From ff7bbb9c6ab6e6620429daeff39424bbde1a94b4 Mon Sep 17 00:00:00 2001 From: Luiz Capitulino Date: Thu, 23 Apr 2015 17:12:42 -0400 Subject: kvmclock: set scheduler clock stable If you try to enable NOHZ_FULL on a guest today, you'll get the following error when the guest tries to deactivate the scheduler tick: WARNING: CPU: 3 PID: 2182 at kernel/time/tick-sched.c:192 can_stop_full_tick+0xb9/0x290() NO_HZ FULL will not work with unstable sched clock CPU: 3 PID: 2182 Comm: kworker/3:1 Not tainted 4.0.0-10545-gb9bb6fb #204 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 Workqueue: events flush_to_ldisc ffffffff8162a0c7 ffff88011f583e88 ffffffff814e6ba0 0000000000000002 ffff88011f583ed8 ffff88011f583ec8 ffffffff8104d095 ffff88011f583eb8 0000000000000000 0000000000000003 0000000000000001 0000000000000001 Call Trace: [] dump_stack+0x4f/0x7b [] warn_slowpath_common+0x85/0xc0 [] warn_slowpath_fmt+0x46/0x50 [] can_stop_full_tick+0xb9/0x290 [] tick_nohz_irq_exit+0x8d/0xb0 [] irq_exit+0xc5/0x130 [] smp_apic_timer_interrupt+0x4a/0x60 [] apic_timer_interrupt+0x6e/0x80 [] ? _raw_spin_unlock_irqrestore+0x31/0x60 [] __wake_up+0x48/0x60 [] n_tty_receive_buf_common+0x49c/0xba0 [] ? tty_ldisc_ref+0x1f/0x70 [] n_tty_receive_buf2+0x14/0x20 [] flush_to_ldisc+0xe0/0x120 [] process_one_work+0x1d5/0x540 [] ? process_one_work+0x151/0x540 [] worker_thread+0x121/0x470 [] ? process_one_work+0x540/0x540 [] kthread+0xef/0x110 [] ? __kthread_parkme+0xa0/0xa0 [] ret_from_fork+0x42/0x70 [] ? __kthread_parkme+0xa0/0xa0 ---[ end trace 06e3507544a38866 ]--- However, it turns out that kvmclock does provide a stable sched_clock callback. So, let the scheduler know this which in turn makes NOHZ_FULL work in the guest. Signed-off-by: Marcelo Tosatti Signed-off-by: Luiz Capitulino Signed-off-by: Paolo Bonzini --- arch/x86/kernel/kvmclock.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 42caaef897c8..4e03921761c4 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -265,6 +266,8 @@ void __init kvmclock_init(void) if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT); + + set_sched_clock_stable(); } int __init kvm_setup_vsyscall_timeinfo(void) -- cgit v1.2.3 From 0097d12e504b3ce57b68810737ad6a5a64a98c68 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Thu, 30 Apr 2015 13:43:30 +0200 Subject: KVM: provide irq_unsafe kvm_guest_{enter|exit} Several kvm architectures disable interrupts before kvm_guest_enter. kvm_guest_enter then uses local_irq_save/restore to disable interrupts again or for the first time. Lets provide underscore versions of kvm_guest_{enter|exit} that assume being called locked. kvm_guest_enter now disables interrupts for the full function and thus we can remove the check for preemptible. This patch then adopts s390/kvm to use local_irq_disable/enable calls which are slighty cheaper that local_irq_save/restore and call these new functions. Signed-off-by: Christian Borntraeger Signed-off-by: Paolo Bonzini --- arch/s390/kvm/kvm-s390.c | 10 ++++++---- include/linux/kvm_host.h | 27 ++++++++++++++++++--------- 2 files changed, 24 insertions(+), 13 deletions(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 8cd8e7b288c5..2be391bb8557 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1993,12 +1993,14 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) * As PF_VCPU will be used in fault handler, between * guest_enter and guest_exit should be no uaccess. */ - preempt_disable(); - kvm_guest_enter(); - preempt_enable(); + local_irq_disable(); + __kvm_guest_enter(); + local_irq_enable(); exit_reason = sie64a(vcpu->arch.sie_block, vcpu->run->s.regs.gprs); - kvm_guest_exit(); + local_irq_disable(); + __kvm_guest_exit(); + local_irq_enable(); vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); rc = vcpu_post_run(vcpu, exit_reason); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ad45054309a0..efc16df1fc5d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -762,16 +762,10 @@ static inline void kvm_iommu_unmap_pages(struct kvm *kvm, } #endif -static inline void kvm_guest_enter(void) +/* must be called with irqs disabled */ +static inline void __kvm_guest_enter(void) { - unsigned long flags; - - BUG_ON(preemptible()); - - local_irq_save(flags); guest_enter(); - local_irq_restore(flags); - /* KVM does not hold any references to rcu protected data when it * switches CPU into a guest mode. In fact switching to a guest mode * is very similar to exiting to userspace from rcu point of view. In @@ -783,12 +777,27 @@ static inline void kvm_guest_enter(void) rcu_virt_note_context_switch(smp_processor_id()); } +/* must be called with irqs disabled */ +static inline void __kvm_guest_exit(void) +{ + guest_exit(); +} + +static inline void kvm_guest_enter(void) +{ + unsigned long flags; + + local_irq_save(flags); + __kvm_guest_enter(); + local_irq_restore(flags); +} + static inline void kvm_guest_exit(void) { unsigned long flags; local_irq_save(flags); - guest_exit(); + __kvm_guest_exit(); local_irq_restore(flags); } -- cgit v1.2.3 From ccf73aaf5adfa37f45be12459c17f534e8f2c2c5 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Thu, 30 Apr 2015 13:43:31 +0200 Subject: KVM: arm/mips/x86/power use __kvm_guest_{enter|exit} Use __kvm_guest_{enter|exit} instead of kvm_guest_{enter|exit} where interrupts are disabled. Signed-off-by: Christian Borntraeger Signed-off-by: Paolo Bonzini --- arch/arm/kvm/arm.c | 4 ++-- arch/mips/kvm/mips.c | 4 ++-- arch/powerpc/kvm/powerpc.c | 2 +- arch/x86/kvm/x86.c | 2 +- 4 files changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index d9631ecddd56..e41cb11f71b2 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -553,13 +553,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) * Enter the guest */ trace_kvm_entry(*vcpu_pc(vcpu)); - kvm_guest_enter(); + __kvm_guest_enter(); vcpu->mode = IN_GUEST_MODE; ret = kvm_call_hyp(__kvm_vcpu_run, vcpu); vcpu->mode = OUTSIDE_GUEST_MODE; - kvm_guest_exit(); + __kvm_guest_exit(); trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu)); /* * We may have taken a host interrupt in HYP mode (ie diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index bb68e8d520e8..71f345b499c8 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -393,7 +393,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) kvm_mips_deliver_interrupts(vcpu, kvm_read_c0_guest_cause(vcpu->arch.cop0)); - kvm_guest_enter(); + __kvm_guest_enter(); /* Disable hardware page table walking while in guest */ htw_stop(); @@ -403,7 +403,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) /* Re-enable HTW before enabling interrupts */ htw_start(); - kvm_guest_exit(); + __kvm_guest_exit(); local_irq_enable(); if (vcpu->sigset_active) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index ac3ddf115f3d..8cd1f80fdc70 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -115,7 +115,7 @@ int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu) continue; } - kvm_guest_enter(); + __kvm_guest_enter(); return 1; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c73efcd03e29..7a959be0aebc 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6347,7 +6347,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (req_immediate_exit) smp_send_reschedule(vcpu->cpu); - kvm_guest_enter(); + __kvm_guest_enter(); if (unlikely(vcpu->arch.switch_db_regs)) { set_debugreg(0, 7); -- cgit v1.2.3 From e233d54d4d975760073700b15de975ef702e8194 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 30 Apr 2015 14:39:40 +0200 Subject: KVM: booke: use __kvm_guest_exit Signed-off-by: Paolo Bonzini --- arch/powerpc/kvm/booke.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 6c1316a15a27..3872ab31c80a 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -1004,10 +1004,10 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, break; } - local_irq_enable(); - trace_kvm_exit(exit_nr, vcpu); - kvm_guest_exit(); + __kvm_guest_exit(); + + local_irq_enable(); run->exit_reason = KVM_EXIT_UNKNOWN; run->ready_for_interrupt_injection = 1; -- cgit v1.2.3 From 90de4a1875180f8347c075319af2cce586c96ab6 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Mon, 13 Apr 2015 01:53:41 +0300 Subject: KVM: x86: Support for disabling quirks Introducing KVM_CAP_DISABLE_QUIRKS for disabling x86 quirks that were previous created in order to overcome QEMU issues. Those issue were mostly result of invalid VM BIOS. Currently there are two quirks that can be disabled: 1. KVM_QUIRK_LINT0_REENABLED - LINT0 was enabled after boot 2. KVM_QUIRK_CD_NW_CLEARED - CD and NW are cleared after boot These two issues are already resolved in recent releases of QEMU, and would therefore be disabled by QEMU. Signed-off-by: Nadav Amit Message-Id: <1428879221-29996-1-git-send-email-namit@cs.technion.ac.il> [Report capability from KVM_CHECK_EXTENSION too. - Paolo] Signed-off-by: Paolo Bonzini --- Documentation/virtual/kvm/api.txt | 3 ++- arch/x86/include/asm/kvm_host.h | 2 ++ arch/x86/include/uapi/asm/kvm.h | 3 +++ arch/x86/kvm/lapic.c | 5 +++-- arch/x86/kvm/svm.c | 3 ++- arch/x86/kvm/x86.c | 30 ++++++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 1 + 7 files changed, 43 insertions(+), 4 deletions(-) diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 9fa2bf8c3f6f..695544420ff2 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -959,7 +959,8 @@ documentation when it pops into existence). 4.37 KVM_ENABLE_CAP Capability: KVM_CAP_ENABLE_CAP, KVM_CAP_ENABLE_CAP_VM -Architectures: ppc, s390 +Architectures: x86 (only KVM_CAP_ENABLE_CAP_VM), + mips (only KVM_CAP_ENABLE_CAP), ppc, s390 Type: vcpu ioctl, vm ioctl (with KVM_CAP_ENABLE_CAP_VM) Parameters: struct kvm_enable_cap (in) Returns: 0 on success; -1 on error diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index dea2e7e962e3..f80ad591aa61 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -635,6 +635,8 @@ struct kvm_arch { #endif bool boot_vcpu_runs_old_kvmclock; + + u64 disabled_quirks; }; struct kvm_vm_stat { diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index d7dcef58aefa..2fec75e4b1e1 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -345,4 +345,7 @@ struct kvm_xcrs { struct kvm_sync_regs { }; +#define KVM_QUIRK_LINT0_REENABLED (1 << 0) +#define KVM_QUIRK_CD_NW_CLEARED (1 << 1) + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 629af0f1c5c4..4071eb161c8f 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1577,8 +1577,9 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu) for (i = 0; i < APIC_LVT_NUM; i++) apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED); apic->lapic_timer.timer_mode = 0; - apic_set_reg(apic, APIC_LVT0, - SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT)); + if (!(vcpu->kvm->arch.disabled_quirks & KVM_QUIRK_LINT0_REENABLED)) + apic_set_reg(apic, APIC_LVT0, + SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT)); apic_set_reg(apic, APIC_DFR, 0xffffffffU); apic_set_spiv(apic, 0xff); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index ce741b8650f6..46299dac7c6d 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1575,7 +1575,8 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) * does not do it - this results in some delay at * reboot */ - cr0 &= ~(X86_CR0_CD | X86_CR0_NW); + if (!(vcpu->kvm->arch.disabled_quirks & KVM_QUIRK_CD_NW_CLEARED)) + cr0 &= ~(X86_CR0_CD | X86_CR0_NW); svm->vmcb->save.cr0 = cr0; mark_dirty(svm->vmcb, VMCB_CR); update_cr0_intercept(svm); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7a959be0aebc..0435b653f583 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2800,6 +2800,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV_TIME: case KVM_CAP_IOAPIC_POLARITY_IGNORED: case KVM_CAP_TSC_DEADLINE_TIMER: + case KVM_CAP_ENABLE_CAP_VM: + case KVM_CAP_DISABLE_QUIRKS: #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT case KVM_CAP_ASSIGN_DEV_IRQ: case KVM_CAP_PCI_2_3: @@ -3847,6 +3849,26 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event, return 0; } +static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, + struct kvm_enable_cap *cap) +{ + int r; + + if (cap->flags) + return -EINVAL; + + switch (cap->cap) { + case KVM_CAP_DISABLE_QUIRKS: + kvm->arch.disabled_quirks = cap->args[0]; + r = 0; + break; + default: + r = -EINVAL; + break; + } + return r; +} + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -4099,7 +4121,15 @@ long kvm_arch_vm_ioctl(struct file *filp, r = 0; break; } + case KVM_ENABLE_CAP: { + struct kvm_enable_cap cap; + r = -EFAULT; + if (copy_from_user(&cap, argp, sizeof(cap))) + goto out; + r = kvm_vm_ioctl_enable_cap(kvm, &cap); + break; + } default: r = kvm_vm_ioctl_assigned_device(kvm, ioctl, arg); } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 4b60056776d1..75bd9f7fd846 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -814,6 +814,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_S390_INJECT_IRQ 113 #define KVM_CAP_S390_IRQ_STATE 114 #define KVM_CAP_PPC_HWRNG 115 +#define KVM_CAP_DISABLE_QUIRKS 116 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From d28bc9dd25ce023270d2e039e7c98d38ecbf7758 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Mon, 13 Apr 2015 14:34:08 +0300 Subject: KVM: x86: INIT and reset sequences are different x86 architecture defines differences between the reset and INIT sequences. INIT does not initialize the FPU (including MMX, XMM, YMM, etc.), TSC, PMU, MSRs (in general), MTRRs machine-check, APIC ID, APIC arbitration ID and BSP. References (from Intel SDM): "If the MP protocol has completed and a BSP is chosen, subsequent INITs (either to a specific processor or system wide) do not cause the MP protocol to be repeated." [8.4.2: MP Initialization Protocol Requirements and Restrictions] [Table 9-1. IA-32 Processor States Following Power-up, Reset, or INIT] "If the processor is reset by asserting the INIT# pin, the x87 FPU state is not changed." [9.2: X87 FPU INITIALIZATION] "The state of the local APIC following an INIT reset is the same as it is after a power-up or hardware reset, except that the APIC ID and arbitration ID registers are not affected." [10.4.7.3: Local APIC State After an INIT Reset ("Wait-for-SIPI" State)] Signed-off-by: Nadav Amit Message-Id: <1428924848-28212-1-git-send-email-namit@cs.technion.ac.il> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 6 ++--- arch/x86/kvm/lapic.c | 11 +++++---- arch/x86/kvm/lapic.h | 2 +- arch/x86/kvm/svm.c | 27 +++++++++++----------- arch/x86/kvm/vmx.c | 51 +++++++++++++++++++++++------------------ arch/x86/kvm/x86.c | 17 ++++++++------ 6 files changed, 63 insertions(+), 51 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f80ad591aa61..3a19e30f0be0 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -711,7 +711,7 @@ struct kvm_x86_ops { /* Create, but do not attach this VCPU */ struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id); void (*vcpu_free)(struct kvm_vcpu *vcpu); - void (*vcpu_reset)(struct kvm_vcpu *vcpu); + void (*vcpu_reset)(struct kvm_vcpu *vcpu, bool init_event); void (*prepare_guest_switch)(struct kvm_vcpu *vcpu); void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu); @@ -1001,7 +1001,7 @@ void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id); void kvm_inject_nmi(struct kvm_vcpu *vcpu); -int fx_init(struct kvm_vcpu *vcpu); +int fx_init(struct kvm_vcpu *vcpu, bool init_event); void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, int bytes); @@ -1145,7 +1145,7 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); -void kvm_vcpu_reset(struct kvm_vcpu *vcpu); +void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu); void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, unsigned long address); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 4071eb161c8f..abf165330881 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1557,7 +1557,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) } -void kvm_lapic_reset(struct kvm_vcpu *vcpu) +void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) { struct kvm_lapic *apic; int i; @@ -1571,7 +1571,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu) /* Stop the timer in case it's a reset to an active apic */ hrtimer_cancel(&apic->lapic_timer.timer); - kvm_apic_set_id(apic, vcpu->vcpu_id); + if (!init_event) + kvm_apic_set_id(apic, vcpu->vcpu_id); kvm_apic_set_version(apic->vcpu); for (i = 0; i < APIC_LVT_NUM; i++) @@ -1713,7 +1714,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE); static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */ - kvm_lapic_reset(vcpu); + kvm_lapic_reset(vcpu, false); kvm_iodevice_init(&apic->dev, &apic_mmio_ops); return 0; @@ -2047,8 +2048,8 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) pe = xchg(&apic->pending_events, 0); if (test_bit(KVM_APIC_INIT, &pe)) { - kvm_lapic_reset(vcpu); - kvm_vcpu_reset(vcpu); + kvm_lapic_reset(vcpu, true); + kvm_vcpu_reset(vcpu, true); if (kvm_vcpu_is_bsp(apic->vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 9d28383fc1e7..793f76183e8b 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -48,7 +48,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu); int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu); int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu); void kvm_apic_accept_events(struct kvm_vcpu *vcpu); -void kvm_lapic_reset(struct kvm_vcpu *vcpu); +void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event); u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu); void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8); void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 46299dac7c6d..b6ad0f9de80a 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1082,7 +1082,7 @@ static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) return target_tsc - tsc; } -static void init_vmcb(struct vcpu_svm *svm) +static void init_vmcb(struct vcpu_svm *svm, bool init_event) { struct vmcb_control_area *control = &svm->vmcb->control; struct vmcb_save_area *save = &svm->vmcb->save; @@ -1153,17 +1153,17 @@ static void init_vmcb(struct vcpu_svm *svm) init_sys_seg(&save->ldtr, SEG_TYPE_LDT); init_sys_seg(&save->tr, SEG_TYPE_BUSY_TSS16); - svm_set_efer(&svm->vcpu, 0); + if (!init_event) + svm_set_efer(&svm->vcpu, 0); save->dr6 = 0xffff0ff0; kvm_set_rflags(&svm->vcpu, 2); save->rip = 0x0000fff0; svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip; /* - * This is the guest-visible cr0 value. * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0. + * It also updates the guest-visible cr0 value. */ - svm->vcpu.arch.cr0 = 0; (void)kvm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET); save->cr4 = X86_CR4_PAE; @@ -1195,13 +1195,19 @@ static void init_vmcb(struct vcpu_svm *svm) enable_gif(svm); } -static void svm_vcpu_reset(struct kvm_vcpu *vcpu) +static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { struct vcpu_svm *svm = to_svm(vcpu); u32 dummy; u32 eax = 1; - init_vmcb(svm); + if (!init_event) { + svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE | + MSR_IA32_APICBASE_ENABLE; + if (kvm_vcpu_is_reset_bsp(&svm->vcpu)) + svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP; + } + init_vmcb(svm, init_event); kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy); kvm_register_write(vcpu, VCPU_REGS_RDX, eax); @@ -1257,12 +1263,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) clear_page(svm->vmcb); svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT; svm->asid_generation = 0; - init_vmcb(svm); - - svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE | - MSR_IA32_APICBASE_ENABLE; - if (kvm_vcpu_is_reset_bsp(&svm->vcpu)) - svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP; + init_vmcb(svm, false); svm_init_osvw(&svm->vcpu); @@ -1884,7 +1885,7 @@ static int shutdown_interception(struct vcpu_svm *svm) * so reinitialize it. */ clear_page(svm->vmcb); - init_vmcb(svm); + init_vmcb(svm, false); kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; return 0; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index f7b61687bd79..a694ff6bce80 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -4708,22 +4708,27 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) return 0; } -static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) +static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct msr_data apic_base_msr; + u64 cr0; vmx->rmode.vm86_active = 0; vmx->soft_vnmi_blocked = 0; vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); - kvm_set_cr8(&vmx->vcpu, 0); - apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; - if (kvm_vcpu_is_reset_bsp(&vmx->vcpu)) - apic_base_msr.data |= MSR_IA32_APICBASE_BSP; - apic_base_msr.host_initiated = true; - kvm_set_apic_base(&vmx->vcpu, &apic_base_msr); + kvm_set_cr8(vcpu, 0); + + if (!init_event) { + apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | + MSR_IA32_APICBASE_ENABLE; + if (kvm_vcpu_is_reset_bsp(vcpu)) + apic_base_msr.data |= MSR_IA32_APICBASE_BSP; + apic_base_msr.host_initiated = true; + kvm_set_apic_base(vcpu, &apic_base_msr); + } vmx_segment_cache_clear(vmx); @@ -4747,9 +4752,12 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_LDTR_LIMIT, 0xffff); vmcs_write32(GUEST_LDTR_AR_BYTES, 0x00082); - vmcs_write32(GUEST_SYSENTER_CS, 0); - vmcs_writel(GUEST_SYSENTER_ESP, 0); - vmcs_writel(GUEST_SYSENTER_EIP, 0); + if (!init_event) { + vmcs_write32(GUEST_SYSENTER_CS, 0); + vmcs_writel(GUEST_SYSENTER_ESP, 0); + vmcs_writel(GUEST_SYSENTER_EIP, 0); + vmcs_write64(GUEST_IA32_DEBUGCTL, 0); + } vmcs_writel(GUEST_RFLAGS, 0x02); kvm_rip_write(vcpu, 0xfff0); @@ -4764,18 +4772,15 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0); - /* Special registers */ - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); - setup_msrs(vmx); vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); /* 22.2.1 */ - if (cpu_has_vmx_tpr_shadow()) { + if (cpu_has_vmx_tpr_shadow() && !init_event) { vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); - if (vm_need_tpr_shadow(vmx->vcpu.kvm)) + if (vm_need_tpr_shadow(vcpu->kvm)) vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, - __pa(vmx->vcpu.arch.apic->regs)); + __pa(vcpu->arch.apic->regs)); vmcs_write32(TPR_THRESHOLD, 0); } @@ -4787,12 +4792,14 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) if (vmx->vpid != 0) vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); - vmx->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; - vmx_set_cr0(&vmx->vcpu, kvm_read_cr0(vcpu)); /* enter rmode */ - vmx_set_cr4(&vmx->vcpu, 0); - vmx_set_efer(&vmx->vcpu, 0); - vmx_fpu_activate(&vmx->vcpu); - update_exception_bitmap(&vmx->vcpu); + cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; + vmx_set_cr0(vcpu, cr0); /* enter rmode */ + vmx->vcpu.arch.cr0 = cr0; + vmx_set_cr4(vcpu, 0); + if (!init_event) + vmx_set_efer(vcpu, 0); + vmx_fpu_activate(vcpu); + update_exception_bitmap(vcpu); vpid_sync_context(vmx); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0435b653f583..755a79fabfc1 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7033,7 +7033,7 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) return 0; } -int fx_init(struct kvm_vcpu *vcpu) +int fx_init(struct kvm_vcpu *vcpu, bool init_event) { int err; @@ -7041,7 +7041,9 @@ int fx_init(struct kvm_vcpu *vcpu) if (err) return err; - fpu_finit(&vcpu->arch.guest_fpu); + if (!init_event) + fpu_finit(&vcpu->arch.guest_fpu); + if (cpu_has_xsaves) vcpu->arch.guest_fpu.state->xsave.xsave_hdr.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED; @@ -7121,7 +7123,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) r = vcpu_load(vcpu); if (r) return r; - kvm_vcpu_reset(vcpu); + kvm_vcpu_reset(vcpu, false); kvm_mmu_setup(vcpu); vcpu_put(vcpu); @@ -7159,7 +7161,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvm_x86_ops->vcpu_free(vcpu); } -void kvm_vcpu_reset(struct kvm_vcpu *vcpu) +void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { atomic_set(&vcpu->arch.nmi_queued, 0); vcpu->arch.nmi_pending = 0; @@ -7186,13 +7188,14 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu) kvm_async_pf_hash_reset(vcpu); vcpu->arch.apf.halted = false; - kvm_pmu_reset(vcpu); + if (!init_event) + kvm_pmu_reset(vcpu); memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs)); vcpu->arch.regs_avail = ~0; vcpu->arch.regs_dirty = ~0; - kvm_x86_ops->vcpu_reset(vcpu); + kvm_x86_ops->vcpu_reset(vcpu, init_event); } void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) @@ -7381,7 +7384,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) goto fail_free_mce_banks; } - r = fx_init(vcpu); + r = fx_init(vcpu, false); if (r) goto fail_free_wbinvd_dirty_mask; -- cgit v1.2.3 From b7cb22317305883d50f930cd6bf2fdb37df930c1 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 21 Apr 2015 14:57:05 +0200 Subject: KVM: x86: tweak types of fields in kvm_lapic_irq Change to u16 if they only contain data in the low 16 bits. Change the level field to bool, since we assign 1 sometimes, but just mask icr_low with APIC_INT_ASSERT in apic_send_ipi. Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 8 ++++---- arch/x86/kvm/lapic.c | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 3a19e30f0be0..dc83b43d0850 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -689,10 +689,10 @@ struct msr_data { struct kvm_lapic_irq { u32 vector; - u32 delivery_mode; - u32 dest_mode; - u32 level; - u32 trig_mode; + u16 delivery_mode; + u16 dest_mode; + bool level; + u16 trig_mode; u32 shorthand; u32 dest_id; }; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index abf165330881..ba585d0c42c5 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -914,7 +914,7 @@ static void apic_send_ipi(struct kvm_lapic *apic) irq.vector = icr_low & APIC_VECTOR_MASK; irq.delivery_mode = icr_low & APIC_MODE_MASK; irq.dest_mode = icr_low & APIC_DEST_MASK; - irq.level = icr_low & APIC_INT_ASSERT; + irq.level = (icr_low & APIC_INT_ASSERT) != 0; irq.trig_mode = icr_low & APIC_INT_LEVELTRIG; irq.shorthand = icr_low & APIC_SHORT_MASK; if (apic_x2apic_mode(apic)) -- cgit v1.2.3 From 93bbf0b8bc80f0ee3c629542a4dea14a3537760b Mon Sep 17 00:00:00 2001 From: James Sullivan Date: Wed, 18 Mar 2015 19:26:03 -0600 Subject: kvm: x86: Extended struct kvm_lapic_irq with msi_redir_hint for MSI delivery MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Extended struct kvm_lapic_irq with bool msi_redir_hint, which will be used to determine if the delivery of the MSI should target only the lowest priority CPU in the logical group specified for delivery. (In physical dest mode, the RH bit is not relevant). Initialized the value of msi_redir_hint to true when RH=1 in kvm_set_msi_irq(), and initialized to false in all other cases. Added value of msi_redir_hint to a debug message dump of an IRQ in apic_send_ipi(). Signed-off-by: James Sullivan Reviewed-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/ioapic.c | 1 + arch/x86/kvm/irq_comm.c | 3 ++- arch/x86/kvm/lapic.c | 6 ++++-- arch/x86/kvm/x86.c | 1 + 5 files changed, 9 insertions(+), 3 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index dc83b43d0850..8b661d1946b5 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -695,6 +695,7 @@ struct kvm_lapic_irq { u16 trig_mode; u32 shorthand; u32 dest_id; + bool msi_redir_hint; }; struct kvm_x86_ops { diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 28146f03c514..274663496f7a 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -349,6 +349,7 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status) irqe.delivery_mode = entry->fields.delivery_mode << 8; irqe.level = 1; irqe.shorthand = 0; + irqe.msi_redir_hint = false; if (irqe.trig_mode == IOAPIC_EDGE_TRIG) ioapic->irr_delivered |= 1 << irq; diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 72298b3ac025..80c10af2bf46 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -106,9 +106,10 @@ static inline void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e, irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo; irq->trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data; irq->delivery_mode = e->msi.data & 0x700; + irq->msi_redir_hint = ((e->msi.address_lo + & MSI_ADDR_REDIRECTION_LOWPRI) > 0); irq->level = 1; irq->shorthand = 0; - /* TODO Deal with RH bit of MSI message address */ } int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index ba585d0c42c5..2573b29bbbb3 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -917,6 +917,7 @@ static void apic_send_ipi(struct kvm_lapic *apic) irq.level = (icr_low & APIC_INT_ASSERT) != 0; irq.trig_mode = icr_low & APIC_INT_LEVELTRIG; irq.shorthand = icr_low & APIC_SHORT_MASK; + irq.msi_redir_hint = false; if (apic_x2apic_mode(apic)) irq.dest_id = icr_high; else @@ -926,10 +927,11 @@ static void apic_send_ipi(struct kvm_lapic *apic) apic_debug("icr_high 0x%x, icr_low 0x%x, " "short_hand 0x%x, dest 0x%x, trig_mode 0x%x, level 0x%x, " - "dest_mode 0x%x, delivery_mode 0x%x, vector 0x%x\n", + "dest_mode 0x%x, delivery_mode 0x%x, vector 0x%x, " + "msi_redir_hint 0x%x\n", icr_high, icr_low, irq.shorthand, irq.dest_id, irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode, - irq.vector); + irq.vector, irq.msi_redir_hint); kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq, NULL); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 755a79fabfc1..bf80ce7656b7 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5984,6 +5984,7 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) lapic_irq.shorthand = 0; lapic_irq.dest_mode = 0; lapic_irq.dest_id = apicid; + lapic_irq.msi_redir_hint = false; lapic_irq.delivery_mode = APIC_DM_REMRD; kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL); -- cgit v1.2.3 From d1ebdbf99a3ce90f3b886c2cf0dfd7da17703d2a Mon Sep 17 00:00:00 2001 From: James Sullivan Date: Wed, 18 Mar 2015 19:26:04 -0600 Subject: kvm: x86: Deliver MSI IRQ to only lowest prio cpu if msi_redir_hint is true MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit An MSI interrupt should only be delivered to the lowest priority CPU when it has RH=1, regardless of the delivery mode. Modified kvm_is_dm_lowest_prio() to check for either irq->delivery_mode == APIC_DM_LOWPRI or irq->msi_redir_hint. Moved kvm_is_dm_lowest_prio() into lapic.h and renamed to kvm_lowest_prio_delivery(). Changed a check in kvm_irq_delivery_to_apic_fast() from irq->delivery_mode == APIC_DM_LOWPRI to kvm_is_dm_lowest_prio(). Signed-off-by: James Sullivan Reviewed-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- arch/x86/kvm/irq_comm.c | 11 ++++------- arch/x86/kvm/lapic.c | 2 +- arch/x86/kvm/lapic.h | 6 ++++++ 3 files changed, 11 insertions(+), 8 deletions(-) diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 80c10af2bf46..9efff9e5b58c 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -31,6 +31,8 @@ #include "ioapic.h" +#include "lapic.h" + static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) @@ -48,11 +50,6 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, line_status); } -inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq) -{ - return irq->delivery_mode == APIC_DM_LOWEST; -} - int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, unsigned long *dest_map) { @@ -60,7 +57,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_vcpu *vcpu, *lowest = NULL; if (irq->dest_mode == 0 && irq->dest_id == 0xff && - kvm_is_dm_lowest_prio(irq)) { + kvm_lowest_prio_delivery(irq)) { printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n"); irq->delivery_mode = APIC_DM_FIXED; } @@ -76,7 +73,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, irq->dest_id, irq->dest_mode)) continue; - if (!kvm_is_dm_lowest_prio(irq)) { + if (!kvm_lowest_prio_delivery(irq)) { if (r < 0) r = 0; r += kvm_apic_set_irq(vcpu, irq, dest_map); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 2573b29bbbb3..dc5b57bb1f76 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -728,7 +728,7 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, dst = map->logical_map[cid]; - if (irq->delivery_mode == APIC_DM_LOWEST) { + if (kvm_lowest_prio_delivery(irq)) { int l = -1; for_each_set_bit(i, &bitmap, 16) { if (!dst[i]) diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 793f76183e8b..71b150cae5f9 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -153,6 +153,12 @@ static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu) return vcpu->arch.apic->pending_events; } +static inline bool kvm_lowest_prio_delivery(struct kvm_lapic_irq *irq) +{ + return (irq->delivery_mode == APIC_DM_LOWEST || + irq->msi_redir_hint); +} + bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector); void wait_lapic_expire(struct kvm_vcpu *vcpu); -- cgit v1.2.3 From 653f52c316a49c5ee2701bc13b15879f20790662 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Thu, 23 Apr 2015 11:52:37 -0400 Subject: kvm,x86: load guest FPU context more eagerly Currently KVM will clear the FPU bits in CR0.TS in the VMCS, and trap to re-load them every time the guest accesses the FPU after a switch back into the guest from the host. This patch copies the x86 task switch semantics for FPU loading, with the FPU loaded eagerly after first use if the system uses eager fpu mode, or if the guest uses the FPU frequently. In the latter case, after loading the FPU for 255 times, the fpu_counter will roll over, and we will revert to loading the FPU on demand, until it has been established that the guest is still actively using the FPU. This mirrors the x86 task switch policy, which seems to work. Signed-off-by: Rik van Riel Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 15 +++++++++++++-- include/linux/kvm_host.h | 1 + 2 files changed, 14 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index bf80ce7656b7..c42134e98e31 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7086,14 +7086,25 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { kvm_put_guest_xcr0(vcpu); - if (!vcpu->guest_fpu_loaded) + if (!vcpu->guest_fpu_loaded) { + vcpu->fpu_counter = 0; return; + } vcpu->guest_fpu_loaded = 0; fpu_save_init(&vcpu->arch.guest_fpu); __kernel_fpu_end(); ++vcpu->stat.fpu_reload; - kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); + /* + * If using eager FPU mode, or if the guest is a frequent user + * of the FPU, just leave the FPU active for next time. + * Every 255 times fpu_counter rolls over to 0; a guest that uses + * the FPU in bursts will revert to loading it on demand. + */ + if (!use_eager_fpu()) { + if (++vcpu->fpu_counter < 5) + kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); + } trace_kvm_fpu(0); } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index efc16df1fc5d..b7a08cd6f4a8 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -230,6 +230,7 @@ struct kvm_vcpu { int fpu_active; int guest_fpu_loaded, guest_xcr0_loaded; + unsigned char fpu_counter; wait_queue_head_t wq; struct pid *pid; int sigset_active; -- cgit v1.2.3 From 74545705cb2e398efc3cd751628c58f021323434 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= Date: Mon, 27 Apr 2015 15:11:25 +0200 Subject: KVM: x86: fix initial PAT value MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit PAT should be 0007_0406_0007_0406h on RESET and not modified on INIT. VMX used a wrong value (host's PAT) and while SVM used the right one, it never got to arch.pat. This is not an issue with QEMU as it will force the correct value. Signed-off-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm.c | 2 +- arch/x86/kvm/vmx.c | 12 ++---------- arch/x86/kvm/x86.c | 2 ++ arch/x86/kvm/x86.h | 2 ++ 4 files changed, 7 insertions(+), 11 deletions(-) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index b6ad0f9de80a..8954d7a07703 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1176,7 +1176,7 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event) clr_exception_intercept(svm, PF_VECTOR); clr_cr_intercept(svm, INTERCEPT_CR3_READ); clr_cr_intercept(svm, INTERCEPT_CR3_WRITE); - save->g_pat = 0x0007040600070406ULL; + save->g_pat = svm->vcpu.arch.pat; save->cr3 = 0; save->cr4 = 0; } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a694ff6bce80..3c218fd59f8c 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -4667,16 +4667,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0); vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest)); - if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { - u32 msr_low, msr_high; - u64 host_pat; - rdmsr(MSR_IA32_CR_PAT, msr_low, msr_high); - host_pat = msr_low | ((u64) msr_high << 32); - /* Write the default value follow host pat */ - vmcs_write64(GUEST_IA32_PAT, host_pat); - /* Keep arch.pat sync with GUEST_IA32_PAT */ - vmx->vcpu.arch.pat = host_pat; - } + if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) + vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) { u32 index = vmx_msr_index[i]; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c42134e98e31..cdccbe1749a5 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7408,6 +7408,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); + vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; + kvm_async_pf_hash_reset(vcpu); kvm_pmu_init(vcpu); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index f5fef1868096..01a1d011e073 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -4,6 +4,8 @@ #include #include "kvm_cache_regs.h" +#define MSR_IA32_CR_PAT_DEFAULT 0x0007040600070406ULL + static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu) { vcpu->arch.exception.pending = false; -- cgit v1.2.3 From d90e3a35e90af7f8beceebefc90e62eae237c5ed Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Mon, 27 Apr 2015 22:35:34 +0200 Subject: KVM: x86: drop unneeded null test If the null test is needed, the call to cancel_delayed_work_sync would have already crashed. Normally, the destroy function should only be called if the init function has succeeded, in which case ioapic is not null. Problem found using Coccinelle. Suggested-by: Michael S. Tsirkin Signed-off-by: Julia Lawall Signed-off-by: Paolo Bonzini --- arch/x86/kvm/ioapic.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 274663496f7a..856f79105bb5 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -638,11 +638,9 @@ void kvm_ioapic_destroy(struct kvm *kvm) struct kvm_ioapic *ioapic = kvm->arch.vioapic; cancel_delayed_work_sync(&ioapic->eoi_inject); - if (ioapic) { - kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev); - kvm->arch.vioapic = NULL; - kfree(ioapic); - } + kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev); + kvm->arch.vioapic = NULL; + kfree(ioapic); } int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) -- cgit v1.2.3 From a3eb97bd80134ba07864ca00747466c02118aca1 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Fri, 24 Apr 2015 22:36:14 -0300 Subject: x86: kvmclock: drop rdtsc_barrier() Drop unnecessary rdtsc_barrier(), as has been determined empirically, see 057e6a8c660e95c3f4e7162e00e2fee1fc90c50d for details. Noticed by Andy Lutomirski. Improves clock_gettime() by approximately 15% on Intel i7-3520M @ 2.90GHz. Signed-off-by: Marcelo Tosatti Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/pvclock.h | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index d6b078e9fa28..628954ceede1 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -86,7 +86,6 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, offset = pvclock_get_nsec_offset(src); ret = src->system_time + offset; ret_flags = src->flags; - rdtsc_barrier(); *cycles = ret; *flags = ret_flags; -- cgit v1.2.3 From 4eb64dce8d0a3ceccc0036383e4683b7c3ea7a50 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 30 Apr 2015 12:57:28 +0200 Subject: KVM: x86: dump VMCS on invalid entry Code and format roughly based on Xen's vmcs_dump_vcpu. Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 153 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 153 insertions(+) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 3c218fd59f8c..63849a0334a6 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -7690,6 +7690,158 @@ static void kvm_flush_pml_buffers(struct kvm *kvm) kvm_vcpu_kick(vcpu); } +static void vmx_dump_sel(char *name, uint32_t sel) +{ + pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n", + name, vmcs_read32(sel), + vmcs_read32(sel + GUEST_ES_AR_BYTES - GUEST_ES_SELECTOR), + vmcs_read32(sel + GUEST_ES_LIMIT - GUEST_ES_SELECTOR), + vmcs_readl(sel + GUEST_ES_BASE - GUEST_ES_SELECTOR)); +} + +static void vmx_dump_dtsel(char *name, uint32_t limit) +{ + pr_err("%s limit=0x%08x, base=0x%016lx\n", + name, vmcs_read32(limit), + vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT)); +} + +static void dump_vmcs(void) +{ + u32 vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS); + u32 vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS); + u32 cpu_based_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); + u32 pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL); + u32 secondary_exec_control = 0; + unsigned long cr4 = vmcs_readl(GUEST_CR4); + u64 efer = vmcs_readl(GUEST_IA32_EFER); + int i, n; + + if (cpu_has_secondary_exec_ctrls()) + secondary_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); + + pr_err("*** Guest State ***\n"); + pr_err("CR0: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n", + vmcs_readl(GUEST_CR0), vmcs_readl(CR0_READ_SHADOW), + vmcs_readl(CR0_GUEST_HOST_MASK)); + pr_err("CR4: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n", + cr4, vmcs_readl(CR4_READ_SHADOW), vmcs_readl(CR4_GUEST_HOST_MASK)); + pr_err("CR3 = 0x%016lx\n", vmcs_readl(GUEST_CR3)); + if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT) && + (cr4 & X86_CR4_PAE) && !(efer & EFER_LMA)) + { + pr_err("PDPTR0 = 0x%016lx PDPTR1 = 0x%016lx\n", + vmcs_readl(GUEST_PDPTR0), vmcs_readl(GUEST_PDPTR1)); + pr_err("PDPTR2 = 0x%016lx PDPTR3 = 0x%016lx\n", + vmcs_readl(GUEST_PDPTR2), vmcs_readl(GUEST_PDPTR3)); + } + pr_err("RSP = 0x%016lx RIP = 0x%016lx\n", + vmcs_readl(GUEST_RSP), vmcs_readl(GUEST_RIP)); + pr_err("RFLAGS=0x%08lx DR7 = 0x%016lx\n", + vmcs_readl(GUEST_RFLAGS), vmcs_readl(GUEST_DR7)); + pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n", + vmcs_readl(GUEST_SYSENTER_ESP), + vmcs_read32(GUEST_SYSENTER_CS), vmcs_readl(GUEST_SYSENTER_EIP)); + vmx_dump_sel("CS: ", GUEST_CS_SELECTOR); + vmx_dump_sel("DS: ", GUEST_DS_SELECTOR); + vmx_dump_sel("SS: ", GUEST_SS_SELECTOR); + vmx_dump_sel("ES: ", GUEST_ES_SELECTOR); + vmx_dump_sel("FS: ", GUEST_FS_SELECTOR); + vmx_dump_sel("GS: ", GUEST_GS_SELECTOR); + vmx_dump_dtsel("GDTR:", GUEST_GDTR_LIMIT); + vmx_dump_sel("LDTR:", GUEST_LDTR_SELECTOR); + vmx_dump_dtsel("IDTR:", GUEST_IDTR_LIMIT); + vmx_dump_sel("TR: ", GUEST_TR_SELECTOR); + if ((vmexit_ctl & (VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER)) || + (vmentry_ctl & (VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_IA32_EFER))) + pr_err("EFER = 0x%016llx PAT = 0x%016lx\n", + efer, vmcs_readl(GUEST_IA32_PAT)); + pr_err("DebugCtl = 0x%016lx DebugExceptions = 0x%016lx\n", + vmcs_readl(GUEST_IA32_DEBUGCTL), + vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS)); + if (vmentry_ctl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) + pr_err("PerfGlobCtl = 0x%016lx\n", + vmcs_readl(GUEST_IA32_PERF_GLOBAL_CTRL)); + if (vmentry_ctl & VM_ENTRY_LOAD_BNDCFGS) + pr_err("BndCfgS = 0x%016lx\n", vmcs_readl(GUEST_BNDCFGS)); + pr_err("Interruptibility = %08x ActivityState = %08x\n", + vmcs_read32(GUEST_INTERRUPTIBILITY_INFO), + vmcs_read32(GUEST_ACTIVITY_STATE)); + if (secondary_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) + pr_err("InterruptStatus = %04x\n", + vmcs_read16(GUEST_INTR_STATUS)); + + pr_err("*** Host State ***\n"); + pr_err("RIP = 0x%016lx RSP = 0x%016lx\n", + vmcs_readl(HOST_RIP), vmcs_readl(HOST_RSP)); + pr_err("CS=%04x SS=%04x DS=%04x ES=%04x FS=%04x GS=%04x TR=%04x\n", + vmcs_read16(HOST_CS_SELECTOR), vmcs_read16(HOST_SS_SELECTOR), + vmcs_read16(HOST_DS_SELECTOR), vmcs_read16(HOST_ES_SELECTOR), + vmcs_read16(HOST_FS_SELECTOR), vmcs_read16(HOST_GS_SELECTOR), + vmcs_read16(HOST_TR_SELECTOR)); + pr_err("FSBase=%016lx GSBase=%016lx TRBase=%016lx\n", + vmcs_readl(HOST_FS_BASE), vmcs_readl(HOST_GS_BASE), + vmcs_readl(HOST_TR_BASE)); + pr_err("GDTBase=%016lx IDTBase=%016lx\n", + vmcs_readl(HOST_GDTR_BASE), vmcs_readl(HOST_IDTR_BASE)); + pr_err("CR0=%016lx CR3=%016lx CR4=%016lx\n", + vmcs_readl(HOST_CR0), vmcs_readl(HOST_CR3), + vmcs_readl(HOST_CR4)); + pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n", + vmcs_readl(HOST_IA32_SYSENTER_ESP), + vmcs_read32(HOST_IA32_SYSENTER_CS), + vmcs_readl(HOST_IA32_SYSENTER_EIP)); + if (vmexit_ctl & (VM_EXIT_LOAD_IA32_PAT | VM_EXIT_LOAD_IA32_EFER)) + pr_err("EFER = 0x%016lx PAT = 0x%016lx\n", + vmcs_readl(HOST_IA32_EFER), vmcs_readl(HOST_IA32_PAT)); + if (vmexit_ctl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) + pr_err("PerfGlobCtl = 0x%016lx\n", + vmcs_readl(HOST_IA32_PERF_GLOBAL_CTRL)); + + pr_err("*** Control State ***\n"); + pr_err("PinBased=%08x CPUBased=%08x SecondaryExec=%08x\n", + pin_based_exec_ctrl, cpu_based_exec_ctrl, secondary_exec_control); + pr_err("EntryControls=%08x ExitControls=%08x\n", vmentry_ctl, vmexit_ctl); + pr_err("ExceptionBitmap=%08x PFECmask=%08x PFECmatch=%08x\n", + vmcs_read32(EXCEPTION_BITMAP), + vmcs_read32(PAGE_FAULT_ERROR_CODE_MASK), + vmcs_read32(PAGE_FAULT_ERROR_CODE_MATCH)); + pr_err("VMEntry: intr_info=%08x errcode=%08x ilen=%08x\n", + vmcs_read32(VM_ENTRY_INTR_INFO_FIELD), + vmcs_read32(VM_ENTRY_EXCEPTION_ERROR_CODE), + vmcs_read32(VM_ENTRY_INSTRUCTION_LEN)); + pr_err("VMExit: intr_info=%08x errcode=%08x ilen=%08x\n", + vmcs_read32(VM_EXIT_INTR_INFO), + vmcs_read32(VM_EXIT_INTR_ERROR_CODE), + vmcs_read32(VM_EXIT_INSTRUCTION_LEN)); + pr_err(" reason=%08x qualification=%016lx\n", + vmcs_read32(VM_EXIT_REASON), vmcs_readl(EXIT_QUALIFICATION)); + pr_err("IDTVectoring: info=%08x errcode=%08x\n", + vmcs_read32(IDT_VECTORING_INFO_FIELD), + vmcs_read32(IDT_VECTORING_ERROR_CODE)); + pr_err("TSC Offset = 0x%016lx\n", vmcs_readl(TSC_OFFSET)); + if (cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW) + pr_err("TPR Threshold = 0x%02x\n", vmcs_read32(TPR_THRESHOLD)); + if (pin_based_exec_ctrl & PIN_BASED_POSTED_INTR) + pr_err("PostedIntrVec = 0x%02x\n", vmcs_read16(POSTED_INTR_NV)); + if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT)) + pr_err("EPT pointer = 0x%016lx\n", vmcs_readl(EPT_POINTER)); + n = vmcs_read32(CR3_TARGET_COUNT); + for (i = 0; i + 1 < n; i += 4) + pr_err("CR3 target%u=%016lx target%u=%016lx\n", + i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2), + i + 1, vmcs_readl(CR3_TARGET_VALUE0 + i * 2 + 2)); + if (i < n) + pr_err("CR3 target%u=%016lx\n", + i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2)); + if (secondary_exec_control & SECONDARY_EXEC_PAUSE_LOOP_EXITING) + pr_err("PLE Gap=%08x Window=%08x\n", + vmcs_read32(PLE_GAP), vmcs_read32(PLE_WINDOW)); + if (secondary_exec_control & SECONDARY_EXEC_ENABLE_VPID) + pr_err("Virtual processor ID = 0x%04x\n", + vmcs_read16(VIRTUAL_PROCESSOR_ID)); +} + /* * The guest has exited. See if we can fix it or if we need userspace * assistance. @@ -7722,6 +7874,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) } if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) { + dump_vmcs(); vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; vcpu->run->fail_entry.hardware_entry_failure_reason = exit_reason; -- cgit v1.2.3 From 251eb84144ec7aba5e344fb8553c67e749655aef Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= Date: Fri, 10 Apr 2015 21:47:27 +0200 Subject: KVM: reuse memslot in kvm_write_guest_page MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Caching memslot value and using mark_page_dirty_in_slot() avoids another O(log N) search when dirtying the page. Signed-off-by: Radim Krčmář Message-Id: <1428695247-27603-1-git-send-email-rkrcmar@redhat.com> Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 90977418aeb6..b6d415156283 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1590,15 +1590,17 @@ int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, int offset, int len) { int r; + struct kvm_memory_slot *memslot; unsigned long addr; - addr = gfn_to_hva(kvm, gfn); + memslot = gfn_to_memslot(kvm, gfn); + addr = gfn_to_hva_memslot(memslot, gfn); if (kvm_is_error_hva(addr)) return -EFAULT; r = __copy_to_user((void __user *)addr + offset, data, len); if (r) return -EFAULT; - mark_page_dirty(kvm, gfn); + mark_page_dirty_in_slot(kvm, memslot, gfn); return 0; } EXPORT_SYMBOL_GPL(kvm_write_guest_page); -- cgit v1.2.3 From acac6f89574c743796c9c947e046a0d6637d5fe2 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Sun, 3 May 2015 20:22:57 +0300 Subject: KVM: x86: Call-far should not be emulated as stack op Far call in 64-bit has a 32-bit operand size. Remove the marking of this operation as Stack so it can be emulated correctly in 64-bit. Signed-off-by: Nadav Amit Signed-off-by: Paolo Bonzini --- arch/x86/kvm/emulate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 630bcb0d7a04..5839fc56cb3e 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3840,7 +3840,7 @@ static const struct opcode group5[] = { F(DstMem | SrcNone | Lock, em_inc), F(DstMem | SrcNone | Lock, em_dec), I(SrcMem | NearBranch, em_call_near_abs), - I(SrcMemFAddr | ImplicitOps | Stack, em_call_far), + I(SrcMemFAddr | ImplicitOps, em_call_far), I(SrcMem | NearBranch, em_jmp_abs), I(SrcMemFAddr | ImplicitOps, em_jmp_far), I(SrcMem | Stack, em_push), D(Undefined), -- cgit v1.2.3 From 8a9781f7ad0087182c51c629335803264568ef3b Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Mon, 4 May 2015 08:32:32 +0200 Subject: KVM: nVMX: Fix host crash when loading MSRs with userspace irqchip vcpu->arch.apic is NULL when a userspace irqchip is active. But instead of letting the test incorrectly depend on in-kernel irqchip mode, open-code it to catch also userspace x2APICs. Signed-off-by: Jan Kiszka Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 63849a0334a6..5e8d41bccc26 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2170,8 +2170,7 @@ static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu) if (is_guest_mode(vcpu)) msr_bitmap = vmx_msr_bitmap_nested; - else if (irqchip_in_kernel(vcpu->kvm) && - apic_x2apic_mode(vcpu->arch.apic)) { + else if (vcpu->arch.apic_base & X2APIC_ENABLE) { if (is_long_mode(vcpu)) msr_bitmap = vmx_msr_bitmap_longmode_x2apic; else @@ -9076,7 +9075,7 @@ static int nested_vmx_msr_check_common(struct kvm_vcpu *vcpu, struct vmx_msr_entry *e) { /* x2APIC MSR accesses are not allowed */ - if (apic_x2apic_mode(vcpu->arch.apic) && e->index >> 8 == 0x8) + if (vcpu->arch.apic_base & X2APIC_ENABLE && e->index >> 8 == 0x8) return -EINVAL; if (e->index == MSR_IA32_UCODE_WRITE || /* SDM Table 35-2 */ e->index == MSR_IA32_UCODE_REV) -- cgit v1.2.3 From a4cca3b419a5081788bb7559023159e3147f66f0 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 5 May 2015 09:39:08 +0200 Subject: KVM: remove pointless cpu hotplug messages On cpu hotplug only KVM emits an unconditional message that its notifier has been called. It certainly can be assumed that calling cpu hotplug notifiers work, therefore there is no added value if KVM prints a message. If an error happens on cpu online KVM will still emit a warning. So let's remove this superfluous message. Signed-off-by: Heiko Carstens Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index b6d415156283..f202c4035134 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2884,18 +2884,12 @@ static int hardware_enable_all(void) static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val, void *v) { - int cpu = (long)v; - val &= ~CPU_TASKS_FROZEN; switch (val) { case CPU_DYING: - pr_info("kvm: disabling virtualization on CPU%d\n", - cpu); hardware_disable(); break; case CPU_STARTING: - pr_info("kvm: enabling virtualization on CPU%d\n", - cpu); hardware_enable(); break; } -- cgit v1.2.3 From ceee7df749da03fa17ab5dc7d06dffb4980a32db Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Thu, 7 May 2015 16:20:15 +0800 Subject: KVM: MMU: fix smap permission check Current permission check assumes that RSVD bit in PFEC is always zero, however, it is not true since MMIO #PF will use it to quickly identify MMIO access Fix it by clearing the bit if walking guest page table is needed Signed-off-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu.h | 2 ++ arch/x86/kvm/paging_tmpl.h | 7 +++++++ 2 files changed, 9 insertions(+) diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index c7d65637c851..06eb2fc1bab8 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -166,6 +166,8 @@ static inline bool permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, int index = (pfec >> 1) + (smap >> (X86_EFLAGS_AC_BIT - PFERR_RSVD_BIT + 1)); + WARN_ON(pfec & PFERR_RSVD_MASK); + return (mmu->permissions[index] >> pte_access) & 1; } diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index fd49c867b25a..6e6d115fe9b5 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -718,6 +718,13 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, mmu_is_nested(vcpu)); if (likely(r != RET_MMIO_PF_INVALID)) return r; + + /* + * page fault with PFEC.RSVD = 1 is caused by shadow + * page fault, should not be used to walk guest page + * table. + */ + error_code &= ~PFERR_RSVD_MASK; }; r = mmu_topup_memory_caches(vcpu); -- cgit v1.2.3 From 31fd9880a1c52de8880ea49dca7848caacb4b3a3 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 2 Apr 2015 11:04:05 +0200 Subject: KVM: MMU: fix CR4.SMEP=1, CR0.WP=0 with shadow pages smep_andnot_wp is initialized in kvm_init_shadow_mmu and shadow pages should not be reused for different values of it. Thus, it has to be added to the mask in kvm_mmu_pte_write. Reviewed-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index d43867c33bc4..209fe1477465 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4238,7 +4238,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, ++vcpu->kvm->stat.mmu_pte_write; kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE); - mask.cr0_wp = mask.cr4_pae = mask.nxe = 1; + mask.cr0_wp = mask.cr4_pae = mask.nxe = mask.smep_andnot_wp = 1; for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) { if (detect_write_misaligned(sp, gpa, bytes) || detect_write_flooding(sp)) { -- cgit v1.2.3 From b938eacea0b6881f2116a061e6da3ec840e75137 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 30 Apr 2015 13:33:59 +0200 Subject: KVM: s390: fix external call injection without sigp interpretation Commit ea5f49692575 ("KVM: s390: only one external call may be pending at a time") introduced a bug on machines that don't have SIGP interpretation facility installed. The injection of an external call will now always fail with -EBUSY (if none is already pending). This leads to the following symptoms: - An external call will be injected but with the wrong "src cpu id", as this id will not be remembered. - The target vcpu will not be woken up, therefore the guest will hang if it cannot deal with unexpected failures of the SIGP EXTERNAL CALL instruction. - If an external call is already pending, -EBUSY will not be reported. Reviewed-by: Christian Borntraeger Reviewed-by: Jens Freimann Signed-off-by: David Hildenbrand Cc: stable@vger.kernel.org # v4.0 Signed-off-by: Christian Borntraeger --- arch/s390/kvm/interrupt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 9de47265ef73..2836b25f63d3 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1061,7 +1061,7 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) if (sclp_has_sigpif()) return __inject_extcall_sigpif(vcpu, src_id); - if (!test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs)) + if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs)) return -EBUSY; *extcall = irq->u.extcall; atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); -- cgit v1.2.3 From 785dbef407d8b3c82348aba2689e493c752c62ec Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Thu, 16 Apr 2015 16:58:22 +0200 Subject: KVM: s390: optimize round trip time in request handling The fast path for a sie exit is that no kvm reqest is pending. Make an early check to skip all single bit checks. Reviewed-by: David Hildenbrand Signed-off-by: Christian Borntraeger --- arch/s390/kvm/kvm-s390.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 8cd8e7b288c5..f5282e62f87f 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1720,6 +1720,8 @@ static bool ibs_enabled(struct kvm_vcpu *vcpu) static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu) { + if (!vcpu->requests) + return 0; retry: s390_vcpu_unblock(vcpu); /* -- cgit v1.2.3 From a4a4f1916abbbc3148d79a37cf3fe4f3f6c604d9 Mon Sep 17 00:00:00 2001 From: Guenther Hutzl Date: Tue, 31 Mar 2015 14:39:49 +0200 Subject: KVM: s390: make EDAT1 depend on host support We should only enable EDAT1 for the guest if the host actually supports it and the cpu model for the guest has EDAT-1 enabled. Reviewed-by: David Hildenbrand Reviewed-by: Cornelia Huck Reviewed-by: Christian Borntraeger Signed-off-by: Guenther Hutzl Signed-off-by: Christian Borntraeger --- arch/s390/kvm/kvm-s390.