Hi,
On Mon, Oct 30, 2000 at 01:56:07PM -0500, Jeff Garzik wrote:
>
> Seen it, re-read my question...
>
> I keep seeing "audio drivers' mmap" used a specific example of a place
> that would benefit from kiobufs. The current via audio mmap looks quite
> a bit like mmap_kiobuf and its support
Andrea Arcangeli <[EMAIL PROTECTED]> wrote:
>> +map = follow_page(ptr, datain, );
>> +if (failed) {
>> +/*
>> + * Page got stolen before we could lock it down.
>> + * Retry.
>> + */
>>
Hi,
On Mon, Oct 30, 2000 at 01:56:07PM -0500, Jeff Garzik wrote:
Seen it, re-read my question...
I keep seeing "audio drivers' mmap" used a specific example of a place
that would benefit from kiobufs. The current via audio mmap looks quite
a bit like mmap_kiobuf and its support code...
On Mon, Oct 30, 2000 at 12:45:13PM +0100, Christoph Hellwig wrote:
> @@ -393,10 +396,15 @@
> pmd = pmd_offset(pgd, address);
> if (pmd) {
> pte_t * pte = pte_offset(pmd, address);
> - if (pte && pte_present(*pte))
> + if (pte && pte_present(*pte))
Christoph Hellwig wrote:
>
> On Mon, Oct 30, 2000 at 03:08:31PM -0500, Jeff Garzik wrote:
> > Actually, I wonder if its even possible for mmap_kiobuf to support audio
> > -- full duplex requires that both record and playback buffer(s),
> > theoretically two separate sets of kiobufs, to be
On Mon, Oct 30, 2000 at 03:08:31PM -0500, Jeff Garzik wrote:
> Actually, I wonder if its even possible for mmap_kiobuf to support audio
> -- full duplex requires that both record and playback buffer(s),
> theoretically two separate sets of kiobufs, to be presented as one space
> (with playback
Christoph Hellwig wrote:
>
> On Mon, Oct 30, 2000 at 01:56:07PM -0500, Jeff Garzik wrote:
> > My question from above is: how can the via audio mmap in test10-preXX
> > be improved by using kiobufs? I am not a kiobuf expert, but AFAICS a
> > non-kiobuf implementation is better for audio
On Mon, Oct 30, 2000 at 01:56:07PM -0500, Jeff Garzik wrote:
> My question from above is: how can the via audio mmap in test10-preXX
> be improved by using kiobufs? I am not a kiobuf expert, but AFAICS a
> non-kiobuf implementation is better for audio drivers. (and the via
> audio mmap
Christoph Hellwig wrote:
> On Mon, Oct 30, 2000 at 12:19:21PM -0500, Jeff Garzik wrote:
> > Take a look at drivers/sound/via82cxxx_audio.c. How can that mmap be
> > improved by using kiobufs?
>
> I think so - but you need Stephen's kvmap patch, that is in the same
> patchset the forward-ported
On Mon, Oct 30, 2000 at 12:19:21PM -0500, Jeff Garzik wrote:
> Christoph Hellwig wrote:
> > +Locking down user memory and doing mass storage device IO with it is not
> > +the only purpose of kiobufs. Another use for kiobufs is allowing
> > +user-space mmaping dma memory, e.g in sound drivers.
Christoph Hellwig wrote:
> +Locking down user memory and doing mass storage device IO with it is not
> +the only purpose of kiobufs. Another use for kiobufs is allowing
> +user-space mmaping dma memory, e.g in sound drivers. To do so you
> +need to lock-down kernel virtual memory and refernece
On Fri, Oct 27, 2000 at 02:23:04PM -0700, Linus Torvalds wrote:
>
> [...]
>
> That solution, btw, might be as simple as just saying:
>
> - raw IO is based on physical pages, and the COW mapping crated by
>fork() may cause the changes to be visibile to either child or parent
>or both,
On Fri, Oct 27, 2000 at 02:23:04PM -0700, Linus Torvalds wrote:
[...]
That solution, btw, might be as simple as just saying:
- raw IO is based on physical pages, and the COW mapping crated by
fork() may cause the changes to be visibile to either child or parent
or both, depending
Christoph Hellwig wrote:
+Locking down user memory and doing mass storage device IO with it is not
+the only purpose of kiobufs. Another use for kiobufs is allowing
+user-space mmaping dma memory, e.g in sound drivers. To do so you
+need to lock-down kernel virtual memory and refernece it
On Mon, Oct 30, 2000 at 12:19:21PM -0500, Jeff Garzik wrote:
Christoph Hellwig wrote:
+Locking down user memory and doing mass storage device IO with it is not
+the only purpose of kiobufs. Another use for kiobufs is allowing
+user-space mmaping dma memory, e.g in sound drivers. To do so
Christoph Hellwig wrote:
On Mon, Oct 30, 2000 at 12:19:21PM -0500, Jeff Garzik wrote:
Take a look at drivers/sound/via82cxxx_audio.c. How can that mmap be
improved by using kiobufs?
I think so - but you need Stephen's kvmap patch, that is in the same
patchset the forward-ported fixes
On Mon, Oct 30, 2000 at 01:56:07PM -0500, Jeff Garzik wrote:
My question from above is: how can the via audio mmap in test10-preXX
be improved by using kiobufs? I am not a kiobuf expert, but AFAICS a
non-kiobuf implementation is better for audio drivers. (and the via
audio mmap
Christoph Hellwig wrote:
On Mon, Oct 30, 2000 at 01:56:07PM -0500, Jeff Garzik wrote:
My question from above is: how can the via audio mmap in test10-preXX
be improved by using kiobufs? I am not a kiobuf expert, but AFAICS a
non-kiobuf implementation is better for audio drivers. (and
On Mon, Oct 30, 2000 at 03:08:31PM -0500, Jeff Garzik wrote:
Actually, I wonder if its even possible for mmap_kiobuf to support audio
-- full duplex requires that both record and playback buffer(s),
theoretically two separate sets of kiobufs, to be presented as one space
(with playback always
Ok, forgot to Cc linux-kernel ...
Please Cc linus on reply.
- Forwarded message from Christoph Hellwig <[EMAIL PROTECTED]> -
Date: Fri, 27 Oct 2000 22:03:54 +0200
From: Christoph Hellwig <[EMAIL PROTECTED]>
To: Linus Torvalds <[EMAIL PROTECTED]>
Subject: [PATCH]
Ok, forgot to Cc linux-kernel ...
Please Cc linus on reply.
- Forwarded message from Christoph Hellwig [EMAIL PROTECTED] -
Date: Fri, 27 Oct 2000 22:03:54 +0200
From: Christoph Hellwig [EMAIL PROTECTED]
To: Linus Torvalds [EMAIL PROTECTED]
Subject: [PATCH] kiobuf/rawio fixes for 2.4.0
21 matches
Mail list logo
