summaryrefslogtreecommitdiff
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.h143
1 files changed, 90 insertions, 53 deletions
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index a884ab544335..f19a76d3ca0e 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -31,10 +31,13 @@
#include <asm/apic.h>
#include <asm/pvclock-abi.h>
+#include <asm/debugreg.h>
#include <asm/desc.h>
#include <asm/mtrr.h>
#include <asm/msr-index.h>
+#include <asm/msr.h>
#include <asm/asm.h>
+#include <asm/irq_remapping.h>
#include <asm/kvm_page_track.h>
#include <asm/kvm_vcpu_regs.h>
#include <asm/reboot.h>
@@ -124,7 +127,8 @@
KVM_ARCH_REQ_FLAGS(31, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_HV_TLB_FLUSH \
KVM_ARCH_REQ_FLAGS(32, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
-#define KVM_REQ_UPDATE_PROTECTED_GUEST_STATE KVM_ARCH_REQ(34)
+#define KVM_REQ_UPDATE_PROTECTED_GUEST_STATE \
+ KVM_ARCH_REQ_FLAGS(34, KVM_REQUEST_WAIT)
#define CR0_RESERVED_BITS \
(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
@@ -246,7 +250,6 @@ enum x86_intercept_stage;
#define DR7_BP_EN_MASK 0x000000ff
#define DR7_GE (1 << 9)
#define DR7_GD (1 << 13)
-#define DR7_FIXED_1 0x00000400
#define DR7_VOLATILE 0xffff2bff
#define KVM_GUESTDBG_VALID_MASK \
@@ -294,6 +297,7 @@ enum x86_intercept_stage;
*/
#define KVM_APIC_PV_EOI_PENDING 1
+struct kvm_kernel_irqfd;
struct kvm_kernel_irq_routing_entry;
/*
@@ -410,7 +414,6 @@ struct kvm_rmap_head {
};
struct kvm_pio_request {
- unsigned long linear_rip;
unsigned long count;
int in;
int port;
@@ -607,8 +610,15 @@ struct kvm_pmu {
struct kvm_pmu_ops;
enum {
- KVM_DEBUGREG_BP_ENABLED = 1,
- KVM_DEBUGREG_WONT_EXIT = 2,
+ KVM_DEBUGREG_BP_ENABLED = BIT(0),
+ KVM_DEBUGREG_WONT_EXIT = BIT(1),
+ /*
+ * Guest debug registers (DR0-3, DR6 and DR7) are saved/restored by
+ * hardware on exit from or enter to guest. KVM needn't switch them.
+ * DR0-3, DR6 and DR7 are set to their architectural INIT value on VM
+ * exit, host values need to be restored.
+ */
+ KVM_DEBUGREG_AUTO_SWITCH = BIT(2),
};
struct kvm_mtrr {
@@ -691,8 +701,13 @@ struct kvm_vcpu_hv {
struct kvm_vcpu_hv_tlb_flush_fifo tlb_flush_fifo[HV_NR_TLB_FLUSH_FIFOS];
- /* Preallocated buffer for handling hypercalls passing sparse vCPU set */
+ /*
+ * Preallocated buffers for handling hypercalls that pass sparse vCPU
+ * sets (for high vCPU counts, they're too large to comfortably fit on
+ * the stack).
+ */
u64 sparse_banks[HV_MAX_SPARSE_VCPU_BANKS];
+ DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS);
struct hv_vp_assist_page vp_assist_page;
@@ -755,6 +770,7 @@ enum kvm_only_cpuid_leafs {
CPUID_8000_0022_EAX,
CPUID_7_2_EDX,
CPUID_24_0_EBX,
+ CPUID_8000_0021_ECX,
NR_KVM_CPU_CAPS,
NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS,
@@ -909,6 +925,7 @@ struct kvm_vcpu_arch {
bool emulate_regs_need_sync_to_vcpu;
bool emulate_regs_need_sync_from_vcpu;
int (*complete_userspace_io)(struct kvm_vcpu *vcpu);
+ unsigned long cui_linear_rip;
gpa_t time;
s8 pvclock_tsc_shift;
@@ -1026,6 +1043,7 @@ struct kvm_vcpu_arch {
int pending_ioapic_eoi;
int pending_external_vector;
+ int highest_stale_pending_ioapic_eoi;
/* be preempted when it's in kernel-mode(cpl=0) */
bool preempted_in_kernel;
@@ -1303,6 +1321,12 @@ enum kvm_apicv_inhibit {
*/
APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED,
+ /*
+ * AVIC is disabled because the vCPU's APIC ID is beyond the max
+ * supported by AVIC/x2AVIC, i.e. the vCPU is unaddressable.