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index f5282e62f87f..2da36c432aea 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1311,8 +1311,11 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH | CPUSTAT_SM | - CPUSTAT_STOPPED | - CPUSTAT_GED); + CPUSTAT_STOPPED); + + if (test_kvm_facility(vcpu->kvm, 8)) + atomic_set_mask(CPUSTAT_GED, &vcpu->arch.sie_block->cpuflags); + kvm_s390_vcpu_setup_model(vcpu); vcpu->arch.sie_block->ecb = 6; -- cgit v1.2.3 From 53df84f8de312586e1c05a8f496f614ca814eeff Mon Sep 17 00:00:00 2001 From: Guenther Hutzl Date: Wed, 18 Feb 2015 11:13:03 +0100 Subject: KVM: s390: Enable guest EDAT2 support 1. Enable EDAT2 in the list of KVM facilities 2. Handle 2G frames in pfmf instruction If we support EDAT2, we may enable handling of 2G frames if not in 24 bit mode. 3. Enable EDAT2 in sie_block If the EDAT2 facility is available we enable GED2 mode control in the sie_block. Reviewed-by: David Hildenbrand Reviewed-by: Cornelia Huck Reviewed-by: Christian Borntraeger Signed-off-by: Guenther Hutzl Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/kvm_host.h | 1 + arch/s390/kvm/kvm-s390.c | 6 ++++-- arch/s390/kvm/priv.c | 8 ++++++-- 3 files changed, 11 insertions(+), 4 deletions(-) diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index d01fc588b5c3..1011ac1434f5 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -80,6 +80,7 @@ struct sca_block { #define CPUSTAT_MCDS 0x00000100 #define CPUSTAT_SM 0x00000080 #define CPUSTAT_IBS 0x00000040 +#define CPUSTAT_GED2 0x00000010 #define CPUSTAT_G 0x00000008 #define CPUSTAT_GED 0x00000004 #define CPUSTAT_J 0x00000002 diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 2da36c432aea..142d9b40528d 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -110,7 +110,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { /* upper facilities limit for kvm */ unsigned long kvm_s390_fac_list_mask[] = { 0xffe6fffbfcfdfc40UL, - 0x005c800000000000UL, + 0x005e800000000000UL, }; unsigned long kvm_s390_fac_list_mask_size(void) @@ -1313,7 +1313,9 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) CPUSTAT_SM | CPUSTAT_STOPPED); - if (test_kvm_facility(vcpu->kvm, 8)) + if (test_kvm_facility(vcpu->kvm, 78)) + atomic_set_mask(CPUSTAT_GED2, &vcpu->arch.sie_block->cpuflags); + else if (test_kvm_facility(vcpu->kvm, 8)) atomic_set_mask(CPUSTAT_GED, &vcpu->arch.sie_block->cpuflags); kvm_s390_vcpu_setup_model(vcpu); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index d22d8ee1ff9d..ad4242245771 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -698,10 +698,14 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) case 0x00001000: end = (start + (1UL << 20)) & ~((1UL << 20) - 1); break; - /* We dont support EDAT2 case 0x00002000: + /* only support 2G frame size if EDAT2 is available and we are + not in 24-bit addressing mode */ + if (!test_kvm_facility(vcpu->kvm, 78) || + psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_AMODE_24BIT) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); end = (start + (1UL << 31)) & ~((1UL << 31) - 1); - break;*/ + break; default: return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); } -- cgit v1.2.3 From 8e23654687c97df1c0e4b1def245a05001eaf640 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Thu, 9 Apr 2015 13:49:04 +0200 Subject: KVM: s390: make exit_sie_sync more robust exit_sie_sync is used to kick CPUs out of SIE and prevent reentering at any point in time. This is used to reload the prefix pages and to set the IBS stuff in a way that guarantees that after this function returns we are no longer in SIE. All current users trigger KVM requests. The request must be set before we block the CPUs to avoid races. Let's make this implicit by adding the request into a new function kvm_s390_sync_requests that replaces exit_sie_sync and split out s390_vcpu_block and s390_vcpu_unblock, that can be used to keep CPUs out of SIE independent of requests. Signed-off-by: Christian Borntraeger Reviewed-by: David Hildenbrand Reviewed-by: Cornelia Huck --- arch/s390/include/asm/kvm_host.h | 3 ++- arch/s390/kernel/entry.S | 2 +- arch/s390/kvm/kvm-s390.c | 28 ++++++++++++++++++---------- arch/s390/kvm/kvm-s390.h | 2 +- 4 files changed, 22 insertions(+), 13 deletions(-) diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 1011ac1434f5..444c412307cb 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -96,7 +96,8 @@ struct kvm_s390_sie_block { #define PROG_IN_SIE (1<<0) __u32 prog0c; /* 0x000c */ __u8 reserved10[16]; /* 0x0010 */ -#define PROG_BLOCK_SIE 0x00000001 +#define PROG_BLOCK_SIE (1<<0) +#define PROG_REQUEST (1<<1) atomic_t prog20; /* 0x0020 */ __u8 reserved24[4]; /* 0x0024 */ __u64 cputm; /* 0x0028 */ diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 99b44acbfcc7..3238893c9d4f 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -1005,7 +1005,7 @@ ENTRY(sie64a) .Lsie_gmap: lg %r14,__SF_EMPTY(%r15) # get control block pointer oi __SIE_PROG0C+3(%r14),1 # we are going into SIE now - tm __SIE_PROG20+3(%r14),1 # last exit... + tm __SIE_PROG20+3(%r14),3 # last exit... jnz .Lsie_done LPP __SF_EMPTY(%r15) # set guest id sie 0(%r14) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 142d9b40528d..9bc57afe54ba 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1424,6 +1424,16 @@ void s390_vcpu_unblock(struct kvm_vcpu *vcpu) atomic_clear_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20); } +static void kvm_s390_vcpu_request(struct kvm_vcpu *vcpu) +{ + atomic_set_mask(PROG_REQUEST, &vcpu->arch.sie_block->prog20); +} + +static void kvm_s390_vcpu_request_handled(struct kvm_vcpu *vcpu) +{ + atomic_clear_mask(PROG_REQUEST, &vcpu->arch.sie_block->prog20); +} + /* * Kick a guest cpu out of SIE and wait until SIE is not running. * If the CPU is not running (e.g. waiting as idle) the function will @@ -1435,10 +1445,11 @@ void exit_sie(struct kvm_vcpu *vcpu) cpu_relax(); } -/* Kick a guest cpu out of SIE and prevent SIE-reentry */ -void exit_sie_sync(struct kvm_vcpu *vcpu) +/* Kick a guest cpu out of SIE to process a request synchronously */ +void kvm_s390_sync_request(int req, struct kvm_vcpu *vcpu) { - s390_vcpu_block(vcpu); + kvm_make_request(req, vcpu); + kvm_s390_vcpu_request(vcpu); exit_sie(vcpu); } @@ -1452,8 +1463,7 @@ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address) /* match against both prefix pages */ if (kvm_s390_get_prefix(vcpu) == (address & ~0x1000UL)) { VCPU_EVENT(vcpu, 2, "gmap notifier for %lx", address); - kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); - exit_sie_sync(vcpu); + kvm_s390_sync_request(KVM_REQ_MMU_RELOAD, vcpu); } } } @@ -1728,7 +1738,7 @@ static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu) if (!vcpu->requests) return 0; retry: - s390_vcpu_unblock(vcpu); + kvm_s390_vcpu_request_handled(vcpu); /* * We use MMU_RELOAD just to re-arm the ipte notifier for the * guest prefix page. gmap_ipte_notify will wait on the ptl lock. @@ -2213,8 +2223,7 @@ int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr) static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu) { kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu); - kvm_make_request(KVM_REQ_DISABLE_IBS, vcpu); - exit_sie_sync(vcpu); + kvm_s390_sync_request(KVM_REQ_DISABLE_IBS, vcpu); } static void __disable_ibs_on_all_vcpus(struct kvm *kvm) @@ -2230,8 +2239,7 @@ static void __disable_ibs_on_all_vcpus(struct kvm *kvm) static void __enable_ibs_on_vcpu(struct kvm_vcpu *vcpu) { kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu); - kvm_make_request(KVM_REQ_ENABLE_IBS, vcpu); - exit_sie_sync(vcpu); + kvm_s390_sync_request(KVM_REQ_ENABLE_IBS, vcpu); } void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu) diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index ca108b90ae56..8edca85e246e 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -214,7 +214,7 @@ void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu); void s390_vcpu_block(struct kvm_vcpu *vcpu); void s390_vcpu_unblock(struct kvm_vcpu *vcpu); void exit_sie(struct kvm_vcpu *vcpu); -void exit_sie_sync(struct kvm_vcpu *vcpu); +void kvm_s390_sync_request(int req, struct kvm_vcpu *vcpu); int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu); void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu); /* is cmma enabled */ -- cgit v1.2.3 From 27406cd50cf6653196eea8ebbb15a75596da01ca Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 14 Apr 2015 12:17:34 +0200 Subject: KVM: s390: provide functions for blocking all CPUs Some updates to the control blocks need to be done in a way that ensures that no CPU is within SIE. Provide wrappers around the s390_vcpu_block functions and adopt the TOD migration code to update in a guaranteed fashion. Also rename these functions to have the kvm_s390_ prefix as everything else. Signed-off-by: Christian Borntraeger Reviewed-by: David Hildenbrand --- arch/s390/kvm/kvm-s390.c | 10 +++++----- arch/s390/kvm/kvm-s390.h | 23 +++++++++++++++++++++-- 2 files changed, 26 insertions(+), 7 deletions(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 9bc57afe54ba..6bc69ab5b5b4 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -454,10 +454,10 @@ static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr) mutex_lock(&kvm->lock); kvm->arch.epoch = gtod - host_tod; - kvm_for_each_vcpu(vcpu_idx, cur_vcpu, kvm) { + kvm_s390_vcpu_block_all(kvm); + kvm_for_each_vcpu(vcpu_idx, cur_vcpu, kvm) cur_vcpu->arch.sie_block->epoch = kvm->arch.epoch; - exit_sie(cur_vcpu); - } + kvm_s390_vcpu_unblock_all(kvm); mutex_unlock(&kvm->lock); return 0; } @@ -1414,12 +1414,12 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) return kvm_s390_vcpu_has_irq(vcpu, 0); } -void s390_vcpu_block(struct kvm_vcpu *vcpu) +void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu) { atomic_set_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20); } -void s390_vcpu_unblock(struct kvm_vcpu *vcpu) +void kvm_s390_vcpu_unblock(struct kvm_vcpu *vcpu) { atomic_clear_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20); } diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 8edca85e246e..c5704786e473 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -211,8 +211,8 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr); int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu); void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu); -void s390_vcpu_block(struct kvm_vcpu *vcpu); -void s390_vcpu_unblock(struct kvm_vcpu *vcpu); +void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu); +void kvm_s390_vcpu_unblock(struct kvm_vcpu *vcpu); void exit_sie(struct kvm_vcpu *vcpu); void kvm_s390_sync_request(int req, struct kvm_vcpu *vcpu); int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu); @@ -228,6 +228,25 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu); int kvm_s390_inject_prog_irq(struct kvm_vcpu *vcpu, struct kvm_s390_pgm_info *pgm_info); +static inline void kvm_s390_vcpu_block_all(struct kvm *kvm) +{ + int i; + struct kvm_vcpu *vcpu; + + WARN_ON(!mutex_is_locked(&kvm->lock)); + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_s390_vcpu_block(vcpu); +} + +static inline void kvm_s390_vcpu_unblock_all(struct kvm *kvm) +{ + int i; + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_s390_vcpu_unblock(vcpu); +} + /** * kvm_s390_inject_prog_cond - conditionally inject a program check * @vcpu: virtual cpu -- cgit v1.2.3 From ffeca0ae880055457e56e45fd79cfa28d7160c30 Mon Sep 17 00:00:00 2001 From: Jens Freimann Date: Fri, 17 Apr 2015 10:21:04 +0200 Subject: KVM: s390: optimize interrupt handling round trip time We can avoid checking guest control registers and guest PSW as well as all the masking and calculations on the interrupt masks when no interrupts are pending. Also, the check for IRQ_PEND_COUNT can be removed, because we won't enter the while loop if no interrupts are pending and invalid interrupt types can't be injected. Signed-off-by: Jens Freimann Reviewed-by: Cornelia Huck Reviewed-by: Dominik Dingel Acked-by: Christian Borntraeger --- arch/s390/kvm/interrupt.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 2836b25f63d3..acf4a4e660c0 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -134,6 +134,8 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu) active_mask = pending_local_irqs(vcpu); active_mask |= pending_floating_irqs(vcpu); + if (!active_mask) + return 0; if (psw_extint_disabled(vcpu)) active_mask &= ~IRQ_PEND_EXT_MASK; @@ -941,12 +943,9 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) if (cpu_timer_irq_pending(vcpu)) set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs); - do { - irqs = deliverable_irqs(vcpu); + while ((irqs = deliverable_irqs(vcpu)) && !rc) { /* bits are in the order of interrupt priority */ irq_type = find_first_bit(&irqs, IRQ_PEND_COUNT); - if (irq_type == IRQ_PEND_COUNT) - break; if (is_ioirq(irq_type)) { rc = __deliver_io(vcpu, irq_type); } else { @@ -958,9 +957,7 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) } rc = func(vcpu); } - if (rc) - break; - } while (!rc); + } set_intercept_indicators(vcpu); -- cgit v1.2.3 From 96e0ed23dca3769053c5211ef885e789097834bf Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 14 Jan 2015 14:08:38 +0100 Subject: KVM: s390: factor out and optimize floating irq VCPU kick This patch factors out the search for a floating irq destination VCPU as well as the kicking of the found VCPU. The search is optimized in the following ways: 1. stopped VCPUs can't take any floating interrupts, so try to find an operating one. We have to take care of the special case where all VCPUs are stopped and we don't have any valid destination. 2. use online_vcpus, not KVM_MAX_VCPU. This speeds up the search especially if KVM_MAX_VCPU is increased one day. As these VCPU objects are initialized prior to increasing online_vcpus, we can be sure that they exist. Reviewed-by: Cornelia Huck Reviewed-by: Dominik Dingel Reviewed-by: Jens Freimann Signed-off-by: David Hildenbrand Signed-off-by: Christian Borntraeger --- arch/s390/kvm/interrupt.c | 74 +++++++++++++++++++++++++++++------------------ 1 file changed, 46 insertions(+), 28 deletions(-) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index acf4a4e660c0..322ef9cfdc80 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1337,12 +1337,54 @@ static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) return 0; } -static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) +/* + * Find a destination VCPU for a floating irq and kick it. + */ +static void __floating_irq_kick(struct kvm *kvm, u64 type) { + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; struct kvm_s390_local_interrupt *li; + struct kvm_vcpu *dst_vcpu; + int sigcpu, online_vcpus, nr_tries = 0; + + online_vcpus = atomic_read(&kvm->online_vcpus); + if (!online_vcpus) + return; + + /* find idle VCPUs first, then round robin */ + sigcpu = find_first_bit(fi->idle_mask, online_vcpus); + if (sigcpu == online_vcpus) { + do { + sigcpu = fi->next_rr_cpu; + fi->next_rr_cpu = (fi->next_rr_cpu + 1) % online_vcpus; + /* avoid endless loops if all vcpus are stopped */ + if (nr_tries++ >= online_vcpus) + return; + } while (is_vcpu_stopped(kvm_get_vcpu(kvm, sigcpu))); + } + dst_vcpu = kvm_get_vcpu(kvm, sigcpu); + + /* make the VCPU drop out of the SIE, or wake it up if sleeping */ + li = &dst_vcpu->arch.local_int; + spin_lock(&li->lock); + switch (type) { + case KVM_S390_MCHK: + atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags); + break; + case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: + atomic_set_mask(CPUSTAT_IO_INT, li->cpuflags); + break; + default: + atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); + break; + } + spin_unlock(&li->lock); + kvm_s390_vcpu_wakeup(dst_vcpu); +} + +static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) +{ struct kvm_s390_float_interrupt *fi; - struct kvm_vcpu *dst_vcpu = NULL; - int sigcpu; u64 type = READ_ONCE(inti->type); int rc; @@ -1370,32 +1412,8 @@ static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) if (rc) return rc; - sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS); - if (sigcpu == KVM_MAX_VCPUS) { - do { - sigcpu = fi->next_rr_cpu++; - if (sigcpu == KVM_MAX_VCPUS) - sigcpu = fi->next_rr_cpu = 0; - } while (kvm_get_vcpu(kvm, sigcpu) == NULL); - } - dst_vcpu = kvm_get_vcpu(kvm, sigcpu); - li = &dst_vcpu->arch.local_int; - spin_lock(&li->lock); - switch (type) { - case KVM_S390_MCHK: - atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags); - break; - case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: - atomic_set_mask(CPUSTAT_IO_INT, li->cpuflags); - break; - default: - atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); - break; - } - spin_unlock(&li->lock); - kvm_s390_vcpu_wakeup(kvm_get_vcpu(kvm, sigcpu)); + __floating_irq_kick(kvm, type); return 0; - } int kvm_s390_inject_vm(struct kvm *kvm, -- cgit v1.2.3 From 06b36753a6466239fc945b6756e12d635621ae5f Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 24 Apr 2015 15:30:24 +0200 Subject: KVM: s390: drop handling of interception code 12 Our implementation will never trigger interception code 12 as the responsible setting is never enabled - and never will be. The handler is dead code. Let's get rid of it. Reviewed-by: Cornelia Huck Signed-off-by: David Hildenbrand Signed-off-by: Christian Borntraeger --- arch/s390/kvm/intercept.c | 16 ---------------- 1 file changed, 16 deletions(-) diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 9e3779e3e496..7365e8a46032 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -241,21 +241,6 @@ static int handle_prog(struct kvm_vcpu *vcpu) return kvm_s390_inject_prog_irq(vcpu, &pgm_info); } -static int handle_instruction_and_prog(struct kvm_vcpu *vcpu) -{ - int rc, rc2; - - vcpu->stat.exit_instr_and_program++; - rc = handle_instruction(vcpu); - rc2 = handle_prog(vcpu); - - if (rc == -EOPNOTSUPP) - vcpu->arch.sie_block->icptcode = 0x04; - if (rc) - return rc; - return rc2; -} - /** * handle_external_interrupt - used for external interruption interceptions * @@ -355,7 +340,6 @@ static const intercept_handler_t intercept_funcs[] = { [0x00 >> 2] = handle_noop, [0x04 >> 2] = handle_instruction, [0x08 >> 2] = handle_prog, - [0x0C >> 2] = handle_instruction_and_prog, [0x10 >> 2] = handle_noop, [0x14 >> 2] = handle_external_interrupt, [0x18 >> 2] = handle_noop, -- cgit v1.2.3 From 3db176d5b4170284d9ce1e1e9c441ebfa9a37417 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Sun, 19 Apr 2015 21:12:59 +0300 Subject: KVM: x86: Fix DR7 mask on task-switch while debugging If the host sets hardware breakpoints to debug the guest, and a task-switch occurs in the guest, the architectural DR7 will not be updated. The effective DR7 would be updated instead. This fix puts the DR7 update during task-switch emulation, so it now uses the standard DR setting mechanism instead of the one that was previously used. As a bonus, the update of DR7 will now be effective for AMD as well. Signed-off-by: Nadav Amit Signed-off-by: Paolo Bonzini --- arch/x86/kvm/emulate.c | 6 +++++- arch/x86/kvm/vmx.c | 3 --- 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 5839fc56cb3e..b32a38e6e287 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -25,6 +25,7 @@ #include #include #include +#include #include "x86.h" #include "tss.h" @@ -2849,7 +2850,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, ulong old_tss_base = ops->get_cached_segment_base(ctxt, VCPU_SREG_TR); u32 desc_limit; - ulong desc_addr; + ulong desc_addr, dr7; /* FIXME: old_tss_base == ~0 ? */ @@ -2934,6 +2935,9 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, ret = em_push(ctxt); } + ops->get_dr(ctxt, 7, &dr7); + ops->set_dr(ctxt, 7, dr7 & ~(DR_LOCAL_ENABLE_MASK | DR_LOCAL_SLOWDOWN)); + return ret; } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 5e8d41bccc26..bcb61b024386 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -5708,9 +5708,6 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) return 0; } - /* clear all local breakpoint enable flags */ - vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~0x155); - /* * TODO: What about debug traps on tss switch? * Are we supposed to inject them and update dr6? -- cgit v1.2.3 From ee122a7109e42313caadf6038ab773d1f68fcce1 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Tue, 28 Apr 2015 13:06:00 +0300 Subject: KVM: x86: Fix update RCX/RDI/RSI on REP-string When REP-string instruction is preceded with an address-size prefix, ECX/EDI/ESI are used as the operation counter and pointers. When they are updated, the high 32-bits of RCX/RDI/RSI are cleared, similarly to the way they are updated on every 32-bit register operation. Fix it. Signed-off-by: Nadav Amit Signed-off-by: Paolo Bonzini --- arch/x86/kvm/emulate.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index b32a38e6e287..e8c03be83e48 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -524,13 +524,9 @@ static void masked_increment(ulong *reg, ulong mask, int inc) static inline void register_address_increment(struct x86_emulate_ctxt *ctxt, int reg, int inc) { - ulong mask; + ulong *preg = reg_rmw(ctxt, reg); - if (ctxt->ad_bytes == sizeof(unsigned long)) - mask = ~0UL; - else - mask = ad_mask(ctxt); - masked_increment(reg_rmw(ctxt, reg), mask, inc); + assign_register(preg, *preg + inc, ctxt->ad_bytes); } static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc) -- cgit v1.2.3 From 428e3d08574b77876ea5e71f294f91bd8afa51b5 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Tue, 28 Apr 2015 13:06:01 +0300 Subject: KVM: x86: Fix zero iterations REP-string When a REP-string is executed in 64-bit mode with an address-size prefix, ECX/EDI/ESI are used as counter and pointers. When ECX is initially zero, Intel CPUs clear the high 32-bits of RCX, and recent Intel CPUs update the high bits of the pointers in MOVS/STOS. This behavior is specific to Intel according to few experiments. As one may guess, this is an undocumented behavior. Yet, it is observable in the guest, since at least VMX traps REP-INS/OUTS even when ECX=0. Note that VMware appears to get it right. The behavior can be observed using the following code: #include #define LOW_MASK (0xffffffff00000000ull) #define ALL_MASK (0xffffffffffffffffull) #define TEST(opcode) \ do { \ asm volatile(".byte 0xf2 \n\t .byte 0x67 \n\t .byte " opcode "\n\t" \ : "=S"(s), "=c"(c), "=D"(d) \ : "S"(ALL_MASK), "c"(LOW_MASK), "D"(ALL_MASK)); \ printf("opcode %s rcx=%llx rsi=%llx rdi=%llx\n", \ opcode, c, s, d); \ } while(0) void main() { unsigned long long s, d, c; iopl(3); TEST("0x6c"); TEST("0x6d"); TEST("0x6e"); TEST("0x6f"); TEST("0xa4"); TEST("0xa5"); TEST("0xa6"); TEST("0xa7"); TEST("0xaa"); TEST("0xab"); TEST("0xae"); TEST("0xaf"); } Signed-off-by: Nadav Amit Signed-off-by: Paolo Bonzini --- arch/x86/kvm/emulate.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index e8c03be83e48..9b655d113fc6 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2570,6 +2570,30 @@ static bool emulator_io_permited(struct x86_emulate_ctxt *ctxt, return true; } +static void string_registers_quirk(struct x86_emulate_ctxt *ctxt) +{ + /* + * Intel CPUs mask the counter and pointers in quite strange + * manner when ECX is zero due to REP-string optimizations. + */ +#ifdef CONFIG_X86_64 + if (ctxt->ad_bytes != 4 || !vendor_intel(ctxt)) + return; + + *reg_write(ctxt, VCPU_REGS_RCX) = 0; + + switch (ctxt->b) { + case 0xa4: /* movsb */ + case 0xa5: /* movsd/w */ + *reg_rmw(ctxt, VCPU_REGS_RSI) &= (u32)-1; + /* fall through */ + case 0xaa: /* stosb */ + case 0xab: /* stosd/w */ + *reg_rmw(ctxt, VCPU_REGS_RDI) &= (u32)-1; + } +#endif +} + static void save_state_to_tss16(struct x86_emulate_ctxt *ctxt, struct tss_segment_16 *tss) { @@ -4910,6 +4934,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) if (ctxt->rep_prefix && (ctxt->d & String)) { /* All REP prefixes have the same first termination condition */ if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0) { + string_registers_quirk(ctxt); ctxt->eip = ctxt->_eip; ctxt->eflags &= ~X86_EFLAGS_RF; goto done; -- cgit v1.2.3 From edc90b7dc4ceef62ef0ad9cc6c3f5dc770e83ad2 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 11 May 2015 22:55:21 +0800 Subject: KVM: MMU: fix SMAP virtualization KVM may turn a user page to a kernel page when kernel writes a readonly user page if CR0.WP = 1. This shadow page entry will be reused after SMAP is enabled so that kernel is allowed to access this user page Fix it by setting SMAP && !CR0.WP into shadow page's role and reset mmu once CR4.SMAP is updated Signed-off-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- Documentation/virtual/kvm/mmu.txt | 18 ++++++++++++++---- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/mmu.c | 16 ++++++++++++---- arch/x86/kvm/mmu.h | 2 -- arch/x86/kvm/x86.c | 8 +++----- 5 files changed, 30 insertions(+), 15 deletions(-) diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt index 53838d9c6295..c59bd9bc41ef 100644 --- a/Documentation/virtual/kvm/mmu.txt +++ b/Documentation/virtual/kvm/mmu.txt @@ -169,6 +169,10 @@ Shadow pages contain the following information: Contains the value of cr4.smep && !cr0.wp for which the page is valid (pages for which this is true are different from other pages; see the treatment of cr0.wp=0 below). + role.smap_andnot_wp: + Contains the value of cr4.smap && !cr0.wp for which the page is valid + (pages for which this is true are different from other pages; see the + treatment of cr0.wp=0 below). gfn: Either the guest page table containing the translations shadowed by this page, or the base page frame for linear translations. See role.direct. @@ -344,10 +348,16 @@ on fault type: (user write faults generate a #PF) -In the first case there is an additional complication if CR4.SMEP is -enabled: since we've turned the page into a kernel page, the kernel may now -execute it. We handle this by also setting spte.nx. If we get a user -fetch or read fault, we'll change spte.u=1 and spte.nx=gpte.nx back. +In the first case there are two additional complications: +- if CR4.SMEP is enabled: since we've turned the page into a kernel page, + the kernel may now execute it. We handle this by also setting spte.nx. + If we get a user fetch or read fault, we'll change spte.u=1 and + spte.nx=gpte.nx back. +- if CR4.SMAP is disabled: since the page has been changed to a kernel + page, it can not be reused when CR4.SMAP is enabled. We set + CR4.SMAP && !CR0.WP into shadow page's role to avoid this case. Note, + here we do not care the case that CR4.SMAP is enabled since KVM will + directly inject #PF to guest due to failed permission check. To prevent an spte that was converted into a kernel page with cr0.wp=0 from being written by the kernel after cr0.wp has changed to 1, we make diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 8b661d1946b5..bbb8f4e7738a 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -207,6 +207,7 @@ union kvm_mmu_page_role { unsigned nxe:1; unsigned cr0_wp:1; unsigned smep_andnot_wp:1; + unsigned smap_andnot_wp:1; }; }; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 209fe1477465..44a7d2515497 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3736,8 +3736,8 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, } } -void update_permission_bitmask(struct kvm_vcpu *vcpu, - struct kvm_mmu *mmu, bool ept) +static void update_permission_bitmask(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu, bool ept) { unsigned bit, byte, pfec; u8 map; @@ -3918,6 +3918,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu) { bool smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP); + bool smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP); struct kvm_mmu *context = &vcpu->arch.mmu; MMU_WARN_ON(VALID_PAGE(context->root_hpa)); @@ -3936,6 +3937,8 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu) context->base_role.cr0_wp = is_write_protection(vcpu); context->base_role.smep_andnot_wp = smep && !is_write_protection(vcpu); + context->base_role.smap_andnot_wp + = smap && !is_write_protection(vcpu); } EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu); @@ -4207,12 +4210,18 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, int bytes) { gfn_t gfn = gpa >> PAGE_SHIFT; - union kvm_mmu_page_role mask = { .word = 0 }; struct kvm_mmu_page *sp; LIST_HEAD(invalid_list); u64 entry, gentry, *spte; int npte; bool remote_flush, local_flush, zap_page; + union kvm_mmu_page_role mask = (union kvm_mmu_page_role) { + .cr0_wp = 1, + .cr4_pae = 1, + .nxe = 1, + .smep_andnot_wp = 1, + .smap_andnot_wp = 1, + }; /* * If we don't have indirect shadow pages, it means no page is @@ -4238,7 +4247,6 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, ++vcpu->kvm->stat.mmu_pte_write; kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE); - mask.cr0_wp = mask.cr4_pae = mask.nxe = mask.smep_andnot_wp = 1; for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) { if (detect_write_misaligned(sp, gpa, bytes) || detect_write_flooding(sp)) { diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 06eb2fc1bab8..0ada65ecddcf 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -71,8 +71,6 @@ enum { int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct); void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu); void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly); -void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - bool ept); static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cdccbe1749a5..cde5d614ff0a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -702,8 +702,9 @@ EXPORT_SYMBOL_GPL(kvm_set_xcr); int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { unsigned long old_cr4 = kvm_read_cr4(vcpu); - unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | - X86_CR4_PAE | X86_CR4_SMEP; + unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | + X86_CR4_SMEP | X86_CR4_SMAP; + if (cr4 & CR4_RESERVED_BITS) return 1; @@ -744,9 +745,6 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) kvm_mmu_reset_context(vcpu); - if ((cr4 ^ old_cr4) & X86_CR4_SMAP) - update_permission_bitmask(vcpu, vcpu->arch.walk_mmu, false); - if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE) kvm_update_cpuid(vcpu); -- cgit v1.2.3 From c35ebbeade127e7bca1f21ef5bf1a39deffba9de Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 13 May 2015 15:59:26 +0200 Subject: Revert "kvmclock: set scheduler clock stable" This reverts commit ff7bbb9c6ab6e6620429daeff39424bbde1a94b4. Sasha Levin is seeing odd jump in time values during boot of a KVM guest: [...] [ 0.000000] tsc: Detected 2260.998 MHz processor [3376355.247558] Calibrating delay loop (skipped) preset value.. [...] and bisected them to this commit. Reported-by: Sasha Levin Signed-off-by: Paolo Bonzini --- arch/x86/kernel/kvmclock.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 4e03921761c4..42caaef897c8 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -24,7 +24,6 @@ #include #include #include -#include #include #include @@ -266,8 +265,6 @@ void __init kvmclock_init(void) if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT); - - set_sched_clock_stable(); } int __init kvm_setup_vsyscall_timeinfo(void) -- cgit v1.2.3 From 0d5367900a319ab8971817b0ca15a8b9f7c47e6f Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Wed, 13 May 2015 14:42:20 +0800 Subject: KVM: MMU: introduce for_each_rmap_spte() It's used to walk all the sptes on the rmap to clean up the code Signed-off-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu.c | 53 ++++++++++++++++-------------------------------- arch/x86/kvm/mmu_audit.c | 4 +--- 2 files changed, 19 insertions(+), 38 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 44a7d2515497..7a1158533f89 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1142,6 +1142,11 @@ static u64 *rmap_get_next(struct rmap_iterator *iter) return NULL; } +#define for_each_rmap_spte(_rmap_, _iter_, _spte_) \ + for (_spte_ = rmap_get_first(*_rmap_, _iter_); \ + _spte_ && ({BUG_ON(!is_shadow_present_pte(*_spte_)); 1;}); \ + _spte_ = rmap_get_next(_iter_)) + static void drop_spte(struct kvm *kvm, u64 *sptep) { if (mmu_spte_clear_track_bits(sptep)) @@ -1205,12 +1210,8 @@ static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp, struct rmap_iterator iter; bool flush = false; - for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { - BUG_ON(!(*sptep & PT_PRESENT_MASK)); - + for_each_rmap_spte(rmapp, &iter, sptep) flush |= spte_write_protect(kvm, sptep, pt_protect); - sptep = rmap_get_next(&iter); - } return flush; } @@ -1232,12 +1233,8 @@ static bool __rmap_clear_dirty(struct kvm *kvm, unsigned long *rmapp) struct rmap_iterator iter; bool flush = false; - for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { - BUG_ON(!(*sptep & PT_PRESENT_MASK)); - + for_each_rmap_spte(rmapp, &iter, sptep) flush |= spte_clear_dirty(kvm, sptep); - sptep = rmap_get_next(&iter); - } return flush; } @@ -1259,12 +1256,8 @@ static bool __rmap_set_dirty(struct kvm *kvm, unsigned long *rmapp) struct rmap_iterator iter; bool flush = false; - for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { - BUG_ON(!(*sptep & PT_PRESENT_MASK)); - + for_each_rmap_spte(rmapp, &iter, sptep) flush |= spte_set_dirty(kvm, sptep); - sptep = rmap_get_next(&iter); - } return flush; } @@ -1394,8 +1387,8 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, WARN_ON(pte_huge(*ptep)); new_pfn = pte_pfn(*ptep); - for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { - BUG_ON(!is_shadow_present_pte(*sptep)); +restart: + for_each_rmap_spte(rmapp, &iter, sptep) { rmap_printk("kvm_set_pte_rmapp: spte %p %llx gfn %llx (%d)\n", sptep, *sptep, gfn, level); @@ -1403,7 +1396,7 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, if (pte_write(*ptep)) { drop_spte(kvm, sptep); - sptep = rmap_get_first(*rmapp, &iter); + goto restart; } else { new_spte = *sptep & ~PT64_BASE_ADDR_MASK; new_spte |= (u64)new_pfn << PAGE_SHIFT; @@ -1414,7 +1407,6 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, mmu_spte_clear_track_bits(sptep); mmu_spte_set(sptep, new_spte); - sptep = rmap_get_next(&iter); } } @@ -1518,16 +1510,13 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, BUG_ON(!shadow_accessed_mask); - for (sptep = rmap_get_first(*rmapp, &iter); sptep; - sptep = rmap_get_next(&iter)) { - BUG_ON(!is_shadow_present_pte(*sptep)); - + for_each_rmap_spte(rmapp, &iter, sptep) if (*sptep & shadow_accessed_mask) { young = 1; clear_bit((ffs(shadow_accessed_mask) - 1), (unsigned long *)sptep); } - } + trace_kvm_age_page(gfn, level, slot, young); return young; } @@ -1548,15 +1537,11 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp, if (!shadow_accessed_mask) goto out; - for (sptep = rmap_get_first(*rmapp, &iter); sptep; - sptep = rmap_get_next(&iter)) { - BUG_ON(!is_shadow_present_pte(*sptep)); - + for_each_rmap_spte(rmapp, &iter, sptep) if (*sptep & shadow_accessed_mask) { young = 1; break; } - } out: return young; } @@ -4482,9 +4467,8 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, pfn_t pfn; struct kvm_mmu_page *sp; - for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { - BUG_ON(!(*sptep & PT_PRESENT_MASK)); - +restart: + for_each_rmap_spte(rmapp, &iter, sptep) { sp = page_header(__pa(sptep)); pfn = spte_to_pfn(*sptep); @@ -4499,10 +4483,9 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, !kvm_is_reserved_pfn(pfn) && PageTransCompound(pfn_to_page(pfn))) { drop_spte(kvm, sptep); - sptep = rmap_get_first(*rmapp, &iter); need_tlb_flush = 1; - } else - sptep = rmap_get_next(&iter); + goto restart; + } } return need_tlb_flush; diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index 9ade5cfb5a4c..368d53497314 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -197,13 +197,11 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp) rmapp = gfn_to_rmap(kvm, sp->gfn, PT_PAGE_TABLE_LEVEL); - for (sptep = rmap_get_first(*rmapp, &iter); sptep; - sptep = rmap_get_next(&iter)) { + for_each_rmap_spte(rmapp, &iter, sptep) if (is_writable_pte(*sptep)) audit_printk(kvm, "shadow page has writable " "mappings: gfn %llx role %x\n", sp->gfn, sp->role.word); - } } static void audit_sp(struct kvm *kvm, struct kvm_mmu_page *sp) -- cgit v1.2.3 From 8a3d08f16fc63400f637dfa69aa5c7ea016ee18a Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Wed, 13 May 2015 14:42:21 +0800 Subject: KVM: MMU: introduce PT_MAX_HUGEPAGE_LEVEL Suggested-by: Paolo Bonzini Signed-off-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu.c | 24 +++++++++--------------- arch/x86/kvm/mmu.h | 1 + 2 files changed, 10 insertions(+), 15 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 7a1158533f89..b1f5f09e0c29 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -811,8 +811,7 @@ static void account_shadowed(struct kvm *kvm, gfn_t gfn) int i; slot = gfn_to_memslot(kvm, gfn); - for (i = PT_DIRECTORY_LEVEL; - i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { + for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { linfo = lpage_info_slot(gfn, slot, i); linfo->write_count += 1; } @@ -826,8 +825,7 @@ static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn) int i; slot = gfn_to_memslot(kvm, gfn); - for (i = PT_DIRECTORY_LEVEL; - i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { + for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { linfo = lpage_info_slot(gfn, slot, i); linfo->write_count -= 1; WARN_ON(linfo->write_count < 0); @@ -858,8 +856,7 @@ static int host_mapping_level(struct kvm *kvm, gfn_t gfn) page_size = kvm_host_page_size(kvm, gfn); - for (i = PT_PAGE_TABLE_LEVEL; - i < (PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES); ++i) { + for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { if (page_size >= KVM_HPAGE_SIZE(i)) ret = i; else @@ -1344,8 +1341,7 @@ static bool rmap_write_protect(struct kvm *kvm, u64 gfn) slot = gfn_to_memslot(kvm, gfn); - for (i = PT_PAGE_TABLE_LEVEL; - i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { + for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { rmapp = __gfn_to_rmap(gfn, i, slot); write_protected |= __rmap_write_protect(kvm, rmapp, true); } @@ -1451,7 +1447,7 @@ static int kvm_handle_hva_range(struct kvm *kvm, gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot); for (j = PT_PAGE_TABLE_LEVEL; - j < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++j) { + j <= PT_MAX_HUGEPAGE_LEVEL; ++j) { unsigned long idx, idx_end; unsigned long *rmapp; gfn_t gfn = gfn_start; @@ -4416,8 +4412,7 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, spin_lock(&kvm->mmu_lock); - for (i = PT_PAGE_TABLE_LEVEL; - i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { + for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { unsigned long *rmapp; unsigned long last_index, index; @@ -4573,8 +4568,8 @@ void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm, spin_lock(&kvm->mmu_lock); - for (i = PT_PAGE_TABLE_LEVEL + 1; /* skip rmap for 4K page */ - i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { + /* skip rmap for 4K page */ + for (i = PT_PAGE_TABLE_LEVEL + 1; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { unsigned long *rmapp; unsigned long last_index, index; @@ -4611,8 +4606,7 @@ void kvm_mmu_slot_set_dirty(struct kvm *kvm, spin_lock(&kvm->mmu_lock); - for (i = PT_PAGE_TABLE_LEVEL; - i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { + for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { unsigned long *rmapp; unsigned long last_index, index; diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 0ada65ecddcf..72bb33f70c16 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -43,6 +43,7 @@ #define PT_PDPE_LEVEL 3 #define PT_DIRECTORY_LEVEL 2 #define PT_PAGE_TABLE_LEVEL 1 +#define PT_MAX_HUGEPAGE_LEVEL (PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES - 1) static inline u64 rsvd_bits(int s, int e) { -- cgit v1.2.3 From 6ce1f4e295dd06b19443341b1684d361739ec117 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Wed, 13 May 2015 14:42:22 +0800 Subject: KVM: MMU: introduce for_each_slot_rmap_range It's used to abstract the code from kvm_handle_hva_range and it will be used by later patch Signed-off-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu.c | 97 +++++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 75 insertions(+), 22 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index b1f5f09e0c29..316c43243995 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1412,6 +1412,74 @@ restart: return 0; } +struct slot_rmap_walk_iterator { + /* input fields. */ + struct kvm_memory_slot *slot; + gfn_t start_gfn; + gfn_t end_gfn; + int start_level; + int end_level; + + /* output fields. */ + gfn_t gfn; + unsigned long *rmap; + int level; + + /* private field. */ + unsigned long *end_rmap; +}; + +static void +rmap_walk_init_level(struct slot_rmap_walk_iterator *iterator, int level) +{ + iterator->level = level; + iterator->gfn = iterator->start_gfn; + iterator->rmap = __gfn_to_rmap(iterator->gfn, level, iterator->slot); + iterator->end_rmap = __gfn_to_rmap(iterator->end_gfn, level, + iterator->slot); +} + +static void +slot_rmap_walk_init(struct slot_rmap_walk_iterator *iterator, + struct kvm_memory_slot *slot, int start_level, + int end_level, gfn_t start_gfn, gfn_t end_gfn) +{ + iterator->slot = slot; + iterator->start_level = start_level; + iterator->end_level = end_level; + iterator->start_gfn = start_gfn; + iterator->end_gfn = end_gfn; + + rmap_walk_init_level(iterator, iterator->start_level); +} + +static bool slot_rmap_walk_okay(struct slot_rmap_walk_iterator *iterator) +{ + return !!iterator->rmap; +} + +static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator) +{ + if (++iterator->rmap <= iterator->end_rmap) { + iterator->gfn += (1UL << KVM_HPAGE_GFN_SHIFT(iterator->level)); + return; + } + + if (++iterator->level > iterator->end_level) { + iterator->rmap = NULL; + return; + } + + rmap_walk_init_level(iterator, iterator->level); +} + +#define for_each_slot_rmap_range(_slot_, _start_level_, _end_level_, \ + _start_gfn, _end_gfn, _iter_) \ + for (slot_rmap_walk_init(_iter_, _slot_, _start_level_, \ + _end_level_, _start_gfn, _end_gfn); \ + slot_rmap_walk_okay(_iter_); \ + slot_rmap_walk_next(_iter_)) + static int kvm_handle_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, @@ -1423,10 +1491,10 @@ static int kvm_handle_hva_range(struct kvm *kvm, int level, unsigned long data)) { - int j; - int ret = 0; struct kvm_memslots *slots; struct kvm_memory_slot *memslot; + struct slot_rmap_walk_iterator iterator; + int ret = 0; slots = kvm_memslots(kvm); @@ -1446,26 +1514,11 @@ static int kvm_handle_hva_range(struct kvm *kvm, gfn_start = hva_to_gfn_memslot(hva_start, memslot); gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot); - for (j = PT_PAGE_TABLE_LEVEL; - j <= PT_MAX_HUGEPAGE_LEVEL; ++j) { - unsigned long idx, idx_end; - unsigned long *rmapp; - gfn_t gfn = gfn_start; - - /* - * {idx(page_j) | page_j intersects with - * [hva_start, hva_end)} = {idx, idx+1, ..., idx_end}. - */ - idx = gfn_to_index(gfn_start, memslot->base_gfn, j); - idx_end = gfn_to_index(gfn_end - 1, memslot->base_gfn, j); - - rmapp = __gfn_to_rmap(gfn_start, j, memslot); - - for (; idx <= idx_end; - ++idx, gfn += (1UL << KVM_HPAGE_GFN_SHIFT(j))) - ret |= handler(kvm, rmapp++, memslot, - gfn, j, data); - } + for_each_slot_rmap_range(memslot, PT_PAGE_TABLE_LEVEL, + PT_MAX_HUGEPAGE_LEVEL, gfn_start, gfn_end - 1, + &iterator) + ret |= handler(kvm, iterator.rmap, memslot, + iterator.gfn, iterator.level, data); } return ret; -- cgit v1.2.3 From 1bad2b2a3b158fbb19fef6cd563301b94b5c28b2 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Wed, 13 May 2015 14:42:23 +0800 Subject: KVM: MMU: introduce slot_handle_level_range() and its helpers There are several places walking all rmaps for the memslot so that introduce common functions to cleanup the code Signed-off-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 69 insertions(+) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 316c43243995..d1d072d70b7b 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4454,6 +4454,75 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu) init_kvm_mmu(vcpu); } +/* The return value indicates if tlb flush on all vcpus is needed. */ +typedef bool (*slot_level_handler) (struct kvm *kvm, unsigned long *rmap); + +/* The caller should hold mmu-lock before calling this function. */ +static bool +slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, int start_level, int end_level, + gfn_t start_gfn, gfn_t end_gfn, bool lock_flush_tlb) +{ + struct slot_rmap_walk_iterator iterator; + bool flush = false; + + for_each_slot_rmap_range(memslot, start_level, end_level, start_gfn, + end_gfn, &iterator) { + if (iterator.rmap) + flush |= fn(kvm, iterator.rmap); + + if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { + if (flush && lock_flush_tlb) { + kvm_flush_remote_tlbs(kvm); + flush = false; + } + cond_resched_lock(&kvm->mmu_lock); + } + } + + if (flush && lock_flush_tlb) { + kvm_flush_remote_tlbs(kvm); + flush = false; + } + + return flush; +} + +static bool +slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, int start_level, int end_level, + bool lock_flush_tlb) +{ + return slot_handle_level_range(kvm, memslot, fn, start_level, + end_level, memslot->base_gfn, + memslot->base_gfn + memslot->npages - 1, + lock_flush_tlb); +} + +static bool +slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, bool lock_flush_tlb) +{ + return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL, + PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); +} + +static bool +slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, bool lock_flush_tlb) +{ + return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL + 1, + PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); +} + +static bool +slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, bool lock_flush_tlb) +{ + return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL, + PT_PAGE_TABLE_LEVEL, lock_flush_tlb); +} + void kvm_mmu_slot_remove_write_access(struct kvm *kvm, struct kvm_memory_slot *memslot) { -- cgit v1.2.3 From d77aa73c7072c598a6d1f3a781c0e4fae067df76 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Wed, 13 May 2015 14:42:24 +0800 Subject: KVM: MMU: use slot_handle_level and its helper to clean up the code slot_handle_level and its helper functions are ready now, use them to clean up the code Signed-off-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu.c | 128 +++++++---------------------------------------------- 1 file changed, 16 insertions(+), 112 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index d1d072d70b7b..ed239c696056 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4523,34 +4523,19 @@ slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, PT_PAGE_TABLE_LEVEL, lock_flush_tlb); } +static bool slot_rmap_write_protect(struct kvm *kvm, unsigned long *rmapp) +{ + return __rmap_write_protect(kvm, rmapp, false); +} + void kvm_mmu_slot_remove_write_access(struct kvm *kvm, struct kvm_memory_slot *memslot) { - gfn_t last_gfn; - int i; - bool flush = false; - - last_gfn = memslot->base_gfn + memslot->npages - 1; + bool flush; spin_lock(&kvm->mmu_lock); - - for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { - unsigned long *rmapp; - unsigned long last_index, index; - - rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL]; - last_index = gfn_to_index(last_gfn, memslot->base_gfn, i); - - for (index = 0; index <= last_index; ++index, ++rmapp) { - if (*rmapp) - flush |= __rmap_write_protect(kvm, rmapp, - false); - - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) - cond_resched_lock(&kvm->mmu_lock); - } - } - + flush = slot_handle_all_level(kvm, memslot, slot_rmap_write_protect, + false); spin_unlock(&kvm->mmu_lock); /* @@ -4611,59 +4596,18 @@ restart: void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, struct kvm_memory_slot *memslot) { - bool flush = false; - unsigned long *rmapp; - unsigned long last_index, index; - spin_lock(&kvm->mmu_lock); - - rmapp = memslot->arch.rmap[0]; - last_index = gfn_to_index(memslot->base_gfn + memslot->npages - 1, - memslot->base_gfn, PT_PAGE_TABLE_LEVEL); - - for (index = 0; index <= last_index; ++index, ++rmapp) { - if (*rmapp) - flush |= kvm_mmu_zap_collapsible_spte(kvm, rmapp); - - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { - if (flush) { - kvm_flush_remote_tlbs(kvm); - flush = false; - } - cond_resched_lock(&kvm->mmu_lock); - } - } - - if (flush) - kvm_flush_remote_tlbs(kvm); - + slot_handle_leaf(kvm, memslot, kvm_mmu_zap_collapsible_spte, true); spin_unlock(&kvm->mmu_lock); } void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot) { - gfn_t last_gfn; - unsigned long *rmapp; - unsigned long last_index, index; - bool flush = false; - - last_gfn = memslot->base_gfn + memslot->npages - 1; + bool flush; spin_lock(&kvm->mmu_lock); - - rmapp = memslot->arch.rmap[PT_PAGE_TABLE_LEVEL - 1]; - last_index = gfn_to_index(last_gfn, memslot->base_gfn, - PT_PAGE_TABLE_LEVEL); - - for (index = 0; index <= last_index; ++index, ++rmapp) { - if (*rmapp) - flush |= __rmap_clear_dirty(kvm, rmapp); - - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) - cond_resched_lock(&kvm->mmu_lock); - } - + flush = slot_handle_leaf(kvm, memslot, __rmap_clear_dirty, false); spin_unlock(&kvm->mmu_lock); lockdep_assert_held(&kvm->slots_lock); @@ -4682,31 +4626,11 @@ EXPORT_SYMBOL_GPL(kvm_mmu_slot_leaf_clear_dirty); void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm, struct kvm_memory_slot *memslot) { - gfn_t last_gfn; - int i; - bool flush = false; - - last_gfn = memslot->base_gfn + memslot->npages - 1; + bool flush; spin_lock(&kvm->mmu_lock); - - /* skip rmap for 4K page */ - for (i = PT_PAGE_TABLE_LEVEL + 1; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { - unsigned long *rmapp; - unsigned long last_index, index; - - rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL]; - last_index = gfn_to_index(last_gfn, memslot->base_gfn, i); - - for (index = 0; index <= last_index; ++index, ++rmapp) { - if (*rmapp) - flush |= __rmap_write_protect(kvm, rmapp, - false); - - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) - cond_resched_lock(&kvm->mmu_lock); - } - } + flush = slot_handle_large_level(kvm, memslot, slot_rmap_write_protect, + false); spin_unlock(&kvm->mmu_lock); /* see kvm_mmu_slot_remove_write_access */ @@ -4720,30 +4644,10 @@ EXPORT_SYMBOL_GPL(kvm_mmu_slot_largepage_remove_write_access); void kvm_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot) { - gfn_t last_gfn; - int i; - bool flush = false; - - last_gfn = memslot->base_gfn + memslot->npages - 1; + bool flush; spin_lock(&kvm->mmu_lock); - - for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { - unsigned long *rmapp; - unsigned long last_index, index; - - rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL]; - last_index = gfn_to_index(last_gfn, memslot->base_gfn, i); - - for (index = 0; index <= last_index; ++index, ++rmapp) { - if (*rmapp) - flush |= __rmap_set_dirty(kvm, rmapp); - - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) - cond_resched_lock(&kvm->mmu_lock); - } - } - + flush = slot_handle_all_level(kvm, memslot, __rmap_set_dirty, false); spin_unlock(&kvm->mmu_lock); lockdep_assert_held(&kvm->slots_lock); -- cgit v1.2.3 From 6a49f85c7ac83c1918d138d40492a5cef40b5ff8 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Wed, 13 May 2015 14:42:25 +0800 Subject: KVM: MMU: introduce kvm_zap_rmapp Split kvm_unmap_rmapp and introduce kvm_zap_rmapp which will be used in the later patch Signed-off-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index ed239c696056..ddf25f39735a 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1349,24 +1349,28 @@ static bool rmap_write_protect(struct kvm *kvm, u64 gfn) return write_protected; } -static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, - struct kvm_memory_slot *slot, gfn_t gfn, int level, - unsigned long data) +static bool kvm_zap_rmapp(struct kvm *kvm, unsigned long *rmapp) { u64 *sptep; struct rmap_iterator iter; - int need_tlb_flush = 0; + bool flush = false; while ((sptep = rmap_get_first(*rmapp, &iter))) { BUG_ON(!(*sptep & PT_PRESENT_MASK)); - rmap_printk("kvm_rmap_unmap_hva: spte %p %llx gfn %llx (%d)\n", - sptep, *sptep, gfn, level); + rmap_printk("%s: spte %p %llx.\n", __func__, sptep, *sptep); drop_spte(kvm, sptep); - need_tlb_flush = 1; + flush = true; } - return need_tlb_flush; + return flush; +} + +static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, + struct kvm_memory_slot *slot, gfn_t gfn, int level, + unsigned long data) +{ + return kvm_zap_rmapp(kvm, rmapp); } static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, -- cgit v1.2.3 From d69afbc6b1b5d0579f13d1a6339d952c4f60a9f4 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Wed, 13 May 2015 14:42:19 +0800 Subject: KVM: MMU: fix decoding cache type from MTRR There are some bugs in current get_mtrr_type(); 1: bit 1 of mtrr_state->enabled is corresponding bit 11 of IA32_MTRR_DEF_TYPE MSR which completely control MTRR's enablement that means other bits are ignored if it is cleared 2: the fixed MTRR ranges are controlled by bit 0 of mtrr_state->enabled (bit 10 of IA32_MTRR_DEF_TYPE) 3: if MTRR is disabled, UC is applied to all of physical memory rather than mtrr_state->def_type Signed-off-by: Xiao Guangrong Reviewed-by: Wanpeng Li Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index ddf25f39735a..e718c76609f9 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2431,19 +2431,20 @@ EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page); static int get_mtrr_type(struct mtrr_state_type *mtrr_state, u64 start, u64 end) { - int i; u64 base, mask; u8 prev_match, curr_match; - int num_var_ranges = KVM_NR_VAR_MTRR; + int i, num_var_ranges = KVM_NR_VAR_MTRR; - if (!mtrr_state->enabled) - return 0xFF; + /* MTRR is completely disabled, use UC for all of physical memory. */ + if (!(mtrr_state->enabled & 0x2)) + return MTRR_TYPE_UNCACHABLE; /* Make end inclusive end, instead of exclusive */ end--; /* Look in fixed ranges. Just return the type as per start */ - if (mtrr_state->have_fixed && (start < 0x100000)) { + if (mtrr_state->have_fixed && (mtrr_state->enabled & 0x1) && + (start < 0x100000)) { int idx; if (start < 0x80000) { @@ -2466,9 +2467,6 @@ static int get_mtrr_type(struct mtrr_state_type *mtrr_state, * Look of multiple ranges matching this address and pick type * as per MTRR precedence */ - if (!(mtrr_state->enabled & 2)) - return mtrr_state->def_type; - prev_match = 0xFF; for (i = 0; i < num_var_ranges; ++i) { unsigned short start_state, end_state; -- cgit v1.2.3 From efdfe536d8c643391e19d5726b072f82964bfbdb Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Wed, 13 May 2015 14:42:27 +0800 Subject: KVM: MMU: fix MTRR update Currently, whenever guest MTRR registers are changed kvm_mmu_reset_context is called to switch to the new root shadow page table, however, it's useless since: 1) the cache type is not cached into shadow page's attribute so that the original root shadow page will be reused 2) the cache type is set on the last spte, that means we should sync the last sptes when MTRR is changed This patch fixs this issue by drop all the spte in the gfn range which is being updated by MTRR Signed-off-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu.c | 24 ++++++++++++++++++++++ arch/x86/kvm/mmu.h | 1 + arch/x86/kvm/x86.c | 59 +++++++++++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 83 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index e718c76609f9..5bebec1191f1 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4525,6 +4525,30 @@ slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, PT_PAGE_TABLE_LEVEL, lock_flush_tlb); } +void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + + slots = kvm_memslots(kvm); + + spin_lock(&kvm->mmu_lock); + kvm_for_each_memslot(memslot, slots) { + gfn_t start, end; + + start = max(gfn_start, memslot->base_gfn); + end = min(gfn_end, memslot->base_gfn + memslot->npages); + if (start >= end) + continue; + + slot_handle_level_range(kvm, memslot, kvm_zap_rmapp, + PT_PAGE_TABLE_LEVEL, PT_MAX_HUGEPAGE_LEVEL, + start, end - 1, true); + } + + spin_unlock(&kvm->mmu_lock); +} + static bool slot_rmap_write_protect(struct kvm *kvm, unsigned long *rmapp) { return __rmap_write_protect(kvm, rmapp, false); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 72bb33f70c16..398d21c0f6dd 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -171,4 +171,5 @@ static inline bool permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, } void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm); +void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end); #endif diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cde5d614ff0a..bbe184f07bf9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1852,6 +1852,63 @@ bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data) } EXPORT_SYMBOL_GPL(kvm_mtrr_valid); +static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr) +{ + struct mtrr_state_type *mtrr_state = &vcpu->arch.mtrr_state; + unsigned char mtrr_enabled = mtrr_state->enabled; + gfn_t start, end, mask; + int index; + bool is_fixed = true; + + if (msr == MSR_IA32_CR_PAT || !tdp_enabled || + !kvm_arch_has_noncoherent_dma(vcpu->kvm)) + return; + + if (!(mtrr_enabled & 0x2) && msr != MSR_MTRRdefType) + return; + + switch (msr) { + case MSR_MTRRfix64K_00000: + start = 0x0; + end = 0x80000; + break; + case MSR_MTRRfix16K_80000: + start = 0x80000; + end = 0xa0000; + break; + case MSR_MTRRfix16K_A0000: + start = 0xa0000; + end = 0xc0000; + break; + case MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000: + index = msr - MSR_MTRRfix4K_C0000; + start = 0xc0000 + index * (32 << 10); + end = start + (32 << 10); + break; + case MSR_MTRRdefType: + is_fixed = false; + start = 0x0; + end = ~0ULL; + break; + default: + /* variable range MTRRs. */ + is_fixed = false; + index = (msr - 0x200) / 2; + start = (((u64)mtrr_state->var_ranges[index].base_hi) << 32) + + (mtrr_state->var_ranges[index].base_lo & PAGE_MASK); + mask = (((u64)mtrr_state->var_ranges[index].mask_hi) << 32) + + (mtrr_state->var_ranges[index].mask_lo & PAGE_MASK); + mask |= ~0ULL << cpuid_maxphyaddr(vcpu); + + end = ((start & mask) | ~mask) + 1; + } + + if (is_fixed && !(mtrr_enabled & 0x1)) + return; + + kvm_zap_gfn_range(vcpu->kvm, gpa_to_gfn(start), gpa_to_gfn(end)); +} + static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data) { u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges; @@ -1885,7 +1942,7 @@ static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data) *pt = data; } - kvm_mmu_reset_context(vcpu); + update_mtrr(vcpu, msr); return 0; } -- cgit v1.2.3 From d81135a57aa66e5bec55cdfe4dda79633f9082dd Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Wed, 13 May 2015 14:42:28 +0800 Subject: KVM: x86: do not reset mmu if CR0.CD and CR0.NW are changed CR0.CD and CR0.NW are not used by shadow page table so that need not adjust mmu if these two bit are changed Signed-off-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index bbe184f07bf9..457b908244f2 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -572,8 +572,7 @@ out: int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { unsigned long old_cr0 = kvm_read_cr0(vcpu); - unsigned long update_bits = X86_CR0_PG | X86_CR0_WP | - X86_CR0_CD | X86_CR0_NW; + unsigned long update_bits = X86_CR0_PG | X86_CR0_WP; cr0 |= X86_CR0_ET; -- cgit v1.2.3 From 69a1220060c1523fd0515216eaa29e22f133b894 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 18 May 2015 08:35:43 +0200 Subject: KVM: mips: use id_to_memslot correctly The argument to KVM_GET_DIRTY_LOG is a memslot id; it may not match the position in the memslots array, which is sorted by gfn. Cc: stable@vger.kernel.org Reviewed-by: James Hogan Signed-off-by: Paolo Bonzini --- arch/mips/kvm/mips.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 71f345b499c8..a8e660a44474 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -982,7 +982,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) /* If nothing is dirty, don't bother messing with page tables. */ if (is_dirty) { - memslot = &kvm->memslots->memslots[log->slot]; + memslot = id_to_memslot(kvm->memslots, log->slot); ga = memslot->base_gfn << PAGE_SHIFT; ga_end = ga + (memslot->npages << PAGE_SHIFT); -- cgit v1.2.3 From 3520469d65f26a1cd2f610f5d5de976f78db74fe Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 2 Apr 2015 11:20:48 +0200 Subject: KVM: export __gfn_to_pfn_memslot, drop gfn_to_pfn_async gfn_to_pfn_async is used in just one place, and because of x86-specific treatment that place will need to look at the memory slot. Hence inline it into try_async_pf and export __gfn_to_pfn_memslot. The patch also switches the subsequent call to gfn_to_pfn_prot to use __gfn_to_pfn_memslot. This is a small optimization. Finally, remove the now-unused async argument of __gfn_to_pfn. Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu.c | 9 +++++---- include/linux/kvm_host.h | 4 ++-- virt/kvm/kvm_main.c | 26 ++++++++------------------ 3 files changed, 15 insertions(+), 24 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 5bebec1191f1..49c34e632b91 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3511,10 +3511,12 @@ static bool can_do_async_pf(struct kvm_vcpu *vcpu) static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, gva_t gva, pfn_t *pfn, bool write, bool *writable) { + struct kvm_memory_slot *slot; bool async; - *pfn = gfn_to_pfn_async(vcpu->kvm, gfn, &async, write, writable); - + slot = gfn_to_memslot(vcpu->kvm, gfn); + async = false; + *pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, write, writable); if (!async) return false; /* *pfn has correct page already */ @@ -3528,8 +3530,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, return true; } - *pfn = gfn_to_pfn_prot(vcpu->kvm, gfn, write, writable); - + *pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL, write, writable); return false; } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index b7a08cd6f4a8..87fd74a04005 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -539,13 +539,13 @@ void kvm_release_page_dirty(struct page *page); void kvm_set_page_accessed(struct page *page); pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn); -pfn_t gfn_to_pfn_async(struct kvm *kvm, gfn_t gfn, bool *async, - bool write_fault, bool *writable); pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, bool *writable); pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn); pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn); +pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, + bool *async, bool write_fault, bool *writable); void kvm_release_pfn_clean(pfn_t pfn); void kvm_set_pfn_dirty(pfn_t pfn); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index f202c4035134..bd3c08a7c6c2 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1355,9 +1355,8 @@ exit: return pfn; } -static pfn_t -__gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, - bool *async, bool write_fault, bool *writable) +pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, + bool *async, bool write_fault, bool *writable) { unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault); @@ -1376,44 +1375,35 @@ __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, return hva_to_pfn(addr, atomic, async, write_fault, writable); } +EXPORT_SYMBOL_GPL(__gfn_to_pfn_memslot); -static pfn_t __gfn_to_pfn(struct kvm *kvm, gfn_t gfn, bool atomic, bool *async, +static pfn_t __gfn_to_pfn(struct kvm *kvm, gfn_t gfn, bool atomic, bool write_fault, bool *writable) { struct kvm_memory_slot *slot; - if (async) - *async = false; - slot = gfn_to_memslot(kvm, gfn); - return __gfn_to_pfn_memslot(slot, gfn, atomic, async, write_fault, + return __gfn_to_pfn_memslot(slot, gfn, atomic, NULL, write_fault, writable); } pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn) { - return __gfn_to_pfn(kvm, gfn, true, NULL, true, NULL); + return __gfn_to_pfn(kvm, gfn, true, true, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_atomic); -pfn_t gfn_to_pfn_async(struct kvm *kvm, gfn_t gfn, bool *async, - bool write_fault, bool *writable) -{ - return __gfn_to_pfn(kvm, gfn, false, async, write_fault, writable); -} -EXPORT_SYMBOL_GPL(gfn_to_pfn_async); - pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) { - return __gfn_to_pfn(kvm, gfn, false, NULL, true, NULL); + return __gfn_to_pfn(kvm, gfn, false, true, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn); pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, bool *writable) { - return __gfn_to_pfn(kvm, gfn, false, NULL, write_fault, writable); + return __gfn_to_pfn(kvm, gfn, false, write_fault, writable); } EXPORT_SYMBOL_GPL(gfn_to_pfn_prot); -- cgit v1.2.3 From ed3cf15271fa150320b46f03d369777b71786298 Mon Sep 17 00:00:00 2001 From: Nicholas Krause Date: Wed, 20 May 2015 00:24:10 -0400 Subject: kvm: x86: Make functions that have no external callers static This makes the functions kvm_guest_cpu_init and kvm_init_debugfs static now due to having no external callers outside their declarations in the file, kvm.c. Signed-off-by: Nicholas Krause Signed-off-by: Paolo Bonzini --- arch/x86/kernel/kvm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 9435620062df..cc34cece853e 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -331,7 +331,7 @@ static void kvm_guest_apic_eoi_write(u32 reg, u32 val) apic_write(APIC_EOI, APIC_EOI_ACK); } -void kvm_guest_cpu_init(void) +static void kvm_guest_cpu_init(void) { if (!kvm_para_available()) return; @@ -655,7 +655,7 @@ static inline void spin_time_accum_blocked(u64 start) static struct dentry *d_spin_debug; static struct dentry *d_kvm_debug; -struct dentry *kvm_init_debugfs(void) +static struct dentry *kvm_init_debugfs(void) { d_kvm_debug = debugfs_create_dir("kvm-guest", NULL); if (!d_kvm_debug) -- cgit v1.2.3 From a47d2b07ea755b1761a93df720d725f464876e72 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Sun, 17 May 2015 11:41:37 +0200 Subject: KVM: introduce kvm_alloc/free_memslots kvm_alloc_memslots is extracted out of previously scattered code that was in kvm_init_memslots_id and kvm_create_vm. kvm_free_memslot and kvm_free_memslots are new names of kvm_free_physmem and kvm_free_physmem_slot, but they also take an explicit pointer to struct kvm_memslots. This will simplify the transition to multiple address spaces, each represented by one pointer to struct kvm_memslots. Reviewed-by: Takuya Yoshikawa Reviewed-by: Radim Krcmar Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 104 +++++++++++++++++++++++++++------------------------- 1 file changed, 55 insertions(+), 49 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index bd3c08a7c6c2..e299763ef744 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -440,13 +440,60 @@ static int kvm_init_mmu_notifier(struct kvm *kvm) #endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */ -static void kvm_init_memslots_id(struct kvm *kvm) +static struct kvm_memslots *kvm_alloc_memslots(void) { int i; - struct kvm_memslots *slots = kvm->memslots; + struct kvm_memslots *slots; + slots = kvm_kvzalloc(sizeof(struct kvm_memslots)); + if (!slots) + return NULL; + + /* + * Init kvm generation close to the maximum to easily test the + * code of handling generation number wrap-around. + */ + slots->generation = -150; for (i = 0; i < KVM_MEM_SLOTS_NUM; i++) slots->id_to_index[i] = slots->memslots[i].id = i; + + return slots; +} + +static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) +{ + if (!memslot->dirty_bitmap) + return; + + kvfree(memslot->dirty_bitmap); + memslot->dirty_bitmap = NULL; +} + +/* + * Free any memory in @free but not in @dont. + */ +static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, + struct kvm_memory_slot *dont) +{ + if (!dont || free->dirty_bitmap != dont->dirty_bitmap) + kvm_destroy_dirty_bitmap(free); + + kvm_arch_free_memslot(kvm, free, dont); + + free->npages = 0; +} + +static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots) +{ + struct kvm_memory_slot *memslot; + + if (!slots) + return; + + kvm_for_each_memslot(memslot, slots) + kvm_free_memslot(kvm, memslot, NULL); + + kvfree(slots); } static struct kvm *kvm_create_vm(unsigned long type) @@ -472,17 +519,10 @@ static struct kvm *kvm_create_vm(unsigned long type) BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); r = -ENOMEM; - kvm->memslots = kvm_kvzalloc(sizeof(struct kvm_memslots)); + kvm->memslots = kvm_alloc_memslots(); if (!kvm->memslots) goto out_err_no_srcu; - /* - * Init kvm generation close to the maximum to easily test the - * code of handling generation number wrap-around. - */ - kvm->memslots->generation = -150; - - kvm_init_memslots_id(kvm); if (init_srcu_struct(&kvm->srcu)) goto out_err_no_srcu; if (init_srcu_struct(&kvm->irq_srcu)) @@ -523,7 +563,7 @@ out_err_no_srcu: out_err_no_disable: for (i = 0; i < KVM_NR_BUSES; i++) kfree(kvm->buses[i]); - kvfree(kvm->memslots); + kvm_free_memslots(kvm, kvm->memslots); kvm_arch_free_vm(kvm); return ERR_PTR(r); } @@ -540,40 +580,6 @@ void *kvm_kvzalloc(unsigned long size) return kzalloc(size, GFP_KERNEL); } -static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) -{ - if (!memslot->dirty_bitmap) - return; - - kvfree(memslot->dirty_bitmap); - memslot->dirty_bitmap = NULL; -} - -/* - * Free any memory in @free but not in @dont. - */ -static void kvm_free_physmem_slot(struct kvm *kvm, struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) -{ - if (!dont || free->dirty_bitmap != dont->dirty_bitmap) - kvm_destroy_dirty_bitmap(free); - - kvm_arch_free_memslot(kvm, free, dont); - - free->npages = 0; -} - -static void kvm_free_physmem(struct kvm *kvm) -{ - struct kvm_memslots *slots = kvm->memslots; - struct kvm_memory_slot *memslot; - - kvm_for_each_memslot(memslot, slots) - kvm_free_physmem_slot(kvm, memslot, NULL); - - kvfree(kvm->memslots); -} - static void kvm_destroy_devices(struct kvm *kvm) { struct list_head *node, *tmp; @@ -607,7 +613,7 @@ static void kvm_destroy_vm(struct kvm *kvm) #endif kvm_arch_destroy_vm(kvm); kvm_destroy_devices(kvm); - kvm_free_physmem(kvm); + kvm_free_memslots(kvm, kvm->memslots); cleanup_srcu_struct(&kvm->irq_srcu); cleanup_srcu_struct(&kvm->srcu); kvm_arch_free_vm(kvm); @@ -898,7 +904,7 @@ int __kvm_set_memory_region(struct kvm *kvm, if (r) goto out_slots; - /* actual memory is freed via old in kvm_free_physmem_slot below */ + /* actual memory is freed via old in kvm_free_memslot below */ if (change == KVM_MR_DELETE) { new.dirty_bitmap = NULL; memset(&new.arch, 0, sizeof(new.arch)); @@ -909,7 +915,7 @@ int __kvm_set_memory_region(struct kvm *kvm, kvm_arch_commit_memory_region(kvm, mem, &old, change); - kvm_free_physmem_slot(kvm, &old, &new); + kvm_free_memslot(kvm, &old, &new); kvfree(old_memslots); /* @@ -931,7 +937,7 @@ int __kvm_set_memory_region(struct kvm *kvm, out_slots: kvfree(slots); out_free: - kvm_free_physmem_slot(kvm, &new, &old); + kvm_free_memslot(kvm, &new, &old); out: return r; } -- cgit v1.2.3 From 9f6b8029787bb37170d4535e9fc09158f634282c Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Sun, 17 May 2015 16:20:07 +0200 Subject: KVM: use kvm_memslots whenever possible kvm_memslots provides lockdep checking. Use it consistently instead of explicit dereferencing of kvm->memslots. Reviewed-by: Radim Krcmar Signed-off-by: Paolo Bonzini --- arch/arm/kvm/mmu.c | 3 ++- arch/mips/kvm/mips.c | 4 +++- arch/powerpc/kvm/book3s_64_mmu_hv.c | 2 +- arch/powerpc/kvm/book3s_hv.c | 8 ++++++-- arch/powerpc/kvm/book3s_pr.c | 4 +++- arch/s390/kvm/kvm-s390.c | 4 +++- arch/x86/kvm/x86.c | 4 +++- virt/kvm/kvm_main.c | 16 ++++++++++------ 8 files changed, 31 insertions(+), 14 deletions(-) diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 1d5accbd3dcf..6f0f8f3ac7df 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -1155,7 +1155,8 @@ static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end) */ void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot) { - struct kvm_memory_slot *memslot = id_to_memslot(kvm->memslots, slot); + struct kvm_memslots *slots = kvm_memslots(kvm); + struct kvm_memory_slot *memslot = id_to_memslot(slots, slot); phys_addr_t start = memslot->base_gfn << PAGE_SHIFT; phys_addr_t end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT; diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index a8e660a44474..bc5ddd973b44 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -968,6 +968,7 @@ out: /* Get (and clear) the dirty memory log for a memory slot. */ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) { + struct kvm_memslots *slots; struct kvm_memory_slot *memslot; unsigned long ga, ga_end; int is_dirty = 0; @@ -982,7 +983,8 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) /* If nothing is dirty, don't bother messing with page tables. */ if (is_dirty) { - memslot = id_to_memslot(kvm->memslots, log->slot); + slots = kvm_memslots(kvm); + memslot = id_to_memslot(slots, log->slot); ga = memslot->base_gfn << PAGE_SHIFT; ga_end = ga + (memslot->npages << PAGE_SHIFT); diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 1a4acf8bf4f4..dab68b7af3f2 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -650,7 +650,7 @@ static void kvmppc_rmap_reset(struct kvm *kvm) int srcu_idx; srcu_idx = srcu_read_lock(&kvm->srcu); - slots = kvm->memslots; + slots = kvm_memslots(kvm); kvm_for_each_memslot(memslot, slots) { /* * This assumes it is acceptable to lose reference and diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index df81caab7383..6aff5a990492 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2321,6 +2321,7 @@ static int kvm_vm_ioctl_get_smmu_info_hv(struct kvm *kvm, static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm, struct kvm_dirty_log *log) { + struct kvm_memslots *slots; struct kvm_memory_slot *memslot; int r; unsigned long n; @@ -2331,7 +2332,8 @@ static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm, if (log->slot >= KVM_USER_MEM_SLOTS) goto out; - memslot = id_to_memslot(kvm->memslots, log->slot); + slots = kvm_memslots(kvm); + memslot = id_to_memslot(slots, log->slot); r = -ENOENT; if (!memslot->dirty_bitmap) goto out; @@ -2384,6 +2386,7 @@ static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm, const struct kvm_memory_slot *old) { unsigned long npages = mem->memory_size >> PAGE_SHIFT; + struct kvm_memslots *slots; struct kvm_memory_slot *memslot; if (npages && old->npages) { @@ -2393,7 +2396,8 @@ static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm, * since the rmap array starts out as all zeroes, * i.e. no pages are dirty. */ - memslot = id_to_memslot(kvm->memslots, mem->slot); + slots = kvm_memslots(kvm); + memslot = id_to_memslot(slots, mem->slot); kvmppc_hv_get_dirty_log(kvm, memslot, NULL); } } diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index f57383941d03..c01dfc798c66 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -1530,6 +1530,7 @@ out: static int kvm_vm_ioctl_get_dirty_log_pr(struct kvm *kvm, struct kvm_dirty_log *log) { + struct kvm_memslots *slots; struct kvm_memory_slot *memslot; struct kvm_vcpu *vcpu; ulong ga, ga_end; @@ -1545,7 +1546,8 @@ static int kvm_vm_ioctl_get_dirty_log_pr(struct kvm *kvm, /* If nothing is dirty, don't bother messing with page tables. */ if (is_dirty) { - memslot = id_to_memslot(kvm->memslots, log->slot); + slots = kvm_memslots(kvm); + memslot = id_to_memslot(slots, log->slot); ga = memslot->base_gfn << PAGE_SHIFT; ga_end = ga + (memslot->npages << PAGE_SHIFT); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index d461f8a15c07..a05107e9b2bf 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -236,6 +236,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, { int r; unsigned long n; + struct kvm_memslots *slots; struct kvm_memory_slot *memslot; int is_dirty = 0; @@ -245,7 +246,8 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, if (log->slot >= KVM_USER_MEM_SLOTS) goto out; - memslot = id_to_memslot(kvm->memslots, log->slot); + slots = kvm_memslots(kvm); + memslot = id_to_memslot(slots, log->slot); r = -ENOENT; if (!memslot->dirty_bitmap) goto out; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index d42d8ace90f1..8918e23e0e8e 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7782,6 +7782,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_memory_slot *old, enum kvm_mr_change change) { + struct kvm_memslots *slots; struct kvm_memory_slot *new; int nr_mmu_pages = 0; @@ -7803,7 +7804,8 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); /* It's OK to get 'new' slot here as it has already been installed */ - new = id_to_memslot(kvm->memslots, mem->slot); + slots = kvm_memslots(kvm); + new = id_to_memslot(slots, mem->slot); /* * Dirty logging tracks sptes in 4k granularity, meaning that large diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index e299763ef744..42df724071c0 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -734,7 +734,7 @@ static int check_memory_region_flags(struct kvm_userspace_memory_region *mem) static struct kvm_memslots *install_new_memslots(struct kvm *kvm, struct kvm_memslots *slots) { - struct kvm_memslots *old_memslots = kvm->memslots; + struct kvm_memslots *old_memslots = kvm_memslots(kvm); /* * Set the low bit in the generation, which disables SPTE caching @@ -799,7 +799,7 @@ int __kvm_set_memory_region(struct kvm *kvm, if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) goto out; - slot = id_to_memslot(kvm->memslots, mem->slot); + slot = id_to_memslot(kvm_memslots(kvm), mem->slot); base_gfn = mem->guest_phys_addr >> PAGE_SHIFT; npages = mem->memory_size >> PAGE_SHIFT; @@ -842,7 +842,7 @@ int __kvm_set_memory_region(struct kvm *kvm, if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) { /* Check for overlaps */ r = -EEXIST; - kvm_for_each_memslot(slot, kvm->memslots) { + kvm_for_each_memslot(slot, kvm_memslots(kvm)) { if ((slot->id >= KVM_USER_MEM_SLOTS) || (slot->id == mem->slot)) continue; @@ -873,7 +873,7 @@ int __kvm_set_memory_region(struct kvm *kvm, slots = kvm_kvzalloc(sizeof(struct kvm_memslots)); if (!slots) goto out_free; - memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots)); + memcpy(slots, kvm_memslots(kvm), sizeof(struct kvm_memslots)); if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) { slot = id_to_memslot(slots, mem->slot); @@ -966,6 +966,7 @@ static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log, int *is_dirty) { + struct kvm_memslots *slots; struct kvm_memory_slot *memslot; int r, i; unsigned long n; @@ -975,7 +976,8 @@ int kvm_get_dirty_log(struct kvm *kvm, if (log->slot >= KVM_USER_MEM_SLOTS) goto out; - memslot = id_to_memslot(kvm->memslots, log->slot); + slots = kvm_memslots(kvm); + memslot = id_to_memslot(slots, log->slot); r = -ENOENT; if (!memslot->dirty_bitmap) goto out; @@ -1024,6 +1026,7 @@ EXPORT_SYMBOL_GPL(kvm_get_dirty_log); int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log, bool *is_dirty) { + struct kvm_memslots *slots; struct kvm_memory_slot *memslot; int r, i; unsigned long n; @@ -1034,7 +1037,8 @@ int kvm_get_dirty_log_protect(struct kvm *kvm, if (log->slot >= KVM_USER_MEM_SLOTS) goto out; - memslot = id_to_memslot(kvm->memslots, log->slot); + slots = kvm_memslots(kvm); + memslot = id_to_memslot(slots, log->slot); dirty_bitmap = memslot->dirty_bitmap; r = -ENOENT; -- cgit v1.2.3 From 09170a49422bd786be3eac5cec1955257c5a34b7 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 18 May 2015 13:59:39 +0200 Subject: KVM: const-ify uses of struct kvm_userspace_memory_region Architecture-specific helpers are not supposed to muck with struct kvm_userspace_memory_region contents. Add const to enforce this. In order to eliminate the only write in __kvm_set_memory_region, the cleaning of deleted slots is pulled up from update_memslots to __kvm_set_memory_region. Reviewed-by: Takuya Yoshikawa Reviewed-by: Radim Krcmar Signed-off-by: Paolo Bonzini --- arch/arm/kvm/mmu.c | 4 ++-- arch/mips/kvm/mips.c | 4 ++-- arch/powerpc/include/asm/kvm_ppc.h | 8 ++++---- arch/powerpc/kvm/book3s.c | 4 ++-- arch/powerpc/kvm/book3s_hv.c | 4 ++-- arch/powerpc/kvm/book3s_pr.c | 4 ++-- arch/powerpc/kvm/booke.c | 4 ++-- arch/powerpc/kvm/powerpc.c | 4 ++-- arch/s390/kvm/kvm-s390.c | 4 ++-- arch/x86/kvm/x86.c | 4 ++-- include/linux/kvm_host.h | 8 ++++---- virt/kvm/kvm_main.c | 22 +++++++++++----------- 12 files changed, 37 insertions(+), 37 deletions(-) diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 6f0f8f3ac7df..b5c023a37aec 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -1719,7 +1719,7 @@ out: } void kvm_arch_commit_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, enum kvm_mr_change change) { @@ -1734,7 +1734,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, enum kvm_mr_change change) { hva_t hva = mem->userspace_addr; diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index bc5ddd973b44..5963e2e8a6d7 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -198,14 +198,14 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, enum kvm_mr_change change) { return 0; } void kvm_arch_commit_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, enum kvm_mr_change change) { diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index b8475daad884..aff563b5f001 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -182,9 +182,9 @@ extern int kvmppc_core_create_memslot(struct kvm *kvm, unsigned long npages); extern int kvmppc_core_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - struct kvm_userspace_memory_region *mem); + const struct kvm_userspace_memory_region *mem); extern void kvmppc_core_commit_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old); extern int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info); @@ -243,9 +243,9 @@ struct kvmppc_ops { void (*flush_memslot)(struct kvm *kvm, struct kvm_memory_slot *memslot); int (*prepare_memory_region)(struct kvm *kvm, struct kvm_memory_slot *memslot, - struct kvm_userspace_memory_region *mem); + const struct kvm_userspace_memory_region *mem); void (*commit_memory_region)(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old); int (*unmap_hva)(struct kvm *kvm, unsigned long hva); int (*unmap_hva_range)(struct kvm *kvm, unsigned long start, diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 453a8a47a467..60aa0726dccc 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -757,13 +757,13 @@ void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot) int kvmppc_core_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - struct kvm_userspace_memory_region *mem) + const struct kvm_userspace_memory_region *mem) { return kvm->arch.kvm_ops->prepare_memory_region(kvm, memslot, mem); } void kvmppc_core_commit_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old) { kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old); diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 6aff5a990492..ed493d123268 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2376,13 +2376,13 @@ static int kvmppc_core_create_memslot_hv(struct kvm_memory_slot *slot, static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm, struct kvm_memory_slot *memslot, - struct kvm_userspace_memory_region *mem) + const struct kvm_userspace_memory_region *mem) { return 0; } static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old) { unsigned long npages = mem->memory_size >> PAGE_SHIFT; diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index c01dfc798c66..0873e766df1b 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -1573,13 +1573,13 @@ static void kvmppc_core_flush_memslot_pr(struct kvm *kvm, static int kvmppc_core_prepare_memory_region_pr(struct kvm *kvm, struct kvm_memory_slot *memslot, - struct kvm_userspace_memory_region *mem) + const struct kvm_userspace_memory_region *mem) { return 0; } static void kvmppc_core_commit_memory_region_pr(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old) { return; diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 3872ab31c80a..518e3a8b351f 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -1784,13 +1784,13 @@ int kvmppc_core_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, int kvmppc_core_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - struct kvm_userspace_memory_region *mem) + const struct kvm_userspace_memory_region *mem) { return 0; } void kvmppc_core_commit_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old) { } diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 8cd1f80fdc70..5985bb2a332b 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -595,14 +595,14 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, enum kvm_mr_change change) { return kvmppc_core_prepare_memory_region(kvm, memslot, mem); } void kvm_arch_commit_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, enum kvm_mr_change change) { diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index a05107e9b2bf..994f9c37f25f 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2582,7 +2582,7 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, /* Section: memory related */ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, enum kvm_mr_change change) { /* A few sanity checks. We can have memory slots which have to be @@ -2600,7 +2600,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, } void kvm_arch_commit_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, enum kvm_mr_change change) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 8918e23e0e8e..30854ea218e7 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7700,7 +7700,7 @@ void kvm_arch_memslots_updated(struct kvm *kvm) int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, enum kvm_mr_change change) { /* @@ -7778,7 +7778,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, } void kvm_arch_commit_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, enum kvm_mr_change change) { diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 87fd74a04005..fbced7015ebd 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -501,9 +501,9 @@ enum kvm_mr_change { }; int kvm_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem); + const struct kvm_userspace_memory_region *mem); int __kvm_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem); + const struct kvm_userspace_memory_region *mem); void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont); int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, @@ -511,10 +511,10 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, void kvm_arch_memslots_updated(struct kvm *kvm); int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, enum kvm_mr_change change); void kvm_arch_commit_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, enum kvm_mr_change change); bool kvm_largepages_enabled(void); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 42df724071c0..fc2dbe1c34fc 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -676,8 +676,6 @@ static void update_memslots(struct kvm_memslots *slots, WARN_ON(mslots[i].id != id); if (!new->npages) { WARN_ON(!mslots[i].npages); - new->base_gfn = 0; - new->flags = 0; if (mslots[i].npages) slots->used_slots--; } else { @@ -717,7 +715,7 @@ static void update_memslots(struct kvm_memslots *slots, slots->id_to_index[mslots[i].id] = i; } -static int check_memory_region_flags(struct kvm_userspace_memory_region *mem) +static int check_memory_region_flags(const struct kvm_userspace_memory_region *mem) { u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES; @@ -767,7 +765,7 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, * Must be called holding kvm->slots_lock for write. */ int __kvm_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem) + const struct kvm_userspace_memory_region *mem) { int r; gfn_t base_gfn; @@ -806,9 +804,6 @@ int __kvm_set_memory_region(struct kvm *kvm, if (npages > KVM_MEM_MAX_NR_PAGES) goto out; - if (!npages) - mem->flags &= ~KVM_MEM_LOG_DIRTY_PAGES; - new = old = *slot; new.id = mem->slot; @@ -834,10 +829,14 @@ int __kvm_set_memory_region(struct kvm *kvm, goto out; } } - } else if (old.npages) { + } else { + if (!old.npages) + goto out; + change = KVM_MR_DELETE; - } else /* Modify a non-existent slot: disallowed. */ - goto out; + new.base_gfn = 0; + new.flags = 0; + } if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) { /* Check for overlaps */ @@ -944,7 +943,7 @@ out: EXPORT_SYMBOL_GPL(__kvm_set_memory_region); int kvm_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem) + const struct kvm_userspace_memory_region *mem) { int r; @@ -960,6 +959,7 @@ static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, { if (mem->slot >= KVM_USER_MEM_SLOTS) return -EINVAL; + return kvm_set_memory_region(kvm, mem); } -- cgit v1.2.3 From 15f46015ee17681b542432df21747f5c51857156 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Sun, 17 May 2015 21:26:08 +0200 Subject: KVM: add memslots argument to kvm_arch_memslots_updated Prepare for the case of multiple address spaces. Reviewed-by: Radim Krcmar Signed-off-by: Paolo Bonzini --- arch/arm/kvm/mmu.c | 2 +- arch/mips/include/asm/kvm_host.h | 2 +- arch/powerpc/include/asm/kvm_host.h | 2 +- arch/s390/include/asm/kvm_host.h | 2 +- arch/x86/kvm/x86.c | 2 +- include/linux/kvm_host.h | 2 +- include/linux/kvm_types.h | 1 + virt/kvm/kvm_main.c | 2 +- 8 files changed, 8 insertions(+), 7 deletions(-) diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index b5c023a37aec..e9ac084d21ea 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -1839,7 +1839,7 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, return 0; } -void kvm_arch_memslots_updated(struct kvm *kvm) +void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) { } diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 4c25823563fe..e8c8d9d0c45f 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -839,7 +839,7 @@ static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {} -static inline void kvm_arch_memslots_updated(struct kvm *kvm) {} +static inline void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) {} static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {} static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) {} diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index a193a13cf08b..d91f65b28e32 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -698,7 +698,7 @@ struct kvm_vcpu_arch { static inline void kvm_arch_hardware_disable(void) {} static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} -static inline void kvm_arch_memslots_updated(struct kvm *kvm) {} +static inline void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) {} static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_exit(void) {} diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 444c412307cb..3024acbe1f9d 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -636,7 +636,7 @@ static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {} -static inline void kvm_arch_memslots_updated(struct kvm *kvm) {} +static inline void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) {} static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {} static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) {} diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 30854ea218e7..f0aec85f8cdd 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7689,7 +7689,7 @@ out_free: return -ENOMEM; } -void kvm_arch_memslots_updated(struct kvm *kvm) +void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) { /* * memslots->generation has been incremented. diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index fbced7015ebd..8815f1dffb77 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -508,7 +508,7 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont); int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, unsigned long npages); -void kvm_arch_memslots_updated(struct kvm *kvm); +void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots); int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, const struct kvm_userspace_memory_region *mem, diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 931da7e917cf..1b47a185c2f0 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -28,6 +28,7 @@ struct kvm_run; struct kvm_userspace_memory_region; struct kvm_vcpu; struct kvm_vcpu_init; +struct kvm_memslots; enum kvm_mr_change; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index fc2dbe1c34fc..4361204a6348 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -751,7 +751,7 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, */ slots->generation++; - kvm_arch_memslots_updated(kvm); + kvm_arch_memslots_updated(kvm, slots); return old_memslots; } -- cgit v1.2.3 From f36f3f2846b5578d62910ee0b6dbef59fdd1cfa4 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 18 May 2015 13:20:23 +0200 Subject: KVM: add "new" argument to kvm_arch_commit_memory_region This lets the function access the new memory slot without going through kvm_memslots and id_to_memslot. It will simplify the code when more than one address space will be supported. Unfortunately, the "const"ness of the new argument must be casted away in two places. Fixing KVM to accept const struct kvm_memory_slot pointers would require modifications in pretty much all architectures, and is left for later. Reviewed-by: Radim Krcmar Signed-off-by: Paolo Bonzini --- arch/arm/kvm/mmu.c | 1 + arch/mips/kvm/mips.c | 1 + arch/powerpc/include/asm/kvm_ppc.h | 6 ++++-- arch/powerpc/kvm/book3s.c | 5 +++-- arch/powerpc/kvm/book3s_hv.c | 3 ++- arch/powerpc/kvm/book3s_pr.c | 3 ++- arch/powerpc/kvm/booke.c | 3 ++- arch/powerpc/kvm/powerpc.c | 3 ++- arch/s390/kvm/kvm-s390.c | 1 + arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/mmu.c | 6 ++++-- arch/x86/kvm/x86.c | 13 +++++-------- include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 2 +- 14 files changed, 30 insertions(+), 20 deletions(-) diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index e9ac084d21ea..7f473e6d3bf5 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -1721,6 +1721,7 @@ out: void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, + const struct kvm_memory_slot *new, enum kvm_mr_change change) { /* diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 5963e2e8a6d7..cd4c129ce743 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -207,6 +207,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, + const struct kvm_memory_slot *new, enum kvm_mr_change change) { unsigned long npages = 0; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index aff563b5f001..c6ef05bd0765 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -185,7 +185,8 @@ extern int kvmppc_core_prepare_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem); extern void kvmppc_core_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old); + const struct kvm_memory_slot *old, + const struct kvm_memory_slot *new); extern int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info); extern void kvmppc_core_flush_memslot(struct kvm *kvm, @@ -246,7 +247,8 @@ struct kvmppc_ops { const struct kvm_userspace_memory_region *mem); void (*commit_memory_region)(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old); + const struct kvm_memory_slot *old, + const struct kvm_memory_slot *new); int (*unmap_hva)(struct kvm *kvm, unsigned long hva); int (*unmap_hva_range)(struct kvm *kvm, unsigned long start, unsigned long end); diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 60aa0726dccc..05ea8fc7f829 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -764,9 +764,10 @@ int kvmppc_core_prepare_memory_region(struct kvm *kvm, void kvmppc_core_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old) + const struct kvm_memory_slot *old, + const struct kvm_memory_slot *new) { - kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old); + kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new); } int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index ed493d123268..68d067ad4222 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2383,7 +2383,8 @@ static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm, static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old) + const struct kvm_memory_slot *old, + const struct kvm_memory_slot *new) { unsigned long npages = mem->memory_size >> PAGE_SHIFT; struct kvm_memslots *slots; diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 0873e766df1b..64891b081ad5 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -1580,7 +1580,8 @@ static int kvmppc_core_prepare_memory_region_pr(struct kvm *kvm, static void kvmppc_core_commit_memory_region_pr(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old) + const struct kvm_memory_slot *old, + const struct kvm_memory_slot *new) { return; } diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 518e3a8b351f..cc5842657161 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -1791,7 +1791,8 @@ int kvmppc_core_prepare_memory_region(struct kvm *kvm, void kvmppc_core_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old) + const struct kvm_memory_slot *old, + const struct kvm_memory_slot *new) { } diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 5985bb2a332b..e5dde32fe71f 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -604,9 +604,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, + const struct kvm_memory_slot *new, enum kvm_mr_change change) { - kvmppc_core_commit_memory_region(kvm, mem, old); + kvmppc_core_commit_memory_region(kvm, mem, old, new); } void kvm_arch_flush_shadow_memslot(struct kvm *kvm, diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 994f9c37f25f..8ad4b9a5667f 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2602,6 +2602,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, + const struct kvm_memory_slot *new, enum kvm_mr_change change) { int rc; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 1a4d6a054749..7276107b35df 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -874,7 +874,7 @@ void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, struct kvm_memory_slot *memslot); void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, - struct kvm_memory_slot *memslot); + const struct kvm_memory_slot *memslot); void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot); void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm, diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 49c34e632b91..1bf2ae9ca521 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4621,10 +4621,12 @@ restart: } void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, - struct kvm_memory_slot *memslot) + const struct kvm_memory_slot *memslot) { + /* FIXME: const-ify all uses of struct kvm_memory_slot. */ spin_lock(&kvm->mmu_lock); - slot_handle_leaf(kvm, memslot, kvm_mmu_zap_collapsible_spte, true); + slot_handle_leaf(kvm, (struct kvm_memory_slot *)memslot, + kvm_mmu_zap_collapsible_spte, true); spin_unlock(&kvm->mmu_lock); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f0aec85f8cdd..ba7b0cc52fed 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7780,13 +7780,12 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, + const struct kvm_memory_slot *new, enum kvm_mr_change change) { - struct kvm_memslots *slots; - struct kvm_memory_slot *new; int nr_mmu_pages = 0; - if ((mem->slot >= KVM_USER_MEM_SLOTS) && (change == KVM_MR_DELETE)) { + if (change == KVM_MR_DELETE && old->id >= KVM_USER_MEM_SLOTS) { int ret; ret = vm_munmap(old->userspace_addr, @@ -7803,10 +7802,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, if (nr_mmu_pages) kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); - /* It's OK to get 'new' slot here as it has already been installed */ - slots = kvm_memslots(kvm); - new = id_to_memslot(slots, mem->slot); - /* * Dirty logging tracks sptes in 4k granularity, meaning that large * sptes have to be split. If live migration is successful, the guest @@ -7831,9 +7826,11 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, * been zapped so no dirty logging staff is needed for old slot. For * KVM_MR_FLAGS_ONLY, the old slot is essentially the same one as the * new and it's also covered when dealing with the new slot. + * + * FIXME: const-ify all uses of struct kvm_memory_slot. */ if (change != KVM_MR_DELETE) - kvm_mmu_slot_apply_flags(kvm, new); + kvm_mmu_slot_apply_flags(kvm, (struct kvm_memory_slot *) new); } void kvm_arch_flush_shadow_all(struct kvm *kvm) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 8815f1dffb77..9bd3bc16be87 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -516,6 +516,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, + const struct kvm_memory_slot *new, enum kvm_mr_change change); bool kvm_largepages_enabled(void); void kvm_disable_largepages(void); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 4361204a6348..9f67c942d8ee 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -912,7 +912,7 @@ int __kvm_set_memory_region(struct kvm *kvm, update_memslots(slots, &new); old_memslots = install_new_memslots(kvm, slots); - kvm_arch_commit_memory_region(kvm, mem, &old, change); + kvm_arch_commit_memory_region(kvm, mem, &old, &new, change); kvm_free_memslot(kvm, &old, &new); kvfree(old_memslots); -- cgit v1.2.3 From d9ef13c2b3983de8dd1373ef670799dbb6498122 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 19 May 2015 16:01:50 +0200 Subject: KVM: pass kvm_memory_slot to gfn_to_page_many_atomic The memory slot is already available from gfn_to_memslot_dirty_bitmap. Isn't it a shame to look it up again? Plus, it makes gfn_to_page_many_atomic agnostic of multiple VCPU address spaces. Reviewed-by: Radim Krcmar Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu.c | 6 ++++-- include/linux/kvm_host.h | 4 ++-- virt/kvm/kvm_main.c | 6 +++--- 3 files changed, 9 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 1bf2ae9ca521..6a7e5b6246b1 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2728,15 +2728,17 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, u64 *start, u64 *end) { struct page *pages[PTE_PREFETCH_NUM]; + struct kvm_memory_slot *slot; unsigned access = sp->role.access; int i, ret; gfn_t gfn; gfn = kvm_mmu_page_get_gfn(sp, start - sp->spt); - if (!gfn_to_memslot_dirty_bitmap(vcpu, gfn, access & ACC_WRITE_MASK)) + slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, access & ACC_WRITE_MASK); + if (!slot) return -1; - ret = gfn_to_page_many_atomic(vcpu->kvm, gfn, pages, end - start); + ret = gfn_to_page_many_atomic(slot, gfn, pages, end - start); if (ret <= 0) return -1; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9bd3bc16be87..a8bcbc9c6078 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -526,8 +526,8 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm); void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); -int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages, - int nr_pages); +int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn, + struct page **pages, int nr_pages); struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn); unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 9f67c942d8ee..c57f44216a4e 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1428,13 +1428,13 @@ pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn) } EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic); -int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages, - int nr_pages) +int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn, + struct page **pages, int nr_pages) { unsigned long addr; gfn_t entry; - addr = gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, &entry); + addr = gfn_to_hva_many(slot, gfn, &entry); if (kvm_is_error_hva(addr)) return -1; -- cgit v1.2.3 From e37afc6ee5a6af9b334e2f214ec795e8bfaaaba5 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 19 May 2015 16:09:04 +0200 Subject: KVM: remove __gfn_to_pfn Most of the function that wrap it can be rewritten without it, except for gfn_to_pfn_prot. Just inline it into gfn_to_pfn_prot, and rewrite the other function on top of gfn_to_pfn_memslot*. Reviewed-by: Radim Krcmar Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 39 +++++++++++++++------------------------ 1 file changed, 15 insertions(+), 24 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index c57f44216a4e..53e66ef8b75e 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1387,33 +1387,11 @@ pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, } EXPORT_SYMBOL_GPL(__gfn_to_pfn_memslot); -static pfn_t __gfn_to_pfn(struct kvm *kvm, gfn_t gfn, bool atomic, - bool write_fault, bool *writable) -{ - struct kvm_memory_slot *slot; - - slot = gfn_to_memslot(kvm, gfn); - - return __gfn_to_pfn_memslot(slot, gfn, atomic, NULL, write_fault, - writable); -} - -pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn) -{ - return __gfn_to_pfn(kvm, gfn, true, true, NULL); -} -EXPORT_SYMBOL_GPL(gfn_to_pfn_atomic); - -pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) -{ - return __gfn_to_pfn(kvm, gfn, false, true, NULL); -} -EXPORT_SYMBOL_GPL(gfn_to_pfn); - pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, bool *writable) { - return __gfn_to_pfn(kvm, gfn, false, write_fault, writable); + return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, NULL, + write_fault, writable); } EXPORT_SYMBOL_GPL(gfn_to_pfn_prot); @@ -1421,6 +1399,7 @@ pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL); } +EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot); pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn) { @@ -1428,6 +1407,18 @@ pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn) } EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic); +pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn) +{ + return gfn_to_pfn_memslot_atomic(gfn_to_memslot(kvm, gfn), gfn); +} +EXPORT_SYMBOL_GPL(gfn_to_pfn_atomic); + +pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) +{ + return gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn); +} +EXPORT_SYMBOL_GPL(gfn_to_pfn); + int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn, struct page **pages, int nr_pages) { -- cgit v1.2.3 From 3ed1a4787617f948631a77903453847142271867 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 19 May 2015 16:29:22 +0200 Subject: KVM: x86: pass struct kvm_mmu_page to account/unaccount_shadowed Prepare for multiple address spaces this way, since a VCPU is not available where unaccount_shadowed is called. We will get to the right kvm_memslots struct through the role field in struct kvm_mmu_page. Reviewed-by: Takuya Yoshikawa Reviewed-by: Radim Krcmar Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 6a7e5b6246b1..deb8862cfd54 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -804,12 +804,14 @@ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn, return &slot->arch.lpage_info[level - 2][idx]; } -static void account_shadowed(struct kvm *kvm, gfn_t gfn) +static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) { struct kvm_memory_slot *slot; struct kvm_lpage_info *linfo; + gfn_t gfn; int i; + gfn = sp->gfn; slot = gfn_to_memslot(kvm, gfn); for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { linfo = lpage_info_slot(gfn, slot, i); @@ -818,12 +820,14 @@ static void account_shadowed(struct kvm *kvm, gfn_t gfn) kvm->arch.indirect_shadow_pages++; } -static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn) +static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) { struct kvm_memory_slot *slot; struct kvm_lpage_info *linfo; + gfn_t gfn; int i; + gfn = sp->gfn; slot = gfn_to_memslot(kvm, gfn); for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { linfo = lpage_info_slot(gfn, slot, i); @@ -2131,7 +2135,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, if (level > PT_PAGE_TABLE_LEVEL && need_sync) kvm_sync_pages(vcpu, gfn); - account_shadowed(vcpu->kvm, gfn); + account_shadowed(vcpu->kvm, sp); } sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen; init_shadow_page_table(sp); @@ -2312,7 +2316,7 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, kvm_mmu_unlink_parents(kvm, sp); if (!sp->role.invalid && !sp->role.direct) - unaccount_shadowed(kvm, sp->gfn); + unaccount_shadowed(kvm, sp); if (sp->unsync) kvm_unlink_unsync_page(kvm, sp); -- cgit v1.2.3 From 630994b3c798dec3de1fb1d5a3dd9201267036f6 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Tue, 12 May 2015 22:42:04 -0300 Subject: KVM: x86: add module parameter to disable periodic kvmclock sync The periodic kvmclock sync can be an undesired source of latencies. When running cyclictest on a guest, a latency spike is visible. With kvmclock periodic sync disabled, the spike is gone. Guests should use ntp which means the propagations of ntp corrections from the host clock are unnecessary. v2: -> Make parameter read-only (Radim) -> Return early on kvmclock_sync_fn (Andrew) Reported-and-tested-by: Luiz Capitulino Signed-off-by: Marcelo Tosatti Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ba7b0cc52fed..2211213a84e7 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -99,6 +99,9 @@ module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR); unsigned int min_timer_period_us = 500; module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR); +static bool __read_mostly kvmclock_periodic_sync = true; +module_param(kvmclock_periodic_sync, bool, S_IRUGO); + bool kvm_has_tsc_control; EXPORT_SYMBOL_GPL(kvm_has_tsc_control); u32 kvm_max_guest_tsc_khz; @@ -1767,6 +1770,9 @@ static void kvmclock_sync_fn(struct work_struct *work) kvmclock_sync_work); struct kvm *kvm = container_of(ka, struct kvm, arch); + if (!kvmclock_periodic_sync) + return; + schedule_delayed_work(&kvm->arch.kvmclock_update_work, 0); schedule_delayed_work(&kvm->arch.kvmclock_sync_work, KVMCLOCK_SYNC_PERIOD); @@ -7221,6 +7227,9 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) kvm_write_tsc(vcpu, &msr); vcpu_put(vcpu); + if (!kvmclock_periodic_sync) + return; + schedule_delayed_work(&kvm->arch.kvmclock_sync_work, KVMCLOCK_SYNC_PERIOD); } -- cgit v1.2.3 From 257b9a5faab5849fa61f1a523b429dc279d33cc3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= Date: Fri, 22 May 2015 18:45:11 +0200 Subject: KVM: x86: use correct APIC ID on x2APIC transition MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit SDM April 2015, 10.12.5 State Changes From xAPIC Mode to x2APIC Mode • Any APIC ID value written to the memory-mapped local APIC ID register is not preserved. Fix it by sourcing vcpu_id (= initial APIC ID) instead of memory-mapped APIC ID. Proper use of apic functions would result in two calls to recalculate_apic_map(), so this patch makes a new helper. Signed-off-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- arch/x86/kvm/lapic.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index dc5b57bb1f76..c2a7d8a7a414 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -240,6 +240,15 @@ static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id) recalculate_apic_map(apic->vcpu->kvm); } +static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u8 id) +{ + u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf)); + + apic_set_reg(apic, APIC_ID, id << 24); + apic_set_reg(apic, APIC_LDR, ldr); + recalculate_apic_map(apic->vcpu->kvm); +} + static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type) { return !(kvm_apic_get_reg(apic, lvt_type) & APIC_LVT_MASKED); @@ -1538,9 +1547,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) if ((old_value ^ value) & X2APIC_ENABLE) { if (value & X2APIC_ENABLE) { - u32 id = kvm_apic_id(apic); - u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf)); - kvm_apic_set_ldr(apic, ldr); + kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id); kvm_x86_ops->set_virtual_x2apic_mode(vcpu, true); } else kvm_x86_ops->set_virtual_x2apic_mode(vcpu, false); -- cgit v1.2.3 From c028dd6bb648251b773f900f59e53544278b3b3c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= Date: Fri, 22 May 2015 19:22:10 +0200 Subject: KVM: x86: preserve x2APIC LDR on INIT MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Logical x2APIC stops working if we rewrite it with zeros. The best references are SDM April 2015: 10.12.10.1 Logical Destination Mode in x2APIC Mode [...], the LDR are initialized by hardware based on the value of x2APIC ID upon x2APIC state transitions. and SDM April 2015: 10.12.10.2 Deriving Logical x2APIC ID from the Local x2APIC ID The LDR initialization occurs whenever the x2APIC mode is enabled Signed-off-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- arch/x86/kvm/lapic.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index c2a7d8a7a414..c789e00dfa8b 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1594,7 +1594,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) apic_set_reg(apic, APIC_DFR, 0xffffffffU); apic_set_spiv(apic, 0xff); apic_set_reg(apic, APIC_TASKPRI, 0); - kvm_apic_set_ldr(apic, 0); + if (!apic_x2apic_mode(apic)) + kvm_apic_set_ldr(apic, 0); apic_set_reg(apic, APIC_ESR, 0); apic_set_reg(apic, APIC_ICR, 0); apic_set_reg(apic, APIC_ICR2, 0); -- cgit v1.2.3 From e453aa0f7e7b10135d7a84742722f5fc799a3df9 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Sun, 24 May 2015 17:22:38 +0200 Subject: KVM: x86: Allow ARAT CPU feature There is no reason to deny this feature to guests. We are emulating the APIC timer, thus are exposing it without stops in power-saving states. Signed-off-by: Jan Kiszka Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 92a74a0428aa..9dadf8d67873 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -415,6 +415,12 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, } break; } + case 6: /* Thermal management */ + entry->eax = 0x4; /* allow ARAT */ + entry->ebx = 0; + entry->ecx = 0; + entry->edx = 0; + break; case 7: { entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; /* Mask ebx against host capability word 9 */ @@ -591,7 +597,6 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, break; case 3: /* Processor serial number */ case 5: /* MONITOR/MWAIT */ - case 6: /* Thermal management */ case 0xC0000002: case 0xC0000003: case 0xC0000004: -- cgit v1.2.3 From bc009e43307916f87f0cbd4bc5ec0e8f6b064c9a Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 26 May 2015 12:43:41 +0200 Subject: KVM: remove unused argument from mark_page_dirty_in_slot Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 53e66ef8b75e..6c8e124006ad 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -103,8 +103,7 @@ static void hardware_disable_all(void); static void kvm_io_bus_destroy(struct kvm_io_bus *bus); static void kvm_release_pfn_dirty(pfn_t pfn); -static void mark_page_dirty_in_slot(struct kvm *kvm, - struct kvm_memory_slot *memslot, gfn_t gfn); +static void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn); __visible bool kvm_rebooting; EXPORT_SYMBOL_GPL(kvm_rebooting); @@ -1591,7 +1590,7 @@ int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, r = __copy_to_user((void __user *)addr + offset, data, len); if (r) return -EFAULT; - mark_page_dirty_in_slot(kvm, memslot, gfn); + mark_page_dirty_in_slot(memslot, gfn); return 0; } EXPORT_SYMBOL_GPL(kvm_write_guest_page); @@ -1674,7 +1673,7 @@ int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, r = __copy_to_user((void __user *)ghc->hva, data, len); if (r) return -EFAULT; - mark_page_dirty_in_slot(kvm, ghc->memslot, ghc->gpa >> PAGE_SHIFT); + mark_page_dirty_in_slot(ghc->memslot, ghc->gpa >> PAGE_SHIFT); return 0; } @@ -1732,8 +1731,7 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len) } EXPORT_SYMBOL_GPL(kvm_clear_guest); -static void mark_page_dirty_in_slot(struct kvm *kvm, - struct kvm_memory_slot *memslot, +static void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn) { if (memslot && memslot->dirty_bitmap) { @@ -1748,7 +1746,7 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn) struct kvm_memory_slot *memslot; memslot = gfn_to_memslot(kvm, gfn); - mark_page_dirty_in_slot(kvm, memslot, gfn); + mark_page_dirty_in_slot(memslot, gfn); } EXPORT_SYMBOL_GPL(mark_page_dirty); -- cgit v1.2.3 From 4141259b56cbd5a8614e487366909a02d702b9dd Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 27 May 2015 11:53:06 +0200 Subject: arch/x86/kvm/mmu.c: work around gcc-4.4.4 bug arch/x86/kvm/mmu.c: In function 'kvm_mmu_pte_write': arch/x86/kvm/mmu.c:4256: error: unknown field 'cr0_wp' specified in initializer arch/x86/kvm/mmu.c:4257: error: unknown field 'cr4_pae' specified in initializer arch/x86/kvm/mmu.c:4257: warning: excess elements in union initializer ... gcc-4.4.4 (at least) has issues when using anonymous unions in initializers. Fixes: edc90b7dc4ceef6 ("KVM: MMU: fix SMAP virtualization") Cc: Xiao Guangrong Cc: Paolo Bonzini Signed-off-by: Andrew Morton Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index deb8862cfd54..a65ce12470f8 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4258,13 +4258,13 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, u64 entry, gentry, *spte; int npte; bool remote_flush, local_flush, zap_page; - union kvm_mmu_page_role mask = (union kvm_mmu_page_role) { - .cr0_wp = 1, - .cr4_pae = 1, - .nxe = 1, - .smep_andnot_wp = 1, - .smap_andnot_wp = 1, - }; + union kvm_mmu_page_role mask = { }; + + mask.cr0_wp = 1; + mask.cr4_pae = 1; + mask.nxe = 1; + mask.smep_andnot_wp = 1; + mask.smap_andnot_wp = 1; /* * If we don't have indirect shadow pages, it means no page is -- cgit v1.2.3 From 611917258f88fb2fa41d1c2826b193f7c3885b54 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Thu, 28 May 2015 20:20:39 -0300 Subject: x86: kvmclock: add flag to indicate pvclock counts from zero Setting sched clock stable for kvmclock causes the printk timestamps to not start from zero, which is different from baremetal and can possibly break userspace. Add a flag to indicate that hypervisor sets clock base at zero when kvmclock is initialized. Signed-off-by: Marcelo Tosatti Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/pvclock-abi.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h index 6167fd798188..655e07a48f6c 100644 --- a/arch/x86/include/asm/pvclock-abi.h +++ b/arch/x86/include/asm/pvclock-abi.h @@ -41,5 +41,6 @@ struct pvclock_wall_clock { #define PVCLOCK_TSC_STABLE_BIT (1 << 0) #define PVCLOCK_GUEST_STOPPED (1 << 1) +#define PVCLOCK_COUNTS_FROM_ZERO (1 << 2) #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_PVCLOCK_ABI_H */ -- cgit v1.2.3 From 0ad83caa21bff9f383c10e73b452425709573042 Mon Sep 17 00:00:00 2001 From: Luiz Capitulino Date: Thu, 28 May 2015 20:20:40 -0300 Subject: x86: kvmclock: set scheduler clock stable If you try to enable NOHZ_FULL on a guest today, you'll get the following error when the guest tries to deactivate the scheduler tick: WARNING: CPU: 3 PID: 2182 at kernel/time/tick-sched.c:192 can_stop_full_tick+0xb9/0x290() NO_HZ FULL will not work with unstable sched clock CPU: 3 PID: 2182 Comm: kworker/3:1 Not tainted 4.0.0-10545-gb9bb6fb #204 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 Workqueue: events flush_to_ldisc ffffffff8162a0c7 ffff88011f583e88 ffffffff814e6ba0 0000000000000002 ffff88011f583ed8 ffff88011f583ec8 ffffffff8104d095 ffff88011f583eb8 0000000000000000 0000000000000003 0000000000000001 0000000000000001 Call Trace: [] dump_stack+0x4f/0x7b [] warn_slowpath_common+0x85/0xc0 [] warn_slowpath_fmt+0x46/0x50 [] can_stop_full_tick+0xb9/0x290 [] tick_nohz_irq_exit+0x8d/0xb0 [] irq_exit+0xc5/0x130 [] smp_apic_timer_interrupt+0x4a/0x60 [] apic_timer_interrupt+0x6e/0x80 [] ? _raw_spin_unlock_irqrestore+0x31/0x60 [] __wake_up+0x48/0x60 [] n_tty_receive_buf_common+0x49c/0xba0 [] ? tty_ldisc_ref+0x1f/0x70 [] n_tty_receive_buf2+0x14/0x20 [] flush_to_ldisc+0xe0/0x120 [] process_one_work+0x1d5/0x540 [] ? process_one_work+0x151/0x540 [] worker_thread+0x121/0x470 [] ? process_one_work+0x540/0x540 [] kthread+0xef/0x110 [] ? __kthread_parkme+0xa0/0xa0 [] ret_from_fork+0x42/0x70 [] ? __kthread_parkme+0xa0/0xa0 ---[ end trace 06e3507544a38866 ]--- However, it turns out that kvmclock does provide a stable sched_clock callback. So, let the scheduler know this which in turn makes NOHZ_FULL work in the guest. Signed-off-by: Marcelo Tosatti Signed-off-by: Luiz Capitulino Signed-off-by: Paolo Bonzini --- arch/x86/kernel/kvmclock.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 42caaef897c8..49487b488061 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -217,8 +218,10 @@ static void kvm_shutdown(void) void __init kvmclock_init(void) { + struct pvclock_vcpu_time_info *vcpu_time; unsigned long mem; - int size; + int size, cpu; + u8 flags; size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS); @@ -264,7 +267,14 @@ void __init kvmclock_init(void) pv_info.name = "KVM"; if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) - pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT); + pvclock_set_flags(~0); + + cpu = get_cpu(); + vcpu_time = &hv_clock[cpu].pvti; + flags = pvclock_read_flags(vcpu_time); + if (flags & PVCLOCK_COUNTS_FROM_ZERO) + set_sched_clock_stable(); + put_cpu(); } int __init kvm_setup_vsyscall_timeinfo(void) -- cgit v1.2.3 From b7e60c5aedd2b63f16ef06fde4f81ca032211bc5 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Thu, 28 May 2015 20:20:41 -0300 Subject: KVM: x86: zero kvmclock_offset when vcpu0 initializes kvmclock system MSR Initialize kvmclock base, on kvmclock system MSR write time, so that the guest sees kvmclock counting from zero. This matches baremetal behaviour when kvmclock in guest sets sched clock stable. Signed-off-by: Marcelo Tosatti [Remove unnecessary comment. - Paolo] Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2211213a84e7..79dde1656db6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1700,6 +1700,8 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) vcpu->pvclock_set_guest_stopped_request = false; } + pvclock_flags |= PVCLOCK_COUNTS_FROM_ZERO; + /* If the host uses TSC clocksource, then it is stable */ if (use_master_clock) pvclock_flags |= PVCLOCK_TSC_STABLE_BIT; @@ -2282,6 +2284,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) &vcpu->requests); ka->boot_vcpu_runs_old_kvmclock = tmp; + + ka->kvmclock_offset = -get_kernel_ns(); } vcpu->arch.time = data; -- cgit v1.2.3 From 61a6df54b64913defc64c87a05d5d258a2020fb5 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 12 May 2015 08:41:40 +0200 Subject: KVM: s390: call exit_sie() directly on vcpu block/request Thinking about it, I can't find a real use case where we want to block a VCPU and not kick it out of SIE. (except if we want to do the same in batch for multiple VCPUs - but that's a micro optimization) So let's simply perform the exit_sie() calls directly when setting the other magic block bits in the SIE. Otherwise e.g. kvm_s390_set_tod_low() still has other VCPUs running after that call, working with a wrong epoch. Fixes: 27406cd50c ("KVM: s390: provide functions for blocking all CPUs") Acked-by: Christian Borntraeger Signed-off-by: David Hildenbrand Signed-off-by: Christian Borntraeger --- arch/s390/kvm/kvm-s390.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 6bc69ab5b5b4..f37557bc2512 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1417,6 +1417,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu) { atomic_set_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20); + exit_sie(vcpu); } void kvm_s390_vcpu_unblock(struct kvm_vcpu *vcpu) @@ -1427,6 +1428,7 @@ void kvm_s390_vcpu_unblock(struct kvm_vcpu *vcpu) static void kvm_s390_vcpu_request(struct kvm_vcpu *vcpu) { atomic_set_mask(PROG_REQUEST, &vcpu->arch.sie_block->prog20); + exit_sie(vcpu); } static void kvm_s390_vcpu_request_handled(struct kvm_vcpu *vcpu) @@ -1450,7 +1452,6 @@ void kvm_s390_sync_request(int req, struct kvm_vcpu *vcpu) { kvm_make_request(req, vcpu); kvm_s390_vcpu_request(vcpu); - exit_sie(vcpu); } static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address) -- cgit v1.2.3 From ea2cdd27dce66dc498c623adacd807ea3a350443 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 20 May 2015 13:24:02 +0200 Subject: KVM: s390: introduce KMSG_COMPONENT for kvm-s390 Let's remove "kvm-s390" from our printk messages and make use of pr_fmt instead. Also replace one printk() occurrence by a equivalent pr_warn on the way. Suggested-by: Christian Borntraeger Signed-off-by: David Hildenbrand Signed-off-by: Christian Borntraeger --- arch/s390/kvm/kvm-s390.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index f37557bc2512..9cb6cfaac986 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -36,6 +36,10 @@ #include "kvm-s390.h" #include "gaccess.h" +#define KMSG_COMPONENT "kvm-s390" +#undef pr_fmt +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #define CREATE_TRACE_POINTS #include "trace.h" #include "trace-s390.h" @@ -2086,7 +2090,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) { kvm_s390_vcpu_start(vcpu); } else if (is_vcpu_stopped(vcpu)) { - pr_err_ratelimited("kvm-s390: can't run stopped vcpu %d\n", + pr_err_ratelimited("can't run stopped vcpu %d\n", vcpu->vcpu_id); return -EINVAL; } @@ -2617,7 +2621,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr, mem->guest_phys_addr, mem->memory_size); if (rc) - printk(KERN_WARNING "kvm-s390: failed to commit memory region\n"); + pr_warn("failed to commit memory region\n"); return; } -- cgit v1.2.3 From e194bbdf362ba7d53cfd23ba24f1a7c90ef69a74 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 4 Jun 2015 09:51:50 +0200 Subject: kvm: x86: default legacy PCI device assignment support to "n" VFIO has proved itself a much better option than KVM's built-in device assignment. It is mature, provides better isolation because it enforces ACS, and even the userspace code is being tested on a wider variety of hardware these days than the legacy support. Disable legacy device assignment by default. Signed-off-by: Paolo Bonzini --- arch/x86/kvm/Kconfig | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 413a7bf9efbb..a0f06a5947c5 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -88,13 +88,14 @@ config KVM_MMU_AUDIT config KVM_DEVICE_ASSIGNMENT bool "KVM legacy PCI device assignment support" depends on KVM && PCI && IOMMU_API - default y + default n ---help--- Provide support for legacy PCI device assignment through KVM. The kernel now also supports a full featured userspace device driver - framework through VFIO, which supersedes much of this support. + framework through VFIO, which supersedes this support and provides + better security. - If unsure, say Y. + If unsure, say N. # OK, it's a little counter-intuitive to do this, but it puts it neatly under # the virtualization menu. -- cgit v1.2.3 From ce40cd3fc7fa40a6119e5fe6c0f2bc0eb4541009 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Sat, 30 May 2015 14:31:24 +0200 Subject: kvm: x86: fix kvm_apic_has_events to check for NULL pointer Malicious (or egregiously buggy) userspace can trigger it, but it should never happen in normal operation. Signed-off-by: Paolo Bonzini --- arch/x86/kvm/lapic.