the bdi flusher threads In realtime environments, it may be desirable to keep the per-bdi flusher threads from running on certain cpus. This patch adds a cpu_list file to /sys/class/bdi/* to enable this. The default is to tie the flusher threads to the same numa node as the backing device (though I could be convinced to make it a mask of all cpus to avoid a change in behaviour). Thanks to Jeremy Eder for the original idea. Signed-off-by: Jeff Moyer Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 2a9a9abc9126..238521a19849 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -18,6 +18,7 @@ #include #include #include +#include struct page; struct device; @@ -105,6 +106,9 @@ struct backing_dev_info { struct timer_list laptop_mode_wb_timer; + cpumask_t *flusher_cpumask; /* used for writeback thread scheduling */ + struct mutex flusher_cpumask_lock; + #ifdef CONFIG_DEBUG_FS struct dentry *debug_dir; struct dentry *debug_stats; -- cgit v1.2.3 From 3f3299d5c0268d6cc3f47b446e8aca436e4a5651 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 28 Nov 2012 13:42:38 +0100 Subject: block: Rename queue dead flag QUEUE_FLAG_DEAD is used to indicate that queuing new requests must stop. After this flag has been set queue draining starts. However, during the queue draining phase it is still safe to invoke the queue's request_fn, so QUEUE_FLAG_DYING is a better name for this flag. This patch has been generated by running the following command over the kernel source tree: git grep -lEw 'blk_queue_dead|QUEUE_FLAG_DEAD' | xargs sed -i.tmp -e 's/blk_queue_dead/blk_queue_dying/g' \ -e 's/QUEUE_FLAG_DEAD/QUEUE_FLAG_DYING/g'; \ sed -i.tmp -e "s/QUEUE_FLAG_DYING$(printf \\t)*5/QUEUE_FLAG_DYING$(printf \\t)5/g" \ include/linux/blkdev.h; \ sed -i.tmp -e 's/ DEAD/ DYING/g' -e 's/dead queue/a dying queue/' \ -e 's/Dead queue/A dying queue/' block/blk-core.c Signed-off-by: Bart Van Assche Acked-by: Tejun Heo Cc: James Bottomley Cc: Mike Christie Cc: Jens Axboe Cc: Chanho Min Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1756001210d2..aba8246afe72 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -437,7 +437,7 @@ struct request_queue { #define QUEUE_FLAG_STOPPED 2 /* queue is stopped */ #define QUEUE_FLAG_SYNCFULL 3 /* read queue has been filled */ #define QUEUE_FLAG_ASYNCFULL 4 /* write queue has been filled */ -#define QUEUE_FLAG_DEAD 5 /* queue being torn down */ +#define QUEUE_FLAG_DYING 5 /* queue being torn down */ #define QUEUE_FLAG_BYPASS 6 /* act as dumb FIFO queue */ #define QUEUE_FLAG_BIDI 7 /* queue supports bidi requests */ #define QUEUE_FLAG_NOMERGES 8 /* disable merge attempts */ @@ -521,7 +521,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define blk_queue_tagged(q) test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags) #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) -#define blk_queue_dead(q) test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags) +#define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags) #define blk_queue_bypass(q) test_bit(QUEUE_FLAG_BYPASS, &(q)->queue_flags) #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) #define blk_queue_noxmerges(q) \ -- cgit v1.2.3 From c246e80d86736312933646896c4157daf511dadc Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 6 Dec 2012 14:32:01 +0100 Subject: block: Avoid that request_fn is invoked on a dead queue A block driver may start cleaning up resources needed by its request_fn as soon as blk_cleanup_queue() finished, so request_fn must not be invoked after draining finished. This is important when blk_run_queue() is invoked without any requests in progress. As an example, if blk_drain_queue() and scsi_run_queue() run in parallel, blk_drain_queue() may have finished all requests after scsi_run_queue() has taken a SCSI device off the starved list but before that last function has had a chance to run the queue. Signed-off-by: Bart Van Assche Cc: James Bottomley Cc: Mike Christie Cc: Chanho Min Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index aba8246afe72..8bc46c250ca4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -452,6 +452,7 @@ struct request_queue { #define QUEUE_FLAG_ADD_RANDOM 