From ebcbc6ea7d8a604ad8504dae70a6ac1b1e64a0b7 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 14 Feb 2022 18:20:24 -0800 Subject: mm/munlock: delete page_mlock() and all its works We have recommended some applications to mlock their userspace, but that turns out to be counter-productive: when many processes mlock the same file, contention on rmap's i_mmap_rwsem can become intolerable at exit: it is needed for write, to remove any vma mapping that file from rmap's tree; but hogged for read by those with mlocks calling page_mlock() (formerly known as try_to_munlock()) on *each* page mapped from the file (the purpose being to find out whether another process has the page mlocked, so therefore it should not be unmlocked yet). Several optimizations have been made in the past: one is to skip page_mlock() when mapcount tells that nothing else has this page mapped; but that doesn't help at all when others do have it mapped. This time around, I initially intended to add a preliminary search of the rmap tree for overlapping VM_LOCKED ranges; but that gets messy with locking order, when in doubt whether a page is actually present; and risks adding even more contention on the i_mmap_rwsem. A solution would be much easier, if only there were space in struct page for an mlock_count... but actually, most of the time, there is space for it - an mlocked page spends most of its life on an unevictable LRU, but since 3.18 removed the scan_unevictable_pages sysctl, that "LRU" has been redundant. Let's try to reuse its page->lru. But leave that until a later patch: in this patch, clear the ground by removing page_mlock(), and all the infrastructure that has gathered around it - which mostly hinders understanding, and will make reviewing new additions harder. Don't mind those old comments about THPs, they date from before 4.5's refcounting rework: splitting is not a risk here. Just keep a minimal version of munlock_vma_page(), as reminder of what it should attend to (in particular, the odd way PGSTRANDED is counted out of PGMUNLOCKED), and likewise a stub for munlock_vma_pages_range(). Move unchanged __mlock_posix_error_return() out of the way, down to above its caller: this series then makes no further change after mlock_fixup(). After this and each following commit, the kernel builds, boots and runs; but with deficiencies which may show up in testing of mlock and munlock. The system calls succeed or fail as before, and mlock remains effective in preventing page reclaim; but meminfo's Unevictable and Mlocked amounts may be shown too low after mlock, grow, then stay too high after munlock: with previously mlocked pages remaining unevictable for too long, until finally unmapped and freed and counts corrected. Normal service will be resumed in "mm/munlock: mlock_pte_range() when mlocking or munlocking". Signed-off-by: Hugh Dickins Acked-by: Vlastimil Babka Signed-off-by: Matthew Wilcox (Oracle) --- mm/rmap.c | 80 --------------------------------------------------------------- 1 file changed, 80 deletions(-) (limited to 'mm/rmap.c') diff --git a/mm/rmap.c b/mm/rmap.c index 6a1e8c7f6213..7ce7f1946cff 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1996,76 +1996,6 @@ void try_to_migrate(struct page *page, enum ttu_flags flags) rmap_walk(page, &rwc); } -/* - * Walks the vma's mapping a page and mlocks the page if any locked vma's are - * found. Once one is found the page is locked and the scan can be terminated. - */ -static bool page_mlock_one(struct page *page, struct vm_area_struct *vma, - unsigned long address, void *unused) -{ - struct page_vma_mapped_walk pvmw = { - .page = page, - .vma = vma, - .address = address, - }; - - /* An un-locked vma doesn't have any pages to lock, continue the scan */ - if (!(vma->vm_flags & VM_LOCKED)) - return true; - - while (page_vma_mapped_walk(&pvmw)) { - /* - * Need to recheck under the ptl to serialise with - * __munlock_pagevec_fill() after VM_LOCKED is cleared in - * munlock_vma_pages_range(). - */ - if (vma->vm_flags & VM_LOCKED) { - /* - * PTE-mapped THP are never marked as mlocked; but - * this function is never called on a DoubleMap THP, - * nor on an Anon THP (which may still be PTE-mapped - * after DoubleMap was cleared). - */ - mlock_vma_page(page); - /* - * No need to scan further once the page is marked - * as mlocked. - */ - page_vma_mapped_walk_done(&pvmw); - return false; - } - } - - return true; -} - -/** - * page_mlock - try to mlock a page - * @page: the page to be mlocked - * - * Called from munlock code. Checks all of the VMAs mapping the page and mlocks - * the page if any are found. The page will be returned with PG_mlocked cleared - * if it is not mapped by any locked vmas. - */ -void page_mlock(struct page *page) -{ - struct rmap_walk_control rwc = { - .rmap_one = page_mlock_one, - .done = page_not_mapped, - .anon_lock = page_lock_anon_vma_read, - - }; - - VM_BUG_ON_PAGE(!PageLocked(page) || PageLRU(page), page); - VM_BUG_ON_PAGE(PageCompound(page) && PageDoubleMap(page), page); - - /* Anon THP are only marked as mlocked when singly mapped */ - if (PageTransCompound(page) && PageAnon(page)) - return; - - rmap_walk(page, &rwc); -} - #ifdef CONFIG_DEVICE_PRIVATE struct make_exclusive_args { struct mm_struct *mm; @@ -2291,11 +2221,6 @@ static struct anon_vma *rmap_walk_anon_lock(struct page *page, * * Find all the mappings of a page using the mapping pointer and the vma chains * contained in the anon_vma struct it points to. - * - * When called from page_mlock(), the mmap_lock of the mm containing the vma - * where the page was found will be held for write. So, we won't recheck - * vm_flags for that VMA. That should be OK, because that vma shouldn't be - * LOCKED. */ static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, bool locked) @@ -2344,11 +2269,6 @@ static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, * * Find all the mappings of a page using the mapping pointer and the vma chains * contained in the address_space struct it points to. - * - * When called from page_mlock(), the mmap_lock of the mm containing the vma - * where the page was found will be held for write. So, we won't recheck - * vm_flags for that VMA. That should be OK, because that vma shouldn't be - * LOCKED. */ static void rmap_walk_file(struct page *page, struct rmap_walk_control *rwc, bool locked) -- cgit v1.2.3 From cea86fe246b694a191804b47378eb9d77aefabec Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 14 Feb 2022 18:26:39 -0800 Subject: mm/munlock: rmap call mlock_vma_page() munlock_vma_page() Add vma argument to mlock_vma_page() and munlock_vma_page(), make them inline functions which check (vma->vm_flags & VM_LOCKED) before calling mlock_page() and munlock_page() in mm/mlock.c. Add bool compound to mlock_vma_page() and munlock_vma_page(): this is because we have understandable difficulty in accounting pte maps of THPs, and if passed a PageHead page, mlock_page() and munlock_page() cannot tell whether it's a pmd map to be counted or a pte map to be ignored. Add vma arg to page_add_file_rmap() and page_remove_rmap(), like the others, and use that to call mlock_vma_page() at the end of the page adds, and munlock_vma_page() at the end of page_remove_rmap() (end or beginning? unimportant, but end was easier for assertions in testing). No page lock is required (although almost all adds happen to hold it): delete the "Serialize with page migration" BUG_ON(!PageLocked(page))s. Certainly page lock did serialize with page migration, but I'm having difficulty explaining why that was ever important. Mlock accounting on THPs has been hard to define, differed between anon and file, involved PageDoubleMap in some places and not others, required clear_page_mlock() at some points. Keep it simple now: just count the pmds and ignore the ptes, there is no reason for ptes to undo pmd mlocks. page_add_new_anon_rmap() callers unchanged: they have long been calling lru_cache_add_inactive_or_unevictable(), which does its own VM_LOCKED handling (it also checks for not VM_SPECIAL: I think that's overcautious, and inconsistent with other checks, that mmap_region() already prevents VM_LOCKED on VM_SPECIAL; but haven't quite convinced myself to change it). Signed-off-by: Hugh Dickins Acked-by: Vlastimil Babka Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/rmap.h | 17 ++++++++------- kernel/events/uprobes.c | 7 ++----- mm/huge_memory.c | 17 +++++++-------- mm/hugetlb.c | 4 ++-- mm/internal.h | 36 ++++++++++++++++++++++++++----- mm/khugepaged.c | 4 ++-- mm/ksm.c | 12 +---------- mm/memory.c | 45 +++++++++++++-------------------------- mm/migrate.c | 9 ++------ mm/mlock.c | 21 +++++++------------ mm/rmap.c | 56 +++++++++++++++++++++++-------------------------- mm/userfaultfd.c | 14 +++++++------ 12 files changed, 113 insertions(+), 129 deletions(-) (limited to 'mm/rmap.c') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index dc48aa8c2c94..ac29b076082b 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -167,18 +167,19 @@ struct anon_vma *page_get_anon_vma(struct page *page); */ void page_move_anon_rmap(struct page *, struct vm_area_struct *); void page_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long, bool); + unsigned long address, bool compound); void do_page_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long, int); + unsigned long address, int flags); void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long, bool); -void page_add_file_rmap(struct page *, bool); -void page_remove_rmap(struct page *, bool); - + unsigned long address, bool compound); +void page_add_file_rmap(struct page *, struct vm_area_struct *, + bool compound); +void page_remove_rmap(struct page *, struct vm_area_struct *, + bool compound); void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long); + unsigned long address); void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long); + unsigned long address); static inline void page_dup_rmap(struct page *page, bool compound) { diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 6357c3580d07..eed2f7437d96 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -173,7 +173,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, return err; } - /* For try_to_free_swap() and munlock_vma_page() below */ + /* For try_to_free_swap() below */ lock_page(old_page); mmu_notifier_invalidate_range_start(&range); @@ -201,13 +201,10 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, set_pte_at_notify(mm, addr, pvmw.pte, mk_pte(new_page, vma->vm_page_prot)); - page_remove_rmap(old_page, false); + page_remove_rmap(old_page, vma, false); if (!page_mapped(old_page)) try_to_free_swap(old_page); page_vma_mapped_walk_done(&pvmw); - - if ((vma->vm_flags & VM_LOCKED) && !PageCompound(old_page)) - munlock_vma_page(old_page); put_page(old_page); err = 0; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 9a34b85ebcf8..d6477f48a27e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1577,7 +1577,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, if (pmd_present(orig_pmd)) { page = pmd_page(orig_pmd); - page_remove_rmap(page, true); + page_remove_rmap(page, vma, true); VM_BUG_ON_PAGE(page_mapcount(page) < 0, page); VM_BUG_ON_PAGE(!PageHead(page), page); } else if (thp_migration_supported()) { @@ -1962,7 +1962,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, set_page_dirty(page); if (!PageReferenced(page) && pmd_young(old_pmd)) SetPageReferenced(page); - page_remove_rmap(page, true); + page_remove_rmap(page, vma, true); put_page(page); } add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR); @@ -2096,6 +2096,9 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, } } unlock_page_memcg(page); + + /* Above is effectively page_remove_rmap(page, vma, true) */ + munlock_vma_page(page, vma, true); } smp_wmb(); /* make pte visible before pmd */ @@ -2103,7 +2106,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, if (freeze) { for (i = 0; i < HPAGE_PMD_NR; i++) { - page_remove_rmap(page + i, false); + page_remove_rmap(page + i, vma, false); put_page(page + i); } } @@ -2163,8 +2166,6 @@ repeat: do_unlock_page = true; } } - if (PageMlocked(page)) - clear_page_mlock(page); } else if (!(pmd_devmap(*pmd) || is_pmd_migration_entry(*pmd))) goto out; __split_huge_pmd_locked(vma, pmd, range.start, freeze); @@ -3138,7 +3139,7 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, if (pmd_soft_dirty(pmdval)) pmdswp = pmd_swp_mksoft_dirty(pmdswp); set_pmd_at(mm, address, pvmw->pmd, pmdswp); - page_remove_rmap(page, true); + page_remove_rmap(page, vma, true); put_page(page); } @@ -3168,10 +3169,8 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) if (PageAnon(new)) page_add_anon_rmap(new, vma, mmun_start, true); else - page_add_file_rmap(new, true); + page_add_file_rmap(new, vma, true); set_pmd_at(mm, mmun_start, pvmw->pmd, pmde); - if ((vma->vm_flags & VM_LOCKED) && !PageDoubleMap(new)) - mlock_vma_page(new); update_mmu_cache_pmd(vma, address, pvmw->pmd); } #endif diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 61895cc01d09..43fb3155298e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5014,7 +5014,7 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct set_page_dirty(page); hugetlb_count_sub(pages_per_huge_page(h), mm); - page_remove_rmap(page, true); + page_remove_rmap(page, vma, true); spin_unlock(ptl); tlb_remove_page_size(tlb, page, huge_page_size(h)); @@ -5259,7 +5259,7 @@ retry_avoidcopy: /* Break COW */ huge_ptep_clear_flush(vma, haddr, ptep); mmu_notifier_invalidate_range(mm, range.start, range.end); - page_remove_rmap(old_page, true); + page_remove_rmap(old_page, vma, true); hugepage_add_new_anon_rmap(new_page, vma, haddr); set_huge_pte_at(mm, haddr, ptep, make_huge_pte(vma, new_page, 1)); diff --git a/mm/internal.h b/mm/internal.h index f235aa92e564..3d7dfc8bc471 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -395,12 +395,35 @@ extern long faultin_vma_page_range(struct vm_area_struct *vma, bool write, int *locked); extern int mlock_future_check(struct mm_struct *mm, unsigned long flags, unsigned long len); - /* - * must be called with vma's mmap_lock held for read or write, and page locked. + * mlock_vma_page() and munlock_vma_page(): + * should be called with vma's mmap_lock held for read or write, + * under page table lock for the pte/pmd being added or removed. + * + * mlock is usually called at the end of page_add_*_rmap(), + * munlock at the end of page_remove_rmap(); but new anon + * pages are managed in lru_cache_add_inactive_or_unevictable(). + * + * @compound is used to include pmd mappings of THPs, but filter out + * pte mappings of THPs, which cannot be consistently counted: a pte + * mapping of the THP head cannot be distinguished by the page alone. */ -extern void mlock_vma_page(struct page *page); -extern void munlock_vma_page(struct page *page); +void mlock_page(struct page *page); +static inline void mlock_vma_page(struct page *page, + struct vm_area_struct *vma, bool compound) +{ + if (unlikely(vma->vm_flags & VM_LOCKED) && + (compound || !PageTransCompound(page))) + mlock_page(page); +} +void munlock_page(struct page *page); +static inline void munlock_vma_page(struct page *page, + struct vm_area_struct *vma, bool compound) +{ + if (unlikely(vma->vm_flags & VM_LOCKED) && + (compound || !PageTransCompound(page))) + munlock_page(page); +} /* * Clear the page's PageMlocked(). This can be useful in a situation where @@ -487,7 +510,10 @@ static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, #else /* !CONFIG_MMU */ static inline void unmap_mapping_folio(struct folio *folio) { } static inline void clear_page_mlock(struct page *page) { } -static inline void mlock_vma_page(struct page *page) { } +static inline void mlock_vma_page(struct page *page, + struct vm_area_struct *vma, bool compound) { } +static inline void munlock_vma_page(struct page *page, + struct vm_area_struct *vma, bool compound) { } static inline void vunmap_range_noflush(unsigned long start, unsigned long end) { } diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 131492fd1148..52add1825525 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -774,7 +774,7 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page, */ spin_lock(ptl); ptep_clear(vma->vm_mm, address, _pte); - page_remove_rmap(src_page, false); + page_remove_rmap(src_page, vma, false); spin_unlock(ptl); free_page_and_swap_cache(src_page); } @@ -1513,7 +1513,7 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) if (pte_none(*pte)) continue; page = vm_normal_page(vma, addr, *pte); - page_remove_rmap(page, false); + page_remove_rmap(page, vma, false); } pte_unmap_unlock(start_pte, ptl); diff --git a/mm/ksm.c b/mm/ksm.c index c20bd4d9a0d9..c5a4403b5dc9 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -1177,7 +1177,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, ptep_clear_flush(vma, addr, ptep); set_pte_at_notify(mm, addr, ptep, newpte); - page_remove_rmap(page, false); + page_remove_rmap(page, vma, false); if (!page_mapped(page)) try_to_free_swap(page); put_page(page); @@ -1252,16 +1252,6 @@ static int try_to_merge_one_page(struct vm_area_struct *vma, err = replace_page(vma, page, kpage, orig_pte); } - if ((vma->vm_flags & VM_LOCKED) && kpage && !err) { - munlock_vma_page(page); - if (!PageMlocked(kpage)) { - unlock_page(page); - lock_page(kpage); - mlock_vma_page(kpage); - page = kpage; /* for final unlock */ - } - } - out_unlock: unlock_page(page); out: diff --git a/mm/memory.c b/mm/memory.c index c125c4969913..53bd9e5f2e33 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -735,9 +735,6 @@ static void restore_exclusive_pte(struct vm_area_struct *vma, set_pte_at(vma->vm_mm, address, ptep, pte); - if (vma->vm_flags & VM_LOCKED) - mlock_vma_page(page); - /* * No need to invalidate - it was non-present before. However * secondary CPUs may have mappings that need invalidating. @@ -1377,7 +1374,7 @@ again: mark_page_accessed(page); } rss[mm_counter(page)]--; - page_remove_rmap(page, false); + page_remove_rmap(page, vma, false); if (unlikely(page_mapcount(page) < 0)) print_bad_pte(vma, addr, ptent, page); if (unlikely(__tlb_remove_page(tlb, page))) { @@ -1397,10 +1394,8 @@ again: continue; pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); rss[mm_counter(page)]--; - if (is_device_private_entry(entry)) - page_remove_rmap(page, false); - + page_remove_rmap(page, vma, false); put_page(page); continue; } @@ -1753,16 +1748,16 @@ static int validate_page_before_insert(struct page *page) return 0; } -static int insert_page_into_pte_locked(struct mm_struct *mm, pte_t *pte, +static int insert_page_into_pte_locked(struct vm_area_struct *vma, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot) { if (!pte_none(*pte)) return -EBUSY; /* Ok, finally just insert the thing.. */ get_page(page); - inc_mm_counter_fast(mm, mm_counter_file(page)); - page_add_file_rmap(page, false); - set_pte_at(mm, addr, pte, mk_pte(page, prot)); + inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); + page_add_file_rmap(page, vma, false); + set_pte_at(vma->vm_mm, addr, pte, mk_pte(page, prot)); return 0; } @@ -1776,7 +1771,6 @@ static int insert_page_into_pte_locked(struct mm_struct *mm, pte_t *pte, static int insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot) { - struct mm_struct *mm = vma->vm_mm; int retval; pte_t *pte; spinlock_t *ptl; @@ -1785,17 +1779,17 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr, if (retval) goto out; retval = -ENOMEM; - pte = get_locked_pte(mm, addr, &ptl); + pte = get_locked_pte(vma->vm_mm, addr, &ptl); if (!pte) goto out; - retval = insert_page_into_pte_locked(mm, pte, addr, page, prot); + retval = insert_page_into_pte_locked(vma, pte, addr, page, prot); pte_unmap_unlock(pte, ptl); out: return retval; } #ifdef pte_index -static int insert_page_in_batch_locked(struct mm_struct *mm, pte_t *pte, +static int insert_page_in_batch_locked(struct vm_area_struct *vma, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot) { int err; @@ -1805,7 +1799,7 @@ static int insert_page_in_batch_locked(struct mm_struct *mm, pte_t *pte, err = validate_page_before_insert(page); if (err) return err; - return insert_page_into_pte_locked(mm, pte, addr, page, prot); + return insert_page_into_pte_locked(vma, pte, addr, page, prot); } /* insert_pages() amortizes the cost of spinlock operations @@ -1842,7 +1836,7 @@ more: start_pte = pte_offset_map_lock(mm, pmd, addr, &pte_lock); for (pte = start_pte; pte_idx < batch_size; ++pte, ++pte_idx) { - int err = insert_page_in_batch_locked(mm, pte, + int err = insert_page_in_batch_locked(vma, pte, addr, pages[curr_page_idx], prot); if (unlikely(err)) { pte_unmap_unlock(start_pte, pte_lock); @@ -3098,7 +3092,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) * mapcount is visible. So transitively, TLBs to * old page will be flushed before it can be reused. */ - page_remove_rmap(old_page, false); + page_remove_rmap(old_page, vma, false); } /* Free the old page.. */ @@ -3118,16 +3112,6 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) */ mmu_notifier_invalidate_range_only_end(&range); if (old_page) { - /* - * Don't let another task, with possibly unlocked vma, - * keep the mlocked page. - */ - if (page_copied && (vma->vm_flags & VM_LOCKED)) { - lock_page(old_page); /* LRU manipulation */ - if (PageMlocked(old_page)) - munlock_vma_page(old_page); - unlock_page(old_page); - } if (page_copied) free_swap_cache(old_page); put_page(old_page); @@ -3947,7 +3931,8 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); add_mm_counter(vma->vm_mm, mm_counter_file(page), HPAGE_PMD_NR); - page_add_file_rmap(page, true); + page_add_file_rmap(page, vma, true); + /* * deposit and withdraw with pmd lock held */ @@ -3996,7 +3981,7 @@ void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr) lru_cache_add_inactive_or_unevictable(page, vma); } else { inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); - page_add_file_rmap(page, false); + page_add_file_rmap(page, vma, false); } set_pte_at(vma->vm_mm, addr, vmf->pte, entry); } diff --git a/mm/migrate.c b/mm/migrate.c index c7da064b4781..7c4223ce2500 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -248,14 +248,9 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, if (PageAnon(new)) page_add_anon_rmap(new, vma, pvmw.address, false); else - page_add_file_rmap(new, false); + page_add_file_rmap(new, vma, false); set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); } - if (vma->vm_flags & VM_LOCKED && !PageTransCompound(new)) - mlock_vma_page(new); - - if (PageTransHuge(page) && PageMlocked(page)) - clear_page_mlock(page); /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, pvmw.address, pvmw.pte); @@ -2331,7 +2326,7 @@ again: * drop page refcount. Page won't be freed, as we took * a reference just above. */ - page_remove_rmap(page, false); + page_remove_rmap(page, vma, false); put_page(page); if (pte_present(pte)) diff --git a/mm/mlock.c b/mm/mlock.c index 5d7ced8303be..92f28258b4ae 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -78,17 +78,13 @@ void clear_page_mlock(struct page *page) } } -/* - * Mark page as mlocked if not already. - * If page on LRU, isolate and putback to move to unevictable list. +/** + * mlock_page - mlock a page + * @page: page to be mlocked, either a normal page or a THP head. */ -void mlock_vma_page(struct page *page) +void mlock_page(struct page *page) { - /* Serialize with page migration */ - BUG_ON(!PageLocked(page)); - VM_BUG_ON_PAGE(PageTail(page), page); - VM_BUG_ON_PAGE(PageCompound(page) && PageDoubleMap(page), page); if (!TestSetPageMlocked(page)) { int nr_pages = thp_nr_pages(page); @@ -101,14 +97,11 @@ void mlock_vma_page(struct page *page) } /** - * munlock_vma_page - munlock a vma page - * @page: page to be unlocked, either a normal page or THP page head + * munlock_page - munlock a page + * @page: page to be munlocked, either a normal page or a THP head. */ -void munlock_vma_page(struct page *page) +void munlock_page(struct page *page) { - /* Serialize with page migration */ - BUG_ON(!PageLocked(page)); - VM_BUG_ON_PAGE(PageTail(page), page); if (TestClearPageMlocked(page)) { diff --git a/mm/rmap.c b/mm/rmap.c index 7ce7f1946cff..6cc8bf129f18 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1181,17 +1181,17 @@ void do_page_add_anon_rmap(struct page *page, __mod_lruvec_page_state(page, NR_ANON_MAPPED, nr); } - if (unlikely(PageKsm(page))) { + if (unlikely(PageKsm(page))) unlock_page_memcg(page); - return; - } /* address might be in next vma when migration races vma_adjust */ - if (first) + else if (first) __page_set_anon_rmap(page, vma, address, flags & RMAP_EXCLUSIVE); else __page_check_anon_rmap(page, vma, address); + + mlock_vma_page(page, vma, compound); } /** @@ -1232,12 +1232,14 @@ void page_add_new_anon_rmap(struct page *page, /** * page_add_file_rmap - add pte mapping to a file page - * @page: the page to add the mapping to - * @compound: charge the page as compound or small page + * @page: the page to add the mapping to + * @vma: the vm area in which the mapping is added + * @compound: charge the page as compound or small page * * The caller needs to hold the pte lock. */ -void page_add_file_rmap(struct page *page, bool compound) +void page_add_file_rmap(struct page *page, + struct vm_area_struct *vma, bool compound) { int i, nr = 1; @@ -1260,13 +1262,8 @@ void page_add_file_rmap(struct page *page, bool compound) nr_pages); } else { if (PageTransCompound(page) && page_mapping(page)) { - struct page *head = compound_head(page); - VM_WARN_ON_ONCE(!PageLocked(page)); - - SetPageDoubleMap(head); - if (PageMlocked(page)) - clear_page_mlock(head); + SetPageDoubleMap(compound_head(page)); } if (!atomic_inc_and_test(&page->_mapcount)) goto out; @@ -1274,6 +1271,8 @@ void page_add_file_rmap(struct page *page, bool compound) __mod_lruvec_page_state(page, NR_FILE_MAPPED, nr); out: unlock_page_memcg(page); + + mlock_vma_page(page, vma, compound); } static void page_remove_file_rmap(struct page *page, bool compound) @@ -1368,11 +1367,13 @@ static void page_remove_anon_compound_rmap(struct page *page) /** * page_remove_rmap - take down pte mapping from a page * @page: page to remove mapping from + * @vma: the vm area from which the mapping is removed * @compound: uncharge the page as compound or small page * * The caller needs to hold the pte lock. */ -void page_remove_rmap(struct page *page, bool compound) +void page_remove_rmap(struct page *page, + struct vm_area_struct *vma, bool compound) { lock_page_memcg(page); @@ -1414,6 +1415,8 @@ void page_remove_rmap(struct page *page, bool compound) */ out: unlock_page_memcg(page); + + munlock_vma_page(page, vma, compound); } /* @@ -1469,28 +1472,21 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { + /* Unexpected PMD-mapped THP? */ + VM_BUG_ON_PAGE(!pvmw.pte, page); + /* - * If the page is mlock()d, we cannot swap it out. + * If the page is in an mlock()d vma, we must not swap it out. */ if (!(flags & TTU_IGNORE_MLOCK) && (vma->vm_flags & VM_LOCKED)) { - /* - * PTE-mapped THP are never marked as mlocked: so do - * not set it on a DoubleMap THP, nor on an Anon THP - * (which may still be PTE-mapped after DoubleMap was - * cleared). But stop unmapping even in those cases. - */ - if (!PageTransCompound(page) || (PageHead(page) && - !PageDoubleMap(page) && !PageAnon(page))) - mlock_vma_page(page); + /* Restore the mlock which got missed */ + mlock_vma_page(page, vma, false); page_vma_mapped_walk_done(&pvmw); ret = false; break; } - /* Unexpected PMD-mapped THP? */ - VM_BUG_ON_PAGE(!pvmw.pte, page); - subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); address = pvmw.address; @@ -1668,7 +1664,7 @@ discard: * * See Documentation/vm/mmu_notifier.rst */ - page_remove_rmap(subpage, PageHuge(page)); + page_remove_rmap(subpage, vma, PageHuge(page)); put_page(page); } @@ -1942,7 +1938,7 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, * * See Documentation/vm/mmu_notifier.rst */ - page_remove_rmap(subpage, PageHuge(page)); + page_remove_rmap(subpage, vma, PageHuge(page)); put_page(page); } @@ -2078,7 +2074,7 @@ static bool page_make_device_exclusive_one(struct page *page, * There is a reference on the page for the swap entry which has * been removed, so shouldn't take another. */ - page_remove_rmap(subpage, false); + page_remove_rmap(subpage, vma, false); } mmu_notifier_invalidate_range_end(&range); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 0780c2a57ff1..15d3e97a6e04 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -95,10 +95,15 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, if (!pte_none(*dst_pte)) goto out_unlock; - if (page_in_cache) - page_add_file_rmap(page, false); - else + if (page_in_cache) { + /* Usually, cache pages are already added to LRU */ + if (newly_allocated) + lru_cache_add(page); + page_add_file_rmap(page, dst_vma, false); + } else { page_add_new_anon_rmap(page, dst_vma, dst_addr, false); + lru_cache_add_inactive_or_unevictable(page, dst_vma); + } /* * Must happen after rmap, as mm_counter() checks mapping (via @@ -106,9 +111,6 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, */ inc_mm_counter(dst_mm, mm_counter(page)); - if (newly_allocated) - lru_cache_add_inactive_or_unevictable(page, dst_vma); - set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); /* No need to invalidate - it was non-present before */ -- cgit v1.2.3 From b109b87050df5438ee745b2bddfa3587970025bb Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 14 Feb 2022 18:28:05 -0800 Subject: mm/munlock: replace clear_page_mlock() by final clearance Placing munlock_vma_page() at the end of page_remove_rmap() shifts most of the munlocking to clear_page_mlock(), since PageMlocked is typically still set when mapcount has fallen to 0. That is not what we want: we want /proc/vmstat's unevictable_pgs_cleared to remain as a useful check on the integrity of of the mlock/munlock protocol - small numbers are not surprising, but big numbers mean the protocol is not working. That could be easily fixed by placing munlock_vma_page() at the start of page_remove_rmap(); but later in the series we shall want to batch the munlocking, and that too would tend to leave PageMlocked still set at the point when it is checked. So delete clear_page_mlock() now: leave it instead to release_pages() (and __page_cache_release()) to do this backstop clearing of Mlocked, when page refcount has fallen to 0. If a pinned page occasionally gets counted as Mlocked and Unevictable until it is unpinned, that's okay. A slightly regrettable side-effect of this change is that, since release_pages() and __page_cache_release() may be called at interrupt time, those places which update NR_MLOCK with interrupts enabled had better use mod_zone_page_state() than __mod_zone_page_state() (but holding the lruvec lock always has interrupts disabled). This change, forcing Mlocked off when refcount 0 instead of earlier when mapcount 0, is not fundamental: it can be reversed if performance or something else is found to suffer; but this is the easiest way to separate the stats - let's not complicate that without good reason. Signed-off-by: Hugh Dickins Acked-by: Vlastimil Babka Signed-off-by: Matthew Wilcox (Oracle) --- mm/internal.h | 12 ------------ mm/mlock.c | 30 ------------------------------ mm/rmap.c | 9 --------- mm/swap.c | 32 ++++++++++++++++++++++++-------- 4 files changed, 24 insertions(+), 59 deletions(-) (limited to 'mm/rmap.c') diff --git a/mm/internal.h b/mm/internal.h index 3d7dfc8bc471..a43d79335c16 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -425,17 +425,6 @@ static inline void munlock_vma_page(struct page *page, munlock_page(page); } -/* - * Clear the page's PageMlocked(). This can be useful in a situation where - * we want to unconditionally remove a page from the pagecache -- e.g., - * on truncation or freeing. - * - * It is legal to call this function for any page, mlocked or not. - * If called for a page that is still mapped by mlocked vmas, all we do - * is revert to lazy LRU behaviour -- semantics are not broken. - */ -extern void clear_page_mlock(struct page *page); - extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); /* @@ -509,7 +498,6 @@ static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, } #else /* !CONFIG_MMU */ static inline void unmap_mapping_folio(struct folio *folio) { } -static inline void clear_page_mlock(struct page *page) { } static inline void mlock_vma_page(struct page *page, struct vm_area_struct *vma, bool compound) { } static inline void munlock_vma_page(struct page *page, diff --git a/mm/mlock.c b/mm/mlock.c index 92f28258b4ae..3c26473050a3 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -48,36 +48,6 @@ EXPORT_SYMBOL(can_do_mlock); * PageUnevictable is set to indicate the unevictable state. */ -/* - * LRU accounting for clear_page_mlock() - */ -void clear_page_mlock(struct page *page) -{ - int nr_pages; - - if (!TestClearPageMlocked(page)) - return; - - nr_pages = thp_nr_pages(page); - mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages); - count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages); - /* - * The previous TestClearPageMlocked() corresponds to the smp_mb() - * in __pagevec_lru_add_fn(). - * - * See __pagevec_lru_add_fn for more explanation. - */ - if (!isolate_lru_page(page)) { - putback_lru_page(page); - } else { - /* - * We lost the race. the page already moved to evictable list. - */ - if (PageUnevictable(page)) - count_vm_events(UNEVICTABLE_PGSTRANDED, nr_pages); - } -} - /** * mlock_page - mlock a page * @page: page to be mlocked, either a normal page or a THP head. diff --git a/mm/rmap.c b/mm/rmap.c index 6cc8bf129f18..5442a5c97a85 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1315,9 +1315,6 @@ static void page_remove_file_rmap(struct page *page, bool compound) * pte lock(a spinlock) is held, which implies preemption disabled. */ __mod_lruvec_page_state(page, NR_FILE_MAPPED, -nr); - - if (unlikely(PageMlocked(page))) - clear_page_mlock(page); } static void page_remove_anon_compound_rmap(struct page *page) @@ -1357,9 +1354,6 @@ static void page_remove_anon_compound_rmap(struct page *page) nr = thp_nr_pages(page); } - if (unlikely(PageMlocked(page))) - clear_page_mlock(page); - if (nr) __mod_lruvec_page_state(page, NR_ANON_MAPPED, -nr); } @@ -1398,9 +1392,6 @@ void page_remove_rmap(struct page *page, */ __dec_lruvec_page_state(page, NR_ANON_MAPPED); - if (unlikely(PageMlocked(page))) - clear_page_mlock(page); - if (PageTransCompound(page)) deferred_split_huge_page(compound_head(page)); diff --git a/mm/swap.c b/mm/swap.c index bcf3ac288b56..ff4810e4a4bc 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -74,8 +74,8 @@ static DEFINE_PER_CPU(struct lru_pvecs, lru_pvecs) = { }; /* - * This path almost never happens for VM activity - pages are normally - * freed via pagevecs. But it gets used by networking. + * This path almost never happens for VM activity - pages are normally freed + * via pagevecs. But it gets used by networking - and for compound pages. */ static void __page_cache_release(struct page *page) { @@ -89,6 +89,14 @@ static void __page_cache_release(struct page *page) __clear_page_lru_flags(page); unlock_page_lruvec_irqrestore(lruvec, flags); } + /* See comment on PageMlocked in release_pages() */ + if (unlikely(PageMlocked(page))) { + int nr_pages = thp_nr_pages(page); + + __ClearPageMlocked(page); + mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages); + count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages); + } __ClearPageWaiters(page); } @@ -489,12 +497,8 @@ void lru_cache_add_inactive_or_unevictable(struct page *page, unevictable = (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED; if (unlikely(unevictable) && !TestSetPageMlocked(page)) { int nr_pages = thp_nr_pages(page); - /* - * We use the irq-unsafe __mod_zone_page_state because this - * counter is not modified from interrupt context, and the pte - * lock is held(spinlock), which implies preemption disabled. - */ - __mod_zone_page_state(page_zone(page), NR_MLOCK, nr_pages); + + mod_zone_page_state(page_zone(page), NR_MLOCK, nr_pages); count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); } lru_cache_add(page); @@ -969,6 +973,18 @@ void release_pages(struct page **pages, int nr) __clear_page_lru_flags(page); } + /* + * In