diff options
Diffstat (limited to 'mm/rmap.c')
| -rw-r--r-- | mm/rmap.c | 1328 |
1 files changed, 751 insertions, 577 deletions
diff --git a/mm/rmap.c b/mm/rmap.c index 1a8bf76bfd0..22a4a7699cd 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -21,25 +21,24 @@ * Lock ordering in mm: * * inode->i_mutex (while writing or truncating, not reading or faulting) - * inode->i_alloc_sem (vmtruncate_range) * mm->mmap_sem * page->flags PG_locked (lock_page) - * mapping->i_mmap_lock - * anon_vma->lock + * mapping->i_mmap_mutex + * anon_vma->rwsem * mm->page_table_lock or pte_lock * zone->lru_lock (in mark_page_accessed, isolate_lru_page) * swap_lock (in swap_duplicate, swap_info_get) * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in __set_page_dirty_buffers) - * inode_lock (in set_page_dirty's __mark_inode_dirty) + * inode->i_lock (in set_page_dirty's __mark_inode_dirty) + * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) * sb_lock (within inode_lock in fs/fs-writeback.c) * mapping->tree_lock (widely used, in set_page_dirty, * in arch-dependent flush_dcache_mmap_lock, - * within inode_lock in __sync_single_inode) + * within bdi.wb->list_lock in __sync_single_inode) * - * (code doesn't rely on that order so it could be switched around) - * ->tasklist_lock - * anon_vma->lock (memory_failure, collect_procs_anon) + * anon_vma->rwsem,mapping->i_mutex (memory_failure, collect_procs_anon) + * ->tasklist_lock * pte map lock */ @@ -52,11 +51,12 @@ #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/rcupdate.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/migrate.h> #include <linux/hugetlb.h> +#include <linux/backing-dev.h> #include <asm/tlbflush.h> @@ -67,17 +67,54 @@ static struct kmem_cache *anon_vma_chain_cachep; static inline struct anon_vma *anon_vma_alloc(void) { - return kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); + struct anon_vma *anon_vma; + + anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); + if (anon_vma) { + atomic_set(&anon_vma->refcount, 1); + /* + * Initialise the anon_vma root to point to itself. If called + * from fork, the root will be reset to the parents anon_vma. + */ + anon_vma->root = anon_vma; + } + + return anon_vma; } -void anon_vma_free(struct anon_vma *anon_vma) +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 + * 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: + * + * page_lock_anon_vma_read() VS put_anon_vma() + * down_read_trylock() atomic_dec_and_test() + * LOCK MB + * atomic_read() rwsem_is_locked() + * + * LOCK should suffice since the actual taking of the lock must + * happen _before_ what follows. + */ + might_sleep(); + if (rwsem_is_locked(&anon_vma->root->rwsem)) { + anon_vma_lock_write(anon_vma); + anon_vma_unlock_write(anon_vma); + } + kmem_cache_free(anon_vma_cachep, anon_vma); } -static inline struct anon_vma_chain *anon_vma_chain_alloc(void) +static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp) { - return kmem_cache_alloc(anon_vma_chain_cachep, GFP_KERNEL); + return kmem_cache_alloc(anon_vma_chain_cachep, gfp); } static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) @@ -85,6 +122,16 @@ static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain); } +static void anon_vma_chain_link(struct vm_area_struct *vma, + struct anon_vma_chain *avc, + struct anon_vma *anon_vma) +{ + avc->vma = vma; + avc->anon_vma = anon_vma; + list_add(&avc->same_vma, &vma->anon_vma_chain); + anon_vma_interval_tree_insert(avc, &anon_vma->rb_root); +} + /** * anon_vma_prepare - attach an anon_vma to a memory region * @vma: the memory region in question @@ -94,13 +141,13 @@ static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) * anonymous pages mapped into it with that anon_vma. * * The common case will be that we already have one, but if - * if not we either need to find an adjacent mapping that we + * not we either need to find an adjacent mapping that we * can re-use the anon_vma from (very common when the only * reason for splitting a vma has been mprotect()), or we * 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() + * optimistically looked up an anon_vma in page_lock_anon_vma_read() * and that may actually touch the spinlock even in the newly * allocated vma (it depends on RCU to make sure that the * anon_vma isn't actually destroyed). @@ -122,7 +169,7 @@ int anon_vma_prepare(struct vm_area_struct *vma) struct mm_struct *mm = vma->vm_mm; struct anon_vma *allocated; - avc = anon_vma_chain_alloc(); + avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_enomem; @@ -133,30 +180,22 @@ int anon_vma_prepare(struct vm_area_struct *vma) if (unlikely(!anon_vma)) goto out_enomem_free_avc; allocated = anon_vma; - /* - * This VMA had no anon_vma yet. This anon_vma is - * the root of any anon_vma tree that might form. - */ - anon_vma->root = anon_vma; } - anon_vma_lock(anon_vma); + anon_vma_lock_write(anon_vma); /* page_table_lock to protect against threads */ spin_lock(&mm->page_table_lock); if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; - avc->anon_vma = anon_vma; - avc->vma = vma; - list_add(&avc->same_vma, &vma->anon_vma_chain); - list_add_tail(&avc->same_anon_vma, &anon_vma->head); + anon_vma_chain_link(vma, avc, anon_vma); allocated = NULL; avc = NULL; } spin_unlock(&mm->page_table_lock); - anon_vma_unlock(anon_vma); + anon_vma_unlock_write(anon_vma); if (unlikely(allocated)) - anon_vma_free(allocated); + put_anon_vma(allocated); if (unlikely(avc)) anon_vma_chain_free(avc); } @@ -168,17 +207,30 @@ int anon_vma_prepare(struct vm_area_struct *vma) return -ENOMEM; } -static void anon_vma_chain_link(struct vm_area_struct *vma, - struct anon_vma_chain *avc, - struct anon_vma *anon_vma) +/* + * This is a useful helper function for locking the anon_vma root as + * we traverse the vma->anon_vma_chain, looping over anon_vma's that + * have the same vma. + * + * Such anon_vma's should have the same root, so you'd expect to see + * just a single mutex_lock for the whole traversal. + */ +static inline struct anon_vma *lock_anon_vma_root(struct anon_vma *root, struct anon_vma *anon_vma) { - avc->vma = vma; - avc->anon_vma = anon_vma; - list_add(&avc->same_vma, &vma->anon_vma_chain); + struct anon_vma *new_root = anon_vma->root; + if (new_root != root) { + if (WARN_ON_ONCE(root)) + up_write(&root->rwsem); + root = new_root; + down_write(&root->rwsem); + } + return root; +} - anon_vma_lock(anon_vma); - list_add_tail(&avc->same_anon_vma, &anon_vma->head); - anon_vma_unlock(anon_vma); +static inline void unlock_anon_vma_root(struct anon_vma *root) +{ + if (root) + up_write(&root->rwsem); } /* @@ -188,13 +240,24 @@ static void anon_vma_chain_link(struct vm_area_struct *vma, int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) { struct anon_vma_chain *avc, *pavc; + struct anon_vma *root = NULL; list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) { - avc = anon_vma_chain_alloc(); - if (!avc) - goto