Re: [PATCH 4/5] powernv:idle: Move initialization of sibling pacas to pnv_alloc_idle_core_states

From	Michael Ellerman <mpe@ellerman.id.au>
Newsgroups	linux.kernel
Subject	Re: [PATCH 4/5] powernv:idle: Move initialization of sibling pacas to pnv_alloc_idle_core_states
Date	2017-07-10 06:40 +0200
Message-ID	<u1yEh-kf-1@gated-at.bofh.it> (permalink)
References	<tZVvk-dV-7@gated-at.bofh.it> <tZVvl-dV-39@gated-at.bofh.it> <u0gJr-6NU-9@gated-at.bofh.it> <u0D3j-5J4-1@gated-at.bofh.it> <u0TUt-iz-1@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

Nicholas Piggin <npiggin@gmail.com> writes:
> On Fri, 7 Jul 2017 20:34:16 +0530
> Gautham R Shenoy <ego@linux.vnet.ibm.com> wrote:
>> On Fri, Jul 07, 2017 at 01:16:09AM +1000, Nicholas Piggin wrote:
>> > 
>> > Speaking of which... core_idle_state and thread_sibling_pacas are
>> > allocated with kmalloc_node... What happens if we take an SLB miss
>> > in the idle wakeup code on these guys? Nothing good I think. Perhaps
>> > we should put them into the pacas or somewhere in bolted memory.  
>> 
>> Yes, though the SLB miss hasn't yet been encountered in practise so
>> far!
>
> Considering it's a node-affine allocation, it may actually be possible
> to hit in practice on very large memory systems in practice.

You can boot with disable_1tb_segments on the kernel command line to
increase the change of hitting it.

cheers

Back to linux.kernel | Previous | Next — Previous in thread | Find similar | Unroll thread

Thread

[PATCH 0/5] powernv:idle: Cleanup idle states initialization "Gautham R. Shenoy" <ego@linux.vnet.ibm.com> - 2017-07-05 18:40 +0200
  [PATCH 3/5] powernv:idle: Define idle init function for power8 "Gautham R. Shenoy" <ego@linux.vnet.ibm.com> - 2017-07-05 18:40 +0200
    Re: [PATCH 3/5] powernv:idle: Define idle init function for power8 Nicholas Piggin <npiggin@gmail.com> - 2017-07-06 17:10 +0200
      Re: [PATCH 3/5] powernv:idle: Define idle init function for power8 Gautham R Shenoy <ego@linux.vnet.ibm.com> - 2017-07-07 14:50 +0200
  [PATCH 5/5] powernv:idle: Disable LOSE_FULL_CONTEXT states when stop-api fails. "Gautham R. Shenoy" <ego@linux.vnet.ibm.com> - 2017-07-05 18:40 +0200
    Re: [PATCH 5/5] powernv:idle: Disable LOSE_FULL_CONTEXT states when  stop-api fails. Nicholas Piggin <npiggin@gmail.com> - 2017-07-06 17:30 +0200
      Re: [PATCH 5/5] powernv:idle: Disable LOSE_FULL_CONTEXT states when  stop-api fails. Gautham R Shenoy <ego@linux.vnet.ibm.com> - 2017-07-07 19:40 +0200
        Re: [PATCH 5/5] powernv:idle: Disable LOSE_FULL_CONTEXT states when  stop-api fails. Nicholas Piggin <npiggin@gmail.com> - 2017-07-08 11:10 +0200
          Re: [PATCH 5/5] powernv:idle: Disable LOSE_FULL_CONTEXT states when  stop-api fails. Gautham R Shenoy <ego@linux.vnet.ibm.com> - 2017-07-11 07:10 +0200
  [PATCH 2/5] powernv:idle: Change return type of pnv_probe_idle_states to int "Gautham R. Shenoy" <ego@linux.vnet.ibm.com> - 2017-07-05 18:40 +0200
    Re: [PATCH 2/5] powernv:idle: Change return type of  pnv_probe_idle_states to int Nicholas Piggin <npiggin@gmail.com> - 2017-07-06 17:10 +0200
      Re: [PATCH 2/5] powernv:idle: Change return type of  pnv_probe_idle_states to int Gautham R Shenoy <ego@linux.vnet.ibm.com> - 2017-07-07 14:40 +0200
  [PATCH 1/5] powernv:idle: Move device-tree parsing to one place. "Gautham R. Shenoy" <ego@linux.vnet.ibm.com> - 2017-07-05 18:40 +0200
    Re: [PATCH 1/5] powernv:idle: Move device-tree parsing to one  place. Nicholas Piggin <npiggin@gmail.com> - 2017-07-06 17:00 +0200
      Re: [PATCH 1/5] powernv:idle: Move device-tree parsing to one place. Gautham R Shenoy <ego@linux.vnet.ibm.com> - 2017-07-07 13:30 +0200
        Re: [PATCH 1/5] powernv:idle: Move device-tree parsing to one  place. Nicholas Piggin <npiggin@gmail.com> - 2017-07-08 10:50 +0200
  [PATCH 4/5] powernv:idle: Move initialization of sibling pacas to pnv_alloc_idle_core_states "Gautham R. Shenoy" <ego@linux.vnet.ibm.com> - 2017-07-05 18:40 +0200
    Re: [PATCH 4/5] powernv:idle: Move initialization of sibling pacas  to pnv_alloc_idle_core_states Nicholas Piggin <npiggin@gmail.com> - 2017-07-06 17:20 +0200
      Re: [PATCH 4/5] powernv:idle: Move initialization of sibling pacas  to pnv_alloc_idle_core_states Gautham R Shenoy <ego@linux.vnet.ibm.com> - 2017-07-07 17:10 +0200
        Re: [PATCH 4/5] powernv:idle: Move initialization of sibling pacas  to pnv_alloc_idle_core_states Nicholas Piggin <npiggin@gmail.com> - 2017-07-08 11:10 +0200
          Re: [PATCH 4/5] powernv:idle: Move initialization of sibling pacas to pnv_alloc_idle_core_states Michael Ellerman <mpe@ellerman.id.au> - 2017-07-10 06:40 +0200

csiph-web