linux/fs/io-wq.h

158 lines
3.6 KiB
C
Raw Normal View History

2019-10-22 16:25:58 +00:00
#ifndef INTERNAL_IO_WQ_H
#define INTERNAL_IO_WQ_H
#include <linux/refcount.h>
2019-10-22 16:25:58 +00:00
struct io_wq;
enum {
IO_WQ_WORK_CANCEL = 1,
IO_WQ_WORK_HASHED = 2,
IO_WQ_WORK_UNBOUND = 4,
IO_WQ_WORK_CONCURRENT = 16,
2019-10-22 16:25:58 +00:00
IO_WQ_HASH_SHIFT = 24, /* upper 8 bits are used for hash key */
};
enum io_wq_cancel {
IO_WQ_CANCEL_OK, /* cancelled before started */
IO_WQ_CANCEL_RUNNING, /* found, running, and attempted cancelled */
IO_WQ_CANCEL_NOTFOUND, /* work not found */
};
struct io_wq_work_node {
struct io_wq_work_node *next;
};
struct io_wq_work_list {
struct io_wq_work_node *first;
struct io_wq_work_node *last;
};
static inline void wq_list_add_after(struct io_wq_work_node *node,
struct io_wq_work_node *pos,
struct io_wq_work_list *list)
{
struct io_wq_work_node *next = pos->next;
pos->next = node;
node->next = next;
if (!next)
list->last = node;
}
static inline void wq_list_add_tail(struct io_wq_work_node *node,
struct io_wq_work_list *list)
{
if (!list->first) {
list->last = node;
WRITE_ONCE(list->first, node);
} else {
list->last->next = node;
list->last = node;
}
io_uring: fix io_wqe->work_list corruption For the first time a req punted to io-wq, we'll initialize io_wq_work's list to be NULL, then insert req to io_wqe->work_list. If this req is not inserted into tail of io_wqe->work_list, this req's io_wq_work list will point to another req's io_wq_work. For splitted bio case, this req maybe inserted to io_wqe->work_list repeatedly, once we insert it to tail of io_wqe->work_list for the second time, now io_wq_work->list->next will be invalid pointer, which then result in many strang error, panic, kernel soft-lockup, rcu stall, etc. In my vm, kernel doest not have commit cc29e1bf0d63f7 ("block: disable iopoll for split bio"), below fio job can reproduce this bug steadily: [global] name=iouring-sqpoll-iopoll-1 ioengine=io_uring iodepth=128 numjobs=1 thread rw=randread direct=1 registerfiles=1 hipri=1 bs=4m size=100M runtime=120 time_based group_reporting randrepeat=0 [device] directory=/home/feiman.wxg/mntpoint/ # an ext4 mount point If we have commit cc29e1bf0d63f7 ("block: disable iopoll for split bio"), there will no splitted bio case for polled io, but I think we still to need to fix this list corruption, it also should maybe go to stable branchs. To fix this corruption, if a req is inserted into tail of io_wqe->work_list, initialize req->io_wq_work->list->next to bu NULL. Cc: stable@vger.kernel.org Signed-off-by: Xiaoguang Wang <xiaoguang.wang@linux.alibaba.com> Reviewed-by: Pavel Begunkov <asml.silence@gmail.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-12-18 07:26:48 +00:00
node->next = NULL;
}
static inline void wq_list_cut(struct io_wq_work_list *list,
struct io_wq_work_node *last,
struct io_wq_work_node *prev)
{
/* first in the list, if prev==NULL */
if (!prev)
WRITE_ONCE(list->first, last->next);
else
prev->next = last->next;
if (last == list->last)
list->last = prev;
last->next = NULL;
}
static inline void wq_list_del(struct io_wq_work_list *list,
struct io_wq_work_node *node,
struct io_wq_work_node *prev)
{
wq_list_cut(list, node, prev);
}
#define wq_list_for_each(pos, prv, head) \
for (pos = (head)->first, prv = NULL; pos; prv = pos, pos = (pos)->next)
#define wq_list_empty(list) (READ_ONCE((list)->first) == NULL)
#define INIT_WQ_LIST(list) do { \
(list)->first = NULL; \
(list)->last = NULL; \
} while (0)
2019-10-22 16:25:58 +00:00
struct io_wq_work {
struct io_wq_work_node list;
const struct cred *creds;
unsigned flags;
2019-10-22 16:25:58 +00:00
};
static inline struct io_wq_work *wq_next_work(struct io_wq_work *work)
{
if (!work->list.next)
return NULL;
return container_of(work->list.next, struct io_wq_work, list);
}
typedef struct io_wq_work *(free_work_fn)(struct io_wq_work *);
typedef void (io_wq_work_fn)(struct io_wq_work *);
struct io_wq_hash {
refcount_t refs;
unsigned long map;
struct wait_queue_head wait;
};
static inline void io_wq_put_hash(struct io_wq_hash *hash)
{
if (refcount_dec_and_test(&hash->refs))
kfree(hash);
}
struct io_wq_data {
struct io_wq_hash *hash;
io_wq_work_fn *do_work;
free_work_fn *free_work;
};
struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data);
void io_wq_put(struct io_wq *wq);
void io_wq_put_and_exit(struct io_wq *wq);
2019-10-22 16:25:58 +00:00
void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work);
void io_wq_hash_work(struct io_wq_work *work, void *val);
static inline bool io_wq_is_hashed(struct io_wq_work *work)
{
return work->flags & IO_WQ_WORK_HASHED;
}
2019-10-22 16:25:58 +00:00
typedef bool (work_cancel_fn)(struct io_wq_work *, void *);
enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel,
void *data, bool cancel_all);
2019-10-22 16:25:58 +00:00
#if defined(CONFIG_IO_WQ)
extern void io_wq_worker_sleeping(struct task_struct *);
extern void io_wq_worker_running(struct task_struct *);
#else
static inline void io_wq_worker_sleeping(struct task_struct *tsk)
{
}
static inline void io_wq_worker_running(struct task_struct *tsk)
{
}
#endif
2019-10-22 16:25:58 +00:00
static inline bool io_wq_current_is_worker(void)
{
return in_task() && (current->flags & PF_IO_WORKER) &&
current->pf_io_worker;
}
#endif