rare cases, when truncation or holepunching raced with + * munlock after VM_LOCKED was cleared, Mlocked may still be + * found set here. This does not indicate a problem, unless + * "unevictable_pgs_cleared" appears worryingly large. + */ + if (unlikely(PageMlocked(page))) { + __ClearPageMlocked(page); + dec_zone_page_state(page, NR_MLOCK); + count_vm_event(UNEVICTABLE_PGCLEARED); + } + __ClearPageWaiters(page); list_add(&page->lru, &pages_to_free); -- cgit v1.2.3 From b74355078b6554271371532a5daa3b1a3db620f9 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 14 Feb 2022 18:38:47 -0800 Subject: mm/munlock: page migration needs mlock pagevec drained Page migration of a VM_LOCKED page tends to fail, because when the old page is unmapped, it is put on the mlock pagevec with raised refcount, which then fails the freeze. At first I thought this would be fixed by a local mlock_page_drain() at the upper rmap_walk() level - which would have nicely batched all the munlocks of that page; but tests show that the task can too easily move to another cpu, leaving pagevec residue behind which fails the migration. So try_to_migrate_one() drain the local pagevec after page_remove_rmap() from a VM_LOCKED vma; and do the same in try_to_unmap_one(), whose TTU_IGNORE_MLOCK users would want the same treatment; and do the same in remove_migration_pte() - not important when successfully inserting a new page, but necessary when hoping to retry after failure. Any new pagevec runs the risk of adding a new way of stranding, and we might discover other corners where mlock_page_drain() or lru_add_drain() would now help. Signed-off-by: Hugh Dickins Acked-by: Vlastimil Babka Signed-off-by: Matthew Wilcox (Oracle) --- mm/migrate.c | 2 ++ mm/rmap.c | 4 ++++ 2 files changed, 6 insertions(+) (limited to 'mm/rmap.c') diff --git a/mm/migrate.c b/mm/migrate.c index f4bcf1541b62..e7d0b68d5dcb 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -251,6 +251,8 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, page_add_file_rmap(new, vma, false); set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); } + if (vma->vm_flags & VM_LOCKED) + mlock_page_drain(smp_processor_id()); /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, pvmw.address, pvmw.pte); diff --git a/mm/rmap.c b/mm/rmap.c index 5442a5c97a85..714bfdc72c7b 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1656,6 +1656,8 @@ discard: * See Documentation/vm/mmu_notifier.rst */ page_remove_rmap(subpage, vma, PageHuge(page)); + if (vma->vm_flags & VM_LOCKED) + mlock_page_drain(smp_processor_id()); put_page(page); } @@ -1930,6 +1932,8 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, * See Documentation/vm/mmu_notifier.rst */ page_remove_rmap(subpage, vma, PageHuge(page)); + if (vma->vm_flags & VM_LOCKED) + mlock_page_drain(smp_processor_id()); put_page(page); } -- cgit v1.2.3 From 47d4f3eeef5f7fd346640fa8b49a942b506d2659 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 14 Feb 2022 18:42:33 -0800 Subject: mm/thp: shrink_page_list() avoid splitting VM_LOCKED THP 4.8 commit 7751b2da6be0 ("vmscan: split file huge pages before paging them out") inserted a split_huge_page_to_list() into shrink_page_list() without considering the mlock case: no problem if the page has already been marked as Mlocked (the !page_evictable check much higher up will have skipped all this), but it has always been the case that races or omissions in setting Mlocked can rely on page reclaim to detect this and correct it before actually reclaiming - and that remains so, but what a shame if a hugepage is needlessly split before discovering it. It is surprising that page_check_references() returns PAGEREF_RECLAIM when VM_LOCKED, but there was a good reason for that: try_to_unmap_one() is where the condition is detected and corrected; and until now it could not be done in page_referenced_one(), because that does not always have the page locked. Now that mlock's requirement for page lock has gone, copy try_to_unmap_one()'s mlock restoration into page_referenced_one(), and let page_check_references() return PAGEREF_ACTIVATE in this case. But page_referenced_one() may find a pte mapping one part of a hugepage: what hold should a pte mapped in a VM_LOCKED area exert over the entire huge page? That's debatable. The approach taken here is to treat that pte mapping in page_referenced_one() as if not VM_LOCKED, and if no VM_LOCKED pmd mapping is found later in the walk, and lack of reference permits, then PAGEREF_RECLAIM take it to attempted splitting as before. Signed-off-by: Hugh Dickins Signed-off-by: Matthew Wilcox (Oracle) --- mm/rmap.c | 7 +++++-- mm/vmscan.c | 6 +++--- 2 files changed, 8 insertions(+), 5 deletions(-) (limited to 'mm/rmap.c') diff --git a/mm/rmap.c b/mm/rmap.c index 714bfdc72c7b..c7921c102bc0 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -812,7 +812,10 @@ static bool page_referenced_one(struct page *page, struct vm_area_struct *vma, while (page_vma_mapped_walk(&pvmw)) { address = pvmw.address; - if (vma->vm_flags & VM_LOCKED) { + if ((vma->vm_flags & VM_LOCKED) && + (!PageTransCompound(page) || !pvmw.pte)) { + /* Restore the mlock which got missed */ + mlock_vma_page(page, vma, !pvmw.pte); page_vma_mapped_walk_done(&pvmw); pra->vm_flags |= VM_LOCKED; return false; /* To break the loop */ @@ -851,7 +854,7 @@ static bool page_referenced_one(struct page *page, struct vm_area_struct *vma, if (referenced) { pra->referenced++; - pra->vm_flags |= vma->vm_flags; + pra->vm_flags |= vma->vm_flags & ~VM_LOCKED; } if (!pra->mapcount) diff --git a/mm/vmscan.c b/mm/vmscan.c index 59b14e0d696c..74d3e5e8ebe9 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1388,11 +1388,11 @@ static enum page_references page_check_references(struct page *page, referenced_page = TestClearPageReferenced(page); /* - * Mlock lost the isolation race with us. Let try_to_unmap() - * move the page to the unevictable list. + * The supposedly reclaimable page was found to be in a VM_LOCKED vma. + * Let the page, now marked Mlocked, be moved to the unevictable list. */ if (vm_flags & VM_LOCKED) - return PAGEREF_RECLAIM; + return PAGEREF_ACTIVATE; if (referenced_ptes) { /* -- cgit v1.2.3 From 5232c63f46fdd779303527ec36c518cc1e9c6b4e Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 6 Jan 2022 16:46:43 -0500 Subject: mm: Make compound_pincount always available Move compound_pincount from the third page to the second page, which means it's available for all compound pages. That lets us delete hpage_pincount_available(). On 32-bit systems, there isn't enough space for both compound_pincount and compound_nr in the second page (it would collide with page->private, which is in use for pages in the swap cache), so revert the optimisation of storing both compound_order and compound_nr on 32-bit systems. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: John Hubbard Reviewed-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: William Kucharski --- Documentation/core-api/pin_user_pages.rst | 18 +++++++++--------- include/linux/mm.h | 21 ++++++++------------- include/linux/mm_types.h | 7 +++++-- mm/debug.c | 14 ++++---------- mm/gup.c | 20 +++++++++----------- mm/hugetlb.c | 4 ++++ mm/page_alloc.c | 3 +-- mm/rmap.c | 6 ++---- 8 files changed, 42 insertions(+), 51 deletions(-) (limited to 'mm/rmap.c') diff --git a/Documentation/core-api/pin_user_pages.rst b/Documentation/core-api/pin_user_pages.rst index fcf605be43d0..b18416f4500f 100644 --- a/Documentation/core-api/pin_user_pages.rst +++ b/Documentation/core-api/pin_user_pages.rst @@ -55,18 +55,18 @@ flags the caller provides. The caller is required to pass in a non-null struct pages* array, and the function then pins pages by incrementing each by a special value: GUP_PIN_COUNTING_BIAS. -For huge pages (and in fact, any compound page of more than 2 pages), the -GUP_PIN_COUNTING_BIAS scheme is not used. Instead, an exact form of pin counting -is achieved, by using the 3rd struct page in the compound page. A new struct -page field, hpage_pinned_refcount, has been added in order to support this. +For compound pages, the GUP_PIN_COUNTING_BIAS scheme is not used. Instead, +an exact form of pin counting is achieved, by using the 2nd struct page +in the compound page. A new struct page field, compound_pincount, has +been added in order to support this. This approach for compound pages avoids the counting upper limit problems that are discussed below. Those limitations would have been aggravated severely by huge pages, because each tail page adds a refcount to the head page. And in -fact, testing revealed that, without a separate hpage_pinned_refcount field, +fact, testing revealed that, without a separate compound_pincount field, page overflows were seen in some huge page stress tests. -This also means that huge pages and compound pages (of order > 1) do not suffer +This also means that huge pages and compound pages do not suffer from the false positives problem that is mentioned below.:: Function @@ -264,9 +264,9 @@ place.) Other diagnostics ================= -dump_page() has been enhanced slightly, to handle these new counting fields, and -to better report on compound pages in general. Specifically, for compound pages -with order > 1, the exact (hpage_pinned_refcount) pincount is reported. +dump_page() has been enhanced slightly, to handle these new counting +fields, and to better report on compound pages in general. Specifically, +for compound pages, the exact (compound_pincount) pincount is reported. References ========== diff --git a/include/linux/mm.h b/include/linux/mm.h index e3f8755f65ed..c64bd0b67d75 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -887,17 +887,6 @@ static inline void destroy_compound_page(struct page *page) compound_page_dtors[page[1].compound_dtor](page); } -static inline bool hpage_pincount_available(struct page *page) -{ - /* - * Can the page->hpage_pinned_refcount field be used? That field is in - * the 3rd page of the compound page, so the smallest (2-page) compound - * pages cannot support it. - */ - page = compound_head(page); - return PageCompound(page) && compound_order(page) > 1; -} - static inline int head_compound_pincount(struct page *head) { return atomic_read(compound_pincount_ptr(head)); @@ -905,7 +894,7 @@ static inline int head_compound_pincount(struct page *head) static inline int compound_pincount(struct page *page) { - VM_BUG_ON_PAGE(!hpage_pincount_available(page), page); + VM_BUG_ON_PAGE(!PageCompound(page), page); page = compound_head(page); return head_compound_pincount(page); } @@ -913,7 +902,9 @@ static inline int compound_pincount(struct page *page) static inline void set_compound_order(struct page *page, unsigned int order) { page[1].compound_order = order; +#ifdef CONFIG_64BIT page[1].compound_nr = 1U << order; +#endif } /* Returns the number of pages in this potentially compound page. */ @@ -921,7 +912,11 @@ static inline unsigned long compound_nr(struct page *page) { if (!PageHead(page)) return 1; +#ifdef CONFIG_64BIT return page[1].compound_nr; +#else + return 1UL << compound_order(page); +#endif } /* Returns the number of bytes in this potentially compound page. */ @@ -1269,7 +1264,7 @@ void unpin_user_pages(struct page **pages, unsigned long npages); */ static inline bool page_maybe_dma_pinned(struct page *page) { - if (hpage_pincount_available(page)) + if (PageCompound(page)) return compound_pincount(page) > 0; /* diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 475bdb282769..0e274c9b934e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -135,11 +135,14 @@ struct page { unsigned char compound_dtor; unsigned char compound_order; atomic_t compound_mapcount; + atomic_t compound_pincount; +#ifdef CONFIG_64BIT unsigned int compound_nr; /* 1 << compound_order */ +#endif }; struct { /* Second tail page of compound page */ unsigned long _compound_pad_1; /* compound_head */ - atomic_t hpage_pinned_refcount; + unsigned long _compound_pad_2; /* For both global and memcg */ struct list_head deferred_list; }; @@ -300,7 +303,7 @@ static inline atomic_t *compound_mapcount_ptr(struct page *page) static inline atomic_t *compound_pincount_ptr(struct page *page) { - return &page[2].hpage_pinned_refcount; + return &page[1].compound_pincount; } /* diff --git a/mm/debug.c b/mm/debug.c index bc9ac87f0e08..c4cf44266430 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -92,16 +92,10 @@ static void __dump_page(struct page *page) page, page_ref_count(head), mapcount, mapping, page_to_pgoff(page), page_to_pfn(page)); if (compound) { - if (hpage_pincount_available(page)) { - pr_warn("head:%p order:%u compound_mapcount:%d compound_pincount:%d\n", - head, compound_order(head), - head_compound_mapcount(head), - head_compound_pincount(head)); - } else { - pr_warn("head:%p order:%u compound_mapcount:%d\n", - head, compound_order(head), - head_compound_mapcount(head)); - } + pr_warn("head:%p order:%u compound_mapcount:%d compound_pincount:%d\n", + head, compound_order(head), + head_compound_mapcount(head), + head_compound_pincount(head)); } #ifdef CONFIG_MEMCG diff --git a/mm/gup.c b/mm/gup.c index 1809dc037a8e..56b6b01a430b 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -99,12 +99,11 @@ retry: * * FOLL_GET: page's refcount will be incremented by @refs. * - * FOLL_PIN on compound pages that are > two pages long: page's refcount will - * be incremented by @refs, and page[2].hpage_pinned_refcount will be - * incremented by @refs * GUP_PIN_COUNTING_BIAS. + * FOLL_PIN on compound pages: page's refcount will be incremented by + * @refs, and page[1].compound_pincount will be incremented by @refs. * - * FOLL_PIN on normal pages, or compound pages that are two pages long: - * page's refcount will be incremented by @refs * GUP_PIN_COUNTING_BIAS. + * FOLL_PIN on normal pages: page's refcount will be incremented by + * @refs * GUP_PIN_COUNTING_BIAS. * * Return: head page (with refcount appropriately incremented) for success, or * NULL upon failure. If neither FOLL_GET nor FOLL_PIN was set, that's @@ -135,16 +134,15 @@ __maybe_unused struct page *try_grab_compound_head(struct page *page, return NULL; /* - * When pinning a compound page of order > 1 (which is - * what hpage_pincount_available() checks for), use an - * exact count to track it. + * When pinning a compound page, use an exact count to + * track it. * * However, be sure to *also* increment the normal page * refcount field at least once, so that the page really * is pinned. That's why the refcount from the earlier * try_get_compound_head() is left intact. */ - if (hpage_pincount_available(page)) + if (PageHead(page)) atomic_add(refs, compound_pincount_ptr(page)); else page_ref_add(page, refs * (GUP_PIN_COUNTING_BIAS - 1)); @@ -166,7 +164,7 @@ static void put_compound_head(struct page *page, int refs, unsigned int flags) if (flags & FOLL_PIN) { mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED, refs); - if (hpage_pincount_available(page)) + if (PageHead(page)) atomic_sub(refs, compound_pincount_ptr(page)); else refs *= GUP_PIN_COUNTING_BIAS; @@ -211,7 +209,7 @@ bool __must_check try_grab_page(struct page *page, unsigned int flags) * increment the normal page refcount field at least once, * so that the page really is pinned. */ - if (hpage_pincount_available(page)) { + if (PageHead(page)) { page_ref_add(page, 1); atomic_add(1, compound_pincount_ptr(page)); } else { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 43fb3155298e..785d6e340292 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1320,7 +1320,9 @@ static void __destroy_compound_gigantic_page(struct page *page, } set_compound_order(page, 0); +#ifdef CONFIG_64BIT page[1].compound_nr = 0; +#endif __ClearPageHead(page); } @@ -1812,7 +1814,9 @@ out_error: for (; j < nr_pages; j++, p = mem_map_next(p, page, j)) __ClearPageReserved(p); set_compound_order(page, 0); +#ifdef CONFIG_64BIT page[1].compound_nr = 0; +#endif __ClearPageHead(page); return false; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3589febc6d31..02283598fd14 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -734,8 +734,7 @@ 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); - if (hpage_pincount_available(page)) - atomic_set(compound_pincount_ptr(page), 0); + atomic_set(compound_pincount_ptr(page), 0); } static void prep_compound_tail(struct page *head, int tail_idx) diff --git a/mm/rmap.c b/mm/rmap.c index c7921c102bc0..1a13d5d6cfc7 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1219,8 +1219,7 @@ 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); - if (hpage_pincount_available(page)) - atomic_set(compound_pincount_ptr(page), 0); + atomic_set(compound_pincount_ptr(page), 0); __mod_lruvec_page_state(page, NR_ANON_THPS, nr); } else { @@ -2353,8 +2352,7 @@ 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); - if (hpage_pincount_available(page)) - atomic_set(compound_pincount_ptr(page), 0); + atomic_set(compound_pincount_ptr(page), 0); __page_set_anon_rmap(page, vma, address, 1); } -- cgit v1.2.3 From eed05e54d275b3cfc5d8c79843c5276a5878e94a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 3 Feb 2022 09:06:08 -0500 Subject: mm: Add DEFINE_PAGE_VMA_WALK and DEFINE_FOLIO_VMA_WALK Instead of declaring a struct page_vma_mapped_walk directly, use these helpers to allow us to transition to a PFN approach in the following patches. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/rmap.h | 16 ++++++++++++++++ kernel/events/uprobes.c | 6 +----- mm/damon/paddr.c | 12 ++---------- mm/ksm.c | 5 +---- mm/migrate.c | 7 +------ mm/page_idle.c | 6 +----- mm/rmap.c | 31 +++++-------------------------- 7 files changed, 27 insertions(+), 56 deletions(-) (limited to 'mm/rmap.c') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index ac29b076082b..0d894a2bfaa1 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -214,6 +214,22 @@ struct page_vma_mapped_walk { unsigned int flags; }; +#define DEFINE_PAGE_VMA_WALK(name, _page, _vma, _address, _flags) \ + struct page_vma_mapped_walk name = { \ + .page = _page, \ + .vma = _vma, \ + .address = _address, \ + .flags = _flags, \ + } + +#define DEFINE_FOLIO_VMA_WALK(name, _folio, _vma, _address, _flags) \ + struct page_vma_mapped_walk name = { \ + .page = &_folio->page, \ + .vma = _vma, \ + .address = _address, \ + .flags = _flags, \ + } + static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw) { /* HugeTLB pte is set to the relevant page table entry without pte_mapped. */ diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index eed2f7437d96..6418083901d4 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -155,11 +155,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, struct page *old_page, struct page *new_page) { struct mm_struct *mm = vma->vm_mm; - struct page_vma_mapped_walk pvmw = { - .page = compound_head(old_page), - .vma = vma, - .address = addr, - }; + DEFINE_FOLIO_VMA_WALK(pvmw, page_folio(old_page), vma, addr, 0); int err; struct mmu_notifier_range range; diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index 5e8244f65a1a..cb45d49c731d 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -19,11 +19,7 @@ static bool __damon_pa_mkold(struct page *page, struct vm_area_struct *vma, unsigned long addr, void *arg) { - struct page_vma_mapped_walk pvmw = { - .page = page, - .vma = vma, - .address = addr, - }; + DEFINE_PAGE_VMA_WALK(pvmw, page, vma, addr, 0); while (page_vma_mapped_walk(&pvmw)) { addr = pvmw.address; @@ -93,11 +89,7 @@ static bool __damon_pa_young(struct page *page, struct vm_area_struct *vma, unsigned long addr, void *arg) { struct damon_pa_access_chk_result *result = arg; - struct page_vma_mapped_walk pvmw = { - .page = page, - .vma = vma, - .address = addr, - }; + DEFINE_PAGE_VMA_WALK(pvmw, page, vma, addr, 0); result->accessed = false; result->page_sz = PAGE_SIZE; diff --git a/mm/ksm.c b/mm/ksm.c index c5a4403b5dc9..ea82fef93a31 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -1034,10 +1034,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, pte_t *orig_pte) { struct mm_struct *mm = vma->vm_mm; - struct page_vma_mapped_walk pvmw = { - .page = page, - .vma = vma, - }; + DEFINE_PAGE_VMA_WALK(pvmw, page, vma, 0, 0); int swapped; int err = -EFAULT; struct mmu_notifier_range range; diff --git a/mm/migrate.c b/mm/migrate.c index f4076093c855..71f92e8ed934 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -174,12 +174,7 @@ void putback_movable_pages(struct list_head *l) static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, unsigned long addr, void *old) { - struct page_vma_mapped_walk pvmw = { - .page = old, - .vma = vma, - .address = addr, - .flags = PVMW_SYNC | PVMW_MIGRATION, - }; + DEFINE_PAGE_VMA_WALK(pvmw, old, vma, addr, PVMW_SYNC | PVMW_MIGRATION); struct page *new; pte_t pte; swp_entry_t entry; diff --git a/mm/page_idle.c b/mm/page_idle.c index edead6a8a5f9..3e05bf1ce825 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -48,11 +48,7 @@ static bool page_idle_clear_pte_refs_one(struct page *page, struct vm_area_struct *vma, unsigned long addr, void *arg) { - struct page_vma_mapped_walk pvmw = { - .page = page, - .vma = vma, - .address = addr, - }; + DEFINE_PAGE_VMA_WALK(pvmw, page, vma, addr, 0); bool referenced = false; while (page_vma_mapped_walk(&pvmw)) { diff --git a/mm/rmap.c b/mm/rmap.c index 1a13d5d6cfc7..a7f06b76b503 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -802,11 +802,7 @@ static bool page_referenced_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { struct page_referenced_arg *pra = arg; - struct page_vma_mapped_walk pvmw = { - .page = page, - .vma = vma, - .address = address, - }; + DEFINE_PAGE_VMA_WALK(pvmw, page, vma, address, 0); int referenced = 0; while (page_vma_mapped_walk(&pvmw)) { @@ -934,12 +930,7 @@ int page_referenced(struct page *page, static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { - struct page_vma_mapped_walk pvmw = { - .page = page, - .vma = vma, - .address = address, - .flags = PVMW_SYNC, - }; + DEFINE_PAGE_VMA_WALK(pvmw, page, vma, address, PVMW_SYNC); struct mmu_notifier_range range; int *cleaned = arg; @@ -1419,11 +1410,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; - struct page_vma_mapped_walk pvmw = { - .page = page, - .vma = vma, - .address = address, - }; + DEFINE_PAGE_VMA_WALK(pvmw, page, vma, address, 0); pte_t pteval; struct page *subpage; bool ret = true; @@ -1714,11 +1701,7 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; - struct page_vma_mapped_walk pvmw = { - .page = page, - .vma = vma, - .address = address, - }; + DEFINE_PAGE_VMA_WALK(pvmw, page, vma, address, 0); pte_t pteval; struct page *subpage; bool ret = true; @@ -2001,11 +1984,7 @@ static bool page_make_device_exclusive_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *priv) { struct mm_struct *mm = vma->vm_mm; - struct page_vma_mapped_walk pvmw = { - .page = page, - .vma = vma, - .address = address, - }; + DEFINE_PAGE_VMA_WALK(pvmw, page, vma, address, 0); struct make_exclusive_args *args = priv; pte_t pteval; struct page *subpage; -- cgit v1.2.3 From 2aff7a4755bed2870ee23b75bc88cdc8d76cdd03 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 3 Feb 2022 11:40:17 -0500 Subject: mm: Convert page_vma_mapped_walk to work on PFNs page_mapped_in_vma() really just wants to walk one page, but as the code stands, if passed the head page of a compound page, it will walk every page in the compound page. Extract pfn/nr_pages/pgoff from the struct page early, so they can be overridden by page_mapped_in_vma(). Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/hugetlb.h | 5 +++++ include/linux/rmap.h | 17 ++++++++++----- mm/internal.h | 15 ++++++++----- mm/migrate.c | 5 +++-- mm/page_vma_mapped.c | 58 ++++++++++++++++++++++--------------------------- mm/rmap.c | 8 +++---- 6 files changed, 58 insertions(+), 50 deletions(-) (limited to 'mm/rmap.c') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index d1897a69c540..6ba2f8e74fbb 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -970,6 +970,11 @@ static inline struct hstate *page_hstate(struct page *page) return NULL; } +static inline struct hstate *size_to_hstate(unsigned long size) +{ + return NULL; +} + static inline unsigned long huge_page_size(struct hstate *h) { return PAGE_SIZE; diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 0d894a2bfaa1..0c838ba1a8ee 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -11,6 +11,7 @@ #include #include #include +#include /* * The anon_vma heads a list of private "related" vmas, to scan if @@ -201,11 +202,13 @@ int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, /* Avoid racy checks */ #define PVMW_SYNC (1 << 0) -/* Look for migarion entries rather than present PTEs */ +/* Look for migration entries rather than present PTEs */ #define PVMW_MIGRATION (1 << 1) struct page_vma_mapped_walk { - struct page *page; + unsigned long pfn; + unsigned long nr_pages; + pgoff_t pgoff; struct vm_area_struct *vma; unsigned long address; pmd_t *pmd; @@ -216,7 +219,9 @@ struct page_vma_mapped_walk { #define DEFINE_PAGE_VMA_WALK(name, _page, _vma, _address, _flags) \ struct page_vma_mapped_walk name = { \ - .page = _page, \ + .pfn = page_to_pfn(_page), \ + .nr_pages = compound_nr(page), \ + .pgoff = page_to_pgoff(page), \ .vma = _vma, \ .address = _address, \ .flags = _flags, \ @@ -224,7 +229,9 @@ struct page_vma_mapped_walk { #define DEFINE_FOLIO_VMA_WALK(name, _folio, _vma, _address, _flags) \ struct page_vma_mapped_walk name = { \ - .page = &_folio->page, \ + .pfn = folio_pfn(_folio), \ + .nr_pages = folio_nr_pages(_folio), \ + .pgoff = folio_pgoff(_folio), \ .vma = _vma, \ .address = _address, \ .flags = _flags, \ @@ -233,7 +240,7 @@ struct page_vma_mapped_walk { static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw) { /* HugeTLB pte is set to the relevant page table entry without pte_mapped. */ - if (pvmw->pte && !PageHuge(pvmw->page)) + if (pvmw->pte && !is_vm_hugetlb_page(pvmw->vma)) pte_unmap(pvmw->pte); if (pvmw->ptl) spin_unlock(pvmw->ptl); diff --git a/mm/internal.h b/mm/internal.h index 6047268076e7..3b652444f070 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -10,6 +10,7 @@ #include #include #include +#include #include struct folio_batch; @@ -475,18 +476,20 @@ vma_address(struct page *page, struct vm_area_struct *vma) } /* - * Then at what user virtual address will none of the page be found in vma? + * Then at what user virtual address will none of the range be found in vma? * Assumes that vma_address() already returned a good starting address. - * If page is a compound head, the entire compound page is considered. */ -static inline unsigned long -vma_address_end(struct page *page, struct vm_area_struct *vma) +static inline unsigned long vma_address_end(struct page_vma_mapped_walk *pvmw) { + struct vm_area_struct *vma = pvmw->vma; pgoff_t pgoff; unsigned long address; - VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ - pgoff = page_to_pgoff(page) + compound_nr(page); + /* Common case, plus ->pgoff is invalid for KSM */ + if (pvmw->nr_pages == 1) + return pvmw->address + PAGE_SIZE; + + pgoff = pvmw->pgoff + pvmw->nr_pages; address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address > vma->vm_end) diff --git a/mm/migrate.c b/mm/migrate.c index 71f92e8ed934..358bc311caaa 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -174,7 +174,8 @@ void putback_movable_pages(struct list_head *l) static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, unsigned long addr, void *old) { - DEFINE_PAGE_VMA_WALK(pvmw, old, vma, addr, PVMW_SYNC | PVMW_MIGRATION); + DEFINE_PAGE_VMA_WALK(pvmw, (struct page *)old, vma, addr, + PVMW_SYNC | PVMW_MIGRATION); struct page *new; pte_t pte; swp_entry_t entry; @@ -184,7 +185,7 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, if (PageKsm(page)) new = page; else - new = page - pvmw.page->index + + new = page - pvmw.pgoff + linear_page_index(vma, pvmw.address); #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index f7b331081791..1187f9c1ec5b 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -53,18 +53,6 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw) return true; } -static inline bool pfn_is_match(struct page *page, unsigned long pfn) -{ - unsigned long page_pfn = page_to_pfn(page); - - /* normal page and hugetlbfs page */ - if (!PageTransCompound(page) || PageHuge(page)) - return page_pfn == pfn; - - /* THP can be referenced by any subpage */ - return pfn >= page_pfn && pfn - page_pfn < thp_nr_pages(page); -} - /** * check_pte - check if @pvmw->page is mapped at the @pvmw->pte * @pvmw: page_vma_mapped_walk struct, includes a pair pte and page for checking @@ -116,7 +104,17 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw) pfn = pte_pfn(*pvmw->pte); } - return pfn_is_match(pvmw->page, pfn); + return (pfn - pvmw->pfn) < pvmw->nr_pages; +} + +/* Returns true if the two ranges overlap. Careful to not overflow. */ +static bool check_pmd(unsigned long pfn, struct page_vma_mapped_walk *pvmw) +{ + if ((pfn + HPAGE_PMD_NR - 1) < pvmw->pfn) + return false; + if (pfn > pvmw->pfn + pvmw->nr_pages - 1) + return false; + return true; } static void step_forward(struct page_vma_mapped_walk *pvmw, unsigned long size) @@ -127,7 +125,7 @@ static void step_forward(struct page_vma_mapped_walk *pvmw, unsigned long size) } /** - * page_vma_mapped_walk - check if @pvmw->page is mapped in @pvmw->vma at + * page_vma_mapped_walk - check if @pvmw->pfn is mapped in @pvmw->vma at * @pvmw->address * @pvmw: pointer to struct page_vma_mapped_walk. page, vma, address and flags * must be set. pmd, pte and ptl must be NULL. @@ -152,8 +150,8 @@ static void step_forward(struct page_vma_mapped_walk *pvmw, unsigned long size) */ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) { - struct mm_struct *mm = pvmw->vma->vm_mm; - struct page *page = pvmw->page; + struct vm_area_struct *vma = pvmw->vma; + struct mm_struct *mm = vma->vm_mm; unsigned long end; pgd_t *pgd; p4d_t *p4d; @@ -164,32 +162,26 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) if (pvmw->pmd && !pvmw->pte) return not_found(pvmw); - if (unlikely(PageHuge(page))) { + if (unlikely(is_vm_hugetlb_page(vma))) { + unsigned long size = pvmw->nr_pages * PAGE_SIZE; /* The only possible mapping was handled on last iteration */ if (pvmw->pte) return not_found(pvmw); /* when pud is not present, pte will be NULL */ - pvmw->pte = huge_pte_offset(mm, pvmw->address, page_size(page)); + pvmw->pte = huge_pte_offset(mm, pvmw->address, size); if (!pvmw->pte) return false; - pvmw->ptl = huge_pte_lockptr(page_hstate(page), mm, pvmw->pte); + pvmw->ptl = huge_pte_lockptr(size_to_hstate(size), mm, + pvmw->pte); spin_lock(pvmw->ptl); if (!check_pte(pvmw)) return not_found(pvmw); return true; } - /* - * Seek to next pte only makes sense for THP. - * But more important than that optimization, is to filter out - * any PageKsm page: whose page->index misleads vma_address() - * and vma_address_end() to disaster. - */ - end = PageTransCompound(page) ? - vma_address_end(page, pvmw->vma) : - pvmw->address + PAGE_SIZE; + end = vma_address_end(pvmw); if (pvmw->pte) goto next_pte; restart: @@ -224,7 +216,7 @@ restart: if (likely(pmd_trans_huge(pmde))) { if (pvmw->flags & PVMW_MIGRATION) return not_found(pvmw); - if (pmd_page(pmde) != page) + if (!check_pmd(pmd_pfn(pmde), pvmw)) return not_found(pvmw); return true; } @@ -236,7 +228,7 @@ restart: return not_found(pvmw); entry = pmd_to_swp_entry(pmde); if (!is_migration_entry(entry) || - pfn_swap_entry_to_page(entry) != page) + !check_pmd(swp_offset(entry), pvmw)) return not_found(pvmw); return true; } @@ -250,7 +242,8 @@ restart: * cleared *pmd but not decremented compound_mapcount(). */ if ((pvmw->flags & PVMW_SYNC) && - PageTransCompound(page)) { + transparent_hugepage_active(vma) && + (pvmw->nr_pages >= HPAGE_PMD_NR)) { spinlock_t *ptl = pmd_lock(mm, pvmw->pmd); spin_unlock(ptl); @@ -307,7 +300,8 @@ next_pte: int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) { struct page_vma_mapped_walk pvmw = { - .page = page, + .pfn = page_to_pfn(page), + .nr_pages = 1, .vma = vma, .flags = PVMW_SYNC, }; diff --git a/mm/rmap.c b/mm/rmap.c index a7f06b76b503..e27ba4172069 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -940,7 +940,7 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, vma, vma->vm_mm, address, - vma_address_end(page, vma)); + vma_address_end(&pvmw)); mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { @@ -1437,8 +1437,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * Note that the page can not be free in this function as call of * try_to_unmap() must hold a reference on the page. */ - range.end = PageKsm(page) ? - address + PAGE_SIZE : vma_address_end(page, vma); + range.end = vma_address_end(&pvmw); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, address, range.end); if (PageHuge(page)) { @@ -1732,8 +1731,7 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, * Note that the page can not be free in this function as call of * try_to_unmap() must hold a reference on the page. */ - range.end = PageKsm(page) ? - address + PAGE_SIZE : vma_address_end(page, vma); + range.end = vma_address_end(&pvmw); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, address, range.end); if (PageHuge(page)) { -- cgit v1.2.3 From e83c09a24e3d229f84163c119224af4c8f6c54c1 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 20 Jan 2022 18:20:07 -0500 Subject: mm/rmap: Use a folio in page_mkclean_one() folio_mkclean() already passes down a head page, so convert it back to a folio. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- mm/rmap.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'mm/rmap.c') diff --git a/mm/rmap.c b/mm/rmap.c index e27ba4172069..b1d7f3e7f58c 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -930,13 +930,14 @@ int page_referenced(struct page *page, static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { - DEFINE_PAGE_VMA_WALK(pvmw, page, vma, address, PVMW_SYNC); + struct folio *folio = page_folio(page); + DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_SYNC); struct mmu_notifier_range range; int *cleaned = arg; /* * We have to assume the worse case ie pmd for invalidation. Note that - * the page can not be free from this function. + * the folio can not be freed from this function. */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, vma, vma->vm_mm, address, @@ -968,14 +969,14 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, if (!pmd_dirty(*pmd) && !pmd_write(*pmd)) continue; - flush_cache_page(vma, address, page_to_pfn(page)); + flush_cache_page(vma, address, folio_pfn(folio)); entry = pmdp_invalidate(vma, address, pmd); entry = pmd_wrprotect(entry); entry = pmd_mkclean(entry); set_pmd_at(vma->vm_mm, address, pmd, entry); ret = 1; #else - /* unexpected pmd-mapped page? */ + /* unexpected pmd-mapped folio? */ WARN_ON_ONCE(1); #endif } -- cgit v1.2.3 From b3ac04132c4b9bc5c9c14608424d410e7ca3b400 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 21 Jan 2022 11:27:31 -0500 Subject: mm/rmap: Turn page_referenced() into folio_referenced() Both its callers pass a page which was previously on an LRU list, so were passing a folio by definition. Use the type system to enforce that and remove a few calls to compound_head(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/rmap.h | 4 +-- mm/page_idle.c | 2 +- mm/rmap.c | 70 ++++++++++++++++++++++++++-------------------------- mm/vmscan.c | 20 +++++++++------ 4 files changed, 50 insertions(+), 46 deletions(-) (limited to 'mm/rmap.c') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 0c838ba1a8ee..69a1664216de 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -190,7 +190,7 @@ static inline void page_dup_rmap(struct page *page, bool compound) /* * Called from mm/vmscan.c to handle paging out */ -int page_referenced(struct page *, int is_locked, +int folio_referenced(struct folio *, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags); void try_to_migrate(struct page *page, enum ttu_flags flags); @@ -301,7 +301,7 @@ void rmap_walk_locked(struct page *page, struct rmap_walk_control *rwc); #define anon_vma_prepare(vma) (0) #define anon_vma_link(vma) do {} while (0) -static inline int page_referenced(struct page *page, int is_locked, +static inline int folio_referenced(struct folio *folio, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags) { diff --git a/mm/page_idle.c b/mm/page_idle.c index 2427d832f5d6..5c73a9b578da 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -77,7 +77,7 @@ static bool page_idle_clear_pte_refs_one(struct page *page, /* * We cleared the referenced bit in a mapping to this page. To * avoid interference with page reclaim, mark it young so that - * page_referenced() will return > 0. + * folio_referenced() will return > 0. */ folio_set_young(folio); } diff --git a/mm/rmap.c b/mm/rmap.c index b1d7f3e7f58c..36eef54d05d8 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -789,29 +789,30 @@ out: return pmd; } -struct page_referenced_arg { +struct folio_referenced_arg { int mapcount; int referenced; unsigned long vm_flags; struct mem_cgroup *memcg; }; /* - * arg: page_referenced_arg will be passed + * arg: folio_referenced_arg will be passed */ -static bool page_referenced_one(struct page *page, struct vm_area_struct *vma, +static bool folio_referenced_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { - struct page_referenced_arg *pra = arg; - DEFINE_PAGE_VMA_WALK(pvmw, page, vma, address, 0); + struct folio *folio = page_folio(page); + struct folio_referenced_arg *pra = arg; + DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); int referenced = 0; while (page_vma_mapped_walk(&pvmw)) { address = pvmw.address; if ((vma->vm_flags & VM_LOCKED) && - (!PageTransCompound(page) || !pvmw.pte)) { + (!folio_test_large(folio) || !pvmw.pte)) { /* Restore the mlock which got missed */ - mlock_vma_page(page, vma, !pvmw.pte); + mlock_vma_folio(folio, vma, !pvmw.pte); page_vma_mapped_walk_done(&pvmw); pra->vm_flags |= VM_LOCKED; return false; /* To break the loop */ @@ -823,10 +824,10 @@ static bool page_referenced_one(struct page *page, struct vm_area_struct *vma, /* * Don't treat a reference through * a sequentially read mapping as such. - * If the page has been used in another mapping, + * If the folio has been used in another mapping, * we will catch it; if this other mapping is * already gone, the unmap path will have set - * PG_referenced or activated the page. + * the referenced flag or activated the folio. */ if (likely(!