drm/msm: add a330/apq8x74

Add support for adreno 330.  Not too much different, just a few
differences in initial configuration plus setting OCMEM base.
Userspace support is already in upstream mesa.

Note that the existing DT code is simply using the bindings from
downstream android kernel, to simplify porting of this driver to
existing devices.  These do not constitute any committed/stable
DT ABI.  The addition of proper DT bindings will be a subsequent
patch, at which point (as best as possible) I will try to support
either upstream bindings or what is found in downstream android
kernel, so that existing device DT files can be used.

Signed-off-by: Rob Clark <robdclark@gmail.com>

drivers/gpu/drm/msm/adreno/a3xx_gpu.c

@@ -15,6 +15,10 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#ifdef CONFIG_MSM_OCMEM
+#  include <mach/ocmem.h>
+#endif
+
 #include "a3xx_gpu.h"
 
 #define A3XX_INT0_MASK \
@@ -63,6 +67,7 @@ static void a3xx_me_init(struct msm_gpu *gpu)
 static int a3xx_hw_init(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a3xx_gpu *a3xx_gpu = to_a3xx_gpu(adreno_gpu);
 	uint32_t *ptr, len;
 	int i, ret;
 
@@ -105,6 +110,21 @@ static int a3xx_hw_init(struct msm_gpu *gpu)
 		gpu_write(gpu, REG_A3XX_VBIF_ABIT_SORT, 0x000000ff);
 		gpu_write(gpu, REG_A3XX_VBIF_ABIT_SORT_CONF, 0x000000a4);
 
+	} else if (adreno_is_a330v2(adreno_gpu)) {
+		/*
+		 * Most of the VBIF registers on 8974v2 have the correct
+		 * values at power on, so we won't modify those if we don't
+		 * need to
+		 */
+		/* Enable 1k sort: */
+		gpu_write(gpu, REG_A3XX_VBIF_ABIT_SORT, 0x0001003f);
+		gpu_write(gpu, REG_A3XX_VBIF_ABIT_SORT_CONF, 0x000000a4);
+		/* Enable WR-REQ: */
+		gpu_write(gpu, REG_A3XX_VBIF_GATE_OFF_WRREQ_EN, 0x00003f);
+		gpu_write(gpu, REG_A3XX_VBIF_DDR_OUT_MAX_BURST, 0x0000303);
+		/* Set up VBIF_ROUND_ROBIN_QOS_ARB: */
+		gpu_write(gpu, REG_A3XX_VBIF_ROUND_ROBIN_QOS_ARB, 0x0003);
+
 	} else if (adreno_is_a330(adreno_gpu)) {
 		/* Set up 16 deep read/write request queues: */
 		gpu_write(gpu, REG_A3XX_VBIF_IN_RD_LIM_CONF0, 0x18181818);
@@ -121,10 +141,10 @@ static int a3xx_hw_init(struct msm_gpu *gpu)
 		/* Set up VBIF_ROUND_ROBIN_QOS_ARB: */
 		gpu_write(gpu, REG_A3XX_VBIF_ROUND_ROBIN_QOS_ARB, 0x0001);
 		/* Set up AOOO: */
-		gpu_write(gpu, REG_A3XX_VBIF_OUT_AXI_AOOO_EN, 0x0000ffff);
+		gpu_write(gpu, REG_A3XX_VBIF_OUT_AXI_AOOO_EN, 0x0000003f);
-		gpu_write(gpu, REG_A3XX_VBIF_OUT_AXI_AOOO, 0xffffffff);
+		gpu_write(gpu, REG_A3XX_VBIF_OUT_AXI_AOOO, 0x003f003f);
 		/* Enable 1K sort: */
-		gpu_write(gpu, REG_A3XX_VBIF_ABIT_SORT, 0x0001ffff);
+		gpu_write(gpu, REG_A3XX_VBIF_ABIT_SORT, 0x0001003f);
 		gpu_write(gpu, REG_A3XX_VBIF_ABIT_SORT_CONF, 0x000000a4);
 		/* Disable VBIF clock gating. This is to enable AXI running
 		 * higher frequency than GPU:
@@ -162,14 +182,23 @@ static int a3xx_hw_init(struct msm_gpu *gpu)
 	gpu_write(gpu, REG_A3XX_UCHE_CACHE_MODE_CONTROL_REG, 0x00000001);
 
