drm/v3d: fix up register addresses for V3D 7.x

This patch updates a number of register addresses that have
been changed in Raspberry Pi 5 (V3D 7.1) and updates the
code to use the corresponding registers and addresses based
on the actual V3D version.
Signed-off-by: Iago Toral Quiroga <itoral@igalia.com>
Reviewed-by: Maíra Canal <mcanal@igalia.com>
Signed-off-by: Maíra Canal <mcanal@igalia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231031073859.25298-3-itoral@igalia.com

drivers/gpu/drm/v3d/v3d_debugfs.c

@@ -12,69 +12,83 @@
 #include "v3d_drv.h"
 #include "v3d_regs.h"
 
-#define REGDEF(reg) { reg, #reg }
+#define REGDEF(min_ver, max_ver, reg) { min_ver, max_ver, reg, #reg }
 struct v3d_reg_def {
+	u32 min_ver;
+	u32 max_ver;
 	u32 reg;
 	const char *name;
 };
 
 static const struct v3d_reg_def v3d_hub_reg_defs[] = {
-	REGDEF(V3D_HUB_AXICFG),
-	REGDEF(V3D_HUB_UIFCFG),
-	REGDEF(V3D_HUB_IDENT0),
-	REGDEF(V3D_HUB_IDENT1),
-	REGDEF(V3D_HUB_IDENT2),
-	REGDEF(V3D_HUB_IDENT3),
-	REGDEF(V3D_HUB_INT_STS),
-	REGDEF(V3D_HUB_INT_MSK_STS),
-
-	REGDEF(V3D_MMU_CTL),
-	REGDEF(V3D_MMU_VIO_ADDR),
-	REGDEF(V3D_MMU_VIO_ID),
-	REGDEF(V3D_MMU_DEBUG_INFO),
+	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(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(71, 71, V3D_GMP_STATUS(71)),
+	REGDEF(71, 71, V3D_GMP_CFG(71)),
+	REGDEF(71, 71, V3D_GMP_VIO_ADDR(71)),
 };
 
 static const struct v3d_reg_def v3d_gca_reg_defs[] = {
-	REGDEF(V3D_GCA_SAFE_SHUTDOWN),
-	REGDEF(V3D_GCA_SAFE_SHUTDOWN_ACK),
+	REGDEF(33, 33, V3D_GCA_SAFE_SHUTDOWN),
+	REGDEF(33, 33, V3D_GCA_SAFE_SHUTDOWN_ACK),
 };
 
 static const struct v3d_reg_def v3d_core_reg_defs[] = {
-	REGDEF(V3D_CTL_IDENT0),
-	REGDEF(V3D_CTL_IDENT1),
-	REGDEF(V3D_CTL_IDENT2),
-	REGDEF(V3D_CTL_MISCCFG),
-	REGDEF(V3D_CTL_INT_STS),
-	REGDEF(V3D_CTL_INT_MSK_STS),
-	REGDEF(V3D_CLE_CT0CS),
-	REGDEF(V3D_CLE_CT0CA),
-	REGDEF(V3D_CLE_CT0EA),
-	REGDEF(V3D_CLE_CT1CS),
-	REGDEF(V3D_CLE_CT1CA),
-	REGDEF(V3D_CLE_CT1EA),
-
-	REGDEF(V3D_PTB_BPCA),
-	REGDEF(V3D_PTB_BPCS),
-
-	REGDEF(V3D_GMP_STATUS),
-	REGDEF(V3D_GMP_CFG),
-	REGDEF(V3D_GMP_VIO_ADDR),
-
-	REGDEF(V3D_ERR_FDBGO),
-	REGDEF(V3D_ERR_FDBGB),
-	REGDEF(V3D_ERR_FDBGS),
-	REGDEF(V3D_ERR_STAT),
+	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(33, 71, V3D_PTB_BPCA),
+	REGDEF(33, 71, V3D_PTB_BPCS),
+
+	REGDEF(33, 41, V3D_GMP_STATUS(33)),
+	REGDEF(33, 41, V3D_GMP_CFG(33)),
+	REGDEF(33, 41, 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),
 };
 
