Merge tag 'drm-msm-next-2021-08-12' of https://gitlab.freedesktop.org/drm/msm into drm-next

This is the main pull for v5.15, after the early pull request with
drm/scheduler conversion:

* New a6xx GPU support: a680 and 7c3
* dsi: 7nm phi, sc7280 support, test pattern generator support
* mdp4 fixes for older hw like the nexus7
* displayport fixes

Signed-off-by: Dave Airlie <[email protected]>
From: Rob Clark <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/CAF6AEGs_tyanTeDGMH1X+Uf4wdyy7jYj-CinGXXVETiYOESahw@mail.gmail.com

Author: airlied

Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml

@@ -64,6 +64,18 @@ properties:
       Indicates if the DSI controller is driving a panel which needs
       2 DSI links.
 
+  assigned-clocks:
+    minItems: 2
+    maxItems: 2
+    description: |
+      Parents of "byte" and "pixel" for the given platform.
+
+  assigned-clock-parents:
+    minItems: 2
+    maxItems: 2
+    description: |
+      The Byte clock and Pixel clock PLL outputs provided by a DSI PHY block.
+
   power-domains:
     maxItems: 1
 
@@ -119,6 +131,8 @@ required:
   - clock-names
   - phys
   - phy-names
+  - assigned-clocks
+  - assigned-clock-parents
   - power-domains
   - operating-points-v2
   - ports
@@ -159,6 +173,9 @@ examples:
            phys = <&dsi0_phy>;
            phy-names = "dsi";
 
+           assigned-clocks = <&dispcc DISP_CC_MDSS_BYTE0_CLK_SRC>, <&dispcc DISP_CC_MDSS_PCLK0_CLK_SRC>;
+           assigned-clock-parents = <&dsi_phy 0>, <&dsi_phy 1>;
+
            power-domains = <&rpmhpd SC7180_CX>;
            operating-points-v2 = <&dsi_opp_table>;
 

Documentation/devicetree/bindings/display/msm/dsi-phy-7nm.yaml

@@ -0,0 +1,72 @@
+# SPDX-License-Identifier: GPL-2.0-only or BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/msm/dsi-phy-7nm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Display DSI 7nm PHY
+
+maintainers:
+  - Jonathan Marek <[email protected]>
+
+allOf:
+  - $ref: dsi-phy-common.yaml#
+
+properties:
+  compatible:
+    oneOf:
+      - const: qcom,dsi-phy-7nm
+      - const: qcom,dsi-phy-7nm-8150
+      - const: qcom,sc7280-dsi-phy-7nm
+
+  reg:
+    items:
+      - description: dsi phy register set
+      - description: dsi phy lane register set
+      - description: dsi pll register set
+
+  reg-names:
+    items:
+      - const: dsi_phy
+      - const: dsi_phy_lane
+      - const: dsi_pll
+
+  vdds-supply:
+    description: |
+      Connected to VDD_A_DSI_PLL_0P9 pin (or VDDA_DSI{0,1}_PLL_0P9 for sm8150)
+
+  phy-type:
+    description: D-PHY (default) or C-PHY mode
+    enum: [ 10, 11 ]
+    default: 10
+
+required:
+  - compatible
+  - reg
+  - reg-names
+  - vdds-supply
+
+unevaluatedProperties: false
+
+examples:
+  - |
+     #include <dt-bindings/clock/qcom,dispcc-sm8250.h>
+     #include <dt-bindings/clock/qcom,rpmh.h>
+
+     dsi-phy@ae94400 {
+         compatible = "qcom,dsi-phy-7nm";
+         reg = <0x0ae94400 0x200>,
+               <0x0ae94600 0x280>,
+               <0x0ae94900 0x260>;
+         reg-names = "dsi_phy",
+                     "dsi_phy_lane",
+                     "dsi_pll";
+
+         #clock-cells = <1>;
+         #phy-cells = <0>;
+
+         vdds-supply = <&vreg_l5a_0p88>;
+         clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
+                  <&rpmhcc RPMH_CXO_CLK>;
+         clock-names = "iface", "ref";
+     };

drivers/gpu/drm/msm/Kconfig

@@ -116,9 +116,9 @@ config DRM_MSM_DSI_10NM_PHY
 	  Choose this option if DSI PHY on SDM845 is used on the platform.
 
 config DRM_MSM_DSI_7NM_PHY
-	bool "Enable DSI 7nm PHY driver in MSM DRM (used by SM8150/SM8250)"
+	bool "Enable DSI 7nm PHY driver in MSM DRM"
 	depends on DRM_MSM_DSI
 	default y
 	help
-	  Choose this option if DSI PHY on SM8150/SM8250 is used on the
-	  platform.
+	  Choose this option if DSI PHY on SM8150/SM8250/SC7280 is used on
+	  the platform.

