* Re: [BK-2.5] Update the generic DMA API to take GFP_ flags on
@ 2003-01-14 15:30 James Bottomley
2003-01-14 15:30 ` David S. Miller
0 siblings, 1 reply; 4+ messages in thread
From: James Bottomley @ 2003-01-14 15:30 UTC (permalink / raw)
To: David S. Miller; +Cc: James.Bottomley, linux-kernel
> What about platforms that can only use GFP_ATOMIC due to
> implementation side issues? Is that "OK"?
Yes.
A GFP_KERNEL request is safely implemented as GFP_ATOMIC as long as the caller
checks return for NULL. for dma_alloc_coherent return checking is a
requirement because the system may return NULL anyway if it is out of mappings
even with a GFP_KERNEL flag.
James
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [BK-2.5] Update the generic DMA API to take GFP_ flags on
2003-01-14 15:30 [BK-2.5] Update the generic DMA API to take GFP_ flags on James Bottomley
@ 2003-01-14 15:30 ` David S. Miller
2003-01-14 15:51 ` James Bottomley
2003-01-14 15:51 ` Russell King
0 siblings, 2 replies; 4+ messages in thread
From: David S. Miller @ 2003-01-14 15:30 UTC (permalink / raw)
To: James.Bottomley; +Cc: linux-kernel
From: James Bottomley <James.Bottomley@steeleye.com>
Date: Tue, 14 Jan 2003 10:30:15 -0500
A GFP_KERNEL request is safely implemented as GFP_ATOMIC as long as the caller
checks return for NULL. for dma_alloc_coherent return checking is a
requirement because the system may return NULL anyway if it is out of mappings
even with a GFP_KERNEL flag.
Now what about the corollary, a platform that needs
to sleep to setup the cpu mapings in a race-free manner?
It could not ever honor GFP_ATOMIC in that case.
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [BK-2.5] Update the generic DMA API to take GFP_ flags on
2003-01-14 15:30 ` David S. Miller
@ 2003-01-14 15:51 ` James Bottomley
2003-01-14 15:51 ` Russell King
1 sibling, 0 replies; 4+ messages in thread
From: James Bottomley @ 2003-01-14 15:51 UTC (permalink / raw)
To: David S. Miller; +Cc: James.Bottomley, linux-kernel
davem@redhat.com said:
> Now what about the corollary, a platform that needs to sleep to setup
> the cpu mapings in a race-free manner?
This one is the big bug bear. The DMA-mapping.txt doc says
pci_alloc_consistent "may be called in interrupt context". Thus if the
dma_alloc with GFP_ATOMIC uses the same code path, it should be safe.
However, there are indications that pci_alloc_consistent wasn't interrupt safe
on certain platforms (see other email re PA-RISC).
In any event, we're no worse off than we were with the pci_ API. Passing in
the flags will hopefully allow us to create GFP_ATOMIC safe paths in the arch
implementations which look iffy.
James
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [BK-2.5] Update the generic DMA API to take GFP_ flags on
2003-01-14 15:30 ` David S. Miller
2003-01-14 15:51 ` James Bottomley
@ 2003-01-14 15:51 ` Russell King
1 sibling, 0 replies; 4+ messages in thread
From: Russell King @ 2003-01-14 15:51 UTC (permalink / raw)
To: David S. Miller; +Cc: James.Bottomley, linux-kernel
On Tue, Jan 14, 2003 at 07:30:23AM -0800, David S. Miller wrote:
> From: James Bottomley <James.Bottomley@steeleye.com>
> Date: Tue, 14 Jan 2003 10:30:15 -0500
>
> A GFP_KERNEL request is safely implemented as GFP_ATOMIC as long as the caller
> checks return for NULL. for dma_alloc_coherent return checking is a
> requirement because the system may return NULL anyway if it is out of mappings
> even with a GFP_KERNEL flag.
>
> Now what about the corollary, a platform that needs
> to sleep to setup the cpu mapings in a race-free manner?
>
> It could not ever honor GFP_ATOMIC in that case.
That got solved in recent 2.5, albiet with limit of 2MB of consistent /
coherent allocations at any one time. We return NULL if we run out of
space, and _all_ callers must check the return code of
pci_alloc_consistent and/or dma_alloc_coherent no matter what flags they
pass in.
--
Russell King (rmk@arm.linux.org.uk) The developer of ARM Linux
http://www.arm.linux.org.uk/personal/aboutme.html
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2003-01-14 15:42 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2003-01-14 15:30 [BK-2.5] Update the generic DMA API to take GFP_ flags on James Bottomley
2003-01-14 15:30 ` David S. Miller
2003-01-14 15:51 ` James Bottomley
2003-01-14 15:51 ` Russell King
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).