 static const struct v3d_reg_def v3d_csd_reg_defs[] = {
-	REGDEF(V3D_CSD_STATUS),
-	REGDEF(V3D_CSD_CURRENT_CFG0),
-	REGDEF(V3D_CSD_CURRENT_CFG1),
-	REGDEF(V3D_CSD_CURRENT_CFG2),
-	REGDEF(V3D_CSD_CURRENT_CFG3),
-	REGDEF(V3D_CSD_CURRENT_CFG4),
-	REGDEF(V3D_CSD_CURRENT_CFG5),
-	REGDEF(V3D_CSD_CURRENT_CFG6),
+	REGDEF(41, 71, V3D_CSD_STATUS),
+	REGDEF(41, 41, V3D_CSD_CURRENT_CFG0(41)),
+	REGDEF(41, 41, V3D_CSD_CURRENT_CFG1(41)),
+	REGDEF(41, 41, V3D_CSD_CURRENT_CFG2(41)),
+	REGDEF(41, 41, V3D_CSD_CURRENT_CFG3(41)),
+	REGDEF(41, 41, V3D_CSD_CURRENT_CFG4(41)),
+	REGDEF(41, 41, V3D_CSD_CURRENT_CFG5(41)),
+	REGDEF(41, 41, 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),
 };
 
 static int v3d_v3d_debugfs_regs(struct seq_file *m, void *unused)
@@ -85,38 +99,41 @@ static int v3d_v3d_debugfs_regs(struct seq_file *m, void *unused)
 	int i, core;
 
 	for (i = 0; i < ARRAY_SIZE(v3d_hub_reg_defs); i++) {
+		const struct v3d_reg_def *def = &v3d_hub_reg_defs[i];
+
+		if (v3d->ver >= def->min_ver && v3d->ver <= def->max_ver) {
 			seq_printf(m, "%s (0x%04x): 0x%08x\n",
-			   v3d_hub_reg_defs[i].name, v3d_hub_reg_defs[i].reg,
-			   V3D_READ(v3d_hub_reg_defs[i].reg));
+				   def->name, def->reg, V3D_READ(def->reg));
+		}
 	}
 
-	if (v3d->ver < 41) {
 	for (i = 0; i < ARRAY_SIZE(v3d_gca_reg_defs); i++) {
+		const struct v3d_reg_def *def = &v3d_gca_reg_defs[i];
+
+		if (v3d->ver >= def->min_ver && v3d->ver <= def->max_ver) {
 			seq_printf(m, "%s (0x%04x): 0x%08x\n",
-				   v3d_gca_reg_defs[i].name,
-				   v3d_gca_reg_defs[i].reg,
-				   V3D_GCA_READ(v3d_gca_reg_defs[i].reg));
+				   def->name, def->reg, V3D_GCA_READ(def->reg));
 		}
 	}
 
 	for (core = 0; core < v3d->cores; core++) {
 		for (i = 0; i < ARRAY_SIZE(v3d_core_reg_defs); i++) {
+			const struct v3d_reg_def *def = &v3d_core_reg_defs[i];
+
+			if (v3d->ver >= def->min_ver && v3d->ver <= def->max_ver) {
 				seq_printf(m, "core %d %s (0x%04x): 0x%08x\n",
-				   core,
-				   v3d_core_reg_defs[i].name,
-				   v3d_core_reg_defs[i].reg,
-				   V3D_CORE_READ(core,
-						 v3d_core_reg_defs[i].reg));
+					   core, def->name, def->reg,
+					   V3D_CORE_READ(core, def->reg));
+			}
 		}
 
