Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
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>,
        Sean Christopherson <sean.j.christopherson@intel.com>
Subject: [PATCH v9 030/105] KVM: x86/mmu: Replace hardcoded value 0 for the initial value for SPTE
Date:   Fri, 30 Sep 2022 03:17:24 -0700
Message-Id: <1d1459082c4ff5316fa14860f4023c23a210c94e.1664530907.git.isaku.yamahata@intel.com>
In-Reply-To: <cover.1664530907.git.isaku.yamahata@intel.com>
References: <cover.1664530907.git.isaku.yamahata@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Isaku Yamahata <isaku.yamahata@intel.com>

The TDX support will need the "suppress #VE" bit (bit 63) set as the
initial value for SPTE.  To reduce code change size, introduce a new macro
SHADOW_NONPRESENT_VALUE for the initial value for the shadow page table
entry (SPTE) and replace hard-coded value 0 for it.  Initialize shadow page
tables with their value.

The plan is to unconditionally set the "suppress #VE" bit for both AMD and
Intel as: 1) AMD hardware doesn't use this bit; 2) for conventional VMX
guests, KVM never enables the "EPT-violation #VE" in VMCS control and
"suppress #VE" bit is ignored by hardware.

Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
---
 arch/x86/kvm/mmu/mmu.c     | 50 +++++++++++++++++++++++++++++++++-----
 arch/x86/kvm/mmu/spte.h    |  2 ++
 arch/x86/kvm/mmu/tdp_mmu.c | 15 ++++++------
 3 files changed, 54 insertions(+), 13 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index c9f60acfc322..ff8de361067c 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -538,9 +538,9 @@ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep)
 
 	if (!is_shadow_present_pte(old_spte) ||
 	    !spte_has_volatile_bits(old_spte))
-		__update_clear_spte_fast(sptep, 0ull);
+		__update_clear_spte_fast(sptep, SHADOW_NONPRESENT_VALUE);
 	else
-		old_spte = __update_clear_spte_slow(sptep, 0ull);
+		old_spte = __update_clear_spte_slow(sptep, SHADOW_NONPRESENT_VALUE);
 
 	if (!is_shadow_present_pte(old_spte))
 		return old_spte;
@@ -574,7 +574,7 @@ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep)
  */
 static void mmu_spte_clear_no_track(u64 *sptep)
 {
-	__update_clear_spte_fast(sptep, 0ull);
+	__update_clear_spte_fast(sptep, SHADOW_NONPRESENT_VALUE);
 }
 
 static u64 mmu_spte_get_lockless(u64 *sptep)
@@ -642,6 +642,39 @@ static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu)
 	}
 }
 
+#ifdef CONFIG_X86_64
+static inline void kvm_init_shadow_page(void *page)
+{
+	memset64(page, SHADOW_NONPRESENT_VALUE, 4096 / 8);
+}
+
+static int mmu_topup_shadow_page_cache(struct kvm_vcpu *vcpu)
+{
+	struct kvm_mmu_memory_cache *mc = &vcpu->arch.mmu_shadow_page_cache;
+	int start, end, i, r;
+
+	start = kvm_mmu_memory_cache_nr_free_objects(mc);
+	r = kvm_mmu_topup_memory_cache(mc, PT64_ROOT_MAX_LEVEL);
+
+	/*
+	 * Note, topup may have allocated objects even if it failed to allocate
+	 * the minimum number of objects required to make forward progress _at
+	 * this time_.  Initialize newly allocated objects even on failure, as
+	 * userspace can free memory and rerun the vCPU in response to -ENOMEM.
+	 */
+	end = kvm_mmu_memory_cache_nr_free_objects(mc);
+	for (i = start; i < end; i++)
+		kvm_init_shadow_page(mc->objects[i]);
+	return r;
+}
+#else
+static int mmu_topup_shadow_page_cache(struct kvm_vcpu *vcpu)
+{
+	return kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_shadow_page_cache,
+					  PT64_ROOT_MAX_LEVEL);
+}
+#endif /* CONFIG_X86_64 */
+
 static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu, bool maybe_indirect)
 {
 	int r;
@@ -651,8 +684,7 @@ static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu, bool maybe_indirect)
 				       1 + PT64_ROOT_MAX_LEVEL + PTE_PREFETCH_NUM);
 	if (r)
 		return r;
-	r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_shadow_page_cache,
-				       PT64_ROOT_MAX_LEVEL);
+	r = mmu_topup_shadow_page_cache(vcpu);
 	if (r)
 		return r;
 	if (maybe_indirect) {
@@ -5861,7 +5893,13 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
 	vcpu->arch.mmu_page_header_cache.kmem_cache = mmu_page_header_cache;
 	vcpu->arch.mmu_page_header_cache.gfp_zero = __GFP_ZERO;
 
