diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2009-09-14 17:43:43 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2009-09-14 17:43:43 -0700 |
commit | 69def9f05dfce3281bb06599057e6b8097385d39 (patch) | |
tree | 7d826b22924268ddbfad101993b248996d40e2ec /arch/x86/kvm | |
parent | 353f6dd2dec992ddd34620a94b051b0f76227379 (diff) | |
parent | 8e616fc8d343bd7f0f0a0c22407fdcb77f6d22b1 (diff) | |
download | blackbird-op-linux-69def9f05dfce3281bb06599057e6b8097385d39.tar.gz blackbird-op-linux-69def9f05dfce3281bb06599057e6b8097385d39.zip |
Merge branch 'kvm-updates/2.6.32' of git://git.kernel.org/pub/scm/virt/kvm/kvm
* 'kvm-updates/2.6.32' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (202 commits)
MAINTAINERS: update KVM entry
KVM: correct error-handling code
KVM: fix compile warnings on s390
KVM: VMX: Check cpl before emulating debug register access
KVM: fix misreporting of coalesced interrupts by kvm tracer
KVM: x86: drop duplicate kvm_flush_remote_tlb calls
KVM: VMX: call vmx_load_host_state() only if msr is cached
KVM: VMX: Conditionally reload debug register 6
KVM: Use thread debug register storage instead of kvm specific data
KVM guest: do not batch pte updates from interrupt context
KVM: Fix coalesced interrupt reporting in IOAPIC
KVM guest: fix bogus wallclock physical address calculation
KVM: VMX: Fix cr8 exiting control clobbering by EPT
KVM: Optimize kvm_mmu_unprotect_page_virt() for tdp
KVM: Document KVM_CAP_IRQCHIP
KVM: Protect update_cr8_intercept() when running without an apic
KVM: VMX: Fix EPT with WP bit change during paging
KVM: Use kvm_{read,write}_guest_virt() to read and write segment descriptors
KVM: x86 emulator: Add adc and sbb missing decoder flags
KVM: Add missing #include
...
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r-- | arch/x86/kvm/Kconfig | 21 | ||||
-rw-r--r-- | arch/x86/kvm/Makefile | 35 | ||||
-rw-r--r-- | arch/x86/kvm/emulate.c (renamed from arch/x86/kvm/x86_emulate.c) | 265 | ||||
-rw-r--r-- | arch/x86/kvm/i8254.c | 160 | ||||
-rw-r--r-- | arch/x86/kvm/i8254.h | 5 | ||||
-rw-r--r-- | arch/x86/kvm/i8259.c | 116 | ||||
-rw-r--r-- | arch/x86/kvm/irq.h | 1 | ||||
-rw-r--r-- | arch/x86/kvm/kvm_cache_regs.h | 9 | ||||
-rw-r--r-- | arch/x86/kvm/kvm_svm.h | 51 | ||||
-rw-r--r-- | arch/x86/kvm/kvm_timer.h | 2 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.c | 334 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.h | 4 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.c | 587 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.h | 4 | ||||
-rw-r--r-- | arch/x86/kvm/mmutrace.h | 220 | ||||
-rw-r--r-- | arch/x86/kvm/paging_tmpl.h | 141 | ||||
-rw-r--r-- | arch/x86/kvm/svm.c | 889 | ||||
-rw-r--r-- | arch/x86/kvm/timer.c | 16 | ||||
-rw-r--r-- | arch/x86/kvm/trace.h | 355 | ||||
-rw-r--r-- | arch/x86/kvm/vmx.c | 497 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 815 | ||||
-rw-r--r-- | arch/x86/kvm/x86.h | 4 |
22 files changed, 3210 insertions, 1321 deletions
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 8600a09e0c6c..b84e571f4175 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -1,12 +1,8 @@ # # KVM configuration # -config HAVE_KVM - bool -config HAVE_KVM_IRQCHIP - bool - default y +source "virt/kvm/Kconfig" menuconfig VIRTUALIZATION bool "Virtualization" @@ -29,6 +25,9 @@ config KVM select PREEMPT_NOTIFIERS select MMU_NOTIFIER select ANON_INODES + select HAVE_KVM_IRQCHIP + select HAVE_KVM_EVENTFD + select KVM_APIC_ARCHITECTURE ---help--- Support hosting fully virtualized guest machines using hardware virtualization extensions. You will need a fairly recent @@ -63,18 +62,6 @@ config KVM_AMD To compile this as a module, choose M here: the module will be called kvm-amd. -config KVM_TRACE - bool "KVM trace support" - depends on KVM && SYSFS - select MARKERS - 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. - # OK, it's a little counter-intuitive to do this, but it puts it neatly under # the virtualization menu. source drivers/lguest/Kconfig diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index b43c4efafe80..0e7fe78d0f74 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -1,22 +1,19 @@ -# -# Makefile for Kernel-based Virtual Machine module -# - -common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \ - coalesced_mmio.o irq_comm.o) -ifeq ($(CONFIG_KVM_TRACE),y) -common-objs += $(addprefix ../../../virt/kvm/, kvm_trace.o) -endif -ifeq ($(CONFIG_IOMMU_API),y) -common-objs += $(addprefix ../../../virt/kvm/, iommu.o) -endif EXTRA_CFLAGS += -Ivirt/kvm -Iarch/x86/kvm -kvm-objs := $(common-objs) x86.o mmu.o x86_emulate.o i8259.o irq.o lapic.o \ - i8254.o timer.o -obj-$(CONFIG_KVM) += kvm.o -kvm-intel-objs = vmx.o -obj-$(CONFIG_KVM_INTEL) += kvm-intel.o -kvm-amd-objs = svm.o -obj-$(CONFIG_KVM_AMD) += kvm-amd.o +CFLAGS_x86.o := -I. +CFLAGS_svm.o := -I. +CFLAGS_vmx.o := -I. + +kvm-y += $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \ + coalesced_mmio.o irq_comm.o eventfd.o) +kvm-$(CONFIG_IOMMU_API) += $(addprefix ../../../virt/kvm/, iommu.o) + +kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ + i8254.o timer.o +kvm-intel-y += vmx.o +kvm-amd-y += svm.o + +obj-$(CONFIG_KVM) += kvm.o +obj-$(CONFIG_KVM_INTEL) += kvm-intel.o +obj-$(CONFIG_KVM_AMD) += kvm-amd.o diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/emulate.c index 616de4628d60..1be5cd640e93 100644 --- a/arch/x86/kvm/x86_emulate.c +++ b/arch/x86/kvm/emulate.c @@ -1,5 +1,5 @@ /****************************************************************************** - * x86_emulate.c + * emulate.c * * Generic x86 (32-bit and 64-bit) instruction decoder and emulator. * @@ -30,7 +30,9 @@ #define DPRINTF(x...) do {} while (0) #endif #include <linux/module.h> -#include <asm/kvm_x86_emulate.h> +#include <asm/kvm_emulate.h> + +#include "mmu.h" /* for is_long_mode() */ /* * Opcode effective-address decode tables. @@ -60,6 +62,7 @@ #define SrcImmByte (6<<4) /* 8-bit sign-extended immediate operand. */ #define SrcOne (7<<4) /* Implied '1' */ #define SrcImmUByte (8<<4) /* 8-bit unsigned immediate operand. */ +#define SrcImmU (9<<4) /* Immediate operand, unsigned */ #define SrcMask (0xf<<4) /* Generic ModRM decode. */ #define ModRM (1<<8) @@ -97,11 +100,11 @@ static u32 opcode_table[256] = { /* 0x10 - 0x17 */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - 0, 0, 0, 0, + ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, 0, 0, /* 0x18 - 0x1F */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - 0, 0, 0, 0, + ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, 0, 0, /* 0x20 - 0x27 */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, @@ -195,7 +198,7 @@ static u32 opcode_table[256] = { ByteOp | SrcImmUByte, SrcImmUByte, /* 0xE8 - 0xEF */ SrcImm | Stack, SrcImm | ImplicitOps, - SrcImm | Src2Imm16, SrcImmByte | ImplicitOps, + SrcImmU | Src2Imm16, SrcImmByte | ImplicitOps, SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, /* 0xF0 - 0xF7 */ @@ -208,7 +211,7 @@ static u32 opcode_table[256] = { static u32 twobyte_table[256] = { /* 0x00 - 0x0F */ - 0, Group | GroupDual | Group7, 0, 0, 0, 0, ImplicitOps, 0, + 0, Group | GroupDual | Group7, 0, 0, 0, ImplicitOps, ImplicitOps, 0, ImplicitOps, ImplicitOps, 0, 0, 0, ImplicitOps | ModRM, 0, 0, /* 0x10 - 0x1F */ 0, 0, 0, 0, 0, 0, 0, 0, ImplicitOps | ModRM, 0, 0, 0, 0, 0, 0, 0, @@ -216,7 +219,9 @@ static u32 twobyte_table[256] = { ModRM | ImplicitOps, ModRM, ModRM | ImplicitOps, ModRM, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 0x30 - 0x3F */ - ImplicitOps, 0, ImplicitOps, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + ImplicitOps, 0, ImplicitOps, 0, + ImplicitOps, ImplicitOps, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, /* 0x40 - 0x47 */ DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, @@ -319,8 +324,11 @@ static u32 group2_table[] = { }; /* EFLAGS bit definitions. */ +#define EFLG_VM (1<<17) +#define EFLG_RF (1<<16) #define EFLG_OF (1<<11) #define EFLG_DF (1<<10) +#define EFLG_IF (1<<9) #define EFLG_SF (1<<7) #define EFLG_ZF (1<<6) #define EFLG_AF (1<<4) @@ -1027,6 +1035,7 @@ done_prefixes: c->src.type = OP_MEM; break; case SrcImm: + case SrcImmU: c->src.type = OP_IMM; c->src.ptr = (unsigned long *)c->eip; c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; @@ -1044,6 +1053,19 @@ done_prefixes: c->src.val = insn_fetch(s32, 4, c->eip); break; } + if ((c->d & SrcMask) == SrcImmU) { + switch (c->src.bytes) { + case 1: + c->src.val &= 0xff; + break; + case 2: + c->src.val &= 0xffff; + break; + case 4: + c->src.val &= 0xffffffff; + break; + } + } break; case SrcImmByte: case SrcImmUByte: @@ -1375,6 +1397,217 @@ static void toggle_interruptibility(struct x86_emulate_ctxt *ctxt, u32 mask) ctxt->interruptibility = mask; } +static inline void +setup_syscalls_segments(struct x86_emulate_ctxt *ctxt, + struct kvm_segment *cs, struct kvm_segment *ss) +{ + memset(cs, 0, sizeof(struct kvm_segment)); + kvm_x86_ops->get_segment(ctxt->vcpu, cs, VCPU_SREG_CS); + memset(ss, 0, sizeof(struct kvm_segment)); + + cs->l = 0; /* will be adjusted later */ + cs->base = 0; /* flat segment */ + cs->g = 1; /* 4kb granularity */ + cs->limit = 0xffffffff; /* 4GB limit */ + cs->type = 0x0b; /* Read, Execute, Accessed */ + cs->s = 1; + cs->dpl = 0; /* will be adjusted later */ + cs->present = 1; + cs->db = 1; + + ss->unusable = 0; + ss->base = 0; /* flat segment */ + ss->limit = 0xffffffff; /* 4GB limit */ + ss->g = 1; /* 4kb granularity */ + ss->s = 1; + ss->type = 0x03; /* Read/Write, Accessed */ + ss->db = 1; /* 32bit stack segment */ + ss->dpl = 0; + ss->present = 1; +} + +static int +emulate_syscall(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + struct kvm_segment cs, ss; + u64 msr_data; + + /* syscall is not available in real mode */ + if (c->lock_prefix || ctxt->mode == X86EMUL_MODE_REAL + || !(ctxt->vcpu->arch.cr0 & X86_CR0_PE)) + return -1; + + setup_syscalls_segments(ctxt, &cs, &ss); + + kvm_x86_ops->get_msr(ctxt->vcpu, MSR_STAR, &msr_data); + msr_data >>= 32; + cs.selector = (u16)(msr_data & 0xfffc); + ss.selector = (u16)(msr_data + 8); + + if (is_long_mode(ctxt->vcpu)) { + cs.db = 0; + cs.l = 1; + } + kvm_x86_ops->set_segment(ctxt->vcpu, &cs, VCPU_SREG_CS); + kvm_x86_ops->set_segment(ctxt->vcpu, &ss, VCPU_SREG_SS); + + c->regs[VCPU_REGS_RCX] = c->eip; + if (is_long_mode(ctxt->vcpu)) { +#ifdef CONFIG_X86_64 + c->regs[VCPU_REGS_R11] = ctxt->eflags & ~EFLG_RF; + + kvm_x86_ops->get_msr(ctxt->vcpu, + ctxt->mode == X86EMUL_MODE_PROT64 ? + MSR_LSTAR : MSR_CSTAR, &msr_data); + c->eip = msr_data; + + kvm_x86_ops->get_msr(ctxt->vcpu, MSR_SYSCALL_MASK, &msr_data); + ctxt->eflags &= ~(msr_data | EFLG_RF); +#endif + } else { + /* legacy mode */ + kvm_x86_ops->get_msr(ctxt->vcpu, MSR_STAR, &msr_data); + c->eip = (u32)msr_data; + + ctxt->eflags &= ~(EFLG_VM | EFLG_IF | EFLG_RF); + } + + return 0; +} + +static int +emulate_sysenter(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + struct kvm_segment cs, ss; + u64 msr_data; + + /* inject #UD if LOCK prefix is used */ + if (c->lock_prefix) + return -1; + + /* inject #GP if in real mode or paging is disabled */ + if (ctxt->mode == X86EMUL_MODE_REAL || + !(ctxt->vcpu->arch.cr0 & X86_CR0_PE)) { + kvm_inject_gp(ctxt->vcpu, 0); + return -1; + } + + /* XXX sysenter/sysexit have not been tested in 64bit mode. + * Therefore, we inject an #UD. + */ + if (ctxt->mode == X86EMUL_MODE_PROT64) + return -1; + + setup_syscalls_segments(ctxt, &cs, &ss); + + kvm_x86_ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_CS, &msr_data); + switch (ctxt->mode) { + case X86EMUL_MODE_PROT32: + if ((msr_data & 0xfffc) == 0x0) { + kvm_inject_gp(ctxt->vcpu, 0); + return -1; + } + break; + case X86EMUL_MODE_PROT64: + if (msr_data == 0x0) { + kvm_inject_gp(ctxt->vcpu, 0); + return -1; + } + break; + } + + ctxt->eflags &= ~(EFLG_VM | EFLG_IF | EFLG_RF); + cs.selector = (u16)msr_data; + cs.selector &= ~SELECTOR_RPL_MASK; + ss.selector = cs.selector + 8; + ss.selector &= ~SELECTOR_RPL_MASK; + if (ctxt->mode == X86EMUL_MODE_PROT64 + || is_long_mode(ctxt->vcpu)) { + cs.db = 0; + cs.l = 1; + } + + kvm_x86_ops->set_segment(ctxt->vcpu, &cs, VCPU_SREG_CS); + kvm_x86_ops->set_segment(ctxt->vcpu, &ss, VCPU_SREG_SS); + + kvm_x86_ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_EIP, &msr_data); + c->eip = msr_data; + + kvm_x86_ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_ESP, &msr_data); + c->regs[VCPU_REGS_RSP] = msr_data; + + return 0; +} + +static int +emulate_sysexit(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + struct kvm_segment cs, ss; + u64 msr_data; + int usermode; + + /* inject #UD if LOCK prefix is used */ + if (c->lock_prefix) + return -1; + + /* inject #GP if in real mode or paging is disabled */ + if (ctxt->mode == X86EMUL_MODE_REAL + || !(ctxt->vcpu->arch.cr0 & X86_CR0_PE)) { + kvm_inject_gp(ctxt->vcpu, 0); + return -1; + } + + /* sysexit must be called from CPL 0 */ + if (kvm_x86_ops->get_cpl(ctxt->vcpu) != 0) { + kvm_inject_gp(ctxt->vcpu, 0); + return -1; + } + + setup_syscalls_segments(ctxt, &cs, &ss); + + if ((c->rex_prefix & 0x8) != 0x0) + usermode = X86EMUL_MODE_PROT64; + else + usermode = X86EMUL_MODE_PROT32; + + cs.dpl = 3; + ss.dpl = 3; + kvm_x86_ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_CS, &msr_data); + switch (usermode) { + case X86EMUL_MODE_PROT32: + cs.selector = (u16)(msr_data + 16); + if ((msr_data & 0xfffc) == 0x0) { + kvm_inject_gp(ctxt->vcpu, 0); + return -1; + } + ss.selector = (u16)(msr_data + 24); + break; + case X86EMUL_MODE_PROT64: + cs.selector = (u16)(msr_data + 32); + if (msr_data == 0x0) { + kvm_inject_gp(ctxt->vcpu, 0); + return -1; + } + ss.selector = cs.selector + 8; + cs.db = 0; + cs.l = 1; + break; + } + cs.selector |= SELECTOR_RPL_MASK; + ss.selector |= SELECTOR_RPL_MASK; + + kvm_x86_ops->set_segment(ctxt->vcpu, &cs, VCPU_SREG_CS); + kvm_x86_ops->set_segment(ctxt->vcpu, &ss, VCPU_SREG_SS); + + c->eip = ctxt->vcpu->arch.regs[VCPU_REGS_RDX]; + c->regs[VCPU_REGS_RSP] = ctxt->vcpu->arch.regs[VCPU_REGS_RCX]; + + return 0; +} + int x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { @@ -1970,6 +2203,12 @@ twobyte_insn: goto cannot_emulate; } break; + case 0x05: /* syscall */ + if (emulate_syscall(ctxt) == -1) + goto cannot_emulate; + else + goto writeback; + break; case 0x06: emulate_clts(ctxt->vcpu); c->dst.type = OP_NONE; @@ -2036,6 +2275,18 @@ twobyte_insn: rc = X86EMUL_CONTINUE; c->dst.type = OP_NONE; break; + case 0x34: /* sysenter */ + if (emulate_sysenter(ctxt) == -1) + goto cannot_emulate; + else + goto writeback; + break; + case 0x35: /* sysexit */ + if (emulate_sysexit(ctxt) == -1) + goto cannot_emulate; + else + goto writeback; + break; case 0x40 ... 0x4f: /* cmov */ c->dst.val = c->dst.orig_val = c->src.val; if (!test_cc(c->b, ctxt->eflags)) diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 21f68e00524f..82ad523b4901 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -231,7 +231,7 @@ int pit_has_pending_timer(struct kvm_vcpu *vcpu) { struct kvm_pit *pit = vcpu->kvm->arch.vpit; - if (pit && vcpu->vcpu_id == 0 && pit->pit_state.irq_ack) + if (pit && kvm_vcpu_is_bsp(vcpu) && pit->pit_state.irq_ack) return atomic_read(&pit->pit_state.pit_timer.pending); return 0; } @@ -252,7 +252,7 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu) struct kvm_pit *pit = vcpu->kvm->arch.vpit; struct hrtimer *timer; - if (vcpu->vcpu_id != 0 || !pit) + if (!kvm_vcpu_is_bsp(vcpu) || !pit) return; timer = &pit->pit_state.pit_timer.timer; @@ -294,7 +294,7 @@ static void create_pit_timer(struct kvm_kpit_state *ps, u32 val, int is_period) pt->timer.function = kvm_timer_fn; pt->t_ops = &kpit_ops; pt->kvm = ps->pit->kvm; - pt->vcpu_id = 0; + pt->vcpu = pt->kvm->bsp_vcpu; atomic_set(&pt->pending, 0); ps->irq_ack = 1; @@ -332,33 +332,62 @@ static void pit_load_count(struct kvm *kvm, int channel, u32 val) case 1: /* FIXME: enhance mode 4 precision */ case 4: - create_pit_timer(ps, val, 0); + if (!(ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)) { + create_pit_timer(ps, val, 0); + } break; case 2: case 3: - create_pit_timer(ps, val, 1); + if (!(ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)){ + create_pit_timer(ps, val, 1); + } break; default: destroy_pit_timer(&ps->pit_timer); } } -void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val) +void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val, int hpet_legacy_start) +{ + u8 saved_mode; + if (hpet_legacy_start) { + /* save existing mode for later reenablement */ + saved_mode = kvm->arch.vpit->pit_state.channels[0].mode; + kvm->arch.vpit->pit_state.channels[0].mode = 0xff; /* disable timer */ + pit_load_count(kvm, channel, val); + kvm->arch.vpit->pit_state.channels[0].mode = saved_mode; + } else { + pit_load_count(kvm, channel, val); + } +} + +static inline struct kvm_pit *dev_to_pit(struct kvm_io_device *dev) +{ + return container_of(dev, struct kvm_pit, dev); +} + +static inline struct kvm_pit *speaker_to_pit(struct kvm_io_device *dev) { - mutex_lock(&kvm->arch.vpit->pit_state.lock); - pit_load_count(kvm, channel, val); - mutex_unlock(&kvm->arch.vpit->pit_state.lock); + return container_of(dev, struct kvm_pit, speaker_dev); } -static void pit_ioport_write(struct kvm_io_device *this, - gpa_t addr, int len, const void *data) +static inline int pit_in_range(gpa_t addr) { - struct kvm_pit *pit = (struct kvm_pit *)this->private; + return ((addr >= KVM_PIT_BASE_ADDRESS) && + (addr < KVM_PIT_BASE_ADDRESS + KVM_PIT_MEM_LENGTH)); +} + +static int pit_ioport_write(struct kvm_io_device *this, + gpa_t addr, int len, const void *data) +{ + struct kvm_pit *pit = dev_to_pit(this); struct kvm_kpit_state *pit_state = &pit->pit_state; struct kvm *kvm = pit->kvm; int channel, access; struct kvm_kpit_channel_state *s; u32 val = *(u32 *) data; + if (!pit_in_range(addr)) + return -EOPNOTSUPP; val &= 0xff; addr &= KVM_PIT_CHANNEL_MASK; @@ -421,16 +450,19 @@ static void pit_ioport_write(struct kvm_io_device *this, } mutex_unlock(&pit_state->lock); + return 0; } -static void pit_ioport_read(struct kvm_io_device *this, - gpa_t addr, int len, void *data) +static int pit_ioport_read(struct kvm_io_device *this, + gpa_t addr, int len, void *data) { - struct kvm_pit *pit = (struct kvm_pit *)this->private; + struct kvm_pit *pit = dev_to_pit(this); struct kvm_kpit_state *pit_state = &pit->pit_state; struct kvm *kvm = pit->kvm; int ret, count; struct kvm_kpit_channel_state *s; + if (!pit_in_range(addr)) + return -EOPNOTSUPP; addr &= KVM_PIT_CHANNEL_MASK; s = &pit_state->channels[addr]; @@ -485,37 +517,36 @@ static void pit_ioport_read(struct kvm_io_device *this, memcpy(data, (char *)&ret, len); mutex_unlock(&pit_state->lock); + return 0; } -static int pit_in_range(struct kvm_io_device *this, gpa_t addr, - int len, int is_write) -{ - return ((addr >= KVM_PIT_BASE_ADDRESS) && - (addr < KVM_PIT_BASE_ADDRESS + KVM_PIT_MEM_LENGTH)); -} - -static void speaker_ioport_write(struct kvm_io_device *this, - gpa_t addr, int len, const void *data) +static int speaker_ioport_write(struct kvm_io_device *this, + gpa_t addr, int len, const void *data) { - struct kvm_pit *pit = (struct kvm_pit *)this->private; + struct kvm_pit *pit = speaker_to_pit(this); struct kvm_kpit_state *pit_state = &pit->pit_state; struct kvm *kvm = pit->kvm; u32 val = *(u32 *) data; + if (addr != KVM_SPEAKER_BASE_ADDRESS) + return -EOPNOTSUPP; mutex_lock(&pit_state->lock); pit_state->speaker_data_on = (val >> 1) & 1; pit_set_gate(kvm, 2, val & 1); mutex_unlock(&pit_state->lock); + return 0; } -static void speaker_ioport_read(struct kvm_io_device *this, - gpa_t addr, int len, void *data) +static int speaker_ioport_read(struct kvm_io_device *this, + gpa_t addr, int len, void *data) { - struct kvm_pit *pit = (struct kvm_pit *)this->private; + struct kvm_pit *pit = speaker_to_pit(this); struct kvm_kpit_state *pit_state = &pit->pit_state; struct kvm *kvm = pit->kvm; unsigned int refresh_clock; int ret; + if (addr != KVM_SPEAKER_BASE_ADDRESS) + return -EOPNOTSUPP; /* Refresh clock toggles at about 15us. We approximate as 2^14ns. */ refresh_clock = ((unsigned int)ktime_to_ns(ktime_get()) >> 14) & 1; @@ -527,12 +558,7 @@ static void speaker_ioport_read(struct kvm_io_device *this, len = sizeof(ret); memcpy(data, (char *)&ret, len); mutex_unlock(&pit_state->lock); -} - -static int speaker_in_range(struct kvm_io_device *this, gpa_t addr, - int len, int is_write) -{ - return (addr == KVM_SPEAKER_BASE_ADDRESS); + return 0; } void kvm_pit_reset(struct kvm_pit *pit) @@ -541,6 +567,7 @@ void kvm_pit_reset(struct kvm_pit *pit) struct kvm_kpit_channel_state *c; mutex_lock(&pit->pit_state.lock); + pit->pit_state.flags = 0; for (i = 0; i < 3; i++) { c = &pit->pit_state.channels[i]; c->mode = 0xff; @@ -563,10 +590,22 @@ static void pit_mask_notifer(struct kvm_irq_mask_notifier *kimn, bool mask) } } -struct kvm_pit *kvm_create_pit(struct kvm *kvm) +static const struct kvm_io_device_ops pit_dev_ops = { + .read = pit_ioport_read, + .write = pit_ioport_write, +}; + +static const struct kvm_io_device_ops speaker_dev_ops = { + .read = speaker_ioport_read, + .write = speaker_ioport_write, +}; + +/* Caller must have writers lock on slots_lock */ +struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags) { struct kvm_pit *pit; struct kvm_kpit_state *pit_state; + int ret; pit = kzalloc(sizeof(struct kvm_pit), GFP_KERNEL); if (!pit) @@ -582,19 +621,6 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm) mutex_lock(&pit->pit_state.lock); spin_lock_init(&pit->pit_state.inject_lock); - /* Initialize PIO device */ - pit->dev.read = pit_ioport_read; - pit->dev.write = pit_ioport_write; - pit->dev.in_range = pit_in_range; - pit->dev.private = pit; - kvm_io_bus_register_dev(&kvm->pio_bus, &pit->dev); - - pit->speaker_dev.read = speaker_ioport_read; - pit->speaker_dev.write = speaker_ioport_write; - pit->speaker_dev.in_range = speaker_in_range; - pit->speaker_dev.private = pit; - kvm_io_bus_register_dev(&kvm->pio_bus, &pit->speaker_dev); - kvm->arch.vpit = pit; pit->kvm = kvm; @@ -613,7 +639,30 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm) pit->mask_notifier.func = pit_mask_notifer; kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier); + kvm_iodevice_init(&pit->dev, &pit_dev_ops); + ret = __kvm_io_bus_register_dev(&kvm->pio_bus, &pit->dev); + if (ret < 0) + goto fail; + + if (flags & KVM_PIT_SPEAKER_DUMMY) { + kvm_iodevice_init(&pit->speaker_dev, &speaker_dev_ops); + ret = __kvm_io_bus_register_dev(&kvm->pio_bus, + &pit->speaker_dev); + if (ret < 0) + goto fail_unregister; + } + return pit; + +fail_unregister: + __kvm_io_bus_unregister_dev(&kvm->pio_bus, &pit->dev); + +fail: + if (pit->irq_source_id >= 0) + kvm_free_irq_source_id(kvm, pit->irq_source_id); + + kfree(pit); + return NULL; } void kvm_free_pit(struct kvm *kvm) @@ -623,6 +672,8 @@ void kvm_free_pit(struct kvm *kvm) if (kvm->arch.vpit) { kvm_unregister_irq_mask_notifier(kvm, 0, &kvm->arch.vpit->mask_notifier); + kvm_unregister_irq_ack_notifier(kvm, + &kvm->arch.vpit->pit_state.irq_ack_notifier); mutex_lock(&kvm->arch.vpit->pit_state.lock); timer = &kvm->arch.vpit->pit_state.pit_timer.timer; hrtimer_cancel(timer); @@ -637,10 +688,10 @@ static void __inject_pit_timer_intr(struct kvm *kvm) struct kvm_vcpu *vcpu; int i; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->irq_lock); kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1); kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->irq_lock); /* * Provides NMI watchdog support via Virtual Wire mode. @@ -652,11 +703,8 @@ static void __inject_pit_timer_intr(struct kvm *kvm) * VCPU0, and only if its LVT0 is in EXTINT mode. */ if (kvm->arch.vapics_in_nmi_mode > 0) - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - vcpu = kvm->vcpus[i]; - if (vcpu) - kvm_apic_nmi_wd_deliver(vcpu); - } + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_apic_nmi_wd_deliver(vcpu); } void kvm_inject_pit_timer_irqs(struct kvm_vcpu *vcpu) @@ -665,7 +713,7 @@ void kvm_inject_pit_timer_irqs(struct kvm_vcpu *vcpu) struct kvm *kvm = vcpu->kvm; struct kvm_kpit_state *ps; - if (vcpu && pit) { + if (pit) { int inject = 0; ps = &pit->pit_state; diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h index bbd863ff60b7..d4c1c7ffdc09 100644 --- a/arch/x86/kvm/i8254.h +++ b/arch/x86/kvm/i8254.h @@ -21,6 +21,7 @@ struct kvm_kpit_channel_state { struct kvm_kpit_state { struct kvm_kpit_channel_state channels[3]; + u32 flags; struct kvm_timer pit_timer; bool is_periodic; u32 speaker_data_on; @@ -49,8 +50,8 @@ struct kvm_pit { #define KVM_PIT_CHANNEL_MASK 0x3 void kvm_inject_pit_timer_irqs(struct kvm_vcpu *vcpu); -void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val); -struct kvm_pit *kvm_create_pit(struct kvm *kvm); +void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val, int hpet_legacy_start); +struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags); void kvm_free_pit(struct kvm *kvm); void kvm_pit_reset(struct kvm_pit *pit); diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 1ccb50c74f18..01f151682802 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -30,50 +30,24 @@ #include "irq.h" #include <linux/kvm_host.h> - -static void pic_lock(struct kvm_pic *s) - __acquires(&s->lock) -{ - spin_lock(&s->lock); -} - -static void pic_unlock(struct kvm_pic *s) - __releases(&s->lock) -{ - struct kvm *kvm = s->kvm; - unsigned acks = s->pending_acks; - bool wakeup = s->wakeup_needed; - struct kvm_vcpu *vcpu; - - s->pending_acks = 0; - s->wakeup_needed = false; - - spin_unlock(&s->lock); - - while (acks) { - kvm_notify_acked_irq(kvm, SELECT_PIC(__ffs(acks)), - __ffs(acks)); - acks &= acks - 1; - } - - if (wakeup) { - vcpu = s->kvm->vcpus[0]; - if (vcpu) - kvm_vcpu_kick(vcpu); - } -} +#include "trace.h" static void pic_clear_isr(struct kvm_kpic_state *s, int irq) { s->isr &= ~(1 << irq); s->isr_ack |= (1 << irq); + if (s != &s->pics_state->pics[0]) + irq += 8; + kvm_notify_acked_irq(s->pics_state->kvm, SELECT_PIC(irq), irq); } void kvm_pic_clear_isr_ack(struct kvm *kvm) { struct kvm_pic *s = pic_irqchip(kvm); + spin_lock(&s->lock); s->pics[0].isr_ack = 0xff; s->pics[1].isr_ack = 0xff; + spin_unlock(&s->lock); } /* @@ -174,9 +148,9 @@ static void pic_update_irq(struct kvm_pic *s) void kvm_pic_update_irq(struct kvm_pic *s) { - pic_lock(s); + spin_lock(&s->lock); pic_update_irq(s); - pic_unlock(s); + spin_unlock(&s->lock); } int kvm_pic_set_irq(void *opaque, int irq, int level) @@ -184,12 +158,14 @@ int kvm_pic_set_irq(void *opaque, int irq, int level) struct kvm_pic *s = opaque; int ret = -1; - pic_lock(s); + spin_lock(&s->lock); if (irq >= 0 && irq < PIC_NUM_PINS) { ret = pic_set_irq1(&s->pics[irq >> 3], irq & 7, level); pic_update_irq(s); + trace_kvm_pic_set_irq(irq >> 3, irq & 7, s->pics[irq >> 3].elcr, + s->pics[irq >> 3].imr, ret == 0); } - pic_unlock(s); + spin_unlock(&s->lock); return ret; } @@ -217,7 +193,7 @@ int kvm_pic_read_irq(struct kvm *kvm) int irq, irq2, intno; struct kvm_pic *s = pic_irqchip(kvm); - pic_lock(s); + spin_lock(&s->lock); irq = pic_get_irq(&s->pics[0]); if (irq >= 0) { pic_intack(&s->pics[0], irq); @@ -242,8 +218,7 @@ int kvm_pic_read_irq(struct kvm *kvm) intno = s->pics[0].irq_base + irq; } pic_update_irq(s); - pic_unlock(s); - kvm_notify_acked_irq(kvm, SELECT_PIC(irq), irq); + spin_unlock(&s->lock); return intno; } @@ -252,7 +227,7 @@ void kvm_pic_reset(struct kvm_kpic_state *s) { int irq, irqbase, n; struct kvm *kvm = s->pics_state->irq_request_opaque; - struct kvm_vcpu *vcpu0 = kvm->vcpus[0]; + struct kvm_vcpu *vcpu0 = kvm->bsp_vcpu; if (s == &s->pics_state->pics[0]) irqbase = 0; @@ -263,7 +238,7 @@ void kvm_pic_reset(struct kvm_kpic_state *s) if (vcpu0 && kvm_apic_accept_pic_intr(vcpu0)) if (s->irr & (1 << irq) || s->isr & (1 << irq)) { n = irq + irqbase; - s->pics_state->pending_acks |= 1 << n; + kvm_notify_acked_irq(kvm, SELECT_PIC(n), n); } } s->last_irr = 0; @@ -428,8 +403,7 @@ static u32 elcr_ioport_read(void *opaque, u32 addr1) return s->elcr; } -static int picdev_in_range(struct kvm_io_device *this, gpa_t addr, - int len, int is_write) +static int picdev_in_range(gpa_t addr) { switch (addr) { case 0x20: @@ -444,18 +418,25 @@ static int picdev_in_range(struct kvm_io_device *this, gpa_t addr, } } -static void picdev_write(struct kvm_io_device *this, +static inline struct kvm_pic *to_pic(struct kvm_io_device *dev) +{ + return container_of(dev, struct kvm_pic, dev); +} + +static int picdev_write(struct kvm_io_device *this, gpa_t addr, int len, const void *val) { - struct kvm_pic *s = this->private; + struct kvm_pic *s = to_pic(this); unsigned char data = *(unsigned char *)val; + if (!picdev_in_range(addr)) + return -EOPNOTSUPP; if (len != 1) { if (printk_ratelimit()) printk(KERN_ERR "PIC: non byte write\n"); - return; + return 0; } - pic_lock(s); + spin_lock(&s->lock); switch (addr) { case 0x20: case 0x21: @@ -468,21 +449,24 @@ static void picdev_write(struct kvm_io_device *this, elcr_ioport_write(&s->pics[addr & 1], addr, data); break; } - pic_unlock(s); + spin_unlock(&s->lock); + return 0; } -static void picdev_read(struct kvm_io_device *this, - gpa_t addr, int