Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:
 "Apart from the core arm64 and perf changes, the Spectre v4 mitigation
  touches the arm KVM code and the ACPI PPTT support touches drivers/
  (acpi and cacheinfo). I should have the maintainers' acks in place.

  Summary:

   - Spectre v4 mitigation (Speculative Store Bypass Disable) support
     for arm64 using SMC firmware call to set a hardware chicken bit

   - ACPI PPTT (Processor Properties Topology Table) parsing support and
     enable the feature for arm64

   - Report signal frame size to user via auxv (AT_MINSIGSTKSZ). The
     primary motivation is Scalable Vector Extensions which requires
     more space on the signal frame than the currently defined
     MINSIGSTKSZ

   - ARM perf patches: allow building arm-cci as module, demote
     dev_warn() to dev_dbg() in arm-ccn event_init(), miscellaneous
     cleanups

   - cmpwait() WFE optimisation to avoid some spurious wakeups

   - L1_CACHE_BYTES reverted back to 64 (for performance reasons that
     have to do with some network allocations) while keeping
     ARCH_DMA_MINALIGN to 128. cache_line_size() returns the actual
     hardware Cache Writeback Granule

   - Turn LSE atomics on by default in Kconfig

   - Kernel fault reporting tidying

   - Some #include and miscellaneous cleanups"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (53 commits)
  arm64: Fix syscall restarting around signal suppressed by tracer
  arm64: topology: Avoid checking numa mask for scheduler MC selection
  ACPI / PPTT: fix build when CONFIG_ACPI_PPTT is not enabled
  arm64: cpu_errata: include required headers
  arm64: KVM: Move VCPU_WORKAROUND_2_FLAG macros to the top of the file
  arm64: signal: Report signal frame size to userspace via auxv
  arm64/sve: Thin out initialisation sanity-checks for sve_max_vl
  arm64: KVM: Add ARCH_WORKAROUND_2 discovery through ARCH_FEATURES_FUNC_ID
  arm64: KVM: Handle guest's ARCH_WORKAROUND_2 requests
  arm64: KVM: Add ARCH_WORKAROUND_2 support for guests
  arm64: KVM: Add HYP per-cpu accessors
  arm64: ssbd: Add prctl interface for per-thread mitigation
  arm64: ssbd: Introduce thread flag to control userspace mitigation
  arm64: ssbd: Restore mitigation status on CPU resume
  arm64: ssbd: Skip apply_ssbd if not using dynamic mitigation
  arm64: ssbd: Add global mitigation state accessor
  arm64: Add 'ssbd' command-line option
  arm64: Add ARCH_WORKAROUND_2 probing
  arm64: Add per-cpu infrastructure to call ARCH_WORKAROUND_2
  arm64: Call ARCH_WORKAROUND_2 on transitions between EL0 and EL1
  ...

5 files changed, 56 insertions, 57 deletions

diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index 28bb5a029558..08ebaf7cca8b 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -6,30 +6,32 @@ menu "Performance monitor support"
 	depends on PERF_EVENTS
 
 config ARM_CCI_PMU
-	bool
+	tristate "ARM CCI PMU driver"
+	depends on (ARM && CPU_V7) || ARM64
 	select ARM_CCI
+	help
+	  Support for PMU events monitoring on the ARM CCI (Cache Coherent
+	  Interconnect) family of products.
+
+	  If compiled as a module, it will be called arm-cci.
 
 config ARM_CCI400_PMU
-	bool "ARM CCI400 PMU support"
-	depends on (ARM && CPU_V7) || ARM64
+	bool "support CCI-400"
+	default y
+	depends on ARM_CCI_PMU
 	select ARM_CCI400_COMMON
-	select ARM_CCI_PMU
 	help
-	  Support for PMU events monitoring on the ARM CCI-400 (cache coherent
-	  interconnect). CCI-400 supports counting events related to the
-	  connected slave/master interfaces.
+	  CCI-400 provides 4 independent event counters counting events related
+	  to the connected slave/master interfaces, plus a cycle counter.
 