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 71b150cae5f9..9d8fcde52027 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -150,7 +150,7 @@ static inline bool kvm_apic_vid_enabled(struct kvm *kvm) static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu) { - return vcpu->arch.apic->pending_events; + return kvm_vcpu_has_lapic(vcpu) && vcpu->arch.apic->pending_events; } static inline bool kvm_lowest_prio_delivery(struct kvm_lapic_irq *irq) -- cgit v1.2.3 From e69fab5df45f993cb3b8cc0625a7791e86450a99 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 4 Jun 2015 10:44:44 +0200 Subject: KVM: x86: clear hidden CPU state at reset time This was noticed by Radim while reviewing the implementation of system management mode. Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 79dde1656db6..bd6bcd54cd44 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7254,6 +7254,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { + vcpu->arch.hflags = 0; + atomic_set(&vcpu->arch.nmi_queued, 0); vcpu->arch.nmi_pending = 0; vcpu->arch.nmi_injected = false; -- cgit v1.2.3 From 62ef68bb4d00f1a662e487f3fc44ce8521c416aa Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 5 May 2015 12:08:55 +0200 Subject: KVM: x86: introduce num_emulated_msrs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We will want to filter away MSR_IA32_SMBASE from the emulated_msrs if the host CPU does not support SMM virtualization. Introduce the logic to do that, and also move paravirt MSRs to emulated_msrs for simplicity and to get rid of KVM_SAVE_MSRS_BEGIN. Reviewed-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 40 +++++++++++++++++++++++++++------------- 1 file changed, 27 insertions(+), 13 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index bd6bcd54cd44..7119b3b510c4 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -925,17 +925,11 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc); * * This list is modified at module load time to reflect the * capabilities of the host cpu. This capabilities test skips MSRs that are - * kvm-specific. Those are put in the beginning of the list. + * kvm-specific. Those are put in emulated_msrs; filtering of emulated_msrs + * may depend on host virtualization features rather than host cpu features. */ -#define KVM_SAVE_MSRS_BEGIN 12 static u32 msrs_to_save[] = { - MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, - MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, - HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, - HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, - HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, - MSR_KVM_PV_EOI_EN, MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_STAR, #ifdef CONFIG_X86_64 @@ -947,7 +941,14 @@ static u32 msrs_to_save[] = { static unsigned num_msrs_to_save; -static const u32 emulated_msrs[] = { +static u32 emulated_msrs[] = { + MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, + MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, + HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, + HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, + HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, + MSR_KVM_PV_EOI_EN, + MSR_IA32_TSC_ADJUST, MSR_IA32_TSCDEADLINE, MSR_IA32_MISC_ENABLE, @@ -955,6 +956,8 @@ static const u32 emulated_msrs[] = { MSR_IA32_MCG_CTL, }; +static unsigned num_emulated_msrs; + bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) { if (efer & efer_reserved_bits) @@ -2928,7 +2931,7 @@ long kvm_arch_dev_ioctl(struct file *filp, if (copy_from_user(&msr_list, user_msr_list, sizeof msr_list)) goto out; n = msr_list.nmsrs; - msr_list.nmsrs = num_msrs_to_save + ARRAY_SIZE(emulated_msrs); + msr_list.nmsrs = num_msrs_to_save + num_emulated_msrs; if (copy_to_user(user_msr_list, &msr_list, sizeof msr_list)) goto out; r = -E2BIG; @@ -2940,7 +2943,7 @@ long kvm_arch_dev_ioctl(struct file *filp, goto out; if (copy_to_user(user_msr_list->indices + num_msrs_to_save, &emulated_msrs, - ARRAY_SIZE(emulated_msrs) * sizeof(u32))) + num_emulated_msrs * sizeof(u32))) goto out; r = 0; break; @@ -4206,8 +4209,7 @@ static void kvm_init_msr_list(void) u32 dummy[2]; unsigned i, j; - /* skip the first msrs in the list. KVM-specific */ - for (i = j = KVM_SAVE_MSRS_BEGIN; i < ARRAY_SIZE(msrs_to_save); i++) { + for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) { if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0) continue; @@ -4232,6 +4234,18 @@ static void kvm_init_msr_list(void) j++; } num_msrs_to_save = j; + + for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) { + switch (emulated_msrs[i]) { + default: + break; + } + + if (j < i) + emulated_msrs[j] = emulated_msrs[i]; + j++; + } + num_emulated_msrs = j; } static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, -- cgit v1.2.3 From 609e36d372ad9329269e4a1467bd35311893d1d6 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 8 Apr 2015 15:30:38 +0200 Subject: KVM: x86: pass host_initiated to functions that read MSRs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit SMBASE is only readable from SMM for the VCPU, but it must be always accessible if userspace is accessing it. Thus, all functions that read MSRs are changed to accept a struct msr_data; the host_initiated and index fields are pre-initialized, while the data field is filled on return. Reviewed-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 6 +-- arch/x86/kvm/svm.c | 54 ++++++++++---------- arch/x86/kvm/vmx.c | 62 ++++++++++++----------- arch/x86/kvm/x86.c | 106 ++++++++++++++++++++++++---------------- 4 files changed, 127 insertions(+), 101 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 7276107b35df..4e299fcd0eb6 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -721,7 +721,7 @@ struct kvm_x86_ops { void (*vcpu_put)(struct kvm_vcpu *vcpu); void (*update_db_bp_intercept)(struct kvm_vcpu *vcpu); - int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); + int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr); 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, @@ -941,7 +941,7 @@ static inline int emulate_instruction(struct kvm_vcpu *vcpu, void kvm_enable_efer_bits(u64); bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer); -int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data); +int kvm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr); int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr); struct x86_emulate_ctxt; @@ -970,7 +970,7 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw); 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_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr); int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr); unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index b9f9e1073e50..a08df4145173 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -3069,42 +3069,42 @@ static u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) svm_scale_tsc(vcpu, host_tsc); } -static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) +static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct vcpu_svm *svm = to_svm(vcpu); - switch (ecx) { + switch (msr_info->index) { case MSR_IA32_TSC: { - *data = svm->vmcb->control.tsc_offset + + msr_info->data = svm->vmcb->control.tsc_offset + svm_scale_tsc(vcpu, native_read_tsc()); break; } case MSR_STAR: - *data = svm->vmcb->save.star; + msr_info->data = svm->vmcb->save.star; break; #ifdef CONFIG_X86_64 case MSR_LSTAR: - *data = svm->vmcb->save.lstar; + msr_info->data = svm->vmcb->save.lstar; break; case MSR_CSTAR: - *data = svm->vmcb->save.cstar; + msr_info->data = svm->vmcb->save.cstar; break; case MSR_KERNEL_GS_BASE: - *data = svm->vmcb->save.kernel_gs_base; + msr_info->data = svm->vmcb->save.kernel_gs_base; break; case MSR_SYSCALL_MASK: - *data = svm->vmcb->save.sfmask; + msr_info->data = svm->vmcb->save.sfmask; break; #endif case MSR_IA32_SYSENTER_CS: - *data = svm->vmcb->save.sysenter_cs; + msr_info->data = svm->vmcb->save.sysenter_cs; break; case MSR_IA32_SYSENTER_EIP: - *data = svm->sysenter_eip; + msr_info->data = svm->sysenter_eip; break; case MSR_IA32_SYSENTER_ESP: - *data = svm->sysenter_esp; + msr_info->data = svm->sysenter_esp; break; /* * Nobody will change the following 5 values in the VMCB so we can @@ -3112,31 +3112,31 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) * implemented. */ case MSR_IA32_DEBUGCTLMSR: - *data = svm->vmcb->save.dbgctl; + msr_info->data = svm->vmcb->save.dbgctl; break; case MSR_IA32_LASTBRANCHFROMIP: - *data = svm->vmcb->save.br_from; + msr_info->data = svm->vmcb->save.br_from; break; case MSR_IA32_LASTBRANCHTOIP: - *data = svm->vmcb->save.br_to; + msr_info->data = svm->vmcb->save.br_to; break; case MSR_IA32_LASTINTFROMIP: - *data = svm->vmcb->save.last_excp_from; + msr_info->data = svm->vmcb->save.last_excp_from; break; case MSR_IA32_LASTINTTOIP: - *data = svm->vmcb->save.last_excp_to; + msr_info->data = svm->vmcb->save.last_excp_to; break; case MSR_VM_HSAVE_PA: - *data = svm->nested.hsave_msr; + msr_info->data = svm->nested.hsave_msr; break; case MSR_VM_CR: - *data = svm->nested.vm_cr_msr; + msr_info->data = svm->nested.vm_cr_msr; break; case MSR_IA32_UCODE_REV: - *data = 0x01000065; + msr_info->data = 0x01000065; break; default: - return kvm_get_msr_common(vcpu, ecx, data); + return kvm_get_msr_common(vcpu, msr_info); } return 0; } @@ -3144,16 +3144,20 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) static int rdmsr_interception(struct vcpu_svm *svm) { u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX); - u64 data; + struct msr_data msr_info; - if (svm_get_msr(&svm->vcpu, ecx, &data)) { + msr_info.index = ecx; + msr_info.host_initiated = false; + if (svm_get_msr(&svm->vcpu, &msr_info)) { trace_kvm_msr_read_ex(ecx); kvm_inject_gp(&svm->vcpu, 0); } else { - trace_kvm_msr_read(ecx, data); + trace_kvm_msr_read(ecx, msr_info.data); - kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, data & 0xffffffff); - kvm_register_write(&svm->vcpu, VCPU_REGS_RDX, data >> 32); + kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, + msr_info.data & 0xffffffff); + kvm_register_write(&svm->vcpu, VCPU_REGS_RDX, + msr_info.data >> 32); svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; skip_emulated_instruction(&svm->vcpu); } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 9cf5030927d5..b5b7b8ab2f59 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2622,76 +2622,69 @@ static int vmx_get_vmx_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_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) +static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { - u64 data; struct shared_msr_entry *msr; - if (!pdata) { - printk(KERN_ERR "BUG: get_msr called with NULL pdata\n"); - return -EINVAL; - } - - switch (msr_index) { + switch (msr_info->index) { #ifdef CONFIG_X86_64 case MSR_FS_BASE: - data = vmcs_readl(GUEST_FS_BASE); + msr_info->data = vmcs_readl(GUEST_FS_BASE); break; case MSR_GS_BASE: - data = vmcs_readl(GUEST_GS_BASE); + msr_info->data = vmcs_readl(GUEST_GS_BASE); break; case MSR_KERNEL_GS_BASE: vmx_load_host_state(to_vmx(vcpu)); - data = to_vmx(vcpu)->msr_guest_kernel_gs_base; + msr_info->data = to_vmx(vcpu)->msr_guest_kernel_gs_base; break; #endif case MSR_EFER: - return kvm_get_msr_common(vcpu, msr_index, pdata); + return kvm_get_msr_common(vcpu, msr_info); case MSR_IA32_TSC: - data = guest_read_tsc(); + msr_info->data = guest_read_tsc(); break; case MSR_IA32_SYSENTER_CS: - data = vmcs_read32(GUEST_SYSENTER_CS); + msr_info->data = vmcs_read32(GUEST_SYSENTER_CS); break; case MSR_IA32_SYSENTER_EIP: - data = vmcs_readl(GUEST_SYSENTER_EIP); + msr_info->data = vmcs_readl(GUEST_SYSENTER_EIP); break; case MSR_IA32_SYSENTER_ESP: - data = vmcs_readl(GUEST_SYSENTER_ESP); + msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP); break; case MSR_IA32_BNDCFGS: if (!vmx_mpx_supported()) return 1; - data = vmcs_read64(GUEST_BNDCFGS); + msr_info->data = vmcs_read64(GUEST_BNDCFGS); break; case MSR_IA32_FEATURE_CONTROL: if (!nested_vmx_allowed(vcpu)) return 1; - data = to_vmx(vcpu)->nested.msr_ia32_feature_control; + msr_info->data = to_vmx(vcpu)->nested.msr_ia32_feature_control; break; case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: if (!nested_vmx_allowed(vcpu)) return 1; - return vmx_get_vmx_msr(vcpu, msr_index, pdata); + return vmx_get_vmx_msr(vcpu, msr_info->index, &msr_info->data); case MSR_IA32_XSS: if (!vmx_xsaves_supported()) return 1; - data = vcpu->arch.ia32_xss; + msr_info->data = vcpu->arch.ia32_xss; break; case MSR_TSC_AUX: if (!to_vmx(vcpu)->rdtscp_enabled) return 1; /* Otherwise falls through */ default: - msr = find_msr_entry(to_vmx(vcpu), msr_index); + msr = find_msr_entry(to_vmx(vcpu), msr_info->index); if (msr) { - data = msr->data; + msr_info->data = msr->data; break; } - return kvm_get_msr_common(vcpu, msr_index, pdata); + return kvm_get_msr_common(vcpu, msr_info); } - *pdata = data; return 0; } @@ -5473,19 +5466,21 @@ static int handle_cpuid(struct kvm_vcpu *vcpu) static int handle_rdmsr(struct kvm_vcpu *vcpu) { u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX]; - u64 data; + struct msr_data msr_info; - if (vmx_get_msr(vcpu, ecx, &data)) { + msr_info.index = ecx; + msr_info.host_initiated = false; + if (vmx_get_msr(vcpu, &msr_info)) { trace_kvm_msr_read_ex(ecx); kvm_inject_gp(vcpu, 0); return 1; } - trace_kvm_msr_read(ecx, data); + trace_kvm_msr_read(ecx, msr_info.data); /* FIXME: handling of bits 32:63 of rax, rdx */ - vcpu->arch.regs[VCPU_REGS_RAX] = data & -1u; - vcpu->arch.regs[VCPU_REGS_RDX] = (data >> 32) & -1u; + vcpu->arch.regs[VCPU_REGS_RAX] = msr_info.data & -1u; + vcpu->arch.regs[VCPU_REGS_RDX] = (msr_info.data >> 32) & -1u; skip_emulated_instruction(vcpu); return 1; } @@ -9147,6 +9142,7 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) struct vmx_msr_entry e; for (i = 0; i < count; i++) { + struct msr_data msr_info; if (kvm_read_guest(vcpu->kvm, gpa + i * sizeof(e), &e, 2 * sizeof(u32))) { @@ -9161,7 +9157,9 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) __func__, i, e.index, e.reserved); return -EINVAL; } - if (kvm_get_msr(vcpu, e.index, &e.value)) { + msr_info.host_initiated = false; + msr_info.index = e.index; + if (kvm_get_msr(vcpu, &msr_info)) { pr_warn_ratelimited( "%s cannot read MSR (%u, 0x%x)\n", __func__, i, e.index); @@ -9170,10 +9168,10 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) if (kvm_write_guest(vcpu->kvm, gpa + i * sizeof(e) + offsetof(struct vmx_msr_entry, value), - &e.value, sizeof(e.value))) { + &msr_info.data, sizeof(msr_info.data))) { pr_warn_ratelimited( "%s cannot write MSR (%u, 0x%x, 0x%llx)\n", - __func__, i, e.index, e.value); + __func__, i, e.index, msr_info.data); return -EINVAL; } } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7119b3b510c4..3632928191f3 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1051,6 +1051,21 @@ EXPORT_SYMBOL_GPL(kvm_set_msr); /* * Adapt set_msr() to msr_io()'s calling convention */ +static int do_get_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) +{ + struct msr_data msr; + int r; + + msr.index = index; + msr.host_initiated = true; + r = kvm_get_msr(vcpu, &msr); + if (r) + return r; + + *data = msr.data; + return 0; +} + static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) { struct msr_data msr; @@ -2448,9 +2463,9 @@ EXPORT_SYMBOL_GPL(kvm_set_msr_common); * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ -int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) +int kvm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { - return kvm_x86_ops->get_msr(vcpu, msr_index, pdata); + return kvm_x86_ops->get_msr(vcpu, msr); } EXPORT_SYMBOL_GPL(kvm_get_msr); @@ -2587,11 +2602,11 @@ static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) return 0; } -int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { u64 data; - switch (msr) { + switch (msr_info->index) { case MSR_IA32_PLATFORM_ID: case MSR_IA32_EBL_CR_POWERON: case MSR_IA32_DEBUGCTLMSR: @@ -2614,26 +2629,26 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_AMD64_NB_CFG: case MSR_FAM10H_MMIO_CONF_BASE: case MSR_AMD64_BU_CFG2: - data = 0; + msr_info->data = 0; break; case MSR_P6_PERFCTR0: case MSR_P6_PERFCTR1: case MSR_P6_EVNTSEL0: case MSR_P6_EVNTSEL1: - if (kvm_pmu_msr(vcpu, msr)) - return kvm_pmu_get_msr(vcpu, msr, pdata); - data = 0; + if (kvm_pmu_msr(vcpu, msr_info->index)) + return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data); + msr_info->data = 0; break; case MSR_IA32_UCODE_REV: - data = 0x100000000ULL; + msr_info->data = 0x100000000ULL; break; case MSR_MTRRcap: - data = 0x500 | KVM_NR_VAR_MTRR; + msr_info->data = 0x500 | KVM_NR_VAR_MTRR; break; case 0x200 ... 0x2ff: - return get_msr_mtrr(vcpu, msr, pdata); + return get_msr_mtrr(vcpu, msr_info->index, &msr_info->data); case 0xcd: /* fsb frequency */ - data = 3; + msr_info->data = 3; break; /* * MSR_EBC_FREQUENCY_ID @@ -2647,48 +2662,48 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) * multiplying by zero otherwise. */ case MSR_EBC_FREQUENCY_ID: - data = 1 << 24; + msr_info->data = 1 << 24; break; case MSR_IA32_APICBASE: - data = kvm_get_apic_base(vcpu); + msr_info->data = kvm_get_apic_base(vcpu); break; case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: - return kvm_x2apic_msr_read(vcpu, msr, pdata); + return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data); break; case MSR_IA32_TSCDEADLINE: - data = kvm_get_lapic_tscdeadline_msr(vcpu); + msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu); break; case MSR_IA32_TSC_ADJUST: - data = (u64)vcpu->arch.ia32_tsc_adjust_msr; + msr_info->data = (u64)vcpu->arch.ia32_tsc_adjust_msr; break; case MSR_IA32_MISC_ENABLE: - data = vcpu->arch.ia32_misc_enable_msr; + msr_info->data = vcpu->arch.ia32_misc_enable_msr; break; case MSR_IA32_PERF_STATUS: /* TSC increment by tick */ - data = 1000ULL; + msr_info->data = 1000ULL; /* CPU multiplier */ data |= (((uint64_t)4ULL) << 40); break; case MSR_EFER: - data = vcpu->arch.efer; + msr_info->data = vcpu->arch.efer; break; case MSR_KVM_WALL_CLOCK: case MSR_KVM_WALL_CLOCK_NEW: - data = vcpu->kvm->arch.wall_clock; + msr_info->data = vcpu->kvm->arch.wall_clock; break; case MSR_KVM_SYSTEM_TIME: case MSR_KVM_SYSTEM_TIME_NEW: - data = vcpu->arch.time; + msr_info->data = vcpu->arch.time; break; case MSR_KVM_ASYNC_PF_EN: - data = vcpu->arch.apf.msr_val; + msr_info->data = vcpu->arch.apf.msr_val; break; case MSR_KVM_STEAL_TIME: - data = vcpu->arch.st.msr_val; + msr_info->data = vcpu->arch.st.msr_val; break; case MSR_KVM_PV_EOI_EN: - data = vcpu->arch.pv_eoi.msr_val; + msr_info->data = vcpu->arch.pv_eoi.msr_val; break; case MSR_IA32_P5_MC_ADDR: case MSR_IA32_P5_MC_TYPE: @@ -2696,7 +2711,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_IA32_MCG_CTL: case MSR_IA32_MCG_STATUS: case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: - return get_msr_mce(vcpu, msr, pdata); + return get_msr_mce(vcpu, msr_info->index, &msr_info->data); case MSR_K7_CLK_CTL: /* * Provide expected ramp-up count for K7. All other @@ -2707,17 +2722,17 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) * type 6, model 8 and higher from exploding due to * the rdmsr failing. */ - data = 0x20000000; + msr_info->data = 0x20000000; break; case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: - if (kvm_hv_msr_partition_wide(msr)) { + if (kvm_hv_msr_partition_wide(msr_info->index)) { int r; mutex_lock(&vcpu->kvm->lock); - r = get_msr_hyperv_pw(vcpu, msr, pdata); + r = get_msr_hyperv_pw(vcpu, msr_info->index, &msr_info->data); mutex_unlock(&vcpu->kvm->lock); return r; } else - return get_msr_hyperv(vcpu, msr, pdata); + return get_msr_hyperv(vcpu, msr_info->index, &msr_info->data); break; case MSR_IA32_BBL_CR_CTL3: /* This legacy MSR exists but isn't fully documented in current @@ -2730,31 +2745,30 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) * L2 cache control register 3: 64GB range, 256KB size, * enabled, latency 0x1, configured */ - data = 0xbe702111; + msr_info->data = 0xbe702111; break; case MSR_AMD64_OSVW_ID_LENGTH: if (!guest_cpuid_has_osvw(vcpu)) return 1; - data = vcpu->arch.osvw.length; + msr_info->data = vcpu->arch.osvw.length; break; case MSR_AMD64_OSVW_STATUS: if (!guest_cpuid_has_osvw(vcpu)) return 1; - data = vcpu->arch.osvw.status; + msr_info->data = vcpu->arch.osvw.status; break; default: - if (kvm_pmu_msr(vcpu, msr)) - return kvm_pmu_get_msr(vcpu, msr, pdata); + if (kvm_pmu_msr(vcpu, msr_info->index)) + return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data); if (!ignore_msrs) { - vcpu_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr); + vcpu_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr_info->index); return 1; } else { - vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr); - data = 0; + vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr_info->index); + msr_info->data = 0; } break; } - *pdata = data; return 0; } EXPORT_SYMBOL_GPL(kvm_get_msr_common); @@ -3525,7 +3539,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_GET_MSRS: - r = msr_io(vcpu, argp, kvm_get_msr, 1); + r = msr_io(vcpu, argp, do_get_msr, 1); break; case KVM_SET_MSRS: r = msr_io(vcpu, argp, do_set_msr, 0); @@ -5056,7 +5070,17 @@ static void emulator_set_segment(struct x86_emulate_ctxt *ctxt, u16 selector, static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata) { - return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata); + struct msr_data msr; + int r; + + msr.index = msr_index; + msr.host_initiated = false; + r = kvm_get_msr(emul_to_vcpu(ctxt), &msr); + if (r) + return r; + + *pdata = msr.data; + return 0; } static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, -- cgit v1.2.3 From a584539b24b87dc8be83a713006396cabec47833 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 1 Apr 2015 18:18:53 +0200 Subject: KVM: x86: pass the whole hflags field to emulator and back MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The hflags field will contain information about system management mode and will be useful for the emulator. Pass the entire field rather than just the guest-mode information. Reviewed-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_emulate.h | 5 ++++- arch/x86/kvm/emulate.c | 6 +++--- arch/x86/kvm/x86.c | 10 +++++++++- 3 files changed, 16 insertions(+), 5 deletions(-) diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 57a9d94fe160..7410879a41f7 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -262,6 +262,9 @@ enum x86emul_mode { X86EMUL_MODE_PROT64, /* 64-bit (long) mode. */ }; +/* These match some of the HF_* flags defined in kvm_host.h */ +#define X86EMUL_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */ + struct x86_emulate_ctxt { const struct x86_emulate_ops *ops; @@ -273,8 +276,8 @@ struct x86_emulate_ctxt { /* interruptibility state, as a result of execution of STI or MOV SS */ int interruptibility; + int emul_flags; - bool guest_mode; /* guest running a nested guest */ bool perm_ok; /* do not check permissions if true */ bool ud; /* inject an #UD if host doesn't support insn */ diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 9b655d113fc6..a1c6c25552e9 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -4895,7 +4895,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) fetch_possible_mmx_operand(ctxt, &ctxt->dst); } - if (unlikely(ctxt->guest_mode) && (ctxt->d & Intercept)) { + if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_PRE_EXCEPT); if (rc != X86EMUL_CONTINUE) @@ -4924,7 +4924,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) goto done; } - if (unlikely(ctxt->guest_mode) && (ctxt->d & Intercept)) { + if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_POST_EXCEPT); if (rc != X86EMUL_CONTINUE) @@ -4978,7 +4978,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) special_insn: - if (unlikely(ctxt->guest_mode) && (ctxt->d & Intercept)) { + if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_POST_MEMACCESS); if (rc != X86EMUL_CONTINUE) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3632928191f3..7aec25f2f45c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5240,7 +5240,8 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) (cs_l && is_long_mode(vcpu)) ? X86EMUL_MODE_PROT64 : cs_db ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; - ctxt->guest_mode = is_guest_mode(vcpu); + BUILD_BUG_ON(HF_GUEST_MASK != X86EMUL_GUEST_MASK); + ctxt->emul_flags = vcpu->arch.hflags; init_decode_cache(ctxt); vcpu->arch.emulate_regs_need_sync_from_vcpu = false; @@ -5409,6 +5410,11 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, static int complete_emulated_mmio(struct kvm_vcpu *vcpu); static int complete_emulated_pio(struct kvm_vcpu *vcpu); +void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags) +{ + vcpu->arch.hflags = emul_flags; +} + static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7, unsigned long *db) { @@ -5608,6 +5614,8 @@ restart: unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; + if (vcpu->arch.hflags != ctxt->emul_flags) + kvm_set_hflags(vcpu, ctxt->emul_flags); kvm_rip_write(vcpu, ctxt->eip); if (r == EMULATE_DONE) kvm_vcpu_check_singlestep(vcpu, rflags, &r); -- cgit v1.2.3 From f077825a8758d79838a757dafb79adcdd047ef3a Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 1 Apr 2015 15:06:40 +0200 Subject: KVM: x86: API changes for SMM support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch includes changes to the external API for SMM support. Userspace can predicate the availability of the new fields and ioctls on a new capability, KVM_CAP_X86_SMM, which is added at the end of the patch series. Reviewed-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- Documentation/virtual/kvm/api.txt | 40 +++++++++++++++++++++++++++++++++------ arch/x86/include/asm/kvm_host.h | 3 +++ arch/x86/include/uapi/asm/kvm.h | 11 ++++++++++- arch/x86/kvm/kvm_cache_regs.h | 5 +++++ arch/x86/kvm/lapic.h | 5 +++++ arch/x86/kvm/x86.c | 40 +++++++++++++++++++++++++++++++++++++-- include/uapi/linux/kvm.h | 5 ++++- 7 files changed, 99 insertions(+), 10 deletions(-) diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 695544420ff2..2ddefd58b1aa 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -820,11 +820,21 @@ struct kvm_vcpu_events { } nmi; __u32 sipi_vector; __u32 flags; + struct { + __u8 smm; + __u8 pending; + __u8 smm_inside_nmi; + __u8 latched_init; + } smi; }; -KVM_VCPUEVENT_VALID_SHADOW may be set in the flags field to signal that -interrupt.shadow contains a valid state. Otherwise, this field is undefined. +Only two fields are defined in the flags field: + +- KVM_VCPUEVENT_VALID_SHADOW may be set in the flags field to signal that + interrupt.shadow contains a valid state. +- KVM_VCPUEVENT_VALID_SMM may be set in the flags field to signal that + smi contains a valid state. 4.32 KVM_SET_VCPU_EVENTS @@ -841,17 +851,20 @@ vcpu. See KVM_GET_VCPU_EVENTS for the data structure. Fields that may be modified asynchronously by running VCPUs can be excluded -from the update. These fields are nmi.pending and sipi_vector. Keep the -corresponding bits in the flags field cleared to suppress overwriting the -current in-kernel state. The bits are: +from the update. These fields are nmi.pending, sipi_vector, smi.smm, +smi.pending. Keep the corresponding bits in the flags field cleared to +suppress overwriting the current in-kernel state. The bits are: KVM_VCPUEVENT_VALID_NMI_PENDING - transfer nmi.pending to the kernel KVM_VCPUEVENT_VALID_SIPI_VECTOR - transfer sipi_vector +KVM_VCPUEVENT_VALID_SMM - transfer the smi sub-struct. If KVM_CAP_INTR_SHADOW is available, KVM_VCPUEVENT_VALID_SHADOW can be set in the flags field to signal that interrupt.shadow contains a valid state and shall be written into the VCPU. +KVM_VCPUEVENT_VALID_SMM can only be set if KVM_CAP_X86_SMM is available. + 4.33 KVM_GET_DEBUGREGS @@ -2979,6 +2992,16 @@ len must be a multiple of sizeof(struct kvm_s390_irq). It must be > 0 and it must not exceed (max_vcpus + 32) * sizeof(struct kvm_s390_irq), which is the maximum number of possibly pending cpu-local interrupts. +4.90 KVM_SMI + +Capability: KVM_CAP_X86_SMM +Architectures: x86 +Type: vcpu ioctl +Parameters: none +Returns: 0 on success, -1 on error + +Queues an SMI on the thread's vcpu. + 5. The kvm_run structure ------------------------ @@ -3014,7 +3037,12 @@ an interrupt can be injected now with KVM_INTERRUPT. The value of the current interrupt flag. Only valid if in-kernel local APIC is not used. - __u8 padding2[2]; + __u16 flags; + +More architecture-specific flags detailing state of the VCPU that may +affect the device's behavior. The only currently defined flag is +KVM_RUN_X86_SMM, which is valid on x86 machines and is set if the +VCPU is in system management mode. /* in (pre_kvm_run), out (post_kvm_run) */ __u64 cr8; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 4e299fcd0eb6..d52d7aea375f 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -471,6 +471,7 @@ struct kvm_vcpu_arch { atomic_t nmi_queued; /* unprocessed asynchronous NMIs */ unsigned nmi_pending; /* NMI queued after currently running handler */ bool nmi_injected; /* Trying to inject an NMI this entry */ + bool smi_pending; /* SMI queued after currently running handler */ struct mtrr_state_type mtrr_state; u64 pat; @@ -1115,6 +1116,8 @@ enum { #define HF_NMI_MASK (1 << 3) #define HF_IRET_MASK (1 << 4) #define HF_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */ +#define HF_SMM_MASK (1 << 6) +#define HF_SMM_INSIDE_NMI_MASK (1 << 7) /* * Hardware virtualization extension instructions may fault if a diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 2fec75e4b1e1..a4ae82eb82aa 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -106,6 +106,8 @@ struct kvm_ioapic_state { #define KVM_IRQCHIP_IOAPIC 2 #define KVM_NR_IRQCHIPS 3 +#define KVM_RUN_X86_SMM (1 << 0) + /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */ @@ -281,6 +283,7 @@ struct kvm_reinject_control { #define KVM_VCPUEVENT_VALID_NMI_PENDING 0x00000001 #define KVM_VCPUEVENT_VALID_SIPI_VECTOR 0x00000002 #define KVM_VCPUEVENT_VALID_SHADOW 0x00000004 +#define KVM_VCPUEVENT_VALID_SMM 0x00000008 /* Interrupt shadow states */ #define KVM_X86_SHADOW_INT_MOV_SS 0x01 @@ -309,7 +312,13 @@ struct kvm_vcpu_events { } nmi; __u32 sipi_vector; __u32 flags; - __u32 reserved[10]; + struct { + __u8 smm; + __u8 pending; + __u8 smm_inside_nmi; + __u8 latched_init; + } smi; + __u32 reserved[9]; }; /* for KVM_GET/SET_DEBUGREGS */ diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 544076c4f44b..e1e89ee4af75 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -99,4 +99,9 @@ static inline bool is_guest_mode(struct kvm_vcpu *vcpu) return vcpu->arch.hflags & HF_GUEST_MASK; } +static inline bool is_smm(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.hflags & HF_SMM_MASK; +} + #endif diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 9d8fcde52027..f2f4e10ab772 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -159,6 +159,11 @@ static inline bool kvm_lowest_prio_delivery(struct kvm_lapic_irq *irq) irq->msi_redir_hint); } +static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_has_lapic(vcpu) && test_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); +} + bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector); void wait_lapic_expire(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7aec25f2f45c..aa46ac1ff48b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3101,6 +3101,11 @@ static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu) return 0; } +static int kvm_vcpu_ioctl_smi(struct kvm_vcpu *vcpu) +{ + return 0; +} + static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu, struct kvm_tpr_access_ctl *tac) { @@ -3206,8 +3211,15 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, events->sipi_vector = 0; /* never valid when reporting to user space */ + events->smi.smm = is_smm(vcpu); + events->smi.pending = vcpu->arch.smi_pending; + events->smi.smm_inside_nmi = + !!(vcpu->arch.hflags & HF_SMM_INSIDE_NMI_MASK); + events->smi.latched_init = kvm_lapic_latched_init(vcpu); + events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING - | KVM_VCPUEVENT_VALID_SHADOW); + | KVM_VCPUEVENT_VALID_SHADOW + | KVM_VCPUEVENT_VALID_SMM); memset(&events->reserved, 0, sizeof(events->reserved)); } @@ -3216,7 +3228,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, { if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING | KVM_VCPUEVENT_VALID_SIPI_VECTOR - | KVM_VCPUEVENT_VALID_SHADOW)) + | KVM_VCPUEVENT_VALID_SHADOW + | KVM_VCPUEVENT_VALID_SMM)) return -EINVAL; process_nmi(vcpu); @@ -3241,6 +3254,24 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, kvm_vcpu_has_lapic(vcpu)) vcpu->arch.apic->sipi_vector = events->sipi_vector; + if (events->flags & KVM_VCPUEVENT_VALID_SMM) { + if (events->smi.smm) + vcpu->arch.hflags |= HF_SMM_MASK; + else + vcpu->arch.hflags &= ~HF_SMM_MASK; + vcpu->arch.smi_pending = events->smi.pending; + if (events->smi.smm_inside_nmi) + vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; + else + vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK; + if (kvm_vcpu_has_lapic(vcpu)) { + if (events->smi.latched_init) + set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + else + clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + } + } + kvm_make_request(KVM_REQ_EVENT, vcpu); return 0; @@ -3500,6 +3531,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_vcpu_ioctl_nmi(vcpu); break; } + case KVM_SMI: { + r = kvm_vcpu_ioctl_smi(vcpu); + break; + } case KVM_SET_CPUID: { struct kvm_cpuid __user *cpuid_arg = argp; struct kvm_cpuid cpuid; @@ -6182,6 +6217,7 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; kvm_run->if_flag = (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0; + kvm_run->flags = is_smm(vcpu) ? KVM_RUN_X86_SMM : 0; kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); if (irqchip_in_kernel(vcpu->kvm)) diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 75bd9f7fd846..eace8babd227 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -202,7 +202,7 @@ struct kvm_run { __u32 exit_reason; __u8 ready_for_interrupt_injection; __u8 if_flag; - __u8 padding2[2]; + __u16 flags; /* in (pre_kvm_run), out (post_kvm_run) */ __u64 cr8; @@ -815,6 +815,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_S390_IRQ_STATE 114 #define KVM_CAP_PPC_HWRNG 115 #define KVM_CAP_DISABLE_QUIRKS 116 +#define KVM_CAP_X86_SMM 117 #ifdef KVM_CAP_IRQ_ROUTING @@ -1200,6 +1201,8 @@ struct kvm_s390_ucas_mapping { /* Available with KVM_CAP_S390_IRQ_STATE */ #define KVM_S390_SET_IRQ_STATE _IOW(KVMIO, 0xb5, struct kvm_s390_irq_state) #define KVM_S390_GET_IRQ_STATE _IOW(KVMIO, 0xb6, struct kvm_s390_irq_state) +/* Available with KVM_CAP_X86_SMM */ +#define KVM_SMI _IO(KVMIO, 0xb7) #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) #define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) -- cgit v1.2.3 From 64d6067057d9658acb8675afcfba549abdb7fc16 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 7 May 2015 11:36:11 +0200 Subject: KVM: x86: stubs for SMM support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds the interface between x86.c and the emulator: the SMBASE register, a new emulator flag, the RSM instruction. It also adds a new request bit that will be used by the KVM_SMI ioctl. Reviewed-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_emulate.h | 4 +++ arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/emulate.c | 10 +++++- arch/x86/kvm/lapic.c | 4 ++- arch/x86/kvm/svm.c | 1 + arch/x86/kvm/x86.c | 64 ++++++++++++++++++++++++++++++++++++-- include/linux/kvm_host.h | 1 + 7 files changed, 81 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 7410879a41f7..e16466ec473c 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -193,6 +193,8 @@ struct x86_emulate_ops { int (*cpl)(struct x86_emulate_ctxt *ctxt); int (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest); int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value); + u64 (*get_smbase)(struct x86_emulate_ctxt *ctxt); + void (*set_smbase)(struct x86_emulate_ctxt *ctxt, u64 smbase); int (*set_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data); int (*get_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata); int (*check_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc); @@ -264,6 +266,8 @@ enum x86emul_mode { /* These match some of the HF_* flags defined in kvm_host.h */ #define X86EMUL_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */ +#define X86EMUL_SMM_MASK (1 << 6) +#define X86EMUL_SMM_INSIDE_NMI_MASK (1 << 7) struct x86_emulate_ctxt { const struct x86_emulate_ops *ops; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d52d7aea375f..12a7318887ad 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -368,6 +368,7 @@ struct kvm_vcpu_arch { int32_t apic_arb_prio; int mp_state; u64 ia32_misc_enable_msr; + u64 smbase; bool tpr_access_reporting; u64 ia32_xss; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index a1c6c25552e9..e763a9b8c26b 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2259,6 +2259,14 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt) return rc; } +static int em_rsm(struct x86_emulate_ctxt *ctxt) +{ + if ((ctxt->emul_flags & X86EMUL_SMM_MASK) == 0) + return emulate_ud(ctxt); + + return X86EMUL_UNHANDLEABLE; +} + static void setup_syscalls_segments(struct x86_emulate_ctxt *ctxt, struct desc_struct *cs, struct desc_struct *ss) @@ -4197,7 +4205,7 @@ static const struct opcode twobyte_table[256] = { F(DstMem | SrcReg | Src2CL | ModRM, em_shld), N, N, /* 0xA8 - 0xAF */ I(Stack | Src2GS, em_push_sreg), I(Stack | Src2GS, em_pop_sreg), - DI(ImplicitOps, rsm), + II(No64 | EmulateOnUD | ImplicitOps, em_rsm, rsm), F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts), F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shrd), F(DstMem | SrcReg | Src2CL | ModRM, em_shrd), diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index c789e00dfa8b..b8e47e2b1d94 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -808,7 +808,9 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, break; case APIC_DM_SMI: - apic_debug("Ignoring guest SMI\n"); + result = 1; + kvm_make_request(KVM_REQ_SMI, vcpu); + kvm_vcpu_kick(vcpu); break; case APIC_DM_NMI: diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index a08df4145173..c48748cf638e 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -3394,6 +3394,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_MWAIT] = mwait_interception, [SVM_EXIT_XSETBV] = xsetbv_interception, [SVM_EXIT_NPF] = pf_interception, + [SVM_EXIT_RSM] = emulate_on_interception, }; static void dump_vmcb(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index aa46ac1ff48b..ab977e763812 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -954,6 +954,7 @@ static u32 emulated_msrs[] = { MSR_IA32_MISC_ENABLE, MSR_IA32_MCG_STATUS, MSR_IA32_MCG_CTL, + MSR_IA32_SMBASE, }; static unsigned num_emulated_msrs; @@ -2282,6 +2283,11 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_MISC_ENABLE: vcpu->arch.ia32_misc_enable_msr = data; break; + case MSR_IA32_SMBASE: + if (!msr_info->host_initiated) + return 1; + vcpu->arch.smbase = data; + break; case MSR_KVM_WALL_CLOCK_NEW: case MSR_KVM_WALL_CLOCK: vcpu->kvm->arch.wall_clock = data; @@ -2679,6 +2685,11 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_MISC_ENABLE: msr_info->data = vcpu->arch.ia32_misc_enable_msr; break; + case MSR_IA32_SMBASE: + if (!msr_info->host_initiated) + return 1; + msr_info->data = vcpu->arch.smbase; + break; case MSR_IA32_PERF_STATUS: /* TSC increment by tick */ msr_info->data = 1000ULL; @@ -3103,6 +3114,8 @@ static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu) static int kvm_vcpu_ioctl_smi(struct kvm_vcpu *vcpu) { + kvm_make_request(KVM_REQ_SMI, vcpu); + return 0; } @@ -5129,6 +5142,20 @@ static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, return kvm_set_msr(emul_to_vcpu(ctxt), &msr); } +static u64 emulator_get_smbase(struct x86_emulate_ctxt *ctxt) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + + return vcpu->arch.smbase; +} + +static void emulator_set_smbase(struct x86_emulate_ctxt *ctxt, u64 smbase) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + + vcpu->arch.smbase = smbase; +} + static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt, u32 pmc) { @@ -5214,6 +5241,8 @@ static const struct x86_emulate_ops emulate_ops = { .cpl = emulator_get_cpl, .get_dr = emulator_get_dr, .set_dr = emulator_set_dr, + .get_smbase = emulator_get_smbase, + .set_smbase = emulator_set_smbase, .set_msr = emulator_set_msr, .get_msr = emulator_get_msr, .check_pmc = emulator_check_pmc, @@ -5276,6 +5305,8 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) cs_db ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; BUILD_BUG_ON(HF_GUEST_MASK != X86EMUL_GUEST_MASK); + BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK); + BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK); ctxt->emul_flags = vcpu->arch.hflags; init_decode_cache(ctxt); @@ -5445,9 +5476,24 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, static int complete_emulated_mmio(struct kvm_vcpu *vcpu); static int complete_emulated_pio(struct kvm_vcpu *vcpu); -void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags) +static void kvm_smm_changed(struct kvm_vcpu *vcpu) { + if (!(vcpu->arch.hflags & HF_SMM_MASK)) { + if (unlikely(vcpu->arch.smi_pending)) { + kvm_make_request(KVM_REQ_SMI, vcpu); + vcpu->arch.smi_pending = 0; + } + } +} + +static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags) +{ + unsigned changed = vcpu->arch.hflags ^ emul_flags; + vcpu->arch.hflags = emul_flags; + + if (changed & HF_SMM_MASK) + kvm_smm_changed(vcpu); } static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7, @@ -6341,6 +6387,16 @@ static void process_nmi(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); } +static void process_smi(struct kvm_vcpu *vcpu) +{ + if (is_smm(vcpu)) { + vcpu->arch.smi_pending = true; + return; + } + + printk_once(KERN_DEBUG "Ignoring guest SMI\n"); +} + static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) { u64 eoi_exit_bitmap[4]; @@ -6449,6 +6505,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu)) record_steal_time(vcpu); + if (kvm_check_request(KVM_REQ_SMI, vcpu)) + process_smi(vcpu); if (kvm_check_request(KVM_REQ_NMI, vcpu)) process_nmi(vcpu); if (kvm_check_request(KVM_REQ_PMU, vcpu)) @@ -7363,8 +7421,10 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_async_pf_hash_reset(vcpu); vcpu->arch.apf.halted = false; - if (!init_event) + if (!init_event) { kvm_pmu_reset(vcpu); + vcpu->arch.smbase = 0x30000; + } memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs)); vcpu->arch.regs_avail = ~0; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a8bcbc9c6078..b019fee6d941 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -134,6 +134,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_ENABLE_IBS 23 #define KVM_REQ_DISABLE_IBS 24 #define KVM_REQ_APIC_PAGE_RELOAD 25 +#define KVM_REQ_SMI 26 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 -- cgit v1.2.3 From cd7764fe9f73530b20a0f2310fa753af635fabb3 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 4 Jun 2015 10:41:21 +0200 Subject: KVM: x86: latch INITs while in system management mode MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Do not process INITs immediately while in system management mode, keep it instead in apic->pending_events. Tell userspace if an INIT is pending when they issue GET_VCPU_EVENTS, and similarly handle the new field in SET_VCPU_EVENTS. Note that the same treatment should be done while in VMX non-root mode. Reviewed-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- arch/x86/kvm/lapic.c | 13 ++++++++++++- arch/x86/kvm/x86.c | 3 +++ 2 files changed, 15 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index b8e47e2b1d94..beeef05bb4d9 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2057,8 +2057,19 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) if (!kvm_vcpu_has_lapic(vcpu) || !apic->pending_events) return; - pe = xchg(&apic->pending_events, 0); + /* + * INITs are latched while in SMM. Because an SMM CPU cannot + * be in KVM_MP_STATE_INIT_RECEIVED state, just eat SIPIs + * and delay processing of INIT until the next RSM. + */ + if (is_smm(vcpu)) { + WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED); + if (test_bit(KVM_APIC_SIPI, &apic->pending_events)) + clear_bit(KVM_APIC_SIPI, &apic->pending_events); + return; + } + pe = xchg(&apic->pending_events, 0); if (test_bit(KVM_APIC_INIT, &pe)) { kvm_lapic_reset(vcpu, true); kvm_vcpu_reset(vcpu, true); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ab977e763812..ab2521b588d8 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5482,6 +5482,9 @@ static void kvm_smm_changed(struct kvm_vcpu *vcpu) if (unlikely(vcpu->arch.smi_pending)) { kvm_make_request(KVM_REQ_SMI, vcpu); vcpu->arch.smi_pending = 0; + } else { + /* Process a latched INIT, if any. */ + kvm_make_request(KVM_REQ_EVENT, vcpu); } } } -- cgit v1.2.3 From 660a5d517aaab9187f93854425c4c63f4a09195c Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 5 May 2015 11:50:23 +0200 Subject: KVM: x86: save/load state on SMM switch MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The big ugly one. This patch adds support for switching in and out of system management mode, respectively upon receiving KVM_REQ_SMI and upon executing a RSM instruction. Both 32- and 64-bit formats are supported for the SMM state save area. Reviewed-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.h | 8 ++ arch/x86/kvm/emulate.c | 248 ++++++++++++++++++++++++++++++++++++++++++++++++- arch/x86/kvm/trace.h | 22 +++++ arch/x86/kvm/x86.c | 222 ++++++++++++++++++++++++++++++++++++++++++- 4 files changed, 498 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 496b3695d3d3..dd05b9cef6ae 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -70,6 +70,14 @@ static inline bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu) return best && (best->ebx & bit(X86_FEATURE_FSGSBASE)); } +static inline bool guest_cpuid_has_longmode(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); + return best && (best->edx & bit(X86_FEATURE_LM)); +} + static inline bool guest_cpuid_has_osvw(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index e763a9b8c26b..e7a4fde5d631 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2259,12 +2259,258 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt) return rc; } +static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt) +{ + u32 eax, ebx, ecx, edx; + + eax = 0x80000001; + ecx = 0; + ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx); + return edx & bit(X86_FEATURE_LM); +} + +#define GET_SMSTATE(type, smbase, offset) \ + ({ \ + type __val; \ + int r = ctxt->ops->read_std(ctxt, smbase + offset, &__val, \ + sizeof(__val), NULL); \ + if (r != X86EMUL_CONTINUE) \ + return X86EMUL_UNHANDLEABLE; \ + __val; \ + }) + +static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags) +{ + desc->g = (flags >> 23) & 1; + desc->d = (flags >> 22) & 1; + desc->l = (flags >> 21) & 1; + desc->avl = (flags >> 20) & 1; + desc->p = (flags >> 15) & 1; + desc->dpl = (flags >> 13) & 3; + desc->s = (flags >> 12) & 1; + desc->type = (flags >> 8) & 15; +} + +static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, u64 smbase, int n) +{ + struct desc_struct desc; + int offset; + u16 selector; + + selector = GET_SMSTATE(u32, smbase, 0x7fa8 + n * 4); + + if (n < 3) + offset = 0x7f84 + n * 12; + else + offset = 0x7f2c + (n - 3) * 12; + + set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8)); + set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4)); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, offset)); + ctxt->ops->set_segment(ctxt, selector, &desc, 0, n); + return X86EMUL_CONTINUE; +} + +static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n) +{ + struct desc_struct desc; + int offset; + u16 selector; + u32 base3; + + offset = 0x7e00 + n * 16; + + selector = GET_SMSTATE(u16, smbase, offset); + rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smbase, offset + 2) << 8); + set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4)); + set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8)); + base3 = GET_SMSTATE(u32, smbase, offset + 12); + + ctxt->ops->set_segment(ctxt, selector, &desc, base3, n); + return X86EMUL_CONTINUE; +} + +static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt, + u64 cr0, u64 cr4) +{ + int bad; + + /* + * First enable PAE, long mode needs it before CR0.PG = 1 is set. + * Then enable protected mode. However, PCID cannot be enabled + * if EFER.LMA=0, so set it separately. + */ + bad = ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE); + if (bad) + return X86EMUL_UNHANDLEABLE; + + bad = ctxt->ops->set_cr(ctxt, 0, cr0); + if (bad) + return X86EMUL_UNHANDLEABLE; + + if (cr4 & X86_CR4_PCIDE) { + bad = ctxt->ops->set_cr(ctxt, 4, cr4); + if (bad) + return X86EMUL_UNHANDLEABLE; + } + + return X86EMUL_CONTINUE; +} + +static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase) +{ + struct desc_struct desc; + struct desc_ptr dt; + u16 selector; + u32 val, cr0, cr4; + int i; + + cr0 = GET_SMSTATE(u32, smbase, 0x7ffc); + ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u32, smbase, 0x7ff8)); + ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED; + ctxt->_eip = GET_SMSTATE(u32, smbase, 0x7ff0); + + for (i = 0; i < 8; i++) + *reg_write(ctxt, i) = GET_SMSTATE(u32, smbase, 0x7fd0 + i * 4); + + val = GET_SMSTATE(u32, smbase, 0x7fcc); + ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1); + val = GET_SMSTATE(u32, smbase, 0x7fc8); + ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1); + + selector = GET_SMSTATE(u32, smbase, 0x7fc4); + set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f64)); + set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f60)); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f5c)); + ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR); + + selector = GET_SMSTATE(u32, smbase, 0x7fc0); + set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f80)); + set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f7c)); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f78)); + ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR); + + dt.address = GET_SMSTATE(u32, smbase, 0x7f74); + dt.size = GET_SMSTATE(u32, smbase, 0x7f70); + ctxt->ops->set_gdt(ctxt, &dt); + + dt.address = GET_SMSTATE(u32, smbase, 0x7f58); + dt.size = GET_SMSTATE(u32, smbase, 0x7f54); + ctxt->ops->set_idt(ctxt, &dt); + + for (i = 0; i < 6; i++) { + int r = rsm_load_seg_32(ctxt, smbase, i); + if (r != X86EMUL_CONTINUE) + return r; + } + + cr4 = GET_SMSTATE(u32, smbase, 0x7f14); + + ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8)); + + return rsm_enter_protected_mode(ctxt, cr0, cr4); +} + +static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase) +{ + struct desc_struct desc; + struct desc_ptr dt; + u64 val, cr0, cr4; + u32 base3; + u16 selector; + int i; + + for (i = 0; i < 16; i++) + *reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8); + + ctxt->_eip = GET_SMSTATE(u64, smbase, 0x7f78); + ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7f70) | X86_EFLAGS_FIXED; + + val = GET_SMSTATE(u32, smbase, 0x7f68); + ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1); + val = GET_SMSTATE(u32, smbase, 0x7f60); + ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1); + + cr0 = GET_SMSTATE(u64, smbase, 0x7f58); + ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u64, smbase, 0x7f50)); + cr4 = GET_SMSTATE(u64, smbase, 0x7f48); + ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00)); + val = GET_SMSTATE(u64, smbase, 0x7ed0); + ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA); + + selector = GET_SMSTATE(u32, smbase, 0x7e90); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e92) << 8); + set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e94)); + set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e98)); + base3 = GET_SMSTATE(u32, smbase, 0x7e9c); + ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR); + + dt.size = GET_SMSTATE(u32, smbase, 0x7e84); + dt.address = GET_SMSTATE(u64, smbase, 0x7e88); + ctxt->ops->set_idt(ctxt, &dt); + + selector = GET_SMSTATE(u32, smbase, 0x7e70); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e72) << 8); + set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e74)); + set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e78)); + base3 = GET_SMSTATE(u32, smbase, 0x7e7c); + ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR); + + dt.size = GET_SMSTATE(u32, smbase, 0x7e64); + dt.address = GET_SMSTATE(u64, smbase, 0x7e68); + ctxt->ops->set_gdt(ctxt, &dt); + + for (i = 0; i < 6; i++) { + int r = rsm_load_seg_64(ctxt, smbase, i); + if (r != X86EMUL_CONTINUE) + return r; + } + + return rsm_enter_protected_mode(ctxt, cr0, cr4); +} + static int em_rsm(struct x86_emulate_ctxt *ctxt) { + unsigned long cr0, cr4, efer; + u64 smbase; + int ret; + if ((ctxt->emul_flags & X86EMUL_SMM_MASK) == 0) return emulate_ud(ctxt); - return X86EMUL_UNHANDLEABLE; + /* + * Get back to real mode, to prepare a safe state in which to load + * CR0/CR3/CR4/EFER. Also this will ensure that addresses passed + * to read_std/write_std are not virtual. + * + * CR4.PCIDE must be zero, because it is a 64-bit mode only feature. + */ + cr0 = ctxt->ops->get_cr(ctxt, 0); + if (cr0 & X86_CR0_PE) + ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE)); + cr4 = ctxt->ops->get_cr(ctxt, 4); + if (cr4 & X86_CR4_PAE) + ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE); + efer = 0; + ctxt->ops->set_msr(ctxt, MSR_EFER, efer); + + smbase = ctxt->ops->get_smbase(ctxt); + if (emulator_has_longmode(ctxt)) + ret = rsm_load_state_64(ctxt, smbase + 0x8000); + else + ret = rsm_load_state_32(ctxt, smbase + 0x8000); + + if (ret != X86EMUL_CONTINUE) { + /* FIXME: should triple fault */ + return X86EMUL_UNHANDLEABLE; + } + + if ((ctxt->emul_flags & X86EMUL_SMM_INSIDE_NMI_MASK) == 0) + ctxt->ops->set_nmi_mask(ctxt, false); + + ctxt->emul_flags &= ~X86EMUL_SMM_INSIDE_NMI_MASK; + ctxt->emul_flags &= ~X86EMUL_SMM_MASK; + return X86EMUL_CONTINUE; } static void diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 7c7bc8bef21f..4eae7c35ddf5 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -952,6 +952,28 @@ TRACE_EVENT(kvm_wait_lapic_expire, __entry->delta < 0 ? "early" : "late") ); +TRACE_EVENT(kvm_enter_smm, + TP_PROTO(unsigned int vcpu_id, u64 smbase, bool entering), + TP_ARGS(vcpu_id, smbase, entering), + + TP_STRUCT__entry( + __field( unsigned int, vcpu_id ) + __field( u64, smbase ) + __field( bool, entering ) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->smbase = smbase; + __entry->entering = entering; + ), + + TP_printk("vcpu %u: %s SMM, smbase 0x%llx", + __entry->vcpu_id, + __entry->entering ? "entering" : "leaving", + __entry->smbase) +); + #endif /* _TRACE_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ab2521b588d8..51d994e1d6af 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5479,6 +5479,9 @@ static int complete_emulated_pio(struct kvm_vcpu *vcpu); static void kvm_smm_changed(struct kvm_vcpu *vcpu) { if (!