len, void *val) +static int picdev_read(struct kvm_io_device *this, + gpa_t addr, int len, void *val) { - struct kvm_pic *s = this->private; + struct kvm_pic *s = to_pic(this); unsigned char data = 0; + if (!picdev_in_range(addr)) + return -EOPNOTSUPP; if (len != 1) { if (printk_ratelimit()) printk(KERN_ERR "PIC: non byte read\n"); - return; + return 0; } - pic_lock(s); + spin_lock(&s->lock); switch (addr) { case 0x20: case 0x21: @@ -496,7 +480,8 @@ static void picdev_read(struct kvm_io_device *this, break; } *(unsigned char *)val = data; - pic_unlock(s); + spin_unlock(&s->lock); + return 0; } /* @@ -505,20 +490,27 @@ static void picdev_read(struct kvm_io_device *this, static void pic_irq_request(void *opaque, int level) { struct kvm *kvm = opaque; - struct kvm_vcpu *vcpu = kvm->vcpus[0]; + struct kvm_vcpu *vcpu = kvm->bsp_vcpu; struct kvm_pic *s = pic_irqchip(kvm); int irq = pic_get_irq(&s->pics[0]); s->output = level; if (vcpu && level && (s->pics[0].isr_ack & (1 << irq))) { s->pics[0].isr_ack &= ~(1 << irq); - s->wakeup_needed = true; + kvm_vcpu_kick(vcpu); } } +static const struct kvm_io_device_ops picdev_ops = { + .read = picdev_read, + .write = picdev_write, +}; + struct kvm_pic *kvm_create_pic(struct kvm *kvm) { struct kvm_pic *s; + int ret; + s = kzalloc(sizeof(struct kvm_pic), GFP_KERNEL); if (!s) return NULL; @@ -534,10 +526,12 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm) /* * Initialize PIO device */ - s->dev.read = picdev_read; - s->dev.write = picdev_write; - s->dev.in_range = picdev_in_range; - s->dev.private = s; - kvm_io_bus_register_dev(&kvm->pio_bus, &s->dev); + kvm_iodevice_init(&s->dev, &picdev_ops); + ret = kvm_io_bus_register_dev(kvm, &kvm->pio_bus, &s->dev); + if (ret < 0) { + kfree(s); + return NULL; + } + return s; } diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 9f593188129e..7d6058a2fd38 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -63,7 +63,6 @@ struct kvm_kpic_state { struct kvm_pic { spinlock_t lock; - bool wakeup_needed; unsigned pending_acks; struct kvm *kvm; struct kvm_kpic_state pics[2]; /* 0 is master pic, 1 is slave pic */ diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 1ff819dce7d3..7bcc5b6a4403 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -29,4 +29,13 @@ static inline void kvm_rip_write(struct kvm_vcpu *vcpu, unsigned long val) kvm_register_write(vcpu, VCPU_REGS_RIP, val); } +static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index) +{ + if (!test_bit(VCPU_EXREG_PDPTR, + (unsigned long *)&vcpu->arch.regs_avail)) + kvm_x86_ops->cache_reg(vcpu, VCPU_EXREG_PDPTR); + + return vcpu->arch.pdptrs[index]; +} + #endif diff --git a/arch/x86/kvm/kvm_svm.h b/arch/x86/kvm/kvm_svm.h deleted file mode 100644 index ed66e4c078dc..000000000000 --- a/arch/x86/kvm/kvm_svm.h +++ /dev/null @@ -1,51 +0,0 @@ -#ifndef __KVM_SVM_H -#define __KVM_SVM_H - -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/list.h> -#include <linux/kvm_host.h> -#include <asm/msr.h> - -#include <asm/svm.h> - -static const u32 host_save_user_msrs[] = { -#ifdef CONFIG_X86_64 - MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE, - MSR_FS_BASE, -#endif - MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, -}; - -#define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs) - -struct kvm_vcpu; - -struct vcpu_svm { - struct kvm_vcpu vcpu; - struct vmcb *vmcb; - unsigned long vmcb_pa; - struct svm_cpu_data *svm_data; - uint64_t asid_generation; - - u64 next_rip; - - u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS]; - u64 host_gs_base; - unsigned long host_cr2; - - u32 *msrpm; - struct vmcb *hsave; - u64 hsave_msr; - - u64 nested_vmcb; - - /* These are the merged vectors */ - u32 *nested_msrpm; - - /* gpa pointers to the real vectors */ - u64 nested_vmcb_msrpm; -}; - -#endif - diff --git a/arch/x86/kvm/kvm_timer.h b/arch/x86/kvm/kvm_timer.h index 26bd6ba74e1c..55c7524dda54 100644 --- a/arch/x86/kvm/kvm_timer.h +++ b/arch/x86/kvm/kvm_timer.h @@ -6,7 +6,7 @@ struct kvm_timer { bool reinject; struct kvm_timer_ops *t_ops; struct kvm *kvm; - int vcpu_id; + struct kvm_vcpu *vcpu; }; struct kvm_timer_ops { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index ae99d83f81a3..1ae5ceba7eb2 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -32,8 +32,11 @@ #include <asm/current.h> #include <asm/apicdef.h> #include <asm/atomic.h> +#include <asm/apicdef.h> #include "kvm_cache_regs.h" #include "irq.h" +#include "trace.h" +#include "x86.h" #ifndef CONFIG_X86_64 #define mod_64(x, y) ((x) - (y) * div64_u64(x, y)) @@ -141,6 +144,26 @@ static inline int apic_lvt_nmi_mode(u32 lvt_val) return (lvt_val & (APIC_MODE_MASK | APIC_LVT_MASKED)) == APIC_DM_NMI; } +void kvm_apic_set_version(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + struct kvm_cpuid_entry2 *feat; + u32 v = APIC_VERSION; + + if (!irqchip_in_kernel(vcpu->kvm)) + return; + + feat = kvm_find_cpuid_entry(apic->vcpu, 0x1, 0); + if (feat && (feat->ecx & (1 << (X86_FEATURE_X2APIC & 31)))) + v |= APIC_LVR_DIRECTED_EOI; + apic_set_reg(apic, APIC_LVR, v); +} + +static inline int apic_x2apic_mode(struct kvm_lapic *apic) +{ + return apic->vcpu->arch.apic_base & X2APIC_ENABLE; +} + static unsigned int apic_lvt_mask[APIC_LVT_NUM] = { LVT_MASK | APIC_LVT_TIMER_PERIODIC, /* LVTT */ LVT_MASK | APIC_MODE_MASK, /* LVTTHMR */ @@ -165,36 +188,52 @@ static int find_highest_vector(void *bitmap) static inline int apic_test_and_set_irr(int vec, struct kvm_lapic *apic) { + apic->irr_pending = true; return apic_test_and_set_vector(vec, apic->regs + APIC_IRR); } -static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) +static inline int apic_search_irr(struct kvm_lapic *apic) { - apic_clear_vector(vec, apic->regs + APIC_IRR); + return find_highest_vector(apic->regs + APIC_IRR); } static inline int apic_find_highest_irr(struct kvm_lapic *apic) { int result; - result = find_highest_vector(apic->regs + APIC_IRR); + if (!apic->irr_pending) + return -1; + + result = apic_search_irr(apic); ASSERT(result == -1 || result >= 16); return result; } +static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) +{ + apic->irr_pending = false; + apic_clear_vector(vec, apic->regs + APIC_IRR); + if (apic_search_irr(apic) != -1) + apic->irr_pending = true; +} + int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; int highest_irr; + /* This may race with setting of irr in __apic_accept_irq() and + * value returned may be wrong, but kvm_vcpu_kick() in __apic_accept_irq + * will cause vmexit immediately and the value will be recalculated + * on the next vmentry. + */ if (!apic) return 0; highest_irr = apic_find_highest_irr(apic); return highest_irr; } -EXPORT_SYMBOL_GPL(kvm_lapic_find_highest_irr); static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, int vector, int level, int trig_mode); @@ -251,7 +290,12 @@ int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest) int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda) { int result = 0; - u8 logical_id; + u32 logical_id; + + if (apic_x2apic_mode(apic)) { + logical_id = apic_get_reg(apic, APIC_LDR); + return logical_id & mda; + } logical_id = GET_APIC_LOGICAL_ID(apic_get_reg(apic, APIC_LDR)); @@ -331,6 +375,8 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, break; result = !apic_test_and_set_irr(vector, apic); + trace_kvm_apic_accept_irq(vcpu->vcpu_id, delivery_mode, + trig_mode, vector, !result); if (!result) { if (trig_mode) apic_debug("level trig mode repeatedly for " @@ -425,7 +471,11 @@ static void apic_set_eoi(struct kvm_lapic *apic) trigger_mode = IOAPIC_LEVEL_TRIG; else trigger_mode = IOAPIC_EDGE_TRIG; - kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode); + if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI)) { + mutex_lock(&apic->vcpu->kvm->irq_lock); + kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode); + mutex_unlock(&apic->vcpu->kvm->irq_lock); + } } static void apic_send_ipi(struct kvm_lapic *apic) @@ -440,7 +490,12 @@ static void apic_send_ipi(struct kvm_lapic *apic) irq.level = icr_low & APIC_INT_ASSERT; irq.trig_mode = icr_low & APIC_INT_LEVELTRIG; irq.shorthand = icr_low & APIC_SHORT_MASK; - irq.dest_id = GET_APIC_DEST_FIELD(icr_high); + if (apic_x2apic_mode(apic)) + irq.dest_id = icr_high; + else + irq.dest_id = GET_APIC_DEST_FIELD(icr_high); + + trace_kvm_apic_ipi(icr_low, irq.dest_id); apic_debug("icr_high 0x%x, icr_low 0x%x, " "short_hand 0x%x, dest 0x%x, trig_mode 0x%x, level 0x%x, " @@ -449,7 +504,9 @@ static void apic_send_ipi(struct kvm_lapic *apic) irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode, irq.vector); + mutex_lock(&apic->vcpu->kvm->irq_lock); kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq); + mutex_unlock(&apic->vcpu->kvm->irq_lock); } static u32 apic_get_tmcct(struct kvm_lapic *apic) @@ -495,12 +552,16 @@ static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset) { u32 val = 0; - KVMTRACE_1D(APIC_ACCESS, apic->vcpu, (u32)offset, handler); - if (offset >= LAPIC_MMIO_LENGTH) return 0; switch (offset) { + case APIC_ID: + if (apic_x2apic_mode(apic)) + val = kvm_apic_id(apic); + else + val = kvm_apic_id(apic) << 24; + break; case APIC_ARBPRI: printk(KERN_WARNING "Access APIC ARBPRI register " "which is for P6\n"); @@ -522,21 +583,35 @@ static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset) return val; } -static void apic_mmio_read(struct kvm_io_device *this, - gpa_t address, int len, void *data) +static inline struct kvm_lapic *to_lapic(struct kvm_io_device *dev) +{ + return container_of(dev, struct kvm_lapic, dev); +} + +static int apic_reg_read(struct kvm_lapic *apic, u32 offset, int len, + void *data) { - struct kvm_lapic *apic = (struct kvm_lapic *)this->private; - unsigned int offset = address - apic->base_address; unsigned char alignment = offset & 0xf; u32 result; + /* this bitmask has a bit cleared for each reserver register */ + static const u64 rmask = 0x43ff01ffffffe70cULL; if ((alignment + len) > 4) { - printk(KERN_ERR "KVM_APIC_READ: alignment error %lx %d", - (unsigned long)address, len); - return; + apic_debug("KVM_APIC_READ: alignment error %x %d\n", + offset, len); + return 1; } + + if (offset > 0x3f0 || !(rmask & (1ULL << (offset >> 4)))) { + apic_debug("KVM_APIC_READ: read reserved register %x\n", + offset); + return 1; + } + result = __apic_read(apic, offset & ~0xf); + trace_kvm_apic_read(offset, result); + switch (len) { case 1: case 2: @@ -548,6 +623,28 @@ static void apic_mmio_read(struct kvm_io_device *this, "should be 1,2, or 4 instead\n", len); break; } + return 0; +} + +static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr) +{ + return apic_hw_enabled(apic) && + addr >= apic->base_address && + addr < apic->base_address + LAPIC_MMIO_LENGTH; +} + +static int apic_mmio_read(struct kvm_io_device *this, + gpa_t address, int len, void *data) +{ + struct kvm_lapic *apic = to_lapic(this); + u32 offset = address - apic->base_address; + + if (!apic_mmio_in_range(apic, address)) + return -EOPNOTSUPP; + + apic_reg_read(apic, offset, len, data); + + return 0; } static void update_divide_count(struct kvm_lapic *apic) @@ -573,6 +670,15 @@ static void start_apic_timer(struct kvm_lapic *apic) if (!apic->lapic_timer.period) return; + /* + * Do not allow the guest to program periodic timers with small + * interval, since the hrtimers are not throttled by the host + * scheduler. + */ + if (apic_lvtt_period(apic)) { + if (apic->lapic_timer.period < NSEC_PER_MSEC/2) + apic->lapic_timer.period = NSEC_PER_MSEC/2; + } hrtimer_start(&apic->lapic_timer.timer, ktime_add_ns(now, apic->lapic_timer.period), @@ -603,40 +709,18 @@ static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val) apic->vcpu->kvm->arch.vapics_in_nmi_mode--; } -static void apic_mmio_write(struct kvm_io_device *this, - gpa_t address, int len, const void *data) +static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) { - struct kvm_lapic *apic = (struct kvm_lapic *)this->private; - unsigned int offset = address - apic->base_address; - unsigned char alignment = offset & 0xf; - u32 val; - - /* - * APIC register must be aligned on 128-bits boundary. - * 32/64/128 bits registers must be accessed thru 32 bits. - * Refer SDM 8.4.1 - */ - if (len != 4 || alignment) { - /* Don't shout loud, $infamous_os would cause only noise. */ - apic_debug("apic write: bad size=%d %lx\n", - len, (long)address); - return; - } - - val = *(u32 *) data; - - /* too common printing */ - if (offset != APIC_EOI) - apic_debug("%s: offset 0x%x with length 0x%x, and value is " - "0x%x\n", __func__, offset, len, val); - - offset &= 0xff0; + int ret = 0; - KVMTRACE_1D(APIC_ACCESS, apic->vcpu, (u32)offset, handler); + trace_kvm_apic_write(reg, val); - switch (offset) { + switch (reg) { case APIC_ID: /* Local APIC ID */ - apic_set_reg(apic, APIC_ID, val); + if (!apic_x2apic_mode(apic)) + apic_set_reg(apic, APIC_ID, val); + else + ret = 1; break; case APIC_TASKPRI: @@ -649,15 +733,24 @@ static void apic_mmio_write(struct kvm_io_device *this, break; case APIC_LDR: - apic_set_reg(apic, APIC_LDR, val & APIC_LDR_MASK); + if (!apic_x2apic_mode(apic)) + apic_set_reg(apic, APIC_LDR, val & APIC_LDR_MASK); + else + ret = 1; break; case APIC_DFR: - apic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF); + if (!apic_x2apic_mode(apic)) + apic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF); + else + ret = 1; break; - case APIC_SPIV: - apic_set_reg(apic, APIC_SPIV, val & 0x3ff); + case APIC_SPIV: { + u32 mask = 0x3ff; + if (apic_get_reg(apic, APIC_LVR) & APIC_LVR_DIRECTED_EOI) + mask |= APIC_SPIV_DIRECTED_EOI; + apic_set_reg(apic, APIC_SPIV, val & mask); if (!(val & APIC_SPIV_APIC_ENABLED)) { int i; u32 lvt_val; @@ -672,7 +765,7 @@ static void apic_mmio_write(struct kvm_io_device *this, } break; - + } case APIC_ICR: /* No delay here, so we always clear the pending bit */ apic_set_reg(apic, APIC_ICR, val & ~(1 << 12)); @@ -680,7 +773,9 @@ static void apic_mmio_write(struct kvm_io_device *this, break; case APIC_ICR2: - apic_set_reg(apic, APIC_ICR2, val & 0xff000000); + if (!apic_x2apic_mode(apic)) + val &= 0xff000000; + apic_set_reg(apic, APIC_ICR2, val); break; case APIC_LVT0: @@ -694,8 +789,8 @@ static void apic_mmio_write(struct kvm_io_device *this, if (!apic_sw_enabled(apic)) val |= APIC_LVT_MASKED; - val &= apic_lvt_mask[(offset - APIC_LVTT) >> 4]; - apic_set_reg(apic, offset, val); + val &= apic_lvt_mask[(reg - APIC_LVTT) >> 4]; + apic_set_reg(apic, reg, val); break; @@ -703,7 +798,7 @@ static void apic_mmio_write(struct kvm_io_device *this, hrtimer_cancel(&apic->lapic_timer.timer); apic_set_reg(apic, APIC_TMICT, val); start_apic_timer(apic); - return; + break; case APIC_TDCR: if (val & 4) @@ -712,27 +807,59 @@ static void apic_mmio_write(struct kvm_io_device *this, update_divide_count(apic); break; + case APIC_ESR: + if (apic_x2apic_mode(apic) && val != 0) { + printk(KERN_ERR "KVM_WRITE:ESR not zero %x\n", val); + ret = 1; + } + break; + + case APIC_SELF_IPI: + if (apic_x2apic_mode(apic)) { + apic_reg_write(apic, APIC_ICR, 0x40000 | (val & 0xff)); + } else + ret = 1; + break; default: - apic_debug("Local APIC Write to read-only register %x\n", - offset); + ret = 1; break; } - + if (ret) + apic_debug("Local APIC Write to read-only register %x\n", reg); + return ret; } -static int apic_mmio_range(struct kvm_io_device *this, gpa_t addr, - int len, int size) +static int apic_mmio_write(struct kvm_io_device *this, + gpa_t address, int len, const void *data) { - struct kvm_lapic *apic = (struct kvm_lapic *)this->private; - int ret = 0; + struct kvm_lapic *apic = to_lapic(this); + unsigned int offset = address - apic->base_address; + u32 val; + if (!apic_mmio_in_range(apic, address)) + return -EOPNOTSUPP; - if (apic_hw_enabled(apic) && - (addr >= apic->base_address) && - (addr < (apic->base_address + LAPIC_MMIO_LENGTH))) - ret = 1; + /* + * APIC register must be aligned on 128-bits boundary. + * 32/64/128 bits registers must be accessed thru 32 bits. + * Refer SDM 8.4.1 + */ + if (len != 4 || (offset & 0xf)) { + /* Don't shout loud, $infamous_os would cause only noise. */ + apic_debug("apic write: bad size=%d %lx\n", len, (long)address); + return 0; + } - return ret; + val = *(u32*)data; + + /* too common printing */ + if (offset != APIC_EOI) + apic_debug("%s: offset 0x%x with length 0x%x, and value is " + "0x%x\n", __func__, offset, len, val); + + apic_reg_write(apic, offset & 0xff0, val); + + return 0; } void kvm_free_lapic(struct kvm_vcpu *vcpu) @@ -763,7 +890,6 @@ void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8) apic_set_tpr(apic, ((cr8 & 0x0f) << 4) | (apic_get_reg(apic, APIC_TASKPRI) & 4)); } -EXPORT_SYMBOL_GPL(kvm_lapic_set_tpr); u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu) { @@ -776,7 +902,6 @@ u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu) return (tpr & 0xf0) >> 4; } -EXPORT_SYMBOL_GPL(kvm_lapic_get_cr8); void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) { @@ -787,10 +912,16 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) vcpu->arch.apic_base = value; return; } - if (apic->vcpu->vcpu_id) + + if (!kvm_vcpu_is_bsp(apic->vcpu)) value &= ~MSR_IA32_APICBASE_BSP; vcpu->arch.apic_base = value; + if (apic_x2apic_mode(apic)) { + u32 id = kvm_apic_id(apic); + u32 ldr = ((id & ~0xf) << 16) | (1 << (id & 0xf)); + apic_set_reg(apic, APIC_LDR, ldr); + } apic->base_address = apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_BASE; @@ -800,12 +931,6 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) } -u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.apic_base; -} -EXPORT_SYMBOL_GPL(kvm_lapic_get_base); - void kvm_lapic_reset(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic; @@ -821,7 +946,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu) hrtimer_cancel(&apic->lapic_timer.timer); apic_set_reg(apic, APIC_ID, vcpu->vcpu_id << 24); - apic_set_reg(apic, APIC_LVR, APIC_VERSION); + kvm_apic_set_version(apic->vcpu); for (i = 0; i < APIC_LVT_NUM; i++) apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED); @@ -842,9 +967,10 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu) apic_set_reg(apic, APIC_ISR + 0x10 * i, 0); apic_set_reg(apic, APIC_TMR + 0x10 * i, 0); } + apic->irr_pending = false; update_divide_count(apic); atomic_set(&apic->lapic_timer.pending, 0); - if (vcpu->vcpu_id == 0) + if (kvm_vcpu_is_bsp(vcpu)) vcpu->arch.apic_base |= MSR_IA32_APICBASE_BSP; apic_update_ppr(apic); @@ -855,7 +981,6 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu) vcpu, kvm_apic_id(apic), vcpu->arch.apic_base, apic->base_address); } -EXPORT_SYMBOL_GPL(kvm_lapic_reset); bool kvm_apic_present(struct kvm_vcpu *vcpu) { @@ -866,7 +991,6 @@ int kvm_lapic_enabled(struct kvm_vcpu *vcpu) { return kvm_apic_present(vcpu) && apic_sw_enabled(vcpu->arch.apic); } -EXPORT_SYMBOL_GPL(kvm_lapic_enabled); /* *---------------------------------------------------------------------- @@ -917,6 +1041,11 @@ static struct kvm_timer_ops lapic_timer_ops = { .is_periodic = lapic_is_periodic, }; +static const struct kvm_io_device_ops apic_mmio_ops = { + .read = apic_mmio_read, + .write = apic_mmio_write, +}; + int kvm_create_lapic(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic; @@ -945,16 +1074,13 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) apic->lapic_timer.timer.function = kvm_timer_fn; apic->lapic_timer.t_ops = &lapic_timer_ops; apic->lapic_timer.kvm = vcpu->kvm; - apic->lapic_timer.vcpu_id = vcpu->vcpu_id; + apic->lapic_timer.vcpu = vcpu; apic->base_address = APIC_DEFAULT_PHYS_BASE; vcpu->arch.apic_base = APIC_DEFAULT_PHYS_BASE; kvm_lapic_reset(vcpu); - apic->dev.read = apic_mmio_read; - apic->dev.write = apic_mmio_write; - apic->dev.in_range = apic_mmio_range; - apic->dev.private = apic; + kvm_iodevice_init(&apic->dev, &apic_mmio_ops); return 0; nomem_free_apic: @@ -962,7 +1088,6 @@ nomem_free_apic: nomem: return -ENOMEM; } -EXPORT_SYMBOL_GPL(kvm_create_lapic); int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) { @@ -985,7 +1110,7 @@ int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu) u32 lvt0 = apic_get_reg(vcpu->arch.apic, APIC_LVT0); int r = 0; - if (vcpu->vcpu_id == 0) { + if (kvm_vcpu_is_bsp(vcpu)) { if (!apic_hw_enabled(vcpu->arch.apic)) r = 1; if ((lvt0 & APIC_LVT_MASKED) == 0 && @@ -1025,7 +1150,8 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu) apic->base_address = vcpu->arch.apic_base & MSR_IA32_APICBASE_BASE; - apic_set_reg(apic, APIC_LVR, APIC_VERSION); + kvm_apic_set_version(vcpu); + apic_update_ppr(apic); hrtimer_cancel(&apic->lapic_timer.timer); update_divide_count(apic); @@ -1092,3 +1218,35 @@ void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr) vcpu->arch.apic->vapic_addr = vapic_addr; } + +int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + u32 reg = (msr - APIC_BASE_MSR) << 4; + + if (!irqchip_in_kernel(vcpu->kvm) || !apic_x2apic_mode(apic)) + return 1; + + /* if this is ICR write vector before command */ + if (msr == 0x830) + apic_reg_write(apic, APIC_ICR2, (u32)(data >> 32)); + return apic_reg_write(apic, reg, (u32)data); +} + +int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + u32 reg = (msr - APIC_BASE_MSR) << 4, low, high = 0; + + if (!irqchip_in_kernel(vcpu->kvm) || !apic_x2apic_mode(apic)) + return 1; + + if (apic_reg_read(apic, reg, 4, &low)) + return 1; + if (msr == 0x830) + apic_reg_read(apic, APIC_ICR2, 4, &high); + + *data = (((u64)high) << 32) | low; + + return 0; +} diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index a587f8349c46..40010b09c4aa 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -12,6 +12,7 @@ struct kvm_lapic { struct kvm_timer lapic_timer; u32 divide_count; struct kvm_vcpu *vcpu; + bool irr_pending; struct page *regs_page; void *regs; gpa_t vapic_addr; @@ -28,6 +29,7 @@ u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu); void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8); void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value); u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu); +void kvm_apic_set_version(struct kvm_vcpu *vcpu); int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest); int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda); @@ -44,4 +46,6 @@ void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr); void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu); void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu); +int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data); +int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data); #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 0ef5bb2b4043..eca41ae9f453 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -18,6 +18,7 @@ */ #include "mmu.h" +#include "kvm_cache_regs.h" #include <linux/kvm_host.h> #include <linux/types.h> @@ -107,6 +108,9 @@ module_param(oos_shadow, bool, 0644); #define PT32_LEVEL_MASK(level) \ (((1ULL << PT32_LEVEL_BITS) - 1) << PT32_LEVEL_SHIFT(level)) +#define PT32_LVL_OFFSET_MASK(level) \ + (PT32_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \ + * PT32_LEVEL_BITS))) - 1)) #define PT32_INDEX(address, level)\ (((address) >> PT32_LEVEL_SHIFT(level)) & ((1 << PT32_LEVEL_BITS) - 1)) @@ -115,10 +119,19 @@ module_param(oos_shadow, bool, 0644); #define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1)) #define PT64_DIR_BASE_ADDR_MASK \ (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + PT64_LEVEL_BITS)) - 1)) +#define PT64_LVL_ADDR_MASK(level) \ + (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \ + * PT64_LEVEL_BITS))) - 1)) +#define PT64_LVL_OFFSET_MASK(level) \ + (PT64_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \ + * PT64_LEVEL_BITS))) - 1)) #define PT32_BASE_ADDR_MASK PAGE_MASK #define PT32_DIR_BASE_ADDR_MASK \ (PAGE_MASK & ~((1ULL << (PAGE_SHIFT + PT32_LEVEL_BITS)) - 1)) +#define PT32_LVL_ADDR_MASK(level) \ + (PAGE_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \ + * PT32_LEVEL_BITS))) - 1)) #define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | PT_USER_MASK \ | PT64_NX_MASK) @@ -129,6 +142,7 @@ module_param(oos_shadow, bool, 0644); #define PFERR_RSVD_MASK (1U << 3) #define PFERR_FETCH_MASK (1U << 4) +#define PT_PDPE_LEVEL 3 #define PT_DIRECTORY_LEVEL 2 #define PT_PAGE_TABLE_LEVEL 1 @@ -139,10 +153,13 @@ module_param(oos_shadow, bool, 0644); #define ACC_USER_MASK PT_USER_MASK #define ACC_ALL (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK) +#define CREATE_TRACE_POINTS +#include "mmutrace.h" + #define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level) struct kvm_rmap_desc { - u64 *shadow_ptes[RMAP_EXT]; + u64 *sptes[RMAP_EXT]; struct kvm_rmap_desc *more; }; @@ -239,16 +256,25 @@ static int is_writeble_pte(unsigned long pte) return pte & PT_WRITABLE_MASK; } -static int is_dirty_pte(unsigned long pte) +static int is_dirty_gpte(unsigned long pte) { - return pte & shadow_dirty_mask; + return pte & PT_DIRTY_MASK; } -static int is_rmap_pte(u64 pte) +static int is_rmap_spte(u64 pte) { return is_shadow_present_pte(pte); } +static int is_last_spte(u64 pte, int level) +{ + if (level == PT_PAGE_TABLE_LEVEL) + return 1; + if (is_large_pte(pte)) + return 1; + return 0; +} + static pfn_t spte_to_pfn(u64 pte) { return (pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; @@ -261,7 +287,7 @@ static gfn_t pse36_gfn_delta(u32 gpte) return (gpte & PT32_DIR_PSE36_MASK) << shift; } -static void set_shadow_pte(u64 *sptep, u64 spte) +static void __set_spte(u64 *sptep, u64 spte) { #ifdef CONFIG_X86_64 set_64bit((unsigned long *)sptep, spte); @@ -380,37 +406,52 @@ static void mmu_free_rmap_desc(struct kvm_rmap_desc *rd) * Return the pointer to the largepage write count for a given * gfn, handling slots that are not large page aligned. */ -static int *slot_largepage_idx(gfn_t gfn, struct kvm_memory_slot *slot) +static int *slot_largepage_idx(gfn_t gfn, + struct kvm_memory_slot *slot, + int level) { unsigned long idx; - idx = (gfn / KVM_PAGES_PER_HPAGE) - - (slot->base_gfn / KVM_PAGES_PER_HPAGE); - return &slot->lpage_info[idx].write_count; + idx = (gfn / KVM_PAGES_PER_HPAGE(level)) - + (slot->base_gfn / KVM_PAGES_PER_HPAGE(level)); + return &slot->lpage_info[level - 2][idx].write_count; } static void account_shadowed(struct kvm *kvm, gfn_t gfn) { + struct kvm_memory_slot *slot; int *write_count; + int i; gfn = unalias_gfn(kvm, gfn); - write_count = slot_largepage_idx(gfn, - gfn_to_memslot_unaliased(kvm, gfn)); - *write_count += 1; + + slot = gfn_to_memslot_unaliased(kvm, gfn); + for (i = PT_DIRECTORY_LEVEL; + i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { + write_count = slot_largepage_idx(gfn, slot, i); + *write_count += 1; + } } static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn) { + struct kvm_memory_slot *slot; int *write_count; + int i; gfn = unalias_gfn(kvm, gfn); - write_count = slot_largepage_idx(gfn, - gfn_to_memslot_unaliased(kvm, gfn)); - *write_count -= 1; - WARN_ON(*write_count < 0); + for (i = PT_DIRECTORY_LEVEL; + i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { + slot = gfn_to_memslot_unaliased(kvm, gfn); + write_count = slot_largepage_idx(gfn, slot, i); + *write_count -= 1; + WARN_ON(*write_count < 0); + } } -static int has_wrprotected_page(struct kvm *kvm, gfn_t gfn) +static int has_wrprotected_page(struct kvm *kvm, + gfn_t gfn, + int level) { struct kvm_memory_slot *slot; int *largepage_idx; @@ -418,47 +459,67 @@ static int has_wrprotected_page(struct kvm *kvm, gfn_t gfn) gfn = unalias_gfn(kvm, gfn); slot = gfn_to_memslot_unaliased(kvm, gfn); if (slot) { - largepage_idx = slot_largepage_idx(gfn, slot); + largepage_idx = slot_largepage_idx(gfn, slot, level); return *largepage_idx; } return 1; } -static int host_largepage_backed(struct kvm *kvm, gfn_t gfn) +static int host_mapping_level(struct kvm *kvm, gfn_t gfn) { + unsigned long page_size = PAGE_SIZE; struct vm_area_struct *vma; unsigned long addr; - int ret = 0; + int i, ret = 0; addr = gfn_to_hva(kvm, gfn); if (kvm_is_error_hva(addr)) - return ret; + return page_size; down_read(¤t->mm->mmap_sem); vma = find_vma(current->mm, addr); - if (vma && is_vm_hugetlb_page(vma)) - ret = 1; + if (!vma) + goto out; + + page_size = vma_kernel_pagesize(vma); + +out: up_read(¤t->mm->mmap_sem); + for (i = PT_PAGE_TABLE_LEVEL; + i < (PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES); ++i) { + if (page_size >= KVM_HPAGE_SIZE(i)) + ret = i; + else + break; + } + return ret; } -static int is_largepage_backed(struct kvm_vcpu *vcpu, gfn_t large_gfn) +static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn) { struct kvm_memory_slot *slot; - - if (has_wrprotected_page(vcpu->kvm, large_gfn)) - return 0; - - if (!host_largepage_backed(vcpu->kvm, large_gfn)) - return 0; + int host_level; + int level = PT_PAGE_TABLE_LEVEL; slot = gfn_to_memslot(vcpu->kvm, large_gfn); if (slot && slot->dirty_bitmap) - return 0; + return PT_PAGE_TABLE_LEVEL; - return 1; + host_level = host_mapping_level(vcpu->kvm, large_gfn); + + if (host_level == PT_PAGE_TABLE_LEVEL) + return host_level; + + for (level = PT_DIRECTORY_LEVEL; level <= host_level; ++level) { + + if (has_wrprotected_page(vcpu->kvm, large_gfn, level)) + break; + } + + return level - 1; } /* @@ -466,19 +527,19 @@ static int is_largepage_backed(struct kvm_vcpu *vcpu, gfn_t large_gfn) * Note: gfn must be unaliased before this function get called */ -static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int lpage) +static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level) { struct kvm_memory_slot *slot; unsigned long idx; slot = gfn_to_memslot(kvm, gfn); - if (!lpage) + if (likely(level == PT_PAGE_TABLE_LEVEL)) return &slot->rmap[gfn - slot->base_gfn]; - idx = (gfn / KVM_PAGES_PER_HPAGE) - - (slot->base_gfn / KVM_PAGES_PER_HPAGE); + idx = (gfn / KVM_PAGES_PER_HPAGE(level)) - + (slot->base_gfn / KVM_PAGES_PER_HPAGE(level)); - return &slot->lpage_info[idx].rmap_pde; + return &slot->lpage_info[level - 2][idx].rmap_pde; } /* @@ -494,42 +555,42 @@ static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int lpage) * the spte was not added. * */ -static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn, int lpage) +static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) { struct kvm_mmu_page *sp; struct kvm_rmap_desc *desc; unsigned long *rmapp; int i, count = 0; - if (!is_rmap_pte(*spte)) + if (!is_rmap_spte(*spte)) return count; gfn = unalias_gfn(vcpu->kvm, gfn); sp = page_header(__pa(spte)); sp->gfns[spte - sp->spt] = gfn; - rmapp = gfn_to_rmap(vcpu->kvm, gfn, lpage); + rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level); if (!