1 files changed, 105 insertions, 158 deletions

diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index bf8d1eb7fca3..1e6764648af3 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -23,30 +23,57 @@
 #include <asm/apic.h>
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
-#include <linux/memblock.h>
+#include <linux/cpuhotplug.h>
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
 
+#include <asm/hypervisor.h>
 #include <asm/mem_encrypt.h>
 #include <asm/x86_init.h>
 #include <asm/reboot.h>
 #include <asm/kvmclock.h>
 
-static int kvmclock __ro_after_init = 1;
-static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
-static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
-static u64 kvm_sched_clock_offset;
+static int kvmclock __initdata = 1;
+static int kvmclock_vsyscall __initdata = 1;
+static int msr_kvm_system_time __ro_after_init = MSR_KVM_SYSTEM_TIME;
+static int msr_kvm_wall_clock __ro_after_init = MSR_KVM_WALL_CLOCK;
+static u64 kvm_sched_clock_offset __ro_after_init;
 
-static int parse_no_kvmclock(char *arg)
+static int __init parse_no_kvmclock(char *arg)
 {
 	kvmclock = 0;
 	return 0;
 }
 early_param("no-kvmclock", parse_no_kvmclock);
 
-/* The hypervisor will put information about time periodically here */
-static struct pvclock_vsyscall_time_info *hv_clock;
-static struct pvclock_wall_clock *wall_clock;
+static int __init parse_no_kvmclock_vsyscall(char *arg)
+{
+	kvmclock_vsyscall = 0;
+	return 0;
+}
+early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall);
+
+/* Aligned to page sizes to match whats mapped via vsyscalls to userspace */
+#define HV_CLOCK_SIZE	(sizeof(struct pvclock_vsyscall_time_info) * NR_CPUS)
+#define HVC_BOOT_ARRAY_SIZE \
+	(PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info))
+
+static struct pvclock_vsyscall_time_info
+			hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __aligned(PAGE_SIZE);
+static struct pvclock_wall_clock wall_clock;
+static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
+
+static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
+{
+	return &this_cpu_read(hv_clock_per_cpu)->pvti;
+}
+
+static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void)
+{
+	return this_cpu_read(hv_clock_per_cpu);
+}
 
 /*
  * The wallclock is the time of day when we booted. Since then, some time may
@@ -55,21 +82,10 @@ static struct pvclock_wall_clock *wall_clock;
  */
 static void kvm_get_wallclock(struct timespec64 *now)
 {
-	struct pvclock_vcpu_time_info *vcpu_time;
-	int low, high;
-	int cpu;
-
-	low = (int)slow_virt_to_phys(wall_clock);
-	high = ((u64)slow_virt_to_phys(wall_clock) >> 32);
-
-	native_write_msr(msr_kvm_wall_clock, low, high);
-
-	cpu = get_cpu();
-
-	vcpu_time = &hv_clock[cpu].pvti;
-	pvclock_read_wallclock(wall_clock, vcpu_time, now);
-
-	put_cpu();
+	wrmsrl(msr_kvm_wall_clock, slow_virt_to_phys(&wall_clock));
+	preempt_disable();
+	pvclock_read_wallclock(&wall_clock, this_cpu_pvti(), now);
+	preempt_enable();
 }
 
 static int kvm_set_wallclock(const struct timespec64 *now)
@@ -79,14 +95,10 @@ static int kvm_set_wallclock(const struct timespec64 *now)
 
 static u64 kvm_clock_read(void)
 {
-	struct pvclock_vcpu_time_info *src;
 	u64 ret;
-	int cpu;
 
 	preempt_disable_notrace();
-	cpu = smp_processor_id();
-	src = &hv_clock[cpu].pvti;
-	ret = pvclock_clocksource_read(src);
+	ret = pvclock_clocksource_read(this_cpu_pvti());
 	preempt_enable_notrace();
 	return ret;
 }
@@ -112,11 +124,11 @@ static inline void kvm_sched_clock_init(bool stable)
 	kvm_sched_clock_offset = kvm_clock_read();
 	pv_time_ops.sched_clock = kvm_sched_clock_read;
 
-	printk(KERN_INFO "kvm-clock: using sched offset of %llu cycles\n",
-			kvm_sched_clock_offset);
+	pr_info("kvm-clock: using sched offset of %llu cycles",
+		kvm_sched_clock_offset);
 
 	BUILD_BUG_ON(sizeof(kvm_sched_clock_offset) >
-	         sizeof(((struct pvclock_vcpu_time_info *)NULL)->system_time));
+		sizeof(((struct pvclock_vcpu_time_info *)NULL)->system_time));
 }
 
