Merge tag 'drm-msm-next-2018-01-10' of git://people.freedesktop.org/~robclark/linux into drm-next

Updates for 4.16.. fairly small this time around, main thing is
devfreq support for the gpu.

* tag 'drm-msm-next-2018-01-10' of git://people.freedesktop.org/~robclark/linux:
  drm/msm: Add devfreq support for the GPU
  drm/msm/adreno: a5xx: Explicitly program the CP0 performance counter
  drm/msm/adreno: Read the speed bins for a5xx targets
  drm/msm/adreno: Move clock parsing to adreno_gpu_init()
  drm/msm/adreno: Cleanup chipid parsing
  drm/msm/gpu: Remove unused bus scaling code
  drm/msm/adreno: Remove a useless call to dev_pm_opp_get_freq()
  drm/msm/adreno: Call dev_pm_opp_put()
  drm/msm: Fix NULL deref in adreno_load_gpu
  drm/msm: gpu: Only sync fences on rings that exist
  drm/msm: fix leak in failed get_pages
  drm/msm: avoid false-positive -Wmaybe-uninitialized warning
  drm/msm/mdp4: Deduplicate bus_find_device() by name matching
  drm/msm: add missing MODULE_FIRMWARE declarations
  drm/msm: update adreno firmware path in MODULE_FIRMWARE
  drm/msm: free kstrdup'd cmdline
  drm/msm: fix msm_rd_dump_submit prototype
  drm/msm: fix spelling mistake: "ringubffer" -> "ringbuffer"

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

@@ -17,6 +17,8 @@
 #include <linux/dma-mapping.h>
 #include <linux/of_address.h>
 #include <linux/soc/qcom/mdt_loader.h>
+#include <linux/pm_opp.h>
+#include <linux/nvmem-consumer.h>
 #include "msm_gem.h"
 #include "msm_mmu.h"
 #include "a5xx_gpu.h"
@@ -595,6 +597,12 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	/* Turn on performance counters */
 	gpu_write(gpu, REG_A5XX_RBBM_PERFCTR_CNTL, 0x01);
 
+	/* Select CP0 to always count cycles */
+	gpu_write(gpu, REG_A5XX_CP_PERFCTR_CP_SEL_0, PERF_CP_ALWAYS_COUNT);
+
+	/* Select RBBM0 to countable 6 to get the busy status for devfreq */
+	gpu_write(gpu, REG_A5XX_RBBM_PERFCTR_RBBM_SEL_0, 6);
+
 	/* Increase VFD cache access so LRZ and other data gets evicted less */
 	gpu_write(gpu, REG_A5XX_UCHE_CACHE_WAYS, 0x02);
 
@@ -1165,6 +1173,14 @@ static struct msm_ringbuffer *a5xx_active_ring(struct msm_gpu *gpu)
 	return a5xx_gpu->cur_ring;
 }
 
+static int a5xx_gpu_busy(struct msm_gpu *gpu, uint64_t *value)
+{
+	*value = gpu_read64(gpu, REG_A5XX_RBBM_PERFCTR_RBBM_0_LO,
+		REG_A5XX_RBBM_PERFCTR_RBBM_0_HI);
+
+	return 0;
+}
+
 static const struct adreno_gpu_funcs funcs = {
 	.base = {
 		.get_param = adreno_get_param,
@@ -1180,10 +1196,30 @@ static const struct adreno_gpu_funcs funcs = {
 #ifdef CONFIG_DEBUG_FS
 		.show = a5xx_show,
 #endif
+		.gpu_busy = a5xx_gpu_busy,
 	},
 	.get_timestamp = a5xx_get_timestamp,
 };
 
