Merge tag 'drm-msm-next-2020-01-14' of https://gitlab.freedesktop.org/drm/msm into drm-next

+ sc7180 display + DSI support
+ a618 (sc7180) support
+ more UBWC (bandwidth compression) support
+ various cleanups to handle devices that use vs don't
  use zap fw, etc
+ usual random cleanups and fixes

Signed-off-by: Dave Airlie <[email protected]>
From: Rob Clark <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/ <CAF6AEGvv03ifuP0tp7-dmqZtr1iS=s8Vc=az8BNGtEoSMD-dkw@mail.gmail.com

Author: airlied

Documentation/devicetree/bindings/display/msm/dpu.txt

@@ -8,7 +8,7 @@ The DPU display controller is found in SDM845 SoC.
 
 MDSS:
 Required properties:
-- compatible: "qcom,sdm845-mdss"
+- compatible:  "qcom,sdm845-mdss", "qcom,sc7180-mdss"
 - reg: physical base address and length of contoller's registers.
 - reg-names: register region names. The following region is required:
   * "mdss"
@@ -41,7 +41,7 @@ Optional properties:
 
 MDP:
 Required properties:
-- compatible: "qcom,sdm845-dpu"
+- compatible: "qcom,sdm845-dpu", "qcom,sc7180-dpu"
 - reg: physical base address and length of controller's registers.
 - reg-names : register region names. The following region is required:
   * "mdp"

Documentation/devicetree/bindings/display/msm/gpu.txt

@@ -23,13 +23,18 @@ Required properties:
 - iommus: optional phandle to an adreno iommu instance
 - operating-points-v2: optional phandle to the OPP operating points
 - interconnects: optional phandle to an interconnect provider.  See
-  ../interconnect/interconnect.txt for details.
+  ../interconnect/interconnect.txt for details. Some A3xx and all A4xx platforms
+  will have two paths; all others will have one path.
+- interconnect-names: The names of the interconnect paths that correspond to the
+  interconnects property. Values must be gfx-mem and ocmem.
 - qcom,gmu: For GMU attached devices a phandle to the GMU device that will
   control the power for the GPU. Applicable targets:
     - qcom,adreno-630.2
 - zap-shader: For a5xx and a6xx devices this node contains a memory-region that
   points to reserved memory to store the zap shader that can be used to help
   bring the GPU out of secure mode.
+- firmware-name: optional property of the 'zap-shader' node, listing the
+  relative path of the device specific zap firmware.
 
 Example 3xx/4xx/a5xx:
 
@@ -76,11 +81,13 @@ Example a6xx (with GMU):
 		operating-points-v2 = <&gpu_opp_table>;
 
 		interconnects = <&rsc_hlos MASTER_GFX3D &rsc_hlos SLAVE_EBI1>;
+		interconnect-names = "gfx-mem";
 
 		qcom,gmu = <&gmu>;
 
 		zap-shader {
 			memory-region = <&zap_shader_region>;
+			firmware-name = "qcom/LENOVO/81JL/qcdxkmsuc850.mbn"
 		};
 	};
 };

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

@@ -506,6 +506,14 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
 		goto fail;
 	}
 
+	/*
+	 * Set the ICC path to maximum speed for now by multiplying the fastest
+	 * frequency by the bus width (8). We'll want to scale this later on to
+	 * improve battery life.
+	 */
+	icc_set_bw(gpu->icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8);
+	icc_set_bw(gpu->ocmem_icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8);
+
 	return gpu;
 
 fail:

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

@@ -591,6 +591,14 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev)
 		goto fail;
 	}
 
+	/*
+	 * Set the ICC path to maximum speed for now by multiplying the fastest
+	 * frequency by the bus width (8). We'll want to scale this later on to
+	 * improve battery life.
+	 */
+	icc_set_bw(gpu->icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8);
+	icc_set_bw(gpu->ocmem_icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8);
+
 	return gpu;
 
 fail:

