Adding upstream version 6.7.7.upstream/6.7.7

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

4 files changed, 46 insertions, 42 deletions

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 4900c07804..6ee925d666 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2972,6 +2972,25 @@ static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm)
 
 		set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux);
 	}
+
+	/*
+	 * For SEV-ES, accesses to MSR_IA32_XSS should not be intercepted if
+	 * the host/guest supports its use.
+	 *
+	 * guest_can_use() checks a number of requirements on the host/guest to
+	 * ensure that MSR_IA32_XSS is available, but it might report true even
+	 * if X86_FEATURE_XSAVES isn't configured in the guest to ensure host
+	 * MSR_IA32_XSS is always properly restored. For SEV-ES, it is better
+	 * to further check that the guest CPUID actually supports
+	 * X86_FEATURE_XSAVES so that accesses to MSR_IA32_XSS by misbehaved
+	 * guests will still get intercepted and caught in the normal
+	 * kvm_emulate_rdmsr()/kvm_emulated_wrmsr() paths.
+	 */
+	if (guest_can_use(vcpu, X86_FEATURE_XSAVES) &&
+	    guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))
+		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 1, 1);
+	else
+		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 0, 0);
 }
 
 void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 77f1eeefcd..a8bd4e909a 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -103,6 +103,7 @@ static const struct svm_direct_access_msrs {
 	{ .index = MSR_IA32_LASTBRANCHTOIP,		.always = false },
 	{ .index = MSR_IA32_LASTINTFROMIP,		.always = false },
 	{ .index = MSR_IA32_LASTINTTOIP,		.always = false },
+	{ .index = MSR_IA32_XSS,			.always = false },
 	{ .index = MSR_EFER,				.always = false },
 	{ .index = MSR_IA32_CR_PAT,			.always = false },
 	{ .index = MSR_AMD64_SEV_ES_GHCB,		.always = true  },
@@ -199,7 +200,7 @@ module_param_named(npt, npt_enabled, bool, 0444);
 
 /* allow nested virtualization in KVM/SVM */
 static int nested = true;
-module_param(nested, int, S_IRUGO);
+module_param(nested, int, 0444);
 
 /* enable/disable Next RIP Save */
 int nrips = true;
@@ -364,8 +365,6 @@ static void svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
 		svm->vmcb->control.int_state |= SVM_INTERRUPT_SHADOW_MASK;
 
 }
-static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
-					void *insn, int insn_len);
 
 static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu,
 					   bool commit_side_effects)
@@ -386,14 +385,6 @@ static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu,
 	}
 
 	if (!svm->next_rip) {
-		/*
-		 * FIXME: Drop this when kvm_emulate_instruction() does the
-		 * right thing and treats "can't emulate" as outright failure
-		 * for EMULTYPE_SKIP.
-		 */
-		if (!svm_can_emulate_instruction(vcpu, EMULTYPE_SKIP, NULL, 0))
-			return 0;
-
 		if (unlikely(!commit_side_effects))
 			old_rflags = svm->vmcb->save.rflags;
 
@@ -531,8 +522,6 @@ static bool __kvm_is_svm_supported(void)
 	int cpu = smp_processor_id();
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-	u64 vm_cr;
-
 	if (c->x86_vendor != X86_VENDOR_AMD &&
 	    c->x86_vendor != X86_VENDOR_HYGON) {
 		pr_err("CPU %d isn't AMD or Hygon\n", cpu);
@@ -549,12 +538,6 @@ static bool __kvm_is_svm_supported(void)
 		return false;
 	}
 
-	rdmsrl(MSR_VM_CR, vm_cr);
-	if (vm_cr & (1 << SVM_VM_CR_SVM_DISABLE)) {
-		pr_err("SVM disabled (by BIOS) in MSR_VM_CR on CPU %d\n", cpu);
-		return false;
-	}
-
 	return true;
 }
 
@@ -2204,12 +2187,6 @@ static int shutdown_interception(struct kvm_vcpu *vcpu)
 	struct kvm_run *kvm_run = vcpu->run;
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	/*
-	 * The VM save area has already been encrypted so it
-	 * cannot be reinitialized - just terminate.
-	 */
-	if (sev_es_guest(vcpu->kvm))
-		return -EINVAL;
 
 	/*
 	 * VMCB is undefined after a SHUTDOWN intercept.  INIT the vCPU to put
@@ -2218,9 +2195,14 @@ static int shutdown_interception(struct kvm_vcpu *vcpu)
 	 * userspace.  At a platform view, INIT is acceptable behavior as
 	 * there exist bare metal platforms that automatically INIT the CPU
 	 * in response to shutdown.
+	 *
+	 * The VM save area for SEV-ES guests has already been encrypted so it
+	 * cannot be reinitialized, i.e. synthesizing INIT is futile.
 	 */
-	clear_page(svm->vmcb);
-	kvm_vcpu_reset(vcpu, true);
+	if (!sev_es_guest(vcpu->kvm)) {
+		clear_page(svm->vmcb);
+		kvm_vcpu_reset(vcpu, true);
+	}
 
 	kvm_run->exit_reason = KVM_EXIT_SHUTDOWN;
 	return 0;
@@ -4729,15 +4711,15 @@ static void svm_enable_smi_window(struct kvm_vcpu *vcpu)
 }
 #endif
 
