diff options
34 files changed, 3054 insertions, 1093 deletions
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 9bef4e4cec50..42542eb802ca 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -175,7 +175,10 @@ Parameters: vcpu id (apic id on x86) Returns: vcpu fd on success, -1 on error This API adds a vcpu to a virtual machine. The vcpu id is a small integer -in the range [0, max_vcpus). +in the range [0, max_vcpus). You can use KVM_CAP_NR_VCPUS of the +KVM_CHECK_EXTENSION ioctl() to determine the value for max_vcpus at run-time. +If the KVM_CAP_NR_VCPUS does not exist, you should assume that max_vcpus is 4 +cpus max. 4.8 KVM_GET_DIRTY_LOG (vm ioctl) @@ -261,7 +264,7 @@ See KVM_GET_REGS for the data structure. 4.13 KVM_GET_SREGS Capability: basic -Architectures: x86 +Architectures: x86, ppc Type: vcpu ioctl Parameters: struct kvm_sregs (out) Returns: 0 on success, -1 on error @@ -279,6 +282,8 @@ struct kvm_sregs { __u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64]; }; +/* ppc -- see arch/powerpc/include/asm/kvm.h */ + interrupt_bitmap is a bitmap of pending external interrupts. At most one bit may be set. This interrupt has been acknowledged by the APIC but not yet injected into the cpu core. @@ -286,7 +291,7 @@ but not yet injected into the cpu core. 4.14 KVM_SET_SREGS Capability: basic -Architectures: x86 +Architectures: x86, ppc Type: vcpu ioctl Parameters: struct kvm_sregs (in) Returns: 0 on success, -1 on error @@ -1263,6 +1268,29 @@ struct kvm_assigned_msix_entry { __u16 padding[3]; }; +4.54 KVM_SET_TSC_KHZ + +Capability: KVM_CAP_TSC_CONTROL +Architectures: x86 +Type: vcpu ioctl +Parameters: virtual tsc_khz +Returns: 0 on success, -1 on error + +Specifies the tsc frequency for the virtual machine. The unit of the +frequency is KHz. + +4.55 KVM_GET_TSC_KHZ + +Capability: KVM_CAP_GET_TSC_KHZ +Architectures: x86 +Type: vcpu ioctl +Parameters: none +Returns: virtual tsc-khz on success, negative value on error + +Returns the tsc frequency of the guest. The unit of the return value is +KHz. If the host has unstable tsc this ioctl returns -EIO instead as an +error. + 5. The kvm_run structure Application code obtains a pointer to the kvm_run structure by diff --git a/arch/ia64/kvm/vti.h b/arch/ia64/kvm/vti.h index f6c5617e16af..b214b5b0432d 100644 --- a/arch/ia64/kvm/vti.h +++ b/arch/ia64/kvm/vti.h @@ -83,13 +83,13 @@ union vac { unsigned long value; struct { - int a_int:1; - int a_from_int_cr:1; - int a_to_int_cr:1; - int a_from_psr:1; - int a_from_cpuid:1; - int a_cover:1; - int a_bsw:1; + unsigned int a_int:1; + unsigned int a_from_int_cr:1; + unsigned int a_to_int_cr:1; + unsigned int a_from_psr:1; + unsigned int a_from_cpuid:1; + unsigned int a_cover:1; + unsigned int a_bsw:1; long reserved:57; }; }; @@ -97,12 +97,12 @@ union vac { union vdc { unsigned long value; struct { - int d_vmsw:1; - int d_extint:1; - int d_ibr_dbr:1; - int d_pmc:1; - int d_to_pmd:1; - int d_itm:1; + unsigned int d_vmsw:1; + unsigned int d_extint:1; + unsigned int d_ibr_dbr:1; + unsigned int d_pmc:1; + unsigned int d_to_pmd:1; + unsigned int d_itm:1; long reserved:58; }; }; diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h index 18ea6963ad77..d2ca5ed3877b 100644 --- a/arch/powerpc/include/asm/kvm.h +++ b/arch/powerpc/include/asm/kvm.h @@ -45,6 +45,114 @@ struct kvm_regs { __u64 gpr[32]; }; +#define KVM_SREGS_E_IMPL_NONE 0 +#define KVM_SREGS_E_IMPL_FSL 1 + +#define KVM_SREGS_E_FSL_PIDn (1 << 0) /* PID1/PID2 */ + +/* + * Feature bits indicate which sections of the sregs struct are valid, + * both in KVM_GET_SREGS and KVM_SET_SREGS. On KVM_SET_SREGS, registers + * corresponding to unset feature bits will not be modified. This allows + * restoring a checkpoint made without that feature, while keeping the + * default values of the new registers. + * + * KVM_SREGS_E_BASE contains: + * CSRR0/1 (refers to SRR2/3 on 40x) + * ESR + * DEAR + * MCSR + * TSR + * TCR + * DEC + * TB + * VRSAVE (USPRG0) + */ +#define KVM_SREGS_E_BASE (1 << 0) + +/* + * KVM_SREGS_E_ARCH206 contains: + * + * PIR + * MCSRR0/1 + * DECAR + * IVPR + */ +#define KVM_SREGS_E_ARCH206 (1 << 1) + +/* + * Contains EPCR, plus the upper half of 64-bit registers + * that are 32-bit on 32-bit implementations. + */ +#define KVM_SREGS_E_64 (1 << 2) + +#define KVM_SREGS_E_SPRG8 (1 << 3) +#define KVM_SREGS_E_MCIVPR (1 << 4) + +/* + * IVORs are used -- contains IVOR0-15, plus additional IVORs + * in combination with an appropriate feature bit. + */ +#define KVM_SREGS_E_IVOR (1 << 5) + +/* + * Contains MAS0-4, MAS6-7, TLBnCFG, MMUCFG. + * Also TLBnPS if MMUCFG[MAVN] = 1. + */ +#define KVM_SREGS_E_ARCH206_MMU (1 << 6) + +/* DBSR, DBCR, IAC, DAC, DVC */ +#define KVM_SREGS_E_DEBUG (1 << 7) + +/* Enhanced debug -- DSRR0/1, SPRG9 */ +#define KVM_SREGS_E_ED (1 << 8) + +/* Embedded Floating Point (SPE) -- IVOR32-34 if KVM_SREGS_E_IVOR */ +#define KVM_SREGS_E_SPE (1 << 9) + +/* External Proxy (EXP) -- EPR */ +#define KVM_SREGS_EXP (1 << 10) + +/* External PID (E.PD) -- EPSC/EPLC */ +#define KVM_SREGS_E_PD (1 << 11) + +/* Processor Control (E.PC) -- IVOR36-37 if KVM_SREGS_E_IVOR */ +#define KVM_SREGS_E_PC (1 << 12) + +/* Page table (E.PT) -- EPTCFG */ +#define KVM_SREGS_E_PT (1 << 13) + +/* Embedded Performance Monitor (E.PM) -- IVOR35 if KVM_SREGS_E_IVOR */ +#define KVM_SREGS_E_PM (1 << 14) + +/* + * Special updates: + * + * Some registers may change even while a vcpu is not running. + * To avoid losing these changes, by default these registers are + * not updated by KVM_SET_SREGS. To force an update, set the bit + * in u.e.update_special corresponding to the register to be updated. + * + * The update_special field is zero on return from KVM_GET_SREGS. + * + * When restoring a checkpoint, the caller can set update_special + * to 0xffffffff to ensure that everything is restored, even new features + * that the caller doesn't know about. + */ +#define KVM_SREGS_E_UPDATE_MCSR (1 << 0) +#define KVM_SREGS_E_UPDATE_TSR (1 << 1) +#define KVM_SREGS_E_UPDATE_DEC (1 << 2) +#define KVM_SREGS_E_UPDATE_DBSR (1 << 3) + +/* + * In KVM_SET_SREGS, reserved/pad fields must be left untouched from a + * previous KVM_GET_REGS. + * + * Unless otherwise indicated, setting any register with KVM_SET_SREGS + * directly sets its value. It does not trigger any special semantics such + * as write-one-to-clear. Calling KVM_SET_SREGS on an unmodified struct + * just received from KVM_GET_SREGS is always a no-op. + */ struct kvm_sregs { __u32 pvr; union { @@ -62,6 +170,82 @@ struct kvm_sregs { __u64 dbat[8]; } ppc32; } s; + struct { + union { + struct { /* KVM_SREGS_E_IMPL_FSL */ + __u32 features; /* KVM_SREGS_E_FSL_ */ + __u32 svr; + __u64 mcar; + __u32 hid0; + + /* KVM_SREGS_E_FSL_PIDn */ + __u32 pid1, pid2; + } fsl; + __u8 pad[256]; + } impl; + + __u32 features; /* KVM_SREGS_E_ */ + __u32 impl_id; /* KVM_SREGS_E_IMPL_ */ + __u32 update_special; /* KVM_SREGS_E_UPDATE_ */ + __u32 pir; /* read-only */ + __u64 sprg8; + __u64 sprg9; /* E.ED */ + __u64 csrr0; + __u64 dsrr0; /* E.ED */ + __u64 mcsrr0; + __u32 csrr1; + __u32 dsrr1; /* E.ED */ + __u32 mcsrr1; + __u32 esr; + __u64 dear; + __u64 ivpr; + __u64 mcivpr; + __u64 mcsr; /* KVM_SREGS_E_UPDATE_MCSR */ + + __u32 tsr; /* KVM_SREGS_E_UPDATE_TSR */ + __u32 tcr; + __u32 decar; + __u32 dec; /* KVM_SREGS_E_UPDATE_DEC */ + + /* + * Userspace can read TB directly, but the + * value reported here is consistent with "dec". + * + * Read-only. + */ + __u64 tb; + + __u32 dbsr; /* KVM_SREGS_E_UPDATE_DBSR */ + __u32 dbcr[3]; + __u32 iac[4]; + __u32 dac[2]; + __u32 dvc[2]; + __u8 num_iac; /* read-only */ + __u8 num_dac; /* read-only */ + __u8 num_dvc; /* read-only */ + __u8 pad; + + __u32 epr; /* EXP */ + __u32 vrsave; /* a.k.a. USPRG0 */ + __u32 epcr; /* KVM_SREGS_E_64 */ + + __u32 mas0; + __u32 mas1; + __u64 mas2; + __u64 mas7_3; + __u32 mas4; + __u32 mas6; + + __u32 ivor_low[16]; /* IVOR0-15 */ + __u32 ivor_high[18]; /* IVOR32+, plus room to expand */ + + __u32 mmucfg; /* read-only */ + __u32 eptcfg; /* E.PT, read-only */ + __u32 tlbcfg[4];/* read-only */ + __u32 tlbps[4]; /* read-only */ + + __u32 eplc, epsc; /* E.PD */ + } e; __u8 pad[1020]; } u; }; diff --git a/arch/powerpc/include/asm/kvm_44x.h b/arch/powerpc/include/asm/kvm_44x.h index d22d39942a92..a0e57618ff33 100644 --- a/arch/powerpc/include/asm/kvm_44x.h +++ b/arch/powerpc/include/asm/kvm_44x.h @@ -61,7 +61,6 @@ static inline struct kvmppc_vcpu_44x *to_44x(struct kvm_vcpu *vcpu) return container_of(vcpu, struct kvmppc_vcpu_44x, vcpu); } -void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 new_pid); void kvmppc_44x_tlb_put(struct kvm_vcpu *vcpu); void kvmppc_44x_tlb_load(struct kvm_vcpu *vcpu); diff --git a/arch/powerpc/include/asm/kvm_e500.h b/arch/powerpc/include/asm/kvm_e500.h index 7fea26fffb25..7a2a565f88c4 100644 --- a/arch/powerpc/include/asm/kvm_e500.h +++ b/arch/powerpc/include/asm/kvm_e500.h @@ -43,6 +43,7 @@ struct kvmppc_vcpu_e500 { u32 host_pid[E500_PID_NUM]; u32 pid[E500_PID_NUM]; + u32 svr; u32 mas0; u32 mas1; @@ -58,6 +59,7 @@ struct kvmppc_vcpu_e500 { u32 hid1; u32 tlb0cfg; u32 tlb1cfg; + u64 mcar; struct kvm_vcpu vcpu; }; diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index bba3b9b72a39..186f150b9b89 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -223,6 +223,7 @@ struct kvm_vcpu_arch { ulong hflags; ulong guest_owned_ext; #endif + u32 vrsave; /* also USPRG0 */ u32 mmucr; ulong sprg4; ulong sprg5; @@ -232,6 +233,9 @@ struct kvm_vcpu_arch { ulong csrr1; ulong dsrr0; ulong dsrr1; + ulong mcsrr0; + ulong mcsrr1; + ulong mcsr; ulong esr; u32 dec; u32 decar; @@ -255,6 +259,7 @@ struct kvm_vcpu_arch { u32 dbsr; #ifdef CONFIG_KVM_EXIT_TIMING + struct mutex exit_timing_lock; struct kvmppc_exit_timing timing_exit; struct kvmppc_exit_timing timing_last_enter; u32 last_exit_type; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index ecb3bc74c344..9345238edecf 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -61,6 +61,7 @@ extern int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu); extern int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu); extern void kvmppc_emulate_dec(struct kvm_vcpu *vcpu); +extern u32 kvmppc_get_dec(struct kvm_vcpu *vcpu, u64 tb); /* Core-specific hooks */ @@ -142,4 +143,12 @@ static inline u32 kvmppc_set_field(u64 inst, int msb, int lsb, int value) return r; } +void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); +int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); + +void kvmppc_get_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); +int kvmppc_set_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); + +void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid); + #endif /* __POWERPC_KVM_PPC_H__ */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 6887661ac072..36e1c8a29be8 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -396,6 +396,7 @@ int main(void) DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack)); DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid)); DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr)); + DEFINE(VCPU_VRSAVE, offsetof(struct kvm_vcpu, arch.vrsave)); DEFINE(VCPU_SPRG4, offsetof(struct kvm_vcpu, arch.sprg4)); DEFINE(VCPU_SPRG5, offsetof(struct kvm_vcpu, arch.sprg5)); DEFINE(VCPU_SPRG6, offsetof(struct kvm_vcpu, arch.sprg6)); diff --git a/arch/powerpc/kvm/44x.c b/arch/powerpc/kvm/44x.c index 74d0e7421143..da3a1225c0ac 100644 --- a/arch/powerpc/kvm/44x.c +++ b/arch/powerpc/kvm/44x.c @@ -107,6 +107,16 @@ int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu, return 0; } +void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + kvmppc_get_sregs_ivor(vcpu, sregs); +} + +int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + return kvmppc_set_sregs_ivor(vcpu, sregs); +} + struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) { struct kvmppc_vcpu_44x *vcpu_44x; diff --git a/arch/powerpc/kvm/44x_emulate.c b/arch/powerpc/kvm/44x_emulate.c index 65ea083a5b27..549bb2c9a47a 100644 --- a/arch/powerpc/kvm/44x_emulate.c +++ b/arch/powerpc/kvm/44x_emulate.c @@ -158,7 +158,6 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs) emulated = kvmppc_booke_emulate_mtspr(vcpu, sprn, rs); } - kvmppc_set_exit_type(vcpu, EMULATED_MTSPR_EXITS); return emulated; } @@ -179,7 +178,6 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt) emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, rt); } - kvmppc_set_exit_type(vcpu, EMULATED_MFSPR_EXITS); return emulated; } diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index ef76acb455c3..8462b3a1c1c7 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -569,6 +569,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) kvmppc_set_msr(vcpu, regs->msr); vcpu->arch.shared->srr0 = regs->srr0; vcpu->arch.shared->srr1 = regs->srr1; + kvmppc_set_pid(vcpu, regs->pid); vcpu->arch.shared->sprg0 = regs->sprg0; vcpu->arch.shared->sprg1 = regs->sprg1; vcpu->arch.shared->sprg2 = regs->sprg2; @@ -584,16 +585,165 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) return 0; } +static void get_sregs_base(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) +{ + u64 tb = get_tb(); + + sregs->u.e.features |= KVM_SREGS_E_BASE; + + sregs->u.e.csrr0 = vcpu->arch.csrr0; + sregs->u.e.csrr1 = vcpu->arch.csrr1; + sregs->u.e.mcsr = vcpu->arch.mcsr; + sregs->u.e.esr = vcpu->arch.esr; + sregs->u.e.dear = vcpu->arch.shared->dar; + sregs->u.e.tsr = vcpu->arch.tsr; + sregs->u.e.tcr = vcpu->arch.tcr; + sregs->u.e.dec = kvmppc_get_dec(vcpu, tb); + sregs->u.e.tb = tb; + sregs->u.e.vrsave = vcpu->arch.vrsave; +} + +static int set_sregs_base(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) +{ + if (!(sregs->u.e.features & KVM_SREGS_E_BASE)) + return 0; + + vcpu->arch.csrr0 = sregs->u.e.csrr0; + vcpu->arch.csrr1 = sregs->u.e.csrr1; + vcpu->arch.mcsr = sregs->u.e.mcsr; + vcpu->arch.esr = sregs->u.e.esr; + vcpu->arch.shared->dar = sregs->u.e.dear; + vcpu->arch.vrsave = sregs->u.e.vrsave; + vcpu->arch.tcr = sregs->u.e.tcr; + + if (sregs->u.e.update_special & KVM_SREGS_E_UPDATE_DEC) + vcpu->arch.dec = sregs->u.e.dec; + + kvmppc_emulate_dec(vcpu); + + if (sregs->u.e.update_special & KVM_SREGS_E_UPDATE_TSR) { + /* + * FIXME: existing KVM timer handling is incomplete. + * TSR cannot be read by the guest, and its value in + * vcpu->arch is always zero. For now, just handle + * the case where the caller is trying to inject a + * decrementer interrupt. + */ + + if ((sregs->u.e.tsr & TSR_DIS) && + (vcpu->arch.tcr & TCR_DIE)) + kvmppc_core_queue_dec(vcpu); + } + + return 0; +} + +static void get_sregs_arch206(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) +{ + sregs->u.e.features |= KVM_SREGS_E_ARCH206; + + sregs->u.e.pir = 0; + sregs->u.e.mcsrr0 = vcpu->arch.mcsrr0; + sregs->u.e.mcsrr1 = vcpu->arch.mcsrr1; + sregs->u.e.decar = vcpu->arch.decar; + sregs->u.e.ivpr = vcpu->arch.ivpr; +} + +static int set_sregs_arch206(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) +{ + if (!(sregs->u.e.features & KVM_SREGS_E_ARCH206)) + return 0; + + if (sregs->u.e.pir != 0) + return -EINVAL; + + vcpu->arch.mcsrr0 = sregs->u.e.mcsrr0; + vcpu->arch.mcsrr1 = sregs->u.e.mcsrr1; + vcpu->arch.decar = sregs->u.e.decar; + vcpu->arch.ivpr = sregs->u.e.ivpr; + + return 0; +} + +void kvmppc_get_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + sregs->u.e.features |= KVM_SREGS_E_IVOR; + + sregs->u.e.ivor_low[0] = vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL]; + sregs->u.e.ivor_low[1] = vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK]; + sregs->u.e.ivor_low[2] = vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE]; + sregs->u.e.ivor_low[3] = vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE]; + sregs->u.e.ivor_low[4] = vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL]; + sregs->u.e.ivor_low[5] = vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT]; + sregs->u.e.ivor_low[6] = vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM]; + sregs->u.e.ivor_low[7] = vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL]; + sregs->u.e.ivor_low[8] = vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL]; + sregs->u.e.ivor_low[9] = vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL]; + sregs->u.e.ivor_low[10] = vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER]; + sregs->u.e.ivor_low[11] = vcpu->arch.ivor[BOOKE_IRQPRIO_FIT]; + sregs->u.e.ivor_low[12] = vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG]; + sregs->u.e.ivor_low[13] = vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS]; + sregs->u.e.ivor_low[14] = vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS]; + sregs->u.e.ivor_low[15] = vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG]; +} + +int kvmppc_set_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + if (!(sregs->u.e.features & KVM_SREGS_E_IVOR)) + return 0; + + vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL] = sregs->u.e.ivor_low[0]; + vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK] = sregs->u.e.ivor_low[1]; + vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE] = sregs->u.e.ivor_low[2]; + vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE] = sregs->u.e.ivor_low[3]; + vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL] = sregs->u.e.ivor_low[4]; + vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT] = sregs->u.e.ivor_low[5]; + vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM] = sregs->u.e.ivor_low[6]; + vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL] = sregs->u.e.ivor_low[7]; + vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL] = sregs->u.e.ivor_low[8]; + vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL] = sregs->u.e.ivor_low[9]; + vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER] = sregs->u.e.ivor_low[10]; + vcpu->arch.ivor[BOOKE_IRQPRIO_FIT] = sregs->u.e.ivor_low[11]; + vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG] = sregs->u.e.ivor_low[12]; + vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS] = sregs->u.e.ivor_low[13]; + vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS] = sregs->u.e.ivor_low[14]; + vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG] = sregs->u.e.ivor_low[15]; + + return 0; +} + int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { - return -ENOTSUPP; + sregs->pvr = vcpu->arch.pvr; + + get_sregs_base(vcpu, sregs); + get_sregs_arch206(vcpu, sregs); + kvmppc_core_get_sregs(vcpu, sregs); + return 0; } int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { - return -ENOTSUPP; + int ret; + + if (vcpu->arch.pvr != sregs->pvr) + return -EINVAL; + + ret = set_sregs_base(vcpu, sregs); + if (ret < 0) + return ret; + + ret = set_sregs_arch206(vcpu, sregs); + if (ret < 0) + return ret; + + return kvmppc_core_set_sregs(vcpu, sregs); } int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S index 1cc471faac2d..b58ccae95904 100644 --- a/arch/powerpc/kvm/booke_interrupts.S +++ b/arch/powerpc/kvm/booke_interrupts.S @@ -380,7 +380,6 @@ lightweight_exit: * because host interrupt handlers would get confused. */ lwz r1, VCPU_GPR(r1)(r4) - /* XXX handle USPRG0 */ /* Host interrupt handlers may have clobbered these guest-readable * SPRGs, so we need to reload them here with the guest's values. */ lwz r3, VCPU_SPRG4(r4) diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index e3768ee9b595..318dbc61ba44 100644 --- a/arch/powerpc/kvm/e500.c +++ b/arch/powerpc/kvm/e500.c @@ -63,6 +63,7 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu) /* Registers init */ vcpu->arch.pvr = mfspr(SPRN_PVR); + vcpu_e500->svr = mfspr(SPRN_SVR); /* Since booke kvm only support one core, update all vcpus' PIR to 0 */ vcpu->vcpu_id = 0; @@ -96,6 +97,81 @@ int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu, return 0; } +void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); + + sregs->u.e.features |= KVM_SREGS_E_ARCH206_MMU | KVM_SREGS_E_SPE | + KVM_SREGS_E_PM; + sregs->u.e.impl_id = KVM_SREGS_E_IMPL_FSL; + + sregs->u.e.impl.fsl.features = 0; + sregs->u.e.impl.fsl.svr = vcpu_e500->svr; + sregs->u.e.impl.fsl.hid0 = vcpu_e500->hid0; + sregs->u.e.impl.fsl.mcar = vcpu_e500->mcar; + + sregs->u.e.mas0 = vcpu_e500->mas0; + sregs->u.e.mas1 = vcpu_e500->mas1; + sregs->u.e.mas2 = vcpu_e500->mas2; + sregs->u.e.mas7_3 = ((u64)vcpu_e500->mas7 << 32) | vcpu_e500->mas3; + sregs->u.e.mas4 = vcpu_e500->mas4; + sregs->u.e.mas6 = vcpu_e500->mas6; + + sregs->u.e.mmucfg = mfspr(SPRN_MMUCFG); + sregs->u.e.tlbcfg[0] = vcpu_e500->tlb0cfg; + sregs->u.e.tlbcfg[1] = vcpu_e500->tlb1cfg; + sregs->u.e.tlbcfg[2] = 0; + sregs->u.e.tlbcfg[3] = 0; + + sregs->u.e.ivor_high[0] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL]; + sregs->u.e.ivor_high[1] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA]; + sregs->u.e.ivor_high[2] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND]; + sregs->u.e.ivor_high[3] = + vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR]; + + kvmppc_get_sregs_ivor(vcpu, sregs); +} + +int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); + + if (sregs->u.e.impl_id == KVM_SREGS_E_IMPL_FSL) { + vcpu_e500->svr = sregs->u.e.impl.fsl.svr; + vcpu_e500->hid0 = sregs->u.e.impl.fsl.hid0; + vcpu_e500->mcar = sregs->u.e.impl.fsl.mcar; + } + + if (sregs->u.e.features & KVM_SREGS_E_ARCH206_MMU) { + vcpu_e500->mas0 = sregs->u.e.mas0; + vcpu_e500->mas1 = sregs->u.e.mas1; + vcpu_e500->mas2 = sregs->u.e.mas2; + vcpu_e500->mas7 = sregs->u.e.mas7_3 >> 32; + vcpu_e500->mas3 = (u32)sregs->u.e.mas7_3; + vcpu_e500->mas4 = sregs->u.e.mas4; + vcpu_e500->mas6 = sregs->u.e.mas6; + } + + if (!(sregs->u.e.features & KVM_SREGS_E_IVOR)) + return 0; + + if (sregs->u.e.features & KVM_SREGS_E_SPE) { + vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL] = + sregs->u.e.ivor_high[0]; + vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA] = + sregs->u.e.ivor_high[1]; + vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND] = + sregs->u.e.ivor_high[2]; + } + + if (sregs->u.e.features & KVM_SREGS_E_PM) { + vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR] = + sregs->u.e.ivor_high[3]; + } + + return kvmppc_set_sregs_ivor(vcpu, sregs); +} + struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) { struct kvmppc_vcpu_e500 *vcpu_e500; diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c index 8e3edfbc9634..69cd665a0caf 100644 --- a/arch/powerpc/kvm/e500_emulate.c +++ b/arch/powerpc/kvm/e500_emulate.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved. + * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved. * * Author: Yu Liu, <yu.liu@freescale.com> * @@ -78,8 +78,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs) switch (sprn) { case SPRN_PID: - vcpu_e500->pid[0] = vcpu->arch.shadow_pid = - vcpu->arch.pid = spr_val; + kvmppc_set_pid(vcpu, spr_val); break; case SPRN_PID1: vcpu_e500->pid[1] = spr_val; break; @@ -175,6 +174,8 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt) kvmppc_set_gpr(vcpu, rt, vcpu_e500->hid0); break; case SPRN_HID1: kvmppc_set_gpr(vcpu, rt, vcpu_e500->hid1); break; + case SPRN_SVR: + kvmppc_set_gpr(vcpu, rt, vcpu_e500->svr); break; case SPRN_MMUCSR0: kvmppc_set_gpr(vcpu, rt, 0); break; diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c index d6d6d47a75a9..b18fe353397d 100644 --- a/arch/powerpc/kvm/e500_tlb.c +++ b/arch/powerpc/kvm/e500_tlb.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved. + * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved. * * Author: Yu Liu, yu.liu@freescale.com * @@ -24,6 +24,7 @@ #include "../mm/mmu_decl.h" #include "e500_tlb.h" #include "trace.h" +#include "timing.h" #define to_htlb1_esel(esel) (tlb1_entry_num - (esel) - 1) @@ -506,6 +507,7 @@ int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb) vcpu_e500->mas7 = 0; } + kvmppc_set_exit_type(vcpu, EMULATED_TLBSX_EXITS); return EMULATE_DONE; } @@ -571,6 +573,7 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu) write_host_tlbe(vcpu_e500, stlbsel, sesel); } + kvmppc_set_exit_type(vcpu, EMULATED_TLBWE_EXITS); return EMULATE_DONE; } @@ -672,6 +675,14 @@ int kvmppc_e500_tlb_search(struct kvm_vcpu *vcpu, return -1; } +void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid) +{ + struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); + + vcpu_e500->pid[0] = vcpu->arch.shadow_pid = + vcpu->arch.pid = pid; +} + void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *vcpu_e500) { struct tlbe *tlbe; diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c index c64fd2909bb2..141dce3c6810 100644 --- a/arch/powerpc/kvm/emulate.c +++ b/arch/powerpc/kvm/emulate.c @@ -114,6 +114,12 @@ void kvmppc_emulate_dec(struct kvm_vcpu *vcpu) } } +u32 kvmppc_get_dec(struct kvm_vcpu *vcpu, u64 tb) +{ + u64 jd = tb - vcpu->arch.dec_jiffies; + return vcpu->arch.dec - jd; +} + /* XXX to do: * lhax * lhaux @@ -279,11 +285,8 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) case SPRN_DEC: { - u64 jd = get_tb() - vcpu->arch.dec_jiffies; - kvmppc_set_gpr(vcpu, rt, vcpu->arch.dec - jd); - pr_debug("mfDEC: %x - %llx = %lx\n", - vcpu->arch.dec, jd, - kvmppc_get_gpr(vcpu, rt)); + kvmppc_set_gpr(vcpu, rt, + kvmppc_get_dec(vcpu, get_tb())); break; } default: @@ -294,6 +297,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) } break; } + kvmppc_set_exit_type(vcpu, EMULATED_MFSPR_EXITS); break; case OP_31_XOP_STHX: @@ -363,6 +367,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) printk("mtspr: unknown spr %x\n", sprn); break; } + kvmppc_set_exit_type(vcpu, EMULATED_MTSPR_EXITS); break; case OP_31_XOP_DCBI: diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 99758460efde..616dd516ca1f 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -175,7 +175,11 @@ int kvm_dev_ioctl_check_extension(long ext) int r; switch (ext) { +#ifdef CONFIG_BOOKE + case KVM_CAP_PPC_BOOKE_SREGS: +#else case KVM_CAP_PPC_SEGSTATE: +#endif case KVM_CAP_PPC_PAIRED_SINGLES: case KVM_CAP_PPC_UNSET_IRQ: case KVM_CAP_PPC_IRQ_LEVEL: @@ -284,6 +288,10 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) tasklet_init(&vcpu->arch.tasklet, kvmppc_decrementer_func, (ulong)vcpu); vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup; +#ifdef CONFIG_KVM_EXIT_TIMING + mutex_init(&vcpu->arch.exit_timing_lock); +#endif + return 0; } @@ -294,12 +302,25 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { +#ifdef CONFIG_BOOKE + /* + * vrsave (formerly usprg0) isn't used by Linux, but may + * be used by the guest. + * + * On non-booke this is associated with Altivec and + * is handled by code in book3s.c. + */ + mtspr(SPRN_VRSAVE, vcpu->arch.vrsave); +#endif kvmppc_core_vcpu_load(vcpu, cpu); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { kvmppc_core_vcpu_put(vcpu); +#ifdef CONFIG_BOOKE + vcpu->arch.vrsave = mfspr(SPRN_VRSAVE); +#endif } int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, diff --git a/arch/powerpc/kvm/timing.c b/arch/powerpc/kvm/timing.c index a021f5827a33..319177df9587 100644 --- a/arch/powerpc/kvm/timing.c +++ b/arch/powerpc/kvm/timing.c @@ -34,8 +34,8 @@ void kvmppc_init_timing_stats(struct kvm_vcpu *vcpu) { int i; - /* pause guest execution to avoid concurrent updates */ - mutex_lock(&vcpu->mutex); + /* Take a lock to avoid concurrent updates */ + mutex_lock(&vcpu->arch.exit_timing_lock); vcpu->arch.last_exit_type = 0xDEAD; for (i = 0; i < __NUMBER_OF_KVM_EXIT_TYPES; i++) { @@ -49,7 +49,7 @@ void kvmppc_init_timing_stats(struct kvm_vcpu *vcpu) vcpu->arch.timing_exit.tv64 = 0; vcpu->arch.timing_last_enter.tv64 = 0; - mutex_unlock(&vcpu->mutex); + mutex_unlock(&vcpu->arch.exit_timing_lock); } static void add_exit_timing(struct kvm_vcpu *vcpu, u64 