linux-kernel - [PATCH v12 07/11] mmu: spp: Enable Lazy mode SPP protection

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: <20200516125507.5277-8-weijiang.yang@intel.com>
Date:   Sat, 16 May 2020 20:55:03 +0800
From:   Yang Weijiang <weijiang.yang@...el.com>
To:     kvm@...r.kernel.org, linux-kernel@...r.kernel.org,
        pbonzini@...hat.com, jmattson@...gle.com,
        sean.j.christopherson@...el.com
Cc:     yu.c.zhang@...ux.intel.com, alazar@...defender.com,
        edwin.zhai@...el.com, ssicleru@...defender.com,
        Yang Weijiang <weijiang.yang@...el.com>
Subject: [PATCH v12 07/11] mmu: spp: Enable Lazy mode SPP protection

When SPP protection is set but the gfn->pfn mapping isn't there,
we need to check and mark SPP protection in EPT while
gfn->pfn mapping is being built, but the setup for SPPT is deferred
to handle_spp() handler.

>From HW's capability, SPP only works for 4KB mappings, to apply
SPP protection for hugepage(2MB,1GB) cases, hugepage entries need
to be zapped before SPP set up. In tdp_page_fault(), there's check
for SPP protection before sets 4KB, 2MB or 1GB mapping, the target
is introducing least impact to hugepage setup, i.e., falls back to
most possible hugepage mapping.

Suggested-by: Paolo Bonzini <pbonzini@...hat.com>
Signed-off-by: Yang Weijiang <weijiang.yang@...el.com>
---
 arch/x86/kvm/mmu/mmu.c | 19 +++++++++++++++++++
 arch/x86/kvm/mmu/spp.c | 43 ++++++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/mmu/spp.h |  2 ++
 3 files changed, 64 insertions(+)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 270dd567272e..9d5a0eb3d24e 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3131,6 +3131,7 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu,
 	unsigned int access = sp->role.access;
 	int i, ret;
 	gfn_t gfn;
+	u32 *wp_bitmap;
 
 	gfn = kvm_mmu_page_get_gfn(sp, start - sp->spt);
 	slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, access & ACC_WRITE_MASK);
@@ -3144,6 +3145,13 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu,
 	for (i = 0; i < ret; i++, gfn++, start++) {
 		mmu_set_spte(vcpu, start, access, 0, sp->role.level, gfn,
 			     page_to_pfn(pages[i]), true, true);
+		if (vcpu->kvm->arch.spp_active) {
+			wp_bitmap = gfn_to_subpage_wp_info(slot, gfn);
+			if (wp_bitmap && *wp_bitmap != FULL_SPP_ACCESS)
+				kvm_spp_mark_protection(vcpu->kvm,
+							gfn,
+							*wp_bitmap);
+		}
 		put_page(pages[i]);
 	}
 
@@ -3336,6 +3344,15 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write,
 			   map_writable);
 	direct_pte_prefetch(vcpu, it.sptep);
 	++vcpu->stat.pf_fixed;
+	if (level == PT_PAGE_TABLE_LEVEL) {
+		int ret;
+		u32 access;
+
+		ret = kvm_spp_get_permission(vcpu->kvm, gfn, 1, &access);
+		if (ret == 1  && access != FULL_SPP_ACCESS)
+			kvm_spp_mark_protection(vcpu->kvm, gfn, access);
+	}
+
 	return ret;
 }
 
@@ -4125,6 +4142,8 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 	if (lpage_disallowed)
 		max_level = PT_PAGE_TABLE_LEVEL;
 
+	check_spp_protection(vcpu, gfn, &max_level);
+
 	r = fast_page_fault(vcpu, gpa, error_code);
 
 	if (r != RET_PF_INVALID)
diff --git a/arch/x86/kvm/mmu/spp.c b/arch/x86/kvm/mmu/spp.c
index bb8f298d72da..8f89df57da7c 100644
--- a/arch/x86/kvm/mmu/spp.c
+++ b/arch/x86/kvm/mmu/spp.c
@@ -433,6 +433,49 @@ int kvm_spp_mark_protection(struct kvm *kvm, u64 gfn, u32 access)
 	return ret;
 }
 
+static bool is_spp_protected(struct kvm_memory_slot *slot, gfn_t gfn, int level)
+{
+	int page_num = KVM_PAGES_PER_HPAGE(level);
+	u32 *access;
+	gfn_t gfn_max;
+
+	gfn &= ~(page_num - 1);
+	gfn_max = gfn + page_num - 1;
+	for (; gfn <= gfn_max; gfn++) {
+		access = gfn_to_subpage_wp_info(slot, gfn);
+		if (access && *access != FULL_SPP_ACCESS)
+			return true;
+	}
+	return false;
+}
+
+void check_spp_protection(struct kvm_vcpu *vcpu, gfn_t gfn,
+			  int *max_level)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_memory_slot *slot;
+	bool protected;
+
+	if (!kvm->arch.spp_active)
+		return;
+
+	slot = gfn_to_memslot(kvm, gfn);
+
+	if (!slot)
+		return;
+
+	protected = is_spp_protected(slot, gfn, PT_DIRECTORY_LEVEL);
+
+	if (protected) {
+		*max_level = PT_PAGE_TABLE_LEVEL;
+	} else if (*max_level == PT_PDPE_LEVEL &&
+		   is_spp_protected(slot, gfn, PT_PDPE_LEVEL)) {
+		*max_level = PT_DIRECTORY_LEVEL;
+	}
+
+	return;
+}
+
 int kvm_vm_ioctl_get_subpages(struct kvm *kvm,
 			      u64 gfn,
 			      u32 npages,
diff --git a/arch/x86/kvm/mmu/spp.h b/arch/x86/kvm/mmu/spp.h
index c3588c20be52..e0541901ec41 100644
--- a/arch/x86/kvm/mmu/spp.h
+++ b/arch/x86/kvm/mmu/spp.h
@@ -11,6 +11,8 @@ int kvm_spp_get_permission(struct kvm *kvm, u64 gfn, u32 npages,
 int kvm_spp_set_permission(struct kvm *kvm, u64 gfn, u32 npages,
 			   u32 *access_map);
 int kvm_spp_mark_protection(struct kvm *kvm, u64 gfn, u32 access);
+void check_spp_protection(struct kvm_vcpu *vcpu, gfn_t gfn,
+			  int *max_level);
 int kvm_vm_ioctl_get_subpages(struct kvm *kvm,
 			      u64 gfn,
 			      u32 npages,
-- 
2.17.2