mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 13:55:32 +00:00
![Tejun Heo](/assets/img/avatar_default.png)
blk-mq uses percpu_ref for its usage counter which tracks the number of in-flight commands and used to synchronously drain the queue on freeze. percpu_ref shutdown takes measureable wallclock time as it involves a sched RCU grace period. This means that draining a blk-mq takes measureable wallclock time. One would think that this shouldn't matter as queue shutdown should be a rare event which takes place asynchronously w.r.t. userland. Unfortunately, SCSI probing involves synchronously setting up and then tearing down a lot of request_queues back-to-back for non-existent LUNs. This means that SCSI probing may take above ten seconds when scsi-mq is used. [ 0.949892] scsi host0: Virtio SCSI HBA [ 1.007864] scsi 0:0:0:0: Direct-Access QEMU QEMU HARDDISK 1.1. PQ: 0 ANSI: 5 [ 1.021299] scsi 0:0:1:0: Direct-Access QEMU QEMU HARDDISK 1.1. PQ: 0 ANSI: 5 [ 1.520356] tsc: Refined TSC clocksource calibration: 2491.910 MHz <stall> [ 16.186549] sd 0:0:0:0: Attached scsi generic sg0 type 0 [ 16.190478] sd 0:0:1:0: Attached scsi generic sg1 type 0 [ 16.194099] osd: LOADED open-osd 0.2.1 [ 16.203202] sd 0:0:0:0: [sda] 31457280 512-byte logical blocks: (16.1 GB/15.0 GiB) [ 16.208478] sd 0:0:0:0: [sda] Write Protect is off [ 16.211439] sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA [ 16.218771] sd 0:0:1:0: [sdb] 31457280 512-byte logical blocks: (16.1 GB/15.0 GiB) [ 16.223264] sd 0:0:1:0: [sdb] Write Protect is off [ 16.225682] sd 0:0:1:0: [sdb] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA This is also the reason why request_queues start in bypass mode which is ended on blk_register_queue() as shutting down a fully functional queue also involves a RCU grace period and the queues for non-existent SCSI devices never reach registration. blk-mq basically needs to do the same thing - start the mq in a degraded mode which is faster to shut down and then make it fully functional only after the queue reaches registration. percpu_ref recently grew facilities to force atomic operation until explicitly switched to percpu mode, which can be used for this purpose. This patch makes blk-mq initialize q->mq_usage_counter in atomic mode and switch it to percpu mode only once blk_register_queue() is reached. Note that this issue was previously worked around by0a30288da1
("blk-mq, percpu_ref: implement a kludge for SCSI blk-mq stall during probe") for v3.17. The temp fix was reverted in preparation of adding persistent atomic mode to percpu_ref by9eca80461a
("Revert "blk-mq, percpu_ref: implement a kludge for SCSI blk-mq stall during probe""). This patch and the prerequisite percpu_ref changes will be merged during v3.18 devel cycle. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Christoph Hellwig <hch@infradead.org> Link: http://lkml.kernel.org/g/20140919113815.GA10791@lst.de Fixes:add703fda9
("blk-mq: use percpu_ref for mq usage count") Reviewed-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Johannes Weiner <hannes@cmpxchg.org>
