Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   yulei.kernel@gmail.com
To:     pbonzini@redhat.com
Cc:     kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
        sean.j.christopherson@intel.com, jmattson@google.com,
        junaids@google.com, bgardon@google.com, vkuznets@redhat.com,
        xiaoguangrong.eric@gmail.com, kernellwp@gmail.com,
        lihaiwei.kernel@gmail.com, Yulei Zhang <yuleixzhang@tencent.com>
Subject: [RFC V2 3/9] Introduce page table remove function for direct build EPT feature
Date:   Tue,  1 Sep 2020 19:55:23 +0800
Message-Id: <12f9b9140f811c1d87f01f94c1477b50d6410263.1598868204.git.yulei.kernel@gmail.com>
In-Reply-To: <cover.1598868203.git.yulei.kernel@gmail.com>
References: <cover.1598868203.git.yulei.kernel@gmail.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

From: Yulei Zhang <yuleixzhang@tencent.com>

During guest boots up it will modify the memory slots multiple times,
so add page table remove function to free pre-pinned memory according
to the the memory slot changes.

Signed-off-by: Yulei Zhang <yuleixzhang@tencent.com>
---
 arch/x86/kvm/mmu/mmu.c | 56 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 56 insertions(+)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index bfe4d2b3e809..03c5e73b96cb 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6482,6 +6482,62 @@ int kvm_direct_tdp_populate_page_table(struct kvm *kvm, struct kvm_memory_slot *
 	return 0;
 }
 
+static int __kvm_remove_spte(struct kvm *kvm, u64 *addr, gfn_t gfn, int level)
+{
+	int i;
+	int ret = level;
+	bool present = false;
+	kvm_pfn_t pfn;
+	u64 *sptep = (u64 *)__va((*addr) & PT64_BASE_ADDR_MASK);
+	unsigned index = SHADOW_PT_INDEX(gfn << PAGE_SHIFT, level);
+
+	for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
+		if (is_shadow_present_pte(sptep[i])) {
+			if (i == index) {
+				if (!is_last_spte(sptep[i], level)) {
+					ret = __kvm_remove_spte(kvm, &sptep[i], gfn, level - 1);
+					if (is_shadow_present_pte(sptep[i]))
+						return ret;
+				} else {
+					pfn = spte_to_pfn(sptep[i]);
+					mmu_spte_clear_track_bits(&sptep[i]);
+					kvm_release_pfn_clean(pfn);
+					if (present)
+						return ret;
+				}
+			} else {
+				if (i > index)
+					return ret;
+				else
+					present = true;
+			}
+		}
+	}
+
+	if (!present) {
+		pfn = spte_to_pfn(*addr);
+		mmu_spte_clear_track_bits(addr);
+		kvm_release_pfn_clean(pfn);
+	}
+	return ret;
+}
+
+void kvm_direct_tdp_remove_page_table(struct kvm *kvm, struct kvm_memory_slot *slot)
+{
+	gfn_t gfn = slot->base_gfn;
+	int host_level;
+
+	if (!kvm->arch.global_root_hpa)
+		return;
+
+	for (gfn = slot->base_gfn;
+		gfn < slot->base_gfn + slot->npages;
+		gfn += KVM_PAGES_PER_HPAGE(host_level))
+		host_level = __kvm_remove_spte(kvm, &(kvm->arch.global_root_hpa), gfn, PT64_ROOT_4LEVEL);
+
+	kvm_flush_remote_tlbs(kvm);
+}
+
 /*
  * Calculate mmu pages needed for kvm.
  */
-- 
2.17.1