Re: [PATCH Part2 v5 37/45] KVM: SVM: Add support to handle MSR based Page State Change VMGEXIT

["Dr. David Alan Gilbert" <dgilbert@redhat.com>]

* Brijesh Singh (brijesh.singh@amd.com) wrote:
> SEV-SNP VMs can ask the hypervisor to change the page state in the RMP
> table to be private or shared using the Page State Change MSR protocol
> as defined in the GHCB specification.
> 
> Before changing the page state in the RMP entry, lookup the page in the
> NPT to make sure that there is a valid mapping for it. If the mapping
> exist then try to find a workable page level between the NPT and RMP for
> the page. If the page is not mapped in the NPT, then create a fault such
> that it gets mapped before we change the page state in the RMP entry.
> 
> Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
> ---
>  arch/x86/include/asm/sev-common.h |   9 ++
>  arch/x86/kvm/svm/sev.c            | 197 ++++++++++++++++++++++++++++++
>  arch/x86/kvm/trace.h              |  34 ++++++
>  arch/x86/kvm/x86.c                |   1 +
>  4 files changed, 241 insertions(+)
> 
> diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h
> index 91089967ab09..4980f77aa1d5 100644
> --- a/arch/x86/include/asm/sev-common.h
> +++ b/arch/x86/include/asm/sev-common.h
> @@ -89,6 +89,10 @@ enum psc_op {
>  };
>  
>  #define GHCB_MSR_PSC_REQ		0x014
> +#define GHCB_MSR_PSC_GFN_POS		12
> +#define GHCB_MSR_PSC_GFN_MASK		GENMASK_ULL(39, 0)
> +#define GHCB_MSR_PSC_OP_POS		52
> +#define GHCB_MSR_PSC_OP_MASK		0xf
>  #define GHCB_MSR_PSC_REQ_GFN(gfn, op)			\
>  	/* GHCBData[55:52] */				\
>  	(((u64)((op) & 0xf) << 52) |			\
> @@ -98,6 +102,11 @@ enum psc_op {
>  	GHCB_MSR_PSC_REQ)
>  
>  #define GHCB_MSR_PSC_RESP		0x015
> +#define GHCB_MSR_PSC_ERROR_POS		32
> +#define GHCB_MSR_PSC_ERROR_MASK		GENMASK_ULL(31, 0)
> +#define GHCB_MSR_PSC_ERROR		GENMASK_ULL(31, 0)
> +#define GHCB_MSR_PSC_RSVD_POS		12
> +#define GHCB_MSR_PSC_RSVD_MASK		GENMASK_ULL(19, 0)
>  #define GHCB_MSR_PSC_RESP_VAL(val)			\
>  	/* GHCBData[63:32] */				\
>  	(((u64)(val) & GENMASK_ULL(63, 32)) >> 32)
> diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
> index 991b8c996fc1..6d9483ec91ab 100644
> --- a/arch/x86/kvm/svm/sev.c
> +++ b/arch/x86/kvm/svm/sev.c
> @@ -31,6 +31,7 @@
>  #include "svm_ops.h"
>  #include "cpuid.h"
>  #include "trace.h"
> +#include "mmu.h"
>  
>  #define __ex(x) __kvm_handle_fault_on_reboot(x)
>  
> @@ -2905,6 +2906,181 @@ static void set_ghcb_msr(struct vcpu_svm *svm, u64 value)
>  	svm->vmcb->control.ghcb_gpa = value;
>  }
>  
> +static int snp_rmptable_psmash(struct kvm *kvm, kvm_pfn_t pfn)
> +{
> +	pfn = pfn & ~(KVM_PAGES_PER_HPAGE(PG_LEVEL_2M) - 1);
> +
> +	return psmash(pfn);
> +}
> +
> +static int snp_make_page_shared(struct kvm *kvm, gpa_t gpa, kvm_pfn_t pfn, int level)

....

> +
> +			/*
> +			 * Mark the userspace range unmerable before adding the pages

                                                    ^^^^^^^^^ typo

> +			 * in the RMP table.
> +			 */
> +			mmap_write_lock(kvm->mm);
> +			rc = snp_mark_unmergable(kvm, hva, page_level_size(level));
> +			mmap_write_unlock(kvm->mm);
> +			if (rc)
> +				return -EINVAL;
> +		}
> +
> +		write_lock(&kvm->mmu_lock);
> +
> +		rc = kvm_mmu_get_tdp_walk(vcpu, gpa, &pfn, &npt_level);
> +		if (!rc) {
> +			/*
> +			 * This may happen if another vCPU unmapped the page
> +			 * before we acquire the lock. Retry the PSC.
> +			 */
> +			write_unlock(&kvm->mmu_lock);
> +			return 0;
> +		}
> +
> +		/*
> +		 * Adjust the level so that we don't go higher than the backing
> +		 * page level.
> +		 */
> +		level = min_t(size_t, level, npt_level);
> +
> +		trace_kvm_snp_psc(vcpu->vcpu_id, pfn, gpa, op, level);
> +
> +		switch (op) {
> +		case SNP_PAGE_STATE_SHARED:
> +			rc = snp_make_page_shared(kvm, gpa, pfn, level);
> +			break;
> +		case SNP_PAGE_STATE_PRIVATE:
> +			rc = rmp_make_private(pfn, gpa, level, sev->asid, false);

Minor nit; it seems a shame that snp_make_page_shared and
rmp_make_private  both take gpa, pfn, level - in different orders.

