From 077fcf116c8c2bd7ee9487b645aa3b50368db7e1 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 11 Feb 2015 15:27:12 -0800 Subject: mm/thp: allocate transparent hugepages on local node This make sure that we try to allocate hugepages from local node if allowed by mempolicy. If we can't, we fallback to small page allocation based on mempolicy. This is based on the observation that allocating pages on local node is more beneficial than allocating hugepages on remote node. With this patch applied we may find transparent huge page allocation failures if the current node doesn't have enough freee hugepages. Before this patch such failures result in us retrying the allocation on other nodes in the numa node mask. [akpm@linux-foundation.org: fix comment, add CONFIG_TRANSPARENT_HUGEPAGE dependency] Signed-off-by: Aneesh Kumar K.V Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Cc: David Rientjes Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 72 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 72 insertions(+) (limited to 'mm/mempolicy.c') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 0e0961b8c39c..8a32873fdbf7 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2030,6 +2030,78 @@ retry_cpuset: return page; } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/** + * alloc_hugepage_vma: Allocate a hugepage for a VMA + * @gfp: + * %GFP_USER user allocation. + * %GFP_KERNEL kernel allocations, + * %GFP_HIGHMEM highmem/user allocations, + * %GFP_FS allocation should not call back into a file system. + * %GFP_ATOMIC don't sleep. + * + * @vma: Pointer to VMA or NULL if not available. + * @addr: Virtual Address of the allocation. Must be inside the VMA. + * @order: Order of the hugepage for gfp allocation. + * + * This functions allocate a huge page from the kernel page pool and applies + * a NUMA policy associated with the VMA or the current process. + * For policy other than %MPOL_INTERLEAVE, we make sure we allocate hugepage + * only from the current node if the current node is part of the node mask. + * If we can't allocate a hugepage we fail the allocation and don' try to fallback + * to other nodes in the node mask. If the current node is not part of node mask + * or if the NUMA policy is MPOL_INTERLEAVE we use the allocator that can + * fallback to nodes in the policy node mask. + * + * When VMA is not NULL caller must hold down_read on the mmap_sem of the + * mm_struct of the VMA to prevent it from going away. Should be used for + * all allocations for pages that will be mapped into + * user space. Returns NULL when no page can be allocated. + * + * Should be called with vma->vm_mm->mmap_sem held. + * + */ +struct page *alloc_hugepage_vma(gfp_t gfp, struct vm_area_struct *vma, + unsigned long addr, int order) +{ + struct page *page; + nodemask_t *nmask; + struct mempolicy *pol; + int node = numa_node_id(); + unsigned int cpuset_mems_cookie; + +retry_cpuset: + pol = get_vma_policy(vma, addr); + cpuset_mems_cookie = read_mems_allowed_begin(); + /* + * For interleave policy, we don't worry about + * current node. Otherwise if current node is + * in nodemask, try to allocate hugepage from + * the current node. Don't fall back to other nodes + * for THP. + */ + if (unlikely(pol->mode == MPOL_INTERLEAVE)) + goto alloc_with_fallback; + nmask = policy_nodemask(gfp, pol); + if (!nmask || node_isset(node, *nmask)) { + mpol_cond_put(pol); + page = alloc_pages_exact_node(node, gfp, order); + if (unlikely(!page && + read_mems_allowed_retry(cpuset_mems_cookie))) + goto retry_cpuset; + return page; + } +alloc_with_fallback: + mpol_cond_put(pol); + /* + * if current node is not part of node mask, try + * the allocation from any node, and we can do retry + * in that case. + */ + return alloc_pages_vma(gfp, order, vma, addr, node); +} +#endif + /** * alloc_pages_current - Allocate pages. * -- cgit v1.2.3