--- zzzz-none-000/linux-3.10.107/mm/rmap.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/mm/rmap.c 2021-02-04 17:41:59.000000000 +0000 @@ -23,13 +23,15 @@ * inode->i_mutex (while writing or truncating, not reading or faulting) * mm->mmap_sem * page->flags PG_locked (lock_page) - * mapping->i_mmap_mutex + * mapping->i_mmap_rwsem * 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) + * mem_cgroup_{begin,end}_page_stat (memcg->move_lock) + * mapping->tree_lock (widely used) * 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) @@ -57,9 +59,12 @@ #include #include #include +#include #include +#include + #include "internal.h" static struct kmem_cache *anon_vma_cachep; @@ -72,6 +77,8 @@ anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); if (anon_vma) { atomic_set(&anon_vma->refcount, 1); + anon_vma->degree = 1; /* Reference for first vma */ + anon_vma->parent = anon_vma; /* * Initialise the anon_vma root to point to itself. If called * from fork, the root will be reset to the parents anon_vma. @@ -188,6 +195,8 @@ if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; anon_vma_chain_link(vma, avc, anon_vma); + /* vma reference or self-parent link for new root */ + anon_vma->degree++; allocated = NULL; avc = NULL; } @@ -236,6 +245,14 @@ /* * Attach the anon_vmas from src to dst. * Returns 0 on success, -ENOMEM on failure. + * + * If dst->anon_vma is NULL this function tries to find and reuse existing + * anon_vma which has no vmas and only one child anon_vma. This prevents + * degradation of anon_vma hierarchy to endless linear chain in case of + * constantly forking task. On the other hand, an anon_vma with more than one + * child isn't reused even if there was no alive vma, thus rmap walker has a + * good chance of avoiding scanning the whole hierarchy when it searches where + * page is mapped. */ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) { @@ -256,11 +273,32 @@ anon_vma = pavc->anon_vma; root = lock_anon_vma_root(root, anon_vma); anon_vma_chain_link(dst, avc, anon_vma); + + /* + * Reuse existing anon_vma if its degree lower than two, + * that means it has no vma and only one anon_vma child. + * + * Do not chose parent anon_vma, otherwise first child + * will always reuse it. Root anon_vma is never reused: + * it has self-parent reference and at least one child. + */ + if (!dst->anon_vma && anon_vma != src->anon_vma && + anon_vma->degree < 2) + dst->anon_vma = anon_vma; } + if (dst->anon_vma) + dst->anon_vma->degree++; unlock_anon_vma_root(root); return 0; enomem_failure: + /* + * dst->anon_vma is dropped here otherwise its degree can be incorrectly + * decremented in unlink_anon_vmas(). + * We can safely do this because callers of anon_vma_clone() don't care + * about dst->anon_vma if anon_vma_clone() failed. + */ + dst->anon_vma = NULL; unlink_anon_vmas(dst); return -ENOMEM; } @@ -274,17 +312,26 @@ { struct anon_vma_chain *avc; struct anon_vma *anon_vma; + int error; /* Don't bother if the parent process has no anon_vma here. */ if (!pvma->anon_vma) return 0; + /* Drop inherited anon_vma, we'll reuse existing or allocate new. */ + vma->anon_vma = NULL; + /* * First, attach the new VMA to the parent VMA's anon_vmas, * so rmap can find non-COWed pages in child processes. */ - if (anon_vma_clone(vma, pvma)) - return -ENOMEM; + error = anon_vma_clone(vma, pvma); + if (error) + return error; + + /* An existing anon_vma has been reused, all done then. */ + if (vma->anon_vma) + return 0; /* Then add our own anon_vma. */ anon_vma = anon_vma_alloc(); @@ -299,6 +346,7 @@ * lock any of the anon_vmas in this anon_vma tree. */ anon_vma->root = pvma->anon_vma->root; + anon_vma->parent = pvma->anon_vma; /* * With refcounts, an anon_vma can stay around longer than the * process it belongs to. The root anon_vma needs to be pinned until @@ -309,6 +357,7 @@ vma->anon_vma = anon_vma; anon_vma_lock_write(anon_vma); anon_vma_chain_link(vma, avc, anon_vma); + anon_vma->parent->degree++; anon_vma_unlock_write(anon_vma); return 