Merge branch 'msm-next' of git://people.freedesktop.org/~robclark/lin…

…ux into drm-next

Noteworthy changes this time:
1) 4k support for newer chips (ganging up hwpipes and mixers)
2) using OPP bindings for gpu
3) more prep work towards per-process pagetables

* 'msm-next' of git://people.freedesktop.org/~robclark/linux: (47 commits)
  msm/drm: gpu: Dynamically locate the clocks from the device tree
  drm/msm: gpu: Use OPP tables if we can
  drm/msm: Hard code the GPU "slow frequency"
  drm/msm: Add MSM_PARAM_GMEM_BASE
  drm/msm: Reference count address spaces
  drm/msm: Make sure to detach the MMU during GPU cleanup
  drm/msm/mdp5: Enable 3D mux in mdp5_ctl
  drm/msm/mdp5: Reset CTL blend registers before configuring them
  drm/msm/mdp5: Assign 'right' mixer to CRTC state
  drm/msm/mdp5: Stage border out on base stage if CRTC has 2 LMs
  drm/msm/mdp5: Stage right side hwpipes on Right-side Layer Mixer
  drm/msm/mdp5: Prepare Layer Mixers for source split
  drm/msm/mdp5: Configure 'right' hwpipe
  drm/msm/mdp5: Assign a 'right hwpipe' to plane state
  drm/msm/mdp5: Create mdp5_hwpipe_mode_set
  drm/msm/mdp5: Add optional 'right' Layer Mixer in CRTC state
  drm/msm/mdp5: Add a CAP for Source Split
  drm/msm/mdp5: Remove mixer/intf pointers from mdp5_ctl
  drm/msm/mdp5: Start using parameters from CRTC state
  drm/msm/mdp5: Add more stuff to CRTC state
  ...

drivers/gpu/drm/msm/Makefile

@@ -40,6 +40,7 @@ msm-y := \
 	mdp/mdp5/mdp5_mdss.o \
 	mdp/mdp5/mdp5_kms.o \
 	mdp/mdp5/mdp5_pipe.o \
+	mdp/mdp5/mdp5_mixer.o \
 	mdp/mdp5/mdp5_plane.o \
 	mdp/mdp5/mdp5_smp.o \
 	msm_atomic.o \

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

@@ -412,10 +412,8 @@ static const unsigned int a3xx_registers[] = {
 #ifdef CONFIG_DEBUG_FS
 static void a3xx_show(struct msm_gpu *gpu, struct seq_file *m)
 {
-	gpu->funcs->pm_resume(gpu);
 	seq_printf(m, "status:   %08x\n",
 			gpu_read(gpu, REG_A3XX_RBBM_STATUS));
-	gpu->funcs->pm_suspend(gpu);
 	adreno_show(gpu, m);
 }
 #endif

drivers/gpu/drm/msm/adreno/a4xx_gpu.c

@@ -456,12 +456,8 @@ static const unsigned int a4xx_registers[] = {
 #ifdef CONFIG_DEBUG_FS
 static void a4xx_show(struct msm_gpu *gpu, struct seq_file *m)
 {
-	gpu->funcs->pm_resume(gpu);
-
 	seq_printf(m, "status:   %08x\n",
 			gpu_read(gpu, REG_A4XX_RBBM_STATUS));
-	gpu->funcs->pm_suspend(gpu);
-
 	adreno_show(gpu, m);
 
 }

drivers/gpu/drm/msm/adreno/a5xx_gpu.c

@@ -638,10 +638,8 @@ static void a5xx_cp_err_irq(struct msm_gpu *gpu)
 	}
 }
 
-static void a5xx_rbbm_err_irq(struct msm_gpu *gpu)
+static void a5xx_rbbm_err_irq(struct msm_gpu *gpu, u32 status)
 {
-	u32 status = gpu_read(gpu, REG_A5XX_RBBM_INT_0_STATUS);
-
 	if (status & A5XX_RBBM_INT_0_MASK_RBBM_AHB_ERROR) {
 		u32 val = gpu_read(gpu, REG_A5XX_RBBM_AHB_ERROR_STATUS);
 
@@ -653,6 +651,10 @@ static void a5xx_rbbm_err_irq(struct msm_gpu *gpu)
 
