summaryrefslogtreecommitdiffstats
path: root/arch/x86/include/asm/kvm_host.h
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/include/asm/kvm_host.h')
-rw-r--r--arch/x86/include/asm/kvm_host.h194
1 files changed, 140 insertions, 54 deletions
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 74e88e5edd9c..40a0c0fd95ca 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -78,6 +78,8 @@
#define KVM_REQ_HV_STIMER KVM_ARCH_REQ(22)
#define KVM_REQ_LOAD_EOI_EXITMAP KVM_ARCH_REQ(23)
#define KVM_REQ_GET_VMCS12_PAGES KVM_ARCH_REQ(24)
+#define KVM_REQ_APICV_UPDATE \
+ KVM_ARCH_REQ_FLAGS(25, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define CR0_RESERVED_BITS \
(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
@@ -156,10 +158,8 @@ enum kvm_reg {
VCPU_REGS_R15 = __VCPU_REGS_R15,
#endif
VCPU_REGS_RIP,
- NR_VCPU_REGS
-};
+ NR_VCPU_REGS,
-enum kvm_reg_ex {
VCPU_EXREG_PDPTR = NR_VCPU_REGS,
VCPU_EXREG_CR3,
VCPU_EXREG_RFLAGS,
@@ -177,6 +177,11 @@ enum {
VCPU_SREG_LDTR,
};
+enum exit_fastpath_completion {
+ EXIT_FASTPATH_NONE,
+ EXIT_FASTPATH_SKIP_EMUL_INS,
+};
+
#include <asm/kvm_emulate.h>
#define KVM_NR_MEM_OBJS 40
@@ -219,13 +224,6 @@ enum {
PFERR_WRITE_MASK | \
PFERR_PRESENT_MASK)
-/*
- * The mask used to denote special SPTEs, which can be either MMIO SPTEs or
- * Access Tracking SPTEs. We use bit 62 instead of bit 63 to avoid conflicting
- * with the SVE bit in EPT PTEs.
- */
-#define SPTE_SPECIAL_MASK (1ULL << 62)
-
/* apic attention bits */
#define KVM_APIC_CHECK_VAPIC 0
/*
@@ -319,8 +317,12 @@ struct kvm_rmap_head {
struct kvm_mmu_page {
struct list_head link;
struct hlist_node hash_link;
+ struct list_head lpage_disallowed_link;
+
bool unsync;
+ u8 mmu_valid_gen;
bool mmio_cached;
+ bool lpage_disallowed; /* Can't be replaced by an equiv large page */
/*
* The following two entries are used to key the shadow page in the
@@ -383,12 +385,12 @@ struct kvm_mmu {
void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root);
unsigned long (*get_cr3)(struct kvm_vcpu *vcpu);
u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index);
- int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err,
+ int (*page_fault)(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 err,
bool prefault);
void (*inject_page_fault)(struct kvm_vcpu *vcpu,
struct x86_exception *fault);
- gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access,
- struct x86_exception *exception);
+ gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t gva_or_gpa,
+ u32 access, struct x86_exception *exception);
gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
struct x86_exception *exception);
int (*sync_page)(struct kvm_vcpu *vcpu,
@@ -457,6 +459,11 @@ struct kvm_pmc {
u64 eventsel;
struct perf_event *perf_event;
struct kvm_vcpu *vcpu;
+ /*
+ * eventsel value for general purpose counters,
+ * ctrl value for fixed counters.
+ */
+ u64 current_config;
};
struct kvm_pmu {
@@ -475,7 +482,21 @@ struct kvm_pmu {
struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED];
struct irq_work irq_work;
- u64 reprogram_pmi;
+ DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX);
+ DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX);
+ DECLARE_BITMAP(pmc_in_use, X86_PMC_IDX_MAX);
+
+ /*
+ * The gate to release perf_events not marked in
+ * pmc_in_use only once in a vcpu time slice.
+ */
+ bool need_cleanup;
+
+ /*
+ * The total number of programmed perf_events and it helps to avoid
+ * redundant check before cleanup if guest don't use vPMU at all.
+ */
+ u8 event_count;
};
struct kvm_pmu_ops;
@@ -568,6 +589,7 @@ struct kvm_vcpu_arch {
u64 smbase;
u64 smi_count;
bool tpr_access_reporting;
+ bool xsaves_enabled;
u64 ia32_xss;
u64 microcode_version;
u64 arch_capabilities;
@@ -591,7 +613,7 @@ struct kvm_vcpu_arch {
* Paging state of an L2 guest (used for nested npt)
*
* This context will save all necessary information to walk page tables
- * of the an L2 guest. This context is only initialized for page table
+ * of an L2 guest. This context is only initialized for page table
* walking and not for faulting since we never handle l2 page faults on
* the host.
