linux-kernel - Re: [PATCH v2] f2fs: fix out-of-free problem caused by atomic write

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Thu, 2 Nov 2017 20:46:18 -0700
From:   Jaegeuk Kim <jaegeuk@...nel.org>
To:     Yunlong Song <yunlong.song@...wei.com>
Cc:     chao@...nel.org, yuchao0@...wei.com, yunlong.song@...oud.com,
        miaoxie@...wei.com, bintian.wang@...wei.com,
        linux-fsdevel@...r.kernel.org,
        linux-f2fs-devel@...ts.sourceforge.net,
        linux-kernel@...r.kernel.org
Subject: Re: [PATCH v2] f2fs: fix out-of-free problem caused by atomic write

On 10/30, Yunlong Song wrote:
> f2fs_balance_fs only actives once in the commit_inmem_pages, but there
> are more than one page to commit, so all the other pages will miss the
> check. This will lead to out-of-free problem when commit a very large
> file. However, we cannot do f2fs_balance_fs for each inmem page, since
> this will break atomicity. As a result, we should collect prefree
> segments if needed and stop atomic commit when there are not enough
> available blocks to write atomic pages.
> 
> Signed-off-by: Yunlong Song <yunlong.song@...wei.com>
> ---
>  fs/f2fs/f2fs.h    |  1 +
>  fs/f2fs/segment.c | 29 ++++++++++++++++++++++++++++-
>  2 files changed, 29 insertions(+), 1 deletion(-)
> 
> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
> index 13a96b8..04ce48f 100644
> --- a/fs/f2fs/f2fs.h
> +++ b/fs/f2fs/f2fs.h
> @@ -610,6 +610,7 @@ struct f2fs_inode_info {
>  	struct list_head inmem_pages;	/* inmemory pages managed by f2fs */
>  	struct task_struct *inmem_task;	/* store inmemory task */
>  	struct mutex inmem_lock;	/* lock for inmemory pages */
> +	unsigned long inmem_blocks;	/* inmemory blocks */
>  	struct extent_tree *extent_tree;	/* cached extent_tree entry */
>  	struct rw_semaphore dio_rwsem[2];/* avoid racing between dio and gc */
>  	struct rw_semaphore i_mmap_sem;
> diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
> index 46dfbca..813c110 100644
> --- a/fs/f2fs/segment.c
> +++ b/fs/f2fs/segment.c
> @@ -210,6 +210,7 @@ void register_inmem_page(struct inode *inode, struct page *page)
>  		list_add_tail(&fi->inmem_ilist, &sbi->inode_list[ATOMIC_FILE]);
>  	spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
>  	inc_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
> +	fi->inmem_blocks++;
>  	mutex_unlock(&fi->inmem_lock);
>  
>  	trace_f2fs_register_inmem_page(page, INMEM);
> @@ -221,6 +222,7 @@ static int __revoke_inmem_pages(struct inode *inode,
>  	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
>  	struct inmem_pages *cur, *tmp;
>  	int err = 0;
> +	struct f2fs_inode_info *fi = F2FS_I(inode);
>  
>  	list_for_each_entry_safe(cur, tmp, head, list) {
>  		struct page *page = cur->page;
> @@ -263,6 +265,7 @@ static int __revoke_inmem_pages(struct inode *inode,
>  		list_del(&cur->list);
>  		kmem_cache_free(inmem_entry_slab, cur);
>  		dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
> +		fi->inmem_blocks--;
>  	}
>  	return err;
>  }
> @@ -302,6 +305,10 @@ void drop_inmem_pages(struct inode *inode)
>  	if (!list_empty(&fi->inmem_ilist))
>  		list_del_init(&fi->inmem_ilist);
>  	spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
> +	if (fi->inmem_blocks) {
> +		f2fs_bug_on(sbi, 1);
> +		fi->inmem_blocks = 0;
> +	}
>  	mutex_unlock(&fi->inmem_lock);
>  
>  	clear_inode_flag(inode, FI_ATOMIC_FILE);
> @@ -326,6 +333,7 @@ void drop_inmem_page(struct inode *inode, struct page *page)
>  
>  	f2fs_bug_on(sbi, !cur || cur->page != page);
>  	list_del(&cur->list);
> +	fi->inmem_blocks--;
>  	mutex_unlock(&fi->inmem_lock);
>  
>  	dec_page_count(sbi, F2FS_INMEM_PAGES);
> @@ -410,11 +418,26 @@ int commit_inmem_pages(struct inode *inode)
>  
>  	INIT_LIST_HEAD(&revoke_list);
>  	f2fs_balance_fs(sbi, true);
> +	if (prefree_segments(sbi)
> +		&& has_not_enough_free_secs(sbi, 0,
> +		fi->inmem_blocks / BLKS_PER_SEC(sbi))) {
> +		struct cp_control cpc;
> +
> +		cpc.reason = __get_cp_reason(sbi);
> +		err = write_checkpoint(sbi, &cpc);
> +		if (err)
> +			goto drop;
> +	}
>  	f2fs_lock_op(sbi);
>  
>  	set_inode_flag(inode, FI_ATOMIC_COMMIT);
>  
>  	mutex_lock(&fi->inmem_lock);
> +	if ((sbi->user_block_count - valid_user_blocks(sbi)) <

What does this mean? We already allocated blocks successfully?

> +		fi->inmem_blocks) {
> +		err = -ENOSPC;
> +		goto drop;
> +	}
>  	err = __commit_inmem_pages(inode, &revoke_list);
>  	if (err) {
>  		int ret;
> @@ -429,7 +452,7 @@ int commit_inmem_pages(struct inode *inode)
>  		ret = __revoke_inmem_pages(inode, &revoke_list, false, true);
>  		if (ret)
>  			err = ret;
> -
> +drop:
>  		/* drop all uncommitted pages */
>  		__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
>  	}
> @@ -437,6 +460,10 @@ int commit_inmem_pages(struct inode *inode)
>  	if (!list_empty(&fi->inmem_ilist))
>  		list_del_init(&fi->inmem_ilist);
>  	spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
> +	if (fi->inmem_blocks) {
> +		f2fs_bug_on(sbi, 1);
> +		fi->inmem_blocks = 0;
> +	}
>  	mutex_unlock(&fi->inmem_lock);
>  
>  	clear_inode_flag(inode, FI_ATOMIC_COMMIT);
> -- 
> 1.8.5.2