linux_dsm_epyc7002/block/blk.h
Yufen Yu 8d6996630c block: fix null pointer dereference in blk_mq_rq_timed_out()
We got a null pointer deference BUG_ON in blk_mq_rq_timed_out()
as following:

[  108.825472] BUG: kernel NULL pointer dereference, address: 0000000000000040
[  108.827059] PGD 0 P4D 0
[  108.827313] Oops: 0000 [#1] SMP PTI
[  108.827657] CPU: 6 PID: 198 Comm: kworker/6:1H Not tainted 5.3.0-rc8+ #431
[  108.829503] Workqueue: kblockd blk_mq_timeout_work
[  108.829913] RIP: 0010:blk_mq_check_expired+0x258/0x330
[  108.838191] Call Trace:
[  108.838406]  bt_iter+0x74/0x80
[  108.838665]  blk_mq_queue_tag_busy_iter+0x204/0x450
[  108.839074]  ? __switch_to_asm+0x34/0x70
[  108.839405]  ? blk_mq_stop_hw_queue+0x40/0x40
[  108.839823]  ? blk_mq_stop_hw_queue+0x40/0x40
[  108.840273]  ? syscall_return_via_sysret+0xf/0x7f
[  108.840732]  blk_mq_timeout_work+0x74/0x200
[  108.841151]  process_one_work+0x297/0x680
[  108.841550]  worker_thread+0x29c/0x6f0
[  108.841926]  ? rescuer_thread+0x580/0x580
[  108.842344]  kthread+0x16a/0x1a0
[  108.842666]  ? kthread_flush_work+0x170/0x170
[  108.843100]  ret_from_fork+0x35/0x40

The bug is caused by the race between timeout handle and completion for
flush request.

When timeout handle function blk_mq_rq_timed_out() try to read
'req->q->mq_ops', the 'req' have completed and reinitiated by next
flush request, which would call blk_rq_init() to clear 'req' as 0.

After commit 12f5b93145 ("blk-mq: Remove generation seqeunce"),
normal requests lifetime are protected by refcount. Until 'rq->ref'
drop to zero, the request can really be free. Thus, these requests
cannot been reused before timeout handle finish.

However, flush request has defined .end_io and rq->end_io() is still
called even if 'rq->ref' doesn't drop to zero. After that, the 'flush_rq'
can be reused by the next flush request handle, resulting in null
pointer deference BUG ON.

We fix this problem by covering flush request with 'rq->ref'.
If the refcount is not zero, flush_end_io() return and wait the
last holder recall it. To record the request status, we add a new
entry 'rq_status', which will be used in flush_end_io().

Cc: Christoph Hellwig <hch@infradead.org>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: stable@vger.kernel.org # v4.18+
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Bob Liu <bob.liu@oracle.com>
Signed-off-by: Yufen Yu <yuyufen@huawei.com>

-------
v2:
 - move rq_status from struct request to struct blk_flush_queue
v3:
 - remove unnecessary '{}' pair.
v4:
 - let spinlock to protect 'fq->rq_status'
v5:
 - move rq_status after flush_running_idx member of struct blk_flush_queue
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-09-27 07:01:25 -06:00

