Add missing content to 24.04_linux-nvidia-internal-6.11-next

debian.nvidia-internal-6.11/config/annotations

@@ -84,6 +84,18 @@ CONFIG_CORESIGHT_TPDM                           note<'Required for Grace enablem
 CONFIG_CORESIGHT_TRBE                           policy<{'arm64': 'm'}>
 CONFIG_CORESIGHT_TRBE                           note<'Required for Grace enablement'>
 
+CONFIG_PREEMPT_NONE                             policy<{'amd64': 'n', 'arm64': 'y'}>
+CONFIG_PREEMPT_NONE                             note<'Required for NVIDIA workloads'>
+
+CONFIG_PREEMPT_VOLUNTARY                        policy<{'amd64': 'y', 'arm64': 'n'}>
+CONFIG_PREEMPT_VOLUNTARY                        note<'Required for NVIDIA workloads'>
+
+CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND            policy<{'arm64': 'n'}>
+CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND            note<'Required for NVIDIA workloads'>
+
+CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE         policy<{'amd64': 'n', 'arm64': 'y'}>
+CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE         note<'Required for NVIDIA workloads'>
+
 CONFIG_DRM_NOUVEAU                              policy<{'amd64': 'n', 'arm64': 'n'}>
 CONFIG_DRM_NOUVEAU                              note<'Disable nouveau for NVIDIA kernels'>
 

drivers/acpi/numa/hmat.c

@@ -442,9 +442,9 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 		return -EINVAL;
 	}
 
-	pr_info("Locality: Flags:%02x Type:%s Initiator Domains:%u Target Domains:%u Base:%lld\n",
-		hmat_loc->flags, hmat_data_type(type), ipds, tpds,
-		hmat_loc->entry_base_unit);
+	pr_debug("Locality: Flags:%02x Type:%s Initiator Domains:%u Target Domains:%u Base:%lld\n",
+		 hmat_loc->flags, hmat_data_type(type), ipds, tpds,
+		 hmat_loc->entry_base_unit);
 
 	inits = (u32 *)(hmat_loc + 1);
 	targs = inits + ipds;
@@ -455,9 +455,9 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 			value = hmat_normalize(entries[init * tpds + targ],
 					       hmat_loc->entry_base_unit,
 					       type);
-			pr_info("  Initiator-Target[%u-%u]:%u%s\n",
-				inits[init], targs[targ], value,
-				hmat_data_type_suffix(type));
+			pr_debug("  Initiator-Target[%u-%u]:%u%s\n",
+				 inits[init], targs[targ], value,
+				 hmat_data_type_suffix(type));
 
 			hmat_update_target(targs[targ], inits[init],
 					   mem_hier, type, value);
@@ -485,9 +485,9 @@ static __init int hmat_parse_cache(union acpi_subtable_headers *header,
 	}
 
 	attrs = cache->cache_attributes;
-	pr_info("Cache: Domain:%u Size:%llu Attrs:%08x SMBIOS Handles:%d\n",
-		cache->memory_PD, cache->cache_size, attrs,
-		cache->number_of_SMBIOShandles);
+	pr_debug("Cache: Domain:%u Size:%llu Attrs:%08x SMBIOS Handles:%d\n",
+		 cache->memory_PD, cache->cache_size, attrs,
+		 cache->number_of_SMBIOShandles);
 
 	target = find_mem_target(cache->memory_PD);
 	if (!target)
@@ -546,9 +546,9 @@ static int __init hmat_parse_proximity_domain(union acpi_subtable_headers *heade
 	}
 
 	if (hmat_revision == 1)
-		pr_info("Memory (%#llx length %#llx) Flags:%04x Processor Domain:%u Memory Domain:%u\n",
-			p->reserved3, p->reserved4, p->flags, p->processor_PD,
-			p->memory_PD);
+		pr_debug("Memory (%#llx length %#llx) Flags:%04x Processor Domain:%u Memory Domain:%u\n",
+			 p->reserved3, p->reserved4, p->flags, p->processor_PD,
+			 p->memory_PD);
 	else
 		pr_info("Memory Flags:%04x Processor Domain:%u Memory Domain:%u\n",
 			p->flags, p->processor_PD, p->memory_PD);

drivers/cpufreq/cppc_cpufreq.c

@@ -36,33 +36,15 @@ static LIST_HEAD(cpu_data_list);
 
 static bool boost_supported;
 
-struct cppc_workaround_oem_info {
-	char oem_id[ACPI_OEM_ID_SIZE + 1];
-	char oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1];
-	u32 oem_revision;
-};
-
-static struct cppc_workaround_oem_info wa_info[] = {
-	{
-		.oem_id		= "HISI  ",
-		.oem_table_id	= "HIP07   ",
-		.oem_revision	= 0,
-	}, {
-		.oem_id		= "HISI  ",
-		.oem_table_id	= "HIP08   ",
-		.oem_revision	= 0,
-	}
-};
-
 static struct cpufreq_driver cppc_cpufreq_driver;
 
