Merge tag 'x86_tdx_for_6.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 TDX updates from Dave Hansen:
 "The biggest change here is making TDX and kexec play nicely together.

  Before this, the memory encryption hardware (which doesn't respect
  cache coherency) could write back old cachelines on top of data in the
  new kernel, so kexec and TDX were made mutually exclusive. This
  removes the limitation.

  There is also some work to tighten up a hardware bug workaround and
  some MAINTAINERS updates.

   - Make TDX and kexec work together

    - Skip TDX bug workaround when the bug is not present

    - Update maintainers entries"

* tag 'x86_tdx_for_6.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/virt/tdx: Use precalculated TDVPR page physical address
  KVM/TDX: Explicitly do WBINVD when no more TDX SEAMCALLs
  x86/virt/tdx: Update the kexec section in the TDX documentation
  x86/virt/tdx: Remove the !KEXEC_CORE dependency
  x86/kexec: Disable kexec/kdump on platforms with TDX partial write erratum
  x86/virt/tdx: Mark memory cache state incoherent when making SEAMCALL
  x86/sme: Use percpu boolean to control WBINVD during kexec
  x86/kexec: Consolidate relocate_kernel() function parameters
  x86/tdx: Skip clearing reclaimed pages unless X86_BUG_TDX_PW_MCE is present
  x86/tdx: Tidy reset_pamt functions
  x86/tdx: Eliminate duplicate code in tdx_clear_page()
  MAINTAINERS: Add KVM mail list to the TDX entry
  MAINTAINERS: Add Rick Edgecombe as a TDX reviewer
  MAINTAINERS: Update the file list in the TDX entry.

1 files changed, 22 insertions, 22 deletions

diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index ca9c8ec7dd01..00f8bfd2330d 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -281,25 +281,6 @@ static inline void tdx_disassociate_vp(struct kvm_vcpu *vcpu)
 	vcpu->cpu = -1;
 }
 
-static void tdx_clear_page(struct page *page)
-{
-	const void *zero_page = (const void *) page_to_virt(ZERO_PAGE(0));
-	void *dest = page_to_virt(page);
-	unsigned long i;
-
-	/*
-	 * The page could have been poisoned.  MOVDIR64B also clears
-	 * the poison bit so the kernel can safely use the page again.
-	 */
-	for (i = 0; i < PAGE_SIZE; i += 64)
-		movdir64b(dest + i, zero_page);
-	/*
-	 * MOVDIR64B store uses WC buffer.  Prevent following memory reads
-	 * from seeing potentially poisoned cache.
-	 */
-	__mb();
-}
-
 static void tdx_no_vcpus_enter_start(struct kvm *kvm)
 {
 	struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
@@ -345,7 +326,7 @@ static int tdx_reclaim_page(struct page *page)
 
 	r = __tdx_reclaim_page(page);
 	if (!r)
-		tdx_clear_page(page);
+		tdx_quirk_reset_page(page);
 	return r;
 }
 
@@ -442,6 +423,16 @@ void tdx_disable_virtualization_cpu(void)
 		tdx_flush_vp(&arg);
 	}
 	local_irq_restore(flags);
+
+	/*
+	 * Flush cache now if kexec is possible: this is necessary to avoid
+	 * having dirty private memory cachelines when the new kernel boots,
+	 * but WBINVD is a relatively expensive operation and doing it during
+	 * kexec can exacerbate races in native_stop_other_cpus().  Do it
+	 * now, since this is a safe moment and there is going to be no more
+	 * TDX activity on this CPU from this point on.
+	 */
+	tdx_cpu_flush_cache_for_kexec();
 }
 
 #define TDX_SEAMCALL_RETRIES 10000
@@ -593,7 +584,7 @@ static void tdx_reclaim_td_control_pages(struct kvm *kvm)
 		pr_tdx_error(TDH_PHYMEM_PAGE_WBINVD, err);
 		return;
 	}
-	tdx_clear_page(kvm_tdx->td.tdr_page);
+	tdx_quirk_reset_page(kvm_tdx->td.tdr_page);
 
 	__free_page(kvm_tdx->td.tdr_page);
 	kvm_tdx->td.tdr_page = NULL;
@@ -861,6 +852,7 @@ void tdx_vcpu_free(struct kvm_vcpu *vcpu)
 	if (tdx->vp.tdvpr_page) {
 		tdx_reclaim_control_page(tdx->vp.tdvpr_page);
 		tdx->vp.tdvpr_page = 0;
+		tdx->vp.tdvpr_pa = 0;
 	}
 
 	tdx->state = VCPU_TD_STATE_UNINITIALIZED;
@@ -1714,7 +1706,7 @@ static int tdx_sept_drop_private_spte(struct kvm *kvm, gfn_t gfn,
 		pr_tdx_error(TDH_PHYMEM_PAGE_WBINVD, err);
 		return -EIO;
 	}
-	tdx_clear_page(page);
+	tdx_quirk_reset_page(page);
 	tdx_unpin(kvm, page);
 	return 0;
 }
@@ -2940,6 +2932,13 @@ static int tdx_td_vcpu_init(struct kvm_vcpu *vcpu, u64 vcpu_rcx)
 		return -ENOMEM;
 	tdx->vp.tdvpr_page = page;
 
+	/*
+	 * page_to_phys() does not work in 'noinstr' code, like guest
+	 * entry via tdh_vp_enter(). Precalculate and store it instead
+	 * of doing it at runtime later.
+	 */
+	tdx->vp.tdvpr_pa = page_to_phys(tdx->vp.tdvpr_page);
+
 	tdx->vp.tdcx_pages = kcalloc(kvm_tdx->td.tdcx_nr_pages, sizeof(*tdx->vp.tdcx_pages),
 			       	     GFP_KERNEL);
 	if (!tdx->vp.tdcx_pages) {
@@ -3002,6 +3001,7 @@ free_tdvpr:
 	if (tdx->vp.tdvpr_page)
 		__free_page(tdx->vp.tdvpr_page);
 	tdx->vp.tdvpr_page = 0;
+	tdx->vp.tdvpr_pa = 0;
 
 	return ret;
 }