Merge tag 'drm-msm-next-2021-04-11' of https://gitlab.freedesktop.org/drm/msm into drm-next

msm-next from Rob:
* Big DSI phy/pll cleanup. Includes some clk patches, acked by
  maintainer
* Initial support for sc7280
* compatibles fixes for sm8150/sm8250
* cleanups for all dpu gens to use same bandwidth scaling paths (\o/)
* various shrinker path lock contention optimizations
* unpin/swap support for GEM objects (disabled by default, enable with
  msm.enable_eviction=1 .. due to various combinations of iommu drivers
  with older gens I want to get more testing on hw I don't have in front
  of me before enabling by default)
* The usual assortment of misc fixes and cleanups

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
From: Rob Clark <robdclark@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/CAF6AEGvL=4aw15qoY8fbKG9FCgnx8Y-dCtf7xiFwTQSHopwSQg@mail.gmail.com

Author: danvet

drivers/clk/clk-mux.c

@@ -8,6 +8,7 @@
  */
 
 #include <linux/clk-provider.h>
+#include <linux/device.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/io.h>
@@ -206,6 +207,40 @@ struct clk_hw *__clk_hw_register_mux(struct device *dev, struct device_node *np,
 }
 EXPORT_SYMBOL_GPL(__clk_hw_register_mux);
 
+static void devm_clk_hw_release_mux(struct device *dev, void *res)
+{
+	clk_hw_unregister_mux(*(struct clk_hw **)res);
+}
+
+struct clk_hw *__devm_clk_hw_register_mux(struct device *dev, struct device_node *np,
+		const char *name, u8 num_parents,
+		const char * const *parent_names,
+		const struct clk_hw **parent_hws,
+		const struct clk_parent_data *parent_data,
+		unsigned long flags, void __iomem *reg, u8 shift, u32 mask,
+		u8 clk_mux_flags, u32 *table, spinlock_t *lock)
+{
+	struct clk_hw **ptr, *hw;
+
+	ptr = devres_alloc(devm_clk_hw_release_mux, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	hw = __clk_hw_register_mux(dev, np, name, num_parents, parent_names, parent_hws,
+				       parent_data, flags, reg, shift, mask,
+				       clk_mux_flags, table, lock);
+
+	if (!IS_ERR(hw)) {
+		*ptr = hw;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
+
+	return hw;
+}
+EXPORT_SYMBOL_GPL(__devm_clk_hw_register_mux);
+
 struct clk *clk_register_mux_table(struct device *dev, const char *name,
 		const char * const *parent_names, u8 num_parents,
 		unsigned long flags, void __iomem *reg, u8 shift, u32 mask,

drivers/gpu/drm/msm/Kconfig

@@ -20,6 +20,7 @@ config DRM_MSM
 	select SND_SOC_HDMI_CODEC if SND_SOC
 	select SYNC_FILE
 	select PM_OPP
+	select NVMEM
 	help
 	  DRM/KMS driver for MSM/snapdragon.
 
@@ -76,14 +77,6 @@ config DRM_MSM_DSI
 	  Choose this option if you have a need for MIPI DSI connector
 	  support.
 
-config DRM_MSM_DSI_PLL
-	bool "Enable DSI PLL driver in MSM DRM"
-	depends on DRM_MSM_DSI && COMMON_CLK
-	default y
-	help
-	  Choose this option to enable DSI PLL driver which provides DSI
-	  source clocks under common clock framework.
-
 config DRM_MSM_DSI_28NM_PHY
 	bool "Enable DSI 28nm PHY driver in MSM DRM"
 	depends on DRM_MSM_DSI

drivers/gpu/drm/msm/Makefile

@@ -136,13 +136,4 @@ msm-$(CONFIG_DRM_MSM_DSI_14NM_PHY) += dsi/phy/dsi_phy_14nm.o
 msm-$(CONFIG_DRM_MSM_DSI_10NM_PHY) += dsi/phy/dsi_phy_10nm.o
 msm-$(CONFIG_DRM_MSM_DSI_7NM_PHY) += dsi/phy/dsi_phy_7nm.o
 
-ifeq ($(CONFIG_DRM_MSM_DSI_PLL),y)
-msm-y += dsi/pll/dsi_pll.o
-msm-$(CONFIG_DRM_MSM_DSI_28NM_PHY) += dsi/pll/dsi_pll_28nm.o
-msm-$(CONFIG_DRM_MSM_DSI_28NM_8960_PHY) += dsi/pll/dsi_pll_28nm_8960.o
-msm-$(CONFIG_DRM_MSM_DSI_14NM_PHY) += dsi/pll/dsi_pll_14nm.o
-msm-$(CONFIG_DRM_MSM_DSI_10NM_PHY) += dsi/pll/dsi_pll_10nm.o
-msm-$(CONFIG_DRM_MSM_DSI_7NM_PHY) += dsi/pll/dsi_pll_7nm.o
-endif
-
 obj-$(CONFIG_DRM_MSM)	+= msm.o

