From:   Padmanabha Srinivasaiah <treasure4paddy@gmail.com>
To:     linux-rpi-kernel@lists.infradead.org,
        linux-arm-kernel@lists.infradead.org,
        linux-staging@lists.linux.dev, linux-kernel@vger.kernel.org,
        stefan.wahren@i2se.com
Cc:     gregkh@linuxfoundation.org, nsaenz@kernel.org,
        treasure4paddy@gmail.com, Gaston Gonzalez <gascoar@gmail.com>,
        Ojaswin Mujoo <ojaswin98@gmail.com>,
        Arnd Bergmann <arnd@arndb.de>,
        Phil Elwell <phil@raspberrypi.com>,
        bcm-kernel-feedback-list@broadcom.com
Subject: [PATCH v3] staging: vc04_services: Fix RCU dereference check
Date:   Fri, 31 Dec 2021 20:54:03 +0100
Message-Id: <20211231195406.5479-1-treasure4paddy@gmail.com>
In-Reply-To: <20211231185611.GA4463@pswork>
References: <20211231185611.GA4463@pswork>
Precedence: bulk

In service_callback path RCU dereferenced pointer struct vchiq_service
need to be accessed inside rcu read-critical section.

Also userdata/user_service part of vchiq_service is accessed around
different synchronization mechanism, getting an extra reference to a
pointer keeps sematics simpler and avoids prolonged graceperiod.

Accessing vchiq_service with rcu_read_[lock/unlock] fixes below issue.

[   32.201659] =============================
[   32.201664] WARNING: suspicious RCU usage
[   32.201670] 5.15.11-rt24-v8+ #3 Not tainted
[   32.201680] -----------------------------
[   32.201685] drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h:529 suspicious rcu_dereference_check() usage!
[   32.201695]
[   32.201695] other info that might help us debug this:
[   32.201695]
[   32.201700]
[   32.201700] rcu_scheduler_active = 2, debug_locks = 1
[   32.201708] no locks held by vchiq-slot/0/98.
[   32.201715]
[   32.201715] stack backtrace:
[   32.201723] CPU: 1 PID: 98 Comm: vchiq-slot/0 Not tainted 5.15.11-rt24-v8+ #3
[   32.201733] Hardware name: Raspberry Pi 4 Model B Rev 1.4 (DT)
[   32.201739] Call trace:
[   32.201742]  dump_backtrace+0x0/0x1b8
[   32.201772]  show_stack+0x20/0x30
[   32.201784]  dump_stack_lvl+0x8c/0xb8
[   32.201799]  dump_stack+0x18/0x34
[   32.201808]  lockdep_rcu_suspicious+0xe4/0xf8
[   32.201817]  service_callback+0x124/0x400
[   32.201830]  slot_handler_func+0xf60/0x1e20
[   32.201839]  kthread+0x19c/0x1a8
[   32.201849]  ret_from_fork+0x10/0x20

Signed-off-by: Padmanabha Srinivasaiah <treasure4paddy@gmail.com>
---
Change in v3:
	Taking an extra reference for service pointer to keep semantics
simpler to accesses in different synchronization mechanism.

Changes in v2:
        RCU dereferenced pointer need to be accessed inside rcu
read-side critical section.

 .../interface/vchiq_arm/vchiq_arm.c           | 20 +++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
index 6759a6261500..3a2e4582db8e 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
@@ -1058,15 +1058,27 @@ service_callback(enum vchiq_reason reason, struct vchiq_header *header,
 
 	DEBUG_TRACE(SERVICE_CALLBACK_LINE);
 
+	rcu_read_lock();
 	service = handle_to_service(handle);
-	if (WARN_ON(!service))
+	if (WARN_ON(!service)) {
+		rcu_read_unlock();
 		return VCHIQ_SUCCESS;
+	}
 
 	user_service = (struct user_service *)service->base.userdata;
 	instance = user_service->instance;
 
-	if (!instance || instance->closing)
+	if (!instance || instance->closing) {
+		rcu_read_unlock();
 		return VCHIQ_SUCCESS;
+	}
+
+	/*
+	 * As hopping around different synchronization mechanism,
+	 * taking an extra reference results in simpler implementation.
+	 */
+	vchiq_service_get(service);
+	rcu_read_unlock();
 
 	vchiq_log_trace(vchiq_arm_log_level,
 			"%s - service %lx(%d,%p), reason %d, header %lx, instance %lx, bulk_userdata %lx",
@@ -1097,6 +1109,7 @@ service_callback(enum vchiq_reason reason, struct vchiq_header *header,
 							bulk_userdata);
 				if (status != VCHIQ_SUCCESS) {
 					DEBUG_TRACE(SERVICE_CALLBACK_LINE);
+					vchiq_service_put(service);
 					return status;
 				}
 			}
@@ -1105,10 +1118,12 @@ service_callback(enum vchiq_reason reason, struct vchiq_header *header,
 			if (wait_for_completion_interruptible(&user_service->remove_event)) {
 				vchiq_log_info(vchiq_arm_log_level, "%s interrupted", __func__);
 				DEBUG_TRACE(SERVICE_CALLBACK_LINE);
+				vchiq_service_put(service);
 				return VCHIQ_RETRY;
 			} else if (instance->closing) {
 				vchiq_log_info(vchiq_arm_log_level, "%s closing", __func__);
 				DEBUG_TRACE(SERVICE_CALLBACK_LINE);
+				vchiq_service_put(service);
 				return VCHIQ_ERROR;
 			}
 			DEBUG_TRACE(SERVICE_CALLBACK_LINE);
@@ -1137,6 +1152,7 @@ service_callback(enum vchiq_reason reason, struct vchiq_header *header,
 		header = NULL;
 	}
 	DEBUG_TRACE(SERVICE_CALLBACK_LINE);
+	vchiq_service_put(service);
 
 	if (skip_completion)
 		return VCHIQ_SUCCESS;
-- 
2.17.1