*/
@@ -670,10 +692,10 @@ struct kvm_vcpu_arch {
bool pvclock_set_guest_stopped_request;
struct {
+ u8 preempted;
u64 msr_val;
u64 last_steal;
- struct gfn_to_hva_cache stime;
- struct kvm_steal_time steal;
+ struct gfn_to_pfn_cache cache;
} st;
u64 tsc_offset;
@@ -717,7 +739,7 @@ struct kvm_vcpu_arch {
/* Cache MMIO info */
u64 mmio_gva;
- unsigned access;
+ unsigned mmio_access;
gfn_t mmio_gfn;
u64 mmio_gen;
@@ -759,9 +781,19 @@ struct kvm_vcpu_arch {
u64 msr_kvm_poll_control;
/*
- * Indicate whether the access faults on its page table in guest
- * which is set when fix page fault and used to detect unhandeable
- * instruction.
+ * Indicates the guest is trying to write a gfn that contains one or
+ * more of the PTEs used to translate the write itself, i.e. the access
+ * is changing its own translation in the guest page tables. KVM exits
+ * to userspace if emulation of the faulting instruction fails and this
+ * flag is set, as KVM cannot make forward progress.
+ *
+ * If emulation fails for a write to guest page tables, KVM unprotects
+ * (zaps) the shadow page for the target gfn and resumes the guest to
+ * retry the non-emulatable instruction (on hardware). Unprotecting the
+ * gfn doesn't allow forward progress for a self-changing access because
+ * doing so also zaps the translation for the gfn, i.e. retrying the
+ * instruction will hit a !PRESENT fault, which results in a new shadow
+ * page and sends KVM back to square one.
*/
bool write_fault_to_shadow_pgtable;
@@ -843,6 +875,8 @@ struct kvm_hv {
/* How many vCPUs have VP index != vCPU index */
atomic_t num_mismatched_vp_indexes;
+
+ struct hv_partition_assist_pg *hv_pa_pg;
};
enum kvm_irqchip_mode {
@@ -851,16 +885,25 @@ enum kvm_irqchip_mode {
KVM_IRQCHIP_SPLIT, /* created with KVM_CAP_SPLIT_IRQCHIP */
};
+#define APICV_INHIBIT_REASON_DISABLE 0
+#define APICV_INHIBIT_REASON_HYPERV 1
+#define APICV_INHIBIT_REASON_NESTED 2
+#define APICV_INHIBIT_REASON_IRQWIN 3
+#define APICV_INHIBIT_REASON_PIT_REINJ 4
+
struct kvm_arch {
unsigned long n_used_mmu_pages;
unsigned long n_requested_mmu_pages;
unsigned long n_max_mmu_pages;
unsigned int indirect_shadow_pages;
+ u8 mmu_valid_gen;
struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
/*
* Hash table of struct kvm_mmu_page.
*/
struct list_head active_mmu_pages;
+ struct list_head zapped_obsolete_pages;
+ struct list_head lpage_disallowed_mmu_pages;
struct kvm_page_track_notifier_node mmu_sp_tracker;
struct kvm_page_track_notifier_head track_notifier_head;
@@ -879,6 +922,7 @@ struct kvm_arch {
struct kvm_apic_map *apic_map;
bool apic_access_page_done;
+ unsigned long apicv_inhibit_reasons;
gpa_t wall_clock;
@@ -935,6 +979,7 @@ struct kvm_arch {
bool exception_payload_enabled;
struct kvm_pmu_event_filter *pmu_event_filter;
+ struct task_struct *nx_lpage_recovery_thread;
};
struct kvm_vm_stat {
@@ -948,6 +993,7 @@ struct kvm_vm_stat {
ulong mmu_unsync;
ulong remote_tlb_flush;
ulong lpages;
+ ulong nx_lpage_splits;
ulong max_mmu_page_hash_collisions;
};
@@ -1000,6 +1046,11 @@ struct kvm_lapic_irq {
bool msi_redir_hint;
};
+static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical)
+{
+ return dest_mode_logical ? APIC_DEST_LOGICAL : APIC_DEST_PHYSICAL;
+}
+
struct kvm_x86_ops {
int (*cpu_has_kvm_support)(void); /* __init */
int (*disabled_by_bios)(void); /* __init */
@@ -1018,7 +1069,7 @@ struct kvm_x86_ops {
void (*vm_destroy)(struct kvm *kvm);
/* Create, but do not attach this VCPU */
- struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id);
+ int (*vcpu_create)(struct kvm_vcpu *vcpu);
void (*vcpu_free)(struct kvm_vcpu *vcpu);
void (*vcpu_reset)(struct kvm_vcpu *vcpu, bool init_event);
