diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-12-13 15:31:08 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-12-13 15:31:08 -0800 |
| commit | 66cdd0ceaf65a18996f561b770eedde1d123b019 (patch) | |
| tree | 4892eaa422d366fce5d1e866ff1fe0988af95569 /arch/x86 | |
| parent | 896ea17d3da5f44b2625c9cda9874d7dfe447393 (diff) | |
| parent | 58b7825bc324da55415034a9f6ca5d716b8fd898 (diff) | |
Merge tag 'kvm-3.8-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull KVM updates from Marcelo Tosatti:
"Considerable KVM/PPC work, x86 kvmclock vsyscall support,
IA32_TSC_ADJUST MSR emulation, amongst others."
Fix up trivial conflict in kernel/sched/core.c due to cross-cpu
migration notifier added next to rq migration call-back.
* tag 'kvm-3.8-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (156 commits)
KVM: emulator: fix real mode segment checks in address linearization
VMX: remove unneeded enable_unrestricted_guest check
KVM: VMX: fix DPL during entry to protected mode
x86/kexec: crash_vmclear_local_vmcss needs __rcu
kvm: Fix irqfd resampler list walk
KVM: VMX: provide the vmclear function and a bitmap to support VMCLEAR in kdump
x86/kexec: VMCLEAR VMCSs loaded on all cpus if necessary
KVM: MMU: optimize for set_spte
KVM: PPC: booke: Get/set guest EPCR register using ONE_REG interface
KVM: PPC: bookehv: Add EPCR support in mtspr/mfspr emulation
KVM: PPC: bookehv: Add guest computation mode for irq delivery
KVM: PPC: Make EPCR a valid field for booke64 and bookehv
KVM: PPC: booke: Extend MAS2 EPN mask for 64-bit
KVM: PPC: e500: Mask MAS2 EPN high 32-bits in 32/64 tlbwe emulation
KVM: PPC: Mask ea's high 32-bits in 32/64 instr emulation
KVM: PPC: e500: Add emulation helper for getting instruction ea
KVM: PPC: bookehv64: Add support for interrupt handling
KVM: PPC: bookehv: Remove GET_VCPU macro from exception handler
KVM: PPC: booke: Fix get_tb() compile error on 64-bit
KVM: PPC: e500: Silence bogus GCC warning in tlb code
...
Diffstat (limited to 'arch/x86')
27 files changed, 1209 insertions, 339 deletions
diff --git a/arch/x86/include/asm/clocksource.h b/arch/x86/include/asm/clocksource.h index 0bdbbb3b9ce..16a57f4ed64 100644 --- a/arch/x86/include/asm/clocksource.h +++ b/arch/x86/include/asm/clocksource.h @@ -8,6 +8,7 @@ #define VCLOCK_NONE 0 /* No vDSO clock available. */ #define VCLOCK_TSC 1 /* vDSO should use vread_tsc. */ #define VCLOCK_HPET 2 /* vDSO should use vread_hpet. */ +#define VCLOCK_PVCLOCK 3 /* vDSO should use vread_pvclock. */ struct arch_clocksource_data { int vclock_mode; diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index da40b1e2228..2d9075e863a 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -202,6 +202,7 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ #define X86_FEATURE_FSGSBASE (9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/ +#define X86_FEATURE_TSC_ADJUST (9*32+ 1) /* TSC adjustment MSR 0x3b */ #define X86_FEATURE_BMI1 (9*32+ 3) /* 1st group bit manipulation extensions */ #define X86_FEATURE_HLE (9*32+ 4) /* Hardware Lock Elision */ #define X86_FEATURE_AVX2 (9*32+ 5) /* AVX2 instructions */ diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 4da3c0c4c97..a09c2857106 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -19,6 +19,7 @@ #include <asm/acpi.h> #include <asm/apicdef.h> #include <asm/page.h> +#include <asm/pvclock.h> #ifdef CONFIG_X86_32 #include <linux/threads.h> #include <asm/kmap_types.h> @@ -81,6 +82,10 @@ enum fixed_addresses { VVAR_PAGE, VSYSCALL_HPET, #endif +#ifdef CONFIG_PARAVIRT_CLOCK + PVCLOCK_FIXMAP_BEGIN, + PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1, +#endif FIX_DBGP_BASE, FIX_EARLYCON_MEM_BASE, #ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index 317ff1703d0..6080d2694ba 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -163,6 +163,9 @@ struct kimage_arch { }; #endif +typedef void crash_vmclear_fn(void); +extern crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss; + #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_KEXEC_H */ diff --git a/arch/x86/include/asm/kvm_guest.h b/arch/x86/include/asm/kvm_guest.h new file mode 100644 index 00000000000..a92b1763c41 --- /dev/null +++ b/arch/x86/include/asm/kvm_guest.h @@ -0,0 +1,6 @@ +#ifndef _ASM_X86_KVM_GUEST_H +#define _ASM_X86_KVM_GUEST_H + +int kvm_setup_vsyscall_timeinfo(void); + +#endif /* _ASM_X86_KVM_GUEST_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index b2e11f45243..dc87b65e9c3 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -22,6 +22,8 @@ #include <linux/kvm_para.h> #include <linux/kvm_types.h> #include <linux/perf_event.h> +#include <linux/pvclock_gtod.h> +#include <linux/clocksource.h> #include <asm/pvclock-abi.h> #include <asm/desc.h> @@ -442,6 +444,7 @@ struct kvm_vcpu_arch { s8 virtual_tsc_shift; u32 virtual_tsc_mult; u32 virtual_tsc_khz; + s64 ia32_tsc_adjust_msr; atomic_t nmi_queued; /* unprocessed asynchronous NMIs */ unsigned nmi_pending; /* NMI queued after currently running handler */ @@ -559,6 +562,12 @@ struct kvm_arch { u64 cur_tsc_write; u64 cur_tsc_offset; u8 cur_tsc_generation; + int nr_vcpus_matched_tsc; + + spinlock_t pvclock_gtod_sync_lock; + bool use_master_clock; + u64 master_kernel_ns; + cycle_t master_cycle_now; struct kvm_xen_hvm_config xen_hvm_config; @@ -612,6 +621,12 @@ struct kvm_vcpu_stat { struct x86_instruction_info; +struct msr_data { + bool host_initiated; + u32 index; + u64 data; +}; + struct kvm_x86_ops { int (*cpu_has_kvm_support)(void); /* __init */ int (*disabled_by_bios)(void); /* __init */ @@ -634,7 +649,7 @@ struct kvm_x86_ops { void (*update_db_bp_intercept)(struct kvm_vcpu *vcpu); int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); - int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); + int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr); u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg); void (*get_segment)(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); @@ -697,10 +712,11 @@ struct kvm_x86_ops { bool (*has_wbinvd_exit)(void); void (*set_tsc_khz)(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale); + u64 (*read_tsc_offset)(struct kvm_vcpu *vcpu); void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); u64 (*compute_tsc_offset)(struct kvm_vcpu *vcpu, u64 target_tsc); - u64 (*read_l1_tsc)(struct kvm_vcpu *vcpu); + u64 (*read_l1_tsc)(struct kvm_vcpu *vcpu, u64 host_tsc); void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2); @@ -785,7 +801,7 @@ static inline int emulate_instruction(struct kvm_vcpu *vcpu, void kvm_enable_efer_bits(u64); int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data); -int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); +int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr); struct x86_emulate_ctxt; @@ -812,7 +828,7 @@ void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l); int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr); int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); -int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data); +int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr); unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu); void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index e400cdb2dd6..6e930b21872 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -236,6 +236,7 @@ #define MSR_IA32_EBL_CR_POWERON 0x0000002a #define MSR_EBC_FREQUENCY_ID 0x0000002c #define MSR_IA32_FEATURE_CONTROL 0x0000003a +#define MSR_IA32_TSC_ADJUST 0x0000003b #define FEATURE_CONTROL_LOCKED (1<<0) #define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX (1<<1) diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index c59cc97fe6c..109a9dd5d45 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -6,6 +6,7 @@ /* some helper functions for xen and kvm pv clock sources */ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src); +u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src); void pvclock_set_flags(u8 flags); unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src); void pvclock_read_wallclock(struct pvclock_wall_clock *wall, @@ -56,4 +57,50 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) return product; } +static __always_inline +u64 pvclock_get_nsec_offset(const struct pvclock_vcpu_time_info *src) +{ + u64 delta = __native_read_tsc() - src->tsc_timestamp; + return pvclock_scale_delta(delta, src->tsc_to_system_mul, + src->tsc_shift); +} + +static __always_inline +unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, + cycle_t *cycles, u8 *flags) +{ + unsigned version; + cycle_t ret, offset; + u8 ret_flags; + + version = src->version; + /* Note: emulated platforms which do not advertise SSE2 support + * result in kvmclock not using the necessary RDTSC barriers. + * Without barriers, it is possible that RDTSC instruction reads from + * the time stamp counter outside rdtsc_barrier protected section + * below, resulting in violation of monotonicity. + */ + rdtsc_barrier(); + offset = pvclock_get_nsec_offset(src); + ret = src->system_time + offset; + ret_flags = src->flags; + rdtsc_barrier(); + + *cycles = ret; + *flags = ret_flags; + return version; +} + +struct pvclock_vsyscall_time_info { + struct pvclock_vcpu_time_info pvti; + u32 migrate_count; +} __attribute__((__aligned__(SMP_CACHE_BYTES))); + +#define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info) +#define PVCLOCK_VSYSCALL_NR_PAGES (((NR_CPUS-1)/(PAGE_SIZE/PVTI_SIZE))+1) + +int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, + int size); +struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu); + #endif /* _ASM_X86_PVCLOCK_H */ diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 36ec21c36d6..c2d56b34830 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -445,8 +445,7 @@ enum vmcs_field { #define VMX_EPTP_WB_BIT (1ull << 14) #define VMX_EPT_2MB_PAGE_BIT (1ull << 16) #define VMX_EPT_1GB_PAGE_BIT (1ull << 17) -#define VMX_EPT_AD_BIT (1ull << 21) -#define VMX_EPT_EXTENT_INDIVIDUAL_BIT (1ull << 24) +#define VMX_EPT_AD_BIT (1ull << 21) #define VMX_EPT_EXTENT_CONTEXT_BIT (1ull << 25) #define VMX_EPT_EXTENT_GLOBAL_BIT (1ull << 26) diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h index eaea1d31f75..80f80955cfd 100644 --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -33,6 +33,26 @@ extern void map_vsyscall(void); */ extern bool emulate_vsyscall(struct pt_regs *regs, unsigned