linux_dsm_epyc7002/arch/x86/kvm/x86.h
Sean Christopherson de761ea792 KVM: x86: Perform non-canonical checks in 32-bit KVM
Remove the CONFIG_X86_64 condition from the low level non-canonical
helpers to effectively enable non-canonical checks on 32-bit KVM.
Non-canonical checks are performed by hardware if the CPU *supports*
64-bit mode, whether or not the CPU is actually in 64-bit mode is
irrelevant.

For the most part, skipping non-canonical checks on 32-bit KVM is ok-ish
because 32-bit KVM always (hopefully) drops bits 63:32 of whatever value
it's checking before propagating it to hardware, and architecturally,
the expected behavior for the guest is a bit of a grey area since the
vCPU itself doesn't support 64-bit mode.  I.e. a 32-bit KVM guest can
observe the missed checks in several paths, e.g. INVVPID and VM-Enter,
but it's debatable whether or not the missed checks constitute a bug
because technically the vCPU doesn't support 64-bit mode.

The primary motivation for enabling the non-canonical checks is defense
in depth.  As mentioned above, a guest can trigger a missed check via
INVVPID or VM-Enter.  INVVPID is straightforward as it takes a 64-bit
virtual address as part of its 128-bit INVVPID descriptor and fails if
the address is non-canonical, even if INVVPID is executed in 32-bit PM.
Nested VM-Enter is a bit more convoluted as it requires the guest to
write natural width VMCS fields via memory accesses and then VMPTRLD the
VMCS, but it's still possible.  In both cases, KVM is saved from a true
bug only because its flows that propagate values to hardware (correctly)
take "unsigned long" parameters and so drop bits 63:32 of the bad value.

Explicitly performing the non-canonical checks makes it less likely that
a bad value will be propagated to hardware, e.g. in the INVVPID case,
if __invvpid() didn't implicitly drop bits 63:32 then KVM would BUG() on
the resulting unexpected INVVPID failure due to hardware rejecting the
non-canonical address.

The only downside to enabling the non-canonical checks is that it adds a
relatively small amount of overhead, but the affected flows are not hot
paths, i.e. the overhead is negligible.

Note, KVM technically could gate the non-canonical checks on 32-bit KVM
with static_cpu_has(X86_FEATURE_LM), but on bare metal that's an even
bigger waste of code for everyone except the 0.00000000000001% of the
population running on Yonah, and nested 32-bit on 64-bit already fudges
things with respect to 64-bit CPU behavior.

Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
[Also do so in nested_vmx_check_host_state as reported by Krish. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2020-01-27 19:59:50 +01:00