 config ARM_CCI5xx_PMU
-	bool "ARM CCI-500/CCI-550 PMU support"
-	depends on (ARM && CPU_V7) || ARM64
-	select ARM_CCI_PMU
+	bool "support CCI-500/CCI-550"
+	default y
+	depends on ARM_CCI_PMU
 	help
-	  Support for PMU events monitoring on the ARM CCI-500/CCI-550 cache
-	  coherent interconnects. Both of them provide 8 independent event counters,
-	  which can count events pertaining to the slave/master interfaces as well
-	  as the internal events to the CCI.
-
-	  If unsure, say Y
+	  CCI-500/CCI-550 both provide 8 independent event counters, which can
+	  count events pertaining to the slave/master interfaces as well as the
+	  internal events to the CCI.
 
 config ARM_CCN
 	tristate "ARM CCN driver support"
@@ -94,7 +96,7 @@ config XGENE_PMU
 
 config ARM_SPE_PMU
 	tristate "Enable support for the ARMv8.2 Statistical Profiling Extension"
-	depends on PERF_EVENTS && ARM64
+	depends on ARM64
 	help
 	  Enable perf support for the ARMv8.2 Statistical Profiling
 	  Extension, which provides periodic sampling of operations in
diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c
index 383b2d3dcbc6..0d09d8e669cd 100644
--- a/drivers/perf/arm-cci.c
+++ b/drivers/perf/arm-cci.c
@@ -120,9 +120,9 @@ enum cci_models {
 
 static void pmu_write_counters(struct cci_pmu *cci_pmu,
 				 unsigned long *mask);
-static ssize_t cci_pmu_format_show(struct device *dev,
+static ssize_t __maybe_unused cci_pmu_format_show(struct device *dev,
 			struct device_attribute *attr, char *buf);
-static ssize_t cci_pmu_event_show(struct device *dev,
+static ssize_t __maybe_unused cci_pmu_event_show(struct device *dev,
 			struct device_attribute *attr, char *buf);
 
 #define CCI_EXT_ATTR_ENTRY(_name, _func, _config) 				\
@@ -1184,16 +1184,11 @@ static int cci_pmu_add(struct perf_event *event, int flags)
 	struct cci_pmu_hw_events *hw_events = &cci_pmu->hw_events;
 	struct hw_perf_event *hwc = &event->hw;
 	int idx;
-	int err = 0;
-
-	perf_pmu_disable(event->pmu);
 
 	/* If we don't have a space for the counter then finish early. */
 	idx = pmu_get_event_idx(hw_events, event);
-	if (idx < 0) {
-		err = idx;
-		goto out;
-	}
+	if (idx < 0)
+		return idx;
 
 	event->hw.idx = idx;
 	hw_events->events[idx] = event;
@@ -1205,9 +1200,7 @@ static int cci_pmu_add(struct perf_event *event, int flags)
 	/* Propagate our changes to the userspace mapping. */
 	perf_event_update_userpage(event);
 
-out:
-	perf_pmu_enable(event->pmu);
-	return err;
+	return 0;
 }
 
 static void cci_pmu_del(struct perf_event *event, int flags)
@@ -1304,15 +1297,6 @@ static int __hw_perf_event_init(struct perf_event *event)
 	 */
 	hwc->config_base	    |= (unsigned long)mapping;
 
