> XXX: The tradeoff is a (predicted) single word size comparison
> penalty, so perhaps a decision needs performance stats.
compared to a TLB shootdown? let's just move along and
try not to hear the noise this _may_ generate..
.mrg.
Le 08/08/2016 à 04:27, Cherry G. Mathew a écrit :
On 2 August 2016 at 19:51, Maxime Villard mailto:m...@netbsd.org>> wrote:
Module Name:src
Committed By: maxv
Date: Tue Aug 2 14:21:53 UTC 2016
Modified Files:
src/sys/arch/xen/x86: x86_xpmap.c
Lo
On 2 August 2016 at 19:51, Maxime Villard wrote:
> Module Name:src
> Committed By: maxv
> Date: Tue Aug 2 14:21:53 UTC 2016
>
> Modified Files:
> src/sys/arch/xen/x86: x86_xpmap.c
>
> Log Message:
> Map the kernel text, rodata and data+bss independently on Xen, with
> res
On Nov 11, 1:05pm, Jukka Ruohonen wrote:
} On Mon, Nov 11, 2013 at 02:52:30AM -0800, John Nemeth wrote:
} > My point is, if you want to know, go read the thread in port-xen@,
} > or the code. Also, what "trivial function for Xen"?
}
} The wrappers in cpufunc.S'es.
So that would be sys
Thanks for the explanation!
Btw, it was not criticism but a question.
- Jukka.
On Mon, Nov 11, 2013 at 12:31:19PM -0800, John Nemeth wrote:
> On Nov 11, 1:05pm, Jukka Ruohonen wrote:
> } On Mon, Nov 11, 2013 at 02:52:30AM -0800, John Nemeth wrote:
> } > My point is, if you want to know, g
On Nov 11, 12:30pm, Jukka Ruohonen wrote:
} On Sun, Nov 10, 2013 at 11:17:54AM -0800, John Nemeth wrote:
} > } x86_wbind()? Which however appears to be (icorrectly?) #ifndef'd for Xen.
} >
} > Uh, the function for Xen would be wbinvd(), which would create
} > a very nice infinite loop as all
On Mon, Nov 11, 2013 at 02:52:30AM -0800, John Nemeth wrote:
> My point is, if you want to know, go read the thread in port-xen@,
> or the code. Also, what "trivial function for Xen"?
The wrappers in cpufunc.S'es.
- Jukka.
On Sun, Nov 10, 2013 at 11:17:54AM -0800, John Nemeth wrote:
> } x86_wbind()? Which however appears to be (icorrectly?) #ifndef'd for Xen.
>
> Uh, the function for Xen would be wbinvd(), which would create
> a very nice infinite loop as all that function does is call
> xpq_flush_cache(). Thi
On Nov 10, 4:50pm, Jukka Ruohonen wrote:
} On Sun, Nov 10, 2013 at 01:19:13AM +, John Nemeth wrote:
} > Module Name:src
} > Committed By: jnemeth
} > Date: Sun Nov 10 01:19:13 UTC 2013
} >
} > Modified Files:
} > src/sys/arch/xen/x86: x86_xpmap.c
} >
} > Log M
On Sun, Nov 10, 2013 at 01:19:13AM +, John Nemeth wrote:
> Module Name: src
> Committed By: jnemeth
> Date: Sun Nov 10 01:19:13 UTC 2013
>
> Modified Files:
> src/sys/arch/xen/x86: x86_xpmap.c
>
> Log Message:
> Change xpq_flush_cache to just do WBINVD letting the hypervisor tr
On Tue, Aug 21, 2012 at 01:17:46AM +, Mindaugas Rasiukevicius wrote:
> Module Name: src
> Committed By: rmind
> Date: Tue Aug 21 01:17:46 UTC 2012
>
> Modified Files:
> src/sys/arch/xen/x86: x86_xpmap.c
>
> Log Message:
> Fix Xen build. Make xcpumask uint32_t, fits 32 CPUs (ca
On Thu, Mar 04, 2010 at 12:58:01AM +0900, Izumi Tsutsui wrote:
> They are in .
>
> >> #define howmany(x, y) (((x)+((y)-1))/(y))
> how many y-byte blocks are required to store x-bytes region?
>
> >> #define roundup(x, y) x)+((y)-1))/(y))*(y))
> >> #define rounddown(x,y) (((x)/(y))*(y))
>
> OT: these are a little unclear to me. Could someone outline what
>
> roundup
> roundup2
> rounddown
> howmany
They are in .
>> #define howmany(x, y) (((x)+((y)-1))/(y))
how many y-byte blocks are required to store x-bytes region?
>> #define roundup(x, y) x)+((y
On Wed, Mar 03, 2010 at 12:09:03AM +, Jean-Yves Migeon wrote:
> Module Name: src
> Committed By: jym
> Date: Wed Mar 3 00:09:03 UTC 2010
>
> Modified Files:
> src/sys/arch/xen/x86: cpu.c
>
> Log Message:
> Use roundup2() instead of hardcoding the CACHE_LINE_SIZE rounding
> ope
14 matches
Mail list logo