-		if (v3d_has_csd(v3d)) {
 		for (i = 0; i < ARRAY_SIZE(v3d_csd_reg_defs); i++) {
+			const struct v3d_reg_def *def = &v3d_csd_reg_defs[i];
+
+			if (v3d->ver >= def->min_ver && v3d->ver <= def->max_ver) {
 				seq_printf(m, "core %d %s (0x%04x): 0x%08x\n",
-					   core,
-					   v3d_csd_reg_defs[i].name,
-					   v3d_csd_reg_defs[i].reg,
-					   V3D_CORE_READ(core,
-							 v3d_csd_reg_defs[i].reg));
+					   core, def->name, def->reg,
+					   V3D_CORE_READ(core, def->reg));
 			}
 		}
 	}
@@ -147,8 +164,10 @@ static int v3d_v3d_debugfs_ident(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) {
 		seq_printf(m, "TSY:        %s\n",
 			   str_yes_no(ident1 & V3D_HUB_IDENT1_WITH_TSY));
+	}
 	seq_printf(m, "MSO:        %s\n",
 		   str_yes_no(ident1 & V3D_HUB_IDENT1_WITH_MSO));
 	seq_printf(m, "L3C:        %s (%dkb)\n",
@@ -177,11 +196,15 @@ static int v3d_v3d_debugfs_ident(struct seq_file *m, void *unused)
 		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) {
 			seq_printf(m, "  BCG int:      %d\n",
 				   (ident2 & V3D_IDENT2_BCG_INT) != 0);
+		}
+		if (v3d->ver < 40) {
 			seq_printf(m, "  Override TMU: %d\n",
 				   (misccfg & V3D_MISCCFG_OVRTMUOUT) != 0);
 		}
+	}
 
 	return 0;
 }
@@ -212,14 +235,15 @@ static int v3d_measure_clock(struct seq_file *m, void *unused)
 	int measure_ms = 1000;
 
 	if (v3d->ver >= 40) {
+		int cycle_count_reg = V3D_PCTR_CYCLE_COUNT(v3d->ver);
 		V3D_CORE_WRITE(core, V3D_V4_PCTR_0_SRC_0_3,
-			       V3D_SET_FIELD(V3D_PCTR_CYCLE_COUNT,
+			       V3D_SET_FIELD(cycle_count_reg,
 					     V3D_PCTR_S0));
 		V3D_CORE_WRITE(core, V3D_V4_PCTR_0_CLR, 1);
 		V3D_CORE_WRITE(core, V3D_V4_PCTR_0_EN, 1);
 	} else {
 		V3D_CORE_WRITE(core, V3D_V3_PCTR_0_PCTRS0,
-			       V3D_PCTR_CYCLE_COUNT);
+			       V3D_PCTR_CYCLE_COUNT(v3d->ver));
 		V3D_CORE_WRITE(core, V3D_V3_PCTR_0_CLR, 1);
 		V3D_CORE_WRITE(core, V3D_V3_PCTR_0_EN,
 			       V3D_V3_PCTR_0_EN_ENABLE |

drivers/gpu/drm/v3d/v3d_gem.c

@@ -47,9 +47,9 @@ v3d_init_hw_state(struct v3d_dev *v3d)
 static void
 v3d_idle_axi(struct v3d_dev *v3d, int core)
 {
-	V3D_CORE_WRITE(core, V3D_GMP_CFG, V3D_GMP_CFG_STOP_REQ);
+	V3D_CORE_WRITE(core, V3D_GMP_CFG(v3d->ver), V3D_GMP_CFG_STOP_REQ);
 
-	if (wait_for((V3D_CORE_READ(core, V3D_GMP_STATUS) &
+	if (wait_for((V3D_CORE_READ(core, V3D_GMP_STATUS(v3d->ver)) &
 		      (V3D_GMP_STATUS_RD_COUNT_MASK |
 		       V3D_GMP_STATUS_WR_COUNT_MASK |
 		       V3D_GMP_STATUS_CFG_BUSY)) == 0, 100)) {

drivers/gpu/drm/v3d/v3d_irq.c

@@ -19,16 +19,17 @@
 #include "v3d_regs.h"
 #include "v3d_trace.h"
 
-#define V3D_CORE_IRQS ((u32)(V3D_INT_OUTOMEM |	\
+#define V3D_CORE_IRQS(ver) ((u32)(V3D_INT_OUTOMEM |	\
 				  V3D_INT_FLDONE |	\
 				  V3D_INT_FRDONE |	\
-			     V3D_INT_CSDDONE |	\
-			     V3D_INT_GMPV))
+				  V3D_INT_CSDDONE(ver) |	\
+				  (ver < 71 ? V3D_INT_GMPV : 0)))
 