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

@@ -753,11 +753,18 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 		gpu->funcs->flush(gpu, gpu->rb[0]);
 		if (!a5xx_idle(gpu, gpu->rb[0]))
 			return -EINVAL;
-	} else {
-		/* Print a warning so if we die, we know why */
+	} else if (ret == -ENODEV) {
+		/*
+		 * This device does not use zap shader (but print a warning
+		 * just in case someone got their dt wrong.. hopefully they
+		 * have a debug UART to realize the error of their ways...
+		 * if you mess this up you are about to crash horribly)
+		 */
 		dev_warn_once(gpu->dev->dev,
 			"Zap shader not enabled - using SECVID_TRUST_CNTL instead\n");
 		gpu_write(gpu, REG_A5XX_RBBM_SECVID_TRUST_CNTL, 0x0);
+	} else {
+		return ret;
 	}
 
 	/* Last step - yield the ringbuffer */

drivers/gpu/drm/msm/adreno/a6xx.xml.h

@@ -16,11 +16,11 @@ The rules-ng-ng source files this header was generated from are:
 - /home/robclark/src/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2018-07-03 19:37:13)
 - /home/robclark/src/envytools/rnndb/adreno/a4xx.xml          ( 112086 bytes, from 2018-07-03 19:37:13)
 - /home/robclark/src/envytools/rnndb/adreno/a5xx.xml          ( 147240 bytes, from 2018-12-02 17:29:54)
-- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml          ( 140790 bytes, from 2018-12-02 17:29:54)
+- /home/smasetty/playarea/envytools/rnndb/adreno/a6xx.xml     ( 161969 bytes, from 2019-11-29 07:18:16)
 - /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml      (  10431 bytes, from 2018-09-14 13:03:07)
 - /home/robclark/src/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2018-07-03 19:37:13)
 
-Copyright (C) 2013-2018 by the following authors:
+Copyright (C) 2013-2019 by the following authors:
 - Rob Clark <[email protected]> (robclark)
 - Ilia Mirkin <[email protected]> (imirkin)
 
@@ -2519,6 +2519,54 @@ static inline uint32_t A6XX_VBIF_TEST_BUS2_CTRL1_DATA_SEL(uint32_t val)
 
 #define REG_A6XX_VBIF_PERF_PWR_CNT_HIGH2			0x0000311a
 
+#define REG_A6XX_GBIF_SCACHE_CNTL1				0x00003c02
+
+#define REG_A6XX_GBIF_QSB_SIDE0					0x00003c03
+
+#define REG_A6XX_GBIF_QSB_SIDE1					0x00003c04
+
+#define REG_A6XX_GBIF_QSB_SIDE2					0x00003c05
+
+#define REG_A6XX_GBIF_QSB_SIDE3					0x00003c06
+
+#define REG_A6XX_GBIF_HALT					0x00003c45
+
+#define REG_A6XX_GBIF_HALT_ACK					0x00003c46
+
+#define REG_A6XX_GBIF_PERF_PWR_CNT_EN				0x00003cc0
+
+#define REG_A6XX_GBIF_PERF_CNT_SEL				0x00003cc2
+
+#define REG_A6XX_GBIF_PERF_PWR_CNT_SEL				0x00003cc3
+
+#define REG_A6XX_GBIF_PERF_CNT_LOW0				0x00003cc4
+
+#define REG_A6XX_GBIF_PERF_CNT_LOW1				0x00003cc5
+
+#define REG_A6XX_GBIF_PERF_CNT_LOW2				0x00003cc6
+
+#define REG_A6XX_GBIF_PERF_CNT_LOW3				0x00003cc7
+
+#define REG_A6XX_GBIF_PERF_CNT_HIGH0				0x00003cc8
+
+#define REG_A6XX_GBIF_PERF_CNT_HIGH1				0x00003cc9
+
+#define REG_A6XX_GBIF_PERF_CNT_HIGH2				0x00003cca
+
+#define REG_A6XX_GBIF_PERF_CNT_HIGH3				0x00003ccb
+
+#define REG_A6XX_GBIF_PWR_CNT_LOW0				0x00003ccc
+
+#define REG_A6XX_GBIF_PWR_CNT_LOW1				0x00003ccd
+
+#define REG_A6XX_GBIF_PWR_CNT_LOW2				0x00003cce
+
+#define REG_A6XX_GBIF_PWR_CNT_HIGH0				0x00003ccf
+
+#define REG_A6XX_GBIF_PWR_CNT_HIGH1				0x00003cd0
+
+#define REG_A6XX_GBIF_PWR_CNT_HIGH2				0x00003cd1
+
 #define REG_A6XX_RB_WINDOW_OFFSET2				0x000088d4
 #define A6XX_RB_WINDOW_OFFSET2_WINDOW_OFFSET_DISABLE		0x80000000
 #define A6XX_RB_WINDOW_OFFSET2_X__MASK				0x00007fff

