From 57a196a58421a4b0c45949ae7309f21829aaa77f Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Sun, 18 Sep 2022 19:13:48 -0700 Subject: hugetlb: simplify hugetlb handling in follow_page_mask During discussions of this series [1], it was suggested that hugetlb handling code in follow_page_mask could be simplified. At the beginning of follow_page_mask, there currently is a call to follow_huge_addr which 'may' handle hugetlb pages. ia64 is the only architecture which provides a follow_huge_addr routine that does not return error. Instead, at each level of the page table a check is made for a hugetlb entry. If a hugetlb entry is found, a call to a routine associated with that entry is made. Currently, there are two checks for hugetlb entries at each page table level. The first check is of the form: if (p?d_huge()) page = follow_huge_p?d(); the second check is of the form: if (is_hugepd()) page = follow_huge_pd(). We can replace these checks, as well as the special handling routines such as follow_huge_p?d() and follow_huge_pd() with a single routine to handle hugetlb vmas. A new routine hugetlb_follow_page_mask is called for hugetlb vmas at the beginning of follow_page_mask. hugetlb_follow_page_mask will use the existing routine huge_pte_offset to walk page tables looking for hugetlb entries. huge_pte_offset can be overwritten by architectures, and already handles special cases such as hugepd entries. [1] https://lore.kernel.org/linux-mm/cover.1661240170.git.baolin.wang@linux.alibaba.com/ [mike.kravetz@oracle.com: remove vma (pmd sharing) per Peter] Link: https://lkml.kernel.org/r/20221028181108.119432-1-mike.kravetz@oracle.com [mike.kravetz@oracle.com: remove left over hugetlb_vma_unlock_read()] Link: https://lkml.kernel.org/r/20221030225825.40872-1-mike.kravetz@oracle.com Link: https://lkml.kernel.org/r/20220919021348.22151-1-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Suggested-by: David Hildenbrand Reviewed-by: David Hildenbrand Reviewed-by: Baolin Wang Tested-by: Baolin Wang Cc: Aneesh Kumar K.V Cc: Christophe Leroy Cc: Michael Ellerman Cc: Muchun Song Cc: Naoya Horiguchi Signed-off-by: Andrew Morton --- mm/hugetlb.c | 172 +++++++++++++++++++---------------------------------------- 1 file changed, 56 insertions(+), 116 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 546df97c31e4..0af18c1e4b31 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -6209,6 +6209,62 @@ static inline bool __follow_hugetlb_must_fault(unsigned int flags, pte_t *pte, return false; } +struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma, + unsigned long address, unsigned int flags) +{ + struct hstate *h = hstate_vma(vma); + struct mm_struct *mm = vma->vm_mm; + unsigned long haddr = address & huge_page_mask(h); + struct page *page = NULL; + spinlock_t *ptl; + pte_t *pte, entry; + + /* + * FOLL_PIN is not supported for follow_page(). Ordinary GUP goes via + * follow_hugetlb_page(). + */ + if (WARN_ON_ONCE(flags & FOLL_PIN)) + return NULL; + +retry: + pte = huge_pte_offset(mm, haddr, huge_page_size(h)); + if (!pte) + return NULL; + + ptl = huge_pte_lock(h, mm, pte); + entry = huge_ptep_get(pte); + if (pte_present(entry)) { + page = pte_page(entry) + + ((address & ~huge_page_mask(h)) >> PAGE_SHIFT); + /* + * Note that page may be a sub-page, and with vmemmap + * optimizations the page struct may be read only. + * try_grab_page() will increase the ref count on the + * head page, so this will be OK. + * + * try_grab_page() should always succeed here, because we hold + * the ptl lock and have verified pte_present(). + */ + if (WARN_ON_ONCE(!try_grab_page(page, flags))) { + page = NULL; + goto out; + } + } else { + if (is_hugetlb_entry_migration(entry)) { + spin_unlock(ptl); + __migration_entry_wait_huge(pte, ptl); + goto retry; + } + /* + * hwpoisoned entry is treated as no_page_table in + * follow_page_mask(). + */ + } +out: + spin_unlock(ptl); + return page; +} + long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page **pages, struct vm_area_struct **vmas, unsigned long *position, unsigned long *nr_pages, @@ -7201,122 +7257,6 @@ __weak unsigned long hugetlb_mask_last_page(struct hstate *h) * These functions are overwritable if your architecture needs its own * behavior. */ -struct page * __weak -follow_huge_addr(struct mm_struct *mm, unsigned long address, - int write) -{ - return ERR_PTR(-EINVAL); -} - -struct page * __weak -follow_huge_pd(struct vm_area_struct *vma, - unsigned long address, hugepd_t hpd, int flags, int pdshift) -{ - WARN(1, "hugepd follow called with no support for hugepage directory format\n"); - return NULL; -} - -struct page * __weak -follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address, int flags) -{ - struct hstate *h = hstate_vma(vma); - struct mm_struct *mm = vma->vm_mm; - struct page *page = NULL; - spinlock_t *ptl; - pte_t *ptep, pte; - - /* - * FOLL_PIN is not supported for follow_page(). Ordinary GUP goes via - * follow_hugetlb_page(). - */ - if (WARN_ON_ONCE(flags & FOLL_PIN)) - return NULL; - -retry: - ptep = huge_pte_offset(mm, address, huge_page_size(h)); - if (!ptep) - return NULL; - - ptl = huge_pte_lock(h, mm, ptep); - pte = huge_ptep_get(ptep); - if (pte_present(pte)) { - page = pte_page(pte) + - ((address & ~huge_page_mask(h)) >> PAGE_SHIFT); - /* - * try_grab_page() should always succeed here, because: a) we - * hold the pmd (ptl) lock, and b) we've just checked that the - * huge pmd (head) page is present in the page tables. The ptl - * prevents the head page and tail pages from being rearranged - * in any way. So this page must be available at this point, - * unless the page refcount overflowed: - */ - if (WARN_ON_ONCE(!try_grab_page(page, flags))) { - page = NULL; - goto out; - } - } else { - if (is_hugetlb_entry_migration(pte)) { - spin_unlock(ptl); - __migration_entry_wait_huge(ptep, ptl); - goto retry; - } - /* - * hwpoisoned entry is treated as no_page_table in - * follow_page_mask(). - */ - } -out: - spin_unlock(ptl); - return page; -} - -struct page * __weak -follow_huge_pud(struct mm_struct *mm, unsigned long address, - pud_t *pud, int flags) -{ - struct page *page = NULL; - spinlock_t *ptl; - pte_t pte; - - if (WARN_ON_ONCE(flags & FOLL_PIN)) - return NULL; - -retry: - ptl = huge_pte_lock(hstate_sizelog(PUD_SHIFT), mm, (pte_t *)pud); - if (!pud_huge(*pud)) - goto out; - pte = huge_ptep_get((pte_t *)pud); - if (pte_present(pte)) { - page = pud_page(*pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT); - if (WARN_ON_ONCE(!try_grab_page(page, flags))) { - page = NULL; - goto out; - } - } else { - if (is_hugetlb_entry_migration(pte)) { - spin_unlock(ptl); - __migration_entry_wait(mm, (pte_t *)pud, ptl); - goto retry; - } - /* - * hwpoisoned entry is treated as no_page_table in - * follow_page_mask(). - */ - } -out: - spin_unlock(ptl); - return page; -} - -struct page * __weak -follow_huge_pgd(struct mm_struct *mm, unsigned long address, pgd_t *pgd, int flags) -{ - if (flags & (FOLL_GET | FOLL_PIN)) - return NULL; - - return pte_page(*(pte_t *)pgd) + ((address & ~PGDIR_MASK) >> PAGE_SHIFT); -} - int isolate_hugetlb(struct page *page, struct list_head *list) { int ret = 0; -- cgit v1.2.3 From 4781593d5dbae50500d1c7975be03b590ae2b92a Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 20 Oct 2022 15:38:32 -0400 Subject: mm/hugetlb: unify clearing of RestoreReserve for private pages A trivial cleanup to move clearing of RestoreReserve into adding anon rmap of private hugetlb mappings. It matches with the shared mappings where we only clear the bit when adding into page cache, rather than spreading it around the code paths. Link: https://lkml.kernel.org/r/20221020193832.776173-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Mike Kravetz Cc: Muchun Song Signed-off-by: Andrew Morton --- mm/hugetlb.c | 14 ++++---------- mm/rmap.c | 2 +- 2 files changed, 5 insertions(+), 11 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 0af18c1e4b31..d11e92117d4a 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4775,7 +4775,6 @@ hugetlb_install_page(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr hugepage_add_new_anon_rmap(new_page, vma, addr); set_huge_pte_at(vma->vm_mm, addr, ptep, make_huge_pte(vma, new_page, 1)); hugetlb_count_add(pages_per_huge_page(hstate_vma(vma)), vma->vm_mm); - ClearHPageRestoreReserve(new_page); SetHPageMigratable(new_page); } @@ -5438,8 +5437,6 @@ retry_avoidcopy: spin_lock(ptl); ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) { - ClearHPageRestoreReserve(new_page); - /* Break COW or unshare */ huge_ptep_clear_flush(vma, haddr, ptep); mmu_notifier_invalidate_range(mm, range.start, range.end); @@ -5734,10 +5731,9 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, if (!pte_same(huge_ptep_get(ptep), old_pte)) goto backout; - if (anon_rmap) { - ClearHPageRestoreReserve(page); + if (anon_rmap) hugepage_add_new_anon_rmap(page, vma, haddr); - } else + else page_dup_file_rmap(page, true); new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_SHARED))); @@ -6120,12 +6116,10 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, if (!huge_pte_none_mostly(huge_ptep_get(dst_pte))) goto out_release_unlock; - if (page_in_pagecache) { + if (page_in_pagecache) page_dup_file_rmap(page, true); - } else { - ClearHPageRestoreReserve(page); + else hugepage_add_new_anon_rmap(page, dst_vma, dst_addr); - } /* * For either: (1) CONTINUE on a non-shared VMA, or (2) UFFDIO_COPY diff --git a/mm/rmap.c b/mm/rmap.c index 9bba65b30e4d..3b2d18bbdc44 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -2571,7 +2571,7 @@ void hugepage_add_new_anon_rmap(struct page *page, BUG_ON(address < vma->vm_start || address >= vma->vm_end); atomic_set(compound_mapcount_ptr(page), 0); atomic_set(compound_pincount_ptr(page), 0); - + ClearHPageRestoreReserve(page); __page_set_anon_rmap(page, vma, address, 1); } #endif /* CONFIG_HUGETLB_PAGE */ -- cgit v1.2.3 From b12fdbf15f92b6cf5fecdd8a1855afe8809e5c58 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 24 Oct 2022 15:33:36 -0400 Subject: Revert "mm/uffd: fix warning without PTE_MARKER_UFFD_WP compiled in" With " mm/uffd: Fix vma check on userfault for wp" to fix the registration, we'll be safe to remove the macro hacks now. Link: https://lkml.kernel.org/r/20221024193336.1233616-3-peterx@redhat.com Signed-off-by: Peter Xu Signed-off-by: Andrew Morton --- mm/hugetlb.c | 4 ---- mm/memory.c | 2 -- mm/mprotect.c | 2 -- 3 files changed, 8 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index d11e92117d4a..fc8908d715d6 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5114,7 +5114,6 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct * unmapped and its refcount is dropped, so just clear pte here. */ if (unlikely(!pte_present(pte))) { -#ifdef CONFIG_PTE_MARKER_UFFD_WP /* * If the pte was wr-protected by uffd-wp in any of the * swap forms, meanwhile the caller does not want to @@ -5126,7 +5125,6 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP)); else -#endif huge_pte_clear(mm, address, ptep, sz); spin_unlock(ptl); continue; @@ -5155,13 +5153,11 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct tlb_remove_huge_tlb_entry(h, tlb, ptep, address); if (huge_pte_dirty(pte)) set_page_dirty(page); -#ifdef CONFIG_PTE_MARKER_UFFD_WP /* Leave a uffd-wp pte marker if needed */ if (huge_pte_uffd_wp(pte) && !(zap_flags & ZAP_FLAG_DROP_MARKER)) set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP)); -#endif hugetlb_count_sub(pages_per_huge_page(h), mm); page_remove_rmap(page, vma, true); diff --git a/mm/memory.c b/mm/memory.c index f88c351aecd4..81cc75e71888 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1393,12 +1393,10 @@ zap_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, struct zap_details *details, pte_t pteval) { -#ifdef CONFIG_PTE_MARKER_UFFD_WP if (zap_drop_file_uffd_wp(details)) return; pte_install_uffd_wp_if_needed(vma, addr, pte, pteval); -#endif } static unsigned long zap_pte_range(struct mmu_gather *tlb, diff --git a/mm/mprotect.c b/mm/mprotect.c index 99762403cc8f..8d770855b591 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -267,7 +267,6 @@ static unsigned long change_pte_range(struct mmu_gather *tlb, } else { /* It must be an none page, or what else?.. */ WARN_ON_ONCE(!pte_none(oldpte)); -#ifdef CONFIG_PTE_MARKER_UFFD_WP if (unlikely(uffd_wp && !vma_is_anonymous(vma))) { /* * For file-backed mem, we need to be able to @@ -279,7 +278,6 @@ static unsigned long change_pte_range(struct mmu_gather *tlb, make_pte_marker(PTE_MARKER_UFFD_WP)); pages++; } -#endif } } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); -- cgit v1.2.3 From e591ef7d96d6ea249916f351dc26a636e565c635 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Mon, 24 Oct 2022 15:20:09 +0900 Subject: mm,hwpoison,hugetlb,memory_hotplug: hotremove memory section with hwpoisoned hugepage Patch series "mm, hwpoison: improve handling workload related to hugetlb and memory_hotplug", v7. This patchset tries to solve the issue among memory_hotplug, hugetlb and hwpoison. In this patchset, memory hotplug handles hwpoison pages like below: - hwpoison pages should not prevent memory hotremove, - memory block with hwpoison pages should not be onlined. This patch (of 4): HWPoisoned page is not supposed to be accessed once marked, but currently such accesses can happen during memory hotremove because do_migrate_range() can be called before dissolve_free_huge_pages() is called. Clear HPageMigratable for hwpoisoned hugepages to prevent them from being migrated. This should be done in hugetlb_lock to avoid race against isolate_hugetlb(). get_hwpoison_huge_page() needs to have a flag to show it's called from unpoison to take refcount of hwpoisoned hugepages, so add it. [naoya.horiguchi@linux.dev: remove TestClearHPageMigratable and reduce to test and clear separately] Link: https://lkml.kernel.org/r/20221025053559.GA2104800@ik1-406-35019.vs.sakura.ne.jp Link: https://lkml.kernel.org/r/20221024062012.1520887-1-naoya.horiguchi@linux.dev Link: https://lkml.kernel.org/r/20221024062012.1520887-2-naoya.horiguchi@linux.dev Signed-off-by: Naoya Horiguchi Reported-by: Miaohe Lin Reviewed-by: Oscar Salvador Reviewed-by: Miaohe Lin Cc: David Hildenbrand Cc: Jane Chu Cc: Mike Kravetz Cc: Muchun Song Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 10 ++++++---- include/linux/mm.h | 6 ++++-- mm/hugetlb.c | 9 +++++---- mm/memory-failure.c | 21 +++++++++++++++++---- 4 files changed, 32 insertions(+), 14 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 20a0d5a08395..65ea34022aa2 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -183,8 +183,9 @@ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); int isolate_hugetlb(struct page *page, struct list_head *list); -int get_hwpoison_huge_page(struct page *page, bool *hugetlb); -int get_huge_page_for_hwpoison(unsigned long pfn, int flags); +int get_hwpoison_huge_page(struct page *page, bool *hugetlb, bool unpoison); +int get_huge_page_for_hwpoison(unsigned long pfn, int flags, + bool *migratable_cleared); void putback_active_hugepage(struct page *page); void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason); void free_huge_page(struct page *page); @@ -391,12 +392,13 @@ static inline int isolate_hugetlb(struct page *page, struct list_head *list) return -EBUSY; } -static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb) +static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb, bool unpoison) { return 0; } -static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags) +static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags, + bool *migratable_cleared) { return 0; } diff --git a/include/linux/mm.h b/include/linux/mm.h index f6d2d2d9e284..e2ac6fff03a8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3277,9 +3277,11 @@ extern void shake_page(struct page *p); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); #ifdef CONFIG_MEMORY_FAILURE -extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags); +extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, + bool *migratable_cleared); #else -static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags) +static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, + bool *migratable_cleared) { return 0; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index fc8908d715d6..fdb36afea2b2 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -7265,7 +7265,7 @@ unlock: return ret; } -int get_hwpoison_huge_page(struct page *page, bool *hugetlb) +int get_hwpoison_huge_page(struct page *page, bool *hugetlb, bool unpoison) { int ret = 0; @@ -7275,7 +7275,7 @@ int get_hwpoison_huge_page(struct page *page, bool *hugetlb) *hugetlb = true; if (HPageFreed(page)) ret = 0; - else if (HPageMigratable(page)) + else if (HPageMigratable(page) || unpoison) ret = get_page_unless_zero(page); else ret = -EBUSY; @@ -7284,12 +7284,13 @@ int get_hwpoison_huge_page(struct page *page, bool *hugetlb) return ret; } -int get_huge_page_for_hwpoison(unsigned long pfn, int flags) +int get_huge_page_for_hwpoison(unsigned long pfn, int flags, + bool *migratable_cleared) { int ret; spin_lock_irq(&hugetlb_lock); - ret = __get_huge_page_for_hwpoison(pfn, flags); + ret = __get_huge_page_for_hwpoison(pfn, flags, migratable_cleared); spin_unlock_irq(&hugetlb_lock); return ret; } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 13594556146c..4fff0b36c61d 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1244,7 +1244,7 @@ static int __get_hwpoison_page(struct page *page, unsigned long flags) int ret = 0; bool hugetlb = false; - ret = get_hwpoison_huge_page(head, &hugetlb); + ret = get_hwpoison_huge_page(head, &hugetlb, false); if (hugetlb) return ret; @@ -1334,7 +1334,7 @@ static int __get_unpoison_page(struct page *page) int ret = 0; bool hugetlb = false; - ret = get_hwpoison_huge_page(head, &hugetlb); + ret = get_hwpoison_huge_page(head, &hugetlb, true); if (hugetlb) return ret; @@ -1785,7 +1785,8 @@ void hugetlb_clear_page_hwpoison(struct page *hpage) * -EBUSY - the hugepage is busy (try to retry) * -EHWPOISON - the hugepage is already hwpoisoned */ -int __get_huge_page_for_hwpoison(unsigned long pfn, int flags) +int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, + bool *migratable_cleared) { struct page *page = pfn_to_page(pfn); struct page *head = compound_head(page); @@ -1815,6 +1816,15 @@ int __get_huge_page_for_hwpoison(unsigned long pfn, int flags) goto out; } + /* + * Clearing HPageMigratable for hwpoisoned hugepages to