0; @@ -339,12 +388,16 @@ * Leave empty anon_vmas on the list - we'll need * to free them outside the lock. */ - if (RB_EMPTY_ROOT(&anon_vma->rb_root)) + if (RB_EMPTY_ROOT(&anon_vma->rb_root)) { + anon_vma->parent->degree--; continue; + } list_del(&avc->same_vma); anon_vma_chain_free(avc); } + if (vma->anon_vma) + vma->anon_vma->degree--; unlock_anon_vma_root(root); /* @@ -355,6 +408,7 @@ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; + BUG_ON(anon_vma->degree); put_anon_vma(anon_vma); list_del(&avc->same_vma); @@ -407,7 +461,7 @@ unsigned long anon_mapping; rcu_read_lock(); - anon_mapping = (unsigned long) ACCESS_ONCE(page->mapping); + anon_mapping = (unsigned long)READ_ONCE(page->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!page_mapped(page)) @@ -451,14 +505,14 @@ unsigned long anon_mapping; rcu_read_lock(); - anon_mapping = (unsigned long) ACCESS_ONCE(page->mapping); + anon_mapping = (unsigned long)READ_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); + 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 @@ -517,11 +571,7 @@ static inline unsigned long __vma_address(struct page *page, struct vm_area_struct *vma) { - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - - if (unlikely(is_vm_hugetlb_page(vma))) - pgoff = page->index << huge_page_order(page_hstate(page)); - + pgoff_t pgoff = page_to_pgoff(page); return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); } @@ -531,11 +581,112 @@ 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); + VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma); return address; } +#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH +static void percpu_flush_tlb_batch_pages(void *data) +{ + /* + * All TLB entries are flushed on the assumption that it is + * cheaper to flush all TLBs and let them be refilled than + * flushing individual PFNs. Note that we do not track mm's + * to flush as that might simply be multiple full TLB flushes + * for no gain. + */ + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); + flush_tlb_local(); +} + +/* + * Flush TLB entries for recently unmapped pages from remote CPUs. It is + * important if a PTE was dirty when it was unmapped that it's flushed + * before any IO is initiated on the page to prevent lost writes. Similarly, + * it must be flushed before freeing to prevent data leakage. + */ +void try_to_unmap_flush(void) +{ + struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; + int cpu; + + if (!tlb_ubc->flush_required) + return; + + cpu = get_cpu(); + + trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, -1UL); + + if (cpumask_test_cpu(cpu, &tlb_ubc->cpumask)) + percpu_flush_tlb_batch_pages(&tlb_ubc->cpumask); + + if (cpumask_any_but(&tlb_ubc->cpumask, cpu) < nr_cpu_ids) { + smp_call_function_many(&tlb_ubc->cpumask, + percpu_flush_tlb_batch_pages, (void *)tlb_ubc, true); + } + cpumask_clear(&tlb_ubc->cpumask); + tlb_ubc->flush_required = false; + tlb_ubc->writable = false; + put_cpu(); +} + +/* Flush iff there are potentially writable TLB entries that can race with IO */ +void try_to_unmap_flush_dirty(void) +{ + struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; + + if (tlb_ubc->writable) + try_to_unmap_flush(); +} + +static void set_tlb_ubc_flush_pending(struct mm_struct *mm, + struct page *page, bool writable) +{ + struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; + + cpumask_or(&tlb_ubc->cpumask, &tlb_ubc->cpumask, mm_cpumask(mm)); + tlb_ubc->flush_required = true; + + /* + * If the PTE was dirty then it's best to assume it's writable. The + * caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush() + * before the page is queued for IO. + */ + if (writable) + tlb_ubc->writable = true; +} + +/* + * Returns true if the TLB flush should be deferred to the end of a batch of + * unmap operations to reduce IPIs. + */ +static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) +{ + bool should_defer = false; + + if (!