Re: [PATCH] page_alloc: skip cpuset enforcement for lower zone allocations (v5)
On Fri, May 30, 2014 at 08:50:56AM -0500, Christoph Lameter wrote: > On Thu, 29 May 2014, David Rientjes wrote: > > > When I said that my point about mempolicies needs more thought, I wasn't > > expecting that there would be no discussion -- at least _something_ that > > would say why we don't care about the mempolicy case. > > Lets get Andi involved here too. I'm not fully sure about the use case for this. On the NUMA systems I'm aware of usually only node 0 has <4GB, so mem policy is pointless. But anyways it seems ok to me to ignore mempolicies. Mempolicies are primarily for user space, which doesn't use GFP_DMA32. -ANdi -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH] page_alloc: skip cpuset enforcement for lower zone allocations (v5)
On Thu, 29 May 2014, David Rientjes wrote: > When I said that my point about mempolicies needs more thought, I wasn't > expecting that there would be no discussion -- at least _something_ that > would say why we don't care about the mempolicy case. Lets get Andi involved here too. > The motivation here is identical for both cpusets and mempolicies. What > is the significant difference between attaching a process to a cpuset > without access to lowmem and a process doing set_mempolicy(MPOL_BIND) > without access to lowmem? Is it because the process should know what it's > doing if it asks for a mempolicy that doesn't include lowmem? If so, is > the cpusets case different because the cpuset attacher isn't held to the > same standard? > > I'd argue that an application may never know if it needs to allocate > GFP_DMA32 or not since its a property of the hardware that its running on > and my driver may need to access lowmem while yours may not. I may even > configure CONFIG_ZONE_DMA=n and CONFIG_ZONE_DMA32=n because I know the > _hardware_ requirements of my platforms. Right. This is a hardware issue and the hardware is pretty messed up. And now one wants to use NUMA features? > If there is no difference, then why are we allowing the exception for > cpusets and not mempolicies? > > I really think you want to allow both cpusets and mempolicies. I'd like > to hear Christoph's thoughts on it as well, though. I said something elsewhere in the thread. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH] page_alloc: skip cpuset enforcement for lower zone allocations (v5)
On Thu, May 29, 2014 at 04:54:00PM -0700, David Rientjes wrote: > On Thu, 29 May 2014, Marcelo Tosatti wrote: > > > diff --git a/kernel/cpuset.c b/kernel/cpuset.c > > index 3d54c41..3bbc23f 100644 > > --- a/kernel/cpuset.c > > +++ b/kernel/cpuset.c > > @@ -2374,6 +2374,7 @@ static struct cpuset > > *nearest_hardwall_ancestor(struct cpuset *cs) > > * variable 'wait' is not set, and the bit ALLOC_CPUSET is not set > > * in alloc_flags. That logic and the checks below have the combined > > * affect that: > > + * gfp_zone(mask) < policy_zone - any node ok > > * in_interrupt - any node ok (current task context irrelevant) > > * GFP_ATOMIC - any node ok > > * TIF_MEMDIE - any node ok > > @@ -2392,6 +2393,10 @@ int __cpuset_node_allowed_softwall(int node, gfp_t > > gfp_mask) > > > > if (in_interrupt() || (gfp_mask & __GFP_THISNODE)) > > return 1; > > +#ifdef CONFIG_NUMA > > + if (gfp_zone(gfp_mask) < policy_zone) > > + return 1; > > +#endif > > might_sleep_if(!(gfp_mask & __GFP_HARDWALL)); > > if (node_isset(node, current->mems_allowed)) > > return 1; > > diff --git a/mm/page_alloc.c b/mm/page_alloc.c > > index 5dba293..0fd6923 100644 > > --- a/mm/page_alloc.c > > +++ b/mm/page_alloc.c > > @@ -2723,6 +2723,11 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int > > order, > > if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order)) > > return NULL; > > > > +#ifdef CONFIG_NUMA > > + if (!nodemask && gfp_zone(gfp_mask) < policy_zone) > > + nodemask = &node_states[N_MEMORY]; > > +#endif > > + > > retry_cpuset: > > cpuset_mems_cookie = read_mems_allowed_begin(); > > > > When I said that my point about mempolicies needs more thought, I wasn't > expecting that there would be no discussion -- at least _something_ that > would say why we don't care about the mempolicy case. We care about the mempolicy case, and that is taken care of by apply_policy_zone. Or does that code fail to handle a particular case ? > The motivation here is identical for both cpusets and mempolicies. What > is the significant difference between attaching a process to a cpuset > without access to lowmem and a process doing set_mempolicy(MPOL_BIND) > without access to lowmem? Is it because the process should know what it's > doing if it asks for a mempolicy that doesn't include lowmem? If so, is > the cpusets case different because the cpuset attacher isn't held to the > same standard? > > I'd argue that an application may never know if it needs to allocate > GFP_DMA32 or not since its a property of the hardware that its running on > and my driver may need to access lowmem while yours may not. I may even > configure CONFIG_ZONE_DMA=n and CONFIG_ZONE_DMA32=n because I know the > _hardware_ requirements of my platforms. > > If there is no difference, then why are we allowing the exception for > cpusets and not mempolicies? > > I really think you want to allow both cpusets and mempolicies. I'd like > to hear Christoph's thoughts on it as well, though. > > Furthermore, I don't know why you're opposed to the comments that Andrew > added here. In the first version of this patch, I suggested a comment and > you referred to a kernel/cpuset.c comment. Nowhere in the above change to > the page allocator would make anyone think of cpusets or what it is trying > to do. Please comment the code accordingly so your intention is > understood for everybody else who happens upon your code. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH] page_alloc: skip cpuset enforcement for lower zone allocations (v5)