+static void check_speed_bin(struct device *dev)
+{
+	struct nvmem_cell *cell;
+	u32 bin, val;
+
+	cell = nvmem_cell_get(dev, "speed_bin");
+
+	/* If a nvmem cell isn't defined, nothing to do */
+	if (IS_ERR(cell))
+		return;
+
+	bin = *((u32 *) nvmem_cell_read(cell, NULL));
+	nvmem_cell_put(cell);
+
+	val = (1 << bin);
+
+	dev_pm_opp_set_supported_hw(dev, &val, 1);
+}
+
 struct msm_gpu *a5xx_gpu_init(struct drm_device *dev)
 {
 	struct msm_drm_private *priv = dev->dev_private;
@@ -1210,6 +1246,8 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev)
 
 	a5xx_gpu->lm_leakage = 0x4E001A;
 
+	check_speed_bin(&pdev->dev);
+
 	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 4);
 	if (ret) {
 		a5xx_destroy(&(a5xx_gpu->base.base));

drivers/gpu/drm/msm/adreno/a5xx_power.c

@@ -103,10 +103,16 @@ static inline uint32_t _get_mvolts(struct msm_gpu *gpu, uint32_t freq)
 	struct msm_drm_private *priv = dev->dev_private;
 	struct platform_device *pdev = priv->gpu_pdev;
 	struct dev_pm_opp *opp;
+	u32 ret = 0;
 
 	opp = dev_pm_opp_find_freq_exact(&pdev->dev, freq, true);
 
-	return (!IS_ERR(opp)) ? dev_pm_opp_get_voltage(opp) / 1000 : 0;
+	if (!IS_ERR(opp)) {
+		ret = dev_pm_opp_get_voltage(opp) / 1000;
+		dev_pm_opp_put(opp);
+	}
+
+	return ret;
 }
 
 /* Setup thermal limit management */

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

@@ -17,7 +17,6 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include <linux/pm_opp.h>
 #include "adreno_gpu.h"
 
 #define ANY_ID 0xff
@@ -90,14 +89,19 @@ static const struct adreno_info gpulist[] = {
 	},
 };
 
-MODULE_FIRMWARE("a300_pm4.fw");
-MODULE_FIRMWARE("a300_pfp.fw");
-MODULE_FIRMWARE("a330_pm4.fw");
-MODULE_FIRMWARE("a330_pfp.fw");
-MODULE_FIRMWARE("a420_pm4.fw");
-MODULE_FIRMWARE("a420_pfp.fw");
-MODULE_FIRMWARE("a530_fm4.fw");
-MODULE_FIRMWARE("a530_pfp.fw");
+MODULE_FIRMWARE("qcom/a300_pm4.fw");
+MODULE_FIRMWARE("qcom/a300_pfp.fw");
+MODULE_FIRMWARE("qcom/a330_pm4.fw");
+MODULE_FIRMWARE("qcom/a330_pfp.fw");
+MODULE_FIRMWARE("qcom/a420_pm4.fw");
+MODULE_FIRMWARE("qcom/a420_pfp.fw");
+MODULE_FIRMWARE("qcom/a530_pm4.fw");
+MODULE_FIRMWARE("qcom/a530_pfp.fw");
+MODULE_FIRMWARE("qcom/a530v3_gpmu.fw2");
+MODULE_FIRMWARE("qcom/a530_zap.mdt");
+MODULE_FIRMWARE("qcom/a530_zap.b00");
+MODULE_FIRMWARE("qcom/a530_zap.b01");
+MODULE_FIRMWARE("qcom/a530_zap.b02");
 
 static inline bool _rev_match(uint8_t entry, uint8_t id)
 {
@@ -125,11 +129,14 @@ struct msm_gpu *adreno_load_gpu(struct drm_device *dev)
 {
 	struct msm_drm_private *priv = dev->dev_private;
 	struct platform_device *pdev = priv->gpu_pdev;
-	struct msm_gpu *gpu = platform_get_drvdata(priv->gpu_pdev);
+	struct msm_gpu *gpu = NULL;
 	int ret;
 