214 lines
5.8 KiB
C
214 lines
5.8 KiB
C
#ifndef BLK_MQ_H
|
|
#define BLK_MQ_H
|
|
|
|
#include <linux/blkdev.h>
|
|
|
|
struct blk_mq_tags;
|
|
|
|
struct blk_mq_cpu_notifier {
|
|
struct list_head list;
|
|
void *data;
|
|
int (*notify)(void *data, unsigned long action, unsigned int cpu);
|
|
};
|
|
|
|
struct blk_mq_ctxmap {
|
|
unsigned int map_size;
|
|
unsigned int bits_per_word;
|
|
struct blk_align_bitmap *map;
|
|
};
|
|
|
|
struct blk_mq_hw_ctx {
|
|
struct {
|
|
spinlock_t lock;
|
|
struct list_head dispatch;
|
|
} ____cacheline_aligned_in_smp;
|
|
|
|
unsigned long state; /* BLK_MQ_S_* flags */
|
|
struct delayed_work run_work;
|
|
struct delayed_work delay_work;
|
|
cpumask_var_t cpumask;
|
|
int next_cpu;
|
|
int next_cpu_batch;
|
|
|
|
unsigned long flags; /* BLK_MQ_F_* flags */
|
|
|
|
struct request_queue *queue;
|
|
unsigned int queue_num;
|
|
|
|
void *driver_data;
|
|
|
|
struct blk_mq_ctxmap ctx_map;
|
|
|
|
unsigned int nr_ctx;
|
|
struct blk_mq_ctx **ctxs;
|
|
|
|
atomic_t wait_index;
|
|
|
|
struct blk_mq_tags *tags;
|
|
|
|
unsigned long queued;
|
|
unsigned long run;
|
|
#define BLK_MQ_MAX_DISPATCH_ORDER 10
|
|
unsigned long dispatched[BLK_MQ_MAX_DISPATCH_ORDER];
|
|
|
|
unsigned int numa_node;
|
|
unsigned int cmd_size; /* per-request extra data */
|
|
|
|
atomic_t nr_active;
|
|
|
|
struct blk_mq_cpu_notifier cpu_notifier;
|
|
struct kobject kobj;
|
|
};
|
|
|
|
struct blk_mq_tag_set {
|
|
struct blk_mq_ops *ops;
|
|
unsigned int nr_hw_queues;
|
|
unsigned int queue_depth; /* max hw supported */
|
|
unsigned int reserved_tags;
|
|
unsigned int cmd_size; /* per-request extra data */
|
|
int numa_node;
|
|
unsigned int timeout;
|
|
unsigned int flags; /* BLK_MQ_F_* */
|
|
void *driver_data;
|
|
|
|
struct blk_mq_tags **tags;
|
|
|
|
struct mutex tag_list_lock;
|
|
struct list_head tag_list;
|
|
};
|
|
|
|
typedef int (queue_rq_fn)(struct blk_mq_hw_ctx *, struct request *);
|
|
typedef struct blk_mq_hw_ctx *(map_queue_fn)(struct request_queue *, const int);
|
|
typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int);
|
|
typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int);
|
|
typedef int (init_request_fn)(void *, struct request *, unsigned int,
|
|
unsigned int, unsigned int);
|
|
typedef void (exit_request_fn)(void *, struct request *, unsigned int,
|
|
unsigned int);
|
|
|
|
struct blk_mq_ops {
|
|
/*
|
|
* Queue request
|
|
*/
|
|
queue_rq_fn *queue_rq;
|
|
|
|
/*
|
|
* Map to specific hardware queue
|
|
*/
|
|
map_queue_fn *map_queue;
|
|
|
|
/*
|
|
* Called on request timeout
|
|
*/
|
|
rq_timed_out_fn *timeout;
|
|
|
|
softirq_done_fn *complete;
|
|
|
|
/*
|
|
* Called when the block layer side of a hardware queue has been
|
|
* set up, allowing the driver to allocate/init matching structures.
|
|
* Ditto for exit/teardown.
|
|
*/
|
|
init_hctx_fn *init_hctx;
|
|
exit_hctx_fn *exit_hctx;
|
|
|
|
/*
|
|
* Called for every command allocated by the block layer to allow
|
|
* the driver to set up driver specific data.
|
|
* Ditto for exit/teardown.
