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

Pull arm64 updates from Catalin Marinas:
 "No major architecture features this time around, just some new HWCAP
  definitions, support for the Ampere SoC PMUs and a few fixes/cleanups.

  The bulk of the changes is reworking of the CPU capability checking
  code (cpus_have_cap() etc).

   - Major refactoring of the CPU capability detection logic resulting
     in the removal of the cpus_have_const_cap() function and migrating
     the code to "alternative" branches where possible

   - Backtrace/kgdb: use IPIs and pseudo-NMI

   - Perf and PMU:

      - Add support for Ampere SoC PMUs

      - Multi-DTC improvements for larger CMN configurations with
        multiple Debug & Trace Controllers

      - Rework the Arm CoreSight PMU driver to allow separate
        registration of vendor backend modules

      - Fixes: add missing MODULE_DEVICE_TABLE to the amlogic perf
        driver; use device_get_match_data() in the xgene driver; fix
        NULL pointer dereference in the hisi driver caused by calling
        cpuhp_state_remove_instance(); use-after-free in the hisi driver

   - HWCAP updates:

      - FEAT_SVE_B16B16 (BFloat16)

      - FEAT_LRCPC3 (release consistency model)

      - FEAT_LSE128 (128-bit atomic instructions)

   - SVE: remove a couple of pseudo registers from the cpufeature code.
     There is logic in place already to detect mismatched SVE features

   - Miscellaneous:

      - Reduce the default swiotlb size (currently 64MB) if no ZONE_DMA
        bouncing is needed. The buffer is still required for small
        kmalloc() buffers

      - Fix module PLT counting with !RANDOMIZE_BASE

      - Restrict CPU_BIG_ENDIAN to LLVM IAS 15.x or newer move
        synchronisation code out of the set_ptes() loop

      - More compact cpufeature displaying enabled cores

      - Kselftest updates for the new CPU features"

 * tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (83 commits)
  arm64: Restrict CPU_BIG_ENDIAN to GNU as or LLVM IAS 15.x or newer
  arm64: module: Fix PLT counting when CONFIG_RANDOMIZE_BASE=n
  arm64, irqchip/gic-v3, ACPI: Move MADT GICC enabled check into a helper
  perf: hisi: Fix use-after-free when register pmu fails
  drivers/perf: hisi_pcie: Initialize event->cpu only on success
  drivers/perf: hisi_pcie: Check the type first in pmu::event_init()
  arm64: cpufeature: Change DBM to display enabled cores
  arm64: cpufeature: Display the set of cores with a feature
  perf/arm-cmn: Enable per-DTC counter allocation
  perf/arm-cmn: Rework DTC counters (again)
  perf/arm-cmn: Fix DTC domain detection
  drivers: perf: arm_pmuv3: Drop some unused arguments from armv8_pmu_init()
  drivers: perf: arm_pmuv3: Read PMMIR_EL1 unconditionally
  drivers/perf: hisi: use cpuhp_state_remove_instance_nocalls() for hisi_hns3_pmu uninit process
  clocksource/drivers/arm_arch_timer: limit XGene-1 workaround
  arm64: Remove system_uses_lse_atomics()
  arm64: Mark the 'addr' argument to set_ptes() and __set_pte_at() as unused
  drivers/perf: xgene: Use device_get_match_data()
  perf/amlogic: add missing MODULE_DEVICE_TABLE
  arm64/mm: Hoist synchronization out of set_ptes() loop
  ...

1 files changed, 117 insertions, 30 deletions

diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 196533c362e1..be95b523c101 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -32,7 +32,9 @@
 #include <linux/irq_work.h>
 #include <linux/kernel_stat.h>
 #include <linux/kexec.h>
+#include <linux/kgdb.h>
 #include <linux/kvm_host.h>
+#include <linux/nmi.h>
 
 #include <asm/alternative.h>
 #include <asm/atomic.h>
@@ -72,13 +74,19 @@ enum ipi_msg_type {
 	IPI_CPU_CRASH_STOP,
 	IPI_TIMER,
 	IPI_IRQ_WORK,
-	IPI_WAKEUP,
-	NR_IPI
+	NR_IPI,
+	/*
+	 * Any enum >= NR_IPI and < MAX_IPI is special and not tracable
+	 * with trace_ipi_*
+	 */
+	IPI_CPU_BACKTRACE = NR_IPI,
+	IPI_KGDB_ROUNDUP,
+	MAX_IPI
 };
 
