drm/v3d: Associate a V3D tech revision to all supported devices

The V3D driver currently determines the GPU tech version (33, 41...)
by reading a register. This approach has worked so far since this
information wasn’t needed before powering on the GPU.

V3D 7.1 introduces new registers that must be written to power on the
GPU, requiring us to know the V3D version beforehand. To address this,
associate each supported SoC with the corresponding VideoCore GPU version
as part of the device data.

To prevent possible mistakes, add an assertion to verify that the version
specified in the device data matches the one reported by the hardware.
If there is a mismatch, the kernel will trigger a warning.

With the goal of maintaining consistency around the driver, use `enum
v3d_gen` to assign values to `v3d->ver` and for comparisons with other
V3D generations. Note that all mentions of unsupported or non-existing V3D
generations (such as V3D 4.0) were removed by this commit and replaced
with supported generations without functional changes.

Reviewed-by: Iago Toral Quiroga <[e-mail]>
Reviewed-by: Stefan Wahren <[e-mail]>
Signed-off-by: Maíra Canal <[e-mail]>
Link: https://patchwork.freedesktop.org/patch/msgid/[e-mail]

drivers/gpu/drm/v3d/v3d_debugfs.c

···
 };
 
 static const struct v3d_reg_def v3d_hub_reg_defs[] = {
-	REGDEF(33, 42, V3D_HUB_AXICFG),
-	REGDEF(33, 71, V3D_HUB_UIFCFG),
-	REGDEF(33, 71, V3D_HUB_IDENT0),
-	REGDEF(33, 71, V3D_HUB_IDENT1),
-	REGDEF(33, 71, V3D_HUB_IDENT2),
-	REGDEF(33, 71, V3D_HUB_IDENT3),
-	REGDEF(33, 71, V3D_HUB_INT_STS),
-	REGDEF(33, 71, V3D_HUB_INT_MSK_STS),
+	REGDEF(V3D_GEN_33, V3D_GEN_42, V3D_HUB_AXICFG),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_HUB_UIFCFG),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_HUB_IDENT0),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_HUB_IDENT1),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_HUB_IDENT2),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_HUB_IDENT3),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_HUB_INT_STS),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_HUB_INT_MSK_STS),
 
-	REGDEF(33, 71, V3D_MMU_CTL),
-	REGDEF(33, 71, V3D_MMU_VIO_ADDR),
-	REGDEF(33, 71, V3D_MMU_VIO_ID),
-	REGDEF(33, 71, V3D_MMU_DEBUG_INFO),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_MMU_CTL),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_MMU_VIO_ADDR),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_MMU_VIO_ID),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_MMU_DEBUG_INFO),
 
-	REGDEF(71, 71, V3D_GMP_STATUS(71)),
-	REGDEF(71, 71, V3D_GMP_CFG(71)),
-	REGDEF(71, 71, V3D_GMP_VIO_ADDR(71)),
+	REGDEF(V3D_GEN_71, V3D_GEN_71, V3D_GMP_STATUS(71)),
+	REGDEF(V3D_GEN_71, V3D_GEN_71, V3D_GMP_CFG(71)),
+	REGDEF(V3D_GEN_71, V3D_GEN_71, V3D_GMP_VIO_ADDR(71)),
 };
 
 static const struct v3d_reg_def v3d_gca_reg_defs[] = {
-	REGDEF(33, 33, V3D_GCA_SAFE_SHUTDOWN),
-	REGDEF(33, 33, V3D_GCA_SAFE_SHUTDOWN_ACK),
+	REGDEF(V3D_GEN_33, V3D_GEN_33, V3D_GCA_SAFE_SHUTDOWN),
+	REGDEF(V3D_GEN_33, V3D_GEN_33, V3D_GCA_SAFE_SHUTDOWN_ACK),
 };
 
