* 'kvm-updates/2.6.35' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (269 commits)
KVM: x86: Add missing locking to arch specific vcpu ioctls
KVM: PPC: Add missing vcpu_load()/vcpu_put() in vcpu ioctls
KVM: MMU: Segregate shadow pages with different cr0.wp
KVM: x86: Check LMA bit before set_efer
KVM: Don't allow lmsw to clear cr0.pe
KVM: Add cpuid.txt file
KVM: x86: Tell the guest we'll warn it about tsc stability
x86, paravirt: don't compute pvclock adjustments if we trust the tsc
x86: KVM guest: Try using new kvm clock msrs
KVM: x86: export paravirtual cpuid flags in KVM_GET_SUPPORTED_CPUID
KVM: x86: add new KVMCLOCK cpuid feature
KVM: x86: change msr numbers for kvmclock
x86, paravirt: Add a global synchronization point for pvclock
x86, paravirt: Enable pvclock flags in vcpu_time_info structure
KVM: x86: Inject #GP with the right rip on efer writes
KVM: SVM: Don't allow nested guest to VMMCALL into host
KVM: x86: Fix exception reinjection forced to true
KVM: Fix wallclock version writing race
KVM: MMU: Don't read pdptrs with mmu spinlock held in mmu_alloc_roots
KVM: VMX: enable VMXON check with SMX enabled (Intel TXT)
...
#include <asm/page.h>
#include <asm/exception-64e.h>
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
- #include <asm/kvm_book3s_64_asm.h>
+ #include <asm/kvm_book3s_asm.h>
#endif
register struct paca_struct *local_paca asm("r13");
s16 hw_cpu_id; /* Physical processor number */
u8 cpu_start; /* At startup, processor spins until */
/* this becomes non-zero. */
+ u8 kexec_state; /* set when kexec down has irqs off */
#ifdef CONFIG_PPC_STD_MMU_64
struct slb_shadow *slb_shadow_ptr;
u64 startpurr; /* PURR/TB value snapshot */
u64 startspurr; /* SPURR value snapshot */
- #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
- struct {
- u64 esid;
- u64 vsid;
- } kvm_slb[64]; /* guest SLB */
+ #ifdef CONFIG_KVM_BOOK3S_HANDLER
/* We use this to store guest state in */
struct kvmppc_book3s_shadow_vcpu shadow_vcpu;
- u8 kvm_slb_max; /* highest used guest slb entry */
- u8 kvm_in_guest; /* are we inside the guest? */
#endif
};
#define HID1_ABE (1<<10) /* 7450 Address Broadcast Enable */
#define HID1_PS (1<<16) /* 750FX PLL selection */
#define SPRN_HID2 0x3F8 /* Hardware Implementation Register 2 */
+ #define SPRN_HID2_GEKKO 0x398 /* Gekko HID2 Register */
#define SPRN_IABR 0x3F2 /* Instruction Address Breakpoint Register */
#define SPRN_IABR2 0x3FA /* 83xx */
#define SPRN_IBCR 0x135 /* 83xx Insn Breakpoint Control Reg */
#define SPRN_HID4 0x3F4 /* 970 HID4 */
+ #define SPRN_HID4_GEKKO 0x3F3 /* Gekko HID4 */
#define SPRN_HID5 0x3F6 /* 970 HID5 */
#define SPRN_HID6 0x3F9 /* BE HID 6 */
#define HID6_LB (0x0F<<12) /* Concurrent Large Page Modes */
#define SPRN_VRSAVE 0x100 /* Vector Register Save Register */
#define SPRN_XER 0x001 /* Fixed Point Exception Register */
+ #define SPRN_MMCR0_GEKKO 0x3B8 /* Gekko Monitor Mode Control Register 0 */
+ #define SPRN_MMCR1_GEKKO 0x3BC /* Gekko Monitor Mode Control Register 1 */
+ #define SPRN_PMC1_GEKKO 0x3B9 /* Gekko Performance Monitor Control 1 */
+ #define SPRN_PMC2_GEKKO 0x3BA /* Gekko Performance Monitor Control 2 */
+ #define SPRN_PMC3_GEKKO 0x3BD /* Gekko Performance Monitor Control 3 */
+ #define SPRN_PMC4_GEKKO 0x3BE /* Gekko Performance Monitor Control 4 */
+ #define SPRN_WPAR_GEKKO 0x399 /* Gekko Write Pipe Address Register */
+
#define SPRN_SCOMC 0x114 /* SCOM Access Control */
#define SPRN_SCOMD 0x115 /* SCOM Access DATA */
#define PVR_403GC 0x00200200
#define PVR_403GCX 0x00201400
#define PVR_405GP 0x40110000
+#define PVR_476 0x11a52000
#define PVR_STB03XXX 0x40310000
#define PVR_NP405H 0x41410000
#define PVR_NP405L 0x41610000
#define PVR_8245 0x80811014
#define PVR_8260 PVR_8240
+/* 476 Simulator seems to currently have the PVR of the 602... */
+#define PVR_476_ISS 0x00052000
+
/* 64-bit processors */
/* XXX the prefix should be PVR_, we'll do a global sweep to fix it one day */
#define PV_NORTHSTAR 0x0033
#endif
#ifdef CONFIG_KVM
#include <linux/kvm_host.h>
+ #ifndef CONFIG_BOOKE
+ #include <asm/kvm_book3s.h>
+ #endif
#endif
#ifdef CONFIG_PPC32
DEFINE(THREAD_USED_SPE, offsetof(struct thread_struct, used_spe));
#endif /* CONFIG_SPE */
#endif /* CONFIG_PPC64 */
+ #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
+ DEFINE(THREAD_KVM_SVCPU, offsetof(struct thread_struct, kvm_shadow_vcpu));
+ #endif
DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
DEFINE(TI_LOCAL_FLAGS, offsetof(struct thread_info, local_flags));
DEFINE(PACAKMSR, offsetof(struct paca_struct, kernel_msr));
DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled));
DEFINE(PACAHARDIRQEN, offsetof(struct paca_struct, hard_enabled));
- DEFINE(PACAPERFPEND, offsetof(struct paca_struct, perf_event_pending));
DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id));
#ifdef CONFIG_PPC_MM_SLICES
DEFINE(PACALOWSLICESPSIZE, offsetof(struct paca_struct,
#endif /* CONFIG_PPC_STD_MMU_64 */
DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp));
DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));
+ DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state));
DEFINE(PACA_STARTPURR, offsetof(struct paca_struct, startpurr));
DEFINE(PACA_STARTSPURR, offsetof(struct paca_struct, startspurr));
DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
DEFINE(PACA_DATA_OFFSET, offsetof(struct paca_struct, data_offset));
DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
- DEFINE(PACA_KVM_IN_GUEST, offsetof(struct paca_struct, kvm_in_guest));
- DEFINE(PACA_KVM_SLB, offsetof(struct paca_struct, kvm_slb));
- DEFINE(PACA_KVM_SLB_MAX, offsetof(struct paca_struct, kvm_slb_max));
- DEFINE(PACA_KVM_CR, offsetof(struct paca_struct, shadow_vcpu.cr));
- DEFINE(PACA_KVM_XER, offsetof(struct paca_struct, shadow_vcpu.xer));
- DEFINE(PACA_KVM_R0, offsetof(struct paca_struct, shadow_vcpu.gpr[0]));
- DEFINE(PACA_KVM_R1, offsetof(struct paca_struct, shadow_vcpu.gpr[1]));
- DEFINE(PACA_KVM_R2, offsetof(struct paca_struct, shadow_vcpu.gpr[2]));
- DEFINE(PACA_KVM_R3, offsetof(struct paca_struct, shadow_vcpu.gpr[3]));
- DEFINE(PACA_KVM_R4, offsetof(struct paca_struct, shadow_vcpu.gpr[4]));
- DEFINE(PACA_KVM_R5, offsetof(struct paca_struct, shadow_vcpu.gpr[5]));
- DEFINE(PACA_KVM_R6, offsetof(struct paca_struct, shadow_vcpu.gpr[6]));
- DEFINE(PACA_KVM_R7, offsetof(struct paca_struct, shadow_vcpu.gpr[7]));
- DEFINE(PACA_KVM_R8, offsetof(struct paca_struct, shadow_vcpu.gpr[8]));
- DEFINE(PACA_KVM_R9, offsetof(struct paca_struct, shadow_vcpu.gpr[9]));
- DEFINE(PACA_KVM_R10, offsetof(struct paca_struct, shadow_vcpu.gpr[10]));
- DEFINE(PACA_KVM_R11, offsetof(struct paca_struct, shadow_vcpu.gpr[11]));
- DEFINE(PACA_KVM_R12, offsetof(struct paca_struct, shadow_vcpu.gpr[12]));
- DEFINE(PACA_KVM_R13, offsetof(struct paca_struct, shadow_vcpu.gpr[13]));
- DEFINE(PACA_KVM_HOST_R1, offsetof(struct paca_struct, shadow_vcpu.host_r1));
- DEFINE(PACA_KVM_HOST_R2, offsetof(struct paca_struct, shadow_vcpu.host_r2));
- DEFINE(PACA_KVM_VMHANDLER, offsetof(struct paca_struct,
- shadow_vcpu.vmhandler));
- DEFINE(PACA_KVM_SCRATCH0, offsetof(struct paca_struct,
- shadow_vcpu.scratch0));
- DEFINE(PACA_KVM_SCRATCH1, offsetof(struct paca_struct,
- shadow_vcpu.scratch1));
+ DEFINE(PACA_KVM_SVCPU, offsetof(struct paca_struct, shadow_vcpu));
+ DEFINE(SVCPU_SLB, offsetof(struct kvmppc_book3s_shadow_vcpu, slb));
+ DEFINE(SVCPU_SLB_MAX, offsetof(struct kvmppc_book3s_shadow_vcpu, slb_max));
#endif
#endif /* CONFIG_PPC64 */
/* Interrupt register frame */
DEFINE(STACK_FRAME_OVERHEAD, STACK_FRAME_OVERHEAD);
DEFINE(INT_FRAME_SIZE, STACK_INT_FRAME_SIZE);
- #ifdef CONFIG_PPC64
DEFINE(SWITCH_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs));
+ #ifdef CONFIG_PPC64
/* Create extra stack space for SRR0 and SRR1 when calling prom/rtas. */
DEFINE(PROM_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16);
DEFINE(RTAS_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16);
DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack));
DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid));
DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr));
- DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr));
- DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr));
- DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc));
DEFINE(VCPU_MSR, offsetof(struct kvm_vcpu, arch.msr));
DEFINE(VCPU_SPRG4, offsetof(struct kvm_vcpu, arch.sprg4));
DEFINE(VCPU_SPRG5, offsetof(struct kvm_vcpu, arch.sprg5));
DEFINE(VCPU_SPRG7, offsetof(struct kvm_vcpu, arch.sprg7));
DEFINE(VCPU_SHADOW_PID, offsetof(struct kvm_vcpu, arch.shadow_pid));
- DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));
- DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear));
- DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr));
-
- /* book3s_64 */
- #ifdef CONFIG_PPC64
- DEFINE(VCPU_FAULT_DSISR, offsetof(struct kvm_vcpu, arch.fault_dsisr));
+ /* book3s */
+ #ifdef CONFIG_PPC_BOOK3S
DEFINE(VCPU_HOST_RETIP, offsetof(struct kvm_vcpu, arch.host_retip));
- DEFINE(VCPU_HOST_R2, offsetof(struct kvm_vcpu, arch.host_r2));
DEFINE(VCPU_HOST_MSR, offsetof(struct kvm_vcpu, arch.host_msr));
DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr));
- DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1));
DEFINE(VCPU_TRAMPOLINE_LOWMEM, offsetof(struct kvm_vcpu, arch.trampoline_lowmem));
DEFINE(VCPU_TRAMPOLINE_ENTER, offsetof(struct kvm_vcpu, arch.trampoline_enter));
DEFINE(VCPU_HIGHMEM_HANDLER, offsetof(struct kvm_vcpu, arch.highmem_handler));
DEFINE(VCPU_RMCALL, offsetof(struct kvm_vcpu, arch.rmcall));
DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags));
+ DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) -
+ offsetof(struct kvmppc_vcpu_book3s, vcpu));
+ DEFINE(SVCPU_CR, offsetof(struct kvmppc_book3s_shadow_vcpu, cr));
+ DEFINE(SVCPU_XER, offsetof(struct kvmppc_book3s_shadow_vcpu, xer));
+ DEFINE(SVCPU_CTR, offsetof(struct kvmppc_book3s_shadow_vcpu, ctr));
+ DEFINE(SVCPU_LR, offsetof(struct kvmppc_book3s_shadow_vcpu, lr));
+ DEFINE(SVCPU_PC, offsetof(struct kvmppc_book3s_shadow_vcpu, pc));
+ DEFINE(SVCPU_R0, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[0]));
+ DEFINE(SVCPU_R1, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[1]));
+ DEFINE(SVCPU_R2, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[2]));
+ DEFINE(SVCPU_R3, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[3]));
+ DEFINE(SVCPU_R4, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[4]));
+ DEFINE(SVCPU_R5, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[5]));
+ DEFINE(SVCPU_R6, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[6]));
+ DEFINE(SVCPU_R7, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[7]));
+ DEFINE(SVCPU_R8, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[8]));
+ DEFINE(SVCPU_R9, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[9]));
+ DEFINE(SVCPU_R10, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[10]));
+ DEFINE(SVCPU_R11, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[11]));
+ DEFINE(SVCPU_R12, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[12]));
+ DEFINE(SVCPU_R13, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[13]));
+ DEFINE(SVCPU_HOST_R1, offsetof(struct kvmppc_book3s_shadow_vcpu, host_r1));
+ DEFINE(SVCPU_HOST_R2, offsetof(struct kvmppc_book3s_shadow_vcpu, host_r2));
+ DEFINE(SVCPU_VMHANDLER, offsetof(struct kvmppc_book3s_shadow_vcpu,
+ vmhandler));
+ DEFINE(SVCPU_SCRATCH0, offsetof(struct kvmppc_book3s_shadow_vcpu,
+ scratch0));
+ DEFINE(SVCPU_SCRATCH1, offsetof(struct kvmppc_book3s_shadow_vcpu,
+ scratch1));
+ DEFINE(SVCPU_IN_GUEST, offsetof(struct kvmppc_book3s_shadow_vcpu,
+ in_guest));
+ DEFINE(SVCPU_FAULT_DSISR, offsetof(struct kvmppc_book3s_shadow_vcpu,
+ fault_dsisr));
+ DEFINE(SVCPU_FAULT_DAR, offsetof(struct kvmppc_book3s_shadow_vcpu,
+ fault_dar));
+ DEFINE(SVCPU_LAST_INST, offsetof(struct kvmppc_book3s_shadow_vcpu,
+ last_inst));
+ DEFINE(SVCPU_SHADOW_SRR1, offsetof(struct kvmppc_book3s_shadow_vcpu,
+ shadow_srr1));
+ #ifdef CONFIG_PPC_BOOK3S_32
+ DEFINE(SVCPU_SR, offsetof(struct kvmppc_book3s_shadow_vcpu, sr));
+ #endif
#else
DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer));
- #endif /* CONFIG_PPC64 */
+ DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr));
+ DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr));
+ DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc));
+ DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));
+ DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear));
+ DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr));
+ #endif /* CONFIG_PPC_BOOK3S */
#endif
#ifdef CONFIG_44x
DEFINE(PGD_T_LOG2, PGD_T_LOG2);
DEFINE(PTE_T_LOG2, PTE_T_LOG2);
#endif
+#ifdef CONFIG_FSL_BOOKE
+ DEFINE(TLBCAM_SIZE, sizeof(struct tlbcam));
+ DEFINE(TLBCAM_MAS0, offsetof(struct tlbcam, MAS0));
+ DEFINE(TLBCAM_MAS1, offsetof(struct tlbcam, MAS1));
+ DEFINE(TLBCAM_MAS2, offsetof(struct tlbcam, MAS2));
+ DEFINE(TLBCAM_MAS3, offsetof(struct tlbcam, MAS3));
+ DEFINE(TLBCAM_MAS7, offsetof(struct tlbcam, MAS7));
+#endif
#ifdef CONFIG_KVM_EXIT_TIMING
DEFINE(VCPU_TIMING_EXIT_TBU, offsetof(struct kvm_vcpu,
/* Global pointer to shared data; NULL means no measured launch. */
struct tboot *tboot __read_mostly;
+ EXPORT_SYMBOL(tboot);
/* timeout for APs (in secs) to enter wait-for-SIPI state during shutdown */
#define AP_WAIT_TIMEOUT 1
struct tboot_mac_region *mr;
phys_addr_t end = start + size;
+ if (tboot->num_mac_regions >= MAX_TB_MAC_REGIONS)
+ panic("tboot: Too many MAC regions\n");
+
if (start && size) {
mr = &tboot->mac_regions[tboot->num_mac_regions++];
mr->start = round_down(start, PAGE_SIZE);
static int tboot_setup_sleep(void)
{
+ int i;
+
tboot->num_mac_regions = 0;
- /* S3 resume code */
- add_mac_region(acpi_wakeup_address, WAKEUP_SIZE);
+ for (i = 0; i < e820.nr_map; i++) {
+ if ((e820.map[i].type != E820_RAM)
+ && (e820.map[i].type != E820_RESERVED_KERN))
+ continue;
-#ifdef CONFIG_X86_TRAMPOLINE
- /* AP trampoline code */
- add_mac_region(virt_to_phys(trampoline_base), TRAMPOLINE_SIZE);
-#endif
-
- /* kernel code + data + bss */
- add_mac_region(virt_to_phys(_text), _end - _text);
+ add_mac_region(e820.map[i].addr, e820.map[i].size);
+ }
tboot->acpi_sinfo.kernel_s3_resume_vector = acpi_wakeup_address;
#define SEG_TYPE_LDT 2
#define SEG_TYPE_BUSY_TSS16 3
- #define SVM_FEATURE_NPT (1 << 0)
- #define SVM_FEATURE_LBRV (1 << 1)
- #define SVM_FEATURE_SVML (1 << 2)
- #define SVM_FEATURE_PAUSE_FILTER (1 << 10)
+ #define SVM_FEATURE_NPT (1 << 0)
+ #define SVM_FEATURE_LBRV (1 << 1)
+ #define SVM_FEATURE_SVML (1 << 2)
+ #define SVM_FEATURE_NRIP (1 << 3)
+ #define SVM_FEATURE_PAUSE_FILTER (1 << 10)
#define NESTED_EXIT_HOST 0 /* Exit handled on host level */
#define NESTED_EXIT_DONE 1 /* Exit caused nested vmexit */
struct nested_state {
struct vmcb *hsave;
u64 hsave_msr;
+ u64 vm_cr_msr;
u64 vmcb;
/* These are the merged vectors */
/* gpa pointers to the real vectors */
u64 vmcb_msrpm;
+ u64 vmcb_iopm;
/* A VMEXIT is required but not yet emulated */
bool exit_required;
};
+ #define MSRPM_OFFSETS 16
+ static u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
+
struct vcpu_svm {
struct kvm_vcpu vcpu;
struct vmcb *vmcb;
struct nested_state nested;
bool nmi_singlestep;
+
+ unsigned int3_injected;
+ unsigned long int3_rip;
+ };
+
+ #define MSR_INVALID 0xffffffffU
+
+ static struct svm_direct_access_msrs {
+ u32 index; /* Index of the MSR */
+ bool always; /* True if intercept is always on */
+ } direct_access_msrs[] = {
+ { .index = MSR_K6_STAR, .always = true },
+ { .index = MSR_IA32_SYSENTER_CS, .always = true },
+ #ifdef CONFIG_X86_64
+ { .index = MSR_GS_BASE, .always = true },
+ { .index = MSR_FS_BASE, .always = true },
+ { .index = MSR_KERNEL_GS_BASE, .always = true },
+ { .index = MSR_LSTAR, .always = true },
+ { .index = MSR_CSTAR, .always = true },
+ { .index = MSR_SYSCALL_MASK, .always = true },
+ #endif
+ { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false },
+ { .index = MSR_IA32_LASTBRANCHTOIP, .always = false },
+ { .index = MSR_IA32_LASTINTFROMIP, .always = false },
+ { .index = MSR_IA32_LASTINTTOIP, .always = false },
+ { .index = MSR_INVALID, .always = false },
};
/* enable NPT for AMD64 and X86 with PAE */
#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
static bool npt_enabled = true;
#else
- static bool npt_enabled = false;
+ static bool npt_enabled;
#endif
static int npt = 1;
static void svm_complete_interrupts(struct vcpu_svm *svm);
static int nested_svm_exit_handled(struct vcpu_svm *svm);
+ static int nested_svm_intercept(struct vcpu_svm *svm);
static int nested_svm_vmexit(struct vcpu_svm *svm);
static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
bool has_error_code, u32 error_code);
struct kvm_ldttss_desc {
u16 limit0;
u16 base0;
- unsigned base1 : 8, type : 5, dpl : 2, p : 1;
- unsigned limit1 : 4, zero0 : 3, g : 1, base2 : 8;
+ unsigned base1:8, type:5, dpl:2, p:1;
+ unsigned limit1:4, zero0:3, g:1, base2:8;
u32 base3;
u32 zero1;
} __attribute__((packed));
#define MSRS_RANGE_SIZE 2048
#define MSRS_IN_RANGE (MSRS_RANGE_SIZE * 8 / 2)
+ static u32 svm_msrpm_offset(u32 msr)
+ {
+ u32 offset;
+ int i;
+
+ for (i = 0; i < NUM_MSR_MAPS; i++) {
+ if (msr < msrpm_ranges[i] ||
+ msr >= msrpm_ranges[i] + MSRS_IN_RANGE)
+ continue;
+
+ offset = (msr - msrpm_ranges[i]) / 4; /* 4 msrs per u8 */
+ offset += (i * MSRS_RANGE_SIZE); /* add range offset */
+
+ /* Now we have the u8 offset - but need the u32 offset */
+ return offset / 4;
+ }
+
+ /* MSR not in any range */
+ return MSR_INVALID;
+ }
+
#define MAX_INST_SIZE 15
static inline u32 svm_has(u32 feat)
static inline void invlpga(unsigned long addr, u32 asid)
{
- asm volatile (__ex(SVM_INVLPGA) :: "a"(addr), "c"(asid));
+ asm volatile (__ex(SVM_INVLPGA) : : "a"(addr), "c"(asid));
}
static inline void force_new_asid(struct kvm_vcpu *vcpu)
vcpu->arch.efer = efer;
}
- static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
- bool has_error_code, u32 error_code)
- {
- struct vcpu_svm *svm = to_svm(vcpu);
-
- /* If we are within a nested VM we'd better #VMEXIT and let the
- guest handle the exception */
- if (nested_svm_check_exception(svm, nr, has_error_code, error_code))
- return;
-
- svm->vmcb->control.event_inj = nr
- | SVM_EVTINJ_VALID
- | (has_error_code ? SVM_EVTINJ_VALID_ERR : 0)
- | SVM_EVTINJ_TYPE_EXEPT;
- svm->vmcb->control.event_inj_err = error_code;
- }
-
static int is_external_interrupt(u32 info)
{
info &= SVM_EVTINJ_TYPE_MASK | SVM_EVTINJ_VALID;
u32 ret = 0;
if (svm->vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK)
- ret |= X86_SHADOW_INT_STI | X86_SHADOW_INT_MOV_SS;
+ ret |= KVM_X86_SHADOW_INT_STI | KVM_X86_SHADOW_INT_MOV_SS;
return ret & mask;
}
{
struct vcpu_svm *svm = to_svm(vcpu);
+ if (svm->vmcb->control.next_rip != 0)
+ svm->next_rip = svm->vmcb->control.next_rip;
+
if (!svm->next_rip) {
if (emulate_instruction(vcpu, 0, 0, EMULTYPE_SKIP) !=
EMULATE_DONE)
svm_set_interrupt_shadow(vcpu, 0);
}
+ static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
+ bool has_error_code, u32 error_code,
+ bool reinject)
+ {
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ /*
+ * If we are within a nested VM we'd better #VMEXIT and let the guest
+ * handle the exception
+ */
+ if (!reinject &&
+ nested_svm_check_exception(svm, nr, has_error_code, error_code))
+ return;
+
+ if (nr == BP_VECTOR && !svm_has(SVM_FEATURE_NRIP)) {
+ unsigned long rip, old_rip = kvm_rip_read(&svm->vcpu);
+
+ /*
+ * For guest debugging where we have to reinject #BP if some
+ * INT3 is guest-owned:
+ * Emulate nRIP by moving RIP forward. Will fail if injection
+ * raises a fault that is not intercepted. Still better than
+ * failing in all cases.