-#define V3D_HUB_IRQS ((u32)(V3D_HUB_INT_MMU_WRV |	\
+#define V3D_HUB_IRQS(ver) ((u32)(V3D_HUB_INT_MMU_WRV |	\
 				 V3D_HUB_INT_MMU_PTI |	\
 				 V3D_HUB_INT_MMU_CAP |	\
-			    V3D_HUB_INT_TFUC))
+				 V3D_HUB_INT_TFUC |		\
+				 (ver >= 71 ? V3D_V7_HUB_INT_GMPV : 0)))
 
 static irqreturn_t
 v3d_hub_irq(int irq, void *arg);
@@ -115,7 +116,7 @@ v3d_irq(int irq, void *arg)
 		status = IRQ_HANDLED;
 	}
 
-	if (intsts & V3D_INT_CSDDONE) {
+	if (intsts & V3D_INT_CSDDONE(v3d->ver)) {
 		struct v3d_fence *fence =
 			to_v3d_fence(v3d->csd_job->base.irq_fence);
 
@@ -127,7 +128,7 @@ v3d_irq(int irq, void *arg)
 	/* We shouldn't be triggering these if we have GMP in
 	 * always-allowed mode.
 	 */
-	if (intsts & V3D_INT_GMPV)
+	if (v3d->ver < 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 &
@@ -197,6 +198,11 @@ v3d_hub_irq(int irq, void *arg)
 		status = IRQ_HANDLED;
 	}
 
+	if (v3d->ver >= 71 && (intsts & V3D_V7_HUB_INT_GMPV)) {
+		dev_err(v3d->drm.dev, "GMP Violation\n");
+		status = IRQ_HANDLED;
+	}
+
 	return status;
 }
 
@@ -211,8 +217,8 @@ v3d_irq_init(struct v3d_dev *v3d)
 	 * for us.
 	 */
 	for (core = 0; core < v3d->cores; core++)
-		V3D_CORE_WRITE(core, V3D_CTL_INT_CLR, V3D_CORE_IRQS);
-	V3D_WRITE(V3D_HUB_INT_CLR, V3D_HUB_IRQS);
+		V3D_CORE_WRITE(core, V3D_CTL_INT_CLR, V3D_CORE_IRQS(v3d->ver));
+	V3D_WRITE(V3D_HUB_INT_CLR, V3D_HUB_IRQS(v3d->ver));
 
 	irq1 = platform_get_irq_optional(v3d_to_pdev(v3d), 1);
 	if (irq1 == -EPROBE_DEFER)
@@ -256,12 +262,12 @@ v3d_irq_enable(struct v3d_dev *v3d)
 
 	/* Enable our set of interrupts, masking out any others. */
 	for (core = 0; core < v3d->cores; core++) {
-		V3D_CORE_WRITE(core, V3D_CTL_INT_MSK_SET, ~V3D_CORE_IRQS);
-		V3D_CORE_WRITE(core, V3D_CTL_INT_MSK_CLR, V3D_CORE_IRQS);
+		V3D_CORE_WRITE(core, V3D_CTL_INT_MSK_SET, ~V3D_CORE_IRQS(v3d->ver));
+		V3D_CORE_WRITE(core, V3D_CTL_INT_MSK_CLR, V3D_CORE_IRQS(v3d->ver));
 	}
 
-	V3D_WRITE(V3D_HUB_INT_MSK_SET, ~V3D_HUB_IRQS);
-	V3D_WRITE(V3D_HUB_INT_MSK_CLR, V3D_HUB_IRQS);
+	V3D_WRITE(V3D_HUB_INT_MSK_SET, ~V3D_HUB_IRQS(v3d->ver));
+	V3D_WRITE(V3D_HUB_INT_MSK_CLR, V3D_HUB_IRQS(v3d->ver));
 }
 
 void
@@ -276,8 +282,8 @@ v3d_irq_disable(struct v3d_dev *v3d)
 
