diff options
Diffstat (limited to 'arch/x86/include/asm/kvm_host.h')
| -rw-r--r-- | arch/x86/include/asm/kvm_host.h | 2157 |
1 files changed, 1524 insertions, 633 deletions
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 4660ce90de7f..5a3bfa293e8b 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Kernel-based Virtual Machine driver for Linux * * This header defines architecture specific interfaces, x86 version - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. - * */ #ifndef _ASM_X86_KVM_HOST_H @@ -18,6 +15,7 @@ #include <linux/cpumask.h> #include <linux/irq_work.h> #include <linux/irq.h> +#include <linux/workqueue.h> #include <linux/kvm.h> #include <linux/kvm_para.h> @@ -26,43 +24,81 @@ #include <linux/pvclock_gtod.h> #include <linux/clocksource.h> #include <linux/irqbypass.h> -#include <linux/hyperv.h> +#include <linux/kfifo.h> +#include <linux/sched/vhost_task.h> +#include <linux/call_once.h> +#include <linux/atomic.h> #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/hyperv-tlfs.h> +#include <asm/kvm_vcpu_regs.h> +#include <asm/reboot.h> +#include <hyperv/hvhdk.h> + +#define __KVM_HAVE_ARCH_VCPU_DEBUGFS + +/* + * CONFIG_KVM_MAX_NR_VCPUS is defined iff CONFIG_KVM!=n, provide a dummy max if + * KVM is disabled (arbitrarily use the default from CONFIG_KVM_MAX_NR_VCPUS). + */ +#ifdef CONFIG_KVM_MAX_NR_VCPUS +#define KVM_MAX_VCPUS CONFIG_KVM_MAX_NR_VCPUS +#else +#define KVM_MAX_VCPUS 1024 +#endif + +/* + * In x86, the VCPU ID corresponds to the APIC ID, and APIC IDs + * might be larger than the actual number of VCPUs because the + * APIC ID encodes CPU topology information. + * + * In the worst case, we'll need less than one extra bit for the + * Core ID, and less than one extra bit for the Package (Die) ID, + * so ratio of 4 should be enough. + */ +#define KVM_VCPU_ID_RATIO 4 +#define KVM_MAX_VCPU_IDS (KVM_MAX_VCPUS * KVM_VCPU_ID_RATIO) -#define KVM_MAX_VCPUS 288 -#define KVM_SOFT_MAX_VCPUS 240 -#define KVM_MAX_VCPU_ID 1023 -#define KVM_USER_MEM_SLOTS 509 /* memory slots that are not exposed to userspace */ -#define KVM_PRIVATE_MEM_SLOTS 3 -#define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS) +#define KVM_INTERNAL_MEM_SLOTS 3 #define KVM_HALT_POLL_NS_DEFAULT 200000 #define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS +#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ + KVM_DIRTY_LOG_INITIALLY_SET) + +#define KVM_BUS_LOCK_DETECTION_VALID_MODE (KVM_BUS_LOCK_DETECTION_OFF | \ + KVM_BUS_LOCK_DETECTION_EXIT) + +#define KVM_X86_NOTIFY_VMEXIT_VALID_BITS (KVM_X86_NOTIFY_VMEXIT_ENABLED | \ + KVM_X86_NOTIFY_VMEXIT_USER) + /* x86-specific vcpu->requests bit members */ #define KVM_REQ_MIGRATE_TIMER KVM_ARCH_REQ(0) #define KVM_REQ_REPORT_TPR_ACCESS KVM_ARCH_REQ(1) #define KVM_REQ_TRIPLE_FAULT KVM_ARCH_REQ(2) #define KVM_REQ_MMU_SYNC KVM_ARCH_REQ(3) #define KVM_REQ_CLOCK_UPDATE KVM_ARCH_REQ(4) -#define KVM_REQ_LOAD_CR3 KVM_ARCH_REQ(5) +#define KVM_REQ_LOAD_MMU_PGD KVM_ARCH_REQ(5) #define KVM_REQ_EVENT KVM_ARCH_REQ(6) #define KVM_REQ_APF_HALT KVM_ARCH_REQ(7) #define KVM_REQ_STEAL_UPDATE KVM_ARCH_REQ(8) #define KVM_REQ_NMI KVM_ARCH_REQ(9) #define KVM_REQ_PMU KVM_ARCH_REQ(10) #define KVM_REQ_PMI KVM_ARCH_REQ(11) +#ifdef CONFIG_KVM_SMM #define KVM_REQ_SMI KVM_ARCH_REQ(12) +#endif #define KVM_REQ_MASTERCLOCK_UPDATE KVM_ARCH_REQ(13) #define KVM_REQ_MCLOCK_INPROGRESS \ KVM_ARCH_REQ_FLAGS(14, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) @@ -77,7 +113,22 @@ #define KVM_REQ_HV_EXIT KVM_ARCH_REQ(21) #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_GET_NESTED_STATE_PAGES KVM_ARCH_REQ(24) +#define KVM_REQ_APICV_UPDATE \ + KVM_ARCH_REQ_FLAGS(25, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_TLB_FLUSH_CURRENT KVM_ARCH_REQ(26) +#define KVM_REQ_TLB_FLUSH_GUEST \ + KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_APF_READY KVM_ARCH_REQ(28) +#define KVM_REQ_RECALC_INTERCEPTS KVM_ARCH_REQ(29) +#define KVM_REQ_UPDATE_CPU_DIRTY_LOGGING \ + KVM_ARCH_REQ_FLAGS(30, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_MMU_FREE_OBSOLETE_ROOTS \ + 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_FLAGS(34, KVM_REQUEST_WAIT) #define CR0_RESERVED_BITS \ (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ @@ -90,7 +141,8 @@ | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \ | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \ | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_VMXE \ - | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP)) + | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP \ + | X86_CR4_LAM_SUP | X86_CR4_CET)) #define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR) @@ -99,71 +151,56 @@ #define INVALID_PAGE (~(hpa_t)0) #define VALID_PAGE(x) ((x) != INVALID_PAGE) -#define UNMAPPED_GVA (~(gpa_t)0) - /* KVM Hugepage definitions for x86 */ -enum { - PT_PAGE_TABLE_LEVEL = 1, - PT_DIRECTORY_LEVEL = 2, - PT_PDPE_LEVEL = 3, - /* set max level to the biggest one */ - PT_MAX_HUGEPAGE_LEVEL = PT_PDPE_LEVEL, -}; -#define KVM_NR_PAGE_SIZES (PT_MAX_HUGEPAGE_LEVEL - \ - PT_PAGE_TABLE_LEVEL + 1) +#define KVM_MAX_HUGEPAGE_LEVEL PG_LEVEL_1G +#define KVM_NR_PAGE_SIZES (KVM_MAX_HUGEPAGE_LEVEL - PG_LEVEL_4K + 1) #define KVM_HPAGE_GFN_SHIFT(x) (((x) - 1) * 9) #define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + KVM_HPAGE_GFN_SHIFT(x)) #define KVM_HPAGE_SIZE(x) (1UL << KVM_HPAGE_SHIFT(x)) #define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1)) #define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE) -static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) -{ - /* KVM_HPAGE_GFN_SHIFT(PT_PAGE_TABLE_LEVEL) must be 0. */ - return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) - - (base_gfn >> KVM_HPAGE_GFN_SHIFT(level)); -} - -#define KVM_PERMILLE_MMU_PAGES 20 -#define KVM_MIN_ALLOC_MMU_PAGES 64 +#define KVM_MEMSLOT_PAGES_TO_MMU_PAGES_RATIO 50 +#define KVM_MIN_ALLOC_MMU_PAGES 64UL #define KVM_MMU_HASH_SHIFT 12 #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT) #define KVM_MIN_FREE_MMU_PAGES 5 #define KVM_REFILL_PAGES 25 -#define KVM_MAX_CPUID_ENTRIES 80 -#define KVM_NR_FIXED_MTRR_REGION 88 +#define KVM_MAX_CPUID_ENTRIES 256 #define KVM_NR_VAR_MTRR 8 #define ASYNC_PF_PER_VCPU 64 enum kvm_reg { - VCPU_REGS_RAX = 0, - VCPU_REGS_RCX = 1, - VCPU_REGS_RDX = 2, - VCPU_REGS_RBX = 3, - VCPU_REGS_RSP = 4, - VCPU_REGS_RBP = 5, - VCPU_REGS_RSI = 6, - VCPU_REGS_RDI = 7, + VCPU_REGS_RAX = __VCPU_REGS_RAX, + VCPU_REGS_RCX = __VCPU_REGS_RCX, + VCPU_REGS_RDX = __VCPU_REGS_RDX, + VCPU_REGS_RBX = __VCPU_REGS_RBX, + VCPU_REGS_RSP = __VCPU_REGS_RSP, + VCPU_REGS_RBP = __VCPU_REGS_RBP, + VCPU_REGS_RSI = __VCPU_REGS_RSI, + VCPU_REGS_RDI = __VCPU_REGS_RDI, #ifdef CONFIG_X86_64 - VCPU_REGS_R8 = 8, - VCPU_REGS_R9 = 9, - VCPU_REGS_R10 = 10, - VCPU_REGS_R11 = 11, - VCPU_REGS_R12 = 12, - VCPU_REGS_R13 = 13, - VCPU_REGS_R14 = 14, - VCPU_REGS_R15 = 15, + VCPU_REGS_R8 = __VCPU_REGS_R8, + VCPU_REGS_R9 = __VCPU_REGS_R9, + VCPU_REGS_R10 = __VCPU_REGS_R10, + VCPU_REGS_R11 = __VCPU_REGS_R11, + VCPU_REGS_R12 = __VCPU_REGS_R12, + VCPU_REGS_R13 = __VCPU_REGS_R13, + VCPU_REGS_R14 = __VCPU_REGS_R14, + 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_CR0, VCPU_EXREG_CR3, + VCPU_EXREG_CR4, VCPU_EXREG_RFLAGS, VCPU_EXREG_SEGMENTS, + VCPU_EXREG_EXIT_INFO_1, + VCPU_EXREG_EXIT_INFO_2, }; enum { @@ -177,54 +214,79 @@ enum { VCPU_SREG_LDTR, }; -#include <asm/kvm_emulate.h> +enum exit_fastpath_completion { + EXIT_FASTPATH_NONE, + EXIT_FASTPATH_REENTER_GUEST, + EXIT_FASTPATH_EXIT_HANDLED, + EXIT_FASTPATH_EXIT_USERSPACE, +}; +typedef enum exit_fastpath_completion fastpath_t; -#define KVM_NR_MEM_OBJS 40 +struct x86_emulate_ctxt; +struct x86_exception; +union kvm_smram; +enum x86_intercept; +enum x86_intercept_stage; #define KVM_NR_DB_REGS 4 +#define DR6_BUS_LOCK (1 << 11) #define DR6_BD (1 << 13) #define DR6_BS (1 << 14) #define DR6_BT (1 << 15) #define DR6_RTM (1 << 16) -#define DR6_FIXED_1 0xfffe0ff0 -#define DR6_INIT 0xffff0ff0 -#define DR6_VOLATILE 0x0001e00f +/* + * DR6_ACTIVE_LOW combines fixed-1 and active-low bits. + * We can regard all the bits in DR6_FIXED_1 as active_low bits; + * they will never be 0 for now, but when they are defined + * in the future it will require no code change. + * + * DR6_ACTIVE_LOW is also used as the init/reset value for DR6. + */ +#define DR6_ACTIVE_LOW 0xffff0ff0 +#define DR6_VOLATILE 0x0001e80f +#define DR6_FIXED_1 (DR6_ACTIVE_LOW & ~DR6_VOLATILE) #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 PFERR_PRESENT_BIT 0 -#define PFERR_WRITE_BIT 1 -#define PFERR_USER_BIT 2 -#define PFERR_RSVD_BIT 3 -#define PFERR_FETCH_BIT 4 -#define PFERR_PK_BIT 5 -#define PFERR_GUEST_FINAL_BIT 32 -#define PFERR_GUEST_PAGE_BIT 33 - -#define PFERR_PRESENT_MASK (1U << PFERR_PRESENT_BIT) -#define PFERR_WRITE_MASK (1U << PFERR_WRITE_BIT) -#define PFERR_USER_MASK (1U << PFERR_USER_BIT) -#define PFERR_RSVD_MASK (1U << PFERR_RSVD_BIT) -#define PFERR_FETCH_MASK (1U << PFERR_FETCH_BIT) -#define PFERR_PK_MASK (1U << PFERR_PK_BIT) -#define PFERR_GUEST_FINAL_MASK (1ULL << PFERR_GUEST_FINAL_BIT) -#define PFERR_GUEST_PAGE_MASK (1ULL << PFERR_GUEST_PAGE_BIT) - -#define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK | \ - PFERR_WRITE_MASK | \ - PFERR_PRESENT_MASK) +#define KVM_GUESTDBG_VALID_MASK \ + (KVM_GUESTDBG_ENABLE | \ + KVM_GUESTDBG_SINGLESTEP | \ + KVM_GUESTDBG_USE_HW_BP | \ + KVM_GUESTDBG_USE_SW_BP | \ + KVM_GUESTDBG_INJECT_BP | \ + KVM_GUESTDBG_INJECT_DB | \ + KVM_GUESTDBG_BLOCKIRQ) + +#define PFERR_PRESENT_MASK BIT(0) +#define PFERR_WRITE_MASK BIT(1) +#define PFERR_USER_MASK BIT(2) +#define PFERR_RSVD_MASK BIT(3) +#define PFERR_FETCH_MASK BIT(4) +#define PFERR_PK_MASK BIT(5) +#define PFERR_SS_MASK BIT(6) +#define PFERR_SGX_MASK BIT(15) +#define PFERR_GUEST_RMP_MASK BIT_ULL(31) +#define PFERR_GUEST_FINAL_MASK BIT_ULL(32) +#define PFERR_GUEST_PAGE_MASK BIT_ULL(33) +#define PFERR_GUEST_ENC_MASK BIT_ULL(34) +#define PFERR_GUEST_SIZEM_MASK BIT_ULL(35) +#define PFERR_GUEST_VMPL_MASK BIT_ULL(36) /* - * 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. + * IMPLICIT_ACCESS is a KVM-defined flag used to correctly perform SMAP checks + * when emulating instructions that triggers implicit access. */ -#define SPTE_SPECIAL_MASK (1ULL << 62) +#define PFERR_IMPLICIT_ACCESS BIT_ULL(48) +/* + * PRIVATE_ACCESS is a KVM-defined flag us to indicate that a fault occurred + * when the guest was accessing private memory. + */ +#define PFERR_PRIVATE_ACCESS BIT_ULL(49) +#define PFERR_SYNTHETIC_MASK (PFERR_IMPLICIT_ACCESS | PFERR_PRIVATE_ACCESS) /* apic attention bits */ #define KVM_APIC_CHECK_VAPIC 0 @@ -236,41 +298,66 @@ enum { */ #define KVM_APIC_PV_EOI_PENDING 