linux-kernel - [RFC PATCH v3 15/16] KVM: x86/mmu: Make kvm fault handelr aware of large page of private memslot

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <89fa5a971d80f6e2cfbb6859d6985156b671b39e.1673541292.git.isaku.yamahata@intel.com>
Date:   Thu, 12 Jan 2023 08:44:07 -0800
From:   isaku.yamahata@...el.com
To:     kvm@...r.kernel.org, linux-kernel@...r.kernel.org
Cc:     isaku.yamahata@...el.com, isaku.yamahata@...il.com,
        Paolo Bonzini <pbonzini@...hat.com>, erdemaktas@...gle.com,
        Sean Christopherson <seanjc@...gle.com>,
        Sagi Shahar <sagis@...gle.com>,
        David Matlack <dmatlack@...gle.com>
Subject: [RFC PATCH v3 15/16] KVM: x86/mmu: Make kvm fault handelr aware of large page of private memslot

From: Isaku Yamahata <isaku.yamahata@...el.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 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@...el.com>
---
 arch/x86/kvm/mmu/mmu.c          | 36 +++++++++++++++++++++------------
 arch/x86/kvm/mmu/mmu_internal.h |  8 ++++++++
 2 files changed, 31 insertions(+), 13 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 961e103e674a..dc767125922e 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3118,12 +3118,12 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn,
 	return level;
 }
 
-int kvm_mmu_max_mapping_level(struct kvm *kvm,
-			      const struct kvm_memory_slot *slot, gfn_t gfn,
-			      int max_level, bool is_private)
+static int __kvm_mmu_max_mapping_level(struct kvm *kvm,
+				       const struct kvm_memory_slot *slot,
+				       gfn_t gfn, int max_level, int host_level,
+				       bool faultin_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--) {
@@ -3132,16 +3132,24 @@ 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 (!faultin_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, bool faultin_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)
 {
 	struct kvm_memory_slot *slot = fault->slot;
@@ -3162,9 +3170,10 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	 * Enforce the iTLB multihit workaround after capturing the requested
 	 * level, which will be used to do precise, accurate accounting.
 	 */
-	fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot,
-						     fault->gfn, fault->max_level,
-						     fault->is_private);
+	fault->req_level = __kvm_mmu_max_mapping_level(vcpu->kvm, slot,
+						       fault->gfn, fault->max_level,
+						       fault->host_level,
+						       kvm_is_faultin_private(fault));
 	if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed)
 		return;
 
@@ -4294,7 +4303,8 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
 	if (kvm_restricted_mem_get_pfn(slot, fault->gfn, &fault->pfn, &order))
 		return RET_PF_RETRY;
 
-	fault->max_level = min(order_to_level(order), fault->max_level);
+	fault->host_level = order_to_level(order);
+	fault->max_level = min((u8)fault->host_level, fault->max_level);
 	fault->map_writable = !(slot->flags & KVM_MEM_READONLY);
 	return RET_PF_CONTINUE;
 }
@@ -4338,7 +4348,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 	if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn))
 		return kvm_do_memory_fault_exit(vcpu, fault);
 
-	if (fault->is_private && kvm_slot_can_be_private(slot))
+	if (kvm_is_faultin_private(fault))
 		return kvm_faultin_pfn_private(vcpu, fault);
 
 	async = false;
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index b2774c164abb..1e73faad6268 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -337,6 +337,7 @@ struct kvm_page_fault {
 	kvm_pfn_t pfn;
 	hva_t hva;
 	bool map_writable;
+	enum pg_level host_level; /* valid only for private memslot && private gfn */
 };
 
 int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
@@ -445,4 +446,11 @@ static inline int kvm_restricted_mem_get_pfn(struct kvm_memory_slot *slot,
 }
 #endif /* CONFIG_HAVE_KVM_RESTRICTED_MEM */
 
+static inline bool kvm_is_faultin_private(const struct kvm_page_fault *fault)
+{
+	if (IS_ENABLED(CONFIG_HAVE_KVM_RESTRICTED_MEM))
+		return fault->is_private && kvm_slot_can_be_private(fault->slot);
+	return false;
+}
+
 #endif /* __KVM_X86_MMU_INTERNAL_H */
-- 
2.25.1