linux/arch/x86/include/uapi/asm/kvm.h

425 lines
8.3 KiB
C
Raw Normal View History

License cleanup: add SPDX license identifier to uapi header files with no license Many user space API headers are missing licensing information, which makes it hard for compliance tools to determine the correct license. By default are files without license information under the default license of the kernel, which is GPLV2. Marking them GPLV2 would exclude them from being included in non GPLV2 code, which is obviously not intended. The user space API headers fall under the syscall exception which is in the kernels COPYING file: NOTE! This copyright does *not* cover user programs that use kernel services by normal system calls - this is merely considered normal use of the kernel, and does *not* fall under the heading of "derived work". otherwise syscall usage would not be possible. Update the files which contain no license information with an SPDX license identifier. The chosen identifier is 'GPL-2.0 WITH Linux-syscall-note' which is the officially assigned identifier for the Linux syscall exception. SPDX license identifiers are a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. See the previous patch in this series for the methodology of how this patch was researched. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 14:08:43 +00:00
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _ASM_X86_KVM_H
#define _ASM_X86_KVM_H
/*
* KVM x86 specific structures and definitions
*
*/
#include <linux/types.h>
#include <linux/ioctl.h>
#define KVM_PIO_PAGE_OFFSET 1
#define KVM_COALESCED_MMIO_PAGE_OFFSET 2
#define DE_VECTOR 0
#define DB_VECTOR 1
#define BP_VECTOR 3
#define OF_VECTOR 4
#define BR_VECTOR 5
#define UD_VECTOR 6
#define NM_VECTOR 7
#define DF_VECTOR 8
#define TS_VECTOR 10
#define NP_VECTOR 11
#define SS_VECTOR 12
#define GP_VECTOR 13
#define PF_VECTOR 14
#define MF_VECTOR 16
#define AC_VECTOR 17
#define MC_VECTOR 18
#define XM_VECTOR 19
#define VE_VECTOR 20
/* Select x86 specific features in <linux/kvm.h> */
#define __KVM_HAVE_PIT
#define __KVM_HAVE_IOAPIC
#define __KVM_HAVE_IRQ_LINE
#define __KVM_HAVE_MSI
#define __KVM_HAVE_USER_NMI
#define __KVM_HAVE_GUEST_DEBUG
2009-02-25 09:22:28 +00:00
#define __KVM_HAVE_MSIX
#define __KVM_HAVE_MCE
#define __KVM_HAVE_PIT_STATE2
#define __KVM_HAVE_XEN_HVM
#define __KVM_HAVE_VCPU_EVENTS
#define __KVM_HAVE_DEBUGREGS
#define __KVM_HAVE_XSAVE
#define __KVM_HAVE_XCRS
#define __KVM_HAVE_READONLY_MEM
/* Architectural interrupt line count. */
#define KVM_NR_INTERRUPTS 256
struct kvm_memory_alias {
__u32 slot; /* this has a different namespace than memory slots */
__u32 flags;
__u64 guest_phys_addr;
__u64 memory_size;
__u64 target_phys_addr;
};
/* for KVM_GET_IRQCHIP and KVM_SET_IRQCHIP */
struct kvm_pic_state {
__u8 last_irr; /* edge detection */
__u8 irr; /* interrupt request register */
__u8 imr; /* interrupt mask register */
__u8 isr; /* interrupt service register */
__u8 priority_add; /* highest irq priority */
__u8 irq_base;
__u8 read_reg_select;
__u8 poll;
__u8 special_mask;
__u8 init_state;
__u8 auto_eoi;
__u8 rotate_on_auto_eoi;
__u8 special_fully_nested_mode;
__u8 init4; /* true if 4 byte init */
__u8 elcr; /* PIIX edge/trigger selection */
__u8 elcr_mask;
};
#define KVM_IOAPIC_NUM_PINS 24
struct kvm_ioapic_state {
__u64 base_address;
__u32 ioregsel;
__u32 id;
__u32 irr;
__u32 pad;
union {
__u64 bits;
struct {
__u8 vector;
__u8 delivery_mode:3;
__u8 dest_mode:1;
__u8 delivery_status:1;
__u8 polarity:1;
__u8 remote_irr:1;
__u8 trig_mode:1;
__u8 mask:1;
__u8 reserve:7;
__u8 reserved[4];
__u8 dest_id;
} fields;
} redirtbl[KVM_IOAPIC_NUM_PINS];
};
#define KVM_IRQCHIP_PIC_MASTER 0
#define KVM_IRQCHIP_PIC_SLAVE 1
#define KVM_IRQCHIP_IOAPIC 2
#define KVM_NR_IRQCHIPS 3
#define KVM_RUN_X86_SMM (1 << 0)