enomem_failure; - anon_vma_chain_link(dst, avc, pavc->anon_vma); + struct anon_vma *anon_vma; + + avc = anon_vma_chain_alloc(GFP_NOWAIT | __GFP_NOWARN); + if (unlikely(!avc)) { + unlock_anon_vma_root(root); + root = NULL; + avc = anon_vma_chain_alloc(GFP_KERNEL); + if (!avc) + goto enomem_failure; + } + anon_vma = pavc->anon_vma; + root = lock_anon_vma_root(root, anon_vma); + anon_vma_chain_link(dst, avc, anon_vma); } + unlock_anon_vma_root(root); return 0; enomem_failure: @@ -227,7 +290,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) anon_vma = anon_vma_alloc(); if (!anon_vma) goto out_error; - avc = anon_vma_chain_alloc(); + avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_error_free_anon_vma; @@ -237,58 +300,63 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) */ anon_vma->root = pvma->anon_vma->root; /* - * With KSM refcounts, an anon_vma can stay around longer than the - * process it belongs to. The root anon_vma needs to be pinned - * until this anon_vma is freed, because the lock lives in the root. + * With refcounts, an anon_vma can stay around longer than the + * process it belongs to. The root anon_vma needs to be pinned until + * this anon_vma is freed, because the lock lives in the root. */ get_anon_vma(anon_vma->root); /* Mark this anon_vma as the one where our new (COWed) pages go. */ vma->anon_vma = anon_vma; + anon_vma_lock_write(anon_vma); anon_vma_chain_link(vma, avc, anon_vma); + anon_vma_unlock_write(anon_vma); return 0; out_error_free_anon_vma: - anon_vma_free(anon_vma); + put_anon_vma(anon_vma); out_error: unlink_anon_vmas(vma); return -ENOMEM; } -static void anon_vma_unlink(struct anon_vma_chain *anon_vma_chain) +void unlink_anon_vmas(struct vm_area_struct *vma) { - struct anon_vma *anon_vma = anon_vma_chain->anon_vma; - int empty; + struct anon_vma_chain *avc, *next; + struct anon_vma *root = NULL; - /* If anon_vma_fork fails, we can get an empty anon_vma_chain. */ - if (!anon_vma) - return; + /* + * Unlink each anon_vma chained to the VMA. This list is ordered + * from newest to oldest, ensuring the root anon_vma gets freed last. + */ + list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { + struct anon_vma *anon_vma = avc->anon_vma; - anon_vma_lock(anon_vma); - list_del(&anon_vma_chain->same_anon_vma); + root = lock_anon_vma_root(root, anon_vma); + anon_vma_interval_tree_remove(avc, &anon_vma->rb_root); - /* We must garbage collect the anon_vma if it's empty */ - empty = list_empty(&anon_vma->head) && !anonvma_external_refcount(anon_vma); - anon_vma_unlock(anon_vma); + /* + * Leave empty anon_vmas on the list - we'll need + * to free them outside the lock. + */ + if (RB_EMPTY_ROOT(&anon_vma->rb_root)) + continue; - if (empty) { - /* We no longer need the root anon_vma */ - if (anon_vma->root != anon_vma) - drop_anon_vma(anon_vma->root); - anon_vma_free(anon_vma); + list_del(&avc->same_vma); + anon_vma_chain_free(avc); } -} - -void unlink_anon_vmas(struct vm_area_struct *vma) -{ - struct anon_vma_chain *avc, *next; + unlock_anon_vma_root(root); /* - * Unlink each anon_vma chained to the VMA. This list is ordered - * from newest to oldest, ensuring the root anon_vma gets freed last. + * Iterate the list once more, it now only contains empty and unlinked + * anon_vmas, destroy them. Could not do before due to __put_anon_vma() + * needing to write-acquire the anon_vma->root->rwsem. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { - anon_vma_unlink(avc); + struct anon_vma *anon_vma = avc->anon_vma; + + put_anon_vma(anon_vma); + list_del(&avc->same_vma); anon_vma_chain_free(avc); } @@ -298,9 +366,9 @@ static void anon_vma_ctor(void *data) { struct anon_vma *anon_vma = data; - spin_lock_init(&anon_vma->lock); - anonvma_external_refcount_init(anon_vma); - INIT_LIST_HEAD(&anon_vma->head); + init_rwsem(&anon_vma->rwsem); + atomic_set(&anon_vma->refcount, 0); + anon_vma->rb_root = RB_ROOT; } void __init anon_vma_init(void) @@ -311,12 +379,31 @@ void __init anon_vma_init(void) } /* - * Getting a lock on a stable anon_vma from a page off the LRU is - * tricky: page_lock_anon_vma rely on RCU to guard against the races. + * Getting a lock on a stable anon_vma from a page off the LRU is tricky! + * + * Since there is no serialization what so ever against page_remove_rmap() + * the best this function can do is return a locked anon_vma that might + * have been relevant to this page. + * + * The page might have been remapped to a different anon_vma or the anon_vma + * returned may already be freed (and even reused). + * + * In case it was remapped to a different anon_vma, the new anon_vma will be a + * child of the old anon_vma, and the anon_vma lifetime rules will therefore + * ensure that any anon_vma obtained from the page will still be valid for as + * long as we observe page_mapped() [ hence all those page_mapped() tests ]. + * + * All users of this function must be very careful when walking the anon_vma + * chain and verify that the page in question is indeed mapped in it + * [ something equivalent to page_mapped_in_vma() ]. + * + * Since anon_vma's slab is DESTROY_BY_RCU and we know from page_remove_rmap() + * that the anon_vma pointer from page->mapping is valid if there is a + * mapcount, we can dereference the anon_vma after observing those. */ -struct anon_vma *__page_lock_anon_vma(struct page *page) +struct anon_vma *page_get_anon_vma(struct page *page) { - struct anon_vma *anon_vma, *root_anon_vma; + struct anon_vma *anon_vma = NULL; unsigned long anon_mapping; rcu_read_lock(); @@ -327,52 +414,121 @@ struct anon_vma *__page_lock_anon_vma(struct page *page) goto out; anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); - root_anon_vma = ACCESS_ONCE(anon_vma->root); - spin_lock(&root_anon_vma->lock); + if (!atomic_inc_not_zero(&anon_vma->refcount)) { + anon_vma = NULL; + goto out; + } /* * If this page is still mapped, then its anon_vma cannot have been - * freed. But if it has been unmapped, we have no security against - * the anon_vma structure being freed and reused (for another anon_vma: - * SLAB_DESTROY_BY_RCU guarantees that - so the spin_lock above cannot - * corrupt): with anon_vma_prepare() or anon_vma_fork() redirecting - * anon_vma->root before page_unlock_anon_vma() is called to unlock. + * freed. But if it has been unmapped, we have no security against the + * anon_vma structure being freed and reused (for another anon_vma: + * SLAB_DESTROY_BY_RCU guarantees that - so the atomic_inc_not_zero() + * above cannot corrupt). */ - if (page_mapped(page)) - return anon_vma; - - spin_unlock(&root_anon_vma->lock); + if (!page_mapped(page)) { + rcu_read_unlock(); + put_anon_vma(anon_vma); + return NULL; + } out: rcu_read_unlock(); - return NULL; + + return anon_vma; } -void page_unlock_anon_vma(struct anon_vma *anon_vma) - __releases(&anon_vma->root->lock) - __releases(RCU) +/* + * Similar to page_get_anon_vma() except it locks the anon_vma. + * + * Its a little more