 		/* Clear the error */
 		gpu_write(gpu, REG_A5XX_RBBM_AHB_CMD, (1 << 4));
+
+		/* Clear the interrupt */
+		gpu_write(gpu, REG_A5XX_RBBM_INT_CLEAR_CMD,
+			A5XX_RBBM_INT_0_MASK_RBBM_AHB_ERROR);
 	}
 
 	if (status & A5XX_RBBM_INT_0_MASK_RBBM_TRANSFER_TIMEOUT)
@@ -704,10 +706,16 @@ static irqreturn_t a5xx_irq(struct msm_gpu *gpu)
 {
 	u32 status = gpu_read(gpu, REG_A5XX_RBBM_INT_0_STATUS);
 
-	gpu_write(gpu, REG_A5XX_RBBM_INT_CLEAR_CMD, status);
+	/*
+	 * Clear all the interrupts except RBBM_AHB_ERROR - if we clear it
+	 * before the source is cleared the interrupt will storm.
+	 */
+	gpu_write(gpu, REG_A5XX_RBBM_INT_CLEAR_CMD,
+		status & ~A5XX_RBBM_INT_0_MASK_RBBM_AHB_ERROR);
 
+	/* Pass status to a5xx_rbbm_err_irq because we've already cleared it */
 	if (status & RBBM_ERROR_MASK)
-		a5xx_rbbm_err_irq(gpu);
+		a5xx_rbbm_err_irq(gpu, status);
 
 	if (status & A5XX_RBBM_INT_0_MASK_CP_HW_ERROR)
 		a5xx_cp_err_irq(gpu);
@@ -837,12 +845,8 @@ static int a5xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value)
 #ifdef CONFIG_DEBUG_FS
 static void a5xx_show(struct msm_gpu *gpu, struct seq_file *m)
 {
-	gpu->funcs->pm_resume(gpu);
-
 	seq_printf(m, "status:   %08x\n",
 			gpu_read(gpu, REG_A5XX_RBBM_STATUS));
-	gpu->funcs->pm_suspend(gpu);
-
 	adreno_show(gpu, m);
 }
 #endif

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

@@ -2,7 +2,7 @@
  * Copyright (C) 2013-2014 Red Hat
  * Author: Rob Clark <robdclark@gmail.com>
  *
- * Copyright (c) 2014 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2014,2017 The Linux Foundation. All rights reserved.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License version 2 as published by
@@ -17,6 +17,7 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/pm_opp.h>
 #include "adreno_gpu.h"
 
 #define ANY_ID 0xff
@@ -155,21 +156,14 @@ struct msm_gpu *adreno_load_gpu(struct drm_device *dev)
 
 	if (gpu) {
 		int ret;
-		mutex_lock(&dev->struct_mutex);
-		gpu->funcs->pm_resume(gpu);
-		mutex_unlock(&dev->struct_mutex);
 
-		disable_irq(gpu->irq);
-
-		ret = gpu->funcs->hw_init(gpu);
+		pm_runtime_get_sync(&pdev->dev);
+		ret = msm_gpu_hw_init(gpu);
+		pm_runtime_put_sync(&pdev->dev);
 		if (ret) {
 			dev_err(dev->dev, "gpu hw init failed: %d\n", ret);
 			gpu->funcs->destroy(gpu);
 			gpu = NULL;
-		} else {
-			enable_irq(gpu->irq);
-			/* give inactive pm a chance to kick in: */
-			msm_gpu_retire(gpu);
 		}
 	}
 
@@ -220,10 +214,71 @@ static int find_chipid(struct device *dev, u32 *chipid)
 	return 0;
 }
 
