Received-SPF: pass (google.com: domain of linux-kernel+bounces-80907-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
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>,
	Kai Huang <kai.huang@intel.com>,
	chen.bo@intel.com,
	hang.yuan@intel.com,
	tina.zhang@intel.com
Subject: [PATCH v8 13/14] KVM: x86/mmu: Make kvm fault handler aware of large page of private memslot
Date: Mon, 26 Feb 2024 00:29:27 -0800
Message-Id: <30209eb4d65d1de3e09dc9fdb3fc0d3d3c96dc7e.1708933625.git.isaku.yamahata@intel.com>
In-Reply-To: <cover.1708933624.git.isaku.yamahata@intel.com>
References: <cover.1708933624.git.isaku.yamahata@intel.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

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

struct kvm_page_fault.req_level is the page level which takes care of the
faulted-in page size.  For now its calculation is only for the conventional
kvm memslot by host_pfn_mapping_level() that traverses page table.

However, host_pfn_mapping_level() cannot be used for private kvm memslot
because private pages of private kvm memlost aren't mapped into user
virtual address space.  Instead, page order is given when getting pfn.
Remember it in struct kvm_page_fault and use it.

Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
---
 arch/x86/kvm/mmu/mmu.c          | 27 ++++++++++++++-------------
 arch/x86/kvm/mmu/mmu_internal.h | 12 +++++++++++-
 arch/x86/kvm/mmu/tdp_mmu.c      |  2 +-
 3 files changed, 26 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index fa7fabc410c4..3c41861b4b3d 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3154,10 +3154,10 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn,
 
 static int __kvm_mmu_max_mapping_level(struct kvm *kvm,
 				       const struct kvm_memory_slot *slot,
-				       gfn_t gfn, int max_level, bool is_private)
+				       gfn_t gfn, int max_level, int host_level,
+				       bool is_private)
 {
 	struct kvm_lpage_info *linfo;
-	int host_level;
 
 	max_level = min(max_level, max_huge_page_level);
 	for ( ; max_level > PG_LEVEL_4K; max_level--) {
@@ -3166,24 +3166,23 @@ static int __kvm_mmu_max_mapping_level(struct kvm *kvm,
 			break;
 	}
 
-	if (is_private)
-		return max_level;
-
 	if (max_level == PG_LEVEL_4K)
 		return PG_LEVEL_4K;
 
-	host_level = host_pfn_mapping_level(kvm, gfn, slot);
+	if (!is_private) {
+		WARN_ON_ONCE(host_level != PG_LEVEL_NONE);
+		host_level = host_pfn_mapping_level(kvm, gfn, slot);
+	}
+	WARN_ON_ONCE(host_level == PG_LEVEL_NONE);
 	return min(host_level, max_level);
 }
 
 int kvm_mmu_max_mapping_level(struct kvm *kvm,
 			      const struct kvm_memory_slot *slot, gfn_t gfn,
-			      int max_level)
+			      int max_level, bool faultin_private)
 {
-	bool is_private = kvm_slot_can_be_private(slot) &&
-			  kvm_mem_is_private(kvm, gfn);
-
-	return __kvm_mmu_max_mapping_level(kvm, slot, gfn, max_level, is_private);
+	return __kvm_mmu_max_mapping_level(kvm, slot, gfn, max_level,
+					   PG_LEVEL_NONE, faultin_private);
 }
 
 void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
@@ -3208,7 +3207,8 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	 */
 	fault->req_level = __kvm_mmu_max_mapping_level(vcpu->kvm, slot,
 						       fault->gfn, fault->max_level,
-						       fault->is_private);
+						       fault->host_level,
+						       kvm_is_faultin_private(fault));
 	if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed)
 		return;
 
@@ -4349,6 +4349,7 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
 	}
 
 	max_level = kvm_max_level_for_order(max_order);
+	fault->host_level = max_level;
 	r = static_call(kvm_x86_gmem_max_level)(vcpu->kvm, fault->pfn,
 						fault->gfn, fault->is_private,
 						&max_level);
@@ -6818,7 +6819,7 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
 		 */
 		if (sp->role.direct &&
 		    sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn,
-							       PG_LEVEL_NUM)) {
+							       PG_LEVEL_NUM, false)) {
 			kvm_zap_one_rmap_spte(kvm, rmap_head, sptep);
 
 			if (kvm_available_flush_remote_tlbs_range())
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 315c123affaf..9d56f9ab16f7 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -327,6 +327,9 @@ struct kvm_page_fault {
 	 * is changing its own translation in the guest page tables.
 	 */
 	bool write_fault_to_shadow_pgtable;
+
+	/* valid only for private memslot && private gfn */
+	enum pg_level host_level;
 };
 
 int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
@@ -421,7 +424,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 
 int kvm_mmu_max_mapping_level(struct kvm *kvm,
 			      const struct kvm_memory_slot *slot, gfn_t gfn,
-			      int max_level);
+			      int max_level, bool faultin_private);
 void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
 void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_level);
 
@@ -439,4 +442,11 @@ static inline bool kvm_hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t g
 }
 #endif
 
+static inline bool kvm_is_faultin_private(const struct kvm_page_fault *fault)
+{
+	if (IS_ENABLED(CONFIG_KVM_GENERIC_PRIVATE_MEM))
+		return fault->is_private && kvm_slot_can_be_private(fault->slot);
+	return false;
+}
+
 #endif /* __KVM_X86_MMU_INTERNAL_H */
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 556974361d36..d6ce8496803f 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -2183,7 +2183,7 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
 			continue;
 
 		max_mapping_level = kvm_mmu_max_mapping_level(kvm, slot,
-							      iter.gfn, PG_LEVEL_NUM);
+							      iter.gfn, PG_LEVEL_NUM, false);
 		if (max_mapping_level < iter.level)
 			continue;
 
-- 
2.25.1