365 lines
8.9 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef ARCH_X86_KVM_X86_H
#define ARCH_X86_KVM_X86_H
#include <linux/kvm_host.h>
#include <asm/pvclock.h>
#include "kvm_cache_regs.h"
#define KVM_DEFAULT_PLE_GAP 128
#define KVM_VMX_DEFAULT_PLE_WINDOW 4096
#define KVM_DEFAULT_PLE_WINDOW_GROW 2
#define KVM_DEFAULT_PLE_WINDOW_SHRINK 0
#define KVM_VMX_DEFAULT_PLE_WINDOW_MAX UINT_MAX
#define KVM_SVM_DEFAULT_PLE_WINDOW_MAX USHRT_MAX
#define KVM_SVM_DEFAULT_PLE_WINDOW 3000
static inline unsigned int __grow_ple_window(unsigned int val,
unsigned int base, unsigned int modifier, unsigned int max)
{
u64 ret = val;
if (modifier < 1)
return base;
if (modifier < base)
ret *= modifier;
else
ret += modifier;
return min(ret, (u64)max);
}
static inline unsigned int __shrink_ple_window(unsigned int val,
unsigned int base, unsigned int modifier, unsigned int min)
{
if (modifier < 1)
return base;
if (modifier < base)
val /= modifier;
else
val -= modifier;
return max(val, min);
}
#define MSR_IA32_CR_PAT_DEFAULT 0x0007040600070406ULL
static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu)
{
vcpu->arch.exception.pending = false;
vcpu->arch.exception.injected = false;
}
static inline void kvm_queue_interrupt(struct kvm_vcpu *vcpu, u8 vector,
bool soft)
{
vcpu->arch.interrupt.injected = true;
vcpu->arch.interrupt.soft = soft;
vcpu->arch.interrupt.nr = vector;
}
static inline void kvm_clear_interrupt_queue(struct kvm_vcpu *vcpu)
{
vcpu->arch.interrupt.injected = false;
}
static inline bool kvm_event_needs_reinjection(struct kvm_vcpu *vcpu)
{
return vcpu->arch.exception.injected || vcpu->arch.interrupt.injected ||
vcpu->arch.nmi_injected;
}
static inline bool kvm_exception_is_soft(unsigned int nr)
{
return (nr == BP_VECTOR) || (nr == OF_VECTOR);
}
static inline bool is_protmode(struct kvm_vcpu *vcpu)
{
return kvm_read_cr0_bits(vcpu, X86_CR0_PE);
}
static inline int is_long_mode(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_X86_64
return vcpu->arch.efer & EFER_LMA;
#else
return 0;
#endif
}
static inline bool is_64_bit_mode(struct kvm_vcpu *vcpu)
{
int cs_db, cs_l;
if (!is_long_mode(vcpu))
return false;
kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
return cs_l;
}
static inline bool is_la57_mode(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_X86_64
return (vcpu->arch.efer & EFER_LMA) &&
kvm_read_cr4_bits(vcpu, X86_CR4_LA57);
#else
return 0;
#endif
}
static inline bool x86_exception_has_error_code(unsigned int vector)
{
static u32 exception_has_error_code = BIT(DF_VECTOR) | BIT(TS_VECTOR) |
BIT(NP_VECTOR) | BIT(SS_VECTOR) | BIT(GP_VECTOR) |
BIT(PF_VECTOR) | BIT(AC_VECTOR);
return (1U << vector) & exception_has_error_code;
}
static inline bool mmu_is_nested(struct kvm_vcpu *vcpu)
{
return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu;
}
static inline int is_pae(struct kvm_vcpu *vcpu)
{
return kvm_read_cr4_bits(vcpu, X86_CR4_PAE);
}
static inline int is_pse(struct kvm_vcpu *vcpu)
{
return kvm_read_cr4_bits(vcpu, X86_CR4_PSE);
}
static inline int is_paging(struct kvm_vcpu *vcpu)
{
return likely(kvm_read_cr0_bits(vcpu, X86_CR0_PG));
}
static inline bool is_pae_paging(struct kvm_vcpu *vcpu)
{
return !is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu);
}
static inline u8 vcpu_virt_addr_bits(struct kvm_vcpu *vcpu)
{
return kvm_read_cr4_bits(vcpu, X86_CR4_LA57) ? 57 : 48;
}
static inline u8 ctxt_virt_addr_bits(struct x86_emulate_ctxt *ctxt)
{
return (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_LA57) ? 57 : 48;
}
static inline u64 get_canonical(u64 la, u8 vaddr_bits)
{
return ((int64_t)la << (64 - vaddr_bits)) >> (64 - vaddr_bits);
}
static inline bool is_noncanonical_address(u64 la, struct kvm_vcpu *vcpu)
{
return get_canonical(la, vcpu_virt_addr_bits(vcpu)) != la;
}
static inline bool emul_is_noncanonical_address(u64 la,
struct x86_emulate_ctxt *ctxt)
{
return get_canonical(la, ctxt_virt_addr_bits(ctxt)) != la;
}
static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu,
gva_t gva, gfn_t gfn, unsigned access)
{
u64 gen = kvm_memslots(vcpu->kvm)->generation;
if (unlikely(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS))
return;
/*
* If this is a shadow nested page table, the "GVA" is
* actually a nGPA.
*/
vcpu->arch.mmio_gva = mmu_is_nested(vcpu) ? 0 : gva & PAGE_MASK;
vcpu->arch.mmio_access = access;
vcpu->arch.mmio_gfn = gfn;
vcpu->arch.mmio_gen = gen;
}
static inline bool vcpu_match_mmio_gen(struct kvm_vcpu *vcpu)