prevent them + * from being migrated by memory hotremove. + */ + if (count_increased && HPageMigratable(head)) { + ClearHPageMigratable(head); + *migratable_cleared = true; + } + return ret; out: if (count_increased) @@ -1834,10 +1844,11 @@ static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb struct page *p = pfn_to_page(pfn); struct page *head; unsigned long page_flags; + bool migratable_cleared = false; *hugetlb = 1; retry: - res = get_huge_page_for_hwpoison(pfn, flags); + res = get_huge_page_for_hwpoison(pfn, flags, &migratable_cleared); if (res == 2) { /* fallback to normal page handling */ *hugetlb = 0; return 0; @@ -1861,6 +1872,8 @@ retry: if (hwpoison_filter(p)) { hugetlb_clear_page_hwpoison(head); + if (migratable_cleared) + SetHPageMigratable(head); unlock_page(head); if (res == 1) put_page(head); -- cgit v1.2.3 From f074732d599e19a2a5b12e54743ad5eaccbe6550 Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Tue, 1 Nov 2022 15:30:52 -0700 Subject: mm/hugetlb_cgroup: convert hugetlb_cgroup_from_page() to folios Introduce folios in __remove_hugetlb_page() by converting hugetlb_cgroup_from_page() to use folios. Also gets rid of unsed hugetlb_cgroup_from_page_resv() function. Link: https://lkml.kernel.org/r/20221101223059.460937-3-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Reviewed-by: Muchun Song Cc: Aneesh Kumar K.V Cc: Bui Quang Minh Cc: Matthew Wilcox (Oracle) Cc: Miaohe Lin Cc: Mike Kravetz Cc: Mina Almasry Signed-off-by: Andrew Morton --- include/linux/hugetlb_cgroup.h | 39 ++++++++++++++++++++------------------- mm/hugetlb.c | 5 +++-- mm/hugetlb_cgroup.c | 13 ++++++++----- 3 files changed, 31 insertions(+), 26 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index 7576e9ed8afe..feb2edafc8b6 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -67,27 +67,34 @@ struct hugetlb_cgroup { }; static inline struct hugetlb_cgroup * -__hugetlb_cgroup_from_page(struct page *page, bool rsvd) +__hugetlb_cgroup_from_folio(struct folio *folio, bool rsvd) { - VM_BUG_ON_PAGE(!PageHuge(page), page); + struct page *tail; - if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER) + VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio); + if (folio_order(folio) < HUGETLB_CGROUP_MIN_ORDER) return NULL; - if (rsvd) - return (void *)page_private(page + SUBPAGE_INDEX_CGROUP_RSVD); - else - return (void *)page_private(page + SUBPAGE_INDEX_CGROUP); + + if (rsvd) { + tail = folio_page(folio, SUBPAGE_INDEX_CGROUP_RSVD); + return (void *)page_private(tail); + } + + else { + tail = folio_page(folio, SUBPAGE_INDEX_CGROUP); + return (void *)page_private(tail); + } } -static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page) +static inline struct hugetlb_cgroup *hugetlb_cgroup_from_folio(struct folio *folio) { - return __hugetlb_cgroup_from_page(page, false); + return __hugetlb_cgroup_from_folio(folio, false); } static inline struct hugetlb_cgroup * -hugetlb_cgroup_from_page_rsvd(struct page *page) +hugetlb_cgroup_from_folio_rsvd(struct folio *folio) { - return __hugetlb_cgroup_from_page(page, true); + return __hugetlb_cgroup_from_folio(folio, true); } static inline void __set_hugetlb_cgroup(struct folio *folio, @@ -181,19 +188,13 @@ static inline void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, { } -static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page) -{ - return NULL; -} - -static inline struct hugetlb_cgroup * -hugetlb_cgroup_from_page_resv(struct page *page) +static inline struct hugetlb_cgroup *hugetlb_cgroup_from_folio(struct folio *folio) { return NULL; } static inline struct hugetlb_cgroup * -hugetlb_cgroup_from_page_rsvd(struct page *page) +hugetlb_cgroup_from_folio_rsvd(struct folio *folio) { return NULL; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index be09678d0582..f86a61a73112 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1446,9 +1446,10 @@ static void __remove_hugetlb_page(struct hstate *h, struct page *page, bool demote) { int nid = page_to_nid(page); + struct folio *folio = page_folio(page); - VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page), page); - VM_BUG_ON_PAGE(hugetlb_cgroup_from_page_rsvd(page), page); + VM_BUG_ON_FOLIO(hugetlb_cgroup_from_folio(folio), folio); + VM_BUG_ON_FOLIO(hugetlb_cgroup_from_folio_rsvd(folio), folio); lockdep_assert_held(&hugetlb_lock); if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index b2316bcbf634..8b95c1560f9c 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -191,8 +191,9 @@ static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg, struct page_counter *counter; struct hugetlb_cgroup *page_hcg; struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(h_cg); + struct folio *folio = page_folio(page); - page_hcg = hugetlb_cgroup_from_page(page); + page_hcg = hugetlb_cgroup_from_folio(folio); /* * We can have pages in active list without any cgroup * ie, hugepage with less than 3 pages. We can safely @@ -349,14 +350,15 @@ static void __hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, struct page *page, bool rsvd) { struct hugetlb_cgroup *h_cg; + struct folio *folio = page_folio(page); if (hugetlb_cgroup_disabled()) return; lockdep_assert_held(&hugetlb_lock); - h_cg = __hugetlb_cgroup_from_page(page, rsvd); + h_cg = __hugetlb_cgroup_from_folio(folio, rsvd); if (unlikely(!h_cg)) return; - __set_hugetlb_cgroup(page_folio(page), NULL, rsvd); + __set_hugetlb_cgroup(folio, NULL, rsvd); page_counter_uncharge(__hugetlb_cgroup_counter_from_cgroup(h_cg, idx, rsvd), @@ -888,13 +890,14 @@ void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage) struct hugetlb_cgroup *h_cg; struct hugetlb_cgroup *h_cg_rsvd; struct hstate *h = page_hstate(oldhpage); + struct folio *old_folio = page_folio(oldhpage); if (hugetlb_cgroup_disabled()) return; spin_lock_irq(&hugetlb_lock); - h_cg = hugetlb_cgroup_from_page(oldhpage); - h_cg_rsvd = hugetlb_cgroup_from_page_rsvd(oldhpage); + h_cg = hugetlb_cgroup_from_folio(old_folio); + h_cg_rsvd = hugetlb_cgroup_from_folio_rsvd(old_folio); set_hugetlb_cgroup(oldhpage, NULL); set_hugetlb_cgroup_rsvd(oldhpage, NULL); -- cgit v1.2.3 From de656ed376c4cb47c5713fba52f8bbfbea44f387 Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Tue, 1 Nov 2022 15:30:53 -0700 Subject: mm/hugetlb_cgroup: convert set_hugetlb_cgroup*() to folios Allows __prep_new_huge_page() to operate on a folio by converting set_hugetlb_cgroup*() to take in a folio. Link: https://lkml.kernel.org/r/20221101223059.460937-4-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Cc: Aneesh Kumar K.V Cc: Bui Quang Minh Cc: Matthew Wilcox (Oracle) Cc: Miaohe Lin Cc: Mina Almasry Cc: Muchun Song Signed-off-by: Andrew Morton --- include/linux/hugetlb_cgroup.h | 12 ++++++------ mm/hugetlb.c | 33 +++++++++++++++++++-------------- mm/hugetlb_cgroup.c | 11 ++++++----- 3 files changed, 31 insertions(+), 25 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index feb2edafc8b6..a7e3540f7f38 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -112,16 +112,16 @@ static inline void __set_hugetlb_cgroup(struct folio *folio, (unsigned long)h_cg); } -static inline void set_hugetlb_cgroup(struct page *page, +static inline void set_hugetlb_cgroup(struct folio *folio, struct hugetlb_cgroup *h_cg) { - __set_hugetlb_cgroup(page_folio(page), h_cg, false); + __set_hugetlb_cgroup(folio, h_cg, false); } -static inline void set_hugetlb_cgroup_rsvd(struct page *page, +static inline void set_hugetlb_cgroup_rsvd(struct folio *folio, struct hugetlb_cgroup *h_cg) { - __set_hugetlb_cgroup(page_folio(page), h_cg, true); + __set_hugetlb_cgroup(folio, h_cg, true); } static inline bool hugetlb_cgroup_disabled(void) @@ -199,12 +199,12 @@ hugetlb_cgroup_from_folio_rsvd(struct folio *folio) return NULL; } -static inline void set_hugetlb_cgroup(struct page *page, +static inline void set_hugetlb_cgroup(struct folio *folio, struct hugetlb_cgroup *h_cg) { } -static inline void set_hugetlb_cgroup_rsvd(struct page *page, +static inline void set_hugetlb_cgroup_rsvd(struct folio *folio, struct hugetlb_cgroup *h_cg) { } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f86a61a73112..01ea43b22724 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1774,19 +1774,21 @@ static void __prep_account_new_huge_page(struct hstate *h, int nid) h->nr_huge_pages_node[nid]++; } -static void __prep_new_huge_page(struct hstate *h, struct page *page) +static void __prep_new_hugetlb_folio(struct hstate *h, struct folio *folio) { - hugetlb_vmemmap_optimize(h, page); - INIT_LIST_HEAD(&page->lru); - set_compound_page_dtor(page, HUGETLB_PAGE_DTOR); - hugetlb_set_page_subpool(page, NULL); - set_hugetlb_cgroup(page, NULL); - set_hugetlb_cgroup_rsvd(page, NULL); + hugetlb_vmemmap_optimize(h, &folio->page); + INIT_LIST_HEAD(&folio->lru); + folio->_folio_dtor = HUGETLB_PAGE_DTOR; + hugetlb_set_folio_subpool(folio, NULL); + set_hugetlb_cgroup(folio, NULL); + set_hugetlb_cgroup_rsvd(folio, NULL); } static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) { - __prep_new_huge_page(h, page); + struct folio *folio = page_folio(page); + + __prep_new_hugetlb_folio(h, folio); spin_lock_irq(&hugetlb_lock); __prep_account_new_huge_page(h, nid); spin_unlock_irq(&hugetlb_lock); @@ -2748,8 +2750,10 @@ static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page, struct list_head *list) { gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; - int nid = page_to_nid(old_page); + struct folio *old_folio = page_folio(old_page); + int nid = folio_nid(old_folio); struct page *new_page; + struct folio *new_folio; int ret = 0; /* @@ -2762,16 +2766,17 @@ static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page, new_page = alloc_buddy_huge_page(h, gfp_mask, nid, NULL, NULL); if (!new_page) return -ENOMEM; - __prep_new_huge_page(h, new_page); + new_folio = page_folio(new_page); + __prep_new_hugetlb_folio(h, new_folio); retry: spin_lock_irq(&hugetlb_lock); - if (!PageHuge(old_page)) { + if (!folio_test_hugetlb(old_folio)) { /* * Freed from under us. Drop new_page too. */ goto free_new; - } else if (page_count(old_page)) { + } else if (folio_ref_count(old_folio)) { /* * Someone has grabbed the page, try to isolate it here. * Fail with -EBUSY if not possible. @@ -2780,7 +2785,7 @@ retry: ret = isolate_hugetlb(old_page, list); spin_lock_irq(&hugetlb_lock); goto free_new; - } else if (!HPageFreed(old_page)) { + } else if (!folio_test_hugetlb_freed(old_folio)) { /* * Page's refcount is 0 but it has not been enqueued in the * freelist yet. Race window is small, so we can succeed here if @@ -2818,7 +2823,7 @@ retry: free_new: spin_unlock_irq(&hugetlb_lock); /* Page has a zero ref count, but needs a ref to be freed */ - set_page_refcounted(new_page); + folio_ref_unfreeze(new_folio, 1); update_and_free_page(h, new_page, false); return ret; diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 8b95c1560f9c..87a1125aa42d 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -212,7 +212,7 @@ static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg, /* Take the pages off the local counter */ page_counter_cancel(counter, nr_pages); - set_hugetlb_cgroup(page, parent); + set_hugetlb_cgroup(folio, parent); out: return; } @@ -891,6 +891,7 @@ void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage) struct hugetlb_cgroup *h_cg_rsvd; struct hstate *h = page_hstate(oldhpage); struct folio *old_folio = page_folio(oldhpage); + struct folio *new_folio = page_folio(newhpage); if (hugetlb_cgroup_disabled()) return; @@ -898,12 +899,12 @@ void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage) spin_lock_irq(&hugetlb_lock); h_cg = hugetlb_cgroup_from_folio(old_folio); h_cg_rsvd = hugetlb_cgroup_from_folio_rsvd(old_folio); - set_hugetlb_cgroup(oldhpage, NULL); - set_hugetlb_cgroup_rsvd(oldhpage, NULL); + set_hugetlb_cgroup(old_folio, NULL); + set_hugetlb_cgroup_rsvd(old_folio, NULL); /* move the h_cg details to new cgroup */ - set_hugetlb_cgroup(newhpage, h_cg); - set_hugetlb_cgroup_rsvd(newhpage, h_cg_rsvd); + set_hugetlb_cgroup(new_folio, h_cg); + set_hugetlb_cgroup_rsvd(new_folio, h_cg_rsvd); list_move(&newhpage->lru, &h->hugepage_activelist); spin_unlock_irq(&hugetlb_lock); return; -- cgit v1.2.3 From 29f394304f624b06fafb3cc9c3da8779f71f4bee Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Tue, 1 Nov 2022 15:30:54 -0700 Subject: mm/hugetlb_cgroup: convert hugetlb_cgroup_migrate to folios Cleans up intermediate page to folio conversion code in hugetlb_cgroup_migrate() by changing its arguments from pages to folios. Link: https://lkml.kernel.org/r/20221101223059.460937-5-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Reviewed-by: Muchun Song Cc: Aneesh Kumar K.V Cc: Bui Quang Minh Cc: Matthew Wilcox (Oracle) Cc: Miaohe Lin Cc: Mina Almasry Signed-off-by: Andrew Morton --- include/linux/hugetlb_cgroup.h | 8 ++++---- mm/hugetlb.c | 2 +- mm/hugetlb_cgroup.c | 8 +++----- 3 files changed, 8 insertions(+), 10 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index a7e3540f7f38..789b6fef176d 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -177,8 +177,8 @@ extern void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, bool region_del); extern void hugetlb_cgroup_file_init(void) __init; -extern void hugetlb_cgroup_migrate(struct page *oldhpage, - struct page *newhpage); +extern void hugetlb_cgroup_migrate(struct folio *old_folio, + struct folio *new_folio); #else static inline void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, @@ -286,8 +286,8 @@ static inline void hugetlb_cgroup_file_init(void) { } -static inline void hugetlb_cgroup_migrate(struct page *oldhpage, - struct page *newhpage) +static inline void hugetlb_cgroup_migrate(struct folio *old_folio, + struct folio *new_folio) { } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 01ea43b22724..05a832886a09 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -7325,7 +7325,7 @@ void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason) { struct hstate *h = page_hstate(oldpage); - hugetlb_cgroup_migrate(oldpage, newpage); + hugetlb_cgroup_migrate(page_folio(oldpage), page_folio(newpage)); set_page_owner_migrate_reason(newpage, reason); /* diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 87a1125aa42d..b1b18337a56a 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -885,13 +885,11 @@ void __init hugetlb_cgroup_file_init(void) * hugetlb_lock will make sure a parallel cgroup rmdir won't happen * when we migrate hugepages */ -void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage) +void hugetlb_cgroup_migrate(struct folio *old_folio, struct folio *new_folio) { struct hugetlb_cgroup *h_cg; struct hugetlb_cgroup *h_cg_rsvd; - struct hstate *h = page_hstate(oldhpage); - struct folio *old_folio = page_folio(oldhpage); - struct folio *new_folio = page_folio(newhpage); + struct hstate *h = folio_hstate(old_folio); if (hugetlb_cgroup_disabled()) return; @@ -905,7 +903,7 @@ void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage) /* move the h_cg details to new cgroup */ set_hugetlb_cgroup(new_folio, h_cg); set_hugetlb_cgroup_rsvd(new_folio, h_cg_rsvd); - list_move(&newhpage->lru, &h->hugepage_activelist); + list_move(&new_folio->lru, &h->hugepage_activelist); spin_unlock_irq(&hugetlb_lock); return; } -- cgit v1.2.3 From d5e33bd8c16b6f5f47665d378f078bee72b85225 Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Tue, 1 Nov 2022 15:30:55 -0700 Subject: mm/hugetlb: convert isolate_or_dissolve_huge_page to folios Removes a call to compound_head() by using a folio when operating on the head page of a hugetlb compound page. Link: https://lkml.kernel.org/r/20221101223059.460937-6-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Reviewed-by: Muchun Song Cc: Aneesh Kumar K.V Cc: Bui Quang Minh Cc: Matthew Wilcox (Oracle) Cc: Miaohe Lin Cc: Mina Almasry Signed-off-by: Andrew Morton --- mm/hugetlb.