*rmapp) { rmap_printk("rmap_add: %p %llx 0->1\n", spte, *spte); *rmapp = (unsigned long)spte; } else if (!(*rmapp & 1)) { rmap_printk("rmap_add: %p %llx 1->many\n", spte, *spte); desc = mmu_alloc_rmap_desc(vcpu); - desc->shadow_ptes[0] = (u64 *)*rmapp; - desc->shadow_ptes[1] = spte; + desc->sptes[0] = (u64 *)*rmapp; + desc->sptes[1] = spte; *rmapp = (unsigned long)desc | 1; } else { rmap_printk("rmap_add: %p %llx many->many\n", spte, *spte); desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul); - while (desc->shadow_ptes[RMAP_EXT-1] && desc->more) { + while (desc->sptes[RMAP_EXT-1] && desc->more) { desc = desc->more; count += RMAP_EXT; } - if (desc->shadow_ptes[RMAP_EXT-1]) { + if (desc->sptes[RMAP_EXT-1]) { desc->more = mmu_alloc_rmap_desc(vcpu); desc = desc->more; } - for (i = 0; desc->shadow_ptes[i]; ++i) + for (i = 0; desc->sptes[i]; ++i) ; - desc->shadow_ptes[i] = spte; + desc->sptes[i] = spte; } return count; } @@ -541,14 +602,14 @@ static void rmap_desc_remove_entry(unsigned long *rmapp, { int j; - for (j = RMAP_EXT - 1; !desc->shadow_ptes[j] && j > i; --j) + for (j = RMAP_EXT - 1; !desc->sptes[j] && j > i; --j) ; - desc->shadow_ptes[i] = desc->shadow_ptes[j]; - desc->shadow_ptes[j] = NULL; + desc->sptes[i] = desc->sptes[j]; + desc->sptes[j] = NULL; if (j != 0) return; if (!prev_desc && !desc->more) - *rmapp = (unsigned long)desc->shadow_ptes[0]; + *rmapp = (unsigned long)desc->sptes[0]; else if (prev_desc) prev_desc->more = desc->more; @@ -566,7 +627,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) unsigned long *rmapp; int i; - if (!is_rmap_pte(*spte)) + if (!is_rmap_spte(*spte)) return; sp = page_header(__pa(spte)); pfn = spte_to_pfn(*spte); @@ -576,7 +637,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) kvm_release_pfn_dirty(pfn); else kvm_release_pfn_clean(pfn); - rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt], is_large_pte(*spte)); + rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt], sp->role.level); if (!*rmapp) { printk(KERN_ERR "rmap_remove: %p %llx 0->BUG\n", spte, *spte); BUG(); @@ -593,8 +654,8 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul); prev_desc = NULL; while (desc) { - for (i = 0; i < RMAP_EXT && desc->shadow_ptes[i]; ++i) - if (desc->shadow_ptes[i] == spte) { + for (i = 0; i < RMAP_EXT && desc->sptes[i]; ++i) + if (desc->sptes[i] == spte) { rmap_desc_remove_entry(rmapp, desc, i, prev_desc); @@ -625,10 +686,10 @@ static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte) prev_desc = NULL; prev_spte = NULL; while (desc) { - for (i = 0; i < RMAP_EXT && desc->shadow_ptes[i]; ++i) { + for (i = 0; i < RMAP_EXT && desc->sptes[i]; ++i) { if (prev_spte == spte) - return desc->shadow_ptes[i]; - prev_spte = desc->shadow_ptes[i]; + return desc->sptes[i]; + prev_spte = desc->sptes[i]; } desc = desc->more; } @@ -639,10 +700,10 @@ static int rmap_write_protect(struct kvm *kvm, u64 gfn) { unsigned long *rmapp; u64 *spte; - int write_protected = 0; + int i, write_protected = 0; gfn = unalias_gfn(kvm, gfn); - rmapp = gfn_to_rmap(kvm, gfn, 0); + rmapp = gfn_to_rmap(kvm, gfn, PT_PAGE_TABLE_LEVEL); spte = rmap_next(kvm, rmapp, NULL); while (spte) { @@ -650,7 +711,7 @@ static int rmap_write_protect(struct kvm *kvm, u64 gfn) BUG_ON(!(*spte & PT_PRESENT_MASK)); rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte); if (is_writeble_pte(*spte)) { - set_shadow_pte(spte, *spte & ~PT_WRITABLE_MASK); + __set_spte(spte, *spte & ~PT_WRITABLE_MASK); write_protected = 1; } spte = rmap_next(kvm, rmapp, spte); @@ -664,21 +725,24 @@ static int rmap_write_protect(struct kvm *kvm, u64 gfn) } /* check for huge page mappings */ - rmapp = gfn_to_rmap(kvm, gfn, 1); - spte = rmap_next(kvm, rmapp, NULL); - while (spte) { - BUG_ON(!spte); - BUG_ON(!(*spte & PT_PRESENT_MASK)); - BUG_ON((*spte & (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK)) != (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK)); - pgprintk("rmap_write_protect(large): spte %p %llx %lld\n", spte, *spte, gfn); - if (is_writeble_pte(*spte)) { - rmap_remove(kvm, spte); - --kvm->stat.lpages; - set_shadow_pte(spte, shadow_trap_nonpresent_pte); - spte = NULL; - write_protected = 1; + for (i = PT_DIRECTORY_LEVEL; + i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { + rmapp = gfn_to_rmap(kvm, gfn, i); + spte = rmap_next(kvm, rmapp, NULL); + while (spte) { + BUG_ON(!spte); + BUG_ON(!(*spte & PT_PRESENT_MASK)); + BUG_ON((*spte & (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK)) != (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK)); + pgprintk("rmap_write_protect(large): spte %p %llx %lld\n", spte, *spte, gfn); + if (is_writeble_pte(*spte)) { + rmap_remove(kvm, spte); + --kvm->stat.lpages; + __set_spte(spte, shadow_trap_nonpresent_pte); + spte = NULL; + write_protected = 1; + } + spte = rmap_next(kvm, rmapp, spte); } - spte = rmap_next(kvm, rmapp, spte); } return write_protected; @@ -693,7 +757,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp) BUG_ON(!(*spte & PT_PRESENT_MASK)); rmap_printk("kvm_rmap_unmap_hva: spte %p %llx\n", spte, *spte); rmap_remove(kvm, spte); - set_shadow_pte(spte, shadow_trap_nonpresent_pte); + __set_spte(spte, shadow_trap_nonpresent_pte); need_tlb_flush = 1; } return need_tlb_flush; @@ -702,7 +766,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp) static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, int (*handler)(struct kvm *kvm, unsigned long *rmapp)) { - int i; + int i, j; int retval = 0; /* @@ -721,11 +785,15 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, end = start + (memslot->npages << PAGE_SHIFT); if (hva >= start && hva < end) { gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT; + retval |= handler(kvm, &memslot->rmap[gfn_offset]); - retval |= handler(kvm, - &memslot->lpage_info[ - gfn_offset / - KVM_PAGES_PER_HPAGE].rmap_pde); + + for (j = 0; j < KVM_NR_PAGE_SIZES - 1; ++j) { + int idx = gfn_offset; + idx /= KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL + j); + retval |= handler(kvm, + &memslot->lpage_info[j][idx].rmap_pde); + } } } @@ -763,12 +831,15 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp) #define RMAP_RECYCLE_THRESHOLD 1000 -static void rmap_recycle(struct kvm_vcpu *vcpu, gfn_t gfn, int lpage) +static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) { unsigned long *rmapp; + struct kvm_mmu_page *sp; + + sp = page_header(__pa(spte)); gfn = unalias_gfn(vcpu->kvm, gfn); - rmapp = gfn_to_rmap(vcpu->kvm, gfn, lpage); + rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level); kvm_unmap_rmapp(vcpu->kvm, rmapp); kvm_flush_remote_tlbs(vcpu->kvm); @@ -1109,6 +1180,7 @@ static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) return 1; } + trace_kvm_mmu_sync_page(sp); if (rmap_write_protect(vcpu->kvm, sp->gfn)) kvm_flush_remote_tlbs(vcpu->kvm); kvm_unlink_unsync_page(vcpu->kvm, sp); @@ -1231,8 +1303,6 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1; role.quadrant = quadrant; } - pgprintk("%s: looking gfn %lx role %x\n", __func__, - gfn, role.word); index = kvm_page_table_hashfn(gfn); bucket = &vcpu->kvm->arch.mmu_page_hash[index]; hlist_for_each_entry_safe(sp, node, tmp, bucket, hash_link) @@ -1249,14 +1319,13 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, set_bit(KVM_REQ_MMU_SYNC, &vcpu->requests); kvm_mmu_mark_parents_unsync(vcpu, sp); } - pgprintk("%s: found\n", __func__); + trace_kvm_mmu_get_page(sp, false); return sp; } ++vcpu->kvm->stat.mmu_cache_miss; sp = kvm_mmu_alloc_page(vcpu, parent_pte); if (!sp) return sp; - pgprintk("%s: adding gfn %lx role %x\n", __func__, gfn, role.word); sp->gfn = gfn; sp->role = role; hlist_add_head(&sp->hash_link, bucket); @@ -1269,6 +1338,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, vcpu->arch.mmu.prefetch_page(vcpu, sp); else nonpaging_prefetch_page(vcpu, sp); + trace_kvm_mmu_get_page(sp, true); return sp; } @@ -1292,6 +1362,11 @@ static bool shadow_walk_okay(struct kvm_shadow_walk_iterator *iterator) { if (iterator->level < PT_PAGE_TABLE_LEVEL) return false; + + if (iterator->level == PT_PAGE_TABLE_LEVEL) + if (is_large_pte(*iterator->sptep)) + return false; + iterator->index = SHADOW_PT_INDEX(iterator->addr, iterator->level); iterator->sptep = ((u64 *)__va(iterator->shadow_addr)) + iterator->index; return true; @@ -1312,25 +1387,17 @@ static void kvm_mmu_page_unlink_children(struct kvm *kvm, pt = sp->spt; - if (sp->role.level == PT_PAGE_TABLE_LEVEL) { - for (i = 0; i < PT64_ENT_PER_PAGE; ++i) { - if (is_shadow_present_pte(pt[i])) - rmap_remove(kvm, &pt[i]); - pt[i] = shadow_trap_nonpresent_pte; - } - return; - } - for (i = 0; i < PT64_ENT_PER_PAGE; ++i) { ent = pt[i]; if (is_shadow_present_pte(ent)) { - if (!is_large_pte(ent)) { + if (!is_last_spte(ent, sp->role.level)) { ent &= PT64_BASE_ADDR_MASK; mmu_page_remove_parent_pte(page_header(ent), &pt[i]); } else { - --kvm->stat.lpages; + if (is_large_pte(ent)) + --kvm->stat.lpages; rmap_remove(kvm, &pt[i]); } } @@ -1346,10 +1413,10 @@ static void kvm_mmu_put_page(struct kvm_mmu_page *sp, u64 *parent_pte) static void kvm_mmu_reset_last_pte_updated(struct kvm *kvm) { int i; + struct kvm_vcpu *vcpu; - for (i = 0; i < KVM_MAX_VCPUS; ++i) - if (kvm->vcpus[i]) - kvm->vcpus[i]->arch.last_pte_updated = NULL; + kvm_for_each_vcpu(i, vcpu, kvm) + vcpu->arch.last_pte_updated = NULL; } static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp) @@ -1368,7 +1435,7 @@ static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp) } BUG_ON(!parent_pte); kvm_mmu_put_page(sp, parent_pte); - set_shadow_pte(parent_pte, shadow_trap_nonpresent_pte); + __set_spte(parent_pte, shadow_trap_nonpresent_pte); } } @@ -1400,6 +1467,8 @@ static int mmu_zap_unsync_children(struct kvm *kvm, static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp) { int ret; + + trace_kvm_mmu_zap_page(sp); ++kvm->stat.mmu_shadow_zapped; ret = mmu_zap_unsync_children(kvm, sp); kvm_mmu_page_unlink_children(kvm, sp); @@ -1516,7 +1585,7 @@ static void mmu_convert_notrap(struct kvm_mmu_page *sp) for (i = 0; i < PT64_ENT_PER_PAGE; ++i) { if (pt[i] == shadow_notrap_nonpresent_pte) - set_shadow_pte(&pt[i], shadow_trap_nonpresent_pte); + __set_spte(&pt[i], shadow_trap_nonpresent_pte); } } @@ -1646,6 +1715,7 @@ static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) struct kvm_mmu_page *s; struct hlist_node *node, *n; + trace_kvm_mmu_unsync_page(sp); index = kvm_page_table_hashfn(sp->gfn); bucket = &vcpu->kvm->arch.mmu_page_hash[index]; /* don't unsync if pagetable is shadowed with multiple roles */ @@ -1682,9 +1752,9 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, return 0; } -static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, +static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, int user_fault, - int write_fault, int dirty, int largepage, + int write_fault, int dirty, int level, gfn_t gfn, pfn_t pfn, bool speculative, bool can_unsync) { @@ -1707,7 +1777,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, spte |= shadow_nx_mask; if (pte_access & ACC_USER_MASK) spte |= shadow_user_mask; - if (largepage) + if (level > PT_PAGE_TABLE_LEVEL) spte |= PT_PAGE_SIZE_MASK; if (tdp_enabled) spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn, @@ -1718,7 +1788,8 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, if ((pte_access & ACC_WRITE_MASK) || (write_fault && !is_write_protection(vcpu) && !user_fault)) { - if (largepage && has_wrprotected_page(vcpu->kvm, gfn)) { + if (level > PT_PAGE_TABLE_LEVEL && + has_wrprotected_page(vcpu->kvm, gfn, level)) { ret = 1; spte = shadow_trap_nonpresent_pte; goto set_pte; @@ -1732,7 +1803,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, * is responsibility of mmu_get_page / kvm_sync_page. * Same reasoning can be applied to dirty page accounting. */ - if (!can_unsync && is_writeble_pte(*shadow_pte)) + if (!can_unsync && is_writeble_pte(*sptep)) goto set_pte; if (mmu_need_write_protect(vcpu, gfn, can_unsync)) { @@ -1749,65 +1820,67 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, mark_page_dirty(vcpu->kvm, gfn); set_pte: - set_shadow_pte(shadow_pte, spte); + __set_spte(sptep, spte); return ret; } -static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, +static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pt_access, unsigned pte_access, int user_fault, int write_fault, int dirty, - int *ptwrite, int largepage, gfn_t gfn, + int *ptwrite, int level, gfn_t gfn, pfn_t pfn, bool speculative) { int was_rmapped = 0; - int was_writeble = is_writeble_pte(*shadow_pte); + int was_writeble = is_writeble_pte(*sptep); int rmap_count; pgprintk("%s: spte %llx access %x write_fault %d" " user_fault %d gfn %lx\n", - __func__, *shadow_pte, pt_access, + __func__, *sptep, pt_access, write_fault, user_fault, gfn); - if (is_rmap_pte(*shadow_pte)) { + if (is_rmap_spte(*sptep)) { /* * If we overwrite a PTE page pointer with a 2MB PMD, unlink * the parent of the now unreachable PTE. */ - if (largepage && !is_large_pte(*shadow_pte)) { + if (level > PT_PAGE_TABLE_LEVEL && + !is_large_pte(*sptep)) { struct kvm_mmu_page *child; - u64 pte = *shadow_pte; + u64 pte = *sptep; child = page_header(pte & PT64_BASE_ADDR_MASK); - mmu_page_remove_parent_pte(child, shadow_pte); - } else if (pfn != spte_to_pfn(*shadow_pte)) { + mmu_page_remove_parent_pte(child, sptep); + } else if (pfn != spte_to_pfn(*sptep)) { pgprintk("hfn old %lx new %lx\n", - spte_to_pfn(*shadow_pte), pfn); - rmap_remove(vcpu->kvm, shadow_pte); + spte_to_pfn(*sptep), pfn); + rmap_remove(vcpu->kvm, sptep); } else was_rmapped = 1; } - if (set_spte(vcpu, shadow_pte, pte_access, user_fault, write_fault, - dirty, largepage, gfn, pfn, speculative, true)) { + + if (set_spte(vcpu, sptep, pte_access, user_fault, write_fault, + dirty, level, gfn, pfn, speculative, true)) { if (write_fault) *ptwrite = 1; kvm_x86_ops->tlb_flush(vcpu); } - pgprintk("%s: setting spte %llx\n", __func__, *shadow_pte); + pgprintk("%s: setting spte %llx\n", __func__, *sptep); pgprintk("instantiating %s PTE (%s) at %ld (%llx) addr %p\n", - is_large_pte(*shadow_pte)? "2MB" : "4kB", - is_present_pte(*shadow_pte)?"RW":"R", gfn, - *shadow_pte, shadow_pte); - if (!was_rmapped && is_large_pte(*shadow_pte)) + is_large_pte(*sptep)? "2MB" : "4kB", + *sptep & PT_PRESENT_MASK ?"RW":"R", gfn, + *sptep, sptep); + if (!was_rmapped && is_large_pte(*sptep)) ++vcpu->kvm->stat.lpages; - page_header_update_slot(vcpu->kvm, shadow_pte, gfn); + page_header_update_slot(vcpu->kvm, sptep, gfn); if (!was_rmapped) { - rmap_count = rmap_add(vcpu, shadow_pte, gfn, largepage); - if (!is_rmap_pte(*shadow_pte)) + rmap_count = rmap_add(vcpu, sptep, gfn); + if (!is_rmap_spte(*sptep)) kvm_release_pfn_clean(pfn); if (rmap_count > RMAP_RECYCLE_THRESHOLD) - rmap_recycle(vcpu, gfn, largepage); + rmap_recycle(vcpu, sptep, gfn); } else { if (was_writeble) kvm_release_pfn_dirty(pfn); @@ -1815,7 +1888,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, kvm_release_pfn_clean(pfn); } if (speculative) { - vcpu->arch.last_pte_updated = shadow_pte; + vcpu->arch.last_pte_updated = sptep; vcpu->arch.last_pte_gfn = gfn; } } @@ -1825,7 +1898,7 @@ static void nonpaging_new_cr3(struct kvm_vcpu *vcpu) } static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, - int largepage, gfn_t gfn, pfn_t pfn) + int level, gfn_t gfn, pfn_t pfn) { struct kvm_shadow_walk_iterator iterator; struct kvm_mmu_page *sp; @@ -1833,11 +1906,10 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, gfn_t pseudo_gfn; for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) { - if (iterator.level == PT_PAGE_TABLE_LEVEL - || (largepage && iterator.level == PT_DIRECTORY_LEVEL)) { + if (iterator.level == level) { mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, ACC_ALL, 0, write, 1, &pt_write, - largepage, gfn, pfn, false); + level, gfn, pfn, false); ++vcpu->stat.pf_fixed; break; } @@ -1853,10 +1925,10 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, return -ENOMEM; } - set_shadow_pte(iterator.sptep, - __pa(sp->spt) - | PT_PRESENT_MASK | PT_WRITABLE_MASK - | shadow_user_mask | shadow_x_mask); + __set_spte(iterator.sptep, + __pa(sp->spt) + | PT_PRESENT_MASK | PT_WRITABLE_MASK + | shadow_user_mask | shadow_x_mask); } } return pt_write; @@ -1865,14 +1937,20 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn) { int r; - int largepage = 0; + int level; pfn_t pfn; unsigned long mmu_seq; - if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) { - gfn &= ~(KVM_PAGES_PER_HPAGE-1); - largepage = 1; - } + level = mapping_level(vcpu, gfn); + + /* + * This path builds a PAE pagetable - so we can map 2mb pages at + * maximum. Therefore check if the level is larger than that. + */ + if (level > PT_DIRECTORY_LEVEL) + level = PT_DIRECTORY_LEVEL; + + gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); @@ -1888,7 +1966,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn) if (mmu_notifier_retry(vcpu, mmu_seq)) goto out_unlock; kvm_mmu_free_some_pages(vcpu); - r = __direct_map(vcpu, v, write, largepage, gfn, pfn); + r = __direct_map(vcpu, v, write, level, gfn, pfn); spin_unlock(&vcpu->kvm->mmu_lock); @@ -1954,6 +2032,7 @@ static int mmu_alloc_roots(struct kvm_vcpu *vcpu) gfn_t root_gfn; struct kvm_mmu_page *sp; int direct = 0; + u64 pdptr; root_gfn = vcpu->arch.cr3 >> PAGE_SHIFT; @@ -1981,11 +2060,12 @@ static int mmu_alloc_roots(struct kvm_vcpu *vcpu) ASSERT(!VALID_PAGE(root)); if (vcpu->arch.mmu.root_level == PT32E_ROOT_LEVEL) { - if (!is_present_pte(vcpu->arch.pdptrs[i])) { + pdptr = kvm_pdptr_read(vcpu, i); + if (!is_present_gpte(pdptr)) { vcpu->arch.mmu.pae_root[i] = 0; continue; } - root_gfn = vcpu->arch.pdptrs[i] >> PAGE_SHIFT; + root_gfn = pdptr >> PAGE_SHIFT; } else if (vcpu->arch.mmu.root_level == 0) root_gfn = 0; if (mmu_check_root(vcpu, root_gfn)) @@ -2062,7 +2142,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, { pfn_t pfn; int r; - int largepage = 0; + int level; gfn_t gfn = gpa >> PAGE_SHIFT; unsigned long mmu_seq; @@ -2073,10 +2153,10 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, if (r) return r; - if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) { - gfn &= ~(KVM_PAGES_PER_HPAGE-1); - largepage = 1; - } + level = mapping_level(vcpu, gfn); + + gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); + mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); pfn = gfn_to_pfn(vcpu->kvm, gfn); @@ -2089,7 +2169,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, goto out_unlock; kvm_mmu_free_some_pages(vcpu); r = __direct_map(vcpu, gpa, error_code & PFERR_WRITE_MASK, - largepage, gfn, pfn); + level, gfn, pfn); spin_unlock(&vcpu->kvm->mmu_lock); return r; @@ -2206,7 +2286,9 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level) context->rsvd_bits_mask[0][0] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51); context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3]; - context->rsvd_bits_mask[1][2] = context->rsvd_bits_mask[0][2]; + context->rsvd_bits_mask[1][2] = exb_bit_rsvd | + rsvd_bits(maxphyaddr, 51) | + rsvd_bits(13, 29); context->rsvd_bits_mask[1][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51) | rsvd_bits(13, 20); /* large page */ @@ -2357,8 +2439,8 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu) spin_unlock(&vcpu->kvm->mmu_lock); if (r) goto out; + /* set_cr3() should ensure TLB has been flushed */ kvm_x86_ops->set_cr3(vcpu, vcpu->arch.mmu.root_hpa); - kvm_mmu_flush_tlb(vcpu); out: return r; } @@ -2378,15 +2460,14 @@ static void mmu_pte_write_zap_pte(struct kvm_vcpu *vcpu, pte = *spte; if (is_shadow_present_pte(pte)) { - if (sp->role.level == PT_PAGE_TABLE_LEVEL || - is_large_pte(pte)) + if (is_last_spte(pte, sp->role.level)) rmap_remove(vcpu->kvm, spte); else { child = page_header(pte & PT64_BASE_ADDR_MASK); mmu_page_remove_parent_pte(child, spte); } } - set_shadow_pte(spte, shadow_trap_nonpresent_pte); + __set_spte(spte, shadow_trap_nonpresent_pte); if (is_large_pte(pte)) --vcpu->kvm->stat.lpages; } @@ -2397,11 +2478,8 @@ static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu, const void *new) { if (sp->role.level != PT_PAGE_TABLE_LEVEL) { - if (!vcpu->arch.update_pte.largepage || - sp->role.glevels == PT32_ROOT_LEVEL) { - ++vcpu->kvm->stat.mmu_pde_zapped; - return; - } + ++vcpu->kvm->stat.mmu_pde_zapped; + return; } ++vcpu->kvm->stat.mmu_pte_updated; @@ -2447,8 +2525,6 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, u64 gpte = 0; pfn_t pfn; - vcpu->arch.update_pte.largepage = 0; - if (bytes != 4 && bytes != 8) return; @@ -2472,14 +2548,10 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, if ((bytes == 4) && (gpa % 4 == 0)) memcpy((void *)&gpte, new, 4); } - if (!is_present_pte(gpte)) + if (!is_present_gpte(gpte)) return; gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; - if (is_large_pte(gpte) && is_largepage_backed(vcpu, gfn)) { - gfn &= ~(KVM_PAGES_PER_HPAGE-1); - vcpu->arch.update_pte.largepage = 1; - } vcpu->arch.update_pte.mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); pfn = gfn_to_pfn(vcpu->kvm, gfn); @@ -2622,6 +2694,9 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) gpa_t gpa; int r; + if (tdp_enabled) + return 0; + gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gva); spin_lock(&vcpu->kvm->mmu_lock); @@ -2633,7 +2708,8 @@ EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt); void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu) { - while (vcpu->kvm->arch.n_free_mmu_pages < KVM_REFILL_PAGES) { + while (vcpu->kvm->arch.n_free_mmu_pages < KVM_REFILL_PAGES && + !list_empty(&vcpu->kvm->arch.active_mmu_pages)) { struct kvm_mmu_page *sp; sp = container_of(vcpu->kvm->arch.active_mmu_pages.prev, @@ -2670,8 +2746,9 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code) ++vcpu->stat.mmio_exits; return 0; case EMULATE_FAIL: - kvm_report_emulation_failure(vcpu, "pagetable"); - return 1; + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + return 0; default: BUG(); } @@ -2712,12 +2789,6 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu) ASSERT(vcpu); - if (vcpu->kvm->arch.n_requested_mmu_pages) - vcpu->kvm->arch.n_free_mmu_pages = - vcpu->kvm->arch.n_requested_mmu_pages; - else - vcpu->kvm->arch.n_free_mmu_pages = - vcpu->kvm->arch.n_alloc_mmu_pages; /* * When emulating 32-bit mode, cr3 is only 32 bits even on x86_64. * Therefore we need to allocate shadow page tables in the first @@ -3029,6 +3100,24 @@ out: return r; } +int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]) +{ + struct kvm_shadow_walk_iterator iterator; + int nr_sptes = 0; + + spin_lock(&vcpu->kvm->mmu_lock); + for_each_shadow_entry(vcpu, addr, iterator) { + sptes[iterator.level-1] = *iterator.sptep; + nr_sptes++; + if (!is_shadow_present_pte(*iterator.sptep)) + break; + } + spin_unlock(&vcpu->kvm->mmu_lock); + + return nr_sptes; +} +EXPORT_SYMBOL_GPL(kvm_mmu_get_spte_hierarchy); + #ifdef AUDIT static const char *audit_msg; @@ -3041,6 +3130,54 @@ static gva_t canonicalize(gva_t gva) return gva; } + +typedef void (*inspect_spte_fn) (struct kvm *kvm, struct kvm_mmu_page *sp, + u64 *sptep); + +static void __mmu_spte_walk(struct kvm *kvm, struct kvm_mmu_page *sp, + inspect_spte_fn fn) +{ + int i; + + for (i = 0; i < PT64_ENT_PER_PAGE; ++i) { + u64 ent = sp->spt[i]; + + if (is_shadow_present_pte(ent)) { + if (!is_last_spte(ent, sp->role.level)) { + struct kvm_mmu_page *child; + child = page_header(ent & PT64_BASE_ADDR_MASK); + __mmu_spte_walk(kvm, child, fn); + } else + fn(kvm, sp, &sp->spt[i]); + } + } +} + +static void mmu_spte_walk(struct kvm_vcpu *vcpu, inspect_spte_fn fn) +{ + int i; + struct kvm_mmu_page *sp; + + if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) + return; + if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) { + hpa_t root = vcpu->arch.mmu.root_hpa; + sp = page_header(root); + __mmu_spte_walk(vcpu->kvm, sp, fn); + return; + } + for (i = 0; i < 4; ++i) { + hpa_t root = vcpu->arch.mmu.pae_root[i]; + + if (root && VALID_PAGE(root)) { + root &= PT64_BASE_ADDR_MASK; + sp = page_header(root); + __mmu_spte_walk(vcpu->kvm, sp, fn); + } + } + return; +} + static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte, gva_t va, int level) { @@ -3055,20 +3192,19 @@ static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte, continue; va = canonicalize(va); - if (level > 1) { - if (ent == shadow_notrap_nonpresent_pte) - printk(KERN_ERR "audit: (%s) nontrapping pte" - " in nonleaf level: levels %d gva %lx" - " level %d pte %llx\n", audit_msg, - vcpu->arch.mmu.root_level, va, level, ent); - else - audit_mappings_page(vcpu, ent, va, level - 1); - } else { + if (is_shadow_present_pte(ent) && !is_last_spte(ent, level)) + audit_mappings_page(vcpu, ent, va, level - 1); + else { gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, va); gfn_t gfn = gpa >> PAGE_SHIFT; pfn_t pfn = gfn_to_pfn(vcpu->kvm, gfn); hpa_t hpa = (hpa_t)pfn << PAGE_SHIFT; + if (is_error_pfn(pfn)) { + kvm_release_pfn_clean(pfn); + continue; + } + if (is_shadow_present_pte(ent) && (ent & PT64_BASE_ADDR_MASK) != hpa) printk(KERN_ERR "xx audit error: (%s) levels %d" @@ -3122,7 +3258,7 @@ static int count_rmaps(struct kvm_vcpu *vcpu) d = (struct kvm_rmap_desc *)(*rmapp & ~1ul); while (d) { for (k = 0; k < RMAP_EXT; ++k) - if (d->shadow_ptes[k]) + if (d->sptes[k]) ++nmaps; else break; @@ -3133,9 +3269,48 @@ static int count_rmaps(struct kvm_vcpu *vcpu) return nmaps; } -static int count_writable_mappings(struct kvm_vcpu *vcpu) +void inspect_spte_has_rmap(struct kvm *kvm, struct kvm_mmu_page *sp, u64 *sptep) +{ + unsigned long *rmapp; + struct kvm_mmu_page *rev_sp; + gfn_t gfn; + + if (*sptep & PT_WRITABLE_MASK) { + rev_sp = page_header(__pa(sptep)); + gfn = rev_sp->gfns[sptep - rev_sp->spt]; + + if (!gfn_to_memslot(kvm, gfn)) { + if (!printk_ratelimit()) + return; + printk(KERN_ERR "%s: no memslot for gfn %ld\n", + audit_msg, gfn); + printk(KERN_ERR "%s: index %ld of sp (gfn=%lx)\n", + audit_msg, sptep - rev_sp->spt, + rev_sp->gfn); + dump_stack(); + return; + } + + rmapp = gfn_to_rmap(kvm, rev_sp->gfns[sptep - rev_sp->spt], + is_large_pte(*sptep)); + if (!*rmapp) { + if (!printk_ratelimit()) + return; + printk(KERN_ERR "%s: no rmap for writable spte %llx\n", + audit_msg, *sptep); + dump_stack(); + } + } + +} + +void audit_writable_sptes_have_rmaps(struct kvm_vcpu *vcpu) +{ + mmu_spte_walk(vcpu, inspect_spte_has_rmap); +} + +static void check_writable_mappings_rmap(struct kvm_vcpu *vcpu) { - int nmaps = 0; struct kvm_mmu_page *sp; int i; @@ -3152,20 +3327,16 @@ static int count_writable_mappings(struct kvm_vcpu *vcpu) continue; if (!