The patch titled Subject: thp: introduce sysfs knob to disable huge zero page has been added to the -mm tree. Its filename is thp-introduce-sysfs-knob-to-disable-huge-zero-page.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 *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ From: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx> Subject: thp: introduce sysfs knob to disable huge zero page By default kernel tries to use huge zero page on read page fault. It's possible to disable huge zero page by writing 0 or enable it back by writing 1: echo 0 >/sys/kernel/mm/transparent_hugepage/khugepaged/use_zero_page echo 1 >/sys/kernel/mm/transparent_hugepage/khugepaged/use_zero_page Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx> Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx> Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx> Cc: "H. Peter Anvin" <hpa@xxxxxxxxxxxxxxx> Cc: Mel Gorman <mel@xxxxxxxxx> Cc: David Rientjes <rientjes@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- Documentation/vm/transhuge.txt | 7 +++++++ include/linux/huge_mm.h | 4 ++++ mm/huge_memory.c | 21 +++++++++++++++++++-- 3 files changed, 30 insertions(+), 2 deletions(-) diff -puN Documentation/vm/transhuge.txt~thp-introduce-sysfs-knob-to-disable-huge-zero-page Documentation/vm/transhuge.txt --- a/Documentation/vm/transhuge.txt~thp-introduce-sysfs-knob-to-disable-huge-zero-page +++ a/Documentation/vm/transhuge.txt @@ -116,6 +116,13 @@ echo always >/sys/kernel/mm/transparent_ echo madvise >/sys/kernel/mm/transparent_hugepage/defrag echo never >/sys/kernel/mm/transparent_hugepage/defrag +By default kernel tries to use huge zero page on read page fault. +It's possible to disable huge zero page by writing 0 or enable it +back by writing 1: + +echo 0 >/sys/kernel/mm/transparent_hugepage/khugepaged/use_zero_page +echo 1 >/sys/kernel/mm/transparent_hugepage/khugepaged/use_zero_page + khugepaged will be automatically started when transparent_hugepage/enabled is set to "always" or "madvise, and it'll be automatically shutdown if it's set to "never". diff -puN include/linux/huge_mm.h~thp-introduce-sysfs-knob-to-disable-huge-zero-page include/linux/huge_mm.h --- a/include/linux/huge_mm.h~thp-introduce-sysfs-knob-to-disable-huge-zero-page +++ a/include/linux/huge_mm.h @@ -39,6 +39,7 @@ enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_DEFRAG_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG, + TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG, #ifdef CONFIG_DEBUG_VM TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG, #endif @@ -78,6 +79,9 @@ extern bool is_vma_temporary_stack(struc (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG) && \ (__vma)->vm_flags & VM_HUGEPAGE)) +#define transparent_hugepage_use_zero_page() \ + (transparent_hugepage_flags & \ + (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) #ifdef CONFIG_DEBUG_VM #define transparent_hugepage_debug_cow() \ (transparent_hugepage_flags & \ diff -puN mm/huge_memory.c~thp-introduce-sysfs-knob-to-disable-huge-zero-page mm/huge_memory.c --- a/mm/huge_memory.c~thp-introduce-sysfs-knob-to-disable-huge-zero-page +++ a/mm/huge_memory.c @@ -40,7 +40,8 @@ unsigned long transparent_hugepage_flags (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)| #endif (1<<TRANSPARENT_HUGEPAGE_DEFRAG_FLAG)| - (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); + (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)| + (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); /* default scan 8*512 pte (or vmas) every 30 second */ static unsigned int khugepaged_pages_to_scan __read_mostly = HPAGE_PMD_NR*8; @@ -358,6 +359,20 @@ static ssize_t defrag_store(struct kobje static struct kobj_attribute defrag_attr = __ATTR(defrag, 0644, defrag_show, defrag_store); +static ssize_t use_zero_page_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return single_flag_show(kobj, attr, buf, + TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); +} +static ssize_t use_zero_page_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + return single_flag_store(kobj, attr, buf, count, + TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); +} +static struct kobj_attribute use_zero_page_attr = + __ATTR(use_zero_page, 0644, use_zero_page_show, use_zero_page_store); #ifdef CONFIG_DEBUG_VM static ssize_t debug_cow_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) @@ -379,6 +394,7 @@ static struct kobj_attribute debug_cow_a static struct attribute *hugepage_attr[] = { &enabled_attr.attr, &defrag_attr.attr, + &use_zero_page_attr.attr, #ifdef CONFIG_DEBUG_VM &debug_cow_attr.attr, #endif @@ -780,7 +796,8 @@ int do_huge_pmd_anonymous_page(struct mm return VM_FAULT_OOM; if (unlikely(khugepaged_enter(vma))) return VM_FAULT_OOM; - if (!(flags & FAULT_FLAG_WRITE)) { + if (!(flags & FAULT_FLAG_WRITE) && + transparent_hugepage_use_zero_page()) { pgtable_t pgtable; unsigned long zero_pfn; pgtable = pte_alloc_one(mm, haddr); _ Patches currently in -mm which might be from kirill.shutemov@xxxxxxxxxxxxxxx are linux-next.patch mm-use-is_enabledconfig_numa-instead-of-numa_build.patch mm-use-is_enabledconfig_compaction-instead-of-compaction_build.patch thp-huge-zero-page-basic-preparation.patch thp-huge-zero-page-basic-preparation-v6.patch thp-zap_huge_pmd-zap-huge-zero-pmd.patch thp-copy_huge_pmd-copy-huge-zero-page.patch thp-copy_huge_pmd-copy-huge-zero-page-v6.patch thp-do_huge_pmd_wp_page-handle-huge-zero-page.patch thp-do_huge_pmd_wp_page-handle-huge-zero-page-v6.patch thp-change_huge_pmd-keep-huge-zero-page-write-protected.patch thp-change-split_huge_page_pmd-interface.patch thp-change-split_huge_page_pmd-interface-v6.patch thp-implement-splitting-pmd-for-huge-zero-page.patch thp-implement-splitting-pmd-for-huge-zero-page-v6.patch thp-setup-huge-zero-page-on-non-write-page-fault.patch thp-lazy-huge-zero-page-allocation.patch thp-implement-refcounting-for-huge-zero-page.patch thp-vmstat-implement-hzp_alloc-and-hzp_alloc_failed-events.patch thp-vmstat-implement-hzp_alloc-and-hzp_alloc_failed-events-v6.patch thp-introduce-sysfs-knob-to-disable-huge-zero-page.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