(vcpu->arch.hflags & HF_SMM_MASK)) { + /* This is a good place to trace that we are exiting SMM. */ + trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, false); + if (unlikely(vcpu->arch.smi_pending)) { kvm_make_request(KVM_REQ_SMI, vcpu); vcpu->arch.smi_pending = 0; @@ -6390,14 +6393,231 @@ static void process_nmi(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); } +#define put_smstate(type, buf, offset, val) \ + *(type *)((buf) + (offset) - 0x7e00) = val + +static u32 process_smi_get_segment_flags(struct kvm_segment *seg) +{ + u32 flags = 0; + flags |= seg->g << 23; + flags |= seg->db << 22; + flags |= seg->l << 21; + flags |= seg->avl << 20; + flags |= seg->present << 15; + flags |= seg->dpl << 13; + flags |= seg->s << 12; + flags |= seg->type << 8; + return flags; +} + +static void process_smi_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n) +{ + struct kvm_segment seg; + int offset; + + kvm_get_segment(vcpu, &seg, n); + put_smstate(u32, buf, 0x7fa8 + n * 4, seg.selector); + + if (n < 3) + offset = 0x7f84 + n * 12; + else + offset = 0x7f2c + (n - 3) * 12; + + put_smstate(u32, buf, offset + 8, seg.base); + put_smstate(u32, buf, offset + 4, seg.limit); + put_smstate(u32, buf, offset, process_smi_get_segment_flags(&seg)); +} + +static void process_smi_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n) +{ + struct kvm_segment seg; + int offset; + u16 flags; + + kvm_get_segment(vcpu, &seg, n); + offset = 0x7e00 + n * 16; + + flags = process_smi_get_segment_flags(&seg) >> 8; + put_smstate(u16, buf, offset, seg.selector); + put_smstate(u16, buf, offset + 2, flags); + put_smstate(u32, buf, offset + 4, seg.limit); + put_smstate(u64, buf, offset + 8, seg.base); +} + +static void process_smi_save_state_32(struct kvm_vcpu *vcpu, char *buf) +{ + struct desc_ptr dt; + struct kvm_segment seg; + unsigned long val; + int i; + + put_smstate(u32, buf, 0x7ffc, kvm_read_cr0(vcpu)); + put_smstate(u32, buf, 0x7ff8, kvm_read_cr3(vcpu)); + put_smstate(u32, buf, 0x7ff4, kvm_get_rflags(vcpu)); + put_smstate(u32, buf, 0x7ff0, kvm_rip_read(vcpu)); + + for (i = 0; i < 8; i++) + put_smstate(u32, buf, 0x7fd0 + i * 4, kvm_register_read(vcpu, i)); + + kvm_get_dr(vcpu, 6, &val); + put_smstate(u32, buf, 0x7fcc, (u32)val); + kvm_get_dr(vcpu, 7, &val); + put_smstate(u32, buf, 0x7fc8, (u32)val); + + kvm_get_segment(vcpu, &seg, VCPU_SREG_TR); + put_smstate(u32, buf, 0x7fc4, seg.selector); + put_smstate(u32, buf, 0x7f64, seg.base); + put_smstate(u32, buf, 0x7f60, seg.limit); + put_smstate(u32, buf, 0x7f5c, process_smi_get_segment_flags(&seg)); + + kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR); + put_smstate(u32, buf, 0x7fc0, seg.selector); + put_smstate(u32, buf, 0x7f80, seg.base); + put_smstate(u32, buf, 0x7f7c, seg.limit); + put_smstate(u32, buf, 0x7f78, process_smi_get_segment_flags(&seg)); + + kvm_x86_ops->get_gdt(vcpu, &dt); + put_smstate(u32, buf, 0x7f74, dt.address); + put_smstate(u32, buf, 0x7f70, dt.size); + + kvm_x86_ops->get_idt(vcpu, &dt); + put_smstate(u32, buf, 0x7f58, dt.address); + put_smstate(u32, buf, 0x7f54, dt.size); + + for (i = 0; i < 6; i++) + process_smi_save_seg_32(vcpu, buf, i); + + put_smstate(u32, buf, 0x7f14, kvm_read_cr4(vcpu)); + + /* revision id */ + put_smstate(u32, buf, 0x7efc, 0x00020000); + put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase); +} + +static void process_smi_save_state_64(struct kvm_vcpu *vcpu, char *buf) +{ +#ifdef CONFIG_X86_64 + struct desc_ptr dt; + struct kvm_segment seg; + unsigned long val; + int i; + + for (i = 0; i < 16; i++) + put_smstate(u64, buf, 0x7ff8 - i * 8, kvm_register_read(vcpu, i)); + + put_smstate(u64, buf, 0x7f78, kvm_rip_read(vcpu)); + put_smstate(u32, buf, 0x7f70, kvm_get_rflags(vcpu)); + + kvm_get_dr(vcpu, 6, &val); + put_smstate(u64, buf, 0x7f68, val); + kvm_get_dr(vcpu, 7, &val); + put_smstate(u64, buf, 0x7f60, val); + + put_smstate(u64, buf, 0x7f58, kvm_read_cr0(vcpu)); + put_smstate(u64, buf, 0x7f50, kvm_read_cr3(vcpu)); + put_smstate(u64, buf, 0x7f48, kvm_read_cr4(vcpu)); + + put_smstate(u32, buf, 0x7f00, vcpu->arch.smbase); + + /* revision id */ + put_smstate(u32, buf, 0x7efc, 0x00020064); + + put_smstate(u64, buf, 0x7ed0, vcpu->arch.efer); + + kvm_get_segment(vcpu, &seg, VCPU_SREG_TR); + put_smstate(u16, buf, 0x7e90, seg.selector); + put_smstate(u16, buf, 0x7e92, process_smi_get_segment_flags(&seg) >> 8); + put_smstate(u32, buf, 0x7e94, seg.limit); + put_smstate(u64, buf, 0x7e98, seg.base); + + kvm_x86_ops->get_idt(vcpu, &dt); + put_smstate(u32, buf, 0x7e84, dt.size); + put_smstate(u64, buf, 0x7e88, dt.address); + + kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR); + put_smstate(u16, buf, 0x7e70, seg.selector); + put_smstate(u16, buf, 0x7e72, process_smi_get_segment_flags(&seg) >> 8); + put_smstate(u32, buf, 0x7e74, seg.limit); + put_smstate(u64, buf, 0x7e78, seg.base); + + kvm_x86_ops->get_gdt(vcpu, &dt); + put_smstate(u32, buf, 0x7e64, dt.size); + put_smstate(u64, buf, 0x7e68, dt.address); + + for (i = 0; i < 6; i++) + process_smi_save_seg_64(vcpu, buf, i); +#else + WARN_ON_ONCE(1); +#endif +} + static void process_smi(struct kvm_vcpu *vcpu) { + struct kvm_segment cs, ds; + char buf[512]; + u32 cr0; + if (is_smm(vcpu)) { vcpu->arch.smi_pending = true; return; } - printk_once(KERN_DEBUG "Ignoring guest SMI\n"); + trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true); + vcpu->arch.hflags |= HF_SMM_MASK; + memset(buf, 0, 512); + if (guest_cpuid_has_longmode(vcpu)) + process_smi_save_state_64(vcpu, buf); + else + process_smi_save_state_32(vcpu, buf); + + kvm_write_guest(vcpu->kvm, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf)); + + if (kvm_x86_ops->get_nmi_mask(vcpu)) + vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; + else + kvm_x86_ops->set_nmi_mask(vcpu, true); + + kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); + kvm_rip_write(vcpu, 0x8000); + + cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG); + kvm_x86_ops->set_cr0(vcpu, cr0); + vcpu->arch.cr0 = cr0; + + kvm_x86_ops->set_cr4(vcpu, 0); + + __kvm_set_dr(vcpu, 7, DR7_FIXED_1); + + cs.selector = (vcpu->arch.smbase >> 4) & 0xffff; + cs.base = vcpu->arch.smbase; + + ds.selector = 0; + ds.base = 0; + + cs.limit = ds.limit = 0xffffffff; + cs.type = ds.type = 0x3; + cs.dpl = ds.dpl = 0; + cs.db = ds.db = 0; + cs.s = ds.s = 1; + cs.l = ds.l = 0; + cs.g = ds.g = 1; + cs.avl = ds.avl = 0; + cs.present = ds.present = 1; + cs.unusable = ds.unusable = 0; + cs.padding = ds.padding = 0; + + kvm_set_segment(vcpu, &cs, VCPU_SREG_CS); + kvm_set_segment(vcpu, &ds, VCPU_SREG_DS); + kvm_set_segment(vcpu, &ds, VCPU_SREG_ES); + kvm_set_segment(vcpu, &ds, VCPU_SREG_FS); + kvm_set_segment(vcpu, &ds, VCPU_SREG_GS); + kvm_set_segment(vcpu, &ds, VCPU_SREG_SS); + + if (guest_cpuid_has_longmode(vcpu)) + kvm_x86_ops->set_efer(vcpu, 0); + + kvm_update_cpuid(vcpu); + kvm_mmu_reset_context(vcpu); } static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) -- cgit v1.2.3 From 8e73485c7959fd25650761eab04db1e72ea14c23 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Sun, 17 May 2015 13:58:53 +0200 Subject: KVM: add vcpu-specific functions to read/write/translate GFNs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We need to hide SMRAM from guests not running in SMM. Therefore, all uses of kvm_read_guest* and kvm_write_guest* must be changed to use different address spaces, depending on whether the VCPU is in system management mode. We need to introduce a new family of functions for this purpose. For now, the VCPU-based functions have the same behavior as the existing per-VM ones, they just accept a different type for the first argument. Later however they will be changed to use one of many "struct kvm_memslots" stored in struct kvm, through an architecture hook. VM-based functions will unconditionally use the first memslots pointer. Whenever possible, this patch introduces slot-based functions with an __ prefix, with two wrappers for generic and vcpu-based actions. The exceptions are kvm_read_guest and kvm_write_guest, which are copied into the new functions kvm_vcpu_read_guest and kvm_vcpu_write_guest. Reviewed-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 24 +++++++ virt/kvm/kvm_main.c | 167 +++++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 178 insertions(+), 13 deletions(-) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index b019fee6d941..ba1ea43998e4 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -471,6 +471,11 @@ static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) || lockdep_is_held(&kvm->slots_lock)); } +static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu) +{ + return kvm_memslots(vcpu->kvm); +} + static inline struct kvm_memory_slot * id_to_memslot(struct kvm_memslots *slots, int id) { @@ -576,6 +581,25 @@ int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); +struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); +struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn); +pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn); +pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); +struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn); +unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn); +unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable); +int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset, + int len); +int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, + unsigned long len); +int kvm_vcpu_read_guest(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, + unsigned long len); +int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, const void *data, + int offset, int len); +int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data, + unsigned long len); +void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); + void kvm_vcpu_block(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); int kvm_vcpu_yield_to(struct kvm_vcpu *target); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 6c8e124006ad..3a121cedcc77 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1100,6 +1100,11 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(gfn_to_memslot); +struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + return __gfn_to_memslot(kvm_vcpu_memslots(vcpu), gfn); +} + int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) { struct kvm_memory_slot *memslot = gfn_to_memslot(kvm, gfn); @@ -1175,6 +1180,12 @@ unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(gfn_to_hva); +unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + return gfn_to_hva_many(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn, NULL); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_hva); + /* * If writable is set to false, the hva returned by this function is only * allowed to be read. @@ -1197,6 +1208,13 @@ unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable) return gfn_to_hva_memslot_prot(slot, gfn, writable); } +unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable) +{ + struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + + return gfn_to_hva_memslot_prot(slot, gfn, writable); +} + static int get_user_page_nowait(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, int write, struct page **page) { @@ -1412,12 +1430,24 @@ pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(gfn_to_pfn_atomic); +pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + return gfn_to_pfn_memslot_atomic(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn_atomic); + pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) { return gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn); } EXPORT_SYMBOL_GPL(gfn_to_pfn); +pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + return gfn_to_pfn_memslot(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn); + int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn, struct page **pages, int nr_pages) { @@ -1458,6 +1488,16 @@ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(gfn_to_page); +struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + pfn_t pfn; + + pfn = kvm_vcpu_gfn_to_pfn(vcpu, gfn); + + return kvm_pfn_to_page(pfn); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_page); + void kvm_release_page_clean(struct page *page) { WARN_ON(is_error_page(page)); @@ -1520,13 +1560,13 @@ static int next_segment(unsigned long len, int offset) return len; } -int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, - int len) +static int __kvm_read_guest_page(struct kvm_memory_slot *slot, gfn_t gfn, + void *data, int offset, int len) { int r; unsigned long addr; - addr = gfn_to_hva_prot(kvm, gfn, NULL); + addr = gfn_to_hva_memslot_prot(slot, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; r = __copy_from_user(data, (void __user *)addr + offset, len); @@ -1534,8 +1574,25 @@ int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, return -EFAULT; return 0; } + +int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, + int len) +{ + struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); + + return __kvm_read_guest_page(slot, gfn, data, offset, len); +} EXPORT_SYMBOL_GPL(kvm_read_guest_page); +int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, + int offset, int len) +{ + struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + + return __kvm_read_guest_page(slot, gfn, data, offset, len); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_page); + int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len) { gfn_t gfn = gpa >> PAGE_SHIFT; @@ -1556,15 +1613,33 @@ int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len) } EXPORT_SYMBOL_GPL(kvm_read_guest); -int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data, - unsigned long len) +int kvm_vcpu_read_guest(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, unsigned long len) { - int r; - unsigned long addr; gfn_t gfn = gpa >> PAGE_SHIFT; + int seg; int offset = offset_in_page(gpa); + int ret; + + while ((seg = next_segment(len, offset)) != 0) { + ret = kvm_vcpu_read_guest_page(vcpu, gfn, data, offset, seg); + if (ret < 0) + return ret; + offset = 0; + len -= seg; + data += seg; + ++gfn; + } + return 0; +} +EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest); - addr = gfn_to_hva_prot(kvm, gfn, NULL); +static int __kvm_read_guest_atomic(struct kvm_memory_slot *slot, gfn_t gfn, + void *data, int offset, unsigned long len) +{ + int r; + unsigned long addr; + + addr = gfn_to_hva_memslot_prot(slot, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; pagefault_disable(); @@ -1574,16 +1649,35 @@ int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data, return -EFAULT; return 0; } -EXPORT_SYMBOL(kvm_read_guest_atomic); -int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, - int offset, int len) +int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data, + unsigned long len) +{ + gfn_t gfn = gpa >> PAGE_SHIFT; + struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); + int offset = offset_in_page(gpa); + + return __kvm_read_guest_atomic(slot, gfn, data, offset, len); +} +EXPORT_SYMBOL_GPL(kvm_read_guest_atomic); + +int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa, + void *data, unsigned long len) +{ + gfn_t gfn = gpa >> PAGE_SHIFT; + struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + int offset = offset_in_page(gpa); + + return __kvm_read_guest_atomic(slot, gfn, data, offset, len); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_atomic); + +static int __kvm_write_guest_page(struct kvm_memory_slot *memslot, gfn_t gfn, + const void *data, int offset, int len) { int r; - struct kvm_memory_slot *memslot; unsigned long addr; - memslot = gfn_to_memslot(kvm, gfn); addr = gfn_to_hva_memslot(memslot, gfn); if (kvm_is_error_hva(addr)) return -EFAULT; @@ -1593,8 +1687,25 @@ int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, mark_page_dirty_in_slot(memslot, gfn); return 0; } + +int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, + const void *data, int offset, int len) +{ + struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); + + return __kvm_write_guest_page(slot, gfn, data, offset, len); +} EXPORT_SYMBOL_GPL(kvm_write_guest_page); +int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, + const void *data, int offset, int len) +{ + struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + + return __kvm_write_guest_page(slot, gfn, data, offset, len); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_write_guest_page); + int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, unsigned long len) { @@ -1616,6 +1727,27 @@ int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, } EXPORT_SYMBOL_GPL(kvm_write_guest); +int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data, + unsigned long len) +{ + gfn_t gfn = gpa >> PAGE_SHIFT; + int seg; + int offset = offset_in_page(gpa); + int ret; + + while ((seg = next_segment(len, offset)) != 0) { + ret = kvm_vcpu_write_guest_page(vcpu, gfn, data, offset, seg); + if (ret < 0) + return ret; + offset = 0; + len -= seg; + data += seg; + ++gfn; + } + return 0; +} +EXPORT_SYMBOL_GPL(kvm_vcpu_write_guest); + int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, gpa_t gpa, unsigned long len) { @@ -1750,6 +1882,15 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(mark_page_dirty); +void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + struct kvm_memory_slot *memslot; + + memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + mark_page_dirty_in_slot(memslot, gfn); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_mark_page_dirty); + static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu) { if (kvm_arch_vcpu_runnable(vcpu)) { -- cgit v1.2.3 From f481b069e674378758c73761827e83ab05c46b52 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Sun, 17 May 2015 17:30:37 +0200 Subject: KVM: implement multiple address spaces MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Only two ioctls have to be modified; the address space id is placed in the higher 16 bits of their slot id argument. As of this patch, no architecture defines more than one address space; x86 will be the first. Reviewed-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- Documentation/virtual/kvm/api.txt | 12 ++++++ arch/powerpc/include/asm/kvm_book3s_64.h | 2 +- include/linux/kvm_host.h | 26 ++++++++++-- include/uapi/linux/kvm.h | 1 + virt/kvm/kvm_main.c | 70 ++++++++++++++++++++------------ 5 files changed, 79 insertions(+), 32 deletions(-) diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 2ddefd58b1aa..461956a0ee8e 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -254,6 +254,11 @@ since the last call to this ioctl. Bit 0 is the first page in the memory slot. Ensure the entire structure is cleared to avoid padding issues. +If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 specifies +the address space for which you want to return the dirty bitmap. +They must be less than the value that KVM_CHECK_EXTENSION returns for +the KVM_CAP_MULTI_ADDRESS_SPACE capability. + 4.9 KVM_SET_MEMORY_ALIAS @@ -924,6 +929,13 @@ slot. When changing an existing slot, it may be moved in the guest physical memory space, or its flags may be modified. It may not be resized. Slots may not overlap in guest physical address space. +If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of "slot" +specifies the address space which is being modified. They must be +less than the value that KVM_CHECK_EXTENSION returns for the +KVM_CAP_MULTI_ADDRESS_SPACE capability. Slots in separate address spaces +are unrelated; the restriction on overlapping slots only applies within +each address space. + Memory for the region is taken starting at the address denoted by the field userspace_addr, which must point at user addressable memory for the entire memory slot size. Any object may back this memory, including diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 3536d12eb798..2aa79c864e91 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -430,7 +430,7 @@ static inline void note_hpte_modification(struct kvm *kvm, */ static inline struct kvm_memslots *kvm_memslots_raw(struct kvm *kvm) { - return rcu_dereference_raw_notrace(kvm->memslots); + return rcu_dereference_raw_notrace(kvm->memslots[0]); } extern void kvmppc_mmu_debugfs_init(struct kvm *kvm); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ba1ea43998e4..9564fd78c547 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -44,6 +44,10 @@ /* Two fragments for cross MMIO pages. */ #define KVM_MAX_MMIO_FRAGMENTS 2 +#ifndef KVM_ADDRESS_SPACE_NUM +#define KVM_ADDRESS_SPACE_NUM 1 +#endif + /* * For the normal pfn, the highest 12 bits should be zero, * so we can mask bit 62 ~ bit 52 to indicate the error pfn, @@ -331,6 +335,13 @@ struct kvm_kernel_irq_routing_entry { #define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS) #endif +#ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE +static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) +{ + return 0; +} +#endif + /* * Note: * memslots are not sorted by id anymore, please use id_to_memslot() @@ -349,7 +360,7 @@ struct kvm { spinlock_t mmu_lock; struct mutex slots_lock; struct mm_struct *mm; /* userspace tied to this vm */ - struct kvm_memslots *memslots; + struct kvm_memslots *memslots[KVM_ADDRESS_SPACE_NUM]; struct srcu_struct srcu; struct srcu_struct irq_srcu; #ifdef CONFIG_KVM_APIC_ARCHITECTURE @@ -464,16 +475,23 @@ void kvm_exit(void); void kvm_get_kvm(struct kvm *kvm); void kvm_put_kvm(struct kvm *kvm); -static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) +static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id) { - return rcu_dereference_check(kvm->memslots, + return rcu_dereference_check(kvm->memslots[as_id], srcu_read_lock_held(&kvm->srcu) || lockdep_is_held(&kvm->slots_lock)); } +static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) +{ + return __kvm_memslots(kvm, 0); +} + static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu) { - return kvm_memslots(vcpu->kvm); + int as_id = kvm_arch_vcpu_memslots_id(vcpu); + + return __kvm_memslots(vcpu->kvm, as_id); } static inline struct kvm_memory_slot * diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index eace8babd227..5ff1038437e3 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -816,6 +816,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_PPC_HWRNG 115 #define KVM_CAP_DISABLE_QUIRKS 116 #define KVM_CAP_X86_SMM 117 +#define KVM_CAP_MULTI_ADDRESS_SPACE 118 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 3a121cedcc77..848af90b8091 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -518,9 +518,11 @@ static struct kvm *kvm_create_vm(unsigned long type) BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); r = -ENOMEM; - kvm->memslots = kvm_alloc_memslots(); - if (!kvm->memslots) - goto out_err_no_srcu; + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + kvm->memslots[i] = kvm_alloc_memslots(); + if (!kvm->memslots[i]) + goto out_err_no_srcu; + } if (init_srcu_struct(&kvm->srcu)) goto out_err_no_srcu; @@ -562,7 +564,8 @@ out_err_no_srcu: out_err_no_disable: for (i = 0; i < KVM_NR_BUSES; i++) kfree(kvm->buses[i]); - kvm_free_memslots(kvm, kvm->memslots); + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) + kvm_free_memslots(kvm, kvm->memslots[i]); kvm_arch_free_vm(kvm); return ERR_PTR(r); } @@ -612,7 +615,8 @@ static void kvm_destroy_vm(struct kvm *kvm) #endif kvm_arch_destroy_vm(kvm); kvm_destroy_devices(kvm); - kvm_free_memslots(kvm, kvm->memslots); + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) + kvm_free_memslots(kvm, kvm->memslots[i]); cleanup_srcu_struct(&kvm->irq_srcu); cleanup_srcu_struct(&kvm->srcu); kvm_arch_free_vm(kvm); @@ -729,9 +733,9 @@ static int check_memory_region_flags(const struct kvm_userspace_memory_region *m } static struct kvm_memslots *install_new_memslots(struct kvm *kvm, - struct kvm_memslots *slots) + int as_id, struct kvm_memslots *slots) { - struct kvm_memslots *old_memslots = kvm_memslots(kvm); + struct kvm_memslots *old_memslots = __kvm_memslots(kvm, as_id); /* * Set the low bit in the generation, which disables SPTE caching @@ -740,7 +744,7 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, WARN_ON(old_memslots->generation & 1); slots->generation = old_memslots->generation + 1; - rcu_assign_pointer(kvm->memslots, slots); + rcu_assign_pointer(kvm->memslots[as_id], slots); synchronize_srcu_expedited(&kvm->srcu); /* @@ -772,6 +776,7 @@ int __kvm_set_memory_region(struct kvm *kvm, struct kvm_memory_slot *slot; struct kvm_memory_slot old, new; struct kvm_memslots *slots = NULL, *old_memslots; + int as_id, id; enum kvm_mr_change change; r = check_memory_region_flags(mem); @@ -779,24 +784,27 @@ int __kvm_set_memory_region(struct kvm *kvm, goto out; r = -EINVAL; + as_id = mem->slot >> 16; + id = (u16)mem->slot; + /* General sanity checks */ if (mem->memory_size & (PAGE_SIZE - 1)) goto out; if (mem->guest_phys_addr & (PAGE_SIZE - 1)) goto out; /* We can read the guest memory with __xxx_user() later on. */ - if ((mem->slot < KVM_USER_MEM_SLOTS) && + if ((id < KVM_USER_MEM_SLOTS) && ((mem->userspace_addr & (PAGE_SIZE - 1)) || !access_ok(VERIFY_WRITE, (void __user *)(unsigned long)mem->userspace_addr, mem->memory_size))) goto out; - if (mem->slot >= KVM_MEM_SLOTS_NUM) + if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM) goto out; if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) goto out; - slot = id_to_memslot(kvm_memslots(kvm), mem->slot); + slot = id_to_memslot(__kvm_memslots(kvm, as_id), id); base_gfn = mem->guest_phys_addr >> PAGE_SHIFT; npages = mem->memory_size >> PAGE_SHIFT; @@ -805,7 +813,7 @@ int __kvm_set_memory_region(struct kvm *kvm, new = old = *slot; - new.id = mem->slot; + new.id = id; new.base_gfn = base_gfn; new.npages = npages; new.flags = mem->flags; @@ -840,9 +848,9 @@ int __kvm_set_memory_region(struct kvm *kvm, if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) { /* Check for overlaps */ r = -EEXIST; - kvm_for_each_memslot(slot, kvm_memslots(kvm)) { + kvm_for_each_memslot(slot, __kvm_memslots(kvm, as_id)) { if ((slot->id >= KVM_USER_MEM_SLOTS) || - (slot->id == mem->slot)) + (slot->id == id)) continue; if (!((base_gfn + npages <= slot->base_gfn) || (base_gfn >= slot->base_gfn + slot->npages))) @@ -871,13 +879,13 @@ int __kvm_set_memory_region(struct kvm *kvm, slots = kvm_kvzalloc(sizeof(struct kvm_memslots)); if (!slots) goto out_free; - memcpy(slots, kvm_memslots(kvm), sizeof(struct kvm_memslots)); + memcpy(slots, __kvm_memslots(kvm, as_id), sizeof(struct kvm_memslots)); if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) { - slot = id_to_memslot(slots, mem->slot); + slot = id_to_memslot(slots, id); slot->flags |= KVM_MEMSLOT_INVALID; - old_memslots = install_new_memslots(kvm, slots); + old_memslots = install_new_memslots(kvm, as_id, slots); /* slot was deleted or moved, clear iommu mapping */ kvm_iommu_unmap_pages(kvm, &old); @@ -909,7 +917,7 @@ int __kvm_set_memory_region(struct kvm *kvm, } update_memslots(slots, &new); - old_memslots = install_new_memslots(kvm, slots); + old_memslots = install_new_memslots(kvm, as_id, slots); kvm_arch_commit_memory_region(kvm, mem, &old, &new, change); @@ -956,7 +964,7 @@ EXPORT_SYMBOL_GPL(kvm_set_memory_region); static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem) { - if (mem->slot >= KVM_USER_MEM_SLOTS) + if ((u16)mem->slot >= KVM_USER_MEM_SLOTS) return -EINVAL; return kvm_set_memory_region(kvm, mem); @@ -967,16 +975,18 @@ int kvm_get_dirty_log(struct kvm *kvm, { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int r, i; + int r, i, as_id, id; unsigned long n; unsigned long any = 0; r = -EINVAL; - if (log->slot >= KVM_USER_MEM_SLOTS) + as_id = log->slot >> 16; + id = (u16)log->slot; + if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS) goto out; - slots = kvm_memslots(kvm); - memslot = id_to_memslot(slots, log->slot); + slots = __kvm_memslots(kvm, as_id); + memslot = id_to_memslot(slots, id); r = -ENOENT; if (!memslot->dirty_bitmap) goto out; @@ -1027,17 +1037,19 @@ int kvm_get_dirty_log_protect(struct kvm *kvm, { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int r, i; + int r, i, as_id, id; unsigned long n; unsigned long *dirty_bitmap; unsigned long *dirty_bitmap_buffer; r = -EINVAL; - if (log->slot >= KVM_USER_MEM_SLOTS) + as_id = log->slot >> 16; + id = (u16)log->slot; + if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS) goto out; - slots = kvm_memslots(kvm); - memslot = id_to_memslot(slots, log->slot); + slots = __kvm_memslots(kvm, as_id); + memslot = id_to_memslot(slots, id); dirty_bitmap = memslot->dirty_bitmap; r = -ENOENT; @@ -2619,6 +2631,10 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING case KVM_CAP_IRQ_ROUTING: return KVM_MAX_IRQ_ROUTES; +#endif +#if KVM_ADDRESS_SPACE_NUM > 1 + case KVM_CAP_MULTI_ADDRESS_SPACE: + return KVM_ADDRESS_SPACE_NUM; #endif default: break; -- cgit v1.2.3 From e4cd1da944ed9d2acd2e4ccabf61ec443735f6db Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 18 May 2015 15:11:46 +0200 Subject: KVM: x86: pass struct kvm_mmu_page to gfn_to_rmap MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is always available (with one exception in the auditing code), and with the same auditing exception the level was coming from sp->role.level. Later, the spte's role will also be used to look up the right memslots array. Reviewed-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu.c | 10 +++++----- arch/x86/kvm/mmu_audit.c | 8 ++++++-- 2 files changed, 11 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index a65ce12470f8..0d01cbbcf3eb 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1043,12 +1043,12 @@ static unsigned long *__gfn_to_rmap(gfn_t gfn, int level, /* * Take gfn and return the reverse mapping to it. */ -static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level) +static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, struct kvm_mmu_page *sp) { struct kvm_memory_slot *slot; slot = gfn_to_memslot(kvm, gfn); - return __gfn_to_rmap(gfn, level, slot); + return __gfn_to_rmap(gfn, sp->role.level, slot); } static bool rmap_can_add(struct kvm_vcpu *vcpu) @@ -1066,7 +1066,7 @@ static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) sp = page_header(__pa(spte)); kvm_mmu_page_set_gfn(sp, spte - sp->spt, gfn); - rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level); + rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp); return pte_list_add(vcpu, spte, rmapp); } @@ -1078,7 +1078,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) sp = page_header(__pa(spte)); gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt); - rmapp = gfn_to_rmap(kvm, gfn, sp->role.level); + rmapp = gfn_to_rmap(kvm, gfn, sp); pte_list_remove(spte, rmapp); } @@ -1612,7 +1612,7 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) sp = page_header(__pa(spte)); - rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level); + rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp); kvm_unmap_rmapp(vcpu->kvm, rmapp, NULL, gfn, sp->role.level, 0); kvm_flush_remote_tlbs(vcpu->kvm); diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index 368d53497314..9d99f17aa3be 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -146,7 +146,7 @@ static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) return; } - rmapp = gfn_to_rmap(kvm, gfn, rev_sp->role.level); + rmapp = gfn_to_rmap(kvm, gfn, rev_sp); if (!*rmapp) { if (!__ratelimit(&ratelimit_state)) return; @@ -191,11 +191,15 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp) unsigned long *rmapp; u64 *sptep; struct rmap_iterator iter; + struct kvm_memslots *slots; + struct kvm_memory_slot *slot; if (sp->role.direct || sp->unsync || sp->role.invalid) return; - rmapp = gfn_to_rmap(kvm, sp->gfn, PT_PAGE_TABLE_LEVEL); + slots = kvm_memslots(kvm); + slot = __gfn_to_memslot(slots, sp->gfn); + rmapp = __gfn_to_rmap(sp->gfn, PT_PAGE_TABLE_LEVEL, slot); for_each_rmap_spte(rmapp, &iter, sptep) if (is_writable_pte(*sptep)) -- cgit v1.2.3 From 54bf36aac520315385fe7623a5c3a698e993ceda Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 8 Apr 2015 15:39:23 +0200 Subject: KVM: x86: use vcpu-specific functions to read/write/translate GFNs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We need to hide SMRAM from guests not running in SMM. Therefore, all uses of kvm_read_guest* and kvm_write_guest* must be changed to check whether the VCPU is in system management mode and use a different set of memslots. Switch from kvm_* to the newly-introduced kvm_vcpu_*, which call into kvm_arch_vcpu_memslots_id. Reviewed-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/mmu.c | 62 ++++++++++++++++++++--------------------- arch/x86/kvm/mmu_audit.c | 2 +- arch/x86/kvm/paging_tmpl.h | 18 ++++++------ arch/x86/kvm/svm.c | 12 ++++---- arch/x86/kvm/vmx.c | 32 ++++++++++----------- arch/x86/kvm/x86.c | 32 ++++++++++----------- 7 files changed, 80 insertions(+), 80 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 12a7318887ad..2fd420255c2f 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -887,7 +887,7 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask); void kvm_mmu_zap_all(struct kvm *kvm); -void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm); +void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, struct kvm_memslots *slots); unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm); void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 0d01cbbcf3eb..3814f483ac45 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -223,15 +223,15 @@ static unsigned int get_mmio_spte_generation(u64 spte) return gen; } -static unsigned int kvm_current_mmio_generation(struct kvm *kvm) +static unsigned int kvm_current_mmio_generation(struct kvm_vcpu *vcpu) { - return kvm_memslots(kvm)->generation & MMIO_GEN_MASK; + return kvm_vcpu_memslots(vcpu)->generation & MMIO_GEN_MASK; } -static void mark_mmio_spte(struct kvm *kvm, u64 *sptep, u64 gfn, +static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, unsigned access) { - unsigned int gen = kvm_current_mmio_generation(kvm); + unsigned int gen = kvm_current_mmio_generation(vcpu); u64 mask = generation_mmio_spte_mask(gen); access &= ACC_WRITE_MASK | ACC_USER_MASK; @@ -258,22 +258,22 @@ static unsigned get_mmio_spte_access(u64 spte) return (spte & ~mask) & ~PAGE_MASK; } -static bool set_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn, +static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, pfn_t pfn, unsigned access) { if (unlikely(is_noslot_pfn(pfn))) { - mark_mmio_spte(kvm, sptep, gfn, access); + mark_mmio_spte(vcpu, sptep, gfn, access); return true; } return false; } -static bool check_mmio_spte(struct kvm *kvm, u64 spte) +static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte) { unsigned int kvm_gen, spte_gen; - kvm_gen = kvm_current_mmio_generation(kvm); + kvm_gen = kvm_current_mmio_generation(vcpu); spte_gen = get_mmio_spte_generation(spte); trace_check_mmio_spte(spte, kvm_gen, spte_gen); @@ -837,14 +837,14 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm->arch.indirect_shadow_pages--; } -static int has_wrprotected_page(struct kvm *kvm, +static int has_wrprotected_page(struct kvm_vcpu *vcpu, gfn_t gfn, int level) { struct kvm_memory_slot *slot; struct kvm_lpage_info *linfo; - slot = gfn_to_memslot(kvm, gfn); + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); if (slot) { linfo = lpage_info_slot(gfn, slot, level); return linfo->write_count; @@ -876,7 +876,7 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn, { struct kvm_memory_slot *slot; - slot = gfn_to_memslot(vcpu->kvm, gfn); + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); if (!slot || slot->flags & KVM_MEMSLOT_INVALID || (no_dirty_log && slot->dirty_bitmap)) slot = NULL; @@ -901,7 +901,7 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn) max_level = min(kvm_x86_ops->get_lpage_level(), host_level); for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level) - if (has_wrprotected_page(vcpu->kvm, large_gfn, level)) + if (has_wrprotected_page(vcpu, large_gfn, level)) break; return level - 1; @@ -1336,18 +1336,18 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask); } -static bool rmap_write_protect(struct kvm *kvm, u64 gfn) +static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn) { struct kvm_memory_slot *slot; unsigned long *rmapp; int i; bool write_protected = false; - slot = gfn_to_memslot(kvm, gfn); + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { rmapp = __gfn_to_rmap(gfn, i, slot); - write_protected |= __rmap_write_protect(kvm, rmapp, true); + write_protected |= __rmap_write_protect(vcpu->kvm, rmapp, true); } return write_protected; @@ -2032,7 +2032,7 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, bool protected = false; for_each_sp(pages, sp, parents, i) - protected |= rmap_write_protect(vcpu->kvm, sp->gfn); + protected |= rmap_write_protect(vcpu, sp->gfn); if (protected) kvm_flush_remote_tlbs(vcpu->kvm); @@ -2130,7 +2130,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, hlist_add_head(&sp->hash_link, &vcpu->kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)]); if (!direct) { - if (rmap_write_protect(vcpu->kvm, gfn)) + if (rmap_write_protect(vcpu, gfn)) kvm_flush_remote_tlbs(vcpu->kvm); if (level > PT_PAGE_TABLE_LEVEL && need_sync) kvm_sync_pages(vcpu, gfn); @@ -2581,7 +2581,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 spte; int ret = 0; - if (set_mmio_spte(vcpu->kvm, sptep, gfn, pfn, pte_access)) + if (set_mmio_spte(vcpu, sptep, gfn, pfn, pte_access)) return 0; spte = PT_PRESENT_MASK; @@ -2618,7 +2618,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, * be fixed if guest refault. */ if (level > PT_PAGE_TABLE_LEVEL && - has_wrprotected_page(vcpu->kvm, gfn, level)) + has_wrprotected_page(vcpu, gfn, level)) goto done; spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE; @@ -2642,7 +2642,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, } if (pte_access & ACC_WRITE_MASK) { - mark_page_dirty(vcpu->kvm, gfn); + kvm_vcpu_mark_page_dirty(vcpu, gfn); spte |= shadow_dirty_mask; } @@ -2860,7 +2860,7 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, pfn_t pfn) return 1; if (pfn == KVM_PFN_ERR_HWPOISON) { - kvm_send_hwpoison_signal(gfn_to_hva(vcpu->kvm, gfn), current); + kvm_send_hwpoison_signal(kvm_vcpu_gfn_to_hva(vcpu, gfn), current); return 0; } @@ -2883,7 +2883,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL && PageTransCompound(pfn_to_page(pfn)) && - !has_wrprotected_page(vcpu->kvm, gfn, PT_DIRECTORY_LEVEL)) { + !has_wrprotected_page(vcpu, gfn, PT_DIRECTORY_LEVEL)) { unsigned long mask; /* * mmu_notifier_retry was successful and we hold the @@ -2975,7 +2975,7 @@ fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, * Compare with set_spte where instead shadow_dirty_mask is set. */ if (cmpxchg64(sptep, spte, spte | PT_WRITABLE_MASK) == spte) - mark_page_dirty(vcpu->kvm, gfn); + kvm_vcpu_mark_page_dirty(vcpu, gfn); return true; } @@ -3430,7 +3430,7 @@ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct) gfn_t gfn = get_mmio_spte_gfn(spte); unsigned access = get_mmio_spte_access(spte); - if (!check_mmio_spte(vcpu->kvm, spte)) + if (!check_mmio_spte(vcpu, spte)) return RET_MMIO_PF_INVALID; if (direct) @@ -3502,7 +3502,7 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) arch.direct_map = vcpu->arch.mmu.direct_map; arch.cr3 = vcpu->arch.mmu.get_cr3(vcpu); - return kvm_setup_async_pf(vcpu, gva, gfn_to_hva(vcpu->kvm, gfn), &arch); + return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); } static bool can_do_async_pf(struct kvm_vcpu *vcpu) @@ -3520,7 +3520,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, struct kvm_memory_slot *slot; bool async; - slot = gfn_to_memslot(vcpu->kvm, gfn); + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); async = false; *pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, write, writable); if (!async) @@ -3633,7 +3633,7 @@ static void inject_page_fault(struct kvm_vcpu *vcpu, vcpu->arch.mmu.inject_page_fault(vcpu, fault); } -static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn, +static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, unsigned access, int *nr_present) { if (unlikely(is_mmio_spte(*sptep))) { @@ -3643,7 +3643,7 @@ static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn, } (*nr_present)++; - mark_mmio_spte(kvm, sptep, gfn, access); + mark_mmio_spte(vcpu, sptep, gfn, access); return true; } @@ -4153,7 +4153,7 @@ static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, /* Handle a 32-bit guest writing two halves of a 64-bit gpte */ *gpa &= ~(gpa_t)7; *bytes = 8; - r = kvm_read_guest(vcpu->kvm, *gpa, &gentry, 8); + r = kvm_vcpu_read_guest(vcpu, *gpa, &gentry, 8); if (r) gentry = 0; new = (const u8 *)&gentry; @@ -4779,13 +4779,13 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm) return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages)); } -void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm) +void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, struct kvm_memslots *slots) { /* * The very rare case: if the generation-number is round, * zap all shadow pages. */ - if (unlikely(kvm_current_mmio_generation(kvm) == 0)) { + if (unlikely((slots->generation & MMIO_GEN_MASK) == 0)) { printk_ratelimited(KERN_DEBUG "kvm: zapping shadow pages for mmio generation wraparound\n"); kvm_mmu_invalidate_zap_all_pages(kvm); } diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index 9d99f17aa3be..78288c15400c 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -114,7 +114,7 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level) return; gfn = kvm_mmu_page_get_gfn(sp, sptep - sp->spt); - pfn = gfn_to_pfn_atomic(vcpu->kvm, gfn); + pfn = kvm_vcpu_gfn_to_pfn_atomic(vcpu, gfn); if (is_error_pfn(pfn)) return; diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 6e6d115fe9b5..0f67d7e24800 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -256,7 +256,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, if (ret) return ret; - mark_page_dirty(vcpu->kvm, table_gfn); + kvm_vcpu_mark_page_dirty(vcpu, table_gfn); walker->ptes[level] = pte; } return 0; @@ -338,7 +338,7 @@ retry_walk: real_gfn = gpa_to_gfn(real_gfn); - host_addr = gfn_to_hva_prot(vcpu->kvm, real_gfn, + host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, real_gfn, &walker->pte_writable[walker->level - 1]); if (unlikely(kvm_is_error_hva(host_addr))) goto error; @@ -511,11 +511,11 @@ static bool FNAME(gpte_changed)(struct kvm_vcpu *vcpu, base_gpa = pte_gpa & ~mask; index = (pte_gpa - base_gpa) / sizeof(pt_element_t); - r = kvm_read_guest_atomic(vcpu->kvm, base_gpa, + r = kvm_vcpu_read_guest_atomic(vcpu, base_gpa, gw->prefetch_ptes, sizeof(gw->prefetch_ptes)); curr_pte = gw->prefetch_ptes[index]; } else - r = kvm_read_guest_atomic(vcpu->kvm, pte_gpa, + r = kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &curr_pte, sizeof(curr_pte)); return r || curr_pte != gw->ptes[level - 1]; @@ -869,8 +869,8 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) if (!rmap_can_add(vcpu)) break; - if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte, - sizeof(pt_element_t))) + if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte, + sizeof(pt_element_t))) break; FNAME(update_pte)(vcpu, sp, sptep, &gpte); @@ -956,8 +956,8 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) pte_gpa = first_pte_gpa + i * sizeof(pt_element_t); - if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte, - sizeof(pt_element_t))) + if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte, + sizeof(pt_element_t))) return -EINVAL; if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) { @@ -970,7 +970,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) pte_access &= FNAME(gpte_access)(vcpu, gpte); FNAME(protect_clean_gpte)(&pte_access, gpte); - if (sync_mmio_spte(vcpu->kvm, &sp->spt[i], gfn, pte_access, + if (sync_mmio_spte(vcpu, &sp->spt[i], gfn, pte_access, &nr_present)) continue; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index c48748cf638e..6ff1faf4a2e8 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1955,8 +1955,8 @@ static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) u64 pdpte; int ret; - ret = kvm_read_guest_page(vcpu->kvm, gpa_to_gfn(cr3), &pdpte, - offset_in_page(cr3) + index * 8, 8); + ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(cr3), &pdpte, + offset_in_page(cr3) + index * 8, 8); if (ret) return 0; return pdpte; @@ -2114,7 +2114,7 @@ static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, struct page **_page) might_sleep(); - page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT); + page = kvm_vcpu_gfn_to_page(&svm->vcpu, gpa >> PAGE_SHIFT); if (is_error_page(page)) goto error; @@ -2153,7 +2153,7 @@ static int nested_svm_intercept_ioio(struct vcpu_svm *svm) mask = (0xf >> (4 - size)) << start_bit; val = 0; - if (kvm_read_guest(svm->vcpu.kvm, gpa, &val, iopm_len)) + if (kvm_vcpu_read_guest(&svm->vcpu, gpa, &val, iopm_len)) return NESTED_EXIT_DONE; return (val & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; @@ -2178,7 +2178,7 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) /* Offset is in 32 bit units but need in 8 bit units */ offset *= 4; - if (kvm_read_guest(svm->vcpu.kvm, svm->nested.vmcb_msrpm + offset, &value, 4)) + if (kvm_vcpu_read_guest(&svm->vcpu, svm->nested.vmcb_msrpm + offset, &value, 4)) return NESTED_EXIT_DONE; return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; @@ -2449,7 +2449,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) p = msrpm_offsets[i]; offset = svm->nested.vmcb_msrpm + (p * 4); - if (kvm_read_guest(svm->vcpu.kvm, offset, &value, 4)) + if (kvm_vcpu_read_guest(&svm->vcpu, offset, &value, 4)) return false; svm->nested.msrpm[p] = svm->msrpm[p] | value; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index b5b7b8ab2f59..8c80b7d7343c 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -786,7 +786,7 @@ static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) static struct page *nested_get_page(struct kvm_vcpu *vcpu, gpa_t addr) { - struct page *page = gfn_to_page(vcpu->kvm, addr >> PAGE_SHIFT); + struct page *page = kvm_vcpu_gfn_to_page(vcpu, addr >> PAGE_SHIFT); if (is_error_page(page)) return NULL; @@ -7323,7 +7323,7 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, bitmap += (port & 0x7fff) / 8; if (last_bitmap != bitmap) - if (kvm_read_guest(vcpu->kvm, bitmap, &b, 1)) + if (kvm_vcpu_read_guest(vcpu, bitmap, &b, 1)) return true; if (b & (1 << (port & 7))) return true; @@ -7367,7 +7367,7 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, /* Then read the msr_index'th bit from this bitmap: */ if (msr_index < 1024*8) { unsigned char b; - if (kvm_read_guest(vcpu->kvm, bitmap + msr_index/8, &b, 1)) + if (kvm_vcpu_read_guest(vcpu, bitmap + msr_index/8, &b, 1)) return true; return 1 & (b >> (msr_index & 7)); } else @@ -7632,9 +7632,9 @@ static void vmx_disable_pml(struct vcpu_vmx *vmx) vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); } -static void vmx_flush_pml_buffer(struct vcpu_vmx *vmx) +static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu) { - struct kvm *kvm = vmx->vcpu.kvm; + struct vcpu_vmx *vmx = to_vmx(vcpu); u64 *pml_buf; u16 pml_idx; @@ -7656,7 +7656,7 @@ static void vmx_flush_pml_buffer(struct vcpu_vmx *vmx) gpa = pml_buf[pml_idx]; WARN_ON(gpa & (PAGE_SIZE - 1)); - mark_page_dirty(kvm, gpa >> PAGE_SHIFT); + kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); } /* reset PML index */ @@ -7851,7 +7851,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) * flushed already. */ if (enable_pml) - vmx_flush_pml_buffer(vmx); + vmx_flush_pml_buffer(vcpu); /* If guest state is invalid, start emulating */ if (vmx->emulation_required) @@ -9109,8 +9109,8 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) msr.host_initiated = false; for (i = 0; i < count; i++) { - if (kvm_read_guest(vcpu->kvm, gpa + i * sizeof(e), - &e, sizeof(e))) { + if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e), + &e, sizeof(e))) { pr_warn_ratelimited( "%s cannot read MSR entry (%u, 0x%08llx)\n", __func__, i, gpa + i * sizeof(e)); @@ -9143,9 +9143,9 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) for (i = 0; i < count; i++) { struct msr_data msr_info; - if (kvm_read_guest(vcpu->kvm, - gpa + i * sizeof(e), - &e, 2 * sizeof(u32))) { + if (kvm_vcpu_read_guest(vcpu, + gpa + i * sizeof(e), + &e, 2 * sizeof(u32))) { pr_warn_ratelimited( "%s cannot read MSR entry (%u, 0x%08llx)\n", __func__, i, gpa + i * sizeof(e)); @@ -9165,10 +9165,10 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) __func__, i, e.index); return -EINVAL; } - if (kvm_write_guest(vcpu->kvm, - gpa + i * sizeof(e) + - offsetof(struct vmx_msr_entry, value), - &msr_info.data, sizeof(msr_info.data))) { + if (kvm_vcpu_write_guest(vcpu, + gpa + i * sizeof(e) + + offsetof(struct vmx_msr_entry, value), + &msr_info.data, sizeof(msr_info.data))) { pr_warn_ratelimited( "%s cannot write MSR (%u, 0x%x, 0x%llx)\n", __func__, i, e.index, msr_info.data); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 51d994e1d6af..a510f135180a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -478,7 +478,7 @@ EXPORT_SYMBOL_GPL(kvm_require_dr); /* * This function will be used to read from the physical memory of the currently - * running guest. The difference to kvm_read_guest_page is that this function + * running guest. The difference to kvm_vcpu_read_guest_page is that this function * can read from guest physical or from the guest's guest physical memory. */ int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, @@ -496,7 +496,7 @@ int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, real_gfn = gpa_to_gfn(real_gfn); - return kvm_read_guest_page(vcpu->kvm, real_gfn, data, offset, len); + return kvm_vcpu_read_guest_page(vcpu, real_gfn, data, offset, len); } EXPORT_SYMBOL_GPL(kvm_read_guest_page_mmu); @@ -2030,7 +2030,7 @@ static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data) r = PTR_ERR(page); goto out; } - if (kvm_write_guest(kvm, page_addr, page, PAGE_SIZE)) + if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE)) goto out_free; r = 0; out_free: @@ -2130,13 +2130,13 @@ static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data) break; } gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT; - addr = gfn_to_hva(vcpu->kvm, gfn); + addr = kvm_vcpu_gfn_to_hva(vcpu, gfn); if (kvm_is_error_hva(addr)) return 1; if (__clear_user((void __user *)addr, PAGE_SIZE)) return 1; vcpu->arch.hv_vapic = data; - mark_page_dirty(vcpu->kvm, gfn); + kvm_vcpu_mark_page_dirty(vcpu, gfn); if (kvm_lapic_enable_pv_eoi(vcpu, gfn_to_gpa(gfn) | KVM_MSR_ENABLED)) return 1; break; @@ -4425,8 +4425,8 @@ static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes, if (gpa == UNMAPPED_GVA) return X86EMUL_PROPAGATE_FAULT; - ret = kvm_read_guest_page(vcpu->kvm, gpa >> PAGE_SHIFT, data, - offset, toread); + ret = kvm_vcpu_read_guest_page(vcpu, gpa >> PAGE_SHIFT, data, + offset, toread); if (ret < 0) { r = X86EMUL_IO_NEEDED; goto out; @@ -4459,8 +4459,8 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt, offset = addr & (PAGE_SIZE-1); if (WARN_ON(offset + bytes > PAGE_SIZE)) bytes = (unsigned)PAGE_SIZE - offset; - ret = kvm_read_guest_page(vcpu->kvm, gpa >> PAGE_SHIFT, val, - offset, bytes); + ret = kvm_vcpu_read_guest_page(vcpu, gpa >> PAGE_SHIFT, val, + offset, bytes); if (unlikely(ret < 0)) return X86EMUL_IO_NEEDED; @@ -4506,7 +4506,7 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt, if (gpa == UNMAPPED_GVA) return X86EMUL_PROPAGATE_FAULT; - ret = kvm_write_guest(vcpu->kvm, gpa, data, towrite); + ret = kvm_vcpu_write_guest(vcpu, gpa, data, towrite); if (ret < 0) { r = X86EMUL_IO_NEEDED; goto out; @@ -4559,7 +4559,7 @@ int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, { int ret; - ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes); + ret = kvm_vcpu_write_guest(vcpu, gpa, val, bytes); if (ret < 0) return 0; kvm_mmu_pte_write(vcpu, gpa, val, bytes); @@ -4593,7 +4593,7 @@ static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes) static int read_emulate(struct kvm_vcpu *vcpu, gpa_t gpa, void *val, int bytes) { - return !kvm_read_guest(vcpu->kvm, gpa, val, bytes); + return !kvm_vcpu_read_guest(vcpu, gpa, val, bytes); } static int write_emulate(struct kvm_vcpu *vcpu, gpa_t gpa, @@ -4791,7 +4791,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK)) goto emul_write; - page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); + page = kvm_vcpu_gfn_to_page(vcpu, gpa >> PAGE_SHIFT); if (is_error_page(page)) goto emul_write; @@ -4819,7 +4819,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, if (!exchanged) return X86EMUL_CMPXCHG_FAILED; - mark_page_dirty(vcpu->kvm, gpa >> PAGE_SHIFT); + kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); kvm_mmu_pte_write(vcpu, gpa, new, bytes); return X86EMUL_CONTINUE; @@ -6570,7 +6570,7 @@ static void process_smi(struct kvm_vcpu *vcpu) else process_smi_save_state_32(vcpu, buf); - kvm_write_guest(vcpu->kvm, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf)); + kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf)); if (kvm_x86_ops->get_nmi_mask(vcpu)) vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; @@ -8075,7 +8075,7 @@ void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) * memslots->generation has been incremented. * mmio generation may have reached its maximum value. */ - kvm_mmu_invalidate_mmio_sptes(kvm); + kvm_mmu_invalidate_mmio_sptes(kvm, slots); } int kvm_arch_prepare_memory_region(struct kvm *kvm, -- cgit v1.2.3 From 9da0e4d5ac969909f6b435ce28ea28135a9cbd69 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 18 May 2015 13:33:16 +0200 Subject: KVM: x86: work on all available address spaces MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch has no semantic change, but it prepares for the introduction of a second address space for system management mode. A new function x86_set_memory_region (and the "slots_lock taken" counterpart __x86_set_memory_region) is introduced in order to operate on all address spaces when adding or deleting private memory slots. Reviewed-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 5 +++ arch/x86/kvm/mmu.c | 84 ++++++++++++++++++++++------------------- arch/x86/kvm/vmx.c | 6 +-- arch/x86/kvm/x86.c | 40 ++++++++++++++++++-- 4 files changed, 91 insertions(+), 44 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 2fd420255c2f..5a5e13af6e03 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1189,4 +1189,9 @@ int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data); void kvm_handle_pmu_event(struct kvm_vcpu *vcpu); void kvm_deliver_pmi(struct kvm_vcpu *vcpu); +int __x86_set_memory_region(struct kvm *kvm, + const struct kvm_userspace_memory_region *mem); +int x86_set_memory_region(struct kvm *kvm, + const struct kvm_userspace_memory_region *mem); + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 3814f483ac45..7619e9e1745c 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1503,30 +1503,33 @@ static int kvm_handle_hva_range(struct kvm *kvm, struct kvm_memory_slot *memslot; struct slot_rmap_walk_iterator iterator; int ret = 0; + int i; - slots = kvm_memslots(kvm); - - kvm_for_each_memslot(memslot, slots) { - unsigned long hva_start, hva_end; - gfn_t gfn_start, gfn_end; + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + slots = __kvm_memslots(kvm, i); + kvm_for_each_memslot(memslot, slots) { + unsigned long hva_start, hva_end; + gfn_t gfn_start, gfn_end; - hva_start = max(start, memslot->userspace_addr); - hva_end = min(end, memslot->userspace_addr + - (memslot->npages << PAGE_SHIFT)); - if (hva_start >= hva_end) - continue; - /* - * {gfn(page) | page intersects with [hva_start, hva_end)} = - * {gfn_start, gfn_start+1, ..., gfn_end-1}. - */ - gfn_start = hva_to_gfn_memslot(hva_start, memslot); - gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot); - - for_each_slot_rmap_range(memslot, PT_PAGE_TABLE_LEVEL, - PT_MAX_HUGEPAGE_LEVEL, gfn_start, gfn_end - 1, - &iterator) - ret |= handler(kvm, iterator.rmap, memslot, - iterator.gfn, iterator.level, data); + hva_start = max(start, memslot->userspace_addr); + hva_end = min(end, memslot->userspace_addr + + (memslot->npages << PAGE_SHIFT)); + if (hva_start >= hva_end) + continue; + /* + * {gfn(page) | page intersects with [hva_start, hva_end)} = + * {gfn_start, gfn_start+1, ..., gfn_end-1}. + */ + gfn_start = hva_to_gfn_memslot(hva_start, memslot); + gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot); + + for_each_slot_rmap_range(memslot, PT_PAGE_TABLE_LEVEL, + PT_MAX_HUGEPAGE_LEVEL, + gfn_start, gfn_end - 1, + &iterator) + ret |= handler(kvm, iterator.rmap, memslot, + iterator.gfn, iterator.level, data); + } } return ret; @@ -4536,21 +4539,23 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - - slots = kvm_memslots(kvm); + int i; spin_lock(&kvm->mmu_lock); - kvm_for_each_memslot(memslot, slots) { - gfn_t start, end; - - start = max(gfn_start, memslot->base_gfn); - end = min(gfn_end, memslot->base_gfn + memslot->npages); - if (start >= end) - continue; + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + slots = __kvm_memslots(kvm, i); + kvm_for_each_memslot(memslot, slots) { + gfn_t start, end; + + start = max(gfn_start, memslot->base_gfn); + end = min(gfn_end, memslot->base_gfn + memslot->npages); + if (start >= end) + continue; - slot_handle_level_range(kvm, memslot, kvm_zap_rmapp, - PT_PAGE_TABLE_LEVEL, PT_MAX_HUGEPAGE_LEVEL, - start, end - 1, true); + slot_handle_level_range(kvm, memslot, kvm_zap_rmapp, + PT_PAGE_TABLE_LEVEL, PT_MAX_HUGEPAGE_LEVEL, + start, end - 1, true); + } } spin_unlock(&kvm->mmu_lock); @@ -4907,15 +4912,18 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm) unsigned int nr_pages = 0; struct kvm_memslots *slots; struct kvm_memory_slot *memslot; + int i; - slots = kvm_memslots(kvm); + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + slots = __kvm_memslots(kvm, i); - kvm_for_each_memslot(memslot, slots) - nr_pages += memslot->npages; + kvm_for_each_memslot(memslot, slots) + nr_pages += memslot->npages; + } nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000; nr_mmu_pages = max(nr_mmu_pages, - (unsigned int) KVM_MIN_ALLOC_MMU_PAGES); + (unsigned int) KVM_MIN_ALLOC_MMU_PAGES); return nr_mmu_pages; } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 8c80b7d7343c..862fa8f2c61d 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -4115,7 +4115,7 @@ static int alloc_apic_access_page(struct kvm *kvm) kvm_userspace_mem.flags = 0; kvm_userspace_mem.guest_phys_addr = APIC_DEFAULT_PHYS_BASE; kvm_userspace_mem.memory_size = PAGE_SIZE; - r = __kvm_set_memory_region(kvm, &kvm_userspace_mem); + r = __x86_set_memory_region(kvm, &kvm_userspace_mem); if (r) goto out; @@ -4150,7 +4150,7 @@ static int alloc_identity_pagetable(struct kvm *kvm) kvm_userspace_mem.guest_phys_addr = kvm->arch.ept_identity_map_addr; kvm_userspace_mem.memory_size = PAGE_SIZE; - r = __kvm_set_memory_region(kvm, &kvm_userspace_mem); + r = __x86_set_memory_region(kvm, &kvm_userspace_mem); return r; } @@ -4956,7 +4956,7 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) .flags = 0, }; - ret = kvm_set_memory_region(kvm, &tss_mem); + ret = x86_set_memory_region(kvm, &tss_mem); if (ret) return ret; kvm->arch.tss_addr = addr; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index a510f135180a..caa0d5f8e6b3 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7963,6 +7963,40 @@ void kvm_arch_sync_events(struct kvm *kvm) kvm_free_pit(kvm); } +int __x86_set_memory_region(struct kvm *kvm, + const struct kvm_userspace_memory_region *mem) +{ + int i, r; + + /* Called with kvm->slots_lock held. */ + BUG_ON(mem->slot >= KVM_MEM_SLOTS_NUM); + + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + struct kvm_userspace_memory_region m = *mem; + + m.slot |= i << 16; + r = __kvm_set_memory_region(kvm, &m); + if (r < 0) + return r; + } + + return 0; +} +EXPORT_SYMBOL_GPL(__x86_set_memory_region); + +int x86_set_memory_region(struct kvm *kvm, + const struct kvm_userspace_memory_region *mem) +{ + int r; + + mutex_lock(&kvm->slots_lock); + r = __x86_set_memory_region(kvm, mem); + mutex_unlock(&kvm->slots_lock); + + return r; +} +EXPORT_SYMBOL_GPL(x86_set_memory_region); + void kvm_arch_destroy_vm(struct kvm *kvm) { if (current->mm == kvm->mm) { @@ -7974,13 +8008,13 @@ void kvm_arch_destroy_vm(struct kvm *kvm) struct kvm_userspace_memory_region mem; memset(&mem, 0, sizeof(mem)); mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT; - kvm_set_memory_region(kvm, &mem); + x86_set_memory_region(kvm, &mem); mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT; - kvm_set_memory_region(kvm, &mem); + x86_set_memory_region(kvm, &mem); mem.slot = TSS_PRIVATE_MEMSLOT; - kvm_set_memory_region(kvm, &mem); + x86_set_memory_region(kvm, &mem); } kvm_iommu_unmap_guest(kvm); kfree(kvm->arch.vpic); -- cgit v1.2.3 From 699023e239658e62da6f42f47d31b54788521ec1 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 18 May 2015 15:03:39 +0200 Subject: KVM: x86: add SMM to the MMU role, support SMRAM address space MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is now very simple to do. The only interesting part is a simple trick to find the right memslot in gfn_to_rmap, retrieving the address space from the spte role word. The same trick is used in the auditing code. The comment on top of union kvm_mmu_page_role has been stale forever, so remove it. Speaking of stale code, remove pad_for_nice_hex_output too: it was splitting the "access" bitfield across two bytes and thus had effectively turned into pad_for_ugly_hex_output. Reviewed-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- Documentation/virtual/kvm/mmu.txt | 6 ++++++ arch/x86/include/asm/kvm_host.h | 26 +++++++++++++++----------- arch/x86/kvm/mmu.c | 15 ++++++++++++--- arch/x86/kvm/mmu_audit.c | 10 +++++++--- arch/x86/kvm/x86.c | 2 ++ 5 files changed, 42 insertions(+), 17 deletions(-) diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt index c59bd9bc41ef..3a4d681c3e98 100644 --- a/Documentation/virtual/kvm/mmu.txt +++ b/Documentation/virtual/kvm/mmu.txt @@ -173,6 +173,12 @@ Shadow pages contain the following information: Contains the value of cr4.smap && !cr0.wp for which the page is valid (pages for which this is true are different from other pages; see the treatment of cr0.wp=0 below). + role.smm: + Is 1 if the page is valid in system management mode. This field + determines which of the kvm_memslots array was used to build this + shadow page; it is also used to go back from a struct kvm_mmu_page + to a memslot, through the kvm_memslots_for_spte_role macro and + __gfn_to_memslot. gfn: Either the guest page table containing the translations shadowed by this page, or the base page frame for linear translations. See role.direct. diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 5a5e13af6e03..47006683f2fe 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -184,23 +184,12 @@ struct kvm_mmu_memory_cache { void *objects[KVM_NR_MEM_OBJS]; }; -/* - * kvm_mmu_page_role, below, is defined as: - * - * bits 0:3 - total guest paging levels (2-4, or zero for real mode) - * bits 4:7 - page table level for this shadow (1-4) - * bits 8:9 - page table quadrant for 2-level guests - * bit 16 - direct mapping of virtual to physical mapping at gfn - * used for real mode and two-dimensional paging - * bits 17:19 - common access permissions for all ptes in this shadow page - */ union kvm_mmu_page_role { unsigned word; struct { unsigned level:4; unsigned cr4_pae:1; unsigned quadrant:2; - unsigned pad_for_nice_hex_output:6; unsigned direct:1; unsigned access:3; unsigned invalid:1; @@ -208,6 +197,15 @@ union kvm_mmu_page_role { unsigned cr0_wp:1; unsigned smep_andnot_wp:1; unsigned smap_andnot_wp:1; + unsigned :8; + + /* + * This is left at the top of the word so that + * kvm_memslots_for_spte_role can extract it with a + * simple shift. While there is room, give it a whole + * byte so it is also faster to load it from memory. + */ + unsigned smm:8; }; }; @@ -1120,6 +1118,12 @@ enum { #define HF_SMM_MASK (1 << 6) #define HF_SMM_INSIDE_NMI_MASK (1 << 7) +#define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE +#define KVM_ADDRESS_SPACE_NUM 2 + +#define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0) +#define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm) + /* * Hardware virtualization extension instructions may fault if a * reboot turns off virtualization while processes are running. diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 7619e9e1745c..c88f0e443669 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -806,13 +806,15 @@ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn, static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) { + struct kvm_memslots *slots; struct kvm_memory_slot *slot; struct kvm_lpage_info *linfo; gfn_t gfn; int i; gfn = sp->gfn; - slot = gfn_to_memslot(kvm, gfn); + slots = kvm_memslots_for_spte_role(kvm, sp->role); + slot = __gfn_to_memslot(slots, gfn); for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { linfo = lpage_info_slot(gfn, slot, i); linfo->write_count += 1; @@ -822,13 +824,15 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) { + struct kvm_memslots *slots; struct kvm_memory_slot *slot; struct kvm_lpage_info *linfo; gfn_t gfn; int i; gfn = sp->gfn; - slot = gfn_to_memslot(kvm, gfn); + slots = kvm_memslots_for_spte_role(kvm, sp->role); + slot = __gfn_to_memslot(slots, gfn); for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { linfo = lpage_info_slot(gfn, slot, i); linfo->write_count -= 1; @@ -1045,9 +1049,11 @@ static unsigned long *__gfn_to_rmap(gfn_t gfn, int level, */ static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, struct kvm_mmu_page *sp) { + struct kvm_memslots *slots; struct kvm_memory_slot *slot; - slot = gfn_to_memslot(kvm, gfn); + slots = kvm_memslots_for_spte_role(kvm, sp->role); + slot = __gfn_to_memslot(slots, gfn); return __gfn_to_rmap(gfn, sp->role.level, slot); } @@ -3924,6 +3930,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) struct kvm_mmu *context = &vcpu->arch.mmu; context->base_role.word = 0; + context->base_role.smm = is_smm(vcpu); context->page_fault = tdp_page_fault; context->sync_page = nonpaging_sync_page; context->invlpg = nonpaging_invlpg; @@ -3985,6 +3992,7 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu) = smep && !is_write_protection(vcpu); context->base_role.smap_andnot_wp = smap && !is_write_protection(vcpu); + context->base_role.smm = is_smm(vcpu); } EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu); @@ -4268,6 +4276,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, mask.nxe = 1; mask.smep_andnot_wp = 1; mask.smap_andnot_wp = 1; + mask.smm = 1; /* * If we don't have indirect shadow pages, it means no page is diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index 78288c15400c..a4f62e6f2db2 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -131,12 +131,16 @@ static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10); unsigned long *rmapp; struct kvm_mmu_page *rev_sp; + struct kvm_memslots *slots; + struct kvm_memory_slot *slot; gfn_t gfn; rev_sp = page_header(__pa(sptep)); gfn = kvm_mmu_page_get_gfn(rev_sp, sptep - rev_sp->spt); - if (!gfn_to_memslot(kvm, gfn)) { + slots = kvm_memslots_for_spte_role(kvm, rev_sp->role); + slot = __gfn_to_memslot(slots, gfn); + if (!slot) { if (!