long address); +#ifdef CONFIG_X86_64 + +#define VGETCPU_CPU_MASK 0xfff + +static inline unsigned int __getcpu(void) +{ + unsigned int p; + + if (VVAR(vgetcpu_mode) == VGETCPU_RDTSCP) { + /* Load per CPU data from RDTSCP */ + native_read_tscp(&p); + } else { + /* Load per CPU data from GDT */ + asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG)); + } + + return p; +} +#endif /* CONFIG_X86_64 */ + #endif /* __KERNEL__ */ #endif /* _ASM_X86_VSYSCALL_H */ diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 13ad89971d4..74467feb4dc 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -16,6 +16,7 @@ #include <linux/delay.h> #include <linux/elf.h> #include <linux/elfcore.h> +#include <linux/module.h> #include <asm/processor.h> #include <asm/hardirq.h> @@ -30,6 +31,27 @@ int in_crash_kexec; +/* + * This is used to VMCLEAR all VMCSs loaded on the + * processor. And when loading kvm_intel module, the + * callback function pointer will be assigned. + * + * protected by rcu. + */ +crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss = NULL; +EXPORT_SYMBOL_GPL(crash_vmclear_loaded_vmcss); + +static inline void cpu_crash_vmclear_loaded_vmcss(void) +{ + crash_vmclear_fn *do_vmclear_operation = NULL; + + rcu_read_lock(); + do_vmclear_operation = rcu_dereference(crash_vmclear_loaded_vmcss); + if (do_vmclear_operation) + do_vmclear_operation(); + rcu_read_unlock(); +} + #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC) static void kdump_nmi_callback(int cpu, struct pt_regs *regs) @@ -46,6 +68,11 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) #endif crash_save_cpu(regs, cpu); + /* + * VMCLEAR VMCSs loaded on all cpus if needed. + */ + cpu_crash_vmclear_loaded_vmcss(); + /* Disable VMX or SVM if needed. * * We need to disable virtualization on all CPUs. @@ -88,6 +115,11 @@ void native_machine_crash_shutdown(struct pt_regs *regs) kdump_nmi_shootdown_cpus(); + /* + * VMCLEAR VMCSs loaded on this cpu if needed. + */ + cpu_crash_vmclear_loaded_vmcss(); + /* Booting kdump kernel with VMX or SVM enabled won't work, * because (among other limitations) we can't disable paging * with the virt flags. diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 4180a874c76..08b973f6403 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -42,6 +42,7 @@ #include <asm/apic.h> #include <asm/apicdef.h> #include <asm/hypervisor.h> +#include <asm/kvm_guest.h> static int kvmapf = 1; @@ -62,6 +63,15 @@ static int parse_no_stealacc(char *arg) early_param("no-steal-acc", parse_no_stealacc); +static int kvmclock_vsyscall = 1; +static int parse_no_kvmclock_vsyscall(char *arg) +{ + kvmclock_vsyscall = 0; + return 0; +} + +early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); + static DEFINE_PER_CPU(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64); static DEFINE_PER_CPU(struct kvm_steal_time, steal_time) __aligned(64); static int has_steal_clock = 0; @@ -110,11 +120,6 @@ void kvm_async_pf_task_wait(u32 token) struct kvm_task_sleep_head *b = &async_pf_sleepers[key]; struct kvm_task_sleep_node n, *e; DEFINE_WAIT(wait); - int cpu, idle; - - cpu = get_cpu(); - idle = idle_cpu(cpu); - put_cpu(); spin_lock(&b->lock); e = _find_apf_task(b, token); @@ -128,7 +133,7 @@ void kvm_async_pf_task_wait(u32 token) n.token = token; n.cpu = smp_processor_id(); - n.halted = idle || preempt_count() > 1; + n.halted = is_idle_task(current) || preempt_count() > 1; init_waitqueue_head(&n.wq); hlist_add_head(&n.link, &b->list); spin_unlock(&b->lock); @@ -471,6 +476,9 @@ void __init kvm_guest_init(void) if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) apic_set_eoi_write(kvm_guest_apic_eoi_write); + if (kvmclock_vsyscall) + kvm_setup_vsyscall_timeinfo(); + #ifdef CONFIG_SMP smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; register_cpu_notifier(&kvm_cpu_notifier); diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index f1b42b3a186..220a360010f 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -23,6 +23,7 @@ #include <asm/apic.h> #include <linux/percpu.h> #include <linux/hardirq.h> +#include <linux/memblock.h> #include <asm/x86_init.h> #include <asm/reboot.h> @@ -39,7 +40,7 @@ static int parse_no_kvmclock(char *arg) early_param("no-kvmclock", parse_no_kvmclock); /* The hypervisor will put information about time periodically here */ -static DEFINE_PER_CPU_SHARED_ALIGNED(struct pvclock_vcpu_time_info, hv_clock); +static struct pvclock_vsyscall_time_info *hv_clock; static struct pvclock_wall_clock wall_clock; /* @@ -52,15 +53,20 @@ static unsigned long kvm_get_wallclock(void) struct pvclock_vcpu_time_info *vcpu_time; struct timespec ts; int low, high; + int cpu; low = (int)__pa_symbol(&wall_clock); high = ((u64)__pa_symbol(&wall_clock) >> 32); native_write_msr(msr_kvm_wall_clock, low, high); - vcpu_time = &get_cpu_var(hv_clock); + preempt_disable(); + cpu = smp_processor_id(); + + vcpu_time = &hv_clock[cpu].pvti; pvclock_read_wallclock(&wall_clock, vcpu_time, &ts); - put_cpu_var(hv_clock); + + preempt_enable(); return ts.tv_sec; } @@ -74,9 +80,11 @@ static cycle_t kvm_clock_read(void) { struct pvclock_vcpu_time_info *src; cycle_t ret; + int cpu; preempt_disable_notrace(); - src = &__get_cpu_var(hv_clock); + cpu = smp_processor_id(); + src = &hv_clock[cpu].pvti; ret = pvclock_clocksource_read(src); preempt_enable_notrace(); return ret; @@ -99,8 +107,15 @@ static cycle_t kvm_clock_get_cycles(struct clocksource *cs) static unsigned long kvm_get_tsc_khz(void) { struct pvclock_vcpu_time_info *src; - src = &per_cpu(hv_clock, 0); - return pvclock_tsc_khz(src); + int cpu; + unsigned long tsc_khz; + + preempt_disable(); + cpu = smp_processor_id(); + src = &hv_clock[cpu].pvti; + tsc_khz = pvclock_tsc_khz(src); + preempt_enable(); + return tsc_khz; } static void kvm_get_preset_lpj(void) @@ -119,10 +134,14 @@ bool kvm_check_and_clear_guest_paused(void) { bool ret = false; struct pvclock_vcpu_time_info *src; + int cpu = smp_processor_id(); - src = &__get_cpu_var(hv_clock); + if (!hv_clock) + return ret; + + src = &hv_clock[cpu].pvti; if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) { - __this_cpu_and(hv_clock.flags, ~PVCLOCK_GUEST_STOPPED); + src->flags &= ~PVCLOCK_GUEST_STOPPED; ret = true; } @@ -141,9 +160,10 @@ int kvm_register_clock(char *txt) { int cpu = smp_processor_id(); int low, high, ret; + struct pvclock_vcpu_time_info *src = &hv_clock[cpu].pvti; - low = (int)__pa(&per_cpu(hv_clock, cpu)) | 1; - high = ((u64)__pa(&per_cpu(hv_clock, cpu)) >> 32); + low = (int)__pa(src) | 1; + high = ((u64)__pa(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); @@ -197,6 +217,8 @@ static void kvm_shutdown(void) void __init kvmclock_init(void) { + unsigned long mem; + if (!kvm_para_available()) return; @@ -209,8 +231,18 @@ void __init kvmclock_init(void) printk(KERN_INFO "kvm-clock: Using msrs %x and %x", msr_kvm_system_time, msr_kvm_wall_clock); - if (kvm_register_clock("boot clock")) + mem = memblock_alloc(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS, + PAGE_SIZE); + if (!mem) + return; + hv_clock = __va(mem); + + if (kvm_register_clock("boot clock")) { + hv_clock = NULL; + memblock_free(mem, + sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS); return; + } pv_time_ops.sched_clock = kvm_clock_read; x86_platform.calibrate_tsc = kvm_get_tsc_khz; x86_platform.get_wallclock = kvm_get_wallclock; @@ -233,3 +265,37 @@ void __init kvmclock_init(void) if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT); } + +int __init kvm_setup_vsyscall_timeinfo(void) +{ +#ifdef CONFIG_X86_64 + int cpu; + int ret; + u8 flags; + struct pvclock_vcpu_time_info *vcpu_time; + unsigned int size; + + size = sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS; + + preempt_disable(); + cpu = smp_processor_id(); + + vcpu_time = &hv_clock[cpu].pvti; + flags = pvclock_read_flags(vcpu_time); + + if (!(flags & PVCLOCK_TSC_STABLE_BIT)) { + preempt_enable(); + return 1; + } + + if ((ret = pvclock_init_vsyscall(hv_clock, size))) { + preempt_enable(); + return ret; + } + + preempt_enable(); + + kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; +#endif + return 0; +} diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 42eb3300dfc..85c39590c1a 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -17,23 +17,13 @@ #include <linux/kernel.h> #include <linux/percpu.h> +#include <linux/notifier.h> +#include <linux/sched.h> +#include <linux/gfp.h> +#include <linux/bootmem.h> +#include <asm/fixmap.h> #include <asm/pvclock.h> -/* - * These are perodically updated - * xen: magic shared_info page - * kvm: gpa registered via msr - * and then copied here. - */ -struct pvclock_shadow_time { - u64 tsc_timestamp; /* TSC at last update of time vals. */ - u64 system_timestamp; /* Time, in nanosecs, since boot. */ - u32 tsc_to_nsec_mul; - int tsc_shift; - u32 version; - u8 flags; -}; - static u8 valid_flags __read_mostly = 0; void pvclock_set_flags(u8 flags) @@ -41,34 +31,6 @@ void pvclock_set_flags(u8 flags) valid_flags = flags; } -static u64 pvclock_get_nsec_offset(struct pvclock_shadow_time *shadow) -{ - u64 delta = native_read_tsc() - shadow->tsc_timestamp; - return pvclock_scale_delta(delta, shadow->tsc_to_nsec_mul, - shadow->tsc_shift); -} - -/* - * Reads a consistent set of time-base values from hypervisor, - * into a shadow data area. - */ -static unsigned pvclock_get_time_values(struct pvclock_shadow_time *dst, - struct pvclock_vcpu_time_info *src) -{ - do { - dst->version = src->version; - rmb(); /* fetch version before data */ - dst->tsc_timestamp = src->tsc_timestamp; - dst->system_timestamp = src->system_time; - dst->tsc_to_nsec_mul = src->tsc_to_system_mul; - dst->tsc_shift = src->tsc_shift; - dst->flags = src->flags; - rmb(); /* test version after fetching data */ - } while ((src->version & 1) || (dst->version != src->version)); - - return dst->version; -} - unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src) { u64 pv_tsc_khz = 1000000ULL << 32; @@ -88,23 +50,32 @@ void pvclock_resume(void) atomic64_set(&last_value, 0); } +u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src) +{ + unsigned version; + cycle_t ret; + u8 flags; + + do { + version = __pvclock_read_cycles(src, &ret, &flags); + } while ((src->version & 1) || version != src->version); + + return flags & valid_flags; +} + cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) { - struct pvclock_shadow_time