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 05a832886a09..666a771c9a3d 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2832,7 +2832,7 @@ free_new: int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) { struct hstate *h; - struct page *head; + struct folio *folio = page_folio(page); int ret = -EBUSY; /* @@ -2841,9 +2841,8 @@ int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) * Return success when racing as if we dissolved the page ourselves. */ spin_lock_irq(&hugetlb_lock); - if (PageHuge(page)) { - head = compound_head(page); - h = page_hstate(head); + if (folio_test_hugetlb(folio)) { + h = folio_hstate(folio); } else { spin_unlock_irq(&hugetlb_lock); return 0; @@ -2858,10 +2857,10 @@ int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) if (hstate_is_gigantic(h)) return -ENOMEM; - if (page_count(head) && !isolate_hugetlb(head, list)) + if (folio_ref_count(folio) && !isolate_hugetlb(&folio->page, list)) ret = 0; - else if (!page_count(head)) - ret = alloc_and_dissolve_huge_page(h, head, list); + else if (!folio_ref_count(folio)) + ret = alloc_and_dissolve_huge_page(h, &folio->page, list); return ret; } -- cgit v1.2.3 From 0356c4b96f6890dd61af4c902f681764f4bdba09 Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Tue, 1 Nov 2022 15:30:56 -0700 Subject: mm/hugetlb: convert free_huge_page to folios Use folios inside free_huge_page(), this is in preparation for converting hugetlb_cgroup_uncharge_page() to take in a folio. Link: https://lkml.kernel.org/r/20221101223059.460937-7-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Reviewed-by: Muchun Song Cc: Aneesh Kumar K.V Cc: Bui Quang Minh Cc: Matthew Wilcox (Oracle) Cc: Miaohe Lin Cc: Mina Almasry Signed-off-by: Andrew Morton --- mm/hugetlb.c | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 666a771c9a3d..9841fb0fcaf9 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1704,21 +1704,22 @@ void free_huge_page(struct page *page) * Can't pass hstate in here because it is called from the * compound page destructor. */ - struct hstate *h = page_hstate(page); - int nid = page_to_nid(page); - struct hugepage_subpool *spool = hugetlb_page_subpool(page); + struct folio *folio = page_folio(page); + struct hstate *h = folio_hstate(folio); + int nid = folio_nid(folio); + struct hugepage_subpool *spool = hugetlb_folio_subpool(folio); bool restore_reserve; unsigned long flags; - VM_BUG_ON_PAGE(page_count(page), page); - VM_BUG_ON_PAGE(page_mapcount(page), page); + VM_BUG_ON_FOLIO(folio_ref_count(folio), folio); + VM_BUG_ON_FOLIO(folio_mapcount(folio), folio); - hugetlb_set_page_subpool(page, NULL); - if (PageAnon(page)) - __ClearPageAnonExclusive(page); - page->mapping = NULL; - restore_reserve = HPageRestoreReserve(page); - ClearHPageRestoreReserve(page); + hugetlb_set_folio_subpool(folio, NULL); + if (folio_test_anon(folio)) + __ClearPageAnonExclusive(&folio->page); + folio->mapping = NULL; + restore_reserve = folio_test_hugetlb_restore_reserve(folio); + folio_clear_hugetlb_restore_reserve(folio); /* * If HPageRestoreReserve was set on page, page allocation consumed a @@ -1740,7 +1741,7 @@ void free_huge_page(struct page *page) } spin_lock_irqsave(&hugetlb_lock, flags); - ClearHPageMigratable(page); + folio_clear_hugetlb_migratable(folio); hugetlb_cgroup_uncharge_page(hstate_index(h), pages_per_huge_page(h), page); hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h), @@ -1748,7 +1749,7 @@ void free_huge_page(struct page *page) if (restore_reserve) h->resv_huge_pages++; - if (HPageTemporary(page)) { + if (folio_test_hugetlb_temporary(folio)) { remove_hugetlb_page(h, page, false); spin_unlock_irqrestore(&hugetlb_lock, flags); update_and_free_page(h, page, true); -- cgit v1.2.3 From d4ab0316cc33aeedf6dcb1c2c25e097a25766132 Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Tue, 1 Nov 2022 15:30:57 -0700 Subject: mm/hugetlb_cgroup: convert hugetlb_cgroup_uncharge_page() to folios Continue to use a folio inside free_huge_page() by converting hugetlb_cgroup_uncharge_page*() to folios. Link: https://lkml.kernel.org/r/20221101223059.460937-8-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Reviewed-by: Muchun Song Cc: Aneesh Kumar K.V Cc: Bui Quang Minh Cc: Matthew Wilcox (Oracle) Cc: Miaohe Lin Cc: Mina Almasry Signed-off-by: Andrew Morton --- include/linux/hugetlb_cgroup.h | 16 ++++++++-------- mm/hugetlb.c | 15 +++++++++------ mm/hugetlb_cgroup.c | 21 ++++++++++----------- 3 files changed, 27 insertions(+), 25 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index 789b6fef176d..c70f92fe493e 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -158,10 +158,10 @@ extern void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, extern void hugetlb_cgroup_commit_charge_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, struct page *page); -extern void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, - struct page *page); -extern void hugetlb_cgroup_uncharge_page_rsvd(int idx, unsigned long nr_pages, - struct page *page); +extern void hugetlb_cgroup_uncharge_folio(int idx, unsigned long nr_pages, + struct folio *folio); +extern void hugetlb_cgroup_uncharge_folio_rsvd(int idx, unsigned long nr_pages, + struct folio *folio); extern void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg); @@ -254,14 +254,14 @@ hugetlb_cgroup_commit_charge_rsvd(int idx, unsigned long nr_pages, { } -static inline void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, - struct page *page) +static inline void hugetlb_cgroup_uncharge_folio(int idx, unsigned long nr_pages, + struct folio *folio) { } -static inline void hugetlb_cgroup_uncharge_page_rsvd(int idx, +static inline void hugetlb_cgroup_uncharge_folio_rsvd(int idx, unsigned long nr_pages, - struct page *page) + struct folio *folio) { } static inline void hugetlb_cgroup_uncharge_cgroup(int idx, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 9841fb0fcaf9..e1950fff6aa9 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1742,10 +1742,10 @@ void free_huge_page(struct page *page) spin_lock_irqsave(&hugetlb_lock, flags); folio_clear_hugetlb_migratable(folio); - hugetlb_cgroup_uncharge_page(hstate_index(h), - pages_per_huge_page(h), page); - hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h), - pages_per_huge_page(h), page); + hugetlb_cgroup_uncharge_folio(hstate_index(h), + pages_per_huge_page(h), folio); + hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), + pages_per_huge_page(h), folio); if (restore_reserve) h->resv_huge_pages++; @@ -2872,6 +2872,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); struct page *page; + struct folio *folio; long map_chg, map_commit; long gbl_chg; int ret, idx; @@ -2935,6 +2936,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, * a reservation exists for the allocation. */ page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, gbl_chg); + if (!page) { spin_unlock_irq(&hugetlb_lock); page = alloc_buddy_huge_page_with_mpol(h, vma, addr); @@ -2949,6 +2951,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, set_page_refcounted(page); /* Fall through */ } + folio = page_folio(page); hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, page); /* If allocation is not consuming a reservation, also store the * hugetlb_cgroup pointer on the page. @@ -2978,8 +2981,8 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, rsv_adjust = hugepage_subpool_put_pages(spool, 1); hugetlb_acct_memory(h, -rsv_adjust); if (deferred_reserve) - hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h), - pages_per_huge_page(h), page); + hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), + pages_per_huge_page(h), folio); } return page; diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index b1b18337a56a..4cd57f979245 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -346,11 +346,10 @@ void hugetlb_cgroup_commit_charge_rsvd(int idx, unsigned long nr_pages, /* * Should be called with hugetlb_lock held */ -static void __hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, - struct page *page, bool rsvd) +static void __hugetlb_cgroup_uncharge_folio(int idx, unsigned long nr_pages, + struct folio *folio, bool rsvd) { struct hugetlb_cgroup *h_cg; - struct folio *folio = page_folio(page); if (hugetlb_cgroup_disabled()) return; @@ -368,27 +367,27 @@ static void __hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, css_put(&h_cg->css); else { unsigned long usage = - h_cg->nodeinfo[page_to_nid(page)]->usage[idx]; + h_cg->nodeinfo[folio_nid(folio)]->usage[idx]; /* * This write is not atomic due to fetching usage and writing * to it, but that's fine because we call this with * hugetlb_lock held anyway. */ - WRITE_ONCE(h_cg->nodeinfo[page_to_nid(page)]->usage[idx], + WRITE_ONCE(h_cg->nodeinfo[folio_nid(folio)]->usage[idx], usage - nr_pages); } } -void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, - struct page *page) +void hugetlb_cgroup_uncharge_folio(int idx, unsigned long nr_pages, + struct folio *folio) { - __hugetlb_cgroup_uncharge_page(idx, nr_pages, page, false); + __hugetlb_cgroup_uncharge_folio(idx, nr_pages, folio, false); } -void hugetlb_cgroup_uncharge_page_rsvd(int idx, unsigned long nr_pages, - struct page *page) +void hugetlb_cgroup_uncharge_folio_rsvd(int idx, unsigned long nr_pages, + struct folio *folio) { - __hugetlb_cgroup_uncharge_page(idx, nr_pages, page, true); + __hugetlb_cgroup_uncharge_folio(idx, nr_pages, folio, true); } static void __hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, -- cgit v1.2.3 From 345c62d163496ae4b5c1ce530b1588067d8f5a8b Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Tue, 1 Nov 2022 15:30:59 -0700 Subject: mm/hugetlb: convert move_hugetlb_state() to folios Clean up unmap_and_move_huge_page() by converting move_hugetlb_state() to take in folios. [akpm@linux-foundation.org: fix CONFIG_HUGETLB_PAGE=n build] Link: https://lkml.kernel.org/r/20221101223059.460937-10-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Reviewed-by: Muchun Song Cc: Aneesh Kumar K.V Cc: Bui Quang Minh Cc: Matthew Wilcox (Oracle) Cc: Miaohe Lin Cc: Mina Almasry Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 11 ++++++++--- mm/hugetlb.c | 22 ++++++++++++---------- mm/migrate.c | 4 ++-- 3 files changed, 22 insertions(+), 15 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 65ea34022aa2..58a30938a9b1 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -187,7 +187,7 @@ int get_hwpoison_huge_page(struct page *page, bool *hugetlb, bool unpoison); int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); void putback_active_hugepage(struct page *page); -void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason); +void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason); void free_huge_page(struct page *page); void hugetlb_fix_reserve_counts(struct inode *inode); extern struct mutex *hugetlb_fault_mutex_table; @@ -407,8 +407,8 @@ static inline void putback_active_hugepage(struct page *page) { } -static inline void move_hugetlb_state(struct page *oldpage, - struct page *newpage, int reason) +static inline void move_hugetlb_state(struct folio *old_folio, + struct folio *new_folio, int reason) { } @@ -991,6 +991,11 @@ void hugetlb_unregister_node(struct node *node); #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; +static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio) +{ + return NULL; +} + static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage) { return NULL; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e1950fff6aa9..76ebefe02827 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -7324,15 +7324,15 @@ void putback_active_hugepage(struct page *page) put_page(page); } -void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason) +void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason) { - struct hstate *h = page_hstate(oldpage); + struct hstate *h = folio_hstate(old_folio); - hugetlb_cgroup_migrate(page_folio(oldpage), page_folio(newpage)); - set_page_owner_migrate_reason(newpage, reason); + hugetlb_cgroup_migrate(old_folio, new_folio); + set_page_owner_migrate_reason(&new_folio->page, reason); /* - * transfer temporary state of the new huge page. This is + * transfer temporary state of the new hugetlb folio. This is * reverse to other transitions because the newpage is going to * be final while the old one will be freed so it takes over * the temporary status. @@ -7341,12 +7341,14 @@ void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason) * here as well otherwise the global surplus count will not match * the per-node's. */ - if (HPageTemporary(newpage)) { - int old_nid = page_to_nid(oldpage); - int new_nid = page_to_nid(newpage); + if (folio_test_hugetlb_temporary(new_folio)) { + int old_nid = folio_nid(old_folio); + int new_nid = folio_nid(new_folio); + + + folio_set_hugetlb_temporary(old_folio); + folio_clear_hugetlb_temporary(new_folio); - SetHPageTemporary(oldpage); - ClearHPageTemporary(newpage); /* * There is no need to transfer the per-node surplus state diff --git a/mm/migrate.c b/mm/migrate.c index f8c85b42e2bc..4aea647a0180 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1298,7 +1298,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, * folio_mapping() set, hugetlbfs specific move page routine will not * be called and we could leak usage counts for subpools. */ - if (hugetlb_page_subpool(hpage) && !folio_mapping(src)) { + if (hugetlb_folio_subpool(src) && !folio_mapping(src)) { rc = -EBUSY; goto out_unlock; } @@ -1348,7 +1348,7 @@ put_anon: put_anon_vma(anon_vma); if (rc == MIGRATEPAGE_SUCCESS) { - move_hugetlb_state(hpage, new_hpage, reason); + move_hugetlb_state(src, dst, reason); put_new_page = NULL; } -- cgit v1.2.3 From cb67f4282bf9693658dbda934a441ddbbb1446df Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 2 Nov 2022 18:51:38 -0700 Subject: mm,thp,rmap: simplify compound page mapcount handling Compound page (folio) mapcount calculations have been different for anon and file (or shmem) THPs, and involved the obscure PageDoubleMap flag. And each huge mapping and unmapping of a file (or shmem) THP involved atomically incrementing and decrementing the mapcount of every subpage of that huge page, dirtying many struct page cachelines. Add subpages_mapcount field to the struct folio and first tail page, so that the total of subpage mapcounts is available in one place near the head: then page_mapcount() and total_mapcount() and page_mapped(), and their folio equivalents, are so quick that anon and file and hugetlb don't need to be optimized differently. Delete the unloved PageDoubleMap. page_add and page_remove rmap functions must now maintain the subpages_mapcount as well as the subpage _mapcount, when dealing with pte mappings of huge pages; and correct maintenance of NR_ANON_MAPPED and NR_FILE_MAPPED statistics still needs reading through the subpages, using nr_subpages_unmapped() - but only when first or last pmd mapping finds subpages_mapcount raised (double-map case, not the common case). But are those counts (used to decide when to split an anon THP, and in vmscan's pagecache_reclaimable heuristic) correctly maintained? Not quite: since page_remove_rmap() (and also split_huge_pmd()) is often called without page lock, there can be races when a subpage pte mapcount 0<->1 while compound pmd mapcount 0<->1 is scanning - races which the previous implementation had prevented. The statistics might become inaccurate, and even drift down until they underflow through 0. That is not good enough, but is better dealt with in a followup patch. Update a few comments on first and second tail page overlaid fields. hugepage_add_new_anon_rmap() has to "increment" compound_mapcount, but subpages_mapcount and compound_pincount are already correctly at 0, so delete its reinitialization of compound_pincount. A simple 100 X munmap(mmap(2GB, MAP_SHARED|MAP_POPULATE, tmpfs), 2GB) took 18 seconds on small pages, and used to take 1 second on huge pages, but now takes 119 milliseconds on huge pages. Mapping by pmds a second time used to take 860ms and now takes 92ms; mapping by pmds after mapping by ptes (when the scan is needed) used to take 870ms and now takes 495ms. But there might be some benchmarks which would show a slowdown, because tail struct pages now fall out of cache until final freeing checks them. Link: https://lkml.kernel.org/r/47ad693-717-79c8-e1ba-46c3a6602e48@google.com Signed-off-by: Hugh Dickins Acked-by: Kirill A. Shutemov Cc: David Hildenbrand Cc: James Houghton Cc: John Hubbard Cc: Matthew Wilcox (Oracle) Cc: Miaohe Lin Cc: Mike Kravetz Cc: Mina Almasry Cc: Muchun Song Cc: Naoya Horiguchi Cc: Peter Xu Cc: Sidhartha Kumar Cc: Vlastimil Babka Cc: Yang Shi Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- Documentation/mm/transhuge.rst | 18 ------ include/linux/mm.h | 85 +++++++++++++++++------- include/linux/mm_types.h | 21 +++++- include/linux/page-flags.h | 21 ------ include/linux/rmap.h | 2 + mm/debug.c | 5 +- mm/folio-compat.c | 6 -- mm/huge_memory.c | 36 +++-------- mm/hugetlb.c | 2 + mm/khugepaged.c | 11 +--- mm/page_alloc.c | 27 ++++---- mm/rmap.c | 142 +++++++++++++++++++++++------------------ mm/util.c | 79 ----------------------- 13 files changed, 194 insertions(+), 261 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/Documentation/mm/transhuge.rst b/Documentation/mm/transhuge.rst index 216db1d67d04..a560e0c01b16 100644 --- a/Documentation/mm/transhuge.rst +++ b/Documentation/mm/transhuge.rst @@ -125,24 +125,6 @@ pages: ->_mapcount of all sub-pages in order to have race-free detection of last unmap of subpages. -PageDoubleMap() indicates that the page is *possibly* mapped with PTEs. - -For anonymous pages, PageDoubleMap() also indicates ->_mapcount in all -subpages is offset up by one. This additional reference is required to -get race-free detection of unmap of subpages when we have them mapped with -both PMDs and PTEs. - -This optimization is required to lower the overhead of per-subpage mapcount -tracking. The alternative is to alter ->_mapcount in all subpages on each -map/unmap of the whole compound page. - -For anonymous pages, we set PG_double_map when a PMD of the page is split -for the first time, but still have a PMD mapping. The additional references -go away with the last compound_mapcount. - -File pages get PG_double_map set on the first map of the page with PTE and -goes away when the page gets evicted from the page cache. - split_huge_page internally has to distribute the refcounts in the head page to the tail pages before clearing all PG_head/tail bits from the page structures. It can be done easily for refcounts taken by page table diff --git a/include/linux/mm.h b/include/linux/mm.h index 3950ef45b9a9..a904c2d60f12 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -818,8 +818,8 @@ static inline int is_vmalloc_or_module_addr(const void *x) /* * How many times the entire folio is mapped as a single unit (eg by a * PMD or PUD entry). This is probably not what you want, except for - * debugging purposes; look at folio_mapcount() or page_mapcount() - * instead. + * debugging purposes - it does not include PTE-mapped sub-pages; look + * at folio_mapcount() or page_mapcount() or total_mapcount() instead. */ static inline int folio_entire_mapcount(struct folio *folio) { @@ -829,12 +829,20 @@ static inline int folio_entire_mapcount(struct folio *folio) /* * Mapcount of compound page as a whole, does not include mapped sub-pages. - * - * Must be called only for compound pages. + * Must be called only on head of compound page. */ -static inline int compound_mapcount(struct page *page) +static inline int head_compound_mapcount(struct page *head) { - return folio_entire_mapcount(page_folio(page)); + return atomic_read(compound_mapcount_ptr(head)) + 1; +} + +/* + * Sum of mapcounts of sub-pages, does not include compound mapcount. + * Must be called only on head of compound page. + */ +static inline int head_subpages_mapcount(struct page *head) +{ + return atomic_read(subpages_mapcount_ptr(head)); } /* @@ -847,11 +855,9 @@ static inline void page_mapcount_reset(struct page *page) atomic_set(&(page)->_mapcount, -1); } -int __page_mapcount(struct page *page); - /* * Mapcount of 0-order page; when compound sub-page, includes - * compound_mapcount(). + * compound_mapcount of compound_head of page. * * Result is undefined for pages which cannot be mapped into userspace. * For example SLAB or special types of pages. See function page_has_type(). @@ -859,25 +865,61 @@ int __page_mapcount(struct page *page); */ static inline int page_mapcount(struct page *page) { - if (unlikely(PageCompound(page))) - return __page_mapcount(page); - return atomic_read(&page->_mapcount) + 1; -} + int mapcount = atomic_read(&page->_mapcount) + 1; -int folio_mapcount(struct folio *folio); + if (likely(!PageCompound(page))) + return mapcount; + page = compound_head(page); + return head_compound_mapcount(page) + mapcount; +} -#ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int total_mapcount(struct page *page) { - return folio_mapcount(page_folio(page)); + if (likely(!PageCompound(page))) + return atomic_read(&page->_mapcount) + 1; + page = compound_head(page); + return head_compound_mapcount(page) + head_subpages_mapcount(page); } -#else -static inline int total_mapcount(struct page *page) +/* + * Return true if this page is mapped into pagetables. + * For compound page it returns true if any subpage of compound page is mapped, + * even if this particular subpage is not itself mapped by any PTE or PMD. + */ +static inline bool page_mapped(struct page *page) { - return page_mapcount(page); + return total_mapcount(page) > 0; +} + +/** + * folio_mapcount() - Calculate the number of mappings of this folio. + * @folio: The folio. + * + * A large folio tracks both how many times the entire folio is mapped, + * and how many times each individual page in the folio is mapped. + * This function calculates the total number of times the folio is + * mapped. + * + * Return: The number of times this folio is mapped. + */ +static inline int folio_mapcount(struct folio *folio) +{ + if (likely(!folio_test_large(folio))) + return atomic_read(&folio->_mapcount) + 1; + return atomic_read(folio_mapcount_ptr(folio)) + 1 + + atomic_read(folio_subpages_mapcount_ptr(folio)); +} + +/** + * folio_mapped - Is this folio mapped into userspace? + * @folio: The folio. + * + * Return: True if any page in this folio is referenced by user page tables. + */ +static inline bool folio_mapped(struct folio *folio) +{ + return folio_mapcount(folio) > 0; } -#endif static inline struct page *virt_to_head_page(const void *x) { @@ -1800,9 +1842,6 @@ static inline pgoff_t page_index(struct page *page) return page->index; } -bool page_mapped(struct page *page); -bool folio_mapped(struct folio *folio); - /* * Return true only if the page has been allocated with * ALLOC_NO_WATERMARKS and the low watermark was not diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 44f1f8b6be02..44a1a699b5ad 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -142,6 +142,7 @@ struct page { unsigned char compound_dtor; unsigned char compound_order; atomic_t compound_mapcount; + atomic_t subpages_mapcount; atomic_t compound_pincount; #ifdef CONFIG_64BIT unsigned int compound_nr; /* 1 << compound_order */ @@ -270,7 +271,8 @@ struct page { * @_head_1: Points to the folio. Do not use. * @_folio_dtor: Which destructor to use for this folio. * @_folio_order: Do not use directly, call folio_order(). - * @_total_mapcount: Do not use directly, call folio_entire_mapcount(). + * @_compound_mapcount: Do not use directly, call folio_entire_mapcount(). + * @_subpages_mapcount: Do not use directly, call folio_mapcount(). * @_pincount: Do not use directly, call folio_maybe_dma_pinned(). * @_folio_nr_pages: Do not use directly, call folio_nr_pages(). * @_flags_2: For alignment. Do not use. @@ -323,7 +325,8 @@ struct folio { unsigned long _head_1; unsigned char _folio_dtor; unsigned char _folio_order; - atomic_t _total_mapcount; + atomic_t _compound_mapcount; + atomic_t _subpages_mapcount; atomic_t _pincount; #ifdef CONFIG_64BIT unsigned int _folio_nr_pages; @@ -365,7 +368,8 @@ FOLIO_MATCH(flags, _flags_1); FOLIO_MATCH(compound_head, _head_1); FOLIO_MATCH(compound_dtor, _folio_dtor); FOLIO_MATCH(compound_order, _folio_order); -FOLIO_MATCH(compound_mapcount, _total_mapcount); +FOLIO_MATCH(compound_mapcount, _compound_mapcount); +FOLIO_MATCH(subpages_mapcount, _subpages_mapcount); FOLIO_MATCH(compound_pincount, _pincount); #ifdef CONFIG_64BIT FOLIO_MATCH(compound_nr, _folio_nr_pages); @@ -388,11 +392,22 @@ static inline atomic_t *folio_mapcount_ptr(struct folio *folio) return &tail->compound_mapcount; } +static inline atomic_t *folio_subpages_mapcount_ptr(struct folio *folio) +{ + struct page *tail = &folio->page + 1; + return &tail->subpages_mapcount; +} + static inline atomic_t *compound_mapcount_ptr(struct page *page) { return &page[1].compound_mapcount; } +static inline atomic_t *subpages_mapcount_ptr(struct page *page) +{ + return &page[1].subpages_mapcount; +} + static inline atomic_t *compound_pincount_ptr(struct page *page) { return &page[1].compound_pincount; diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 0b0ae5084e60..e42c55a7e012 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -176,9 +176,6 @@ enum pageflags { /* SLOB */ PG_slob_free = PG_private, - /* Compound pages. Stored in first tail page's flags */ - PG_double_map = PG_workingset, - #ifdef CONFIG_MEMORY_FAILURE /* * Compound pages. Stored in first tail page's flags. @@ -874,29 +871,11 @@ static inline int PageTransTail(struct page *page) { return PageTail(page); } - -/* - * PageDoubleMap indicates that the compound page is mapped with PTEs as well - * as PMDs. - * - * This is required for optimization of rmap operations for THP: we can postpone - * per small page mapcount accounting (and its overhead from atomic operations) - * until the first PMD split. - * - * For the page PageDoubleMap means ->_mapcount in all sub-pages is offset up - * by one. This reference will go away with last compound_mapcount. - * - * See also __split_huge_pmd_locked() and page_remove_anon_compound_rmap(). - */ -PAGEFLAG(DoubleMap, double_map, PF_SECOND) - TESTSCFLAG(DoubleMap, double_map, PF_SECOND) #else TESTPAGEFLAG_FALSE(TransHuge, transhuge) TESTPAGEFLAG_FALSE(TransCompound, transcompound) TESTPAGEFLAG_FALSE(TransCompoundMap, transcompoundmap) TESTPAGEFLAG_FALSE(TransTail, transtail) -PAGEFLAG_FALSE(DoubleMap, double_map) - TESTSCFLAG_FALSE(DoubleMap, double_map) #endif #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_TRANSPARENT_HUGEPAGE) diff --git a/include/linux/rmap.h b/include/linux/rmap.h index bd3504d11b15..1973649e8f93 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -206,6 +206,8 @@ void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, static inline void __page_dup_rmap(struct page *page, bool compound) { + if (!compound && PageCompound(page)) + atomic_inc(subpages_mapcount_ptr(compound_head(page))); atomic_inc(compound ? compound_mapcount_ptr(page) : &page->_mapcount); } diff --git a/mm/debug.c b/mm/debug.c index 0fd15ba70d16..7f8e5f744e42 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -94,9 +94,10 @@ static void __dump_page(struct page *page) page, page_ref_count(head), mapcount, mapping, page_to_pgoff(page), page_to_pfn(page)); if (compound) { - pr_warn("head:%p order:%u compound_mapcount:%d compound_pincount:%d\n", + pr_warn("head:%p order:%u compound_mapcount:%d subpages_mapcount:%d compound_pincount:%d\n", head, compound_order(head), - folio_entire_mapcount(folio), + head_compound_mapcount(head), + head_subpages_mapcount(head), head_compound_pincount(head)); } diff --git a/mm/folio-compat.c b/mm/folio-compat.c index bac2a366aada..cbfe51091c39 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -39,12 +39,6 @@ void wait_for_stable_page(struct page *page) } EXPORT_SYMBOL_GPL(wait_for_stable_page); -bool page_mapped(struct page *page) -{ - return folio_mapped(page_folio(page)); -} -EXPORT_SYMBOL(page_mapped); - void mark_page_accessed(struct page *page) { folio_mark_accessed(page_folio(page)); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index b26998d1845f..7703169107c6 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2142,6 +2142,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, VM_BUG_ON_PAGE(!page_count(page), page); page_ref_add(page, HPAGE_PMD_NR - 1); + atomic_add(HPAGE_PMD_NR, subpages_mapcount_ptr(page)); /* * Without "freeze", we'll simply split the PMD, propagating the @@ -2225,33 +2226,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, pte_unmap(pte); } - if (!pmd_migration) { - /* - * Set PG_double_map before dropping compound_mapcount to avoid - * false-negative page_mapped(). - */ - if (compound_mapcount(page) > 1 && - !TestSetPageDoubleMap(page)) { - for (i = 0; i < HPAGE_PMD_NR; i++) - atomic_inc(&page[i]._mapcount); - } - - lock_page_memcg(page); - if (atomic_add_negative(-1, compound_mapcount_ptr(page))) { - /* Last compound_mapcount is gone. */ - __mod_lruvec_page_state(page, NR_ANON_THPS, - -HPAGE_PMD_NR); - if (TestClearPageDoubleMap(page)) { - /* No need in mapcount reference anymore */ - for (i = 0; i < HPAGE_PMD_NR; i++) - atomic_dec(&page[i]._mapcount); - } - } - unlock_page_memcg(page); - - /* Above is effectively page_remove_rmap(page, vma, true) */ - munlock_vma_page(page, vma, true); - } + if (!pmd_migration) + page_remove_rmap(page, vma, true); smp_wmb(); /* make pte visible before pmd */ pmd_populate(mm, pmd, pgtable); @@ -2453,7 +2429,7 @@ static void __split_huge_page_tail(struct page *head, int tail, (1L << PG_dirty) | LRU_GEN_MASK | LRU_REFS_MASK)); - /* ->mapping in first tail page is compound_mapcount */ + /* ->mapping in first and second tail page is replaced by other uses */ VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING, page_tail); page_tail->mapping = head->mapping; @@ -2463,6 +2439,10 @@ static void __split_huge_page_tail(struct page *head, int tail, * page->private should not be set in tail pages with the exception * of swap cache pages that store the swp_entry_t in tail pages. * Fix up and warn once if private is unexpectedly set. + * + * What of 32-bit systems, on which head[1].compound_pincount overlays + * head[1].private? No problem: THP_SWAP is not enabled on 32-bit, and + * compound_pincount must be 0 for folio_ref_freeze() to have succeeded. */ if (!folio_test_swapcache(page_folio(head))) { VM_WARN_ON_ONCE_PAGE(page_tail->private != 0, page_tail); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 76ebefe02827..4f1338d82aab 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1333,6 +1333,7 @@ static void __destroy_compound_gigantic_page(struct page *page, struct page *p; atomic_set(compound_mapcount_ptr(page), 0); + atomic_set(subpages_mapcount_ptr(page), 0); atomic_set(compound_pincount_ptr(page), 0); for (i = 1; i < nr_pages; i++) { @@ -1852,6 +1853,7 @@ static bool __prep_compound_gigantic_page(struct page *page, unsigned int order, set_compound_head(p, page); } atomic_set(compound_mapcount_ptr(page), -1); + atomic_set(subpages_mapcount_ptr(page), 0); atomic_set(compound_pincount_ptr(page), 0); return true; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 9c111273bbf9..0d8f548d9d7e 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1238,15 +1238,8 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, /* * Check if the page has any GUP (or other external) pins. * - * Here the check is racy it may see total_mapcount > refcount - * in some cases. - * For example, one process with one forked child process. - * The parent has the PMD split due to MADV_DONTNEED, then - * the child is trying unmap the whole PMD, but khugepaged - * may be scanning the parent between the child has - * PageDoubleMap flag cleared and dec the mapcount. So - * khugepaged may see total_mapcount > refcount. - * + * Here the check may be racy: + * it may see total_mapcount > refcount in some cases? * But such case is ephemeral we could always retry collapse * later. However it may report false positive if the page * has excessive GUP pins (i.e. 512). Anyway the same check diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6e60657875d3..0705917ddf54 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -798,6 +798,7 @@ static void prep_compound_head(struct page *page, unsigned int order) set_compound_page_dtor(page, COMPOUND_PAGE_DTOR); set_compound_order(page, order); atomic_set(compound_mapcount_ptr(page), -1); + atomic_set(subpages_mapcount_ptr(page), 0); atomic_set(compound_pincount_ptr(page), 0); } @@ -1324,11 +1325,19 @@ static int free_tail_pages_check(struct page *head_page, struct page *page) } switch (page - head_page) { case 1: - /* the first tail page: ->mapping may be compound_mapcount() */ - if (unlikely(compound_mapcount(page))) { + /* the first tail page: these may be in place of ->mapping */ + if (unlikely(head_compound_mapcount(head_page))) { bad_page(page, "nonzero compound_mapcount"); goto out; } + if (unlikely(head_subpages_mapcount(head_page))) { + bad_page(page, "nonzero subpages_mapcount"); + goto out; + } + if (unlikely(head_compound_pincount(head_page))) { + bad_page(page, "nonzero compound_pincount"); + goto out; + } break; case 2: /* @@ -1431,10 +1440,8 @@ static __always_inline bool free_pages_prepare(struct page *page, VM_BUG_ON_PAGE(compound && compound_order(page) != order, page); - if (compound) { - ClearPageDoubleMap(page); + if (compound) ClearPageHasHWPoisoned(page); - } for (i = 1; i < (1 << order); i++) { if (compound) bad += free_tail_pages_check(page, page + i); @@ -6874,13 +6881,11 @@ static void __ref memmap_init_compound(struct page *head, set_page_count(page, 0); /* - * The first tail page stores compound_mapcount_ptr() and - * compound_order() and the second tail page stores - * compound_pincount_ptr(). Call prep_compound_head() after - * the first and second tail pages have been initialized to - * not have the data overwritten. + * The first tail page stores important compound page info. + * Call prep_compound_head() after the first tail page has + * been initialized, to not have the data overwritten. */ - if (pfn == head_pfn + 2) + if (pfn == head_pfn + 1) prep_compound_head(head, order); } } diff --git a/mm/rmap.c b/mm/rmap.c index 3b2d18bbdc44..f43339ea4970 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1085,6 +1085,24 @@ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, return page_vma_mkclean_one(&pvmw); } +/* + * When mapping a THP's first pmd, or unmapping its last pmd, if that THP + * also has pte mappings, then those must be discounted: in order to maintain + * NR_ANON_MAPPED and NR_FILE_MAPPED statistics exactly, without any drift, + * and to decide when an anon THP should be put on the deferred split queue. + */ +static int nr_subpages_unmapped(struct page *head, int nr_subpages) +{ + int nr = nr_subpages; + int i; + + /* Discount those subpages mapped by pte */ + for (i = 0; i < nr_subpages; i++) + if (atomic_read(&head[i]._mapcount) >= 0) + nr--; + return nr; +} + /** * page_move_anon_rmap - move a page to our anon_vma * @page: the page to move to our anon_vma @@ -1194,6 +1212,7 @@ static void __page_check_anon_rmap(struct page *page, void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { + int nr, nr_pages; bool compound = flags & RMAP_COMPOUND; bool first; @@ -1202,28 +1221,32 @@ void page_add_anon_rmap(struct page *page, else VM_BUG_ON_PAGE(!PageLocked(page), page); - if (compound) { + if (compound && PageTransHuge(page)) { atomic_t *mapcount; VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(!PageTransHuge(page), page); mapcount = compound_mapcount_ptr(page); first = atomic_inc_and_test(mapcount); + + nr = nr_pages = thp_nr_pages(page); + if (first && head_subpages_mapcount(page)) + nr = nr_subpages_unmapped(page, nr_pages); } else { + nr = 1; + if (PageTransCompound(page)) { + struct page *head = compound_head(page); + + atomic_inc(subpages_mapcount_ptr(head)); + nr = !head_compound_mapcount(head); + } first = atomic_inc_and_test(&page->_mapcount); } + VM_BUG_ON_PAGE(!first && (flags & RMAP_EXCLUSIVE), page); VM_BUG_ON_PAGE(!first && PageAnonExclusive(page), page); if (first) { - int nr = compound ? thp_nr_pages(page) : 1; - /* - * We use the irq-unsafe __{inc|mod}_zone_page_stat because - * these counters are not modified in interrupt context, and - * pte lock(a spinlock) is held, which implies preemption - * disabled. - */ if (compound) - __mod_lruvec_page_state(page, NR_ANON_THPS, nr); + __mod_lruvec_page_state(page, NR_ANON_THPS, nr_pages); __mod_lruvec_page_state(page, NR_ANON_MAPPED, nr); } @@ -1265,8 +1288,6 @@ void page_add_new_anon_rmap(struct page *page, VM_BUG_ON_PAGE(!PageTransHuge(page), page); /* increment count (starts at -1) */ atomic_set(compound_mapcount_ptr(page), 0); - atomic_set(compound_pincount_ptr(page), 0); - __mod_lruvec_page_state(page, NR_ANON_THPS, nr); } else { /* increment count (starts at -1) */ @@ -1287,29 +1308,19 @@ void page_add_new_anon_rmap(struct page *page, void page_add_file_rmap(struct page *page, struct vm_area_struct *vma, bool compound) { - int i, nr = 0; + int nr = 0; VM_BUG_ON_PAGE(compound && !PageTransHuge(page), page); lock_page_memcg(page); if (compound && PageTransHuge(page)) { - int nr_pages = thp_nr_pages(page); + int nr_pages; - for (i = 0; i < nr_pages; i++) { - if (atomic_inc_and_test(&page[i]._mapcount)) - nr++; - } if (!atomic_inc_and_test(compound_mapcount_ptr(page))) goto out; - /* - * It is racy to ClearPageDoubleMap in page_remove_file_rmap(); - * but page lock is held by all page_add_file_rmap() compound - * callers, and SetPageDoubleMap below warns if !PageLocked: - * so here is a place that DoubleMap can be safely cleared. - */ - VM_WARN_ON_ONCE(!PageLocked(page)); - if (nr == nr_pages && PageDoubleMap(page)) - ClearPageDoubleMap(page); + nr = nr_pages = thp_nr_pages(page); + if (head_subpages_mapcount(page)) + nr = nr_subpages_unmapped(page, nr_pages); if (PageSwapBacked(page)) __mod_lruvec_page_state(page, NR_SHMEM_PMDMAPPED, @@ -1318,11 +1329,15 @@ void page_add_file_rmap(struct page *page, __mod_lruvec_page_state(page, NR_FILE_PMDMAPPED, nr_pages); } else { - if (PageTransCompound(page) && page_mapping(page)) { - VM_WARN_ON_ONCE(!PageLocked(page)); - SetPageDoubleMap(compound_head(page)); + bool pmd_mapped = false; + + if (PageTransCompound(page)) { + struct page *head = compound_head(page); + + atomic_inc(subpages_mapcount_ptr(head)); + pmd_mapped = head_compound_mapcount(head); } - if (atomic_inc_and_test(&page->_mapcount)) + if (atomic_inc_and_test(&page->_mapcount) && !pmd_mapped) nr++; } out: @@ -1335,7 +1350,7 @@ out: static void page_remove_file_rmap(struct page *page, bool compound) { - int i, nr = 0; + int nr = 0; VM_BUG_ON_PAGE(compound && !PageHead(page), page); @@ -1348,14 +1363,15 @@ static void page_remove_file_rmap(struct page *page, bool compound) /* page still mapped by someone else? */ if (compound && PageTransHuge(page)) { - int nr_pages = thp_nr_pages(page); + int nr_pages; - for (i = 0; i < nr_pages; i++) { - if (atomic_add_negative(-1, &page[i]._mapcount)) - nr++; - } if (!atomic_add_negative(-1, compound_mapcount_ptr(page))) - goto out; + return; + + nr = nr_pages = thp_nr_pages(page); + if (head_subpages_mapcount(page)) + nr = nr_subpages_unmapped(page, nr_pages); + if (PageSwapBacked(page)) __mod_lruvec_page_state(page, NR_SHMEM_PMDMAPPED, -nr_pages); @@ -1363,17 +1379,25 @@ static void page_remove_file_rmap(struct page *page, bool compound) __mod_lruvec_page_state(page, NR_FILE_PMDMAPPED, -nr_pages); } else { - if (atomic_add_negative(-1, &page->_mapcount)) + bool pmd_mapped = false; + + if (PageTransCompound(page)) { + struct page *head = compound_head(page); + + atomic_dec(subpages_mapcount_ptr(head)); + pmd_mapped = head_compound_mapcount(head); + } + if (atomic_add_negative(-1, &page->_mapcount) && !pmd_mapped) nr++; } -out: + if (nr) __mod_lruvec_page_state(page, NR_FILE_MAPPED, -nr); } static void page_remove_anon_compound_rmap(struct page *page) { - int i, nr; + int nr, nr_pages; if (!atomic_add_negative(-1, compound_mapcount_ptr(page))) return; @@ -1385,27 +1409,19 @@ static void page_remove_anon_compound_rmap(struct page *page) if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return; - __mod_lruvec_page_state(page, NR_ANON_THPS, -thp_nr_pages(page)); + nr = nr_pages = thp_nr_pages(page); + __mod_lruvec_page_state(page, NR_ANON_THPS, -nr); - if (TestClearPageDoubleMap(page)) { - /* - * Subpages can be mapped with PTEs too. Check how many of - * them are still mapped. - */ - for (i = 0, nr = 0; i < thp_nr_pages(page); i++) { - if (atomic_add_negative(-1, &page[i]._mapcount)) - nr++; - } + if (head_subpages_mapcount(page)) { + nr = nr_subpages_unmapped(page, nr_pages); /* * Queue the page for deferred split if at least one small * page of the compound page is unmapped, but at least one * small page is still mapped. */ - if (nr && nr < thp_nr_pages(page)) + if (nr && nr < nr_pages) deferred_split_huge_page(page); - } else { - nr = thp_nr_pages(page); } if (nr) @@ -1423,6 +1439,8 @@ static void page_remove_anon_compound_rmap(struct page *page) void page_remove_rmap(struct page *page, struct vm_area_struct *vma, bool compound) { + bool pmd_mapped = false; + lock_page_memcg(page); if (!PageAnon(page)) { @@ -1435,15 +1453,17 @@ void page_remove_rmap(struct page *page, goto out; } + if (PageTransCompound(page)) { + struct page *head = compound_head(page); + + atomic_dec(subpages_mapcount_ptr(head)); + pmd_mapped = head_compound_mapcount(head); + } + /* page still mapped by someone else? */ - if (!atomic_add_negative(-1, &page->_mapcount)) + if (!atomic_add_negative(-1, &page->_mapcount) || pmd_mapped) goto out; - /* - * We use the irq-unsafe __{inc|mod}_zone_page_stat because - * these counters are not modified in interrupt context, and - * pte lock(a spinlock) is held, which implies preemption disabled. - */ __dec_lruvec_page_state(page, NR_ANON_MAPPED); if (PageTransCompound(page)) @@ -2569,8 +2589,8 @@ void hugepage_add_new_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address) { BUG_ON(address < vma->vm_start || address >= vma->vm_end); + /* increment count (starts at -1) */ atomic_set(compound_mapcount_ptr(page), 0); - atomic_set(compound_pincount_ptr(page), 0); ClearHPageRestoreReserve(page); __page_set_anon_rmap(page, vma, address, 1); } diff --git a/mm/util.c b/mm/util.c index 12984e76767e..b56c92fb910f 100644 --- a/mm/util.c +++ b/mm/util.c @@ -717,32 +717,6 @@ void *page_rmapping(struct page *page) return folio_raw_mapping(page_folio(page)); } -/** - * folio_mapped - Is this folio mapped into userspace? - * @folio: The folio. - * - * Return: True if any page in this folio is referenced by user page tables. - */ -bool folio_mapped(struct folio *folio) -{ - long i, nr; - - if (!folio_test_large(folio)) - return atomic_read(&folio->_mapcount) >= 0; - if (atomic_read(folio_mapcount_ptr(folio)) >= 0) - return true; - if (folio_test_hugetlb(folio)) - return false; - - nr = folio_nr_pages(folio); - for (i = 0; i < nr; i++) { - if (atomic_read(&folio_page(folio, i)->_mapcount) >= 0) - return true; - } - return false; -} -EXPORT_SYMBOL(folio_mapped); - struct anon_vma *folio_anon_vma(struct folio *folio) { unsigned long mapping = (unsigned long)folio->mapping; @@ -783,59 +757,6 @@ struct address_space *folio_mapping(struct folio *folio) } EXPORT_SYMBOL(folio_mapping); -/* Slow path of page_mapcount() for compound pages */ -int __page_mapcount(struct page *page) -{ - int ret; - - ret = atomic_read(&page->_mapcount) + 1; - /* - * For file THP page->_mapcount contains total number of mapping - * of the page: no need to look into compound_mapcount. - */ - if (!PageAnon(page) && !PageHuge(page)) - return ret; - page = compound_head(page); - ret += atomic_read(compound_mapcount_ptr(page)) + 1; - if (PageDoubleMap(page)) - ret--; - return ret; -} -EXPORT_SYMBOL_GPL(__page_mapcount); - -/** - * folio_mapcount() - Calculate the number of mappings of this folio. - * @folio: The folio. - * - * A large folio tracks both how many times the entire folio is mapped, - * and how many times each individual page in the folio is mapped. - * This function calculates the total number of times the folio is - * mapped. - * - * Return: The number of times this folio is mapped. - */ -int folio_mapcount(struct folio *folio) -{ - int i, compound, nr, ret; - - if (likely(!folio_test_large(folio))) - return atomic_read(&folio->_mapcount) + 1; - - compound = folio_entire_mapcount(folio); - if (folio_test_hugetlb(folio)) - return compound; - ret = compound; - nr = folio_nr_pages(folio); - for (i = 0; i < nr; i++) - ret += atomic_read(&folio_page(folio, i)->_mapcount) + 1; - /* File pages has compound_mapcount included in _mapcount */ - if (!folio_test_anon(folio)) - return ret - compound * nr; - if (folio_test_double_map(folio)) - ret -= nr; - return ret; -} - /** * folio_copy - Copy the contents of one folio to another. * @dst: Folio to copy to. -- cgit v1.2.3 From 369258ce41c6d7663a7b6d509356fecad577378d Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Mon, 14 Nov 2022 15:55:07 -0800 Subject: hugetlb: remove duplicate mmu notifications The common hugetlb unmap routine __unmap_hugepage_range performs mmu notification calls. However, in the case where __unmap_hugepage_range is called via __unmap_hugepage_range_final, mmu notification calls are performed earlier in other calling routines. Remove mmu notification calls from __unmap_hugepage_range. Add notification calls to the only other caller: unmap_hugepage_range. unmap_hugepage_range is called for truncation and hole punch, so change notification type from UNMAP to CLEAR as this is more appropriate. Link: https://lkml.kernel.org/r/20221114235507.294320-4-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Suggested-by: Peter Xu Cc: Wei Chen Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Matthew Wilcox Cc: Mina Almasry Cc: Nadav Amit Cc: Naoya Horiguchi Cc: Rik van Riel Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- mm/hugetlb.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 4f1338d82aab..3fd4570fb8b0 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5076,7 +5076,6 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct struct page *page; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); - struct mmu_notifier_range range; unsigned long last_addr_mask; bool force_flush = false; @@ -5091,13 +5090,6 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct tlb_change_page_size(tlb, sz); tlb_start_vma(tlb, vma); - /* - * If sharing possible, alert mmu notifiers of worst case. - */ - mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, mm, start, - end); - adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); - mmu_notifier_invalidate_range_start(&range); last_addr_mask = hugetlb_mask_last_page(h); address = start; for (; address < end; address += sz) { @@ -5182,7 +5174,6 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct if (ref_page) break; } - mmu_notifier_invalidate_range_end(&range); tlb_end_vma(tlb, vma); /* @@ -5210,6 +5201,7 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb, hugetlb_vma_lock_write(vma); i_mmap_lock_write(vma->vm_file->f_mapping); + /* mmu notification performed in caller */ __unmap_hugepage_range(tlb, vma, start, end, ref_page, zap_flags); if (zap_flags & ZAP_FLAG_UNMAP) { /* final unmap */ @@ -5234,10 +5226,18 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page, zap_flags_t zap_flags) { + struct mmu_notifier_range range; struct mmu_gather tlb; + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, + start, end); + adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); + mmu_notifier_invalidate_range_start(&range); tlb_gather_mmu(&tlb, vma->vm_mm); + __unmap_hugepage_range(&tlb, vma, start, end, ref_page, zap_flags); + + mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb); } -- cgit v1.2.3 From cdc5021cda194112bc0962d6a0e90b379968c504 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 16 Nov 2022 11:26:43 +0100 Subject: mm: add early FAULT_FLAG_UNSHARE consistency checks For now, FAULT_FLAG_UNSHARE only applies to anonymous pages, which implies a COW mapping. Let's hide FAULT_FLAG_UNSHARE early if we're not dealing with a COW mapping, such that we treat it like a read fault as documented and don't have to worry about the flag throughout all fault handlers. While at it, centralize the check for mutual exclusion of FAULT_FLAG_UNSHARE and FAULT_FLAG_WRITE and just drop the check that either flag is set in the WP handler. Link: https://lkml.kernel.org/r/20221116102659.70287-5-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Vlastimil Babka Signed-off-by: Andrew Morton --- mm/huge_memory.c | 3 --- mm/hugetlb.c | 5 ----- mm/memory.c | 23 ++++++++++++++++++++--- 3 files changed, 20 insertions(+), 11 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 29102e3ddf84..5eb702726a0e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1313,9 +1313,6 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) vmf->ptl = pmd_lockptr(vma->vm_mm, vmf->pmd); VM_BUG_ON_VMA(!vma->anon_vma, vma); - VM_BUG_ON(unshare && (vmf->flags & FAULT_FLAG_WRITE)); - VM_BUG_ON(!unshare && !(vmf->flags & FAULT_FLAG_WRITE)); - if (is_huge_zero_pmd(orig_pmd)) goto fallback; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3fd4570fb8b0..3d381b26d553 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5316,9 +5316,6 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr = address & huge_page_mask(h); struct mmu_notifier_range range; - VM_BUG_ON(unshare && (flags & FOLL_WRITE)); - VM_BUG_ON(!unshare && !(flags & FOLL_WRITE)); - /* * hugetlb does not support FOLL_FORCE-style write faults that keep the * PTE mapped R/O such as maybe_mkwrite() would do. @@ -5328,8 +5325,6 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, /* Let's take out MAP_SHARED mappings first. */ if (vma->vm_flags & VM_MAYSHARE) { - if (unlikely(unshare)) - return 0; set_huge_ptep_writable(vma, haddr, ptep); return 0; } diff --git a/mm/memory.c b/mm/memory.c index 086cb3dd8608..07380ef935ac 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3343,9 +3343,6 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; struct folio *folio; - VM_BUG_ON(unshare && (vmf->flags & FAULT_FLAG_WRITE)); - VM_BUG_ON(!unshare && !(vmf->flags & FAULT_FLAG_WRITE)); - if (likely(!unshare)) { if (userfaultfd_pte_wp(vma, *vmf->pte)) { pte_unmap_unlock(vmf->pte, vmf->ptl); @@ -5161,6 +5158,22 @@ static void lru_gen_exit_fault(void) } #endif /* CONFIG_LRU_GEN */ +static vm_fault_t sanitize_fault_flags(struct vm_area_struct *vma, + unsigned int *flags) +{ + if (unlikely(*flags & FAULT_FLAG_UNSHARE)) { + if (WARN_ON_ONCE(*flags & FAULT_FLAG_WRITE)) + return VM_FAULT_SIGSEGV; + /* + * FAULT_FLAG_UNSHARE only applies to COW mappings. Let's + * just treat it like an ordinary read-fault otherwise. + */ + if (!is_cow_mapping(vma->vm_flags)) + *flags &= ~FAULT_FLAG_UNSHARE; + } + return 0; +} + /* * By the time we get here, we already hold the mm semaphore * @@ -5177,6 +5190,10 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, count_vm_event(PGFAULT); count_memcg_event_mm(vma->vm_mm, PGFAULT); + ret = sanitize_fault_flags(vma, &flags); + if (ret) + return ret; + if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE, flags & FAULT_FLAG_INSTRUCTION, flags & FAULT_FLAG_REMOTE)) -- cgit v1.2.3 From 84209e87c6963f928194a890399e24e8ad299db1 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 16 Nov 2022 11:26:48 +0100 Subject: mm/gup: reliable R/O long-term pinning in COW mappings We already support reliable R/O pinning of anonymous memory. However, assume we end up pinning (R/O long-term) a pagecache page or the shared zeropage inside a writable private ("COW") mapping. The next write access will trigger a write-fault and replace the pinned page by an exclusive anonymous page in the process page tables to break COW: the pinned page no longer corresponds to the page mapped into the process' page table. Now that FAULT_FLAG_UNSHARE can break COW on anything mapped into a COW mapping, let's properly break COW first before R/O long-term pinning something that's not an exclusive anon page inside a COW mapping. FAULT_FLAG_UNSHARE will break COW and map an exclusive anon page instead that can get pinned safely. With this change, we can stop using FOLL_FORCE|FOLL_WRITE for reliable R/O long-term pinning in COW mappings. With this change, the new R/O long-term pinning tests for non-anonymous memory succeed: # [RUN] R/O longterm GUP pin ... with shared zeropage ok 151 Longterm R/O pin is reliable # [RUN] R/O longterm GUP pin ... with memfd ok 152 Longterm R/O pin is reliable # [RUN] R/O longterm GUP pin ... with tmpfile ok 153 Longterm R/O pin is reliable # [RUN] R/O longterm GUP pin ... with huge zeropage ok 154 Longterm R/O pin is reliable # [RUN] R/O longterm GUP pin ... with memfd hugetlb (2048 kB) ok 155 Longterm R/O pin is reliable # [RUN] R/O longterm GUP pin ... with memfd hugetlb (1048576 kB) ok 156 Longterm R/O pin is reliable # [RUN] R/O longterm GUP-fast pin ... with shared zeropage ok 157 Longterm R/O pin is reliable # [RUN] R/O longterm GUP-fast pin ... with memfd ok 158 Longterm R/O pin is reliable # [RUN] R/O longterm GUP-fast pin ... with tmpfile ok 159 Longterm R/O pin is reliable # [RUN] R/O longterm GUP-fast pin ... with huge zeropage ok 160 Longterm R/O pin is reliable # [RUN] R/O longterm GUP-fast pin ... with memfd hugetlb (2048 kB) ok 161 Longterm R/O pin is reliable # [RUN] R/O longterm GUP-fast pin ... with memfd hugetlb (1048576 kB) ok 162 Longterm R/O pin is reliable Note 1: We don't care about short-term R/O-pinning, because they have snapshot semantics: they are not supposed to observe modifications that happen after pinning. As one example, assume we start direct I/O to read from a page and store page content into a file: modifications to page content after starting direct I/O are not guaranteed to end up in the file. So even if we'd pin the shared zeropage, the end result would be as expected -- getting zeroes stored to the file. Note 2: For shared mappings we'll now always fallback to the slow path to lookup the VMA when R/O long-term pining. While that's the necessary price we have to pay right now, it's actually not that bad in practice: most FOLL_LONGTERM users already specify FOLL_WRITE, for example, along with FOLL_FORCE because they tried dealing with COW mappings correctly ... Note 3: For users that use FOLL_LONGTERM right now without FOLL_WRITE, such as VFIO, we'd now no longer pin the shared zeropage. Instead, we'd populate exclusive anon pages that we can pin. There was a concern that this could affect the memlock limit of existing setups. For example, a VM running with VFIO could run into the memlock limit and fail to run. However, we essentially had the same behavior already in commit 17839856fd58 ("gup: document and work around "COW can break either way" issue") which got merged into some enterprise distros, and there were not any such complaints. So most probably, we're fine. Link: https://lkml.kernel.org/r/20221116102659.70287-10-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Daniel Vetter Reviewed-by: Vlastimil Babka Reviewed-by: John Hubbard Signed-off-by: Andrew Morton --- include/linux/mm.h | 27 ++++++++++++++++++++++++--- mm/gup.c | 10 +++++----- mm/huge_memory.c | 2 +- mm/hugetlb.c | 7 ++++--- 4 files changed, 34 insertions(+), 12 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/include/linux/mm.h b/include/linux/mm.h index 686879dbb0bd..d8363ac34a7c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3149,8 +3149,12 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) * Must be called with the (sub)page that's actually referenced via the * page table entry, which might not necessarily be the head page for a * PTE-mapped THP. + * + * If the vma is NULL, we're coming from the GUP-fast path and might have + * to fallback to the slow path just to lookup the vma. */ -static inline bool gup_must_unshare(unsigned int flags, struct page *page) +static inline bool gup_must_unshare(struct vm_area_struct *vma, + unsigned int flags, struct page *page) { /* * FOLL_WRITE is implicitly handled correctly as the page table entry @@ -3163,8 +3167,25 @@ static inline bool gup_must_unshare(unsigned int flags, struct page *page) * Note: PageAnon(page) is stable until the page is actually getting * freed. */ - if (!PageAnon(page)) - return false; + if (!PageAnon(page)) { + /* + * We only care about R/O long-term pining: R/O short-term + * pinning does not have the semantics to observe successive + * changes through the process page tables. + */ + if (!