On 01/08, Andreas Gruenbacher wrote:
> Hi Darrick,
>
> here's an updated version with the latest feedback incorporated. Hope
> you find that useful.
>
> As far as the f2fs merge conflict goes, I've been told by Linus not to
> resolve those kinds of conflicts but to point them out when sending the
> merge request. So this shouldn't be a big deal.
>
> Changes:
>
> * Turn page_mkwrite_check_truncate into a non-inline function.
> * Get rid of now-unused mapping variable in ext4_page_mkwrite.
> * In btrfs_page_mkwrite, don't ignore the return value of
> block_page_mkwrite_return (no change in behavior).
> * Clean up the f2fs_vm_page_mkwrite changes as suggested by
> Jaegeuk Kim.
>
> Thanks,
> Andreas
>
> --
>
> The check in block_page_mkwrite that is meant to determine whether an
> offset is within the inode size is off by one. This bug has been copied
> into iomap_page_mkwrite and several filesystems (ubifs, ext4, f2fs,
> ceph).
>
> Fix that by introducing a new page_mkwrite_check_truncate helper that
> checks for truncate and computes the bytes in the page up to EOF. Use
> the helper in the above mentioned filesystems.
>
> In addition, use the new helper in btrfs as well.
>
> Signed-off-by: Andreas Gruenbacher <agruenba@xxxxxxxxxx>
> Acked-by: David Sterba <dsterba@xxxxxxxx> (btrfs)
> Acked-by: Richard Weinberger <richard@xxxxxx> (ubifs)
> Acked-by: Theodore Ts'o <tytso@xxxxxxx> (ext4)
> Acked-by: Chao Yu <yuchao0@xxxxxxxxxx> (f2fs)
Acked-by: Jaegeuk Kim <jaegeuk@xxxxxxxxxx>
> ---
> fs/btrfs/inode.c | 16 +++++-----------
> fs/buffer.c | 16 +++-------------
> fs/ceph/addr.c | 2 +-
> fs/ext4/inode.c | 15 ++++-----------
> fs/f2fs/file.c | 19 +++++++------------
> fs/iomap/buffered-io.c | 18 +++++-------------
> fs/ubifs/file.c | 3 +--
> include/linux/pagemap.h | 2 ++
> mm/filemap.c | 28 ++++++++++++++++++++++++++++
> 9 files changed, 56 insertions(+), 63 deletions(-)
>
> diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
> index e3c76645cad7..23e6f614e000 100644
> --- a/fs/btrfs/inode.c
> +++ b/fs/btrfs/inode.c
> @@ -9011,16 +9011,15 @@ vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
> goto out_noreserve;
> }
>
> - ret = VM_FAULT_NOPAGE; /* make the VM retry the fault */
> again:
> lock_page(page);
> - size = i_size_read(inode);
>
> - if ((page->mapping != inode->i_mapping) ||
> - (page_start >= size)) {
> - /* page got truncated out from underneath us */
> + ret2 = page_mkwrite_check_truncate(page, inode);
> + if (ret2 < 0) {
> + ret = block_page_mkwrite_return(ret2);
> goto out_unlock;
> }
> + zero_start = ret2;
> wait_on_page_writeback(page);
>
> lock_extent_bits(io_tree, page_start, page_end, &cached_state);
> @@ -9041,6 +9040,7 @@ vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
> goto again;
> }
>
> + size = i_size_read(inode);
> if (page->index == ((size - 1) >> PAGE_SHIFT)) {
> reserved_space = round_up(size - page_start,
> fs_info->sectorsize);
> @@ -9073,12 +9073,6 @@ vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
> }
> ret2 = 0;
>
> - /* page is wholly or partially inside EOF */
> - if (page_start + PAGE_SIZE > size)
> - zero_start = offset_in_page(size);
> - else
> - zero_start = PAGE_SIZE;
> -
> if (zero_start != PAGE_SIZE) {
> kaddr = kmap(page);
> memset(kaddr + zero_start, 0, PAGE_SIZE - zero_start);
> diff --git a/fs/buffer.c b/fs/buffer.c
> index d8c7242426bb..53aabde57ca7 100644
> --- a/fs/buffer.c
> +++ b/fs/buffer.c
> @@ -2499,23 +2499,13 @@ int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