Dave

> +			break;
> +		default:
> +			rc = -EINVAL;
> +			break;
> +		}
> +
> +		write_unlock(&kvm->mmu_lock);
> +
> +		if (rc) {
> +			pr_err_ratelimited("Error op %d gpa %llx pfn %llx level %d rc %d\n",
> +					   op, gpa, pfn, level, rc);
> +			return rc;
> +		}
> +
> +		gpa = gpa + page_level_size(level);
> +	}
> +
> +	return 0;
> +}
> +
>  static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
>  {
>  	struct vmcb_control_area *control = &svm->vmcb->control;
> @@ -3005,6 +3181,27 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
>  				  GHCB_MSR_INFO_POS);
>  		break;
>  	}
> +	case GHCB_MSR_PSC_REQ: {
> +		gfn_t gfn;
> +		int ret;
> +		enum psc_op op;
> +
> +		gfn = get_ghcb_msr_bits(svm, GHCB_MSR_PSC_GFN_MASK, GHCB_MSR_PSC_GFN_POS);
> +		op = get_ghcb_msr_bits(svm, GHCB_MSR_PSC_OP_MASK, GHCB_MSR_PSC_OP_POS);
> +
> +		ret = __snp_handle_page_state_change(vcpu, op, gfn_to_gpa(gfn), PG_LEVEL_4K);
> +
> +		if (ret)
> +			set_ghcb_msr_bits(svm, GHCB_MSR_PSC_ERROR,
> +					  GHCB_MSR_PSC_ERROR_MASK, GHCB_MSR_PSC_ERROR_POS);
> +		else
> +			set_ghcb_msr_bits(svm, 0,
> +					  GHCB_MSR_PSC_ERROR_MASK, GHCB_MSR_PSC_ERROR_POS);
> +
> +		set_ghcb_msr_bits(svm, 0, GHCB_MSR_PSC_RSVD_MASK, GHCB_MSR_PSC_RSVD_POS);
> +		set_ghcb_msr_bits(svm, GHCB_MSR_PSC_RESP, GHCB_MSR_INFO_MASK, GHCB_MSR_INFO_POS);
> +		break;
> +	}
>  	case GHCB_MSR_TERM_REQ: {
>  		u64 reason_set, reason_code;
>  
> diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
> index 1c360e07856f..35ca1cf8440a 100644
> --- a/arch/x86/kvm/trace.h
> +++ b/arch/x86/kvm/trace.h
> @@ -7,6 +7,7 @@
>  #include <asm/svm.h>
>  #include <asm/clocksource.h>
>  #include <asm/pvclock-abi.h>
> +#include <asm/sev-common.h>
>  
>  #undef TRACE_SYSTEM
>  #define TRACE_SYSTEM kvm
> @@ -1711,6 +1712,39 @@ TRACE_EVENT(kvm_vmgexit_msr_protocol_exit,
>  		  __entry->vcpu_id, __entry->ghcb_gpa, __entry->result)
>  );
>  
> +/*
> + * Tracepoint for the SEV-SNP page state change processing
> + */
> +#define psc_operation					\
> +	{SNP_PAGE_STATE_PRIVATE, "private"},		\
> +	{SNP_PAGE_STATE_SHARED,  "shared"}		\
> +
> +TRACE_EVENT(kvm_snp_psc,
> +	TP_PROTO(unsigned int vcpu_id, u64 pfn, u64 gpa, u8 op, int level),
> +	TP_ARGS(vcpu_id, pfn, gpa, op, level),
> +
> +	TP_STRUCT__entry(
> +		__field(int, vcpu_id)
> +		__field(u64, pfn)
> +		__field(u64, gpa)
> +		__field(u8, op)
> +		__field(int, level)
> +	),
> +
> +	TP_fast_assign(
> +		__entry->vcpu_id = vcpu_id;
> +		__entry->pfn = pfn;
> +		__entry->gpa = gpa;
> +		__entry->op = op;
> +		__entry->level = level;
> +	),
> +
> +	TP_printk("vcpu %u, pfn %llx, gpa %llx, op %s, level %d",
> +		  __entry->vcpu_id, __entry->pfn, __entry->gpa,
> +		  __print_symbolic(__entry->op, psc_operation),
> +		  __entry->level)
> +);
> +
>  #endif /* _TRACE_KVM_H */
>  
>  #undef TRACE_INCLUDE_PATH
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index e5d5c5ed7dd4..afcdc75a99f2 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -12371,3 +12371,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter);
>  EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit);
>  EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter);
>  EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit);
> +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_snp_psc);
> -- 
> 2.17.1
> 
> 
-- 
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK