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

Pull arm64 updates from Catalin Marinas:
 "Nothing major this time around.

  Apart from the usual perf/PMU updates, some page table cleanups, the
  notable features are average CPU frequency based on the AMUv1
  counters, CONFIG_HOTPLUG_SMT and MOPS instructions (memcpy/memset) in
  the uaccess routines.

  Perf and PMUs:

   - Support for the 'Rainier' CPU PMU from Arm

   - Preparatory driver changes and cleanups that pave the way for BRBE
     support

   - Support for partial virtualisation of the Apple-M1 PMU

   - Support for the second event filter in Arm CSPMU designs

   - Minor fixes and cleanups (CMN and DWC PMUs)

   - Enable EL2 requirements for FEAT_PMUv3p9

  Power, CPU topology:

   - Support for AMUv1-based average CPU frequency

   - Run-time SMT control wired up for arm64 (CONFIG_HOTPLUG_SMT). It
     adds a generic topology_is_primary_thread() function overridden by
     x86 and powerpc

  New(ish) features:

   - MOPS (memcpy/memset) support for the uaccess routines

  Security/confidential compute:

   - Fix the DMA address for devices used in Realms with Arm CCA. The
     CCA architecture uses the address bit to differentiate between
     shared and private addresses

   - Spectre-BHB: assume CPUs Linux doesn't know about vulnerable by
     default

  Memory management clean-ups:

   - Drop the P*D_TABLE_BIT definition in preparation for 128-bit PTEs

   - Some minor page table accessor clean-ups

   - PIE/POE (permission indirection/overlay) helpers clean-up

  Kselftests:

   - MTE: skip hugetlb tests if MTE is not supported on such mappings
     and user correct naming for sync/async tag checking modes

  Miscellaneous:

   - Add a PKEY_UNRESTRICTED definition as 0 to uapi (toolchain people
     request)

   - Sysreg updates for new register fields

   - CPU type info for some Qualcomm Kryo cores"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (72 commits)
  arm64: mm: Don't use %pK through printk
  perf/arm_cspmu: Fix missing io.h include
  arm64: errata: Add newer ARM cores to the spectre_bhb_loop_affected() lists
  arm64: cputype: Add MIDR_CORTEX_A76AE
  arm64: errata: Add KRYO 2XX/3XX/4XX silver cores to Spectre BHB safe list
  arm64: errata: Assume that unknown CPUs _are_ vulnerable to Spectre BHB
  arm64: errata: Add QCOM_KRYO_4XX_GOLD to the spectre_bhb_k24_list
  arm64/sysreg: Enforce whole word match for open/close tokens
  arm64/sysreg: Fix unbalanced closing block
  arm64: Kconfig: Enable HOTPLUG_SMT
  arm64: topology: Support SMT control on ACPI based system
  arch_topology: Support SMT control for OF based system
  cpu/SMT: Provide a default topology_is_primary_thread()
  arm64/mm: Define PTDESC_ORDER
  perf/arm_cspmu: Add PMEVFILT2R support
  perf/arm_cspmu: Generalise event filtering
  perf/arm_cspmu: Move register definitons to header
  arm64/kernel: Always use level 2 or higher for early mappings
  arm64/mm: Drop PXD_TABLE_BIT
  arm64/mm: Check pmd_table() in pmd_trans_huge()
  ...

1 files changed, 23 insertions, 3 deletions

diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 3ebe77566788..af0029d30dbe 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -11,6 +11,7 @@
 #include <linux/cleanup.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
+#include <linux/cpu_smt.h>
 #include <linux/device.h>
 #include <linux/of.h>
 #include <linux/slab.h>
@@ -28,7 +29,7 @@
 static DEFINE_PER_CPU(struct scale_freq_data __rcu *, sft_data);
 static struct cpumask scale_freq_counters_mask;
 static bool scale_freq_invariant;
-DEFINE_PER_CPU(unsigned long, capacity_freq_ref) = 1;
+DEFINE_PER_CPU(unsigned long, capacity_freq_ref) = 0;
 EXPORT_PER_CPU_SYMBOL_GPL(capacity_freq_ref);
 
 static bool supports_scale_freq_counters(const struct cpumask *cpus)
@@ -293,13 +294,15 @@ void topology_normalize_cpu_scale(void)
 
 	capacity_scale = 1;
 	for_each_possible_cpu(cpu) {
-		capacity = raw_capacity[cpu] * per_cpu(capacity_freq_ref, cpu);
+		capacity = raw_capacity[cpu] *
+			   (per_cpu(capacity_freq_ref, cpu) ?: 1);
 		capacity_scale = max(capacity, capacity_scale);
 	}
 
 	pr_debug("cpu_capacity: capacity_scale=%llu\n", capacity_scale);
 	for_each_possible_cpu(cpu) {
-		capacity = raw_capacity[cpu] * per_cpu(capacity_freq_ref, cpu);
+		capacity = raw_capacity[cpu] *
+			   (per_cpu(capacity_freq_ref, cpu) ?: 1);
 		capacity = div64_u64(capacity << SCHED_CAPACITY_SHIFT,
 			capacity_scale);
 		topology_set_cpu_scale(cpu, capacity);
@@ -506,6 +509,10 @@ core_initcall(free_raw_capacity);
 #endif
 
 #if defined(CONFIG_ARM64) || defined(CONFIG_RISCV)
+
+/* Used to enable the SMT control */
+static unsigned int max_smt_thread_num = 1;
+
 /*
  * This function returns the logic cpu number of the node.
  * There are basically three kinds of return values:
@@ -565,6 +572,8 @@ static int __init parse_core(struct device_node *core, int package_id,
 		i++;
 	} while (1);
 
+	max_smt_thread_num = max_t(unsigned int, max_smt_thread_num, i);
+
 	cpu = get_cpu_for_node(core);
 	if (cpu >= 0) {
 		if (!leaf) {
@@ -677,6 +686,17 @@ static int __init parse_socket(struct device_node *socket)
 	if (!has_socket)
 		ret = parse_cluster(socket, 0, -1, 0);
 
+	/*
+	 * Reset the max_smt_thread_num to 1 on failure. Since on failure
+	 * we need to notify the framework the SMT is not supported, but
+	 * max_smt_thread_num can be initialized to the SMT thread number
+	 * of the cores which are successfully parsed.
+	 */
+	if (ret)
+		max_smt_thread_num = 1;
+
+	cpu_smt_set_num_threads(max_smt_thread_num, max_smt_thread_num);
+
 	return ret;
 }