+	if (pdev)
+		gpu = platform_get_drvdata(pdev);
+
 	if (!gpu) {
-		dev_err(dev->dev, "no adreno device\n");
+		dev_err_once(dev->dev, "no GPU device was found\n");
 		return NULL;
 	}
 
@@ -153,101 +160,45 @@ static void set_gpu_pdev(struct drm_device *dev,
 	priv->gpu_pdev = pdev;
 }
 
-static int find_chipid(struct device *dev, u32 *chipid)
+static int find_chipid(struct device *dev, struct adreno_rev *rev)
 {
 	struct device_node *node = dev->of_node;
 	const char *compat;
 	int ret;
+	u32 chipid;
 
 	/* first search the compat strings for qcom,adreno-XYZ.W: */
 	ret = of_property_read_string_index(node, "compatible", 0, &compat);
 	if (ret == 0) {
-		unsigned rev, patch;
+		unsigned int r, patch;
 
-		if (sscanf(compat, "qcom,adreno-%u.%u", &rev, &patch) == 2) {
-			*chipid = 0;
-			*chipid |= (rev / 100) << 24;  /* core */
-			rev %= 100;
-			*chipid |= (rev / 10) << 16;   /* major */
-			rev %= 10;
-			*chipid |= rev << 8;           /* minor */
-			*chipid |= patch;
+		if (sscanf(compat, "qcom,adreno-%u.%u", &r, &patch) == 2) {
+			rev->core = r / 100;
+			r %= 100;
+			rev->major = r / 10;
+			r %= 10;
+			rev->minor = r;
+			rev->patchid = patch;
 
 			return 0;
 		}
 	}
 
 	/* and if that fails, fall back to legacy "qcom,chipid" property: */
-	ret = of_property_read_u32(node, "qcom,chipid", chipid);
-	if (ret)
+	ret = of_property_read_u32(node, "qcom,chipid", &chipid);
+	if (ret) {
+		dev_err(dev, "could not parse qcom,chipid: %d\n", ret);
 		return ret;
-
-	dev_warn(dev, "Using legacy qcom,chipid binding!\n");
-	dev_warn(dev, "Use compatible qcom,adreno-%u%u%u.%u instead.\n",
-			(*chipid >> 24) & 0xff, (*chipid >> 16) & 0xff,
-			(*chipid >> 8) & 0xff, *chipid & 0xff);
-
-	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;
+	rev->core = (chipid >> 24) & 0xff;
+	rev->major = (chipid >> 16) & 0xff;
+	rev->minor = (chipid >> 8) & 0xff;
+	rev->patchid = (chipid & 0xff);
 
-		/*
-		 * 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;
-	}
+	dev_warn(dev, "Using legacy qcom,chipid binding!\n");
+	dev_warn(dev, "Use compatible qcom,adreno-%u%u%u.%u instead.\n",
+		rev->core, rev->major, rev->minor, rev->patchid);
 
 	return 0;
 }
@@ -258,22 +209,9 @@ static int adreno_bind(struct device *dev, struct device *master, void *data)
 	const struct adreno_info *info;
 	struct drm_device *drm = dev_get_drvdata(master);
 	struct msm_gpu *gpu;
-	u32 val;
 	int ret;
 
-	ret = find_chipid(dev, &val);
-	if (ret) {
-		dev_err(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;
-
-	ret = adreno_get_pwrlevels(dev, &config);
+	ret = find_chipid(dev, &config.rev);
 	if (ret)
 		return ret;
 

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

@@ -17,11 +17,11 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/pm_opp.h>
 #include "adreno_gpu.h"
 #include "msm_gem.h"
 #include "msm_mmu.h"
 
-
 int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -461,10 +461,80 @@ void adreno_wait_ring(struct msm_ringbuffer *ring, uint32_t ndwords)
 {
 	if (spin_until(ring_freewords(ring) >= ndwords))
 		DRM_DEV_ERROR(ring->gpu->dev->dev,
-			"timeout waiting for space in ringubffer %d\n",
+			"timeout waiting for space in ringbuffer %d\n",
 			ring->id);
 }
 