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

@@ -246,7 +246,7 @@ static int a6xx_gmu_hfi_start(struct a6xx_gmu *gmu)
 }
 
 struct a6xx_gmu_oob_bits {
-	int set, ack, set_new, ack_new;
+	int set, ack, set_new, ack_new, clear, clear_new;
 	const char *name;
 };
 
@@ -260,6 +260,8 @@ static const struct a6xx_gmu_oob_bits a6xx_gmu_oob_bits[] = {
 		.ack = 24,
 		.set_new = 30,
 		.ack_new = 31,
+		.clear = 24,
+		.clear_new = 31,
 	},
 
 	[GMU_OOB_PERFCOUNTER_SET] = {
@@ -268,18 +270,22 @@ static const struct a6xx_gmu_oob_bits a6xx_gmu_oob_bits[] = {
 		.ack = 25,
 		.set_new = 28,
 		.ack_new = 30,
+		.clear = 25,
+		.clear_new = 29,
 	},
 
 	[GMU_OOB_BOOT_SLUMBER] = {
 		.name = "BOOT_SLUMBER",
 		.set = 22,
 		.ack = 30,
+		.clear = 30,
 	},
 
 	[GMU_OOB_DCVS_SET] = {
 		.name = "GPU_DCVS",
 		.set = 23,
 		.ack = 31,
+		.clear = 31,
 	},
 };
 
@@ -335,9 +341,9 @@ void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state)
 		return;
 
 	if (gmu->legacy)
-		bit = a6xx_gmu_oob_bits[state].ack;
+		bit = a6xx_gmu_oob_bits[state].clear;
 	else
-		bit = a6xx_gmu_oob_bits[state].ack_new;
+		bit = a6xx_gmu_oob_bits[state].clear_new;
 
 	gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, 1 << bit);
 }

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

@@ -273,6 +273,9 @@ int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value)
 	case MSM_PARAM_FAULTS:
 		*value = gpu->global_faults;
 		return 0;
+	case MSM_PARAM_SUSPENDS:
+		*value = gpu->suspend_count;
+		return 0;
 	default:
 		DBG("%s: invalid param: %u", gpu->name, param);
 		return -EINVAL;

drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c

@@ -58,8 +58,8 @@ int dpu_core_irq_idx_lookup(struct dpu_kms *dpu_kms,
 	if (!dpu_kms->hw_intr || !dpu_kms->hw_intr->ops.irq_idx_lookup)
 		return -EINVAL;
 
-	return dpu_kms->hw_intr->ops.irq_idx_lookup(intr_type,
-			instance_idx);
+	return dpu_kms->hw_intr->ops.irq_idx_lookup(dpu_kms->hw_intr,
+			intr_type, instance_idx);
 }
 
 /**

drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c

@@ -380,7 +380,6 @@ int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
 	} else {
 		DPU_DEBUG("crtc=%d disable\n", crtc->base.id);
 		memset(old, 0, sizeof(*old));
-		memset(new, 0, sizeof(*new));
 		update_bus = true;
 		update_clk = true;
 	}

drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c

@@ -66,6 +66,83 @@ static void dpu_crtc_destroy(struct drm_crtc *crtc)
 	kfree(dpu_crtc);
 }
 
+static struct drm_encoder *get_encoder_from_crtc(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_encoder *encoder;
+
+	drm_for_each_encoder(encoder, dev)
+		if (encoder->crtc == crtc)
+			return encoder;
+
+	return NULL;
+}
+
+static u32 dpu_crtc_get_vblank_counter(struct drm_crtc *crtc)
+{
+	struct drm_encoder *encoder;
+
+	encoder = get_encoder_from_crtc(crtc);
+	if (!encoder) {
+		DRM_ERROR("no encoder found for crtc %d\n", crtc->index);
+		return false;
+	}
+
+	return dpu_encoder_get_frame_count(encoder);
+}
+
+static bool dpu_crtc_get_scanout_position(struct drm_crtc *crtc,
+					   bool in_vblank_irq,
+					   int *vpos, int *hpos,
+					   ktime_t *stime, ktime_t *etime,
+					   const struct drm_display_mode *mode)
+{
+	unsigned int pipe = crtc->index;
+	struct drm_encoder *encoder;
+	int line, vsw, vbp, vactive_start, vactive_end, vfp_end;
+
+	encoder = get_encoder_from_crtc(crtc);
+	if (!encoder) {
+		DRM_ERROR("no encoder found for crtc %d\n", pipe);
+		return false;
+	}
+
+	vsw = mode->crtc_vsync_end - mode->crtc_vsync_start;
+	vbp = mode->crtc_vtotal - mode->crtc_vsync_end;
+
+	/*
+	 * the line counter is 1 at the start of the VSYNC pulse and VTOTAL at
+	 * the end of VFP. Translate the porch values relative to the line
+	 * counter positions.
+	 */
+
+	vactive_start = vsw + vbp + 1;
+	vactive_end = vactive_start + mode->crtc_vdisplay;
+
+	/* last scan line before VSYNC */
+	vfp_end = mode->crtc_vtotal;
+
+	if (stime)
+		*stime = ktime_get();
+
+	line = dpu_encoder_get_linecount(encoder);
+
+	if (line < vactive_start)
+		line -= vactive_start;
+	else if (line > vactive_end)
+		line = line - vfp_end - vactive_start;
+	else
+		line -= vactive_start;
+
+	*vpos = line;
+	*hpos = 0;
+
+	if (etime)
+		*etime = ktime_get();
+
+	return true;
+}
+
 static void _dpu_crtc_setup_blend_cfg(struct dpu_crtc_mixer *mixer,
 		struct dpu_plane_state *pstate, struct dpu_format *format)
 {
@@ -130,7 +207,9 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc,
 	uint32_t stage_idx, lm_idx;
 	int zpos_cnt[DPU_STAGE_MAX + 1] = { 0 };
 	bool bg_alpha_enable = false;
+	DECLARE_BITMAP(fetch_active, SSPP_MAX);
 