duration, int type) @@ -65,6 +65,8 @@ static void add_exit_timing(struct kvm_vcpu *vcpu, u64 duration, int type) return; } + mutex_lock(&vcpu->arch.exit_timing_lock); + vcpu->arch.timing_count_type[type]++; /* sum */ @@ -93,6 +95,8 @@ static void add_exit_timing(struct kvm_vcpu *vcpu, u64 duration, int type) vcpu->arch.timing_min_duration[type] = duration; if (unlikely(duration > vcpu->arch.timing_max_duration[type])) vcpu->arch.timing_max_duration[type] = duration; + + mutex_unlock(&vcpu->arch.exit_timing_lock); } void kvmppc_update_timing_stats(struct kvm_vcpu *vcpu) @@ -147,17 +151,30 @@ static int kvmppc_exit_timing_show(struct seq_file *m, void *private) { struct kvm_vcpu *vcpu = m->private; int i; + u64 min, max, sum, sum_quad; seq_printf(m, "%s", "type count min max sum sum_squared\n"); + for (i = 0; i < __NUMBER_OF_KVM_EXIT_TYPES; i++) { + + min = vcpu->arch.timing_min_duration[i]; + do_div(min, tb_ticks_per_usec); + max = vcpu->arch.timing_max_duration[i]; + do_div(max, tb_ticks_per_usec); + sum = vcpu->arch.timing_sum_duration[i]; + do_div(sum, tb_ticks_per_usec); + sum_quad = vcpu->arch.timing_sum_quad_duration[i]; + do_div(sum_quad, tb_ticks_per_usec); + seq_printf(m, "%12s %10d %10lld %10lld %20lld %20lld\n", kvm_exit_names[i], vcpu->arch.timing_count_type[i], - vcpu->arch.timing_min_duration[i], - vcpu->arch.timing_max_duration[i], - vcpu->arch.timing_sum_duration[i], - vcpu->arch.timing_sum_quad_duration[i]); + min, + max, + sum, + sum_quad); + } return 0; } diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 0f5213564326..0049211959c0 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -14,6 +14,8 @@ #include <asm/desc_defs.h> struct x86_emulate_ctxt; +enum x86_intercept; +enum x86_intercept_stage; struct x86_exception { u8 vector; @@ -24,6 +26,24 @@ struct x86_exception { }; /* + * This struct is used to carry enough information from the instruction + * decoder to main KVM so that a decision can be made whether the + * instruction needs to be intercepted or not. + */ +struct x86_instruction_info { + u8 intercept; /* which intercept */ + u8 rep_prefix; /* rep prefix? */ + u8 modrm_mod; /* mod part of modrm */ + u8 modrm_reg; /* index of register used */ + u8 modrm_rm; /* rm part of modrm */ + u64 src_val; /* value of source operand */ + u8 src_bytes; /* size of source operand */ + u8 dst_bytes; /* size of destination operand */ + u8 ad_bytes; /* size of src/dst address */ + u64 next_rip; /* rip following the instruction */ +}; + +/* * x86_emulate_ops: * * These operations represent the instruction emulator's interface to memory. @@ -62,6 +82,7 @@ struct x86_exception { #define X86EMUL_RETRY_INSTR 3 /* retry the instruction for some reason */ #define X86EMUL_CMPXCHG_FAILED 4 /* cmpxchg did not see expected value */ #define X86EMUL_IO_NEEDED 5 /* IO is needed to complete emulation */ +#define X86EMUL_INTERCEPTED 6 /* Intercepted by nested VMCB/VMCS */ struct x86_emulate_ops { /* @@ -71,8 +92,9 @@ struct x86_emulate_ops { * @val: [OUT] Value read from memory, zero-extended to 'u_long'. * @bytes: [IN ] Number of bytes to read from memory. */ - int (*read_std)(unsigned long addr, void *val, - unsigned int bytes, struct kvm_vcpu *vcpu, + int (*read_std)(struct x86_emulate_ctxt *ctxt, + unsigned long addr, void *val, + unsigned int bytes, struct x86_exception *fault); /* @@ -82,8 +104,8 @@ struct x86_emulate_ops { * @val: [OUT] Value write to memory, zero-extended to 'u_long'. * @bytes: [IN ] Number of bytes to write to memory. */ - int (*write_std)(unsigned long addr, void *val, - unsigned int bytes, struct kvm_vcpu *vcpu, + int (*write_std)(struct x86_emulate_ctxt *ctxt, + unsigned long addr, void *val, unsigned int bytes, struct x86_exception *fault); /* * fetch: Read bytes of standard (non-emulated/special) memory. @@ -92,8 +114,8 @@ struct x86_emulate_ops { * @val: [OUT] Value read from memory, zero-extended to 'u_long'. * @bytes: [IN ] Number of bytes to read from memory. */ - int (*fetch)(unsigned long addr, void *val, - unsigned int bytes, struct kvm_vcpu *vcpu, + int (*fetch)(struct x86_emulate_ctxt *ctxt, + unsigned long addr, void *val, unsigned int bytes, struct x86_exception *fault); /* @@ -102,11 +124,9 @@ struct x86_emulate_ops { * @val: [OUT] Value read from memory, zero-extended to 'u_long'. * @bytes: [IN ] Number of bytes to read from memory. */ - int (*read_emulated)(unsigned long addr, - void *val, - unsigned int bytes, - struct x86_exception *fault, - struct kvm_vcpu *vcpu); + int (*read_emulated)(struct x86_emulate_ctxt *ctxt, + unsigned long addr, void *val, unsigned int bytes, + struct x86_exception *fault); /* * write_emulated: Write bytes to emulated/special memory area. @@ -115,11 +135,10 @@ struct x86_emulate_ops { * required). * @bytes: [IN ] Number of bytes to write to memory. */ - int (*write_emulated)(unsigned long addr, - const void *val, + int (*write_emulated)(struct x86_emulate_ctxt *ctxt, + unsigned long addr, const void *val, unsigned int bytes, - struct x86_exception *fault, - struct kvm_vcpu *vcpu); + struct x86_exception *fault); /* * cmpxchg_emulated: Emulate an atomic (LOCKed) CMPXCHG operation on an @@ -129,40 +148,54 @@ struct x86_emulate_ops { * @new: [IN ] Value to write to @addr. * @bytes: [IN ] Number of bytes to access using CMPXCHG. */ - int (*cmpxchg_emulated)(unsigned long addr, + int (*cmpxchg_emulated)(struct x86_emulate_ctxt *ctxt, + unsigned long addr, const void *old, const void *new, unsigned int bytes, - struct x86_exception *fault, - struct kvm_vcpu *vcpu); - - int (*pio_in_emulated)(int size, unsigned short port, void *val, - unsigned int count, struct kvm_vcpu *vcpu); - - int (*pio_out_emulated)(int size, unsigned short port, const void *val, - unsigned int count, struct kvm_vcpu *vcpu); - - bool (*get_cached_descriptor)(struct desc_struct *desc, u32 *base3, - int seg, struct kvm_vcpu *vcpu); - void (*set_cached_descriptor)(struct desc_struct *desc, u32 base3, - int seg, struct kvm_vcpu *vcpu); - u16 (*get_segment_selector)(int seg, struct kvm_vcpu *vcpu); - void (*set_segment_selector)(u16 sel, int seg, struct kvm_vcpu *vcpu); - unsigned long (*get_cached_segment_base)(int seg, struct kvm_vcpu *vcpu); - void (*get_gdt)(struct desc_ptr *dt, struct kvm_vcpu *vcpu); - void (*get_idt)(struct desc_ptr *dt, struct kvm_vcpu *vcpu); - ulong (*get_cr)(int cr, struct kvm_vcpu *vcpu); - int (*set_cr)(int cr, ulong val, struct kvm_vcpu *vcpu); - int (*cpl)(struct kvm_vcpu *vcpu); - int (*get_dr)(int dr, unsigned long *dest, struct kvm_vcpu *vcpu); - int (*set_dr)(int dr, unsigned long value, struct kvm_vcpu *vcpu); - int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); - int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); + struct x86_exception *fault); + void (*invlpg)(struct x86_emulate_ctxt *ctxt, ulong addr); + + int (*pio_in_emulated)(struct x86_emulate_ctxt *ctxt, + int size, unsigned short port, void *val, + unsigned int count); + + int (*pio_out_emulated)(struct x86_emulate_ctxt *ctxt, + int size, unsigned short port, const void *val, + unsigned int count); + + bool (*get_segment)(struct x86_emulate_ctxt *ctxt, u16 *selector, + struct desc_struct *desc, u32 *base3, int seg); + void (*set_segment)(struct x86_emulate_ctxt *ctxt, u16 selector, + struct desc_struct *desc, u32 base3, int seg); + unsigned long (*get_cached_segment_base)(struct x86_emulate_ctxt *ctxt, + int seg); + void (*get_gdt)(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt); + void (*get_idt)(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt); + void (*set_gdt)(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt); + void (*set_idt)(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt); + ulong (*get_cr)(struct x86_emulate_ctxt *ctxt, int cr); + int (*set_cr)(struct x86_emulate_ctxt *ctxt, int cr, ulong val); + int (*cpl)(struct x86_emulate_ctxt *ctxt); + int (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest); + int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value); + int (*set_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data); + int (*get_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata); + void (*halt)(struct x86_emulate_ctxt *ctxt); + void (*wbinvd)(struct x86_emulate_ctxt *ctxt); + int (*fix_hypercall)(struct x86_emulate_ctxt *ctxt); + void (*get_fpu)(struct x86_emulate_ctxt *ctxt); /* disables preempt */ + void (*put_fpu)(struct x86_emulate_ctxt *ctxt); /* reenables preempt */ + int (*intercept)(struct x86_emulate_ctxt *ctxt, + struct x86_instruction_info *info, + enum x86_intercept_stage stage); }; +typedef u32 __attribute__((vector_size(16))) sse128_t; + /* Type, address-of, and value of an instruction's operand. */ struct operand { - enum { OP_REG, OP_MEM, OP_IMM, OP_NONE } type; + enum { OP_REG, OP_MEM, OP_IMM, OP_XMM, OP_NONE } type; unsigned int bytes; union { unsigned long orig_val; @@ -174,11 +207,13 @@ struct operand { ulong ea; unsigned seg; } mem; + unsigned xmm; } addr; union { unsigned long val; u64 val64; char valptr[sizeof(unsigned long) + 2]; + sse128_t vec_val; }; }; @@ -197,6 +232,7 @@ struct read_cache { struct decode_cache { u8 twobyte; u8 b; + u8 intercept; u8 lock_prefix; u8 rep_prefix; u8 op_bytes; @@ -209,6 +245,7 @@ struct decode_cache { u8 seg_override; unsigned int d; int (*execute)(struct x86_emulate_ctxt *ctxt); + int (*check_perm)(struct x86_emulate_ctxt *ctxt); unsigned long regs[NR_VCPU_REGS]; unsigned long eip; /* modrm */ @@ -227,17 +264,15 @@ struct x86_emulate_ctxt { struct x86_emulate_ops *ops; /* Register state before/after emulation. */ - struct kvm_vcpu *vcpu; - unsigned long eflags; unsigned long eip; /* eip before instruction emulation */ /* Emulated execution mode, represented by an X86EMUL_MODE value. */ int mode; - u32 cs_base; /* interruptibility state, as a result of execution of STI or MOV SS */ int interruptibility; + bool guest_mode; /* guest running a nested guest */ bool perm_ok; /* do not check permissions if true */ bool only_vendor_specific_insn; @@ -249,8 +284,8 @@ struct x86_emulate_ctxt { }; /* Repeat String Operation Prefix */ -#define REPE_PREFIX 1 -#define REPNE_PREFIX 2 +#define REPE_PREFIX 0xf3 +#define REPNE_PREFIX 0xf2 /* Execution mode, passed to the emulator. */ #define X86EMUL_MODE_REAL 0 /* Real mode. */ @@ -259,6 +294,69 @@ struct x86_emulate_ctxt { #define X86EMUL_MODE_PROT32 4 /* 32-bit protected mode. */ #define X86EMUL_MODE_PROT64 8 /* 64-bit (long) mode. */ +/* any protected mode */ +#define X86EMUL_MODE_PROT (X86EMUL_MODE_PROT16|X86EMUL_MODE_PROT32| \ + X86EMUL_MODE_PROT64) + +enum x86_intercept_stage { + X86_ICTP_NONE = 0, /* Allow zero-init to not match anything */ + X86_ICPT_PRE_EXCEPT, + X86_ICPT_POST_EXCEPT, + X86_ICPT_POST_MEMACCESS, +}; + +enum x86_intercept { + x86_intercept_none, + x86_intercept_cr_read, + x86_intercept_cr_write, + x86_intercept_clts, + x86_intercept_lmsw, + x86_intercept_smsw, + x86_intercept_dr_read, + x86_intercept_dr_write, + x86_intercept_lidt, + x86_intercept_sidt, + x86_intercept_lgdt, + x86_intercept_sgdt, + x86_intercept_lldt, + x86_intercept_sldt, + x86_intercept_ltr, + x86_intercept_str, + x86_intercept_rdtsc, + x86_intercept_rdpmc, + x86_intercept_pushf, + x86_intercept_popf, + x86_intercept_cpuid, + x86_intercept_rsm, + x86_intercept_iret, + x86_intercept_intn, + x86_intercept_invd, + x86_intercept_pause, + x86_intercept_hlt, + x86_intercept_invlpg, + x86_intercept_invlpga, + x86_intercept_vmrun, + x86_intercept_vmload, + x86_intercept_vmsave, + x86_intercept_vmmcall, + x86_intercept_stgi, + x86_intercept_clgi, + x86_intercept_skinit, + x86_intercept_rdtscp, + x86_intercept_icebp, + x86_intercept_wbinvd, + x86_intercept_monitor, + x86_intercept_mwait, + x86_intercept_rdmsr, + x86_intercept_wrmsr, + x86_intercept_in, + x86_intercept_ins, + x86_intercept_out, + x86_intercept_outs, + + nr_x86_intercepts +}; + /* Host execution mode. */ #if defined(CONFIG_X86_32) #define X86EMUL_MODE_HOST X86EMUL_MODE_PROT32 @@ -270,6 +368,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len); #define EMULATION_FAILED -1 #define EMULATION_OK 0 #define EMULATION_RESTART 1 +#define EMULATION_INTERCEPTED 2 int x86_emulate_insn(struct x86_emulate_ctxt *ctxt); int emulator_task_switch(struct x86_emulate_ctxt *ctxt, u16 tss_selector, int reason, diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index c8af0991fdf0..d2ac8e2ee897 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -30,14 +30,30 @@ #define KVM_MEMORY_SLOTS 32 /* memory slots that does not exposed to userspace */ #define KVM_PRIVATE_MEM_SLOTS 4 +#define KVM_MMIO_SIZE 16 #define KVM_PIO_PAGE_OFFSET 1 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2 +#define CR0_RESERVED_BITS \ + (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ + | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \ + | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG)) + #define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1) #define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD)) #define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS | \ 0xFFFFFF0000000000ULL) +#define CR4_RESERVED_BITS \ + (~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\ + | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \ + | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR \ + | X86_CR4_OSXSAVE \ + | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE)) + +#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR) + + #define INVALID_PAGE (~(hpa_t)0) #define VALID_PAGE(x) ((x) != INVALID_PAGE) @@ -118,6 +134,9 @@ enum kvm_reg { enum kvm_reg_ex { VCPU_EXREG_PDPTR = NR_VCPU_REGS, VCPU_EXREG_CR3, + VCPU_EXREG_RFLAGS, + VCPU_EXREG_CPL, + VCPU_EXREG_SEGMENTS, }; enum { @@ -256,7 +275,7 @@ struct kvm_mmu { struct kvm_mmu_page *sp); void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva); void (*update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - u64 *spte, const void *pte, unsigned long mmu_seq); + u64 *spte, const void *pte); hpa_t root_hpa; int root_level; int shadow_root_level; @@ -340,7 +359,6 @@ struct kvm_vcpu_arch { struct fpu guest_fpu; u64 xcr0; - gva_t mmio_fault_cr2; struct kvm_pio_request pio; void *pio_data; @@ -367,18 +385,22 @@ struct kvm_vcpu_arch { /* emulate context */ struct x86_emulate_ctxt emulate_ctxt; + bool emulate_regs_need_sync_to_vcpu; + bool emulate_regs_need_sync_from_vcpu; gpa_t time; struct pvclock_vcpu_time_info hv_clock; unsigned int hw_tsc_khz; unsigned int time_offset; struct page *time_page; - u64 last_host_tsc; u64 last_guest_tsc; u64 last_kernel_ns; u64 last_tsc_nsec; u64 last_tsc_write; + u32 virtual_tsc_khz; bool tsc_catchup; + u32 tsc_catchup_mult; + s8 tsc_catchup_shift; bool nmi_pending; bool nmi_injected; @@ -448,9 +470,6 @@ struct kvm_arch { u64 last_tsc_nsec; u64 last_tsc_offset; u64 last_tsc_write; - u32 virtual_tsc_khz; - u32 virtual_tsc_mult; - s8 virtual_tsc_shift; struct kvm_xen_hvm_config xen_hvm_config; @@ -502,6 +521,8 @@ struct kvm_vcpu_stat { u32 nmi_injections; }; +struct x86_instruction_info; + struct kvm_x86_ops { int (*cpu_has_kvm_support)(void); /* __init */ int (*disabled_by_bios)(void); /* __init */ @@ -586,9 +607,17 @@ struct kvm_x86_ops { bool (*has_wbinvd_exit)(void); + void (*set_tsc_khz)(struct kvm_vcpu *vcpu, u32 user_tsc_khz); void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); + u64 (*compute_tsc_offset)(struct kvm_vcpu *vcpu, u64 target_tsc); + void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2); + + int (*check_intercept)(struct kvm_vcpu *vcpu, + struct x86_instruction_info *info, + enum x86_intercept_stage stage); + const struct trace_print_flags *exit_reasons_str; }; @@ -627,6 +656,13 @@ u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn); extern bool tdp_enabled; +/* control of guest tsc rate supported? */ +extern bool kvm_has_tsc_control; +/* minimum supported tsc_khz for guests */ +extern u32 kvm_min_guest_tsc_khz; +/* maximum supported tsc_khz for guests */ +extern u32 kvm_max_guest_tsc_khz; + enum emulation_result { EMULATE_DONE, /* no further processing */ EMULATE_DO_MMIO, /* kvm_run filled with mmio request */ @@ -645,9 +681,6 @@ static inline int emulate_instruction(struct kvm_vcpu *vcpu, return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0); } -void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address); -void realmode_lidt(struct kvm_vcpu *vcpu, u16 size, unsigned long address); - void kvm_enable_efer_bits(u64); int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data); int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); @@ -657,8 +690,6 @@ struct x86_emulate_ctxt; int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port); void kvm_emulate_cpuid(struct kvm_vcpu *vcpu); int kvm_emulate_halt(struct kvm_vcpu *vcpu); -int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address); -int emulate_clts(struct kvm_vcpu *vcpu); int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); @@ -721,8 +752,6 @@ gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); -int kvm_fix_hypercall(struct kvm_vcpu *vcpu); - int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code, void *insn, int insn_len); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 3cce71413d0b..485b4f1f079b 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -118,6 +118,7 @@ complete list. */ #define MSR_AMD64_PATCH_LEVEL 0x0000008b +#define MSR_AMD64_TSC_RATIO 0xc0000104 #define MSR_AMD64_NB_CFG 0xc001001f #define MSR_AMD64_PATCH_LOADER 0xc0010020 #define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140 diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 0ad47b819a8b..d6e2477feb18 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -73,9 +73,14 @@ #define MemAbs (1<<11) /* Memory operand is absolute displacement */ #define String (1<<12) /* String instruction (rep capable) */ #define Stack (1<<13) /* Stack instruction (push/pop) */ +#define GroupMask (7<<14) /* Opcode uses one of the group mechanisms */ #define Group (1<<14) /* Bits 3:5 of modrm byte extend opcode */ -#define GroupDual (1<<15) /* Alternate decoding of mod == 3 */ +#define GroupDual (2<<14) /* Alternate decoding of mod == 3 */ +#define Prefix (3<<14) /* Instruction varies with 66/f2/f3 prefix */ +#define RMExt (4<<14) /* Opcode extension in ModRM r/m if mod == 3 */ +#define Sse (1<<17) /* SSE Vector instruction */ /* Misc flags */ +#define Prot (1<<21) /* instruction generates #UD if not in prot-mode */ #define VendorSpecific (1<<22) /* Vendor specific instruction */ #define NoAccess (1<<23) /* Don't access memory (lea/invlpg/verr etc) */ #define Op3264 (1<<24) /* Operand is 64b in long mode, 32b otherwise */ @@ -102,11 +107,14 @@ struct opcode { u32 flags; + u8 intercept; union { int (*execute)(struct x86_emulate_ctxt *ctxt); struct opcode *group; struct group_dual *gdual; + struct gprefix *gprefix; } u; + int (*check_perm)(struct x86_emulate_ctxt *ctxt); }; struct group_dual { @@ -114,6 +122,13 @@ struct group_dual { struct opcode mod3[8]; }; +struct gprefix { + struct opcode pfx_no; + struct opcode pfx_66; + struct opcode pfx_f2; + struct opcode pfx_f3; +}; + /* EFLAGS bit definitions. */ #define EFLG_ID (1<<21) #define EFLG_VIP (1<<20) @@ -248,42 +263,42 @@ struct group_dual { "w", "r", _LO32, "r", "", "r") /* Instruction has three operands and one operand is stored in ECX register */ -#define __emulate_2op_cl(_op, _cl, _src, _dst, _eflags, _suffix, _type) \ - do { \ - unsigned long _tmp; \ - _type _clv = (_cl).val; \ - _type _srcv = (_src).val; \ - _type _dstv = (_dst).val; \ - \ - __asm__ __volatile__ ( \ - _PRE_EFLAGS("0", "5", "2") \ - _op _suffix " %4,%1 \n" \ - _POST_EFLAGS("0", "5", "2") \ - : "=m" (_eflags), "+r" (_dstv), "=&r" (_tmp) \ - : "c" (_clv) , "r" (_srcv), "i" (EFLAGS_MASK) \ - ); \ - \ - (_cl).val = (unsigned long) _clv; \ - (_src).val = (unsigned long) _srcv; \ - (_dst).val = (unsigned long) _dstv; \ +#define __emulate_2op_cl(_op, _cl, _src, _dst, _eflags, _suffix, _type) \ + do { \ + unsigned long _tmp; \ + _type _clv = (_cl).val; \ + _type _srcv = (_src).val; \ + _type _dstv = (_dst).val; \ + \ + __asm__ __volatile__ ( \ + _PRE_EFLAGS("0", "5", "2") \ + _op _suffix " %4,%1 \n" \ + _POST_EFLAGS("0", "5", "2") \ + : "=m" (_eflags), "+r" (_dstv), "=&r" (_tmp) \ + : "c" (_clv) , "r" (_srcv), "i" (EFLAGS_MASK) \ + ); \ + \ + (_cl).val = (unsigned long) _clv; \ + (_src).val = (unsigned long) _srcv; \ + (_dst).val = (unsigned long) _dstv; \ } while (0) -#define emulate_2op_cl(_op, _cl, _src, _dst, _eflags) \ - do { \ - switch ((_dst).bytes) { \ - case 2: \ - __emulate_2op_cl(_op, _cl, _src, _dst, _eflags, \ - "w", unsigned short); \ - break; \ - case 4: \ - __emulate_2op_cl(_op, _cl, _src, _dst, _eflags, \ - "l", unsigned int); \ - break; \ - case 8: \ - ON64(__emulate_2op_cl(_op, _cl, _src, _dst, _eflags, \ - "q", unsigned long)); \ - break; \ - } \ +#define emulate_2op_cl(_op, _cl, _src, _dst, _eflags) \ + do { \ + switch ((_dst).bytes) { \ + case 2: \ + __emulate_2op_cl(_op, _cl, _src, _dst, _eflags, \ + "w", unsigned short); \ + break; \ + case 4: \ + __emulate_2op_cl(_op, _cl, _src, _dst, _eflags, \ + "l", unsigned int); \ + break; \ + case 8: \ + ON64(__emulate_2op_cl(_op, _cl, _src, _dst, _eflags, \ + "q", unsigned long)); \ + break; \ + } \ } while (0) #define __emulate_1op(_op, _dst, _eflags, _suffix) \ @@ -346,13 +361,25 @@ struct group_dual { } while (0) /* instruction has only one source operand, destination is implicit (e.g. mul, div, imul, idiv) */ -#define emulate_1op_rax_rdx(_op, _src, _rax, _rdx, _eflags) \ - do { \ - switch((_src).bytes) { \ - case 1: __emulate_1op_rax_rdx(_op, _src, _rax, _rdx, _eflags, "b"); break; \ - case 2: __emulate_1op_rax_rdx(_op, _src, _rax, _rdx, _eflags, "w"); break; \ - case 4: __emulate_1op_rax_rdx(_op, _src, _rax, _rdx, _eflags, "l"); break; \ - case 8: ON64(__emulate_1op_rax_rdx(_op, _src, _rax, _rdx, _eflags, "q")); break; \ +#define emulate_1op_rax_rdx(_op, _src, _rax, _rdx, _eflags) \ + do { \ + switch((_src).bytes) { \ + case 1: \ + __emulate_1op_rax_rdx(_op, _src, _rax, _rdx, \ + _eflags, "b"); \ + break; \ + case 2: \ + __emulate_1op_rax_rdx(_op, _src, _rax, _rdx, \ + _eflags, "w"); \ + break; \ + case 4: \ + __emulate_1op_rax_rdx(_op, _src, _rax, _rdx, \ + _eflags, "l"); \ + break; \ + case 8: \ + ON64(__emulate_1op_rax_rdx(_op, _src, _rax, _rdx, \ + _eflags, "q")); \ + break; \ } \ } while (0) @@ -388,13 +415,33 @@ struct group_dual { (_type)_x; \ }) -#define insn_fetch_arr(_arr, _size, _eip) \ +#define insn_fetch_arr(_arr, _size, _eip) \ ({ rc = do_insn_fetch(ctxt, ops, (_eip), _arr, (_size)); \ if (rc != X86EMUL_CONTINUE) \ goto done; \ (_eip) += (_size); \ }) +static int emulator_check_intercept(struct x86_emulate_ctxt *ctxt, + enum x86_intercept intercept, + enum x86_intercept_stage stage) +{ + struct x86_instruction_info info = { + .intercept = intercept, + .rep_prefix = ctxt->decode.rep_prefix, + .modrm_mod = ctxt->decode.modrm_mod, + .modrm_reg = ctxt->decode.modrm_reg, + .modrm_rm = ctxt->decode.modrm_rm, + .src_val = ctxt->decode.src.val64, + .src_bytes = ctxt->decode.src.bytes, + .dst_bytes = ctxt->decode.dst.bytes, + .ad_bytes = ctxt->decode.ad_bytes, + .next_rip = ctxt->eip, + }; + + return ctxt->ops->intercept(ctxt, &info, stage); +} + static inline unsigned long ad_mask(struct decode_cache *c) { return (1UL << (c->ad_bytes << 3)) - 1; @@ -430,6 +477,13 @@ static inline void jmp_rel(struct decode_cache *c, int rel) register_address_increment(c, &c->eip, rel); } +static u32 desc_limit_scaled(struct desc_struct *desc) +{ + u32 limit = get_desc_limit(desc); + + return desc->g ? (limit << 12) | 0xfff : limit; +} + static void set_seg_override(struct decode_cache *c, int seg) { c->has_seg_override = true; @@ -442,11 +496,10 @@ static unsigned long seg_base(struct x86_emulate_ctxt *ctxt, if (ctxt->mode == X86EMUL_MODE_PROT64 && seg < VCPU_SREG_FS) return 0; - return ops->get_cached_segment_base(seg, ctxt->vcpu); + return ops->get_cached_segment_base(ctxt, seg); } static unsigned seg_override(struct x86_emulate_ctxt *ctxt, - struct x86_emulate_ops *ops, struct decode_cache *c) { if (!c->has_seg_override) @@ -455,18 +508,6 @@ static unsigned seg_override(struct x86_emulate_ctxt *ctxt, return c->seg_override; } -static ulong linear(struct x86_emulate_ctxt *ctxt, - struct segmented_address addr) -{ - struct decode_cache *c = &ctxt->decode; - ulong la; - - la = seg_base(ctxt, ctxt->ops, addr.seg) + addr.ea; - if (c->ad_bytes != 8) - la &= (u32)-1; - return la; -} - static int emulate_exception(struct x86_emulate_ctxt *ctxt, int vec, u32 error, bool valid) { @@ -476,11 +517,21 @@ static int emulate_exception(struct x86_emulate_ctxt *ctxt, int vec, return X86EMUL_PROPAGATE_FAULT; } +static int emulate_db(struct x86_emulate_ctxt *ctxt) +{ + return emulate_exception(ctxt, DB_VECTOR, 0, false); +} + static int emulate_gp(struct x86_emulate_ctxt *ctxt, int err) { return emulate_exception(ctxt, GP_VECTOR, err, true); } +static int emulate_ss(struct x86_emulate_ctxt *ctxt, int err) +{ + return emulate_exception(ctxt, SS_VECTOR, err, true); +} + static int emulate_ud(struct x86_emulate_ctxt *ctxt) { return emulate_exception(ctxt, UD_VECTOR, 0, false); @@ -496,6 +547,128 @@ static int emulate_de(struct x86_emulate_ctxt *ctxt) return emulate_exception(ctxt, DE_VECTOR, 0, false); } +static int emulate_nm(struct x86_emulate_ctxt *ctxt) +{ + return emulate_exception(ctxt, NM_VECTOR, 0, false); +} + +static u16 get_segment_selector(struct x86_emulate_ctxt *ctxt, unsigned seg) +{ + u16 selector; + struct desc_struct desc; + + ctxt->ops->get_segment(ctxt, &selector, &desc, NULL, seg); + return selector; +} + +static void set_segment_selector(struct x86_emulate_ctxt *ctxt, u16 selector, + unsigned seg) +{ + u16 dummy; + u32 base3; + struct desc_struct desc; + + ctxt->ops->get_segment(ctxt, &dummy, &desc, &base3, seg); + ctxt->ops->set_segment(ctxt, selector, &desc, base3, seg); +} + +static int __linearize(struct x86_emulate_ctxt *ctxt, + struct segmented_address addr, + unsigned size, bool write, bool fetch, + ulong *linear) +{ + struct decode_cache *c = &ctxt->decode; + struct desc_struct desc; + bool usable; + ulong la; + u32 lim; + u16 sel; + unsigned cpl, rpl; + + la = seg_base(ctxt, ctxt->ops, addr.seg) + addr.ea; + switch (ctxt->mode) { + case X86EMUL_MODE_REAL: + break; + case X86EMUL_MODE_PROT64: + if (((signed long)la << 16) >> 16 != la) + return emulate_gp(ctxt, 0); + break; + default: + usable = ctxt->ops->get_segment(ctxt, &sel, &desc, NULL, + addr.seg); + if (!usable) + goto bad; + /* code segment or read-only data segment */ + if (((desc.type & 8) || !(desc.type & 2)) && write) + goto bad; + /* unreadable code segment */ + if (!fetch && (desc.type & 8) && !(desc.type & 2)) + goto bad; + lim = desc_limit_scaled(&desc); + if ((desc.type & 8) || !(desc.type & 4)) { + /* expand-up segment */ + if (addr.ea > lim || (u32)(addr.ea + size - 1) > lim) + goto bad; + } else { + /* exapand-down segment */ + if (addr.ea <= lim || (u32)(addr.ea + size - 1) <= lim) + goto bad; + lim = desc.d ? 0xffffffff : 0xffff; + if (addr.ea > lim || (u32)(addr.ea + size - 1) > lim) + goto bad; + } + cpl = ctxt->ops->cpl(ctxt); + rpl = sel & 3; + cpl = max(cpl, rpl); + if (!(desc.type & 8)) { + /* data segment */ + if (cpl > desc.dpl) + goto bad; + } else if ((desc.type & 8) && !