+ */
+ skip_emulated_instruction(&svm->vcpu);
+ rip = kvm_rip_read(&svm->vcpu);
+ svm->int3_rip = rip + svm->vmcb->save.cs.base;
+ svm->int3_injected = rip - old_rip;
+ }
+
+ svm->vmcb->control.event_inj = nr
+ | SVM_EVTINJ_VALID
+ | (has_error_code ? SVM_EVTINJ_VALID_ERR : 0)
+ | SVM_EVTINJ_TYPE_EXEPT;
+ svm->vmcb->control.event_inj_err = error_code;
+ }
+
static int has_svm(void)
{
const char *msg;
struct svm_cpu_data *sd;
uint64_t efer;
- struct descriptor_table gdt_descr;
+ struct desc_ptr gdt_descr;
struct desc_struct *gdt;
int me = raw_smp_processor_id();
sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1;
sd->next_asid = sd->max_asid + 1;
- kvm_get_gdt(&gdt_descr);
- gdt = (struct desc_struct *)gdt_descr.base;
+ native_store_gdt(&gdt_descr);
+ gdt = (struct desc_struct *)gdt_descr.address;
sd->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS);
wrmsrl(MSR_EFER, efer | EFER_SVME);
}
+ static bool valid_msr_intercept(u32 index)
+ {
+ int i;
+
+ for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++)
+ if (direct_access_msrs[i].index == index)
+ return true;
+
+ return false;
+ }
+
static void set_msr_interception(u32 *msrpm, unsigned msr,
int read, int write)
{
+ u8 bit_read, bit_write;
+ unsigned long tmp;
+ u32 offset;
+
+ /*
+ * If this warning triggers extend the direct_access_msrs list at the
+ * beginning of the file
+ */
+ WARN_ON(!valid_msr_intercept(msr));
+
+ offset = svm_msrpm_offset(msr);
+ bit_read = 2 * (msr & 0x0f);
+ bit_write = 2 * (msr & 0x0f) + 1;
+ tmp = msrpm[offset];
+
+ BUG_ON(offset == MSR_INVALID);
+
+ read ? clear_bit(bit_read, &tmp) : set_bit(bit_read, &tmp);
+ write ? clear_bit(bit_write, &tmp) : set_bit(bit_write, &tmp);
+
+ msrpm[offset] = tmp;
+ }
+
+ static void svm_vcpu_init_msrpm(u32 *msrpm)
+ {
int i;
- for (i = 0; i < NUM_MSR_MAPS; i++) {
- if (msr >= msrpm_ranges[i] &&
- msr < msrpm_ranges[i] + MSRS_IN_RANGE) {
- u32 msr_offset = (i * MSRS_IN_RANGE + msr -
- msrpm_ranges[i]) * 2;
-
- u32 *base = msrpm + (msr_offset / 32);
- u32 msr_shift = msr_offset % 32;
- u32 mask = ((write) ? 0 : 2) | ((read) ? 0 : 1);
- *base = (*base & ~(0x3 << msr_shift)) |
- (mask << msr_shift);
+ memset(msrpm, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER));
+
+ for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
+ if (!direct_access_msrs[i].always)
+ continue;
+
+ set_msr_interception(msrpm, direct_access_msrs[i].index, 1, 1);
+ }
+ }
+
+ static void add_msr_offset(u32 offset)
+ {
+ int i;
+
+ for (i = 0; i < MSRPM_OFFSETS; ++i) {
+
+ /* Offset already in list? */
+ if (msrpm_offsets[i] == offset)
return;
- }
+
+ /* Slot used by another offset? */
+ if (msrpm_offsets[i] != MSR_INVALID)
+ continue;
+
+ /* Add offset to list */
+ msrpm_offsets[i] = offset;
+
+ return;
}
+
+ /*
+ * If this BUG triggers the msrpm_offsets table has an overflow. Just
+ * increase MSRPM_OFFSETS in this case.
+ */
BUG();
}
- static void svm_vcpu_init_msrpm(u32 *msrpm)
+ static void init_msrpm_offsets(void)
{
- memset(msrpm, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER));
+ int i;
- #ifdef CONFIG_X86_64
- set_msr_interception(msrpm, MSR_GS_BASE, 1, 1);
- set_msr_interception(msrpm, MSR_FS_BASE, 1, 1);
- set_msr_interception(msrpm, MSR_KERNEL_GS_BASE, 1, 1);
- set_msr_interception(msrpm, MSR_LSTAR, 1, 1);
- set_msr_interception(msrpm, MSR_CSTAR, 1, 1);
- set_msr_interception(msrpm, MSR_SYSCALL_MASK, 1, 1);
- #endif
- set_msr_interception(msrpm, MSR_K6_STAR, 1, 1);
- set_msr_interception(msrpm, MSR_IA32_SYSENTER_CS, 1, 1);
+ memset(msrpm_offsets, 0xff, sizeof(msrpm_offsets));
+
+ for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
+ u32 offset;
+
+ offset = svm_msrpm_offset(direct_access_msrs[i].index);
+ BUG_ON(offset == MSR_INVALID);
+
+ add_msr_offset(offset);
+ }
}
static void svm_enable_lbrv(struct vcpu_svm *svm)
memset(iopm_va, 0xff, PAGE_SIZE * (1 << IOPM_ALLOC_ORDER));
iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT;
+ init_msrpm_offsets();
+
if (boot_cpu_has(X86_FEATURE_NX))
kvm_enable_efer_bits(EFER_NX);
{
seg->selector = 0;
seg->attrib = SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK |
- SVM_SELECTOR_WRITE_MASK; /* Read/Write Data Segment */
+ SVM_SELECTOR_WRITE_MASK; /* Read/Write Data Segment */
seg->limit = 0xffff;
seg->base = 0;
}
svm->vcpu.fpu_active = 1;
- control->intercept_cr_read = INTERCEPT_CR0_MASK |
+ control->intercept_cr_read = INTERCEPT_CR0_MASK |
INTERCEPT_CR3_MASK |
INTERCEPT_CR4_MASK;
- control->intercept_cr_write = INTERCEPT_CR0_MASK |
+ control->intercept_cr_write = INTERCEPT_CR0_MASK |
INTERCEPT_CR3_MASK |
INTERCEPT_CR4_MASK |
INTERCEPT_CR8_MASK;
- control->intercept_dr_read = INTERCEPT_DR0_MASK |
+ control->intercept_dr_read = INTERCEPT_DR0_MASK |
INTERCEPT_DR1_MASK |
INTERCEPT_DR2_MASK |
INTERCEPT_DR3_MASK |
INTERCEPT_DR6_MASK |
INTERCEPT_DR7_MASK;
- control->intercept_dr_write = INTERCEPT_DR0_MASK |
+ control->intercept_dr_write = INTERCEPT_DR0_MASK |
INTERCEPT_DR1_MASK |
INTERCEPT_DR2_MASK |
INTERCEPT_DR3_MASK |
(1 << MC_VECTOR);
- control->intercept = (1ULL << INTERCEPT_INTR) |
+ control->intercept = (1ULL << INTERCEPT_INTR) |
(1ULL << INTERCEPT_NMI) |
(1ULL << INTERCEPT_SMI) |
(1ULL << INTERCEPT_SELECTIVE_CR0) |
save->rip = 0x0000fff0;
svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip;
- /* This is the guest-visible cr0 value.
+ /*
+ * This is the guest-visible cr0 value.
* svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0.
*/
svm->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
svm_vcpu_init_msrpm(svm->msrpm);
svm->nested.msrpm = page_address(nested_msrpm_pages);
+ svm_vcpu_init_msrpm(svm->nested.msrpm);
svm->vmcb = page_address(page);
clear_page(svm->vmcb);
var->db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1;
var->g = (s->attrib >> SVM_SELECTOR_G_SHIFT) & 1;
- /* AMD's VMCB does not have an explicit unusable field, so emulate it
+ /*
+ * AMD's VMCB does not have an explicit unusable field, so emulate it
* for cross vendor migration purposes by "not present"
*/
var->unusable = !var->present || (var->type == 0);
var->type |= 0x1;
break;
case VCPU_SREG_SS:
- /* On AMD CPUs sometimes the DB bit in the segment
+ /*
+ * On AMD CPUs sometimes the DB bit in the segment
* descriptor is left as 1, although the whole segment has
* been made unusable. Clear it here to pass an Intel VMX
* entry check when cross vendor migrating.
return save->cpl;
}
- static void svm_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+ static void svm_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
struct vcpu_svm *svm = to_svm(vcpu);
- dt->limit = svm->vmcb->save.idtr.limit;
- dt->base = svm->vmcb->save.idtr.base;
+ dt->size = svm->vmcb->save.idtr.limit;
+ dt->address = svm->vmcb->save.idtr.base;
}
- static void svm_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+ static void svm_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
struct vcpu_svm *svm = to_svm(vcpu);
- svm->vmcb->save.idtr.limit = dt->limit;
- svm->vmcb->save.idtr.base = dt->base ;
+ svm->vmcb->save.idtr.limit = dt->size;
+ svm->vmcb->save.idtr.base = dt->address ;
}
- static void svm_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+ static void svm_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
struct vcpu_svm *svm = to_svm(vcpu);
- dt->limit = svm->vmcb->save.gdtr.limit;
- dt->base = svm->vmcb->save.gdtr.base;
+ dt->size = svm->vmcb->save.gdtr.limit;
+ dt->address = svm->vmcb->save.gdtr.base;
}
- static void svm_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+ static void svm_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
struct vcpu_svm *svm = to_svm(vcpu);
- svm->vmcb->save.gdtr.limit = dt->limit;
- svm->vmcb->save.gdtr.base = dt->base ;
+ svm->vmcb->save.gdtr.limit = dt->size;
+ svm->vmcb->save.gdtr.base = dt->address ;
}
static void svm_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
static void update_cr0_intercept(struct vcpu_svm *svm)
{
+ struct vmcb *vmcb = svm->vmcb;
ulong gcr0 = svm->vcpu.arch.cr0;
u64 *hcr0 = &svm->vmcb->save.cr0;
if (gcr0 == *hcr0 && svm->vcpu.fpu_active) {
- svm->vmcb->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK;
- svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK;
+ vmcb->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK;
+ vmcb->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK;
+ if (is_nested(svm)) {
+ struct vmcb *hsave = svm->nested.hsave;
+
+ hsave->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK;
+ hsave->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK;
+ vmcb->control.intercept_cr_read |= svm->nested.intercept_cr_read;
+ vmcb->control.intercept_cr_write |= svm->nested.intercept_cr_write;
+ }
} else {
svm->vmcb->control.intercept_cr_read |= INTERCEPT_CR0_MASK;
svm->vmcb->control.intercept_cr_write |= INTERCEPT_CR0_MASK;
+ if (is_nested(svm)) {
+ struct vmcb *hsave = svm->nested.hsave;
+
+ hsave->control.intercept_cr_read |= INTERCEPT_CR0_MASK;
+ hsave->control.intercept_cr_write |= INTERCEPT_CR0_MASK;
+ }
}
}
{
struct vcpu_svm *svm = to_svm(vcpu);
+ if (is_nested(svm)) {
+ /*
+ * We are here because we run in nested mode, the host kvm
+ * intercepts cr0 writes but the l1 hypervisor does not.
+ * But the L1 hypervisor may intercept selective cr0 writes.
+ * This needs to be checked here.
+ */
+ unsigned long old, new;
+
+ /* Remove bits that would trigger a real cr0 write intercept */
+ old = vcpu->arch.cr0 & SVM_CR0_SELECTIVE_MASK;
+ new = cr0 & SVM_CR0_SELECTIVE_MASK;
+
+ if (old == new) {
+ /* cr0 write with ts and mp unchanged */
+ svm->vmcb->control.exit_code = SVM_EXIT_CR0_SEL_WRITE;
+ if (nested_svm_exit_handled(svm) == NESTED_EXIT_DONE)
+ return;
+ }
+ }
+
#ifdef CONFIG_X86_64
if (vcpu->arch.efer & EFER_LME) {
if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) {
svm->vmcb->control.asid = sd->next_asid++;
}
- static int svm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *dest)
+ static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value)
{
struct vcpu_svm *svm = to_svm(vcpu);
- switch (dr) {
- case 0 ... 3:
- *dest = vcpu->arch.db[dr];
- break;
- case 4:
- if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
- return EMULATE_FAIL; /* will re-inject UD */
- /* fall through */
- case 6:
- if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
- *dest = vcpu->arch.dr6;
- else
- *dest = svm->vmcb->save.dr6;
- break;
- case 5:
- if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
- return EMULATE_FAIL; /* will re-inject UD */
- /* fall through */
- case 7:
- if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
- *dest = vcpu->arch.dr7;
- else
- *dest = svm->vmcb->save.dr7;
- break;
- }
-
- return EMULATE_DONE;
- }
-
- static int svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value)
- {
- struct vcpu_svm *svm = to_svm(vcpu);
-
- switch (dr) {
- case 0 ... 3:
- vcpu->arch.db[dr] = value;
- if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
- vcpu->arch.eff_db[dr] = value;
- break;
- case 4:
- if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
- return EMULATE_FAIL; /* will re-inject UD */
- /* fall through */
- case 6:
- vcpu->arch.dr6 = (value & DR6_VOLATILE) | DR6_FIXED_1;
- break;
- case 5:
- if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
- return EMULATE_FAIL; /* will re-inject UD */
- /* fall through */
- case 7:
- vcpu->arch.dr7 = (value & DR7_VOLATILE) | DR7_FIXED_1;
- if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
- svm->vmcb->save.dr7 = vcpu->arch.dr7;
- vcpu->arch.switch_db_regs = (value & DR7_BP_EN_MASK);
- }
- break;
- }
-
- return EMULATE_DONE;
+ svm->vmcb->save.dr7 = value;
}
static int pf_interception(struct vcpu_svm *svm)
}
if (svm->vcpu.guest_debug &
- (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)){
+ (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) {
kvm_run->exit_reason = KVM_EXIT_DEBUG;
kvm_run->debug.arch.pc =
svm->vmcb->save.cs.base + svm->vmcb->save.rip;
static void svm_fpu_activate(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR);
+ u32 excp;
+
+ if (is_nested(svm)) {
+ u32 h_excp, n_excp;
+
+ h_excp = svm->nested.hsave->control.intercept_exceptions;
+ n_excp = svm->nested.intercept_exceptions;
+ h_excp &= ~(1 << NM_VECTOR);
+ excp = h_excp | n_excp;
+ } else {
+ excp = svm->vmcb->control.intercept_exceptions;
+ excp &= ~(1 << NM_VECTOR);
+ }
+
+ svm->vmcb->control.intercept_exceptions = excp;
+
svm->vcpu.fpu_active = 1;
update_cr0_intercept(svm);
}
static int io_interception(struct vcpu_svm *svm)
{
+ struct kvm_vcpu *vcpu = &svm->vcpu;
u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */
int size, in, string;
unsigned port;
++svm->vcpu.stat.io_exits;
-
- svm->next_rip = svm->vmcb->control.exit_info_2;
-
string = (io_info & SVM_IOIO_STR_MASK) != 0;
-
- if (string) {
- if (emulate_instruction(&svm->vcpu,
- 0, 0, 0) == EMULATE_DO_MMIO)
- return 0;
- return 1;
- }
-
in = (io_info & SVM_IOIO_TYPE_MASK) != 0;
+ if (string || in)
+ return !(emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO);
+
port = io_info >> 16;
size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT;
-
+ svm->next_rip = svm->vmcb->control.exit_info_2;
skip_emulated_instruction(&svm->vcpu);
- return kvm_emulate_pio(&svm->vcpu, in, size, port);
+
+ return kvm_fast_pio_out(vcpu, size, port);
}
static int nmi_interception(struct vcpu_svm *svm)
static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
bool has_error_code, u32 error_code)
{
+ int vmexit;
+
if (!is_nested(svm))
return 0;
svm->vmcb->control.exit_info_1 = error_code;
svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2;
- return nested_svm_exit_handled(svm);
+ vmexit = nested_svm_intercept(svm);
+ if (vmexit == NESTED_EXIT_DONE)
+ svm->nested.exit_required = true;
+
+ return vmexit;
}
- static inline int nested_svm_intr(struct vcpu_svm *svm)
+ /* This function returns true if it is save to enable the irq window */
+ static inline bool nested_svm_intr(struct vcpu_svm *svm)
{
if (!is_nested(svm))
- return 0;
+ return true;
if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK))
- return 0;
+ return true;
if (!(svm->vcpu.arch.hflags & HF_HIF_MASK))
- return 0;
+ return false;
- svm->vmcb->control.exit_code = SVM_EXIT_INTR;
+ svm->vmcb->control.exit_code = SVM_EXIT_INTR;
+ svm->vmcb->control.exit_info_1 = 0;
+ svm->vmcb->control.exit_info_2 = 0;
if (svm->nested.intercept & 1ULL) {
/*
*/
svm->nested.exit_required = true;
trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip);
- return 1;
+ return false;
}
- return 0;
+ return true;
+ }
+
+ /* This function returns true if it is save to enable the nmi window */
+ static inline bool nested_svm_nmi(struct vcpu_svm *svm)
+ {
+ if (!is_nested(svm))
+ return true;
+
+ if (!(svm->nested.intercept & (1ULL << INTERCEPT_NMI)))
+ return true;
+
+ svm->vmcb->control.exit_code = SVM_EXIT_NMI;
+ svm->nested.exit_required = true;
+
+ return false;
}
- static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, enum km_type idx)
+ static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, struct page **_page)
{
struct page *page;
+ might_sleep();
+
page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT);
if (is_error_page(page))
goto error;
- return kmap_atomic(page, idx);
+ *_page = page;
+
+ return kmap(page);
error:
kvm_release_page_clean(page);
return NULL;
}
- static void nested_svm_unmap(void *addr, enum km_type idx)
+ static void nested_svm_unmap(struct page *page)
{
- struct page *page;
+ kunmap(page);
+ kvm_release_page_dirty(page);
+ }
- if (!addr)
- return;
+ static int nested_svm_intercept_ioio(struct vcpu_svm *svm)
+ {
+ unsigned port;
+ u8 val, bit;
+ u64 gpa;
- page = kmap_atomic_to_page(addr);
+ if (!(svm->nested.intercept & (1ULL << INTERCEPT_IOIO_PROT)))
+ return NESTED_EXIT_HOST;
- kunmap_atomic(addr, idx);
- kvm_release_page_dirty(page);
+ port = svm->vmcb->control.exit_info_1 >> 16;
+ gpa = svm->nested.vmcb_iopm + (port / 8);
+ bit = port % 8;
+ val = 0;
+
+ if (kvm_read_guest(svm->vcpu.kvm, gpa, &val, 1))
+ val &= (1 << bit);
+
+ return val ? NESTED_EXIT_DONE : NESTED_EXIT_HOST;
}
- static bool nested_svm_exit_handled_msr(struct vcpu_svm *svm)
+ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm)
{
- u32 param = svm->vmcb->control.exit_info_1 & 1;
- u32 msr = svm->vcpu.arch.regs[VCPU_REGS_RCX];
- bool ret = false;
- u32 t0, t1;
- u8 *msrpm;
+ u32 offset, msr, value;
+ int write, mask;
if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT)))
- return false;
+ return NESTED_EXIT_HOST;
- msrpm = nested_svm_map(svm, svm->nested.vmcb_msrpm, KM_USER0);
+ msr = svm->vcpu.arch.regs[VCPU_REGS_RCX];
+ offset = svm_msrpm_offset(msr);
+ write = svm->vmcb->control.exit_info_1 & 1;
+ mask = 1 << ((2 * (msr & 0xf)) + write);
- if (!msrpm)
- goto out;
+ if (offset == MSR_INVALID)
+ return NESTED_EXIT_DONE;
- switch (msr) {
- case 0 ... 0x1fff:
- t0 = (msr * 2) % 8;
- t1 = msr / 8;
- break;
- case 0xc0000000 ... 0xc0001fff:
- t0 = (8192 + msr - 0xc0000000) * 2;
- t1 = (t0 / 8);
- t0 %= 8;
- break;
- case 0xc0010000 ... 0xc0011fff:
- t0 = (16384 + msr - 0xc0010000) * 2;
- t1 = (t0 / 8);
- t0 %= 8;
- break;
- default:
- ret = true;
- goto out;
- }
+ /* Offset is in 32 bit units but need in 8 bit units */
+ offset *= 4;
- ret = msrpm[t1] & ((1 << param) << t0);
-
- out:
- nested_svm_unmap(msrpm, KM_USER0);
+ if (kvm_read_guest(svm->vcpu.kvm, svm->nested.vmcb_msrpm + offset, &value, 4))
+ return NESTED_EXIT_DONE;