shadow; unsigned version; - cycle_t ret, offset; + cycle_t ret; u64 last; + u8 flags; do { - version = pvclock_get_time_values(&shadow, src); - barrier(); - offset = pvclock_get_nsec_offset(&shadow); - ret = shadow.system_timestamp + offset; - barrier(); - } while (version != src->version); + version = __pvclock_read_cycles(src, &ret, &flags); + } while ((src->version & 1) || version != src->version); if ((valid_flags & PVCLOCK_TSC_STABLE_BIT) && - (shadow.flags & PVCLOCK_TSC_STABLE_BIT)) + (flags & PVCLOCK_TSC_STABLE_BIT)) return ret; /* @@ -156,3 +127,71 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); } + +static struct pvclock_vsyscall_time_info *pvclock_vdso_info; + +static struct pvclock_vsyscall_time_info * +pvclock_get_vsyscall_user_time_info(int cpu) +{ + if (!pvclock_vdso_info) { + BUG(); + return NULL; + } + + return &pvclock_vdso_info[cpu]; +} + +struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu) +{ + return &pvclock_get_vsyscall_user_time_info(cpu)->pvti; +} + +#ifdef CONFIG_X86_64 +static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l, + void *v) +{ + struct task_migration_notifier *mn = v; + struct pvclock_vsyscall_time_info *pvti; + + pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu); + + /* this is NULL when pvclock vsyscall is not initialized */ + if (unlikely(pvti == NULL)) + return NOTIFY_DONE; + + pvti->migrate_count++; + + return NOTIFY_DONE; +} + +static struct notifier_block pvclock_migrate = { + .notifier_call = pvclock_task_migrate, +}; + +/* + * Initialize the generic pvclock vsyscall state. This will allocate + * a/some page(s) for the per-vcpu pvclock information, set up a + * fixmap mapping for the page(s) + */ + +int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, + int size) +{ + int idx; + + WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE); + + pvclock_vdso_info = i; + + for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) { + __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx, + __pa_symbol(i) + (idx*PAGE_SIZE), + PAGE_KERNEL_VVAR); + } + + + register_task_migration_notifier(&pvclock_migrate); + + return 0; +} +#endif diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index ec79e773342..a20ecb5b6cb 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -320,6 +320,8 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, if (index == 0) { entry->ebx &= kvm_supported_word9_x86_features; cpuid_mask(&entry->ebx, 9); + // TSC_ADJUST is emulated + entry->ebx |= F(TSC_ADJUST); } else entry->ebx = 0; entry->eax = 0; @@ -659,6 +661,7 @@ void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) } else *eax = *ebx = *ecx = *edx = 0; } +EXPORT_SYMBOL_GPL(kvm_cpuid); void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) { diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 58fc5148882..b7fd0798488 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -31,6 +31,14 @@ static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu) return best && (best->ecx & bit(X86_FEATURE_XSAVE)); } +static inline bool guest_cpuid_has_tsc_adjust(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 7, 0); + return best && (best->ebx & bit(X86_FEATURE_TSC_ADJUST)); +} + static inline bool guest_cpuid_has_smep(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index bba39bfa1c4..a27e7637110 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -676,8 +676,9 @@ static int __linearize(struct x86_emulate_ctxt *ctxt, addr.seg); if (!usable) goto bad; - /* code segment or read-only data segment */ - if (((desc.type & 8) || !(desc.type & 2)) && write) + /* code segment in protected mode or read-only data segment */ + if ((((ctxt->mode != X86EMUL_MODE_REAL) && (desc.type & 8)) + || !(desc.type & 2)) && write) goto bad; /* unreadable code segment */ if (!fetch && (desc.type & 8) && !(desc.type & 2)) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 43e9fadca5d..9392f527f10 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1011,7 +1011,7 @@ static void start_apic_timer(struct kvm_lapic *apic) local_irq_save(flags); now = apic->lapic_timer.timer.base->get_time(); - guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu); + guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, native_read_tsc()); if (likely(tscdeadline > guest_tsc)) { ns = (tscdeadline - guest_tsc) * 1000000ULL; do_div(ns, this_tsc_khz); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 6f85fe0bf95..01d7c2ad05f 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2382,12 +2382,20 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, || (!vcpu->arch.mmu.direct_map && write_fault && !is_write_protection(vcpu) && !user_fault)) { + /* + * There are two cases: + * - the one is other vcpu creates new sp in the window + * between mapping_level() and acquiring mmu-lock. + * - the another case is the new sp is created by itself + * (page-fault path) when guest uses the target gfn as + * its page table. + * Both of these cases can be fixed by allowing guest to + * retry the access, it will refault, then we can establish + * the mapping by using small page. + */ if (level > PT_PAGE_TABLE_LEVEL && - has_wrprotected_page(vcpu->kvm, gfn, level)) { - ret = 1; - drop_spte(vcpu->kvm, sptep); + has_wrprotected_page(vcpu->kvm, gfn, level)) goto done; - } spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE; @@ -2505,6 +2513,14 @@ static void nonpaging_new_cr3(struct kvm_vcpu *vcpu) mmu_free_roots(vcpu); } +static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level) +{ + int bit7; + + bit7 = (gpte >> 7) & 1; + return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) != 0; +} + static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, bool no_dirty_log) { @@ -2517,6 +2533,26 @@ static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, return gfn_to_pfn_memslot_atomic(slot, gfn); } +static bool prefetch_invalid_gpte(struct kvm_vcpu *vcpu, + struct kvm_mmu_page *sp, u64 *spte, + u64 gpte) +{ + if (is_rsvd_bits_set(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL)) + goto no_present; + + if (!is_present_gpte(gpte)) + goto no_present; + + if (!(gpte & PT_ACCESSED_MASK)) + goto no_present; + + return false; + +no_present: + drop_spte(vcpu->kvm, spte); + return true; +} + static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *start, u64 *end) @@ -2671,7 +2707,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, * PT_PAGE_TABLE_LEVEL and there would be no adjustment done * here. */ - if (!is_error_pfn(pfn) && !kvm_is_mmio_pfn(pfn) && + if (!is_error_noslot_pfn(pfn) && !kvm_is_mmio_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL && PageTransCompound(pfn_to_page(pfn)) && !has_wrprotected_page(vcpu->kvm, gfn, PT_DIRECTORY_LEVEL)) { @@ -2699,18 +2735,13 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, } } -static bool mmu_invalid_pfn(pfn_t pfn) -{ - return unlikely(is_invalid_pfn(pfn)); -} - static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, pfn_t pfn, unsigned access, int *ret_val) { bool ret = true; /* The pfn is invalid, report the error! */ - if (unlikely(is_invalid_pfn(pfn))) { + if (unlikely(is_error_pfn(pfn))) { *ret_val = kvm_handle_bad_page(vcpu, gfn, pfn); goto exit; } @@ -2862,7 +2893,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, return r; spin_lock(&vcpu->kvm->mmu_lock); - if (mmu_notifier_retry(vcpu, mmu_seq)) + if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) goto out_unlock; kvm_mmu_free_some_pages(vcpu); if (likely(!force_pt_level)) @@ -3331,7 +3362,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, return r; spin_lock(&vcpu->kvm->mmu_lock); - if (mmu_notifier_retry(vcpu, mmu_seq)) + if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) goto out_unlock; kvm_mmu_free_some_pages(vcpu); if (likely(!force_pt_level)) @@ -3399,14 +3430,6 @@ static void paging_free(struct kvm_vcpu *vcpu) nonpaging_free(vcpu); } -static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level) -{ - int bit7; - - bit7 = (gpte >> 7) & 1; - return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) != 0; -} - static inline void protect_clean_gpte(unsigned *access, unsigned gpte) { unsigned mask; diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 714e2c01a6f..891eb6d93b8 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -305,51 +305,43 @@ static int FNAME(walk_addr_nested)(struct guest_walker *walker, addr, access); } -static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *sp, u64 *spte, - pt_element_t gpte) +static bool +FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, + u64 *spte, pt_element_t gpte, bool no_dirty_log) { - if (is_rsvd_bits_set(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL)) - goto no_present; - - if (!is_present_gpte(gpte)) - goto no_present; - - if (!(gpte & PT_ACCESSED_MASK)) - goto no_present; - - return false; - -no_present: - drop_spte(vcpu->kvm, spte); - return true; -} - -static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - u64 *spte, const void *pte) -{ - pt_element_t gpte; unsigned pte_access; + gfn_t gfn; pfn_t pfn; - gpte = *(const pt_element_t *)pte; - if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte)) - return; + if (prefetch_invalid_gpte(vcpu, sp, spte, gpte)) + return false; pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte); + + gfn = gpte_to_gfn(gpte); pte_access = sp->role.access & gpte_access(vcpu, gpte); protect_clean_gpte(&pte_access, gpte); - pfn = gfn_to_pfn_atomic(vcpu->kvm, gpte_to_gfn(gpte)); - if (mmu_invalid_pfn(pfn)) - return; + pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn, + no_dirty_log && (pte_access & ACC_WRITE_MASK)); + if (is_error_pfn(pfn)) + return false; /* - * we call mmu_set_spte() with host_writable = true because that - * vcpu->arch.update_pte.pfn was fetched from get_user_pages(write = 1). + * we call mmu_set_spte() with host_writable = true because + * pte_prefetch_gfn_to_pfn always gets a writable pfn. */ mmu_set_spte(vcpu, spte, sp->role.access, pte_access, 0, 0, - NULL, PT_PAGE_TABLE_LEVEL, - gpte_to_gfn(gpte), pfn, true, true); + NULL, PT_PAGE_TABLE_LEVEL, gfn, pfn, true, true); + + return true; +} + +static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, + u64 *spte, const void *pte) +{ + pt_element_t gpte = *(const pt_element_t *)pte; + + FNAME(prefetch_gpte)(vcpu, sp, spte, gpte, false); } static bool FNAME(gpte_changed)(struct