arm64: Retrieve stolen time as paravirtualized guest

Enable paravirtualization features when running under a hypervisor
supporting the PV_TIME_ST hypercall.

For each (v)CPU, we ask the hypervisor for the location of a shared
page which the hypervisor will use to report stolen time to us. We set
pv_time_ops to the stolen time function which simply reads the stolen
value from the shared page for a VCPU. We guarantee single-copy
atomicity using READ_ONCE which means we can also read the stolen
time for another VCPU than the currently running one while it is
potentially being updated by the hypervisor.

Signed-off-by: Steven Price <[email protected]>
Signed-off-by: Marc Zyngier <[email protected]>

Author: Steven Price

Documentation/admin-guide/kernel-parameters.txt

@@ -3083,9 +3083,9 @@
 			[X86,PV_OPS] Disable paravirtualized VMware scheduler
 			clock and use the default one.
 
-	no-steal-acc	[X86,KVM] Disable paravirtualized steal time accounting.
-			steal time is computed, but won't influence scheduler
-			behaviour
+	no-steal-acc	[X86,KVM,ARM64] Disable paravirtualized steal time
+			accounting. steal time is computed, but won't
+			influence scheduler behaviour
 
 	nolapic		[X86-32,APIC] Do not enable or use the local APIC.
 

arch/arm64/include/asm/paravirt.h

@@ -21,6 +21,13 @@ static inline u64 paravirt_steal_clock(int cpu)
 {
 	return pv_ops.time.steal_clock(cpu);
 }
-#endif
+
+int __init pv_time_init(void);
+
+#else
+
+#define pv_time_init() do {} while (0)
+
+#endif // CONFIG_PARAVIRT
 
 #endif

arch/arm64/kernel/paravirt.c

@@ -6,13 +6,153 @@
  * Author: Stefano Stabellini <[email protected]>
  */
 
+#define pr_fmt(fmt) "arm-pv: " fmt
+
+#include <linux/arm-smccc.h>
+#include <linux/cpuhotplug.h>
 #include <linux/export.h>
+#include <linux/io.h>
 #include <linux/jump_label.h>
+#include <linux/printk.h>
+#include <linux/psci.h>
+#include <linux/reboot.h>
+#include <linux/slab.h>
 #include <linux/types.h>
+
 #include <asm/paravirt.h>
+#include <asm/pvclock-abi.h>
+#include <asm/smp_plat.h>
 
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
 
 struct paravirt_patch_template pv_ops;
 EXPORT_SYMBOL_GPL(pv_ops);
+
+struct pv_time_stolen_time_region {
+	struct pvclock_vcpu_stolen_time *kaddr;
+};
+
+static DEFINE_PER_CPU(struct pv_time_stolen_time_region, stolen_time_region);
+
+static bool steal_acc = true;
+static int __init parse_no_stealacc(char *arg)
+{
+	steal_acc = false;
+	return 0;
+}
+
+early_param("no-steal-acc", parse_no_stealacc);
+
+/* return stolen time in ns by asking the hypervisor */
+static u64 pv_steal_clock(int cpu)
+{
+	struct pv_time_stolen_time_region *reg;
+
+	reg = per_cpu_ptr(&stolen_time_region, cpu);
+	if (!reg->kaddr) {
+		pr_warn_once("stolen time enabled but not configured for cpu %d\n",
+			     cpu);
+		return 0;
+	}
+
+	return le64_to_cpu(READ_ONCE(reg->kaddr->stolen_time));
+}
+
+static int stolen_time_dying_cpu(unsigned int cpu)
+{
+	struct pv_time_stolen_time_region *reg;
+
+	reg = this_cpu_ptr(&stolen_time_region);
+	if (!reg->kaddr)
+		return 0;
+
+	memunmap(reg->kaddr);
+	memset(reg, 0, sizeof(*reg));
+
+	return 0;
+}
+
+static int init_stolen_time_cpu(unsigned int cpu)
+{
+	struct pv_time_stolen_time_region *reg;
+	struct arm_smccc_res res;
+
+	reg = this_cpu_ptr(&stolen_time_region);
+
+	arm_smccc_1_1_invoke(ARM_SMCCC_HV_PV_TIME_ST, &res);
+
+	if (res.a0 == SMCCC_RET_NOT_SUPPORTED)
+		return -EINVAL;
+
+	reg->kaddr = memremap(res.a0,
+			      sizeof(struct pvclock_vcpu_stolen_time),
+			      MEMREMAP_WB);
+
+	if (!reg->kaddr) {
+		pr_warn("Failed to map stolen time data structure\n");
+		return -ENOMEM;
+	}
+
+	if (le32_to_cpu(reg->kaddr->revision) != 0 ||
+	    le32_to_cpu(reg->kaddr->attributes) != 0) {
+		pr_warn_once("Unexpected revision or attributes in stolen time data\n");
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
+static int pv_time_init_stolen_time(void)
+{
+	int ret;
+
+	ret = cpuhp_setup_state(CPUHP_AP_ARM_KVMPV_STARTING,
+				"hypervisor/arm/pvtime:starting",
+				init_stolen_time_cpu, stolen_time_dying_cpu);
+	if (ret < 0)
+		return ret;
+	return 0;
+}
+
+static bool has_pv_steal_clock(void)
+{
+	struct arm_smccc_res res;
+
+	/* To detect the presence of PV time support we require SMCCC 1.1+ */
+	if (psci_ops.smccc_version < SMCCC_VERSION_1_1)
+		return false;
+
+	arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+			     ARM_SMCCC_HV_PV_TIME_FEATURES, &res);
+
+	if (res.a0 != SMCCC_RET_SUCCESS)
+		return false;
+
+	arm_smccc_1_1_invoke(ARM_SMCCC_HV_PV_TIME_FEATURES,
+			     ARM_SMCCC_HV_PV_TIME_ST, &res);
+
+	return (res.a0 == SMCCC_RET_SUCCESS);
+}
+
+int __init pv_time_init(void)
+{
+	int ret;
+
+	if (!has_pv_steal_clock())
+		return 0;
+
+	ret = pv_time_init_stolen_time();
+	if (ret)
+		return ret;
+
+	pv_ops.time.steal_clock = pv_steal_clock;
+
+	static_key_slow_inc(&paravirt_steal_enabled);
+	if (steal_acc)
+		static_key_slow_inc(&paravirt_steal_rq_enabled);
+
+	pr_info("using stolen time PV\n");
+
+	return 0;
+}

arch/arm64/kernel/time.c

@@ -30,6 +30,7 @@
 
 #include <asm/thread_info.h>
 #include <asm/stacktrace.h>
+#include <asm/paravirt.h>
 
 unsigned long profile_pc(struct pt_regs *regs)
 {
@@ -65,4 +66,6 @@ void __init time_init(void)
 
 	/* Calibrate the delay loop directly */
 	lpj_fine = arch_timer_rate / HZ;
+
+	pv_time_init();
 }

include/linux/cpuhotplug.h

@@ -136,6 +136,7 @@ enum cpuhp_state {
 	/* Must be the last timer callback */
 	CPUHP_AP_DUMMY_TIMER_STARTING,
 	CPUHP_AP_ARM_XEN_STARTING,
+	CPUHP_AP_ARM_KVMPV_STARTING,
 	CPUHP_AP_ARM_CORESIGHT_STARTING,
 	CPUHP_AP_ARM64_ISNDEP_STARTING,
 	CPUHP_AP_SMPCFD_DYING,