- return ret;
+ return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST;
}
static int nested_svm_exit_special(struct vcpu_svm *svm)
switch (exit_code) {
case SVM_EXIT_INTR:
case SVM_EXIT_NMI:
+ case SVM_EXIT_EXCP_BASE + MC_VECTOR:
return NESTED_EXIT_HOST;
- /* For now we are always handling NPFs when using them */
case SVM_EXIT_NPF:
+ /* For now we are always handling NPFs when using them */
if (npt_enabled)
return NESTED_EXIT_HOST;
break;
- /* When we're shadowing, trap PFs */
case SVM_EXIT_EXCP_BASE + PF_VECTOR:
+ /* When we're shadowing, trap PFs */
if (!npt_enabled)
return NESTED_EXIT_HOST;
break;
+ case SVM_EXIT_EXCP_BASE + NM_VECTOR:
+ nm_interception(svm);
+ break;
default:
break;
}
/*
* If this function returns true, this #vmexit was already handled
*/
- static int nested_svm_exit_handled(struct vcpu_svm *svm)
+ static int nested_svm_intercept(struct vcpu_svm *svm)
{
u32 exit_code = svm->vmcb->control.exit_code;
int vmexit = NESTED_EXIT_HOST;
case SVM_EXIT_MSR:
vmexit = nested_svm_exit_handled_msr(svm);
break;
+ case SVM_EXIT_IOIO:
+ vmexit = nested_svm_intercept_ioio(svm);
+ break;
case SVM_EXIT_READ_CR0 ... SVM_EXIT_READ_CR8: {
u32 cr_bits = 1 << (exit_code - SVM_EXIT_READ_CR0);
if (svm->nested.intercept_cr_read & cr_bits)
vmexit = NESTED_EXIT_DONE;
break;
}
+ case SVM_EXIT_ERR: {
+ vmexit = NESTED_EXIT_DONE;
+ break;
+ }
default: {
u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR);
if (svm->nested.intercept & exit_bits)
}
}
- if (vmexit == NESTED_EXIT_DONE) {
+ return vmexit;
+ }
+
+ static int nested_svm_exit_handled(struct vcpu_svm *svm)
+ {
+ int vmexit;
+
+ vmexit = nested_svm_intercept(svm);
+
+ if (vmexit == NESTED_EXIT_DONE)
nested_svm_vmexit(svm);
- }
return vmexit;
}
struct vmcb *nested_vmcb;
struct vmcb *hsave = svm->nested.hsave;
struct vmcb *vmcb = svm->vmcb;
+ struct page *page;
trace_kvm_nested_vmexit_inject(vmcb->control.exit_code,
vmcb->control.exit_info_1,
vmcb->control.exit_int_info,
vmcb->control.exit_int_info_err);
- nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, KM_USER0);
+ nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, &page);
if (!nested_vmcb)
return 1;
+ /* Exit nested SVM mode */
+ svm->nested.vmcb = 0;
+
/* Give the current vmcb to the guest */
disable_gif(svm);
nested_vmcb->save.ds = vmcb->save.ds;
nested_vmcb->save.gdtr = vmcb->save.gdtr;
nested_vmcb->save.idtr = vmcb->save.idtr;
- if (npt_enabled)
- nested_vmcb->save.cr3 = vmcb->save.cr3;
+ nested_vmcb->save.cr0 = kvm_read_cr0(&svm->vcpu);
+ nested_vmcb->save.cr3 = svm->vcpu.arch.cr3;
nested_vmcb->save.cr2 = vmcb->save.cr2;
+ nested_vmcb->save.cr4 = svm->vcpu.arch.cr4;
nested_vmcb->save.rflags = vmcb->save.rflags;
nested_vmcb->save.rip = vmcb->save.rip;
nested_vmcb->save.rsp = vmcb->save.rsp;
svm->vmcb->save.cpl = 0;
svm->vmcb->control.exit_int_info = 0;
- /* Exit nested SVM mode */
- svm->nested.vmcb = 0;
-
- nested_svm_unmap(nested_vmcb, KM_USER0);
+ nested_svm_unmap(page);
kvm_mmu_reset_context(&svm->vcpu);
kvm_mmu_load(&svm->vcpu);
static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
{
- u32 *nested_msrpm;
+ /*
+ * This function merges the msr permission bitmaps of kvm and the
+ * nested vmcb. It is omptimized in that it only merges the parts where
+ * the kvm msr permission bitmap may contain zero bits
+ */
int i;
- nested_msrpm = nested_svm_map(svm, svm->nested.vmcb_msrpm, KM_USER0);
- if (!nested_msrpm)
- return false;
+ if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT)))
+ return true;
- for (i=0; i< PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER) / 4; i++)
- svm->nested.msrpm[i] = svm->msrpm[i] | nested_msrpm[i];
+ for (i = 0; i < MSRPM_OFFSETS; i++) {
+ u32 value, p;
+ u64 offset;
- svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm);
+ if (msrpm_offsets[i] == 0xffffffff)
+ break;
+
+ p = msrpm_offsets[i];
+ offset = svm->nested.vmcb_msrpm + (p * 4);
+
+ if (kvm_read_guest(svm->vcpu.kvm, offset, &value, 4))
+ return false;
+
+ svm->nested.msrpm[p] = svm->msrpm[p] | value;
+ }
- nested_svm_unmap(nested_msrpm, KM_USER0);
+ svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm);
return true;
}
struct vmcb *nested_vmcb;
struct vmcb *hsave = svm->nested.hsave;
struct vmcb *vmcb = svm->vmcb;
+ struct page *page;
+ u64 vmcb_gpa;
- nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0);
+ vmcb_gpa = svm->vmcb->save.rax;
+
+ nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
if (!nested_vmcb)
return false;
- /* nested_vmcb is our indicator if nested SVM is activated */
- svm->nested.vmcb = svm->vmcb->save.rax;
-
- trace_kvm_nested_vmrun(svm->vmcb->save.rip - 3, svm->nested.vmcb,
+ trace_kvm_nested_vmrun(svm->vmcb->save.rip - 3, vmcb_gpa,
nested_vmcb->save.rip,
nested_vmcb->control.int_ctl,
nested_vmcb->control.event_inj,
nested_vmcb->control.nested_ctl);
+ trace_kvm_nested_intercepts(nested_vmcb->control.intercept_cr_read,
+ nested_vmcb->control.intercept_cr_write,
+ nested_vmcb->control.intercept_exceptions,
+ nested_vmcb->control.intercept);
+
/* Clear internal status */
kvm_clear_exception_queue(&svm->vcpu);
kvm_clear_interrupt_queue(&svm->vcpu);
- /* Save the old vmcb, so we don't need to pick what we save, but
- can restore everything when a VMEXIT occurs */
+ /*
+ * Save the old vmcb, so we don't need to pick what we save, but can
+ * restore everything when a VMEXIT occurs
+ */
hsave->save.es = vmcb->save.es;
hsave->save.cs = vmcb->save.cs;
hsave->save.ss = vmcb->save.ss;
if (npt_enabled) {
svm->vmcb->save.cr3 = nested_vmcb->save.cr3;
svm->vcpu.arch.cr3 = nested_vmcb->save.cr3;
- } else {
+ } else
kvm_set_cr3(&svm->vcpu, nested_vmcb->save.cr3);
- kvm_mmu_reset_context(&svm->vcpu);
- }
+
+ /* Guest paging mode is active - reset mmu */
+ kvm_mmu_reset_context(&svm->vcpu);
+
svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = nested_vmcb->save.cr2;
kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, nested_vmcb->save.rax);
kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, nested_vmcb->save.rsp);
kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, nested_vmcb->save.rip);
+
/* In case we don't even reach vcpu_run, the fields are not updated */
svm->vmcb->save.rax = nested_vmcb->save.rax;
svm->vmcb->save.rsp = nested_vmcb->save.rsp;
svm->vmcb->save.dr6 = nested_vmcb->save.dr6;
svm->vmcb->save.cpl = nested_vmcb->save.cpl;
- /* We don't want a nested guest to be more powerful than the guest,
- so all intercepts are ORed */
- svm->vmcb->control.intercept_cr_read |=
- nested_vmcb->control.intercept_cr_read;
- svm->vmcb->control.intercept_cr_write |=
- nested_vmcb->control.intercept_cr_write;
- svm->vmcb->control.intercept_dr_read |=
- nested_vmcb->control.intercept_dr_read;
- svm->vmcb->control.intercept_dr_write |=
- nested_vmcb->control.intercept_dr_write;
- svm->vmcb->control.intercept_exceptions |=
- nested_vmcb->control.intercept_exceptions;
-
- svm->vmcb->control.intercept |= nested_vmcb->control.intercept;
-
- svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa;
+ svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa & ~0x0fffULL;
+ svm->nested.vmcb_iopm = nested_vmcb->control.iopm_base_pa & ~0x0fffULL;
/* cache intercepts */
svm->nested.intercept_cr_read = nested_vmcb->control.intercept_cr_read;
else
svm->vcpu.arch.hflags &= ~HF_VINTR_MASK;
+ if (svm->vcpu.arch.hflags & HF_VINTR_MASK) {
+ /* We only want the cr8 intercept bits of the guest */
+ svm->vmcb->control.intercept_cr_read &= ~INTERCEPT_CR8_MASK;
+ svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR8_MASK;
+ }
+
+ /* We don't want to see VMMCALLs from a nested guest */
+ svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_VMMCALL);
+
+ /*
+ * We don't want a nested guest to be more powerful than the guest, so
+ * all intercepts are ORed
+ */
+ svm->vmcb->control.intercept_cr_read |=
+ nested_vmcb->control.intercept_cr_read;
+ svm->vmcb->control.intercept_cr_write |=
+ nested_vmcb->control.intercept_cr_write;
+ svm->vmcb->control.intercept_dr_read |=
+ nested_vmcb->control.intercept_dr_read;
+ svm->vmcb->control.intercept_dr_write |=
+ nested_vmcb->control.intercept_dr_write;
+ svm->vmcb->control.intercept_exceptions |=
+ nested_vmcb->control.intercept_exceptions;
+
+ svm->vmcb->control.intercept |= nested_vmcb->control.intercept;
+
+ svm->vmcb->control.lbr_ctl = nested_vmcb->control.lbr_ctl;
svm->vmcb->control.int_vector = nested_vmcb->control.int_vector;
svm->vmcb->control.int_state = nested_vmcb->control.int_state;
svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset;
svm->vmcb->control.event_inj = nested_vmcb->control.event_inj;
svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err;
- nested_svm_unmap(nested_vmcb, KM_USER0);
+ nested_svm_unmap(page);
+
+ /* nested_vmcb is our indicator if nested SVM is activated */
+ svm->nested.vmcb = vmcb_gpa;
enable_gif(svm);
static int vmload_interception(struct vcpu_svm *svm)
{
struct vmcb *nested_vmcb;
+ struct page *page;
if (nested_svm_check_permissions(svm))
return 1;
svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
skip_emulated_instruction(&svm->vcpu);
- nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0);
+ nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
if (!nested_vmcb)
return 1;
nested_svm_vmloadsave(nested_vmcb, svm->vmcb);
- nested_svm_unmap(nested_vmcb, KM_USER0);
+ nested_svm_unmap(page);
return 1;
}
static int vmsave_interception(struct vcpu_svm *svm)
{
struct vmcb *nested_vmcb;
+ struct page *page;
if (nested_svm_check_permissions(svm))
return 1;
svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
skip_emulated_instruction(&svm->vcpu);
- nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0);
+ nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
if (!nested_vmcb)
return 1;
nested_svm_vmloadsave(svm->vmcb, nested_vmcb);
- nested_svm_unmap(nested_vmcb, KM_USER0);
+ nested_svm_unmap(page);
return 1;
}
svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_TYPE_MASK;
uint32_t idt_v =
svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_VALID;
+ bool has_error_code = false;
+ u32 error_code = 0;
tss_selector = (u16)svm->vmcb->control.exit_info_1;
svm->vcpu.arch.nmi_injected = false;
break;
case SVM_EXITINTINFO_TYPE_EXEPT:
+ if (svm->vmcb->control.exit_info_2 &
+ (1ULL << SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE)) {
+ has_error_code = true;
+ error_code =
+ (u32)svm->vmcb->control.exit_info_2;
+ }
kvm_clear_exception_queue(&svm->vcpu);
break;
case SVM_EXITINTINFO_TYPE_INTR:
(int_vec == OF_VECTOR || int_vec == BP_VECTOR)))
skip_emulated_instruction(&svm->vcpu);
- return kvm_task_switch(&svm->vcpu, tss_selector, reason);
+ if (kvm_task_switch(&svm->vcpu, tss_selector, reason,
+ has_error_code, error_code) == EMULATE_FAIL) {
+ svm->vcpu.run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+ svm->vcpu.run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+ svm->vcpu.run->internal.ndata = 0;
+ return 0;
+ }
+ return 1;
}
static int cpuid_interception(struct vcpu_svm *svm)
static int iret_interception(struct vcpu_svm *svm)
{
++svm->vcpu.stat.nmi_window_exits;
- svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET);
+ svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_IRET);
svm->vcpu.arch.hflags |= HF_IRET_MASK;
return 1;
}
case MSR_IA32_SYSENTER_ESP:
*data = svm->sysenter_esp;
break;
- /* Nobody will change the following 5 values in the VMCB so
- we can safely return them on rdmsr. They will always be 0
- until LBRV is implemented. */
+ /*
+ * Nobody will change the following 5 values in the VMCB so we can
+ * safely return them on rdmsr. They will always be 0 until LBRV is
+ * implemented.
+ */
case MSR_IA32_DEBUGCTLMSR:
*data = svm->vmcb->save.dbgctl;
break;
*data = svm->nested.hsave_msr;
break;
case MSR_VM_CR:
- *data = 0;
+ *data = svm->nested.vm_cr_msr;
break;
case MSR_IA32_UCODE_REV:
*data = 0x01000065;
return 1;
}
+ static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data)
+ {
+ struct vcpu_svm *svm = to_svm(vcpu);
+ int svm_dis, chg_mask;
+
+ if (data & ~SVM_VM_CR_VALID_MASK)
+ return 1;
+
+ chg_mask = SVM_VM_CR_VALID_MASK;
+
+ if (svm->nested.vm_cr_msr & SVM_VM_CR_SVM_DIS_MASK)
+ chg_mask &= ~(SVM_VM_CR_SVM_LOCK_MASK | SVM_VM_CR_SVM_DIS_MASK);
+
+ svm->nested.vm_cr_msr &= ~chg_mask;
+ svm->nested.vm_cr_msr |= (data & chg_mask);
+
+ svm_dis = svm->nested.vm_cr_msr & SVM_VM_CR_SVM_DIS_MASK;
+
+ /* check for svm_disable while efer.svme is set */
+ if (svm_dis && (vcpu->arch.efer & EFER_SVME))
+ return 1;
+
+ return 0;
+ }
+
static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data)
{
struct vcpu_svm *svm = to_svm(vcpu);
svm->nested.hsave_msr = data;
break;
case MSR_VM_CR:
+ return svm_set_vm_cr(vcpu, data);
case MSR_VM_IGNNE:
pr_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
break;
}
static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = {
- [SVM_EXIT_READ_CR0] = emulate_on_interception,
- [SVM_EXIT_READ_CR3] = emulate_on_interception,
- [SVM_EXIT_READ_CR4] = emulate_on_interception,
- [SVM_EXIT_READ_CR8] = emulate_on_interception,
+ [SVM_EXIT_READ_CR0] = emulate_on_interception,
+ [SVM_EXIT_READ_CR3] = emulate_on_interception,
+ [SVM_EXIT_READ_CR4] = emulate_on_interception,
+ [SVM_EXIT_READ_CR8] = emulate_on_interception,
[SVM_EXIT_CR0_SEL_WRITE] = emulate_on_interception,
- [SVM_EXIT_WRITE_CR0] = emulate_on_interception,
- [SVM_EXIT_WRITE_CR3] = emulate_on_interception,
- [SVM_EXIT_WRITE_CR4] = emulate_on_interception,
- [SVM_EXIT_WRITE_CR8] = cr8_write_interception,
- [SVM_EXIT_READ_DR0] = emulate_on_interception,
+ [SVM_EXIT_WRITE_CR0] = emulate_on_interception,
+ [SVM_EXIT_WRITE_CR3] = emulate_on_interception,
+ [SVM_EXIT_WRITE_CR4] = emulate_on_interception,
+ [SVM_EXIT_WRITE_CR8] = cr8_write_interception,
+ [SVM_EXIT_READ_DR0] = emulate_on_interception,
[SVM_EXIT_READ_DR1] = emulate_on_interception,
[SVM_EXIT_READ_DR2] = emulate_on_interception,
[SVM_EXIT_READ_DR3] = emulate_on_interception,
[SVM_EXIT_EXCP_BASE + DB_VECTOR] = db_interception,
[SVM_EXIT_EXCP_BASE + BP_VECTOR] = bp_interception,
[SVM_EXIT_EXCP_BASE + UD_VECTOR] = ud_interception,
- [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception,
- [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception,
- [SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception,
- [SVM_EXIT_INTR] = intr_interception,
+ [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception,
+ [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception,
+ [SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception,
+ [SVM_EXIT_INTR] = intr_interception,
[SVM_EXIT_NMI] = nmi_interception,
[SVM_EXIT_SMI] = nop_on_interception,
[SVM_EXIT_INIT] = nop_on_interception,
[SVM_EXIT_VINTR] = interrupt_window_interception,
- /* [SVM_EXIT_CR0_SEL_WRITE] = emulate_on_interception, */
[SVM_EXIT_CPUID] = cpuid_interception,
[SVM_EXIT_IRET] = iret_interception,
[SVM_EXIT_INVD] = emulate_on_interception,
[SVM_EXIT_HLT] = halt_interception,
[SVM_EXIT_INVLPG] = invlpg_interception,
[SVM_EXIT_INVLPGA] = invlpga_interception,
- [SVM_EXIT_IOIO] = io_interception,
+ [SVM_EXIT_IOIO] = io_interception,
[SVM_EXIT_MSR] = msr_interception,
[SVM_EXIT_TASK_SWITCH] = task_switch_interception,
[SVM_EXIT_SHUTDOWN] = shutdown_interception,
struct kvm_run *kvm_run = vcpu->run;
u32 exit_code = svm->vmcb->control.exit_code;
- trace_kvm_exit(exit_code, svm->vmcb->save.rip);
+ trace_kvm_exit(exit_code, vcpu);
+
+ if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR0_MASK))
+ vcpu->arch.cr0 = svm->vmcb->save.cr0;
+ if (npt_enabled)
+ vcpu->arch.cr3 = svm->vmcb->save.cr3;
if (unlikely(svm->nested.exit_required)) {
nested_svm_vmexit(svm);
svm_complete_interrupts(svm);
- if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR0_MASK))
- vcpu->arch.cr0 = svm->vmcb->save.cr0;
- if (npt_enabled)
- vcpu->arch.cr3 = svm->vmcb->save.cr3;
-
if (svm->vmcb->control.exit_code == SVM_EXIT_ERR) {
kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
kvm_run->fail_entry.hardware_entry_failure_reason
svm->vmcb->control.event_inj = SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_NMI;
vcpu->arch.hflags |= HF_NMI_MASK;
- svm->vmcb->control.intercept |= (1UL << INTERCEPT_IRET);
+ svm->vmcb->control.intercept |= (1ULL << INTERCEPT_IRET);
++vcpu->stat.nmi_injections;
}
{
struct vcpu_svm *svm = to_svm(vcpu);
+ if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK))
+ return;
+
if (irr == -1)
return;
{
struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb *vmcb = svm->vmcb;
- return !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) &&
- !(svm->vcpu.arch.hflags & HF_NMI_MASK);
+ int ret;
+ ret = !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) &&
+ !(svm->vcpu.arch.hflags & HF_NMI_MASK);
+ ret = ret && gif_set(svm) && nested_svm_nmi(svm);
+
+ return ret;
}
static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu)
if (masked) {
svm->vcpu.arch.hflags |= HF_NMI_MASK;
- svm->vmcb->control.intercept |= (1UL << INTERCEPT_IRET);
+ svm->vmcb->control.intercept |= (1ULL << INTERCEPT_IRET);
} else {
svm->vcpu.arch.hflags &= ~HF_NMI_MASK;
- svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET);
+ svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_IRET);
}
}
{
struct vcpu_svm *svm = to_svm(vcpu);
- nested_svm_intr(svm);
-
- /* In case GIF=0 we can't rely on the CPU to tell us when
- * GIF becomes 1, because that's a separate STGI/VMRUN intercept.
