All of lore.kernel.org
 help / color / mirror / 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 04/28] vfs: strengthen checking of file range inputs to generic_remap_checks
Date: Sun, 21 Oct 2018 09:15:30 -0700	[thread overview]
Message-ID: <154013853068.29026.16132846055457280127.stgit@magnolia> (raw)
In-Reply-To: <154013850285.29026.16168387526580596209.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 |   84 ++++++++++++++++++++++++++++++++++++----------------------
 1 file changed, 52 insertions(+), 32 deletions(-)


diff --git a/mm/filemap.c b/mm/filemap.c
index 47e6bfd45a91..84b7301e41a0 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2915,6 +2915,42 @@ struct page *read_cache_page_gfp(struct address_space *mapping,
 }
 EXPORT_SYMBOL(read_cache_page_gfp);
 
+/*
+ * Don't operate on ranges the page cache doesn't support, and don't exceed the
+ * LFS limits.  If pos is under the limit it becomes a short access.  If it
+ * exceeds the limit we return -EFBIG.
+ */
+static int generic_access_check_limits(struct file *file, loff_t pos,
+				       loff_t *count)
+{
+	struct inode *inode = file->f_mapping->host;
+	loff_t max_size = inode->i_sb->s_maxbytes;
+
+	if (!(file->f_flags & O_LARGEFILE))
+		max_size = MAX_NON_LFS;
+
+	if (unlikely(pos >= max_size))
+		return -EFBIG;
+	*count = min(*count, max_size - pos);
+	return 0;
+}
+
+static int generic_write_check_limits(struct file *file, loff_t pos,
+				      loff_t *count)
+{
+	loff_t limit = rlimit(RLIMIT_FSIZE);
+
+	if (limit != RLIM_INFINITY) {
+		if (pos >= limit) {
+			send_sig(SIGXFSZ, current, 0);
+			return -EFBIG;
+		}
+		*count = min(*count, limit - pos);
+	}
+
+	return generic_access_check_limits(file, pos, count);
+}
+
 /*
  * Performs necessary checks before doing a write
  *
@@ -2926,8 +2962,8 @@ 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 +2972,15 @@ 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);
-	}
-
-	/*
-	 * 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;
+	count = iov_iter_count(from);
+	ret = generic_write_check_limits(file, iocb->ki_pos, &count);
+	if (ret)
+		return ret;
 
-	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 +3002,7 @@ 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 +3026,14 @@ 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.

WARNING: multiple messages have this Message-ID
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: [Ocfs2-devel] [PATCH 04/28] vfs: strengthen checking of file range inputs to generic_remap_checks
Date: Sun, 21 Oct 2018 09:15:30 -0700	[thread overview]
Message-ID: <154013853068.29026.16132846055457280127.stgit@magnolia> (raw)
In-Reply-To: <154013850285.29026.16168387526580596209.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 |   84 ++++++++++++++++++++++++++++++++++++----------------------
 1 file changed, 52 insertions(+), 32 deletions(-)


diff --git a/mm/filemap.c b/mm/filemap.c
index 47e6bfd45a91..84b7301e41a0 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2915,6 +2915,42 @@ struct page *read_cache_page_gfp(struct address_space *mapping,
 }
 EXPORT_SYMBOL(read_cache_page_gfp);
 
+/*
+ * Don't operate on ranges the page cache doesn't support, and don't exceed the
+ * LFS limits.  If pos is under the limit it becomes a short access.  If it
+ * exceeds the limit we return -EFBIG.
+ */
+static int generic_access_check_limits(struct file *file, loff_t pos,
+				       loff_t *count)
+{
+	struct inode *inode = file->f_mapping->host;
+	loff_t max_size = inode->i_sb->s_maxbytes;
+
+	if (!(file->f_flags & O_LARGEFILE))
+		max_size = MAX_NON_LFS;
+
+	if (unlikely(pos >= max_size))
+		return -EFBIG;
+	*count = min(*count, max_size - pos);
+	return 0;
+}
+
+static int generic_write_check_limits(struct file *file, loff_t pos,
+				      loff_t *count)
+{
+	loff_t limit = rlimit(RLIMIT_FSIZE);
+
+	if (limit != RLIM_INFINITY) {
+		if (pos >= limit) {
+			send_sig(SIGXFSZ, current, 0);
+			return -EFBIG;
+		}
+		*count = min(*count, limit - pos);
+	}
+
+	return generic_access_check_limits(file, pos, count);
+}
+
 /*
  * Performs necessary checks before doing a write
  *
@@ -2926,8 +2962,8 @@ 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 +2972,15 @@ 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);
-	}
-
-	/*
-	 * 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;
+	count = iov_iter_count(from);
+	ret = generic_write_check_limits(file, iocb->ki_pos, &count);
+	if (ret)
+		return ret;
 
-	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 +3002,7 @@ 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 +3026,14 @@ 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	other threads:[~2018-10-21 16:15 UTC|newest]

