提交 c3036021 编写于 作者: C Christoph Hellwig 提交者: Jens Axboe

block: use GFP_NOIO instead of __GFP_DIRECT_RECLAIM

We just can't do I/O when doing block layer requests allocations,
so use GFP_NOIO instead of the even more limited __GFP_DIRECT_RECLAIM.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
上级 4accf5fc
......@@ -1577,8 +1577,7 @@ static struct request *blk_old_get_request(struct request_queue *q,
unsigned int op, blk_mq_req_flags_t flags)
{
struct request *rq;
gfp_t gfp_mask = flags & BLK_MQ_REQ_NOWAIT ? GFP_ATOMIC :
__GFP_DIRECT_RECLAIM;
gfp_t gfp_mask = flags & BLK_MQ_REQ_NOWAIT ? GFP_ATOMIC : GFP_NOIO;
int ret = 0;
WARN_ON_ONCE(q->mq_ops);
......@@ -2056,7 +2055,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
* Returns with the queue unlocked.
*/
blk_queue_enter_live(q);
req = get_request(q, bio->bi_opf, bio, 0, __GFP_DIRECT_RECLAIM);
req = get_request(q, bio->bi_opf, bio, 0, GFP_NOIO);
if (IS_ERR(req)) {
blk_queue_exit(q);
__wbt_done(q->rq_wb, wb_acct);
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册