The patch titled thp: add numa awareness to hugepage allocations has been added to the -mm tree. Its filename is thp-add-numa-awareness-to-hugepage-allocations.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find out what to do about this The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/ ------------------------------------------------------ Subject: thp: add numa awareness to hugepage allocations From: Andrea Arcangeli <aarcange@xxxxxxxxxx> It's mostly a matter of replacing alloc_pages with alloc_pages_vma after introducing alloc_pages_vma. khugepaged needs special handling as the allocation has to happen inside collapse_huge_page where the vma is known and an error has to be returned to the outer loop to sleep alloc_sleep_millisecs in case of failure. But it retains the more efficient logic of handling allocation failures in khugepaged in case of CONFIG_NUMA=n. Signed-off-by: Andrea Arcangeli <aarcange@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/gfp.h | 7 ++- mm/huge_memory.c | 87 +++++++++++++++++++++++++++++++++++------- mm/mempolicy.c | 13 +++--- 3 files changed, 87 insertions(+), 20 deletions(-) diff -puN include/linux/gfp.h~thp-add-numa-awareness-to-hugepage-allocations include/linux/gfp.h --- a/include/linux/gfp.h~thp-add-numa-awareness-to-hugepage-allocations +++ a/include/linux/gfp.h @@ -331,14 +331,17 @@ alloc_pages(gfp_t gfp_mask, unsigned int { return alloc_pages_current(gfp_mask, order); } -extern struct page *alloc_page_vma(gfp_t gfp_mask, +extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr); #else #define alloc_pages(gfp_mask, order) \ alloc_pages_node(numa_node_id(), gfp_mask, order) -#define alloc_page_vma(gfp_mask, vma, addr) alloc_pages(gfp_mask, 0) +#define alloc_pages_vma(gfp_mask, order, vma, addr) \ + alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) +#define alloc_page_vma(gfp_mask, vma, addr) \ + alloc_pages_vma(gfp_mask, 0, vma, addr) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); diff -puN mm/huge_memory.c~thp-add-numa-awareness-to-hugepage-allocations mm/huge_memory.c --- a/mm/huge_memory.c~thp-add-numa-awareness-to-hugepage-allocations +++ a/mm/huge_memory.c @@ -620,11 +620,26 @@ static int __do_huge_pmd_anonymous_page( return ret; } +static inline gfp_t alloc_hugepage_gfpmask(int defrag) +{ + return GFP_TRANSHUGE & ~(defrag ? 0 : __GFP_WAIT); +} + +static inline struct page *alloc_hugepage_vma(int defrag, + struct vm_area_struct *vma, + unsigned long haddr) +{ + return alloc_pages_vma(alloc_hugepage_gfpmask(defrag), + HPAGE_PMD_ORDER, vma, haddr); +} + +#ifndef CONFIG_NUMA static inline struct page *alloc_hugepage(int defrag) { - return alloc_pages(GFP_TRANSHUGE & ~(defrag ? 0 : __GFP_WAIT), + return alloc_pages(alloc_hugepage_gfpmask(defrag), HPAGE_PMD_ORDER); } +#endif int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, @@ -639,7 +654,8 @@ int do_huge_pmd_anonymous_page(struct mm return VM_FAULT_OOM; if (unlikely(khugepaged_enter(vma))) return VM_FAULT_OOM; - page = alloc_hugepage(transparent_hugepage_defrag(vma)); + page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), + vma, haddr); if (unlikely(!page)) goto out; if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) { @@ -862,7 +878,8 @@ int do_huge_pmd_wp_page(struct mm_struct if (transparent_hugepage_enabled(vma) && !transparent_hugepage_debug_cow()) - new_page = alloc_hugepage(transparent_hugepage_defrag(vma)); + new_page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), + vma, haddr); else new_page = NULL; @@ -1661,7 +1678,11 @@ static void collapse_huge_page(struct mm unsigned long hstart, hend; VM_BUG_ON(address & ~HPAGE_PMD_MASK); +#ifndef CONFIG_NUMA VM_BUG_ON(!