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

@@ -18,6 +18,18 @@ static void a5xx_dump(struct msm_gpu *gpu);
 
 #define GPU_PAS_ID 13
 
+static void update_shadow_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
+
+	if (a5xx_gpu->has_whereami) {
+		OUT_PKT7(ring, CP_WHERE_AM_I, 2);
+		OUT_RING(ring, lower_32_bits(shadowptr(a5xx_gpu, ring)));
+		OUT_RING(ring, upper_32_bits(shadowptr(a5xx_gpu, ring)));
+	}
+}
+
 void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 		bool sync)
 {
@@ -30,11 +42,8 @@ void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 	 * Most flush operations need to issue a WHERE_AM_I opcode to sync up
 	 * the rptr shadow
 	 */
-	if (a5xx_gpu->has_whereami && sync) {
-		OUT_PKT7(ring, CP_WHERE_AM_I, 2);
-		OUT_RING(ring, lower_32_bits(shadowptr(a5xx_gpu, ring)));
-		OUT_RING(ring, upper_32_bits(shadowptr(a5xx_gpu, ring)));
-	}
+	if (sync)
+		update_shadow_rptr(gpu, ring);
 
 	spin_lock_irqsave(&ring->preempt_lock, flags);
 
@@ -168,6 +177,16 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 			ibs++;
 			break;
 		}
+
+		/*
+		 * Periodically update shadow-wptr if needed, so that we
+		 * can see partial progress of submits with large # of
+		 * cmds.. otherwise we could needlessly stall waiting for
+		 * ringbuffer state, simply due to looking at a shadow
+		 * rptr value that has not been updated
+		 */
+		if ((ibs % 32) == 0)
+			update_shadow_rptr(gpu, ring);
 	}
 
 	/*

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

@@ -519,9 +519,9 @@ static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu)
 	if (!pdcptr)
 		goto err;
 
-	if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu))
+	if (adreno_is_a650(adreno_gpu) || adreno_is_a660_family(adreno_gpu))
 		pdc_in_aop = true;
-	else if (adreno_is_a618(adreno_gpu) || adreno_is_a640(adreno_gpu))
+	else if (adreno_is_a618(adreno_gpu) || adreno_is_a640_family(adreno_gpu))
 		pdc_address_offset = 0x30090;
 	else
 		pdc_address_offset = 0x30080;
@@ -933,6 +933,7 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 
 	/* Use a known rate to bring up the GMU */
 	clk_set_rate(gmu->core_clk, 200000000);
+	clk_set_rate(gmu->hub_clk, 150000000);
 	ret = clk_bulk_prepare_enable(gmu->nr_clocks, gmu->clocks);
 	if (ret) {
 		pm_runtime_put(gmu->gxpd);
@@ -1393,6 +1394,9 @@ static int a6xx_gmu_clocks_probe(struct a6xx_gmu *gmu)
 	gmu->core_clk = msm_clk_bulk_get_clock(gmu->clocks,
 		gmu->nr_clocks, "gmu");
 
+	gmu->hub_clk = msm_clk_bulk_get_clock(gmu->clocks,
+		gmu->nr_clocks, "hub");
+
 	return 0;
 }
 
@@ -1504,7 +1508,7 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 	 * are otherwise unused by a660.
 	 */
 	gmu->dummy.size = SZ_4K;
-	if (adreno_is_a660(adreno_gpu)) {
+	if (adreno_is_a660_family(adreno_gpu)) {
 		ret = a6xx_gmu_memory_alloc(gmu, &gmu->debug, SZ_4K * 7, 0x60400000);
 		if (ret)
 			goto err_memory;
@@ -1522,7 +1526,7 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 			SZ_16M - SZ_16K, 0x04000);
 		if (ret)
 			goto err_memory;
-	} else if (adreno_is_a640(adreno_gpu)) {
+	} else if (adreno_is_a640_family(adreno_gpu)) {
 		ret = a6xx_gmu_memory_alloc(gmu, &gmu->icache,
 			SZ_256K - SZ_16K, 0x04000);
 		if (ret)

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

@@ -66,6 +66,7 @@ struct a6xx_gmu {
 	int nr_clocks;
 	struct clk_bulk_data *clocks;
 	struct clk *core_clk;
+	struct clk *hub_clk;
 
 	/* current performance index set externally */
 	int current_perf_index;