1 +struct kvm_kernel_irqfd; struct kvm_kernel_irq_routing_entry; /* - * We don't want allocation failures within the mmu code, so we preallocate - * enough memory for a single page fault in a cache. - */ -struct kvm_mmu_memory_cache { - int nobjs; - void *objects[KVM_NR_MEM_OBJS]; -}; - -/* - * the pages used as guest page table on soft mmu are tracked by - * kvm_memory_slot.arch.gfn_track which is 16 bits, so the role bits used - * by indirect shadow page can not be more than 15 bits. + * kvm_mmu_page_role tracks the properties of a shadow page (where shadow page + * also includes TDP pages) to determine whether or not a page can be used in + * the given MMU context. This is a subset of the overall kvm_cpu_role to + * minimize the size of kvm_memory_slot.arch.gfn_write_track, i.e. allows + * allocating 2 bytes per gfn instead of 4 bytes per gfn. + * + * Upper-level shadow pages having gptes are tracked for write-protection via + * gfn_write_track. As above, gfn_write_track is a 16 bit counter, so KVM must + * not create more than 2^16-1 upper-level shadow pages at a single gfn, + * otherwise gfn_write_track will overflow and explosions will ensue. * - * Currently, we used 14 bits that are @level, @cr4_pae, @quadrant, @access, - * @nxe, @cr0_wp, @smep_andnot_wp and @smap_andnot_wp. + * A unique shadow page (SP) for a gfn is created if and only if an existing SP + * cannot be reused. The ability to reuse a SP is tracked by its role, which + * incorporates various mode bits and properties of the SP. Roughly speaking, + * the number of unique SPs that can theoretically be created is 2^n, where n + * is the number of bits that are used to compute the role. + * + * But, even though there are 20 bits in the mask below, not all combinations + * of modes and flags are possible: + * + * - invalid shadow pages are not accounted, mirror pages are not shadowed, + * so the bits are effectively 18. + * + * - quadrant will only be used if has_4_byte_gpte=1 (non-PAE paging); + * execonly and ad_disabled are only used for nested EPT which has + * has_4_byte_gpte=0. Therefore, 2 bits are always unused. + * + * - the 4 bits of level are effectively limited to the values 2/3/4/5, + * as 4k SPs are not tracked (allowed to go unsync). In addition non-PAE + * paging has exactly one upper level, making level completely redundant + * when has_4_byte_gpte=1. + * + * - on top of this, smep_andnot_wp and smap_andnot_wp are only set if + * cr0_wp=0, therefore these three bits only give rise to 5 possibilities. + * + * Therefore, the maximum number of possible upper-level shadow pages for a + * single gfn is a bit less than 2^13. */ union kvm_mmu_page_role { u32 word; struct { unsigned level:4; - unsigned cr4_pae:1; + unsigned has_4_byte_gpte:1; unsigned quadrant:2; unsigned direct:1; unsigned access:3; unsigned invalid:1; - unsigned nxe:1; + unsigned efer_nx:1; unsigned cr0_wp:1; unsigned smep_andnot_wp:1; unsigned smap_andnot_wp:1; unsigned ad_disabled:1; unsigned guest_mode:1; - unsigned :6; + unsigned passthrough:1; + unsigned is_mirror:1; + unsigned :4; /* * This is left at the top of the word so that @@ -282,27 +369,40 @@ union kvm_mmu_page_role { }; }; -union kvm_mmu_extended_role { /* - * This structure complements kvm_mmu_page_role caching everything needed for - * MMU configuration. If nothing in both these structures changed, MMU - * re-configuration can be skipped. @valid bit is set on first usage so we don't - * treat all-zero structure as valid data. + * kvm_mmu_extended_role complements kvm_mmu_page_role, tracking properties + * relevant to the current MMU configuration. When loading CR0, CR4, or EFER, + * including on nested transitions, if nothing in the full role changes then + * MMU re-configuration can be skipped. @valid bit is set on first usage so we + * don't treat all-zero structure as valid data. + * + * The properties that are tracked in the extended role but not the page role + * are for things that either (a) do not affect the validity of the shadow page + * or (b) are indirectly reflected in the shadow page's role. For example, + * CR4.PKE only affects permission checks for software walks of the guest page + * tables (because KVM doesn't support Protection Keys with shadow paging), and + * CR0.PG, CR4.PAE, and CR4.PSE are indirectly reflected in role.level. + * + * Note, SMEP and SMAP are not redundant with sm*p_andnot_wp in the page role. + * If CR0.WP=1, KVM can reuse shadow pages for the guest regardless of SMEP and + * SMAP, but the MMU's permission checks for software walks need to be SMEP and + * SMAP aware regardless of CR0.WP. */ +union kvm_mmu_extended_role { u32 word; struct { unsigned int valid:1; unsigned int execonly:1; - unsigned int cr0_pg:1; unsigned int cr4_pse:1; unsigned int cr4_pke:1; unsigned int cr4_smap:1; unsigned int cr4_smep:1; unsigned int cr4_la57:1; + unsigned int efer_lma:1; }; }; -union kvm_mmu_role { +union kvm_cpu_role { u64 as_u64; struct { union kvm_mmu_page_role base; @@ -311,43 +411,7 @@ union kvm_mmu_role { }; struct kvm_rmap_head { - unsigned long val; -}; - -struct kvm_mmu_page { - struct list_head link; - struct hlist_node hash_link; - bool unsync; - - /* - * The following two entries are used to key the shadow page in the - * hash table. - */ - union kvm_mmu_page_role role; - gfn_t gfn; - - u64 *spt; - /* hold the gfn of each spte inside spt */ - gfn_t *gfns; - int root_count; /* Currently serving as active root */ - unsigned int unsync_children; - struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */ - - /* The page is obsolete if mmu_valid_gen != kvm->arch.mmu_valid_gen. */ - unsigned long mmu_valid_gen; - - DECLARE_BITMAP(unsync_child_bitmap, 512); - -#ifdef CONFIG_X86_32 - /* - * Used out of the mmu-lock to avoid reading spte values while an - * update is in progress; see the comments in __get_spte_lockless(). - */ - int clear_spte_count; -#endif - - /* Number of writes since the last time traversal visited this page. */ - atomic_t write_flooding_count; + atomic_long_t val; }; struct kvm_pio_request { @@ -365,51 +429,44 @@ struct rsvd_bits_validate { }; struct kvm_mmu_root_info { - gpa_t cr3; + gpa_t pgd; hpa_t hpa; }; #define KVM_MMU_ROOT_INFO_INVALID \ - ((struct kvm_mmu_root_info) { .cr3 = INVALID_PAGE, .hpa = INVALID_PAGE }) + ((struct kvm_mmu_root_info) { .pgd = INVALID_PAGE, .hpa = INVALID_PAGE }) #define KVM_MMU_NUM_PREV_ROOTS 3 +#define KVM_MMU_ROOT_CURRENT BIT(0) +#define KVM_MMU_ROOT_PREVIOUS(i) BIT(1+i) +#define KVM_MMU_ROOTS_ALL (BIT(1 + KVM_MMU_NUM_PREV_ROOTS) - 1) + +#define KVM_HAVE_MMU_RWLOCK + +struct kvm_mmu_page; +struct kvm_page_fault; + /* * x86 supports 4 paging modes (5-level 64-bit, 4-level 64-bit, 3-level 32-bit, * and 2-level 32-bit). The kvm_mmu structure abstracts the details of the * current mmu mode. */ struct kvm_mmu { - void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root); - unsigned long (*get_cr3)(struct kvm_vcpu *vcpu); + unsigned long (*get_guest_pgd)(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, - bool prefault); + int (*page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); 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, + gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + gpa_t gva_or_gpa, u64 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, - struct kvm_mmu_page *sp); - void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa); - void (*update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - u64 *spte, const void *pte); - hpa_t root_hpa; - union kvm_mmu_role mmu_role; - u8 root_level; - u8 shadow_root_level; - u8 ept_ad; - bool direct_map; - struct kvm_mmu_root_info prev_roots[KVM_MMU_NUM_PREV_ROOTS]; - - /* - * Bitmap; bit set = permission fault - * Byte index: page fault error code [4:1] - * Bit index: pte permissions in ACC_* format - */ - u8 permissions[16]; + int (*sync_spte)(struct kvm_vcpu *vcpu, + struct kvm_mmu_page *sp, int i); + struct kvm_mmu_root_info root; + hpa_t mirror_root_hpa; + union kvm_cpu_role cpu_role; + union kvm_mmu_page_role root_role; /* * The pkru_mask indicates if protection key checks are needed. It @@ -419,8 +476,18 @@ struct kvm_mmu { */ u32 pkru_mask; + struct kvm_mmu_root_info prev_roots[KVM_MMU_NUM_PREV_ROOTS]; + + /* + * Bitmap; bit set = permission fault + * Byte index: page fault error code [4:1] + * Bit index: pte permissions in ACC_* format + */ + u8 permissions[16]; + u64 *pae_root; - u64 *lm_root; + u64 *pml4_root; + u64 *pml5_root; /* * check zero bits on shadow page table entries, these @@ -431,19 +498,9 @@ struct kvm_mmu { struct rsvd_bits_validate guest_rsvd_check; - /* Can have large pages at levels 2..last_nonleaf_level-1. */ - u8 last_nonleaf_level; - - bool nx; - u64 pdptrs[4]; /* pae */ }; -struct kvm_tlb_range { - u64 start_gfn; - u64 pages; -}; - enum pmc_type { KVM_PMC_GP = 0, KVM_PMC_FIXED, @@ -452,50 +509,128 @@ enum pmc_type { struct kvm_pmc { enum pmc_type type; u8 idx; + bool is_paused; + bool intr; + /* + * Base value of the PMC counter, relative to the *consumed* count in + * the associated perf_event. This value includes counter updates from + * the perf_event and emulated_count since the last time the counter + * was reprogrammed, but it is *not* the current value as seen by the + * guest or userspace. + * + * The count is relative to the associated perf_event so that KVM + * doesn't need to reprogram the perf_event every time the guest writes + * to the counter. + */ u64 counter; + /* + * PMC events triggered by KVM emulation that haven't been fully + * processed, i.e. haven't undergone overflow detection. + */ + u64 emulated_counter; u64 eventsel; struct perf_event *perf_event; struct kvm_vcpu *vcpu; + /* + * only for creating or reusing perf_event, + * eventsel value for general purpose counters, + * ctrl value for fixed counters. + */ + u64 current_config; }; +/* More counters may conflict with other existing Architectural MSRs */ +#define KVM_MAX(a, b) ((a) >= (b) ? (a) : (b)) +#define KVM_MAX_NR_INTEL_GP_COUNTERS 8 +#define KVM_MAX_NR_AMD_GP_COUNTERS 6 +#define KVM_MAX_NR_GP_COUNTERS KVM_MAX(KVM_MAX_NR_INTEL_GP_COUNTERS, \ + KVM_MAX_NR_AMD_GP_COUNTERS) + +#define KVM_MAX_NR_INTEL_FIXED_COUNTERS 3 +#define KVM_MAX_NR_AMD_FIXED_COUNTERS 0 +#define KVM_MAX_NR_FIXED_COUNTERS KVM_MAX(KVM_MAX_NR_INTEL_FIXED_COUNTERS, \ + KVM_MAX_NR_AMD_FIXED_COUNTERS) + struct kvm_pmu { + u8 version; unsigned nr_arch_gp_counters; unsigned nr_arch_fixed_counters; unsigned available_event_types; u64 fixed_ctr_ctrl; + u64 fixed_ctr_ctrl_rsvd; u64 global_ctrl; u64 global_status; - u64 global_ovf_ctrl; u64 