(flags & TTU_BATCH_FLUSH)) + return false; + + /* If remote CPUs need to be flushed then defer batch the flush */ + if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids) + should_defer = true; + put_cpu(); + + return should_defer; +} +#else +static void set_tlb_ubc_flush_pending(struct mm_struct *mm, + struct page *page, bool writable) +{ +} + +static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) +{ + return false; +} +#endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ + /* * At what user virtual address is page expected in vma? * Caller should check the page is actually part of the vma. @@ -552,9 +703,8 @@ if (!vma->anon_vma || !page__anon_vma || vma->anon_vma->root != page__anon_vma->root) return -EFAULT; - } else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) { - if (!vma->vm_file || - vma->vm_file->f_mapping != page->mapping) + } else if (page->mapping) { + if (!vma->vm_file || vma->vm_file->f_mapping != page->mapping) return -EFAULT; } else return -EFAULT; @@ -569,6 +719,7 @@ pgd_t *pgd; pud_t *pud; pmd_t *pmd = NULL; + pmd_t pmde; pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) @@ -579,7 +730,14 @@ goto out; pmd = pmd_offset(pud, address); - if (!pmd_present(*pmd)) + /* + * Some THP functions use the sequence pmdp_huge_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 = *pmd; + barrier(); + if (!pmd_present(pmde) || pmd_trans_huge(pmde)) pmd = NULL; out: return pmd; @@ -607,7 +765,7 @@ if (!pte) return NULL; - ptl = &mm->page_table_lock; + ptl = huge_pte_lockptr(page_hstate(page), mm, pte); goto check; } @@ -615,9 +773,6 @@ if (!pmd) return NULL; - if (pmd_trans_huge(*pmd)) - return NULL; - pte = pte_offset_map(pmd, address); /* Make a quick check before getting the lock */ if (!sync && !pte_present(*pte)) { @@ -662,46 +817,47 @@ 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; + spinlock_t *ptl; int referenced = 0; + struct page_referenced_arg *pra = arg; if (unlikely(PageTransHuge(page))) { pmd_t *pmd; - spin_lock(&mm->page_table_lock); /* * rmap might return false positives; we must filter * these out using page_check_address_pmd(). */ pmd = page_check_address_pmd(page, mm, address, - PAGE_CHECK_ADDRESS_PMD_FLAG); - if (!pmd) { - spin_unlock(&mm->page_table_lock); - goto out; - } + PAGE_CHECK_ADDRESS_PMD_FLAG, &ptl); + if (!pmd) + return SWAP_AGAIN; if (vma->vm_flags & VM_LOCKED) { - spin_unlock(&mm->page_table_lock); - *mapcount = 0; /* break early from loop */ - *vm_flags |= VM_LOCKED; - goto out; + spin_unlock(ptl); + pra->vm_flags |= VM_LOCKED; + return SWAP_FAIL; /* To break the loop */ } /* go ahead even if the pmd is pmd_trans_splitting() */ if (pmdp_clear_flush_young_notify(vma, address, pmd)) referenced++; - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); } else { pte_t *pte; - spinlock_t *ptl; /* * rmap might return false positives; we must filter @@ -709,13 +865,12 @@ */ pte = page_check_address(page, mm, address, &ptl, 0); if (!pte) - goto out; + return SWAP_AGAIN; if (vma->vm_flags & VM_LOCKED) { pte_unmap_unlock(pte, ptl); - *mapcount = 0; /* break early from loop */ - *vm_flags |= VM_LOCKED; - goto out; + pra->vm_flags |= VM_LOCKED; + return SWAP_FAIL; /* To break the loop */ } if (ptep_clear_flush_young_notify(vma, address, pte)) { @@ -726,119 +881,38 @@ * mapping is already gone, the unmap path will have * set PG_referenced or activated the page. */ - if (likely(!VM_SequentialReadHint(vma))) + if (likely(!