To make apic access page migratable, we do not pin it in memory now.
When it is migrated, we should reload its physical address for all
vmcses. But when we tried to do this, all vcpu will access
kvm_arch->apic_access_page without any locking. This is not safe.
Actually, we do not need kvm_arch->apic_access_page anymore. Since
apic access page is not pinned in memory now, we can remove
kvm_arch->apic_access_page. When we need to write its physical address
into vmcs, use gfn_to_page() to get its page struct, which will also
pin it. And unpin it after then.
Suggested-by: Gleb Natapov <gleb@xxxxxxxxxx>
Signed-off-by: Tang Chen <tangchen@xxxxxxxxxxxxxx>
---
arch/x86/include/asm/kvm_host.h | 2 +-
arch/x86/kvm/vmx.c | 17 ++++++++++-------
arch/x86/kvm/x86.c | 16 ++++++++++------
3 files changed, 21 insertions(+), 14 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 408b944..e27e1f9 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -576,7 +576,7 @@ 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 40bb9fc..4069075 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -4010,7 +4010,7 @@ 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;
@@ -4026,7 +4026,12 @@ static int alloc_apic_access_page(struct kvm *kvm)
goto out;
}
- kvm->arch.apic_access_page = page;
+ /*
+ * Do not pin apic access page in memory so that memory hotplug
+ * process is able to migrate it.
+ */
+ put_page(page);
+ kvm->arch.apic_access_page_done = true;
out:
mutex_unlock(&kvm->slots_lock);
return r;
@@ -4541,9 +4546,8 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu)
vmcs_write32(TPR_THRESHOLD, 0);
}
- if (vm_need_virtualize_apic_accesses(vmx->vcpu.kvm))
- vmcs_write64(APIC_ACCESS_ADDR,
- page_to_phys(vmx->vcpu.kvm->arch.apic_access_page));
+ /* Reload apic access page in case it was migrated. */
+ kvm_vcpu_reload_apic_access_page(vcpu);
if (vmx_vm_has_apicv(vcpu->kvm))
memset(&vmx->pi_desc, 0, sizeof(struct pi_desc));
@@ -8026,8 +8030,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
} else if (vm_need_virtualize_apic_accesses(vmx->vcpu.kvm)) {
exec_control |=
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
- vmcs_write64(APIC_ACCESS_ADDR,
- page_to_phys(vcpu->kvm->arch.apic_access_page));
+ kvm_vcpu_reload_apic_access_page(vcpu);
}
vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e042ef6..f7cbc36 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5991,6 +5991,8 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
{
+ struct page *page = NULL;
+
/*
* If platform doesn't have 2nd exec virtualize apic access affinity,
* set_apic_access_page_addr() will be set to NULL in hardware_setup(),
@@ -6004,10 +6006,14 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
* migrated, GUP will wait till the migrate entry is replaced
* with the new pte entry pointing to the new page.
*/
- 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 so that memory hotplug
+ * process is able to migrate it.
+ */
+ put_page(page);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page);
@@ -7272,8 +7278,6 @@ 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));
}
--
1.8.3.1
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
