From:   isaku.yamahata@intel.com
To:     kvm@vger.kernel.org, linux-kernel@vger.kernel.org
Cc:     isaku.yamahata@intel.com, isaku.yamahata@gmail.com,
        Paolo Bonzini <pbonzini@redhat.com>, erdemaktas@google.com,
        Sean Christopherson <seanjc@google.com>,
        Sagi Shahar <sagis@google.com>,
        David Matlack <dmatlack@google.com>,
        Kai Huang <kai.huang@intel.com>,
        Zhi Wang <zhi.wang.linux@gmail.com>,
        Sean Christopherson <sean.j.christopherson@intel.com>
Subject: [PATCH v13 059/113] KVM: x86/mmu: Introduce kvm_mmu_map_tdp_page() for use by TDX
Date:   Sun, 12 Mar 2023 10:56:23 -0700
Message-Id: <fb5409edafd2a109dcfcbd777dda2d97c3375557.1678643052.git.isaku.yamahata@intel.com>
In-Reply-To: <cover.1678643051.git.isaku.yamahata@intel.com>
References: <cover.1678643051.git.isaku.yamahata@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Sean Christopherson <sean.j.christopherson@intel.com>

Introduce a helper to directly (pun intended) fault-in a TDP page
without having to go through the full page fault path.  This allows
TDX to get the resulting pfn and also allows the RET_PF_* enums to
stay in mmu.c where they belong.

Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
---
 arch/x86/kvm/mmu.h     |  3 +++
 arch/x86/kvm/mmu/mmu.c | 49 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 52 insertions(+)

diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 0ecdad63ad8c..d10b08eeaefe 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -154,6 +154,9 @@ static inline void kvm_mmu_load_pgd(struct kvm_vcpu *vcpu)
 					  vcpu->arch.mmu->root_role.level);
 }
 
+kvm_pfn_t kvm_mmu_map_tdp_page(struct kvm_vcpu *vcpu, gpa_t gpa,
+			       u32 error_code, int max_level);
+
 /*
  * Check if a given access (described through the I/D, W/R and U/S bits of a
  * page fault error code pfec) causes a permission fault with the given PTE
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index fb858594cfec..d4596b7594fa 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4590,6 +4590,55 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 	return direct_page_fault(vcpu, fault);
 }
 
+kvm_pfn_t kvm_mmu_map_tdp_page(struct kvm_vcpu *vcpu, gpa_t gpa,
+			       u32 error_code, int max_level)
+{
+	int r;
+	struct kvm_page_fault fault = (struct kvm_page_fault) {
+		.addr = gpa,
+		.error_code = error_code,
+		.exec = error_code & PFERR_FETCH_MASK,
+		.write = error_code & PFERR_WRITE_MASK,
+		.present = error_code & PFERR_PRESENT_MASK,
+		.rsvd = error_code & PFERR_RSVD_MASK,
+		.user = error_code & PFERR_USER_MASK,
+		.prefetch = false,
+		.is_tdp = true,
+		.nx_huge_page_workaround_enabled = is_nx_huge_page_enabled(vcpu->kvm),
+		.is_private = kvm_is_private_gpa(vcpu->kvm, gpa),
+	};
+
+	WARN_ON_ONCE(!vcpu->arch.mmu->root_role.direct);
+	fault.gfn = gpa_to_gfn(fault.addr) & ~kvm_gfn_shared_mask(vcpu->kvm);
+	fault.slot = kvm_vcpu_gfn_to_memslot(vcpu, fault.gfn);
+
+	if (mmu_topup_memory_caches(vcpu, false))
+		return KVM_PFN_ERR_FAULT;
+
+	/*
+	 * Loop on the page fault path to handle the case where an mmu_notifier
+	 * invalidation triggers RET_PF_RETRY.  In the normal page fault path,
+	 * KVM needs to resume the guest in case the invalidation changed any
+	 * of the page fault properties, i.e. the gpa or error code.  For this
+	 * path, the gpa and error code are fixed by the caller, and the caller
+	 * expects failure if and only if the page fault can't be fixed.
+	 */
+	do {
+		fault.max_level = max_level;
+		fault.req_level = PG_LEVEL_4K;
+		fault.goal_level = PG_LEVEL_4K;
+
+#ifdef CONFIG_X86_64
+		if (tdp_mmu_enabled)
+			r = kvm_tdp_mmu_page_fault(vcpu, &fault);
+		else
+#endif
+			r = direct_page_fault(vcpu, &fault);
+	} while (r == RET_PF_RETRY && !is_error_noslot_pfn(fault.pfn));
+	return fault.pfn;
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_map_tdp_page);
+
 static void nonpaging_init_context(struct kvm_mmu *context)
 {
 	context->page_fault = nonpaging_page_fault;
-- 
2.25.1