- * The next time we get that intercept, this function will be
- * called again though and we'll get the vintr intercept. */
- if (gif_set(svm)) {
+ /*
+ * In case GIF=0 we can't rely on the CPU to tell us when GIF becomes
+ * 1, because that's a separate STGI/VMRUN intercept. The next time we
+ * get that intercept, this function will be called again though and
+ * we'll get the vintr intercept.
+ */
+ if (gif_set(svm) && nested_svm_intr(svm)) {
svm_set_vintr(svm);
svm_inject_irq(svm, 0x0);
}
== HF_NMI_MASK)
return; /* IRET will cause a vm exit */
- /* Something prevents NMI from been injected. Single step over
- possible problem (IRET or exception injection or interrupt
- shadow) */
+ /*
+ * Something prevents NMI from been injected. Single step over possible
+ * problem (IRET or exception injection or interrupt shadow)
+ */
svm->nmi_singlestep = true;
svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF);
update_db_intercept(vcpu);
{
struct vcpu_svm *svm = to_svm(vcpu);
+ if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK))
+ return;
+
if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR8_MASK)) {
int cr8 = svm->vmcb->control.int_ctl & V_TPR_MASK;
kvm_set_cr8(vcpu, cr8);
struct vcpu_svm *svm = to_svm(vcpu);
u64 cr8;
+ if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK))
+ return;
+
cr8 = kvm_get_cr8(vcpu);
svm->vmcb->control.int_ctl &= ~V_TPR_MASK;
svm->vmcb->control.int_ctl |= cr8 & V_TPR_MASK;
u8 vector;
int type;
u32 exitintinfo = svm->vmcb->control.exit_int_info;
+ unsigned int3_injected = svm->int3_injected;
+
+ svm->int3_injected = 0;
if (svm->vcpu.arch.hflags & HF_IRET_MASK)
svm->vcpu.arch.hflags &= ~(HF_NMI_MASK | HF_IRET_MASK);
svm->vcpu.arch.nmi_injected = true;
break;
case SVM_EXITINTINFO_TYPE_EXEPT:
- /* In case of software exception do not reinject an exception
- vector, but re-execute and instruction instead */
- if (is_nested(svm))
- break;
- if (kvm_exception_is_soft(vector))
+ /*
+ * In case of software exceptions, do not reinject the vector,
+ * but re-execute the instruction instead. Rewind RIP first
+ * if we emulated INT3 before.
+ */
+ if (kvm_exception_is_soft(vector)) {
+ if (vector == BP_VECTOR && int3_injected &&
+ kvm_is_linear_rip(&svm->vcpu, svm->int3_rip))
+ kvm_rip_write(&svm->vcpu,
+ kvm_rip_read(&svm->vcpu) -
+ int3_injected);
break;
+ }
if (exitintinfo & SVM_EXITINTINFO_VALID_ERR) {
u32 err = svm->vmcb->control.exit_int_info_err;
- kvm_queue_exception_e(&svm->vcpu, vector, err);
+ kvm_requeue_exception_e(&svm->vcpu, vector, err);
} else
- kvm_queue_exception(&svm->vcpu, vector);
+ kvm_requeue_exception(&svm->vcpu, vector);
break;
case SVM_EXITINTINFO_TYPE_INTR:
kvm_queue_interrupt(&svm->vcpu, vector, false);
u16 gs_selector;
u16 ldt_selector;
+ svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
+ svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
+ svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
+
/*
* A vmexit emulation is required before the vcpu can be executed
* again.
if (unlikely(svm->nested.exit_required))
return;
- svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
- svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
- svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
-
pre_svm_run(svm);
sync_lapic_to_cr8(vcpu);
{
}
+ static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
+ {
+ switch (func) {
+ case 0x8000000A:
+ entry->eax = 1; /* SVM revision 1 */
+ entry->ebx = 8; /* Lets support 8 ASIDs in case we add proper
+ ASID emulation to nested SVM */
+ entry->ecx = 0; /* Reserved */
+ entry->edx = 0; /* Do not support any additional features */
+
+ break;
+ }
+ }
+
static const struct trace_print_flags svm_exit_reasons_str[] = {
- { SVM_EXIT_READ_CR0, "read_cr0" },
- { SVM_EXIT_READ_CR3, "read_cr3" },
- { SVM_EXIT_READ_CR4, "read_cr4" },
- { SVM_EXIT_READ_CR8, "read_cr8" },
- { SVM_EXIT_WRITE_CR0, "write_cr0" },
- { SVM_EXIT_WRITE_CR3, "write_cr3" },
- { SVM_EXIT_WRITE_CR4, "write_cr4" },
- { SVM_EXIT_WRITE_CR8, "write_cr8" },
- { SVM_EXIT_READ_DR0, "read_dr0" },
- { SVM_EXIT_READ_DR1, "read_dr1" },
- { SVM_EXIT_READ_DR2, "read_dr2" },
- { SVM_EXIT_READ_DR3, "read_dr3" },
- { SVM_EXIT_WRITE_DR0, "write_dr0" },
- { SVM_EXIT_WRITE_DR1, "write_dr1" },
- { SVM_EXIT_WRITE_DR2, "write_dr2" },
- { SVM_EXIT_WRITE_DR3, "write_dr3" },
- { SVM_EXIT_WRITE_DR5, "write_dr5" },
- { SVM_EXIT_WRITE_DR7, "write_dr7" },
+ { SVM_EXIT_READ_CR0, "read_cr0" },
+ { SVM_EXIT_READ_CR3, "read_cr3" },
+ { SVM_EXIT_READ_CR4, "read_cr4" },
+ { SVM_EXIT_READ_CR8, "read_cr8" },
+ { SVM_EXIT_WRITE_CR0, "write_cr0" },
+ { SVM_EXIT_WRITE_CR3, "write_cr3" },
+ { SVM_EXIT_WRITE_CR4, "write_cr4" },
+ { SVM_EXIT_WRITE_CR8, "write_cr8" },
+ { SVM_EXIT_READ_DR0, "read_dr0" },
+ { SVM_EXIT_READ_DR1, "read_dr1" },
+ { SVM_EXIT_READ_DR2, "read_dr2" },
+ { SVM_EXIT_READ_DR3, "read_dr3" },
+ { SVM_EXIT_WRITE_DR0, "write_dr0" },
+ { SVM_EXIT_WRITE_DR1, "write_dr1" },
+ { SVM_EXIT_WRITE_DR2, "write_dr2" },
+ { SVM_EXIT_WRITE_DR3, "write_dr3" },
+ { SVM_EXIT_WRITE_DR5, "write_dr5" },
+ { SVM_EXIT_WRITE_DR7, "write_dr7" },
{ SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" },
{ SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" },
{ SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" },
{
struct vcpu_svm *svm = to_svm(vcpu);
- update_cr0_intercept(svm);
svm->vmcb->control.intercept_exceptions |= 1 << NM_VECTOR;
+ if (is_nested(svm))
+ svm->nested.hsave->control.intercept_exceptions |= 1 << NM_VECTOR;
+ update_cr0_intercept(svm);
}
static struct kvm_x86_ops svm_x86_ops = {
.set_idt = svm_set_idt,
.get_gdt = svm_get_gdt,
.set_gdt = svm_set_gdt,
- .get_dr = svm_get_dr,
- .set_dr = svm_set_dr,
+ .set_dr7 = svm_set_dr7,
.cache_reg = svm_cache_reg,
.get_rflags = svm_get_rflags,
.set_rflags = svm_set_rflags,
.cpuid_update = svm_cpuid_update,
.rdtscp_supported = svm_rdtscp_supported,
+
+ .set_supported_cpuid = svm_set_supported_cpuid,
};
static int __init svm_init(void)
{
return kvm_init(&svm_x86_ops, sizeof(struct vcpu_svm),
- THIS_MODULE);
+ __alignof__(struct vcpu_svm), THIS_MODULE);
}
static void __exit svm_exit(void)
#include <linux/moduleparam.h>
#include <linux/ftrace_event.h>
#include <linux/slab.h>
+ #include <linux/tboot.h>
#include "kvm_cache_regs.h"
#include "x86.h"
static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
module_param(ple_window, int, S_IRUGO);
+ #define NR_AUTOLOAD_MSRS 1
+
struct vmcs {
u32 revision_id;
u32 abort;
u64 msr_guest_kernel_gs_base;
#endif
struct vmcs *vmcs;
+ struct msr_autoload {
+ unsigned nr;
+ struct vmx_msr_entry guest[NR_AUTOLOAD_MSRS];
+ struct vmx_msr_entry host[NR_AUTOLOAD_MSRS];
+ } msr_autoload;
struct {
int loaded;
u16 fs_sel, gs_sel, ldt_sel;
};
#define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index)
- static inline int is_page_fault(u32 intr_info)
+ static inline bool is_page_fault(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
INTR_INFO_VALID_MASK)) ==
(INTR_TYPE_HARD_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK);
}
- static inline int is_no_device(u32 intr_info)
+ static inline bool is_no_device(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
INTR_INFO_VALID_MASK)) ==
(INTR_TYPE_HARD_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK);
}
- static inline int is_invalid_opcode(u32 intr_info)
+ static inline bool is_invalid_opcode(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
INTR_INFO_VALID_MASK)) ==
(INTR_TYPE_HARD_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK);
}
- static inline int is_external_interrupt(u32 intr_info)
+ static inline bool is_external_interrupt(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
== (INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK);
}
- static inline int is_machine_check(u32 intr_info)
+ static inline bool is_machine_check(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
INTR_INFO_VALID_MASK)) ==
(INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK);
}
- static inline int cpu_has_vmx_msr_bitmap(void)
+ static inline bool cpu_has_vmx_msr_bitmap(void)
{
return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS;
}
- static inline int cpu_has_vmx_tpr_shadow(void)
+ static inline bool cpu_has_vmx_tpr_shadow(void)
{
return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW;
}
- static inline int vm_need_tpr_shadow(struct kvm *kvm)
+ static inline bool vm_need_tpr_shadow(struct kvm *kvm)
{
return (cpu_has_vmx_tpr_shadow()) && (irqchip_in_kernel(kvm));
}
- static inline int cpu_has_secondary_exec_ctrls(void)
+ static inline bool cpu_has_secondary_exec_ctrls(void)
{
return vmcs_config.cpu_based_exec_ctrl &
CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
static inline bool cpu_has_vmx_ept_execute_only(void)
{
- return !!(vmx_capability.ept & VMX_EPT_EXECUTE_ONLY_BIT);
+ return vmx_capability.ept & VMX_EPT_EXECUTE_ONLY_BIT;
}
static inline bool cpu_has_vmx_eptp_uncacheable(void)
{
- return !!(vmx_capability.ept & VMX_EPTP_UC_BIT);
+ return vmx_capability.ept & VMX_EPTP_UC_BIT;
}
static inline bool cpu_has_vmx_eptp_writeback(void)
{
- return !!(vmx_capability.ept & VMX_EPTP_WB_BIT);
+ return vmx_capability.ept & VMX_EPTP_WB_BIT;
}
static inline bool cpu_has_vmx_ept_2m_page(void)
{
- return !!(vmx_capability.ept & VMX_EPT_2MB_PAGE_BIT);
+ return vmx_capability.ept & VMX_EPT_2MB_PAGE_BIT;
}
static inline bool cpu_has_vmx_ept_1g_page(void)
{
- return !!(vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT);
+ return vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT;
}
- static inline int cpu_has_vmx_invept_individual_addr(void)
+ static inline bool cpu_has_vmx_invept_individual_addr(void)
{
- return !!(vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT);
+ return vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT;
}
- static inline int cpu_has_vmx_invept_context(void)
+ static inline bool cpu_has_vmx_invept_context(void)
{
- return !!(vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT);
+ return vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT;
}
- static inline int cpu_has_vmx_invept_global(void)
+ static inline bool cpu_has_vmx_invept_global(void)
{
- return !!(vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT);
+ return vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT;
}
- static inline int cpu_has_vmx_ept(void)
+ static inline bool cpu_has_vmx_ept(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_ENABLE_EPT;
}
- static inline int cpu_has_vmx_unrestricted_guest(void)
+ static inline bool cpu_has_vmx_unrestricted_guest(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_UNRESTRICTED_GUEST;
}
- static inline int cpu_has_vmx_ple(void)
+ static inline bool cpu_has_vmx_ple(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_PAUSE_LOOP_EXITING;
}
- static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm)
+ static inline bool vm_need_virtualize_apic_accesses(struct kvm *kvm)
{
return flexpriority_enabled && irqchip_in_kernel(kvm);
}
- static inline int cpu_has_vmx_vpid(void)
+ static inline bool cpu_has_vmx_vpid(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_ENABLE_VPID;
}
- static inline int cpu_has_vmx_rdtscp(void)
+ static inline bool cpu_has_vmx_rdtscp(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_RDTSCP;
}
- static inline int cpu_has_virtual_nmis(void)
+ static inline bool cpu_has_virtual_nmis(void)
{
return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS;
}
vmcs_write32(EXCEPTION_BITMAP, eb);
}
+ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
+ {
+ unsigned i;
+ struct msr_autoload *m = &vmx->msr_autoload;
+
+ for (i = 0; i < m->nr; ++i)
+ if (m->guest[i].index == msr)
+ break;
+
+ if (i == m->nr)
+ return;
+ --m->nr;
+ m->guest[i] = m->guest[m->nr];
+ m->host[i] = m->host[m->nr];
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
+ }
+
+ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
+ u64 guest_val, u64 host_val)
+ {
+ unsigned i;
+ struct msr_autoload *m = &vmx->msr_autoload;
+
+ for (i = 0; i < m->nr; ++i)
+ if (m->guest[i].index == msr)
+ break;
+
+ if (i == m->nr) {
+ ++m->nr;
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
+ }
+
+ m->guest[i].index = msr;
+ m->guest[i].value = guest_val;
+ m->host[i].index = msr;
+ m->host[i].value = host_val;
+ }
+
static void reload_tss(void)
{
/*
* VT restores TR but not its size. Useless.
*/
- struct descriptor_table gdt;
+ struct desc_ptr gdt;
struct desc_struct *descs;
- kvm_get_gdt(&gdt);
- descs = (void *)gdt.base;
+ native_store_gdt(&gdt);
+ descs = (void *)gdt.address;
descs[GDT_ENTRY_TSS].type = 9; /* available TSS */
load_TR_desc();
}
guest_efer |= host_efer & ignore_bits;
vmx->guest_msrs[efer_offset].data = guest_efer;
vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
+
+ clear_atomic_switch_msr(vmx, MSR_EFER);
+ /* On ept, can't emulate nx, and must switch nx atomically */
+ if (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX)) {
+ guest_efer = vmx->vcpu.arch.efer;
+ if (!(guest_efer & EFER_LMA))
+ guest_efer &= ~EFER_LME;
+ add_atomic_switch_msr(vmx, MSR_EFER, guest_efer, host_efer);
+ return false;
+ }
+
return true;
}
+ static unsigned long segment_base(u16 selector)
+ {
+ struct desc_ptr gdt;
+ struct desc_struct *d;
+ unsigned long table_base;
+ unsigned long v;
+
+ if (!(selector & ~3))
+ return 0;
+
+ native_store_gdt(&gdt);
+ table_base = gdt.address;
+
+ if (selector & 4) { /* from ldt */
+ u16 ldt_selector = kvm_read_ldt();
+
+ if (!(ldt_selector & ~3))
+ return 0;
+
+ table_base = segment_base(ldt_selector);
+ }
+ d = (struct desc_struct *)(table_base + (selector & ~7));
+ v = get_desc_base(d);
+ #ifdef CONFIG_X86_64
+ if (d->s == 0 && (d->type == 2 || d->type == 9 || d->type == 11))
+ v |= ((unsigned long)((struct ldttss_desc64 *)d)->base3) << 32;
+ #endif
+ return v;
+ }
+
+ static inline unsigned long kvm_read_tr_base(void)
+ {
+ u16 tr;
+ asm("str %0" : "=g"(tr));
+ return segment_base(tr);
+ }
+
static void vmx_save_host_state(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
}
if (vcpu->cpu != cpu) {
- struct descriptor_table dt;
+ struct desc_ptr dt;
unsigned long sysenter_esp;
vcpu->cpu = cpu;
* processors.
