@@ -298,6 +298,9 @@ enum x86_intercept_stage {
enum x86_intercept {
x86_intercept_none,
+ x86_intercept_cr_read,
+ x86_intercept_cr_write,
+ x86_intercept_clts,
x86_intercept_lmsw,
x86_intercept_smsw,
x86_intercept_lidt,
@@ -34,10 +34,25 @@
#define KVM_PIO_PAGE_OFFSET 1
#define KVM_COALESCED_MMIO_PAGE_OFFSET 2
+#define CR0_RESERVED_BITS \
+ (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
+ | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \
+ | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG))
+
#define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1)
#define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD))
#define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS | \
0xFFFFFF0000000000ULL)
+#define CR4_RESERVED_BITS \
+ (~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\
+ | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \
+ | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR \
+ | X86_CR4_OSXSAVE \
+ | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE))
+
+#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
+
+
#define INVALID_PAGE (~(hpa_t)0)
#define VALID_PAGE(x) ((x) != INVALID_PAGE)
@@ -2348,6 +2348,95 @@ static int em_mov(struct x86_emulate_ctxt *ctxt)
return X86EMUL_CONTINUE;
}
+static bool valid_cr(int nr)
+{
+ switch (nr) {
+ case 0:
+ case 2 ... 4:
+ case 8:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static int check_cr_read(struct x86_emulate_ctxt *ctxt)
+{
+ struct decode_cache *c = &ctxt->decode;
+
+ if (!valid_cr(c->modrm_reg))
+ return emulate_ud(ctxt);
+
+ return X86EMUL_CONTINUE;
+}
+
+static int check_cr_write(struct x86_emulate_ctxt *ctxt)
+{
+ struct decode_cache *c = &ctxt->decode;
+ u64 new_val = c->src.val64;
+ int cr = c->modrm_reg;
+
+ static u64 cr_reserved_bits[] = {
+ 0xffffffff00000000ULL,
+ 0, 0, 0, /* CR3 checked later */
+ CR4_RESERVED_BITS,
+ 0, 0, 0,
+ CR8_RESERVED_BITS,
+ };
+
+ if (!valid_cr(cr))
+ return emulate_ud(ctxt);
+
+ if (new_val & cr_reserved_bits[cr])
+ return emulate_gp(ctxt, 0);
+
+ switch (cr) {
+ case 0: {
+ u64 cr4, efer;
+ if (((new_val & X86_CR0_PG) && !(new_val & X86_CR0_PE)) ||
+ ((new_val & X86_CR0_NW) && !(new_val & X86_CR0_CD)))
+ return emulate_gp(ctxt, 0);
+
+ cr4 = ctxt->ops->get_cr(4, ctxt->vcpu);
+ ctxt->ops->get_msr(ctxt->vcpu, MSR_EFER, &efer);
+
+ if ((new_val & X86_CR0_PG) && (efer & EFER_LME) &&
+ !(cr4 & X86_CR4_PAE))
+ return emulate_gp(ctxt, 0);
+
+ break;
+ }
+ case 3: {
+ u64 rsvd = 0;
+
+ if (is_long_mode(ctxt->vcpu))
+ rsvd = CR3_L_MODE_RESERVED_BITS;
+ else if (is_pae(ctxt->vcpu))
+ rsvd = CR3_PAE_RESERVED_BITS;
+ else if (is_paging(ctxt->vcpu))
+ rsvd = CR3_NONPAE_RESERVED_BITS;
+
+ if (new_val & rsvd)
+ return emulate_gp(ctxt, 0);
+
+ break;
+ }
+ case 4: {
+ u64 cr4, efer;
+
+ cr4 = ctxt->ops->get_cr(4, ctxt->vcpu);
+ ctxt->ops->get_msr(ctxt->vcpu, MSR_EFER, &efer);
+
+ if ((efer & EFER_LMA) && !(new_val & X86_CR4_PAE))
+ return emulate_gp(ctxt, 0);
+
+ break;
+ }
+ }
+
+ return X86EMUL_CONTINUE;
+}
+
#define D(_y) { .flags = (_y) }
#define DI(_y, _i) { .flags = (_y), .intercept = x86_intercept_##_i }
#define DIP(_y, _i, _p) { .flags = (_y), .intercept = x86_intercept_##_i, \
@@ -2532,14 +2621,16 @@ static struct opcode opcode_table[256] = {
static struct opcode twobyte_table[256] = {
/* 0x00 - 0x0F */
N, GD(0, &group7), N, N,
- N, D(ImplicitOps | VendorSpecific), D(ImplicitOps | Priv), N,
+ N, D(ImplicitOps | VendorSpecific), DI(ImplicitOps | Priv, clts), N,
DI(ImplicitOps | Priv, invd), DI(ImplicitOps | Priv, wbinvd), N, N,
N, D(ImplicitOps | ModRM), N, N,
/* 0x10 - 0x1F */
N, N, N, N, N, N, N, N, D(ImplicitOps | ModRM), N, N, N, N, N, N, N,
/* 0x20 - 0x2F */
- D(ModRM | DstMem | Priv | Op3264), D(ModRM | DstMem | Priv | Op3264),
- D(ModRM | SrcMem | Priv | Op3264), D(ModRM | SrcMem | Priv | Op3264),
+ DIP(ModRM | DstMem | Priv | Op3264, cr_read, check_cr_read),
+ D(ModRM | DstMem | Priv | Op3264),