complex as it tries to keep the fast path to a single + * 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) { - anon_vma_unlock(anon_vma); + struct anon_vma *anon_vma = NULL; + struct anon_vma *root_anon_vma; + unsigned long anon_mapping; + + rcu_read_lock(); + anon_mapping = (unsigned long) ACCESS_ONCE(page->mapping); + if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) + goto out; + if (!page_mapped(page)) + goto out; + + anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); + root_anon_vma = ACCESS_ONCE(anon_vma->root); + if (down_read_trylock(&root_anon_vma->rwsem)) { + /* + * If the page 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)) { + up_read(&root_anon_vma->rwsem); + anon_vma = NULL; + } + goto out; + } + + /* trylock failed, we got to sleep */ + if (!atomic_inc_not_zero(&anon_vma->refcount)) { + anon_vma = NULL; + goto out; + } + + if (!page_mapped(page)) { + rcu_read_unlock(); + put_anon_vma(anon_vma); + return NULL; + } + + /* we pinned the anon_vma, its safe to sleep */ rcu_read_unlock(); + anon_vma_lock_read(anon_vma); + + if (atomic_dec_and_test(&anon_vma->refcount)) { + /* + * Oops, we held the last refcount, release the lock + * and bail -- can't simply use put_anon_vma() because + * we'll deadlock on the anon_vma_lock_write() recursion. + */ + anon_vma_unlock_read(anon_vma); + __put_anon_vma(anon_vma); + anon_vma = NULL; + } + + return anon_vma; + +out: + rcu_read_unlock(); + return anon_vma; +} + +void page_unlock_anon_vma_read(struct anon_vma *anon_vma) +{ + anon_vma_unlock_read(anon_vma); } /* * At what user virtual address is page expected in @vma? - * Returns virtual address or -EFAULT if page's index/offset is not - * within the range mapped the @vma. */ static inline unsigned long +__vma_address(struct page *page, struct vm_area_struct *vma) +{ + pgoff_t pgoff = page_to_pgoff(page); + return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); +} + +inline unsigned long vma_address(struct page *page, struct vm_area_struct *vma) { - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - unsigned long address; + unsigned long address = __vma_address(page, vma); + + /* page should be within @vma mapping range */ + VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end); - if (unlikely(is_vm_hugetlb_page(vma))) - pgoff = page->index << huge_page_order(page_hstate(page)); - address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); - if (unlikely(address < vma->vm_start || address >= vma->vm_end)) { - /* page should be within @vma mapping range */ - return -EFAULT; - } return address; } @@ -382,6 +538,7 @@ vma_address(struct page *page, struct vm_area_struct *vma) */ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) { + unsigned long address; if (PageAnon(page)) { struct anon_vma *page__anon_vma = page_anon_vma(page); /* @@ -397,7 +554,38 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) return -EFAULT; } else return -EFAULT; - return vma_address(page, vma); + address = __vma_address(page, vma); + if (unlikely(address < vma->vm_start || address >= vma->vm_end)) + return -EFAULT; + return address; +} + +pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd = NULL; + pmd_t pmde; + + pgd = pgd_offset(mm, address); + if (!pgd_present(*pgd)) + goto out; + + pud = pud_offset(pgd, address); + if (!pud_present(*pud)) + goto out; + + pmd = pmd_offset(pud, address); + /* + * Some THP functions use the sequence pmdp_clear_flush(), set_pmd_at() + * without holding anon_vma lock for write. So when looking for a + * genuine pmde (in which to find pte), test present and !THP together. + */ + pmde = ACCESS_ONCE(*pmd); + if (!pmd_present(pmde) || pmd_trans_huge(pmde)) + pmd = NULL; +out: + return pmd; } /* @@ -412,28 +600,22 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) pte_t *__page_check_address(struct page *page, struct mm_struct *mm, unsigned long address, spinlock_t **ptlp, int sync) { - pgd_t *pgd; - pud_t *pud; pmd_t *pmd; pte_t *pte; spinlock_t *ptl; if (unlikely(PageHuge(page))) { + /* when pud is not present, pte will be NULL */ pte = huge_pte_offset(mm, address); - ptl = &mm->page_table_lock; + if (!pte) + return NULL; + + ptl = huge_pte_lockptr(page_hstate(page), mm, pte); goto check; } - pgd = pgd_offset(mm, address); - if (!pgd_present(*pgd)) - return NULL; - - pud = pud_offset(pgd, address); - if (!pud_present(*pud)) - return NULL; - - pmd = pmd_offset(pud, address); - if (!pmd_present(*pmd)) + pmd = mm_find_pmd(mm, address); + if (!pmd) return NULL; pte = pte_offset_map(pmd, address); @@ -469,8 +651,8 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) pte_t *pte; spinlock_t *ptl; - address = vma_address(page, vma); - if (address == -EFAULT) /* out of vma range */ + address = __vma_address(page, vma); + if (unlikely(address < vma->vm_start || address >= vma->vm_end)) return 0; pte = page_check_address(page, vma->vm_mm, address, &ptl, 1); if (!pte) /* the page is not in this mm */ @@ -480,171 +662,104 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) return 1; } +struct page_referenced_arg { + int mapcount; + int referenced; + unsigned long vm_flags; + struct mem_cgroup *memcg; +}; /* - * Subfunctions of page_referenced: page_referenced_one called - * repeatedly from either page_referenced_anon or page_referenced_file. + * arg: page_referenced_arg will be passed */ -int page_referenced_one(struct page *page, struct vm_area_struct *vma, - unsigned long address, unsigned int *mapcount, - unsigned long *vm_flags) +static int page_referenced_one(struct page *page, struct vm_area_struct *vma, + unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; - pte_t *pte; spinlock_t *ptl; int referenced = 0; + struct page_referenced_arg *pra = arg; - pte = page_check_address(page, mm, address, &ptl, 0); - if (!pte) - goto out; - - /* - * Don't want to elevate referenced for mlocked page that gets this far, - * in order that it progresses to try_to_unmap and is moved to the - * unevictable list. - */ - if (vma->vm_flags & VM_LOCKED) { - *mapcount = 1; /* break early from loop */ - *vm_flags |= VM_LOCKED; - goto out_unmap; - } + if (unlikely(PageTransHuge(page))) { + pmd_t *pmd; - if (ptep_clear_flush_young_notify(vma, address, pte)) { /* - * Don't treat a reference through a sequentially read - * mapping as such. If the page 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. + * rmap might return false positives; we must filter + * these out using page_check_address_pmd(). */ - if (likely(!VM_SequentialReadHint(vma))) - referenced++; - } - - /* Pretend the page is referenced if the task has the - swap token and is in the middle of a page fault. */ - if (mm != current->mm && has_swap_token(mm) && - rwsem_is_locked(&mm->mmap_sem)) - referenced++; - -out_unmap: - (*mapcount)--; - pte_unmap_unlock(pte, ptl); + pmd = page_check_address_pmd(page, mm, address, + PAGE_CHECK_ADDRESS_PMD_FLAG, &ptl); + if (!pmd) + return SWAP_AGAIN; - if (referenced) - *vm_flags |= vma->vm_flags; -out: - return referenced; -} - -static int page_referenced_anon(struct page *page, - struct mem_cgroup *mem_cont, - unsigned long *vm_flags) -{ - unsigned int mapcount; - struct anon_vma *anon_vma; - struct anon_vma_chain *avc; - int referenced = 0; + if (vma->vm_flags & VM_LOCKED) { + spin_unlock(ptl); + pra->vm_flags |= VM_LOCKED; + return SWAP_FAIL; /* To break the loop */ + } - anon_vma = page_lock_anon_vma(page); - if (!anon_vma) - return referenced; + /* go ahead even if the pmd is pmd_trans_splitting() */ + if (pmdp_clear_flush_young_notify(vma, address, pmd)) + referenced++; + spin_unlock(ptl); + } else { + pte_t *pte; - mapcount = page_mapcount(page); - list_for_each_entry(avc, &anon_vma->head, same_anon_vma) { - struct vm_area_struct *vma = avc->vma; - unsigned long address = vma_address(page, vma); - if (address == -EFAULT) - continue; /* - * If we are reclaiming on behalf of a cgroup, skip - * counting on behalf of references from different - * cgroups + * rmap might return false positives; we must filter + * these out using page_check_address(). */ - if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont)) - continue; - referenced += page_referenced_one(page, vma, address, - &mapcount, vm_flags); - if (!mapcount) - break; - } + pte = page_check_address(page, mm, address, &ptl, 0); + if (!pte) + return SWAP_AGAIN; - page_unlock_anon_vma(anon_vma); - return referenced; -} + if (vma->vm_flags & VM_LOCKED) { + pte_unmap_unlock(pte, ptl); + pra->vm_flags |= VM_LOCKED; + return SWAP_FAIL; /* To break the loop */ + } -/** - * page_referenced_file - referenced check for object-based rmap - * @page: the page we're checking references on. - * @mem_cont: target memory controller - * @vm_flags: collect encountered vma->vm_flags who actually referenced the page - * - * For an object-based mapped page, find all the places it is mapped and - * check/clear the referenced flag. This is done by following the page->mapping - * pointer, then walking the chain of vmas it holds. It returns the number - * of references it found. - * - * This function is only called from page_referenced for object-based pages. - */ -static int page_referenced_file(struct page *page, - struct mem_cgroup *mem_cont, - unsigned long *vm_flags) -{ - unsigned int mapcount; - struct address_space *mapping = page->mapping; - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - struct vm_area_struct *vma; - struct prio_tree_iter iter; - int referenced = 0; + if (ptep_clear_flush_young_notify(vma, address, pte)) { + /* + * Don't treat a reference through a sequentially read + * mapping as such. If the page 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. + */ + if (likely(!(vma->vm_flags & VM_SEQ_READ))) + referenced++; + } + pte_unmap_unlock(pte, ptl); + } - /* - * The caller's checks on page->mapping and !PageAnon have made - * sure that this is a file page: the check for page->mapping - * excludes the case just before it gets set on an anon page. - */ - BUG_ON(PageAnon(page)); + if (referenced) { + pra->referenced++; + pra->vm_flags |= vma->vm_flags; + } - /* - * The page lock not only makes sure that page->mapping cannot - * suddenly be NULLified by truncation, it makes sure that the - * structure at mapping cannot be freed and reused yet, - * so we can safely take mapping->i_mmap_lock. - */ - BUG_ON(!PageLocked(page)); + pra->mapcount--; + if (!pra->mapcount) + return SWAP_SUCCESS; /* To break the loop */ - spin_lock(&mapping->i_mmap_lock); + return SWAP_AGAIN; +} - /* - * i_mmap_lock does not stabilize mapcount at all, but mapcount - * is more likely to be accurate if we note it after spinning. - */ - mapcount = page_mapcount(page); +static bool invalid_page_referenced_vma(struct vm_area_struct *vma, void *arg) +{ + struct page_referenced_arg *pra = arg; + struct mem_cgroup *memcg = pra->memcg; - vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { - unsigned long address = vma_address(page, vma); - if (address == -EFAULT) - continue; - /* - * If we are reclaiming on behalf of a cgroup, skip - * counting on behalf of references from different - * cgroups - */ - if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont)) - continue; - referenced += page_referenced_one(page, vma, address, - &mapcount, vm_flags); - if (!mapcount) - break; - } + if (!mm_match_cgroup(vma->vm_mm, memcg)) + return true; - spin_unlock(&mapping->i_mmap_lock); - return referenced; + return false; } /** * page_referenced - test if the page was referenced * @page: the page to test * @is_locked: caller holds lock on the page - * @mem_cont: target memory controller + * @memcg: target memory cgroup * @vm_flags: collect encountered vma->vm_flags who actually referenced the page * * Quick test_and_clear_referenced for all mappings to a page, @@ -652,47 +767,60 @@ static int page_referenced_file(struct page *page, */ int page_referenced(struct page *page, int is_locked, - struct mem_cgroup *mem_cont, + struct mem_cgroup *memcg, unsigned long *vm_flags) { - int referenced = 0; + int ret; int we_locked = 0; + struct page_referenced_arg pra = { + .mapcount = page_mapcount(page), + .memcg = memcg, + }; + struct rmap_walk_control rwc = { + .rmap_one = page_referenced_one, + .arg = (void *)&pra, + .anon_lock = page_lock_anon_vma_read, + }; *vm_flags = 0; - if (page_mapped(page) && page_rmapping(page)) { - if (!is_locked && (!PageAnon(page) || PageKsm(page))) { - we_locked = trylock_page(page); - if (!we_locked) { - referenced++; - goto out; - } - } - if (unlikely(PageKsm(page))) - referenced += page_referenced_ksm(page, mem_cont, - vm_flags); - else if (PageAnon(page)) - referenced += page_referenced_anon(page, mem_cont, - vm_flags); - else if (page->mapping) - referenced += page_referenced_file(page, mem_cont, - vm_flags); - if (we_locked) - unlock_page(page); + if (!page_mapped(page)) + return 0; + + if (!page_rmapping(page)) + return 0; + + if (!is_locked && (!PageAnon(page) || PageKsm(page))) { + we_locked = trylock_page(page); + if (!we_locked) + return 1; } -out: - if (page_test_and_clear_young(page)) - referenced++; - return referenced; + /* + * If we are reclaiming on behalf of a cgroup, skip + * counting on behalf of references from different + * cgroups + */ + if (memcg) { + rwc.invalid_vma = invalid_page_referenced_vma; + } + + ret = rmap_walk(page, &rwc); + *vm_flags = pra.vm_flags; + + if (we_locked) + unlock_page(page); + + return pra.referenced; } static int page_mkclean_one(struct page *page, struct vm_area_struct *vma, - unsigned long address) + unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; pte_t *pte; spinlock_t *ptl; int ret = 0; + int *cleaned = arg; pte = page_check_address(page, mm, address, &ptl, 1); if (!pte) @@ -702,7 +830,7 @@ static int page_mkclean_one(struct page *page, struct vm_area_struct *vma, pte_t entry; flush_cache_page(vma, address, pte_pfn(*pte)); - entry = ptep_clear_flush_notify(vma, address, pte); + entry = ptep_clear_flush(vma, address, pte); entry = pte_wrprotect(entry); entry = pte_mkclean(entry); set_pte_at(mm, address, pte, entry); @@ -710,50 +838,45 @@ static int page_mkclean_one(struct page *page, struct vm_area_struct *vma, } pte_unmap_unlock(pte, ptl); + + if (ret) { + mmu_notifier_invalidate_page(mm, address); + (*cleaned)++; + } out: - return ret; + return SWAP_AGAIN; } -static int page_mkclean_file(struct address_space *mapping, struct page *page) +static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg) { - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - struct vm_area_struct *vma; - struct prio_tree_iter iter; - int ret = 0; - - BUG_ON(PageAnon(page)); + if (vma->vm_flags & VM_SHARED) + return false; - spin_lock(&mapping->i_mmap_lock); - vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { - if (vma->vm_flags & VM_SHARED) { - unsigned long address = vma_address(page, vma); - if (address == -EFAULT) - continue; - ret += page_mkclean_one(page, vma, address); - } - } - spin_unlock(&mapping->i_mmap_lock); - return ret; + return true; } int page_mkclean(struct page *page) { - int ret = 0; + int cleaned = 0; + struct address_space *mapping; + struct rmap_walk_control rwc = { + .arg = (void *)&cleaned, + .rmap_one = page_mkclean_one, + .invalid_vma = invalid_mkclean_vma, + }; BUG_ON(!PageLocked(page)); - if (page_mapped(page)) { - struct address_space *mapping = page_mapping(page); - if (mapping) { - ret = page_mkclean_file(mapping, page); - if (page_test_dirty(page)) { - page_clear_dirty(page, 1); - ret = 1; - } - } - } + if (!page_mapped(page)) + return 0; - return ret; + mapping = page_mapping(page); + if (!mapping) + return 0; + + rmap_walk(page, &rwc); + + return cleaned; } EXPORT_SYMBOL_GPL(page_mkclean); @@ -773,9 +896,9 @@ void page_move_anon_rmap(struct page *page, { struct anon_vma *anon_vma = vma->anon_vma; - VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON(!anon_vma); - VM_BUG_ON(page->index != linear_page_index(vma, address)); + VM_BUG_ON_PAGE(page->index != linear_page_index(vma, address), page); anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; page->mapping = (struct address_space *) anon_vma; @@ -864,13 +987,24 @@ void do_page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address, int exclusive) { int first = atomic_inc_and_test(&page->_mapcount); - if (first) - __inc_zone_page_state(page, NR_ANON_PAGES); + if (first) { + /* + * We use the irq-unsafe __{inc|mod}_zone_page_stat because + * these counters are not modified in interrupt context, and + * pte lock(a spinlock) is held, which implies preemption + * disabled. + */ + if (PageTransHuge(page)) + __inc_zone_page_state(page, + NR_ANON_TRANSPARENT_HUGEPAGES); + __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, + hpage_nr_pages(page)); + } if (unlikely(PageKsm(page))) return; - VM_BUG_ON(!PageLocked(page)); - VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end); + VM_BUG_ON_PAGE(!PageLocked(page), page); + /* address might be in next vma when migration races vma_adjust */ if (first) __page_set_anon_rmap(page, vma, address, exclusive); else @@ -893,12 +1027,30 @@ void page_add_new_anon_rmap(struct page *page, VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end); SetPageSwapBacked(page); atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */ - __inc_zone_page_state(page, NR_ANON_PAGES); + if (PageTransHuge(page)) + __inc_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); + __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, + hpage_nr_pages(page)); __page_set_anon_rmap(page, vma, address, 1); - if (page_evictable(page, vma)) - lru_cache_add_lru(page, LRU_ACTIVE_ANON); - else - add_page_to_unevictable_list(page); + + VM_BUG_ON_PAGE(PageLRU(page), page); + if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED)) { + SetPageActive(page); + lru_cache_add(page); + return; + } + + if (!TestSetPageMlocked(page)) { + /* + * We use the irq-unsafe __mod_zone_page_stat 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, + hpage_nr_pages(page)); + count_vm_event(UNEVICTABLE_PGMLOCKED); + } + add_page_to_unevictable_list(page); } /** @@ -909,10 +1061,15 @@ void page_add_new_anon_rmap(struct page *page, */ void page_add_file_rmap(struct page *page) { + bool locked; + unsigned long flags; + + mem_cgroup_begin_update_page_stat(page, &locked, &flags); if (atomic_inc_and_test(&page->_mapcount)) { __inc_zone_page_state(page, NR_FILE_MAPPED); - mem_cgroup_update_file_mapped(page, 1); + mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED); } + mem_cgroup_end_update_page_stat(page, &locked, &flags); } /** @@ -923,34 +1080,47 @@ void page_add_file_rmap(struct page *page) */ void page_remove_rmap(struct page *page) { - /* page still mapped by someone else? */ - if (!atomic_add_negative(-1, &page->_mapcount)) - return; + bool anon = PageAnon(page); + bool locked; + unsigned long flags; /* - * Now that the last pte has gone, s390 must transfer dirty - * flag from storage key to struct page. We can usually skip - * this if the page is anon, so about to be freed; but perhaps - * not if it's in swapcache - there might be another pte slot - * containing the swap entry, but page not yet written to swap. + * The anon case has no mem_cgroup page_stat to update; but may + * uncharge_page() below, where the lock ordering can deadlock if + * we hold the lock against page_stat move: so avoid it on anon. */ - if ((!PageAnon(page) || PageSwapCache(page)) && page_test_dirty(page)) { - page_clear_dirty(page, 1); - set_page_dirty(page); - } + if (!anon) + mem_cgroup_begin_update_page_stat(page, &locked, &flags); + + /* page still mapped by someone else? */ + if (!atomic_add_negative(-1, &page->_mapcount)) + goto out; + /* * Hugepages are not counted in NR_ANON_PAGES nor NR_FILE_MAPPED * and not charged by memcg for now. + * + * We use the irq-unsafe __{inc|mod}_zone_page_stat because + * these counters are not modified in interrupt context, and + * these counters are not modified in interrupt context, and + * pte lock(a spinlock) is held, which implies preemption disabled. */ if (unlikely(PageHuge(page))) - return; - if (PageAnon(page)) { + goto out; + if (anon) { mem_cgroup_uncharge_page(page); - __dec_zone_page_state(page, NR_ANON_PAGES); + if (PageTransHuge(page)) + __dec_zone_page_state(page, + NR_ANON_TRANSPARENT_HUGEPAGES); + __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, + -hpage_nr_pages(page)); } else { __dec_zone_page_state(page, NR_FILE_MAPPED); - mem_cgroup_update_file_mapped(page, -1); + mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED); + mem_cgroup_end_update_page_stat(page, &locked, &flags); } + if (unlikely(PageMlocked(page))) + clear_page_mlock(page); /* * It would be tidy to reset the PageAnon mapping here, * but that might overwrite a racing page_add_anon_rmap @@ -960,20 +1130,24 @@ void page_remove_rmap(struct page *page) * Leaving it set also helps swapoff to reinstate ptes * faster for those pages still in swapcache. */ + return; +out: + if (!anon) + mem_cgroup_end_update_page_stat(page, &locked, &flags); } /* - * Subfunctions of try_to_unmap: try_to_unmap_one called - * repeatedly from either try_to_unmap_anon or try_to_unmap_file. + * @arg: enum ttu_flags will be passed to this argument */ -int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, - unsigned long address, enum ttu_flags flags) +static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, + unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; pte_t *pte; pte_t pteval; spinlock_t *ptl; int ret = SWAP_AGAIN; + enum ttu_flags flags = (enum ttu_flags)arg; pte = page_check_address(page, mm, address, &ptl, 0); if (!pte) @@ -988,7 +1162,7 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, if (vma->vm_flags & VM_LOCKED) goto out_mlock; - if (TTU_ACTION(flags) == TTU_MUNLOCK) + if (flags & TTU_MUNLOCK) goto out_unmap; } if (!