*hpage); +#else + VM_BUG_ON(*hpage); +#endif /* * Prevent all access to pagetables with the exception of @@ -1699,9 +1720,17 @@ static void collapse_huge_page(struct mm if (!pmd_present(*pmd) || pmd_trans_huge(*pmd)) goto out; +#ifndef CONFIG_NUMA new_page = *hpage; - if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) +#else + new_page = alloc_hugepage_vma(khugepaged_defrag(), vma, address); + if (unlikely(!new_page)) { + *hpage = ERR_PTR(-ENOMEM); goto out; + } +#endif + if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) + goto out_put_page; anon_vma_lock(vma->anon_vma); @@ -1730,7 +1759,7 @@ static void collapse_huge_page(struct mm spin_unlock(&mm->page_table_lock); anon_vma_unlock(vma->anon_vma); mem_cgroup_uncharge_page(new_page); - goto out; + goto out_put_page; } /* @@ -1765,10 +1794,19 @@ static void collapse_huge_page(struct mm mm->nr_ptes--; spin_unlock(&mm->page_table_lock); +#ifndef CONFIG_NUMA *hpage = NULL; +#endif khugepaged_pages_collapsed++; out: up_write(&mm->mmap_sem); + return; + +out_put_page: +#ifdef CONFIG_NUMA + put_page(new_page); +#endif + goto out; } static int khugepaged_scan_pmd(struct mm_struct *mm, @@ -2001,11 +2039,16 @@ static void khugepaged_do_scan(struct pa while (progress < pages) { cond_resched(); +#ifndef CONFIG_NUMA if (!*hpage) { *hpage = alloc_hugepage(khugepaged_defrag()); if (unlikely(!*hpage)) break; } +#else + if (IS_ERR(*hpage)) + break; +#endif spin_lock(&khugepaged_mm_lock); if (!khugepaged_scan.mm_slot) @@ -2020,37 +2063,55 @@ static void khugepaged_do_scan(struct pa } } +static void khugepaged_alloc_sleep(void) +{ + DEFINE_WAIT(wait); + add_wait_queue(&khugepaged_wait, &wait); + schedule_timeout_interruptible( + msecs_to_jiffies( + khugepaged_alloc_sleep_millisecs)); + remove_wait_queue(&khugepaged_wait, &wait); +} + +#ifndef CONFIG_NUMA static struct page *khugepaged_alloc_hugepage(void) { struct page *hpage; do { hpage = alloc_hugepage(khugepaged_defrag()); - if (!hpage) { - DEFINE_WAIT(wait); - add_wait_queue(&khugepaged_wait, &wait); - schedule_timeout_interruptible( - msecs_to_jiffies( - khugepaged_alloc_sleep_millisecs)); - remove_wait_queue(&khugepaged_wait, &wait); - } + if (!hpage) + khugepaged_alloc_sleep(); } while (unlikely(!hpage) && likely(khugepaged_enabled())); return hpage; } +#endif static void khugepaged_loop(void) { struct page *hpage; +#ifdef CONFIG_NUMA + hpage = NULL; +#endif while (likely(khugepaged_enabled())) { +#ifndef CONFIG_NUMA hpage = khugepaged_alloc_hugepage(); if (unlikely(!hpage)) break; +#else + if (IS_ERR(hpage)) { + khugepaged_alloc_sleep(); + hpage = NULL; + } +#endif khugepaged_do_scan(&hpage); +#ifndef CONFIG_NUMA if (hpage) put_page(hpage); +#endif if (khugepaged_has_work()) { DEFINE_WAIT(wait); if (!khugepaged_scan_sleep_millisecs) diff -puN mm/mempolicy.c~thp-add-numa-awareness-to-hugepage-allocations mm/mempolicy.c --- a/mm/mempolicy.c~thp-add-numa-awareness-to-hugepage-allocations +++ a/mm/mempolicy.c @@ -1796,7 +1796,7 @@ static struct page *alloc_page_interleav } /** - * alloc_page_vma - Allocate a page for a VMA. + * alloc_pages_vma - Allocate a page for a VMA. * * @gfp: * %GFP_USER user allocation. @@ -1805,6 +1805,7 @@ static struct page *alloc_page_interleav * %GFP_FS allocation should not call back into a file system. * %GFP_ATOMIC don't sleep. * + * @order:Order of the GFP allocation. * @vma: Pointer to VMA or NULL if not available. * @addr: Virtual Address of the allocation. Must be inside the VMA. * @@ -1818,7 +1819,8 @@ static struct page *alloc_page_interleav * Should be called with the mm_sem of the vma hold. */ struct page * -alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr) +alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, + unsigned long addr) { struct mempolicy *pol = get_vma_policy(current, vma, addr); struct zonelist *zl; @@ -1830,7 +1832,7 @@ alloc_page_vma(gfp_t gfp, struct vm_area nid = interleave_nid(pol, vma, addr, PAGE_SHIFT); mpol_cond_put(pol); - page = alloc_page_interleave(gfp, 0, nid); + page = alloc_page_interleave(gfp, order, nid); put_mems_allowed(); return page; } @@ -1839,7 +1841,7 @@ alloc_page_vma(gfp_t gfp, struct vm_area /* * slow path: ref counted shared policy */ - struct page *page = __alloc_pages_nodemask(gfp, 0, + struct page *page = __alloc_pages_nodemask(gfp, order, zl, policy_nodemask(gfp, pol)); __mpol_put(pol); put_mems_allowed(); @@ -1848,7 +1850,8 @@ alloc_page_vma(gfp_t gfp, struct vm_area /* * fast path: default