 	/* Enable Clock gating: */
-	gpu_write(gpu, REG_A3XX_RBBM_CLOCK_CTL, 0xbfffffff);
+	if (adreno_is_a320(adreno_gpu))
+		gpu_write(gpu, REG_A3XX_RBBM_CLOCK_CTL, 0xbfffffff);
+	else if (adreno_is_a330v2(adreno_gpu))
+		gpu_write(gpu, REG_A3XX_RBBM_CLOCK_CTL, 0xaaaaaaaa);
+	else if (adreno_is_a330(adreno_gpu))
+		gpu_write(gpu, REG_A3XX_RBBM_CLOCK_CTL, 0xbffcffff);
 
-	/* Set the OCMEM base address for A330 */
+	if (adreno_is_a330v2(adreno_gpu))
-//TODO:
+		gpu_write(gpu, REG_A3XX_RBBM_GPR0_CTL, 0x05515455);
-//	if (adreno_is_a330(adreno_gpu)) {
+	else if (adreno_is_a330(adreno_gpu))
-//		gpu_write(gpu, REG_A3XX_RB_GMEM_BASE_ADDR,
+		gpu_write(gpu, REG_A3XX_RBBM_GPR0_CTL, 0x00000000);
-//			(unsigned int)(a3xx_gpu->ocmem_base >> 14));
+
-//	}
+	/* Set the OCMEM base address for A330, etc */
+	if (a3xx_gpu->ocmem_hdl) {
+		gpu_write(gpu, REG_A3XX_RB_GMEM_BASE_ADDR,
+			(unsigned int)(a3xx_gpu->ocmem_base >> 14));
+	}
 
 	/* Turn on performance counters: */
 	gpu_write(gpu, REG_A3XX_RBBM_PERFCTR_CTL, 0x01);
@@ -238,12 +267,19 @@ static int a3xx_hw_init(struct msm_gpu *gpu)
 		gpu_write(gpu, REG_A3XX_CP_PFP_UCODE_DATA, ptr[i]);
 
 	/* CP ROQ queue sizes (bytes) - RB:16, ST:16, IB1:32, IB2:64 */
-	if (adreno_is_a305(adreno_gpu) || adreno_is_a320(adreno_gpu))
+	if (adreno_is_a305(adreno_gpu) || adreno_is_a320(adreno_gpu)) {
 		gpu_write(gpu, REG_AXXX_CP_QUEUE_THRESHOLDS,
 				AXXX_CP_QUEUE_THRESHOLDS_CSQ_IB1_START(2) |
 				AXXX_CP_QUEUE_THRESHOLDS_CSQ_IB2_START(6) |
 				AXXX_CP_QUEUE_THRESHOLDS_CSQ_ST_START(14));
-
+	} else if (adreno_is_a330(adreno_gpu)) {
+		/* NOTE: this (value take from downstream android driver)
+		 * includes some bits outside of the known bitfields.  But
+		 * A330 has this "MERCIU queue" thing too, which might
+		 * explain a new bitfield or reshuffling:
+		 */
+		gpu_write(gpu, REG_AXXX_CP_QUEUE_THRESHOLDS, 0x003e2008);
+	}
 
 	/* clear ME_HALT to start micro engine */
 	gpu_write(gpu, REG_AXXX_CP_ME_CNTL, 0);
@@ -253,6 +289,14 @@ static int a3xx_hw_init(struct msm_gpu *gpu)
 	return 0;
 }
 
+static void a3xx_recover(struct msm_gpu *gpu)
+{
+	gpu_write(gpu, REG_A3XX_RBBM_SW_RESET_CMD, 1);
+	gpu_read(gpu, REG_A3XX_RBBM_SW_RESET_CMD);
+	gpu_write(gpu, REG_A3XX_RBBM_SW_RESET_CMD, 0);
+	adreno_recover(gpu);
+}
+
 static void a3xx_destroy(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -261,6 +305,12 @@ static void a3xx_destroy(struct msm_gpu *gpu)
 	DBG("%s", gpu->name);
 
 	adreno_gpu_cleanup(adreno_gpu);
+
+#ifdef CONFIG_MSM_OCMEM
+	if (a3xx_gpu->ocmem_base)
+		ocmem_free(OCMEM_GRAPHICS, a3xx_gpu->ocmem_hdl);
+#endif
+
 	put_device(&a3xx_gpu->pdev->dev);
 	kfree(a3xx_gpu);
 }
@@ -371,7 +421,7 @@ static const struct adreno_gpu_funcs funcs = {
 		.hw_init = a3xx_hw_init,
 		.pm_suspend = msm_gpu_pm_suspend,
 		.pm_resume = msm_gpu_pm_resume,
-		.recover = adreno_recover,
+		.recover = a3xx_recover,
 		.last_fence = adreno_last_fence,
 		.submit = adreno_submit,
 		.flush = adreno_flush,
@@ -387,6 +437,7 @@ static const struct adreno_gpu_funcs funcs = {
 struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
 {
 	struct a3xx_gpu *a3xx_gpu = NULL;
+	struct adreno_gpu *adreno_gpu;
 	struct msm_gpu *gpu;
 	struct platform_device *pdev = a3xx_pdev;
 	struct adreno_platform_config *config;
@@ -406,7 +457,8 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
 		goto fail;
 	}
 
-	gpu = &a3xx_gpu->base.base;
+	adreno_gpu = &a3xx_gpu->base;
+	gpu = &adreno_gpu->base;
 
 	get_device(&pdev->dev);
 	a3xx_gpu->pdev = pdev;
@@ -421,11 +473,25 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
 	DBG("fast_rate=%u, slow_rate=%u, bus_freq=%u",
 			gpu->fast_rate, gpu->slow_rate, gpu->bus_freq);
 
-	ret = adreno_gpu_init(dev, pdev, &a3xx_gpu->base,
+	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, config->rev);
-			&funcs, config->rev);
 	if (ret)
 		goto fail;
 
+	/* if needed, allocate gmem: */
+	if (adreno_is_a330(adreno_gpu)) {
+#ifdef CONFIG_MSM_OCMEM
+		/* TODO this is different/missing upstream: */
+		struct ocmem_buf *ocmem_hdl =
+				ocmem_allocate(OCMEM_GRAPHICS, adreno_gpu->gmem);
+
+		a3xx_gpu->ocmem_hdl = ocmem_hdl;
+		a3xx_gpu->ocmem_base = ocmem_hdl->addr;
+		adreno_gpu->gmem = ocmem_hdl->len;
+		DBG("using %dK of OCMEM at 0x%08x", adreno_gpu->gmem / 1024,
+				a3xx_gpu->ocmem_base);
+#endif
+	}
+
 	if (!gpu->mmu) {
 		/* TODO we think it is possible to configure the GPU to
 		 * restrict access to VRAM carveout.  But the required
@@ -460,7 +526,42 @@ static int a3xx_probe(struct platform_device *pdev)
 {
 	static struct adreno_platform_config config = {};
 #ifdef CONFIG_OF
-	/* TODO */
+	struct device_node *child, *node = pdev->dev.of_node;
+	u32 val;
+	int ret;
+
+	ret = of_property_read_u32(node, "qcom,chipid", &val);
+	if (ret) {
+		dev_err(&pdev->dev, "could not find chipid: %d\n", ret);
+		return ret;
+	}
+
+	config.rev = ADRENO_REV((val >> 24) & 0xff,
+			(val >> 16) & 0xff, (val >> 8) & 0xff, val & 0xff);
+
+	/* find clock rates: */
+	config.fast_rate = 0;
+	config.slow_rate = ~0;
+	for_each_child_of_node(node, child) {
+		if (of_device_is_compatible(child, "qcom,gpu-pwrlevels")) {
+			struct device_node *pwrlvl;
+			for_each_child_of_node(child, pwrlvl) {
+				ret = of_property_read_u32(pwrlvl, "qcom,gpu-freq", &val);
+				if (ret) {
+					dev_err(&pdev->dev, "could not find gpu-freq: %d\n", ret);
+					return ret;
+				}
+				config.fast_rate = max(config.fast_rate, val);
+				config.slow_rate = min(config.slow_rate, val);
+			}
+		}
+	}
+
+	if (!config.fast_rate) {
+		dev_err(&pdev->dev, "could not find clk rates\n");
+		return -ENXIO;
+	}
+
 #else
 	struct kgsl_device_platform_data *pdata = pdev->dev.platform_data;
 	uint32_t version = socinfo_get_version();
@@ -519,10 +620,19 @@ static int a3xx_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct of_device_id dt_match[] = {
+	{ .compatible = "qcom,kgsl-3d0" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, dt_match);
+
 static struct platform_driver a3xx_driver = {
 	.probe = a3xx_probe,
 	.remove = a3xx_remove,
-	.driver.name = "kgsl-3d0",
+	.driver = {
+		.name = "kgsl-3d0",
+		.of_match_table = dt_match,
+	},
 };
 