(desc.type & 4)) { + /* nonconforming code segment */ + if (cpl != desc.dpl) + goto bad; + } else if ((desc.type & 8) && (desc.type & 4)) { + /* conforming code segment */ + if (cpl < desc.dpl) + goto bad; + } + break; + } + if (fetch ? ctxt->mode != X86EMUL_MODE_PROT64 : c->ad_bytes != 8) + la &= (u32)-1; + *linear = la; + return X86EMUL_CONTINUE; +bad: + if (addr.seg == VCPU_SREG_SS) + return emulate_ss(ctxt, addr.seg); + else + return emulate_gp(ctxt, addr.seg); +} + +static int linearize(struct x86_emulate_ctxt *ctxt, + struct segmented_address addr, + unsigned size, bool write, + ulong *linear) +{ + return __linearize(ctxt, addr, size, write, false, linear); +} + + +static int segmented_read_std(struct x86_emulate_ctxt *ctxt, + struct segmented_address addr, + void *data, + unsigned size) +{ + int rc; + ulong linear; + + rc = linearize(ctxt, addr, size, false, &linear); + if (rc != X86EMUL_CONTINUE) + return rc; + return ctxt->ops->read_std(ctxt, linear, data, size, &ctxt->exception); +} + static int do_fetch_insn_byte(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops, unsigned long eip, u8 *dest) @@ -505,10 +678,15 @@ static int do_fetch_insn_byte(struct x86_emulate_ctxt *ctxt, int size, cur_size; if (eip == fc->end) { + unsigned long linear; + struct segmented_address addr = { .seg=VCPU_SREG_CS, .ea=eip}; cur_size = fc->end - fc->start; size = min(15UL - cur_size, PAGE_SIZE - offset_in_page(eip)); - rc = ops->fetch(ctxt->cs_base + eip, fc->data + cur_size, - size, ctxt->vcpu, &ctxt->exception); + rc = __linearize(ctxt, addr, size, false, true, &linear); + if (rc != X86EMUL_CONTINUE) + return rc; + rc = ops->fetch(ctxt, linear, fc->data + cur_size, + size, &ctxt->exception); if (rc != X86EMUL_CONTINUE) return rc; fc->end += size; @@ -551,7 +729,6 @@ static void *decode_register(u8 modrm_reg, unsigned long *regs, } static int read_descriptor(struct x86_emulate_ctxt *ctxt, - struct x86_emulate_ops *ops, struct segmented_address addr, u16 *size, unsigned long *address, int op_bytes) { @@ -560,13 +737,11 @@ static int read_descriptor(struct x86_emulate_ctxt *ctxt, if (op_bytes == 2) op_bytes = 3; *address = 0; - rc = ops->read_std(linear(ctxt, addr), (unsigned long *)size, 2, - ctxt->vcpu, &ctxt->exception); + rc = segmented_read_std(ctxt, addr, size, 2); if (rc != X86EMUL_CONTINUE) return rc; addr.ea += 2; - rc = ops->read_std(linear(ctxt, addr), address, op_bytes, - ctxt->vcpu, &ctxt->exception); + rc = segmented_read_std(ctxt, addr, address, op_bytes); return rc; } @@ -623,7 +798,63 @@ static void fetch_register_operand(struct operand *op) } } -static void decode_register_operand(struct operand *op, +static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg) +{ + ctxt->ops->get_fpu(ctxt); + switch (reg) { + case 0: asm("movdqu %%xmm0, %0" : "=m"(*data)); break; + case 1: asm("movdqu %%xmm1, %0" : "=m"(*data)); break; + case 2: asm("movdqu %%xmm2, %0" : "=m"(*data)); break; + case 3: asm("movdqu %%xmm3, %0" : "=m"(*data)); break; + case 4: asm("movdqu %%xmm4, %0" : "=m"(*data)); break; + case 5: asm("movdqu %%xmm5, %0" : "=m"(*data)); break; + case 6: asm("movdqu %%xmm6, %0" : "=m"(*data)); break; + case 7: asm("movdqu %%xmm7, %0" : "=m"(*data)); break; +#ifdef CONFIG_X86_64 + case 8: asm("movdqu %%xmm8, %0" : "=m"(*data)); break; + case 9: asm("movdqu %%xmm9, %0" : "=m"(*data)); break; + case 10: asm("movdqu %%xmm10, %0" : "=m"(*data)); break; + case 11: asm("movdqu %%xmm11, %0" : "=m"(*data)); break; + case 12: asm("movdqu %%xmm12, %0" : "=m"(*data)); break; + case 13: asm("movdqu %%xmm13, %0" : "=m"(*data)); break; + case 14: asm("movdqu %%xmm14, %0" : "=m"(*data)); break; + case 15: asm("movdqu %%xmm15, %0" : "=m"(*data)); break; +#endif + default: BUG(); + } + ctxt->ops->put_fpu(ctxt); +} + +static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, + int reg) +{ + ctxt->ops->get_fpu(ctxt); + switch (reg) { + case 0: asm("movdqu %0, %%xmm0" : : "m"(*data)); break; + case 1: asm("movdqu %0, %%xmm1" : : "m"(*data)); break; + case 2: asm("movdqu %0, %%xmm2" : : "m"(*data)); break; + case 3: asm("movdqu %0, %%xmm3" : : "m"(*data)); break; + case 4: asm("movdqu %0, %%xmm4" : : "m"(*data)); break; + case 5: asm("movdqu %0, %%xmm5" : : "m"(*data)); break; + case 6: asm("movdqu %0, %%xmm6" : : "m"(*data)); break; + case 7: asm("movdqu %0, %%xmm7" : : "m"(*data)); break; +#ifdef CONFIG_X86_64 + case 8: asm("movdqu %0, %%xmm8" : : "m"(*data)); break; + case 9: asm("movdqu %0, %%xmm9" : : "m"(*data)); break; + case 10: asm("movdqu %0, %%xmm10" : : "m"(*data)); break; + case 11: asm("movdqu %0, %%xmm11" : : "m"(*data)); break; + case 12: asm("movdqu %0, %%xmm12" : : "m"(*data)); break; + case 13: asm("movdqu %0, %%xmm13" : : "m"(*data)); break; + case 14: asm("movdqu %0, %%xmm14" : : "m"(*data)); break; + case 15: asm("movdqu %0, %%xmm15" : : "m"(*data)); break; +#endif + default: BUG(); + } + ctxt->ops->put_fpu(ctxt); +} + +static void decode_register_operand(struct x86_emulate_ctxt *ctxt, + struct operand *op, struct decode_cache *c, int inhibit_bytereg) { @@ -632,6 +863,15 @@ static void decode_register_operand(struct operand *op, if (!(c->d & ModRM)) reg = (c->b & 7) | ((c->rex_prefix & 1) << 3); + + if (c->d & Sse) { + op->type = OP_XMM; + op->bytes = 16; + op->addr.xmm = reg; + read_sse_reg(ctxt, &op->vec_val, reg); + return; + } + op->type = OP_REG; if ((c->d & ByteOp) && !inhibit_bytereg) { op->addr.reg = decode_register(reg, c->regs, highbyte_regs); @@ -671,6 +911,13 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, op->bytes = (c->d & ByteOp) ? 1 : c->op_bytes; op->addr.reg = decode_register(c->modrm_rm, c->regs, c->d & ByteOp); + if (c->d & Sse) { + op->type = OP_XMM; + op->bytes = 16; + op->addr.xmm = c->modrm_rm; + read_sse_reg(ctxt, &op->vec_val, c->modrm_rm); + return rc; + } fetch_register_operand(op); return rc; } @@ -819,8 +1066,8 @@ static int read_emulated(struct x86_emulate_ctxt *ctxt, if (mc->pos < mc->end) goto read_cached; - rc = ops->read_emulated(addr, mc->data + mc->end, n, - &ctxt->exception, ctxt->vcpu); + rc = ops->read_emulated(ctxt, addr, mc->data + mc->end, n, + &ctxt->exception); if (rc != X86EMUL_CONTINUE) return rc; mc->end += n; @@ -834,6 +1081,50 @@ static int read_emulated(struct x86_emulate_ctxt *ctxt, return X86EMUL_CONTINUE; } +static int segmented_read(struct x86_emulate_ctxt *ctxt, + struct segmented_address addr, + void *data, + unsigned size) +{ + int rc; + ulong linear; + + rc = linearize(ctxt, addr, size, false, &linear); + if (rc != X86EMUL_CONTINUE) + return rc; + return read_emulated(ctxt, ctxt->ops, linear, data, size); +} + +static int segmented_write(struct x86_emulate_ctxt *ctxt, + struct segmented_address addr, + const void *data, + unsigned size) +{ + int rc; + ulong linear; + + rc = linearize(ctxt, addr, size, true, &linear); + if (rc != X86EMUL_CONTINUE) + return rc; + return ctxt->ops->write_emulated(ctxt, linear, data, size, + &ctxt->exception); +} + +static int segmented_cmpxchg(struct x86_emulate_ctxt *ctxt, + struct segmented_address addr, + const void *orig_data, const void *data, + unsigned size) +{ + int rc; + ulong linear; + + rc = linearize(ctxt, addr, size, true, &linear); + if (rc != X86EMUL_CONTINUE) + return rc; + return ctxt->ops->cmpxchg_emulated(ctxt, linear, orig_data, data, + size, &ctxt->exception); +} + static int pio_in_emulated(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops, unsigned int size, unsigned short port, @@ -854,7 +1145,7 @@ static int pio_in_emulated(struct x86_emulate_ctxt *ctxt, if (n == 0) n = 1; rc->pos = rc->end = 0; - if (!ops->pio_in_emulated(size, port, rc->data, n, ctxt->vcpu)) + if (!ops->pio_in_emulated(ctxt, size, port, rc->data, n)) return 0; rc->end = n * size; } @@ -864,28 +1155,22 @@ static int pio_in_emulated(struct x86_emulate_ctxt *ctxt, return 1; } -static u32 desc_limit_scaled(struct desc_struct *desc) -{ - u32 limit = get_desc_limit(desc); - - return desc->g ? (limit << 12) | 0xfff : limit; -} - static void get_descriptor_table_ptr(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops, u16 selector, struct desc_ptr *dt) { if (selector & 1 << 2) { struct desc_struct desc; + u16 sel; + memset (dt, 0, sizeof *dt); - if (!ops->get_cached_descriptor(&desc, NULL, VCPU_SREG_LDTR, - ctxt->vcpu)) + if (!ops->get_segment(ctxt, &sel, &desc, NULL, VCPU_SREG_LDTR)) return; dt->size = desc_limit_scaled(&desc); /* what if limit > 65535? */ dt->address = get_desc_base(&desc); } else - ops->get_gdt(dt, ctxt->vcpu); + ops->get_gdt(ctxt, dt); } /* allowed just for 8 bytes segments */ @@ -903,8 +1188,7 @@ static int read_segment_descriptor(struct x86_emulate_ctxt *ctxt, if (dt.size < index * 8 + 7) return emulate_gp(ctxt, selector & 0xfffc); addr = dt.address + index * 8; - ret = ops->read_std(addr, desc, sizeof *desc, ctxt->vcpu, - &ctxt->exception); + ret = ops->read_std(ctxt, addr, desc, sizeof *desc, &ctxt->exception); return ret; } @@ -925,8 +1209,7 @@ static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt, return emulate_gp(ctxt, selector & 0xfffc); addr = dt.address + index * 8; - ret = ops->write_std(addr, desc, sizeof *desc, ctxt->vcpu, - &ctxt->exception); + ret = ops->write_std(ctxt, addr, desc, sizeof *desc, &ctxt->exception); return ret; } @@ -986,7 +1269,7 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, rpl = selector & 3; dpl = seg_desc.dpl; - cpl = ops->cpl(ctxt->vcpu); + cpl = ops->cpl(ctxt); switch (seg) { case VCPU_SREG_SS: @@ -1042,8 +1325,7 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, return ret; } load: - ops->set_segment_selector(selector, seg, ctxt->vcpu); - ops->set_cached_descriptor(&seg_desc, 0, seg, ctxt->vcpu); + ops->set_segment(ctxt, selector, &seg_desc, 0, seg); return X86EMUL_CONTINUE; exception: emulate_exception(ctxt, err_vec, err_code, true); @@ -1069,8 +1351,7 @@ static void write_register_operand(struct operand *op) } } -static inline int writeback(struct x86_emulate_ctxt *ctxt, - struct x86_emulate_ops *ops) +static int writeback(struct x86_emulate_ctxt *ctxt) { int rc; struct decode_cache *c = &ctxt->decode; @@ -1081,23 +1362,22 @@ static inline int writeback(struct x86_emulate_ctxt *ctxt, break; case OP_MEM: if (c->lock_prefix) - rc = ops->cmpxchg_emulated( - linear(ctxt, c->dst.addr.mem), - &c->dst.orig_val, - &c->dst.val, - c->dst.bytes, - &ctxt->exception, - ctxt->vcpu); + rc = segmented_cmpxchg(ctxt, + c->dst.addr.mem, + &c->dst.orig_val, + &c->dst.val, + c->dst.bytes); else - rc = ops->write_emulated( - linear(ctxt, c->dst.addr.mem), - &c->dst.val, - c->dst.bytes, - &ctxt->exception, - ctxt->vcpu); + rc = segmented_write(ctxt, + c->dst.addr.mem, + &c->dst.val, + c->dst.bytes); if (rc != X86EMUL_CONTINUE) return rc; break; + case OP_XMM: + write_sse_reg(ctxt, &c->dst.vec_val, c->dst.addr.xmm); + break; case OP_NONE: /* no writeback */ break; @@ -1107,21 +1387,21 @@ static inline int writeback(struct x86_emulate_ctxt *ctxt, return X86EMUL_CONTINUE; } -static inline void emulate_push(struct x86_emulate_ctxt *ctxt, - struct x86_emulate_ops *ops) +static int em_push(struct x86_emulate_ctxt *ctxt) { struct decode_cache *c = &ctxt->decode; + struct segmented_address addr; - c->dst.type = OP_MEM; - c->dst.bytes = c->op_bytes; - c->dst.val = c->src.val; register_address_increment(c, &c->regs[VCPU_REGS_RSP], -c->op_bytes); - c->dst.addr.mem.ea = register_address(c, c->regs[VCPU_REGS_RSP]); - c->dst.addr.mem.seg = VCPU_SREG_SS; + addr.ea = register_address(c, c->regs[VCPU_REGS_RSP]); + addr.seg = VCPU_SREG_SS; + + /* Disable writeback. */ + c->dst.type = OP_NONE; + return segmented_write(ctxt, addr, &c->src.val, c->op_bytes); } static int emulate_pop(struct x86_emulate_ctxt *ctxt, - struct x86_emulate_ops *ops, void *dest, int len) { struct decode_cache *c = &ctxt->decode; @@ -1130,7 +1410,7 @@ static int emulate_pop(struct x86_emulate_ctxt *ctxt, addr.ea = register_address(c, c->regs[VCPU_REGS_RSP]); addr.seg = VCPU_SREG_SS; - rc = read_emulated(ctxt, ops, linear(ctxt, addr), dest, len); + rc = segmented_read(ctxt, addr, dest, len); if (rc != X86EMUL_CONTINUE) return rc; @@ -1138,6 +1418,13 @@ static int emulate_pop(struct x86_emulate_ctxt *ctxt, return rc; } +static int em_pop(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + + return emulate_pop(ctxt, &c->dst.val, c->op_bytes); +} + static int emulate_popf(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops, void *dest, int len) @@ -1145,9 +1432,9 @@ static int emulate_popf(struct x86_emulate_ctxt *ctxt, int rc; unsigned long val, change_mask; int iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> IOPL_SHIFT; - int cpl = ops->cpl(ctxt->vcpu); + int cpl = ops->cpl(ctxt); - rc = emulate_pop(ctxt, ops, &val, len); + rc = emulate_pop(ctxt, &val, len); if (rc != X86EMUL_CONTINUE) return rc; @@ -1179,14 +1466,24 @@ static int emulate_popf(struct x86_emulate_ctxt *ctxt, return rc; } -static void emulate_push_sreg(struct x86_emulate_ctxt *ctxt, - struct x86_emulate_ops *ops, int seg) +static int em_popf(struct x86_emulate_ctxt *ctxt) { struct decode_cache *c = &ctxt->decode; - c->src.val = ops->get_segment_selector(seg, ctxt->vcpu); + c->dst.type = OP_REG; + c->dst.addr.reg = &ctxt->eflags; + c->dst.bytes = c->op_bytes; + return emulate_popf(ctxt, ctxt->ops, &c->dst.val, c->op_bytes); +} - emulate_push(ctxt, ops); +static int emulate_push_sreg(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, int seg) +{ + struct decode_cache *c = &ctxt->decode; + + c->src.val = get_segment_selector(ctxt, seg); + + return em_push(ctxt); } static int emulate_pop_sreg(struct x86_emulate_ctxt *ctxt, @@ -1196,7 +1493,7 @@ static int emulate_pop_sreg(struct x86_emulate_ctxt *ctxt, unsigned long selector; int rc; - rc = emulate_pop(ctxt, ops, &selector, c->op_bytes); + rc = emulate_pop(ctxt, &selector, c->op_bytes); if (rc != X86EMUL_CONTINUE) return rc; @@ -1204,8 +1501,7 @@ static int emulate_pop_sreg(struct x86_emulate_ctxt *ctxt, return rc; } -static int emulate_pusha(struct x86_emulate_ctxt *ctxt, - struct x86_emulate_ops *ops) +static int em_pusha(struct x86_emulate_ctxt *ctxt) { struct decode_cache *c = &ctxt->decode; unsigned long old_esp = c->regs[VCPU_REGS_RSP]; @@ -1216,23 +1512,25 @@ static int emulate_pusha(struct x86_emulate_ctxt *ctxt, (reg == VCPU_REGS_RSP) ? (c->src.val = old_esp) : (c->src.val = c->regs[reg]); - emulate_push(ctxt, ops); - - rc = writeback(ctxt, ops); + rc = em_push(ctxt); if (rc != X86EMUL_CONTINUE) return rc; ++reg; } - /* Disable writeback. */ - c->dst.type = OP_NONE; - return rc; } -static int emulate_popa(struct x86_emulate_ctxt *ctxt, - struct x86_emulate_ops *ops) +static int em_pushf(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + + c->src.val = (unsigned long)ctxt->eflags; + return em_push(ctxt); +} + +static int em_popa(struct x86_emulate_ctxt *ctxt) { struct decode_cache *c = &ctxt->decode; int rc = X86EMUL_CONTINUE; @@ -1245,7 +1543,7 @@ static int emulate_popa(struct x86_emulate_ctxt *ctxt, --reg; } - rc = emulate_pop(ctxt, ops, &c->regs[reg], c->op_bytes); + rc = emulate_pop(ctxt, &c->regs[reg], c->op_bytes); if (rc != X86EMUL_CONTINUE) break; --reg; @@ -1265,37 +1563,32 @@ int emulate_int_real(struct x86_emulate_ctxt *ctxt, /* TODO: Add limit checks */ c->src.val = ctxt->eflags; - emulate_push(ctxt, ops); - rc = writeback(ctxt, ops); + rc = em_push(ctxt); if (rc != X86EMUL_CONTINUE) return rc; ctxt->eflags &= ~(EFLG_IF | EFLG_TF | EFLG_AC); - c->src.val = ops->get_segment_selector(VCPU_SREG_CS, ctxt->vcpu); - emulate_push(ctxt, ops); - rc = writeback(ctxt, ops); + c->src.val = get_segment_selector(ctxt, VCPU_SREG_CS); + rc = em_push(ctxt); if (rc != X86EMUL_CONTINUE) return rc; c->src.val = c->eip; - emulate_push(ctxt, ops); - rc = writeback(ctxt, ops); + rc = em_push(ctxt); if (rc != X86EMUL_CONTINUE) return rc; - c->dst.type = OP_NONE; - - ops->get_idt(&dt, ctxt->vcpu); + ops->get_idt(ctxt, &dt); eip_addr = dt.address + (irq << 2); cs_addr = dt.address + (irq << 2) + 2; - rc = ops->read_std(cs_addr, &cs, 2, ctxt->vcpu, &ctxt->exception); + rc = ops->read_std(ctxt, cs_addr, &cs, 2, &ctxt->exception); if (rc != X86EMUL_CONTINUE) return rc; - rc = ops->read_std(eip_addr, &eip, 2, ctxt->vcpu, &ctxt->exception); + rc = ops->read_std(ctxt, eip_addr, &eip, 2, &ctxt->exception); if (rc != X86EMUL_CONTINUE) return rc; @@ -1339,7 +1632,7 @@ static int emulate_iret_real(struct x86_emulate_ctxt *ctxt, /* TODO: Add stack limit check */ - rc = emulate_pop(ctxt, ops, &temp_eip, c->op_bytes); + rc = emulate_pop(ctxt, &temp_eip, c->op_bytes); if (rc != X86EMUL_CONTINUE) return rc; @@ -1347,12 +1640,12 @@ static int emulate_iret_real(struct x86_emulate_ctxt *ctxt, if (temp_eip & ~0xffff) return emulate_gp(ctxt, 0); - rc = emulate_pop(ctxt, ops, &cs, c->op_bytes); + rc = emulate_pop(ctxt, &cs, c->op_bytes); if (rc != X86EMUL_CONTINUE) return rc; - rc = emulate_pop(ctxt, ops, &temp_eflags, c->op_bytes); + rc = emulate_pop(ctxt, &temp_eflags, c->op_bytes); if (rc != X86EMUL_CONTINUE) return rc; @@ -1394,15 +1687,31 @@ static inline int emulate_iret(struct x86_emulate_ctxt *ctxt, } } -static inline int emulate_grp1a(struct x86_emulate_ctxt *ctxt, - struct x86_emulate_ops *ops) +static int em_jmp_far(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + int rc; + unsigned short sel; + + memcpy(&sel, c->src.valptr + c->op_bytes, 2); + + rc = load_segment_descriptor(ctxt, ctxt->ops, sel, VCPU_SREG_CS); + if (rc != X86EMUL_CONTINUE) + return rc; + + c->eip = 0; + memcpy(&c->eip, c->src.valptr, c->op_bytes); + return X86EMUL_CONTINUE; +} + +static int em_grp1a(struct x86_emulate_ctxt *ctxt) { struct decode_cache *c = &ctxt->decode; - return emulate_pop(ctxt, ops, &c->dst.val, c->dst.bytes); + return emulate_pop(ctxt, &c->dst.val, c->dst.bytes); } -static inline void emulate_grp2(struct x86_emulate_ctxt *ctxt) +static int em_grp2(struct x86_emulate_ctxt *ctxt) { struct decode_cache *c = &ctxt->decode; switch (c->modrm_reg) { @@ -1429,10 +1738,10 @@ static inline void emulate_grp2(struct x86_emulate_ctxt *ctxt) emulate_2op_SrcB("sar", c->src, c->dst, ctxt->eflags); break; } + return X86EMUL_CONTINUE; } -static inline int emulate_grp3(struct x86_emulate_ctxt *ctxt, - struct x86_emulate_ops *ops) +static int em_grp3(struct x86_emulate_ctxt *ctxt) { struct decode_cache *c = &ctxt->decode; unsigned long *rax = &c->regs[VCPU_REGS_RAX]; @@ -1471,10 +1780,10 @@ static inline int emulate_grp3(struct x86_emulate_ctxt *ctxt, return X86EMUL_CONTINUE; } -static inline int emulate_grp45(struct x86_emulate_ctxt *ctxt, - struct x86_emulate_ops *ops) +static int em_grp45(struct x86_emulate_ctxt *ctxt) { struct decode_cache *c = &ctxt->decode; + int rc = X86EMUL_CONTINUE; switch (c->modrm_reg) { case 0: /* inc */ @@ -1488,21 +1797,23 @@ static inline int emulate_grp45(struct x86_emulate_ctxt *ctxt, old_eip = c->eip; c->eip = c->src.val; c->src.val = old_eip; - emulate_push(ctxt, ops); + rc = em_push(ctxt); break; } case 4: /* jmp abs */ c->eip = c->src.val; break; + case 5: /* jmp far */ + rc = em_jmp_far(ctxt); + break; case 6: /* push */ - emulate_push(ctxt, ops); + rc = em_push(ctxt); break; } - return X86EMUL_CONTINUE; + return rc; } -static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt, - struct x86_emulate_ops *ops) +static int em_grp9(struct x86_emulate_ctxt *ctxt) { struct decode_cache *c = &ctxt->decode; u64 old = c->dst.orig_val64; @@ -1528,12 +1839,12 @@ static int emulate_ret_far(struct x86_emulate_ctxt *ctxt, int rc; unsigned long cs; - rc = emulate_pop(ctxt, ops, &c->eip, c->op_bytes); + rc = emulate_pop(ctxt, &c->eip, c->op_bytes); if (rc != X86EMUL_CONTINUE) return rc; if (c->op_bytes == 4) c->eip = (u32)c->eip; - rc = emulate_pop(ctxt, ops, &cs, c->op_bytes); + rc = emulate_pop(ctxt, &cs, c->op_bytes); if (rc != X86EMUL_CONTINUE) return rc; rc = load_segment_descriptor(ctxt, ops, (u16)cs, VCPU_SREG_CS); @@ -1562,8 +1873,10 @@ setup_syscalls_segments(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops, struct desc_struct *cs, struct desc_struct *ss) { + u16 selector; + memset(cs, 0, sizeof(struct desc_struct)); - ops->get_cached_descriptor(cs, NULL, VCPU_SREG_CS, ctxt->vcpu); + ops->get_segment(ctxt, &selector, cs, NULL, VCPU_SREG_CS); memset(ss, 0, sizeof(struct desc_struct)); cs->l = 0; /* will be adjusted later */ @@ -1593,44 +1906,44 @@ emulate_syscall(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) struct desc_struct cs, ss; u64 msr_data; u16 cs_sel, ss_sel; + u64 efer = 0; /* syscall is not available in real mode */ if (ctxt->mode == X86EMUL_MODE_REAL || ctxt->mode == X86EMUL_MODE_VM86) return emulate_ud(ctxt); + ops->get_msr(ctxt, MSR_EFER, &efer); setup_syscalls_segments(ctxt, ops, &cs, &ss); - ops->get_msr(ctxt->vcpu, MSR_STAR, &msr_data); + ops->get_msr(ctxt, MSR_STAR, &msr_data); msr_data >>= 32; cs_sel = (u16)(msr_data & 0xfffc); ss_sel = (u16)(msr_data + 8); - if (is_long_mode(ctxt->vcpu)) { + if (efer & EFER_LMA) { cs.d = 0; cs.l = 1; } - ops->set_cached_descriptor(&cs, 0, VCPU_SREG_CS, ctxt->vcpu); - ops->set_segment_selector(cs_sel, VCPU_SREG_CS, ctxt->vcpu); - ops->set_cached_descriptor(&ss, 0, VCPU_SREG_SS, ctxt->vcpu); - ops->set_segment_selector(ss_sel, VCPU_SREG_SS, ctxt->vcpu); + ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS); + ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); c->regs[VCPU_REGS_RCX] = c->eip; - if (is_long_mode(ctxt->vcpu)) { + if (efer & EFER_LMA) { #ifdef CONFIG_X86_64 c->regs[VCPU_REGS_R11] = ctxt->eflags & ~EFLG_RF; - ops->get_msr(ctxt->vcpu, + ops->get_msr(ctxt, ctxt->mode == X86EMUL_MODE_PROT64 ? MSR_LSTAR : MSR_CSTAR, &msr_data); c->eip = msr_data; - ops->get_msr(ctxt->vcpu, MSR_SYSCALL_MASK, &msr_data); + ops->get_msr(ctxt, MSR_SYSCALL_MASK, &msr_data); ctxt->eflags &= ~(msr_data | EFLG_RF); #endif } else { /* legacy mode */ - ops->get_msr(ctxt->vcpu, MSR_STAR, &msr_data); + ops->get_msr(ctxt, MSR_STAR, &msr_data); c->eip = (u32)msr_data; ctxt->eflags &= ~(EFLG_VM | EFLG_IF | EFLG_RF); @@ -1646,7 +1959,9 @@ emulate_sysenter(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) struct desc_struct cs, ss; u64 msr_data; u16 cs_sel, ss_sel; + u64 efer = 0; + ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); /* inject #GP if in real mode */ if (ctxt->mode == X86EMUL_MODE_REAL) return emulate_gp(ctxt, 0); @@ -1659,7 +1974,7 @@ emulate_sysenter(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) setup_syscalls_segments(ctxt, ops, &cs, &ss); - ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_CS, &msr_data); + ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data); switch (ctxt->mode) { case X86EMUL_MODE_PROT32: if ((msr_data & 0xfffc) == 0x0) @@ -1676,21 +1991,18 @@ emulate_sysenter(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) cs_sel &= ~SELECTOR_RPL_MASK; ss_sel = cs_sel + 8; ss_sel &= ~SELECTOR_RPL_MASK; - if (ctxt->mode == X86EMUL_MODE_PROT64 - || is_long_mode(ctxt->vcpu)) { + if (ctxt->mode == X86EMUL_MODE_PROT64 || (efer & EFER_LMA)) { cs.d = 0; cs.l = 1; } - ops->set_cached_descriptor(&cs, 0, VCPU_SREG_CS, ctxt->vcpu); - ops->set_segment_selector(cs_sel, VCPU_SREG_CS, ctxt->vcpu); - ops->set_cached_descriptor(&ss, 0, VCPU_SREG_SS, ctxt->vcpu); - ops->set_segment_selector(ss_sel, VCPU_SREG_SS, ctxt->vcpu); + ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS); + ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); - ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_EIP, &msr_data); + ops->get_msr(ctxt, MSR_IA32_SYSENTER_EIP, &msr_data); c->eip = msr_data; - ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_ESP, &msr_data); + ops->get_msr(ctxt, MSR_IA32_SYSENTER_ESP, &msr_data); c->regs[VCPU_REGS_RSP] = msr_data; return X86EMUL_CONTINUE; @@ -1719,7 +2031,7 @@ emulate_sysexit(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) cs.dpl = 3; ss.dpl = 3; - ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_CS, &msr_data); + ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data); switch (usermode) { case X86EMUL_MODE_PROT32: cs_sel = (u16)(msr_data + 16); @@ -1739,10 +2051,8 @@ emulate_sysexit(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) cs_sel |= SELECTOR_RPL_MASK; ss_sel |= SELECTOR_RPL_MASK; - ops->set_cached_descriptor(&cs, 0, VCPU_SREG_CS, ctxt->vcpu); - ops->set_segment_selector(cs_sel, VCPU_SREG_CS, ctxt->vcpu); - ops->set_cached_descriptor(&ss, 0, VCPU_SREG_SS, ctxt->vcpu); - ops->set_segment_selector(ss_sel, VCPU_SREG_SS, ctxt->vcpu); + ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS); + ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); c->eip = c->regs[VCPU_REGS_RDX]; c->regs[VCPU_REGS_RSP] = c->regs[VCPU_REGS_RCX]; @@ -1759,7 +2069,7 @@ static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt, if (ctxt->mode == X86EMUL_MODE_VM86) return true; iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> IOPL_SHIFT; - return ops->cpl(ctxt->vcpu) > iopl; + return ops->cpl(ctxt) > iopl; } static bool emulator_io_port_access_allowed(struct x86_emulate_ctxt *ctxt, @@ -1769,11 +2079,11 @@ static bool emulator_io_port_access_allowed(struct x86_emulate_ctxt *ctxt, struct desc_struct tr_seg; u32 base3; int r; - u16 io_bitmap_ptr, perm, bit_idx = port & 0x7; + u16 tr, io_bitmap_ptr, perm, bit_idx = port & 0x7; unsigned mask = (1 << len) - 1; unsigned long base; - ops->get_cached_descriptor(&tr_seg, &base3, VCPU_SREG_TR, ctxt->vcpu); + ops->get_segment(ctxt, &tr, &tr_seg, &base3, VCPU_SREG_TR); if (!tr_seg.p) return false; if (desc_limit_scaled(&tr_seg) < 103) @@ -1782,13 +2092,12 @@ static bool emulator_io_port_access_allowed(struct x86_emulate_ctxt *ctxt, #ifdef CONFIG_X86_64 base |= ((u64)base3) << 32; #endif - r = ops->read_std(base + 102, &io_bitmap_ptr, 2, ctxt->vcpu, NULL); + r = ops->read_std(ctxt, base + 102, &io_bitmap_ptr, 2, NULL); if (r != X86EMUL_CONTINUE) return false; if (io_bitmap_ptr + port/8 > desc_limit_scaled(&tr_seg)) return false; - r = ops->read_std(base + io_bitmap_ptr + port/8, &perm, 2, ctxt->vcpu, - NULL); + r = ops->read_std(ctxt, base + io_bitmap_ptr + port/8, &perm, 2, NULL); if (r != X86EMUL_CONTINUE) return false; if ((perm >> bit_idx) & mask) @@ -1829,11 +2138,11 @@ static void save_state_to_tss16(struct x86_emulate_ctxt *ctxt, tss->si = c->regs[VCPU_REGS_RSI]; tss->di = c->regs[VCPU_REGS_RDI]; - tss->es = ops->get_segment_selector(VCPU_SREG_ES, ctxt->vcpu); - tss->cs = ops->get_segment_selector(VCPU_SREG_CS, ctxt->vcpu); - tss->ss = ops->get_segment_selector(VCPU_SREG_SS, ctxt->vcpu); - tss->ds = ops->get_segment_selector(VCPU_SREG_DS, ctxt->vcpu); - tss->ldt = ops->get_segment_selector(VCPU_SREG_LDTR, ctxt->vcpu); + tss->es = get_segment_selector(ctxt, VCPU_SREG_ES); + tss->cs = get_segment_selector(ctxt, VCPU_SREG_CS); + tss->ss = get_segment_selector(ctxt, VCPU_SREG_SS); + tss->ds = get_segment_selector(ctxt, VCPU_SREG_DS); + tss->ldt = get_segment_selector(ctxt, VCPU_SREG_LDTR); } static int load_state_from_tss16(struct x86_emulate_ctxt *ctxt, @@ -1858,11 +2167,11 @@ static int load_state_from_tss16(struct x86_emulate_ctxt *ctxt, * SDM says that segment selectors are loaded before segment * descriptors */ - ops->set_segment_selector(tss->ldt, VCPU_SREG_LDTR, ctxt->vcpu); - ops->set_segment_selector(tss->es, VCPU_SREG_ES, ctxt->vcpu); - ops->set_segment_selector(tss->cs, VCPU_SREG_CS, ctxt->vcpu); - ops->set_segment_selector(tss->ss, VCPU_SREG_SS, ctxt->vcpu); - ops->set_segment_selector(tss->ds, VCPU_SREG_DS, ctxt->vcpu); + set_segment_selector(ctxt, tss->ldt, VCPU_SREG_LDTR); + set_segment_selector(ctxt, tss->es, VCPU_SREG_ES); + set_segment_selector(ctxt, tss->cs, VCPU_SREG_CS); + set_segment_selector(ctxt, tss->ss, VCPU_SREG_SS); + set_segment_selector(ctxt, tss->ds, VCPU_SREG_DS); /* * Now load segment descriptors. If fault