diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 76efe5b71d7d..3120f8dd2c31 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -512,16 +512,24 @@ locking rules: BKL mmap_sem PageLocked(page) open: no yes close: no yes -fault: no yes -page_mkwrite: no yes no +fault: no yes can return with page locked +page_mkwrite: no yes can return with page locked access: no yes - ->page_mkwrite() is called when a previously read-only page is -about to become writeable. The file system is responsible for -protecting against truncate races. Once appropriate action has been -taking to lock out truncate, the page range should be verified to be -within i_size. The page mapping should also be checked that it is not -NULL. + ->fault() is called when a previously not present pte is about +to be faulted in. The filesystem must find and return the page associated +with the passed in "pgoff" in the vm_fault structure. If it is possible that +the page may be truncated and/or invalidated, then the filesystem must lock +the page, then ensure it is not already truncated (the page lock will block +subsequent truncate), and then return with VM_FAULT_LOCKED, and the page +locked. The VM will unlock the page. + + ->page_mkwrite() is called when a previously read-only pte is +about to become writeable. The filesystem again must ensure that there are +no truncate/invalidate races, and then return with the page locked. If +the page has been truncated, the filesystem should not look up a new page +like the ->fault() handler, but simply return with VM_FAULT_NOPAGE, which +will cause the VM to retry the fault. ->access() is called when get_user_pages() fails in acces_process_vm(), typically used to debug a process through diff --git a/fs/buffer.c b/fs/buffer.c index b3e5be7514f5..aed297739eb0 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2397,7 +2397,8 @@ block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, if ((page->mapping != inode->i_mapping) || (page_offset(page) > size)) { /* page got truncated out from underneath us */ - goto out_unlock; + unlock_page(page); + goto out; } /* page is wholly or partially inside EOF */ @@ -2411,14 +2412,15 @@ block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, ret = block_commit_write(page, 0, end); if (unlikely(ret)) { + unlock_page(page); if (ret == -ENOMEM) ret = VM_FAULT_OOM; else /* -ENOSPC, -EIO, etc */ ret = VM_FAULT_SIGBUS; - } + } else + ret = VM_FAULT_LOCKED; -out_unlock: - unlock_page(page); +out: return ret; } diff --git a/mm/memory.c b/mm/memory.c index 6a4ef0fd0711..4126dd16778c 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1971,6 +1971,15 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, ret = tmp; goto unwritable_page; } + if (unlikely(!(tmp & VM_FAULT_LOCKED))) { + lock_page(old_page); + if (!old_page->mapping) { + ret = 0; /* retry the fault */ + unlock_page(old_page); + goto unwritable_page; + } + } else + VM_BUG_ON(!PageLocked(old_page)); /* * Since we dropped the lock we need to revalidate @@ -1980,9 +1989,11 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, */ page_table = pte_offset_map_lock(mm, pmd, address, &ptl); - page_cache_release(old_page); - if (!pte_same(*page_table, orig_pte)) + if (!pte_same(*page_table, orig_pte)) { + unlock_page(old_page); + page_cache_release(old_page); goto unlock; + } page_mkwrite = 1; } @@ -2094,9 +2105,6 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, unlock: pte_unmap_unlock(page_table, ptl); if (dirty_page) { - if (vma->vm_file) - file_update_time(vma->vm_file); - /* * Yes, Virginia, this is actually required to prevent a race * with clear_page_dirty_for_io() from clearing the page dirty @@ -2105,16 +2113,41 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, * * do_no_page is protected similarly. */ - wait_on_page_locked(dirty_page); - set_page_dirty_balance(dirty_page, page_mkwrite); + if (!page_mkwrite) { + wait_on_page_locked(dirty_page); + set_page_dirty_balance(dirty_page, page_mkwrite); + } put_page(dirty_page); + if (page_mkwrite) { + struct address_space *mapping = dirty_page->mapping; + + set_page_dirty(dirty_page); + unlock_page(dirty_page); + page_cache_release(dirty_page); + if (mapping) { + /* + * Some device drivers do not set page.mapping + * but still dirty their pages + */ + balance_dirty_pages_ratelimited(mapping); + } + } + + /* file_update_time outside page_lock */ + if (vma->vm_file) + file_update_time(vma->vm_file); } return ret; oom_free_new: page_cache_release(new_page); oom: - if (old_page) + if (old_page) { + if (page_mkwrite) { + unlock_page(old_page); + page_cache_release(old_page); + } page_cache_release(old_page); + } return VM_FAULT_OOM; unwritable_page: @@ -2664,27 +2697,22 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, int tmp; unlock_page(page); - vmf.flags |= FAULT_FLAG_MKWRITE; + vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; tmp = vma->vm_ops->page_mkwrite(vma, &vmf); if (unlikely(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { ret = tmp; - anon = 1; /* no anon but release vmf.page */ - goto out_unlocked; - } - lock_page(page); - /* - * XXX: this is not quite right (racy vs - * invalidate) to unlock and relock the page - * like this, however a better fix requires - * reworking page_mkwrite locking API, which - * is better done later. - */ - if (!page->mapping) { - ret = 0; - anon = 1; /* no anon but release vmf.page */ - goto out; + goto unwritable_page; } + if (unlikely(!(tmp & VM_FAULT_LOCKED))) { + lock_page(page); + if (!page->mapping) { + ret = 0; /* retry the fault */ + unlock_page(page); + goto unwritable_page; + } + } else + VM_BUG_ON(!PageLocked(page)); page_mkwrite = 1; } } @@ -2736,19 +2764,35 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, pte_unmap_unlock(page_table, ptl); out: - unlock_page(vmf.page); -out_unlocked: - if (anon) - page_cache_release(vmf.page); - else if (dirty_page) { + if (dirty_page) { + struct address_space *mapping = page->mapping; + + if (set_page_dirty(dirty_page)) + page_mkwrite = 1; + unlock_page(dirty_page); + put_page(dirty_page); + if (page_mkwrite && mapping) { + /* + * Some device drivers do not set page.mapping but still + * dirty their pages + */ + balance_dirty_pages_ratelimited(mapping); + } + + /* file_update_time outside page_lock */ if (vma->vm_file) file_update_time(vma->vm_file); - - set_page_dirty_balance(dirty_page, page_mkwrite); - put_page(dirty_page); + } else { + unlock_page(vmf.page); + if (anon) + page_cache_release(vmf.page); } return ret; + +unwritable_page: + page_cache_release(page); + return ret; } static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,