From 051ac83adf69eea4f57a97356e4282e395a5fa6d Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 21 Jan 2014 15:49:48 -0800 Subject: mm/rmap: make rmap_walk to get the rmap_walk_control argument In each rmap traverse case, there is some difference so that we need function pointers and arguments to them in order to handle these For this purpose, struct rmap_walk_control is introduced in this patch, and will be extended in following patch. Introducing and extending are separate, because it clarify changes. Signed-off-by: Joonsoo Kim Reviewed-by: Naoya Horiguchi Cc: Mel Gorman Cc: Hugh Dickins Cc: Rik van Riel Cc: Ingo Molnar Cc: Hillf Danton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux/rmap.h') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 6dacb93a6d9..6a456ce6de2 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -235,11 +235,16 @@ struct anon_vma *page_lock_anon_vma_read(struct page *page); void page_unlock_anon_vma_read(struct anon_vma *anon_vma); int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); +struct rmap_walk_control { + void *arg; + int (*rmap_one)(struct page *page, struct vm_area_struct *vma, + unsigned long addr, void *arg); +}; + /* * Called by migrate.c to remove migration ptes, but might be used more later. */ -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); #else /* !CONFIG_MMU */ -- cgit v1.2.3-70-g09d2 From 0dd1c7bbce8d1d142bb25aefaa50262dfd77cb78 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 21 Jan 2014 15:49:49 -0800 Subject: mm/rmap: extend rmap_walk_xxx() to cope with different cases There are a lot of common parts in traversing functions, but there are also a little of uncommon parts in it. By assigning proper function pointer on each rmap_walker_control, we can handle these difference correctly. Following are differences we should handle. 1. difference of lock function in anon mapping case 2. nonlinear handling in file mapping case 3. prechecked condition: checking memcg in page_referenced(), checking VM_SHARE in page_mkclean() checking temporary vma in try_to_unmap() 4. exit condition: checking page_mapped() in try_to_unmap() So, in this patch, I introduce 4 function pointers to handle above differences. Signed-off-by: Joonsoo Kim Cc: Naoya Horiguchi Cc: Mel Gorman Cc: Hugh Dickins Cc: Rik van Riel Cc: Ingo Molnar Cc: Hillf Danton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 15 +++++++++++++++ mm/ksm.c | 7 +++++++ mm/rmap.c | 37 +++++++++++++++++++++++++++++-------- 3 files changed, 51 insertions(+), 8 deletions(-) (limited to 'include/linux/rmap.h') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 6a456ce6de2..616aa4d05f0 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -235,10 +235,25 @@ struct anon_vma *page_lock_anon_vma_read(struct page *page); void page_unlock_anon_vma_read(struct anon_vma *anon_vma); int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); +/* + * rmap_walk_control: To control rmap traversing for specific needs + * + * arg: passed to rmap_one() and invalid_vma() + * rmap_one: executed on each vma where page is mapped + * done: for checking traversing termination condition + * file_nonlinear: for handling file nonlinear mapping + * anon_lock: for getting anon_lock by optimized way rather than default + * invalid_vma: for skipping uninterested vma + */ struct rmap_walk_control { void *arg; int (*rmap_one)(struct page *page, struct vm_area_struct *vma, unsigned long addr, void *arg); + int (*done)(struct page *page); + int (*file_nonlinear)(struct page *, struct address_space *, + struct vm_area_struct *vma); + struct anon_vma *(*anon_lock)(struct page *page); + bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; /* diff --git a/mm/ksm.c b/mm/ksm.c index c3035fee808..91b8cb35f7c 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -2032,12 +2032,19 @@ again: if ((rmap_item->mm == vma->vm_mm) == search_new_forks) continue; + if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) + continue; + ret = rwc->rmap_one(page, vma, rmap_item->address, rwc->arg); if (ret != SWAP_AGAIN) { anon_vma_unlock_read(anon_vma); goto out; } + if (rwc->done && rwc->done(page)) { + anon_vma_unlock_read(anon_vma); + goto out; + } } anon_vma_unlock_read(anon_vma); } diff --git a/mm/rmap.c b/mm/rmap.c index f8f10ad5d35..97bf8f0396f 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1684,10 +1684,14 @@ void __put_anon_vma(struct anon_vma *anon_vma) } #ifdef CONFIG_MIGRATION -static struct anon_vma *rmap_walk_anon_lock(struct page *page) +static struct anon_vma *rmap_walk_anon_lock(struct page *page, + struct rmap_walk_control *rwc) { struct anon_vma *anon_vma; + if (rwc->anon_lock) + return rwc->anon_lock(page); + /* * Note: remove_migration_ptes() cannot use page_lock_anon_vma_read() * because that depends on page_mapped(); but not all its usages @@ -1713,16 +1717,22 @@ static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc) struct anon_vma_chain *avc; int ret = SWAP_AGAIN; - anon_vma = rmap_walk_anon_lock(page); + anon_vma = rmap_walk_anon_lock(page, rwc); if (!anon_vma) return ret; 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 (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; @@ -1740,15 +1750,26 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc) mutex_lock(&mapping->i_mmap_mutex); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { unsigned long address = vma_address(page, vma); + + 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. - */ + + if (!rwc->file_nonlinear) + goto done; + + if (list_empty(&mapping->i_mmap_nonlinear)) + goto done; + + ret = rwc->file_nonlinear(page, mapping, vma); + +done: mutex_unlock(&mapping->i_mmap_mutex); return ret; } -- cgit v1.2.3-70-g09d2 From 52629506420ce32997f1fba0a1ab2f1aaa9a4f79 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 21 Jan 2014 15:49:50 -0800 Subject: mm/rmap: use rmap_walk() in try_to_unmap() Now, we have an infrastructure in rmap_walk() to handle difference from variants of rmap traversing functions. So, just use it in try_to_unmap(). In this patch, I change following things. 1. enable rmap_walk() if !CONFIG_MIGRATION. 2. mechanical change to use rmap_walk() in try_to_unmap(). Signed-off-by: Joonsoo Kim Reviewed-by: Naoya Horiguchi Cc: Mel Gorman Cc: Hugh Dickins Cc: Rik van Riel Cc: Ingo Molnar Cc: Hillf Danton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 5 +---- mm/ksm.c | 4 ++-- mm/rmap.c | 48 ++++++++++++++++++++++++++++++++++++------------ 3 files changed, 39 insertions(+), 18 deletions(-) (limited to 'include/linux/rmap.h') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 616aa4d05f0..2462458708c 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -190,7 +190,7 @@ int page_referenced_one(struct page *, struct vm_area_struct *, int try_to_unmap(struct page *, enum ttu_flags flags); int try_to_unmap_one(struct page *, struct vm_area_struct *, - unsigned long address, enum ttu_flags flags); + unsigned long address, void *arg); /* * Called from mm/filemap_xip.c to unmap empty zero page @@ -256,9 +256,6 @@ struct rmap_walk_control { bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; -/* - * Called by migrate.c to remove migration ptes, but might be used more later. - */ int rmap_walk(struct page *page, struct rmap_walk_control *rwc); #else /* !CONFIG_MMU */ diff --git a/mm/ksm.c b/mm/ksm.c index 91b8cb35f7c..6b4baa97f4c 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -1982,7 +1982,7 @@ again: continue; ret = try_to_unmap_one(page, vma, - rmap_item->address, flags); + rmap_item->address, (void *)flags); if (ret != SWAP_AGAIN || !page_mapped(page)) { anon_vma_unlock_read(anon_vma); goto out; @@ -1996,7 +1996,6 @@ out: return ret; } -#ifdef CONFIG_MIGRATION int rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc) { struct stable_node *stable_node; @@ -2054,6 +2053,7 @@ out: return ret; } +#ifdef CONFIG_MIGRATION void ksm_migrate_page(struct page *newpage, struct page *oldpage) { struct stable_node *stable_node; diff --git a/mm/rmap.c b/mm/rmap.c index 