counter_bitmask[2]; - u64 global_ctrl_mask; + u64 global_ctrl_rsvd; + u64 global_status_rsvd; u64 reserved_bits; - u8 version; - 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; + u64 raw_event_mask; + struct kvm_pmc gp_counters[KVM_MAX_NR_GP_COUNTERS]; + struct kvm_pmc fixed_counters[KVM_MAX_NR_FIXED_COUNTERS]; + + /* + * Overlay the bitmap with a 64-bit atomic so that all bits can be + * set in a single access, e.g. to reprogram all counters when the PMU + * filter changes. + */ + union { + DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX); + atomic64_t __reprogram_pmi; + }; + DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX); + DECLARE_BITMAP(pmc_in_use, X86_PMC_IDX_MAX); + + DECLARE_BITMAP(pmc_counting_instructions, X86_PMC_IDX_MAX); + DECLARE_BITMAP(pmc_counting_branches, X86_PMC_IDX_MAX); + + u64 ds_area; + u64 pebs_enable; + u64 pebs_enable_rsvd; + u64 pebs_data_cfg; + u64 pebs_data_cfg_rsvd; + + /* + * If a guest counter is cross-mapped to host counter with different + * index, its PEBS capability will be temporarily disabled. + * + * The user should make sure that this mask is updated + * after disabling interrupts and before perf_guest_get_msrs(); + */ + u64 host_cross_mapped_mask; + + /* + * 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; enum { - KVM_DEBUGREG_BP_ENABLED = 1, - KVM_DEBUGREG_WONT_EXIT = 2, - KVM_DEBUGREG_RELOAD = 4, -}; - -struct kvm_mtrr_range { - u64 base; - u64 mask; - struct list_head node; + 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 { - struct kvm_mtrr_range var_ranges[KVM_NR_VAR_MTRR]; - mtrr_type fixed_ranges[KVM_NR_FIXED_MTRR_REGION]; + u64 var[KVM_NR_VAR_MTRR * 2]; + u64 fixed_64k; + u64 fixed_16k[2]; + u64 fixed_4k[8]; u64 deftype; - - struct list_head head; }; /* Hyper-V SynIC timer */ @@ -523,8 +658,32 @@ struct kvm_vcpu_hv_synic { bool dont_zero_synic_pages; }; +/* The maximum number of entries on the TLB flush fifo. */ +#define KVM_HV_TLB_FLUSH_FIFO_SIZE (16) +/* + * Note: the following 'magic' entry is made up by KVM to avoid putting + * anything besides GVA on the TLB flush fifo. It is theoretically possible + * to observe a request to flush 4095 PFNs starting from 0xfffffffffffff000 + * which will look identical. KVM's action to 'flush everything' instead of + * flushing these particular addresses is, however, fully legitimate as + * flushing more than requested is always OK. + */ +#define KVM_HV_TLB_FLUSHALL_ENTRY ((u64)-1) + +enum hv_tlb_flush_fifos { + HV_L1_TLB_FLUSH_FIFO, + HV_L2_TLB_FLUSH_FIFO, + HV_NR_TLB_FLUSH_FIFOS, +}; + +struct kvm_vcpu_hv_tlb_flush_fifo { + spinlock_t write_lock; + DECLARE_KFIFO(entries, u64, KVM_HV_TLB_FLUSH_FIFO_SIZE); +}; + /* Hyper-V per vcpu emulation context */ struct kvm_vcpu_hv { + struct kvm_vcpu *vcpu; u32 vp_index; u64 hv_vapic; s64 runtime_offset; @@ -532,7 +691,94 @@ struct kvm_vcpu_hv { struct kvm_hyperv_exit exit; struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT]; DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT); - cpumask_t tlb_flush; + bool enforce_cpuid; + struct { + u32 features_eax; /* HYPERV_CPUID_FEATURES.EAX */ + u32 features_ebx; /* HYPERV_CPUID_FEATURES.EBX */ + u32 features_edx; /* HYPERV_CPUID_FEATURES.EDX */ + u32 enlightenments_eax; /* HYPERV_CPUID_ENLIGHTMENT_INFO.EAX */ + u32 enlightenments_ebx; /* HYPERV_CPUID_ENLIGHTMENT_INFO.EBX */ + u32 syndbg_cap_eax; /* HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES.EAX */ + u32 nested_eax; /* HYPERV_CPUID_NESTED_FEATURES.EAX */ + u32 nested_ebx; /* HYPERV_CPUID_NESTED_FEATURES.EBX */ + } cpuid_cache; + + struct kvm_vcpu_hv_tlb_flush_fifo tlb_flush_fifo[HV_NR_TLB_FLUSH_FIFOS]; + + /* + * 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; + + struct { + u64 pa_page_gpa; + u64 vm_id; + u32 vp_id; + } nested; +}; + +struct kvm_hypervisor_cpuid { + u32 base; + u32 limit; +}; + +#ifdef CONFIG_KVM_XEN +/* Xen HVM per vcpu emulation context */ +struct kvm_vcpu_xen { + u64 hypercall_rip; + u32 current_runstate; + u8 upcall_vector; + struct gfn_to_pfn_cache vcpu_info_cache; + struct gfn_to_pfn_cache vcpu_time_info_cache; + struct gfn_to_pfn_cache runstate_cache; + struct gfn_to_pfn_cache runstate2_cache; + u64 last_steal; + u64 runstate_entry_time; + u64 runstate_times[4]; + unsigned long evtchn_pending_sel; + u32 vcpu_id; /* The Xen / ACPI vCPU ID */ + u32 timer_virq; + u64 timer_expires; /* In guest epoch */ + atomic_t timer_pending; + struct hrtimer timer; + int poll_evtchn; + struct timer_list poll_timer; + struct kvm_hypervisor_cpuid cpuid; +}; +#endif + +struct kvm_queued_exception { + bool pending; + bool injected; + bool has_error_code; + u8 vector; + u32 error_code; + unsigned long payload; + bool has_payload; +}; + +/* + * Hardware-defined CPUID leafs that are either scattered by the kernel or are + * unknown to the kernel, but need to be directly used by KVM. Note, these + * word values conflict with the kernel's "bug" caps, but KVM doesn't use those. + */ +enum kvm_only_cpuid_leafs { + CPUID_12_EAX = NCAPINTS, + CPUID_7_1_EDX, + CPUID_8000_0007_EDX, + CPUID_8000_0022_EAX, + CPUID_7_2_EDX, + CPUID_24_0_EBX, + CPUID_8000_0021_ECX, + CPUID_7_1_ECX, + NR_KVM_CPU_CAPS, + + NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, }; struct kvm_vcpu_arch { @@ -550,13 +796,15 @@ struct kvm_vcpu_arch { unsigned long cr3; unsigned long cr4; unsigned long cr4_guest_owned_bits; + unsigned long cr4_guest_rsvd_bits; unsigned long cr8; + u32 host_pkru; u32 pkru; u32 hflags; u64 efer; + u64 host_debugctl; u64 apic_base; struct kvm_lapic *apic; /* kernel irqchip context */ - bool apicv_active; bool load_eoi_exitmap_pending; DECLARE_BITMAP(ioapic_handled_vectors, 256); unsigned long apic_attention; @@ -565,9 +813,12 @@ struct kvm_vcpu_arch { u64 ia32_misc_enable_msr; u64 smbase; u64 smi_count; + bool at_instruction_boundary; bool tpr_access_reporting; - u64 ia32_xss; + bool xfd_no_write_intercept; u64 microcode_version; + u64 arch_capabilities; + u64 perf_capabilities; /* * Paging state of the vcpu @@ -588,7 +839,7 @@ 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. */ @@ -601,41 +852,46 @@ struct kvm_vcpu_arch { struct kvm_mmu *walk_mmu; struct kvm_mmu_memory_cache mmu_pte_list_desc_cache; - struct kvm_mmu_memory_cache mmu_page_cache; + struct kvm_mmu_memory_cache mmu_shadow_page_cache; + struct kvm_mmu_memory_cache mmu_shadowed_info_cache; struct kvm_mmu_memory_cache mmu_page_header_cache; + /* + * This cache is to allocate external page table. E.g. private EPT used + * by the TDX module. + */ + struct kvm_mmu_memory_cache mmu_external_spt_cache; /* * QEMU userspace and the guest each have their own FPU state. - * In vcpu_run, we switch between the user, maintained in the - * task_struct struct, and guest FPU contexts. While running a VCPU, - * the VCPU thread will have the guest FPU context. + * In vcpu_run, we switch between the user and guest FPU contexts. + * While running a VCPU, the VCPU thread will have the guest FPU + * context. * * Note that while the PKRU state lives inside the fpu registers, * it is switched out separately at VMENTER and VMEXIT time. The - * "guest_fpu" state here contains the guest FPU context, with the + * "guest_fpstate" state here contains the guest FPU context, with the * host PRKU bits. */ - struct fpu *guest_fpu; + struct fpu_guest guest_fpu; u64 xcr0; u64 guest_supported_xcr0; - u32 guest_xstate_size; + u64 ia32_xss; + u64 guest_supported_xss; struct kvm_pio_request pio; void *pio_data; + void *sev_pio_data; + unsigned sev_pio_count; u8 event_exit_inst_len; - struct kvm_queued_exception { - bool pending; - bool injected; - bool has_error_code; - u8 nr; - u32 error_code; - unsigned long payload; - bool has_payload; - u8 nested_apf; - } exception; + bool exception_from_userspace; + + /* Exceptions to be injected to the guest. */ + struct kvm_queued_exception exception; + /* Exception VM-Exits to be synthesized to L1. */ + struct kvm_queued_exception exception_vmexit; struct kvm_queued_interrupt { bool injected; @@ -646,33 +902,55 @@ struct kvm_vcpu_arch { int halt_request; /* real mode on Intel only */ int cpuid_nent; - struct kvm_cpuid_entry2 cpuid_entries[KVM_MAX_CPUID_ENTRIES]; + struct kvm_cpuid_entry2 *cpuid_entries; + bool cpuid_dynamic_bits_dirty; + bool is_amd_compatible; + /* + * cpu_caps holds the effective guest capabilities, i.e. the features + * the vCPU is allowed to use. Typically, but not always, features can + * be used by the guest if and only if both KVM and userspace want to + * expose the feature to the guest. + * + * A common exception is for virtualization holes, i.e. when KVM can't + * prevent the guest from using a feature, in which case the vCPU "has" + * the feature regardless of what KVM or userspace desires. + * + * Note, features that don't require KVM involvement in any way are + * NOT enforced/sanitized by KVM, i.e. are taken verbatim from the + * guest CPUID provided by userspace. + */ + u32 cpu_caps[NR_KVM_CPU_CAPS]; + + u64 reserved_gpa_bits; int maxphyaddr; /* emulate context */ - struct x86_emulate_ctxt emulate_ctxt; + struct x86_emulate_ctxt *emulate_ctxt; 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; + int cui_rdmsr_imm_reg; gpa_t time; - struct pvclock_vcpu_time_info hv_clock; + s8 pvclock_tsc_shift; + u32 pvclock_tsc_mul; unsigned int hw_tsc_khz; - struct gfn_to_hva_cache pv_time; - bool pv_time_enabled; + struct gfn_to_pfn_cache pv_time; /* set guest stopped flag in pvclock flags field */ 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_hva_cache cache; } st; - u64 tsc_offset; + u64 l1_tsc_offset; + u64 tsc_offset; /* current tsc offset */ u64 last_guest_tsc; u64 last_host_tsc; u64 tsc_offset_adjustment; @@ -685,12 +963,16 @@ struct kvm_vcpu_arch { u32 virtual_tsc_mult; u32 virtual_tsc_khz; s64 ia32_tsc_adjust_msr; - u64 tsc_scaling_ratio; + u64 msr_ia32_power_ctl; + u64 l1_tsc_scaling_ratio; + u64 tsc_scaling_ratio; /* current scaling ratio */ atomic_t nmi_queued; /* unprocessed asynchronous NMIs */ - unsigned nmi_pending; /* NMI queued after currently running handler */ + /* Number of NMIs pending injection, not including hardware vNMIs. */ + unsigned int nmi_pending; bool nmi_injected; /* Trying to inject an NMI this entry */ bool smi_pending; /* SMI queued after currently running handler */ + u8 handling_intr_from_guest; struct kvm_mtrr mtrr_state; u64 pat; @@ -709,10 +991,11 @@ struct kvm_vcpu_arch { u64 mcg_ctl; u64 mcg_ext_ctl; u64 *mce_banks; + u64 *mci_ctl2_banks; /* Cache MMIO info */ u64 mmio_gva; - unsigned access; + unsigned mmio_access; gfn_t mmio_gfn; u64 mmio_gen; @@ -721,8 +1004,13 @@ struct kvm_vcpu_arch { /* used for guest single stepping over the given code position */ unsigned long singlestep_rip; - struct kvm_vcpu_hv hyperv; - +#ifdef CONFIG_KVM_HYPERV + bool hyperv_enabled; + struct kvm_vcpu_hv *hyperv; +#endif +#ifdef CONFIG_KVM_XEN + struct kvm_vcpu_xen xen; +#endif cpumask_var_t wbinvd_dirty_mask; unsigned long last_retry_eip; @@ -730,14 +1018,16 @@ struct kvm_vcpu_arch { struct { bool halted; - gfn_t gfns[roundup_pow_of_two(ASYNC_PF_PER_VCPU)]; + gfn_t gfns[ASYNC_PF_PER_VCPU]; struct gfn_to_hva_cache data; - u64 msr_val; + u64 msr_en_val; /* MSR_KVM_ASYNC_PF_EN */ + u64 msr_int_val; /* MSR_KVM_ASYNC_PF_INT */ + u16 vec; u32 id; - bool send_user_only; - u32 host_apf_reason; - unsigned long nested_apf_token; + u32 host_apf_flags; + bool send_always; bool delivery_as_pf_vmexit; + bool pageready_pending; } apf; /* OSVW MSRs (AMD only) */ @@ -751,15 +1041,7 @@ struct kvm_vcpu_arch { struct gfn_to_hva_cache data; } pv_eoi; - /* - * Indicate whether the access faults on its page table in guest - * which is set when fix page fault and used to detect unhandeable - * instruction. - */ - bool write_fault_to_shadow_pgtable; - - /* set at EPT violation at this point */ - unsigned long exit_qualification; + u64 msr_kvm_poll_control; /* pv related host specific info */ struct { @@ -768,16 +1050,45 @@ struct kvm_vcpu_arch { int pending_ioapic_eoi; int pending_external_vector; - - /* GPA available */ - bool gpa_available; - gpa_t gpa_val; + int highest_stale_pending_ioapic_eoi; /* be preempted when it's in kernel-mode(cpl=0) */ bool preempted_in_kernel; - /* Flush the L1 Data cache for L1TF mitigation on VMENTER */ - bool l1tf_flush_l1d; + /* Host CPU on which VM-entry was most recently attempted */ + int last_vmentry_cpu; + + /* AMD MSRC001_0015 Hardware Configuration */ + u64 msr_hwcr; + + /* pv related cpuid info */ + struct { + /* + * value of the eax register in the KVM_CPUID_FEATURES CPUID + * leaf. + */ + u32 features; + + /* + * indicates whether pv emulation should be disabled if features + * are not present in the guest's cpuid + */ + bool enforce; + } pv_cpuid; + + /* Protected Guests */ + bool guest_state_protected; + bool guest_tsc_protected; + + /* + * Set when PDPTS were loaded directly by the userspace without + * reading the guest memory + */ + bool pdptrs_from_userspace; + +#if IS_ENABLED(CONFIG_HYPERV) + hpa_t hv_root_tdp; +#endif }; struct kvm_lpage_info { @@ -787,23 +1098,34 @@ struct kvm_lpage_info { struct kvm_arch_memory_slot { struct kvm_rmap_head *rmap[KVM_NR_PAGE_SIZES]; struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1]; - unsigned short *gfn_track[KVM_PAGE_TRACK_MAX]; + unsigned short *gfn_write_track; }; /* - * We use as the mode the number of bits allocated in the LDR for the - * logical processor ID. It happens that these are all powers of two. - * This makes it is very easy to detect cases where the APICs are - * configured for multiple modes; in that case, we cannot use the map and - * hence cannot use kvm_irq_delivery_to_apic_fast either. + * Track the mode of the optimized logical map, as the rules for decoding the + * destination vary per mode. Enabling the optimized logical map requires all + * software-enabled local APIs to be in the same mode, each addressable APIC to + * be mapped to only one MDA, and each MDA to map to at most one APIC. */ -#define KVM_APIC_MODE_XAPIC_CLUSTER 4 -#define KVM_APIC_MODE_XAPIC_FLAT 8 -#define KVM_APIC_MODE_X2APIC 16 +enum kvm_apic_logical_mode { + /* All local APICs are software disabled. */ + KVM_APIC_MODE_SW_DISABLED, + /* All software enabled local APICs in xAPIC cluster addressing mode. */ + KVM_APIC_MODE_XAPIC_CLUSTER, + /* All software enabled local APICs in xAPIC flat addressing mode. */ + KVM_APIC_MODE_XAPIC_FLAT, + /* All software enabled local APICs in x2APIC mode. */ + KVM_APIC_MODE_X2APIC, + /* + * Optimized map disabled, e.g. not all local APICs in the same logical + * mode, same logical ID assigned to multiple APICs, etc. + */ + KVM_APIC_MODE_MAP_DISABLED, +}; struct kvm_apic_map { struct rcu_head rcu; - u8 mode; + enum kvm_apic_logical_mode logical_mode; u32 max_apic_id; union { struct kvm_lapic *xapic_flat_map[8]; @@ -812,28 +1134,91 @@ struct kvm_apic_map { struct kvm_lapic *phys_map[]; }; +/* Hyper-V synthetic debugger (SynDbg)*/ +struct kvm_hv_syndbg { + struct { + u64 control; + u64 status; + u64 send_page; + u64 recv_page; + u64 pending_page; + } control; + u64 options; +}; + +/* Current state of Hyper-V TSC page clocksource */ +enum hv_tsc_page_status { + /* TSC page was not set up or disabled */ + HV_TSC_PAGE_UNSET = 0, + /* TSC page MSR was written by the guest, update pending */ + HV_TSC_PAGE_GUEST_CHANGED, + /* TSC page update was triggered from the host side */ + HV_TSC_PAGE_HOST_CHANGED, + /* TSC page was properly set up and is currently active */ + HV_TSC_PAGE_SET, + /* TSC page was set up with an inaccessible GPA */ + HV_TSC_PAGE_BROKEN, +}; + +#ifdef CONFIG_KVM_HYPERV /* Hyper-V emulation context */ struct kvm_hv { struct mutex hv_lock; u64 hv_guest_os_id; u64 hv_hypercall; u64 hv_tsc_page; + enum hv_tsc_page_status hv_tsc_page_status; /* Hyper-v based guest crash (NT kernel bugcheck) parameters */ u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS]; u64 hv_crash_ctl; - HV_REFERENCE_TSC_PAGE tsc_ref; + struct ms_hyperv_tsc_page tsc_ref; struct idr conn_to_evt; u64 hv_reenlightenment_control; u64 hv_tsc_emulation_control; u64 hv_tsc_emulation_status; + u64 hv_invtsc_control; /* How many vCPUs have VP index != vCPU index */ atomic_t num_mismatched_vp_indexes; + + /* + * How many SynICs use 'AutoEOI' feature + * (protected by arch.apicv_update_lock) + */ + unsigned int synic_auto_eoi_used; + + struct kvm_hv_syndbg hv_syndbg; + + bool xsaves_xsavec_checked; }; +#endif + +struct msr_bitmap_range { + u32 flags; + u32 nmsrs; + u32 base; + unsigned long *bitmap; +}; + +#ifdef CONFIG_KVM_XEN +/* Xen emulation context */ +struct kvm_xen { + struct mutex xen_lock; + u32 xen_version; + bool long_mode; + bool runstate_update_flag; + u8 upcall_vector; + struct gfn_to_pfn_cache shinfo_cache; + struct idr evtchn_ports; + unsigned long poll_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)]; + + struct kvm_xen_hvm_config hvm_config; +}; +#endif enum kvm_irqchip_mode { KVM_IRQCHIP_NONE, @@ -841,72 +1226,241 @@ enum kvm_irqchip_mode { KVM_IRQCHIP_SPLIT, /* created with KVM_CAP_SPLIT_IRQCHIP */ }; -struct kvm_arch { - unsigned int n_used_mmu_pages; - unsigned int n_requested_mmu_pages; - unsigned int n_max_mmu_pages; - unsigned int indirect_shadow_pages; - unsigned long mmu_valid_gen; - struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES]; +struct kvm_x86_msr_filter { + u8 count; + bool default_allow:1; + struct msr_bitmap_range ranges[16]; +}; + +struct kvm_x86_pmu_event_filter { + __u32 action; + __u32 nevents; + __u32 fixed_counter_bitmap; + __u32 flags; + __u32 nr_includes; + __u32 nr_excludes; + __u64 *includes; + __u64 *excludes; + __u64 events[]; +}; + +enum kvm_apicv_inhibit { + + /********************************************************************/ + /* INHIBITs that are relevant to both Intel's APICv and AMD's AVIC. */ + /********************************************************************/ + + /* + * APIC acceleration is disabled by a module parameter + * and/or not supported in hardware. + */ + APICV_INHIBIT_REASON_DISABLED, + + /* + * APIC acceleration is inhibited because AutoEOI feature is + * being used by a HyperV guest. + */ + APICV_INHIBIT_REASON_HYPERV, + + /* + * APIC acceleration is inhibited because the userspace didn't yet + * enable the kernel/split irqchip. + */ + APICV_INHIBIT_REASON_ABSENT, + + /* APIC acceleration is inhibited because KVM_GUESTDBG_BLOCKIRQ + * (out of band, debug measure of blocking all interrupts on this vCPU) + * was enabled, to avoid AVIC/APICv bypassing it. + */ + APICV_INHIBIT_REASON_BLOCKIRQ, + + /* + * APICv is disabled because not all vCPUs have a 1:1 mapping between + * APIC ID and vCPU, _and_ KVM is not applying its x2APIC hotplug hack. + */ + APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED, + /* - * Hash table of struct kvm_mmu_page. + * For simplicity, the APIC acceleration is inhibited + * first time either APIC ID or APIC base are changed by the guest + * from their reset values. */ + APICV_INHIBIT_REASON_APIC_ID_MODIFIED, + APICV_INHIBIT_REASON_APIC_BASE_MODIFIED, + + /******************************************************/ + /* INHIBITs that are relevant only to the AMD's AVIC. */ + /******************************************************/ + + /* + * AVIC is inhibited on a vCPU because it runs a nested guest. + * + * This is needed because unlike APICv, the peers of this vCPU + * cannot use the doorbell mechanism to signal interrupts via AVIC when + * a vCPU runs nested. + */ + APICV_INHIBIT_REASON_NESTED, + + /* + * On SVM, the wait for the IRQ window is implemented with pending vIRQ, + * which cannot be injected when the AVIC is enabled, thus AVIC + * is inhibited while KVM waits for IRQ window. + */ + APICV_INHIBIT_REASON_IRQWIN, + + /* + * PIT (i8254) 're-inject' mode, relies on EOI intercept, + * which AVIC doesn't support for edge triggered interrupts. + */ + APICV_INHIBIT_REASON_PIT_REINJ, + + /* + * AVIC is disabled because SEV doesn't support it. + */ + APICV_INHIBIT_REASON_SEV, + + /* + * AVIC is disabled because not all vCPUs with a valid LDR have a 1:1 + * mapping between logical ID and vCPU. + */ + APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED, + + /* + * 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, +}; + +#define __APICV_INHIBIT_REASON(reason) \ + { BIT(APICV_INHIBIT_REASON_##reason), #reason } + +#define APICV_INHIBIT_REASONS \ + __APICV_INHIBIT_REASON(DISABLED), \ + __APICV_INHIBIT_REASON(HYPERV), \ + __APICV_INHIBIT_REASON(ABSENT), \ + __APICV_INHIBIT_REASON(BLOCKIRQ), \ + __APICV_INHIBIT_REASON(PHYSICAL_ID_ALIASED), \ + __APICV_INHIBIT_REASON(APIC_ID_MODIFIED), \ + __APICV_INHIBIT_REASON(APIC_BASE_MODIFIED), \ + __APICV_INHIBIT_REASON(NESTED), \ + __APICV_INHIBIT_REASON(IRQWIN), \ + __APICV_INHIBIT_REASON(PIT_REINJ), \ + __APICV_INHIBIT_REASON(SEV), \ + __APICV_INHIBIT_REASON(LOGICAL_ID_ALIASED), \ + __APICV_INHIBIT_REASON(PHYSICAL_ID_TOO_BIG) + +struct kvm_possible_nx_huge_pages { + /* + * A list of kvm_mmu_page structs that, if zapped, could possibly be + * replaced by an NX huge page. A shadow page is on this list if its + * existence disallows an NX huge page (nx_huge_page_disallowed is set) + * and there are no other conditions that prevent a huge page, e.g. + * the backing host page is