linux-kernel - [RFC PATCH v2 05/15] KVM: TDX: Pass size to reclaim

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1844264da0ccee5570a6eace87d386426a9ac4c7.1670541736.git.isaku.yamahata@intel.com>
Date:   Thu,  8 Dec 2022 15:35:40 -0800
From:   isaku.yamahata@...el.com
To:     kvm@...r.kernel.org, linux-kernel@...r.kernel.org
Cc:     isaku.yamahata@...el.com, isaku.yamahata@...il.com,
        Paolo Bonzini <pbonzini@...hat.com>,
        Sean Christopherson <seanjc@...gle.com>,
        David Matlack <dmatlack@...gle.com>
Subject: [RFC PATCH v2 05/15] KVM: TDX: Pass size to reclaim_page()

From: Xiaoyao Li <xiaoyao.li@...el.com>

A 2MB large page can be tdh_mem_page_aug()'ed to TD directly. In this case,
it needs to reclaim and clear the page as 2MB size.

Signed-off-by: Xiaoyao Li <xiaoyao.li@...el.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@...el.com>
---
 arch/x86/kvm/vmx/tdx.c | 27 +++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 5b392d9baa25..df213b488f89 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -184,14 +184,17 @@ void tdx_hardware_disable(void)
 		tdx_disassociate_vp(&tdx->vcpu);
 }
 
-static void tdx_clear_page(unsigned long page_pa)
+static void tdx_clear_page(unsigned long page_pa, int size)
 {
 	const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0)));
 	void *page = __va(page_pa);
 	unsigned long i;
 
+	WARN_ON_ONCE(size % PAGE_SIZE);
+
 	if (!static_cpu_has(X86_FEATURE_MOVDIR64B)) {
-		clear_page(page);
+		for (i = 0; i < size; i += PAGE_SIZE)
+			clear_page(page + i);
 		return;
 	}
 
@@ -204,7 +207,7 @@ static void tdx_clear_page(unsigned long page_pa)
 	 * The cache line could be poisoned (even without MKTME-i), clear the
 	 * poison bit.
 	 */
-	for (i = 0; i < PAGE_SIZE; i += 64)
+	for (i = 0; i < size; i += 64)
 		movdir64b(page + i, zero_page);
 	/*
 	 * MOVDIR64B store uses WC buffer.  Prevent following memory reads
@@ -213,7 +216,8 @@ static void tdx_clear_page(unsigned long page_pa)
 	__mb();
 }
 
-static int tdx_reclaim_page(hpa_t pa, bool do_wb, u16 hkid)
+static int tdx_reclaim_page(hpa_t pa, enum pg_level level,
+			    bool do_wb, u16 hkid)
 {
 	struct tdx_module_output out;
 	u64 err;
@@ -231,8 +235,10 @@ static int tdx_reclaim_page(hpa_t pa, bool do_wb, u16 hkid)
 		pr_tdx_error(TDH_PHYMEM_PAGE_RECLAIM, err, &out);
 		return -EIO;
 	}
+	/* out.r8 == tdx sept page level */
+	WARN_ON_ONCE(out.r8 != pg_level_to_tdx_sept_level(level));
 
-	if (do_wb) {
+	if (do_wb && level == PG_LEVEL_4K) {
 		/*
 		 * Only TDR page gets into this path.  No contention is expected
 		 * because the last page of TD.
@@ -244,7 +250,7 @@ static int tdx_reclaim_page(hpa_t pa, bool do_wb, u16 hkid)
 		}
 	}
 
-	tdx_clear_page(pa);
+	tdx_clear_page(pa, KVM_HPAGE_SIZE(level));
 	return 0;
 }
 
@@ -275,7 +281,7 @@ static void tdx_reclaim_td_page(struct tdx_td_page *page)
 		 * was already flushed by TDH.PHYMEM.CACHE.WB before here, So
 		 * cache doesn't need to be flushed again.
 		 */
-		if (tdx_reclaim_page(page->pa, false, 0))
+		if (tdx_reclaim_page(page->pa, PG_LEVEL_4K, false, 0))
 			return;
 
 		page->added = false;
@@ -428,7 +434,8 @@ void tdx_vm_free(struct kvm *kvm)
 	 * TDX global HKID is needed.
 	 */
 	if (kvm_tdx->tdr.added &&
-		tdx_reclaim_page(kvm_tdx->tdr.pa, true, tdx_global_keyid))
+		tdx_reclaim_page(kvm_tdx->tdr.pa, PG_LEVEL_4K, true,
+				 tdx_global_keyid))
 		return;
 
 	free_page((unsigned long)__va(kvm_tdx->tdr.pa));
@@ -1398,7 +1405,7 @@ static int tdx_sept_drop_private_spte(struct kvm *kvm, gfn_t gfn,
 		 * The HKID assigned to this TD was already freed and cache
 		 * was already flushed. We don't have to flush again.
 		 */
-		err = tdx_reclaim_page(hpa, false, 0);
+		err = tdx_reclaim_page(hpa, level, false, 0);
 		if (KVM_BUG_ON(err, kvm))
 			return -EIO;
 		tdx_unpin(kvm, pfn);
@@ -1537,7 +1544,7 @@ static int tdx_sept_free_private_spt(struct kvm *kvm, gfn_t gfn,
 	 * already flushed. We don't have to flush again.
 	 */
 	if (!is_hkid_assigned(kvm_tdx))
-		return tdx_reclaim_page(__pa(private_spt), false, 0);
+		return tdx_reclaim_page(__pa(private_spt), PG_LEVEL_4K, false, 0);
 
 	/*
 	 * free_private_spt() is (obviously) called when a shadow page is being
-- 
2.25.1