__ratelimit(&ratelimit_state)) return; audit_printk(kvm, "no memslot for gfn %llx\n", gfn); @@ -146,7 +150,7 @@ static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) return; } - rmapp = gfn_to_rmap(kvm, gfn, rev_sp); + rmapp = __gfn_to_rmap(gfn, rev_sp->role.level, slot); if (!*rmapp) { if (!__ratelimit(&ratelimit_state)) return; @@ -197,7 +201,7 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp) if (sp->role.direct || sp->unsync || sp->role.invalid) return; - slots = kvm_memslots(kvm); + slots = kvm_memslots_for_spte_role(kvm, sp->role); slot = __gfn_to_memslot(slots, sp->gfn); rmapp = __gfn_to_rmap(sp->gfn, PT_PAGE_TABLE_LEVEL, slot); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index caa0d5f8e6b3..7489871b63df 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5490,6 +5490,8 @@ static void kvm_smm_changed(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); } } + + kvm_mmu_reset_context(vcpu); } static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags) -- cgit v1.2.3 From 6d396b55203969ca61cc8f838db2e68433e13f7b Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 1 Apr 2015 14:25:33 +0200 Subject: KVM: x86: advertise KVM_CAP_X86_SMM MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ... and we're done. :) Because SMBASE is usually relocated above 1M on modern chipsets, and SMM handlers might indeed rely on 4G segment limits, we only expose it if KVM is able to run the guest in big real mode. This includes any of VMX+emulate_invalid_guest_state, VMX+unrestricted_guest, or SVM. Reviewed-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/svm.c | 6 ++++++ arch/x86/kvm/vmx.c | 6 ++++++ arch/x86/kvm/x86.c | 15 +++++++++++++++ 4 files changed, 28 insertions(+) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 47006683f2fe..8ca32cfbcbd8 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -709,6 +709,7 @@ struct kvm_x86_ops { int (*hardware_setup)(void); /* __init */ void (*hardware_unsetup)(void); /* __exit */ bool (*cpu_has_accelerated_tpr)(void); + bool (*cpu_has_high_real_mode_segbase)(void); void (*cpuid_update)(struct kvm_vcpu *vcpu); /* Create, but do not attach this VCPU */ diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 6ff1faf4a2e8..680753186489 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -4080,6 +4080,11 @@ static bool svm_cpu_has_accelerated_tpr(void) return false; } +static bool svm_has_high_real_mode_segbase(void) +{ + return true; +} + static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { return 0; @@ -4353,6 +4358,7 @@ static struct kvm_x86_ops svm_x86_ops = { .hardware_enable = svm_hardware_enable, .hardware_disable = svm_hardware_disable, .cpu_has_accelerated_tpr = svm_cpu_has_accelerated_tpr, + .cpu_has_high_real_mode_segbase = svm_has_high_real_mode_segbase, .vcpu_create = svm_create_vcpu, .vcpu_free = svm_free_vcpu, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 862fa8f2c61d..06a186b07631 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -8139,6 +8139,11 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) local_irq_enable(); } +static bool vmx_has_high_real_mode_segbase(void) +{ + return enable_unrestricted_guest || emulate_invalid_guest_state; +} + static bool vmx_mpx_supported(void) { return (vmcs_config.vmexit_ctrl & VM_EXIT_CLEAR_BNDCFGS) && @@ -10296,6 +10301,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .hardware_enable = hardware_enable, .hardware_disable = hardware_disable, .cpu_has_accelerated_tpr = report_flexpriority, + .cpu_has_high_real_mode_segbase = vmx_has_high_real_mode_segbase, .vcpu_create = vmx_create_vcpu, .vcpu_free = vmx_free_vcpu, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7489871b63df..43f0df7ddc9c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2900,6 +2900,17 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) #endif r = 1; break; + case KVM_CAP_X86_SMM: + /* SMBASE is usually relocated above 1M on modern chipsets, + * and SMM handlers might indeed rely on 4G segment limits, + * so do not report SMM to be available if real mode is + * emulated via vm86 mode. Still, do not go to great lengths + * to avoid userspace's usage of the feature, because it is a + * fringe case that is not enabled except via specific settings + * of the module parameters. + */ + r = kvm_x86_ops->cpu_has_high_real_mode_segbase(); + break; case KVM_CAP_COALESCED_MMIO: r = KVM_COALESCED_MMIO_PAGE_OFFSET; break; @@ -4299,6 +4310,10 @@ static void kvm_init_msr_list(void) for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) { switch (emulated_msrs[i]) { + case MSR_IA32_SMBASE: + if (!kvm_x86_ops->cpu_has_high_real_mode_segbase()) + continue; + break; default: break; } -- cgit v1.2.3 From e80a4a9426adeaa34c009bc0bc61365e0580bf01 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 4 Jun 2015 16:32:48 +0200 Subject: KVM: x86: mark legacy PCI device assignment as deprecated Follow up to commit e194bbdf362ba7d53cfd23ba24f1a7c90ef69a74. Suggested-by: Bandan Das Suggested-by: Alex Williamson Signed-off-by: Paolo Bonzini --- Documentation/virtual/kvm/api.txt | 14 +++++++------- arch/x86/kvm/Kconfig | 2 +- 2 files changed, 8 insertions(+), 8 deletions(-) diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 461956a0ee8e..a7926a90156f 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -1294,7 +1294,7 @@ The flags bitmap is defined as: /* the host supports the ePAPR idle hcall #define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0) -4.48 KVM_ASSIGN_PCI_DEVICE +4.48 KVM_ASSIGN_PCI_DEVICE (deprecated) Capability: none Architectures: x86 @@ -1344,7 +1344,7 @@ Errors: have their standard meanings. -4.49 KVM_DEASSIGN_PCI_DEVICE +4.49 KVM_DEASSIGN_PCI_DEVICE (deprecated) Capability: none Architectures: x86 @@ -1363,7 +1363,7 @@ Errors: Other error conditions may be defined by individual device types or have their standard meanings. -4.50 KVM_ASSIGN_DEV_IRQ +4.50 KVM_ASSIGN_DEV_IRQ (deprecated) Capability: KVM_CAP_ASSIGN_DEV_IRQ Architectures: x86 @@ -1403,7 +1403,7 @@ Errors: have their standard meanings. -4.51 KVM_DEASSIGN_DEV_IRQ +4.51 KVM_DEASSIGN_DEV_IRQ (deprecated) Capability: KVM_CAP_ASSIGN_DEV_IRQ Architectures: x86 @@ -1477,7 +1477,7 @@ struct kvm_irq_routing_s390_adapter { }; -4.53 KVM_ASSIGN_SET_MSIX_NR +4.53 KVM_ASSIGN_SET_MSIX_NR (deprecated) Capability: none Architectures: x86 @@ -1499,7 +1499,7 @@ struct kvm_assigned_msix_nr { #define KVM_MAX_MSIX_PER_DEV 256 -4.54 KVM_ASSIGN_SET_MSIX_ENTRY +4.54 KVM_ASSIGN_SET_MSIX_ENTRY (deprecated) Capability: none Architectures: x86 @@ -1655,7 +1655,7 @@ should skip processing the bitmap and just invalidate everything. It must be set to the number of set bits in the bitmap. -4.61 KVM_ASSIGN_SET_INTX_MASK +4.61 KVM_ASSIGN_SET_INTX_MASK (deprecated) Capability: KVM_CAP_PCI_2_3 Architectures: x86 diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index a0f06a5947c5..d8a1d56276e1 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -86,7 +86,7 @@ config KVM_MMU_AUDIT auditing of KVM MMU events at runtime. config KVM_DEVICE_ASSIGNMENT - bool "KVM legacy PCI device assignment support" + bool "KVM legacy PCI device assignment support (DEPRECATED)" depends on KVM && PCI && IOMMU_API default n ---help--- -- cgit v1.2.3 From a5f56ba3b4ec8d2ad80da4c447d47e37e2b504fb Mon Sep 17 00:00:00 2001 From: Firo Yang Date: Thu, 23 Apr 2015 11:07:40 +0100 Subject: ARM: KVM: Remove pointless void pointer cast No need to cast the void pointer returned by kmalloc() in arch/arm/kvm/mmu.c::kvm_alloc_stage2_pgd(). Signed-off-by: Firo Yang Acked-by: Paolo Bonzini Signed-off-by: Marc Zyngier --- arch/arm/kvm/mmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 1d5accbd3dcf..ce0bce472455 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -691,8 +691,8 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm) * work. This is not used by the hardware and we have no * alignment requirement for this allocation. */ - pgd = (pgd_t *)kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t), - GFP_KERNEL | __GFP_ZERO); + pgd = kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t), + GFP_KERNEL | __GFP_ZERO); if (!pgd) { kvm_free_hwpgd(hwpgd); -- cgit v1.2.3 From c11b532910f71246e0d5b580e3694ee3b7ddf54c Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Thu, 23 Apr 2015 20:01:53 +0100 Subject: KVM: arm64: add active register handling to GICv3 emulation as well Commit 47a98b15ba7c ("arm/arm64: KVM: support for un-queuing active IRQs") introduced handling of the GICD_I[SC]ACTIVER registers, but only for the GICv2 emulation. For the sake of completeness and as this is a pre-requisite for save/restore of the GICv3 distributor state, we should also emulate their handling in the distributor and redistributor frames of an emulated GICv3. Acked-by: Christoffer Dall Signed-off-by: Andre Przywara Signed-off-by: Marc Zyngier --- virt/kvm/arm/vgic-v3-emul.c | 54 +++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 50 insertions(+), 4 deletions(-) diff --git a/virt/kvm/arm/vgic-v3-emul.c b/virt/kvm/arm/vgic-v3-emul.c index e9c3a7a83833..2b369de04e8e 100644 --- a/virt/kvm/arm/vgic-v3-emul.c +++ b/virt/kvm/arm/vgic-v3-emul.c @@ -173,6 +173,32 @@ static bool handle_mmio_clear_pending_reg_dist(struct kvm_vcpu *vcpu, return false; } +static bool handle_mmio_set_active_reg_dist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + if (likely(offset >= VGIC_NR_PRIVATE_IRQS / 8)) + return vgic_handle_set_active_reg(vcpu->kvm, mmio, offset, + vcpu->vcpu_id); + + vgic_reg_access(mmio, NULL, offset, + ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED); + return false; +} + +static bool handle_mmio_clear_active_reg_dist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + if (likely(offset >= VGIC_NR_PRIVATE_IRQS / 8)) + return vgic_handle_clear_active_reg(vcpu->kvm, mmio, offset, + vcpu->vcpu_id); + + vgic_reg_access(mmio, NULL, offset, + ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED); + return false; +} + static bool handle_mmio_priority_reg_dist(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio, phys_addr_t offset) @@ -428,13 +454,13 @@ static const struct vgic_io_range vgic_v3_dist_ranges[] = { .base = GICD_ISACTIVER, .len = 0x80, .bits_per_irq = 1, - .handle_mmio = handle_mmio_raz_wi, + .handle_mmio = handle_mmio_set_active_reg_dist, }, { .base = GICD_ICACTIVER, .len = 0x80, .bits_per_irq = 1, - .handle_mmio = handle_mmio_raz_wi, + .handle_mmio = handle_mmio_clear_active_reg_dist, }, { .base = GICD_IPRIORITYR, @@ -561,6 +587,26 @@ static bool handle_mmio_clear_enable_reg_redist(struct kvm_vcpu *vcpu, ACCESS_WRITE_CLEARBIT); } +static bool handle_mmio_set_active_reg_redist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + struct kvm_vcpu *redist_vcpu = mmio->private; + + return vgic_handle_set_active_reg(vcpu->kvm, mmio, offset, + redist_vcpu->vcpu_id); +} + +static bool handle_mmio_clear_active_reg_redist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + struct kvm_vcpu *redist_vcpu = mmio->private; + + return vgic_handle_clear_active_reg(vcpu->kvm, mmio, offset, + redist_vcpu->vcpu_id); +} + static bool handle_mmio_set_pending_reg_redist(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio, phys_addr_t offset) @@ -674,13 +720,13 @@ static const struct vgic_io_range vgic_redist_ranges[] = { .base = SGI_base(GICR_ISACTIVER0), .len = 0x04, .bits_per_irq = 1, - .handle_mmio = handle_mmio_raz_wi, + .handle_mmio = handle_mmio_set_active_reg_redist, }, { .base = SGI_base(GICR_ICACTIVER0), .len = 0x04, .bits_per_irq = 1, - .handle_mmio = handle_mmio_raz_wi, + .handle_mmio = handle_mmio_clear_active_reg_redist, }, { .base = SGI_base(GICR_IPRIORITYR0), -- cgit v1.2.3 From 85e84ba31039595995dae80b277378213602891b Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 16 Mar 2015 10:59:43 +0000 Subject: arm: KVM: force execution of HCPTR access on VM exit On VM entry, we disable access to the VFP registers in order to perform a lazy save/restore of these registers. On VM exit, we restore access, test if we did enable them before, and save/restore the guest/host registers if necessary. In this sequence, the FPEXC register is always accessed, irrespective of the trapping configuration. If the guest didn't touch the VFP registers, then the HCPTR access has now enabled such access, but we're missing a barrier to ensure architectural execution of the new HCPTR configuration. If the HCPTR access has been delayed/reordered, the subsequent access to FPEXC will cause a trap, which we aren't prepared to handle at all. The same condition exists when trapping to enable VFP for the guest. The fix is to introduce a barrier after enabling VFP access. In the vmexit case, it can be relaxed to only takes place if the guest hasn't accessed its view of the VFP registers, making the access to FPEXC safe. The set_hcptr macro is modified to deal with both vmenter/vmexit and vmtrap operations, and now takes an optional label that is branched to when the guest hasn't touched the VFP registers. Reported-by: Vikram Sethi Cc: stable@kernel.org # v3.9+ Signed-off-by: Marc Zyngier --- arch/arm/kvm/interrupts.S | 10 ++++------ arch/arm/kvm/interrupts_head.S | 20 ++++++++++++++++++-- 2 files changed, 22 insertions(+), 8 deletions(-) diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S index 79caf79b304a..f7db3a5d80e3 100644 --- a/arch/arm/kvm/interrupts.S +++ b/arch/arm/kvm/interrupts.S @@ -170,13 +170,9 @@ __kvm_vcpu_return: @ Don't trap coprocessor accesses for host kernel set_hstr vmexit set_hdcr vmexit - set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)) + set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)), after_vfp_restore #ifdef CONFIG_VFPv3 - @ Save floating point registers we if let guest use them. - tst r2, #(HCPTR_TCP(10) | HCPTR_TCP(11)) - bne after_vfp_restore - @ Switch VFP/NEON hardware state to the host's add r7, vcpu, #VCPU_VFP_GUEST store_vfp_state r7 @@ -188,6 +184,8 @@ after_vfp_restore: @ Restore FPEXC_EN which we clobbered on entry pop {r2} VFPFMXR FPEXC, r2 +#else +after_vfp_restore: #endif @ Reset Hyp-role @@ -483,7 +481,7 @@ switch_to_guest_vfp: push {r3-r7} @ NEON/VFP used. Turn on VFP access. - set_hcptr vmexit, (HCPTR_TCP(10) | HCPTR_TCP(11)) + set_hcptr vmtrap, (HCPTR_TCP(10) | HCPTR_TCP(11)) @ Switch VFP/NEON hardware state to the guest's add r7, r0, #VCPU_VFP_HOST diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S index 35e4a3a0c476..48efe2ee452c 100644 --- a/arch/arm/kvm/interrupts_head.S +++ b/arch/arm/kvm/interrupts_head.S @@ -591,8 +591,13 @@ ARM_BE8(rev r6, r6 ) .endm /* Configures the HCPTR (Hyp Coprocessor Trap Register) on entry/return - * (hardware reset value is 0). Keep previous value in r2. */ -.macro set_hcptr operation, mask + * (hardware reset value is 0). Keep previous value in r2. + * An ISB is emited on vmexit/vmtrap, but executed on vmexit only if + * VFP wasn't already enabled (always executed on vmtrap). + * If a label is specified with vmexit, it is branched to if VFP wasn't + * enabled. + */ +.macro set_hcptr operation, mask, label = none mrc p15, 4, r2, c1, c1, 2 ldr r3, =\mask .if \operation == vmentry @@ -601,6 +606,17 @@ ARM_BE8(rev r6, r6 ) bic r3, r2, r3 @ Don't trap defined coproc-accesses .endif mcr p15, 4, r3, c1, c1, 2 + .if \operation != vmentry + .if \operation == vmexit + tst r2, #(HCPTR_TCP(10) | HCPTR_TCP(11)) + beq 1f + .endif + isb + .if \label != none + b \label + .endif +1: + .endif .endm /* Configures the HDCR (Hyp Debug Configuration Register) on entry/return -- cgit v1.2.3 From ea2c6d9745c6698d9f820bc230aa1a80d9e908ac Mon Sep 17 00:00:00 2001 From: Tiejun Chen Date: Mon, 4 May 2015 10:48:49 +0800 Subject: kvm: remove one useless check extension We already check KVM_CAP_IRQFD in generic once enable CONFIG_HAVE_KVM_IRQFD, kvm_vm_ioctl_check_extension_generic() | + switch (arg) { + ... + #ifdef CONFIG_HAVE_KVM_IRQFD + case KVM_CAP_IRQFD: + #endif + ... + return 1; + ... + } | + kvm_vm_ioctl_check_extension() So its not necessary to check this in arch again, and also fix one typo, s/emlation/emulation. Signed-off-by: Tiejun Chen Acked-by: Paolo Bonzini Signed-off-by: Christoffer Dall --- arch/arm/kvm/arm.c | 1 - include/uapi/linux/kvm.h | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index e41cb11f71b2..7e8233015ad8 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -171,7 +171,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) int r; switch (ext) { case KVM_CAP_IRQCHIP: - case KVM_CAP_IRQFD: case KVM_CAP_IOEVENTFD: case KVM_CAP_DEVICE_CTRL: case KVM_CAP_USER_MEMORY: diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 75bd9f7fd846..cbfd1acdeda7 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -895,7 +895,7 @@ struct kvm_xen_hvm_config { * * KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies * the irqfd to operate in resampling mode for level triggered interrupt - * emlation. See Documentation/virtual/kvm/api.txt. + * emulation. See Documentation/virtual/kvm/api.txt. */ #define KVM_IRQFD_FLAG_RESAMPLE (1 << 1) -- cgit v1.2.3 From 1b3d546daf85ed2bc9966e12cee3e6435fb65eca Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Thu, 28 May 2015 19:49:10 +0100 Subject: arm/arm64: KVM: Properly account for guest CPU time Until now we have been calling kvm_guest_exit after re-enabling interrupts when we come back from the guest, but this has the unfortunate effect that CPU time accounting done in the context of timer interrupts occurring while the guest is running doesn't properly notice that the time since the last tick was spent in the guest. Inspired by the comment in the x86 code, move the kvm_guest_exit() call below the local_irq_enable() call and change __kvm_guest_exit() to kvm_guest_exit(), because we are now calling this function with interrupts enabled. We have to now explicitly disable preemption and not enable preemption before we've called kvm_guest_exit(), since otherwise we could be preempted and everything happening before we eventually get scheduled again would be accounted for as guest time. At the same time, move the trace_kvm_exit() call outside of the atomic section, since there is no reason for us to do that with interrupts disabled. Signed-off-by: Christoffer Dall Signed-off-by: Marc Zyngier --- arch/arm/kvm/arm.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 7e8233015ad8..bc738d2b8392 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -531,6 +531,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) kvm_vgic_flush_hwstate(vcpu); kvm_timer_flush_hwstate(vcpu); + preempt_disable(); local_irq_disable(); /* @@ -543,6 +544,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) if (ret <= 0 || need_new_vmid_gen(vcpu->kvm)) { local_irq_enable(); + preempt_enable(); kvm_timer_sync_hwstate(vcpu); kvm_vgic_sync_hwstate(vcpu); continue; @@ -558,8 +560,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) ret = kvm_call_hyp(__kvm_vcpu_run, vcpu); vcpu->mode = OUTSIDE_GUEST_MODE; - __kvm_guest_exit(); - trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu)); + /* + * Back from guest + *************************************************************/ + /* * We may have taken a host interrupt in HYP mode (ie * while executing the guest). This interrupt is still @@ -573,8 +577,17 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) local_irq_enable(); /* - * Back from guest - *************************************************************/ + * We do local_irq_enable() before calling kvm_guest_exit() so + * that if a timer interrupt hits while running the guest we + * account that tick as being spent in the guest. We enable + * preemption after calling kvm_guest_exit() so that if we get + * preempted we make sure ticks after that is not counted as + * guest time. + */ + kvm_guest_exit(); + trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu)); + preempt_enable(); + kvm_timer_sync_hwstate(vcpu); kvm_vgic_sync_hwstate(vcpu); -- cgit v1.2.3 From 8889583c037c776041b08d7109acc2450e560036 Mon Sep 17 00:00:00 2001 From: Kim Phillips Date: Fri, 5 Jun 2015 16:21:49 +0100 Subject: KVM: arm/arm64: Enable the KVM-VFIO device The KVM-VFIO device is used by the QEMU VFIO device. It is used to record the list of in-use VFIO groups so that KVM can manipulate them. Signed-off-by: Kim Phillips Signed-off-by: Eric Auger Signed-off-by: Marc Zyngier --- arch/arm/kvm/Kconfig | 1 + arch/arm/kvm/Makefile | 2 +- arch/arm64/kvm/Kconfig | 1 + arch/arm64/kvm/Makefile | 2 +- 4 files changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig index f1f79d104309..bfb915d05665 100644 --- a/arch/arm/kvm/Kconfig +++ b/arch/arm/kvm/Kconfig @@ -28,6 +28,7 @@ config KVM select KVM_GENERIC_DIRTYLOG_READ_PROTECT select SRCU select MMU_NOTIFIER + select KVM_VFIO select HAVE_KVM_EVENTFD select HAVE_KVM_IRQFD depends on ARM_VIRT_EXT && ARM_LPAE && ARM_ARCH_TIMER diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile index 139e46c08b6e..c5eef02c52ba 100644 --- a/arch/arm/kvm/Makefile +++ b/arch/arm/kvm/Makefile @@ -15,7 +15,7 @@ AFLAGS_init.o := -Wa,-march=armv7-a$(plus_virt) AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt) KVM := ../../../virt/kvm -kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o +kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o obj-y += kvm-arm.o init.o interrupts.o obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 5105e297ed5f..bfffe8f4bd53 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -28,6 +28,7 @@ config KVM select KVM_ARM_HOST select KVM_GENERIC_DIRTYLOG_READ_PROTECT select SRCU + select KVM_VFIO select HAVE_KVM_EVENTFD select HAVE_KVM_IRQFD ---help--- diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index d5904f876cdb..f90f4aa7f88d 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -11,7 +11,7 @@ ARM=../../../arch/arm/kvm obj-$(CONFIG_KVM_ARM_HOST) += kvm.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/arm.o $(ARM)/mmu.o $(ARM)/mmio.o kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/psci.o $(ARM)/perf.o -- cgit v1.2.3 From 921ef1e16c762db13be740a35e691104d6740572 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Alex=20Benn=C3=A9e?= Date: Thu, 4 Jun 2015 14:28:37 +0100 Subject: KVM: arm64: fix misleading comments in save/restore MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The elr_el2 and spsr_el2 registers in fact contain the processor state before entry into EL2. In the case of guest state it could be in either el0 or el1. Signed-off-by: Alex Bennée Signed-off-by: Marc Zyngier --- arch/arm64/kvm/hyp.S | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S index 5befd010e232..519805f71876 100644 --- a/arch/arm64/kvm/hyp.S +++ b/arch/arm64/kvm/hyp.S @@ -50,8 +50,8 @@ stp x29, lr, [x3, #80] mrs x19, sp_el0 - mrs x20, elr_el2 // EL1 PC - mrs x21, spsr_el2 // EL1 pstate + mrs x20, elr_el2 // pc before entering el2 + mrs x21, spsr_el2 // pstate before entering el2 stp x19, x20, [x3, #96] str x21, [x3, #112] @@ -82,8 +82,8 @@ ldr x21, [x3, #16] msr sp_el0, x19 - msr elr_el2, x20 // EL1 PC - msr spsr_el2, x21 // EL1 pstate + msr elr_el2, x20 // pc on return from el2 + msr spsr_el2, x21 // pstate on return from el2 add x3, x2, #CPU_XREG_OFFSET(19) ldp x19, x20, [x3] -- cgit v1.2.3 From e2d997366dc5b6c9d14035867f73957f93e7578c Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Wed, 10 Jun 2015 15:19:24 +0100 Subject: ARM: kvm: psci: fix handling of unimplemented functions According to the PSCI specification and the SMC/HVC calling convention, PSCI function_ids that are not implemented must return NOT_SUPPORTED as return value. Current KVM implementation takes an unhandled PSCI function_id as an error and injects an undefined instruction into the guest if PSCI implementation is called with a function_id that is not handled by the resident PSCI version (ie it is not implemented), which is not the behaviour expected by a guest when calling a PSCI function_id that is not implemented. This patch fixes this issue by returning NOT_SUPPORTED whenever the kvm PSCI call is executed for a function_id that is not implemented by the PSCI kvm layer. Cc: # 3.18+ Cc: Christoffer Dall Acked-by: Sudeep Holla Signed-off-by: Lorenzo Pieralisi Signed-off-by: Marc Zyngier --- arch/arm/kvm/psci.c | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c index 02fa8eff6ae1..531e922486b2 100644 --- a/arch/arm/kvm/psci.c +++ b/arch/arm/kvm/psci.c @@ -230,10 +230,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) case PSCI_0_2_FN64_AFFINITY_INFO: val = kvm_psci_vcpu_affinity_info(vcpu); break; - case PSCI_0_2_FN_MIGRATE: - case PSCI_0_2_FN64_MIGRATE: - val = PSCI_RET_NOT_SUPPORTED; - break; case PSCI_0_2_FN_MIGRATE_INFO_TYPE: /* * Trusted OS is MP hence does not require migration @@ -242,10 +238,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) */ val = PSCI_0_2_TOS_MP; break; - case PSCI_0_2_FN_MIGRATE_INFO_UP_CPU: - case PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU: - val = PSCI_RET_NOT_SUPPORTED; - break; case PSCI_0_2_FN_SYSTEM_OFF: kvm_psci_system_off(vcpu); /* @@ -271,7 +263,8 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) ret = 0; break; default: - return -EINVAL; + val = PSCI_RET_NOT_SUPPORTED; + break; } *vcpu_reg(vcpu, 0) = val; @@ -291,12 +284,9 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) case KVM_PSCI_FN_CPU_ON: val = kvm_psci_vcpu_on(vcpu); break; - case KVM_PSCI_FN_CPU_SUSPEND: - case KVM_PSCI_FN_MIGRATE: + default: val = PSCI_RET_NOT_SUPPORTED; break; - default: - return -EINVAL; } *vcpu_reg(vcpu, 0) = val; -- cgit v1.2.3 From f5a202db12b42aef9543029934681df019d7b749 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 29 May 2015 16:54:56 +0100 Subject: KVM: arm: vgic: Drop useless Group0 warning If a GICv3-enabled guest tries to configure Group0, we print a warning on the console (because we don't support Group0 interrupts). This is fairly pointless, and would allow a guest to spam the console. Let's just drop the warning. Acked-by: Christoffer Dall Signed-off-by: Marc Zyngier --- virt/kvm/arm/vgic-v3-emul.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/virt/kvm/arm/vgic-v3-emul.c b/virt/kvm/arm/vgic-v3-emul.c index 2b369de04e8e..e661e7fb9d91 100644 --- a/virt/kvm/arm/vgic-v3-emul.c +++ b/virt/kvm/arm/vgic-v3-emul.c @@ -76,8 +76,6 @@ static bool handle_mmio_ctlr(struct kvm_vcpu *vcpu, vgic_reg_access(mmio, ®, offset, ACCESS_READ_VALUE | ACCESS_WRITE_VALUE); if (mmio->is_write) { - if (reg & GICD_CTLR_ENABLE_SS_G0) - kvm_info("guest tried to enable unsupported Group0 interrupts\n"); vcpu->kvm->arch.vgic.enabled = !!(reg & GICD_CTLR_ENABLE_SS_G1); vgic_update_state(vcpu->kvm); return true; -- cgit v1.2.3 From 4642019dc4457486223e1fb75a6a4cba6e0e903a Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 11 Jun 2015 18:50:17 +0100 Subject: arm/arm64: KVM: vgic: Do not save GICH_HCR / ICH_HCR_EL2 The GIC Hypervisor Configuration Register is used to enable the delivery of virtual interupts to a guest, as well as to define in which conditions maintenance interrupts are delivered to the host. This register doesn't contain any information that we need to read back (the EOIcount is utterly useless for us). So let's save ourselves some cycles, and not save it before writing zero to it. Signed-off-by: Marc Zyngier --- arch/arm/kvm/interrupts_head.S | 3 --- arch/arm64/kvm/vgic-v2-switch.S | 3 --- arch/arm64/kvm/vgic-v3-switch.S | 2 -- 3 files changed, 8 deletions(-) diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S index 48efe2ee452c..702740d37465 100644 --- a/arch/arm/kvm/interrupts_head.S +++ b/arch/arm/kvm/interrupts_head.S @@ -412,7 +412,6 @@ vcpu .req r0 @ vcpu pointer always in r0 add r11, vcpu, #VCPU_VGIC_CPU /* Save all interesting registers */ - ldr r3, [r2, #GICH_HCR] ldr r4, [r2, #GICH_VMCR] ldr r5, [r2, #GICH_MISR] ldr r6, [r2, #GICH_EISR0] @@ -420,7 +419,6 @@ vcpu .req r0 @ vcpu pointer always in r0 ldr r8, [r2, #GICH_ELRSR0] ldr r9, [r2, #GICH_ELRSR1] ldr r10, [r2, #GICH_APR] -ARM_BE8(rev r3, r3 ) ARM_BE8(rev r4, r4 ) ARM_BE8(rev r5, r5 ) ARM_BE8(rev r6, r6 ) @@ -429,7 +427,6 @@ ARM_BE8(rev r8, r8 ) ARM_BE8(rev r9, r9 ) ARM_BE8(rev r10, r10 ) - str r3, [r11, #VGIC_V2_CPU_HCR] str r4, [r11, #VGIC_V2_CPU_VMCR] str r5, [r11, #VGIC_V2_CPU_MISR] #ifdef CONFIG_CPU_ENDIAN_BE8 diff --git a/arch/arm64/kvm/vgic-v2-switch.S b/arch/arm64/kvm/vgic-v2-switch.S index f002fe1c3700..3f000712a85d 100644 --- a/arch/arm64/kvm/vgic-v2-switch.S +++ b/arch/arm64/kvm/vgic-v2-switch.S @@ -47,7 +47,6 @@ __save_vgic_v2_state: add x3, x0, #VCPU_VGIC_CPU /* Save all interesting registers */ - ldr w4, [x2, #GICH_HCR] ldr w5, [x2, #GICH_VMCR] ldr w6, [x2, #GICH_MISR] ldr w7, [x2, #GICH_EISR0] @@ -55,7 +54,6 @@ __save_vgic_v2_state: ldr w9, [x2, #GICH_ELRSR0] ldr w10, [x2, #GICH_ELRSR1] ldr w11, [x2, #GICH_APR] -CPU_BE( rev w4, w4 ) CPU_BE( rev w5, w5 ) CPU_BE( rev w6, w6 ) CPU_BE( rev w7, w7 ) @@ -64,7 +62,6 @@ CPU_BE( rev w9, w9 ) CPU_BE( rev w10, w10 ) CPU_BE( rev w11, w11 ) - str w4, [x3, #VGIC_V2_CPU_HCR] str w5, [x3, #VGIC_V2_CPU_VMCR] str w6, [x3, #VGIC_V2_CPU_MISR] CPU_LE( str w7, [x3, #VGIC_V2_CPU_EISR] ) diff --git a/arch/arm64/kvm/vgic-v3-switch.S b/arch/arm64/kvm/vgic-v3-switch.S index 617a012a0107..3c20730ddff5 100644 --- a/arch/arm64/kvm/vgic-v3-switch.S +++ b/arch/arm64/kvm/vgic-v3-switch.S @@ -48,13 +48,11 @@ dsb st // Save all interesting registers - mrs_s x4, ICH_HCR_EL2 mrs_s x5, ICH_VMCR_EL2 mrs_s x6, ICH_MISR_EL2 mrs_s x7, ICH_EISR_EL2 mrs_s x8, ICH_ELSR_EL2 - str w4, [x3, #VGIC_V3_CPU_HCR] str w5, [x3, #VGIC_V3_CPU_VMCR] str w6, [x3, #VGIC_V3_CPU_MISR] str w7, [x3, #VGIC_V3_CPU_EISR] -- cgit v1.2.3 From 4839ddc27b7212ec58874f62c97da7400c8523be Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 17 Jun 2015 14:43:35 +0100 Subject: KVM: arm/arm64: vgic: Avoid injecting reserved IRQ numbers Commit fd1d0ddf2ae9 (KVM: arm/arm64: check IRQ number on userland injection) rightly limited the range of interrupts userspace can inject in a guest, but failed to consider the (unlikely) case where a guest is configured with 1024 interrupts. In this case, interrupts ranging from 1020 to 1023 are unuseable, as they have a special meaning for the GIC CPU interface. Make sure that these number cannot be used as an IRQ. Also delete a redundant (and similarily buggy) check in kvm_set_irq. Reported-by: Peter Maydell Cc: Andre Przywara Cc: # 4.1, 4.0, 3.19, 3.18 Signed-off-by: Marc Zyngier --- virt/kvm/arm/vgic.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index 78fb8201014f..950064a0942d 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -1561,7 +1561,7 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num, goto out; } - if (irq_num >= kvm->arch.vgic.nr_irqs) + if (irq_num >= min(kvm->arch.vgic.nr_irqs, 1020)) return -EINVAL; vcpu_id = vgic_update_irq_pending(kvm, cpuid, irq_num, level); @@ -2161,10 +2161,7 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, BUG_ON(!vgic_initialized(kvm)); - if (spi > kvm->arch.vgic.nr_irqs) - return -EINVAL; return kvm_vgic_inject_irq(kvm, 0, spi, level); - } /* MSI not implemented yet */ -- cgit v1.2.3 From c62e631d4a8e41493c6341d8259e996ed5fc11e3 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 18 Jun 2015 15:50:31 +0100 Subject: KVM: arm/arm64: vgic: Remove useless arm-gic.h #include Back in the days, vgic.c used to have an intimate knowledge of the actual GICv2. These days, this has been abstracted away into hardware-specific backends. Remove the now useless arm-gic.h #include directive, making it clear that GICv2 specific code doesn't belong here. Signed-off-by: Marc Zyngier --- virt/kvm/arm/vgic.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index 950064a0942d..f94d887d20e6 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -26,8 +26,6 @@ #include #include -#include - #include #include #include -- cgit v1.2.3 From e73f61e41f3bb9bc453fd9c21b82d0b89c2b83e7 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 8 May 2015 14:31:44 +0200 Subject: kvm: irqchip: Break up high order allocations of kvm_irq_routing_table The allocation size of the kvm_irq_routing_table depends on the number of irq routing entries because they are all allocated with one kzalloc call. When the irq routing table gets bigger this requires high order allocations which fail from time to time: qemu-kvm: page allocation failure: order:4, mode:0xd0 This patch fixes this issue by breaking up the allocation of the table and its entries into individual kzalloc calls. These could all be satisfied with order-0 allocations, which are less likely to fail. The downside of this change is the lower performance, because of more calls to kzalloc. But given how often kvm_set_irq_routing is called in the lifetime of a guest, it doesn't really matter much. Signed-off-by: Joerg Roedel [Avoid sparse warning through rcu_access_pointer. - Paolo] Signed-off-by: Paolo Bonzini --- virt/kvm/irqchip.c | 41 +++++++++++++++++++++++++++++++++-------- 1 file changed, 33 insertions(+), 8 deletions(-) diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c index 1d56a901e791..21c14244f4c4 100644 --- a/virt/kvm/irqchip.c +++ b/virt/kvm/irqchip.c @@ -33,7 +33,6 @@ struct kvm_irq_routing_table { int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS]; - struct kvm_kernel_irq_routing_entry *rt_entries; u32 nr_rt_entries; /* * Array indexed by gsi. Each entry contains list of irq chips @@ -118,11 +117,32 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, return ret; } +static void free_irq_routing_table(struct kvm_irq_routing_table *rt) +{ + int i; + + if (!rt) + return; + + for (i = 0; i < rt->nr_rt_entries; ++i) { + struct kvm_kernel_irq_routing_entry *e; + struct hlist_node *n; + + hlist_for_each_entry_safe(e, n, &rt->map[i], link) { + hlist_del(&e->link); + kfree(e); + } + } + + kfree(rt); +} + void kvm_free_irq_routing(struct kvm *kvm) { /* Called only during vm destruction. Nobody can use the pointer at this stage */ - kfree(kvm->irq_routing); + struct kvm_irq_routing_table *rt = rcu_access_pointer(kvm->irq_routing); + free_irq_routing_table(rt); } static int setup_routing_entry(struct kvm_irq_routing_table *rt, @@ -173,25 +193,29 @@ int kvm_set_irq_routing(struct kvm *kvm, nr_rt_entries += 1; - new = kzalloc(sizeof(*new) + (nr_rt_entries * sizeof(struct hlist_head)) - + (nr * sizeof(struct kvm_kernel_irq_routing_entry)), + new = kzalloc(sizeof(*new) + (nr_rt_entries * sizeof(struct hlist_head)), GFP_KERNEL); if (!new) return -ENOMEM; - new->rt_entries = (void *)&new->map[nr_rt_entries]; - new->nr_rt_entries = nr_rt_entries; for (i = 0; i < KVM_NR_IRQCHIPS; i++) for (j = 0; j < KVM_IRQCHIP_NUM_PINS; j++) new->chip[i][j] = -1; for (i = 0; i < nr; ++i) { + struct kvm_kernel_irq_routing_entry *e; + + r = -ENOMEM; + e = kzalloc(sizeof(*e), GFP_KERNEL); + if (!e) + goto out; + r = -EINVAL; if (ue->flags) goto out; - r = setup_routing_entry(new, &new->rt_entries[i], ue); + r = setup_routing_entry(new, e, ue); if (r) goto out; ++ue; @@ -209,6 +233,7 @@ int kvm_set_irq_routing(struct kvm *kvm, r = 0; out: - kfree(new); + free_irq_routing_table(new); + return r; } -- cgit v1.2.3 From d626f3d5b39e0fc8908fa044fa08cbbc4daeffce Mon Sep 17 00:00:00 2001 From: Kevin Mulvey Date: Tue, 16 Jun 2015 07:33:59 -0400 Subject: KVM: fix checkpatch.pl errors in kvm/async_pf.h fix brace spacing Signed-off-by: Kevin Mulvey Signed-off-by: Paolo Bonzini --- virt/kvm/async_pf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/virt/kvm/async_pf.h b/virt/kvm/async_pf.h index e7ef6447cb82..ec4cfa278f04 100644 --- a/virt/kvm/async_pf.h +++ b/virt/kvm/async_pf.h @@ -29,8 +29,8 @@ void kvm_async_pf_deinit(void); void kvm_async_pf_vcpu_init(struct kvm_vcpu *vcpu); #else #define kvm_async_pf_init() (0) -#define kvm_async_pf_deinit() do{}while(0) -#define kvm_async_pf_vcpu_init(C) do{}while(0) +#define kvm_async_pf_deinit() do {} while (0) +#define kvm_async_pf_vcpu_init(C) do {} while (0) #endif #endif -- cgit v1.2.3 From 0b8ba4a2b65860ac1fcd5be6cfca5d3b27a5b170 Mon Sep 17 00:00:00 2001 From: Kevin Mulvey Date: Tue, 16 Jun 2015 07:34:00 -0400 Subject: KVM: fix checkpatch.pl errors in kvm/coalesced_mmio.h Tabs rather than spaces Signed-off-by: Kevin Mulvey Signed-off-by: Paolo Bonzini --- virt/kvm/coalesced_mmio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/virt/kvm/coalesced_mmio.h b/virt/kvm/coalesced_mmio.h index b280c20444d1..5cbf190d238c 100644 --- a/virt/kvm/coalesced_mmio.h +++ b/virt/kvm/coalesced_mmio.h @@ -24,9 +24,9 @@ struct kvm_coalesced_mmio_dev { int kvm_coalesced_mmio_init(struct kvm *kvm); void kvm_coalesced_mmio_free(struct kvm *kvm); int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm, - struct kvm_coalesced_mmio_zone *zone); + struct kvm_coalesced_mmio_zone *zone); int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm, - struct kvm_coalesced_mmio_zone *zone); + struct kvm_coalesced_mmio_zone *zone); #else -- cgit v1.2.3 From f104765b4f81fd74d69e0eb161e89096deade2db Mon Sep 17 00:00:00 2001 From: Bandan Das Date: Thu, 11 Jun 2015 02:05:33 -0400 Subject: KVM: nSVM: Check for NRIPS support before updating control field If hardware doesn't support DecodeAssist - a feature that provides more information about the intercept in the VMCB, KVM decodes the instruction and then updates the next_rip vmcb control field. However, NRIP support itself depends on cpuid Fn8000_000A_EDX[NRIPS]. Since skip_emulated_instruction() doesn't verify nrip support before accepting control.next_rip as valid, avoid writing this field if support isn't present. Signed-off-by: Bandan Das Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 680753186489..e7685af399e4 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -511,8 +511,10 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - if (svm->vmcb->control.next_rip != 0) + if (svm->vmcb->control.next_rip != 0) { + WARN_ON(!static_cpu_has(X86_FEATURE_NRIPS)); svm->next_rip = svm->vmcb->control.next_rip; + } if (!svm->next_rip) { if (emulate_instruction(vcpu, EMULTYPE_SKIP) != @@ -4329,7 +4331,9 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu, break; } - vmcb->control.next_rip = info->next_rip; + /* TODO: Advertise NRIPS to guest hypervisor unconditionally */ + if (static_cpu_has(X86_FEATURE_NRIPS)) + vmcb->control.next_rip = info->next_rip; vmcb->control.exit_code = icpt_info.exit_code; vmexit = nested_svm_exit_handled(svm); -- cgit v1.2.3 From b18d5431acc7a2fd22767925f3a6f597aa4bd29e Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 15 Jun 2015 16:55:21 +0800 Subject: KVM: x86: fix CR0.CD virtualization Currently, CR0.CD is not checked when we virtualize memory cache type for noncoherent_dma guests, this patch fixes it by : - setting UC for all memory if CR0.CD = 1 - zapping all the last sptes in MMU if CR0.CD is changed Signed-off-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 32 ++++++++++++++++++++++---------- arch/x86/kvm/x86.c | 4 ++++ 2 files changed, 26 insertions(+), 10 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 06a186b07631..2764381a1b02 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -8628,7 +8628,8 @@ static int get_ept_level(void) static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { - u64 ret; + u8 cache; + u64 ipat = 0; /* For VT-d and EPT combination * 1. MMIO: always map as UC @@ -8641,16 +8642,27 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep * consistent with host MTRR */ - if (is_mmio) - ret = MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT; - else if (kvm_arch_has_noncoherent_dma(vcpu->kvm)) - ret = kvm_get_guest_memory_type(vcpu, gfn) << - VMX_EPT_MT_EPTE_SHIFT; - else - ret = (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) - | VMX_EPT_IPAT_BIT; + if (is_mmio) { + cache = MTRR_TYPE_UNCACHABLE; + goto exit; + } - return ret; + if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) { + ipat = VMX_EPT_IPAT_BIT; + cache = MTRR_TYPE_WRBACK; + goto exit; + } + + if (kvm_read_cr0(vcpu) & X86_CR0_CD) { + ipat = VMX_EPT_IPAT_BIT; + cache = MTRR_TYPE_UNCACHABLE; + goto exit; + } + + cache = kvm_get_guest_memory_type(vcpu, gfn); + +exit: + return (cache << VMX_EPT_MT_EPTE_SHIFT) | ipat; } static int vmx_get_lpage_level(void) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 43f0df7ddc9c..43fdb10c1580 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -621,6 +621,10 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if ((cr0 ^ old_cr0) & update_bits) kvm_mmu_reset_context(vcpu); + + if ((cr0 ^ old_cr0) & X86_CR0_CD) + kvm_zap_gfn_range(vcpu->kvm, 0, ~0ULL); + return 0; } EXPORT_SYMBOL_GPL(kvm_set_cr0); -- cgit v1.2.3 From ff53604b40b439cbb235f89bda99839ca81d3b9d Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 15 Jun 2015 16:55:22 +0800 Subject: KVM: x86: move MTRR related code to a separate file MTRR code locates in x86.c and mmu.c so that move them to a separate file to make the organization more clearer and it will be the place where we fully implement vMTRR Signed-off-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 1 - arch/x86/kvm/Makefile | 2 +- arch/x86/kvm/mmu.c | 103 ------------ arch/x86/kvm/mtrr.c | 335 ++++++++++++++++++++++++++++++++++++++++ arch/x86/kvm/vmx.c | 2 +- arch/x86/kvm/x86.c | 214 +------------------------ arch/x86/kvm/x86.h | 3 + 7 files changed, 342 insertions(+), 318 deletions(-) create mode 100644 arch/x86/kvm/mtrr.c diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 8ca32cfbcbd8..cf8d320dc7a5 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -894,7 +894,6 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3); int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, const void *val, int bytes); -u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn); struct kvm_irq_mask_notifier { void (*func)(struct kvm_irq_mask_notifier *kimn, bool masked); diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 16e8f962eaad..470dc6c9d409 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -12,7 +12,7 @@ kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \ kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ - i8254.o ioapic.o irq_comm.o cpuid.o pmu.o + i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += assigned-dev.o iommu.o kvm-intel-y += vmx.o kvm-amd-y += svm.o diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index c88f0e443669..532aad251cca 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2437,109 +2437,6 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page); -/* - * The function is based on mtrr_type_lookup() in - * arch/x86/kernel/cpu/mtrr/generic.c - */ -static int get_mtrr_type(struct mtrr_state_type *mtrr_state, - u64 start, u64 end) -{ - u64 base, mask; - u8 prev_match, curr_match; - int i, num_var_ranges = KVM_NR_VAR_MTRR; - - /* MTRR is completely disabled, use UC for all of physical memory. */ - if (!(mtrr_state->enabled & 0x2)) - return MTRR_TYPE_UNCACHABLE; - - /* Make end inclusive end, instead of exclusive */ - end--; - - /* Look in fixed ranges. Just return the type as per start */ - if (mtrr_state->have_fixed && (mtrr_state->enabled & 0x1) && - (start < 0x100000)) { - int idx; - - if (start < 0x80000) { - idx = 0; - idx += (start >> 16); - return mtrr_state->fixed_ranges[idx]; - } else if (start < 0xC0000) { - idx = 1 * 8; - idx += ((start - 0x80000) >> 14); - return mtrr_state->fixed_ranges[idx]; - } else if (start < 0x1000000) { - idx = 3 * 8; - idx += ((start - 0xC0000) >> 12); - return mtrr_state->fixed_ranges[idx]; - } - } - - /* - * Look in variable ranges - * Look of multiple ranges matching this address and pick type - * as per MTRR precedence - */ - prev_match = 0xFF; - for (i = 0; i < num_var_ranges; ++i) { - unsigned short start_state, end_state; - - if (!(mtrr_state->var_ranges[i].mask_lo & (1 << 11))) - continue; - - base = (((u64)mtrr_state->var_ranges[i].base_hi) << 32) + - (mtrr_state->var_ranges[i].base_lo & PAGE_MASK); - mask = (((u64)mtrr_state->var_ranges[i].mask_hi) << 32) + - (mtrr_state->var_ranges[i].mask_lo & PAGE_MASK); - - start_state = ((start & mask) == (base & mask)); - end_state = ((end & mask) == (base & mask)); - if (start_state != end_state) - return 0xFE; - - if ((start & mask) != (base & mask)) - continue; - - curr_match = mtrr_state->var_ranges[i].base_lo & 0xff; - if (prev_match == 0xFF) { - prev_match = curr_match; - continue; - } - - if (prev_match == MTRR_TYPE_UNCACHABLE || - curr_match == MTRR_TYPE_UNCACHABLE) - return MTRR_TYPE_UNCACHABLE; - - if ((prev_match == MTRR_TYPE_WRBACK && - curr_match == MTRR_TYPE_WRTHROUGH) || - (prev_match == MTRR_TYPE_WRTHROUGH && - curr_match == MTRR_TYPE_WRBACK)) { - prev_match = MTRR_TYPE_WRTHROUGH; - curr_match = MTRR_TYPE_WRTHROUGH; - } - - if (prev_match != curr_match) - return MTRR_TYPE_UNCACHABLE; - } - - if (prev_match != 0xFF) - return prev_match; - - return mtrr_state->def_type; -} - -u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) -{ - u8 mtrr; - - mtrr = get_mtrr_type(&vcpu->arch.mtrr_state, gfn << PAGE_SHIFT, - (gfn << PAGE_SHIFT) + PAGE_SIZE); - if (mtrr == 0xfe || mtrr == 0xff) - mtrr = MTRR_TYPE_WRBACK; - return mtrr; -} -EXPORT_SYMBOL_GPL(kvm_get_guest_memory_type); - static void __kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { trace_kvm_mmu_unsync_page(sp); diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c new file mode 100644 index 000000000000..fb2f7e10e8bc --- /dev/null +++ b/arch/x86/kvm/mtrr.c @@ -0,0 +1,335 @@ +/* + * vMTRR implementation + * + * Copyright (C) 2006 Qumranet, Inc. + * Copyright 2010 Red Hat, Inc. and/or its affiliates. + * Copyright(C) 2015 Intel Corporation. + * + * Authors: + * Yaniv Kamay + * Avi Kivity + * Marcelo Tosatti + * Paolo Bonzini + * Xiao Guangrong + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include +#include + +#include "cpuid.h" +#include "mmu.h" + +static bool msr_mtrr_valid(unsigned msr) +{ + switch (msr) { + case 0x200 ... 0x200 + 2 * KVM_NR_VAR_MTRR - 1: + case MSR_MTRRfix64K_00000: + case MSR_MTRRfix16K_80000: + case MSR_MTRRfix16K_A0000: + case MSR_MTRRfix4K_C0000: + case MSR_MTRRfix4K_C8000: + case MSR_MTRRfix4K_D0000: + case MSR_MTRRfix4K_D8000: + case MSR_MTRRfix4K_E0000: + case MSR_MTRRfix4K_E8000: + case MSR_MTRRfix4K_F0000: + case MSR_MTRRfix4K_F8000: + case MSR_MTRRdefType: + case MSR_IA32_CR_PAT: + return true; + case 0x2f8: + return true; + } + return false; +} + +static bool valid_pat_type(unsigned t) +{ + return t < 8 && (1 << t) & 0xf3; /* 0, 1, 4, 5, 6, 7 */ +} + +static bool valid_mtrr_type(unsigned t) +{ + return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */ +} + +bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + int i; + u64 mask; + + if (!msr_mtrr_valid(msr)) + return false; + + if (msr == MSR_IA32_CR_PAT) { + for (i = 0; i < 8; i++) + if (!valid_pat_type((data >> (i * 8)) & 0xff)) + return false; + return true; + } else if (msr == MSR_MTRRdefType) { + if (data & ~0xcff) + return false; + return valid_mtrr_type(data & 0xff); + } else if (msr >= MSR_MTRRfix64K_00000 && msr <= MSR_MTRRfix4K_F8000) { + for (i = 0; i < 8 ; i++) + if (!valid_mtrr_type((data >> (i * 8)) & 0xff)) + return false; + return true; + } + + /* variable MTRRs */ + WARN_ON(!(msr >= 0x200 && msr < 0x200 + 2 * KVM_NR_VAR_MTRR)); + + mask = (~0ULL) << cpuid_maxphyaddr(vcpu); + if ((msr & 1) == 0) { + /* MTRR base */ + if (!valid_mtrr_type(data & 0xff)) + return false; + mask |= 0xf00; + } else + /* MTRR mask */ + mask |= 0x7ff; + if (data & mask) { + kvm_inject_gp(vcpu, 0); + return false; + } + + return true; +} +EXPORT_SYMBOL_GPL(kvm_mtrr_valid); + +static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr) +{ + struct mtrr_state_type *mtrr_state = &vcpu->arch.mtrr_state; + unsigned char mtrr_enabled = mtrr_state->enabled; + gfn_t start, end, mask; + int index; + bool is_fixed = true; + + if (msr == MSR_IA32_CR_PAT || !tdp_enabled || + !kvm_arch_has_noncoherent_dma(vcpu->kvm)) + return; + + if (!(mtrr_enabled & 0x2) && msr != MSR_MTRRdefType) + return; + + switch (msr) { + case MSR_MTRRfix64K_00000: + start = 0x0; + end = 0x80000; + break; + case MSR_MTRRfix16K_80000: + start = 0x80000; + end = 0xa0000; + break; + case MSR_MTRRfix16K_A0000: + start = 0xa0000; + end = 0xc0000; + break; + case MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000: + index = msr - MSR_MTRRfix4K_C0000; + start = 0xc0000 + index * (32 << 10); + end = start + (32 << 10); + break; + case MSR_MTRRdefType: + is_fixed = false; + start = 0x0; + end = ~0ULL; + break; + default: + /* variable range MTRRs. */ + is_fixed = false; + index = (msr - 0x200) / 2; + start = (((u64)mtrr_state->var_ranges[index].base_hi) << 32) + + (mtrr_state->var_ranges[index].base_lo & PAGE_MASK); + mask = (((u64)mtrr_state->var_ranges[index].mask_hi) << 32) + + (mtrr_state->var_ranges[index].mask_lo & PAGE_MASK); + mask |= ~0ULL << cpuid_maxphyaddr(vcpu); + + end = ((start & mask) | ~mask) + 1; + } + + if (is_fixed && !(mtrr_enabled & 0x1)) + return; + + kvm_zap_gfn_range(vcpu->kvm, gpa_to_gfn(start), gpa_to_gfn(end)); +} + +int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges; + + if (!kvm_mtrr_valid(vcpu, msr, data)) + return 1; + + if (msr == MSR_MTRRdefType) { + vcpu->arch.mtrr_state.def_type = data; + vcpu->arch.mtrr_state.enabled = (data & 0xc00) >> 10; + } else if (msr == MSR_MTRRfix64K_00000) + p[0] = data; + else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000) + p[1 + msr - MSR_MTRRfix16K_80000] = data; + else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000) + p[3 + msr - MSR_MTRRfix4K_C0000] = data; + else if (msr == MSR_IA32_CR_PAT) + vcpu->arch.pat = data; + else { /* Variable MTRRs */ + int idx, is_mtrr_mask; + u64 *pt; + + idx = (msr - 0x200) / 2; + is_mtrr_mask = msr - 0x200 - 2 * idx; + if (!is_mtrr_mask) + pt = + (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo; + else + pt = + (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo; + *pt = data; + } + + update_mtrr(vcpu, msr); + return 0; +} + +int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges; + + if (!msr_mtrr_valid(msr)) + return 1; + + if (msr == MSR_MTRRdefType) + *pdata = vcpu->arch.mtrr_state.def_type + + (vcpu->arch.mtrr_state.enabled << 10); + else if (msr == MSR_MTRRfix64K_00000) + *pdata = p[0]; + else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000) + *pdata = p[1 + msr - MSR_MTRRfix16K_80000]; + else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000) + *pdata = p[3 + msr - MSR_MTRRfix4K_C0000]; + else if (msr == MSR_IA32_CR_PAT) + *pdata = vcpu->arch.pat; + else { /* Variable MTRRs */ + int idx, is_mtrr_mask; + u64 *pt; + + idx = (msr - 0x200) / 2; + is_mtrr_mask = msr - 0x200 - 2 * idx; + if (!is_mtrr_mask) + pt = + (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo; + else + pt = + (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo; + *pdata = *pt; + } + + return 0; +} + +/* + * The function is based on mtrr_type_lookup() in + * arch/x86/kernel/cpu/mtrr/generic.c + */ +static int get_mtrr_type(struct mtrr_state_type *mtrr_state, + u64 start, u64 end) +{ + u64 base, mask; + u8 prev_match, curr_match; + int i, num_var_ranges = KVM_NR_VAR_MTRR; + + /* MTRR is completely disabled, use UC for all of physical memory. */ + if (!(mtrr_state->enabled & 0x2)) + return MTRR_TYPE_UNCACHABLE; + + /* Make end inclusive end, instead of exclusive */ + end--; + + /* Look in fixed ranges. Just return the type as per start */ + if (mtrr_state->have_fixed && (mtrr_state->enabled & 0x1) && + (start < 0x100000)) { + int idx; + + if (start < 0x80000) { + idx = 0; + idx += (start >> 16); + return mtrr_state->fixed_ranges[idx]; + } else if (start < 0xC0000) { + idx = 1 * 8; + idx += ((start - 0x80000) >> 14); + return mtrr_state->fixed_ranges[idx]; + } else if (start < 0x1000000) { + idx = 3 * 8; + idx += ((start - 0xC0000) >> 12); + return mtrr_state->fixed_ranges[idx]; + } + } + + /* + * Look in variable ranges + * Look of multiple ranges matching this address and pick type + * as per MTRR precedence + */ + prev_match = 0xFF; + for (i = 0; i < num_var_ranges; ++i) { + unsigned short start_state, end_state; + + if (!(mtrr_state->var_ranges[i].mask_lo & (1 << 11))) + continue; + + base = (((u64)mtrr_state->var_ranges[i].base_hi) << 32) + + (mtrr_state->var_ranges[i].base_lo & PAGE_MASK); + mask = (((u64)mtrr_state->var_ranges[i].mask_hi) << 32) + + (mtrr_state->var_ranges[i].mask_lo & PAGE_MASK); + + start_state = ((start & mask) == (base & mask)); + end_state = ((end & mask) == (base & mask)); + if (start_state != end_state) + return 0xFE; + + if ((start & mask) != (base & mask)) + continue; + + curr_match = mtrr_state->var_ranges[i].base_lo & 0xff; + if (prev_match == 0xFF) { + prev_match = curr_match; + continue; + } + + if (prev_match == MTRR_TYPE_UNCACHABLE || + curr_match == MTRR_TYPE_UNCACHABLE) + return MTRR_TYPE_UNCACHABLE; + + if ((prev_match == MTRR_TYPE_WRBACK && + curr_match == MTRR_TYPE_WRTHROUGH) || + (prev_match == MTRR_TYPE_WRTHROUGH && + curr_match == MTRR_TYPE_WRBACK)) { + prev_match = MTRR_TYPE_WRTHROUGH; + curr_match = MTRR_TYPE_WRTHROUGH; + } + + if (prev_match != curr_match) + return MTRR_TYPE_UNCACHABLE; + } + + if (prev_match != 0xFF) + return prev_match; + + return mtrr_state->def_type; +} + +u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + u8 mtrr; + + mtrr = get_mtrr_type(&vcpu->arch.mtrr_state, gfn << PAGE_SHIFT, + (gfn << PAGE_SHIFT) + PAGE_SIZE); + if (mtrr == 0xfe || mtrr == 0xff) + mtrr = MTRR_TYPE_WRBACK; + return mtrr; +} +EXPORT_SYMBOL_GPL(kvm_mtrr_get_guest_memory_type); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 2764381a1b02..44eafdb440c9 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -8659,7 +8659,7 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) goto exit; } - cache = kvm_get_guest_memory_type(vcpu, gfn); + cache = kvm_mtrr_get_guest_memory_type(vcpu, gfn); exit: return (cache << VMX_EPT_MT_EPTE_SHIFT) | ipat; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 43fdb10c1580..e2bc79821b45 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -57,7 +57,6 @@ #include #include #include -#include #include #include #include /* Ugh! */ @@ -1803,179 +1802,6 @@ static void kvmclock_sync_fn(struct work_struct *work) KVMCLOCK_SYNC_PERIOD); } -static bool msr_mtrr_valid(unsigned msr) -{ - switch (msr) { - case 0x200 ... 0x200 + 2 * KVM_NR_VAR_MTRR - 1: - case MSR_MTRRfix64K_00000: - case MSR_MTRRfix16K_80000: - case MSR_MTRRfix16K_A0000: - case MSR_MTRRfix4K_C0000: - case MSR_MTRRfix4K_C8000: - case MSR_MTRRfix4K_D0000: - case MSR_MTRRfix4K_D8000: - case MSR_MTRRfix4K_E0000: - case MSR_MTRRfix4K_E8000: - case MSR_MTRRfix4K_F0000: - case MSR_MTRRfix4K_F8000: - case MSR_MTRRdefType: - case MSR_IA32_CR_PAT: - return true; - case 0x2f8: - return true; - } - return false; -} - -static bool valid_pat_type(unsigned t) -{ - return t < 8 && (1 << t) & 0xf3; /* 0, 1, 4, 5, 6, 7 */ -} - -static bool valid_mtrr_type(unsigned t) -{ - return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */ -} - -bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data) -{ - int i; - u64 mask; - - if (!msr_mtrr_valid(msr)) - return false; - - if (msr == MSR_IA32_CR_PAT) { - for (i = 0; i < 8; i++) - if (!valid_pat_type((data >> (i * 8)) & 0xff)) - return false; - return true; - } else if (msr == MSR_MTRRdefType) { - if (data & ~0xcff) - return false; - return valid_mtrr_type(data & 0xff); - } else if (msr >= MSR_MTRRfix64K_00000 && msr <= MSR_MTRRfix4K_F8000) { - for (i = 0; i < 8 ; i++) - if (!valid_mtrr_type((data >> (i * 8)) & 0xff)) - return false; - return true; - } - - /* variable MTRRs */ - WARN_ON(!(msr >= 0x200 && msr < 0x200 + 2 * KVM_NR_VAR_MTRR)); - - mask = (~0ULL) << cpuid_maxphyaddr(vcpu); - if ((msr & 1) == 0) { - /* MTRR base */ - if (!valid_mtrr_type(data & 0xff)) - return false; - mask |= 0xf00; - } else - /* MTRR mask */ - mask |= 0x7ff; - if (data & mask) { - kvm_inject_gp(vcpu, 0); - return false; - } - - return true; -} -EXPORT_SYMBOL_GPL(kvm_mtrr_valid); - -static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr) -{ - struct mtrr_state_type *mtrr_state = &vcpu->arch.mtrr_state; - unsigned char mtrr_enabled = mtrr_state->enabled; - gfn_t start, end, mask; - int index; - bool is_fixed = true; - - if (msr == MSR_IA32_CR_PAT || !tdp_enabled || - !kvm_arch_has_noncoherent_dma(vcpu->kvm)) - return; - - if (!(mtrr_enabled & 0x2) && msr != MSR_MTRRdefType) - return; - - switch (msr) { - case MSR_MTRRfix64K_00000: - start = 0x0; - end = 0x80000; - break; - case MSR_MTRRfix16K_80000: - start = 0x80000; - end = 0xa0000; - break; - case MSR_MTRRfix16K_A0000: - start = 0xa0000; - end = 0xc0000; - break; - case MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000: - index = msr - MSR_MTRRfix4K_C0000; - start = 0xc0000 + index * (32 << 10); - end = start + (32 << 10); - break; - case MSR_MTRRdefType: - is_fixed = false; - start = 0x0; - end = ~0ULL; - break; - default: - /* variable range MTRRs. */ - is_fixed = false; - index = (msr - 0x200) / 2; - start = (((u64)mtrr_state->var_ranges[index].base_hi) << 32) + - (mtrr_state->var_ranges[index].base_lo & PAGE_MASK); - mask = (((u64)mtrr_state->var_ranges[index].mask_hi) << 32) + - (mtrr_state->var_ranges[index].mask_lo & PAGE_MASK); - mask |= ~0ULL << cpuid_maxphyaddr(vcpu); - - end = ((start & mask) | ~mask) + 1; - } - - if (is_fixed && !(mtrr_enabled & 0x1)) - return; - - kvm_zap_gfn_range(vcpu->kvm, gpa_to_gfn(start), gpa_to_gfn(end)); -} - -static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data) -{ - u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges; - - if (!kvm_mtrr_valid(vcpu, msr, data)) - return 1; - - if (msr == MSR_MTRRdefType) { - vcpu->arch.mtrr_state.def_type = data; - vcpu->arch.mtrr_state.enabled = (data & 0xc00) >> 10; - } else if (msr == MSR_MTRRfix64K_00000) - p[0] = data; - else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000) - p[1 + msr - MSR_MTRRfix16K_80000] = data; - else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000) - p[3 + msr - MSR_MTRRfix4K_C0000] = data; - else if (msr == MSR_IA32_CR_PAT) - vcpu->arch.pat = data; - else { /* Variable MTRRs */ - int idx, is_mtrr_mask; - u64 *pt; - - idx = (msr - 0x200) / 2; - is_mtrr_mask = msr - 0x200 - 2 * idx; - if (!is_mtrr_mask) - pt = - (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo; - else - pt = - (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo; - *pt = data; - } - - update_mtrr(vcpu, msr); - return 0; -} - static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data) { u64 mcg_cap = vcpu->arch.mcg_cap; @@ -2267,7 +2093,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) __func__, data); break; case 0x200 ... 0x2ff: - return set_msr_mtrr(vcpu, msr, data); + return kvm_mtrr_set_msr(vcpu, msr, data); case MSR_IA32_APICBASE: return kvm_set_apic_base(vcpu, msr_info); case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: @@ -2479,42 +2305,6 @@ int kvm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) } EXPORT_SYMBOL_GPL(kvm_get_msr); -static int get_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) -{ - u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges; - - if (!msr_mtrr_valid(msr)) - return 1; - - if (msr == MSR_MTRRdefType) - *pdata = vcpu->arch.mtrr_state.def_type + - (vcpu->arch.mtrr_state.enabled << 10); - else if (msr == MSR_MTRRfix64K_00000) - *pdata = p[0]; - else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000) - *pdata = p[1 + msr - MSR_MTRRfix16K_80000]; - else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000) - *pdata = p[3 + msr - MSR_MTRRfix4K_C0000]; - else if (msr == MSR_IA32_CR_PAT) - *pdata = vcpu->arch.pat; - else { /* Variable MTRRs */ - int idx, is_mtrr_mask; - u64 *pt; - - idx = (msr - 0x200) / 2; - is_mtrr_mask = msr - 0x200 - 2 * idx; - if (!is_mtrr_mask) - pt = - (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo; - else - pt = - (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo; - *pdata = *pt; - } - - return 0; -} - static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) { u64 data; @@ -2656,7 +2446,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = 0x500 | KVM_NR_VAR_MTRR; break; case 0x200 ... 