(vma->vm_flags & VM_SEQ_READ))) referenced++; @@ -836,7 +837,7 @@ static bool page_referenced_one(struct page *page, struct vm_area_struct *vma, pvmw.pmd)) referenced++; } else { - /* unexpected pmd-mapped page? */ + /* unexpected pmd-mapped folio? */ WARN_ON_ONCE(1); } @@ -844,8 +845,8 @@ static bool page_referenced_one(struct page *page, struct vm_area_struct *vma, } if (referenced) - clear_page_idle(page); - if (test_and_clear_page_young(page)) + folio_clear_idle(folio); + if (folio_test_clear_young(folio)) referenced++; if (referenced) { @@ -859,9 +860,9 @@ static bool page_referenced_one(struct page *page, struct vm_area_struct *vma, return true; } -static bool invalid_page_referenced_vma(struct vm_area_struct *vma, void *arg) +static bool invalid_folio_referenced_vma(struct vm_area_struct *vma, void *arg) { - struct page_referenced_arg *pra = arg; + struct folio_referenced_arg *pra = arg; struct mem_cgroup *memcg = pra->memcg; if (!mm_match_cgroup(vma->vm_mm, memcg)) @@ -871,27 +872,26 @@ static bool invalid_page_referenced_vma(struct vm_area_struct *vma, void *arg) } /** - * page_referenced - test if the page was referenced - * @page: the page to test - * @is_locked: caller holds lock on the page + * folio_referenced() - Test if the folio was referenced. + * @folio: The folio to test. + * @is_locked: Caller holds lock on the folio. * @memcg: target memory cgroup - * @vm_flags: collect encountered vma->vm_flags who actually referenced the page + * @vm_flags: A combination of all the vma->vm_flags which referenced the folio. * - * Quick test_and_clear_referenced for all mappings to a page, - * returns the number of ptes which referenced the page. + * Quick test_and_clear_referenced for all mappings of a folio, + * + * Return: The number of mappings which referenced the folio. */ -int page_referenced(struct page *page, - int is_locked, - struct mem_cgroup *memcg, - unsigned long *vm_flags) +int folio_referenced(struct folio *folio, int is_locked, + struct mem_cgroup *memcg, unsigned long *vm_flags) { int we_locked = 0; - struct page_referenced_arg pra = { - .mapcount = total_mapcount(page), + struct folio_referenced_arg pra = { + .mapcount = folio_mapcount(folio), .memcg = memcg, }; struct rmap_walk_control rwc = { - .rmap_one = page_referenced_one, + .rmap_one = folio_referenced_one, .arg = (void *)&pra, .anon_lock = page_lock_anon_vma_read, }; @@ -900,11 +900,11 @@ int page_referenced(struct page *page, if (!pra.mapcount) return 0; - if (!page_rmapping(page)) + if (!folio_raw_mapping(folio)) return 0; - if (!is_locked && (!PageAnon(page) || PageKsm(page))) { - we_locked = trylock_page(page); + if (!is_locked && (!folio_test_anon(folio) || folio_test_ksm(folio))) { + we_locked = folio_trylock(folio); if (!we_locked) return 1; } @@ -915,14 +915,14 @@ int page_referenced(struct page *page, * cgroups */ if (memcg) { - rwc.invalid_vma = invalid_page_referenced_vma; + rwc.invalid_vma = invalid_folio_referenced_vma; } - rmap_walk(page, &rwc); + rmap_walk(&folio->page, &rwc); *vm_flags = pra.vm_flags; if (we_locked) - unlock_page(page); + folio_unlock(folio); return pra.referenced; } @@ -1052,8 +1052,8 @@ void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma) anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; /* * Ensure that anon_vma and the PAGE_MAPPING_ANON bit are written - * simultaneously, so a concurrent reader (eg page_referenced()'s - * PageAnon()) will not see one without the other. + * simultaneously, so a concurrent reader (eg folio_referenced()'s + * folio_test_anon()) will not see one without the other. */ WRITE_ONCE(page->mapping, (struct address_space *) anon_vma); } diff --git a/mm/vmscan.c b/mm/vmscan.c index 94729d2d1125..38f124c41bcd 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1386,11 +1386,12 @@ enum page_references { static enum page_references page_check_references(struct page *page, struct scan_control *sc) { + struct folio *folio = page_folio(page); int referenced_ptes, referenced_page; unsigned long vm_flags; - referenced_ptes = page_referenced(page, 1, sc->target_mem_cgroup, - &vm_flags); + referenced_ptes = folio_referenced(folio, 1, sc->target_mem_cgroup, + &vm_flags); referenced_page = TestClearPageReferenced(page); /* @@ -2490,7 +2491,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, * * If the pages are mostly unmapped, the processing is fast and it is * appropriate to hold lru_lock across the whole operation. But if - * the pages are mapped, the processing is slow (page_referenced()), so + * the pages are mapped, the processing is slow (folio_referenced()), so * we should drop lru_lock around each page. It's impossible to balance * this, so instead we remove the pages from the LRU while processing them. * It is safe to rely on PG_active against the non-LRU pages in here because @@ -2510,7 +2511,6 @@ static void shrink_active_list(unsigned long nr_to_scan, LIST_HEAD(l_hold); /* The pages which were snipped off */ LIST_HEAD(l_active); LIST_HEAD(l_inactive); - struct page *page; unsigned nr_deactivate, nr_activate; unsigned nr_rotated = 0; int file = is_file_lru(lru); @@ -2532,9 +2532,13 @@ static void shrink_active_list(unsigned long nr_to_scan, spin_unlock_irq(&lruvec->lru_lock); while (!list_empty(&l_hold)) { + struct folio *folio; + struct page *page; + cond_resched(); - page = lru_to_page(&l_hold); - list_del(&page->lru); + folio = lru_to_folio(&l_hold); + list_del(&folio->lru); + page = &folio->page; if (unlikely(!page_evictable(page))) { putback_lru_page(page); @@ -2549,8 +2553,8 @@ static void shrink_active_list(unsigned long nr_to_scan, } } - if (page_referenced(page, 0, sc->target_mem_cgroup, - &vm_flags)) { + if (folio_referenced(folio, 0, sc->target_mem_cgroup, + &vm_flags)) { /* * Identify referenced, file-backed active pages and * give them one more trip around the active list. So -- cgit v1.2.3 From af28a988b313a601c12c410a42e485ca46adcfee Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 21 Jan 2022 10:44:52 -0500 Subject: mm/huge_memory: Convert __split_huge_pmd() to take a folio Convert split_huge_pmd_address() at the same time since it only passes the folio through, and its two callers already have a folio on hand. Removes numerous calls to compound_head() and removes an assumption that a page cannot be larger than a PMD. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/huge_mm.h | 8 ++++---- mm/huge_memory.c | 46 +++++++++++++++++++++++----------------------- mm/rmap.c | 6 ++++-- 3 files changed, 31 insertions(+), 29 deletions(-) (limited to 'mm/rmap.c') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 71c073d411ac..4368b314d9c8 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -194,7 +194,7 @@ static inline int split_huge_page(struct page *page) void deferred_split_huge_page(struct page *page); void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long address, bool freeze, struct page *page); + unsigned long address, bool freeze, struct folio *folio); #define split_huge_pmd(__vma, __pmd, __address) \ do { \ @@ -207,7 +207,7 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, - bool freeze, struct page *page); + bool freeze, struct folio *folio); void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, unsigned long address); @@ -406,9 +406,9 @@ static inline void deferred_split_huge_page(struct page *page) {} do { } while (0) static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long address, bool freeze, struct page *page) {} + unsigned long address, bool freeze, struct folio *folio) {} static inline void split_huge_pmd_address(struct vm_area_struct *vma, - unsigned long address, bool freeze, struct page *page) {} + unsigned long address, bool freeze, struct folio *folio) {} #define split_huge_pud(__vma, __pmd, __address) \ do { } while (0) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index beebe4105659..583b735a079b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2113,11 +2113,11 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, } void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long address, bool freeze, struct page *page) + unsigned long address, bool freeze, struct folio *folio) { spinlock_t *ptl; struct mmu_notifier_range range; - bool do_unlock_page = false; + bool do_unlock_folio = false; pmd_t _pmd; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, @@ -2127,20 +2127,20 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, ptl = pmd_lock(vma->vm_mm, pmd); /* - * If caller asks to setup a migration entries, we need a page to check - * pmd against. Otherwise we can end up replacing wrong page. + * If caller asks to setup a migration entry, we need a folio to check + * pmd against. Otherwise we can end up replacing wrong folio. */ - VM_BUG_ON(freeze && !page); - if (page) { - VM_WARN_ON_ONCE(!PageLocked(page)); - if (page != pmd_page(*pmd)) + VM_BUG_ON(freeze && !folio); + if (folio) { + VM_WARN_ON_ONCE(!folio_test_locked(folio)); + if (folio != page_folio(pmd_page(*pmd))) goto out; } repeat: if (pmd_trans_huge(*pmd)) { - if (!page) { - page = pmd_page(*pmd); + if (!folio) { + folio = page_folio(pmd_page(*pmd)); /* * An anonymous page must be locked, to ensure that a * concurrent reuse_swap_page() sees stable mapcount; @@ -2148,22 +2148,22 @@ repeat: * and page lock must not be taken when zap_pmd_range() * calls __split_huge_pmd() while i_mmap_lock is held. */ - if (PageAnon(page)) { - if (unlikely(!trylock_page(page))) { - get_page(page); + if (folio_test_anon(folio)) { + if (unlikely(!folio_trylock(folio))) { + folio_get(folio); _pmd = *pmd; spin_unlock(ptl); - lock_page(page); + folio_lock(folio); spin_lock(ptl); if (unlikely(!pmd_same(*pmd, _pmd))) { - unlock_page(page); - put_page(page); - page = NULL; + folio_unlock(folio); + folio_put(folio); + folio = NULL; goto repeat; } - put_page(page); + folio_put(folio); } - do_unlock_page = true; + do_unlock_folio = true; } } } else if (!(pmd_devmap(*pmd) || is_pmd_migration_entry(*pmd))) @@ -2171,8 +2171,8 @@ repeat: __split_huge_pmd_locked(vma, pmd, range.start, freeze); out: spin_unlock(ptl); - if (do_unlock_page) - unlock_page(page); + if (do_unlock_folio) + folio_unlock(folio); /* * No need to double call mmu_notifier->invalidate_range() callback. * They are 3 cases to consider inside __split_huge_pmd_locked(): @@ -2190,7 +2190,7 @@ out: } void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, - bool freeze, struct page *page) + bool freeze, struct folio *folio) { pgd_t *pgd; p4d_t *p4d; @@ -2211,7 +2211,7 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, pmd = pmd_offset(pud, address); - __split_huge_pmd(vma, pmd, address, freeze, page); + __split_huge_pmd(vma, pmd, address, freeze, folio); } static inline void split_huge_pmd_if_needed(struct vm_area_struct *vma, unsigned long address) diff --git a/mm/rmap.c b/mm/rmap.c index 36eef54d05d8..8b3d44e56e30 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1410,6 +1410,7 @@ out: static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { + struct folio *folio = page_folio(page); struct mm_struct *mm = vma->vm_mm; DEFINE_PAGE_VMA_WALK(pvmw, page, vma, address, 0); pte_t pteval; @@ -1428,7 +1429,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, pvmw.flags = PVMW_SYNC; if (flags & TTU_SPLIT_HUGE_PMD) - split_huge_pmd_address(vma, address, false, page); + split_huge_pmd_address(vma, address, false, folio); /* * For THP, we have to assume the worse case ie pmd for invalidation. @@ -1700,6 +1701,7 @@ void try_to_unmap(struct page *page, enum ttu_flags flags) static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { + struct folio *folio = page_folio(page); struct mm_struct *mm = vma->vm_mm; DEFINE_PAGE_VMA_WALK(pvmw, page, vma, address, 0); pte_t pteval; @@ -1722,7 +1724,7 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, * TTU_SPLIT_HUGE_PMD and it wants to freeze. */ if (flags & TTU_SPLIT_HUGE_PMD) - split_huge_pmd_address(vma, address, true, page); + split_huge_pmd_address(vma, address, true, folio); /* * For THP, we have to assume the worse case ie pmd for invalidation. -- cgit v1.2.3 From 869f7ee6f6477341f859c8b0949ae81caf9ca7f3 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 15 Feb 2022 09:28:49 -0500 Subject: mm/rmap: Convert try_to_unmap() to take a folio Change all three callers and the worker function try_to_unmap_one(). Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/rmap.h | 4 +-- mm/huge_memory.c | 3 +- mm/khugepaged.c | 3 +- mm/memory-failure.c | 7 +++-- mm/memory_hotplug.c | 13 ++++---- mm/rmap.c | 83 +++++++++++++++++++++++++++------------------------- mm/vmscan.c | 2 +- 7 files changed, 62 insertions(+), 53 deletions(-) (limited to 'mm/rmap.c') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 69a1664216de..a0c5c38c733f 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -194,7 +194,7 @@ int folio_referenced(struct folio *, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags); void try_to_migrate(struct page *page, enum ttu_flags flags); -void try_to_unmap(struct page *, enum ttu_flags flags); +void try_to_unmap(struct folio *, enum ttu_flags flags); int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, unsigned long end, struct page **pages, @@ -309,7 +309,7 @@ static inline int folio_referenced(struct folio *folio, int is_locked, return 0; } -static inline void try_to_unmap(struct page *page, enum ttu_flags flags) +static inline void try_to_unmap(struct folio *folio, enum ttu_flags flags) { } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 583b735a079b..de684427f79c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2251,6 +2251,7 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma, static void unmap_page(struct page *page) { + struct folio *folio = page_folio(page); enum ttu_flags ttu_flags = TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | TTU_SYNC; @@ -2264,7 +2265,7 @@ static void unmap_page(struct page *page) if (PageAnon(page)) try_to_migrate(page, ttu_flags); else - try_to_unmap(page, ttu_flags | TTU_IGNORE_MLOCK); + try_to_unmap(folio, ttu_flags | TTU_IGNORE_MLOCK); VM_WARN_ON_ONCE_PAGE(page_mapped(page), page); } diff --git a/mm/khugepaged.c b/mm/khugepaged.c index fa05e6d39783..1cdf7c38b9e5 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1834,7 +1834,8 @@ static void collapse_file(struct mm_struct *mm, } if (page_mapped(page)) - try_to_unmap(page, TTU_IGNORE_MLOCK | TTU_BATCH_FLUSH); + try_to_unmap(page_folio(page), + TTU_IGNORE_MLOCK | TTU_BATCH_FLUSH); xas_lock_irq(&xas); xas_set(&xas, index); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 0b72a936b8dd..258913d5e036 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1347,6 +1347,7 @@ static int get_hwpoison_page(struct page *p, unsigned long flags) static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, int flags, struct page *hpage) { + struct folio *folio = page_folio(hpage); enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC; struct address_space *mapping; LIST_HEAD(tokill); @@ -1412,7 +1413,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, collect_procs(hpage, &tokill, flags & MF_ACTION_REQUIRED); if (!PageHuge(hpage)) { - try_to_unmap(hpage, ttu); + try_to_unmap(folio, ttu); } else { if (!PageAnon(hpage)) { /* @@ -1424,12 +1425,12 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, */ mapping = hugetlb_page_mapping_lock_write(hpage); if (mapping) { - try_to_unmap(hpage, ttu|TTU_RMAP_LOCKED); + try_to_unmap(folio, ttu|TTU_RMAP_LOCKED); i_mmap_unlock_write(mapping); } else pr_info("Memory failure: %#lx: could not lock mapping for mapped huge page\n", pfn); } else { - try_to_unmap(hpage, ttu); + try_to_unmap(folio, ttu); } } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 2a9627dc784c..914057da53c7 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1690,10 +1690,13 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) DEFAULT_RATELIMIT_BURST); for (pfn = start_pfn; pfn < end_pfn; pfn++) { + struct folio *folio; + if (!pfn_valid(pfn)) continue; page = pfn_to_page(pfn); - head = compound_head(page); + folio = page_folio(page); + head = &folio->page; if (PageHuge(page)) { pfn = page_to_pfn(head) + compound_nr(head) - 1; @@ -1710,10 +1713,10 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) * the unmap as the catch all safety net). */ if (PageHWPoison(page)) { - if (WARN_ON(PageLRU(page))) - isolate_lru_page(page); - if (page_mapped(page)) - try_to_unmap(page, TTU_IGNORE_MLOCK); + if (WARN_ON(folio_test_lru(folio))) + folio_isolate_lru(folio); + if (folio_mapped(folio)) + try_to_unmap(folio, TTU_IGNORE_MLOCK); continue; } diff --git a/mm/rmap.c b/mm/rmap.c index 8b3d44e56e30..cf6e3de9d2f7 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1412,7 +1412,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, { struct folio *folio = page_folio(page); struct mm_struct *mm = vma->vm_mm; - DEFINE_PAGE_VMA_WALK(pvmw, page, vma, address, 0); + DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); pte_t pteval; struct page *subpage; bool ret = true; @@ -1436,13 +1436,13 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * For hugetlb, it could be much worse if we need to do pud * invalidation in the case of pmd sharing. * - * Note that the page can not be free in this function as call of - * try_to_unmap() must hold a reference on the page. + * Note that the folio can not be freed in this function as call of + * try_to_unmap() must hold a reference on the folio. */ range.end = vma_address_end(&pvmw); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, address, range.end); - if (PageHuge(page)) { + if (folio_test_hugetlb(folio)) { /* * If sharing is possible, start and end will be adjusted * accordingly. @@ -1454,24 +1454,25 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, while (page_vma_mapped_walk(&pvmw)) { /* Unexpected PMD-mapped THP? */ - VM_BUG_ON_PAGE(!pvmw.pte, page); + VM_BUG_ON_FOLIO(!pvmw.pte, folio); /* - * If the page is in an mlock()d vma, we must not swap it out. + * If the folio is in an mlock()d vma, we must not swap it out. */ if (!