From e0685fa228fdaf386f82ac0d64b2d6f3e0ddd588 Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 21 Oct 2019 16:28:23 +0100 Subject: [PATCH] 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 Signed-off-by: Marc Zyngier --- .../admin-guide/kernel-parameters.txt | 6 +- arch/arm64/include/asm/paravirt.h | 9 +- arch/arm64/kernel/paravirt.c | 140 ++++++++++++++++++ arch/arm64/kernel/time.c | 3 + include/linux/cpuhotplug.h | 1 + 5 files changed, 155 insertions(+), 4 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index a84a83f8881e..19f465530e86 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/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. diff --git a/arch/arm64/include/asm/paravirt.h b/arch/arm64/include/asm/paravirt.h index 799d9dd6f7cc..cf3a0fd7c1a7 100644 --- a/arch/arm64/include/asm/paravirt.h +++ b/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 diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c index 4cfed91fe256..1ef702b0be2d 100644 --- a/arch/arm64/kernel/paravirt.c +++ b/arch/arm64/kernel/paravirt.c @@ -6,13 +6,153 @@ * Author: Stefano Stabellini */ +#define pr_fmt(fmt) "arm-pv: " fmt + +#include +#include #include +#include #include +#include +#include +#include +#include #include + #include +#include +#include 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(¶virt_steal_enabled); + if (steal_acc) + static_key_slow_inc(¶virt_steal_rq_enabled); + + pr_info("using stolen time PV\n"); + + return 0; +} diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c index 0b2946414dc9..73f06d4b3aae 100644 --- a/arch/arm64/kernel/time.c +++ b/arch/arm64/kernel/time.c @@ -30,6 +30,7 @@ #include #include +#include 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(); } diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 068793a619ca..89d75edb5750 100644 --- a/include/linux/cpuhotplug.h +++ b/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, -- 2.30.2