huge, dirtly logging is not enabled for its + * memslot, etc... Note, zapping shadow pages on this list doesn't + * guarantee an NX huge page will be created in its stead, e.g. if the + * guest attempts to execute from the region then KVM obviously can't + * create an NX huge page (without hanging the guest). + */ + struct list_head pages; + u64 nr_pages; +}; + +enum kvm_mmu_type { + KVM_SHADOW_MMU, +#ifdef CONFIG_X86_64 + KVM_TDP_MMU, +#endif + KVM_NR_MMU_TYPES, +}; + +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; + u8 vm_type; + bool has_private_mem; + bool has_protected_state; + bool has_protected_eoi; + bool pre_fault_allowed; + struct hlist_head *mmu_page_hash; struct list_head active_mmu_pages; - struct list_head zapped_obsolete_pages; - struct kvm_page_track_notifier_node mmu_sp_tracker; + struct kvm_possible_nx_huge_pages possible_nx_huge_pages[KVM_NR_MMU_TYPES]; +#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING struct kvm_page_track_notifier_head track_notifier_head; +#endif + /* + * Protects marking pages unsync during page faults, as TDP MMU page + * faults only take mmu_lock for read. For simplicity, the unsync + * pages lock is always taken when marking pages unsync regardless of + * whether mmu_lock is held for read or write. + */ + spinlock_t mmu_unsync_pages_lock; + + u64 shadow_mmio_value; - struct list_head assigned_dev_head; - struct iommu_domain *iommu_domain; - bool iommu_noncoherent; #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 *apic_map; + struct kvm_apic_map __rcu *apic_map; + atomic_t apic_map_dirty; - bool apic_access_page_done; + bool apic_access_memslot_enabled; + bool apic_access_memslot_inhibited; + + /* Protects apicv_inhibit_reasons */ + struct rw_semaphore apicv_update_lock; + unsigned long apicv_inhibit_reasons; gpa_t wall_clock; - bool mwait_in_guest; - bool hlt_in_guest; - bool pause_in_guest; + u64 disabled_exits; - unsigned long irq_sources_bitmap; s64 kvmclock_offset; + + /* + * This also protects nr_vcpus_matched_tsc which is read from a + * preemption-disabled region, so it must be a raw spinlock. + */ raw_spinlock_t tsc_write_lock; u64 last_tsc_nsec; u64 last_tsc_write; u32 last_tsc_khz; + u64 last_tsc_offset; u64 cur_tsc_nsec; u64 cur_tsc_write; u64 cur_tsc_offset; u64 cur_tsc_generation; int nr_vcpus_matched_tsc; - spinlock_t pvclock_gtod_sync_lock; + u32 default_tsc_khz; + bool user_set_tsc; + u64 apic_bus_cycle_ns; + + seqcount_raw_spinlock_t pvclock_sc; bool use_master_clock; u64 master_kernel_ns; u64 master_cycle_now; - struct delayed_work kvmclock_update_work; - struct delayed_work kvmclock_sync_work; - - struct kvm_xen_hvm_config xen_hvm_config; - - /* reads protected by irq_srcu, writes by irq_lock */ - struct hlist_head mask_notifier_list; +#ifdef CONFIG_KVM_HYPERV struct kvm_hv hyperv; +#endif - #ifdef CONFIG_KVM_MMU_AUDIT - int audit_point; - #endif +#ifdef CONFIG_KVM_XEN + struct kvm_xen xen; +#endif bool backwards_tsc_observed; bool boot_vcpu_runs_old_kvmclock; @@ -922,26 +1476,175 @@ 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; + + bool triple_fault_event; + + bool bus_lock_detection_enabled; + bool enable_pmu; + + u32 notify_window; + u32 notify_vmexit_flags; + /* + * If exit_on_emulation_error is set, and the in-kernel instruction + * emulator fails to emulate an instruction, allow userspace + * the opportunity to look at it. + */ + bool exit_on_emulation_error; + + /* Deflect RDMSR and WRMSR to user space when they trigger a #GP */ + u32 user_space_msr_mask; + struct kvm_x86_msr_filter __rcu *msr_filter; + + u32 hypercall_exit_enabled; + + /* Guest can access the SGX PROVISIONKEY. */ + bool sgx_provisioning_allowed; + + struct kvm_x86_pmu_event_filter __rcu *pmu_event_filter; + struct vhost_task *nx_huge_page_recovery_thread; + u64 nx_huge_page_last; + struct once nx_once; + +#ifdef CONFIG_X86_64 +#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. + * All struct kvm_mmu_pages in the list should have + * tdp_mmu_page set. + * + * For reads, this list is protected by: + * RCU alone or + * the MMU lock in read mode + RCU or + * the MMU lock in write mode + * + * For writes, this list is protected by tdp_mmu_pages_lock; see + * below for the details. + * + * Roots will remain in the list until their tdp_mmu_root_count + * drops to zero, at which point the thread that decremented the + * count to zero should removed the root from the list and clean + * it up, freeing the root after an RCU grace period. + */ + struct list_head tdp_mmu_roots; + + /* + * Protects accesses to the following fields when the MMU lock + * is held in read mode: + * - tdp_mmu_roots (above) + * - the link field of kvm_mmu_page structs used by the TDP MMU + * - possible_nx_huge_pages[KVM_TDP_MMU]; + * - the possible_nx_huge_page_link field of kvm_mmu_page structs used + * by the TDP MMU + * Because the lock is only taken within the MMU lock, strictly + * speaking it is redundant to acquire this lock when the thread + * holds the MMU lock in write mode. However it often simplifies + * the code to do so. + */ + spinlock_t tdp_mmu_pages_lock; +#endif /* CONFIG_X86_64 */ + + /* + * If set, at least one shadow root has been allocated. This flag + * is used as one input when determining whether certain memslot + * related allocations are necessary. + */ + bool shadow_root_allocated; + +#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING + /* + * If set, the VM has (or had) an external write tracking user, and + * thus all write tracking metadata has been allocated, even if KVM + * itself isn't using write tracking. + */ + bool external_write_tracking_enabled; +#endif + +#if IS_ENABLED(CONFIG_HYPERV) + hpa_t hv_root_tdp; + spinlock_t hv_root_tdp_lock; + struct hv_partition_assist_pg *hv_pa_pg; +#endif + /* + * VM-scope maximum vCPU ID. Used to determine the size of structures + * that increase along with the maximum vCPU ID, in which case, using + * the global KVM_MAX_VCPU_IDS may lead to significant memory waste. + */ + u32 max_vcpu_ids; + + bool disable_nx_huge_pages; + + /* + * Memory caches used to allocate shadow pages when performing eager + * page splitting. No need for a shadowed_info_cache since eager page + * splitting only allocates direct shadow pages. + * + * Protected by kvm->slots_lock. + */ + struct kvm_mmu_memory_cache split_shadow_page_cache; + struct kvm_mmu_memory_cache split_page_header_cache; + + /* + * Memory cache used to allocate pte_list_desc structs while splitting + * huge pages. In the worst case, to split one huge page, 512 + * pte_list_desc structs are needed to add each lower level leaf sptep + * to the rmap plus 1 to extend the parent_ptes rmap of the lower level + * page table. + * + * Protected by kvm->slots_lock. + */ +#define SPLIT_DESC_CACHE_MIN_NR_OBJECTS (SPTE_ENT_PER_PAGE + 1) + 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 { - ulong mmu_shadow_zapped; - ulong mmu_pte_write; - ulong mmu_pte_updated; - ulong mmu_pde_zapped; - ulong mmu_flooded; - ulong mmu_recycled; - ulong mmu_cache_miss; - ulong mmu_unsync; - ulong remote_tlb_flush; - ulong lpages; - ulong max_mmu_page_hash_collisions; + struct kvm_vm_stat_generic generic; + u64 mmu_shadow_zapped; + u64 mmu_pte_write; + u64 mmu_pde_zapped; + u64 mmu_flooded; + u64 mmu_recycled; + u64 mmu_cache_miss; + u64 mmu_unsync; + union { + struct { + atomic64_t pages_4k; + atomic64_t pages_2m; + atomic64_t pages_1g; + }; + atomic64_t pages[KVM_NR_PAGE_SIZES]; + }; + u64 nx_lpage_splits; + u64 max_mmu_page_hash_collisions; + u64 max_mmu_rmap_size; }; struct kvm_vcpu_stat { + struct kvm_vcpu_stat_generic generic; + u64 pf_taken; u64 pf_fixed; + u64 pf_emulate; + u64 pf_spurious; + u64 pf_fast; + u64 pf_mmio_spte_created; u64 pf_guest; u64 tlb_flush; u64 invlpg; @@ -954,10 +1657,6 @@ struct kvm_vcpu_stat { u64 nmi_window_exits; u64 l1d_flush; u64 halt_exits; - u64 halt_successful_poll; - u64 halt_attempted_poll; - u64 halt_poll_invalid; - u64 halt_wakeup; u64 request_irq_exits; u64 irq_exits; u64 host_state_reload; @@ -968,6 +1667,13 @@ struct kvm_vcpu_stat { u64 irq_injections; u64 nmi_injections; u64 req_event; + u64 nested_run; + u64 directed_yield_attempted; + u64 directed_yield_successful; + u64 preemption_reported; + u64 preemption_other; + u64 guest_mode; + u64 notify_window_exits; }; struct x86_instruction_info; @@ -989,65 +1695,86 @@ 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; +} + +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 { - int (*cpu_has_kvm_support)(void); /* __init */ - int (*disabled_by_bios)(void); /* __init */ - int (*hardware_enable)(void); - void (*hardware_disable)(void); - void (*check_processor_compatibility)(void *rtn); - int (*hardware_setup)(void); /* __init */ - void (*hardware_unsetup)(void); /* __exit */ - bool (*cpu_has_accelerated_tpr)(void); - bool (*has_emulated_msr)(int index); - void (*cpuid_update)(struct kvm_vcpu *vcpu); - - struct kvm *(*vm_alloc)(void); - void (*vm_free)(struct kvm *); + const char *name; + + int (*check_processor_compatibility)(void); + + int (*enable_virtualization_cpu)(void); + void (*disable_virtualization_cpu)(void); + cpu_emergency_virt_cb *emergency_disable_virtualization_cpu; + + void (*hardware_unsetup)(void); + bool (*has_emulated_msr)(struct kvm *kvm, u32 index); + void (*vcpu_after_set_cpuid)(struct kvm_vcpu *vcpu); + + 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 */ - struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id); + int (*vcpu_precreate)(struct kvm *kvm); + int (*vcpu_create)(struct kvm_vcpu *vcpu); void (*vcpu_free)(struct kvm_vcpu *vcpu); void (*vcpu_reset)(struct kvm_vcpu *vcpu, bool init_event); - void (*prepare_guest_switch)(struct kvm_vcpu *vcpu); + void (*prepare_switch_to_guest)(struct kvm_vcpu *vcpu); void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu); void (*vcpu_put)(struct kvm_vcpu *vcpu); - void (*update_bp_intercept)(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); u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg); void (*get_segment)(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); int (*get_cpl)(struct kvm_vcpu *vcpu); + int (*get_cpl_no_cache)(struct kvm_vcpu *vcpu); void (*set_segment)(struct kvm_vcpu *vcpu, 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); + bool (*is_valid_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0); void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0); - void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); - int (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4); - void (*set_efer)(struct kvm_vcpu *vcpu, u64 efer); + void (*post_set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); + bool (*is_valid_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4); + void (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4); + int (*set_efer)(struct kvm_vcpu *vcpu, u64 efer); void (*get_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*set_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); - u64 (*get_dr6)(struct kvm_vcpu *vcpu); - void (*set_dr6)(struct kvm_vcpu *vcpu, unsigned long value); void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu); 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); void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); - - void (*tlb_flush)(struct kvm_vcpu *vcpu, bool invalidate_gpa); - int (*tlb_remote_flush)(struct kvm *kvm); - int (*tlb_remote_flush_with_range)(struct kvm *kvm, - struct kvm_tlb_range *range); + bool (*get_if_flag)(struct kvm_vcpu *vcpu); + + void (*flush_tlb_all)(struct kvm_vcpu *vcpu); + void (*flush_tlb_current)(struct kvm_vcpu *vcpu); +#if IS_ENABLED(CONFIG_HYPERV) + int (*flush_remote_tlbs)(struct kvm *kvm); + int (*flush_remote_tlbs_range)(struct kvm *kvm, gfn_t gfn, + gfn_t nr_pages); +#endif /* * Flush any TLB entries associated with the given GVA. @@ -1055,145 +1782,194 @@ struct kvm_x86_ops { * Can potentially get non-canonical addresses through INVLPGs, which * the implementation may choose to ignore if appropriate. */ - void (*tlb_flush_gva)(struct kvm_vcpu *vcpu, gva_t addr); + void (*flush_tlb_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); + /* + * Flush any TLB entries created by the guest. Like tlb_flush_gva(), + * does not need to flush GPA->HPA mappings. + */ + void (*flush_tlb_guest)(struct kvm_vcpu *vcpu); + + int (*vcpu_pre_run)(struct kvm_vcpu *vcpu); + enum exit_fastpath_completion (*vcpu_run)(struct kvm_vcpu *vcpu, + u64 run_flags); + int (*handle_exit)(struct kvm_vcpu *vcpu, + enum exit_fastpath_completion exit_fastpath); + int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); + void (*update_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, unsigned char *hypercall_addr); - void (*set_irq)(struct kvm_vcpu *vcpu); - void (*set_nmi)(struct kvm_vcpu *vcpu); - void (*queue_exception)(struct kvm_vcpu *vcpu); + void (*inject_irq)(struct kvm_vcpu *vcpu, bool reinjected); + void (*inject_nmi)(struct kvm_vcpu *vcpu); + void (*inject_exception)(struct kvm_vcpu *vcpu); void (*cancel_injection)(struct kvm_vcpu *vcpu); - int (*interrupt_allowed)(struct kvm_vcpu *vcpu); - int (*nmi_allowed)(struct kvm_vcpu *vcpu); + int (*interrupt_allowed)(struct kvm_vcpu *vcpu, bool for_injection); + int (*nmi_allowed)(struct kvm_vcpu *vcpu, bool for_injection); bool (*get_nmi_mask)(struct kvm_vcpu *vcpu); void (*set_nmi_mask)(struct kvm_vcpu *vcpu, bool masked); + /* Whether or not a virtual NMI is pending in hardware. */ + bool (*is_vnmi_pending)(struct kvm_vcpu *vcpu); + /* + * Attempt to pend a virtual NMI in hardware. Returns %true on success + * to allow using static_call_ret0 as the fallback. + */ + bool (*set_vnmi_pending)(struct kvm_vcpu *vcpu); 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); + + const bool x2apic_icr_is_split; + const unsigned long required_apicv_inhibits; + bool allow_apicv_in_x2apic_without_x2apic_virtualization; void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); - void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr); - bool (*guest_apic_has_interrupt)(struct kvm_vcpu *vcpu); void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu); - void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa); - void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); + void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu); + void (*deliver_interrupt)(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector); int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); int (*set_tss_addr)(struct kvm *kvm, unsigned int addr); int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr); - int (*get_tdp_level)(struct kvm_vcpu *vcpu); - u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio); - int (*get_lpage_level)(void); - bool (*rdtscp_supported)(void); - bool (*invpcid_supported)(void); + u8 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio); + + void (*load_mmu_pgd)(struct kvm_vcpu *vcpu, hpa_t root_hpa, + int root_level); + + /* Update external mapping with page table link. */ + int (*link_external_spt)(struct kvm *kvm, gfn_t gfn, enum pg_level level, + void *external_spt); + /* Update the external page table from spte getting set. */ + int (*set_external_spte)(struct kvm *kvm, gfn_t gfn, enum pg_level level, + u64 mirror_spte); - void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); + /* Update external page tables for page table about to be freed. */ + int (*free_external_spt)(struct kvm *kvm, gfn_t gfn, enum pg_level level, + void *external_spt); - void (*set_supported_cpuid)(u32 func, struct kvm_cpuid_entry2 *entry); + /* Update external page table from spte getting removed, and flush TLB. */ + void (*remove_external_spte)(struct kvm *kvm, gfn_t gfn, enum pg_level level, + u64 mirror_spte); bool (*has_wbinvd_exit)(void); - u64 (*read_l1_tsc_offset)(struct kvm_vcpu *vcpu); - /* Returns actual tsc_offset set in active VMCS */ - u64 (*write_l1_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); + u64 (*get_l2_tsc_offset)(struct kvm_vcpu *vcpu); + u64 (*get_l2_tsc_multiplier)(struct kvm_vcpu *vcpu); + void (*write_tsc_offset)(struct kvm_vcpu *vcpu); + void (*write_tsc_multiplier)(struct kvm_vcpu *vcpu); - void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2); + /* + * Retrieve somewhat arbitrary exit/entry information. Intended to + * be used only from within tracepoints or error paths. + */ + void (*get_exit_info)(struct kvm_vcpu *vcpu, u32 *reason, + u64 *info1, u64 *info2, + u32 *intr_info, u32 *error_code); + + void (*get_entry_info)(struct kvm_vcpu *vcpu, + u32 *intr_info, u32 *error_code); int (*check_intercept)(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, - enum x86_intercept_stage stage); - void (*handle_external_intr)(struct kvm_vcpu *vcpu); - bool (*mpx_supported)(void); - bool (*xsaves_supported)(void); - bool (*umip_emulated)(void); - bool (*pt_supported)(void); - - int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr); - void (*request_immediate_exit)(struct kvm_vcpu *vcpu); - - void (*sched_in)(struct kvm_vcpu *kvm, int cpu); + enum x86_intercept_stage stage, + struct x86_exception *exception); + void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu); - /* - * Arch-specific dirty logging hooks. These hooks are only supposed to - * be valid if the specific arch has hardware-accelerated dirty logging - * mechanism. Currently only for PML on VMX. - * - * - slot_enable_log_dirty: - * called when enabling log dirty mode for the slot. - * - slot_disable_log_dirty: - * called when disabling log dirty mode for the slot. - * also called when slot is created with log dirty disabled. - * - flush_log_dirty: - * called before reporting dirty_bitmap to userspace. - * - enable_log_dirty_pt_masked: - * called when reenabling log dirty for the GFNs in the mask after - * corresponding bits are cleared in slot->dirty_bitmap. - */ - void (*slot_enable_log_dirty)(struct kvm *kvm, - struct kvm_memory_slot *slot); - void (*slot_disable_log_dirty)(struct kvm *kvm, - struct kvm_memory_slot *slot); - void (*flush_log_dirty)(struct kvm *kvm); - void (*enable_log_dirty_pt_masked)(struct kvm *kvm, - struct kvm_memory_slot *slot, - gfn_t offset, unsigned long mask); - int (*write_log_dirty)(struct kvm_vcpu *vcpu); - - /* pmu operations of sub-arch */ - const struct kvm_pmu_ops *pmu_ops; + void (*update_cpu_dirty_logging)(struct kvm_vcpu *vcpu); - /* - * Architecture specific hooks for vCPU blocking due to - * HLT instruction. - * Returns for .pre_block(): - * - 0 means continue to block the vCPU. - * - 1 means we cannot block the vCPU since some event - * happens during this period, such as, 'ON' bit in - * posted-interrupts descriptor is set. - */ - int (*pre_block)(struct kvm_vcpu *vcpu); - void (*post_block)(struct kvm_vcpu *vcpu); + const struct kvm_x86_nested_ops *nested_ops; void (*vcpu_blocking)(struct kvm_vcpu *vcpu); void (*vcpu_unblocking)(struct kvm_vcpu *vcpu); - int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set); + 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); + int (*set_hv_timer)(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, + bool *expired); void (*cancel_hv_timer)(struct kvm_vcpu *vcpu); void (*setup_mce)(struct kvm_vcpu *vcpu); - int (*get_nested_state)(struct kvm_vcpu *vcpu, - struct kvm_nested_state __user *user_kvm_nested_state, - unsigned user_data_size); - 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); +#ifdef CONFIG_KVM_SMM + int (*smi_allowed)(struct kvm_vcpu *vcpu, bool for_injection); + int (*enter_smm)(struct kvm_vcpu *vcpu, union kvm_smram *smram); + int (*leave_smm)(struct kvm_vcpu *vcpu, const union kvm_smram *smram); + void (*enable_smi_window)(struct kvm_vcpu *vcpu); +#endif + + 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 (*vcpu_mem_enc_unlocked_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); + int (*vm_move_enc_context_from)(struct kvm *kvm, unsigned int source_fd); + void (*guest_memory_reclaimed)(struct kvm *kvm); + + int (*get_feature_msr)(u32 msr, u64 *data); + + int (*check_emulate_instruction)(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len); + + bool (*apic_init_signal_blocked)(struct kvm_vcpu *vcpu); + int (*enable_l2_tlb_flush)(struct kvm_vcpu *vcpu); + + void (*migrate_timers)(struct kvm_vcpu *vcpu); + void (*recalc_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); + + /* + * Returns vCPU specific APICv inhibit reasons + */ + unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu); - int (*smi_allowed)(struct kvm_vcpu *vcpu); - int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate); - int (*pre_leave_smm)(struct kvm_vcpu *vcpu, u64 smbase); - int (*enable_smi_window)(struct kvm_vcpu *vcpu); + gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags); + void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu); + int (*gmem_prepare)(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order); + void (*gmem_invalidate)(kvm_pfn_t start, kvm_pfn_t end); + int (*gmem_max_mapping_level)(struct kvm *kvm, kvm_pfn_t pfn, bool is_private); +}; - int (*mem_enc_op)(struct kvm *kvm, void __user *argp); - int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp); - int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp); +struct kvm_x86_nested_ops { + void (*leave_nested)(struct kvm_vcpu *vcpu); + bool (*is_exception_vmexit)(struct kvm_vcpu *vcpu, u8 vector, + u32 error_code); + int (*check_events)(struct kvm_vcpu *vcpu); + bool (*has_events)(struct kvm_vcpu *vcpu, bool for_injection); + void (*triple_fault)(struct kvm_vcpu *vcpu); + int (*get_state)(struct kvm_vcpu *vcpu, + struct kvm_nested_state __user *user_kvm_nested_state, + unsigned user_data_size); + int (*set_state)(struct kvm_vcpu *vcpu, + struct kvm_nested_state __user *user_kvm_nested_state, + struct kvm_nested_state *kvm_state); + bool (*get_nested_state_pages)(struct kvm_vcpu *vcpu); + int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa); + + int (*enable_evmcs)(struct kvm_vcpu *vcpu, + uint16_t *vmcs_version); + uint16_t (*get_evmcs_version)(struct kvm_vcpu *vcpu); + void (*hv_inject_synthetic_vmexit_post_tlb_flush)(struct kvm_vcpu *vcpu); +}; - int (*get_msr_feature)(struct kvm_msr_entry *entry); +struct kvm_x86_init_ops { + int (*hardware_setup)(void); + unsigned int (*handle_intel_pt_intr)(void); - int (*nested_enable_evmcs)(struct kvm_vcpu *vcpu, - uint16_t *vmcs_version); - uint16_t (*nested_get_evmcs_version)(struct kvm_vcpu *vcpu); + struct kvm_x86_ops *runtime_ops; + struct kvm_pmu_ops *pmu_ops; }; struct kvm_arch_async_pf { @@ -1201,160 +1977,264 @@ struct kvm_arch_async_pf { gfn_t gfn; unsigned long cr3; bool direct_map; + u64 error_code; }; -extern struct kvm_x86_ops *kvm_x86_ops; -extern struct kmem_cache *x86_fpu_cache; +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) +#define kvm_pmu_call(func) static_call(kvm_x86_pmu_##func) + +#define KVM_X86_OP(func) \ + DECLARE_STATIC_CALL(kvm_x86_##func, *(((struct kvm_x86_ops *)0)->func)); +#define KVM_X86_OP_OPTIONAL KVM_X86_OP +#define KVM_X86_OP_OPTIONAL_RET0 KVM_X86_OP +#include <asm/kvm-x86-ops.h> + +int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops); +void kvm_x86_vendor_exit(void); #define __KVM_HAVE_ARCH_VM_ALLOC static inline struct kvm *kvm_arch_alloc_vm(void) { - return kvm_x86_ops->vm_alloc(); + return kvzalloc(kvm_x86_ops.vm_size, GFP_KERNEL_ACCOUNT); } -static inline void kvm_arch_free_vm(struct kvm *kvm) -{ - return kvm_x86_ops->vm_free(kvm); -} +#define __KVM_HAVE_ARCH_VM_FREE +void kvm_arch_free_vm(struct kvm *kvm); -#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB -static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm) +#if IS_ENABLED(CONFIG_HYPERV) +#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS +static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm) { - if (kvm_x86_ops->tlb_remote_flush && - !kvm_x86_ops->tlb_remote_flush(kvm)) + if (kvm_x86_ops.flush_remote_tlbs && + !kvm_x86_call(flush_remote_tlbs)(kvm)) return 0; else return -ENOTSUPP; } -int kvm_mmu_module_init(void); -void kvm_mmu_module_exit(void); +#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE +static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, + u64 nr_pages) +{ + if (!kvm_x86_ops.flush_remote_tlbs_range) + return -EOPNOTSUPP; + + return kvm_x86_call(flush_remote_tlbs_range)(kvm, gfn, nr_pages); +} +#endif /* CONFIG_HYPERV */ + +enum kvm_intr_type { + /* Values are arbitrary, but must be non-zero. */ + KVM_HANDLING_IRQ = 1, + KVM_HANDLING_NMI, +}; + +/* Enable perf NMI and timer modes to work, and minimise false positives. */ +#define kvm_arch_pmi_in_guest(vcpu) \ + ((vcpu) && (vcpu)->arch.handling_intr_from_guest && \ + (!!in_nmi() == ((vcpu)->arch.handling_intr_from_guest == KVM_HANDLING_NMI))) + +void __init kvm_mmu_x86_module_init(void); +int kvm_mmu_vendor_module_init(void); +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_set_mask_ptes(u64 user_mask, u64 accessed_mask, - u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask, - u64 acc_track_mask, u64 me_mask); +void kvm_mmu_init_memslot_memory_attributes(struct kvm *kvm, + struct kvm_memory_slot *slot); + +void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu); void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, - struct kvm_memory_slot *memslot); -void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, - const struct kvm_memory_slot *memslot); + const struct kvm_memory_slot *memslot, + int start_level); +void kvm_mmu_slot_try_split_huge_pages(struct kvm *kvm, + const struct kvm_memory_slot *memslot, + int target_level); +void kvm_mmu_try_split_huge_pages(struct kvm *kvm, + const struct kvm_memory_slot *memslot, + u64 start, u64 end, + int target_level); +void kvm_mmu_recover_huge_pages(struct kvm *kvm, + const struct kvm_memory_slot *memslot); void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, - struct kvm_memory_slot *memslot); -void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm, - struct kvm_memory_slot *memslot); -void kvm_mmu_slot_set_dirty(struct kvm *kvm, - struct kvm_memory_slot *memslot); -void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, - struct kvm_memory_slot *slot, - gfn_t gfn_offset, unsigned long mask); -void kvm_mmu_zap_all(struct kvm *kvm); -void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, struct kvm_memslots *slots); -unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm); -void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages); - -int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3); -bool pdptrs_changed(struct kvm_vcpu *vcpu); + const struct kvm_memory_slot *memslot); +void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen); +void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages); +void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end); + +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); -/* control of guest tsc rate supported? */ -extern bool kvm_has_tsc_control; -/* maximum supported tsc_khz for guests */ -extern u32 kvm_max_guest_tsc_khz; -/* number of bits of the fractional part of the TSC scaling ratio */ -extern u8 kvm_tsc_scaling_ratio_frac_bits; -/* maximum allowed value of TSC scaling ratio */ -extern u64 kvm_max_tsc_scaling_ratio; -/* 1ull << kvm_tsc_scaling_ratio_frac_bits */ -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 reused 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 if + * EMULTYPE_COMPLETE_USER_EXIT is not set. + * + * EMULTYPE_ALLOW_RETRY_PF - Set when the emulator should resume the guest to + * retry native execution under certain conditions, + * Can only be set in conjunction with EMULTYPE_PF. + * + * 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 backdoor emulation handles select instructions + * and reinjects the #GP for all other cases. + * + * EMULTYPE_PF - Set when an intercepted #PF triggers the emulation, in which case + * the CR2/GPA value pass on the stack is valid. + * + * EMULTYPE_COMPLETE_USER_EXIT - Set when the emulator should update interruptibility + * state and inject single-step #DBs after skipping + * an instruction (after completing userspace I/O). + * + * EMULTYPE_WRITE_PF_TO_SP - Set when emulating an intercepted page fault that + * is attempting to write a gfn that contains one or + * more of the PTEs used to translate the write itself, + * and the owning page table is being shadowed by KVM. + * If emulation of the faulting instruction fails and + * this flag is set, KVM will exit to userspace instead + * of retrying emulation 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. + * + * EMULTYPE_SKIP_SOFT_INT - Set in combination with EMULTYPE_SKIP to only skip + * an instruction if it could generate a given software + * interrupt, which must be encoded via + * EMULTYPE_SET_SOFT_INT_VECTOR(). + */ #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_ALLOW_RETRY_PF (1 << 3) +#define EMULTYPE_TRAP_UD_FORCED (1 << 4) +#define EMULTYPE_VMWARE_GP (1 << 5) +#define EMULTYPE_PF (1 << 6) +#define EMULTYPE_COMPLETE_USER_EXIT (1 << 7) +#define EMULTYPE_WRITE_PF_TO_SP (1 << 8) +#define EMULTYPE_SKIP_SOFT_INT (1 << 9) + +#define EMULTYPE_SET_SOFT_INT_VECTOR(v) ((u32)((v) & 0xff) << 16) +#define EMULTYPE_GET_SOFT_INT_VECTOR(e) (((e) >> 16) & 0xff) + +static inline bool kvm_can_emulate_event_vectoring(int emul_type) +{ + return !(emul_type & EMULTYPE_PF); +} + 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_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, + u64 *data, u8 ndata); +void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu); + +void kvm_prepare_event_vectoring_exit(struct kvm_vcpu *vcpu, gpa_t gpa); +void kvm_prepare_unexpected_reason_exit(struct kvm_vcpu *vcpu, u64 exit_reason); 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); - -struct x86_emulate_ctxt; +int kvm_emulate_msr_read(struct kvm_vcpu *vcpu, u32 index, u64 *data); +int kvm_emulate_msr_write(struct kvm_vcpu *vcpu, u32 index, u64 data); +int __kvm_emulate_msr_read(struct kvm_vcpu *vcpu, u32 index, u64 *data); +int __kvm_emulate_msr_write(struct kvm_vcpu *vcpu, u32 index, u64 data); +int kvm_msr_read(struct kvm_vcpu *vcpu, u32 index, u64 *data); +int kvm_msr_write(struct kvm_vcpu *vcpu, u32 index, u64 data); +int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu); +int kvm_emulate_rdmsr_imm(struct kvm_vcpu *vcpu, u32 msr, int reg); +int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu); +int kvm_emulate_wrmsr_imm(struct kvm_vcpu *vcpu, u32 msr, int reg); +int kvm_emulate_as_nop(struct kvm_vcpu *vcpu); +int kvm_emulate_invd(struct kvm_vcpu *vcpu); +int kvm_emulate_mwait(struct kvm_vcpu *vcpu); +int kvm_handle_invalid_op(struct kvm_vcpu *vcpu); +int kvm_emulate_monitor(struct kvm_vcpu *vcpu); int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in); int kvm_emulate_cpuid(struct kvm_vcpu *vcpu); int kvm_emulate_halt(struct kvm_vcpu *vcpu); -int kvm_vcpu_halt(struct kvm_vcpu *vcpu); +int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu); +int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu); int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); +void kvm_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg); void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, int reason, bool has_error_code, u32 error_code); +void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0); +void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned long cr4); int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3); int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8); int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val); -int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val); +unsigned long kvm_get_dr(struct kvm_vcpu *vcpu, int dr); unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu); void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw); -void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l); -int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr); +int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr); +int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu); int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr); int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr); unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu); void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); -bool kvm_rdpmc(struct kvm_vcpu *vcpu); +int kvm_emulate_rdpmc(struct kvm_vcpu *vcpu); void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr); void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); -void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr); -void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); +void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, unsigned long payload); +void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned int nr, + bool has_error_code, u32 error_code); void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault); -int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - gfn_t gfn, void *data, int offset, int len, - u32 access); +void kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, + struct x86_exception *fault); bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl); bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr); @@ -1370,59 +2250,68 @@ static inline int __kvm_irq_line_state(unsigned long *irq_state, return !!