(flags & TTU_IGNORE_MLOCK) && (vma->vm_flags & VM_LOCKED)) { /* Restore the mlock which got missed */ - mlock_vma_page(page, vma, false); + mlock_vma_folio(folio, vma, false); page_vma_mapped_walk_done(&pvmw); ret = false; break; } - subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); + subpage = folio_page(folio, + pte_pfn(*pvmw.pte) - folio_pfn(folio)); address = pvmw.address; - if (PageHuge(page) && !PageAnon(page)) { + if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) { /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly @@ -1510,7 +1511,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, if (should_defer_flush(mm, flags)) { /* * We clear the PTE but do not flush so potentially - * a remote CPU could still be writing to the page. + * a remote CPU could still be writing to the folio. * If the entry was previously clean then the * architecture must guarantee that a clear->dirty * transition on a cached TLB entry is written through @@ -1523,22 +1524,22 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, pteval = ptep_clear_flush(vma, address, pvmw.pte); } - /* Move the dirty bit to the page. Now the pte is gone. */ + /* Set the dirty flag on the folio now the pte is gone. */ if (pte_dirty(pteval)) - set_page_dirty(page); + folio_mark_dirty(folio); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); - if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) { + if (PageHWPoison(subpage) && !(flags & TTU_IGNORE_HWPOISON)) { pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); - if (PageHuge(page)) { - hugetlb_count_sub(compound_nr(page), mm); + if (folio_test_hugetlb(folio)) { + hugetlb_count_sub(folio_nr_pages(folio), mm); set_huge_swap_pte_at(mm, address, pvmw.pte, pteval, vma_mmu_pagesize(vma)); } else { - dec_mm_counter(mm, mm_counter(page)); + dec_mm_counter(mm, mm_counter(&folio->page)); set_pte_at(mm, address, pvmw.pte, pteval); } @@ -1553,18 +1554,19 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * migration) will not expect userfaults on already * copied pages. */ - dec_mm_counter(mm, mm_counter(page)); + dec_mm_counter(mm, mm_counter(&folio->page)); /* We have to invalidate as we cleared the pte */ mmu_notifier_invalidate_range(mm, address, address + PAGE_SIZE); - } else if (PageAnon(page)) { + } else if (folio_test_anon(folio)) { swp_entry_t entry = { .val = page_private(subpage) }; pte_t swp_pte; /* * Store the swap location in the pte. * See handle_pte_fault() ... */ - if (unlikely(PageSwapBacked(page) != PageSwapCache(page))) { + if (unlikely(folio_test_swapbacked(folio) != + folio_test_swapcache(folio))) { WARN_ON_ONCE(1); ret = false; /* We have to invalidate as we cleared the pte */ @@ -1575,8 +1577,8 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } /* MADV_FREE page check */ - if (!PageSwapBacked(page)) { - if (!PageDirty(page)) { + if (!folio_test_swapbacked(folio)) { + if (!folio_test_dirty(folio)) { /* Invalidate as we cleared the pte */ mmu_notifier_invalidate_range(mm, address, address + PAGE_SIZE); @@ -1585,11 +1587,11 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } /* - * If the page was redirtied, it cannot be + * If the folio was redirtied, it cannot be * discarded. Remap the page to page table. */ set_pte_at(mm, address, pvmw.pte, pteval); - SetPageSwapBacked(page); + folio_set_swapbacked(folio); ret = false; page_vma_mapped_walk_done(&pvmw); break; @@ -1626,16 +1628,17 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, address + PAGE_SIZE); } else { /* - * This is a locked file-backed page, thus it cannot - * be removed from the page cache and replaced by a new - * page before mmu_notifier_invalidate_range_end, so no - * concurrent thread might update its page table to - * point at new page while a device still is using this - * page. + * This is a locked file-backed folio, + * so it cannot be removed from the page + * cache and replaced by a new folio before + * mmu_notifier_invalidate_range_end, so no + * concurrent thread might update its page table + * to point at a new folio while a device is + * still using this folio. * * See Documentation/vm/mmu_notifier.rst */ - dec_mm_counter(mm, mm_counter_file(page)); + dec_mm_counter(mm, mm_counter_file(&folio->page)); } discard: /* @@ -1645,10 +1648,10 @@ discard: * * See Documentation/vm/mmu_notifier.rst */ - page_remove_rmap(subpage, vma, PageHuge(page)); + page_remove_rmap(subpage, vma, folio_test_hugetlb(folio)); if (vma->vm_flags & VM_LOCKED) mlock_page_drain(smp_processor_id()); - put_page(page); + folio_put(folio); } mmu_notifier_invalidate_range_end(&range); @@ -1667,17 +1670,17 @@ static int page_not_mapped(struct page *page) } /** - * try_to_unmap - try to remove all page table mappings to a page - * @page: the page to get unmapped + * try_to_unmap - Try to remove all page table mappings to a folio. + * @folio: The folio to unmap. * @flags: action and flags * * Tries to remove all the page table entries which are mapping this - * page, used in the pageout path. Caller must hold the page lock. + * folio. It is the caller's responsibility to check if the folio is + * still mapped if needed (use TTU_SYNC to prevent accounting races). * - * It is the caller's responsibility to check if the page is still - * mapped when needed (use TTU_SYNC to prevent accounting races). + * Context: Caller must hold the folio lock. */ -void try_to_unmap(struct page *page, enum ttu_flags flags) +void try_to_unmap(struct folio *folio, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, @@ -1687,9 +1690,9 @@ void try_to_unmap(struct page *page, enum ttu_flags flags) }; if (flags & TTU_RMAP_LOCKED) - rmap_walk_locked(page, &rwc); + rmap_walk_locked(&folio->page, &rwc); else - rmap_walk(page, &rwc); + rmap_walk(&folio->page, &rwc); } /* diff --git a/mm/vmscan.c b/mm/vmscan.c index 38f124c41bcd..a57eb747f08d 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1768,7 +1768,7 @@ retry: if (unlikely(PageTransHuge(page))) flags |= TTU_SPLIT_HUGE_PMD; - try_to_unmap(page, flags); + try_to_unmap(folio, flags); if (page_mapped(page)) { stat->nr_unmap_fail += nr_pages; if (!was_swapbacked && PageSwapBacked(page)) -- cgit v1.2.3 From 4b8554c527f3cfa183f6c06d231a9387873205a0 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 28 Jan 2022 14:29:43 -0500 Subject: mm/rmap: Convert try_to_migrate() to folios Convert the callers to pass a folio and the try_to_migrate_one() worker to use a folio throughout. Fixes an assumption that a folio must be <= PMD size. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/rmap.h | 2 +- mm/huge_memory.c | 4 ++-- mm/migrate.c | 6 ++++-- mm/migrate_device.c | 6 ++++-- mm/rmap.c | 59 +++++++++++++++++++++++++++------------------------- 5 files changed, 42 insertions(+), 35 deletions(-) (limited to 'mm/rmap.c') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index a0c5c38c733f..e6e935c81414 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -193,7 +193,7 @@ static inline void page_dup_rmap(struct page *page, bool compound) int folio_referenced(struct folio *, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags); -void try_to_migrate(struct page *page, enum ttu_flags flags); +void try_to_migrate(struct folio *folio, enum ttu_flags flags); void try_to_unmap(struct folio *, enum ttu_flags flags); int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index de684427f79c..7df1934d6528 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2262,8 +2262,8 @@ static void unmap_page(struct page *page) * pages can simply be left unmapped, then faulted back on demand. * If that is ever changed (perhaps for mlock), update remap_page(). */ - if (PageAnon(page)) - try_to_migrate(page, ttu_flags); + if (folio_test_anon(folio)) + try_to_migrate(folio, ttu_flags); else try_to_unmap(folio, ttu_flags | TTU_IGNORE_MLOCK); diff --git a/mm/migrate.c b/mm/migrate.c index 358bc311caaa..6ed85a5d1be5 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -912,6 +912,7 @@ out: static int __unmap_and_move(struct page *page, struct page *newpage, int force, enum migrate_mode mode) { + struct folio *folio = page_folio(page); int rc = -EAGAIN; bool page_was_mapped = false; struct anon_vma *anon_vma = NULL; @@ -1015,7 +1016,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, /* Establish migration ptes */ VM_BUG_ON_PAGE(PageAnon(page) && !PageKsm(page) && !anon_vma, page); - try_to_migrate(page, 0); + try_to_migrate(folio, 0); page_was_mapped = true; } @@ -1165,6 +1166,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, enum migrate_mode mode, int reason, struct list_head *ret) { + struct folio *src = page_folio(hpage); int rc = -EAGAIN; int page_was_mapped = 0; struct page *new_hpage; @@ -1241,7 +1243,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, ttu |= TTU_RMAP_LOCKED; } - try_to_migrate(hpage, ttu); + try_to_migrate(src, ttu); page_was_mapped = 1; if (mapping_locked) diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 0326b901d2fd..b2c611d4bdb2 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -333,6 +333,7 @@ static void migrate_vma_unmap(struct migrate_vma *migrate) for (i = 0; i < npages; i++) { struct page *page = migrate_pfn_to_page(migrate->src[i]); + struct folio *folio; if (!page) continue; @@ -356,8 +357,9 @@ static void migrate_vma_unmap(struct migrate_vma *migrate) put_page(page); } - if (page_mapped(page)) - try_to_migrate(page, 0); + folio = page_folio(page); + if (folio_mapped(folio)) + try_to_migrate(folio, 0); if (page_mapped(page) || !migrate_vma_check_page(page)) { if (!is_zone_device_page(page)) { diff --git a/mm/rmap.c b/mm/rmap.c index cf6e3de9d2f7..8497da29193c 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1706,7 +1706,7 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, { struct folio *folio = page_folio(page); struct mm_struct *mm = vma->vm_mm; - DEFINE_PAGE_VMA_WALK(pvmw, page, vma, address, 0); + DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); pte_t pteval; struct page *subpage; bool ret = true; @@ -1740,7 +1740,7 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, range.end = vma_address_end(&pvmw); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, address, range.end); - if (PageHuge(page)) { + if (folio_test_hugetlb(folio)) { /* * If sharing is possible, start and end will be adjusted * accordingly. @@ -1754,21 +1754,24 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION /* PMD-mapped THP migration entry */ if (!pvmw.pte) { - VM_BUG_ON_PAGE(PageHuge(page) || - !PageTransCompound(page), page); + subpage = folio_page(folio, + pmd_pfn(*pvmw.pmd) - folio_pfn(folio)); + VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) || + !folio_test_pmd_mappable(folio), folio); - set_pmd_migration_entry(&pvmw, page); + set_pmd_migration_entry(&pvmw, subpage); continue; } #endif /* Unexpected PMD-mapped THP? */ - VM_BUG_ON_PAGE(!pvmw.pte, page); + VM_BUG_ON_FOLIO(!pvmw.pte, folio); - subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); + subpage = folio_page(folio, + pte_pfn(*pvmw.pte) - folio_pfn(folio)); address = pvmw.address; - if (PageHuge(page) && !PageAnon(page)) { + if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) { /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly @@ -1806,15 +1809,15 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); pteval = ptep_clear_flush(vma, address, pvmw.pte); - /* Move the dirty bit to the page. Now the pte is gone. */ + /* Set the dirty flag on the folio now the pte is gone. */ if (pte_dirty(pteval)) - set_page_dirty(page); + folio_mark_dirty(folio); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); - if (is_zone_device_page(page)) { - unsigned long pfn = page_to_pfn(page); + if (folio_is_zone_device(folio)) { + unsigned long pfn = folio_pfn(folio); swp_entry_t entry; pte_t swp_pte; @@ -1850,16 +1853,16 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, * changed when hugepage migrations to device private * memory are supported. */ - subpage = page; - } else if (PageHWPoison(page)) { + subpage = &folio->page; + } else if (PageHWPoison(subpage)) { pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); - if (PageHuge(page)) { - hugetlb_count_sub(compound_nr(page), mm); + if (folio_test_hugetlb(folio)) { + hugetlb_count_sub(folio_nr_pages(folio), mm); set_huge_swap_pte_at(mm, address, pvmw.pte, pteval, vma_mmu_pagesize(vma)); } else { - dec_mm_counter(mm, mm_counter(page)); + dec_mm_counter(mm, mm_counter(&folio->page)); set_pte_at(mm, address, pvmw.pte, pteval); } @@ -1874,7 +1877,7 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, * migration) will not expect userfaults on already * copied pages. */ - dec_mm_counter(mm, mm_counter(page)); + dec_mm_counter(mm, mm_counter(&folio->page)); /* We have to invalidate as we cleared the pte */ mmu_notifier_invalidate_range(mm, address, address + PAGE_SIZE); @@ -1920,10 +1923,10 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, * * See Documentation/vm/mmu_notifier.rst */ - page_remove_rmap(subpage, vma, PageHuge(page)); + page_remove_rmap(subpage, vma, folio_test_hugetlb(folio)); if (vma->vm_flags & VM_LOCKED) mlock_page_drain(smp_processor_id()); - put_page(page); + folio_put(folio); } mmu_notifier_invalidate_range_end(&range); @@ -1933,13 +1936,13 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, /** * try_to_migrate - try to replace all page table mappings with swap entries - * @page: the page to replace page table entries for + * @folio: the folio to replace page table entries for * @flags: action and flags * - * Tries to remove all the page table entries which are mapping this page and - * replace them with special swap entries. Caller must hold the page lock. + * Tries to remove all the page table entries which are mapping this folio and + * replace them with special swap entries. Caller must hold the folio lock. */ -void try_to_migrate(struct page *page, enum ttu_flags flags) +void try_to_migrate(struct folio *folio, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_migrate_one, @@ -1956,7 +1959,7 @@ void try_to_migrate(struct page *page, enum ttu_flags flags) TTU_SYNC))) return; - if (is_zone_device_page(page) && !is_device_private_page(page)) + if (folio_is_zone_device(folio) && !folio_is_device_private(folio)) return; /* @@ -1967,13 +1970,13 @@ void try_to_migrate(struct page *page, enum ttu_flags flags) * locking requirements of exec(), migration skips * temporary VMAs until after exec() completes. */ - if (!PageKsm(page) && PageAnon(page)) + if (!folio_test_ksm(folio) && folio_test_anon(folio)) rwc.invalid_vma = invalid_migration_vma; if (flags & TTU_RMAP_LOCKED) - rmap_walk_locked(page, &rwc); + rmap_walk_locked(&folio->page, &rwc); else - rmap_walk(page, &rwc); + rmap_walk(&folio->page, &rwc); } #ifdef CONFIG_DEVICE_PRIVATE -- cgit v1.2.3 From 0d2514859ceda3cc42386f819d3131f782fd69d5 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 28 Jan 2022 16:03:42 -0500 Subject: mm/rmap: Convert make_device_exclusive_range() to use folios Move the PageTail check earlier so we can avoid even taking the folio lock on tail pages. Otherwise, this is a straightforward use of folios throughout. Signed-off-by: Matthew Wilcox (Oracle) --- mm/rmap.c | 58 +++++++++++++++++++++++++++++++--------------------------- 1 file changed, 31 insertions(+), 27 deletions(-) (limited to 'mm/rmap.c') diff --git a/mm/rmap.c b/mm/rmap.c index 8497da29193c..c74de8af7eec 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1990,8 +1990,9 @@ struct make_exclusive_args { static bool page_make_device_exclusive_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *priv) { + struct folio *folio = page_folio(page); struct mm_struct *mm = vma->vm_mm; - DEFINE_PAGE_VMA_WALK(pvmw, page, vma, address, 0); + DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); struct make_exclusive_args *args = priv; pte_t pteval; struct page *subpage; @@ -2002,12 +2003,13 @@ static bool page_make_device_exclusive_one(struct page *page, mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma, vma->vm_mm, address, min(vma->vm_end, - address + page_size(page)), args->owner); + address + folio_size(folio)), + args->owner); mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { /* Unexpected