(ent & PT_WRITABLE_MASK)) continue; - ++nmaps; + inspect_spte_has_rmap(vcpu->kvm, sp, &pt[i]); } } - return nmaps; + return; } static void audit_rmap(struct kvm_vcpu *vcpu) { - int n_rmap = count_rmaps(vcpu); - int n_actual = count_writable_mappings(vcpu); - - if (n_rmap != n_actual) - printk(KERN_ERR "%s: (%s) rmap %d actual %d\n", - __func__, audit_msg, n_rmap, n_actual); + check_writable_mappings_rmap(vcpu); + count_rmaps(vcpu); } static void audit_write_protection(struct kvm_vcpu *vcpu) @@ -3173,20 +3344,28 @@ static void audit_write_protection(struct kvm_vcpu *vcpu) struct kvm_mmu_page *sp; struct kvm_memory_slot *slot; unsigned long *rmapp; + u64 *spte; gfn_t gfn; list_for_each_entry(sp, &vcpu->kvm->arch.active_mmu_pages, link) { if (sp->role.direct) continue; + if (sp->unsync) + continue; gfn = unalias_gfn(vcpu->kvm, sp->gfn); slot = gfn_to_memslot_unaliased(vcpu->kvm, sp->gfn); rmapp = &slot->rmap[gfn - slot->base_gfn]; - if (*rmapp) - printk(KERN_ERR "%s: (%s) shadow page has writable" - " mappings: gfn %lx role %x\n", + + spte = rmap_next(vcpu->kvm, rmapp, NULL); + while (spte) { + if (*spte & PT_WRITABLE_MASK) + printk(KERN_ERR "%s: (%s) shadow page has " + "writable mappings: gfn %lx role %x\n", __func__, audit_msg, sp->gfn, sp->role.word); + spte = rmap_next(vcpu->kvm, rmapp, spte); + } } } @@ -3198,7 +3377,9 @@ static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg) audit_msg = msg; audit_rmap(vcpu); audit_write_protection(vcpu); - audit_mappings(vcpu); + if (strcmp("pre pte write", audit_msg) != 0) + audit_mappings(vcpu); + audit_writable_sptes_have_rmaps(vcpu); dbg = olddbg; } diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 3494a2fb136e..61a1b3884b49 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -37,6 +37,8 @@ #define PT32_ROOT_LEVEL 2 #define PT32E_ROOT_LEVEL 3 +int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]); + static inline void kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu) { if (unlikely(vcpu->kvm->arch.n_free_mmu_pages < KVM_MIN_FREE_MMU_PAGES)) @@ -75,7 +77,7 @@ static inline int is_paging(struct kvm_vcpu *vcpu) return vcpu->arch.cr0 & X86_CR0_PG; } -static inline int is_present_pte(unsigned long pte) +static inline int is_present_gpte(unsigned long pte) { return pte & PT_PRESENT_MASK; } diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h new file mode 100644 index 000000000000..3e4a5c6ca2a9 --- /dev/null +++ b/arch/x86/kvm/mmutrace.h @@ -0,0 +1,220 @@ +#if !defined(_TRACE_KVMMMU_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_KVMMMU_H + +#include <linux/tracepoint.h> +#include <linux/ftrace_event.h> + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM kvmmmu +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE mmutrace + +#define KVM_MMU_PAGE_FIELDS \ + __field(__u64, gfn) \ + __field(__u32, role) \ + __field(__u32, root_count) \ + __field(__u32, unsync) + +#define KVM_MMU_PAGE_ASSIGN(sp) \ + __entry->gfn = sp->gfn; \ + __entry->role = sp->role.word; \ + __entry->root_count = sp->root_count; \ + __entry->unsync = sp->unsync; + +#define KVM_MMU_PAGE_PRINTK() ({ \ + const char *ret = p->buffer + p->len; \ + static const char *access_str[] = { \ + "---", "--x", "w--", "w-x", "-u-", "-ux", "wu-", "wux" \ + }; \ + union kvm_mmu_page_role role; \ + \ + role.word = __entry->role; \ + \ + trace_seq_printf(p, "sp gfn %llx %u/%u q%u%s %s%s %spge" \ + " %snxe root %u %s%c", \ + __entry->gfn, role.level, role.glevels, \ + role.quadrant, \ + role.direct ? " direct" : "", \ + access_str[role.access], \ + role.invalid ? " invalid" : "", \ + role.cr4_pge ? "" : "!", \ + role.nxe ? "" : "!", \ + __entry->root_count, \ + __entry->unsync ? "unsync" : "sync", 0); \ + ret; \ + }) + +#define kvm_mmu_trace_pferr_flags \ + { PFERR_PRESENT_MASK, "P" }, \ + { PFERR_WRITE_MASK, "W" }, \ + { PFERR_USER_MASK, "U" }, \ + { PFERR_RSVD_MASK, "RSVD" }, \ + { PFERR_FETCH_MASK, "F" } + +/* + * A pagetable walk has started + */ +TRACE_EVENT( + kvm_mmu_pagetable_walk, + TP_PROTO(u64 addr, int write_fault, int user_fault, int fetch_fault), + TP_ARGS(addr, write_fault, user_fault, fetch_fault), + + TP_STRUCT__entry( + __field(__u64, addr) + __field(__u32, pferr) + ), + + TP_fast_assign( + __entry->addr = addr; + __entry->pferr = (!!write_fault << 1) | (!!user_fault << 2) + | (!!fetch_fault << 4); + ), + + TP_printk("addr %llx pferr %x %s", __entry->addr, __entry->pferr, + __print_flags(__entry->pferr, "|", kvm_mmu_trace_pferr_flags)) +); + + +/* We just walked a paging element */ +TRACE_EVENT( + kvm_mmu_paging_element, + TP_PROTO(u64 pte, int level), + TP_ARGS(pte, level), + + TP_STRUCT__entry( + __field(__u64, pte) + __field(__u32, level) + ), + + TP_fast_assign( + __entry->pte = pte; + __entry->level = level; + ), + + TP_printk("pte %llx level %u", __entry->pte, __entry->level) +); + +/* We set a pte accessed bit */ +TRACE_EVENT( + kvm_mmu_set_accessed_bit, + TP_PROTO(unsigned long table_gfn, unsigned index, unsigned size), + TP_ARGS(table_gfn, index, size), + + TP_STRUCT__entry( + __field(__u64, gpa) + ), + + TP_fast_assign( + __entry->gpa = ((u64)table_gfn << PAGE_SHIFT) + + index * size; + ), + + TP_printk("gpa %llx", __entry->gpa) +); + +/* We set a pte dirty bit */ +TRACE_EVENT( + kvm_mmu_set_dirty_bit, + TP_PROTO(unsigned long table_gfn, unsigned index, unsigned size), + TP_ARGS(table_gfn, index, size), + + TP_STRUCT__entry( + __field(__u64, gpa) + ), + + TP_fast_assign( + __entry->gpa = ((u64)table_gfn << PAGE_SHIFT) + + index * size; + ), + + TP_printk("gpa %llx", __entry->gpa) +); + +TRACE_EVENT( + kvm_mmu_walker_error, + TP_PROTO(u32 pferr), + TP_ARGS(pferr), + + TP_STRUCT__entry( + __field(__u32, pferr) + ), + + TP_fast_assign( + __entry->pferr = pferr; + ), + + TP_printk("pferr %x %s", __entry->pferr, + __print_flags(__entry->pferr, "|", kvm_mmu_trace_pferr_flags)) +); + +TRACE_EVENT( + kvm_mmu_get_page, + TP_PROTO(struct kvm_mmu_page *sp, bool created), + TP_ARGS(sp, created), + + TP_STRUCT__entry( + KVM_MMU_PAGE_FIELDS + __field(bool, created) + ), + + TP_fast_assign( + KVM_MMU_PAGE_ASSIGN(sp) + __entry->created = created; + ), + + TP_printk("%s %s", KVM_MMU_PAGE_PRINTK(), + __entry->created ? "new" : "existing") +); + +TRACE_EVENT( + kvm_mmu_sync_page, + TP_PROTO(struct kvm_mmu_page *sp), + TP_ARGS(sp), + + TP_STRUCT__entry( + KVM_MMU_PAGE_FIELDS + ), + + TP_fast_assign( + KVM_MMU_PAGE_ASSIGN(sp) + ), + + TP_printk("%s", KVM_MMU_PAGE_PRINTK()) +); + +TRACE_EVENT( + kvm_mmu_unsync_page, + TP_PROTO(struct kvm_mmu_page *sp), + TP_ARGS(sp), + + TP_STRUCT__entry( + KVM_MMU_PAGE_FIELDS + ), + + TP_fast_assign( + KVM_MMU_PAGE_ASSIGN(sp) + ), + + TP_printk("%s", KVM_MMU_PAGE_PRINTK()) +); + +TRACE_EVENT( + kvm_mmu_zap_page, + TP_PROTO(struct kvm_mmu_page *sp), + TP_ARGS(sp), + + TP_STRUCT__entry( + KVM_MMU_PAGE_FIELDS + ), + + TP_fast_assign( + KVM_MMU_PAGE_ASSIGN(sp) + ), + + TP_printk("%s", KVM_MMU_PAGE_PRINTK()) +); + +#endif /* _TRACE_KVMMMU_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 67785f635399..d2fec9c12d22 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -27,7 +27,8 @@ #define guest_walker guest_walker64 #define FNAME(name) paging##64_##name #define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK - #define PT_DIR_BASE_ADDR_MASK PT64_DIR_BASE_ADDR_MASK + #define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl) + #define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl) #define PT_INDEX(addr, level) PT64_INDEX(addr, level) #define PT_LEVEL_MASK(level) PT64_LEVEL_MASK(level) #define PT_LEVEL_BITS PT64_LEVEL_BITS @@ -43,7 +44,8 @@ #define guest_walker guest_walker32 #define FNAME(name) paging##32_##name #define PT_BASE_ADDR_MASK PT32_BASE_ADDR_MASK - #define PT_DIR_BASE_ADDR_MASK PT32_DIR_BASE_ADDR_MASK + #define PT_LVL_ADDR_MASK(lvl) PT32_LVL_ADDR_MASK(lvl) + #define PT_LVL_OFFSET_MASK(lvl) PT32_LVL_OFFSET_MASK(lvl) #define PT_INDEX(addr, level) PT32_INDEX(addr, level) #define PT_LEVEL_MASK(level) PT32_LEVEL_MASK(level) #define PT_LEVEL_BITS PT32_LEVEL_BITS @@ -53,8 +55,8 @@ #error Invalid PTTYPE value #endif -#define gpte_to_gfn FNAME(gpte_to_gfn) -#define gpte_to_gfn_pde FNAME(gpte_to_gfn_pde) +#define gpte_to_gfn_lvl FNAME(gpte_to_gfn_lvl) +#define gpte_to_gfn(pte) gpte_to_gfn_lvl((pte), PT_PAGE_TABLE_LEVEL) /* * The guest_walker structure emulates the behavior of the hardware page @@ -71,14 +73,9 @@ struct guest_walker { u32 error_code; }; -static gfn_t gpte_to_gfn(pt_element_t gpte) +static gfn_t gpte_to_gfn_lvl(pt_element_t gpte, int lvl) { - return (gpte & PT_BASE_ADDR_MASK) >> PAGE_SHIFT; -} - -static gfn_t gpte_to_gfn_pde(pt_element_t gpte) -{ - return (gpte & PT_DIR_BASE_ADDR_MASK) >> PAGE_SHIFT; + return (gpte & PT_LVL_ADDR_MASK(lvl)) >> PAGE_SHIFT; } static bool FNAME(cmpxchg_gpte)(struct kvm *kvm, @@ -125,14 +122,16 @@ static int FNAME(walk_addr)(struct guest_walker *walker, gpa_t pte_gpa; int rsvd_fault = 0; - pgprintk("%s: addr %lx\n", __func__, addr); + trace_kvm_mmu_pagetable_walk(addr, write_fault, user_fault, + fetch_fault); walk: walker->level = vcpu->arch.mmu.root_level; pte = vcpu->arch.cr3; #if PTTYPE == 64 if (!is_long_mode(vcpu)) { - pte = vcpu->arch.pdptrs[(addr >> 30) & 3]; - if (!is_present_pte(pte)) + pte = kvm_pdptr_read(vcpu, (addr >> 30) & 3); + trace_kvm_mmu_paging_element(pte, walker->level); + if (!is_present_gpte(pte)) goto not_present; --walker->level; } @@ -150,12 +149,11 @@ walk: pte_gpa += index * sizeof(pt_element_t); walker->table_gfn[walker->level - 1] = table_gfn; walker->pte_gpa[walker->level - 1] = pte_gpa; - pgprintk("%s: table_gfn[%d] %lx\n", __func__, - walker->level - 1, table_gfn); kvm_read_guest(vcpu->kvm, pte_gpa, &pte, sizeof(pte)); + trace_kvm_mmu_paging_element(pte, walker->level); - if (!is_present_pte(pte)) + if (!is_present_gpte(pte)) goto not_present; rsvd_fault = is_rsvd_bits_set(vcpu, pte, walker->level); @@ -175,6 +173,8 @@ walk: #endif if (!(pte & PT_ACCESSED_MASK)) { + trace_kvm_mmu_set_accessed_bit(table_gfn, index, + sizeof(pte)); mark_page_dirty(vcpu->kvm, table_gfn); if (FNAME(cmpxchg_gpte)(vcpu->kvm, table_gfn, index, pte, pte|PT_ACCESSED_MASK)) @@ -186,18 +186,24 @@ walk: walker->ptes[walker->level - 1] = pte; - if (walker->level == PT_PAGE_TABLE_LEVEL) { - walker->gfn = gpte_to_gfn(pte); - break; - } - - if (walker->level == PT_DIRECTORY_LEVEL - && (pte & PT_PAGE_SIZE_MASK) - && (PTTYPE == 64 || is_pse(vcpu))) { - walker->gfn = gpte_to_gfn_pde(pte); - walker->gfn += PT_INDEX(addr, PT_PAGE_TABLE_LEVEL); - if (PTTYPE == 32 && is_cpuid_PSE36()) + if ((walker->level == PT_PAGE_TABLE_LEVEL) || + ((walker->level == PT_DIRECTORY_LEVEL) && + (pte & PT_PAGE_SIZE_MASK) && + (PTTYPE == 64 || is_pse(vcpu))) || + ((walker->level == PT_PDPE_LEVEL) && + (pte & PT_PAGE_SIZE_MASK) && + is_long_mode(vcpu))) { + int lvl = walker->level; + + walker->gfn = gpte_to_gfn_lvl(pte, lvl); + walker->gfn += (addr & PT_LVL_OFFSET_MASK(lvl)) + >> PAGE_SHIFT; + + if (PTTYPE == 32 && + walker->level == PT_DIRECTORY_LEVEL && + is_cpuid_PSE36()) walker->gfn += pse36_gfn_delta(pte); + break; } @@ -205,9 +211,10 @@ walk: --walker->level; } - if (write_fault && !is_dirty_pte(pte)) { + if (write_fault && !is_dirty_gpte(pte)) { bool ret; + trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte)); mark_page_dirty(vcpu->kvm, table_gfn); ret = FNAME(cmpxchg_gpte)(vcpu->kvm, table_gfn, index, pte, pte|PT_DIRTY_MASK); @@ -239,6 +246,7 @@ err: walker->error_code |= PFERR_FETCH_MASK; if (rsvd_fault) walker->error_code |= PFERR_RSVD_MASK; + trace_kvm_mmu_walker_error(walker->error_code); return 0; } @@ -248,12 +256,11 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page, pt_element_t gpte; unsigned pte_access; pfn_t pfn; - int largepage = vcpu->arch.update_pte.largepage; gpte = *(const pt_element_t *)pte; if (~gpte & (PT_PRESENT_MASK | PT_ACCESSED_MASK)) { - if (!is_present_pte(gpte)) - set_shadow_pte(spte, shadow_notrap_nonpresent_pte); + if (!is_present_gpte(gpte)) + __set_spte(spte, shadow_notrap_nonpresent_pte); return; } pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte); @@ -267,7 +274,7 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page, return; kvm_get_pfn(pfn); mmu_set_spte(vcpu, spte, page->role.access, pte_access, 0, 0, - gpte & PT_DIRTY_MASK, NULL, largepage, + gpte & PT_DIRTY_MASK, NULL, PT_PAGE_TABLE_LEVEL, gpte_to_gfn(gpte), pfn, true); } @@ -276,7 +283,7 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page, */ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, struct guest_walker *gw, - int user_fault, int write_fault, int largepage, + int user_fault, int write_fault, int hlevel, int *ptwrite, pfn_t pfn) { unsigned access = gw->pt_access; @@ -289,19 +296,18 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, pt_element_t curr_pte; struct kvm_shadow_walk_iterator iterator; - if (!is_present_pte(gw->ptes[gw->level - 1])) + if (!is_present_gpte(gw->ptes[gw->level - 1])) return NULL; for_each_shadow_entry(vcpu, addr, iterator) { level = iterator.level; sptep = iterator.sptep; - if (level == PT_PAGE_TABLE_LEVEL - || (largepage && level == PT_DIRECTORY_LEVEL)) { + if (iterator.level == hlevel) { mmu_set_spte(vcpu, sptep, access, gw->pte_access & access, user_fault, write_fault, gw->ptes[gw->level-1] & PT_DIRTY_MASK, - ptwrite, largepage, + ptwrite, level, gw->gfn, pfn, false); break; } @@ -311,16 +317,19 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, if (is_large_pte(*sptep)) { rmap_remove(vcpu->kvm, sptep); - set_shadow_pte(sptep, shadow_trap_nonpresent_pte); + __set_spte(sptep, shadow_trap_nonpresent_pte); kvm_flush_remote_tlbs(vcpu->kvm); } - if (level == PT_DIRECTORY_LEVEL - && gw->level == PT_DIRECTORY_LEVEL) { + if (level <= gw->level) { + int delta = level - gw->level + 1; direct = 1; - if (!is_dirty_pte(gw->ptes[level - 1])) + if (!is_dirty_gpte(gw->ptes[level - delta])) access &= ~ACC_WRITE_MASK; - table_gfn = gpte_to_gfn(gw->ptes[level - 1]); + table_gfn = gpte_to_gfn(gw->ptes[level - delta]); + /* advance table_gfn when emulating 1gb pages with 4k */ + if (delta == 0) + table_gfn += PT_INDEX(addr, level); } else { direct = 0; table_gfn = gw->table_gfn[level - 2]; @@ -369,11 +378,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, int user_fault = error_code & PFERR_USER_MASK; int fetch_fault = error_code & PFERR_FETCH_MASK; struct guest_walker walker; - u64 *shadow_pte; + u64 *sptep; int write_pt = 0; int r; pfn_t pfn; - int largepage = 0; + int level = PT_PAGE_TABLE_LEVEL; unsigned long mmu_seq; pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code); @@ -399,14 +408,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, return 0; } - if (walker.level == PT_DIRECTORY_LEVEL) { - gfn_t large_gfn; - large_gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE-1); - if (is_largepage_backed(vcpu, large_gfn)) { - walker.gfn = large_gfn; - largepage = 1; - } + if (walker.level >= PT_DIRECTORY_LEVEL) { + level = min(walker.level, mapping_level(vcpu, walker.gfn)); + walker.gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE(level) - 1); } + mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); pfn = gfn_to_pfn(vcpu->kvm, walker.gfn); @@ -422,11 +428,10 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, if (mmu_notifier_retry(vcpu, mmu_seq)) goto out_unlock; kvm_mmu_free_some_pages(vcpu); - shadow_pte = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault, - largepage, &write_pt, pfn); - + sptep = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault, + level, &write_pt, pfn); pgprintk("%s: shadow pte %p %llx ptwrite %d\n", __func__, - shadow_pte, *shadow_pte, write_pt); + sptep, *sptep, write_pt); if (!write_pt) vcpu->arch.last_pt_write_count = 0; /* reset fork detector */ @@ -459,8 +464,9 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) sptep = iterator.sptep; /* FIXME: properly handle invlpg on large guest pages */ - if (level == PT_PAGE_TABLE_LEVEL || - ((level == PT_DIRECTORY_LEVEL) && is_large_pte(*sptep))) { + if (level == PT_PAGE_TABLE_LEVEL || + ((level == PT_DIRECTORY_LEVEL && is_large_pte(*sptep))) || + ((level == PT_PDPE_LEVEL && is_large_pte(*sptep)))) { struct kvm_mmu_page *sp = page_header(__pa(sptep)); pte_gpa = (sp->gfn << PAGE_SHIFT); @@ -472,7 +478,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) --vcpu->kvm->stat.lpages; need_flush = 1; } - set_shadow_pte(sptep, shadow_trap_nonpresent_pte); + __set_spte(sptep, shadow_trap_nonpresent_pte); break; } @@ -489,7 +495,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte, sizeof(pt_element_t))) return; - if (is_present_pte(gpte) && (gpte & PT_ACCESSED_MASK)) { + if (is_present_gpte(gpte) && (gpte & PT_ACCESSED_MASK)) { if (mmu_topup_memory_caches(vcpu)) return; kvm_mmu_pte_write(vcpu, pte_gpa, (const u8 *)&gpte, @@ -536,7 +542,7 @@ static void FNAME(prefetch_page)(struct kvm_vcpu *vcpu, r = kvm_read_guest_atomic(vcpu->kvm, pte_gpa, pt, sizeof pt); pte_gpa += ARRAY_SIZE(pt) * sizeof(pt_element_t); for (j = 0; j < ARRAY_SIZE(pt); ++j) - if (r || is_present_pte(pt[j])) + if (r || is_present_gpte(pt[j])) sp->spt[i+j] = shadow_trap_nonpresent_pte; else sp->spt[i+j] = shadow_notrap_nonpresent_pte; @@ -574,23 +580,23 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) sizeof(pt_element_t))) return -EINVAL; - if (gpte_to_gfn(gpte) != gfn || !is_present_pte(gpte) || + if (gpte_to_gfn(gpte) != gfn || !is_present_gpte(gpte) || !(gpte & PT_ACCESSED_MASK)) { u64 nonpresent; rmap_remove(vcpu->kvm, &sp->spt[i]); - if (is_present_pte(gpte)) + if (is_present_gpte(gpte)) nonpresent = shadow_trap_nonpresent_pte; else nonpresent = shadow_notrap_nonpresent_pte; - set_shadow_pte(&sp->spt[i], nonpresent); + __set_spte(&sp->spt[i], nonpresent); continue; } nr_present++; pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte); set_spte(vcpu, &sp->spt[i], pte_access, 0, 0, - is_dirty_pte(gpte), 0, gfn, + is_dirty_gpte(gpte), PT_PAGE_TABLE_LEVEL, gfn, spte_to_pfn(sp->spt[i]), true, false); } @@ -603,9 +609,10 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) #undef PT_BASE_ADDR_MASK #undef PT_INDEX #undef PT_LEVEL_MASK -#undef PT_DIR_BASE_ADDR_MASK +#undef PT_LVL_ADDR_MASK +#undef PT_LVL_OFFSET_MASK #undef PT_LEVEL_BITS #undef PT_MAX_FULL_LEVELS #undef gpte_to_gfn -#undef gpte_to_gfn_pde +#undef gpte_to_gfn_lvl #undef CMPXCHG diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index b1f658ad2f06..944cc9c04b3c 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -15,7 +15,6 @@ */ #include <linux/kvm_host.h> -#include "kvm_svm.h" #include "irq.h" #include "mmu.h" #include "kvm_cache_regs.h" @@ -26,10 +25,12 @@ #include <linux/vmalloc.h> #include <linux/highmem.h> #include <linux/sched.h> +#include <linux/ftrace_event.h> #include <asm/desc.h> #include <asm/virtext.h> +#include "trace.h" #define __ex(x) __kvm_handle_fault_on_reboot(x) @@ -46,6 +47,10 @@ MODULE_LICENSE("GPL"); #define SVM_FEATURE_LBRV (1 << 1) #define SVM_FEATURE_SVML (1 << 2) +#define NESTED_EXIT_HOST 0 /* Exit handled on host level */ +#define NESTED_EXIT_DONE 1 /* Exit caused nested vmexit */ +#define NESTED_EXIT_CONTINUE 2 /* Further checks needed */ + #define DEBUGCTL_RESERVED_BITS (~(0x3fULL)) /* Turn on to get debugging output*/ @@ -57,6 +62,58 @@ MODULE_LICENSE("GPL"); #define nsvm_printk(fmt, args...) do {} while(0) #endif +static const u32 host_save_user_msrs[] = { +#ifdef CONFIG_X86_64 + MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE, + MSR_FS_BASE, +#endif + MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, +}; + +#define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs) + +struct kvm_vcpu; + +struct nested_state { + struct vmcb *hsave; + u64 hsave_msr; + u64 vmcb; + + /* These are the merged vectors */ + u32 *msrpm; + + /* gpa pointers to the real vectors */ + u64 vmcb_msrpm; + + /* cache for intercepts of the guest */ + u16 intercept_cr_read; + u16 intercept_cr_write; + u16 intercept_dr_read; + u16 intercept_dr_write; + u32 intercept_exceptions; + u64 intercept; + +}; + +struct vcpu_svm { + struct kvm_vcpu vcpu; + struct vmcb *vmcb; + unsigned long vmcb_pa; + struct svm_cpu_data *svm_data; + uint64_t asid_generation; + uint64_t sysenter_esp; + uint64_t sysenter_eip; + + u64 next_rip; + + u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS]; + u64 host_gs_base; + + u32 *msrpm; + + struct nested_state nested; +}; + /* enable NPT for AMD64 and X86 with PAE */ #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) static bool npt_enabled = true; @@ -67,15 +124,14 @@ static int npt = 1; module_param(npt, int, S_IRUGO); -static int nested = 0; +static int nested = 1; module_param(nested, int, S_IRUGO); static void svm_flush_tlb(struct kvm_vcpu *vcpu); +static void svm_complete_interrupts(struct vcpu_svm *svm); -static int nested_svm_exit_handled(struct vcpu_svm *svm, bool kvm_override); +static int nested_svm_exit_handled(struct vcpu_svm *svm); static int nested_svm_vmexit(struct vcpu_svm *svm); -static int nested_svm_vmsave(struct vcpu_svm *svm, void *nested_vmcb, - void *arg2, void *opaque); static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code); @@ -86,7 +142,22 @@ static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu) static inline bool is_nested(struct vcpu_svm *svm) { - return svm->nested_vmcb; + return svm->nested.vmcb; +} + +static inline void enable_gif(struct vcpu_svm *svm) +{ + svm->vcpu.arch.hflags |= HF_GIF_MASK; +} + +static inline void disable_gif(struct vcpu_svm *svm) +{ + svm->vcpu.arch.hflags &= ~HF_GIF_MASK; +} + +static inline bool gif_set(struct vcpu_svm *svm) +{ + return !!(svm->vcpu.arch.hflags & HF_GIF_MASK); } static unsigned long iopm_base; @@ -147,19 +218,6 @@ static inline void invlpga(unsigned long addr, u32 asid) asm volatile (__ex(SVM_INVLPGA) :: "a"(addr), "c"(asid)); } -static inline unsigned long kvm_read_cr2(void) -{ - unsigned long cr2; - - asm volatile ("mov %%cr2, %0" : "=r" (cr2)); - return cr2; -} - -static inline void kvm_write_cr2(unsigned long val) -{ - asm volatile ("mov %0, %%cr2" :: "r" (val)); -} - static inline void force_new_asid(struct kvm_vcpu *vcpu) { to_svm(vcpu)->asid_generation--; @@ -263,7 +321,7 @@ static void svm_hardware_enable(void *garbage) struct svm_cpu_data *svm_data; uint64_t efer; - struct desc_ptr gdt_descr; + struct descriptor_table gdt_descr; struct desc_struct *gdt; int me = raw_smp_processor_id(); @@ -283,8 +341,8 @@ static void svm_hardware_enable(void *garbage) svm_data->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1; svm_data->next_asid = svm_data->max_asid + 1; - asm volatile ("sgdt %0" : "=m"(gdt_descr)); - gdt = (struct desc_struct *)gdt_descr.address; + kvm_get_gdt(&gdt_descr); + gdt = (struct desc_struct *)gdt_descr.base; svm_data->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS); rdmsrl(MSR_EFER, efer); @@ -367,8 +425,6 @@ static void svm_vcpu_init_msrpm(u32 *msrpm) #endif set_msr_interception(msrpm, MSR_K6_STAR, 1, 1); set_msr_interception(msrpm, MSR_IA32_SYSENTER_CS, 1, 1); - set_msr_interception(msrpm, MSR_IA32_SYSENTER_ESP, 1, 1); - set_msr_interception(msrpm, MSR_IA32_SYSENTER_EIP, 1, 1); } static void svm_enable_lbrv(struct vcpu_svm *svm) @@ -595,8 +651,10 @@ static void init_vmcb(struct vcpu_svm *svm) } force_new_asid(&svm->vcpu); - svm->nested_vmcb = 0; - svm->vcpu.arch.hflags = HF_GIF_MASK; + svm->nested.vmcb = 0; + svm->vcpu.arch.hflags = 0; + + enable_gif(svm); } static int svm_vcpu_reset(struct kvm_vcpu *vcpu) @@ -605,7 +663,7 @@ static int svm_vcpu_reset(struct kvm_vcpu *vcpu) init_vmcb(svm); - if (vcpu->vcpu_id != 0) { + if (!kvm_vcpu_is_bsp(vcpu)) { 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; @@ -656,9 +714,9 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) hsave_page = alloc_page(GFP_KERNEL); if (!hsave_page) goto uninit; - svm->hsave = page_address(hsave_page); + svm->nested.hsave = page_address(hsave_page); - svm->nested_msrpm = page_address(nested_msrpm_pages); + svm->nested.msrpm = page_address(nested_msrpm_pages); svm->vmcb = page_address(page); clear_page(svm->vmcb); @@ -669,7 +727,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) fx_init(&svm->vcpu); svm->vcpu.fpu_active = 1; svm->vcpu.arch.apic_base = 0xfee00000 | MSR_IA32_APICBASE_ENABLE; - if (svm->vcpu.vcpu_id == 0) + if (kvm_vcpu_is_bsp(&svm->vcpu)) svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP; return &svm->vcpu; @@ -688,8 +746,8 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) __free_page(pfn_to_page(svm->vmcb_pa >> PAGE_SHIFT)); __free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER); - __free_page(virt_to_page(svm->hsave)); - __free_pages(virt_to_page(svm->nested_msrpm), MSRPM_ALLOC_ORDER); + __free_page(virt_to_page(svm->nested.hsave)); + __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, svm); } @@ -740,6 +798,18 @@ static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) to_svm(vcpu)->vmcb->save.rflags = rflags; } +static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) +{ + switch (reg) { + case VCPU_EXREG_PDPTR: + BUG_ON(!npt_enabled); + load_pdptrs(vcpu, vcpu->arch.cr3); + break; + default: + BUG(); + } +} + static void svm_set_vintr(struct vcpu_svm *svm) { svm->vmcb->control.intercept |= 1ULL << INTERCEPT_VINTR; @@ -1061,7 +1131,6 @@ static unsigned long svm_get_dr(struct kvm_vcpu *vcpu, int dr) val = 0; } - KVMTRACE_2D(DR_READ, vcpu, (u32)dr, (u32)val, handler); return val; } @@ -1070,8 +1139,6 @@ static void svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value, { struct vcpu_svm *svm = to_svm(vcpu); - KVMTRACE_2D(DR_WRITE, vcpu, (u32)dr, (u32)value, handler); - *exception = 0; switch (dr) { @@ -1119,25 +1186,9 @@ static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) fault_address = svm->vmcb->control.exit_info_2; error_code = svm->vmcb->control.exit_info_1; - if (!npt_enabled) - KVMTRACE_3D(PAGE_FAULT, &svm->vcpu, error_code, - (u32)fault_address, (u32)(fault_address >> 32), - handler); - else - KVMTRACE_3D(TDP_FAULT, &svm->vcpu, error_code, - (u32)fault_address, (u32)(fault_address >> 32), - handler); - /* - * FIXME: Tis shouldn't be necessary here, but there is a flush - * missing in the MMU code. Until we find this bug, flush the - * complete TLB here on an NPF - */ - if (npt_enabled) - svm_flush_tlb(&svm->vcpu); - else { - if (kvm_event_needs_reinjection(&svm->vcpu)) - kvm_mmu_unprotect_page_virt(&svm->vcpu, fault_address); - } + trace_kvm_page_fault(fault_address, error_code); + if (!npt_enabled && kvm_event_needs_reinjection(&svm->vcpu)) + kvm_mmu_unprotect_page_virt(&svm->vcpu, fault_address); return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code); } @@ -1253,14 +1304,12 @@ static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) static int nmi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) { - KVMTRACE_0D(NMI, &svm->vcpu, handler); return 1; } static int intr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) { ++svm->vcpu.stat.irq_exits; - KVMTRACE_0D(INTR, &svm->vcpu, handler); return 1; } @@ -1303,44 +1352,39 @@ static int nested_svm_check_permissions(struct vcpu_svm *svm) static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code) { - if (is_nested(svm)) { - svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr; - svm->vmcb->control.exit_code_hi = 0; - svm->vmcb->control.exit_info_1 = error_code; - svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2; - if (nested_svm_exit_handled(svm, false)) { - nsvm_printk("VMexit -> EXCP 0x%x\n", nr); - - nested_svm_vmexit(svm); - return 1; - } - } + if (!is_nested(svm)) + return 0; - return 0; + svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr; + svm->vmcb->control.exit_code_hi = 0; + svm->vmcb->control.exit_info_1 = error_code; + svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2; + + return nested_svm_exit_handled(svm); } static inline int nested_svm_intr(struct vcpu_svm *svm) { - if (is_nested(svm)) { - if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK)) - return 0; + if (!is_nested(svm)) + return 0; - if (!(svm->vcpu.arch.hflags & HF_HIF_MASK)) - return 0; + if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK)) + return 0; - svm->vmcb->control.exit_code = SVM_EXIT_INTR; + if (!(svm->vcpu.arch.hflags & HF_HIF_MASK)) + return 0; - if (nested_svm_exit_handled(svm, false)) { - nsvm_printk("VMexit -> INTR\n"); - nested_svm_vmexit(svm); - return 1; - } + svm->vmcb->control.exit_code = SVM_EXIT_INTR; + + if (nested_svm_exit_handled(svm)) { + nsvm_printk("VMexit -> INTR\n"); + return 1; } return 0; } -static struct page *nested_svm_get_page(struct vcpu_svm *svm, u64 gpa) +static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, enum km_type idx) { struct page *page; @@ -1348,236 +1392,246 @@ static struct page *nested_svm_get_page(struct vcpu_svm *svm, u64 gpa) page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT); up_read(¤t->mm->mmap_sem); - if (is_error_page(page)) { - printk(KERN_INFO "%s: could not find page at 0x%llx\n", - __func__, gpa); - kvm_release_page_clean(page); - kvm_inject_gp(&svm->vcpu, 0); - return NULL; - } - return page; + if (is_error_page(page)) + goto error; + + return kmap_atomic(page, idx); + +error: + kvm_release_page_clean(page); + kvm_inject_gp(&svm->vcpu, 0); + + return NULL; } -static int nested_svm_do(struct vcpu_svm *svm, - u64 arg1_gpa, u64 arg2_gpa, void *opaque, - int (*handler)(struct vcpu_svm *svm, - void *arg1, - void *arg2, - void *opaque)) +static void nested_svm_unmap(void *addr, enum km_type idx) { - struct page *arg1_page; - struct page *arg2_page = NULL; - void *arg1; - void *arg2 = NULL; - int retval; + struct page *page; - arg1_page = nested_svm_get_page(svm, arg1_gpa); - if(arg1_page == NULL) - return 1; + if (!addr) + return; - if (arg2_gpa) { - arg2_page = nested_svm_get_page(svm, arg2_gpa); - if(arg2_page == NULL) { - kvm_release_page_clean(arg1_page); - return 1; - } - } + page = kmap_atomic_to_page(addr); + + kunmap_atomic(addr, idx); + kvm_release_page_dirty(page); +} + +static bool nested_svm_exit_handled_msr(struct vcpu_svm *svm) +{ + u32 param = svm->vmcb->control.exit_info_1 & 1; + u32 msr = svm->vcpu.arch.regs[VCPU_REGS_RCX]; + bool ret = false; + u32 t0, t1; + u8 *msrpm; - arg1 = kmap_atomic(arg1_page, KM_USER0); - if (arg2_gpa) - arg2 = kmap_atomic(arg2_page, KM_USER1); + if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT))) + return false; - retval = handler(svm, arg1, arg2, opaque); + msrpm = nested_svm_map(svm, svm->nested.vmcb_msrpm, KM_USER0); + + if (!msrpm) + goto out; + + switch (msr) { + case 0 ... 