Linux-Fsdevel Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: Al Viro <viro@zeniv.linux.org.uk>,
	Michael Ellerman <mpe@ellerman.id.au>,
	x86@kernel.org
Cc: Kees Cook <keescook@chromium.org>,
	linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-arch@vger.kernel.org, linuxppc-dev@lists.ozlabs.org
Subject: [PATCH 02/11] fs: don't allow kernel reads and writes without iter ops
Date: Mon, 17 Aug 2020 09:32:03 +0200	[thread overview]
Message-ID: <20200817073212.830069-3-hch@lst.de> (raw)
In-Reply-To: <20200817073212.830069-1-hch@lst.de>

Don't allow calling ->read or ->write with set_fs as a preparation for
killing off set_fs.  All the instances that we use kernel_read/write on
are using the iter ops already.

If a file has both the regular ->read/->write methods and the iter
variants those could have different semantics for messed up enough
drivers.  Also fails the kernel access to them in that case.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/read_write.c | 67 +++++++++++++++++++++++++++++++------------------
 1 file changed, 42 insertions(+), 25 deletions(-)

diff --git a/fs/read_write.c b/fs/read_write.c
index 5db58b8c78d0dd..702c4301d9eb6b 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -419,27 +419,41 @@ static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, lo
 	return ret;
 }
 
+static int warn_unsupported(struct file *file, const char *op)
+{
+	pr_warn_ratelimited(
+		"kernel %s not supported for file %pD4 (pid: %d comm: %.20s)\n",
+		op, file, current->pid, current->comm);
+	return -EINVAL;
+}
+
 ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos)
 {
-	mm_segment_t old_fs = get_fs();
+	struct kvec iov = {
+		.iov_base	= buf,
+		.iov_len	= min_t(size_t, count, MAX_RW_COUNT),
+	};
+	struct kiocb kiocb;
+	struct iov_iter iter;
 	ssize_t ret;
 
 	if (WARN_ON_ONCE(!(file->f_mode & FMODE_READ)))
 		return -EINVAL;
 	if (!(file->f_mode & FMODE_CAN_READ))
 		return -EINVAL;
+	/*
+	 * Also fail if ->read_iter and ->read are both wired up as that
+	 * implies very convoluted semantics.
+	 */
+	if (unlikely(!file->f_op->read_iter || file->f_op->read))
+		return warn_unsupported(file, "read");
 
-	if (count > MAX_RW_COUNT)
-		count =  MAX_RW_COUNT;
-	set_fs(KERNEL_DS);
-	if (file->f_op->read)
-		ret = file->f_op->read(file, (void __user *)buf, count, pos);
-	else if (file->f_op->read_iter)
-		ret = new_sync_read(file, (void __user *)buf, count, pos);
-	else
-		ret = -EINVAL;
-	set_fs(old_fs);
+	init_sync_kiocb(&kiocb, file);
+	kiocb.ki_pos = *pos;
+	iov_iter_kvec(&iter, READ, &iov, 1, iov.iov_len);
+	ret = file->f_op->read_iter(&kiocb, &iter);
 	if (ret > 0) {
+		*pos = kiocb.ki_pos;
 		fsnotify_access(file);
 		add_rchar(current, ret);
 	}
@@ -510,28 +524,31 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t
 /* caller is responsible for file_start_write/file_end_write */
 ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos)
 {
-	mm_segment_t old_fs;
-	const char __user *p;
+	struct kvec iov = {
+		.iov_base	= (void *)buf,
+		.iov_len	= min_t(size_t, count, MAX_RW_COUNT),
+	};
+	struct kiocb kiocb;
+	struct iov_iter iter;
 	ssize_t ret;
 
 	if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE)))
 		return -EBADF;
 	if (!(file->f_mode & FMODE_CAN_WRITE))
 		return -EINVAL;
+	/*
+	 * Also fail if ->write_iter and ->write are both wired up as that
+	 * implies very convoluted semantics.
+	 */
+	if (unlikely(!file->f_op->write_iter || file->f_op->write))
+		return warn_unsupported(file, "write");
 