 static const struct v3d_reg_def v3d_core_reg_defs[] = {
-	REGDEF(33, 71, V3D_CTL_IDENT0),
-	REGDEF(33, 71, V3D_CTL_IDENT1),
-	REGDEF(33, 71, V3D_CTL_IDENT2),
-	REGDEF(33, 71, V3D_CTL_MISCCFG),
-	REGDEF(33, 71, V3D_CTL_INT_STS),
-	REGDEF(33, 71, V3D_CTL_INT_MSK_STS),
-	REGDEF(33, 71, V3D_CLE_CT0CS),
-	REGDEF(33, 71, V3D_CLE_CT0CA),
-	REGDEF(33, 71, V3D_CLE_CT0EA),
-	REGDEF(33, 71, V3D_CLE_CT1CS),
-	REGDEF(33, 71, V3D_CLE_CT1CA),
-	REGDEF(33, 71, V3D_CLE_CT1EA),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_CTL_IDENT0),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_CTL_IDENT1),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_CTL_IDENT2),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_CTL_MISCCFG),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_CTL_INT_STS),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_CTL_INT_MSK_STS),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_CLE_CT0CS),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_CLE_CT0CA),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_CLE_CT0EA),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_CLE_CT1CS),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_CLE_CT1CA),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_CLE_CT1EA),
 
-	REGDEF(33, 71, V3D_PTB_BPCA),
-	REGDEF(33, 71, V3D_PTB_BPCS),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_PTB_BPCA),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_PTB_BPCS),
 
-	REGDEF(33, 42, V3D_GMP_STATUS(33)),
-	REGDEF(33, 42, V3D_GMP_CFG(33)),
-	REGDEF(33, 42, V3D_GMP_VIO_ADDR(33)),
+	REGDEF(V3D_GEN_33, V3D_GEN_42, V3D_GMP_STATUS(33)),
+	REGDEF(V3D_GEN_33, V3D_GEN_42, V3D_GMP_CFG(33)),
+	REGDEF(V3D_GEN_33, V3D_GEN_42, V3D_GMP_VIO_ADDR(33)),
 
-	REGDEF(33, 71, V3D_ERR_FDBGO),
-	REGDEF(33, 71, V3D_ERR_FDBGB),
-	REGDEF(33, 71, V3D_ERR_FDBGS),
-	REGDEF(33, 71, V3D_ERR_STAT),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_ERR_FDBGO),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_ERR_FDBGB),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_ERR_FDBGS),
+	REGDEF(V3D_GEN_33, V3D_GEN_71, V3D_ERR_STAT),
 };
 
 static const struct v3d_reg_def v3d_csd_reg_defs[] = {
-	REGDEF(41, 71, V3D_CSD_STATUS),
-	REGDEF(41, 42, V3D_CSD_CURRENT_CFG0(41)),
-	REGDEF(41, 42, V3D_CSD_CURRENT_CFG1(41)),
-	REGDEF(41, 42, V3D_CSD_CURRENT_CFG2(41)),
-	REGDEF(41, 42, V3D_CSD_CURRENT_CFG3(41)),
-	REGDEF(41, 42, V3D_CSD_CURRENT_CFG4(41)),
-	REGDEF(41, 42, V3D_CSD_CURRENT_CFG5(41)),
-	REGDEF(41, 42, V3D_CSD_CURRENT_CFG6(41)),
-	REGDEF(71, 71, V3D_CSD_CURRENT_CFG0(71)),
-	REGDEF(71, 71, V3D_CSD_CURRENT_CFG1(71)),
-	REGDEF(71, 71, V3D_CSD_CURRENT_CFG2(71)),
-	REGDEF(71, 71, V3D_CSD_CURRENT_CFG3(71)),
-	REGDEF(71, 71, V3D_CSD_CURRENT_CFG4(71)),
-	REGDEF(71, 71, V3D_CSD_CURRENT_CFG5(71)),
-	REGDEF(71, 71, V3D_CSD_CURRENT_CFG6(71)),
-	REGDEF(71, 71, V3D_V7_CSD_CURRENT_CFG7),
+	REGDEF(V3D_GEN_41, V3D_GEN_71, V3D_CSD_STATUS),
+	REGDEF(V3D_GEN_41, V3D_GEN_42, V3D_CSD_CURRENT_CFG0(41)),
+	REGDEF(V3D_GEN_41, V3D_GEN_42, V3D_CSD_CURRENT_CFG1(41)),
+	REGDEF(V3D_GEN_41, V3D_GEN_42, V3D_CSD_CURRENT_CFG2(41)),
+	REGDEF(V3D_GEN_41, V3D_GEN_42, V3D_CSD_CURRENT_CFG3(41)),
+	REGDEF(V3D_GEN_41, V3D_GEN_42, V3D_CSD_CURRENT_CFG4(41)),
+	REGDEF(V3D_GEN_41, V3D_GEN_42, V3D_CSD_CURRENT_CFG5(41)),
+	REGDEF(V3D_GEN_41, V3D_GEN_42, V3D_CSD_CURRENT_CFG6(41)),
+	REGDEF(V3D_GEN_71, V3D_GEN_71, V3D_CSD_CURRENT_CFG0(71)),
+	REGDEF(V3D_GEN_71, V3D_GEN_71, V3D_CSD_CURRENT_CFG1(71)),
+	REGDEF(V3D_GEN_71, V3D_GEN_71, V3D_CSD_CURRENT_CFG2(71)),
+	REGDEF(V3D_GEN_71, V3D_GEN_71, V3D_CSD_CURRENT_CFG3(71)),
+	REGDEF(V3D_GEN_71, V3D_GEN_71, V3D_CSD_CURRENT_CFG4(71)),
+	REGDEF(V3D_GEN_71, V3D_GEN_71, V3D_CSD_CURRENT_CFG5(71)),
+	REGDEF(V3D_GEN_71, V3D_GEN_71, V3D_CSD_CURRENT_CFG6(71)),
+	REGDEF(V3D_GEN_71, V3D_GEN_71, V3D_V7_CSD_CURRENT_CFG7),
 };
 