happenes at this stage @@ -1896,7 +2205,7 @@ static int task_switch_16(struct x86_emulate_ctxt *ctxt, int ret; u32 new_tss_base = get_desc_base(new_desc); - ret = ops->read_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + ret = ops->read_std(ctxt, old_tss_base, &tss_seg, sizeof tss_seg, &ctxt->exception); if (ret != X86EMUL_CONTINUE) /* FIXME: need to provide precise fault address */ @@ -1904,13 +2213,13 @@ static int task_switch_16(struct x86_emulate_ctxt *ctxt, save_state_to_tss16(ctxt, ops, &tss_seg); - ret = ops->write_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + ret = ops->write_std(ctxt, old_tss_base, &tss_seg, sizeof tss_seg, &ctxt->exception); if (ret != X86EMUL_CONTINUE) /* FIXME: need to provide precise fault address */ return ret; - ret = ops->read_std(new_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + ret = ops->read_std(ctxt, new_tss_base, &tss_seg, sizeof tss_seg, &ctxt->exception); if (ret != X86EMUL_CONTINUE) /* FIXME: need to provide precise fault address */ @@ -1919,10 +2228,10 @@ static int task_switch_16(struct x86_emulate_ctxt *ctxt, if (old_tss_sel != 0xffff) { tss_seg.prev_task_link = old_tss_sel; - ret = ops->write_std(new_tss_base, + ret = ops->write_std(ctxt, new_tss_base, &tss_seg.prev_task_link, sizeof tss_seg.prev_task_link, - ctxt->vcpu, &ctxt->exception); + &ctxt->exception); if (ret != X86EMUL_CONTINUE) /* FIXME: need to provide precise fault address */ return ret; @@ -1937,7 +2246,7 @@ static void save_state_to_tss32(struct x86_emulate_ctxt *ctxt, { struct decode_cache *c = &ctxt->decode; - tss->cr3 = ops->get_cr(3, ctxt->vcpu); + tss->cr3 = ops->get_cr(ctxt, 3); tss->eip = c->eip; tss->eflags = ctxt->eflags; tss->eax = c->regs[VCPU_REGS_RAX]; @@ -1949,13 +2258,13 @@ static void save_state_to_tss32(struct x86_emulate_ctxt *ctxt, tss->esi = c->regs[VCPU_REGS_RSI]; tss->edi = c->regs[VCPU_REGS_RDI]; - tss->es = ops->get_segment_selector(VCPU_SREG_ES, ctxt->vcpu); - tss->cs = ops->get_segment_selector(VCPU_SREG_CS, ctxt->vcpu); - tss->ss = ops->get_segment_selector(VCPU_SREG_SS, ctxt->vcpu); - tss->ds = ops->get_segment_selector(VCPU_SREG_DS, ctxt->vcpu); - tss->fs = ops->get_segment_selector(VCPU_SREG_FS, ctxt->vcpu); - tss->gs = ops->get_segment_selector(VCPU_SREG_GS, ctxt->vcpu); - tss->ldt_selector = ops->get_segment_selector(VCPU_SREG_LDTR, ctxt->vcpu); + tss->es = get_segment_selector(ctxt, VCPU_SREG_ES); + tss->cs = get_segment_selector(ctxt, VCPU_SREG_CS); + tss->ss = get_segment_selector(ctxt, VCPU_SREG_SS); + tss->ds = get_segment_selector(ctxt, VCPU_SREG_DS); + tss->fs = get_segment_selector(ctxt, VCPU_SREG_FS); + tss->gs = get_segment_selector(ctxt, VCPU_SREG_GS); + tss->ldt_selector = get_segment_selector(ctxt, VCPU_SREG_LDTR); } static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, @@ -1965,7 +2274,7 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, struct decode_cache *c = &ctxt->decode; int ret; - if (ops->set_cr(3, tss->cr3, ctxt->vcpu)) + if (ops->set_cr(ctxt, 3, tss->cr3)) return emulate_gp(ctxt, 0); c->eip = tss->eip; ctxt->eflags = tss->eflags | 2; @@ -1982,13 +2291,13 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, * SDM says that segment selectors are loaded before segment * descriptors */ - ops->set_segment_selector(tss->ldt_selector, VCPU_SREG_LDTR, ctxt->vcpu); - ops->set_segment_selector(tss->es, VCPU_SREG_ES, ctxt->vcpu); - ops->set_segment_selector(tss->cs, VCPU_SREG_CS, ctxt->vcpu); - ops->set_segment_selector(tss->ss, VCPU_SREG_SS, ctxt->vcpu); - ops->set_segment_selector(tss->ds, VCPU_SREG_DS, ctxt->vcpu); - ops->set_segment_selector(tss->fs, VCPU_SREG_FS, ctxt->vcpu); - ops->set_segment_selector(tss->gs, VCPU_SREG_GS, ctxt->vcpu); + set_segment_selector(ctxt, tss->ldt_selector, VCPU_SREG_LDTR); + set_segment_selector(ctxt, tss->es, VCPU_SREG_ES); + set_segment_selector(ctxt, tss->cs, VCPU_SREG_CS); + set_segment_selector(ctxt, tss->ss, VCPU_SREG_SS); + set_segment_selector(ctxt, tss->ds, VCPU_SREG_DS); + set_segment_selector(ctxt, tss->fs, VCPU_SREG_FS); + set_segment_selector(ctxt, tss->gs, VCPU_SREG_GS); /* * Now load segment descriptors. If fault happenes at this stage @@ -2028,7 +2337,7 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt, int ret; u32 new_tss_base = get_desc_base(new_desc); - ret = ops->read_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + ret = ops->read_std(ctxt, old_tss_base, &tss_seg, sizeof tss_seg, &ctxt->exception); if (ret != X86EMUL_CONTINUE) /* FIXME: need to provide precise fault address */ @@ -2036,13 +2345,13 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt, save_state_to_tss32(ctxt, ops, &tss_seg); - ret = ops->write_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + ret = ops->write_std(ctxt, old_tss_base, &tss_seg, sizeof tss_seg, &ctxt->exception); if (ret != X86EMUL_CONTINUE) /* FIXME: need to provide precise fault address */ return ret; - ret = ops->read_std(new_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + ret = ops->read_std(ctxt, new_tss_base, &tss_seg, sizeof tss_seg, &ctxt->exception); if (ret != X86EMUL_CONTINUE) /* FIXME: need to provide precise fault address */ @@ -2051,10 +2360,10 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt, if (old_tss_sel != 0xffff) { tss_seg.prev_task_link = old_tss_sel; - ret = ops->write_std(new_tss_base, + ret = ops->write_std(ctxt, new_tss_base, &tss_seg.prev_task_link, sizeof tss_seg.prev_task_link, - ctxt->vcpu, &ctxt->exception); + &ctxt->exception); if (ret != X86EMUL_CONTINUE) /* FIXME: need to provide precise fault address */ return ret; @@ -2070,9 +2379,9 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, { struct desc_struct curr_tss_desc, next_tss_desc; int ret; - u16 old_tss_sel = ops->get_segment_selector(VCPU_SREG_TR, ctxt->vcpu); + u16 old_tss_sel = get_segment_selector(ctxt, VCPU_SREG_TR); ulong old_tss_base = - ops->get_cached_segment_base(VCPU_SREG_TR, ctxt->vcpu); + ops->get_cached_segment_base(ctxt, VCPU_SREG_TR); u32 desc_limit; /* FIXME: old_tss_base == ~0 ? */ @@ -2088,7 +2397,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, if (reason != TASK_SWITCH_IRET) { if ((tss_selector & 3) > next_tss_desc.dpl || - ops->cpl(ctxt->vcpu) > next_tss_desc.dpl) + ops->cpl(ctxt) > next_tss_desc.dpl) return emulate_gp(ctxt, 0); } @@ -2132,9 +2441,8 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, &next_tss_desc); } - ops->set_cr(0, ops->get_cr(0, ctxt->vcpu) | X86_CR0_TS, ctxt->vcpu); - ops->set_cached_descriptor(&next_tss_desc, 0, VCPU_SREG_TR, ctxt->vcpu); - ops->set_segment_selector(tss_selector, VCPU_SREG_TR, ctxt->vcpu); + ops->set_cr(ctxt, 0, ops->get_cr(ctxt, 0) | X86_CR0_TS); + ops->set_segment(ctxt, tss_selector, &next_tss_desc, 0, VCPU_SREG_TR); if (has_error_code) { struct decode_cache *c = &ctxt->decode; @@ -2142,7 +2450,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, c->op_bytes = c->ad_bytes = (next_tss_desc.type & 8) ? 4 : 2; c->lock_prefix = 0; c->src.val = (unsigned long) error_code; - emulate_push(ctxt, ops); + ret = em_push(ctxt); } return ret; @@ -2162,13 +2470,10 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt, rc = emulator_do_task_switch(ctxt, ops, tss_selector, reason, has_error_code, error_code); - if (rc == X86EMUL_CONTINUE) { - rc = writeback(ctxt, ops); - if (rc == X86EMUL_CONTINUE) - ctxt->eip = c->eip; - } + if (rc == X86EMUL_CONTINUE) + ctxt->eip = c->eip; - return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0; + return (rc == X86EMUL_UNHANDLEABLE) ? EMULATION_FAILED : EMULATION_OK; } static void string_addr_inc(struct x86_emulate_ctxt *ctxt, unsigned seg, @@ -2182,12 +2487,6 @@ static void string_addr_inc(struct x86_emulate_ctxt *ctxt, unsigned seg, op->addr.mem.seg = seg; } -static int em_push(struct x86_emulate_ctxt *ctxt) -{ - emulate_push(ctxt, ctxt->ops); - return X86EMUL_CONTINUE; -} - static int em_das(struct x86_emulate_ctxt *ctxt) { struct decode_cache *c = &ctxt->decode; @@ -2234,7 +2533,7 @@ static int em_call_far(struct x86_emulate_ctxt *ctxt) ulong old_eip; int rc; - old_cs = ctxt->ops->get_segment_selector(VCPU_SREG_CS, ctxt->vcpu); + old_cs = get_segment_selector(ctxt, VCPU_SREG_CS); old_eip = c->eip; memcpy(&sel, c->src.valptr + c->op_bytes, 2); @@ -2245,20 +2544,12 @@ static int em_call_far(struct x86_emulate_ctxt *ctxt) memcpy(&c->eip, c->src.valptr, c->op_bytes); c->src.val = old_cs; - emulate_push(ctxt, ctxt->ops); - rc = writeback(ctxt, ctxt->ops); + rc = em_push(ctxt); if (rc != X86EMUL_CONTINUE) return rc; c->src.val = old_eip; - emulate_push(ctxt, ctxt->ops); - rc = writeback(ctxt, ctxt->ops); - if (rc != X86EMUL_CONTINUE) - return rc; - - c->dst.type = OP_NONE; - - return X86EMUL_CONTINUE; + return em_push(ctxt); } static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt) @@ -2269,13 +2560,79 @@ static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt) c->dst.type = OP_REG; c->dst.addr.reg = &c->eip; c->dst.bytes = c->op_bytes; - rc = emulate_pop(ctxt, ctxt->ops, &c->dst.val, c->op_bytes); + rc = emulate_pop(ctxt, &c->dst.val, c->op_bytes); if (rc != X86EMUL_CONTINUE) return rc; register_address_increment(c, &c->regs[VCPU_REGS_RSP], c->src.val); return X86EMUL_CONTINUE; } +static int em_add(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + + emulate_2op_SrcV("add", c->src, c->dst, ctxt->eflags); + return X86EMUL_CONTINUE; +} + +static int em_or(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + + emulate_2op_SrcV("or", c->src, c->dst, ctxt->eflags); + return X86EMUL_CONTINUE; +} + +static int em_adc(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + + emulate_2op_SrcV("adc", c->src, c->dst, ctxt->eflags); + return X86EMUL_CONTINUE; +} + +static int em_sbb(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + + emulate_2op_SrcV("sbb", c->src, c->dst, ctxt->eflags); + return X86EMUL_CONTINUE; +} + +static int em_and(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + + emulate_2op_SrcV("and", c->src, c->dst, ctxt->eflags); + return X86EMUL_CONTINUE; +} + +static int em_sub(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + + emulate_2op_SrcV("sub", c->src, c->dst, ctxt->eflags); + return X86EMUL_CONTINUE; +} + +static int em_xor(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + + emulate_2op_SrcV("xor", c->src, c->dst, ctxt->eflags); + return X86EMUL_CONTINUE; +} + +static int em_cmp(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + + emulate_2op_SrcV("cmp", c->src, c->dst, ctxt->eflags); + /* Disable writeback. */ + c->dst.type = OP_NONE; + return X86EMUL_CONTINUE; +} + static int em_imul(struct x86_emulate_ctxt *ctxt) { struct decode_cache *c = &ctxt->decode; @@ -2306,13 +2663,10 @@ static int em_cwd(struct x86_emulate_ctxt *ctxt) static int em_rdtsc(struct x86_emulate_ctxt *ctxt) { - unsigned cpl = ctxt->ops->cpl(ctxt->vcpu); struct decode_cache *c = &ctxt->decode; u64 tsc = 0; - if (cpl > 0 && (ctxt->ops->get_cr(4, ctxt->vcpu) & X86_CR4_TSD)) - return emulate_gp(ctxt, 0); - ctxt->ops->get_msr(ctxt->vcpu, MSR_IA32_TSC, &tsc); + ctxt->ops->get_msr(ctxt, MSR_IA32_TSC, &tsc); c->regs[VCPU_REGS_RAX] = (u32)tsc; c->regs[VCPU_REGS_RDX] = tsc >> 32; return X86EMUL_CONTINUE; @@ -2325,22 +2679,375 @@ static int em_mov(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_movdqu(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + memcpy(&c->dst.vec_val, &c->src.vec_val, c->op_bytes); + return X86EMUL_CONTINUE; +} + +static int em_invlpg(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + int rc; + ulong linear; + + rc = linearize(ctxt, c->src.addr.mem, 1, false, &linear); + if (rc == X86EMUL_CONTINUE) + ctxt->ops->invlpg(ctxt, linear); + /* Disable writeback. */ + c->dst.type = OP_NONE; + return X86EMUL_CONTINUE; +} + +static int em_clts(struct x86_emulate_ctxt *ctxt) +{ + ulong cr0; + + cr0 = ctxt->ops->get_cr(ctxt, 0); + cr0 &= ~X86_CR0_TS; + ctxt->ops->set_cr(ctxt, 0, cr0); + return X86EMUL_CONTINUE; +} + +static int em_vmcall(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + int rc; + + if (c->modrm_mod != 3 || c->modrm_rm != 1) + return X86EMUL_UNHANDLEABLE; + + rc = ctxt->ops->fix_hypercall(ctxt); + if (rc != X86EMUL_CONTINUE) + return rc; + + /* Let the processor re-execute the fixed hypercall */ + c->eip = ctxt->eip; + /* Disable writeback. */ + c->dst.type = OP_NONE; + return X86EMUL_CONTINUE; +} + +static int em_lgdt(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + struct desc_ptr desc_ptr; + int rc; + + rc = read_descriptor(ctxt, c->src.addr.mem, + &desc_ptr.size, &desc_ptr.address, + c->op_bytes); + if (rc != X86EMUL_CONTINUE) + return rc; + ctxt->ops->set_gdt(ctxt, &desc_ptr); + /* Disable writeback. */ + c->dst.type = OP_NONE; + return X86EMUL_CONTINUE; +} + +static int em_vmmcall(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + int rc; + + rc = ctxt->ops->fix_hypercall(ctxt); + + /* Disable writeback. */ + c->dst.type = OP_NONE; + return rc; +} + +static int em_lidt(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + struct desc_ptr desc_ptr; + int rc; + + rc = read_descriptor(ctxt, c->src.addr.mem, + &desc_ptr.size, &desc_ptr.address, + c->op_bytes); + if (rc != X86EMUL_CONTINUE) + return rc; + ctxt->ops->set_idt(ctxt, &desc_ptr); + /* Disable writeback. */ + c->dst.type = OP_NONE; + return X86EMUL_CONTINUE; +} + +static int em_smsw(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + + c->dst.bytes = 2; + c->dst.val = ctxt->ops->get_cr(ctxt, 0); + return X86EMUL_CONTINUE; +} + +static int em_lmsw(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + ctxt->ops->set_cr(ctxt, 0, (ctxt->ops->get_cr(ctxt, 0) & ~0x0eul) + | (c->src.val & 0x0f)); + c->dst.type = OP_NONE; + return X86EMUL_CONTINUE; +} + +static bool valid_cr(int nr) +{ + switch (nr) { + case 0: + case 2 ... 4: + case 8: + return true; + default: + return false; + } +} + +static int check_cr_read(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + + if (!valid_cr(c->modrm_reg)) + return emulate_ud(ctxt); + + return X86EMUL_CONTINUE; +} + +static int check_cr_write(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + u64 new_val = c->src.val64; + int cr = c->modrm_reg; + u64 efer = 0; + + static u64 cr_reserved_bits[] = { + 0xffffffff00000000ULL, + 0, 0, 0, /* CR3 checked later */ + CR4_RESERVED_BITS, + 0, 0, 0, + CR8_RESERVED_BITS, + }; + + if (!valid_cr(cr)) + return emulate_ud(ctxt); + + if (new_val & cr_reserved_bits[cr]) + return emulate_gp(ctxt, 0); + + switch (cr) { + case 0: { + u64 cr4; + if (((new_val & X86_CR0_PG) && !(new_val & X86_CR0_PE)) || + ((new_val & X86_CR0_NW) && !(new_val & X86_CR0_CD))) + return emulate_gp(ctxt, 0); + + cr4 = ctxt->ops->get_cr(ctxt, 4); + ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); + + if ((new_val & X86_CR0_PG) && (efer & EFER_LME) && + !(cr4 & X86_CR4_PAE)) + return emulate_gp(ctxt, 0); + + break; + } + case 3: { + u64 rsvd = 0; + + ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); + if (efer & EFER_LMA) + rsvd = CR3_L_MODE_RESERVED_BITS; + else if (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_PAE) + rsvd = CR3_PAE_RESERVED_BITS; + else if (ctxt->ops->get_cr(ctxt, 0) & X86_CR0_PG) + rsvd = CR3_NONPAE_RESERVED_BITS; + + if (new_val & rsvd) + return emulate_gp(ctxt, 0); + + break; + } + case 4: { + u64 cr4; + + cr4 = ctxt->ops->get_cr(ctxt, 4); + ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); + + if ((efer & EFER_LMA) && !(new_val & X86_CR4_PAE)) + return emulate_gp(ctxt, 0); + + break; + } + } + + return X86EMUL_CONTINUE; +} + +static int check_dr7_gd(struct x86_emulate_ctxt *ctxt) +{ + unsigned long dr7; + + ctxt->ops->get_dr(ctxt, 7, &dr7); + + /* Check if DR7.Global_Enable is set */ + return dr7 & (1 << 13); +} + +static int check_dr_read(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + int dr = c->modrm_reg; + u64 cr4; + + if (dr > 7) + return emulate_ud(ctxt); + + cr4 = ctxt->ops->get_cr(ctxt, 4); + if ((cr4 & X86_CR4_DE) && (dr == 4 || dr == 5)) + return emulate_ud(ctxt); + + if (check_dr7_gd(ctxt)) + return emulate_db(ctxt); + + return X86EMUL_CONTINUE; +} + +static int check_dr_write(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + u64 new_val = c->src.val64; + int dr = c->modrm_reg; + + if ((dr == 6 || dr == 7) && (new_val & 0xffffffff00000000ULL)) + return emulate_gp(ctxt, 0); + + return check_dr_read(ctxt); +} + +static int check_svme(struct x86_emulate_ctxt *ctxt) +{ + u64 efer; + + ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); + + if (!(efer & EFER_SVME)) + return emulate_ud(ctxt); + + return X86EMUL_CONTINUE; +} + +static int check_svme_pa(struct x86_emulate_ctxt *ctxt) +{ + u64 rax = ctxt->decode.regs[VCPU_REGS_RAX]; + + /* Valid physical address? */ + if (rax & 0xffff000000000000ULL) + return emulate_gp(ctxt, 0); + + return check_svme(ctxt); +} + +static int check_rdtsc(struct x86_emulate_ctxt *ctxt) +{ + u64 cr4 = ctxt->ops->get_cr(ctxt, 4); + + if (cr4 & X86_CR4_TSD && ctxt->ops->cpl(ctxt)) + return emulate_ud(ctxt); + + return X86EMUL_CONTINUE; +} + +static int check_rdpmc(struct x86_emulate_ctxt *ctxt) +{ + u64 cr4 = ctxt->ops->get_cr(ctxt, 4); + u64 rcx = ctxt->decode.regs[VCPU_REGS_RCX]; + + if ((!(cr4 & X86_CR4_PCE) && ctxt->ops->cpl(ctxt)) || + (rcx > 3)) + return emulate_gp(ctxt, 0); + + return X86EMUL_CONTINUE; +} + +static int check_perm_in(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + + c->dst.bytes = min(c->dst.bytes, 4u); + if (!emulator_io_permited(ctxt, ctxt->ops, c->src.val, c->dst.bytes)) + return emulate_gp(ctxt, 0); + + return X86EMUL_CONTINUE; +} + +static int check_perm_out(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + + c->src.bytes = min(c->src.bytes, 4u); + if (!emulator_io_permited(ctxt, ctxt->ops, c->dst.val, c->src.bytes)) + return emulate_gp(ctxt, 0); + + return X86EMUL_CONTINUE; +} + #define D(_y) { .flags = (_y) } +#define DI(_y, _i) { .flags = (_y), .intercept = x86_intercept_##_i } +#define DIP(_y, _i, _p) { .flags = (_y), .intercept = x86_intercept_##_i, \ + .check_perm = (_p) } #define N D(0) +#define EXT(_f, _e) { .flags = ((_f) | RMExt), .u.group = (_e) } #define G(_f, _g) { .flags = ((_f) | Group), .u.group = (_g) } -#define GD(_f, _g) { .flags = ((_f) | Group | GroupDual), .u.gdual = (_g) } +#define GD(_f, _g) { .flags = ((_f) | GroupDual), .u.gdual = (_g) } #define I(_f, _e) { .flags = (_f), .u.execute = (_e) } +#define II(_f, _e, _i) \ + { .flags = (_f), .u.execute = (_e), .intercept = x86_intercept_##_i } +#define IIP(_f, _e, _i, _p) \ + { .flags = (_f), .u.execute = (_e), .intercept = x86_intercept_##_i, \ + .check_perm = (_p) } +#define GP(_f, _g) { .flags = ((_f) | Prefix), .u.gprefix = (_g) } #define D2bv(_f) D((_f) | ByteOp), D(_f) +#define D2bvIP(_f, _i, _p) DIP((_f) | ByteOp, _i, _p), DIP(_f, _i, _p) #define I2bv(_f, _e) I((_f) | ByteOp, _e), I(_f, _e) -#define D6ALU(_f) D2bv((_f) | DstMem | SrcReg | ModRM), \ - D2bv(((_f) | DstReg | SrcMem | ModRM) & ~Lock), \ - D2bv(((_f) & ~Lock) | DstAcc | SrcImm) +#define I6ALU(_f, _e) I2bv((_f) | DstMem | SrcReg | ModRM, _e), \ + I2bv(((_f) | DstReg | SrcMem | ModRM) & ~Lock, _e), \ + I2bv(((_f) & ~Lock) | DstAcc | SrcImm, _e) +static struct opcode group7_rm1[] = { + DI(SrcNone | ModRM | Priv, monitor), + DI(SrcNone | ModRM | Priv, mwait), + N, N, N, N, N, N, +}; + +static struct opcode group7_rm3[] = { + DIP(SrcNone | ModRM | Prot | Priv, vmrun, check_svme_pa), + II(SrcNone | ModRM | Prot | VendorSpecific, em_vmmcall, vmmcall), + DIP(SrcNone | ModRM | Prot | Priv, vmload, check_svme_pa), + DIP(SrcNone | ModRM | Prot | Priv, vmsave, check_svme_pa), + DIP(SrcNone | ModRM | Prot | Priv, stgi, check_svme), + DIP(SrcNone | ModRM | Prot | Priv, clgi, check_svme), + DIP(SrcNone | ModRM | Prot | Priv, skinit, check_svme), + DIP(SrcNone | ModRM | Prot | Priv, invlpga, check_svme), +}; + +static struct opcode group7_rm7[] = { + N, + DIP(SrcNone | ModRM, rdtscp, check_rdtsc), + N, N, N, N, N, N, +}; static struct opcode group1[] = { - X7(D(Lock)), N + I(Lock, em_add), + I(Lock, em_or), + I(Lock, em_adc), + I(Lock, em_sbb), + I(Lock, em_and), + I(Lock, em_sub), + I(Lock, em_xor), + I(0, em_cmp), }; static struct opcode group1A[] = { @@ -2366,16 +3073,28 @@ static struct opcode group5[] = { D(SrcMem | ModRM | Stack), N, }; +static struct opcode group6[] = { + DI(ModRM | Prot, sldt), + DI(ModRM | Prot, str), + DI(ModRM | Prot | Priv, lldt), + DI(ModRM | Prot | Priv, ltr), + N, N, N, N, +}; + static struct group_dual group7 = { { - N, N, D(ModRM | SrcMem | Priv), D(ModRM | SrcMem | Priv), - D(SrcNone | ModRM | DstMem | Mov), N, - D(SrcMem16 | ModRM | Mov | Priv), - D(SrcMem | ModRM | ByteOp | Priv | NoAccess), + DI(ModRM | Mov | DstMem | Priv, sgdt), + DI(ModRM | Mov | DstMem | Priv, sidt), + II(ModRM | SrcMem | Priv, em_lgdt, lgdt), + II(ModRM | SrcMem | Priv, em_lidt, lidt), + II(SrcNone | ModRM | DstMem | Mov, em_smsw, smsw), N, + II(SrcMem16 | ModRM | Mov | Priv, em_lmsw, lmsw), + II(SrcMem | ModRM | ByteOp | Priv | NoAccess, em_invlpg, invlpg), }, { - D(SrcNone | ModRM | Priv | VendorSpecific), N, - N, D(SrcNone | ModRM | Priv | VendorSpecific), - D(SrcNone | ModRM | DstMem | Mov), N, - D(SrcMem16 | ModRM | Mov | Priv), N, + I(SrcNone | ModRM | Priv | VendorSpecific, em_vmcall), + EXT(0, group7_rm1), + N, EXT(0, group7_rm3), + II(SrcNone | ModRM | DstMem | Mov, em_smsw, smsw), N, + II(SrcMem16 | ModRM | Mov | Priv, em_lmsw, lmsw), EXT(0, group7_rm7), } }; static struct opcode group8[] = { @@ -2394,35 +3113,40 @@ static struct opcode group11[] = { I(DstMem | SrcImm | ModRM | Mov, em_mov), X7(D(Undefined)), }; +static struct gprefix pfx_0f_6f_0f_7f = { + N, N, N, I(Sse, em_movdqu), +}; + static struct opcode opcode_table[256] = { /* 0x00 - 0x07 */ - D6ALU(Lock), + I6ALU(Lock, em_add), D(ImplicitOps | Stack | No64), D(ImplicitOps | Stack | No64), /* 0x08 - 0x0F */ - D6ALU(Lock), + I6ALU(Lock, em_or), D(ImplicitOps | Stack | No64), N, /* 0x10 - 0x17 */ - D6ALU(Lock), + I6ALU(Lock, em_adc), D(ImplicitOps | Stack | No64), D(ImplicitOps | Stack | No64), /* 0x18 - 0x1F */ - D6ALU(Lock), + I6ALU(Lock, em_sbb), D(ImplicitOps | Stack | No64), D(ImplicitOps | Stack | No64), /* 0x20 - 0x27 */ - D6ALU(Lock), N, N, + I6ALU(Lock, em_and), N, N, /* 0x28 - 0x2F */ - D6ALU(Lock), N, I(ByteOp | DstAcc | No64, em_das), + I6ALU(Lock, em_sub), N, I(ByteOp | DstAcc | No64, em_das), /* 0x30 - 0x37 */ - D6ALU(Lock), N, N, + I6ALU(Lock, em_xor), N, N, /* 0x38 - 0x3F */ - D6ALU(0), N, N, + I6ALU(0, em_cmp), N, N, /* 0x40 - 0x4F */ X16(D(DstReg)), /* 0x50 - 0x57 */ X8(I(SrcReg | Stack, em_push)), /* 0x58 - 0x5F */ - X8(D(DstReg | Stack)), + X8(I(DstReg | Stack, em_pop)), /* 0x60 - 0x67 */ - D(ImplicitOps | Stack | No64), D(ImplicitOps | Stack | No64), + I(ImplicitOps | Stack | No64, em_pusha), + I(ImplicitOps | Stack | No64, em_popa), N, D(DstReg | SrcMem32 | ModRM | Mov) /* movsxd (x86/64) */ , N, N, N, N, /* 0x68 - 0x6F */ @@ -2430,8 +3154,8 @@ static struct opcode opcode_table[256] = { I(DstReg | SrcMem | ModRM | Src2Imm, em_imul_3op), I(SrcImmByte | Mov | Stack, em_push), I(DstReg | SrcMem | ModRM | Src2ImmByte, em_imul_3op), - D2bv(DstDI | Mov | String), /* insb, insw/insd */ - D2bv(SrcSI | ImplicitOps | String), /* outsb, outsw/outsd */ + D2bvIP(DstDI | Mov | String, ins, check_perm_in), /* insb, insw/insd */ + D2bvIP(SrcSI | ImplicitOps | String, outs, check_perm_out), /* outsb, outsw/outsd */ /* 0x70 - 0x7F */ X16(D(SrcImmByte)), /* 0x80 - 0x87 */ @@ -2446,21 +3170,22 @@ static struct opcode opcode_table[256] = { D(DstMem | SrcNone | ModRM | Mov), D(ModRM | SrcMem | NoAccess | DstReg), D(ImplicitOps | SrcMem16 | ModRM), G(0, group1A), /* 0x90 - 0x97 */ - X8(D(SrcAcc | DstReg)), + DI(SrcAcc | DstReg, pause), X7(D(SrcAcc | DstReg)), /* 0x98 - 0x9F */ D(DstAcc | SrcNone), I(ImplicitOps | SrcAcc, em_cwd), I(SrcImmFAddr | No64, em_call_far), N, - D(ImplicitOps | Stack), D(ImplicitOps | Stack), N, N, + II(ImplicitOps | Stack, em_pushf, pushf), + II(ImplicitOps | Stack, em_popf, popf), N, N, /* 0xA0 - 0xA7 */ I2bv(DstAcc | SrcMem | Mov | MemAbs, em_mov), I2bv(DstMem | SrcAcc | Mov | MemAbs, em_mov), I2bv(SrcSI | DstDI | Mov | String, em_mov), - D2bv(SrcSI | DstDI | String), + I2bv(SrcSI | DstDI | String, em_cmp), /* 0xA8 - 0xAF */ D2bv(DstAcc | SrcImm), I2bv(SrcAcc | DstDI | Mov | String, em_mov), I2bv(SrcSI | DstAcc | Mov | String, em_mov), - D2bv(SrcAcc | DstDI | String), + I2bv(SrcAcc | DstDI | String, em_cmp), /* 0xB0 - 0xB7 */ X8(I(ByteOp | DstReg | SrcImm | Mov, em_mov)), /* 0xB8 - 0xBF */ @@ -2473,7 +3198,8 @@ static struct opcode opcode_table[256] = { G(ByteOp, group11), G(0, group11), /* 0xC8 - 0xCF */ N, N, N, D(ImplicitOps | Stack), - D(ImplicitOps), D(SrcImmByte), D(ImplicitOps | No64), D(ImplicitOps), + D(ImplicitOps), DI(SrcImmByte, intn), + D(ImplicitOps | No64), DI(ImplicitOps, iret), /* 0xD0 - 0xD7 */ D2bv(DstMem | SrcOne | ModRM), D2bv(DstMem | ModRM), N, N, N, N, @@ -2481,14 +3207,17 @@ static struct opcode opcode_table[256] = { N, N, N, N, N, N, N, N, /* 0xE0 - 0xE7 */ X4(D(SrcImmByte)), - D2bv(SrcImmUByte | DstAcc), D2bv(SrcAcc | DstImmUByte), + D2bvIP(SrcImmUByte | DstAcc, in, check_perm_in), + D2bvIP(SrcAcc | DstImmUByte, out, check_perm_out), /* 0xE8 - 0xEF */ D(SrcImm | Stack), D(SrcImm | ImplicitOps), D(SrcImmFAddr | No64), D(SrcImmByte | ImplicitOps), - D2bv(SrcNone | DstAcc), D2bv(SrcAcc | ImplicitOps), + D2bvIP(SrcNone | DstAcc, in, check_perm_in), + D2bvIP(SrcAcc | ImplicitOps, out, check_perm_out), /* 0xF0 - 0xF7 */ - N, N, N, N, - D(ImplicitOps | Priv), D(ImplicitOps), G(ByteOp, group3), G(0, group3), + N, DI(ImplicitOps, icebp), N, N, + DI(ImplicitOps | Priv, hlt), D(ImplicitOps), + G(ByteOp, group3), G(0, group3), /* 0xF8 - 0xFF */ D(ImplicitOps), D(ImplicitOps), D(ImplicitOps), D(ImplicitOps), D(ImplicitOps), D(ImplicitOps), G(0, group4), G(0, group5), @@ -2496,20 +3225,24 @@ static struct opcode opcode_table[256] = { static struct opcode twobyte_table[256] = { /* 0x00 - 0x0F */ - N, GD(0, &group7), N, N, - N, D(ImplicitOps | VendorSpecific), D(ImplicitOps | Priv), N, - D(ImplicitOps | Priv), D(ImplicitOps | Priv), N, N, + G(0, group6), GD(0, &group7), N, N, + N, D(ImplicitOps | VendorSpecific), DI(ImplicitOps | Priv, clts), N, + DI(ImplicitOps | Priv, invd), DI(ImplicitOps | Priv, wbinvd), N, N, N, D(ImplicitOps | ModRM), N, N, /* 0x10 - 0x1F */ N, N, N, N, N, N, N, N, D(ImplicitOps | ModRM), N, N, N, N, N, N, N, /* 0x20 - 0x2F */ - D(ModRM | DstMem | Priv | Op3264), D(ModRM | DstMem | Priv | Op3264), - D(ModRM | SrcMem | Priv | Op3264), D(ModRM | SrcMem | Priv | Op3264), + DIP(ModRM | DstMem | Priv | Op3264, cr_read, check_cr_read), + DIP(ModRM | DstMem | Priv | Op3264, dr_read, check_dr_read), + DIP(ModRM | SrcMem | Priv | Op3264, cr_write, check_cr_write), + DIP(ModRM | SrcMem | Priv | Op3264, dr_write, check_dr_write), N, N, N, N, N, N, N, N, N, N, N, N, /* 0x30 - 0x3F */ - D(ImplicitOps | Priv), I(ImplicitOps, em_rdtsc), - D(ImplicitOps | Priv), N, + DI(ImplicitOps | Priv, wrmsr), + IIP(ImplicitOps, em_rdtsc, rdtsc, check_rdtsc), + DI(ImplicitOps | Priv, rdmsr), + DIP(ImplicitOps | Priv, rdpmc, check_rdpmc), D(ImplicitOps | VendorSpecific), D(ImplicitOps | Priv | VendorSpecific), N, N, N, N, N, N, N, N, N, N, @@ -2518,21 +3251,27 @@ static struct opcode twobyte_table[256] = { /* 0x50 - 0x5F */ N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, /* 0x60 - 0x6F */ - N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, + N, N, N, N, + N, N, N, N, + N, N, N, N, + N, N, N, GP(SrcMem | DstReg | ModRM | Mov, &pfx_0f_6f_0f_7f), /* 0x70 - 0x7F */ - N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, + N, N, N, N, + N, N, N, N, + N, N, N, N, + N, N, N, GP(SrcReg | DstMem | ModRM | Mov, &pfx_0f_6f_0f_7f), /* 0x80 - 0x8F */ X16(D(SrcImm)), /* 0x90 - 0x9F */ X16(D(ByteOp | DstMem | SrcNone | ModRM| Mov)), /* 0xA0 - 0xA7 */ D(ImplicitOps | Stack), D(ImplicitOps | Stack), - N, D(DstMem | SrcReg | ModRM | BitOp), + DI(ImplicitOps, cpuid), D(DstMem | SrcReg | ModRM | BitOp), D(DstMem | SrcReg | Src2ImmByte | ModRM), D(DstMem | SrcReg | Src2CL | ModRM), N, N, /* 0xA8 - 0xAF */ D(ImplicitOps | Stack), D(ImplicitOps | Stack), - N, D(DstMem | SrcReg | ModRM | BitOp | Lock), + DI(ImplicitOps, rsm), D(DstMem | SrcReg | ModRM | BitOp | Lock), D(DstMem | SrcReg | Src2ImmByte | ModRM), D(DstMem | SrcReg | Src2CL | ModRM), D(ModRM), I(DstReg | SrcMem | ModRM, em_imul), @@ -2564,10 +3303,13 @@ static struct opcode twobyte_table[256] = { #undef G #undef GD #undef I +#undef GP +#undef EXT #undef D2bv +#undef D2bvIP #undef I2bv -#undef D6ALU +#undef I6ALU static unsigned imm_size(struct decode_cache *c) { @@ -2625,8 +3367,9 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) struct decode_cache *c = &ctxt->decode; int rc = X86EMUL_CONTINUE; int mode = ctxt->mode; - int def_op_bytes, def_ad_bytes, dual, goffset; - struct opcode opcode, *g_mod012, *g_mod3; + int def_op_bytes, def_ad_bytes, goffset, simd_prefix; + bool op_prefix = false; + struct opcode opcode; struct operand memop = { .type = OP_NONE }; c->eip = ctxt->eip; @@ -2634,7 +3377,6 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) c->fetch.end = c->fetch.start + insn_len; if (insn_len > 0) memcpy(c->fetch.data, insn, insn_len); - ctxt->cs_base = seg_base(ctxt, ops, VCPU_SREG_CS); switch (mode) { case X86EMUL_MODE_REAL: @@ -2662,6 +3404,7 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) for (;;) { switch (c->b = insn_fetch(u8, 1, c->eip)) { case 0x66: /* operand-size override */ + op_prefix = true; /* switch between 2/4 bytes */ c->op_bytes = def_op_bytes ^ 6; break; @@ -2692,10 +3435,8 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) c->lock_prefix = 1; break; case 0xf2: /* REPNE/REPNZ */ - c->rep_prefix = REPNE_PREFIX; - break; case 0xf3: /* REP/REPE/REPZ */ - c->rep_prefix = REPE_PREFIX; + c->rep_prefix = c->b; break; default: goto done_prefixes; @@ -2722,29 +3463,49 @@ done_prefixes: } c->d = opcode.flags; - if (c->d & Group) { - dual = c->d & GroupDual; - c->modrm = insn_fetch(u8, 1, c->eip); - --c->eip; - - if (c->d & GroupDual) { - g_mod012 = opcode.u.gdual->mod012; - g_mod3 = opcode.u.gdual->mod3; - } else - g_mod012 = g_mod3 = opcode.u.group; - - c->d &= ~(Group | GroupDual); - - goffset = (c->modrm >> 3) & 7; + while (c->d & GroupMask) { + switch (c->d & GroupMask) { + case Group: + c->modrm = insn_fetch(u8, 1, c->eip); + --c->eip; + goffset = (c->modrm >> 3) & 7; + opcode = opcode.u.group[goffset]; + break; + case GroupDual: + c->modrm = insn_fetch(u8, 1, c->eip); + --c->eip; + goffset = (c->modrm >> 3) & 7; + if ((c->modrm >> 6) == 3) + opcode = opcode.u.gdual->mod3[goffset]; + else + opcode = opcode.u.gdual->mod012[goffset]; + break; + case RMExt: + goffset = c->modrm & 7; + opcode = opcode.u.group[goffset]; + break; + case Prefix: + if (c->rep_prefix && op_prefix) + return X86EMUL_UNHANDLEABLE; + simd_prefix = op_prefix ? 