KVM: TDX: Move external page table freeing to TDX code

Move the freeing of external page tables into the reclaim operation that
lives in TDX code.

The TDP MMU supports traversing the TDP without holding locks. Page tables
need to be freed via RCU to prevent walking one that gets freed.

While none of these lockless walk operations actually happen for the mirror
page table, the TDP MMU nonetheless frees the mirror page table in the same
way, and (because it's a handy place to plug it in) the external page table
as well.

However, the external page table definitely can't be walked once the page
table pages are reclaimed from the TDX module. The TDX module releases the
page for the host VMM to use, so this RCU-time free is unnecessary for the
external page table.

So move the free_page() call to TDX code. Create an
tdp_mmu_free_unused_sp() to allow for freeing external page tables that
have never left the TDP MMU code (i.e. don't need to be freed in a special
way).

Link: https://lore.kernel.org/kvm/aYpjNrtGmogNzqwT@google.com
[Based on a diff by Sean, added log]
Co-developed-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
Link: https://patch.msgid.link/20260509075740.4371-1-yan.y.zhao@intel.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 74531e4bbee62bd5052fd27b9b13e304c3d7f599..5b3041138301b55b8c77ac1557ebf551bc4dfbcd 100644 (file)
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -53,13 +53,18 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
        rcu_barrier();
 }
 
-static void tdp_mmu_free_sp(struct kvm_mmu_page *sp)
+static void __tdp_mmu_free_sp(struct kvm_mmu_page *sp)
 {
-       free_page((unsigned long)sp->external_spt);
        free_page((unsigned long)sp->spt);
        kmem_cache_free(mmu_page_header_cache, sp);
 }
 
+static void tdp_mmu_free_unused_sp(struct kvm_mmu_page *sp)
+{
+       free_page((unsigned long)sp->external_spt);
+       __tdp_mmu_free_sp(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
@@ -73,7 +78,8 @@ 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);
+       WARN_ON_ONCE(sp->external_spt);
+       __tdp_mmu_free_sp(sp);
 }
 
 void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root)
@@ -1268,7 +1274,7 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
                 * failed, e.g. because a different task modified the SPTE.
                 */
                if (r) {
-                       tdp_mmu_free_sp(sp);
+                       tdp_mmu_free_unused_sp(sp);
                        goto retry;
                }
 
@@ -1579,7 +1585,7 @@ retry:
         * installs its own sp in place of the last sp we tried to split.
         */
        if (sp)
-               tdp_mmu_free_sp(sp);
+               tdp_mmu_free_unused_sp(sp);
 
        return 0;
 }

diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index b3185cd9c6d6507eef6c24438084d77997d10518..54f9eb1a0202aaf639bcfc994e6b1e502690f60d 100644 (file)
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -1869,7 +1869,16 @@ static void tdx_sept_free_private_spt(struct kvm *kvm, struct kvm_mmu_page *sp)
         */
        if (KVM_BUG_ON(is_hkid_assigned(to_kvm_tdx(kvm)), kvm) ||
            tdx_reclaim_page(virt_to_page(sp->external_spt)))
-               sp->external_spt = NULL;
+               goto out;
+
+       /*
+        * Immediately free the S-EPT page because RCU-time free is unnecessary
+        * after TDH.PHYMEM.PAGE.RECLAIM ensures there are no outstanding
+        * readers.
+        */
+       free_page((unsigned long)sp->external_spt);
+out:
+       sp->external_spt = NULL;
 }
 
 void tdx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,