drm/msm/a6xx: Add support for Adreno 612

Add support for Adreno 612 GPU found in SM6150/QCS615 chipsets.
A612 falls under ADRENO_6XX_GEN1 family and is a cut down version
of A615 GPU.

A612 has a new IP called Reduced Graphics Management Unit or RGMU
which is a small state machine which helps to toggle GX GDSC
(connected to CX rail) to implement IFPC feature. It doesn't support
any other features of a full fledged GMU like clock control, resource
voting to rpmh etc. So we need linux clock driver support like other
gmu-wrapper implementations to control gpu core clock and gpu GX gdsc.
This patch skips RGMU core initialization and act more like a
gmu-wrapper case.

Signed-off-by: Jie Zhang <quic_jiezh@quicinc.com>
Signed-off-by: Akhil P Oommen <akhilpo@oss.qualcomm.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/686212/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>

drivers/gpu/drm/msm/adreno/a6xx_catalog.c

@@ -705,6 +705,22 @@ static const struct adreno_info a6xx_gpus[] = {
 			{ 157, 3 },
 			{ 127, 4 },
 		),
+	}, {
+		.chip_ids = ADRENO_CHIP_IDS(0x06010200),
+		.family = ADRENO_6XX_GEN1,
+		.fw = {
+			[ADRENO_FW_SQE] = "a630_sqe.fw",
+			[ADRENO_FW_GMU] = "a612_rgmu.bin",
+		},
+		.gmem = (SZ_128K + SZ_4K),
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
+		.init = a6xx_gpu_init,
+		.a6xx = &(const struct a6xx_info) {
+			.hwcg = a612_hwcg,
+			.protect = &a630_protect,
+			.gmu_cgc_mode = 0x00000022,
+			.prim_fifo_threshold = 0x00080000,
+		},
 	}, {
 		.chip_ids = ADRENO_CHIP_IDS(0x06010500),
 		.family = ADRENO_6XX_GEN1,

drivers/gpu/drm/msm/adreno/a6xx_gmu.c

@@ -350,12 +350,18 @@ static const struct a6xx_gmu_oob_bits a6xx_gmu_oob_bits[] = {
 /* Trigger a OOB (out of band) request to the GMU */
 int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state)
 {
+	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
+	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	int ret;
 	u32 val;
 	int request, ack;
 
 	WARN_ON_ONCE(!mutex_is_locked(&gmu->lock));
 
+	/* Skip OOB calls since RGMU is not enabled */
+	if (adreno_has_rgmu(adreno_gpu))
+		return 0;
+
 	if (state >= ARRAY_SIZE(a6xx_gmu_oob_bits))
 		return -EINVAL;
 
@@ -395,10 +401,16 @@ int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state)
 /* Clear a pending OOB state in the GMU */
 void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state)
 {
+	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
+	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	int bit;
 
 	WARN_ON_ONCE(!mutex_is_locked(&gmu->lock));
 
+	/* Skip OOB calls since RGMU is not enabled */
+	if (adreno_has_rgmu(adreno_gpu))
+		return;
+
 	if (state >= ARRAY_SIZE(a6xx_gmu_oob_bits))
 		return;
 
@@ -1900,7 +1912,8 @@ void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu)
 	gmu->mmio = NULL;
 	gmu->rscc = NULL;
 
-	if (!adreno_has_gmu_wrapper(adreno_gpu)) {
+	if (!adreno_has_gmu_wrapper(adreno_gpu) &&
+	    !adreno_has_rgmu(adreno_gpu)) {
 		a6xx_gmu_memory_free(gmu);
 
 		free_irq(gmu->gmu_irq, gmu);
@@ -1942,6 +1955,13 @@ int a6xx_gmu_wrapper_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 	/* Mark legacy for manual SPTPRAC control */
 	gmu->legacy = true;
 
+	/* RGMU requires clocks */
+	ret = devm_clk_bulk_get_all(gmu->dev, &gmu->clocks);
+	if (ret < 0)
+		goto err_clk;
+
+	gmu->nr_clocks = ret;
+
 	/* Map the GMU registers */
 	gmu->mmio = a6xx_gmu_get_mmio(pdev, "gmu");
 	if (IS_ERR(gmu->mmio)) {
@@ -1981,6 +2001,7 @@ detach_cxpd:
 err_mmio:
 	iounmap(gmu->mmio);
 