(flags & TTU_IGNORE_ACCESS)) { @@ -1000,7 +1174,7 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, /* Nuke the page table entry. */ flush_cache_page(vma, address, page_to_pfn(page)); - pteval = ptep_clear_flush_notify(vma, address, pte); + pteval = ptep_clear_flush(vma, address, pte); /* Move the dirty bit to the physical page now the pte is gone. */ if (pte_dirty(pteval)) @@ -1010,14 +1184,27 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, update_hiwater_rss(mm); if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) { + if (!PageHuge(page)) { + if (PageAnon(page)) + dec_mm_counter(mm, MM_ANONPAGES); + else + dec_mm_counter(mm, MM_FILEPAGES); + } + set_pte_at(mm, address, pte, + swp_entry_to_pte(make_hwpoison_entry(page))); + } else if (pte_unused(pteval)) { + /* + * The guest indicated that the page content is of no + * interest anymore. Simply discard the pte, vmscan + * will take care of the rest. + */ if (PageAnon(page)) dec_mm_counter(mm, MM_ANONPAGES); else dec_mm_counter(mm, MM_FILEPAGES); - set_pte_at(mm, address, pte, - swp_entry_to_pte(make_hwpoison_entry(page))); } else if (PageAnon(page)) { swp_entry_t entry = { .val = page_private(page) }; + pte_t swp_pte; if (PageSwapCache(page)) { /* @@ -1037,18 +1224,22 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } dec_mm_counter(mm, MM_ANONPAGES); inc_mm_counter(mm, MM_SWAPENTS); - } else if (PAGE_MIGRATION) { + } else if (IS_ENABLED(CONFIG_MIGRATION)) { /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ - BUG_ON(TTU_ACTION(flags) != TTU_MIGRATION); + BUG_ON(!(flags & TTU_MIGRATION)); entry = make_migration_entry(page, pte_write(pteval)); } - set_pte_at(mm, address, pte, swp_entry_to_pte(entry)); + swp_pte = swp_entry_to_pte(entry); + if (pte_soft_dirty(pteval)) + swp_pte = pte_swp_mksoft_dirty(swp_pte); + set_pte_at(mm, address, pte, swp_pte); BUG_ON(pte_file(*pte)); - } else if (PAGE_MIGRATION && (TTU_ACTION(flags) == TTU_MIGRATION)) { + } else if (IS_ENABLED(CONFIG_MIGRATION) && + (flags & TTU_MIGRATION)) { /* Establish migration entry for a file page */ swp_entry_t entry; entry = make_migration_entry(page, pte_write(pteval)); @@ -1061,6 +1252,8 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, out_unmap: pte_unmap_unlock(pte, ptl); + if (ret != SWAP_FAIL && !(flags & TTU_MUNLOCK)) + mmu_notifier_invalidate_page(mm, address); out: return ret; @@ -1071,7 +1264,7 @@ out_mlock: /* * We need mmap_sem locking, Otherwise VM_LOCKED check makes * unstable result and race. Plus, We can't wait here because - * we now hold anon_vma->lock or mapping->i_mmap_lock. + * we now hold anon_vma->rwsem or mapping->i_mmap_mutex. * if trylock failed, the page remain in evictable lru and later * vmscan could retry to move the page to unevictable lru if the * page is actually mlocked. @@ -1117,14 +1310,14 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, struct vm_area_struct *vma, struct page *check_page) { struct mm_struct *mm = vma->vm_mm; - pgd_t *pgd; - pud_t *pud; pmd_t *pmd; pte_t *pte; pte_t pteval; spinlock_t *ptl; struct page *page; unsigned long address; + unsigned long mmun_start; /* For mmu_notifiers */ + unsigned long mmun_end; /* For mmu_notifiers */ unsigned long end; int ret = SWAP_AGAIN; int locked_vma = 0; @@ -1136,17 +1329,13 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, if (end > vma->vm_end) end = vma->vm_end; - pgd = pgd_offset(mm, address); - if (!pgd_present(*pgd)) - return ret; - - pud = pud_offset(pgd, address); - if (!pud_present(*pud)) + pmd = mm_find_pmd(mm, address); + if (!pmd) return ret; - pmd = pmd_offset(pud, address); - if (!pmd_present(*pmd)) - return ret; + mmun_start = address; + mmun_end = end; + mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); /* * If we can acquire the mmap_sem for read, and vma is VM_LOCKED, @@ -1170,9 +1359,19 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, BUG_ON(!page || PageAnon(page)); if (locked_vma) { - mlock_vma_page(page); /* no-op if already mlocked */ - if (page == check_page) + if (page == check_page) { + /* we know we have check_page locked */ + mlock_vma_page(page); ret = SWAP_MLOCK; + } else if (trylock_page(page)) { + /* + * If we can lock the page, perform mlock. + * Otherwise leave the page alone, it will be + * eventually encountered again later. + */ + mlock_vma_page(page); + unlock_page(page); + } continue; /* don't unmap */ } @@ -1181,11 +1380,15 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, /* Nuke the page table entry. */ flush_cache_page(vma, address, pte_pfn(*pte)); - pteval = ptep_clear_flush_notify(vma, address, pte); + pteval = ptep_clear_flush(vma, address, pte); /* If nonlinear, store the file page offset in the pte. */ - if (page->index != linear_page_index(vma, address)) - set_pte_at(mm, address, pte, pgoff_to_pte(page->index)); + if (page->index != linear_page_index(vma, address)) { + pte_t ptfile = pgoff_to_pte(page->index); + if (pte_soft_dirty(pteval)) + ptfile = pte_file_mksoft_dirty(ptfile); + set_pte_at(mm, address, pte, ptfile); + } /* Move the dirty bit to the physical page now the pte is gone. */ if (pte_dirty(pteval)) @@ -1197,129 +1400,25 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, (*mapcount)--; } pte_unmap_unlock(pte - 1, ptl); + mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); if (locked_vma) up_read(&vma->vm_mm->mmap_sem); return ret; } -static bool is_vma_temporary_stack(struct vm_area_struct *vma) -{ - int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); - - if (!maybe_stack) - return false; - - if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) == - VM_STACK_INCOMPLETE_SETUP) - return true; - - return false; -} - -/** - * try_to_unmap_anon - unmap or unlock anonymous page using the object-based - * rmap method - * @page: the page to unmap/unlock - * @flags: action and flags - * - * Find all the mappings of a page using the mapping pointer and the vma chains - * contained in the anon_vma struct it