diff options
Diffstat (limited to 'arch')
158 files changed, 5357 insertions, 2291 deletions
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index c0b178d1bb4f..a51e6e8f3171 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -16,6 +16,15 @@ #define CLIDR_LOC(clidr) (((clidr) >> CLIDR_LOC_SHIFT) & 0x7) #define CLIDR_LOUIS(clidr) (((clidr) >> CLIDR_LOUIS_SHIFT) & 0x7) +/* Ctypen, bits[3(n - 1) + 2 : 3(n - 1)], for n = 1 to 7 */ +#define CLIDR_CTYPE_SHIFT(level) (3 * (level - 1)) +#define CLIDR_CTYPE_MASK(level) (7 << CLIDR_CTYPE_SHIFT(level)) +#define CLIDR_CTYPE(clidr, level) \ + (((clidr) & CLIDR_CTYPE_MASK(level)) >> CLIDR_CTYPE_SHIFT(level)) + +/* Ttypen, bits [2(n - 1) + 34 : 2(n - 1) + 33], for n = 1 to 7 */ +#define CLIDR_TTYPE_SHIFT(level) (2 * ((level) - 1) + CLIDR_EL1_Ttypen_SHIFT) + /* * Memory returned by kmalloc() may be used for DMA, so we must make * sure that all such allocations are cache aligned. Otherwise, diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index 2cdd010f9524..037724b19c5c 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -196,4 +196,103 @@ __init_el2_nvhe_prepare_eret .endm +#ifndef __KVM_NVHE_HYPERVISOR__ +// This will clobber tmp1 and tmp2, and expect tmp1 to contain +// the id register value as read from the HW +.macro __check_override idreg, fld, width, pass, fail, tmp1, tmp2 + ubfx \tmp1, \tmp1, #\fld, #\width + cbz \tmp1, \fail + + adr_l \tmp1, \idreg\()_override + ldr \tmp2, [\tmp1, FTR_OVR_VAL_OFFSET] + ldr \tmp1, [\tmp1, FTR_OVR_MASK_OFFSET] + ubfx \tmp2, \tmp2, #\fld, #\width + ubfx \tmp1, \tmp1, #\fld, #\width + cmp \tmp1, xzr + and \tmp2, \tmp2, \tmp1 + csinv \tmp2, \tmp2, xzr, ne + cbnz \tmp2, \pass + b \fail +.endm + +// This will clobber tmp1 and tmp2 +.macro check_override idreg, fld, pass, fail, tmp1, tmp2 + mrs \tmp1, \idreg\()_el1 + __check_override \idreg \fld 4 \pass \fail \tmp1 \tmp2 +.endm +#else +// This will clobber tmp +.macro __check_override idreg, fld, width, pass, fail, tmp, ignore + ldr_l \tmp, \idreg\()_el1_sys_val + ubfx \tmp, \tmp, #\fld, #\width + cbnz \tmp, \pass + b \fail +.endm + +.macro check_override idreg, fld, pass, fail, tmp, ignore + __check_override \idreg \fld 4 \pass \fail \tmp \ignore +.endm +#endif + +.macro finalise_el2_state + check_override id_aa64pfr0, ID_AA64PFR0_EL1_SVE_SHIFT, .Linit_sve_\@, .Lskip_sve_\@, x1, x2 + +.Linit_sve_\@: /* SVE register access */ + mrs x0, cptr_el2 // Disable SVE traps + bic x0, x0, #CPTR_EL2_TZ + msr cptr_el2, x0 + isb + mov x1, #ZCR_ELx_LEN_MASK // SVE: Enable full vector + msr_s SYS_ZCR_EL2, x1 // length for EL1. + +.Lskip_sve_\@: + check_override id_aa64pfr1, ID_AA64PFR1_EL1_SME_SHIFT, .Linit_sme_\@, .Lskip_sme_\@, x1, x2 + +.Linit_sme_\@: /* SME register access and priority mapping */ + mrs x0, cptr_el2 // Disable SME traps + bic x0, x0, #CPTR_EL2_TSM + msr cptr_el2, x0 + isb + + mrs x1, sctlr_el2 + orr x1, x1, #SCTLR_ELx_ENTP2 // Disable TPIDR2 traps + msr sctlr_el2, x1 + isb + + mov x0, #0 // SMCR controls + + // Full FP in SM? + mrs_s x1, SYS_ID_AA64SMFR0_EL1 + __check_override id_aa64smfr0, ID_AA64SMFR0_EL1_FA64_SHIFT, 1, .Linit_sme_fa64_\@, .Lskip_sme_fa64_\@, x1, x2 + +.Linit_sme_fa64_\@: + orr x0, x0, SMCR_ELx_FA64_MASK +.Lskip_sme_fa64_\@: + + // ZT0 available? + mrs_s x1, SYS_ID_AA64SMFR0_EL1 + __check_override id_aa64smfr0, ID_AA64SMFR0_EL1_SMEver_SHIFT, 4, .Linit_sme_zt0_\@, .Lskip_sme_zt0_\@, x1, x2 +.Linit_sme_zt0_\@: + orr x0, x0, SMCR_ELx_EZT0_MASK +.Lskip_sme_zt0_\@: + + orr x0, x0, #SMCR_ELx_LEN_MASK // Enable full SME vector + msr_s SYS_SMCR_EL2, x0 // length for EL1. + + mrs_s x1, SYS_SMIDR_EL1 // Priority mapping supported? + ubfx x1, x1, #SMIDR_EL1_SMPS_SHIFT, #1 + cbz x1, .Lskip_sme_\@ + + msr_s SYS_SMPRIMAP_EL2, xzr // Make all priorities equal + + mrs x1, id_aa64mmfr1_el1 // HCRX_EL2 present? + ubfx x1, x1, #ID_AA64MMFR1_EL1_HCX_SHIFT, #4 + cbz x1, .Lskip_sme_\@ + + mrs_s x1, SYS_HCRX_EL2 + orr x1, x1, #HCRX_EL2_SMPME_MASK // Enable priority mapping + msr_s SYS_HCRX_EL2, x1 +.Lskip_sme_\@: +.endm + #endif /* __ARM_KVM_INIT_H__ */ diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index c9f15b9e3c71..8487aec9b658 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -272,6 +272,10 @@ (((e) & ESR_ELx_SYS64_ISS_OP2_MASK) >> \ ESR_ELx_SYS64_ISS_OP2_SHIFT)) +/* ISS field definitions for ERET/ERETAA/ERETAB trapping */ +#define ESR_ELx_ERET_ISS_ERET 0x2 +#define ESR_ELx_ERET_ISS_ERETA 0x1 + /* * ISS field definitions for floating-point exception traps * (FP_EXC_32/FP_EXC_64). diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 26b0c97df986..baef29fcbeee 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -81,11 +81,12 @@ * SWIO: Turn set/way invalidates into set/way clean+invalidate * PTW: Take a stage2 fault if a stage1 walk steps in device memory * TID3: Trap EL1 reads of group 3 ID registers + * TID2: Trap CTR_EL0, CCSIDR2_EL1, CLIDR_EL1, and CSSELR_EL1 */ #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \ HCR_BSU_IS | HCR_FB | HCR_TACR | \ HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \ - HCR_FMO | HCR_IMO | HCR_PTW | HCR_TID3 ) + HCR_FMO | HCR_IMO | HCR_PTW | HCR_TID3 | HCR_TID2) #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF) #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK | HCR_ATA) #define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC) @@ -344,10 +345,26 @@ ECN(SP_ALIGN), ECN(FP_EXC32), ECN(FP_EXC64), ECN(SERROR), \ ECN(BREAKPT_LOW), ECN(BREAKPT_CUR), ECN(SOFTSTP_LOW), \ ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \ - ECN(BKPT32), ECN(VECTOR32), ECN(BRK64) + ECN(BKPT32), ECN(VECTOR32), ECN(BRK64), ECN(ERET) -#define CPACR_EL1_TTA (1 << 28) #define CPACR_EL1_DEFAULT (CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN |\ CPACR_EL1_ZEN_EL1EN) +#define kvm_mode_names \ + { PSR_MODE_EL0t, "EL0t" }, \ + { PSR_MODE_EL1t, "EL1t" }, \ + { PSR_MODE_EL1h, "EL1h" }, \ + { PSR_MODE_EL2t, "EL2t" }, \ + { PSR_MODE_EL2h, "EL2h" }, \ + { PSR_MODE_EL3t, "EL3t" }, \ + { PSR_MODE_EL3h, "EL3h" }, \ + { PSR_AA32_MODE_USR, "32-bit USR" }, \ + { PSR_AA32_MODE_FIQ, "32-bit FIQ" }, \ + { PSR_AA32_MODE_IRQ, "32-bit IRQ" }, \ + { PSR_AA32_MODE_SVC, "32-bit SVC" }, \ + { PSR_AA32_MODE_ABT, "32-bit ABT" }, \ + { PSR_AA32_MODE_HYP, "32-bit HYP" }, \ + { PSR_AA32_MODE_UND, "32-bit UND" }, \ + { PSR_AA32_MODE_SYS, "32-bit SYS" } + #endif /* __ARM64_KVM_ARM_H__ */ diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 193583df2d9c..b31b32ecbe2d 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -33,6 +33,12 @@ enum exception_type { except_type_serror = 0x180, }; +#define kvm_exception_type_names \ + { except_type_sync, "SYNC" }, \ + { except_type_irq, "IRQ" }, \ + { except_type_fiq, "FIQ" }, \ + { except_type_serror, "SERROR" } + bool kvm_condition_valid32(const struct kvm_vcpu *vcpu); void kvm_skip_instr32(struct kvm_vcpu *vcpu); @@ -44,6 +50,10 @@ void kvm_inject_size_fault(struct kvm_vcpu *vcpu); void kvm_vcpu_wfi(struct kvm_vcpu *vcpu); +void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu); +int kvm_inject_nested_sync(struct kvm_vcpu *vcpu, u64 esr_el2); +int kvm_inject_nested_irq(struct kvm_vcpu *vcpu); + #if defined(__KVM_VHE_HYPERVISOR__) || defined(__KVM_NVHE_HYPERVISOR__) static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) { @@ -88,10 +98,6 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) if (vcpu_el1_is_32bit(vcpu)) vcpu->arch.hcr_el2 &= ~HCR_RW; - if (cpus_have_const_cap(ARM64_MISMATCHED_CACHE_TYPE) || - vcpu_el1_is_32bit(vcpu)) - vcpu->arch.hcr_el2 |= HCR_TID2; - if (kvm_has_mte(vcpu->kvm)) vcpu->arch.hcr_el2 |= HCR_ATA; } @@ -183,6 +189,62 @@ static __always_inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num, vcpu_gp_regs(vcpu)->regs[reg_num] = val; } +static inline bool vcpu_is_el2_ctxt(const struct kvm_cpu_context *ctxt) +{ + switch (ctxt->regs.pstate & (PSR_MODE32_BIT | PSR_MODE_MASK)) { + case PSR_MODE_EL2h: + case PSR_MODE_EL2t: + return true; + default: + return false; + } +} + +static inline bool vcpu_is_el2(const struct kvm_vcpu *vcpu) +{ + return vcpu_is_el2_ctxt(&vcpu->arch.ctxt); +} + +static inline bool __vcpu_el2_e2h_is_set(const struct kvm_cpu_context *ctxt) +{ + return ctxt_sys_reg(ctxt, HCR_EL2) & HCR_E2H; +} + +static inline bool vcpu_el2_e2h_is_set(const struct kvm_vcpu *vcpu) +{ + return __vcpu_el2_e2h_is_set(&vcpu->arch.ctxt); +} + +static inline bool __vcpu_el2_tge_is_set(const struct kvm_cpu_context *ctxt) +{ + return ctxt_sys_reg(ctxt, HCR_EL2) & HCR_TGE; +} + +static inline bool vcpu_el2_tge_is_set(const struct kvm_vcpu *vcpu) +{ + return __vcpu_el2_tge_is_set(&vcpu->arch.ctxt); +} + +static inline bool __is_hyp_ctxt(const struct kvm_cpu_context *ctxt) +{ + /* + * We are in a hypervisor context if the vcpu mode is EL2 or + * E2H and TGE bits are set. The latter means we are in the user space + * of the VHE kernel. ARMv8.1 ARM describes this as 'InHost' + * + * Note that the HCR_EL2.{E2H,TGE}={0,1} isn't really handled in the + * rest of the KVM code, and will result in a misbehaving guest. + */ + return vcpu_is_el2_ctxt(ctxt) || + (__vcpu_el2_e2h_is_set(ctxt) && __vcpu_el2_tge_is_set(ctxt)) || + __vcpu_el2_tge_is_set(ctxt); +} + +static inline bool is_hyp_ctxt(const struct kvm_vcpu *vcpu) +{ + return __is_hyp_ctxt(&vcpu->arch.ctxt); +} + /* * The layout of SPSR for an AArch32 state is different when observed from an * AArch64 SPSR_ELx or an AArch32 SPSR_*. This function generates the AArch32 diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 35a159d131b5..a1892a8f6032 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -60,14 +60,19 @@ enum kvm_mode { KVM_MODE_DEFAULT, KVM_MODE_PROTECTED, + KVM_MODE_NV, KVM_MODE_NONE, }; +#ifdef CONFIG_KVM enum kvm_mode kvm_get_mode(void); +#else +static inline enum kvm_mode kvm_get_mode(void) { return KVM_MODE_NONE; }; +#endif DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); -extern unsigned int kvm_sve_max_vl; -int kvm_arm_init_sve(void); +extern unsigned int __ro_after_init kvm_sve_max_vl; +int __init kvm_arm_init_sve(void); u32 __attribute_const__ kvm_target_cpu(void); int kvm_reset_vcpu(struct kvm_vcpu *vcpu); @@ -252,6 +257,7 @@ struct kvm_vcpu_fault_info { enum vcpu_sysreg { __INVALID_SYSREG__, /* 0 is reserved as an invalid value */ MPIDR_EL1, /* MultiProcessor Affinity Register */ + CLIDR_EL1, /* Cache Level ID Register */ CSSELR_EL1, /* Cache Size Selection Register */ SCTLR_EL1, /* System Control Register */ ACTLR_EL1, /* Auxiliary Control Register */ @@ -320,12 +326,43 @@ enum vcpu_sysreg { TFSR_EL1, /* Tag Fault Status Register (EL1) */ TFSRE0_EL1, /* Tag Fault Status Register (EL0) */ - /* 32bit specific registers. Keep them at the end of the range */ + /* 32bit specific registers. */ DACR32_EL2, /* Domain Access Control Register */ IFSR32_EL2, /* Instruction Fault Status Register */ FPEXC32_EL2, /* Floating-Point Exception Control Register */ DBGVCR32_EL2, /* Debug Vector Catch Register */ + /* EL2 registers */ + VPIDR_EL2, /* Virtualization Processor ID Register */ + VMPIDR_EL2, /* Virtualization Multiprocessor ID Register */ + SCTLR_EL2, /* System Control Register (EL2) */ + ACTLR_EL2, /* Auxiliary Control Register (EL2) */ + HCR_EL2, /* Hypervisor Configuration Register */ + MDCR_EL2, /* Monitor Debug Configuration Register (EL2) */ + CPTR_EL2, /* Architectural Feature Trap Register (EL2) */ + HSTR_EL2, /* Hypervisor System Trap Register */ + HACR_EL2, /* Hypervisor Auxiliary Control Register */ + TTBR0_EL2, /* Translation Table Base Register 0 (EL2) */ + TTBR1_EL2, /* Translation Table Base Register 1 (EL2) */ + TCR_EL2, /* Translation Control Register (EL2) */ + VTTBR_EL2, /* Virtualization Translation Table Base Register */ + VTCR_EL2, /* Virtualization Translation Control Register */ + SPSR_EL2, /* EL2 saved program status register */ + ELR_EL2, /* EL2 exception link register */ + AFSR0_EL2, /* Auxiliary Fault Status Register 0 (EL2) */ + AFSR1_EL2, /* Auxiliary Fault Status Register 1 (EL2) */ + ESR_EL2, /* Exception Syndrome Register (EL2) */ + FAR_EL2, /* Fault Address Register (EL2) */ + HPFAR_EL2, /* Hypervisor IPA Fault Address Register */ + MAIR_EL2, /* Memory Attribute Indirection Register (EL2) */ + AMAIR_EL2, /* Auxiliary Memory Attribute Indirection Register (EL2) */ + VBAR_EL2, /* Vector Base Address Register (EL2) */ + RVBAR_EL2, /* Reset Vector Base Address Register */ + CONTEXTIDR_EL2, /* Context ID Register (EL2) */ + TPIDR_EL2, /* EL2 Software Thread ID Register */ + CNTHCTL_EL2, /* Counter-timer Hypervisor Control register */ + SP_EL2, /* EL2 Stack Pointer */ + NR_SYS_REGS /* Nothing after this line! */ }; @@ -501,6 +538,9 @@ struct kvm_vcpu_arch { u64 last_steal; gpa_t base; } steal; + + /* Per-vcpu CCSIDR override or NULL */ + u32 *ccsidr; }; /* @@ -598,7 +638,7 @@ struct kvm_vcpu_arch { #define EXCEPT_AA64_EL1_IRQ __vcpu_except_flags(1) #define EXCEPT_AA64_EL1_FIQ __vcpu_except_flags(2) #define EXCEPT_AA64_EL1_SERR __vcpu_except_flags(3) -/* For AArch64 with NV (one day): */ +/* For AArch64 with NV: */ #define EXCEPT_AA64_EL2_SYNC __vcpu_except_flags(4) #define EXCEPT_AA64_EL2_IRQ __vcpu_except_flags(5) #define EXCEPT_AA64_EL2_FIQ __vcpu_except_flags(6) @@ -609,6 +649,8 @@ struct kvm_vcpu_arch { #define DEBUG_STATE_SAVE_SPE __vcpu_single_flag(iflags, BIT(5)) /* Save TRBE context if active */ #define DEBUG_STATE_SAVE_TRBE __vcpu_single_flag(iflags, BIT(6)) +/* vcpu running in HYP context */ +#define VCPU_HYP_CONTEXT __vcpu_single_flag(iflags, BIT(7)) /* SVE enabled for host EL0 */ #define HOST_SVE_ENABLED __vcpu_single_flag(sflags, BIT(0)) @@ -705,7 +747,6 @@ static inline bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val) return false; switch (reg) { - case CSSELR_EL1: *val = read_sysreg_s(SYS_CSSELR_EL1); break; case SCTLR_EL1: *val = read_sysreg_s(SYS_SCTLR_EL12); break; case CPACR_EL1: *val = read_sysreg_s(SYS_CPACR_EL12); break; case TTBR0_EL1: *val = read_sysreg_s(SYS_TTBR0_EL12); break; @@ -750,7 +791,6 @@ static inline bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg) return false; switch (reg) { - case CSSELR_EL1: write_sysreg_s(val, SYS_CSSELR_EL1); break; case SCTLR_EL1: write_sysreg_s(val, SYS_SCTLR_EL12); break; case CPACR_EL1: write_sysreg_s(val, SYS_CPACR_EL12); break; case TTBR0_EL1: write_sysreg_s(val, SYS_TTBR0_EL12); break; @@ -877,7 +917,7 @@ int kvm_handle_cp10_id(struct kvm_vcpu *vcpu); void kvm_reset_sys_regs(struct kvm_vcpu *vcpu); -int kvm_sys_reg_table_init(void); +int __init kvm_sys_reg_table_init(void); /* MMIO helpers */ void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data); @@ -908,20 +948,20 @@ int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu, int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); -extern unsigned int kvm_arm_vmid_bits; -int kvm_arm_vmid_alloc_init(void); -void kvm_arm_vmid_alloc_free(void); +extern unsigned int __ro_after_init kvm_arm_vmid_bits; +int __init kvm_arm_vmid_alloc_init(void); +void __init kvm_arm_vmid_alloc_free(void); void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid); void kvm_arm_vmid_clear_active(void); static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch) { - vcpu_arch->steal.base = GPA_INVALID; + vcpu_arch->steal.base = INVALID_GPA; } static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch) { - return (vcpu_arch->steal.base != GPA_INVALID); + return (vcpu_arch->steal.base != INVALID_GPA); } void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 syndrome); @@ -943,7 +983,6 @@ static inline bool kvm_system_needs_idmapped_vectors(void) void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu); -static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} @@ -994,7 +1033,7 @@ static inline void kvm_clr_pmu_events(u32 clr) {} void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu); void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu); -int kvm_set_ipa_limit(void); +int __init kvm_set_ipa_limit(void); #define __KVM_HAVE_ARCH_VM_ALLOC struct kvm *kvm_arch_alloc_vm(void); diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index 6797eafe7890..bdd9cf546d95 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -122,6 +122,7 @@ extern u64 kvm_nvhe_sym(id_aa64isar2_el1_sys_val); extern u64 kvm_nvhe_sym(id_aa64mmfr0_el1_sys_val); extern u64 kvm_nvhe_sym(id_aa64mmfr1_el1_sys_val); extern u64 kvm_nvhe_sym(id_aa64mmfr2_el1_sys_val); +extern u64 kvm_nvhe_sym(id_aa64smfr0_el1_sys_val); extern unsigned long kvm_nvhe_sym(__icache_flags); extern unsigned int kvm_nvhe_sym(kvm_arm_vmid_bits); diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index e4a7e6369499..083cc47dca08 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -115,6 +115,7 @@ alternative_cb_end #include <asm/cache.h> #include <asm/cacheflush.h> #include <asm/mmu_context.h> +#include <asm/kvm_emulate.h> #include <asm/kvm_host.h> void kvm_update_va_mask(struct alt_instr *alt, @@ -163,7 +164,7 @@ int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size, void __iomem **haddr); int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size, void **haddr); -void free_hyp_pgds(void); +void __init free_hyp_pgds(void); void stage2_unmap_vm(struct kvm *kvm); int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type); @@ -175,7 +176,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu); phys_addr_t kvm_mmu_get_httbr(void); phys_addr_t kvm_get_idmap_vector(void); -int kvm_mmu_init(u32 *hyp_va_bits); +int __init kvm_mmu_init(u32 *hyp_va_bits); static inline void *__kvm_vector_slot2addr(void *base, enum arm64_hyp_spectre_vector slot) @@ -192,7 +193,15 @@ struct kvm; static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) { - return (vcpu_read_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101; + u64 cache_bits = SCTLR_ELx_M | SCTLR_ELx_C; + int reg; + + if (vcpu_is_el2(vcpu)) + reg = SCTLR_EL2; + else + reg = SCTLR_EL1; + + return (vcpu_read_sys_reg(vcpu, reg) & cache_bits) == cache_bits; } static inline void __clean_dcache_guest_page(void *va, size_t size) diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h new file mode 100644 index 000000000000..8fb67f032fd1 --- /dev/null +++ b/arch/arm64/include/asm/kvm_nested.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ARM64_KVM_NESTED_H +#define __ARM64_KVM_NESTED_H + +#include <linux/kvm_host.h> + +static inline bool vcpu_has_nv(const struct kvm_vcpu *vcpu) +{ + return (!__is_defined(__KVM_NVHE_HYPERVISOR__) && + cpus_have_final_cap(ARM64_HAS_NESTED_VIRT) && + test_bit(KVM_ARM_VCPU_HAS_EL2, vcpu->arch.features)); +} + +struct sys_reg_params; +struct sys_reg_desc; + +void access_nested_id_reg(struct kvm_vcpu *v, struct sys_reg_params *p, + const struct sys_reg_desc *r); + +#endif /* __ARM64_KVM_NESTED_H */ diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 63f81b27a4e3..4cd6762bda80 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -71,6 +71,11 @@ static inline kvm_pte_t kvm_phys_to_pte(u64 pa) return pte; } +static inline kvm_pfn_t kvm_pte_to_pfn(kvm_pte_t pte) +{ + return __phys_to_pfn(kvm_pte_to_phys(pte)); +} + static inline u64 kvm_granule_shift(u32 level) { /* Assumes KVM_PGTABLE_MAX_LEVELS is 4 */ @@ -188,12 +193,15 @@ typedef bool (*kvm_pgtable_force_pte_cb_t)(u64 addr, u64 end, * children. * @KVM_PGTABLE_WALK_SHARED: Indicates the page-tables may be shared * with other software walkers. + * @KVM_PGTABLE_WALK_HANDLE_FAULT: Indicates the page-table walk was + * invoked from a fault handler. */ enum kvm_pgtable_walk_flags { KVM_PGTABLE_WALK_LEAF = BIT(0), KVM_PGTABLE_WALK_TABLE_PRE = BIT(1), KVM_PGTABLE_WALK_TABLE_POST = BIT(2), KVM_PGTABLE_WALK_SHARED = BIT(3), + KVM_PGTABLE_WALK_HANDLE_FAULT = BIT(4), }; struct kvm_pgtable_visit_ctx { diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 043ecc3405e7..9e3ecba3c4e6 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -325,7 +325,6 @@ #define SYS_CNTKCTL_EL1 sys_reg(3, 0, 14, 1, 0) -#define SYS_CCSIDR_EL1 sys_reg(3, 1, 0, 0, 0) #define SYS_AIDR_EL1 sys_reg(3, 1, 0, 0, 7) #define SYS_RNDR_EL0 sys_reg(3, 3, 2, 4, 0) @@ -411,23 +410,51 @@ #define SYS_PMCCFILTR_EL0 sys_reg(3, 3, 14, 15, 7) +#define SYS_VPIDR_EL2 sys_reg(3, 4, 0, 0, 0) +#define SYS_VMPIDR_EL2 sys_reg(3, 4, 0, 0, 5) + #define SYS_SCTLR_EL2 sys_reg(3, 4, 1, 0, 0) +#define SYS_ACTLR_EL2 sys_reg(3, 4, 1, 0, 1) +#define SYS_HCR_EL2 sys_reg(3, 4, 1, 1, 0) +#define SYS_MDCR_EL2 sys_reg(3, 4, 1, 1, 1) +#define SYS_CPTR_EL2 sys_reg(3, 4, 1, 1, 2) +#define SYS_HSTR_EL2 sys_reg(3, 4, 1, 1, 3) #define SYS_HFGRTR_EL2 sys_reg(3, 4, 1, 1, 4) #define SYS_HFGWTR_EL2 sys_reg(3, 4, 1, 1, 5) #define SYS_HFGITR_EL2 sys_reg(3, 4, 1, 1, 6) +#define SYS_HACR_EL2 sys_reg(3, 4, 1, 1, 7) + +#define SYS_TTBR0_EL2 sys_reg(3, 4, 2, 0, 0) +#define SYS_TTBR1_EL2 sys_reg(3, 4, 2, 0, 1) +#define SYS_TCR_EL2 sys_reg(3, 4, 2, 0, 2) +#define SYS_VTTBR_EL2 sys_reg(3, 4, 2, 1, 0) +#define SYS_VTCR_EL2 sys_reg(3, 4, 2, 1, 2) + #define SYS_TRFCR_EL2 sys_reg(3, 4, 1, 2, 1) #define SYS_HDFGRTR_EL2 sys_reg(3, 4, 3, 1, 4) #define SYS_HDFGWTR_EL2 sys_reg(3, 4, 3, 1, 5) #define SYS_HAFGRTR_EL2 sys_reg(3, 4, 3, 1, 6) #define SYS_SPSR_EL2 sys_reg(3, 4, 4, 0, 0) #define SYS_ELR_EL2 sys_reg(3, 4, 4, 0, 1) +#define SYS_SP_EL1 sys_reg(3, 4, 4, 1, 0) #define SYS_IFSR32_EL2 sys_reg(3, 4, 5, 0, 1) +#define SYS_AFSR0_EL2 sys_reg(3, 4, 5, 1, 0) +#define SYS_AFSR1_EL2 sys_reg(3, 4, 5, 1, 1) #define SYS_ESR_EL2 sys_reg(3, 4, 5, 2, 0) #define SYS_VSESR_EL2 sys_reg(3, 4, 5, 2, 3) #define SYS_FPEXC32_EL2 sys_reg(3, 4, 5, 3, 0) #define SYS_TFSR_EL2 sys_reg(3, 4, 5, 6, 0) -#define SYS_VDISR_EL2 sys_reg(3, 4, 12, 1, 1) +#define SYS_FAR_EL2 sys_reg(3, 4, 6, 0, 0) +#define SYS_HPFAR_EL2 sys_reg(3, 4, 6, 0, 4) + +#define SYS_MAIR_EL2 sys_reg(3, 4, 10, 2, 0) +#define SYS_AMAIR_EL2 sys_reg(3, 4, 10, 3, 0) + +#define SYS_VBAR_EL2 sys_reg(3, 4, 12, 0, 0) +#define SYS_RVBAR_EL2 sys_reg(3, 4, 12, 0, 1) +#define SYS_RMR_EL2 sys_reg(3, 4, 12, 0, 2) +#define SYS_VDISR_EL2 sys_reg(3, 4, 12, 1, 1) #define __SYS__AP0Rx_EL2(x) sys_reg(3, 4, 12, 8, x) #define SYS_ICH_AP0R0_EL2 __SYS__AP0Rx_EL2(0) #define SYS_ICH_AP0R1_EL2 __SYS__AP0Rx_EL2(1) @@ -469,6 +496,12 @@ #define SYS_ICH_LR14_EL2 __SYS__LR8_EL2(6) #define SYS_ICH_LR15_EL2 __SYS__LR8_EL2(7) +#define SYS_CONTEXTIDR_EL2 sys_reg(3, 4, 13, 0, 1) +#define SYS_TPIDR_EL2 sys_reg(3, 4, 13, 0, 2) + +#define SYS_CNTVOFF_EL2 sys_reg(3, 4, 14, 0, 3) +#define SYS_CNTHCTL_EL2 sys_reg(3, 4, 14, 1, 0) + /* VHE encodings for architectural EL0/1 system registers */ #define SYS_SCTLR_EL12 sys_reg(3, 5, 1, 0, 0) #define SYS_TTBR0_EL12 sys_reg(3, 5, 2, 0, 0) @@ -491,6 +524,8 @@ #define SYS_CNTV_CTL_EL02 sys_reg(3, 5, 14, 3, 1) #define SYS_CNTV_CVAL_EL02 sys_reg(3, 5, 14, 3, 2) +#define SYS_SP_EL2 sys_reg(3, 6, 4, 1, 0) + /* Common SCTLR_ELx flags. */ #define SCTLR_ELx_ENTP2 (BIT(60)) #define SCTLR_ELx_DSSBS (BIT(44)) diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index a7a857f1784d..f8129c624b07 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -109,6 +109,7 @@ struct kvm_regs { #define KVM_ARM_VCPU_SVE 4 /* enable SVE for this CPU */ #define KVM_ARM_VCPU_PTRAUTH_ADDRESS 5 /* VCPU uses address authentication */ #define KVM_ARM_VCPU_PTRAUTH_GENERIC 6 /* VCPU uses generic authentication */ +#define KVM_ARM_VCPU_HAS_EL2 7 /* Support nested virtualization */ struct kvm_vcpu_init { __u32 target; diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c index 3ba70985e3a2..c307f69e9b55 100644 --- a/arch/arm64/kernel/cacheinfo.c +++ b/arch/arm64/kernel/cacheinfo.c @@ -11,11 +11,6 @@ #include <linux/of.h> #define MAX_CACHE_LEVEL 7 /* Max 7 level supported */ -/* Ctypen, bits[3(n - 1) + 2 : 3(n - 1)], for n = 1 to 7 */ -#define CLIDR_CTYPE_SHIFT(level) (3 * (level - 1)) -#define CLIDR_CTYPE_MASK(level) (7 << CLIDR_CTYPE_SHIFT(level)) -#define CLIDR_CTYPE(clidr, level) \ - (((clidr) & CLIDR_CTYPE_MASK(level)) >> CLIDR_CTYPE_SHIFT(level)) int cache_line_size(void) { diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 45a42cf2191c..87687e99fee3 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1967,6 +1967,20 @@ static void cpu_copy_el2regs(const struct arm64_cpu_capabilities *__unused) write_sysreg(read_sysreg(tpidr_el1), tpidr_el2); } +static bool has_nested_virt_support(const struct arm64_cpu_capabilities *cap, + int scope) +{ + if (kvm_get_mode() != KVM_MODE_NV) + return false; + + if (!has_cpuid_feature(cap, scope)) { + pr_warn("unavailable: %s\n", cap->desc); + return false; + } + + return true; +} + #ifdef CONFIG_ARM64_PAN static void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused) { @@ -2263,6 +2277,17 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .cpu_enable = cpu_copy_el2regs, }, { + .desc = "Nested Virtualization Support", + .capability = ARM64_HAS_NESTED_VIRT, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .matches = has_nested_virt_support, + .sys_reg = SYS_ID_AA64MMFR2_EL1, + .sign = FTR_UNSIGNED, + .field_pos = ID_AA64MMFR2_EL1_NV_SHIFT, + .field_width = 4, + .min_field_value = ID_AA64MMFR2_EL1_NV_IMP, + }, + { .capability = ARM64_HAS_32BIT_EL0_DO_NOT_USE, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_32bit_el0, diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S index 111ff33d93ee..9439240c3fcf 100644 --- a/arch/arm64/kernel/hyp-stub.S +++ b/arch/arm64/kernel/hyp-stub.S @@ -16,30 +16,6 @@ #include <asm/ptrace.h> #include <asm/virt.h> -// Warning, hardcoded register allocation -// This will clobber x1 and x2, and expect x1 to contain -// the id register value as read from the HW -.macro __check_override idreg, fld, width, pass, fail - ubfx x1, x1, #\fld, #\width - cbz x1, \fail - - adr_l x1, \idreg\()_override - ldr x2, [x1, FTR_OVR_VAL_OFFSET] - ldr x1, [x1, FTR_OVR_MASK_OFFSET] - ubfx x2, x2, #\fld, #\width - ubfx x1, x1, #\fld, #\width - cmp x1, xzr - and x2, x2, x1 - csinv x2, x2, xzr, ne - cbnz x2, \pass - b \fail -.endm - -.macro check_override idreg, fld, pass, fail - mrs x1, \idreg\()_el1 - __check_override \idreg \fld 4 \pass \fail -.endm - .text .pushsection .hyp.text, "ax" @@ -98,65 +74,7 @@ SYM_CODE_START_LOCAL(elx_sync) SYM_CODE_END(elx_sync) SYM_CODE_START_LOCAL(__finalise_el2) - check_override id_aa64pfr0 ID_AA64PFR0_EL1_SVE_SHIFT .Linit_sve .Lskip_sve - -.Linit_sve: /* SVE register access */ - mrs x0, cptr_el2 // Disable SVE traps - bic x0, x0, #CPTR_EL2_TZ - msr cptr_el2, x0 - isb - mov x1, #ZCR_ELx_LEN_MASK // SVE: Enable full vector - msr_s SYS_ZCR_EL2, x1 // length for EL1. - -.Lskip_sve: - check_override id_aa64pfr1 ID_AA64PFR1_EL1_SME_SHIFT .Linit_sme .Lskip_sme - -.Linit_sme: /* SME register access and priority mapping */ - mrs x0, cptr_el2 // Disable SME traps - bic x0, x0, #CPTR_EL2_TSM - msr cptr_el2, x0 - isb - - mrs x1, sctlr_el2 - orr x1, x1, #SCTLR_ELx_ENTP2 // Disable TPIDR2 traps - msr sctlr_el2, x1 - isb - - mov x0, #0 // SMCR controls - - // Full FP in SM? - mrs_s x1, SYS_ID_AA64SMFR0_EL1 - __check_override id_aa64smfr0 ID_AA64SMFR0_EL1_FA64_SHIFT 1 .Linit_sme_fa64 .Lskip_sme_fa64 - -.Linit_sme_fa64: - orr x0, x0, SMCR_ELx_FA64_MASK -.Lskip_sme_fa64: - - // ZT0 available? - mrs_s x1, SYS_ID_AA64SMFR0_EL1 - __check_override id_aa64smfr0 ID_AA64SMFR0_EL1_SMEver_SHIFT 4 .Linit_sme_zt0 .Lskip_sme_zt0 -.Linit_sme_zt0: - orr x0, x0, SMCR_ELx_EZT0_MASK -.Lskip_sme_zt0: - - orr x0, x0, #SMCR_ELx_LEN_MASK // Enable full SME vector - msr_s SYS_SMCR_EL2, x0 // length for EL1. - - mrs_s x1, SYS_SMIDR_EL1 // Priority mapping supported? - ubfx x1, x1, #SMIDR_EL1_SMPS_SHIFT, #1 - cbz x1, .Lskip_sme - - msr_s SYS_SMPRIMAP_EL2, xzr // Make all priorities equal - - mrs x1, id_aa64mmfr1_el1 // HCRX_EL2 present? - ubfx x1, x1, #ID_AA64MMFR1_EL1_HCX_SHIFT, #4 - cbz x1, .Lskip_sme - - mrs_s x1, SYS_HCRX_EL2 - orr x1, x1, #HCRX_EL2_SMPME_MASK // Enable priority mapping - msr_s SYS_HCRX_EL2, x1 - -.Lskip_sme: + finalise_el2_state // nVHE? No way! Give me the real thing! // Sanity check: MMU *must* be off @@ -164,7 +82,7 @@ SYM_CODE_START_LOCAL(__finalise_el2) tbnz x1, #0, 1f // Needs to be VHE capable, obviously - check_override id_aa64mmfr1 ID_AA64MMFR1_EL1_VH_SHIFT 2f 1f + check_override id_aa64mmfr1 ID_AA64MMFR1_EL1_VH_SHIFT 2f 1f x1 x2 1: mov_q x0, HVC_STUB_ERR eret diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 05da3c8f7e88..ca6eadeb7d1a 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -21,6 +21,7 @@ if VIRTUALIZATION menuconfig KVM bool "Kernel-based Virtual Machine (KVM) support" depends on HAVE_KVM + select KVM_GENERIC_HARDWARE_ENABLING select MMU_NOTIFIER select PREEMPT_NOTIFIERS select HAVE_KVM_CPU_RELAX_INTERCEPT diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 5e33c2d4645a..c0c050e53157 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -14,7 +14,7 @@ kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \ inject_fault.o va_layout.o handle_exit.o \ guest.o debug.o reset.o sys_regs.o stacktrace.o \ vgic-sys-reg-v3.o fpsimd.o pkvm.o \ - arch_timer.o trng.o vmid.o \ + arch_timer.o trng.o vmid.o emulate-nested.o nested.o \ vgic/vgic.o vgic/vgic-init.o \ vgic/vgic-irqfd.o vgic/vgic-v2.o \ vgic/vgic-v3.o vgic/vgic-v4.o \ diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index bb24a76b4224..00610477ec7b 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -428,14 +428,17 @@ static void timer_emulate(struct arch_timer_context *ctx) * scheduled for the future. If the timer cannot fire at all, * then we also don't need a soft timer. */ - if (!kvm_timer_irq_can_fire(ctx)) { - soft_timer_cancel(&ctx->hrtimer); + if (should_fire || !kvm_timer_irq_can_fire(ctx)) return; - } soft_timer_start(&ctx->hrtimer, kvm_timer_compute_delta(ctx)); } +static void set_cntvoff(u64 cntvoff) +{ + kvm_call_hyp(__kvm_timer_set_cntvoff, cntvoff); +} + static void timer_save_state(struct arch_timer_context *ctx) { struct arch_timer_cpu *timer = vcpu_timer(ctx->vcpu); @@ -459,6 +462,22 @@ static void timer_save_state(struct arch_timer_context *ctx) write_sysreg_el0(0, SYS_CNTV_CTL); isb(); + /* + * The kernel may decide to run userspace after + * calling vcpu_put, so we reset cntvoff to 0 to + * ensure a consistent read between user accesses to + * the virtual counter and kernel access to the + * physical counter of non-VHE case. + * + * For VHE, the virtual counter uses a fixed virtual + * offset of zero, so no need to zero CNTVOFF_EL2 + * register, but this is actually useful when switching + * between EL1/vEL2 with NV. + * + * Do it unconditionally, as this is either unavoidable + * or dirt cheap. + */ + set_cntvoff(0); break; case TIMER_PTIMER: timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTP_CTL)); @@ -532,6 +551,7 @@ static void timer_restore_state(struct arch_timer_context *ctx) switch (index) { case TIMER_VTIMER: + set_cntvoff(timer_get_offset(ctx)); write_sysreg_el0(timer_get_cval(ctx), SYS_CNTV_CVAL); isb(); write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTV_CTL); @@ -552,11 +572,6 @@ out: local_irq_restore(flags); } -static void set_cntvoff(u64 cntvoff) -{ - kvm_call_hyp(__kvm_timer_set_cntvoff, cntvoff); -} - static inline void set_timer_irq_phys_active(struct arch_timer_context *ctx, bool active) { int r; @@ -631,8 +646,6 @@ void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu) kvm_timer_vcpu_load_nogic(vcpu); } - set_cntvoff(timer_get_offset(map.direct_vtimer)); - kvm_timer_unblocking(vcpu); timer_restore_state(map.direct_vtimer); @@ -688,15 +701,6 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) if (kvm_vcpu_is_blocking(vcpu)) kvm_timer_blocking(vcpu); - - /* - * The kernel may decide to run userspace after calling vcpu_put, so - * we reset cntvoff to 0 to ensure a consistent read between user - * accesses to the virtual counter and kernel access to the physical - * counter of non-VHE case. For VHE, the virtual counter uses a fixed - * virtual offset of zero, so no need to zero CNTVOFF_EL2 register. - */ - set_cntvoff(0); } /* @@ -811,10 +815,18 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) ptimer->host_timer_irq_flags = host_ptimer_irq_flags; } -static void kvm_timer_init_interrupt(void *info) +void kvm_timer_cpu_up(void) { enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); - enable_percpu_irq(host_ptimer_irq, host_ptimer_irq_flags); + if (host_ptimer_irq) + enable_percpu_irq(host_ptimer_irq, host_ptimer_irq_flags); +} + +void kvm_timer_cpu_down(void) +{ + disable_percpu_irq(host_vtimer_irq); + if (host_ptimer_irq) + disable_percpu_irq(host_ptimer_irq); } int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value) @@ -926,14 +938,22 @@ u64 kvm_arm_timer_read_sysreg(struct kvm_vcpu *vcpu, enum kvm_arch_timers tmr, enum kvm_arch_timer_regs treg) { + struct arch_timer_context *timer; + struct timer_map map; u64 val; + get_timer_map(vcpu, &map); + timer = vcpu_get_timer(vcpu, tmr); + + if (timer == map.emul_ptimer) + return kvm_arm_timer_read(vcpu, timer, treg); + preempt_disable(); - kvm_timer_vcpu_put(vcpu); + timer_save_state(timer); - val = kvm_arm_timer_read(vcpu, vcpu_get_timer(vcpu, tmr), treg); + val = kvm_arm_timer_read(vcpu, timer, treg); - kvm_timer_vcpu_load(vcpu); + timer_restore_state(timer); preempt_enable(); return val; @@ -967,25 +987,22 @@ void kvm_arm_timer_write_sysreg(struct kvm_vcpu *vcpu, enum kvm_arch_timer_regs treg, u64 val) { - preempt_disable(); - kvm_timer_vcpu_put(vcpu); - - kvm_arm_timer_write(vcpu, vcpu_get_timer(vcpu, tmr), treg, val); - - kvm_timer_vcpu_load(vcpu); - preempt_enable(); -} - -static int kvm_timer_starting_cpu(unsigned int cpu) -{ - kvm_timer_init_interrupt(NULL); - return 0; -} + struct arch_timer_context *timer; + struct timer_map map; -static int kvm_timer_dying_cpu(unsigned int cpu) -{ - disable_percpu_irq(host_vtimer_irq); - return 0; + get_timer_map(vcpu, &map); + timer = vcpu_get_timer(vcpu, tmr); + if (timer == map.emul_ptimer) { + soft_timer_cancel(&timer->hrtimer); + kvm_arm_timer_write(vcpu, timer, treg, val); + timer_emulate(timer); + } else { + preempt_disable(); + timer_save_state(timer); + kvm_arm_timer_write(vcpu, timer, treg, val); + timer_restore_state(timer); + preempt_enable(); + } } static int timer_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu) @@ -1117,7 +1134,7 @@ static int kvm_irq_init(struct arch_timer_kvm_info *info) return 0; } -int kvm_timer_hyp_init(bool has_gic) +int __init kvm_timer_hyp_init(bool has_gic) { struct arch_timer_kvm_info *info; int err; @@ -1185,9 +1202,6 @@ int kvm_timer_hyp_init(bool has_gic) goto out_free_irq; } - cpuhp_setup_state(CPUHP_AP_KVM_ARM_TIMER_STARTING, - "kvm/arm/timer:starting", kvm_timer_starting_cpu, - kvm_timer_dying_cpu); return 0; out_free_irq: free_percpu_irq(host_vtimer_irq, kvm_get_running_vcpus()); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 9c5573bc4614..3bd732eaf087 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -63,16 +63,6 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; } -int kvm_arch_hardware_setup(void *opaque) -{ - return 0; -} - -int kvm_arch_check_processor_compat(void *opaque) -{ - return 0; -} - int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) { @@ -146,7 +136,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) if (ret) goto err_unshare_kvm; - if (!zalloc_cpumask_var(&kvm->arch.supported_cpus, GFP_KERNEL)) { + if (!zalloc_cpumask_var(&kvm->arch.supported_cpus, GFP_KERNEL_ACCOUNT)) { ret = -ENOMEM; goto err_unshare_kvm; } @@ -1539,7 +1529,7 @@ static int kvm_init_vector_slots(void) return 0; } -static void cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits) +static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits) { struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu); unsigned long tcr; @@ -1682,7 +1672,15 @@ static void _kvm_arch_hardware_enable(void *discard) int kvm_arch_hardware_enable(void) { + int was_enabled = __this_cpu_read(kvm_arm_hardware_enabled); + _kvm_arch_hardware_enable(NULL); + + if (!was_enabled) { + kvm_vgic_cpu_up(); + kvm_timer_cpu_up(); + } + return 0; } @@ -1696,6 +1694,11 @@ static void _kvm_arch_hardware_disable(void *discard) void kvm_arch_hardware_disable(void) { + if (__this_cpu_read(kvm_arm_hardware_enabled)) { + kvm_timer_cpu_down(); + kvm_vgic_cpu_down(); + } + if (!is_protected_kvm_enabled()) _kvm_arch_hardware_disable(NULL); } @@ -1738,26 +1741,26 @@ static struct notifier_block hyp_init_cpu_pm_nb = { .notifier_call = hyp_init_cpu_pm_notifier, }; -static void hyp_cpu_pm_init(void) +static void __init hyp_cpu_pm_init(void) { if (!is_protected_kvm_enabled()) cpu_pm_register_notifier(&hyp_init_cpu_pm_nb); } -static void hyp_cpu_pm_exit(void) +static void __init hyp_cpu_pm_exit(void) { if (!is_protected_kvm_enabled()) cpu_pm_unregister_notifier(&hyp_init_cpu_pm_nb); } #else -static inline void hyp_cpu_pm_init(void) +static inline void __init hyp_cpu_pm_init(void) { } -static inline void hyp_cpu_pm_exit(void) +static inline void __init hyp_cpu_pm_exit(void) { } #endif -static void init_cpu_logical_map(void) +static void __init init_cpu_logical_map(void) { unsigned int cpu; @@ -1774,7 +1777,7 @@ static void init_cpu_logical_map(void) #define init_psci_0_1_impl_state(config, what) \ config.psci_0_1_ ## what ## _implemented = psci_ops.what -static bool init_psci_relay(void) +static bool __init init_psci_relay(void) { /* * If PSCI has not been initialized, protected KVM cannot install @@ -1797,7 +1800,7 @@ static bool init_psci_relay(void) return true; } -static int init_subsystems(void) +static int __init init_subsystems(void) { int err = 0; @@ -1838,13 +1841,22 @@ static int init_subsystems(void) kvm_register_perf_callbacks(NULL); out: + if (err) + hyp_cpu_pm_exit(); + if (err || !is_protected_kvm_enabled()) on_each_cpu(_kvm_arch_hardware_disable, NULL, 1); return err; } -static void teardown_hyp_mode(void) +static void __init teardown_subsystems(void) +{ + kvm_unregister_perf_callbacks(); + hyp_cpu_pm_exit(); +} + +static void __init teardown_hyp_mode(void) { int cpu; @@ -1855,7 +1867,7 @@ static void teardown_hyp_mode(void) } } -static int do_pkvm_init(u32 hyp_va_bits) +static int __init do_pkvm_init(u32 hyp_va_bits) { void *per_cpu_base = kvm_ksym_ref(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)); int ret; @@ -1887,11 +1899,12 @@ static void kvm_hyp_init_symbols(void) kvm_nvhe_sym(id_aa64mmfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); kvm_nvhe_sym(id_aa64mmfr1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); kvm_nvhe_sym(id_aa64mmfr2_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR2_EL1); + kvm_nvhe_sym(id_aa64smfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64SMFR0_EL1); kvm_nvhe_sym(__icache_flags) = __icache_flags; kvm_nvhe_sym(kvm_arm_vmid_bits) = kvm_arm_vmid_bits; } -static int kvm_hyp_init_protection(u32 hyp_va_bits) +static int __init kvm_hyp_init_protection(u32 hyp_va_bits) { void *addr = phys_to_virt(hyp_mem_base); int ret; @@ -1909,10 +1922,8 @@ static int kvm_hyp_init_protection(u32 hyp_va_bits) return 0; } -/** - * Inits Hyp-mode on all online CPUs - */ -static int init_hyp_mode(void) +/* Inits Hyp-mode on all online CPUs */ +static int __init init_hyp_mode(void) { u32 hyp_va_bits; int cpu; @@ -2094,7 +2105,7 @@ out_err: return err; } -static void _kvm_host_prot_finalize(void *arg) +static void __init _kvm_host_prot_finalize(void *arg) { int *err = arg; @@ -2102,7 +2113,7 @@ static void _kvm_host_prot_finalize(void *arg) WRITE_ONCE(*err, -EINVAL); } -static int pkvm_drop_host_privileges(void) +static int __init pkvm_drop_host_privileges(void) { int ret = 0; @@ -2115,7 +2126,7 @@ static int pkvm_drop_host_privileges(void) return ret; } -static int finalize_hyp_mode(void) +static int __init finalize_hyp_mode(void) { if (!is_protected_kvm_enabled()) return 0; @@ -2187,10 +2198,8 @@ void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *cons) kvm_arm_resume_guest(irqfd->kvm); } -/** - * Initialize Hyp-mode and memory mappings on all CPUs. - */ -int kvm_arch_init(void *opaque) +/* Initialize Hyp-mode and memory mappings on all CPUs */ +static __init int kvm_arm_init(void) { int err; bool in_hyp_mode; @@ -2241,7 +2250,7 @@ int kvm_arch_init(void *opaque) err = kvm_init_vector_slots(); if (err) { kvm_err("Cannot initialise vector slots\n"); - goto out_err; + goto out_hyp; } err = init_subsystems(); @@ -2252,7 +2261,7 @@ int kvm_arch_init(void *opaque) err = finalize_hyp_mode(); if (err) { kvm_err("Failed to finalize Hyp protection\n"); - goto out_hyp; + goto out_subs; } } @@ -2264,10 +2273,19 @@ int kvm_arch_init(void *opaque) kvm_info("Hyp mode initialized successfully\n"); } + /* + * FIXME: Do something reasonable if kvm_init() fails after pKVM + * hypervisor protection is finalized. + */ + err = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); + if (err) + goto out_subs; + return 0; +out_subs: + teardown_subsystems(); out_hyp: - hyp_cpu_pm_exit(); if (!in_hyp_mode) teardown_hyp_mode(); out_err: @@ -2275,12 +2293,6 @@ out_err: return err; } -/* NOP: Compiling as a module not supported */ -void kvm_arch_exit(void) -{ - kvm_unregister_perf_callbacks(); -} - static int __init early_kvm_mode_cfg(char *arg) { if (!arg) @@ -2310,6 +2322,11 @@ static int __init early_kvm_mode_cfg(char *arg) return 0; } + if (strcmp(arg, "nested") == 0 && !WARN_ON(!is_kernel_in_hyp_mode())) { + kvm_mode = KVM_MODE_NV; + return 0; + } + return -EINVAL; } early_param("kvm-arm.mode", early_kvm_mode_cfg); @@ -2319,10 +2336,4 @@ enum kvm_mode kvm_get_mode(void) return kvm_mode; } -static int arm_init(void) -{ - int rc = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); - return rc; -} - -module_init(arm_init); +module_init(kvm_arm_init); diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c new file mode 100644 index 000000000000..b96662029fb1 --- /dev/null +++ b/arch/arm64/kvm/emulate-nested.c @@ -0,0 +1,203 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2016 - Linaro and Columbia University + * Author: Jintack Lim <jintack.lim@linaro.org> + */ + +#include <linux/kvm.h> +#include <linux/kvm_host.h> + +#include <asm/kvm_emulate.h> +#include <asm/kvm_nested.h> + +#include "hyp/include/hyp/adjust_pc.h" + +#include "trace.h" + +static u64 kvm_check_illegal_exception_return(struct kvm_vcpu *vcpu, u64 spsr) +{ + u64 mode = spsr & PSR_MODE_MASK; + + /* + * Possible causes for an Illegal Exception Return from EL2: + * - trying to return to EL3 + * - trying to return to an illegal M value + * - trying to return to a 32bit EL + * - trying to return to EL1 with HCR_EL2.TGE set + */ + if (mode == PSR_MODE_EL3t || mode == PSR_MODE_EL3h || + mode == 0b00001 || (mode & BIT(1)) || + (spsr & PSR_MODE32_BIT) || + (vcpu_el2_tge_is_set(vcpu) && (mode == PSR_MODE_EL1t || + mode == PSR_MODE_EL1h))) { + /* + * The guest is playing with our nerves. Preserve EL, SP, + * masks, flags from the existing PSTATE, and set IL. + * The HW will then generate an Illegal State Exception + * immediately after ERET. + */ + spsr = *vcpu_cpsr(vcpu); + + spsr &= (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT | + PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT | PSR_V_BIT | + PSR_MODE_MASK | PSR_MODE32_BIT); + spsr |= PSR_IL_BIT; + } + + return spsr; +} + +void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu) +{ + u64 spsr, elr, mode; + bool direct_eret; + + /* + * Going through the whole put/load motions is a waste of time + * if this is a VHE guest hypervisor returning to its own + * userspace, or the hypervisor performing a local exception + * return. No need to save/restore registers, no need to + * switch S2 MMU. Just do the canonical ERET. + */ + spsr = vcpu_read_sys_reg(vcpu, SPSR_EL2); + spsr = kvm_check_illegal_exception_return(vcpu, spsr); + + mode = spsr & (PSR_MODE_MASK | PSR_MODE32_BIT); + + direct_eret = (mode == PSR_MODE_EL0t && + vcpu_el2_e2h_is_set(vcpu) && + vcpu_el2_tge_is_set(vcpu)); + direct_eret |= (mode == PSR_MODE_EL2h || mode == PSR_MODE_EL2t); + + if (direct_eret) { + *vcpu_pc(vcpu) = vcpu_read_sys_reg(vcpu, ELR_EL2); + *vcpu_cpsr(vcpu) = spsr; + trace_kvm_nested_eret(vcpu, *vcpu_pc(vcpu), spsr); + return; + } + + preempt_disable(); + kvm_arch_vcpu_put(vcpu); + + elr = __vcpu_sys_reg(vcpu, ELR_EL2); + + trace_kvm_nested_eret(vcpu, elr, spsr); + + /* + * Note that the current exception level is always the virtual EL2, + * since we set HCR_EL2.NV bit only when entering the virtual EL2. + */ + *vcpu_pc(vcpu) = elr; + *vcpu_cpsr(vcpu) = spsr; + + kvm_arch_vcpu_load(vcpu, smp_processor_id()); + preempt_enable(); +} + +static void kvm_inject_el2_exception(struct kvm_vcpu *vcpu, u64 esr_el2, + enum exception_type type) +{ + trace_kvm_inject_nested_exception(vcpu, esr_el2, type); + + switch (type) { + case except_type_sync: + kvm_pend_exception(vcpu, EXCEPT_AA64_EL2_SYNC); + vcpu_write_sys_reg(vcpu, esr_el2, ESR_EL2); + break; + case except_type_irq: + kvm_pend_exception(vcpu, EXCEPT_AA64_EL2_IRQ); + break; + default: + WARN_ONCE(1, "Unsupported EL2 exception injection %d\n", type); + } +} + +/* + * Emulate taking an exception to EL2. + * See ARM ARM J8.1.2 AArch64.TakeException() + */ +static int kvm_inject_nested(struct kvm_vcpu *vcpu, u64 esr_el2, + enum exception_type type) +{ + u64 pstate, mode; + bool direct_inject; + + if (!vcpu_has_nv(vcpu)) { + kvm_err("Unexpected call to %s for the non-nesting configuration\n", + __func__); + return -EINVAL; + } + + /* + * As for ERET, we can avoid doing too much on the injection path by + * checking that we either took the exception from a VHE host + * userspace or from vEL2. In these cases, there is no change in + * translation regime (or anything else), so let's do as little as + * possible. + */ + pstate = *vcpu_cpsr(vcpu); + mode = pstate & (PSR_MODE_MASK | PSR_MODE32_BIT); + + direct_inject = (mode == PSR_MODE_EL0t && + vcpu_el2_e2h_is_set(vcpu) && + vcpu_el2_tge_is_set(vcpu)); + direct_inject |= (mode == PSR_MODE_EL2h || mode == PSR_MODE_EL2t); + + if (direct_inject) { + kvm_inject_el2_exception(vcpu, esr_el2, type); + return 1; + } + + preempt_disable(); + + /* + * We may have an exception or PC update in the EL0/EL1 context. + * Commit it before entering EL2. + */ + __kvm_adjust_pc(vcpu); + + kvm_arch_vcpu_put(vcpu); + + kvm_inject_el2_exception(vcpu, esr_el2, type); + + /* + * A hard requirement is that a switch between EL1 and EL2 + * contexts has to happen between a put/load, so that we can + * pick the correct timer and interrupt configuration, among + * other things. + * + * Make sure the exception actually took place before we load + * the new context. + */ + __kvm_adjust_pc(vcpu); + + kvm_arch_vcpu_load(vcpu, smp_processor_id()); + preempt_enable(); + + return 1; +} + +int kvm_inject_nested_sync(struct kvm_vcpu *vcpu, u64 esr_el2) +{ + return kvm_inject_nested(vcpu, esr_el2, except_type_sync); +} + +int kvm_inject_nested_irq(struct kvm_vcpu *vcpu) +{ + /* + * Do not inject an irq if the: + * - Current exception level is EL2, and + * - virtual HCR_EL2.TGE == 0 + * - virtual HCR_EL2.IMO == 0 + * + * See Table D1-17 "Physical interrupt target and masking when EL3 is + * not implemented and EL2 is implemented" in ARM DDI 0487C.a. + */ + + if (vcpu_is_el2(vcpu) && !vcpu_el2_tge_is_set(vcpu) && + !(__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_IMO)) + return 1; + + /* esr_el2 value doesn't matter for exits due to irqs. */ + return kvm_inject_nested(vcpu, 0, except_type_irq); +} diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 235775d0c825..1279949599b5 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -184,6 +184,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) sysreg_clear_set(CPACR_EL1, CPACR_EL1_SMEN_EL0EN, CPACR_EL1_SMEN_EL1EN); + isb(); } if (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED) { diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index cf4c495a4321..07444fa22888 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -24,6 +24,7 @@ #include <asm/fpsimd.h> #include <asm/kvm.h> #include <asm/kvm_emulate.h> +#include <asm/kvm_nested.h> #include <asm/sigcontext.h> #include "trace.h" @@ -253,6 +254,11 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) if (!vcpu_el1_is_32bit(vcpu)) return -EINVAL; break; + case PSR_MODE_EL2h: + case PSR_MODE_EL2t: + if (!vcpu_has_nv(vcpu)) + return -EINVAL; + fallthrough; case PSR_MODE_EL0t: case PSR_MODE_EL1t: case PSR_MODE_EL1h: diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index e778eefcf214..a798c0b4d717 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -16,6 +16,7 @@ #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> +#include <asm/kvm_nested.h> #include <asm/debug-monitors.h> #include <asm/stacktrace/nvhe.h> #include <asm/traps.h> @@ -41,6 +42,16 @@ static int handle_hvc(struct kvm_vcpu *vcpu) kvm_vcpu_hvc_get_imm(vcpu)); vcpu->stat.hvc_exit_stat++; + /* Forward hvc instructions to the virtual EL2 if the guest has EL2. */ + if (vcpu_has_nv(vcpu)) { + if (vcpu_read_sys_reg(vcpu, HCR_EL2) & HCR_HCD) + kvm_inject_undefined(vcpu); + else + kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu)); + + return 1; + } + ret = kvm_hvc_call_handler(vcpu); if (ret < 0) { vcpu_set_reg(vcpu, 0, ~0UL); @@ -52,6 +63,8 @@ static int handle_hvc(struct kvm_vcpu *vcpu) static int handle_smc(struct kvm_vcpu *vcpu) { + int ret; + /* * "If an SMC instruction executed at Non-secure EL1 is * trapped to EL2 because HCR_EL2.TSC is 1, the exception is a @@ -59,10 +72,30 @@ static int handle_smc(struct kvm_vcpu *vcpu) * * We need to advance the PC after the trap, as it would * otherwise return to the same address... + * + * Only handle SMCs from the virtual EL2 with an immediate of zero and + * skip it otherwise. */ - vcpu_set_reg(vcpu, 0, ~0UL); + if (!vcpu_is_el2(vcpu) || kvm_vcpu_hvc_get_imm(vcpu)) { + vcpu_set_reg(vcpu, 0, ~0UL); + kvm_incr_pc(vcpu); + return 1; + } + + /* + * If imm is zero then it is likely an SMCCC call. + * + * Note that on ARMv8.3, even if EL3 is not implemented, SMC executed + * at Non-secure EL1 is trapped to EL2 if HCR_EL2.TSC==1, rather than + * being treated as UNDEFINED. + */ + ret = kvm_hvc_call_handler(vcpu); + if (ret < 0) + vcpu_set_reg(vcpu, 0, ~0UL); + kvm_incr_pc(vcpu); - return 1; + + return ret; } /* @@ -196,6 +229,15 @@ static int kvm_handle_ptrauth(struct kvm_vcpu *vcpu) return 1; } +static int kvm_handle_eret(struct kvm_vcpu *vcpu) +{ + if (kvm_vcpu_get_esr(vcpu) & ESR_ELx_ERET_ISS_ERET) + return kvm_handle_ptrauth(vcpu); + + kvm_emulate_nested_eret(vcpu); + return 1; +} + static exit_handle_fn arm_exit_handlers[] = { [0 ... ESR_ELx_EC_MAX] = kvm_handle_unknown_ec, [ESR_ELx_EC_WFx] = kvm_handle_wfx, @@ -211,6 +253,7 @@ static exit_handle_fn arm_exit_handlers[] = { [ESR_ELx_EC_SMC64] = handle_smc, [ESR_ELx_EC_SYS64] = kvm_handle_sys_reg, [ESR_ELx_EC_SVE] = handle_sve, + [ESR_ELx_EC_ERET] = kvm_handle_eret, [ESR_ELx_EC_IABT_LOW] = kvm_handle_guest_abort, [ESR_ELx_EC_DABT_LOW] = kvm_handle_guest_abort, [ESR_ELx_EC_SOFTSTP_LOW]= kvm_handle_guest_debug, diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c index 791d3de76771..424a5107cddb 100644 --- a/arch/arm64/kvm/hyp/exception.c +++ b/arch/arm64/kvm/hyp/exception.c @@ -14,6 +14,7 @@ #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> +#include <asm/kvm_nested.h> #if !defined (__KVM_NVHE_HYPERVISOR__) && !defined (__KVM_VHE_HYPERVISOR__) #error Hypervisor code only! @@ -23,7 +24,9 @@ static inline u64 __vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg) { u64 val; - if (__vcpu_read_sys_reg_from_cpu(reg, &val)) + if (unlikely(vcpu_has_nv(vcpu))) + return vcpu_read_sys_reg(vcpu, reg); + else if (__vcpu_read_sys_reg_from_cpu(reg, &val)) return val; return __vcpu_sys_reg(vcpu, reg); @@ -31,18 +34,25 @@ static inline u64 __vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg) static inline void __vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg) { - if (__vcpu_write_sys_reg_to_cpu(val, reg)) - return; - - __vcpu_sys_reg(vcpu, reg) = val; + if (unlikely(vcpu_has_nv(vcpu))) + vcpu_write_sys_reg(vcpu, val, reg); + else if (!