Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Zhang Yi <yi.z.zhang@linux.intel.com>
To:     pbonzini@redhat.com, mdontu@bitdefender.com, ncitu@bitdefender.com
Cc:     rkrcmar@redhat.com, linux-kernel@vger.kernel.org,
        kvm@vger.kernel.org, Zhang Yi <yi.z.zhang@linux.intel.com>
Subject: [RFC PATCH V2 07/11] KVM: VMX: Added handle of SPP write protection fault.
Date:   Fri, 30 Nov 2018 16:08:48 +0800
Message-Id: <b77f9e8df8c587d78c680ee49d447f56f206de70.1543481993.git.yi.z.zhang@linux.intel.com>
In-Reply-To: <cover.1543481993.git.yi.z.zhang@linux.intel.com>
References: <cover.1543481993.git.yi.z.zhang@linux.intel.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

A control bit in EPT leaf paging-structure entries is defined as
“Sub-Page Permission” (SPP bit). The bit position is 61

While hardware walking the SPP page table, If the sub-page
region write permission bit is set, the write is allowed,
else the write is disallowed and results in an EPT violation.

we need peek this case in EPT violation handler, and trigger
a user-space exit, return the write protected address(GPA)
to user(qemu).

Signed-off-by: Zhang Yi <yi.z.zhang@linux.intel.com>
Signed-off-by: He Chen <he.chen@linux.intel.com>
---
 arch/x86/kvm/mmu.c       | 19 +++++++++++++++++++
 arch/x86/kvm/mmu.h       |  1 +
 include/uapi/linux/kvm.h |  5 +++++
 3 files changed, 25 insertions(+)

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d1f1fe1..d077693 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3378,6 +3378,21 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
 		if ((error_code & PFERR_WRITE_MASK) &&
 		    spte_can_locklessly_be_made_writable(spte))
 		{
+			/*
+			 * Record write protect fault caused by
+			 * Sub-page Protection
+			 */
+			if (spte & PT_SPP_MASK) {
+				fault_handled = true;
+
+				vcpu->run->exit_reason = KVM_EXIT_SPP;
+				vcpu->run->spp.addr = gva;
+				kvm_skip_emulated_instruction(vcpu);
+
+				/* Let QEMU decide how to handle this. */
+				break;
+			}
+
 			new_spte |= PT_WRITABLE_MASK;
 
 			/*
@@ -5343,6 +5358,10 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
 		r = vcpu->arch.mmu->page_fault(vcpu, cr2,
 					       lower_32_bits(error_code),
 					       false);
+
+		if (vcpu->run->exit_reason == KVM_EXIT_SPP)
+			return 0;
+
 		WARN_ON(r == RET_PF_INVALID);
 	}
 
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index c7b3331..b41e9e9 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -26,6 +26,7 @@
 #define PT_PAGE_SIZE_MASK (1ULL << PT_PAGE_SIZE_SHIFT)
 #define PT_PAT_MASK (1ULL << 7)
 #define PT_GLOBAL_MASK (1ULL << 8)
+#define PT_SPP_MASK (1ULL << 61)
 #define PT64_NX_SHIFT 63
 #define PT64_NX_MASK (1ULL << PT64_NX_SHIFT)
 
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 2b7a652..01174f8 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -235,6 +235,7 @@ struct kvm_hyperv_exit {
 #define KVM_EXIT_S390_STSI        25
 #define KVM_EXIT_IOAPIC_EOI       26
 #define KVM_EXIT_HYPERV           27
+#define KVM_EXIT_SPP              28
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -390,6 +391,10 @@ struct kvm_run {
 		struct {
 			__u8 vector;
 		} eoi;
+		/* KVM_EXIT_SPP */
+		struct {
+			__u64 addr;
+		} spp;
 		/* KVM_EXIT_HYPERV */
 		struct kvm_hyperv_exit hyperv;
 		/* Fix the size of the union. */
-- 
2.7.4