+/* 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 msm_gpu *gpu)
+{
+	unsigned long freq = ULONG_MAX;
+	struct dev_pm_opp *opp;
+	int ret;
+
+	gpu->fast_rate = 0;
+
+	/* 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)
+			dev_err(dev, "Unable to set the OPP table\n");
+	}
+
+	if (!ret) {
+		/* Find the fastest defined rate */
+		opp = dev_pm_opp_find_freq_floor(dev, &freq);
+		if (!IS_ERR(opp)) {
+			gpu->fast_rate = freq;
+			dev_pm_opp_put(opp);
+		}
+	}
+
+	if (!gpu->fast_rate) {
+		dev_warn(dev,
+			"Could not find a clock rate. Using a reasonable default\n");
+		/* Pick a suitably safe clock speed for any target */
+		gpu->fast_rate = 200000000;
+	}
+
+	DBG("fast_rate=%u, slow_rate=27000000", gpu->fast_rate);
+
+	return 0;
+}
+
 int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 		struct adreno_gpu *adreno_gpu,
 		const struct adreno_gpu_funcs *funcs, int nr_rings)
@@ -479,15 +549,6 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	adreno_gpu->revn = adreno_gpu->info->revn;
 	adreno_gpu->rev = config->rev;
 
-	gpu->fast_rate = config->fast_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=27000000, bus_freq=%u",
-			gpu->fast_rate, gpu->bus_freq);
-
 	adreno_gpu_config.ioname = "kgsl_3d0_reg_memory";
 	adreno_gpu_config.irqname = "kgsl_3d0_irq";
 
@@ -496,6 +557,8 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 
 	adreno_gpu_config.nr_rings = nr_rings;
 
+	adreno_get_pwrlevels(&pdev->dev, gpu);
+
 	pm_runtime_set_autosuspend_delay(&pdev->dev, DRM_MSM_INACTIVE_PERIOD);
 	pm_runtime_use_autosuspend(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);

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

@@ -129,10 +129,6 @@ struct adreno_gpu {
 /* platform config data (ie. from DT, or pdata) */
 struct adreno_platform_config {
 	struct adreno_rev rev;
-	uint32_t fast_rate, bus_freq;
-#ifdef DOWNSTREAM_CONFIG_MSM_BUS_SCALING
-	struct msm_bus_scale_pdata *bus_scale_table;
-#endif
 };
 
 #define ADRENO_IDLE_TIMEOUT msecs_to_jiffies(1000)

drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h

@@ -234,10 +234,6 @@ static inline struct clk *mpd4_lvds_pll_init(struct drm_device *dev)
 #endif
 
 #ifdef DOWNSTREAM_CONFIG_MSM_BUS_SCALING
-static inline int match_dev_name(struct device *dev, void *data)
-{
-	return !strcmp(dev_name(dev), data);
-}
 /* bus scaling data is associated with extra pointless platform devices,
  * "dtv", etc.. this is a bit of a hack, but we need a way for encoders
  * to find their pdata to make the bus-scaling stuff work.
@@ -245,8 +241,7 @@ static inline int match_dev_name(struct device *dev, void *data)
 static inline void *mdp4_find_pdata(const char *devname)
 {
 	struct device *dev;
-	dev = bus_find_device(&platform_bus_type, NULL,
-			(void *)devname, match_dev_name);
+	dev = bus_find_device_by_name(&platform_bus_type, NULL, devname);
 	return dev ? dev->platform_data : NULL;
 }
 #endif

drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c

@@ -966,8 +966,6 @@ static int mdp5_plane_mode_set(struct drm_plane *plane,
 	uint32_t src_x, src_y;
 	uint32_t src_w, src_h;
 	uint32_t src_img_w, src_img_h;
-	uint32_t src_x_r;
-	int crtc_x_r;
 	int ret;
 
