Linux-BTRFS Archive on lore.kernel.org
 help / color / Atom feed
From: "Darrick J. Wong" <darrick.wong@oracle.com>
To: david@fromorbit.com, darrick.wong@oracle.com
Cc: sandeen@redhat.com, linux-nfs@vger.kernel.org,
	linux-cifs@vger.kernel.org, Amir Goldstein <amir73il@gmail.com>,
	linux-unionfs@vger.kernel.org, linux-xfs@vger.kernel.org,
	linux-mm@kvack.org, linux-btrfs@vger.kernel.org,
	linux-fsdevel@vger.kernel.org, Christoph Hellwig <hch@lst.de>,
	ocfs2-devel@oss.oracle.com
Subject: [PATCH 05/26] vfs: strengthen checking of file range inputs to generic_remap_checks
Date: Mon, 15 Oct 2018 20:10:30 -0700
Message-ID: <153965943066.1256.17049880978132186525.stgit@magnolia> (raw)
In-Reply-To: <153965939489.1256.7400115244528045860.stgit@magnolia>

From: Darrick J. Wong <darrick.wong@oracle.com>

File range remapping, if allowed to run past the destination file's EOF,
is an optimization on a regular file write.  Regular file writes that
extend the file length are subject to various constraints which are not
checked by range cloning.

This is a correctness problem because we're never allowed to touch
ranges that the page cache can't support (s_maxbytes); we're not
supposed to deal with large offsets (MAX_NON_LFS) if O_LARGEFILE isn't
set; and we must obey resource limits (RLIMIT_FSIZE).

Therefore, add these checks to the new generic_remap_checks function so
that we curtail unexpected behavior.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 mm/filemap.c |   91 ++++++++++++++++++++++++++++++++++++++--------------------
 1 file changed, 59 insertions(+), 32 deletions(-)


diff --git a/mm/filemap.c b/mm/filemap.c
index 47e6bfd45a91..08ad210fee49 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2915,6 +2915,49 @@ struct page *read_cache_page_gfp(struct address_space *mapping,
 }
 EXPORT_SYMBOL(read_cache_page_gfp);
 
+static int generic_access_check_limits(struct file *file, loff_t pos,
+				       loff_t *count)
+{
+	struct inode *inode = file->f_mapping->host;
+
+	/* Don't exceed the LFS limits. */
+	if (unlikely(pos + *count > MAX_NON_LFS &&
+				!(file->f_flags & O_LARGEFILE))) {
+		if (pos >= MAX_NON_LFS)
+			return -EFBIG;
+		*count = min(*count, (loff_t)MAX_NON_LFS - pos);
+	}
+
+	/*
+	 * Don't operate on ranges the page cache doesn't support.
+	 *
+	 * If we have written data it becomes a short write.  If we have
+	 * exceeded without writing data we send a signal and return EFBIG.
+	 * Linus frestrict idea will clean these up nicely..
+	 */
+	if (unlikely(pos >= inode->i_sb->s_maxbytes))
+		return -EFBIG;
+
+	*count = min(*count, inode->i_sb->s_maxbytes - pos);
+	return 0;
+}
+
+static int generic_write_check_limits(struct file *file, loff_t pos,
+				      loff_t *count)
+{
+	unsigned long limit = rlimit(RLIMIT_FSIZE);
+
+	if (limit != RLIM_INFINITY) {
+		if (pos >= limit) {
+			send_sig(SIGXFSZ, current, 0);
+			return -EFBIG;
+		}
+		*count = min(*count, (loff_t)limit - pos);
+	}
+
+	return generic_access_check_limits(file, pos, count);
+}
+
 /*
  * Performs necessary checks before doing a write
  *
@@ -2926,8 +2969,8 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
-	unsigned long limit = rlimit(RLIMIT_FSIZE);
-	loff_t pos;
+	loff_t count;
+	int ret;
 
 	if (!iov_iter_count(from))
 		return 0;
@@ -2936,40 +2979,15 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
 	if (iocb->ki_flags & IOCB_APPEND)
 		iocb->ki_pos = i_size_read(inode);
 
-	pos = iocb->ki_pos;
-
 	if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
 		return -EINVAL;
 
-	if (limit != RLIM_INFINITY) {
-		if (iocb->ki_pos >= limit) {
-			send_sig(SIGXFSZ, current, 0);
-			return -EFBIG;
-		}
-		iov_iter_truncate(from, limit - (unsigned long)pos);
-	}
+	count = iov_iter_count(from);
+	ret = generic_write_check_limits(file, iocb->ki_pos, &count);
+	if (ret)
+		return ret;
 
-	/*
-	 * LFS rule
-	 */
-	if (unlikely(pos + iov_iter_count(from) > MAX_NON_LFS &&
-				!(file->f_flags & O_LARGEFILE))) {
-		if (pos >= MAX_NON_LFS)
-			return -EFBIG;
-		iov_iter_truncate(from, MAX_NON_LFS - (unsigned long)pos);
-	}
-
-	/*
-	 * Are we about to exceed the fs block limit ?
-	 *
-	 * If we have written data it becomes a short write.  If we have
-	 * exceeded without writing data we send a signal and return EFBIG.
-	 * Linus frestrict idea will clean these up nicely..
-	 */
-	if (unlikely(pos >= inode->i_sb->s_maxbytes))
-		return -EFBIG;
-
-	iov_iter_truncate(from, inode->i_sb->s_maxbytes - pos);
+	iov_iter_truncate(from, count);
 	return iov_iter_count(from);
 }
 EXPORT_SYMBOL(generic_write_checks);
@@ -2991,6 +3009,7 @@ int generic_remap_checks(struct file *file_in, loff_t pos_in,
 	uint64_t bcount;
 	loff_t size_in, size_out;
 	loff_t bs = inode_out->i_sb->s_blocksize;
+	int ret;
 
