diff options
Diffstat (limited to 'arch/x86/kernel/kvm.c')
| -rw-r--r-- | arch/x86/kernel/kvm.c | 350 |
1 files changed, 329 insertions, 21 deletions
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 9c2bd8bd4b4..3dd8e2c4d74 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -20,6 +20,7 @@ * Authors: Anthony Liguori <aliguori@us.ibm.com> */ +#include <linux/context_tracking.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/kvm_para.h> @@ -33,6 +34,7 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/kprobes.h> +#include <linux/debugfs.h> #include <asm/timer.h> #include <asm/cpu.h> #include <asm/traps.h> @@ -43,7 +45,6 @@ #include <asm/apicdef.h> #include <asm/hypervisor.h> #include <asm/kvm_guest.h> -#include <asm/context_tracking.h> static int kvmapf = 1; @@ -250,20 +251,23 @@ u32 kvm_read_and_reset_pf_reason(void) return reason; } EXPORT_SYMBOL_GPL(kvm_read_and_reset_pf_reason); +NOKPROBE_SYMBOL(kvm_read_and_reset_pf_reason); -dotraplinkage void __kprobes +dotraplinkage void do_async_page_fault(struct pt_regs *regs, unsigned long error_code) { + enum ctx_state prev_state; + switch (kvm_read_and_reset_pf_reason()) { default: - do_page_fault(regs, error_code); + trace_do_page_fault(regs, error_code); break; case KVM_PV_REASON_PAGE_NOT_PRESENT: /* page is swapped out by the host. */ - exception_enter(regs); + prev_state = exception_enter(); exit_idle(); kvm_async_pf_task_wait((u32)read_cr2()); - exception_exit(regs); + exception_exit(prev_state); break; case KVM_PV_REASON_PAGE_READY: rcu_irq_enter(); @@ -273,6 +277,7 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) break; } } +NOKPROBE_SYMBOL(do_async_page_fault); static void __init paravirt_ops_setup(void) { @@ -297,9 +302,9 @@ static void kvm_register_steal_time(void) memset(st, 0, sizeof(*st)); - wrmsrl(MSR_KVM_STEAL_TIME, (__pa(st) | KVM_MSR_ENABLED)); - printk(KERN_INFO "kvm-stealtime: cpu %d, msr %lx\n", - cpu, __pa(st)); + wrmsrl(MSR_KVM_STEAL_TIME, (slow_virt_to_phys(st) | KVM_MSR_ENABLED)); + pr_info("kvm-stealtime: cpu %d, msr %llx\n", + cpu, (unsigned long long) slow_virt_to_phys(st)); } static DEFINE_PER_CPU(unsigned long, kvm_apic_eoi) = KVM_PV_EOI_DISABLED; @@ -318,13 +323,13 @@ static void kvm_guest_apic_eoi_write(u32 reg, u32 val) apic_write(APIC_EOI, APIC_EOI_ACK); } -void __cpuinit kvm_guest_cpu_init(void) +void kvm_guest_cpu_init(void) { if (!kvm_para_available()) return; if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) { - u64 pa = __pa(&__get_cpu_var(apf_reason)); + u64 pa = slow_virt_to_phys(&__get_cpu_var(apf_reason)); #ifdef CONFIG_PREEMPT pa |= KVM_ASYNC_PF_SEND_ALWAYS; @@ -340,7 +345,8 @@ void __cpuinit kvm_guest_cpu_init(void) /* Size alignment is implied but just to make it explicit. */ BUILD_BUG_ON(__alignof__(kvm_apic_eoi) < 4); __get_cpu_var(kvm_apic_eoi) = 0; - pa = __pa(&__get_cpu_var(kvm_apic_eoi)) | KVM_MSR_ENABLED; + pa = slow_virt_to_phys(&__get_cpu_var(kvm_apic_eoi)) + | KVM_MSR_ENABLED; wrmsrl(MSR_KVM_PV_EOI_EN, pa); } @@ -413,12 +419,12 @@ void kvm_disable_steal_time(void) #ifdef CONFIG_SMP static void __init kvm_smp_prepare_boot_cpu(void) { - WARN_ON(kvm_register_clock("primary cpu clock")); kvm_guest_cpu_init(); native_smp_prepare_boot_cpu(); + kvm_spinlock_init(); } -static void __cpuinit kvm_guest_cpu_online(void *dummy) +static void kvm_guest_cpu_online(void *dummy) { kvm_guest_cpu_init(); } @@ -432,8 +438,8 @@ static void kvm_guest_cpu_offline(void *dummy) apf_task_wake_all(); } -static int __cpuinit kvm_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) +static int kvm_cpu_notify(struct notifier_block *self, unsigned long action, + void *hcpu) { int cpu = (unsigned long)hcpu; switch (action) { @@ -452,14 +458,14 @@ static int __cpuinit kvm_cpu_notify(struct notifier_block *self, return NOTIFY_OK; } -static struct notifier_block __cpuinitdata kvm_cpu_notifier = { +static struct notifier_block