Merge remote-tracking branch 'kvmarm/kvm-arm64/stolen-time' into kvmarm-master/next

12 files changed, 251 insertions, 73 deletions

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 019bc560edc1..b36dae9ee5f9 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -44,6 +44,7 @@
 	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_IRQ_PENDING	KVM_ARCH_REQ(1)
 #define KVM_REQ_VCPU_RESET	KVM_ARCH_REQ(2)
+#define KVM_REQ_RECORD_STEAL	KVM_ARCH_REQ(3)
 
 DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
@@ -346,6 +347,13 @@ struct kvm_vcpu_arch {
 	/* True when deferrable sysregs are loaded on the physical CPU,
 	 * see kvm_vcpu_load_sysregs and kvm_vcpu_put_sysregs. */
 	bool sysregs_loaded_on_cpu;
+
+	/* Guest PV state */
+	struct {
+		u64 steal;
+		u64 last_steal;
+		gpa_t base;
+	} steal;
 };
 
 /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */
@@ -486,6 +494,27 @@ void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run,
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
+long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu);
+gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu);
+void kvm_update_stolen_time(struct kvm_vcpu *vcpu);
+
+int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr);
+int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr);
+int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr);
+
+static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch)
+{
+	vcpu_arch->steal.base = GPA_INVALID;
+}
+
+static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch)
+{
+	return (vcpu_arch->steal.base != GPA_INVALID);
+}
+
 void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 syndrome);
 
 struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);
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/include/asm/pvclock-abi.h b/arch/arm64/include/asm/pvclock-abi.h
new file mode 100644
index 000000000000..c4f1c0a0789c
--- /dev/null
+++ b/arch/arm64/include/asm/pvclock-abi.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2019 Arm Ltd. */
+
+#ifndef __ASM_PVCLOCK_ABI_H
+#define __ASM_PVCLOCK_ABI_H
+
+/* The below structure is defined in ARM DEN0057A */
+
+struct pvclock_vcpu_stolen_time {
+	__le32 revision;
+	__le32 attributes;
+	__le64 stolen_time;
+	/* Structure must be 64 byte aligned, pad to that size */
+	u8 padding[48];
+} __packed;
+
+#endif
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index d49c17a80491..820e5751ada7 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -324,6 +324,8 @@ struct kvm_vcpu_events {
 #define KVM_ARM_VCPU_TIMER_CTRL		1
 #define   KVM_ARM_VCPU_TIMER_IRQ_VTIMER		0
 #define   KVM_ARM_VCPU_TIMER_IRQ_PTIMER		1
+#define KVM_ARM_VCPU_PVTIME_CTRL	2
+#define   KVM_ARM_VCPU_PVTIME_IPA	0
 
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_VCPU2_SHIFT		28
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index f593f4cffc0d..401246e095e7 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -6,7 +6,6 @@
  */
 
 #include <linux/arm-smccc.h>
-#include <linux/psci.h>
 #include <linux/types.h>
 #include <linux/cpu.h>
 #include <asm/cpu.h>
@@ -166,9 +165,7 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn,
 }
 #endif	/* CONFIG_KVM_INDIRECT_VECTORS */
 
-#include <uapi/linux/psci.h>
 #include <linux/arm-smccc.h>
-#include <linux/psci.h>
 
 static void call_smc_arch_workaround_1(void)
 {
@@ -212,43 +209,31 @@ static int detect_harden_bp_fw(void)
 	struct arm_smccc_res res;
 	u32 midr = read_cpuid_id();
 
-	if (psci_ops.smccc_version == SMCCC_VERSION_1_0)
+	arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+			     ARM_SMCCC_ARCH_WORKAROUND_1, &res);
+
+	switch ((int)res.a0) {
+	case 1:
+		/* Firmware says we're just fine */
+		return 0;
+	case 0:
+		break;
+	default:
 		return -1;
+	}
 
-	switch (psci_ops.conduit) {
-	case PSCI_CONDUIT_HVC:
-		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
-				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-		switch ((int)res.a0) {
-		case 1:
-			/* Firmware says we're just fine */
-			return 0;
-		case 0:
-			cb = call_hvc_arch_workaround_1;
-			/* This is a guest, no need to patch KVM vectors */
-			smccc_start = NULL;
-			smccc_end = NULL;
-			break;
-		default:
-			return -1;
-		}
+	switch (arm_smccc_1_1_get_conduit()) {
+	case SMCCC_CONDUIT_HVC:
+		cb = call_hvc_arch_workaround_1;
+		/* This is a guest, no need to patch KVM vectors */
+		smccc_start = NULL;
+		smccc_end = NULL;
 		break;
 
-	case PSCI_CONDUIT_SMC:
-		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
-				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-		switch ((int)res.a0) {
-		case 1:
-			/* Firmware says we're just fine */
-			return 0;
-		case 0:
-			cb = call_smc_arch_workaround_1;
-			smccc_start = __smccc_workaround_1_smc_start;
-			smccc_end = __smccc_workaround_1_smc_end;
-			break;
-		default:
-			return -1;
-		}
+	case SMCCC_CONDUIT_SMC:
+		cb = call_smc_arch_workaround_1;
+		smccc_start = __smccc_workaround_1_smc_start;
+		smccc_end = __smccc_workaround_1_smc_end;
 		break;
 
 	default:
@@ -308,11 +293,11 @@ void __init arm64_update_smccc_conduit(struct alt_instr *alt,
 
 	BUG_ON(nr_inst != 1);
 
-	switch (psci_ops.conduit) {
-	case PSCI_CONDUIT_HVC:
+	switch (arm_smccc_1_1_get_conduit()) {
+	case SMCCC_CONDUIT_HVC:
 		insn = aarch64_insn_get_hvc_value();
 		break;
-	case PSCI_CONDUIT_SMC:
+	case SMCCC_CONDUIT_SMC:
 		insn = aarch64_insn_get_smc_value();
 		break;
 	default:
@@ -338,6 +323,8 @@ void __init arm64_enable_wa2_handling(struct alt_instr *alt,
 
 void arm64_set_ssbd_mitigation(bool state)
 {
+	int conduit;
+
 	if (!IS_ENABLED(CONFIG_ARM64_SSBD)) {
 		pr_info_once("SSBD disabled by kernel configuration\n");
 		return;
@@ -351,19 +338,10 @@ void arm64_set_ssbd_mitigation(bool state)
 		return;
 	}
 
-	switch (psci_ops.conduit) {
-	case PSCI_CONDUIT_HVC:
-		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL);
-		break;
-
-	case PSCI_CONDUIT_SMC:
-		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL);
-		break;
+	conduit = arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_WORKAROUND_2, state,
+				       NULL);
 
-	default:
-		WARN_ON_ONCE(1);
-		break;
-	}
+	WARN_ON_ONCE(conduit == SMCCC_CONDUIT_NONE);
 }
 
 static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
@@ -373,6 +351,7 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
 	bool required = true;
 	s32 val;
 	bool this_cpu_safe = false;
+	int conduit;
 
 	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
 
@@ -390,25 +369,10 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
 		goto out_printmsg;
 	}
 
-	if (psci_ops.smccc_version == SMCCC_VERSION_1_0) {
-		ssbd_state = ARM64_SSBD_UNKNOWN;
-		if (!this_cpu_safe)
-			__ssb_safe = false;
-		return false;
-	}
-
-	switch (psci_ops.conduit) {
-	case PSCI_CONDUIT_HVC:
-		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
-				  ARM_SMCCC_ARCH_WORKAROUND_2, &res);
-		break;
+	conduit = arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+				       ARM_SMCCC_ARCH_WORKAROUND_2, &res);
 
-	case PSCI_CONDUIT_SMC:
-		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
-				  ARM_SMCCC_ARCH_WORKAROUND_2, &res);
-		break;
-
-	default:
+	if (conduit == SMCCC_CONDUIT_NONE) {
 		ssbd_state = ARM64_SSBD_UNKNOWN;
 		if (!this_cpu_safe)
 			__ssb_safe = false;
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 <stefano.stabellini@eu.citrix.com>
  */
 
