On Tue, Jun 09, 2009 at 10:35:33AM -0400, Chuck Ebbert wrote:
> The VIA Nano has a bug that makes the padlock unit fetch extra data
> during encryption operations. Add workarounds for that, and enable
> the driver on x86_64.
Thanks!
Where did you get the errata from, and what kind of document / r
* Chuck Ebbert | 2009-06-09 10:39:07 [-0400]:
>From: Sebastian Andrzej Siewior
>crypto: padlock-aes: enable on 64-bit kernels
>
>The only required change now is using the right push/pop instruction
>on x86-64. Taken from the original patch by Sebastian Andrzej Siewior.
>(Added a dependency on X86
* Chuck Ebbert | 2009-06-09 10:35:33 [-0400]:
>The VIA Nano has a bug that makes the padlock unit fetch extra data
>during encryption operations. Add workarounds for that, and enable
>the driver on x86_64.
Nice. The X86_64 padlock will make it mainline in next merge window so
I'm asking you kindly
On Tue, 9 Jun 2009 10:35:33 -0400
Chuck Ebbert wrote:
> The VIA Nano has a bug that makes the padlock unit fetch extra data
> during encryption operations. Add workarounds for that, and enable
> the driver on x86_64.
>
> 1/3 Fix ECB encryption mode
> 2/3 Fix CBC mode, clean up code
> 3/3 Enable
From: Sebastian Andrzej Siewior
crypto: padlock-aes: enable on 64-bit kernels
The only required change now is using the right push/pop instruction
on x86-64. Taken from the original patch by Sebastian Andrzej Siewior.
(Added a dependency on X86.)
Signed-off-by: Sebastian Andrzej Siewior
Signed-
From: Chuck Ebbert
crypto: padlock-aes: work around Nano CPU errata in CBC mode
Extend previous workarounds for the prefetch bug to cover CBC mode,
clean up the code a bit.
Signed-off-by: Chuck Ebbert
--- work-2.6.29.4.orig/drivers/crypto/padlock-aes.c
+++ work-2.6.29.4/drivers/crypto/padlock-
From: Chuck Ebbert
crypto: padlock-aes: work around Nano CPU errata in ECB mode
The VIA Nano processor has a bug that makes it prefetch extra data
during encryption operations, causing spurious page faults. Extend
existing workarounds for ECB mode to copy the data to an temporary
buffer to avoid
The VIA Nano has a bug that makes the padlock unit fetch extra data
during encryption operations. Add workarounds for that, and enable
the driver on x86_64.
1/3 Fix ECB encryption mode
2/3 Fix CBC mode, clean up code
3/3 Enable building for 64-bit kernels
--
To unsubscribe from this list: send the