kvm_vcpu *vcpu, @@ -395,53 +387,34 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, spte = sp->spt + i; for (i = 0; i < PTE_PREFETCH_NUM; i++, spte++) { - pt_element_t gpte; - unsigned pte_access; - gfn_t gfn; - pfn_t pfn; - if (spte == sptep) continue; if (is_shadow_present_pte(*spte)) continue; - gpte = gptep[i]; - - if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte)) - continue; - - pte_access = sp->role.access & gpte_access(vcpu, gpte); - protect_clean_gpte(&pte_access, gpte); - gfn = gpte_to_gfn(gpte); - pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn, - pte_access & ACC_WRITE_MASK); - if (mmu_invalid_pfn(pfn)) + if (!FNAME(prefetch_gpte)(vcpu, sp, spte, gptep[i], true)) break; - - mmu_set_spte(vcpu, spte, sp->role.access, pte_access, 0, 0, - NULL, PT_PAGE_TABLE_LEVEL, gfn, - pfn, true, true); } } /* * Fetch a shadow pte for a specific level in the paging hierarchy. + * If the guest tries to write a write-protected page, we need to + * emulate this operation, return 1 to indicate this case. */ -static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, +static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, struct guest_walker *gw, int user_fault, int write_fault, int hlevel, - int *emulate, pfn_t pfn, bool map_writable, - bool prefault) + pfn_t pfn, bool map_writable, bool prefault) { - unsigned access = gw->pt_access; struct kvm_mmu_page *sp = NULL; - int top_level; - unsigned direct_access; struct kvm_shadow_walk_iterator it; + unsigned direct_access, access = gw->pt_access; + int top_level, emulate = 0; if (!is_present_gpte(gw->ptes[gw->level - 1])) - return NULL; + return 0; direct_access = gw->pte_access; @@ -505,17 +478,17 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, clear_sp_write_flooding_count(it.sptep); mmu_set_spte(vcpu, it.sptep, access, gw->pte_access, - user_fault, write_fault, emulate, it.level, + user_fault, write_fault, &emulate, it.level, gw->gfn, pfn, prefault, map_writable); FNAME(pte_prefetch)(vcpu, gw, it.sptep); - return it.sptep; + return emulate; out_gpte_changed: if (sp) kvm_mmu_put_page(sp, it.sptep); kvm_release_pfn_clean(pfn); - return NULL; + return 0; } /* @@ -538,8 +511,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, int write_fault = error_code & PFERR_WRITE_MASK; int user_fault = error_code & PFERR_USER_MASK; struct guest_walker walker; - u64 *sptep; - int emulate = 0; int r; pfn_t pfn; int level = PT_PAGE_TABLE_LEVEL; @@ -594,24 +565,20 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, return r; spin_lock(&vcpu->kvm->mmu_lock); - if (mmu_notifier_retry(vcpu, mmu_seq)) + if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) goto out_unlock; kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT); kvm_mmu_free_some_pages(vcpu); if (!force_pt_level) transparent_hugepage_adjust(vcpu, &walker.gfn, &pfn, &level); - sptep = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault, - level, &emulate, pfn, map_writable, prefault); - (void)sptep; - pgprintk("%s: shadow pte %p %llx emulate %d\n", __func__, - sptep, *sptep, emulate); - + r = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault, + level, pfn, map_writable, prefault); ++vcpu->stat.pf_fixed; kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT); spin_unlock(&vcpu->kvm->mmu_lock); - return emulate; + return r; out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); @@ -757,7 +724,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) sizeof(pt_element_t))) return -EINVAL; - if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) { + if (prefetch_invalid_gpte(vcpu, sp, &sp->spt[i], gpte)) { vcpu->kvm->tlbs_dirty++; continue; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index d017df3899e..d29d3cd1c15 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -20,6 +20,7 @@ #include "mmu.h" #include "kvm_cache_regs.h" #include "x86.h" +#include "cpuid.h" #include <linux/module.h> #include <linux/mod_devicetable.h> @@ -630,15 +631,12 @@ static int svm_hardware_enable(void *garbage) return -EBUSY; if (!has_svm()) { - printk(KERN_ERR "svm_hardware_enable: err EOPNOTSUPP on %d\n", - me); + pr_err("%s: err EOPNOTSUPP on %d\n", __func__, me); return -EINVAL; } sd = per_cpu(svm_data, me); - if (!sd) { - printk(KERN_ERR "svm_hardware_enable: svm_data is NULL on %d\n", - me); + pr_err("%s: svm_data is NULL on %d\n", __func__, me); return -EINVAL; } @@ -1012,6 +1010,13 @@ static void svm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) svm->tsc_ratio = ratio; } +static u64 svm_read_tsc_offset(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + return svm->vmcb->control.tsc_offset; +} + static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1189,6 +1194,8 @@ static void init_vmcb(struct vcpu_svm *svm) static int svm_vcpu_reset(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + u32 dummy; + u32 eax = 1; init_vmcb(svm); @@ -1197,8 +1204,9 @@ static int svm_vcpu_reset(struct kvm_vcpu *vcpu) svm->vmcb->save.cs.base = svm->vcpu.arch.sipi_vector << 12; svm->vmcb->save.cs.selector = svm->vcpu.arch.sipi_vector << 8; } - vcpu->arch.regs_avail = ~0; - vcpu->arch.regs_dirty = ~0; + + kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy); + kvm_register_write(vcpu, VCPU_REGS_RDX, eax); return 0; } @@ -1254,11 +1262,6 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT; svm->asid_generation = 0; init_vmcb(svm); - kvm_write_tsc(&svm->vcpu, 0); - - err = fx_init(&svm->vcpu); - if (err) - goto free_page4; svm->vcpu.arch.apic_base = 0xfee00000 | MSR_IA32_APICBASE_ENABLE; if (kvm_vcpu_is_bsp(&svm->vcpu)) @@ -1268,8 +1271,6 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) return &svm->vcpu; -free_page4: - __free_page(hsave_page); free_page3: __free_pages(nested_msrpm_pages, MSRPM_ALLOC_ORDER); free_page2: @@ -3008,11 +3009,11 @@ static int cr8_write_interception(struct vcpu_svm *svm) return 0; } -u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu) +u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) { struct vmcb *vmcb = get_host_vmcb(to_svm(vcpu)); return vmcb->control.tsc_offset + - svm_scale_tsc(vcpu, native_read_tsc()); + svm_scale_tsc(vcpu, host_tsc); } static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) @@ -3131,13 +3132,15 @@ static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data) return 0; } -static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) +static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { struct vcpu_svm *svm = to_svm(vcpu); + u32 ecx = msr->index; + u64 data = msr->data; switch (ecx) { case MSR_IA32_TSC: - kvm_write_tsc(vcpu, data); + kvm_write_tsc(vcpu, msr); break; case MSR_STAR: svm->vmcb->save.star = data; @@ -3192,20 +3195,24 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); break; default: - return kvm_set_msr_common(vcpu, ecx, data); + return kvm_set_msr_common(vcpu, msr); } return 0; } static int wrmsr_interception(struct vcpu_svm *svm) { + struct msr_data msr; u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; u64 data = (svm->vcpu.arch.regs[VCPU_REGS_RAX] & -1u) | ((u64)(svm->vcpu.arch.regs[VCPU_REGS_RDX] & -1u) << 32); + msr.data = data; + msr.index = ecx; + msr.host_initiated = false; svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; - if (svm_set_msr(&svm->vcpu, ecx, data)) { + if (svm_set_msr(&svm->vcpu, &msr)) { trace_kvm_msr_write_ex(ecx, data); kvm_inject_gp(&svm->vcpu, 0); } else { @@ -4302,6 +4309,7 @@ static struct kvm_x86_ops svm_x86_ops = { .has_wbinvd_exit = svm_has_wbinvd_exit, .set_tsc_khz = svm_set_tsc_khz, + .read_tsc_offset = svm_read_tsc_offset, .write_tsc_offset = svm_write_tsc_offset, .adjust_tsc_offset = svm_adjust_tsc_offset, .compute_tsc_offset = svm_compute_tsc_offset, diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index bca63f04dcc..fe5e00ed703 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -4,6 +4,7 @@ #include <linux/tracepoint.h> #include <asm/vmx.h> #include <asm/svm.h> +#include <asm/clocksource.h> #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm @@ -754,6 +755,68 @@ TRACE_EVENT( __entry->write ? "Write" : "Read", __entry->gpa_match ? "GPA" : "GVA") ); + +#ifdef CONFIG_X86_64 + +#define host_clocks \ + {VCLOCK_NONE, "none"}, \ + {VCLOCK_TSC, "tsc"}, \ + {VCLOCK_HPET, "hpet"} \ + +TRACE_EVENT(kvm_update_master_clock, + TP_PROTO(bool use_master_clock, unsigned int host_clock, bool offset_matched), + TP_ARGS(use_master_clock, host_clock, offset_matched), + + TP_STRUCT__entry( + __field( bool, use_master_clock ) + __field( unsigned int, host_clock ) + __field( bool, offset_matched ) + ), + + TP_fast_assign( + __entry->use_master_clock = use_master_clock; + __entry->host_clock = host_clock; + __entry->offset_matched = offset_matched; + ), + + TP_printk("masterclock %d hostclock %s offsetmatched %u", + __entry->use_master_clock, + __print_symbolic(__entry->host_clock, host_clocks), + __entry->offset_matched) +); + +TRACE_EVENT(kvm_track_tsc, + TP_PROTO(unsigned int vcpu_id, unsigned int nr_matched, + unsigned int online_vcpus, bool use_master_clock, + unsigned int host_clock), + TP_ARGS(vcpu_id, nr_matched, online_vcpus, use_master_clock, + host_clock), + + TP_STRUCT__entry( + __field( unsigned int, vcpu_id ) + __field( unsigned int, nr_vcpus_matched_tsc ) + __field( unsigned int, online_vcpus ) + __field( bool, use_master_clock ) + __field( unsigned int, host_clock ) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->nr_vcpus_matched_tsc = nr_matched; + __entry->online_vcpus = online_vcpus; + __entry->use_master_clock = use_master_clock; + __entry->host_clock = host_clock; + ), + + TP_printk("vcpu_id %u masterclock %u offsetmatched %u nr_online %u" + " hostclock %s", + __entry->vcpu_id, __entry->use_master_clock, + __entry->nr_vcpus_matched_tsc, __entry->online_vcpus, + __print_symbolic(__entry->host_clock, host_clocks)) +); + +#endif /* CONFIG_X86_64 */ + #endif /* _TRACE_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index f85815945fc..9120ae1901e 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -42,6 +42,7 @@ #include <asm/i387.h> #include <asm/xcr.h> #include <asm/perf_event.h> +#include <asm/kexec.h> #include "trace.h" @@ -802,11 +803,6 @@ static inline bool cpu_has_vmx_ept_ad_bits(void) return vmx_capability.ept & VMX_EPT_AD_BIT; } -static inline bool cpu_has_vmx_invept_individual_addr(void) -{ - return vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT; -} - static inline bool cpu_has_vmx_invept_context(void) { return vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT; @@ -992,6 +988,46 @@ static void vmcs_load(struct vmcs *vmcs) vmcs, phys_addr); } +#ifdef CONFIG_KEXEC +/* + * This bitmap is used to indicate whether the vmclear + * operation is enabled on all cpus. All disabled by + * default. + */ +static cpumask_t crash_vmclear_enabled_bitmap = CPU_MASK_NONE; + +static inline void crash_enable_local_vmclear(int cpu) +{ + cpumask_set_cpu(cpu, &crash_vmclear_enabled_bitmap); +} + +static inline void crash_disable_local_vmclear(int cpu) +{ + cpumask_clear_cpu(cpu, &crash_vmclear_enabled_bitmap); +} + +static inline int crash_local_vmclear_enabled(int cpu) +{ + return cpumask_test_cpu(cpu, &crash_vmclear_enabled_bitmap); +} + +static void crash_vmclear_local_loaded_vmcss(void) +{ + int cpu = raw_smp_processor_id(); + struct loaded_vmcs *v; + + if (!crash_local_vmclear_enabled(cpu)) + return; + + list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu), + loaded_vmcss_on_cpu_link) + vmcs_clear(v->vmcs); +} +#else +static inline void crash_enable_local_vmclear(int cpu) { } +static inline void crash_disable_local_vmclear(int cpu) { } +#endif /* CONFIG_KEXEC */ + static void __loaded_vmcs_clear(void *arg) { struct loaded_vmcs *loaded_vmcs = arg; @@ -1001,15 +1037,28 @@ static void __loaded_vmcs_clear(void *arg) return; /* vcpu migration can race with cpu offline */ if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs) per_cpu(current_vmcs, cpu) = NULL; + crash_disable_local_vmclear(cpu); list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link); + + /* + * we should ensure updating loaded_vmcs->loaded_vmcss_on_cpu_link + * is before setting loaded_vmcs->vcpu to -1 which is done in + * loaded_vmcs_init. Otherwise, other cpu can see vcpu = -1 fist + * then adds the vmcs into percpu list before it is deleted. + */ + smp_wmb(); + loaded_vmcs_init(loaded_vmcs); + crash_enable_local_vmclear(cpu); } static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs) { - if (loaded_vmcs->cpu != -1) - smp_call_function_single( - loaded_vmcs->cpu, __loaded_vmcs_clear, loaded_vmcs, 1); + int cpu = loaded_vmcs->cpu; + + if (cpu != -1) + smp_call_function_single(cpu, + __loaded_vmcs_clear, loaded_vmcs, 1); } static inline void vpid_sync_vcpu_single(struct vcpu_vmx *vmx) @@ -1051,17 +1100,6 @@ static inline void ept_sync_context(u64 eptp) } } -static inline void ept_sync_individual_addr(u64 eptp, gpa_t gpa) -{ - if (enable_ept) { - if (cpu_has_vmx_invept_individual_addr()) - __invept(VMX_EPT_EXTENT_INDIVIDUAL_ADDR, - eptp, gpa); - else - ept_sync_context(eptp); - } -} - static __always_inline unsigned long vmcs_readl(unsigned long field) { unsigned long value; @@ -1535,8 +1573,18 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); local_irq_disable(); + crash_disable_local_vmclear(cpu); + + /* + * Read loaded_vmcs->cpu should be before fetching + * loaded_vmcs->loaded_vmcss_on_cpu_link. + * See the comments in __loaded_vmcs_clear(). + */ + smp_rmb(); + list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link, &per_cpu(loaded_vmcss_on_cpu, cpu)); + crash_enable_local_vmclear(cpu); local_irq_enable(); /* @@ -1839,11 +1887,10 @@ static u64 guest_read_tsc(void) * Like guest_read_tsc, but always returns L1's notion of the timestamp * counter, even if a nested guest (L2) is currently running. */ -u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu) +u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) { - u64 host_tsc, tsc_offset; + u64 tsc_offset; - rdtscll(host_tsc); tsc_offset = is_guest_mode(vcpu) ? to_vmx(vcpu)->nested.vmcs01_tsc_offset : vmcs_read64(TSC_OFFSET); @@ -1866,6 +1913,11 @@ static void vmx_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) WARN(1, "user requested TSC rate below hardware speed\n"); } +static u64 vmx_read_tsc_offset(struct kvm_vcpu *vcpu) +{ + return vmcs_read64(TSC_OFFSET); +} + /* * writes 'offset' into guest's timestamp counter offset register */ @@ -2202,15 +2254,17 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ -static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) +static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct shared_msr_entry *msr; int ret = 0; + u32 msr_index = msr_info->index; + u64 data = msr_info->data; switch (msr_index) { case MSR_EFER: - ret = kvm_set_msr_common(vcpu, msr_index, data); + ret = kvm_set_msr_common(vcpu, msr_info); break; #ifdef CONFIG_X86_64 case MSR_FS_BASE: @@ -2236,7 +2290,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) vmcs_writel(GUEST_SYSENTER_ESP, data); break; case MSR_IA32_TSC: - kvm_write_tsc(vcpu, data); + kvm_write_tsc(vcpu, msr_info); break; case MSR_IA32_CR_PAT: if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { @@ -2244,7 +2298,10 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) vcpu->arch.pat = data; break; } - ret = kvm_set_msr_common(vcpu, msr_index, data); + ret = kvm_set_msr_common(vcpu, msr_info); + break; + case MSR_IA32_TSC_ADJUST: + ret = kvm_set_msr_common(vcpu, msr_info); break; case MSR_TSC_AUX: if (!vmx->rdtscp_enabled) @@ -2267,7 +2324,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) } break; } - ret = kvm_set_msr_common(vcpu, msr_index, data); + ret = kvm_set_msr_common(vcpu, msr_info); } return ret; @@ -2341,6 +2398,18 @@ static int hardware_enable(void *garbage) return -EBUSY; INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); + + /* + * Now we can enable the vmclear operation in kdump + * since the loaded_vmcss_on_cpu list on this cpu + * has been initialized. + * + * Though the cpu is not in VMX operation now, there + * is no problem to enable the vmclear operation + * for the loaded_vmcss_on_cpu list is empty! + */ + crash_enable_local_vmclear(cpu); + rdmsrl(MSR_IA32_FEATURE_CONTROL, old); test_bits = FEATURE_CONTROL_LOCKED; @@ -2697,6 +2766,7 @@ static void fix_pmode_dataseg(struct kvm_vcpu *vcpu, int seg, struct kvm_segment if (!(vmcs_readl(sf->base) == tmp.base && tmp.s)) { tmp.base = vmcs_readl(sf->base); tmp.selector = vmcs_read16(sf->selector); + tmp.dpl = tmp.selector & SELECTOR_RPL_MASK; tmp.s = 1; } vmx_set_segment(vcpu, &tmp, seg); @@ -3246,7 +3316,7 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, * unrestricted guest like Westmere to older host that don't have * unrestricted guest like Nehelem. */ - if (!enable_unrestricted_guest && vmx->rmode.vm86_active) { + if (vmx->rmode.vm86_active) { switch (seg) { case VCPU_SREG_CS: vmcs_write32(GUEST_CS_AR_BYTES, 0xf3); @@ -3897,8 +3967,6 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL); set_cr4_guest_host_mask(vmx); - kvm_write_tsc(&vmx->vcpu, 0); - return 0; } @@ -3908,8 +3976,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) u64 msr; int ret; - vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)); - vmx->rmode.vm86_active = 0; vmx->soft_vnmi_blocked = 0; @@ -3921,10 +3987,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) msr |= MSR_IA32_APICBASE_BSP; kvm_set_apic_base(&vmx->vcpu, msr); - ret = fx_init(&vmx->vcpu); - if (ret != 0) - goto out; - vmx_segment_cache_clear(vmx); seg_setup(VCPU_SREG_CS); @@ -3965,7 +4027,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) kvm_rip_write(vcpu, 0xfff0); else kvm_rip_write(vcpu, 0); - kvm_register_write(vcpu, VCPU_REGS_RSP, 0); vmcs_writel(GUEST_GDTR_BASE, 0); vmcs_write32(GUEST_GDTR_LIMIT, 0xffff); @@ -4015,7 +4076,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) /* HACK: Don't enable emulation on guest boot/reset */ vmx->emulation_required = 0; -out: return ret; } @@ -4287,16 +4347,6 @@ static int handle_exception(struct kvm_vcpu *vcpu) if (is_machine_check(intr_info)) return handle_machine_check(vcpu); - if ((vect_info & VECTORING_INFO_VALID_MASK) && - !is_page_fault(intr_info)) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_SIMUL_EX; - vcpu->run->internal.ndata = 2; - vcpu->run->internal.data[0] = vect_info; - vcpu->run->internal.data[1] = intr_info; - return 0; - } - if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR) return 1; /* already handled by vmx_vcpu_run() */ @@ -4315,6 +4365,22 @@ static int handle_exception(struct kvm_vcpu *vcpu) error_code = 0; if (intr_info & INTR_INFO_DELIVER_CODE_MASK) error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); + + /* + * The #PF with PFEC.RSVD = 1 indicates the guest is accessing + * MMIO, it is better to report an internal error. + * See the comments in vmx_handle_exit. + */ + if ((vect_info & VECTORING_INFO_VALID_MASK) && + !(is_page_fault(intr_info) && !(error_code & PFERR_RSVD_MASK))) { + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_SIMUL_EX; + vcpu->run->internal.ndata = 2; + vcpu->run->internal.data[0] = vect_info; + vcpu->run->internal.data[1] = intr_info; + return 0; + } + if (is_page_fault(intr_info)) { /* EPT won't cause page fault directly */ BUG_ON(enable_ept); @@ -4626,11 +4692,15 @@ static int handle_rdmsr(struct kvm_vcpu *vcpu) static int handle_wrmsr(struct kvm_vcpu *vcpu) { + struct msr_data msr; u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX]; u64 data = (vcpu->arch.regs[VCPU_REGS_RAX] & -1u) | ((u64)(vcpu->arch.regs[VCPU_REGS_RDX] & -1u) << 32); - if (vmx_set_msr(vcpu, ecx, data) != 0) { + msr.data = data; + msr.index = ecx; + msr.host_initiated = false; + if (vmx_set_msr(vcpu, &msr) != 0) { trace_kvm_msr_write_ex(ecx, data); kvm_inject_gp(vcpu, 0); return 1; @@ -4827,11 +4897,6 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - if (exit_qualification & (1 << 6)) { - printk(KERN_ERR "EPT: GPA exceeds GAW!\n"); - return -EINVAL; - } - gla_validity = (exit_qualification >> 7) & 0x3; if (gla_validity != 0x3 && gla_validity != 0x1 && gla_validity != 0) { printk(KERN_ERR "EPT: Handling EPT violation failed!\n"); @@ -5979,13 +6044,24 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) return 0; } + /* + * Note: + * Do not try to fix EXIT_REASON_EPT_MISCONFIG if it caused by + * delivery event since it indicates guest is accessing MMIO. + * The vm-exit can be triggered again after return to guest that + * will cause infinite loop. + */ if ((vectoring_info & VECTORING_INFO_VALID_MASK) && (exit_reason != EXIT_REASON_EXCEPTION_NMI && exit_reason != EXIT_REASON_EPT_VIOLATION && - exit_reason != EXIT_REASON_TASK_SWITCH)) - printk(KERN_WARNING "%s: unexpected, valid vectoring info " - "(0x%x) and exit reason is 0x%x\n", - __func__, vectoring_info, exit_reason); + exit_reason != EXIT_REASON_TASK_SWITCH)) { + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; + vcpu->run->internal.ndata = 2; + vcpu->run->internal.data[0] = vectoring_info; + vcpu->run->internal.data[1] = exit_reason; + return 0; + } if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked && !(is_guest_mode(vcpu) && nested_cpu_has_virtual_nmis( @@ -7309,6 +7385,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, .set_tsc_khz = vmx_set_tsc_khz, + .read_tsc_offset = vmx_read_tsc_offset, .write_tsc_offset = vmx_write_tsc_offset, .adjust_tsc_offset = vmx_adjust_tsc_offset, .compute_tsc_offset = vmx_compute_tsc_offset, @@ -7367,6 +7444,11 @@ static int __init vmx_init(void) if (r) goto out3; +#ifdef CONFIG_KEXEC + rcu_assign_pointer(crash_vmclear_loaded_vmcss, + crash_vmclear_local_loaded_vmcss); +#endif + vmx_disable_intercept_for_msr(MSR_FS_BASE, false); vmx_disable_intercept_for_msr(MSR_GS_BASE, false); vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true); @@ -7404,6 +7486,11 @@ static void __exit vmx_exit(void) free_page((unsigned long)vmx_io_bitmap_b); free_page((unsigned long)vmx_io_bitmap_a); +#ifdef CONFIG_KEXEC + rcu_assign_pointer(crash_vmclear_loaded_vmcss, NULL); + synchronize_rcu(); +#endif + kvm_exit(); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4f7641756be..76f54461f7c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -46,6 +46,8 @@ #include <linux/uaccess.h> #include <linux/hash.h> #include <linux/pci.h> +#include <linux/timekeeper_internal.h> +#include <linux/pvclock_gtod.h> #include <trace/events/kvm.h> #define CREATE_TRACE_POINTS @@ -158,7 +160,9 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { u64 __read_mostly host_xcr0; -int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt); +static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt); + +static int kvm_vcpu_reset(struct kvm_vcpu *vcpu); static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu) { @@ -633,7 +637,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) } if (is_long_mode(vcpu)) { - if (kvm_read_cr4(vcpu) & X86_CR4_PCIDE) { + if (kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) { if (cr3 & CR3_PCID_ENABLED_RESERVED_BITS) return 1; } else @@ -827,6 +831,7 @@ static u32 msrs_to_save[] = { static unsigned num_msrs_to_save; static const u32 emulated_msrs[] = { + MSR_IA32_TSC_ADJUST, MSR_IA32_TSCDEADLINE, MSR_IA32_MISC_ENABLE, MSR_IA32_MCG_STATUS, @@ -886,9 +891,9 @@ EXPORT_SYMBOL_GPL(kvm_enable_efer_bits); * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ -int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) +int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { - return kvm_x86_ops->set_msr(vcpu, msr_index, data); + return kvm_x86_ops->set_msr(vcpu, msr); } /* @@ -896,9 +901,63 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) */ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) { - return kvm_set_msr(vcpu, index, *data); + struct msr_data msr; + + msr.data = *data; + msr.index = index; + msr.host_initiated = true; + return kvm_set_msr(vcpu, &msr); } +#ifdef CONFIG_X86_64 +struct pvclock_gtod_data { + seqcount_t seq; + + struct { /* extract of a clocksource struct */ + int vclock_mode; + cycle_t cycle_last; + cycle_t mask; + u32 mult; + u32 shift; + } clock; + + /* open coded 'struct timespec' */ + u64 monotonic_time_snsec; + time_t monotonic_time_sec; +}; + +static struct pvclock_gtod_data pvclock_gtod_data; + +static void update_pvclock_gtod(struct timekeeper *tk) +{ + struct pvclock_gtod_data *vdata = &pvclock_gtod_data; + + write_seqcount_begin(&vdata->seq); + + /* copy pvclock gtod data */ + vdata->clock.vclock_mode = tk->clock->archdata.vclock_mode; + vdata->clock.cycle_last = tk->clock->cycle_last; + vdata->clock.mask = tk->clock->mask; + vdata->clock.mult = tk->mult; + vdata->clock.shift = tk->shift; + + vdata->monotonic_time_sec = tk->xtime_sec + + tk->wall_to_monotonic.tv_sec; + vdata->monotonic_time_snsec = tk->xtime_nsec + + (tk->wall_to_monotonic.tv_nsec + << tk->shift); + while (vdata->monotonic_time_snsec >= + (((u64)NSEC_PER_SEC) << tk->shift)) { + vdata->monotonic_time_snsec -= + ((u64)NSEC_PER_SEC) << tk->shift; + vdata->monotonic_time_sec++; + } + + write_seqcount_end(&vdata->seq); +} +#endif + + static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) { int version; @@ -995,6 +1054,10 @@ static inline u64 get_kernel_ns(void) return timespec_to_ns(&ts); } +#ifdef CONFIG_X86_64 +static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0); +#endif + static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz); unsigned long max_tsc_khz; @@ -1046,12 +1109,47 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) return tsc; } -void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data) +void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_X86_64 + bool vcpus_matched; + bool do_request = false; + struct kvm_arch *ka = &vcpu->kvm->arch; + struct pvclock_gtod_data *gtod = &pvclock_gtod_data; + + vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 == + atomic_read(&vcpu->kvm->online_vcpus)); + + if (vcpus_matched && gtod->clock.vclock_mode == VCLOCK_TSC) + if (!ka->use_master_clock) + do_request = 1; + + if (!vcpus_matched && ka->use_master_clock) + do_request = 1; + + if (do_request) + kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); + + trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc, + atomic_read(&vcpu->kvm->online_vcpus), + ka->use_master_clock, gtod->clock.vclock_mode); +#endif +} + +static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset) +{ + u64 curr_offset = kvm_x86_ops->read_tsc_offset(vcpu); + vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset; +} + +void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) { struct kvm *kvm = vcpu->kvm; u64 offset, ns, elapsed; unsigned long flags; s64 usdiff; + bool matched; + u64 data = msr->data; raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); offset = kvm_x86_ops->compute_tsc_offset(vcpu, data); @@ -1094,6 +1192,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data) offset = kvm_x86_ops->compute_tsc_offset(vcpu, data); pr_debug("kvm: adjusted tsc offset by %llu\n", delta); } + matched = true; } else { /* * We split periods of matched TSC writes into generations. @@ -1108,6 +1207,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data) kvm->arch.cur_tsc_nsec = ns; kvm->arch.cur_tsc_write = data; kvm->arch.cur_tsc_offset = offset; + matched = false; pr_debug("kvm: new tsc generation %u, clock %llu\n", kvm->arch.cur_tsc_generation, data); } @@ -1129,26 +1229,195 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data) vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec; vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write; + if (guest_cpuid_has_tsc_adjust(vcpu) && !msr->host_initiated) + update_ia32_tsc_adjust_msr(vcpu, offset); kvm_x86_ops->write_tsc_offset(vcpu, offset); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); + + spin_lock(&kvm->arch.pvclock_gtod_sync_lock); + if (matched) + kvm->arch.nr_vcpus_matched_tsc++; + else + kvm->arch.nr_vcpus_matched_tsc = 0; + + kvm_track_tsc_matching(vcpu); + spin_unlock(&kvm->arch.pvclock_gtod_sync_lock); } EXPORT_SYMBOL_GPL(kvm_write_tsc); +#ifdef CONFIG_X86_64 + +static cycle_t read_tsc(void) +{ + cycle_t ret; + u64 last; + + /* + * Empirically, a fence (of type that depends on the CPU) + * before rdtsc is enough to ensure that rdtsc is ordered + * with respect to loads. The various CPU manuals are unclear + * as to whether rdtsc can be reordered with later loads, + * but no one has ever seen it happen. + */ + rdtsc_barrier(); + ret = (cycle_t)vget_cycles(); + + last = pvclock_gtod_data.clock.cycle_last; + + if (likely(ret >= last)) + return ret; + + /* + * GCC likes to generate cmov here, but this branch is extremely + * predictable (it's just a funciton of time and the likely is + * very likely) and there's a data dependence, so force GCC + * to generate a branch instead. I don't barrier() because + * we don't actually need a barrier, and if this function + * ever gets inlined it will generate worse code. + */ + asm volatile (""); + return last; +} + +static inline u64 vgettsc(cycle_t *cycle_now) +{ + long v; + struct pvclock_gtod_data *gtod = &pvclock_gtod_data; + + *cycle_now = read_tsc(); + + v = (*cycle_now - gtod->clock.cycle_last) & gtod->clock.mask; + return v * gtod->clock.mult; +} + +static int do_monotonic(struct timespec *ts, cycle_t *cycle_now) +{ + unsigned long seq; + u64 ns; + int mode; + struct pvclock_gtod_data *gtod = &pvclock_gtod_data; + + ts->tv_nsec = 0; + do { + seq = read_seqcount_begin(>od->seq); + mode = gtod->clock.vclock_mode; + ts->tv_sec = gtod->monotonic_time_sec; + ns = gtod->monotonic_time_snsec; + ns += vgettsc(cycle_now); + ns >>= gtod->clock.shift; + } while (unlikely(read_seqcount_retry(>od->seq, seq))); + timespec_add_ns(ts, ns); + + return mode; +} + +/* returns true if host is using tsc clocksource */ +static bool kvm_get_time_and_clockread(s64 *kernel_ns, cycle_t *cycle_now) +{ + struct timespec ts; + + /* checked again under seqlock below */ + if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC) + return false; + + if (do_monotonic(&ts, cycle_now) != VCLOCK_TSC) + return false; + + monotonic_to_bootbased(&ts); + *kernel_ns = timespec_to_ns(&ts); + + return true; +} +#endif + +/* + * + * Assuming a stable TSC across physical CPUS, and a stable TSC + * across virtual CPUs, the following condition is possible. + * Each numbered line represents an event visible to both + * CPUs at the next numbered event. + * + * "timespecX" represents host monotonic time. "tscX" represents + * RDTSC value. + * + * VCPU0 on CPU0 | VCPU1 on CPU1 + * + * 1. read timespec0,tsc0 + * 2. | timespec1 = timespec0 + N + * | tsc1 = tsc0 + M + * 3. transition to guest | transition to guest + * 4. ret0 = timespec0 + (rdtsc - tsc0) | + * 5. | ret1 = timespec1 + (rdtsc - tsc1) + * | ret1 = timespec0 + N + (rdtsc - (tsc0 + M)) + * + * Since ret0 update is visible to VCPU1 at time 5, to obey monotonicity: + * + * - ret0 < ret1 + * - timespec0 + (rdtsc - tsc0) < timespec0 + N + (rdtsc - (tsc0 + M)) + * ... + * - 0 < N - M => M < N + * + * That is, when timespec0 != timespec1, M < N. Unfortunately that is not + * always the case (the difference between two distinct xtime instances + * might be smaller then the difference between corresponding TSC reads, + * when updating guest vcpus pvclock areas). + * + * To avoid that problem, do not allow visibility of distinct + * system_timestamp/tsc_timestamp values simultaneously: use a master + * copy of host monotonic time values. Update that master copy + * in lockstep. + * + * Rely on synchronization of host TSCs and guest TSCs for monotonicity. + * + */ + +static void pvclock_update_vm_gtod_copy(struct kvm *kvm) +{ +#ifdef CONFIG_X86_64 + struct kvm_arch *ka = &kvm->arch; + int vclock_mode; + bool host_tsc_clocksource, vcpus_matched; + + vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 == + atomic_read(&kvm->online_vcpus)); + + /* + * If the host uses TSC clock, then passthrough TSC as stable + * to the guest. + */ + host_tsc_clocksource = kvm_get_time_and_clockread( + &ka->master_kernel_ns, + &ka->master_cycle_now); + + ka->use_master_clock = host_tsc_clocksource & vcpus_matched; + + if (ka->use_master_clock) + atomic_set(&kvm_guest_has_master_clock, 1); + + vclock_mode = pvclock_gtod_data.clock.vclock_mode; + trace_kvm_update_master_clock(ka->use_master_clock, vclock_mode, + vcpus_matched); +#endif +} + static int kvm_guest_time_update(struct kvm_vcpu *v) { - unsigned long flags; + unsigned long flags, this_tsc_khz; struct kvm_vcpu_arch *vcpu = &v->arch; + struct kvm_arch *ka = &v->kvm->arch; void *shared_kaddr; - unsigned long this_tsc_khz; s64 kernel_ns, max_kernel_ns; - u64 tsc_timestamp; + u64 tsc_timestamp, host_tsc; + struct pvclock_vcpu_time_info *guest_hv_clock; u8 pvclock_flags; + bool use_master_clock; + + kernel_ns = 0; + host_tsc = 0; /* Keep irq disabled to prevent changes to the clock */ local_irq_save(flags); - tsc_timestamp = kvm_x86_ops->read_l1_tsc(v); - kernel_ns = get_kernel_ns(); this_tsc_khz = __get_cpu_var(cpu_tsc_khz); if (unlikely(this_tsc_khz == 0)) { local_irq_restore(flags); @@ -1157,6 +1426,24 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) } /* + * If the host uses TSC clock, then passthrough TSC as stable + * to the guest. + */ + spin_lock(&ka->pvclock_gtod_sync_lock); + use_master_clock = ka->use_master_clock; + if (use_master_clock) { + host_tsc = ka->master_cycle_now; + kernel_ns = ka->master_kernel_ns; + } + spin_unlock(&ka->pvclock_gtod_sync_lock); + if (!use_master_clock) { + host_tsc = native_read_tsc(); + kernel_ns = get_kernel_ns(); + } + + tsc_timestamp = kvm_x86_ops->read_l1_tsc(v, host_tsc); + + /* * We may have to catch up the TSC to match elapsed wall clock * time for two reasons, even if kvmclock is used. * 1) CPU could have been running below the maximum TSC rate @@ -1217,23 +1504,20 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) vcpu->hw_tsc_khz = this_tsc_khz; } - if (max_kernel_ns > kernel_ns) - kernel_ns = max_kernel_ns; - + /* with a master <monotonic time, tsc value> tuple, + * pvclock clock reads always increase at the (scaled) rate + * of guest TSC - no need to deal with sampling errors. + */ + if (!use_master_clock) { + if (max_kernel_ns > kernel_ns) + kernel_ns = max_kernel_ns; + } /* With all the info we got, fill in the values */ vcpu->hv_clock.tsc_timestamp = tsc_timestamp; vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset; vcpu->last_kernel_ns = kernel_ns; vcpu->last_guest_tsc = tsc_timestamp; - pvclock_flags = 0; - if (vcpu->pvclock_set_guest_stopped_request) { - pvclock_flags |= PVCLOCK_GUEST_STOPPED; - vcpu->pvclock_set_guest_stopped_request = false; - } - - vcpu->hv_clock.flags = pvclock_flags; - /* * The interface expects us to write an even number signaling that the * update is finished. Since the guest won't see the intermediate @@ -1243,6 +1527,22 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) shared_kaddr = kmap_atomic(vcpu->time_page); + guest_hv_clock = shared_kaddr + vcpu->time_offset; + + /* retain PVCLOCK_GUEST_STOPPED if set in guest copy */ + pvclock_flags = (guest_hv_clock->flags & PVCLOCK_GUEST_STOPPED); + + if (vcpu->pvclock_set_guest_stopped_request) { + pvclock_flags |= PVCLOCK_GUEST_STOPPED; + vcpu->pvclock_set_guest_stopped_request = false; + } + + /* If the host uses TSC clocksource, then it is stable */ + if (use_master_clock) + pvclock_flags |= PVCLOCK_TSC_STABLE_BIT; + + vcpu->hv_clock.flags = pvclock_flags; + memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock, sizeof(vcpu->hv_clock)); @@ -1572,9 +1872,11 @@ static void record_steal_time(struct kvm_vcpu *vcpu) &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); } -int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) +int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { bool pr = false; + u32 msr = msr_info->index; + u64 data = msr_info->data; switch (msr) { case MSR_EFER: @@ -1625,6 +1927,15 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) case MSR_IA32_TSCDEADLINE: kvm_set_lapic_tscdeadline_msr(vcpu, data); break; + case MSR_IA32_TSC_ADJUST: + if (guest_cpuid_has_tsc_adjust(vcpu)) { + if (!msr_info->host_initiated) { + u64 adj = data - vcpu->arch.ia32_tsc_adjust_msr; + kvm_x86_ops->adjust_tsc_offset(vcpu, adj, true); + } + vcpu->arch.ia32_tsc_adjust_msr = data; + } + break; case MSR_IA32_MISC_ENABLE: vcpu->arch.ia32_misc_enable_msr = data; break; @@ -1984,6 +2295,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_IA32_TSCDEADLINE: data = kvm_get_lapic_tscdeadline_msr(vcpu); break; + case MSR_IA32_TSC_ADJUST: + data = (u64)vcpu->arch.ia32_tsc_adjust_msr; + break; case MSR_IA32_MISC_ENABLE: data = vcpu->arch.ia32_misc_enable_msr; break; @@ -2342,7 +2656,12 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_x86_ops->write_tsc_offset(vcpu, offset); vcpu->arch.tsc_catchup = 1; } - kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); + /* + * On a host with synchronized TSC, there is no need to update + * kvmclock on vcpu->cpu migration + */ + if (!vcpu->kvm->arch.use_master_clock || vcpu->cpu == -1) + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); if (vcpu->cpu != cpu) kvm_migrate_timers(vcpu); vcpu->cpu = cpu; @@ -2691,15 +3010,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (!vcpu->arch.apic) goto out; u.lapic = memdup_user(argp, sizeof(*u.lapic)); - if (IS_ERR(u.lapic)) { - r = PTR_ERR(u.lapic); - goto out; - } + if (IS_ERR(u.lapic)) + return PTR_ERR(u.lapic); r = kvm_vcpu_ioctl_set_lapic(vcpu, u.lapic); - if (r) - goto out; - r = 0; break; } case KVM_INTERRUPT: { @@ -2709,16 +3023,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (copy_from_user(&irq, argp, sizeof irq)) goto out; r = kvm_vcpu_ioctl_interrupt(vcpu, &irq); - if (r) - goto out; - r = 0; break; } case KVM_NMI: { r = kvm_vcpu_ioctl_nmi(vcpu); - if (r) - goto out; - r = 0; break; } case KVM_SET_CPUID: { @@ -2729,8 +3037,6 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) goto out; r = kvm_vcpu_ioctl_set_cpuid(vcpu, &cpuid, cpuid_arg->entries); - if (r) - goto out; break; } case KVM_SET_CPUID2: { @@ -2742,8 +3048,6 @@ long kvm_arch_vcpu_ioctl(struct file *filp, goto out; r = kvm_vcpu_ioctl_set_cpuid2(vcpu, &cpuid, cpuid_arg->entries); - if (r) - goto out; break; } case KVM_GET_CPUID2: { @@ -2875,10 +3179,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp, } case KVM_SET_XSAVE: { u.xsave = memdup_user(argp, sizeof(*u.xsave)); - if (IS_ERR(u.xsave)) { - r = PTR_ERR(u.xsave); - goto out; - } + if (IS_ERR(u.xsave)) + return PTR_ERR(u.xsave); r = kvm_vcpu_ioctl_x86_set_xsave(vcpu, u.xsave); break; @@ -2900,10 +3202,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp, } case KVM_SET_XCRS: { u.xcrs = memdup_user(argp, sizeof(*u.xcrs)); - if (IS_ERR(u.xcrs)) { - r = PTR_ERR(u.xcrs); - goto out; - } + if (IS_ERR(u.xcrs)) + return PTR_ERR(u.xcrs); r = kvm_vcpu_ioctl_x86_set_xcrs(vcpu, u.xcrs); break; @@ -2951,7 +3251,7 @@ static int kvm_vm_ioctl_set_tss_addr(struct kvm *kvm, unsigned long addr) int ret; if (addr > (unsigned int)(-3 * PAGE_SIZE)) - return -1; + return -EINVAL; ret = kvm_x86_ops->set_tss_addr(kvm, addr); return ret; } @@ -3212,8 +3512,6 @@ long kvm_arch_vm_ioctl(struct file *filp, switch (ioctl) { case KVM_SET_TSS_ADDR: r = kvm_vm_ioctl_set_tss_addr(kvm, arg); - if (r < 0) - goto out; break; case KVM_SET_IDENTITY_MAP_ADDR: { u64 ident_addr; @@ -3222,14 +3520,10 @@ long kvm_arch_vm_ioctl(struct file *filp, if (copy_from_user(&ident_addr, argp, sizeof ident_addr)) goto out; r = kvm_vm_ioctl_set_identity_map_addr(kvm, ident_addr); - if (r < 0) - goto out; break; } case KVM_SET_NR_MMU_PAGES: r = kvm_vm_ioctl_set_nr_mmu_pages(kvm, arg); - if (r) - goto out; break; case KVM_GET_NR_MMU_PAGES: r = kvm_vm_ioctl_get_nr_mmu_pages(kvm); @@ -3320,8 +3614,6 @@ long kvm_arch_vm_ioctl(struct file *filp, r = 0; get_irqchip_out: kfree(chip); - if (r) - goto out; break; } case KVM_SET_IRQCHIP: { @@ -3343,8 +3635,6 @@ long kvm_arch_vm_ioctl(struct file *filp, r = 0; set_irqchip_out: kfree(chip); - if (r) - goto out; break; } case KVM_GET_PIT: { @@ -3371,9 +3661,6 @@ long kvm_arch_vm_ioctl(struct file *filp, if (!kvm->arch.vpit) goto out; r = kvm_vm_ioctl_set_pit(kvm, &u.ps); - if (r) - goto out; - r = 0; break; } case KVM_GET_PIT2: { @@ -3397,9 +3684,6 @@ long kvm_arch_vm_ioctl(struct file *filp, if (!kvm->arch.vpit) goto out; r = kvm_vm_ioctl_set_pit2(kvm, &u.ps2); - if (r) - goto out; - r = 0; break; } case KVM_REINJECT_CONTROL: { @@ -3408,9 +3692,6 @@ long kvm_arch_vm_ioctl(struct file *filp, if (copy_from_user(&control, argp, sizeof(control))) goto out; r = kvm_vm_ioctl_reinject(kvm, &control); - if (r) - goto out; - r = 0; break; } case KVM_XEN_HVM_CONFIG: { @@ -4273,7 +4554,12 @@ static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data) { - return kvm_set_msr(emul_to_vcpu(ctxt), msr_index, data); + struct msr_data msr; + + msr.data = data; + msr.index = msr_index; + msr.host_initiated = false; + return kvm_set_msr(emul_to_vcpu(ctxt), &msr); } static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt, @@ -4495,7 +4781,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva) * instruction -> ... */ pfn = gfn_to_pfn(vcpu->kvm, gpa_to_gfn(gpa)); - if (!is_error_pfn(pfn)) { + if (!is_error_noslot_pfn(pfn)) { kvm_release_pfn_clean(pfn); return true; } @@ -4881,6 +5167,50 @@ static void kvm_set_mmio_spte_mask(void) kvm_mmu_set_mmio_spte_mask(mask); } +#ifdef CONFIG_X86_64 +static void pvclock_gtod_update_fn(struct