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

Pull arm64 updates from Will Deacon:
 "Highlights include a major rework of our kPTI page-table rewriting
  code (which makes it both more maintainable and considerably faster in
  the cases where it is required) as well as significant changes to our
  early boot code to reduce the need for data cache maintenance and
  greatly simplify the KASLR relocation dance.

  Summary:

   - Remove unused generic cpuidle support (replaced by PSCI version)

   - Fix documentation describing the kernel virtual address space

   - Handling of some new CPU errata in Arm implementations

   - Rework of our exception table code in preparation for handling
     machine checks (i.e. RAS errors) more gracefully

   - Switch over to the generic implementation of ioremap()

   - Fix lockdep tracking in NMI context

   - Instrument our memory barrier macros for KCSAN

   - Rework of the kPTI G->nG page-table repainting so that the MMU
     remains enabled and the boot time is no longer slowed to a crawl
     for systems which require the late remapping

   - Enable support for direct swapping of 2MiB transparent huge-pages
     on systems without MTE

   - Fix handling of MTE tags with allocating new pages with HW KASAN

   - Expose the SMIDR register to userspace via sysfs

   - Continued rework of the stack unwinder, particularly improving the
     behaviour under KASAN

   - More repainting of our system register definitions to match the
     architectural terminology

   - Improvements to the layout of the vDSO objects

   - Support for allocating additional bits of HWCAP2 and exposing
     FEAT_EBF16 to userspace on CPUs that support it

   - Considerable rework and optimisation of our early boot code to
     reduce the need for cache maintenance and avoid jumping in and out
     of the kernel when handling relocation under KASLR

   - Support for disabling SVE and SME support on the kernel
     command-line

   - Support for the Hisilicon HNS3 PMU

   - Miscellanous cleanups, trivial updates and minor fixes"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (136 commits)
  arm64: Delay initialisation of cpuinfo_arm64::reg_{zcr,smcr}
  arm64: fix KASAN_INLINE
  arm64/hwcap: Support FEAT_EBF16
  arm64/cpufeature: Store elf_hwcaps as a bitmap rather than unsigned long
  arm64/hwcap: Document allocation of upper bits of AT_HWCAP
  arm64: enable THP_SWAP for arm64
  arm64/mm: use GENMASK_ULL for TTBR_BADDR_MASK_52
  arm64: errata: Remove AES hwcap for COMPAT tasks
  arm64: numa: Don't check node against MAX_NUMNODES
  drivers/perf: arm_spe: Fix consistency of SYS_PMSCR_EL1.CX
  perf: RISC-V: Add of_node_put() when breaking out of for_each_of_cpu_node()
  docs: perf: Include hns3-pmu.rst in toctree to fix 'htmldocs' WARNING
  arm64: kasan: Revert "arm64: mte: reset the page tag in page->flags"
  mm: kasan: Skip page unpoisoning only if __GFP_SKIP_KASAN_UNPOISON
  mm: kasan: Skip unpoisoning of user pages
  mm: kasan: Ensure the tags are visible before the tag in page->flags
  drivers/perf: hisi: add driver for HNS3 PMU
  drivers/perf: hisi: Add description for HNS3 PMU driver
  drivers/perf: riscv_pmu_sbi: perf format
  perf/arm-cci: Use the bitmap API to allocate bitmaps
  ...

1 files changed, 101 insertions, 5 deletions

diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c
index dca3537a8dcc..79a3de515ece 100644
--- a/drivers/perf/riscv_pmu_sbi.c
+++ b/drivers/perf/riscv_pmu_sbi.c
@@ -17,10 +17,30 @@
 #include <linux/irqdomain.h>
 #include <linux/of_irq.h>
 #include <linux/of.h>
+#include <linux/cpu_pm.h>
 
