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

Pull arm64 updates from Will Deacon:
 "Although there isn't tonnes of code in terms of line count, there are
  a fair few headline features which I've noted both in the tag and also
  in the merge commits when I pulled everything together.

  The part I'm most pleased with is that we had 35 contributors this
  time around, which feels like a big jump from the usual small group of
  core arm64 arch developers. Hopefully they all enjoyed it so much that
  they'll continue to contribute, but we'll see.

  It's probably worth highlighting that we've pulled in a branch from
  the risc-v folks which moves our CPU topology code out to where it can
  be shared with others.

  Summary:

   - 52-bit virtual addressing in the kernel

   - New ABI to allow tagged user pointers to be dereferenced by
     syscalls

   - Early RNG seeding by the bootloader

   - Improve robustness of SMP boot

   - Fix TLB invalidation in light of recent architectural
     clarifications

   - Support for i.MX8 DDR PMU

   - Remove direct LSE instruction patching in favour of static keys

   - Function error injection using kprobes

   - Support for the PPTT "thread" flag introduced by ACPI 6.3

   - Move PSCI idle code into proper cpuidle driver

   - Relaxation of implicit I/O memory barriers

   - Build with RELR relocations when toolchain supports them

   - Numerous cleanups and non-critical fixes"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (114 commits)
  arm64: remove __iounmap
  arm64: atomics: Use K constraint when toolchain appears to support it
  arm64: atomics: Undefine internal macros after use
  arm64: lse: Make ARM64_LSE_ATOMICS depend on JUMP_LABEL
  arm64: asm: Kill 'asm/atomic_arch.h'
  arm64: lse: Remove unused 'alt_lse' assembly macro
  arm64: atomics: Remove atomic_ll_sc compilation unit
  arm64: avoid using hard-coded registers for LSE atomics
  arm64: atomics: avoid out-of-line ll/sc atomics
  arm64: Use correct ll/sc atomic constraints
  jump_label: Don't warn on __exit jump entries
  docs/perf: Add documentation for the i.MX8 DDR PMU
  perf/imx_ddr: Add support for AXI ID filtering
  arm64: kpti: ensure patched kernel text is fetched from PoU
  arm64: fix fixmap copy for 16K pages and 48-bit VA
  perf/smmuv3: Validate groups for global filtering
  perf/smmuv3: Validate group size
  arm64: Relax Documentation/arm64/tagged-pointers.rst
  arm64: kvm: Replace hardcoded '1' with SYS_PAR_EL1_F
  arm64: mm: Ignore spurious translation faults taken from the kernel
  ...

2 files changed, 299 insertions, 1 deletions

diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index dc404492381d..28b92e3cc570 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -202,7 +202,7 @@ config GENERIC_ARCH_TOPOLOGY
 	help
 	  Enable support for architectures common topology code: e.g., parsing
 	  CPU capacity information from DT, usage of such information for
-	  appropriate scaling, sysfs interface for changing capacity values at
+	  appropriate scaling, sysfs interface for reading capacity values at
 	  runtime.
 
 endmenu
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 63c1e76739f1..b54d241a2ff5 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -15,6 +15,11 @@
 #include <linux/string.h>
 #include <linux/sched/topology.h>
 #include <linux/cpuset.h>
+#include <linux/cpumask.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
 
 DEFINE_PER_CPU(unsigned long, freq_scale) = SCHED_CAPACITY_SCALE;
 
@@ -241,3 +246,296 @@ static void parsing_done_workfn(struct work_struct *work)
 #else
 core_initcall(free_raw_capacity);
 #endif
+
+#if defined(CONFIG_ARM64) || defined(CONFIG_RISCV)
+static int __init get_cpu_for_node(struct device_node *node)
+{
+	struct device_node *cpu_node;
+	int cpu;
+
+	cpu_node = of_parse_phandle(node, "cpu", 0);
+	if (!cpu_node)
+		return -1;
+
+	cpu = of_cpu_node_to_id(cpu_node);
+	if (cpu >= 0)
+		topology_parse_cpu_capacity(cpu_node, cpu);
+	else
+		pr_crit("Unable to find CPU node for %pOF\n", cpu_node);
+
+	of_node_put(cpu_node);
+	return cpu;
+}
+
+static int __init parse_core(struct device_node *core, int package_id,
+			     int core_id)
+{
+	char name[10];
+	bool leaf = true;
+	int i = 0;
+	int cpu;
+	struct device_node *t;
+
+	do {
+		snprintf(name, sizeof(name), "thread%d", i);
+		t = of_get_child_by_name(core, name);
+		if (t) {
+			leaf = false;
+			cpu = get_cpu_for_node(t);
+			if (cpu >= 0) {
+				cpu_topology[cpu].package_id = package_id;
+				cpu_topology[cpu].core_id = core_id;
+				cpu_topology[cpu].thread_id = i;
+			} else {
+				pr_err("%pOF: Can't get CPU for thread\n",
+				       t);
+				of_node_put(t);
+				return -EINVAL;
+			}
+			of_node_put(t);
+		}
+		i++;
+	} while (t);
+
+	cpu = get_cpu_for_node(core);
+	if (cpu >= 0) {
+		if (!leaf) {
+			pr_err("%pOF: Core has both threads and CPU\n",
+			       core);
+			return -EINVAL;
+		}
+
+		cpu_topology[cpu].package_id = package_id;
+		cpu_topology[cpu].core_id = core_id;
+	} else if (leaf) {
+		pr_err("%pOF: Can't get CPU for leaf core\n", core);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int __init parse_cluster(struct device_node *cluster, int depth)
+{
+	char name[10];
+	bool leaf = true;
+	bool has_cores = false;
+	struct device_node *c;
+	static int package_id __initdata;
+	int core_id = 0;
+	int i, ret;
+
+	/*
+	 * First check for child clusters; we currently ignore any
+	 * information about the nesting of clusters and present the
+	 * scheduler with a flat list of them.
+	 */
+	i = 0;
+	do {
+		snprintf(name, sizeof(name), "cluster%d", i);
+		c = of_get_child_by_name(cluster, name);
+		if (c) {
+			leaf = false;
+			ret = parse_cluster(c, depth + 1);
+			of_node_put(c);
+			if (ret != 0)
+				return ret;
+		}
+		i++;
+	} while (c);
+
+	/* Now check for cores */
+	i = 0;
+	do {
+		snprintf(name, sizeof(name), "core%d", i);
+		c = of_get_child_by_name(cluster, name);
+		if (c) {
+			has_cores = true;
+
+			if (depth == 0) {
+				pr_err("%pOF: cpu-map children should be clusters\n",
+				       c);
+				of_node_put(c);
+				return -EINVAL;
+			}
+
+			if (leaf) {
+				ret = parse_core(c, package_id, core_id++);
+			} else {
+				pr_err("%pOF: Non-leaf cluster with core %s\n",
+				       cluster, name);
+				ret = -EINVAL;
+			}
+
+			of_node_put(c);
+			if (ret != 0)
+				return ret;
+		}
+		i++;
+	} while (c);
+
+	if (leaf && !has_cores)
+		pr_warn("%pOF: empty cluster\n", cluster);
+
+	if (leaf)
+		package_id++;
+
+	return 0;
+}
+
+static int __init parse_dt_topology(void)
+{
+	struct device_node *cn, *map;
+	int ret = 0;
+	int cpu;
+
+	cn = of_find_node_by_path("/cpus");
+	if (!cn) {
+		pr_err("No CPU information found in DT\n");
+		return 0;
+	}
+
+	/*
+	 * When topology is provided cpu-map is essentially a root
+	 * cluster with restricted subnodes.
+	 */
+	map = of_get_child_by_name(cn, "cpu-map");
+	if (!map)