> struct page *page = vmf->page;
> struct inode *inode = file_inode(vma->vm_file);
> unsigned long end;
> - loff_t size;
> int ret;
>
> lock_page(page);
> - size = i_size_read(inode);
> - if ((page->mapping != inode->i_mapping) ||
> - (page_offset(page) > size)) {
> - /* We overload EFAULT to mean page got truncated */
> - ret = -EFAULT;
> + ret = page_mkwrite_check_truncate(page, inode);
> + if (ret < 0)
> goto out_unlock;
> - }
> -
> - /* page is wholly or partially inside EOF */
> - if (((page->index + 1) << PAGE_SHIFT) > size)
> - end = size & ~PAGE_MASK;
> - else
> - end = PAGE_SIZE;
> + end = ret;
>
> ret = __block_write_begin(page, 0, end, get_block);
> if (!ret)
> diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
> index 7ab616601141..ef958aa4adb4 100644
> --- a/fs/ceph/addr.c
> +++ b/fs/ceph/addr.c
> @@ -1575,7 +1575,7 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf)
> do {
> lock_page(page);
>
> - if ((off > size) || (page->mapping != inode->i_mapping)) {
> + if (page_mkwrite_check_truncate(page, inode) < 0) {
> unlock_page(page);
> ret = VM_FAULT_NOPAGE;
> break;
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index 629a25d999f0..3244803df30a 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -5871,13 +5871,11 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
> {
> struct vm_area_struct *vma = vmf->vma;
> struct page *page = vmf->page;
> - loff_t size;
> unsigned long len;
> int err;
> vm_fault_t ret;
> struct file *file = vma->vm_file;
> struct inode *inode = file_inode(file);
> - struct address_space *mapping = inode->i_mapping;
> handle_t *handle;
> get_block_t *get_block;
> int retries = 0;
> @@ -5907,18 +5905,13 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
> }
>
> lock_page(page);
> - size = i_size_read(inode);
> - /* Page got truncated from under us? */
> - if (page->mapping != mapping || page_offset(page) > size) {
> + err = page_mkwrite_check_truncate(page, inode);
> + if (err < 0) {
> unlock_page(page);
> - ret = VM_FAULT_NOPAGE;
> - goto out;
> + goto out_ret;
> }
> + len = err;
>
> - if (page->index == size >> PAGE_SHIFT)
> - len = size & ~PAGE_MASK;
> - else
> - len = PAGE_SIZE;
> /*
> * Return if we have all the buffers mapped. This avoids the need to do
> * journal_start/journal_stop which can block and take a long time
> diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
> index 85af112e868d..c2d919210a26 100644
> --- a/fs/f2fs/file.c
> +++ b/fs/f2fs/file.c
> @@ -51,7 +51,7 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
> struct inode *inode = file_inode(vmf->vma->vm_file);
> struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
> struct dnode_of_data dn = { .node_changed = false };
> - int err;
> + int offset, err;
>
> if (unlikely(f2fs_cp_error(sbi))) {
> err = -EIO;
> @@ -70,11 +70,12 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
> file_update_time(vmf->vma->vm_file);
> down_read(&F2FS_I(inode)->i_mmap_sem);
> lock_page(page);
> - if (unlikely(page->mapping != inode->i_mapping ||
> - page_offset(page) > i_size_read(inode) ||
> - !PageUptodate(page))) {
> + offset = -EFAULT;
> + if (likely(PageUptodate(page)))
> + offset = page_mkwrite_check_truncate(page, inode);
> + if (unlikely(offset < 0)) {
> unlock_page(page);
> - err = -EFAULT;
> + err = offset;
> goto out_sem;
> }
>
> @@ -101,14 +102,8 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
> if (PageMappedToDisk(page))
> goto out_sem;
>