 	nplanes = fb->format->num_planes;
@@ -1012,9 +1010,6 @@ static int mdp5_plane_mode_set(struct drm_plane *plane,
 		crtc_w /= 2;
 		src_w /= 2;
 		src_img_w /= 2;
-
-		crtc_x_r = crtc_x + crtc_w;
-		src_x_r = src_x + src_w;
 	}
 
 	ret = calc_scalex_steps(plane, pix_format, src_w, crtc_w, step.x);
@@ -1054,9 +1049,9 @@ static int mdp5_plane_mode_set(struct drm_plane *plane,
 	if (right_hwpipe)
 		mdp5_hwpipe_mode_set(mdp5_kms, right_hwpipe, fb, &step, &pe,
 				     config, hdecm, vdecm, hflip, vflip,
-				     crtc_x_r, crtc_y, crtc_w, crtc_h,
+				     crtc_x + crtc_w, crtc_y, crtc_w, crtc_h,
 				     src_img_w, src_img_h,
-				     src_x_r, src_y, src_w, src_h);
+				     src_x + src_w, src_y, src_w, src_h);
 
 	plane->fb = fb;
 

drivers/gpu/drm/msm/msm_drv.h

@@ -303,7 +303,8 @@ int msm_perf_debugfs_init(struct drm_minor *minor);
 void msm_perf_debugfs_cleanup(struct msm_drm_private *priv);
 #else
 static inline int msm_debugfs_late_init(struct drm_device *dev) { return 0; }
-static inline void msm_rd_dump_submit(struct msm_gem_submit *submit) {}
+static inline void msm_rd_dump_submit(struct msm_rd_state *rd, struct msm_gem_submit *submit,
+		const char *fmt, ...) {}
 static inline void msm_rd_debugfs_cleanup(struct msm_drm_private *priv) {}
 static inline void msm_perf_debugfs_cleanup(struct msm_drm_private *priv) {}
 #endif

drivers/gpu/drm/msm/msm_gem.c

@@ -93,14 +93,17 @@ static struct page **get_pages(struct drm_gem_object *obj)
 			return p;
 		}
 
+		msm_obj->pages = p;
+
 		msm_obj->sgt = drm_prime_pages_to_sg(p, npages);
 		if (IS_ERR(msm_obj->sgt)) {
+			void *ptr = ERR_CAST(msm_obj->sgt);
+
 			dev_err(dev->dev, "failed to allocate sgt\n");
-			return ERR_CAST(msm_obj->sgt);
+			msm_obj->sgt = NULL;
+			return ptr;
 		}
 
-		msm_obj->pages = p;
-
 		/* For non-cached buffers, ensure the new pages are clean
 		 * because display controller, GPU, etc. are not coherent:
 		 */
@@ -135,7 +138,10 @@ static void put_pages(struct drm_gem_object *obj)
 		if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED))
 			dma_unmap_sg(obj->dev->dev, msm_obj->sgt->sgl,
 					msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+
+		if (msm_obj->sgt)
 			sg_free_table(msm_obj->sgt);
+
 		kfree(msm_obj->sgt);
 
 		if (use_pages(obj))

drivers/gpu/drm/msm/msm_gpu.c

@@ -21,42 +21,90 @@
 #include "msm_fence.h"
 
 #include <linux/string_helpers.h>
+#include <linux/pm_opp.h>
+#include <linux/devfreq.h>
 
