On Wed, 2021-08-11 at 15:29 +0300, Maxim Levitsky wrote:
> Currently #TS interception is only done once.
> Also exception interception is not enabled for SEV guests.
> 
> Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
> ---
>  arch/x86/include/asm/kvm_host.h |  2 +
>  arch/x86/kvm/svm/svm.c          | 70 +++++++++++++++++++++++++++++++++
>  arch/x86/kvm/svm/svm.h          |  6 ++-
>  arch/x86/kvm/x86.c              |  5 ++-
>  4 files changed, 80 insertions(+), 3 deletions(-)
> 
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 20daaf67a5bf..72fe03506018 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -1690,6 +1690,8 @@ 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_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, unsigned long payload);
> +void kvm_queue_exception_e_p(struct kvm_vcpu *vcpu, unsigned nr,
> +			     u32 error_code, unsigned long payload);
>  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_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
> diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
> index e45259177009..19f54b07161a 100644
> --- a/arch/x86/kvm/svm/svm.c
> +++ b/arch/x86/kvm/svm/svm.c
> @@ -233,6 +233,8 @@ static const u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000};
>  #define MSRS_RANGE_SIZE 2048
>  #define MSRS_IN_RANGE (MSRS_RANGE_SIZE * 8 / 2)
>  
> +static int svm_handle_invalid_exit(struct kvm_vcpu *vcpu, u64 exit_code);
> +
>  u32 svm_msrpm_offset(u32 msr)
>  {
>  	u32 offset;
> @@ -1153,6 +1155,22 @@ static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu,
>  	}
>  }
>  
> +static void svm_init_force_exceptions_intercepts(struct vcpu_svm *svm)
> +{
> +	int exc;
> +
> +	svm->force_intercept_exceptions_mask = force_intercept_exceptions_mask;
> +	for (exc = 0 ; exc < 32 ; exc++) {
> +		if (!(svm->force_intercept_exceptions_mask & (1 << exc)))
> +			continue;
> +
> +		/* Those are defined to have undefined behavior in the SVM spec */
> +		if (exc != 2 && exc != 9)
> +			continue;
> +		set_exception_intercept(svm, exc);

I made a mistake here, during one of the refactoring I think, after I finished
testing this througfully, and I noticed it now while looking again
at the code.

I attached a fix for this, and I also tested more carefully that the
feature works with selftests, kvm unit tests and by booting few VMs.