-static int ipi_irq_base __read_mostly;
-static int nr_ipi __read_mostly = NR_IPI;
-static struct irq_desc *ipi_desc[NR_IPI] __read_mostly;
+static int ipi_irq_base __ro_after_init;
+static int nr_ipi __ro_after_init = NR_IPI;
+static struct irq_desc *ipi_desc[MAX_IPI] __ro_after_init;
 
 static void ipi_setup(int cpu);
 
@@ -431,9 +439,10 @@ static void __init hyp_mode_check(void)
 void __init smp_cpus_done(unsigned int max_cpus)
 {
 	pr_info("SMP: Total of %d processors activated.\n", num_online_cpus());
-	setup_cpu_features();
+	setup_system_features();
 	hyp_mode_check();
 	apply_alternatives_all();
+	setup_user_features();
 	mark_linear_text_alias_ro();
 }
 
@@ -520,7 +529,7 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
 {
 	u64 hwid = processor->arm_mpidr;
 
-	if (!(processor->flags & ACPI_MADT_ENABLED)) {
+	if (!acpi_gicc_is_usable(processor)) {
 		pr_debug("skipping disabled CPU entry with 0x%llx MPIDR\n", hwid);
 		return;
 	}
@@ -764,7 +773,6 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = {
 	[IPI_CPU_CRASH_STOP]	= "CPU stop (for crash dump) interrupts",
 	[IPI_TIMER]		= "Timer broadcast interrupts",
 	[IPI_IRQ_WORK]		= "IRQ work interrupts",
-	[IPI_WAKEUP]		= "CPU wake-up interrupts",
 };
 
 static void smp_cross_call(const struct cpumask *target, unsigned int ipinr);
@@ -797,13 +805,6 @@ void arch_send_call_function_single_ipi(int cpu)
 	smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC);
 }
 
-#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL
-void arch_send_wakeup_ipi_mask(const struct cpumask *mask)
-{
-	smp_cross_call(mask, IPI_WAKEUP);
-}
-#endif
-
 #ifdef CONFIG_IRQ_WORK
 void arch_irq_work_raise(void)
 {
@@ -854,6 +855,38 @@ static void __noreturn ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs
 #endif
 }
 
+static void arm64_backtrace_ipi(cpumask_t *mask)
+{
+	__ipi_send_mask(ipi_desc[IPI_CPU_BACKTRACE], mask);
+}
+
+void arch_trigger_cpumask_backtrace(const cpumask_t *mask, int exclude_cpu)
+{
+	/*
+	 * NOTE: though nmi_trigger_cpumask_backtrace() has "nmi_" in the name,
+	 * nothing about it truly needs to be implemented using an NMI, it's
+	 * just that it's _allowed_ to work with NMIs. If ipi_should_be_nmi()
+	 * returned false our backtrace attempt will just use a regular IPI.
+	 */
+	nmi_trigger_cpumask_backtrace(mask, exclude_cpu, arm64_backtrace_ipi);
+}
+
+#ifdef CONFIG_KGDB
+void kgdb_roundup_cpus(void)
+{
+	int this_cpu = raw_smp_processor_id();
+	int cpu;
+
+	for_each_online_cpu(cpu) {
+		/* No need to roundup ourselves */
+		if (cpu == this_cpu)
+			continue;
+
+		__ipi_send_single(ipi_desc[IPI_KGDB_ROUNDUP], cpu);
+	}
+}
+#endif
+
 /*
  * Main handler for inter-processor interrupts
  */
@@ -897,13 +930,17 @@ static void do_handle_IPI(int ipinr)
 		break;
 #endif
 
