[PATCH] nvme-pci: remove two deallocate zeroes quirks

[PATCH] nvme-pci: remove two deallocate zeroes quirks

[Keith Busch]

From: Keith Busch <kbusch@kernel.org>

The quirk was initially used as a signal to set the discard_zeroes_data
queue limit because there were some use cases that relied on that
behavior. The queue limit no longer exists as every user of it has been
converted to use the write zeroes operation instead.

The quirk now means to use a discard command as an alias to a write
zeroes request. Two of the devices previously using the quirk support
the write zeroes command directly, so these don't need or want to use
discard when the desired operation is to write zeroes.

Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 4c644bb7f0692..9535e35ef18a5 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3588,12 +3588,10 @@ static const struct pci_device_id nvme_id_table[] = {
 				NVME_QUIRK_DEALLOCATE_ZEROES, },
 	{ PCI_VDEVICE(INTEL, 0x0a54),	/* Intel P4500/P4600 */
 		.driver_data = NVME_QUIRK_STRIPE_SIZE |
-				NVME_QUIRK_DEALLOCATE_ZEROES |
 				NVME_QUIRK_IGNORE_DEV_SUBNQN |
 				NVME_QUIRK_BOGUS_NID, },
 	{ PCI_VDEVICE(INTEL, 0x0a55),	/* Dell Express Flash P4600 */
-		.driver_data = NVME_QUIRK_STRIPE_SIZE |
-				NVME_QUIRK_DEALLOCATE_ZEROES, },
+		.driver_data = NVME_QUIRK_STRIPE_SIZE, },
 	{ PCI_VDEVICE(INTEL, 0xf1a5),	/* Intel 600P/P3100 */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
 				NVME_QUIRK_MEDIUM_PRIO_SQ |
-- 
2.43.5

Re: [PATCH] nvme-pci: remove two deallocate zeroes quirks

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

I guess we actually do need it for the other two can can't remove it
entirely?

Re: [PATCH] nvme-pci: remove two deallocate zeroes quirks

[Keith Busch]

On Tue, Dec 03, 2024 at 01:34:35AM +0100, Christoph Hellwig wrote:
> I guess we actually do need it for the other two can can't remove it
> entirely?

Right, the other two are 1.0 spec devices that don't support the write
zeroes commmand, so leveraging dataset management to get the same
outcome is still desirable there.