0x2ff: - return get_msr_mtrr(vcpu, msr_info->index, &msr_info->data); + return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data); case 0xcd: /* fsb frequency */ msr_info->data = 3; break; diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 01a1d011e073..aeb0bb2f1df4 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -162,7 +162,10 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception); +u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn); bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data); +int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data); +int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); #define KVM_SUPPORTED_XCR0 (XSTATE_FP | XSTATE_SSE | XSTATE_YMM \ | XSTATE_BNDREGS | XSTATE_BNDCSR \ -- cgit v1.2.3 From eb839917a75207b89799e3500211163cb6de0dea Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 15 Jun 2015 16:55:23 +0800 Subject: KVM: MTRR: handle MSR_MTRRcap in kvm_mtrr_get_msr MSR_MTRRcap is a MTRR msr so move the handler to the common place, also add some comments to make the hard code more readable Signed-off-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mtrr.c | 12 ++++++++++++ arch/x86/kvm/x86.c | 2 -- 2 files changed, 12 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index fb2f7e10e8bc..a05846a524d9 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -199,6 +199,18 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) { u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges; + /* MSR_MTRRcap is a readonly MSR. */ + if (msr == MSR_MTRRcap) { + /* + * SMRR = 0 + * WC = 1 + * FIX = 1 + * VCNT = KVM_NR_VAR_MTRR + */ + *pdata = 0x500 | KVM_NR_VAR_MTRR; + return 0; + } + if (!msr_mtrr_valid(msr)) return 1; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e2bc79821b45..fb6c9a11b5c1 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2443,8 +2443,6 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = 0x100000000ULL; break; case MSR_MTRRcap: - msr_info->data = 0x500 | KVM_NR_VAR_MTRR; - break; case 0x200 ... 0x2ff: return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data); case 0xcd: /* fsb frequency */ -- cgit v1.2.3 From 70109e7d9d4ac7182786ddf7cd53bc651a157896 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 15 Jun 2015 16:55:24 +0800 Subject: KVM: MTRR: remove mtrr_state.have_fixed vMTRR does not depend on any host MTRR feature and fixed MTRRs have always been implemented, so drop this field Signed-off-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 9 ++++++++- arch/x86/kvm/mtrr.c | 7 +++---- arch/x86/kvm/x86.c | 1 - 3 files changed, 11 insertions(+), 6 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index cf8d320dc7a5..cbf9f076f57c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -342,6 +342,13 @@ enum { KVM_DEBUGREG_RELOAD = 4, }; +struct kvm_mtrr { + struct mtrr_var_range var_ranges[MTRR_MAX_VAR_RANGES]; + mtrr_type fixed_ranges[KVM_NR_FIXED_MTRR_REGION]; + unsigned char enabled; + mtrr_type def_type; +}; + struct kvm_vcpu_arch { /* * rip and regs accesses must go through @@ -472,7 +479,7 @@ struct kvm_vcpu_arch { bool nmi_injected; /* Trying to inject an NMI this entry */ bool smi_pending; /* SMI queued after currently running handler */ - struct mtrr_state_type mtrr_state; + struct kvm_mtrr mtrr_state; u64 pat; unsigned switch_db_regs; diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index a05846a524d9..ce061fffc077 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -103,7 +103,7 @@ EXPORT_SYMBOL_GPL(kvm_mtrr_valid); static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr) { - struct mtrr_state_type *mtrr_state = &vcpu->arch.mtrr_state; + struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; unsigned char mtrr_enabled = mtrr_state->enabled; gfn_t start, end, mask; int index; @@ -247,7 +247,7 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) * The function is based on mtrr_type_lookup() in * arch/x86/kernel/cpu/mtrr/generic.c */ -static int get_mtrr_type(struct mtrr_state_type *mtrr_state, +static int get_mtrr_type(struct kvm_mtrr *mtrr_state, u64 start, u64 end) { u64 base, mask; @@ -262,8 +262,7 @@ static int get_mtrr_type(struct mtrr_state_type *mtrr_state, end--; /* Look in fixed ranges. Just return the type as per start */ - if (mtrr_state->have_fixed && (mtrr_state->enabled & 0x1) && - (start < 0x100000)) { + if ((mtrr_state->enabled & 0x1) && (start < 0x100000)) { int idx; if (start < 0x80000) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index fb6c9a11b5c1..2ffad7f2a28e 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7379,7 +7379,6 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { int r; - vcpu->arch.mtrr_state.have_fixed = 1; r = vcpu_load(vcpu); if (r) return r; -- cgit v1.2.3 From 910a6aae4e2e45855efc4a268e43eed2d8445575 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 15 Jun 2015 16:55:25 +0800 Subject: KVM: MTRR: exactly define the size of variable MTRRs Only KVM_NR_VAR_MTRR variable MTRRs are available in KVM guest Signed-off-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index cbf9f076f57c..fe9cbe49e272 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -343,7 +343,7 @@ enum { }; struct kvm_mtrr { - struct mtrr_var_range var_ranges[MTRR_MAX_VAR_RANGES]; + struct mtrr_var_range var_ranges[KVM_NR_VAR_MTRR]; mtrr_type fixed_ranges[KVM_NR_FIXED_MTRR_REGION]; unsigned char enabled; mtrr_type def_type; -- cgit v1.2.3 From 10fac2dc2b3b549d371d67f57193362b6bcc6dfd Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 15 Jun 2015 16:55:26 +0800 Subject: KVM: MTRR: clean up mtrr default type Drop kvm_mtrr->enable, omit the decode/code workload and get rid of all the hard code Signed-off-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 3 +-- arch/x86/kvm/mtrr.c | 40 ++++++++++++++++++++++++++++------------ 2 files changed, 29 insertions(+), 14 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index fe9cbe49e272..8d43006a6df0 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -345,8 +345,7 @@ enum { struct kvm_mtrr { struct mtrr_var_range var_ranges[KVM_NR_VAR_MTRR]; mtrr_type fixed_ranges[KVM_NR_FIXED_MTRR_REGION]; - unsigned char enabled; - mtrr_type def_type; + u64 deftype; }; struct kvm_vcpu_arch { diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index ce061fffc077..191de6435f23 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -22,6 +22,10 @@ #include "cpuid.h" #include "mmu.h" +#define IA32_MTRR_DEF_TYPE_E (1ULL << 11) +#define IA32_MTRR_DEF_TYPE_FE (1ULL << 10) +#define IA32_MTRR_DEF_TYPE_TYPE_MASK (0xff) + static bool msr_mtrr_valid(unsigned msr) { switch (msr) { @@ -101,10 +105,24 @@ bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data) } EXPORT_SYMBOL_GPL(kvm_mtrr_valid); +static bool mtrr_is_enabled(struct kvm_mtrr *mtrr_state) +{ + return !!(mtrr_state->deftype & IA32_MTRR_DEF_TYPE_E); +} + +static bool fixed_mtrr_is_enabled(struct kvm_mtrr *mtrr_state) +{ + return !!(mtrr_state->deftype & IA32_MTRR_DEF_TYPE_FE); +} + +static u8 mtrr_default_type(struct kvm_mtrr *mtrr_state) +{ + return mtrr_state->deftype & IA32_MTRR_DEF_TYPE_TYPE_MASK; +} + static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr) { struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; - unsigned char mtrr_enabled = mtrr_state->enabled; gfn_t start, end, mask; int index; bool is_fixed = true; @@ -113,7 +131,7 @@ static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr) !kvm_arch_has_noncoherent_dma(vcpu->kvm)) return; - if (!(mtrr_enabled & 0x2) && msr != MSR_MTRRdefType) + if (!mtrr_is_enabled(mtrr_state) && msr != MSR_MTRRdefType) return; switch (msr) { @@ -152,7 +170,7 @@ static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr) end = ((start & mask) | ~mask) + 1; } - if (is_fixed && !(mtrr_enabled & 0x1)) + if (is_fixed && !fixed_mtrr_is_enabled(mtrr_state)) return; kvm_zap_gfn_range(vcpu->kvm, gpa_to_gfn(start), gpa_to_gfn(end)); @@ -165,10 +183,9 @@ int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) if (!kvm_mtrr_valid(vcpu, msr, data)) return 1; - if (msr == MSR_MTRRdefType) { - vcpu->arch.mtrr_state.def_type = data; - vcpu->arch.mtrr_state.enabled = (data & 0xc00) >> 10; - } else if (msr == MSR_MTRRfix64K_00000) + if (msr == MSR_MTRRdefType) + vcpu->arch.mtrr_state.deftype = data; + else if (msr == MSR_MTRRfix64K_00000) p[0] = data; else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000) p[1 + msr - MSR_MTRRfix16K_80000] = data; @@ -215,8 +232,7 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) return 1; if (msr == MSR_MTRRdefType) - *pdata = vcpu->arch.mtrr_state.def_type + - (vcpu->arch.mtrr_state.enabled << 10); + *pdata = vcpu->arch.mtrr_state.deftype; else if (msr == MSR_MTRRfix64K_00000) *pdata = p[0]; else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000) @@ -255,14 +271,14 @@ static int get_mtrr_type(struct kvm_mtrr *mtrr_state, int i, num_var_ranges = KVM_NR_VAR_MTRR; /* MTRR is completely disabled, use UC for all of physical memory. */ - if (!(mtrr_state->enabled & 0x2)) + if (!mtrr_is_enabled(mtrr_state)) return MTRR_TYPE_UNCACHABLE; /* Make end inclusive end, instead of exclusive */ end--; /* Look in fixed ranges. Just return the type as per start */ - if ((mtrr_state->enabled & 0x1) && (start < 0x100000)) { + if (fixed_mtrr_is_enabled(mtrr_state) && (start < 0x100000)) { int idx; if (start < 0x80000) { @@ -330,7 +346,7 @@ static int get_mtrr_type(struct kvm_mtrr *mtrr_state, if (prev_match != 0xFF) return prev_match; - return mtrr_state->def_type; + return mtrr_default_type(mtrr_state); } u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) -- cgit v1.2.3 From 86fd52701cfae760711fb02a03c1ab8c80ea72f3 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 15 Jun 2015 16:55:27 +0800 Subject: KVM: MTRR: do not split 64 bits MSR content Variable MTRR MSRs are 64 bits which are directly accessed with full length, no reason to split them to two 32 bits Signed-off-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 7 ++++++- arch/x86/kvm/mtrr.c | 32 ++++++++++---------------------- 2 files changed, 16 insertions(+), 23 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 8d43006a6df0..f73554874845 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -342,8 +342,13 @@ enum { KVM_DEBUGREG_RELOAD = 4, }; +struct kvm_mtrr_range { + u64 base; + u64 mask; +}; + struct kvm_mtrr { - struct mtrr_var_range var_ranges[KVM_NR_VAR_MTRR]; + struct kvm_mtrr_range var_ranges[KVM_NR_VAR_MTRR]; mtrr_type fixed_ranges[KVM_NR_FIXED_MTRR_REGION]; u64 deftype; }; diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 191de6435f23..c4b80a46a530 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -161,10 +161,8 @@ static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr) /* variable range MTRRs. */ is_fixed = false; index = (msr - 0x200) / 2; - start = (((u64)mtrr_state->var_ranges[index].base_hi) << 32) + - (mtrr_state->var_ranges[index].base_lo & PAGE_MASK); - mask = (((u64)mtrr_state->var_ranges[index].mask_hi) << 32) + - (mtrr_state->var_ranges[index].mask_lo & PAGE_MASK); + start = mtrr_state->var_ranges[index].base & PAGE_MASK; + mask = mtrr_state->var_ranges[index].mask & PAGE_MASK; mask |= ~0ULL << cpuid_maxphyaddr(vcpu); end = ((start & mask) | ~mask) + 1; @@ -195,17 +193,13 @@ int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) vcpu->arch.pat = data; else { /* Variable MTRRs */ int idx, is_mtrr_mask; - u64 *pt; idx = (msr - 0x200) / 2; is_mtrr_mask = msr - 0x200 - 2 * idx; if (!is_mtrr_mask) - pt = - (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo; + vcpu->arch.mtrr_state.var_ranges[idx].base = data; else - pt = - (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo; - *pt = data; + vcpu->arch.mtrr_state.var_ranges[idx].mask = data; } update_mtrr(vcpu, msr); @@ -243,17 +237,13 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) *pdata = vcpu->arch.pat; else { /* Variable MTRRs */ int idx, is_mtrr_mask; - u64 *pt; idx = (msr - 0x200) / 2; is_mtrr_mask = msr - 0x200 - 2 * idx; if (!is_mtrr_mask) - pt = - (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo; + *pdata = vcpu->arch.mtrr_state.var_ranges[idx].base; else - pt = - (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo; - *pdata = *pt; + *pdata = vcpu->arch.mtrr_state.var_ranges[idx].mask; } return 0; @@ -305,13 +295,11 @@ static int get_mtrr_type(struct kvm_mtrr *mtrr_state, for (i = 0; i < num_var_ranges; ++i) { unsigned short start_state, end_state; - if (!(mtrr_state->var_ranges[i].mask_lo & (1 << 11))) + if (!(mtrr_state->var_ranges[i].mask & (1 << 11))) continue; - base = (((u64)mtrr_state->var_ranges[i].base_hi) << 32) + - (mtrr_state->var_ranges[i].base_lo & PAGE_MASK); - mask = (((u64)mtrr_state->var_ranges[i].mask_hi) << 32) + - (mtrr_state->var_ranges[i].mask_lo & PAGE_MASK); + base = mtrr_state->var_ranges[i].base & PAGE_MASK; + mask = mtrr_state->var_ranges[i].mask & PAGE_MASK; start_state = ((start & mask) == (base & mask)); end_state = ((end & mask) == (base & mask)); @@ -321,7 +309,7 @@ static int get_mtrr_type(struct kvm_mtrr *mtrr_state, if ((start & mask) != (base & mask)) continue; - curr_match = mtrr_state->var_ranges[i].base_lo & 0xff; + curr_match = mtrr_state->var_ranges[i].base & 0xff; if (prev_match == 0xFF) { prev_match = curr_match; continue; -- cgit v1.2.3 From 3f3f78b61462fdc62469334c259b1e5555ebd1ed Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 15 Jun 2015 16:55:28 +0800 Subject: KVM: MTRR: improve kvm_mtrr_get_guest_memory_type - kvm_mtrr_get_guest_memory_type() only checks one page in MTRRs so that it's unnecessary to check to see if the range is partially covered in MTRR - optimize the check of overlap memory type and add some comments to explain the precedence Signed-off-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mtrr.c | 94 ++++++++++++++++++++++++++++------------------------- 1 file changed, 49 insertions(+), 45 deletions(-) diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index c4b80a46a530..2ea12130e74a 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -249,24 +249,22 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) return 0; } -/* - * The function is based on mtrr_type_lookup() in - * arch/x86/kernel/cpu/mtrr/generic.c - */ -static int get_mtrr_type(struct kvm_mtrr *mtrr_state, - u64 start, u64 end) +u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) { - u64 base, mask; - u8 prev_match, curr_match; - int i, num_var_ranges = KVM_NR_VAR_MTRR; + struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; + u64 base, mask, start; + int i, num_var_ranges, type; + const int wt_wb_mask = (1 << MTRR_TYPE_WRBACK) + | (1 << MTRR_TYPE_WRTHROUGH); + + start = gfn_to_gpa(gfn); + num_var_ranges = KVM_NR_VAR_MTRR; + type = -1; /* MTRR is completely disabled, use UC for all of physical memory. */ if (!mtrr_is_enabled(mtrr_state)) return MTRR_TYPE_UNCACHABLE; - /* Make end inclusive end, instead of exclusive */ - end--; - /* Look in fixed ranges. Just return the type as per start */ if (fixed_mtrr_is_enabled(mtrr_state) && (start < 0x100000)) { int idx; @@ -291,9 +289,8 @@ static int get_mtrr_type(struct kvm_mtrr *mtrr_state, * Look of multiple ranges matching this address and pick type * as per MTRR precedence */ - prev_match = 0xFF; for (i = 0; i < num_var_ranges; ++i) { - unsigned short start_state, end_state; + int curr_type; if (!(mtrr_state->var_ranges[i].mask & (1 << 11))) continue; @@ -301,50 +298,57 @@ static int get_mtrr_type(struct kvm_mtrr *mtrr_state, base = mtrr_state->var_ranges[i].base & PAGE_MASK; mask = mtrr_state->var_ranges[i].mask & PAGE_MASK; - start_state = ((start & mask) == (base & mask)); - end_state = ((end & mask) == (base & mask)); - if (start_state != end_state) - return 0xFE; - if ((start & mask) != (base & mask)) continue; - curr_match = mtrr_state->var_ranges[i].base & 0xff; - if (prev_match == 0xFF) { - prev_match = curr_match; + /* + * Please refer to Intel SDM Volume 3: 11.11.4.1 MTRR + * Precedences. + */ + + curr_type = mtrr_state->var_ranges[i].base & 0xff; + if (type == -1) { + type = curr_type; continue; } - if (prev_match == MTRR_TYPE_UNCACHABLE || - curr_match == MTRR_TYPE_UNCACHABLE) + /* + * If two or more variable memory ranges match and the + * memory types are identical, then that memory type is + * used. + */ + if (type == curr_type) + continue; + + /* + * If two or more variable memory ranges match and one of + * the memory types is UC, the UC memory type used. + */ + if (curr_type == MTRR_TYPE_UNCACHABLE) return MTRR_TYPE_UNCACHABLE; - if ((prev_match == MTRR_TYPE_WRBACK && - curr_match == MTRR_TYPE_WRTHROUGH) || - (prev_match == MTRR_TYPE_WRTHROUGH && - curr_match == MTRR_TYPE_WRBACK)) { - prev_match = MTRR_TYPE_WRTHROUGH; - curr_match = MTRR_TYPE_WRTHROUGH; + /* + * If two or more variable memory ranges match and the + * memory types are WT and WB, the WT memory type is used. + */ + if (((1 << type) & wt_wb_mask) && + ((1 << curr_type) & wt_wb_mask)) { + type = MTRR_TYPE_WRTHROUGH; + continue; } - if (prev_match != curr_match) - return MTRR_TYPE_UNCACHABLE; + /* + * For overlaps not defined by the above rules, processor + * behavior is undefined. + */ + + /* We use WB for this undefined behavior. :( */ + return MTRR_TYPE_WRBACK; } - if (prev_match != 0xFF) - return prev_match; + if (type != -1) + return type; return mtrr_default_type(mtrr_state); } - -u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) -{ - u8 mtrr; - - mtrr = get_mtrr_type(&vcpu->arch.mtrr_state, gfn << PAGE_SHIFT, - (gfn << PAGE_SHIFT) + PAGE_SIZE); - if (mtrr == 0xfe || mtrr == 0xff) - mtrr = MTRR_TYPE_WRBACK; - return mtrr; -} EXPORT_SYMBOL_GPL(kvm_mtrr_get_guest_memory_type); -- cgit v1.2.3 From de9aef5e1ad6e504d6992df17dfa193e8ba5cc34 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 15 Jun 2015 16:55:29 +0800 Subject: KVM: MTRR: introduce fixed_mtrr_segment table This table summarizes the information of fixed MTRRs and introduce some APIs to abstract its operation which helps us to clean up the code and will be used in later patches Signed-off-by: Xiao Guangrong [Change range_size to range_shift, in order to avoid udivdi3 errors. - Paolo] Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mtrr.c | 200 ++++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 147 insertions(+), 53 deletions(-) diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 2ea12130e74a..cfeeaef9e419 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -120,12 +120,132 @@ static u8 mtrr_default_type(struct kvm_mtrr *mtrr_state) return mtrr_state->deftype & IA32_MTRR_DEF_TYPE_TYPE_MASK; } +/* +* Three terms are used in the following code: +* - segment, it indicates the address segments covered by fixed MTRRs. +* - unit, it corresponds to the MSR entry in the segment. +* - range, a range is covered in one memory cache type. +*/ +struct fixed_mtrr_segment { + u64 start; + u64 end; + + int range_shift; + + /* the start position in kvm_mtrr.fixed_ranges[]. */ + int range_start; +}; + +static struct fixed_mtrr_segment fixed_seg_table[] = { + /* MSR_MTRRfix64K_00000, 1 unit. 64K fixed mtrr. */ + { + .start = 0x0, + .end = 0x80000, + .range_shift = 16, /* 64K */ + .range_start = 0, + }, + + /* + * MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000, 2 units, + * 16K fixed mtrr. + */ + { + .start = 0x80000, + .end = 0xc0000, + .range_shift = 14, /* 16K */ + .range_start = 8, + }, + + /* + * MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000, 8 units, + * 4K fixed mtrr. + */ + { + .start = 0xc0000, + .end = 0x100000, + .range_shift = 12, /* 12K */ + .range_start = 24, + } +}; + +/* + * The size of unit is covered in one MSR, one MSR entry contains + * 8 ranges so that unit size is always 8 * 2^range_shift. + */ +static u64 fixed_mtrr_seg_unit_size(int seg) +{ + return 8 << fixed_seg_table[seg].range_shift; +} + +static bool fixed_msr_to_seg_unit(u32 msr, int *seg, int *unit) +{ + switch (msr) { + case MSR_MTRRfix64K_00000: + *seg = 0; + *unit = 0; + break; + case MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000: + *seg = 1; + *unit = msr - MSR_MTRRfix16K_80000; + break; + case MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000: + *seg = 2; + *unit = msr - MSR_MTRRfix4K_C0000; + break; + default: + return false; + } + + return true; +} + +static void fixed_mtrr_seg_unit_range(int seg, int unit, u64 *start, u64 *end) +{ + struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg]; + u64 unit_size = fixed_mtrr_seg_unit_size(seg); + + *start = mtrr_seg->start + unit * unit_size; + *end = *start + unit_size; + WARN_ON(*end > mtrr_seg->end); +} + +static int fixed_mtrr_seg_unit_range_index(int seg, int unit) +{ + struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg]; + + WARN_ON(mtrr_seg->start + unit * fixed_mtrr_seg_unit_size(seg) + > mtrr_seg->end); + + /* each unit has 8 ranges. */ + return mtrr_seg->range_start + 8 * unit; +} + +static bool fixed_msr_to_range(u32 msr, u64 *start, u64 *end) +{ + int seg, unit; + + if (!fixed_msr_to_seg_unit(msr, &seg, &unit)) + return false; + + fixed_mtrr_seg_unit_range(seg, unit, start, end); + return true; +} + +static int fixed_msr_to_range_index(u32 msr) +{ + int seg, unit; + + if (!fixed_msr_to_seg_unit(msr, &seg, &unit)) + return -1; + + return fixed_mtrr_seg_unit_range_index(seg, unit); +} + static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr) { struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; gfn_t start, end, mask; int index; - bool is_fixed = true; if (msr == MSR_IA32_CR_PAT || !tdp_enabled || !kvm_arch_has_noncoherent_dma(vcpu->kvm)) @@ -134,32 +254,15 @@ static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr) if (!mtrr_is_enabled(mtrr_state) && msr != MSR_MTRRdefType) return; - switch (msr) { - case MSR_MTRRfix64K_00000: - start = 0x0; - end = 0x80000; - break; - case MSR_MTRRfix16K_80000: - start = 0x80000; - end = 0xa0000; - break; - case MSR_MTRRfix16K_A0000: - start = 0xa0000; - end = 0xc0000; - break; - case MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000: - index = msr - MSR_MTRRfix4K_C0000; - start = 0xc0000 + index * (32 << 10); - end = start + (32 << 10); - break; - case MSR_MTRRdefType: - is_fixed = false; + /* fixed MTRRs. */ + if (fixed_msr_to_range(msr, &start, &end)) { + if (!fixed_mtrr_is_enabled(mtrr_state)) + return; + } else if (msr == MSR_MTRRdefType) { start = 0x0; end = ~0ULL; - break; - default: + } else { /* variable range MTRRs. */ - is_fixed = false; index = (msr - 0x200) / 2; start = mtrr_state->var_ranges[index].base & PAGE_MASK; mask = mtrr_state->var_ranges[index].mask & PAGE_MASK; @@ -168,38 +271,32 @@ static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr) end = ((start & mask) | ~mask) + 1; } - if (is_fixed && !fixed_mtrr_is_enabled(mtrr_state)) - return; - kvm_zap_gfn_range(vcpu->kvm, gpa_to_gfn(start), gpa_to_gfn(end)); } int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) { - u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges; + int index; if (!kvm_mtrr_valid(vcpu, msr, data)) return 1; - if (msr == MSR_MTRRdefType) + index = fixed_msr_to_range_index(msr); + if (index >= 0) + *(u64 *)&vcpu->arch.mtrr_state.fixed_ranges[index] = data; + else if (msr == MSR_MTRRdefType) vcpu->arch.mtrr_state.deftype = data; - else if (msr == MSR_MTRRfix64K_00000) - p[0] = data; - else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000) - p[1 + msr - MSR_MTRRfix16K_80000] = data; - else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000) - p[3 + msr - MSR_MTRRfix4K_C0000] = data; else if (msr == MSR_IA32_CR_PAT) vcpu->arch.pat = data; else { /* Variable MTRRs */ - int idx, is_mtrr_mask; + int is_mtrr_mask; - idx = (msr - 0x200) / 2; - is_mtrr_mask = msr - 0x200 - 2 * idx; + index = (msr - 0x200) / 2; + is_mtrr_mask = msr - 0x200 - 2 * index; if (!is_mtrr_mask) - vcpu->arch.mtrr_state.var_ranges[idx].base = data; + vcpu->arch.mtrr_state.var_ranges[index].base = data; else - vcpu->arch.mtrr_state.var_ranges[idx].mask = data; + vcpu->arch.mtrr_state.var_ranges[index].mask = data; } update_mtrr(vcpu, msr); @@ -208,7 +305,7 @@ int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) { - u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges; + int index; /* MSR_MTRRcap is a readonly MSR. */ if (msr == MSR_MTRRcap) { @@ -225,25 +322,22 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) if (!msr_mtrr_valid(msr)) return 1; - if (msr == MSR_MTRRdefType) + index = fixed_msr_to_range_index(msr); + if (index >= 0) + *pdata = *(u64 *)&vcpu->arch.mtrr_state.fixed_ranges[index]; + else if (msr == MSR_MTRRdefType) *pdata = vcpu->arch.mtrr_state.deftype; - else if (msr == MSR_MTRRfix64K_00000) - *pdata = p[0]; - else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000) - *pdata = p[1 + msr - MSR_MTRRfix16K_80000]; - else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000) - *pdata = p[3 + msr - MSR_MTRRfix4K_C0000]; else if (msr == MSR_IA32_CR_PAT) *pdata = vcpu->arch.pat; else { /* Variable MTRRs */ - int idx, is_mtrr_mask; + int is_mtrr_mask; - idx = (msr - 0x200) / 2; - is_mtrr_mask = msr - 0x200 - 2 * idx; + index = (msr - 0x200) / 2; + is_mtrr_mask = msr - 0x200 - 2 * index; if (!is_mtrr_mask) - *pdata = vcpu->arch.mtrr_state.var_ranges[idx].base; + *pdata = vcpu->arch.mtrr_state.var_ranges[index].base; else - *pdata = vcpu->arch.mtrr_state.var_ranges[idx].mask; + *pdata = vcpu->arch.mtrr_state.var_ranges[index].mask; } return 0; -- cgit v1.2.3 From a13842dc668b40daef4327294a6d3bdc8bd30276 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 15 Jun 2015 16:55:30 +0800 Subject: KVM: MTRR: introduce var_mtrr_range It gets the range for the specified variable MTRR Signed-off-by: Xiao Guangrong [Simplify boolean operations. - Paolo] Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mtrr.c | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index cfeeaef9e419..b081e3ba186f 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -241,10 +241,25 @@ static int fixed_msr_to_range_index(u32 msr) return fixed_mtrr_seg_unit_range_index(seg, unit); } +static void var_mtrr_range(struct kvm_mtrr_range *range, u64 *start, u64 *end) +{ + u64 mask; + + *start = range->base & PAGE_MASK; + + mask = range->mask & PAGE_MASK; + mask |= ~0ULL << boot_cpu_data.x86_phys_bits; + + /* This cannot overflow because writing to the reserved bits of + * variable MTRRs causes a #GP. + */ + *end = (*start | ~mask) + 1; +} + static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr) { struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; - gfn_t start, end, mask; + gfn_t start, end; int index; if (msr == MSR_IA32_CR_PAT || !tdp_enabled || @@ -264,11 +279,7 @@ static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr) } else { /* variable range MTRRs. */ index = (msr - 0x200) / 2; - start = mtrr_state->var_ranges[index].base & PAGE_MASK; - mask = mtrr_state->var_ranges[index].mask & PAGE_MASK; - mask |= ~0ULL << cpuid_maxphyaddr(vcpu); - - end = ((start & mask) | ~mask) + 1; + var_mtrr_range(&mtrr_state->var_ranges[index], &start, &end); } kvm_zap_gfn_range(vcpu->kvm, gpa_to_gfn(start), gpa_to_gfn(end)); -- cgit v1.2.3 From 19efffa244071ccd0385b240d03adb38feaab04e Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 15 Jun 2015 16:55:31 +0800 Subject: KVM: MTRR: sort variable MTRRs Sort all valid variable MTRRs based on its base address, it will help us to check a range to see if it's fully contained in variable MTRRs Signed-off-by: Xiao Guangrong [Fix list insertion sort, simplify var_mtrr_range_is_valid to just test the V bit. - Paolo] Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 3 +++ arch/x86/kvm/mtrr.c | 50 ++++++++++++++++++++++++++++++++--------- arch/x86/kvm/x86.c | 2 +- arch/x86/kvm/x86.h | 1 + 4 files changed, 45 insertions(+), 11 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f73554874845..f2d60cce7595 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -345,12 +345,15 @@ enum { struct kvm_mtrr_range { u64 base; u64 mask; + struct list_head node; }; struct kvm_mtrr { struct kvm_mtrr_range var_ranges[KVM_NR_VAR_MTRR]; mtrr_type fixed_ranges[KVM_NR_FIXED_MTRR_REGION]; u64 deftype; + + struct list_head head; }; struct kvm_vcpu_arch { diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index b081e3ba186f..faa582488bb8 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -285,6 +285,39 @@ static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr) kvm_zap_gfn_range(vcpu->kvm, gpa_to_gfn(start), gpa_to_gfn(end)); } +static bool var_mtrr_range_is_valid(struct kvm_mtrr_range *range) +{ + return (range->mask & (1 << 11)) != 0; +} + +static void set_var_mtrr_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; + struct kvm_mtrr_range *tmp, *cur; + int index, is_mtrr_mask; + + index = (msr - 0x200) / 2; + is_mtrr_mask = msr - 0x200 - 2 * index; + cur = &mtrr_state->var_ranges[index]; + + /* remove the entry if it's in the list. */ + if (var_mtrr_range_is_valid(cur)) + list_del(&mtrr_state->var_ranges[index].node); + + if (!is_mtrr_mask) + cur->base = data; + else + cur->mask = data; + + /* add it to the list if it's enabled. */ + if (var_mtrr_range_is_valid(cur)) { + list_for_each_entry(tmp, &mtrr_state->head, node) + if (cur->base >= tmp->base) + break; + list_add_tail(&cur->node, &tmp->node); + } +} + int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) { int index; @@ -299,16 +332,8 @@ int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) vcpu->arch.mtrr_state.deftype = data; else if (msr == MSR_IA32_CR_PAT) vcpu->arch.pat = data; - else { /* Variable MTRRs */ - int is_mtrr_mask; - - index = (msr - 0x200) / 2; - is_mtrr_mask = msr - 0x200 - 2 * index; - if (!is_mtrr_mask) - vcpu->arch.mtrr_state.var_ranges[index].base = data; - else - vcpu->arch.mtrr_state.var_ranges[index].mask = data; - } + else + set_var_mtrr_msr(vcpu, msr, data); update_mtrr(vcpu, msr); return 0; @@ -354,6 +379,11 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) return 0; } +void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu) +{ + INIT_LIST_HEAD(&vcpu->arch.mtrr_state.head); +} + u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) { struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2ffad7f2a28e..6574fa36cb65 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7379,13 +7379,13 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { int r; + kvm_vcpu_mtrr_init(vcpu); r = vcpu_load(vcpu); if (r) return r; kvm_vcpu_reset(vcpu, false); kvm_mmu_setup(vcpu); vcpu_put(vcpu); - return r; } diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index aeb0bb2f1df4..0e4727c49279 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -162,6 +162,7 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception); +void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu); u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn); bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data); int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data); -- cgit v1.2.3 From f7bfb57b3e89ff89c0da9f93dedab89f68d6ca27 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 15 Jun 2015 16:55:32 +0800 Subject: KVM: MTRR: introduce fixed_mtrr_addr_* functions Two functions are introduced: - fixed_mtrr_addr_to_seg() translates the address to the fixed MTRR segment - fixed_mtrr_addr_seg_to_range_index() translates the address to the index of kvm_mtrr.fixed_ranges[] They will be used in the later patch Signed-off-by: Xiao Guangrong [Adjust for range_size->range_shift change. - Paolo] Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mtrr.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index faa582488bb8..b5346d20f458 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -241,6 +241,31 @@ static int fixed_msr_to_range_index(u32 msr) return fixed_mtrr_seg_unit_range_index(seg, unit); } +static int fixed_mtrr_addr_to_seg(u64 addr) +{ + struct fixed_mtrr_segment *mtrr_seg; + int seg, seg_num = ARRAY_SIZE(fixed_seg_table); + + for (seg = 0; seg < seg_num; seg++) { + mtrr_seg = &fixed_seg_table[seg]; + if (mtrr_seg->start >= addr && addr < mtrr_seg->end) + return seg; + } + + return -1; +} + +static int fixed_mtrr_addr_seg_to_range_index(u64 addr, int seg) +{ + struct fixed_mtrr_segment *mtrr_seg; + int index; + + mtrr_seg = &fixed_seg_table[seg]; + index = mtrr_seg->range_start; + index += (addr - mtrr_seg->start) >> mtrr_seg->range_shift; + return index; +} + static void var_mtrr_range(struct kvm_mtrr_range *range, u64 *start, u64 *end) { u64 mask; -- cgit v1.2.3 From f571c0973e4b8c888e049b6842e4b4f93b5c609c Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 15 Jun 2015 16:55:33 +0800 Subject: KVM: MTRR: introduce mtrr_for_each_mem_type It walks all MTRRs and gets all the memory cache type setting for the specified range also it checks if the range is fully covered by MTRRs Signed-off-by: Xiao Guangrong [Adjust for range_size->range_shift change. - Paolo] Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mtrr.c | 188 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 188 insertions(+) diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index b5346d20f458..4c6ac464063e 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -220,6 +220,15 @@ static int fixed_mtrr_seg_unit_range_index(int seg, int unit) return mtrr_seg->range_start + 8 * unit; } +static int fixed_mtrr_seg_end_range_index(int seg) +{ + struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg]; + int n; + + n = (mtrr_seg->end - mtrr_seg->start) >> mtrr_seg->range_shift; + return mtrr_seg->range_start + n - 1; +} + static bool fixed_msr_to_range(u32 msr, u64 *start, u64 *end) { int seg, unit; @@ -266,6 +275,14 @@ static int fixed_mtrr_addr_seg_to_range_index(u64 addr, int seg) return index; } +static u64 fixed_mtrr_range_end_addr(int seg, int index) +{ + struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg]; + int pos = index - mtrr_seg->range_start; + + return mtrr_seg->start + ((pos + 1) << mtrr_seg->range_shift); +} + static void var_mtrr_range(struct kvm_mtrr_range *range, u64 *start, u64 *end) { u64 mask; @@ -409,6 +426,177 @@ void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu) INIT_LIST_HEAD(&vcpu->arch.mtrr_state.head); } +struct mtrr_iter { + /* input fields. */ + struct kvm_mtrr *mtrr_state; + u64 start; + u64 end; + + /* output fields. */ + int mem_type; + /* [start, end) is not fully covered in MTRRs? */ + bool partial_map; + + /* private fields. */ + union { + /* used for fixed MTRRs. */ + struct { + int index; + int seg; + }; + + /* used for var MTRRs. */ + struct { + struct kvm_mtrr_range *range; + /* max address has been covered in var MTRRs. */ + u64 start_max; + }; + }; + + bool fixed; +}; + +static bool mtrr_lookup_fixed_start(struct mtrr_iter *iter) +{ + int seg, index; + + if (!fixed_mtrr_is_enabled(iter->mtrr_state)) + return false; + + seg = fixed_mtrr_addr_to_seg(iter->start); + if (seg < 0) + return false; + + iter->fixed = true; + index = fixed_mtrr_addr_seg_to_range_index(iter->start, seg); + iter->index = index; + iter->seg = seg; + return true; +} + +static bool match_var_range(struct mtrr_iter *iter, + struct kvm_mtrr_range *range) +{ + u64 start, end; + + var_mtrr_range(range, &start, &end); + if (!(start >= iter->end || end <= iter->start)) { + iter->range = range; + + /* + * the function is called when we do kvm_mtrr.head walking. + * Range has the minimum base address which interleaves + * [looker->start_max, looker->end). + */ + iter->partial_map |= iter->start_max < start; + + /* update the max address has been covered. */ + iter->start_max = max(iter->start_max, end); + return true; + } + + return false; +} + +static void __mtrr_lookup_var_next(struct mtrr_iter *iter) +{ + struct kvm_mtrr *mtrr_state = iter->mtrr_state; + + list_for_each_entry_continue(iter->range, &mtrr_state->head, node) + if (match_var_range(iter, iter->range)) + return; + + iter->range = NULL; + iter->partial_map |= iter->start_max < iter->end; +} + +static void mtrr_lookup_var_start(struct mtrr_iter *iter) +{ + struct kvm_mtrr *mtrr_state = iter->mtrr_state; + + iter->fixed = false; + iter->start_max = iter->start; + iter->range = list_prepare_entry(iter->range, &mtrr_state->head, node); + + __mtrr_lookup_var_next(iter); +} + +static void mtrr_lookup_fixed_next(struct mtrr_iter *iter) +{ + /* terminate the lookup. */ + if (fixed_mtrr_range_end_addr(iter->seg, iter->index) >= iter->end) { + iter->fixed = false; + iter->range = NULL; + return; + } + + iter->index++; + + /* have looked up for all fixed MTRRs. */ + if (iter->index >= ARRAY_SIZE(iter->mtrr_state->fixed_ranges)) + return mtrr_lookup_var_start(iter); + + /* switch to next segment. */ + if (iter->index > fixed_mtrr_seg_end_range_index(iter->seg)) + iter->seg++; +} + +static void mtrr_lookup_var_next(struct mtrr_iter *iter) +{ + __mtrr_lookup_var_next(iter); +} + +static void mtrr_lookup_start(struct mtrr_iter *iter) +{ + if (!mtrr_is_enabled(iter->mtrr_state)) { + iter->partial_map = true; + return; + } + + if (!mtrr_lookup_fixed_start(iter)) + mtrr_lookup_var_start(iter); +} + +static void mtrr_lookup_init(struct mtrr_iter *iter, + struct kvm_mtrr *mtrr_state, u64 start, u64 end) +{ + iter->mtrr_state = mtrr_state; + iter->start = start; + iter->end = end; + iter->partial_map = false; + iter->fixed = false; + iter->range = NULL; + + mtrr_lookup_start(iter); +} + +static bool mtrr_lookup_okay(struct mtrr_iter *iter) +{ + if (iter->fixed) { + iter->mem_type = iter->mtrr_state->fixed_ranges[iter->index]; + return true; + } + + if (iter->range) { + iter->mem_type = iter->range->base & 0xff; + return true; + } + + return false; +} + +static void mtrr_lookup_next(struct mtrr_iter *iter) +{ + if (iter->fixed) + mtrr_lookup_fixed_next(iter); + else + mtrr_lookup_var_next(iter); +} + +#define mtrr_for_each_mem_type(_iter_, _mtrr_, _gpa_start_, _gpa_end_) \ + for (mtrr_lookup_init(_iter_, _mtrr_, _gpa_start_, _gpa_end_); \ + mtrr_lookup_okay(_iter_); mtrr_lookup_next(_iter_)) + u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) { struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; -- cgit v1.2.3 From fa61213746a706dd975661151c35795ca4dd82c2 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 15 Jun 2015 16:55:34 +0800 Subject: KVM: MTRR: simplify kvm_mtrr_get_guest_memory_type mtrr_for_each_mem_type() is ready now, use it to simplify kvm_mtrr_get_guest_memory_type() Signed-off-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mtrr.c | 64 ++++++++++++++--------------------------------------- 1 file changed, 16 insertions(+), 48 deletions(-) diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 4c6ac464063e..1445c4a03a92 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -600,61 +600,23 @@ static void mtrr_lookup_next(struct mtrr_iter *iter) u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) { struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; - u64 base, mask, start; - int i, num_var_ranges, type; + struct mtrr_iter iter; + u64 start, end; + int type = -1; const int wt_wb_mask = (1 << MTRR_TYPE_WRBACK) | (1 << MTRR_TYPE_WRTHROUGH); start = gfn_to_gpa(gfn); - num_var_ranges = KVM_NR_VAR_MTRR; - type = -1; - - /* MTRR is completely disabled, use UC for all of physical memory. */ - if (!mtrr_is_enabled(mtrr_state)) - return MTRR_TYPE_UNCACHABLE; - - /* Look in fixed ranges. Just return the type as per start */ - if (fixed_mtrr_is_enabled(mtrr_state) && (start < 0x100000)) { - int idx; - - if (start < 0x80000) { - idx = 0; - idx += (start >> 16); - return mtrr_state->fixed_ranges[idx]; - } else if (start < 0xC0000) { - idx = 1 * 8; - idx += ((start - 0x80000) >> 14); - return mtrr_state->fixed_ranges[idx]; - } else if (start < 0x1000000) { - idx = 3 * 8; - idx += ((start - 0xC0000) >> 12); - return mtrr_state->fixed_ranges[idx]; - } - } - - /* - * Look in variable ranges - * Look of multiple ranges matching this address and pick type - * as per MTRR precedence - */ - for (i = 0; i < num_var_ranges; ++i) { - int curr_type; - - if (!(mtrr_state->var_ranges[i].mask & (1 << 11))) - continue; - - base = mtrr_state->var_ranges[i].base & PAGE_MASK; - mask = mtrr_state->var_ranges[i].mask & PAGE_MASK; + end = start + PAGE_SIZE; - if ((start & mask) != (base & mask)) - continue; + mtrr_for_each_mem_type(&iter, mtrr_state, start, end) { + int curr_type = iter.mem_type; /* * Please refer to Intel SDM Volume 3: 11.11.4.1 MTRR * Precedences. */ - curr_type = mtrr_state->var_ranges[i].base & 0xff; if (type == -1) { type = curr_type; continue; @@ -694,9 +656,15 @@ u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) return MTRR_TYPE_WRBACK; } - if (type != -1) - return type; - - return mtrr_default_type(mtrr_state); + /* It is not covered by MTRRs. */ + if (iter.partial_map) { + /* + * We just check one page, partially covered by MTRRs is + * impossible. + */ + WARN_ON(type != -1); + type = mtrr_default_type(mtrr_state); + } + return type; } EXPORT_SYMBOL_GPL(kvm_mtrr_get_guest_memory_type); -- cgit v1.2.3 From 6a39bbc5da27c3b2520876b71e4f7b50f5313503 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 15 Jun 2015 16:55:35 +0800 Subject: KVM: MTRR: do not map huge page for non-consistent range Based on Intel's SDM, mapping huge page which do not have consistent memory cache for each 4k page will cause undefined behavior In order to avoiding this kind of undefined behavior, we force to use 4k pages under this case Signed-off-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu.c | 20 +++++++++++++++++++- arch/x86/kvm/mtrr.c | 29 +++++++++++++++++++++++++++++ arch/x86/kvm/x86.h | 2 ++ 3 files changed, 50 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 532aad251cca..f807496b62c2 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3446,6 +3446,16 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, return false; } +static bool +check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level) +{ + int page_num = KVM_PAGES_PER_HPAGE(level); + + gfn &= ~(page_num - 1); + + return kvm_mtrr_check_gfn_range_consistency(vcpu, gfn, page_num); +} + static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, bool prefault) { @@ -3471,9 +3481,17 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, if (r) return r; - force_pt_level = mapping_level_dirty_bitmap(vcpu, gfn); + if (mapping_level_dirty_bitmap(vcpu, gfn) || + !check_hugepage_cache_consistency(vcpu, gfn, PT_DIRECTORY_LEVEL)) + force_pt_level = 1; + else + force_pt_level = 0; + if (likely(!force_pt_level)) { level = mapping_level(vcpu, gfn); + if (level > PT_DIRECTORY_LEVEL && + !check_hugepage_cache_consistency(vcpu, gfn, level)) + level = PT_DIRECTORY_LEVEL; gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); } else level = PT_PAGE_TABLE_LEVEL; diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 1445c4a03a92..de1d2d8062e2 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -668,3 +668,32 @@ u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) return type; } EXPORT_SYMBOL_GPL(kvm_mtrr_get_guest_memory_type); + +bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, + int page_num) +{ + struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; + struct mtrr_iter iter; + u64 start, end; + int type = -1; + + start = gfn_to_gpa(gfn); + end = gfn_to_gpa(gfn + page_num); + mtrr_for_each_mem_type(&iter, mtrr_state, start, end) { + if (type == -1) { + type = iter.mem_type; + continue; + } + + if (type != iter.mem_type) + return false; + } + + if (!iter.partial_map) + return true; + + if (type == -1) + return true; + + return type == mtrr_default_type(mtrr_state); +} diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 0e4727c49279..edc8cdcd786b 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -167,6 +167,8 @@ u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn); bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data); int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data); int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); +bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, + int page_num); #define KVM_SUPPORTED_XCR0 (XSTATE_FP | XSTATE_SSE | XSTATE_YMM \ | XSTATE_BNDREGS | XSTATE_BNDCSR \ -- cgit v1.2.3 From c6702c9dcfe72b63a85e7ae35533c11e2b7c1040 Mon Sep 17 00:00:00 2001 From: Wei Huang Date: Fri, 19 Jun 2015 13:44:45 +0200 Subject: KVM: x86/vPMU: rename a few PMU functions Before introducing a pmu.h header for them, make the naming more consistent. Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 12 ++++---- arch/x86/kvm/cpuid.c | 2 +- arch/x86/kvm/pmu.c | 66 ++++++++++++++++++++--------------------- arch/x86/kvm/x86.c | 18 +++++------ 4 files changed, 49 insertions(+), 49 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f2d60cce7595..d92d7edc016b 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1198,14 +1198,14 @@ int kvm_is_in_guest(void); void kvm_pmu_init(struct kvm_vcpu *vcpu); void kvm_pmu_destroy(struct kvm_vcpu *vcpu); void kvm_pmu_reset(struct kvm_vcpu *vcpu); -void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu); -bool kvm_pmu_msr(struct kvm_vcpu *vcpu, u32 msr); +void kvm_pmu_refresh(struct kvm_vcpu *vcpu); +bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr); int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data); int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); -int kvm_pmu_check_pmc(struct kvm_vcpu *vcpu, unsigned pmc); -int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data); -void kvm_handle_pmu_event(struct kvm_vcpu *vcpu); -void kvm_deliver_pmi(struct kvm_vcpu *vcpu); +int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned pmc); +int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data); +void kvm_pmu_handle_event(struct kvm_vcpu *vcpu); +void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu); int __x86_set_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 9dadf8d67873..9d69f76aa0fa 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -111,7 +111,7 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) /* Update physical-address width */ vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); - kvm_pmu_cpuid_update(vcpu); + kvm_pmu_refresh(vcpu); return 0; } diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 29fbf9dfdc54..d6a4506f62a8 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -52,7 +52,7 @@ static inline u64 pmc_bitmask(struct kvm_pmc *pmc) return pmu->counter_bitmask[pmc->type]; } -static inline bool pmc_enabled(struct kvm_pmc *pmc) +static inline bool pmc_is_enabled(struct kvm_pmc *pmc) { struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; return test_bit(pmc->idx, (unsigned long *)&pmu->global_ctrl); @@ -87,20 +87,20 @@ static struct kvm_pmc *global_idx_to_pmc(struct kvm_pmu *pmu, int idx) return get_fixed_pmc_idx(pmu, idx - INTEL_PMC_IDX_FIXED); } -void kvm_deliver_pmi(struct kvm_vcpu *vcpu) +void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu) { if (vcpu->arch.apic) kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTPC); } -static void trigger_pmi(struct irq_work *irq_work) +static void kvm_pmi_trigger_fn(struct irq_work *irq_work) { struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, irq_work); struct kvm_vcpu *vcpu = container_of(pmu, struct kvm_vcpu, arch.pmu); - kvm_deliver_pmi(vcpu); + kvm_pmu_deliver_pmi(vcpu); } static void kvm_perf_overflow(struct perf_event *perf_event, @@ -138,7 +138,7 @@ static void kvm_perf_overflow_intr(struct perf_event *perf_event, } } -static u64 read_pmc(struct kvm_pmc *pmc) +static u64 pmc_read_counter(struct kvm_pmc *pmc) { u64 counter, enabled, running; @@ -153,16 +153,16 @@ static u64 read_pmc(struct kvm_pmc *pmc) return counter & pmc_bitmask(pmc); } -static void stop_counter(struct kvm_pmc *pmc) +static void pmc_stop_counter(struct kvm_pmc *pmc) { if (pmc->perf_event) { - pmc->counter = read_pmc(pmc); + pmc->counter = pmc_read_counter(pmc); perf_event_release_kernel(pmc->perf_event); pmc->perf_event = NULL; } } -static void reprogram_counter(struct kvm_pmc *pmc, u32 type, +static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, unsigned config, bool exclude_user, bool exclude_kernel, bool intr, bool in_tx, bool in_tx_cp) { @@ -224,9 +224,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) pmc->eventsel = eventsel; - stop_counter(pmc); + pmc_stop_counter(pmc); - if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_enabled(pmc)) + if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_is_enabled(pmc)) return; event_select = eventsel & ARCH_PERFMON_EVENTSEL_EVENT; @@ -246,7 +246,7 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) if (type == PERF_TYPE_RAW) config = eventsel & X86_RAW_EVENT_MASK; - reprogram_counter(pmc, type, config, + pmc_reprogram_counter(pmc, type, config, !(eventsel & ARCH_PERFMON_EVENTSEL_USR), !(eventsel & ARCH_PERFMON_EVENTSEL_OS), eventsel & ARCH_PERFMON_EVENTSEL_INT, @@ -259,19 +259,19 @@ static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx) unsigned en = en_pmi & 0x3; bool pmi = en_pmi & 0x8; - stop_counter(pmc); + pmc_stop_counter(pmc); - if (!en || !pmc_enabled(pmc)) + if (!en || !pmc_is_enabled(pmc)) return; - reprogram_counter(pmc, PERF_TYPE_HARDWARE, + pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE, arch_events[fixed_pmc_events[idx]].event_type, !(en & 0x2), /* exclude user */ !(en & 0x1), /* exclude kernel */ pmi, false, false); } -static inline u8 fixed_en_pmi(u64 ctrl, int idx) +static inline u8 fixed_ctrl_field(u64 ctrl, int idx) { return (ctrl >> (idx * 4)) & 0xf; } @@ -281,10 +281,10 @@ static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) int i; for (i = 0; i < pmu->nr_arch_fixed_counters; i++) { - u8 en_pmi = fixed_en_pmi(data, i); + u8 en_pmi = fixed_ctrl_field(data, i); struct kvm_pmc *pmc = get_fixed_pmc_idx(pmu, i); - if (fixed_en_pmi(pmu->fixed_ctr_ctrl, i) == en_pmi) + if (fixed_ctrl_field(pmu->fixed_ctr_ctrl, i) == en_pmi) continue; reprogram_fixed_counter(pmc, en_pmi, i); @@ -293,7 +293,7 @@ static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) pmu->fixed_ctr_ctrl = data; } -static void reprogram_idx(struct kvm_pmu *pmu, int idx) +static void reprogram_counter(struct kvm_pmu *pmu, int idx) { struct kvm_pmc *pmc = global_idx_to_pmc(pmu, idx); @@ -305,7 +305,7 @@ static void reprogram_idx(struct kvm_pmu *pmu, int idx) else { int fidx = idx - INTEL_PMC_IDX_FIXED; reprogram_fixed_counter(pmc, - fixed_en_pmi(pmu->fixed_ctr_ctrl, fidx), fidx); + fixed_ctrl_field(pmu->fixed_ctr_ctrl, fidx), fidx); } } @@ -317,10 +317,10 @@ static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data) pmu->global_ctrl = data; for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) - reprogram_idx(pmu, bit); + reprogram_counter(pmu, bit); } -bool kvm_pmu_msr(struct kvm_vcpu *vcpu, u32 msr) +bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) { struct kvm_pmu *pmu = &vcpu->arch.pmu; int ret; @@ -362,7 +362,7 @@ int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data) default: if ((pmc = get_gp_pmc(pmu, index, MSR_IA32_PERFCTR0)) || (pmc = get_fixed_pmc(pmu, index))) { - *data = read_pmc(pmc); + *data = pmc_read_counter(pmc); return 0; } else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) { *data = pmc->eventsel; @@ -415,7 +415,7 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) (pmc = get_fixed_pmc(pmu, index))) { if (!msr_info->host_initiated) data = (s64)(s32)data; - pmc->counter += data - read_pmc(pmc); + pmc->counter += data - pmc_read_counter(pmc); return 0; } else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) { if (data == pmc->eventsel) @@ -429,7 +429,7 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; } -int kvm_pmu_check_pmc(struct kvm_vcpu *vcpu, unsigned pmc) +int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned pmc) { struct kvm_pmu *pmu = &vcpu->arch.pmu; bool fixed = pmc & (1u << 30); @@ -438,7 +438,7 @@ int kvm_pmu_check_pmc(struct kvm_vcpu *vcpu, unsigned pmc) (fixed && pmc >= pmu->nr_arch_fixed_counters); } -int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data) +int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data) { struct kvm_pmu *pmu = &vcpu->arch.pmu; bool fast_mode = pmc & (1u << 31); @@ -452,7 +452,7 @@ int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data) if (fixed && pmc >= pmu->nr_arch_fixed_counters) return 1; counters = fixed ? pmu->fixed_counters : pmu->gp_counters; - ctr = read_pmc(&counters[pmc]); + ctr = pmc_read_counter(&counters[pmc]); if (fast_mode) ctr = (u32)ctr; *data = ctr; @@ -460,7 +460,7 @@ int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data) return 0; } -void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu) +void kvm_pmu_refresh(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = &vcpu->arch.pmu; struct kvm_cpuid_entry2 *entry; @@ -527,8 +527,8 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu) pmu->fixed_counters[i].vcpu = vcpu; pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED; } - init_irq_work(&pmu->irq_work, trigger_pmi); - kvm_pmu_cpuid_update(vcpu); + init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn); + kvm_pmu_refresh(vcpu); } void kvm_pmu_reset(struct kvm_vcpu *vcpu) @@ -539,12 +539,12 @@ void kvm_pmu_reset(struct kvm_vcpu *vcpu) irq_work_sync(&pmu->irq_work); for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { struct kvm_pmc *pmc = &pmu->gp_counters[i]; - stop_counter(pmc); + pmc_stop_counter(pmc); pmc->counter = pmc->eventsel = 0; } for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) - stop_counter(&pmu->fixed_counters[i]); + pmc_stop_counter(&pmu->fixed_counters[i]); pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = pmu->global_ovf_ctrl = 0; @@ -555,7 +555,7 @@ void kvm_pmu_destroy(struct kvm_vcpu *vcpu) kvm_pmu_reset(vcpu); } -void kvm_handle_pmu_event(struct kvm_vcpu *vcpu) +void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = &vcpu->arch.pmu; u64 bitmask; @@ -571,6 +571,6 @@ void kvm_handle_pmu_event(struct kvm_vcpu *vcpu) continue; } - reprogram_idx(pmu, bit); + reprogram_counter(pmu, bit); } } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6574fa36cb65..c34b52c828ea 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -913,7 +913,7 @@ bool kvm_rdpmc(struct kvm_vcpu *vcpu) u64 data; int err; - err = kvm_pmu_read_pmc(vcpu, ecx, &data); + err = kvm_pmu_rdpmc(vcpu, ecx, &data); if (err) return err; kvm_register_write(vcpu, VCPU_REGS_RAX, (u32)data); @@ -2231,7 +2231,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) pr = true; case MSR_P6_EVNTSEL0: case MSR_P6_EVNTSEL1: - if (kvm_pmu_msr(vcpu, msr)) + if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); if (pr || data != 0) @@ -2277,7 +2277,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) default: if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr)) return xen_hvm_config(vcpu, data); - if (kvm_pmu_msr(vcpu, msr)) + if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); if (!ignore_msrs) { vcpu_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", @@ -2435,7 +2435,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_P6_PERFCTR1: case MSR_P6_EVNTSEL0: case MSR_P6_EVNTSEL1: - if (kvm_pmu_msr(vcpu, msr_info->index)) + if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data); msr_info->data = 0; break; @@ -2561,7 +2561,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.osvw.status; break; default: - if (kvm_pmu_msr(vcpu, msr_info->index)) + if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data); if (!ignore_msrs) { vcpu_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr_info->index); @@ -4966,13 +4966,13 @@ static void emulator_set_smbase(struct x86_emulate_ctxt *ctxt, u64 smbase) static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt, u32 pmc) { - return kvm_pmu_check_pmc(emul_to_vcpu(ctxt), pmc); + return kvm_pmu_is_valid_msr_idx(emul_to_vcpu(ctxt), pmc); } static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt, u32 pmc, u64 *pdata) { - return kvm_pmu_read_pmc(emul_to_vcpu(ctxt), pmc, pdata); + return kvm_pmu_rdpmc(emul_to_vcpu(ctxt), pmc, pdata); } static void emulator_halt(struct x86_emulate_ctxt *ctxt) @@ -6542,9 +6542,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_NMI, vcpu)) process_nmi(vcpu); if (kvm_check_request(KVM_REQ_PMU, vcpu)) - kvm_handle_pmu_event(vcpu); + kvm_pmu_handle_event(vcpu); if (kvm_check_request(KVM_REQ_PMI, vcpu)) - kvm_deliver_pmi(vcpu); + kvm_pmu_deliver_pmi(vcpu); if (kvm_check_request(KVM_REQ_SCAN_IOAPIC, vcpu)) vcpu_scan_ioapic(vcpu); if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu)) -- cgit v1.2.3 From 474a5bb944d2ad308a1360dcae72b16b8eecd250 Mon Sep 17 00:00:00 2001 From: Wei Huang Date: Fri, 19 Jun 2015 13:54:23 +0200 Subject: KVM: x86/vPMU: introduce pmu.h header This will be used for private function used by AMD- and Intel-specific PMU implementations. Signed-off-by: Wei Huang Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 12 ------------ arch/x86/kvm/cpuid.c | 1 + arch/x86/kvm/pmu.c | 8 ++------ arch/x86/kvm/pmu.h | 26 ++++++++++++++++++++++++++ arch/x86/kvm/x86.c | 1 + 5 files changed, 30 insertions(+), 18 deletions(-) create mode 100644 arch/x86/kvm/pmu.h diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d92d7edc016b..534dfa324e35 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1195,18 +1195,6 @@ void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err); int kvm_is_in_guest(void); -void kvm_pmu_init(struct kvm_vcpu *vcpu); -void kvm_pmu_destroy(struct kvm_vcpu *vcpu); -void kvm_pmu_reset(struct kvm_vcpu *vcpu); -void kvm_pmu_refresh(struct kvm_vcpu *vcpu); -bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr); -int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data); -int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); -int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned pmc); -int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data); -void kvm_pmu_handle_event(struct kvm_vcpu *vcpu); -void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu); - int __x86_set_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem); int x86_set_memory_region(struct kvm *kvm, diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 9d69f76aa0fa..a64cc76ea92f 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -24,6 +24,7 @@ #include "lapic.h" #include "mmu.h" #include "trace.h" +#include "pmu.h" static u32 xstate_required_size(u64 xstate_bv, bool compacted) { diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index d6a4506f62a8..3d2990207be2 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -19,13 +19,9 @@ #include "x86.h" #include "cpuid.h" #include "lapic.h" +#include "pmu.h" -static struct kvm_arch_event_perf_mapping { - u8 eventsel; - u8 unit_mask; - unsigned event_type; - bool inexact; -} arch_events[] = { +static struct kvm_event_hw_type_mapping arch_events[] = { /* Index must match CPUID 0x0A.EBX bit vector */ [0] = { 0x3c, 0x00, PERF_COUNT_HW_CPU_CYCLES }, [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h new file mode 100644 index 000000000000..19bf0172f93b --- /dev/null +++ b/arch/x86/kvm/pmu.h @@ -0,0 +1,26 @@ +#ifndef __KVM_X86_PMU_H +#define __KVM_X86_PMU_H + +#define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu) +#define pmu_to_vcpu(pmu) (container_of((pmu), struct kvm_vcpu, arch.pmu)) +#define pmc_to_pmu(pmc) (&(pmc)->vcpu->arch.pmu) + +struct kvm_event_hw_type_mapping { + u8 eventsel; + u8 unit_mask; + unsigned event_type; +}; + +void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu); +void kvm_pmu_handle_event(struct kvm_vcpu *vcpu); +int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data); +int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx); +bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr); +int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data); +int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); +void kvm_pmu_refresh(struct kvm_vcpu *vcpu); +void kvm_pmu_reset(struct kvm_vcpu *vcpu); +void kvm_pmu_init(struct kvm_vcpu *vcpu); +void kvm_pmu_destroy(struct kvm_vcpu *vcpu); + +#endif /* __KVM_X86_PMU_H */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c34b52c828ea..c386f0bd1830 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -28,6 +28,7 @@ #include "x86.h" #include "cpuid.h" #include "assigned-dev.h" +#include "pmu.h" #include #include -- cgit v1.2.3 From 212dba1267a1be228635014fa35c98a59853de9e Mon Sep 17 00:00:00 2001 From: Wei Huang Date: Fri, 19 Jun 2015 14:00:33 +0200 Subject: KVM: x86/vPMU: use the new macros to go between PMC, PMU and VCPU Signed-off-by: Wei Huang Signed-off-by: Paolo Bonzini --- arch/x86/kvm/pmu.c | 38 ++++++++++++++++++-------------------- 1 file changed, 18 insertions(+), 20 deletions(-) diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 3d2990207be2..38819bc923cf 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -43,14 +43,14 @@ static bool pmc_is_gp(struct kvm_pmc *pmc) static inline u64 pmc_bitmask(struct kvm_pmc *pmc) { - struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; + struct kvm_pmu *pmu = pmc_to_pmu(pmc); return pmu->counter_bitmask[pmc->type]; } static inline bool pmc_is_enabled(struct kvm_pmc *pmc) { - struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; + struct kvm_pmu *pmu = pmc_to_pmu(pmc); return test_bit(pmc->idx, (unsigned long *)&pmu->global_ctrl); } @@ -91,10 +91,8 @@ void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu) static void kvm_pmi_trigger_fn(struct irq_work *irq_work) { - struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, - irq_work); - struct kvm_vcpu *vcpu = container_of(pmu, struct kvm_vcpu, - arch.pmu); + struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, irq_work); + struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); kvm_pmu_deliver_pmi(vcpu); } @@ -104,7 +102,7 @@ static void kvm_perf_overflow(struct perf_event *perf_event, struct pt_regs *regs) { struct kvm_pmc *pmc = perf_event->overflow_handler_context; - struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; + struct kvm_pmu *pmu = pmc_to_pmu(pmc); if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) { __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); kvm_make_request(KVM_REQ_PMU, pmc->vcpu); @@ -115,7 +113,7 @@ static void kvm_perf_overflow_intr(struct perf_event *perf_event, struct perf_sample_data *data, struct pt_regs *regs) { struct kvm_pmc *pmc = perf_event->overflow_handler_context; - struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; + struct kvm_pmu *pmu = pmc_to_pmu(pmc); if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) { __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); kvm_make_request(KVM_REQ_PMU, pmc->vcpu); @@ -128,7 +126,7 @@ static void kvm_perf_overflow_intr(struct perf_event *perf_event, * NMI context. Do it from irq work instead. */ if (!kvm_is_in_guest()) - irq_work_queue(&pmc->vcpu->arch.pmu.irq_work); + irq_work_queue(&pmc_to_pmu(pmc)->irq_work); else kvm_make_request(KVM_REQ_PMI, pmc->vcpu); } @@ -190,7 +188,7 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, } pmc->perf_event = event; - clear_bit(pmc->idx, (unsigned long*)&pmc->vcpu->arch.pmu.reprogram_pmi); + clear_bit(pmc->idx, (unsigned long*)&pmc_to_pmu(pmc)->reprogram_pmi); } static unsigned find_arch_event(struct kvm_pmu *pmu, u8 event_select, @@ -233,7 +231,7 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) ARCH_PERFMON_EVENTSEL_CMASK | HSW_IN_TX | HSW_IN_TX_CHECKPOINTED))) { - config = find_arch_event(&pmc->vcpu->arch.pmu, event_select, + config = find_arch_event(pmc_to_pmu(pmc), event_select, unit_mask); if (config != PERF_COUNT_HW_MAX) type = PERF_TYPE_HARDWARE; @@ -318,7 +316,7 @@ static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data) bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) { - struct kvm_pmu *pmu = &vcpu->arch.pmu; + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); int ret; switch (msr) { @@ -339,7 +337,7 @@ bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data) { - struct kvm_pmu *pmu = &vcpu->arch.pmu; + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct kvm_pmc *pmc; switch (index) { @@ -370,7 +368,7 @@ int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data) int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { - struct kvm_pmu *pmu = &vcpu->arch.pmu; + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct kvm_pmc *pmc; u32 index = msr_info->index; u64 data = msr_info->data; @@ -427,7 +425,7 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned pmc) { - struct kvm_pmu *pmu = &vcpu->arch.pmu; + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); bool fixed = pmc & (1u << 30); pmc &= ~(3u << 30); return (!fixed && pmc >= pmu->nr_arch_gp_counters) || @@ -436,7 +434,7 @@ int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned pmc) int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data) { - struct kvm_pmu *pmu = &vcpu->arch.pmu; + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); bool fast_mode = pmc & (1u << 31); bool fixed = pmc & (1u << 30); struct kvm_pmc *counters; @@ -458,7 +456,7 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data) void kvm_pmu_refresh(struct kvm_vcpu *vcpu) { - struct kvm_pmu *pmu = &vcpu->arch.pmu; + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct kvm_cpuid_entry2 *entry; union cpuid10_eax eax; union cpuid10_edx edx; @@ -510,7 +508,7 @@ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) void kvm_pmu_init(struct kvm_vcpu *vcpu) { int i; - struct kvm_pmu *pmu = &vcpu->arch.pmu; + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); memset(pmu, 0, sizeof(*pmu)); for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { @@ -529,7 +527,7 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu) void kvm_pmu_reset(struct kvm_vcpu *vcpu) { - struct kvm_pmu *pmu = &vcpu->arch.pmu; + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); int i; irq_work_sync(&pmu->irq_work); @@ -553,7 +551,7 @@ void kvm_pmu_destroy(struct kvm_vcpu *vcpu) void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) { - struct kvm_pmu *pmu = &vcpu->arch.pmu; + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); u64 bitmask; int bit; -- cgit v1.2.3 From e84cfe4ce0113a6c5e3bdf70e20a21552ad3a28d Mon Sep 17 00:00:00 2001 From: Wei Huang Date: Fri, 19 Jun 2015 14:15:28 +0200 Subject: KVM: x86/vPMU: whitespace and stylistic adjustments in PMU code Signed-off-by: Wei Huang Signed-off-by: Paolo Bonzini --- arch/x86/kvm/pmu.c | 112 ++++++++++++++++++++++++++++++----------------------- 1 file changed, 64 insertions(+), 48 deletions(-) diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 38819bc923cf..24d213bd42d4 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -103,25 +103,31 @@ static void kvm_perf_overflow(struct perf_event *perf_event, { struct kvm_pmc *pmc = perf_event->overflow_handler_context; struct kvm_pmu *pmu = pmc_to_pmu(pmc); - if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) { + + if (!test_and_set_bit(pmc->idx, + (unsigned long *)&pmu->reprogram_pmi)) { __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); kvm_make_request(KVM_REQ_PMU, pmc->vcpu); } } static void kvm_perf_overflow_intr(struct perf_event *perf_event, - struct perf_sample_data *data, struct pt_regs *regs) + struct perf_sample_data *data, + struct pt_regs *regs) { struct kvm_pmc *pmc = perf_event->overflow_handler_context; struct kvm_pmu *pmu = pmc_to_pmu(pmc); - if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) { + + if (!test_and_set_bit(pmc->idx, + (unsigned long *)&pmu->reprogram_pmi)) { __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); kvm_make_request(KVM_REQ_PMU, pmc->vcpu); + /* * Inject PMI. If vcpu was in a guest mode during NMI PMI * can be ejected on a guest mode re-entry. Otherwise we can't * be sure that vcpu wasn't executing hlt instruction at the - * time of vmexit and is not going to re-enter guest mode until, + * time of vmexit and is not going to re-enter guest mode until * woken up. So we should wake it, but this is impossible from * NMI context. Do it from irq work instead. */ @@ -157,8 +163,9 @@ static void pmc_stop_counter(struct kvm_pmc *pmc) } static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, - unsigned config, bool exclude_user, bool exclude_kernel, - bool intr, bool in_tx, bool in_tx_cp) + unsigned config, bool exclude_user, + bool exclude_kernel, bool intr, + bool in_tx, bool in_tx_cp) { struct perf_event *event; struct perf_event_attr attr = { @@ -171,6 +178,7 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, .exclude_kernel = exclude_kernel, .config = config, }; + if (in_tx) attr.config |= HSW_IN_TX; if (in_tx_cp) @@ -182,8 +190,8 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, intr ? kvm_perf_overflow_intr : kvm_perf_overflow, pmc); if (IS_ERR(event)) { - printk_once("kvm: pmu event creation failed %ld\n", - PTR_ERR(event)); + printk_once("kvm_pmu: event creation failed %ld\n", + PTR_ERR(event)); return; } @@ -227,10 +235,10 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) unit_mask = (eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE | - ARCH_PERFMON_EVENTSEL_INV | - ARCH_PERFMON_EVENTSEL_CMASK | - HSW_IN_TX | - HSW_IN_TX_CHECKPOINTED))) { + ARCH_PERFMON_EVENTSEL_INV | + ARCH_PERFMON_EVENTSEL_CMASK | + HSW_IN_TX | + HSW_IN_TX_CHECKPOINTED))) { config = find_arch_event(pmc_to_pmu(pmc), event_select, unit_mask); if (config != PERF_COUNT_HW_MAX) @@ -241,28 +249,28 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) config = eventsel & X86_RAW_EVENT_MASK; pmc_reprogram_counter(pmc, type, config, - !