 	/* Clear any pending interrupts we might have left. */
 	for (core = 0; core < v3d->cores; core++)
-		V3D_CORE_WRITE(core, V3D_CTL_INT_CLR, V3D_CORE_IRQS);
-	V3D_WRITE(V3D_HUB_INT_CLR, V3D_HUB_IRQS);
+		V3D_CORE_WRITE(core, V3D_CTL_INT_CLR, V3D_CORE_IRQS(v3d->ver));
+	V3D_WRITE(V3D_HUB_INT_CLR, V3D_HUB_IRQS(v3d->ver));
 
 	cancel_work_sync(&v3d->overflow_mem_work);
 }

drivers/gpu/drm/v3d/v3d_sched.c

@@ -190,20 +190,22 @@ v3d_tfu_job_run(struct drm_sched_job *sched_job)
 
 	trace_v3d_submit_tfu(dev, to_v3d_fence(fence)->seqno);
 
-	V3D_WRITE(V3D_TFU_IIA, job->args.iia);
-	V3D_WRITE(V3D_TFU_IIS, job->args.iis);
-	V3D_WRITE(V3D_TFU_ICA, job->args.ica);
-	V3D_WRITE(V3D_TFU_IUA, job->args.iua);
-	V3D_WRITE(V3D_TFU_IOA, job->args.ioa);
-	V3D_WRITE(V3D_TFU_IOS, job->args.ios);
-	V3D_WRITE(V3D_TFU_COEF0, job->args.coef[0]);
-	if (job->args.coef[0] & V3D_TFU_COEF0_USECOEF) {
-		V3D_WRITE(V3D_TFU_COEF1, job->args.coef[1]);
-		V3D_WRITE(V3D_TFU_COEF2, job->args.coef[2]);
-		V3D_WRITE(V3D_TFU_COEF3, job->args.coef[3]);
+	V3D_WRITE(V3D_TFU_IIA(v3d->ver), job->args.iia);
+	V3D_WRITE(V3D_TFU_IIS(v3d->ver), job->args.iis);
+	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)
+		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)) {
+		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]);
 	}
 	/* ICFG kicks off the job. */
-	V3D_WRITE(V3D_TFU_ICFG, job->args.icfg | V3D_TFU_ICFG_IOC);
+	V3D_WRITE(V3D_TFU_ICFG(v3d->ver), job->args.icfg | V3D_TFU_ICFG_IOC);
 
 	return fence;
 }
@@ -215,7 +217,7 @@ v3d_csd_job_run(struct drm_sched_job *sched_job)
 	struct v3d_dev *v3d = job->base.v3d;
 	struct drm_device *dev = &v3d->drm;
 	struct dma_fence *fence;
-	int i;
+	int i, csd_cfg0_reg, csd_cfg_reg_count;
 
 	v3d->csd_job = job;
 
@@ -233,10 +235,12 @@ v3d_csd_job_run(struct drm_sched_job *sched_job)
 
 	v3d_switch_perfmon(v3d, &job->base);
 
-	for (i = 1; i <= 6; i++)
-		V3D_CORE_WRITE(0, V3D_CSD_QUEUED_CFG0 + 4 * i, job->args.cfg[i]);
+	csd_cfg0_reg = V3D_CSD_QUEUED_CFG0(v3d->ver);
+	csd_cfg_reg_count = v3d->ver < 71 ? 6 : 7;
+	for (i = 1; i <= csd_cfg_reg_count; i++)
+		V3D_CORE_WRITE(0, csd_cfg0_reg + 4 * i, job->args.cfg[i]);
 	/* CFG0 write kicks off the job. */
-	V3D_CORE_WRITE(0, V3D_CSD_QUEUED_CFG0, job->args.cfg[0]);
+	V3D_CORE_WRITE(0, csd_cfg0_reg, job->args.cfg[0]);
 
 	return fence;
 }
@@ -336,7 +340,7 @@ v3d_csd_job_timedout(struct drm_sched_job *sched_job)
 {
 	struct v3d_csd_job *job = to_csd_job(sched_job);
 	struct v3d_dev *v3d = job->base.v3d;
-	u32 batches = V3D_CORE_READ(0, V3D_CSD_CURRENT_CFG4);
+	u32 batches = V3D_CORE_READ(0, V3D_CSD_CURRENT_CFG4(v3d->ver));
 
 	/* If we've made progress, skip reset and let the timer get
 	 * rearmed.