-	/*
-	 * Limit the sample_period to half of the counter width. That way, the
-	 * new counter value is far less likely to overtake the previous one
-	 * unless you have some serious IRQ latency issues.
-	 */
-	hwc->sample_period  = CCI_PMU_CNTR_MASK >> 1;
-	hwc->last_period    = hwc->sample_period;
-	local64_set(&hwc->period_left, hwc->sample_period);
-
 	if (event->group_leader != event) {
 		if (validate_group(event) != 0)
 			return -EINVAL;
@@ -1423,6 +1407,7 @@ static int cci_pmu_init(struct cci_pmu *cci_pmu, struct platform_device *pdev)
 	pmu_format_attr_group.attrs = model->format_attrs;
 
 	cci_pmu->pmu = (struct pmu) {
+		.module		= THIS_MODULE,
 		.name		= cci_pmu->model->name,
 		.task_ctx_nr	= perf_invalid_context,
 		.pmu_enable	= cci_pmu_enable,
@@ -1466,7 +1451,7 @@ static int cci_pmu_offline_cpu(unsigned int cpu)
 	return 0;
 }
 
-static struct cci_pmu_model cci_pmu_models[] = {
+static __maybe_unused struct cci_pmu_model cci_pmu_models[] = {
 #ifdef CONFIG_ARM_CCI400_PMU
 	[CCI400_R0] = {
 		.name = "CCI_400",
@@ -1588,6 +1573,7 @@ static const struct of_device_id arm_cci_pmu_matches[] = {
 #endif
 	{},
 };
+MODULE_DEVICE_TABLE(of, arm_cci_pmu_matches);
 
 static bool is_duplicate_irq(int irq, int *irqs, int nr_irqs)
 {
@@ -1709,14 +1695,27 @@ static int cci_pmu_probe(struct platform_device *pdev)
 	return 0;
 }
 
+static int cci_pmu_remove(struct platform_device *pdev)
+{
+	if (!g_cci_pmu)
+		return 0;
+
+	cpuhp_remove_state(CPUHP_AP_PERF_ARM_CCI_ONLINE);
+	perf_pmu_unregister(&g_cci_pmu->pmu);
+	g_cci_pmu = NULL;
+
+	return 0;
+}
+
 static struct platform_driver cci_pmu_driver = {
 	.driver = {
 		   .name = DRIVER_NAME,
 		   .of_match_table = arm_cci_pmu_matches,
 		  },
 	.probe = cci_pmu_probe,
+	.remove = cci_pmu_remove,
 };
 
-builtin_platform_driver(cci_pmu_driver);
-MODULE_LICENSE("GPL");
+module_platform_driver(cci_pmu_driver);
+MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("ARM CCI PMU support");
diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c
index 65b7e4042ece..b416ee18e6bb 100644
--- a/drivers/perf/arm-ccn.c
+++ b/drivers/perf/arm-ccn.c
@@ -736,7 +736,7 @@ static int arm_ccn_pmu_event_init(struct perf_event *event)
 	ccn = pmu_to_arm_ccn(event->pmu);
 
 	if (hw->sample_period) {
-		dev_warn(ccn->dev, "Sampling not supported!\n");
+		dev_dbg(ccn->dev, "Sampling not supported!\n");
 		return -EOPNOTSUPP;
 	}
 
@@ -744,12 +744,12 @@ static int arm_ccn_pmu_event_init(struct perf_event *event)
 			event->attr.exclude_kernel || event->attr.exclude_hv ||
 			event->attr.exclude_idle || event->attr.exclude_host ||
 			event->attr.exclude_guest) {
-		dev_warn(ccn->dev, "Can't exclude execution levels!\n");
+		dev_dbg(ccn->dev, "Can't exclude execution levels!\n");
 		return -EINVAL;
 	}
 