(eventsel & ARCH_PERFMON_EVENTSEL_USR), - !(eventsel & ARCH_PERFMON_EVENTSEL_OS), - eventsel & ARCH_PERFMON_EVENTSEL_INT, - (eventsel & HSW_IN_TX), - (eventsel & HSW_IN_TX_CHECKPOINTED)); + !(eventsel & ARCH_PERFMON_EVENTSEL_USR), + !(eventsel & ARCH_PERFMON_EVENTSEL_OS), + eventsel & ARCH_PERFMON_EVENTSEL_INT, + (eventsel & HSW_IN_TX), + (eventsel & HSW_IN_TX_CHECKPOINTED)); } -static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx) +static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx) { - unsigned en = en_pmi & 0x3; - bool pmi = en_pmi & 0x8; + unsigned en_field = ctrl & 0x3; + bool pmi = ctrl & 0x8; pmc_stop_counter(pmc); - if (!en || !pmc_is_enabled(pmc)) + if (!en_field || !pmc_is_enabled(pmc)) return; pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE, - arch_events[fixed_pmc_events[idx]].event_type, - !(en & 0x2), /* exclude user */ - !(en & 0x1), /* exclude kernel */ - pmi, false, false); + arch_events[fixed_pmc_events[idx]].event_type, + !(en_field & 0x2), /* exclude user */ + !(en_field & 0x1), /* exclude kernel */ + pmi, false, false); } static inline u8 fixed_ctrl_field(u64 ctrl, int idx) @@ -275,21 +283,22 @@ static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) int i; for (i = 0; i < pmu->nr_arch_fixed_counters; i++) { - u8 en_pmi = fixed_ctrl_field(data, i); + u8 old_ctrl = fixed_ctrl_field(pmu->fixed_ctr_ctrl, i); + u8 new_ctrl = fixed_ctrl_field(data, i); struct kvm_pmc *pmc = get_fixed_pmc_idx(pmu, i); - if (fixed_ctrl_field(pmu->fixed_ctr_ctrl, i) == en_pmi) + if (old_ctrl == new_ctrl) continue; - reprogram_fixed_counter(pmc, en_pmi, i); + reprogram_fixed_counter(pmc, new_ctrl, i); } pmu->fixed_ctr_ctrl = data; } -static void reprogram_counter(struct kvm_pmu *pmu, int idx) +static void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx) { - struct kvm_pmc *pmc = global_idx_to_pmc(pmu, idx); + struct kvm_pmc *pmc = global_idx_to_pmc(pmu, pmc_idx); if (!pmc) return; @@ -297,9 +306,10 @@ static void reprogram_counter(struct kvm_pmu *pmu, int idx) if (pmc_is_gp(pmc)) reprogram_gp_counter(pmc, pmc->eventsel); else { - int fidx = idx - INTEL_PMC_IDX_FIXED; - reprogram_fixed_counter(pmc, - fixed_ctrl_field(pmu->fixed_ctr_ctrl, fidx), fidx); + int idx = pmc_idx - INTEL_PMC_IDX_FIXED; + u8 ctrl = fixed_ctrl_field(pmu->fixed_ctr_ctrl, idx); + + reprogram_fixed_counter(pmc, ctrl, idx); } } @@ -423,37 +433,43 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; } -int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned pmc) +/* check if idx is a valid index to access PMU */ +int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - bool fixed = pmc & (1u << 30); - pmc &= ~(3u << 30); - return (!fixed && pmc >= pmu->nr_arch_gp_counters) || - (fixed && pmc >= pmu->nr_arch_fixed_counters); + bool fixed = idx & (1u << 30); + idx &= ~(3u << 30); + return (!fixed && idx >= pmu->nr_arch_gp_counters) || + (fixed && idx >= pmu->nr_arch_fixed_counters); } -int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data) +int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - bool fast_mode = pmc & (1u << 31); - bool fixed = pmc & (1u << 30); + bool fast_mode = idx & (1u << 31); + bool fixed = idx & (1u << 30); struct kvm_pmc *counters; - u64 ctr; + u64 ctr_val; - pmc &= ~(3u << 30); - if (!fixed && pmc >= pmu->nr_arch_gp_counters) + idx &= ~(3u << 30); + if (!fixed && idx >= pmu->nr_arch_gp_counters) return 1; - if (fixed && pmc >= pmu->nr_arch_fixed_counters) + if (fixed && idx >= pmu->nr_arch_fixed_counters) return 1; counters = fixed ? pmu->fixed_counters : pmu->gp_counters; - ctr = pmc_read_counter(&counters[pmc]); + + ctr_val = pmc_read_counter(&counters[idx]); if (fast_mode) - ctr = (u32)ctr; - *data = ctr; + ctr_val = (u32)ctr_val; + *data = ctr_val; return 0; } +/* refresh PMU settings. This function generally is called when underlying + * settings are changed (such as changes of PMU CPUID by guest VMs), which + * should rarely happen. + */ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); -- cgit v1.2.3 From e5af058aacd55e578b3c57b1582b90c4290b77f9 Mon Sep 17 00:00:00 2001 From: Wei Huang Date: Fri, 19 Jun 2015 15:51:47 +0200 Subject: KVM: x86/vPMU: reorder PMU functions Keep called functions closer to their callers, and init/destroy functions next to each other. Signed-off-by: Paolo Bonzini --- arch/x86/kvm/pmu.c | 156 ++++++++++++++++++++++++++--------------------------- 1 file changed, 78 insertions(+), 78 deletions(-) diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 24d213bd42d4..f38ad84be87e 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -83,12 +83,6 @@ static struct kvm_pmc *global_idx_to_pmc(struct kvm_pmu *pmu, int idx) return get_fixed_pmc_idx(pmu, idx - INTEL_PMC_IDX_FIXED); } -void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu) -{ - if (vcpu->arch.apic) - kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTPC); -} - static void kvm_pmi_trigger_fn(struct irq_work *irq_work) { struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, irq_work); @@ -324,6 +318,65 @@ static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data) reprogram_counter(pmu, bit); } +void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + u64 bitmask; + int bit; + + bitmask = pmu->reprogram_pmi; + + for_each_set_bit(bit, (unsigned long *)&bitmask, X86_PMC_IDX_MAX) { + struct kvm_pmc *pmc = global_idx_to_pmc(pmu, bit); + + if (unlikely(!pmc || !pmc->perf_event)) { + clear_bit(bit, (unsigned long *)&pmu->reprogram_pmi); + continue; + } + + reprogram_counter(pmu, bit); + } +} + +/* check if idx is a valid index to access PMU */ +int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + bool fixed = idx & (1u << 30); + idx &= ~(3u << 30); + return (!fixed && idx >= pmu->nr_arch_gp_counters) || + (fixed && idx >= pmu->nr_arch_fixed_counters); +} + +int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + bool fast_mode = idx & (1u << 31); + bool fixed = idx & (1u << 30); + struct kvm_pmc *counters; + u64 ctr_val; + + idx &= ~(3u << 30); + if (!fixed && idx >= pmu->nr_arch_gp_counters) + return 1; + if (fixed && idx >= pmu->nr_arch_fixed_counters) + return 1; + counters = fixed ? pmu->fixed_counters : pmu->gp_counters; + + ctr_val = pmc_read_counter(&counters[idx]); + if (fast_mode) + ctr_val = (u32)ctr_val; + + *data = ctr_val; + return 0; +} + +void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.apic) + kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTPC); +} + bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -433,39 +486,6 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; } -/* check if idx is a valid index to access PMU */ -int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) -{ - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - bool fixed = idx & (1u << 30); - idx &= ~(3u << 30); - return (!fixed && idx >= pmu->nr_arch_gp_counters) || - (fixed && idx >= pmu->nr_arch_fixed_counters); -} - -int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) -{ - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - bool fast_mode = idx & (1u << 31); - bool fixed = idx & (1u << 30); - struct kvm_pmc *counters; - u64 ctr_val; - - idx &= ~(3u << 30); - if (!fixed && idx >= pmu->nr_arch_gp_counters) - return 1; - if (fixed && idx >= pmu->nr_arch_fixed_counters) - return 1; - counters = fixed ? pmu->fixed_counters : pmu->gp_counters; - - ctr_val = pmc_read_counter(&counters[idx]); - if (fast_mode) - ctr_val = (u32)ctr_val; - - *data = ctr_val; - return 0; -} - /* refresh PMU settings. This function generally is called when underlying * settings are changed (such as changes of PMU CPUID by guest VMs), which * should rarely happen. @@ -521,26 +541,6 @@ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED; } -void kvm_pmu_init(struct kvm_vcpu *vcpu) -{ - int i; - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - - memset(pmu, 0, sizeof(*pmu)); - for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { - pmu->gp_counters[i].type = KVM_PMC_GP; - pmu->gp_counters[i].vcpu = vcpu; - pmu->gp_counters[i].idx = i; - } - for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) { - pmu->fixed_counters[i].type = KVM_PMC_FIXED; - pmu->fixed_counters[i].vcpu = vcpu; - pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED; - } - init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn); - kvm_pmu_refresh(vcpu); -} - void kvm_pmu_reset(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -560,27 +560,27 @@ void kvm_pmu_reset(struct kvm_vcpu *vcpu) pmu->global_ovf_ctrl = 0; } -void kvm_pmu_destroy(struct kvm_vcpu *vcpu) -{ - kvm_pmu_reset(vcpu); -} - -void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) +void kvm_pmu_init(struct kvm_vcpu *vcpu) { + int i; struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - u64 bitmask; - int bit; - - bitmask = pmu->reprogram_pmi; - - for_each_set_bit(bit, (unsigned long *)&bitmask, X86_PMC_IDX_MAX) { - struct kvm_pmc *pmc = global_idx_to_pmc(pmu, bit); - if (unlikely(!pmc || !pmc->perf_event)) { - clear_bit(bit, (unsigned long *)&pmu->reprogram_pmi); - continue; - } - - reprogram_counter(pmu, bit); + memset(pmu, 0, sizeof(*pmu)); + for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { + pmu->gp_counters[i].type = KVM_PMC_GP; + pmu->gp_counters[i].vcpu = vcpu; + pmu->gp_counters[i].idx = i; } + for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) { + pmu->fixed_counters[i].type = KVM_PMC_FIXED; + pmu->fixed_counters[i].vcpu = vcpu; + pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED; + } + init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn); + kvm_pmu_refresh(vcpu); +} + +void kvm_pmu_destroy(struct kvm_vcpu *vcpu) +{ + kvm_pmu_reset(vcpu); } -- cgit v1.2.3 From 41aac14a8dee66a720894e5979c2372c0d5afd34 Mon Sep 17 00:00:00 2001 From: Wei Huang Date: Fri, 19 Jun 2015 16:16:59 +0200 Subject: KVM: x86/vPMU: introduce kvm_pmu_msr_idx_to_pmc This function will be part of the kvm_pmu_ops interface. Introduce it already. Signed-off-by: Paolo Bonzini --- arch/x86/kvm/pmu.c | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index f38ad84be87e..bd5dbd9ce0e3 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -348,22 +348,34 @@ int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) (fixed && idx >= pmu->nr_arch_fixed_counters); } -int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) +static struct kvm_pmc *kvm_pmu_msr_idx_to_pmc(struct kvm_vcpu *vcpu, + unsigned idx) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - bool fast_mode = idx & (1u << 31); bool fixed = idx & (1u << 30); struct kvm_pmc *counters; - u64 ctr_val; idx &= ~(3u << 30); if (!fixed && idx >= pmu->nr_arch_gp_counters) - return 1; + return NULL; if (fixed && idx >= pmu->nr_arch_fixed_counters) - return 1; + return NULL; counters = fixed ? pmu->fixed_counters : pmu->gp_counters; - ctr_val = pmc_read_counter(&counters[idx]); + return &counters[idx]; +} + +int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) +{ + bool fast_mode = idx & (1u << 31); + struct kvm_pmc *pmc; + u64 ctr_val; + + pmc = kvm_pmu_msr_idx_to_pmc(vcpu, idx); + if (!pmc) + return 1; + + ctr_val = pmc_read_counter(pmc); if (fast_mode) ctr_val = (u32)ctr_val; -- cgit v1.2.3 From 25462f7f5295e2d3e9c2b31761ac95f0b3c8562f Mon Sep 17 00:00:00 2001 From: Wei Huang Date: Fri, 19 Jun 2015 15:45:05 +0200 Subject: KVM: x86/vPMU: Define kvm_pmu_ops to support vPMU function dispatch This patch defines a new function pointer struct (kvm_pmu_ops) to support vPMU for both Intel and AMD. The functions pointers defined in this new struct will be linked with Intel and AMD functions later. In the meanwhile the struct that maps from event_sel bits to PERF_TYPE_HARDWARE events is renamed and moved from Intel specific code to kvm_host.h as a common struct. Reviewed-by: Joerg Roedel Tested-by: Joerg Roedel Signed-off-by: Wei Huang Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 4 + arch/x86/kvm/Makefile | 4 +- arch/x86/kvm/pmu.c | 383 +++++----------------------------------- arch/x86/kvm/pmu.h | 92 ++++++++++ arch/x86/kvm/pmu_amd.c | 97 ++++++++++ arch/x86/kvm/pmu_intel.c | 358 +++++++++++++++++++++++++++++++++++++ arch/x86/kvm/svm.c | 3 + arch/x86/kvm/vmx.c | 3 + 8 files changed, 606 insertions(+), 338 deletions(-) create mode 100644 arch/x86/kvm/pmu_amd.c create mode 100644 arch/x86/kvm/pmu_intel.c diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 534dfa324e35..5a2b4508be44 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -336,6 +336,8 @@ struct kvm_pmu { u64 reprogram_pmi; }; +struct kvm_pmu_ops; + enum { KVM_DEBUGREG_BP_ENABLED = 1, KVM_DEBUGREG_WONT_EXIT = 2, @@ -854,6 +856,8 @@ struct kvm_x86_ops { void (*enable_log_dirty_pt_masked)(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t offset, unsigned long mask); + /* pmu operations of sub-arch */ + const struct kvm_pmu_ops *pmu_ops; }; struct kvm_arch_async_pf { diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 470dc6c9d409..67d215cb8953 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -14,8 +14,8 @@ kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += assigned-dev.o iommu.o -kvm-intel-y += vmx.o -kvm-amd-y += svm.o +kvm-intel-y += vmx.o pmu_intel.o +kvm-amd-y += svm.o pmu_amd.o obj-$(CONFIG_KVM) += kvm.o obj-$(CONFIG_KVM_INTEL) += kvm-intel.o diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index bd5dbd9ce0e3..31aa2c85dc97 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -1,11 +1,12 @@ /* * Kernel-based Virtual Machine -- Performance Monitoring Unit support * - * Copyright 2011 Red Hat, Inc. and/or its affiliates. + * Copyright 2015 Red Hat, Inc. and/or its affiliates. * * Authors: * Avi Kivity * Gleb Natapov + * Wei Huang * * This work is licensed under the terms of the GNU GPL, version 2. See * the COPYING file in the top-level directory. @@ -21,67 +22,30 @@ #include "lapic.h" #include "pmu.h" -static struct kvm_event_hw_type_mapping arch_events[] = { - /* Index must match CPUID 0x0A.EBX bit vector */ - [0] = { 0x3c, 0x00, PERF_COUNT_HW_CPU_CYCLES }, - [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, - [2] = { 0x3c, 0x01, PERF_COUNT_HW_BUS_CYCLES }, - [3] = { 0x2e, 0x4f, PERF_COUNT_HW_CACHE_REFERENCES }, - [4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES }, - [5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, - [6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, - [7] = { 0x00, 0x30, PERF_COUNT_HW_REF_CPU_CYCLES }, -}; - -/* mapping between fixed pmc index and arch_events array */ -static int fixed_pmc_events[] = {1, 0, 7}; - -static bool pmc_is_gp(struct kvm_pmc *pmc) -{ - return pmc->type == KVM_PMC_GP; -} - -static inline u64 pmc_bitmask(struct kvm_pmc *pmc) -{ - struct kvm_pmu *pmu = pmc_to_pmu(pmc); - - return pmu->counter_bitmask[pmc->type]; -} - -static inline bool pmc_is_enabled(struct kvm_pmc *pmc) -{ - struct kvm_pmu *pmu = pmc_to_pmu(pmc); - return test_bit(pmc->idx, (unsigned long *)&pmu->global_ctrl); -} - -static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr, - u32 base) -{ - if (msr >= base && msr < base + pmu->nr_arch_gp_counters) - return &pmu->gp_counters[msr - base]; - return NULL; -} - -static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr) -{ - int base = MSR_CORE_PERF_FIXED_CTR0; - if (msr >= base && msr < base + pmu->nr_arch_fixed_counters) - return &pmu->fixed_counters[msr - base]; - return NULL; -} - -static inline struct kvm_pmc *get_fixed_pmc_idx(struct kvm_pmu *pmu, int idx) -{ - return get_fixed_pmc(pmu, MSR_CORE_PERF_FIXED_CTR0 + idx); -} - -static struct kvm_pmc *global_idx_to_pmc(struct kvm_pmu *pmu, int idx) -{ - if (idx < INTEL_PMC_IDX_FIXED) - return get_gp_pmc(pmu, MSR_P6_EVNTSEL0 + idx, MSR_P6_EVNTSEL0); - else - return get_fixed_pmc_idx(pmu, idx - INTEL_PMC_IDX_FIXED); -} +/* NOTE: + * - Each perf counter is defined as "struct kvm_pmc"; + * - There are two types of perf counters: general purpose (gp) and fixed. + * gp counters are stored in gp_counters[] and fixed counters are stored + * in fixed_counters[] respectively. Both of them are part of "struct + * kvm_pmu"; + * - pmu.c understands the difference between gp counters and fixed counters. + * However AMD doesn't support fixed-counters; + * - There are three types of index to access perf counters (PMC): + * 1. MSR (named msr): For example Intel has MSR_IA32_PERFCTRn and AMD + * has MSR_K7_PERFCTRn. + * 2. MSR Index (named idx): This normally is used by RDPMC instruction. + * For instance AMD RDPMC instruction uses 0000_0003h in ECX to access + * C001_0007h (MSR_K7_PERCTR3). Intel has a similar mechanism, except + * that it also supports fixed counters. idx can be used to as index to + * gp and fixed counters. + * 3. Global PMC Index (named pmc): pmc is an index specific to PMU + * code. Each pmc, stored in kvm_pmc.idx field, is unique across + * all perf counters (both gp and fixed). The mapping relationship + * between pmc and perf counters is as the following: + * * Intel: [0 .. INTEL_PMC_MAX_GENERIC-1] <=> gp counters + * [INTEL_PMC_IDX_FIXED .. INTEL_PMC_IDX_FIXED + 2] <=> fixed + * * AMD: [0 .. AMD64_NUM_COUNTERS-1] <=> gp counters + */ static void kvm_pmi_trigger_fn(struct irq_work *irq_work) { @@ -132,30 +96,6 @@ static void kvm_perf_overflow_intr(struct perf_event *perf_event, } } -static u64 pmc_read_counter(struct kvm_pmc *pmc) -{ - u64 counter, enabled, running; - - counter = pmc->counter; - - if (pmc->perf_event) - counter += perf_event_read_value(pmc->perf_event, - &enabled, &running); - - /* FIXME: Scaling needed? */ - - return counter & pmc_bitmask(pmc); -} - -static void pmc_stop_counter(struct kvm_pmc *pmc) -{ - if (pmc->perf_event) { - pmc->counter = pmc_read_counter(pmc); - perf_event_release_kernel(pmc->perf_event); - pmc->perf_event = NULL; - } -} - static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, unsigned config, bool exclude_user, bool exclude_kernel, bool intr, @@ -193,24 +133,7 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, clear_bit(pmc->idx, (unsigned long*)&pmc_to_pmu(pmc)->reprogram_pmi); } -static unsigned find_arch_event(struct kvm_pmu *pmu, u8 event_select, - u8 unit_mask) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(arch_events); i++) - if (arch_events[i].eventsel == event_select - && arch_events[i].unit_mask == unit_mask - && (pmu->available_event_types & (1 << i))) - break; - - if (i == ARRAY_SIZE(arch_events)) - return PERF_COUNT_HW_MAX; - - return arch_events[i].event_type; -} - -static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) +void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) { unsigned config, type = PERF_TYPE_RAW; u8 event_select, unit_mask; @@ -233,8 +156,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) ARCH_PERFMON_EVENTSEL_CMASK | HSW_IN_TX | HSW_IN_TX_CHECKPOINTED))) { - config = find_arch_event(pmc_to_pmu(pmc), event_select, - unit_mask); + config = kvm_x86_ops->pmu_ops->find_arch_event(pmc_to_pmu(pmc), + event_select, + unit_mask); if (config != PERF_COUNT_HW_MAX) type = PERF_TYPE_HARDWARE; } @@ -249,8 +173,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) (eventsel & HSW_IN_TX), (eventsel & HSW_IN_TX_CHECKPOINTED)); } +EXPORT_SYMBOL_GPL(reprogram_gp_counter); -static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx) +void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx) { unsigned en_field = ctrl & 0x3; bool pmi = ctrl & 0x8; @@ -261,38 +186,16 @@ static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx) return; pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE, - arch_events[fixed_pmc_events[idx]].event_type, + kvm_x86_ops->pmu_ops->find_fixed_event(idx), !(en_field & 0x2), /* exclude user */ !(en_field & 0x1), /* exclude kernel */ pmi, false, false); } +EXPORT_SYMBOL_GPL(reprogram_fixed_counter); -static inline u8 fixed_ctrl_field(u64 ctrl, int idx) -{ - return (ctrl >> (idx * 4)) & 0xf; -} - -static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) +void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx) { - int i; - - for (i = 0; i < pmu->nr_arch_fixed_counters; i++) { - u8 old_ctrl = fixed_ctrl_field(pmu->fixed_ctr_ctrl, i); - u8 new_ctrl = fixed_ctrl_field(data, i); - struct kvm_pmc *pmc = get_fixed_pmc_idx(pmu, i); - - if (old_ctrl == new_ctrl) - continue; - - reprogram_fixed_counter(pmc, new_ctrl, i); - } - - pmu->fixed_ctr_ctrl = data; -} - -static void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx) -{ - struct kvm_pmc *pmc = global_idx_to_pmc(pmu, pmc_idx); + struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, pmc_idx); if (!pmc) return; @@ -306,17 +209,7 @@ static void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx) reprogram_fixed_counter(pmc, ctrl, idx); } } - -static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data) -{ - int bit; - u64 diff = pmu->global_ctrl ^ data; - - pmu->global_ctrl = data; - - for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) - reprogram_counter(pmu, bit); -} +EXPORT_SYMBOL_GPL(reprogram_counter); void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) { @@ -327,7 +220,7 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) bitmask = pmu->reprogram_pmi; for_each_set_bit(bit, (unsigned long *)&bitmask, X86_PMC_IDX_MAX) { - struct kvm_pmc *pmc = global_idx_to_pmc(pmu, bit); + struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, bit); if (unlikely(!pmc || !pmc->perf_event)) { clear_bit(bit, (unsigned long *)&pmu->reprogram_pmi); @@ -341,28 +234,7 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) /* check if idx is a valid index to access PMU */ int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) { - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - bool fixed = idx & (1u << 30); - idx &= ~(3u << 30); - return (!fixed && idx >= pmu->nr_arch_gp_counters) || - (fixed && idx >= pmu->nr_arch_fixed_counters); -} - -static struct kvm_pmc *kvm_pmu_msr_idx_to_pmc(struct kvm_vcpu *vcpu, - unsigned idx) -{ - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - bool fixed = idx & (1u << 30); - struct kvm_pmc *counters; - - idx &= ~(3u << 30); - if (!fixed && idx >= pmu->nr_arch_gp_counters) - return NULL; - if (fixed && idx >= pmu->nr_arch_fixed_counters) - return NULL; - counters = fixed ? pmu->fixed_counters : pmu->gp_counters; - - return &counters[idx]; + return kvm_x86_ops->pmu_ops->is_valid_msr_idx(vcpu, idx); } int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) @@ -371,7 +243,7 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) struct kvm_pmc *pmc; u64 ctr_val; - pmc = kvm_pmu_msr_idx_to_pmc(vcpu, idx); + pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, idx); if (!pmc) return 1; @@ -391,111 +263,17 @@ void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu) bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) { - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - int ret; - - switch (msr) { - case MSR_CORE_PERF_FIXED_CTR_CTRL: - case MSR_CORE_PERF_GLOBAL_STATUS: - case MSR_CORE_PERF_GLOBAL_CTRL: - case MSR_CORE_PERF_GLOBAL_OVF_CTRL: - ret = pmu->version > 1; - break; - default: - ret = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0) - || get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0) - || get_fixed_pmc(pmu, msr); - break; - } - return ret; + return kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, msr); } -int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data) +int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) { - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - struct kvm_pmc *pmc; - - switch (index) { - case MSR_CORE_PERF_FIXED_CTR_CTRL: - *data = pmu->fixed_ctr_ctrl; - return 0; - case MSR_CORE_PERF_GLOBAL_STATUS: - *data = pmu->global_status; - return 0; - case MSR_CORE_PERF_GLOBAL_CTRL: - *data = pmu->global_ctrl; - return 0; - case MSR_CORE_PERF_GLOBAL_OVF_CTRL: - *data = pmu->global_ovf_ctrl; - return 0; - default: - if ((pmc = get_gp_pmc(pmu, index, MSR_IA32_PERFCTR0)) || - (pmc = get_fixed_pmc(pmu, index))) { - *data = pmc_read_counter(pmc); - return 0; - } else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) { - *data = pmc->eventsel; - return 0; - } - } - return 1; + return kvm_x86_ops->pmu_ops->get_msr(vcpu, msr, data); } int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - struct kvm_pmc *pmc; - u32 index = msr_info->index; - u64 data = msr_info->data; - - switch (index) { - case MSR_CORE_PERF_FIXED_CTR_CTRL: - if (pmu->fixed_ctr_ctrl == data) - return 0; - if (!(data & 0xfffffffffffff444ull)) { - reprogram_fixed_counters(pmu, data); - return 0; - } - break; - case MSR_CORE_PERF_GLOBAL_STATUS: - if (msr_info->host_initiated) { - pmu->global_status = data; - return 0; - } - break; /* RO MSR */ - case MSR_CORE_PERF_GLOBAL_CTRL: - if (pmu->global_ctrl == data) - return 0; - if (!(data & pmu->global_ctrl_mask)) { - global_ctrl_changed(pmu, data); - return 0; - } - break; - case MSR_CORE_PERF_GLOBAL_OVF_CTRL: - if (!(data & (pmu->global_ctrl_mask & ~(3ull<<62)))) { - if (!msr_info->host_initiated) - pmu->global_status &= ~data; - pmu->global_ovf_ctrl = data; - return 0; - } - break; - default: - if ((pmc = get_gp_pmc(pmu, index, MSR_IA32_PERFCTR0)) || - (pmc = get_fixed_pmc(pmu, index))) { - if (!msr_info->host_initiated) - data = (s64)(s32)data; - pmc->counter += data - pmc_read_counter(pmc); - return 0; - } else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) { - if (data == pmc->eventsel) - return 0; - if (!(data & pmu->reserved_bits)) { - reprogram_gp_counter(pmc, data); - return 0; - } - } - } - return 1; + return kvm_x86_ops->pmu_ops->set_msr(vcpu, msr_info); } /* refresh PMU settings. This function generally is called when underlying @@ -504,90 +282,23 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) */ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) { - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - struct kvm_cpuid_entry2 *entry; - union cpuid10_eax eax; - union cpuid10_edx edx; - - pmu->nr_arch_gp_counters = 0; - pmu->nr_arch_fixed_counters = 0; - pmu->counter_bitmask[KVM_PMC_GP] = 0; - pmu->counter_bitmask[KVM_PMC_FIXED] = 0; - pmu->version = 0; - pmu->reserved_bits = 0xffffffff00200000ull; - - entry = kvm_find_cpuid_entry(vcpu, 0xa, 0); - if (!entry) - return; - eax.full = entry->eax; - edx.full = entry->edx; - - pmu->version = eax.split.version_id; - if (!pmu->version) - return; - - pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters, - INTEL_PMC_MAX_GENERIC); - pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1; - pmu->available_event_types = ~entry->ebx & - ((1ull << eax.split.mask_length) - 1); - - if (pmu->version == 1) { - pmu->nr_arch_fixed_counters = 0; - } else { - pmu->nr_arch_fixed_counters = - min_t(int, edx.split.num_counters_fixed, - INTEL_PMC_MAX_FIXED); - pmu->counter_bitmask[KVM_PMC_FIXED] = - ((u64)1 << edx.split.bit_width_fixed) - 1; - } - - pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) | - (((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED); - pmu->global_ctrl_mask = ~pmu->global_ctrl; - - entry = kvm_find_cpuid_entry(vcpu, 7, 0); - if (entry && - (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) && - (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM))) - pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED; + kvm_x86_ops->pmu_ops->refresh(vcpu); } void kvm_pmu_reset(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - int i; irq_work_sync(&pmu->irq_work); - for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { - struct kvm_pmc *pmc = &pmu->gp_counters[i]; - pmc_stop_counter(pmc); - pmc->counter = pmc->eventsel = 0; - } - - for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) - pmc_stop_counter(&pmu->fixed_counters[i]); - - pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = - pmu->global_ovf_ctrl = 0; + kvm_x86_ops->pmu_ops->reset(vcpu); } void kvm_pmu_init(struct kvm_vcpu *vcpu) { - int i; struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); memset(pmu, 0, sizeof(*pmu)); - for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { - pmu->gp_counters[i].type = KVM_PMC_GP; - pmu->gp_counters[i].vcpu = vcpu; - pmu->gp_counters[i].idx = i; - } - for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) { - pmu->fixed_counters[i].type = KVM_PMC_FIXED; - pmu->fixed_counters[i].vcpu = vcpu; - pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED; - } + kvm_x86_ops->pmu_ops->init(vcpu); init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn); kvm_pmu_refresh(vcpu); } diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 19bf0172f93b..f96e1f962587 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -5,12 +5,102 @@ #define pmu_to_vcpu(pmu) (container_of((pmu), struct kvm_vcpu, arch.pmu)) #define pmc_to_pmu(pmc) (&(pmc)->vcpu->arch.pmu) +/* retrieve the 4 bits for EN and PMI out of IA32_FIXED_CTR_CTRL */ +#define fixed_ctrl_field(ctrl_reg, idx) (((ctrl_reg) >> ((idx)*4)) & 0xf) + struct kvm_event_hw_type_mapping { u8 eventsel; u8 unit_mask; unsigned event_type; }; +struct kvm_pmu_ops { + unsigned (*find_arch_event)(struct kvm_pmu *pmu, u8 event_select, + u8 unit_mask); + unsigned (*find_fixed_event)(int idx); + bool (*pmc_is_enabled)(struct kvm_pmc *pmc); + struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx); + struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, unsigned idx); + int (*is_valid_msr_idx)(struct kvm_vcpu *vcpu, unsigned idx); + bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr); + int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr, u64 *data); + int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info); + void (*refresh)(struct kvm_vcpu *vcpu); + void (*init)(struct kvm_vcpu *vcpu); + void (*reset)(struct kvm_vcpu *vcpu); +}; + +static inline u64 pmc_bitmask(struct kvm_pmc *pmc) +{ + struct kvm_pmu *pmu = pmc_to_pmu(pmc); + + return pmu->counter_bitmask[pmc->type]; +} + +static inline u64 pmc_read_counter(struct kvm_pmc *pmc) +{ + u64 counter, enabled, running; + + counter = pmc->counter; + if (pmc->perf_event) + counter += perf_event_read_value(pmc->perf_event, + &enabled, &running); + /* FIXME: Scaling needed? */ + return counter & pmc_bitmask(pmc); +} + +static inline void pmc_stop_counter(struct kvm_pmc *pmc) +{ + if (pmc->perf_event) { + pmc->counter = pmc_read_counter(pmc); + perf_event_release_kernel(pmc->perf_event); + pmc->perf_event = NULL; + } +} + +static inline bool pmc_is_gp(struct kvm_pmc *pmc) +{ + return pmc->type == KVM_PMC_GP; +} + +static inline bool pmc_is_fixed(struct kvm_pmc *pmc) +{ + return pmc->type == KVM_PMC_FIXED; +} + +static inline bool pmc_is_enabled(struct kvm_pmc *pmc) +{ + return kvm_x86_ops->pmu_ops->pmc_is_enabled(pmc); +} + +/* returns general purpose PMC with the specified MSR. Note that it can be + * used for both PERFCTRn and EVNTSELn; that is why it accepts base as a + * paramenter to tell them apart. + */ +static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr, + u32 base) +{ + if (msr >= base && msr < base + pmu->nr_arch_gp_counters) + return &pmu->gp_counters[msr - base]; + + return NULL; +} + +/* returns fixed PMC with the specified MSR */ +static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr) +{ + int base = MSR_CORE_PERF_FIXED_CTR0; + + if (msr >= base && msr < base + pmu->nr_arch_fixed_counters) + return &pmu->fixed_counters[msr - base]; + + return NULL; +} + +void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel); +void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int fixed_idx); +void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx); + void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu); void kvm_pmu_handle_event(struct kvm_vcpu *vcpu); int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data); @@ -23,4 +113,6 @@ void kvm_pmu_reset(struct kvm_vcpu *vcpu); void kvm_pmu_init(struct kvm_vcpu *vcpu); void kvm_pmu_destroy(struct kvm_vcpu *vcpu); +extern struct kvm_pmu_ops intel_pmu_ops; +extern struct kvm_pmu_ops amd_pmu_ops; #endif /* __KVM_X86_PMU_H */ diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c new file mode 100644 index 000000000000..48786407fee1 --- /dev/null +++ b/arch/x86/kvm/pmu_amd.c @@ -0,0 +1,97 @@ +/* + * KVM PMU support for AMD + * + * Copyright 2015, Red Hat, Inc. and/or its affiliates. + * + * Author: + * Wei Huang + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Implementation is based on pmu_intel.c file + */ +#include +#include +#include +#include "x86.h" +#include "cpuid.h" +#include "lapic.h" +#include "pmu.h" + +static unsigned amd_find_arch_event(struct kvm_pmu *pmu, + u8 event_select, + u8 unit_mask) +{ + return PERF_COUNT_HW_MAX; +} + +/* return PERF_COUNT_HW_MAX as AMD doesn't have fixed events */ +static unsigned amd_find_fixed_event(int idx) +{ + return PERF_COUNT_HW_MAX; +} + +static bool amd_pmc_is_enabled(struct kvm_pmc *pmc) +{ + return false; +} + +static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) +{ + return NULL; +} + +/* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */ +static int amd_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) +{ + return 1; +} + +/* idx is the ECX register of RDPMC instruction */ +static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx) +{ + return NULL; +} + +static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) +{ + return false; +} + +static int amd_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) +{ + return 1; +} + +static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +{ + return 1; +} + +static void amd_pmu_refresh(struct kvm_vcpu *vcpu) +{ +} + +static void amd_pmu_init(struct kvm_vcpu *vcpu) +{ +} + +static void amd_pmu_reset(struct kvm_vcpu *vcpu) +{ +} + +struct kvm_pmu_ops amd_pmu_ops = { + .find_arch_event = amd_find_arch_event, + .find_fixed_event = amd_find_fixed_event, + .pmc_is_enabled = amd_pmc_is_enabled, + .pmc_idx_to_pmc = amd_pmc_idx_to_pmc, + .msr_idx_to_pmc = amd_msr_idx_to_pmc, + .is_valid_msr_idx = amd_is_valid_msr_idx, + .is_valid_msr = amd_is_valid_msr, + .get_msr = amd_pmu_get_msr, + .set_msr = amd_pmu_set_msr, + .refresh = amd_pmu_refresh, + .init = amd_pmu_init, + .reset = amd_pmu_reset, +}; diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/pmu_intel.c new file mode 100644 index 000000000000..ab38af4f4947 --- /dev/null +++ b/arch/x86/kvm/pmu_intel.c @@ -0,0 +1,358 @@ +/* + * KVM PMU support for Intel CPUs + * + * Copyright 2011 Red Hat, Inc. and/or its affiliates. + * + * Authors: + * Avi Kivity + * Gleb Natapov + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ +#include +#include +#include +#include +#include "x86.h" +#include "cpuid.h" +#include "lapic.h" +#include "pmu.h" + +static struct kvm_event_hw_type_mapping intel_arch_events[] = { + /* Index must match CPUID 0x0A.EBX bit vector */ + [0] = { 0x3c, 0x00, PERF_COUNT_HW_CPU_CYCLES }, + [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, + [2] = { 0x3c, 0x01, PERF_COUNT_HW_BUS_CYCLES }, + [3] = { 0x2e, 0x4f, PERF_COUNT_HW_CACHE_REFERENCES }, + [4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES }, + [5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, + [6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, + [7] = { 0x00, 0x30, PERF_COUNT_HW_REF_CPU_CYCLES }, +}; + +/* mapping between fixed pmc index and intel_arch_events array */ +static int fixed_pmc_events[] = {1, 0, 7}; + +static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) +{ + int i; + + for (i = 0; i < pmu->nr_arch_fixed_counters; i++) { + u8 new_ctrl = fixed_ctrl_field(data, i); + u8 old_ctrl = fixed_ctrl_field(pmu->fixed_ctr_ctrl, i); + struct kvm_pmc *pmc; + + pmc = get_fixed_pmc(pmu, MSR_CORE_PERF_FIXED_CTR0 + i); + + if (old_ctrl == new_ctrl) + continue; + + reprogram_fixed_counter(pmc, new_ctrl, i); + } + + pmu->fixed_ctr_ctrl = data; +} + +/* function is called when global control register has been updated. */ +static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data) +{ + int bit; + u64 diff = pmu->global_ctrl ^ data; + + pmu->global_ctrl = data; + + for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) + reprogram_counter(pmu, bit); +} + +static unsigned intel_find_arch_event(struct kvm_pmu *pmu, + u8 event_select, + u8 unit_mask) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(intel_arch_events); i++) + if (intel_arch_events[i].eventsel == event_select + && intel_arch_events[i].unit_mask == unit_mask + && (pmu->available_event_types & (1 << i))) + break; + + if (i == ARRAY_SIZE(intel_arch_events)) + return PERF_COUNT_HW_MAX; + + return intel_arch_events[i].event_type; +} + +static unsigned intel_find_fixed_event(int idx) +{ + if (idx >= ARRAY_SIZE(fixed_pmc_events)) + return PERF_COUNT_HW_MAX; + + return intel_arch_events[fixed_pmc_events[idx]].event_type; +} + +/* check if a PMC is enabled by comparising it with globl_ctrl bits. */ +static bool intel_pmc_is_enabled(struct kvm_pmc *pmc) +{ + struct kvm_pmu *pmu = pmc_to_pmu(pmc); + + return test_bit(pmc->idx, (unsigned long *)&pmu->global_ctrl); +} + +static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) +{ + if (pmc_idx < INTEL_PMC_IDX_FIXED) + return get_gp_pmc(pmu, MSR_P6_EVNTSEL0 + pmc_idx, + MSR_P6_EVNTSEL0); + else { + u32 idx = pmc_idx - INTEL_PMC_IDX_FIXED; + + return get_fixed_pmc(pmu, idx + MSR_CORE_PERF_FIXED_CTR0); + } +} + +/* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */ +static int intel_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + bool fixed = idx & (1u << 30); + + idx &= ~(3u << 30); + + return (!fixed && idx >= pmu->nr_arch_gp_counters) || + (fixed && idx >= pmu->nr_arch_fixed_counters); +} + +static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu, + unsigned idx) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + bool fixed = idx & (1u << 30); + struct kvm_pmc *counters; + + idx &= ~(3u << 30); + if (!fixed && idx >= pmu->nr_arch_gp_counters) + return NULL; + if (fixed && idx >= pmu->nr_arch_fixed_counters) + return NULL; + counters = fixed ? pmu->fixed_counters : pmu->gp_counters; + + return &counters[idx]; +} + +static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + int ret; + + switch (msr) { + case MSR_CORE_PERF_FIXED_CTR_CTRL: + case MSR_CORE_PERF_GLOBAL_STATUS: + case MSR_CORE_PERF_GLOBAL_CTRL: + case MSR_CORE_PERF_GLOBAL_OVF_CTRL: + ret = pmu->version > 1; + break; + default: + ret = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0) || + get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0) || + get_fixed_pmc(pmu, msr); + break; + } + + return ret; +} + +static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + + switch (msr) { + case MSR_CORE_PERF_FIXED_CTR_CTRL: + *data = pmu->fixed_ctr_ctrl; + return 0; + case MSR_CORE_PERF_GLOBAL_STATUS: + *data = pmu->global_status; + return 0; + case MSR_CORE_PERF_GLOBAL_CTRL: + *data = pmu->global_ctrl; + return 0; + case MSR_CORE_PERF_GLOBAL_OVF_CTRL: + *data = pmu->global_ovf_ctrl; + return 0; + default: + if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || + (pmc = get_fixed_pmc(pmu, msr))) { + *data = pmc_read_counter(pmc); + return 0; + } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { + *data = pmc->eventsel; + return 0; + } + } + + return 1; +} + +static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + u32 msr = msr_info->index; + u64 data = msr_info->data; + + switch (msr) { + case MSR_CORE_PERF_FIXED_CTR_CTRL: + if (pmu->fixed_ctr_ctrl == data) + return 0; + if (!(data & 0xfffffffffffff444ull)) { + reprogram_fixed_counters(pmu, data); + return 0; + } + break; + case MSR_CORE_PERF_GLOBAL_STATUS: + if (msr_info->host_initiated) { + pmu->global_status = data; + return 0; + } + break; /* RO MSR */ + case MSR_CORE_PERF_GLOBAL_CTRL: + if (pmu->global_ctrl == data) + return 0; + if (!(data & pmu->global_ctrl_mask)) { + global_ctrl_changed(pmu, data); + return 0; + } + break; + case MSR_CORE_PERF_GLOBAL_OVF_CTRL: + if (!(data & (pmu->global_ctrl_mask & ~(3ull<<62)))) { + if (!msr_info->host_initiated) + pmu->global_status &= ~data; + pmu->global_ovf_ctrl = data; + return 0; + } + break; + default: + if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || + (pmc = get_fixed_pmc(pmu, msr))) { + if (!msr_info->host_initiated) + data = (s64)(s32)data; + pmc->counter += data - pmc_read_counter(pmc); + return 0; + } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { + if (data == pmc->eventsel) + return 0; + if (!(data & pmu->reserved_bits)) { + reprogram_gp_counter(pmc, data); + return 0; + } + } + } + + return 1; +} + +static void intel_pmu_refresh(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_cpuid_entry2 *entry; + union cpuid10_eax eax; + union cpuid10_edx edx; + + pmu->nr_arch_gp_counters = 0; + pmu->nr_arch_fixed_counters = 0; + pmu->counter_bitmask[KVM_PMC_GP] = 0; + pmu->counter_bitmask[KVM_PMC_FIXED] = 0; + pmu->version = 0; + pmu->reserved_bits = 0xffffffff00200000ull; + + entry = kvm_find_cpuid_entry(vcpu, 0xa, 0); + if (!entry) + return; + eax.full = entry->eax; + edx.full = entry->edx; + + pmu->version = eax.split.version_id; + if (!pmu->version) + return; + + pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters, + INTEL_PMC_MAX_GENERIC); + pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1; + pmu->available_event_types = ~entry->ebx & + ((1ull << eax.split.mask_length) - 1); + + if (pmu->version == 1) { + pmu->nr_arch_fixed_counters = 0; + } else { + pmu->nr_arch_fixed_counters = + min_t(int, edx.split.num_counters_fixed, + INTEL_PMC_MAX_FIXED); + pmu->counter_bitmask[KVM_PMC_FIXED] = + ((u64)1 << edx.split.bit_width_fixed) - 1; + } + + pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) | + (((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED); + pmu->global_ctrl_mask = ~pmu->global_ctrl; + + entry = kvm_find_cpuid_entry(vcpu, 7, 0); + if (entry && + (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) && + (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM))) + pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED; +} + +static void intel_pmu_init(struct kvm_vcpu *vcpu) +{ + int i; + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + + for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { + pmu->gp_counters[i].type = KVM_PMC_GP; + pmu->gp_counters[i].vcpu = vcpu; + pmu->gp_counters[i].idx = i; + } + + for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) { + pmu->fixed_counters[i].type = KVM_PMC_FIXED; + pmu->fixed_counters[i].vcpu = vcpu; + pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED; + } +} + +static void intel_pmu_reset(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + int i; + + for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { + struct kvm_pmc *pmc = &pmu->gp_counters[i]; + + pmc_stop_counter(pmc); + pmc->counter = pmc->eventsel = 0; + } + + for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) + pmc_stop_counter(&pmu->fixed_counters[i]); + + pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = + pmu->global_ovf_ctrl = 0; +} + +struct kvm_pmu_ops intel_pmu_ops = { + .find_arch_event = intel_find_arch_event, + .find_fixed_event = intel_find_fixed_event, + .pmc_is_enabled = intel_pmc_is_enabled, + .pmc_idx_to_pmc = intel_pmc_idx_to_pmc, + .msr_idx_to_pmc = intel_msr_idx_to_pmc, + .is_valid_msr_idx = intel_is_valid_msr_idx, + .is_valid_msr = intel_is_valid_msr, + .get_msr = intel_pmu_get_msr, + .set_msr = intel_pmu_set_msr, + .refresh = intel_pmu_refresh, + .init = intel_pmu_init, + .reset = intel_pmu_reset, +}; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index e7685af399e4..851a9a1c6dfc 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -21,6 +21,7 @@ #include "kvm_cache_regs.h" #include "x86.h" #include "cpuid.h" +#include "pmu.h" #include #include @@ -4457,6 +4458,8 @@ static struct kvm_x86_ops svm_x86_ops = { .handle_external_intr = svm_handle_external_intr, .sched_in = svm_sched_in, + + .pmu_ops = &amd_pmu_ops, }; static int __init svm_init(void) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 44eafdb440c9..e5a379f82672 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -48,6 +48,7 @@ #include #include "trace.h" +#include "pmu.h" #define __ex(x) __kvm_handle_fault_on_reboot(x) #define __ex_clear(x, reg) \ @@ -10419,6 +10420,8 @@ static struct kvm_x86_ops vmx_x86_ops = { .slot_disable_log_dirty = vmx_slot_disable_log_dirty, .flush_log_dirty = vmx_flush_log_dirty, .enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked, + + .pmu_ops = &intel_pmu_ops, }; static int __init vmx_init(void) -- cgit v1.2.3 From ca724305a2b02abcbecbf22577536fc8e965ab4f Mon Sep 17 00:00:00 2001 From: Wei Huang Date: Fri, 12 Jun 2015 01:34:55 -0400 Subject: KVM: x86/vPMU: Implement AMD vPMU code for KVM This patch replaces the empty AMD vPMU functions (in pmu_amd.c) with real implementation. Reviewed-by: Joerg Roedel Tested-by: Joerg Roedel Signed-off-by: Wei Huang Signed-off-by: Paolo Bonzini --- arch/x86/kvm/pmu_amd.c | 122 ++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 116 insertions(+), 6 deletions(-) diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c index 48786407fee1..886aa25a7131 100644 --- a/arch/x86/kvm/pmu_amd.c +++ b/arch/x86/kvm/pmu_amd.c @@ -19,11 +19,33 @@ #include "lapic.h" #include "pmu.h" +/* duplicated from amd_perfmon_event_map, K7 and above should work. */ +static struct kvm_event_hw_type_mapping amd_event_mapping[] = { + [0] = { 0x76, 0x00, PERF_COUNT_HW_CPU_CYCLES }, + [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, + [2] = { 0x80, 0x00, PERF_COUNT_HW_CACHE_REFERENCES }, + [3] = { 0x81, 0x00, PERF_COUNT_HW_CACHE_MISSES }, + [4] = { 0xc2, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, + [5] = { 0xc3, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, + [6] = { 0xd0, 0x00, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND }, + [7] = { 0xd1, 0x00, PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, +}; + static unsigned amd_find_arch_event(struct kvm_pmu *pmu, u8 event_select, u8 unit_mask) { - return PERF_COUNT_HW_MAX; + int i; + + for (i = 0; i < ARRAY_SIZE(amd_event_mapping); i++) + if (amd_event_mapping[i].eventsel == event_select + && amd_event_mapping[i].unit_mask == unit_mask) + break; + + if (i == ARRAY_SIZE(amd_event_mapping)) + return PERF_COUNT_HW_MAX; + + return amd_event_mapping[i].event_type; } /* return PERF_COUNT_HW_MAX as AMD doesn't have fixed events */ @@ -32,53 +54,141 @@ static unsigned amd_find_fixed_event(int idx) return PERF_COUNT_HW_MAX; } +/* check if a PMC is enabled by comparing it against global_ctrl bits. Because + * AMD CPU doesn't have global_ctrl MSR, all PMCs are enabled (return TRUE). + */ static bool amd_pmc_is_enabled(struct kvm_pmc *pmc) { - return false; + return true; } static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) { - return NULL; + return get_gp_pmc(pmu, MSR_K7_EVNTSEL0 + pmc_idx, MSR_K7_EVNTSEL0); } /* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */ static int amd_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) { - return 1; + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + + idx &= ~(3u << 30); + + return (idx >= pmu->nr_arch_gp_counters); } /* idx is the ECX register of RDPMC instruction */ static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx) { - return NULL; + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *counters; + + idx &= ~(3u << 30); + if (idx >= pmu->nr_arch_gp_counters) + return NULL; + counters = pmu->gp_counters; + + return &counters[idx]; } static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) { - return false; + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + int ret = false; + + ret = get_gp_pmc(pmu, msr, MSR_K7_PERFCTR0) || + get_gp_pmc(pmu, msr, MSR_K7_EVNTSEL0); + + return ret; } static int amd_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) { + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + + /* MSR_K7_PERFCTRn */ + pmc = get_gp_pmc(pmu, msr, MSR_K7_PERFCTR0); + if (pmc) { + *data = pmc_read_counter(pmc); + return 0; + } + /* MSR_K7_EVNTSELn */ + pmc = get_gp_pmc(pmu, msr, MSR_K7_EVNTSEL0); + if (pmc) { + *data = pmc->eventsel; + return 0; + } + return 1; } static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + u32 msr = msr_info->index; + u64 data = msr_info->data; + + /* MSR_K7_PERFCTRn */ + pmc = get_gp_pmc(pmu, msr, MSR_K7_PERFCTR0); + if (pmc) { + if (!msr_info->host_initiated) + data = (s64)data; + pmc->counter += data - pmc_read_counter(pmc); + return 0; + } + /* MSR_K7_EVNTSELn */ + pmc = get_gp_pmc(pmu, msr, MSR_K7_EVNTSEL0); + if (pmc) { + if (data == pmc->eventsel) + return 0; + if (!(data & pmu->reserved_bits)) { + reprogram_gp_counter(pmc, data); + return 0; + } + } + return 1; } static void amd_pmu_refresh(struct kvm_vcpu *vcpu) { + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + + pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS; + pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1; + pmu->reserved_bits = 0xffffffff00200000ull; + /* not applicable to AMD; but clean them to prevent any fall out */ + pmu->counter_bitmask[KVM_PMC_FIXED] = 0; + pmu->nr_arch_fixed_counters = 0; + pmu->version = 0; + pmu->global_status = 0; } static void amd_pmu_init(struct kvm_vcpu *vcpu) { + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + int i; + + for (i = 0; i < AMD64_NUM_COUNTERS ; i++) { + pmu->gp_counters[i].type = KVM_PMC_GP; + pmu->gp_counters[i].vcpu = vcpu; + pmu->gp_counters[i].idx = i; + } } static void amd_pmu_reset(struct kvm_vcpu *vcpu) { + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + int i; + + for (i = 0; i < AMD64_NUM_COUNTERS; i++) { + struct kvm_pmc *pmc = &pmu->gp_counters[i]; + + pmc_stop_counter(pmc); + pmc->counter = pmc->eventsel = 0; + } } struct kvm_pmu_ops amd_pmu_ops = { -- cgit v1.2.3 From 6912ac326d3aab9c0774ebec99f60a73fd04a520 Mon Sep 17 00:00:00 2001 From: Wei Huang Date: Fri, 12 Jun 2015 01:34:56 -0400 Subject: KVM: x86/vPMU: Enable PMU handling for AMD PERFCTRn and EVNTSELn MSRs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch enables AMD guest VM to access (R/W) PMU related MSRs, which include PERFCTR[0..3] and EVNTSEL[0..3]. Reviewed-by: Joerg Roedel Tested-by: Joerg Roedel Reviewed-by: Radim Krčmář Signed-off-by: Wei Huang Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 51 +++++++++------------------------------------------ 1 file changed, 9 insertions(+), 42 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c386f0bd1830..613e13a61cb5 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2202,36 +2202,11 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: return set_msr_mce(vcpu, msr, data); - /* Performance counters are not protected by a CPUID bit, - * so we should check all of them in the generic path for the sake of - * cross vendor migration. - * Writing a zero into the event select MSRs disables them, - * which we perfectly emulate ;-). Any other value should be at least - * reported, some guests depend on them. - */ - case MSR_K7_EVNTSEL0: - case MSR_K7_EVNTSEL1: - case MSR_K7_EVNTSEL2: - case MSR_K7_EVNTSEL3: - if (data != 0) - vcpu_unimpl(vcpu, "unimplemented perfctr wrmsr: " - "0x%x data 0x%llx\n", msr, data); - break; - /* at least RHEL 4 unconditionally writes to the perfctr registers, - * so we ignore writes to make it happy. - */ - case MSR_K7_PERFCTR0: - case MSR_K7_PERFCTR1: - case MSR_K7_PERFCTR2: - case MSR_K7_PERFCTR3: - vcpu_unimpl(vcpu, "unimplemented perfctr wrmsr: " - "0x%x data 0x%llx\n", msr, data); - break; - case MSR_P6_PERFCTR0: - case MSR_P6_PERFCTR1: - pr = true; - case MSR_P6_EVNTSEL0: - case MSR_P6_EVNTSEL1: + case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: + case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: + pr = true; /* fall through */ + case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: + case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1: if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); @@ -2418,24 +2393,16 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_K8_SYSCFG: case MSR_K7_HWCR: case MSR_VM_HSAVE_PA: - case MSR_K7_EVNTSEL0: - case MSR_K7_EVNTSEL1: - case MSR_K7_EVNTSEL2: - case MSR_K7_EVNTSEL3: - case MSR_K7_PERFCTR0: - case MSR_K7_PERFCTR1: - case MSR_K7_PERFCTR2: - case MSR_K7_PERFCTR3: case MSR_K8_INT_PENDING_MSG: case MSR_AMD64_NB_CFG: case MSR_FAM10H_MMIO_CONF_BASE: case MSR_AMD64_BU_CFG2: msr_info->data = 0; break; - case MSR_P6_PERFCTR0: - case MSR_P6_PERFCTR1: - case MSR_P6_EVNTSEL0: - case MSR_P6_EVNTSEL1: + case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: + case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: + case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: + case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1: if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data); msr_info->data = 0; -- cgit v1.2.3 From f2ae45edbca7ba5324eef01719ede0151dc5cead Mon Sep 17 00:00:00 2001 From: Jens Freimann Date: Mon, 22 Jun 2015 13:20:12 +0200 Subject: KVM: s390: clear floating interrupt bitmap and parameters commit 6d3da24141 ("KVM: s390: deliver floating interrupts in order of priority") introduced a regression for the reset handling. We don't clear the bitmap of pending floating interrupts and interrupt parameters. This could result in stale interrupts even after a reset. Let's fix this by clearing the pending bitmap and the parameters for service and machine check interrupts. Cc: stable@vger.kernel.org # 4.1 Signed-off-by: Jens Freimann Signed-off-by: Christian Borntraeger Signed-off-by: Paolo Bonzini --- arch/s390/kvm/interrupt.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 322ef9cfdc80..480b9750e15e 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1621,6 +1621,9 @@ void kvm_s390_clear_float_irqs(struct kvm *kvm) int i; spin_lock(&fi->lock); + fi->pending_irqs = 0; + memset(&fi->srv_signal, 0, sizeof(fi->srv_signal)); + memset(&fi->mchk, 0, sizeof(fi->mchk)); for (i = 0; i < FIRQ_LIST_COUNT; i++) clear_irq_list(&fi->lists[i]); for (i = 0; i < FIRQ_MAX_COUNT; i++) -- cgit v1.2.3