Re: [PATCH v2 2/3] KVM:SVM: Add extended intercept support

[Vitaly Kuznetsov]

Babu Moger <babu.moger@xxxxxxx> writes:

> The new intercept bits have been added in vmcb control
> area to support the interception of INVPCID instruction.
>
> The following bit is added to the VMCB layout control area
> to control intercept of INVPCID:
>
> Byte Offset     Bit(s)          Function
> 14h             2               intercept INVPCID
>
> Add the interfaces to support these extended interception.
> Also update the tracing for extended intercepts.
>
> AMD documentation for INVPCID feature is available at "AMD64
> Architecture Programmerâs Manual Volume 2: System Programming,
> Pub. 24593 Rev. 3.34(or later)"
>
> The documentation can be obtained at the links below:
> Link: https://www.amd.com/system/files/TechDocs/24593.pdf
> Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537
>
> Signed-off-by: Babu Moger <babu.moger@xxxxxxx>
> ---
>  arch/x86/include/asm/svm.h |    3 ++-
>  arch/x86/kvm/svm/nested.c  |    6 +++++-
>  arch/x86/kvm/svm/svm.c     |    1 +
>  arch/x86/kvm/svm/svm.h     |   18 ++++++++++++++++++
>  arch/x86/kvm/trace.h       |   12 ++++++++----
>  5 files changed, 34 insertions(+), 6 deletions(-)
>
> diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
> index 8a1f5382a4ea..62649fba8908 100644
> --- a/arch/x86/include/asm/svm.h
> +++ b/arch/x86/include/asm/svm.h
> @@ -61,7 +61,8 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
>  	u32 intercept_dr;
>  	u32 intercept_exceptions;
>  	u64 intercept;
> -	u8 reserved_1[40];
> +	u32 intercept_extended;
> +	u8 reserved_1[36];
>  	u16 pause_filter_thresh;
>  	u16 pause_filter_count;
>  	u64 iopm_base_pa;
> diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
> index 8a6db11dcb43..7f6d0f2533e2 100644
> --- a/arch/x86/kvm/svm/nested.c
> +++ b/arch/x86/kvm/svm/nested.c
> @@ -121,6 +121,7 @@ void recalc_intercepts(struct vcpu_svm *svm)
>  	c->intercept_dr = h->intercept_dr;
>  	c->intercept_exceptions = h->intercept_exceptions;
>  	c->intercept = h->intercept;
> +	c->intercept_extended = h->intercept_extended;
>  
>  	if (g->int_ctl & V_INTR_MASKING_MASK) {
>  		/* We only want the cr8 intercept bits of L1 */
> @@ -142,6 +143,7 @@ void recalc_intercepts(struct vcpu_svm *svm)
>  	c->intercept_dr |= g->intercept_dr;
>  	c->intercept_exceptions |= g->intercept_exceptions;
>  	c->intercept |= g->intercept;
> +	c->intercept_extended |= g->intercept_extended;
>  }
>  
>  static void copy_vmcb_control_area(struct vmcb_control_area *dst,
> @@ -151,6 +153,7 @@ static void copy_vmcb_control_area(struct vmcb_control_area *dst,
>  	dst->intercept_dr         = from->intercept_dr;
>  	dst->intercept_exceptions = from->intercept_exceptions;
>  	dst->intercept            = from->intercept;
> +	dst->intercept_extended   = from->intercept_extended;
>  	dst->iopm_base_pa         = from->iopm_base_pa;
>  	dst->msrpm_base_pa        = from->msrpm_base_pa;
>  	dst->tsc_offset           = from->tsc_offset;
> @@ -433,7 +436,8 @@ int nested_svm_vmrun(struct vcpu_svm *svm)
>  	trace_kvm_nested_intercepts(nested_vmcb->control.intercept_cr & 0xffff,
>  				    nested_vmcb->control.intercept_cr >> 16,
>  				    nested_vmcb->control.intercept_exceptions,
> -				    nested_vmcb->control.intercept);
> +				    nested_vmcb->control.intercept,
> +				    nested_vmcb->control.intercept_extended);
>  