+#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;
+}
diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
index ea94cf8f9dc6..d6259dac62b6 100644
--- a/arch/arm64/kernel/sdei.c
+++ b/arch/arm64/kernel/sdei.c
@@ -2,6 +2,7 @@
 // Copyright (C) 2017 Arm Ltd.
 #define pr_fmt(fmt) "sdei: " fmt
 
+#include <linux/arm-smccc.h>
 #include <linux/arm_sdei.h>
 #include <linux/hardirq.h>
 #include <linux/irqflags.h>
@@ -161,7 +162,7 @@ unsigned long sdei_arch_get_entry_point(int conduit)
 			return 0;
 	}
 
-	sdei_exit_mode = (conduit == CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC;
+	sdei_exit_mode = (conduit == SMCCC_CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC;
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	if (arm64_kernel_unmapped_at_el0()) {
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 <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();
 }
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index a67121d419a2..a475c68cbfec 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -21,6 +21,8 @@ if VIRTUALIZATION
 config KVM
 	bool "Kernel-based Virtual Machine (KVM) support"
 	depends on OF
+	# for TASKSTATS/TASK_DELAY_ACCT:
+	depends on NET && MULTIUSER
 	select MMU_NOTIFIER
 	select PREEMPT_NOTIFIERS
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
@@ -39,6 +41,8 @@ config KVM
 	select IRQ_BYPASS_MANAGER
 	select HAVE_KVM_IRQ_BYPASS
 	select HAVE_KVM_VCPU_RUN_PID_CHANGE
+	select TASKSTATS
+	select TASK_DELAY_ACCT
 	---help---
 	  Support hosting virtualized guest machines.
 	  We don't support KVM with 16K page tables yet, due to the multiple
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 3ac1a64d2fb9..5ffbdc39e780 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -13,6 +13,8 @@ obj-$(CONFIG_KVM_ARM_HOST) += hyp/
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arm.o $(KVM)/arm/mmu.o $(KVM)/arm/mmio.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/psci.o $(KVM)/arm/perf.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hypercalls.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/pvtime.o
 
 kvm-$(CONFIG_KVM_ARM_HOST) += inject_fault.o regmap.o va_layout.o
 kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index ca613a44c6ec..cd4429bfe5dc 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -868,6 +868,9 @@ int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
 	case KVM_ARM_VCPU_TIMER_CTRL:
 		ret = kvm_arm_timer_set_attr(vcpu, attr);
 		break;
+	case KVM_ARM_VCPU_PVTIME_CTRL:
+		ret = kvm_arm_pvtime_set_attr(vcpu, attr);
+		break;
 	default:
 		ret = -ENXIO;
 		break;
@@ -888,6 +891,9 @@ int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
 	case KVM_ARM_VCPU_TIMER_CTRL:
 		ret = kvm_arm_timer_get_attr(vcpu, attr);
 		break;
+	case KVM_ARM_VCPU_PVTIME_CTRL:
+		ret = kvm_arm_pvtime_get_attr(vcpu, attr);
+		break;
 	default:
 		ret = -ENXIO;
 		break;
@@ -908,6 +914,9 @@ int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
 	case KVM_ARM_VCPU_TIMER_CTRL:
 		ret = kvm_arm_timer_has_attr(vcpu, attr);
 		break;
+	case KVM_ARM_VCPU_PVTIME_CTRL:
+		ret = kvm_arm_pvtime_has_attr(vcpu, attr);
+		break;
 	default:
 		ret = -ENXIO;
 		break;
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 706cca23f0d2..aacfc55de44c 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -11,8 +11,6 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 
-#include <kvm/arm_psci.h>
-
 #include <asm/esr.h>
 #include <asm/exception.h>
 #include <asm/kvm_asm.h>
@@ -22,6 +20,8 @@
 #include <asm/debug-monitors.h>
 #include <asm/traps.h>
 
+#include <kvm/arm_hypercalls.h>
+
 #define CREATE_TRACE_POINTS
 #include "trace.h"