kvm_cpu_notifier = { .notifier_call = kvm_cpu_notify, }; #endif static void __init kvm_apf_trap_init(void) { - set_intr_gate(14, &async_page_fault); + set_intr_gate(14, async_page_fault); } void __init kvm_guest_init(void) @@ -495,16 +501,47 @@ void __init kvm_guest_init(void) #endif } -static bool __init kvm_detect(void) +static noinline uint32_t __kvm_cpuid_base(void) { - if (!kvm_para_available()) - return false; - return true; + if (boot_cpu_data.cpuid_level < 0) + return 0; /* So we don't blow up on old processors */ + + if (cpu_has_hypervisor) + return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0); + + return 0; +} + +static inline uint32_t kvm_cpuid_base(void) +{ + static int kvm_cpuid_base = -1; + + if (kvm_cpuid_base == -1) + kvm_cpuid_base = __kvm_cpuid_base(); + + return kvm_cpuid_base; +} + +bool kvm_para_available(void) +{ + return kvm_cpuid_base() != 0; +} +EXPORT_SYMBOL_GPL(kvm_para_available); + +unsigned int kvm_arch_para_features(void) +{ + return cpuid_eax(kvm_cpuid_base() | KVM_CPUID_FEATURES); +} + +static uint32_t __init kvm_detect(void) +{ + return kvm_cpuid_base(); } const struct hypervisor_x86 x86_hyper_kvm __refconst = { .name = "KVM", .detect = kvm_detect, + .x2apic_available = kvm_para_available, }; EXPORT_SYMBOL_GPL(x86_hyper_kvm); @@ -519,3 +556,274 @@ static __init int activate_jump_labels(void) return 0; } arch_initcall(activate_jump_labels); + +#ifdef CONFIG_PARAVIRT_SPINLOCKS + +/* Kick a cpu by its apicid. Used to wake up a halted vcpu */ +static void kvm_kick_cpu(int cpu) +{ + int apicid; + unsigned long flags = 0; + + apicid = per_cpu(x86_cpu_to_apicid, cpu); + kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid); +} + +enum kvm_contention_stat { + TAKEN_SLOW, + TAKEN_SLOW_PICKUP, + RELEASED_SLOW, + RELEASED_SLOW_KICKED, + NR_CONTENTION_STATS +}; + +#ifdef CONFIG_KVM_DEBUG_FS +#define HISTO_BUCKETS 30 + +static struct kvm_spinlock_stats +{ + u32 contention_stats[NR_CONTENTION_STATS]; + u32 histo_spin_blocked[HISTO_BUCKETS+1]; + u64 time_blocked; +} spinlock_stats; + +static u8 zero_stats; + +static inline void check_zero(void) +{ + u8 ret; + u8 old; + + old = ACCESS_ONCE(zero_stats); + if (unlikely(old)) { + ret = cmpxchg(&zero_stats, old, 0); + /* This ensures only one fellow resets the stat */ + if (ret == old) + memset(&spinlock_stats, 0, sizeof(spinlock_stats)); + } +} + +static inline void add_stats(enum kvm_contention_stat var, u32 val) +{ + check_zero(); + spinlock_stats.contention_stats[var] += val; +} + + +static inline u64 spin_time_start(void) +{ + return sched_clock(); +} + +static void __spin_time_accum(u64 delta, u32 *array) +{ + unsigned index; + + index = ilog2(delta); + check_zero(); + + if (index < HISTO_BUCKETS) + array[index]++; + else + array[HISTO_BUCKETS]++; +} + +static inline void spin_time_accum_blocked(u64 start) +{ + u32 delta; + + delta = sched_clock() - start; + __spin_time_accum(delta, spinlock_stats.histo_spin_blocked); + spinlock_stats.time_blocked += delta; +} + +static struct dentry *d_spin_debug; +static struct dentry *d_kvm_debug; + +struct dentry *kvm_init_debugfs(void) +{ + d_kvm_debug = debugfs_create_dir("kvm-guest", NULL); + if (!d_kvm_debug) + printk(KERN_WARNING "Could not create 'kvm' debugfs directory\n"); + + return d_kvm_debug; +} + +static int __init kvm_spinlock_debugfs(void) +{ + struct dentry *d_kvm; + + d_kvm = kvm_init_debugfs(); + if (d_kvm == NULL) + return -ENOMEM; + + d_spin_debug = debugfs_create_dir("spinlocks", d_kvm); + + debugfs_create_u8("zero_stats", 0644, d_spin_debug, &zero_stats); + + debugfs_create_u32("taken_slow", 0444, d_spin_debug, + &spinlock_stats.contention_stats[TAKEN_SLOW]); + debugfs_create_u32("taken_slow_pickup", 0444, d_spin_debug, + &spinlock_stats.contention_stats[TAKEN_SLOW_PICKUP]); + + debugfs_create_u32("released_slow", 0444, d_spin_debug, + &spinlock_stats.contention_stats[RELEASED_SLOW]); + debugfs_create_u32("released_slow_kicked", 