0x1fff: + t0 = (msr * 2) % 8; + t1 = msr / 8; + break; + case 0xc0000000 ... 0xc0001fff: + t0 = (8192 + msr - 0xc0000000) * 2; + t1 = (t0 / 8); + t0 %= 8; + break; + case 0xc0010000 ... 0xc0011fff: + t0 = (16384 + msr - 0xc0010000) * 2; + t1 = (t0 / 8); + t0 %= 8; + break; + default: + ret = true; + goto out; + } - kunmap_atomic(arg1, KM_USER0); - if (arg2_gpa) - kunmap_atomic(arg2, KM_USER1); + ret = msrpm[t1] & ((1 << param) << t0); - kvm_release_page_dirty(arg1_page); - if (arg2_gpa) - kvm_release_page_dirty(arg2_page); +out: + nested_svm_unmap(msrpm, KM_USER0); - return retval; + return ret; } -static int nested_svm_exit_handled_real(struct vcpu_svm *svm, - void *arg1, - void *arg2, - void *opaque) +static int nested_svm_exit_special(struct vcpu_svm *svm) { - struct vmcb *nested_vmcb = (struct vmcb *)arg1; - bool kvm_overrides = *(bool *)opaque; u32 exit_code = svm->vmcb->control.exit_code; - if (kvm_overrides) { - switch (exit_code) { - case SVM_EXIT_INTR: - case SVM_EXIT_NMI: - return 0; + switch (exit_code) { + case SVM_EXIT_INTR: + case SVM_EXIT_NMI: + return NESTED_EXIT_HOST; /* For now we are always handling NPFs when using them */ - case SVM_EXIT_NPF: - if (npt_enabled) - return 0; - break; - /* When we're shadowing, trap PFs */ - case SVM_EXIT_EXCP_BASE + PF_VECTOR: - if (!npt_enabled) - return 0; - break; - default: - break; - } + case SVM_EXIT_NPF: + if (npt_enabled) + return NESTED_EXIT_HOST; + break; + /* When we're shadowing, trap PFs */ + case SVM_EXIT_EXCP_BASE + PF_VECTOR: + if (!npt_enabled) + return NESTED_EXIT_HOST; + break; + default: + break; } + return NESTED_EXIT_CONTINUE; +} + +/* + * If this function returns true, this #vmexit was already handled + */ +static int nested_svm_exit_handled(struct vcpu_svm *svm) +{ + u32 exit_code = svm->vmcb->control.exit_code; + int vmexit = NESTED_EXIT_HOST; + switch (exit_code) { + case SVM_EXIT_MSR: + vmexit = nested_svm_exit_handled_msr(svm); + break; case SVM_EXIT_READ_CR0 ... SVM_EXIT_READ_CR8: { u32 cr_bits = 1 << (exit_code - SVM_EXIT_READ_CR0); - if (nested_vmcb->control.intercept_cr_read & cr_bits) - return 1; + if (svm->nested.intercept_cr_read & cr_bits) + vmexit = NESTED_EXIT_DONE; break; } case SVM_EXIT_WRITE_CR0 ... SVM_EXIT_WRITE_CR8: { u32 cr_bits = 1 << (exit_code - SVM_EXIT_WRITE_CR0); - if (nested_vmcb->control.intercept_cr_write & cr_bits) - return 1; + if (svm->nested.intercept_cr_write & cr_bits) + vmexit = NESTED_EXIT_DONE; break; } case SVM_EXIT_READ_DR0 ... SVM_EXIT_READ_DR7: { u32 dr_bits = 1 << (exit_code - SVM_EXIT_READ_DR0); - if (nested_vmcb->control.intercept_dr_read & dr_bits) - return 1; + if (svm->nested.intercept_dr_read & dr_bits) + vmexit = NESTED_EXIT_DONE; break; } case SVM_EXIT_WRITE_DR0 ... SVM_EXIT_WRITE_DR7: { u32 dr_bits = 1 << (exit_code - SVM_EXIT_WRITE_DR0); - if (nested_vmcb->control.intercept_dr_write & dr_bits) - return 1; + if (svm->nested.intercept_dr_write & dr_bits) + vmexit = NESTED_EXIT_DONE; break; } case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: { u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE); - if (nested_vmcb->control.intercept_exceptions & excp_bits) - return 1; + if (svm->nested.intercept_exceptions & excp_bits) + vmexit = NESTED_EXIT_DONE; break; } default: { u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR); nsvm_printk("exit code: 0x%x\n", exit_code); - if (nested_vmcb->control.intercept & exit_bits) - return 1; + if (svm->nested.intercept & exit_bits) + vmexit = NESTED_EXIT_DONE; } } - return 0; -} - -static int nested_svm_exit_handled_msr(struct vcpu_svm *svm, - void *arg1, void *arg2, - void *opaque) -{ - struct vmcb *nested_vmcb = (struct vmcb *)arg1; - u8 *msrpm = (u8 *)arg2; - u32 t0, t1; - u32 msr = svm->vcpu.arch.regs[VCPU_REGS_RCX]; - u32 param = svm->vmcb->control.exit_info_1 & 1; - - if (!(nested_vmcb->control.intercept & (1ULL << INTERCEPT_MSR_PROT))) - return 0; - - switch(msr) { - case 0 ... 0x1fff: - t0 = (msr * 2) % 8; - t1 = msr / 8; - break; - case 0xc0000000 ... 0xc0001fff: - t0 = (8192 + msr - 0xc0000000) * 2; - t1 = (t0 / 8); - t0 %= 8; - break; - case 0xc0010000 ... 0xc0011fff: - t0 = (16384 + msr - 0xc0010000) * 2; - t1 = (t0 / 8); - t0 %= 8; - break; - default: - return 1; - break; + if (vmexit == NESTED_EXIT_DONE) { + nsvm_printk("#VMEXIT reason=%04x\n", exit_code); + nested_svm_vmexit(svm); } - if (msrpm[t1] & ((1 << param) << t0)) - return 1; - return 0; + return vmexit; +} + +static inline void copy_vmcb_control_area(struct vmcb *dst_vmcb, struct vmcb *from_vmcb) +{ + struct vmcb_control_area *dst = &dst_vmcb->control; + struct vmcb_control_area *from = &from_vmcb->control; + + dst->intercept_cr_read = from->intercept_cr_read; + dst->intercept_cr_write = from->intercept_cr_write; + dst->intercept_dr_read = from->intercept_dr_read; + dst->intercept_dr_write = from->intercept_dr_write; + dst->intercept_exceptions = from->intercept_exceptions; + dst->intercept = from->intercept; + dst->iopm_base_pa = from->iopm_base_pa; + dst->msrpm_base_pa = from->msrpm_base_pa; + dst->tsc_offset = from->tsc_offset; + dst->asid = from->asid; + dst->tlb_ctl = from->tlb_ctl; + dst->int_ctl = from->int_ctl; + dst->int_vector = from->int_vector; + dst->int_state = from->int_state; + dst->exit_code = from->exit_code; + dst->exit_code_hi = from->exit_code_hi; + dst->exit_info_1 = from->exit_info_1; + dst->exit_info_2 = from->exit_info_2; + dst->exit_int_info = from->exit_int_info; + dst->exit_int_info_err = from->exit_int_info_err; + dst->nested_ctl = from->nested_ctl; + dst->event_inj = from->event_inj; + dst->event_inj_err = from->event_inj_err; + dst->nested_cr3 = from->nested_cr3; + dst->lbr_ctl = from->lbr_ctl; } -static int nested_svm_exit_handled(struct vcpu_svm *svm, bool kvm_override) +static int nested_svm_vmexit(struct vcpu_svm *svm) { - bool k = kvm_override; - - switch (svm->vmcb->control.exit_code) { - case SVM_EXIT_MSR: - return nested_svm_do(svm, svm->nested_vmcb, - svm->nested_vmcb_msrpm, NULL, - nested_svm_exit_handled_msr); - default: break; - } + struct vmcb *nested_vmcb; + struct vmcb *hsave = svm->nested.hsave; + struct vmcb *vmcb = svm->vmcb; - return nested_svm_do(svm, svm->nested_vmcb, 0, &k, - nested_svm_exit_handled_real); -} - -static int nested_svm_vmexit_real(struct vcpu_svm *svm, void *arg1, - void *arg2, void *opaque) -{ - struct vmcb *nested_vmcb = (struct vmcb *)arg1; - struct vmcb *hsave = svm->hsave; - u64 nested_save[] = { nested_vmcb->save.cr0, - nested_vmcb->save.cr3, - nested_vmcb->save.cr4, - nested_vmcb->save.efer, - nested_vmcb->control.intercept_cr_read, - nested_vmcb->control.intercept_cr_write, - nested_vmcb->control.intercept_dr_read, - nested_vmcb->control.intercept_dr_write, - nested_vmcb->control.intercept_exceptions, - nested_vmcb->control.intercept, - nested_vmcb->control.msrpm_base_pa, - nested_vmcb->control.iopm_base_pa, - nested_vmcb->control.tsc_offset }; + nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, KM_USER0); + if (!nested_vmcb) + return 1; /* Give the current vmcb to the guest */ - memcpy(nested_vmcb, svm->vmcb, sizeof(struct vmcb)); - nested_vmcb->save.cr0 = nested_save[0]; - if (!npt_enabled) - nested_vmcb->save.cr3 = nested_save[1]; - nested_vmcb->save.cr4 = nested_save[2]; - nested_vmcb->save.efer = nested_save[3]; - nested_vmcb->control.intercept_cr_read = nested_save[4]; - nested_vmcb->control.intercept_cr_write = nested_save[5]; - nested_vmcb->control.intercept_dr_read = nested_save[6]; - nested_vmcb->control.intercept_dr_write = nested_save[7]; - nested_vmcb->control.intercept_exceptions = nested_save[8]; - nested_vmcb->control.intercept = nested_save[9]; - nested_vmcb->control.msrpm_base_pa = nested_save[10]; - nested_vmcb->control.iopm_base_pa = nested_save[11]; - nested_vmcb->control.tsc_offset = nested_save[12]; + disable_gif(svm); + + nested_vmcb->save.es = vmcb->save.es; + nested_vmcb->save.cs = vmcb->save.cs; + nested_vmcb->save.ss = vmcb->save.ss; + nested_vmcb->save.ds = vmcb->save.ds; + nested_vmcb->save.gdtr = vmcb->save.gdtr; + nested_vmcb->save.idtr = vmcb->save.idtr; + if (npt_enabled) + nested_vmcb->save.cr3 = vmcb->save.cr3; + nested_vmcb->save.cr2 = vmcb->save.cr2; + nested_vmcb->save.rflags = vmcb->save.rflags; + nested_vmcb->save.rip = vmcb->save.rip; + nested_vmcb->save.rsp = vmcb->save.rsp; + nested_vmcb->save.rax = vmcb->save.rax; + nested_vmcb->save.dr7 = vmcb->save.dr7; + nested_vmcb->save.dr6 = vmcb->save.dr6; + nested_vmcb->save.cpl = vmcb->save.cpl; + + nested_vmcb->control.int_ctl = vmcb->control.int_ctl; + nested_vmcb->control.int_vector = vmcb->control.int_vector; + nested_vmcb->control.int_state = vmcb->control.int_state; + nested_vmcb->control.exit_code = vmcb->control.exit_code; + nested_vmcb->control.exit_code_hi = vmcb->control.exit_code_hi; + nested_vmcb->control.exit_info_1 = vmcb->control.exit_info_1; + nested_vmcb->control.exit_info_2 = vmcb->control.exit_info_2; + nested_vmcb->control.exit_int_info = vmcb->control.exit_int_info; + nested_vmcb->control.exit_int_info_err = vmcb->control.exit_int_info_err; + nested_vmcb->control.tlb_ctl = 0; + nested_vmcb->control.event_inj = 0; + nested_vmcb->control.event_inj_err = 0; /* We always set V_INTR_MASKING and remember the old value in hflags */ if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK)) nested_vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK; - if ((nested_vmcb->control.int_ctl & V_IRQ_MASK) && - (nested_vmcb->control.int_vector)) { - nsvm_printk("WARNING: IRQ 0x%x still enabled on #VMEXIT\n", - nested_vmcb->control.int_vector); - } - /* Restore the original control entries */ - svm->vmcb->control = hsave->control; + copy_vmcb_control_area(vmcb, hsave); /* Kill any pending exceptions */ if (svm->vcpu.arch.exception.pending == true) nsvm_printk("WARNING: Pending Exception\n"); - svm->vcpu.arch.exception.pending = false; + + kvm_clear_exception_queue(&svm->vcpu); + kvm_clear_interrupt_queue(&svm->vcpu); /* Restore selected save entries */ svm->vmcb->save.es = hsave->save.es; @@ -1603,19 +1657,10 @@ static int nested_svm_vmexit_real(struct vcpu_svm *svm, void *arg1, svm->vmcb->save.cpl = 0; svm->vmcb->control.exit_int_info = 0; - svm->vcpu.arch.hflags &= ~HF_GIF_MASK; /* Exit nested SVM mode */ - svm->nested_vmcb = 0; + svm->nested.vmcb = 0; - return 0; -} - -static int nested_svm_vmexit(struct vcpu_svm *svm) -{ - nsvm_printk("VMexit\n"); - if (nested_svm_do(svm, svm->nested_vmcb, 0, - NULL, nested_svm_vmexit_real)) - return 1; + nested_svm_unmap(nested_vmcb, KM_USER0); kvm_mmu_reset_context(&svm->vcpu); kvm_mmu_load(&svm->vcpu); @@ -1623,38 +1668,63 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) return 0; } -static int nested_svm_vmrun_msrpm(struct vcpu_svm *svm, void *arg1, - void *arg2, void *opaque) +static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) { + u32 *nested_msrpm; int i; - u32 *nested_msrpm = (u32*)arg1; + + nested_msrpm = nested_svm_map(svm, svm->nested.vmcb_msrpm, KM_USER0); + if (!nested_msrpm) + return false; + for (i=0; i< PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER) / 4; i++) - svm->nested_msrpm[i] = svm->msrpm[i] | nested_msrpm[i]; - svm->vmcb->control.msrpm_base_pa = __pa(svm->nested_msrpm); + svm->nested.msrpm[i] = svm->msrpm[i] | nested_msrpm[i]; - return 0; + svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm); + + nested_svm_unmap(nested_msrpm, KM_USER0); + + return true; } -static int nested_svm_vmrun(struct vcpu_svm *svm, void *arg1, - void *arg2, void *opaque) +static bool nested_svm_vmrun(struct vcpu_svm *svm) { - struct vmcb *nested_vmcb = (struct vmcb *)arg1; - struct vmcb *hsave = svm->hsave; + struct vmcb *nested_vmcb; + struct vmcb *hsave = svm->nested.hsave; + struct vmcb *vmcb = svm->vmcb; + + nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0); + if (!nested_vmcb) + return false; /* nested_vmcb is our indicator if nested SVM is activated */ - svm->nested_vmcb = svm->vmcb->save.rax; + svm->nested.vmcb = svm->vmcb->save.rax; /* Clear internal status */ - svm->vcpu.arch.exception.pending = false; + kvm_clear_exception_queue(&svm->vcpu); + kvm_clear_interrupt_queue(&svm->vcpu); /* Save the old vmcb, so we don't need to pick what we save, but can restore everything when a VMEXIT occurs */ - memcpy(hsave, svm->vmcb, sizeof(struct vmcb)); - /* We need to remember the original CR3 in the SPT case */ - if (!npt_enabled) - hsave->save.cr3 = svm->vcpu.arch.cr3; - hsave->save.cr4 = svm->vcpu.arch.cr4; - hsave->save.rip = svm->next_rip; + hsave->save.es = vmcb->save.es; + hsave->save.cs = vmcb->save.cs; + hsave->save.ss = vmcb->save.ss; + hsave->save.ds = vmcb->save.ds; + hsave->save.gdtr = vmcb->save.gdtr; + hsave->save.idtr = vmcb->save.idtr; + hsave->save.efer = svm->vcpu.arch.shadow_efer; + hsave->save.cr0 = svm->vcpu.arch.cr0; + hsave->save.cr4 = svm->vcpu.arch.cr4; + hsave->save.rflags = vmcb->save.rflags; + hsave->save.rip = svm->next_rip; + hsave->save.rsp = vmcb->save.rsp; + hsave->save.rax = vmcb->save.rax; + if (npt_enabled) + hsave->save.cr3 = vmcb->save.cr3; + else + hsave->save.cr3 = svm->vcpu.arch.cr3; + + copy_vmcb_control_area(hsave, vmcb); if (svm->vmcb->save.rflags & X86_EFLAGS_IF) svm->vcpu.arch.hflags |= HF_HIF_MASK; @@ -1679,7 +1749,7 @@ static int nested_svm_vmrun(struct vcpu_svm *svm, void *arg1, kvm_set_cr3(&svm->vcpu, nested_vmcb->save.cr3); kvm_mmu_reset_context(&svm->vcpu); } - svm->vmcb->save.cr2 = nested_vmcb->save.cr2; + svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = nested_vmcb->save.cr2; kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, nested_vmcb->save.rax); kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, nested_vmcb->save.rsp); kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, nested_vmcb->save.rip); @@ -1706,7 +1776,15 @@ static int nested_svm_vmrun(struct vcpu_svm *svm, void *arg1, svm->vmcb->control.intercept |= nested_vmcb->control.intercept; - svm->nested_vmcb_msrpm = nested_vmcb->control.msrpm_base_pa; + svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa; + + /* cache intercepts */ + svm->nested.intercept_cr_read = nested_vmcb->control.intercept_cr_read; + svm->nested.intercept_cr_write = nested_vmcb->control.intercept_cr_write; + svm->nested.intercept_dr_read = nested_vmcb->control.intercept_dr_read; + svm->nested.intercept_dr_write = nested_vmcb->control.intercept_dr_write; + svm->nested.intercept_exceptions = nested_vmcb->control.intercept_exceptions; + svm->nested.intercept = nested_vmcb->control.intercept; force_new_asid(&svm->vcpu); svm->vmcb->control.exit_int_info = nested_vmcb->control.exit_int_info; @@ -1734,12 +1812,14 @@ static int nested_svm_vmrun(struct vcpu_svm *svm, void *arg1, svm->vmcb->control.event_inj = nested_vmcb->control.event_inj; svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err; - svm->vcpu.arch.hflags |= HF_GIF_MASK; + nested_svm_unmap(nested_vmcb, KM_USER0); - return 0; + enable_gif(svm); + + return true; } -static int nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) +static void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) { to_vmcb->save.fs = from_vmcb->save.fs; to_vmcb->save.gs = from_vmcb->save.gs; @@ -1753,44 +1833,44 @@ static int nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) to_vmcb->save.sysenter_cs = from_vmcb->save.sysenter_cs; to_vmcb->save.sysenter_esp = from_vmcb->save.sysenter_esp; to_vmcb->save.sysenter_eip = from_vmcb->save.sysenter_eip; - - return 1; -} - -static int nested_svm_vmload(struct vcpu_svm *svm, void *nested_vmcb, - void *arg2, void *opaque) -{ - return nested_svm_vmloadsave((struct vmcb *)nested_vmcb, svm->vmcb); -} - -static int nested_svm_vmsave(struct vcpu_svm *svm, void *nested_vmcb, - void *arg2, void *opaque) -{ - return nested_svm_vmloadsave(svm->vmcb, (struct vmcb *)nested_vmcb); } static int vmload_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) { + struct vmcb *nested_vmcb; + if (nested_svm_check_permissions(svm)) return 1; svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; skip_emulated_instruction(&svm->vcpu); - nested_svm_do(svm, svm->vmcb->save.rax, 0, NULL, nested_svm_vmload); + nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0); + if (!nested_vmcb) + return 1; + + nested_svm_vmloadsave(nested_vmcb, svm->vmcb); + nested_svm_unmap(nested_vmcb, KM_USER0); return 1; } static int vmsave_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) { + struct vmcb *nested_vmcb; + if (nested_svm_check_permissions(svm)) return 1; svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; skip_emulated_instruction(&svm->vcpu); - nested_svm_do(svm, svm->vmcb->save.rax, 0, NULL, nested_svm_vmsave); + nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0); + if (!nested_vmcb) + return 1; + + nested_svm_vmloadsave(svm->vmcb, nested_vmcb); + nested_svm_unmap(nested_vmcb, KM_USER0); return 1; } @@ -1798,19 +1878,29 @@ static int vmsave_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) static int vmrun_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) { nsvm_printk("VMrun\n"); + if (nested_svm_check_permissions(svm)) return 1; svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; skip_emulated_instruction(&svm->vcpu); - if (nested_svm_do(svm, svm->vmcb->save.rax, 0, - NULL, nested_svm_vmrun)) + if (!nested_svm_vmrun(svm)) return 1; - if (nested_svm_do(svm, svm->nested_vmcb_msrpm, 0, - NULL, nested_svm_vmrun_msrpm)) - return 1; + if (!nested_svm_vmrun_msrpm(svm)) + goto failed; + + return 1; + +failed: + + svm->vmcb->control.exit_code = SVM_EXIT_ERR; + svm->vmcb->control.exit_code_hi = 0; + svm->vmcb->control.exit_info_1 = 0; + svm->vmcb->control.exit_info_2 = 0; + + nested_svm_vmexit(svm); return 1; } @@ -1823,7 +1913,7 @@ static int stgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; skip_emulated_instruction(&svm->vcpu); - svm->vcpu.arch.hflags |= HF_GIF_MASK; + enable_gif(svm); return 1; } @@ -1836,7 +1926,7 @@ static int clgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; skip_emulated_instruction(&svm->vcpu); - svm->vcpu.arch.hflags &= ~HF_GIF_MASK; + disable_gif(svm); /* After a CLGI no interrupts should come */ svm_clear_vintr(svm); @@ -1845,6 +1935,19 @@ static int clgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } +static int invlpga_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + nsvm_printk("INVLPGA\n"); + + /* Let's treat INVLPGA the same as INVLPG (can be optimized!) */ + kvm_mmu_invlpg(vcpu, vcpu->arch.regs[VCPU_REGS_RAX]); + + svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; + skip_emulated_instruction(&svm->vcpu); + return 1; +} + static int invalid_op_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) { @@ -1953,7 +2056,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) struct vcpu_svm *svm = to_svm(vcpu); switch (ecx) { - case MSR_IA32_TIME_STAMP_COUNTER: { + case MSR_IA32_TSC: { u64 tsc; rdtscll(tsc); @@ -1981,10 +2084,10 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) *data = svm->vmcb->save.sysenter_cs; break; case MSR_IA32_SYSENTER_EIP: - *data = svm->vmcb->save.sysenter_eip; + *data = svm->sysenter_eip; break; case MSR_IA32_SYSENTER_ESP: - *data = svm->vmcb->save.sysenter_esp; + *data = svm->sysenter_esp; break; /* Nobody will change the following 5 values in the VMCB so we can safely return them on rdmsr. They will always be 0 @@ -2005,7 +2108,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) *data = svm->vmcb->save.last_excp_to; break; case MSR_VM_HSAVE_PA: - *data = svm->hsave_msr; + *data = svm->nested.hsave_msr; break; case MSR_VM_CR: *data = 0; @@ -2027,8 +2130,7 @@ static int rdmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) if (svm_get_msr(&svm->vcpu, ecx, &data)) kvm_inject_gp(&svm->vcpu, 0); else { - KVMTRACE_3D(MSR_READ, &svm->vcpu, ecx, (u32)data, - (u32)(data >> 32), handler); + trace_kvm_msr_read(ecx, data); svm->vcpu.arch.regs[VCPU_REGS_RAX] = data & 0xffffffff; svm->vcpu.arch.regs[VCPU_REGS_RDX] = data >> 32; @@ -2043,7 +2145,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) struct vcpu_svm *svm = to_svm(vcpu); switch (ecx) { - case MSR_IA32_TIME_STAMP_COUNTER: { + case MSR_IA32_TSC: { u64 tsc; rdtscll(tsc); @@ -2071,9 +2173,11 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) svm->vmcb->save.sysenter_cs = data; break; case MSR_IA32_SYSENTER_EIP: + svm->sysenter_eip = data; svm->vmcb->save.sysenter_eip = data; break; case MSR_IA32_SYSENTER_ESP: + svm->sysenter_esp = data; svm->vmcb->save.sysenter_esp = data; break; case MSR_IA32_DEBUGCTLMSR: @@ -2091,24 +2195,12 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) else svm_disable_lbrv(svm); break; - case MSR_K7_EVNTSEL0: - case MSR_K7_EVNTSEL1: - case MSR_K7_EVNTSEL2: - case MSR_K7_EVNTSEL3: - case MSR_K7_PERFCTR0: - case MSR_K7_PERFCTR1: - case MSR_K7_PERFCTR2: - case MSR_K7_PERFCTR3: - /* - * Just discard all writes to the performance counters; this - * should keep both older linux and windows 64-bit guests - * happy - */ - pr_unimpl(vcpu, "unimplemented perfctr wrmsr: 0x%x data 0x%llx\n", ecx, data); - - break; case MSR_VM_HSAVE_PA: - svm->hsave_msr = data; + svm->nested.hsave_msr = data; + break; + case MSR_VM_CR: + case MSR_VM_IGNNE: + pr_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); break; default: return kvm_set_msr_common(vcpu, ecx, data); @@ -2122,8 +2214,7 @@ static int wrmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) 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); + trace_kvm_msr_write(ecx, data); svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; if (svm_set_msr(&svm->vcpu, ecx, data)) @@ -2144,8 +2235,6 @@ static int msr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) static int interrupt_window_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) { - KVMTRACE_0D(PEND_INTR, &svm->vcpu, handler); - svm_clear_vintr(svm); svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; /* @@ -2201,7 +2290,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm, [SVM_EXIT_INVD] = emulate_on_interception, [SVM_EXIT_HLT] = halt_interception, [SVM_EXIT_INVLPG] = invlpg_interception, - [SVM_EXIT_INVLPGA] = invalid_op_interception, + [SVM_EXIT_INVLPGA] = invlpga_interception, [SVM_EXIT_IOIO] = io_interception, [SVM_EXIT_MSR] = msr_interception, [SVM_EXIT_TASK_SWITCH] = task_switch_interception, @@ -2224,20 +2313,26 @@ static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); u32 exit_code = svm->vmcb->control.exit_code; - KVMTRACE_3D(VMEXIT, vcpu, exit_code, (u32)svm->vmcb->save.rip, - (u32)((u64)svm->vmcb->save.rip >> 32), entryexit); + trace_kvm_exit(exit_code, svm->vmcb->save.rip); if (is_nested(svm)) { + int vmexit; + nsvm_printk("nested handle_exit: 0x%x | 0x%lx | 0x%lx | 0x%lx\n", exit_code, svm->vmcb->control.exit_info_1, svm->vmcb->control.exit_info_2, svm->vmcb->save.rip); - if (nested_svm_exit_handled(svm, true)) { - nested_svm_vmexit(svm); - nsvm_printk("-> #VMEXIT\n"); + + vmexit = nested_svm_exit_special(svm); + + if (vmexit == NESTED_EXIT_CONTINUE) + vmexit = nested_svm_exit_handled(svm); + + if (vmexit == NESTED_EXIT_DONE) return 1; - } } + svm_complete_interrupts(svm); + if (npt_enabled) { int mmu_reload = 0; if ((vcpu->arch.cr0 ^ svm->vmcb->save.cr0) & X86_CR0_PG) { @@ -2246,12 +2341,6 @@ static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) } vcpu->arch.cr0 = svm->vmcb->save.cr0; vcpu->arch.cr3 = svm->vmcb->save.cr3; - if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) { - if (!load_pdptrs(vcpu, vcpu->arch.cr3)) { - kvm_inject_gp(vcpu, 0); - return 1; - } - } if (mmu_reload) { kvm_mmu_reset_context(vcpu); kvm_mmu_load(vcpu); @@ -2319,7 +2408,7 @@ static inline void svm_inject_irq(struct vcpu_svm *svm, int irq) { struct vmcb_control_area *control; - KVMTRACE_1D(INJ_VIRQ, &svm->vcpu, (u32)irq, handler); + trace_kvm_inj_virq(irq); ++svm->vcpu.stat.irq_injections; control = &svm->vmcb->control; @@ -2329,21 +2418,14 @@ static inline void svm_inject_irq(struct vcpu_svm *svm, int irq) ((/*control->int_vector >> 4*/ 0xf) << V_INTR_PRIO_SHIFT); } -static void svm_queue_irq(struct kvm_vcpu *vcpu, unsigned nr) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - svm->vmcb->control.event_inj = nr | - SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR; -} - static void svm_set_irq(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - nested_svm_intr(svm); + BUG_ON(!(gif_set(svm))); - svm_queue_irq(vcpu, vcpu->arch.interrupt.nr); + svm->vmcb->control.event_inj = vcpu->arch.interrupt.nr | + SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR; } static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) @@ -2371,13 +2453,25 @@ static int svm_interrupt_allowed(struct kvm_vcpu *vcpu) struct vmcb *vmcb = svm->vmcb; return (vmcb->save.rflags & X86_EFLAGS_IF) && !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) && - (svm->vcpu.arch.hflags & HF_GIF_MASK); + gif_set(svm) && + !