Thread overview: 83+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-10-21 16:15 [Ocfs2-devel] [PATCH v6 00/28] fs: fixes for serious clone/dedupe problems Darrick J. Wong
2018-10-21 16:15 ` [Ocfs2-devel] [PATCH 01/28] vfs: vfs_clone_file_prep_inodes should return EINVAL for a clone from beyond EOF Darrick J. Wong
2018-10-21 16:15 ` [Ocfs2-devel] [PATCH 02/28] vfs: check file ranges before cloning files Darrick J. Wong
2018-10-21 16:15 ` [Ocfs2-devel] [PATCH 03/28] vfs: exit early from zero length remap operations Darrick J. Wong
2018-10-21 16:15 ` Darrick J. Wong [this message]
2018-10-21 16:15 ` [Ocfs2-devel] [PATCH 05/28] vfs: avoid problematic remapping requests into partial EOF block Darrick J. Wong
2018-10-21 16:15 ` [Ocfs2-devel] [PATCH 06/28] vfs: skip zero-length dedupe requests Darrick J. Wong
2018-10-21 16:15 ` [Ocfs2-devel] [PATCH 07/28] vfs: rename vfs_clone_file_prep to be more descriptive Darrick J. Wong
2018-10-21 16:15 ` [Ocfs2-devel] [PATCH 08/28] vfs: rename clone_verify_area to remap_verify_area Darrick J. Wong
2018-10-21 16:16 ` [Ocfs2-devel] [PATCH 09/28] vfs: combine the clone and dedupe into a single remap_file_range Darrick J. Wong
2018-10-21 16:16 ` [Ocfs2-devel] [PATCH 10/28] vfs: pass remap flags to generic_remap_file_range_prep Darrick J. Wong
2018-10-21 16:16 ` [Ocfs2-devel] [PATCH 11/28] vfs: pass remap flags to generic_remap_checks Darrick J. Wong
2018-10-21 16:16 ` [Ocfs2-devel] [PATCH 12/28] vfs: remap helper should update destination inode metadata Darrick J. Wong
2018-10-21 16:16 ` [Ocfs2-devel] [PATCH 13/28] vfs: make remap_file_range functions take and return bytes completed Darrick J. Wong
2018-10-21 16:16 ` [Ocfs2-devel] [PATCH 14/28] vfs: plumb remap flags through the vfs clone functions Darrick J. Wong
2018-10-21 16:16 ` [Ocfs2-devel] [PATCH 15/28] vfs: plumb remap flags through the vfs dedupe functions Darrick J. Wong
2018-10-21 16:16 ` [Ocfs2-devel] [PATCH 16/28] vfs: enable remap callers that can handle short operations Darrick J. Wong
2018-10-21 16:17 ` [Ocfs2-devel] [PATCH 17/28] vfs: hide file range comparison function Darrick J. Wong
2018-10-21 16:17 ` [Ocfs2-devel] [PATCH 18/28] vfs: clean up generic_remap_file_range_prep return value Darrick J. Wong
2018-10-21 16:17 ` [Ocfs2-devel] [PATCH 19/28] ocfs2: truncate page cache for clone destination file before remapping Darrick J. Wong
2018-10-21 16:17 ` [Ocfs2-devel] [PATCH 20/28] ocfs2: fix pagecache truncation prior to reflink Darrick J. Wong
2018-10-21 16:17 ` [Ocfs2-devel] [PATCH 21/28] ocfs2: support partial clone range and dedupe range Darrick J. Wong
2018-10-21 16:17 ` [Ocfs2-devel] [PATCH 22/28] ocfs2: remove ocfs2_reflink_remap_range Darrick J. Wong
2018-10-21 16:17 ` [Ocfs2-devel] [PATCH 23/28] xfs: fix pagecache truncation prior to reflink Darrick J. Wong
2018-10-21 16:17 ` [Ocfs2-devel] [PATCH 24/28] xfs: clean up xfs_reflink_remap_blocks call site Darrick J. Wong
2018-10-22  2:11   ` Dave Chinner
2018-10-21 16:17 ` [Ocfs2-devel] [PATCH 25/28] xfs: support returning partial reflink results Darrick J. Wong
2018-10-22  2:14   ` Dave Chinner
2018-10-21 16:18 ` [Ocfs2-devel] [PATCH 26/28] xfs: remove redundant remap partial EOF block checks Darrick J. Wong
2018-10-21 16:18 ` [Ocfs2-devel] [PATCH 27/28] xfs: remove xfs_reflink_remap_range Darrick J. Wong
2018-10-22  2:17   ` Dave Chinner
2018-10-21 16:18 ` [Ocfs2-devel] [PATCH 28/28] xfs: remove [cm]time update from reflink calls Darrick J. Wong
2018-10-22  2:18   ` Dave Chinner
2018-10-22  2:21 ` [Ocfs2-devel] [PATCH v6 00/28] fs: fixes for serious clone/dedupe problems Dave Chinner
2018-10-22  4:37   ` Dave Chinner
2018-10-22  4:52     ` Al Viro
2018-10-22  5:08       ` Dave Chinner
2018-10-22  5:42         ` Amir Goldstein
2018-10-22  6:55           ` [Ocfs2-devel] " Dave Chinner

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=154013853068.29026.16132846055457280127.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 \
    --subject='Re: [PATCH 04/28] vfs: strengthen checking of file range inputs to generic_remap_checks' \
    /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

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.