The patch titled thp: remove PG_buddy has been added to the -mm tree. Its filename is thp-remove-pg_buddy.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: remove PG_buddy From: Andrea Arcangeli <aarcange@xxxxxxxxxx> PG_buddy can be converted to _mapcount == -2. So the PG_compound_lock can be added to page->flags without overflowing (because of the sparse section bits increasing) with CONFIG_X86_PAE=y and CONFIG_X86_PAT=y. This also has to move the memory hotplug code from _mapcount to lru.next to avoid any risk of clashes. We can't use lru.next for PG_buddy removal, but memory hotplug can use lru.next even more easily than the mapcount instead. Signed-off-by: Andrea Arcangeli <aarcange@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- fs/proc/page.c | 14 ++++++++------ include/linux/memory_hotplug.h | 14 +++++++++----- include/linux/mm.h | 21 +++++++++++++++++++++ include/linux/page-flags.h | 7 +------ mm/memory_hotplug.c | 14 ++++++++------ mm/page_alloc.c | 7 +++---- mm/sparse.c | 4 ++-- 7 files changed, 52 insertions(+), 29 deletions(-) diff -puN fs/proc/page.c~thp-remove-pg_buddy fs/proc/page.c --- a/fs/proc/page.c~thp-remove-pg_buddy +++ a/fs/proc/page.c @@ -116,15 +116,17 @@ u64 stable_page_flags(struct page *page) if (PageHuge(page)) u |= 1 << KPF_HUGE; - u |= kpf_copy_bit(k, KPF_LOCKED, PG_locked); - /* - * Caveats on high order pages: - * PG_buddy will only be set on the head page; SLUB/SLQB do the same - * for PG_slab; SLOB won't set PG_slab at all on compound pages. + * Caveats on high order pages: page->_count will only be set + * -1 on the head page; SLUB/SLQB do the same for PG_slab; + * SLOB won't set PG_slab at all on compound pages. */ + if (PageBuddy(page)) + u |= 1 << KPF_BUDDY; + + u |= kpf_copy_bit(k, KPF_LOCKED, PG_locked); + u |= kpf_copy_bit(k, KPF_SLAB, PG_slab); - u |= kpf_copy_bit(k, KPF_BUDDY, PG_buddy); u |= kpf_copy_bit(k, KPF_ERROR, PG_error); u |= kpf_copy_bit(k, KPF_DIRTY, PG_dirty); diff -puN include/linux/memory_hotplug.h~thp-remove-pg_buddy include/linux/memory_hotplug.h --- a/include/linux/memory_hotplug.h~thp-remove-pg_buddy +++ a/include/linux/memory_hotplug.h @@ -13,12 +13,16 @@ struct mem_section; #ifdef CONFIG_MEMORY_HOTPLUG /* - * Types for free bootmem. - * The normal smallest mapcount is -1. Here is smaller value than it. + * Types for free bootmem stored in page->lru.next. These have to be in + * some random range in unsigned long space for debugging purposes. */ -#define SECTION_INFO (-1 - 1) -#define MIX_SECTION_INFO (-1 - 2) -#define NODE_INFO (-1 - 3) +enum { + MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12, + SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE, + MIX_SECTION_INFO, + NODE_INFO, + MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO, +}; /* * pgdat resizing functions diff -puN include/linux/mm.h~thp-remove-pg_buddy include/linux/mm.h --- a/include/linux/mm.h~thp-remove-pg_buddy +++ a/include/linux/mm.h @@ -398,6 +398,27 @@ static inline void init_page_count(struc atomic_set(&page->_count, 1); } +/* + * PageBuddy() indicate that the page is free and in the buddy system + * (see mm/page_alloc.c). + */ +static inline int PageBuddy(struct page *page) +{ + return atomic_read(&page->_mapcount) == -2; +} + +static inline void __SetPageBuddy(struct page *page) +{ + VM_BUG_ON(atomic_read(&page->_mapcount) != -1); + atomic_set(&page->_mapcount, -2); +} + +static inline void __ClearPageBuddy(struct page *page) +{ + VM_BUG_ON(!PageBuddy(page)); + atomic_set(&page->_mapcount, -1); +} + void put_page(struct page *page); void put_pages_list(struct list_head *pages); diff -puN include/linux/page-flags.h~thp-remove-pg_buddy include/linux/page-flags.h --- a/include/linux/page-flags.h~thp-remove-pg_buddy +++ a/include/linux/page-flags.h @@ -48,9 +48,6 @@ * struct page (these bits with information) are always mapped into kernel * address space... * - * PG_buddy is set to indicate that the page is free and in the buddy system - * (see mm/page_alloc.c). - * * PG_hwpoison indicates that a page got corrupted in hardware and contains * data with incorrect ECC bits that triggered a machine check. Accessing is * not safe since it may cause another machine check. Don't touch! @@ -96,7 +93,6 @@ enum pageflags { PG_swapcache, /* Swap page: swp_entry_t