On 07/11/2020 21:18, Pavel Begunkov wrote:
> On 07/11/2020 21:16, Pavel Begunkov wrote:
>> SQPOLL task may find sqo_task->files == NULL, so
>> __io_sq_thread_acquire_files() would left it unset and so all the
>> following fails, e.g. attempts to submit. Fail if sqo_task doesn't have
>> files.
>
> Josef, could you try this one?
Hmm, as you said it happens often... IIUC there is a drawback with
SQPOLL -- after the creator process/thread exits most of subsequent
requests will start failing.
I'd say from application correctness POV such tasks should exit
only after their SQPOLL io_urings got killed.
>
>>
>> [ 118.962785] BUG: kernel NULL pointer dereference, address:
>> 0000000000000020
>> [ 118.963812] #PF: supervisor read access in kernel mode
>> [ 118.964534] #PF: error_code(0x0000) - not-present page
>> [ 118.969029] RIP: 0010:__fget_files+0xb/0x80
>> [ 119.005409] Call Trace:
>> [ 119.005651] fget_many+0x2b/0x30
>> [ 119.005964] io_file_get+0xcf/0x180
>> [ 119.006315] io_submit_sqes+0x3a4/0x950
>> [ 119.006678] ? io_double_put_req+0x43/0x70
>> [ 119.007054] ? io_async_task_func+0xc2/0x180
>> [ 119.007481] io_sq_thread+0x1de/0x6a0
>> [ 119.007828] kthread+0x114/0x150
>> [ 119.008135] ? __ia32_sys_io_uring_enter+0x3c0/0x3c0
>> [ 119.008623] ? kthread_park+0x90/0x90
>> [ 119.008963] ret_from_fork+0x22/0x30
>>
>> Reported-by: Josef Grieb <josef.grieb@xxxxxxxxx>
>> Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
>> ---
>> fs/io_uring.c | 19 ++++++++++++-------
>> 1 file changed, 12 insertions(+), 7 deletions(-)
>>
>> diff --git a/fs/io_uring.c b/fs/io_uring.c
>> index 8d721a652d61..9c035c5c4080 100644
>> --- a/fs/io_uring.c
>> +++ b/fs/io_uring.c
>> @@ -1080,7 +1080,7 @@ static void io_sq_thread_drop_mm_files(void)
>> }
>> }
>>
>> -static void __io_sq_thread_acquire_files(struct io_ring_ctx *ctx)
>> +static int __io_sq_thread_acquire_files(struct io_ring_ctx *ctx)
>> {
>> if (!current->files) {
>> struct files_struct *files;
>> @@ -1091,7 +1091,7 @@ static void __io_sq_thread_acquire_files(struct io_ring_ctx *ctx)
>> files = ctx->sqo_task->files;
>> if (!files) {
>> task_unlock(ctx->sqo_task);
>> - return;
>> + return -EFAULT;
>> }
>> atomic_inc(&files->count);
>> get_nsproxy(ctx->sqo_task->nsproxy);
>> @@ -1105,6 +1105,7 @@ static void __io_sq_thread_acquire_files(struct io_ring_ctx *ctx)
>> current->thread_pid = thread_pid;
>> task_unlock(current);
>> }
>> + return 0;
>> }
>>
>> static int __io_sq_thread_acquire_mm(struct io_ring_ctx *ctx)
>> @@ -1136,15 +1137,19 @@ static int io_sq_thread_acquire_mm_files(struct io_ring_ctx *ctx,
>> struct io_kiocb *req)
>> {
>> const struct io_op_def *def = &io_op_defs[req->opcode];
>> + int ret;
>>
>> if (def->work_flags & IO_WQ_WORK_MM) {
>> - int ret = __io_sq_thread_acquire_mm(ctx);
>> + ret = __io_sq_thread_acquire_mm(ctx);
>> if (unlikely(ret))
>> return ret;
>> }
>>
>> - if (def->needs_file || (def->work_flags & IO_WQ_WORK_FILES))
>> - __io_sq_thread_acquire_files(ctx);
>> + if (def->needs_file || (def->work_flags & IO_WQ_WORK_FILES)) {
>> + ret = __io_sq_thread_acquire_files(ctx);
>> + if (unlikely(ret))
>> + return ret;
>> + }
>>
>> return 0;
>> }
>> @@ -2117,8 +2122,8 @@ static void __io_req_task_submit(struct io_kiocb *req)
>> {
>> struct io_ring_ctx *ctx = req->ctx;
>>
>> - if (!__io_sq_thread_acquire_mm(ctx)) {
>> - __io_sq_thread_acquire_files(ctx);
>> + if (!__io_sq_thread_acquire_mm(ctx) &&
>> + !__io_sq_thread_acquire_files(ctx)) {
>> mutex_lock(&ctx->uring_lock);
>> __io_queue_sqe(req, NULL);
>> mutex_unlock(&ctx->uring_lock);
>>
>
--
Pavel Begunkov