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

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2017-2018 The Linux Foundation. All rights reserved. */
+/* Copyright (c) 2017-2019 The Linux Foundation. All rights reserved. */
 
 #include <linux/clk.h>
 #include <linux/interconnect.h>
@@ -149,6 +149,8 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, unsigned long freq)
 		if (freq == gmu->gpu_freqs[perf_index])
 			break;
 
+	gmu->current_perf_index = perf_index;
+
 	__a6xx_gmu_set_freq(gmu, perf_index);
 }
 
@@ -433,6 +435,8 @@ static void __iomem *a6xx_gmu_get_mmio(struct platform_device *pdev,
 
 static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu)
 {
+	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
+	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	struct platform_device *pdev = to_platform_device(gmu->dev);
 	void __iomem *pdcptr = a6xx_gmu_get_mmio(pdev, "gmu_pdc");
 	void __iomem *seqptr = a6xx_gmu_get_mmio(pdev, "gmu_pdc_seq");
@@ -480,20 +484,34 @@ static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu)
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_MSGID + 4, 0x10108);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_ADDR + 4, 0x30000);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_DATA + 4, 0x0);
+
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_MSGID + 8, 0x10108);
-	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_ADDR + 8, 0x30080);
+	if (adreno_is_a618(adreno_gpu))
+		pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_ADDR + 8, 0x30090);
+	else
+		pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_ADDR + 8, 0x30080);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_DATA + 8, 0x0);
+
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD_ENABLE_BANK, 7);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD_WAIT_FOR_CMPL_BANK, 0);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CONTROL, 0);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_MSGID, 0x10108);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR, 0x30010);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA, 2);
+
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_MSGID + 4, 0x10108);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR + 4, 0x30000);
-	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA + 4, 0x3);
+	if (adreno_is_a618(adreno_gpu))
+		pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA + 4, 0x2);
+	else
+		pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA + 4, 0x3);
+
+
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_MSGID + 8, 0x10108);
-	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR + 8, 0x30080);
+	if (adreno_is_a618(adreno_gpu))
+		pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR + 8, 0x30090);
+	else
+		pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR + 8, 0x30080);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA + 8, 0x3);
 
 	/* Setup GPU PDC */
@@ -741,8 +759,8 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 	gmu_write(gmu, REG_A6XX_GMU_GMU2HOST_INTR_MASK, ~A6XX_HFI_IRQ_MASK);
 	enable_irq(gmu->hfi_irq);
 
-	/* Set the GPU to the highest power frequency */
-	__a6xx_gmu_set_freq(gmu, gmu->nr_gpu_freqs - 1);
+	/* Set the GPU to the current freq */
+	__a6xx_gmu_set_freq(gmu, gmu->current_perf_index);
 
 	/*
 	 * "enable" the GX power domain which won't actually do anything but it
@@ -1166,6 +1184,8 @@ static int a6xx_gmu_pwrlevels_probe(struct a6xx_gmu *gmu)
 	gmu->nr_gpu_freqs = a6xx_gmu_build_freq_table(&gpu->pdev->dev,
 		gmu->gpu_freqs, ARRAY_SIZE(gmu->gpu_freqs));
 
+	gmu->current_perf_index = gmu->nr_gpu_freqs - 1;
+
 	/* Build the list of RPMh votes that we'll send to the GMU */
 	return a6xx_gmu_rpmh_votes_init(gmu);
 }

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

@@ -63,6 +63,9 @@ struct a6xx_gmu {
 	struct clk_bulk_data *clocks;
 	struct clk *core_clk;
 
+	/* current performance index set externally */
+	int current_perf_index;
+
 	int nr_gpu_freqs;
 	unsigned long gpu_freqs[16];
 	u32 gx_arc_votes[16];

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

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2017-2018 The Linux Foundation. All rights reserved. */
+/* Copyright (c) 2017-2019 The Linux Foundation. All rights reserved. */
 
 
 #include "msm_gem.h"
@@ -378,6 +378,18 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 	int ret;
 