-	vcpu->arch.mmu_shadow_page_cache.gfp_zero = __GFP_ZERO;
+	/*
+	 * When X86_64, initial SEPT entries are initialized with
+	 * SHADOW_NONPRESENT_VALUE.  Otherwise zeroed.  See
+	 * mmu_topup_shadow_page_cache().
+	 */
+	if (!IS_ENABLED(CONFIG_X86_64))
+		vcpu->arch.mmu_shadow_page_cache.gfp_zero = __GFP_ZERO;
 
 	vcpu->arch.mmu = &vcpu->arch.root_mmu;
 	vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 7670c13ce251..42ecaa75da15 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -148,6 +148,8 @@ static_assert(MMIO_SPTE_GEN_LOW_BITS == 8 && MMIO_SPTE_GEN_HIGH_BITS == 11);
 
 #define MMIO_SPTE_GEN_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_BITS + MMIO_SPTE_GEN_HIGH_BITS - 1, 0)
 
+#define SHADOW_NONPRESENT_VALUE	0ULL
+
 extern u64 __read_mostly shadow_host_writable_mask;
 extern u64 __read_mostly shadow_mmu_writable_mask;
 extern u64 __read_mostly shadow_nx_mask;
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index bf2ccf9debca..0a7edea7488e 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -683,7 +683,7 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm,
 	 * here since the SPTE is going from non-present to non-present.  Use
 	 * the raw write helper to avoid an unnecessary check on volatile bits.
 	 */
-	__kvm_tdp_mmu_write_spte(iter->sptep, 0);
+	__kvm_tdp_mmu_write_spte(iter->sptep, SHADOW_NONPRESENT_VALUE);
 
 	return 0;
 }
@@ -860,8 +860,8 @@ static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root,
 			continue;
 
 		if (!shared)
-			tdp_mmu_set_spte(kvm, &iter, 0);
-		else if (tdp_mmu_set_spte_atomic(kvm, &iter, 0))
+			tdp_mmu_set_spte(kvm, &iter, SHADOW_NONPRESENT_VALUE);
+		else if (tdp_mmu_set_spte_atomic(kvm, &iter, SHADOW_NONPRESENT_VALUE))
 			goto retry;
 	}
 }
@@ -917,8 +917,9 @@ bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
 	if (WARN_ON_ONCE(!is_shadow_present_pte(old_spte)))
 		return false;
 
-	__tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte, 0,
-			   sp->gfn, sp->role.level + 1, true, true);
+	__tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte,
+			   SHADOW_NONPRESENT_VALUE, sp->gfn, sp->role.level + 1,
+			   true, true);
 
 	return true;
 }
@@ -952,7 +953,7 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root,
 		    !is_last_spte(iter.old_spte, iter.level))
 			continue;
 
-		tdp_mmu_set_spte(kvm, &iter, 0);
+		tdp_mmu_set_spte(kvm, &iter, SHADOW_NONPRESENT_VALUE);
 		flush = true;
 	}
 
@@ -1316,7 +1317,7 @@ static bool set_spte_gfn(struct kvm *kvm, struct tdp_iter *iter,
 	 * invariant that the PFN of a present * leaf SPTE can never change.
 	 * See __handle_changed_spte().
 	 */
-	tdp_mmu_set_spte(kvm, iter, 0);
+	tdp_mmu_set_spte(kvm, iter, SHADOW_NONPRESENT_VALUE);
 
 	if (!pte_write(range->pte)) {
 		new_spte = kvm_mmu_changed_pte_notifier_make_spte(iter->old_spte,
-- 
2.25.1