*/
vmcs_writel(HOST_TR_BASE, kvm_read_tr_base()); /* 22.2.4 */
- kvm_get_gdt(&dt);
- vmcs_writel(HOST_GDTR_BASE, dt.base); /* 22.2.4 */
+ native_store_gdt(&dt);
+ vmcs_writel(HOST_GDTR_BASE, dt.address); /* 22.2.4 */
rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
int ret = 0;
if (interruptibility & GUEST_INTR_STATE_STI)
- ret |= X86_SHADOW_INT_STI;
+ ret |= KVM_X86_SHADOW_INT_STI;
if (interruptibility & GUEST_INTR_STATE_MOV_SS)
- ret |= X86_SHADOW_INT_MOV_SS;
+ ret |= KVM_X86_SHADOW_INT_MOV_SS;
return ret & mask;
}
interruptibility &= ~(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS);
- if (mask & X86_SHADOW_INT_MOV_SS)
+ if (mask & KVM_X86_SHADOW_INT_MOV_SS)
interruptibility |= GUEST_INTR_STATE_MOV_SS;
- if (mask & X86_SHADOW_INT_STI)
+ else if (mask & KVM_X86_SHADOW_INT_STI)
interruptibility |= GUEST_INTR_STATE_STI;
if ((interruptibility != interruptibility_old))
}
static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
- bool has_error_code, u32 error_code)
+ bool has_error_code, u32 error_code,
+ bool reinject)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 intr_info = nr | INTR_INFO_VALID_MASK;
u64 msr;
rdmsrl(MSR_IA32_FEATURE_CONTROL, msr);
- return (msr & (FEATURE_CONTROL_LOCKED |
- FEATURE_CONTROL_VMXON_ENABLED))
- == FEATURE_CONTROL_LOCKED;
+ if (msr & FEATURE_CONTROL_LOCKED) {
+ if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX)
+ && tboot_enabled())
+ return 1;
+ if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX)
+ && !tboot_enabled())
+ return 1;
+ }
+
+ return 0;
/* locked but not enabled */
}
{
int cpu = raw_smp_processor_id();
u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
- u64 old;
+ u64 old, test_bits;
if (read_cr4() & X86_CR4_VMXE)
return -EBUSY;
INIT_LIST_HEAD(&per_cpu(vcpus_on_cpu, cpu));
rdmsrl(MSR_IA32_FEATURE_CONTROL, old);
- if ((old & (FEATURE_CONTROL_LOCKED |
- FEATURE_CONTROL_VMXON_ENABLED))
- != (FEATURE_CONTROL_LOCKED |
- FEATURE_CONTROL_VMXON_ENABLED))
+
+ test_bits = FEATURE_CONTROL_LOCKED;
+ test_bits |= FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+ if (tboot_enabled())
+ test_bits |= FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX;
+
+ if ((old & test_bits) != test_bits) {
/* enable and lock */
- wrmsrl(MSR_IA32_FEATURE_CONTROL, old |
- FEATURE_CONTROL_LOCKED |
- FEATURE_CONTROL_VMXON_ENABLED);
+ wrmsrl(MSR_IA32_FEATURE_CONTROL, old | test_bits);
+ }
write_cr4(read_cr4() | X86_CR4_VMXE); /* FIXME: not cpu hotplug safe */
asm volatile (ASM_VMX_VMXON_RAX
: : "a"(&phys_addr), "m"(phys_addr)
struct kvm_memslots *slots;
gfn_t base_gfn;
- slots = rcu_dereference(kvm->memslots);
+ slots = kvm_memslots(kvm);
base_gfn = kvm->memslots->memslots[0].base_gfn +
kvm->memslots->memslots[0].npages - 3;
return base_gfn << PAGE_SHIFT;
vmcs_write32(VM_ENTRY_CONTROLS,
vmcs_read32(VM_ENTRY_CONTROLS)
& ~VM_ENTRY_IA32E_MODE);
+ vmx_set_efer(vcpu, vcpu->arch.efer);
}
#endif
*l = (ar >> 13) & 1;
}
- static void vmx_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+ static void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
- dt->limit = vmcs_read32(GUEST_IDTR_LIMIT);
- dt->base = vmcs_readl(GUEST_IDTR_BASE);
+ dt->size = vmcs_read32(GUEST_IDTR_LIMIT);
+ dt->address = vmcs_readl(GUEST_IDTR_BASE);
}
- static void vmx_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+ static void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
- vmcs_write32(GUEST_IDTR_LIMIT, dt->limit);
- vmcs_writel(GUEST_IDTR_BASE, dt->base);
+ vmcs_write32(GUEST_IDTR_LIMIT, dt->size);
+ vmcs_writel(GUEST_IDTR_BASE, dt->address);
}
- static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+ static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
- dt->limit = vmcs_read32(GUEST_GDTR_LIMIT);
- dt->base = vmcs_readl(GUEST_GDTR_BASE);
+ dt->size = vmcs_read32(GUEST_GDTR_LIMIT);
+ dt->address = vmcs_readl(GUEST_GDTR_BASE);
}
- static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+ static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
- vmcs_write32(GUEST_GDTR_LIMIT, dt->limit);
- vmcs_writel(GUEST_GDTR_BASE, dt->base);
+ vmcs_write32(GUEST_GDTR_LIMIT, dt->size);
+ vmcs_writel(GUEST_GDTR_BASE, dt->address);
}
static bool rmode_segment_valid(struct kvm_vcpu *vcpu, int seg)
spin_unlock(&vmx_vpid_lock);
}
+ static void free_vpid(struct vcpu_vmx *vmx)
+ {
+ if (!enable_vpid)
+ return;
+ spin_lock(&vmx_vpid_lock);
+ if (vmx->vpid != 0)
+ __clear_bit(vmx->vpid, vmx_vpid_bitmap);
+ spin_unlock(&vmx_vpid_lock);
+ }
+
static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, u32 msr)
{
int f = sizeof(unsigned long);
u32 junk;
u64 host_pat, tsc_this, tsc_base;
unsigned long a;
- struct descriptor_table dt;
+ struct desc_ptr dt;
int i;
unsigned long kvm_vmx_return;
u32 exec_control;
vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8); /* 22.2.4 */
- kvm_get_idt(&dt);
- vmcs_writel(HOST_IDTR_BASE, dt.base); /* 22.2.4 */
+ native_store_idt(&dt);
+ vmcs_writel(HOST_IDTR_BASE, dt.address); /* 22.2.4 */
asm("mov $.Lkvm_vmx_return, %0" : "=r"(kvm_vmx_return));
vmcs_writel(HOST_RIP, kvm_vmx_return); /* 22.2.5 */
vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
+ vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
+ vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
rdmsr(MSR_IA32_SYSENTER_CS, host_sysenter_cs, junk);
vmcs_write32(HOST_IA32_SYSENTER_CS, host_sysenter_cs);
return 0;
return !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
- (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS |
- GUEST_INTR_STATE_NMI));
+ (GUEST_INTR_STATE_MOV_SS | GUEST_INTR_STATE_NMI));
}
static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu)
int size, in, string;
unsigned port;
- ++vcpu->stat.io_exits;
exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
string = (exit_qualification & 16) != 0;
+ in = (exit_qualification & 8) != 0;
- if (string) {
- if (emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO)
- return 0;
- return 1;
- }
+ ++vcpu->stat.io_exits;
- size = (exit_qualification & 7) + 1;
- in = (exit_qualification & 8) != 0;
- port = exit_qualification >> 16;
+ if (string || in)
+ return !(emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO);
+ port = exit_qualification >> 16;
+ size = (exit_qualification & 7) + 1;
skip_emulated_instruction(vcpu);
- return kvm_emulate_pio(vcpu, in, size, port);
+
+ return kvm_fast_pio_out(vcpu, size, port);
}
static void
return 0;
}
static int handle_dr(struct kvm_vcpu *vcpu)
{
unsigned long exit_qualification;
- unsigned long val;
int dr, reg;
/* Do not handle if the CPL > 0, will trigger GP on re-entry */
dr = exit_qualification & DEBUG_REG_ACCESS_NUM;
reg = DEBUG_REG_ACCESS_REG(exit_qualification);
if (exit_qualification & TYPE_MOV_FROM_DR) {
- switch (dr) {
- case 0 ... 3:
- val = vcpu->arch.db[dr];
- break;
- case 4:
- if (check_dr_alias(vcpu) < 0)
- return 1;
- /* fall through */
- case 6:
- val = vcpu->arch.dr6;
- break;
- case 5:
- if (check_dr_alias(vcpu) < 0)
- return 1;
- /* fall through */
- default: /* 7 */
- val = vcpu->arch.dr7;
- break;
- }
- kvm_register_write(vcpu, reg, val);
- } else {
- val = vcpu->arch.regs[reg];
- switch (dr) {
- case 0 ... 3:
- vcpu->arch.db[dr] = val;
- if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
- vcpu->arch.eff_db[dr] = val;
- break;
- case 4:
- if (check_dr_alias(vcpu) < 0)
- return 1;
- /* fall through */
- case 6:
- if (val & 0xffffffff00000000ULL) {
- kvm_inject_gp(vcpu, 0);
- return 1;
- }
- vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1;
- break;
- case 5:
- if (check_dr_alias(vcpu) < 0)
- return 1;
- /* fall through */
- default: /* 7 */
- if (val & 0xffffffff00000000ULL) {
- kvm_inject_gp(vcpu, 0);
- return 1;
- }
- vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1;
- if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
- vmcs_writel(GUEST_DR7, vcpu->arch.dr7);
- vcpu->arch.switch_db_regs =
- (val & DR7_BP_EN_MASK);
- }
- break;
- }
- }
+ unsigned long val;
+ if (!kvm_get_dr(vcpu, dr, &val))
+ kvm_register_write(vcpu, reg, val);
+ } else
+ kvm_set_dr(vcpu, dr, vcpu->arch.regs[reg]);
skip_emulated_instruction(vcpu);
return 1;
}
+ static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
+ {
+ vmcs_writel(GUEST_DR7, val);
+ }
+
static int handle_cpuid(struct kvm_vcpu *vcpu)
{
kvm_emulate_cpuid(vcpu);
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long exit_qualification;
+ bool has_error_code = false;
+ u32 error_code = 0;
u16 tss_selector;
int reason, type, idt_v;
kvm_clear_interrupt_queue(vcpu);
break;
case INTR_TYPE_HARD_EXCEPTION:
+ if (vmx->idt_vectoring_info &
+ VECTORING_INFO_DELIVER_CODE_MASK) {
+ has_error_code = true;
+ error_code =
+ vmcs_read32(IDT_VECTORING_ERROR_CODE);
+ }
+ /* fall through */
case INTR_TYPE_SOFT_EXCEPTION:
kvm_clear_exception_queue(vcpu);
break;
type != INTR_TYPE_NMI_INTR))
skip_emulated_instruction(vcpu);
- if (!kvm_task_switch(vcpu, tss_selector, reason))
+ if (kvm_task_switch(vcpu, tss_selector, reason,
+ has_error_code, error_code) == EMULATE_FAIL) {
+ vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+ vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+ vcpu->run->internal.ndata = 0;
return 0;
+ }
/* clear all local breakpoint enable flags */
vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~55);
u32 exit_reason = vmx->exit_reason;
u32 vectoring_info = vmx->idt_vectoring_info;
- trace_kvm_exit(exit_reason, kvm_rip_read(vcpu));
+ trace_kvm_exit(exit_reason, vcpu);
/* If guest state is invalid, start emulating */
if (vmx->emulation_required && emulate_invalid_guest_state)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- spin_lock(&vmx_vpid_lock);
- if (vmx->vpid != 0)
- __clear_bit(vmx->vpid, vmx_vpid_bitmap);
- spin_unlock(&vmx_vpid_lock);
+ free_vpid(vmx);
vmx_free_vmcs(vcpu);
kfree(vmx->guest_msrs);
kvm_vcpu_uninit(vcpu);
uninit_vcpu:
kvm_vcpu_uninit(&vmx->vcpu);
free_vcpu:
+ free_vpid(vmx);
kmem_cache_free(kvm_vcpu_cache, vmx);
return ERR_PTR(err);
}
}
}
+ static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
+ {
+ }
+
static struct kvm_x86_ops vmx_x86_ops = {
.cpu_has_kvm_support = cpu_has_kvm_support,
.disabled_by_bios = vmx_disabled_by_bios,
.set_idt = vmx_set_idt,
.get_gdt = vmx_get_gdt,
.set_gdt = vmx_set_gdt,
+ .set_dr7 = vmx_set_dr7,
.cache_reg = vmx_cache_reg,
.get_rflags = vmx_get_rflags,
.set_rflags = vmx_set_rflags,
.cpuid_update = vmx_cpuid_update,
.rdtscp_supported = vmx_rdtscp_supported,
+
+ .set_supported_cpuid = vmx_set_supported_cpuid,
};
static int __init vmx_init(void)
set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
- r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), THIS_MODULE);
+ r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
+ __alignof__(struct vcpu_vmx), THIS_MODULE);
if (r)
goto out3;
#include <linux/slab.h>
#include <linux/perf_event.h>
#include <trace/events/kvm.h>
- #undef TRACE_INCLUDE_FILE
+
#define CREATE_TRACE_POINTS
#include "trace.h"
kvm_on_user_return(&smsr->urn);
}
- unsigned long segment_base(u16 selector)
- {
- struct descriptor_table gdt;
- struct desc_struct *d;
- unsigned long table_base;
- unsigned long v;
-
- if (selector == 0)
- return 0;
-
- kvm_get_gdt(&gdt);
- table_base = gdt.base;
-
- if (selector & 4) { /* from ldt */
- u16 ldt_selector = kvm_read_ldt();
-
- table_base = segment_base(ldt_selector);
- }
- d = (struct desc_struct *)(table_base + (selector & ~7));
- v = get_desc_base(d);
- #ifdef CONFIG_X86_64
- if (d->s == 0 && (d->type == 2 || d->type == 9 || d->type == 11))
- v |= ((unsigned long)((struct ldttss_desc64 *)d)->base3) << 32;
- #endif
- return v;
- }
- EXPORT_SYMBOL_GPL(segment_base);
-
u64 kvm_get_apic_base(struct kvm_vcpu *vcpu)
{
if (irqchip_in_kernel(vcpu->kvm))
}
static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
- unsigned nr, bool has_error, u32 error_code)
+ unsigned nr, bool has_error, u32 error_code,
+ bool reinject)
{
u32 prev_nr;
int class1, class2;
vcpu->arch.exception.has_error_code = has_error;
vcpu->arch.exception.nr = nr;
vcpu->arch.exception.error_code = error_code;
+ vcpu->arch.exception.reinject = reinject;
return;
}
void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr)
{
- kvm_multiple_exception(vcpu, nr, false, 0);
+ kvm_multiple_exception(vcpu, nr, false, 0, false);
}
EXPORT_SYMBOL_GPL(kvm_queue_exception);
+ void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr)
+ {
+ kvm_multiple_exception(vcpu, nr, false, 0, true);
+ }
+ EXPORT_SYMBOL_GPL(kvm_requeue_exception);
+
void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr,
u32 error_code)
{
void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
{
- kvm_multiple_exception(vcpu, nr, true, error_code);
+ kvm_multiple_exception(vcpu, nr, true, error_code, false);
}
EXPORT_SYMBOL_GPL(kvm_queue_exception_e);
+ void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
+ {
+ kvm_multiple_exception(vcpu, nr, true, error_code, true);
+ }
+ EXPORT_SYMBOL_GPL(kvm_requeue_exception_e);
+
/*
* Checks if cpl <= required_cpl; if true, return true. Otherwise queue
* a #GP and return false.
}
kvm_x86_ops->set_cr0(vcpu, cr0);
- vcpu->arch.cr0 = cr0;
kvm_mmu_reset_context(vcpu);
return;
void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
{
- kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0ful) | (msw & 0x0f));
+ kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0eul) | (msw & 0x0f));
}
EXPORT_SYMBOL_GPL(kvm_lmsw);
}
kvm_x86_ops->set_cr4(vcpu, cr4);
vcpu->arch.cr4 = cr4;
- vcpu->arch.mmu.base_role.cr4_pge = (cr4 & X86_CR4_PGE) && !tdp_enabled;
kvm_mmu_reset_context(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_set_cr4);
}
EXPORT_SYMBOL_GPL(kvm_get_cr8);
+ int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
+ {
+ switch (dr) {
+ case 0 ... 3:
+ vcpu->arch.db[dr] = val;
+ if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
+ vcpu->arch.eff_db[dr] = val;
+ break;
+ case 4:
+ if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+ }
+ /* fall through */
+ case 6:
+ if (val & 0xffffffff00000000ULL) {
+ kvm_inject_gp(vcpu, 0);
+ return 1;
+ }
+ vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1;
+ break;
+ case 5:
+ if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+ }
+ /* fall through */
+ default: /* 7 */
+ if (val & 0xffffffff00000000ULL) {
+ kvm_inject_gp(vcpu, 0);
+ return 1;
+ }
+ vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1;
+ if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
+ kvm_x86_ops->set_dr7(vcpu, vcpu->arch.dr7);
+ vcpu->arch.switch_db_regs = (val & DR7_BP_EN_MASK);
+ }
+ break;
+ }
+
+ return 0;
+ }
+ EXPORT_SYMBOL_GPL(kvm_set_dr);
+
+ int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
+ {
+ switch (dr) {
+ case 0 ... 3:
+ *val = vcpu->arch.db[dr];
+ break;
+ case 4:
+ if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+ }
+ /* fall through */
+ case 6:
+ *val = vcpu->arch.dr6;
+ break;
+ case 5:
+ if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+ }
+ /* fall through */
+ default: /* 7 */
+ *val = vcpu->arch.dr7;
+ break;
+ }
+
+ return 0;
+ }
+ EXPORT_SYMBOL_GPL(kvm_get_dr);
+
static inline u32 bit(int bitno)
{
return 1 << (bitno & 31);
* kvm-specific. Those are put in the beginning of the list.
*/
- #define KVM_SAVE_MSRS_BEGIN 5
+ #define KVM_SAVE_MSRS_BEGIN 7
static u32 msrs_to_save[] = {
MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
+ MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
HV_X64_MSR_APIC_ASSIST_PAGE,
MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
MSR_IA32_MISC_ENABLE,
};
- static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
+ static int set_efer(struct kvm_vcpu *vcpu, u64 efer)
{
- if (efer & efer_reserved_bits) {
- kvm_inject_gp(vcpu, 0);
- return;
- }
+ if (efer & efer_reserved_bits)
+ return 1;
if (is_paging(vcpu)
- && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) {
- kvm_inject_gp(vcpu, 0);
- return;
- }
+ && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME))
+ return 1;
if (efer & EFER_FFXSR) {
struct kvm_cpuid_entry2 *feat;
feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
- if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT))) {
- kvm_inject_gp(vcpu, 0);
- return;
- }
+ if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT)))
+ return 1;
}
if (efer & EFER_SVME) {
struct kvm_cpuid_entry2 *feat;
feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
- if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM))) {
- kvm_inject_gp(vcpu, 0);
- return;
- }
+ if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM)))
+ return 1;
}
efer &= ~EFER_LMA;
efer |= vcpu->arch.efer & EFER_LMA;
+ kvm_x86_ops->set_efer(vcpu, efer);
+
vcpu->arch.efer = efer;
vcpu->arch.mmu.base_role.nxe = (efer & EFER_NX) && !tdp_enabled;
kvm_mmu_reset_context(vcpu);
+
+ return 0;
}
void kvm_enable_efer_bits(u64 mask)
static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
{
- static int version;
+ int version;
+ int r;
struct pvclock_wall_clock wc;
struct timespec boot;
if (!wall_clock)
return;
- version++;
+ r = kvm_read_guest(kvm, wall_clock, &version, sizeof(version));
+ if (r)
+ return;
+
+ if (version & 1)
+ ++version; /* first time write, random junk */
+
+ ++version;
kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
vcpu->hv_clock.system_time = ts.tv_nsec +
(NSEC_PER_SEC * (u64)ts.tv_sec) + v->kvm->arch.kvmclock_offset;
+ vcpu->hv_clock.flags = 0;
+
/*
* The interface expects us to write an even number signaling that the
* update is finished. Since the guest won't see the intermediate
{
switch (msr) {
case MSR_EFER:
- set_efer(vcpu, data);
- break;
+ return set_efer(vcpu, data);
case MSR_K7_HWCR:
data &= ~(u64)0x40; /* ignore flush filter disable */
+ data &= ~(u64)0x100; /* ignore ignne emulation enable */
if (data != 0) {
pr_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n",
data);
case MSR_IA32_MISC_ENABLE:
vcpu->arch.ia32_misc_enable_msr = data;
break;
+ case MSR_KVM_WALL_CLOCK_NEW:
case MSR_KVM_WALL_CLOCK:
vcpu->kvm->arch.wall_clock = data;
kvm_write_wall_clock(vcpu->kvm, data);
break;
+ case MSR_KVM_SYSTEM_TIME_NEW:
case MSR_KVM_SYSTEM_TIME: {
if (vcpu->arch.time_page) {
kvm_release_page_dirty(vcpu->arch.time_page);
data = vcpu->arch.efer;
break;
case MSR_KVM_WALL_CLOCK:
+ case MSR_KVM_WALL_CLOCK_NEW:
data = vcpu->kvm->arch.wall_clock;
break;
case MSR_KVM_SYSTEM_TIME:
+ case MSR_KVM_SYSTEM_TIME_NEW:
data = vcpu->arch.time;