|
|
*/
|
|
init_request_fn *init_request;
|
|
exit_request_fn *exit_request;
|
|
};
|
|
|
|
enum {
|
|
BLK_MQ_RQ_QUEUE_OK = 0, /* queued fine */
|
|
BLK_MQ_RQ_QUEUE_BUSY = 1, /* requeue IO for later */
|
|
BLK_MQ_RQ_QUEUE_ERROR = 2, /* end IO with error */
|
|
|
|
BLK_MQ_F_SHOULD_MERGE = 1 << 0,
|
|
BLK_MQ_F_TAG_SHARED = 1 << 1,
|
|
BLK_MQ_F_SG_MERGE = 1 << 2,
|
|
BLK_MQ_F_SYSFS_UP = 1 << 3,
|
|
|
|
BLK_MQ_S_STOPPED = 0,
|
|
BLK_MQ_S_TAG_ACTIVE = 1,
|
|
|
|
BLK_MQ_MAX_DEPTH = 10240,
|
|
|
|
BLK_MQ_CPU_WORK_BATCH = 8,
|
|
};
|
|
|
|
struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *);
|
|
void blk_mq_finish_init(struct request_queue *q);
|
|
int blk_mq_register_disk(struct gendisk *);
|
|
void blk_mq_unregister_disk(struct gendisk *);
|
|
|
|
int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set);
|
|
void blk_mq_free_tag_set(struct blk_mq_tag_set *set);
|
|
|
|
void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
|
|
|
|
void blk_mq_insert_request(struct request *, bool, bool, bool);
|
|
void blk_mq_run_queues(struct request_queue *q, bool async);
|
|
void blk_mq_free_request(struct request *rq);
|
|
bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
|
|
struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
|
|
gfp_t gfp, bool reserved);
|
|
struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag);
|
|
|
|
struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_index);
|
|
struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_tag_set *, unsigned int, int);
|
|
|
|
void blk_mq_end_io(struct request *rq, int error);
|
|
void __blk_mq_end_io(struct request *rq, int error);
|
|
|
|
void blk_mq_requeue_request(struct request *rq);
|
|
void blk_mq_add_to_requeue_list(struct request *rq, bool at_head);
|
|
void blk_mq_kick_requeue_list(struct request_queue *q);
|
|
void blk_mq_complete_request(struct request *rq);
|
|
|
|
void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx);
|
|
void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx);
|
|
void blk_mq_stop_hw_queues(struct request_queue *q);
|
|
void blk_mq_start_hw_queues(struct request_queue *q);
|
|
void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
|
|
void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
|
|
void blk_mq_tag_busy_iter(struct blk_mq_tags *tags, void (*fn)(void *data, unsigned long *), void *data);
|
|
|
|
/*
|
|
* Driver command data is immediately after the request. So subtract request
|
|
* size to get back to the original request.
|
|
*/
|
|
static inline struct request *blk_mq_rq_from_pdu(void *pdu)
|
|
{
|
|
return pdu - sizeof(struct request);
|
|
}
|
|
static inline void *blk_mq_rq_to_pdu(struct request *rq)
|
|
{
|
|
return (void *) rq + sizeof(*rq);
|
|
}
|
|
|
|
#define queue_for_each_hw_ctx(q, hctx, i) \
|
|
for ((i) = 0; (i) < (q)->nr_hw_queues && \
|
|
({ hctx = (q)->queue_hw_ctx[i]; 1; }); (i)++)
|
|
|
|
#define queue_for_each_ctx(q, ctx, i) \
|
|
for ((i) = 0; (i) < (q)->nr_queues && \
|
|
({ ctx = per_cpu_ptr((q)->queue_ctx, (i)); 1; }); (i)++)
|
|
|
|
#define hctx_for_each_ctx(hctx, ctx, i) \
|
|
for ((i) = 0; (i) < (hctx)->nr_ctx && \
|
|
({ ctx = (hctx)->ctxs[(i)]; 1; }); (i)++)
|
|
|
|
#define blk_ctx_sum(q, sum) \
|
|
({ \
|
|
struct blk_mq_ctx *__x; \
|
|
unsigned int __ret = 0, __i; \
|
|
\
|
|
queue_for_each_ctx((q), __x, __i) \
|
|
__ret += sum; \
|
|
__ret; \
|
|
})
|
|
|
|
#endif
|