work_struct *work) +{ + struct kvm *kvm; + + struct kvm_vcpu *vcpu; + int i; + + raw_spin_lock(&kvm_lock); + list_for_each_entry(kvm, &vm_list, vm_list) + kvm_for_each_vcpu(i, vcpu, kvm) + set_bit(KVM_REQ_MASTERCLOCK_UPDATE, &vcpu->requests); + atomic_set(&kvm_guest_has_master_clock, 0); + raw_spin_unlock(&kvm_lock); +} + +static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn); + +/* + * Notification about pvclock gtod data update. + */ +static int pvclock_gtod_notify(struct notifier_block *nb, unsigned long unused, + void *priv) +{ + struct pvclock_gtod_data *gtod = &pvclock_gtod_data; + struct timekeeper *tk = priv; + + update_pvclock_gtod(tk); + + /* disable master clock if host does not trust, or does not + * use, TSC clocksource + */ + if (gtod->clock.vclock_mode != VCLOCK_TSC && + atomic_read(&kvm_guest_has_master_clock) != 0) + queue_work(system_long_wq, &pvclock_gtod_work); + + return 0; +} + +static struct notifier_block pvclock_gtod_notifier = { + .notifier_call = pvclock_gtod_notify, +}; +#endif + int kvm_arch_init(void *opaque) { int r; @@ -4922,6 +5252,10 @@ int kvm_arch_init(void *opaque) host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); kvm_lapic_init(); +#ifdef CONFIG_X86_64 + pvclock_gtod_register_notifier(&pvclock_gtod_notifier); +#endif + return 0; out: @@ -4936,6 +5270,9 @@ void kvm_arch_exit(void) cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); unregister_hotcpu_notifier(&kvmclock_cpu_notifier_block); +#ifdef CONFIG_X86_64 + pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier); +#endif kvm_x86_ops = NULL; kvm_mmu_module_exit(); } @@ -5059,7 +5396,7 @@ out: } EXPORT_SYMBOL_GPL(kvm_emulate_hypercall); -int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) +static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); char instruction[3]; @@ -5235,6 +5572,29 @@ static void process_nmi(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); } +static void kvm_gen_update_masterclock(struct kvm *kvm) +{ +#ifdef CONFIG_X86_64 + int i; + struct kvm_vcpu *vcpu; + struct kvm_arch *ka = &kvm->arch; + + spin_lock(&ka->pvclock_gtod_sync_lock); + kvm_make_mclock_inprogress_request(kvm); + /* no guest entries from this point */ + pvclock_update_vm_gtod_copy(kvm); + + kvm_for_each_vcpu(i, vcpu, kvm) + set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests); + + /* guest entries allowed */ + kvm_for_each_vcpu(i, vcpu, kvm) + clear_bit(KVM_REQ_MCLOCK_INPROGRESS, &vcpu->requests); + + spin_unlock(&ka->pvclock_gtod_sync_lock); +#endif +} + static int vcpu_enter_guest(struct kvm_vcpu *vcpu) { int r; @@ -5247,6 +5607,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_mmu_unload(vcpu); if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu)) __kvm_migrate_timers(vcpu); + if (kvm_check_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu)) + kvm_gen_update_masterclock(vcpu->kvm); if (kvm_check_request(KVM_REQ_CLOCK_UPDATE, vcpu)) { r = kvm_guest_time_update(vcpu); if (unlikely(r)) @@ -5362,7 +5724,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (hw_breakpoint_active()) hw_breakpoint_restore(); - vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu); + vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, + native_read_tsc()); vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); @@ -5419,7 +5782,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) pr_debug("vcpu %d received sipi with vector # %x\n", vcpu->vcpu_id, vcpu->arch.sipi_vector); kvm_lapic_reset(vcpu); - r = kvm_arch_vcpu_reset(vcpu); + r = kvm_vcpu_reset(vcpu); if (r) return r; vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -6047,7 +6410,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) r = vcpu_load(vcpu); if (r) return r; - r = kvm_arch_vcpu_reset(vcpu); + r = kvm_vcpu_reset(vcpu); if (r == 0) r = kvm_mmu_setup(vcpu); vcpu_put(vcpu); @@ -6055,6 +6418,23 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) return r; } +int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) +{ + int r; + struct msr_data msr; + + r = vcpu_load(vcpu); + if (r) + return r; + msr.data = 0x0; + msr.index = MSR_IA32_TSC; + msr.host_initiated = true; + kvm_write_tsc(vcpu, &msr); + vcpu_put(vcpu); + + return r; +} + void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { int r; @@ -6069,7 +6449,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvm_x86_ops->vcpu_free(vcpu); } -int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) +static int kvm_vcpu_reset(struct kvm_vcpu *vcpu) { atomic_set(&vcpu->arch.nmi_queued, 0); vcpu->arch.nmi_pending = 0; @@ -6092,6 +6472,10 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) kvm_pmu_reset(vcpu); + memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs)); + vcpu->arch.regs_avail = ~0; + vcpu->arch.regs_dirty = ~0; + return kvm_x86_ops->vcpu_reset(vcpu); } @@ -6168,6 +6552,8 @@ int kvm_arch_hardware_enable(void *garbage) kvm_for_each_vcpu(i, vcpu, kvm) { vcpu->arch.tsc_offset_adjustment += delta_cyc; vcpu->arch.last_host_tsc = local_tsc; + set_bit(KVM_REQ_MASTERCLOCK_UPDATE, + &vcpu->requests); } /* @@ -6258,10 +6644,17 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, GFP_KERNEL)) goto fail_free_mce_banks; + r = fx_init(vcpu); + if (r) + goto fail_free_wbinvd_dirty_mask; + + vcpu->arch.ia32_tsc_adjust_msr = 0x0; kvm_async_pf_hash_reset(vcpu); kvm_pmu_init(vcpu); return 0; +fail_free_wbinvd_dirty_mask: + free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); fail_free_mce_banks: kfree(vcpu->arch.mce_banks); fail_free_lapic: @@ -6305,6 +6698,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) raw_spin_lock_init(&kvm->arch.tsc_write_lock); mutex_init(&kvm->arch.apic_map_lock); + spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock); + + pvclock_update_vm_gtod_copy(kvm); return 0; } diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 2b5219c12ac..e224f7a671b 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -112,7 +112,7 @@ void kvm_before_handle_nmi(struct kvm_vcpu *vcpu); void kvm_after_handle_nmi(struct kvm_vcpu *vcpu); int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip); -void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data); +void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr); int kvm_read_guest_virt(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 4df6c373421..205ad328aa5 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -22,6 +22,7 @@ #include <asm/hpet.h> #include <asm/unistd.h> #include <asm/io.h> +#include <asm/pvclock.h> #define gtod (&VVAR(vsyscall_gtod_data)) @@ -62,6 +63,76 @@ static notrace cycle_t vread_hpet(void) return readl((const void __iomem *)fix_to_virt(VSYSCALL_HPET) + 0xf0); } +#ifdef CONFIG_PARAVIRT_CLOCK + +static notrace const struct pvclock_vsyscall_time_info *get_pvti(int cpu) +{ + const struct pvclock_vsyscall_time_info *pvti_base; + int idx = cpu / (PAGE_SIZE/PVTI_SIZE); + int offset = cpu % (PAGE_SIZE/PVTI_SIZE); + + BUG_ON(PVCLOCK_FIXMAP_BEGIN + idx > PVCLOCK_FIXMAP_END); + + pvti_base = (struct pvclock_vsyscall_time_info *) + __fix_to_virt(PVCLOCK_FIXMAP_BEGIN+idx); + + return &pvti_base[offset]; +} + +static notrace cycle_t vread_pvclock(int *mode) +{ + const struct pvclock_vsyscall_time_info *pvti; + cycle_t ret; + u64 last; + u32 version; + u32 migrate_count; + u8 flags; + unsigned cpu, cpu1; + + + /* + * When looping to get a consistent (time-info, tsc) pair, we + * also need to deal with the possibility we can switch vcpus, + * so make sure we always re-fetch time-info for the current vcpu. + */ + do { + cpu = __getcpu() & VGETCPU_CPU_MASK; + /* TODO: We can put vcpu id into higher bits of pvti.version. + * This will save a couple of cycles by getting rid of + * __getcpu() calls (Gleb). + */ + + pvti = get_pvti(cpu); + + migrate_count = pvti->migrate_count; + + version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags); + + /* + * Test we're still on the cpu as well as the version. + * We could have been migrated just after the first + * vgetcpu but before fetching the version, so we + * wouldn't notice a version change. + */ + cpu1 = __getcpu() & VGETCPU_CPU_MASK; + } while (unlikely(cpu != cpu1 || + (pvti->pvti.version & 1) || + pvti->pvti.version != version || + pvti->migrate_count != migrate_count)); + + if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT))) + *mode = VCLOCK_NONE; + + /* refer to tsc.c read_tsc() comment for rationale */ + last = VVAR(vsyscall_gtod_data).clock.cycle_last; + + if (likely(ret >= last)) + return ret; + + return last; +} +#endif + notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { long ret; @@ -80,7 +151,7 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) } -notrace static inline u64 vgetsns(void) +notrace static inline u64 vgetsns(int *mode) { long v; cycles_t cycles; @@ -88,6 +159,10 @@ notrace static inline u64 vgetsns(void) cycles = vread_tsc(); else if (gtod->clock.vclock_mode == VCLOCK_HPET) cycles = vread_hpet(); +#ifdef CONFIG_PARAVIRT_CLOCK + else if (gtod->clock.vclock_mode == VCLOCK_PVCLOCK) + cycles = vread_pvclock(mode); +#endif else return 0; v = (cycles - gtod->clock.cycle_last) & gtod->clock.mask; @@ -107,7 +182,7 @@ notrace static int __always_inline do_realtime(struct timespec *ts) mode = gtod->clock.vclock_mode; ts->tv_sec = gtod->wall_time_sec; ns = gtod->wall_time_snsec; - ns += vgetsns(); + ns += vgetsns(&mode); ns >>= gtod->clock.shift; } while (unlikely(read_seqcount_retry(>od->seq, seq))); @@ -127,7 +202,7 @@ notrace static int do_monotonic(struct timespec *ts) mode = gtod->clock.vclock_mode; ts->tv_sec = gtod->monotonic_time_sec; ns = gtod->monotonic_time_snsec; - ns += vgetsns(); + ns += vgetsns(&mode); ns >>= gtod->clock.shift; } while (unlikely(read_seqcount_retry(>od->seq, seq))); timespec_add_ns(ts, ns); diff --git a/arch/x86/vdso/vgetcpu.c b/arch/x86/vdso/vgetcpu.c index 5463ad55857..2f94b039e55 100644 --- a/arch/x86/vdso/vgetcpu.c +++ b/arch/x86/vdso/vgetcpu.c @@ -17,15 +17,10 @@ __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused) { unsigned int p; - if (VVAR(vgetcpu_mode) == VGETCPU_RDTSCP) { - /* Load per CPU data from RDTSCP */ - native_read_tscp(&p); - } else { - /* Load per CPU data from GDT */ - asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG)); - } + p = __getcpu(); + if (cpu) - *cpu = p & 0xfff; + *cpu = p & VGETCPU_CPU_MASK; if (node) *node = p >> 12; return 0; |