On Fri, 2016-03-11 at 10:18 +1100, Gavin Shan wrote:
> However, PowerKVM guest doesn't have it. I guess it's a problem,
> right?
What is the number we use for the TCE h-calls ? I think it's from the
first part of the dma window property no ?
Cheers,
Ben.
On Fri, Mar 11, 2016 at 09:52:13PM +1100, Benjamin Herrenschmidt wrote:
>On Fri, 2016-03-11 at 10:18 +1100, Gavin Shan wrote:
>> However, PowerKVM guest doesn't have it. I guess it's a problem,
>> right?
>
>What is the number we use for the TCE h-calls ? I think it's from the
>first part of the dma
On 03/11/2016 10:14 AM, Gavin Shan wrote:
Yeah, the BUID is PHB's identifier, but we only need the low 16-bits
as its base is 0x8002000ULL in QEMU or pHyp. I think other platforms
(like freescale's) still need dynamically allocated domain number, which
could be managed by a bitmap.
Than
On Tue, Feb 09, 2016 at 05:08:00PM +0100, Christophe Leroy wrote:
> Memory: 124428K/131072K available (3748K kernel code, 188K rwdata,
> 648K rodata, 508K init, 290K bss, 6644K reserved)
> Kernel virtual memory layout:
> * 0xfffdf000..0xf000 : fixmap
> * 0xfde0..0xfe00 : consisten
On Tue, Feb 09, 2016 at 05:08:02PM +0100, Christophe Leroy wrote:
> Once the linear memory space has been mapped with 8Mb pages, as
> seen in the related commit, we get 11 millions DTLB missed during
> the reference 600s period. 77% of the misses are on user addresses
> and 23% are on kernel addres
On Mon, Aug 03, 2015 at 11:14:10AM +0300, Igal.Liberman wrote:
> From: Igal Liberman
>
> Describe the PHY topology for all configurations supported by each board
>
> Based on prior work by Andy Fleming
>
> Signed-off-by: Shruti Kanetkar
> Signed-off-by: Emil Medve
> Signed-off-by: Igal Liber
Highlights include 8xx optimizations, 32-bit checksum optimizations, 86xx
consolidation, e5500/e6500 cpu hotplug, more fman and other dt bits, and
minor fixes/cleanup.
The following changes since commit ee3b93ebfbed6279f7a329001433c75c50ddfcc9:
powerpc/mm: Move hash64 tlbflush code into a new h