__vcpu_write_sys_reg_to_cpu(val, reg)) + __vcpu_sys_reg(vcpu, reg) = val; } -static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, u64 val) +static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long target_mode, + u64 val) { - if (has_vhe()) + if (unlikely(vcpu_has_nv(vcpu))) { + if (target_mode == PSR_MODE_EL1h) + vcpu_write_sys_reg(vcpu, val, SPSR_EL1); + else + vcpu_write_sys_reg(vcpu, val, SPSR_EL2); + } else if (has_vhe()) { write_sysreg_el1(val, SYS_SPSR); - else + } else { __vcpu_sys_reg(vcpu, SPSR_EL1) = val; + } } static void __vcpu_write_spsr_abt(struct kvm_vcpu *vcpu, u64 val) @@ -101,6 +111,11 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode, sctlr = __vcpu_read_sys_reg(vcpu, SCTLR_EL1); __vcpu_write_sys_reg(vcpu, *vcpu_pc(vcpu), ELR_EL1); break; + case PSR_MODE_EL2h: + vbar = __vcpu_read_sys_reg(vcpu, VBAR_EL2); + sctlr = __vcpu_read_sys_reg(vcpu, SCTLR_EL2); + __vcpu_write_sys_reg(vcpu, *vcpu_pc(vcpu), ELR_EL2); + break; default: /* Don't do that */ BUG(); @@ -153,7 +168,7 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode, new |= target_mode; *vcpu_cpsr(vcpu) = new; - __vcpu_write_spsr(vcpu, old); + __vcpu_write_spsr(vcpu, target_mode, old); } /* @@ -323,11 +338,20 @@ static void kvm_inject_exception(struct kvm_vcpu *vcpu) case unpack_vcpu_flag(EXCEPT_AA64_EL1_SYNC): enter_exception64(vcpu, PSR_MODE_EL1h, except_type_sync); break; + + case unpack_vcpu_flag(EXCEPT_AA64_EL2_SYNC): + enter_exception64(vcpu, PSR_MODE_EL2h, except_type_sync); + break; + + case unpack_vcpu_flag(EXCEPT_AA64_EL2_IRQ): + enter_exception64(vcpu, PSR_MODE_EL2h, except_type_irq); + break; + default: /* - * Only EL1_SYNC makes sense so far, EL2_{SYNC,IRQ} - * will be implemented at some point. Everything - * else gets silently ignored. + * Only EL1_SYNC and EL2_{SYNC,IRQ} makes + * sense so far. Everything else gets silently + * ignored. */ break; } diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h index baa5b9b3dde5..699ea1f8d409 100644 --- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h +++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h @@ -39,7 +39,6 @@ static inline bool ctxt_has_mte(struct kvm_cpu_context *ctxt) static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt) { - ctxt_sys_reg(ctxt, CSSELR_EL1) = read_sysreg(csselr_el1); ctxt_sys_reg(ctxt, SCTLR_EL1) = read_sysreg_el1(SYS_SCTLR); ctxt_sys_reg(ctxt, CPACR_EL1) = read_sysreg_el1(SYS_CPACR); ctxt_sys_reg(ctxt, TTBR0_EL1) = read_sysreg_el1(SYS_TTBR0); @@ -95,7 +94,6 @@ static inline void __sysreg_restore_user_state(struct kvm_cpu_context *ctxt) static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt) { write_sysreg(ctxt_sys_reg(ctxt, MPIDR_EL1), vmpidr_el2); - write_sysreg(ctxt_sys_reg(ctxt, CSSELR_EL1), csselr_el1); if (has_vhe() || !cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { @@ -156,9 +154,26 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt) write_sysreg_el1(ctxt_sys_reg(ctxt, SPSR_EL1), SYS_SPSR); } +/* Read the VCPU state's PSTATE, but translate (v)EL2 to EL1. */ +static inline u64 to_hw_pstate(const struct kvm_cpu_context *ctxt) +{ + u64 mode = ctxt->regs.pstate & (PSR_MODE_MASK | PSR_MODE32_BIT); + + switch (mode) { + case PSR_MODE_EL2t: + mode = PSR_MODE_EL1t; + break; + case PSR_MODE_EL2h: + mode = PSR_MODE_EL1h; + break; + } + + return (ctxt->regs.pstate & ~(PSR_MODE_MASK | PSR_MODE32_BIT)) | mode; +} + static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt) { - u64 pstate = ctxt->regs.pstate; + u64 pstate = to_hw_pstate(ctxt); u64 mode = pstate & PSR_AA32_MODE_MASK; /* diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S index c953fb4b9a13..a6d67c2bb5ae 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S +++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S @@ -183,6 +183,7 @@ SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu) /* Initialize EL2 CPU state to sane values. */ init_el2_state // Clobbers x0..x2 + finalise_el2_state /* Enable MMU, set vectors and stack. */ mov x0, x28 diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index 0f9ac25afdf4..08d2b004f4b7 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -26,6 +26,7 @@ u64 id_aa64isar2_el1_sys_val; u64 id_aa64mmfr0_el1_sys_val; u64 id_aa64mmfr1_el1_sys_val; u64 id_aa64mmfr2_el1_sys_val; +u64 id_aa64smfr0_el1_sys_val; /* * Inject an unknown/undefined exception to an AArch64 guest while most of its diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index b11cf2c618a6..3d61bd3e591d 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -168,6 +168,25 @@ static int kvm_pgtable_visitor_cb(struct kvm_pgtable_walk_data *data, return walker->cb(ctx, visit); } +static bool kvm_pgtable_walk_continue(const struct kvm_pgtable_walker *walker, + int r) +{ + /* + * Visitor callbacks return EAGAIN when the conditions that led to a + * fault are no longer reflected in the page tables due to a race to + * update a PTE. In the context of a fault handler this is interpreted + * as a signal to retry guest execution. + * + * Ignore the return code altogether for walkers outside a fault handler + * (e.g. write protecting a range of memory) and chug along with the + * page table walk. + */ + if (r == -EAGAIN) + return !(walker->flags & KVM_PGTABLE_WALK_HANDLE_FAULT); + + return !r; +} + static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data, struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, u32 level); @@ -200,7 +219,7 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, table = kvm_pte_table(ctx.old, level); } - if (ret) + if (!kvm_pgtable_walk_continue(data->walker, ret)) goto out; if (!table) { @@ -211,13 +230,16 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, childp = (kvm_pteref_t)kvm_pte_follow(ctx.old, mm_ops); ret = __kvm_pgtable_walk(data, mm_ops, childp, level + 1); - if (ret) + if (!kvm_pgtable_walk_continue(data->walker, ret)) goto out; if (ctx.flags & KVM_PGTABLE_WALK_TABLE_POST) ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_TABLE_POST); out: + if (kvm_pgtable_walk_continue(data->walker, ret)) + return 0; + return ret; } @@ -584,12 +606,14 @@ u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift) lvls = 2; vtcr |= VTCR_EL2_LVLS_TO_SL0(lvls); +#ifdef CONFIG_ARM64_HW_AFDBM /* * Enable the Hardware Access Flag management, unconditionally * on all CPUs. The features is RES0 on CPUs without the support * and must be ignored by the CPUs. */ vtcr |= VTCR_EL2_HA; +#endif /* CONFIG_ARM64_HW_AFDBM */ /* Set the vmid bits */ vtcr |= (get_vmid_bits(mmfr1) == 16) ? @@ -1026,7 +1050,7 @@ static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx, struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (!kvm_pte_valid(ctx->old)) - return 0; + return -EAGAIN; data->level = ctx->level; data->pte = pte; @@ -1094,9 +1118,15 @@ int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size) kvm_pte_t kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr) { kvm_pte_t pte = 0; - stage2_update_leaf_attrs(pgt, addr, 1, KVM_PTE_LEAF_ATTR_LO_S2_AF, 0, - &pte, NULL, 0); - dsb(ishst); + int ret; + + ret = stage2_update_leaf_attrs(pgt, addr, 1, KVM_PTE_LEAF_ATTR_LO_S2_AF, 0, + &pte, NULL, + KVM_PGTABLE_WALK_HANDLE_FAULT | + KVM_PGTABLE_WALK_SHARED); + if (!ret) + dsb(ishst); + return pte; } @@ -1141,6 +1171,7 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, clr |= KVM_PTE_LEAF_ATTR_HI_S2_XN; ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level, + KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED); if (!ret) kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, pgt->mmu, addr, level); diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 1a97391fedd2..cd3f3117bf16 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -40,7 +40,7 @@ static void __activate_traps(struct kvm_vcpu *vcpu) ___activate_traps(vcpu); val = read_sysreg(cpacr_el1); - val |= CPACR_EL1_TTA; + val |= CPACR_ELx_TTA; val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN | CPACR_EL1_SMEN_EL0EN | CPACR_EL1_SMEN_EL1EN); @@ -120,6 +120,25 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu) static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) { + /* + * If we were in HYP context on entry, adjust the PSTATE view + * so that the usual helpers work correctly. + */ + if (unlikely(vcpu_get_flag(vcpu, VCPU_HYP_CONTEXT))) { + u64 mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT); + + switch (mode) { + case PSR_MODE_EL1t: + mode = PSR_MODE_EL2t; + break; + case PSR_MODE_EL1h: + mode = PSR_MODE_EL2h; + break; + } + + *vcpu_cpsr(vcpu) &= ~(PSR_MODE_MASK | PSR_MODE32_BIT); + *vcpu_cpsr(vcpu) |= mode; + } } /* Switch to the guest for VHE systems running in EL2 */ @@ -154,6 +173,11 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) sysreg_restore_guest_state_vhe(guest_ctxt); __debug_switch_to_guest(vcpu); + if (is_hyp_ctxt(vcpu)) + vcpu_set_flag(vcpu, VCPU_HYP_CONTEXT); + else + vcpu_clear_flag(vcpu, VCPU_HYP_CONTEXT); + do { /* Jump in the fire! */ exit_code = __guest_enter(vcpu); diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index c9f401fa01a9..64c086c02c60 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -198,7 +198,7 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) break; case ARM_SMCCC_HV_PV_TIME_ST: gpa = kvm_init_stolen_time(vcpu); - if (gpa != GPA_INVALID) + if (gpa != INVALID_GPA) val[0] = gpa; break; case ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID: diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index f32f4a2a347f..64c3aec0d937 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -12,17 +12,55 @@ #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> +#include <asm/kvm_nested.h> #include <asm/esr.h> +static void pend_sync_exception(struct kvm_vcpu *vcpu) +{ + /* If not nesting, EL1 is the only possible exception target */ + if (likely(!vcpu_has_nv(vcpu))) { + kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC); + return; + } + + /* + * With NV, we need to pick between EL1 and EL2. Note that we + * never deal with a nesting exception here, hence never + * changing context, and the exception itself can be delayed + * until the next entry. + */ + switch(*vcpu_cpsr(vcpu) & PSR_MODE_MASK) { + case PSR_MODE_EL2h: + case PSR_MODE_EL2t: + kvm_pend_exception(vcpu, EXCEPT_AA64_EL2_SYNC); + break; + case PSR_MODE_EL1h: + case PSR_MODE_EL1t: + kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC); + break; + case PSR_MODE_EL0t: + if (vcpu_el2_tge_is_set(vcpu)) + kvm_pend_exception(vcpu, EXCEPT_AA64_EL2_SYNC); + else + kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC); + break; + default: + BUG(); + } +} + +static bool match_target_el(struct kvm_vcpu *vcpu, unsigned long target) +{ + return (vcpu_get_flag(vcpu, EXCEPT_MASK) == target); +} + static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr) { unsigned long cpsr = *vcpu_cpsr(vcpu); bool is_aarch32 = vcpu_mode_is_32bit(vcpu); u64 esr = 0; - kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC); - - vcpu_write_sys_reg(vcpu, addr, FAR_EL1); + pend_sync_exception(vcpu); /* * Build an {i,d}abort, depending on the level and the @@ -43,14 +81,22 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr if (!is_iabt) esr |= ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT; - vcpu_write_sys_reg(vcpu, esr | ESR_ELx_FSC_EXTABT, ESR_EL1); + esr |= ESR_ELx_FSC_EXTABT; + + if (match_target_el(vcpu, unpack_vcpu_flag(EXCEPT_AA64_EL1_SYNC))) { + vcpu_write_sys_reg(vcpu, addr, FAR_EL1); + vcpu_write_sys_reg(vcpu, esr, ESR_EL1); + } else { + vcpu_write_sys_reg(vcpu, addr, FAR_EL2); + vcpu_write_sys_reg(vcpu, esr, ESR_EL2); + } } static void inject_undef64(struct kvm_vcpu *vcpu) { u64 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT); - kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC); + pend_sync_exception(vcpu); /* * Build an unknown exception, depending on the instruction @@ -59,7 +105,10 @@ static void inject_undef64(struct kvm_vcpu *vcpu) if (kvm_vcpu_trap_il_is32bit(vcpu)) esr |= ESR_ELx_IL; - vcpu_write_sys_reg(vcpu, esr, ESR_EL1); + if (match_target_el(vcpu, unpack_vcpu_flag(EXCEPT_AA64_EL1_SYNC))) + vcpu_write_sys_reg(vcpu, esr, ESR_EL1); + else + vcpu_write_sys_reg(vcpu, esr, ESR_EL2); } #define DFSR_FSC_EXTABT_LPAE 0x10 diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index a3ee3b605c9b..7113587222ff 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -25,11 +25,11 @@ static struct kvm_pgtable *hyp_pgtable; static DEFINE_MUTEX(kvm_hyp_pgd_mutex); -static unsigned long hyp_idmap_start; -static unsigned long hyp_idmap_end; -static phys_addr_t hyp_idmap_vector; +static unsigned long __ro_after_init hyp_idmap_start; +static unsigned long __ro_after_init hyp_idmap_end; +static phys_addr_t __ro_after_init hyp_idmap_vector; -static unsigned long io_map_base; +static unsigned long __ro_after_init io_map_base; static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end) { @@ -46,16 +46,17 @@ static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end) * long will also starve other vCPUs. We have to also make sure that the page * tables are not freed while we released the lock. */ -static int stage2_apply_range(struct kvm *kvm, phys_addr_t addr, +static int stage2_apply_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end, int (*fn)(struct kvm_pgtable *, u64, u64), bool resched) { + struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu); int ret; u64 next; do { - struct kvm_pgtable *pgt = kvm->arch.mmu.pgt; + struct kvm_pgtable *pgt = mmu->pgt; if (!pgt) return -EINVAL; @@ -71,8 +72,8 @@ static int stage2_apply_range(struct kvm *kvm, phys_addr_t addr, return ret; } -#define stage2_apply_range_resched(kvm, addr, end, fn) \ - stage2_apply_range(kvm, addr, end, fn, true) +#define stage2_apply_range_resched(mmu, addr, end, fn) \ + stage2_apply_range(mmu, addr, end, fn, true) static bool memslot_is_logging(struct kvm_memory_slot *memslot) { @@ -235,7 +236,7 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 lockdep_assert_held_write(&kvm->mmu_lock); WARN_ON(size & ~PAGE_MASK); - WARN_ON(stage2_apply_range(kvm, start, end, kvm_pgtable_stage2_unmap, + WARN_ON(stage2_apply_range(mmu, start, end, kvm_pgtable_stage2_unmap, may_block)); } @@ -250,7 +251,7 @@ static void stage2_flush_memslot(struct kvm *kvm, phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT; phys_addr_t end = addr + PAGE_SIZE * memslot->npages; - stage2_apply_range_resched(kvm, addr, end, kvm_pgtable_stage2_flush); + stage2_apply_range_resched(&kvm->arch.mmu, addr, end, kvm_pgtable_stage2_flush); } /** @@ -280,7 +281,7 @@ static void stage2_flush_vm(struct kvm *kvm) /** * free_hyp_pgds - free Hyp-mode page tables */ -void free_hyp_pgds(void) +void __init free_hyp_pgds(void) { mutex_lock(&kvm_hyp_pgd_mutex); if (hyp_pgtable) { @@ -934,8 +935,7 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, */ static void stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end) { - struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu); - stage2_apply_range_resched(kvm, addr, end, kvm_pgtable_stage2_wrprotect); + stage2_apply_range_resched(mmu, addr, end, kvm_pgtable_stage2_wrprotect); } /** @@ -1383,7 +1383,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, else ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize, __pfn_to_phys(pfn), prot, - memcache, KVM_PGTABLE_WALK_SHARED); + memcache, + KVM_PGTABLE_WALK_HANDLE_FAULT | + KVM_PGTABLE_WALK_SHARED); /* Mark the page dirty only if the fault is handled successfully */ if (writable && !ret) { @@ -1401,20 +1403,18 @@ out_unlock: /* Resolve the access fault by making the page young again. */ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa) { - pte_t pte; - kvm_pte_t kpte; + kvm_pte_t pte; struct kvm_s2_mmu *mmu; trace_kvm_access_fault(fault_ipa); - write_lock(&vcpu->kvm->mmu_lock); + read_lock(&vcpu->kvm->mmu_lock); mmu = vcpu->arch.hw_mmu; - kpte = kvm_pgtable_stage2_mkyoung(mmu->pgt, fault_ipa); - write_unlock(&vcpu->kvm->mmu_lock); + pte = kvm_pgtable_stage2_mkyoung(mmu->pgt, fault_ipa); + read_unlock(&vcpu->kvm->mmu_lock); - pte = __pte(kpte); - if (pte_valid(pte)) - kvm_set_pfn_accessed(pte_pfn(pte)); + if (kvm_pte_valid(pte)) + kvm_set_pfn_accessed(kvm_pte_to_pfn(pte)); } /** @@ -1668,7 +1668,7 @@ static struct kvm_pgtable_mm_ops kvm_hyp_mm_ops = { .virt_to_phys = kvm_host_pa, }; -int kvm_mmu_init(u32 *hyp_va_bits) +int __init kvm_mmu_init(u32 *hyp_va_bits) { int err; u32 idmap_bits; diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c new file mode 100644 index 000000000000..315354d27978 --- /dev/null +++ b/arch/arm64/kvm/nested.c @@ -0,0 +1,161 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2017 - Columbia University and Linaro Ltd. + * Author: Jintack Lim <jintack.lim@linaro.org> + */ + +#include <linux/kvm.h> +#include <linux/kvm_host.h> + +#include <asm/kvm_emulate.h> +#include <asm/kvm_nested.h> +#include <asm/sysreg.h> + +#include "sys_regs.h" + +/* Protection against the sysreg repainting madness... */ +#define NV_FTR(r, f) ID_AA64##r##_EL1_##f + +/* + * Our emulated CPU doesn't support all the possible features. For the + * sake of simplicity (and probably mental sanity), wipe out a number + * of feature bits we don't intend to support for the time being. + * This list should get updated as new features get added to the NV + * support, and new extension to the architecture. + */ +void access_nested_id_reg(struct kvm_vcpu *v, struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + u32 id = reg_to_encoding(r); + u64 val, tmp; + + val = p->regval; + + switch (id) { + case SYS_ID_AA64ISAR0_EL1: + /* Support everything but TME, O.S. and Range TLBIs */ + val &= ~(NV_FTR(ISAR0, TLB) | + NV_FTR(ISAR0, TME)); + break; + + case SYS_ID_AA64ISAR1_EL1: + /* Support everything but PtrAuth and Spec Invalidation */ + val &= ~(GENMASK_ULL(63, 56) | + NV_FTR(ISAR1, SPECRES) | + NV_FTR(ISAR1, GPI) | + NV_FTR(ISAR1, GPA) | + NV_FTR(ISAR1, API) | + NV_FTR(ISAR1, APA)); + break; + + case SYS_ID_AA64PFR0_EL1: + /* No AMU, MPAM, S-EL2, RAS or SVE */ + val &= ~(GENMASK_ULL(55, 52) | + NV_FTR(PFR0, AMU) | + NV_FTR(PFR0, MPAM) | + NV_FTR(PFR0, SEL2) | + NV_FTR(PFR0, RAS) | + NV_FTR(PFR0, SVE) | + NV_FTR(PFR0, EL3) | + NV_FTR(PFR0, EL2) | + NV_FTR(PFR0, EL1)); + /* 64bit EL1/EL2/EL3 only */ + val |= FIELD_PREP(NV_FTR(PFR0, EL1), 0b0001); + val |= FIELD_PREP(NV_FTR(PFR0, EL2), 0b0001); + val |= FIELD_PREP(NV_FTR(PFR0, EL3), 0b0001); + break; + + case SYS_ID_AA64PFR1_EL1: + /* Only support SSBS */ + val &= NV_FTR(PFR1, SSBS); + break; + + case SYS_ID_AA64MMFR0_EL1: + /* Hide ECV, FGT, ExS, Secure Memory */ + val &= ~(GENMASK_ULL(63, 43) | + NV_FTR(MMFR0, TGRAN4_2) | + NV_FTR(MMFR0, TGRAN16_2) | + NV_FTR(MMFR0, TGRAN64_2) | + NV_FTR(MMFR0, SNSMEM)); + + /* Disallow unsupported S2 page sizes */ + switch (PAGE_SIZE) { + case SZ_64K: + val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN16_2), 0b0001); + fallthrough; + case SZ_16K: + val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN4_2), 0b0001); + fallthrough; + case SZ_4K: + /* Support everything */ + break; + } + /* + * Since we can't support a guest S2 page size smaller than + * the host's own page size (due to KVM only populating its + * own S2 using the kernel's page size), advertise the + * limitation using FEAT_GTG. + */ + switch (PAGE_SIZE) { + case SZ_4K: + val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN4_2), 0b0010); + fallthrough; + case SZ_16K: + val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN16_2), 0b0010); + fallthrough; + case SZ_64K: + val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN64_2), 0b0010); + break; + } + /* Cap PARange to 48bits */ + tmp = FIELD_GET(NV_FTR(MMFR0, PARANGE), val); + if (tmp > 0b0101) { + val &= ~NV_FTR(MMFR0, PARANGE); + val |= FIELD_PREP(NV_FTR(MMFR0, PARANGE), 0b0101); + } + break; + + case SYS_ID_AA64MMFR1_EL1: + val &= (NV_FTR(MMFR1, PAN) | + NV_FTR(MMFR1, LO) | + NV_FTR(MMFR1, HPDS) | + NV_FTR(MMFR1, VH) | + NV_FTR(MMFR1, VMIDBits)); + break; + + case SYS_ID_AA64MMFR2_EL1: + val &= ~(NV_FTR(MMFR2, EVT) | + NV_FTR(MMFR2, BBM) | + NV_FTR(MMFR2, TTL) | + GENMASK_ULL(47, 44) | + NV_FTR(MMFR2, ST) | + NV_FTR(MMFR2, CCIDX) | + NV_FTR(MMFR2, VARange)); + + /* Force TTL support */ + val |= FIELD_PREP(NV_FTR(MMFR2, TTL), 0b0001); + break; + + case SYS_ID_AA64DFR0_EL1: + /* Only limited support for PMU, Debug, BPs and WPs */ + val &= (NV_FTR(DFR0, PMUVer) | + NV_FTR(DFR0, WRPs) | + NV_FTR(DFR0, BRPs) | + NV_FTR(DFR0, DebugVer)); + + /* Cap Debug to ARMv8.1 */ + tmp = FIELD_GET(NV_FTR(DFR0, DebugVer), val); + if (tmp > 0b0111) { + val &= ~NV_FTR(DFR0, DebugVer); + val |= FIELD_PREP(NV_FTR(DFR0, DebugVer), 0b0111); + } + break; + + default: + /* Unknown register, just wipe it clean */ + val = 0; + break; + } + + p->regval = val; +} diff --git a/arch/arm64/kvm/pvtime.c b/arch/arm64/kvm/pvtime.c index 78a09f7a6637..4ceabaa4c30b 100644 --- a/arch/arm64/kvm/pvtime.c +++ b/arch/arm64/kvm/pvtime.c @@ -19,7 +19,7 @@ void kvm_update_stolen_time(struct kvm_vcpu *vcpu) u64 steal = 0; int idx; - if (base == GPA_INVALID) + if (base == INVALID_GPA) return; idx = srcu_read_lock(&kvm->srcu); @@ -40,7 +40,7 @@ long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu) switch (feature) { case ARM_SMCCC_HV_PV_TIME_FEATURES: case ARM_SMCCC_HV_PV_TIME_ST: - if (vcpu->arch.steal.base != GPA_INVALID) + if (vcpu->arch.steal.base != INVALID_GPA) val = SMCCC_RET_SUCCESS; break; } @@ -54,7 +54,7 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu) struct kvm *kvm = vcpu->kvm; u64 base = vcpu->arch.steal.base; - if (base == GPA_INVALID) + if (base == INVALID_GPA) return base; /* @@ -89,7 +89,7 @@ int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu, return -EFAULT; if (!IS_ALIGNED(ipa, 64)) return -EINVAL; - if (vcpu->arch.steal.base != GPA_INVALID) + if (vcpu->arch.steal.base != INVALID_GPA) return -EEXIST; /* Check the address is in a valid memslot */ diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index e0267f672b8a..49a3257dec46 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -27,10 +27,11 @@ #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> +#include <asm/kvm_nested.h> #include <asm/virt.h> /* Maximum phys_shift supported for any VM on this host */ -static u32 kvm_ipa_limit; +static u32 __ro_after_init kvm_ipa_limit; /* * ARMv8 Reset Values @@ -38,12 +39,15 @@ static u32 kvm_ipa_limit; #define VCPU_RESET_PSTATE_EL1 (PSR_MODE_EL1h | PSR_A_BIT | PSR_I_BIT | \ PSR_F_BIT | PSR_D_BIT) +#define VCPU_RESET_PSTATE_EL2 (PSR_MODE_EL2h | PSR_A_BIT | PSR_I_BIT | \ + PSR_F_BIT | PSR_D_BIT) + #define VCPU_RESET_PSTATE_SVC (PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \ PSR_AA32_I_BIT | PSR_AA32_F_BIT) -unsigned int kvm_sve_max_vl; +unsigned int __ro_after_init kvm_sve_max_vl; -int kvm_arm_init_sve(void) +int __init kvm_arm_init_sve(void) { if (system_supports_sve()) { kvm_sve_max_vl = sve_max_virtualisable_vl(); @@ -157,6 +161,7 @@ void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu) if (sve_state) kvm_unshare_hyp(sve_state, sve_state + vcpu_sve_state_size(vcpu)); kfree(sve_state); + kfree(vcpu->arch.ccsidr); } static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu) @@ -220,6 +225,10 @@ static int kvm_set_vm_width(struct kvm_vcpu *vcpu) if (kvm_has_mte(kvm) && is32bit) return -EINVAL; + /* NV is incompatible with AArch32 */ + if (vcpu_has_nv(vcpu) && is32bit) + return -EINVAL; + if (is32bit) set_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags); @@ -272,6 +281,12 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) if (loaded) kvm_arch_vcpu_put(vcpu); + /* Disallow NV+SVE for the time being */ + if (vcpu_has_nv(vcpu) && vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) { + ret = -EINVAL; + goto out; + } + if (!kvm_arm_vcpu_sve_finalized(vcpu)) { if (test_bit(KVM_ARM_VCPU_SVE, vcpu->arch.features)) { ret = kvm_vcpu_enable_sve(vcpu); @@ -294,6 +309,8 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) default: if (vcpu_el1_is_32bit(vcpu)) { pstate = VCPU_RESET_PSTATE_SVC; + } else if (vcpu_has_nv(vcpu)) { + pstate = VCPU_RESET_PSTATE_EL2; } else { pstate = VCPU_RESET_PSTATE_EL1; } @@ -352,7 +369,7 @@ u32 get_kvm_ipa_limit(void) return kvm_ipa_limit; } -int kvm_set_ipa_limit(void) +int __init kvm_set_ipa_limit(void) { unsigned int parange; u64 mmfr0; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index c6cbfe6b854b..53749d3a0996 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -11,6 +11,7 @@ #include <linux/bitfield.h> #include <linux/bsearch.h> +#include <linux/cacheinfo.h> #include <linux/kvm_host.h> #include <linux/mm.h> #include <linux/printk.h> @@ -24,6 +25,7 @@ #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> +#include <asm/kvm_nested.h> #include <asm/perf_event.h> #include <asm/sysreg.h> @@ -78,28 +80,112 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg) __vcpu_write_sys_reg_to_cpu(val, reg)) return; - __vcpu_sys_reg(vcpu, reg) = val; + __vcpu_sys_reg(vcpu, reg) = val; } -/* 3 bits per cache level, as per CLIDR, but non-existent caches always 0 */ -static u32 cache_levels; - /* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */ #define CSSELR_MAX 14 +/* + * Returns the minimum line size for the selected cache, expressed as + * Log2(bytes). + */ +static u8 get_min_cache_line_size(bool icache) +{ + u64 ctr = read_sanitised_ftr_reg(SYS_CTR_EL0); + u8 field; + + if (icache) + field = SYS_FIELD_GET(CTR_EL0, IminLine, ctr); + else + field = SYS_FIELD_GET(CTR_EL0, DminLine, ctr); + + /* + * Cache line size is represented as Log2(words) in CTR_EL0. + * Log2(bytes) can be derived with the following: + * + * Log2(words) + 2 = Log2(bytes / 4) + 2 + * = Log2(bytes) - 2 + 2 + * = Log2(bytes) + */ + return field + 2; +} + /* Which cache CCSIDR represents depends on CSSELR value. */ -static u32 get_ccsidr(u32 csselr) +static u32 get_ccsidr(struct kvm_vcpu *vcpu, u32 csselr) { - u32 ccsidr; + u8 line_size; - /* Make sure noone else changes CSSELR during this! */ - local_irq_disable(); - write_sysreg(csselr, csselr_el1); - isb(); - ccsidr = read_sysreg(ccsidr_el1); - local_irq_enable(); + if (vcpu->arch.ccsidr) + return vcpu->arch.ccsidr[csselr]; - return ccsidr; + line_size = get_min_cache_line_size(csselr & CSSELR_EL1_InD); + + /* + * Fabricate a CCSIDR value as the overriding value does not exist. + * The real CCSIDR value will not be used as it can vary by the + * physical CPU which the vcpu currently resides in. + * + * The line size is determined with get_min_cache_line_size(), which + * should be valid for all CPUs even if they have different cache + * configuration. + * + * The associativity bits are cleared, meaning the geometry of all data + * and unified caches (which are guaranteed to be PIPT and thus + * non-aliasing) are 1 set and 1 way. + * Guests should not be doing cache operations by set/way at all, and + * for this reason, we trap them and attempt to infer the intent, so + * that we can flush the entire guest's address space at the appropriate + * time. The exposed geometry minimizes the number of the traps. + * [If guests should attempt to infer aliasing properties from the + * geometry (which is not permitted by the architecture), they would + * only do so for virtually indexed caches.] + * + * We don't check if the cache level exists as it is allowed to return + * an UNKNOWN value if not. + */ + return SYS_FIELD_PREP(CCSIDR_EL1, LineSize, line_size - 4); +} + +static int set_ccsidr(struct kvm_vcpu *vcpu, u32 csselr, u32 val) +{ + u8 line_size = FIELD_GET(CCSIDR_EL1_LineSize, val) + 4; + u32 *ccsidr = vcpu->arch.ccsidr; + u32 i; + + if ((val & CCSIDR_EL1_RES0) || + line_size < get_min_cache_line_size(csselr & CSSELR_EL1_InD)) + return -EINVAL; + + if (!ccsidr) { + if (val == get_ccsidr(vcpu, csselr)) + return 0; + + ccsidr = kmalloc_array(CSSELR_MAX, sizeof(u32), GFP_KERNEL_ACCOUNT); + if (!ccsidr) + return -ENOMEM; + + for (i = 0; i < CSSELR_MAX; i++) + ccsidr[i] = get_ccsidr(vcpu, i); + + vcpu->arch.ccsidr = ccsidr; + } + + ccsidr[csselr] = val; + + return 0; +} + +static bool access_rw(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) + vcpu_write_sys_reg(vcpu, p->regval, r->reg); + else + p->regval = vcpu_read_sys_reg(vcpu, r->reg); + + return true; } /* @@ -260,6 +346,14 @@ static bool trap_raz_wi(struct kvm_vcpu *vcpu, return read_zero(vcpu, p); } +static bool trap_undef(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + kvm_inject_undefined(vcpu); + return false; +} + /* * ARMv8.1 mandates at least a trivial LORegion implementation, where all the * RW registers are RES0 (which we can implement as RAZ/WI). On an ARMv8.0 @@ -370,12 +464,9 @@ static bool trap_debug_regs(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { - if (p->is_write) { - vcpu_write_sys_reg(vcpu, p->regval, r->reg); + access_rw(vcpu, p, r); + if (p->is_write) vcpu_set_flag(vcpu, DEBUG_DIRTY); - } else { - p->regval = vcpu_read_sys_reg(vcpu, r->reg); - } trace_trap_reg(__func__, r->reg, p->is_write, p->regval); @@ -1049,7 +1140,9 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu, treg = TIMER_REG_CVAL; break; default: - BUG(); + print_sys_reg_msg(p, "%s", "Unhandled trapped timer register"); + kvm_inject_undefined(vcpu); + return false; } if (p->is_write) @@ -1155,6 +1248,12 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, struct sys_reg_desc const *r val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_DFR0_EL1_PerfMon), pmuver_to_perfmon(vcpu_pmuver(vcpu))); break; + case SYS_ID_AA64MMFR2_EL1: + val &= ~ID_AA64MMFR2_EL1_CCIDX_MASK; + break; + case SYS_ID_MMFR4_EL1: + val &= ~ARM64_FEATURE_MASK(ID_MMFR4_EL1_CCIDX); + break; } return val; @@ -1205,6 +1304,9 @@ static bool access_id_reg(struct kvm_vcpu *vcpu, return write_to_read_only(vcpu, p, r); p->regval = read_id_reg(vcpu, r); + if (vcpu_has_nv(vcpu)) + access_nested_id_reg(vcpu, p, r); + return true; } @@ -1385,10 +1487,78 @@ static bool access_clidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, if (p->is_write) return write_to_read_only(vcpu, p, r); - p->regval = read_sysreg(clidr_el1); + p->regval = __vcpu_sys_reg(vcpu, r->reg); return true; } +/* + * Fabricate a CLIDR_EL1 value instead of using the real value, which can vary + * by the physical CPU which the vcpu currently resides in. + */ +static void reset_clidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) +{ + u64 ctr_el0 = read_sanitised_ftr_reg(SYS_CTR_EL0); + u64 clidr; + u8 loc; + + if ((ctr_el0 & CTR_EL0_IDC)) { + /* + * Data cache clean to the PoU is not required so LoUU and LoUIS + * will not be set and a unified cache, which will be marked as + * LoC, will be added. + * + * If not DIC, let the unified cache L2 so that an instruction + * cache can be added as L1 later. + */ + loc = (ctr_el0 & CTR_EL0_DIC) ? 1 : 2; + clidr = CACHE_TYPE_UNIFIED << CLIDR_CTYPE_SHIFT(loc); + } else { + /* + * Data cache clean to the PoU is required so let L1 have a data + * cache and mark it as LoUU and LoUIS. As L1 has a data cache, + * it can be marked as LoC too. + */ + loc = 1; + clidr = 1 << CLIDR_LOUU_SHIFT; + clidr |= 1 << CLIDR_LOUIS_SHIFT; + clidr |= CACHE_TYPE_DATA << CLIDR_CTYPE_SHIFT(1); + } + + /* + * Instruction cache invalidation to the PoU is required so let L1 have + * an instruction cache. If L1 already has a data cache, it will be + * CACHE_TYPE_SEPARATE. + */ + if (!(ctr_el0 & CTR_EL0_DIC)) + clidr |= CACHE_TYPE_INST << CLIDR_CTYPE_SHIFT(1); + + clidr |= loc << CLIDR_LOC_SHIFT; + + /* + * Add tag cache unified to data cache. Allocation tags and data are + * unified in a cache line so that it looks valid even if there is only + * one cache line. + */ + if (kvm_has_mte(vcpu->kvm)) + clidr |= 2 << CLIDR_TTYPE_SHIFT(loc); + + __vcpu_sys_reg(vcpu, r->reg) = clidr; +} + +static int set_clidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, + u64 val) +{ + u64 ctr_el0 = read_sanitised_ftr_reg(SYS_CTR_EL0); + u64 idc = !CLIDR_LOC(val) || (!CLIDR_LOUIS(val) && !CLIDR_LOUU(val)); + + if ((val & CLIDR_EL1_RES0) || (!(ctr_el0 & CTR_EL0_IDC) && idc)) + return -EINVAL; + + __vcpu_sys_reg(vcpu, rd->reg) = val; + + return 0; +} + static bool access_csselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { @@ -1410,22 +1580,10 @@ static bool access_ccsidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, return write_to_read_only(vcpu, p, r); csselr = vcpu_read_sys_reg(vcpu, CSSELR_EL1); - p->regval = get_ccsidr(csselr); + csselr &= CSSELR_EL1_Level | CSSELR_EL1_InD; + if (csselr < CSSELR_MAX) + p->regval = get_ccsidr(vcpu, csselr); - /* - * Guests should not be doing cache operations by set/way at all, and - * for this reason, we trap them and attempt to infer the intent, so - * that we can flush the entire guest's address space at the appropriate - * time. - * To prevent this trapping from causing performance problems, let's - * expose the geometry of all data and unified caches (which are - * guaranteed to be PIPT and thus non-aliasing) as 1 set and 1 way. - * [If guests should attempt to infer aliasing properties from the - * geometry (which is not permitted by the architecture), they would - * only do so for virtually indexed caches.] - */ - if (!(csselr & 1)) // data or unified cache - p->regval &= ~GENMASK(27, 3); return true; } @@ -1446,6 +1604,44 @@ static unsigned int mte_visibility(const struct kvm_vcpu *vcpu, .visibility = mte_visibility, \ } +static unsigned int el2_visibility(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd) +{ + if (vcpu_has_nv(vcpu)) + return 0; + + return REG_HIDDEN; +} + +#define EL2_REG(name, acc, rst, v) { \ + SYS_DESC(SYS_##name), \ + .access = acc, \ + .reset = rst, \ + .reg = name, \ + .visibility = el2_visibility, \ + .val = v, \ +} + +/* + * EL{0,1}2 registers are the EL2 view on an EL0 or EL1 register when + * HCR_EL2.E2H==1, and only in the sysreg table for convenience of + * handling traps. Given that, they are always hidden from userspace. + */ +static unsigned int elx2_visibility(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd) +{ + return REG_HIDDEN_USER; +} + +#define EL12_REG(name, acc, rst, v) { \ + SYS_DESC(SYS_##name##_EL12), \ + .access = acc, \ + .reset = rst, \ + .reg = name##_EL1, \ + .val = v, \ + .visibility = elx2_visibility, \ +} + /* sys_reg_desc initialiser for known cpufeature ID registers */ #define ID_SANITISED(name) { \ SYS_DESC(SYS_##name), \ @@ -1490,6 +1686,42 @@ static unsigned int mte_visibility(const struct kvm_vcpu *vcpu, .visibility = raz_visibility, \ } +static bool access_sp_el1(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) + __vcpu_sys_reg(vcpu, SP_EL1) = p->regval; + else + p->regval = __vcpu_sys_reg(vcpu, SP_EL1); + + return true; +} + +static bool access_elr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) + vcpu_write_sys_reg(vcpu, p->regval, ELR_EL1); + else + p->regval = vcpu_read_sys_reg(vcpu, ELR_EL1); + + return true; +} + +static bool access_spsr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) + __vcpu_sys_reg(vcpu, SPSR_EL1) = p->regval; + else + p->regval = __vcpu_sys_reg(vcpu, SPSR_EL1); + + return true; +} + /* * Architected system registers. * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2 @@ -1646,6 +1878,9 @@ static const struct sys_reg_desc sys_reg_descs[] = { PTRAUTH_KEY(APDB), PTRAUTH_KEY(APGA), + { SYS_DESC(SYS_SPSR_EL1), access_spsr}, + { SYS_DESC(SYS_ELR_EL1), access_elr}, + { SYS_DESC(SYS_AFSR0_EL1), access_vm_reg, reset_unknown, AFSR0_EL1 }, { SYS_DESC(SYS_AFSR1_EL1), access_vm_reg, reset_unknown, AFSR1_EL1 }, { SYS_DESC(SYS_ESR_EL1), access_vm_reg, reset_unknown, ESR_EL1 }, @@ -1693,7 +1928,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_LORC_EL1), trap_loregion }, { SYS_DESC(SYS_LORID_EL1), trap_loregion }, - { SYS_DESC(SYS_VBAR_EL1), NULL, reset_val, VBAR_EL1, 0 }, + { SYS_DESC(SYS_VBAR_EL1), access_rw, reset_val, VBAR_EL1, 0 }, { SYS_DESC(SYS_DISR_EL1), NULL, reset_val, DISR_EL1, 0 }, { SYS_DESC(SYS_ICC_IAR0_EL1), write_to_read_only }, @@ -1717,7 +1952,9 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_CNTKCTL_EL1), NULL, reset_val, CNTKCTL_EL1, 0}, { SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr }, - { SYS_DESC(SYS_CLIDR_EL1), access_clidr }, + { SYS_DESC(SYS_CLIDR_EL1), access_clidr, reset_clidr, CLIDR_EL1, + .set_user = set_clidr }, + { SYS_DESC(SYS_CCSIDR2_EL1), undef_access }, { SYS_DESC(SYS_SMIDR_EL1), undef_access }, { SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 }, { SYS_DESC(SYS_CTR_EL0), access_ctr }, @@ -1913,9 +2150,67 @@ static const struct sys_reg_desc sys_reg_descs[] = { { PMU_SYS_REG(SYS_PMCCFILTR_EL0), .access = access_pmu_evtyper, .reset = reset_val, .reg = PMCCFILTR_EL0, .val = 0 }, + EL2_REG(VPIDR_EL2, access_rw, reset_unknown, 0), + EL2_REG(VMPIDR_EL2, access_rw, reset_unknown, 0), + EL2_REG(SCTLR_EL2, access_rw, reset_val, SCTLR_EL2_RES1), + EL2_REG(ACTLR_EL2, access_rw, reset_val, 0), + EL2_REG(HCR_EL2, access_rw, reset_val, 0), + EL2_REG(MDCR_EL2, access_rw, reset_val, 0), + EL2_REG(CPTR_EL2, access_rw, reset_val, CPTR_EL2_DEFAULT ), + EL2_REG(HSTR_EL2, access_rw, reset_val, 0), + EL2_REG(HACR_EL2, access_rw, reset_val, 0), + + EL2_REG(TTBR0_EL2, access_rw, reset_val, 0), + EL2_REG(TTBR1_EL2, access_rw, reset_val, 0), + EL2_REG(TCR_EL2, access_rw, reset_val, TCR_EL2_RES1), + EL2_REG(VTTBR_EL2, access_rw, reset_val, 0), + EL2_REG(VTCR_EL2, access_rw, reset_val, 0), + { SYS_DESC(SYS_DACR32_EL2), NULL, reset_unknown, DACR32_EL2 }, + EL2_REG(SPSR_EL2, access_rw, reset_val, 0), + EL2_REG(ELR_EL2, access_rw, reset_val, 0), + { SYS_DESC(SYS_SP_EL1), access_sp_el1}, + { SYS_DESC(SYS_IFSR32_EL2), NULL, reset_unknown, IFSR32_EL2 }, + EL2_REG(AFSR0_EL2, access_rw, reset_val, 0), + EL2_REG(AFSR1_EL2, access_rw, reset_val, 0), + EL2_REG(ESR_EL2, access_rw, reset_val, 0), { SYS_DESC(SYS_FPEXC32_EL2), NULL, reset_val, FPEXC32_EL2, 0x700 }, + + EL2_REG(FAR_EL2, access_rw, reset_val, 0), + EL2_REG(HPFAR_EL2, access_rw, reset_val, 0), + + EL2_REG(MAIR_EL2, access_rw, reset_val, 0), + EL2_REG(AMAIR_EL2, access_rw, reset_val, 0), + + EL2_REG(VBAR_EL2, access_rw, reset_val, 0), + EL2_REG(RVBAR_EL2, access_rw, reset_val, 0), + { SYS_DESC(SYS_RMR_EL2), trap_undef }, + + EL2_REG(CONTEXTIDR_EL2, access_rw, reset_val, 0), + EL2_REG(TPIDR_EL2, access_rw, reset_val, 0), + + EL2_REG(CNTVOFF_EL2, access_rw, reset_val, 0), + EL2_REG(CNTHCTL_EL2, access_rw, reset_val, 0), + + EL12_REG(SCTLR, access_vm_reg, reset_val, 0x00C50078), + EL12_REG(CPACR, access_rw, reset_val, 0), + EL12_REG(TTBR0, access_vm_reg, reset_unknown, 0), + EL12_REG(TTBR1, access_vm_reg, reset_unknown, 0), + EL12_REG(TCR, access_vm_reg, reset_val, 0), + { SYS_DESC(SYS_SPSR_EL12), access_spsr}, + { SYS_DESC(SYS_ELR_EL12), access_elr}, + EL12_REG(AFSR0, access_vm_reg, reset_unknown, 0), + EL12_REG(AFSR1, access_vm_reg, reset_unknown, 0), + EL12_REG(ESR, access_vm_reg, reset_unknown, 0), + EL12_REG(FAR, access_vm_reg, reset_unknown, 0), + EL12_REG(MAIR, access_vm_reg, reset_unknown, 0), + EL12_REG(AMAIR, access_vm_reg, reset_amair_el1, 0), + EL12_REG(VBAR, access_rw, reset_val, 0), + EL12_REG(CONTEXTIDR, access_vm_reg, reset_val, 0), + EL12_REG(CNTKCTL, access_rw, reset_val, 0), + + EL2_REG(SP_EL2, NULL, reset_unknown, 0), }; static bool trap_dbgdidr(struct kvm_vcpu *vcpu, @@ -2219,6 +2514,10 @@ static const struct sys_reg_desc cp15_regs[] = { { Op1(1), CRn( 0), CRm( 0), Op2(0), access_ccsidr }, { Op1(1), CRn( 0), CRm( 0), Op2(1), access_clidr }, + + /* CCSIDR2 */ + { Op1(1), CRn( 0), CRm( 0), Op2(2), undef_access }, + { Op1(2), CRn( 0), CRm( 0), Op2(0), access_csselr, NULL, CSSELR_EL1 }, }; @@ -2724,7 +3023,6 @@ id_to_sys_reg_desc(struct kvm_vcpu *vcpu, u64 id, FUNCTION_INVARIANT(midr_el1) FUNCTION_INVARIANT(revidr_el1) -FUNCTION_INVARIANT(clidr_el1) FUNCTION_INVARIANT(aidr_el1) static void get_ctr_el0(struct kvm_vcpu *v, const struct sys_reg_desc *r) @@ -2733,10 +3031,9 @@ static void get_ctr_el0(struct kvm_vcpu *v, const struct sys_reg_desc *r) } /* ->val is filled in by kvm_sys_reg_table_init() */ -static struct sys_reg_desc invariant_sys_regs[] = { +static struct sys_reg_desc invariant_sys_regs[] __ro_after_init = { { SYS_DESC(SYS_MIDR_EL1), NULL, get_midr_el1 }, { SYS_DESC(SYS_REVIDR_EL1), NULL, get_revidr_el1 }, - { SYS_DESC(SYS_CLIDR_EL1), NULL, get_clidr_el1 }, { SYS_DESC(SYS_AIDR_EL1), NULL, get_aidr_el1 }, { SYS_DESC(SYS_CTR_EL0), NULL, get_ctr_el0 }, }; @@ -2773,33 +3070,7 @@ static int set_invariant_sys_reg(u64 id, u64 __user *uaddr) return 0; } -static bool is_valid_cache(u32 val) -{ - u32 level, ctype; - - if (val >= CSSELR_MAX) - return false; - - /* Bottom bit is Instruction or Data bit. Next 3 bits are level. */ - level = (val >> 1); - ctype = (cache_levels >> (level * 3)) & 7; - - switch (ctype) { - case 0: /* No cache */ - return false; - case 1: /* Instruction cache only */ - return (val & 1); - case 2: /* Data cache only */ - case 4: /* Unified cache */ - return !(val & 1); - case 3: /* Separate instruction and data caches */ - return true; - default: /* Reserved: we can't know instruction or data. */ - return false; - } -} - -static int demux_c15_get(u64 id, void __user *uaddr) +static int demux_c15_get(struct kvm_vcpu *vcpu, u64 id, void __user *uaddr) { u32 val; u32 __user *uval = uaddr; @@ -2815,16 +3086,16 @@ static int demux_c15_get(u64 id, void __user *uaddr) return -ENOENT; val = (id & KVM_REG_ARM_DEMUX_VAL_MASK) >> KVM_REG_ARM_DEMUX_VAL_SHIFT; - if (!is_valid_cache(val)) + if (val >= CSSELR_MAX) return -ENOENT; - return put_user(get_ccsidr(val), uval); + return put_user(get_ccsidr(vcpu, val), uval); default: return -ENOENT; } } -static int demux_c15_set(u64 id, void __user *uaddr) +static int demux_c15_set(struct kvm_vcpu *vcpu, u64 id, void __user *uaddr) { u32 val, newval; u32 __user *uval = uaddr; @@ -2840,16 +3111,13 @@ static int demux_c15_set(u64 id, void __user *uaddr) return -ENOENT; val = (id & KVM_REG_ARM_DEMUX_VAL_MASK) >> KVM_REG_ARM_DEMUX_VAL_SHIFT; - if (!is_valid_cache(val)) + if (val >= CSSELR_MAX) return -ENOENT; if (get_user(newval, uval)) return -EFAULT; - /* This is also invariant: you can't change it. */ - if (newval != get_ccsidr(val)) - return -EINVAL; - return 0; + return set_ccsidr(vcpu, val, newval); default: return -ENOENT; } @@ -2864,7 +3132,7 @@ int kvm_sys_reg_get_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, int ret; r = id_to_sys_reg_desc(vcpu, reg->id, table, num); - if (!r) + if (!r || sysreg_hidden_user(vcpu, r)) return -ENOENT; if (r->get_user) { @@ -2886,7 +3154,7 @@ int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg int err; if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX) - return demux_c15_get(reg->id, uaddr); + return demux_c15_get(vcpu, reg->id, uaddr); err = get_invariant_sys_reg(reg->id, uaddr); if (err != -ENOENT) @@ -2908,7 +3176,7 @@ int kvm_sys_reg_set_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, return -EFAULT; r = id_to_sys_reg_desc(vcpu, reg->id, table, num); - if (!r) + if (!r || sysreg_hidden_user(vcpu, r)) return -ENOENT; if (sysreg_user_write_ignore(vcpu, r)) @@ -2930,7 +3198,7 @@ int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg int err; if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX) - return demux_c15_set(reg->id, uaddr); + return demux_c15_set(vcpu, reg->id, uaddr); err = set_invariant_sys_reg(reg->id, uaddr); if (err != -ENOENT) @@ -2942,13 +3210,7 @@ int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg static unsigned int num_demux_regs(void) { - unsigned int i, count = 0; - - for (i = 0; i < CSSELR_MAX; i++) - if (is_valid_cache(i)) - count++; - - return count; + return CSSELR_MAX; } static int write_demux_regids(u64 __user *uindices) @@ -2958,8 +3220,6 @@ static int write_demux_regids(u64 __user *uindices) val |= KVM_REG_ARM_DEMUX_ID_CCSIDR; for (i = 0; i < CSSELR_MAX; i++) { - if (!is_valid_cache(i)) - continue; if (put_user(val | i, uindices)) return -EFAULT; uindices++; @@ -3002,7 +3262,7 @@ static int walk_one_sys_reg(const struct kvm_vcpu *vcpu, if (!(rd->reg || rd->get_user)) return 0; - if (sysreg_hidden(vcpu, rd)) + if (sysreg_hidden_user(vcpu, rd)) return 0; if (!copy_reg_to_user(rd, uind)) @@ -3057,11 +3317,10 @@ int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) return write_demux_regids(uindices); } -int kvm_sys_reg_table_init(void) +int __init kvm_sys_reg_table_init(void) { bool valid = true; unsigned int i; - struct sys_reg_desc clidr; /* Make sure tables are unique and in order. */ valid &= check_sysreg_table(sys_reg_descs, ARRAY_SIZE(sys_reg_descs), false); @@ -3078,23 +3337,5 @@ int kvm_sys_reg_table_init(void) for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++) invariant_sys_regs[i].reset(NULL, &invariant_sys_regs[i]); - /* - * CLIDR format is awkward, so clean it up. See ARM B4.1.20: - * - * If software reads the Cache Type fields from Ctype1 - * upwards, once it has seen a value of 0b000, no caches - * exist at further-out levels of the hierarchy. So, for - * example, if Ctype3 is the first Cache Type field with a - * value of 0b000, the values of Ctype4 to Ctype7 must be - * ignored. - */ - get_clidr_el1(NULL, &clidr); /* Ugly... */ - cache_levels = clidr.val; - for (i = 0; i < 7; i++) - if (((cache_levels >> (i*3)) & 7) == 0) - break; - /* Clear all higher bits. */ - cache_levels &= (1 << (i*3))-1; - return 0; } diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h index e4ebb3a379fd..6b11f2cc7146 100644 --- a/arch/arm64/kvm/sys_regs.h +++ b/arch/arm64/kvm/sys_regs.h @@ -85,8 +85,9 @@ struct sys_reg_desc { }; #define REG_HIDDEN (1 << 0) /* hidden from userspace and guest */ -#define REG_RAZ (1 << 1) /* RAZ from userspace and guest */ -#define REG_USER_WI (1 << 2) /* WI from userspace only */ +#define REG_HIDDEN_USER (1 << 1) /* hidden from userspace only */ +#define REG_RAZ (1 << 2) /* RAZ from userspace and guest */ +#define REG_USER_WI (1 << 3) /* WI from userspace only */ static __printf(2, 3) inline void print_sys_reg_msg(const struct sys_reg_params *p, @@ -152,6 +153,15 @@ static inline bool sysreg_hidden(const struct kvm_vcpu *vcpu, return sysreg_visibility(vcpu, r) & REG_HIDDEN; } +static inline bool sysreg_hidden_user(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *r) +{ + if (likely(!r->visibility)) + return false; + + return r->visibility(vcpu, r) & (REG_HIDDEN | REG_HIDDEN_USER); +} + static inline bool sysreg_visible_as_raz(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { diff --git a/arch/arm64/kvm/trace_arm.h b/arch/arm64/kvm/trace_arm.h index 33e4e7dd2719..f3e46a976125 100644 --- a/arch/arm64/kvm/trace_arm.h +++ b/arch/arm64/kvm/trace_arm.h @@ -2,6 +2,7 @@ #if !defined(_TRACE_ARM_ARM64_KVM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_ARM_ARM64_KVM_H +#include <asm/kvm_emulate.h> #include <kvm/arm_arch_timer.h> #include <linux/tracepoint.h> @@ -301,6 +302,64 @@ TRACE_EVENT(kvm_timer_emulate, __entry->timer_idx, __entry->should_fire) ); +TRACE_EVENT(kvm_nested_eret, + TP_PROTO(struct kvm_vcpu *vcpu, unsigned long elr_el2, + unsigned long spsr_el2), + TP_ARGS(vcpu, elr_el2, spsr_el2), + + TP_STRUCT__entry( + __field(struct kvm_vcpu *, vcpu) + __field(unsigned long, elr_el2) + __field(unsigned long, spsr_el2) + __field(unsigned long, target_mode) + __field(unsigned long, hcr_el2) + ), + + TP_fast_assign( + __entry->vcpu = vcpu; + __entry->elr_el2 = elr_el2; + __entry->spsr_el2 = spsr_el2; + __entry->target_mode = spsr_el2 & (PSR_MODE_MASK | PSR_MODE32_BIT); + __entry->hcr_el2 = __vcpu_sys_reg(vcpu, HCR_EL2); + ), + + TP_printk("elr_el2: 0x%lx spsr_el2: 0x%08lx (M: %s) hcr_el2: %lx", + __entry->elr_el2, __entry->spsr_el2, + __print_symbolic(__entry->target_mode, kvm_mode_names), + __entry->hcr_el2) +); + +TRACE_EVENT(kvm_inject_nested_exception, + TP_PROTO(struct kvm_vcpu *vcpu, u64 esr_el2, int type), + TP_ARGS(vcpu, esr_el2, type), + + TP_STRUCT__entry( + __field(struct kvm_vcpu *, vcpu) + __field(unsigned long, esr_el2) + __field(int, type) + __field(unsigned long, spsr_el2) + __field(unsigned long, pc) + __field(unsigned long, source_mode) + __field(unsigned long, hcr_el2) + ), + + TP_fast_assign( + __entry->vcpu = vcpu; + __entry->esr_el2 = esr_el2; + __entry->type = type; + __entry->spsr_el2 = *vcpu_cpsr(vcpu); + __entry->pc = *vcpu_pc(vcpu); + __entry->source_mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT); + __entry->hcr_el2 = __vcpu_sys_reg(vcpu, HCR_EL2); + ), + + TP_printk("%s: esr_el2 0x%lx elr_el2: 0x%lx spsr_el2: 0x%08lx (M: %s) hcr_el2: %lx", + __print_symbolic(__entry->type, kvm_exception_type_names), + __entry->esr_el2, __entry->pc, __entry->spsr_el2, + __print_symbolic(__entry->source_mode, kvm_mode_names), + __entry->hcr_el2) +); + #endif /* _TRACE_ARM_ARM64_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index f6d4f4052555..cd134db41a57 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -465,17 +465,15 @@ out: /* GENERIC PROBE */ -static int vgic_init_cpu_starting(unsigned int cpu) +void kvm_vgic_cpu_up(void) { enable_percpu_irq(kvm_vgic_global_state.maint_irq, 0); - return 0; } -static int vgic_init_cpu_dying(unsigned int cpu) +void kvm_vgic_cpu_down(void) { disable_percpu_irq(kvm_vgic_global_state.maint_irq); - return 0; } static irqreturn_t vgic_maintenance_handler(int irq, void *data) @@ -572,7 +570,7 @@ int kvm_vgic_hyp_init(void) if (ret) return ret; - if (!has_mask) + if (!has_mask && !kvm_vgic_global_state.maint_irq) return 0; ret = request_percpu_irq(kvm_vgic_global_state.maint_irq, @@ -584,19 +582,6 @@ int kvm_vgic_hyp_init(void) return ret; } - ret = cpuhp_setup_state(CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING, - "kvm/arm/vgic:starting", - vgic_init_cpu_starting, vgic_init_cpu_dying); - if (ret) { - kvm_err("Cannot register vgic CPU notifier\n"); - goto out_free_irq; - } - kvm_info("vgic interrupt IRQ%d\n", kvm_vgic_global_state.maint_irq); return 0; - -out_free_irq: - free_percpu_irq(kvm_vgic_global_state.maint_irq, - kvm_get_running_vcpus()); - return ret; } diff --git a/arch/arm64/kvm/vgic/vgic-mmio.c b/arch/arm64/kvm/vgic/vgic-mmio.c index b32d434c1d4a..e67b3b2c8044 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio.c +++ b/arch/arm64/kvm/vgic/vgic-mmio.c @@ -473,9 +473,10 @@ int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu, * active state can be overwritten when the VCPU's state is synced coming back * from the guest. * - * For shared interrupts as well as GICv3 private interrupts, we have to - * stop all the VCPUs because interrupts can be migrated while we don't hold - * the IRQ locks and we don't want to be chasing moving targets. + * For shared interrupts as well as GICv3 private interrupts accessed from the + * non-owning CPU, we have to stop all the VCPUs because interrupts can be + * migrated while we don't hold the IRQ locks and we don't want to be chasing + * moving targets. * * For GICv2 private interrupts we don't have to do anything because * userspace accesses to the VGIC state already require all VCPUs to be @@ -484,7 +485,8 @@ int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu, */ static void vgic_access_active_prepare(struct kvm_vcpu *vcpu, u32 intid) { - if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || + if ((vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 && + vcpu != kvm_get_running_vcpu()) || intid >= VGIC_NR_PRIVATE_IRQS) kvm_arm_halt_guest(vcpu->kvm); } @@ -492,7 +494,8 @@ static void vgic_access_active_prepare(struct kvm_vcpu *vcpu, u32 intid) /* See vgic_access_active_prepare */ static void vgic_access_active_finish(struct kvm_vcpu *vcpu, u32 intid) { - if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || + if ((vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 && + vcpu != kvm_get_running_vcpu()) || intid >= VGIC_NR_PRIVATE_IRQS) kvm_arm_resume_guest(vcpu->kvm); } diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 684bdfaad4a9..469d816f356f 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -3,6 +3,7 @@ #include <linux/irqchip/arm-gic-v3.h> #include <linux/irq.h> #include <linux/irqdomain.h> +#include <linux/kstrtox.