{
return vcpu->arch.mmio_gen == kvm_memslots(vcpu->kvm)->generation;
}
/*
* Clear the mmio cache info for the given gva. If gva is MMIO_GVA_ANY, we
* clear all mmio cache info.
*/
#define MMIO_GVA_ANY (~(gva_t)0)
static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva)
{
if (gva != MMIO_GVA_ANY && vcpu->arch.mmio_gva != (gva & PAGE_MASK))
return;
vcpu->arch.mmio_gva = 0;
}
static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva)
{
if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gva &&
vcpu->arch.mmio_gva == (gva & PAGE_MASK))
return true;
return false;
}
static inline bool vcpu_match_mmio_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
{
if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gfn &&
vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT)
return true;
return false;
}
static inline unsigned long kvm_register_readl(struct kvm_vcpu *vcpu, int reg)
{
unsigned long val = kvm_register_read(vcpu, reg);
return is_64_bit_mode(vcpu) ? val : (u32)val;
}
static inline void kvm_register_writel(struct kvm_vcpu *vcpu,
int reg, unsigned long val)
{
if (!is_64_bit_mode(vcpu))
val = (u32)val;
return kvm_register_write(vcpu, reg, val);
}
static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk)
{
return !(kvm->arch.disabled_quirks & quirk);
}
static inline bool kvm_vcpu_latch_init(struct kvm_vcpu *vcpu)
{
return is_smm(vcpu) || kvm_x86_ops->apic_init_signal_blocked(vcpu);
}
void kvm_set_pending_timer(struct kvm_vcpu *vcpu);
void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip);
void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr);
u64 get_kvmclock_ns(struct kvm *kvm);
int kvm_read_guest_virt(struct kvm_vcpu *vcpu,
gva_t addr, void *val, unsigned int bytes,
struct x86_exception *exception);
int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu,
gva_t addr, void *val, unsigned int bytes,
struct x86_exception *exception);
int handle_ud(struct kvm_vcpu *vcpu);
void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu);
void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu);
u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn);
bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data);
int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data);
int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn,
int page_num);
bool kvm_vector_hashing_enabled(void);
int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
int emulation_type, void *insn, int insn_len);
enum exit_fastpath_completion handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu);
#define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \
| XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \
| XFEATURE_MASK_BNDCSR | XFEATURE_MASK_AVX512 \
| XFEATURE_MASK_PKRU)
extern u64 host_xcr0;
extern u64 kvm_supported_xcr0(void);
extern unsigned int min_timer_period_us;
extern bool enable_vmware_backdoor;
extern int pi_inject_timer;
extern struct static_key kvm_no_apic_vcpu;
static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
{
return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult,
vcpu->arch.virtual_tsc_shift);
}
/* Same "calling convention" as do_div:
* - divide (n << 32) by base
* - put result in n
* - return remainder
*/
#define do_shl32_div32(n, base) \
({ \
u32 __quot, __rem; \
asm("divl %2" : "=a" (__quot), "=d" (__rem) \
: "rm" (base), "0" (0), "1" ((u32) n)); \
n = __quot; \
__rem; \
})
static inline bool kvm_mwait_in_guest(struct kvm *kvm)
{
return kvm->arch.mwait_in_guest;
}
static inline bool kvm_hlt_in_guest(struct kvm *kvm)
{
return kvm->arch.hlt_in_guest;
}
static inline bool kvm_pause_in_guest(struct kvm *kvm)
{
return kvm->arch.pause_in_guest;
}
static inline bool kvm_cstate_in_guest(struct kvm *kvm)
{
return kvm->arch.cstate_in_guest;
}
DECLARE_PER_CPU(struct kvm_vcpu *, current_vcpu);
static inline void kvm_before_interrupt(struct kvm_vcpu *vcpu)
{
__this_cpu_write(current_vcpu, vcpu);
}
static inline void kvm_after_interrupt(struct kvm_vcpu *vcpu)
{
__this_cpu_write(current_vcpu, NULL);
}
static inline bool kvm_pat_valid(u64 data)
{
if (data & 0xF8F8F8F8F8F8F8F8ull)
return false;
/* 0, 1, 4, 5, 6, 7 are valid values. */
return (data | ((data & 0x0202020202020202ull) << 1)) == data;
}
void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu);
void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu);
u64 kvm_spec_ctrl_valid_bits(struct kvm_vcpu *vcpu);
#endif