Patchwork [git] libata bug fix

login
register
mail settings
Submitter Jeff Garzik
Date Feb. 25, 2010, 3:49 a.m.
Message ID <20100225034937.GA26364@havoc.gtf.org>
Download mbox | patch
Permalink /patch/46218/
State Not Applicable
Delegated to: David Miller
Headers show

Comments

Jeff Garzik - Feb. 25, 2010, 3:49 a.m.
This is a fix that probably should have gone into 2.6.33.  It never
received an ack from the bug reporter, hence the delay,
but NVIDIA ok'd it anyway.  It merely disables an optimization.




Please pull from 'upstream-linus' branch of
master.kernel.org:/pub/scm/linux/kernel/git/jgarzik/libata-dev.git upstream-linus

to receive the following updates:

 drivers/ata/ahci.c |   12 ++++++++++--
 1 files changed, 10 insertions(+), 2 deletions(-)

Robert Hancock (1):
      ahci: disable FPDMA auto-activate optimization on NVIDIA AHCI

--
To unsubscribe from this list: send the line "unsubscribe linux-ide" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Andrew Morton - Feb. 25, 2010, 4:03 a.m.
On Wed, 24 Feb 2010 22:49:37 -0500 Jeff Garzik <jeff@garzik.org> wrote:

> 
> This is a fix that probably should have gone into 2.6.33.

It still can if we cc stable@kernel.org?

>  It never
> received an ack from the bug reporter, hence the delay,
> but NVIDIA ok'd it anyway.  It merely disables an optimization.
> 
> 
> 
> 
> Please pull from 'upstream-linus' branch of
> master.kernel.org:/pub/scm/linux/kernel/git/jgarzik/libata-dev.git upstream-linus
> 
> to receive the following updates:
> 
>  drivers/ata/ahci.c |   12 ++++++++++--
>  1 files changed, 10 insertions(+), 2 deletions(-)
> 
> Robert Hancock (1):
>       ahci: disable FPDMA auto-activate optimization on NVIDIA AHCI
> 
> diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
> index b343903..a6a736a 100644
> --- a/drivers/ata/ahci.c
> +++ b/drivers/ata/ahci.c
> @@ -3082,8 +3082,16 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
>  	ahci_save_initial_config(pdev, hpriv);
>  
>  	/* prepare host */
> -	if (hpriv->cap & HOST_CAP_NCQ)
> -		pi.flags |= ATA_FLAG_NCQ | ATA_FLAG_FPDMA_AA;
> +	if (hpriv->cap & HOST_CAP_NCQ) {
> +		pi.flags |= ATA_FLAG_NCQ;
> +		/* Auto-activate optimization is supposed to be supported on
> +		   all AHCI controllers indicating NCQ support, but it seems
> +		   to be broken at least on some NVIDIA MCP79 chipsets.
> +		   Until we get info on which NVIDIA chipsets don't have this
> +		   issue, if any, disable AA on all NVIDIA AHCIs. */
> +		if (pdev->vendor != PCI_VENDOR_ID_NVIDIA)
> +			pi.flags |= ATA_FLAG_FPDMA_AA;
> +	}
>  
>  	if (hpriv->cap & HOST_CAP_PMP)
>  		pi.flags |= ATA_FLAG_PMP;
--
To unsubscribe from this list: send the line "unsubscribe linux-ide" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Jeff Garzik - Feb. 25, 2010, 4:07 a.m.
On 02/24/2010 11:03 PM, Andrew Morton wrote:
> On Wed, 24 Feb 2010 22:49:37 -0500 Jeff Garzik<jeff@garzik.org>  wrote:
>
>>
>> This is a fix that probably should have gone into 2.6.33.
>
> It still can if we cc stable@kernel.org?

The commit message includes the Cc as per standard.

	Jeff



--
To unsubscribe from this list: send the line "unsubscribe linux-ide" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index b343903..a6a736a 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -3082,8 +3082,16 @@  static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	ahci_save_initial_config(pdev, hpriv);
 
 	/* prepare host */
-	if (hpriv->cap & HOST_CAP_NCQ)
-		pi.flags |= ATA_FLAG_NCQ | ATA_FLAG_FPDMA_AA;
+	if (hpriv->cap & HOST_CAP_NCQ) {
+		pi.flags |= ATA_FLAG_NCQ;
+		/* Auto-activate optimization is supposed to be supported on
+		   all AHCI controllers indicating NCQ support, but it seems
+		   to be broken at least on some NVIDIA MCP79 chipsets.
+		   Until we get info on which NVIDIA chipsets don't have this
+		   issue, if any, disable AA on all NVIDIA AHCIs. */
+		if (pdev->vendor != PCI_VENDOR_ID_NVIDIA)
+			pi.flags |= ATA_FLAG_FPDMA_AA;
+	}
 
 	if (hpriv->cap & HOST_CAP_PMP)
 		pi.flags |= ATA_FLAG_PMP;