Re: [RFC REBASED 5/5] powerpc/mm/slice: use the dynamic high slice size to limit bitmap operations

2018-03-01 Thread Nicholas Piggin
On Thu, 1 Mar 2018 08:09:55 +0100 Christophe LEROY wrote: > Le 28/02/2018 à 07:53, Nicholas Piggin a écrit : > > On Tue, 27 Feb 2018 18:11:07 +0530 > > "Aneesh Kumar K.V" wrote: > > > >> Nicholas Piggin writes: > >> > >>> On Tue, 27 Feb 2018 14:31:07 +0530 > >>> "Aneesh Kumar K.V" wrote:

Re: [RFC REBASED 5/5] powerpc/mm/slice: use the dynamic high slice size to limit bitmap operations

2018-02-28 Thread Christophe LEROY
Le 28/02/2018 à 07:53, Nicholas Piggin a écrit : On Tue, 27 Feb 2018 18:11:07 +0530 "Aneesh Kumar K.V" wrote: Nicholas Piggin writes: On Tue, 27 Feb 2018 14:31:07 +0530 "Aneesh Kumar K.V" wrote: Christophe Leroy writes: The number of high slices a process might use now depends

Re: [RFC REBASED 5/5] powerpc/mm/slice: use the dynamic high slice size to limit bitmap operations

2018-02-27 Thread Aneesh Kumar K.V
I also noticed that the slice mask printing use wrong variables now. I guess this should take care of it diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index fef3f36b0b73..6b3575c39668 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -535,8 +535,6 @@ unsigned

Re: [RFC REBASED 5/5] powerpc/mm/slice: use the dynamic high slice size to limit bitmap operations

2018-02-27 Thread Aneesh Kumar K.V
On 02/28/2018 12:23 PM, Nicholas Piggin wrote: On Tue, 27 Feb 2018 18:11:07 +0530 "Aneesh Kumar K.V" wrote: Nicholas Piggin writes: On Tue, 27 Feb 2018 14:31:07 +0530 "Aneesh Kumar K.V" wrote: Christophe Leroy writes: The number of high slices a process might use now depends on

Re: [RFC REBASED 5/5] powerpc/mm/slice: use the dynamic high slice size to limit bitmap operations

2018-02-27 Thread Nicholas Piggin
On Tue, 27 Feb 2018 18:11:07 +0530 "Aneesh Kumar K.V" wrote: > Nicholas Piggin writes: > > > On Tue, 27 Feb 2018 14:31:07 +0530 > > "Aneesh Kumar K.V" wrote: > > > >> Christophe Leroy writes: > >> > >> > The number of high slices a process might use now depends on its > >> > address spac

Re: [RFC REBASED 5/5] powerpc/mm/slice: use the dynamic high slice size to limit bitmap operations

2018-02-27 Thread Aneesh Kumar K.V
Nicholas Piggin writes: > On Tue, 27 Feb 2018 14:31:07 +0530 > "Aneesh Kumar K.V" wrote: > >> Christophe Leroy writes: >> >> > The number of high slices a process might use now depends on its >> > address space size, and what allocation address it has requested. >> > >> > This patch uses that

Re: [RFC REBASED 5/5] powerpc/mm/slice: use the dynamic high slice size to limit bitmap operations

2018-02-27 Thread Nicholas Piggin
On Tue, 27 Feb 2018 14:31:07 +0530 "Aneesh Kumar K.V" wrote: > Christophe Leroy writes: > > > The number of high slices a process might use now depends on its > > address space size, and what allocation address it has requested. > > > > This patch uses that limit throughout call chains where po

Re: [RFC REBASED 5/5] powerpc/mm/slice: use the dynamic high slice size to limit bitmap operations

2018-02-27 Thread Aneesh Kumar K.V
Christophe Leroy writes: > The number of high slices a process might use now depends on its > address space size, and what allocation address it has requested. > > This patch uses that limit throughout call chains where possible, > rather than use the fixed SLICE_NUM_HIGH for bitmap operations. >

[RFC REBASED 5/5] powerpc/mm/slice: use the dynamic high slice size to limit bitmap operations

2018-02-12 Thread Christophe Leroy
The number of high slices a process might use now depends on its address space size, and what allocation address it has requested. This patch uses that limit throughout call chains where possible, rather than use the fixed SLICE_NUM_HIGH for bitmap operations. This saves some cost for processes th