 static int v3d_v3d_debugfs_regs(struct seq_file *m, void *unused)
···
 		   str_yes_no(ident2 & V3D_HUB_IDENT2_WITH_MMU));
 	seq_printf(m, "TFU:        %s\n",
 		   str_yes_no(ident1 & V3D_HUB_IDENT1_WITH_TFU));
-	if (v3d->ver <= 42) {
+	if (v3d->ver <= V3D_GEN_42) {
 		seq_printf(m, "TSY:        %s\n",
 			   str_yes_no(ident1 & V3D_HUB_IDENT1_WITH_TSY));
 	}
···
 		seq_printf(m, "  QPUs:         %d\n", nslc * qups);
 		seq_printf(m, "  Semaphores:   %d\n",
 			   V3D_GET_FIELD(ident1, V3D_IDENT1_NSEM));
-		if (v3d->ver <= 42) {
+		if (v3d->ver <= V3D_GEN_42) {
 			seq_printf(m, "  BCG int:      %d\n",
 				   (ident2 & V3D_IDENT2_BCG_INT) != 0);
 		}
-		if (v3d->ver < 40) {
+		if (v3d->ver < V3D_GEN_41) {
 			seq_printf(m, "  Override TMU: %d\n",
 				   (misccfg & V3D_MISCCFG_OVRTMUOUT) != 0);
 		}
···
 	int core = 0;
 	int measure_ms = 1000;
 
-	if (v3d->ver >= 40) {
+	if (v3d->ver >= V3D_GEN_41) {
 		int cycle_count_reg = V3D_PCTR_CYCLE_COUNT(v3d->ver);
 		V3D_CORE_WRITE(core, V3D_V4_PCTR_0_SRC_0_3,
 			       V3D_SET_FIELD_VER(cycle_count_reg,

drivers/gpu/drm/v3d/v3d_drv.c

···
 #include <linux/dma-mapping.h>
 #include <linux/io.h>
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/sched/clock.h>
···
 		args->value = 1;
 		return 0;
 	case DRM_V3D_PARAM_SUPPORTS_PERFMON:
-		args->value = (v3d->ver >= 40);
+		args->value = (v3d->ver >= V3D_GEN_41);
 		return 0;
 	case DRM_V3D_PARAM_SUPPORTS_MULTISYNC_EXT:
 		args->value = 1;
···
 };
 