0x66 : c->rep_prefix; + switch (simd_prefix) { + case 0x00: opcode = opcode.u.gprefix->pfx_no; break; + case 0x66: opcode = opcode.u.gprefix->pfx_66; break; + case 0xf2: opcode = opcode.u.gprefix->pfx_f2; break; + case 0xf3: opcode = opcode.u.gprefix->pfx_f3; break; + } + break; + default: + return X86EMUL_UNHANDLEABLE; + } - if ((c->modrm >> 6) == 3) - opcode = g_mod3[goffset]; - else - opcode = g_mod012[goffset]; + c->d &= ~GroupMask; c->d |= opcode.flags; } c->execute = opcode.u.execute; + c->check_perm = opcode.check_perm; + c->intercept = opcode.intercept; /* Unrecognised? */ if (c->d == 0 || (c->d & Undefined)) @@ -2763,6 +3524,9 @@ done_prefixes: c->op_bytes = 4; } + if (c->d & Sse) + c->op_bytes = 16; + /* ModRM and SIB bytes. */ if (c->d & ModRM) { rc = decode_modrm(ctxt, ops, &memop); @@ -2776,7 +3540,7 @@ done_prefixes: if (!c->has_seg_override) set_seg_override(c, VCPU_SREG_DS); - memop.addr.mem.seg = seg_override(ctxt, ops, c); + memop.addr.mem.seg = seg_override(ctxt, c); if (memop.type == OP_MEM && c->ad_bytes != 8) memop.addr.mem.ea = (u32)memop.addr.mem.ea; @@ -2792,7 +3556,7 @@ done_prefixes: case SrcNone: break; case SrcReg: - decode_register_operand(&c->src, c, 0); + decode_register_operand(ctxt, &c->src, c, 0); break; case SrcMem16: memop.bytes = 2; @@ -2836,7 +3600,7 @@ done_prefixes: c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; c->src.addr.mem.ea = register_address(c, c->regs[VCPU_REGS_RSI]); - c->src.addr.mem.seg = seg_override(ctxt, ops, c), + c->src.addr.mem.seg = seg_override(ctxt, c); c->src.val = 0; break; case SrcImmFAddr: @@ -2883,7 +3647,7 @@ done_prefixes: /* Decode and fetch the destination operand: register or memory. */ switch (c->d & DstMask) { case DstReg: - decode_register_operand(&c->dst, c, + decode_register_operand(ctxt, &c->dst, c, c->twobyte && (c->b == 0xb6 || c->b == 0xb7)); break; case DstImmUByte: @@ -2926,7 +3690,7 @@ done_prefixes: } done: - return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0; + return (rc == X86EMUL_UNHANDLEABLE) ? EMULATION_FAILED : EMULATION_OK; } static bool string_insn_completed(struct x86_emulate_ctxt *ctxt) @@ -2979,12 +3743,51 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt) goto done; } + if ((c->d & Sse) + && ((ops->get_cr(ctxt, 0) & X86_CR0_EM) + || !(ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR))) { + rc = emulate_ud(ctxt); + goto done; + } + + if ((c->d & Sse) && (ops->get_cr(ctxt, 0) & X86_CR0_TS)) { + rc = emulate_nm(ctxt); + goto done; + } + + if (unlikely(ctxt->guest_mode) && c->intercept) { + rc = emulator_check_intercept(ctxt, c->intercept, + X86_ICPT_PRE_EXCEPT); + if (rc != X86EMUL_CONTINUE) + goto done; + } + /* Privileged instruction can be executed only in CPL=0 */ - if ((c->d & Priv) && ops->cpl(ctxt->vcpu)) { + if ((c->d & Priv) && ops->cpl(ctxt)) { rc = emulate_gp(ctxt, 0); goto done; } + /* Instruction can only be executed in protected mode */ + if ((c->d & Prot) && !(ctxt->mode & X86EMUL_MODE_PROT)) { + rc = emulate_ud(ctxt); + goto done; + } + + /* Do instruction specific permission checks */ + if (c->check_perm) { + rc = c->check_perm(ctxt); + if (rc != X86EMUL_CONTINUE) + goto done; + } + + if (unlikely(ctxt->guest_mode) && c->intercept) { + rc = emulator_check_intercept(ctxt, c->intercept, + X86_ICPT_POST_EXCEPT); + if (rc != X86EMUL_CONTINUE) + goto done; + } + if (c->rep_prefix && (c->d & String)) { /* All REP prefixes have the same first termination condition */ if (address_mask(c, c->regs[VCPU_REGS_RCX]) == 0) { @@ -2994,16 +3797,16 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt) } if ((c->src.type == OP_MEM) && !(c->d & NoAccess)) { - rc = read_emulated(ctxt, ops, linear(ctxt, c->src.addr.mem), - c->src.valptr, c->src.bytes); + rc = segmented_read(ctxt, c->src.addr.mem, + c->src.valptr, c->src.bytes); if (rc != X86EMUL_CONTINUE) goto done; c->src.orig_val64 = c->src.val64; } if (c->src2.type == OP_MEM) { - rc = read_emulated(ctxt, ops, linear(ctxt, c->src2.addr.mem), - &c->src2.val, c->src2.bytes); + rc = segmented_read(ctxt, c->src2.addr.mem, + &c->src2.val, c->src2.bytes); if (rc != X86EMUL_CONTINUE) goto done; } @@ -3014,7 +3817,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt) if ((c->dst.type == OP_MEM) && !(c->d & Mov)) { /* optimisation - avoid slow emulated read if Mov */ - rc = read_emulated(ctxt, ops, linear(ctxt, c->dst.addr.mem), + rc = segmented_read(ctxt, c->dst.addr.mem, &c->dst.val, c->dst.bytes); if (rc != X86EMUL_CONTINUE) goto done; @@ -3023,6 +3826,13 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt) special_insn: + if (unlikely(ctxt->guest_mode) && c->intercept) { + rc = emulator_check_intercept(ctxt, c->intercept, + X86_ICPT_POST_MEMACCESS); + if (rc != X86EMUL_CONTINUE) + goto done; + } + if (c->execute) { rc = c->execute(ctxt); if (rc != X86EMUL_CONTINUE) @@ -3034,75 +3844,33 @@ special_insn: goto twobyte_insn; switch (c->b) { - case 0x00 ... 0x05: - add: /* add */ - emulate_2op_SrcV("add", c->src, c->dst, ctxt->eflags); - break; case 0x06: /* push es */ - emulate_push_sreg(ctxt, ops, VCPU_SREG_ES); + rc = emulate_push_sreg(ctxt, ops, VCPU_SREG_ES); break; case 0x07: /* pop es */ rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_ES); break; - case 0x08 ... 0x0d: - or: /* or */ - emulate_2op_SrcV("or", c->src, c->dst, ctxt->eflags); - break; case 0x0e: /* push cs */ - emulate_push_sreg(ctxt, ops, VCPU_SREG_CS); - break; - case 0x10 ... 0x15: - adc: /* adc */ - emulate_2op_SrcV("adc", c->src, c->dst, ctxt->eflags); + rc = emulate_push_sreg(ctxt, ops, VCPU_SREG_CS); break; case 0x16: /* push ss */ - emulate_push_sreg(ctxt, ops, VCPU_SREG_SS); + rc = emulate_push_sreg(ctxt, ops, VCPU_SREG_SS); break; case 0x17: /* pop ss */ rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_SS); break; - case 0x18 ... 0x1d: - sbb: /* sbb */ - emulate_2op_SrcV("sbb", c->src, c->dst, ctxt->eflags); - break; case 0x1e: /* push ds */ - emulate_push_sreg(ctxt, ops, VCPU_SREG_DS); + rc = emulate_push_sreg(ctxt, ops, VCPU_SREG_DS); break; case 0x1f: /* pop ds */ rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_DS); break; - case 0x20 ... 0x25: - and: /* and */ - emulate_2op_SrcV("and", c->src, c->dst, ctxt->eflags); - break; - case 0x28 ... 0x2d: - sub: /* sub */ - emulate_2op_SrcV("sub", c->src, c->dst, ctxt->eflags); - break; - case 0x30 ... 0x35: - xor: /* xor */ - emulate_2op_SrcV("xor", c->src, c->dst, ctxt->eflags); - break; - case 0x38 ... 0x3d: - cmp: /* cmp */ - emulate_2op_SrcV("cmp", c->src, c->dst, ctxt->eflags); - break; case 0x40 ... 0x47: /* inc r16/r32 */ emulate_1op("inc", c->dst, ctxt->eflags); break; case 0x48 ... 0x4f: /* dec r16/r32 */ emulate_1op("dec", c->dst, ctxt->eflags); break; - case 0x58 ... 0x5f: /* pop reg */ - pop_instruction: - rc = emulate_pop(ctxt, ops, &c->dst.val, c->op_bytes); - break; - case 0x60: /* pusha */ - rc = emulate_pusha(ctxt, ops); - break; - case 0x61: /* popa */ - rc = emulate_popa(ctxt, ops); - break; case 0x63: /* movsxd */ if (ctxt->mode != X86EMUL_MODE_PROT64) goto cannot_emulate; @@ -3121,26 +3889,6 @@ special_insn: if (test_cc(c->b, ctxt->eflags)) jmp_rel(c, c->src.val); break; - case 0x80 ... 0x83: /* Grp1 */ - switch (c->modrm_reg) { - case 0: - goto add; - case 1: - goto or; - case 2: - goto adc; - case 3: - goto sbb; - case 4: - goto and; - case 5: - goto sub; - case 6: - goto xor; - case 7: - goto cmp; - } - break; case 0x84 ... 0x85: test: emulate_2op_SrcV("test", c->src, c->dst, ctxt->eflags); @@ -3162,7 +3910,7 @@ special_insn: rc = emulate_ud(ctxt); goto done; } - c->dst.val = ops->get_segment_selector(c->modrm_reg, ctxt->vcpu); + c->dst.val = get_segment_selector(ctxt, c->modrm_reg); break; case 0x8d: /* lea r16/r32, m */ c->dst.val = c->src.addr.mem.ea; @@ -3187,7 +3935,7 @@ special_insn: break; } case 0x8f: /* pop (sole member of Grp1a) */ - rc = emulate_grp1a(ctxt, ops); + rc = em_grp1a(ctxt); break; case 0x90 ... 0x97: /* nop / xchg reg, rax */ if (c->dst.addr.reg == &c->regs[VCPU_REGS_RAX]) @@ -3200,31 +3948,17 @@ special_insn: case 8: c->dst.val = (s32)c->dst.val; break; } break; - case 0x9c: /* pushf */ - c->src.val = (unsigned long) ctxt->eflags; - emulate_push(ctxt, ops); - break; - case 0x9d: /* popf */ - c->dst.type = OP_REG; - c->dst.addr.reg = &ctxt->eflags; - c->dst.bytes = c->op_bytes; - rc = emulate_popf(ctxt, ops, &c->dst.val, c->op_bytes); - break; - case 0xa6 ... 0xa7: /* cmps */ - c->dst.type = OP_NONE; /* Disable writeback. */ - goto cmp; case 0xa8 ... 0xa9: /* test ax, imm */ goto test; - case 0xae ... 0xaf: /* scas */ - goto cmp; case 0xc0 ... 0xc1: - emulate_grp2(ctxt); + rc = em_grp2(ctxt); break; case 0xc3: /* ret */ c->dst.type = OP_REG; c->dst.addr.reg = &c->eip; c->dst.bytes = c->op_bytes; - goto pop_instruction; + rc = em_pop(ctxt); + break; case 0xc4: /* les */ rc = emulate_load_segment(ctxt, ops, VCPU_SREG_ES); break; @@ -3252,11 +3986,11 @@ special_insn: rc = emulate_iret(ctxt, ops); break; case 0xd0 ... 0xd1: /* Grp2 */ - emulate_grp2(ctxt); + rc = em_grp2(ctxt); break; case 0xd2 ... 0xd3: /* Grp2 */ c->src.val = c->regs[VCPU_REGS_RCX]; - emulate_grp2(ctxt); + rc = em_grp2(ctxt); break; case 0xe0 ... 0xe2: /* loop/loopz/loopnz */ register_address_increment(c, &c->regs[VCPU_REGS_RCX], -1); @@ -3278,23 +4012,14 @@ special_insn: long int rel = c->src.val; c->src.val = (unsigned long) c->eip; jmp_rel(c, rel); - emulate_push(ctxt, ops); + rc = em_push(ctxt); break; } case 0xe9: /* jmp rel */ goto jmp; - case 0xea: { /* jmp far */ - unsigned short sel; - jump_far: - memcpy(&sel, c->src.valptr + c->op_bytes, 2); - - if (load_segment_descriptor(ctxt, ops, sel, VCPU_SREG_CS)) - goto done; - - c->eip = 0; - memcpy(&c->eip, c->src.valptr, c->op_bytes); + case 0xea: /* jmp far */ + rc = em_jmp_far(ctxt); break; - } case 0xeb: jmp: /* jmp rel short */ jmp_rel(c, c->src.val); @@ -3304,11 +4029,6 @@ special_insn: case 0xed: /* in (e/r)ax,dx */ c->src.val = c->regs[VCPU_REGS_RDX]; do_io_in: - c->dst.bytes = min(c->dst.bytes, 4u); - if (!emulator_io_permited(ctxt, ops, c->src.val, c->dst.bytes)) { - rc = emulate_gp(ctxt, 0); - goto done; - } if (!pio_in_emulated(ctxt, ops, c->dst.bytes, c->src.val, &c->dst.val)) goto done; /* IO is needed */ @@ -3317,25 +4037,19 @@ special_insn: case 0xef: /* out dx,(e/r)ax */ c->dst.val = c->regs[VCPU_REGS_RDX]; do_io_out: - c->src.bytes = min(c->src.bytes, 4u); - if (!emulator_io_permited(ctxt, ops, c->dst.val, - c->src.bytes)) { - rc = emulate_gp(ctxt, 0); - goto done; - } - ops->pio_out_emulated(c->src.bytes, c->dst.val, - &c->src.val, 1, ctxt->vcpu); + ops->pio_out_emulated(ctxt, c->src.bytes, c->dst.val, + &c->src.val, 1); c->dst.type = OP_NONE; /* Disable writeback. */ break; case 0xf4: /* hlt */ - ctxt->vcpu->arch.halt_request = 1; + ctxt->ops->halt(ctxt); break; case 0xf5: /* cmc */ /* complement carry flag from eflags reg */ ctxt->eflags ^= EFLG_CF; break; case 0xf6 ... 0xf7: /* Grp3 */ - rc = emulate_grp3(ctxt, ops); + rc = em_grp3(ctxt); break; case 0xf8: /* clc */ ctxt->eflags &= ~EFLG_CF; @@ -3366,13 +4080,11 @@ special_insn: ctxt->eflags |= EFLG_DF; break; case 0xfe: /* Grp4 */ - grp45: - rc = emulate_grp45(ctxt, ops); + rc = em_grp45(ctxt); break; case 0xff: /* Grp5 */ - if (c->modrm_reg == 5) - goto jump_far; - goto grp45; + rc = em_grp45(ctxt); + break; default: goto cannot_emulate; } @@ -3381,7 +4093,7 @@ special_insn: goto done; writeback: - rc = writeback(ctxt, ops); + rc = writeback(ctxt); if (rc != X86EMUL_CONTINUE) goto done; @@ -3392,7 +4104,7 @@ writeback: c->dst.type = saved_dst_type; if ((c->d & SrcMask) == SrcSI) - string_addr_inc(ctxt, seg_override(ctxt, ops, c), + string_addr_inc(ctxt, seg_override(ctxt, c), VCPU_REGS_RSI, &c->src); if ((c->d & DstMask) == DstDI) @@ -3427,115 +4139,34 @@ writeback: done: if (rc == X86EMUL_PROPAGATE_FAULT) ctxt->have_exception = true; + if (rc == X86EMUL_INTERCEPTED) + return EMULATION_INTERCEPTED; + return (rc == X86EMUL_UNHANDLEABLE) ? EMULATION_FAILED : EMULATION_OK; twobyte_insn: switch (c->b) { - case 0x01: /* lgdt, lidt, lmsw */ - switch (c->modrm_reg) { - u16 size; - unsigned long address; - - case 0: /* vmcall */ - if (c->modrm_mod != 3 || c->modrm_rm != 1) - goto cannot_emulate; - - rc = kvm_fix_hypercall(ctxt->vcpu); - if (rc != X86EMUL_CONTINUE) - goto done; - - /* Let the processor re-execute the fixed hypercall */ - c->eip = ctxt->eip; - /* Disable writeback. */ - c->dst.type = OP_NONE; - break; - case 2: /* lgdt */ - rc = read_descriptor(ctxt, ops, c->src.addr.mem, - &size, &address, c->op_bytes); - if (rc != X86EMUL_CONTINUE) - goto done; - realmode_lgdt(ctxt->vcpu, size, address); - /* Disable writeback. */ - c->dst.type = OP_NONE; - break; - case 3: /* lidt/vmmcall */ - if (c->modrm_mod == 3) { - switch (c->modrm_rm) { - case 1: - rc = kvm_fix_hypercall(ctxt->vcpu); - break; - default: - goto cannot_emulate; - } - } else { - rc = read_descriptor(ctxt, ops, c->src.addr.mem, - &size, &address, - c->op_bytes); - if (rc != X86EMUL_CONTINUE) - goto done; - realmode_lidt(ctxt->vcpu, size, address); - } - /* Disable writeback. */ - c->dst.type = OP_NONE; - break; - case 4: /* smsw */ - c->dst.bytes = 2; - c->dst.val = ops->get_cr(0, ctxt->vcpu); - break; - case 6: /* lmsw */ - ops->set_cr(0, (ops->get_cr(0, ctxt->vcpu) & ~0x0eul) | - (c->src.val & 0x0f), ctxt->vcpu); - c->dst.type = OP_NONE; - break; - case 5: /* not defined */ - emulate_ud(ctxt); - rc = X86EMUL_PROPAGATE_FAULT; - goto done; - case 7: /* invlpg*/ - emulate_invlpg(ctxt->vcpu, - linear(ctxt, c->src.addr.mem)); - /* Disable writeback. */ - c->dst.type = OP_NONE; - break; - default: - goto cannot_emulate; - } - break; case 0x05: /* syscall */ rc = emulate_syscall(ctxt, ops); break; case 0x06: - emulate_clts(ctxt->vcpu); + rc = em_clts(ctxt); break; case 0x09: /* wbinvd */ - kvm_emulate_wbinvd(ctxt->vcpu); + (ctxt->ops->wbinvd)(ctxt); break; case 0x08: /* invd */ case 0x0d: /* GrpP (prefetch) */ case 0x18: /* Grp16 (prefetch/nop) */ break; case 0x20: /* mov cr, reg */ - switch (c->modrm_reg) { - case 1: - case 5 ... 7: - case 9 ... 15: - emulate_ud(ctxt); - rc = X86EMUL_PROPAGATE_FAULT; - goto done; - } - c->dst.val = ops->get_cr(c->modrm_reg, ctxt->vcpu); + c->dst.val = ops->get_cr(ctxt, c->modrm_reg); break; case 0x21: /* mov from dr to reg */ - if ((ops->get_cr(4, ctxt->vcpu) & X86_CR4_DE) && - (c->modrm_reg == 4 || c->modrm_reg == 5)) { - emulate_ud(ctxt); - rc = X86EMUL_PROPAGATE_FAULT; - goto done; - } - ops->get_dr(c->modrm_reg, &c->dst.val, ctxt->vcpu); + ops->get_dr(ctxt, c->modrm_reg, &c->dst.val); break; case 0x22: /* mov reg, cr */ - if (ops->set_cr(c->modrm_reg, c->src.val, ctxt->vcpu)) { + if (ops->set_cr(ctxt, c->modrm_reg, c->src.val)) { emulate_gp(ctxt, 0); rc = X86EMUL_PROPAGATE_FAULT; goto done; @@ -3543,16 +4174,9 @@ twobyte_insn: c->dst.type = OP_NONE; break; case 0x23: /* mov from reg to dr */ - if ((ops->get_cr(4, ctxt->vcpu) & X86_CR4_DE) && - (c->modrm_reg == 4 || c->modrm_reg == 5)) { - emulate_ud(ctxt); - rc = X86EMUL_PROPAGATE_FAULT; - goto done; - } - - if (ops->set_dr(c->modrm_reg, c->src.val & + if (ops->set_dr(ctxt, c->modrm_reg, c->src.val & ((ctxt->mode == X86EMUL_MODE_PROT64) ? - ~0ULL : ~0U), ctxt->vcpu) < 0) { + ~0ULL : ~0U)) < 0) { /* #UD condition is already handled by the code above */ emulate_gp(ctxt, 0); rc = X86EMUL_PROPAGATE_FAULT; @@ -3565,7 +4189,7 @@ twobyte_insn: /* wrmsr */ msr_data = (u32)c->regs[VCPU_REGS_RAX] | ((u64)c->regs[VCPU_REGS_RDX] << 32); - if (ops->set_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], msr_data)) { + if (ops->set_msr(ctxt, c->regs[VCPU_REGS_RCX], msr_data)) { emulate_gp(ctxt, 0); rc = X86EMUL_PROPAGATE_FAULT; goto done; @@ -3574,7 +4198,7 @@ twobyte_insn: break; case 0x32: /* rdmsr */ - if (ops->get_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], &msr_data)) { + if (ops->get_msr(ctxt, c->regs[VCPU_REGS_RCX], &msr_data)) { emulate_gp(ctxt, 0); rc = X86EMUL_PROPAGATE_FAULT; goto done; @@ -3603,7 +4227,7 @@ twobyte_insn: c->dst.val = test_cc(c->b, ctxt->eflags); break; case 0xa0: /* push fs */ - emulate_push_sreg(ctxt, ops, VCPU_SREG_FS); + rc = emulate_push_sreg(ctxt, ops, VCPU_SREG_FS); break; case 0xa1: /* pop fs */ rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_FS); @@ -3620,7 +4244,7 @@ twobyte_insn: emulate_2op_cl("shld", c->src2, c->src, c->dst, ctxt->eflags); break; case 0xa8: /* push gs */ - emulate_push_sreg(ctxt, ops, VCPU_SREG_GS); + rc = emulate_push_sreg(ctxt, ops, VCPU_SREG_GS); break; case 0xa9: /* pop gs */ rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_GS); @@ -3727,7 +4351,7 @@ twobyte_insn: (u64) c->src.val; break; case 0xc7: /* Grp9 (cmpxchg8b) */ - rc = emulate_grp9(ctxt, ops); + rc = em_grp9(ctxt); break; default: goto cannot_emulate; @@ -3739,5 +4363,5 @@ twobyte_insn: goto writeback; cannot_emulate: - return -1; + return EMULATION_FAILED; } diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h index 46d08ca0b48f..51a97426e791 100644 --- a/arch/x86/kvm/i8254.h +++ b/arch/x86/kvm/i8254.h @@ -33,7 +33,6 @@ struct kvm_kpit_state { }; struct kvm_pit { - unsigned long base_addresss; struct kvm_io_device dev; struct kvm_io_device speaker_dev; struct kvm *kvm; @@ -51,7 +50,6 @@ struct kvm_pit { #define KVM_MAX_PIT_INTR_INTERVAL HZ / 100 #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, int hpet_legacy_start); struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags); void kvm_free_pit(struct kvm *kvm); diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index ba910d149410..53e2d084bffb 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -75,7 +75,6 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm); void kvm_destroy_pic(struct kvm *kvm); int kvm_pic_read_irq(struct kvm *kvm); void kvm_pic_update_irq(struct kvm_pic *s); -void kvm_pic_clear_isr_ack(struct kvm *kvm); static inline struct kvm_pic *pic_irqchip(struct kvm *kvm) { @@ -100,7 +99,6 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu); void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu); void __kvm_migrate_timers(struct kvm_vcpu *vcpu); -int pit_has_pending_timer(struct kvm_vcpu *vcpu); int apic_has_pending_timer(struct kvm_vcpu *vcpu); #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 22fae7593ee7..28418054b880 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1206,7 +1206,7 @@ static void nonpaging_invlpg(struct kvm_vcpu *vcpu, gva_t gva) static void nonpaging_update_pte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, - const void *pte, unsigned long mmu_seq) + const void *pte) { WARN_ON(1); } @@ -3163,9 +3163,8 @@ static void mmu_pte_write_zap_pte(struct kvm_vcpu *vcpu, } static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *sp, - u64 *spte, - const void *new, unsigned long mmu_seq) + struct kvm_mmu_page *sp, u64 *spte, + const void *new) { if (sp->role.level != PT_PAGE_TABLE_LEVEL) { ++vcpu->kvm->stat.mmu_pde_zapped; @@ -3173,7 +3172,7 @@ static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu, } ++vcpu->kvm->stat.mmu_pte_updated; - vcpu->arch.mmu.update_pte(vcpu, sp, spte, new, mmu_seq); + vcpu->arch.mmu.update_pte(vcpu, sp, spte, new); } static bool need_remote_flush(u64 old, u64 new) @@ -3229,7 +3228,6 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_mmu_page *sp; struct hlist_node *node; LIST_HEAD(invalid_list); - unsigned long mmu_seq; u64 entry, gentry, *spte; unsigned pte_size, page_offset, misaligned, quadrant, offset; int level, npte, invlpg_counter, r, flooded = 0; @@ -3271,9 +3269,6 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, break; } - mmu_seq = vcpu->kvm->mmu_notifier_seq; - smp_rmb(); - spin_lock(&vcpu->kvm->mmu_lock); if (atomic_read(&vcpu->kvm->arch.invlpg_counter) != invlpg_counter) gentry = 0; @@ -3345,8 +3340,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, if (gentry && !((sp->role.word ^ vcpu->arch.mmu.base_role.word) & mask.word)) - mmu_pte_write_new_pte(vcpu, sp, spte, &gentry, - mmu_seq); + mmu_pte_write_new_pte(vcpu, sp, spte, &gentry); if (!remote_flush && need_remote_flush(entry, *spte)) remote_flush = true; ++spte; diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index c6397795d865..6c4dc010c4cb 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -78,15 +78,19 @@ static gfn_t gpte_to_gfn_lvl(pt_element_t gpte, int lvl) return (gpte & PT_LVL_ADDR_MASK(lvl)) >> PAGE_SHIFT; } -static bool FNAME(cmpxchg_gpte)(struct kvm *kvm, - gfn_t table_gfn, unsigned index, - pt_element_t orig_pte, pt_element_t new_pte) +static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + pt_element_t __user *ptep_user, unsigned index, + pt_element_t orig_pte, pt_element_t new_pte) { + int npages; pt_element_t ret; pt_element_t *table; struct page *page; - page = gfn_to_page(kvm, table_gfn); + npages = get_user_pages_fast((unsigned long)ptep_user, 1, 1, &page); + /* Check if the user is doing something meaningless. */ + if (unlikely(npages != 1)) + return -EFAULT; table = kmap_atomic(page, KM_USER0); ret = CMPXCHG(&table[index], orig_pte, new_pte); @@ -117,6 +121,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, gva_t addr, u32 access) { pt_element_t pte; + pt_element_t __user *ptep_user; gfn_t table_gfn; unsigned index, pt_access, uninitialized_var(pte_access); gpa_t pte_gpa; @@ -152,6 +157,9 @@ walk: pt_access = ACC_ALL; for (;;) { + gfn_t real_gfn; + unsigned long host_addr; + index = PT_INDEX(addr, walker->level); table_gfn = gpte_to_gfn(pte); @@ -160,43 +168,64 @@ walk: walker->table_gfn[walker->level - 1] = table_gfn; walker->pte_gpa[walker->level - 1] = pte_gpa; - if (kvm_read_guest_page_mmu(vcpu, mmu, table_gfn, &pte, - offset, sizeof(pte), - PFERR_USER_MASK|PFERR_WRITE_MASK)) { + real_gfn = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn), + PFERR_USER_MASK|PFERR_WRITE_MASK); + if (unlikely(real_gfn == UNMAPPED_GVA)) { + present = false; + break; + } + real_gfn = gpa_to_gfn(real_gfn); + + host_addr = gfn_to_hva(vcpu->kvm, real_gfn); + if (unlikely(kvm_is_error_hva(host_addr))) { + present = false; + break; + } + + ptep_user = (pt_element_t __user *)((void *)host_addr + offset); + if (unlikely(__copy_from_user(&pte, ptep_user, sizeof(pte)))) { present = false; break; } trace_kvm_mmu_paging_element(pte, walker->level); - if (!is_present_gpte(pte)) { + if (unlikely(!is_present_gpte(pte))) { present = false; break; } - if (is_rsvd_bits_set(&vcpu->arch.mmu, pte, walker->level)) { + if (unlikely(is_rsvd_bits_set(&vcpu->arch.mmu, pte, + walker->level))) { rsvd_fault = true; break; } - if (write_fault && !is_writable_pte(pte)) - if (user_fault || is_write_protection(vcpu)) - eperm = true; + if (unlikely(write_fault && !is_writable_pte(pte) + && (user_fault || is_write_protection(vcpu)))) + eperm = true; - if (user_fault && !(pte & PT_USER_MASK)) + if (unlikely(user_fault && !(pte & PT_USER_MASK))) eperm = true; #if PTTYPE == 64 - if (fetch_fault && (pte & PT64_NX_MASK)) + if (unlikely(fetch_fault && (pte & PT64_NX_MASK))) eperm = true; #endif - if (!eperm && !rsvd_fault && !(pte & PT_ACCESSED_MASK)) { + if (!eperm && !rsvd_fault + && unlikely(!