+#ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE
 static enum {
 	FIE_UNSET = -1,
 	FIE_ENABLED,
 	FIE_DISABLED
 } fie_disabled = FIE_UNSET;
 
-#ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE
 module_param(fie_disabled, int, 0444);
 MODULE_PARM_DESC(fie_disabled, "Disable Frequency Invariance Engine (FIE)");
 
@@ -78,7 +60,6 @@ struct cppc_freq_invariance {
 static DEFINE_PER_CPU(struct cppc_freq_invariance, cppc_freq_inv);
 static struct kthread_worker *kworker_fie;
 
-static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu);
 static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,
 				 struct cppc_perf_fb_ctrs *fb_ctrs_t0,
 				 struct cppc_perf_fb_ctrs *fb_ctrs_t1);
@@ -118,6 +99,9 @@ static void cppc_scale_freq_workfn(struct kthread_work *work)
 
 	perf = cppc_perf_from_fbctrs(cpu_data, &cppc_fi->prev_perf_fb_ctrs,
 				     &fb_ctrs);
+	if (!perf)
+		return;
+
 	cppc_fi->prev_perf_fb_ctrs = fb_ctrs;
 
 	perf <<= SCHED_CAPACITY_SHIFT;
@@ -724,13 +708,31 @@ static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,
 	delta_delivered = get_delta(fb_ctrs_t1->delivered,
 				    fb_ctrs_t0->delivered);
 
-	/* Check to avoid divide-by zero and invalid delivered_perf */
+	/*
+	 * Avoid divide-by zero and unchanged feedback counters.
+	 * Leave it for callers to handle.
+	 */
 	if (!delta_reference || !delta_delivered)
-		return cpu_data->perf_ctrls.desired_perf;
+		return 0;
 
 	return (reference_perf * delta_delivered) / delta_reference;
 }
 
+static int cppc_get_perf_ctrs_sample(int cpu,
+				     struct cppc_perf_fb_ctrs *fb_ctrs_t0,
+				     struct cppc_perf_fb_ctrs *fb_ctrs_t1)
+{
+	int ret;
+
+	ret = cppc_get_perf_ctrs(cpu, fb_ctrs_t0);
+	if (ret)
+		return ret;
+
+	udelay(2); /* 2usec delay between sampling */
+
+	return cppc_get_perf_ctrs(cpu, fb_ctrs_t1);
+}
+
 static unsigned int cppc_cpufreq_get_rate(unsigned int cpu)
 {
 	struct cppc_perf_fb_ctrs fb_ctrs_t0 = {0}, fb_ctrs_t1 = {0};
@@ -746,18 +748,32 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu)
 
 	cpufreq_cpu_put(policy);
 
-	ret = cppc_get_perf_ctrs(cpu, &fb_ctrs_t0);
-	if (ret)
-		return 0;
-
-	udelay(2); /* 2usec delay between sampling */
-
-	ret = cppc_get_perf_ctrs(cpu, &fb_ctrs_t1);
-	if (ret)
-		return 0;
+	ret = cppc_get_perf_ctrs_sample(cpu, &fb_ctrs_t0, &fb_ctrs_t1);
+	if (ret) {
+		if (ret == -EFAULT)
+			/* Any of the associated CPPC regs is 0. */
+			goto out_invalid_counters;
+		else
+			return 0;
+	}
 
 	delivered_perf = cppc_perf_from_fbctrs(cpu_data, &fb_ctrs_t0,
 					       &fb_ctrs_t1);
+	if (!delivered_perf)
+		goto out_invalid_counters;
+
+	return cppc_perf_to_khz(&cpu_data->perf_caps, delivered_perf);
+
+out_invalid_counters:
+	/*
+	 * Feedback counters could be unchanged or 0 when a cpu enters a
+	 * low-power idle state, e.g. clock-gated or power-gated.
+	 * Use desired perf for reflecting frequency.  Get the latest register
+	 * value first as some platforms may update the actual delivered perf
+	 * there; if failed, resort to the cached desired perf.
+	 */
+	if (cppc_get_desired_perf(cpu, &delivered_perf))
+		delivered_perf = cpu_data->perf_ctrls.desired_perf;
 
 	return cppc_perf_to_khz(&cpu_data->perf_caps, delivered_perf);
 }
@@ -812,65 +828,13 @@ static struct cpufreq_driver cppc_cpufreq_driver = {
 	.name = "cppc_cpufreq",
 };
 