97bf8f0396f..b3263cb3236 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1179,15 +1179,18 @@ out: /* * 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) + 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) @@ -1513,6 +1516,11 @@ bool is_vma_temporary_stack(struct vm_area_struct *vma) return false; } +static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) +{ + return is_vma_temporary_stack(vma); +} + /** * try_to_unmap_anon - unmap or unlock anonymous page using the object-based * rmap method @@ -1558,7 +1566,7 @@ static int try_to_unmap_anon(struct page *page, enum ttu_flags flags) continue; address = vma_address(page, vma); - ret = try_to_unmap_one(page, vma, address, flags); + ret = try_to_unmap_one(page, vma, address, (void *)flags); if (ret != SWAP_AGAIN || !page_mapped(page)) break; } @@ -1592,7 +1600,7 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) 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); + ret = try_to_unmap_one(page, vma, address, (void *)flags); if (ret != SWAP_AGAIN || !page_mapped(page)) goto out; } @@ -1614,6 +1622,11 @@ out: return ret; } +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 @@ -1631,16 +1644,29 @@ 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(!PageHuge(page) && PageTransHuge(page)); - 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); + /* + * 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 (ret != SWAP_MLOCK && !page_mapped(page)) ret = SWAP_SUCCESS; return ret; @@ -1683,7 +1709,6 @@ void __put_anon_vma(struct anon_vma *anon_vma) anon_vma_free(anon_vma); } -#ifdef CONFIG_MIGRATION static struct anon_vma *rmap_walk_anon_lock(struct page *page, struct rmap_walk_control *rwc) { @@ -1785,7 +1810,6 @@ int rmap_walk(struct page *page, struct rmap_walk_control *rwc) else return rmap_walk_file(page, rwc); } -#endif /* CONFIG_MIGRATION */ #ifdef CONFIG_HUGETLB_PAGE /* -- cgit v1.2.3-70-g09d2 From 9f32624be943538983eb0f18b73a9052d1493c80 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 21 Jan 2014 15:49:53 -0800 Subject: mm/rmap: use rmap_walk() in page_referenced() Now, we have an infrastructure in rmap_walk() to handle difference from variants of rmap traversing functions. So, just use it in page_referenced(). In this patch, I change following things. 1. remove some variants of rmap traversing functions. cf> page_referenced_ksm, page_referenced_anon, page_referenced_file 2. introduce new struct page_referenced_arg and pass it to page_referenced_one(), main function of rmap_walk, in order to count reference, to store vm_flags and to check finish condition. 3. mechanical change to use rmap_walk() in page_referenced(). [liwanp@linux.vnet.ibm.com: fix BUG at rmap_walk] Signed-off-by: Joonsoo Kim Reviewed-by: Naoya Horiguchi Cc: Mel Gorman Cc: Hugh Dickins Cc: Rik van Riel Cc: Ingo Molnar Cc: Hillf Danton Signed-off-by: Wanpeng Li Cc: Sasha Levin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ksm.h | 2 - include/linux/rmap.h | 2 +- mm/ksm.c | 60 ++------------- mm/rmap.c | 210 ++++++++++++++++++--------------------------------- 4 files changed, 80 insertions(+), 194 deletions(-) (limited to 'include/linux/rmap.h') diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 91b9719722c..3be6bb18562 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -73,8 +73,6 @@ static inline void set_page_stable_node(struct page *page, struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address); -int page_referenced_ksm(struct page *page, - struct mem_cgroup *memcg, unsigned long *vm_flags); int rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc); void ksm_migrate_page(struct page *newpage, struct page *oldpage); diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 2462458708c..1da693d5125 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -184,7 +184,7 @@ static inline void page_dup_rmap(struct page *page) int page_referenced(struct page *, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags); int page_referenced_one(struct page *, struct vm_area_struct *, - unsigned long address, unsigned int *mapcount, unsigned long *vm_flags); + unsigned long address, void *arg); #define TTU_ACTION(x) ((x) & TTU_ACTION_MASK) diff --git a/mm/ksm.c b/mm/ksm.c index 646d45a6b6c..3df141e5f3e 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -1891,61 +1891,6 @@ struct page *ksm_might_need_to_copy(struct page *page, return new_page; } -int page_referenced_ksm(struct page *page, struct mem_cgroup *memcg, - unsigned long *vm_flags) -{ - struct stable_node *stable_node; - struct rmap_item *rmap_item; - unsigned int mapcount = page_mapcount(page); - int referenced = 0; - int search_new_forks = 0; - - VM_BUG_ON(!PageKsm(page)); - VM_BUG_ON(!PageLocked(page)); - - stable_node = page_stable_node(page); - if (!stable_node) - return 0; -again: - hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { - struct anon_vma *anon_vma = rmap_item->anon_vma; - struct anon_vma_chain *vmac; - struct vm_area_struct *vma; - - anon_vma_lock_read(anon_vma); - anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root, - 0, ULONG_MAX) { - vma = vmac->vma; - if (rmap_item->address < vma->vm_start || - rmap_item->address >= vma->vm_end) - continue; - /* - * Initially we examine only the vma which covers this - * rmap_item; but later, if there is still work to do, - * we examine covering vmas in other mms: in case they - * were forked from the original since ksmd passed. - */ - if ((rmap_item->mm == vma->vm_mm) == search_new_forks) - continue; - - if (memcg && !mm_match_cgroup(vma->vm_mm, memcg)) - continue; - - referenced += page_referenced_one(page, vma, - rmap_item->address, &mapcount, vm_flags); - if (!search_new_forks || !mapcount) - break; - } - anon_vma_unlock_read(anon_vma); - if (!mapcount) - goto out; - } - if (!search_new_forks++) - goto again; -out: - return referenced; -} - int rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc) { struct stable_node *stable_node; @@ -1954,6 +1899,11 @@ int rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc) int search_new_forks = 0; VM_BUG_ON(!PageKsm(page)); + + /* + * Rely on the page lock to protect against concurrent modifications + * to that page's node of the stable tree. + */ VM_BUG_ON(!PageLocked(page)); stable_node = page_stable_node(page); diff --git a/mm/rmap.c b/mm/rmap.c index c73e0c645d0..08041303640 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -660,17 +660,22 @@ 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) + 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; @@ -682,13 +687,12 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma, pmd = page_check_address_pmd(page, mm, address, PAGE_CHECK_ADDRESS_PMD_FLAG, &ptl); if (!pmd) - goto out; + return SWAP_AGAIN; if (vma->vm_flags & VM_LOCKED) { spin_unlock(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 */ } /* go ahead even if the pmd is pmd_trans_splitting() */ @@ -704,13 +708,12 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma, */ 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)) { @@ -727,113 +730,27 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma, pte_unmap_unlock(pte, ptl); } - (*mapcount)--; - - if (referenced) - *vm_flags |= vma->vm_flags; -out: - return 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)); + struct page_referenced_arg *pra = arg; + struct mem_cgroup *memcg = pra->memcg; - /* - * 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)); - - 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; } /** @@ -851,32 +768,47 @@ int page_referenced(struct page *page, 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_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, @@ -1700,6 +1632,14 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc) 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_mutex. + */ + VM_BUG_ON(!PageLocked(page)); + if (!mapping) return ret; mutex_lock(&mapping->i_mmap_mutex); @@ -1731,8 +1671,6 @@ done: 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, rwc); else if (PageAnon(page)) -- cgit v1.2.3-70-g09d2