diff options
29 files changed, 801 insertions, 654 deletions
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 2672f4d278ac..7a37d06376be 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -125,9 +125,9 @@ void kvm_arch_hardware_enable(void *garbage) PAGE_KERNEL)); local_irq_save(saved_psr); slot = ia64_itr_entry(0x3, KVM_VMM_BASE, pte, KVM_VMM_SHIFT); + local_irq_restore(saved_psr); if (slot < 0) return; - local_irq_restore(saved_psr); spin_lock(&vp_lock); status = ia64_pal_vp_init_env(kvm_vsa_base ? @@ -160,9 +160,9 @@ void kvm_arch_hardware_disable(void *garbage) local_irq_save(saved_psr); slot = ia64_itr_entry(0x3, KVM_VMM_BASE, pte, KVM_VMM_SHIFT); + local_irq_restore(saved_psr); if (slot < 0) return; - local_irq_restore(saved_psr); status = ia64_pal_vp_exit_env(host_iva); if (status) @@ -1253,6 +1253,7 @@ static int vti_vcpu_setup(struct kvm_vcpu *vcpu, int id) uninit: kvm_vcpu_uninit(vcpu); fail: + local_irq_restore(psr); return r; } diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c index 75dff7cfa814..1170daeda020 100644 --- a/arch/powerpc/kvm/44x_tlb.c +++ b/arch/powerpc/kvm/44x_tlb.c @@ -19,6 +19,7 @@ #include <linux/types.h> #include <linux/string.h> +#include <linux/kvm.h> #include <linux/kvm_host.h> #include <linux/highmem.h> #include <asm/mmu-44x.h> @@ -175,6 +176,10 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gfn_t gfn, u64 asid, stlbe->word1 = (hpaddr & 0xfffffc00) | ((hpaddr >> 32) & 0xf); stlbe->word2 = kvmppc_44x_tlb_shadow_attrib(flags, vcpu->arch.msr & MSR_PR); + + KVMTRACE_5D(STLB_WRITE, vcpu, victim, + stlbe->tid, stlbe->word0, stlbe->word1, stlbe->word2, + handler); } void kvmppc_mmu_invalidate(struct kvm_vcpu *vcpu, u64 eaddr, u64 asid) @@ -203,6 +208,9 @@ void kvmppc_mmu_invalidate(struct kvm_vcpu *vcpu, u64 eaddr, u64 asid) kvmppc_44x_shadow_release(vcpu, i); stlbe->word0 = 0; + KVMTRACE_5D(STLB_INVAL, vcpu, i, + stlbe->tid, stlbe->word0, stlbe->word1, + stlbe->word2, handler); } up_write(¤t->mm->mmap_sem); } @@ -216,8 +224,13 @@ void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode) /* XXX Replace loop with fancy data structures. */ down_write(¤t->mm->mmap_sem); for (i = 0; i <= tlb_44x_hwater; i++) { + struct tlbe *stlbe = &vcpu->arch.shadow_tlb[i]; + kvmppc_44x_shadow_release(vcpu, i); - vcpu->arch.shadow_tlb[i].word0 = 0; + stlbe->word0 = 0; + KVMTRACE_5D(STLB_INVAL, vcpu, i, + stlbe->tid, stlbe->word0, stlbe->word1, + stlbe->word2, handler); } up_write(¤t->mm->mmap_sem); } diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index 6b076010213b..53aaa66b25e5 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -37,6 +37,17 @@ config KVM_BOOKE_HOST Provides host support for KVM on Book E PowerPC processors. Currently this works on 440 processors only. +config KVM_TRACE + bool "KVM trace support" + depends on KVM && MARKERS && SYSFS + select RELAY + select DEBUG_FS + default n + ---help--- + This option allows reading a trace of kvm-related events through + relayfs. Note the ABI is not considered stable and will be + modified in future updates. + source drivers/virtio/Kconfig endif # VIRTUALIZATION diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 04e3449e1f42..2a5d4397ac4b 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -4,9 +4,11 @@ EXTRA_CFLAGS += -Ivirt/kvm -Iarch/powerpc/kvm -common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o) +common-objs-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o) -kvm-objs := $(common-objs) powerpc.o emulate.o booke_guest.o +common-objs-$(CONFIG_KVM_TRACE) += $(addprefix ../../../virt/kvm/, kvm_trace.o) + +kvm-objs := $(common-objs-y) powerpc.o emulate.o booke_guest.o obj-$(CONFIG_KVM) += kvm.o AFLAGS_booke_interrupts.o := -I$(obj) diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c index 000097461283..ce0b4114754d 100644 --- a/arch/powerpc/kvm/emulate.c +++ b/arch/powerpc/kvm/emulate.c @@ -170,6 +170,10 @@ static int kvmppc_emul_tlbwe(struct kvm_vcpu *vcpu, u32 inst) kvmppc_mmu_map(vcpu, eaddr, raddr >> PAGE_SHIFT, asid, flags); } + KVMTRACE_5D(GTLB_WRITE, vcpu, index, + tlbe->tid, tlbe->word0, tlbe->word1, tlbe->word2, + handler); + return EMULATE_DONE; } @@ -765,6 +769,8 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) break; } + KVMTRACE_3D(PPC_INSTR, vcpu, inst, vcpu->arch.pc, emulated, entryexit); + if (advance) vcpu->arch.pc += 4; /* Advance past emulated instruction. */ diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index 4e0633c413f3..ed60f3a74a85 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -18,11 +18,11 @@ #include <asm/uaccess.h> static inline void __user *__guestaddr_to_user(struct kvm_vcpu *vcpu, - u64 guestaddr) + unsigned long guestaddr) { - u64 prefix = vcpu->arch.sie_block->prefix; - u64 origin = vcpu->kvm->arch.guest_origin; - u64 memsize = vcpu->kvm->arch.guest_memsize; + unsigned long prefix = vcpu->arch.sie_block->prefix; + unsigned long origin = vcpu->kvm->arch.guest_origin; + unsigned long memsize = vcpu->kvm->arch.guest_memsize; if (guestaddr < 2 * PAGE_SIZE) guestaddr += prefix; @@ -37,7 +37,7 @@ static inline void __user *__guestaddr_to_user(struct kvm_vcpu *vcpu, return (void __user *) guestaddr; } -static inline int get_guest_u64(struct kvm_vcpu *vcpu, u64 guestaddr, +static inline int get_guest_u64(struct kvm_vcpu *vcpu, unsigned long guestaddr, u64 *result) { void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); @@ -47,10 +47,10 @@ static inline int get_guest_u64(struct kvm_vcpu *vcpu, u64 guestaddr, if (IS_ERR((void __force *) uptr)) return PTR_ERR((void __force *) uptr); - return get_user(*result, (u64 __user *) uptr); + return get_user(*result, (unsigned long __user *) uptr); } -static inline int get_guest_u32(struct kvm_vcpu *vcpu, u64 guestaddr, +static inline int get_guest_u32(struct kvm_vcpu *vcpu, unsigned long guestaddr, u32 *result) { void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); @@ -63,7 +63,7 @@ static inline int get_guest_u32(struct kvm_vcpu *vcpu, u64 guestaddr, return get_user(*result, (u32 __user *) uptr); } -static inline int get_guest_u16(struct kvm_vcpu *vcpu, u64 guestaddr, +static inline int get_guest_u16(struct kvm_vcpu *vcpu, unsigned long guestaddr, u16 *result) { void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); @@ -76,7 +76,7 @@ static inline int get_guest_u16(struct kvm_vcpu *vcpu, u64 guestaddr, return get_user(*result, (u16 __user *) uptr); } -static inline int get_guest_u8(struct kvm_vcpu *vcpu, u64 guestaddr, +static inline int get_guest_u8(struct kvm_vcpu *vcpu, unsigned long guestaddr, u8 *result) { void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); @@ -87,7 +87,7 @@ static inline int get_guest_u8(struct kvm_vcpu *vcpu, u64 guestaddr, return get_user(*result, (u8 __user *) uptr); } -static inline int put_guest_u64(struct kvm_vcpu *vcpu, u64 guestaddr, +static inline int put_guest_u64(struct kvm_vcpu *vcpu, unsigned long guestaddr, u64 value) { void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); @@ -100,7 +100,7 @@ static inline int put_guest_u64(struct kvm_vcpu *vcpu, u64 guestaddr, return put_user(value, (u64 __user *) uptr); } -static inline int put_guest_u32(struct kvm_vcpu *vcpu, u64 guestaddr, +static inline int put_guest_u32(struct kvm_vcpu *vcpu, unsigned long guestaddr, u32 value) { void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); @@ -113,7 +113,7 @@ static inline int put_guest_u32(struct kvm_vcpu *vcpu, u64 guestaddr, return put_user(value, (u32 __user *) uptr); } -static inline int put_guest_u16(struct kvm_vcpu *vcpu, u64 guestaddr, +static inline int put_guest_u16(struct kvm_vcpu *vcpu, unsigned long guestaddr, u16 value) { void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); @@ -126,7 +126,7 @@ static inline int put_guest_u16(struct kvm_vcpu *vcpu, u64 guestaddr, return put_user(value, (u16 __user *) uptr); } -static inline int put_guest_u8(struct kvm_vcpu *vcpu, u64 guestaddr, +static inline int put_guest_u8(struct kvm_vcpu *vcpu, unsigned long guestaddr, u8 value) { void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); @@ -138,7 +138,8 @@ static inline int put_guest_u8(struct kvm_vcpu *vcpu, u64 guestaddr, } -static inline int __copy_to_guest_slow(struct kvm_vcpu *vcpu, u64 guestdest, +static inline int __copy_to_guest_slow(struct kvm_vcpu *vcpu, + unsigned long guestdest, const void *from, unsigned long n) { int rc; @@ -153,12 +154,12 @@ static inline int __copy_to_guest_slow(struct kvm_vcpu *vcpu, u64 guestdest, return 0; } -static inline int copy_to_guest(struct kvm_vcpu *vcpu, u64 guestdest, +static inline int copy_to_guest(struct kvm_vcpu *vcpu, unsigned long guestdest, const void *from, unsigned long n) { - u64 prefix = vcpu->arch.sie_block->prefix; - u64 origin = vcpu->kvm->arch.guest_origin; - u64 memsize = vcpu->kvm->arch.guest_memsize; + unsigned long prefix = vcpu->arch.sie_block->prefix; + unsigned long origin = vcpu->kvm->arch.guest_origin; + unsigned long memsize = vcpu->kvm->arch.guest_memsize; if ((guestdest < 2 * PAGE_SIZE) && (guestdest + n > 2 * PAGE_SIZE)) goto slowpath; @@ -189,7 +190,8 @@ slowpath: } static inline int __copy_from_guest_slow(struct kvm_vcpu *vcpu, void *to, - u64 guestsrc, unsigned long n) + unsigned long guestsrc, + unsigned long n) { int rc; unsigned long i; @@ -204,11 +206,11 @@ static inline int __copy_from_guest_slow(struct kvm_vcpu *vcpu, void *to, } static inline int copy_from_guest(struct kvm_vcpu *vcpu, void *to, - u64 guestsrc, unsigned long n) + unsigned long guestsrc, unsigned long n) { - u64 prefix = vcpu->arch.sie_block->prefix; - u64 origin = vcpu->kvm->arch.guest_origin; - u64 memsize = vcpu->kvm->arch.guest_memsize; + unsigned long prefix = vcpu->arch.sie_block->prefix; + unsigned long origin = vcpu->kvm->arch.guest_origin; + unsigned long memsize = vcpu->kvm->arch.guest_memsize; if ((guestsrc < 2 * PAGE_SIZE) && (guestsrc + n > 2 * PAGE_SIZE)) goto slowpath; @@ -238,11 +240,12 @@ slowpath: return __copy_from_guest_slow(vcpu, to, guestsrc, n); } -static inline int copy_to_guest_absolute(struct kvm_vcpu *vcpu, u64 guestdest, +static inline int copy_to_guest_absolute(struct kvm_vcpu *vcpu, + unsigned long guestdest, const void *from, unsigned long n) { - u64 origin = vcpu->kvm->arch.guest_origin; - u64 memsize = vcpu->kvm->arch.guest_memsize; + unsigned long origin = vcpu->kvm->arch.guest_origin; + unsigned long memsize = vcpu->kvm->arch.guest_memsize; if (guestdest + n > memsize) return -EFAULT; @@ -256,10 +259,11 @@ static inline int copy_to_guest_absolute(struct kvm_vcpu *vcpu, u64 guestdest, } static inline int copy_from_guest_absolute(struct kvm_vcpu *vcpu, void *to, - u64 guestsrc, unsigned long n) + unsigned long guestsrc, + unsigned long n) { - u64 origin = vcpu->kvm->arch.guest_origin; - u64 memsize = vcpu->kvm->arch.guest_memsize; + unsigned long origin = vcpu->kvm->arch.guest_origin; + unsigned long memsize = vcpu->kvm->arch.guest_memsize; if (guestsrc + n > memsize) return -EFAULT; diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 47a0b642174c..61236102203e 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -20,7 +20,7 @@ #include "kvm-s390.h" #include "gaccess.h" -static int handle_lctg(struct kvm_vcpu *vcpu) +static int handle_lctlg(struct kvm_vcpu *vcpu) { int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; int reg3 = vcpu->arch.sie_block->ipa & 0x000f; @@ -30,7 +30,7 @@ static int handle_lctg(struct kvm_vcpu *vcpu) u64 useraddr; int reg, rc; - vcpu->stat.instruction_lctg++; + vcpu->stat.instruction_lctlg++; if ((vcpu->arch.sie_block->ipb & 0xff) != 0x2f) return -ENOTSUPP; @@ -38,9 +38,12 @@ static int handle_lctg(struct kvm_vcpu *vcpu) if (base2) useraddr += vcpu->arch.guest_gprs[base2]; + if (useraddr & 7) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + reg = reg1; - VCPU_EVENT(vcpu, 5, "lctg r1:%x, r3:%x,b2:%x,d2:%x", reg1, reg3, base2, + VCPU_EVENT(vcpu, 