Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Sasha Levin <sashal@kernel.org>
To:     linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc:     YuBiao Wang <YuBiao.Wang@amd.com>, Jack Xiao <Jack.Xiao@amd.com>,
        Alex Deucher <alexander.deucher@amd.com>,
        Sasha Levin <sashal@kernel.org>, christian.koenig@amd.com,
        Xinhui.Pan@amd.com, airlied@gmail.com, daniel@ffwll.ch,
        Hawking.Zhang@amd.com, Felix.Kuehling@amd.com,
        Graham.Sider@amd.com, yifan1.zhang@amd.com,
        amd-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org
Subject: [PATCH AUTOSEL 6.0 30/34] drm/amdgpu: dequeue mes scheduler during fini
Date:   Tue,  1 Nov 2022 07:27:22 -0400
Message-Id: <20221101112726.799368-30-sashal@kernel.org>
In-Reply-To: <20221101112726.799368-1-sashal@kernel.org>
References: <20221101112726.799368-1-sashal@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: YuBiao Wang <YuBiao.Wang@amd.com>

[ Upstream commit 2abe92c7adc9c0397ba51bf74909b85bc0fff84b ]

[Why]
If mes is not dequeued during fini, mes will be in an uncleaned state
during reload, then mes couldn't receive some commands which leads to
reload failure.

[How]
Perform MES dequeue via MMIO after all the unmap jobs are done by mes
and before kiq fini.

v2: Move the dequeue operation inside kiq_hw_fini.

Signed-off-by: YuBiao Wang <YuBiao.Wang@amd.com>
Reviewed-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/amdgpu/mes_v11_0.c | 42 ++++++++++++++++++++++++--
 1 file changed, 39 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index f92744b8d79d..2dd827472d6e 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -1145,6 +1145,42 @@ static int mes_v11_0_sw_fini(void *handle)
 	return 0;
 }
 
+static void mes_v11_0_kiq_dequeue_sched(struct amdgpu_device *adev)
+{
+	uint32_t data;
+	int i;
+
+	mutex_lock(&adev->srbm_mutex);
+	soc21_grbm_select(adev, 3, AMDGPU_MES_SCHED_PIPE, 0, 0);
+
+	/* disable the queue if it's active */
+	if (RREG32_SOC15(GC, 0, regCP_HQD_ACTIVE) & 1) {
+		WREG32_SOC15(GC, 0, regCP_HQD_DEQUEUE_REQUEST, 1);
+		for (i = 0; i < adev->usec_timeout; i++) {
+			if (!(RREG32_SOC15(GC, 0, regCP_HQD_ACTIVE) & 1))
+				break;
+			udelay(1);
+		}
+	}
+	data = RREG32_SOC15(GC, 0, regCP_HQD_PQ_DOORBELL_CONTROL);
+	data = REG_SET_FIELD(data, CP_HQD_PQ_DOORBELL_CONTROL,
+				DOORBELL_EN, 0);
+	data = REG_SET_FIELD(data, CP_HQD_PQ_DOORBELL_CONTROL,
+				DOORBELL_HIT, 1);
+	WREG32_SOC15(GC, 0, regCP_HQD_PQ_DOORBELL_CONTROL, data);
+
+	WREG32_SOC15(GC, 0, regCP_HQD_PQ_DOORBELL_CONTROL, 0);
+
+	WREG32_SOC15(GC, 0, regCP_HQD_PQ_WPTR_LO, 0);
+	WREG32_SOC15(GC, 0, regCP_HQD_PQ_WPTR_HI, 0);
+	WREG32_SOC15(GC, 0, regCP_HQD_PQ_RPTR, 0);
+
+	soc21_grbm_select(adev, 0, 0, 0, 0);
+	mutex_unlock(&adev->srbm_mutex);
+
+	adev->mes.ring.sched.ready = false;
+}
+
 static void mes_v11_0_kiq_setting(struct amdgpu_ring *ring)
 {
 	uint32_t tmp;
@@ -1196,6 +1232,9 @@ static int mes_v11_0_kiq_hw_init(struct amdgpu_device *adev)
 
 static int mes_v11_0_kiq_hw_fini(struct amdgpu_device *adev)
 {
+	if (adev->mes.ring.sched.ready)
+		mes_v11_0_kiq_dequeue_sched(adev);
+
 	mes_v11_0_enable(adev, false);
 	return 0;
 }
@@ -1251,9 +1290,6 @@ static int mes_v11_0_hw_init(void *handle)
 
 static int mes_v11_0_hw_fini(void *handle)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
-	adev->mes.ring.sched.ready = false;
 	return 0;
 }
 
-- 
2.35.1