drm/amdkfd: Fix kernel queue 64 bit doorbell offset calculation

The bitmap index calculation should reverse the logic used on allocation
so it will clear the same bit used on allocation
Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

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

@@ -189,8 +189,8 @@ void __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd,
 
 	pr_debug("Get kernel queue doorbell\n"
 			"     doorbell offset   == 0x%08X\n"
-			 "     kernel address    == %p\n",
-		*doorbell_off, (kfd->doorbell_kernel_ptr + inx));
+			"     doorbell index    == 0x%x\n",
+		*doorbell_off, inx);
 
 	return kfd->doorbell_kernel_ptr + inx;
 }
@@ -199,7 +199,8 @@ void kfd_release_kernel_doorbell(struct kfd_dev *kfd, u32 __iomem *db_addr)
 {
 	unsigned int inx;
 
-	inx = (unsigned int)(db_addr - kfd->doorbell_kernel_ptr);
+	inx = (unsigned int)(db_addr - kfd->doorbell_kernel_ptr)
+		* sizeof(u32) / kfd->device_info->doorbell_size;
 
 	mutex_lock(&kfd->doorbell_mutex);
 	__clear_bit(inx, kfd->doorbell_available_index);