5, "lctlg r1:%x, r3:%x,b2:%x,d2:%x", reg1, reg3, base2, disp2); do { @@ -74,6 +77,9 @@ static int handle_lctl(struct kvm_vcpu *vcpu) if (base2) useraddr += vcpu->arch.guest_gprs[base2]; + if (useraddr & 3) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x,b2:%x,d2:%x", reg1, reg3, base2, disp2); @@ -99,7 +105,7 @@ static intercept_handler_t instruction_handlers[256] = { [0xae] = kvm_s390_handle_sigp, [0xb2] = kvm_s390_handle_priv, [0xb7] = handle_lctl, - [0xeb] = handle_lctg, + [0xeb] = handle_lctlg, }; static int handle_noop(struct kvm_vcpu *vcpu) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 11230b0db957..2960702b4824 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -13,6 +13,7 @@ #include <asm/lowcore.h> #include <asm/uaccess.h> #include <linux/kvm_host.h> +#include <linux/signal.h> #include "kvm-s390.h" #include "gaccess.h" @@ -246,15 +247,10 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu, default: BUG(); } - if (exception) { - VCPU_EVENT(vcpu, 1, "%s", "program exception while delivering" - " interrupt"); - kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - if (inti->type == KVM_S390_PROGRAM_INT) { - printk(KERN_WARNING "kvm: recursive program check\n"); - BUG(); - } + printk("kvm: The guest lowcore is not mapped during interrupt " + "delivery, killing userspace\n"); + do_exit(SIGKILL); } } @@ -277,14 +273,11 @@ static int __try_deliver_ckc_interrupt(struct kvm_vcpu *vcpu) __LC_EXT_NEW_PSW, sizeof(psw_t)); if (rc == -EFAULT) exception = 1; - if (exception) { - VCPU_EVENT(vcpu, 1, "%s", "program exception while delivering" \ - " ckc interrupt"); - kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - return 0; + printk("kvm: The guest lowcore is not mapped during interrupt " + "delivery, killing userspace\n"); + do_exit(SIGKILL); } - return 1; } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 1782cbcd2829..8b00eb2ddf57 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -39,7 +39,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "exit_instruction", VCPU_STAT(exit_instruction) }, { "exit_program_interruption", VCPU_STAT(exit_program_interruption) }, { "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) }, - { "instruction_lctg", VCPU_STAT(instruction_lctg) }, + { "instruction_lctlg", VCPU_STAT(instruction_lctlg) }, { "instruction_lctl", VCPU_STAT(instruction_lctl) }, { "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) }, { "deliver_service_signal", VCPU_STAT(deliver_service_signal) }, @@ -112,7 +112,12 @@ long kvm_arch_dev_ioctl(struct file *filp, int kvm_dev_ioctl_check_extension(long ext) { - return 0; + switch (ext) { + case KVM_CAP_USER_MEMORY: + return 1; + default: + return 0; + } } /* Section: vm related */ diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index 5a556114eaa5..170392687ce0 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -43,7 +43,8 @@ #define SIGP_STAT_RECEIVER_CHECK 0x00000001UL -static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr, u64 *reg) +static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr, + unsigned long *reg) { struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; int rc; @@ -167,7 +168,7 @@ static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter) } static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, - u64 *reg) + unsigned long *reg) { struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; struct kvm_s390_local_interrupt *li; diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index c31164e8aa46..55e179ad98ef 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -30,6 +30,11 @@ #include <linux/kvm_host.h> +static void pic_clear_isr(struct kvm_kpic_state *s, int irq) +{ + s->isr &= ~(1 << irq); +} + /* * set irq level. If an edge is detected, then the IRR is set to 1 */ @@ -141,11 +146,12 @@ void kvm_pic_set_irq(void *opaque, int irq, int level) */ static inline void pic_intack(struct kvm_kpic_state *s, int irq) { + s->isr |= 1 << irq; if (s->auto_eoi) { if (s->rotate_on_auto_eoi) s->priority_add = (irq + 1) & 7; - } else - s->isr |= (1 << irq); + pic_clear_isr(s, irq); + } /* * We don't clear a level sensitive interrupt here */ @@ -243,7 +249,7 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) priority = get_priority(s, s->isr); if (priority != 8) { irq = (priority + s->priority_add) & 7; - s->isr &= ~(1 << irq); + pic_clear_isr(s, irq); if (cmd == 5) s->priority_add = (irq + 1) & 7; pic_update_irq(s->pics_state); @@ -251,7 +257,7 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) break; case 3: irq = val & 7; - s->isr &= ~(1 << irq); + pic_clear_isr(s, irq); pic_update_irq(s->pics_state); break; case 6: @@ -260,8 +266,8 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) break; case 7: irq = val & 7; - s->isr &= ~(1 << irq); s->priority_add = (irq + 1) & 7; + pic_clear_isr(s, irq); pic_update_irq(s->pics_state); break; default: @@ -303,7 +309,7 @@ static u32 pic_poll_read(struct kvm_kpic_state *s, u32 addr1) s->pics_state->pics[0].irr &= ~(1 << 2); } s->irr &= ~(1 << ret); - s->isr &= ~(1 << ret); + pic_clear_isr(s, ret); if (addr1 >> 7 || ret != 2) pic_update_irq(s->pics_state); } else { diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 76d736b5f664..0d9e55275af1 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -100,3 +100,14 @@ void __kvm_migrate_timers(struct kvm_vcpu *vcpu) __kvm_migrate_apic_timer(vcpu); __kvm_migrate_pit_timer(vcpu); } + +/* This should be called with the kvm->lock mutex held */ +void kvm_set_irq(struct kvm *kvm, int irq, int level) +{ + /* Not possible to detect if the guest uses the PIC or the + * IOAPIC. So set the bit in both. The guest will ignore + * writes to the unused one. + */ + kvm_ioapic_set_irq(kvm->arch.vioapic, irq, level); + kvm_pic_set_irq(pic_irqchip(kvm), irq, level); +} diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 7ca47cbb48bb..07ff2aef0c13 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -82,6 +82,8 @@ static inline int irqchip_in_kernel(struct kvm *kvm) void kvm_pic_reset(struct kvm_kpic_state *s); +void kvm_set_irq(struct kvm *kvm, int irq, int level); + void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec); void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu); void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h new file mode 100644 index 000000000000..1ff819dce7d3 --- /dev/null +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -0,0 +1,32 @@ +#ifndef ASM_KVM_CACHE_REGS_H +#define ASM_KVM_CACHE_REGS_H + +static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + if (!test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail)) + kvm_x86_ops->cache_reg(vcpu, reg); + + return vcpu->arch.regs[reg]; +} + +static inline void kvm_register_write(struct kvm_vcpu *vcpu, + enum kvm_reg reg, + unsigned long val) +{ + vcpu->arch.regs[reg] = val; + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); +} + +static inline unsigned long kvm_rip_read(struct kvm_vcpu *vcpu) +{ + return kvm_register_read(vcpu, VCPU_REGS_RIP); +} + +static inline void kvm_rip_write(struct kvm_vcpu *vcpu, unsigned long val) +{ + kvm_register_write(vcpu, VCPU_REGS_RIP, val); +} + +#endif diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 73f43de69f67..9fde0ac24268 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -32,6 +32,7 @@ #include <asm/current.h> #include <asm/apicdef.h> #include <asm/atomic.h> +#include "kvm_cache_regs.h" #include "irq.h" #define PRId64 "d" @@ -558,8 +559,7 @@ static void __report_tpr_access(struct kvm_lapic *apic, bool write) struct kvm_run *run = vcpu->run; set_bit(KVM_REQ_REPORT_TPR_ACCESS, &vcpu->requests); - kvm_x86_ops->cache_regs(vcpu); - run->tpr_access.rip = vcpu->arch.rip; + run->tpr_access.rip = kvm_rip_read(vcpu); run->tpr_access.is_write = write; } diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index b0e4ddca6c18..2b60b7dc231d 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -909,11 +909,10 @@ static void kvm_mmu_reset_last_pte_updated(struct kvm *kvm) kvm->vcpus[i]->arch.last_pte_updated = NULL; } -static void kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp) +static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp) { u64 *parent_pte; - ++kvm->stat.mmu_shadow_zapped; while (sp->multimapped || sp->parent_pte) { if (!sp->multimapped) parent_pte = sp->parent_pte; @@ -928,19 +927,22 @@ static void kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_put_page(sp, parent_pte); set_shadow_pte(parent_pte, shadow_trap_nonpresent_pte); } +} + +static void kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + ++kvm->stat.mmu_shadow_zapped; kvm_mmu_page_unlink_children(kvm, sp); + kvm_mmu_unlink_parents(kvm, sp); + if (!sp->role.invalid && !sp->role.metaphysical) + unaccount_shadowed(kvm, sp->gfn); if (!sp->root_count) { - if (!sp->role.metaphysical && !sp->role.invalid) - unaccount_shadowed(kvm, sp->gfn); hlist_del(&sp->hash_link); kvm_mmu_free_page(kvm, sp); } else { - int invalid = sp->role.invalid; - list_move(&sp->link, &kvm->arch.active_mmu_pages); sp->role.invalid = 1; + list_move(&sp->link, &kvm->arch.active_mmu_pages); kvm_reload_remote_mmus(kvm); - if (!sp->role.metaphysical && !invalid) - unaccount_shadowed(kvm, sp->gfn); } kvm_mmu_reset_last_pte_updated(kvm); } @@ -1733,7 +1735,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, index = kvm_page_table_hashfn(gfn); bucket = &vcpu->kvm->arch.mmu_page_hash[index]; hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) { - if (sp->gfn != gfn || sp->role.metaphysical) + if (sp->gfn != gfn || sp->role.metaphysical || sp->role.invalid) continue; pte_size = sp->role.glevels == PT32_ROOT_LEVEL ? 4 : 8; misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1); @@ -1814,6 +1816,7 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) spin_unlock(&vcpu->kvm->mmu_lock); return r; } +EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt); void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu) { @@ -1870,6 +1873,12 @@ void kvm_enable_tdp(void) } EXPORT_SYMBOL_GPL(kvm_enable_tdp); +void kvm_disable_tdp(void) +{ + tdp_enabled = false; +} +EXPORT_SYMBOL_GPL(kvm_disable_tdp); + static void free_mmu_pages(struct kvm_vcpu *vcpu) { struct kvm_mmu_page *sp; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index b756e876dce3..551547f8fa7e 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -18,6 +18,7 @@ #include "kvm_svm.h" #include "irq.h" #include "mmu.h" +#include "kvm_cache_regs.h" #include <linux/module.h> #include <linux/kernel.h> @@ -35,10 +36,6 @@ MODULE_LICENSE("GPL"); #define IOPM_ALLOC_ORDER 2 #define MSRPM_ALLOC_ORDER 1 -#define DB_VECTOR 1 -#define UD_VECTOR 6 -#define GP_VECTOR 13 - #define DR7_GD_MASK (1 << 13) #define DR6_BD_MASK (1 << 13) @@ -235,13 +232,11 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) printk(KERN_DEBUG "%s: NOP\n", __func__); return; } - if (svm->next_rip - svm->vmcb->save.rip > MAX_INST_SIZE) - printk(KERN_ERR "%s: ip 0x%llx next 0x%llx\n", - __func__, - svm->vmcb->save.rip, - svm->next_rip); + if (svm->next_rip - kvm_rip_read(vcpu) > MAX_INST_SIZE) + printk(KERN_ERR "%s: ip 0x%lx next 0x%llx\n", + __func__, kvm_rip_read(vcpu), svm->next_rip); - vcpu->arch.rip = svm->vmcb->save.rip = svm->next_rip; + kvm_rip_write(vcpu, svm->next_rip); svm->vmcb->control.int_state &= ~SVM_INTERRUPT_SHADOW_MASK; vcpu->arch.interrupt_window_open = 1; @@ -453,7 +448,8 @@ static __init int svm_hardware_setup(void) if (npt_enabled) { printk(KERN_INFO "kvm: Nested Paging enabled\n"); kvm_enable_tdp(); - } + } else + kvm_disable_tdp(); return 0; @@ -579,6 +575,7 @@ static void init_vmcb(struct vcpu_svm *svm) save->dr7 = 0x400; save->rflags = 2; save->rip = 0x0000fff0; + svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip; /* * cr0 val on cpu init should be 0x60000010, we enable cpu @@ -613,10 +610,12 @@ static int svm_vcpu_reset(struct kvm_vcpu *vcpu) init_vmcb(svm); if (vcpu->vcpu_id != 0) { - svm->vmcb->save.rip = 0; + kvm_rip_write(vcpu, 0); svm->vmcb->save.cs.base = svm->vcpu.arch.sipi_vector << 12; svm->vmcb->save.cs.selector = svm->vcpu.arch.sipi_vector << 8; } + vcpu->arch.regs_avail = ~0; + vcpu->arch.regs_dirty = ~0; return 0; } @@ -719,23 +718,6 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu) rdtscll(vcpu->arch.host_tsc); } -static void svm_cache_regs(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - vcpu->arch.regs[VCPU_REGS_RAX] = svm->vmcb->save.rax; - vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; - vcpu->arch.rip = svm->vmcb->save.rip; -} - -static void svm_decache_regs(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; - svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; - svm->vmcb->save.rip = vcpu->arch.rip; -} - static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) { return to_svm(vcpu)->vmcb->save.rflags; @@ -1007,10 +989,13 @@ static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) struct kvm *kvm = svm->vcpu.kvm; u64 fault_address; u32 error_code; + bool event_injection = false; if (!irqchip_in_kernel(kvm) && - is_external_interrupt(exit_int_info)) + is_external_interrupt(exit_int_info)) { + event_injection = true; push_irq(&svm->vcpu, exit_int_info & SVM_EVTINJ_VEC_MASK); + } fault_address = svm->vmcb->control.exit_info_2; error_code = svm->vmcb->control.exit_info_1; @@ -1024,6 +1009,8 @@ static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) (u32)fault_address, (u32)(fault_address >> 32), handler); + if (event_injection) + kvm_mmu_unprotect_page_virt(&svm->vcpu, fault_address); return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code); } @@ -1121,14 +1108,14 @@ static int nop_on_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) static int halt_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) { - svm->next_rip = svm->vmcb->save.rip + 1; + svm->next_rip = kvm_rip_read(&svm->vcpu) + 1; skip_emulated_instruction(&svm->vcpu); return kvm_emulate_halt(&svm->vcpu); } static int vmmcall_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) { - svm->next_rip = svm->vmcb->save.rip + 3; + svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; skip_emulated_instruction(&svm->vcpu); kvm_emulate_hypercall(&svm->vcpu); return 1; @@ -1160,7 +1147,7 @@ static int task_switch_interception(struct vcpu_svm *svm, static int cpuid_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) { - svm->next_rip = svm->vmcb->save.rip + 2; + svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; kvm_emulate_cpuid(&svm->vcpu); return 1; } @@ -1255,9 +1242,9 @@ static int rdmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) KVMTRACE_3D(MSR_READ, &svm->vcpu, ecx, (u32)data, (u32)(data >> 32), handler); - svm->vmcb->save.rax = data & 0xffffffff; + svm->vcpu.arch.regs[VCPU_REGS_RAX] = data & 0xffffffff; svm->vcpu.arch.regs[VCPU_REGS_RDX] = data >> 32; - svm->next_rip = svm->vmcb->save.rip + 2; + svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; skip_emulated_instruction(&svm->vcpu); } return 1; @@ -1341,13 +1328,13 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) static int wrmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) { u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; - u64 data = (svm->vmcb->save.rax & -1u) + u64 data = (svm->vcpu.arch.regs[VCPU_REGS_RAX] & -1u) | ((u64)(svm->vcpu.arch.regs[VCPU_REGS_RDX] & -1u) << 32); KVMTRACE_3D(MSR_WRITE, &svm->vcpu, ecx, (u32)data, (u32)(data >> 32), handler); - svm->next_rip = svm->vmcb->save.rip + 2; + svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; if (svm_set_msr(&svm->vcpu, ecx, data)) kvm_inject_gp(&svm->vcpu, 0); else @@ -1698,6 +1685,12 @@ static inline void sync_lapic_to_cr8(struct kvm_vcpu *vcpu) svm->vmcb->control.int_ctl |= cr8 & V_TPR_MASK; } +#ifdef CONFIG_X86_64 +#define R "r" +#else +#define R "e" +#endif + static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1705,6 +1698,10 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) u16 gs_selector; u16 ldt_selector; + svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; + svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; + svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; + pre_svm_run(svm); sync_lapic_to_cr8(vcpu); @@ -1732,19 +1729,14 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) local_irq_enable(); asm volatile ( + "push %%"R"bp; \n\t" + "mov %c[rbx](%[svm]), %%"R"bx \n\t" + "mov %c[rcx](%[svm]), %%"R"cx \n\t" + "mov %c[rdx](%[svm]), %%"R"dx \n\t" + "mov %c[rsi](%[svm]), %%"R"si \n\t" + "mov %c[rdi](%[svm]), %%"R"di \n\t" + "mov %c[rbp](%[svm]), %%"R"bp \n\t" #ifdef CONFIG_X86_64 - "push %%rbp; \n\t" -#else - "push %%ebp; \n\t" -#endif - -#ifdef CONFIG_X86_64 - "mov %c[rbx](%[svm]), %%rbx \n\t" - "mov %c[rcx](%[svm]), %%rcx \n\t" - "mov %c[rdx](%[svm]), %%rdx \n\t" - "mov %c[rsi](%[svm]), %%rsi \n\t" - "mov %c[rdi](%[svm]), %%rdi \n\t" - "mov %c[rbp](%[svm]), %%rbp \n\t" "mov %c[r8](%[svm]), %%r8 \n\t" "mov %c[r9](%[svm]), %%r9 \n\t" "mov %c[r10](%[svm]), %%r10 \n\t" @@ -1753,41 +1745,24 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) "mov %c[r13](%[svm]), %%r13 \n\t" "mov %c[r14](%[svm]), %%r14 \n\t" "mov %c[r15](%[svm]), %%r15 \n\t" -#else - "mov %c[rbx](%[svm]), %%ebx \n\t" - "mov %c[rcx](%[svm]), %%ecx \n\t" - "mov %c[rdx](%[svm]), %%edx \n\t" - "mov %c[rsi](%[svm]), %%esi \n\t" - "mov %c[rdi](%[svm]), %%edi \n\t" - "mov %c[rbp](%[svm]), %%ebp \n\t" #endif -#ifdef CONFIG_X86_64 - /* Enter guest mode */ - "push %%rax \n\t" - "mov %c[vmcb](%[svm]), %%rax \n\t" - __ex(SVM_VMLOAD) "\n\t" - __ex(SVM_VMRUN) "\n\t" - __ex(SVM_VMSAVE) "\n\t" - "pop %%rax \n\t" -#else /* Enter guest mode */ - "push %%eax \n\t" - "mov %c[vmcb](%[svm]), %%eax \n\t" + "push %%"R"ax \n\t" + "mov %c[vmcb](%[svm]), %%"R"ax \n\t" __ex(SVM_VMLOAD) "\n\t" __ex(SVM_VMRUN) "\n\t" __ex(SVM_VMSAVE) "\n\t" - "pop %%eax \n\t" -#endif + "pop %%"R"ax \n\t" /* Save guest registers, load host registers */ + "mov %%"R"bx, %c[rbx](%[svm]) \n\t" + "mov %%"R"cx, %c[rcx](%[svm]) \n\t" + "mov %%"R"dx, %c[rdx](%[svm]) \n\t" + "mov %%"R"si, %c[rsi](%[svm]) \n\t" + "mov %%"R"di, %c[rdi](%[svm]) \n\t" + "mov %%"R"bp, %c[rbp](%[svm]) \n\t" #ifdef CONFIG_X86_64 - "mov %%rbx, %c[rbx](%[svm]) \n\t" - "mov %%rcx, %c[rcx](%[svm]) \n\t" - "mov %%rdx, %c[rdx](%[svm]) \n\t" - "mov %%rsi, %c[rsi](%[svm]) \n\t" - "mov %%rdi, %c[rdi](%[svm]) \n\t" - "mov %%rbp, %c[rbp](%[svm]) \n\t" "mov %%r8, %c[r8](%[svm]) \n\t" "mov %%r9, %c[r9](%[svm]) \n\t" "mov %%r10, %c[r10](%[svm]) \n\t" @@ -1796,18 +1771,8 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) "mov %%r13, %c[r13](%[svm]) \n\t" "mov %%r14, %c[r14](%[svm]) \n\t" "mov %%r15, %c[r15](%[svm]) \n\t" - - "pop %%rbp; \n\t" -#else - "mov %%ebx, %c[rbx](%[svm]) \n\t" - "mov %%ecx, %c[rcx](%[svm]) \n\t" - "mov %%edx, %c[rdx](%[svm]) \n\t" - "mov %%esi, %c[rsi](%[svm]) \n\t" - "mov %%edi, %c[rdi](%[svm]) \n\t" - "mov %%ebp, %c[rbp](%[svm]) \n\t" - - "pop %%ebp; \n\t" #endif + "pop %%"R"bp" : : [svm]"a"(svm), [vmcb]"i"(offsetof(struct vcpu_svm, vmcb_pa)), @@ -1828,11 +1793,9 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) [r15]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_R15])) #endif : "cc", "memory" + , R"bx", R"cx", R"dx", R"si", R"di" #ifdef CONFIG_X86_64 - , "rbx", "rcx", "rdx", "rsi", "rdi" , "r8", "r9", "r10", "r11" , "r12", "r13", "r14", "r15" -#else - , "ebx", "ecx", "edx" , "esi", "edi" #endif ); @@ -1840,6 +1803,9 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) load_db_regs(svm->host_db_regs); vcpu->arch.cr2 = svm->vmcb->save.cr2; + vcpu->arch.regs[VCPU_REGS_RAX] = svm->vmcb->save.rax; + vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; + vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; write_dr6(svm->host_dr6); write_dr7(svm->host_dr7); @@ -1861,6 +1827,8 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) svm->next_rip = 0; } +#undef R + static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1959,8 +1927,6 @@ static struct kvm_x86_ops svm_x86_ops = { .set_gdt = svm_set_gdt, .get_dr = svm_get_dr, .set_dr = svm_set_dr, - .cache_regs = svm_cache_regs, - .decache_regs = svm_decache_regs, .get_rflags = svm_get_rflags, .set_rflags = svm_set_rflags, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 0cac63701719..c4510fe0b2b9 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -26,6 +26,8 @@ #include <linux/highmem.h> #include <linux/sched.h> #include <linux/moduleparam.h> +#include "kvm_cache_regs.h" +#include "x86.h" #include <asm/io.h> #include <asm/desc.h> @@ -56,6 +58,7 @@ struct vmcs { struct vcpu_vmx { struct kvm_vcpu vcpu; struct list_head local_vcpus_link; + unsigned long host_rsp; int launched; u8 fail; u32 idt_vectoring_info; @@ -468,7 +471,7 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) if (!vcpu->fpu_active) eb |= 1u << NM_VECTOR; if (vcpu->guest_debug.enabled) - eb |= 1u << 1; + eb |= 1u << DB_VECTOR; if (vcpu->arch.rmode.active) eb = ~0; if (vm_need_ept()) @@ -715,9 +718,9 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) unsigned long rip; u32 interruptibility; - rip = vmcs_readl(GUEST_RIP); + rip = kvm_rip_read(vcpu); rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN); - vmcs_writel(GUEST_RIP, rip); + kvm_rip_write(vcpu, rip); /* * We emulated an instruction, so temporary interrupt blocking @@ -733,19 +736,35 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, bool has_error_code, u32 error_code) { + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (has_error_code) + vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code); + + if (vcpu->arch.rmode.active) { + vmx->rmode.irq.pending = true; + vmx->rmode.irq.vector = nr; + vmx->rmode.irq.rip = kvm_rip_read(vcpu); + if (nr == BP_VECTOR) + vmx->rmode.irq.rip++; + vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, + nr | INTR_TYPE_SOFT_INTR + | (has_error_code ? INTR_INFO_DELIVER_CODE_MASK : 0) + | INTR_INFO_VALID_MASK); + vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1); + kvm_rip_write(vcpu, vmx->rmode.irq.rip - 1); + return; + } + vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, nr | INTR_TYPE_EXCEPTION | (has_error_code ? INTR_INFO_DELIVER_CODE_MASK : 0) | INTR_INFO_VALID_MASK); - if (has_error_code) - vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code); } static bool vmx_exception_injected(struct kvm_vcpu *vcpu) { - struct vcpu_vmx *vmx = to_vmx(vcpu); - - return !(vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK); + return false; } /* @@ -947,24 +966,19 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) return ret; } -/* - * Sync the rsp and rip registers into the vcpu structure. This allows - * registers to be accessed by indexing vcpu->arch.regs. - */ -static void vcpu_load_rsp_rip(struct kvm_vcpu *vcpu) -{ - vcpu->arch.regs[VCPU_REGS_RSP] = vmcs_readl(GUEST_RSP); - vcpu->arch.rip = vmcs_readl(GUEST_RIP); -} - -/* - * Syncs rsp and rip back into the vmcs. Should be called after possible - * modification. - */ -static void vcpu_put_rsp_rip(struct kvm_vcpu *vcpu) +static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) { - vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); - vmcs_writel(GUEST_RIP, vcpu->arch.rip); + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); + switch (reg) { + case VCPU_REGS_RSP: + vcpu->arch.regs[VCPU_REGS_RSP] = vmcs_readl(GUEST_RSP); + break; + case VCPU_REGS_RIP: + vcpu->arch.regs[VCPU_REGS_RIP] = vmcs_readl(GUEST_RIP); + break; + default: + break; + } } static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg) @@ -1007,17 +1021,9 @@ static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg) static int vmx_get_irq(struct kvm_vcpu *vcpu) { - struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 idtv_info_field; - - idtv_info_field = vmx->idt_vectoring_info; - if (idtv_info_field & INTR_INFO_VALID_MASK) { - if (is_external_interrupt(idtv_info_field)) - return idtv_info_field & VECTORING_INFO_VECTOR_MASK; - else - printk(KERN_DEBUG "pending exception: not handled yet\n"); - } - return -1; + if (!vcpu->arch.interrupt.pending) + return -1; + return vcpu->arch.interrupt.nr; } static __init int cpu_has_kvm_support(void) @@ -1031,9 +1037,9 @@ static __init int vmx_disabled_by_bios(void) u64 msr; rdmsrl(MSR_IA32_FEATURE_CONTROL, msr); - return (msr & (MSR_IA32_FEATURE_CONTROL_LOCKED | - MSR_IA32_FEATURE_CONTROL_VMXON_ENABLED)) - == MSR_IA32_FEATURE_CONTROL_LOCKED; + return (msr & (IA32_FEATURE_CONTROL_LOCKED_BIT | + IA32_FEATURE_CONTROL_VMXON_ENABLED_BIT)) + == IA32_FEATURE_CONTROL_LOCKED_BIT; /* locked but not enabled */ } @@ -1045,14 +1051,14 @@ static void hardware_enable(void *garbage) INIT_LIST_HEAD(&per_cpu(vcpus_on_cpu, cpu)); rdmsrl(MSR_IA32_FEATURE_CONTROL, old); - if ((old & (MSR_IA32_FEATURE_CONTROL_LOCKED | - MSR_IA32_FEATURE_CONTROL_VMXON_ENABLED)) - != (MSR_IA32_FEATURE_CONTROL_LOCKED | - MSR_IA32_FEATURE_CONTROL_VMXON_ENABLED)) + if ((old & (IA32_FEATURE_CONTROL_LOCKED_BIT | + IA32_FEATURE_CONTROL_VMXON_ENABLED_BIT)) + != (IA32_FEATURE_CONTROL_LOCKED_BIT | + IA32_FEATURE_CONTROL_VMXON_ENABLED_BIT)) /* enable and lock */ wrmsrl(MSR_IA32_FEATURE_CONTROL, old | - MSR_IA32_FEATURE_CONTROL_LOCKED | - MSR_IA32_FEATURE_CONTROL_VMXON_ENABLED); + IA32_FEATURE_CONTROL_LOCKED_BIT | + IA32_FEATURE_CONTROL_VMXON_ENABLED_BIT); write_cr4(read_cr4() | X86_CR4_VMXE); /* FIXME: not cpu hotplug safe */ asm volatile (ASM_VMX_VMXON_RAX : : "a"(&phys_addr), "m"(phys_addr) @@ -2019,6 +2025,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) u64 msr; int ret; + vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)); down_read(&vcpu->kvm->slots_lock); if (!init_rmode(vmx->vcpu.kvm)) { ret = -ENOMEM; @@ -2072,10 +2079,10 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_RFLAGS, 0x02); if (vmx->vcpu.vcpu_id == 0) - vmcs_writel(GUEST_RIP, 0xfff0); + kvm_rip_write(vcpu, 0xfff0); else - vmcs_writel(GUEST_RIP, 0); - vmcs_writel(GUEST_RSP, 0); + kvm_rip_write(vcpu, 0); + kvm_register_write(vcpu, VCPU_REGS_RSP, 0); /* todo: dr0 = dr1 = dr2 = dr3 = 0; dr6 = 0xffff0ff0 */ vmcs_writel(GUEST_DR7, 0x400); @@ -2139,11 +2146,11 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu, int irq) if (vcpu->arch.rmode.active) { vmx->rmode.irq.pending = true; vmx->rmode.irq.vector = irq; - vmx->rmode.irq.rip = vmcs_readl(GUEST_RIP); + vmx->rmode.irq.rip = kvm_rip_read(vcpu); vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, irq | INTR_TYPE_SOFT_INTR | INTR_INFO_VALID_MASK); vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1); - vmcs_writel(GUEST_RIP, vmx->rmode.irq.rip - 1); + kvm_rip_write(vcpu, vmx->rmode.irq.rip - 1); return; } vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, @@ -2154,7 +2161,6 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu) { vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR); - vcpu->arch.nmi_pending = 0; } static void kvm_do_inject_irq(struct kvm_vcpu *vcpu) @@ -2237,9 +2243,6 @@ static void kvm_guest_debug_pre(struct kvm_vcpu *vcpu) static int handle_rmode_exception(struct kvm_vcpu *vcpu, int vec, u32 err_code) { - if (!vcpu->arch.rmode.active) - return 0; - /* * Instruction with address size override prefix opcode 0x67 * Cause the #SS fault with 0 error code in VM86 mode. @@ -2247,6 +2250,25 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) if (emulate_instruction(vcpu, NULL, 0, 0, 0) == EMULATE_DONE) return 1; + /* + * Forward all other exceptions that are valid in real mode. + * FIXME: Breaks guest debugging in real mode, needs to be fixed with + * the required debugging infrastructure rework. + */ + switch (vec) { + case DE_VECTOR: + case DB_VECTOR: + case BP_VECTOR: + case OF_VECTOR: + case BR_VECTOR: + case UD_VECTOR: + case DF_VECTOR: + case SS_VECTOR: + case GP_VECTOR: + case MF_VECTOR: + kvm_queue_exception(vcpu, vec); + return 1; + } return 0; } @@ -2288,7 +2310,7 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } error_code = 0; - rip = vmcs_readl(GUEST_RIP); + rip = kvm_rip_read(vcpu); if (intr_info & INTR_INFO_DELIVER_CODE_MASK) error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); if (is_page_fault(intr_info)) { @@ -2298,6 +2320,8 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) cr2 = vmcs_readl(EXIT_QUALIFICATION); KVMTRACE_3D(PAGE_FAULT, vcpu, error_code, (u32)cr2, (u32)((u64)cr2 >> 32), handler); + if (vcpu->arch.interrupt.pending || vcpu->arch.exception.pending) + kvm_mmu_unprotect_page_virt(vcpu, cr2); return kvm_mmu_page_fault(vcpu, cr2, error_code); } @@ -2384,27 +2408,25 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) reg = (exit_qualification >> 8) & 15; switch ((exit_qualification >> 4) & 3) { case 0: /* mov to cr */ - KVMTRACE_3D(CR_WRITE, vcpu, (u32)cr, (u32)vcpu->arch.regs[reg], - (u32)((u64)vcpu->arch.regs[reg] >> 32), handler); + KVMTRACE_3D(CR_WRITE, vcpu, (u32)cr, + (u32)kvm_register_read(vcpu, reg), + (u32)((u64)kvm_register_read(vcpu, reg) >> 32), + handler); switch (cr) { case 0: - vcpu_load_rsp_rip(vcpu); - kvm_set_cr0(vcpu, vcpu->arch.regs[reg]); + kvm_set_cr0(vcpu, kvm_register_read(vcpu, reg)); skip_emulated_instruction(vcpu); return 1; case 3: - vcpu_load_rsp_rip(vcpu); - kvm_set_cr3(vcpu, vcpu->arch.regs[reg]); + kvm_set_cr3(vcpu, kvm_register_read(vcpu, reg)); skip_emulated_instruction(vcpu); return 1; case 4: - vcpu_load_rsp_rip(vcpu); - kvm_set_cr4(vcpu, vcpu->arch.regs[reg]); + kvm_set_cr4(vcpu, kvm_register_read(vcpu, reg)); skip_emulated_instruction(vcpu); return 1; case 8: - vcpu_load_rsp_rip(vcpu); - kvm_set_cr8(vcpu, vcpu->arch.regs[reg]); + kvm_set_cr8(vcpu, kvm_register_read(vcpu, reg)); skip_emulated_instruction(vcpu); if (irqchip_in_kernel(vcpu->kvm)) return 1; @@ -2413,7 +2435,6 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) }; break; case 2: /* clts */ - vcpu_load_rsp_rip(vcpu); vmx_fpu_deactivate(vcpu); vcpu->arch.cr0 &= ~X86_CR0_TS; vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0); @@ -2424,21 +2445,17 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) case 1: /*mov from cr*/ switch (cr) { case 3: - vcpu_load_rsp_rip(vcpu); - vcpu->arch.regs[reg] = vcpu->arch.cr3; - vcpu_put_rsp_rip(vcpu); + kvm_register_write(vcpu, reg, vcpu->arch.cr3); KVMTRACE_3D(CR_READ, vcpu, (u32)cr, - (u32)vcpu->arch.regs[reg], - (u32)((u64)vcpu->arch.regs[reg] >> 32), + (u32)kvm_register_read(vcpu, reg), + (u32)((u64)kvm_register_read(vcpu, reg) >> 32), handler); skip_emulated_instruction(vcpu); return 1; case 8: - vcpu_load_rsp_rip(vcpu); - vcpu->arch.regs[reg] = kvm_get_cr8(vcpu); - vcpu_put_rsp_rip(vcpu); + kvm_register_write(vcpu, reg, kvm_get_cr8(vcpu)); KVMTRACE_2D(CR_READ, vcpu, (u32)cr, - (u32)vcpu->arch.regs[reg], handler); + (u32)kvm_register_read(vcpu, reg), handler); skip_emulated_instruction(vcpu); return 1; } @@ -2470,7 +2487,6 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) exit_qualification = vmcs_readl(EXIT_QUALIFICATION); dr = exit_qualification & 7; reg = (exit_qualification >> 8) & 15; - vcpu_load_rsp_rip(vcpu); if (exit_qualification & 16) { /* mov from dr */ switch (dr) { @@ -2483,12 +2499,11 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) default: val = 0; } - vcpu->arch.regs[reg] = val; + kvm_register_write(vcpu, reg, val); KVMTRACE_2D(DR_READ, vcpu, (u32)dr, (u32)val, handler); } else { /* mov to dr */ } - vcpu_put_rsp_rip(vcpu); skip_emulated_instruction(vcpu); return 1; } @@ -2733,8 +2748,8 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); u32 vectoring_info = vmx->idt_vectoring_info; - KVMTRACE_3D(VMEXIT, vcpu, exit_reason, (u32)vmcs_readl(GUEST_RIP), - (u32)((u64)vmcs_readl(GUEST_RIP) >> 32), entryexit); + KVMTRACE_3D(VMEXIT, vcpu, exit_reason, (u32)kvm_rip_read(vcpu), + (u32)((u64)kvm_rip_read(vcpu) >> 32), entryexit); /* Access CR3 don't cause VMExit in paging mode, so we need * to sync with guest real CR3. */ @@ -2827,88 +2842,95 @@ static void enable_intr_window(struct kvm_vcpu *vcpu) enable_irq_window(vcpu); } -static void vmx_intr_assist(struct kvm_vcpu *vcpu) +static void vmx_complete_interrupts(struct vcpu_vmx *vmx) { - struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 idtv_info_field, intr_info_field, exit_intr_info_field; - int vector; + u32 exit_intr_info; + u32 idt_vectoring_info; + bool unblock_nmi; + u8 vector; + int type; + bool idtv_info_valid; + u32 error; - update_tpr_threshold(vcpu); - - intr_info_field = vmcs_read32(VM_ENTRY_INTR_INFO_FIELD); - exit_intr_info_field = vmcs_read32(VM_EXIT_INTR_INFO); - idtv_info_field = vmx->idt_vectoring_info; - if (intr_info_field & INTR_INFO_VALID_MASK) { - if (idtv_info_field & INTR_INFO_VALID_MASK) { - /* TODO: fault when IDT_Vectoring */ - if (printk_ratelimit()) - printk(KERN_ERR "Fault when IDT_Vectoring\n"); - } - enable_intr_window(vcpu); - return; + exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); + if (cpu_has_virtual_nmis()) { + unblock_nmi = (exit_intr_info & INTR_INFO_UNBLOCK_NMI) != 0; + vector = exit_intr_info & INTR_INFO_VECTOR_MASK; + /* + * SDM 3: 25.7.1.2 + * Re-set bit "block by NMI" before VM entry if vmexit caused by + * a guest IRET fault. + */ + if (unblock_nmi && vector != DF_VECTOR) + vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, + GUEST_INTR_STATE_NMI); } - if (unlikely(idtv_info_field & INTR_INFO_VALID_MASK)) { - if ((idtv_info_field & VECTORING_INFO_TYPE_MASK) - == INTR_TYPE_EXT_INTR - && vcpu->arch.rmode.active) { - u8 vect = idtv_info_field & VECTORING_INFO_VECTOR_MASK; - - vmx_inject_irq(vcpu, vect); - enable_intr_window(vcpu); - return; - } - - KVMTRACE_1D(REDELIVER_EVT, vcpu, idtv_info_field, handler); + idt_vectoring_info = vmx->idt_vectoring_info; + idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK; + vector = idt_vectoring_info & VECTORING_INFO_VECTOR_MASK; + type = idt_vectoring_info & VECTORING_INFO_TYPE_MASK; + if (vmx->vcpu.arch.nmi_injected) { /* * SDM 3: 25.7.1.2 * Clear bit "block by NMI" before VM entry if a NMI delivery * faulted. */ - if ((idtv_info_field & VECTORING_INFO_TYPE_MASK) - == INTR_TYPE_NMI_INTR && cpu_has_virtual_nmis()) - vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, - vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & - ~GUEST_INTR_STATE_NMI); - - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, idtv_info_field - & ~INTR_INFO_RESVD_BITS_MASK); - vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, - vmcs_read32(VM_EXIT_INSTRUCTION_LEN)); - - if (unlikely(idtv_info_field & INTR_INFO_DELIVER_CODE_MASK)) - vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, - vmcs_read32(IDT_VECTORING_ERROR_CODE)); - enable_intr_window(vcpu); - return; + if (idtv_info_valid && type == INTR_TYPE_NMI_INTR) + vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO, + GUEST_INTR_STATE_NMI); + else + vmx->vcpu.arch.nmi_injected = false; + } + kvm_clear_exception_queue(&vmx->vcpu); + if (idtv_info_valid && type == INTR_TYPE_EXCEPTION) { + if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) { + error = vmcs_read32(IDT_VECTORING_ERROR_CODE); + kvm_queue_exception_e(&vmx->vcpu, vector, error); + } else + kvm_queue_exception(&vmx->vcpu, vector); + vmx->idt_vectoring_info = 0; } + kvm_clear_interrupt_queue(&vmx->vcpu); + if (idtv_info_valid && type == INTR_TYPE_EXT_INTR) { + kvm_queue_interrupt(&vmx->vcpu, vector); + vmx->idt_vectoring_info = 0; + } +} + +static void vmx_intr_assist(struct kvm_vcpu *vcpu) +{ + u32 intr_info_field; + + update_tpr_threshold(vcpu); + + intr_info_field = vmcs_read32(VM_ENTRY_INTR_INFO_FIELD); if (cpu_has_virtual_nmis()) { - /* - * SDM 3: 25.7.1.2 - * Re-set bit "block by NMI" before VM entry if vmexit caused by - * a guest IRET fault. - */ - if ((exit_intr_info_field & INTR_INFO_UNBLOCK_NMI) && - (exit_intr_info_field & INTR_INFO_VECTOR_MASK) != 8) - vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, - vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) | - GUEST_INTR_STATE_NMI); - else