diff options
Diffstat (limited to 'mm/madvise.c')
| -rw-r--r-- | mm/madvise.c | 61 |
1 files changed, 38 insertions, 23 deletions
diff --git a/mm/madvise.c b/mm/madvise.c index d03e149ffe6e..a56a6d17e201 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -95,9 +95,6 @@ struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma) { mmap_assert_locked(vma->vm_mm); - if (vma->vm_file) - return NULL; - return vma->anon_name; } @@ -183,7 +180,7 @@ success: * vm_flags is protected by the mmap_lock held in write mode. */ vma->vm_flags = new_flags; - if (!vma->vm_file) { + if (!vma->vm_file || vma_is_anon_shmem(vma)) { error = replace_anon_vma_name(vma, anon_name); if (error) return error; @@ -226,6 +223,7 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, put_page(page); } swap_read_unplug(splug); + cond_resched(); return 0; } @@ -321,6 +319,21 @@ static long madvise_willneed(struct vm_area_struct *vma, return 0; } +static inline bool can_do_file_pageout(struct vm_area_struct *vma) +{ + if (!vma->vm_file) + return false; + /* + * paging out pagecache only for non-anonymous mappings that correspond + * to the files the calling process could (if tried) open for writing; + * otherwise we'd be including shared non-exclusive mappings, which + * opens a side channel. + */ + return inode_owner_or_capable(&init_user_ns, + file_inode(vma->vm_file)) || + file_permission(vma->vm_file, MAY_WRITE) == 0; +} + static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -334,10 +347,14 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, spinlock_t *ptl; struct page *page = NULL; LIST_HEAD(page_list); + bool pageout_anon_only_filter; if (fatal_signal_pending(current)) return -EINTR; + pageout_anon_only_filter = pageout && !vma_is_anonymous(vma) && + !can_do_file_pageout(vma); + #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (pmd_trans_huge(*pmd)) { pmd_t orig_pmd; @@ -364,6 +381,9 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, if (page_mapcount(page) != 1) goto huge_unlock; + if (pageout_anon_only_filter && !PageAnon(page)) + goto huge_unlock; + if (next - addr != HPAGE_PMD_SIZE) { int err; @@ -432,6 +452,8 @@ regular_page: if (PageTransCompound(page)) { if (page_mapcount(page) != 1) break; + if (pageout_anon_only_filter && !PageAnon(page)) + break; get_page(page); if (!trylock_page(page)) { put_page(page); @@ -459,6 +481,9 @@ regular_page: if (!PageLRU(page) || page_mapcount(page) != 1) continue; + if (pageout_anon_only_filter && !PageAnon(page)) + continue; + VM_BUG_ON_PAGE(PageTransCompound(page), page); if (pte_young(ptent)) { @@ -553,23 +578,6 @@ static void madvise_pageout_page_range(struct mmu_gather *tlb, tlb_end_vma(tlb, vma); } -static inline bool can_do_pageout(struct vm_area_struct *vma) -{ - if (vma_is_anonymous(vma)) - return true; - if (!vma->vm_file) - return false; - /* - * paging out pagecache only for non-anonymous mappings that correspond - * to the files the calling process could (if tried) open for writing; - * otherwise we'd be including shared non-exclusive mappings, which - * opens a side channel. - */ - return inode_owner_or_capable(&init_user_ns, - file_inode(vma->vm_file)) || - file_permission(vma->vm_file, MAY_WRITE) == 0; -} - static long madvise_pageout(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start_addr, unsigned long end_addr) @@ -581,7 +589,14 @@ static long madvise_pageout(struct vm_area_struct *vma, if (!can_madv_lru_vma(vma)) return -EINVAL; - if (!can_do_pageout(vma)) + /* + * If the VMA belongs to a private file mapping, there can be private + * dirty pages which can be paged out if even this process is neither + * owner nor write capable of the file. We allow private file mappings + * further to pageout dirty anon pages. + */ + if (!vma_is_anonymous(vma) && (!can_do_file_pageout(vma) && + (vma->vm_flags & VM_MAYSHARE))) return 0; lru_add_drain(); @@ -1273,7 +1288,7 @@ static int madvise_vma_anon_name(struct vm_area_struct *vma, int error; /* Only anonymous mappings can be named */ - if (vma->vm_file) + if (vma->vm_file && !vma_is_anon_shmem(vma)) return -EBADF; error = madvise_update_vma(vma, prev, start, end, vma->vm_flags, |