+		goto out;
+
+	ret = parse_cluster(map, 0);
+	if (ret != 0)
+		goto out_map;
+
+	topology_normalize_cpu_scale();
+
+	/*
+	 * Check that all cores are in the topology; the SMP code will
+	 * only mark cores described in the DT as possible.
+	 */
+	for_each_possible_cpu(cpu)
+		if (cpu_topology[cpu].package_id == -1)
+			ret = -EINVAL;
+
+out_map:
+	of_node_put(map);
+out:
+	of_node_put(cn);
+	return ret;
+}
+#endif
+
+/*
+ * cpu topology table
+ */
+struct cpu_topology cpu_topology[NR_CPUS];
+EXPORT_SYMBOL_GPL(cpu_topology);
+
+const struct cpumask *cpu_coregroup_mask(int cpu)
+{
+	const cpumask_t *core_mask = cpumask_of_node(cpu_to_node(cpu));
+
+	/* Find the smaller of NUMA, core or LLC siblings */
+	if (cpumask_subset(&cpu_topology[cpu].core_sibling, core_mask)) {
+		/* not numa in package, lets use the package siblings */
+		core_mask = &cpu_topology[cpu].core_sibling;
+	}
+	if (cpu_topology[cpu].llc_id != -1) {
+		if (cpumask_subset(&cpu_topology[cpu].llc_sibling, core_mask))
+			core_mask = &cpu_topology[cpu].llc_sibling;
+	}
+
+	return core_mask;
+}
+
+void update_siblings_masks(unsigned int cpuid)
+{
+	struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
+	int cpu;
+
+	/* update core and thread sibling masks */
+	for_each_online_cpu(cpu) {
+		cpu_topo = &cpu_topology[cpu];
+
+		if (cpuid_topo->llc_id == cpu_topo->llc_id) {
+			cpumask_set_cpu(cpu, &cpuid_topo->llc_sibling);
+			cpumask_set_cpu(cpuid, &cpu_topo->llc_sibling);
+		}
+
+		if (cpuid_topo->package_id != cpu_topo->package_id)
+			continue;
+
+		cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
+		cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
+
+		if (cpuid_topo->core_id != cpu_topo->core_id)
+			continue;
+
+		cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
+		cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
+	}
+}
+
+static void clear_cpu_topology(int cpu)
+{
+	struct cpu_topology *cpu_topo = &cpu_topology[cpu];
+
+	cpumask_clear(&cpu_topo->llc_sibling);
+	cpumask_set_cpu(cpu, &cpu_topo->llc_sibling);
+
+	cpumask_clear(&cpu_topo->core_sibling);
+	cpumask_set_cpu(cpu, &cpu_topo->core_sibling);
+	cpumask_clear(&cpu_topo->thread_sibling);
+	cpumask_set_cpu(cpu, &cpu_topo->thread_sibling);
+}
+
+void __init reset_cpu_topology(void)
+{
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct cpu_topology *cpu_topo = &cpu_topology[cpu];
+
+		cpu_topo->thread_id = -1;
+		cpu_topo->core_id = -1;
+		cpu_topo->package_id = -1;
+		cpu_topo->llc_id = -1;
+
+		clear_cpu_topology(cpu);
+	}
+}
+
+void remove_cpu_topology(unsigned int cpu)
+{
+	int sibling;
+
+	for_each_cpu(sibling, topology_core_cpumask(cpu))
+		cpumask_clear_cpu(cpu, topology_core_cpumask(sibling));
+	for_each_cpu(sibling, topology_sibling_cpumask(cpu))
+		cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling));
+	for_each_cpu(sibling, topology_llc_cpumask(cpu))
+		cpumask_clear_cpu(cpu, topology_llc_cpumask(sibling));
+
+	clear_cpu_topology(cpu);
+}
+
+__weak int __init parse_acpi_topology(void)
+{
+	return 0;
+}
+
+#if defined(CONFIG_ARM64) || defined(CONFIG_RISCV)
+void __init init_cpu_topology(void)
+{
+	reset_cpu_topology();
+
+	/*
+	 * Discard anything that was parsed if we hit an error so we
+	 * don't use partial information.
+	 */
+	if (parse_acpi_topology())
+		reset_cpu_topology();
+	else if (of_have_populated_dt() && parse_dt_topology())
+		reset_cpu_topology();
+}
+#endif