 static const struct of_device_id v3d_of_match[] = {
-	{ .compatible = "brcm,2711-v3d" },
-	{ .compatible = "brcm,2712-v3d" },
-	{ .compatible = "brcm,7268-v3d" },
-	{ .compatible = "brcm,7278-v3d" },
+	{ .compatible = "brcm,2711-v3d", .data = (void *)V3D_GEN_42 },
+	{ .compatible = "brcm,2712-v3d", .data = (void *)V3D_GEN_71 },
+	{ .compatible = "brcm,7268-v3d", .data = (void *)V3D_GEN_33 },
+	{ .compatible = "brcm,7278-v3d", .data = (void *)V3D_GEN_41 },
 	{},
 };
 MODULE_DEVICE_TABLE(of, v3d_of_match);
···
 	struct device *dev = &pdev->dev;
 	struct drm_device *drm;
 	struct v3d_dev *v3d;
+	enum v3d_gen gen;
 	int ret;
 	u32 mmu_debug;
 	u32 ident1, ident3;
···
 	drm = &v3d->drm;
 
 	platform_set_drvdata(pdev, drm);
+
+	gen = (uintptr_t)of_device_get_match_data(dev);
+	v3d->ver = gen;
 
 	ret = map_regs(v3d, &v3d->hub_regs, "hub");
 	if (ret)
···
 	ident1 = V3D_READ(V3D_HUB_IDENT1);
 	v3d->ver = (V3D_GET_FIELD(ident1, V3D_HUB_IDENT1_TVER) * 10 +
 		    V3D_GET_FIELD(ident1, V3D_HUB_IDENT1_REV));
+	/* Make sure that the V3D tech version retrieved from the HW is equal
+	 * to the one advertised by the device tree.
+	 */
+	WARN_ON(v3d->ver != gen);
+
 	v3d->cores = V3D_GET_FIELD(ident1, V3D_HUB_IDENT1_NCORES);
 	WARN_ON(v3d->cores > 1); /* multicore not yet implemented */
 
···
 		}
 	}
 
-	if (v3d->ver < 41) {
+	if (v3d->ver < V3D_GEN_41) {
 		ret = map_regs(v3d, &v3d->gca_regs, "gca");
 		if (ret)
 			goto clk_disable;

drivers/gpu/drm/v3d/v3d_drv.h

···
 	u64 values[] __counted_by(ncounters);
 };
 
+enum v3d_gen {
+	V3D_GEN_33 = 33,
+	V3D_GEN_41 = 41,
+	V3D_GEN_42 = 42,
+	V3D_GEN_71 = 71,
+};
+
 struct v3d_dev {
 	struct drm_device drm;
 
 	/* Short representation (e.g. 33, 41) of the V3D tech version */
-	int ver;
+	enum v3d_gen ver;
 
 	/* Short representation (e.g. 5, 6) of the V3D tech revision */
 	int rev;
···
 static inline bool
 v3d_has_csd(struct v3d_dev *v3d)
 {
-	return v3d->ver >= 41;
+	return v3d->ver >= V3D_GEN_41;
 }
 
 #define v3d_to_pdev(v3d) to_platform_device((v3d)->drm.dev)

drivers/gpu/drm/v3d/v3d_gem.c

···
 	 * type.  If you want the default behavior, you can still put
 	 * "2" in the indirect texture state's output_type field.
 	 */
-	if (v3d->ver < 40)
+	if (v3d->ver < V3D_GEN_41)
 		V3D_CORE_WRITE(core, V3D_CTL_MISCCFG, V3D_MISCCFG_OVRTMUOUT);
 
 	/* Whenever we flush the L2T cache, we always want to flush
···
 static void
 v3d_idle_gca(struct v3d_dev *v3d)
 {
-	if (v3d->ver >= 41)
+	if (v3d->ver >= V3D_GEN_41)
 		return;
 
 	V3D_GCA_WRITE(V3D_GCA_SAFE_SHUTDOWN, V3D_GCA_SAFE_SHUTDOWN_EN);
···
 static void
 v3d_flush_l3(struct v3d_dev *v3d)
 {
-	if (v3d->ver < 41) {
+	if (v3d->ver < V3D_GEN_41) {
 		u32 gca_ctrl = V3D_GCA_READ(V3D_GCA_CACHE_CTRL);
 
 		V3D_GCA_WRITE(V3D_GCA_CACHE_CTRL,
 			      gca_ctrl | V3D_GCA_CACHE_CTRL_FLUSH);
 