16 /* Contributes to random pool */ #define QUEUE_FLAG_SECDISCARD 17 /* supports SECDISCARD */ #define QUEUE_FLAG_SAME_FORCE 18 /* force complete on same CPU */ +#define QUEUE_FLAG_DEAD 19 /* queue tear-down finished */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_STACKABLE) | \ @@ -522,6 +523,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define blk_queue_tagged(q) test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags) #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags) +#define blk_queue_dead(q) test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags) #define blk_queue_bypass(q) test_bit(QUEUE_FLAG_BYPASS, &(q)->queue_flags) #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) #define blk_queue_noxmerges(q) \ -- cgit v1.2.3 From 24faf6f604efe18236bded4303009fc252913bf0 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 28 Nov 2012 13:46:45 +0100 Subject: block: Make blk_cleanup_queue() wait until request_fn finished Some request_fn implementations, e.g. scsi_request_fn(), unlock the queue lock internally. This may result in multiple threads executing request_fn for the same queue simultaneously. Keep track of the number of active request_fn calls and make sure that blk_cleanup_queue() waits until all active request_fn invocations have finished. A block driver may start cleaning up resources needed by its request_fn as soon as blk_cleanup_queue() finished, so blk_cleanup_queue() must wait for all outstanding request_fn invocations to finish. Signed-off-by: Bart Van Assche Reported-by: Chanho Min Cc: James Bottomley Cc: Mike Christie Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8bc46c250ca4..c9d233e727f2 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -378,6 +378,12 @@ struct request_queue { unsigned int nr_sorted; unsigned int in_flight[2]; + /* + * Number of active block driver functions for which blk_drain_queue() + * must wait. Must be incremented around functions that unlock the + * queue_lock internally, e.g. scsi_request_fn(). + */ + unsigned int request_fn_active; unsigned int rq_timeout; struct timer_list timeout; -- cgit v1.2.3 From 80729beb3326fd682543f4f4ea534df47ab48967 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 28 Nov 2012 13:47:36 +0100 Subject: bsg: Remove unused function bsg_goose_queue() The function bsg_goose_queue() does not have any in-tree callers, so let's remove it. Signed-off-by: Bart Van Assche Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/bsg-lib.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index 4d0fb3df2f4a..a226652a5a6c 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -67,6 +67,5 @@ void bsg_job_done(struct bsg_job *job, int result, int bsg_setup_queue(struct device *dev, struct request_queue *q, char *name, bsg_job_fn *job_fn, int dd_job_size); void bsg_request_fn(struct request_queue *q); -void bsg_goose_queue(struct request_queue *q); #endif -- cgit v1.2.3 From 8dd2cb7e880d2f77fba53b523c99133ad5054cfd Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Fri, 14 Dec 2012 11:15:36 +0800 Subject: block: discard granularity might not be power of 2 In MD raid case, discard granularity might not be power of 2, for example, a 4-disk raid5 has 3*chunk_size discard granularity. Correct the calculation for such cases. Reported-by: Neil Brown Signed-off-by: Shaohua Li Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c9d233e727f2..acb4f7bbbd32 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1188,13 +1188,14 @@ static inline int queue_discard_alignment(struct request_queue *q) static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector) { - unsigned int alignment = (sector << 9) & (lim->discard_granularity - 1); + sector_t alignment = sector << 9; + alignment = sector_div(alignment, lim->discard_granularity); if (!lim->max_discard_sectors) return 0; - return (lim->discard_granularity + lim->discard_alignment - alignment) - & (lim->discard_granularity - 1); + alignment = lim->discard_granularity + lim->discard_alignment - alignment; + return sector_div(alignment, lim->discard_granularity); } static inline int bdev_discard_alignment(struct block_device *bdev) -- cgit v1.2.3