(is_nested(svm) && (svm->vcpu.arch.hflags & HF_VINTR_MASK)); } static void enable_irq_window(struct kvm_vcpu *vcpu) { - svm_set_vintr(to_svm(vcpu)); - svm_inject_irq(to_svm(vcpu), 0x0); + struct vcpu_svm *svm = to_svm(vcpu); + nsvm_printk("Trying to open IRQ window\n"); + + nested_svm_intr(svm); + + /* In case GIF=0 we can't rely on the CPU to tell us when + * GIF becomes 1, because that's a separate STGI/VMRUN intercept. + * The next time we get that intercept, this function will be + * called again though and we'll get the vintr intercept. */ + if (gif_set(svm)) { + svm_set_vintr(svm); + svm_inject_irq(svm, 0x0); + } } static void enable_nmi_window(struct kvm_vcpu *vcpu) @@ -2456,6 +2550,8 @@ static void svm_complete_interrupts(struct vcpu_svm *svm) case SVM_EXITINTINFO_TYPE_EXEPT: /* In case of software exception do not reinject an exception vector, but re-execute and instruction instead */ + if (is_nested(svm)) + break; if (kvm_exception_is_soft(vector)) break; if (exitintinfo & SVM_EXITINTINFO_VALID_ERR) { @@ -2498,9 +2594,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) fs_selector = kvm_read_fs(); gs_selector = kvm_read_gs(); ldt_selector = kvm_read_ldt(); - svm->host_cr2 = kvm_read_cr2(); - if (!is_nested(svm)) - svm->vmcb->save.cr2 = vcpu->arch.cr2; + svm->vmcb->save.cr2 = vcpu->arch.cr2; /* required for live migration with NPT */ if (npt_enabled) svm->vmcb->save.cr3 = vcpu->arch.cr3; @@ -2585,8 +2679,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; - kvm_write_cr2(svm->host_cr2); - kvm_load_fs(fs_selector); kvm_load_gs(gs_selector); kvm_load_ldt(ldt_selector); @@ -2602,7 +2694,10 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) svm->next_rip = 0; - svm_complete_interrupts(svm); + if (npt_enabled) { + vcpu->arch.regs_avail &= ~(1 << VCPU_EXREG_PDPTR); + vcpu->arch.regs_dirty &= ~(1 << VCPU_EXREG_PDPTR); + } } #undef R @@ -2673,6 +2768,64 @@ static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) return 0; } +static const struct trace_print_flags svm_exit_reasons_str[] = { + { SVM_EXIT_READ_CR0, "read_cr0" }, + { SVM_EXIT_READ_CR3, "read_cr3" }, + { SVM_EXIT_READ_CR4, "read_cr4" }, + { SVM_EXIT_READ_CR8, "read_cr8" }, + { SVM_EXIT_WRITE_CR0, "write_cr0" }, + { SVM_EXIT_WRITE_CR3, "write_cr3" }, + { SVM_EXIT_WRITE_CR4, "write_cr4" }, + { SVM_EXIT_WRITE_CR8, "write_cr8" }, + { SVM_EXIT_READ_DR0, "read_dr0" }, + { SVM_EXIT_READ_DR1, "read_dr1" }, + { SVM_EXIT_READ_DR2, "read_dr2" }, + { SVM_EXIT_READ_DR3, "read_dr3" }, + { SVM_EXIT_WRITE_DR0, "write_dr0" }, + { SVM_EXIT_WRITE_DR1, "write_dr1" }, + { SVM_EXIT_WRITE_DR2, "write_dr2" }, + { SVM_EXIT_WRITE_DR3, "write_dr3" }, + { SVM_EXIT_WRITE_DR5, "write_dr5" }, + { SVM_EXIT_WRITE_DR7, "write_dr7" }, + { SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" }, + { SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" }, + { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, + { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, + { SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, + { SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, + { SVM_EXIT_INTR, "interrupt" }, + { SVM_EXIT_NMI, "nmi" }, + { SVM_EXIT_SMI, "smi" }, + { SVM_EXIT_INIT, "init" }, + { SVM_EXIT_VINTR, "vintr" }, + { SVM_EXIT_CPUID, "cpuid" }, + { SVM_EXIT_INVD, "invd" }, + { SVM_EXIT_HLT, "hlt" }, + { SVM_EXIT_INVLPG, "invlpg" }, + { SVM_EXIT_INVLPGA, "invlpga" }, + { SVM_EXIT_IOIO, "io" }, + { SVM_EXIT_MSR, "msr" }, + { SVM_EXIT_TASK_SWITCH, "task_switch" }, + { SVM_EXIT_SHUTDOWN, "shutdown" }, + { SVM_EXIT_VMRUN, "vmrun" }, + { SVM_EXIT_VMMCALL, "hypercall" }, + { SVM_EXIT_VMLOAD, "vmload" }, + { SVM_EXIT_VMSAVE, "vmsave" }, + { SVM_EXIT_STGI, "stgi" }, + { SVM_EXIT_CLGI, "clgi" }, + { SVM_EXIT_SKINIT, "skinit" }, + { SVM_EXIT_WBINVD, "wbinvd" }, + { SVM_EXIT_MONITOR, "monitor" }, + { SVM_EXIT_MWAIT, "mwait" }, + { SVM_EXIT_NPF, "npf" }, + { -1, NULL } +}; + +static bool svm_gb_page_enable(void) +{ + return true; +} + static struct kvm_x86_ops svm_x86_ops = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, @@ -2710,6 +2863,7 @@ static struct kvm_x86_ops svm_x86_ops = { .set_gdt = svm_set_gdt, .get_dr = svm_get_dr, .set_dr = svm_set_dr, + .cache_reg = svm_cache_reg, .get_rflags = svm_get_rflags, .set_rflags = svm_set_rflags, @@ -2733,6 +2887,9 @@ static struct kvm_x86_ops svm_x86_ops = { .set_tss_addr = svm_set_tss_addr, .get_tdp_level = get_npt_level, .get_mt_mask = svm_get_mt_mask, + + .exit_reasons_str = svm_exit_reasons_str, + .gb_page_enable = svm_gb_page_enable, }; static int __init svm_init(void) diff --git a/arch/x86/kvm/timer.c b/arch/x86/kvm/timer.c index 86dbac072d0c..eea40439066c 100644 --- a/arch/x86/kvm/timer.c +++ b/arch/x86/kvm/timer.c @@ -9,12 +9,16 @@ static int __kvm_timer_fn(struct kvm_vcpu *vcpu, struct kvm_timer *ktimer) int restart_timer = 0; wait_queue_head_t *q = &vcpu->wq; - /* FIXME: this code should not know anything about vcpus */ - if (!atomic_inc_and_test(&ktimer->pending)) + /* + * There is a race window between reading and incrementing, but we do + * not care about potentially loosing timer events in the !reinject + * case anyway. + */ + if (ktimer->reinject || !atomic_read(&ktimer->pending)) { + atomic_inc(&ktimer->pending); + /* FIXME: this code should not know anything about vcpus */ set_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests); - - if (!ktimer->reinject) - atomic_set(&ktimer->pending, 1); + } if (waitqueue_active(q)) wake_up_interruptible(q); @@ -33,7 +37,7 @@ enum hrtimer_restart kvm_timer_fn(struct hrtimer *data) struct kvm_vcpu *vcpu; struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer); - vcpu = ktimer->kvm->vcpus[ktimer->vcpu_id]; + vcpu = ktimer->vcpu; if (!vcpu) return HRTIMER_NORESTART; diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h new file mode 100644 index 000000000000..0d480e77eacf --- /dev/null +++ b/arch/x86/kvm/trace.h @@ -0,0 +1,355 @@ +#if !defined(_TRACE_KVM_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_KVM_H + +#include <linux/tracepoint.h> + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM kvm +#define TRACE_INCLUDE_PATH arch/x86/kvm +#define TRACE_INCLUDE_FILE trace + +/* + * Tracepoint for guest mode entry. + */ +TRACE_EVENT(kvm_entry, + TP_PROTO(unsigned int vcpu_id), + TP_ARGS(vcpu_id), + + TP_STRUCT__entry( + __field( unsigned int, vcpu_id ) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + ), + + TP_printk("vcpu %u", __entry->vcpu_id) +); + +/* + * Tracepoint for hypercall. + */ +TRACE_EVENT(kvm_hypercall, + TP_PROTO(unsigned long nr, unsigned long a0, unsigned long a1, + unsigned long a2, unsigned long a3), + TP_ARGS(nr, a0, a1, a2, a3), + + TP_STRUCT__entry( + __field( unsigned long, nr ) + __field( unsigned long, a0 ) + __field( unsigned long, a1 ) + __field( unsigned long, a2 ) + __field( unsigned long, a3 ) + ), + + TP_fast_assign( + __entry->nr = nr; + __entry->a0 = a0; + __entry->a1 = a1; + __entry->a2 = a2; + __entry->a3 = a3; + ), + + TP_printk("nr 0x%lx a0 0x%lx a1 0x%lx a2 0x%lx a3 0x%lx", + __entry->nr, __entry->a0, __entry->a1, __entry->a2, + __entry->a3) +); + +/* + * Tracepoint for PIO. + */ +TRACE_EVENT(kvm_pio, + TP_PROTO(unsigned int rw, unsigned int port, unsigned int size, + unsigned int count), + TP_ARGS(rw, port, size, count), + + TP_STRUCT__entry( + __field( unsigned int, rw ) + __field( unsigned int, port ) + __field( unsigned int, size ) + __field( unsigned int, count ) + ), + + TP_fast_assign( + __entry->rw = rw; + __entry->port = port; + __entry->size = size; + __entry->count = count; + ), + + TP_printk("pio_%s at 0x%x size %d count %d", + __entry->rw ? "write" : "read", + __entry->port, __entry->size, __entry->count) +); + +/* + * Tracepoint for cpuid. + */ +TRACE_EVENT(kvm_cpuid, + TP_PROTO(unsigned int function, unsigned long rax, unsigned long rbx, + unsigned long rcx, unsigned long rdx), + TP_ARGS(function, rax, rbx, rcx, rdx), + + TP_STRUCT__entry( + __field( unsigned int, function ) + __field( unsigned long, rax ) + __field( unsigned long, rbx ) + __field( unsigned long, rcx ) + __field( unsigned long, rdx ) + ), + + TP_fast_assign( + __entry->function = function; + __entry->rax = rax; + __entry->rbx = rbx; + __entry->rcx = rcx; + __entry->rdx = rdx; + ), + + TP_printk("func %x rax %lx rbx %lx rcx %lx rdx %lx", + __entry->function, __entry->rax, + __entry->rbx, __entry->rcx, __entry->rdx) +); + +#define AREG(x) { APIC_##x, "APIC_" #x } + +#define kvm_trace_symbol_apic \ + AREG(ID), AREG(LVR), AREG(TASKPRI), AREG(ARBPRI), AREG(PROCPRI), \ + AREG(EOI), AREG(RRR), AREG(LDR), AREG(DFR), AREG(SPIV), AREG(ISR), \ + AREG(TMR), AREG(IRR), AREG(ESR), AREG(ICR), AREG(ICR2), AREG(LVTT), \ + AREG(LVTTHMR), AREG(LVTPC), AREG(LVT0), AREG(LVT1), AREG(LVTERR), \ + AREG(TMICT), AREG(TMCCT), AREG(TDCR), AREG(SELF_IPI), AREG(EFEAT), \ + AREG(ECTRL) +/* + * Tracepoint for apic access. + */ +TRACE_EVENT(kvm_apic, + TP_PROTO(unsigned int rw, unsigned int reg, unsigned int val), + TP_ARGS(rw, reg, val), + + TP_STRUCT__entry( + __field( unsigned int, rw ) + __field( unsigned int, reg ) + __field( unsigned int, val ) + ), + + TP_fast_assign( + __entry->rw = rw; + __entry->reg = reg; + __entry->val = val; + ), + + TP_printk("apic_%s %s = 0x%x", + __entry->rw ? "write" : "read", + __print_symbolic(__entry->reg, kvm_trace_symbol_apic), + __entry->val) +); + +#define trace_kvm_apic_read(reg, val) trace_kvm_apic(0, reg, val) +#define trace_kvm_apic_write(reg, val) trace_kvm_apic(1, reg, val) + +/* + * Tracepoint for kvm guest exit: + */ +TRACE_EVENT(kvm_exit, + TP_PROTO(unsigned int exit_reason, unsigned long guest_rip), + TP_ARGS(exit_reason, guest_rip), + + TP_STRUCT__entry( + __field( unsigned int, exit_reason ) + __field( unsigned long, guest_rip ) + ), + + TP_fast_assign( + __entry->exit_reason = exit_reason; + __entry->guest_rip = guest_rip; + ), + + TP_printk("reason %s rip 0x%lx", + ftrace_print_symbols_seq(p, __entry->exit_reason, + kvm_x86_ops->exit_reasons_str), + __entry->guest_rip) +); + +/* + * Tracepoint for kvm interrupt injection: + */ +TRACE_EVENT(kvm_inj_virq, + TP_PROTO(unsigned int irq), + TP_ARGS(irq), + + TP_STRUCT__entry( + __field( unsigned int, irq ) + ), + + TP_fast_assign( + __entry->irq = irq; + ), + + TP_printk("irq %u", __entry->irq) +); + +/* + * Tracepoint for page fault. + */ +TRACE_EVENT(kvm_page_fault, + TP_PROTO(unsigned long fault_address, unsigned int error_code), + TP_ARGS(fault_address, error_code), + + TP_STRUCT__entry( + __field( unsigned long, fault_address ) + __field( unsigned int, error_code ) + ), + + TP_fast_assign( + __entry->fault_address = fault_address; + __entry->error_code = error_code; + ), + + TP_printk("address %lx error_code %x", + __entry->fault_address, __entry->error_code) +); + +/* + * Tracepoint for guest MSR access. + */ +TRACE_EVENT(kvm_msr, + TP_PROTO(unsigned int rw, unsigned int ecx, unsigned long data), + TP_ARGS(rw, ecx, data), + + TP_STRUCT__entry( + __field( unsigned int, rw ) + __field( unsigned int, ecx ) + __field( unsigned long, data ) + ), + + TP_fast_assign( + __entry->rw = rw; + __entry->ecx = ecx; + __entry->data = data; + ), + + TP_printk("msr_%s %x = 0x%lx", + __entry->rw ? "write" : "read", + __entry->ecx, __entry->data) +); + +#define trace_kvm_msr_read(ecx, data) trace_kvm_msr(0, ecx, data) +#define trace_kvm_msr_write(ecx, data) trace_kvm_msr(1, ecx, data) + +/* + * Tracepoint for guest CR access. + */ +TRACE_EVENT(kvm_cr, + TP_PROTO(unsigned int rw, unsigned int cr, unsigned long val), + TP_ARGS(rw, cr, val), + + TP_STRUCT__entry( + __field( unsigned int, rw ) + __field( unsigned int, cr ) + __field( unsigned long, val ) + ), + + TP_fast_assign( + __entry->rw = rw; + __entry->cr = cr; + __entry->val = val; + ), + + TP_printk("cr_%s %x = 0x%lx", + __entry->rw ? "write" : "read", + __entry->cr, __entry->val) +); + +#define trace_kvm_cr_read(cr, val) trace_kvm_cr(0, cr, val) +#define trace_kvm_cr_write(cr, val) trace_kvm_cr(1, cr, val) + +TRACE_EVENT(kvm_pic_set_irq, + TP_PROTO(__u8 chip, __u8 pin, __u8 elcr, __u8 imr, bool coalesced), + TP_ARGS(chip, pin, elcr, imr, coalesced), + + TP_STRUCT__entry( + __field( __u8, chip ) + __field( __u8, pin ) + __field( __u8, elcr ) + __field( __u8, imr ) + __field( bool, coalesced ) + ), + + TP_fast_assign( + __entry->chip = chip; + __entry->pin = pin; + __entry->elcr = elcr; + __entry->imr = imr; + __entry->coalesced = coalesced; + ), + + TP_printk("chip %u pin %u (%s%s)%s", + __entry->chip, __entry->pin, + (__entry->elcr & (1 << __entry->pin)) ? "level":"edge", + (__entry->imr & (1 << __entry->pin)) ? "|masked":"", + __entry->coalesced ? " (coalesced)" : "") +); + +#define kvm_apic_dst_shorthand \ + {0x0, "dst"}, \ + {0x1, "self"}, \ + {0x2, "all"}, \ + {0x3, "all-but-self"} + +TRACE_EVENT(kvm_apic_ipi, + TP_PROTO(__u32 icr_low, __u32 dest_id), + TP_ARGS(icr_low, dest_id), + + TP_STRUCT__entry( + __field( __u32, icr_low ) + __field( __u32, dest_id ) + ), + + TP_fast_assign( + __entry->icr_low = icr_low; + __entry->dest_id = dest_id; + ), + + TP_printk("dst %x vec %u (%s|%s|%s|%s|%s)", + __entry->dest_id, (u8)__entry->icr_low, + __print_symbolic((__entry->icr_low >> 8 & 0x7), + kvm_deliver_mode), + (__entry->icr_low & (1<<11)) ? "logical" : "physical", + (__entry->icr_low & (1<<14)) ? "assert" : "de-assert", + (__entry->icr_low & (1<<15)) ? "level" : "edge", + __print_symbolic((__entry->icr_low >> 18 & 0x3), + kvm_apic_dst_shorthand)) +); + +TRACE_EVENT(kvm_apic_accept_irq, + TP_PROTO(__u32 apicid, __u16 dm, __u8 tm, __u8 vec, bool coalesced), + TP_ARGS(apicid, dm, tm, vec, coalesced), + + TP_STRUCT__entry( + __field( __u32, apicid ) + __field( __u16, dm ) + __field( __u8, tm ) + __field( __u8, vec ) + __field( bool, coalesced ) + ), + + TP_fast_assign( + __entry->apicid = apicid; + __entry->dm = dm; + __entry->tm = tm; + __entry->vec = vec; + __entry->coalesced = coalesced; + ), + + TP_printk("apicid %x vec %u (%s|%s)%s", + __entry->apicid, __entry->vec, + __print_symbolic((__entry->dm >> 8 & 0x7), kvm_deliver_mode), + __entry->tm ? "level" : "edge", + __entry->coalesced ? " (coalesced)" : "") +); + +#endif /* _TRACE_KVM_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 29f912927a58..f3812014bd0b 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -25,6 +25,7 @@ #include <linux/highmem.h> #include <linux/sched.h> #include <linux/moduleparam.h> +#include <linux/ftrace_event.h> #include "kvm_cache_regs.h" #include "x86.h" @@ -34,6 +35,8 @@ #include <asm/virtext.h> #include <asm/mce.h> +#include "trace.h" + #define __ex(x) __kvm_handle_fault_on_reboot(x) MODULE_AUTHOR("Qumranet"); @@ -51,6 +54,10 @@ module_param_named(flexpriority, flexpriority_enabled, bool, S_IRUGO); static int __read_mostly enable_ept = 1; module_param_named(ept, enable_ept, bool, S_IRUGO); +static int __read_mostly enable_unrestricted_guest = 1; +module_param_named(unrestricted_guest, + enable_unrestricted_guest, bool, S_IRUGO); + static int __read_mostly emulate_invalid_guest_state = 0; module_param(emulate_invalid_guest_state, bool, S_IRUGO); @@ -84,6 +91,14 @@ struct vcpu_vmx { int guest_efer_loaded; } host_state; struct { + int vm86_active; + u8 save_iopl; + struct kvm_save_segment { + u16 selector; + unsigned long base; + u32 limit; + u32 ar; + } tr, es, ds, fs, gs; struct { bool pending; u8 vector; @@ -161,6 +176,8 @@ static struct kvm_vmx_segment_field { VMX_SEGMENT_FIELD(LDTR), }; +static void ept_save_pdptrs(struct kvm_vcpu *vcpu); + /* * Keep MSR_K6_STAR at the end, as setup_msrs() will try to optimize it * away by decrementing the array size. @@ -256,6 +273,26 @@ static inline bool cpu_has_vmx_flexpriority(void) cpu_has_vmx_virtualize_apic_accesses(); } +static inline bool cpu_has_vmx_ept_execute_only(void) +{ + return !!(vmx_capability.ept & VMX_EPT_EXECUTE_ONLY_BIT); +} + +static inline bool cpu_has_vmx_eptp_uncacheable(void) +{ + return !!(vmx_capability.ept & VMX_EPTP_UC_BIT); +} + +static inline bool cpu_has_vmx_eptp_writeback(void) +{ + return !!(vmx_capability.ept & VMX_EPTP_WB_BIT); +} + +static inline bool cpu_has_vmx_ept_2m_page(void) +{ + return !!(vmx_capability.ept & VMX_EPT_2MB_PAGE_BIT); +} + static inline int cpu_has_vmx_invept_individual_addr(void) { return !!(vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT); @@ -277,6 +314,12 @@ static inline int cpu_has_vmx_ept(void) SECONDARY_EXEC_ENABLE_EPT; } +static inline int cpu_has_vmx_unrestricted_guest(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_UNRESTRICTED_GUEST; +} + static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm) { return flexpriority_enabled && @@ -497,14 +540,16 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR); if (!vcpu->fpu_active) eb |= 1u << NM_VECTOR; + /* + * Unconditionally intercept #DB so we can maintain dr6 without + * reading it every exit. + */ + eb |= 1u << DB_VECTOR; if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) { - if (vcpu->guest_debug & - (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) - eb |= 1u << DB_VECTOR; if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) eb |= 1u << BP_VECTOR; } - if (vcpu->arch.rmode.vm86_active) + if (to_vmx(vcpu)->rmode.vm86_active) eb = ~0; if (enable_ept) eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */ @@ -528,12 +573,15 @@ static void reload_tss(void) static void load_transition_efer(struct vcpu_vmx *vmx) { int efer_offset = vmx->msr_offset_efer; - u64 host_efer = vmx->host_msrs[efer_offset].data; - u64 guest_efer = vmx->guest_msrs[efer_offset].data; + u64 host_efer; + u64 guest_efer; u64 ignore_bits; if (efer_offset < 0) return; + host_efer = vmx->host_msrs[efer_offset].data; + guest_efer = vmx->guest_msrs[efer_offset].data; + /* * NX is emulated; LMA and LME handled by hardware; SCE meaninless * outside long mode @@ -735,12 +783,17 @@ static void vmx_fpu_deactivate(struct kvm_vcpu *vcpu) static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu) { - return vmcs_readl(GUEST_RFLAGS); + unsigned long rflags; + + rflags = vmcs_readl(GUEST_RFLAGS); + if (to_vmx(vcpu)->rmode.vm86_active) + rflags &= ~(unsigned long)(X86_EFLAGS_IOPL | X86_EFLAGS_VM); + return rflags; } static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { - if (vcpu->arch.rmode.vm86_active) + if (to_vmx(vcpu)->rmode.vm86_active) rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM; vmcs_writel(GUEST_RFLAGS, rflags); } @@ -797,12 +850,13 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, intr_info |= INTR_INFO_DELIVER_CODE_MASK; } - if (vcpu->arch.rmode.vm86_active) { + if (vmx->rmode.vm86_active) { vmx->rmode.irq.pending = true; vmx->rmode.irq.vector = nr; vmx->rmode.irq.rip = kvm_rip_read(vcpu); - if (nr == BP_VECTOR || nr == OF_VECTOR) - vmx->rmode.irq.rip++; + if (kvm_exception_is_soft(nr)) + vmx->rmode.irq.rip += + vmx->vcpu.arch.event_exit_inst_len; intr_info |= INTR_TYPE_SOFT_INTR; vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info); vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1); @@ -940,7 +994,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) case MSR_EFER: return kvm_get_msr_common(vcpu, msr_index, pdata); #endif - case MSR_IA32_TIME_STAMP_COUNTER: + case MSR_IA32_TSC: data = guest_read_tsc(); break; case MSR_IA32_SYSENTER_CS: @@ -953,9 +1007,9 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) data = vmcs_readl(GUEST_SYSENTER_ESP); break; default: - vmx_load_host_state(to_vmx(vcpu)); msr = find_msr_entry(to_vmx(vcpu), msr_index); if (msr) { + vmx_load_host_state(to_vmx(vcpu)); data = msr->data; break; } @@ -1000,22 +1054,10 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) case MSR_IA32_SYSENTER_ESP: vmcs_writel(GUEST_SYSENTER_ESP, data); break; - case MSR_IA32_TIME_STAMP_COUNTER: + case MSR_IA32_TSC: rdtscll(host_tsc); guest_write_tsc(data, host_tsc); break; - case MSR_P6_PERFCTR0: - case MSR_P6_PERFCTR1: - case MSR_P6_EVNTSEL0: - case MSR_P6_EVNTSEL1: - /* - * Just discard all writes to the performance counters; this - * should keep both older linux and windows 64-bit guests - * happy - */ - pr_unimpl(vcpu, "unimplemented perfctr wrmsr: 0x%x data 0x%llx\n", msr_index, data); - - break; case MSR_IA32_CR_PAT: if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { vmcs_write64(GUEST_IA32_PAT, data); @@ -1024,9 +1066,9 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) } /* Otherwise falls through to kvm_set_msr_common */ default: - vmx_load_host_state(vmx); msr = find_msr_entry(vmx, msr_index); if (msr) { + vmx_load_host_state(vmx); msr->data = data; break; } @@ -1046,6 +1088,10 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) case VCPU_REGS_RIP: vcpu->arch.regs[VCPU_REGS_RIP] = vmcs_readl(GUEST_RIP); break; + case VCPU_EXREG_PDPTR: + if (enable_ept) + ept_save_pdptrs(vcpu); + break; default: break; } @@ -1203,7 +1249,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) opt2 = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_WBINVD_EXITING | SECONDARY_EXEC_ENABLE_VPID | - SECONDARY_EXEC_ENABLE_EPT; + SECONDARY_EXEC_ENABLE_EPT | + SECONDARY_EXEC_UNRESTRICTED_GUEST; if (adjust_vmx_controls(min2, opt2, MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control) < 0) @@ -1217,12 +1264,9 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) if (_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) { /* CR3 accesses and invlpg don't need to cause VM Exits when EPT enabled */ - min &= ~(CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_CR3_STORE_EXITING | - CPU_BASED_INVLPG_EXITING); - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS, - &_cpu_based_exec_control) < 0) - return -EIO; + _cpu_based_exec_control &= ~(CPU_BASED_CR3_LOAD_EXITING | + CPU_BASED_CR3_STORE_EXITING | + CPU_BASED_INVLPG_EXITING); rdmsr(MSR_IA32_VMX_EPT_VPID_CAP, vmx_capability.ept, vmx_capability.vpid); } @@ -1333,8 +1377,13 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_vpid()) enable_vpid = 0; - if (!cpu_has_vmx_ept()) + if (!cpu_has_vmx_ept()) { enable_ept = 0; + enable_unrestricted_guest = 0; + } + + if (!cpu_has_vmx_unrestricted_guest()) + enable_unrestricted_guest = 0; if (!cpu_has_vmx_flexpriority()) flexpriority_enabled = 0; @@ -1342,6 +1391,9 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_tpr_shadow()) kvm_x86_ops->update_cr8_intercept = NULL; + if (enable_ept && !cpu_has_vmx_ept_2m_page()) + kvm_disable_largepages(); + return alloc_kvm_area(); } @@ -1372,15 +1424,15 @@ static void enter_pmode(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); vmx->emulation_required = 1; - vcpu->arch.rmode.vm86_active = 0; + vmx->rmode.vm86_active = 0; - vmcs_writel(GUEST_TR_BASE, vcpu->arch.rmode.tr.base); - vmcs_write32(GUEST_TR_LIMIT, vcpu->arch.rmode.tr.limit); - vmcs_write32(GUEST_TR_AR_BYTES, vcpu->arch.rmode.tr.ar); + vmcs_writel(GUEST_TR_BASE, vmx->rmode.tr.base); + vmcs_write32(GUEST_TR_LIMIT, vmx->rmode.tr.limit); + vmcs_write32(GUEST_TR_AR_BYTES, vmx->rmode.tr.ar); flags = vmcs_readl(GUEST_RFLAGS); flags &= ~(X86_EFLAGS_IOPL | X86_EFLAGS_VM); - flags |= (vcpu->arch.rmode.save_iopl << IOPL_SHIFT); + flags |= (vmx->rmode.save_iopl << IOPL_SHIFT); vmcs_writel(GUEST_RFLAGS, flags); vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) | @@ -1391,10 +1443,10 @@ static void enter_pmode(struct kvm_vcpu *vcpu) if (emulate_invalid_guest_state) return; - fix_pmode_dataseg(VCPU_SREG_ES, &vcpu->arch.rmode.es); - fix_pmode_dataseg(VCPU_SREG_DS, &vcpu->arch.rmode.ds); - fix_pmode_dataseg(VCPU_SREG_GS, &vcpu->arch.rmode.gs); - fix_pmode_dataseg(VCPU_SREG_FS, &vcpu->arch.rmode.fs); + fix_pmode_dataseg(VCPU_SREG_ES, &vmx->rmode.es); + fix_pmode_dataseg(VCPU_SREG_DS, &vmx->rmode.ds); + fix_pmode_dataseg(VCPU_SREG_GS, &vmx->rmode.gs); + fix_pmode_dataseg(VCPU_SREG_FS, &vmx->rmode.fs); vmcs_write16(GUEST_SS_SELECTOR, 0); vmcs_write32(GUEST_SS_AR_BYTES, 0x93); @@ -1433,20 +1485,23 @@ static void enter_rmode(struct kvm_vcpu *vcpu) unsigned long flags; struct vcpu_vmx *vmx = to_vmx(vcpu); + if (enable_unrestricted_guest) + return; + vmx->emulation_required = 1; - vcpu->arch.rmode.vm86_active = 1; + vmx->rmode.vm86_active = 1; - vcpu->arch.rmode.tr.base = vmcs_readl(GUEST_TR_BASE); + vmx->rmode.tr.base = vmcs_readl(GUEST_TR_BASE); vmcs_writel(GUEST_TR_BASE, rmode_tss_base(vcpu->kvm)); - vcpu->arch.rmode.tr.limit = vmcs_read32(GUEST_TR_LIMIT); + vmx->rmode.tr.limit = vmcs_read32(GUEST_TR_LIMIT); vmcs_write32(GUEST_TR_LIMIT, RMODE_TSS_SIZE - 1); - vcpu->arch.rmode.tr.ar = vmcs_read32(GUEST_TR_AR_BYTES); + vmx->rmode.tr.ar = vmcs_read32(GUEST_TR_AR_BYTES); vmcs_write32(GUEST_TR_AR_BYTES, 0x008b); flags = vmcs_readl(GUEST_RFLAGS); - vcpu->arch.rmode.save_iopl + vmx->rmode.save_iopl = (flags & X86_EFLAGS_IOPL) >> IOPL_SHIFT; flags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM; @@ -1468,10 +1523,10 @@ static void enter_rmode(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_CS_BASE, 0xf0000); vmcs_write16(GUEST_CS_SELECTOR, vmcs_readl(GUEST_CS_BASE) >> 4); - fix_rmode_seg(VCPU_SREG_ES, &vcpu->arch.rmode.es); - fix_rmode_seg(VCPU_SREG_DS, &vcpu->arch.rmode.ds); - fix_rmode_seg(VCPU_SREG_GS, &vcpu->arch.rmode.gs); - fix_rmode_seg(VCPU_SREG_FS, &vcpu->arch.rmode.fs); + fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.es); + fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.ds); + fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.gs); + fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.fs); continue_rmode: kvm_mmu_reset_context(vcpu); @@ -1545,11 +1600,11 @@ static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) static void ept_load_pdptrs(struct kvm_vcpu *vcpu) { + if (!test_bit(VCPU_EXREG_PDPTR, + (unsigned long *)&vcpu->arch.regs_dirty)) + return; + if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) { - if (!load_pdptrs(vcpu, vcpu->arch.cr3)) { - printk(KERN_ERR "EPT: Fail to load pdptrs!\n"); - return; - } vmcs_write64(GUEST_PDPTR0, vcpu->arch.pdptrs[0]); vmcs_write64(GUEST_PDPTR1, vcpu->arch.pdptrs[1]); vmcs_write64(GUEST_PDPTR2, vcpu->arch.pdptrs[2]); @@ -1557,6 +1612,21 @@ static void ept_load_pdptrs(struct kvm_vcpu *vcpu) } } +static void ept_save_pdptrs(struct kvm_vcpu *vcpu) +{ + if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) { + vcpu->arch.pdptrs[0] = vmcs_read64(GUEST_PDPTR0); + vcpu->arch.pdptrs[1] = vmcs_read64(GUEST_PDPTR1); + vcpu->arch.pdptrs[2] = vmcs_read64(GUEST_PDPTR2); + vcpu->arch.pdptrs[3] = vmcs_read64(GUEST_PDPTR3); + } + + __set_bit(VCPU_EXREG_PDPTR, + (unsigned long *)&vcpu->arch.regs_avail); + __set_bit(VCPU_EXREG_PDPTR, + (unsigned long *)&vcpu->arch.regs_dirty); +} + static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); static void ept_update_paging_mode_cr0(unsigned long *hw_cr0, @@ -1571,8 +1641,6 @@ static void ept_update_paging_mode_cr0(unsigned long *hw_cr0, CPU_BASED_CR3_STORE_EXITING)); vcpu->arch.cr0 = cr0; vmx_set_cr4(vcpu, vcpu->arch.cr4); - *hw_cr0 |= X86_CR0_PE | X86_CR0_PG; - *hw_cr0 &= ~X86_CR0_WP; } else if (!is_paging(vcpu)) { /* From nonpaging to paging */ vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, @@ -1581,9 +1649,10 @@ static void ept_update_paging_mode_cr0(unsigned long *hw_cr0, CPU_BASED_CR3_STORE_EXITING)); vcpu->arch.cr0 = cr0; vmx_set_cr4(vcpu, vcpu->arch.cr4); - if (!(vcpu->arch.cr0 & X86_CR0_WP)) - *hw_cr0 &= ~X86_CR0_WP; } + + if (!(cr0 & X86_CR0_WP)) + *hw_cr0 &= ~X86_CR0_WP; } static void ept_update_paging_mode_cr4(unsigned long *hw_cr4, @@ -1598,15 +1667,21 @@ static void ept_update_paging_mode_cr4(unsigned long *hw_cr4, static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { - unsigned long hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK) | - KVM_VM_CR0_ALWAYS_ON; + struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned long hw_cr0; + + if (enable_unrestricted_guest) + hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST) + | KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST; + else + hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK) | KVM_VM_CR0_ALWAYS_ON; vmx_fpu_deactivate(vcpu); - if (vcpu->arch.rmode.vm86_active && (cr0 & X86_CR0_PE)) + if (vmx->rmode.vm86_active && (cr0 & X86_CR0_PE)) enter_pmode(vcpu); - if (!vcpu->arch.rmode.vm86_active && !(cr0 & X86_CR0_PE)) + if (!vmx->rmode.vm86_active && !(cr0 & X86_CR0_PE)) enter_rmode(vcpu); #ifdef CONFIG_X86_64 @@ -1650,10 +1725,8 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) if (enable_ept) { eptp = construct_eptp(cr3); vmcs_write64(EPT_POINTER, eptp); - ept_sync_context(eptp); - ept_load_pdptrs(vcpu); guest_cr3 = is_paging(vcpu) ? vcpu->arch.cr3 : - VMX_EPT_IDENTITY_PAGETABLE_ADDR; + vcpu->kvm->arch.ept_identity_map_addr; } vmx_flush_tlb(vcpu); @@ -1664,7 +1737,7 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { - unsigned long hw_cr4 = cr4 | (vcpu->arch.rmode.vm86_active ? + unsigned long hw_cr4 = cr4 | (to_vmx(vcpu)->rmode.vm86_active ? KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON); vcpu->arch.cr4 = cr4; @@ -1707,16 +1780,13 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu, static int vmx_get_cpl(struct kvm_vcpu *vcpu) { - struct kvm_segment kvm_seg; - if (!