PMD-mapped THP? */ - VM_BUG_ON_PAGE(!pvmw.pte, page); + VM_BUG_ON_FOLIO(!pvmw.pte, folio); if (!pte_present(*pvmw.pte)) { ret = false; @@ -2015,16 +2017,17 @@ static bool page_make_device_exclusive_one(struct page *page, break; } - subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); + subpage = folio_page(folio, + pte_pfn(*pvmw.pte) - folio_pfn(folio)); address = pvmw.address; /* Nuke the page table entry. */ flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); pteval = ptep_clear_flush(vma, address, pvmw.pte); - /* Move the dirty bit to the page. Now the pte is gone. */ + /* Set the dirty flag on the folio now the pte is gone. */ if (pte_dirty(pteval)) - set_page_dirty(page); + folio_mark_dirty(folio); /* * Check that our target page is still mapped at the expected @@ -2066,21 +2069,22 @@ static bool page_make_device_exclusive_one(struct page *page, } /** - * page_make_device_exclusive - mark the page exclusively owned by a device - * @page: the page to replace page table entries for - * @mm: the mm_struct where the page is expected to be mapped - * @address: address where the page is expected to be mapped + * folio_make_device_exclusive - Mark the folio exclusively owned by a device. + * @folio: The folio to replace page table entries for. + * @mm: The mm_struct where the folio is expected to be mapped. + * @address: Address where the folio is expected to be mapped. * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier callbacks * - * Tries to remove all the page table entries which are mapping this page and - * replace them with special device exclusive swap entries to grant a device - * exclusive access to the page. Caller must hold the page lock. + * Tries to remove all the page table entries which are mapping this + * folio and replace them with special device exclusive swap entries to + * grant a device exclusive access to the folio. * - * Returns false if the page is still mapped, or if it could not be unmapped + * Context: Caller must hold the folio lock. + * Return: false if the page is still mapped, or if it could not be unmapped * from the expected address. Otherwise returns true (success). */ -static bool page_make_device_exclusive(struct page *page, struct mm_struct *mm, - unsigned long address, void *owner) +static bool folio_make_device_exclusive(struct folio *folio, + struct mm_struct *mm, unsigned long address, void *owner) { struct make_exclusive_args args = { .mm = mm, @@ -2096,16 +2100,15 @@ static bool page_make_device_exclusive(struct page *page, struct mm_struct *mm, }; /* - * Restrict to anonymous pages for now to avoid potential writeback - * issues. Also tail pages shouldn't be passed to rmap_walk so skip - * those. + * Restrict to anonymous folios for now to avoid potential writeback + * issues. */ - if (!PageAnon(page) || PageTail(page)) + if (!folio_test_anon(folio)) return false; - rmap_walk(page, &rwc); + rmap_walk(&folio->page, &rwc); - return args.valid && !page_mapcount(page); + return args.valid && !folio_mapcount(folio); } /** @@ -2143,15 +2146,16 @@ int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, return npages; for (i = 0; i < npages; i++, start += PAGE_SIZE) { - if (!trylock_page(pages[i])) { - put_page(pages[i]); + struct folio *folio = page_folio(pages[i]); + if (PageTail(pages[i]) || !folio_trylock(folio)) { + folio_put(folio); pages[i] = NULL; continue; } - if (!page_make_device_exclusive(pages[i], mm, start, owner)) { - unlock_page(pages[i]); - put_page(pages[i]); + if (!folio_make_device_exclusive(folio, mm, start, owner)) { + folio_unlock(folio); + folio_put(folio); pages[i] = NULL; } } -- cgit v1.2.3 From 9595d76942b8714627d670a7e7ae543812c731ae Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 1 Feb 2022 23:33:08 -0500 Subject: mm/rmap: Turn page_lock_anon_vma_read() into folio_lock_anon_vma_read() Add back page_lock_anon_vma_read() as a wrapper. This saves a few calls to compound_head(). If any callers were passing a tail page before, this would have failed to lock the anon VMA as page->mapping is not valid for tail pages. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/rmap.h | 1 + mm/folio-compat.c | 7 +++++++ mm/memory-failure.c | 3 ++- mm/rmap.c | 12 ++++++------ 4 files changed, 16 insertions(+), 7 deletions(-) (limited to 'mm/rmap.c') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 21af80d5b711..be020d38b0a5 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -267,6 +267,7 @@ void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked); * Called by memory-failure.c to kill processes. */ struct anon_vma *page_lock_anon_vma_read(struct page *page); +struct anon_vma *folio_lock_anon_vma_read(struct folio *folio); void page_unlock_anon_vma_read(struct anon_vma *anon_vma); int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 46fa179e32fb..968ad97bbffa 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -164,3 +164,10 @@ void putback_lru_page(struct page *page) { folio_putback_lru(page_folio(page)); } + +#ifdef CONFIG_MMU +struct anon_vma *page_lock_anon_vma_read(struct page *page) +{ + return folio_lock_anon_vma_read(page_folio(page)); +} +#endif diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 258913d5e036..aa8236848949 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -487,12 +487,13 @@ static struct task_struct *task_early_kill(struct task_struct *tsk, static void collect_procs_anon(struct page *page, struct list_head *to_kill, int force_early) { + struct folio *folio = page_folio(page); struct vm_area_struct *vma; struct task_struct *tsk; struct anon_vma *av; pgoff_t pgoff; - av = page_lock_anon_vma_read(page); + av = folio_lock_anon_vma_read(folio); if (av == NULL) /* Not actually mapped anymore */ return; diff --git a/mm/rmap.c b/mm/rmap.c index c74de8af7eec..64655d345234 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -526,28 +526,28 @@ out: * atomic op -- the trylock. If we fail the trylock, we fall back to getting a * reference like with page_get_anon_vma() and then block on the mutex. */ -struct anon_vma *page_lock_anon_vma_read(struct page *page) +struct anon_vma *folio_lock_anon_vma_read(struct folio *folio) { struct anon_vma *anon_vma = NULL; struct anon_vma *root_anon_vma; unsigned long anon_mapping; rcu_read_lock(); - anon_mapping = (unsigned long)READ_ONCE(page->mapping); + anon_mapping = (unsigned long)READ_ONCE(folio->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; - if (!page_mapped(page)) + if (!folio_mapped(folio)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); root_anon_vma = READ_ONCE(anon_vma->root); if (down_read_trylock(&root_anon_vma->rwsem)) { /* - * If the page is still mapped, then this anon_vma is still + * If the folio is still mapped, then this anon_vma is still * its anon_vma, and holding the mutex ensures that it will * not go away, see anon_vma_free(). */ - if (!page_mapped(page)) { + if (!folio_mapped(folio)) { up_read(&root_anon_vma->rwsem); anon_vma = NULL; } @@ -560,7 +560,7 @@ struct anon_vma *page_lock_anon_vma_read(struct page *page) goto out; } - if (!page_mapped(page)) { + if (!folio_mapped(folio)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; -- cgit v1.2.3 From e05b34539d008ab819388f699b25eae962ba24ac Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 29 Jan 2022 11:52:52 -0500 Subject: mm: Turn page_anon_vma() into folio_anon_vma() Move the prototype from mm.h to mm/internal.h and convert all callers to pass a folio. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/mm.h | 1 - mm/internal.h | 1 + mm/ksm.c | 3 ++- mm/rmap.c | 19 ++++++++++++------- mm/util.c | 3 +-- 5 files changed, 16 insertions(+), 11 deletions(-) (limited to 'mm/rmap.c') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0d380dc26847..a879c583f665 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1730,7 +1730,6 @@ static inline void *folio_address(const struct folio *folio) } extern void *page_rmapping(struct page *page); -extern struct anon_vma *page_anon_vma(struct page *page); extern pgoff_t __page_file_index(struct page *page); /* diff --git a/mm/internal.h b/mm/internal.h index 6039acc780c0..2b2c2c4eb63a 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -392,6 +392,7 @@ static inline bool is_data_mapping(vm_flags_t flags) void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev); void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma); +struct anon_vma *folio_anon_vma(struct folio *folio); #ifdef CONFIG_MMU void unmap_mapping_folio(struct folio *folio); diff --git a/mm/ksm.c b/mm/ksm.c index ea82fef93a31..b25d545e0cd1 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -2554,7 +2554,8 @@ void __ksm_exit(struct mm_struct *mm) struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address) { - struct anon_vma *anon_vma = page_anon_vma(page); + struct folio *folio = page_folio(page); + struct anon_vma *anon_vma = folio_anon_vma(folio); struct page *new_page; if (PageKsm(page)) { diff --git a/mm/rmap.c b/mm/rmap.c index 64655d345234..09301aecf2fc 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -737,8 +737,9 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) */ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) { - if (PageAnon(page)) { - struct anon_vma *page__anon_vma = page_anon_vma(page); + struct folio *folio = page_folio(page); + if (folio_test_anon(folio)) { + struct anon_vma *page__anon_vma = folio_anon_vma(folio); /* * Note: swapoff's unuse_vma() is more efficient with this * check, and needs it to match anon_vma when KSM is active. @@ -748,7 +749,7 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) return -EFAULT; } else if (!vma->vm_file) { return -EFAULT; - } else if (vma->vm_file->f_mapping != compound_head(page)->mapping) { + } else if (vma->vm_file->f_mapping != folio->mapping) { return -EFAULT; } @@ -1103,6 +1104,7 @@ static void __page_set_anon_rmap(struct page *page, static void __page_check_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address) { + struct folio *folio = page_folio(page); /* * The page's anon-rmap details (mapping and index) are guaranteed to * be set up correctly at this point. @@ -1114,7 +1116,8 @@ static void __page_check_anon_rmap(struct page *page, * are initially only visible via the pagetables, and the pte is locked * over the call to page_add_new_anon_rmap. */ - VM_BUG_ON_PAGE(page_anon_vma(page)->root != vma->anon_vma->root, page); + VM_BUG_ON_FOLIO(folio_anon_vma(folio)->root != vma->anon_vma->root, + folio); VM_BUG_ON_PAGE(page_to_pgoff(page) != linear_page_index(vma, address), page); } @@ -2177,6 +2180,7 @@ void __put_anon_vma(struct anon_vma *anon_vma) static struct anon_vma *rmap_walk_anon_lock(struct page *page, struct rmap_walk_control *rwc) { + struct folio *folio = page_folio(page); struct anon_vma *anon_vma; if (rwc->anon_lock) @@ -2188,7 +2192,7 @@ static struct anon_vma *rmap_walk_anon_lock(struct page *page, * are holding mmap_lock. Users without mmap_lock are required to * take a reference count to prevent the anon_vma disappearing */ - anon_vma = page_anon_vma(page); + anon_vma = folio_anon_vma(folio); if (!anon_vma) return NULL; @@ -2208,14 +2212,15 @@ static struct anon_vma *rmap_walk_anon_lock(struct page *page, static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, bool locked) { + struct folio *folio = page_folio(page); struct anon_vma *anon_vma; pgoff_t pgoff_start, pgoff_end; struct anon_vma_chain *avc; if (locked) { - anon_vma = page_anon_vma(page); + anon_vma = folio_anon_vma(folio); /* anon_vma disappear under us? */ - VM_BUG_ON_PAGE(!anon_vma, page); + VM_BUG_ON_FOLIO(!anon_vma, folio); } else { anon_vma = rmap_walk_anon_lock(page, rwc); } diff --git a/mm/util.c b/mm/util.c index b614f423aaa4..13fc88ac8e70 100644 --- a/mm/util.c +++ b/mm/util.c @@ -679,9 +679,8 @@ bool folio_mapped(struct folio *folio) } EXPORT_SYMBOL(folio_mapped); -struct anon_vma *page_anon_vma(struct page *page) +struct anon_vma *folio_anon_vma(struct folio *folio) { - struct folio *folio = page_folio(page); unsigned long mapping = (unsigned long)folio->mapping; if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) -- cgit v1.2.3 From 2f031c6f042cb8a9b221a8b6b80e69de5170f830 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 29 Jan 2022 16:06:53 -0500 Subject: mm/rmap: Convert rmap_walk() to take a folio This ripples all the way through to every calling and called function from rmap. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/ksm.h | 4 +- include/linux/rmap.h | 11 +++-- mm/damon/paddr.c | 15 ++++--- mm/folio-compat.c | 7 ---- mm/huge_memory.c | 2 +- mm/ksm.c | 12 +++--- mm/migrate.c | 10 ++--- mm/page_idle.c | 7 ++-- mm/rmap.c | 111 ++++++++++++++++++++++++--------------------------- 9 files changed, 80 insertions(+), 99 deletions(-) (limited to 'mm/rmap.c') diff --git a/include/linux/ksm.h b/include/linux/ksm.h index a38a5bca1ba5..0b4f17418f64 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -51,7 +51,7 @@ static inline void ksm_exit(struct mm_struct *mm) struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address); -void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc); +void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); #else /* !CONFIG_KSM */ @@ -78,7 +78,7 @@ static inline struct page *ksm_might_need_to_copy(struct page *page, return page; } -static inline void rmap_walk_ksm(struct page *page, +static inline void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc) { } diff --git a/include/linux/rmap.h b/include/linux/rmap.h index be020d38b0a5..a74d811c5b3f 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -266,7 +266,6 @@ void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked); /* * Called by memory-failure.c to kill processes. */ -struct anon_vma *page_lock_anon_vma_read(struct page *page); struct anon_vma *folio_lock_anon_vma_read(struct folio *folio); void page_unlock_anon_vma_read(struct anon_vma *anon_vma); int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); @@ -286,15 +285,15 @@ struct rmap_walk_control { * Return false if page table scanning in rmap_walk should be stopped. * Otherwise, return true. */ - bool (*rmap_one)(struct page *page, struct vm_area_struct *vma, + bool (*rmap_one)(struct folio *folio, struct vm_area_struct *vma, unsigned long addr, void *arg); - int (*done)(struct page *page); - struct anon_vma *(*anon_lock)(struct page *page); + int (*done)(struct folio *folio); + struct anon_vma *(*anon_lock)(struct folio *folio); bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; -void rmap_walk(struct page *page, struct rmap_walk_control *rwc); -void rmap_walk_locked(struct page *page, struct rmap_walk_control *rwc); +void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc); +void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc); #else /* !CONFIG_MMU */ diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index eee8a3395d71..ae24549921e2 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -16,10 +16,10 @@ #include "../internal.h" #include "prmtv-common.h" -static bool __damon_pa_mkold(struct page *page, struct vm_area_struct *vma, +static bool __damon_pa_mkold(struct folio *folio, struct vm_area_struct *vma, unsigned long addr, void *arg) { - DEFINE_PAGE_VMA_WALK(pvmw, page, vma, addr, 0); + DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, addr, 0); while (page_vma_mapped_walk(&pvmw)) { addr = pvmw.address; @@ -37,7 +37,7 @@ static void damon_pa_mkold(unsigned long paddr) struct page *page = damon_get_page(PHYS_PFN(paddr)); struct rmap_walk_control rwc = { .rmap_one = __damon_pa_mkold, - .anon_lock = page_lock_anon_vma_read, + .anon_lock = folio_lock_anon_vma_read, }; bool need_lock; @@ -54,7 +54,7 @@ static void damon_pa_mkold(unsigned long paddr) if (need_lock && !folio_trylock(folio)) goto out; - rmap_walk(&folio->page, &rwc); + rmap_walk(folio, &rwc); if (need_lock) folio_unlock(folio); @@ -87,10 +87,9 @@ struct damon_pa_access_chk_result { bool accessed; }; -static bool __damon_pa_young(struct page *page, struct vm_area_struct *vma, +static bool __damon_pa_young(struct folio *folio, struct vm_area_struct *vma, unsigned long addr, void *arg) { - struct folio *folio = page_folio(page); struct damon_pa_access_chk_result *result = arg; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, addr, 0); @@ -133,7 +132,7 @@ static bool damon_pa_young(unsigned long paddr, unsigned long *page_sz) struct rmap_walk_control rwc = { .arg = &result, .rmap_one = __damon_pa_young, - .anon_lock = page_lock_anon_vma_read, + .anon_lock = folio_lock_anon_vma_read, }; bool need_lock; @@ -156,7 +155,7 @@ static bool damon_pa_young(unsigned long paddr, unsigned long *page_sz) return NULL; } - rmap_walk(&folio->page, &rwc); + rmap_walk(folio, &rwc); if (need_lock) folio_unlock(folio); diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 968ad97bbffa..46fa179e32fb 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -164,10 +164,3 @@ void putback_lru_page(struct page *page) { folio_putback_lru(page_folio(page)); } - -#ifdef CONFIG_MMU -struct anon_vma *page_lock_anon_vma_read(struct page *page) -{ - return folio_lock_anon_vma_read(page_folio(page)); -} -#endif diff --git a/mm/huge_memory.c b/mm/huge_memory.c index d55b25f1ceba..d874d50e703b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2572,7 +2572,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) * The caller does not necessarily hold an mmap_lock that would * prevent the anon_vma disappearing so we first we take a * reference to it and then lock the anon_vma for write. This - * is similar to page_lock_anon_vma_read except the write lock + * is similar to folio_lock_anon_vma_read except the write lock * is taken to serialise against parallel split or collapse * operations. */ diff --git a/mm/ksm.c b/mm/ksm.c index b25d545e0cd1..dd737f925c04 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -2588,21 +2588,21 @@ struct page *ksm_might_need_to_copy(struct page *page, return new_page; } -void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc) +void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc) { struct stable_node *stable_node; struct rmap_item *rmap_item; int search_new_forks = 