+err_clk:
 	/* Drop reference taken in of_find_device_by_node */
 	put_device(gmu->dev);
 

drivers/gpu/drm/msm/adreno/a6xx_gpu.c

@@ -612,15 +612,26 @@ static void a6xx_set_hwcg(struct msm_gpu *gpu, bool state)
 
 	if (adreno_is_a630(adreno_gpu))
 		clock_cntl_on = 0x8aa8aa02;
-	else if (adreno_is_a610(adreno_gpu))
+	else if (adreno_is_a610(adreno_gpu) || adreno_is_a612(adreno_gpu))
 		clock_cntl_on = 0xaaa8aa82;
 	else if (adreno_is_a702(adreno_gpu))
 		clock_cntl_on = 0xaaaaaa82;
 	else
 		clock_cntl_on = 0x8aa8aa82;
 
-	cgc_delay = adreno_is_a615_family(adreno_gpu) ? 0x111 : 0x10111;
-	cgc_hyst = adreno_is_a615_family(adreno_gpu) ? 0x555 : 0x5555;
+	if (adreno_is_a612(adreno_gpu))
+		cgc_delay = 0x11;
+	else if (adreno_is_a615_family(adreno_gpu))
+		cgc_delay = 0x111;
+	else
+		cgc_delay = 0x10111;
+
+	if (adreno_is_a612(adreno_gpu))
+		cgc_hyst = 0x55;
+	else if (adreno_is_a615_family(adreno_gpu))
+		cgc_hyst = 0x555;
+	else
+		cgc_hyst = 0x5555;
 
 	gmu_write(&a6xx_gpu->gmu, REG_A6XX_GPU_GMU_AO_GMU_CGC_MODE_CNTL,
 			state ? adreno_gpu->info->a6xx->gmu_cgc_mode : 0);
@@ -714,6 +725,9 @@ static int a6xx_calc_ubwc_config(struct adreno_gpu *gpu)
 		cfg->ubwc_swizzle = 0x7;
 	}
 
+	if (adreno_is_a612(gpu))
+		cfg->highest_bank_bit = 14;
+
 	if (adreno_is_a618(gpu))
 		cfg->highest_bank_bit = 14;
 
@@ -1288,7 +1302,7 @@ static int hw_init(struct msm_gpu *gpu)
 		gpu_write(gpu, REG_A6XX_CP_LPAC_PROG_FIFO_SIZE, 0x00000020);
 
 	/* Setting the mem pool size */
-	if (adreno_is_a610(adreno_gpu)) {
+	if (adreno_is_a610(adreno_gpu) || adreno_is_a612(adreno_gpu)) {
 		gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, 48);
 		gpu_write(gpu, REG_A6XX_CP_MEM_POOL_DBG_ADDR, 47);
 	} else if (adreno_is_a702(adreno_gpu)) {
@@ -1321,7 +1335,8 @@ static int hw_init(struct msm_gpu *gpu)
 	a6xx_set_ubwc_config(gpu);
 
 	/* Enable fault detection */
-	if (adreno_is_a730(adreno_gpu) ||
+	if (adreno_is_a612(adreno_gpu) ||
+	    adreno_is_a730(adreno_gpu) ||
 	    adreno_is_a740_family(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL, (1 << 30) | 0xcfffff);
 	else if (adreno_is_a690(adreno_gpu))
@@ -1576,7 +1591,7 @@ static void a6xx_recover(struct msm_gpu *gpu)
 	 */
 	gpu->active_submits = 0;
 
-	if (adreno_has_gmu_wrapper(adreno_gpu)) {
+	if (adreno_has_gmu_wrapper(adreno_gpu) || adreno_has_rgmu(adreno_gpu)) {
 		/* Drain the outstanding traffic on memory buses */
 		a6xx_bus_clear_pending_transactions(adreno_gpu, true);
 
@@ -2229,6 +2244,12 @@ static int a6xx_pm_resume(struct msm_gpu *gpu)
 	if (ret)
 		goto err_bulk_clk;
 
+	ret = clk_bulk_prepare_enable(gmu->nr_clocks, gmu->clocks);
+	if (ret) {
+		clk_bulk_disable_unprepare(gpu->nr_clocks, gpu->grp_clks);
+		goto err_bulk_clk;
+	}
+
 	if (adreno_is_a619_holi(adreno_gpu))
 		a6xx_sptprac_enable(gmu);
 