 /*
@@ -130,18 +142,11 @@ static inline void kvm_sched_clock_init(bool stable)
  */
 static unsigned long kvm_get_tsc_khz(void)
 {
-	struct pvclock_vcpu_time_info *src;
-	int cpu;
-	unsigned long tsc_khz;
-
-	cpu = get_cpu();
-	src = &hv_clock[cpu].pvti;
-	tsc_khz = pvclock_tsc_khz(src);
-	put_cpu();
-	return tsc_khz;
+	setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
+	return pvclock_tsc_khz(this_cpu_pvti());
 }
 
-static void kvm_get_preset_lpj(void)
+static void __init kvm_get_preset_lpj(void)
 {
 	unsigned long khz;
 	u64 lpj;
@@ -155,49 +160,40 @@ static void kvm_get_preset_lpj(void)
 
 bool kvm_check_and_clear_guest_paused(void)
 {
+	struct pvclock_vsyscall_time_info *src = this_cpu_hvclock();
 	bool ret = false;
-	struct pvclock_vcpu_time_info *src;
-	int cpu = smp_processor_id();
 
-	if (!hv_clock)
+	if (!src)
 		return ret;
 
-	src = &hv_clock[cpu].pvti;
-	if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) {
-		src->flags &= ~PVCLOCK_GUEST_STOPPED;
+	if ((src->pvti.flags & PVCLOCK_GUEST_STOPPED) != 0) {
+		src->pvti.flags &= ~PVCLOCK_GUEST_STOPPED;
 		pvclock_touch_watchdogs();
 		ret = true;
 	}
-
 	return ret;
 }
 
 struct clocksource kvm_clock = {
-	.name = "kvm-clock",
-	.read = kvm_clock_get_cycles,
-	.rating = 400,
-	.mask = CLOCKSOURCE_MASK(64),
-	.flags = CLOCK_SOURCE_IS_CONTINUOUS,
+	.name	= "kvm-clock",
+	.read	= kvm_clock_get_cycles,
+	.rating	= 400,
+	.mask	= CLOCKSOURCE_MASK(64),
+	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 EXPORT_SYMBOL_GPL(kvm_clock);
 
-int kvm_register_clock(char *txt)
+static void kvm_register_clock(char *txt)
 {
-	int cpu = smp_processor_id();
-	int low, high, ret;
-	struct pvclock_vcpu_time_info *src;
-
-	if (!hv_clock)
-		return 0;
+	struct pvclock_vsyscall_time_info *src = this_cpu_hvclock();
+	u64 pa;
 
-	src = &hv_clock[cpu].pvti;
-	low = (int)slow_virt_to_phys(src) | 1;
-	high = ((u64)slow_virt_to_phys(src) >> 32);
-	ret = native_write_msr_safe(msr_kvm_system_time, low, high);
-	printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n",
-	       cpu, high, low, txt);
+	if (!src)
+		return;
 
-	return ret;
+	pa = slow_virt_to_phys(&src->pvti) | 0x01ULL;
+	wrmsrl(msr_kvm_system_time, pa);
+	pr_info("kvm-clock: cpu %d, msr %llx, %s", smp_processor_id(), pa, txt);
 }
 
 static void kvm_save_sched_clock_state(void)
@@ -212,11 +208,7 @@ static void kvm_restore_sched_clock_state(void)
 #ifdef CONFIG_X86_LOCAL_APIC
 static void kvm_setup_secondary_clock(void)
 {
-	/*
-	 * Now that the first cpu already had this clocksource initialized,
-	 * we shouldn't fail.
-	 */
-	WARN_ON(kvm_register_clock("secondary cpu clock"));
+	kvm_register_clock("secondary cpu clock");
 }
 #endif
 
@@ -244,98 +236,84 @@ static void kvm_shutdown(void)
 	native_machine_shutdown();
 }
 
-static phys_addr_t __init kvm_memblock_alloc(phys_addr_t size,
-					     phys_addr_t align)
+static int __init kvm_setup_vsyscall_timeinfo(void)
 {
-	phys_addr_t mem;
+#ifdef CONFIG_X86_64
+	u8 flags;
 
-	mem = memblock_alloc(size, align);
-	if (!mem)
+	if (!per_cpu(hv_clock_per_cpu, 0) || !kvmclock_vsyscall)
 		return 0;
 
-	if (sev_active()) {
-		if (early_set_memory_decrypted((unsigned long)__va(mem), size))
-			goto e_free;
-	}
+	flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
+	if (!(flags & PVCLOCK_TSC_STABLE_BIT))
+		return 0;
 
-	return mem;
-e_free:
-	memblock_free(mem, size);
+	kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;
+#endif
 	return 0;
 }
+early_initcall(kvm_setup_vsyscall_timeinfo);
 