/* for KVM_GET_REGS and KVM_SET_REGS */
struct kvm_regs {
/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
__u64 rax, rbx, rcx, rdx;
__u64 rsi, rdi, rsp, rbp;
__u64 r8, r9, r10, r11;
__u64 r12, r13, r14, r15;
__u64 rip, rflags;
};
/* for KVM_GET_LAPIC and KVM_SET_LAPIC */
#define KVM_APIC_REG_SIZE 0x400
struct kvm_lapic_state {
char regs[KVM_APIC_REG_SIZE];
};
struct kvm_segment {
__u64 base;
__u32 limit;
__u16 selector;
__u8 type;
__u8 present, dpl, db, s, l, g, avl;
__u8 unusable;
__u8 padding;
};
struct kvm_dtable {
__u64 base;
__u16 limit;
__u16 padding[3];
};
/* for KVM_GET_SREGS and KVM_SET_SREGS */
struct kvm_sregs {
/* out (KVM_GET_SREGS) / in (KVM_SET_SREGS) */
struct kvm_segment cs, ds, es, fs, gs, ss;
struct kvm_segment tr, ldt;
struct kvm_dtable gdt, idt;
__u64 cr0, cr2, cr3, cr4, cr8;
__u64 efer;
__u64 apic_base;
__u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64];
};
/* for KVM_GET_FPU and KVM_SET_FPU */
struct kvm_fpu {
__u8 fpr[8][16];
__u16 fcw;
__u16 fsw;
__u8 ftwx; /* in fxsave format */
__u8 pad1;
__u16 last_opcode;
__u64 last_ip;
__u64 last_dp;
__u8 xmm[16][16];
__u32 mxcsr;
__u32 pad2;
};
struct kvm_msr_entry {
__u32 index;
__u32 reserved;
__u64 data;
};
/* for KVM_GET_MSRS and KVM_SET_MSRS */
struct kvm_msrs {
__u32 nmsrs; /* number of msrs in entries */
__u32 pad;
struct kvm_msr_entry entries[0];
};
/* for KVM_GET_MSR_INDEX_LIST */
struct kvm_msr_list {
__u32 nmsrs; /* number of msrs in entries */
__u32 indices[0];
};
struct kvm_cpuid_entry {
__u32 function;
__u32 eax;
__u32 ebx;
__u32 ecx;
__u32 edx;
__u32 padding;
};
/* for KVM_SET_CPUID */
struct kvm_cpuid {
__u32 nent;
__u32 padding;
struct kvm_cpuid_entry entries[0];
};
struct kvm_cpuid_entry2 {
__u32 function;
__u32 index;
__u32 flags;
__u32 eax;
__u32 ebx;
__u32 ecx;
__u32 edx;
__u32 padding[3];
};
#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX (1 << 0)
#define KVM_CPUID_FLAG_STATEFUL_FUNC (1 << 1)
#define KVM_CPUID_FLAG_STATE_READ_NEXT (1 << 2)
/* for KVM_SET_CPUID2 */
struct kvm_cpuid2 {
__u32 nent;
__u32 padding;
struct kvm_cpuid_entry2 entries[0];
};
/* for KVM_GET_PIT and KVM_SET_PIT */
struct kvm_pit_channel_state {
__u32 count; /* can be 65536 */
__u16 latched_count;
__u8 count_latched;
__u8 status_latched;
__u8 status;
__u8 read_state;
__u8 write_state;
__u8 write_latch;
__u8 rw_mode;
__u8 mode;
__u8 bcd;
__u8 gate;
__s64 count_load_time;
};
struct kvm_debug_exit_arch {
__u32 exception;
__u32 pad;
__u64 pc;
__u64 dr6;
__u64 dr7;
};
#define KVM_GUESTDBG_USE_SW_BP 0x00010000
#define KVM_GUESTDBG_USE_HW_BP 0x00020000
#define KVM_GUESTDBG_INJECT_DB 0x00040000
#define KVM_GUESTDBG_INJECT_BP 0x00080000
/* for KVM_SET_GUEST_DEBUG */
struct kvm_guest_debug_arch {
__u64 debugreg[8];
};
struct kvm_pit_state {
struct kvm_pit_channel_state channels[3];
};
#define KVM_PIT_FLAGS_HPET_LEGACY 0x00000001
struct kvm_pit_state2 {
struct kvm_pit_channel_state channels[3];
__u32 flags;
__u32 reserved[9];
};
struct kvm_reinject_control {
__u8 pit_reinject;
__u8 reserved[31];
};
/* When set in flags, include corresponding fields on KVM_SET_VCPU_EVENTS */
#define KVM_VCPUEVENT_VALID_NMI_PENDING 0x00000001
#define KVM_VCPUEVENT_VALID_SIPI_VECTOR 0x00000002
#define KVM_VCPUEVENT_VALID_SHADOW 0x00000004
#define KVM_VCPUEVENT_VALID_SMM 0x00000008
#define KVM_VCPUEVENT_VALID_PAYLOAD 0x00000010
/* Interrupt shadow states */
#define KVM_X86_SHADOW_INT_MOV_SS 0x01
#define KVM_X86_SHADOW_INT_STI 0x02
/* for KVM_GET/SET_VCPU_EVENTS */
struct kvm_vcpu_events {
struct {
__u8 injected;
__u8 nr;
__u8 has_error_code;
__u8 pending;
__u32 error_code;
} exception;
struct {
__u8 injected;
__u8 nr;
__u8 soft;
__u8 shadow;
} interrupt;
struct {
__u8 injected;
__u8 pending;
__u8 masked;
__u8 pad;
} nmi;
__u32 sipi_vector;
__u32 flags;
struct {