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <kvm/arm_vgic.h> @@ -584,25 +585,25 @@ DEFINE_STATIC_KEY_FALSE(vgic_v3_cpuif_trap); static int __init early_group0_trap_cfg(char *buf) { - return strtobool(buf, &group0_trap); + return kstrtobool(buf, &group0_trap); } early_param("kvm-arm.vgic_v3_group0_trap", early_group0_trap_cfg); static int __init early_group1_trap_cfg(char *buf) { - return strtobool(buf, &group1_trap); + return kstrtobool(buf, &group1_trap); } early_param("kvm-arm.vgic_v3_group1_trap", early_group1_trap_cfg); static int __init early_common_trap_cfg(char *buf) { - return strtobool(buf, &common_trap); + return kstrtobool(buf, &common_trap); } early_param("kvm-arm.vgic_v3_common_trap", early_common_trap_cfg); static int __init early_gicv4_enable(char *buf) { - return strtobool(buf, &gicv4_enable); + return kstrtobool(buf, &gicv4_enable); } early_param("kvm-arm.vgic_v4_enable", early_gicv4_enable); diff --git a/arch/arm64/kvm/vmid.c b/arch/arm64/kvm/vmid.c index d78ae63d7c15..08978d0672e7 100644 --- a/arch/arm64/kvm/vmid.c +++ b/arch/arm64/kvm/vmid.c @@ -16,7 +16,7 @@ #include <asm/kvm_asm.h> #include <asm/kvm_mmu.h> -unsigned int kvm_arm_vmid_bits; +unsigned int __ro_after_init kvm_arm_vmid_bits; static DEFINE_RAW_SPINLOCK(cpu_vmid_lock); static atomic64_t vmid_generation; @@ -172,7 +172,7 @@ void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid) /* * Initialize the VMID allocator */ -int kvm_arm_vmid_alloc_init(void) +int __init kvm_arm_vmid_alloc_init(void) { kvm_arm_vmid_bits = kvm_get_vmid_bits(); @@ -190,7 +190,7 @@ int kvm_arm_vmid_alloc_init(void) return 0; } -void kvm_arm_vmid_alloc_free(void) +void __init kvm_arm_vmid_alloc_free(void) { kfree(vmid_map); } diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index 10dcfa13390a..37b1340e9646 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -33,6 +33,7 @@ HAS_GIC_PRIO_MASKING HAS_GIC_PRIO_RELAXED_SYNC HAS_LDAPR HAS_LSE_ATOMICS +HAS_NESTED_VIRT HAS_NO_FPSIMD HAS_NO_HW_PREFETCH HAS_PAN diff --git a/arch/arm64/tools/gen-sysreg.awk b/arch/arm64/tools/gen-sysreg.awk index 7f27d66a17e1..6fa0468caa00 100755 --- a/arch/arm64/tools/gen-sysreg.awk +++ b/arch/arm64/tools/gen-sysreg.awk @@ -103,6 +103,7 @@ END { res0 = "UL(0)" res1 = "UL(0)" + unkn = "UL(0)" next_bit = 63 @@ -117,11 +118,13 @@ END { define(reg "_RES0", "(" res0 ")") define(reg "_RES1", "(" res1 ")") + define(reg "_UNKN", "(" unkn ")") print "" reg = null res0 = null res1 = null + unkn = null next } @@ -139,6 +142,7 @@ END { res0 = "UL(0)" res1 = "UL(0)" + unkn = "UL(0)" define("REG_" reg, "S" op0 "_" op1 "_C" crn "_C" crm "_" op2) define("SYS_" reg, "sys_reg(" op0 ", " op1 ", " crn ", " crm ", " op2 ")") @@ -166,7 +170,9 @@ END { define(reg "_RES0", "(" res0 ")") if (res1 != null) define(reg "_RES1", "(" res1 ")") - if (res0 != null || res1 != null) + if (unkn != null) + define(reg "_UNKN", "(" unkn ")") + if (res0 != null || res1 != null || unkn != null) print "" reg = null @@ -177,6 +183,7 @@ END { op2 = null res0 = null res1 = null + unkn = null next } @@ -195,6 +202,7 @@ END { next_bit = 0 res0 = null res1 = null + unkn = null next } @@ -220,6 +228,16 @@ END { next } +/^Unkn/ && (block == "Sysreg" || block == "SysregFields") { + expect_fields(2) + parse_bitdef(reg, "UNKN", $2) + field = "UNKN_" msb "_" lsb + + unkn = unkn " | GENMASK_ULL(" msb ", " lsb ")" + + next +} + /^Field/ && (block == "Sysreg" || block == "SysregFields") { expect_fields(3) field = $3 diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 94d78acafb67..dd5a9c7e310f 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -15,6 +15,8 @@ # Res1 <msb>[:<lsb>] +# Unkn <msb>[:<lsb>] + # Field <msb>[:<lsb>] <name> # Enum <msb>[:<lsb>] <name> @@ -1779,6 +1781,16 @@ Sysreg SCXTNUM_EL1 3 0 13 0 7 Field 63:0 SoftwareContextNumber EndSysreg +# The bit layout for CCSIDR_EL1 depends on whether FEAT_CCIDX is implemented. +# The following is for case when FEAT_CCIDX is not implemented. +Sysreg CCSIDR_EL1 3 1 0 0 0 +Res0 63:32 +Unkn 31:28 +Field 27:13 NumSets +Field 12:3 Associativity +Field 2:0 LineSize +EndSysreg + Sysreg CLIDR_EL1 3 1 0 0 1 Res0 63:47 Field 46:33 Ttypen @@ -1795,6 +1807,11 @@ Field 5:3 Ctype2 Field 2:0 Ctype1 EndSysreg +Sysreg CCSIDR2_EL1 3 1 0 0 2 +Res0 63:24 +Field 23:0 NumSets +EndSysreg + Sysreg GMID_EL1 3 1 0 0 4 Res0 63:4 Field 3:0 BS diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 5cedb28e8a40..2803c9c21ef9 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -758,7 +758,7 @@ struct kvm_mips_callbacks { void (*vcpu_reenter)(struct kvm_vcpu *vcpu); }; extern struct kvm_mips_callbacks *kvm_mips_callbacks; -int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks); +int kvm_mips_emulation_init(void); /* Debug: dump vcpu state */ int kvm_arch_vcpu_dump_regs(struct kvm_vcpu *vcpu); @@ -888,7 +888,6 @@ extern unsigned long kvm_mips_get_ramsize(struct kvm *kvm); extern int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_mips_interrupt *irq); -static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) {} diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig index 91d197bee9c0..29e51649203b 100644 --- a/arch/mips/kvm/Kconfig +++ b/arch/mips/kvm/Kconfig @@ -28,6 +28,7 @@ config KVM select MMU_NOTIFIER select SRCU select INTERVAL_TREE + select KVM_GENERIC_HARDWARE_ENABLING help Support for hosting Guest kernels. diff --git a/arch/mips/kvm/Makefile b/arch/mips/kvm/Makefile index 21ff75bcdbc4..805aeea2166e 100644 --- a/arch/mips/kvm/Makefile +++ b/arch/mips/kvm/Makefile @@ -17,4 +17,4 @@ kvm-$(CONFIG_CPU_LOONGSON64) += loongson_ipi.o kvm-y += vz.o obj-$(CONFIG_KVM) += kvm.o -obj-y += callback.o tlb.o +obj-y += tlb.o diff --git a/arch/mips/kvm/callback.c b/arch/mips/kvm/callback.c deleted file mode 100644 index d88aa2173fb0..000000000000 --- a/arch/mips/kvm/callback.c +++ /dev/null @@ -1,14 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2012 MIPS Technologies, Inc. All rights reserved. - * Authors: Yann Le Du <ledu@kymasys.com> - */ - -#include <linux/export.h> -#include <linux/kvm_host.h> - -struct kvm_mips_callbacks *kvm_mips_callbacks; -EXPORT_SYMBOL_GPL(kvm_mips_callbacks); diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index a25e0b73ee70..36c8991b5d39 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -135,16 +135,6 @@ void kvm_arch_hardware_disable(void) kvm_mips_callbacks->hardware_disable(); } -int kvm_arch_hardware_setup(void *opaque) -{ - return 0; -} - -int kvm_arch_check_processor_compat(void *opaque) -{ - return 0; -} - extern void kvm_init_loongson_ipi(struct kvm *kvm); int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) @@ -1015,21 +1005,6 @@ long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) return r; } -int kvm_arch_init(void *opaque) -{ - if (kvm_mips_callbacks) { - kvm_err("kvm: module already exists\n"); - return -EEXIST; - } - - return kvm_mips_emulation_init(&kvm_mips_callbacks); -} - -void kvm_arch_exit(void) -{ - kvm_mips_callbacks = NULL; -} - int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { @@ -1646,16 +1621,21 @@ static int __init kvm_mips_init(void) if (ret) return ret; - ret = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); - + ret = kvm_mips_emulation_init(); if (ret) return ret; + if (boot_cpu_type() == CPU_LOONGSON64) kvm_priority_to_irq = kvm_loongson3_priority_to_irq; register_die_notifier(&kvm_mips_csr_die_notifier); + ret = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); + if (ret) { + unregister_die_notifier(&kvm_mips_csr_die_notifier); + return ret; + } return 0; } diff --git a/arch/mips/kvm/vz.c b/arch/mips/kvm/vz.c index c706f5890a05..dafab003ea0d 100644 --- a/arch/mips/kvm/vz.c +++ b/arch/mips/kvm/vz.c @@ -3304,7 +3304,10 @@ static struct kvm_mips_callbacks kvm_vz_callbacks = { .vcpu_reenter = kvm_vz_vcpu_reenter, }; -int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks) +/* FIXME: Get rid of the callbacks now that trap-and-emulate is gone. */ +struct kvm_mips_callbacks *kvm_mips_callbacks = &kvm_vz_callbacks; + +int kvm_mips_emulation_init(void) { if (!cpu_has_vz) return -ENODEV; @@ -3318,7 +3321,5 @@ int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks) return -ENODEV; pr_info("Starting KVM with MIPS VZ extensions\n"); - - *install_callbacks = &kvm_vz_callbacks; return 0; } diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index caea15dcb91d..959f566a455c 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -876,13 +876,10 @@ struct kvm_vcpu_arch { #define __KVM_HAVE_ARCH_WQP #define __KVM_HAVE_CREATE_DEVICE -static inline void kvm_arch_hardware_disable(void) {} -static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {} static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} -static inline void kvm_arch_exit(void) {} static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index eae9619b6190..6bef23d6d0e3 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -118,7 +118,6 @@ extern int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, extern int kvmppc_core_vcpu_create(struct kvm_vcpu *vcpu); extern void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu); extern int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu); -extern int kvmppc_core_check_processor_compat(void); extern int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu, struct kvm_translation *tr); diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 6d525285dbe8..57f4e7896d67 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -999,16 +999,6 @@ int kvmppc_h_logical_ci_store(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvmppc_h_logical_ci_store); -int kvmppc_core_check_processor_compat(void) -{ - /* - * We always return 0 for book3s. We check - * for compatibility while loading the HV - * or PR module - */ - return 0; -} - int kvmppc_book3s_hcall_implemented(struct kvm *kvm, unsigned long hcall) { return kvm->arch.kvm_ops->hcall_implemented(hcall); @@ -1062,7 +1052,7 @@ static int kvmppc_book3s_init(void) { int r; - r = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); + r = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); if (r) return r; #ifdef CONFIG_KVM_BOOK3S_32_HANDLER diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index e89281d3ba28..01adffb24667 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -1210,7 +1210,7 @@ int kvmppc_handle_exit(struct kvm_vcpu *vcpu, unsigned int exit_nr) /* * On cores with Vector category, KVM is loaded only if CONFIG_ALTIVEC, - * see kvmppc_core_check_processor_compat(). + * see kvmppc_e500mc_check_processor_compat(). */ #ifdef CONFIG_ALTIVEC case BOOKE_INTERRUPT_ALTIVEC_UNAVAIL: diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index c8b2b4478545..b0f695428733 100644 --- a/arch/powerpc/kvm/e500.c +++ b/arch/powerpc/kvm/e500.c @@ -314,7 +314,7 @@ static void kvmppc_core_vcpu_put_e500(struct kvm_vcpu *vcpu) kvmppc_booke_vcpu_put(vcpu); } -int kvmppc_core_check_processor_compat(void) +static int kvmppc_e500_check_processor_compat(void) { int r; @@ -507,7 +507,7 @@ static int __init kvmppc_e500_init(void) unsigned long handler_len; unsigned long max_ivor = 0; - r = kvmppc_core_check_processor_compat(); + r = kvmppc_e500_check_processor_compat(); if (r) goto err_out; @@ -531,7 +531,7 @@ static int __init kvmppc_e500_init(void) flush_icache_range(kvmppc_booke_handlers, kvmppc_booke_handlers + ivor[max_ivor] + handler_len); - r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE); + r = kvm_init(sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE); if (r) goto err_out; kvm_ops_e500.owner = THIS_MODULE; diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index 57e0ad6a2ca3..a309138927ff 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -168,7 +168,7 @@ static void kvmppc_core_vcpu_put_e500mc(struct kvm_vcpu *vcpu) kvmppc_booke_vcpu_put(vcpu); } -int kvmppc_core_check_processor_compat(void) +int kvmppc_e500mc_check_processor_compat(void) { int r; @@ -388,6 +388,10 @@ static int __init kvmppc_e500mc_init(void) { int r; + r = kvmppc_e500mc_check_processor_compat(); + if (r) + goto err_out; + r = kvmppc_booke_init(); if (r) goto err_out; @@ -400,7 +404,7 @@ static int __init kvmppc_e500mc_init(void) */ kvmppc_init_lpid(KVMPPC_NR_LPIDS/threads_per_core); - r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE); + r = kvm_init(sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE); if (r) goto err_out; kvm_ops_e500mc.owner = THIS_MODULE; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 04494a4fb37a..4c5405fc5538 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -435,21 +435,6 @@ int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, } EXPORT_SYMBOL_GPL(kvmppc_ld); -int kvm_arch_hardware_enable(void) -{ - return 0; -} - -int kvm_arch_hardware_setup(void *opaque) -{ - return 0; -} - -int kvm_arch_check_processor_compat(void *opaque) -{ - return kvmppc_core_check_processor_compat(); -} - int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { struct kvmppc_ops *kvm_ops = NULL; @@ -2544,11 +2529,6 @@ void kvmppc_init_lpid(unsigned long nr_lpids_param) } EXPORT_SYMBOL_GPL(kvmppc_init_lpid); -int kvm_arch_init(void *opaque) -{ - return 0; -} - EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ppc_instr); void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry) diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 93f43a3e7886..cc7da66ee0c0 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -18,6 +18,7 @@ #include <asm/kvm_vcpu_insn.h> #include <asm/kvm_vcpu_sbi.h> #include <asm/kvm_vcpu_timer.h> +#include <asm/kvm_vcpu_pmu.h> #define KVM_MAX_VCPUS 1024 @@ -228,9 +229,11 @@ struct kvm_vcpu_arch { /* Don't run the VCPU (blocked) */ bool pause; + + /* Performance monitoring context */ + struct kvm_pmu pmu_context; }; -static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} @@ -297,11 +300,11 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu, int kvm_riscv_gstage_alloc_pgd(struct kvm *kvm); void kvm_riscv_gstage_free_pgd(struct kvm *kvm); void kvm_riscv_gstage_update_hgatp(struct kvm_vcpu *vcpu); -void kvm_riscv_gstage_mode_detect(void); -unsigned long kvm_riscv_gstage_mode(void); +void __init kvm_riscv_gstage_mode_detect(void); +unsigned long __init kvm_riscv_gstage_mode(void); int kvm_riscv_gstage_gpa_bits(void); -void kvm_riscv_gstage_vmid_detect(void); +void __init kvm_riscv_gstage_vmid_detect(void); unsigned long kvm_riscv_gstage_vmid_bits(void); int kvm_riscv_gstage_vmid_init(struct kvm *kvm); bool kvm_riscv_gstage_vmid_ver_changed(struct kvm_vmid *vmid); diff --git a/arch/riscv/include/asm/kvm_vcpu_pmu.h b/arch/riscv/include/asm/kvm_vcpu_pmu.h new file mode 100644 index 000000000000..395518a1664e --- /dev/null +++ b/arch/riscv/include/asm/kvm_vcpu_pmu.h @@ -0,0 +1,107 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2023 Rivos Inc + * + * Authors: + * Atish Patra <atishp@rivosinc.com> + */ + +#ifndef __KVM_VCPU_RISCV_PMU_H +#define __KVM_VCPU_RISCV_PMU_H + +#include <linux/perf/riscv_pmu.h> +#include <asm/sbi.h> + +#ifdef CONFIG_RISCV_PMU_SBI +#define RISCV_KVM_MAX_FW_CTRS 32 +#define RISCV_KVM_MAX_HW_CTRS 32 +#define RISCV_KVM_MAX_COUNTERS (RISCV_KVM_MAX_HW_CTRS + RISCV_KVM_MAX_FW_CTRS) +static_assert(RISCV_KVM_MAX_COUNTERS <= 64); + +struct kvm_fw_event { + /* Current value of the event */ + unsigned long value; + + /* Event monitoring status */ + bool started; +}; + +/* Per virtual pmu counter data */ +struct kvm_pmc { + u8 idx; + struct perf_event *perf_event; + u64 counter_val; + union sbi_pmu_ctr_info cinfo; + /* Event monitoring status */ + bool started; + /* Monitoring event ID */ + unsigned long event_idx; +}; + +/* PMU data structure per vcpu */ +struct kvm_pmu { + struct kvm_pmc pmc[RISCV_KVM_MAX_COUNTERS]; + struct kvm_fw_event fw_event[RISCV_KVM_MAX_FW_CTRS]; + /* Number of the virtual firmware counters available */ + int num_fw_ctrs; + /* Number of the virtual hardware counters available */ + int num_hw_ctrs; + /* A flag to indicate that pmu initialization is done */ + bool init_done; + /* Bit map of all the virtual counter used */ + DECLARE_BITMAP(pmc_in_use, RISCV_KVM_MAX_COUNTERS); +}; + +#define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu_context) +#define pmu_to_vcpu(pmu) (container_of((pmu), struct kvm_vcpu, arch.pmu_context)) + +#if defined(CONFIG_32BIT) +#define KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS \ +{.base = CSR_CYCLEH, .count = 31, .func = kvm_riscv_vcpu_pmu_read_hpm }, \ +{.base = CSR_CYCLE, .count = 31, .func = kvm_riscv_vcpu_pmu_read_hpm }, +#else +#define KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS \ +{.base = CSR_CYCLE, .count = 31, .func = kvm_riscv_vcpu_pmu_read_hpm }, +#endif + +int kvm_riscv_vcpu_pmu_incr_fw(struct kvm_vcpu *vcpu, unsigned long fid); +int kvm_riscv_vcpu_pmu_read_hpm(struct kvm_vcpu *vcpu, unsigned int csr_num, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask); + +int kvm_riscv_vcpu_pmu_num_ctrs(struct kvm_vcpu *vcpu, struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_ctr_info(struct kvm_vcpu *vcpu, unsigned long cidx, + struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_ctr_start(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, u64 ival, + struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, + struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_ctr_cfg_match(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, + unsigned long eidx, u64 evtdata, + struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx, + struct kvm_vcpu_sbi_return *retdata); +void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_pmu_deinit(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_pmu_reset(struct kvm_vcpu *vcpu); + +#else +struct kvm_pmu { +}; + +#define KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS \ +{.base = 0, .count = 0, .func = NULL }, + +static inline void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu) {} +static inline int kvm_riscv_vcpu_pmu_incr_fw(struct kvm_vcpu *vcpu, unsigned long fid) +{ + return 0; +} + +static inline void kvm_riscv_vcpu_pmu_deinit(struct kvm_vcpu *vcpu) {} +static inline void kvm_riscv_vcpu_pmu_reset(struct kvm_vcpu *vcpu) {} +#endif /* CONFIG_RISCV_PMU_SBI */ +#endif /* !__KVM_VCPU_RISCV_PMU_H */ diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h index f79478a85d2d..8425556af7d1 100644 --- a/arch/riscv/include/asm/kvm_vcpu_sbi.h +++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h @@ -18,6 +18,13 @@ struct kvm_vcpu_sbi_context { int return_handled; }; +struct kvm_vcpu_sbi_return { + unsigned long out_val; + unsigned long err_val; + struct kvm_cpu_trap *utrap; + bool uexit; +}; + struct kvm_vcpu_sbi_extension { unsigned long extid_start; unsigned long extid_end; @@ -27,8 +34,10 @@ struct kvm_vcpu_sbi_extension { * specific error codes. */ int (*handler)(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, struct kvm_cpu_trap *utrap, - bool *exit); + struct kvm_vcpu_sbi_return *retdata); + + /* Extension specific probe function */ + unsigned long (*probe)(struct kvm_vcpu *vcpu); }; void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run); diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h index 4ca7fbacff42..945b7be249c1 100644 --- a/arch/riscv/include/asm/sbi.h +++ b/arch/riscv/include/asm/sbi.h @@ -169,9 +169,9 @@ enum sbi_pmu_fw_generic_events_t { SBI_PMU_FW_ILLEGAL_INSN = 4, SBI_PMU_FW_SET_TIMER = 5, SBI_PMU_FW_IPI_SENT = 6, - SBI_PMU_FW_IPI_RECVD = 7, + SBI_PMU_FW_IPI_RCVD = 7, SBI_PMU_FW_FENCE_I_SENT = 8, - SBI_PMU_FW_FENCE_I_RECVD = 9, + SBI_PMU_FW_FENCE_I_RCVD = 9, SBI_PMU_FW_SFENCE_VMA_SENT = 10, SBI_PMU_FW_SFENCE_VMA_RCVD = 11, SBI_PMU_FW_SFENCE_VMA_ASID_SENT = 12, @@ -215,6 +215,9 @@ enum sbi_pmu_ctr_type { #define SBI_PMU_EVENT_CACHE_OP_ID_CODE_MASK 0x06 #define SBI_PMU_EVENT_CACHE_RESULT_ID_CODE_MASK 0x01 +#define SBI_PMU_EVENT_CACHE_ID_SHIFT 3 +#define SBI_PMU_EVENT_CACHE_OP_SHIFT 1 + #define SBI_PMU_EVENT_IDX_INVALID 0xFFFFFFFF /* Flags defined for config matching function */ diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig index f36a737d5f96..d5a658a047a7 100644 --- a/arch/riscv/kvm/Kconfig +++ b/arch/riscv/kvm/Kconfig @@ -20,6 +20,7 @@ if VIRTUALIZATION config KVM tristate "Kernel-based Virtual Machine (KVM) support (EXPERIMENTAL)" depends on RISCV_SBI && MMU + select KVM_GENERIC_HARDWARE_ENABLING select MMU_NOTIFIER select PREEMPT_NOTIFIERS select KVM_MMIO diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile index 019df9208bdd..278e97c06e0a 100644 --- a/arch/riscv/kvm/Makefile +++ b/arch/riscv/kvm/Makefile @@ -25,3 +25,4 @@ kvm-y += vcpu_sbi_base.o kvm-y += vcpu_sbi_replace.o kvm-y += vcpu_sbi_hsm.o kvm-y += vcpu_timer.o +kvm-$(CONFIG_RISCV_PMU_SBI) += vcpu_pmu.o vcpu_sbi_pmu.o diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c index 58c5489d3031..41ad7639a17b 100644 --- a/arch/riscv/kvm/main.c +++ b/arch/riscv/kvm/main.c @@ -20,16 +20,6 @@ long kvm_arch_dev_ioctl(struct file *filp, return -EINVAL; } -int kvm_arch_check_processor_compat(void *opaque) -{ - return 0; -} - -int kvm_arch_hardware_setup(void *opaque) -{ - return 0; -} - int kvm_arch_hardware_enable(void) { unsigned long hideleg, hedeleg; @@ -49,7 +39,8 @@ int kvm_arch_hardware_enable(void) hideleg |= (1UL << IRQ_VS_EXT); csr_write(CSR_HIDELEG, hideleg); - csr_write(CSR_HCOUNTEREN, -1UL); + /* VS should access only the time counter directly. Everything else should trap */ + csr_write(CSR_HCOUNTEREN, 0x02); csr_write(CSR_HVIP, 0); @@ -70,7 +61,7 @@ void kvm_arch_hardware_disable(void) csr_write(CSR_HIDELEG, 0); } -int kvm_arch_init(void *opaque) +static int __init riscv_kvm_init(void) { const char *str; @@ -115,16 +106,7 @@ int kvm_arch_init(void *opaque) kvm_info("VMID %ld bits available\n", kvm_riscv_gstage_vmid_bits()); - return 0; -} - -void kvm_arch_exit(void) -{ -} - -static int __init riscv_kvm_init(void) -{ - return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); + return kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); } module_init(riscv_kvm_init); diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index 34b57e0be2ef..78211aed36fa 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -20,12 +20,12 @@ #include <asm/pgtable.h> #ifdef CONFIG_64BIT -static unsigned long gstage_mode = (HGATP_MODE_SV39X4 << HGATP_MODE_SHIFT); -static unsigned long gstage_pgd_levels = 3; +static unsigned long gstage_mode __ro_after_init = (HGATP_MODE_SV39X4 << HGATP_MODE_SHIFT); +static unsigned long gstage_pgd_levels __ro_after_init = 3; #define gstage_index_bits 9 #else -static unsigned long gstage_mode = (HGATP_MODE_SV32X4 << HGATP_MODE_SHIFT); -static unsigned long gstage_pgd_levels = 2; +static unsigned long gstage_mode __ro_after_init = (HGATP_MODE_SV32X4 << HGATP_MODE_SHIFT); +static unsigned long gstage_pgd_levels __ro_after_init = 2; #define gstage_index_bits 10 #endif @@ -585,7 +585,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) if (!kvm->arch.pgd) return false; - WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PGDIR_SIZE); + WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE); if (!gstage_get_leaf_entry(kvm, range->start << PAGE_SHIFT, &ptep, &ptep_level)) @@ -603,7 +603,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) if (!kvm->arch.pgd) return false; - WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PGDIR_SIZE); + WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE); if (!gstage_get_leaf_entry(kvm, range->start << PAGE_SHIFT, &ptep, &ptep_level)) @@ -645,12 +645,12 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu, if (logging || (vma->vm_flags & VM_PFNMAP)) vma_pagesize = PAGE_SIZE; - if (vma_pagesize == PMD_SIZE || vma_pagesize == PGDIR_SIZE) + if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE) gfn = (gpa & huge_page_mask(hstate_vma(vma))) >> PAGE_SHIFT; mmap_read_unlock(current->mm); - if (vma_pagesize != PGDIR_SIZE && + if (vma_pagesize != PUD_SIZE && vma_pagesize != PMD_SIZE && vma_pagesize != PAGE_SIZE) { kvm_err("Invalid VMA page size 0x%lx\n", vma_pagesize); @@ -758,7 +758,7 @@ void kvm_riscv_gstage_update_hgatp(struct kvm_vcpu *vcpu) kvm_riscv_local_hfence_gvma_all(); } -void kvm_riscv_gstage_mode_detect(void) +void __init kvm_riscv_gstage_mode_detect(void) { #ifdef CONFIG_64BIT /* Try Sv57x4 G-stage mode */ @@ -782,7 +782,7 @@ skip_sv48x4_test: #endif } -unsigned long kvm_riscv_gstage_mode(void) +unsigned long __init kvm_riscv_gstage_mode(void) { return gstage_mode >> HGATP_MODE_SHIFT; } diff --git a/arch/riscv/kvm/tlb.c b/arch/riscv/kvm/tlb.c index aa3da18ad873..0e5479600695 100644 --- a/arch/riscv/kvm/tlb.c +++ b/arch/riscv/kvm/tlb.c @@ -180,6 +180,7 @@ void kvm_riscv_local_tlb_sanitize(struct kvm_vcpu *vcpu) void kvm_riscv_fence_i_process(struct kvm_vcpu *vcpu) { + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_FENCE_I_RCVD); local_flush_icache_all(); } @@ -263,15 +264,18 @@ void kvm_riscv_hfence_process(struct kvm_vcpu *vcpu) d.addr, d.size, d.order); break; case KVM_RISCV_HFENCE_VVMA_ASID_GVA: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_ASID_RCVD); kvm_riscv_local_hfence_vvma_asid_gva( READ_ONCE(v->vmid), d.asid, d.addr, d.size, d.order); break; case KVM_RISCV_HFENCE_VVMA_ASID_ALL: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_ASID_RCVD); kvm_riscv_local_hfence_vvma_asid_all( READ_ONCE(v->vmid), d.asid); break; case KVM_RISCV_HFENCE_VVMA_GVA: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_RCVD); kvm_riscv_local_hfence_vvma_gva( READ_ONCE(v->vmid), d.addr, d.size, d.order); diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 7c08567097f0..7d010b0be54e 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -138,6 +138,8 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu) WRITE_ONCE(vcpu->arch.irqs_pending, 0); WRITE_ONCE(vcpu->arch.irqs_pending_mask, 0); + kvm_riscv_vcpu_pmu_reset(vcpu); + vcpu->arch.hfence_head = 0; vcpu->arch.hfence_tail = 0; memset(vcpu->arch.hfence_queue, 0, sizeof(vcpu->arch.hfence_queue)); @@ -194,6 +196,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) /* Setup VCPU timer */ kvm_riscv_vcpu_timer_init(vcpu); + /* setup performance monitoring */ + kvm_riscv_vcpu_pmu_init(vcpu); + /* Reset VCPU */ kvm_riscv_reset_vcpu(vcpu); @@ -216,6 +221,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) /* Cleanup VCPU timer */ kvm_riscv_vcpu_timer_deinit(vcpu); + kvm_riscv_vcpu_pmu_deinit(vcpu); + /* Free unused pages pre-allocated for G-stage page table mappings */ kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); } diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c index c9f741ab26f5..4ea101a73d8b 100644 --- a/arch/riscv/kvm/vcpu_exit.c +++ b/arch/riscv/kvm/vcpu_exit.c @@ -160,6 +160,9 @@ void kvm_riscv_vcpu_trap_redirect(struct kvm_vcpu *vcpu, /* Set Guest PC to Guest exception vector */ vcpu->arch.guest_context.sepc = csr_read(CSR_VSTVEC); + + /* Set Guest privilege mode to supervisor */ + vcpu->arch.guest_context.sstatus |= SR_SPP; } /* @@ -179,6 +182,12 @@ int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, ret = -EFAULT; run->exit_reason = KVM_EXIT_UNKNOWN; switch (trap->scause) { + case EXC_INST_ILLEGAL: + if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) { + kvm_riscv_vcpu_trap_redirect(vcpu, trap); + ret = 1; + } + break; case EXC_VIRTUAL_INST_FAULT: if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) ret = kvm_riscv_vcpu_virtual_insn(vcpu, run, trap); diff --git a/arch/riscv/kvm/vcpu_insn.c b/arch/riscv/kvm/vcpu_insn.c index 0bb52761a3f7..f689337b78ff 100644 --- a/arch/riscv/kvm/vcpu_insn.c +++ b/arch/riscv/kvm/vcpu_insn.c @@ -213,7 +213,9 @@ struct csr_func { unsigned long wr_mask); }; -static const struct csr_func csr_funcs[] = { }; +static const struct csr_func csr_funcs[] = { + KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS +}; /** * kvm_riscv_vcpu_csr_return -- Handle CSR read/write after user space diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c new file mode 100644 index 000000000000..86391a5061dd --- /dev/null +++ b/arch/riscv/kvm/vcpu_pmu.c @@ -0,0 +1,633 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023 Rivos Inc + * + * Authors: + * Atish Patra <atishp@rivosinc.com> + */ + +#define pr_fmt(fmt) "riscv-kvm-pmu: " fmt +#include <linux/errno.h> +#include <linux/err.h> +#include <linux/kvm_host.h> +#include <linux/perf/riscv_pmu.h> +#include <asm/csr.h> +#include <asm/kvm_vcpu_sbi.h> +#include <asm/kvm_vcpu_pmu.h> +#include <linux/bitops.h> + +#define kvm_pmu_num_counters(pmu) ((pmu)->num_hw_ctrs + (pmu)->num_fw_ctrs) +#define get_event_type(x) (((x) & SBI_PMU_EVENT_IDX_TYPE_MASK) >> 16) +#define get_event_code(x) ((x) & SBI_PMU_EVENT_IDX_CODE_MASK) + +static enum perf_hw_id hw_event_perf_map[SBI_PMU_HW_GENERAL_MAX] = { + [SBI_PMU_HW_CPU_CYCLES] = PERF_COUNT_HW_CPU_CYCLES, + [SBI_PMU_HW_INSTRUCTIONS] = PERF_COUNT_HW_INSTRUCTIONS, + [SBI_PMU_HW_CACHE_REFERENCES] = PERF_COUNT_HW_CACHE_REFERENCES, + [SBI_PMU_HW_CACHE_MISSES] = PERF_COUNT_HW_CACHE_MISSES, + [SBI_PMU_HW_BRANCH_INSTRUCTIONS] = PERF_COUNT_HW_BRANCH_INSTRUCTIONS, + [SBI_PMU_HW_BRANCH_MISSES] = PERF_COUNT_HW_BRANCH_MISSES, + [SBI_PMU_HW_BUS_CYCLES] = PERF_COUNT_HW_BUS_CYCLES, + [SBI_PMU_HW_STALLED_CYCLES_FRONTEND] = PERF_COUNT_HW_STALLED_CYCLES_FRONTEND, + [SBI_PMU_HW_STALLED_CYCLES_BACKEND] = PERF_COUNT_HW_STALLED_CYCLES_BACKEND, + [SBI_PMU_HW_REF_CPU_CYCLES] = PERF_COUNT_HW_REF_CPU_CYCLES, +}; + +static u64 kvm_pmu_get_sample_period(struct kvm_pmc *pmc) +{ + u64 counter_val_mask = GENMASK(pmc->cinfo.width, 0); + u64 sample_period; + + if (!pmc->counter_val) + sample_period = counter_val_mask + 1; + else + sample_period = (-pmc->counter_val) & counter_val_mask; + + return sample_period; +} + +static u32 kvm_pmu_get_perf_event_type(unsigned long eidx) +{ + enum sbi_pmu_event_type etype = get_event_type(eidx); + u32 type = PERF_TYPE_MAX; + + switch (etype) { + case SBI_PMU_EVENT_TYPE_HW: + type = PERF_TYPE_HARDWARE; + break; + case SBI_PMU_EVENT_TYPE_CACHE: + type = PERF_TYPE_HW_CACHE; + break; + case SBI_PMU_EVENT_TYPE_RAW: + case SBI_PMU_EVENT_TYPE_FW: + type = PERF_TYPE_RAW; + break; + default: + break; + } + + return type; +} + +static bool kvm_pmu_is_fw_event(unsigned long eidx) +{ + return get_event_type(eidx) == SBI_PMU_EVENT_TYPE_FW; +} + +static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc) +{ + if (pmc->perf_event) { + perf_event_disable(pmc->perf_event); + perf_event_release_kernel(pmc->perf_event); + pmc->perf_event = NULL; + } +} + +static u64 kvm_pmu_get_perf_event_hw_config(u32 sbi_event_code) +{ + return hw_event_perf_map[sbi_event_code]; +} + +static u64 kvm_pmu_get_perf_event_cache_config(u32 sbi_event_code) +{ + u64 config = U64_MAX; + unsigned int cache_type, cache_op, cache_result; + + /* All the cache event masks lie within 0xFF. No separate masking is necessary */ + cache_type = (sbi_event_code & SBI_PMU_EVENT_CACHE_ID_CODE_MASK) >> + SBI_PMU_EVENT_CACHE_ID_SHIFT; + cache_op = (sbi_event_code & SBI_PMU_EVENT_CACHE_OP_ID_CODE_MASK) >> + SBI_PMU_EVENT_CACHE_OP_SHIFT; + cache_result = sbi_event_code & SBI_PMU_EVENT_CACHE_RESULT_ID_CODE_MASK; + + if (cache_type >= PERF_COUNT_HW_CACHE_MAX || + cache_op >= PERF_COUNT_HW_CACHE_OP_MAX || + cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX) + return config; + + config = cache_type | (cache_op << 8) | (cache_result << 16); + + return config; +} + +static u64 kvm_pmu_get_perf_event_config(unsigned long eidx, uint64_t evt_data) +{ + enum sbi_pmu_event_type etype = get_event_type(eidx); + u32 ecode = get_event_code(eidx); + u64 config = U64_MAX; + + switch (etype) { + case SBI_PMU_EVENT_TYPE_HW: + if (ecode < SBI_PMU_HW_GENERAL_MAX) + config = kvm_pmu_get_perf_event_hw_config(ecode); + break; + case SBI_PMU_EVENT_TYPE_CACHE: + config = kvm_pmu_get_perf_event_cache_config(ecode); + break; + case SBI_PMU_EVENT_TYPE_RAW: + config = evt_data & RISCV_PMU_RAW_EVENT_MASK; + break; + case SBI_PMU_EVENT_TYPE_FW: + if (ecode < SBI_PMU_FW_MAX) + config = (1ULL << 63) | ecode; + break; + default: + break; + } + + return config; +} + +static int kvm_pmu_get_fixed_pmc_index(unsigned long eidx) +{ + u32 etype = kvm_pmu_get_perf_event_type(eidx); + u32 ecode = get_event_code(eidx); + + if (etype != SBI_PMU_EVENT_TYPE_HW) + return -EINVAL; + + if (ecode == SBI_PMU_HW_CPU_CYCLES) + return 0; + else if (ecode == SBI_PMU_HW_INSTRUCTIONS) + return 2; + else + return -EINVAL; +} + +static int kvm_pmu_get_programmable_pmc_index(struct kvm_pmu *kvpmu, unsigned long eidx, + unsigned long cbase, unsigned long cmask) +{ + int ctr_idx = -1; + int i, pmc_idx; + int min, max; + + if (kvm_pmu_is_fw_event(eidx)) { + /* Firmware counters are mapped 1:1 starting from num_hw_ctrs for simplicity */ + min = kvpmu->num_hw_ctrs; + max = min + kvpmu->num_fw_ctrs; + } else { + /* First 3 counters are reserved for fixed counters */ + min = 3; + max = kvpmu->num_hw_ctrs; + } + + for_each_set_bit(i, &cmask, BITS_PER_LONG) { + pmc_idx = i + cbase; + if ((pmc_idx >= min && pmc_idx < max) && + !test_bit(pmc_idx, kvpmu->pmc_in_use)) { + ctr_idx = pmc_idx; + break; + } + } + + return ctr_idx; +} + +static int pmu_get_pmc_index(struct kvm_pmu *pmu, unsigned long eidx, + unsigned long cbase, unsigned long cmask) +{ + int ret; + + /* Fixed counters need to be have fixed mapping as they have different width */ + ret = kvm_pmu_get_fixed_pmc_index(eidx); + if (ret >= 0) + return ret; + + return kvm_pmu_get_programmable_pmc_index(pmu, eidx, cbase, cmask); +} + +static int pmu_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx, + unsigned long *out_val) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + u64 enabled, running; + int fevent_code; + + pmc = &kvpmu->pmc[cidx]; + + if (pmc->cinfo.type == SBI_PMU_CTR_TYPE_FW) { + fevent_code = get_event_code(pmc->event_idx); + pmc->counter_val = kvpmu->fw_event[fevent_code].value; + } else if (pmc->perf_event) { + pmc->counter_val += perf_event_read_value(pmc->perf_event, &enabled, &running); + } else { + return -EINVAL; + } + *out_val = pmc->counter_val; + + return 0; +} + +static int kvm_pmu_validate_counter_mask(struct kvm_pmu *kvpmu, unsigned long ctr_base, + unsigned long ctr_mask) +{ + /* Make sure the we have a valid counter mask requested from the caller */ + if (!ctr_mask || (ctr_base + __fls(ctr_mask) >= kvm_pmu_num_counters(kvpmu))) + return -EINVAL; + + return 0; +} + +static int kvm_pmu_create_perf_event(struct kvm_pmc *pmc, struct perf_event_attr *attr, + unsigned long flags, unsigned long eidx, unsigned long evtdata) +{ + struct perf_event *event; + + kvm_pmu_release_perf_event(pmc); + attr->config = kvm_pmu_get_perf_event_config(eidx, evtdata); + if (flags & SBI_PMU_CFG_FLAG_CLEAR_VALUE) { + //TODO: Do we really want to clear the value in hardware counter + pmc->counter_val = 0; + } + + /* + * Set the default sample_period for now. The guest specified value + * will be updated in the start call. + */ + attr->sample_period = kvm_pmu_get_sample_period(pmc); + + event = perf_event_create_kernel_counter(attr, -1, current, NULL, pmc); + if (IS_ERR(event)) { + pr_err("kvm pmu event creation failed for eidx %lx: %ld\n", eidx, PTR_ERR(event)); + return PTR_ERR(event); + } + + pmc->perf_event = event; + if (flags & SBI_PMU_CFG_FLAG_AUTO_START) + perf_event_enable(pmc->perf_event); + + return 0; +} + +int kvm_riscv_vcpu_pmu_incr_fw(struct kvm_vcpu *vcpu, unsigned long fid) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct kvm_fw_event *fevent; + + if (!kvpmu || fid >= SBI_PMU_FW_MAX) + return -EINVAL; + + fevent = &kvpmu->fw_event[fid]; + if (fevent->started) + fevent->value++; + + return 0; +} + +int kvm_riscv_vcpu_pmu_read_hpm(struct kvm_vcpu *vcpu, unsigned int csr_num, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + int cidx, ret = KVM_INSN_CONTINUE_NEXT_SEPC; + + if (!kvpmu || !kvpmu->init_done) { + /* + * In absence of sscofpmf in the platform, the guest OS may use + * the legacy PMU driver to read cycle/instret. In that case, + * just return 0 to avoid any illegal trap. However, any other + * hpmcounter access should result in illegal trap as they must + * be access through SBI PMU only. + */ + if (csr_num == CSR_CYCLE || csr_num == CSR_INSTRET) { + *val = 0; + return ret; + } else { + return KVM_INSN_ILLEGAL_TRAP; + } + } + + /* The counter CSR are read only. Thus, any write should result in illegal traps */ + if (wr_mask) + return KVM_INSN_ILLEGAL_TRAP; + + cidx = csr_num - CSR_CYCLE; + + if (pmu_ctr_read(vcpu, cidx, val) < 0) + return KVM_INSN_ILLEGAL_TRAP; + + return ret; +} + +int kvm_riscv_vcpu_pmu_num_ctrs(struct kvm_vcpu *vcpu, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + + retdata->out_val = kvm_pmu_num_counters(kvpmu); + + return 0; +} + +int kvm_riscv_vcpu_pmu_ctr_info(struct kvm_vcpu *vcpu, unsigned long cidx, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + + if (cidx > RISCV_KVM_MAX_COUNTERS || cidx == 1) { + retdata->err_val = SBI_ERR_INVALID_PARAM; + return 0; + } + + retdata->out_val = kvpmu->pmc[cidx].cinfo.value; + + return 0; +} + +int kvm_riscv_vcpu_pmu_ctr_start(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, u64 ival, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + int i, pmc_index, sbiret = 0; + struct kvm_pmc *pmc; + int fevent_code; + + if (kvm_pmu_validate_counter_mask(kvpmu, ctr_base, ctr_mask) < 0) { + sbiret = SBI_ERR_INVALID_PARAM; + goto out; + } + + /* Start the counters that have been configured and requested by the guest */ + for_each_set_bit(i, &ctr_mask, RISCV_MAX_COUNTERS) { + pmc_index = i + ctr_base; + if (!test_bit(pmc_index, kvpmu->pmc_in_use)) + continue; + pmc = &kvpmu->pmc[pmc_index]; + if (flags & SBI_PMU_START_FLAG_SET_INIT_VALUE) + pmc->counter_val = ival; + if (pmc->cinfo.type == SBI_PMU_CTR_TYPE_FW) { + fevent_code = get_event_code(pmc->event_idx); + if (fevent_code >= SBI_PMU_FW_MAX) { + sbiret = SBI_ERR_INVALID_PARAM; + goto out; + } + + /* Check if the counter was already started for some reason */ + if (kvpmu->fw_event[fevent_code].started) { + sbiret = SBI_ERR_ALREADY_STARTED; + continue; + } + + kvpmu->fw_event[fevent_code].started = true; + kvpmu->fw_event[fevent_code].value = pmc->counter_val; + } else if (pmc->perf_event) { + if (unlikely(pmc->started)) { + sbiret = SBI_ERR_ALREADY_STARTED; + continue; + } + perf_event_period(pmc->perf_event, kvm_pmu_get_sample_period(pmc)); + perf_event_enable(pmc->perf_event); + pmc->started = true; + } else { + sbiret = SBI_ERR_INVALID_PARAM; + } + } + +out: + retdata->err_val = sbiret; + + return 0; +} + +int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + int i, pmc_index, sbiret = 0; + u64 enabled, running; + struct kvm_pmc *pmc; + int fevent_code; + + if (kvm_pmu_validate_counter_mask(kvpmu, ctr_base, ctr_mask) < 0) { + sbiret = SBI_ERR_INVALID_PARAM; + goto out; + } + + /* Stop the counters that have been configured and requested by the guest */ + for_each_set_bit(i, &ctr_mask, RISCV_MAX_COUNTERS) { + pmc_index = i + ctr_base; + if (!test_bit(pmc_index, kvpmu->pmc_in_use)) + continue; + pmc = &kvpmu->pmc[pmc_index]; + if (pmc->cinfo.type == SBI_PMU_CTR_TYPE_FW) { + fevent_code = get_event_code(pmc->event_idx); + if (fevent_code >= SBI_PMU_FW_MAX) { + sbiret = SBI_ERR_INVALID_PARAM; + goto out; + } + + if (!kvpmu->fw_event[fevent_code].started) + sbiret = SBI_ERR_ALREADY_STOPPED; + + kvpmu->fw_event[fevent_code].started = false; + } else if (pmc->perf_event) { + if (pmc->started) { + /* Stop counting the counter */ + perf_event_disable(pmc->perf_event); + pmc->started = false; + } else { + sbiret = SBI_ERR_ALREADY_STOPPED; + } + + if (flags & SBI_PMU_STOP_FLAG_RESET) { + /* Relase the counter if this is a reset request */ + pmc->counter_val += perf_event_read_value(pmc->perf_event, + &enabled, &running); + kvm_pmu_release_perf_event(pmc); + } + } else { + sbiret = SBI_ERR_INVALID_PARAM; + } + if (flags & SBI_PMU_STOP_FLAG_RESET) { + pmc->event_idx = SBI_PMU_EVENT_IDX_INVALID; + clear_bit(pmc_index, kvpmu->pmc_in_use); + } + } + +out: + retdata->err_val = sbiret; + + return 0; +} + +int kvm_riscv_vcpu_pmu_ctr_cfg_match(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, + unsigned long eidx, u64 evtdata, + struct kvm_vcpu_sbi_return *retdata) +{ + int ctr_idx, ret, sbiret = 0; + bool is_fevent; + unsigned long event_code; + u32 etype = kvm_pmu_get_perf_event_type(eidx); + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc = NULL; + struct perf_event_attr attr = { + .type = etype, + .size = sizeof(struct perf_event_attr), + .pinned = true, + /* + * It should never reach here if the platform doesn't support the sscofpmf + * extension as mode filtering won't work without it. + */ + .exclude_host = true, + .exclude_hv = true, + .exclude_user = !!(flags & SBI_PMU_CFG_FLAG_SET_UINH), + .exclude_kernel = !!(flags & SBI_PMU_CFG_FLAG_SET_SINH), + .config1 = RISCV_PMU_CONFIG1_GUEST_EVENTS, + }; + + if (kvm_pmu_validate_counter_mask(kvpmu, ctr_base, ctr_mask) < 0) { + sbiret = SBI_ERR_INVALID_PARAM; + goto out; + } + + event_code = get_event_code(eidx); + is_fevent = kvm_pmu_is_fw_event(eidx); + if (is_fevent && event_code >= SBI_PMU_FW_MAX) { + sbiret = SBI_ERR_NOT_SUPPORTED; + goto out; + } + + /* + * SKIP_MATCH flag indicates the caller is aware of the assigned counter + * for this event. Just do a sanity check if it already marked used. + */ + if (flags & SBI_PMU_CFG_FLAG_SKIP_MATCH) { + if (!test_bit(ctr_base + __ffs(ctr_mask), kvpmu->pmc_in_use)) { + sbiret = SBI_ERR_FAILURE; + goto out; + } + ctr_idx = ctr_base + __ffs(ctr_mask); + } else { + ctr_idx = pmu_get_pmc_index(kvpmu, eidx, ctr_base, ctr_mask); + if (ctr_idx < 0) { + sbiret = SBI_ERR_NOT_SUPPORTED; + goto out; + } + } + + pmc = &kvpmu->pmc[ctr_idx]; + pmc->idx = ctr_idx; + + if (is_fevent) { + if (flags & SBI_PMU_CFG_FLAG_AUTO_START) + kvpmu->fw_event[event_code].started = true; + } else { + ret = kvm_pmu_create_perf_event(pmc, &attr, flags, eidx, evtdata); + if (ret) + return ret; + } + + set_bit(ctr_idx, kvpmu->pmc_in_use); + pmc->event_idx = eidx; + retdata->out_val = ctr_idx; +out: + retdata->err_val = sbiret; + + return 0; +} + +int kvm_riscv_vcpu_pmu_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx, + struct kvm_vcpu_sbi_return *retdata) +{ + int ret; + + ret = pmu_ctr_read(vcpu, cidx, &retdata->out_val); + if (ret == -EINVAL) + retdata->err_val = SBI_ERR_INVALID_PARAM; + + return 0; +} + +void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu) +{ + int i = 0, ret, num_hw_ctrs = 0, hpm_width = 0; + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + + /* + * PMU functionality should be only available to guests if privilege mode + * filtering is available in the host. Otherwise, guest will always count + * events while the execution is in hypervisor mode. + */ + if (!riscv_isa_extension_available(NULL, SSCOFPMF)) + return; + + ret = riscv_pmu_get_hpm_info(&hpm_width, &num_hw_ctrs); + if (ret < 0 || !hpm_width || !num_hw_ctrs) + return; + + /* + * Increase the number of hardware counters to offset the time counter. + */ + kvpmu->num_hw_ctrs = num_hw_ctrs + 1; + kvpmu->num_fw_ctrs = SBI_PMU_FW_MAX; + memset(&kvpmu->fw_event, 0, SBI_PMU_FW_MAX * sizeof(struct kvm_fw_event)); + + if (kvpmu->num_hw_ctrs > RISCV_KVM_MAX_HW_CTRS) { + pr_warn_once("Limiting the hardware counters to 32 as specified by the ISA"); + kvpmu->num_hw_ctrs = RISCV_KVM_MAX_HW_CTRS; + } + + /* + * There is no correlation between the logical hardware counter and virtual counters. + * However, we need to encode a hpmcounter CSR in the counter info field so that + * KVM can trap n emulate the read. This works well in the migration use case as + * KVM doesn't care if the actual hpmcounter is available in the hardware or not. + */ + for (i = 0; i < kvm_pmu_num_counters(kvpmu); i++) { + /* TIME CSR shouldn't be read from perf interface */ + if (i == 1) + continue; + pmc = &kvpmu->pmc[i]; + pmc->idx = i; + pmc->event_idx = SBI_PMU_EVENT_IDX_INVALID; + if (i < kvpmu->num_hw_ctrs) { + pmc->cinfo.type = SBI_PMU_CTR_TYPE_HW; + if (i < 3) + /* CY, IR counters */ + pmc->cinfo.width = 63; + else + pmc->cinfo.width = hpm_width; + /* + * The CSR number doesn't have any relation with the logical + * hardware counters. The CSR numbers are encoded sequentially + * to avoid maintaining a map between the virtual counter + * and CSR number. + */ + pmc->cinfo.csr = CSR_CYCLE + i; + } else { + pmc->cinfo.type = SBI_PMU_CTR_TYPE_FW; + pmc->cinfo.width = BITS_PER_LONG - 1; + } + } + + kvpmu->init_done = true; +} + +void kvm_riscv_vcpu_pmu_deinit(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + int i; + + if (!kvpmu) + return; + + for_each_set_bit(i, kvpmu->pmc_in_use, RISCV_MAX_COUNTERS) { + pmc = &kvpmu->pmc[i]; + pmc->counter_val = 0; + kvm_pmu_release_perf_event(pmc); + pmc->event_idx = SBI_PMU_EVENT_IDX_INVALID; + } + bitmap_zero(kvpmu->pmc_in_use, RISCV_MAX_COUNTERS); + memset(&kvpmu->fw_event, 0, SBI_PMU_FW_MAX * sizeof(struct kvm_fw_event)); +} + +void kvm_riscv_vcpu_pmu_reset(struct kvm_vcpu *vcpu) +{ + kvm_riscv_vcpu_pmu_deinit(vcpu); +} diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index f96991d230bf..15fde15f9fb8 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -12,26 +12,6 @@ #include <asm/sbi.h> #include <asm/kvm_vcpu_sbi.h> -static int kvm_linux_err_map_sbi(int err) -{ - switch (err) { - case 0: - return SBI_SUCCESS; - case -EPERM: - return SBI_ERR_DENIED; - case -EINVAL: - return SBI_ERR_INVALID_PARAM; - case -EFAULT: - return SBI_ERR_INVALID_ADDRESS; - case -EOPNOTSUPP: - return SBI_ERR_NOT_SUPPORTED; - case -EALREADY: - return SBI_ERR_ALREADY_AVAILABLE; - default: - return SBI_ERR_FAILURE; - }; -} - #ifndef CONFIG_RISCV_SBI_V01 static const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01 = { .extid_start = -1UL, @@ -40,6 +20,16 @@ static const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01 = { }; #endif +#ifdef CONFIG_RISCV_PMU_SBI +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_pmu; +#else +static const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_pmu = { + .extid_start = -1UL, + .extid_end = -1UL, + .handler = NULL, +}; +#endif + static const struct kvm_vcpu_sbi_extension *sbi_ext[] = { &vcpu_sbi_ext_v01, &vcpu_sbi_ext_base, @@ -48,6 +38,7 @@ static const struct kvm_vcpu_sbi_extension *sbi_ext[] = { &vcpu_sbi_ext_rfence, &vcpu_sbi_ext_srst, &vcpu_sbi_ext_hsm, + &vcpu_sbi_ext_pmu, &vcpu_sbi_ext_experimental, &vcpu_sbi_ext_vendor, }; @@ -125,11 +116,14 @@ int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run) { int ret = 1; bool next_sepc = true; - bool userspace_exit = false; struct kvm_cpu_context *cp = &vcpu->arch.guest_context; const struct kvm_vcpu_sbi_extension *sbi_ext; - struct kvm_cpu_trap utrap = { 0 }; - unsigned long out_val = 0; + struct kvm_cpu_trap utrap = {0}; + struct kvm_vcpu_sbi_return sbi_ret = { + .out_val = 0, + .err_val = 0, + .utrap = &utrap, + }; bool ext_is_v01 = false; sbi_ext = kvm_vcpu_sbi_find_ext(cp->a7); @@ -139,42 +133,46 @@ int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run) cp->a7 <= SBI_EXT_0_1_SHUTDOWN) ext_is_v01 = true; #endif - ret = sbi_ext->handler(vcpu, run, &out_val, &utrap, &userspace_exit); + ret = sbi_ext->handler(vcpu, run, &sbi_ret); } else { /* Return error for unsupported SBI calls */ cp->a0 = SBI_ERR_NOT_SUPPORTED; goto ecall_done; } + /* + * When the SBI extension returns a Linux error code, it exits the ioctl + * loop and forwards the error to userspace. + */ + if (ret < 0) { + next_sepc = false; + goto ecall_done; + } + /* Handle special error cases i.e trap, exit or userspace forward */ - if (utrap.scause) { + if (sbi_ret.utrap->scause) { /* No need to increment sepc or exit ioctl loop */ ret = 1; - utrap.sepc = cp->sepc; - kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); + sbi_ret.utrap->sepc = cp->sepc; + kvm_riscv_vcpu_trap_redirect(vcpu, sbi_ret.utrap); next_sepc = false; goto ecall_done; } /* Exit ioctl loop or Propagate the error code the guest */ - if (userspace_exit) { + if (sbi_ret.uexit) { next_sepc = false; ret = 0; } else { - /** - * SBI extension handler always returns an Linux error code. Convert - * it to the SBI specific error code that can be propagated the SBI - * caller. - */ - ret = kvm_linux_err_map_sbi(ret); - cp->a0 = ret; + cp->a0 = sbi_ret.err_val; ret = 1; } ecall_done: if (next_sepc) cp->sepc += 4; - if (!ext_is_v01) - cp->a1 = out_val; + /* a1 should only be updated when we continue the ioctl loop */ + if (!ext_is_v01 && ret == 1) + cp->a1 = sbi_ret.out_val; return ret; } diff --git a/arch/riscv/kvm/vcpu_sbi_base.c b/arch/riscv/kvm/vcpu_sbi_base.c index 5d65c634d301..9945aff34c14 100644 --- a/arch/riscv/kvm/vcpu_sbi_base.c +++ b/arch/riscv/kvm/vcpu_sbi_base.c @@ -14,11 +14,11 @@ #include <asm/kvm_vcpu_sbi.h> static int kvm_sbi_ext_base_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *trap, bool *exit) + struct kvm_vcpu_sbi_return *retdata) { - int ret = 0; struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + const struct kvm_vcpu_sbi_extension *sbi_ext; + unsigned long *out_val = &retdata->out_val; switch (cp->a6) { case SBI_EXT_BASE_GET_SPEC_VERSION: @@ -42,9 +42,12 @@ static int kvm_sbi_ext_base_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, * forward it to the userspace */ kvm_riscv_vcpu_sbi_forward(vcpu, run); - *exit = true; - } else - *out_val = kvm_vcpu_sbi_find_ext(cp->a0) ? 