-		if (v3d->ver < 33) {
+		if (v3d->ver < V3D_GEN_33) {
 			V3D_GCA_WRITE(V3D_GCA_CACHE_CTRL,
 				      gca_ctrl & ~V3D_GCA_CACHE_CTRL_FLUSH);
 		}
···
 static void
 v3d_invalidate_l2c(struct v3d_dev *v3d, int core)
 {
-	if (v3d->ver > 32)
+	if (v3d->ver >= V3D_GEN_33)
 		return;
 
 	V3D_CORE_WRITE(core, V3D_CTL_L2CACTL,

drivers/gpu/drm/v3d/v3d_irq.c

···
 	/* We shouldn't be triggering these if we have GMP in
 	 * always-allowed mode.
 	 */
-	if (v3d->ver < 71 && (intsts & V3D_INT_GMPV))
+	if (v3d->ver < V3D_GEN_71 && (intsts & V3D_INT_GMPV))
 		dev_err(v3d->drm.dev, "GMP violation\n");
 
 	/* V3D 4.2 wires the hub and core IRQs together, so if we &
···
 
 		V3D_WRITE(V3D_MMU_CTL, V3D_READ(V3D_MMU_CTL));
 
-		if (v3d->ver >= 41) {
+		if (v3d->ver >= V3D_GEN_41) {
 			axi_id = axi_id >> 5;
 			if (axi_id < ARRAY_SIZE(v3d41_axi_ids))
 				client = v3d41_axi_ids[axi_id];
···
 		status = IRQ_HANDLED;
 	}
 
-	if (v3d->ver >= 71 && (intsts & V3D_V7_HUB_INT_GMPV)) {
+	if (v3d->ver >= V3D_GEN_71 && (intsts & V3D_V7_HUB_INT_GMPV)) {
 		dev_err(v3d->drm.dev, "GMP Violation\n");
 		status = IRQ_HANDLED;
 	}

drivers/gpu/drm/v3d/v3d_perfmon.c

···
 	const struct v3d_perf_counter_desc *counters = NULL;
 	unsigned int max = 0;
 
-	if (v3d->ver >= 71) {
+	if (v3d->ver >= V3D_GEN_71) {
 		counters = v3d_v71_performance_counters;
 		max = ARRAY_SIZE(v3d_v71_performance_counters);
-	} else if (v3d->ver >= 42) {
+	} else if (v3d->ver >= V3D_GEN_42) {
 		counters = v3d_v42_performance_counters;
 		max = ARRAY_SIZE(v3d_v42_performance_counters);
 	}

drivers/gpu/drm/v3d/v3d_sched.c

···
 	V3D_WRITE(V3D_TFU_ICA(v3d->ver), job->args.ica);
 	V3D_WRITE(V3D_TFU_IUA(v3d->ver), job->args.iua);
 	V3D_WRITE(V3D_TFU_IOA(v3d->ver), job->args.ioa);
-	if (v3d->ver >= 71)
+	if (v3d->ver >= V3D_GEN_71)
 		V3D_WRITE(V3D_V7_TFU_IOC, job->args.v71.ioc);
 	V3D_WRITE(V3D_TFU_IOS(v3d->ver), job->args.ios);
 	V3D_WRITE(V3D_TFU_COEF0(v3d->ver), job->args.coef[0]);
-	if (v3d->ver >= 71 || (job->args.coef[0] & V3D_TFU_COEF0_USECOEF)) {
+	if (v3d->ver >= V3D_GEN_71 || (job->args.coef[0] & V3D_TFU_COEF0_USECOEF)) {
 		V3D_WRITE(V3D_TFU_COEF1(v3d->ver), job->args.coef[1]);
 		V3D_WRITE(V3D_TFU_COEF2(v3d->ver), job->args.coef[2]);
 		V3D_WRITE(V3D_TFU_COEF3(v3d->ver), job->args.coef[3]);
···
 	 *
 	 * XXX: Set the CFG7 register
 	 */
-	if (v3d->ver >= 71)
+	if (v3d->ver >= V3D_GEN_71)
 		V3D_CORE_WRITE(0, V3D_V7_CSD_QUEUED_CFG7, 0);
 
 	/* CFG0 write kicks off the job. */