[PATCH] drm/amdgpu/mes: tear down the rs64mem bitmap in sw_fini

It's more reasonable to tear down the rs64mem bitmap software
context at MES sw_fini phase. This also can avoid the following
lock order issue.

[ 2529.150983] kworker/u64:1/3134 is trying to acquire lock:
[ 2529.151206] ffff8aebd9a3fa10 (reservation_ww_class_mutex){+.+.}-{4:4}, at: amdgpu_bo_free_kernel+0x4e/0x130 [amdgpu]
[ 2529.151989]
               but task is already holding lock:
[ 2529.152227] ffff8aebd2411648 (&reset_domain->sem){++++}-{4:4}, at: amdgpu_device_lock_reset_domain+0x20/0x30 [amdgpu]
[ 2529.153008]
               which lock already depends on the new lock.

[ 2529.153342]
               the existing dependency chain (in reverse order) is:
[ 2529.153645]
               -> #2 (&reset_domain->sem){++++}-{4:4}:
[ 2529.153913]        down_read+0x4a/0x240
[ 2529.154081]        amdgpu_userq_destroy+0xd8/0x3a0 [amdgpu]
[ 2529.154635]        amdgpu_userq_ioctl+0x3e2/0xe30 [amdgpu]
[ 2529.155157]        drm_ioctl_kernel+0xaf/0x110 [drm]
[ 2529.155401]        drm_ioctl+0x290/0x510 [drm]
[ 2529.155612]        amdgpu_drm_ioctl+0x52/0x90 [amdgpu]
[ 2529.156068]        __x64_sys_ioctl+0xa0/0xf0
[ 2529.156249]        x64_sys_call+0x1278/0x21c0
[ 2529.156434]        do_syscall_64+0xbe/0x5f0
[ 2529.156611]        entry_SYSCALL_64_after_hwframe+0x76/0x7e
[ 2529.156842]
               -> #1 (&userq_mgr->userq_mutex){+.+.}-{4:4}:
[ 2529.157127]        __mutex_lock+0xb2/0x11a0
[ 2529.157304]        mutex_lock_nested+0x1f/0x30
[ 2529.157492]        amdgpu_userq_vm_validate_and_restore_queue+0x710/0x9b0 [amdgpu]
[ 2529.158098]        amdgpu_userq_restore_worker+0x39/0x290 [amdgpu]
[ 2529.158646]        process_one_work+0x23e/0x6f
               -> #0 (reservation_ww_class_mutex){+.+.}-{4:4}:
[ 2529.159832]        __lock_acquire+0x14c4/0x2210
[ 2529.160021]        lock_acquire+0xc6/0x310
[ 2529.160193]        __ww_mutex_lock.constprop.0+0xd9/0x1a30
[ 2529.160419]        ww_mutex_lock+0x40/0xb0
[ 2529.160590]        amdgpu_bo_free_kernel+0x4e/0x130 [amdgpu]
[ 2529.161077]        amdgpu_mes_rs64mem_fini+0x35/0x60 [amdgpu]
[ 2529.161601]        mes_v11_0_suspend+0x2d/0x40 [amdgpu]
[ 2529.162102]        amdgpu_ip_block_suspend+0x2b/0x70 [amdgpu]
[ 2529.162609]        amdgpu_device_ip_suspend_phase2+0xa4/0x270 [amdgpu]
[ 2529.163116]        amdgpu_device_pre_asic_reset+0x130/0x1f0 [amdgpu]
[ 2529.163617]        amdgpu_device_asic_reset+0x55/0x530 [amdgpu]
[ 2529.164101]        amdgpu_device_gpu_recover+0x1e5/0x410 [amdgpu]
[ 2529.164592]        amdgpu_userq_mgr_reset_work+0x80/0xa0 [amdgpu]
[ 2529.165140]        amdgpu_userq_hang_detect_work+0xbb/0x1c0 [amdgpu]
[ 2529.165693]        process_one_work+0x23e/0x6f0
[ 2529.165884]        worker_thread+0x1c4/0x380
[ 2529.166065]        kthread+0x10c/0x150
[ 2529.166226]        ret_from_fork+0x314/0x390
[ 2529.166408]        ret_from_fork_asm+0x1a/0x30
[ 2529.166595]
               other info that might help us debug this:

[ 2529.166917] Chain exists of:
                 reservation_ww_class_mutex --> &userq_mgr->userq_mutex --> &reset_domain->sem

Signed-off-by: Prike Liang <[email protected]>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c | 4 ++++
 drivers/gpu/drm/amd/amdgpu/mes_v11_0.c  | 4 ----
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index 5998e05ecd79..b96f94e5169f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -308,8 +308,12 @@ void amdgpu_mes_fini(struct amdgpu_device *adev)
 
 	amdgpu_mes_doorbell_free(adev);
 
+	if (adev->mes.use_rs64mem)
+		amdgpu_mes_rs64mem_fini(&adev->mes);
+
 	ida_destroy(&adev->mes.doorbell_ida);
 	mutex_destroy(&adev->mes.mutex_hidden);
+
 }
 
 int amdgpu_mes_suspend(struct amdgpu_device *adev, u32 xcc_id)
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 37985c37be18..31722bb10038 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -2038,10 +2038,6 @@ static int mes_v11_0_hw_init(struct amdgpu_ip_block *ip_block)
 
 static int mes_v11_0_hw_fini(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = ip_block->adev;
-
-	if (adev->mes.use_rs64mem)
-		amdgpu_mes_rs64mem_fini(&adev->mes);
 	return 0;
 }
 
-- 
2.34.1