1 : 0; + retdata->uexit = true; + } else { + sbi_ext = kvm_vcpu_sbi_find_ext(cp->a0); + *out_val = sbi_ext && sbi_ext->probe ? + sbi_ext->probe(vcpu) : !!sbi_ext; + } break; case SBI_EXT_BASE_GET_MVENDORID: *out_val = vcpu->arch.mvendorid; @@ -56,11 +59,11 @@ static int kvm_sbi_ext_base_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, *out_val = vcpu->arch.mimpid; break; default: - ret = -EOPNOTSUPP; + retdata->err_val = SBI_ERR_NOT_SUPPORTED; break; } - return ret; + return 0; } const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_base = { @@ -70,17 +73,15 @@ const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_base = { }; static int kvm_sbi_ext_forward_handler(struct kvm_vcpu *vcpu, - struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *utrap, - bool *exit) + struct kvm_run *run, + struct kvm_vcpu_sbi_return *retdata) { /* * Both SBI experimental and vendor extensions are * unconditionally forwarded to userspace. */ kvm_riscv_vcpu_sbi_forward(vcpu, run); - *exit = true; + retdata->uexit = true; return 0; } diff --git a/arch/riscv/kvm/vcpu_sbi_hsm.c b/arch/riscv/kvm/vcpu_sbi_hsm.c index 2e915cafd551..7dca0e9381d9 100644 --- a/arch/riscv/kvm/vcpu_sbi_hsm.c +++ b/arch/riscv/kvm/vcpu_sbi_hsm.c @@ -21,9 +21,9 @@ static int kvm_sbi_hsm_vcpu_start(struct kvm_vcpu *vcpu) target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, target_vcpuid); if (!target_vcpu) - return -EINVAL; + return SBI_ERR_INVALID_PARAM; if (!target_vcpu->arch.power_off) - return -EALREADY; + return SBI_ERR_ALREADY_AVAILABLE; reset_cntx = &target_vcpu->arch.guest_reset_context; /* start address */ @@ -42,7 +42,7 @@ static int kvm_sbi_hsm_vcpu_start(struct kvm_vcpu *vcpu) static int kvm_sbi_hsm_vcpu_stop(struct kvm_vcpu *vcpu) { if (vcpu->arch.power_off) - return -EINVAL; + return SBI_ERR_FAILURE; kvm_riscv_vcpu_power_off(vcpu); @@ -57,7 +57,7 @@ static int kvm_sbi_hsm_vcpu_get_status(struct kvm_vcpu *vcpu) target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, target_vcpuid); if (!target_vcpu) - return -EINVAL; + return SBI_ERR_INVALID_PARAM; if (!target_vcpu->arch.power_off) return SBI_HSM_STATE_STARTED; else if (vcpu->stat.generic.blocking) @@ -67,9 +67,7 @@ static int kvm_sbi_hsm_vcpu_get_status(struct kvm_vcpu *vcpu) } static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *utrap, - bool *exit) + struct kvm_vcpu_sbi_return *retdata) { int ret = 0; struct kvm_cpu_context *cp = &vcpu->arch.guest_context; @@ -88,27 +86,29 @@ static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, case SBI_EXT_HSM_HART_STATUS: ret = kvm_sbi_hsm_vcpu_get_status(vcpu); if (ret >= 0) { - *out_val = ret; - ret = 0; + retdata->out_val = ret; + retdata->err_val = 0; } - break; + return 0; case SBI_EXT_HSM_HART_SUSPEND: switch (cp->a0) { case SBI_HSM_SUSPEND_RET_DEFAULT: kvm_riscv_vcpu_wfi(vcpu); break; case SBI_HSM_SUSPEND_NON_RET_DEFAULT: - ret = -EOPNOTSUPP; + ret = SBI_ERR_NOT_SUPPORTED; break; default: - ret = -EINVAL; + ret = SBI_ERR_INVALID_PARAM; } break; default: - ret = -EOPNOTSUPP; + ret = SBI_ERR_NOT_SUPPORTED; } - return ret; + retdata->err_val = ret; + + return 0; } const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_hsm = { diff --git a/arch/riscv/kvm/vcpu_sbi_pmu.c b/arch/riscv/kvm/vcpu_sbi_pmu.c new file mode 100644 index 000000000000..7eca72df2cbd --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi_pmu.c @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023 Rivos Inc + * + * Authors: + * Atish Patra <atishp@rivosinc.com> + */ + +#include <linux/errno.h> +#include <linux/err.h> +#include <linux/kvm_host.h> +#include <asm/csr.h> +#include <asm/sbi.h> +#include <asm/kvm_vcpu_sbi.h> + +static int kvm_sbi_ext_pmu_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_vcpu_sbi_return *retdata) +{ + int ret = 0; + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + unsigned long funcid = cp->a6; + u64 temp; + + if (!kvpmu->init_done) { + retdata->err_val = SBI_ERR_NOT_SUPPORTED; + return 0; + } + + switch (funcid) { + case SBI_EXT_PMU_NUM_COUNTERS: + ret = kvm_riscv_vcpu_pmu_num_ctrs(vcpu, retdata); + break; + case SBI_EXT_PMU_COUNTER_GET_INFO: + ret = kvm_riscv_vcpu_pmu_ctr_info(vcpu, cp->a0, retdata); + break; + case SBI_EXT_PMU_COUNTER_CFG_MATCH: +#if defined(CONFIG_32BIT) + temp = ((uint64_t)cp->a5 << 32) | cp->a4; +#else + temp = cp->a4; +#endif + /* + * This can fail if perf core framework fails to create an event. + * Forward the error to userspace because it's an error which + * happened within the host kernel. The other option would be + * to convert to an SBI error and forward to the guest. + */ + ret = kvm_riscv_vcpu_pmu_ctr_cfg_match(vcpu, cp->a0, cp->a1, + cp->a2, cp->a3, temp, retdata); + break; + case SBI_EXT_PMU_COUNTER_START: +#if defined(CONFIG_32BIT) + temp = ((uint64_t)cp->a4 << 32) | cp->a3; +#else + temp = cp->a3; +#endif + ret = kvm_riscv_vcpu_pmu_ctr_start(vcpu, cp->a0, cp->a1, cp->a2, + temp, retdata); + break; + case SBI_EXT_PMU_COUNTER_STOP: + ret = kvm_riscv_vcpu_pmu_ctr_stop(vcpu, cp->a0, cp->a1, cp->a2, retdata); + break; + case SBI_EXT_PMU_COUNTER_FW_READ: + ret = kvm_riscv_vcpu_pmu_ctr_read(vcpu, cp->a0, retdata); + break; + default: + retdata->err_val = SBI_ERR_NOT_SUPPORTED; + } + + return ret; +} + +static unsigned long kvm_sbi_ext_pmu_probe(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + + return kvpmu->init_done; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_pmu = { + .extid_start = SBI_EXT_PMU, + .extid_end = SBI_EXT_PMU, + .handler = kvm_sbi_ext_pmu_handler, + .probe = kvm_sbi_ext_pmu_probe, +}; diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c index 03a0198389f0..7c4d5d38a339 100644 --- a/arch/riscv/kvm/vcpu_sbi_replace.c +++ b/arch/riscv/kvm/vcpu_sbi_replace.c @@ -11,19 +11,21 @@ #include <linux/kvm_host.h> #include <asm/sbi.h> #include <asm/kvm_vcpu_timer.h> +#include <asm/kvm_vcpu_pmu.h> #include <asm/kvm_vcpu_sbi.h> static int kvm_sbi_ext_time_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *utrap, bool *exit) + struct kvm_vcpu_sbi_return *retdata) { - int ret = 0; struct kvm_cpu_context *cp = &vcpu->arch.guest_context; u64 next_cycle; - if (cp->a6 != SBI_EXT_TIME_SET_TIMER) - return -EINVAL; + if (cp->a6 != SBI_EXT_TIME_SET_TIMER) { + retdata->err_val = SBI_ERR_INVALID_PARAM; + return 0; + } + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_SET_TIMER); #if __riscv_xlen == 32 next_cycle = ((u64)cp->a1 << 32) | (u64)cp->a0; #else @@ -31,7 +33,7 @@ static int kvm_sbi_ext_time_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, #endif kvm_riscv_vcpu_timer_next_event(vcpu, next_cycle); - return ret; + return 0; } const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_time = { @@ -41,8 +43,7 @@ const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_time = { }; static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *utrap, bool *exit) + struct kvm_vcpu_sbi_return *retdata) { int ret = 0; unsigned long i; @@ -51,9 +52,12 @@ static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, unsigned long hmask = cp->a0; unsigned long hbase = cp->a1; - if (cp->a6 != SBI_EXT_IPI_SEND_IPI) - return -EINVAL; + if (cp->a6 != SBI_EXT_IPI_SEND_IPI) { + retdata->err_val = SBI_ERR_INVALID_PARAM; + return 0; + } + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_IPI_SENT); kvm_for_each_vcpu(i, tmp, vcpu->kvm) { if (hbase != -1UL) { if (tmp->vcpu_id < hbase) @@ -64,6 +68,7 @@ static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, ret = kvm_riscv_vcpu_set_interrupt(tmp, IRQ_VS_SOFT); if (ret < 0) break; + kvm_riscv_vcpu_pmu_incr_fw(tmp, SBI_PMU_FW_IPI_RCVD); } return ret; @@ -76,10 +81,8 @@ const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_ipi = { }; static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *utrap, bool *exit) + struct kvm_vcpu_sbi_return *retdata) { - int ret = 0; struct kvm_cpu_context *cp = &vcpu->arch.guest_context; unsigned long hmask = cp->a0; unsigned long hbase = cp->a1; @@ -88,6 +91,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run switch (funcid) { case SBI_EXT_RFENCE_REMOTE_FENCE_I: kvm_riscv_fence_i(vcpu->kvm, hbase, hmask); + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_FENCE_I_SENT); break; case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA: if (cp->a2 == 0 && cp->a3 == 0) @@ -95,6 +99,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run else kvm_riscv_hfence_vvma_gva(vcpu->kvm, hbase, hmask, cp->a2, cp->a3, PAGE_SHIFT); + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_SENT); break; case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID: if (cp->a2 == 0 && cp->a3 == 0) @@ -105,6 +110,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run hbase, hmask, cp->a2, cp->a3, PAGE_SHIFT, cp->a4); + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_ASID_SENT); break; case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA: case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID: @@ -116,10 +122,10 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run */ break; default: - ret = -EOPNOTSUPP; + retdata->err_val = SBI_ERR_NOT_SUPPORTED; } - return ret; + return 0; } const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence = { @@ -130,14 +136,12 @@ const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence = { static int kvm_sbi_ext_srst_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *utrap, bool *exit) + struct kvm_vcpu_sbi_return *retdata) { struct kvm_cpu_context *cp = &vcpu->arch.guest_context; unsigned long funcid = cp->a6; u32 reason = cp->a1; u32 type = cp->a0; - int ret = 0; switch (funcid) { case SBI_EXT_SRST_RESET: @@ -146,24 +150,24 @@ static int kvm_sbi_ext_srst_handler(struct kvm_vcpu *vcpu, kvm_riscv_vcpu_sbi_system_reset(vcpu, run, KVM_SYSTEM_EVENT_SHUTDOWN, reason); - *exit = true; + retdata->uexit = true; break; case SBI_SRST_RESET_TYPE_COLD_REBOOT: case SBI_SRST_RESET_TYPE_WARM_REBOOT: kvm_riscv_vcpu_sbi_system_reset(vcpu, run, KVM_SYSTEM_EVENT_RESET, reason); - *exit = true; + retdata->uexit = true; break; default: - ret = -EOPNOTSUPP; + retdata->err_val = SBI_ERR_NOT_SUPPORTED; } break; default: - ret = -EOPNOTSUPP; + retdata->err_val = SBI_ERR_NOT_SUPPORTED; } - return ret; + return 0; } const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_srst = { diff --git a/arch/riscv/kvm/vcpu_sbi_v01.c b/arch/riscv/kvm/vcpu_sbi_v01.c index 489f225ee66d..8f4c4fa16227 100644 --- a/arch/riscv/kvm/vcpu_sbi_v01.c +++ b/arch/riscv/kvm/vcpu_sbi_v01.c @@ -14,9 +14,7 @@ #include <asm/kvm_vcpu_sbi.h> static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *utrap, - bool *exit) + struct kvm_vcpu_sbi_return *retdata) { ulong hmask; int i, ret = 0; @@ -24,6 +22,7 @@ static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, struct kvm_vcpu *rvcpu; struct kvm *kvm = vcpu->kvm; struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + struct kvm_cpu_trap *utrap = retdata->utrap; switch (cp->a7) { case SBI_EXT_0_1_CONSOLE_GETCHAR: @@ -33,7 +32,7 @@ static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, * handled in kernel so we forward these to user-space */ kvm_riscv_vcpu_sbi_forward(vcpu, run); - *exit = true; + retdata->uexit = true; break; case SBI_EXT_0_1_SET_TIMER: #if __riscv_xlen == 32 @@ -48,8 +47,7 @@ static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, break; case SBI_EXT_0_1_SEND_IPI: if (cp->a0) - hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0, - utrap); + hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0, utrap); else hmask = (1UL << atomic_read(&kvm->online_vcpus)) - 1; if (utrap->scause) @@ -65,14 +63,13 @@ static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, case SBI_EXT_0_1_SHUTDOWN: kvm_riscv_vcpu_sbi_system_reset(vcpu, run, KVM_SYSTEM_EVENT_SHUTDOWN, 0); - *exit = true; + retdata->uexit = true; break; case SBI_EXT_0_1_REMOTE_FENCE_I: case SBI_EXT_0_1_REMOTE_SFENCE_VMA: case SBI_EXT_0_1_REMOTE_SFENCE_VMA_ASID: if (cp->a0) - hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0, - utrap); + hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0, utrap); else hmask = (1UL << atomic_read(&kvm->online_vcpus)) - 1; if (utrap->scause) @@ -103,7 +100,7 @@ static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, } break; default: - ret = -EINVAL; + retdata->err_val = SBI_ERR_NOT_SUPPORTED; break; } diff --git a/arch/riscv/kvm/vmid.c b/arch/riscv/kvm/vmid.c index 6cd93995fb65..5246da1c9167 100644 --- a/arch/riscv/kvm/vmid.c +++ b/arch/riscv/kvm/vmid.c @@ -17,10 +17,10 @@ static unsigned long vmid_version = 1; static unsigned long vmid_next; -static unsigned long vmid_bits; +static unsigned long vmid_bits __ro_after_init; static DEFINE_SPINLOCK(vmid_lock); -void kvm_riscv_gstage_vmid_detect(void) +void __init kvm_riscv_gstage_vmid_detect(void) { unsigned long old; diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index d67ce719d16a..2bbc3d54959d 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -1031,7 +1031,6 @@ extern char sie_exit; extern int kvm_s390_gisc_register(struct kvm *kvm, u32 gisc); extern int kvm_s390_gisc_unregister(struct kvm *kvm, u32 gisc); -static inline void kvm_arch_hardware_disable(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_free_memslot(struct kvm *kvm, diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 0243b6e38d36..3eb85f254881 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -1162,6 +1162,115 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, } /** + * cmpxchg_guest_abs_with_key() - Perform cmpxchg on guest absolute address. + * @kvm: Virtual machine instance. + * @gpa: Absolute guest address of the location to be changed. + * @len: Operand length of the cmpxchg, required: 1 <= len <= 16. Providing a + * non power of two will result in failure. + * @old_addr: Pointer to old value. If the location at @gpa contains this value, + * the exchange will succeed. After calling cmpxchg_guest_abs_with_key() + * *@old_addr contains the value at @gpa before the attempt to + * exchange the value. + * @new: The value to place at @gpa. + * @access_key: The access key to use for the guest access. + * @success: output value indicating if an exchange occurred. + * + * Atomically exchange the value at @gpa by @new, if it contains *@old. + * Honors storage keys. + * + * Return: * 0: successful exchange + * * >0: a program interruption code indicating the reason cmpxchg could + * not be attempted + * * -EINVAL: address misaligned or len not power of two + * * -EAGAIN: transient failure (len 1 or 2) + * * -EOPNOTSUPP: read-only memslot (should never occur) + */ +int cmpxchg_guest_abs_with_key(struct kvm *kvm, gpa_t gpa, int len, + __uint128_t *old_addr, __uint128_t new, + u8 access_key, bool *success) +{ + gfn_t gfn = gpa_to_gfn(gpa); + struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); + bool writable; + hva_t hva; + int ret; + + if (!IS_ALIGNED(gpa, len)) + return -EINVAL; + + hva = gfn_to_hva_memslot_prot(slot, gfn, &writable); + if (kvm_is_error_hva(hva)) + return PGM_ADDRESSING; + /* + * Check if it's a read-only memslot, even though that cannot occur + * since those are unsupported. + * Don't try to actually handle that case. + */ + if (!writable) + return -EOPNOTSUPP; + + hva += offset_in_page(gpa); + /* + * The cmpxchg_user_key macro depends on the type of "old", so we need + * a case for each valid length and get some code duplication as long + * as we don't introduce a new macro. + */ + switch (len) { + case 1: { + u8 old; + + ret = cmpxchg_user_key((u8 __user *)hva, &old, *old_addr, new, access_key); + *success = !ret && old == *old_addr; + *old_addr = old; + break; + } + case 2: { + u16 old; + + ret = cmpxchg_user_key((u16 __user *)hva, &old, *old_addr, new, access_key); + *success = !ret && old == *old_addr; + *old_addr = old; + break; + } + case 4: { + u32 old; + + ret = cmpxchg_user_key((u32 __user *)hva, &old, *old_addr, new, access_key); + *success = !ret && old == *old_addr; + *old_addr = old; + break; + } + case 8: { + u64 old; + + ret = cmpxchg_user_key((u64 __user *)hva, &old, *old_addr, new, access_key); + *success = !ret && old == *old_addr; + *old_addr = old; + break; + } + case 16: { + __uint128_t old; + + ret = cmpxchg_user_key((__uint128_t __user *)hva, &old, *old_addr, new, access_key); + *success = !ret && old == *old_addr; + *old_addr = old; + break; + } + default: + return -EINVAL; + } + if (*success) + mark_page_dirty_in_slot(kvm, slot, gfn); + /* + * Assume that the fault is caused by protection, either key protection + * or user page write protection. + */ + if (ret == -EFAULT) + ret = PGM_PROTECTION; + return ret; +} + +/** * guest_translate_address_with_key - translate guest logical into guest absolute address * @vcpu: virtual cpu * @gva: Guest virtual address diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index 9408d6cc8e2c..b320d12aa049 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -206,6 +206,9 @@ int access_guest_with_key(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data, unsigned long len, enum gacc_mode mode); +int cmpxchg_guest_abs_with_key(struct kvm *kvm, gpa_t gpa, int len, __uint128_t *old, + __uint128_t new, u8 access_key, bool *success); + /** * write_guest_with_key - copy data from kernel space to guest space * @vcpu: virtual cpu diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index ab26aa53ee37..9250fde1f97d 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -3103,9 +3103,9 @@ static enum hrtimer_restart gisa_vcpu_kicker(struct hrtimer *timer) static void process_gib_alert_list(void) { struct kvm_s390_gisa_interrupt *gi; + u32 final, gisa_phys, origin = 0UL; struct kvm_s390_gisa *gisa; struct kvm *kvm; - u32 final, origin = 0UL; do { /* @@ -3131,9 +3131,10 @@ static void process_gib_alert_list(void) * interruptions asap. */ while (origin & GISA_ADDR_MASK) { - gisa = (struct kvm_s390_gisa *)(u64)origin; + gisa_phys = origin; + gisa = phys_to_virt(gisa_phys); origin = gisa->next_alert; - gisa->next_alert = (u32)(u64)gisa; + gisa->next_alert = gisa_phys; kvm = container_of(gisa, struct sie_page2, gisa)->kvm; gi = &kvm->arch.gisa_int; if (hrtimer_active(&gi->timer)) @@ -3415,8 +3416,9 @@ void kvm_s390_gib_destroy(void) gib = NULL; } -int kvm_s390_gib_init(u8 nisc) +int __init kvm_s390_gib_init(u8 nisc) { + u32 gib_origin; int rc = 0; if (!css_general_characteristics.aiv) { @@ -3438,7 +3440,8 @@ int kvm_s390_gib_init(u8 nisc) } gib->nisc = nisc; - if (chsc_sgib((u32)(u64)gib)) { + gib_origin = virt_to_phys(gib); + if (chsc_sgib(gib_origin)) { pr_err("Associating the GIB with the AIV facility failed\n"); free_page((unsigned long)gib); gib = NULL; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index e4890e04b210..39b36562c043 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -256,17 +256,6 @@ debug_info_t *kvm_s390_dbf; debug_info_t *kvm_s390_dbf_uv; /* Section: not file related */ -int kvm_arch_hardware_enable(void) -{ - /* every s390 is virtualization enabled ;-) */ - return 0; -} - -int kvm_arch_check_processor_compat(void *opaque) -{ - return 0; -} - /* forward declarations */ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start, unsigned long end); @@ -329,25 +318,6 @@ static struct notifier_block kvm_clock_notifier = { .notifier_call = kvm_clock_sync, }; -int kvm_arch_hardware_setup(void *opaque) -{ - gmap_notifier.notifier_call = kvm_gmap_notifier; - gmap_register_pte_notifier(&gmap_notifier); - vsie_gmap_notifier.notifier_call = kvm_s390_vsie_gmap_notifier; - gmap_register_pte_notifier(&vsie_gmap_notifier); - atomic_notifier_chain_register(&s390_epoch_delta_notifier, - &kvm_clock_notifier); - return 0; -} - -void kvm_arch_hardware_unsetup(void) -{ - gmap_unregister_pte_notifier(&gmap_notifier); - gmap_unregister_pte_notifier(&vsie_gmap_notifier); - atomic_notifier_chain_unregister(&s390_epoch_delta_notifier, - &kvm_clock_notifier); -} - static void allow_cpu_feat(unsigned long nr) { set_bit_inv(nr, kvm_s390_available_cpu_feat); @@ -385,7 +355,7 @@ static __always_inline void __insn32_query(unsigned int opcode, u8 *query) #define INSN_SORTL 0xb938 #define INSN_DFLTCC 0xb939 -static void kvm_s390_cpu_feat_init(void) +static void __init kvm_s390_cpu_feat_init(void) { int i; @@ -488,7 +458,7 @@ static void kvm_s390_cpu_feat_init(void) */ } -int kvm_arch_init(void *opaque) +static int __init __kvm_s390_init(void) { int rc = -ENOMEM; @@ -498,11 +468,11 @@ int kvm_arch_init(void *opaque) kvm_s390_dbf_uv = debug_register("kvm-uv", 32, 1, 7 * sizeof(long)); if (!kvm_s390_dbf_uv) - goto out; + goto err_kvm_uv; if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view) || debug_register_view(kvm_s390_dbf_uv, &debug_sprintf_view)) - goto out; + goto err_debug_view; kvm_s390_cpu_feat_init(); @@ -510,30 +480,49 @@ int kvm_arch_init(void *opaque) rc = kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC); if (rc) { pr_err("A FLIC registration call failed with rc=%d\n", rc); - goto out; + goto err_flic; } if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) { rc = kvm_s390_pci_init(); if (rc) { pr_err("Unable to allocate AIFT for PCI\n"); - goto out; + goto err_pci; } } rc = kvm_s390_gib_init(GAL_ISC); if (rc) - goto out; + goto err_gib; + + gmap_notifier.notifier_call = kvm_gmap_notifier; + gmap_register_pte_notifier(&gmap_notifier); + vsie_gmap_notifier.notifier_call = kvm_s390_vsie_gmap_notifier; + gmap_register_pte_notifier(&vsie_gmap_notifier); + atomic_notifier_chain_register(&s390_epoch_delta_notifier, + &kvm_clock_notifier); return 0; -out: - kvm_arch_exit(); +err_gib: + if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) + kvm_s390_pci_exit(); +err_pci: +err_flic: +err_debug_view: + debug_unregister(kvm_s390_dbf_uv); +err_kvm_uv: + debug_unregister(kvm_s390_dbf); return rc; } -void kvm_arch_exit(void) +static void __kvm_s390_exit(void) { + gmap_unregister_pte_notifier(&gmap_notifier); + gmap_unregister_pte_notifier(&vsie_gmap_notifier); + atomic_notifier_chain_unregister(&s390_epoch_delta_notifier, + &kvm_clock_notifier); + kvm_s390_gib_destroy(); if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) kvm_s390_pci_exit(); @@ -584,7 +573,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_VCPU_RESETS: case KVM_CAP_SET_GUEST_DEBUG: case KVM_CAP_S390_DIAG318: - case KVM_CAP_S390_MEM_OP_EXTENSION: r = 1; break; case KVM_CAP_SET_GUEST_DEBUG2: @@ -598,6 +586,15 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_MEM_OP: r = MEM_OP_MAX_SIZE; break; + case KVM_CAP_S390_MEM_OP_EXTENSION: + /* + * Flag bits indicating which extensions are supported. + * If r > 0, the base extension must also be supported/indicated, + * in order to maintain backwards compatibility. + */ + r = KVM_S390_MEMOP_EXTENSION_CAP_BASE | + KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG; + break; case KVM_CAP_NR_VCPUS: case KVM_CAP_MAX_VCPUS: case KVM_CAP_MAX_VCPU_ID: @@ -2764,41 +2761,33 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd) return r; } -static bool access_key_invalid(u8 access_key) -{ - return access_key > 0xf; -} - -static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop) +static int mem_op_validate_common(struct kvm_s390_mem_op *mop, u64 supported_flags) { - void __user *uaddr = (void __user *)mop->buf; - u64 supported_flags; - void *tmpbuf = NULL; - int r, srcu_idx; - - supported_flags = KVM_S390_MEMOP_F_SKEY_PROTECTION - | KVM_S390_MEMOP_F_CHECK_ONLY; if (mop->flags & ~supported_flags || !mop->size) return -EINVAL; if (mop->size > MEM_OP_MAX_SIZE) return -E2BIG; - /* - * This is technically a heuristic only, if the kvm->lock is not - * taken, it is not guaranteed that the vm is/remains non-protected. - * This is ok from a kernel perspective, wrongdoing is detected - * on the access, -EFAULT is returned and the vm may crash the - * next time it accesses the memory in question. - * There is no sane usecase to do switching and a memop on two - * different CPUs at the same time. - */ - if (kvm_s390_pv_get_handle(kvm)) - return -EINVAL; if (mop->flags & KVM_S390_MEMOP_F_SKEY_PROTECTION) { - if (access_key_invalid(mop->key)) + if (mop->key > 0xf) return -EINVAL; } else { mop->key = 0; } + return 0; +} + +static int kvm_s390_vm_mem_op_abs(struct kvm *kvm, struct kvm_s390_mem_op *mop) +{ + void __user *uaddr = (void __user *)mop->buf; + enum gacc_mode acc_mode; + void *tmpbuf = NULL; + int r, srcu_idx; + + r = mem_op_validate_common(mop, KVM_S390_MEMOP_F_SKEY_PROTECTION | + KVM_S390_MEMOP_F_CHECK_ONLY); + if (r) + return r; + if (!(mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY)) { tmpbuf = vmalloc(mop->size); if (!tmpbuf) @@ -2812,35 +2801,25 @@ static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop) goto out_unlock; } - switch (mop->op) { - case KVM_S390_MEMOP_ABSOLUTE_READ: { - if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) { - r = check_gpa_range(kvm, mop->gaddr, mop->size, GACC_FETCH, mop->key); - } else { - r = access_guest_abs_with_key(kvm, mop->gaddr, tmpbuf, - mop->size, GACC_FETCH, mop->key); - if (r == 0) { - if (copy_to_user(uaddr, tmpbuf, mop->size)) - r = -EFAULT; - } - } - break; + acc_mode = mop->op == KVM_S390_MEMOP_ABSOLUTE_READ ? GACC_FETCH : GACC_STORE; + if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) { + r = check_gpa_range(kvm, mop->gaddr, mop->size, acc_mode, mop->key); + goto out_unlock; } - case KVM_S390_MEMOP_ABSOLUTE_WRITE: { - if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) { - r = check_gpa_range(kvm, mop->gaddr, mop->size, GACC_STORE, mop->key); - } else { - if (copy_from_user(tmpbuf, uaddr, mop->size)) { - r = -EFAULT; - break; - } - r = access_guest_abs_with_key(kvm, mop->gaddr, tmpbuf, - mop->size, GACC_STORE, mop->key); + if (acc_mode == GACC_FETCH) { + r = access_guest_abs_with_key(kvm, mop->gaddr, tmpbuf, + mop->size, GACC_FETCH, mop->key); + if (r) + goto out_unlock; + if (copy_to_user(uaddr, tmpbuf, mop->size)) + r = -EFAULT; + } else { + if (copy_from_user(tmpbuf, uaddr, mop->size)) { + r = -EFAULT; + goto out_unlock; } - break; - } - default: - r = -EINVAL; + r = access_guest_abs_with_key(kvm, mop->gaddr, tmpbuf, + mop->size, GACC_STORE, mop->key); } out_unlock: @@ -2850,6 +2829,75 @@ out_unlock: return r; } +static int kvm_s390_vm_mem_op_cmpxchg(struct kvm *kvm, struct kvm_s390_mem_op *mop) +{ + void __user *uaddr = (void __user *)mop->buf; + void __user *old_addr = (void __user *)mop->old_addr; + union { + __uint128_t quad; + char raw[sizeof(__uint128_t)]; + } old = { .quad = 0}, new = { .quad = 0 }; + unsigned int off_in_quad = sizeof(new) - mop->size; + int r, srcu_idx; + bool success; + + r = mem_op_validate_common(mop, KVM_S390_MEMOP_F_SKEY_PROTECTION); + if (r) + return r; + /* + * This validates off_in_quad. Checking that size is a power + * of two is not necessary, as cmpxchg_guest_abs_with_key + * takes care of that + */ + if (mop->size > sizeof(new)) + return -EINVAL; + if (copy_from_user(&new.raw[off_in_quad], uaddr, mop->size)) + return -EFAULT; + if (copy_from_user(&old.raw[off_in_quad], old_addr, mop->size)) + return -EFAULT; + + srcu_idx = srcu_read_lock(&kvm->srcu); + + if (kvm_is_error_gpa(kvm, mop->gaddr)) { + r = PGM_ADDRESSING; + goto out_unlock; + } + + r = cmpxchg_guest_abs_with_key(kvm, mop->gaddr, mop->size, &old.quad, + new.quad, mop->key, &success); + if (!success && copy_to_user(old_addr, &old.raw[off_in_quad], mop->size)) + r = -EFAULT; + +out_unlock: + srcu_read_unlock(&kvm->srcu, srcu_idx); + return r; +} + +static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop) +{ + /* + * This is technically a heuristic only, if the kvm->lock is not + * taken, it is not guaranteed that the vm is/remains non-protected. + * This is ok from a kernel perspective, wrongdoing is detected + * on the access, -EFAULT is returned and the vm may crash the + * next time it accesses the memory in question. + * There is no sane usecase to do switching and a memop on two + * different CPUs at the same time. + */ + if (kvm_s390_pv_get_handle(kvm)) + return -EINVAL; + + switch (mop->op) { + case KVM_S390_MEMOP_ABSOLUTE_READ: + case KVM_S390_MEMOP_ABSOLUTE_WRITE: + return kvm_s390_vm_mem_op_abs(kvm, mop); + case KVM_S390_MEMOP_ABSOLUTE_CMPXCHG: + return kvm_s390_vm_mem_op_cmpxchg(kvm, mop); + default: + return -EINVAL; + } +} + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -5249,62 +5297,54 @@ static long kvm_s390_vcpu_mem_op(struct kvm_vcpu *vcpu, struct kvm_s390_mem_op *mop) { void __user *uaddr = (void __user *)mop->buf; + enum gacc_mode acc_mode; void *tmpbuf = NULL; - int r = 0; - const u64 supported_flags = KVM_S390_MEMOP_F_INJECT_EXCEPTION - | KVM_S390_MEMOP_F_CHECK_ONLY - | KVM_S390_MEMOP_F_SKEY_PROTECTION; + int r; - if (mop->flags & ~supported_flags || mop->ar >= NUM_ACRS || !mop->size) + r = mem_op_validate_common(mop, KVM_S390_MEMOP_F_INJECT_EXCEPTION | + KVM_S390_MEMOP_F_CHECK_ONLY | + KVM_S390_MEMOP_F_SKEY_PROTECTION); + if (r) + return r; + if (mop->ar >= NUM_ACRS) return -EINVAL; - if (mop->size > MEM_OP_MAX_SIZE) - return -E2BIG; if (kvm_s390_pv_cpu_is_protected(vcpu)) return -EINVAL; - if (mop->flags & KVM_S390_MEMOP_F_SKEY_PROTECTION) { - if (access_key_invalid(mop->key)) - return -EINVAL; - } else { - mop->key = 0; - } if (!(mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY)) { tmpbuf = vmalloc(mop->size); if (!tmpbuf) return -ENOMEM; } - switch (mop->op) { - case KVM_S390_MEMOP_LOGICAL_READ: - if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) { - r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, - GACC_FETCH, mop->key); - break; - } + acc_mode = mop->op == KVM_S390_MEMOP_LOGICAL_READ ? GACC_FETCH : GACC_STORE; + if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) { + r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, + acc_mode, mop->key); + goto out_inject; + } + if (acc_mode == GACC_FETCH) { r = read_guest_with_key(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size, mop->key); - if (r == 0) { - if (copy_to_user(uaddr, tmpbuf, mop->size)) - r = -EFAULT; - } - break; - case KVM_S390_MEMOP_LOGICAL_WRITE: - if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) { - r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, - GACC_STORE, mop->key); - break; + if (r) + goto out_inject; + if (copy_to_user(uaddr, tmpbuf, mop->size)) { + r = -EFAULT; + goto out_free; } + } else { if (copy_from_user(tmpbuf, uaddr, mop->size)) { r = -EFAULT; - break; + goto out_free; } r = write_guest_with_key(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size, mop->key); - break; } +out_inject: if (r > 0 && (mop->flags & KVM_S390_MEMOP_F_INJECT_EXCEPTION) != 0) kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); +out_free: vfree(tmpbuf); return r; } @@ -5633,23 +5673,40 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, if (kvm_s390_pv_get_handle(kvm)) return -EINVAL; - if (change == KVM_MR_DELETE || change == KVM_MR_FLAGS_ONLY) - return 0; + if (change != KVM_MR_DELETE && change != KVM_MR_FLAGS_ONLY) { + /* + * A few sanity checks. We can have memory slots which have to be + * located/ended at a segment boundary (1MB). The memory in userland is + * ok to be fragmented into various different vmas. It is okay to mmap() + * and munmap() stuff in this slot after doing this call at any time + */ - /* A few sanity checks. We can have memory slots which have to be - located/ended at a segment boundary (1MB). The memory in userland is - ok to be fragmented into various different vmas. It is okay to mmap() - and munmap() stuff in this slot after doing this call at any time */ + if (new->userspace_addr & 0xffffful) + return -EINVAL; - if (new->userspace_addr & 0xffffful) - return -EINVAL; + size = new->npages * PAGE_SIZE; + if (size & 0xffffful) + return -EINVAL; - size = new->npages * PAGE_SIZE; - if (size & 0xffffful) - return -EINVAL; + if ((new->base_gfn * PAGE_SIZE) + size > kvm->arch.mem_limit) + return -EINVAL; + } - if ((new->base_gfn * PAGE_SIZE) + size > kvm->arch.mem_limit) - return -EINVAL; + if (!kvm->arch.migration_mode) + return 0; + + /* + * Turn off migration mode when: + * - userspace creates a new memslot with dirty logging off, + * - userspace modifies an existing memslot (MOVE or FLAGS_ONLY) and + * dirty logging is turned off. + * Migration mode expects dirty page logging being enabled to store + * its dirty bitmap. + */ + if (change != KVM_MR_DELETE && + !(new->flags & KVM_MEM_LOG_DIRTY_PAGES)) + WARN(kvm_s390_vm_stop_migration(kvm), + "Failed to stop migration mode"); return 0; } @@ -5696,7 +5753,7 @@ static inline unsigned long nonhyp_mask(int i) static int __init kvm_s390_init(void) { - int i; + int i, r; if (!sclp.has_sief2) { pr_info("SIE is not available\n"); @@ -5712,12 +5769,23 @@ static int __init kvm_s390_init(void) kvm_s390_fac_base[i] |= stfle_fac_list[i] & nonhyp_mask(i); - return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); + r = __kvm_s390_init(); + if (r) + return r; + + r = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); + if (r) { + __kvm_s390_exit(); + return r; + } + return 0; } static void __exit kvm_s390_exit(void) { kvm_exit(); + + __kvm_s390_exit(); } module_init(kvm_s390_init); diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index d48588c207d8..0261d42c7d01 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -470,7 +470,7 @@ void kvm_s390_gisa_clear(struct kvm *kvm); void kvm_s390_gisa_destroy(struct kvm *kvm); void kvm_s390_gisa_disable(struct kvm *kvm); void kvm_s390_gisa_enable(struct kvm *kvm); -int kvm_s390_gib_init(u8 nisc); +int __init kvm_s390_gib_init(u8 nisc); void kvm_s390_gib_destroy(void); /* implemented in guestdbg.c */ diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index ec51e810e381..b124d586db55 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -672,7 +672,7 @@ out: return r; } -int kvm_s390_pci_init(void) +int __init kvm_s390_pci_init(void) { zpci_kvm_hook.kvm_register = kvm_s390_pci_register_kvm; zpci_kvm_hook.kvm_unregister = kvm_s390_pci_unregister_kvm; diff --git a/arch/s390/kvm/pci.h b/arch/s390/kvm/pci.h index 486d06ef563f..ff0972dd5e71 100644 --- a/arch/s390/kvm/pci.h +++ b/arch/s390/kvm/pci.h @@ -60,7 +60,7 @@ void kvm_s390_pci_clear_list(struct kvm *kvm); int kvm_s390_pci_zpci_op(struct kvm *kvm, struct kvm_s390_zpci_op *args); -int kvm_s390_pci_init(void); +int __init kvm_s390_pci_init(void); void kvm_s390_pci_exit(void); static inline bool kvm_s390_pci_interp_allowed(void) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 9fce2d1247a7..a3fb996a86a1 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -6495,6 +6495,7 @@ __init int intel_pmu_init(void) x86_pmu.pebs_constraints = intel_spr_pebs_event_constraints; x86_pmu.extra_regs = intel_spr_extra_regs; x86_pmu.limit_period = spr_limit_period; + x86_pmu.pebs_ept = 1; x86_pmu.pebs_aliases = NULL; x86_pmu.pebs_prec_dist = true; x86_pmu.pebs_block = true; diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index b0354dc869d2..a2e566e53076 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -2366,8 +2366,10 @@ void __init intel_ds_init(void) x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME; break; - case 4: case 5: + x86_pmu.pebs_ept = 1; + fallthrough; + case 4: x86_pmu.drain_pebs = intel_pmu_drain_pebs_icl; x86_pmu.pebs_record_size = sizeof(struct pebs_basic); if (x86_pmu.intel_cap.pebs_baseline) { diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 389ea336258f..73c9672c123b 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -315,6 +315,9 @@ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ #define X86_FEATURE_CMPCCXADD (12*32+ 7) /* "" CMPccXADD instructions */ #define X86_FEATURE_ARCH_PERFMON_EXT (12*32+ 8) /* "" Intel Architectural PerfMon Extension */ +#define X86_FEATURE_FZRM (12*32+10) /* "" Fast zero-length REP MOVSB */ +#define X86_FEATURE_FSRS (12*32+11) /* "" Fast short REP STOSB */ +#define X86_FEATURE_FSRC (12*32+12) /* "" Fast short REP {CMPSB,SCASB} */ #define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */ #define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */ #define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */ diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 566ac26239ba..0b73a809e9e1 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -269,6 +269,9 @@ enum hv_isolation_type { /* TSC invariant control */ #define HV_X64_MSR_TSC_INVARIANT_CONTROL 0x40000118 +/* HV_X64_MSR_TSC_INVARIANT_CONTROL bits */ +#define HV_EXPOSE_INVARIANT_TSC BIT_ULL(0) + /* Register name aliases for temporary compatibility */ #define HV_X64_MSR_STIMER0_COUNT HV_REGISTER_STIMER0_COUNT #define HV_X64_MSR_STIMER0_CONFIG HV_REGISTER_STIMER0_CONFIG diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index 72184b0b2219..b241af4ce9b4 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -582,18 +582,14 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_MC, xenpv_exc_machine_check); /* NMI */ -#if defined(CONFIG_X86_64) && IS_ENABLED(CONFIG_KVM_INTEL) +#if IS_ENABLED(CONFIG_KVM_INTEL) /* - * Special NOIST entry point for VMX which invokes this on the kernel - * stack. asm_exc_nmi() requires an IST to work correctly vs. the NMI - * 'executing' marker. - * - * On 32bit this just uses the regular NMI entry point because 32-bit does - * not have ISTs. + * Special entry point for VMX which invokes this on the kernel stack, even for + * 64-bit, i.e. without using an IST. asm_exc_nmi() requires an IST to work + * correctly vs. the NMI 'executing' marker. Used for 32-bit kernels as well + * to avoid more ifdeffery. */ -DECLARE_IDTENTRY(X86_TRAP_NMI, exc_nmi_noist); -#else -#define asm_exc_nmi_noist asm_exc_nmi +DECLARE_IDTENTRY(X86_TRAP_NMI, exc_nmi_kvm_vmx); #endif DECLARE_IDTENTRY_NMI(X86_TRAP_NMI, exc_nmi); diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index abccd51dcfca..8dc345cc6318 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -14,6 +14,7 @@ BUILD_BUG_ON(1) * to make a definition optional, but in this case the default will * be __static_call_return0. */ +KVM_X86_OP(check_processor_compatibility) KVM_X86_OP(hardware_enable) KVM_X86_OP(hardware_disable) KVM_X86_OP(hardware_unsetup) @@ -76,7 +77,6 @@ KVM_X86_OP(set_nmi_mask) KVM_X86_OP(enable_nmi_window) KVM_X86_OP(enable_irq_window) KVM_X86_OP_OPTIONAL(update_cr8_intercept) -KVM_X86_OP(check_apicv_inhibit_reasons) KVM_X86_OP(refresh_apicv_exec_ctrl) KVM_X86_OP_OPTIONAL(hwapic_irr_update) KVM_X86_OP_OPTIONAL(hwapic_isr_update) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 6aaae18f1854..808c292ad3f4 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -134,8 +134,6 @@ #define INVALID_PAGE (~(hpa_t)0) #define VALID_PAGE(x) ((x) != INVALID_PAGE) -#define INVALID_GPA (~(gpa_t)0) - /* KVM Hugepage definitions for x86 */ #define KVM_MAX_HUGEPAGE_LEVEL PG_LEVEL_1G #define KVM_NR_PAGE_SIZES (KVM_MAX_HUGEPAGE_LEVEL - PG_LEVEL_4K + 1) @@ -514,6 +512,7 @@ struct kvm_pmc { #define MSR_ARCH_PERFMON_PERFCTR_MAX (MSR_ARCH_PERFMON_PERFCTR0 + KVM_INTEL_PMC_MAX_GENERIC - 1) #define MSR_ARCH_PERFMON_EVENTSEL_MAX (MSR_ARCH_PERFMON_EVENTSEL0 + KVM_INTEL_PMC_MAX_GENERIC - 1) #define KVM_PMC_MAX_FIXED 3 +#define MSR_ARCH_PERFMON_FIXED_CTR_MAX (MSR_ARCH_PERFMON_FIXED_CTR0 + KVM_PMC_MAX_FIXED - 1) #define KVM_AMD_PMC_MAX_GENERIC 6 struct kvm_pmu { unsigned nr_arch_gp_counters; @@ -678,6 +677,11 @@ struct kvm_vcpu_hv { } nested; }; +struct kvm_hypervisor_cpuid { + u32 base; + u32 limit; +}; + /* Xen HVM per vcpu emulation context */ struct kvm_vcpu_xen { u64 hypercall_rip; @@ -698,6 +702,7 @@ struct kvm_vcpu_xen { struct hrtimer timer; int poll_evtchn; struct timer_list poll_timer; + struct kvm_hypervisor_cpuid cpuid; }; struct kvm_queued_exception { @@ -826,7 +831,7 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; - u32 kvm_cpuid_base; + struct kvm_hypervisor_cpuid kvm_cpuid; u64 reserved_gpa_bits; int maxphyaddr; @@ -1022,19 +1027,30 @@ struct kvm_arch_memory_slot { }; /* - * We use as the mode the number of bits allocated in the LDR for the - * logical processor ID. It happens that these are all powers of two. - * This makes it is very easy to detect cases where the APICs are - * configured for multiple modes; in that case, we cannot use the map and - * hence cannot use kvm_irq_delivery_to_apic_fast either. + * Track the mode of the optimized logical map, as the rules for decoding the + * destination vary per mode. Enabling the optimized logical map requires all + * software-enabled local APIs to be in the same mode, each addressable APIC to + * be mapped to only one MDA, and each MDA to map to at most one APIC. */ -#define KVM_APIC_MODE_XAPIC_CLUSTER 4 -#define KVM_APIC_MODE_XAPIC_FLAT 8 -#define KVM_APIC_MODE_X2APIC 16 +enum kvm_apic_logical_mode { + /* All local APICs are software disabled. */ + KVM_APIC_MODE_SW_DISABLED, + /* All software enabled local APICs in xAPIC cluster addressing mode. */ + KVM_APIC_MODE_XAPIC_CLUSTER, + /* All software enabled local APICs in xAPIC flat addressing mode. */ + KVM_APIC_MODE_XAPIC_FLAT, + /* All software enabled local APICs in x2APIC mode. */ + KVM_APIC_MODE_X2APIC, + /* + * Optimized map disabled, e.g. not all local APICs in the same logical + * mode, same logical ID assigned to multiple APICs, etc. + */ + KVM_APIC_MODE_MAP_DISABLED, +}; struct kvm_apic_map { struct rcu_head rcu; - u8 mode; + enum kvm_apic_logical_mode logical_mode; u32 max_apic_id; union { struct kvm_lapic *xapic_flat_map[8]; @@ -1088,6 +1104,7 @@ struct kvm_hv { u64 hv_reenlightenment_control; u64 hv_tsc_emulation_control; u64 hv_tsc_emulation_status; + u64 hv_invtsc_control; /* How many vCPUs have VP index != vCPU index */ atomic_t num_mismatched_vp_indexes; @@ -1133,6 +1150,18 @@ struct kvm_x86_msr_filter { struct msr_bitmap_range ranges[16]; }; +struct kvm_x86_pmu_event_filter { + __u32 action; + __u32 nevents; + __u32 fixed_counter_bitmap; + __u32 flags; + __u32 nr_includes; + __u32 nr_excludes; + __u64 *includes; + __u64 *excludes; + __u64 events[]; +}; + enum kvm_apicv_inhibit { /********************************************************************/ @@ -1164,6 +1193,12 @@ enum kvm_apicv_inhibit { APICV_INHIBIT_REASON_BLOCKIRQ, /* + * APICv is disabled because not all vCPUs have a 1:1 mapping between + * APIC ID and vCPU, _and_ KVM is not applying its x2APIC hotplug hack. + */ + APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED, + + /* * For simplicity, the APIC acceleration is inhibited * first time either APIC ID or APIC base are changed by the guest * from their reset values. @@ -1201,6 +1236,12 @@ enum kvm_apicv_inhibit { * AVIC is disabled because SEV doesn't support it. */ APICV_INHIBIT_REASON_SEV, + + /* + * AVIC is disabled because not all vCPUs with a valid LDR have a 1:1 + * mapping between logical ID and vCPU. + */ + APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED, }; struct kvm_arch { @@ -1249,10 +1290,11 @@ struct kvm_arch { struct kvm_apic_map __rcu *apic_map; atomic_t apic_map_dirty; - /* Protects apic_access_memslot_enabled and apicv_inhibit_reasons */ - struct rw_semaphore apicv_update_lock; - bool apic_access_memslot_enabled; + bool apic_access_memslot_inhibited; + + /* Protects apicv_inhibit_reasons */ + struct rw_semaphore apicv_update_lock; unsigned long apicv_inhibit_reasons; gpa_t wall_clock; @@ -1302,7 +1344,6 @@ struct kvm_arch { u32 bsp_vcpu_id; u64 disabled_quirks; - int cpu_dirty_logging_count; enum kvm_irqchip_mode irqchip_mode; u8 nr_reserved_ioapic_pins; @@ -1338,25 +1379,16 @@ struct kvm_arch { /* Guest can access the SGX PROVISIONKEY. */ bool sgx_provisioning_allowed; - struct kvm_pmu_event_filter __rcu *pmu_event_filter; + struct kvm_x86_pmu_event_filter __rcu *pmu_event_filter; struct task_struct *nx_huge_page_recovery_thread; #ifdef CONFIG_X86_64 - /* - * Whether the TDP MMU is enabled for this VM. This contains a - * snapshot of the TDP MMU module parameter from when the VM was - * created and remains unchanged for the life of the VM. If this is - * true, TDP MMU handler functions will run for various MMU - * operations. - */ - bool tdp_mmu_enabled; - /* The number of TDP MMU pages across all roots. */ atomic64_t tdp_mmu_pages; /* - * List of kvm_mmu_page structs being used as roots. - * All kvm_mmu_page structs in the list should have + * List of struct kvm_mmu_pages being used as roots. + * All struct kvm_mmu_pages in the list should have * tdp_mmu_page set. * * For reads, this list is protected by: @@ -1520,6 +1552,8 @@ static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical) struct kvm_x86_ops { const char *name; + int (*check_processor_compatibility)(void); + int (*hardware_enable)(void); void (*hardware_disable)(void); void (*hardware_unsetup)(void); @@ -1608,6 +1642,8 @@ struct kvm_x86_ops { void (*enable_irq_window)(struct kvm_vcpu *vcpu); void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr); bool (*check_apicv_inhibit_reasons)(enum kvm_apicv_inhibit reason); + const unsigned long required_apicv_inhibits; + bool allow_apicv_in_x2apic_without_x2apic_virtualization; void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); void (*hwapic_isr_update)(int isr); @@ -1731,9 +1767,6 @@ struct kvm_x86_nested_ops { }; struct kvm_x86_init_ops { - int (*cpu_has_kvm_support)(void); - int (*disabled_by_bios)(void); - int (*check_processor_compatibility)(void); int (*hardware_setup)(void); unsigned int (*handle_intel_pt_intr)(void); @@ -1760,6 +1793,9 @@ extern struct kvm_x86_ops kvm_x86_ops; #define KVM_X86_OP_OPTIONAL_RET0 KVM_X86_OP #include <asm/kvm-x86-ops.h> +int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops); +void kvm_x86_vendor_exit(void); + #define __KVM_HAVE_ARCH_VM_ALLOC static inline struct kvm *kvm_arch_alloc_vm(void) { @@ -1982,7 +2018,7 @@ gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, bool kvm_apicv_activated(struct kvm *kvm); bool kvm_vcpu_apicv_activated(struct kvm_vcpu *vcpu); -void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu); +void __kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu); void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, enum kvm_apicv_inhibit reason, bool set); void kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, @@ -2054,14 +2090,11 @@ enum { TASK_SWITCH_GATE = 3, }; -#define HF_GIF_MASK (1 << 0) -#define HF_NMI_MASK (1 << 3) -#define HF_IRET_MASK (1 << 4) -#define HF_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */ +#define HF_GUEST_MASK (1 << 0) /* VCPU is in guest-mode */ #ifdef CONFIG_KVM_SMM -#define HF_SMM_MASK (1 << 6) -#define HF_SMM_INSIDE_NMI_MASK (1 << 7) +#define HF_SMM_MASK (1 << 1) +#define HF_SMM_INSIDE_NMI_MASK (1 << 2) # define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE # define KVM_ADDRESS_SPACE_NUM 2 diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index 04c17be9b5fd..bc5b4d788c08 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -25,6 +25,8 @@ void __noreturn machine_real_restart(unsigned int type); #define MRR_BIOS 0 #define MRR_APM 1 +void cpu_emergency_disable_virtualization(void); + typedef void (*nmi_shootdown_cb)(int, struct pt_regs*); void nmi_panic_self_stop(struct pt_regs *regs); void nmi_shootdown_cpus(nmi_shootdown_cb callback); diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h index 8757078d4442..3b12e6b99412 100644 --- a/arch/x86/include/asm/virtext.h +++ b/arch/x86/include/asm/virtext.h @@ -126,7 +126,21 @@ static inline void cpu_svm_disable(void) wrmsrl(MSR_VM_HSAVE_PA, 0); rdmsrl(MSR_EFER, efer); - wrmsrl(MSR_EFER, efer & ~EFER_SVME); + if (efer & EFER_SVME) { + /* + * Force GIF=1 prior to disabling SVM to ensure INIT and NMI + * aren't blocked, e.g. if a fatal error occurred between CLGI + * and STGI. Note, STGI may #UD if SVM is disabled from NMI + * context between reading EFER and executing STGI. In that + * case, GIF must already be set, otherwise the NMI would have + * been blocked, so just eat the fault. + */ + asm_volatile_goto("1: stgi\n\t" + _ASM_EXTABLE(1b, %l[fault]) + ::: "memory" : fault); +fault: + wrmsrl(MSR_EFER, efer & ~EFER_SVME); + } } /** Makes sure SVM is disabled, if it is supported on the CPU diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index 16f548a661cf..5fc35f889cd1 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -38,9 +38,11 @@ extern struct start_info *xen_start_info; #include <asm/processor.h> +#define XEN_SIGNATURE "XenVMMXenVMM" + static inline uint32_t xen_cpuid_base(void) { - return hypervisor_cpuid_base("XenVMMXenVMM", 2); + return hypervisor_cpuid_base(XEN_SIGNATURE, 2); } struct pci_dev; diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index e48deab8901d..7f467fe05d42 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -9,6 +9,7 @@ #include <linux/types.h> #include <linux/ioctl.h> +#include <linux/stddef.h> #define KVM_PIO_PAGE_OFFSET 1 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2 @@ -507,8 +508,8 @@ struct kvm_nested_state { * KVM_{GET,PUT}_NESTED_STATE ioctl values. */ union { - struct kvm_vmx_nested_state_data vmx[0]; - struct kvm_svm_nested_state_data svm[0]; + __DECLARE_FLEX_ARRAY(struct kvm_vmx_nested_state_data, vmx); + __DECLARE_FLEX_ARRAY(struct kvm_svm_nested_state_data, svm); } data; }; @@ -525,6 +526,35 @@ struct kvm_pmu_event_filter { #define KVM_PMU_EVENT_ALLOW 0 #define KVM_PMU_EVENT_DENY 1 +#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS BIT(0) +#define KVM_PMU_EVENT_FLAGS_VALID_MASK (KVM_PMU_EVENT_FLAG_MASKED_EVENTS) + +/* + * Masked event layout. + * Bits Description + * ---- ----------- + * 7:0 event select (low bits) + * 15:8 umask match + * 31:16 unused + * 35:32 event select (high bits) + * 36:54 unused + * 55 exclude bit + * 63:56 umask mask + */ + +#define KVM_PMU_ENCODE_MASKED_ENTRY(event_select, mask, match, exclude) \ + (((event_select) & 0xFFULL) | (((event_select) & 0XF00ULL) << 24) | \ + (((mask) & 0xFFULL) << 56) | \ + (((match) & 0xFFULL) << 8) | \ + ((__u64)(!!(exclude)) << 55)) + +#define KVM_PMU_MASKED_ENTRY_EVENT_SELECT \ + (GENMASK_ULL(7, 0) | GENMASK_ULL(35, 32)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (GENMASK_ULL(63, 56)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (GENMASK_ULL(15, 8)) +#define KVM_PMU_MASKED_ENTRY_EXCLUDE (BIT_ULL(55)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT (56) + /* for KVM_{GET,SET,HAS}_DEVICE_ATTR */ #define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */ #define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index f924a76c6923..f36dc2f796c5 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -460,7 +460,7 @@ static void __init ms_hyperv_init_platform(void) * setting of this MSR bit should happen before init_intel() * is called. */ - wrmsrl(HV_X64_MSR_TSC_INVARIANT_CONTROL, 0x1); + wrmsrl(HV_X64_MSR_TSC_INVARIANT_CONTROL, HV_EXPOSE_INVARIANT_TSC); setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); } diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 305514431f26..cdd92ab43cda 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -37,7 +37,6 @@ #include <linux/kdebug.h> #include <asm/cpu.h> #include <asm/reboot.h> -#include <asm/virtext.h> #include <asm/intel_pt.h> #include <asm/crash.h> #include <asm/cmdline.h> @@ -81,15 +80,6 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) */ cpu_crash_vmclear_loaded_vmcss(); - /* Disable VMX or SVM if needed. - * - * We need to disable virtualization on all CPUs. - * Having VMX or SVM enabled on any CPU may break rebooting - * after the kdump kernel has finished its task. - */ - cpu_emergency_vmxoff(); - cpu_emergency_svm_disable(); - /* * Disable Intel PT to stop its logging */ @@ -148,12 +138,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs) */ cpu_crash_vmclear_loaded_vmcss(); - /* Booting kdump kernel with VMX or SVM enabled won't work, - * because (among other limitations) we can't disable paging - * with the virt flags. - */ - cpu_emergency_vmxoff(); - cpu_emergency_svm_disable(); + cpu_emergency_disable_virtualization(); /* * Disable Intel PT to stop its logging diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index c315b18ec7c8..776f4b1e395b 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -560,14 +560,14 @@ nmi_restart: } } -#if defined(CONFIG_X86_64) && IS_ENABLED(CONFIG_KVM_INTEL) -DEFINE_IDTENTRY_RAW(exc_nmi_noist) +#if IS_ENABLED(CONFIG_KVM_INTEL) +DEFINE_IDTENTRY_RAW(exc_nmi_kvm_vmx) { exc_nmi(regs); } -#endif #if IS_MODULE(CONFIG_KVM_INTEL) -EXPORT_SYMBOL_GPL(asm_exc_nmi_noist); +EXPORT_SYMBOL_GPL(asm_exc_nmi_kvm_vmx); +#endif #endif #ifdef CONFIG_NMI_CHECK_CPU diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index c3636ea4aa71..d03c551defcc 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -528,33 +528,29 @@ static inline void kb_wait(void) } } -static void vmxoff_nmi(int cpu, struct pt_regs *regs) -{ - cpu_emergency_vmxoff(); -} +static inline void nmi_shootdown_cpus_on_restart(void); -/* Use NMIs as IPIs to tell all CPUs to disable virtualization */ -static void emergency_vmx_disable_all(void) +static void emergency_reboot_disable_virtualization(void) { /* Just make sure we won't change CPUs while doing this */ local_irq_disable(); /* - * Disable VMX on all CPUs before rebooting, otherwise we risk hanging - * the machine, because the CPU blocks INIT when it's in VMX root. + * Disable virtualization on all CPUs before rebooting to avoid hanging + * the system, as VMX and SVM block INIT when running in the host. * * We can't take any locks and we may be on an inconsistent state, so - * use NMIs as IPIs to tell the other CPUs to exit VMX root and halt. + * use NMIs as IPIs to tell the other CPUs to disable VMX/SVM and halt. * - * Do the NMI shootdown even if VMX if off on _this_ CPU, as that - * doesn't prevent a different CPU from being in VMX root operation. + * Do the NMI shootdown even if virtualization is off on _this_ CPU, as + * other CPUs may have virtualization enabled. */ - if (cpu_has_vmx()) { - /* Safely force _this_ CPU out of VMX root operation. */ - __cpu_emergency_vmxoff(); + if (cpu_has_vmx() || cpu_has_svm(NULL)) { + /* Safely force _this_ CPU out of VMX/SVM operation. */ + cpu_emergency_disable_virtualization(); - /* Halt and exit VMX root operation on the other CPUs. */ - nmi_shootdown_cpus(vmxoff_nmi); + /* Disable VMX/SVM and halt on other CPUs. */ + nmi_shootdown_cpus_on_restart(); } } @@ -590,7 +586,7 @@ static void native_machine_emergency_restart(void) unsigned short mode; if (reboot_emergency) - emergency_vmx_disable_all(); + emergency_reboot_disable_virtualization(); tboot_shutdown(TB_SHUTDOWN_REBOOT); @@ -795,6 +791,17 @@ void machine_crash_shutdown(struct pt_regs *regs) /* This is the CPU performing the emergency shutdown work. */ int crashing_cpu = -1; +/* + * Disable virtualization, i.e. VMX or SVM, to ensure INIT is recognized during + * reboot. VMX blocks INIT if the CPU is post-VMXON, and SVM blocks INIT if + * GIF=0, i.e. if the crash occurred between CLGI and STGI. + */ +void cpu_emergency_disable_virtualization(void) +{ + cpu_emergency_vmxoff(); + cpu_emergency_svm_disable(); +} + #if defined(CONFIG_SMP) static nmi_shootdown_cb shootdown_callback; @@ -817,7 +824,14 @@ static int crash_nmi_callback(unsigned int val, struct pt_regs *regs) return NMI_HANDLED; local_irq_disable(); - shootdown_callback(cpu, regs); + if (shootdown_callback) + shootdown_callback(cpu, regs); + + /* + * Prepare the CPU for reboot _after_ invoking the callback so that the + * callback can safely use virtualization instructions, e.g. VMCLEAR. + */ + cpu_emergency_disable_virtualization(); atomic_dec(&waiting_for_crash_ipi); /* Assume hlt works */ @@ -828,18 +842,32 @@ static int crash_nmi_callback(unsigned int val, struct pt_regs *regs) return NMI_HANDLED; } -/* - * Halt all other CPUs, calling the specified function on each of them +/** + * nmi_shootdown_cpus - Stop other CPUs via NMI + * @callback: Optional callback to be invoked from the NMI handler + * + * The NMI handler on the remote CPUs invokes @callback, if not + * NULL, first and then disables virtualization to ensure that + * INIT is recognized during reboot. * - * This function can be used to halt all other CPUs on crash - * or emergency reboot time. The function passed as parameter - * will be called inside a NMI handler on all CPUs. + * nmi_shootdown_cpus() can only be invoked once. After the first + * invocation all other CPUs are stuck in crash_nmi_callback() and + * cannot respond to a second NMI. */ void nmi_shootdown_cpus(nmi_shootdown_cb callback) { unsigned long msecs; + local_irq_disable(); + /* + * Avoid certain doom if a shootdown already occurred; re-registering + * the NMI handler will cause list corruption, modifying the callback + * will do who knows what, etc... + */ + if (WARN_ON_ONCE(crash_ipi_issued)) + return; + /* Make a note of crashing cpu. Will be used in NMI callback. */ crashing_cpu = safe_smp_processor_id(); @@ -867,7 +895,17 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback) msecs--; } - /* Leave the nmi callback set */ + /* + * Leave the nmi callback set, shootdown is a one-time thing. Clearing + * the callback could result in a NULL pointer dereference if a CPU + * (finally) responds after the timeout expires. + */ +} + +static inline void nmi_shootdown_cpus_on_restart(void) +{ + if (!crash_ipi_issued) + nmi_shootdown_cpus(NULL); } /* @@ -897,6 +935,8 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback) /* No other CPUs to shoot down */ } +static inline void nmi_shootdown_cpus_on_restart(void) { } + void run_crash_ipi_callback(struct pt_regs *regs) { } diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 06db901fabe8..375b33ecafa2 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -32,7 +32,7 @@ #include <asm/mce.h> #include <asm/trace/irq_vectors.h> #include <asm/kexec.h> -#include <asm/virtext.h> +#include <asm/reboot.h> /* * Some notes on x86 processor bugs affecting SMP operation: @@ -122,7 +122,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs) if (raw_smp_processor_id() == atomic_read(&stopping_cpu)) return NMI_HANDLED; - cpu_emergency_vmxoff(); + cpu_emergency_disable_virtualization(); stop_this_cpu(NULL); return NMI_HANDLED; @@ -134,7 +134,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs) DEFINE_IDTENTRY_SYSVEC(sysvec_reboot) { ack_APIC_irq(); - cpu_emergency_vmxoff(); + cpu_emergency_disable_virtualization(); stop_this_cpu(NULL); } diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index fbeaa9ddef59..8e578311ca9d 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -49,6 +49,7 @@ config KVM select SRCU select INTERVAL_TREE select HAVE_KVM_PM_NOTIFIER if PM + select KVM_GENERIC_HARDWARE_ENABLING help Support hosting fully virtualized guest machines using hardware virtualization extensions. You will need a fairly recent diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 7f1b585f9a67..599aebec2d52 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -8,6 +8,7 @@ * Copyright 2011 Red Hat, Inc. and/or its affiliates. * Copyright IBM Corporation, 2008 */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <linux/export.h> @@ -25,6 +26,7 @@ #include "mmu.h" #include "trace.h" #include "pmu.h" +#include "xen.h" /* * Unlike "struct cpuinfo_x86.x86_capability", kvm_cpu_caps doesn't need to be @@ -180,15 +182,15 @@ static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 return 0; } -static void kvm_update_kvm_cpuid_base(struct kvm_vcpu *vcpu) +static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcpu, + const char *sig) { - u32 function; + struct kvm_hypervisor_cpuid cpuid = {}; struct kvm_cpuid_entry2 *entry; + u32 base; - vcpu->arch.kvm_cpuid_base = 0; - - for_each_possible_hypervisor_cpuid_base(function) { - entry = kvm_find_cpuid_entry(vcpu, function); + for_each_possible_hypervisor_cpuid_base(base) { + entry = kvm_find_cpuid_entry(vcpu, base); if (entry) { u32 signature[3]; @@ -197,19 +199,21 @@ static void kvm_update_kvm_cpuid_base(struct kvm_vcpu *vcpu) signature[1] = entry->ecx; signature[2] = entry->edx; - BUILD_BUG_ON(sizeof(signature) > sizeof(KVM_SIGNATURE)); - if (!memcmp(signature, KVM_SIGNATURE, sizeof(signature))) { - vcpu->arch.kvm_cpuid_base = function; + if (!memcmp(signature, sig, sizeof(signature))) { + cpuid.base = base; + cpuid.limit = entry->eax; break; } } } + + return cpuid; } static struct kvm_cpuid_entry2 *__kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *entries, int nent) { - u32 base = vcpu->arch.kvm_cpuid_base; + u32 base = vcpu->arch.kvm_cpuid.base; if (!base) return NULL; @@ -439,7 +443,8 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, vcpu->arch.cpuid_entries = e2; vcpu->arch.cpuid_nent = nent; - kvm_update_kvm_cpuid_base(vcpu); + vcpu->arch.kvm_cpuid = kvm_get_hypervisor_cpuid(vcpu, KVM_SIGNATURE); + vcpu->arch.xen.cpuid = kvm_get_hypervisor_cpuid(vcpu, XEN_SIGNATURE); kvm_vcpu_after_set_cpuid(vcpu); return 0; @@ -663,8 +668,9 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_set(X86_FEATURE_SPEC_CTRL_SSBD); kvm_cpu_cap_mask(CPUID_7_1_EAX, - F(AVX_VNNI) | F(AVX512_BF16) | F(CMPCCXADD) | F(AMX_FP16) | - F(AVX_IFMA) + F(AVX_VNNI) | F(AVX512_BF16) | F(CMPCCXADD) | + F(FZRM) | F(FSRS) | F(FSRC) | + F(AMX_FP16) | F(AVX_IFMA) ); kvm_cpu_cap_init_kvm_defined(CPUID_7_1_EDX, @@ -701,6 +707,10 @@ void kvm_set_cpu_caps(void) if (!tdp_enabled && IS_ENABLED(CONFIG_X86_64)) kvm_cpu_cap_set(X86_FEATURE_GBPAGES); + kvm_cpu_cap_init_kvm_defined(CPUID_8000_0007_EDX, + SF(CONSTANT_TSC) + ); + kvm_cpu_cap_mask(CPUID_8000_0008_EBX, F(CLZERO) | F(XSAVEERPTR) | F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | @@ -1169,8 +1179,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->edx &= ~GENMASK(17, 16); break; case 0x80000007: /* Advanced power management */ - /* invariant TSC is CPUID.80000007H:EDX[8] */ - entry->edx &= (1 << 8); + cpuid_entry_override(entry, CPUID_8000_0007_EDX); + /* mask against host */ entry->edx &= boot_cpu_data.x86_power; entry->eax = entry->ebx = entry->ecx = 0; @@ -1485,6 +1495,9 @@ bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, if (!__kvm_get_msr(vcpu, MSR_IA32_TSX_CTRL, &data, true) && (data & TSX_CTRL_CPUID_CLEAR)) *ebx &= ~(F(RTM) | F(HLE)); + } else if (function == 0x80000007) { + if (kvm_hv_invtsc_suppressed(vcpu)) + *edx &= ~SF(CONSTANT_TSC); } } else { *eax = *ebx = *ecx = *edx = 0; diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index c1390357126a..ee8c4c3496ed 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -4,6 +4,8 @@ * * Copyright 2016 Red Hat, Inc. and/or its affiliates. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kvm_host.h> #include <linux/debugfs.h> #include "lapic.h" diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 56e1cf7c339e..a20bec931764 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -17,6 +17,7 @@ * * From: xen-unstable 10676:af9809f51f81a3c43f276f00c81a52ef558afda4 */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include "kvm_cache_regs.h" @@ -1633,7 +1634,7 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, case VCPU_SREG_SS: /* * segment is not a writable data segment or segment - * selector's RPL != CPL or segment selector's RPL != CPL + * selector's RPL != CPL or DPL != CPL */ if (rpl != cpl || (seg_desc.type & 0xa) != 0x2 || dpl != cpl) goto exception; @@ -1695,11 +1696,11 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, /* * segment is not a data or readable code segment or * ((segment is a data or nonconforming code segment) - * and (both RPL and CPL > DPL)) + * and ((RPL > DPL) or (CPL > DPL))) */ if ((seg_desc.type & 0xa) == 0x8 || (((seg_desc.type & 0xc) != 0xc) && - (rpl > dpl && cpl > dpl))) + (rpl > dpl || cpl > dpl))) goto exception; break; } @@ -2309,7 +2310,7 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt) static int em_rsm(struct x86_emulate_ctxt *ctxt) { - if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0) + if (!ctxt->ops->is_smm(ctxt)) return emulate_ud(ctxt); if (ctxt->ops->leave_smm(ctxt)) @@ -5132,7 +5133,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) const struct x86_emulate_ops *ops = ctxt->ops; int rc = X86EMUL_CONTINUE; int saved_dst_type = ctxt->dst.type; - unsigned emul_flags; + bool is_guest_mode = ctxt->ops->is_guest_mode(ctxt); ctxt->mem_read.pos = 0; @@ -5147,7 +5148,6 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) goto done; } - emul_flags = ctxt->ops->get_hflags(ctxt); if (unlikely(ctxt->d & (No64|Undefined|Sse|Mmx|Intercept|CheckPerm|Priv|Prot|String))) { if ((ctxt->mode == X86EMUL_MODE_PROT64 && (ctxt->d & No64)) || @@ -5181,7 +5181,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) fetch_possible_mmx_operand(&ctxt->dst); } - if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) { + if (unlikely(is_guest_mode) && ctxt->intercept) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_PRE_EXCEPT); if (rc != X86EMUL_CONTINUE) @@ -5210,7 +5210,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) goto done; } - if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) { + if (unlikely(is_guest_mode) && (ctxt->d & Intercept)) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_POST_EXCEPT); if (rc != X86EMUL_CONTINUE) @@ -5264,7 +5264,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) special_insn: - if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) { + if (unlikely(is_guest_mode) && (ctxt->d & Intercept)) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_POST_MEMACCESS); if (rc != X86EMUL_CONTINUE) diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index e8296942a868..b28fd020066f 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -17,6 +17,7 @@ * Ben-Ami Yassour <benami@il.ibm.com> * Andrey Smetanin <asmetanin@virtuozzo.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "x86.h" #include "lapic.h" @@ -43,6 +44,24 @@ #define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, HV_VCPUS_PER_SPARSE_BANK) +/* + * As per Hyper-V TLFS, extended hypercalls start from 0x8001 + * (HvExtCallQueryCapabilities). Response of this hypercalls is a 64 bit value + * where each bit tells which extended hypercall is available besides + * HvExtCallQueryCapabilities. + * + * 0x8001 - First extended hypercall, HvExtCallQueryCapabilities, no bit + * assigned. + * + * 0x8002 - Bit 0 + * 0x8003 - Bit 1 + * .. + * 0x8041 - Bit 63 + * + * Therefore, HV_EXT_CALL_MAX = 0x8001 + 64 + */ +#define HV_EXT_CALL_MAX (HV_EXT_CALL_QUERY_CAPABILITIES + 64) + static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer, bool vcpu_kick); @@ -999,6 +1018,7 @@ static bool kvm_hv_msr_partition_wide(u32 msr) case HV_X64_MSR_REENLIGHTENMENT_CONTROL: case HV_X64_MSR_TSC_EMULATION_CONTROL: case HV_X64_MSR_TSC_EMULATION_STATUS: + case HV_X64_MSR_TSC_INVARIANT_CONTROL: case HV_X64_MSR_SYNDBG_OPTIONS: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: r = true; @@ -1283,6 +1303,9 @@ static bool hv_check_msr_access(struct kvm_vcpu_hv *hv_vcpu, u32 msr) case HV_X64_MSR_TSC_EMULATION_STATUS: return hv_vcpu->cpuid_cache.features_eax & HV_ACCESS_REENLIGHTENMENT; + case HV_X64_MSR_TSC_INVARIANT_CONTROL: + return hv_vcpu->cpuid_cache.features_eax & + HV_ACCESS_TSC_INVARIANT; case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: case HV_X64_MSR_CRASH_CTL: return hv_vcpu->cpuid_cache.features_edx & @@ -1410,12 +1433,22 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, if (!host) return 1; break; + case HV_X64_MSR_TSC_INVARIANT_CONTROL: + /* Only bit 0 is supported */ + if (data & ~HV_EXPOSE_INVARIANT_TSC) + return 1; + + /* The feature can't be disabled from the guest */ + if (!host && hv->hv_invtsc_control && !data) + return 1; + + hv->hv_invtsc_control = data; + break; case HV_X64_MSR_SYNDBG_OPTIONS: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: return syndbg_set_msr(vcpu, msr, data, host); default: - vcpu_unimpl(vcpu, "Hyper-V unhandled wrmsr: 0x%x data 0x%llx\n", - msr, data); + kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } return 0; @@ -1536,8 +1569,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) return 1; break; default: - vcpu_unimpl(vcpu, "Hyper-V unhandled wrmsr: 0x%x data 0x%llx\n", - msr, data); + kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } @@ -1585,11 +1617,14 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, case HV_X64_MSR_TSC_EMULATION_STATUS: data = hv->hv_tsc_emulation_status; break; + case HV_X64_MSR_TSC_INVARIANT_CONTROL: + data = hv->hv_invtsc_control; + break; case HV_X64_MSR_SYNDBG_OPTIONS: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: return syndbg_get_msr(vcpu, msr, pdata, host); default: - vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + kvm_pr_unimpl_rdmsr(vcpu, msr); return 1; } @@ -1654,7 +1689,7 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, data = APIC_BUS_FREQUENCY; break; default: - vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + kvm_pr_unimpl_rdmsr(vcpu, msr); return 1; } *pdata = data; @@ -2420,6 +2455,9 @@ static bool hv_check_hypercall_access(struct kvm_vcpu_hv *hv_vcpu, u16 code) case HVCALL_SEND_IPI: return hv_vcpu->cpuid_cache.enlightenments_eax & HV_X64_CLUSTER_IPI_RECOMMENDED; + case HV_EXT_CALL_QUERY_CAPABILITIES ... HV_EXT_CALL_MAX: + return hv_vcpu->cpuid_cache.features_ebx & + HV_ENABLE_EXTENDED_HYPERCALLS; default: break; } @@ -2512,14 +2550,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } - vcpu->run->exit_reason = KVM_EXIT_HYPERV; - vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL; - vcpu->run->hyperv.u.hcall.input = hc.param; - vcpu->run->hyperv.u.hcall.params[0] = hc.ingpa; - vcpu->run->hyperv.u.hcall.params[1] = hc.outgpa; - vcpu->arch.complete_userspace_io = - kvm_hv_hypercall_complete_userspace; - return 0; + goto hypercall_userspace_exit; case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST: if (unlikely(hc.var_cnt)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; @@ -2578,15 +2609,14 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) ret = HV_STATUS_OPERATION_DENIED; break; } - vcpu->run->exit_reason = KVM_EXIT_HYPERV; - vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL; - vcpu->run->hyperv.u.hcall.input = hc.param; - vcpu->run->hyperv.u.hcall.params[0] = hc.ingpa; - vcpu->run->hyperv.u.hcall.params[1] = hc.outgpa; - vcpu->arch.complete_userspace_io = - kvm_hv_hypercall_complete_userspace; - return 0; + goto hypercall_userspace_exit; } + case HV_EXT_CALL_QUERY_CAPABILITIES ... HV_EXT_CALL_MAX: + if (unlikely(hc.fast)) { + ret = HV_STATUS_INVALID_PARAMETER; + break; + } + goto hypercall_userspace_exit; default: ret = HV_STATUS_INVALID_HYPERCALL_CODE; break; @@ -2594,6 +2624,15 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) hypercall_complete: return kvm_hv_hypercall_complete(vcpu, ret); + +hypercall_userspace_exit: + vcpu->run->exit_reason = KVM_EXIT_HYPERV; + vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL; + vcpu->run->hyperv.u.hcall.input = hc.param; + vcpu->run->hyperv.u.hcall.params[0] = hc.ingpa; + vcpu->run->hyperv.u.hcall.params[1] = hc.outgpa; + vcpu->arch.complete_userspace_io = kvm_hv_hypercall_complete_userspace; + return 0; } void kvm_hv_init_vm(struct kvm *kvm) @@ -2733,9 +2772,11 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, ent->eax |= HV_MSR_REFERENCE_TSC_AVAILABLE; ent->eax |= HV_ACCESS_FREQUENCY_MSRS; ent->eax |= HV_ACCESS_REENLIGHTENMENT; + ent->eax |= HV_ACCESS_TSC_INVARIANT; ent->ebx |= HV_POST_MESSAGES; ent->ebx |= HV_SIGNAL_EVENTS; + ent->ebx |= HV_ENABLE_EXTENDED_HYPERCALLS; ent->edx |= HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE; ent->edx |= HV_FEATURE_FREQUENCY_MSRS_AVAILABLE; diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 9f96414a31c5..f83b8db72b11 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -136,6 +136,33 @@ static inline bool kvm_hv_has_stimer_pending(struct kvm_vcpu *vcpu) HV_SYNIC_STIMER_COUNT); } +/* + * With HV_ACCESS_TSC_INVARIANT feature, invariant TSC (CPUID.80000007H:EDX[8]) + * is only observed after HV_X64_MSR_TSC_INVARIANT_CONTROL was written to. + */ +static inline bool kvm_hv_invtsc_suppressed(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + + /* + * If Hyper-V's invariant TSC control is not exposed to the guest, + * the invariant TSC CPUID flag is not suppressed, Windows guests were + * observed to be able to handle it correctly. Going forward, VMMs are + * encouraged to enable Hyper-V's invariant TSC control when invariant + * TSC CPUID flag is set to make KVM's behavior match genuine Hyper-V. + */ + if (!hv_vcpu || + !(hv_vcpu->cpuid_cache.features_eax & HV_ACCESS_TSC_INVARIANT)) + return false; + + /* + * If Hyper-V's invariant TSC control is exposed to the guest, KVM is + * responsible for suppressing the invariant TSC CPUID flag if the + * Hyper-V control is not enabled. + */ + return !(to_kvm_hv(vcpu->kvm)->hv_invtsc_control & HV_EXPOSE_INVARIANT_TSC); +} + void kvm_hv_process_stimers(struct kvm_vcpu *vcpu); void kvm_hv_setup_tsc_page(struct kvm *kvm, diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index e0a7a0e7a73c..cd57a517d04a 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -30,7 +30,7 @@ * Based on QEMU and Xen. */ -#define pr_fmt(fmt) "pit: " fmt +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <linux/slab.h> @@ -351,7 +351,7 @@ static void create_pit_timer(struct kvm_pit *pit, u32 val, int is_period) if (ps->period < min_period) { pr_info_ratelimited( - "kvm: requested %lld ns " + "requested %lld ns " "i8254 timer period limited to %lld ns\n", ps->period, min_period); ps->period = min_period; diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index e1bb6218bb96..4756bcb5724f 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -26,6 +26,8 @@ * Yaozu (Eddie) Dong <Eddie.dong@intel.com> * Port from Qemu. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/mm.h> #include <linux/slab.h> #include <linux/bitops.h> @@ -35,7 +37,7 @@ #include "trace.h" #define pr_pic_unimpl(fmt, ...) \ - pr_err_ratelimited("kvm: pic: " fmt, ## __VA_ARGS__) + pr_err_ratelimited("pic: " fmt, ## __VA_ARGS__) static void pic_irq_request(struct kvm *kvm, int level); diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 765943d7cfa5..042dee556125 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -26,6 +26,7 @@ * Yaozu (Eddie) Dong <eddie.dong@intel.com> * Based on Xen 3.1 code. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <linux/kvm.h> diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index a70952eca905..b2c397dd2bc6 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -7,6 +7,7 @@ * Authors: * Yaozu (Eddie) Dong <Eddie.dong@intel.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/export.h> #include <linux/kvm_host.h> diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 3742d9adacfc..16d076a1b91a 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -8,6 +8,7 @@ * * Copyright 2010 Red Hat, Inc. and/or its affiliates. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <linux/slab.h> @@ -56,7 +57,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, if (irq->dest_mode == APIC_DEST_PHYSICAL && irq->dest_id == 0xff && kvm_lowest_prio_delivery(irq)) { - printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n"); + pr_info("apic: phys broadcast and lowest prio\n"); irq->delivery_mode = APIC_DM_FIXED; } @@ -199,7 +200,7 @@ int kvm_request_irq_source_id(struct kvm *kvm) irq_source_id = find_first_zero_bit(bitmap, BITS_PER_LONG); if (irq_source_id >= BITS_PER_LONG) { - printk(KERN_WARNING "kvm: exhaust allocatable IRQ sources!\n"); + pr_warn("exhausted allocatable IRQ sources!\n"); irq_source_id = -EFAULT; goto unlock; } @@ -221,7 +222,7 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) mutex_lock(&kvm->irq_lock); if (irq_source_id < 0 || irq_source_id >= BITS_PER_LONG) { - printk(KERN_ERR "kvm: IRQ source ID out of range!\n"); + pr_err("IRQ source ID out of range!\n"); goto unlock; } clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap); diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index c09174f73a34..4c91f626c058 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -76,6 +76,18 @@ static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu, } /* + * kvm_register_test_and_mark_available() is a special snowflake that uses an + * arch bitop directly to avoid the explicit instrumentation that comes with + * the generic bitops. This allows code that cannot be instrumented (noinstr + * functions), e.g. the low level VM-Enter/VM-Exit paths, to cache registers. + */ +static __always_inline bool kvm_register_test_and_mark_available(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + return arch___test_and_set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); +} + +/* * The "raw" register helpers are only for cases where the full 64 bits of a * register are read/written irrespective of current vCPU mode. In other words, * odds are good you shouldn't be using the raw variants. diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index 2d9662be8333..ab65f3a47dfd 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -220,7 +220,8 @@ struct x86_emulate_ops { void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked); - unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt); + bool (*is_smm)(struct x86_emulate_ctxt *ctxt); + bool (*is_guest_mode)(struct x86_emulate_ctxt *ctxt); int (*leave_smm)(struct x86_emulate_ctxt *ctxt); void (*triple_fault)(struct x86_emulate_ctxt *ctxt); int (*set_xcr)(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr); @@ -275,10 +276,6 @@ enum x86emul_mode { X86EMUL_MODE_PROT64, /* 64-bit (long) mode. */ }; -/* These match some of the HF_* flags defined in kvm_host.h */ -#define X86EMUL_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */ -#define X86EMUL_SMM_MASK (1 << 6) - /* * fastop functions are declared as taking a never-defined fastop parameter, * so they can't be called from C directly. diff --git a/arch/x86/kvm/kvm_onhyperv.c b/arch/x86/kvm/kvm_onhyperv.c index ee4f696a0782..482d6639ef88 100644 --- a/arch/x86/kvm/kvm_onhyperv.c +++ b/arch/x86/kvm/kvm_onhyperv.c @@ -2,6 +2,7 @@ /* * KVM L1 hypervisor optimizations on Hyper-V. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <asm/mshyperv.h> diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 4efdb4a4d72c..e542cf285b51 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -15,6 +15,7 @@ * * Based on Xen 3.1 code, Copyright (c) 2004, Intel Corporation. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <linux/kvm.h> @@ -166,9 +167,19 @@ static bool kvm_use_posted_timer_interrupt(struct kvm_vcpu *vcpu) return kvm_can_post_timer_interrupt(vcpu) && vcpu->mode == IN_GUEST_MODE; } +static inline u32 kvm_apic_calc_x2apic_ldr(u32 id) +{ + return ((id >> 4) << 16) | (1 << (id & 0xf)); +} + static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map, u32 dest_id, struct kvm_lapic ***cluster, u16 *mask) { - switch (map->mode) { + switch (map->logical_mode) { + case KVM_APIC_MODE_SW_DISABLED: + /* Arbitrarily use the flat map so that @cluster isn't NULL. */ + *cluster = map->xapic_flat_map; + *mask = 0; + return true; case KVM_APIC_MODE_X2APIC: { u32 offset = (dest_id >> 16) * 16; u32 max_apic_id = map->max_apic_id; @@ -193,8 +204,10 @@ static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map, *cluster = map->xapic_cluster_map[(dest_id >> 4) & 0xf]; *mask = dest_id & 0xf; return true; + case KVM_APIC_MODE_MAP_DISABLED: + return false; default: - /* Not optimized. */ + WARN_ON_ONCE(1); return false; } } @@ -206,6 +219,134 @@ static void kvm_apic_map_free(struct rcu_head *rcu) kvfree(map); } +static int kvm_recalculate_phys_map(struct kvm_apic_map *new, + struct kvm_vcpu *vcpu, + bool *xapic_id_mismatch) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + u32 x2apic_id = kvm_x2apic_id(apic); + u32 xapic_id = kvm_xapic_id(apic); + u32 physical_id; + + /* + * Deliberately truncate the vCPU ID when detecting a mismatched APIC + * ID to avoid false positives if the vCPU ID, i.e. x2APIC ID, is a + * 32-bit value. Any unwanted aliasing due to truncation results will + * be detected below. + */ + if (!apic_x2apic_mode(apic) && xapic_id != (u8)vcpu->vcpu_id) + *xapic_id_mismatch = true; + + /* + * Apply KVM's hotplug hack if userspace has enable 32-bit APIC IDs. + * Allow sending events to vCPUs by their x2APIC ID even if the target + * vCPU is in legacy xAPIC mode, and silently ignore aliased xAPIC IDs + * (the x2APIC ID is truncated to 8 bits, causing IDs > 0xff to wrap + * and collide). + * + * Honor the architectural (and KVM's non-optimized) behavior if + * userspace has not enabled 32-bit x2APIC IDs. Each APIC is supposed + * to process messages independently. If multiple vCPUs have the same + * effective APIC ID, e.g. due to the x2APIC wrap or because the guest + * manually modified its xAPIC IDs, events targeting that ID are + * supposed to be recognized by all vCPUs with said ID. + */ + if (vcpu->kvm->arch.x2apic_format) { + /* See also kvm_apic_match_physical_addr(). */ + if ((apic_x2apic_mode(apic) || x2apic_id > 0xff) && + x2apic_id <= new->max_apic_id) + new->phys_map[x2apic_id] = apic; + + if (!apic_x2apic_mode(apic) && !new->phys_map[xapic_id]) + new->phys_map[xapic_id] = apic; + } else { + /* + * Disable the optimized map if the physical APIC ID is already + * mapped, i.e. is aliased to multiple vCPUs. The optimized + * map requires a strict 1:1 mapping between IDs and vCPUs. + */ + if (apic_x2apic_mode(apic)) + physical_id = x2apic_id; + else + physical_id = xapic_id; + + if (new->phys_map[physical_id]) + return -EINVAL; + + new->phys_map[physical_id] = apic; + } + + return 0; +} + +static void kvm_recalculate_logical_map(struct kvm_apic_map *new, + struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + enum kvm_apic_logical_mode logical_mode; + struct kvm_lapic **cluster; + u16 mask; + u32 ldr; + + if (new->logical_mode == KVM_APIC_MODE_MAP_DISABLED) + return; + + if (!kvm_apic_sw_enabled(apic)) + return; + + ldr = kvm_lapic_get_reg(apic, APIC_LDR); + if (!ldr) + return; + + if (apic_x2apic_mode(apic)) { + logical_mode = KVM_APIC_MODE_X2APIC; + } else { + ldr = GET_APIC_LOGICAL_ID(ldr); + if (kvm_lapic_get_reg(apic, APIC_DFR) == APIC_DFR_FLAT) + logical_mode = KVM_APIC_MODE_XAPIC_FLAT; + else + logical_mode = KVM_APIC_MODE_XAPIC_CLUSTER; + } + + /* + * To optimize logical mode delivery, all software-enabled APICs must + * be configured for the same mode. + */ + if (new->logical_mode == KVM_APIC_MODE_SW_DISABLED) { + new->logical_mode = logical_mode; + } else if (new->logical_mode != logical_mode) { + new->logical_mode = KVM_APIC_MODE_MAP_DISABLED; + return; + } + + /* + * In x2APIC mode, the LDR is read-only and derived directly from the + * x2APIC ID, thus is guaranteed to be addressable. KVM reuses + * kvm_apic_map.phys_map to optimize logical mode x2APIC interrupts by + * reversing the LDR calculation to get cluster of APICs, i.e. no + * additional work is required. + */ + if (apic_x2apic_mode(apic)) { + WARN_ON_ONCE(ldr != kvm_apic_calc_x2apic_ldr(kvm_x2apic_id(apic))); + return; + } + + if (WARN_ON_ONCE(!kvm_apic_map_get_logical_dest(new, ldr, + &cluster, &mask))) { + new->logical_mode = KVM_APIC_MODE_MAP_DISABLED; + return; + } + + if (!mask) + return; + + ldr = ffs(mask) - 1; + if (!is_power_of_2(mask) || cluster[ldr]) + new->logical_mode = KVM_APIC_MODE_MAP_DISABLED; + else + cluster[ldr] = apic; +} + /* * CLEAN -> DIRTY and UPDATE_IN_PROGRESS -> DIRTY changes happen without a lock. * @@ -224,6 +365,7 @@ void kvm_recalculate_apic_map(struct kvm *kvm) struct kvm_vcpu *vcpu; unsigned long i; u32 max_id = 255; /* enough space for any xAPIC ID */ + bool xapic_id_mismatch = false; /* Read kvm->arch.apic_map_dirty before kvm->arch.apic_map. */ if (atomic_read_acquire(&kvm->arch.apic_map_dirty) == CLEAN) @@ -256,54 +398,41 @@ void kvm_recalculate_apic_map(struct kvm *kvm) goto out; new->max_apic_id = max_id; + new->logical_mode = KVM_APIC_MODE_SW_DISABLED; kvm_for_each_vcpu(i, vcpu, kvm) { - struct kvm_lapic *apic = vcpu->arch.apic; - struct kvm_lapic **cluster; - u16 mask; - u32 ldr; - u8 xapic_id; - u32 x2apic_id; - if (!kvm_apic_present(vcpu)) continue; - xapic_id = kvm_xapic_id(apic); - x2apic_id = kvm_x2apic_id(apic); - - /* Hotplug hack: see kvm_apic_match_physical_addr(), ... */ - if ((apic_x2apic_mode(apic) || x2apic_id > 0xff) && - x2apic_id <= new->max_apic_id) - new->phys_map[x2apic_id] = apic; - /* - * ... xAPIC ID of VCPUs with APIC ID > 0xff will wrap-around, - * prevent them from masking VCPUs with APIC ID <= 0xff. - */ - if (!apic_x2apic_mode(apic) && !new->phys_map[xapic_id]) - new->phys_map[xapic_id] = apic; - - if (!kvm_apic_sw_enabled(apic)) - continue; - - ldr = kvm_lapic_get_reg(apic, APIC_LDR); - - if (apic_x2apic_mode(apic)) { - new->mode |= KVM_APIC_MODE_X2APIC; - } else if (ldr) { - ldr = GET_APIC_LOGICAL_ID(ldr); - if (kvm_lapic_get_reg(apic, APIC_DFR) == APIC_DFR_FLAT) - new->mode |= KVM_APIC_MODE_XAPIC_FLAT; - else - new->mode |= KVM_APIC_MODE_XAPIC_CLUSTER; + if (kvm_recalculate_phys_map(new, vcpu, &xapic_id_mismatch)) { + kvfree(new); + new = NULL; + goto out; } - if (!kvm_apic_map_get_logical_dest(new, ldr, &cluster, &mask)) - continue; - - if (mask) - cluster[ffs(mask) - 1] = apic; + kvm_recalculate_logical_map(new, vcpu); } out: + /* + * The optimized map is effectively KVM's internal version of APICv, + * and all unwanted aliasing that results in disabling the optimized + * map also applies to APICv. + */ + if (!new) + kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED); + else + kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED); + + if (!new || new->logical_mode == KVM_APIC_MODE_MAP_DISABLED) + kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED); + else + kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED); + + if (xapic_id_mismatch) + kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_APIC_ID_MODIFIED); + else + kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_APIC_ID_MODIFIED); + old = rcu_dereference_protected(kvm->arch.apic_map, lockdep_is_held(&kvm->arch.apic_map_lock)); rcu_assign_pointer(kvm->arch.apic_map, new); @@ -360,11 +489,6 @@ static inline void kvm_apic_set_dfr(struct kvm_lapic *apic, u32 val) atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } -static inline u32 kvm_apic_calc_x2apic_ldr(u32 id) -{ - return ((id >> 4) << 16) | (1 << (id & 0xf)); -} - static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id) { u32 ldr = kvm_apic_calc_x2apic_ldr(id); @@ -941,8 +1065,7 @@ static void kvm_apic_disabled_lapic_found(struct kvm *kvm) { if (!kvm->arch.disabled_lapic_found) { kvm->arch.disabled_lapic_found = true; - printk(KERN_INFO - "Disabled LAPIC found during irq injection\n"); + pr_info("Disabled LAPIC found during irq injection\n"); } } @@ -951,7 +1074,7 @@ static bool kvm_apic_is_broadcast_dest(struct kvm *kvm, struct kvm_lapic **src, { if (kvm->arch.x2apic_broadcast_quirk_disabled) { if ((irq->dest_id == APIC_BROADCAST && - map->mode != KVM_APIC_MODE_X2APIC)) + map->logical_mode != KVM_APIC_MODE_X2APIC)) return true; if (irq->dest_id == X2APIC_BROADCAST) return true; @@ -1364,7 +1487,6 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic) { ktime_t remaining, now; s64 ns; - u32 tmcct; ASSERT(apic != NULL); @@ -1379,10 +1501,7 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic) remaining = 0; ns = mod_64(ktime_to_ns(remaining), apic->lapic_timer.period); - tmcct = div64_u64(ns, - (APIC_BUS_CYCLE_NS * apic->divide_count)); - - return tmcct; + return div64_u64(ns, (APIC_BUS_CYCLE_NS * apic->divide_count)); } static void __report_tpr_access(struct kvm_lapic *apic, bool write) @@ -1442,19 +1561,15 @@ static inline struct kvm_lapic *to_lapic(struct kvm_io_device *dev) #define APIC_REGS_MASK(first, count) \ (APIC_REG_MASK(first) * ((1ull << (count)) - 1)) -static int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, - void *data) +u64 kvm_lapic_readable_reg_mask(struct kvm_lapic *apic) { - unsigned char alignment = offset & 0xf; - u32 result; - /* this bitmask has a bit cleared for each reserved register */ + /* Leave bits '0' for reserved and write-only registers. */ u64 valid_reg_mask = APIC_REG_MASK(APIC_ID) | APIC_REG_MASK(APIC_LVR) | APIC_REG_MASK(APIC_TASKPRI) | APIC_REG_MASK(APIC_PROCPRI) | APIC_REG_MASK(APIC_LDR) | - APIC_REG_MASK(APIC_DFR) | APIC_REG_MASK(APIC_SPIV) | APIC_REGS_MASK(APIC_ISR, APIC_ISR_NR) | APIC_REGS_MASK(APIC_TMR, APIC_ISR_NR) | @@ -1474,21 +1589,33 @@ static int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, if (kvm_lapic_lvt_supported(apic, LVT_CMCI)) valid_reg_mask |= APIC_REG_MASK(APIC_LVTCMCI); - /* - * ARBPRI and ICR2 are not valid in x2APIC mode. WARN if KVM reads ICR - * in x2APIC mode as it's an 8-byte register in x2APIC and needs to be - * manually handled by the caller. - */ + /* ARBPRI, DFR, and ICR2 are not valid in x2APIC mode. */ if (!apic_x2apic_mode(apic)) valid_reg_mask |= APIC_REG_MASK(APIC_ARBPRI) | + APIC_REG_MASK(APIC_DFR) | APIC_REG_MASK(APIC_ICR2); - else - WARN_ON_ONCE(offset == APIC_ICR); + + return valid_reg_mask; +} +EXPORT_SYMBOL_GPL(kvm_lapic_readable_reg_mask); + +static int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, + void *data) +{ + unsigned char alignment = offset & 0xf; + u32 result; + + /* + * WARN if KVM reads ICR in x2APIC mode, as it's an 8-byte register in + * x2APIC and needs to be manually handled by the caller. + */ + WARN_ON_ONCE(apic_x2apic_mode(apic) && offset == APIC_ICR); if (alignment + len > 4) return 1; - if (offset > 0x3f0 || !(valid_reg_mask & APIC_REG_MASK(offset))) + if (offset > 0x3f0 || + !(kvm_lapic_readable_reg_mask(apic) & APIC_REG_MASK(offset))) return 1; result = __apic_read(apic, offset & ~0xf); @@ -1560,7 +1687,7 @@ static void limit_periodic_timer_frequency(struct kvm_lapic *apic) if (apic->lapic_timer.period < min_period) { pr_info_ratelimited( - "kvm: vcpu %i: requested %lld ns " + "vcpu %i: requested %lld ns " "lapic timer period limited to %lld ns\n", apic->vcpu->vcpu_id, apic->lapic_timer.period, min_period); @@ -1841,11 +1968,15 @@ static bool set_target_expiration(struct kvm_lapic *apic, u32 count_reg) if (unlikely(count_reg != APIC_TMICT)) { deadline = tmict_to_ns(apic, kvm_lapic_get_reg(apic, count_reg)); - if (unlikely(deadline <= 0)) - deadline = apic->lapic_timer.period; + if (unlikely(deadline <= 0)) { + if (apic_lvtt_period(apic)) + deadline = apic->lapic_timer.period; + else + deadline = 0; + } else if (unlikely(deadline > apic->lapic_timer.period)) { pr_info_ratelimited( - "kvm: vcpu %i: requested lapic timer restore with " + "vcpu %i: requested lapic timer restore with " "starting count register %#x=%u (%lld ns) > initial count (%lld ns). " "Using initial count to start timer.\n", apic->vcpu->vcpu_id, @@ -2068,19 +2199,6 @@ static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val) } } -static void kvm_lapic_xapic_id_updated(struct kvm_lapic *apic) -{ - struct kvm *kvm = apic->vcpu->kvm; - - if (KVM_BUG_ON(apic_x2apic_mode(apic), kvm)) - return; - - if (kvm_xapic_id(apic) == apic->vcpu->vcpu_id) - return; - - kvm_set_apicv_inhibit(apic->vcpu->kvm, APICV_INHIBIT_REASON_APIC_ID_MODIFIED); -} - static int get_lvt_index(u32 reg) { if (reg == APIC_LVTCMCI) @@ -2101,7 +2219,6 @@ static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_ID: /* Local APIC ID */ if (!apic_x2apic_mode(apic)) { kvm_apic_set_xapic_id(apic, val >> 24); - kvm_lapic_xapic_id_updated(apic); } else { ret = 1; } @@ -2219,10 +2336,14 @@ static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) break; case APIC_SELF_IPI: - if (apic_x2apic_mode(apic)) - kvm_apic_send_ipi(apic, APIC_DEST_SELF | (val & APIC_VECTOR_MASK), 0); - else + /* + * Self-IPI exists only when x2APIC is enabled. Bits 7:0 hold + * the vector, everything else is reserved. + */ + if (!apic_x2apic_mode(apic) || (val & ~APIC_VECTOR_MASK)) ret = 1; + else + kvm_apic_send_ipi(apic, APIC_DEST_SELF | val, 0); break; default: ret = 1; @@ -2284,23 +2405,18 @@ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset) struct kvm_lapic *apic = vcpu->arch.apic; u64 val; - if (apic_x2apic_mode(apic)) { - if (KVM_BUG_ON(kvm_lapic_msr_read(apic, offset, &val), vcpu->kvm)) - return; - } else { - val = kvm_lapic_get_reg(apic, offset); - } - /* * ICR is a single 64-bit register when x2APIC is enabled. For legacy * xAPIC, ICR writes need to go down the common (slightly slower) path * to get the upper half from ICR2. */ if (apic_x2apic_mode(apic) && offset == APIC_ICR) { + val = kvm_lapic_get_reg64(apic, APIC_ICR); kvm_apic_send_ipi(apic, (u32)val, (u32)(val >> 32)); trace_kvm_apic_write(APIC_ICR, val); } else { /* TODO: optimize to just emulate side effect w/o one more write */ + val = kvm_lapic_get_reg(apic, offset); kvm_lapic_reg_write(apic, offset, (u32)val); } } @@ -2394,11 +2510,15 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) } } - if (((old_value ^ value) & X2APIC_ENABLE) && (value & X2APIC_ENABLE)) - kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id); + if ((old_value ^ value) & X2APIC_ENABLE) { + if (value & X2APIC_ENABLE) + kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id); + else if (value & MSR_IA32_APICBASE_ENABLE) + kvm_apic_set_xapic_id(apic, vcpu->vcpu_id); + } if ((old_value ^ value) & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE)) { - kvm_vcpu_update_apicv(vcpu); + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); static_call_cond(kvm_x86_set_virtual_apic_mode)(vcpu); } @@ -2429,6 +2549,78 @@ void kvm_apic_update_apicv(struct kvm_vcpu *vcpu) */ apic->isr_count = count_vectors(apic->regs + APIC_ISR); } + apic->highest_isr_cache = -1; +} + +int kvm_alloc_apic_access_page(struct kvm *kvm) +{ + struct page *page; + void __user *hva; + int ret = 0; + + mutex_lock(&kvm->slots_lock); + if (kvm->arch.apic_access_memslot_enabled || + kvm->arch.apic_access_memslot_inhibited) + goto out; + + hva = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, + APIC_DEFAULT_PHYS_BASE, PAGE_SIZE); + if (IS_ERR(hva)) { + ret = PTR_ERR(hva); + goto out; + } + + page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); + if (is_error_page(page)) { + ret = -EFAULT; + goto out; + } + + /* + * Do not pin the page in memory, so that memory hot-unplug + * is able to migrate it. + */ + put_page(page); + kvm->arch.apic_access_memslot_enabled = true; +out: + mutex_unlock(&kvm->slots_lock); + return ret; +} +EXPORT_SYMBOL_GPL(kvm_alloc_apic_access_page); + +void kvm_inhibit_apic_access_page(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + + if (!kvm->arch.apic_access_memslot_enabled) + return; + + kvm_vcpu_srcu_read_unlock(vcpu); + + mutex_lock(&kvm->slots_lock); + + if (kvm->arch.apic_access_memslot_enabled) { + __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, 0, 0); + /* + * Clear "enabled" after the memslot is deleted so that a + * different vCPU doesn't get a false negative when checking + * the flag out of slots_lock. No additional memory barrier is + * needed as modifying memslots requires waiting other vCPUs to + * drop SRCU (see above), and false positives are ok as the + * flag is rechecked after acquiring slots_lock. + */ + kvm->arch.apic_access_memslot_enabled = false; + + /* + * Mark the memslot as inhibited to prevent reallocating the + * memslot during vCPU creation, e.g. if a vCPU is hotplugged. + */ + kvm->arch.apic_access_memslot_inhibited = true; + } + + mutex_unlock(&kvm->slots_lock); + + kvm_vcpu_srcu_read_lock(vcpu); } void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) @@ -2484,7 +2676,6 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_lapic_set_reg(apic, APIC_TMR + 0x10 * i, 0); } kvm_apic_update_apicv(vcpu); - apic->highest_isr_cache = -1; update_divide_count(apic); atomic_set(&apic->lapic_timer.pending, 0); @@ -2756,9 +2947,6 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) } memcpy(vcpu->arch.apic->regs, s->regs, sizeof(*s)); - if (!apic_x2apic_mode(apic)) - kvm_lapic_xapic_id_updated(apic); - atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); kvm_recalculate_apic_map(vcpu->kvm); kvm_apic_set_version(vcpu); @@ -2772,7 +2960,6 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) __start_apic_timer(apic, APIC_TMCCT); kvm_lapic_set_reg(apic, APIC_TMCCT, 0); kvm_apic_update_apicv(vcpu); - apic->highest_isr_cache = -1; if (apic->apicv_active) { static_call_cond(kvm_x86_apicv_post_state_restore)(vcpu); static_call_cond(kvm_x86_hwapic_irr_update)(vcpu, apic_find_highest_irr(apic)); @@ -2943,13 +3130,17 @@ static int kvm_lapic_msr_read(struct kvm_lapic *apic, u32 reg, u64 *data) static int kvm_lapic_msr_write(struct kvm_lapic *apic, u32 reg, u64 data) { /* - * ICR is a 64-bit register in x2APIC mode (and Hyper'v PV vAPIC) and + * ICR is a 64-bit register in x2APIC mode (and Hyper-V PV vAPIC) and * can be written as such, all other registers remain accessible only * through 32-bit reads/writes. */ if (reg == APIC_ICR) return kvm_x2apic_icr_write(apic, data); + /* Bits 63:32 are reserved in all other registers. */ + if (data >> 32) + return 1; + return kvm_lapic_reg_write(apic, reg, (u32)data); } @@ -2972,9 +3163,6 @@ int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data) if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(apic)) return 1; - if (reg == APIC_DFR) - return 1; - return kvm_lapic_msr_read(apic, reg, data); } diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 58c3242fcc7a..0a0ea4b5dd8c 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -112,6 +112,8 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, struct dest_map *dest_map); int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type); void kvm_apic_update_apicv(struct kvm_vcpu *vcpu); +int kvm_alloc_apic_access_page(struct kvm *kvm); +void kvm_inhibit_apic_access_page(struct kvm_vcpu *vcpu); bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map); @@ -144,6 +146,8 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data); int kvm_lapic_set_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len); void kvm_lapic_exit(void); +u64 kvm_lapic_readable_reg_mask(struct kvm_lapic *apic); + #define VEC_POS(v) ((v) & (32 - 1)) #define REG_POS(v) (((v) >> 5) << 4) diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 6bdaacb6faa0..168c46fd8dd1 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -230,14 +230,14 @@ static inline bool kvm_shadow_root_allocated(struct kvm *kvm) } #ifdef CONFIG_X86_64 -static inline bool is_tdp_mmu_enabled(struct kvm *kvm) { return kvm->arch.tdp_mmu_enabled; } +extern bool tdp_mmu_enabled; #else -static inline bool is_tdp_mmu_enabled(struct kvm *kvm) { return false; } +#define tdp_mmu_enabled false #endif static inline bool kvm_memslots_have_rmaps(struct kvm *kvm) { - return !is_tdp_mmu_enabled(kvm) || kvm_shadow_root_allocated(kvm); + return !tdp_mmu_enabled || kvm_shadow_root_allocated(kvm); } static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 835426254e76..c8ebe542c565 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -14,6 +14,7 @@ * Yaniv Kamay <yaniv@qumranet.com> * Avi Kivity <avi@qumranet.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "irq.h" #include "ioapic.h" @@ -43,6 +44,7 @@ #include <linux/uaccess.h> #include <linux/hash.h> #include <linux/kern_levels.h> +#include <linux/kstrtox.h> #include <linux/kthread.h> #include <asm/page.h> @@ -99,6 +101,13 @@ module_param_named(flush_on_reuse, force_flush_and_sync_on_reuse, bool, 0644); */ bool tdp_enabled = false; +static bool __ro_after_init tdp_mmu_allowed; + +#ifdef CONFIG_X86_64 +bool __read_mostly tdp_mmu_enabled = true; +module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0444); +#endif + static int max_huge_page_level __read_mostly; static int tdp_root_level __read_mostly; static int max_tdp_level __read_mostly; @@ -261,6 +270,17 @@ void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, kvm_flush_remote_tlbs_with_range(kvm, &range); } +static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index); + +/* Flush the range of guest memory mapped by the given SPTE. */ +static void kvm_flush_remote_tlbs_sptep(struct kvm *kvm, u64 *sptep) +{ + struct kvm_mmu_page *sp = sptep_to_sp(sptep); + gfn_t gfn = kvm_mmu_page_get_gfn(sp, spte_index(sptep)); + + kvm_flush_remote_tlbs_gfn(kvm, gfn, sp->role.level); +} + static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, unsigned int access) { @@ -609,9 +629,14 @@ static bool mmu_spte_age(u64 *sptep) return true; } +static inline bool is_tdp_mmu_active(struct kvm_vcpu *vcpu) +{ + return tdp_mmu_enabled && vcpu->arch.mmu->root_role.direct; +} + static void walk_shadow_page_lockless_begin(struct kvm_vcpu *vcpu) { - if (is_tdp_mmu(vcpu->arch.mmu)) { + if (is_tdp_mmu_active(vcpu)) { kvm_tdp_mmu_walk_lockless_begin(); } else { /* @@ -630,7 +655,7 @@ static void walk_shadow_page_lockless_begin(struct kvm_vcpu *vcpu) static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu) { - if (is_tdp_mmu(vcpu->arch.mmu)) { + if (is_tdp_mmu_active(vcpu)) { kvm_tdp_mmu_walk_lockless_end(); } else { /* @@ -800,7 +825,7 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_gfn_disallow_lpage(slot, gfn); if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K)) - kvm_flush_remote_tlbs_with_address(kvm, gfn, 1); + kvm_flush_remote_tlbs_gfn(kvm, gfn, PG_LEVEL_4K); } void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp) @@ -1174,8 +1199,7 @@ static void drop_large_spte(struct kvm *kvm, u64 *sptep, bool flush) drop_spte(kvm, sptep); if (flush) - kvm_flush_remote_tlbs_with_address(kvm, sp->gfn, - KVM_PAGES_PER_HPAGE(sp->role.level)); + kvm_flush_remote_tlbs_sptep(kvm, sptep); } /* @@ -1279,7 +1303,7 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, { struct kvm_rmap_head *rmap_head; - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot, slot->base_gfn + gfn_offset, mask, true); @@ -1312,7 +1336,7 @@ static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, { struct kvm_rmap_head *rmap_head; - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot, slot->base_gfn + gfn_offset, mask, false); @@ -1395,7 +1419,7 @@ bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, } } - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) write_protected |= kvm_tdp_mmu_write_protect_gfn(kvm, slot, gfn, min_level); @@ -1456,7 +1480,7 @@ restart: } if (need_flush && kvm_available_flush_tlb_with_range()) { - kvm_flush_remote_tlbs_with_address(kvm, gfn, 1); + kvm_flush_remote_tlbs_gfn(kvm, gfn, level); return false; } @@ -1558,7 +1582,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) if (kvm_memslots_have_rmaps(kvm)) flush = kvm_handle_gfn_range(kvm, range, kvm_zap_rmap); - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush); return flush; @@ -1571,7 +1595,7 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) if (kvm_memslots_have_rmaps(kvm)) flush = kvm_handle_gfn_range(kvm, range, kvm_set_pte_rmap); - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) flush |= kvm_tdp_mmu_set_spte_gfn(kvm, range); return flush; @@ -1626,8 +1650,7 @@ static void __rmap_add(struct kvm *kvm, kvm->stat.max_mmu_rmap_size = rmap_count; if (rmap_count > RMAP_RECYCLE_THRESHOLD) { kvm_zap_all_rmap_sptes(kvm, rmap_head); - kvm_flush_remote_tlbs_with_address( - kvm, sp->gfn, KVM_PAGES_PER_HPAGE(sp->role.level)); + kvm_flush_remote_tlbs_gfn(kvm, gfn, sp->role.level); } } @@ -1646,7 +1669,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) if (kvm_memslots_have_rmaps(kvm)) young = kvm_handle_gfn_range(kvm, range, kvm_age_rmap); - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) young |= kvm_tdp_mmu_age_gfn_range(kvm, range); return young; @@ -1659,7 +1682,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) if (kvm_memslots_have_rmaps(kvm)) young = kvm_handle_gfn_range(kvm, range, kvm_test_age_rmap); - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) young |= kvm_tdp_mmu_test_age_gfn(kvm, range); return young; @@ -1921,7 +1944,7 @@ static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp) return true; /* TDP MMU pages do not use the MMU generation. */ - return !sp->tdp_mmu_page && + return !is_tdp_mmu_page(sp) && unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen); } @@ -2355,7 +2378,16 @@ static void __link_shadow_page(struct kvm *kvm, mmu_page_add_parent_pte(cache, sp, sptep); - if (sp->unsync_children || sp->unsync) + /* + * The non-direct sub-pagetable must be updated before linking. For + * L1 sp, the pagetable is updated via kvm_sync_page() in + * kvm_mmu_find_shadow_page() without write-protecting the gfn, + * so sp->unsync can be true or false. For higher level non-direct + * sp, the pagetable is updated/synced via mmu_sync_children() in + * FNAME(fetch)(), so sp->unsync_children can only be false. + * WARN_ON_ONCE() if anything happens unexpectedly. + */ + if (WARN_ON_ONCE(sp->unsync_children) || sp->unsync) mark_unsync(sptep); } @@ -2383,7 +2415,7 @@ static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, return; drop_parent_pte(child, sptep); - kvm_flush_remote_tlbs_with_address(vcpu->kvm, child->gfn, 1); + kvm_flush_remote_tlbs_sptep(vcpu->kvm, sptep); } } @@ -2867,8 +2899,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, } if (flush) - kvm_flush_remote_tlbs_with_address(vcpu->kvm, gfn, - KVM_PAGES_PER_HPAGE(level)); + kvm_flush_remote_tlbs_gfn(vcpu->kvm, gfn, level); pgprintk("%s: setting spte %llx\n", __func__, *sptep); @@ -3116,11 +3147,11 @@ void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_ !is_large_pte(spte) && spte_to_child_sp(spte)->nx_huge_page_disallowed) { /* - * A small SPTE exists for this pfn, but FNAME(fetch) - * and __direct_map would like to create a large PTE - * instead: just force them to go down another level, - * patching back for them into pfn the next 9 bits of - * the address. + * A small SPTE exists for this pfn, but FNAME(fetch), + * direct_map(), or kvm_tdp_mmu_map() would like to create a + * large PTE instead: just force them to go down another level, + * patching back for them into pfn the next 9 bits of the + * address. */ u64 page_mask = KVM_PAGES_PER_HPAGE(cur_level) - KVM_PAGES_PER_HPAGE(cur_level - 1); @@ -3129,7 +3160,7 @@ void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_ } } -static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) +static int direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_shadow_walk_iterator it; struct kvm_mmu_page *sp; @@ -3147,7 +3178,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) if (fault->nx_huge_page_workaround_enabled) disallowed_hugepage_adjust(fault, *it.sptep, it.level); - base_gfn = fault->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + base_gfn = gfn_round_for_level(fault->gfn, it.level); if (it.level == fault->goal_level) break; @@ -3173,14 +3204,16 @@ static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) return ret; } -static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *tsk) +static void kvm_send_hwpoison_signal(struct kvm_memory_slot *slot, gfn_t gfn) { - send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, PAGE_SHIFT, tsk); + unsigned long hva = gfn_to_hva_memslot(slot, gfn); + + send_sig_mceerr(BUS_MCEERR_AR, (void __user *)hva, PAGE_SHIFT, current); } -static int kvm_handle_error_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) +static int kvm_handle_error_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { - if (is_sigpending_pfn(pfn)) { + if (is_sigpending_pfn(fault->pfn)) { kvm_handle_signal_exit(vcpu); return -EINTR; } @@ -3190,43 +3223,43 @@ static int kvm_handle_error_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) * into the spte otherwise read access on readonly gfn also can * caused mmio page fault and treat it as mmio access. */ - if (pfn == KVM_PFN_ERR_RO_FAULT) + if (fault->pfn == KVM_PFN_ERR_RO_FAULT) return RET_PF_EMULATE; - if (pfn == KVM_PFN_ERR_HWPOISON) { - kvm_send_hwpoison_signal(kvm_vcpu_gfn_to_hva(vcpu, gfn), current); + if (fault->pfn == KVM_PFN_ERR_HWPOISON) { + kvm_send_hwpoison_signal(fault->slot, fault->gfn); return RET_PF_RETRY; } return -EFAULT; } -static int handle_abnormal_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, - unsigned int access) +static int kvm_handle_noslot_fault(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault, + unsigned int access) { - /* The pfn is invalid, report the error! */ - if (unlikely(is_error_pfn(fault->pfn))) - return kvm_handle_error_pfn(vcpu, fault->gfn, fault->pfn); + gva_t gva = fault->is_tdp ? 0 : fault->addr; - if (unlikely(!fault->slot)) { - gva_t gva = fault->is_tdp ? 0 : fault->addr; + vcpu_cache_mmio_info(vcpu, gva, fault->gfn, + access & shadow_mmio_access_mask); - vcpu_cache_mmio_info(vcpu, gva, fault->gfn, - access & shadow_mmio_access_mask); - /* - * If MMIO caching is disabled, emulate immediately without - * touching the shadow page tables as attempting to install an - * MMIO SPTE will just be an expensive nop. Do not cache MMIO - * whose gfn is greater than host.MAXPHYADDR, any guest that - * generates such gfns is running nested and is being tricked - * by L0 userspace (you can observe gfn > L1.MAXPHYADDR if - * and only if L1's MAXPHYADDR is inaccurate with respect to - * the hardware's). - */ - if (unlikely(!enable_mmio_caching) || - unlikely(fault->gfn > kvm_mmu_max_gfn())) - return RET_PF_EMULATE; - } + /* + * If MMIO caching is disabled, emulate immediately without + * touching the shadow page tables as attempting to install an + * MMIO SPTE will just be an expensive nop. + */ + if (unlikely(!enable_mmio_caching)) + return RET_PF_EMULATE; + + /* + * Do not create an MMIO SPTE for a gfn greater than host.MAXPHYADDR, + * any guest that generates such gfns is running nested and is being + * tricked by L0 userspace (you can observe gfn > L1.MAXPHYADDR if and + * only if L1's MAXPHYADDR is inaccurate with respect to the + * hardware's). + */ + if (unlikely(fault->gfn > kvm_mmu_max_gfn())) + return RET_PF_EMULATE; return RET_PF_CONTINUE; } @@ -3350,7 +3383,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) do { u64 new_spte; - if (is_tdp_mmu(vcpu->arch.mmu)) + if (tdp_mmu_enabled) sptep = kvm_tdp_mmu_fast_pf_get_last_sptep(vcpu, fault->addr, &spte); else sptep = fast_pf_get_last_sptep(vcpu, fault->addr, &spte); @@ -3433,8 +3466,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) } if (++retry_count > 4) { - printk_once(KERN_WARNING - "kvm: Fast #PF retrying more than 4 times.\n"); + pr_warn_once("Fast #PF retrying more than 4 times.