kvm: x86: Unpin and remove kvm_arch->apic_access_page

In order to make the APIC access page migratable, stop pinning it in
memory.

And because the APIC access page is not pinned in memory, we can
remove kvm_arch->apic_access_page.  When we need to write its
physical address into vmcs, we use gfn_to_page() to get its page
struct, which is needed to call page_to_phys(); the page is then
immediately unpinned.

Suggested-by: Gleb Natapov <gleb@kernel.org>
Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 60f9d73..7d603a7 100644 (file)
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -574,7 +574,7 @@ struct kvm_arch {
        struct kvm_apic_map *apic_map;
 
        unsigned int tss_addr;
-       struct page *apic_access_page;
+       bool apic_access_page_done;
 
        gpa_t wall_clock;
 

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 881d266..04fa1b8 100644 (file)
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -4033,7 +4033,7 @@ static int alloc_apic_access_page(struct kvm *kvm)
        int r = 0;
 
        mutex_lock(&kvm->slots_lock);
-       if (kvm->arch.apic_access_page)
+       if (kvm->arch.apic_access_page_done)
                goto out;
        kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT;
        kvm_userspace_mem.flags = 0;
@@ -4049,7 +4049,12 @@ static int alloc_apic_access_page(struct kvm *kvm)
                goto out;
        }
 
-       kvm->arch.apic_access_page = page;
+       /*
+        * Do not pin the page in memory, so that memory hot-unplug
+        * is able to migrate it.
+        */
+       put_page(page);
+       kvm->arch.apic_access_page_done = true;
 out:
        mutex_unlock(&kvm->slots_lock);
        return r;

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c1412f5..6857257 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6028,19 +6028,31 @@ static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
 
 void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
 {
+       struct page *page = NULL;
+
        if (!kvm_x86_ops->set_apic_access_page_addr)
                return;
 
-       vcpu->kvm->arch.apic_access_page = gfn_to_page(vcpu->kvm,
-                       APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
-       kvm_x86_ops->set_apic_access_page_addr(vcpu,
-                       page_to_phys(vcpu->kvm->arch.apic_access_page));
+       page = gfn_to_page(vcpu->kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
+       kvm_x86_ops->set_apic_access_page_addr(vcpu, page_to_phys(page));
+
+       /*
+        * Do not pin apic access page in memory, the MMU notifier
+        * will call us again if it is migrated or swapped out.
+        */
+       put_page(page);
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page);
 
 void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
                                           unsigned long address)
 {
+       /*
+        * The physical address of apic access page is stored in the VMCS.
+        * Update it when it becomes invalid.
+        */
+       if (address == gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT))
+               kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD);
 }
 
 /*
@@ -7297,8 +7309,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
        kfree(kvm->arch.vpic);
        kfree(kvm->arch.vioapic);
        kvm_free_vcpus(kvm);
-       if (kvm->arch.apic_access_page)
-               put_page(kvm->arch.apic_access_page);
        kfree(rcu_dereference_check(kvm->arch.apic_map, 1));
 }