0; - VM_BUG_ON_PAGE(!PageKsm(page), page); + VM_BUG_ON_FOLIO(!folio_test_ksm(folio), folio); /* * Rely on the page lock to protect against concurrent modifications * to that page's node of the stable tree. */ - VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); - stable_node = page_stable_node(page); + stable_node = folio_stable_node(folio); if (!stable_node) return; again: @@ -2637,11 +2637,11 @@ again: if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; - if (!rwc->rmap_one(page, vma, addr, rwc->arg)) { + if (!rwc->rmap_one(folio, vma, addr, rwc->arg)) { anon_vma_unlock_read(anon_vma); return; } - if (rwc->done && rwc->done(page)) { + if (rwc->done && rwc->done(folio)) { anon_vma_unlock_read(anon_vma); return; } diff --git a/mm/migrate.c b/mm/migrate.c index eba3cd5376e3..2defe9aa4d0e 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -171,13 +171,11 @@ void putback_movable_pages(struct list_head *l) /* * Restore a potential migration pte to a working pte entry */ -static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, - unsigned long addr, void *old) +static bool remove_migration_pte(struct folio *folio, + struct vm_area_struct *vma, unsigned long addr, void *old) { - struct folio *folio = page_folio(page); DEFINE_FOLIO_VMA_WALK(pvmw, old, vma, addr, PVMW_SYNC | PVMW_MIGRATION); - VM_BUG_ON_PAGE(PageTail(page), page); while (page_vma_mapped_walk(&pvmw)) { pte_t pte; swp_entry_t entry; @@ -269,9 +267,9 @@ void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked) }; if (locked) - rmap_walk_locked(&dst->page, &rwc); + rmap_walk_locked(dst, &rwc); else - rmap_walk(&dst->page, &rwc); + rmap_walk(dst, &rwc); } /* diff --git a/mm/page_idle.c b/mm/page_idle.c index 5c73a9b578da..e34ba04e22e2 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -46,11 +46,10 @@ static struct page *page_idle_get_page(unsigned long pfn) return page; } -static bool page_idle_clear_pte_refs_one(struct page *page, +static bool page_idle_clear_pte_refs_one(struct folio *folio, struct vm_area_struct *vma, unsigned long addr, void *arg) { - struct folio *folio = page_folio(page); DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, addr, 0); bool referenced = false; @@ -93,7 +92,7 @@ static void page_idle_clear_pte_refs(struct page *page) */ static const struct rmap_walk_control rwc = { .rmap_one = page_idle_clear_pte_refs_one, - .anon_lock = page_lock_anon_vma_read, + .anon_lock = folio_lock_anon_vma_read, }; bool need_lock; @@ -104,7 +103,7 @@ static void page_idle_clear_pte_refs(struct page *page) if (need_lock && !folio_trylock(folio)) return; - rmap_walk(&folio->page, (struct rmap_walk_control *)&rwc); + rmap_walk(folio, (struct rmap_walk_control *)&rwc); if (need_lock) folio_unlock(folio); diff --git a/mm/rmap.c b/mm/rmap.c index 09301aecf2fc..2cc97c64901e 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -107,15 +107,15 @@ static inline void anon_vma_free(struct anon_vma *anon_vma) VM_BUG_ON(atomic_read(&anon_vma->refcount)); /* - * Synchronize against page_lock_anon_vma_read() such that + * Synchronize against folio_lock_anon_vma_read() such that * we can safely hold the lock without the anon_vma getting * freed. * * Relies on the full mb implied by the atomic_dec_and_test() from * put_anon_vma() against the acquire barrier implied by - * down_read_trylock() from page_lock_anon_vma_read(). This orders: + * down_read_trylock() from folio_lock_anon_vma_read(). This orders: * - * page_lock_anon_vma_read() VS put_anon_vma() + * folio_lock_anon_vma_read() VS put_anon_vma() * down_read_trylock() atomic_dec_and_test() * LOCK MB * atomic_read() rwsem_is_locked() @@ -168,7 +168,7 @@ static void anon_vma_chain_link(struct vm_area_struct *vma, * allocate a new one. * * Anon-vma allocations are very subtle, because we may have - * optimistically looked up an anon_vma in page_lock_anon_vma_read() + * optimistically looked up an anon_vma in folio_lock_anon_vma_read() * and that may actually touch the rwsem even in the newly * allocated vma (it depends on RCU to make sure that the * anon_vma isn't actually destroyed). @@ -799,10 +799,9 @@ struct folio_referenced_arg { /* * arg: folio_referenced_arg will be passed */ -static bool folio_referenced_one(struct page *page, struct vm_area_struct *vma, - unsigned long address, void *arg) +static bool folio_referenced_one(struct folio *folio, + struct vm_area_struct *vma, unsigned long address, void *arg) { - struct folio *folio = page_folio(page); struct folio_referenced_arg *pra = arg; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); int referenced = 0; @@ -894,7 +893,7 @@ int folio_referenced(struct folio *folio, int is_locked, struct rmap_walk_control rwc = { .rmap_one = folio_referenced_one, .arg = (void *)&pra, - .anon_lock = page_lock_anon_vma_read, + .anon_lock = folio_lock_anon_vma_read, }; *vm_flags = 0; @@ -919,7 +918,7 @@ int folio_referenced(struct folio *folio, int is_locked, rwc.invalid_vma = invalid_folio_referenced_vma; } - rmap_walk(&folio->page, &rwc); + rmap_walk(folio, &rwc); *vm_flags = pra.vm_flags; if (we_locked) @@ -928,10 +927,9 @@ int folio_referenced(struct folio *folio, int is_locked, return pra.referenced; } -static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, +static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { - struct folio *folio = page_folio(page); DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_SYNC); struct mmu_notifier_range range; int *cleaned = arg; @@ -1025,7 +1023,7 @@ int folio_mkclean(struct folio *folio) if (!mapping) return 0; - rmap_walk(&folio->page, &rwc); + rmap_walk(folio, &rwc); return cleaned; } @@ -1410,10 +1408,9 @@ out: /* * @arg: enum ttu_flags will be passed to this argument */ -static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, +static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { - struct folio *folio = page_folio(page); struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); pte_t pteval; @@ -1667,9 +1664,9 @@ static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) return vma_is_temporary_stack(vma); } -static int page_not_mapped(struct page *page) +static int page_not_mapped(struct folio *folio) { - return !page_mapped(page); + return !folio_mapped(folio); } /** @@ -1689,13 +1686,13 @@ void try_to_unmap(struct folio *folio, enum ttu_flags flags) .rmap_one = try_to_unmap_one, .arg = (void *)flags, .done = page_not_mapped, - .anon_lock = page_lock_anon_vma_read, + .anon_lock = folio_lock_anon_vma_read, }; if (flags & TTU_RMAP_LOCKED) - rmap_walk_locked(&folio->page, &rwc); + rmap_walk_locked(folio, &rwc); else - rmap_walk(&folio->page, &rwc); + rmap_walk(folio, &rwc); } /* @@ -1704,10 +1701,9 @@ void try_to_unmap(struct folio *folio, enum ttu_flags flags) * If TTU_SPLIT_HUGE_PMD is specified any PMD mappings will be split into PTEs * containing migration entries. */ -static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, +static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { - struct folio *folio = page_folio(page); struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); pte_t pteval; @@ -1951,7 +1947,7 @@ void try_to_migrate(struct folio *folio, enum ttu_flags flags) .rmap_one = try_to_migrate_one, .arg = (void *)flags, .done = page_not_mapped, - .anon_lock = page_lock_anon_vma_read, + .anon_lock = folio_lock_anon_vma_read, }; /* @@ -1977,9 +1973,9 @@ void try_to_migrate(struct folio *folio, enum ttu_flags flags) rwc.invalid_vma = invalid_migration_vma; if (flags & TTU_RMAP_LOCKED) - rmap_walk_locked(&folio->page, &rwc); + rmap_walk_locked(folio, &rwc); else - rmap_walk(&folio->page, &rwc); + rmap_walk(folio, &rwc); } #ifdef CONFIG_DEVICE_PRIVATE @@ -1990,10 +1986,9 @@ struct make_exclusive_args { bool valid; }; -static bool page_make_device_exclusive_one(struct page *page, +static bool page_make_device_exclusive_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *priv) { - struct folio *folio = page_folio(page); struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); struct make_exclusive_args *args = priv; @@ -2098,7 +2093,7 @@ static bool folio_make_device_exclusive(struct folio *folio, struct rmap_walk_control rwc = { .rmap_one = page_make_device_exclusive_one, .done = page_not_mapped, - .anon_lock = page_lock_anon_vma_read, + .anon_lock = folio_lock_anon_vma_read, .arg = &args, }; @@ -2109,7 +2104,7 @@ static bool folio_make_device_exclusive(struct folio *folio, if (!folio_test_anon(folio)) return false; - rmap_walk(&folio->page, &rwc); + rmap_walk(folio, &rwc); return args.valid && !folio_mapcount(folio); } @@ -2177,17 +2172,16 @@ void __put_anon_vma(struct anon_vma *anon_vma) anon_vma_free(root); } -static struct anon_vma *rmap_walk_anon_lock(struct page *page, +static struct anon_vma *rmap_walk_anon_lock(struct folio *folio, struct rmap_walk_control *rwc) { - struct folio *folio = page_folio(page); struct anon_vma *anon_vma; if (rwc->anon_lock) - return rwc->anon_lock(page); + return rwc->anon_lock(folio); /* - * Note: remove_migration_ptes() cannot use page_lock_anon_vma_read() + * Note: remove_migration_ptes() cannot use folio_lock_anon_vma_read() * because that depends on page_mapped(); but not all its usages * are holding mmap_lock. Users without mmap_lock are required to * take a reference count to prevent the anon_vma disappearing @@ -2209,10 +2203,9 @@ static struct anon_vma *rmap_walk_anon_lock(struct page *page, * Find all the mappings of a page using the mapping pointer and the vma chains * contained in the anon_vma struct it points to. */ -static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, +static void rmap_walk_anon(struct folio *folio, struct rmap_walk_control *rwc, bool locked) { - struct folio *folio = page_folio(page); struct anon_vma *anon_vma; pgoff_t pgoff_start, pgoff_end; struct anon_vma_chain *avc; @@ -2222,17 +2215,17 @@ static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, /* anon_vma disappear under us? */ VM_BUG_ON_FOLIO(!anon_vma, folio); } else { - anon_vma = rmap_walk_anon_lock(page, rwc); + anon_vma = rmap_walk_anon_lock(folio, rwc); } if (!anon_vma) return; - pgoff_start = page_to_pgoff(page); - pgoff_end = pgoff_start + thp_nr_pages(page) - 1; + pgoff_start = folio_pgoff(folio); + pgoff_end = pgoff_start + folio_nr_pages(folio) - 1; anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff_start, pgoff_end) { struct vm_area_struct *vma = avc->vma; - unsigned long address = vma_address(page, vma); + unsigned long address = vma_address(&folio->page, vma); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); @@ -2240,9 +2233,9 @@ static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; - if (!rwc->rmap_one(page, vma, address, rwc->arg)) + if (!rwc->rmap_one(folio, vma, address, rwc->arg)) break; - if (rwc->done && rwc->done(page)) + if (rwc->done && rwc->done(folio)) break; } @@ -2258,10 +2251,10 @@ static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, * Find all the mappings of a page using the mapping pointer and the vma chains * contained in the address_space struct it points to. */ -static void rmap_walk_file(struct page *page, struct rmap_walk_control *rwc, +static void rmap_walk_file(struct folio *folio, struct rmap_walk_control *rwc, bool locked) { - struct address_space *mapping = page_mapping(page); + struct address_space *mapping = folio_mapping(folio); pgoff_t pgoff_start, pgoff_end; struct vm_area_struct *vma; @@ -2271,18 +2264,18 @@ static void rmap_walk_file(struct page *page, struct rmap_walk_control *rwc, * structure at mapping cannot be freed and reused yet, * so we can safely take mapping->i_mmap_rwsem. */ - VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (!mapping) return; - pgoff_start = page_to_pgoff(page); - pgoff_end = pgoff_start + thp_nr_pages(page) - 1; + pgoff_start = folio_pgoff(folio); + pgoff_end = pgoff_start + folio_nr_pages(folio) - 1; if (!locked) i_mmap_lock_read(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff_start, pgoff_end) { - unsigned long address = vma_address(page, vma); + unsigned long address = vma_address(&folio->page, vma); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); @@ -2290,9 +2283,9 @@ static void rmap_walk_file(struct page *page, struct rmap_walk_control *rwc, if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; - if (!rwc->rmap_one(page, vma, address, rwc->arg)) + if (!rwc->rmap_one(folio, vma, address, rwc->arg)) goto done; - if (rwc->done && rwc->done(page)) + if (rwc->done && rwc->done(folio)) goto done; } @@ -2301,25 +2294,25 @@ done: i_mmap_unlock_read(mapping); } -void rmap_walk(struct page *page, struct rmap_walk_control *rwc) +void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc) { - if (unlikely(PageKsm(page))) - rmap_walk_ksm(page, rwc); - else if (PageAnon(page)) - rmap_walk_anon(page, rwc, false); + if (unlikely(folio_test_ksm(folio))) + rmap_walk_ksm(folio, rwc); + else if (folio_test_anon(folio)) + rmap_walk_anon(folio, rwc, false); else - rmap_walk_file(page, rwc, false); + rmap_walk_file(folio, rwc, false); } /* Like rmap_walk, but caller holds relevant rmap lock */ -void rmap_walk_locked(struct page *page, struct rmap_walk_control *rwc) +void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc) { /* no ksm support for now */ - VM_BUG_ON_PAGE(PageKsm(page), page); - if (PageAnon(page)) - rmap_walk_anon(page, rwc, true); + VM_BUG_ON_FOLIO(folio_test_ksm(folio), folio); + if (folio_test_anon(folio)) + rmap_walk_anon(folio, rwc, true); else - rmap_walk_file(page, rwc, true); + rmap_walk_file(folio, rwc, true); } #ifdef CONFIG_HUGETLB_PAGE -- cgit v1.2.3 From 84fbbe21894bb9be8e16df408cbfbb9466fe396d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 29 Jan 2022 16:16:54 -0500 Subject: mm/rmap: Constify the rmap_walk_control argument The rmap walking functions do not modify the rmap_walk_control, and page_idle_clear_pte_refs() takes advantage of that to move construction of the rmap_walk_control to compile time. This lets us remove an unclean cast. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/ksm.h | 4 ++-- include/linux/rmap.h | 4 ++-- mm/ksm.c | 2 +- mm/page_idle.c | 2 +- mm/rmap.c | 14 +++++++------- 5 files changed, 13 insertions(+), 13 deletions(-) (limited to 'mm/rmap.c') diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 0b4f17418f64..0630e545f4cb 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -51,7 +51,7 @@ static inline void ksm_exit(struct mm_struct *mm) struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address); -void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); +void rmap_walk_ksm(struct folio *folio, const struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); #else /* !CONFIG_KSM */ @@ -79,7 +79,7 @@ static inline struct page *ksm_might_need_to_copy(struct page *page, } static inline void rmap_walk_ksm(struct folio *folio, - struct rmap_walk_control *rwc) + const struct rmap_walk_control *rwc) { } diff --git a/include/linux/rmap.h b/include/linux/rmap.h index a74d811c5b3f..17230c458341 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -292,8 +292,8 @@ struct rmap_walk_control { bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; -void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc); -void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc); +void rmap_walk(struct folio *folio, const struct rmap_walk_control *rwc); +void rmap_walk_locked(struct folio *folio, const struct rmap_walk_control *rwc); #else /* !CONFIG_MMU */ diff --git a/mm/ksm.c b/mm/ksm.c index dd737f925c04..eed2ff25a2fb 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -2588,7 +2588,7 @@ struct page *ksm_might_need_to_copy(struct page *page, return new_page; } -void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc) +void rmap_walk_ksm(struct folio *folio, const struct rmap_walk_control *rwc) { struct stable_node *stable_node; struct rmap_item *rmap_item; diff --git a/mm/page_idle.c b/mm/page_idle.c index e34ba04e22e2..fc0435abf909 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -103,7 +103,7 @@ static void page_idle_clear_pte_refs(struct page *page) if (need_lock && !folio_trylock(folio)) return; - rmap_walk(folio, (struct rmap_walk_control *)&rwc); + rmap_walk(folio, &rwc); if (need_lock) folio_unlock(folio); diff --git a/mm/rmap.c b/mm/rmap.c index 2cc97c64901e..8192cb5809bc 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -2173,7 +2173,7 @@ void __put_anon_vma(struct anon_vma *anon_vma) } static struct anon_vma *rmap_walk_anon_lock(struct folio *folio, - struct rmap_walk_control *rwc) + const struct rmap_walk_control *rwc) { struct anon_vma *anon_vma; @@ -2203,8 +2203,8 @@ static struct anon_vma *rmap_walk_anon_lock(struct folio *folio, * Find all the mappings of a page using the mapping pointer and the vma chains * contained in the anon_vma struct it points to. */ -static void rmap_walk_anon(struct folio *folio, struct rmap_walk_control *rwc, - bool locked) +static void rmap_walk_anon(struct folio *folio, + const struct rmap_walk_control *rwc, bool locked) { struct anon_vma *anon_vma; pgoff_t pgoff_start, pgoff_end; @@ -2251,8 +2251,8 @@ static void rmap_walk_anon(struct folio *folio, struct rmap_walk_control *rwc, * Find all the mappings of a page using the mapping pointer and the vma chains * contained in the address_space struct it points to. */ -static void rmap_walk_file(struct folio *folio, struct rmap_walk_control *rwc, - bool locked) +static void rmap_walk_file(struct folio *folio, + const struct rmap_walk_control *rwc, bool locked) { struct address_space *mapping = folio_mapping(folio); pgoff_t pgoff_start, pgoff_end; @@ -2294,7 +2294,7 @@ done: i_mmap_unlock_read(mapping); } -void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc) +void rmap_walk(struct folio *folio, const struct rmap_walk_control *rwc) { if (unlikely(folio_test_ksm(folio))) rmap_walk_ksm(folio, rwc); @@ -2305,7 +2305,7 @@ void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc) } /* Like rmap_walk, but caller holds relevant rmap lock */ -void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc) +void rmap_walk_locked(struct folio *folio, const struct rmap_walk_control *rwc) { /* no ksm support for now */ VM_BUG_ON_FOLIO(folio_test_ksm(folio), folio); -- cgit v1.2.3