in private */ PG_mappedtodisk, /* Has blocks allocated on-disk */ PG_reclaim, /* To be reclaimed asap */ - PG_buddy, /* Page is free, on buddy lists */ PG_swapbacked, /* Page is backed by RAM/swap */ PG_unevictable, /* Page is "unevictable" */ #ifdef CONFIG_MMU @@ -233,7 +229,6 @@ PAGEFLAG(OwnerPriv1, owner_priv_1) TESTC * risky: they bypass page accounting. */ TESTPAGEFLAG(Writeback, writeback) TESTSCFLAG(Writeback, writeback) -__PAGEFLAG(Buddy, buddy) PAGEFLAG(MappedToDisk, mappedtodisk) /* PG_readahead is only used for file reads; PG_reclaim is only for writes */ @@ -457,7 +452,7 @@ static inline int PageTransCompound(stru #define PAGE_FLAGS_CHECK_AT_FREE \ (1 << PG_lru | 1 << PG_locked | \ 1 << PG_private | 1 << PG_private_2 | \ - 1 << PG_buddy | 1 << PG_writeback | 1 << PG_reserved | \ + 1 << PG_writeback | 1 << PG_reserved | \ 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \ 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON | \ __PG_COMPOUND_LOCK) diff -puN mm/memory_hotplug.c~thp-remove-pg_buddy mm/memory_hotplug.c --- a/mm/memory_hotplug.c~thp-remove-pg_buddy +++ a/mm/memory_hotplug.c @@ -82,9 +82,10 @@ static void release_memory_resource(stru #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE #ifndef CONFIG_SPARSEMEM_VMEMMAP -static void get_page_bootmem(unsigned long info, struct page *page, int type) +static void get_page_bootmem(unsigned long info, struct page *page, + unsigned long type) { - atomic_set(&page->_mapcount, type); + page->lru.next = (struct list_head *) type; SetPagePrivate(page); set_page_private(page, info); atomic_inc(&page->_count); @@ -94,15 +95,16 @@ static void get_page_bootmem(unsigned lo * so use __ref to tell modpost not to generate a warning */ void __ref put_page_bootmem(struct page *page) { - int type; + unsigned long type; - type = atomic_read(&page->_mapcount); - BUG_ON(type >= -1); + type = (unsigned long) page->lru.next; + BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE || + type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE); if (atomic_dec_return(&page->_count) == 1) { ClearPagePrivate(page); set_page_private(page, 0); - reset_page_mapcount(page); + INIT_LIST_HEAD(&page->lru); __free_pages_bootmem(page, 0); } diff -puN mm/page_alloc.c~thp-remove-pg_buddy mm/page_alloc.c --- a/mm/page_alloc.c~thp-remove-pg_buddy +++ a/mm/page_alloc.c @@ -449,8 +449,8 @@ __find_combined_index(unsigned long page * (c) a page and its buddy have the same order && * (d) a page and its buddy are in the same zone. * - * For recording whether a page is in the buddy system, we use PG_buddy. - * Setting, clearing, and testing PG_buddy is serialized by zone->lock. + * For recording whether a page is in the buddy system, we set ->_mapcount -2. + * Setting, clearing, and testing _mapcount -2 is serialized by zone->lock. * * For recording page's order, we use page_private(page). */ @@ -483,7 +483,7 @@ static inline int page_is_buddy(struct p * as necessary, plus some accounting needed to play nicely with other * parts of the VM system. * At each level, we keep a list of pages, which are heads of continuous - * free pages of length of (1 << order) and marked with PG_buddy. Page's + * free pages of length of (1 << order) and marked with _mapcount -2. Page's * order is recorded in page_private(page) field. * So when we are allocating or freeing one, we can derive the state of the * other. That is, if we allocate a small block, and both were @@ -5571,7 +5571,6 @@ static struct trace_print_flags pageflag {1UL << PG_swapcache, "swapcache" }, {1UL << PG_mappedtodisk, "mappedtodisk" }, {1UL << PG_reclaim, "reclaim" }, - {1UL << PG_buddy, "buddy" }, {1UL << PG_swapbacked, "swapbacked" }, {1UL << PG_unevictable, "unevictable" }, #ifdef CONFIG_MMU diff -puN mm/sparse.c~thp-remove-pg_buddy mm/sparse.c --- a/mm/sparse.c~thp-remove-pg_buddy +++ a/mm/sparse.c @@ -671,10 +671,10 @@ static void __kfree_section_memmap(struc static void free_map_bootmem(struct page *page, unsigned long nr_pages) { unsigned long maps_section_nr, removing_section_nr, i; - int magic; + unsigned long magic; for (i = 0; i < nr_pages; i++, page++) { - magic = atomic_read(&page->_mapcount); + magic = (unsigned long) page->lru.next; BUG_ON(magic == NODE_INFO); _ 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