break;
case MSR_IA32_P5_MC_ADDR:
case KVM_CAP_HYPERV_VAPIC:
case KVM_CAP_HYPERV_SPIN:
case KVM_CAP_PCI_SEGMENT:
+ case KVM_CAP_DEBUGREGS:
case KVM_CAP_X86_ROBUST_SINGLESTEP:
r = 1;
break;
if (copy_from_user(cpuid_entries, entries,
cpuid->nent * sizeof(struct kvm_cpuid_entry)))
goto out_free;
+ vcpu_load(vcpu);
for (i = 0; i < cpuid->nent; i++) {
vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function;
vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax;
r = 0;
kvm_apic_set_version(vcpu);
kvm_x86_ops->cpuid_update(vcpu);
+ vcpu_put(vcpu);
out_free:
vfree(cpuid_entries);
if (copy_from_user(&vcpu->arch.cpuid_entries, entries,
cpuid->nent * sizeof(struct kvm_cpuid_entry2)))
goto out;
+ vcpu_load(vcpu);
vcpu->arch.cpuid_nent = cpuid->nent;
kvm_apic_set_version(vcpu);
kvm_x86_ops->cpuid_update(vcpu);
+ vcpu_put(vcpu);
return 0;
out:
{
int r;
+ vcpu_load(vcpu);
r = -E2BIG;
if (cpuid->nent < vcpu->arch.cpuid_nent)
goto out;
out:
cpuid->nent = vcpu->arch.cpuid_nent;
+ vcpu_put(vcpu);
return r;
}
}
break;
}
+ case KVM_CPUID_SIGNATURE: {
+ char signature[12] = "KVMKVMKVM\0\0";
+ u32 *sigptr = (u32 *)signature;
+ entry->eax = 0;
+ entry->ebx = sigptr[0];
+ entry->ecx = sigptr[1];
+ entry->edx = sigptr[2];
+ break;
+ }
+ case KVM_CPUID_FEATURES:
+ entry->eax = (1 << KVM_FEATURE_CLOCKSOURCE) |
+ (1 << KVM_FEATURE_NOP_IO_DELAY) |
+ (1 << KVM_FEATURE_CLOCKSOURCE2) |
+ (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT);
+ entry->ebx = 0;
+ entry->ecx = 0;
+ entry->edx = 0;
+ break;
case 0x80000000:
entry->eax = min(entry->eax, 0x8000001a);
break;
entry->ecx &= kvm_supported_word6_x86_features;
break;
}
+
+ kvm_x86_ops->set_supported_cpuid(function, entry);
+
put_cpu();
}
for (func = 0x80000001; func <= limit && nent < cpuid->nent; ++func)
do_cpuid_ent(&cpuid_entries[nent], func, 0,
&nent, cpuid->nent);
+
+
+
+ r = -E2BIG;
+ if (nent >= cpuid->nent)
+ goto out_free;
+
+ do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_SIGNATURE, 0, &nent,
+ cpuid->nent);
+
+ r = -E2BIG;
+ if (nent >= cpuid->nent)
+ goto out_free;
+
+ do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_FEATURES, 0, &nent,
+ cpuid->nent);
+
r = -E2BIG;
if (nent >= cpuid->nent)
goto out_free;
int r;
unsigned bank_num = mcg_cap & 0xff, bank;
+ vcpu_load(vcpu);
r = -EINVAL;
if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS)
goto out;
for (bank = 0; bank < bank_num; bank++)
vcpu->arch.mce_banks[bank*4] = ~(u64)0;
out:
+ vcpu_put(vcpu);
return r;
}
{
vcpu_load(vcpu);
- events->exception.injected = vcpu->arch.exception.pending;
+ events->exception.injected =
+ vcpu->arch.exception.pending &&
+ !kvm_exception_is_soft(vcpu->arch.exception.nr);
events->exception.nr = vcpu->arch.exception.nr;
events->exception.has_error_code = vcpu->arch.exception.has_error_code;
events->exception.error_code = vcpu->arch.exception.error_code;
- events->interrupt.injected = vcpu->arch.interrupt.pending;
+ events->interrupt.injected =
+ vcpu->arch.interrupt.pending && !vcpu->arch.interrupt.soft;
events->interrupt.nr = vcpu->arch.interrupt.nr;
- events->interrupt.soft = vcpu->arch.interrupt.soft;
+ events->interrupt.soft = 0;
+ events->interrupt.shadow =
+ kvm_x86_ops->get_interrupt_shadow(vcpu,
+ KVM_X86_SHADOW_INT_MOV_SS | KVM_X86_SHADOW_INT_STI);
events->nmi.injected = vcpu->arch.nmi_injected;
events->nmi.pending = vcpu->arch.nmi_pending;
events->sipi_vector = vcpu->arch.sipi_vector;
events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
- | KVM_VCPUEVENT_VALID_SIPI_VECTOR);
+ | KVM_VCPUEVENT_VALID_SIPI_VECTOR
+ | KVM_VCPUEVENT_VALID_SHADOW);
vcpu_put(vcpu);
}
struct kvm_vcpu_events *events)
{
if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING
- | KVM_VCPUEVENT_VALID_SIPI_VECTOR))
+ | KVM_VCPUEVENT_VALID_SIPI_VECTOR
+ | KVM_VCPUEVENT_VALID_SHADOW))
return -EINVAL;
vcpu_load(vcpu);
vcpu->arch.interrupt.soft = events->interrupt.soft;
if (vcpu->arch.interrupt.pending && irqchip_in_kernel(vcpu->kvm))
kvm_pic_clear_isr_ack(vcpu->kvm);
+ if (events->flags & KVM_VCPUEVENT_VALID_SHADOW)
+ kvm_x86_ops->set_interrupt_shadow(vcpu,
+ events->interrupt.shadow);
vcpu->arch.nmi_injected = events->nmi.injected;
if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING)
return 0;
}
+ static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu,
+ struct kvm_debugregs *dbgregs)
+ {
+ vcpu_load(vcpu);
+
+ memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db));
+ dbgregs->dr6 = vcpu->arch.dr6;
+ dbgregs->dr7 = vcpu->arch.dr7;
+ dbgregs->flags = 0;
+
+ vcpu_put(vcpu);
+ }
+
+ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
+ struct kvm_debugregs *dbgregs)
+ {
+ if (dbgregs->flags)
+ return -EINVAL;
+
+ vcpu_load(vcpu);
+
+ memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db));
+ vcpu->arch.dr6 = dbgregs->dr6;
+ vcpu->arch.dr7 = dbgregs->dr7;
+
+ vcpu_put(vcpu);
+
+ return 0;
+ }
+
long kvm_arch_vcpu_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
r = -EFAULT;
if (copy_from_user(&mce, argp, sizeof mce))
goto out;
+ vcpu_load(vcpu);
r = kvm_vcpu_ioctl_x86_set_mce(vcpu, &mce);
+ vcpu_put(vcpu);
break;
}
case KVM_GET_VCPU_EVENTS: {
r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events);
break;
}
+ case KVM_GET_DEBUGREGS: {
+ struct kvm_debugregs dbgregs;
+
+ kvm_vcpu_ioctl_x86_get_debugregs(vcpu, &dbgregs);
+
+ r = -EFAULT;
+ if (copy_to_user(argp, &dbgregs,
+ sizeof(struct kvm_debugregs)))
+ break;
+ r = 0;
+ break;
+ }
+ case KVM_SET_DEBUGREGS: {
+ struct kvm_debugregs dbgregs;
+
+ r = -EFAULT;
+ if (copy_from_user(&dbgregs, argp,
+ sizeof(struct kvm_debugregs)))
+ break;
+
+ r = kvm_vcpu_ioctl_x86_set_debugregs(vcpu, &dbgregs);
+ break;
+ }
default:
r = -EINVAL;
}
struct kvm_mem_alias *alias;
struct kvm_mem_aliases *aliases;
- aliases = rcu_dereference(kvm->arch.aliases);
+ aliases = kvm_aliases(kvm);
for (i = 0; i < aliases->naliases; ++i) {
alias = &aliases->aliases[i];
struct kvm_mem_alias *alias;
struct kvm_mem_aliases *aliases;
- aliases = rcu_dereference(kvm->arch.aliases);
+ aliases = kvm_aliases(kvm);
for (i = 0; i < aliases->naliases; ++i) {
alias = &aliases->aliases[i];
r = -EFAULT;
if (copy_from_user(&irq_event, argp, sizeof irq_event))
goto out;
+ r = -ENXIO;
if (irqchip_in_kernel(kvm)) {
__s32 status;
status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
irq_event.irq, irq_event.level);
if (ioctl == KVM_IRQ_LINE_STATUS) {
+ r = -EFAULT;
irq_event.status = status;
if (copy_to_user(argp, &irq_event,
sizeof irq_event))
return kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, addr, len, v);
}
+ static void kvm_set_segment(struct kvm_vcpu *vcpu,
+ struct kvm_segment *var, int seg)
+ {
+ kvm_x86_ops->set_segment(vcpu, var, seg);
+ }
+
+ void kvm_get_segment(struct kvm_vcpu *vcpu,
+ struct kvm_segment *var, int seg)
+ {
+ kvm_x86_ops->get_segment(vcpu, var, seg);
+ }
+
gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, u32 *error)
{
u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, error);
}
- static int kvm_write_guest_virt(gva_t addr, void *val, unsigned int bytes,
- struct kvm_vcpu *vcpu, u32 *error)
+ static int kvm_write_guest_virt_system(gva_t addr, void *val,
+ unsigned int bytes,
+ struct kvm_vcpu *vcpu,
+ u32 *error)
{
void *data = val;
int r = X86EMUL_CONTINUE;
while (bytes) {
- gpa_t gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, error);
+ gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr,
+ PFERR_WRITE_MASK, error);
unsigned offset = addr & (PAGE_SIZE-1);
unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset);
int ret;
return r;
}
-
static int emulator_read_emulated(unsigned long addr,
void *val,
unsigned int bytes,
}
int emulator_write_emulated(unsigned long addr,
- const void *val,
- unsigned int bytes,
- struct kvm_vcpu *vcpu)
+ const void *val,
+ unsigned int bytes,
+ struct kvm_vcpu *vcpu)
{
/* Crossing a page boundary? */
if (((addr + bytes - 1) ^ addr) & PAGE_MASK) {
}
EXPORT_SYMBOL_GPL(emulator_write_emulated);
+ #define CMPXCHG_TYPE(t, ptr, old, new) \
+ (cmpxchg((t *)(ptr), *(t *)(old), *(t *)(new)) == *(t *)(old))
+
+ #ifdef CONFIG_X86_64
+ # define CMPXCHG64(ptr, old, new) CMPXCHG_TYPE(u64, ptr, old, new)
+ #else
+ # define CMPXCHG64(ptr, old, new) \
+ (cmpxchg64((u64 *)(ptr), *(u64 *)(old), *(u64 *)(new)) == *(u64 *)(old))
+ #endif
+
static int emulator_cmpxchg_emulated(unsigned long addr,
const void *old,
const void *new,
unsigned int bytes,
struct kvm_vcpu *vcpu)
{
- printk_once(KERN_WARNING "kvm: emulating exchange as write\n");
- #ifndef CONFIG_X86_64
- /* guests cmpxchg8b have to be emulated atomically */
- if (bytes == 8) {
- gpa_t gpa;
- struct page *page;
- char *kaddr;
- u64 val;
+ gpa_t gpa;
+ struct page *page;
+ char *kaddr;
+ bool exchanged;
- gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, NULL);
+ /* guests cmpxchg8b have to be emulated atomically */
+ if (bytes > 8 || (bytes & (bytes - 1)))
+ goto emul_write;
- if (gpa == UNMAPPED_GVA ||
- (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
- goto emul_write;
+ gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, NULL);
- if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK))
- goto emul_write;
+ if (gpa == UNMAPPED_GVA ||
+ (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
+ goto emul_write;
- val = *(u64 *)new;
+ if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK))
+ goto emul_write;
- page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
+ page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
- kaddr = kmap_atomic(page, KM_USER0);
- set_64bit((u64 *)(kaddr + offset_in_page(gpa)), val);
- kunmap_atomic(kaddr, KM_USER0);
- kvm_release_page_dirty(page);
+ kaddr = kmap_atomic(page, KM_USER0);
+ kaddr += offset_in_page(gpa);
+ switch (bytes) {
+ case 1:
+ exchanged = CMPXCHG_TYPE(u8, kaddr, old, new);
+ break;
+ case 2:
+ exchanged = CMPXCHG_TYPE(u16, kaddr, old, new);
+ break;
+ case 4:
+ exchanged = CMPXCHG_TYPE(u32, kaddr, old, new);
+ break;
+ case 8:
+ exchanged = CMPXCHG64(kaddr, old, new);
+ break;
+ default:
+ BUG();
}
+ kunmap_atomic(kaddr, KM_USER0);
+ kvm_release_page_dirty(page);
+
+ if (!exchanged)
+ return X86EMUL_CMPXCHG_FAILED;
+
+ kvm_mmu_pte_write(vcpu, gpa, new, bytes, 1);
+
+ return X86EMUL_CONTINUE;
+
emul_write:
- #endif
+ printk_once(KERN_WARNING "kvm: emulating exchange as write\n");
return emulator_write_emulated(addr, new, bytes, vcpu);
}
+ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
+ {
+ /* TODO: String I/O for in kernel device */
+ int r;
+
+ if (vcpu->arch.pio.in)
+ r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port,
+ vcpu->arch.pio.size, pd);
+ else
+ r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS,
+ vcpu->arch.pio.port, vcpu->arch.pio.size,
+ pd);
+ return r;
+ }
+
+
+ static int emulator_pio_in_emulated(int size, unsigned short port, void *val,
+ unsigned int count, struct kvm_vcpu *vcpu)
+ {
+ if (vcpu->arch.pio.count)
+ goto data_avail;
+
+ trace_kvm_pio(1, port, size, 1);
+
+ vcpu->arch.pio.port = port;
+ vcpu->arch.pio.in = 1;
+ vcpu->arch.pio.count = count;
+ vcpu->arch.pio.size = size;
+
+ if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
+ data_avail:
+ memcpy(val, vcpu->arch.pio_data, size * count);
+ vcpu->arch.pio.count = 0;
+ return 1;
+ }
+
+ vcpu->run->exit_reason = KVM_EXIT_IO;
+ vcpu->run->io.direction = KVM_EXIT_IO_IN;
+ vcpu->run->io.size = size;
+ vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
+ vcpu->run->io.count = count;
+ vcpu->run->io.port = port;
+
+ return 0;
+ }
+
+ static int emulator_pio_out_emulated(int size, unsigned short port,
+ const void *val, unsigned int count,
+ struct kvm_vcpu *vcpu)
+ {
+ trace_kvm_pio(0, port, size, 1);
+
+ vcpu->arch.pio.port = port;
+ vcpu->arch.pio.in = 0;
+ vcpu->arch.pio.count = count;
+ vcpu->arch.pio.size = size;
+
+ memcpy(vcpu->arch.pio_data, val, size * count);
+
+ if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
+ vcpu->arch.pio.count = 0;
+ return 1;
+ }
+
+ vcpu->run->exit_reason = KVM_EXIT_IO;
+ vcpu->run->io.direction = KVM_EXIT_IO_OUT;
+ vcpu->run->io.size = size;
+ vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
+ vcpu->run->io.count = count;
+ vcpu->run->io.port = port;
+
+ return 0;
+ }
+
static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg)
{
return kvm_x86_ops->get_segment_base(vcpu, seg);
int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest)
{
- return kvm_x86_ops->get_dr(ctxt->vcpu, dr, dest);
+ return kvm_get_dr(ctxt->vcpu, dr, dest);
}
int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value)
{
unsigned long mask = (ctxt->mode == X86EMUL_MODE_PROT64) ? ~0ULL : ~0U;
- return kvm_x86_ops->set_dr(ctxt->vcpu, dr, value & mask);
+ return kvm_set_dr(ctxt->vcpu, dr, value & mask);
}
void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context)
}
EXPORT_SYMBOL_GPL(kvm_report_emulation_failure);
- static struct x86_emulate_ops emulate_ops = {
- .read_std = kvm_read_guest_virt_system,
- .fetch = kvm_fetch_guest_virt,
- .read_emulated = emulator_read_emulated,
- .write_emulated = emulator_write_emulated,
- .cmpxchg_emulated = emulator_cmpxchg_emulated,
- };
-
- static void cache_all_regs(struct kvm_vcpu *vcpu)
+ static u64 mk_cr_64(u64 curr_cr, u32 new_val)
{
- kvm_register_read(vcpu, VCPU_REGS_RAX);
- kvm_register_read(vcpu, VCPU_REGS_RSP);
- kvm_register_read(vcpu, VCPU_REGS_RIP);
- vcpu->arch.regs_dirty = ~0;
+ return (curr_cr & ~((1ULL << 32) - 1)) | new_val;
}
- int emulate_instruction(struct kvm_vcpu *vcpu,
- unsigned long cr2,
- u16 error_code,
- int emulation_type)
+ static unsigned long emulator_get_cr(int cr, struct kvm_vcpu *vcpu)
{
- int r, shadow_mask;
- struct decode_cache *c;
- struct kvm_run *run = vcpu->run;
-
- kvm_clear_exception_queue(vcpu);
- vcpu->arch.mmio_fault_cr2 = cr2;
- /*
- * TODO: fix emulate.c to use guest_read/write_register
- * instead of direct ->regs accesses, can save hundred cycles
- * on Intel for instructions that don't read/change RSP, for
- * for example.
- */
- cache_all_regs(vcpu);
-
- vcpu->mmio_is_write = 0;
- vcpu->arch.pio.string = 0;
+ unsigned long value;
+
+ switch (cr) {
+ case 0:
+ value = kvm_read_cr0(vcpu);
+ break;
+ case 2:
+ value = vcpu->arch.cr2;
+ break;
+ case 3:
+ value = vcpu->arch.cr3;
+ break;
+ case 4:
+ value = kvm_read_cr4(vcpu);
+ break;
+ case 8:
+ value = kvm_get_cr8(vcpu);
+ break;
+ default:
+ vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr);
+ return 0;
+ }
+
+ return value;
+ }
+
+ static void emulator_set_cr(int cr, unsigned long val, struct kvm_vcpu *vcpu)
+ {
+ switch (cr) {
+ case 0:
+ kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val));
+ break;
+ case 2:
+ vcpu->arch.cr2 = val;
+ break;
+ case 3:
+ kvm_set_cr3(vcpu, val);
+ break;
+ case 4:
+ kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val));
+ break;
+ case 8:
+ kvm_set_cr8(vcpu, val & 0xfUL);
+ break;
+ default:
+ vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr);
+ }
+ }
+
+ static int emulator_get_cpl(struct kvm_vcpu *vcpu)
+ {
+ return kvm_x86_ops->get_cpl(vcpu);
+ }
+
+ static void emulator_get_gdt(struct desc_ptr *dt, struct kvm_vcpu *vcpu)
+ {
+ kvm_x86_ops->get_gdt(vcpu, dt);
+ }
+
+ static bool emulator_get_cached_descriptor(struct desc_struct *desc, int seg,
+ struct kvm_vcpu *vcpu)
+ {
+ struct kvm_segment var;
+
+ kvm_get_segment(vcpu, &var, seg);
+
+ if (var.unusable)
+ return false;
+
+ if (var.g)
+ var.limit >>= 12;
+ set_desc_limit(desc, var.limit);
+ set_desc_base(desc, (unsigned long)var.base);
+ desc->type = var.type;
+ desc->s = var.s;
+ desc->dpl = var.dpl;
+ desc->p = var.present;
+ desc->avl = var.avl;
+ desc->l = var.l;
+ desc->d = var.db;
+ desc->g = var.g;
+
+ return true;
+ }
+
+ static void emulator_set_cached_descriptor(struct desc_struct *desc, int seg,
+ struct kvm_vcpu *vcpu)
+ {
+ struct kvm_segment var;
+
+ /* needed to preserve selector */
+ kvm_get_segment(vcpu, &var, seg);
+
+ var.base = get_desc_base(desc);
+ var.limit = get_desc_limit(desc);
+ if (desc->g)
+ var.limit = (var.limit << 12) | 0xfff;
+ var.type = desc->type;
+ var.present = desc->p;
+ var.dpl = desc->dpl;
+ var.db = desc->d;
+ var.s = desc->s;
+ var.l = desc->l;
+ var.g = desc->g;
+ var.avl = desc->avl;
+ var.present = desc->p;
+ var.unusable = !var.present;
+ var.padding = 0;
+
+ kvm_set_segment(vcpu, &var, seg);
+ return;
+ }
+
+ static u16 emulator_get_segment_selector(int seg, struct kvm_vcpu *vcpu)
+ {
+ struct kvm_segment kvm_seg;
+
+ kvm_get_segment(vcpu, &kvm_seg, seg);
+ return kvm_seg.selector;
+ }
+
+ static void emulator_set_segment_selector(u16 sel, int seg,
+ struct kvm_vcpu *vcpu)
+ {
+ struct kvm_segment kvm_seg;
+
+ kvm_get_segment(vcpu, &kvm_seg, seg);
+ kvm_seg.selector = sel;
+ kvm_set_segment(vcpu, &kvm_seg, seg);
+ }
+
+ static void emulator_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
+ {
+ kvm_x86_ops->set_rflags(vcpu, rflags);
+ }
+
+ static struct x86_emulate_ops emulate_ops = {
+ .read_std = kvm_read_guest_virt_system,
+ .write_std = kvm_write_guest_virt_system,
+ .fetch = kvm_fetch_guest_virt,
+ .read_emulated = emulator_read_emulated,
+ .write_emulated = emulator_write_emulated,
+ .cmpxchg_emulated = emulator_cmpxchg_emulated,
+ .pio_in_emulated = emulator_pio_in_emulated,
+ .pio_out_emulated = emulator_pio_out_emulated,
+ .get_cached_descriptor = emulator_get_cached_descriptor,
+ .set_cached_descriptor = emulator_set_cached_descriptor,
+ .get_segment_selector = emulator_get_segment_selector,
+ .set_segment_selector = emulator_set_segment_selector,
+ .get_gdt = emulator_get_gdt,
+ .get_cr = emulator_get_cr,
+ .set_cr = emulator_set_cr,
+ .cpl = emulator_get_cpl,
+ .set_rflags = emulator_set_rflags,
+ };
+
+ static void cache_all_regs(struct kvm_vcpu *vcpu)
+ {
+ kvm_register_read(vcpu, VCPU_REGS_RAX);
+ kvm_register_read(vcpu, VCPU_REGS_RSP);
+ kvm_register_read(vcpu, VCPU_REGS_RIP);
+ vcpu->arch.regs_dirty = ~0;
+ }
+
+ int emulate_instruction(struct kvm_vcpu *vcpu,
+ unsigned long cr2,
+ u16 error_code,
+ int emulation_type)
+ {
+ int r, shadow_mask;
+ struct decode_cache *c;
+ struct kvm_run *run = vcpu->run;
+
+ kvm_clear_exception_queue(vcpu);
+ vcpu->arch.mmio_fault_cr2 = cr2;
+ /*
+ * TODO: fix emulate.c to use guest_read/write_register
+ * instead of direct ->regs accesses, can save hundred cycles
+ * on Intel for instructions that don't read/change RSP, for
+ * for example.