if (vcpu->arch.nmi_pending) { - if (vmx_nmi_enabled(vcpu)) - vmx_inject_nmi(vcpu); + if (vcpu->arch.nmi_pending && !vcpu->arch.nmi_injected) { + if (vmx_nmi_enabled(vcpu)) { + vcpu->arch.nmi_pending = false; + vcpu->arch.nmi_injected = true; + } else { + enable_intr_window(vcpu); + return; + } + } + if (vcpu->arch.nmi_injected) { + vmx_inject_nmi(vcpu); enable_intr_window(vcpu); return; } - } - if (!kvm_cpu_has_interrupt(vcpu)) - return; - if (vmx_irq_enabled(vcpu)) { - vector = kvm_cpu_get_interrupt(vcpu); - vmx_inject_irq(vcpu, vector); - kvm_timer_intr_post(vcpu, vector); - } else - enable_irq_window(vcpu); + if (!vcpu->arch.interrupt.pending && kvm_cpu_has_interrupt(vcpu)) { + if (vmx_irq_enabled(vcpu)) + kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu)); + else + enable_irq_window(vcpu); + } + if (vcpu->arch.interrupt.pending) { + vmx_inject_irq(vcpu, vcpu->arch.interrupt.nr); + kvm_timer_intr_post(vcpu, vcpu->arch.interrupt.nr); + } } /* @@ -2920,9 +2942,9 @@ static void vmx_intr_assist(struct kvm_vcpu *vcpu) static void fixup_rmode_irq(struct vcpu_vmx *vmx) { vmx->rmode.irq.pending = 0; - if (vmcs_readl(GUEST_RIP) + 1 != vmx->rmode.irq.rip) + if (kvm_rip_read(&vmx->vcpu) + 1 != vmx->rmode.irq.rip) return; - vmcs_writel(GUEST_RIP, vmx->rmode.irq.rip); + kvm_rip_write(&vmx->vcpu, vmx->rmode.irq.rip); if (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK) { vmx->idt_vectoring_info &= ~VECTORING_INFO_TYPE_MASK; vmx->idt_vectoring_info |= INTR_TYPE_EXT_INTR; @@ -2934,11 +2956,24 @@ static void fixup_rmode_irq(struct vcpu_vmx *vmx) | vmx->rmode.irq.vector; } +#ifdef CONFIG_X86_64 +#define R "r" +#define Q "q" +#else +#define R "e" +#define Q "l" +#endif + static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 intr_info; + if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty)) + vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); + if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty)) + vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); + /* * Loading guest fpu may have cleared host cr0.ts */ @@ -2946,26 +2981,25 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) asm( /* Store host registers */ -#ifdef CONFIG_X86_64 - "push %%rdx; push %%rbp;" - "push %%rcx \n\t" -#else - "push %%edx; push %%ebp;" - "push %%ecx \n\t" -#endif + "push %%"R"dx; push %%"R"bp;" + "push %%"R"cx \n\t" + "cmp %%"R"sp, %c[host_rsp](%0) \n\t" + "je 1f \n\t" + "mov %%"R"sp, %c[host_rsp](%0) \n\t" __ex(ASM_VMX_VMWRITE_RSP_RDX) "\n\t" + "1: \n\t" /* Check if vmlaunch of vmresume is needed */ "cmpl $0, %c[launched](%0) \n\t" /* Load guest registers. Don't clobber flags. */ + "mov %c[cr2](%0), %%"R"ax \n\t" + "mov %%"R"ax, %%cr2 \n\t" + "mov %c[rax](%0), %%"R"ax \n\t" + "mov %c[rbx](%0), %%"R"bx \n\t" + "mov %c[rdx](%0), %%"R"dx \n\t" + "mov %c[rsi](%0), %%"R"si \n\t" + "mov %c[rdi](%0), %%"R"di \n\t" + "mov %c[rbp](%0), %%"R"bp \n\t" #ifdef CONFIG_X86_64 - "mov %c[cr2](%0), %%rax \n\t" - "mov %%rax, %%cr2 \n\t" - "mov %c[rax](%0), %%rax \n\t" - "mov %c[rbx](%0), %%rbx \n\t" - "mov %c[rdx](%0), %%rdx \n\t" - "mov %c[rsi](%0), %%rsi \n\t" - "mov %c[rdi](%0), %%rdi \n\t" - "mov %c[rbp](%0), %%rbp \n\t" "mov %c[r8](%0), %%r8 \n\t" "mov %c[r9](%0), %%r9 \n\t" "mov %c[r10](%0), %%r10 \n\t" @@ -2974,18 +3008,9 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) "mov %c[r13](%0), %%r13 \n\t" "mov %c[r14](%0), %%r14 \n\t" "mov %c[r15](%0), %%r15 \n\t" - "mov %c[rcx](%0), %%rcx \n\t" /* kills %0 (rcx) */ -#else - "mov %c[cr2](%0), %%eax \n\t" - "mov %%eax, %%cr2 \n\t" - "mov %c[rax](%0), %%eax \n\t" - "mov %c[rbx](%0), %%ebx \n\t" - "mov %c[rdx](%0), %%edx \n\t" - "mov %c[rsi](%0), %%esi \n\t" - "mov %c[rdi](%0), %%edi \n\t" - "mov %c[rbp](%0), %%ebp \n\t" - "mov %c[rcx](%0), %%ecx \n\t" /* kills %0 (ecx) */ #endif + "mov %c[rcx](%0), %%"R"cx \n\t" /* kills %0 (ecx) */ + /* Enter guest mode */ "jne .Llaunched \n\t" __ex(ASM_VMX_VMLAUNCH) "\n\t" @@ -2993,15 +3018,15 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) ".Llaunched: " __ex(ASM_VMX_VMRESUME) "\n\t" ".Lkvm_vmx_return: " /* Save guest registers, load host registers, keep flags */ + "xchg %0, (%%"R"sp) \n\t" + "mov %%"R"ax, %c[rax](%0) \n\t" + "mov %%"R"bx, %c[rbx](%0) \n\t" + "push"Q" (%%"R"sp); pop"Q" %c[rcx](%0) \n\t" + "mov %%"R"dx, %c[rdx](%0) \n\t" + "mov %%"R"si, %c[rsi](%0) \n\t" + "mov %%"R"di, %c[rdi](%0) \n\t" + "mov %%"R"bp, %c[rbp](%0) \n\t" #ifdef CONFIG_X86_64 - "xchg %0, (%%rsp) \n\t" - "mov %%rax, %c[rax](%0) \n\t" - "mov %%rbx, %c[rbx](%0) \n\t" - "pushq (%%rsp); popq %c[rcx](%0) \n\t" - "mov %%rdx, %c[rdx](%0) \n\t" - "mov %%rsi, %c[rsi](%0) \n\t" - "mov %%rdi, %c[rdi](%0) \n\t" - "mov %%rbp, %c[rbp](%0) \n\t" "mov %%r8, %c[r8](%0) \n\t" "mov %%r9, %c[r9](%0) \n\t" "mov %%r10, %c[r10](%0) \n\t" @@ -3010,28 +3035,16 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) "mov %%r13, %c[r13](%0) \n\t" "mov %%r14, %c[r14](%0) \n\t" "mov %%r15, %c[r15](%0) \n\t" - "mov %%cr2, %%rax \n\t" - "mov %%rax, %c[cr2](%0) \n\t" - - "pop %%rbp; pop %%rbp; pop %%rdx \n\t" -#else - "xchg %0, (%%esp) \n\t" - "mov %%eax, %c[rax](%0) \n\t" - "mov %%ebx, %c[rbx](%0) \n\t" - "pushl (%%esp); popl %c[rcx](%0) \n\t" - "mov %%edx, %c[rdx](%0) \n\t" - "mov %%esi, %c[rsi](%0) \n\t" - "mov %%edi, %c[rdi](%0) \n\t" - "mov %%ebp, %c[rbp](%0) \n\t" - "mov %%cr2, %%eax \n\t" - "mov %%eax, %c[cr2](%0) \n\t" - - "pop %%ebp; pop %%ebp; pop %%edx \n\t" #endif + "mov %%cr2, %%"R"ax \n\t" + "mov %%"R"ax, %c[cr2](%0) \n\t" + + "pop %%"R"bp; pop %%"R"bp; pop %%"R"dx \n\t" "setbe %c[fail](%0) \n\t" : : "c"(vmx), "d"((unsigned long)HOST_RSP), [launched]"i"(offsetof(struct vcpu_vmx, launched)), [fail]"i"(offsetof(struct vcpu_vmx, fail)), + [host_rsp]"i"(offsetof(struct vcpu_vmx, host_rsp)), [rax]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RAX])), [rbx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RBX])), [rcx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RCX])), @@ -3051,14 +3064,15 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) #endif [cr2]"i"(offsetof(struct vcpu_vmx, vcpu.arch.cr2)) : "cc", "memory" + , R"bx", R"di", R"si" #ifdef CONFIG_X86_64 - , "rbx", "rdi", "rsi" , "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15" -#else - , "ebx", "edi", "rsi" #endif ); + vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)); + vcpu->arch.regs_dirty = 0; + vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); if (vmx->rmode.irq.pending) fixup_rmode_irq(vmx); @@ -3078,8 +3092,13 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) KVMTRACE_0D(NMI, vcpu, handler); asm("int $2"); } + + vmx_complete_interrupts(vmx); } +#undef R +#undef Q + static void vmx_free_vmcs(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3116,15 +3135,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) return ERR_PTR(-ENOMEM); allocate_vpid(vmx); - if (id == 0 && vm_need_ept()) { - kvm_mmu_set_base_ptes(VMX_EPT_READABLE_MASK | - VMX_EPT_WRITABLE_MASK | - VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT); - kvm_mmu_set_mask_ptes(0ull, VMX_EPT_FAKE_ACCESSED_MASK, - VMX_EPT_FAKE_DIRTY_MASK, 0ull, - VMX_EPT_EXECUTABLE_MASK); - kvm_enable_tdp(); - } err = kvm_vcpu_init(&vmx->vcpu, kvm, id); if (err) @@ -3231,8 +3241,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .set_idt = vmx_set_idt, .get_gdt = vmx_get_gdt, .set_gdt = vmx_set_gdt, - .cache_regs = vcpu_load_rsp_rip, - .decache_regs = vcpu_put_rsp_rip, + .cache_reg = vmx_cache_reg, .get_rflags = vmx_get_rflags, .set_rflags = vmx_set_rflags, @@ -3303,8 +3312,17 @@ static int __init vmx_init(void) vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_ESP); vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_EIP); - if (cpu_has_vmx_ept()) + if (vm_need_ept()) { bypass_guest_pf = 0; + kvm_mmu_set_base_ptes(VMX_EPT_READABLE_MASK | + VMX_EPT_WRITABLE_MASK | + VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT); + kvm_mmu_set_mask_ptes(0ull, VMX_EPT_FAKE_ACCESSED_MASK, + VMX_EPT_FAKE_DIRTY_MASK, 0ull, + VMX_EPT_EXECUTABLE_MASK); + kvm_enable_tdp(); + } else + kvm_disable_tdp(); if (bypass_guest_pf) kvm_mmu_set_nonpresent_ptes(~0xffeull, 0ull); diff --git a/arch/x86/kvm/vmx.h b/arch/x86/kvm/vmx.h index 425a13436b3f..0c22e5f2af86 100644 --- a/arch/x86/kvm/vmx.h +++ b/arch/x86/kvm/vmx.h @@ -346,8 +346,8 @@ enum vmcs_field { #define MSR_IA32_VMX_EPT_VPID_CAP 0x48c #define MSR_IA32_FEATURE_CONTROL 0x3a -#define MSR_IA32_FEATURE_CONTROL_LOCKED 0x1 -#define MSR_IA32_FEATURE_CONTROL_VMXON_ENABLED 0x4 +#define IA32_FEATURE_CONTROL_LOCKED_BIT 0x1 +#define IA32_FEATURE_CONTROL_VMXON_ENABLED_BIT 0x4 #define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT 9 #define IDENTITY_PAGETABLE_PRIVATE_MEMSLOT 10 diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9f1cdb011cff..f7726a022328 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -19,6 +19,8 @@ #include "mmu.h" #include "i8254.h" #include "tss.h" +#include "kvm_cache_regs.h" +#include "x86.h" #include <linux/clocksource.h> #include <linux/kvm.h> @@ -61,6 +63,7 @@ static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries); struct kvm_x86_ops *kvm_x86_ops; +EXPORT_SYMBOL_GPL(kvm_x86_ops); struct kvm_stats_debugfs_item debugfs_entries[] = { { "pf_fixed", VCPU_STAT(pf_fixed) }, @@ -662,6 +665,18 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) pr_unimpl(vcpu, "%s: MSR_IA32_MCG_CTL 0x%llx, nop\n", __func__, data); break; + case MSR_IA32_DEBUGCTLMSR: + if (!data) { + /* We support the non-activated case already */ + break; + } else if (data & ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_BTF)) { + /* Values other than LBR and BTF are vendor-specific, + thus reserved and should throw a #GP */ + return 1; + } + pr_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n", + __func__, data); + break; case MSR_IA32_UCODE_REV: case MSR_IA32_UCODE_WRITE: break; @@ -754,6 +769,11 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_IA32_MC0_MISC+16: case MSR_IA32_UCODE_REV: case MSR_IA32_EBL_CR_POWERON: + case MSR_IA32_DEBUGCTLMSR: + case MSR_IA32_LASTBRANCHFROMIP: + case MSR_IA32_LASTBRANCHTOIP: + case MSR_IA32_LASTINTFROMIP: + case MSR_IA32_LASTINTTOIP: data = 0; break; case MSR_MTRRcap: @@ -2077,7 +2097,7 @@ int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value) void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context) { u8 opcodes[4]; - unsigned long rip = vcpu->arch.rip; + unsigned long rip = kvm_rip_read(vcpu); unsigned long rip_linear; if (!printk_ratelimit()) @@ -2099,6 +2119,14 @@ static struct x86_emulate_ops emulate_ops = { .cmpxchg_emulated = emulator_cmpxchg_emulated, }; +static void cache_all_regs(struct kvm_vcpu *vcpu) +{ + kvm_register_read(vcpu, VCPU_REGS_RAX); + kvm_register_read(vcpu, VCPU_REGS_RSP); + kvm_register_read(vcpu, VCPU_REGS_RIP); + vcpu->arch.regs_dirty = ~0; +} + int emulate_instruction(struct kvm_vcpu *vcpu, struct kvm_run *run, unsigned long cr2, @@ -2108,8 +2136,15 @@ int emulate_instruction(struct kvm_vcpu *vcpu, int r; struct decode_cache *c; + kvm_clear_exception_queue(vcpu); vcpu->arch.mmio_fault_cr2 = cr2; - kvm_x86_ops->cache_regs(vcpu); + /* + * TODO: fix x86_emulate.c to use guest_read/write_register + * instead of direct ->regs accesses, can save hundred cycles + * on Intel for instructions that don't read/change RSP, for + * for example. + */ + cache_all_regs(vcpu); vcpu->mmio_is_write = 0; vcpu->arch.pio.string = 0; @@ -2169,7 +2204,6 @@ int emulate_instruction(struct kvm_vcpu *vcpu, return EMULATE_DO_MMIO; } - kvm_x86_ops->decache_regs(vcpu); kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); if (vcpu->mmio_is_write) { @@ -2222,20 +2256,19 @@ int complete_pio(struct kvm_vcpu *vcpu) struct kvm_pio_request *io = &vcpu->arch.pio; long delta; int r; - - kvm_x86_ops->cache_regs(vcpu); + unsigned long val; if (!io->string) { - if (io->in) - memcpy(&vcpu->arch.regs[VCPU_REGS_RAX], vcpu->arch.pio_data, - io->size); + if (io->in) { + val = kvm_register_read(vcpu, VCPU_REGS_RAX); + memcpy(&val, vcpu->arch.pio_data, io->size); + kvm_register_write(vcpu, VCPU_REGS_RAX, val); + } } else { if (io->in) { r = pio_copy_data(vcpu); - if (r) { - kvm_x86_ops->cache_regs(vcpu); + if (r) return r; - } } delta = 1; @@ -2245,19 +2278,24 @@ int complete_pio(struct kvm_vcpu *vcpu) * The size of the register should really depend on * current address size. */ - vcpu->arch.regs[VCPU_REGS_RCX] -= delta; + val = kvm_register_read(vcpu, VCPU_REGS_RCX); + val -= delta; + kvm_register_write(vcpu, VCPU_REGS_RCX, val); } if (io->down) delta = -delta; delta *= io->size; - if (io->in) - vcpu->arch.regs[VCPU_REGS_RDI] += delta; - else - vcpu->arch.regs[VCPU_REGS_RSI] += delta; + if (io->in) { + val = kvm_register_read(vcpu, VCPU_REGS_RDI); + val += delta; + kvm_register_write(vcpu, VCPU_REGS_RDI, val); + } else { + val = kvm_register_read(vcpu, VCPU_REGS_RSI); + val += delta; + kvm_register_write(vcpu, VCPU_REGS_RSI, val); + } } - kvm_x86_ops->decache_regs(vcpu); - io->count -= io->cur_count; io->cur_count = 0; @@ -2310,6 +2348,7 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, int size, unsigned port) { struct kvm_io_device *pio_dev; + unsigned long val; vcpu->run->exit_reason = KVM_EXIT_IO; vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; @@ -2330,8 +2369,8 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, KVMTRACE_2D(IO_WRITE, vcpu, vcpu->run->io.port, (u32)size, handler); - kvm_x86_ops->cache_regs(vcpu); - memcpy(vcpu->arch.pio_data, &vcpu->arch.regs[VCPU_REGS_RAX], 4); + val = kvm_register_read(vcpu, VCPU_REGS_RAX); + memcpy(vcpu->arch.pio_data, &val, 4); kvm_x86_ops->skip_emulated_instruction(vcpu); @@ -2516,13 +2555,11 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) unsigned long nr, a0, a1, a2, a3, ret; int r = 1; - kvm_x86_ops->cache_regs(vcpu); - - nr = vcpu->arch.regs[VCPU_REGS_RAX]; - a0 = vcpu->arch.regs[VCPU_REGS_RBX]; - a1 = vcpu->arch.regs[VCPU_REGS_RCX]; - a2 = vcpu->arch.regs[VCPU_REGS_RDX]; - a3 = vcpu->arch.regs[VCPU_REGS_RSI]; + nr = kvm_register_read(vcpu, VCPU_REGS_RAX); + a0 = kvm_register_read(vcpu, VCPU_REGS_RBX); + a1 = kvm_register_read(vcpu, VCPU_REGS_RCX); + a2 = kvm_register_read(vcpu, VCPU_REGS_RDX); + a3 = kvm_register_read(vcpu, VCPU_REGS_RSI); KVMTRACE_1D(VMMCALL, vcpu, (u32)nr, handler); @@ -2545,8 +2582,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) ret = -KVM_ENOSYS; break; } - vcpu->arch.regs[VCPU_REGS_RAX] = ret; - kvm_x86_ops->decache_regs(vcpu); + kvm_register_write(vcpu, VCPU_REGS_RAX, ret); ++vcpu->stat.hypercalls; return r; } @@ -2556,6 +2592,7 @@ int kvm_fix_hypercall(struct kvm_vcpu *vcpu) { char instruction[3]; int ret = 0; + unsigned long rip = kvm_rip_read(vcpu); /* @@ -2565,9 +2602,8 @@ int kvm_fix_hypercall(struct kvm_vcpu *vcpu) */ kvm_mmu_zap_all(vcpu->kvm); - kvm_x86_ops->cache_regs(vcpu); kvm_x86_ops->patch_hypercall(vcpu, instruction); - if (emulator_write_emulated(vcpu->arch.rip, instruction, 3, vcpu) + if (emulator_write_emulated(rip, instruction, 3, vcpu) != X86EMUL_CONTINUE) ret = -EFAULT; @@ -2697,13 +2733,12 @@ void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) u32 function, index; struct kvm_cpuid_entry2 *e, *best; - kvm_x86_ops->cache_regs(vcpu); - function = vcpu->arch.regs[VCPU_REGS_RAX]; - index = vcpu->arch.regs[VCPU_REGS_RCX]; - vcpu->arch.regs[VCPU_REGS_RAX] = 0; - vcpu->arch.regs[VCPU_REGS_RBX] = 0; - vcpu->arch.regs[VCPU_REGS_RCX] = 0; - vcpu->arch.regs[VCPU_REGS_RDX] = 0; + function = kvm_register_read(vcpu, VCPU_REGS_RAX); + index = kvm_register_read(vcpu, VCPU_REGS_RCX); + kvm_register_write(vcpu, VCPU_REGS_RAX, 0); + kvm_register_write(vcpu, VCPU_REGS_RBX, 0); + kvm_register_write(vcpu, VCPU_REGS_RCX, 0); + kvm_register_write(vcpu, VCPU_REGS_RDX, 0); best = NULL; for (i = 0; i < vcpu->arch.cpuid_nent; ++i) { e = &vcpu->arch.cpuid_entries[i]; @@ -2721,18 +2756,17 @@ void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) best = e; } if (best) { - vcpu->arch.regs[VCPU_REGS_RAX] = best->eax; - vcpu->arch.regs[VCPU_REGS_RBX] = best->ebx; - vcpu->arch.regs[VCPU_REGS_RCX] = best->ecx; - vcpu->arch.regs[VCPU_REGS_RDX] = best->edx; + kvm_register_write(vcpu, VCPU_REGS_RAX, best->eax); + kvm_register_write(vcpu, VCPU_REGS_RBX, best->ebx); + kvm_register_write(vcpu, VCPU_REGS_RCX, best->ecx); + kvm_register_write(vcpu, VCPU_REGS_RDX, best->edx); } - kvm_x86_ops->decache_regs(vcpu); kvm_x86_ops->skip_emulated_instruction(vcpu); KVMTRACE_5D(CPUID, vcpu, function, - (u32)vcpu->arch.regs[VCPU_REGS_RAX], - (u32)vcpu->arch.regs[VCPU_REGS_RBX], - (u32)vcpu->arch.regs[VCPU_REGS_RCX], - (u32)vcpu->arch.regs[VCPU_REGS_RDX], handler); + (u32)kvm_register_read(vcpu, VCPU_REGS_RAX), + (u32)kvm_register_read(vcpu, VCPU_REGS_RBX), + (u32)kvm_register_read(vcpu, VCPU_REGS_RCX), + (u32)kvm_register_read(vcpu, VCPU_REGS_RDX), handler); } EXPORT_SYMBOL_GPL(kvm_emulate_cpuid); @@ -2914,8 +2948,8 @@ again: * Profile KVM exit RIPs: */ if (unlikely(prof_on == KVM_PROFILING)) { - kvm_x86_ops->cache_regs(vcpu); - profile_hit(KVM_PROFILING, (void *)vcpu->arch.rip); + unsigned long rip = kvm_rip_read(vcpu); + profile_hit(KVM_PROFILING, (void *)rip); } if (vcpu->arch.exception.pending && kvm_x86_ops->exception_injected(vcpu)) @@ -2996,11 +3030,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } } #endif - if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL) { - kvm_x86_ops->cache_regs(vcpu); - vcpu->arch.regs[VCPU_REGS_RAX] = kvm_run->hypercall.ret; - kvm_x86_ops->decache_regs(vcpu); - } + if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL) + kvm_register_write(vcpu, VCPU_REGS_RAX, + kvm_run->hypercall.ret); r = __vcpu_run(vcpu, kvm_run); @@ -3016,28 +3048,26 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { vcpu_load(vcpu); - kvm_x86_ops->cache_regs(vcpu); - - regs->rax = vcpu->arch.regs[VCPU_REGS_RAX]; - regs->rbx = vcpu->arch.regs[VCPU_REGS_RBX]; - regs->rcx = vcpu->arch.regs[VCPU_REGS_RCX]; - regs->rdx = vcpu->arch.regs[VCPU_REGS_RDX]; - regs->rsi = vcpu->arch.regs[VCPU_REGS_RSI]; - regs->rdi = vcpu->arch.regs[VCPU_REGS_RDI]; - regs->rsp = vcpu->arch.regs[VCPU_REGS_RSP]; - regs->rbp = vcpu->arch.regs[VCPU_REGS_RBP]; + regs->rax = kvm_register_read(vcpu, VCPU_REGS_RAX); + regs->rbx = kvm_register_read(vcpu, VCPU_REGS_RBX); + regs->rcx = kvm_register_read(vcpu, VCPU_REGS_RCX); + regs->rdx = kvm_register_read(vcpu, VCPU_REGS_RDX); + regs->rsi = kvm_register_read(vcpu, VCPU_REGS_RSI); + regs->rdi = kvm_register_read(vcpu, VCPU_REGS_RDI); + regs->rsp = kvm_register_read(vcpu, VCPU_REGS_RSP); + regs->rbp = kvm_register_read(vcpu, VCPU_REGS_RBP); #ifdef CONFIG_X86_64 - regs->r8 = vcpu->arch.regs[VCPU_REGS_R8]; - regs->r9 = vcpu->arch.regs[VCPU_REGS_R9]; - regs->r10 = vcpu->arch.regs[VCPU_REGS_R10]; - regs->r11 = vcpu->arch.regs[VCPU_REGS_R11]; - regs->r12 = vcpu->arch.regs[VCPU_REGS_R12]; - regs->r13 = vcpu->arch.regs[VCPU_REGS_R13]; - regs->r14 = vcpu->arch.regs[VCPU_REGS_R14]; - regs->r15 = vcpu->arch.regs[VCPU_REGS_R15]; + regs->r8 = kvm_register_read(vcpu, VCPU_REGS_R8); + regs->r9 = kvm_register_read(vcpu, VCPU_REGS_R9); + regs->r10 = kvm_register_read(vcpu, VCPU_REGS_R10); + regs->r11 = kvm_register_read(vcpu, VCPU_REGS_R11); + regs->r12 = kvm_register_read(vcpu, VCPU_REGS_R12); + regs->r13 = kvm_register_read(vcpu, VCPU_REGS_R13); + regs->r14 = kvm_register_read(vcpu, VCPU_REGS_R14); + regs->r15 = kvm_register_read(vcpu, VCPU_REGS_R15); #endif - regs->rip = vcpu->arch.rip; + regs->rip = kvm_rip_read(vcpu); regs->rflags = kvm_x86_ops->get_rflags(vcpu); /* @@ -3055,29 +3085,29 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { vcpu_load(vcpu); - vcpu->arch.regs[VCPU_REGS_RAX] = regs->rax; - vcpu->arch.regs[VCPU_REGS_RBX] = regs->rbx; - vcpu->arch.regs[VCPU_REGS_RCX] = regs->rcx; - vcpu->arch.regs[VCPU_REGS_RDX] = regs->rdx; - vcpu->arch.regs[VCPU_REGS_RSI] = regs->rsi; - vcpu->arch.regs[VCPU_REGS_RDI] = regs->rdi; - vcpu->arch.regs[VCPU_REGS_RSP] = regs->rsp; - vcpu->arch.regs[VCPU_REGS_RBP] = regs->rbp; + kvm_register_write(vcpu, VCPU_REGS_RAX, regs->rax); + kvm_register_write(vcpu, VCPU_REGS_RBX, regs->rbx); + kvm_register_write(vcpu, VCPU_REGS_RCX, regs->rcx); + kvm_register_write(vcpu, VCPU_REGS_RDX, regs->rdx); + kvm_register_write(vcpu, VCPU_REGS_RSI, regs->rsi); + kvm_register_write(vcpu, VCPU_REGS_RDI, regs->rdi); + kvm_register_write(vcpu, VCPU_REGS_RSP, regs->rsp); + kvm_register_write(vcpu, VCPU_REGS_RBP, regs->rbp); #ifdef CONFIG_X86_64 - vcpu->arch.regs[VCPU_REGS_R8] = regs->r8; - vcpu->arch.regs[VCPU_REGS_R9] = regs->r9; - vcpu->arch.regs[VCPU_REGS_R10] = regs->r10; - vcpu->arch.regs[VCPU_REGS_R11] = regs->r11; - vcpu->arch.regs[VCPU_REGS_R12] = regs->r12; - vcpu->arch.regs[VCPU_REGS_R13] = regs->r13; - vcpu->arch.regs[VCPU_REGS_R14] = regs->r14; - vcpu->arch.regs[VCPU_REGS_R15] = regs->r15; + kvm_register_write(vcpu, VCPU_REGS_R8, regs->r8); + kvm_register_write(vcpu, VCPU_REGS_R9, regs->r9); + kvm_register_write(vcpu, VCPU_REGS_R10, regs->r10); + kvm_register_write(vcpu, VCPU_REGS_R11, regs->r11); + kvm_register_write(vcpu, VCPU_REGS_R12, regs->r12); + kvm_register_write(vcpu, VCPU_REGS_R13, regs->r13); + kvm_register_write(vcpu, VCPU_REGS_R14, regs->r14); + kvm_register_write(vcpu, VCPU_REGS_R15, regs->r15); + #endif - vcpu->arch.rip = regs->rip; + kvm_rip_write(vcpu, regs->rip); kvm_x86_ops->set_rflags(vcpu, regs->rflags); - kvm_x86_ops->decache_regs(vcpu); vcpu->arch.exception.pending = false; @@ -3184,6 +3214,10 @@ static void seg_desct_to_kvm_desct(struct desc_struct *seg_desc, u16 selector, kvm_desct->base |= seg_desc->base2 << 24; kvm_desct->limit = seg_desc->limit0; kvm_desct->limit |= seg_desc->limit << 16; + if (seg_desc->g) { + kvm_desct->limit <<= 12; + kvm_desct->limit |= 0xfff; + } kvm_desct->selector = selector; kvm_desct->type = seg_desc->type; kvm_desct->present = seg_desc->p; @@ -3223,6 +3257,7 @@ static void get_segment_descritptor_dtable(struct kvm_vcpu *vcpu, static int load_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, struct desc_struct *seg_desc) { + gpa_t gpa; struct descriptor_table dtable; u16 index = selector >> 3; @@ -3232,13 +3267,16 @@ static int load_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, kvm_queue_exception_e(vcpu, GP_VECTOR, selector & 0xfffc); return 1; } - return kvm_read_guest(vcpu->kvm, dtable.base + index * 8, seg_desc, 8); + gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, dtable.base); + gpa += index * 8; + return kvm_read_guest(vcpu->kvm, gpa, seg_desc, 8); } /* allowed just for 8 bytes segments */ static int save_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, struct desc_struct *seg_desc) { + gpa_t gpa; struct descriptor_table dtable; u16 index = selector >> 3; @@ -3246,7 +3284,9 @@ static int save_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, if (dtable.limit < index * 8 + 7) return 1; - return kvm_write_guest(vcpu->kvm, dtable.base + index * 8, seg_desc, 8); + gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, dtable.base); + gpa += index * 8; + return kvm_write_guest(vcpu->kvm, gpa, seg_desc, 8); } static u32 get_tss_base_addr(struct kvm_vcpu *vcpu, @@ -3258,55 +3298,7 @@ static u32 get_tss_base_addr(struct kvm_vcpu *vcpu, base_addr |= (seg_desc->base1 << 16); base_addr |= (seg_desc->base2 << 24); - return base_addr; -} - -static int load_tss_segment32(struct kvm_vcpu *vcpu, - struct desc_struct *seg_desc, - struct tss_segment_32 *tss) -{ - u32 base_addr; - - base_addr = get_tss_base_addr(vcpu, seg_desc); - - return kvm_read_guest(vcpu->kvm, base_addr, tss, - sizeof(struct tss_segment_32)); -} - -static int save_tss_segment32(struct kvm_vcpu *vcpu, - struct desc_struct *seg_desc, - struct tss_segment_32 *tss) -{ - u32 base_addr; - - base_addr = get_tss_base_addr(vcpu, seg_desc); - - return kvm_write_guest(vcpu->kvm, base_addr, tss, - sizeof(struct tss_segment_32)); -} - -static int load_tss_segment16(struct kvm_vcpu *vcpu, - struct desc_struct *seg_desc, - struct tss_segment_16 *tss) -{ - u32 base_addr; - - base_addr = get_tss_base_addr(vcpu, seg_desc); - - return kvm_read_guest(vcpu->kvm, base_addr, tss, - sizeof(struct tss_segment_16)); -} - -static int save_tss_segment16(struct kvm_vcpu *vcpu, - struct desc_struct *seg_desc, - struct tss_segment_16 *tss) -{ - u32 base_addr; - - base_addr = get_tss_base_addr(vcpu, seg_desc); - - return kvm_write_guest(vcpu->kvm, base_addr, tss, - sizeof(struct tss_segment_16)); + return vcpu->arch.mmu.gva_to_gpa(vcpu, base_addr); } static u16 get_segment_selector(struct kvm_vcpu *vcpu, int seg) @@ -3351,17 +3343,16 @@ static void save_state_to_tss32(struct kvm_vcpu *vcpu, struct tss_segment_32 *tss) { tss->cr3 = vcpu->arch.cr3; - tss->eip = vcpu->arch.rip; + tss->eip = kvm_rip_read(vcpu); tss->eflags = kvm_x86_ops->get_rflags(vcpu); - tss->eax = vcpu->arch.regs[VCPU_REGS_RAX]; - tss->ecx = vcpu->arch.regs[VCPU_REGS_RCX]; - tss->edx = vcpu->arch.regs[VCPU_REGS_RDX]; - tss->ebx = vcpu->arch.regs[VCPU_REGS_RBX]; - tss->esp = vcpu->arch.regs[VCPU_REGS_RSP]; - tss->ebp = vcpu->arch.regs[VCPU_REGS_RBP]; - tss->esi = vcpu->arch.regs[VCPU_REGS_RSI]; - tss->edi = vcpu->arch.regs[VCPU_REGS_RDI]; - + tss->eax = kvm_register_read(vcpu, VCPU_REGS_RAX); + tss->ecx = kvm_register_read(vcpu, VCPU_REGS_RCX); + tss->edx = kvm_register_read(vcpu, VCPU_REGS_RDX); + tss->ebx = kvm_register_read(vcpu, VCPU_REGS_RBX); + tss->esp = kvm_register_read(vcpu, VCPU_REGS_RSP); + tss->ebp = kvm_register_read(vcpu, VCPU_REGS_RBP); + tss->esi = kvm_register_read(vcpu, VCPU_REGS_RSI); + tss->edi = kvm_register_read(vcpu, VCPU_REGS_RDI); tss->es = get_segment_selector(vcpu, VCPU_SREG_ES); tss->cs = get_segment_selector(vcpu, VCPU_SREG_CS); tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS); @@ -3377,17 +3368,17 @@ static int load_state_from_tss32(struct kvm_vcpu *vcpu, { kvm_set_cr3(vcpu, tss->cr3); - vcpu->arch.rip = tss->eip; + kvm_rip_write(vcpu, tss->eip); kvm_x86_ops->set_rflags(vcpu, tss->eflags | 2); - vcpu->arch.regs[VCPU_REGS_RAX] = tss->eax; - vcpu->arch.regs[VCPU_REGS_RCX] = tss->ecx; - vcpu->arch.regs[VCPU_REGS_RDX] = tss->edx; - vcpu->arch.regs[VCPU_REGS_RBX] = tss->ebx; - vcpu->arch.regs[VCPU_REGS_RSP] = tss->esp; - vcpu->arch.regs[VCPU_REGS_RBP] = tss->ebp; - vcpu->arch.regs[VCPU_REGS_RSI] = tss->esi; - vcpu->arch.regs[VCPU_REGS_RDI] = tss->edi; + kvm_register_write(vcpu, VCPU_REGS_RAX, tss->eax); + kvm_register_write(vcpu, VCPU_REGS_RCX, tss->ecx); + kvm_register_write(vcpu, VCPU_REGS_RDX, tss->edx); + kvm_register_write(vcpu, VCPU_REGS_RBX, tss->ebx); + kvm_register_write(vcpu, VCPU_REGS_RSP, tss->esp); + kvm_register_write(vcpu, VCPU_REGS_RBP, tss->ebp); + kvm_register_write(vcpu, VCPU_REGS_RSI, tss->esi); + kvm_register_write(vcpu, VCPU_REGS_RDI, tss->edi); if (kvm_load_segment_descriptor(vcpu, tss->ldt_selector, 0, VCPU_SREG_LDTR)) return 1; @@ -3415,16 +3406,16 @@ static int load_state_from_tss32(struct kvm_vcpu *vcpu, static void save_state_to_tss16(struct kvm_vcpu *vcpu, struct tss_segment_16 *tss) { - tss->ip = vcpu->arch.rip; + tss->ip = kvm_rip_read(vcpu); tss->flag = kvm_x86_ops->get_rflags(vcpu); - tss->ax = vcpu->arch.regs[VCPU_REGS_RAX]; - tss->cx = vcpu->arch.regs[VCPU_REGS_RCX]; - tss->dx = vcpu->arch.regs[VCPU_REGS_RDX]; - tss->bx = vcpu->arch.regs[VCPU_REGS_RBX]; - tss->sp = vcpu->arch.regs[VCPU_REGS_RSP]; - tss->bp = vcpu->arch.regs[VCPU_REGS_RBP]; - tss->si = vcpu->arch.regs[VCPU_REGS_RSI]; - tss->di = vcpu->arch.regs[VCPU_REGS_RDI]; + tss->ax = kvm_register_read(vcpu, VCPU_REGS_RAX); + tss->cx = kvm_register_read(vcpu, VCPU_REGS_RCX); + tss->dx = kvm_register_read(vcpu, VCPU_REGS_RDX); + tss->bx = kvm_register_read(vcpu, VCPU_REGS_RBX); + tss->sp = kvm_register_read(vcpu, VCPU_REGS_RSP); + tss->bp = kvm_register_read(vcpu, VCPU_REGS_RBP); + tss->si = kvm_register_read(vcpu, VCPU_REGS_RSI); + tss->di = kvm_register_read(vcpu, VCPU_REGS_RDI); tss->es = get_segment_selector(vcpu, VCPU_SREG_ES); tss->cs = get_segment_selector(vcpu, VCPU_SREG_CS); @@ -3437,16 +3428,16 @@ static void save_state_to_tss16(struct kvm_vcpu *vcpu, static int load_state_from_tss16(struct kvm_vcpu *vcpu, struct tss_segment_16 *tss) { - vcpu->arch.rip = tss->ip; + kvm_rip_write(vcpu, tss->ip); kvm_x86_ops->set_rflags(vcpu, tss->flag | 2); - vcpu->arch.regs[VCPU_REGS_RAX] = tss->ax; - vcpu->arch.regs[VCPU_REGS_RCX] = tss->cx; - vcpu->arch.regs[VCPU_REGS_RDX] = tss->dx; - vcpu->arch.regs[VCPU_REGS_RBX] = tss->bx; - vcpu->arch.regs[VCPU_REGS_RSP] = tss->sp; - vcpu->arch.regs[VCPU_REGS_RBP] = tss->bp; - vcpu->arch.regs[VCPU_REGS_RSI] = tss->si; - vcpu->arch.regs[VCPU_REGS_RDI] = tss->di; + kvm_register_write(vcpu, VCPU_REGS_RAX, tss->ax); + kvm_register_write(vcpu, VCPU_REGS_RCX, tss->cx); + kvm_register_write(vcpu, VCPU_REGS_RDX, tss->dx); + kvm_register_write(vcpu, VCPU_REGS_RBX, tss->bx); + kvm_register_write(vcpu, VCPU_REGS_RSP, tss->sp); + kvm_register_write(vcpu, VCPU_REGS_RBP, tss->bp); + kvm_register_write(vcpu, VCPU_REGS_RSI, tss->si); + kvm_register_write(vcpu, VCPU_REGS_RDI, tss->di); if (kvm_load_segment_descriptor(vcpu, tss->ldt, 0, VCPU_SREG_LDTR)) return 1; @@ -3466,20 +3457,26 @@ static int load_state_from_tss16(struct kvm_vcpu *vcpu, } static int kvm_task_switch_16(struct kvm_vcpu *vcpu, u16 tss_selector, - struct desc_struct *cseg_desc, + u32 old_tss_base, struct desc_struct *nseg_desc) { struct tss_segment_16 tss_segment_16; int ret = 0; - if (load_tss_segment16(vcpu, cseg_desc, &tss_segment_16)) + if (kvm_read_guest(vcpu->kvm, old_tss_base, &tss_segment_16, + sizeof tss_segment_16)) goto out; save_state_to_tss16(vcpu, &tss_segment_16); - save_tss_segment16(vcpu, cseg_desc, &tss_segment_16); - if (load_tss_segment16(vcpu, nseg_desc, &tss_segment_16)) + if (kvm_write_guest(vcpu->kvm, old_tss_base, &tss_segment_16, + sizeof tss_segment_16)) goto out; + + if (kvm_read_guest(vcpu->kvm, get_tss_base_addr(vcpu, nseg_desc), + &tss_segment_16, sizeof tss_segment_16)) + goto out; + if (load_state_from_tss16(vcpu, &tss_segment_16)) goto out; @@ -3489,20 +3486,26 @@ out: } static int kvm_task_switch_32(struct kvm_vcpu *vcpu, u16 tss_selector, - struct desc_struct *cseg_desc, + u32 old_tss_base, struct desc_struct *nseg_desc) { struct tss_segment_32 tss_segment_32; int ret = 0; - if (load_tss_segment32(vcpu, cseg_desc, &tss_segment_32)) + if (kvm_read_guest(vcpu->kvm, old_tss_base, &tss_segment_32, + sizeof tss_segment_32)) goto out; save_state_to_tss32(vcpu, &tss_segment_32); - save_tss_segment32(vcpu, cseg_desc, &tss_segment_32); - if (load_tss_segment32(vcpu, nseg_desc, &tss_segment_32)) + if (kvm_write_guest(vcpu->kvm, old_tss_base, &tss_segment_32, + sizeof tss_segment_32)) + goto out; + + if (kvm_read_guest(vcpu->kvm, get_tss_base_addr(vcpu, nseg_desc), + &tss_segment_32, sizeof tss_segment_32)) goto out; + if (load_state_from_tss32(vcpu, &tss_segment_32)) goto out; @@ -3517,16 +3520,20 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) struct desc_struct cseg_desc; struct desc_struct nseg_desc; int ret = 0; + u32 old_tss_base = get_segment_base(vcpu, VCPU_SREG_TR); + u16 old_tss_sel = get_segment_selector(vcpu, VCPU_SREG_TR); - kvm_get_segment(vcpu, &tr_seg, VCPU_SREG_TR); + old_tss_base = vcpu->arch.mmu.gva_to_gpa(vcpu, old_tss_base); + /* FIXME: Handle errors. Failure to read either TSS or their + * descriptors should generate a pagefault. + */ if (load_guest_segment_descriptor(vcpu, tss_selector, &nseg_desc)) goto out; - if (load_guest_segment_descriptor(vcpu, tr_seg.selector, &cseg_desc)) + if (load_guest_segment_descriptor(vcpu, old_tss_sel, &cseg_desc)) goto out; - if (reason != TASK_SWITCH_IRET) { int cpl; @@ -3544,8 +3551,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) if (reason == TASK_SWITCH_IRET || reason == TASK_SWITCH_JMP) { cseg_desc.type &= ~(1 << 1); //clear the B flag - save_guest_segment_descriptor(vcpu, tr_seg.selector, - &cseg_desc); + save_guest_segment_descriptor(vcpu, old_tss_sel, &cseg_desc); } if (reason == TASK_SWITCH_IRET) { @@ -3554,13 +3560,12 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) } kvm_x86_ops->skip_emulated_instruction(vcpu); - kvm_x86_ops->cache_regs(vcpu); if (nseg_desc.type & 8) - ret = kvm_task_switch_32(vcpu, tss_selector, &cseg_desc, + ret = kvm_task_switch_32(vcpu, tss_selector, old_tss_base, &nseg_desc); else - ret = kvm_task_switch_16(vcpu, tss_selector, &cseg_desc, + ret = kvm_task_switch_16(vcpu, tss_selector, old_tss_base, &nseg_desc); if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) { @@ -3579,7 +3584,6 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) tr_seg.type = 11; kvm_set_segment(vcpu, &tr_seg, VCPU_SREG_TR); out: - kvm_x86_ops->decache_regs(vcpu); return ret; } EXPORT_SYMBOL_GPL(kvm_task_switch); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h new file mode 100644 index 000000000000..6a4be78a7384 --- /dev/null +++ b/arch/x86/kvm/x86.h @@ -0,0 +1,22 @@ +#ifndef ARCH_X86_KVM_X86_H +#define ARCH_X86_KVM_X86_H + +#include <linux/kvm_host.h> + +static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu) +{ + vcpu->arch.exception.pending = false; +} + +static inline void kvm_queue_interrupt(struct kvm_vcpu *vcpu, u8 vector) +{ + vcpu->arch.interrupt.pending = true; + vcpu->arch.interrupt.nr = vector; +} + +static inline void kvm_clear_interrupt_queue(struct kvm_vcpu *vcpu) +{ + vcpu->arch.interrupt.pending = false; +} + +#endif diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c index f2f90468f8b1..d5da7f14d536 100644 --- a/arch/x86/kvm/x86_emulate.c +++ b/arch/x86/kvm/x86_emulate.c @@ -26,6 +26,7 @@ #define DPRINTF(_f, _a ...) printf(_f , ## _a) #else #include <linux/kvm_host.h> +#include "kvm_cache_regs.h" #define DPRINTF(x...) do {} while (0) #endif #include <linux/module.h> @@ -839,7 +840,7 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) /* Shadow copy of register state. Committed on successful emulation. */ memset(c, 0, sizeof(struct decode_cache)); - c->eip = ctxt->vcpu->arch.rip; + c->eip = kvm_rip_read(ctxt->vcpu); ctxt->cs_base = seg_base(ctxt, VCPU_SREG_CS); memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs); @@ -1267,7 +1268,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) if (c->rep_prefix && (c->d & String)) { /* All REP prefixes have the same first termination condition */ if (c->regs[VCPU_REGS_RCX] == 0) { - ctxt->vcpu->arch.rip = c->eip; + kvm_rip_write(ctxt->vcpu, c->eip); goto done; } /* The second termination condition only applies for REPE @@ -1281,17 +1282,17 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) (c->b == 0xae) || (c->b == 0xaf)) { if ((c->rep_prefix == REPE_PREFIX) && ((ctxt->eflags & EFLG_ZF) == 0)) { - ctxt->vcpu->arch.rip = c->eip; + kvm_rip_write(ctxt->vcpu, c->eip); goto done; } if ((c->rep_prefix == REPNE_PREFIX) && ((ctxt->eflags & EFLG_ZF) == EFLG_ZF)) { - ctxt->vcpu->arch.rip = c->eip; + kvm_rip_write(ctxt->vcpu, c->eip); goto done; } } c->regs[VCPU_REGS_RCX]--; - c->eip = ctxt->vcpu->arch.rip; + c->eip = kvm_rip_read(ctxt->vcpu); } if (c->src.type == OP_MEM) { @@ -1768,7 +1769,7 @@ writeback: /* Commit shadow register state. */ memcpy(ctxt->vcpu->arch.regs, c->regs, sizeof c->regs); - ctxt->vcpu->arch.rip = c->eip; + kvm_rip_write(ctxt->vcpu, c->eip); done: if (rc == X86EMUL_UNHANDLEABLE) { @@ -1793,7 +1794,7 @@ twobyte_insn: goto done; /* Let the processor re-execute the fixed hypercall */ - c->eip = ctxt->vcpu->arch.rip; + c->eip = kvm_rip_read(ctxt->vcpu); /* Disable writeback. */ c->dst.type = OP_NONE; break; @@ -1889,7 +1890,7 @@ twobyte_insn: rc = kvm_set_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], msr_data); if (rc) { kvm_inject_gp(ctxt->vcpu, 0); - c->eip = ctxt->vcpu->arch.rip; + c->eip = kvm_rip_read(ctxt->vcpu); } rc = X86EMUL_CONTINUE; c->dst.type = OP_NONE; @@ -1899,7 +1900,7 @@ twobyte_insn: rc = kvm_get_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], &msr_data); if (rc) { kvm_inject_gp(ctxt->vcpu, 0); - c->eip = ctxt->vcpu->arch.rip; + c->eip = kvm_rip_read(ctxt->vcpu); } else { c->regs[VCPU_REGS_RAX] = (u32)msr_data; c->regs[VCPU_REGS_RDX] = msr_data >> 32; diff --git a/drivers/s390/kvm/Makefile b/drivers/s390/kvm/Makefile index 4a5ec39f9ca6..0815690ac1e0 100644 --- a/drivers/s390/kvm/Makefile +++ b/drivers/s390/kvm/Makefile @@ -6,4 +6,4 @@ # it under the terms of the GNU General Public License (version 2 only) # as published by the Free Software Foundation. -obj-$(CONFIG_VIRTIO) += kvm_virtio.o +obj-$(CONFIG_S390_GUEST) += kvm_virtio.o diff --git a/include/asm-s390/kvm_host.h b/include/asm-s390/kvm_host.h index 3234dd5b3511..3c55e4107dcc 100644 --- a/include/asm-s390/kvm_host.h +++ b/include/asm-s390/kvm_host.h @@ -111,7 +111,7 @@ struct kvm_vcpu_stat { u32 exit_validity; u32 exit_instruction; u32 instruction_lctl; - u32 instruction_lctg; + u32 instruction_lctlg; u32 exit_program_interruption; u32 exit_instr_and_program; u32 deliver_emergency_signal; @@ -231,5 +231,5 @@ struct kvm_arch{ struct kvm_s390_float_interrupt float_int; }; -extern int sie64a(struct kvm_s390_sie_block *, __u64 *); +extern int sie64a(struct kvm_s390_sie_block *, unsigned long *); #endif diff --git a/include/asm-x86/kvm.h b/include/asm-x86/kvm.h index 6f1840812e59..8f137495f561 100644 --- a/include/asm-x86/kvm.h +++ b/include/asm-x86/kvm.h @@ -208,26 +208,4 @@ struct kvm_pit_channel_state { struct kvm_pit_state { struct kvm_pit_channel_state channels[3]; }; - -#define KVM_TRC_INJ_VIRQ (KVM_TRC_HANDLER + 0x02) -#define KVM_TRC_REDELIVER_EVT (KVM_TRC_HANDLER + 0x03) -#define KVM_TRC_PEND_INTR (KVM_TRC_HANDLER + 0x04) -#define KVM_TRC_IO_READ (KVM_TRC_HANDLER + 0x05) -#define KVM_TRC_IO_WRITE (KVM_TRC_HANDLER + 0x06) -#define KVM_TRC_CR_READ (KVM_TRC_HANDLER + 0x07) -#define KVM_TRC_CR_WRITE (KVM_TRC_HANDLER + 0x08) -#define KVM_TRC_DR_READ (KVM_TRC_HANDLER + 0x09) -#define KVM_TRC_DR_WRITE (KVM_TRC_HANDLER + 0x0A) -#define KVM_TRC_MSR_READ (KVM_TRC_HANDLER + 0x0B) -#define KVM_TRC_MSR_WRITE (KVM_TRC_HANDLER + 0x0C) -#define KVM_TRC_CPUID (KVM_TRC_HANDLER + 0x0D) -#define KVM_TRC_INTR (KVM_TRC_HANDLER + 0x0E) -#define KVM_TRC_NMI (KVM_TRC_HANDLER + 0x0F) -#define KVM_TRC_VMMCALL (KVM_TRC_HANDLER + 0x10) -#define KVM_TRC_HLT (KVM_TRC_HANDLER + 0x11) -#define KVM_TRC_CLTS (KVM_TRC_HANDLER + 0x12) -#define KVM_TRC_LMSW (KVM_TRC_HANDLER + 0x13) -#define KVM_TRC_APIC_ACCESS (KVM_TRC_HANDLER + 0x14) -#define KVM_TRC_TDP_FAULT (KVM_TRC_HANDLER + 0x15) - #endif diff --git a/include/asm-x86/kvm_host.h b/include/asm-x86/kvm_host.h index fdde0bedaa90..0b6b996a9cb3 100644 --- a/include/asm-x86/kvm_host.h +++ b/include/asm-x86/kvm_host.h @@ -56,6 +56,10 @@ #define KVM_PAGES_PER_HPAGE (KVM_HPAGE_SIZE / PAGE_SIZE) #define DE_VECTOR 0 +#define DB_VECTOR 1 +#define BP_VECTOR 3 +#define OF_VECTOR 4 +#define BR_VECTOR 5 #define UD_VECTOR 6 #define NM_VECTOR 7 #define DF_VECTOR 8 @@ -64,6 +68,7 @@ #define SS_VECTOR 12 #define GP_VECTOR 13 #define PF_VECTOR 14 +#define MF_VECTOR 16 #define MC_VECTOR 18 #define SELECTOR_TI_MASK (1 << 2) @@ -88,7 +93,7 @@ extern struct list_head vm_list; struct kvm_vcpu; struct kvm; -enum { +enum kvm_reg { VCPU_REGS_RAX = 0, VCPU_REGS_RCX = 1, VCPU_REGS_RDX = 2, @@ -107,6 +112,7 @@ enum { VCPU_REGS_R14 = 14, VCPU_REGS_R15 = 15, #endif + VCPU_REGS_RIP, NR_VCPU_REGS }; @@ -218,8 +224,13 @@ struct kvm_vcpu_arch { int interrupt_window_open; unsigned long irq_summary; /* bit vector: 1 per word in irq_pending */ DECLARE_BITMAP(irq_pending, KVM_NR_INTERRUPTS); - unsigned long regs[NR_VCPU_REGS]; /* for rsp: vcpu_load_rsp_rip() */ - unsigned long rip; /* needs vcpu_load_rsp_rip() */ + /* + * rip and regs accesses must go through + * kvm_{register,rip}_{read,write} functions. + */ + unsigned long regs[NR_VCPU_REGS]; + u32 regs_avail; + u32 regs_dirty; unsigned long cr0; unsigned long cr2; @@ -267,6 +278,11 @@ struct kvm_vcpu_arch { u32 error_code; } exception; + struct kvm_queued_interrupt { + bool pending; + u8 nr; + } interrupt; + struct { int active; u8 save_iopl; @@ -292,6 +308,7 @@ struct kvm_vcpu_arch { struct page *time_page; bool nmi_pending; + bool nmi_injected; u64 mtrr[0x100]; }; @@ -412,8 +429,7 @@ struct kvm_x86_ops { unsigned long (*get_dr)(struct kvm_vcpu *vcpu, int dr); void (*set_dr)(struct kvm_vcpu *vcpu, int dr, unsigned long value, int *exception); - void (*cache_regs)(struct kvm_vcpu *vcpu); - void (*decache_regs)(struct kvm_vcpu *vcpu); + void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); @@ -556,6 +572,7 @@ int kvm_fix_hypercall(struct kvm_vcpu *vcpu); int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code); void kvm_enable_tdp(void); +void kvm_disable_tdp(void); int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3); int complete_pio(struct kvm_vcpu *vcpu); @@ -683,24 +700,6 @@ enum { TASK_SWITCH_GATE = 3, }; -#define KVMTRACE_5D(evt, vcpu, d1, d2, d3, d4, d5, name) \ - trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ - vcpu, 5, d1, d2, d3, d4, d5) -#define KVMTRACE_4D(evt, vcpu, d1, d2, d3, d4, name) \ - trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ - vcpu, 4, d1, d2, d3, d4, 0) -#define KVMTRACE_3D(evt, vcpu, d1, d2, d3, name) \ - trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ - vcpu, 3, d1, d2, d3, 0, 0) -#define KVMTRACE_2D(evt, vcpu, d1, d2, name) \ - trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ - vcpu, 2, d1, d2, 0, 0, 0) -#define KVMTRACE_1D(evt, vcpu, d1, name) \ - trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ - vcpu, 1, d1, 0, 0, 0, 0) -#define KVMTRACE_0D(evt, vcpu, name) \ - trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ - vcpu, 0, 0, 0, 0, 0, 0) #ifdef CONFIG_64BIT # define KVM_EX_ENTRY ".quad" diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 0ea064cbfbc8..6edba45ca0aa 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -311,22 +311,33 @@ struct kvm_s390_interrupt { /* This structure represents a single trace buffer record. */ struct kvm_trace_rec { - __u32 event:28; - __u32 extra_u32:3; - __u32 cycle_in:1; + /* variable rec_val + * is split into: + * bits 0 - 27 -> event id + * bits 28 -30 -> number of extra data args of size u32 + * bits 31 -> binary indicator for if tsc is in record + */ + __u32 rec_val; __u32 pid; __u32 vcpu_id; union { struct { - __u64 cycle_u64; + __u64 timestamp; __u32 extra_u32[KVM_TRC_EXTRA_MAX]; - } cycle; + } timestamp; struct { __u32 extra_u32[KVM_TRC_EXTRA_MAX]; - } nocycle; + } notimestamp; } u; } __attribute__((packed)); +#define TRACE_REC_EVENT_ID(val) \ + (0x0fffffff & (val)) +#define TRACE_REC_NUM_DATA_ARGS(val) \ + (0x70000000 & ((val) << 28)) +#define TRACE_REC_TCS(val) \ + (0x80000000 & ((val) << 31)) + #define KVMIO 0xAE /* @@ -439,4 +450,29 @@ struct kvm_trace_rec { #define KVM_GET_MP_STATE _IOR(KVMIO, 0x98, struct kvm_mp_state) #define KVM_SET_MP_STATE _IOW(KVMIO, 0x99, struct kvm_mp_state) +#define KVM_TRC_INJ_VIRQ (KVM_TRC_HANDLER + 0x02) +#define KVM_TRC_REDELIVER_EVT (KVM_TRC_HANDLER + 0x03) +#define KVM_TRC_PEND_INTR (KVM_TRC_HANDLER + 0x04) +#define KVM_TRC_IO_READ (KVM_TRC_HANDLER + 0x05) +#define KVM_TRC_IO_WRITE (KVM_TRC_HANDLER + 0x06) +#define KVM_TRC_CR_READ (KVM_TRC_HANDLER + 0x07) +#define KVM_TRC_CR_WRITE (KVM_TRC_HANDLER + 0x08) +#define KVM_TRC_DR_READ (KVM_TRC_HANDLER + 0x09) +#define KVM_TRC_DR_WRITE (KVM_TRC_HANDLER + 0x0A) +#define KVM_TRC_MSR_READ (KVM_TRC_HANDLER + 0x0B) +#define KVM_TRC_MSR_WRITE (KVM_TRC_HANDLER + 0x0C) +#define KVM_TRC_CPUID (KVM_TRC_HANDLER + 0x0D) +#define KVM_TRC_INTR (KVM_TRC_HANDLER + 0x0E) +#define KVM_TRC_NMI (KVM_TRC_HANDLER + 0x0F) +#define KVM_TRC_VMMCALL (KVM_TRC_HANDLER + 0x10) +#define KVM_TRC_HLT (KVM_TRC_HANDLER + 0x11) +#define KVM_TRC_CLTS (KVM_TRC_HANDLER + 0x12) +#define KVM_TRC_LMSW (KVM_TRC_HANDLER + 0x13) +#define KVM_TRC_APIC_ACCESS (KVM_TRC_HANDLER + 0x14) +#define KVM_TRC_TDP_FAULT (KVM_TRC_HANDLER + 0x15) +#define KVM_TRC_GTLB_WRITE (KVM_TRC_HANDLER + 0x16) +#define KVM_TRC_STLB_WRITE (KVM_TRC_HANDLER + 0x17) +#define KVM_TRC_STLB_INVAL (KVM_TRC_HANDLER + 0x18) +#define KVM_TRC_PPC_INSTR (KVM_TRC_HANDLER + 0x19) + #endif diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 07d68a8ae8e9..379809750ec0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -320,6 +320,25 @@ struct kvm_stats_debugfs_item { extern struct kvm_stats_debugfs_item debugfs_entries[]; extern struct dentry *kvm_debugfs_dir; +#define KVMTRACE_5D(evt, vcpu, d1, d2, d3, d4, d5, name) \ + trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ + vcpu, 5, d1, d2, d3, d4, d5) +#define KVMTRACE_4D(evt, vcpu, d1, d2, d3, d4, name) \ + trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ + vcpu, 4, d1, d2, d3, d4, 0) +#define KVMTRACE_3D(evt, vcpu, d1, d2, d3, name) \ + trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ + vcpu, 3, d1, d2, d3, 0, 0) +#define KVMTRACE_2D(evt, vcpu, d1, d2, name) \ + trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ + vcpu, 2, d1, d2, 0, 0, 0) +#define KVMTRACE_1D(evt, vcpu, d1, name) \ + trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ + vcpu, 1, d1, 0, 0, 0, 0) +#define KVMTRACE_0D(evt, vcpu, name) \ + trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ + vcpu, 0, 0, 0, 0, 0, 0) + #ifdef CONFIG_KVM_TRACE int kvm_trace_ioctl(unsigned int ioctl, unsigned long arg); void kvm_trace_cleanup(void); diff --git a/virt/kvm/kvm_trace.c b/virt/kvm/kvm_trace.c index 58141f31ea8f..41dcc845f78c 100644 --- a/virt/kvm/kvm_trace.c +++ b/virt/kvm/kvm_trace.c @@ -17,6 +17,7 @@ #include <linux/module.h> #include <linux/relay.h> #include <linux/debugfs.h> +#include <linux/ktime.h> #include <linux/kvm_host.h> @@ -35,16 +36,16 @@ static struct kvm_trace *kvm_trace; struct kvm_trace_probe { const char *name; const char *format; - u32 cycle_in; + u32 timestamp_in; marker_probe_func *probe_func; }; -static inline int calc_rec_size(int cycle, int extra) +static inline int calc_rec_size(int timestamp, int extra) { int rec_size = KVM_TRC_HEAD_SIZE; rec_size += extra; - return cycle ? rec_size += KVM_TRC_CYCLE_SIZE : rec_size; + return timestamp ? rec_size += KVM_TRC_CYCLE_SIZE : rec_size; } static void kvm_add_trace(void *probe_private, void *call_data, @@ -54,12 +55,13 @@ static void kvm_add_trace(void *probe_private, void *call_data, struct kvm_trace *kt = kvm_trace; struct kvm_trace_rec rec; struct kvm_vcpu *vcpu; - int i, extra, size; + int i, size; + u32 extra; if (unlikely(kt->trace_state != KVM_TRACE_STATE_RUNNING)) return; - rec.event = va_arg(*args, u32); + rec.rec_val = TRACE_REC_EVENT_ID(va_arg(*args, u32)); vcpu = va_arg(*args, struct kvm_vcpu *); rec.pid = current->tgid; rec.vcpu_id = vcpu->vcpu_id; @@ -67,21 +69,21 @@ static void kvm_add_trace(void *probe_private, void *call_data, extra = va_arg(*args, u32); WARN_ON(!(extra <= KVM_TRC_EXTRA_MAX)); extra = min_t(u32, extra, KVM_TRC_EXTRA_MAX); - rec.extra_u32 = extra; - rec.cycle_in = p->cycle_in; + rec.rec_val |= TRACE_REC_TCS(p->timestamp_in) + | TRACE_REC_NUM_DATA_ARGS(extra); - if (rec.cycle_in) { - rec.u.cycle.cycle_u64 = get_cycles(); + if (p->timestamp_in) { + rec.u.timestamp.timestamp = ktime_to_ns(ktime_get()); - for (i = 0; i < rec.extra_u32; i++) - rec.u.cycle.extra_u32[i] = va_arg(*args, u32); + for (i = 0; i < extra; i++) + rec.u.timestamp.extra_u32[i] = va_arg(*args, u32); } else { - for (i = 0; i < rec.extra_u32; i++) - rec.u.nocycle.extra_u32[i] = va_arg(*args, u32); + for (i = 0; i < extra; i++) + rec.u.notimestamp.extra_u32[i] = va_arg(*args, u32); } - size = calc_rec_size(rec.cycle_in, rec.extra_u32 * sizeof(u32)); + size = calc_rec_size(p->timestamp_in, extra * sizeof(u32)); relay_write(kt->rchan, &rec, size); } |