+	/*
+	 * During a previous slumber, GBIF halt is asserted to ensure
+	 * no further transaction can go through GPU before GPU
+	 * headswitch is turned off.
+	 *
+	 * This halt is deasserted once headswitch goes off but
+	 * incase headswitch doesn't goes off clear GBIF halt
+	 * here to ensure GPU wake-up doesn't fail because of
+	 * halted GPU transactions.
+	 */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0);
+
 	/* Make sure the GMU keeps the GPU on while we set it up */
 	a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET);
 
@@ -406,12 +418,17 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	gpu_write(gpu, REG_A6XX_TPL1_ADDR_MODE_CNTL, 0x1);
 	gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_ADDR_MODE_CNTL, 0x1);
 
-	/* enable hardware clockgating */
-	a6xx_set_hwcg(gpu, true);
+	/*
+	 * enable hardware clockgating
+	 * For now enable clock gating only for a630
+	 */
+	if (adreno_is_a630(adreno_gpu))
+		a6xx_set_hwcg(gpu, true);
 
-	/* VBIF start */
-	gpu_write(gpu, REG_A6XX_VBIF_GATE_OFF_WRREQ_EN, 0x00000009);
+	/* VBIF/GBIF start*/
 	gpu_write(gpu, REG_A6XX_RBBM_VBIF_CLIENT_QOS_CNTL, 0x3);
+	if (adreno_is_a630(adreno_gpu))
+		gpu_write(gpu, REG_A6XX_VBIF_GATE_OFF_WRREQ_EN, 0x00000009);
 
 	/* Make all blocks contribute to the GPU BUSY perf counter */
 	gpu_write(gpu, REG_A6XX_RBBM_PERFCTR_GPU_BUSY_MASKED, 0xffffffff);
@@ -537,12 +554,19 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 		a6xx_flush(gpu, gpu->rb[0]);
 		if (!a6xx_idle(gpu, gpu->rb[0]))
 			return -EINVAL;
-	} else {
-		/* Print a warning so if we die, we know why */
+	} else if (ret == -ENODEV) {
+		/*
+		 * This device does not use zap shader (but print a warning
+		 * just in case someone got their dt wrong.. hopefully they
+		 * have a debug UART to realize the error of their ways...
+		 * if you mess this up you are about to crash horribly)
+		 */
 		dev_warn_once(gpu->dev->dev,
 			"Zap shader not enabled - using SECVID_TRUST_CNTL instead\n");
 		gpu_write(gpu, REG_A6XX_RBBM_SECVID_TRUST_CNTL, 0x0);
 		ret = 0;
+	} else {
+		return ret;
 	}
 
 out:
@@ -724,6 +748,39 @@ static const u32 a6xx_register_offsets[REG_ADRENO_REGISTER_MAX] = {
 	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_CNTL, REG_A6XX_CP_RB_CNTL),
 };
 
+#define GBIF_CLIENT_HALT_MASK             BIT(0)
+#define GBIF_ARB_HALT_MASK                BIT(1)
+
+static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu)
+{
+	struct msm_gpu *gpu = &adreno_gpu->base;
+
+	if(!a6xx_has_gbif(adreno_gpu)){
+		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf);
+		spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) &
+								0xf) == 0xf);
+		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0);
+
+		return;
+	}
+
+	/* Halt new client requests on GBIF */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK);
+	spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) &
+			(GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK);
+
+	/* Halt all AXI requests on GBIF */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK);
+	spin_until((gpu_read(gpu,  REG_A6XX_GBIF_HALT_ACK) &
+			(GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK);
+
+	/*
+	 * GMU needs DDR access in slumber path. Deassert GBIF halt now
+	 * to allow for GMU to access system memory.
+	 */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0);
+}
+
 static int a6xx_pm_resume(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -748,6 +805,16 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu)
 
 	devfreq_suspend_device(gpu->devfreq.devfreq);
 
+	/*
+	 * Make sure the GMU is idle before continuing (because some transitions
+	 * may use VBIF
+	 */
+	a6xx_gmu_wait_for_idle(&a6xx_gpu->gmu);
+
+	/* Clear the VBIF pipe before shutting down */
+	/* FIXME: This accesses the GPU - do we need to make sure it is on? */
+	a6xx_bus_clear_pending_transactions(adreno_gpu);
+
 	return a6xx_gmu_stop(a6xx_gpu);
 }