(vcpu->arch.cr0 & X86_CR0_PE)) /* if real mode */ return 0; if (vmx_get_rflags(vcpu) & X86_EFLAGS_VM) /* if virtual 8086 */ return 3; - vmx_get_segment(vcpu, &kvm_seg, VCPU_SREG_CS); - return kvm_seg.selector & 3; + return vmcs_read16(GUEST_CS_SELECTOR) & 3; } static u32 vmx_segment_access_rights(struct kvm_segment *var) @@ -1744,20 +1814,21 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var) static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { + struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; u32 ar; - if (vcpu->arch.rmode.vm86_active && seg == VCPU_SREG_TR) { - vcpu->arch.rmode.tr.selector = var->selector; - vcpu->arch.rmode.tr.base = var->base; - vcpu->arch.rmode.tr.limit = var->limit; - vcpu->arch.rmode.tr.ar = vmx_segment_access_rights(var); + if (vmx->rmode.vm86_active && seg == VCPU_SREG_TR) { + vmx->rmode.tr.selector = var->selector; + vmx->rmode.tr.base = var->base; + vmx->rmode.tr.limit = var->limit; + vmx->rmode.tr.ar = vmx_segment_access_rights(var); return; } vmcs_writel(sf->base, var->base); vmcs_write32(sf->limit, var->limit); vmcs_write16(sf->selector, var->selector); - if (vcpu->arch.rmode.vm86_active && var->s) { + if (vmx->rmode.vm86_active && var->s) { /* * Hack real-mode segments into vm86 compatibility. */ @@ -1766,6 +1837,21 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, ar = 0xf3; } else ar = vmx_segment_access_rights(var); + + /* + * Fix the "Accessed" bit in AR field of segment registers for older + * qemu binaries. + * IA32 arch specifies that at the time of processor reset the + * "Accessed" bit in the AR field of segment registers is 1. And qemu + * is setting it to 0 in the usedland code. This causes invalid guest + * state vmexit when "unrestricted guest" mode is turned on. + * Fix for this setup issue in cpu_reset is being pushed in the qemu + * tree. Newer qemu binaries with that qemu fix would not need this + * kvm hack. + */ + if (enable_unrestricted_guest && (seg != VCPU_SREG_LDTR)) + ar |= 0x1; /* Accessed */ + vmcs_write32(sf->ar_bytes, ar); } @@ -2040,7 +2126,7 @@ static int init_rmode_identity_map(struct kvm *kvm) if (likely(kvm->arch.ept_identity_pagetable_done)) return 1; ret = 0; - identity_map_pfn = VMX_EPT_IDENTITY_PAGETABLE_ADDR >> PAGE_SHIFT; + identity_map_pfn = kvm->arch.ept_identity_map_addr >> PAGE_SHIFT; r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE); if (r < 0) goto out; @@ -2062,11 +2148,19 @@ out: static void seg_setup(int seg) { struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; + unsigned int ar; vmcs_write16(sf->selector, 0); vmcs_writel(sf->base, 0); vmcs_write32(sf->limit, 0xffff); - vmcs_write32(sf->ar_bytes, 0xf3); + if (enable_unrestricted_guest) { + ar = 0x93; + if (seg == VCPU_SREG_CS) + ar |= 0x08; /* code segment */ + } else + ar = 0xf3; + + vmcs_write32(sf->ar_bytes, ar); } static int alloc_apic_access_page(struct kvm *kvm) @@ -2101,14 +2195,15 @@ static int alloc_identity_pagetable(struct kvm *kvm) goto out; kvm_userspace_mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT; kvm_userspace_mem.flags = 0; - kvm_userspace_mem.guest_phys_addr = VMX_EPT_IDENTITY_PAGETABLE_ADDR; + kvm_userspace_mem.guest_phys_addr = + kvm->arch.ept_identity_map_addr; kvm_userspace_mem.memory_size = PAGE_SIZE; r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, 0); if (r) goto out; kvm->arch.ept_identity_pagetable = gfn_to_page(kvm, - VMX_EPT_IDENTITY_PAGETABLE_ADDR >> PAGE_SHIFT); + kvm->arch.ept_identity_map_addr >> PAGE_SHIFT); out: up_write(&kvm->slots_lock); return r; @@ -2209,6 +2304,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) exec_control &= ~SECONDARY_EXEC_ENABLE_VPID; if (!enable_ept) exec_control &= ~SECONDARY_EXEC_ENABLE_EPT; + if (!enable_unrestricted_guest) + exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST; vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); } @@ -2326,14 +2423,14 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) goto out; } - vmx->vcpu.arch.rmode.vm86_active = 0; + vmx->rmode.vm86_active = 0; vmx->soft_vnmi_blocked = 0; vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); kvm_set_cr8(&vmx->vcpu, 0); msr = 0xfee00000 | MSR_IA32_APICBASE_ENABLE; - if (vmx->vcpu.vcpu_id == 0) + if (kvm_vcpu_is_bsp(&vmx->vcpu)) msr |= MSR_IA32_APICBASE_BSP; kvm_set_apic_base(&vmx->vcpu, msr); @@ -2344,7 +2441,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) * GUEST_CS_BASE should really be 0xffff0000, but VT vm86 mode * insists on having GUEST_CS_BASE == GUEST_CS_SELECTOR << 4. Sigh. */ - if (vmx->vcpu.vcpu_id == 0) { + if (kvm_vcpu_is_bsp(&vmx->vcpu)) { vmcs_write16(GUEST_CS_SELECTOR, 0xf000); vmcs_writel(GUEST_CS_BASE, 0x000f0000); } else { @@ -2373,7 +2470,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_SYSENTER_EIP, 0); vmcs_writel(GUEST_RFLAGS, 0x02); - if (vmx->vcpu.vcpu_id == 0) + if (kvm_vcpu_is_bsp(&vmx->vcpu)) kvm_rip_write(vcpu, 0xfff0); else kvm_rip_write(vcpu, 0); @@ -2461,13 +2558,16 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu) uint32_t intr; int irq = vcpu->arch.interrupt.nr; - KVMTRACE_1D(INJ_VIRQ, vcpu, (u32)irq, handler); + trace_kvm_inj_virq(irq); ++vcpu->stat.irq_injections; - if (vcpu->arch.rmode.vm86_active) { + if (vmx->rmode.vm86_active) { vmx->rmode.irq.pending = true; vmx->rmode.irq.vector = irq; vmx->rmode.irq.rip = kvm_rip_read(vcpu); + if (vcpu->arch.interrupt.soft) + vmx->rmode.irq.rip += + vmx->vcpu.arch.event_exit_inst_len; vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, irq | INTR_TYPE_SOFT_INTR | INTR_INFO_VALID_MASK); vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1); @@ -2502,7 +2602,7 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu) } ++vcpu->stat.nmi_injections; - if (vcpu->arch.rmode.vm86_active) { + if (vmx->rmode.vm86_active) { vmx->rmode.irq.pending = true; vmx->rmode.irq.vector = NMI_VECTOR; vmx->rmode.irq.rip = kvm_rip_read(vcpu); @@ -2659,14 +2759,14 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (enable_ept) BUG(); cr2 = vmcs_readl(EXIT_QUALIFICATION); - KVMTRACE_3D(PAGE_FAULT, vcpu, error_code, (u32)cr2, - (u32)((u64)cr2 >> 32), handler); + trace_kvm_page_fault(cr2, error_code); + if (kvm_event_needs_reinjection(vcpu)) kvm_mmu_unprotect_page_virt(vcpu, cr2); return kvm_mmu_page_fault(vcpu, cr2, error_code); } - if (vcpu->arch.rmode.vm86_active && + if (vmx->rmode.vm86_active && handle_rmode_exception(vcpu, intr_info & INTR_INFO_VECTOR_MASK, error_code)) { if (vcpu->arch.halt_request) { @@ -2707,7 +2807,6 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { ++vcpu->stat.irq_exits; - KVMTRACE_1D(INTR, vcpu, vmcs_read32(VM_EXIT_INTR_INFO), handler); return 1; } @@ -2755,7 +2854,7 @@ vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { - unsigned long exit_qualification; + unsigned long exit_qualification, val; int cr; int reg; @@ -2764,21 +2863,19 @@ 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)kvm_register_read(vcpu, reg), - (u32)((u64)kvm_register_read(vcpu, reg) >> 32), - handler); + val = kvm_register_read(vcpu, reg); + trace_kvm_cr_write(cr, val); switch (cr) { case 0: - kvm_set_cr0(vcpu, kvm_register_read(vcpu, reg)); + kvm_set_cr0(vcpu, val); skip_emulated_instruction(vcpu); return 1; case 3: - kvm_set_cr3(vcpu, kvm_register_read(vcpu, reg)); + kvm_set_cr3(vcpu, val); skip_emulated_instruction(vcpu); return 1; case 4: - kvm_set_cr4(vcpu, kvm_register_read(vcpu, reg)); + kvm_set_cr4(vcpu, val); skip_emulated_instruction(vcpu); return 1; case 8: { @@ -2800,23 +2897,19 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vcpu->arch.cr0 &= ~X86_CR0_TS; vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0); vmx_fpu_activate(vcpu); - KVMTRACE_0D(CLTS, vcpu, handler); skip_emulated_instruction(vcpu); return 1; case 1: /*mov from cr*/ switch (cr) { case 3: kvm_register_write(vcpu, reg, vcpu->arch.cr3); - KVMTRACE_3D(CR_READ, vcpu, (u32)cr, - (u32)kvm_register_read(vcpu, reg), - (u32)((u64)kvm_register_read(vcpu, reg) >> 32), - handler); + trace_kvm_cr_read(cr, vcpu->arch.cr3); skip_emulated_instruction(vcpu); return 1; case 8: - kvm_register_write(vcpu, reg, kvm_get_cr8(vcpu)); - KVMTRACE_2D(CR_READ, vcpu, (u32)cr, - (u32)kvm_register_read(vcpu, reg), handler); + val = kvm_get_cr8(vcpu); + kvm_register_write(vcpu, reg, val); + trace_kvm_cr_read(cr, val); skip_emulated_instruction(vcpu); return 1; } @@ -2841,6 +2934,8 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) unsigned long val; int dr, reg; + if (!kvm_require_cpl(vcpu, 0)) + return 1; dr = vmcs_readl(GUEST_DR7); if (dr & DR7_GD) { /* @@ -2884,7 +2979,6 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) val = 0; } kvm_register_write(vcpu, reg, val); - KVMTRACE_2D(DR_READ, vcpu, (u32)dr, (u32)val, handler); } else { val = vcpu->arch.regs[reg]; switch (dr) { @@ -2917,7 +3011,6 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } break; } - KVMTRACE_2D(DR_WRITE, vcpu, (u32)dr, (u32)val, handler); } skip_emulated_instruction(vcpu); return 1; @@ -2939,8 +3032,7 @@ static int handle_rdmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } - KVMTRACE_3D(MSR_READ, vcpu, ecx, (u32)data, (u32)(data >> 32), - handler); + trace_kvm_msr_read(ecx, data); /* FIXME: handling of bits 32:63 of rax, rdx */ vcpu->arch.regs[VCPU_REGS_RAX] = data & -1u; @@ -2955,8 +3047,7 @@ static int handle_wrmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) u64 data = (vcpu->arch.regs[VCPU_REGS_RAX] & -1u) | ((u64)(vcpu->arch.regs[VCPU_REGS_RDX] & -1u) << 32); - KVMTRACE_3D(MSR_WRITE, vcpu, ecx, (u32)data, (u32)(data >> 32), - handler); + trace_kvm_msr_write(ecx, data); if (vmx_set_msr(vcpu, ecx, data) != 0) { kvm_inject_gp(vcpu, 0); @@ -2983,7 +3074,6 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu, cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING; vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); - KVMTRACE_0D(PEND_INTR, vcpu, handler); ++vcpu->stat.irq_window_exits; /* @@ -3049,7 +3139,7 @@ static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) printk(KERN_ERR "Fail to handle apic access vmexit! Offset is 0x%lx\n", offset); - return -ENOTSUPP; + return -ENOEXEC; } return 1; } @@ -3118,7 +3208,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (exit_qualification & (1 << 6)) { printk(KERN_ERR "EPT: GPA exceeds GAW!\n"); - return -ENOTSUPP; + return -EINVAL; } gla_validity = (exit_qualification >> 7) & 0x3; @@ -3130,14 +3220,98 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) printk(KERN_ERR "EPT: Exit qualification is 0x%lx\n", (long unsigned int)exit_qualification); kvm_run->exit_reason = KVM_EXIT_UNKNOWN; - kvm_run->hw.hardware_exit_reason = 0; - return -ENOTSUPP; + kvm_run->hw.hardware_exit_reason = EXIT_REASON_EPT_VIOLATION; + return 0; } gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); + trace_kvm_page_fault(gpa, exit_qualification); return kvm_mmu_page_fault(vcpu, gpa & PAGE_MASK, 0); } +static u64 ept_rsvd_mask(u64 spte, int level) +{ + int i; + u64 mask = 0; + + for (i = 51; i > boot_cpu_data.x86_phys_bits; i--) + mask |= (1ULL << i); + + if (level > 2) + /* bits 7:3 reserved */ + mask |= 0xf8; + else if (level == 2) { + if (spte & (1ULL << 7)) + /* 2MB ref, bits 20:12 reserved */ + mask |= 0x1ff000; + else + /* bits 6:3 reserved */ + mask |= 0x78; + } + + return mask; +} + +static void ept_misconfig_inspect_spte(struct kvm_vcpu *vcpu, u64 spte, + int level) +{ + printk(KERN_ERR "%s: spte 0x%llx level %d\n", __func__, spte, level); + + /* 010b (write-only) */ + WARN_ON((spte & 0x7) == 0x2); + + /* 110b (write/execute) */ + WARN_ON((spte & 0x7) == 0x6); + + /* 100b (execute-only) and value not supported by logical processor */ + if (!cpu_has_vmx_ept_execute_only()) + WARN_ON((spte & 0x7) == 0x4); + + /* not 000b */ + if ((spte & 0x7)) { + u64 rsvd_bits = spte & ept_rsvd_mask(spte, level); + + if (rsvd_bits != 0) { + printk(KERN_ERR "%s: rsvd_bits = 0x%llx\n", + __func__, rsvd_bits); + WARN_ON(1); + } + + if (level == 1 || (level == 2 && (spte & (1ULL << 7)))) { + u64 ept_mem_type = (spte & 0x38) >> 3; + + if (ept_mem_type == 2 || ept_mem_type == 3 || + ept_mem_type == 7) { + printk(KERN_ERR "%s: ept_mem_type=0x%llx\n", + __func__, ept_mem_type); + WARN_ON(1); + } + } + } +} + +static int handle_ept_misconfig(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + u64 sptes[4]; + int nr_sptes, i; + gpa_t gpa; + + gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); + + printk(KERN_ERR "EPT: Misconfiguration.\n"); + printk(KERN_ERR "EPT: GPA: 0x%llx\n", gpa); + + nr_sptes = kvm_mmu_get_spte_hierarchy(vcpu, gpa, sptes); + + for (i = PT64_ROOT_LEVEL; i > PT64_ROOT_LEVEL - nr_sptes; --i) + ept_misconfig_inspect_spte(vcpu, sptes[i-1], i); + + kvm_run->exit_reason = KVM_EXIT_UNKNOWN; + kvm_run->hw.hardware_exit_reason = EXIT_REASON_EPT_MISCONFIG; + + return 0; +} + static int handle_nmi_window(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { u32 cpu_based_vm_exec_control; @@ -3217,8 +3391,9 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu, [EXIT_REASON_APIC_ACCESS] = handle_apic_access, [EXIT_REASON_WBINVD] = handle_wbinvd, [EXIT_REASON_TASK_SWITCH] = handle_task_switch, - [EXIT_REASON_EPT_VIOLATION] = handle_ept_violation, [EXIT_REASON_MCE_DURING_VMENTRY] = handle_machine_check, + [EXIT_REASON_EPT_VIOLATION] = handle_ept_violation, + [EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig, }; static const int kvm_vmx_max_exit_handlers = @@ -3234,8 +3409,7 @@ static int vmx_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) u32 exit_reason = vmx->exit_reason; u32 vectoring_info = vmx->idt_vectoring_info; - KVMTRACE_3D(VMEXIT, vcpu, exit_reason, (u32)kvm_rip_read(vcpu), - (u32)((u64)kvm_rip_read(vcpu) >> 32), entryexit); + trace_kvm_exit(exit_reason, kvm_rip_read(vcpu)); /* If we need to emulate an MMIO from handle_invalid_guest_state * we just return 0 */ @@ -3247,10 +3421,8 @@ static int vmx_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) /* Access CR3 don't cause VMExit in paging mode, so we need * to sync with guest real CR3. */ - if (enable_ept && is_paging(vcpu)) { + if (enable_ept && is_paging(vcpu)) vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); - ept_load_pdptrs(vcpu); - } if (unlikely(vmx->fail)) { kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; @@ -3326,10 +3498,8 @@ static void vmx_complete_interrupts(struct vcpu_vmx *vmx) /* We need to handle NMIs before interrupts are enabled */ if ((exit_intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR && - (exit_intr_info & INTR_INFO_VALID_MASK)) { - KVMTRACE_0D(NMI, &vmx->vcpu, handler); + (exit_intr_info & INTR_INFO_VALID_MASK)) asm("int $2"); - } idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK; @@ -3434,6 +3604,10 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { struct vcpu_vmx *vmx = to_vmx(vcpu); + if (enable_ept && is_paging(vcpu)) { + vmcs_writel(GUEST_CR3, vcpu->arch.cr3); + ept_load_pdptrs(vcpu); + } /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked)) vmx->entry_time = ktime_get(); @@ -3449,12 +3623,21 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty)) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); + /* When single-stepping over STI and MOV SS, we must clear the + * corresponding interruptibility bits in the guest state. Otherwise + * vmentry fails as it then expects bit 14 (BS) in pending debug + * exceptions being set, but that's not correct for the guest debugging + * case. */ + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + vmx_set_interrupt_shadow(vcpu, 0); + /* * Loading guest fpu may have cleared host cr0.ts */ vmcs_writel(HOST_CR0, read_cr0()); - set_debugreg(vcpu->arch.dr6, 6); + if (vcpu->arch.switch_db_regs) + set_debugreg(vcpu->arch.dr6, 6); asm( /* Store host registers */ @@ -3465,11 +3648,16 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) "mov %%"R"sp, %c[host_rsp](%0) \n\t" __ex(ASM_VMX_VMWRITE_RSP_RDX) "\n\t" "1: \n\t" + /* Reload cr2 if changed */ + "mov %c[cr2](%0), %%"R"ax \n\t" + "mov %%cr2, %%"R"dx \n\t" + "cmp %%"R"ax, %%"R"dx \n\t" + "je 2f \n\t" + "mov %%"R"ax, %%cr2 \n\t" + "2: \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" @@ -3547,10 +3735,12 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) #endif ); - vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)); + vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP) + | (1 << VCPU_EXREG_PDPTR)); vcpu->arch.regs_dirty = 0; - get_debugreg(vcpu->arch.dr6, 6); + if (vcpu->arch.switch_db_regs) + get_debugreg(vcpu->arch.dr6, 6); vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); if (vmx->rmode.irq.pending) @@ -3633,9 +3823,13 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (alloc_apic_access_page(kvm) != 0) goto free_vmcs; - if (enable_ept) + if (enable_ept) { + if (!kvm->arch.ept_identity_map_addr) + kvm->arch.ept_identity_map_addr = + VMX_EPT_IDENTITY_PAGETABLE_ADDR; if (alloc_identity_pagetable(kvm) != 0) goto free_vmcs; + } return &vmx->vcpu; @@ -3699,6 +3893,34 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) return ret; } +static const struct trace_print_flags vmx_exit_reasons_str[] = { + { EXIT_REASON_EXCEPTION_NMI, "exception" }, + { EXIT_REASON_EXTERNAL_INTERRUPT, "ext_irq" }, + { EXIT_REASON_TRIPLE_FAULT, "triple_fault" }, + { EXIT_REASON_NMI_WINDOW, "nmi_window" }, + { EXIT_REASON_IO_INSTRUCTION, "io_instruction" }, + { EXIT_REASON_CR_ACCESS, "cr_access" }, + { EXIT_REASON_DR_ACCESS, "dr_access" }, + { EXIT_REASON_CPUID, "cpuid" }, + { EXIT_REASON_MSR_READ, "rdmsr" }, + { EXIT_REASON_MSR_WRITE, "wrmsr" }, + { EXIT_REASON_PENDING_INTERRUPT, "interrupt_window" }, + { EXIT_REASON_HLT, "halt" }, + { EXIT_REASON_INVLPG, "invlpg" }, + { EXIT_REASON_VMCALL, "hypercall" }, + { EXIT_REASON_TPR_BELOW_THRESHOLD, "tpr_below_thres" }, + { EXIT_REASON_APIC_ACCESS, "apic_access" }, + { EXIT_REASON_WBINVD, "wbinvd" }, + { EXIT_REASON_TASK_SWITCH, "task_switch" }, + { EXIT_REASON_EPT_VIOLATION, "ept_violation" }, + { -1, NULL } +}; + +static bool vmx_gb_page_enable(void) +{ + return false; +} + static struct kvm_x86_ops vmx_x86_ops = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios, @@ -3758,6 +3980,9 @@ static struct kvm_x86_ops vmx_x86_ops = { .set_tss_addr = vmx_set_tss_addr, .get_tdp_level = get_ept_level, .get_mt_mask = vmx_get_mt_mask, + + .exit_reasons_str = vmx_exit_reasons_str, + .gb_page_enable = vmx_gb_page_enable, }; static int __init vmx_init(void) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 633ccc7400a4..be451ee44249 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -37,11 +37,16 @@ #include <linux/iommu.h> #include <linux/intel-iommu.h> #include <linux/cpufreq.h> +#include <trace/events/kvm.h> +#undef TRACE_INCLUDE_FILE +#define CREATE_TRACE_POINTS +#include "trace.h" #include <asm/uaccess.h> #include <asm/msr.h> #include <asm/desc.h> #include <asm/mtrr.h> +#include <asm/mce.h> #define MAX_IO_MSRS 256 #define CR0_RESERVED_BITS \ @@ -55,6 +60,10 @@ | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE)) #define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR) + +#define KVM_MAX_MCE_BANKS 32 +#define KVM_MCE_CAP_SUPPORTED MCG_CTL_P + /* EFER defaults: * - enable syscall per default because its emulated by KVM * - enable LME and LMA per default on 64 bit KVM @@ -68,14 +77,16 @@ static u64 __read_mostly efer_reserved_bits = 0xfffffffffffffffeULL; #define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU +static void update_cr8_intercept(struct kvm_vcpu *vcpu); static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries); -struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, - u32 function, u32 index); struct kvm_x86_ops *kvm_x86_ops; EXPORT_SYMBOL_GPL(kvm_x86_ops); +int ignore_msrs = 0; +module_param_named(ignore_msrs, ignore_msrs, bool, S_IRUGO | S_IWUSR); + struct kvm_stats_debugfs_item debugfs_entries[] = { { "pf_fixed", VCPU_STAT(pf_fixed) }, { "pf_guest", VCPU_STAT(pf_guest) }, @@ -122,18 +133,16 @@ unsigned long segment_base(u16 selector) if (selector == 0) return 0; - asm("sgdt %0" : "=m"(gdt)); + kvm_get_gdt(&gdt); table_base = gdt.base; if (selector & 4) { /* from ldt */ - u16 ldt_selector; + u16 ldt_selector = kvm_read_ldt(); - asm("sldt %0" : "=g"(ldt_selector)); table_base = segment_base(ldt_selector); } d = (struct desc_struct *)(table_base + (selector & ~7)); - v = d->base0 | ((unsigned long)d->base1 << 16) | - ((unsigned long)d->base2 << 24); + v = get_desc_base(d); #ifdef CONFIG_X86_64 if (d->s == 0 && (d->type == 2 || d->type == 9 || d->type == 11)) v |= ((unsigned long)((struct ldttss_desc64 *)d)->base3) << 32; @@ -176,16 +185,22 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr, ++vcpu->stat.pf_guest; if (vcpu->arch.exception.pending) { - if (vcpu->arch.exception.nr == PF_VECTOR) { - printk(KERN_DEBUG "kvm: inject_page_fault:" - " double fault 0x%lx\n", addr); - vcpu->arch.exception.nr = DF_VECTOR; - vcpu->arch.exception.error_code = 0; - } else if (vcpu->arch.exception.nr == DF_VECTOR) { + switch(vcpu->arch.exception.nr) { + case DF_VECTOR: /* triple fault -> shutdown */ set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests); + return; + case PF_VECTOR: + vcpu->arch.exception.nr = DF_VECTOR; + vcpu->arch.exception.error_code = 0; + return; + default: + /* replace previous exception with a new one in a hope + that instruction re-execution will regenerate lost + exception */ + vcpu->arch.exception.pending = false; + break; } - return; } vcpu->arch.cr2 = addr; kvm_queue_exception_e(vcpu, PF_VECTOR, error_code); @@ -207,12 +222,18 @@ void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code) } EXPORT_SYMBOL_GPL(kvm_queue_exception_e); -static void __queue_exception(struct kvm_vcpu *vcpu) +/* + * Checks if cpl <= required_cpl; if true, return true. Otherwise queue + * a #GP and return false. + */ +bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl) { - kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr, - vcpu->arch.exception.has_error_code, - vcpu->arch.exception.error_code); + if (kvm_x86_ops->get_cpl(vcpu) <= required_cpl) + return true; + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return false; } +EXPORT_SYMBOL_GPL(kvm_require_cpl); /* * Load the pae pdptrs. Return true is they are all valid. @@ -232,7 +253,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3) goto out; } for (i = 0; i < ARRAY_SIZE(pdpte); ++i) { - if (is_present_pte(pdpte[i]) && + if (is_present_gpte(pdpte[i]) && (pdpte[i] & vcpu->arch.mmu.rsvd_bits_mask[0][2])) { ret = 0; goto out; @@ -241,6 +262,10 @@ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3) ret = 1; memcpy(vcpu->arch.pdptrs, pdpte, sizeof(vcpu->arch.pdptrs)); + __set_bit(VCPU_EXREG_PDPTR, + (unsigned long *)&vcpu->arch.regs_avail); + __set_bit(VCPU_EXREG_PDPTR, + (unsigned long *)&vcpu->arch.regs_dirty); out: return ret; @@ -256,6 +281,10 @@ static bool pdptrs_changed(struct kvm_vcpu *vcpu) if (is_long_mode(vcpu) || !is_pae(vcpu)) return false; + if (!test_bit(VCPU_EXREG_PDPTR, + (unsigned long *)&vcpu->arch.regs_avail)) + return true; + r = kvm_read_guest(vcpu->kvm, vcpu->arch.cr3 & ~31u, pdpte, sizeof(pdpte)); if (r < 0) goto out; @@ -328,9 +357,6 @@ EXPORT_SYMBOL_GPL(kvm_set_cr0); void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw) { kvm_set_cr0(vcpu, (vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f)); - KVMTRACE_1D(LMSW, vcpu, - (u32)((vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f)), - handler); } EXPORT_SYMBOL_GPL(kvm_lmsw); @@ -466,7 +492,7 @@ static u32 msrs_to_save[] = { #ifdef CONFIG_X86_64 MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif - MSR_IA32_TIME_STAMP_COUNTER, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, + MSR_IA32_TSC, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA }; @@ -644,8 +670,7 @@ static void kvm_write_guest_time(struct kvm_vcpu *v) /* Keep irq disabled to prevent changes to the clock */ local_irq_save(flags); - kvm_get_msr(v, MSR_IA32_TIME_STAMP_COUNTER, - &vcpu->hv_clock.tsc_timestamp); + kvm_get_msr(v, MSR_IA32_TSC, &vcpu->hv_clock.tsc_timestamp); ktime_get_ts(&ts); local_irq_restore(flags); @@ -778,23 +803,60 @@ static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data) return 0; } +static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + u64 mcg_cap = vcpu->arch.mcg_cap; + unsigned bank_num = mcg_cap & 0xff; + + switch (msr) { + case MSR_IA32_MCG_STATUS: + vcpu->arch.mcg_status = data; + break; + case MSR_IA32_MCG_CTL: + if (!(mcg_cap & MCG_CTL_P)) + return 1; + if (data != 0 && data != ~(u64)0) + return -1; + vcpu->arch.mcg_ctl = data; + break; + default: + if (msr >= MSR_IA32_MC0_CTL && + msr < MSR_IA32_MC0_CTL + 4 * bank_num) { + u32 offset = msr - MSR_IA32_MC0_CTL; + /* only 0 or all 1s can be written to IA32_MCi_CTL */ + if ((offset & 0x3) == 0 && + data != 0 && data != ~(u64)0) + return -1; + vcpu->arch.mce_banks[offset] = data; + break; + } + return 1; + } + return 0; +} + int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) { switch (msr) { case MSR_EFER: set_efer(vcpu, data); break; - case MSR_IA32_MC0_STATUS: - pr_unimpl(vcpu, "%s: MSR_IA32_MC0_STATUS 0x%llx, nop\n", - __func__, data); + case MSR_K7_HWCR: + data &= ~(u64)0x40; /* ignore flush filter disable */ + if (data != 0) { + pr_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n", + data); + return 1; + } break; - case MSR_IA32_MCG_STATUS: - pr_unimpl(vcpu, "%s: MSR_IA32_MCG_STATUS 0x%llx, nop\n", - __func__, data); + case MSR_FAM10H_MMIO_CONF_BASE: + if (data != 0) { + pr_unimpl(vcpu, "unimplemented MMIO_CONF_BASE wrmsr: " + "0x%llx\n", data); + return 1; + } break; - case MSR_IA32_MCG_CTL: - pr_unimpl(vcpu, "%s: MSR_IA32_MCG_CTL 0x%llx, nop\n", - __func__, data); + case MSR_AMD64_NB_CFG: break; case MSR_IA32_DEBUGCTLMSR: if (!data) { @@ -811,12 +873,15 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) case MSR_IA32_UCODE_REV: case MSR_IA32_UCODE_WRITE: case MSR_VM_HSAVE_PA: + case MSR_AMD64_PATCH_LOADER: break; case 0x200 ... 0x2ff: return set_msr_mtrr(vcpu, msr, data); case MSR_IA32_APICBASE: kvm_set_apic_base(vcpu, data); break; + case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + return kvm_x2apic_msr_write(vcpu, msr, data); case MSR_IA32_MISC_ENABLE: vcpu->arch.ia32_misc_enable_msr = data; break; @@ -850,9 +915,50 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) kvm_request_guest_time_update(vcpu); break; } + case MSR_IA32_MCG_CTL: + case MSR_IA32_MCG_STATUS: + case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1: + return set_msr_mce(vcpu, msr, data); + + /* Performance counters are not protected by a CPUID bit, + * so we should check all of them in the generic path for the sake of + * cross vendor migration. + * Writing a zero into the event select MSRs disables them, + * which we perfectly emulate ;-). Any other value should be at least + * reported, some guests depend on them. + */ + case MSR_P6_EVNTSEL0: + case MSR_P6_EVNTSEL1: + case MSR_K7_EVNTSEL0: + case MSR_K7_EVNTSEL1: + case MSR_K7_EVNTSEL2: + case MSR_K7_EVNTSEL3: + if (data != 0) + pr_unimpl(vcpu, "unimplemented perfctr wrmsr: " + "0x%x data 0x%llx\n", msr, data); + break; + /* at least RHEL 4 unconditionally writes to the perfctr registers, + * so we ignore writes to make it happy. + */ + case MSR_P6_PERFCTR0: + case MSR_P6_PERFCTR1: + case MSR_K7_PERFCTR0: + case MSR_K7_PERFCTR1: + case MSR_K7_PERFCTR2: + case MSR_K7_PERFCTR3: + pr_unimpl(vcpu, "unimplemented perfctr wrmsr: " + "0x%x data 0x%llx\n", msr, data); + break; default: - pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", msr, data); - return 1; + if (!ignore_msrs) { + pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", + msr, data); + return 1; + } else { + pr_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", + msr, data); + break; + } } return 0; } @@ -905,26 +1011,47 @@ static int get_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) return 0; } -int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) { u64 data; + u64 mcg_cap = vcpu->arch.mcg_cap; + unsigned bank_num = mcg_cap & 0xff; switch (msr) { - case 0xc0010010: /* SYSCFG */ - case 0xc0010015: /* HWCR */ - case MSR_IA32_PLATFORM_ID: case MSR_IA32_P5_MC_ADDR: case MSR_IA32_P5_MC_TYPE: - case MSR_IA32_MC0_CTL: - case MSR_IA32_MCG_STATUS: + data = 0; + break; case MSR_IA32_MCG_CAP: + data = vcpu->arch.mcg_cap; + break; case MSR_IA32_MCG_CTL: - case MSR_IA32_MC0_MISC: - case MSR_IA32_MC0_MISC+4: - case MSR_IA32_MC0_MISC+8: - case MSR_IA32_MC0_MISC+12: - case MSR_IA32_MC0_MISC+16: - case MSR_IA32_MC0_MISC+20: + if (!(mcg_cap & MCG_CTL_P)) + return 1; + data = vcpu->arch.mcg_ctl; + break; + case MSR_IA32_MCG_STATUS: + data = vcpu->arch.mcg_status; + break; + default: + if (msr >= MSR_IA32_MC0_CTL && + msr < MSR_IA32_MC0_CTL + 4 * bank_num) { + u32 offset = msr - MSR_IA32_MC0_CTL; + data = vcpu->arch.mce_banks[offset]; + break; + } + return 1; + } + *pdata = data; + return 0; +} + +int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + u64 data; + + switch (msr) { + case MSR_IA32_PLATFORM_ID: case MSR_IA32_UCODE_REV: case MSR_IA32_EBL_CR_POWERON: case MSR_IA32_DEBUGCTLMSR: @@ -932,10 +1059,18 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_IA32_LASTBRANCHTOIP: case MSR_IA32_LASTINTFROMIP: case MSR_IA32_LASTINTTOIP: + case MSR_K8_SYSCFG: + case MSR_K7_HWCR: case MSR_VM_HSAVE_PA: + case MSR_P6_PERFCTR0: + case MSR_P6_PERFCTR1: case MSR_P6_EVNTSEL0: case MSR_P6_EVNTSEL1: case MSR_K7_EVNTSEL0: + case MSR_K7_PERFCTR0: + case MSR_K8_INT_PENDING_MSG: + case MSR_AMD64_NB_CFG: + case MSR_FAM10H_MMIO_CONF_BASE: data = 0; break; case MSR_MTRRcap: @@ -949,6 +1084,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_IA32_APICBASE: data = kvm_get_apic_base(vcpu); break; + case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + return kvm_x2apic_msr_read(vcpu, msr, pdata); + break; case MSR_IA32_MISC_ENABLE: data = vcpu->arch.ia32_misc_enable_msr; break; @@ -967,9 +1105,22 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_KVM_SYSTEM_TIME: data = vcpu->arch.time; break; + case MSR_IA32_P5_MC_ADDR: + case MSR_IA32_P5_MC_TYPE: + case MSR_IA32_MCG_CAP: + case MSR_IA32_MCG_CTL: + case MSR_IA32_MCG_STATUS: + case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1: + return get_msr_mce(vcpu, msr, pdata); default: - pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr); - return 1; + if (!ignore_msrs) { + pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr); + return 1; + } else { + pr_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr); + data = 0; + } + break; } *pdata = data; return 0; @@ -1068,6 +1219,11 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_REINJECT_CONTROL: case KVM_CAP_IRQ_INJECT_STATUS: case KVM_CAP_ASSIGN_DEV_IRQ: + case KVM_CAP_IRQFD: + case KVM_CAP_IOEVENTFD: + case KVM_CAP_PIT2: + case KVM_CAP_PIT_STATE2: + case KVM_CAP_SET_IDENTITY_MAP_ADDR: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -1088,6 +1244,9 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_IOMMU: r = iommu_found(); break; + case KVM_CAP_MCE: + r = KVM_MAX_MCE_BANKS; + break; default: r = 0; break; @@ -1147,6 +1306,16 @@ long kvm_arch_dev_ioctl(struct file *filp, r = 0; break; } + case KVM_X86_GET_MCE_CAP_SUPPORTED: { + u64 mce_cap; + + mce_cap = KVM_MCE_CAP_SUPPORTED; + r = -EFAULT; + if (copy_to_user(argp, &mce_cap, sizeof mce_cap)) + goto out; + r = 0; + break; + } default: r = -EINVAL; } @@ -1227,6 +1396,7 @@ static int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, vcpu->arch.cpuid_nent = cpuid->nent; cpuid_fix_nx_cap(vcpu); r = 0; + kvm_apic_set_version(vcpu); out_free: vfree(cpuid_entries); @@ -1248,6 +1418,7 @@ static int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, cpuid->nent * sizeof(struct kvm_cpuid_entry2))) goto out; vcpu->arch.cpuid_nent = cpuid->nent; + kvm_apic_set_version(vcpu); return 0; out: @@ -1290,6 +1461,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, u32 index, int *nent, int maxnent) { unsigned f_nx = is_efer_nx() ? F(NX) : 0; + unsigned f_gbpages = kvm_x86_ops->gb_page_enable() ? F(GBPAGES) : 0; #ifdef CONFIG_X86_64 unsigned f_lm = F(LM); #else @@ -1314,7 +1486,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | F(PAT) | F(PSE36) | 0 /* Reserved */ | f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) | - F(FXSR) | F(FXSR_OPT) | 0 /* GBPAGES */ | 0 /* RDTSCP */ | + F(FXSR) | F(FXSR_OPT) | f_gbpages | 0 /* RDTSCP */ | 0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW); /* cpuid 1.ecx */ const u32 kvm_supported_word4_x86_features = @@ -1323,7 +1495,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, 0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ | 0 /* Reserved */ | F(CX16) | 0 /* xTPR Update, PDCM */ | 0 /* Reserved, DCA */ | F(XMM4_1) | - F(XMM4_2) | 0 /* x2APIC */ | F(MOVBE) | F(POPCNT) | + F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) | 0 /* Reserved, XSAVE, OSXSAVE */; /* cpuid 0x80000001.ecx */ const u32 kvm_supported_word6_x86_features = @@ -1344,6 +1516,9 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, case 1: entry->edx &= kvm_supported_word0_x86_features; entry->ecx &= kvm_supported_word4_x86_features; + /* we support x2apic emulation even if host does not support + * it since we emulate x2apic in software */ + entry->ecx |= F(X2APIC); break; /* function 2 entries are STATEFUL. That is, repeated cpuid commands * may return different values. This forces us to get_cpu() before @@ -1435,6 +1610,10 @@ static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, for (func = 0x80000001; func <= limit && nent < cpuid->nent; ++func) do_cpuid_ent(&cpuid_entries[nent], func, 0, &nent, cpuid->nent); + r = -E2BIG; + if (nent >= cpuid->nent) + goto out_free; + r = -EFAULT; if (copy_to_user(entries, cpuid_entries, nent * sizeof(struct kvm_cpuid_entry2))) @@ -1464,6 +1643,7 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, vcpu_load(vcpu); memcpy(vcpu->arch.apic->regs, s->regs, sizeof *s); kvm_apic_post_state_restore(vcpu); + update_cr8_intercept(vcpu); vcpu_put(vcpu); return 0; @@ -1503,6 +1683,80 @@ static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu, return 0; } +static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, + u64 mcg_cap) +{ + int r; + unsigned bank_num = mcg_cap & 0xff, bank; + + r = -EINVAL; + if (!bank_num) + goto out; + if (mcg_cap & ~(KVM_MCE_CAP_SUPPORTED | 0xff | 0xff0000)) + goto out; + r = 0; + vcpu->arch.mcg_cap = mcg_cap; + /* Init IA32_MCG_CTL to all 1s */ + if (mcg_cap & MCG_CTL_P) + vcpu->arch.mcg_ctl = ~(u64)0; + /* Init IA32_MCi_CTL to all 1s */ + for (bank = 0; bank < bank_num; bank++) + vcpu->arch.mce_banks[bank*4] = ~(u64)0; +out: + return r; +} + +static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, + struct kvm_x86_mce *mce) +{ + u64 mcg_cap = vcpu->arch.mcg_cap; + unsigned bank_num = mcg_cap & 0xff; + u64 *banks = vcpu->arch.mce_banks; + + if (mce->bank >= bank_num || !