(vma->vm_flags & VM_SEQ_READ))) referenced++; } pte_unmap_unlock(pte, ptl); } - (*mapcount)--; - if (referenced) - *vm_flags |= vma->vm_flags; -out: - return referenced; -} + clear_page_idle(page); + if (test_and_clear_page_young(page)) + referenced++; -static int page_referenced_anon(struct page *page, - struct mem_cgroup *memcg, - unsigned long *vm_flags) -{ - unsigned int mapcount; - struct anon_vma *anon_vma; - pgoff_t pgoff; - struct anon_vma_chain *avc; - int referenced = 0; - - anon_vma = page_lock_anon_vma_read(page); - if (!anon_vma) - return referenced; - - mapcount = page_mapcount(page); - pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - 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 we are reclaiming on behalf of a cgroup, skip - * counting on behalf of references from different - * cgroups - */ - if (memcg && !mm_match_cgroup(vma->vm_mm, memcg)) - continue; - referenced += page_referenced_one(page, vma, address, - &mapcount, vm_flags); - if (!mapcount) - break; + if (referenced) { + pra->referenced++; + pra->vm_flags |= vma->vm_flags; } - page_unlock_anon_vma_read(anon_vma); - return referenced; + pra->mapcount--; + if (!pra->mapcount) + return SWAP_SUCCESS; /* To break the loop */ + + return SWAP_AGAIN; } -/** - * page_referenced_file - referenced check for object-based rmap - * @page: the page we're checking references on. - * @memcg: target memory control group - * @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 *memcg, - unsigned long *vm_flags) +static bool invalid_page_referenced_vma(struct vm_area_struct *vma, void *arg) { - unsigned int mapcount; - struct address_space *mapping = page->mapping; - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - struct vm_area_struct *vma; - int referenced = 0; - - /* - * 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)); - - /* - * 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. - */ - BUG_ON(!PageLocked(page)); + struct page_referenced_arg *pra = arg; + struct mem_cgroup *memcg = pra->memcg; - mutex_lock(&mapping->i_mmap_mutex); - - /* - * i_mmap_mutex does not stabilize mapcount at all, but mapcount - * is more likely to be accurate if we note it after spinning. - */ - mapcount = page_mapcount(page); - - vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { - unsigned long address = vma_address(page, vma); - /* - * If we are reclaiming on behalf of a cgroup, skip - * counting on behalf of references from different - * cgroups - */ - if (memcg && !mm_match_cgroup(vma->vm_mm, memcg)) - continue; - referenced += page_referenced_one(page, vma, address, - &mapcount, vm_flags); - if (!mapcount) - break; - } + if (!mm_match_cgroup(vma->vm_mm, memcg)) + return true; - mutex_unlock(&mapping->i_mmap_mutex); - return referenced; + return false; } /** @@ -856,44 +930,57 @@ 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, memcg, - vm_flags); - else if (PageAnon(page)) - referenced += page_referenced_anon(page, memcg, - vm_flags); - else if (page->mapping) - referenced += page_referenced_file(page, memcg, - vm_flags); - if (we_locked) - unlock_page(page); + if (!page_mapped(page)) + return 0; - if (page_test_and_clear_young(page_to_pfn(page))) - referenced++; + if (!page_rmapping(page)) + return 0; + + if (!is_locked && (!PageAnon(page) || PageKsm(page))) { + we_locked = trylock_page(page); + if (!we_locked) + return 1; } -out: - 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) @@ -912,44 +999,44 @@ pte_unmap_unlock(pte, ptl); - if (ret) + 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; - int ret = 0; - - BUG_ON(PageAnon(page)); + if (vma->vm_flags & VM_SHARED) + return false; - mutex_lock(&mapping->i_mmap_mutex); - vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { - if (vma->vm_flags & VM_SHARED) { - unsigned long address = vma_address(page, vma); - ret += page_mkclean_one(page, vma, address); - } - } - mutex_unlock(&mapping->i_mmap_mutex); - 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_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); @@ -969,12 +1056,17 @@ { struct anon_vma *anon_vma = vma->anon_vma; - VM_BUG_ON(!PageLocked(page)); - VM_BUG_ON(!anon_vma); - VM_BUG_ON(page->index != linear_page_index(vma, address)); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_VMA(!anon_vma, vma); + 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; + /* + * 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. + */ + WRITE_ONCE(page->mapping, (struct