> - /* page is wholly or partially inside EOF */
> - if (((loff_t)(page->index + 1) << PAGE_SHIFT) >
> - i_size_read(inode)) {
> - loff_t offset;
> -
> - offset = i_size_read(inode) & ~PAGE_MASK;
> + if (offset != PAGE_SIZE)
> zero_user_segment(page, offset, PAGE_SIZE);
> - }
> set_page_dirty(page);
> if (!PageUptodate(page))
> SetPageUptodate(page);
> diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
> index 828444e14d09..7c84c4c027c4 100644
> --- a/fs/iomap/buffered-io.c
> +++ b/fs/iomap/buffered-io.c
> @@ -1077,24 +1077,16 @@ vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops)
> struct page *page = vmf->page;
> struct inode *inode = file_inode(vmf->vma->vm_file);
> unsigned long length;
> - loff_t offset, size;
> + loff_t offset;
> ssize_t ret;
>
> lock_page(page);
> - size = i_size_read(inode);
> - offset = page_offset(page);
> - if (page->mapping != inode->i_mapping || offset > size) {
> - /* We overload EFAULT to mean page got truncated */
> - ret = -EFAULT;
> + ret = page_mkwrite_check_truncate(page, inode);
> + if (ret < 0)
> goto out_unlock;
> - }
> -
> - /* page is wholly or partially inside EOF */
> - if (offset > size - PAGE_SIZE)
> - length = offset_in_page(size);
> - else
> - length = PAGE_SIZE;
> + length = ret;
>
> + offset = page_offset(page);
> while (length > 0) {
> ret = iomap_apply(inode, offset, length,
> IOMAP_WRITE | IOMAP_FAULT, ops, page,
> diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
> index cd52585c8f4f..91f7a1f2db0d 100644
> --- a/fs/ubifs/file.c
> +++ b/fs/ubifs/file.c
> @@ -1563,8 +1563,7 @@ static vm_fault_t ubifs_vm_page_mkwrite(struct vm_fault *vmf)
> }
>
> lock_page(page);
> - if (unlikely(page->mapping != inode->i_mapping ||
> - page_offset(page) > i_size_read(inode))) {
> + if (unlikely(page_mkwrite_check_truncate(page, inode) < 0)) {
> /* Page got truncated out from underneath us */
> goto sigbus;
> }
> diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
> index 37a4d9e32cd3..6c9c5b88924d 100644
> --- a/include/linux/pagemap.h
> +++ b/include/linux/pagemap.h
> @@ -636,4 +636,6 @@ static inline unsigned long dir_pages(struct inode *inode)
> PAGE_SHIFT;
> }
>
> +int page_mkwrite_check_truncate(struct page *page, struct inode *inode);
> +
> #endif /* _LINUX_PAGEMAP_H */
> diff --git a/mm/filemap.c b/mm/filemap.c
> index bf6aa30be58d..d3e2766216e3 100644
> --- a/mm/filemap.c
> +++ b/mm/filemap.c
> @@ -2700,6 +2700,34 @@ const struct vm_operations_struct generic_file_vm_ops = {
> .page_mkwrite = filemap_page_mkwrite,
> };
>
> +/**
> + * page_mkwrite_check_truncate - check if page was truncated
> + * @page: the page to check
> + * @inode: the inode to check the page against
> + *
> + * Returns the number of bytes in the page up to EOF,
> + * or -EFAULT if the page was truncated.
> + */
> +int page_mkwrite_check_truncate(struct page *page, struct inode *inode)
> +{
> + loff_t size = i_size_read(inode);
> + pgoff_t index = size >> PAGE_SHIFT;
> + int offset = offset_in_page(size);
> +
> + if (page->mapping != inode->i_mapping)
> + return -EFAULT;
> +
> + /* page is wholly inside EOF */
> + if (page->index < index)
> + return PAGE_SIZE;
> + /* page is wholly past EOF */
> + if (page->index > index || !offset)
> + return -EFAULT;
> + /* page is partially inside EOF */
> + return offset;
> +}
> +EXPORT_SYMBOL(page_mkwrite_check_truncate);
> +
> /* This is used for a general mmap of a disk file */
>
> int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
> --
> 2.20.1