\n"); break; } @@ -3596,7 +3628,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) if (r < 0) goto out_unlock; - if (is_tdp_mmu_enabled(vcpu->kvm)) { + if (tdp_mmu_enabled) { root = kvm_tdp_mmu_get_vcpu_root_hpa(vcpu); mmu->root.hpa = root; } else if (shadow_root_level >= PT64_ROOT_4LEVEL) { @@ -4026,7 +4058,7 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) walk_shadow_page_lockless_begin(vcpu); - if (is_tdp_mmu(vcpu->arch.mmu)) + if (is_tdp_mmu_active(vcpu)) leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root); else leaf = get_walk(vcpu, addr, sptes, &root); @@ -4174,7 +4206,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true); } -static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) +static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_memory_slot *slot = fault->slot; bool async; @@ -4235,12 +4267,33 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) return RET_PF_CONTINUE; } +static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, + unsigned int access) +{ + int ret; + + fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq; + smp_rmb(); + + ret = __kvm_faultin_pfn(vcpu, fault); + if (ret != RET_PF_CONTINUE) + return ret; + + if (unlikely(is_error_pfn(fault->pfn))) + return kvm_handle_error_pfn(vcpu, fault); + + if (unlikely(!fault->slot)) + return kvm_handle_noslot_fault(vcpu, fault, access); + + return RET_PF_CONTINUE; +} + /* * Returns true if the page fault is stale and needs to be retried, i.e. if the * root was invalidated by a memslot update or a relevant mmu_notifier fired. */ static bool is_page_fault_stale(struct kvm_vcpu *vcpu, - struct kvm_page_fault *fault, int mmu_seq) + struct kvm_page_fault *fault) { struct kvm_mmu_page *sp = to_shadow_page(vcpu->arch.mmu->root.hpa); @@ -4260,19 +4313,13 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu, return true; return fault->slot && - mmu_invalidate_retry_hva(vcpu->kvm, mmu_seq, fault->hva); + mmu_invalidate_retry_hva(vcpu->kvm, fault->mmu_seq, fault->hva); } static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { - bool is_tdp_mmu_fault = is_tdp_mmu(vcpu->arch.mmu); - - unsigned long mmu_seq; int r; - fault->gfn = fault->addr >> PAGE_SHIFT; - fault->slot = kvm_vcpu_gfn_to_memslot(vcpu, fault->gfn); - if (page_fault_handle_page_track(vcpu, fault)) return RET_PF_EMULATE; @@ -4284,41 +4331,24 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault if (r) return r; - mmu_seq = vcpu->kvm->mmu_invalidate_seq; - smp_rmb(); - - r = kvm_faultin_pfn(vcpu, fault); - if (r != RET_PF_CONTINUE) - return r; - - r = handle_abnormal_pfn(vcpu, fault, ACC_ALL); + r = kvm_faultin_pfn(vcpu, fault, ACC_ALL); if (r != RET_PF_CONTINUE) return r; r = RET_PF_RETRY; + write_lock(&vcpu->kvm->mmu_lock); - if (is_tdp_mmu_fault) - read_lock(&vcpu->kvm->mmu_lock); - else - write_lock(&vcpu->kvm->mmu_lock); + if (is_page_fault_stale(vcpu, fault)) + goto out_unlock; - if (is_page_fault_stale(vcpu, fault, mmu_seq)) + r = make_mmu_pages_available(vcpu); + if (r) goto out_unlock; - if (is_tdp_mmu_fault) { - r = kvm_tdp_mmu_map(vcpu, fault); - } else { - r = make_mmu_pages_available(vcpu); - if (r) - goto out_unlock; - r = __direct_map(vcpu, fault); - } + r = direct_map(vcpu, fault); out_unlock: - if (is_tdp_mmu_fault) - read_unlock(&vcpu->kvm->mmu_lock); - else - write_unlock(&vcpu->kvm->mmu_lock); + write_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(fault->pfn); return r; } @@ -4366,6 +4396,42 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, } EXPORT_SYMBOL_GPL(kvm_handle_page_fault); +#ifdef CONFIG_X86_64 +static int kvm_tdp_mmu_page_fault(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) +{ + int r; + + if (page_fault_handle_page_track(vcpu, fault)) + return RET_PF_EMULATE; + + r = fast_page_fault(vcpu, fault); + if (r != RET_PF_INVALID) + return r; + + r = mmu_topup_memory_caches(vcpu, false); + if (r) + return r; + + r = kvm_faultin_pfn(vcpu, fault, ACC_ALL); + if (r != RET_PF_CONTINUE) + return r; + + r = RET_PF_RETRY; + read_lock(&vcpu->kvm->mmu_lock); + + if (is_page_fault_stale(vcpu, fault)) + goto out_unlock; + + r = kvm_tdp_mmu_map(vcpu, fault); + +out_unlock: + read_unlock(&vcpu->kvm->mmu_lock); + kvm_release_pfn_clean(fault->pfn); + return r; +} +#endif + int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { /* @@ -4383,13 +4449,19 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) if (shadow_memtype_mask && kvm_arch_has_noncoherent_dma(vcpu->kvm)) { for ( ; fault->max_level > PG_LEVEL_4K; --fault->max_level) { int page_num = KVM_PAGES_PER_HPAGE(fault->max_level); - gfn_t base = (fault->addr >> PAGE_SHIFT) & ~(page_num - 1); + gfn_t base = gfn_round_for_level(fault->gfn, + fault->max_level); if (kvm_mtrr_check_gfn_range_consistency(vcpu, base, page_num)) break; } } +#ifdef CONFIG_X86_64 + if (tdp_mmu_enabled) + return kvm_tdp_mmu_page_fault(vcpu, fault); +#endif + return direct_page_fault(vcpu, fault); } @@ -4494,10 +4566,12 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd) struct kvm_mmu *mmu = vcpu->arch.mmu; union kvm_mmu_page_role new_role = mmu->root_role; - if (!fast_pgd_switch(vcpu->kvm, mmu, new_pgd, new_role)) { - /* kvm_mmu_ensure_valid_pgd will set up a new root. */ + /* + * Return immediately if no usable root was found, kvm_mmu_reload() + * will establish a valid root prior to the next VM-Enter. + */ + if (!fast_pgd_switch(vcpu->kvm, mmu, new_pgd, new_role)) return; - } /* * It's possible that the cached previous root page is obsolete because @@ -5719,6 +5793,9 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, tdp_root_level = tdp_forced_root_level; max_tdp_level = tdp_max_root_level; +#ifdef CONFIG_X86_64 + tdp_mmu_enabled = tdp_mmu_allowed && tdp_enabled; +#endif /* * max_huge_page_level reflects KVM's MMU capabilities irrespective * of kernel support, e.g. KVM may be capable of using 1GB pages when @@ -5966,7 +6043,7 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm) * write and in the same critical section as making the reload request, * e.g. before kvm_zap_obsolete_pages() could drop mmu_lock and yield. */ - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) kvm_tdp_mmu_invalidate_all_roots(kvm); /* @@ -5991,7 +6068,7 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm) * Deferring the zap until the final reference to the root is put would * lead to use-after-free. */ - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) kvm_tdp_mmu_zap_invalidated_roots(kvm); } @@ -6017,9 +6094,11 @@ int kvm_mmu_init_vm(struct kvm *kvm) INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages); spin_lock_init(&kvm->arch.mmu_unsync_pages_lock); - r = kvm_mmu_init_tdp_mmu(kvm); - if (r < 0) - return r; + if (tdp_mmu_enabled) { + r = kvm_mmu_init_tdp_mmu(kvm); + if (r < 0) + return r; + } node->track_write = kvm_mmu_pte_write; node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot; @@ -6049,7 +6128,8 @@ void kvm_mmu_uninit_vm(struct kvm *kvm) kvm_page_track_unregister_notifier(kvm, node); - kvm_mmu_uninit_tdp_mmu(kvm); + if (tdp_mmu_enabled) + kvm_mmu_uninit_tdp_mmu(kvm); mmu_free_vm_memory_caches(kvm); } @@ -6103,7 +6183,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end); - if (is_tdp_mmu_enabled(kvm)) { + if (tdp_mmu_enabled) { for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) flush = kvm_tdp_mmu_zap_leafs(kvm, i, gfn_start, gfn_end, true, flush); @@ -6136,7 +6216,7 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, write_unlock(&kvm->mmu_lock); } - if (is_tdp_mmu_enabled(kvm)) { + if (tdp_mmu_enabled) { read_lock(&kvm->mmu_lock); kvm_tdp_mmu_wrprot_slot(kvm, memslot, start_level); read_unlock(&kvm->mmu_lock); @@ -6379,7 +6459,7 @@ void kvm_mmu_try_split_huge_pages(struct kvm *kvm, u64 start, u64 end, int target_level) { - if (!is_tdp_mmu_enabled(kvm)) + if (!tdp_mmu_enabled) return; if (kvm_memslots_have_rmaps(kvm)) @@ -6400,7 +6480,7 @@ void kvm_mmu_slot_try_split_huge_pages(struct kvm *kvm, u64 start = memslot->base_gfn; u64 end = start + memslot->npages; - if (!is_tdp_mmu_enabled(kvm)) + if (!tdp_mmu_enabled) return; if (kvm_memslots_have_rmaps(kvm)) { @@ -6450,8 +6530,7 @@ restart: kvm_zap_one_rmap_spte(kvm, rmap_head, sptep); if (kvm_available_flush_tlb_with_range()) - kvm_flush_remote_tlbs_with_address(kvm, sp->gfn, - KVM_PAGES_PER_HPAGE(sp->role.level)); + kvm_flush_remote_tlbs_sptep(kvm, sptep); else need_tlb_flush = 1; @@ -6483,7 +6562,7 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, write_unlock(&kvm->mmu_lock); } - if (is_tdp_mmu_enabled(kvm)) { + if (tdp_mmu_enabled) { read_lock(&kvm->mmu_lock); kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot); read_unlock(&kvm->mmu_lock); @@ -6518,7 +6597,7 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, write_unlock(&kvm->mmu_lock); } - if (is_tdp_mmu_enabled(kvm)) { + if (tdp_mmu_enabled) { read_lock(&kvm->mmu_lock); kvm_tdp_mmu_clear_dirty_slot(kvm, memslot); read_unlock(&kvm->mmu_lock); @@ -6553,7 +6632,7 @@ restart: kvm_mmu_commit_zap_page(kvm, &invalid_list); - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) kvm_tdp_mmu_zap_all(kvm); write_unlock(&kvm->mmu_lock); @@ -6579,7 +6658,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) * zap all shadow pages. */ if (unlikely(gen == 0)) { - kvm_debug_ratelimited("kvm: zapping shadow pages for mmio generation wraparound\n"); + kvm_debug_ratelimited("zapping shadow pages for mmio generation wraparound\n"); kvm_mmu_zap_all_fast(kvm); } } @@ -6684,7 +6763,7 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) new_val = 1; else if (sysfs_streq(val, "auto")) new_val = get_nx_auto_mode(); - else if (strtobool(val, &new_val) < 0) + else if (kstrtobool(val, &new_val) < 0) return -EINVAL; __set_nx_huge_pages(new_val); @@ -6718,6 +6797,13 @@ void __init kvm_mmu_x86_module_init(void) if (nx_huge_pages == -1) __set_nx_huge_pages(get_nx_auto_mode()); + /* + * Snapshot userspace's desire to enable the TDP MMU. Whether or not the + * TDP MMU is actually enabled is determined in kvm_configure_mmu() + * when the vendor module is loaded. + */ + tdp_mmu_allowed = tdp_mmu_enabled; + kvm_mmu_spte_module_init(); } diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index dbaf6755c5a7..cc58631e2336 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -156,6 +156,11 @@ static inline bool kvm_mmu_page_ad_need_write_protect(struct kvm_mmu_page *sp) return kvm_x86_ops.cpu_dirty_log_size && sp->role.guest_mode; } +static inline gfn_t gfn_round_for_level(gfn_t gfn, int level) +{ + return gfn & -KVM_PAGES_PER_HPAGE(level); +} + int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, gfn_t gfn, bool can_unsync, bool prefetch); @@ -164,8 +169,17 @@ void kvm_mmu_gfn_allow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn); bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn, int min_level); + void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, u64 start_gfn, u64 pages); + +/* Flush the given page (huge or not) of guest memory. */ +static inline void kvm_flush_remote_tlbs_gfn(struct kvm *kvm, gfn_t gfn, int level) +{ + kvm_flush_remote_tlbs_with_address(kvm, gfn_round_for_level(gfn, level), + KVM_PAGES_PER_HPAGE(level)); +} + unsigned int pte_list_count(struct kvm_rmap_head *rmap_head); extern int nx_huge_pages; @@ -199,7 +213,7 @@ struct kvm_page_fault { /* * Maximum page size that can be created for this fault; input to - * FNAME(fetch), __direct_map and kvm_tdp_mmu_map. + * FNAME(fetch), direct_map() and kvm_tdp_mmu_map(). */ u8 max_level; @@ -222,6 +236,7 @@ struct kvm_page_fault { struct kvm_memory_slot *slot; /* Outputs of kvm_faultin_pfn. */ + unsigned long mmu_seq; kvm_pfn_t pfn; hva_t hva; bool map_writable; @@ -279,6 +294,11 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, }; int r; + if (vcpu->arch.mmu->root_role.direct) { + fault.gfn = fault.addr >> PAGE_SHIFT; + fault.slot = kvm_vcpu_gfn_to_memslot(vcpu, fault.gfn); + } + /* * Async #PF "faults", a.k.a. prefetch faults, are not faults from the * guest perspective and have already been counted at the time of the diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index 2e09d1b6249f..0a2ac438d647 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -10,6 +10,7 @@ * Author: * Xiao Guangrong <guangrong.xiao@linux.intel.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <linux/rculist.h> diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 0f6455072055..57f0b75c80f9 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -642,12 +642,12 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root.hpa))) goto out_gpte_changed; - for (shadow_walk_init(&it, vcpu, fault->addr); - shadow_walk_okay(&it) && it.level > gw->level; - shadow_walk_next(&it)) { + for_each_shadow_entry(vcpu, fault->addr, it) { gfn_t table_gfn; clear_sp_write_flooding_count(it.sptep); + if (it.level == gw->level) + break; table_gfn = gw->table_gfn[it.level - 2]; access = gw->pt_access[it.level - 2]; @@ -692,8 +692,6 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, trace_kvm_mmu_spte_requested(fault); for (; shadow_walk_okay(&it); shadow_walk_next(&it)) { - clear_sp_write_flooding_count(it.sptep); - /* * We cannot overwrite existing page tables with an NX * large page, as the leaf could be executable. @@ -701,7 +699,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, if (fault->nx_huge_page_workaround_enabled) disallowed_hugepage_adjust(fault, *it.sptep, it.level); - base_gfn = fault->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + base_gfn = gfn_round_for_level(fault->gfn, it.level); if (it.level == fault->goal_level) break; @@ -791,7 +789,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault { struct guest_walker walker; int r; - unsigned long mmu_seq; bool is_self_change_mapping; pgprintk("%s: addr %lx err %x\n", __func__, fault->addr, fault->error_code); @@ -838,14 +835,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault else fault->max_level = walker.level; - mmu_seq = vcpu->kvm->mmu_invalidate_seq; - smp_rmb(); - - r = kvm_faultin_pfn(vcpu, fault); - if (r != RET_PF_CONTINUE) - return r; - - r = handle_abnormal_pfn(vcpu, fault, walker.pte_access); + r = kvm_faultin_pfn(vcpu, fault, walker.pte_access); if (r != RET_PF_CONTINUE) return r; @@ -871,7 +861,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault r = RET_PF_RETRY; write_lock(&vcpu->kvm->mmu_lock); - if (is_page_fault_stale(vcpu, fault, mmu_seq)) + if (is_page_fault_stale(vcpu, fault)) goto out_unlock; r = make_mmu_pages_available(vcpu); @@ -937,8 +927,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) mmu_page_zap_pte(vcpu->kvm, sp, sptep, NULL); if (is_shadow_present_pte(old_spte)) - kvm_flush_remote_tlbs_with_address(vcpu->kvm, - sp->gfn, KVM_PAGES_PER_HPAGE(sp->role.level)); + kvm_flush_remote_tlbs_sptep(vcpu->kvm, sptep); if (!rmap_can_add(vcpu)) break; diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index c0fd7e049b4e..c15bfca3ed15 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -7,7 +7,7 @@ * Copyright (C) 2006 Qumranet, Inc. * Copyright 2020 Red Hat, Inc. and/or its affiliates. */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include "mmu.h" @@ -147,9 +147,9 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, WARN_ON_ONCE(!pte_access && !shadow_present_mask); if (sp->role.ad_disabled) - spte |= SPTE_TDP_AD_DISABLED_MASK; + spte |= SPTE_TDP_AD_DISABLED; else if (kvm_mmu_page_ad_need_write_protect(sp)) - spte |= SPTE_TDP_AD_WRPROT_ONLY_MASK; + spte |= SPTE_TDP_AD_WRPROT_ONLY; /* * For the EPT case, shadow_present_mask is 0 if hardware @@ -317,7 +317,7 @@ u64 make_nonleaf_spte(u64 *child_pt, bool ad_disabled) shadow_user_mask | shadow_x_mask | shadow_me_value; if (ad_disabled) - spte |= SPTE_TDP_AD_DISABLED_MASK; + spte |= SPTE_TDP_AD_DISABLED; else spte |= shadow_accessed_mask; @@ -352,7 +352,7 @@ u64 mark_spte_for_access_track(u64 spte) WARN_ONCE(spte & (SHADOW_ACC_TRACK_SAVED_BITS_MASK << SHADOW_ACC_TRACK_SAVED_BITS_SHIFT), - "kvm: Access Tracking saved bit locations are not zero\n"); + "Access Tracking saved bit locations are not zero\n"); spte |= (spte & SHADOW_ACC_TRACK_SAVED_BITS_MASK) << SHADOW_ACC_TRACK_SAVED_BITS_SHIFT; diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 6f54dc9409c9..1279db2eab44 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -28,10 +28,10 @@ */ #define SPTE_TDP_AD_SHIFT 52 #define SPTE_TDP_AD_MASK (3ULL << SPTE_TDP_AD_SHIFT) -#define SPTE_TDP_AD_ENABLED_MASK (0ULL << SPTE_TDP_AD_SHIFT) -#define SPTE_TDP_AD_DISABLED_MASK (1ULL << SPTE_TDP_AD_SHIFT) -#define SPTE_TDP_AD_WRPROT_ONLY_MASK (2ULL << SPTE_TDP_AD_SHIFT) -static_assert(SPTE_TDP_AD_ENABLED_MASK == 0); +#define SPTE_TDP_AD_ENABLED (0ULL << SPTE_TDP_AD_SHIFT) +#define SPTE_TDP_AD_DISABLED (1ULL << SPTE_TDP_AD_SHIFT) +#define SPTE_TDP_AD_WRPROT_ONLY (2ULL << SPTE_TDP_AD_SHIFT) +static_assert(SPTE_TDP_AD_ENABLED == 0); #ifdef CONFIG_DYNAMIC_PHYSICAL_MASK #define SPTE_BASE_ADDR_MASK (physical_mask & ~(u64)(PAGE_SIZE-1)) @@ -164,7 +164,7 @@ extern u64 __read_mostly shadow_me_value; extern u64 __read_mostly shadow_me_mask; /* - * SPTEs in MMUs without A/D bits are marked with SPTE_TDP_AD_DISABLED_MASK; + * SPTEs in MMUs without A/D bits are marked with SPTE_TDP_AD_DISABLED; * shadow_acc_track_mask is the set of bits to be cleared in non-accessed * pages. */ @@ -266,18 +266,18 @@ static inline bool sp_ad_disabled(struct kvm_mmu_page *sp) static inline bool spte_ad_enabled(u64 spte) { MMU_WARN_ON(!is_shadow_present_pte(spte)); - return (spte & SPTE_TDP_AD_MASK) != SPTE_TDP_AD_DISABLED_MASK; + return (spte & SPTE_TDP_AD_MASK) != SPTE_TDP_AD_DISABLED; } static inline bool spte_ad_need_write_protect(u64 spte) { MMU_WARN_ON(!is_shadow_present_pte(spte)); /* - * This is benign for non-TDP SPTEs as SPTE_TDP_AD_ENABLED_MASK is '0', + * This is benign for non-TDP SPTEs as SPTE_TDP_AD_ENABLED is '0', * and non-TDP SPTEs will never set these bits. Optimize for 64-bit * TDP and do the A/D type check unconditionally. */ - return (spte & SPTE_TDP_AD_MASK) != SPTE_TDP_AD_ENABLED_MASK; + return (spte & SPTE_TDP_AD_MASK) != SPTE_TDP_AD_ENABLED; } static inline u64 spte_shadow_accessed_mask(u64 spte) @@ -435,11 +435,11 @@ static inline void check_spte_writable_invariants(u64 spte) { if (spte & shadow_mmu_writable_mask) WARN_ONCE(!(spte & shadow_host_writable_mask), - "kvm: MMU-writable SPTE is not Host-writable: %llx", + KBUILD_MODNAME ": MMU-writable SPTE is not Host-writable: %llx", spte); else WARN_ONCE(is_writable_pte(spte), - "kvm: Writable SPTE is not MMU-writable: %llx", spte); + KBUILD_MODNAME ": Writable SPTE is not MMU-writable: %llx", spte); } static inline bool is_mmu_writable_spte(u64 spte) diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c index 39b48e7d7d1a..d2eb0d4f8710 100644 --- a/arch/x86/kvm/mmu/tdp_iter.c +++ b/arch/x86/kvm/mmu/tdp_iter.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "mmu_internal.h" #include "tdp_iter.h" @@ -15,11 +16,6 @@ static void tdp_iter_refresh_sptep(struct tdp_iter *iter) iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep); } -static gfn_t round_gfn_for_level(gfn_t gfn, int level) -{ - return gfn & -KVM_PAGES_PER_HPAGE(level); -} - /* * Return the TDP iterator to the root PT and allow it to continue its * traversal over the paging structure from there. @@ -30,7 +26,7 @@ void tdp_iter_restart(struct tdp_iter *iter) iter->yielded_gfn = iter->next_last_level_gfn; iter->level = iter->root_level; - iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level); + iter->gfn = gfn_round_for_level(iter->next_last_level_gfn, iter->level); tdp_iter_refresh_sptep(iter); iter->valid = true; @@ -97,7 +93,7 @@ static bool try_step_down(struct tdp_iter *iter) iter->level--; iter->pt_path[iter->level - 1] = child_pt; - iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level); + iter->gfn = gfn_round_for_level(iter->next_last_level_gfn, iter->level); tdp_iter_refresh_sptep(iter); return true; @@ -139,7 +135,7 @@ static bool try_step_up(struct tdp_iter *iter) return false; iter->level++; - iter->gfn = round_gfn_for_level(iter->gfn, iter->level); + iter->gfn = gfn_round_for_level(iter->gfn, iter->level); tdp_iter_refresh_sptep(iter); return true; diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index d6df38d371a0..7c25dbf32ecc 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "mmu.h" #include "mmu_internal.h" @@ -10,23 +11,15 @@ #include <asm/cmpxchg.h> #include <trace/events/kvm.h> -static bool __read_mostly tdp_mmu_enabled = true; -module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0644); - /* Initializes the TDP MMU for the VM, if enabled. */ int kvm_mmu_init_tdp_mmu(struct kvm *kvm) { struct workqueue_struct *wq; - if (!tdp_enabled || !READ_ONCE(tdp_mmu_enabled)) - return 0; - wq = alloc_workqueue("kvm", WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 0); if (!wq) return -ENOMEM; - /* This should not be changed for the lifetime of the VM. */ - kvm->arch.tdp_mmu_enabled = true; INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots); spin_lock_init(&kvm->arch.tdp_mmu_pages_lock); kvm->arch.tdp_mmu_zap_wq = wq; @@ -47,9 +40,6 @@ static __always_inline bool kvm_lockdep_assert_mmu_lock_held(struct kvm *kvm, void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) { - if (!kvm->arch.tdp_mmu_enabled) - return; - /* Also waits for any queued work items. */ destroy_workqueue(kvm->arch.tdp_mmu_zap_wq); @@ -144,7 +134,7 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, if (!refcount_dec_and_test(&root->tdp_mmu_root_count)) return; - WARN_ON(!root->tdp_mmu_page); + WARN_ON(!is_tdp_mmu_page(root)); /* * The root now has refcount=0. It is valid, but readers already @@ -690,8 +680,7 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm, if (ret) return ret; - kvm_flush_remote_tlbs_with_address(kvm, iter->gfn, - KVM_PAGES_PER_HPAGE(iter->level)); + kvm_flush_remote_tlbs_gfn(kvm, iter->gfn, iter->level); /* * No other thread can overwrite the removed SPTE as they must either @@ -1090,8 +1079,7 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, return RET_PF_RETRY; else if (is_shadow_present_pte(iter->old_spte) && !is_last_spte(iter->old_spte, iter->level)) - kvm_flush_remote_tlbs_with_address(vcpu->kvm, sp->gfn, - KVM_PAGES_PER_HPAGE(iter->level + 1)); + kvm_flush_remote_tlbs_gfn(vcpu->kvm, iter->gfn, iter->level); /* * If the page fault was caused by a write but the page is write diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index d3714200b932..0a63b1afabd3 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -7,6 +7,9 @@ #include "spte.h" +int kvm_mmu_init_tdp_mmu(struct kvm *kvm); +void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); + hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu); __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) @@ -68,31 +71,9 @@ u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, u64 addr, u64 *spte); #ifdef CONFIG_X86_64 -int kvm_mmu_init_tdp_mmu(struct kvm *kvm); -void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return sp->tdp_mmu_page; } - -static inline bool is_tdp_mmu(struct kvm_mmu *mmu) -{ - struct kvm_mmu_page *sp; - hpa_t hpa = mmu->root.hpa; - - if (WARN_ON(!VALID_PAGE(hpa))) - return false; - - /* - * A NULL shadow page is legal when shadowing a non-paging guest with - * PAE paging, as the MMU will be direct with root_hpa pointing at the - * pae_root page, not a shadow page. - */ - sp = to_shadow_page(hpa); - return sp && is_tdp_mmu_page(sp) && sp->root_count; -} #else -static inline int kvm_mmu_init_tdp_mmu(struct kvm *kvm) { return 0; } -static inline void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) {} static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return false; } -static inline bool is_tdp_mmu(struct kvm_mmu *mmu) { return false; } #endif #endif /* __KVM_X86_MMU_TDP_MMU_H */ diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index a8502e02f479..9fac1ec03463 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -13,6 +13,7 @@ * Paolo Bonzini <pbonzini@redhat.com> * Xiao Guangrong <guangrong.xiao@linux.intel.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <asm/mtrr.h> diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index eb594620dd75..612e6c70ce2e 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -9,6 +9,7 @@ * Gleb Natapov <gleb@redhat.com> * Wei Huang <wei@redhat.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/kvm_host.h> @@ -28,9 +29,18 @@ struct x86_pmu_capability __read_mostly kvm_pmu_cap; EXPORT_SYMBOL_GPL(kvm_pmu_cap); -static const struct x86_cpu_id vmx_icl_pebs_cpu[] = { +/* Precise Distribution of Instructions Retired (PDIR) */ +static const struct x86_cpu_id vmx_pebs_pdir_cpu[] = { X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, NULL), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, NULL), + /* Instruction-Accurate PDIR (PDIR++) */ + X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, NULL), + {} +}; + +/* Precise Distribution (PDist) */ +static const struct x86_cpu_id vmx_pebs_pdist_cpu[] = { + X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, NULL), {} }; @@ -155,6 +165,28 @@ static void kvm_perf_overflow(struct perf_event *perf_event, kvm_make_request(KVM_REQ_PMU, pmc->vcpu); } +static u64 pmc_get_pebs_precise_level(struct kvm_pmc *pmc) +{ + /* + * For some model specific pebs counters with special capabilities + * (PDIR, PDIR++, PDIST), KVM needs to raise the event precise + * level to the maximum value (currently 3, backwards compatible) + * so that the perf subsystem would assign specific hardware counter + * with that capability for vPMC. + */ + if ((pmc->idx == 0 && x86_match_cpu(vmx_pebs_pdist_cpu)) || + (pmc->idx == 32 && x86_match_cpu(vmx_pebs_pdir_cpu))) + return 3; + + /* + * The non-zero precision level of guest event makes the ordinary + * guest event becomes a guest PEBS event and triggers the host + * PEBS PMI handler to determine whether the PEBS overflow PMI + * comes from the host counters or the guest. + */ + return 1; +} + static int pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config, bool exclude_user, bool exclude_kernel, bool intr) @@ -186,22 +218,12 @@ static int pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config, } if (pebs) { /* - * The non-zero precision level of guest event makes the ordinary - * guest event becomes a guest PEBS event and triggers the host - * PEBS PMI handler to determine whether the PEBS overflow PMI - * comes from the host counters or the guest. - * * For most PEBS hardware events, the difference in the software * precision levels of guest and host PEBS events will not affect * the accuracy of the PEBS profiling result, because the "event IP" * in the PEBS record is calibrated on the guest side. - * - * On Icelake everything is fine. Other hardware (GLC+, TNT+) that - * could possibly care here is unsupported and needs changes. */ - attr.precise_ip = 1; - if (x86_match_cpu(vmx_icl_pebs_cpu) && pmc->idx == 32) - attr.precise_ip = 3; + attr.precise_ip = pmc_get_pebs_precise_level(pmc); } event = perf_event_create_kernel_counter(&attr, -1, current, @@ -254,48 +276,128 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc) return true; } -static int cmp_u64(const void *pa, const void *pb) +static int filter_cmp(const void *pa, const void *pb, u64 mask) { - u64 a = *(u64 *)pa; - u64 b = *(u64 *)pb; + u64 a = *(u64 *)pa & mask; + u64 b = *(u64 *)pb & mask; return (a > b) - (a < b); } + +static int filter_sort_cmp(const void *pa, const void *pb) +{ + return filter_cmp(pa, pb, (KVM_PMU_MASKED_ENTRY_EVENT_SELECT | + KVM_PMU_MASKED_ENTRY_EXCLUDE)); +} + +/* + * For the event filter, searching is done on the 'includes' list and + * 'excludes' list separately rather than on the 'events' list (which + * has both). As a result the exclude bit can be ignored. + */ +static int filter_event_cmp(const void *pa, const void *pb) +{ + return filter_cmp(pa, pb, (KVM_PMU_MASKED_ENTRY_EVENT_SELECT)); +} + +static int find_filter_index(u64 *events, u64 nevents, u64 key) +{ + u64 *fe = bsearch(&key, events, nevents, sizeof(events[0]), + filter_event_cmp); + + if (!fe) + return -1; + + return fe - events; +} + +static bool is_filter_entry_match(u64 filter_event, u64 umask) +{ + u64 mask = filter_event >> (KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT - 8); + u64 match = filter_event & KVM_PMU_MASKED_ENTRY_UMASK_MATCH; + + BUILD_BUG_ON((KVM_PMU_ENCODE_MASKED_ENTRY(0, 0xff, 0, false) >> + (KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT - 8)) != + ARCH_PERFMON_EVENTSEL_UMASK); + + return (umask & mask) == match; +} + +static bool filter_contains_match(u64 *events, u64 nevents, u64 eventsel) +{ + u64 event_select = eventsel & kvm_pmu_ops.EVENTSEL_EVENT; + u64 umask = eventsel & ARCH_PERFMON_EVENTSEL_UMASK; + int i, index; + + index = find_filter_index(events, nevents, event_select); + if (index < 0) + return false; + + /* + * Entries are sorted by the event select. Walk the list in both + * directions to process all entries with the targeted event select. + */ + for (i = index; i < nevents; i++) { + if (filter_event_cmp(&events[i], &event_select)) + break; + + if (is_filter_entry_match(events[i], umask)) + return true; + } + + for (i = index - 1; i >= 0; i--) { + if (filter_event_cmp(&events[i], &event_select)) + break; + + if (is_filter_entry_match(events[i], umask)) + return true; + } + + return false; +} + +static bool is_gp_event_allowed(struct kvm_x86_pmu_event_filter *f, + u64 eventsel) +{ + if (filter_contains_match(f->includes, f->nr_includes, eventsel) && + !filter_contains_match(f->excludes, f->nr_excludes, eventsel)) + return f->action == KVM_PMU_EVENT_ALLOW; + + return f->action == KVM_PMU_EVENT_DENY; +} + +static bool is_fixed_event_allowed(struct kvm_x86_pmu_event_filter *filter, + int idx) +{ + int fixed_idx = idx - INTEL_PMC_IDX_FIXED; + + if (filter->action == KVM_PMU_EVENT_DENY && + test_bit(fixed_idx, (ulong *)&filter->fixed_counter_bitmap)) + return false; + if (filter->action == KVM_PMU_EVENT_ALLOW && + !test_bit(fixed_idx, (ulong *)&filter->fixed_counter_bitmap)) + return false; + + return true; +} + static bool check_pmu_event_filter(struct kvm_pmc *pmc) { - struct kvm_pmu_event_filter *filter; + struct kvm_x86_pmu_event_filter *filter; struct kvm *kvm = pmc->vcpu->kvm; - bool allow_event = true; - __u64 key; - int idx; if (!static_call(kvm_x86_pmu_hw_event_available)(pmc)) return false; filter = srcu_dereference(kvm->arch.pmu_event_filter, &kvm->srcu); if (!filter) - goto out; + return true; - if (pmc_is_gp(pmc)) { - key = pmc->eventsel & AMD64_RAW_EVENT_MASK_NB; - if (bsearch(&key, filter->events, filter->nevents, - sizeof(__u64), cmp_u64)) - allow_event = filter->action == KVM_PMU_EVENT_ALLOW; - else - allow_event = filter->action == KVM_PMU_EVENT_DENY; - } else { - idx = pmc->idx - INTEL_PMC_IDX_FIXED; - if (filter->action == KVM_PMU_EVENT_DENY && - test_bit(idx, (ulong *)&filter->fixed_counter_bitmap)) - allow_event = false; - if (filter->action == KVM_PMU_EVENT_ALLOW && - !test_bit(idx, (ulong *)&filter->fixed_counter_bitmap)) - allow_event = false; - } + if (pmc_is_gp(pmc)) + return is_gp_event_allowed(filter, pmc->eventsel); -out: - return allow_event; + return is_fixed_event_allowed(filter, pmc->idx); } static void reprogram_counter(struct kvm_pmc *pmc) @@ -592,47 +694,133 @@ void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 perf_hw_id) } EXPORT_SYMBOL_GPL(kvm_pmu_trigger_event); +static bool is_masked_filter_valid(const struct kvm_x86_pmu_event_filter *filter) +{ + u64 mask = kvm_pmu_ops.EVENTSEL_EVENT | + KVM_PMU_MASKED_ENTRY_UMASK_MASK | + KVM_PMU_MASKED_ENTRY_UMASK_MATCH | + KVM_PMU_MASKED_ENTRY_EXCLUDE; + int i; + + for (i = 0; i < filter->nevents; i++) { + if (filter->events[i] & ~mask) + return false; + } + + return true; +} + +static void convert_to_masked_filter(struct kvm_x86_pmu_event_filter *filter) +{ + int i, j; + + for (i = 0, j = 0; i < filter->nevents; i++) { + /* + * Skip events that are impossible to match against a guest + * event. When filtering, only the event select + unit mask + * of the guest event is used. To maintain backwards + * compatibility, impossible filters can't be rejected :-( + */ + if (filter->events[i] & ~(kvm_pmu_ops.EVENTSEL_EVENT | + ARCH_PERFMON_EVENTSEL_UMASK)) + continue; + /* + * Convert userspace events to a common in-kernel event so + * only one code path is needed to support both events. For + * the in-kernel events use masked events because they are + * flexible enough to handle both cases. To convert to masked + * events all that's needed is to add an "all ones" umask_mask, + * (unmasked filter events don't support EXCLUDE). + */ + filter->events[j++] = filter->events[i] | + (0xFFULL << KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT); + } + + filter->nevents = j; +} + +static int prepare_filter_lists(struct kvm_x86_pmu_event_filter *filter) +{ + int i; + + if (!(filter->flags & KVM_PMU_EVENT_FLAG_MASKED_EVENTS)) + convert_to_masked_filter(filter); + else if (!is_masked_filter_valid(filter)) + return -EINVAL; + + /* + * Sort entries by event select and includes vs. excludes so that all + * entries for a given event select can be processed efficiently during + * filtering. The EXCLUDE flag uses a more significant bit than the + * event select, and so the sorted list is also effectively split into + * includes and excludes sub-lists. + */ + sort(&filter->events, filter->nevents, sizeof(filter->events[0]), + filter_sort_cmp, NULL); + + i = filter->nevents; + /* Find the first EXCLUDE event (only supported for masked events). */ + if (filter->flags & KVM_PMU_EVENT_FLAG_MASKED_EVENTS) { + for (i = 0; i < filter->nevents; i++) { + if (filter->events[i] & KVM_PMU_MASKED_ENTRY_EXCLUDE) + break; + } + } + + filter->nr_includes = i; + filter->nr_excludes = filter->nevents - filter->nr_includes; + filter->includes = filter->events; + filter->excludes = filter->events + filter->nr_includes; + + return 0; +} + int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp) { - struct kvm_pmu_event_filter tmp, *filter; + struct kvm_pmu_event_filter __user *user_filter = argp; + struct kvm_x86_pmu_event_filter *filter; + struct kvm_pmu_event_filter tmp; struct kvm_vcpu *vcpu; unsigned long i; size_t size; int r; - if (copy_from_user(&tmp, argp, sizeof(tmp))) + if (copy_from_user(&tmp, user_filter, sizeof(tmp))) return -EFAULT; if (tmp.action != KVM_PMU_EVENT_ALLOW && tmp.action != KVM_PMU_EVENT_DENY) return -EINVAL; - if (tmp.flags != 0) + if (tmp.flags & ~KVM_PMU_EVENT_FLAGS_VALID_MASK) return -EINVAL; if (tmp.nevents > KVM_PMU_EVENT_FILTER_MAX_EVENTS) return -E2BIG; size = struct_size(filter, events, tmp.nevents); - filter = kmalloc(size, GFP_KERNEL_ACCOUNT); + filter = kzalloc(size, GFP_KERNEL_ACCOUNT); if (!filter) return -ENOMEM; + filter->action = tmp.action; + filter->nevents = tmp.nevents; + filter->fixed_counter_bitmap = tmp.fixed_counter_bitmap; + filter->flags = tmp.flags; + r = -EFAULT; - if (copy_from_user(filter, argp, size)) + if (copy_from_user(filter->events, user_filter->events, + sizeof(filter->events[0]) * filter->nevents)) goto cleanup; - /* Ensure nevents can't be changed between the user copies. */ - *filter = tmp; - - /* - * Sort the in-kernel list so that we can search it with bsearch. - */ - sort(&filter->events, filter->nevents, sizeof(__u64), cmp_u64, NULL); + r = prepare_filter_lists(filter); + if (r) + goto cleanup; mutex_lock(&kvm->lock); filter = rcu_replace_pointer(kvm->arch.pmu_event_filter, filter, mutex_is_locked(&kvm->lock)); + mutex_unlock(&kvm->lock); synchronize_srcu_expedited(&kvm->srcu); BUILD_BUG_ON(sizeof(((struct kvm_pmu *)0)->reprogram_pmi) > @@ -643,8 +831,6 @@ int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp) kvm_make_all_cpus_request(kvm, KVM_REQ_PMU); - mutex_unlock(&kvm->lock); - r = 0; cleanup: kfree(filter); diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index ee67ba625094..be62c16f2265 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -18,12 +18,6 @@ #define VMWARE_BACKDOOR_PMC_REAL_TIME 0x10001 #define VMWARE_BACKDOOR_PMC_APPARENT_TIME 0x10002 -struct kvm_event_hw_type_mapping { - u8 eventsel; - u8 unit_mask; - unsigned event_type; -}; - struct kvm_pmu_ops { bool (*hw_event_available)(struct kvm_pmc *pmc); bool (*pmc_is_enabled)(struct kvm_pmc *pmc); @@ -40,6 +34,9 @@ struct kvm_pmu_ops { void (*reset)(struct kvm_vcpu *vcpu); void (*deliver_pmi)(struct kvm_vcpu *vcpu); void (*cleanup)(struct kvm_vcpu *vcpu); + + const u64 EVENTSEL_EVENT; + const int MAX_NR_GP_COUNTERS; }; void kvm_pmu_ops_update(const struct kvm_pmu_ops *pmu_ops); @@ -161,7 +158,7 @@ static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc) extern struct x86_pmu_capability kvm_pmu_cap; -static inline void kvm_init_pmu_capability(void) +static inline void kvm_init_pmu_capability(const struct kvm_pmu_ops *pmu_ops) { bool is_intel = boot_cpu_data.x86_vendor == X86_VENDOR_INTEL; @@ -192,6 +189,8 @@ static inline void kvm_init_pmu_capability(void) } kvm_pmu_cap.version = min(kvm_pmu_cap.version, 2); + kvm_pmu_cap.num_counters_gp = min(kvm_pmu_cap.num_counters_gp, + pmu_ops->MAX_NR_GP_COUNTERS); kvm_pmu_cap.num_counters_fixed = min(kvm_pmu_cap.num_counters_fixed, KVM_PMC_MAX_FIXED); } diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index 81f4e9ce0c77..a5717282bb9c 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -14,6 +14,7 @@ enum kvm_only_cpuid_leafs { CPUID_12_EAX = NCAPINTS, CPUID_7_1_EDX, + CPUID_8000_0007_EDX, NR_KVM_CPU_CAPS, NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, @@ -43,6 +44,9 @@ enum kvm_only_cpuid_leafs { #define X86_FEATURE_AVX_NE_CONVERT KVM_X86_FEATURE(CPUID_7_1_EDX, 5) #define X86_FEATURE_PREFETCHITI KVM_X86_FEATURE(CPUID_7_1_EDX, 14) +/* CPUID level 0x80000007 (EDX). */ +#define KVM_X86_FEATURE_CONSTANT_TSC KVM_X86_FEATURE(CPUID_8000_0007_EDX, 8) + struct cpuid_reg { u32 function; u32 index; @@ -68,6 +72,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_12_EAX] = {0x00000012, 0, CPUID_EAX}, [CPUID_8000_001F_EAX] = {0x8000001f, 0, CPUID_EAX}, [CPUID_7_1_EDX] = { 7, 1, CPUID_EDX}, + [CPUID_8000_0007_EDX] = {0x80000007, 0, CPUID_EDX}, [CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX}, }; @@ -101,6 +106,8 @@ static __always_inline u32 __feature_translate(int x86_feature) return KVM_X86_FEATURE_SGX2; else if (x86_feature == X86_FEATURE_SGX_EDECCSSA) return KVM_X86_FEATURE_SGX_EDECCSSA; + else if (x86_feature == X86_FEATURE_CONSTANT_TSC) + return KVM_X86_FEATURE_CONSTANT_TSC; return x86_feature; } diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c index a9c1c2af8d94..b42111a24cc2 100644 --- a/arch/x86/kvm/smm.c +++ b/arch/x86/kvm/smm.c @@ -1,4 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include "x86.h" @@ -110,8 +111,6 @@ static void check_smram_offsets(void) void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm) { - BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK); - trace_kvm_smm_transition(vcpu->vcpu_id, vcpu->arch.smbase, entering_smm); if (entering_smm) { diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 6919dee69f18..ca684979e90d 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -12,7 +12,7 @@ * Avi Kivity <avi@qumranet.com> */ -#define pr_fmt(fmt) "SVM: " fmt +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_types.h> #include <linux/hashtable.h> @@ -53,7 +53,7 @@ static DEFINE_HASHTABLE(svm_vm_data_hash, SVM_VM_DATA_HASH_BITS); static u32 next_vm_id = 0; static bool next_vm_id_wrapped = 0; static DEFINE_SPINLOCK(svm_vm_data_hash_lock); -enum avic_modes avic_mode; +bool x2avic_enabled; /* * This is a wrapper of struct amd_iommu_ir_data. @@ -72,20 +72,25 @@ static void avic_activate_vmcb(struct vcpu_svm *svm) vmcb->control.int_ctl |= AVIC_ENABLE_MASK; - /* Note: - * KVM can support hybrid-AVIC mode, where KVM emulates x2APIC - * MSR accesses, while interrupt injection to a running vCPU - * can be achieved using AVIC doorbell. The AVIC hardware still - * accelerate MMIO accesses, but this does not cause any harm - * as the guest is not supposed to access xAPIC mmio when uses x2APIC. + /* + * Note: KVM supports hybrid-AVIC mode, where KVM emulates x2APIC MSR + * accesses, while interrupt injection to a running vCPU can be + * achieved using AVIC doorbell. KVM disables the APIC access page + * (deletes the memslot) if any vCPU has x2APIC enabled, thus enabling + * AVIC in hybrid mode activates only the doorbell mechanism. */ - if (apic_x2apic_mode(svm->vcpu.arch.apic) && - avic_mode == AVIC_MODE_X2) { + if (x2avic_enabled && apic_x2apic_mode(svm->vcpu.arch.apic)) { vmcb->control.int_ctl |= X2APIC_MODE_MASK; vmcb->control.avic_physical_id |= X2AVIC_MAX_PHYSICAL_ID; /* Disabling MSR intercept for x2APIC registers */ svm_set_x2apic_msr_interception(svm, false); } else { + /* + * Flush the TLB, the guest may have inserted a non-APIC + * mapping into the TLB while AVIC was disabled. + */ + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, &svm->vcpu); + /* For xAVIC and hybrid-xAVIC modes */ vmcb->control.avic_physical_id |= AVIC_MAX_PHYSICAL_ID; /* Enabling MSR intercept for x2APIC registers */ @@ -241,8 +246,8 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, u64 *avic_physical_id_table; struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm); - if ((avic_mode == AVIC_MODE_X1 && index > AVIC_MAX_PHYSICAL_ID) || - (avic_mode == AVIC_MODE_X2 && index > X2AVIC_MAX_PHYSICAL_ID)) + if ((!x2avic_enabled && index > AVIC_MAX_PHYSICAL_ID) || + (index > X2AVIC_MAX_PHYSICAL_ID)) return NULL; avic_physical_id_table = page_address(kvm_svm->avic_physical_id_table_page); @@ -250,47 +255,14 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, return &avic_physical_id_table[index]; } -/* - * Note: - * AVIC hardware walks the nested page table to check permissions, - * but does not use the SPA address specified in the leaf page - * table entry since it uses address in the AVIC_BACKING_PAGE pointer - * field of the VMCB. Therefore, we set up the - * APIC_ACCESS_PAGE_PRIVATE_MEMSLOT (4KB) here. - */ -static int avic_alloc_access_page(struct kvm *kvm) -{ - void __user *ret; - int r = 0; - - mutex_lock(&kvm->slots_lock); - - if (kvm->arch.apic_access_memslot_enabled) - goto out; - - ret = __x86_set_memory_region(kvm, - APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, - APIC_DEFAULT_PHYS_BASE, - PAGE_SIZE); - if (IS_ERR(ret)) { - r = PTR_ERR(ret); - goto out; - } - - kvm->arch.apic_access_memslot_enabled = true; -out: - mutex_unlock(&kvm->slots_lock); - return r; -} - static int avic_init_backing_page(struct kvm_vcpu *vcpu) { u64 *entry, new_entry; int id = vcpu->vcpu_id; struct vcpu_svm *svm = to_svm(vcpu); - if ((avic_mode == AVIC_MODE_X1 && id > AVIC_MAX_PHYSICAL_ID) || - (avic_mode == AVIC_MODE_X2 && id > X2AVIC_MAX_PHYSICAL_ID)) + if ((!x2avic_enabled && id > AVIC_MAX_PHYSICAL_ID) || + (id > X2AVIC_MAX_PHYSICAL_ID)) return -EINVAL; if (!vcpu->arch.apic->regs) @@ -299,7 +271,13 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) if (kvm_apicv_activated(vcpu->kvm)) { int ret; - ret = avic_alloc_access_page(vcpu->kvm); + /* + * Note, AVIC hardware walks the nested page table to check + * permissions, but does not use the SPA address specified in + * the leaf SPTE since it uses address in the AVIC_BACKING_PAGE + * pointer field of the VMCB. + */ + ret = kvm_alloc_apic_access_page(vcpu->kvm); if (ret) return ret; } @@ -339,6 +317,60 @@ void avic_ring_doorbell(struct kvm_vcpu *vcpu) put_cpu(); } + +static void avic_kick_vcpu(struct kvm_vcpu *vcpu, u32 icrl) +{ + vcpu->arch.apic->irr_pending = true; + svm_complete_interrupt_delivery(vcpu, + icrl & APIC_MODE_MASK, + icrl & APIC_INT_LEVELTRIG, + icrl & APIC_VECTOR_MASK); +} + +static void avic_kick_vcpu_by_physical_id(struct kvm *kvm, u32 physical_id, + u32 icrl) +{ + /* + * KVM inhibits AVIC if any vCPU ID diverges from the vCPUs APIC ID, + * i.e. APIC ID == vCPU ID. + */ + struct kvm_vcpu *target_vcpu = kvm_get_vcpu_by_id(kvm, physical_id); + + /* Once again, nothing to do if the target vCPU doesn't exist. */ + if (unlikely(!target_vcpu)) + return; + + avic_kick_vcpu(target_vcpu, icrl); +} + +static void avic_kick_vcpu_by_logical_id(struct kvm *kvm, u32 *avic_logical_id_table, + u32 logid_index, u32 icrl) +{ + u32 physical_id; + + if (avic_logical_id_table) { + u32 logid_entry = avic_logical_id_table[logid_index]; + + /* Nothing to do if the logical destination is invalid. */ + if (unlikely(!(logid_entry & AVIC_LOGICAL_ID_ENTRY_VALID_MASK))) + return; + + physical_id = logid_entry & + AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK; + } else { + /* + * For x2APIC, the logical APIC ID is a read-only value that is + * derived from the x2APIC ID, thus the x2APIC ID can be found + * by reversing the calculation (stored in logid_index). Note, + * bits 31:20 of the x2APIC ID aren't propagated to the logical + * ID, but KVM limits the x2APIC ID limited to KVM_MAX_VCPU_IDS. + */ + physical_id = logid_index; + } + + avic_kick_vcpu_by_physical_id(kvm, physical_id, icrl); +} + /* * A fast-path version of avic_kick_target_vcpus(), which attempts to match * destination APIC ID to vCPU without looping through all vCPUs. @@ -346,11 +378,10 @@ void avic_ring_doorbell(struct kvm_vcpu *vcpu) static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source, u32 icrl, u32 icrh, u32 index) { - u32 l1_physical_id, dest; - struct kvm_vcpu *target_vcpu; int dest_mode = icrl & APIC_DEST_MASK; int shorthand = icrl & APIC_SHORT_MASK; struct kvm_svm *kvm_svm = to_kvm_svm(kvm); + u32 dest; if (shorthand != APIC_DEST_NOSHORT) return -EINVAL; @@ -367,18 +398,18 @@ static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source if (!apic_x2apic_mode(source) && dest == APIC_BROADCAST) return -EINVAL; - l1_physical_id = dest; - - if (WARN_ON_ONCE(l1_physical_id != index)) + if (WARN_ON_ONCE(dest != index)) return -EINVAL; + avic_kick_vcpu_by_physical_id(kvm, dest, icrl); } else { - u32 bitmap, cluster; - int logid_index; + u32 *avic_logical_id_table; + unsigned long bitmap, i; + u32 cluster; if (apic_x2apic_mode(source)) { /* 16 bit dest mask, 16 bit cluster id */ - bitmap = dest & 0xFFFF0000; + bitmap = dest & 0xFFFF; cluster = (dest >> 16) << 4; } else if (kvm_lapic_get_reg(source, APIC_DFR) == APIC_DFR_FLAT) { /* 8 bit dest mask*/ @@ -390,67 +421,32 @@ static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source cluster = (dest >> 4) << 2; } + /* Nothing to do if there are no destinations in the cluster. */ if (unlikely(!bitmap)) - /* guest bug: nobody to send the logical interrupt to */ return 0; - if (!is_power_of_2(bitmap)) - /* multiple logical destinations, use slow path */ - return -EINVAL; - - logid_index = cluster + __ffs(bitmap); - - if (!apic_x2apic_mode(source)) { - u32 *avic_logical_id_table = - page_address(kvm_svm->avic_logical_id_table_page); - - u32 logid_entry = avic_logical_id_table[logid_index]; - - if (WARN_ON_ONCE(index != logid_index)) - return -EINVAL; - - /* guest bug: non existing/reserved logical destination */ - if (unlikely(!(logid_entry & AVIC_LOGICAL_ID_ENTRY_VALID_MASK))) - return 0; - - l1_physical_id = logid_entry & - AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK; - } else { - /* - * For x2APIC logical mode, cannot leverage the index. - * Instead, calculate physical ID from logical ID in ICRH. - */ - int cluster = (icrh & 0xffff0000) >> 16; - int apic = ffs(icrh & 0xffff) - 1; - - /* - * If the x2APIC logical ID sub-field (i.e. icrh[15:0]) - * contains anything but a single bit, we cannot use the - * fast path, because it is limited to a single vCPU. - */ - if (apic < 0 || icrh != (1 << apic)) - return -EINVAL; + if (apic_x2apic_mode(source)) + avic_logical_id_table = NULL; + else + avic_logical_id_table = page_address(kvm_svm->avic_logical_id_table_page); - l1_physical_id = (cluster << 4) + apic; - } + /* + * AVIC is inhibited if vCPUs aren't mapped 1:1 with logical + * IDs, thus each bit in the destination is guaranteed to map + * to at most one vCPU. + */ + for_each_set_bit(i, &bitmap, 16) + avic_kick_vcpu_by_logical_id(kvm, avic_logical_id_table, + cluster + i, icrl); } - target_vcpu = kvm_get_vcpu_by_id(kvm, l1_physical_id); - if (unlikely(!target_vcpu)) - /* guest bug: non existing vCPU is a target of this IPI*/ - return 0; - - target_vcpu->arch.apic->irr_pending = true; - svm_complete_interrupt_delivery(target_vcpu, - icrl & APIC_MODE_MASK, - icrl & APIC_INT_LEVELTRIG, - icrl & APIC_VECTOR_MASK); return 0; } static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, u32 icrl, u32 icrh, u32 index) { + u32 dest = apic_x2apic_mode(source) ? icrh : GET_XAPIC_DEST_FIELD(icrh); unsigned long i; struct kvm_vcpu *vcpu; @@ -466,21 +462,9 @@ static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, * since entered the guest will have processed pending IRQs at VMRUN. */ kvm_for_each_vcpu(i, vcpu, kvm) { - u32 dest; - - if (apic_x2apic_mode(vcpu->arch.apic)) - dest = icrh; - else - dest = GET_XAPIC_DEST_FIELD(icrh); - if (kvm_apic_match_dest(vcpu, source, icrl & APIC_SHORT_MASK, - dest, icrl & APIC_DEST_MASK)) { - vcpu->arch.apic->irr_pending = true; - svm_complete_interrupt_delivery(vcpu, - icrl & APIC_MODE_MASK, - icrl & APIC_INT_LEVELTRIG, - icrl & APIC_VECTOR_MASK); - } + dest, icrl & APIC_DEST_MASK)) + avic_kick_vcpu(vcpu, icrl); } } @@ -496,14 +480,18 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu) trace_kvm_avic_incomplete_ipi(vcpu->vcpu_id, icrh, icrl, id, index); switch (id) { + case AVIC_IPI_FAILURE_INVALID_TARGET: case AVIC_IPI_FAILURE_INVALID_INT_TYPE: /* * Emulate IPIs that are not handled by AVIC hardware, which - * only virtualizes Fixed, Edge-Triggered INTRs. The exit is - * a trap, e.g. ICR holds the correct value and RIP has been - * advanced, KVM is responsible only for emulating the IPI. - * Sadly, hardware may sometimes leave the BUSY flag set, in - * which case KVM needs to emulate the ICR write as well in + * only virtualizes Fixed, Edge-Triggered INTRs, and falls over + * if _any_ targets are invalid, e.g. if the logical mode mask + * is a superset of running vCPUs. + * + * The exit is a trap, e.g. ICR holds the correct value and RIP + * has been advanced, KVM is responsible only for emulating the + * IPI. Sadly, hardware may sometimes leave the BUSY flag set, + * in which case KVM needs to emulate the ICR write as well in * order to clear the BUSY flag. */ if (icrl & APIC_ICR_BUSY) @@ -519,8 +507,6 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu) */ avic_kick_target_vcpus(vcpu->kvm, apic, icrl, icrh, index); break; - case AVIC_IPI_FAILURE_INVALID_TARGET: - break; case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE: WARN_ONCE(1, "Invalid backing page\n"); break; @@ -541,33 +527,33 @@ unsigned long avic_vcpu_get_apicv_inhibit_reasons(struct kvm_vcpu *vcpu) static u32 *avic_get_logical_id_entry(struct kvm_vcpu *vcpu, u32 ldr, bool flat) { struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm); - int index; u32 *logical_apic_id_table; - int dlid = GET_APIC_LOGICAL_ID(ldr); - - if (!dlid) - return NULL; + u32 cluster, index; - if (flat) { /* flat */ - index = ffs(dlid) - 1; - if (index > 7) - return NULL; - } else { /* cluster */ - int cluster = (dlid & 0xf0) >> 4; - int apic = ffs(dlid & 0x0f) - 1; + ldr = GET_APIC_LOGICAL_ID(ldr); - if ((apic < 0) || (apic > 7) || - (cluster >= 0xf)) + if (flat) { + cluster = 0; + } else { + cluster = (ldr >> 4); + if (cluster >= 0xf) return NULL; - index = (cluster << 2) + apic; + ldr &= 0xf; } + if (!ldr || !is_power_of_2(ldr)) + return NULL; + + index = __ffs(ldr); + if (WARN_ON_ONCE(index > 7)) + return NULL; + index += (cluster << 2); logical_apic_id_table = (u32 *) page_address(kvm_svm->avic_logical_id_table_page); return &logical_apic_id_table[index]; } -static int avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr) +static void avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr) { bool flat; u32 *entry, new_entry; @@ -575,15 +561,13 @@ static int avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr) flat = kvm_lapic_get_reg(vcpu->arch.apic, APIC_DFR) == APIC_DFR_FLAT; entry = avic_get_logical_id_entry(vcpu, ldr, flat); if (!entry) - return -EINVAL; + return; new_entry = READ_ONCE(*entry); new_entry &= ~AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK; new_entry |= (g_physical_id & AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK); new_entry |= AVIC_LOGICAL_ID_ENTRY_VALID_MASK; WRITE_ONCE(*entry, new_entry); - - return 0; } static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu) @@ -601,29 +585,23 @@ static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu) clear_bit(AVIC_LOGICAL_ID_ENTRY_VALID_BIT, (unsigned long *)entry); } -static int avic_handle_ldr_update(struct kvm_vcpu *vcpu) +static void avic_handle_ldr_update(struct kvm_vcpu *vcpu) { - int ret = 0; struct vcpu_svm *svm = to_svm(vcpu); u32 ldr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LDR); u32 id = kvm_xapic_id(vcpu->arch.apic); /* AVIC does not support LDR update for x2APIC */ if (apic_x2apic_mode(vcpu->arch.apic)) - return 0; + return; if (ldr == svm->ldr_reg) - return 0; + return; avic_invalidate_logical_id_entry(vcpu); - if (ldr) - ret = avic_ldr_write(vcpu, id, ldr); - - if (!ret) - svm->ldr_reg = ldr; - - return ret; + svm->ldr_reg = ldr; + avic_ldr_write(vcpu, id, ldr); } static void avic_handle_dfr_update(struct kvm_vcpu *vcpu) @@ -645,12 +623,14 @@ static int avic_unaccel_trap_write(struct kvm_vcpu *vcpu) switch (offset) { case APIC_LDR: - if (avic_handle_ldr_update(vcpu)) - return 0; + avic_handle_ldr_update(vcpu); break; case APIC_DFR: avic_handle_dfr_update(vcpu); break; + case APIC_RRR: + /* Ignore writes to Read Remote Data, it's read-only. */ + return 1; default: break; } @@ -739,18 +719,6 @@ void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu) avic_handle_ldr_update(vcpu); } -void avic_set_virtual_apic_mode(struct kvm_vcpu *vcpu) -{ - if (!lapic_in_kernel(vcpu) || avic_mode == AVIC_MODE_NONE) - return; - - if (kvm_get_apic_mode(vcpu) == LAPIC_MODE_INVALID) { - WARN_ONCE(true, "Invalid local APIC state (vcpu_id=%d)", vcpu->vcpu_id); - return; - } - avic_refresh_apicv_exec_ctrl(vcpu); -} - static int avic_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate) { int ret = 0; @@ -995,23 +963,6 @@ out: return ret; } -bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason) -{ - ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | - BIT(APICV_INHIBIT_REASON_ABSENT) | - BIT(APICV_INHIBIT_REASON_HYPERV) | - BIT(APICV_INHIBIT_REASON_NESTED) | - BIT(APICV_INHIBIT_REASON_IRQWIN) | - BIT(APICV_INHIBIT_REASON_PIT_REINJ) | - BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | - BIT(APICV_INHIBIT_REASON_SEV) | - BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | - BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED); - - return supported & BIT(reason); -} - - static inline int avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r) { @@ -1064,6 +1015,7 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) return; entry = READ_ONCE(*(svm->avic_physical_id_cache)); + WARN_ON_ONCE(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK); entry &= ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK; entry |= (h_physical_id & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK); @@ -1092,17 +1044,15 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu) WRITE_ONCE(*(svm->avic_physical_id_cache), entry); } - -void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) +void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb01.ptr; - bool activated = kvm_vcpu_apicv_active(vcpu); - if (!enable_apicv) + if (!lapic_in_kernel(vcpu) || !enable_apicv) return; - if (activated) { + if (kvm_vcpu_apicv_active(vcpu)) { /** * During AVIC temporary deactivation, guest could update * APIC ID, DFR and LDR registers, which would not be trapped @@ -1116,6 +1066,16 @@ void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) avic_deactivate_vmcb(svm); } vmcb_mark_dirty(vmcb, VMCB_AVIC); +} + +void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) +{ + bool activated = kvm_vcpu_apicv_active(vcpu); + + if (!enable_apicv) + return; + + avic_refresh_virtual_apic_mode(vcpu); if (activated) avic_vcpu_load(vcpu, vcpu->cpu); @@ -1160,37 +1120,37 @@ void avic_vcpu_unblocking(struct kvm_vcpu *vcpu) * - Hypervisor can support both xAVIC and x2AVIC in the same guest. * - The mode can be switched at run-time. */ -bool avic_hardware_setup(struct kvm_x86_ops *x86_ops) +bool avic_hardware_setup(void) { if (!npt_enabled) return false; + /* AVIC is a prerequisite for x2AVIC. */ + if (!boot_cpu_has(X86_FEATURE_AVIC) && !force_avic) { + if (boot_cpu_has(X86_FEATURE_X2AVIC)) { + pr_warn(FW_BUG "Cannot support x2AVIC due to AVIC is disabled"); + pr_warn(FW_BUG "Try enable AVIC using force_avic option"); + } + return false; + } + if (boot_cpu_has(X86_FEATURE_AVIC)) { - avic_mode = AVIC_MODE_X1; pr_info("AVIC enabled\n"); } else if (force_avic) { /* * Some older systems does not advertise AVIC support. * See Revision Guide for specific AMD processor for more detail. */ - avic_mode = AVIC_MODE_X1; pr_warn("AVIC is not supported in CPUID but force enabled"); pr_warn("Your system might crash and burn"); } /* AVIC is a prerequisite for x2AVIC. */ - if (boot_cpu_has(X86_FEATURE_X2AVIC)) { - if (avic_mode == AVIC_MODE_X1) { - avic_mode = AVIC_MODE_X2; - pr_info("x2AVIC enabled\n"); - } else { - pr_warn(FW_BUG "Cannot support x2AVIC due to AVIC is disabled"); - pr_warn(FW_BUG "Try enable AVIC using force_avic option"); - } - } + x2avic_enabled = boot_cpu_has(X86_FEATURE_X2AVIC); + if (x2avic_enabled) + pr_info("x2AVIC enabled\n"); - if (avic_mode != AVIC_MODE_NONE) - amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier); + amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier); - return !!avic_mode; + return true; } diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index add65dd59756..05d38944a6c0 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -12,7 +12,7 @@ * Avi Kivity <avi@qumranet.com> */ -#define pr_fmt(fmt) "SVM: " fmt +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_types.h> #include <linux/kvm_host.h> @@ -1008,7 +1008,6 @@ int nested_svm_vmexit(struct vcpu_svm *svm) vmcb12->control.next_rip = vmcb02->control.next_rip; vmcb12->control.int_ctl = svm->nested.ctl.int_ctl; - vmcb12->control.tlb_ctl = svm->nested.ctl.tlb_ctl; vmcb12->control.event_inj = svm->nested.ctl.event_inj; vmcb12->control.event_inj_err = svm->nested.ctl.event_inj_err; @@ -1104,7 +1103,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm) * to benefit from it right away. */ if (kvm_apicv_activated(vcpu->kvm)) - kvm_vcpu_update_apicv(vcpu); + __kvm_vcpu_update_apicv(vcpu); return 0; } diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 0e313fbae055..cc77a0681800 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -9,6 +9,8 @@ * * Implementation is based on pmu_intel.c file */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/types.h> #include <linux/kvm_host.h> #include <linux/perf_event.h> @@ -229,4 +231,6 @@ struct kvm_pmu_ops amd_pmu_ops __initdata = { .refresh = amd_pmu_refresh, .init = amd_pmu_init, .reset = amd_pmu_reset, + .EVENTSEL_EVENT = AMD64_EVENTSEL_EVENT, + .MAX_NR_GP_COUNTERS = KVM_AMD_PMC_MAX_GENERIC, }; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 86d6897f4806..c25aeb550cd9 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -6,6 +6,7 @@ * * Copyright 2010 Red Hat, Inc. and/or its affiliates. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_types.h> #include <linux/kvm_host.h> @@ -812,7 +813,7 @@ static int __sev_dbg_decrypt_user(struct kvm *kvm, unsigned long paddr, if (!IS_ALIGNED(dst_paddr, 16) || !IS_ALIGNED(paddr, 16) || !IS_ALIGNED(size, 16)) { - tpage = (void *)alloc_page(GFP_KERNEL | __GFP_ZERO); + tpage = (void *)alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!tpage) return -ENOMEM; @@ -1293,7 +1294,7 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) /* Check if we are crossing the page boundary */ offset = params.guest_uaddr & (PAGE_SIZE - 1); - if ((params.guest_len + offset > PAGE_SIZE)) + if (params.guest_len > PAGE_SIZE || (params.guest_len + offset) > PAGE_SIZE) return -EINVAL; /* Pin guest memory */ @@ -1473,7 +1474,7 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) /* Check if we are crossing the page boundary */ offset = params.guest_uaddr & (PAGE_SIZE - 1); - if ((params.guest_len + offset > PAGE_SIZE)) + if (params.guest_len > PAGE_SIZE || (params.guest_len + offset) > PAGE_SIZE) return -EINVAL; hdr = psp_copy_user_blob(params.hdr_uaddr, params.hdr_len); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 60c7c880266b..252e7f37e4e2 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1,4 +1,4 @@ -#define pr_fmt(fmt) "SVM: " fmt +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> @@ -519,21 +519,37 @@ static void svm_init_osvw(struct kvm_vcpu *vcpu) vcpu->arch.osvw.status |= 1; } -static int has_svm(void) +static bool kvm_is_svm_supported(void) { + int cpu = raw_smp_processor_id(); const char *msg; + u64 vm_cr; if (!cpu_has_svm(&msg)) { - printk(KERN_INFO "has_svm: %s\n", msg); - return 0; + pr_err("SVM not supported by CPU %d, %s\n", cpu, msg); + return false; } if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) { pr_info("KVM is unsupported when running as an SEV guest\n"); - return 0; + return false; } - return 1; + rdmsrl(MSR_VM_CR, vm_cr); + if (vm_cr & (1 << SVM_VM_CR_SVM_DISABLE)) { + pr_err("SVM disabled (by BIOS) in MSR_VM_CR on CPU %d\n", cpu); + return false; + } + + return true; +} + +static int svm_check_processor_compat(void) +{ + if (!kvm_is_svm_supported()) + return -EIO; + + return 0; } void __svm_write_tsc_multiplier(u64 multiplier) @@ -572,10 +588,6 @@ static int svm_hardware_enable(void) if (efer & EFER_SVME) return -EBUSY; - if (!has_svm()) { - pr_err("%s: err EOPNOTSUPP on %d\n", __func__, me); - return -EINVAL; - } sd = per_cpu_ptr(&svm_data, me); sd->asid_generation = 1; sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1; @@ -813,7 +825,7 @@ void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept) if (intercept == svm->x2avic_msrs_intercepted) return; - if (avic_mode != AVIC_MODE_X2 || + if (!x2avic_enabled || !apic_x2apic_mode(svm->vcpu.arch.apic)) return; @@ -1326,6 +1338,9 @@ static void __svm_vcpu_reset(struct kvm_vcpu *vcpu) vcpu->arch.microcode_version = 0x01000065; svm->tsc_ratio_msr = kvm_caps.default_tsc_scaling_ratio; + svm->nmi_masked = false; + svm->awaiting_iret_completion = false; + if (sev_es_guest(vcpu->kvm)) sev_es_vcpu_reset(svm); } @@ -2076,7 +2091,7 @@ static void svm_handle_mce(struct kvm_vcpu *vcpu) * Erratum 383 triggered. Guest state is corrupt so kill the * guest. */ - pr_err("KVM: Guest triggered AMD Erratum 383\n"); + pr_err("Guest triggered AMD Erratum 383\n"); kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); @@ -2470,7 +2485,7 @@ static int iret_interception(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); ++vcpu->stat.nmi_window_exits; - vcpu->arch.hflags |= HF_IRET_MASK; + svm->awaiting_iret_completion = true; if (!sev_es_guest(vcpu->kvm)) { svm_clr_intercept(svm, INTERCEPT_IRET); svm->nmi_iret_rip = kvm_rip_read(vcpu); @@ -3003,8 +3018,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_IA32_DEBUGCTLMSR: if (!lbrv) { - vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTL 0x%llx, nop\n", - __func__, data); + kvm_pr_unimpl_wrmsr(vcpu, ecx, data); break; } if (data & DEBUGCTL_RESERVED_BITS) @@ -3033,7 +3047,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_VM_CR: return svm_set_vm_cr(vcpu, data); case MSR_VM_IGNNE: - vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); + kvm_pr_unimpl_wrmsr(vcpu, ecx, data); break; case MSR_AMD64_DE_CFG: { struct kvm_msr_entry msr_entry; @@ -3466,7 +3480,7 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu) if (svm->nmi_l1_to_l2) return; - vcpu->arch.hflags |= HF_NMI_MASK; + svm->nmi_masked = true; if (!sev_es_guest(vcpu->kvm)) svm_set_intercept(svm, INTERCEPT_IRET); ++vcpu->stat.nmi_injections; @@ -3571,7 +3585,6 @@ bool svm_nmi_blocked(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb; - bool ret; if (!gif_set(svm)) return true; @@ -3579,10 +3592,8 @@ bool svm_nmi_blocked(struct kvm_vcpu *vcpu) if (is_guest_mode(vcpu) && nested_exit_on_nmi(svm)) return false; - ret = (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) || - (vcpu->arch.hflags & HF_NMI_MASK); - - return ret; + return (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) || + svm->nmi_masked; } static int svm_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) @@ -3602,7 +3613,7 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu) { - return !!(vcpu->arch.hflags & HF_NMI_MASK); + return to_svm(vcpu)->nmi_masked; } static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) @@ -3610,11 +3621,11 @@ static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) struct vcpu_svm *svm = to_svm(vcpu); if (masked) { - vcpu->arch.hflags |= HF_NMI_MASK; + svm->nmi_masked = true; if (!sev_es_guest(vcpu->kvm)) svm_set_intercept(svm, INTERCEPT_IRET); } else { - vcpu->arch.hflags &= ~HF_NMI_MASK; + svm->nmi_masked = false; if (!sev_es_guest(vcpu->kvm)) svm_clr_intercept(svm, INTERCEPT_IRET); } @@ -3700,7 +3711,7 @@ static void svm_enable_nmi_window(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - if ((vcpu->arch.hflags & (HF_NMI_MASK | HF_IRET_MASK)) == HF_NMI_MASK) + if (svm->nmi_masked && !svm->awaiting_iret_completion) return; /* IRET will cause a vm exit */ if (!gif_set(svm)) { @@ -3824,10 +3835,11 @@ static void svm_complete_interrupts(struct kvm_vcpu *vcpu) * If we've made progress since setting HF_IRET_MASK, we've * executed an IRET and can allow NMI injection. */ - if ((vcpu->arch.hflags & HF_IRET_MASK) && + if (svm->awaiting_iret_completion && (sev_es_guest(vcpu->kvm) || kvm_rip_read(vcpu) != svm->nmi_iret_rip)) { - vcpu->arch.hflags &= ~(HF_NMI_MASK | HF_IRET_MASK); + svm->awaiting_iret_completion = false; + svm->nmi_masked = false; kvm_make_request(KVM_REQ_EVENT, vcpu); } @@ -4076,17 +4088,6 @@ static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, vmcb_mark_dirty(svm->vmcb, VMCB_CR); } -static int is_disabled(void) -{ - u64 vm_cr; - - rdmsrl(MSR_VM_CR, vm_cr); - if (vm_cr & (1 << SVM_VM_CR_SVM_DISABLE)) - return 1; - - return 0; -} - static void svm_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) { @@ -4098,11 +4099,6 @@ svm_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) hypercall[2] = 0xd9; } -static int __init svm_check_processor_compat(void) -{ - return 0; -} - /* * The kvm parameter can be NULL (module initialization, or invocation before * VM creation). Be sure to check the kvm parameter before using it. @@ -4629,7 +4625,7 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, smap = cr4 & X86_CR4_SMAP; is_user = svm_get_cpl(vcpu) == 3; if (smap && (!smep || is_user)) { - pr_err_ratelimited("KVM: SEV Guest triggered AMD Erratum 1096\n"); + pr_err_ratelimited("SEV Guest triggered AMD Erratum 1096\n"); /* * If the fault occurred in userspace, arbitrarily inject #GP @@ -4701,7 +4697,9 @@ static int svm_vm_init(struct kvm *kvm) } static struct kvm_x86_ops svm_x86_ops __initdata = { - .name = "kvm_amd", + .name = KBUILD_MODNAME, + + .check_processor_compatibility = svm_check_processor_compat, .hardware_unsetup = svm_hardware_unsetup, .hardware_enable = svm_hardware_enable, @@ -4771,10 +4769,10 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .enable_nmi_window = svm_enable_nmi_window, .enable_irq_window = svm_enable_irq_window, .update_cr8_intercept = svm_update_cr8_intercept, - .set_virtual_apic_mode = avic_set_virtual_apic_mode, + .set_virtual_apic_mode = avic_refresh_virtual_apic_mode, .refresh_apicv_exec_ctrl = avic_refresh_apicv_exec_ctrl, - .check_apicv_inhibit_reasons = avic_check_apicv_inhibit_reasons, .apicv_post_state_restore = avic_apicv_post_state_restore, + .required_apicv_inhibits = AVIC_REQUIRED_APICV_INHIBITS, .get_exit_info = svm_get_exit_info, @@ -4981,7 +4979,7 @@ static __init int svm_hardware_setup(void) } if (nested) { - printk(KERN_INFO "kvm: Nested Virtualization enabled\n"); + pr_info("Nested Virtualization enabled\n"); kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE); } @@ -4999,7 +4997,7 @@ static __init int svm_hardware_setup(void) /* Force VM NPT level equal to the host's paging level */ kvm_configure_mmu(npt_enabled, get_npt_level(), get_npt_level(), PG_LEVEL_1G); - pr_info("kvm: Nested Paging %sabled\n", npt_enabled ? "en" : "dis"); + pr_info("Nested Paging %sabled\n", npt_enabled ? "en" : "dis"); /* Setup shadow_me_value and shadow_me_mask */ kvm_mmu_set_me_spte_mask(sme_me_mask, sme_me_mask); @@ -5025,12 +5023,14 @@ static __init int svm_hardware_setup(void) nrips = false; } - enable_apicv = avic = avic && avic_hardware_setup(&svm_x86_ops); + enable_apicv = avic = avic && avic_hardware_setup(); if (!enable_apicv) { svm_x86_ops.vcpu_blocking = NULL; svm_x86_ops.vcpu_unblocking = NULL; svm_x86_ops.vcpu_get_apicv_inhibit_reasons = NULL; + } else if (!x2avic_enabled) { + svm_x86_ops.allow_apicv_in_x2apic_without_x2apic_virtualization = true; } if (vls) { @@ -5089,10 +5089,7 @@ err: static struct kvm_x86_init_ops svm_init_ops __initdata = { - .cpu_has_kvm_support = has_svm, - .disabled_by_bios = is_disabled, .hardware_setup = svm_hardware_setup, - .check_processor_compatibility = svm_check_processor_compat, .runtime_ops = &svm_x86_ops, .pmu_ops = &amd_pmu_ops, @@ -5100,15 +5097,37 @@ static struct kvm_x86_init_ops svm_init_ops __initdata = { static int __init svm_init(void) { + int r; + __unused_size_checks(); - return kvm_init(&svm_init_ops, sizeof(struct vcpu_svm), - __alignof__(struct vcpu_svm), THIS_MODULE); + if (!kvm_is_svm_supported()) + return -EOPNOTSUPP; + + r = kvm_x86_vendor_init(&svm_init_ops); + if (r) + return r; + + /* + * Common KVM initialization _must_ come last, after this, /dev/kvm is + * exposed to userspace! + */ + r = kvm_init(sizeof(struct vcpu_svm), __alignof__(struct vcpu_svm), + THIS_MODULE); + if (r) + goto err_kvm_init; + + return 0; + +err_kvm_init: + kvm_x86_vendor_exit(); + return r; } static void __exit svm_exit(void) { kvm_exit(); + kvm_x86_vendor_exit(); } module_init(svm_init) diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 4826e6cc611b..839809972da1 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -35,14 +35,7 @@ extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; extern int vgif; extern bool intercept_smi; - -enum avic_modes { - AVIC_MODE_NONE = 0, - AVIC_MODE_X1, - AVIC_MODE_X2, -}; - -extern enum avic_modes avic_mode; +extern bool x2avic_enabled; /* * Clean bits in VMCB. @@ -237,8 +230,26 @@ struct vcpu_svm { struct svm_nested_state nested; + /* NMI mask value, used when vNMI is not enabled */ + bool nmi_masked; + + /* + * True when NMIs are still masked but guest IRET was just intercepted + * and KVM is waiting for RIP to change, which will signal that the + * intercepted IRET was retired and thus NMI can be unmasked. + */ + bool awaiting_iret_completion; + + /* + * Set when KVM is awaiting IRET completion and needs to inject NMIs as + * soon as the IRET completes (e.g. NMI is pending injection). KVM + * temporarily steals RFLAGS.TF to single-step the guest in this case + * in order to regain control as soon as the NMI-blocking condition + * goes away. + */ bool nmi_singlestep; u64 nmi_singlestep_guest_rflags; + bool nmi_l1_to_l2; unsigned long soft_int_csbase; @@ -280,6 +291,9 @@ struct vcpu_svm { bool guest_state_loaded; bool x2avic_msrs_intercepted; + + /* Guest GIF value, used when vGIF is not enabled */ + bool guest_gif; }; struct svm_cpu_data { @@ -497,7 +511,7 @@ static inline void enable_gif(struct vcpu_svm *svm) if (vmcb) vmcb->control.int_ctl |= V_GIF_MASK; else - svm->vcpu.arch.hflags |= HF_GIF_MASK; + svm->guest_gif = true; } static inline void disable_gif(struct vcpu_svm *svm) @@ -507,7 +521,7 @@ static inline void disable_gif(struct vcpu_svm *svm) if (vmcb) vmcb->control.int_ctl &= ~V_GIF_MASK; else - svm->vcpu.arch.hflags &= ~HF_GIF_MASK; + svm->guest_gif = false; } static inline bool gif_set(struct vcpu_svm *svm) @@ -517,7 +531,7 @@ static inline bool gif_set(struct vcpu_svm *svm) if (vmcb) return !!(vmcb->control.int_ctl & V_GIF_MASK); else - return !!(svm->vcpu.arch.hflags & HF_GIF_MASK); + return svm->guest_gif; } static inline bool nested_npt_enabled(struct vcpu_svm *svm) @@ -628,8 +642,23 @@ void svm_switch_vmcb(struct vcpu_svm *svm, struct kvm_vmcb_info *target_vmcb); extern struct kvm_x86_nested_ops svm_nested_ops; /* avic.c */ - -bool avic_hardware_setup(struct kvm_x86_ops *ops); +#define AVIC_REQUIRED_APICV_INHIBITS \ +( \ + BIT(APICV_INHIBIT_REASON_DISABLE) | \ + BIT(APICV_INHIBIT_REASON_ABSENT) | \ + BIT(APICV_INHIBIT_REASON_HYPERV) | \ + BIT(APICV_INHIBIT_REASON_NESTED) | \ + BIT(APICV_INHIBIT_REASON_IRQWIN) | \ + BIT(APICV_INHIBIT_REASON_PIT_REINJ) | \ + BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | \ + BIT(APICV_INHIBIT_REASON_SEV) | \ + BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) | \ + BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | \ + BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED) | \ + BIT(APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED) \ +) + +bool avic_hardware_setup(void); int avic_ga_log_notifier(u32 ga_tag); void avic_vm_destroy(struct kvm *kvm); int avic_vm_init(struct kvm *kvm); @@ -641,14 +670,13 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu); void avic_vcpu_put(struct kvm_vcpu *vcpu); void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu); void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu); -bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason); int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); void avic_vcpu_blocking(struct kvm_vcpu *vcpu); void avic_vcpu_unblocking(struct kvm_vcpu *vcpu); void avic_ring_doorbell(struct kvm_vcpu *vcpu); unsigned long avic_vcpu_get_apicv_inhibit_reasons(struct kvm_vcpu *vcpu); -void avic_set_virtual_apic_mode(struct kvm_vcpu *vcpu); +void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu); /* sev.c */ diff --git a/arch/x86/kvm/svm/svm_onhyperv.c b/arch/x86/kvm/svm/svm_onhyperv.c index 26a89d0da93e..7af8422d3382 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.c +++ b/arch/x86/kvm/svm/svm_onhyperv.c @@ -2,6 +2,7 @@ /* * KVM L1 hypervisor optimizations on Hyper-V for SVM. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h index 45faf84476ce..cff838f15db5 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.h +++ b/arch/x86/kvm/svm/svm_onhyperv.h @@ -30,11 +30,11 @@ static inline void svm_hv_init_vmcb(struct vmcb *vmcb) hve->hv_enlightenments_control.msr_bitmap = 1; } -static inline void svm_hv_hardware_setup(void) +static inline __init void svm_hv_hardware_setup(void) { if (npt_enabled && ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB) { - pr_info("kvm: Hyper-V enlightened NPT TLB flush enabled\n"); + pr_info(KBUILD_MODNAME ": Hyper-V enlightened NPT TLB flush enabled\n"); svm_x86_ops.tlb_remote_flush = hv_remote_flush_tlb; svm_x86_ops.tlb_remote_flush_with_range = hv_remote_flush_tlb_with_range; @@ -43,7 +43,7 @@ static inline void svm_hv_hardware_setup(void) if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) { int cpu; - pr_info("kvm: Hyper-V Direct TLB Flush enabled\n"); + pr_info(KBUILD_MODNAME ": Hyper-V Direct TLB Flush enabled\n"); for_each_online_cpu(cpu) { struct hv_vp_assist_page *vp_ap = hv_get_vp_assist_page(cpu); @@ -84,7 +84,7 @@ static inline void svm_hv_init_vmcb(struct vmcb *vmcb) { } -static inline void svm_hv_hardware_setup(void) +static inline __init void svm_hv_hardware_setup(void) { } diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index cd2ac9536c99..45162c1bcd8f 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -66,13 +66,13 @@ struct vmcs_config { u64 misc; struct nested_vmx_msrs nested; }; -extern struct vmcs_config vmcs_config; +extern struct vmcs_config vmcs_config __ro_after_init; struct vmx_capability { u32 ept; u32 vpid; }; -extern struct vmx_capability vmx_capability; +extern struct vmx_capability vmx_capability __ro_after_init; static inline bool cpu_has_vmx_basic_inout(void) { diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c index ae03d1fe0355..22daca752797 100644 --- a/arch/x86/kvm/vmx/hyperv.c +++ b/arch/x86/kvm/vmx/hyperv.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/errno.h> #include <linux/smp.h> @@ -361,35 +362,43 @@ enum evmcs_revision { enum evmcs_ctrl_type { EVMCS_EXIT_CTRLS, EVMCS_ENTRY_CTRLS, + EVMCS_EXEC_CTRL, EVMCS_2NDEXEC, + EVMCS_3RDEXEC, EVMCS_PINCTRL, EVMCS_VMFUNC, NR_EVMCS_CTRLS, }; -static const u32 evmcs_unsupported_ctrls[NR_EVMCS_CTRLS][NR_EVMCS_REVISIONS] = { +static const u32 evmcs_supported_ctrls[NR_EVMCS_CTRLS][NR_EVMCS_REVISIONS] = { [EVMCS_EXIT_CTRLS] = { - [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_VMEXIT_CTRL, + [EVMCSv1_LEGACY] = EVMCS1_SUPPORTED_VMEXIT_CTRL, }, [EVMCS_ENTRY_CTRLS] = { - [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_VMENTRY_CTRL, + [EVMCSv1_LEGACY] = EVMCS1_SUPPORTED_VMENTRY_CTRL, + }, + [EVMCS_EXEC_CTRL] = { + [EVMCSv1_LEGACY] = EVMCS1_SUPPORTED_EXEC_CTRL, }, [EVMCS_2NDEXEC] = { - [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_2NDEXEC, + [EVMCSv1_LEGACY] = EVMCS1_SUPPORTED_2NDEXEC & ~SECONDARY_EXEC_TSC_SCALING, + }, + [EVMCS_3RDEXEC] = { + [EVMCSv1_LEGACY] = EVMCS1_SUPPORTED_3RDEXEC, }, [EVMCS_PINCTRL] = { - [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_PINCTRL, + [EVMCSv1_LEGACY] = EVMCS1_SUPPORTED_PINCTRL, }, [EVMCS_VMFUNC] = { - [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_VMFUNC, + [EVMCSv1_LEGACY] = EVMCS1_SUPPORTED_VMFUNC, }, }; -static u32 evmcs_get_unsupported_ctls(enum evmcs_ctrl_type ctrl_type) +static u32 evmcs_get_supported_ctls(enum evmcs_ctrl_type ctrl_type) { enum evmcs_revision evmcs_rev = EVMCSv1_LEGACY; - return evmcs_unsupported_ctrls[ctrl_type][evmcs_rev]; + return evmcs_supported_ctrls[ctrl_type][evmcs_rev]; } static bool evmcs_has_perf_global_ctrl(struct kvm_vcpu *vcpu) @@ -413,7 +422,7 @@ void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 * { u32 ctl_low = (u32)*pdata; u32 ctl_high = (u32)(*pdata >> 32); - u32 unsupported_ctrls; + u32 supported_ctrls; /* * Hyper-V 2016 and 2019 try using these features even when eVMCS @@ -422,27 +431,31 @@ void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 * switch (msr_index) { case MSR_IA32_VMX_EXIT_CTLS: case MSR_IA32_VMX_TRUE_EXIT_CTLS: - unsupported_ctrls = evmcs_get_unsupported_ctls(EVMCS_EXIT_CTRLS); + supported_ctrls = evmcs_get_supported_ctls(EVMCS_EXIT_CTRLS); if (!evmcs_has_perf_global_ctrl(vcpu)) - unsupported_ctrls |= VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; - ctl_high &= ~unsupported_ctrls; + supported_ctrls &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + ctl_high &= supported_ctrls; break; case MSR_IA32_VMX_ENTRY_CTLS: case MSR_IA32_VMX_TRUE_ENTRY_CTLS: - unsupported_ctrls = evmcs_get_unsupported_ctls(EVMCS_ENTRY_CTRLS); + supported_ctrls = evmcs_get_supported_ctls(EVMCS_ENTRY_CTRLS); if (!evmcs_has_perf_global_ctrl(vcpu)) - unsupported_ctrls |= VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; - ctl_high &= ~unsupported_ctrls; + supported_ctrls &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + ctl_high &= supported_ctrls; + break; + case MSR_IA32_VMX_PROCBASED_CTLS: + case MSR_IA32_VMX_TRUE_PROCBASED_CTLS: + ctl_high &= evmcs_get_supported_ctls(EVMCS_EXEC_CTRL); break; case MSR_IA32_VMX_PROCBASED_CTLS2: - ctl_high &= ~evmcs_get_unsupported_ctls(EVMCS_2NDEXEC); + ctl_high &= evmcs_get_supported_ctls(EVMCS_2NDEXEC); break; case MSR_IA32_VMX_TRUE_PINBASED_CTLS: case MSR_IA32_VMX_PINBASED_CTLS: - ctl_high &= ~evmcs_get_unsupported_ctls(EVMCS_PINCTRL); + ctl_high &= evmcs_get_supported_ctls(EVMCS_PINCTRL); break; case MSR_IA32_VMX_VMFUNC: - ctl_low &= ~evmcs_get_unsupported_ctls(EVMCS_VMFUNC); + ctl_low &= evmcs_get_supported_ctls(EVMCS_VMFUNC); break; } @@ -452,7 +465,7 @@ void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 * static bool nested_evmcs_is_valid_controls(enum evmcs_ctrl_type ctrl_type, u32 val) { - return !(val & evmcs_get_unsupported_ctls(ctrl_type)); + return !(val & ~evmcs_get_supported_ctls(ctrl_type)); } int nested_evmcs_check_controls(struct vmcs12 *vmcs12) @@ -461,6 +474,10 @@ int nested_evmcs_check_controls(struct vmcs12 *vmcs12) vmcs12->pin_based_vm_exec_control))) return -EINVAL; + if (CC(!nested_evmcs_is_valid_controls(EVMCS_EXEC_CTRL, + vmcs12->cpu_based_vm_exec_control))) + return -EINVAL; + if (CC(!nested_evmcs_is_valid_controls(EVMCS_2NDEXEC, vmcs12->secondary_vm_exec_control))) return -EINVAL; @@ -488,6 +505,38 @@ int nested_evmcs_check_controls(struct vmcs12 *vmcs12) return 0; } +#if IS_ENABLED(CONFIG_HYPERV) +/* + * KVM on Hyper-V always uses the latest known eVMCSv1 revision, the assumption + * is: in case a feature has corresponding fields in eVMCS described and it was + * exposed in VMX feature MSRs, KVM is free to use it. Warn if KVM meets a + * feature which has no corresponding eVMCS field, this likely means that KVM + * needs to be updated. + */ +#define evmcs_check_vmcs_conf(field, ctrl) \ + do { \ + typeof(vmcs_conf->field) unsupported; \ + \ + unsupported = vmcs_conf->field & ~EVMCS1_SUPPORTED_ ## ctrl; \ + if (unsupported) { \ + pr_warn_once(#field " unsupported with eVMCS: 0x%llx\n",\ + (u64)unsupported); \ + vmcs_conf->field &= EVMCS1_SUPPORTED_ ## ctrl; \ + } \ + } \ + while (0) + +void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) +{ + evmcs_check_vmcs_conf(cpu_based_exec_ctrl, EXEC_CTRL); + evmcs_check_vmcs_conf(pin_based_exec_ctrl, PINCTRL); + evmcs_check_vmcs_conf(cpu_based_2nd_exec_ctrl, 2NDEXEC); + evmcs_check_vmcs_conf(cpu_based_3rd_exec_ctrl, 3RDEXEC); + evmcs_check_vmcs_conf(vmentry_ctrl, VMENTRY_CTRL); + evmcs_check_vmcs_conf(vmexit_ctrl, VMEXIT_CTRL); +} +#endif + int nested_enable_evmcs(struct kvm_vcpu *vcpu, uint16_t *vmcs_version) { diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h index 571e7929d14e..78d17667e7ec 100644 --- a/arch/x86/kvm/vmx/hyperv.h +++ b/arch/x86/kvm/vmx/hyperv.h @@ -48,22 +48,84 @@ DECLARE_STATIC_KEY_FALSE(enable_evmcs); * Currently unsupported in KVM: * GUEST_IA32_RTIT_CTL = 0x00002814, */ -#define EVMCS1_UNSUPPORTED_PINCTRL (PIN_BASED_POSTED_INTR | \ - PIN_BASED_VMX_PREEMPTION_TIMER) -#define EVMCS1_UNSUPPORTED_EXEC_CTRL (CPU_BASED_ACTIVATE_TERTIARY_CONTROLS) -#define EVMCS1_UNSUPPORTED_2NDEXEC \ - (SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | \ - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | \ - SECONDARY_EXEC_APIC_REGISTER_VIRT | \ - SECONDARY_EXEC_ENABLE_PML | \ - SECONDARY_EXEC_ENABLE_VMFUNC | \ - SECONDARY_EXEC_SHADOW_VMCS | \ +#define EVMCS1_SUPPORTED_PINCTRL \ + (PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ + PIN_BASED_EXT_INTR_MASK | \ + PIN_BASED_NMI_EXITING | \ + PIN_BASED_VIRTUAL_NMIS) + +#define EVMCS1_SUPPORTED_EXEC_CTRL \ + (CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ + CPU_BASED_HLT_EXITING | \ + CPU_BASED_CR3_LOAD_EXITING | \ + CPU_BASED_CR3_STORE_EXITING | \ + CPU_BASED_UNCOND_IO_EXITING | \ + CPU_BASED_MOV_DR_EXITING | \ + CPU_BASED_USE_TSC_OFFSETTING | \ + CPU_BASED_MWAIT_EXITING | \ + CPU_BASED_MONITOR_EXITING | \ + CPU_BASED_INVLPG_EXITING | \ + CPU_BASED_RDPMC_EXITING | \ + CPU_BASED_INTR_WINDOW_EXITING | \ + CPU_BASED_CR8_LOAD_EXITING | \ + CPU_BASED_CR8_STORE_EXITING | \ + CPU_BASED_RDTSC_EXITING | \ + CPU_BASED_TPR_SHADOW | \ + CPU_BASED_USE_IO_BITMAPS | \ + CPU_BASED_MONITOR_TRAP_FLAG | \ + CPU_BASED_USE_MSR_BITMAPS | \ + CPU_BASED_NMI_WINDOW_EXITING | \ + CPU_BASED_PAUSE_EXITING | \ + CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) + +#define EVMCS1_SUPPORTED_2NDEXEC \ + (SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ + SECONDARY_EXEC_WBINVD_EXITING | \ + SECONDARY_EXEC_ENABLE_VPID | \ + SECONDARY_EXEC_ENABLE_EPT | \ + SECONDARY_EXEC_UNRESTRICTED_GUEST | \ + SECONDARY_EXEC_DESC | \ + SECONDARY_EXEC_ENABLE_RDTSCP | \ + SECONDARY_EXEC_ENABLE_INVPCID | \ + SECONDARY_EXEC_XSAVES | \ + SECONDARY_EXEC_RDSEED_EXITING | \ + SECONDARY_EXEC_RDRAND_EXITING | \ SECONDARY_EXEC_TSC_SCALING | \ - SECONDARY_EXEC_PAUSE_LOOP_EXITING) -#define EVMCS1_UNSUPPORTED_VMEXIT_CTRL \ - (VM_EXIT_SAVE_VMX_PREEMPTION_TIMER) -#define EVMCS1_UNSUPPORTED_VMENTRY_CTRL (0) -#define EVMCS1_UNSUPPORTED_VMFUNC (VMX_VMFUNC_EPTP_SWITCHING) + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ + SECONDARY_EXEC_PT_USE_GPA | \ + SECONDARY_EXEC_PT_CONCEAL_VMX | \ + SECONDARY_EXEC_BUS_LOCK_DETECTION | \ + SECONDARY_EXEC_NOTIFY_VM_EXITING | \ + SECONDARY_EXEC_ENCLS_EXITING) + +#define EVMCS1_SUPPORTED_3RDEXEC (0ULL) + +#define EVMCS1_SUPPORTED_VMEXIT_CTRL \ + (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | \ + VM_EXIT_SAVE_DEBUG_CONTROLS | \ + VM_EXIT_ACK_INTR_ON_EXIT | \ + VM_EXIT_HOST_ADDR_SPACE_SIZE | \ + VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_EXIT_SAVE_IA32_PAT | \ + VM_EXIT_LOAD_IA32_PAT | \ + VM_EXIT_SAVE_IA32_EFER | \ + VM_EXIT_LOAD_IA32_EFER | \ + VM_EXIT_CLEAR_BNDCFGS | \ + VM_EXIT_PT_CONCEAL_PIP | \ + VM_EXIT_CLEAR_IA32_RTIT_CTL) + +#define EVMCS1_SUPPORTED_VMENTRY_CTRL \ + (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | \ + VM_ENTRY_LOAD_DEBUG_CONTROLS | \ + VM_ENTRY_IA32E_MODE | \ + VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_ENTRY_LOAD_IA32_PAT | \ + VM_ENTRY_LOAD_IA32_EFER | \ + VM_ENTRY_LOAD_BNDCFGS | \ + VM_ENTRY_PT_CONCEAL_PIP | \ + VM_ENTRY_LOAD_IA32_RTIT_CTL) + +#define EVMCS1_SUPPORTED_VMFUNC (0) struct evmcs_field { u16 offset; @@ -117,9 +179,7 @@ static __always_inline int get_evmcs_offset(unsigned long field, { int offset = evmcs_field_offset(field, clean_field); - WARN_ONCE(offset < 0, "KVM: accessing unsupported EVMCS field %lx\n", - field); - + WARN_ONCE(offset < 0, "accessing unsupported EVMCS field %lx\n", field); return offset; } @@ -136,7 +196,7 @@ static __always_inline void evmcs_write64(unsigned long field, u64 value) current_evmcs->hv_clean_fields &= ~clean_field; } -static inline void evmcs_write32(unsigned long field, u32 value) +static __always_inline void evmcs_write32(unsigned long field, u32 value) { u16 clean_field; int offset = get_evmcs_offset(field, &clean_field); @@ -148,7 +208,7 @@ static inline void evmcs_write32(unsigned long field, u32 value) current_evmcs->hv_clean_fields &= ~clean_field; } -static inline void evmcs_write16(unsigned long field, u16 value) +static __always_inline void evmcs_write16(unsigned long field, u16 value) { u16 clean_field; int offset = get_evmcs_offset(field, &clean_field); @@ -160,7 +220,7 @@ static inline void evmcs_write16(unsigned long field, u16 value) current_evmcs->hv_clean_fields &= ~clean_field; } -static inline u64 evmcs_read64(unsigned long field) +static __always_inline u64 evmcs_read64(unsigned long field) { int offset = get_evmcs_offset(field, NULL); @@ -170,7 +230,7 @@ static inline u64 evmcs_read64(unsigned long field) return *(u64 *)((char *)current_evmcs + offset); } -static inline u32 evmcs_read32(unsigned long field) +static __always_inline u32 evmcs_read32(unsigned long field) { int offset = get_evmcs_offset(field, NULL); @@ -180,7 +240,7 @@ static inline u32 evmcs_read32(unsigned long field) return *(u32 *)((char *)current_evmcs + offset); } -static inline u16 evmcs_read16(unsigned long field) +static __always_inline u16 evmcs_read16(unsigned long field) { int offset = get_evmcs_offset(field, NULL); @@ -190,16 +250,6 @@ static inline u16 evmcs_read16(unsigned long field) return *(u16 *)((char *)current_evmcs + offset); } -static inline void evmcs_touch_msr_bitmap(void) -{ - if (unlikely(!current_evmcs)) - return; - - if (current_evmcs->hv_enlightenments_control.msr_bitmap) - current_evmcs->hv_clean_fields &= - ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP; -} - static inline void evmcs_load(u64 phys_addr) { struct hv_vp_assist_page *vp_ap = @@ -211,15 +261,15 @@ static inline void evmcs_load(u64 phys_addr) vp_ap->enlighten_vmentry = 1; } +void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf); #else /* !IS_ENABLED(CONFIG_HYPERV) */ static __always_inline void evmcs_write64(unsigned long field, u64 value) {} -static inline void evmcs_write32(unsigned long field, u32 value) {} -static inline void evmcs_write16(unsigned long field, u16 value) {} -static inline u64 evmcs_read64(unsigned long field) { return 0; } -static inline u32 evmcs_read32(unsigned long field) { return 0; } -static inline u16 evmcs_read16(unsigned long field) { return 0; } +static __always_inline void evmcs_write32(unsigned long field, u32 value) {} +static __always_inline void evmcs_write16(unsigned long field, u16 value) {} +static __always_inline u64 evmcs_read64(unsigned long field) { return 0; } +static __always_inline u32 evmcs_read32(unsigned long field) { return 0; } +static __always_inline u16 evmcs_read16(unsigned long field) { return 0; } static inline void evmcs_load(u64 phys_addr) {} -static inline void evmcs_touch_msr_bitmap(void) {} #endif /* IS_ENABLED(CONFIG_HYPERV) */ #define EVMPTR_INVALID (-1ULL) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index d93c715cda6a..7c4f5ca405c7 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/objtool.h> #include <linux/percpu.h> @@ -203,7 +204,7 @@ static void nested_vmx_abort(struct kvm_vcpu *vcpu, u32 indicator) { /* TODO: not to reset guest simply here. */ kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); - pr_debug_ratelimited("kvm: nested vmx abort, indicator %d\n", indicator); + pr_debug_ratelimited("nested vmx abort, indicator %d\n", indicator); } static inline bool vmx_control_verify(u32 control, u32 low, u32 high) @@ -5863,11 +5864,10 @@ static int handle_vmfunc(struct kvm_vcpu *vcpu) u32 function = kvm_rax_read(vcpu); /* - * VMFUNC is only supported for nested guests, but we always enable the - * secondary control for simplicity; for non-nested mode, fake that we - * didn't by injecting #UD. + * VMFUNC should never execute cleanly while L1 is active; KVM supports + * VMFUNC for nested VMs, but not for L1. */ - if (!is_guest_mode(vcpu)) { + if (WARN_ON_ONCE(!is_guest_mode(vcpu))) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } @@ -6880,6 +6880,7 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_RDRAND_EXITING | SECONDARY_EXEC_ENABLE_INVPCID | + SECONDARY_EXEC_ENABLE_VMFUNC | SECONDARY_EXEC_RDSEED_EXITING | SECONDARY_EXEC_XSAVES | SECONDARY_EXEC_TSC_SCALING | @@ -6912,18 +6913,13 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) SECONDARY_EXEC_ENABLE_PML; msrs->ept_caps |= VMX_EPT_AD_BIT; } - } - if (cpu_has_vmx_vmfunc()) { - msrs->secondary_ctls_high |= - SECONDARY_EXEC_ENABLE_VMFUNC; /* - * Advertise EPTP switching unconditionally - * since we emulate it + * Advertise EPTP switching irrespective of hardware support, + * KVM emulates it in software so long as VMFUNC is supported. */ - if (enable_ept) - msrs->vmfunc_controls = - VMX_VMFUNC_EPTP_SWITCHING; + if (cpu_has_vmx_vmfunc()) + msrs->vmfunc_controls = VMX_VMFUNC_EPTP_SWITCHING; } /* diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index e5cec07ca8d9..e8a3be0b9df9 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -8,6 +8,8 @@ * Avi Kivity <avi@redhat.com> * Gleb Natapov <gleb@redhat.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/types.h> #include <linux/kvm_host.h> #include <linux/perf_event.h> @@ -20,16 +22,19 @@ #define MSR_PMC_FULL_WIDTH_BIT (MSR_IA32_PMC0 - MSR_IA32_PERFCTR0) -static struct kvm_event_hw_type_mapping intel_arch_events[] = { - [0] = { 0x3c, 0x00, PERF_COUNT_HW_CPU_CYCLES }, - [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, - [2] = { 0x3c, 0x01, PERF_COUNT_HW_BUS_CYCLES }, - [3] = { 0x2e, 0x4f, PERF_COUNT_HW_CACHE_REFERENCES }, - [4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES }, - [5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, - [6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, +static struct { + u8 eventsel; + u8 unit_mask; +} const intel_arch_events[] = { + [0] = { 0x3c, 0x00 }, + [1] = { 0xc0, 0x00 }, + [2] = { 0x3c, 0x01 }, + [3] = { 0x2e, 0x4f }, + [4] = { 0x2e, 0x41 }, + [5] = { 0xc4, 0x00 }, + [6] = { 0xc5, 0x00 }, /* The above index must match CPUID 0x0A.EBX bit vector */ - [7] = { 0x00, 0x03, PERF_COUNT_HW_REF_CPU_CYCLES }, + [7] = { 0x00, 0x03 }, }; /* mapping between fixed pmc index and intel_arch_events array */ @@ -762,8 +767,7 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu) return; warn: - pr_warn_ratelimited("kvm: vcpu-%d: fail to passthrough LBR.\n", - vcpu->vcpu_id); + pr_warn_ratelimited("vcpu-%d: fail to passthrough LBR.\n", vcpu->vcpu_id); } static void intel_pmu_cleanup(struct kvm_vcpu *vcpu) @@ -810,4 +814,6 @@ struct kvm_pmu_ops intel_pmu_ops __initdata = { .reset = intel_pmu_reset, .deliver_pmi = intel_pmu_deliver_pmi, .cleanup = intel_pmu_cleanup, + .EVENTSEL_EVENT = ARCH_PERFMON_EVENTSEL_EVENT, + .MAX_NR_GP_COUNTERS = KVM_INTEL_PMC_MAX_GENERIC, }; diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 1b56c5e5c9fb..94c38bea60e7 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -1,4 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kvm_host.h> #include <asm/irq_remapping.h> diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index b12da2a6dec9..aa53c98034bf 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2021 Intel Corporation. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <asm/sgx.h> @@ -164,7 +165,7 @@ static int __handle_encls_ecreate(struct kvm_vcpu *vcpu, if (!vcpu->kvm->arch.sgx_provisioning_allowed && (attributes & SGX_ATTR_PROVISIONKEY)) { if (sgx_12_1->eax & SGX_ATTR_PROVISIONKEY) - pr_warn_once("KVM: SGX PROVISIONKEY advertised but not allowed\n"); + pr_warn_once("SGX PROVISIONKEY advertised but not allowed\n"); kvm_inject_gp(vcpu, 0); return 1; } @@ -381,7 +382,7 @@ int handle_encls(struct kvm_vcpu *vcpu) return handle_encls_ecreate(vcpu); if (leaf == EINIT) return handle_encls_einit(vcpu); - WARN(1, "KVM: unexpected exit on ENCLS[%u]", leaf); + WARN_ONCE(1, "unexpected exit on ENCLS[%u]", leaf); vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; vcpu->run->hw.hardware_exit_reason = EXIT_REASON_ENCLS; return 0; diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h index ac290a44a693..7c1996b433e2 100644 --- a/arch/x86/kvm/vmx/vmcs.h +++ b/arch/x86/kvm/vmx/vmcs.h @@ -75,7 +75,7 @@ struct loaded_vmcs { struct vmcs_controls_shadow controls_shadow; }; -static inline bool is_intr_type(u32 intr_info, u32 type) +static __always_inline bool is_intr_type(u32 intr_info, u32 type) { const u32 mask = INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK; @@ -146,7 +146,7 @@ static inline bool is_icebp(u32 intr_info) return is_intr_type(intr_info, INTR_TYPE_PRIV_SW_EXCEPTION); } -static inline bool is_nmi(u32 intr_info) +static __always_inline bool is_nmi(u32 intr_info) { return is_intr_type(intr_info, INTR_TYPE_NMI_INTR); } diff --git a/arch/x86/kvm/vmx/vmcs12.c b/arch/x86/kvm/vmx/vmcs12.c index 2251b60920f8..106a72c923ca 100644 --- a/arch/x86/kvm/vmx/vmcs12.c +++ b/arch/x86/kvm/vmx/vmcs12.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "vmcs12.h" diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 766c6b3ef5ed..f550540ed54e 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -31,6 +31,39 @@ #define VCPU_R15 __VCPU_REGS_R15 * WORD_SIZE #endif +.macro VMX_DO_EVENT_IRQOFF call_insn call_target + /* + * Unconditionally create a stack frame, getting the correct RSP on the + * stack (for x86-64) would take two instructions anyways, and RBP can + * be used to restore RSP to make objtool happy (see below). + */ + push %_ASM_BP + mov %_ASM_SP, %_ASM_BP + +#ifdef CONFIG_X86_64 + /* + * Align RSP to a 16-byte boundary (to emulate CPU behavior) before + * creating the synthetic interrupt stack frame for the IRQ/NMI. + */ + and $-16, %rsp + push $__KERNEL_DS + push %rbp +#endif + pushf + push $__KERNEL_CS + \call_insn \call_target + + /* + * "Restore" RSP from RBP, even though IRET has already unwound RSP to + * the correct value. objtool doesn't know the callee will IRET and, + * without the explicit restore, thinks the stack is getting walloped. + * Using an unwind hint is problematic due to x86-64's dynamic alignment. + */ + mov %_ASM_BP, %_ASM_SP + pop %_ASM_BP + RET +.endm + .section .noinstr.text, "ax" /** @@ -69,8 +102,8 @@ SYM_FUNC_START(__vmx_vcpu_run) */ push %_ASM_ARG2 - /* Copy @flags to BL, _ASM_ARG3 is volatile. */ - mov %_ASM_ARG3B, %bl + /* Copy @flags to EBX, _ASM_ARG3 is volatile. */ + mov %_ASM_ARG3L, %ebx lea (%_ASM_SP), %_ASM_ARG2 call vmx_update_host_rsp @@ -106,7 +139,7 @@ SYM_FUNC_START(__vmx_vcpu_run) mov (%_ASM_SP), %_ASM_AX /* Check if vmlaunch or vmresume is needed */ - testb $VMX_RUN_VMRESUME, %bl + test $VMX_RUN_VMRESUME, %ebx /* Load guest registers. Don't clobber flags. */ mov VCPU_RCX(%_ASM_AX), %_ASM_CX @@ -128,7 +161,7 @@ SYM_FUNC_START(__vmx_vcpu_run) /* Load guest RAX. This kills the @regs pointer! */ mov VCPU_RAX(%_ASM_AX), %_ASM_AX - /* Check EFLAGS.ZF from 'testb' above */ + /* Check EFLAGS.ZF from 'test VMX_RUN_VMRESUME' above */ jz .Lvmlaunch /* @@ -266,6 +299,10 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) SYM_FUNC_END(__vmx_vcpu_run) +SYM_FUNC_START(vmx_do_nmi_irqoff) + VMX_DO_EVENT_IRQOFF call asm_exc_nmi_kvm_vmx +SYM_FUNC_END(vmx_do_nmi_irqoff) + .section .text, "ax" @@ -320,35 +357,6 @@ SYM_FUNC_START(vmread_error_trampoline) SYM_FUNC_END(vmread_error_trampoline) #endif -SYM_FUNC_START(vmx_do_interrupt_nmi_irqoff) - /* - * Unconditionally create a stack frame, getting the correct RSP on the - * stack (for x86-64) would take two instructions anyways, and RBP can - * be used to restore RSP to make objtool happy (see below). - */ - push %_ASM_BP - mov %_ASM_SP, %_ASM_BP - -#ifdef CONFIG_X86_64 - /* - * Align RSP to a 16-byte boundary (to emulate CPU behavior) before - * creating the synthetic interrupt stack frame for the IRQ/NMI. - */ - and $-16, %rsp - push $__KERNEL_DS - push %rbp -#endif - pushf - push $__KERNEL_CS - CALL_NOSPEC _ASM_ARG1 - - /* - * "Restore" RSP from RBP, even though IRET has already unwound RSP to - * the correct value. objtool doesn't know the callee will IRET and, - * without the explicit restore, thinks the stack is getting walloped. - * Using an unwind hint is problematic due to x86-64's dynamic alignment. - */ - mov %_ASM_BP, %_ASM_SP - pop %_ASM_BP - RET -SYM_FUNC_END(vmx_do_interrupt_nmi_irqoff) +SYM_FUNC_START(vmx_do_interrupt_irqoff) + VMX_DO_EVENT_IRQOFF CALL_NOSPEC _ASM_ARG1 +SYM_FUNC_END(vmx_do_interrupt_irqoff) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 7eec0226d56a..bcac3efcde41 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -12,6 +12,7 @@ * Avi Kivity <avi@qumranet.com> * Yaniv Kamay <yaniv@qumranet.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/highmem.h> #include <linux/hrtimer.h> @@ -444,36 +445,36 @@ void vmread_error(unsigned long field, bool fault) if (fault) kvm_spurious_fault(); else - vmx_insn_failed("kvm: vmread failed: field=%lx\n", field); + vmx_insn_failed("vmread failed: field=%lx\n", field); } noinline void vmwrite_error(unsigned long field, unsigned long value) { - vmx_insn_failed("kvm: vmwrite failed: field=%lx val=%lx err=%u\n", + vmx_insn_failed("vmwrite failed: field=%lx val=%lx err=%u\n", field, value, vmcs_read32(VM_INSTRUCTION_ERROR)); } noinline void vmclear_error(struct vmcs *vmcs, u64 phys_addr) { - vmx_insn_failed("kvm: vmclear failed: %p/%llx err=%u\n", + vmx_insn_failed("vmclear failed: %p/%llx err=%u\n", vmcs, phys_addr, vmcs_read32(VM_INSTRUCTION_ERROR)); } noinline void vmptrld_error(struct vmcs *vmcs, u64 phys_addr) { - vmx_insn_failed("kvm: vmptrld failed: %p/%llx err=%u\n", + vmx_insn_failed("vmptrld failed: %p/%llx err=%u\n", vmcs, phys_addr, vmcs_read32(VM_INSTRUCTION_ERROR)); } noinline void invvpid_error(unsigned long ext, u16 vpid, gva_t gva) { - vmx_insn_failed("kvm: invvpid failed: ext=0x%lx vpid=%u gva=0x%lx\n", + vmx_insn_failed("invvpid failed: ext=0x%lx vpid=%u gva=0x%lx\n", ext, vpid, gva); } noinline void invept_error(unsigned long ext, u64 eptp, gpa_t gpa) { - vmx_insn_failed("kvm: invept failed: ext=0x%lx eptp=%llx gpa=0x%llx\n", + vmx_insn_failed("invept failed: ext=0x%lx eptp=%llx gpa=0x%llx\n", ext, eptp, gpa); } @@ -488,8 +489,8 @@ static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu); static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS); static DEFINE_SPINLOCK(vmx_vpid_lock); -struct vmcs_config vmcs_config; -struct vmx_capability vmx_capability; +struct vmcs_config vmcs_config __ro_after_init; +struct vmx_capability vmx_capability __ro_after_init; #define VMX_SEGMENT_FIELD(seg) \ [VCPU_SREG_##seg] = { \ @@ -523,6 +524,8 @@ static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) static unsigned long host_idt_base; #if IS_ENABLED(CONFIG_HYPERV) +static struct kvm_x86_ops vmx_x86_ops __initdata; + static bool __read_mostly enlightened_vmcs = true; module_param(enlightened_vmcs, bool, 0444); @@ -551,6 +554,71 @@ static int hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu) return 0; } +static __init void hv_init_evmcs(void) +{ + int cpu; + + if (!enlightened_vmcs) + return; + + /* + * Enlightened VMCS usage should be recommended and the host needs + * to support eVMCS v1 or above. + */ + if (ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED && + (ms_hyperv.nested_features & HV_X64_ENLIGHTENED_VMCS_VERSION) >= + KVM_EVMCS_VERSION) { + + /* Check that we have assist pages on all online CPUs */ + for_each_online_cpu(cpu) { + if (!hv_get_vp_assist_page(cpu)) { + enlightened_vmcs = false; + break; + } + } + + if (enlightened_vmcs) { + pr_info("Using Hyper-V Enlightened VMCS\n"); + static_branch_enable(&enable_evmcs); + } + + if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) + vmx_x86_ops.enable_l2_tlb_flush + = hv_enable_l2_tlb_flush; + + } else { + enlightened_vmcs = false; + } +} + +static void hv_reset_evmcs(void) +{ + struct hv_vp_assist_page *vp_ap; + + if (!static_branch_unlikely(&enable_evmcs)) + return; + + /* + * KVM should enable eVMCS if and only if all CPUs have a VP assist + * page, and should reject CPU onlining if eVMCS is enabled the CPU + * doesn't have a VP assist page allocated. + */ + vp_ap = hv_get_vp_assist_page(smp_processor_id()); + if (WARN_ON_ONCE(!vp_ap)) + return; + + /* + * Reset everything to support using non-enlightened VMCS access later + * (e.g. when we reload the module with enlightened_vmcs=0) + */ + vp_ap->nested_control.features.directhypercall = 0; + vp_ap->current_nested_vmcs = 0; + vp_ap->enlighten_vmentry = 0; +} + +#else /* IS_ENABLED(CONFIG_HYPERV) */ +static void hv_init_evmcs(void) {} +static void hv_reset_evmcs(void) {} #endif /* IS_ENABLED(CONFIG_HYPERV) */ /* @@ -1613,8 +1681,8 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu) if (!instr_len) goto rip_updated; - WARN(exit_reason.enclave_mode, - "KVM: skipping instruction after SGX enclave VM-Exit"); + WARN_ONCE(exit_reason.enclave_mode, + "skipping instruction after SGX enclave VM-Exit"); orig_rip = kvm_rip_read(vcpu); rip = orig_rip + instr_len; @@ -2138,9 +2206,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated); if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) { - if (report_ignored_msrs) - vcpu_unimpl(vcpu, "%s: BTF|LBR in IA32_DEBUGCTLMSR 0x%llx, nop\n", - __func__, data); + kvm_pr_unimpl_wrmsr(vcpu, msr_index, data); data &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); invalid &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); } @@ -2448,88 +2514,6 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) } } -static __init int cpu_has_kvm_support(void) -{ - return cpu_has_vmx(); -} - -static __init int vmx_disabled_by_bios(void) -{ - return !boot_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || - !boot_cpu_has(X86_FEATURE_VMX); -} - -static int kvm_cpu_vmxon(u64 vmxon_pointer) -{ - u64 msr; - - cr4_set_bits(X86_CR4_VMXE); - - asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t" - _ASM_EXTABLE(1b, %l[fault]) - : : [vmxon_pointer] "m"(vmxon_pointer) - : : fault); - return 0; - -fault: - WARN_ONCE(1, "VMXON faulted, MSR_IA32_FEAT_CTL (0x3a) = 0x%llx\n", - rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr) ? 0xdeadbeef : msr); - cr4_clear_bits(X86_CR4_VMXE); - - return -EFAULT; -} - -static int vmx_hardware_enable(void) -{ - int cpu = raw_smp_processor_id(); - u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); - int r; - - if (cr4_read_shadow() & X86_CR4_VMXE) - return -EBUSY; - - /* - * This can happen if we hot-added a CPU but failed to allocate - * VP assist page for it. - */ - if (static_branch_unlikely(&enable_evmcs) && - !hv_get_vp_assist_page(cpu)) - return -EFAULT; - - intel_pt_handle_vmx(1); - - r = kvm_cpu_vmxon(phys_addr); - if (r) { - intel_pt_handle_vmx(0); - return r; - } - - if (enable_ept) - ept_sync_global(); - - return 0; -} - -static void vmclear_local_loaded_vmcss(void) -{ - int cpu = raw_smp_processor_id(); - struct loaded_vmcs *v, *n; - - list_for_each_entry_safe(v, n, &per_cpu(loaded_vmcss_on_cpu, cpu), - loaded_vmcss_on_cpu_link) - __loaded_vmcs_clear(v); -} - -static void vmx_hardware_disable(void) -{ - vmclear_local_loaded_vmcss(); - - if (cpu_vmxoff()) - kvm_spurious_fault(); - - intel_pt_handle_vmx(0); -} - /* * There is no X86_FEATURE for SGX yet, but anyway we need to query CPUID * directly instead of going through cpu_has(), to ensure KVM is trapping @@ -2565,8 +2549,7 @@ static bool cpu_has_perf_global_ctrl_bug(void) return false; } -static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, - u32 msr, u32 *result) +static int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, u32 msr, u32 *result) { u32 vmx_msr_low, vmx_msr_high; u32 ctl = ctl_min | ctl_opt; @@ -2584,7 +2567,7 @@ static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, return 0; } -static __init u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr) +static u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr) { u64 allowed; @@ -2593,8 +2576,8 @@ static __init u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr) return ctl_opt & allowed; } -static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, - struct vmx_capability *vmx_cap) +static int setup_vmcs_config(struct vmcs_config *vmcs_conf, + struct vmx_capability *vmx_cap) { u32 vmx_msr_low, vmx_msr_high; u32 _pin_based_exec_control = 0; @@ -2752,9 +2735,127 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, vmcs_conf->vmentry_ctrl = _vmentry_control; vmcs_conf->misc = misc_msr; +#if IS_ENABLED(CONFIG_HYPERV) + if (enlightened_vmcs) + evmcs_sanitize_exec_ctrls(vmcs_conf); +#endif + + return 0; +} + +static bool kvm_is_vmx_supported(void) +{ + int cpu = raw_smp_processor_id(); + + if (!cpu_has_vmx()) { + pr_err("VMX not supported by CPU %d\n", cpu); + return false; + } + + if (!this_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || + !this_cpu_has(X86_FEATURE_VMX)) { + pr_err("VMX not enabled (by BIOS) in MSR_IA32_FEAT_CTL on CPU %d\n", cpu); + return false; + } + + return true; +} + +static int vmx_check_processor_compat(void) +{ + int cpu = raw_smp_processor_id(); + struct vmcs_config vmcs_conf; + struct vmx_capability vmx_cap; + + if (!kvm_is_vmx_supported()) + return -EIO; + + if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) { + pr_err("Failed to setup VMCS config on CPU %d\n", cpu); + return -EIO; + } + if (nested) + nested_vmx_setup_ctls_msrs(&vmcs_conf, vmx_cap.ept); + if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config))) { + pr_err("Inconsistent VMCS config on CPU %d\n", cpu); + return -EIO; + } + return 0; +} + +static int kvm_cpu_vmxon(u64 vmxon_pointer) +{ + u64 msr; + + cr4_set_bits(X86_CR4_VMXE); + + asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t" + _ASM_EXTABLE(1b, %l[fault]) + : : [vmxon_pointer] "m"(vmxon_pointer) + : : fault); + return 0; + +fault: + WARN_ONCE(1, "VMXON faulted, MSR_IA32_FEAT_CTL (0x3a) = 0x%llx\n", + rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr) ? 