(pte & PT_ACCESSED_MASK))) { + int ret; trace_kvm_mmu_set_accessed_bit(table_gfn, index, sizeof(pte)); - if (FNAME(cmpxchg_gpte)(vcpu->kvm, table_gfn, - index, pte, pte|PT_ACCESSED_MASK)) + ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index, + pte, pte|PT_ACCESSED_MASK); + if (unlikely(ret < 0)) { + present = false; + break; + } else if (ret) goto walk; + mark_page_dirty(vcpu->kvm, table_gfn); pte |= PT_ACCESSED_MASK; } @@ -241,17 +270,21 @@ walk: --walker->level; } - if (!present || eperm || rsvd_fault) + if (unlikely(!present || eperm || rsvd_fault)) goto error; - if (write_fault && !is_dirty_gpte(pte)) { - bool ret; + if (write_fault && unlikely(!is_dirty_gpte(pte))) { + int ret; trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte)); - ret = FNAME(cmpxchg_gpte)(vcpu->kvm, table_gfn, index, pte, - pte|PT_DIRTY_MASK); - if (ret) + ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index, + pte, pte|PT_DIRTY_MASK); + if (unlikely(ret < 0)) { + present = false; + goto error; + } else if (ret) goto walk; + mark_page_dirty(vcpu->kvm, table_gfn); pte |= PT_DIRTY_MASK; walker->ptes[walker->level - 1] = pte; @@ -325,7 +358,7 @@ no_present: } static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - u64 *spte, const void *pte, unsigned long mmu_seq) + u64 *spte, const void *pte) { pt_element_t gpte; unsigned pte_access; @@ -342,8 +375,6 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, kvm_release_pfn_clean(pfn); return; } - if (mmu_notifier_retry(vcpu, mmu_seq)) - return; /* * we call mmu_set_spte() with host_writable = true because that diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 6bb15d583e47..506e4fe23adc 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -63,6 +63,10 @@ MODULE_LICENSE("GPL"); #define DEBUGCTL_RESERVED_BITS (~(0x3fULL)) +#define TSC_RATIO_RSVD 0xffffff0000000000ULL +#define TSC_RATIO_MIN 0x0000000000000001ULL +#define TSC_RATIO_MAX 0x000000ffffffffffULL + static bool erratum_383_found __read_mostly; static const u32 host_save_user_msrs[] = { @@ -93,14 +97,6 @@ struct nested_state { /* A VMEXIT is required but not yet emulated */ bool exit_required; - /* - * If we vmexit during an instruction emulation we need this to restore - * the l1 guest rip after the emulation - */ - unsigned long vmexit_rip; - unsigned long vmexit_rsp; - unsigned long vmexit_rax; - /* cache for intercepts of the guest */ u32 intercept_cr; u32 intercept_dr; @@ -144,8 +140,13 @@ struct vcpu_svm { unsigned int3_injected; unsigned long int3_rip; u32 apf_reason; + + u64 tsc_ratio; }; +static DEFINE_PER_CPU(u64, current_tsc_ratio); +#define TSC_RATIO_DEFAULT 0x0100000000ULL + #define MSR_INVALID 0xffffffffU static struct svm_direct_access_msrs { @@ -190,6 +191,7 @@ static int nested_svm_intercept(struct vcpu_svm *svm); static int nested_svm_vmexit(struct vcpu_svm *svm); static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code); +static u64 __scale_tsc(u64 ratio, u64 tsc); enum { VMCB_INTERCEPTS, /* Intercept vectors, TSC offset, @@ -376,7 +378,6 @@ struct svm_cpu_data { }; static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data); -static uint32_t svm_features; struct svm_init_data { int cpu; @@ -569,6 +570,10 @@ static int has_svm(void) static void svm_hardware_disable(void *garbage) { + /* Make sure we clean up behind us */ + if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) + wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT); + cpu_svm_disable(); } @@ -610,6 +615,11 @@ static int svm_hardware_enable(void *garbage) wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(sd->save_area) << PAGE_SHIFT); + if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) { + wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT); + __get_cpu_var(current_tsc_ratio) = TSC_RATIO_DEFAULT; + } + svm_init_erratum_383(); return 0; @@ -791,6 +801,23 @@ static __init int svm_hardware_setup(void) if (boot_cpu_has(X86_FEATURE_FXSR_OPT)) kvm_enable_efer_bits(EFER_FFXSR); + if (boot_cpu_has(X86_FEATURE_TSCRATEMSR)) { + u64 max; + + kvm_has_tsc_control = true; + + /* + * Make sure the user can only configure tsc_khz values that + * fit into a signed integer. + * A min value is not calculated needed because it will always + * be 1 on all machines and a value of 0 is used to disable + * tsc-scaling for the vcpu. + */ + max = min(0x7fffffffULL, __scale_tsc(tsc_khz, TSC_RATIO_MAX)); + + kvm_max_guest_tsc_khz = max; + } + if (nested) { printk(KERN_INFO "kvm: Nested Virtualization enabled\n"); kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE); @@ -802,8 +829,6 @@ static __init int svm_hardware_setup(void) goto err; } - svm_features = cpuid_edx(SVM_CPUID_FUNC); - if (!boot_cpu_has(X86_FEATURE_NPT)) npt_enabled = false; @@ -854,6 +879,64 @@ static void init_sys_seg(struct vmcb_seg *seg, uint32_t type) seg->base = 0; } +static u64 __scale_tsc(u64 ratio, u64 tsc) +{ + u64 mult, frac, _tsc; + + mult = ratio >> 32; + frac = ratio & ((1ULL << 32) - 1); + + _tsc = tsc; + _tsc *= mult; + _tsc += (tsc >> 32) * frac; + _tsc += ((tsc & ((1ULL << 32) - 1)) * frac) >> 32; + + return _tsc; +} + +static u64 svm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u64 _tsc = tsc; + + if (svm->tsc_ratio != TSC_RATIO_DEFAULT) + _tsc = __scale_tsc(svm->tsc_ratio, tsc); + + return _tsc; +} + +static void svm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u64 ratio; + u64 khz; + + /* TSC scaling supported? */ + if (!boot_cpu_has(X86_FEATURE_TSCRATEMSR)) + return; + + /* TSC-Scaling disabled or guest TSC same frequency as host TSC? */ + if (user_tsc_khz == 0) { + vcpu->arch.virtual_tsc_khz = 0; + svm->tsc_ratio = TSC_RATIO_DEFAULT; + return; + } + + khz = user_tsc_khz; + + /* TSC scaling required - calculate ratio */ + ratio = khz << 32; + do_div(ratio, tsc_khz); + + if (ratio == 0 || ratio & TSC_RATIO_RSVD) { + WARN_ONCE(1, "Invalid TSC ratio - virtual-tsc-khz=%u\n", + user_tsc_khz); + return; + } + vcpu->arch.virtual_tsc_khz = user_tsc_khz; + svm->tsc_ratio = ratio; +} + static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) { struct vcpu_svm *svm = to_svm(vcpu); @@ -880,6 +963,15 @@ static void svm_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment) mark_dirty(svm->vmcb, VMCB_INTERCEPTS); } +static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) +{ + u64 tsc; + + tsc = svm_scale_tsc(vcpu, native_read_tsc()); + + return target_tsc - tsc; +} + static void init_vmcb(struct vcpu_svm *svm) { struct vmcb_control_area *control = &svm->vmcb->control; @@ -975,7 +1067,7 @@ static void init_vmcb(struct vcpu_svm *svm) svm_set_efer(&svm->vcpu, 0); save->dr6 = 0xffff0ff0; save->dr7 = 0x400; - save->rflags = 2; + kvm_set_rflags(&svm->vcpu, 2); save->rip = 0x0000fff0; svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip; @@ -1048,6 +1140,8 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) goto out; } + svm->tsc_ratio = TSC_RATIO_DEFAULT; + err = kvm_vcpu_init(&svm->vcpu, kvm, id); if (err) goto free_svm; @@ -1141,6 +1235,12 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); + + if (static_cpu_has(X86_FEATURE_TSCRATEMSR) && + svm->tsc_ratio != __get_cpu_var(current_tsc_ratio)) { + __get_cpu_var(current_tsc_ratio) = svm->tsc_ratio; + wrmsrl(MSR_AMD64_TSC_RATIO, svm->tsc_ratio); + } } static void svm_vcpu_put(struct kvm_vcpu *vcpu) @@ -1365,31 +1465,6 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { struct vcpu_svm *svm = to_svm(vcpu); - if (is_guest_mode(vcpu)) { - /* - * We are here because we run in nested mode, the host kvm - * intercepts cr0 writes but the l1 hypervisor does not. - * But the L1 hypervisor may intercept selective cr0 writes. - * This needs to be checked here. - */ - unsigned long old, new; - - /* Remove bits that would trigger a real cr0 write intercept */ - old = vcpu->arch.cr0 & SVM_CR0_SELECTIVE_MASK; - new = cr0 & SVM_CR0_SELECTIVE_MASK; - - if (old == new) { - /* cr0 write with ts and mp unchanged */ - svm->vmcb->control.exit_code = SVM_EXIT_CR0_SEL_WRITE; - if (nested_svm_exit_handled(svm) == NESTED_EXIT_DONE) { - svm->nested.vmexit_rip = kvm_rip_read(vcpu); - svm->nested.vmexit_rsp = kvm_register_read(vcpu, VCPU_REGS_RSP); - svm->nested.vmexit_rax = kvm_register_read(vcpu, VCPU_REGS_RAX); - return; - } - } - } - #ifdef CONFIG_X86_64 if (vcpu->arch.efer & EFER_LME) { if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { @@ -2127,7 +2202,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) nested_vmcb->save.cr3 = kvm_read_cr3(&svm->vcpu); nested_vmcb->save.cr2 = vmcb->save.cr2; nested_vmcb->save.cr4 = svm->vcpu.arch.cr4; - nested_vmcb->save.rflags = vmcb->save.rflags; + nested_vmcb->save.rflags = kvm_get_rflags(&svm->vcpu); nested_vmcb->save.rip = vmcb->save.rip; nested_vmcb->save.rsp = vmcb->save.rsp; nested_vmcb->save.rax = vmcb->save.rax; @@ -2184,7 +2259,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) svm->vmcb->save.ds = hsave->save.ds; svm->vmcb->save.gdtr = hsave->save.gdtr; svm->vmcb->save.idtr = hsave->save.idtr; - svm->vmcb->save.rflags = hsave->save.rflags; + kvm_set_rflags(&svm->vcpu, hsave->save.rflags); svm_set_efer(&svm->vcpu, hsave->save.efer); svm_set_cr0(&svm->vcpu, hsave->save.cr0 | X86_CR0_PE); svm_set_cr4(&svm->vcpu, hsave->save.cr4); @@ -2312,7 +2387,7 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) hsave->save.efer = svm->vcpu.arch.efer; hsave->save.cr0 = kvm_read_cr0(&svm->vcpu); hsave->save.cr4 = svm->vcpu.arch.cr4; - hsave->save.rflags = vmcb->save.rflags; + hsave->save.rflags = kvm_get_rflags(&svm->vcpu); hsave->save.rip = kvm_rip_read(&svm->vcpu); hsave->save.rsp = vmcb->save.rsp; hsave->save.rax = vmcb->save.rax; @@ -2323,7 +2398,7 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) copy_vmcb_control_area(hsave, vmcb); - if (svm->vmcb->save.rflags & X86_EFLAGS_IF) + if (kvm_get_rflags(&svm->vcpu) & X86_EFLAGS_IF) svm->vcpu.arch.hflags |= HF_HIF_MASK; else svm->vcpu.arch.hflags &= ~HF_HIF_MASK; @@ -2341,7 +2416,7 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) svm->vmcb->save.ds = nested_vmcb->save.ds; svm->vmcb->save.gdtr = nested_vmcb->save.gdtr; svm->vmcb->save.idtr = nested_vmcb->save.idtr; - svm->vmcb->save.rflags = nested_vmcb->save.rflags; + kvm_set_rflags(&svm->vcpu, nested_vmcb->save.rflags); svm_set_efer(&svm->vcpu, nested_vmcb->save.efer); svm_set_cr0(&svm->vcpu, nested_vmcb->save.cr0); svm_set_cr4(&svm->vcpu, nested_vmcb->save.cr4); @@ -2443,13 +2518,13 @@ static int vmload_interception(struct vcpu_svm *svm) if (nested_svm_check_permissions(svm)) return 1; - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; - skip_emulated_instruction(&svm->vcpu); - nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page); if (!nested_vmcb) return 1; + svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; + skip_emulated_instruction(&svm->vcpu); + nested_svm_vmloadsave(nested_vmcb, svm->vmcb); nested_svm_unmap(page); @@ -2464,13 +2539,13 @@ static int vmsave_interception(struct vcpu_svm *svm) if (nested_svm_check_permissions(svm)) return 1; - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; - skip_emulated_instruction(&svm->vcpu); - nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page); if (!nested_vmcb) return 1; + svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; + skip_emulated_instruction(&svm->vcpu); + nested_svm_vmloadsave(svm->vmcb, nested_vmcb); nested_svm_unmap(page); @@ -2676,6 +2751,29 @@ static int emulate_on_interception(struct vcpu_svm *svm) return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; } +bool check_selective_cr0_intercepted(struct vcpu_svm *svm, unsigned long val) +{ + unsigned long cr0 = svm->vcpu.arch.cr0; + bool ret = false; + u64 intercept; + + intercept = svm->nested.intercept; + + if (!is_guest_mode(&svm->vcpu) || + (!(intercept & (1ULL << INTERCEPT_SELECTIVE_CR0)))) + return false; + + cr0 &= ~SVM_CR0_SELECTIVE_MASK; + val &= ~SVM_CR0_SELECTIVE_MASK; + + if (cr0 ^ val) { + svm->vmcb->control.exit_code = SVM_EXIT_CR0_SEL_WRITE; + ret = (nested_svm_exit_handled(svm) == NESTED_EXIT_DONE); + } + + return ret; +} + #define CR_VALID (1ULL << 63) static int cr_interception(struct vcpu_svm *svm) @@ -2699,7 +2797,11 @@ static int cr_interception(struct vcpu_svm *svm) val = kvm_register_read(&svm->vcpu, reg); switch (cr) { case 0: - err = kvm_set_cr0(&svm->vcpu, val); + if (!check_selective_cr0_intercepted(svm, val)) + err = kvm_set_cr0(&svm->vcpu, val); + else + return 1; + break; case 3: err = kvm_set_cr3(&svm->vcpu, val); @@ -2744,23 +2846,6 @@ static int cr_interception(struct vcpu_svm *svm) return 1; } -static int cr0_write_interception(struct vcpu_svm *svm) -{ - struct kvm_vcpu *vcpu = &svm->vcpu; - int r; - - r = cr_interception(svm); - - if (svm->nested.vmexit_rip) { - kvm_register_write(vcpu, VCPU_REGS_RIP, svm->nested.vmexit_rip); - kvm_register_write(vcpu, VCPU_REGS_RSP, svm->nested.vmexit_rsp); - kvm_register_write(vcpu, VCPU_REGS_RAX, svm->nested.vmexit_rax); - svm->nested.vmexit_rip = 0; - } - - return r; -} - static int dr_interception(struct vcpu_svm *svm) { int reg, dr; @@ -2813,7 +2898,9 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) case MSR_IA32_TSC: { struct vmcb *vmcb = get_host_vmcb(svm); - *data = vmcb->control.tsc_offset + native_read_tsc(); + *data = vmcb->control.tsc_offset + + svm_scale_tsc(vcpu, native_read_tsc()); + break; } case MSR_STAR: @@ -3048,7 +3135,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_READ_CR4] = cr_interception, [SVM_EXIT_READ_CR8] = cr_interception, [SVM_EXIT_CR0_SEL_WRITE] = emulate_on_interception, - [SVM_EXIT_WRITE_CR0] = cr0_write_interception, + [SVM_EXIT_WRITE_CR0] = cr_interception, [SVM_EXIT_WRITE_CR3] = cr_interception, [SVM_EXIT_WRITE_CR4] = cr_interception, [SVM_EXIT_WRITE_CR8] = cr8_write_interception, @@ -3104,97 +3191,109 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_NPF] = pf_interception, }; -void dump_vmcb(struct kvm_vcpu *vcpu) +static void dump_vmcb(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct vmcb_control_area *control = &svm->vmcb->control; struct vmcb_save_area *save = &svm->vmcb->save; pr_err("VMCB Control Area:\n"); - pr_err("cr_read: %04x\n", control->intercept_cr & 0xffff); - pr_err("cr_write: %04x\n", control->intercept_cr >> 16); - pr_err("dr_read: %04x\n", control->intercept_dr & 0xffff); - pr_err("dr_write: %04x\n", control->intercept_dr >> 16); - pr_err("exceptions: %08x\n", control->intercept_exceptions); - pr_err("intercepts: %016llx\n", control->intercept); - pr_err("pause filter count: %d\n", control->pause_filter_count); - pr_err("iopm_base_pa: %016llx\n", control->iopm_base_pa); - pr_err("msrpm_base_pa: %016llx\n", control->msrpm_base_pa); - pr_err("tsc_offset: %016llx\n", control->tsc_offset); - pr_err("asid: %d\n", control->asid); - pr_err("tlb_ctl: %d\n", control->tlb_ctl); - pr_err("int_ctl: %08x\n", control->int_ctl); - pr_err("int_vector: %08x\n", control->int_vector); - pr_err("int_state: %08x\n", control->int_state); - pr_err("exit_code: %08x\n", control->exit_code); - pr_err("exit_info1: %016llx\n", control->exit_info_1); - pr_err("exit_info2: %016llx\n", control->exit_info_2); - pr_err("exit_int_info: %08x\n", control->exit_int_info); - pr_err("exit_int_info_err: %08x\n", control->exit_int_info_err); - pr_err("nested_ctl: %lld\n", control->nested_ctl); - pr_err("nested_cr3: %016llx\n", control->nested_cr3); - pr_err("event_inj: %08x\n", control->event_inj); - pr_err("event_inj_err: %08x\n", control->event_inj_err); - pr_err("lbr_ctl: %lld\n", control->lbr_ctl); - pr_err("next_rip: %016llx\n", control->next_rip); + pr_err("%-20s%04x\n", "cr_read:", control->intercept_cr & 0xffff); + pr_err("%-20s%04x\n", "cr_write:", control->intercept_cr >> 16); + pr_err("%-20s%04x\n", "dr_read:", control->intercept_dr & 0xffff); + pr_err("%-20s%04x\n", "dr_write:", control->intercept_dr >> 16); + pr_err("%-20s%08x\n", "exceptions:", control->intercept_exceptions); + pr_err("%-20s%016llx\n", "intercepts:", control->intercept); + pr_err("%-20s%d\n", "pause filter count:", control->pause_filter_count); + pr_err("%-20s%016llx\n", "iopm_base_pa:", control->iopm_base_pa); + pr_err("%-20s%016llx\n", "msrpm_base_pa:", control->msrpm_base_pa); + pr_err("%-20s%016llx\n", "tsc_offset:", control->tsc_offset); + pr_err("%-20s%d\n", "asid:", control->asid); + pr_err("%-20s%d\n", "tlb_ctl:", control->tlb_ctl); + pr_err("%-20s%08x\n", "int_ctl:", control->int_ctl); + pr_err("%-20s%08x\n", "int_vector:", control->int_vector); + pr_err("%-20s%08x\n", "int_state:", control->int_state); + pr_err("%-20s%08x\n", "exit_code:", control->exit_code); + pr_err("%-20s%016llx\n", "exit_info1:", control->exit_info_1); + pr_err("%-20s%016llx\n", "exit_info2:", control->exit_info_2); + pr_err("%-20s%08x\n", "exit_int_info:", control->exit_int_info); + pr_err("%-20s%08x\n", "exit_int_info_err:", control->exit_int_info_err); + pr_err("%-20s%lld\n", "nested_ctl:", control->nested_ctl); + pr_err("%-20s%016llx\n", "nested_cr3:", control->nested_cr3); + pr_err("%-20s%08x\n", "event_inj:", control->event_inj); + pr_err("%-20s%08x\n", "event_inj_err:", control->event_inj_err); + pr_err("%-20s%lld\n", "lbr_ctl:", control->lbr_ctl); + pr_err("%-20s%016llx\n", "next_rip:", control->next_rip); pr_err("VMCB State Save Area:\n"); - pr_err("es: s: %04x a: %04x l: %08x b: %016llx\n", - save->es.selector, save->es.attrib, - save->es.limit, save->es.base); - pr_err("cs: s: %04x a: %04x l: %08x b: %016llx\n", - save->cs.selector, save->cs.attrib, - save->cs.limit, save->cs.base); - pr_err("ss: s: %04x a: %04x l: %08x b: %016llx\n", - save->ss.selector, save->ss.attrib, - save->ss.limit, save->ss.base); - pr_err("ds: s: %04x a: %04x l: %08x b: %016llx\n", - save->ds.selector, save->ds.attrib, - save->ds.limit, save->ds.base); - pr_err("fs: s: %04x a: %04x l: %08x b: %016llx\n", - save->fs.selector, save->fs.attrib, - save->fs.limit, save->fs.base); - pr_err("gs: s: %04x a: %04x l: %08x b: %016llx\n", - save->gs.selector, save->gs.attrib, - save->gs.limit, save->gs.base); - pr_err("gdtr: s: %04x a: %04x l: %08x b: %016llx\n", - save->gdtr.selector, save->gdtr.attrib, - save->gdtr.limit, save->gdtr.base); - pr_err("ldtr: s: %04x a: %04x l: %08x b: %016llx\n", - save->ldtr.selector, save->ldtr.attrib, - save->ldtr.limit, save->ldtr.base); - pr_err("idtr: s: %04x a: %04x l: %08x b: %016llx\n", - save->idtr.selector, save->idtr.attrib, - save->idtr.limit, save->idtr.base); - pr_err("tr: s: %04x a: %04x l: %08x b: %016llx\n", - save->tr.selector, save->tr.attrib, - save->tr.limit, save->tr.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "es:", + save->es.selector, save->es.attrib, + save->es.limit, save->es.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "cs:", + save->cs.selector, save->cs.attrib, + save->cs.limit, save->cs.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "ss:", + save->ss.selector, save->ss.attrib, + save->ss.limit, save->ss.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "ds:", + save->ds.selector, save->ds.attrib, + save->ds.limit, save->ds.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "fs:", + save->fs.selector, save->fs.attrib, + save->fs.limit, save->fs.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "gs:", + save->gs.selector, save->gs.attrib, + save->gs.limit, save->gs.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "gdtr:", + save->gdtr.selector, save->gdtr.attrib, + save->gdtr.limit, save->gdtr.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "ldtr:", + save->ldtr.selector, save->ldtr.attrib, + save->ldtr.limit, save->ldtr.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "idtr:", + save->idtr.selector, save->idtr.attrib, + save->idtr.limit, save->idtr.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "tr:", + save->tr.selector, save->tr.attrib, + save->tr.limit, save->tr.base); pr_err("cpl: %d efer: %016llx\n", save->cpl, save->efer); - pr_err("cr0: %016llx cr2: %016llx\n", - save->cr0, save->cr2); - pr_err("cr3: %016llx cr4: %016llx\n", - save->cr3, save->cr4); - pr_err("dr6: %016llx dr7: %016llx\n", - save->dr6, save->dr7); - pr_err("rip: %016llx rflags: %016llx\n", - save->rip, save->rflags); - pr_err("rsp: %016llx rax: %016llx\n", - save->rsp, save->rax); - pr_err("star: %016llx lstar: %016llx\n", - save->star, save->lstar); - pr_err("cstar: %016llx sfmask: %016llx\n", - save->cstar, save->sfmask); - pr_err("kernel_gs_base: %016llx sysenter_cs: %016llx\n", - save->kernel_gs_base, save->sysenter_cs); - pr_err("sysenter_esp: %016llx sysenter_eip: %016llx\n", - save->sysenter_esp, save->sysenter_eip); - pr_err("gpat: %016llx dbgctl: %016llx\n", - save->g_pat, save->dbgctl); - pr_err("br_from: %016llx br_to: %016llx\n", - save->br_from, save->br_to); - pr_err("excp_from: %016llx excp_to: %016llx\n", - save->last_excp_from, save->last_excp_to); - + pr_err("%-15s %016llx %-13s %016llx\n", + "cr0:", save->cr0, "cr2:", save->cr2); + pr_err("%-15s %016llx %-13s %016llx\n", + "cr3:", save->cr3, "cr4:", save->cr4); + pr_err("%-15s %016llx %-13s %016llx\n", + "dr6:", save->dr6, "dr7:", save->dr7); + pr_err("%-15s %016llx %-13s %016llx\n", + "rip:", save->rip, "rflags:", save->rflags); + pr_err("%-15s %016llx %-13s %016llx\n", + "rsp:", save->rsp, "rax:", save->rax); + pr_err("%-15s %016llx %-13s %016llx\n", + "star:", save->star, "lstar:", save->lstar); + pr_err("%-15s %016llx %-13s %016llx\n", + "cstar:", save->cstar, "sfmask:", save->sfmask); + pr_err("%-15s %016llx %-13s %016llx\n", + "kernel_gs_base:", save->kernel_gs_base, + "sysenter_cs:", save->sysenter_cs); + pr_err("%-15s %016llx %-13s %016llx\n", + "sysenter_esp:", save->sysenter_esp, + "sysenter_eip:", save->sysenter_eip); + pr_err("%-15s %016llx %-13s %016llx\n", + "gpat:", save->g_pat, "dbgctl:", save->dbgctl); + pr_err("%-15s %016llx %-13s %016llx\n", + "br_from:", save->br_from, "br_to:", save->br_to); + pr_err("%-15s %016llx %-13s %016llx\n", + "excp_from:", save->last_excp_from, + "excp_to:", save->last_excp_to); } static void svm_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2) @@ -3384,7 +3483,7 @@ static int svm_interrupt_allowed(struct kvm_vcpu *vcpu) (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK)) return 0; - ret = !!(vmcb->save.rflags & X86_EFLAGS_IF); + ret = !!(kvm_get_rflags(vcpu) & X86_EFLAGS_IF); if (is_guest_mode(vcpu)) return ret && !(svm->vcpu.arch.hflags & HF_VINTR_MASK); @@ -3871,6 +3970,186 @@ static void svm_fpu_deactivate(struct kvm_vcpu *vcpu) update_cr0_intercept(svm); } +#define PRE_EX(exit) { .exit_code = (exit), \ + .stage = X86_ICPT_PRE_EXCEPT, } +#define POST_EX(exit) { .exit_code = (exit), \ + .stage = X86_ICPT_POST_EXCEPT, } +#define POST_MEM(exit) { .exit_code = (exit), \ + .stage = X86_ICPT_POST_MEMACCESS, } + +static struct __x86_intercept { + u32 exit_code; + enum x86_intercept_stage stage; +} x86_intercept_map[] = { + [x86_intercept_cr_read] = POST_EX(SVM_EXIT_READ_CR0), + [x86_intercept_cr_write] = POST_EX(SVM_EXIT_WRITE_CR0), + [x86_intercept_clts] = POST_EX(SVM_EXIT_WRITE_CR0), + [x86_intercept_lmsw] = POST_EX(SVM_EXIT_WRITE_CR0), + [x86_intercept_smsw] = POST_EX(SVM_EXIT_READ_CR0), + [x86_intercept_dr_read] = POST_EX(SVM_EXIT_READ_DR0), + [x86_intercept_dr_write] = POST_EX(SVM_EXIT_WRITE_DR0), + [x86_intercept_sldt] = POST_EX(SVM_EXIT_LDTR_READ), + [x86_intercept_str] = POST_EX(SVM_EXIT_TR_READ), + [x86_intercept_lldt] = POST_EX(SVM_EXIT_LDTR_WRITE), + [x86_intercept_ltr] = POST_EX(SVM_EXIT_TR_WRITE), + [x86_intercept_sgdt] = POST_EX(SVM_EXIT_GDTR_READ), + [x86_intercept_sidt] = POST_EX(SVM_EXIT_IDTR_READ), + [x86_intercept_lgdt] = POST_EX(SVM_EXIT_GDTR_WRITE), + [x86_intercept_lidt] = POST_EX(SVM_EXIT_IDTR_WRITE), + [x86_intercept_vmrun] = POST_EX(SVM_EXIT_VMRUN), + [x86_intercept_vmmcall] = POST_EX(SVM_EXIT_VMMCALL), + [x86_intercept_vmload] = POST_EX(SVM_EXIT_VMLOAD), + [x86_intercept_vmsave] = POST_EX(SVM_EXIT_VMSAVE), + [x86_intercept_stgi] = POST_EX(SVM_EXIT_STGI), + [x86_intercept_clgi] = POST_EX(SVM_EXIT_CLGI), + [x86_intercept_skinit] = POST_EX(SVM_EXIT_SKINIT), + [x86_intercept_invlpga] = POST_EX(SVM_EXIT_INVLPGA), + [x86_intercept_rdtscp] = POST_EX(SVM_EXIT_RDTSCP), + [x86_intercept_monitor] = POST_MEM(SVM_EXIT_MONITOR), + [x86_intercept_mwait] = POST_EX(SVM_EXIT_MWAIT), + [x86_intercept_invlpg] = POST_EX(SVM_EXIT_INVLPG), + [x86_intercept_invd] = POST_EX(SVM_EXIT_INVD), + [x86_intercept_wbinvd] = POST_EX(SVM_EXIT_WBINVD), + [x86_intercept_wrmsr] = POST_EX(SVM_EXIT_MSR), + [x86_intercept_rdtsc] = POST_EX(SVM_EXIT_RDTSC), + [x86_intercept_rdmsr] = POST_EX(SVM_EXIT_MSR), + [x86_intercept_rdpmc] = POST_EX(SVM_EXIT_RDPMC), + [x86_intercept_cpuid] = PRE_EX(SVM_EXIT_CPUID), + [x86_intercept_rsm] = PRE_EX(SVM_EXIT_RSM), + [x86_intercept_pause] = PRE_EX(SVM_EXIT_PAUSE), + [x86_intercept_pushf] = PRE_EX(SVM_EXIT_PUSHF), + [x86_intercept_popf] = PRE_EX(SVM_EXIT_POPF), + [x86_intercept_intn] = PRE_EX(SVM_EXIT_SWINT), + [x86_intercept_iret] = PRE_EX(SVM_EXIT_IRET), + [x86_intercept_icebp] = PRE_EX(SVM_EXIT_ICEBP), + [x86_intercept_hlt] = POST_EX(SVM_EXIT_HLT), + [x86_intercept_in] = POST_EX(SVM_EXIT_IOIO), + [x86_intercept_ins] = POST_EX(SVM_EXIT_IOIO), + [x86_intercept_out] = POST_EX(SVM_EXIT_IOIO), + [x86_intercept_outs] = POST_EX(SVM_EXIT_IOIO), +}; + +#undef PRE_EX +#undef POST_EX +#undef POST_MEM + +static int svm_check_intercept(struct kvm_vcpu *vcpu, + struct x86_instruction_info *info, + enum x86_intercept_stage stage) +{ + struct vcpu_svm *svm = to_svm(vcpu); + int vmexit, ret = X86EMUL_CONTINUE; + struct __x86_intercept icpt_info; + struct vmcb *vmcb = svm->vmcb; + + if (info->intercept >= ARRAY_SIZE(x86_intercept_map)) + goto out; + + icpt_info = x86_intercept_map[info->intercept]; + + if (stage != icpt_info.stage) + goto out; + + switch (icpt_info.exit_code) { + case SVM_EXIT_READ_CR0: + if (info->intercept == x86_intercept_cr_read) + icpt_info.exit_code += info->modrm_reg; + break; + case SVM_EXIT_WRITE_CR0: { + unsigned long cr0, val; + u64 intercept; + + if (info->intercept == x86_intercept_cr_write) + icpt_info.exit_code += info->modrm_reg; + + if (icpt_info.exit_code != SVM_EXIT_WRITE_CR0) + break; + + intercept = svm->nested.intercept; + + if (!(intercept & (1ULL << INTERCEPT_SELECTIVE_CR0))) + break; + + cr0 = vcpu->arch.cr0 & ~SVM_CR0_SELECTIVE_MASK; + val = info->src_val & ~SVM_CR0_SELECTIVE_MASK; + + if (info->intercept == x86_intercept_lmsw) { + cr0 &= 0xfUL; + val &= 0xfUL; + /* lmsw can't clear PE - catch this here */ + if (cr0 & X86_CR0_PE) + val |= X86_CR0_PE; + } + + if (cr0 ^ val) + icpt_info.exit_code = SVM_EXIT_CR0_SEL_WRITE; + + break; + } + case SVM_EXIT_READ_DR0: + case SVM_EXIT_WRITE_DR0: + icpt_info.exit_code += info->modrm_reg; + break; + case SVM_EXIT_MSR: + if (info->intercept == x86_intercept_wrmsr) + vmcb->control.exit_info_1 = 1; + else + vmcb->control.exit_info_1 = 0; + break; + case SVM_EXIT_PAUSE: + /* + * We get this for NOP only, but pause + * is rep not, check this here + */ + if (info->rep_prefix != REPE_PREFIX) + goto out; + case SVM_EXIT_IOIO: { + u64 exit_info; + u32 bytes; + + exit_info = (vcpu->arch.regs[VCPU_REGS_RDX] & 0xffff) << 16; + + if (info->intercept == x86_intercept_in || + info->intercept == x86_intercept_ins) { + exit_info |= SVM_IOIO_TYPE_MASK; + bytes = info->src_bytes; + } else { + bytes = info->dst_bytes; + } + + if (info->intercept == x86_intercept_outs || + info->intercept == x86_intercept_ins) + exit_info |= SVM_IOIO_STR_MASK; + + if (info->rep_prefix) + exit_info |= SVM_IOIO_REP_MASK; + + bytes = min(bytes, 4u); + + exit_info |= bytes << SVM_IOIO_SIZE_SHIFT; + + exit_info |= (u32)info->ad_bytes << (SVM_IOIO_ASIZE_SHIFT - 1); + + vmcb->control.exit_info_1 = exit_info; + vmcb->control.exit_info_2 = info->next_rip; + + break; + } + default: + break; + } + + vmcb->control.next_rip = info->next_rip; + vmcb->control.exit_code = icpt_info.exit_code; + vmexit = nested_svm_exit_handled(svm); + + ret = (vmexit == NESTED_EXIT_DONE) ? X86EMUL_INTERCEPTED + : X86EMUL_CONTINUE; + +out: + return ret; +} + static struct kvm_x86_ops svm_x86_ops = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, @@ -3952,10 +4231,14 @@ static struct kvm_x86_ops svm_x86_ops = { .has_wbinvd_exit = svm_has_wbinvd_exit, + .set_tsc_khz = svm_set_tsc_khz, .write_tsc_offset = svm_write_tsc_offset, .adjust_tsc_offset = svm_adjust_tsc_offset, + .compute_tsc_offset = svm_compute_tsc_offset, .set_tdp_cr3 = set_tdp_cr3, + + .check_intercept = svm_check_intercept, }; static int __init svm_init(void) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 5b4cdcbd154c..4c3fa0f67469 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -128,8 +128,11 @@ struct vcpu_vmx { unsigned long host_rsp; int launched; u8 fail; + u8 cpl; + bool nmi_known_unmasked; u32 exit_intr_info; u32 idt_vectoring_info; + ulong rflags; struct shared_msr_entry *guest_msrs; int nmsrs; int save_nmsrs; @@ -159,6 +162,10 @@ struct vcpu_vmx { u32 ar; } tr, es, ds, fs, gs; } rmode; + struct { + u32 bitmask; /* 4 bits per segment (1 bit per field) */ + struct kvm_save_segment seg[8]; + } segment_cache; int vpid; bool emulation_required; @@ -171,6 +178,15 @@ struct vcpu_vmx { bool rdtscp_enabled; }; +enum segment_cache_field { + SEG_FIELD_SEL = 0, + SEG_FIELD_BASE = 1, + SEG_FIELD_LIMIT = 2, + SEG_FIELD_AR = 3, + + SEG_FIELD_NR = 4 +}; + static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) { return container_of(vcpu, struct vcpu_vmx, vcpu); @@ -643,6 +659,62 @@ static void vmcs_set_bits(unsigned long field, u32 mask) vmcs_writel(field, vmcs_readl(field) | mask); } +static void vmx_segment_cache_clear(struct vcpu_vmx *vmx) +{ + vmx->segment_cache.bitmask = 0; +} + +static bool vmx_segment_cache_test_set(struct vcpu_vmx *vmx, unsigned seg, + unsigned field) +{ + bool ret; + u32 mask = 1 << (seg * SEG_FIELD_NR + field); + + if (!