@@ -1037,7 +1088,6 @@ struct kvm_x86_ops {
struct kvm_segment *var, int seg);
void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
void (*decache_cr0_guest_bits)(struct kvm_vcpu *vcpu);
- void (*decache_cr3)(struct kvm_vcpu *vcpu);
void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu);
void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0);
void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
@@ -1069,8 +1119,9 @@ struct kvm_x86_ops {
void (*tlb_flush_gva)(struct kvm_vcpu *vcpu, gva_t addr);
void (*run)(struct kvm_vcpu *vcpu);
- int (*handle_exit)(struct kvm_vcpu *vcpu);
- void (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
+ int (*handle_exit)(struct kvm_vcpu *vcpu,
+ enum exit_fastpath_completion exit_fastpath);
+ int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask);
u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu);
void (*patch_hypercall)(struct kvm_vcpu *vcpu,
@@ -1086,7 +1137,8 @@ struct kvm_x86_ops {
void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
void (*enable_irq_window)(struct kvm_vcpu *vcpu);
void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
- bool (*get_enable_apicv)(struct kvm_vcpu *vcpu);
+ bool (*check_apicv_inhibit_reasons)(ulong bit);
+ void (*pre_update_apicv_exec_ctrl)(struct kvm *kvm, bool activate);
void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu);
void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr);
@@ -1119,11 +1171,13 @@ struct kvm_x86_ops {
int (*check_intercept)(struct kvm_vcpu *vcpu,
struct x86_instruction_info *info,
enum x86_intercept_stage stage);
- void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu);
+ void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu,
+ enum exit_fastpath_completion *exit_fastpath);
bool (*mpx_supported)(void);
bool (*xsaves_supported)(void);
bool (*umip_emulated)(void);
bool (*pt_supported)(void);
+ bool (*pku_supported)(void);
int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr);
void (*request_immediate_exit)(struct kvm_vcpu *vcpu);
@@ -1191,7 +1245,7 @@ struct kvm_x86_ops {
int (*set_nested_state)(struct kvm_vcpu *vcpu,
struct kvm_nested_state __user *user_kvm_nested_state,
struct kvm_nested_state *kvm_state);
- void (*get_vmcs12_pages)(struct kvm_vcpu *vcpu);
+ bool (*get_vmcs12_pages)(struct kvm_vcpu *vcpu);
int (*smi_allowed)(struct kvm_vcpu *vcpu);
int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
@@ -1209,6 +1263,9 @@ struct kvm_x86_ops {
uint16_t (*nested_get_evmcs_version)(struct kvm_vcpu *vcpu);
bool (*need_emulation_on_page_fault)(struct kvm_vcpu *vcpu);
+
+ bool (*apic_init_signal_blocked)(struct kvm_vcpu *vcpu);
+ int (*enable_direct_tlbflush)(struct kvm_vcpu *vcpu);
};
struct kvm_arch_async_pf {
@@ -1308,26 +1365,53 @@ extern u64 kvm_default_tsc_scaling_ratio;
extern u64 kvm_mce_cap_supported;
-enum emulation_result {
- EMULATE_DONE, /* no further processing */
- EMULATE_USER_EXIT, /* kvm_run ready for userspace exit */
- EMULATE_FAIL, /* can't emulate this instruction */
-};
-
+/*
+ * EMULTYPE_NO_DECODE - Set when re-emulating an instruction (after completing
+ * userspace I/O) to indicate that the emulation context
+ * should be resued as is, i.e. skip initialization of
+ * emulation context, instruction fetch and decode.
+ *
+ * EMULTYPE_TRAP_UD - Set when emulating an intercepted #UD from hardware.
+ * Indicates that only select instructions (tagged with
+ * EmulateOnUD) should be emulated (to minimize the emulator
+ * attack surface). See also EMULTYPE_TRAP_UD_FORCED.
+ *
+ * EMULTYPE_SKIP - Set when emulating solely to skip an instruction, i.e. to
+ * decode the instruction length. For use *only* by
+ * kvm_x86_ops->skip_emulated_instruction() implementations.