356 lines
11 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef BLK_INTERNAL_H
#define BLK_INTERNAL_H
#include <linux/idr.h>
#include <linux/blk-mq.h>
#include <xen/xen.h>
#include "blk-mq.h"
#include "blk-mq-sched.h"
/* Max future timer expiry for timeouts */
#define BLK_MAX_TIMEOUT (5 * HZ)
#ifdef CONFIG_DEBUG_FS
extern struct dentry *blk_debugfs_root;
#endif
struct blk_flush_queue {
unsigned int flush_queue_delayed:1;
unsigned int flush_pending_idx:1;
unsigned int flush_running_idx:1;
blk_status_t rq_status;
unsigned long flush_pending_since;
struct list_head flush_queue[2];
struct list_head flush_data_in_flight;
struct request *flush_rq;
/*
* flush_rq shares tag with this rq, both can't be active
* at the same time
*/
struct request *orig_rq;
spinlock_t mq_flush_lock;
};
extern struct kmem_cache *blk_requestq_cachep;
extern struct kobj_type blk_queue_ktype;
extern struct ida blk_queue_ida;
static inline struct blk_flush_queue *
blk_get_flush_queue(struct request_queue *q, struct blk_mq_ctx *ctx)
{
return blk_mq_map_queue(q, REQ_OP_FLUSH, ctx)->fq;
}
static inline void __blk_get_queue(struct request_queue *q)
{
kobject_get(&q->kobj);
}
static inline bool
is_flush_rq(struct request *req, struct blk_mq_hw_ctx *hctx)
{
return hctx->fq->flush_rq == req;
}
struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q,
int node, int cmd_size, gfp_t flags);
void blk_free_flush_queue(struct blk_flush_queue *q);
void blk_freeze_queue(struct request_queue *q);
static inline void blk_queue_enter_live(struct request_queue *q)
{
/*
* Given that running in generic_make_request() context
* guarantees that a live reference against q_usage_counter has
* been established, further references under that same context
* need not check that the queue has been frozen (marked dead).
*/
percpu_ref_get(&q->q_usage_counter);
}
static inline bool biovec_phys_mergeable(struct request_queue *q,
struct bio_vec *vec1, struct bio_vec *vec2)
{
unsigned long mask = queue_segment_boundary(q);
phys_addr_t addr1 = page_to_phys(vec1->bv_page) + vec1->bv_offset;
phys_addr_t addr2 = page_to_phys(vec2->bv_page) + vec2->bv_offset;
if (addr1 + vec1->bv_len != addr2)
return false;
if (xen_domain() && !xen_biovec_phys_mergeable(vec1, vec2->bv_page))
return false;
if ((addr1 | mask) != ((addr2 + vec2->bv_len - 1) | mask))
return false;
return true;
}
static inline bool __bvec_gap_to_prev(struct request_queue *q,
struct bio_vec *bprv, unsigned int offset)
{
return (offset & queue_virt_boundary(q)) ||
((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q));
}
/*
* Check if adding a bio_vec after bprv with offset would create a gap in
* the SG list. Most drivers don't care about this, but some do.
*/
static inline bool bvec_gap_to_prev(struct request_queue *q,
struct bio_vec *bprv, unsigned int offset)
{
if (!queue_virt_boundary(q))
return false;
return __bvec_gap_to_prev(q, bprv, offset);
}
static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio,
unsigned int nr_segs)
{
rq->nr_phys_segments = nr_segs;
rq->__data_len = bio->bi_iter.bi_size;
rq->bio = rq->biotail = bio;
rq->ioprio = bio_prio(bio);
if (bio->bi_disk)
rq->rq_disk = bio->bi_disk;
}
#ifdef CONFIG_BLK_DEV_INTEGRITY
void blk_flush_integrity(void);
bool __bio_integrity_endio(struct bio *);
static inline bool bio_integrity_endio(struct bio *bio)
{
if (bio_integrity(bio))
return __bio_integrity_endio(bio);
return true;
}
static inline bool integrity_req_gap_back_merge(struct request *req,
struct bio *next)
{
struct bio_integrity_payload *bip = bio_integrity(req->bio);
struct bio_integrity_payload *bip_next = bio_integrity(next);
return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1],
bip_next->bip_vec[0].bv_offset);
}
static inline bool integrity_req_gap_front_merge(struct request *req,
struct bio *bio)
{
struct bio_integrity_payload *bip = bio_integrity(bio);
struct bio_integrity_payload *bip_next = bio_integrity(req->bio);
return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1],
bip_next->bip_vec[0].bv_offset);
}
#else /* CONFIG_BLK_DEV_INTEGRITY */
static inline bool integrity_req_gap_back_merge(struct request *req,
struct bio *next)
{
return false;
}
static inline bool integrity_req_gap_front_merge(struct request *req,
struct bio *bio)
{
return false;
}
static inline void blk_flush_integrity(void)
{
}
static inline bool bio_integrity_endio(struct bio *bio)
{
return true;
}
#endif /* CONFIG_BLK_DEV_INTEGRITY */
unsigned long blk_rq_timeout(unsigned long timeout);
void blk_add_timer(struct request *req);
bool bio_attempt_front_merge(struct request *req, struct bio *bio,
unsigned int nr_segs);
bool bio_attempt_back_merge(struct request *req, struct bio *bio,
unsigned int nr_segs);
bool bio_attempt_discard_merge(struct request_queue *q, struct request *req,
struct bio *bio);
bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
unsigned int nr_segs, struct request **same_queue_rq);
void blk_account_io_start(struct request *req, bool new_io);
void blk_account_io_completion(struct request *req, unsigned int bytes);
void blk_account_io_done(struct request *req, u64 now);
/*
* Internal elevator interface
*/
#define ELV_ON_HASH(rq) ((rq)->rq_flags & RQF_HASHED)
void blk_insert_flush(struct request *rq);
void elevator_init_mq(struct request_queue *q);
int elevator_switch_mq(struct request_queue *q,