+ */
+ APICV_INHIBIT_REASON_PHYSICAL_ID_TOO_BIG,
+
NR_APICV_INHIBIT_REASONS,
};
@@ -1321,7 +1345,8 @@ enum kvm_apicv_inhibit {
__APICV_INHIBIT_REASON(IRQWIN), \
__APICV_INHIBIT_REASON(PIT_REINJ), \
__APICV_INHIBIT_REASON(SEV), \
- __APICV_INHIBIT_REASON(LOGICAL_ID_ALIASED)
+ __APICV_INHIBIT_REASON(LOGICAL_ID_ALIASED), \
+ __APICV_INHIBIT_REASON(PHYSICAL_ID_TOO_BIG)
struct kvm_arch {
unsigned long n_used_mmu_pages;
@@ -1333,7 +1358,7 @@ struct kvm_arch {
bool has_private_mem;
bool has_protected_state;
bool pre_fault_allowed;
- struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
+ struct hlist_head *mmu_page_hash;
struct list_head active_mmu_pages;
/*
* A list of kvm_mmu_page structs that, if zapped, could possibly be
@@ -1362,11 +1387,13 @@ struct kvm_arch {
#define __KVM_HAVE_ARCH_NONCOHERENT_DMA
atomic_t noncoherent_dma_count;
-#define __KVM_HAVE_ARCH_ASSIGNED_DEVICE
- atomic_t assigned_device_count;
+ unsigned long nr_possible_bypass_irqs;
+
+#ifdef CONFIG_KVM_IOAPIC
struct kvm_pic *vpic;
struct kvm_ioapic *vioapic;
struct kvm_pit *vpit;
+#endif
atomic_t vapics_in_nmi_mode;
struct mutex apic_map_lock;
struct kvm_apic_map __rcu *apic_map;
@@ -1381,12 +1408,8 @@ struct kvm_arch {
gpa_t wall_clock;
- bool mwait_in_guest;
- bool hlt_in_guest;
- bool pause_in_guest;
- bool cstate_in_guest;
+ u64 disabled_exits;
- unsigned long irq_sources_bitmap;
s64 kvmclock_offset;
/*
@@ -1415,9 +1438,6 @@ struct kvm_arch {
struct delayed_work kvmclock_update_work;
struct delayed_work kvmclock_sync_work;
- /* reads protected by irq_srcu, writes by irq_lock */
- struct hlist_head mask_notifier_list;
-
#ifdef CONFIG_KVM_HYPERV
struct kvm_hv hyperv;
#endif
@@ -1440,6 +1460,7 @@ struct kvm_arch {
bool x2apic_format;
bool x2apic_broadcast_quirk_disabled;
+ bool has_mapped_host_mmio;
bool guest_can_read_msr_platform_info;
bool exception_payload_enabled;
@@ -1472,8 +1493,13 @@ struct kvm_arch {
struct once nx_once;
#ifdef CONFIG_X86_64
- /* The number of TDP MMU pages across all roots. */
+#ifdef CONFIG_KVM_PROVE_MMU
+ /*
+ * The number of TDP MMU pages across all roots. Used only to sanity
+ * check that KVM isn't leaking TDP MMU pages.
+ */
atomic64_t tdp_mmu_pages;
+#endif
/*
* List of struct kvm_mmu_pages being used as roots.
@@ -1564,6 +1590,13 @@ struct kvm_arch {
struct kvm_mmu_memory_cache split_desc_cache;
gfn_t gfn_direct_bits;
+
+ /*
+ * Size of the CPU's dirty log buffer, i.e. VMX's PML buffer. A Zero
+ * value indicates CPU dirty logging is unsupported or disabled in
+ * current VM.