+ *
+ * EMULTYPE_ALLOW_RETRY - Set when the emulator should resume the guest to
+ * retry native execution under certain conditions.
+ *
+ * EMULTYPE_TRAP_UD_FORCED - Set when emulating an intercepted #UD that was
+ * triggered by KVM's magic "force emulation" prefix,
+ * which is opt in via module param (off by default).
+ * Bypasses EmulateOnUD restriction despite emulating
+ * due to an intercepted #UD (see EMULTYPE_TRAP_UD).
+ * Used to test the full emulator from userspace.
+ *
+ * EMULTYPE_VMWARE_GP - Set when emulating an intercepted #GP for VMware
+ * backdoor emulation, which is opt in via module param.
+ * VMware backoor emulation handles select instructions
+ * and reinjects the #GP for all other cases.
+ */
#define EMULTYPE_NO_DECODE (1 << 0)
#define EMULTYPE_TRAP_UD (1 << 1)
#define EMULTYPE_SKIP (1 << 2)
#define EMULTYPE_ALLOW_RETRY (1 << 3)
-#define EMULTYPE_NO_UD_ON_FAIL (1 << 4)
-#define EMULTYPE_VMWARE (1 << 5)
+#define EMULTYPE_TRAP_UD_FORCED (1 << 4)
+#define EMULTYPE_VMWARE_GP (1 << 5)
int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type);
int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu,
void *insn, int insn_len);
void kvm_enable_efer_bits(u64);
bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer);
-int kvm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr);
-int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr);
+int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, bool host_initiated);
+int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data);
+int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data);
+int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu);
+int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu);
struct x86_emulate_ctxt;
@@ -1413,11 +1497,15 @@ gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva,
gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva,
struct x86_exception *exception);
-void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu);
+bool kvm_apicv_activated(struct kvm *kvm);
+void kvm_apicv_init(struct kvm *kvm, bool enable);
+void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu);
+void kvm_request_apicv_update(struct kvm *kvm, bool activate,
+ unsigned long bit);
int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
-int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u64 error_code,
+int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
void *insn, int insn_len);
void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid);
@@ -1500,7 +1588,7 @@ enum {
#define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
#define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)
-asmlinkage void __noreturn kvm_spurious_fault(void);
+asmlinkage void kvm_spurious_fault(void);
/*
* Hardware virtualization extension instructions may fault if a
@@ -1508,24 +1596,14 @@ asmlinkage void __noreturn kvm_spurious_fault(void);
* Usually after catching the fault we just panic; during reboot
* instead the instruction is ignored.
*/
-#define ____kvm_handle_fault_on_reboot(insn, cleanup_insn) \
+#define __kvm_handle_fault_on_reboot(insn) \
"666: \n\t" \
insn "\n\t" \
"jmp 668f \n\t" \
"667: \n\t" \
"call kvm_spurious_fault \n\t" \
"668: \n\t" \
- ".pushsection .fixup, \"ax\" \n\t" \
- "700: \n\t" \
- cleanup_insn "\n\t" \
- "cmpb $0, kvm_rebooting\n\t" \
- "je 667b \n\t" \
- "jmp 668b \n\t" \
- ".popsection \n\t" \
- _ASM_EXTABLE(666b, 700b)
-
-#define __kvm_handle_fault_on_reboot(insn) \
- ____kvm_handle_fault_on_reboot(insn, "")
+ _ASM_EXTABLE(666b, 667b)
#define KVM_ARCH_WANT_MMU_NOTIFIER
int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end);
@@ -1554,6 +1632,8 @@ bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip);
void kvm_make_mclock_inprogress_request(struct kvm *kvm);
void kvm_make_scan_ioapic_request(struct kvm *kvm);
+void kvm_make_scan_ioapic_request_mask(struct kvm *kvm,
+ unsigned long *vcpu_bitmap);
void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
struct kvm_async_pf *work);
@@ -1571,7 +1651,6 @@ void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu);
int kvm_is_in_guest(void);
int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size);
-int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size);
bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu);
bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu);
@@ -1581,6 +1660,13 @@ bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq,
void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
struct kvm_lapic_irq *irq);
+static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq)
+{
+ /* We can only post Fixed and LowPrio IRQs */
+ return (irq->delivery_mode == dest_Fixed ||
+ irq->delivery_mode == dest_LowestPrio);
+}
+
static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
{
if (kvm_x86_ops->vcpu_blocking)
OpenPOWER on IntegriCloud