+/* Get legacy powerlevels from qcom,gpu-pwrlevels and populate the opp table */
+static int adreno_get_legacy_pwrlevels(struct device *dev)
+{
+	struct device_node *child, *node;
+	int ret;
+
+	node = of_find_compatible_node(dev->of_node, NULL,
+		"qcom,gpu-pwrlevels");
+	if (!node) {
+		dev_err(dev, "Could not find the GPU powerlevels\n");
+		return -ENXIO;
+	}
+
+	for_each_child_of_node(node, child) {
+		unsigned int val;
+
+		ret = of_property_read_u32(child, "qcom,gpu-freq", &val);
+		if (ret)
+			continue;
+
+		/*
+		 * Skip the intentionally bogus clock value found at the bottom
+		 * of most legacy frequency tables
+		 */
+		if (val != 27000000)
+			dev_pm_opp_add(dev, val, 0);
+	}
+
+	return 0;
+}
+
+static int adreno_get_pwrlevels(struct device *dev,
+		struct adreno_platform_config *config)
+{
+	unsigned long freq = ULONG_MAX;
+	struct dev_pm_opp *opp;
+	int ret;
+
+	/* You down with OPP? */
+	if (!of_find_property(dev->of_node, "operating-points-v2", NULL))
+		ret = adreno_get_legacy_pwrlevels(dev);
+	else
+		ret = dev_pm_opp_of_add_table(dev);
+
+	if (ret)
+		return ret;
+
+	/* Find the fastest defined rate */
+	opp = dev_pm_opp_find_freq_floor(dev, &freq);
+	if (!IS_ERR(opp))
+		config->fast_rate = dev_pm_opp_get_freq(opp);
+
+	if (!config->fast_rate) {
+		DRM_DEV_INFO(dev,
+			"Could not find clock rate. Using default\n");
+		/* Pick a suitably safe clock speed for any target */
+		config->fast_rate = 200000000;
+	}
+
+	return 0;
+}
+
 static int adreno_bind(struct device *dev, struct device *master, void *data)
 {
 	static struct adreno_platform_config config = {};
-	struct device_node *child, *node = dev->of_node;
 	u32 val;
 	int ret;
 
@@ -238,28 +293,10 @@ static int adreno_bind(struct device *dev, struct device *master, void *data)
 
 	/* 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(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_warn(dev, "could not find clk rates\n");
-		/* This is a safe low speed for all devices: */
-		config.fast_rate = 200000000;
-		config.slow_rate = 27000000;
-	}
+	ret = adreno_get_pwrlevels(dev, &config);
+	if (ret)
+		return ret;
 
 	dev->platform_data = &config;
 	set_gpu_pdev(dev_get_drvdata(master), to_platform_device(dev));
@@ -296,12 +333,35 @@ static const struct of_device_id dt_match[] = {
 	{}
 };
 
+#ifdef CONFIG_PM
+static int adreno_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct msm_gpu *gpu = platform_get_drvdata(pdev);
+
+	return gpu->funcs->pm_resume(gpu);
+}
+
+static int adreno_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct msm_gpu *gpu = platform_get_drvdata(pdev);
+
+	return gpu->funcs->pm_suspend(gpu);
+}
+#endif
+
+static const struct dev_pm_ops adreno_pm_ops = {
+	SET_RUNTIME_PM_OPS(adreno_suspend, adreno_resume, NULL)
+};
+
 static struct platform_driver adreno_driver = {
 	.probe = adreno_probe,
 	.remove = adreno_remove,
 	.driver = {
 		.name = "adreno",
 		.of_match_table = dt_match,
+		.pm = &adreno_pm_ops,
 	},
 };
 

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

@@ -35,6 +35,9 @@ int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value)
 	case MSM_PARAM_GMEM_SIZE:
 		*value = adreno_gpu->gmem;
 		return 0;
+	case MSM_PARAM_GMEM_BASE:
+		*value = 0x100000;
+		return 0;
 	case MSM_PARAM_CHIP_ID:
 		*value = adreno_gpu->rev.patchid |
 				(adreno_gpu->rev.minor << 8) |
@@ -68,6 +71,14 @@ int adreno_hw_init(struct msm_gpu *gpu)
 		return ret;
 	}
 
+	/* reset ringbuffer: */
+	gpu->rb->cur = gpu->rb->start;
+
+	/* reset completed fence seqno: */
+	adreno_gpu->memptrs->fence = gpu->fctx->completed_fence;
+	adreno_gpu->memptrs->rptr  = 0;
+	adreno_gpu->memptrs->wptr  = 0;
+
 	/* Setup REG_CP_RB_CNTL: */
 	adreno_gpu_write(adreno_gpu, REG_ADRENO_CP_RB_CNTL,
 			/* size is log2(quad-words): */
@@ -111,29 +122,20 @@ uint32_t adreno_last_fence(struct msm_gpu *gpu)
 
 void adreno_recover(struct msm_gpu *gpu)
 {
-	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct drm_device *dev = gpu->dev;
 	int ret;
 
-	gpu->funcs->pm_suspend(gpu);
-
-	/* reset ringbuffer: */
-	gpu->rb->cur = gpu->rb->start;
-
-	/* reset completed fence seqno: */
-	adreno_gpu->memptrs->fence = gpu->fctx->completed_fence;
-	adreno_gpu->memptrs->rptr  = 0;
-	adreno_gpu->memptrs->wptr  = 0;
+	// XXX pm-runtime??  we *need* the device to be off after this
+	// so maybe continuing to call ->pm_suspend/resume() is better?
 