address_space *) anon_vma); } /** @@ -1061,16 +1153,22 @@ { int first = atomic_inc_and_test(&page->_mapcount); if (first) { - if (!PageTransHuge(page)) - __inc_zone_page_state(page, NR_ANON_PAGES); - else + /* + * 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_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); @@ -1091,18 +1189,14 @@ void page_add_new_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address) { - VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end); + VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma); SetPageSwapBacked(page); atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */ - if (!PageTransHuge(page)) - __inc_zone_page_state(page, NR_ANON_PAGES); - else + 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 (!mlocked_vma_newpage(vma, page)) - lru_cache_add_lru(page, LRU_ACTIVE_ANON); - else - add_page_to_unevictable_list(page); } /** @@ -1113,15 +1207,42 @@ */ void page_add_file_rmap(struct page *page) { - bool locked; - unsigned long flags; + struct mem_cgroup *memcg; - mem_cgroup_begin_update_page_stat(page, &locked, &flags); + memcg = mem_cgroup_begin_page_stat(page); if (atomic_inc_and_test(&page->_mapcount)) { __inc_zone_page_state(page, NR_FILE_MAPPED); - mem_cgroup_inc_page_stat(page, MEMCG_NR_FILE_MAPPED); + mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_FILE_MAPPED); } - mem_cgroup_end_update_page_stat(page, &locked, &flags); + mem_cgroup_end_page_stat(memcg); +} + +static void page_remove_file_rmap(struct page *page) +{ + struct mem_cgroup *memcg; + + memcg = mem_cgroup_begin_page_stat(page); + + /* page still mapped by someone else? */ + if (!atomic_add_negative(-1, &page->_mapcount)) + goto out; + + /* Hugepages are not counted in NR_FILE_MAPPED for now. */ + if (unlikely(PageHuge(page))) + goto out; + + /* + * We use the irq-unsafe __{inc|mod}_zone_page_stat because + * these counters are not modified in interrupt context, and + * pte lock(a spinlock) is held, which implies preemption disabled. + */ + __dec_zone_page_state(page, NR_FILE_MAPPED); + mem_cgroup_dec_page_stat(memcg, MEM_CGROUP_STAT_FILE_MAPPED); + + if (unlikely(PageMlocked(page))) + clear_page_mlock(page); +out: + mem_cgroup_end_page_stat(memcg); } /** @@ -1132,42 +1253,33 @@ */ void page_remove_rmap(struct page *page) { - bool anon = PageAnon(page); - bool locked; - unsigned long flags; - - /* - * 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 (!anon) - mem_cgroup_begin_update_page_stat(page, &locked, &flags); + if (!PageAnon(page)) { + page_remove_file_rmap(page); + return; + } /* page still mapped by someone else? */ if (!atomic_add_negative(-1, &page->_mapcount)) - goto out; + return; + + /* Hugepages are not counted in NR_ANON_PAGES for now. */ + if (unlikely(PageHuge(page))) + return; /* - * 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 + * pte lock(a spinlock) is held, which implies preemption disabled. */ - if (unlikely(PageHuge(page))) - goto out; - if (anon) { - mem_cgroup_uncharge_page(page); - if (!PageTransHuge(page)) - __dec_zone_page_state(page, NR_ANON_PAGES); - else - __dec_zone_page_state(page, - NR_ANON_TRANSPARENT_HUGEPAGES); - } else { - __dec_zone_page_state(page, NR_FILE_MAPPED); - mem_cgroup_dec_page_stat(page, MEMCG_NR_FILE_MAPPED); - mem_cgroup_end_update_page_stat(page, &locked, &flags); - } + 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)); + 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 @@ -1177,24 +1289,24 @@ * 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 try_to_unmap_ksm, 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; + + /* munlock has nothing to gain from examining un-locked vmas */ + if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED)) + goto out; pte = page_check_address(page, mm, address, &ptl, 0); if (!pte) @@ -1206,10 +1318,13 @@ * skipped over this mm) then we should reactivate it. */ if (!