linux-kernel - [RFC PATCH 14/21] KVM: x86/tdp_mmu: Invoke split_external_spt hook with exclusive mmu

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: <20250424030744.435-1-yan.y.zhao@intel.com>
Date: Thu, 24 Apr 2025 11:07:44 +0800
From: Yan Zhao <yan.y.zhao@...el.com>
To: pbonzini@...hat.com,
	seanjc@...gle.com
Cc: linux-kernel@...r.kernel.org,
	kvm@...r.kernel.org,
	x86@...nel.org,
	rick.p.edgecombe@...el.com,
	dave.hansen@...el.com,
	kirill.shutemov@...el.com,
	tabba@...gle.com,
	ackerleytng@...gle.com,
	quic_eberman@...cinc.com,
	michael.roth@....com,
	david@...hat.com,
	vannapurve@...gle.com,
	vbabka@...e.cz,
	jroedel@...e.de,
	thomas.lendacky@....com,
	pgonda@...gle.com,
	zhiquan1.li@...el.com,
	fan.du@...el.com,
	jun.miao@...el.com,
	ira.weiny@...el.com,
	isaku.yamahata@...el.com,
	xiaoyao.li@...el.com,
	binbin.wu@...ux.intel.com,
	chao.p.peng@...el.com,
	Yan Zhao <yan.y.zhao@...el.com>
Subject: [RFC PATCH 14/21] KVM: x86/tdp_mmu: Invoke split_external_spt hook with exclusive mmu_lock

Introduce the split_external_spt hook and call it within tdp_mmu_set_spte()
for the mirror page table when kvm->mmu_lock is held for writing.

When tdp_mmu_set_spte() is invoked to transition an old leaf SPTE to a new
non-leaf SPTE in the mirror page table, use the split_external_spt hook to
propagate the entry splitting request to the external page table.

Signed-off-by: Xiaoyao Li <xiaoyao.li@...el.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@...el.com>
Signed-off-by: Yan Zhao <yan.y.zhao@...el.com>
---
 arch/x86/include/asm/kvm-x86-ops.h |  1 +
 arch/x86/include/asm/kvm_host.h    |  4 ++++
 arch/x86/kvm/mmu/tdp_mmu.c         | 26 ++++++++++++++++++++------
 3 files changed, 25 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 79406bf07a1c..f8403e0f6c1e 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -99,6 +99,7 @@ KVM_X86_OP_OPTIONAL(link_external_spt)
 KVM_X86_OP_OPTIONAL(set_external_spte)
 KVM_X86_OP_OPTIONAL(free_external_spt)
 KVM_X86_OP_OPTIONAL(remove_external_spte)
+KVM_X86_OP_OPTIONAL(split_external_spt)
 KVM_X86_OP(has_wbinvd_exit)
 KVM_X86_OP(get_l2_tsc_offset)
 KVM_X86_OP(get_l2_tsc_multiplier)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f96d30ad4ae8..6962a8a424ef 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1812,6 +1812,10 @@ struct kvm_x86_ops {
 	int (*remove_external_spte)(struct kvm *kvm, gfn_t gfn, enum pg_level level,
 				    kvm_pfn_t pfn_for_gfn);
 
+	/* Split the external page table into smaller page tables */
+	int (*split_external_spt)(struct kvm *kvm, gfn_t gfn, enum pg_level level,
+				  void *external_spt);
+
 	bool (*has_wbinvd_exit)(void);
 
 	u64 (*get_l2_tsc_offset)(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 799a08f91bf9..0f683753a7bb 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -325,6 +325,7 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
 				bool shared);
 
 static struct kvm_mmu_page *tdp_mmu_alloc_sp_for_split(bool mirror);
+static void *get_external_spt(gfn_t gfn, u64 new_spte, int level);
 
 static void tdp_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
@@ -384,6 +385,19 @@ static void remove_external_spte(struct kvm *kvm, gfn_t gfn, u64 old_spte,
 	KVM_BUG_ON(ret, kvm);
 }
 
+static int split_external_spt(struct kvm *kvm, gfn_t gfn, u64 old_spte,
+			      u64 new_spte, int level)
+{
+	void *external_spt = get_external_spt(gfn, new_spte, level);
+	int ret;
+
+	KVM_BUG_ON(!external_spt, kvm);
+
+	ret = static_call(kvm_x86_split_external_spt)(kvm, gfn, level, external_spt);
+	KVM_BUG_ON(ret, kvm);
+
+	return ret;
+}
 /**
  * handle_removed_pt() - handle a page table removed from the TDP structure
  *
@@ -764,13 +778,13 @@ static u64 tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep,
 
 	handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level, false);
 
-	/*
-	 * Users that do non-atomic setting of PTEs don't operate on mirror
-	 * roots, so don't handle it and bug the VM if it's seen.
-	 */
 	if (is_mirror_sptep(sptep)) {
-		KVM_BUG_ON(is_shadow_present_pte(new_spte), kvm);
-		remove_external_spte(kvm, gfn, old_spte, level);
+		if (!is_shadow_present_pte(new_spte))
+			remove_external_spte(kvm, gfn, old_spte, level);
+		else if (is_last_spte(old_spte, level) && !is_last_spte(new_spte, level))
+			split_external_spt(kvm, gfn, old_spte, new_spte, level);
+		else
+			KVM_BUG_ON(1, kvm);
 	}
 
 	return old_spte;
-- 
2.43.2