+	gpu->funcs->pm_suspend(gpu);
 	gpu->funcs->pm_resume(gpu);
 
-	disable_irq(gpu->irq);
-	ret = gpu->funcs->hw_init(gpu);
+	ret = msm_gpu_hw_init(gpu);
 	if (ret) {
 		dev_err(dev->dev, "gpu hw init failed: %d\n", ret);
 		/* hmm, oh well? */
 	}
-	enable_irq(gpu->irq);
 }
 
 void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
@@ -259,8 +261,6 @@ void adreno_show(struct msm_gpu *gpu, struct seq_file *m)
 	seq_printf(m, "wptr:     %d\n", adreno_gpu->memptrs->wptr);
 	seq_printf(m, "rb wptr:  %d\n", get_wptr(gpu->rb));
 
-	gpu->funcs->pm_resume(gpu);
-
 	/* dump these out in a form that can be parsed by demsm: */
 	seq_printf(m, "IO:region %s 00000000 00020000\n", gpu->name);
 	for (i = 0; adreno_gpu->registers[i] != ~0; i += 2) {
@@ -273,8 +273,6 @@ void adreno_show(struct msm_gpu *gpu, struct seq_file *m)
 			seq_printf(m, "IO:R %08x %08x\n", addr<<2, val);
 		}
 	}
-
-	gpu->funcs->pm_suspend(gpu);
 }
 #endif
 
@@ -354,21 +352,24 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	adreno_gpu->rev = config->rev;
 
 	gpu->fast_rate = config->fast_rate;
-	gpu->slow_rate = config->slow_rate;
 	gpu->bus_freq  = config->bus_freq;
 #ifdef DOWNSTREAM_CONFIG_MSM_BUS_SCALING
 	gpu->bus_scale_table = config->bus_scale_table;
 #endif
 
-	DBG("fast_rate=%u, slow_rate=%u, bus_freq=%u",
-			gpu->fast_rate, gpu->slow_rate, gpu->bus_freq);
+	DBG("fast_rate=%u, slow_rate=27000000, bus_freq=%u",
+			gpu->fast_rate, gpu->bus_freq);
 
 	ret = msm_gpu_init(drm, pdev, &adreno_gpu->base, &funcs->base,
 			adreno_gpu->info->name, "kgsl_3d0_reg_memory", "kgsl_3d0_irq",
 			RB_SIZE);
 	if (ret)
 		return ret;
 
+	pm_runtime_set_autosuspend_delay(&pdev->dev, DRM_MSM_INACTIVE_PERIOD);
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+
 	ret = request_firmware(&adreno_gpu->pm4, adreno_gpu->info->pm4fw, drm->dev);
 	if (ret) {
 		dev_err(drm->dev, "failed to load %s PM4 firmware: %d\n",
@@ -439,6 +440,6 @@ void adreno_gpu_cleanup(struct adreno_gpu *adreno_gpu)
 	if (gpu->aspace) {
 		gpu->aspace->mmu->funcs->detach(gpu->aspace->mmu,
 			iommu_ports, ARRAY_SIZE(iommu_ports));
-		msm_gem_address_space_destroy(gpu->aspace);
+		msm_gem_address_space_put(gpu->aspace);
 	}
 }

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

@@ -123,7 +123,7 @@ struct adreno_gpu {
 /* platform config data (ie. from DT, or pdata) */
 struct adreno_platform_config {
 	struct adreno_rev rev;
-	uint32_t fast_rate, slow_rate, bus_freq;
+	uint32_t fast_rate, bus_freq;
 #ifdef DOWNSTREAM_CONFIG_MSM_BUS_SCALING
 	struct msm_bus_scale_pdata *bus_scale_table;
 #endif