linux-kernel - [RFC PATCH v2 18/18] KVM: TDX: Add macro to retry SEAMCALLs when forcing vCPUs out of guest

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: <20250829000618.351013-19-seanjc@google.com>
Date: Thu, 28 Aug 2025 17:06:18 -0700
From: Sean Christopherson <seanjc@...gle.com>
To: Sean Christopherson <seanjc@...gle.com>, Paolo Bonzini <pbonzini@...hat.com>
Cc: kvm@...r.kernel.org, linux-kernel@...r.kernel.org, 
	Ira Weiny <ira.weiny@...el.com>, Kai Huang <kai.huang@...el.com>, 
	Michael Roth <michael.roth@....com>, Yan Zhao <yan.y.zhao@...el.com>, 
	Vishal Annapurve <vannapurve@...gle.com>, Rick Edgecombe <rick.p.edgecombe@...el.com>, 
	Ackerley Tng <ackerleytng@...gle.com>
Subject: [RFC PATCH v2 18/18] KVM: TDX: Add macro to retry SEAMCALLs when
 forcing vCPUs out of guest

Add a macro to handle kicking vCPUs out of the guest and retrying
SEAMCALLs on -EBUSY instead of providing small helpers to be used by each
SEAMCALL.  Wrapping the SEAMCALLs in a macro makes it a little harder to
tease out which SEAMCALL is being made, but significantly reduces the
amount of copy+paste code and makes it all but impossible to leave an
elevated wait_for_sept_zap.

Signed-off-by: Sean Christopherson <seanjc@...gle.com>
---
 arch/x86/kvm/vmx/tdx.c | 72 ++++++++++++++----------------------------
 1 file changed, 23 insertions(+), 49 deletions(-)

diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index aa740eeb1c2a..d6c9defad9cd 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -313,25 +313,24 @@ static void tdx_clear_page(struct page *page)
 	__mb();
 }
 
-static void tdx_no_vcpus_enter_start(struct kvm *kvm)
-{
-	struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
-
-	lockdep_assert_held_write(&kvm->mmu_lock);
-
-	WRITE_ONCE(kvm_tdx->wait_for_sept_zap, true);
-
-	kvm_make_all_cpus_request(kvm, KVM_REQ_OUTSIDE_GUEST_MODE);
-}
-
-static void tdx_no_vcpus_enter_stop(struct kvm *kvm)
-{
-	struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
-
-	lockdep_assert_held_write(&kvm->mmu_lock);
-
-	WRITE_ONCE(kvm_tdx->wait_for_sept_zap, false);
-}
+#define tdh_do_no_vcpus(tdh_func, kvm, args...)					\
+({										\
+	struct kvm_tdx *__kvm_tdx = to_kvm_tdx(kvm);				\
+	u64 __err;								\
+										\
+	lockdep_assert_held_write(&kvm->mmu_lock);				\
+										\
+	__err = tdh_func(args);							\
+	if (unlikely(tdx_operand_busy(__err))) {				\
+		WRITE_ONCE(__kvm_tdx->wait_for_sept_zap, true);			\
+		kvm_make_all_cpus_request(kvm, KVM_REQ_OUTSIDE_GUEST_MODE);	\
+										\
+		__err = tdh_func(args);						\
+										\
+		WRITE_ONCE(__kvm_tdx->wait_for_sept_zap, false);		\
+	}									\
+	__err;									\
+})
 
 /* TDH.PHYMEM.PAGE.RECLAIM is allowed only when destroying the TD. */
 static int __tdx_reclaim_page(struct page *page)
@@ -1714,14 +1713,7 @@ static void tdx_track(struct kvm *kvm)
 	if (unlikely(kvm_tdx->state != TD_STATE_RUNNABLE))
 		return;
 
-	err = tdh_mem_track(&kvm_tdx->td);
-	if (unlikely(tdx_operand_busy(err))) {
-		/* After no vCPUs enter, the second retry is expected to succeed */
-		tdx_no_vcpus_enter_start(kvm);
-		err = tdh_mem_track(&kvm_tdx->td);
-		tdx_no_vcpus_enter_stop(kvm);
-	}
-
+	err = tdh_do_no_vcpus(tdh_mem_track, kvm, &kvm_tdx->td);
 	TDX_BUG_ON(err, TDH_MEM_TRACK, kvm);
 
 	kvm_make_all_cpus_request(kvm, KVM_REQ_OUTSIDE_GUEST_MODE);
@@ -1773,14 +1765,8 @@ static void tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn,
 	if (KVM_BUG_ON(level != PG_LEVEL_4K, kvm))
 		return;
 
-	err = tdh_mem_range_block(&kvm_tdx->td, gpa, tdx_level, &entry, &level_state);
-	if (unlikely(tdx_operand_busy(err))) {
-		/* After no vCPUs enter, the second retry is expected to succeed */
-		tdx_no_vcpus_enter_start(kvm);
-		err = tdh_mem_range_block(&kvm_tdx->td, gpa, tdx_level, &entry, &level_state);
-		tdx_no_vcpus_enter_stop(kvm);
-	}
-
+	err = tdh_do_no_vcpus(tdh_mem_range_block, kvm, &kvm_tdx->td, gpa,
+			      tdx_level, &entry, &level_state);
 	if (TDX_BUG_ON_2(err, TDH_MEM_RANGE_BLOCK, entry, level_state, kvm))
 		return;
 
@@ -1795,20 +1781,8 @@ static void tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn,
 	 * with other vcpu sept operation.
 	 * Race with TDH.VP.ENTER due to (0-step mitigation) and Guest TDCALLs.
 	 */
-	err = tdh_mem_page_remove(&kvm_tdx->td, gpa, tdx_level, &entry,
-				  &level_state);
-
-	if (unlikely(tdx_operand_busy(err))) {
-		/*
-		 * The second retry is expected to succeed after kicking off all
-		 * other vCPUs and prevent them from invoking TDH.VP.ENTER.
-		 */
-		tdx_no_vcpus_enter_start(kvm);
-		err = tdh_mem_page_remove(&kvm_tdx->td, gpa, tdx_level, &entry,
-					  &level_state);
-		tdx_no_vcpus_enter_stop(kvm);
-	}
-
+	err = tdh_do_no_vcpus(tdh_mem_page_remove, kvm, &kvm_tdx->td, gpa,
+			      tdx_level, &entry, &level_state);
 	if (TDX_BUG_ON_2(err, TDH_MEM_PAGE_REMOVE, entry, level_state, kvm))
 		return;
 
-- 
2.51.0.318.gd7df087d1a-goog