linux_dsm_epyc7002/block/blk-mq.h
Ming Lei c7e2d94b3d blk-mq: free hw queue's resource in hctx's release handler
Once blk_cleanup_queue() returns, tags shouldn't be used any more,
because blk_mq_free_tag_set() may be called. Commit 45a9c9d909
("blk-mq: Fix a use-after-free") fixes this issue exactly.

However, that commit introduces another issue. Before 45a9c9d909,
we are allowed to run queue during cleaning up queue if the queue's
kobj refcount is held. After that commit, queue can't be run during
queue cleaning up, otherwise oops can be triggered easily because
some fields of hctx are freed by blk_mq_free_queue() in blk_cleanup_queue().

We have invented ways for addressing this kind of issue before, such as:

	8dc765d438 ("SCSI: fix queue cleanup race before queue initialization is done")
	c2856ae2f3 ("blk-mq: quiesce queue before freeing queue")

But still can't cover all cases, recently James reports another such
kind of issue:

	https://marc.info/?l=linux-scsi&m=155389088124782&w=2

This issue can be quite hard to address by previous way, given
scsi_run_queue() may run requeues for other LUNs.

Fixes the above issue by freeing hctx's resources in its release handler, and this
way is safe becasue tags isn't needed for freeing such hctx resource.

This approach follows typical design pattern wrt. kobject's release handler.

Cc: Dongli Zhang <dongli.zhang@oracle.com>
Cc: James Smart <james.smart@broadcom.com>
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Cc: linux-scsi@vger.kernel.org,
Cc: Martin K . Petersen <martin.petersen@oracle.com>,
Cc: Christoph Hellwig <hch@lst.de>,
Cc: James E . J . Bottomley <jejb@linux.vnet.ibm.com>,
Reported-by: James Smart <james.smart@broadcom.com>
Fixes: 45a9c9d909 ("blk-mq: Fix a use-after-free")
Cc: stable@vger.kernel.org
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-05-04 07:24:05 -06:00

242 lines
6.5 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef INT_BLK_MQ_H
#define INT_BLK_MQ_H
#include "blk-stat.h"
#include "blk-mq-tag.h"
struct blk_mq_tag_set;
struct blk_mq_ctxs {
struct kobject kobj;
struct blk_mq_ctx __percpu *queue_ctx;
};
/**
* struct blk_mq_ctx - State for a software queue facing the submitting CPUs
*/
struct blk_mq_ctx {
struct {
spinlock_t lock;
struct list_head rq_lists[HCTX_MAX_TYPES];
} ____cacheline_aligned_in_smp;
unsigned int cpu;
unsigned short index_hw[HCTX_MAX_TYPES];
struct blk_mq_hw_ctx *hctxs[HCTX_MAX_TYPES];
/* 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 blk_mq_ctxs *ctxs;
struct kobject kobj;
} ____cacheline_aligned_in_smp;
void blk_mq_exit_queue(struct request_queue *q);
int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
void blk_mq_wake_waiters(struct request_queue *q);
bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *, bool);
void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
bool kick_requeue_list);
void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
bool blk_mq_get_driver_tag(struct request *rq);
struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
struct blk_mq_ctx *start);
/*
* Internal helpers for allocating/freeing the request map
*/
void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
unsigned int hctx_idx);
void blk_mq_free_rq_map(struct blk_mq_tags *tags);
struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
unsigned int hctx_idx,
unsigned int nr_tags,
unsigned int reserved_tags);
int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
unsigned int hctx_idx, unsigned int depth);
/*
* Internal helpers for request insertion into sw queues
*/
void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
bool at_head);
void blk_mq_request_bypass_insert(struct request *rq, bool run_queue);
void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
struct list_head *list);
/* Used by blk_insert_cloned_request() to issue request directly */
blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last);
void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
struct list_head *list);
/*
* CPU -> queue mappings
*/
extern int blk_mq_hw_queue_to_node(struct blk_mq_queue_map *qmap, unsigned int);
/*
* blk_mq_map_queue_type() - map (hctx_type,cpu) to hardware queue
* @q: request queue
* @type: the hctx type index
* @cpu: CPU
*/
static inline struct blk_mq_hw_ctx *blk_mq_map_queue_type(struct request_queue *q,
enum hctx_type type,
unsigned int cpu)
{
return q->queue_hw_ctx[q->tag_set->map[type].mq_map[cpu]];
}
/*
* blk_mq_map_queue() - map (cmd_flags,type) to hardware queue
* @q: request queue
* @flags: request command flags
* @cpu: cpu ctx
*/
static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
unsigned int flags,
struct blk_mq_ctx *ctx)
{
enum hctx_type type = HCTX_TYPE_DEFAULT;
/*
* The caller ensure that if REQ_HIPRI, poll must be enabled.
*/
if (flags & REQ_HIPRI)
type = HCTX_TYPE_POLL;
else if ((flags & REQ_OP_MASK) == REQ_OP_READ)
type = HCTX_TYPE_READ;
return ctx->hctxs[type];
}
/*
* sysfs helpers
*/
extern void blk_mq_sysfs_init(struct request_queue *q);
extern void blk_mq_sysfs_deinit(struct request_queue *q);
extern int __blk_mq_register_dev(struct device *dev, struct request_queue *q);
extern int blk_mq_sysfs_register(struct request_queue *q);
extern void blk_mq_sysfs_unregister(struct request_queue *q);
extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
void blk_mq_release(struct request_queue *q);
/**
* blk_mq_rq_state() - read the current MQ_RQ_* state of a request
* @rq: target request.
*/
static inline enum mq_rq_state blk_mq_rq_state(struct request *rq)
{
return READ_ONCE(rq->state);
}
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;
blk_mq_req_flags_t flags;
unsigned int shallow_depth;
unsigned int cmd_flags;
/* input & output parameter */
struct blk_mq_ctx *ctx;
struct blk_mq_hw_ctx *hctx;
};
static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data)
{
if (data->flags & BLK_MQ_REQ_INTERNAL)
return data->hctx->sched_tags;
return data->hctx->tags;
}
static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx)
{
return test_bit(BLK_MQ_S_STOPPED, &hctx->state);
}
static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx)
{
return hctx->nr_ctx && hctx->tags;
}
unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part);
void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
unsigned int inflight[2]);
static inline void blk_mq_put_dispatch_budget(struct blk_mq_hw_ctx *hctx)
{
struct request_queue *q = hctx->queue;
if (q->mq_ops->put_budget)
q->mq_ops->put_budget(hctx);
}
static inline bool blk_mq_get_dispatch_budget(struct blk_mq_hw_ctx *hctx)
{
struct request_queue *q = hctx->queue;
if (q->mq_ops->get_budget)
return q->mq_ops->get_budget(hctx);
return true;
}
static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
struct request *rq)
{
blk_mq_put_tag(hctx, hctx->tags, rq->mq_ctx, rq->tag);
rq->tag = -1;
if (rq->rq_flags & RQF_MQ_INFLIGHT) {
rq->rq_flags &= ~RQF_MQ_INFLIGHT;
atomic_dec(&hctx->nr_active);
}
}
static inline void blk_mq_put_driver_tag(struct request *rq)
{
if (rq->tag == -1 || rq->internal_tag == -1)
return;
__blk_mq_put_driver_tag(rq->mq_hctx, rq);
}
static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap)
{
int cpu;
for_each_possible_cpu(cpu)
qmap->mq_map[cpu] = 0;
}
#endif