-static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
-					void *insn, int insn_len)
+static int svm_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
+					 void *insn, int insn_len)
 {
 	bool smep, smap, is_user;
 	u64 error_code;
 
 	/* Emulation is always possible when KVM has access to all guest state. */
 	if (!sev_guest(vcpu->kvm))
-		return true;
+		return X86EMUL_CONTINUE;
 
 	/* #UD and #GP should never be intercepted for SEV guests. */
 	WARN_ON_ONCE(emul_type & (EMULTYPE_TRAP_UD |
@@ -4749,14 +4731,14 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
 	 * to guest register state.
 	 */
 	if (sev_es_guest(vcpu->kvm))
-		return false;
+		return X86EMUL_RETRY_INSTR;
 
 	/*
 	 * Emulation is possible if the instruction is already decoded, e.g.
 	 * when completing I/O after returning from userspace.
 	 */
 	if (emul_type & EMULTYPE_NO_DECODE)
-		return true;
+		return X86EMUL_CONTINUE;
 
 	/*
 	 * Emulation is possible for SEV guests if and only if a prefilled
@@ -4782,9 +4764,11 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
 	 * success (and in practice it will work the vast majority of the time).
 	 */
 	if (unlikely(!insn)) {
-		if (!(emul_type & EMULTYPE_SKIP))
-			kvm_queue_exception(vcpu, UD_VECTOR);
-		return false;
+		if (emul_type & EMULTYPE_SKIP)
+			return X86EMUL_UNHANDLEABLE;
+
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return X86EMUL_PROPAGATE_FAULT;
 	}
 
 	/*
@@ -4795,7 +4779,7 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
 	 * table used to translate CS:RIP resides in emulated MMIO.
 	 */
 	if (likely(insn_len))
-		return true;
+		return X86EMUL_CONTINUE;
 
 	/*
 	 * Detect and workaround Errata 1096 Fam_17h_00_0Fh.
@@ -4853,6 +4837,7 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
 			kvm_inject_gp(vcpu, 0);
 		else
 			kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
+		return X86EMUL_PROPAGATE_FAULT;
 	}
 
 resume_guest:
@@ -4870,7 +4855,7 @@ resume_guest:
 	 * doesn't explicitly define "ignored", i.e. doing nothing and letting
 	 * the guest spin is technically "ignoring" the access.
 	 */
-	return false;
+	return X86EMUL_RETRY_INSTR;
 }
 
 static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
@@ -5030,7 +5015,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.vm_copy_enc_context_from = sev_vm_copy_enc_context_from,
 	.vm_move_enc_context_from = sev_vm_move_enc_context_from,
 
-	.can_emulate_instruction = svm_can_emulate_instruction,
+	.check_emulate_instruction = svm_check_emulate_instruction,
 
 	.apic_init_signal_blocked = svm_apic_init_signal_blocked,
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index be67ab7fdd..c409f934c3 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -30,7 +30,7 @@
 #define	IOPM_SIZE PAGE_SIZE * 3
 #define	MSRPM_SIZE PAGE_SIZE * 2
 
-#define MAX_DIRECT_ACCESS_MSRS	46
+#define MAX_DIRECT_ACCESS_MSRS	47
 #define MSRPM_OFFSETS	32
 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
 extern bool npt_enabled;
diff --git a/arch/x86/kvm/svm/svm_ops.h b/arch/x86/kvm/svm/svm_ops.h
index 36c8af87a7..4e725854c6 100644
--- a/arch/x86/kvm/svm/svm_ops.h
+++ b/arch/x86/kvm/svm/svm_ops.h
@@ -8,7 +8,7 @@
 
 #define svm_asm(insn, clobber...)				\
 do {								\
-	asm_volatile_goto("1: " __stringify(insn) "\n\t"	\
+	asm goto("1: " __stringify(insn) "\n\t"	\
 			  _ASM_EXTABLE(1b, %l[fault])		\
 			  ::: clobber : fault);			\
 	return;							\
@@ -18,7 +18,7 @@ fault:								\
 
 #define svm_asm1(insn, op1, clobber...)				\
 do {								\
-	asm_volatile_goto("1: "  __stringify(insn) " %0\n\t"	\
+	asm goto("1: "  __stringify(insn) " %0\n\t"	\
 			  _ASM_EXTABLE(1b, %l[fault])		\
 			  :: op1 : clobber : fault);		\
 	return;							\
@@ -28,7 +28,7 @@ fault:								\
 
 #define svm_asm2(insn, op1, op2, clobber...)				\
 do {									\
-	asm_volatile_goto("1: "  __stringify(insn) " %1, %0\n\t"	\
+	asm goto("1: "  __stringify(insn) " %1, %0\n\t"	\
 			  _ASM_EXTABLE(1b, %l[fault])			\
 			  :: op1, op2 : clobber : fault);		\
 	return;								\