+ DIP(ModRM | SrcMem | Priv | Op3264, cr_write, check_cr_write),
+ D(ModRM | SrcMem | Priv | Op3264),
N, N, N, N,
N, N, N, N, N, N, N, N,
/* 0x30 - 0x3F */
@@ -3589,14 +3680,6 @@ twobyte_insn:
case 0x18: /* Grp16 (prefetch/nop) */
break;
case 0x20: /* mov cr, reg */
- switch (c->modrm_reg) {
- case 1:
- case 5 ... 7:
- case 9 ... 15:
- emulate_ud(ctxt);
- rc = X86EMUL_PROPAGATE_FAULT;
- goto done;
- }
c->dst.val = ops->get_cr(c->modrm_reg, ctxt->vcpu);
break;
case 0x21: /* mov from dr to reg */
@@ -3868,11 +3868,90 @@ static void svm_fpu_deactivate(struct kvm_vcpu *vcpu)
update_cr0_intercept(svm);
}
+#define POST_EX(exit) { .exit_code = (exit), \
+ .stage = X86_ICPT_POST_EXCEPT, \
+ .valid = true }
+
+static struct __x86_intercept {
+ u32 exit_code;
+ enum x86_intercept_stage stage;
+ bool valid;
+} x86_intercept_map[] = {
+ [x86_intercept_cr_read] = POST_EX(SVM_EXIT_READ_CR0),
+ [x86_intercept_cr_write] = POST_EX(SVM_EXIT_WRITE_CR0),
+ [x86_intercept_clts] = POST_EX(SVM_EXIT_WRITE_CR0),
+ [x86_intercept_lmsw] = POST_EX(SVM_EXIT_WRITE_CR0),
+ [x86_intercept_smsw] = POST_EX(SVM_EXIT_READ_CR0),
+};
+
+#undef POST_EX
+
static int svm_check_intercept(struct kvm_vcpu *vcpu,
struct x86_instruction_info *info,
enum x86_intercept_stage stage)
{
- return X86EMUL_CONTINUE;
+ struct vcpu_svm *svm = to_svm(vcpu);
+ int vmexit, ret = X86EMUL_CONTINUE;
+ struct __x86_intercept icpt_info;
+ struct vmcb *vmcb = svm->vmcb;
+
+ if (info->intercept >= ARRAY_SIZE(x86_intercept_map))
+ goto out;
+
+ icpt_info = x86_intercept_map[info->intercept];
+
+ if (!icpt_info.valid || stage != icpt_info.stage)
+ goto out;
+
+ switch (icpt_info.exit_code) {
+ case SVM_EXIT_READ_CR0:
+ if (info->intercept == x86_intercept_cr_read)
+ icpt_info.exit_code += info->modrm_reg;
+ break;
+ case SVM_EXIT_WRITE_CR0: {
+ unsigned long cr0, val;
+ u64 intercept;
+
+ if (info->intercept == x86_intercept_cr_write)
+ icpt_info.exit_code += info->modrm_reg;
+
+ if (icpt_info.exit_code != SVM_EXIT_WRITE_CR0)
+ break;
+
+ intercept = svm->nested.intercept;
+
+ if (!(intercept & (1ULL << INTERCEPT_SELECTIVE_CR0)))
+ break;
+
+ cr0 = vcpu->arch.cr0 & ~SVM_CR0_SELECTIVE_MASK;
+ val = info->src_val & ~SVM_CR0_SELECTIVE_MASK;
+
+ if (info->intercept == x86_intercept_lmsw) {
+ cr0 &= 0xfUL;
+ val &= 0xfUL;
+ /* lmsw can't clear PE - catch this here */
+ if (cr0 & X86_CR0_PE)
+ val |= X86_CR0_PE;
+ }
+
+ if (cr0 ^ val)
+ icpt_info.exit_code = SVM_EXIT_CR0_SEL_WRITE;
+
+ break;
+ }
+ default:
+ break;
+ }
+
+ vmcb->control.next_rip = info->next_rip;
+ vmcb->control.exit_code = icpt_info.exit_code;
+ vmexit = nested_svm_exit_handled(svm);
+
+ ret = (vmexit == NESTED_EXIT_DONE) ? X86EMUL_INTERCEPTED
+ : X86EMUL_CONTINUE;
+
+out:
+ return ret;
}
static struct kvm_x86_ops svm_x86_ops = {
@@ -60,19 +60,6 @@
#include <asm/div64.h>
#define MAX_IO_MSRS 256
-#define CR0_RESERVED_BITS \
- (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
- | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \
- | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG))
-#define CR4_RESERVED_BITS \
- (~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\
- | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \
- | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR \
- | X86_CR4_OSXSAVE \
- | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE))
-
-#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
-
#define KVM_MAX_MCE_BANKS 32
#define KVM_MCE_CAP_SUPPORTED (MCG_CTL_P | MCG_SER_P)
This patch adds all necessary intercept checks for instructions that access the crX registers. Signed-off-by: Joerg Roedel <joerg.roedel@amd.com> --- arch/x86/include/asm/kvm_emulate.h | 3 + arch/x86/include/asm/kvm_host.h | 15 +++++ arch/x86/kvm/emulate.c | 105 ++++++++++++++++++++++++++++++++---- arch/x86/kvm/svm.c | 81 +++++++++++++++++++++++++++- arch/x86/kvm/x86.c | 13 ----- 5 files changed, 192 insertions(+), 25 deletions(-)