From 5da7ca86078964cbfe6c83efc1205904587706fe Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Fri, 6 Jan 2006 00:10:46 -0800 Subject: [PATCH] Add NUMA policy support for huge pages. The huge_zonelist() function in the memory policy layer provides an list of zones ordered by NUMA distance. The hugetlb layer will walk that list looking for a zone that has available huge pages but is also in the nodeset of the current cpuset. This patch does not contain the folding of find_or_alloc_huge_page() that was controversial in the earlier discussion. Signed-off-by: Christoph Lameter Cc: Andi Kleen Acked-by: William Lee Irwin III Cc: Adam Litke Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux/mempolicy.h') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 8b67cf8..817db64 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -156,6 +156,8 @@ extern void numa_default_policy(void); extern void numa_policy_init(void); extern void numa_policy_rebind(const nodemask_t *old, const nodemask_t *new); extern struct mempolicy default_policy; +extern struct zonelist *huge_zonelist(struct vm_area_struct *vma, + unsigned long addr); #else @@ -232,6 +234,12 @@ static inline void numa_policy_rebind(const nodemask_t *old, { } +static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma, + unsigned long addr) +{ + return NODE_DATA(0)->node_zonelists + gfp_zone(GFP_HIGHUSER); +} + #endif /* CONFIG_NUMA */ #endif /* __KERNEL__ */ -- cgit v1.1 From 21abb1478a87e26f5fa71dbcb7cf4264272c2248 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Fri, 6 Jan 2006 00:10:47 -0800 Subject: [PATCH] Remove old node based policy interface from mempolicy.c mempolicy.c contains provisional interface for huge page allocation based on node numbers. This is in use in SLES9 but was never used (AFAIK) in upstream versions of Linux. Huge page allocations now use zonelists to figure out where to allocate pages. The use of zonelists allows us to find the closest hugepage which was the consideration of the NUMA distance for huge page allocations. Remove the obsolete functions. Signed-off-by: Christoph Lameter Cc: Andi Kleen Acked-by: William Lee Irwin III Cc: Adam Litke Acked-by: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include/linux/mempolicy.h') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 817db64..b972f985 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -110,14 +110,6 @@ static inline int mpol_equal(struct mempolicy *a, struct mempolicy *b) #define mpol_set_vma_default(vma) ((vma)->vm_policy = NULL) /* - * Hugetlb policy. i386 hugetlb so far works with node numbers - * instead of zone lists, so give it special interfaces for now. - */ -extern int mpol_first_node(struct vm_area_struct *vma, unsigned long addr); -extern int mpol_node_valid(int nid, struct vm_area_struct *vma, - unsigned long addr); - -/* * Tree of shared policies for a shared memory region. * Maintain the policies in a pseudo mm that contains vmas. The vmas * carry the policy. As a special twist the pseudo mm is indexed in pages, not @@ -184,17 +176,6 @@ static inline struct mempolicy *mpol_copy(struct mempolicy *old) return NULL; } -static inline int mpol_first_node(struct vm_area_struct *vma, unsigned long a) -{ - return numa_node_id(); -} - -static inline int -mpol_node_valid(int nid, struct vm_area_struct *vma, unsigned long a) -{ - return 1; -} - struct shared_policy {}; static inline int mpol_set_shared_policy(struct shared_policy *info, -- cgit v1.1 From 4be38e351c5f455f6f490f5aff29053e33ab4f99 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Fri, 6 Jan 2006 00:11:17 -0800 Subject: [PATCH] mm: move determination of policy_zone into page allocator Currently the function to build a zonelist for a BIND policy has the side effect to set the policy_zone. This seems to be a bit strange. policy zone seems to not be initialized elsewhere and therefore 0. Do we police ZONE_DMA if no bind policy has been used yet? This patch moves the determination of the zone to apply policies to into the page allocator. We determine the zone while building the zonelist for nodes. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux/mempolicy.h') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index b972f985..ed00b27 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -151,6 +151,14 @@ extern struct mempolicy default_policy; extern struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr); +extern int policy_zone; + +static inline void check_highest_zone(int k) +{ + if (k > policy_zone) + policy_zone = k; +} + #else struct mempolicy {}; @@ -221,6 +229,9 @@ static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma, return NODE_DATA(0)->node_zonelists + gfp_zone(GFP_HIGHUSER); } +static inline void check_highest_zone(int k) +{ +} #endif /* CONFIG_NUMA */ #endif /* __KERNEL__ */ -- cgit v1.1