or task policy */ - page = __alloc_pages_nodemask(gfp, 0, zl, policy_nodemask(gfp, pol)); + page = __alloc_pages_nodemask(gfp, order, zl, + policy_nodemask(gfp, pol)); put_mems_allowed(); return page; } _ Patches currently in -mm which might be from aarcange@xxxxxxxxxx are mm-compaction-add-trace-events-for-memory-compaction-activity.patch mm-vmscan-convert-lumpy_mode-into-a-bitmask.patch mm-vmscan-reclaim-order-0-and-use-compaction-instead-of-lumpy-reclaim.patch mm-vmscan-reclaim-order-0-and-use-compaction-instead-of-lumpy-reclaim-fix.patch mm-migration-allow-migration-to-operate-asynchronously-and-avoid-synchronous-compaction-in-the-faster-path.patch mm-migration-allow-migration-to-operate-asynchronously-and-avoid-synchronous-compaction-in-the-faster-path-fix.patch mm-migration-cleanup-migrate_pages-api-by-matching-types-for-offlining-and-sync.patch mm-compaction-perform-a-faster-migration-scan-when-migrating-asynchronously.patch mm-vmscan-rename-lumpy_mode-to-reclaim_mode.patch mm-vmscan-rename-lumpy_mode-to-reclaim_mode-fix.patch thp-ksm-free-swap-when-swapcache-page-is-replaced.patch thp-fix-bad_page-to-show-the-real-reason-the-page-is-bad.patch thp-transparent-hugepage-support-documentation.patch thp-mm-define-madv_hugepage.patch thp-compound_lock.patch thp-alter-compound-get_page-put_page.patch thp-put_page-recheck-pagehead-after-releasing-the-compound_lock.patch thp-update-futex-compound-knowledge.patch thp-clear-compound-mapping.patch thp-add-native_set_pmd_at.patch thp-add-pmd-paravirt-ops.patch thp-no-paravirt-version-of-pmd-ops.patch thp-export-maybe_mkwrite.patch thp-comment-reminder-in-destroy_compound_page.patch thp-config_transparent_hugepage.patch thp-special-pmd_trans_-functions.patch thp-add-pmd-mangling-generic-functions.patch thp-add-pmd-mangling-functions-to-x86.patch thp-bail-out-gup_fast-on-splitting-pmd.patch thp-pte-alloc-trans-splitting.patch thp-add-pmd-mmu_notifier-helpers.patch thp-clear-page-compound.patch thp-add-pmd_huge_pte-to-mm_struct.patch thp-split_huge_page_mm-vma.patch thp-split_huge_page-paging.patch thp-clear_copy_huge_page.patch thp-_gfp_no_kswapd.patch thp-dont-alloc-harder-for-gfp-nomemalloc-even-if-nowait.patch thp-transparent-hugepage-core.patch thp-split_huge_page-anon_vma-ordering-dependency.patch thp-verify-pmd_trans_huge-isnt-leaking.patch thp-madvisemadv_hugepage.patch thp-add-pagetranscompound.patch thp-pmd_trans_huge-migrate-bugcheck.patch thp-memcg-compound.patch thp-transhuge-memcg-commit-tail-pages-at-charge.patch thp-memcg-huge-memory.patch thp-transparent-hugepage-vmstat.patch thp-khugepaged.patch thp-khugepaged-vma-merge.patch thp-skip-transhuge-pages-in-ksm-for-now.patch thp-remove-pg_buddy.patch thp-add-x86-32bit-support.patch thp-mincore-transparent-hugepage-support.patch thp-add-pmd_modify.patch thp-mprotect-pass-vma-down-to-page-table-walkers.patch thp-mprotect-transparent-huge-page-support.patch thp-set-recommended-min-free-kbytes.patch thp-enable-direct-defrag.patch thp-add-numa-awareness-to-hugepage-allocations.patch thp-allocate-memory-in-khugepaged-outside-of-mmap_sem-write-mode.patch thp-transparent-hugepage-config-choice.patch thp-select-config_compaction-if-transparent_hugepage-enabled.patch thp-transhuge-isolate_migratepages.patch thp-avoid-breaking-huge-pmd-invariants-in-case-of-vma_adjust-failures.patch thp-dont-allow-transparent-hugepage-support-without-pse.patch thp-mmu_notifier_test_young.patch thp-freeze-khugepaged-and-ksmd.patch thp-use-compaction-in-kswapd-for-gfp_atomic-order-0.patch thp-use-compaction-for-all-allocation-orders.patch thp-disable-transparent-hugepages-by-default-on-small-systems.patch thp-fix-anon-memory-statistics-with-transparent-hugepages.patch thp-scale-nr_rotated-to-balance-memory-pressure.patch thp-transparent-hugepage-sysfs-meminfo.patch thp-add-debug-checks-for-mapcount-related-invariants.patch thp-fix-memory-failure-hugetlbfs-vs-thp-collision.patch thp-compound_trans_order.patch thp-mm-define-madv_nohugepage.patch thp-madvisemadv_nohugepage.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