The patch titled mm: use correct numa policy node for transparent hugepages has been removed from the -mm tree. Its filename was mm-use-correct-numa-policy-node-for-transparent-hugepages.patch This patch was dropped because it was merged into mainline or a subsystem tree The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/ ------------------------------------------------------ Subject: mm: use correct numa policy node for transparent hugepages From: Andi Kleen <ak@xxxxxxxxxxxxxxx> Pass down the correct node for a transparent hugepage allocation. Most callers continue to use the current node, however the hugepaged daemon now uses the previous node of the first to be collapsed page instead. This ensures that khugepaged does not mess up local memory for an existing process which uses local policy. The choice of node is somewhat primitive currently: it just uses the node of the first page in the pmd range. An alternative would be to look at multiple pages and use the most popular node. I used the simplest variant for now which should work well enough for the case of all pages being on the same node. [akpm@xxxxxxxxxxxxxxxxxxxx: coding-style fixes] Acked-by: Andrea Arcangeli <aarcange@xxxxxxxxxx> Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/huge_memory.c | 24 +++++++++++++++++------- mm/mempolicy.c | 3 ++- 2 files changed, 19 insertions(+), 8 deletions(-) diff -puN mm/huge_memory.c~mm-use-correct-numa-policy-node-for-transparent-hugepages mm/huge_memory.c --- a/mm/huge_memory.c~mm-use-correct-numa-policy-node-for-transparent-hugepages +++ a/mm/huge_memory.c @@ -650,10 +650,10 @@ static inline gfp_t alloc_hugepage_gfpma static inline struct page *alloc_hugepage_vma(int defrag, struct vm_area_struct *vma, - unsigned long haddr) + unsigned long haddr, int nd) { return alloc_pages_vma(alloc_hugepage_gfpmask(defrag), - HPAGE_PMD_ORDER, vma, haddr, numa_node_id()); + HPAGE_PMD_ORDER, vma, haddr, nd); } #ifndef CONFIG_NUMA @@ -678,7 +678,7 @@ int do_huge_pmd_anonymous_page(struct mm if (unlikely(khugepaged_enter(vma))) return VM_FAULT_OOM; page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), - vma, haddr); + vma, haddr, numa_node_id()); if (unlikely(!page)) goto out; if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) { @@ -902,7 +902,7 @@ int do_huge_pmd_wp_page(struct mm_struct if (transparent_hugepage_enabled(vma) && !transparent_hugepage_debug_cow()) new_page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), - vma, haddr); + vma, haddr, numa_node_id()); else new_page = NULL; @@ -1745,7 +1745,8 @@ static void __collapse_huge_page_copy(pt static void collapse_huge_page(struct mm_struct *mm, unsigned long address, struct page **hpage, - struct vm_area_struct *vma) + struct vm_area_struct *vma, + int node) { pgd_t *pgd; pud_t *pud; @@ -1773,7 +1774,8 @@ static void collapse_huge_page(struct mm * mmap_sem in read mode is good idea also to allow greater * scalability. */ - new_page = alloc_hugepage_vma(khugepaged_defrag(), vma, address); + new_page = alloc_hugepage_vma(khugepaged_defrag(), vma, address, + node); if (unlikely(!new_page)) { up_read(&mm->mmap_sem); *hpage = ERR_PTR(-ENOMEM); @@ -1919,6 +1921,7 @@ static int khugepaged_scan_pmd(struct mm struct page *page; unsigned long _address; spinlock_t *ptl; + int node = -1; VM_BUG_ON(address & ~HPAGE_PMD_MASK); @@ -1949,6 +1952,13 @@ static int khugepaged_scan_pmd(struct mm page = vm_normal_page(vma, _address, pteval); if (unlikely(!page)) goto out_unmap; + /* + * Chose the node of the first page. This could + * be more sophisticated and look at more pages, + * but isn't for now. + */ + if (node == -1) + node = page_to_nid(page); VM_BUG_ON(PageCompound(page)); if (!PageLRU(page) || PageLocked(page) || !PageAnon(page)) goto out_unmap; @@ -1965,7 +1975,7 @@ out_unmap: pte_unmap_unlock(pte, ptl); if (ret) /* collapse_huge_page will return with the mmap_sem released */ - collapse_huge_page(mm, address, hpage, vma); + collapse_huge_page(mm, address, hpage, vma, node); out: return ret; } diff -puN mm/mempolicy.c~mm-use-correct-numa-policy-node-for-transparent-hugepages mm/mempolicy.c --- a/mm/mempolicy.c~mm-use-correct-numa-policy-node-for-transparent-hugepages +++ a/mm/mempolicy.c @@ -1891,7 +1891,8 @@ struct page *alloc_pages_current(gfp_t g page = alloc_page_interleave(gfp, order, interleave_nodes(pol)); else page = __alloc_pages_nodemask(gfp, order, - policy_zonelist(gfp, pol), policy_nodemask(gfp, pol)); + policy_zonelist(gfp, pol, numa_node_id()), + policy_nodemask(gfp, pol)); put_mems_allowed(); return page; } _ Patches currently in -mm which might be from ak@xxxxxxxxxxxxxxx are origin.patch linux-next.patch mm-numa-aware-alloc_task_struct_node.patch mm-numa-aware-alloc_thread_info_node.patch kthread-numa-aware-kthread_create_on_cpu.patch kthread-use-kthread_create_on_cpu.patch mm-add-__gfp_other_node-flag.patch mm-add-__gfp_other_node-flag-checkpatch-fixes.patch mm-use-__gfp_other_node-for-transparent-huge-pages.patch mm-use-__gfp_other_node-for-transparent-huge-pages-checkpatch-fixes.patch mm-add-vm-counters-for-transparent-hugepages.patch mm-add-vm-counters-for-transparent-hugepages-checkpatch-fixes.patch llist-irq_work-use-llist-in-irq_work.patch llist-net-rds-replace-xlist-in-net-rds-xlisth-with-llist.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html