nvme-pci: Add quirk for broken MSIs

Sandisk SN530 NVMe drives have broken MSIs. On systems without MSI-X
support, all commands time out resulting in the following message:

nvme nvme0: I/O tag 12 (100c) QID 0 timeout, completion polled

These timeouts cause the boot to take an excessively-long time (over 20
minutes) while the initial command queue is flushed.

Address this by adding a quirk for drives with buggy MSIs. The lspci
output for this device (recorded on a system with MSI-X support) is:

02:00.0 Non-Volatile memory controller: Sandisk Corp Device 5008 (rev 01) (prog-if 02 [NVM Express])
	Subsystem: Sandisk Corp Device 5008
	Flags: bus master, fast devsel, latency 0, IRQ 16, NUMA node 0
	Memory at f7e00000 (64-bit, non-prefetchable) [size=16K]
	Memory at f7e04000 (64-bit, non-prefetchable) [size=256]
	Capabilities: [80] Power Management version 3
	Capabilities: [90] MSI: Enable- Count=1/32 Maskable- 64bit+
	Capabilities: [b0] MSI-X: Enable+ Count=17 Masked-
	Capabilities: [c0] Express Endpoint, MSI 00
	Capabilities: [100] Advanced Error Reporting
	Capabilities: [150] Device Serial Number 00-00-00-00-00-00-00-00
	Capabilities: [1b8] Latency Tolerance Reporting
	Capabilities: [300] Secondary PCI Express
	Capabilities: [900] L1 PM Substates
	Kernel driver in use: nvme
	Kernel modules: nvme

Cc: <stable@vger.kernel.org>
Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Reviewed-by: Christoph Hellwig <hch@lst.de>

2 files changed, 16 insertions, 3 deletions

diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index b564c5f1450c6a..05532c2811774a 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -162,6 +162,11 @@ enum nvme_quirks {
 	 * Disables simple suspend/resume path.
 	 */
 	NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND	= (1 << 20),
+
+	/*
+	 * MSI (but not MSI-X) interrupts are broken and never fire.
+	 */
+	NVME_QUIRK_BROKEN_MSI			= (1 << 21),
 };
 
 /*
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index e393f6947ce493..710043086dffa5 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2224,6 +2224,7 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 		.priv		= dev,
 	};
 	unsigned int irq_queues, poll_queues;
+	unsigned int flags = PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY;
 
 	/*
 	 * Poll queues don't need interrupts, but we need at least one I/O queue
@@ -2247,8 +2248,10 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 	irq_queues = 1;
 	if (!(dev->ctrl.quirks & NVME_QUIRK_SINGLE_VECTOR))
 		irq_queues += (nr_io_queues - poll_queues);
-	return pci_alloc_irq_vectors_affinity(pdev, 1, irq_queues,
-			      PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd);
+	if (dev->ctrl.quirks & NVME_QUIRK_BROKEN_MSI)
+		flags &= ~PCI_IRQ_MSI;
+	return pci_alloc_irq_vectors_affinity(pdev, 1, irq_queues, flags,
+					      &affd);
 }
 
 static unsigned int nvme_max_io_queues(struct nvme_dev *dev)
@@ -2477,6 +2480,7 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 {
 	int result = -ENOMEM;
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
+	unsigned int flags = PCI_IRQ_ALL_TYPES;
 
 	if (pci_enable_device_mem(pdev))
 		return result;
@@ -2493,7 +2497,9 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 	 * interrupts. Pre-enable a single MSIX or MSI vec for setup. We'll
 	 * adjust this later.
 	 */
-	result = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
+	if (dev->ctrl.quirks & NVME_QUIRK_BROKEN_MSI)
+		flags &= ~PCI_IRQ_MSI;
+	result = pci_alloc_irq_vectors(pdev, 1, 1, flags);
 	if (result < 0)
 		goto disable;
 
@@ -3390,6 +3396,8 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY |
 				NVME_QUIRK_DISABLE_WRITE_ZEROES|
 				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
+	{ PCI_DEVICE(0x15b7, 0x5008),   /* Sandisk SN530 */
+		.driver_data = NVME_QUIRK_BROKEN_MSI },
 	{ PCI_DEVICE(0x1987, 0x5012),	/* Phison E12 */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1987, 0x5016),	/* Phison E16 */