(*irq_state); } -#define KVM_MMU_ROOT_CURRENT BIT(0) -#define KVM_MMU_ROOT_PREVIOUS(i) BIT(1+i) -#define KVM_MMU_ROOTS_ALL (~0UL) +void kvm_inject_nmi(struct kvm_vcpu *vcpu); +int kvm_get_nr_pending_nmis(struct kvm_vcpu *vcpu); -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_update_dr7(struct kvm_vcpu *vcpu); -void kvm_inject_nmi(struct kvm_vcpu *vcpu); +bool __kvm_mmu_unprotect_gfn_and_retry(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + bool always_retry); -int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn); -int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva); -void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu); -int kvm_mmu_load(struct kvm_vcpu *vcpu); -void kvm_mmu_unload(struct kvm_vcpu *vcpu); -void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu); -void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, +static inline bool kvm_mmu_unprotect_gfn_and_retry(struct kvm_vcpu *vcpu, + gpa_t cr2_or_gpa) +{ + return __kvm_mmu_unprotect_gfn_and_retry(vcpu, cr2_or_gpa, false); +} + +void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, ulong roots_to_free); -gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, - struct x86_exception *exception); +void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu); gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception); -gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, - struct x86_exception *exception); gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception); 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); +bool kvm_vcpu_apicv_activated(struct kvm_vcpu *vcpu); +void __kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu); +void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, + enum kvm_apicv_inhibit reason, bool set); +void kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, + enum kvm_apicv_inhibit reason, bool set); -int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); +static inline void kvm_set_apicv_inhibit(struct kvm *kvm, + enum kvm_apicv_inhibit reason) +{ + kvm_set_or_clear_apicv_inhibit(kvm, reason, true); +} -int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u64 error_code, +static inline void kvm_clear_apicv_inhibit(struct kvm *kvm, + enum kvm_apicv_inhibit reason) +{ + kvm_set_or_clear_apicv_inhibit(kvm, reason, false); +} + +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_print_sptes(struct kvm_vcpu *vcpu, gpa_t gpa, const char *msg); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva); +void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + u64 addr, unsigned long roots); void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid); -void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3, bool skip_tlb_flush); +void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd); -void kvm_enable_tdp(void); -void kvm_disable_tdp(void); +void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, + int tdp_max_root_level, int tdp_huge_page_level); -static inline gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, - struct x86_exception *exception) -{ - return gpa; -} -static inline struct kvm_mmu_page *page_header(hpa_t shadow_page) -{ - struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT); +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +#define kvm_arch_has_private_mem(kvm) ((kvm)->arch.has_private_mem) +#endif - return (struct kvm_mmu_page *)page_private(page); -} +#define kvm_arch_has_readonly_mem(kvm) (!(kvm)->arch.has_protected_state) static inline u16 kvm_read_ldt(void) { @@ -1441,16 +2330,11 @@ static inline unsigned long read_msr(unsigned long msr) { u64 value; - rdmsrl(msr, value); + rdmsrq(msr, value); return value; } #endif -static inline u32 get_rdx_init_val(void) -{ - return 0x600; /* P6 family */ -} - static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code) { kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); @@ -1470,113 +2354,90 @@ enum { TASK_SWITCH_GATE = 3, }; -#define HF_GIF_MASK (1 << 0) -#define HF_HIF_MASK (1 << 1) -#define HF_VINTR_MASK (1 << 2) -#define HF_NMI_MASK (1 << 3) -#define HF_IRET_MASK (1 << 4) -#define HF_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */ -#define HF_SMM_MASK (1 << 6) -#define HF_SMM_INSIDE_NMI_MASK (1 << 7) +#define HF_GUEST_MASK (1 << 0) /* VCPU is in guest-mode */ -#define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE -#define KVM_ADDRESS_SPACE_NUM 2 +#ifdef CONFIG_KVM_SMM +#define HF_SMM_MASK (1 << 1) +#define HF_SMM_INSIDE_NMI_MASK (1 << 2) -#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) +# define KVM_MAX_NR_ADDRESS_SPACES 2 +/* SMM is currently unsupported for guests with private memory. */ +# define kvm_arch_nr_memslot_as_ids(kvm) (kvm_arch_has_private_mem(kvm) ? 1 : 2) +# 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) +#else +# define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, 0) +#endif -/* - * Hardware virtualization extension instructions may fault if a - * reboot turns off virtualization while processes are running. - * Trap the fault and ignore the instruction if that happens. - */ -asmlinkage void kvm_spurious_fault(void); - -#define ____kvm_handle_fault_on_reboot(insn, cleanup_insn) \ - "666: " insn "\n\t" \ - "668: \n\t" \ - ".pushsection .fixup, \"ax\" \n" \ - "667: \n\t" \ - cleanup_insn "\n\t" \ - "cmpb $0, kvm_rebooting \n\t" \ - "jne 668b \n\t" \ - __ASM_SIZE(push) " $666b \n\t" \ - "jmp kvm_spurious_fault \n\t" \ - ".popsection \n\t" \ - _ASM_EXTABLE(666b, 667b) - -#define __kvm_handle_fault_on_reboot(insn) \ - ____kvm_handle_fault_on_reboot(insn, "") - -#define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); -int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); -int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); -int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); +int kvm_cpu_has_extint(struct kvm_vcpu *v); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); +int kvm_cpu_get_extint(struct kvm_vcpu *v); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); -void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu); int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, unsigned long ipi_bitmap_high, u32 min, unsigned long icr, int op_64_bit); -u64 kvm_get_arch_capabilities(void); -void kvm_define_shared_msr(unsigned index, u32 msr); -int kvm_set_shared_msr(unsigned index, u64 val, u64 mask); +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); +u64 kvm_get_user_return_msr(unsigned int slot); -u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc); +static inline bool kvm_is_supported_user_return_msr(u32 msr) +{ + return kvm_find_user_return_msr(msr) >= 0; +} + +u64 kvm_scale_tsc(u64 tsc, u64 ratio); u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc); +u64 kvm_calc_nested_tsc_offset(u64 l1_offset, u64 l2_offset, u64 l2_multiplier); +u64 kvm_calc_nested_tsc_multiplier(u64 l1_multiplier, u64 l2_multiplier); unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu); 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, +bool kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work); void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work); void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work); -bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu); +void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu); +bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu); extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu); int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err); -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); +void __user *__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); -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 */ + return (irq->delivery_mode == APIC_DM_FIXED || + irq->delivery_mode == APIC_DM_LOWEST); +} static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) { - if (kvm_x86_ops->vcpu_blocking) - kvm_x86_ops->vcpu_blocking(vcpu); + kvm_x86_call(vcpu_blocking)(vcpu); } static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) { - if (kvm_x86_ops->vcpu_unblocking) - kvm_x86_ops->vcpu_unblocking(vcpu); + kvm_x86_call(vcpu_unblocking)(vcpu); } -static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} - static inline int kvm_cpu_get_apicid(int mps_cpu) { #ifdef CONFIG_X86_LOCAL_APIC @@ -1587,7 +2448,37 @@ static inline int kvm_cpu_get_apicid(int mps_cpu) #endif } -#define put_smstate(type, buf, offset, val) \ - *(type *)((buf) + (offset) - 0x7e00) = val +int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages); + +#define KVM_CLOCK_VALID_FLAGS \ + (KVM_CLOCK_TSC_STABLE | KVM_CLOCK_REALTIME | KVM_CLOCK_HOST_TSC) + +#define KVM_X86_VALID_QUIRKS \ + (KVM_X86_QUIRK_LINT0_REENABLED | \ + KVM_X86_QUIRK_CD_NW_CLEARED | \ + KVM_X86_QUIRK_LAPIC_MMIO_HOLE | \ + KVM_X86_QUIRK_OUT_7E_INC_RIP | \ + KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT | \ + 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_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 + * initiated from long mode. KVM now sets bit 0 to indicate long mode, but the + * remaining 31 lower bits must be 0 to preserve ABI. + */ +#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 */ |