points to. - * - * This function is only called from try_to_unmap/try_to_munlock for - * anonymous pages. - * When called from try_to_munlock(), the mmap_sem 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 int try_to_unmap_anon(struct page *page, enum ttu_flags flags) +static int try_to_unmap_nonlinear(struct page *page, + struct address_space *mapping, void *arg) { - struct anon_vma *anon_vma; - struct anon_vma_chain *avc; - int ret = SWAP_AGAIN; - - anon_vma = page_lock_anon_vma(page); - if (!anon_vma) - return ret; - - list_for_each_entry(avc, &anon_vma->head, same_anon_vma) { - struct vm_area_struct *vma = avc->vma; - unsigned long address; - - /* - * During exec, a temporary VMA is setup and later moved. - * The VMA is moved under the anon_vma lock but not the - * page tables leading to a race where migration cannot - * find the migration ptes. Rather than increasing the - * locking requirements of exec(), migration skips - * temporary VMAs until after exec() completes. - */ - if (PAGE_MIGRATION && (flags & TTU_MIGRATION) && - is_vma_temporary_stack(vma)) - continue; - - address = vma_address(page, vma); - if (address == -EFAULT) - continue; - ret = try_to_unmap_one(page, vma, address, flags); - if (ret != SWAP_AGAIN || !page_mapped(page)) - break; - } - - page_unlock_anon_vma(anon_vma); - return ret; -} - -/** - * try_to_unmap_file - unmap/unlock file page using the object-based rmap method - * @page: the page to unmap/unlock - * @flags: action and flags - * - * Find all the mappings of a page using the mapping pointer and the vma chains - * contained in the address_space struct it points to. - * - * This function is only called from try_to_unmap/try_to_munlock for - * object-based pages. - * When called from try_to_munlock(), the mmap_sem 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 int try_to_unmap_file(struct page *page, enum ttu_flags flags) -{ - struct address_space *mapping = page->mapping; - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); struct vm_area_struct *vma; - struct prio_tree_iter iter; int ret = SWAP_AGAIN; unsigned long cursor; unsigned long max_nl_cursor = 0; unsigned long max_nl_size = 0; unsigned int mapcount; - spin_lock(&mapping->i_mmap_lock); - vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { - unsigned long address = vma_address(page, vma); - if (address == -EFAULT) - continue; - ret = try_to_unmap_one(page, vma, address, flags); - if (ret != SWAP_AGAIN || !page_mapped(page)) - goto out; - } - - if (list_empty(&mapping->i_mmap_nonlinear)) - goto out; - - /* - * We don't bother to try to find the munlocked page in nonlinears. - * It's costly. Instead, later, page reclaim logic may call - * try_to_unmap(TTU_MUNLOCK) and recover PG_mlocked lazily. - */ - if (TTU_ACTION(flags) == TTU_MUNLOCK) - goto out; + list_for_each_entry(vma, + &mapping->i_mmap_nonlinear, shared.nonlinear) { - list_for_each_entry(vma, &mapping->i_mmap_nonlinear, - shared.vm_set.list) { cursor = (unsigned long) vma->vm_private_data; if (cursor > max_nl_cursor) max_nl_cursor = cursor; @@ -1329,8 +1428,7 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) } if (max_nl_size == 0) { /* all nonlinears locked or reserved ? */ - ret = SWAP_FAIL; - goto out; + return SWAP_FAIL; } /* @@ -1342,18 +1440,20 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) */ mapcount = page_mapcount(page); if (!mapcount) - goto out; - cond_resched_lock(&mapping->i_mmap_lock); + return ret; + + cond_resched(); max_nl_size = (max_nl_size + CLUSTER_SIZE - 1) & CLUSTER_MASK; if (max_nl_cursor == 0) max_nl_cursor = CLUSTER_SIZE; do { - list_for_each_entry(vma, &mapping->i_mmap_nonlinear, - shared.vm_set.list) { + list_for_each_entry(vma, + &mapping->i_mmap_nonlinear, shared.nonlinear) { + cursor = (unsigned long) vma->vm_private_data; - while ( cursor < max_nl_cursor && + while (cursor < max_nl_cursor && cursor < vma->vm_end - vma->vm_start) { if (try_to_unmap_cluster(cursor, &mapcount, vma, page) == SWAP_MLOCK) @@ -1361,11 +1461,11 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) cursor += CLUSTER_SIZE; vma->vm_private_data = (void *) cursor; if ((int)mapcount <= 0) - goto out; + return ret; } vma->vm_private_data = (void *) max_nl_cursor; } - cond_resched_lock(&mapping->i_mmap_lock); + cond_resched(); max_nl_cursor += CLUSTER_SIZE; } while (max_nl_cursor <= max_nl_size); @@ -1374,13 +1474,36 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) * in locked vmas). Reset cursor on all unreserved nonlinear * vmas, now forgetting on which ones it had fallen behind. */ - list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list) + list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.nonlinear) vma->vm_private_data = NULL; -out: - spin_unlock(&mapping->i_mmap_lock); + return ret; } +bool is_vma_temporary_stack(struct vm_area_struct *vma) +{ + int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); + + if (!maybe_stack) + return false; + + if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) == + VM_STACK_INCOMPLETE_SETUP) + return true; + + return false; +} + +static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) +{ + return is_vma_temporary_stack(vma); +} + +static int page_not_mapped(struct page *page) +{ + return !page_mapped(page); +}; + /** * try_to_unmap - try to remove all page table mappings to a page * @page: the page to get unmapped @@ -1398,15 +1521,29 @@ out: int try_to_unmap(struct page *page, enum ttu_flags flags) { int ret; + struct rmap_walk_control rwc = { + .rmap_one = try_to_unmap_one, + .arg = (void *)flags, + .done = page_not_mapped, + .file_nonlinear = try_to_unmap_nonlinear, + .anon_lock = page_lock_anon_vma_read, + }; - BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(!PageHuge(page) && PageTransHuge(page), page); + + /* + * During exec, a temporary VMA is setup and later moved. + * The VMA is moved under the anon_vma lock but not the + * page tables leading to a race where migration cannot + * find the migration ptes. Rather than increasing the + * locking requirements of exec(), migration skips + * temporary VMAs until after exec() completes. + */ + if ((flags & TTU_MIGRATION) && !PageKsm(page) && PageAnon(page)) + rwc.invalid_vma = invalid_migration_vma; + + ret = rmap_walk(page, &rwc); - if (unlikely(PageKsm(page))) - ret = try_to_unmap_ksm(page, flags); - else if (PageAnon(page)) - ret = try_to_unmap_anon(page, flags); - else - ret = try_to_unmap_file(page, flags); if (ret != SWAP_MLOCK && !page_mapped(page)) ret = SWAP_SUCCESS; return ret; @@ -1429,129 +1566,166 @@ int try_to_unmap(struct page *page, enum ttu_flags flags) */ int try_to_munlock(struct page *page) { - VM_BUG_ON(!PageLocked(page) || PageLRU(page)); + int ret; + struct rmap_walk_control rwc = { + .rmap_one = try_to_unmap_one, + .arg = (void *)TTU_MUNLOCK, + .done = page_not_mapped, + /* + * We don't bother to try to find the munlocked page in + * nonlinears. It's costly. Instead, later, page