[PATCH 13/24] kvm: x86/mmu: Only free tdp_mmu pages after a grace period

From: Ben Gardon <bgardon@google.com>
To: linux-kernel@vger.kernel.org, kvm@vger.kernel.org
Cc: Paolo Bonzini <pbonzini@redhat.com>, Peter Xu <peterx@redhat.com>,
	Sean Christopherson <seanjc@google.com>,
	Peter Shier <pshier@google.com>,
	Peter Feiner <pfeiner@google.com>,
	Junaid Shahid <junaids@google.com>,
	Jim Mattson <jmattson@google.com>,
	Yulei Zhang <yulei.kernel@gmail.com>,
	Wanpeng Li <kernellwp@gmail.com>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	Xiao Guangrong <xiaoguangrong.eric@gmail.com>,
	Ben Gardon <bgardon@google.com>
Subject: [PATCH 13/24] kvm: x86/mmu: Only free tdp_mmu pages after a grace period
Date: Tue, 12 Jan 2021 10:10:30 -0800	[thread overview]
Message-ID: <20210112181041.356734-14-bgardon@google.com> (raw)
In-Reply-To: <20210112181041.356734-1-bgardon@google.com>

By waiting until an RCU grace period has elapsed to free TDP MMU PT memory,
the system can ensure that no kernel threads access the memory after it
has been freed.

Reviewed-by: Peter Feiner <pfeiner@google.com>

Signed-off-by: Ben Gardon <bgardon@google.com>
---
 arch/x86/kvm/mmu/mmu_internal.h |  3 +++
 arch/x86/kvm/mmu/tdp_mmu.c      | 31 +++++++++++++++++++++++++++++--
 2 files changed, 32 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index bfc6389edc28..7f599cc64178 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -57,6 +57,9 @@ struct kvm_mmu_page {
 	atomic_t write_flooding_count;
 
 	bool tdp_mmu_page;
+
+	/* Used for freeing the page asyncronously if it is a TDP MMU page. */
+	struct rcu_head rcu_head;
 };
 
 extern struct kmem_cache *mmu_page_header_cache;
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 662907d374b3..dc5b4bf34ca2 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -42,6 +42,12 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
 		return;
 
 	WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots));
+
+	/*
+	 * Ensure that all the outstanding RCU callbacks to free shadow pages
+	 * can run before the VM is torn down.
+	 */
+	rcu_barrier();
 }
 
 static void tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root)
@@ -196,6 +202,28 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu)
 	return __pa(root->spt);
 }
 
+static void tdp_mmu_free_sp(struct kvm_mmu_page *sp)
+{
+	free_page((unsigned long)sp->spt);
+	kmem_cache_free(mmu_page_header_cache, sp);
+}
+
+/*
+ * This is called through call_rcu in order to free TDP page table memory
+ * safely with respect to other kernel threads that may be operating on
+ * the memory.
+ * By only accessing TDP MMU page table memory in an RCU read critical
+ * section, and freeing it after a grace period, lockless access to that
+ * memory won't use it after it is freed.
+ */
+static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head)
+{
+	struct kvm_mmu_page *sp = container_of(head, struct kvm_mmu_page,
+					       rcu_head);
+
+	tdp_mmu_free_sp(sp);
+}
+
 static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
 				u64 old_spte, u64 new_spte, int level);
 
@@ -273,8 +301,7 @@ static void handle_disconnected_tdp_mmu_page(struct kvm *kvm, u64 *pt)
 	kvm_flush_remote_tlbs_with_address(kvm, gfn,
 					   KVM_PAGES_PER_HPAGE(level));
 
-	free_page((unsigned long)pt);
-	kmem_cache_free(mmu_page_header_cache, sp);
+	call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback);
 }
 
 /**
-- 
2.30.0.284.gd98b1dd5eaa7-goog

