[PATCH v2] nvme-pci: Save PCI state before putting drive into deepest state

[PATCH v2] nvme-pci: Save PCI state before putting drive into deepest state

[Mario Limonciello]

The action of saving the PCI state will cause numerous PCI configuration
space reads which depending upon the vendor implementation may cause
the drive to exit the deepest NVMe state.

In these cases ASPM will typically resolve the PCIe link state and APST
may resolve the NVMe power state.  However it has also been observed
that this register access after quiesced will cause PC10 failure
on some device combinations.

To resolve this, move the PCI state saving to before SetFeatures has been
called.  This has been proven to resolve the issue across a 5000 sample
test on previously failing disk/system combinations.

Signed-off-by: Mario Limonciello <mario.limonciello@dell.com>
---
 drivers/nvme/host/pci.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

Changes from v1:
 * Discard saved state in error scenario
 * Removed unneeded goto statement in error scenario

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 732d5b6..ef69013 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2894,11 +2894,21 @@ static int nvme_suspend(struct device *dev)
 	if (ret < 0)
 		goto unfreeze;
 
+	/*
+	 * A saved state prevents pci pm from generically controlling the
+	 * device's power. If we're using protocol specific settings, we don't
+	 * want pci interfering.
+	 */
+	pci_save_state(pdev);
+
 	ret = nvme_set_power_state(ctrl, ctrl->npss);
 	if (ret < 0)
 		goto unfreeze;
 
 	if (ret) {
+		/* discard the saved state */
+		pci_load_saved_state(pdev, NULL);
+
 		/*
 		 * Clearing npss forces a controller reset on resume. The
 		 * correct value will be resdicovered then.
@@ -2906,14 +2916,7 @@ static int nvme_suspend(struct device *dev)
 		nvme_dev_disable(ndev, true);
 		ctrl->npss = 0;
 		ret = 0;
-		goto unfreeze;
 	}
-	/*
-	 * A saved state prevents pci pm from generically controlling the
-	 * device's power. If we're using protocol specific settings, we don't
-	 * want pci interfering.
-	 */
-	pci_save_state(pdev);
 unfreeze:
 	nvme_unfreeze(ctrl);
 	return ret;
-- 
2.7.4

Re: [PATCH v2] nvme-pci: Save PCI state before putting drive into deepest state

[Sagi Grimberg]

Keith, can we get a review from you for this?

Re: [PATCH v2] nvme-pci: Save PCI state before putting drive into deepest state

[Keith Busch]

On Wed, Sep 18, 2019 at 01:15:55PM -0500, Mario Limonciello wrote:
> The action of saving the PCI state will cause numerous PCI configuration
> space reads which depending upon the vendor implementation may cause
> the drive to exit the deepest NVMe state.
> 
> In these cases ASPM will typically resolve the PCIe link state and APST
> may resolve the NVMe power state.  However it has also been observed
> that this register access after quiesced will cause PC10 failure
> on some device combinations.
> 
> To resolve this, move the PCI state saving to before SetFeatures has been
> called.  This has been proven to resolve the issue across a 5000 sample
> test on previously failing disk/system combinations.
> 
> Signed-off-by: Mario Limonciello <mario.limonciello@dell.com>

This looks good. It clashes with something I posted yesterday, but
I'll rebase after this one.

Reviewed-by: Keith Busch <kbusch@kernel.org>

Re: [PATCH v2] nvme-pci: Save PCI state before putting drive into deepest state

[Christoph Hellwig]

Looks sensible to me:

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