Received-SPF: pass (google.com: domain of linux-kernel+bounces-179676-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
From: libaokun@huaweicloud.com
To: netfs@lists.linux.dev,
	dhowells@redhat.com,
	jlayton@kernel.org
Cc: hsiangkao@linux.alibaba.com,
	jefflexu@linux.alibaba.com,
	zhujia.zj@bytedance.com,
	linux-erofs@lists.ozlabs.org,
	linux-fsdevel@vger.kernel.org,
	linux-kernel@vger.kernel.org,
	libaokun@huaweicloud.com,
	yangerkun@huawei.com,
	houtao1@huawei.com,
	yukuai3@huawei.com,
	wozizhi@huawei.com,
	Baokun Li <libaokun1@huawei.com>
Subject: [PATCH v2 04/12] cachefiles: fix slab-use-after-free in cachefiles_ondemand_daemon_read()
Date: Wed, 15 May 2024 16:45:53 +0800
Message-Id: <20240515084601.3240503-5-libaokun@huaweicloud.com>
In-Reply-To: <20240515084601.3240503-1-libaokun@huaweicloud.com>
References: <20240515084601.3240503-1-libaokun@huaweicloud.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

From: Baokun Li <libaokun1@huawei.com>

We got the following issue in a fuzz test of randomly issuing the restore
command:

==================================================================
BUG: KASAN: slab-use-after-free in cachefiles_ondemand_daemon_read+0xb41/0xb60
Read of size 8 at addr ffff888122e84088 by task ondemand-04-dae/963

CPU: 13 PID: 963 Comm: ondemand-04-dae Not tainted 6.8.0-dirty #564
Call Trace:
 kasan_report+0x93/0xc0
 cachefiles_ondemand_daemon_read+0xb41/0xb60
 vfs_read+0x169/0xb50
 ksys_read+0xf5/0x1e0

Allocated by task 116:
 kmem_cache_alloc+0x140/0x3a0
 cachefiles_lookup_cookie+0x140/0xcd0
 fscache_cookie_state_machine+0x43c/0x1230
 [...]

Freed by task 792:
 kmem_cache_free+0xfe/0x390
 cachefiles_put_object+0x241/0x480
 fscache_cookie_state_machine+0x5c8/0x1230
 [...]
==================================================================

Following is the process that triggers the issue:

     mount  |   daemon_thread1    |    daemon_thread2
------------------------------------------------------------
cachefiles_withdraw_cookie
 cachefiles_ondemand_clean_object(object)
  cachefiles_ondemand_send_req
   REQ_A = kzalloc(sizeof(*req) + data_len)
   wait_for_completion(&REQ_A->done)

            cachefiles_daemon_read
             cachefiles_ondemand_daemon_read
              REQ_A = cachefiles_ondemand_select_req
              msg->object_id = req->object->ondemand->ondemand_id
                                  ------ restore ------
                                  cachefiles_ondemand_restore
                                  xas_for_each(&xas, req, ULONG_MAX)
                                   xas_set_mark(&xas, CACHEFILES_REQ_NEW)

                                  cachefiles_daemon_read
                                   cachefiles_ondemand_daemon_read
                                    REQ_A = cachefiles_ondemand_select_req
              copy_to_user(_buffer, msg, n)
               xa_erase(&cache->reqs, id)
               complete(&REQ_A->done)
              ------ close(fd) ------
              cachefiles_ondemand_fd_release
               cachefiles_put_object
 cachefiles_put_object
  kmem_cache_free(cachefiles_object_jar, object)
                                    REQ_A->object->ondemand->ondemand_id
                                     // object UAF !!!

When we see the request within xa_lock, req->object must not have been
freed yet, so grab the reference count of object before xa_unlock to
avoid the above issue.

Fixes: 0a7e54c1959c ("cachefiles: resend an open request if the read request's object is closed")
Signed-off-by: Baokun Li <libaokun1@huawei.com>
Reviewed-by: Jia Zhu <zhujia.zj@bytedance.com>
---
 fs/cachefiles/ondemand.c          | 2 ++
 include/trace/events/cachefiles.h | 6 +++++-
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c
index 56d12fe4bf73..bb94ef6a6f61 100644
--- a/fs/cachefiles/ondemand.c
+++ b/fs/cachefiles/ondemand.c
@@ -336,6 +336,7 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
 	xas_clear_mark(&xas, CACHEFILES_REQ_NEW);
 	cache->req_id_next = xas.xa_index + 1;
 	refcount_inc(&req->ref);
+	cachefiles_grab_object(req->object, cachefiles_obj_get_read_req);
 	xa_unlock(&cache->reqs);
 
 	if (msg->opcode == CACHEFILES_OP_OPEN) {
@@ -355,6 +356,7 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
 			close_fd(((struct cachefiles_open *)msg->data)->fd);
 	}
 out:
+	cachefiles_put_object(req->object, cachefiles_obj_put_read_req);
 	/* Remove error request and CLOSE request has no reply */
 	if (ret || msg->opcode == CACHEFILES_OP_CLOSE) {
 		xas_reset(&xas);
diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h
index cf4b98b9a9ed..119a823fb5a0 100644
--- a/include/trace/events/cachefiles.h
+++ b/include/trace/events/cachefiles.h
@@ -33,6 +33,8 @@ enum cachefiles_obj_ref_trace {
 	cachefiles_obj_see_withdrawal,
 	cachefiles_obj_get_ondemand_fd,
 	cachefiles_obj_put_ondemand_fd,
+	cachefiles_obj_get_read_req,
+	cachefiles_obj_put_read_req,
 };
 
 enum fscache_why_object_killed {
@@ -127,7 +129,9 @@ enum cachefiles_error_trace {
 	EM(cachefiles_obj_see_lookup_cookie,	"SEE lookup_cookie")	\
 	EM(cachefiles_obj_see_lookup_failed,	"SEE lookup_failed")	\
 	EM(cachefiles_obj_see_withdraw_cookie,	"SEE withdraw_cookie")	\
-	E_(cachefiles_obj_see_withdrawal,	"SEE withdrawal")
+	EM(cachefiles_obj_see_withdrawal,	"SEE withdrawal")	\
+	EM(cachefiles_obj_get_read_req,		"GET read_req")		\
+	E_(cachefiles_obj_put_read_req,		"PUT read_req")
 
 #define cachefiles_coherency_traces					\
 	EM(cachefiles_coherency_check_aux,	"BAD aux ")		\
-- 
2.39.2