linux_dsm_epyc7002/fs/io-wq.h
Xiaoguang Wang b1442adcd9 io_uring: fix io_wqe->work_list corruption
commit 0020ef04e48571a88d4f482ad08f71052c5c5a08 upstream.

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>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-12-30 11:54:03 +01:00

159 lines
3.7 KiB
C

#ifndef INTERNAL_IO_WQ_H
#define INTERNAL_IO_WQ_H
#include <linux/io_uring.h>
struct io_wq;
enum {
IO_WQ_WORK_CANCEL = 1,
IO_WQ_WORK_HASHED = 2,
IO_WQ_WORK_UNBOUND = 4,
IO_WQ_WORK_NO_CANCEL = 8,
IO_WQ_WORK_CONCURRENT = 16,
IO_WQ_WORK_FILES = 32,
IO_WQ_WORK_FS = 64,
IO_WQ_WORK_MM = 128,
IO_WQ_WORK_CREDS = 256,
IO_WQ_WORK_BLKCG = 512,
IO_WQ_WORK_FSIZE = 1024,
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;
}
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)
struct io_wq_work {
struct io_wq_work_node list;
struct io_identity *identity;
unsigned flags;
};
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 void (free_work_fn)(struct io_wq_work *);
typedef struct io_wq_work *(io_wq_work_fn)(struct io_wq_work *);
struct io_wq_data {
struct user_struct *user;
io_wq_work_fn *do_work;
free_work_fn *free_work;
};
struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data);
bool io_wq_get(struct io_wq *wq, struct io_wq_data *data);
void io_wq_destroy(struct io_wq *wq);
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;
}
void io_wq_cancel_all(struct io_wq *wq);
enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork);
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);
struct task_struct *io_wq_get_task(struct io_wq *wq);
#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
static inline bool io_wq_current_is_worker(void)
{
return in_task() && (current->flags & PF_IO_WORKER);
}
#endif