-/*
- * HISI platform does not support delivered performance counter and
- * reference performance counter. It can calculate the performance using the
- * platform specific mechanism. We reuse the desired performance register to
- * store the real performance calculated by the platform.
- */
-static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu)
-{
-	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
-	struct cppc_cpudata *cpu_data;
-	u64 desired_perf;
-	int ret;
-
-	if (!policy)
-		return -ENODEV;
-
-	cpu_data = policy->driver_data;
-
-	cpufreq_cpu_put(policy);
-
-	ret = cppc_get_desired_perf(cpu, &desired_perf);
-	if (ret < 0)
-		return -EIO;
-
-	return cppc_perf_to_khz(&cpu_data->perf_caps, desired_perf);
-}
-
-static void cppc_check_hisi_workaround(void)
-{
-	struct acpi_table_header *tbl;
-	acpi_status status = AE_OK;
-	int i;
-
-	status = acpi_get_table(ACPI_SIG_PCCT, 0, &tbl);
-	if (ACPI_FAILURE(status) || !tbl)
-		return;
-
-	for (i = 0; i < ARRAY_SIZE(wa_info); i++) {
-		if (!memcmp(wa_info[i].oem_id, tbl->oem_id, ACPI_OEM_ID_SIZE) &&
-		    !memcmp(wa_info[i].oem_table_id, tbl->oem_table_id, ACPI_OEM_TABLE_ID_SIZE) &&
-		    wa_info[i].oem_revision == tbl->oem_revision) {
-			/* Overwrite the get() callback */
-			cppc_cpufreq_driver.get = hisi_cppc_cpufreq_get_rate;
-			fie_disabled = FIE_DISABLED;
-			break;
-		}
-	}
-
-	acpi_put_table(tbl);
-}
-
 static int __init cppc_cpufreq_init(void)
 {
 	int ret;
 
 	if (!acpi_cpc_valid())
 		return -ENODEV;
 
-	cppc_check_hisi_workaround();
 	cppc_freq_invariance_init();
 	populate_efficiency_class();
 

drivers/hwtracing/coresight/coresight-core.c

@@ -487,23 +487,25 @@ struct coresight_device *coresight_get_sink(struct list_head *path)
 	return csdev;
 }
 
+u32 coresight_get_sink_id(struct coresight_device *csdev)
+{
+	if (!csdev->ea)
+		return 0;
+
+	/*
+	 * See function etm_perf_add_symlink_sink() to know where
+	 * this comes from.
+	 */
+	return (u32) (unsigned long) csdev->ea->var;
+}
+
 static int coresight_sink_by_id(struct device *dev, const void *data)
 {
 	struct coresight_device *csdev = to_coresight_device(dev);
-	unsigned long hash;
 
 	if (csdev->type == CORESIGHT_DEV_TYPE_SINK ||
-	     csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) {
-
-		if (!csdev->ea)
-			return 0;
-		/*
-		 * See function etm_perf_add_symlink_sink() to know where
-		 * this comes from.
-		 */
-		hash = (unsigned long)csdev->ea->var;
-
-		if ((u32)hash == *(u32 *)data)
+	    csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) {
+		if (coresight_get_sink_id(csdev) == *(u32 *)data)
 			return 1;
 	}
 
@@ -902,6 +904,7 @@ static void coresight_device_release(struct device *dev)
 	struct coresight_device *csdev = to_coresight_device(dev);
 
 	fwnode_handle_put(csdev->dev.fwnode);
+	free_percpu(csdev->perf_sink_id_map.cpu_map);
 	kfree(csdev);
 }
 
@@ -1159,6 +1162,16 @@ struct coresight_device *coresight_register(struct coresight_desc *desc)
 	csdev->dev.fwnode = fwnode_handle_get(dev_fwnode(desc->dev));
 	dev_set_name(&csdev->dev, "%s", desc->name);
 
+	if (csdev->type == CORESIGHT_DEV_TYPE_SINK ||
+	    csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) {
+		spin_lock_init(&csdev->perf_sink_id_map.lock);
+		csdev->perf_sink_id_map.cpu_map = alloc_percpu(atomic_t);
+		if (!csdev->perf_sink_id_map.cpu_map) {
+			kfree(csdev);
+			ret = -ENOMEM;
+			goto err_out;
+		}
+	}
 	/*
 	 * Make sure the device registration and the connection fixup
 	 * are synchronised, so that we don't see uninitialised devices

drivers/hwtracing/coresight/coresight-dummy.c

@@ -21,7 +21,8 @@ DEFINE_CORESIGHT_DEVLIST(source_devs, "dummy_source");
 DEFINE_CORESIGHT_DEVLIST(sink_devs, "dummy_sink");
 
 static int dummy_source_enable(struct coresight_device *csdev,
-			       struct perf_event *event, enum cs_mode mode)
+			       struct perf_event *event, enum cs_mode mode,
+			       __maybe_unused struct coresight_trace_id_map *id_map)
 {
 	dev_dbg(csdev->dev.parent, "Dummy source enabled\n");