[PATCH AUTOSEL for 4.4 10/35] drm/amdgpu: Fix SDMA load/unload sequence on HWS disabled mode

[Sasha Levin <Alexander.Levin@microsoft.com>]

From: Felix Kuehling <Felix.Kuehling@amd.com>

[ Upstream commit cf21654b40968609779751b34e7923180968fe5b ]

Fix the SDMA load and unload sequence as suggested by HW document.

Signed-off-by: shaoyun liu <shaoyun.liu@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c | 47 ++++++++++++++++-------
 1 file changed, 34 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index 0e1376317683..b233cf8436b0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -367,29 +367,50 @@ static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct cik_sdma_rlc_registers *m;
+	unsigned long end_jiffies;
 	uint32_t sdma_base_addr;
+	uint32_t data;
 
 	m = get_sdma_mqd(mqd);
 	sdma_base_addr = get_sdma_base_addr(m);
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_VIRTUAL_ADDR,
-			m->sdma_rlc_virtual_addr);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
+		m->sdma_rlc_rb_cntl & (~SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK));
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE,
-			m->sdma_rlc_rb_base);
+	end_jiffies = msecs_to_jiffies(2000) + jiffies;
+	while (true) {
+		data = RREG32(sdma_base_addr + mmSDMA0_RLC0_CONTEXT_STATUS);
+		if (data & SDMA0_RLC0_CONTEXT_STATUS__IDLE_MASK)
+			break;
+		if (time_after(jiffies, end_jiffies))
+			return -ETIME;
+		usleep_range(500, 1000);
+	}
+	if (m->sdma_engine_id) {
+		data = RREG32(mmSDMA1_GFX_CONTEXT_CNTL);
+		data = REG_SET_FIELD(data, SDMA1_GFX_CONTEXT_CNTL,
+				RESUME_CTX, 0);
+		WREG32(mmSDMA1_GFX_CONTEXT_CNTL, data);
+	} else {
+		data = RREG32(mmSDMA0_GFX_CONTEXT_CNTL);
+		data = REG_SET_FIELD(data, SDMA0_GFX_CONTEXT_CNTL,
+				RESUME_CTX, 0);
+		WREG32(mmSDMA0_GFX_CONTEXT_CNTL, data);
+	}
 
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL,
+				m->sdma_rlc_doorbell);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR, 0);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR, 0);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_VIRTUAL_ADDR,
+				m->sdma_rlc_virtual_addr);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE, m->sdma_rlc_rb_base);
 	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE_HI,
 			m->sdma_rlc_rb_base_hi);
-
 	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_ADDR_LO,
 			m->sdma_rlc_rb_rptr_addr_lo);
-
 	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_ADDR_HI,
 			m->sdma_rlc_rb_rptr_addr_hi);
-
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL,
-			m->sdma_rlc_doorbell);
-
 	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
 			m->sdma_rlc_rb_cntl);
 
@@ -492,9 +513,9 @@ static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd,
 	}
 
 	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL, 0);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR, 0);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR, 0);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE, 0);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
+		RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL) |
+		SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK);
 
 	return 0;
 }
-- 
2.11.0