(mce->status & MCI_STATUS_VAL)) + return -EINVAL; + /* + * if IA32_MCG_CTL is not all 1s, the uncorrected error + * reporting is disabled + */ + if ((mce->status & MCI_STATUS_UC) && (mcg_cap & MCG_CTL_P) && + vcpu->arch.mcg_ctl != ~(u64)0) + return 0; + banks += 4 * mce->bank; + /* + * if IA32_MCi_CTL is not all 1s, the uncorrected error + * reporting is disabled for the bank + */ + if ((mce->status & MCI_STATUS_UC) && banks[0] != ~(u64)0) + return 0; + if (mce->status & MCI_STATUS_UC) { + if ((vcpu->arch.mcg_status & MCG_STATUS_MCIP) || + !(vcpu->arch.cr4 & X86_CR4_MCE)) { + printk(KERN_DEBUG "kvm: set_mce: " + "injects mce exception while " + "previous one is in progress!\n"); + set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests); + return 0; + } + if (banks[1] & MCI_STATUS_VAL) + mce->status |= MCI_STATUS_OVER; + banks[2] = mce->addr; + banks[3] = mce->misc; + vcpu->arch.mcg_status = mce->mcg_status; + banks[1] = mce->status; + kvm_queue_exception(vcpu, MC_VECTOR); + } else if (!(banks[1] & MCI_STATUS_VAL) + || !(banks[1] & MCI_STATUS_UC)) { + if (banks[1] & MCI_STATUS_VAL) + mce->status |= MCI_STATUS_OVER; + banks[2] = mce->addr; + banks[3] = mce->misc; + banks[1] = mce->status; + } else + banks[1] |= MCI_STATUS_OVER; + return 0; +} + long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -1636,6 +1890,24 @@ long kvm_arch_vcpu_ioctl(struct file *filp, kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr); break; } + case KVM_X86_SETUP_MCE: { + u64 mcg_cap; + + r = -EFAULT; + if (copy_from_user(&mcg_cap, argp, sizeof mcg_cap)) + goto out; + r = kvm_vcpu_ioctl_x86_setup_mce(vcpu, mcg_cap); + break; + } + case KVM_X86_SET_MCE: { + struct kvm_x86_mce mce; + + r = -EFAULT; + if (copy_from_user(&mce, argp, sizeof mce)) + goto out; + r = kvm_vcpu_ioctl_x86_set_mce(vcpu, &mce); + break; + } default: r = -EINVAL; } @@ -1654,6 +1926,13 @@ static int kvm_vm_ioctl_set_tss_addr(struct kvm *kvm, unsigned long addr) return ret; } +static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm, + u64 ident_addr) +{ + kvm->arch.ept_identity_map_addr = ident_addr; + return 0; +} + static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, u32 kvm_nr_mmu_pages) { @@ -1775,19 +2054,25 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) r = 0; switch (chip->chip_id) { case KVM_IRQCHIP_PIC_MASTER: + spin_lock(&pic_irqchip(kvm)->lock); memcpy(&pic_irqchip(kvm)->pics[0], &chip->chip.pic, sizeof(struct kvm_pic_state)); + spin_unlock(&pic_irqchip(kvm)->lock); break; case KVM_IRQCHIP_PIC_SLAVE: + spin_lock(&pic_irqchip(kvm)->lock); memcpy(&pic_irqchip(kvm)->pics[1], &chip->chip.pic, sizeof(struct kvm_pic_state)); + spin_unlock(&pic_irqchip(kvm)->lock); break; case KVM_IRQCHIP_IOAPIC: + mutex_lock(&kvm->irq_lock); memcpy(ioapic_irqchip(kvm), &chip->chip.ioapic, sizeof(struct kvm_ioapic_state)); + mutex_unlock(&kvm->irq_lock); break; default: r = -EINVAL; @@ -1801,7 +2086,9 @@ static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps) { int r = 0; + mutex_lock(&kvm->arch.vpit->pit_state.lock); memcpy(ps, &kvm->arch.vpit->pit_state, sizeof(struct kvm_pit_state)); + mutex_unlock(&kvm->arch.vpit->pit_state.lock); return r; } @@ -1809,8 +2096,39 @@ static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps) { int r = 0; + mutex_lock(&kvm->arch.vpit->pit_state.lock); memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state)); - kvm_pit_load_count(kvm, 0, ps->channels[0].count); + kvm_pit_load_count(kvm, 0, ps->channels[0].count, 0); + mutex_unlock(&kvm->arch.vpit->pit_state.lock); + return r; +} + +static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) +{ + int r = 0; + + mutex_lock(&kvm->arch.vpit->pit_state.lock); + memcpy(ps->channels, &kvm->arch.vpit->pit_state.channels, + sizeof(ps->channels)); + ps->flags = kvm->arch.vpit->pit_state.flags; + mutex_unlock(&kvm->arch.vpit->pit_state.lock); + return r; +} + +static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) +{ + int r = 0, start = 0; + u32 prev_legacy, cur_legacy; + mutex_lock(&kvm->arch.vpit->pit_state.lock); + prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY; + cur_legacy = ps->flags & KVM_PIT_FLAGS_HPET_LEGACY; + if (!prev_legacy && cur_legacy) + start = 1; + memcpy(&kvm->arch.vpit->pit_state.channels, &ps->channels, + sizeof(kvm->arch.vpit->pit_state.channels)); + kvm->arch.vpit->pit_state.flags = ps->flags; + kvm_pit_load_count(kvm, 0, kvm->arch.vpit->pit_state.channels[0].count, start); + mutex_unlock(&kvm->arch.vpit->pit_state.lock); return r; } @@ -1819,7 +2137,9 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm, { if (!kvm->arch.vpit) return -ENXIO; + mutex_lock(&kvm->arch.vpit->pit_state.lock); kvm->arch.vpit->pit_state.pit_timer.reinject = control->pit_reinject; + mutex_unlock(&kvm->arch.vpit->pit_state.lock); return 0; } @@ -1845,7 +2165,6 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, spin_lock(&kvm->mmu_lock); kvm_mmu_slot_remove_write_access(kvm, log->slot); spin_unlock(&kvm->mmu_lock); - kvm_flush_remote_tlbs(kvm); memslot = &kvm->memslots[log->slot]; n = ALIGN(memslot->npages, BITS_PER_LONG) / 8; memset(memslot->dirty_bitmap, 0, n); @@ -1869,7 +2188,9 @@ long kvm_arch_vm_ioctl(struct file *filp, */ union { struct kvm_pit_state ps; + struct kvm_pit_state2 ps2; struct kvm_memory_alias alias; + struct kvm_pit_config pit_config; } u; switch (ioctl) { @@ -1878,6 +2199,17 @@ long kvm_arch_vm_ioctl(struct file *filp, if (r < 0) goto out; break; + case KVM_SET_IDENTITY_MAP_ADDR: { + u64 ident_addr; + + r = -EFAULT; + if (copy_from_user(&ident_addr, argp, sizeof ident_addr)) + goto out; + r = kvm_vm_ioctl_set_identity_map_addr(kvm, ident_addr); + if (r < 0) + goto out; + break; + } case KVM_SET_MEMORY_REGION: { struct kvm_memory_region kvm_mem; struct kvm_userspace_memory_region kvm_userspace_mem; @@ -1930,16 +2262,24 @@ long kvm_arch_vm_ioctl(struct file *filp, } break; case KVM_CREATE_PIT: - mutex_lock(&kvm->lock); + u.pit_config.flags = KVM_PIT_SPEAKER_DUMMY; + goto create_pit; + case KVM_CREATE_PIT2: + r = -EFAULT; + if (copy_from_user(&u.pit_config, argp, + sizeof(struct kvm_pit_config))) + goto out; + create_pit: + down_write(&kvm->slots_lock); r = -EEXIST; if (kvm->arch.vpit) goto create_pit_unlock; r = -ENOMEM; - kvm->arch.vpit = kvm_create_pit(kvm); + kvm->arch.vpit = kvm_create_pit(kvm, u.pit_config.flags); if (kvm->arch.vpit) r = 0; create_pit_unlock: - mutex_unlock(&kvm->lock); + up_write(&kvm->slots_lock); break; case KVM_IRQ_LINE_STATUS: case KVM_IRQ_LINE: { @@ -1950,10 +2290,10 @@ long kvm_arch_vm_ioctl(struct file *filp, goto out; if (irqchip_in_kernel(kvm)) { __s32 status; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->irq_lock); status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irq_event.irq, irq_event.level); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->irq_lock); if (ioctl == KVM_IRQ_LINE_STATUS) { irq_event.status = status; if (copy_to_user(argp, &irq_event, @@ -2042,6 +2382,32 @@ long kvm_arch_vm_ioctl(struct file *filp, r = 0; break; } + case KVM_GET_PIT2: { + r = -ENXIO; + if (!kvm->arch.vpit) + goto out; + r = kvm_vm_ioctl_get_pit2(kvm, &u.ps2); + if (r) + goto out; + r = -EFAULT; + if (copy_to_user(argp, &u.ps2, sizeof(u.ps2))) + goto out; + r = 0; + break; + } + case KVM_SET_PIT2: { + r = -EFAULT; + if (copy_from_user(&u.ps2, argp, sizeof(u.ps2))) + goto out; + r = -ENXIO; + if (!kvm->arch.vpit) + goto out; + r = kvm_vm_ioctl_set_pit2(kvm, &u.ps2); + if (r) + goto out; + r = 0; + break; + } case KVM_REINJECT_CONTROL: { struct kvm_reinject_control control; r = -EFAULT; @@ -2075,35 +2441,23 @@ static void kvm_init_msr_list(void) num_msrs_to_save = j; } -/* - * Only apic need an MMIO device hook, so shortcut now.. - */ -static struct kvm_io_device *vcpu_find_pervcpu_dev(struct kvm_vcpu *vcpu, - gpa_t addr, int len, - int is_write) +static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, + const void *v) { - struct kvm_io_device *dev; + if (vcpu->arch.apic && + !kvm_iodevice_write(&vcpu->arch.apic->dev, addr, len, v)) + return 0; - if (vcpu->arch.apic) { - dev = &vcpu->arch.apic->dev; - if (dev->in_range(dev, addr, len, is_write)) - return dev; - } - return NULL; + return kvm_io_bus_write(&vcpu->kvm->mmio_bus, addr, len, v); } - -static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu, - gpa_t addr, int len, - int is_write) +static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) { - struct kvm_io_device *dev; + if (vcpu->arch.apic && + !kvm_iodevice_read(&vcpu->arch.apic->dev, addr, len, v)) + return 0; - dev = vcpu_find_pervcpu_dev(vcpu, addr, len, is_write); - if (dev == NULL) - dev = kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr, len, - is_write); - return dev; + return kvm_io_bus_read(&vcpu->kvm->mmio_bus, addr, len, v); } static int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes, @@ -2172,11 +2526,12 @@ static int emulator_read_emulated(unsigned long addr, unsigned int bytes, struct kvm_vcpu *vcpu) { - struct kvm_io_device *mmio_dev; gpa_t gpa; if (vcpu->mmio_read_completed) { memcpy(val, vcpu->mmio_data, bytes); + trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes, + vcpu->mmio_phys_addr, *(u64 *)val); vcpu->mmio_read_completed = 0; return X86EMUL_CONTINUE; } @@ -2197,14 +2552,12 @@ mmio: /* * Is this MMIO handled locally? */ - mutex_lock(&vcpu->kvm->lock); - mmio_dev = vcpu_find_mmio_dev(vcpu, gpa, bytes, 0); - if (mmio_dev) { - kvm_iodevice_read(mmio_dev, gpa, bytes, val); - mutex_unlock(&vcpu->kvm->lock); + if (!vcpu_mmio_read(vcpu, gpa, bytes, val)) { + trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes, gpa, *(u64 *)val); return X86EMUL_CONTINUE; } - mutex_unlock(&vcpu->kvm->lock); + + trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, 0); vcpu->mmio_needed = 1; vcpu->mmio_phys_addr = gpa; @@ -2231,7 +2584,6 @@ static int emulator_write_emulated_onepage(unsigned long addr, unsigned int bytes, struct kvm_vcpu *vcpu) { - struct kvm_io_device *mmio_dev; gpa_t gpa; gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); @@ -2249,17 +2601,12 @@ static int emulator_write_emulated_onepage(unsigned long addr, return X86EMUL_CONTINUE; mmio: + trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, *(u64 *)val); /* * Is this MMIO handled locally? */ - mutex_lock(&vcpu->kvm->lock); - mmio_dev = vcpu_find_mmio_dev(vcpu, gpa, bytes, 1); - if (mmio_dev) { - kvm_iodevice_write(mmio_dev, gpa, bytes, val); - mutex_unlock(&vcpu->kvm->lock); + if (!vcpu_mmio_write(vcpu, gpa, bytes, val)) return X86EMUL_CONTINUE; - } - mutex_unlock(&vcpu->kvm->lock); vcpu->mmio_needed = 1; vcpu->mmio_phys_addr = gpa; @@ -2343,7 +2690,6 @@ int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address) int emulate_clts(struct kvm_vcpu *vcpu) { - KVMTRACE_0D(CLTS, vcpu, handler); kvm_x86_ops->set_cr0(vcpu, vcpu->arch.cr0 & ~X86_CR0_TS); return X86EMUL_CONTINUE; } @@ -2420,7 +2766,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu, kvm_clear_exception_queue(vcpu); vcpu->arch.mmio_fault_cr2 = cr2; /* - * TODO: fix x86_emulate.c to use guest_read/write_register + * TODO: fix 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. @@ -2444,14 +2790,33 @@ int emulate_instruction(struct kvm_vcpu *vcpu, r = x86_decode_insn(&vcpu->arch.emulate_ctxt, &emulate_ops); - /* Reject the instructions other than VMCALL/VMMCALL when - * try to emulate invalid opcode */ + /* Only allow emulation of specific instructions on #UD + * (namely VMMCALL, sysenter, sysexit, syscall)*/ c = &vcpu->arch.emulate_ctxt.decode; - if ((emulation_type & EMULTYPE_TRAP_UD) && - (!(c->twobyte && c->b == 0x01 && - (c->modrm_reg == 0 || c->modrm_reg == 3) && - c->modrm_mod == 3 && c->modrm_rm == 1))) - return EMULATE_FAIL; + if (emulation_type & EMULTYPE_TRAP_UD) { + if (!c->twobyte) + return EMULATE_FAIL; + switch (c->b) { + case 0x01: /* VMMCALL */ + if (c->modrm_mod != 3 || c->modrm_rm != 1) + return EMULATE_FAIL; + break; + case 0x34: /* sysenter */ + case 0x35: /* sysexit */ + if (c->modrm_mod != 0 || c->modrm_rm != 0) + return EMULATE_FAIL; + break; + case 0x05: /* syscall */ + if (c->modrm_mod != 0 || c->modrm_rm != 0) + return EMULATE_FAIL; + break; + default: + return EMULATE_FAIL; + } + + if (!(c->modrm_reg == 0 || c->modrm_reg == 3)) + return EMULATE_FAIL; + } ++vcpu->stat.insn_emulation; if (r) { @@ -2571,52 +2936,40 @@ int complete_pio(struct kvm_vcpu *vcpu) return 0; } -static void kernel_pio(struct kvm_io_device *pio_dev, - struct kvm_vcpu *vcpu, - void *pd) +static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) { /* TODO: String I/O for in kernel device */ + int r; - mutex_lock(&vcpu->kvm->lock); if (vcpu->arch.pio.in) - kvm_iodevice_read(pio_dev, vcpu->arch.pio.port, - vcpu->arch.pio.size, - pd); + r = kvm_io_bus_read(&vcpu->kvm->pio_bus, vcpu->arch.pio.port, + vcpu->arch.pio.size, pd); else - kvm_iodevice_write(pio_dev, vcpu->arch.pio.port, - vcpu->arch.pio.size, - pd); - mutex_unlock(&vcpu->kvm->lock); + r = kvm_io_bus_write(&vcpu->kvm->pio_bus, vcpu->arch.pio.port, + vcpu->arch.pio.size, pd); + return r; } -static void pio_string_write(struct kvm_io_device *pio_dev, - struct kvm_vcpu *vcpu) +static int pio_string_write(struct kvm_vcpu *vcpu) { struct kvm_pio_request *io = &vcpu->arch.pio; void *pd = vcpu->arch.pio_data; - int i; + int i, r = 0; - mutex_lock(&vcpu->kvm->lock); for (i = 0; i < io->cur_count; i++) { - kvm_iodevice_write(pio_dev, io->port, - io->size, - pd); + if (kvm_io_bus_write(&vcpu->kvm->pio_bus, + io->port, io->size, pd)) { + r = -EOPNOTSUPP; + break; + } pd += io->size; } - mutex_unlock(&vcpu->kvm->lock); -} - -static struct kvm_io_device *vcpu_find_pio_dev(struct kvm_vcpu *vcpu, - gpa_t addr, int len, - int is_write) -{ - return kvm_io_bus_find_dev(&vcpu->kvm->pio_bus, addr, len, is_write); + return r; } 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; @@ -2630,19 +2983,13 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, vcpu->arch.pio.down = 0; vcpu->arch.pio.rep = 0; - if (vcpu->run->io.direction == KVM_EXIT_IO_IN) - KVMTRACE_2D(IO_READ, vcpu, vcpu->run->io.port, (u32)size, - handler); - else - KVMTRACE_2D(IO_WRITE, vcpu, vcpu->run->io.port, (u32)size, - handler); + trace_kvm_pio(vcpu->run->io.direction == KVM_EXIT_IO_OUT, port, + size, 1); val = kvm_register_read(vcpu, VCPU_REGS_RAX); memcpy(vcpu->arch.pio_data, &val, 4); - pio_dev = vcpu_find_pio_dev(vcpu, port, size, !in); - if (pio_dev) { - kernel_pio(pio_dev, vcpu, vcpu->arch.pio_data); + if (!kernel_pio(vcpu, vcpu->arch.pio_data)) { complete_pio(vcpu); return 1; } @@ -2656,7 +3003,6 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, { unsigned now, in_page; int ret = 0; - struct kvm_io_device *pio_dev; vcpu->run->exit_reason = KVM_EXIT_IO; vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; @@ -2669,12 +3015,8 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, vcpu->arch.pio.down = down; vcpu->arch.pio.rep = rep; - if (vcpu->run->io.direction == KVM_EXIT_IO_IN) - KVMTRACE_2D(IO_READ, vcpu, vcpu->run->io.port, (u32)size, - handler); - else - KVMTRACE_2D(IO_WRITE, vcpu, vcpu->run->io.port, (u32)size, - handler); + trace_kvm_pio(vcpu->run->io.direction == KVM_EXIT_IO_OUT, port, + size, count); if (!count) { kvm_x86_ops->skip_emulated_instruction(vcpu); @@ -2704,9 +3046,6 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, vcpu->arch.pio.guest_gva = address; - pio_dev = vcpu_find_pio_dev(vcpu, port, - vcpu->arch.pio.cur_count, - !vcpu->arch.pio.in); if (!vcpu->arch.pio.in) { /* string PIO write */ ret = pio_copy_data(vcpu); @@ -2714,16 +3053,13 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, kvm_inject_gp(vcpu, 0); return 1; } - if (ret == 0 && pio_dev) { - pio_string_write(pio_dev, vcpu); + if (ret == 0 && !pio_string_write(vcpu)) { complete_pio(vcpu); if (vcpu->arch.pio.count == 0) ret = 1; } - } else if (pio_dev) - pr_unimpl(vcpu, "no string pio read support yet, " - "port %x size %d count %ld\n", - port, size, count); + } + /* no string PIO read support yet */ return ret; } @@ -2756,10 +3092,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - vcpu = kvm->vcpus[i]; - if (!vcpu) - continue; + kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->cpu != freq->cpu) continue; if (!kvm_request_guest_time_update(vcpu)) @@ -2852,7 +3185,6 @@ void kvm_arch_exit(void) int kvm_emulate_halt(struct kvm_vcpu *vcpu) { ++vcpu->stat.halt_exits; - KVMTRACE_0D(HLT, vcpu, handler); if (irqchip_in_kernel(vcpu->kvm)) { vcpu->arch.mp_state = KVM_MP_STATE_HALTED; return 1; @@ -2883,7 +3215,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) a2 = kvm_register_read(vcpu, VCPU_REGS_RDX); a3 = kvm_register_read(vcpu, VCPU_REGS_RSI); - KVMTRACE_1D(VMMCALL, vcpu, (u32)nr, handler); + trace_kvm_hypercall(nr, a0, a1, a2, a3); if (!is_long_mode(vcpu)) { nr &= 0xFFFFFFFF; @@ -2893,6 +3225,11 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) a3 &= 0xFFFFFFFF; } + if (kvm_x86_ops->get_cpl(vcpu) != 0) { + ret = -KVM_EPERM; + goto out; + } + switch (nr) { case KVM_HC_VAPIC_POLL_IRQ: ret = 0; @@ -2904,6 +3241,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) ret = -KVM_ENOSYS; break; } +out: kvm_register_write(vcpu, VCPU_REGS_RAX, ret); ++vcpu->stat.hypercalls; return r; @@ -2983,8 +3321,6 @@ unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr) vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr); return 0; } - KVMTRACE_3D(CR_READ, vcpu, (u32)cr, (u32)value, - (u32)((u64)value >> 32), handler); return value; } @@ -2992,9 +3328,6 @@ unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr) void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val, unsigned long *rflags) { - KVMTRACE_3D(CR_WRITE, vcpu, (u32)cr, (u32)val, - (u32)((u64)val >> 32), handler); - switch (cr) { case 0: kvm_set_cr0(vcpu, mk_cr_64(vcpu->arch.cr0, val)); @@ -3104,11 +3437,11 @@ void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) kvm_register_write(vcpu, VCPU_REGS_RDX, best->edx); } kvm_x86_ops->skip_emulated_instruction(vcpu); - KVMTRACE_5D(CPUID, vcpu, function, - (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); + trace_kvm_cpuid(function, + kvm_register_read(vcpu, VCPU_REGS_RAX), + kvm_register_read(vcpu, VCPU_REGS_RBX), + kvm_register_read(vcpu, VCPU_REGS_RCX), + kvm_register_read(vcpu, VCPU_REGS_RDX)); } EXPORT_SYMBOL_GPL(kvm_emulate_cpuid); @@ -3174,6 +3507,9 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) if (!kvm_x86_ops->update_cr8_intercept) return; + if (!vcpu->arch.apic) + return; + if (!vcpu->arch.apic->vapic_addr) max_irr = kvm_lapic_find_highest_irr(vcpu); else @@ -3187,12 +3523,16 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr); } -static void inject_pending_irq(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static void inject_pending_event(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - kvm_x86_ops->set_interrupt_shadow(vcpu, 0); - /* try to reinject previous events if any */ + if (vcpu->arch.exception.pending) { + kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr, + vcpu->arch.exception.has_error_code, + vcpu->arch.exception.error_code); + return; + } + if (vcpu->arch.nmi_injected) { kvm_x86_ops->set_nmi(vcpu); return; @@ -3266,16 +3606,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) smp_mb__after_clear_bit(); if (vcpu->requests || need_resched() || signal_pending(current)) { + set_bit(KVM_REQ_KICK, &vcpu->requests); local_irq_enable(); preempt_enable(); r = 1; goto out; } - if (vcpu->arch.exception.pending) - __queue_exception(vcpu); - else - inject_pending_irq(vcpu, kvm_run); + inject_pending_event(vcpu, kvm_run); /* enable NMI/IRQ window open exits if needed */ if (vcpu->arch.nmi_pending) @@ -3292,14 +3630,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_guest_enter(); - get_debugreg(vcpu->arch.host_dr6, 6); - get_debugreg(vcpu->arch.host_dr7, 7); if (unlikely(vcpu->arch.switch_db_regs)) { - get_debugreg(vcpu->arch.host_db[0], 0); - get_debugreg(vcpu->arch.host_db[1], 1); - get_debugreg(vcpu->arch.host_db[2], 2); - get_debugreg(vcpu->arch.host_db[3], 3); - set_debugreg(0, 7); set_debugreg(vcpu->arch.eff_db[0], 0); set_debugreg(vcpu->arch.eff_db[1], 1); @@ -3307,18 +3638,17 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) set_debugreg(vcpu->arch.eff_db[3], 3); } - KVMTRACE_0D(VMENTRY, vcpu, entryexit); + trace_kvm_entry(vcpu->vcpu_id); kvm_x86_ops->run(vcpu, kvm_run); - if (unlikely(vcpu->arch.switch_db_regs)) { - set_debugreg(0, 7); - set_debugreg(vcpu->arch.host_db[0], 0); - set_debugreg(vcpu->arch.host_db[1], 1); - set_debugreg(vcpu->arch.host_db[2], 2); - set_debugreg(vcpu->arch.host_db[3], 3); + if (unlikely(vcpu->arch.switch_db_regs || test_thread_flag(TIF_DEBUG))) { + set_debugreg(current->thread.debugreg0, 0); + set_debugreg(current->thread.debugreg1, 1); + set_debugreg(current->thread.debugreg2, 2); + set_debugreg(current->thread.debugreg3, 3); + set_debugreg(current->thread.debugreg6, 6); + set_debugreg(current->thread.debugreg7, 7); } - set_debugreg(vcpu->arch.host_dr6, 6); - set_debugreg(vcpu->arch.host_dr7, 7); set_bit(KVM_REQ_KICK, &vcpu->requests); local_irq_enable(); @@ -3648,11 +3978,8 @@ static void kvm_set_segment(struct kvm_vcpu *vcpu, static void seg_desct_to_kvm_desct(struct desc_struct *seg_desc, u16 selector, struct kvm_segment *kvm_desct) { - kvm_desct->base = seg_desc->base0; - kvm_desct->base |= seg_desc->base1 << 16; - kvm_desct->base |= seg_desc->base2 << 24; - kvm_desct->limit = seg_desc->limit0; - kvm_desct->limit |= seg_desc->limit << 16; + kvm_desct->base = get_desc_base(seg_desc); + kvm_desct->limit = get_desc_limit(seg_desc); if (seg_desc->g) { kvm_desct->limit <<= 12; kvm_desct->limit |= 0xfff; @@ -3696,7 +4023,6 @@ static void get_segment_descriptor_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; @@ -3706,16 +4032,13 @@ static int load_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, kvm_queue_exception_e(vcpu, GP_VECTOR, selector & 0xfffc); return 1; } - gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, dtable.base); - gpa += index * 8; - return kvm_read_guest(vcpu->kvm, gpa, seg_desc, 8); + return kvm_read_guest_virt(dtable.base + index*8, seg_desc, sizeof(*seg_desc), vcpu); } /* 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; @@ -3723,19 +4046,13 @@ static int save_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, if (dtable.limit < index * 8 + 7) return 1; - gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, dtable.base); - gpa += index * 8; - return kvm_write_guest(vcpu->kvm, gpa, seg_desc, 8); + return kvm_write_guest_virt(dtable.base + index*8, seg_desc, sizeof(*seg_desc), vcpu); } static u32 get_tss_base_addr(struct kvm_vcpu *vcpu, struct desc_struct *seg_desc) { - u32 base_addr; - - base_addr = seg_desc->base0; - base_addr |= (seg_desc->base1 << 16); - base_addr |= (seg_desc->base2 << 24); + u32 base_addr = get_desc_base(seg_desc); return vcpu->arch.mmu.gva_to_gpa(vcpu, base_addr); } @@ -3780,12 +4097,19 @@ static int kvm_load_realmode_segment(struct kvm_vcpu *vcpu, u16 selector, int se return 0; } +static int is_vm86_segment(struct kvm_vcpu *vcpu, int seg) +{ + return (seg != VCPU_SREG_LDTR) && + (seg != VCPU_SREG_TR) && + (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_VM); +} + int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int type_bits, int seg) { struct kvm_segment kvm_seg; - if (!(vcpu->arch.cr0 & X86_CR0_PE)) + if (is_vm86_segment(vcpu, seg) || !(vcpu->arch.cr0 & X86_CR0_PE)) return kvm_load_realmode_segment(vcpu, selector, seg); if (load_segment_descriptor_to_kvm_desct(vcpu, selector, &kvm_seg)) return 1; @@ -4024,7 +4348,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) } } - if (!nseg_desc.p || (nseg_desc.limit0 | nseg_desc.limit << 16) < 0x67) { + if (!nseg_desc.p || get_desc_limit(&nseg_desc) < 0x67) { kvm_queue_exception_e(vcpu, TS_VECTOR, tss_selector & 0xfffc); return 1; } @@ -4094,13 +4418,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, vcpu->arch.cr2 = sregs->cr2; mmu_reset_needed |= vcpu->arch.cr3 != sregs->cr3; - - down_read(&vcpu->kvm->slots_lock); - if (gfn_to_memslot(vcpu->kvm, sregs->cr3 >> PAGE_SHIFT)) - vcpu->arch.cr3 = sregs->cr3; - else - set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests); - up_read(&vcpu->kvm->slots_lock); + vcpu->arch.cr3 = sregs->cr3; kvm_set_cr8(vcpu, sregs->cr8); @@ -4142,8 +4460,10 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, kvm_set_segment(vcpu, &sregs->tr, VCPU_SREG_TR); kvm_set_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); + update_cr8_intercept(vcpu); + /* Older userspace won't unhalt the vcpu on reset. */ - if (vcpu->vcpu_id == 0 && kvm_rip_read(vcpu) == 0xfff0 && + if (kvm_vcpu_is_bsp(vcpu) && kvm_rip_read(vcpu) == 0xfff0 && sregs->cs.selector == 0xf000 && sregs->cs.base == 0xffff0000 && !(vcpu->arch.cr0 & X86_CR0_PE)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -4414,7 +4734,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) kvm = vcpu->kvm; vcpu->arch.mmu.root_hpa = INVALID_PAGE; - if (!irqchip_in_kernel(kvm) || vcpu->vcpu_id == 0) + if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED; @@ -4436,6 +4756,14 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) goto fail_mmu_destroy; } + vcpu->arch.mce_banks = kzalloc(KVM_MAX_MCE_BANKS * sizeof(u64) * 4, + GFP_KERNEL); + if (!vcpu->arch.mce_banks) { + r = -ENOMEM; + goto fail_mmu_destroy; + } + vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS; + return 0; fail_mmu_destroy: @@ -4483,20 +4811,22 @@ static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) static void kvm_free_vcpus(struct kvm *kvm) { unsigned int i; + struct kvm_vcpu *vcpu; /* * Unpin any mmu pages first. */ - for (i = 0; i < KVM_MAX_VCPUS; ++i) - if (kvm->vcpus[i]) - kvm_unload_vcpu_mmu(kvm->vcpus[i]); - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - if (kvm->vcpus[i]) { - kvm_arch_vcpu_free(kvm->vcpus[i]); - kvm->vcpus[i] = NULL; - } - } + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_unload_vcpu_mmu(vcpu); + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_arch_vcpu_free(vcpu); + + mutex_lock(&kvm->lock); + for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) + kvm->vcpus[i] = NULL; + atomic_set(&kvm->online_vcpus, 0); + mutex_unlock(&kvm->lock); } void kvm_arch_sync_events(struct kvm *kvm) @@ -4573,7 +4903,6 @@ int kvm_arch_set_memory_region(struct kvm *kvm, kvm_mmu_slot_remove_write_access(kvm, mem->slot); spin_unlock(&kvm->mmu_lock); - kvm_flush_remote_tlbs(kvm); return 0; } @@ -4587,8 +4916,10 @@ void kvm_arch_flush_shadow(struct kvm *kvm) int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { return vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE - || vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED - || vcpu->arch.nmi_pending; + || vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED + || vcpu->arch.nmi_pending || + (kvm_arch_interrupt_allowed(vcpu) && + kvm_cpu_has_interrupt(vcpu)); } void kvm_vcpu_kick(struct kvm_vcpu *vcpu) @@ -4612,3 +4943,9 @@ int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) { return kvm_x86_ops->interrupt_allowed(vcpu); } + +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_msr); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_cr); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 4c8e10af78e8..5eadea585d2a 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -31,4 +31,8 @@ static inline bool kvm_exception_is_soft(unsigned int nr) { return (nr == BP_VECTOR) || (nr == OF_VECTOR); } + +struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, + u32 function, u32 index); + #endif |