0444, d_spin_debug, + &spinlock_stats.contention_stats[RELEASED_SLOW_KICKED]); + + debugfs_create_u64("time_blocked", 0444, d_spin_debug, + &spinlock_stats.time_blocked); + + debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug, + spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1); + + return 0; +} +fs_initcall(kvm_spinlock_debugfs); +#else /* !CONFIG_KVM_DEBUG_FS */ +static inline void add_stats(enum kvm_contention_stat var, u32 val) +{ +} + +static inline u64 spin_time_start(void) +{ + return 0; +} + +static inline void spin_time_accum_blocked(u64 start) +{ +} +#endif /* CONFIG_KVM_DEBUG_FS */ + +struct kvm_lock_waiting { + struct arch_spinlock *lock; + __ticket_t want; +}; + +/* cpus 'waiting' on a spinlock to become available */ +static cpumask_t waiting_cpus; + +/* Track spinlock on which a cpu is waiting */ +static DEFINE_PER_CPU(struct kvm_lock_waiting, klock_waiting); + +__visible void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want) +{ + struct kvm_lock_waiting *w; + int cpu; + u64 start; + unsigned long flags; + + if (in_nmi()) + return; + + w = &__get_cpu_var(klock_waiting); + cpu = smp_processor_id(); + start = spin_time_start(); + + /* + * Make sure an interrupt handler can't upset things in a + * partially setup state. + */ + local_irq_save(flags); + + /* + * The ordering protocol on this is that the "lock" pointer + * may only be set non-NULL if the "want" ticket is correct. + * If we're updating "want", we must first clear "lock". + */ + w->lock = NULL; + smp_wmb(); + w->want = want; + smp_wmb(); + w->lock = lock; + + add_stats(TAKEN_SLOW, 1); + + /* + * This uses set_bit, which is atomic but we should not rely on its + * reordering gurantees. So barrier is needed after this call. + */ + cpumask_set_cpu(cpu, &waiting_cpus); + + barrier(); + + /* + * Mark entry to slowpath before doing the pickup test to make + * sure we don't deadlock with an unlocker. + */ + __ticket_enter_slowpath(lock); + + /* + * check again make sure it didn't become free while + * we weren't looking. + */ + if (ACCESS_ONCE(lock->tickets.head) == want) { + add_stats(TAKEN_SLOW_PICKUP, 1); + goto out; + } + + /* + * halt until it's our turn and kicked. Note that we do safe halt + * for irq enabled case to avoid hang when lock info is overwritten + * in irq spinlock slowpath and no spurious interrupt occur to save us. + */ + if (arch_irqs_disabled_flags(flags)) + halt(); + else + safe_halt(); + +out: + cpumask_clear_cpu(cpu, &waiting_cpus); + w->lock = NULL; + local_irq_restore(flags); + spin_time_accum_blocked(start); +} +PV_CALLEE_SAVE_REGS_THUNK(kvm_lock_spinning); + +/* Kick vcpu waiting on @lock->head to reach value @ticket */ +static void kvm_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket) +{ + int cpu; + + add_stats(RELEASED_SLOW, 1); + for_each_cpu(cpu, &waiting_cpus) { + const struct kvm_lock_waiting *w = &per_cpu(klock_waiting, cpu); + if (ACCESS_ONCE(w->lock) == lock && + ACCESS_ONCE(w->want) == ticket) { + add_stats(RELEASED_SLOW_KICKED, 1); + kvm_kick_cpu(cpu); + break; + } + } +} + +/* + * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present. + */ +void __init kvm_spinlock_init(void) +{ + if (!kvm_para_available()) + return; + /* Does host kernel support KVM_FEATURE_PV_UNHALT? */ + if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) + return; + + pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning); + pv_lock_ops.unlock_kick = kvm_unlock_kick; +} + +static __init int kvm_spinlock_init_jump(void) +{ + if (!kvm_para_available()) + return 0; + if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) + return 0; + + static_key_slow_inc(¶virt_ticketlocks_enabled); + printk(KERN_INFO "KVM setup paravirtual spinlock\n"); + + return 0; +} +early_initcall(kvm_spinlock_init_jump); + +#endif /* CONFIG_PARAVIRT_SPINLOCKS */ |