 	/* The start of both ranges must be aligned to an fs block. */
 	if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs))
@@ -3014,6 +3033,14 @@ int generic_remap_checks(struct file *file_in, loff_t pos_in,
 		return -EINVAL;
 	count = min(count, size_in - (uint64_t)pos_in);
 
+	ret = generic_access_check_limits(file_in, pos_in, &count);
+	if (ret)
+		return ret;
+
+	ret = generic_write_check_limits(file_out, pos_out, &count);
+	if (ret)
+		return ret;
+
 	/*
 	 * If the user wanted us to link to the infile's EOF, round up to the
 	 * next block boundary for this check.


  parent reply index

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-10-16  3:09 [PATCH v5 00/26] fs: fixes for serious clone/dedupe problems Darrick J. Wong
2018-10-16  3:10 ` [PATCH 01/26] xfs: add a per-xfs trace_printk macro Darrick J. Wong
2018-10-16  3:10 ` [PATCH 02/26] vfs: vfs_clone_file_prep_inodes should return EINVAL for a clone from beyond EOF Darrick J. Wong
2018-10-16  3:10 ` [PATCH 03/26] vfs: check file ranges before cloning files Darrick J. Wong
2018-10-16  3:10 ` [PATCH 04/26] vfs: exit early from zero length remap operations Darrick J. Wong
2018-10-17  8:26   ` Christoph Hellwig
2018-10-16  3:10 ` Darrick J. Wong [this message]
2018-10-16  3:10 ` [PATCH 06/26] vfs: avoid problematic remapping requests into partial EOF block Darrick J. Wong
2018-10-16  3:10 ` [PATCH 07/26] vfs: skip zero-length dedupe requests Darrick J. Wong
2018-10-16  3:10 ` [PATCH 08/26] vfs: rename vfs_clone_file_prep to be more descriptive Darrick J. Wong
2018-10-16  3:10 ` [PATCH 09/26] vfs: rename clone_verify_area to remap_verify_area Darrick J. Wong
2018-10-16  3:11 ` [PATCH 10/26] vfs: combine the clone and dedupe into a single remap_file_range Darrick J. Wong
2018-10-17  8:28   ` Christoph Hellwig
2018-10-16  3:11 ` [PATCH 11/26] vfs: pass remap flags to generic_remap_file_range_prep Darrick J. Wong
2018-10-17  8:28   ` Christoph Hellwig
2018-10-16  3:11 ` [PATCH 12/26] vfs: pass remap flags to generic_remap_checks Darrick J. Wong
2018-10-17  8:29   ` Christoph Hellwig
2018-10-16  3:19 ` [PATCH 13/26] vfs: create generic_remap_file_range_touch to update inode metadata Darrick J. Wong
2018-10-17  8:33   ` Christoph Hellwig
2018-10-16  3:19 ` [PATCH 14/26] vfs: make remap_file_range functions take and return bytes completed Darrick J. Wong
2018-10-16  3:19 ` [PATCH 15/26] vfs: plumb remap flags through the vfs clone functions Darrick J. Wong
2018-10-16  3:19 ` [PATCH 16/26] vfs: plumb remap flags through the vfs dedupe functions Darrick J. Wong
2018-10-16  3:19 ` [PATCH 17/26] vfs: enable remap callers that can handle short operations Darrick J. Wong
2018-10-17  8:36   ` Christoph Hellwig
2018-10-17 16:35     ` Darrick J. Wong
2018-10-16  3:20 ` [PATCH 18/26] vfs: hide file range comparison function Darrick J. Wong
2018-10-16  3:20 ` [PATCH 19/26] vfs: clean up generic_remap_file_range_prep return value Darrick J. Wong
2018-10-17  8:37   ` Christoph Hellwig
2018-10-16  3:20 ` [PATCH 20/26] ocfs2: truncate page cache for clone destination file before remapping Darrick J. Wong
2018-10-16  3:20 ` [PATCH 21/26] ocfs2: fix pagecache truncation prior to reflink Darrick J. Wong
2018-10-16  3:20 ` [PATCH 22/26] ocfs2: support partial clone range and dedupe range Darrick J. Wong
2018-10-16  3:20 ` [PATCH 23/26] ocfs2: remove ocfs2_reflink_remap_range Darrick J. Wong
2018-10-16  3:20 ` [PATCH 24/26] xfs: fix pagecache truncation prior to reflink Darrick J. Wong
2018-10-17  8:37   ` Christoph Hellwig
2018-10-16  3:20 ` [PATCH 25/26] xfs: support returning partial reflink results Darrick J. Wong
2018-10-17  8:40   ` Christoph Hellwig
2018-10-17 16:40     ` Darrick J. Wong
2018-10-16  3:21 ` [PATCH 26/26] xfs: remove redundant remap partial EOF block checks Darrick J. Wong
2018-10-17  8:40   ` Christoph Hellwig

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=153965943066.1256.17049880978132186525.stgit@magnolia \
    --to=darrick.wong@oracle.com \
    --cc=amir73il@gmail.com \
    --cc=david@fromorbit.com \
    --cc=hch@lst.de \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=linux-cifs@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-nfs@vger.kernel.org \
    --cc=linux-unionfs@vger.kernel.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=ocfs2-devel@oss.oracle.com \
    --cc=sandeen@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-BTRFS Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-btrfs/0 linux-btrfs/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-btrfs linux-btrfs/ https://lore.kernel.org/linux-btrfs \
		linux-btrfs@vger.kernel.org
	public-inbox-index linux-btrfs

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-btrfs


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git