0xdeadbeef : msr); + cr4_clear_bits(X86_CR4_VMXE); + + return -EFAULT; +} + +static int vmx_hardware_enable(void) +{ + int cpu = raw_smp_processor_id(); + u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); + int r; + + if (cr4_read_shadow() & X86_CR4_VMXE) + return -EBUSY; + + /* + * This can happen if we hot-added a CPU but failed to allocate + * VP assist page for it. + */ + if (static_branch_unlikely(&enable_evmcs) && + !hv_get_vp_assist_page(cpu)) + return -EFAULT; + + intel_pt_handle_vmx(1); + + r = kvm_cpu_vmxon(phys_addr); + if (r) { + intel_pt_handle_vmx(0); + return r; + } + + if (enable_ept) + ept_sync_global(); + return 0; } +static void vmclear_local_loaded_vmcss(void) +{ + int cpu = raw_smp_processor_id(); + struct loaded_vmcs *v, *n; + + list_for_each_entry_safe(v, n, &per_cpu(loaded_vmcss_on_cpu, cpu), + loaded_vmcss_on_cpu_link) + __loaded_vmcs_clear(v); +} + +static void vmx_hardware_disable(void) +{ + vmclear_local_loaded_vmcss(); + + if (cpu_vmxoff()) + kvm_spurious_fault(); + + hv_reset_evmcs(); + + intel_pt_handle_vmx(0); +} + struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) { int node = cpu_to_node(cpu); @@ -2950,9 +3051,8 @@ static void fix_rmode_seg(int seg, struct kvm_segment *save) var.type = 0x3; var.avl = 0; if (save->base & 0xf) - printk_once(KERN_WARNING "kvm: segment base is not " - "paragraph aligned when entering " - "protected mode (seg=%d)", seg); + pr_warn_once("segment base is not paragraph aligned " + "when entering protected mode (seg=%d)", seg); } vmcs_write16(sf->selector, var.selector); @@ -2982,8 +3082,7 @@ static void enter_rmode(struct kvm_vcpu *vcpu) * vcpu. Warn the user that an update is overdue. */ if (!kvm_vmx->tss_addr) - printk_once(KERN_WARNING "kvm: KVM_SET_TSS_ADDR need to be " - "called before entering vcpu\n"); + pr_warn_once("KVM_SET_TSS_ADDR needs to be called before running vCPU\n"); vmx_segment_cache_clear(vmx); @@ -3800,39 +3899,6 @@ static void seg_setup(int seg) vmcs_write32(sf->ar_bytes, ar); } -static int alloc_apic_access_page(struct kvm *kvm) -{ - struct page *page; - void __user *hva; - int ret = 0; - - mutex_lock(&kvm->slots_lock); - if (kvm->arch.apic_access_memslot_enabled) - goto out; - hva = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, - APIC_DEFAULT_PHYS_BASE, PAGE_SIZE); - if (IS_ERR(hva)) { - ret = PTR_ERR(hva); - goto out; - } - - page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); - if (is_error_page(page)) { - ret = -EFAULT; - goto out; - } - - /* - * Do not pin the page in memory, so that memory hot-unplug - * is able to migrate it. - */ - put_page(page); - kvm->arch.apic_access_memslot_enabled = true; -out: - mutex_unlock(&kvm->slots_lock); - return ret; -} - int allocate_vpid(void) { int vpid; @@ -3865,8 +3931,13 @@ static void vmx_msr_bitmap_l01_changed(struct vcpu_vmx *vmx) * 'Enlightened MSR Bitmap' feature L0 needs to know that MSR * bitmap has changed. */ - if (static_branch_unlikely(&enable_evmcs)) - evmcs_touch_msr_bitmap(); + if (IS_ENABLED(CONFIG_HYPERV) && static_branch_unlikely(&enable_evmcs)) { + struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs; + + if (evmcs->hv_enlightenments_control.msr_bitmap) + evmcs->hv_clean_fields &= + ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP; + } vmx->nested.force_msr_bitmap_recalc = true; } @@ -3947,29 +4018,20 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) vmx_set_msr_bitmap_write(msr_bitmap, msr); } -static void vmx_reset_x2apic_msrs(struct kvm_vcpu *vcpu, u8 mode) -{ - unsigned long *msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap; - unsigned long read_intercept; - int msr; - - read_intercept = (mode & MSR_BITMAP_MODE_X2APIC_APICV) ? 0 : ~0; - - for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { - unsigned int read_idx = msr / BITS_PER_LONG; - unsigned int write_idx = read_idx + (0x800 / sizeof(long)); - - msr_bitmap[read_idx] = read_intercept; - msr_bitmap[write_idx] = ~0ul; - } -} - static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu) { + /* + * x2APIC indices for 64-bit accesses into the RDMSR and WRMSR halves + * of the MSR bitmap. KVM emulates APIC registers up through 0x3f0, + * i.e. MSR 0x83f, and so only needs to dynamically manipulate 64 bits. + */ + const int read_idx = APIC_BASE_MSR / BITS_PER_LONG_LONG; + const int write_idx = read_idx + (0x800 / sizeof(u64)); struct vcpu_vmx *vmx = to_vmx(vcpu); + u64 *msr_bitmap = (u64 *)vmx->vmcs01.msr_bitmap; u8 mode; - if (!cpu_has_vmx_msr_bitmap()) + if (!cpu_has_vmx_msr_bitmap() || WARN_ON_ONCE(!lapic_in_kernel(vcpu))) return; if (cpu_has_secondary_exec_ctrls() && @@ -3987,7 +4049,18 @@ static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu) vmx->x2apic_msr_bitmap_mode = mode; - vmx_reset_x2apic_msrs(vcpu, mode); + /* + * Reset the bitmap for MSRs 0x800 - 0x83f. Leave AMD's uber-extended + * registers (0x840 and above) intercepted, KVM doesn't support them. + * Intercept all writes by default and poke holes as needed. Pass + * through reads for all valid registers by default in x2APIC+APICv + * mode, only the current timer count needs on-demand emulation by KVM. + */ + if (mode & MSR_BITMAP_MODE_X2APIC_APICV) + msr_bitmap[read_idx] = ~kvm_lapic_readable_reg_mask(vcpu->arch.apic); + else + msr_bitmap[read_idx] = ~0ull; + msr_bitmap[write_idx] = ~0ull; /* * TPR reads and writes can be virtualized even if virtual interrupt @@ -4519,6 +4592,12 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; + /* + * KVM doesn't support VMFUNC for L1, but the control is set in KVM's + * base configuration as KVM emulates VMFUNC[EPTP_SWITCHING] for L2. + */ + exec_control &= ~SECONDARY_EXEC_ENABLE_VMFUNC; + /* SECONDARY_EXEC_DESC is enabled/disabled on writes to CR4.UMIP, * in vmx_set_cr4. */ exec_control &= ~SECONDARY_EXEC_DESC; @@ -4535,7 +4614,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) * it needs to be set here when dirty logging is already active, e.g. * if this vCPU was created after dirty logging was enabled. */ - if (!vcpu->kvm->arch.cpu_dirty_logging_count) + if (!enable_pml || !atomic_read(&vcpu->kvm->nr_memslots_dirty_logging)) exec_control &= ~SECONDARY_EXEC_ENABLE_PML; if (cpu_has_vmx_xsaves()) { @@ -5099,8 +5178,13 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) vect_info = vmx->idt_vectoring_info; intr_info = vmx_get_intr_info(vcpu); + /* + * Machine checks are handled by handle_exception_irqoff(), or by + * vmx_vcpu_run() if a #MC occurs on VM-Entry. NMIs are handled by + * vmx_vcpu_enter_exit(). + */ if (is_machine_check(intr_info) || is_nmi(intr_info)) - return 1; /* handled by handle_exception_nmi_irqoff() */ + return 1; /* * Queue the exception here instead of in handle_nm_fault_irqoff(). @@ -6790,17 +6874,8 @@ static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu) memset(vmx->pi_desc.pir, 0, sizeof(vmx->pi_desc.pir)); } -void vmx_do_interrupt_nmi_irqoff(unsigned long entry); - -static void handle_interrupt_nmi_irqoff(struct kvm_vcpu *vcpu, - unsigned long entry) -{ - bool is_nmi = entry == (unsigned long)asm_exc_nmi_noist; - - kvm_before_interrupt(vcpu, is_nmi ? KVM_HANDLING_NMI : KVM_HANDLING_IRQ); - vmx_do_interrupt_nmi_irqoff(entry); - kvm_after_interrupt(vcpu); -} +void vmx_do_interrupt_irqoff(unsigned long entry); +void vmx_do_nmi_irqoff(void); static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu) { @@ -6822,9 +6897,8 @@ static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu) rdmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); } -static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx) +static void handle_exception_irqoff(struct vcpu_vmx *vmx) { - const unsigned long nmi_entry = (unsigned long)asm_exc_nmi_noist; u32 intr_info = vmx_get_intr_info(&vmx->vcpu); /* if exit due to PF check for async PF */ @@ -6836,9 +6910,6 @@ static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx) /* Handle machine checks before interrupts are enabled */ else if (is_machine_check(intr_info)) kvm_machine_check(); - /* We need to handle NMIs before interrupts are enabled */ - else if (is_nmi(intr_info)) - handle_interrupt_nmi_irqoff(&vmx->vcpu, nmi_entry); } static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) @@ -6848,10 +6919,13 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) gate_desc *desc = (gate_desc *)host_idt_base + vector; if (KVM_BUG(!is_external_intr(intr_info), vcpu->kvm, - "KVM: unexpected VM-Exit interrupt info: 0x%x", intr_info)) + "unexpected VM-Exit interrupt info: 0x%x", intr_info)) return; - handle_interrupt_nmi_irqoff(vcpu, gate_offset(desc)); + kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ); + vmx_do_interrupt_irqoff(gate_offset(desc)); + kvm_after_interrupt(vcpu); + vcpu->arch.at_instruction_boundary = true; } @@ -6865,7 +6939,7 @@ static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) if (vmx->exit_reason.basic == EXIT_REASON_EXTERNAL_INTERRUPT) handle_external_interrupt_irqoff(vcpu); else if (vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI) - handle_exception_nmi_irqoff(vmx); + handle_exception_irqoff(vmx); } /* @@ -7100,9 +7174,10 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) } static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, - struct vcpu_vmx *vmx, - unsigned long flags) + unsigned int flags) { + struct vcpu_vmx *vmx = to_vmx(vcpu); + guest_state_enter_irqoff(); /* L1D Flush includes CPU buffer clear to mitigate MDS */ @@ -7126,6 +7201,18 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, vmx_enable_fb_clear(vmx); + if (unlikely(vmx->fail)) + vmx->exit_reason.full = 0xdead; + else + vmx->exit_reason.full = vmcs_read32(VM_EXIT_REASON); + + if ((u16)vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI && + is_nmi(vmx_get_intr_info(vcpu))) { + kvm_before_interrupt(vcpu, KVM_HANDLING_NMI); + vmx_do_nmi_irqoff(); + kvm_after_interrupt(vcpu); + } + guest_state_exit_irqoff(); } @@ -7220,7 +7307,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) kvm_wait_lapic_expire(vcpu); /* The actual VMENTER/EXIT is in the .noinstr.text section. */ - vmx_vcpu_enter_exit(vcpu, vmx, __vmx_vcpu_run_flags(vmx)); + vmx_vcpu_enter_exit(vcpu, __vmx_vcpu_run_flags(vmx)); /* All fields are clean at this point */ if (static_branch_unlikely(&enable_evmcs)) { @@ -7267,12 +7354,9 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->idt_vectoring_info = 0; - if (unlikely(vmx->fail)) { - vmx->exit_reason.full = 0xdead; + if (unlikely(vmx->fail)) return EXIT_FASTPATH_NONE; - } - vmx->exit_reason.full = vmcs_read32(VM_EXIT_REASON); if (unlikely((u16)vmx->exit_reason.basic == EXIT_REASON_MCE_DURING_VMENTRY)) kvm_machine_check(); @@ -7386,7 +7470,7 @@ static int vmx_vcpu_create(struct kvm_vcpu *vcpu) vmx->loaded_vmcs = &vmx->vmcs01; if (cpu_need_virtualize_apic_accesses(vcpu)) { - err = alloc_apic_access_page(vcpu->kvm); + err = kvm_alloc_apic_access_page(vcpu->kvm); if (err) goto free_vmcs; } @@ -7446,29 +7530,6 @@ static int vmx_vm_init(struct kvm *kvm) return 0; } -static int __init vmx_check_processor_compat(void) -{ - struct vmcs_config vmcs_conf; - struct vmx_capability vmx_cap; - - if (!this_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || - !this_cpu_has(X86_FEATURE_VMX)) { - pr_err("kvm: VMX is disabled on CPU %d\n", smp_processor_id()); - return -EIO; - } - - if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) - return -EIO; - if (nested) - nested_vmx_setup_ctls_msrs(&vmcs_conf, vmx_cap.ept); - if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) { - printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n", - smp_processor_id()); - return -EIO; - } - return 0; -} - static u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { u8 cache; @@ -7940,17 +8001,20 @@ void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + if (WARN_ON_ONCE(!enable_pml)) + return; + if (is_guest_mode(vcpu)) { vmx->nested.update_vmcs01_cpu_dirty_logging = true; return; } /* - * Note, cpu_dirty_logging_count can be changed concurrent with this + * Note, nr_memslots_dirty_logging can be changed concurrent with this * code, but in that case another update request will be made and so * the guest will never run with a stale PML value. */ - if (vcpu->kvm->arch.cpu_dirty_logging_count) + if (atomic_read(&vcpu->kvm->nr_memslots_dirty_logging)) secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_ENABLE_PML); else secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_ENABLE_PML); @@ -8048,17 +8112,16 @@ static void vmx_hardware_unsetup(void) free_kvm_area(); } -static bool vmx_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason) -{ - ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | - BIT(APICV_INHIBIT_REASON_ABSENT) | - BIT(APICV_INHIBIT_REASON_HYPERV) | - BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | - BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | - BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED); - - return supported & BIT(reason); -} +#define VMX_REQUIRED_APICV_INHIBITS \ +( \ + BIT(APICV_INHIBIT_REASON_DISABLE)| \ + BIT(APICV_INHIBIT_REASON_ABSENT) | \ + BIT(APICV_INHIBIT_REASON_HYPERV) | \ + BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | \ + BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) | \ + BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | \ + BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED) \ +) static void vmx_vm_destroy(struct kvm *kvm) { @@ -8068,7 +8131,9 @@ static void vmx_vm_destroy(struct kvm *kvm) } static struct kvm_x86_ops vmx_x86_ops __initdata = { - .name = "kvm_intel", + .name = KBUILD_MODNAME, + + .check_processor_compatibility = vmx_check_processor_compat, .hardware_unsetup = vmx_hardware_unsetup, @@ -8142,7 +8207,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, .load_eoi_exitmap = vmx_load_eoi_exitmap, .apicv_post_state_restore = vmx_apicv_post_state_restore, - .check_apicv_inhibit_reasons = vmx_check_apicv_inhibit_reasons, + .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, @@ -8288,7 +8353,7 @@ static __init int hardware_setup(void) return -EIO; if (cpu_has_perf_global_ctrl_bug()) - pr_warn_once("kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL " + pr_warn_once("VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL " "does not work properly. Using workaround\n"); if (boot_cpu_has(X86_FEATURE_NX)) @@ -8296,7 +8361,7 @@ static __init int hardware_setup(void) if (boot_cpu_has(X86_FEATURE_MPX)) { rdmsrl(MSR_IA32_BNDCFGS, host_bndcfgs); - WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost"); + WARN_ONCE(host_bndcfgs, "BNDCFGS in host will be lost"); } if (!cpu_has_vmx_mpx()) @@ -8315,7 +8380,7 @@ static __init int hardware_setup(void) /* NX support is required for shadow paging. */ if (!enable_ept && !boot_cpu_has(X86_FEATURE_NX)) { - pr_err_ratelimited("kvm: NX (Execute Disable) not supported\n"); + pr_err_ratelimited("NX (Execute Disable) not supported\n"); return -EOPNOTSUPP; } @@ -8467,9 +8532,6 @@ static __init int hardware_setup(void) } static struct kvm_x86_init_ops vmx_init_ops __initdata = { - .cpu_has_kvm_support = cpu_has_kvm_support, - .disabled_by_bios = vmx_disabled_by_bios, - .check_processor_compatibility = vmx_check_processor_compat, .hardware_setup = hardware_setup, .handle_intel_pt_intr = NULL, @@ -8487,41 +8549,23 @@ static void vmx_cleanup_l1d_flush(void) l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; } -static void vmx_exit(void) +static void __vmx_exit(void) { + allow_smaller_maxphyaddr = false; + #ifdef CONFIG_KEXEC_CORE RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL); synchronize_rcu(); #endif + vmx_cleanup_l1d_flush(); +} +static void vmx_exit(void) +{ kvm_exit(); + kvm_x86_vendor_exit(); -#if IS_ENABLED(CONFIG_HYPERV) - if (static_branch_unlikely(&enable_evmcs)) { - int cpu; - struct hv_vp_assist_page *vp_ap; - /* - * Reset everything to support using non-enlightened VMCS - * access later (e.g. when we reload the module with - * enlightened_vmcs=0) - */ - for_each_online_cpu(cpu) { - vp_ap = hv_get_vp_assist_page(cpu); - - if (!vp_ap) - continue; - - vp_ap->nested_control.features.directhypercall = 0; - vp_ap->current_nested_vmcs = 0; - vp_ap->enlighten_vmentry = 0; - } - - static_branch_disable(&enable_evmcs); - } -#endif - vmx_cleanup_l1d_flush(); - - allow_smaller_maxphyaddr = false; + __vmx_exit(); } module_exit(vmx_exit); @@ -8529,56 +8573,29 @@ static int __init vmx_init(void) { int r, cpu; -#if IS_ENABLED(CONFIG_HYPERV) + if (!kvm_is_vmx_supported()) + return -EOPNOTSUPP; + /* - * Enlightened VMCS usage should be recommended and the host needs - * to support eVMCS v1 or above. We can also disable eVMCS support - * with module parameter. + * Note, hv_init_evmcs() touches only VMX knobs, i.e. there's nothing + * to unwind if a later step fails. */ - if (enlightened_vmcs && - ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED && - (ms_hyperv.nested_features & HV_X64_ENLIGHTENED_VMCS_VERSION) >= - KVM_EVMCS_VERSION) { - - /* Check that we have assist pages on all online CPUs */ - for_each_online_cpu(cpu) { - if (!hv_get_vp_assist_page(cpu)) { - enlightened_vmcs = false; - break; - } - } + hv_init_evmcs(); - if (enlightened_vmcs) { - pr_info("KVM: vmx: using Hyper-V Enlightened VMCS\n"); - static_branch_enable(&enable_evmcs); - } - - if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) - vmx_x86_ops.enable_l2_tlb_flush - = hv_enable_l2_tlb_flush; - - } else { - enlightened_vmcs = false; - } -#endif - - r = kvm_init(&vmx_init_ops, sizeof(struct vcpu_vmx), - __alignof__(struct vcpu_vmx), THIS_MODULE); + r = kvm_x86_vendor_init(&vmx_init_ops); if (r) return r; /* - * Must be called after kvm_init() so enable_ept is properly set + * Must be called after common x86 init so enable_ept is properly set * up. Hand the parameter mitigation value in which was stored in * the pre module init parser. If no parameter was given, it will * contain 'auto' which will be turned into the default 'cond' * mitigation mode. */ r = vmx_setup_l1d_flush(vmentry_l1d_flush_param); - if (r) { - vmx_exit(); - return r; - } + if (r) + goto err_l1d_flush; vmx_setup_fb_clear_ctrl(); @@ -8602,6 +8619,21 @@ static int __init vmx_init(void) if (!enable_ept) allow_smaller_maxphyaddr = true; + /* + * Common KVM initialization _must_ come last, after this, /dev/kvm is + * exposed to userspace! + */ + r = kvm_init(sizeof(struct vcpu_vmx), __alignof__(struct vcpu_vmx), + THIS_MODULE); + if (r) + goto err_kvm_init; + return 0; + +err_kvm_init: + __vmx_exit(); +err_l1d_flush: + kvm_x86_vendor_exit(); + return r; } module_init(vmx_init); diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index a3da84f4ea45..2acdc54bc34b 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -640,12 +640,12 @@ BUILD_CONTROLS_SHADOW(tertiary_exec, TERTIARY_VM_EXEC_CONTROL, 64) (1 << VCPU_EXREG_EXIT_INFO_1) | \ (1 << VCPU_EXREG_EXIT_INFO_2)) -static inline struct kvm_vmx *to_kvm_vmx(struct kvm *kvm) +static __always_inline struct kvm_vmx *to_kvm_vmx(struct kvm *kvm) { return container_of(kvm, struct kvm_vmx, kvm); } -static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) +static __always_inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) { return container_of(vcpu, struct vcpu_vmx, vcpu); } @@ -669,25 +669,23 @@ void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu); int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu); void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu); -static inline unsigned long vmx_get_exit_qual(struct kvm_vcpu *vcpu) +static __always_inline unsigned long vmx_get_exit_qual(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!kvm_register_is_available(vcpu, VCPU_EXREG_EXIT_INFO_1)) { - kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1); + if (!kvm_register_test_and_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1)) vmx->exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - } + return vmx->exit_qualification; } -static inline u32 vmx_get_intr_info(struct kvm_vcpu *vcpu) +static __always_inline u32 vmx_get_intr_info(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!kvm_register_is_available(vcpu, VCPU_EXREG_EXIT_INFO_2)) { - kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2); + if (!kvm_register_test_and_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2)) vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - } + return vmx->exit_intr_info; } diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index 842dc898c972..db95bde52998 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -100,8 +100,10 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field) return value; do_fail: - WARN_ONCE(1, "kvm: vmread failed: field=%lx\n", field); - pr_warn_ratelimited("kvm: vmread failed: field=%lx\n", field); + instrumentation_begin(); + WARN_ONCE(1, KBUILD_MODNAME ": vmread failed: field=%lx\n", field); + pr_warn_ratelimited(KBUILD_MODNAME ": vmread failed: field=%lx\n", field); + instrumentation_end(); return 0; do_exception: diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0735fbc9ba8c..7713420abab0 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -15,6 +15,7 @@ * Amit Shah <amit.shah@qumranet.com> * Ben-Ami Yassour <benami@il.ibm.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include "irq.h" @@ -128,6 +129,7 @@ static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu); static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); +static DEFINE_MUTEX(vendor_module_lock); struct kvm_x86_ops kvm_x86_ops __read_mostly; #define KVM_X86_OP(func) \ @@ -1421,7 +1423,7 @@ EXPORT_SYMBOL_GPL(kvm_emulate_rdpmc); * may depend on host virtualization features rather than host cpu features. */ -static const u32 msrs_to_save_all[] = { +static const u32 msrs_to_save_base[] = { MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_STAR, #ifdef CONFIG_X86_64 @@ -1438,6 +1440,10 @@ static const u32 msrs_to_save_all[] = { MSR_IA32_RTIT_ADDR3_A, MSR_IA32_RTIT_ADDR3_B, MSR_IA32_UMWAIT_CONTROL, + MSR_IA32_XFD, MSR_IA32_XFD_ERR, +}; + +static const u32 msrs_to_save_pmu[] = { MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1, MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS, @@ -1462,11 +1468,10 @@ static const u32 msrs_to_save_all[] = { MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5, MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2, MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5, - - MSR_IA32_XFD, MSR_IA32_XFD_ERR, }; -static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)]; +static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_base) + + ARRAY_SIZE(msrs_to_save_pmu)]; static unsigned num_msrs_to_save; static const u32 emulated_msrs_all[] = { @@ -1484,7 +1489,7 @@ static const u32 emulated_msrs_all[] = { HV_X64_MSR_STIMER0_CONFIG, HV_X64_MSR_VP_ASSIST_PAGE, HV_X64_MSR_REENLIGHTENMENT_CONTROL, HV_X64_MSR_TSC_EMULATION_CONTROL, - HV_X64_MSR_TSC_EMULATION_STATUS, + HV_X64_MSR_TSC_EMULATION_STATUS, HV_X64_MSR_TSC_INVARIANT_CONTROL, HV_X64_MSR_SYNDBG_OPTIONS, HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS, HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER, @@ -2093,7 +2098,7 @@ static int kvm_emulate_monitor_mwait(struct kvm_vcpu *vcpu, const char *insn) !guest_cpuid_has(vcpu, X86_FEATURE_MWAIT)) return kvm_handle_invalid_op(vcpu); - pr_warn_once("kvm: %s instruction emulated as NOP!\n", insn); + pr_warn_once("%s instruction emulated as NOP!\n", insn); return kvm_emulate_as_nop(vcpu); } int kvm_emulate_mwait(struct kvm_vcpu *vcpu) @@ -2440,7 +2445,8 @@ static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz) thresh_lo = adjust_tsc_khz(tsc_khz, -tsc_tolerance_ppm); thresh_hi = adjust_tsc_khz(tsc_khz, tsc_tolerance_ppm); if (user_tsc_khz < thresh_lo || user_tsc_khz > thresh_hi) { - pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", user_tsc_khz, thresh_lo, thresh_hi); + pr_debug("requested TSC rate %u falls outside tolerance [%u,%u]\n", + user_tsc_khz, thresh_lo, thresh_hi); use_scaling = 1; } return set_tsc_khz(vcpu, user_tsc_khz, use_scaling); @@ -3165,6 +3171,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) &vcpu->hv_clock.tsc_shift, &vcpu->hv_clock.tsc_to_system_mul); vcpu->hw_tsc_khz = tgt_tsc_khz; + kvm_xen_update_tsc_info(v); } vcpu->hv_clock.tsc_timestamp = tsc_timestamp; @@ -3562,9 +3569,20 @@ static void record_steal_time(struct kvm_vcpu *vcpu) mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); } +static bool kvm_is_msr_to_save(u32 msr_index) +{ + unsigned int i; + + for (i = 0; i < num_msrs_to_save; i++) { + if (msrs_to_save[i] == msr_index) + return true; + } + + return false; +} + int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { - bool pr = false; u32 msr = msr_info->index; u64 data = msr_info->data; @@ -3610,15 +3628,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data == BIT_ULL(18)) { vcpu->arch.msr_hwcr = data; } else if (data != 0) { - vcpu_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n", - data); + kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } break; case MSR_FAM10H_MMIO_CONF_BASE: if (data != 0) { - vcpu_unimpl(vcpu, "unimplemented MMIO_CONF_BASE wrmsr: " - "0x%llx\n", data); + kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } break; @@ -3798,16 +3814,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: - pr = true; - fallthrough; case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1: if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); - if (pr || data != 0) - vcpu_unimpl(vcpu, "disabled perfctr wrmsr: " - "0x%x data 0x%llx\n", msr, data); + if (data) + kvm_pr_unimpl_wrmsr(vcpu, msr, data); break; case MSR_K7_CLK_CTL: /* @@ -3828,15 +3841,14 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case HV_X64_MSR_REENLIGHTENMENT_CONTROL: case HV_X64_MSR_TSC_EMULATION_CONTROL: case HV_X64_MSR_TSC_EMULATION_STATUS: + case HV_X64_MSR_TSC_INVARIANT_CONTROL: return kvm_hv_set_msr_common(vcpu, msr, data, msr_info->host_initiated); case MSR_IA32_BBL_CR_CTL3: /* Drop writes to this legacy MSR -- see rdmsr * counterpart for further detail. */ - if (report_ignored_msrs) - vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n", - msr, data); + kvm_pr_unimpl_wrmsr(vcpu, msr, data); break; case MSR_AMD64_OSVW_ID_LENGTH: if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW)) @@ -3884,20 +3896,18 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vcpu->arch.guest_fpu.xfd_err = data; break; #endif - case MSR_IA32_PEBS_ENABLE: - case MSR_IA32_DS_AREA: - case MSR_PEBS_DATA_CFG: - case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5: + default: if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); + /* * Userspace is allowed to write '0' to MSRs that KVM reports * as to-be-saved, even if an MSRs isn't fully supported. */ - return !msr_info->host_initiated || data; - default: - if (kvm_pmu_is_valid_msr(vcpu, msr)) - return kvm_pmu_set_msr(vcpu, msr_info); + if (msr_info->host_initiated && !data && + kvm_is_msr_to_save(msr)) + break; + return KVM_MSR_RET_INVALID; } return 0; @@ -3987,20 +3997,6 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_DRAM_ENERGY_STATUS: /* DRAM controller */ msr_info->data = 0; break; - case MSR_IA32_PEBS_ENABLE: - case MSR_IA32_DS_AREA: - case MSR_PEBS_DATA_CFG: - case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5: - if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) - return kvm_pmu_get_msr(vcpu, msr_info); - /* - * Userspace is allowed to read MSRs that KVM reports as - * to-be-saved, even if an MSR isn't fully supported. - */ - if (!msr_info->host_initiated) - return 1; - msr_info->data = 0; - break; case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: @@ -4198,6 +4194,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case HV_X64_MSR_REENLIGHTENMENT_CONTROL: case HV_X64_MSR_TSC_EMULATION_CONTROL: case HV_X64_MSR_TSC_EMULATION_STATUS: + case HV_X64_MSR_TSC_INVARIANT_CONTROL: return kvm_hv_get_msr_common(vcpu, msr_info->index, &msr_info->data, msr_info->host_initiated); @@ -4255,6 +4252,17 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) default: if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) return kvm_pmu_get_msr(vcpu, msr_info); + + /* + * Userspace is allowed to read MSRs that KVM reports as + * to-be-saved, even if an MSR isn't fully supported. + */ + if (msr_info->host_initiated && + kvm_is_msr_to_save(msr_info->index)) { + msr_info->data = 0; + break; + } + return KVM_MSR_RET_INVALID; } return 0; @@ -4292,8 +4300,8 @@ static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs, { struct kvm_msrs msrs; struct kvm_msr_entry *entries; - int r, n; unsigned size; + int r; r = -EFAULT; if (copy_from_user(&msrs, user_msrs, sizeof(msrs))) @@ -4310,17 +4318,11 @@ static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs, goto out; } - r = n = __msr_io(vcpu, &msrs, entries, do_msr); - if (r < 0) - goto out_free; + r = __msr_io(vcpu, &msrs, entries, do_msr); - r = -EFAULT; if (writeback && copy_to_user(user_msrs->entries, entries, size)) - goto out_free; - - r = n; + r = -EFAULT; -out_free: kfree(entries); out: return r; @@ -4408,6 +4410,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SPLIT_IRQCHIP: case KVM_CAP_IMMEDIATE_EXIT: case KVM_CAP_PMU_EVENT_FILTER: + case KVM_CAP_PMU_EVENT_MASKED_EVENTS: case KVM_CAP_GET_MSR_FEATURES: case KVM_CAP_MSR_PLATFORM_INFO: case KVM_CAP_EXCEPTION_PAYLOAD: @@ -6482,7 +6485,7 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, struct kvm_x86_msr_filter *new_filter, *old_filter; bool default_allow; bool empty = true; - int r = 0; + int r; u32 i; if (filter->flags & ~KVM_MSR_FILTER_VALID_MASK) @@ -6508,17 +6511,14 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, } mutex_lock(&kvm->lock); - - /* The per-VM filter is protected by kvm->lock... */ - old_filter = srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1); - - rcu_assign_pointer(kvm->arch.msr_filter, new_filter); + old_filter = rcu_replace_pointer(kvm->arch.msr_filter, new_filter, + mutex_is_locked(&kvm->lock)); + mutex_unlock(&kvm->lock); synchronize_srcu(&kvm->srcu); kvm_free_msr_filter(old_filter); kvm_make_all_cpus_request(kvm, KVM_REQ_MSR_FILTER_CHANGED); - mutex_unlock(&kvm->lock); return 0; } @@ -7018,83 +7018,98 @@ out: return r; } -static void kvm_init_msr_list(void) +static void kvm_probe_msr_to_save(u32 msr_index) { u32 dummy[2]; + + if (rdmsr_safe(msr_index, &dummy[0], &dummy[1])) + return; + + /* + * Even MSRs that are valid in the host may not be exposed to guests in + * some cases. + */ + switch (msr_index) { + case MSR_IA32_BNDCFGS: + if (!kvm_mpx_supported()) + return; + break; + case MSR_TSC_AUX: + if (!kvm_cpu_cap_has(X86_FEATURE_RDTSCP) && + !kvm_cpu_cap_has(X86_FEATURE_RDPID)) + return; + break; + case MSR_IA32_UMWAIT_CONTROL: + if (!kvm_cpu_cap_has(X86_FEATURE_WAITPKG)) + return; + break; + case MSR_IA32_RTIT_CTL: + case MSR_IA32_RTIT_STATUS: + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT)) + return; + break; + case MSR_IA32_RTIT_CR3_MATCH: + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || + !intel_pt_validate_hw_cap(PT_CAP_cr3_filtering)) + return; + break; + case MSR_IA32_RTIT_OUTPUT_BASE: + case MSR_IA32_RTIT_OUTPUT_MASK: + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || + (!intel_pt_validate_hw_cap(PT_CAP_topa_output) && + !intel_pt_validate_hw_cap(PT_CAP_single_range_output))) + return; + break; + case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || + (msr_index - MSR_IA32_RTIT_ADDR0_A >= + intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2)) + return; + break; + case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR_MAX: + if (msr_index - MSR_ARCH_PERFMON_PERFCTR0 >= + kvm_pmu_cap.num_counters_gp) + return; + break; + case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL_MAX: + if (msr_index - MSR_ARCH_PERFMON_EVENTSEL0 >= + kvm_pmu_cap.num_counters_gp) + return; + break; + case MSR_ARCH_PERFMON_FIXED_CTR0 ... MSR_ARCH_PERFMON_FIXED_CTR_MAX: + if (msr_index - MSR_ARCH_PERFMON_FIXED_CTR0 >= + kvm_pmu_cap.num_counters_fixed) + return; + break; + case MSR_IA32_XFD: + case MSR_IA32_XFD_ERR: + if (!kvm_cpu_cap_has(X86_FEATURE_XFD)) + return; + break; + default: + break; + } + + msrs_to_save[num_msrs_to_save++] = msr_index; +} + +static void kvm_init_msr_list(void) +{ unsigned i; BUILD_BUG_ON_MSG(KVM_PMC_MAX_FIXED != 3, - "Please update the fixed PMCs in msrs_to_saved_all[]"); + "Please update the fixed PMCs in msrs_to_save_pmu[]"); num_msrs_to_save = 0; num_emulated_msrs = 0; num_msr_based_features = 0; - for (i = 0; i < ARRAY_SIZE(msrs_to_save_all); i++) { - if (rdmsr_safe(msrs_to_save_all[i], &dummy[0], &dummy[1]) < 0) - continue; - - /* - * Even MSRs that are valid in the host may not be exposed - * to the guests in some cases. - */ - switch (msrs_to_save_all[i]) { - case MSR_IA32_BNDCFGS: - if (!kvm_mpx_supported()) - continue; - break; - case MSR_TSC_AUX: - if (!kvm_cpu_cap_has(X86_FEATURE_RDTSCP) && - !kvm_cpu_cap_has(X86_FEATURE_RDPID)) - continue; - break; - case MSR_IA32_UMWAIT_CONTROL: - if (!kvm_cpu_cap_has(X86_FEATURE_WAITPKG)) - continue; - break; - case MSR_IA32_RTIT_CTL: - case MSR_IA32_RTIT_STATUS: - if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT)) - continue; - break; - case MSR_IA32_RTIT_CR3_MATCH: - if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || - !intel_pt_validate_hw_cap(PT_CAP_cr3_filtering)) - continue; - break; - case MSR_IA32_RTIT_OUTPUT_BASE: - case MSR_IA32_RTIT_OUTPUT_MASK: - if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || - (!intel_pt_validate_hw_cap(PT_CAP_topa_output) && - !intel_pt_validate_hw_cap(PT_CAP_single_range_output))) - continue; - break; - case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: - if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || - msrs_to_save_all[i] - MSR_IA32_RTIT_ADDR0_A >= - intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2) - continue; - break; - case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR_MAX: - if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >= - min(KVM_INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp)) - continue; - break; - case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL_MAX: - if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >= - min(KVM_INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp)) - continue; - break; - case MSR_IA32_XFD: - case MSR_IA32_XFD_ERR: - if (!kvm_cpu_cap_has(X86_FEATURE_XFD)) - continue; - break; - default: - break; - } + for (i = 0; i < ARRAY_SIZE(msrs_to_save_base); i++) + kvm_probe_msr_to_save(msrs_to_save_base[i]); - msrs_to_save[num_msrs_to_save++] = msrs_to_save_all[i]; + if (enable_pmu) { + for (i = 0; i < ARRAY_SIZE(msrs_to_save_pmu); i++) + kvm_probe_msr_to_save(msrs_to_save_pmu[i]); } for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) { @@ -7721,7 +7736,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, return X86EMUL_CONTINUE; emul_write: - printk_once(KERN_WARNING "kvm: emulating exchange as write\n"); + pr_warn_once("emulating exchange as write\n"); return emulator_write_emulated(ctxt, addr, new, bytes, exception); } @@ -8167,9 +8182,14 @@ static void emulator_set_nmi_mask(struct x86_emulate_ctxt *ctxt, bool masked) static_call(kvm_x86_set_nmi_mask)(emul_to_vcpu(ctxt), masked); } -static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt) +static bool emulator_is_smm(struct x86_emulate_ctxt *ctxt) +{ + return is_smm(emul_to_vcpu(ctxt)); +} + +static bool emulator_is_guest_mode(struct x86_emulate_ctxt *ctxt) { - return emul_to_vcpu(ctxt)->arch.hflags; + return is_guest_mode(emul_to_vcpu(ctxt)); } #ifndef CONFIG_KVM_SMM @@ -8238,7 +8258,8 @@ static const struct x86_emulate_ops emulate_ops = { .guest_has_fxsr = emulator_guest_has_fxsr, .guest_has_rdpid = emulator_guest_has_rdpid, .set_nmi_mask = emulator_set_nmi_mask, - .get_hflags = emulator_get_hflags, + .is_smm = emulator_is_smm, + .is_guest_mode = emulator_is_guest_mode, .leave_smm = emulator_leave_smm, .triple_fault = emulator_triple_fault, .set_xcr = emulator_set_xcr, @@ -8282,7 +8303,7 @@ static struct x86_emulate_ctxt *alloc_emulate_ctxt(struct kvm_vcpu *vcpu) ctxt = kmem_cache_zalloc(x86_emulator_cache, GFP_KERNEL_ACCOUNT); if (!ctxt) { - pr_err("kvm: failed to allocate vcpu's emulator\n"); + pr_err("failed to allocate vcpu's emulator\n"); return NULL; } @@ -8310,8 +8331,6 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) (cs_l && is_long_mode(vcpu)) ? X86EMUL_MODE_PROT64 : cs_db ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; - BUILD_BUG_ON(HF_GUEST_MASK != X86EMUL_GUEST_MASK); - ctxt->interruptibility = 0; ctxt->have_exception = false; ctxt->exception.vector = -1; @@ -9293,35 +9312,66 @@ static struct notifier_block pvclock_gtod_notifier = { }; #endif -int kvm_arch_init(void *opaque) +static inline void kvm_ops_update(struct kvm_x86_init_ops *ops) +{ + memcpy(&kvm_x86_ops, ops->runtime_ops, sizeof(kvm_x86_ops)); + +#define __KVM_X86_OP(func) \ + static_call_update(kvm_x86_##func, kvm_x86_ops.func); +#define KVM_X86_OP(func) \ + WARN_ON(!kvm_x86_ops.func); __KVM_X86_OP(func) +#define KVM_X86_OP_OPTIONAL __KVM_X86_OP +#define KVM_X86_OP_OPTIONAL_RET0(func) \ + static_call_update(kvm_x86_##func, (void *)kvm_x86_ops.func ? : \ + (void *)__static_call_return0); +#include <asm/kvm-x86-ops.h> +#undef __KVM_X86_OP + + kvm_pmu_ops_update(ops->pmu_ops); +} + +static int kvm_x86_check_processor_compatibility(void) +{ + int cpu = smp_processor_id(); + struct cpuinfo_x86 *c = &cpu_data(cpu); + + /* + * Compatibility checks are done when loading KVM and when enabling + * hardware, e.g. during CPU hotplug, to ensure all online CPUs are + * compatible, i.e. KVM should never perform a compatibility check on + * an offline CPU. + */ + WARN_ON(!cpu_online(cpu)); + + if (__cr4_reserved_bits(cpu_has, c) != + __cr4_reserved_bits(cpu_has, &boot_cpu_data)) + return -EIO; + + return static_call(kvm_x86_check_processor_compatibility)(); +} + +static void kvm_x86_check_cpu_compat(void *ret) +{ + *(int *)ret = kvm_x86_check_processor_compatibility(); +} + +static int __kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) { - struct kvm_x86_init_ops *ops = opaque; u64 host_pat; - int r; + int r, cpu; if (kvm_x86_ops.hardware_enable) { - pr_err("kvm: already loaded vendor module '%s'\n", kvm_x86_ops.name); + pr_err("already loaded vendor module '%s'\n", kvm_x86_ops.name); return -EEXIST; } - if (!ops->cpu_has_kvm_support()) { - pr_err_ratelimited("kvm: no hardware support for '%s'\n", - ops->runtime_ops->name); - return -EOPNOTSUPP; - } - if (ops->disabled_by_bios()) { - pr_err_ratelimited("kvm: support for '%s' disabled by bios\n", - ops->runtime_ops->name); - return -EOPNOTSUPP; - } - /* * KVM explicitly assumes that the guest has an FPU and * FXSAVE/FXRSTOR. For example, the KVM_GET_FPU explicitly casts the * vCPU's FPU state as a fxregs_state struct. */ if (!boot_cpu_has(X86_FEATURE_FPU) || !boot_cpu_has(X86_FEATURE_FXSR)) { - printk(KERN_ERR "kvm: inadequate fpu\n"); + pr_err("inadequate fpu\n"); return -EOPNOTSUPP; } @@ -9339,19 +9389,19 @@ int kvm_arch_init(void *opaque) */ if (rdmsrl_safe(MSR_IA32_CR_PAT, &host_pat) || (host_pat & GENMASK(2, 0)) != 6) { - pr_err("kvm: host PAT[0] is not WB\n"); + pr_err("host PAT[0] is not WB\n"); return -EIO; } x86_emulator_cache = kvm_alloc_emulator_cache(); if (!x86_emulator_cache) { - pr_err("kvm: failed to allocate cache for x86 emulator\n"); + pr_err("failed to allocate cache for x86 emulator\n"); return -ENOMEM; } user_return_msrs = alloc_percpu(struct kvm_user_return_msrs); if (!user_return_msrs) { - printk(KERN_ERR "kvm: failed to allocate percpu kvm_user_return_msrs\n"); + pr_err("failed to allocate percpu kvm_user_return_msrs\n"); r = -ENOMEM; goto out_free_x86_emulator_cache; } @@ -9361,13 +9411,37 @@ int kvm_arch_init(void *opaque) if (r) goto out_free_percpu; - kvm_timer_init(); - if (boot_cpu_has(X86_FEATURE_XSAVE)) { host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); kvm_caps.supported_xcr0 = host_xcr0 & KVM_SUPPORTED_XCR0; } + rdmsrl_safe(MSR_EFER, &host_efer); + + if (boot_cpu_has(X86_FEATURE_XSAVES)) + rdmsrl(MSR_IA32_XSS, host_xss); + + kvm_init_pmu_capability(ops->pmu_ops); + + r = ops->hardware_setup(); + if (r != 0) + goto out_mmu_exit; + + kvm_ops_update(ops); + + for_each_online_cpu(cpu) { + smp_call_function_single(cpu, kvm_x86_check_cpu_compat, &r, 1); + if (r < 0) + goto out_unwind_ops; + } + + /* + * Point of no return! DO NOT add error paths below this point unless + * absolutely necessary, as most operations from this point forward + * require unwinding. + */ + kvm_timer_init(); + if (pi_inject_timer == -1) pi_inject_timer = housekeeping_enabled(HK_TYPE_TIMER); #ifdef CONFIG_X86_64 @@ -9377,8 +9451,35 @@ int kvm_arch_init(void *opaque) set_hv_tscchange_cb(kvm_hyperv_tsc_notifier); #endif + kvm_register_perf_callbacks(ops->handle_intel_pt_intr); + + if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) + kvm_caps.supported_xss = 0; + +#define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f) + cr4_reserved_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_); +#undef __kvm_cpu_cap_has + + if (kvm_caps.has_tsc_control) { + /* + * Make sure the user can only configure tsc_khz values that + * fit into a signed integer. + * A min value is not calculated because it will always + * be 1 on all machines. + */ + u64 max = min(0x7fffffffULL, + __scale_tsc(kvm_caps.max_tsc_scaling_ratio, tsc_khz)); + kvm_caps.max_guest_tsc_khz = max; + } + kvm_caps.default_tsc_scaling_ratio = 1ULL << kvm_caps.tsc_scaling_ratio_frac_bits; + kvm_init_msr_list(); return 0; +out_unwind_ops: + kvm_x86_ops.hardware_enable = NULL; + static_call(kvm_x86_hardware_unsetup)(); +out_mmu_exit: + kvm_mmu_vendor_module_exit(); out_free_percpu: free_percpu(user_return_msrs); out_free_x86_emulator_cache: @@ -9386,8 +9487,22 @@ out_free_x86_emulator_cache: return r; } -void kvm_arch_exit(void) +int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) +{ + int r; + + mutex_lock(&vendor_module_lock); + r = __kvm_x86_vendor_init(ops); + mutex_unlock(&vendor_module_lock); + + return r; +} +EXPORT_SYMBOL_GPL(kvm_x86_vendor_init); + +void kvm_x86_vendor_exit(void) { + kvm_unregister_perf_callbacks(); + #ifdef CONFIG_X86_64 if (hypervisor_is_type(X86_HYPER_MS_HYPERV)) clear_hv_tscchange_cb(); @@ -9404,7 +9519,7 @@ void kvm_arch_exit(void) irq_work_sync(&pvclock_irq_work); cancel_work_sync(&pvclock_gtod_work); #endif - kvm_x86_ops.hardware_enable = NULL; + static_call(kvm_x86_hardware_unsetup)(); kvm_mmu_vendor_module_exit(); free_percpu(user_return_msrs); kmem_cache_destroy(x86_emulator_cache); @@ -9412,7 +9527,11 @@ void kvm_arch_exit(void) static_key_deferred_flush(&kvm_xen_enabled); WARN_ON(static_branch_unlikely(&kvm_xen_enabled.key)); #endif + mutex_lock(&vendor_module_lock); + kvm_x86_ops.hardware_enable = NULL; + mutex_unlock(&vendor_module_lock); } +EXPORT_SYMBOL_GPL(kvm_x86_vendor_exit); static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason) { @@ -10065,7 +10184,7 @@ void kvm_make_scan_ioapic_request(struct kvm *kvm) kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC); } -void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) +void __kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; bool activate; @@ -10100,7 +10219,30 @@ out: preempt_enable(); up_read(&vcpu->kvm->arch.apicv_update_lock); } -EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv); +EXPORT_SYMBOL_GPL(__kvm_vcpu_update_apicv); + +static void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) +{ + if (!lapic_in_kernel(vcpu)) + return; + + /* + * Due to sharing page tables across vCPUs, the xAPIC memslot must be + * deleted if any vCPU has xAPIC virtualization and x2APIC enabled, but + * and hardware doesn't support x2APIC virtualization. E.g. some AMD + * CPUs support AVIC but not x2APIC. KVM still allows enabling AVIC in + * this case so that KVM can the AVIC doorbell to inject interrupts to + * running vCPUs, but KVM must not create SPTEs for the APIC base as + * the vCPU would incorrectly be able to access the vAPIC page via MMIO + * despite being in x2APIC mode. For simplicity, inhibiting the APIC + * access page is sticky. + */ + if (apic_x2apic_mode(vcpu->arch.apic) && + kvm_x86_ops.allow_apicv_in_x2apic_without_x2apic_virtualization) + kvm_inhibit_apic_access_page(vcpu); + + __kvm_vcpu_update_apicv(vcpu); +} void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, enum kvm_apicv_inhibit reason, bool set) @@ -10109,7 +10251,7 @@ void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, lockdep_assert_held_write(&kvm->arch.apicv_update_lock); - if (!static_call(kvm_x86_check_apicv_inhibit_reasons)(reason)) + if (!(kvm_x86_ops.required_apicv_inhibits & BIT(reason))) return; old = new = kvm->arch.apicv_inhibit_reasons; @@ -11553,7 +11695,7 @@ static int sync_regs(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) { if (kvm_check_tsc_unstable() && kvm->created_vcpus) - pr_warn_once("kvm: SMP vm created on host with unstable TSC; " + pr_warn_once("SMP vm created on host with unstable TSC; " "guest TSC will not be reliable\n"); if (!kvm->arch.max_vcpu_ids) @@ -11630,7 +11772,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) goto free_wbinvd_dirty_mask; if (!fpu_alloc_guest_fpstate(&vcpu->arch.guest_fpu)) { - pr_err("kvm: failed to allocate vcpu's fpu\n"); + pr_err("failed to allocate vcpu's fpu\n"); goto free_emulate_ctxt; } @@ -11904,6 +12046,11 @@ int kvm_arch_hardware_enable(void) bool stable, backwards_tsc = false; kvm_user_return_msr_cpu_online(); + + ret = kvm_x86_check_processor_compatibility(); + if (ret) + return ret; + ret = static_call(kvm_x86_hardware_enable)(); if (ret != 0) return ret; @@ -11990,88 +12137,6 @@ void kvm_arch_hardware_disable(void) drop_user_return_notifiers(); } -static inline void kvm_ops_update(struct kvm_x86_init_ops *ops) -{ - memcpy(&kvm_x86_ops, ops->runtime_ops, sizeof(kvm_x86_ops)); - -#define __KVM_X86_OP(func) \ - static_call_update(kvm_x86_##func, kvm_x86_ops.func); -#define KVM_X86_OP(func) \ - WARN_ON(!kvm_x86_ops.func); __KVM_X86_OP(func) -#define KVM_X86_OP_OPTIONAL __KVM_X86_OP -#define KVM_X86_OP_OPTIONAL_RET0(func) \ - static_call_update(kvm_x86_##func, (void *)kvm_x86_ops.func ? : \ - (void *)__static_call_return0); -#include <asm/kvm-x86-ops.h> -#undef __KVM_X86_OP - - kvm_pmu_ops_update(ops->pmu_ops); -} - -int kvm_arch_hardware_setup(void *opaque) -{ - struct kvm_x86_init_ops *ops = opaque; - int r; - - rdmsrl_safe(MSR_EFER, &host_efer); - - if (boot_cpu_has(X86_FEATURE_XSAVES)) - rdmsrl(MSR_IA32_XSS, host_xss); - - kvm_init_pmu_capability(); - - r = ops->hardware_setup(); - if (r != 0) - return r; - - kvm_ops_update(ops); - - kvm_register_perf_callbacks(ops->handle_intel_pt_intr); - - if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) - kvm_caps.supported_xss = 0; - -#define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f) - cr4_reserved_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_); -#undef __kvm_cpu_cap_has - - if (kvm_caps.has_tsc_control) { - /* - * Make sure the user can only configure tsc_khz values that - * fit into a signed integer. - * A min value is not calculated because it will always - * be 1 on all machines. - */ - u64 max = min(0x7fffffffULL, - __scale_tsc(kvm_caps.max_tsc_scaling_ratio, tsc_khz)); - kvm_caps.max_guest_tsc_khz = max; - } - kvm_caps.default_tsc_scaling_ratio = 1ULL << kvm_caps.tsc_scaling_ratio_frac_bits; - kvm_init_msr_list(); - return 0; -} - -void kvm_arch_hardware_unsetup(void) -{ - kvm_unregister_perf_callbacks(); - - static_call(kvm_x86_hardware_unsetup)(); -} - -int kvm_arch_check_processor_compat(void *opaque) -{ - struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); - struct kvm_x86_init_ops *ops = opaque; - - WARN_ON(!irqs_disabled()); - - if (__cr4_reserved_bits(cpu_has, c) != - __cr4_reserved_bits(cpu_has, &boot_cpu_data)) - return -EIO; - - return ops->check_processor_compatibility(); -} - bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu) { return vcpu->kvm->arch.bsp_vcpu_id == vcpu->vcpu_id; @@ -12244,7 +12309,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, */ hva = vm_mmap(NULL, 0, size, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, 0); - if (IS_ERR((void *)hva)) + if (IS_ERR_VALUE(hva)) return (void __user *)hva; } else { if (!slot || !slot->npages) @@ -12459,16 +12524,14 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, static void kvm_mmu_update_cpu_dirty_logging(struct kvm *kvm, bool enable) { - struct kvm_arch *ka = &kvm->arch; + int nr_slots; if (!kvm_x86_ops.cpu_dirty_log_size) return; - if ((enable && ++ka->cpu_dirty_logging_count == 1) || - (!enable && --ka->cpu_dirty_logging_count == 0)) + nr_slots = atomic_read(&kvm->nr_memslots_dirty_logging); + if ((enable && nr_slots == 1) || !nr_slots) kvm_make_all_cpus_request(kvm, KVM_REQ_UPDATE_CPU_DIRTY_LOGGING); - - WARN_ON_ONCE(ka->cpu_dirty_logging_count < 0); } static void kvm_mmu_slot_apply_flags(struct kvm *kvm, diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 9de72586f406..a8167b47b8c8 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -331,6 +331,18 @@ extern bool report_ignored_msrs; extern bool eager_page_split; +static inline void kvm_pr_unimpl_wrmsr(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + if (report_ignored_msrs) + vcpu_unimpl(vcpu, "Unhandled WRMSR(0x%x) = 0x%llx\n", msr, data); +} + +static inline void kvm_pr_unimpl_rdmsr(struct kvm_vcpu *vcpu, u32 msr) +{ + if (report_ignored_msrs) + vcpu_unimpl(vcpu, "Unhandled RDMSR(0x%x)\n", msr); +} + static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) { return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult, @@ -382,13 +394,13 @@ enum kvm_intr_type { KVM_HANDLING_NMI, }; -static inline void kvm_before_interrupt(struct kvm_vcpu *vcpu, - enum kvm_intr_type intr) +static __always_inline void kvm_before_interrupt(struct kvm_vcpu *vcpu, + enum kvm_intr_type intr) { WRITE_ONCE(vcpu->arch.handling_intr_from_guest, (u8)intr); } -static inline void kvm_after_interrupt(struct kvm_vcpu *vcpu) +static __always_inline void kvm_after_interrupt(struct kvm_vcpu *vcpu) { WRITE_ONCE(vcpu->arch.handling_intr_from_guest, 0); } diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 8fd41f5deae3..40edf4d1974c 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -5,6 +5,7 @@ * * KVM Xen emulation */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "x86.h" #include "xen.h" @@ -22,6 +23,9 @@ #include <xen/interface/event_channel.h> #include <xen/interface/sched.h> +#include <asm/xen/cpuid.h> + +#include "cpuid.h" #include "trace.h" static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm); @@ -2076,6 +2080,29 @@ void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu) del_timer_sync(&vcpu->arch.xen.poll_timer); } +void kvm_xen_update_tsc_info(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *entry; + u32 function; + + if (!vcpu->arch.xen.cpuid.base) + return; + + function = vcpu->arch.xen.cpuid.base | XEN_CPUID_LEAF(3); + if (function > vcpu->arch.xen.cpuid.limit) + return; + + entry = kvm_find_cpuid_entry_index(vcpu, function, 1); + if (entry) { + entry->ecx = vcpu->arch.hv_clock.tsc_to_system_mul; + entry->edx = vcpu->arch.hv_clock.tsc_shift; + } + + entry = kvm_find_cpuid_entry_index(vcpu, function, 2); + if (entry) + entry->eax = vcpu->arch.hw_tsc_khz; +} + void kvm_xen_init_vm(struct kvm *kvm) { mutex_init(&kvm->arch.xen.xen_lock); diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h index ea33d80a0c51..f8f1fe22d090 100644 --- a/arch/x86/kvm/xen.h +++ b/arch/x86/kvm/xen.h @@ -9,6 +9,8 @@ #ifndef __ARCH_X86_KVM_XEN_H__ #define __ARCH_X86_KVM_XEN_H__ +#include <asm/xen/hypervisor.h> + #ifdef CONFIG_KVM_XEN #include <linux/jump_label_ratelimit.h> @@ -32,6 +34,7 @@ int kvm_xen_set_evtchn_fast(struct kvm_xen_evtchn *xe, int kvm_xen_setup_evtchn(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue); +void kvm_xen_update_tsc_info(struct kvm_vcpu *vcpu); static inline bool kvm_xen_msr_enabled(struct kvm *kvm) { @@ -135,6 +138,10 @@ static inline bool kvm_xen_timer_enabled(struct kvm_vcpu *vcpu) { return false; } + +static inline void kvm_xen_update_tsc_info(struct kvm_vcpu *vcpu) +{ +} #endif int kvm_xen_hypercall(struct kvm_vcpu *vcpu); |