 
 /*
  * Power Management:
  */
 
-#ifdef DOWNSTREAM_CONFIG_MSM_BUS_SCALING
-#include <mach/board.h>
-static void bs_init(struct msm_gpu *gpu)
+static int msm_devfreq_target(struct device *dev, unsigned long *freq,
+		u32 flags)
 {
-	if (gpu->bus_scale_table) {
-		gpu->bsc = msm_bus_scale_register_client(gpu->bus_scale_table);
-		DBG("bus scale client: %08x", gpu->bsc);
-	}
+	struct msm_gpu *gpu = platform_get_drvdata(to_platform_device(dev));
+	struct dev_pm_opp *opp;
+
+	opp = devfreq_recommended_opp(dev, freq, flags);
+
+	if (IS_ERR(opp))
+		return PTR_ERR(opp);
+
+	clk_set_rate(gpu->core_clk, *freq);
+	dev_pm_opp_put(opp);
+
+	return 0;
 }
 
-static void bs_fini(struct msm_gpu *gpu)
+static int msm_devfreq_get_dev_status(struct device *dev,
+		struct devfreq_dev_status *status)
 {
-	if (gpu->bsc) {
-		msm_bus_scale_unregister_client(gpu->bsc);
-		gpu->bsc = 0;
-	}
+	struct msm_gpu *gpu = platform_get_drvdata(to_platform_device(dev));
+	u64 cycles;
+	u32 freq = ((u32) status->current_frequency) / 1000000;
+	ktime_t time;
+
+	status->current_frequency = (unsigned long) clk_get_rate(gpu->core_clk);
+	gpu->funcs->gpu_busy(gpu, &cycles);
+
+	status->busy_time = ((u32) (cycles - gpu->devfreq.busy_cycles)) / freq;
+
+	gpu->devfreq.busy_cycles = cycles;
+
+	time = ktime_get();
+	status->total_time = ktime_us_delta(time, gpu->devfreq.time);
+	gpu->devfreq.time = time;
+
+	return 0;
+}
+
+static int msm_devfreq_get_cur_freq(struct device *dev, unsigned long *freq)
+{
+	struct msm_gpu *gpu = platform_get_drvdata(to_platform_device(dev));
+
+	*freq = (unsigned long) clk_get_rate(gpu->core_clk);
+
+	return 0;
 }
 
-static void bs_set(struct msm_gpu *gpu, int idx)
+static struct devfreq_dev_profile msm_devfreq_profile = {
+	.polling_ms = 10,
+	.target = msm_devfreq_target,
+	.get_dev_status = msm_devfreq_get_dev_status,
+	.get_cur_freq = msm_devfreq_get_cur_freq,
+};
+
+static void msm_devfreq_init(struct msm_gpu *gpu)
 {
-	if (gpu->bsc) {
-		DBG("set bus scaling: %d", idx);
-		msm_bus_scale_client_update_request(gpu->bsc, idx);
+	/* We need target support to do devfreq */
+	if (!gpu->funcs->gpu_busy)
+		return;
+
+	msm_devfreq_profile.initial_freq = gpu->fast_rate;
+
+	/*
+	 * Don't set the freq_table or max_state and let devfreq build the table
+	 * from OPP
+	 */
+
+	gpu->devfreq.devfreq = devm_devfreq_add_device(&gpu->pdev->dev,
+			&msm_devfreq_profile, "simple_ondemand", NULL);
+
+	if (IS_ERR(gpu->devfreq.devfreq)) {
+		dev_err(&gpu->pdev->dev, "Couldn't initialize GPU devfreq\n");
+		gpu->devfreq.devfreq = NULL;
 	}
 }
-#else
-static void bs_init(struct msm_gpu *gpu) {}
-static void bs_fini(struct msm_gpu *gpu) {}
-static void bs_set(struct msm_gpu *gpu, int idx) {}
-#endif
 
 static int enable_pwrrail(struct msm_gpu *gpu)
 {
@@ -143,8 +191,6 @@ static int enable_axi(struct msm_gpu *gpu)
 {
 	if (gpu->ebi1_clk)
 		clk_prepare_enable(gpu->ebi1_clk);
-	if (gpu->bus_freq)
-		bs_set(gpu, gpu->bus_freq);
 	return 0;
 }
 