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	p = (__force const char __user *)buf;
-	if (count > MAX_RW_COUNT)
-		count =  MAX_RW_COUNT;
-	if (file->f_op->write)
-		ret = file->f_op->write(file, p, count, pos);
-	else if (file->f_op->write_iter)
-		ret = new_sync_write(file, p, count, pos);
-	else
-		ret = -EINVAL;
-	set_fs(old_fs);
+	init_sync_kiocb(&kiocb, file);
+	kiocb.ki_pos = *pos;
+	iov_iter_kvec(&iter, WRITE, &iov, 1, iov.iov_len);
+	ret = file->f_op->write_iter(&kiocb, &iter);
 	if (ret > 0) {
+		*pos = kiocb.ki_pos;
 		fsnotify_modify(file);
 		add_wchar(current, ret);
 	}
-- 
2.28.0


  parent reply	other threads:[~2020-08-17  7:33 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-08-17  7:32 remove the last set_fs() in common code, and remove it for x86 and powerpc Christoph Hellwig
2020-08-17  7:32 ` [PATCH 01/11] mem: remove duplicate ops for /dev/zero and /dev/null Christoph Hellwig
2020-08-18 19:33   ` Kees Cook
2020-08-17  7:32 ` Christoph Hellwig [this message]
2020-08-18 19:34   ` [PATCH 02/11] fs: don't allow kernel reads and writes without iter ops Kees Cook
2020-08-17  7:32 ` [PATCH 03/11] fs: don't allow splice read/write without explicit ops Christoph Hellwig
2020-08-18 19:39   ` Kees Cook
2020-08-18 19:54     ` Christoph Hellwig
2020-08-18 19:58       ` Kees Cook
2020-08-18 20:07         ` Christoph Hellwig
2020-08-17  7:32 ` [PATCH 04/11] uaccess: add infrastructure for kernel builds with set_fs() Christoph Hellwig
2020-08-18 19:40   ` Kees Cook
2020-08-17  7:32 ` [PATCH 05/11] test_bitmap: skip user bitmap tests for !CONFIG_SET_FS Christoph Hellwig
2020-08-17  7:50   ` Christophe Leroy
2020-08-17  7:52     ` Christoph Hellwig
2020-08-18 19:43   ` Kees Cook
2020-08-17  7:32 ` [PATCH 06/11] lkdtm: disable set_fs-based " Christoph Hellwig
2020-08-18 19:32   ` Kees Cook
2020-08-17  7:32 ` [PATCH 07/11] x86: move PAGE_OFFSET, TASK_SIZE & friends to page_{32,64}_types.h Christoph Hellwig
2020-08-18 19:27   ` Kees Cook
2020-08-17  7:32 ` [PATCH 08/11] x86: make TASK_SIZE_MAX usable from assembly code Christoph Hellwig
2020-08-18 19:44   ` Kees Cook
2020-08-18 19:55     ` Christoph Hellwig
2020-08-18 19:59       ` Kees Cook
2020-08-18 20:00         ` Christoph Hellwig
2020-08-18 20:08           ` Kees Cook
2020-08-17  7:32 ` [PATCH 09/11] x86: remove address space overrides using set_fs() Christoph Hellwig
2020-08-17  8:23   ` David Laight
2020-08-27  9:37     ` 'Christoph Hellwig'
2020-08-18 19:46   ` Kees Cook
2020-08-17  7:32 ` [PATCH 10/11] powerpc: use non-set_fs based maccess routines Christoph Hellwig
2020-08-17 15:47   ` Christophe Leroy
2020-08-17  7:32 ` [PATCH 11/11] powerpc: remove address space overrides using set_fs() Christoph Hellwig
2020-08-17  7:39 ` remove the last set_fs() in common code, and remove it for x86 and powerpc Christoph Hellwig
2020-08-18 17:46 ` Christophe Leroy
2020-08-18 18:05   ` Christoph Hellwig
2020-08-18 18:23     ` Christophe Leroy
2020-08-19  7:16       ` Christophe Leroy
2020-08-19  7:22         ` iter and normal ops on /dev/zero & co, was " 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=20200817073212.830069-3-hch@lst.de \
    --to=hch@lst.de \
    --cc=keescook@chromium.org \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=mpe@ellerman.id.au \
    --cc=viro@zeniv.linux.org.uk \
    --cc=x86@kernel.org \
    --subject='Re: [PATCH 02/11] fs: don'\''t allow kernel reads and writes without iter ops' \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).