 void __init a3xx_register(void)

drivers/gpu/drm/msm/adreno/a3xx_gpu.h

@@ -24,6 +24,10 @@
 struct a3xx_gpu {
 	struct adreno_gpu base;
 	struct platform_device *pdev;
+
+	/* if OCMEM is used for GMEM: */
+	uint32_t ocmem_base;
+	void *ocmem_hdl;
 };
 #define to_a3xx_gpu(x) container_of(x, struct a3xx_gpu, base)
 

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

@@ -45,7 +45,7 @@ static const struct adreno_info gpulist[] = {
 		.pfpfw = "a300_pfp.fw",
 		.gmem  = SZ_512K,
 	}, {
-		.rev   = ADRENO_REV(3, 3, 0, 0),
+		.rev   = ADRENO_REV(3, 3, 0, ANY_ID),
 		.revn  = 330,
 		.name  = "A330",
 		.pm4fw = "a330_pm4.fw",
@@ -71,7 +71,7 @@ int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value)
 		*value = adreno_gpu->info->revn;
 		return 0;
 	case MSM_PARAM_GMEM_SIZE:
-		*value = adreno_gpu->info->gmem;
+		*value = adreno_gpu->gmem;
 		return 0;
 	default:
 		DBG("%s: invalid param: %u", gpu->name, param);
@@ -92,7 +92,7 @@ int adreno_hw_init(struct msm_gpu *gpu)
 	gpu_write(gpu, REG_AXXX_CP_RB_CNTL,
 			/* size is log2(quad-words): */
 			AXXX_CP_RB_CNTL_BUFSZ(ilog2(gpu->rb->size / 8)) |
-			AXXX_CP_RB_CNTL_BLKSZ(RB_BLKSIZE));
+			AXXX_CP_RB_CNTL_BLKSZ(ilog2(RB_BLKSIZE / 8)));
 
 	/* Setup ringbuffer address: */
 	gpu_write(gpu, REG_AXXX_CP_RB_BASE, gpu->rb_iova);
@@ -318,6 +318,7 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 			rev.core, rev.major, rev.minor, rev.patchid);
 
 	gpu->funcs = funcs;
+	gpu->gmem = gpu->info->gmem;
 	gpu->rev = rev;
 
 	ret = request_firmware(&gpu->pm4, gpu->info->pm4fw, drm->dev);

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

@@ -51,6 +51,7 @@ struct adreno_gpu {
 	struct msm_gpu base;
 	struct adreno_rev rev;
 	const struct adreno_info *info;
+	uint32_t gmem;  /* actual gmem size */
 	uint32_t revn;  /* numeric revision name */
 	const struct adreno_gpu_funcs *funcs;
 
@@ -97,6 +98,11 @@ static inline bool adreno_is_a330(struct adreno_gpu *gpu)
 	return gpu->revn == 330;
 }
 
+static inline bool adreno_is_a330v2(struct adreno_gpu *gpu)
+{
+	return adreno_is_a330(gpu) && (gpu->rev.patchid > 0);
+}
+
 int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value);
 int adreno_hw_init(struct msm_gpu *gpu);
 uint32_t adreno_last_fence(struct msm_gpu *gpu);

drivers/gpu/drm/msm/msm_iommu.c

@@ -40,7 +40,7 @@ static int msm_iommu_attach(struct msm_mmu *mmu, const char **names, int cnt)
 	for (i = 0; i < cnt; i++) {
 		struct device *msm_iommu_get_ctx(const char *ctx_name);
 		struct device *ctx = msm_iommu_get_ctx(names[i]);
-		if (!ctx)
+		if (IS_ERR_OR_NULL(ctx))
 			continue;
 		ret = iommu_attach_device(iommu->domain, ctx);
 		if (ret) {