linux/block/blk-mq.h
Akinobu Mita 5778322e67 blk-mq: avoid inserting requests before establishing new mapping
Notifier callbacks for CPU_ONLINE action can be run on the other CPU
than the CPU which was just onlined.  So it is possible for the
process running on the just onlined CPU to insert request and run
hw queue before establishing new mapping which is done by
blk_mq_queue_reinit_notify().

This can cause a problem when the CPU has just been onlined first time
since the request queue was initialized.  At this time ctx->index_hw
for the CPU, which is the index in hctx->ctxs[] for this ctx, is still
zero before blk_mq_queue_reinit_notify() is called by notifier
callbacks for CPU_ONLINE action.

For example, there is a single hw queue (hctx) and two CPU queues
(ctx0 for CPU0, and ctx1 for CPU1).  Now CPU1 is just onlined and
a request is inserted into ctx1->rq_list and set bit0 in pending
bitmap as ctx1->index_hw is still zero.

And then while running hw queue, flush_busy_ctxs() finds bit0 is set
in pending bitmap and tries to retrieve requests in
hctx->ctxs[0]->rq_list.  But htx->ctxs[0] is a pointer to ctx0, so the
request in ctx1->rq_list is ignored.

Fix it by ensuring that new mapping is established before onlined cpu
starts running.

Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Reviewed-by: Ming Lei <tom.leiming@gmail.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Ming Lei <tom.leiming@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
2015-09-29 11:32:50 -06:00

128 lines
3.4 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_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);
void blk_mq_wake_waiters(struct request_queue *q);
/*
* 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,
const struct cpumask *online_mask);
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);
extern void blk_mq_rq_timed_out(struct request *req, bool reserved);
void blk_mq_release(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;
}
static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx)
{
return hctx->nr_ctx && hctx->tags;
}
#endif