Re: [PATCHv2 2/2] nvme/pci: Mask device interrupts for threaded handlers

["Sironi, Filippo" <sironi@amazon.de>]

> On 2. Dec 2019, at 23:20, Keith Busch <kbusch@kernel.org> wrote:
> 
> Local interrupts are reenabled when the nvme irq thread is woken, so
> subsequent MSI or a level triggered interrupts may restart the nvme irq
> check while the thread handler is running. This unnecessarily spends CPU
> cycles and potentially triggers spurious interrupt detection, disabling
> our nvme irq.
> 
> Prevent the controller from sending future messages. For legacy and MSI,
> use the nvme interrupt mask/clear registers. For MSIx, use the quick
> control mask function.
> 
> Signed-off-by: Keith Busch <kbusch@kernel.org>
> ---
> drivers/nvme/host/pci.c | 28 ++++++++++++++++++++++++----
> 1 file changed, 24 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
> index 0590640ba62c..4022a872d29c 100644
> --- a/drivers/nvme/host/pci.c
> +++ b/drivers/nvme/host/pci.c
> @@ -13,8 +13,10 @@
> #include <linux/init.h>
> #include <linux/interrupt.h>
> #include <linux/io.h>
> +#include <linux/irq.h>
> #include <linux/mm.h>
> #include <linux/module.h>
> +#include <linux/msi.h>
> #include <linux/mutex.h>
> #include <linux/once.h>
> #include <linux/pci.h>
> @@ -1036,12 +1038,29 @@ static irqreturn_t nvme_irq(int irq, void *data)
> 	return ret;
> }
> 
> +static irqreturn_t nvme_irq_thread(int irq, void *data)
> +{
> +	struct nvme_queue *nvmeq = data;
> +
> +	nvme_irq(irq, data);
> +	if (to_pci_dev(nvmeq->dev->dev)->msix_enabled)
> +		__pci_msix_desc_mask_irq(irq_get_msi_desc(irq), 0);
> +	else
> +		writel(1 << nvmeq->cq_vector, nvmeq->dev->bar + NVME_REG_INTMC);
> +	return IRQ_HANDLED;
> +}
> +
> static irqreturn_t nvme_irq_check(int irq, void *data)
> {
> 	struct nvme_queue *nvmeq = data;
> -	if (nvme_cqe_pending(nvmeq))
> -		return IRQ_WAKE_THREAD;
> -	return IRQ_NONE;
> +
> +	if (!nvme_cqe_pending(nvmeq))
> +		return IRQ_NONE;
> +	if (to_pci_dev(nvmeq->dev->dev)->msix_enabled)
> +		__pci_msix_desc_mask_irq(irq_get_msi_desc(irq), 1);

Have you considered that __pci_msix_desc_mask_irq will cause
a trap from guest to hypervisor mode when running virtualized?

> +	else
> +		writel(1 << nvmeq->cq_vector, nvmeq->dev->bar + NVME_REG_INTMS);

What's stopping us from always using this method?

> +	return IRQ_WAKE_THREAD;
> }
> 
> /*
> @@ -1499,7 +1518,8 @@ static int queue_request_irq(struct nvme_queue *nvmeq)
> 
> 	if (use_threaded_interrupts) {
> 		return pci_request_irq(pdev, nvmeq->cq_vector, nvme_irq_check,
> -				nvme_irq, nvmeq, "nvme%dq%d", nr, nvmeq->qid);
> +				nvme_irq_thread, nvmeq, "nvme%dq%d", nr,
> +				nvmeq->qid);
> 	} else {
> 		return pci_request_irq(pdev, nvmeq->cq_vector, nvme_irq,
> 				NULL, nvmeq, "nvme%dq%d", nr, nvmeq->qid);
> -- 
> 2.21.0
> 
> 
> _______________________________________________
> linux-nvme mailing list
> linux-nvme@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-nvme




Amazon Development Center Germany GmbH
Krausenstr. 38
10117 Berlin
Geschaeftsfuehrung: Christian Schlaeger, Ralf Herbrich
Eingetragen am Amtsgericht Charlottenburg unter HRB 149173 B
Sitz: Berlin
Ust-ID: DE 289 237 879




_______________________________________________
linux-nvme mailing list
linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme