kernel-ark/block/blk-mq.h
Tejun Heo 780db2071a blk-mq: decouble blk-mq freezing from generic bypassing
blk_mq freezing is entangled with generic bypassing which bypasses
blkcg and io scheduler and lets IO requests fall through the block
layer to the drivers in FIFO order.  This allows forward progress on
IOs with the advanced features disabled so that those features can be
configured or altered without worrying about stalling IO which may
lead to deadlock through memory allocation.

However, generic bypassing doesn't quite fit blk-mq.  blk-mq currently
doesn't make use of blkcg or ioscheds and it maps bypssing to
freezing, which blocks request processing and drains all the in-flight
ones.  This causes problems as bypassing assumes that request
processing is online.  blk-mq works around this by conditionally
allowing request processing for the problem case - during queue
initialization.

Another weirdity is that except for during queue cleanup, bypassing
started on the generic side prevents blk-mq from processing new
requests but doesn't drain the in-flight ones.  This shouldn't break
anything but again highlights that something isn't quite right here.

The root cause is conflating blk-mq freezing and generic bypassing
which are two different mechanisms.  The only intersecting purpose
that they serve is during queue cleanup.  Let's properly separate
blk-mq freezing from generic bypassing and simply use it where
necessary.

* request_queue->mq_freeze_depth is added and
  blk_mq_[un]freeze_queue() now operate on this counter instead of
  ->bypass_depth.  The replacement for QUEUE_FLAG_BYPASS isn't added
  but the counter is tested directly.  This will be further updated by
  later changes.

* blk_mq_drain_queue() is dropped and "__" prefix is dropped from
  blk_mq_freeze_queue().  Queue cleanup path now calls
  blk_mq_freeze_queue() directly.

* blk_queue_enter()'s fast path condition is simplified to simply
  check @q->mq_freeze_depth.  Previously, the condition was

	!blk_queue_dying(q) &&
	    (!blk_queue_bypass(q) || !blk_queue_init_done(q))

  mq_freeze_depth is incremented right after dying is set and
  blk_queue_init_done() exception isn't necessary as blk-mq doesn't
  start frozen, which only leaves the blk_queue_bypass() test which
  can be replaced by @q->mq_freeze_depth test.

This change simplifies the code and reduces confusion in the area.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Nicholas A. Bellinger <nab@linux-iscsi.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
2014-07-01 10:31:13 -06:00

118 lines
3.1 KiB
C

#ifndef INT_BLK_MQ_H
#define INT_BLK_MQ_H
struct blk_mq_tag_set;
struct blk_mq_ctx {
struct {
spinlock_t lock;
struct list_head rq_list;
} ____cacheline_aligned_in_smp;
unsigned int cpu;
unsigned int index_hw;
unsigned int last_tag ____cacheline_aligned_in_smp;
/* incremented at dispatch time */
unsigned long rq_dispatched[2];
unsigned long rq_merged;
/* incremented at completion time */
unsigned long ____cacheline_aligned_in_smp rq_completed[2];
struct request_queue *queue;
struct kobject kobj;
} ____cacheline_aligned_in_smp;
void __blk_mq_complete_request(struct request *rq);
void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
void blk_mq_init_flush(struct request_queue *q);
void blk_mq_freeze_queue(struct request_queue *q);
void blk_mq_free_queue(struct request_queue *q);
void blk_mq_clone_flush_request(struct request *flush_rq,
struct request *orig_rq);
int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
/*
* CPU hotplug helpers
*/
struct blk_mq_cpu_notifier;
void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier,
int (*fn)(void *, unsigned long, unsigned int),
void *data);
void blk_mq_register_cpu_notifier(struct blk_mq_cpu_notifier *notifier);
void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier);
void blk_mq_cpu_init(void);
void blk_mq_enable_hotplug(void);
void blk_mq_disable_hotplug(void);
/*
* CPU -> queue mappings
*/
extern unsigned int *blk_mq_make_queue_map(struct blk_mq_tag_set *set);
extern int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues);
extern int blk_mq_hw_queue_to_node(unsigned int *map, unsigned int);
/*
* sysfs helpers
*/
extern int blk_mq_sysfs_register(struct request_queue *q);
extern void blk_mq_sysfs_unregister(struct request_queue *q);
/*
* Basic implementation of sparser bitmap, allowing the user to spread
* the bits over more cachelines.
*/
struct blk_align_bitmap {
unsigned long word;
unsigned long depth;
} ____cacheline_aligned_in_smp;
static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
unsigned int cpu)
{
return per_cpu_ptr(q->queue_ctx, cpu);
}
/*
* This assumes per-cpu software queueing queues. They could be per-node
* as well, for instance. For now this is hardcoded as-is. Note that we don't
* care about preemption, since we know the ctx's are persistent. This does
* mean that we can't rely on ctx always matching the currently running CPU.
*/
static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q)
{
return __blk_mq_get_ctx(q, get_cpu());
}
static inline void blk_mq_put_ctx(struct blk_mq_ctx *ctx)
{
put_cpu();
}
struct blk_mq_alloc_data {
/* input parameter */
struct request_queue *q;
gfp_t gfp;
bool reserved;
/* input & output parameter */
struct blk_mq_ctx *ctx;
struct blk_mq_hw_ctx *hctx;
};
static inline void blk_mq_set_alloc_data(struct blk_mq_alloc_data *data,
struct request_queue *q, gfp_t gfp, bool reserved,
struct blk_mq_ctx *ctx,
struct blk_mq_hw_ctx *hctx)
{
data->q = q;
data->gfp = gfp;
data->reserved = reserved;
data->ctx = ctx;
data->hctx = hctx;
}
#endif