-static void __init kvm_memblock_free(phys_addr_t addr, phys_addr_t size)
+static int kvmclock_setup_percpu(unsigned int cpu)
 {
-	if (sev_active())
-		early_set_memory_encrypted((unsigned long)__va(addr), size);
+	struct pvclock_vsyscall_time_info *p = per_cpu(hv_clock_per_cpu, cpu);
+
+	/*
+	 * The per cpu area setup replicates CPU0 data to all cpu
+	 * pointers. So carefully check. CPU0 has been set up in init
+	 * already.
+	 */
+	if (!cpu || (p && p != per_cpu(hv_clock_per_cpu, 0)))
+		return 0;
+
+	/* Use the static page for the first CPUs, allocate otherwise */
+	if (cpu < HVC_BOOT_ARRAY_SIZE)
+		p = &hv_clock_boot[cpu];
+	else
+		p = kzalloc(sizeof(*p), GFP_KERNEL);
 
-	memblock_free(addr, size);
+	per_cpu(hv_clock_per_cpu, cpu) = p;
+	return p ? 0 : -ENOMEM;
 }
 
 void __init kvmclock_init(void)
 {
-	struct pvclock_vcpu_time_info *vcpu_time;
-	unsigned long mem, mem_wall_clock;
-	int size, cpu, wall_clock_size;
 	u8 flags;
 
-	size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
-
-	if (!kvm_para_available())
+	if (!kvm_para_available() || !kvmclock)
 		return;
 
-	if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) {
+	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) {
 		msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW;
 		msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW;
-	} else if (!(kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)))
-		return;
-
-	wall_clock_size = PAGE_ALIGN(sizeof(struct pvclock_wall_clock));
-	mem_wall_clock = kvm_memblock_alloc(wall_clock_size, PAGE_SIZE);
-	if (!mem_wall_clock)
-		return;
-
-	wall_clock = __va(mem_wall_clock);
-	memset(wall_clock, 0, wall_clock_size);
-
-	mem = kvm_memblock_alloc(size, PAGE_SIZE);
-	if (!mem) {
-		kvm_memblock_free(mem_wall_clock, wall_clock_size);
-		wall_clock = NULL;
+	} else if (!kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
 		return;
 	}
 
-	hv_clock = __va(mem);
-	memset(hv_clock, 0, size);
-
-	if (kvm_register_clock("primary cpu clock")) {
-		hv_clock = NULL;
-		kvm_memblock_free(mem, size);
-		kvm_memblock_free(mem_wall_clock, wall_clock_size);
-		wall_clock = NULL;
+	if (cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "kvmclock:setup_percpu",
+			      kvmclock_setup_percpu, NULL) < 0) {
 		return;
 	}
 
-	printk(KERN_INFO "kvm-clock: Using msrs %x and %x",
+	pr_info("kvm-clock: Using msrs %x and %x",
 		msr_kvm_system_time, msr_kvm_wall_clock);
 
+	this_cpu_write(hv_clock_per_cpu, &hv_clock_boot[0]);
+	kvm_register_clock("primary cpu clock");
+	pvclock_set_pvti_cpu0_va(hv_clock_boot);
+
 	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
 		pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
 
-	cpu = get_cpu();
-	vcpu_time = &hv_clock[cpu].pvti;
-	flags = pvclock_read_flags(vcpu_time);
-
+	flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
 	kvm_sched_clock_init(flags & PVCLOCK_TSC_STABLE_BIT);
-	put_cpu();
 
 	x86_platform.calibrate_tsc = kvm_get_tsc_khz;
 	x86_platform.calibrate_cpu = kvm_get_tsc_khz;
 	x86_platform.get_wallclock = kvm_get_wallclock;
 	x86_platform.set_wallclock = kvm_set_wallclock;
 #ifdef CONFIG_X86_LOCAL_APIC
-	x86_cpuinit.early_percpu_clock_init =
-		kvm_setup_secondary_clock;
+	x86_cpuinit.early_percpu_clock_init = kvm_setup_secondary_clock;
 #endif
 	x86_platform.save_sched_clock_state = kvm_save_sched_clock_state;
 	x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state;
@@ -347,34 +325,3 @@ void __init kvmclock_init(void)
 	clocksource_register_hz(&kvm_clock, NSEC_PER_SEC);
 	pv_info.name = "KVM";
 }
-
-int __init kvm_setup_vsyscall_timeinfo(void)
-{
-#ifdef CONFIG_X86_64
-	int cpu;
-	u8 flags;
-	struct pvclock_vcpu_time_info *vcpu_time;
-	unsigned int size;
-
-	if (!hv_clock)
-		return 0;
-
-	size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
-
-	cpu = get_cpu();
-
-	vcpu_time = &hv_clock[cpu].pvti;
-	flags = pvclock_read_flags(vcpu_time);
-
-	if (!(flags & PVCLOCK_TSC_STABLE_BIT)) {
-		put_cpu();
-		return 1;
-	}
-
-	pvclock_set_pvti_cpu0_va(hv_clock);
-	put_cpu();
-
-	kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;
-#endif
-	return 0;
-}