+	memset(fetch_active, 0, sizeof(fetch_active));
 	drm_atomic_crtc_for_each_plane(plane, crtc) {
 		state = plane->state;
 		if (!state)
@@ -140,7 +219,7 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc,
 		fb = state->fb;
 
 		dpu_plane_get_ctl_flush(plane, ctl, &flush_mask);
-
+		set_bit(dpu_plane_pipe(plane), fetch_active);
 		DPU_DEBUG("crtc %d stage:%d - plane %d sspp %d fb %d\n",
 				crtc->base.id,
 				pstate->stage,
@@ -180,6 +259,9 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc,
 		}
 	}
 
+	if (ctl->ops.set_active_pipes)
+		ctl->ops.set_active_pipes(ctl, fetch_active);
+
 	 _dpu_crtc_program_lm_output_roi(crtc);
 }
 
@@ -839,6 +921,7 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc,
 		DPU_DEBUG("crtc%d -> enable %d, active %d, skip atomic_check\n",
 				crtc->base.id, crtc_state->enable,
 				crtc_state->active);
+		memset(&cstate->new_perf, 0, sizeof(cstate->new_perf));
 		goto end;
 	}
 
@@ -1247,6 +1330,8 @@ static const struct drm_crtc_funcs dpu_crtc_funcs = {
 	.early_unregister = dpu_crtc_early_unregister,
 	.enable_vblank  = msm_crtc_enable_vblank,
 	.disable_vblank = msm_crtc_disable_vblank,
+	.get_vblank_timestamp = drm_crtc_vblank_helper_get_vblank_timestamp,
+	.get_vblank_counter = dpu_crtc_get_vblank_counter,
 };
 
 static const struct drm_crtc_helper_funcs dpu_crtc_helper_funcs = {
@@ -1255,6 +1340,7 @@ static const struct drm_crtc_helper_funcs dpu_crtc_helper_funcs = {
 	.atomic_check = dpu_crtc_atomic_check,
 	.atomic_begin = dpu_crtc_atomic_begin,
 	.atomic_flush = dpu_crtc_atomic_flush,
+	.get_scanout_position = dpu_crtc_get_scanout_position,
 };
 
 /* initialize crtc */

drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c

@@ -426,6 +426,36 @@ int dpu_encoder_helper_unregister_irq(struct dpu_encoder_phys *phys_enc,
 	return 0;
 }
 
+int dpu_encoder_get_frame_count(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_encoder_phys *phys;
+	int framecount = 0;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	phys = dpu_enc ? dpu_enc->cur_master : NULL;
+
+	if (phys && phys->ops.get_frame_count)
+		framecount = phys->ops.get_frame_count(phys);
+
+	return framecount;
+}
+
+int dpu_encoder_get_linecount(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_encoder_phys *phys;
+	int linecount = 0;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	phys = dpu_enc ? dpu_enc->cur_master : NULL;
+
+	if (phys && phys->ops.get_line_count)
+		linecount = phys->ops.get_line_count(phys);
+
+	return linecount;
+}
+
 void dpu_encoder_get_hw_resources(struct drm_encoder *drm_enc,
 				  struct dpu_encoder_hw_resources *hw_res)
 {

drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h

@@ -156,5 +156,16 @@ void dpu_encoder_prepare_commit(struct drm_encoder *drm_enc);
  */
 void dpu_encoder_set_idle_timeout(struct drm_encoder *drm_enc,
 							u32 idle_timeout);
+/**
+ * dpu_encoder_get_linecount - get interface line count for the encoder.
+ * @drm_enc:    Pointer to previously created drm encoder structure
+ */
+int dpu_encoder_get_linecount(struct drm_encoder *drm_enc);
+
+/**
+ * dpu_encoder_get_frame_count - get interface frame count for the encoder.
+ * @drm_enc:    Pointer to previously created drm encoder structure
+ */
+int dpu_encoder_get_frame_count(struct drm_encoder *drm_enc);
 
 #endif /* __DPU_ENCODER_H__ */