struct elevator_type *new_e);
void __elevator_exit(struct request_queue *, struct elevator_queue *);
int elv_register_queue(struct request_queue *q, bool uevent);
void elv_unregister_queue(struct request_queue *q);
static inline void elevator_exit(struct request_queue *q,
struct elevator_queue *e)
{
lockdep_assert_held(&q->sysfs_lock);
blk_mq_sched_free_requests(q);
__elevator_exit(q, e);
}
struct hd_struct *__disk_get_part(struct gendisk *disk, int partno);
#ifdef CONFIG_FAIL_IO_TIMEOUT
int blk_should_fake_timeout(struct request_queue *);
ssize_t part_timeout_show(struct device *, struct device_attribute *, char *);
ssize_t part_timeout_store(struct device *, struct device_attribute *,
const char *, size_t);
#else
static inline int blk_should_fake_timeout(struct request_queue *q)
{
return 0;
}
#endif
void __blk_queue_split(struct request_queue *q, struct bio **bio,
unsigned int *nr_segs);
int ll_back_merge_fn(struct request *req, struct bio *bio,
unsigned int nr_segs);
int ll_front_merge_fn(struct request *req, struct bio *bio,
unsigned int nr_segs);
struct request *attempt_back_merge(struct request_queue *q, struct request *rq);
struct request *attempt_front_merge(struct request_queue *q, struct request *rq);
int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
struct request *next);
unsigned int blk_recalc_rq_segments(struct request *rq);
void blk_rq_set_mixed_merge(struct request *rq);
bool blk_rq_merge_ok(struct request *rq, struct bio *bio);
enum elv_merge blk_try_merge(struct request *rq, struct bio *bio);
int blk_dev_init(void);
/*
* Contribute to IO statistics IFF:
*
* a) it's attached to a gendisk, and
* b) the queue had IO stats enabled when this request was started, and
* c) it's a file system request
*/
static inline bool blk_do_io_stat(struct request *rq)
{
return rq->rq_disk &&
(rq->rq_flags & RQF_IO_STAT) &&
!blk_rq_is_passthrough(rq);
}
static inline void req_set_nomerge(struct request_queue *q, struct request *req)
{
req->cmd_flags |= REQ_NOMERGE;
if (req == q->last_merge)
q->last_merge = NULL;
}
/*
* The max size one bio can handle is UINT_MAX becasue bvec_iter.bi_size
* is defined as 'unsigned int', meantime it has to aligned to with logical
* block size which is the minimum accepted unit by hardware.
*/
static inline unsigned int bio_allowed_max_sectors(struct request_queue *q)
{
return round_down(UINT_MAX, queue_logical_block_size(q)) >> 9;
}
/*
* Internal io_context interface
*/
void get_io_context(struct io_context *ioc);
struct io_cq *ioc_lookup_icq(struct io_context *ioc, struct request_queue *q);
struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q,
gfp_t gfp_mask);
void ioc_clear_queue(struct request_queue *q);
int create_task_io_context(struct task_struct *task, gfp_t gfp_mask, int node);
/**
* create_io_context - try to create task->io_context
* @gfp_mask: allocation mask
* @node: allocation node
*
* If %current->io_context is %NULL, allocate a new io_context and install
* it. Returns the current %current->io_context which may be %NULL if
* allocation failed.
*
* Note that this function can't be called with IRQ disabled because
* task_lock which protects %current->io_context is IRQ-unsafe.
*/
static inline struct io_context *create_io_context(gfp_t gfp_mask, int node)
{
WARN_ON_ONCE(irqs_disabled());
if (unlikely(!current->io_context))
create_task_io_context(current, gfp_mask, node);
return current->io_context;
}
/*
* Internal throttling interface
*/
#ifdef CONFIG_BLK_DEV_THROTTLING
extern void blk_throtl_drain(struct request_queue *q);
extern int blk_throtl_init(struct request_queue *q);
extern void blk_throtl_exit(struct request_queue *q);
extern void blk_throtl_register_queue(struct request_queue *q);
#else /* CONFIG_BLK_DEV_THROTTLING */
static inline void blk_throtl_drain(struct request_queue *q) { }
static inline int blk_throtl_init(struct request_queue *q) { return 0; }
static inline void blk_throtl_exit(struct request_queue *q) { }
static inline void blk_throtl_register_queue(struct request_queue *q) { }
#endif /* CONFIG_BLK_DEV_THROTTLING */
#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
extern ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page);
extern ssize_t blk_throtl_sample_time_store(struct request_queue *q,
const char *page, size_t count);
extern void blk_throtl_bio_endio(struct bio *bio);
extern void blk_throtl_stat_add(struct request *rq, u64 time);
#else
static inline void blk_throtl_bio_endio(struct bio *bio) { }
static inline void blk_throtl_stat_add(struct request *rq, u64 time) { }
#endif
#ifdef CONFIG_BOUNCE
extern int init_emergency_isa_pool(void);
extern void blk_queue_bounce(struct request_queue *q, struct bio **bio);
#else
static inline int init_emergency_isa_pool(void)
{
return 0;
}
static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio)
{
}
#endif /* CONFIG_BOUNCE */
#ifdef CONFIG_BLK_CGROUP_IOLATENCY
extern int blk_iolatency_init(struct request_queue *q);
#else
static inline int blk_iolatency_init(struct request_queue *q) { return 0; }
#endif
struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp);
#ifdef CONFIG_BLK_DEV_ZONED
void blk_queue_free_zone_bitmaps(struct request_queue *q);
#else
static inline void blk_queue_free_zone_bitmaps(struct request_queue *q) {}
#endif
#endif /* BLK_INTERNAL_H */