[PATCH RESEND v2 46/51] proc: sysctl: copy to and from userspace without holding the table

[Christian Brauner <brauner@kernel.org>]

proc_sys_call_handler() grabs the table, copies in what is written,
calls the handler and copies what it produced out to userspace before
it lets go of the table again. Unregistering a table waits until nobody
uses it anymore. So a reader or writer whose copy faults for as long as
it wants, with userfaultfd or a stalled FUSE mapping, keeps
unregister_sysctl_table() waiting, and its callers like to hold locks
while they do that. addrconf unregisters the ipv6 sysctls of a device
with RTNL held, so a stalled read of /proc/sys/net/ipv6/conf/<dev>/mtu
holds up every RTNL user until the reader gives up.

Copy in before grabbing the table and copy out after letting go of it,
like procfs and kernfs do for their files. The buffer is ours, nothing
needs the table for the copies.

That moves the allocation and the copy in before the permission check.
A write that can't be copied in, or a request that is too large, now
fails with -EFAULT or -ENOMEM where it used to fail with -EPERM.

Fixes: 330d57fb98a9 ("[PATCH] Fix sysctl unregistration oops (CVE-2005-2709)")
Cc: stable@vger.kernel.org
Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>
---
 fs/proc/proc_sysctl.c | 50 ++++++++++++++++++++++++++++----------------------
 1 file changed, 28 insertions(+), 22 deletions(-)

diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index ba52f13eb8f3..f5c9f04e8509 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -602,14 +602,36 @@ static ssize_t proc_sys_call_handler(struct kiocb *iocb, struct iov_iter *iter,
 		int write)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
-	struct ctl_table_header *head = grab_header(inode);
 	const struct ctl_table *table = PROC_I(inode)->sysctl_entry;
+	struct ctl_table_header *head;
 	size_t count = iov_iter_count(iter);
 	char *kbuf;
 	ssize_t error;
 
-	if (IS_ERR(head))
-		return PTR_ERR(head);
+	/* don't even try if the size is too large */
+	if (count >= KMALLOC_MAX_SIZE)
+		return -ENOMEM;
+	kbuf = kvzalloc(count + 1, GFP_KERNEL);
+	if (!kbuf)
+		return -ENOMEM;
+
+	/*
+	 * Copy in before grabbing the table and copy out after letting go of
+	 * it. Unregistering the table waits for us and a copy that faults can
+	 * take as long as userspace wants.
+	 */
+	if (write) {
+		error = -EFAULT;
+		if (!copy_from_iter_full(kbuf, count, iter))
+			goto out_free_buf;
+		kbuf[count] = '\0';
+	}
+
+	head = grab_header(inode);
+	if (IS_ERR(head)) {
+		error = PTR_ERR(head);
+		goto out_free_buf;
+	}
 
 	/*
 	 * At this point we know that the sysctl was not unregistered
@@ -624,28 +646,15 @@ static ssize_t proc_sys_call_handler(struct kiocb *iocb, struct iov_iter *iter,
 	if (!table->proc_handler)
 		goto out;
 
-	/* don't even try if the size is too large */
-	error = -ENOMEM;
-	if (count >= KMALLOC_MAX_SIZE)
-		goto out;
-	kbuf = kvzalloc(count + 1, GFP_KERNEL);
-	if (!kbuf)
-		goto out;
-
-	if (write) {
-		error = -EFAULT;
-		if (!copy_from_iter_full(kbuf, count, iter))
-			goto out_free_buf;
-		kbuf[count] = '\0';
-	}
-
 	error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, &kbuf, &count,
 					   &iocb->ki_pos);
 	if (error)
-		goto out_free_buf;
+		goto out;
 
 	/* careful: calling conventions are nasty here */
 	error = table->proc_handler(table, write, kbuf, &count, &iocb->ki_pos);
+out:
+	sysctl_head_finish(head);
 	if (error)
 		goto out_free_buf;
 
@@ -658,9 +667,6 @@ static ssize_t proc_sys_call_handler(struct kiocb *iocb, struct iov_iter *iter,
 	error = count;
 out_free_buf:
 	kvfree(kbuf);
-out:
-	sysctl_head_finish(head);
-
 	return error;
 }
 

-- 
2.53.0