 #include <asm/sbi.h>
 #include <asm/hwcap.h>
 
+PMU_FORMAT_ATTR(event, "config:0-47");
+PMU_FORMAT_ATTR(firmware, "config:63");
+
+static struct attribute *riscv_arch_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_firmware.attr,
+	NULL,
+};
+
+static struct attribute_group riscv_pmu_format_group = {
+	.name = "format",
+	.attrs = riscv_arch_formats_attr,
+};
+
+static const struct attribute_group *riscv_pmu_attr_groups[] = {
+	&riscv_pmu_format_group,
+	NULL,
+};
+
 union sbi_pmu_ctr_info {
 	unsigned long value;
 	struct {
@@ -666,12 +686,15 @@ static int pmu_sbi_setup_irqs(struct riscv_pmu *pmu, struct platform_device *pde
 		child = of_get_compatible_child(cpu, "riscv,cpu-intc");
 		if (!child) {
 			pr_err("Failed to find INTC node\n");
+			of_node_put(cpu);
 			return -ENODEV;
 		}
 		domain = irq_find_host(child);
 		of_node_put(child);
-		if (domain)
+		if (domain) {
+			of_node_put(cpu);
 			break;
+		}
 	}
 	if (!domain) {
 		pr_err("Failed to find INTC IRQ root domain\n");
@@ -693,6 +716,73 @@ static int pmu_sbi_setup_irqs(struct riscv_pmu *pmu, struct platform_device *pde
 	return 0;
 }
 
+#ifdef CONFIG_CPU_PM
+static int riscv_pm_pmu_notify(struct notifier_block *b, unsigned long cmd,
+				void *v)
+{
+	struct riscv_pmu *rvpmu = container_of(b, struct riscv_pmu, riscv_pm_nb);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(rvpmu->hw_events);
+	int enabled = bitmap_weight(cpuc->used_hw_ctrs, RISCV_MAX_COUNTERS);
+	struct perf_event *event;
+	int idx;
+
+	if (!enabled)
+		return NOTIFY_OK;
+
+	for (idx = 0; idx < RISCV_MAX_COUNTERS; idx++) {
+		event = cpuc->events[idx];
+		if (!event)
+			continue;
+
+		switch (cmd) {
+		case CPU_PM_ENTER:
+			/*
+			 * Stop and update the counter
+			 */
+			riscv_pmu_stop(event, PERF_EF_UPDATE);
+			break;
+		case CPU_PM_EXIT:
+		case CPU_PM_ENTER_FAILED:
+			/*
+			 * Restore and enable the counter.
+			 *
+			 * Requires RCU read locking to be functional,
+			 * wrap the call within RCU_NONIDLE to make the
+			 * RCU subsystem aware this cpu is not idle from
+			 * an RCU perspective for the riscv_pmu_start() call
+			 * duration.
+			 */
+			RCU_NONIDLE(riscv_pmu_start(event, PERF_EF_RELOAD));
+			break;
+		default:
+			break;
+		}
+	}
+
+	return NOTIFY_OK;
+}
+
+static int riscv_pm_pmu_register(struct riscv_pmu *pmu)
+{
+	pmu->riscv_pm_nb.notifier_call = riscv_pm_pmu_notify;
+	return cpu_pm_register_notifier(&pmu->riscv_pm_nb);
+}
+
+static void riscv_pm_pmu_unregister(struct riscv_pmu *pmu)
+{
+	cpu_pm_unregister_notifier(&pmu->riscv_pm_nb);
+}
+#else
+static inline int riscv_pm_pmu_register(struct riscv_pmu *pmu) { return 0; }
+static inline void riscv_pm_pmu_unregister(struct riscv_pmu *pmu) { }
+#endif
+
+static void riscv_pmu_destroy(struct riscv_pmu *pmu)
+{
+	riscv_pm_pmu_unregister(pmu);
+	cpuhp_state_remove_instance(CPUHP_AP_PERF_RISCV_STARTING, &pmu->node);
+}
+
 static int pmu_sbi_device_probe(struct platform_device *pdev)
 {
 	struct riscv_pmu *pmu = NULL;
@@ -720,6 +810,7 @@ static int pmu_sbi_device_probe(struct platform_device *pdev)
 		pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
 		pmu->pmu.capabilities |= PERF_PMU_CAP_NO_EXCLUDE;
 	}
+	pmu->pmu.attr_groups = riscv_pmu_attr_groups;
 	pmu->num_counters = num_counters;
 	pmu->ctr_start = pmu_sbi_ctr_start;
 	pmu->ctr_stop = pmu_sbi_ctr_stop;
@@ -733,14 +824,19 @@ static int pmu_sbi_device_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	ret = riscv_pm_pmu_register(pmu);
+	if (ret)
+		goto out_unregister;
+
 	ret = perf_pmu_register(&pmu->pmu, "cpu", PERF_TYPE_RAW);
-	if (ret) {
-		cpuhp_state_remove_instance(CPUHP_AP_PERF_RISCV_STARTING, &pmu->node);
-		return ret;
-	}
+	if (ret)
+		goto out_unregister;
 
 	return 0;
 
+out_unregister:
+	riscv_pmu_destroy(pmu);
+
 out_free:
 	kfree(pmu);
 	return ret;