+ */
+ cache_all_regs(vcpu);
+
+ vcpu->mmio_is_write = 0;
if (!(emulation_type & EMULTYPE_NO_DECODE)) {
int cs_db, cs_l;
kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
vcpu->arch.emulate_ctxt.vcpu = vcpu;
- vcpu->arch.emulate_ctxt.eflags = kvm_get_rflags(vcpu);
+ vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu);
+ vcpu->arch.emulate_ctxt.eip = kvm_rip_read(vcpu);
vcpu->arch.emulate_ctxt.mode =
(!is_protmode(vcpu)) ? X86EMUL_MODE_REAL :
(vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM)
? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
r = x86_decode_insn(&vcpu->arch.emulate_ctxt, &emulate_ops);
+ trace_kvm_emulate_insn_start(vcpu);
/* Only allow emulation of specific instructions on #UD
* (namely VMMCALL, sysenter, sysexit, syscall)*/
++vcpu->stat.insn_emulation;
if (r) {
++vcpu->stat.insn_emulation_fail;
+ trace_kvm_emulate_insn_failed(vcpu);
if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
return EMULATE_DONE;
return EMULATE_FAIL;
return EMULATE_DONE;
}
+ restart:
r = x86_emulate_insn(&vcpu->arch.emulate_ctxt, &emulate_ops);
shadow_mask = vcpu->arch.emulate_ctxt.interruptibility;
if (r == 0)
kvm_x86_ops->set_interrupt_shadow(vcpu, shadow_mask);
- if (vcpu->arch.pio.string)
+ if (vcpu->arch.pio.count) {
+ if (!vcpu->arch.pio.in)
+ vcpu->arch.pio.count = 0;
return EMULATE_DO_MMIO;
+ }
- if ((r || vcpu->mmio_is_write) && run) {
+ if (r || vcpu->mmio_is_write) {
run->exit_reason = KVM_EXIT_MMIO;
run->mmio.phys_addr = vcpu->mmio_phys_addr;
memcpy(run->mmio.data, vcpu->mmio_data, 8);
if (r) {
if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
- return EMULATE_DONE;
+ goto done;
if (!vcpu->mmio_needed) {
+ ++vcpu->stat.insn_emulation_fail;
+ trace_kvm_emulate_insn_failed(vcpu);
kvm_report_emulation_failure(vcpu, "mmio");
return EMULATE_FAIL;
}
return EMULATE_DO_MMIO;
}
- kvm_set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
-
if (vcpu->mmio_is_write) {
vcpu->mmio_needed = 0;
return EMULATE_DO_MMIO;
}
- return EMULATE_DONE;
- }
- EXPORT_SYMBOL_GPL(emulate_instruction);
-
- static int pio_copy_data(struct kvm_vcpu *vcpu)
- {
- void *p = vcpu->arch.pio_data;
- gva_t q = vcpu->arch.pio.guest_gva;
- unsigned bytes;
- int ret;
- u32 error_code;
-
- bytes = vcpu->arch.pio.size * vcpu->arch.pio.cur_count;
- if (vcpu->arch.pio.in)
- ret = kvm_write_guest_virt(q, p, bytes, vcpu, &error_code);
- else
- ret = kvm_read_guest_virt(q, p, bytes, vcpu, &error_code);
-
- if (ret == X86EMUL_PROPAGATE_FAULT)
- kvm_inject_page_fault(vcpu, q, error_code);
-
- return ret;
- }
-
- int complete_pio(struct kvm_vcpu *vcpu)
- {
- struct kvm_pio_request *io = &vcpu->arch.pio;
- long delta;
- int r;
- unsigned long val;
-
- if (!io->string) {
- if (io->in) {
- val = kvm_register_read(vcpu, VCPU_REGS_RAX);
- memcpy(&val, vcpu->arch.pio_data, io->size);
- kvm_register_write(vcpu, VCPU_REGS_RAX, val);
- }
- } else {
- if (io->in) {
- r = pio_copy_data(vcpu);
- if (r)
- goto out;
- }
-
- delta = 1;
- if (io->rep) {
- delta *= io->cur_count;
- /*
- * The size of the register should really depend on
- * current address size.
- */
- val = kvm_register_read(vcpu, VCPU_REGS_RCX);
- val -= delta;
- kvm_register_write(vcpu, VCPU_REGS_RCX, val);
- }
- if (io->down)
- delta = -delta;
- delta *= io->size;
- if (io->in) {
- val = kvm_register_read(vcpu, VCPU_REGS_RDI);
- val += delta;
- kvm_register_write(vcpu, VCPU_REGS_RDI, val);
- } else {
- val = kvm_register_read(vcpu, VCPU_REGS_RSI);
- val += delta;
- kvm_register_write(vcpu, VCPU_REGS_RSI, val);
- }
- }
- out:
- io->count -= io->cur_count;
- io->cur_count = 0;
-
- return 0;
- }
-
- static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
- {
- /* TODO: String I/O for in kernel device */
- int r;
-
- if (vcpu->arch.pio.in)
- r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port,
- vcpu->arch.pio.size, pd);
- else
- r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS,
- vcpu->arch.pio.port, vcpu->arch.pio.size,
- pd);
- return r;
- }
-
- static int pio_string_write(struct kvm_vcpu *vcpu)
- {
- struct kvm_pio_request *io = &vcpu->arch.pio;
- void *pd = vcpu->arch.pio_data;
- int i, r = 0;
-
- for (i = 0; i < io->cur_count; i++) {
- if (kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS,
- io->port, io->size, pd)) {
- r = -EOPNOTSUPP;
- break;
- }
- pd += io->size;
- }
- return r;
- }
-
- int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in, int size, unsigned port)
- {
- unsigned long val;
+ done:
+ if (vcpu->arch.exception.pending)
+ vcpu->arch.emulate_ctxt.restart = false;
- trace_kvm_pio(!in, port, size, 1);
+ if (vcpu->arch.emulate_ctxt.restart)
+ goto restart;
- vcpu->run->exit_reason = KVM_EXIT_IO;
- vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
- vcpu->run->io.size = vcpu->arch.pio.size = size;
- vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
- vcpu->run->io.count = vcpu->arch.pio.count = vcpu->arch.pio.cur_count = 1;
- vcpu->run->io.port = vcpu->arch.pio.port = port;
- vcpu->arch.pio.in = in;
- vcpu->arch.pio.string = 0;
- vcpu->arch.pio.down = 0;
- vcpu->arch.pio.rep = 0;
-
- if (!vcpu->arch.pio.in) {
- val = kvm_register_read(vcpu, VCPU_REGS_RAX);
- memcpy(vcpu->arch.pio_data, &val, 4);
- }
-
- if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
- complete_pio(vcpu);
- return 1;
- }
- return 0;
+ return EMULATE_DONE;
}
- EXPORT_SYMBOL_GPL(kvm_emulate_pio);
+ EXPORT_SYMBOL_GPL(emulate_instruction);
- int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in,
- int size, unsigned long count, int down,
- gva_t address, int rep, unsigned port)
+ int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port)
{
- unsigned now, in_page;
- int ret = 0;
-
- trace_kvm_pio(!in, port, size, count);
-
- vcpu->run->exit_reason = KVM_EXIT_IO;
- vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
- vcpu->run->io.size = vcpu->arch.pio.size = size;
- vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
- vcpu->run->io.count = vcpu->arch.pio.count = vcpu->arch.pio.cur_count = count;
- vcpu->run->io.port = vcpu->arch.pio.port = port;
- vcpu->arch.pio.in = in;
- vcpu->arch.pio.string = 1;
- vcpu->arch.pio.down = down;
- vcpu->arch.pio.rep = rep;
-
- if (!count) {
- kvm_x86_ops->skip_emulated_instruction(vcpu);
- return 1;
- }
-
- if (!down)
- in_page = PAGE_SIZE - offset_in_page(address);
- else
- in_page = offset_in_page(address) + size;
- now = min(count, (unsigned long)in_page / size);
- if (!now)
- now = 1;
- if (down) {
- /*
- * String I/O in reverse. Yuck. Kill the guest, fix later.
- */
- pr_unimpl(vcpu, "guest string pio down\n");
- kvm_inject_gp(vcpu, 0);
- return 1;
- }
- vcpu->run->io.count = now;
- vcpu->arch.pio.cur_count = now;
-
- if (vcpu->arch.pio.cur_count == vcpu->arch.pio.count)
- kvm_x86_ops->skip_emulated_instruction(vcpu);
-
- vcpu->arch.pio.guest_gva = address;
-
- if (!vcpu->arch.pio.in) {
- /* string PIO write */
- ret = pio_copy_data(vcpu);
- if (ret == X86EMUL_PROPAGATE_FAULT)
- return 1;
- if (ret == 0 && !pio_string_write(vcpu)) {
- complete_pio(vcpu);
- if (vcpu->arch.pio.count == 0)
- ret = 1;
- }
- }
- /* no string PIO read support yet */
-
+ unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX);
+ int ret = emulator_pio_out_emulated(size, port, &val, 1, vcpu);
+ /* do not return to emulator after return from userspace */
+ vcpu->arch.pio.count = 0;
return ret;
}
- EXPORT_SYMBOL_GPL(kvm_emulate_pio_string);
+ EXPORT_SYMBOL_GPL(kvm_fast_pio_out);
static void bounce_off(void *info)
{
return emulator_write_emulated(rip, instruction, 3, vcpu);
}
- static u64 mk_cr_64(u64 curr_cr, u32 new_val)
- {
- return (curr_cr & ~((1ULL << 32) - 1)) | new_val;
- }
-
void realmode_lgdt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base)
{
- struct descriptor_table dt = { limit, base };
+ struct desc_ptr dt = { limit, base };
kvm_x86_ops->set_gdt(vcpu, &dt);
}
void realmode_lidt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base)
{
- struct descriptor_table dt = { limit, base };
+ struct desc_ptr dt = { limit, base };
kvm_x86_ops->set_idt(vcpu, &dt);
}
- void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw,
- unsigned long *rflags)
- {
- kvm_lmsw(vcpu, msw);
- *rflags = kvm_get_rflags(vcpu);
- }
-
- unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr)
- {
- unsigned long value;
-
- switch (cr) {
- case 0:
- value = kvm_read_cr0(vcpu);
- break;
- case 2:
- value = vcpu->arch.cr2;
- break;
- case 3:
- value = vcpu->arch.cr3;
- break;
- case 4:
- value = kvm_read_cr4(vcpu);
- break;
- case 8:
- value = kvm_get_cr8(vcpu);
- break;
- default:
- vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr);
- return 0;
- }
-
- return value;
- }
-
- void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val,
- unsigned long *rflags)
- {
- switch (cr) {
- case 0:
- kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val));
- *rflags = kvm_get_rflags(vcpu);
- break;
- case 2:
- vcpu->arch.cr2 = val;
- break;
- case 3:
- kvm_set_cr3(vcpu, val);
- break;
- case 4:
- kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val));
- break;
- case 8:
- kvm_set_cr8(vcpu, val & 0xfUL);
- break;
- default:
- vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr);
- }
- }
-
static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i)
{
struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i];
{
struct kvm_cpuid_entry2 *best;
+ best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0);
+ if (!best || best->eax < 0x80000008)
+ goto not_found;
best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
if (best)
return best->eax & 0xff;
+ not_found:
return 36;
}
{
/* try to reinject previous events if any */
if (vcpu->arch.exception.pending) {
+ trace_kvm_inj_exception(vcpu->arch.exception.nr,
+ vcpu->arch.exception.has_error_code,
+ vcpu->arch.exception.error_code);
kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr,
vcpu->arch.exception.has_error_code,
- vcpu->arch.exception.error_code);
+ vcpu->arch.exception.error_code,
+ vcpu->arch.exception.reinject);
return;
}
}
srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
- post_kvm_run_save(vcpu);
vapic_exit(vcpu);
if (!irqchip_in_kernel(vcpu->kvm))
kvm_set_cr8(vcpu, kvm_run->cr8);
- if (vcpu->arch.pio.cur_count) {
- vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
- r = complete_pio(vcpu);
- srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
- if (r)
- goto out;
- }
- if (vcpu->mmio_needed) {
- memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
- vcpu->mmio_read_completed = 1;
- vcpu->mmio_needed = 0;
-
+ if (vcpu->arch.pio.count || vcpu->mmio_needed ||
+ vcpu->arch.emulate_ctxt.restart) {
+ if (vcpu->mmio_needed) {
+ memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
+ vcpu->mmio_read_completed = 1;
+ vcpu->mmio_needed = 0;
+ }
vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
- r = emulate_instruction(vcpu, vcpu->arch.mmio_fault_cr2, 0,
- EMULTYPE_NO_DECODE);
+ r = emulate_instruction(vcpu, 0, 0, EMULTYPE_NO_DECODE);
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
if (r == EMULATE_DO_MMIO) {
- /*
- * Read-modify-write. Back to userspace.
- */
r = 0;
goto out;
}
r = __vcpu_run(vcpu);
out:
+ post_kvm_run_save(vcpu);
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &sigsaved, NULL);
return 0;
}
- void kvm_get_segment(struct kvm_vcpu *vcpu,
- struct kvm_segment *var, int seg)
- {
- kvm_x86_ops->get_segment(vcpu, var, seg);
- }
-
void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
{
struct kvm_segment cs;
int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
struct kvm_sregs *sregs)
{
- struct descriptor_table dt;
+ struct desc_ptr dt;
vcpu_load(vcpu);
kvm_get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR);
kvm_x86_ops->get_idt(vcpu, &dt);
- sregs->idt.limit = dt.limit;
- sregs->idt.base = dt.base;
+ sregs->idt.limit = dt.size;
+ sregs->idt.base = dt.address;
kvm_x86_ops->get_gdt(vcpu, &dt);
- sregs->gdt.limit = dt.limit;
- sregs->gdt.base = dt.base;
+ sregs->gdt.limit = dt.size;
+ sregs->gdt.base = dt.address;
sregs->cr0 = kvm_read_cr0(vcpu);
sregs->cr2 = vcpu->arch.cr2;
return 0;
}
- static void kvm_set_segment(struct kvm_vcpu *vcpu,
- struct kvm_segment *var, int seg)
+ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason,
+ bool has_error_code, u32 error_code)
{
- kvm_x86_ops->set_segment(vcpu, var, seg);
- }
-
- static void seg_desct_to_kvm_desct(struct desc_struct *seg_desc, u16 selector,
- struct kvm_segment *kvm_desct)
- {
- kvm_desct->base = get_desc_base(seg_desc);
- kvm_desct->limit = get_desc_limit(seg_desc);
- if (seg_desc->g) {
- kvm_desct->limit <<= 12;
- kvm_desct->limit |= 0xfff;
- }
- kvm_desct->selector = selector;
- kvm_desct->type = seg_desc->type;
- kvm_desct->present = seg_desc->p;
- kvm_desct->dpl = seg_desc->dpl;
- kvm_desct->db = seg_desc->d;
- kvm_desct->s = seg_desc->s;
- kvm_desct->l = seg_desc->l;
- kvm_desct->g = seg_desc->g;
- kvm_desct->avl = seg_desc->avl;
- if (!selector)
- kvm_desct->unusable = 1;
- else
- kvm_desct->unusable = 0;
- kvm_desct->padding = 0;
- }
-
- static void get_segment_descriptor_dtable(struct kvm_vcpu *vcpu,
- u16 selector,
- struct descriptor_table *dtable)
- {
- if (selector & 1 << 2) {
- struct kvm_segment kvm_seg;
-
- kvm_get_segment(vcpu, &kvm_seg, VCPU_SREG_LDTR);
-
- if (kvm_seg.unusable)
- dtable->limit = 0;
- else
- dtable->limit = kvm_seg.limit;
- dtable->base = kvm_seg.base;
- }
- else
- kvm_x86_ops->get_gdt(vcpu, dtable);
- }
-
- /* allowed just for 8 bytes segments */
- static int load_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
- struct desc_struct *seg_desc)
- {
- struct descriptor_table dtable;
- u16 index = selector >> 3;
- int ret;
- u32 err;
- gva_t addr;
-
- get_segment_descriptor_dtable(vcpu, selector, &dtable);
-
- if (dtable.limit < index * 8 + 7) {
- kvm_queue_exception_e(vcpu, GP_VECTOR, selector & 0xfffc);
- return X86EMUL_PROPAGATE_FAULT;
- }
- addr = dtable.base + index * 8;
- ret = kvm_read_guest_virt_system(addr, seg_desc, sizeof(*seg_desc),
- vcpu, &err);
- if (ret == X86EMUL_PROPAGATE_FAULT)
- kvm_inject_page_fault(vcpu, addr, err);
-
- return ret;
- }
-
- /* allowed just for 8 bytes segments */
- static int save_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
- struct desc_struct *seg_desc)
- {
- struct descriptor_table dtable;
- u16 index = selector >> 3;
-
- get_segment_descriptor_dtable(vcpu, selector, &dtable);
-
- if (dtable.limit < index * 8 + 7)
- return 1;
- return kvm_write_guest_virt(dtable.base + index*8, seg_desc, sizeof(*seg_desc), vcpu, NULL);
- }
-
- static gpa_t get_tss_base_addr_write(struct kvm_vcpu *vcpu,
- struct desc_struct *seg_desc)
- {
- u32 base_addr = get_desc_base(seg_desc);
-
- return kvm_mmu_gva_to_gpa_write(vcpu, base_addr, NULL);
- }
-
- static gpa_t get_tss_base_addr_read(struct kvm_vcpu *vcpu,
- struct desc_struct *seg_desc)
- {
- u32 base_addr = get_desc_base(seg_desc);
-
- return kvm_mmu_gva_to_gpa_read(vcpu, base_addr, NULL);
- }
-
- static u16 get_segment_selector(struct kvm_vcpu *vcpu, int seg)
- {
- struct kvm_segment kvm_seg;
-
- kvm_get_segment(vcpu, &kvm_seg, seg);
- return kvm_seg.selector;
- }
-
- static int kvm_load_realmode_segment(struct kvm_vcpu *vcpu, u16 selector, int seg)
- {
- struct kvm_segment segvar = {
- .base = selector << 4,
- .limit = 0xffff,
- .selector = selector,
- .type = 3,
- .present = 1,
- .dpl = 3,
- .db = 0,
- .s = 1,
- .l = 0,
- .g = 0,
- .avl = 0,
- .unusable = 0,
- };
- kvm_x86_ops->set_segment(vcpu, &segvar, seg);
- return X86EMUL_CONTINUE;
- }
-
- static int is_vm86_segment(struct kvm_vcpu *vcpu, int seg)
- {
- return (seg != VCPU_SREG_LDTR) &&
- (seg != VCPU_SREG_TR) &&
- (kvm_get_rflags(vcpu) & X86_EFLAGS_VM);
- }
-
- int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg)
- {
- struct kvm_segment kvm_seg;
- struct desc_struct seg_desc;
- u8 dpl, rpl, cpl;
- unsigned err_vec = GP_VECTOR;
- u32 err_code = 0;
- bool null_selector = !(selector & ~0x3); /* 0000-0003 are null */
- int ret;
+ int cs_db, cs_l, ret;
+ cache_all_regs(vcpu);
- if (is_vm86_segment(vcpu, seg) || !is_protmode(vcpu))
- return kvm_load_realmode_segment(vcpu, selector, seg);
+ kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
- /* NULL selector is not valid for TR, CS and SS */
- if ((seg == VCPU_SREG_CS || seg == VCPU_SREG_SS || seg == VCPU_SREG_TR)
- && null_selector)
- goto exception;
+ vcpu->arch.emulate_ctxt.vcpu = vcpu;
+ vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu);
+ vcpu->arch.emulate_ctxt.eip = kvm_rip_read(vcpu);
+ vcpu->arch.emulate_ctxt.mode =
+ (!is_protmode(vcpu)) ? X86EMUL_MODE_REAL :
+ (vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM)
+ ? X86EMUL_MODE_VM86 : cs_l
+ ? X86EMUL_MODE_PROT64 : cs_db
+ ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
- /* TR should be in GDT only */
- if (seg == VCPU_SREG_TR && (selector & (1 << 2)))
- goto exception;
+ ret = emulator_task_switch(&vcpu->arch.emulate_ctxt, &emulate_ops,
+ tss_selector, reason, has_error_code,
+ error_code);
- ret = load_guest_segment_descriptor(vcpu, selector, &seg_desc);
if (ret)
- return ret;
-
- seg_desct_to_kvm_desct(&seg_desc, selector, &kvm_seg);
-
- if (null_selector) { /* for NULL selector skip all following checks */
- kvm_seg.unusable = 1;
- goto load;
- }
-
- err_code = selector & 0xfffc;
- err_vec = GP_VECTOR;
-
- /* can't load system descriptor into segment selecor */
- if (seg <= VCPU_SREG_GS && !kvm_seg.s)
- goto exception;
-
- if (!kvm_seg.present) {
- err_vec = (seg == VCPU_SREG_SS) ? SS_VECTOR : NP_VECTOR;
- goto exception;
