Re: [PATCH v2] MIPS64: Support of at least 48 bits of SEGBITS

2015-05-15 Thread Maciej W. Rozycki
On Fri, 15 May 2015, Leonid Yegoshin wrote: > > Many processors support larger VA space than is utilized by the kernel. > >A choice was made to reduce the size of the VA space in order to > > reduce TLB handling overhead. > > > > If the true reason for the patch is to enable larger VA space, s

Re: [PATCH v2] MIPS64: Support of at least 48 bits of SEGBITS

2015-05-15 Thread Leonid Yegoshin
On 05/15/2015 02:53 PM, Ralf Baechle wrote: On Thu, May 14, 2015 at 06:34:43PM -0700, Leonid Yegoshin wrote: The order 1 allocation for the PGD are concerning me a little. On a system under even moderate memory pressure that might become a bit of a reliability or performance issue. With 4kB pa

Re: [PATCH v2] MIPS64: Support of at least 48 bits of SEGBITS

2015-05-15 Thread Ralf Baechle
On Thu, May 14, 2015 at 06:34:43PM -0700, Leonid Yegoshin wrote: The order 1 allocation for the PGD are concerning me a little. On a system under even moderate memory pressure that might become a bit of a reliability or performance issue. With 4kB pages we already need order 1 or even 2 allocati

Re: [PATCH v2] MIPS64: Support of at least 48 bits of SEGBITS

2015-05-15 Thread Leonid Yegoshin
On 05/15/2015 01:49 PM, David Daney wrote: On 05/14/2015 06:34 PM, Leonid Yegoshin wrote: SEGBITS default is 40 bits or less, depending from CPU type. This patch introduces 48bits of application virtual address (SEGBITS) support. It is defined only for 16K and 64K pages and is optional (config

Re: [PATCH v2] MIPS64: Support of at least 48 bits of SEGBITS

2015-05-15 Thread David Daney
On 05/14/2015 06:34 PM, Leonid Yegoshin wrote: SEGBITS default is 40 bits or less, depending from CPU type. This patch introduces 48bits of application virtual address (SEGBITS) support. It is defined only for 16K and 64K pages and is optional (configurable). Penalty - a small number of addition

Re: [PATCH v2] MIPS64: Support of at least 48 bits of SEGBITS

2015-05-15 Thread Leonid Yegoshin
On 05/15/2015 09:28 AM, David Daney wrote: On 05/14/2015 06:34 PM, Leonid Yegoshin wrote: SEGBITS default is 40 bits or less, depending from CPU type. This patch introduces 48bits of application virtual address (SEGBITS) support. It is defined only for 16K and 64K pages and is optional (configur

Re: [PATCH v2] MIPS64: Support of at least 48 bits of SEGBITS

2015-05-15 Thread David Daney
On 05/14/2015 06:34 PM, Leonid Yegoshin wrote: SEGBITS default is 40 bits or less, depending from CPU type. This patch introduces 48bits of application virtual address (SEGBITS) support. It is defined only for 16K and 64K pages and is optional (configurable). Penalty - a small number of addition

Re: [PATCH v2] MIPS64: Support of at least 48 bits of SEGBITS

2015-05-15 Thread Sergei Shtylyov
Hello. On 5/15/2015 4:34 AM, Leonid Yegoshin wrote: SEGBITS default is 40 bits or less, depending from CPU type. This patch introduces 48bits of application virtual address (SEGBITS) support. It is defined only for 16K and 64K pages and is optional (configurable). Penalty - a small number of

[PATCH v2] MIPS64: Support of at least 48 bits of SEGBITS

2015-05-14 Thread Leonid Yegoshin
SEGBITS default is 40 bits or less, depending from CPU type. This patch introduces 48bits of application virtual address (SEGBITS) support. It is defined only for 16K and 64K pages and is optional (configurable). Penalty - a small number of additional pages for generic (small) applications. But fo