Re: [PATCH 15/15] btrfs: Writeprotect mmap pages on snapshot

From: "Darrick J. Wong" <darrick.wong@oracle.com>
To: Goldwyn Rodrigues <rgoldwyn@suse.de>
Cc: linux-btrfs@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	Goldwyn Rodrigues <rgoldwyn@suse.com>
Subject: Re: [PATCH 15/15] btrfs: Writeprotect mmap pages on snapshot
Date: Thu, 28 Mar 2019 08:48:16 -0700	[thread overview]
Message-ID: <20190328154816.GG1172@magnolia> (raw)
In-Reply-To: <20190326190301.32365-16-rgoldwyn@suse.de>

On Tue, Mar 26, 2019 at 02:03:01PM -0500, Goldwyn Rodrigues wrote:
> From: Goldwyn Rodrigues <rgoldwyn@suse.com>
> 
> Inorder to make sure mmap'd files don't change after snapshot,
> writeprotect the mmap pages on snapshot. This is done by performing
> a data writeback on the pages (which simply mark the pages are
> wrprotected). This way if the user process tries to access the memory
> we will get another fault and we can perform a CoW.
> 
> In order to accomplish this, we tag all CoW pages as
> PAGECACHE_TAG_TOWRITE, and add the mmapd inode in delalloc_inodes.
> During snapshot, it starts writeback of all delalloc'd inodes and
> here we perform a data writeback. We don't want to keep the inodes
> in delalloc_inodes until it umount (WARN_ON), so we remove it
> during inode evictions.
> 
> This looks hackish. Other alternatives could be to create another
> list for mmap'd files or rename delalloc_inodes to writeback_inodes.
> Suggestions?

Is there a function to invalidate only the writable mappings in the
pagecache?  Could there be?

> Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
> ---
>  fs/btrfs/ctree.h |  3 ++-
>  fs/btrfs/dax.c   |  7 +++++++
>  fs/btrfs/inode.c | 13 ++++++++++++-
>  fs/dax.c         |  3 +++
>  4 files changed, 24 insertions(+), 2 deletions(-)
> 
> diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
> index 21068dc4a95a..68a63d93556a 100644
> --- a/fs/btrfs/ctree.h
> +++ b/fs/btrfs/ctree.h
> @@ -3252,7 +3252,8 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
>  			     struct btrfs_root *new_root,
>  			     struct btrfs_root *parent_root,
>  			     u64 new_dirid);
> - void btrfs_set_delalloc_extent(struct inode *inode, struct extent_state *state,
> +void btrfs_add_delalloc_inodes(struct btrfs_root *root, struct inode *inode);
> +void btrfs_set_delalloc_extent(struct inode *inode, struct extent_state *state,
>  			       unsigned *bits);
>  void btrfs_clear_delalloc_extent(struct inode *inode,
>  				 struct extent_state *state, unsigned *bits);
> diff --git a/fs/btrfs/dax.c b/fs/btrfs/dax.c
> index d73945d50b88..bcb961242c74 100644
> --- a/fs/btrfs/dax.c
> +++ b/fs/btrfs/dax.c
> @@ -166,10 +166,17 @@ vm_fault_t btrfs_dax_fault(struct vm_fault *vmf)
>  {
>  	vm_fault_t ret;
>  	pfn_t pfn;
> +	struct inode *inode = file_inode(vmf->vma->vm_file);
> +	struct btrfs_inode *binode = BTRFS_I(inode);
>  	ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &pfn, NULL, &btrfs_iomap_ops);
>  	if (ret & VM_FAULT_NEEDDSYNC)
>  		ret = dax_finish_sync_fault(vmf, PE_SIZE_PTE, pfn);
>  
> +	/* Insert into delalloc so we get writeback calls on snapshots */
> +	if (vmf->flags & FAULT_FLAG_WRITE &&
> +			!test_bit(BTRFS_INODE_IN_DELALLOC_LIST, &binode->runtime_flags))
> +		btrfs_add_delalloc_inodes(binode->root, inode);
> +
>  	return ret;
>  }
>  
> diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
> index 5350e5f23728..3b72c1c96b34 100644
> --- a/fs/btrfs/inode.c
> +++ b/fs/btrfs/inode.c
> @@ -1713,7 +1713,7 @@ void btrfs_merge_delalloc_extent(struct inode *inode, struct extent_state *new,
>  	spin_unlock(&BTRFS_I(inode)->lock);
>  }
>  
> -static void btrfs_add_delalloc_inodes(struct btrfs_root *root,
> +void btrfs_add_delalloc_inodes(struct btrfs_root *root,
>  				      struct inode *inode)
>  {
>  	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
> @@ -5358,12 +5358,17 @@ void btrfs_evict_inode(struct inode *inode)
>  {
>  	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
>  	struct btrfs_trans_handle *trans;
> +	struct btrfs_inode *binode = BTRFS_I(inode);
>  	struct btrfs_root *root = BTRFS_I(inode)->root;
>  	struct btrfs_block_rsv *rsv;
>  	int ret;
>  
>  	trace_btrfs_inode_evict(inode);
>  
> +	if (IS_DAX(inode)
> +	    && test_bit(BTRFS_INODE_IN_DELALLOC_LIST, &binode->runtime_flags))
> +		btrfs_del_delalloc_inode(root, binode);
> +
>  	if (!root) {
>  		clear_inode(inode);
>  		return;
> @@ -8683,6 +8688,10 @@ static int btrfs_dax_writepages(struct address_space *mapping,
>  {
>  	struct inode *inode = mapping->host;
>  	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
> +	struct btrfs_inode *binode = BTRFS_I(inode);
> +	if ((wbc->sync_mode == WB_SYNC_ALL) &&
> +	    test_bit(BTRFS_INODE_IN_DELALLOC_LIST, &binode->runtime_flags))
> +		btrfs_del_delalloc_inode(binode->root, binode);
>  	return dax_writeback_mapping_range(mapping, fs_info->fs_devices->latest_bdev,
>  			wbc);
>  }
> @@ -9981,6 +9990,8 @@ static void btrfs_run_delalloc_work(struct btrfs_work *work)
>  	delalloc_work = container_of(work, struct btrfs_delalloc_work,
>  				     work);
>  	inode = delalloc_work->inode;
> +	if (IS_DAX(inode))
> +		filemap_fdatawrite(inode->i_mapping);
>  	filemap_flush(inode->i_mapping);
>  	if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
>  				&BTRFS_I(inode)->runtime_flags))
> diff --git a/fs/dax.c b/fs/dax.c
> index 93146142bb00..c42e9cb486ef 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
> @@ -753,6 +753,9 @@ static void *dax_insert_entry(struct xa_state *xas,
>  	if (dirty)
>  		xas_set_mark(xas, PAGECACHE_TAG_DIRTY);
>  
> +	if (cow)
> +		xas_set_mark(xas, PAGECACHE_TAG_TOWRITE);
> +

Was this supposed to go with the dax_insert_entry changes (patch 9)?

--D

>  	xas_unlock_irq(xas);
>  	return entry;
>  }
> -- 
> 2.16.4
> 