@@ -152,8 +198,6 @@ static int disable_axi(struct msm_gpu *gpu)
 {
 	if (gpu->ebi1_clk)
 		clk_disable_unprepare(gpu->ebi1_clk);
-	if (gpu->bus_freq)
-		bs_set(gpu, 0);
 	return 0;
 }
 
@@ -175,6 +219,13 @@ int msm_gpu_pm_resume(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
+	if (gpu->devfreq.devfreq) {
+		gpu->devfreq.busy_cycles = 0;
+		gpu->devfreq.time = ktime_get();
+
+		devfreq_resume_device(gpu->devfreq.devfreq);
+	}
+
 	gpu->needs_hw_init = true;
 
 	return 0;
@@ -186,6 +237,9 @@ int msm_gpu_pm_suspend(struct msm_gpu *gpu)
 
 	DBG("%s", gpu->name);
 
+	if (gpu->devfreq.devfreq)
+		devfreq_suspend_device(gpu->devfreq.devfreq);
+
 	ret = disable_axi(gpu);
 	if (ret)
 		return ret;
@@ -294,6 +348,8 @@ static void recover_worker(struct work_struct *work)
 
 			msm_rd_dump_submit(priv->hangrd, submit,
 				"offending task: %s (%s)", task->comm, cmd);
+
+			kfree(cmd);
 		} else {
 			msm_rd_dump_submit(priv->hangrd, submit, NULL);
 		}
@@ -306,7 +362,7 @@ static void recover_worker(struct work_struct *work)
 	 * needs to happen after msm_rd_dump_submit() to ensure that the
 	 * bo's referenced by the offending submit are still around.
 	 */
-	for (i = 0; i < ARRAY_SIZE(gpu->rb); i++) {
+	for (i = 0; i < gpu->nr_rings; i++) {
 		struct msm_ringbuffer *ring = gpu->rb[i];
 
 		uint32_t fence = ring->memptrs->fence;
@@ -753,7 +809,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	gpu->pdev = pdev;
 	platform_set_drvdata(pdev, gpu);
 
-	bs_init(gpu);
+	msm_devfreq_init(gpu);
 
 	gpu->aspace = msm_gpu_create_address_space(gpu, pdev,
 		config->va_start, config->va_end);
@@ -824,8 +880,6 @@ void msm_gpu_cleanup(struct msm_gpu *gpu)
 
 	WARN_ON(!list_empty(&gpu->active_list));
 
-	bs_fini(gpu);
-
 	for (i = 0; i < ARRAY_SIZE(gpu->rb); i++) {
 		msm_ringbuffer_destroy(gpu->rb[i]);
 		gpu->rb[i] = NULL;

drivers/gpu/drm/msm/msm_gpu.h

@@ -66,6 +66,7 @@ struct msm_gpu_funcs {
 	/* show GPU status in debugfs: */
 	void (*show)(struct msm_gpu *gpu, struct seq_file *m);
 #endif
+	int (*gpu_busy)(struct msm_gpu *gpu, uint64_t *value);
 };
 
 struct msm_gpu {
@@ -108,12 +109,7 @@ struct msm_gpu {
 	struct clk **grp_clks;
 	int nr_clocks;
 	struct clk *ebi1_clk, *core_clk, *rbbmtimer_clk;
-	uint32_t fast_rate, bus_freq;
-
-#ifdef DOWNSTREAM_CONFIG_MSM_BUS_SCALING
-	struct msm_bus_scale_pdata *bus_scale_table;
-	uint32_t bsc;
-#endif
+	uint32_t fast_rate;
 
 	/* Hang and Inactivity Detection:
 	 */
@@ -125,6 +121,12 @@ struct msm_gpu {
 	struct work_struct recover_work;
 
 	struct drm_gem_object *memptrs_bo;
+
+	struct {
+		struct devfreq *devfreq;
+		u64 busy_cycles;
+		ktime_t time;
+	} devfreq;
 };
 
 /* It turns out that all targets use the same ringbuffer size */