 	if (event->cpu < 0) {
-		dev_warn(ccn->dev, "Can't provide per-task data!\n");
+		dev_dbg(ccn->dev, "Can't provide per-task data!\n");
 		return -EOPNOTSUPP;
 	}
 	/*
@@ -771,13 +771,13 @@ static int arm_ccn_pmu_event_init(struct perf_event *event)
 	switch (type) {
 	case CCN_TYPE_MN:
 		if (node_xp != ccn->mn_id) {
-			dev_warn(ccn->dev, "Invalid MN ID %d!\n", node_xp);
+			dev_dbg(ccn->dev, "Invalid MN ID %d!\n", node_xp);
 			return -EINVAL;
 		}
 		break;
 	case CCN_TYPE_XP:
 		if (node_xp >= ccn->num_xps) {
-			dev_warn(ccn->dev, "Invalid XP ID %d!\n", node_xp);
+			dev_dbg(ccn->dev, "Invalid XP ID %d!\n", node_xp);
 			return -EINVAL;
 		}
 		break;
@@ -785,11 +785,11 @@ static int arm_ccn_pmu_event_init(struct perf_event *event)
 		break;
 	default:
 		if (node_xp >= ccn->num_nodes) {
-			dev_warn(ccn->dev, "Invalid node ID %d!\n", node_xp);
+			dev_dbg(ccn->dev, "Invalid node ID %d!\n", node_xp);
 			return -EINVAL;
 		}
 		if (!arm_ccn_pmu_type_eq(type, ccn->node[node_xp].type)) {
-			dev_warn(ccn->dev, "Invalid type 0x%x for node %d!\n",
+			dev_dbg(ccn->dev, "Invalid type 0x%x for node %d!\n",
 					type, node_xp);
 			return -EINVAL;
 		}
@@ -808,19 +808,19 @@ static int arm_ccn_pmu_event_init(struct perf_event *event)
 		if (event_id != e->event)
 			continue;
 		if (e->num_ports && port >= e->num_ports) {
-			dev_warn(ccn->dev, "Invalid port %d for node/XP %d!\n",
+			dev_dbg(ccn->dev, "Invalid port %d for node/XP %d!\n",
 					port, node_xp);
 			return -EINVAL;
 		}
 		if (e->num_vcs && vc >= e->num_vcs) {
-			dev_warn(ccn->dev, "Invalid vc %d for node/XP %d!\n",
+			dev_dbg(ccn->dev, "Invalid vc %d for node/XP %d!\n",
 					vc, node_xp);
 			return -EINVAL;
 		}
 		valid = 1;
 	}
 	if (!valid) {
-		dev_warn(ccn->dev, "Invalid event 0x%x for node/XP %d!\n",
+		dev_dbg(ccn->dev, "Invalid event 0x%x for node/XP %d!\n",
 				event_id, node_xp);
 		return -EINVAL;
 	}
@@ -1594,4 +1594,4 @@ module_init(arm_ccn_init);
 module_exit(arm_ccn_exit);
 
 MODULE_AUTHOR("Pawel Moll <pawel.moll@arm.com>");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 1a0d340b65cf..a6347d487635 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -339,7 +339,7 @@ static irqreturn_t armpmu_dispatch_irq(int irq, void *dev)
 		return IRQ_NONE;
 
 	start_clock = sched_clock();
-	ret = armpmu->handle_irq(irq, armpmu);
+	ret = armpmu->handle_irq(armpmu);
 	finish_clock = sched_clock();
 
 	perf_sample_event_took(finish_clock - start_clock);
diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index 28bb642af18b..54ec278d2fc4 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -131,8 +131,7 @@ static ssize_t arm_spe_pmu_cap_show(struct device *dev,
 				    struct device_attribute *attr,
 				    char *buf)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct arm_spe_pmu *spe_pmu = platform_get_drvdata(pdev);
+	struct arm_spe_pmu *spe_pmu = dev_get_drvdata(dev);
 	struct dev_ext_attribute *ea =
 		container_of(attr, struct dev_ext_attribute, attr);
 	int cap = (long)ea->var;
@@ -247,8 +246,7 @@ static ssize_t arm_spe_pmu_get_attr_cpumask(struct device *dev,
 					    struct device_attribute *attr,
 					    char *buf)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct arm_spe_pmu *spe_pmu = platform_get_drvdata(pdev);
+	struct arm_spe_pmu *spe_pmu = dev_get_drvdata(dev);
 
 	return cpumap_print_to_pagebuf(true, buf, &spe_pmu->supported_cpus);
 }