>  	/* Clear internal status */
>  	kvm_clear_exception_queue(&svm->vcpu);
> diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
> index 9e333b91ff78..285e5e1ff518 100644
> --- a/arch/x86/kvm/svm/svm.c
> +++ b/arch/x86/kvm/svm/svm.c
> @@ -2801,6 +2801,7 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
>  	pr_err("%-20s%04x\n", "dr_write:", control->intercept_dr >> 16);
>  	pr_err("%-20s%08x\n", "exceptions:", control->intercept_exceptions);
>  	pr_err("%-20s%016llx\n", "intercepts:", control->intercept);
> +	pr_err("%-20s%08x\n", "intercepts (extended):", control->intercept_extended);
>  	pr_err("%-20s%d\n", "pause filter count:", control->pause_filter_count);
>  	pr_err("%-20s%d\n", "pause filter threshold:",
>  	       control->pause_filter_thresh);
> diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
> index 6ac4c00a5d82..935d08fac03d 100644
> --- a/arch/x86/kvm/svm/svm.h
> +++ b/arch/x86/kvm/svm/svm.h
> @@ -311,6 +311,24 @@ static inline void clr_intercept(struct vcpu_svm *svm, int bit)
>  	recalc_intercepts(svm);
>  }
>  
> +static inline void set_extended_intercept(struct vcpu_svm *svm, int bit)
> +{
> +	struct vmcb *vmcb = get_host_vmcb(svm);
> +
> +	vmcb->control.intercept_extended |= (1U << bit);
> +
> +	recalc_intercepts(svm);
> +}
> +
> +static inline void clr_extended_intercept(struct vcpu_svm *svm, int bit)
> +{
> +	struct vmcb *vmcb = get_host_vmcb(svm);
> +
> +	vmcb->control.intercept_extended &= ~(1U << bit);
> +
> +	recalc_intercepts(svm);
> +}
> +
>  static inline bool is_intercept(struct vcpu_svm *svm, int bit)
>  {
>  	return (svm->vmcb->control.intercept & (1ULL << bit)) != 0;
> diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
> index b66432b015d2..5c841c42b33d 100644
> --- a/arch/x86/kvm/trace.h
> +++ b/arch/x86/kvm/trace.h
> @@ -544,14 +544,16 @@ TRACE_EVENT(kvm_nested_vmrun,
>  );
>  
>  TRACE_EVENT(kvm_nested_intercepts,
> -	    TP_PROTO(__u16 cr_read, __u16 cr_write, __u32 exceptions, __u64 intercept),
> -	    TP_ARGS(cr_read, cr_write, exceptions, intercept),
> +	    TP_PROTO(__u16 cr_read, __u16 cr_write, __u32 exceptions, __u64 intercept,
> +		     __u32 extended),
> +	    TP_ARGS(cr_read, cr_write, exceptions, intercept, extended),
>  
>  	TP_STRUCT__entry(
>  		__field(	__u16,		cr_read		)
>  		__field(	__u16,		cr_write	)
>  		__field(	__u32,		exceptions	)
>  		__field(	__u64,		intercept	)
> +		__field(	__u32,		extended	)
>  	),
>  
>  	TP_fast_assign(
> @@ -559,11 +561,13 @@ TRACE_EVENT(kvm_nested_intercepts,
>  		__entry->cr_write	= cr_write;
>  		__entry->exceptions	= exceptions;
>  		__entry->intercept	= intercept;
> +		__entry->extended	= extended;
>  	),
>  
> -	TP_printk("cr_read: %04x cr_write: %04x excp: %08x intercept: %016llx",
> +	TP_printk("cr_read: %04x cr_write: %04x excp: %08x intercept: %016llx"
> +		  "intercept (extended): %08x",
>  		__entry->cr_read, __entry->cr_write, __entry->exceptions,
> -		__entry->intercept)
> +		__entry->intercept, __entry->extended)

Nit: I would've renamed 'extended' to something like 'intercept_ext' as
it is not clear what it is about otherwise. Also, if you decide to do
so, you may as well shorten 'intercept_extended' to 'intercept_ext'
everywhere else to be consistent. Or just use 'intercept_extended', with
no 80-character-per-line limitation we no longer need to be concise.

>  );
>  /*
>   * Tracepoint for #VMEXIT while nested
>

-- 
Vitaly