NVMe: Need to lock queue during interrupt handling (ec6ce618) · Commits · 戴 / test

If we're sharing a queue between multiple CPUs and we cancel a sync I/O, we must have the queue locked to avoid corrupting the stack of the thread that submitted the I/O. It turns out this is the same locking that's needed for the threaded irq handler, so share that code. Signed-off-by:

Matthew Wilcox <matthew.r.wilcox@intel.com>

drivers/block/nvme.c

+1 −6

Original line number	Diff line number	Diff line
		@@ -476,11 +476,6 @@ static irqreturn_t nvme_process_cq(struct nvme_queue *nvmeq)
		}

		static irqreturn_t nvme_irq(int irq, void *data)
		{
		return nvme_process_cq(data);
		}

		static irqreturn_t nvme_irq_thread(int irq, void *data)
		{
		irqreturn_t result;
		struct nvme_queue *nvmeq = data;
		@@ -676,7 +671,7 @@ static int queue_request_irq(struct nvme_dev dev, struct nvme_queue nvmeq,
		{
		if (use_threaded_interrupts)
		return request_threaded_irq(dev->entry[nvmeq->cq_vector].vector,
		nvme_irq_check, nvme_irq_thread,
		nvme_irq_check, nvme_irq,
		IRQF_DISABLED \| IRQF_SHARED,
		name, nvmeq);
		return request_irq(dev->entry[nvmeq->cq_vector].vector, nvme_irq,

Admin message