+ */
+ int cpu_dirty_log_size;
};
struct kvm_vm_stat {
@@ -1651,6 +1684,12 @@ static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical)
return dest_mode_logical ? APIC_DEST_LOGICAL : APIC_DEST_PHYSICAL;
}
+enum kvm_x86_run_flags {
+ KVM_RUN_FORCE_IMMEDIATE_EXIT = BIT(0),
+ KVM_RUN_LOAD_GUEST_DR6 = BIT(1),
+ KVM_RUN_LOAD_DEBUGCTL = BIT(2),
+};
+
struct kvm_x86_ops {
const char *name;
@@ -1667,6 +1706,7 @@ struct kvm_x86_ops {
unsigned int vm_size;
int (*vm_init)(struct kvm *kvm);
void (*vm_destroy)(struct kvm *kvm);
+ void (*vm_pre_destroy)(struct kvm *kvm);
/* Create, but do not attach this VCPU */
int (*vcpu_precreate)(struct kvm *kvm);
@@ -1678,6 +1718,12 @@ struct kvm_x86_ops {
void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
void (*vcpu_put)(struct kvm_vcpu *vcpu);
+ /*
+ * Mask of DEBUGCTL bits that are owned by the host, i.e. that need to
+ * match the host's value even while the guest is active.
+ */
+ const u64 HOST_OWNED_DEBUGCTL;
+
void (*update_exception_bitmap)(struct kvm_vcpu *vcpu);
int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
@@ -1700,7 +1746,6 @@ struct kvm_x86_ops {
void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu);
- void (*set_dr6)(struct kvm_vcpu *vcpu, unsigned long value);
void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value);
void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
@@ -1731,7 +1776,7 @@ struct kvm_x86_ops {
int (*vcpu_pre_run)(struct kvm_vcpu *vcpu);
enum exit_fastpath_completion (*vcpu_run)(struct kvm_vcpu *vcpu,
- bool force_immediate_exit);
+ u64 run_flags);
int (*handle_exit)(struct kvm_vcpu *vcpu,
enum exit_fastpath_completion exit_fastpath);
int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
@@ -1816,11 +1861,6 @@ struct kvm_x86_ops {
struct x86_exception *exception);
void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu);
- /*
- * Size of the CPU's dirty log buffer, i.e. VMX's PML buffer. A zero
- * value indicates CPU dirty logging is unsupported or disabled.
- */
- int cpu_dirty_log_size;
void (*update_cpu_dirty_logging)(struct kvm_vcpu *vcpu);
const struct kvm_x86_nested_ops *nested_ops;
@@ -1828,12 +1868,14 @@ struct kvm_x86_ops {
void (*vcpu_blocking)(struct kvm_vcpu *vcpu);
void (*vcpu_unblocking)(struct kvm_vcpu *vcpu);
- int (*pi_update_irte)(struct kvm *kvm, unsigned int host_irq,
- uint32_t guest_irq, bool set);
- void (*pi_start_assignment)(struct kvm *kvm);
+ int (*pi_update_irte)(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
+ unsigned int host_irq, uint32_t guest_irq,
+ struct kvm_vcpu *vcpu, u32 vector);
+ void (*pi_start_bypass)(struct kvm *kvm);
void (*apicv_pre_state_restore)(struct kvm_vcpu *vcpu);
void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu);
bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu);
+ bool (*protected_apic_has_interrupt)(struct kvm_vcpu *vcpu);
int (*set_hv_timer)(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc,
bool *expired);
@@ -1850,6 +1892,7 @@ struct kvm_x86_ops {
int (*dev_get_attr)(u32 group, u64 attr, u64 *val);
int (*mem_enc_ioctl)(struct kvm *kvm, void __user *argp);
+ int (*vcpu_mem_enc_ioctl)(struct kvm_vcpu *vcpu, void __user *argp);
int (*mem_enc_register_region)(struct kvm *kvm, struct kvm_enc_region *argp);
int (*mem_enc_unregister_region)(struct kvm *kvm, struct kvm_enc_region *argp);
int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd);
@@ -1865,7 +1908,7 @@ struct kvm_x86_ops {
int (*enable_l2_tlb_flush)(struct kvm_vcpu *vcpu);
void (*migrate_timers)(struct kvm_vcpu *vcpu);
- void (*msr_filter_changed)(struct kvm_vcpu *vcpu);
+ void (*recalc_msr_intercepts)(struct kvm_vcpu *vcpu);
int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err);
void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector);
@@ -1923,6 +1966,8 @@ struct kvm_arch_async_pf {
extern u32 __read_mostly kvm_nr_uret_msrs;
extern bool __read_mostly allow_smaller_maxphyaddr;
extern bool __read_mostly enable_apicv;
+extern bool __read_mostly enable_ipiv;
+extern bool __read_mostly enable_device_posted_irqs;
extern struct kvm_x86_ops kvm_x86_ops;
#define kvm_x86_call(func) static_call(kvm_x86_##func)
@@ -1940,7 +1985,7 @@ void kvm_x86_vendor_exit(void);
#define __KVM_HAVE_ARCH_VM_ALLOC
static inline struct kvm *kvm_arch_alloc_vm(void)
{
- return __vmalloc(kvm_x86_ops.vm_size, GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+ return kvzalloc(kvm_x86_ops.vm_size, GFP_KERNEL_ACCOUNT);
}
#define __KVM_HAVE_ARCH_VM_FREE
@@ -1985,7 +2030,7 @@ void kvm_mmu_vendor_module_exit(void);
void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
int kvm_mmu_create(struct kvm_vcpu *vcpu);
-void kvm_mmu_init_vm(struct kvm *kvm);
+int kvm_mmu_init_vm(struct kvm *kvm);
void kvm_mmu_uninit_vm(struct kvm *kvm);
void kvm_mmu_init_memslot_memory_attributes(struct kvm *kvm,
@@ -2016,19 +2061,6 @@ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3);
int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
const void *val, int bytes);
-struct kvm_irq_mask_notifier {
- void (*func)(struct kvm_irq_mask_notifier *kimn, bool masked);
- int irq;
- struct hlist_node link;
-};
-
-void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
- struct kvm_irq_mask_notifier *kimn);
-void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
- struct kvm_irq_mask_notifier *kimn);
-void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
- bool mask);
-
extern bool tdp_enabled;
u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu);
@@ -2187,9 +2219,6 @@ static inline int __kvm_irq_line_state(unsigned long *irq_state,
return !!(*irq_state);
}
-int kvm_pic_set_irq(struct kvm_pic *pic, int irq, int irq_source_id, int level);
-void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id);
-
void kvm_inject_nmi(struct kvm_vcpu *vcpu);
int kvm_get_nr_pending_nmis(struct kvm_vcpu *vcpu);
@@ -2272,7 +2301,7 @@ static inline unsigned long read_msr(unsigned long msr)
{
u64 value;
- rdmsrl(msr, value);
+ rdmsrq(msr, value);
return value;
}
#endif
@@ -2326,6 +2355,7 @@ int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low,
int kvm_add_user_return_msr(u32 msr);
int kvm_find_user_return_msr(u32 msr);
int kvm_set_user_return_msr(unsigned index, u64 val, u64 mask);
+void kvm_user_return_msr_update_cache(unsigned int index, u64 val);
static inline bool kvm_is_supported_user_return_msr(u32 msr)
{
@@ -2365,9 +2395,6 @@ bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu);
bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq,
struct kvm_vcpu **dest_vcpu);
-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 */
@@ -2409,7 +2436,12 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
KVM_X86_QUIRK_FIX_HYPERCALL_INSN | \
KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS | \
KVM_X86_QUIRK_SLOT_ZAP_ALL | \
- KVM_X86_QUIRK_STUFF_FEATURE_MSRS)
+ KVM_X86_QUIRK_STUFF_FEATURE_MSRS | \
+ KVM_X86_QUIRK_IGNORE_GUEST_PAT)
+
+#define KVM_X86_CONDITIONAL_QUIRKS \
+ (KVM_X86_QUIRK_CD_NW_CLEARED | \
+ KVM_X86_QUIRK_IGNORE_GUEST_PAT)
/*
* KVM previously used a u32 field in kvm_run to indicate the hypercall was
@@ -2418,4 +2450,9 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
*/
#define KVM_EXIT_HYPERCALL_MBZ GENMASK_ULL(31, 1)
+static inline bool kvm_arch_has_irq_bypass(void)
+{
+ return enable_device_posted_irqs;
+}
+
#endif /* _ASM_X86_KVM_HOST_H */
generated by cgit (git 2.34.1) at 2025-08-06 01:06:02 +0000