(flags & FOLL_LONGTERM)) + return false; + + /* We really need the vma ... */ + if (!vma) + return true; + + /* + * ... because we only care about writable private ("COW") + * mappings where we have to break COW early. + */ + return is_cow_mapping(vma->vm_flags); + } /* Paired with a memory barrier in page_try_share_anon_rmap(). */ if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) diff --git a/mm/gup.c b/mm/gup.c index 2500d00db51b..39c84a200f06 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -603,7 +603,7 @@ retry: } } - if (!pte_write(pte) && gup_must_unshare(flags, page)) { + if (!pte_write(pte) && gup_must_unshare(vma, flags, page)) { page = ERR_PTR(-EMLINK); goto out; } @@ -2380,7 +2380,7 @@ static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, goto pte_unmap; } - if (!pte_write(pte) && gup_must_unshare(flags, page)) { + if (!pte_write(pte) && gup_must_unshare(NULL, flags, page)) { gup_put_folio(folio, 1, flags); goto pte_unmap; } @@ -2566,7 +2566,7 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, return 0; } - if (!pte_write(pte) && gup_must_unshare(flags, &folio->page)) { + if (!pte_write(pte) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } @@ -2632,7 +2632,7 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, return 0; } - if (!pmd_write(orig) && gup_must_unshare(flags, &folio->page)) { + if (!pmd_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } @@ -2672,7 +2672,7 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, return 0; } - if (!pud_write(orig) && gup_must_unshare(flags, &folio->page)) { + if (!pud_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 5eb702726a0e..86a30041a2e1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1480,7 +1480,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, if (pmd_protnone(*pmd) && !gup_can_follow_protnone(flags)) return NULL; - if (!pmd_write(*pmd) && gup_must_unshare(flags, page)) + if (!pmd_write(*pmd) && gup_must_unshare(vma, flags, page)) return ERR_PTR(-EMLINK); VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3d381b26d553..9d97c9a2a15d 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -6197,7 +6197,8 @@ static void record_subpages_vmas(struct page *page, struct vm_area_struct *vma, } } -static inline bool __follow_hugetlb_must_fault(unsigned int flags, pte_t *pte, +static inline bool __follow_hugetlb_must_fault(struct vm_area_struct *vma, + unsigned int flags, pte_t *pte, bool *unshare) { pte_t pteval = huge_ptep_get(pte); @@ -6209,7 +6210,7 @@ static inline bool __follow_hugetlb_must_fault(unsigned int flags, pte_t *pte, return false; if (flags & FOLL_WRITE) return true; - if (gup_must_unshare(flags, pte_page(pteval))) { + if (gup_must_unshare(vma, flags, pte_page(pteval))) { *unshare = true; return true; } @@ -6338,7 +6339,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, * directly from any kind of swap entries. */ if (absent || - __follow_hugetlb_must_fault(flags, pte, &unshare)) { + __follow_hugetlb_must_fault(vma, flags, pte, &unshare)) { vm_fault_t ret; unsigned int fault_flags = 0; -- cgit v1.2.3 From 9fd330582b2fe43c49ebcd02b2480f051f85aad4 Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Tue, 29 Nov 2022 14:50:30 -0800 Subject: mm: add folio dtor and order setter functions Patch series "convert core hugetlb functions to folios", v5. ============== OVERVIEW =========================== Now that many hugetlb helper functions that deal with hugetlb specific flags[1] and hugetlb cgroups[2] are converted to folios, higher level allocation, prep, and freeing functions within hugetlb can also be converted to operate in folios. Patch 1 of this series implements the wrapper functions around setting the compound destructor and compound order for a folio. Besides the user added in patch 1, patch 2 and patch 9 also use these helper functions. Patches 2-10 convert the higher level hugetlb functions to folios. ============== TESTING =========================== LTP: Ran 10 back to back rounds of the LTP hugetlb test suite. Gigantic Huge Pages: Test allocation and freeing via hugeadm commands: hugeadm --pool-pages-min 1GB:10 hugeadm --pool-pages-min 1GB:0 Demote: Demote 1 1GB hugepages to 512 2MB hugepages echo 1 > /sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages echo 1 > /sys/kernel/mm/hugepages/hugepages-1048576kB/demote cat /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages # 512 cat /sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages # 0 [1] https://lore.kernel.org/lkml/20220922154207.1575343-1-sidhartha.kumar@oracle.com/ [2] https://lore.kernel.org/linux-mm/20221101223059.460937-1-sidhartha.kumar@oracle.com/ This patch (of 10): Add folio equivalents for set_compound_order() and set_compound_page_dtor(). Also remove extra new-lines introduced by mm/hugetlb: convert move_hugetlb_state() to folios and mm/hugetlb_cgroup: convert hugetlb_cgroup_uncharge_page() to folios. [sidhartha.kumar@oracle.com: clarify folio_set_compound_order() zero support] Link: https://lkml.kernel.org/r/20221207223731.32784-1-sidhartha.kumar@oracle.com Link: https://lkml.kernel.org/r/20221129225039.82257-1-sidhartha.kumar@oracle.com Link: https://lkml.kernel.org/r/20221129225039.82257-2-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Suggested-by: Mike Kravetz Suggested-by: Muchun Song Reviewed-by: Mike Kravetz Cc: David Hildenbrand Cc: John Hubbard Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Mina Almasry Cc: Tarun Sahu Cc: Rasmus Villemoes Cc: Wei Chen Signed-off-by: Andrew Morton --- include/linux/mm.h | 23 +++++++++++++++++++++++ mm/hugetlb.c | 4 +--- 2 files changed, 24 insertions(+), 3 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/include/linux/mm.h b/include/linux/mm.h index 472cb60ace07..7dc376052d40 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -997,6 +997,13 @@ static inline void set_compound_page_dtor(struct page *page, page[1].compound_dtor = compound_dtor; } +static inline void folio_set_compound_dtor(struct folio *folio, + enum compound_dtor_id compound_dtor) +{ + VM_BUG_ON_FOLIO(compound_dtor >= NR_COMPOUND_DTORS, folio); + folio->_folio_dtor = compound_dtor; +} + void destroy_large_folio(struct folio *folio); static inline int head_compound_pincount(struct page *head) @@ -1012,6 +1019,22 @@ static inline void set_compound_order(struct page *page, unsigned int order) #endif } +/* + * folio_set_compound_order is generally passed a non-zero order to + * initialize a large folio. However, hugetlb code abuses this by + * passing in zero when 'dissolving' a large folio. + */ +static inline void folio_set_compound_order(struct folio *folio, + unsigned int order) +{ + VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); + + folio->_folio_order = order; +#ifdef CONFIG_64BIT + folio->_folio_nr_pages = order ? 1U << order : 0; +#endif +} + /* Returns the number of pages in this potentially compound page. */ static inline unsigned long compound_nr(struct page *page) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 9d97c9a2a15d..22512f7b0237 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1780,7 +1780,7 @@ static void __prep_new_hugetlb_folio(struct hstate *h, struct folio *folio) { hugetlb_vmemmap_optimize(h, &folio->page); INIT_LIST_HEAD(&folio->lru); - folio->_folio_dtor = HUGETLB_PAGE_DTOR; + folio_set_compound_dtor(folio, HUGETLB_PAGE_DTOR); hugetlb_set_folio_subpool(folio, NULL); set_hugetlb_cgroup(folio, NULL); set_hugetlb_cgroup_rsvd(folio, NULL); @@ -2938,7 +2938,6 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, * a reservation exists for the allocation. */ page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, gbl_chg); - if (!page) { spin_unlock_irq(&hugetlb_lock); page = alloc_buddy_huge_page_with_mpol(h, vma, addr); @@ -7343,7 +7342,6 @@ void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int re int old_nid = folio_nid(old_folio); int new_nid = folio_nid(new_folio); - folio_set_hugetlb_temporary(old_folio); folio_clear_hugetlb_temporary(new_folio); -- cgit v1.2.3 From 911565b8285381e62d3bfd0cae2889a022737c37 Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Tue, 29 Nov 2022 14:50:31 -0800 Subject: mm/hugetlb: convert destroy_compound_gigantic_page() to folios Convert page operations within __destroy_compound_gigantic_page() to the corresponding folio operations. Link: https://lkml.kernel.org/r/20221129225039.82257-3-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Cc: David Hildenbrand Cc: John Hubbard Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Mina Almasry Cc: Muchun Song Cc: Rasmus Villemoes Cc: Tarun Sahu Cc: Wei Chen Signed-off-by: Andrew Morton --- mm/hugetlb.c | 43 +++++++++++++++++++++---------------------- 1 file changed, 21 insertions(+), 22 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 22512f7b0237..5960a05cb370 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1325,43 +1325,40 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) nr_nodes--) /* used to demote non-gigantic_huge pages as well */ -static void __destroy_compound_gigantic_page(struct page *page, +static void __destroy_compound_gigantic_folio(struct folio *folio, unsigned int order, bool demote) { int i; int nr_pages = 1 << order; struct page *p; - atomic_set(compound_mapcount_ptr(page), 0); - atomic_set(subpages_mapcount_ptr(page), 0); - atomic_set(compound_pincount_ptr(page), 0); + atomic_set(folio_mapcount_ptr(folio), 0); + atomic_set(folio_subpages_mapcount_ptr(folio), 0); + atomic_set(folio_pincount_ptr(folio), 0); for (i = 1; i < nr_pages; i++) { - p = nth_page(page, i); + p = folio_page(folio, i); p->mapping = NULL; clear_compound_head(p); if (!demote) set_page_refcounted(p); } - set_compound_order(page, 0); -#ifdef CONFIG_64BIT - page[1].compound_nr = 0; -#endif - __ClearPageHead(page); + folio_set_compound_order(folio, 0); + __folio_clear_head(folio); } -static void destroy_compound_hugetlb_page_for_demote(struct page *page, +static void destroy_compound_hugetlb_folio_for_demote(struct folio *folio, unsigned int order) { - __destroy_compound_gigantic_page(page, order, true); + __destroy_compound_gigantic_folio(folio, order, true); } #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE -static void destroy_compound_gigantic_page(struct page *page, +static void destroy_compound_gigantic_folio(struct folio *folio, unsigned int order) { - __destroy_compound_gigantic_page(page, order, false); + __destroy_compound_gigantic_folio(folio, order, false); } static void free_gigantic_page(struct page *page, unsigned int order) @@ -1430,7 +1427,7 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, return NULL; } static inline void free_gigantic_page(struct page *page, unsigned int order) { } -static inline void destroy_compound_gigantic_page(struct page *page, +static inline void destroy_compound_gigantic_folio(struct folio *folio, unsigned int order) { } #endif @@ -1477,8 +1474,8 @@ static void __remove_hugetlb_page(struct hstate *h, struct page *page, * * For gigantic pages set the destructor to the null dtor. This * destructor will never be called. Before freeing the gigantic - * page destroy_compound_gigantic_page will turn the compound page - * into a simple group of pages. After this the destructor does not + * page destroy_compound_gigantic_folio will turn the folio into a + * simple group of pages. After this the destructor does not * apply. * * This handles the case where more than one ref is held when and @@ -1559,6 +1556,7 @@ static void add_hugetlb_page(struct hstate *h, struct page *page, static void __update_and_free_page(struct hstate *h, struct page *page) { int i; + struct folio *folio = page_folio(page); struct page *subpage; if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) @@ -1587,8 +1585,8 @@ static void __update_and_free_page(struct hstate *h, struct page *page) * Move PageHWPoison flag from head page to the raw error pages, * which makes any healthy subpages reusable. */ - if (unlikely(PageHWPoison(page))) - hugetlb_clear_page_hwpoison(page); + if (unlikely(folio_test_hwpoison(folio))) + hugetlb_clear_page_hwpoison(&folio->page); for (i = 0; i < pages_per_huge_page(h); i++) { subpage = nth_page(page, i); @@ -1604,7 +1602,7 @@ static void __update_and_free_page(struct hstate *h, struct page *page) */ if (hstate_is_gigantic(h) || hugetlb_cma_page(page, huge_page_order(h))) { - destroy_compound_gigantic_page(page, huge_page_order(h)); + destroy_compound_gigantic_folio(folio, huge_page_order(h)); free_gigantic_page(page, huge_page_order(h)); } else { __free_pages(page, huge_page_order(h)); @@ -3437,6 +3435,7 @@ static int demote_free_huge_page(struct hstate *h, struct page *page) { int i, nid = page_to_nid(page); struct hstate *target_hstate; + struct folio *folio = page_folio(page); struct page *subpage; int rc = 0; @@ -3455,10 +3454,10 @@ static int demote_free_huge_page(struct hstate *h, struct page *page) } /* - * Use destroy_compound_hugetlb_page_for_demote for all huge page + * Use destroy_compound_hugetlb_folio_for_demote for all huge page * sizes as it will not ref count pages. */ - destroy_compound_hugetlb_page_for_demote(page, huge_page_order(h)); + destroy_compound_hugetlb_folio_for_demote(folio, huge_page_order(h)); /* * Taking target hstate mutex synchronizes with set_max_huge_pages. -- cgit v1.2.3 From 1a7cdab59b22465b850501e3897a3f3aa01670d8 Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Tue, 29 Nov 2022 14:50:32 -0800 Subject: mm/hugetlb: convert dissolve_free_huge_page() to folios Removes compound_head() call by using a folio rather than a head page. Link: https://lkml.kernel.org/r/20221129225039.82257-4-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Cc: David Hildenbrand Cc: John Hubbard Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Mina Almasry Cc: Muchun Song Cc: Rasmus Villemoes Cc: Tarun Sahu Cc: Wei Chen Signed-off-by: Andrew Morton --- mm/hugetlb.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 5960a05cb370..d02293fd2e64 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2128,21 +2128,21 @@ static struct page *remove_pool_huge_page(struct hstate *h, int dissolve_free_huge_page(struct page *page) { int rc = -EBUSY; + struct folio *folio = page_folio(page); retry: /* Not to disrupt normal path by vainly holding hugetlb_lock */ - if (!PageHuge(page)) + if (!folio_test_hugetlb(folio)) return 0; spin_lock_irq(&hugetlb_lock); - if (!PageHuge(page)) { + if (!folio_test_hugetlb(folio)) { rc = 0; goto out; } - if (!page_count(page)) { - struct page *head = compound_head(page); - struct hstate *h = page_hstate(head); + if (!folio_ref_count(folio)) { + struct hstate *h = folio_hstate(folio); if (!available_huge_pages(h)) goto out; @@ -2150,7 +2150,7 @@ retry: * We should make sure that the page is already on the free list * when it is dissolved. */ - if (unlikely(!HPageFreed(head))) { + if (unlikely(!folio_test_hugetlb_freed(folio))) { spin_unlock_irq(&hugetlb_lock); cond_resched(); @@ -2165,7 +2165,7 @@ retry: goto retry; } - remove_hugetlb_page(h, head, false); + remove_hugetlb_page(h, &folio->page, false); h->max_huge_pages--; spin_unlock_irq(&hugetlb_lock); @@ -2177,12 +2177,12 @@ retry: * Attempt to allocate vmemmmap here so that we can take * appropriate action on failure. */ - rc = hugetlb_vmemmap_restore(h, head); + rc = hugetlb_vmemmap_restore(h, &folio->page); if (!rc) { - update_and_free_page(h, head, false); + update_and_free_page(h, &folio->page, false); } else { spin_lock_irq(&hugetlb_lock); - add_hugetlb_page(h, head, false); + add_hugetlb_page(h, &folio->page, false); h->max_huge_pages++; spin_unlock_irq(&hugetlb_lock); } -- cgit v1.2.3 From cfd5082b514765f873504cc60a50cce30738bfd3 Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Tue, 29 Nov 2022 14:50:33 -0800 Subject: mm/hugetlb: convert remove_hugetlb_page() to folios Removes page_folio() call by converting callers to directly pass a folio into __remove_hugetlb_page(). Link: https://lkml.kernel.org/r/20221129225039.82257-5-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Cc: David Hildenbrand Cc: John Hubbard Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Mina Almasry Cc: Muchun Song Cc: Rasmus Villemoes Cc: Tarun Sahu Cc: Wei Chen Signed-off-by: Andrew Morton --- mm/hugetlb.c | 48 +++++++++++++++++++++++++----------------------- 1 file changed, 25 insertions(+), 23 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index d02293fd2e64..9b1c9d05ba34 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1432,19 +1432,18 @@ static inline void destroy_compound_gigantic_folio(struct folio *folio, #endif /* - * Remove hugetlb page from lists, and update dtor so that page appears + * Remove hugetlb folio from lists, and update dtor so that the folio appears * as just a compound page. * - * A reference is held on the page, except in the case of demote. + * A reference is held on the folio, except in the case of demote. * * Must be called with hugetlb lock held. */ -static void __remove_hugetlb_page(struct hstate *h, struct page *page, +static void __remove_hugetlb_folio(struct hstate *h, struct folio *folio, bool adjust_surplus, bool demote) { - int nid = page_to_nid(page); - struct folio *folio = page_folio(page); + int nid = folio_nid(folio); VM_BUG_ON_FOLIO(hugetlb_cgroup_from_folio(folio), folio); VM_BUG_ON_FOLIO(hugetlb_cgroup_from_folio_rsvd(folio), folio); @@ -1453,9 +1452,9 @@ static void __remove_hugetlb_page(struct hstate *h, struct page *page, if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; - list_del(&page->lru); + list_del(&folio->lru); - if (HPageFreed(page)) { + if (folio_test_hugetlb_freed(folio)) { h->free_huge_pages--; h->free_huge_pages_node[nid]--; } @@ -1485,26 +1484,26 @@ static void __remove_hugetlb_page(struct hstate *h, struct page *page, * be turned into a page of smaller size. */ if (!demote) - set_page_refcounted(page); + folio_ref_unfreeze(folio, 1); if (hstate_is_gigantic(h)) - set_compound_page_dtor(page, NULL_COMPOUND_DTOR); + folio_set_compound_dtor(folio, NULL_COMPOUND_DTOR); else - set_compound_page_dtor(page, COMPOUND_PAGE_DTOR); + folio_set_compound_dtor(folio, COMPOUND_PAGE_DTOR); h->nr_huge_pages--; h->nr_huge_pages_node[nid]--; } -static void remove_hugetlb_page(struct hstate *h, struct page *page, +static void remove_hugetlb_folio(struct hstate *h, struct folio *folio, bool adjust_surplus) { - __remove_hugetlb_page(h, page, adjust_surplus, false); + __remove_hugetlb_folio(h, folio, adjust_surplus, false); } -static void remove_hugetlb_page_for_demote(struct hstate *h, struct page *page, +static void remove_hugetlb_folio_for_demote(struct hstate *h, struct folio *folio, bool adjust_surplus) { - __remove_hugetlb_page(h, page, adjust_surplus, true); + __remove_hugetlb_folio(h, folio, adjust_surplus, true); } static void add_hugetlb_page(struct hstate *h, struct page *page, @@ -1639,8 +1638,9 @@ static void free_hpage_workfn(struct work_struct *work) /* * The VM_BUG_ON_PAGE(!PageHuge(page), page) in page_hstate() * is going to trigger because a previous call to - * remove_hugetlb_page() will set_compound_page_dtor(page, - * NULL_COMPOUND_DTOR), so do not use page_hstate() directly. + * remove_hugetlb_folio() will call folio_set_compound_dtor + * (folio, NULL_COMPOUND_DTOR), so do not use page_hstate() + * directly. */ h = size_to_hstate(page_size(page)); @@ -1749,12 +1749,12 @@ void free_huge_page(struct page *page) h->resv_huge_pages++; if (folio_test_hugetlb_temporary(folio)) { - remove_hugetlb_page(h, page, false); + remove_hugetlb_folio(h, folio, false); spin_unlock_irqrestore(&hugetlb_lock, flags); update_and_free_page(h, page, true); } else if (h->surplus_huge_pages_node[nid]) { /* remove the page from active list */ - remove_hugetlb_page(h, page, true); + remove_hugetlb_folio(h, folio, true); spin_unlock_irqrestore(&hugetlb_lock, flags); update_and_free_page(h, page, true); } else { @@ -2092,6 +2092,7 @@ static struct page *remove_pool_huge_page(struct hstate *h, { int nr_nodes, node; struct page *page = NULL; + struct folio *folio; lockdep_assert_held(&hugetlb_lock); for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { @@ -2103,7 +2104,8 @@ static struct page *remove_pool_huge_page(struct hstate *h, !list_empty(&h->hugepage_freelists[node])) { page = list_entry(h->hugepage_freelists[node].next, struct page, lru); - remove_hugetlb_page(h, page, acct_surplus); + folio = page_folio(page); + remove_hugetlb_folio(h, folio, acct_surplus); break; } } @@ -2165,7 +2167,7 @@ retry: goto retry; } - remove_hugetlb_page(h, &folio->page, false); + remove_hugetlb_folio(h, folio, false); h->max_huge_pages--; spin_unlock_irq(&hugetlb_lock); @@ -2803,7 +2805,7 @@ retry: * and enqueue_huge_page() for new_page. The counters will remain * stable since this happens under the lock. */ - remove_hugetlb_page(h, old_page, false); + remove_hugetlb_folio(h, old_folio, false); /* * Ref count on new page is already zero as it was dropped @@ -3230,7 +3232,7 @@ static void try_to_free_low(struct hstate *h, unsigned long count, goto out; if (PageHighMem(page)) continue; - remove_hugetlb_page(h, page, false); + remove_hugetlb_folio(h, page_folio(page), false); list_add(&page->lru, &page_list); } } @@ -3441,7 +3443,7 @@ static int demote_free_huge_page(struct hstate *h, struct page *page) target_hstate = size_to_hstate(PAGE_SIZE << h->demote_order); - remove_hugetlb_page_for_demote(h, page, false); + remove_hugetlb_folio_for_demote(h, folio, false); spin_unlock_irq(&hugetlb_lock); rc = hugetlb_vmemmap_restore(h, page); -- cgit v1.2.3 From d6ef19e25df2aa50f932a78c368d7bb710eaaa1b Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Tue, 29 Nov 2022 14:50:34 -0800 Subject: mm/hugetlb: convert update_and_free_page() to folios Make more progress on converting the free_huge_page() destructor to operate on folios by converting update_and_free_page() to folios. Link: https://lkml.kernel.org/r/20221129225039.82257-6-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar \ Reviewed-by: Mike Kravetz Cc: David Hildenbrand Cc: John Hubbard Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Mina Almasry Cc: Muchun Song Cc: Rasmus Villemoes Cc: Tarun Sahu Cc: Wei Chen Signed-off-by: Andrew Morton --- mm/hugetlb.c | 30 ++++++++++++++++-------------- 1 file changed, 16 insertions(+), 14 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 9b1c9d05ba34..5f3622ce791f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1478,7 +1478,7 @@ static void __remove_hugetlb_folio(struct hstate *h, struct folio *folio, * apply. * * This handles the case where more than one ref is held when and - * after update_and_free_page is called. + * after update_and_free_hugetlb_folio is called. * * In the case of demote we do not ref count the page as it will soon * be turned into a page of smaller size. @@ -1609,7 +1609,7 @@ static void __update_and_free_page(struct hstate *h, struct page *page) } /* - * As update_and_free_page() can be called under any context, so we cannot + * As update_and_free_hugetlb_folio() can be called under any context, so we cannot * use GFP_KERNEL to allocate vmemmap pages. However, we can defer the * actual freeing in a workqueue to prevent from using GFP_ATOMIC to allocate * the vmemmap pages. @@ -1657,11 +1657,11 @@ static inline void flush_free_hpage_work(struct hstate *h) flush_work(&free_hpage_work); } -static void update_and_free_page(struct hstate *h, struct page *page, +static void update_and_free_hugetlb_folio(struct hstate *h, struct folio *folio, bool atomic) { - if (!HPageVmemmapOptimized(page) || !atomic) { - __update_and_free_page(h, page); + if (!folio_test_hugetlb_vmemmap_optimized(folio) || !atomic) { + __update_and_free_page(h, &folio->page); return; } @@ -1672,16 +1672,18 @@ static void update_and_free_page(struct hstate *h, struct page *page, * empty. Otherwise, schedule_work() had been called but the workfn * hasn't retrieved the list yet. */ - if (llist_add((struct llist_node *)&page->mapping, &hpage_freelist)) + if (llist_add((struct llist_node *)&folio->mapping, &hpage_freelist)) schedule_work(&free_hpage_work); } static void update_and_free_pages_bulk(struct hstate *h, struct list_head *list) { struct page *page, *t_page; + struct folio *folio; list_for_each_entry_safe(page, t_page, list, lru) { - update_and_free_page(h, page, false); + folio = page_folio(page); + update_and_free_hugetlb_folio(h, folio, false); cond_resched(); } } @@ -1751,12 +1753,12 @@ void free_huge_page(struct page *page) if (folio_test_hugetlb_temporary(folio)) { remove_hugetlb_folio(h, folio, false); spin_unlock_irqrestore(&hugetlb_lock, flags); - update_and_free_page(h, page, true); + update_and_free_hugetlb_folio(h, folio, true); } else if (h->surplus_huge_pages_node[nid]) { /* remove the page from active list */ remove_hugetlb_folio(h, folio, true); spin_unlock_irqrestore(&hugetlb_lock, flags); - update_and_free_page(h, page, true); + update_and_free_hugetlb_folio(h, folio, true); } else { arch_clear_hugepage_flags(page); enqueue_huge_page(h, page); @@ -2172,8 +2174,8 @@ retry: spin_unlock_irq(&hugetlb_lock); /* - * Normally update_and_free_page will allocate required vmemmmap - * before freeing the page. update_and_free_page will fail to + * Normally update_and_free_hugtlb_folio will allocate required vmemmmap + * before freeing the page. update_and_free_hugtlb_folio will fail to * free the page if it can not allocate required vmemmap. We * need to adjust max_huge_pages if the page is not freed. * Attempt to allocate vmemmmap here so that we can take @@ -2181,7 +2183,7 @@ retry: */ rc = hugetlb_vmemmap_restore(h, &folio->page); if (!rc) { - update_and_free_page(h, &folio->page, false); + update_and_free_hugetlb_folio(h, folio, false); } else { spin_lock_irq(&hugetlb_lock); add_hugetlb_page(h, &folio->page, false); @@ -2818,7 +2820,7 @@ retry: * Pages have been replaced, we can safely free the old one. */ spin_unlock_irq(&hugetlb_lock); - update_and_free_page(h, old_page, false); + update_and_free_hugetlb_folio(h, old_folio, false); } return ret; @@ -2827,7 +2829,7 @@ free_new: spin_unlock_irq(&hugetlb_lock); /* Page has a zero ref count, but needs a ref to be freed */ folio_ref_unfreeze(new_folio, 1); - update_and_free_page(h, new_page, false); + update_and_free_hugetlb_folio(h, new_folio, false); return ret; } -- cgit v1.2.3 From 2f6c57d696abcd2d27d07b8506d5e6bcc060e77a Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Tue, 29 Nov 2022 14:50:35 -0800 Subject: mm/hugetlb: convert add_hugetlb_page() to folios and add hugetlb_cma_folio() Convert add_hugetlb_page() to take in a folio, also convert hugetlb_cma_page() to take in a folio. Link: https://lkml.kernel.org/r/20221129225039.82257-7-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Cc: David Hildenbrand Cc: John Hubbard Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Mina Almasry Cc: Muchun Song Cc: Rasmus Villemoes Cc: Tarun Sahu Cc: Wei Chen Signed-off-by: Andrew Morton --- mm/hugetlb.c | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 5f3622ce791f..d80a83490b9a 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -54,13 +54,13 @@ struct hstate hstates[HUGE_MAX_HSTATE]; #ifdef CONFIG_CMA static struct cma *hugetlb_cma[MAX_NUMNODES]; static unsigned long hugetlb_cma_size_in_node[MAX_NUMNODES] __initdata; -static bool hugetlb_cma_page(struct page *page, unsigned int order) +static bool hugetlb_cma_folio(struct folio *folio, unsigned int order) { - return cma_pages_valid(hugetlb_cma[page_to_nid(page)], page, + return cma_pages_valid(hugetlb_cma[folio_nid(folio)], &folio->page, 1 << order); } #else -static bool hugetlb_cma_page(struct page *page, unsigned int order) +static bool hugetlb_cma_folio(struct folio *folio, unsigned int order) { return false; } @@ -1506,17 +1506,17 @@ static void remove_hugetlb_folio_for_demote(struct hstate *h, struct folio *foli __remove_hugetlb_folio(h, folio, adjust_surplus, true); } -static void add_hugetlb_page(struct hstate *h, struct page *page, +static void add_hugetlb_folio(struct hstate *h, struct folio *folio, bool adjust_surplus) { int zeroed; - int nid = page_to_nid(page); + int nid = folio_nid(folio); - VM_BUG_ON_PAGE(!HPageVmemmapOptimized(page), page); + VM_BUG_ON_FOLIO(!folio_test_hugetlb_vmemmap_optimized(folio), folio); lockdep_assert_held(&hugetlb_lock); - INIT_LIST_HEAD(&page->lru); + INIT_LIST_HEAD(&folio->lru); h->nr_huge_pages++; h->nr_huge_pages_node[nid]++; @@ -1525,21 +1525,21 @@ static void add_hugetlb_page(struct hstate *h, struct page *page, h->surplus_huge_pages_node[nid]++; } - set_compound_page_dtor(page, HUGETLB_PAGE_DTOR); - set_page_private(page, 0); + folio_set_compound_dtor(folio, HUGETLB_PAGE_DTOR); + folio_change_private(folio, NULL); /* - * We have to set HPageVmemmapOptimized again as above - * set_page_private(page, 0) cleared it. + * We have to set hugetlb_vmemmap_optimized again as above + * folio_change_private(folio, NULL) cleared it. */ - SetHPageVmemmapOptimized(page); + folio_set_hugetlb_vmemmap_optimized(folio); /* - * This page is about to be managed by the hugetlb allocator and + * This folio is about to be managed by the hugetlb allocator and * should have no users. Drop our reference, and check for others * just in case. */ - zeroed = put_page_testzero(page); - if (!zeroed) + zeroed = folio_put_testzero(folio); + if (unlikely(!zeroed)) /* * It is VERY unlikely soneone else has taken a ref on * the page. In this case, we simply return as the @@ -1548,8 +1548,8 @@ static void add_hugetlb_page(struct hstate *h, struct page *page, */ return; - arch_clear_hugepage_flags(page); - enqueue_huge_page(h, page); + arch_clear_hugepage_flags(&folio->page); + enqueue_huge_page(h, &folio->page); } static void __update_and_free_page(struct hstate *h, struct page *page) @@ -1575,7 +1575,7 @@ static void __update_and_free_page(struct hstate *h, struct page *page) * page and put the page back on the hugetlb free list and treat * as a surplus page. */ - add_hugetlb_page(h, page, true); + add_hugetlb_folio(h, page_folio(page), true); spin_unlock_irq(&hugetlb_lock); return; } @@ -1600,7 +1600,7 @@ static void __update_and_free_page(struct hstate *h, struct page *page) * need to be given back to CMA in free_gigantic_page. */ if (hstate_is_gigantic(h) || - hugetlb_cma_page(page, huge_page_order(h))) { + hugetlb_cma_folio(folio, huge_page_order(h))) { destroy_compound_gigantic_folio(folio, huge_page_order(h)); free_gigantic_page(page, huge_page_order(h)); } else { @@ -2186,7 +2186,7 @@ retry: update_and_free_hugetlb_folio(h, folio, false); } else { spin_lock_irq(&hugetlb_lock); - add_hugetlb_page(h, &folio->page, false); + add_hugetlb_folio(h, folio, false); h->max_huge_pages++; spin_unlock_irq(&hugetlb_lock); } @@ -3453,7 +3453,7 @@ static int demote_free_huge_page(struct hstate *h, struct page *page) /* Allocation of vmemmmap failed, we can not demote page */ spin_lock_irq(&hugetlb_lock); set_page_refcounted(page); - add_hugetlb_page(h, page, false); + add_hugetlb_folio(h, page_folio(page), false); return rc; } -- cgit v1.2.3 From 240d67a86ecb0fa18863821a0cb55783ad50ef30 Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Tue, 29 Nov 2022 14:50:36 -0800 Subject: mm/hugetlb: convert enqueue_huge_page() to folios Convert callers of enqueue_huge_page() to pass in a folio, function is renamed to enqueue_hugetlb_folio(). Link: https://lkml.kernel.org/r/20221129225039.82257-8-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Cc: David Hildenbrand Cc: John Hubbard Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Mina Almasry Cc: Muchun Song Cc: Rasmus Villemoes Cc: Tarun Sahu Cc: Wei Chen Signed-off-by: Andrew Morton --- mm/hugetlb.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index d80a83490b9a..6da673f1d830 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1127,17 +1127,17 @@ static bool vma_has_reserves(struct vm_area_struct *vma, long chg) return false; } -static void enqueue_huge_page(struct hstate *h, struct page *page) +static void enqueue_hugetlb_folio(struct hstate *h, struct folio *folio) { - int nid = page_to_nid(page); + int nid = folio_nid(folio); lockdep_assert_held(&hugetlb_lock); - VM_BUG_ON_PAGE(page_count(page), page); + VM_BUG_ON_FOLIO(folio_ref_count(folio), folio); - list_move(&page->lru, &h->hugepage_freelists[nid]); + list_move(&folio->lru, &h->hugepage_freelists[nid]); h->free_huge_pages++; h->free_huge_pages_node[nid]++; - SetHPageFreed(page); + folio_set_hugetlb_freed(folio); } static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid) @@ -1549,7 +1549,7 @@ static void add_hugetlb_folio(struct hstate *h, struct folio *folio, return; arch_clear_hugepage_flags(&folio->page); - enqueue_huge_page(h, &folio->page); + enqueue_hugetlb_folio(h, folio); } static void __update_and_free_page(struct hstate *h, struct page *page) @@ -1761,7 +1761,7 @@ void free_huge_page(struct page *page) update_and_free_hugetlb_folio(h, folio, true); } else { arch_clear_hugepage_flags(page); - enqueue_huge_page(h, page); + enqueue_hugetlb_folio(h, folio); spin_unlock_irqrestore(&hugetlb_lock, flags); } } @@ -2438,7 +2438,7 @@ retry: if ((--needed) < 0) break; /* Add the page to the hugetlb allocator */ - enqueue_huge_page(h, page); + enqueue_hugetlb_folio(h, page_folio(page)); } free: spin_unlock_irq(&hugetlb_lock); @@ -2804,8 +2804,8 @@ retry: * Ok, old_page is still a genuine free hugepage. Remove it from * the freelist and decrease the counters. These will be * incremented again when calling __prep_account_new_huge_page() - * and enqueue_huge_page() for new_page. The counters will remain - * stable since this happens under the lock. + * and enqueue_hugetlb_folio() for new_folio. The counters will + * remain stable since this happens under the lock. */ remove_hugetlb_folio(h, old_folio, false); @@ -2814,7 +2814,7 @@ retry: * earlier. It can be directly added to the pool free list. */ __prep_account_new_huge_page(h, nid); - enqueue_huge_page(h, new_page); + enqueue_hugetlb_folio(h, new_folio); /* * Pages have been replaced, we can safely free the old one. -- cgit v1.2.3 From 7f325a8d25631e68cd75afaeaf330187e45e0eb5 Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Tue, 29 Nov 2022 14:50:37 -0800 Subject: mm/hugetlb: convert free_gigantic_page() to folios Convert callers of free_gigantic_page() to use folios, function is then renamed to free_gigantic_folio(). Link: https://lkml.kernel.org/r/20221129225039.82257-9-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Cc: David Hildenbrand Cc: John Hubbard Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Mina Almasry Cc: Muchun Song Cc: Rasmus Villemoes Cc: Tarun Sahu Cc: Wei Chen Signed-off-by: Andrew Morton --- mm/hugetlb.c | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6da673f1d830..eb58b0f38222 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1361,18 +1361,20 @@ static void destroy_compound_gigantic_folio(struct folio *folio, __destroy_compound_gigantic_folio(folio, order, false); } -static void free_gigantic_page(struct page *page, unsigned int order) +static void free_gigantic_folio(struct folio *folio, unsigned int order) { /* * If the page isn't allocated using the cma allocator, * cma_release() returns false. */ #ifdef CONFIG_CMA - if (cma_release(hugetlb_cma[page_to_nid(page)], page, 1 << order)) + int nid = folio_nid(folio); + + if (cma_release(hugetlb_cma[nid], &folio->page, 1 << order)) return; #endif - free_contig_range(page_to_pfn(page), 1 << order); + free_contig_range(folio_pfn(folio), 1 << order); } #ifdef CONFIG_CONTIG_ALLOC @@ -1426,7 +1428,8 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, { return NULL; } -static inline void free_gigantic_page(struct page *page, unsigned int order) { } +static inline void free_gigantic_folio(struct folio *folio, + unsigned int order) { } static inline void destroy_compound_gigantic_folio(struct folio *folio, unsigned int order) { } #endif @@ -1565,7 +1568,7 @@ static void __update_and_free_page(struct hstate *h, struct page *page) * If we don't know which subpages are hwpoisoned, we can't free * the hugepage, so it's leaked intentionally. */ - if (HPageRawHwpUnreliable(page)) + if (folio_test_hugetlb_raw_hwp_unreliable(folio)) return; if (hugetlb_vmemmap_restore(h, page)) { @@ -1575,7 +1578,7 @@ static void __update_and_free_page(struct hstate *h, struct page *page) * page and put the page back on the hugetlb free list and treat * as a surplus page. */ - add_hugetlb_folio(h, page_folio(page), true); + add_hugetlb_folio(h, folio, true); spin_unlock_irq(&hugetlb_lock); return; } @@ -1588,7 +1591,7 @@ static void __update_and_free_page(struct hstate *h, struct page *page) hugetlb_clear_page_hwpoison(&folio->page); for (i = 0; i < pages_per_huge_page(h); i++) { - subpage = nth_page(page, i); + subpage = folio_page(folio, i); subpage->flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced | 1 << PG_dirty | 1 << PG_active | 1 << PG_private | @@ -1597,12 +1600,12 @@ static void __update_and_free_page(struct hstate *h, struct page *page) /* * Non-gigantic pages demoted from CMA allocated gigantic pages - * need to be given back to CMA in free_gigantic_page. + * need to be given back to CMA in free_gigantic_folio. */ if (hstate_is_gigantic(h) || hugetlb_cma_folio(folio, huge_page_order(h))) { destroy_compound_gigantic_folio(folio, huge_page_order(h)); - free_gigantic_page(page, huge_page_order(h)); + free_gigantic_folio(folio, huge_page_order(h)); } else { __free_pages(page, huge_page_order(h)); } @@ -2025,6 +2028,7 @@ static struct page *alloc_fresh_huge_page(struct hstate *h, nodemask_t *node_alloc_noretry) { struct page *page; + struct folio *folio; bool retry = false; retry: @@ -2035,14 +2039,14 @@ retry: nid, nmask, node_alloc_noretry); if (!page) return NULL; - + folio = page_folio(page); if (hstate_is_gigantic(h)) { if (!prep_compound_gigantic_page(page, huge_page_order(h))) { /* * Rare failure to convert pages to compound page. * Free pages and try again - ONCE! */ - free_gigantic_page(page, huge_page_order(h)); + free_gigantic_folio(folio, huge_page_order(h)); if (!retry) { retry = true; goto retry; @@ -3050,6 +3054,7 @@ static void __init gather_bootmem_prealloc(void) list_for_each_entry(m, &huge_boot_pages, list) { struct page *page = virt_to_page(m); + struct folio *folio = page_folio(page); struct hstate *h = m->hstate; VM_BUG_ON(!hstate_is_gigantic(h)); @@ -3060,7 +3065,7 @@ static void __init gather_bootmem_prealloc(void) free_huge_page(page); /* add to the hugepage allocator */ } else { /* VERY unlikely inflated ref count on a tail page */ - free_gigantic_page(page, huge_page_order(h)); + free_gigantic_folio(folio, huge_page_order(h)); } /* -- cgit v1.2.3 From d1c6095572d0cf00c0cd30378639ff9387b34edd Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Tue, 29 Nov 2022 14:50:38 -0800 Subject: mm/hugetlb: convert hugetlb prep functions to folios Convert prep_new_huge_page() and __prep_compound_gigantic_page() to folios. Link: https://lkml.kernel.org/r/20221129225039.82257-10-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Cc: David Hildenbrand Cc: John Hubbard Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Mina Almasry Cc: Muchun Song Cc: Rasmus Villemoes Cc: Tarun Sahu Cc: Wei Chen Signed-off-by: Andrew Morton --- mm/hugetlb.c | 63 +++++++++++++++++++++++++++++------------------------------- 1 file changed, 30 insertions(+), 33 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index eb58b0f38222..903ee75cccd6 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1789,29 +1789,27 @@ static void __prep_new_hugetlb_folio(struct hstate *h, struct folio *folio) set_hugetlb_cgroup_rsvd(folio, NULL); } -static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) +static void prep_new_hugetlb_folio(struct hstate *h, struct folio *folio, int nid) { - struct folio *folio = page_folio(page); - __prep_new_hugetlb_folio(h, folio); spin_lock_irq(&hugetlb_lock); __prep_account_new_huge_page(h, nid); spin_unlock_irq(&hugetlb_lock); } -static bool __prep_compound_gigantic_page(struct page *page, unsigned int order, - bool demote) +static bool __prep_compound_gigantic_folio(struct folio *folio, + unsigned int order, bool demote) { int i, j; int nr_pages = 1 << order; struct page *p; - /* we rely on prep_new_huge_page to set the destructor */ - set_compound_order(page, order); - __ClearPageReserved(page); - __SetPageHead(page); + /* we rely on prep_new_hugetlb_folio to set the destructor */ + folio_set_compound_order(folio, order); + __folio_clear_reserved(folio); + __folio_set_head(folio); for (i = 0; i < nr_pages; i++) { - p = nth_page(page, i); + p = folio_page(folio, i); /* * For gigantic hugepages allocated through bootmem at @@ -1853,43 +1851,41 @@ static bool __prep_compound_gigantic_page(struct page *page, unsigned int order, VM_BUG_ON_PAGE(page_count(p), p); } if (i != 0) - set_compound_head(p, page); + set_compound_head(p, &folio->page); } - atomic_set(compound_mapcount_ptr(page), -1); - atomic_set(subpages_mapcount_ptr(page), 0); - atomic_set(compound_pincount_ptr(page), 0); + atomic_set(folio_mapcount_ptr(folio), -1); + atomic_set(folio_subpages_mapcount_ptr(folio), 0); + atomic_set(folio_pincount_ptr(folio), 0); return true; out_error: /* undo page modifications made above */ for (j = 0; j < i; j++) { - p = nth_page(page, j); + p = folio_page(folio, j); if (j != 0) clear_compound_head(p); set_page_refcounted(p); } /* need to clear PG_reserved on remaining tail pages */ for (; j < nr_pages; j++) { - p = nth_page(page, j); + p = folio_page(folio, j); __ClearPageReserved(p); } - set_compound_order(page, 0); -#ifdef CONFIG_64BIT - page[1].compound_nr = 0; -#endif - __ClearPageHead(page); + folio_set_compound_order(folio, 0); + __folio_clear_head(folio); return false; } -static bool prep_compound_gigantic_page(struct page *page, unsigned int order) +static bool prep_compound_gigantic_folio(struct folio *folio, + unsigned int order) { - return __prep_compound_gigantic_page(page, order, false); + return __prep_compound_gigantic_folio(folio, order, false); } -static bool prep_compound_gigantic_page_for_demote(struct page *page, +static bool prep_compound_gigantic_folio_for_demote(struct folio *folio, unsigned int order) { - return __prep_compound_gigantic_page(page, order, true); + return __prep_compound_gigantic_folio(folio, order, true); } /* @@ -2041,7 +2037,7 @@ retry: return NULL; folio = page_folio(page); if (hstate_is_gigantic(h)) { - if (!prep_compound_gigantic_page(page, huge_page_order(h))) { + if (!prep_compound_gigantic_folio(folio, huge_page_order(h))) { /* * Rare failure to convert pages to compound page. * Free pages and try again - ONCE! @@ -2054,7 +2050,7 @@ retry: return NULL; } } - prep_new_huge_page(h, page, page_to_nid(page)); + prep_new_hugetlb_folio(h, folio, folio_nid(folio)); return page; } @@ -3058,10 +3054,10 @@ static void __init gather_bootmem_prealloc(void) struct hstate *h = m->hstate; VM_BUG_ON(!hstate_is_gigantic(h)); - WARN_ON(page_count(page) != 1); - if (prep_compound_gigantic_page(page, huge_page_order(h))) { - WARN_ON(PageReserved(page)); - prep_new_huge_page(h, page, page_to_nid(page)); + WARN_ON(folio_ref_count(folio) != 1); + if (prep_compound_gigantic_folio(folio, huge_page_order(h))) { + WARN_ON(folio_test_reserved(folio)); + prep_new_hugetlb_folio(h, folio, folio_nid(folio)); free_huge_page(page); /* add to the hugepage allocator */ } else { /* VERY unlikely inflated ref count on a tail page */ @@ -3480,13 +3476,14 @@ static int demote_free_huge_page(struct hstate *h, struct page *page) for (i = 0; i < pages_per_huge_page(h); i += pages_per_huge_page(target_hstate)) { subpage = nth_page(page, i); + folio = page_folio(subpage); if (hstate_is_gigantic(target_hstate)) - prep_compound_gigantic_page_for_demote(subpage, + prep_compound_gigantic_folio_for_demote(folio, target_hstate->order); else prep_compound_page(subpage, target_hstate->order); set_page_private(subpage, 0); - prep_new_huge_page(target_hstate, subpage, nid); + prep_new_hugetlb_folio(target_hstate, folio, nid); free_huge_page(subpage); } mutex_unlock(&target_hstate->resize_lock); -- cgit v1.2.3 From 19fc1a7e8b2b3b0e18fbea84ee26517e1b0f1a6e Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Tue, 29 Nov 2022 14:50:39 -0800 Subject: mm/hugetlb: change hugetlb allocation functions to return a folio Many hugetlb allocation helper functions have now been converting to folios, update their higher level callers to be compatible with folios. alloc_pool_huge_page is reorganized to avoid a smatch warning reporting the folio variable is uninitialized. [sidhartha.kumar@oracle.com: update alloc_and_dissolve_hugetlb_folio comments] Link: https://lkml.kernel.org/r/20221206233512.146535-1-sidhartha.kumar@oracle.com Link: https://lkml.kernel.org/r/20221129225039.82257-11-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Reported-by: Wei Chen Suggested-by: John Hubbard Suggested-by: Rasmus Villemoes Reviewed-by: Mike Kravetz Cc: David Hildenbrand Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Mina Almasry Cc: Muchun Song Cc: Tarun Sahu Signed-off-by: Andrew Morton --- mm/hugetlb.c | 134 ++++++++++++++++++++++++++++------------------------------- 1 file changed, 64 insertions(+), 70 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 903ee75cccd6..8c6fe2286814 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1378,23 +1378,23 @@ static void free_gigantic_folio(struct folio *folio, unsigned int order) } #ifdef CONFIG_CONTIG_ALLOC -static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, +static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { + struct page *page; unsigned long nr_pages = pages_per_huge_page(h); if (nid == NUMA_NO_NODE) nid = numa_mem_id(); #ifdef CONFIG_CMA { - struct page *page; int node; if (hugetlb_cma[nid]) { page = cma_alloc(hugetlb_cma[nid], nr_pages, huge_page_order(h), true); if (page) - return page; + return page_folio(page); } if (!(gfp_mask & __GFP_THISNODE)) { @@ -1405,17 +1405,18 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, page = cma_alloc(hugetlb_cma[node], nr_pages, huge_page_order(h), true); if (page) - return page; + return page_folio(page); } } } #endif - return alloc_contig_pages(nr_pages, gfp_mask, nid, nodemask); + page = alloc_contig_pages(nr_pages, gfp_mask, nid, nodemask); + return page ? page_folio(page) : NULL; } #else /* !CONFIG_CONTIG_ALLOC */ -static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, +static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { return NULL; @@ -1423,7 +1424,7 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, #endif /* CONFIG_CONTIG_ALLOC */ #else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE */ -static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, +static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { return NULL; @@ -1950,7 +1951,7 @@ pgoff_t hugetlb_basepage_index(struct page *page) return (index << compound_order(page_head)) + compound_idx; } -static struct page *alloc_buddy_huge_page(struct hstate *h, +static struct folio *alloc_buddy_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { @@ -1988,11 +1989,6 @@ retry: page = NULL; } - if (page) - __count_vm_event(HTLB_BUDDY_PGALLOC); - else - __count_vm_event(HTLB_BUDDY_PGALLOC_FAIL); - /* * If we did not specify __GFP_RETRY_MAYFAIL, but still got a page this * indicates an overall state change. Clear bit so that we resume @@ -2009,7 +2005,13 @@ retry: if (node_alloc_noretry && !page && alloc_try_hard) node_set(nid, *node_alloc_noretry); - return page; + if (!page) { + __count_vm_event(HTLB_BUDDY_PGALLOC_FAIL); + return NULL; + } + + __count_vm_event(HTLB_BUDDY_PGALLOC); + return page_folio(page); } /* @@ -2019,23 +2021,21 @@ retry: * Note that returned page is 'frozen': ref count of head page and all tail * pages is zero. */ -static struct page *alloc_fresh_huge_page(struct hstate *h, +static struct folio *alloc_fresh_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { - struct page *page; struct folio *folio; bool retry = false; retry: if (hstate_is_gigantic(h)) - page = alloc_gigantic_page(h, gfp_mask, nid, nmask); + folio = alloc_gigantic_folio(h, gfp_mask, nid, nmask); else - page = alloc_buddy_huge_page(h, gfp_mask, + folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, nmask, node_alloc_noretry); - if (!page) + if (!folio) return NULL; - folio = page_folio(page); if (hstate_is_gigantic(h)) { if (!prep_compound_gigantic_folio(folio, huge_page_order(h))) { /* @@ -2052,7 +2052,7 @@ retry: } prep_new_hugetlb_folio(h, folio, folio_nid(folio)); - return page; + return folio; } /* @@ -2062,23 +2062,20 @@ retry: static int alloc_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, nodemask_t *node_alloc_noretry) { - struct page *page; + struct folio *folio; int nr_nodes, node; gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) { - page = alloc_fresh_huge_page(h, gfp_mask, node, nodes_allowed, - node_alloc_noretry); - if (page) - break; + folio = alloc_fresh_hugetlb_folio(h, gfp_mask, node, + nodes_allowed, node_alloc_noretry); + if (folio) { + free_huge_page(&folio->page); /* free it into the hugepage allocator */ + return 1; + } } - if (!page) - return 0; - - free_huge_page(page); /* free it into the hugepage allocator */ - - return 1; + return 0; } /* @@ -2237,7 +2234,7 @@ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn) static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { - struct page *page = NULL; + struct folio *folio = NULL; if (hstate_is_gigantic(h)) return NULL; @@ -2247,8 +2244,8 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask, goto out_unlock; spin_unlock_irq(&hugetlb_lock); - page = alloc_fresh_huge_page(h, gfp_mask, nid, nmask, NULL); - if (!page) + folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, NULL); + if (!folio) return NULL; spin_lock_irq(&hugetlb_lock); @@ -2260,43 +2257,42 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask, * codeflow */ if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) { - SetHPageTemporary(page); + folio_set_hugetlb_temporary(folio); spin_unlock_irq(&hugetlb_lock); - free_huge_page(page); + free_huge_page(&folio->page); return NULL; } h->surplus_huge_pages++; - h->surplus_huge_pages_node[page_to_nid(page)]++; + h->surplus_huge_pages_node[folio_nid(folio)]++; out_unlock: spin_unlock_irq(&hugetlb_lock); - return page; + return &folio->page; } static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { - struct page *page; + struct folio *folio; if (hstate_is_gigantic(h)) return NULL; - page = alloc_fresh_huge_page(h, gfp_mask, nid, nmask, NULL); - if (!page) + folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, NULL); + if (!folio) return NULL; /* fresh huge pages are frozen */ - set_page_refcounted(page); - + folio_ref_unfreeze(folio, 1); /* * We do not account these pages as surplus because they are only * temporary and will be released properly on the last reference */ - SetHPageTemporary(page); + folio_set_hugetlb_temporary(folio); - return page; + return &folio->page; } /* @@ -2745,54 +2741,52 @@ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, } /* - * alloc_and_dissolve_huge_page - Allocate a new page and dissolve the old one + * alloc_and_dissolve_hugetlb_folio - Allocate a new folio and dissolve + * the old one * @h: struct hstate old page belongs to - * @old_page: Old page to dissolve + * @old_folio: Old folio to dissolve * @list: List to isolate the page in case we need to * Returns 0 on success, otherwise negated error. */ -static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page, - struct list_head *list) +static int alloc_and_dissolve_hugetlb_folio(struct hstate *h, + struct folio *old_folio, struct list_head *list) { gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; - struct folio *old_folio = page_folio(old_page); int nid = folio_nid(old_folio); - struct page *new_page; struct folio *new_folio; int ret = 0; /* - * Before dissolving the page, we need to allocate a new one for the - * pool to remain stable. Here, we allocate the page and 'prep' it + * Before dissolving the folio, we need to allocate a new one for the + * pool to remain stable. Here, we allocate the folio and 'prep' it * by doing everything but actually updating counters and adding to * the pool. This simplifies and let us do most of the processing * under the lock. */ - new_page = alloc_buddy_huge_page(h, gfp_mask, nid, NULL, NULL); - if (!new_page) + new_folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, NULL, NULL); + if (!new_folio) return -ENOMEM; - new_folio = page_folio(new_page); __prep_new_hugetlb_folio(h, new_folio); retry: spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(old_folio)) { /* - * Freed from under us. Drop new_page too. + * Freed from under us. Drop new_folio too. */ goto free_new; } else if (folio_ref_count(old_folio)) { /* - * Someone has grabbed the page, try to isolate it here. + * Someone has grabbed the folio, try to isolate it here. * Fail with -EBUSY if not possible. */ spin_unlock_irq(&hugetlb_lock); - ret = isolate_hugetlb(old_page, list); + ret = isolate_hugetlb(&old_folio->page, list); spin_lock_irq(&hugetlb_lock); goto free_new; } else if (!folio_test_hugetlb_freed(old_folio)) { /* - * Page's refcount is 0 but it has not been enqueued in the + * Folio's refcount is 0 but it has not been enqueued in the * freelist yet. Race window is small, so we can succeed here if * we retry. */ @@ -2801,7 +2795,7 @@ retry: goto retry; } else { /* - * Ok, old_page is still a genuine free hugepage. Remove it from + * Ok, old_folio is still a genuine free hugepage. Remove it from * the freelist and decrease the counters. These will be * incremented again when calling __prep_account_new_huge_page() * and enqueue_hugetlb_folio() for new_folio. The counters will @@ -2810,14 +2804,14 @@ retry: remove_hugetlb_folio(h, old_folio, false); /* - * Ref count on new page is already zero as it was dropped + * Ref count on new_folio is already zero as it was dropped * earlier. It can be directly added to the pool free list. */ __prep_account_new_huge_page(h, nid); enqueue_hugetlb_folio(h, new_folio); /* - * Pages have been replaced, we can safely free the old one. + * Folio has been replaced, we can safely free the old one. */ spin_unlock_irq(&hugetlb_lock); update_and_free_hugetlb_folio(h, old_folio, false); @@ -2827,7 +2821,7 @@ retry: free_new: spin_unlock_irq(&hugetlb_lock); - /* Page has a zero ref count, but needs a ref to be freed */ + /* Folio has a zero ref count, but needs a ref to be freed */ folio_ref_unfreeze(new_folio, 1); update_and_free_hugetlb_folio(h, new_folio, false); @@ -2865,7 +2859,7 @@ int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) if (folio_ref_count(folio) && !isolate_hugetlb(&folio->page, list)) ret = 0; else if (!folio_ref_count(folio)) - ret = alloc_and_dissolve_huge_page(h, &folio->page, list); + ret = alloc_and_dissolve_hugetlb_folio(h, folio, list); return ret; } @@ -3083,14 +3077,14 @@ static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid) if (!alloc_bootmem_huge_page(h, nid)) break; } else { - struct page *page; + struct folio *folio; gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; - page = alloc_fresh_huge_page(h, gfp_mask, nid, + folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, &node_states[N_MEMORY], NULL); - if (!page) + if (!folio) break; - free_huge_page(page); /* free it into the hugepage allocator */ + free_huge_page(&folio->page); /* free it into the hugepage allocator */ } cond_resched(); } -- cgit v1.2.3 From c45bc55a99957b20e4e0333bcd42e12d1833a7f5 Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Mon, 12 Dec 2022 14:55:29 -0800 Subject: mm/hugetlb: set head flag before setting compound_order in __prep_compound_gigantic_folio folio_set_compound_order() checks if the passed in folio is a large folio. A large folio is indicated by the PG_head flag. Call __folio_set_head() before setting the order. Link: https://lkml.kernel.org/r/20221212225529.22493-1-sidhartha.kumar@oracle.com Fixes: d1c6095572d0 ("mm/hugetlb: convert hugetlb prep functions to folios") Signed-off-by: Sidhartha Kumar Reported-by: David Hildenbrand Signed-off-by: Andrew Morton --- mm/hugetlb.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 8c6fe2286814..7cdbcc22587b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1805,10 +1805,10 @@ static bool __prep_compound_gigantic_folio(struct folio *folio, int nr_pages = 1 << order; struct page *p; - /* we rely on prep_new_hugetlb_folio to set the destructor */ - folio_set_compound_order(folio, order); __folio_clear_reserved(folio); __folio_set_head(folio); + /* we rely on prep_new_hugetlb_folio to set the destructor */ + folio_set_compound_order(folio, order); for (i = 0; i < nr_pages; i++) { p = folio_page(folio, i); -- cgit v1.2.3