reclaim logic + * may call try_to_unmap() and recover PG_mlocked lazily. + */ + .file_nonlinear = NULL, + .anon_lock = page_lock_anon_vma_read, - if (unlikely(PageKsm(page))) - return try_to_unmap_ksm(page, TTU_MUNLOCK); - else if (PageAnon(page)) - return try_to_unmap_anon(page, TTU_MUNLOCK); - else - return try_to_unmap_file(page, TTU_MUNLOCK); + }; + + VM_BUG_ON_PAGE(!PageLocked(page) || PageLRU(page), page); + + ret = rmap_walk(page, &rwc); + return ret; } -#if defined(CONFIG_KSM) || defined(CONFIG_MIGRATION) -/* - * Drop an anon_vma refcount, freeing the anon_vma and anon_vma->root - * if necessary. Be careful to do all the tests under the lock. Once - * we know we are the last user, nobody else can get a reference and we - * can do the freeing without the lock. - */ -void drop_anon_vma(struct anon_vma *anon_vma) +void __put_anon_vma(struct anon_vma *anon_vma) { - BUG_ON(atomic_read(&anon_vma->external_refcount) <= 0); - if (atomic_dec_and_lock(&anon_vma->external_refcount, &anon_vma->root->lock)) { - struct anon_vma *root = anon_vma->root; - int empty = list_empty(&anon_vma->head); - int last_root_user = 0; - int root_empty = 0; + struct anon_vma *root = anon_vma->root; - /* - * The refcount on a non-root anon_vma got dropped. Drop - * the refcount on the root and check if we need to free it. - */ - if (empty && anon_vma != root) { - BUG_ON(atomic_read(&root->external_refcount) <= 0); - last_root_user = atomic_dec_and_test(&root->external_refcount); - root_empty = list_empty(&root->head); - } - anon_vma_unlock(anon_vma); - - if (empty) { - anon_vma_free(anon_vma); - if (root_empty && last_root_user) - anon_vma_free(root); - } - } + anon_vma_free(anon_vma); + if (root != anon_vma && atomic_dec_and_test(&root->refcount)) + anon_vma_free(root); } -#endif -#ifdef CONFIG_MIGRATION -/* - * rmap_walk() and its helpers rmap_walk_anon() and rmap_walk_file(): - * Called by migrate.c to remove migration ptes, but might be used more later. - */ -static int rmap_walk_anon(struct page *page, int (*rmap_one)(struct page *, - struct vm_area_struct *, unsigned long, void *), void *arg) +static struct anon_vma *rmap_walk_anon_lock(struct page *page, + struct rmap_walk_control *rwc) { struct anon_vma *anon_vma; - struct anon_vma_chain *avc; - int ret = SWAP_AGAIN; + + if (rwc->anon_lock) + return rwc->anon_lock(page); /* - * Note: remove_migration_ptes() cannot use page_lock_anon_vma() + * Note: remove_migration_ptes() cannot use page_lock_anon_vma_read() * because that depends on page_mapped(); but not all its usages * are holding mmap_sem. Users without mmap_sem are required to * take a reference count to prevent the anon_vma disappearing */ anon_vma = page_anon_vma(page); if (!anon_vma) + return NULL; + + anon_vma_lock_read(anon_vma); + return anon_vma; +} + +/* + * rmap_walk_anon - do something to anonymous page using the object-based + * rmap method + * @page: the page to be handled + * @rwc: control variable according to each walk type + * + * 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 try_to_munlock(), the mmap_sem 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 int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc) +{ + struct anon_vma *anon_vma; + pgoff_t pgoff = page_to_pgoff(page); + struct anon_vma_chain *avc; + int ret = SWAP_AGAIN; + + anon_vma = rmap_walk_anon_lock(page, rwc); + if (!anon_vma) return ret; - anon_vma_lock(anon_vma); - list_for_each_entry(avc, &anon_vma->head, same_anon_vma) { + + anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) { struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(page, vma); - if (address == -EFAULT) + + if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; - ret = rmap_one(page, vma, address, arg); + + ret = rwc->rmap_one(page, vma, address, rwc->arg); if (ret != SWAP_AGAIN) break; + if (rwc->done && rwc->done(page)) + break; } - anon_vma_unlock(anon_vma); + anon_vma_unlock_read(anon_vma); return ret; } -static int rmap_walk_file(struct page *page, int (*rmap_one)(struct page *, - struct vm_area_struct *, unsigned long, void *), void *arg) +/* + * rmap_walk_file - do something to file page using the object-based rmap method + * @page: the page to be handled + * @rwc: control variable according to each walk type + * + * 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 try_to_munlock(), the mmap_sem 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 int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc) { struct address_space *mapping = page->mapping; - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + pgoff_t pgoff = page_to_pgoff(page); struct vm_area_struct *vma; - struct prio_tree_iter iter; int ret = SWAP_AGAIN; + /* + * The page lock not only makes sure that page->mapping cannot + * suddenly be NULLified by truncation, it makes sure that the + * structure at mapping cannot be freed and reused yet, + * so we can safely take mapping->i_mmap_mutex. + */ + VM_BUG_ON(!PageLocked(page)); + if (!mapping) return ret; - spin_lock(&mapping->i_mmap_lock); - vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { + mutex_lock(&mapping->i_mmap_mutex); + vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { unsigned long address = vma_address(page, vma); - if (address == -EFAULT) + + if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; - ret = rmap_one(page, vma, address, arg); + + ret = rwc->rmap_one(page, vma, address, rwc->arg); if (ret != SWAP_AGAIN) - break; + goto done; + if (rwc->done && rwc->done(page)) + goto done; } - /* - * No nonlinear handling: being always shared, nonlinear vmas - * never contain migration ptes. Decide what to do about this - * limitation to linear when we need rmap_walk() on nonlinear. - */ - spin_unlock(&mapping->i_mmap_lock); + + if (!rwc->file_nonlinear) + goto done; + + if (list_empty(&mapping->i_mmap_nonlinear)) + goto done; + + ret = rwc->file_nonlinear(page, mapping, rwc->arg); + +done: + mutex_unlock(&mapping->i_mmap_mutex); return ret; } -int rmap_walk(struct page *page, int (*rmap_one)(struct page *, - struct vm_area_struct *, unsigned long, void *), void *arg) +int rmap_walk(struct page *page, struct rmap_walk_control *rwc) { - VM_BUG_ON(!PageLocked(page)); - if (unlikely(PageKsm(page))) - return rmap_walk_ksm(page, rmap_one, arg); + return rmap_walk_ksm(page, rwc); else if (PageAnon(page)) - return rmap_walk_anon(page, rmap_one, arg); + return rmap_walk_anon(page, rwc); else - return rmap_walk_file(page, rmap_one, arg); + return rmap_walk_file(page, rwc); } -#endif /* CONFIG_MIGRATION */ #ifdef CONFIG_HUGETLB_PAGE /* @@ -1584,7 +1758,7 @@ void hugepage_add_anon_rmap(struct page *page, BUG_ON(!PageLocked(page)); BUG_ON(!anon_vma); - BUG_ON(address < vma->vm_start || address >= vma->vm_end); + /* address might be in next vma when migration races vma_adjust */ first = atomic_inc_and_test(&page->_mapcount); if (first) __hugepage_set_anon_rmap(page, vma, address, 0); |