(vmx->vcpu.arch.regs_avail & (1 << VCPU_EXREG_SEGMENTS))) { + vmx->vcpu.arch.regs_avail |= (1 << VCPU_EXREG_SEGMENTS); + vmx->segment_cache.bitmask = 0; + } + ret = vmx->segment_cache.bitmask & mask; + vmx->segment_cache.bitmask |= mask; + return ret; +} + +static u16 vmx_read_guest_seg_selector(struct vcpu_vmx *vmx, unsigned seg) +{ + u16 *p = &vmx->segment_cache.seg[seg].selector; + + if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_SEL)) + *p = vmcs_read16(kvm_vmx_segment_fields[seg].selector); + return *p; +} + +static ulong vmx_read_guest_seg_base(struct vcpu_vmx *vmx, unsigned seg) +{ + ulong *p = &vmx->segment_cache.seg[seg].base; + + if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_BASE)) + *p = vmcs_readl(kvm_vmx_segment_fields[seg].base); + return *p; +} + +static u32 vmx_read_guest_seg_limit(struct vcpu_vmx *vmx, unsigned seg) +{ + u32 *p = &vmx->segment_cache.seg[seg].limit; + + if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_LIMIT)) + *p = vmcs_read32(kvm_vmx_segment_fields[seg].limit); + return *p; +} + +static u32 vmx_read_guest_seg_ar(struct vcpu_vmx *vmx, unsigned seg) +{ + u32 *p = &vmx->segment_cache.seg[seg].ar; + + if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_AR)) + *p = vmcs_read32(kvm_vmx_segment_fields[seg].ar_bytes); + return *p; +} + static void update_exception_bitmap(struct kvm_vcpu *vcpu) { u32 eb; @@ -970,17 +1042,24 @@ static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu) { unsigned long rflags, save_rflags; - rflags = vmcs_readl(GUEST_RFLAGS); - if (to_vmx(vcpu)->rmode.vm86_active) { - rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS; - save_rflags = to_vmx(vcpu)->rmode.save_rflags; - rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS; + if (!test_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail)) { + __set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail); + rflags = vmcs_readl(GUEST_RFLAGS); + if (to_vmx(vcpu)->rmode.vm86_active) { + rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS; + save_rflags = to_vmx(vcpu)->rmode.save_rflags; + rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS; + } + to_vmx(vcpu)->rflags = rflags; } - return rflags; + return to_vmx(vcpu)->rflags; } static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { + __set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail); + __clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); + to_vmx(vcpu)->rflags = rflags; if (to_vmx(vcpu)->rmode.vm86_active) { to_vmx(vcpu)->rmode.save_rflags = rflags; rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM; @@ -1053,7 +1132,10 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, } if (vmx->rmode.vm86_active) { - if (kvm_inject_realmode_interrupt(vcpu, nr) != EMULATE_DONE) + int inc_eip = 0; + if (kvm_exception_is_soft(nr)) + inc_eip = vcpu->arch.event_exit_inst_len; + if (kvm_inject_realmode_interrupt(vcpu, nr, inc_eip) != EMULATE_DONE) kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); return; } @@ -1151,6 +1233,16 @@ static u64 guest_read_tsc(void) } /* + * Empty call-back. Needs to be implemented when VMX enables the SET_TSC_KHZ + * ioctl. In this case the call-back should update internal vmx state to make + * the changes effective. + */ +static void vmx_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz) +{ + /* Nothing to do here */ +} + +/* * writes 'offset' into guest's timestamp counter offset register */ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) @@ -1164,6 +1256,11 @@ static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment) vmcs_write64(TSC_OFFSET, offset + adjustment); } +static u64 vmx_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) +{ + return target_tsc - native_read_tsc(); +} + /* * Reads an msr value (of 'msr_index') into 'pdata'. * Returns 0 on success, non-0 otherwise. @@ -1243,9 +1340,11 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) break; #ifdef CONFIG_X86_64 case MSR_FS_BASE: + vmx_segment_cache_clear(vmx); vmcs_writel(GUEST_FS_BASE, data); break; case MSR_GS_BASE: + vmx_segment_cache_clear(vmx); vmcs_writel(GUEST_GS_BASE, data); break; case MSR_KERNEL_GS_BASE: @@ -1689,6 +1788,8 @@ static void enter_pmode(struct kvm_vcpu *vcpu) vmx->emulation_required = 1; vmx->rmode.vm86_active = 0; + vmx_segment_cache_clear(vmx); + vmcs_write16(GUEST_TR_SELECTOR, vmx->rmode.tr.selector); vmcs_writel(GUEST_TR_BASE, vmx->rmode.tr.base); vmcs_write32(GUEST_TR_LIMIT, vmx->rmode.tr.limit); @@ -1712,6 +1813,8 @@ static void enter_pmode(struct kvm_vcpu *vcpu) fix_pmode_dataseg(VCPU_SREG_GS, &vmx->rmode.gs); fix_pmode_dataseg(VCPU_SREG_FS, &vmx->rmode.fs); + vmx_segment_cache_clear(vmx); + vmcs_write16(GUEST_SS_SELECTOR, 0); vmcs_write32(GUEST_SS_AR_BYTES, 0x93); @@ -1775,6 +1878,8 @@ static void enter_rmode(struct kvm_vcpu *vcpu) vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); } + vmx_segment_cache_clear(vmx); + vmx->rmode.tr.selector = vmcs_read16(GUEST_TR_SELECTOR); vmx->rmode.tr.base = vmcs_readl(GUEST_TR_BASE); vmcs_writel(GUEST_TR_BASE, rmode_tss_base(vcpu->kvm)); @@ -1851,6 +1956,8 @@ static void enter_lmode(struct kvm_vcpu *vcpu) { u32 guest_tr_ar; + vmx_segment_cache_clear(to_vmx(vcpu)); + guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES); if ((guest_tr_ar & AR_TYPE_MASK) != AR_TYPE_BUSY_64_TSS) { printk(KERN_DEBUG "%s: tss fixup for long mode. \n", @@ -1998,6 +2105,7 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) vmcs_writel(CR0_READ_SHADOW, cr0); vmcs_writel(GUEST_CR0, hw_cr0); vcpu->arch.cr0 = cr0; + __clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); } static u64 construct_eptp(unsigned long root_hpa) @@ -2053,7 +2161,6 @@ static void vmx_get_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]; struct kvm_save_segment *save; u32 ar; @@ -2075,13 +2182,13 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu, var->limit = save->limit; ar = save->ar; if (seg == VCPU_SREG_TR - || var->selector == vmcs_read16(sf->selector)) + || var->selector == vmx_read_guest_seg_selector(vmx, seg)) goto use_saved_rmode_seg; } - var->base = vmcs_readl(sf->base); - var->limit = vmcs_read32(sf->limit); - var->selector = vmcs_read16(sf->selector); - ar = vmcs_read32(sf->ar_bytes); + var->base = vmx_read_guest_seg_base(vmx, seg); + var->limit = vmx_read_guest_seg_limit(vmx, seg); + var->selector = vmx_read_guest_seg_selector(vmx, seg); + ar = vmx_read_guest_seg_ar(vmx, seg); use_saved_rmode_seg: if ((ar & AR_UNUSABLE_MASK) && !emulate_invalid_guest_state) ar = 0; @@ -2098,27 +2205,37 @@ use_saved_rmode_seg: static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) { - struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; struct kvm_segment s; if (to_vmx(vcpu)->rmode.vm86_active) { vmx_get_segment(vcpu, &s, seg); return s.base; } - return vmcs_readl(sf->base); + return vmx_read_guest_seg_base(to_vmx(vcpu), seg); } -static int vmx_get_cpl(struct kvm_vcpu *vcpu) +static int __vmx_get_cpl(struct kvm_vcpu *vcpu) { if (!is_protmode(vcpu)) return 0; - if (vmx_get_rflags(vcpu) & X86_EFLAGS_VM) /* if virtual 8086 */ + if (!is_long_mode(vcpu) + && (kvm_get_rflags(vcpu) & X86_EFLAGS_VM)) /* if virtual 8086 */ return 3; - return vmcs_read16(GUEST_CS_SELECTOR) & 3; + return vmx_read_guest_seg_selector(to_vmx(vcpu), VCPU_SREG_CS) & 3; } +static int vmx_get_cpl(struct kvm_vcpu *vcpu) +{ + if (!test_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail)) { + __set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); + to_vmx(vcpu)->cpl = __vmx_get_cpl(vcpu); + } + return to_vmx(vcpu)->cpl; +} + + static u32 vmx_segment_access_rights(struct kvm_segment *var) { u32 ar; @@ -2148,6 +2265,8 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; u32 ar; + vmx_segment_cache_clear(vmx); + if (vmx->rmode.vm86_active && seg == VCPU_SREG_TR) { vmcs_write16(sf->selector, var->selector); vmx->rmode.tr.selector = var->selector; @@ -2184,11 +2303,12 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, ar |= 0x1; /* Accessed */ vmcs_write32(sf->ar_bytes, ar); + __clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); } static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) { - u32 ar = vmcs_read32(GUEST_CS_AR_BYTES); + u32 ar = vmx_read_guest_seg_ar(to_vmx(vcpu), VCPU_SREG_CS); *db = (ar >> 14) & 1; *l = (ar >> 13) & 1; @@ -2775,6 +2895,8 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) if (ret != 0) goto out; + vmx_segment_cache_clear(vmx); + seg_setup(VCPU_SREG_CS); /* * GUEST_CS_BASE should really be 0xffff0000, but VT vm86 mode @@ -2904,7 +3026,10 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu) ++vcpu->stat.irq_injections; if (vmx->rmode.vm86_active) { - if (kvm_inject_realmode_interrupt(vcpu, irq) != EMULATE_DONE) + int inc_eip = 0; + if (vcpu->arch.interrupt.soft) + inc_eip = vcpu->arch.event_exit_inst_len; + if (kvm_inject_realmode_interrupt(vcpu, irq, inc_eip) != EMULATE_DONE) kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); return; } @@ -2937,8 +3062,9 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu) } ++vcpu->stat.nmi_injections; + vmx->nmi_known_unmasked = false; if (vmx->rmode.vm86_active) { - if (kvm_inject_realmode_interrupt(vcpu, NMI_VECTOR) != EMULATE_DONE) + if (kvm_inject_realmode_interrupt(vcpu, NMI_VECTOR, 0) != EMULATE_DONE) kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); return; } @@ -2961,6 +3087,8 @@ static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu) { if (!cpu_has_virtual_nmis()) return to_vmx(vcpu)->soft_vnmi_blocked; + if (to_vmx(vcpu)->nmi_known_unmasked) + return false; return vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI; } @@ -2974,6 +3102,7 @@ static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) vmx->vnmi_blocked_time = 0; } } else { + vmx->nmi_known_unmasked = !masked; if (masked) vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); @@ -3091,7 +3220,7 @@ static int handle_exception(struct kvm_vcpu *vcpu) enum emulation_result er; vect_info = vmx->idt_vectoring_info; - intr_info = vmcs_read32(VM_EXIT_INTR_INFO); + intr_info = vmx->exit_intr_info; if (is_machine_check(intr_info)) return handle_machine_check(vcpu); @@ -3122,7 +3251,6 @@ static int handle_exception(struct kvm_vcpu *vcpu) } error_code = 0; - rip = kvm_rip_read(vcpu); if (intr_info & INTR_INFO_DELIVER_CODE_MASK) error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); if (is_page_fault(intr_info)) { @@ -3169,6 +3297,7 @@ static int handle_exception(struct kvm_vcpu *vcpu) vmx->vcpu.arch.event_exit_inst_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN); kvm_run->exit_reason = KVM_EXIT_DEBUG; + rip = kvm_rip_read(vcpu); kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip; kvm_run->debug.arch.exception = ex_no; break; @@ -3505,9 +3634,7 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) switch (type) { case INTR_TYPE_NMI_INTR: vcpu->arch.nmi_injected = false; - if (cpu_has_virtual_nmis()) - vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, - GUEST_INTR_STATE_NMI); + vmx_set_nmi_mask(vcpu, true); break; case INTR_TYPE_EXT_INTR: case INTR_TYPE_SOFT_INTR: @@ -3867,12 +3994,17 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx) { - u32 exit_intr_info = vmx->exit_intr_info; + u32 exit_intr_info; + + if (!(vmx->exit_reason == EXIT_REASON_MCE_DURING_VMENTRY + || vmx->exit_reason == EXIT_REASON_EXCEPTION_NMI)) + return; + + vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); + exit_intr_info = vmx->exit_intr_info; /* Handle machine checks before interrupts are enabled */ - if ((vmx->exit_reason == EXIT_REASON_MCE_DURING_VMENTRY) - || (vmx->exit_reason == EXIT_REASON_EXCEPTION_NMI - && is_machine_check(exit_intr_info))) + if (is_machine_check(exit_intr_info)) kvm_machine_check(); /* We need to handle NMIs before interrupts are enabled */ @@ -3886,7 +4018,7 @@ static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx) static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) { - u32 exit_intr_info = vmx->exit_intr_info; + u32 exit_intr_info; bool unblock_nmi; u8 vector; bool idtv_info_valid; @@ -3894,6 +4026,13 @@ static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) idtv_info_valid = vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK; if (cpu_has_virtual_nmis()) { + if (vmx->nmi_known_unmasked) + return; + /* + * Can't use vmx->exit_intr_info since we're not sure what + * the exit reason is. + */ + exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); unblock_nmi = (exit_intr_info & INTR_INFO_UNBLOCK_NMI) != 0; vector = exit_intr_info & INTR_INFO_VECTOR_MASK; /* @@ -3910,6 +4049,10 @@ static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) vector != DF_VECTOR && !idtv_info_valid) vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); + else + vmx->nmi_known_unmasked = + !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) + & GUEST_INTR_STATE_NMI); } else if (unlikely(vmx->soft_vnmi_blocked)) vmx->vnmi_blocked_time += ktime_to_ns(ktime_sub(ktime_get(), vmx->entry_time)); @@ -3946,8 +4089,7 @@ static void __vmx_complete_interrupts(struct vcpu_vmx *vmx, * Clear bit "block by NMI" before VM entry if a NMI * delivery faulted. */ - vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO, - GUEST_INTR_STATE_NMI); + vmx_set_nmi_mask(&vmx->vcpu, false); break; case INTR_TYPE_SOFT_EXCEPTION: vmx->vcpu.arch.event_exit_inst_len = @@ -4124,7 +4266,10 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) ); vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP) + | (1 << VCPU_EXREG_RFLAGS) + | (1 << VCPU_EXREG_CPL) | (1 << VCPU_EXREG_PDPTR) + | (1 << VCPU_EXREG_SEGMENTS) | (1 << VCPU_EXREG_CR3)); vcpu->arch.regs_dirty = 0; @@ -4134,7 +4279,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->launched = 1; vmx->exit_reason = vmcs_read32(VM_EXIT_REASON); - vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); vmx_complete_atomic_exit(vmx); vmx_recover_nmi_blocking(vmx); @@ -4195,8 +4339,8 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) goto free_vcpu; vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL); + err = -ENOMEM; if (!vmx->guest_msrs) { - err = -ENOMEM; goto uninit_vcpu; } @@ -4215,7 +4359,8 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (err) goto free_vmcs; if (vm_need_virtualize_apic_accesses(kvm)) - if (alloc_apic_access_page(kvm) != 0) + err = alloc_apic_access_page(kvm); + if (err) goto free_vmcs; if (enable_ept) { @@ -4368,6 +4513,13 @@ static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) { } +static int vmx_check_intercept(struct kvm_vcpu *vcpu, + struct x86_instruction_info *info, + enum x86_intercept_stage stage) +{ + return X86EMUL_CONTINUE; +} + static struct kvm_x86_ops vmx_x86_ops = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios, @@ -4449,10 +4601,14 @@ static struct kvm_x86_ops vmx_x86_ops = { .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, + .set_tsc_khz = vmx_set_tsc_khz, .write_tsc_offset = vmx_write_tsc_offset, .adjust_tsc_offset = vmx_adjust_tsc_offset, + .compute_tsc_offset = vmx_compute_tsc_offset, .set_tdp_cr3 = vmx_set_cr3, + + .check_intercept = vmx_check_intercept, }; static int __init vmx_init(void) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 934b4c6b0bf9..77c9d8673dc4 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -60,22 +60,12 @@ #include <asm/div64.h> #define MAX_IO_MSRS 256 -#define CR0_RESERVED_BITS \ - (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ - | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \ - | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG)) -#define CR4_RESERVED_BITS \ - (~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\ - | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \ - | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR \ - | X86_CR4_OSXSAVE \ - | 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 | MCG_SER_P) +#define emul_to_vcpu(ctxt) \ + container_of(ctxt, struct kvm_vcpu, arch.emulate_ctxt) + /* EFER defaults: * - enable syscall per default because its emulated by KVM * - enable LME and LMA per default on 64 bit KVM @@ -100,6 +90,11 @@ EXPORT_SYMBOL_GPL(kvm_x86_ops); int ignore_msrs = 0; module_param_named(ignore_msrs, ignore_msrs, bool, S_IRUGO | S_IWUSR); +bool kvm_has_tsc_control; +EXPORT_SYMBOL_GPL(kvm_has_tsc_control); +u32 kvm_max_guest_tsc_khz; +EXPORT_SYMBOL_GPL(kvm_max_guest_tsc_khz); + #define KVM_NR_SHARED_MSRS 16 struct kvm_shared_msrs_global { @@ -157,6 +152,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { u64 __read_mostly host_xcr0; +int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt); + static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu) { int i; @@ -361,8 +358,8 @@ void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) void kvm_inject_nmi(struct kvm_vcpu *vcpu) { - kvm_make_request(KVM_REQ_NMI, vcpu); kvm_make_request(KVM_REQ_EVENT, vcpu); + vcpu->arch.nmi_pending = 1; } EXPORT_SYMBOL_GPL(kvm_inject_nmi); @@ -982,7 +979,15 @@ static inline int kvm_tsc_changes_freq(void) return ret; } -static inline u64 nsec_to_cycles(u64 nsec) +static u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.virtual_tsc_khz) + return vcpu->arch.virtual_tsc_khz; + else + return __this_cpu_read(cpu_tsc_khz); +} + +static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) { u64 ret; @@ -990,25 +995,24 @@ static inline u64 nsec_to_cycles(u64 nsec) if (kvm_tsc_changes_freq()) printk_once(KERN_WARNING "kvm: unreliable cycle conversion on adjustable rate TSC\n"); - ret = nsec * __this_cpu_read(cpu_tsc_khz); + ret = nsec * vcpu_tsc_khz(vcpu); do_div(ret, USEC_PER_SEC); return ret; } -static void kvm_arch_set_tsc_khz(struct kvm *kvm, u32 this_tsc_khz) +static void kvm_init_tsc_catchup(struct kvm_vcpu *vcpu, u32 this_tsc_khz) { /* Compute a scale to convert nanoseconds in TSC cycles */ kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000, - &kvm->arch.virtual_tsc_shift, - &kvm->arch.virtual_tsc_mult); - kvm->arch.virtual_tsc_khz = this_tsc_khz; + &vcpu->arch.tsc_catchup_shift, + &vcpu->arch.tsc_catchup_mult); } static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) { u64 tsc = pvclock_scale_delta(kernel_ns-vcpu->arch.last_tsc_nsec, - vcpu->kvm->arch.virtual_tsc_mult, - vcpu->kvm->arch.virtual_tsc_shift); + vcpu->arch.tsc_catchup_mult, + vcpu->arch.tsc_catchup_shift); tsc += vcpu->arch.last_tsc_write; return tsc; } @@ -1021,7 +1025,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data) s64 sdiff; raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); - offset = data - native_read_tsc(); + offset = kvm_x86_ops->compute_tsc_offset(vcpu, data); ns = get_kernel_ns(); elapsed = ns - kvm->arch.last_tsc_nsec; sdiff = data - kvm->arch.last_tsc_write; @@ -1037,13 +1041,13 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data) * In that case, for a reliable TSC, we can match TSC offsets, * or make a best guest using elapsed value. */ - if (sdiff < nsec_to_cycles(5ULL * NSEC_PER_SEC) && + if (sdiff < nsec_to_cycles(vcpu, 5ULL * NSEC_PER_SEC) && elapsed < 5ULL * NSEC_PER_SEC) { if (!check_tsc_unstable()) { offset = kvm->arch.last_tsc_offset; pr_debug("kvm: matched tsc offset for %llu\n", data); } else { - u64 delta = nsec_to_cycles(elapsed); + u64 delta = nsec_to_cycles(vcpu, elapsed); offset += delta; pr_debug("kvm: adjusted tsc offset by %llu\n", delta); } @@ -1075,8 +1079,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) local_irq_save(flags); kvm_get_msr(v, MSR_IA32_TSC, &tsc_timestamp); kernel_ns = get_kernel_ns(); - this_tsc_khz = __this_cpu_read(cpu_tsc_khz); - + this_tsc_khz = vcpu_tsc_khz(v); if (unlikely(this_tsc_khz == 0)) { local_irq_restore(flags); kvm_make_request(KVM_REQ_CLOCK_UPDATE, v); @@ -1993,6 +1996,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_X86_ROBUST_SINGLESTEP: case KVM_CAP_XSAVE: case KVM_CAP_ASYNC_PF: + case KVM_CAP_GET_TSC_KHZ: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -2019,6 +2023,9 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_XCRS: r = cpu_has_xsave; break; + case KVM_CAP_TSC_CONTROL: + r = kvm_has_tsc_control; + break; default: r = 0; break; @@ -2120,8 +2127,13 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_x86_ops->vcpu_load(vcpu, cpu); if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) { /* Make sure TSC doesn't go backwards */ - s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 : - native_read_tsc() - vcpu->arch.last_host_tsc; + s64 tsc_delta; + u64 tsc; + + kvm_get_msr(vcpu, MSR_IA32_TSC, &tsc); + tsc_delta = !vcpu->arch.last_guest_tsc ? 0 : + tsc - vcpu->arch.last_guest_tsc; + if (tsc_delta < 0) mark_tsc_unstable("KVM discovered backwards TSC"); if (check_tsc_unstable()) { @@ -2139,7 +2151,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { kvm_x86_ops->vcpu_put(vcpu); kvm_put_guest_fpu(vcpu); - vcpu->arch.last_host_tsc = native_read_tsc(); + kvm_get_msr(vcpu, MSR_IA32_TSC, &vcpu->arch.last_guest_tsc); } static int is_efer_nx(void) @@ -2324,6 +2336,12 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(XOP) | 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM); + /* cpuid 0xC0000001.edx */ + const u32 kvm_supported_word5_x86_features = + F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) | + F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) | + F(PMM) | F(PMM_EN); + /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); do_cpuid_1_ent(entry, function, index); @@ -2418,6 +2436,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->eax = (1 << KVM_FEATURE_CLOCKSOURCE) | (1 << KVM_FEATURE_NOP_IO_DELAY) | (1 << KVM_FEATURE_CLOCKSOURCE2) | + (1 << KVM_FEATURE_ASYNC_PF) | (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT); entry->ebx = 0; entry->ecx = 0; @@ -2432,6 +2451,20 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->ecx &= kvm_supported_word6_x86_features; cpuid_mask(&entry->ecx, 6); break; + /*Add support for Centaur's CPUID instruction*/ + case 0xC0000000: + /*Just support up to 0xC0000004 now*/ + entry->eax = min(entry->eax, 0xC0000004); + break; + case 0xC0000001: + entry->edx &= kvm_supported_word5_x86_features; + cpuid_mask(&entry->edx, 5); + break; + case 0xC0000002: + case 0xC0000003: + case 0xC0000004: + /*Now nothing to do, reserved for the future*/ + break; } kvm_x86_ops->set_supported_cpuid(function, entry); @@ -2478,6 +2511,26 @@ static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, if (nent >= cpuid->nent) goto out_free; + /* Add support for Centaur's CPUID instruction. */ + if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR) { + do_cpuid_ent(&cpuid_entries[nent], 0xC0000000, 0, + &nent, cpuid->nent); + + r = -E2BIG; + if (nent >= cpuid->nent) + goto out_free; + + limit = cpuid_entries[nent - 1].eax; + for (func = 0xC0000001; + 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; + } + do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_SIGNATURE, 0, &nent, cpuid->nent); @@ -3046,6 +3099,32 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_vcpu_ioctl_x86_set_xcrs(vcpu, u.xcrs); break; } + case KVM_SET_TSC_KHZ: { + u32 user_tsc_khz; + + r = -EINVAL; + if (!kvm_has_tsc_control) + break; + + user_tsc_khz = (u32)arg; + + if (user_tsc_khz >= kvm_max_guest_tsc_khz) + goto out; + + kvm_x86_ops->set_tsc_khz(vcpu, user_tsc_khz); + + r = 0; + goto out; + } + case KVM_GET_TSC_KHZ: { + r = -EIO; + if (check_tsc_unstable()) + goto out; + + r = vcpu_tsc_khz(vcpu); + + goto out; + } default: r = -EINVAL; } @@ -3595,20 +3674,43 @@ static void kvm_init_msr_list(void) static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, const void *v) { - if (vcpu->arch.apic && - !kvm_iodevice_write(&vcpu->arch.apic->dev, addr, len, v)) - return 0; + int handled = 0; + int n; - return kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, addr, len, v); + do { + n = min(len, 8); + if (!(vcpu->arch.apic && + !kvm_iodevice_write(&vcpu->arch.apic->dev, addr, n, v)) + && kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, addr, n, v)) + break; + handled += n; + addr += n; + len -= n; + v += n; + } while (len); + + return handled; } static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) { - if (vcpu->arch.apic && - !kvm_iodevice_read(&vcpu->arch.apic->dev, addr, len, v)) - return 0; + int handled = 0; + int n; + + do { + n = min(len, 8); + if (!