@@ -2242,8 +2263,10 @@ err_bulk_clk:
 err_set_opp:
 	mutex_unlock(&a6xx_gpu->gmu.lock);
 
-	if (!ret)
+	if (!ret) {
 		msm_devfreq_resume(gpu);
+		a6xx_llc_activate(a6xx_gpu);
+	}
 
 	return ret;
 }
@@ -2284,6 +2307,8 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu)
 
 	trace_msm_gpu_suspend(0);
 
+	a6xx_llc_deactivate(a6xx_gpu);
+
 	msm_devfreq_suspend(gpu);
 
 	mutex_lock(&a6xx_gpu->gmu.lock);
@@ -2295,6 +2320,7 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu)
 		a6xx_sptprac_disable(gmu);
 
 	clk_bulk_disable_unprepare(gpu->nr_clocks, gpu->grp_clks);
+	clk_bulk_disable_unprepare(gmu->nr_clocks, gmu->clocks);
 
 	pm_runtime_put_sync(gmu->gxpd);
 	dev_pm_opp_set_opp(&gpu->pdev->dev, NULL);
@@ -2673,7 +2699,8 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 		ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs_a7xx, 4);
 	else if (is_a7xx)
 		ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs_a7xx, 1);
-	else if (adreno_has_gmu_wrapper(adreno_gpu))
+	else if (adreno_has_gmu_wrapper(adreno_gpu) ||
+		 of_device_is_compatible(node, "qcom,adreno-rgmu"))
 		ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs_gmuwrapper, 1);
 	else
 		ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1);
@@ -2689,7 +2716,7 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 	if (adreno_is_a618(adreno_gpu) || adreno_is_7c3(adreno_gpu))
 		priv->gpu_clamp_to_idle = true;
 
-	if (adreno_has_gmu_wrapper(adreno_gpu))
+	if (adreno_has_gmu_wrapper(adreno_gpu) || adreno_has_rgmu(adreno_gpu))
 		ret = a6xx_gmu_wrapper_init(a6xx_gpu, node);
 	else
 		ret = a6xx_gmu_init(a6xx_gpu, node);

drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c

@@ -1596,7 +1596,8 @@ struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu)
 	/* Get the generic state from the adreno core */
 	adreno_gpu_state_get(gpu, &a6xx_state->base);
 
-	if (!adreno_has_gmu_wrapper(adreno_gpu)) {
+	if (!adreno_has_gmu_wrapper(adreno_gpu) &&
+	    !adreno_has_rgmu(adreno_gpu)) {
 		a6xx_get_gmu_registers(gpu, a6xx_state);
 
 		a6xx_state->gmu_log = a6xx_snapshot_gmu_bo(a6xx_state, &a6xx_gpu->gmu.log);

drivers/gpu/drm/msm/adreno/adreno_gpu.c

@@ -1189,6 +1189,7 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 
 	/* Only handle the core clock when GMU is not in use (or is absent). */
 	if (adreno_has_gmu_wrapper(adreno_gpu) ||
+	    adreno_has_rgmu(adreno_gpu) ||
 	    adreno_gpu->info->family < ADRENO_6XX_GEN1) {
 		/*
 		 * This can only be done before devm_pm_opp_of_add_table(), or

drivers/gpu/drm/msm/adreno/adreno_gpu.h

@@ -392,6 +392,16 @@ static inline int adreno_is_a610(const struct adreno_gpu *gpu)
 	return adreno_is_revn(gpu, 610);
 }
 
+static inline int adreno_is_a612(const struct adreno_gpu *gpu)
+{
+	return gpu->info->chip_ids[0] == 0x06010200;
+}
+
+static inline bool adreno_has_rgmu(const struct adreno_gpu *gpu)
+{
+	return adreno_is_a612(gpu);
+}
+
 static inline int adreno_is_a618(const struct adreno_gpu *gpu)
 {
 	return adreno_is_revn(gpu, 618);
@@ -466,9 +476,9 @@ static inline int adreno_is_a610_family(const struct adreno_gpu *gpu)
 {
 	if (WARN_ON_ONCE(!gpu->info))
 		return false;
-
-	/* TODO: A612 */
-	return adreno_is_a610(gpu) || adreno_is_a702(gpu);
+	return adreno_is_a610(gpu) ||
+	       adreno_is_a612(gpu) ||
+	       adreno_is_a702(gpu);
 }
 
 /* TODO: 615/616 */