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 --- mm/mempolicy.c | 39 ++++++++++++++++++++++++++++++--------- 1 file changed, 30 insertions(+), 9 deletions(-) (limited to 'mm/mempolicy.c') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 72f402cc9c9a..45c51ac63443 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -785,6 +785,34 @@ static unsigned offset_il_node(struct mempolicy *pol, return nid; } +/* Determine a node number for interleave */ +static inline unsigned interleave_nid(struct mempolicy *pol, + struct vm_area_struct *vma, unsigned long addr, int shift) +{ + if (vma) { + unsigned long off; + + off = vma->vm_pgoff; + off += (addr - vma->vm_start) >> shift; + return offset_il_node(pol, vma, off); + } else + return interleave_nodes(pol); +} + +/* Return a zonelist suitable for a huge page allocation. */ +struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr) +{ + struct mempolicy *pol = get_vma_policy(current, vma, addr); + + if (pol->policy == MPOL_INTERLEAVE) { + unsigned nid; + + nid = interleave_nid(pol, vma, addr, HPAGE_SHIFT); + return NODE_DATA(nid)->node_zonelists + gfp_zone(GFP_HIGHUSER); + } + return zonelist_policy(GFP_HIGHUSER, pol); +} + /* Allocate a page in interleaved policy. Own path because it needs to do special accounting. */ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, @@ -833,15 +861,8 @@ alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr) if (unlikely(pol->policy == MPOL_INTERLEAVE)) { unsigned nid; - if (vma) { - unsigned long off; - off = vma->vm_pgoff; - off += (addr - vma->vm_start) >> PAGE_SHIFT; - nid = offset_il_node(pol, vma, off); - } else { - /* fall back to process interleaving */ - nid = interleave_nodes(pol); - } + + nid = interleave_nid(pol, vma, addr, PAGE_SHIFT); return alloc_page_interleave(gfp, 0, nid); } return __alloc_pages(gfp, 0, zonelist_policy(gfp, pol)); -- cgit v1.2.3-55-g7522