(vcpu->arch.apic && + !kvm_iodevice_read(&vcpu->arch.apic->dev, addr, n, v)) + && kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, addr, n, v)) + break; + trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, *(u64 *)v); + handled += n; + addr += n; + len -= n; + v += n; + } while (len); - return kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, addr, len, v); + return handled; } static void kvm_set_segment(struct kvm_vcpu *vcpu, @@ -3703,37 +3805,43 @@ out: } /* used for instruction fetching */ -static int kvm_fetch_guest_virt(gva_t addr, void *val, unsigned int bytes, - struct kvm_vcpu *vcpu, +static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt, + gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception) { + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access | PFERR_FETCH_MASK, exception); } -static int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes, - struct kvm_vcpu *vcpu, +static int kvm_read_guest_virt(struct x86_emulate_ctxt *ctxt, + gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception) { + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception); } -static int kvm_read_guest_virt_system(gva_t addr, void *val, unsigned int bytes, - struct kvm_vcpu *vcpu, +static int kvm_read_guest_virt_system(struct x86_emulate_ctxt *ctxt, + gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception) { + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, exception); } -static int kvm_write_guest_virt_system(gva_t addr, void *val, +static int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt, + gva_t addr, void *val, unsigned int bytes, - struct kvm_vcpu *vcpu, struct x86_exception *exception) { + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); void *data = val; int r = X86EMUL_CONTINUE; @@ -3761,13 +3869,15 @@ out: return r; } -static int emulator_read_emulated(unsigned long addr, +static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt, + unsigned long addr, void *val, unsigned int bytes, - struct x86_exception *exception, - struct kvm_vcpu *vcpu) + struct x86_exception *exception) { + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); gpa_t gpa; + int handled; if (vcpu->mmio_read_completed) { memcpy(val, vcpu->mmio_data, bytes); @@ -3786,7 +3896,7 @@ static int emulator_read_emulated(unsigned long addr, if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) goto mmio; - if (kvm_read_guest_virt(addr, val, bytes, vcpu, exception) + if (kvm_read_guest_virt(ctxt, addr, val, bytes, exception) == X86EMUL_CONTINUE) return X86EMUL_CONTINUE; @@ -3794,18 +3904,24 @@ mmio: /* * Is this MMIO handled locally? */ - if (!vcpu_mmio_read(vcpu, gpa, bytes, val)) { - trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes, gpa, *(u64 *)val); + handled = vcpu_mmio_read(vcpu, gpa, bytes, val); + + if (handled == bytes) return X86EMUL_CONTINUE; - } + + gpa += handled; + bytes -= handled; + val += handled; trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, 0); vcpu->mmio_needed = 1; vcpu->run->exit_reason = KVM_EXIT_MMIO; vcpu->run->mmio.phys_addr = vcpu->mmio_phys_addr = gpa; - vcpu->run->mmio.len = vcpu->mmio_size = bytes; + vcpu->mmio_size = bytes; + vcpu->run->mmio.len = min(vcpu->mmio_size, 8); vcpu->run->mmio.is_write = vcpu->mmio_is_write = 0; + vcpu->mmio_index = 0; return X86EMUL_IO_NEEDED; } @@ -3829,6 +3945,7 @@ static int emulator_write_emulated_onepage(unsigned long addr, struct kvm_vcpu *vcpu) { gpa_t gpa; + int handled; gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, exception); @@ -3847,25 +3964,35 @@ mmio: /* * Is this MMIO handled locally? */ - if (!vcpu_mmio_write(vcpu, gpa, bytes, val)) + handled = vcpu_mmio_write(vcpu, gpa, bytes, val); + if (handled == bytes) return X86EMUL_CONTINUE; + gpa += handled; + bytes -= handled; + val += handled; + vcpu->mmio_needed = 1; + memcpy(vcpu->mmio_data, val, bytes); vcpu->run->exit_reason = KVM_EXIT_MMIO; vcpu->run->mmio.phys_addr = vcpu->mmio_phys_addr = gpa; - vcpu->run->mmio.len = vcpu->mmio_size = bytes; + vcpu->mmio_size = bytes; + vcpu->run->mmio.len = min(vcpu->mmio_size, 8); vcpu->run->mmio.is_write = vcpu->mmio_is_write = 1; - memcpy(vcpu->run->mmio.data, val, bytes); + memcpy(vcpu->run->mmio.data, vcpu->mmio_data, 8); + vcpu->mmio_index = 0; return X86EMUL_CONTINUE; } -int emulator_write_emulated(unsigned long addr, +int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, + unsigned long addr, const void *val, unsigned int bytes, - struct x86_exception *exception, - struct kvm_vcpu *vcpu) + struct x86_exception *exception) { + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + /* Crossing a page boundary? */ if (((addr + bytes - 1) ^ addr) & PAGE_MASK) { int rc, now; @@ -3893,13 +4020,14 @@ int emulator_write_emulated(unsigned long addr, (cmpxchg64((u64 *)(ptr), *(u64 *)(old), *(u64 *)(new)) == *(u64 *)(old)) #endif -static int emulator_cmpxchg_emulated(unsigned long addr, +static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, + unsigned long addr, const void *old, const void *new, unsigned int bytes, - struct x86_exception *exception, - struct kvm_vcpu *vcpu) + struct x86_exception *exception) { + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); gpa_t gpa; struct page *page; char *kaddr; @@ -3955,7 +4083,7 @@ static int emulator_cmpxchg_emulated(unsigned long addr, emul_write: printk_once(KERN_WARNING "kvm: emulating exchange as write\n"); - return emulator_write_emulated(addr, new, bytes, exception, vcpu); + return emulator_write_emulated(ctxt, addr, new, bytes, exception); } static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) @@ -3974,9 +4102,12 @@ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) } -static int emulator_pio_in_emulated(int size, unsigned short port, void *val, - unsigned int count, struct kvm_vcpu *vcpu) +static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, + int size, unsigned short port, void *val, + unsigned int count) { + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + if (vcpu->arch.pio.count) goto data_avail; @@ -4004,10 +4135,12 @@ static int emulator_pio_in_emulated(int size, unsigned short port, void *val, return 0; } -static int emulator_pio_out_emulated(int size, unsigned short port, - const void *val, unsigned int count, - struct kvm_vcpu *vcpu) +static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, + int size, unsigned short port, + const void *val, unsigned int count) { + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + trace_kvm_pio(1, port, size, count); vcpu->arch.pio.port = port; @@ -4037,10 +4170,9 @@ static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg) return kvm_x86_ops->get_segment_base(vcpu, seg); } -int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address) +static void emulator_invlpg(struct x86_emulate_ctxt *ctxt, ulong address) { - kvm_mmu_invlpg(vcpu, address); - return X86EMUL_CONTINUE; + kvm_mmu_invlpg(emul_to_vcpu(ctxt), address); } int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu) @@ -4062,22 +4194,20 @@ int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_emulate_wbinvd); -int emulate_clts(struct kvm_vcpu *vcpu) +static void emulator_wbinvd(struct x86_emulate_ctxt *ctxt) { - kvm_x86_ops->set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS)); - kvm_x86_ops->fpu_activate(vcpu); - return X86EMUL_CONTINUE; + kvm_emulate_wbinvd(emul_to_vcpu(ctxt)); } -int emulator_get_dr(int dr, unsigned long *dest, struct kvm_vcpu *vcpu) +int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest) { - return _kvm_get_dr(vcpu, dr, dest); + return _kvm_get_dr(emul_to_vcpu(ctxt), dr, dest); } -int emulator_set_dr(int dr, unsigned long value, struct kvm_vcpu *vcpu) +int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value) { - return __kvm_set_dr(vcpu, dr, value); + return __kvm_set_dr(emul_to_vcpu(ctxt), dr, value); } static u64 mk_cr_64(u64 curr_cr, u32 new_val) @@ -4085,8 +4215,9 @@ static u64 mk_cr_64(u64 curr_cr, u32 new_val) return (curr_cr & ~((1ULL << 32) - 1)) | new_val; } -static unsigned long emulator_get_cr(int cr, struct kvm_vcpu *vcpu) +static unsigned long emulator_get_cr(struct x86_emulate_ctxt *ctxt, int cr) { + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); unsigned long value; switch (cr) { @@ -4113,8 +4244,9 @@ static unsigned long emulator_get_cr(int cr, struct kvm_vcpu *vcpu) return value; } -static int emulator_set_cr(int cr, unsigned long val, struct kvm_vcpu *vcpu) +static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val) { + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); int res = 0; switch (cr) { @@ -4141,33 +4273,45 @@ static int emulator_set_cr(int cr, unsigned long val, struct kvm_vcpu *vcpu) return res; } -static int emulator_get_cpl(struct kvm_vcpu *vcpu) +static int emulator_get_cpl(struct x86_emulate_ctxt *ctxt) +{ + return kvm_x86_ops->get_cpl(emul_to_vcpu(ctxt)); +} + +static void emulator_get_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) +{ + kvm_x86_ops->get_gdt(emul_to_vcpu(ctxt), dt); +} + +static void emulator_get_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - return kvm_x86_ops->get_cpl(vcpu); + kvm_x86_ops->get_idt(emul_to_vcpu(ctxt), dt); } -static void emulator_get_gdt(struct desc_ptr *dt, struct kvm_vcpu *vcpu) +static void emulator_set_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - kvm_x86_ops->get_gdt(vcpu, dt); + kvm_x86_ops->set_gdt(emul_to_vcpu(ctxt), dt); } -static void emulator_get_idt(struct desc_ptr *dt, struct kvm_vcpu *vcpu) +static void emulator_set_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - kvm_x86_ops->get_idt(vcpu, dt); + kvm_x86_ops->set_idt(emul_to_vcpu(ctxt), dt); } -static unsigned long emulator_get_cached_segment_base(int seg, - struct kvm_vcpu *vcpu) +static unsigned long emulator_get_cached_segment_base( + struct x86_emulate_ctxt *ctxt, int seg) { - return get_segment_base(vcpu, seg); + return get_segment_base(emul_to_vcpu(ctxt), seg); } -static bool emulator_get_cached_descriptor(struct desc_struct *desc, u32 *base3, - int seg, struct kvm_vcpu *vcpu) +static bool emulator_get_segment(struct x86_emulate_ctxt *ctxt, u16 *selector, + struct desc_struct *desc, u32 *base3, + int seg) { struct kvm_segment var; - kvm_get_segment(vcpu, &var, seg); + kvm_get_segment(emul_to_vcpu(ctxt), &var, seg); + *selector = var.selector; if (var.unusable) return false; @@ -4192,14 +4336,14 @@ static bool emulator_get_cached_descriptor(struct desc_struct *desc, u32 *base3, return true; } -static void emulator_set_cached_descriptor(struct desc_struct *desc, u32 base3, - int seg, struct kvm_vcpu *vcpu) +static void emulator_set_segment(struct x86_emulate_ctxt *ctxt, u16 selector, + struct desc_struct *desc, u32 base3, + int seg) { + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); struct kvm_segment var; - /* needed to preserve selector */ - kvm_get_segment(vcpu, &var, seg); - + var.selector = selector; var.base = get_desc_base(desc); #ifdef CONFIG_X86_64 var.base |= ((u64)base3) << 32; @@ -4223,22 +4367,44 @@ static void emulator_set_cached_descriptor(struct desc_struct *desc, u32 base3, return; } -static u16 emulator_get_segment_selector(int seg, struct kvm_vcpu *vcpu) +static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, + u32 msr_index, u64 *pdata) { - struct kvm_segment kvm_seg; + return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata); +} - kvm_get_segment(vcpu, &kvm_seg, seg); - return kvm_seg.selector; +static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, + u32 msr_index, u64 data) +{ + return kvm_set_msr(emul_to_vcpu(ctxt), msr_index, data); } -static void emulator_set_segment_selector(u16 sel, int seg, - struct kvm_vcpu *vcpu) +static void emulator_halt(struct x86_emulate_ctxt *ctxt) { - struct kvm_segment kvm_seg; + emul_to_vcpu(ctxt)->arch.halt_request = 1; +} - kvm_get_segment(vcpu, &kvm_seg, seg); - kvm_seg.selector = sel; - kvm_set_segment(vcpu, &kvm_seg, seg); +static void emulator_get_fpu(struct x86_emulate_ctxt *ctxt) +{ + preempt_disable(); + kvm_load_guest_fpu(emul_to_vcpu(ctxt)); + /* + * CR0.TS may reference the host fpu state, not the guest fpu state, + * so it may be clear at this point. + */ + clts(); +} + +static void emulator_put_fpu(struct x86_emulate_ctxt *ctxt) +{ + preempt_enable(); +} + +static int emulator_intercept(struct x86_emulate_ctxt *ctxt, + struct x86_instruction_info *info, + enum x86_intercept_stage stage) +{ + return kvm_x86_ops->check_intercept(emul_to_vcpu(ctxt), info, stage); } static struct x86_emulate_ops emulate_ops = { @@ -4248,22 +4414,29 @@ static struct x86_emulate_ops emulate_ops = { .read_emulated = emulator_read_emulated, .write_emulated = emulator_write_emulated, .cmpxchg_emulated = emulator_cmpxchg_emulated, + .invlpg = emulator_invlpg, .pio_in_emulated = emulator_pio_in_emulated, .pio_out_emulated = emulator_pio_out_emulated, - .get_cached_descriptor = emulator_get_cached_descriptor, - .set_cached_descriptor = emulator_set_cached_descriptor, - .get_segment_selector = emulator_get_segment_selector, - .set_segment_selector = emulator_set_segment_selector, + .get_segment = emulator_get_segment, + .set_segment = emulator_set_segment, .get_cached_segment_base = emulator_get_cached_segment_base, .get_gdt = emulator_get_gdt, .get_idt = emulator_get_idt, + .set_gdt = emulator_set_gdt, + .set_idt = emulator_set_idt, .get_cr = emulator_get_cr, .set_cr = emulator_set_cr, .cpl = emulator_get_cpl, .get_dr = emulator_get_dr, .set_dr = emulator_set_dr, - .set_msr = kvm_set_msr, - .get_msr = kvm_get_msr, + .set_msr = emulator_set_msr, + .get_msr = emulator_get_msr, + .halt = emulator_halt, + .wbinvd = emulator_wbinvd, + .fix_hypercall = emulator_fix_hypercall, + .get_fpu = emulator_get_fpu, + .put_fpu = emulator_put_fpu, + .intercept = emulator_intercept, }; static void cache_all_regs(struct kvm_vcpu *vcpu) @@ -4305,12 +4478,17 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) struct decode_cache *c = &vcpu->arch.emulate_ctxt.decode; int cs_db, cs_l; + /* + * 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. + */ cache_all_regs(vcpu); kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); - vcpu->arch.emulate_ctxt.vcpu = vcpu; - vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu); + vcpu->arch.emulate_ctxt.eflags = kvm_get_rflags(vcpu); vcpu->arch.emulate_ctxt.eip = kvm_rip_read(vcpu); vcpu->arch.emulate_ctxt.mode = (!is_protmode(vcpu)) ? X86EMUL_MODE_REAL : @@ -4318,11 +4496,13 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) ? X86EMUL_MODE_VM86 : cs_l ? X86EMUL_MODE_PROT64 : cs_db ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; + vcpu->arch.emulate_ctxt.guest_mode = is_guest_mode(vcpu); memset(c, 0, sizeof(struct decode_cache)); memcpy(c->regs, vcpu->arch.regs, sizeof c->regs); + vcpu->arch.emulate_regs_need_sync_from_vcpu = false; } -int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq) +int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) { struct decode_cache *c = &vcpu->arch.emulate_ctxt.decode; int ret; @@ -4331,7 +4511,8 @@ int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq) vcpu->arch.emulate_ctxt.decode.op_bytes = 2; vcpu->arch.emulate_ctxt.decode.ad_bytes = 2; - vcpu->arch.emulate_ctxt.decode.eip = vcpu->arch.emulate_ctxt.eip; + vcpu->arch.emulate_ctxt.decode.eip = vcpu->arch.emulate_ctxt.eip + + inc_eip; ret = emulate_int_real(&vcpu->arch.emulate_ctxt, &emulate_ops, irq); if (ret != X86EMUL_CONTINUE) @@ -4340,7 +4521,7 @@ int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq) vcpu->arch.emulate_ctxt.eip = c->eip; memcpy(vcpu->arch.regs, c->regs, sizeof c->regs); kvm_rip_write(vcpu, vcpu->arch.emulate_ctxt.eip); - kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); + kvm_set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); if (irq == NMI_VECTOR) vcpu->arch.nmi_pending = false; @@ -4402,16 +4583,9 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, { int r; struct decode_cache *c = &vcpu->arch.emulate_ctxt.decode; + bool writeback = true; kvm_clear_exception_queue(vcpu); - vcpu->arch.mmio_fault_cr2 = cr2; - /* - * 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. - */ - cache_all_regs(vcpu); if (!(emulation_type & EMULTYPE_NO_DECODE)) { init_emulate_ctxt(vcpu); @@ -4442,13 +4616,19 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, return EMULATE_DONE; } - /* this is needed for vmware backdor interface to work since it + /* this is needed for vmware backdoor interface to work since it changes registers values during IO operation */ - memcpy(c->regs, vcpu->arch.regs, sizeof c->regs); + if (vcpu->arch.emulate_regs_need_sync_from_vcpu) { + vcpu->arch.emulate_regs_need_sync_from_vcpu = false; + memcpy(c->regs, vcpu->arch.regs, sizeof c->regs); + } restart: r = x86_emulate_insn(&vcpu->arch.emulate_ctxt); + if (r == EMULATION_INTERCEPTED) + return EMULATE_DONE; + if (r == EMULATION_FAILED) { if (reexecute_instruction(vcpu, cr2)) return EMULATE_DONE; @@ -4462,21 +4642,28 @@ restart: } else if (vcpu->arch.pio.count) { if (!vcpu->arch.pio.in) vcpu->arch.pio.count = 0; + else + writeback = false; r = EMULATE_DO_MMIO; } else if (vcpu->mmio_needed) { - if (vcpu->mmio_is_write) - vcpu->mmio_needed = 0; + if (!vcpu->mmio_is_write) + writeback = false; r = EMULATE_DO_MMIO; } else if (r == EMULATION_RESTART) goto restart; else r = EMULATE_DONE; - toggle_interruptibility(vcpu, vcpu->arch.emulate_ctxt.interruptibility); - kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); - kvm_make_request(KVM_REQ_EVENT, vcpu); - memcpy(vcpu->arch.regs, c->regs, sizeof c->regs); - kvm_rip_write(vcpu, vcpu->arch.emulate_ctxt.eip); + if (writeback) { + toggle_interruptibility(vcpu, + vcpu->arch.emulate_ctxt.interruptibility); + kvm_set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); + kvm_make_request(KVM_REQ_EVENT, vcpu); + memcpy(vcpu->arch.regs, c->regs, sizeof c->regs); + vcpu->arch.emulate_regs_need_sync_to_vcpu = false; + kvm_rip_write(vcpu, vcpu->arch.emulate_ctxt.eip); + } else + vcpu->arch.emulate_regs_need_sync_to_vcpu = true; return r; } @@ -4485,7 +4672,8 @@ EXPORT_SYMBOL_GPL(x86_emulate_instruction); int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port) { unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX); - int ret = emulator_pio_out_emulated(size, port, &val, 1, vcpu); + int ret = emulator_pio_out_emulated(&vcpu->arch.emulate_ctxt, + size, port, &val, 1); /* do not return to emulator after return from userspace */ vcpu->arch.pio.count = 0; return ret; @@ -4879,8 +5067,9 @@ out: } EXPORT_SYMBOL_GPL(kvm_emulate_hypercall); -int kvm_fix_hypercall(struct kvm_vcpu *vcpu) +int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) { + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); char instruction[3]; unsigned long rip = kvm_rip_read(vcpu); @@ -4893,21 +5082,8 @@ int kvm_fix_hypercall(struct kvm_vcpu *vcpu) kvm_x86_ops->patch_hypercall(vcpu, instruction); - return emulator_write_emulated(rip, instruction, 3, NULL, vcpu); -} - -void realmode_lgdt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base) -{ - struct desc_ptr dt = { limit, base }; - - kvm_x86_ops->set_gdt(vcpu, &dt); -} - -void realmode_lidt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base) -{ - struct desc_ptr dt = { limit, base }; - - kvm_x86_ops->set_idt(vcpu, &dt); + return emulator_write_emulated(&vcpu->arch.emulate_ctxt, + rip, instruction, 3, NULL); } static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i) @@ -5170,6 +5346,7 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) static int vcpu_enter_guest(struct kvm_vcpu *vcpu) { int r; + bool nmi_pending; bool req_int_win = !irqchip_in_kernel(vcpu->kvm) && vcpu->run->request_interrupt_window; @@ -5207,19 +5384,25 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) r = 1; goto out; } - if (kvm_check_request(KVM_REQ_NMI, vcpu)) - vcpu->arch.nmi_pending = true; } r = kvm_mmu_reload(vcpu); if (unlikely(r)) goto out; + /* + * An NMI can be injected between local nmi_pending read and + * vcpu->arch.nmi_pending read inside inject_pending_event(). + * But in that case, KVM_REQ_EVENT will be set, which makes + * the race described above benign. + */ + nmi_pending = ACCESS_ONCE(vcpu->arch.nmi_pending); + if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { inject_pending_event(vcpu); /* enable NMI/IRQ window open exits if needed */ - if (vcpu->arch.nmi_pending) + if (nmi_pending) kvm_x86_ops->enable_nmi_window(vcpu); else if (kvm_cpu_has_interrupt(vcpu) || req_int_win) kvm_x86_ops->enable_irq_window(vcpu); @@ -5399,6 +5582,41 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) return r; } +static int complete_mmio(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + int r; + + if (!(vcpu->arch.pio.count || vcpu->mmio_needed)) + return 1; + + if (vcpu->mmio_needed) { + vcpu->mmio_needed = 0; + if (!vcpu->mmio_is_write) + memcpy(vcpu->mmio_data + vcpu->mmio_index, + run->mmio.data, 8); + vcpu->mmio_index += 8; + if (vcpu->mmio_index < vcpu->mmio_size) { + run->exit_reason = KVM_EXIT_MMIO; + run->mmio.phys_addr = vcpu->mmio_phys_addr + vcpu->mmio_index; + memcpy(run->mmio.data, vcpu->mmio_data + vcpu->mmio_index, 8); + run->mmio.len = min(vcpu->mmio_size - vcpu->mmio_index, 8); + run->mmio.is_write = vcpu->mmio_is_write; + vcpu->mmio_needed = 1; + return 0; + } + if (vcpu->mmio_is_write) + return 1; + vcpu->mmio_read_completed = 1; + } + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + r = emulate_instruction(vcpu, EMULTYPE_NO_DECODE); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + if (r != EMULATE_DONE) + return 0; + return 1; +} + int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { int r; @@ -5425,20 +5643,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } } - if (vcpu->arch.pio.count || vcpu->mmio_needed) { - if (vcpu->mmio_needed) { - memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8); - vcpu->mmio_read_completed = 1; - vcpu->mmio_needed = 0; - } - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); - r = emulate_instruction(vcpu, EMULTYPE_NO_DECODE); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - if (r != EMULATE_DONE) { - r = 0; - goto out; - } - } + r = complete_mmio(vcpu); + if (r <= 0) + goto out; + if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL) kvm_register_write(vcpu, VCPU_REGS_RAX, kvm_run->hypercall.ret); @@ -5455,6 +5663,18 @@ out: int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { + if (vcpu->arch.emulate_regs_need_sync_to_vcpu) { + /* + * We are here if userspace calls get_regs() in the middle of + * instruction emulation. Registers state needs to be copied + * back from emulation context to vcpu. Usrapace shouldn't do + * that usually, but some bad designed PV devices (vmware + * backdoor interface) need this to work + */ + struct decode_cache *c = &vcpu->arch.emulate_ctxt.decode; + memcpy(vcpu->arch.regs, c->regs, sizeof c->regs); + vcpu->arch.emulate_regs_need_sync_to_vcpu = false; + } regs->rax = kvm_register_read(vcpu, VCPU_REGS_RAX); regs->rbx = kvm_register_read(vcpu, VCPU_REGS_RBX); regs->rcx = kvm_register_read(vcpu, VCPU_REGS_RCX); @@ -5482,6 +5702,9 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { + vcpu->arch.emulate_regs_need_sync_from_vcpu = true; + vcpu->arch.emulate_regs_need_sync_to_vcpu = false; + kvm_register_write(vcpu, VCPU_REGS_RAX, regs->rax); kvm_register_write(vcpu, VCPU_REGS_RBX, regs->rbx); kvm_register_write(vcpu, VCPU_REGS_RCX, regs->rcx); @@ -5592,7 +5815,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason, memcpy(vcpu->arch.regs, c->regs, sizeof c->regs); kvm_rip_write(vcpu, vcpu->arch.emulate_ctxt.eip); - kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); + kvm_set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); kvm_make_request(KVM_REQ_EVENT, vcpu); return EMULATE_DONE; } @@ -5974,8 +6197,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) } vcpu->arch.pio_data = page_address(page); - if (!kvm->arch.virtual_tsc_khz) - kvm_arch_set_tsc_khz(kvm, max_tsc_khz); + kvm_init_tsc_catchup(vcpu, max_tsc_khz); r = kvm_mmu_create(vcpu); if (r < 0) diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index c600da830ce0..e407ed3df817 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -77,7 +77,7 @@ static inline u32 bit(int bitno) void kvm_before_handle_nmi(struct kvm_vcpu *vcpu); void kvm_after_handle_nmi(struct kvm_vcpu *vcpu); -int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq); +int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip); void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data); diff --git a/include/linux/kvm.h b/include/linux/kvm.h index ea2dc1a2e13d..55ef181521ff 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -541,6 +541,9 @@ struct kvm_ppc_pvinfo { #define KVM_CAP_PPC_GET_PVINFO 57 #define KVM_CAP_PPC_IRQ_LEVEL 58 #define KVM_CAP_ASYNC_PF 59 +#define KVM_CAP_TSC_CONTROL 60 +#define KVM_CAP_GET_TSC_KHZ 61 +#define KVM_CAP_PPC_BOOKE_SREGS 62 #ifdef KVM_CAP_IRQ_ROUTING @@ -677,6 +680,9 @@ struct kvm_clock_data { #define KVM_SET_PIT2 _IOW(KVMIO, 0xa0, struct kvm_pit_state2) /* Available with KVM_CAP_PPC_GET_PVINFO */ #define KVM_PPC_GET_PVINFO _IOW(KVMIO, 0xa1, struct kvm_ppc_pvinfo) +/* Available with KVM_CAP_TSC_CONTROL */ +#define KVM_SET_TSC_KHZ _IO(KVMIO, 0xa2) +#define KVM_GET_TSC_KHZ _IO(KVMIO, 0xa3) /* * ioctls for vcpu fds diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ab428552af8e..b9c3299c6a55 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -27,6 +27,10 @@ #include <asm/kvm_host.h> +#ifndef KVM_MMIO_SIZE +#define KVM_MMIO_SIZE 8 +#endif + /* * vcpu->requests bit members */ @@ -43,7 +47,6 @@ #define KVM_REQ_DEACTIVATE_FPU 10 #define KVM_REQ_EVENT 11 #define KVM_REQ_APF_HALT 12 -#define KVM_REQ_NMI 13 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 @@ -133,7 +136,8 @@ struct kvm_vcpu { int mmio_read_completed; int mmio_is_write; int mmio_size; - unsigned char mmio_data[8]; + int mmio_index; + unsigned char mmio_data[KVM_MMIO_SIZE]; gpa_t mmio_phys_addr; #endif @@ -292,9 +296,10 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) } #define kvm_for_each_vcpu(idx, vcpup, kvm) \ - for (idx = 0, vcpup = kvm_get_vcpu(kvm, idx); \ - idx < atomic_read(&kvm->online_vcpus) && vcpup; \ - vcpup = kvm_get_vcpu(kvm, ++idx)) + for (idx = 0; \ + idx < atomic_read(&kvm->online_vcpus) && \ + (vcpup = kvm_get_vcpu(kvm, idx)) != NULL; \ + idx++) int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id); void kvm_vcpu_uninit(struct kvm_vcpu *vcpu); @@ -365,7 +370,6 @@ pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, bool *writable); pfn_t gfn_to_pfn_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn); -int memslot_id(struct kvm *kvm, gfn_t gfn); void kvm_release_pfn_dirty(pfn_t); void kvm_release_pfn_clean(pfn_t pfn); void kvm_set_pfn_dirty(pfn_t pfn); @@ -587,8 +591,17 @@ static inline int kvm_deassign_device(struct kvm *kvm, static inline void kvm_guest_enter(void) { + BUG_ON(preemptible()); account_system_vtime(current); current->flags |= PF_VCPU; + /* KVM does not hold any references to rcu protected data when it + * switches CPU into a guest mode. In fact switching to a guest mode + * is very similar to exiting to userspase from rcu point of view. In + * addition CPU may stay in a guest mode for quite a long time (up to + * one time slice). Lets treat guest mode as quiescent state, just like + * we do with user-mode execution. + */ + rcu_virt_note_context_switch(smp_processor_id()); } static inline void kvm_guest_exit(void) @@ -597,6 +610,11 @@ static inline void kvm_guest_exit(void) current->flags &= ~PF_VCPU; } +static inline int memslot_id(struct kvm *kvm, gfn_t gfn) +{ + return gfn_to_memslot(kvm, gfn)->id; +} + static inline unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index 0b9df8303dcf..8df1ca104a7f 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -167,7 +167,7 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq) ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x " "vector=%x trig_mode=%x\n", - entry->fields.dest, entry->fields.dest_mode, + entry->fields.dest_id, entry->fields.dest_mode, entry->fields.delivery_mode, entry->fields.vector, entry->fields.trig_mode); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 6330653480e4..22cdb960660a 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -467,6 +467,7 @@ static struct kvm *kvm_create_vm(void) if (!kvm->buses[i]) goto out_err; } + spin_lock_init(&kvm->mmu_lock); r = kvm_init_mmu_notifier(kvm); if (r) @@ -474,7 +475,6 @@ static struct kvm *kvm_create_vm(void) kvm->mm = current->mm; atomic_inc(&kvm->mm->mm_count); - spin_lock_init(&kvm->mmu_lock); kvm_eventfd_init(kvm); mutex_init(&kvm->lock); mutex_init(&kvm->irq_lock); @@ -648,7 +648,10 @@ int __kvm_set_memory_region(struct kvm *kvm, goto out; if (mem->guest_phys_addr & (PAGE_SIZE - 1)) goto out; - if (user_alloc && (mem->userspace_addr & (PAGE_SIZE - 1))) + /* We can read the guest memory with __xxx_user() later on. */ + if (user_alloc && + ((mem->userspace_addr & (PAGE_SIZE - 1)) || + !access_ok(VERIFY_WRITE, mem->userspace_addr, mem->memory_size))) goto out; if (mem->slot >= KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS) goto out; @@ -996,23 +999,6 @@ out: return size; } -int memslot_id(struct kvm *kvm, gfn_t gfn) -{ - int i; - struct kvm_memslots *slots = kvm_memslots(kvm); - struct kvm_memory_slot *memslot = NULL; - - for (i = 0; i < slots->nmemslots; ++i) { - memslot = &slots->memslots[i]; - - if (gfn >= memslot->base_gfn - && gfn < memslot->base_gfn + memslot->npages) - break; - } - - return memslot - slots->memslots; -} - static unsigned long gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn, gfn_t *nr_pages) { @@ -1300,7 +1286,7 @@ int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, addr = gfn_to_hva(kvm, gfn); if (kvm_is_error_hva(addr)) return -EFAULT; - r = copy_from_user(data, (void __user *)addr + offset, len); + r = __copy_from_user(data, (void __user *)addr + offset, len); if (r) return -EFAULT; return 0; |