Best regards,
	Maxim Levitsky

> +	}
> +}
> +
>  static void init_vmcb(struct kvm_vcpu *vcpu)
>  {
>  	struct vcpu_svm *svm = to_svm(vcpu);
> @@ -1304,6 +1322,9 @@ static void init_vmcb(struct kvm_vcpu *vcpu)
>  
>  	enable_gif(svm);
>  
> +	if (!sev_es_guest(vcpu->kvm))
> +		svm_init_force_exceptions_intercepts(svm);
> +
>  }
>  
>  static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
> @@ -1892,6 +1913,17 @@ static int pf_interception(struct kvm_vcpu *vcpu)
>  	u64 fault_address = svm->vmcb->control.exit_info_2;
>  	u64 error_code = svm->vmcb->control.exit_info_1;
>  
> +	if ((svm->force_intercept_exceptions_mask & (1 << PF_VECTOR)))
> +		if (npt_enabled && !vcpu->arch.apf.host_apf_flags) {
> +			/* If the #PF was only intercepted for debug, inject
> +			 * it directly to the guest, since the kvm's mmu code
> +			 * is not ready to deal with such page faults.
> +			 */
> +			kvm_queue_exception_e_p(vcpu, PF_VECTOR,
> +						error_code, fault_address);
> +			return 1;
> +		}
> +
>  	return kvm_handle_page_fault(vcpu, error_code, fault_address,
>  			static_cpu_has(X86_FEATURE_DECODEASSISTS) ?
>  			svm->vmcb->control.insn_bytes : NULL,
> @@ -1967,6 +1999,40 @@ static int ac_interception(struct kvm_vcpu *vcpu)
>  	return 1;
>  }
>  
> +static int gen_exc_interception(struct kvm_vcpu *vcpu)
> +{
> +	/*
> +	 * Generic exception intercept handler which forwards a guest exception
> +	 * as-is to the guest.
> +	 * For exceptions that don't have a special intercept handler.
> +	 *
> +	 * Used only for 'force_intercept_exceptions_mask' KVM debug feature.
> +	 */
> +	struct vcpu_svm *svm = to_svm(vcpu);
> +	int exc = svm->vmcb->control.exit_code - SVM_EXIT_EXCP_BASE;
> +
> +	/* SVM doesn't provide us with an error code for the #DF */
> +	u32 err_code = exc == DF_VECTOR ? 0 : svm->vmcb->control.exit_info_1;
> +
> +	if (!(svm->force_intercept_exceptions_mask & (1 << exc)))
> +		return svm_handle_invalid_exit(vcpu, svm->vmcb->control.exit_code);
> +
> +	if (exc == TS_VECTOR) {
> +		/*
> +		 * SVM doesn't provide us with an error code to be able to
> +		 * re-inject the #TS exception, so just disable its
> +		 * intercept, and let the guest re-execute the instruction.
> +		 */
> +		vmcb_clr_intercept(&svm->vmcb01.ptr->control,
> +				   INTERCEPT_EXCEPTION_OFFSET + TS_VECTOR);
> +		recalc_intercepts(svm);
> +	} else if (x86_exception_has_error_code(exc))
> +		kvm_queue_exception_e(vcpu, exc, err_code);
> +	else
> +		kvm_queue_exception(vcpu, exc);
> +	return 1;
> +}
> +
>  static bool is_erratum_383(void)
>  {
>  	int err, i;
> @@ -3065,6 +3131,10 @@ static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = {
>  	[SVM_EXIT_WRITE_DR5]			= dr_interception,
>  	[SVM_EXIT_WRITE_DR6]			= dr_interception,
>  	[SVM_EXIT_WRITE_DR7]			= dr_interception,
> +
> +	[SVM_EXIT_EXCP_BASE ...
> +	SVM_EXIT_EXCP_BASE + 31]		= gen_exc_interception,
> +
>  	[SVM_EXIT_EXCP_BASE + DB_VECTOR]	= db_interception,
>  	[SVM_EXIT_EXCP_BASE + BP_VECTOR]	= bp_interception,
>  	[SVM_EXIT_EXCP_BASE + UD_VECTOR]	= ud_interception,
> diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
> index 524d943f3efc..187ada7c5b03 100644
> --- a/arch/x86/kvm/svm/svm.h
> +++ b/arch/x86/kvm/svm/svm.h
> @@ -196,6 +196,7 @@ struct vcpu_svm {
>  	bool ghcb_sa_free;
>  
>  	bool guest_state_loaded;
> +	u32 force_intercept_exceptions_mask;
>  };
>  
>  struct svm_cpu_data {
> @@ -351,8 +352,11 @@ static inline void clr_exception_intercept(struct vcpu_svm *svm, u32 bit)
>  	struct vmcb *vmcb = svm->vmcb01.ptr;
>  
>  	WARN_ON_ONCE(bit >= 32);
> -	vmcb_clr_intercept(&vmcb->control, INTERCEPT_EXCEPTION_OFFSET + bit);
>  
> +	if ((1 << bit) & svm->force_intercept_exceptions_mask)
> +		return;
> +
> +	vmcb_clr_intercept(&vmcb->control, INTERCEPT_EXCEPTION_OFFSET + bit);
>  	recalc_intercepts(svm);
>  }
>  
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 092e2fad3c0d..e5c7b8fa1f7f 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -695,12 +695,13 @@ void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr,
>  }
>  EXPORT_SYMBOL_GPL(kvm_queue_exception_p);
>  
> -static void kvm_queue_exception_e_p(struct kvm_vcpu *vcpu, unsigned nr,
> -				    u32 error_code, unsigned long payload)
> +void kvm_queue_exception_e_p(struct kvm_vcpu *vcpu, unsigned nr,
> +			     u32 error_code, unsigned long payload)
>  {
>  	kvm_multiple_exception(vcpu, nr, true, error_code,
>  			       true, payload, false);
>  }
> +EXPORT_SYMBOL_GPL(kvm_queue_exception_e_p);
>  
>  int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err)
>  {