(flags & TTU_IGNORE_MLOCK)) { - if (vma->vm_flags & VM_LOCKED) - goto out_mlock; - - if (TTU_ACTION(flags) == TTU_MUNLOCK) + if (vma->vm_flags & VM_LOCKED) { + /* Holding pte lock, we do *not* need mmap_sem here */ + mlock_vma_page(page); + ret = SWAP_MLOCK; + goto out_unmap; + } + if (flags & TTU_MUNLOCK) goto out_unmap; } if (!(flags & TTU_IGNORE_ACCESS)) { @@ -1221,7 +1336,20 @@ /* Nuke the page table entry. */ flush_cache_page(vma, address, page_to_pfn(page)); - pteval = ptep_clear_flush(vma, address, pte); + 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. If the entry was + * previously clean then the architecture must guarantee that + * a clear->dirty transition on a cached TLB entry is written + * through and traps if the PTE is unmapped. + */ + pteval = ptep_get_and_clear(mm, address, pte); + + set_tlb_ubc_flush_pending(mm, page, pte_dirty(pteval)); + } else { + pteval = ptep_clear_flush(vma, address, pte); + } /* Move the dirty bit to the physical page now the pte is gone. */ if (pte_dirty(pteval)) @@ -1231,7 +1359,9 @@ update_hiwater_rss(mm); if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) { - if (!PageHuge(page)) { + if (PageHuge(page)) { + hugetlb_count_sub(1 << compound_order(page), mm); + } else { if (PageAnon(page)) dec_mm_counter(mm, MM_ANONPAGES); else @@ -1239,44 +1369,55 @@ } 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) }; - - if (PageSwapCache(page)) { - /* - * Store the swap location in the pte. - * See handle_pte_fault() ... - */ - if (swap_duplicate(entry) < 0) { - set_pte_at(mm, address, pte, pteval); - ret = SWAP_FAIL; - goto out_unmap; - } - if (list_empty(&mm->mmlist)) { - spin_lock(&mmlist_lock); - if (list_empty(&mm->mmlist)) - list_add(&mm->mmlist, &init_mm.mmlist); - spin_unlock(&mmlist_lock); - } + } 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); - inc_mm_counter(mm, MM_SWAPENTS); - } 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); - entry = make_migration_entry(page, pte_write(pteval)); - } - set_pte_at(mm, address, pte, swp_entry_to_pte(entry)); - BUG_ON(pte_file(*pte)); - } else if (IS_ENABLED(CONFIG_MIGRATION) && - (TTU_ACTION(flags) == TTU_MIGRATION)) { - /* Establish migration entry for a file page */ + else + dec_mm_counter(mm, MM_FILEPAGES); + } else if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION)) { swp_entry_t entry; + pte_t swp_pte; + /* + * 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. + */ 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); + } else if (PageAnon(page)) { + swp_entry_t entry = { .val = page_private(page) }; + pte_t swp_pte; + /* + * Store the swap location in the pte. + * See handle_pte_fault() ... + */ + VM_BUG_ON_PAGE(!PageSwapCache(page), page); + if (swap_duplicate(entry) < 0) { + set_pte_at(mm, address, pte, pteval); + ret = SWAP_FAIL; + goto out_unmap; + } + if (list_empty(&mm->mmlist)) { + spin_lock(&mmlist_lock); + if (list_empty(&mm->mmlist)) + list_add(&mm->mmlist, &init_mm.mmlist); + spin_unlock(&mmlist_lock); + } + dec_mm_counter(mm, MM_ANONPAGES); + inc_mm_counter(mm, MM_SWAPENTS); + inc_mm_counter(mm, MM_SWAPOUTS); + 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); } else dec_mm_counter(mm, MM_FILEPAGES); @@ -1285,154 +1426,10 @@ out_unmap: pte_unmap_unlock(pte, ptl); - if (ret != SWAP_FAIL) + if (ret != SWAP_FAIL && ret != SWAP_MLOCK && !(flags & TTU_MUNLOCK)) mmu_notifier_invalidate_page(mm, address); out: return ret; - -out_mlock: - pte_unmap_unlock(pte, ptl); - - - /* - * 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->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. - */ - if (down_read_trylock(&vma->vm_mm->mmap_sem)) { - if (vma->vm_flags & VM_LOCKED) { - mlock_vma_page(page); - ret = SWAP_MLOCK; - } - up_read(&vma->vm_mm->mmap_sem); - } - return ret; -} - -/* - * objrmap doesn't work for nonlinear VMAs because the assumption that - * offset-into-file correlates with offset-into-virtual-addresses does not hold. - * Consequently, given a particular page and its ->index, we cannot locate the - * ptes which are mapping that page without an exhaustive linear search. - * - * So what this code does is a mini "virtual scan" of each nonlinear VMA which - * maps the file to which the target page belongs. The ->vm_private_data field - * holds the current cursor into that scan. Successive searches will circulate - * around the vma's virtual address space. - * - * So as more replacement pressure is applied to the pages in a nonlinear VMA, - * more scanning pressure is placed against them as well. Eventually pages - * will become fully unmapped and are eligible for eviction. - * - * For very sparsely populated VMAs this is a little inefficient - chances are - * there there won't be many ptes located within the scan cluster. In this case - * maybe we could scan further - to the end of the pte page, perhaps. - * - * Mlocked pages: check VM_LOCKED under mmap_sem held for read, if we can - * acquire it without blocking. If vma locked, mlock the pages in the cluster, - * rather than unmapping them. If we encounter the "check_page" that vmscan is - * trying to unmap, return SWAP_MLOCK, else default SWAP_AGAIN. - */ -#define CLUSTER_SIZE min(32*PAGE_SIZE, PMD_SIZE) -#define CLUSTER_MASK (~(CLUSTER_SIZE - 1)) - -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; - 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; - - address = (vma->vm_start + cursor) & CLUSTER_MASK; - end = address + CLUSTER_SIZE; - if (address < vma->vm_start) - address = vma->vm_start; - if (end > vma->vm_end) - end = vma->vm_end; - - pmd = mm_find_pmd(mm, address); - if (!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, - * keep the sem while scanning the cluster for mlocking pages. - */ - if (down_read_trylock(&vma->vm_mm->mmap_sem)) { - locked_vma = (vma->vm_flags & VM_LOCKED); - if (!locked_vma) - up_read(&vma->vm_mm->mmap_sem); /* don't need it */ - } - - pte = pte_offset_map_lock(mm, pmd, address, &ptl); - - /* Update high watermark before we lower rss */ - update_hiwater_rss(mm); - - for (; address < end; pte++, address += PAGE_SIZE) { - if (!pte_present(*pte)) - continue; - page = vm_normal_page(vma, address, *pte); - BUG_ON(!page || PageAnon(page)); - - if (locked_vma) { - 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 */ - } - - if (ptep_clear_flush_young_notify(vma, address, pte)) - continue; - - /* Nuke the page table entry. */ - flush_cache_page(vma, address, pte_pfn(*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)); - - /* Move the dirty bit to the physical page now the pte is gone. */ - if (pte_dirty(pteval)) - set_page_dirty(page); - - page_remove_rmap(page); - page_cache_release(page); - dec_mm_counter(mm, MM_FILEPAGES); - (*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; } bool is_vma_temporary_stack(struct vm_area_struct *vma) @@ -1449,170 +1446,15 @@ 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 bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) { - struct anon_vma *anon_vma; - pgoff_t pgoff; - struct anon_vma_chain *avc; - int ret = SWAP_AGAIN; - - anon_vma = page_lock_anon_vma_read(page); - if (!anon_vma) - return ret; - - pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) { - 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 (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) && - is_vma_temporary_stack(vma)) - continue; - - address = vma_address(page, vma); - ret = try_to_unmap_one(page, vma, address, flags); - if (ret != SWAP_AGAIN || !page_mapped(page)) - break; - } - - page_unlock_anon_vma_read(anon_vma); - return ret; + return is_vma_temporary_stack(vma); } -/** - * 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) +static int page_not_mapped(struct page *page) { - struct address_space *mapping = page->mapping; - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - struct vm_area_struct *vma; - int ret = SWAP_AGAIN; - unsigned long cursor; - unsigned long max_nl_cursor = 0; - unsigned long max_nl_size = 0; - unsigned int mapcount; - - if (PageHuge(page)) - pgoff = page->index << compound_order(page); - - mutex_lock(&mapping->i_mmap_mutex); - vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { - unsigned long address = vma_address(page, vma); - 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) { - cursor = (unsigned long) vma->vm_private_data; - if (cursor > max_nl_cursor) - max_nl_cursor = cursor; - cursor = vma->vm_end - vma->vm_start; - if (cursor > max_nl_size) - max_nl_size = cursor; - } - - if (max_nl_size == 0) { /* all nonlinears locked or reserved ? */ - ret = SWAP_FAIL; - goto out; - } - - /* - * We don't try to search for this page in the nonlinear vmas, - * and page_referenced wouldn't have found it anyway. Instead - * just walk the nonlinear vmas trying to age and unmap some. - * The mapcount of the page we came in with is irrelevant, - * but even so use it as a guide to how hard we should try? - */ - mapcount = page_mapcount(page); - if (!mapcount) - goto out; - 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.nonlinear) { - cursor = (unsigned long) vma->vm_private_data; - while ( cursor < max_nl_cursor && - cursor < vma->vm_end - vma->vm_start) { - if (try_to_unmap_cluster(cursor, &mapcount, - vma, page) == SWAP_MLOCK) - ret = SWAP_MLOCK; - cursor += CLUSTER_SIZE; - vma->vm_private_data = (void *) cursor; - if ((int)mapcount <= 0) - goto out; - } - vma->vm_private_data = (void *) max_nl_cursor; - } - cond_resched(); - max_nl_cursor += CLUSTER_SIZE; - } while (max_nl_cursor <= max_nl_size); - - /* - * Don't loop forever (perhaps all the remaining pages are - * 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.nonlinear) - vma->vm_private_data = NULL; -out: - mutex_unlock(&mapping->i_mmap_mutex); - return ret; -} + return !page_mapped(page); +}; /** * try_to_unmap - try to remove all page table mappings to a page @@ -1631,16 +1473,28 @@ 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, + .anon_lock = page_lock_anon_vma_read, + }; + + 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; - BUG_ON(!PageLocked(page)); - VM_BUG_ON(!PageHuge(page) && PageTransHuge(page)); + 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; @@ -1663,14 +1517,19 @@ */ 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, + .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; } void __put_anon_vma(struct anon_vma *anon_vma) @@ -1682,18 +1541,13 @@ anon_vma_free(root); } -#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; - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - 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_read() @@ -1703,58 +1557,119 @@ */ anon_vma = page_anon_vma(page); if (!anon_vma) - return ret; + 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; + struct anon_vma_chain *avc; + int ret = SWAP_AGAIN; + + anon_vma = rmap_walk_anon_lock(page, rwc); + if (!anon_vma) + return ret; + + pgoff = page_to_pgoff(page); 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); - ret = rmap_one(page, vma, address, arg); + + cond_resched(); + + if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) + continue; + + ret = rwc->rmap_one(page, vma, address, rwc->arg); if (ret != SWAP_AGAIN) break; + if (rwc->done && rwc->done(page)) + break; } 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; struct vm_area_struct *vma; 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_rwsem. + */ + VM_BUG_ON_PAGE(!PageLocked(page), page); + if (!mapping) return ret; - mutex_lock(&mapping->i_mmap_mutex); + + pgoff = page_to_pgoff(page); + i_mmap_lock_read(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { unsigned long address = vma_address(page, vma); - ret = rmap_one(page, vma, address, arg); + + cond_resched(); + + if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) + continue; + + 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. - */ - mutex_unlock(&mapping->i_mmap_mutex); + +done: + i_mmap_unlock_read(mapping); 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 /*