drm/amdkfd: dqm fence memory corruption

Amdgpu driver uses 4-byte data type as DQM fence memory,
and transmits GPU address of fence memory to microcode
through query status PM4 message. However, query status
PM4 message definition and microcode processing are all
processed according to 8 bytes. Fence memory only allocates
4 bytes of memory, but microcode does write 8 bytes of memory,
so there is a memory corruption.

Changes since v1:
  * Change dqm->fence_addr as a u64 pointer to fix this issue,
also fix up query_status and amdkfd_fence_wait_timeout function
uses 64 bit fence value to make them consistent.
Signed-off-by: Qu Huang <jinsdb@126.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c

@@ -155,7 +155,7 @@ static int dbgdev_diq_submit_ib(struct kfd_dbgdev *dbgdev,
 
 	/* Wait till CP writes sync code: */
 	status = amdkfd_fence_wait_timeout(
-			(unsigned int *) rm_state,
+			rm_state,
 			QUEUESTATE__ACTIVE, 1500);
 
 	kfd_gtt_sa_free(dbgdev->dev, mem_obj);

drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c

@@ -1180,7 +1180,7 @@ static int start_cpsch(struct device_queue_manager *dqm)
 	if (retval)
 		goto fail_allocate_vidmem;
 
-	dqm->fence_addr = dqm->fence_mem->cpu_ptr;
+	dqm->fence_addr = (uint64_t *)dqm->fence_mem->cpu_ptr;
 	dqm->fence_gpu_addr = dqm->fence_mem->gpu_addr;
 
 	init_interrupts(dqm);
@@ -1353,8 +1353,8 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 	return retval;
 }
 
-int amdkfd_fence_wait_timeout(unsigned int *fence_addr,
-				unsigned int fence_value,
+int amdkfd_fence_wait_timeout(uint64_t *fence_addr,
+				uint64_t fence_value,
 				unsigned int timeout_ms)
 {
 	unsigned long end_jiffies = msecs_to_jiffies(timeout_ms) + jiffies;

drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h

@@ -187,7 +187,7 @@ struct device_queue_manager {
 	uint16_t		vmid_pasid[VMID_NUM];
 	uint64_t		pipelines_addr;
 	uint64_t		fence_gpu_addr;
-	unsigned int		*fence_addr;
+	uint64_t		*fence_addr;
 	struct kfd_mem_obj	*fence_mem;
 	bool			active_runlist;
 	int			sched_policy;

drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c

@@ -348,7 +348,7 @@ int pm_send_runlist(struct packet_manager *pm, struct list_head *dqm_queues)
 }
 
 int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address,
-			uint32_t fence_value)
+			uint64_t fence_value)
 {
 	uint32_t *buffer, size;
 	int retval = 0;

drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c

@@ -283,7 +283,7 @@ static int pm_unmap_queues_v9(struct packet_manager *pm, uint32_t *buffer,
 }
 
 static int pm_query_status_v9(struct packet_manager *pm, uint32_t *buffer,
-			uint64_t fence_address,	uint32_t fence_value)
+			uint64_t fence_address,	uint64_t fence_value)
 {
 	struct pm4_mes_query_status *packet;
 

drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c

@@ -263,7 +263,7 @@ static int pm_unmap_queues_vi(struct packet_manager *pm, uint32_t *buffer,
 }
 
 static int pm_query_status_vi(struct packet_manager *pm, uint32_t *buffer,
-			uint64_t fence_address,	uint32_t fence_value)
+			uint64_t fence_address,	uint64_t fence_value)
 {
 	struct pm4_mes_query_status *packet;
 

drivers/gpu/drm/amd/amdkfd/kfd_priv.h

@@ -1000,8 +1000,8 @@ int pqm_get_wave_state(struct process_queue_manager *pqm,
 		       u32 *ctl_stack_used_size,
 		       u32 *save_area_used_size);
 
-int amdkfd_fence_wait_timeout(unsigned int *fence_addr,
-			      unsigned int fence_value,
+int amdkfd_fence_wait_timeout(uint64_t *fence_addr,
+			      uint64_t fence_value,
 			      unsigned int timeout_ms);
 
 /* Packet Manager */
@@ -1037,7 +1037,7 @@ struct packet_manager_funcs {
 			uint32_t filter_param, bool reset,
 			unsigned int sdma_engine);
 	int (*query_status)(struct packet_manager *pm, uint32_t *buffer,
-			uint64_t fence_address,	uint32_t fence_value);
+			uint64_t fence_address,	uint64_t fence_value);
 	int (*release_mem)(uint64_t gpu_addr, uint32_t *buffer);
 
 	/* Packet sizes */
@@ -1059,7 +1059,7 @@ int pm_send_set_resources(struct packet_manager *pm,
 				struct scheduling_resources *res);
 int pm_send_runlist(struct packet_manager *pm, struct list_head *dqm_queues);
 int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address,
-				uint32_t fence_value);
+				uint64_t fence_value);
 
 int pm_send_unmap_queue(struct packet_manager *pm, enum kfd_queue_type type,
 			enum kfd_unmap_queues_filter mode,