mmap'ed memory cacheable or uncheable

mmap'ed memory cacheable or uncheable

[Teresa Tao]

Hi there,

I got a question regarding the mmap'ed memory. Is the mmap'ed memory cacheable or uncheable? My driver just use the remap_page_range to map a reserved physical memory.

Thanks in advance!

Teresa

mmap'ed memory cacheable or uncheable

[Teresa Tao]

Hi there,

I got a question regarding the mmap'ed memory. Is the mmap'ed memory cacheable or uncheable? My driver just use the remap_page_range to map a reserved physical memory.

Thanks in advance!

Teresa

Re: mmap'ed memory cacheable or uncheable

[Jun Sun]

On Thu, Jul 24, 2003 at 08:26:59PM -0700, Teresa Tao wrote:
> Hi there,
> 
> I got a question regarding the mmap'ed memory. Is the mmap'ed memory cacheable or uncheable? My driver just use the remap_page_range to map a reserved physical memory.
>

I am pretty much sure it is cached, although I can't pin down exactly
where in the mm subsystem it does so - I have had cache bugs related
to mmap().

Jun

Re: mmap'ed memory cacheable or uncheable

[Ralf Baechle]

On Thu, Jul 24, 2003 at 08:26:59PM -0700, Teresa Tao wrote:

> I got a question regarding the mmap'ed memory. Is the mmap'ed memory
> cacheable or uncheable? My driver just use the remap_page_range to map
> a reserved physical memory.

Mmap(2) creates cachable mappings for everything below the highest memory
address and uncached above that.  That's a somewhat naive mechanism
which fails a few systems but somehow nobody did complain so far ...

  Ralf

RE: mmap'ed memory cacheable or uncheable

[Teresa Tao]

How about if I specify the following flags in my mmap routine just like what the pgprot_noncached micro did.
	pgprot_val(vma->vm_page_prot) &= ~_CACHE_MASK;
	pgprot_val(vma->vm_page_prot) |= _CACHE_UNCACHED;

Will this have kernel make the mmap'd memory non-cacheable? Or is there a mmap non-cacheable patch?

Thanks in advance!

Teresa



-----Original Message-----
From: Jun Sun [mailto:jsun@mvista.com]
Sent: Friday, July 25, 2003 3:02 PM
To: Teresa Tao
Cc: linux-mips@linux-mips.org; jsun@mvista.com
Subject: Re: mmap'ed memory cacheable or uncheable


On Thu, Jul 24, 2003 at 08:26:59PM -0700, Teresa Tao wrote:
> Hi there,
> 
> I got a question regarding the mmap'ed memory. Is the mmap'ed memory cacheable or uncheable? My driver just use the remap_page_range to map a reserved physical memory.
>

I am pretty much sure it is cached, although I can't pin down exactly
where in the mm subsystem it does so - I have had cache bugs related
to mmap().

Jun

RE: mmap'ed memory cacheable or uncheable

[Teresa Tao]

How about if I specify the following flags in my mmap routine just like what the pgprot_noncached micro did.
	pgprot_val(vma->vm_page_prot) &= ~_CACHE_MASK;
	pgprot_val(vma->vm_page_prot) |= _CACHE_UNCACHED;

Will this have kernel make the mmap'd memory non-cacheable? Or is there a mmap non-cacheable patch?

Thanks in advance!

Teresa



-----Original Message-----
From: Jun Sun [mailto:jsun@mvista.com]
Sent: Friday, July 25, 2003 3:02 PM
To: Teresa Tao
Cc: linux-mips@linux-mips.org; jsun@mvista.com
Subject: Re: mmap'ed memory cacheable or uncheable


On Thu, Jul 24, 2003 at 08:26:59PM -0700, Teresa Tao wrote:
> Hi there,
> 
> I got a question regarding the mmap'ed memory. Is the mmap'ed memory cacheable or uncheable? My driver just use the remap_page_range to map a reserved physical memory.
>

I am pretty much sure it is cached, although I can't pin down exactly
where in the mm subsystem it does so - I have had cache bugs related
to mmap().

Jun

Re: mmap'ed memory cacheable or uncheable

[Jun Sun]

On Fri, Jul 25, 2003 at 03:52:33PM -0700, Teresa Tao wrote:
> How about if I specify the following flags in my mmap routine just like what the pgprot_noncached micro did.
> 	pgprot_val(vma->vm_page_prot) &= ~_CACHE_MASK;
> 	pgprot_val(vma->vm_page_prot) |= _CACHE_UNCACHED;
> 
> Will this have kernel make the mmap'd memory non-cacheable? Or is there a mmap non-cacheable patch?
>

I think this might work.  Did you try it?  The performance will be bad
though as mmap() is used widely by userland.

Jun

Re: mmap'ed memory cacheable or uncheable

[Maciej W. Rozycki]

On Mon, 28 Jul 2003, Jun Sun wrote:

> > How about if I specify the following flags in my mmap routine just like what the pgprot_noncached micro did.
> > 	pgprot_val(vma->vm_page_prot) &= ~_CACHE_MASK;
> > 	pgprot_val(vma->vm_page_prot) |= _CACHE_UNCACHED;
> > 
> > Will this have kernel make the mmap'd memory non-cacheable? Or is there a mmap non-cacheable patch?
> 
> I think this might work.  Did you try it?  The performance will be bad
> though as mmap() is used widely by userland.

 See mmap_mem() for how to select between cached and uncached mmap()ing
cleanly. 

-- 
+  Maciej W. Rozycki, Technical University of Gdansk, Poland   +
+--------------------------------------------------------------+
+        e-mail: macro@ds2.pg.gda.pl, PGP key available        +