nvme-pci: fix NULL req in completion handler

[ Upstream commit 50b7c24390a53c78de546215282fb52980f1d7b7 ]

Currently, we use nvmeq->q_depth as the upper limit for a valid tag in
nvme_handle_cqe(), it is not correct. Because the available tag number
is recorded in tagset, which is not equal to nvmeq->q_depth.

The nvme driver registers interrupts for queues before initializing the
tagset, because it uses the number of successful request_irq() calls to
configure the tagset parameters. This allows a race condition with the
current tag validity check if the controller happens to produce an
interrupt with a corrupted CQE before the tagset is initialized.

Replace the driver's indirect tag check with the one already provided by
the block layer.

Signed-off-by: Xianting Tian <tian.xianting@h3c.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
This commit is contained in:
Xianting Tian 2020-09-22 14:25:17 +08:00 committed by Greg Kroah-Hartman
parent 157ccdf7eb
commit 2b217eafcf

View File

@ -941,13 +941,6 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
volatile struct nvme_completion *cqe = &nvmeq->cqes[idx];
struct request *req;
if (unlikely(cqe->command_id >= nvmeq->q_depth)) {
dev_warn(nvmeq->dev->ctrl.device,
"invalid id %d completed on queue %d\n",
cqe->command_id, le16_to_cpu(cqe->sq_id));
return;
}
/*
* AEN requests are special as they don't time out and can
* survive any kind of queue freeze and often don't respond to
@ -962,6 +955,13 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
}
req = blk_mq_tag_to_rq(nvme_queue_tagset(nvmeq), cqe->command_id);
if (unlikely(!req)) {
dev_warn(nvmeq->dev->ctrl.device,
"invalid id %d completed on queue %d\n",
cqe->command_id, le16_to_cpu(cqe->sq_id));
return;
}
trace_nvme_sq(req, cqe->sq_head, nvmeq->sq_tail);
nvme_end_request(req, cqe->status, cqe->result);
}