- }
-
- rpl = selector & 3;
- dpl = kvm_seg.dpl;
- cpl = kvm_x86_ops->get_cpl(vcpu);
-
- switch (seg) {
- case VCPU_SREG_SS:
- /*
- * segment is not a writable data segment or segment
- * selector's RPL != CPL or segment selector's RPL != CPL
- */
- if (rpl != cpl || (kvm_seg.type & 0xa) != 0x2 || dpl != cpl)
- goto exception;
- break;
- case VCPU_SREG_CS:
- if (!(kvm_seg.type & 8))
- goto exception;
-
- if (kvm_seg.type & 4) {
- /* conforming */
- if (dpl > cpl)
- goto exception;
- } else {
- /* nonconforming */
- if (rpl > cpl || dpl != cpl)
- goto exception;
- }
- /* CS(RPL) <- CPL */
- selector = (selector & 0xfffc) | cpl;
- break;
- case VCPU_SREG_TR:
- if (kvm_seg.s || (kvm_seg.type != 1 && kvm_seg.type != 9))
- goto exception;
- break;
- case VCPU_SREG_LDTR:
- if (kvm_seg.s || kvm_seg.type != 2)
- goto exception;
- break;
- default: /* DS, ES, FS, or GS */
- /*
- * segment is not a data or readable code segment or
- * ((segment is a data or nonconforming code segment)
- * and (both RPL and CPL > DPL))
- */
- if ((kvm_seg.type & 0xa) == 0x8 ||
- (((kvm_seg.type & 0xc) != 0xc) && (rpl > dpl && cpl > dpl)))
- goto exception;
- break;
- }
-
- if (!kvm_seg.unusable && kvm_seg.s) {
- /* mark segment as accessed */
- kvm_seg.type |= 1;
- seg_desc.type |= 1;
- save_guest_segment_descriptor(vcpu, selector, &seg_desc);
- }
- load:
- kvm_set_segment(vcpu, &kvm_seg, seg);
- return X86EMUL_CONTINUE;
- exception:
- kvm_queue_exception_e(vcpu, err_vec, err_code);
- return X86EMUL_PROPAGATE_FAULT;
- }
-
- static void save_state_to_tss32(struct kvm_vcpu *vcpu,
- struct tss_segment_32 *tss)
- {
- tss->cr3 = vcpu->arch.cr3;
- tss->eip = kvm_rip_read(vcpu);
- tss->eflags = kvm_get_rflags(vcpu);
- tss->eax = kvm_register_read(vcpu, VCPU_REGS_RAX);
- tss->ecx = kvm_register_read(vcpu, VCPU_REGS_RCX);
- tss->edx = kvm_register_read(vcpu, VCPU_REGS_RDX);
- tss->ebx = kvm_register_read(vcpu, VCPU_REGS_RBX);
- tss->esp = kvm_register_read(vcpu, VCPU_REGS_RSP);
- tss->ebp = kvm_register_read(vcpu, VCPU_REGS_RBP);
- tss->esi = kvm_register_read(vcpu, VCPU_REGS_RSI);
- tss->edi = kvm_register_read(vcpu, VCPU_REGS_RDI);
- tss->es = get_segment_selector(vcpu, VCPU_SREG_ES);
- tss->cs = get_segment_selector(vcpu, VCPU_SREG_CS);
- tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS);
- tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS);
- tss->fs = get_segment_selector(vcpu, VCPU_SREG_FS);
- tss->gs = get_segment_selector(vcpu, VCPU_SREG_GS);
- tss->ldt_selector = get_segment_selector(vcpu, VCPU_SREG_LDTR);
- }
-
- static void kvm_load_segment_selector(struct kvm_vcpu *vcpu, u16 sel, int seg)
- {
- struct kvm_segment kvm_seg;
- kvm_get_segment(vcpu, &kvm_seg, seg);
- kvm_seg.selector = sel;
- kvm_set_segment(vcpu, &kvm_seg, seg);
- }
-
- static int load_state_from_tss32(struct kvm_vcpu *vcpu,
- struct tss_segment_32 *tss)
- {
- kvm_set_cr3(vcpu, tss->cr3);
-
- kvm_rip_write(vcpu, tss->eip);
- kvm_set_rflags(vcpu, tss->eflags | 2);
-
- kvm_register_write(vcpu, VCPU_REGS_RAX, tss->eax);
- kvm_register_write(vcpu, VCPU_REGS_RCX, tss->ecx);
- kvm_register_write(vcpu, VCPU_REGS_RDX, tss->edx);
- kvm_register_write(vcpu, VCPU_REGS_RBX, tss->ebx);
- kvm_register_write(vcpu, VCPU_REGS_RSP, tss->esp);
- kvm_register_write(vcpu, VCPU_REGS_RBP, tss->ebp);
- kvm_register_write(vcpu, VCPU_REGS_RSI, tss->esi);
- kvm_register_write(vcpu, VCPU_REGS_RDI, tss->edi);
-
- /*
- * SDM says that segment selectors are loaded before segment
- * descriptors
- */
- kvm_load_segment_selector(vcpu, tss->ldt_selector, VCPU_SREG_LDTR);
- kvm_load_segment_selector(vcpu, tss->es, VCPU_SREG_ES);
- kvm_load_segment_selector(vcpu, tss->cs, VCPU_SREG_CS);
- kvm_load_segment_selector(vcpu, tss->ss, VCPU_SREG_SS);
- kvm_load_segment_selector(vcpu, tss->ds, VCPU_SREG_DS);
- kvm_load_segment_selector(vcpu, tss->fs, VCPU_SREG_FS);
- kvm_load_segment_selector(vcpu, tss->gs, VCPU_SREG_GS);
-
- /*
- * Now load segment descriptors. If fault happenes at this stage
- * it is handled in a context of new task
- */
- if (kvm_load_segment_descriptor(vcpu, tss->ldt_selector, VCPU_SREG_LDTR))
- return 1;
-
- if (kvm_load_segment_descriptor(vcpu, tss->es, VCPU_SREG_ES))
- return 1;
-
- if (kvm_load_segment_descriptor(vcpu, tss->cs, VCPU_SREG_CS))
- return 1;
-
- if (kvm_load_segment_descriptor(vcpu, tss->ss, VCPU_SREG_SS))
- return 1;
-
- if (kvm_load_segment_descriptor(vcpu, tss->ds, VCPU_SREG_DS))
- return 1;
-
- if (kvm_load_segment_descriptor(vcpu, tss->fs, VCPU_SREG_FS))
- return 1;
-
- if (kvm_load_segment_descriptor(vcpu, tss->gs, VCPU_SREG_GS))
- return 1;
- return 0;
- }
-
- static void save_state_to_tss16(struct kvm_vcpu *vcpu,
- struct tss_segment_16 *tss)
- {
- tss->ip = kvm_rip_read(vcpu);
- tss->flag = kvm_get_rflags(vcpu);
- tss->ax = kvm_register_read(vcpu, VCPU_REGS_RAX);
- tss->cx = kvm_register_read(vcpu, VCPU_REGS_RCX);
- tss->dx = kvm_register_read(vcpu, VCPU_REGS_RDX);
- tss->bx = kvm_register_read(vcpu, VCPU_REGS_RBX);
- tss->sp = kvm_register_read(vcpu, VCPU_REGS_RSP);
- tss->bp = kvm_register_read(vcpu, VCPU_REGS_RBP);
- tss->si = kvm_register_read(vcpu, VCPU_REGS_RSI);
- tss->di = kvm_register_read(vcpu, VCPU_REGS_RDI);
-
- tss->es = get_segment_selector(vcpu, VCPU_SREG_ES);
- tss->cs = get_segment_selector(vcpu, VCPU_SREG_CS);
- tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS);
- tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS);
- tss->ldt = get_segment_selector(vcpu, VCPU_SREG_LDTR);
- }
-
- static int load_state_from_tss16(struct kvm_vcpu *vcpu,
- struct tss_segment_16 *tss)
- {
- kvm_rip_write(vcpu, tss->ip);
- kvm_set_rflags(vcpu, tss->flag | 2);
- kvm_register_write(vcpu, VCPU_REGS_RAX, tss->ax);
- kvm_register_write(vcpu, VCPU_REGS_RCX, tss->cx);
- kvm_register_write(vcpu, VCPU_REGS_RDX, tss->dx);
- kvm_register_write(vcpu, VCPU_REGS_RBX, tss->bx);
- kvm_register_write(vcpu, VCPU_REGS_RSP, tss->sp);
- kvm_register_write(vcpu, VCPU_REGS_RBP, tss->bp);
- kvm_register_write(vcpu, VCPU_REGS_RSI, tss->si);
- kvm_register_write(vcpu, VCPU_REGS_RDI, tss->di);
-
- /*
- * SDM says that segment selectors are loaded before segment
- * descriptors
- */
- kvm_load_segment_selector(vcpu, tss->ldt, VCPU_SREG_LDTR);
- kvm_load_segment_selector(vcpu, tss->es, VCPU_SREG_ES);
- kvm_load_segment_selector(vcpu, tss->cs, VCPU_SREG_CS);
- kvm_load_segment_selector(vcpu, tss->ss, VCPU_SREG_SS);
- kvm_load_segment_selector(vcpu, tss->ds, VCPU_SREG_DS);
-
- /*
- * Now load segment descriptors. If fault happenes at this stage
- * it is handled in a context of new task
- */
- if (kvm_load_segment_descriptor(vcpu, tss->ldt, VCPU_SREG_LDTR))
- return 1;
-
- if (kvm_load_segment_descriptor(vcpu, tss->es, VCPU_SREG_ES))
- return 1;
-
- if (kvm_load_segment_descriptor(vcpu, tss->cs, VCPU_SREG_CS))
- return 1;
-
- if (kvm_load_segment_descriptor(vcpu, tss->ss, VCPU_SREG_SS))
- return 1;
-
- if (kvm_load_segment_descriptor(vcpu, tss->ds, VCPU_SREG_DS))
- return 1;
- return 0;
- }
-
- static int kvm_task_switch_16(struct kvm_vcpu *vcpu, u16 tss_selector,
- u16 old_tss_sel, u32 old_tss_base,
- struct desc_struct *nseg_desc)
- {
- struct tss_segment_16 tss_segment_16;
- int ret = 0;
-
- if (kvm_read_guest(vcpu->kvm, old_tss_base, &tss_segment_16,
- sizeof tss_segment_16))
- goto out;
-
- save_state_to_tss16(vcpu, &tss_segment_16);
-
- if (kvm_write_guest(vcpu->kvm, old_tss_base, &tss_segment_16,
- sizeof tss_segment_16))
- goto out;
-
- if (kvm_read_guest(vcpu->kvm, get_tss_base_addr_read(vcpu, nseg_desc),
- &tss_segment_16, sizeof tss_segment_16))
- goto out;
-
- if (old_tss_sel != 0xffff) {
- tss_segment_16.prev_task_link = old_tss_sel;
-
- if (kvm_write_guest(vcpu->kvm,
- get_tss_base_addr_write(vcpu, nseg_desc),
- &tss_segment_16.prev_task_link,
- sizeof tss_segment_16.prev_task_link))
- goto out;
- }
-
- if (load_state_from_tss16(vcpu, &tss_segment_16))
- goto out;
+ return EMULATE_FAIL;
- ret = 1;
- out:
- return ret;
- }
-
- static int kvm_task_switch_32(struct kvm_vcpu *vcpu, u16 tss_selector,
- u16 old_tss_sel, u32 old_tss_base,
- struct desc_struct *nseg_desc)
- {
- struct tss_segment_32 tss_segment_32;
- int ret = 0;
-
- if (kvm_read_guest(vcpu->kvm, old_tss_base, &tss_segment_32,
- sizeof tss_segment_32))
- goto out;
-
- save_state_to_tss32(vcpu, &tss_segment_32);
-
- if (kvm_write_guest(vcpu->kvm, old_tss_base, &tss_segment_32,
- sizeof tss_segment_32))
- goto out;
-
- if (kvm_read_guest(vcpu->kvm, get_tss_base_addr_read(vcpu, nseg_desc),
- &tss_segment_32, sizeof tss_segment_32))
- goto out;
-
- if (old_tss_sel != 0xffff) {
- tss_segment_32.prev_task_link = old_tss_sel;
-
- if (kvm_write_guest(vcpu->kvm,
- get_tss_base_addr_write(vcpu, nseg_desc),
- &tss_segment_32.prev_task_link,
- sizeof tss_segment_32.prev_task_link))
- goto out;
- }
-
- if (load_state_from_tss32(vcpu, &tss_segment_32))
- goto out;
-
- ret = 1;
- out:
- return ret;
- }
-
- int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
- {
- struct kvm_segment tr_seg;
- struct desc_struct cseg_desc;
- struct desc_struct nseg_desc;
- int ret = 0;
- u32 old_tss_base = get_segment_base(vcpu, VCPU_SREG_TR);
- u16 old_tss_sel = get_segment_selector(vcpu, VCPU_SREG_TR);
- u32 desc_limit;
-
- old_tss_base = kvm_mmu_gva_to_gpa_write(vcpu, old_tss_base, NULL);
-
- /* FIXME: Handle errors. Failure to read either TSS or their
- * descriptors should generate a pagefault.
- */
- if (load_guest_segment_descriptor(vcpu, tss_selector, &nseg_desc))
- goto out;
-
- if (load_guest_segment_descriptor(vcpu, old_tss_sel, &cseg_desc))
- goto out;
-
- if (reason != TASK_SWITCH_IRET) {
- int cpl;
-
- cpl = kvm_x86_ops->get_cpl(vcpu);
- if ((tss_selector & 3) > nseg_desc.dpl || cpl > nseg_desc.dpl) {
- kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
- return 1;
- }
- }
-
- desc_limit = get_desc_limit(&nseg_desc);
- if (!nseg_desc.p ||
- ((desc_limit < 0x67 && (nseg_desc.type & 8)) ||
- desc_limit < 0x2b)) {
- kvm_queue_exception_e(vcpu, TS_VECTOR, tss_selector & 0xfffc);
- return 1;
- }
-
- if (reason == TASK_SWITCH_IRET || reason == TASK_SWITCH_JMP) {
- cseg_desc.type &= ~(1 << 1); //clear the B flag
- save_guest_segment_descriptor(vcpu, old_tss_sel, &cseg_desc);
- }
-
- if (reason == TASK_SWITCH_IRET) {
- u32 eflags = kvm_get_rflags(vcpu);
- kvm_set_rflags(vcpu, eflags & ~X86_EFLAGS_NT);
- }
-
- /* set back link to prev task only if NT bit is set in eflags
- note that old_tss_sel is not used afetr this point */
- if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE)
- old_tss_sel = 0xffff;
-
- if (nseg_desc.type & 8)
- ret = kvm_task_switch_32(vcpu, tss_selector, old_tss_sel,
- old_tss_base, &nseg_desc);
- else
- ret = kvm_task_switch_16(vcpu, tss_selector, old_tss_sel,
- old_tss_base, &nseg_desc);
-
- if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) {
- u32 eflags = kvm_get_rflags(vcpu);
- kvm_set_rflags(vcpu, eflags | X86_EFLAGS_NT);
- }
-
- if (reason != TASK_SWITCH_IRET) {
- nseg_desc.type |= (1 << 1);
- save_guest_segment_descriptor(vcpu, tss_selector,
- &nseg_desc);
- }
-
- kvm_x86_ops->set_cr0(vcpu, kvm_read_cr0(vcpu) | X86_CR0_TS);
- seg_desct_to_kvm_desct(&nseg_desc, tss_selector, &tr_seg);
- tr_seg.type = 11;
- kvm_set_segment(vcpu, &tr_seg, VCPU_SREG_TR);
- out:
- return ret;
+ kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
+ return EMULATE_DONE;
}
EXPORT_SYMBOL_GPL(kvm_task_switch);
{
int mmu_reset_needed = 0;
int pending_vec, max_bits;
- struct descriptor_table dt;
+ struct desc_ptr dt;
vcpu_load(vcpu);
- dt.limit = sregs->idt.limit;
- dt.base = sregs->idt.base;
+ dt.size = sregs->idt.limit;
+ dt.address = sregs->idt.base;
kvm_x86_ops->set_idt(vcpu, &dt);
- dt.limit = sregs->gdt.limit;
- dt.base = sregs->gdt.base;
+ dt.size = sregs->gdt.limit;
+ dt.address = sregs->gdt.base;
kvm_x86_ops->set_gdt(vcpu, &dt);
vcpu->arch.cr2 = sregs->cr2;
vcpu->arch.switch_db_regs = (vcpu->arch.dr7 & DR7_BP_EN_MASK);
}
- if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
- vcpu->arch.singlestep_cs =
- get_segment_selector(vcpu, VCPU_SREG_CS);
- vcpu->arch.singlestep_rip = kvm_rip_read(vcpu);
- }
+ if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+ vcpu->arch.singlestep_rip = kvm_rip_read(vcpu) +
+ get_segment_base(vcpu, VCPU_SREG_CS);
/*
* Trigger an rflags update that will inject or remove the trace
return kvm_x86_ops->interrupt_allowed(vcpu);
}
+ bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip)
+ {
+ unsigned long current_rip = kvm_rip_read(vcpu) +
+ get_segment_base(vcpu, VCPU_SREG_CS);
+
+ return current_rip == linear_rip;
+ }
+ EXPORT_SYMBOL_GPL(kvm_is_linear_rip);
+
unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu)
{
unsigned long rflags;
rflags = kvm_x86_ops->get_rflags(vcpu);
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
- rflags &= ~(unsigned long)(X86_EFLAGS_TF | X86_EFLAGS_RF);
+ rflags &= ~X86_EFLAGS_TF;
return rflags;
}
EXPORT_SYMBOL_GPL(kvm_get_rflags);
void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
{
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP &&
- vcpu->arch.singlestep_cs ==
- get_segment_selector(vcpu, VCPU_SREG_CS) &&
- vcpu->arch.singlestep_rip == kvm_rip_read(vcpu))
- rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF;
+ kvm_is_linear_rip(vcpu, vcpu->arch.singlestep_rip))
+ rflags |= X86_EFLAGS_TF;
kvm_x86_ops->set_rflags(vcpu, rflags);
}
EXPORT_SYMBOL_GPL(kvm_set_rflags);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit);
+ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts);
static void kvm_iommu_put_pages(struct kvm *kvm,
gfn_t base_gfn, unsigned long npages);
+static pfn_t kvm_pin_pages(struct kvm *kvm, struct kvm_memory_slot *slot,
+ gfn_t gfn, unsigned long size)
+{
+ gfn_t end_gfn;
+ pfn_t pfn;
+
+ pfn = gfn_to_pfn_memslot(kvm, slot, gfn);
+ end_gfn = gfn + (size >> PAGE_SHIFT);
+ gfn += 1;
+
+ if (is_error_pfn(pfn))
+ return pfn;
+
+ while (gfn < end_gfn)
+ gfn_to_pfn_memslot(kvm, slot, gfn++);
+
+ return pfn;
+}
+
int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
{
- gfn_t gfn = slot->base_gfn;
- unsigned long npages = slot->npages;
+ gfn_t gfn, end_gfn;
pfn_t pfn;
- int i, r = 0;
+ int r = 0;
struct iommu_domain *domain = kvm->arch.iommu_domain;
int flags;
if (!domain)
return 0;
+ gfn = slot->base_gfn;
+ end_gfn = gfn + slot->npages;
+
flags = IOMMU_READ | IOMMU_WRITE;
if (kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY)
flags |= IOMMU_CACHE;
- for (i = 0; i < npages; i++) {
- /* check if already mapped */
- if (iommu_iova_to_phys(domain, gfn_to_gpa(gfn)))
+
+ while (gfn < end_gfn) {
+ unsigned long page_size;
+
+ /* Check if already mapped */
+ if (iommu_iova_to_phys(domain, gfn_to_gpa(gfn))) {
+ gfn += 1;
+ continue;
+ }
+
+ /* Get the page size we could use to map */
+ page_size = kvm_host_page_size(kvm, gfn);
+
+ /* Make sure the page_size does not exceed the memslot */
+ while ((gfn + (page_size >> PAGE_SHIFT)) > end_gfn)
+ page_size >>= 1;
+
+ /* Make sure gfn is aligned to the page size we want to map */
+ while ((gfn << PAGE_SHIFT) & (page_size - 1))
+ page_size >>= 1;
+
+ /*
+ * Pin all pages we are about to map in memory. This is
+ * important because we unmap and unpin in 4kb steps later.
+ */
+ pfn = kvm_pin_pages(kvm, slot, gfn, page_size);
+ if (is_error_pfn(pfn)) {
+ gfn += 1;
continue;
+ }
- pfn = gfn_to_pfn_memslot(kvm, slot, gfn);
- r = iommu_map_range(domain,
- gfn_to_gpa(gfn),
- pfn_to_hpa(pfn),
- PAGE_SIZE, flags);
+ /* Map into IO address space */
+ r = iommu_map(domain, gfn_to_gpa(gfn), pfn_to_hpa(pfn),
+ get_order(page_size), flags);
if (r) {
printk(KERN_ERR "kvm_iommu_map_address:"
"iommu failed to map pfn=%lx\n", pfn);
goto unmap_pages;
}
- gfn++;
+
+ gfn += page_size >> PAGE_SHIFT;
+
+
}
+
return 0;
unmap_pages:
- kvm_iommu_put_pages(kvm, slot->base_gfn, i);
+ kvm_iommu_put_pages(kvm, slot->base_gfn, gfn);
return r;
}
int i, r = 0;
struct kvm_memslots *slots;
- slots = rcu_dereference(kvm->memslots);
+ slots = kvm_memslots(kvm);
for (i = 0; i < slots->nmemslots; i++) {
r = kvm_iommu_map_pages(kvm, &slots->memslots[i]);
return r;
}
+static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages)
+{
+ unsigned long i;
+
+ for (i = 0; i < npages; ++i)
+ kvm_release_pfn_clean(pfn + i);
+}
+
static void kvm_iommu_put_pages(struct kvm *kvm,
gfn_t base_gfn, unsigned long npages)
{
- gfn_t gfn = base_gfn;
+ struct iommu_domain *domain;
+ gfn_t end_gfn, gfn;
pfn_t pfn;
- struct iommu_domain *domain = kvm->arch.iommu_domain;
- unsigned long i;
u64 phys;
+ domain = kvm->arch.iommu_domain;
+ end_gfn = base_gfn + npages;
+ gfn = base_gfn;
+
/* check if iommu exists and in use */
if (!domain)
return;
- for (i = 0; i < npages; i++) {
+ while (gfn < end_gfn) {
+ unsigned long unmap_pages;
+ int order;
+
+ /* Get physical address */
phys = iommu_iova_to_phys(domain, gfn_to_gpa(gfn));
- pfn = phys >> PAGE_SHIFT;
- kvm_release_pfn_clean(pfn);
- gfn++;
- }
+ pfn = phys >> PAGE_SHIFT;
+
+ /* Unmap address from IO address space */
+ order = iommu_unmap(domain, gfn_to_gpa(gfn), PAGE_SIZE);
+ unmap_pages = 1ULL << order;
- iommu_unmap_range(domain, gfn_to_gpa(base_gfn), PAGE_SIZE * npages);
+ /* Unpin all pages we just unmapped to not leak any memory */
+ kvm_unpin_pages(kvm, pfn, unmap_pages);
+
+ gfn += unmap_pages;
+ }
}
static int kvm_iommu_unmap_memslots(struct kvm *kvm)
int i;
struct kvm_memslots *slots;
- slots = rcu_dereference(kvm->memslots);
+ slots = kvm_memslots(kvm);
for (i = 0; i < slots->nmemslots; i++) {
kvm_iommu_put_pages(kvm, slots->memslots[i].base_gfn,