* octeon disable SWIOTLB
@ 2015-02-25 14:41 dwalker
2015-02-25 16:08 ` David Daney
0 siblings, 1 reply; 4+ messages in thread
From: dwalker @ 2015-02-25 14:41 UTC (permalink / raw)
To: David Daney; +Cc: linux-mips
Hi,
Back in 2010 you made CONFIG_SWIOTLB mandatory (commit b93b2a). This prevents the Continuous
memory allocation from being enabled. Would you be willing to accept a patch which allows
this option to be disabled if CONFIG_EXPERT is set? I suspect some users of Octeon can
review their hardware to be sure it's save to do.
Daniel
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: octeon disable SWIOTLB
@ 2015-02-25 16:08 ` David Daney
0 siblings, 0 replies; 4+ messages in thread
From: David Daney @ 2015-02-25 16:08 UTC (permalink / raw)
To: dwalker; +Cc: linux-mips
On 02/25/2015 06:41 AM, dwalker@fifo99.com wrote:
> Hi,
>
> Back in 2010 you made CONFIG_SWIOTLB mandatory (commit b93b2a). This prevents the Continuous
> memory allocation from being enabled. Would you be willing to accept a patch which allows
> this option to be disabled if CONFIG_EXPERT is set?
Ralf has the final say, so it really is not up to me.
That said, any patch that improves the flexibility of the kernel without
adversely effecting reliability and correctness would be welcome.
> I suspect some users of Octeon can
> review their hardware to be sure it's save to do.
>
> Daniel
>
>
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: octeon disable SWIOTLB
@ 2015-02-25 16:08 ` David Daney
0 siblings, 0 replies; 4+ messages in thread
From: David Daney @ 2015-02-25 16:08 UTC (permalink / raw)
To: dwalker; +Cc: linux-mips
On 02/25/2015 06:41 AM, dwalker@fifo99.com wrote:
> Hi,
>
> Back in 2010 you made CONFIG_SWIOTLB mandatory (commit b93b2a). This prevents the Continuous
> memory allocation from being enabled. Would you be willing to accept a patch which allows
> this option to be disabled if CONFIG_EXPERT is set?
Ralf has the final say, so it really is not up to me.
That said, any patch that improves the flexibility of the kernel without
adversely effecting reliability and correctness would be welcome.
> I suspect some users of Octeon can
> review their hardware to be sure it's save to do.
>
> Daniel
>
>
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: octeon disable SWIOTLB
2015-02-25 16:08 ` David Daney
(?)
@ 2015-02-26 22:33 ` Maciej W. Rozycki
-1 siblings, 0 replies; 4+ messages in thread
From: Maciej W. Rozycki @ 2015-02-26 22:33 UTC (permalink / raw)
To: David Daney; +Cc: dwalker, linux-mips
On Wed, 25 Feb 2015, David Daney wrote:
> > Back in 2010 you made CONFIG_SWIOTLB mandatory (commit b93b2a). This
> > prevents the Continuous
> > memory allocation from being enabled. Would you be willing to accept a patch
> > which allows
> > this option to be disabled if CONFIG_EXPERT is set?
>
> Ralf has the final say, so it really is not up to me.
>
> That said, any patch that improves the flexibility of the kernel without
> adversely effecting reliability and correctness would be welcome.
So how's DMA to/from 64-bit memory supposed to be handled then for 32-bit
PCI option cards that don't support DAC by systems that use continuous
memory allocation (whatever that is)? Is that a bug in continuous memory
allocation support?
Maciej
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2015-02-26 22:33 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2015-02-25 14:41 octeon disable SWIOTLB dwalker
2015-02-25 16:08 ` David Daney
2015-02-25 16:08 ` David Daney
2015-02-26 22:33 ` Maciej W. Rozycki
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.