-#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL
-	case IPI_WAKEUP:
-		WARN_ONCE(!acpi_parking_protocol_valid(cpu),
-			  "CPU%u: Wake-up IPI outside the ACPI parking protocol\n",
-			  cpu);
+	case IPI_CPU_BACKTRACE:
+		/*
+		 * NOTE: in some cases this _won't_ be NMI context. See the
+		 * comment in arch_trigger_cpumask_backtrace().
+		 */
+		nmi_cpu_backtrace(get_irq_regs());
+		break;
+
+	case IPI_KGDB_ROUNDUP:
+		kgdb_nmicallback(cpu, get_irq_regs());
 		break;
-#endif
 
 	default:
 		pr_crit("CPU%u: Unknown IPI message 0x%x\n", cpu, ipinr);
@@ -926,6 +963,25 @@ static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
 	__ipi_send_mask(ipi_desc[ipinr], target);
 }
 
+static bool ipi_should_be_nmi(enum ipi_msg_type ipi)
+{
+	DECLARE_STATIC_KEY_FALSE(supports_pseudo_nmis);
+
+	if (!system_uses_irq_prio_masking() ||
+	    !static_branch_likely(&supports_pseudo_nmis))
+		return false;
+
+	switch (ipi) {
+	case IPI_CPU_STOP:
+	case IPI_CPU_CRASH_STOP:
+	case IPI_CPU_BACKTRACE:
+	case IPI_KGDB_ROUNDUP:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static void ipi_setup(int cpu)
 {
 	int i;
@@ -933,8 +989,14 @@ static void ipi_setup(int cpu)
 	if (WARN_ON_ONCE(!ipi_irq_base))
 		return;
 
-	for (i = 0; i < nr_ipi; i++)
-		enable_percpu_irq(ipi_irq_base + i, 0);
+	for (i = 0; i < nr_ipi; i++) {
+		if (ipi_should_be_nmi(i)) {
+			prepare_percpu_nmi(ipi_irq_base + i);
+			enable_percpu_nmi(ipi_irq_base + i, 0);
+		} else {
+			enable_percpu_irq(ipi_irq_base + i, 0);
+		}
+	}
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -945,8 +1007,14 @@ static void ipi_teardown(int cpu)
 	if (WARN_ON_ONCE(!ipi_irq_base))
 		return;
 
-	for (i = 0; i < nr_ipi; i++)
-		disable_percpu_irq(ipi_irq_base + i);
+	for (i = 0; i < nr_ipi; i++) {
+		if (ipi_should_be_nmi(i)) {
+			disable_percpu_nmi(ipi_irq_base + i);
+			teardown_percpu_nmi(ipi_irq_base + i);
+		} else {
+			disable_percpu_irq(ipi_irq_base + i);
+		}
+	}
 }
 #endif
 
@@ -954,15 +1022,23 @@ void __init set_smp_ipi_range(int ipi_base, int n)
 {
 	int i;
 
-	WARN_ON(n < NR_IPI);
-	nr_ipi = min(n, NR_IPI);
+	WARN_ON(n < MAX_IPI);
+	nr_ipi = min(n, MAX_IPI);
 
 	for (i = 0; i < nr_ipi; i++) {
 		int err;
 
-		err = request_percpu_irq(ipi_base + i, ipi_handler,
-					 "IPI", &cpu_number);
-		WARN_ON(err);
+		if (ipi_should_be_nmi(i)) {
+			err = request_percpu_nmi(ipi_base + i, ipi_handler,
+						 "IPI", &cpu_number);
+			WARN(err, "Could not request IPI %d as NMI, err=%d\n",
+			     i, err);
+		} else {
+			err = request_percpu_irq(ipi_base + i, ipi_handler,
+						 "IPI", &cpu_number);
+			WARN(err, "Could not request IPI %d as IRQ, err=%d\n",
+			     i, err);
+		}
 
 		ipi_desc[i] = irq_to_desc(ipi_base + i);
 		irq_set_status_flags(ipi_base + i, IRQ_HIDDEN);
@@ -979,6 +1055,17 @@ void arch_smp_send_reschedule(int cpu)
 	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
 }
 
+#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL
+void arch_send_wakeup_ipi(unsigned int cpu)
+{
+	/*
+	 * We use a scheduler IPI to wake the CPU as this avoids the need for a
+	 * dedicated IPI and we can safely handle spurious scheduler IPIs.
+	 */
+	smp_send_reschedule(cpu);
+}
+#endif
+
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 void tick_broadcast(const struct cpumask *mask)
 {