__u8 smm;
__u8 pending;
__u8 smm_inside_nmi;
__u8 latched_init;
} smi;
__u8 reserved[27];
__u8 exception_has_payload;
__u64 exception_payload;
};
/* for KVM_GET/SET_DEBUGREGS */
struct kvm_debugregs {
__u64 db[4];
__u64 dr6;
__u64 dr7;
__u64 flags;
__u64 reserved[9];
};
/* for KVM_CAP_XSAVE */
struct kvm_xsave {
__u32 region[1024];
};
#define KVM_MAX_XCRS 16
struct kvm_xcr {
__u32 xcr;
__u32 reserved;
__u64 value;
};
struct kvm_xcrs {
__u32 nr_xcrs;
__u32 flags;
struct kvm_xcr xcrs[KVM_MAX_XCRS];
__u64 padding[16];
};
#define KVM_SYNC_X86_REGS (1UL << 0)
#define KVM_SYNC_X86_SREGS (1UL << 1)
#define KVM_SYNC_X86_EVENTS (1UL << 2)
#define KVM_SYNC_X86_VALID_FIELDS \
(KVM_SYNC_X86_REGS| \
KVM_SYNC_X86_SREGS| \
KVM_SYNC_X86_EVENTS)
/* kvm_sync_regs struct included by kvm_run struct */
struct kvm_sync_regs {
/* Members of this structure are potentially malicious.
* Care must be taken by code reading, esp. interpreting,
* data fields from them inside KVM to prevent TOCTOU and
* double-fetch types of vulnerabilities.
*/
struct kvm_regs regs;
struct kvm_sregs sregs;
struct kvm_vcpu_events events;
};
#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0)
#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1)
x86/kvm/lapic: always disable MMIO interface in x2APIC mode When VMX is used with flexpriority disabled (because of no support or if disabled with module parameter) MMIO interface to lAPIC is still available in x2APIC mode while it shouldn't be (kvm-unit-tests): PASS: apic_disable: Local apic enabled in x2APIC mode PASS: apic_disable: CPUID.1H:EDX.APIC[bit 9] is set FAIL: apic_disable: *0xfee00030: 50014 The issue appears because we basically do nothing while switching to x2APIC mode when APIC access page is not used. apic_mmio_{read,write} only check if lAPIC is disabled before proceeding to actual write. When APIC access is virtualized we correctly manipulate with VMX controls in vmx_set_virtual_apic_mode() and we don't get vmexits from memory writes in x2APIC mode so there's no issue. Disabling MMIO interface seems to be easy. The question is: what do we do with these reads and writes? If we add apic_x2apic_mode() check to apic_mmio_in_range() and return -EOPNOTSUPP these reads and writes will go to userspace. When lAPIC is in kernel, Qemu uses this interface to inject MSIs only (see kvm_apic_mem_write() in hw/i386/kvm/apic.c). This somehow works with disabled lAPIC but when we're in xAPIC mode we will get a real injected MSI from every write to lAPIC. Not good. The simplest solution seems to be to just ignore writes to the region and return ~0 for all reads when we're in x2APIC mode. This is what this patch does. However, this approach is inconsistent with what currently happens when flexpriority is enabled: we allocate APIC access page and create KVM memory region so in x2APIC modes all reads and writes go to this pre-allocated page which is, btw, the same for all vCPUs. Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2018-08-02 15:08:16 +00:00
#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2)
#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3)
#define KVM_STATE_NESTED_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_RUN_PENDING 0x00000002
#define KVM_STATE_NESTED_EVMCS 0x00000004
#define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_SMM_VMXON 0x00000002
struct kvm_vmx_nested_state {
__u64 vmxon_pa;
__u64 vmcs_pa;
struct {
__u16 flags;
} smm;
};
/* for KVM_CAP_NESTED_STATE */
struct kvm_nested_state {
/* KVM_STATE_* flags */
__u16 flags;
/* 0 for VMX, 1 for SVM. */
__u16 format;
/* 128 for SVM, 128 + VMCS size for VMX. */
__u32 size;
union {
/* VMXON, VMCS */
struct kvm_vmx_nested_state vmx;
/* Pad the header to 128 bytes. */
__u8 pad[120];
};
__u8 data[0];
};
#endif /* _ASM_X86_KVM_H */