On Thu, 29 May 2014, Marcelo Tosatti wrote: > diff --git a/kernel/cpuset.c b/kernel/cpuset.c > index 3d54c41..3bbc23f 100644 > --- a/kernel/cpuset.c > +++ b/kernel/cpuset.c > @@ -2374,6 +2374,7 @@ static struct cpuset *nearest_hardwall_ancestor(struct > cpuset *cs) > * variable 'wait' is not set, and the bit ALLOC_CPUSET is not set > * in alloc_flags. That logic and the checks below have the combined > * affect that: > + * gfp_zone(mask) < policy_zone - any node ok > * in_interrupt - any node ok (current task context irrelevant) > * GFP_ATOMIC - any node ok > * TIF_MEMDIE - any node ok > @@ -2392,6 +2393,10 @@ int __cpuset_node_allowed_softwall(int node, gfp_t > gfp_mask) > > if (in_interrupt() || (gfp_mask & __GFP_THISNODE)) > return 1; > +#ifdef CONFIG_NUMA > + if (gfp_zone(gfp_mask) < policy_zone) > + return 1; > +#endif > might_sleep_if(!(gfp_mask & __GFP_HARDWALL)); > if (node_isset(node, current->mems_allowed)) > return 1; > diff --git a/mm/page_alloc.c b/mm/page_alloc.c > index 5dba293..0fd6923 100644 > --- a/mm/page_alloc.c > +++ b/mm/page_alloc.c > @@ -2723,6 +2723,11 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int > order, > if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order)) > return NULL; > > +#ifdef CONFIG_NUMA > + if (!nodemask && gfp_zone(gfp_mask) < policy_zone) > + nodemask = &node_states[N_MEMORY]; > +#endif > + > retry_cpuset: > cpuset_mems_cookie = read_mems_allowed_begin(); > When I said that my point about mempolicies needs more thought, I wasn't expecting that there would be no discussion -- at least _something_ that would say why we don't care about the mempolicy case. The motivation here is identical for both cpusets and mempolicies. What is the significant difference between attaching a process to a cpuset without access to lowmem and a process doing set_mempolicy(MPOL_BIND) without access to lowmem? Is it because the process should know what it's doing if it asks for a mempolicy that doesn't include lowmem? If so, is the cpusets case different because the cpuset attacher isn't held to the same standard? I'd argue that an application may never know if it needs to allocate GFP_DMA32 or not since its a property of the hardware that its running on and my driver may need to access lowmem while yours may not. I may even configure CONFIG_ZONE_DMA=n and CONFIG_ZONE_DMA32=n because I know the _hardware_ requirements of my platforms. If there is no difference, then why are we allowing the exception for cpusets and not mempolicies? I really think you want to allow both cpusets and mempolicies. I'd like to hear Christoph's thoughts on it as well, though. Furthermore, I don't know why you're opposed to the comments that Andrew added here. In the first version of this patch, I suggested a comment and you referred to a kernel/cpuset.c comment. Nowhere in the above change to the page allocator would make anyone think of cpusets or what it is trying to do. Please comment the code accordingly so your intention is understood for everybody else who happens upon your code. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
[PATCH] page_alloc: skip cpuset enforcement for lower zone allocations (v5)
Zone specific allocations, such as GFP_DMA32, should not be restricted to cpusets allowed node list: the zones which such allocations demand might be contained in particular nodes outside the cpuset node list. Necessary for the following usecase: - driver which requires zone specific memory (such as KVM, which requires root pagetable at paddr < 4GB). - user wants to limit allocations of application to nodeX, and nodeX has no memory < 4GB. Signed-off-by: Marcelo Tosatti diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 3d54c41..3bbc23f 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2374,6 +2374,7 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) * variable 'wait' is not set, and the bit ALLOC_CPUSET is not set * in alloc_flags. That logic and the checks below have the combined * affect that: + * gfp_zone(mask) < policy_zone - any node ok * in_interrupt - any node ok (current task context irrelevant) * GFP_ATOMIC - any node ok * TIF_MEMDIE - any node ok @@ -2392,6 +2393,10 @@ int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask) if (in_interrupt() || (gfp_mask & __GFP_THISNODE)) return 1; +#ifdef CONFIG_NUMA + if (gfp_zone(gfp_mask) < policy_zone) + return 1; +#endif might_sleep_if(!(gfp_mask & __GFP_HARDWALL)); if (node_isset(node, current->mems_allowed)) return 1; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5dba293..0fd6923 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2723,6 +2723,11 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order)) return NULL; +#ifdef CONFIG_NUMA + if (!nodemask && gfp_zone(gfp_mask) < policy_zone) + nodemask = &node_states[N_MEMORY]; +#endif + retry_cpuset: cpuset_mems_cookie = read_mems_allowed_begin(); -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
