[RFC PATCH 2/2] KVM: TDX: Kick off vCPUs when SEAMCALL is busy during TD page removal

[Yan Zhao <yan.y.zhao@intel.com>]

For tdh_mem_range_block(), tdh_mem_track(), tdh_mem_page_remove(),

- Upon detection of TDX_OPERAND_BUSY, retry each SEAMCALL only once.
- During the retry, kick off all vCPUs and prevent any vCPU from entering
  to avoid potential contentions.

Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
---
 arch/x86/include/asm/kvm_host.h |  2 ++
 arch/x86/kvm/vmx/tdx.c          | 49 +++++++++++++++++++++++++--------
 2 files changed, 40 insertions(+), 11 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 521c7cf725bc..bb7592110337 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -123,6 +123,8 @@
 #define KVM_REQ_HV_TLB_FLUSH \
 	KVM_ARCH_REQ_FLAGS(32, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_UPDATE_PROTECTED_GUEST_STATE	KVM_ARCH_REQ(34)
+#define KVM_REQ_NO_VCPU_ENTER_INPROGRESS \
+	KVM_ARCH_REQ_FLAGS(33, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 
 #define CR0_RESERVED_BITS                                               \
 	(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 60d9e9d050ad..ed6b41bbcec6 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -311,6 +311,20 @@ static void tdx_clear_page(unsigned long page_pa)
 	__mb();
 }
 
+static void tdx_no_vcpus_enter_start(struct kvm *kvm)
+{
+	kvm_make_all_cpus_request(kvm, KVM_REQ_NO_VCPU_ENTER_INPROGRESS);
+}
+
+static void tdx_no_vcpus_enter_stop(struct kvm *kvm)
+{
+	struct kvm_vcpu *vcpu;
+	unsigned long i;
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_clear_request(KVM_REQ_NO_VCPU_ENTER_INPROGRESS, vcpu);
+}
+
 /* TDH.PHYMEM.PAGE.RECLAIM is allowed only when destroying the TD. */
 static int __tdx_reclaim_page(hpa_t pa)
 {
@@ -1648,15 +1662,20 @@ static int tdx_sept_drop_private_spte(struct kvm *kvm, gfn_t gfn,
 	if (KVM_BUG_ON(!is_hkid_assigned(kvm_tdx), kvm))
 		return -EINVAL;
 
-	do {
-		/*
-		 * When zapping private page, write lock is held. So no race
-		 * condition with other vcpu sept operation.  Race only with
-		 * TDH.VP.ENTER.
-		 */
+	/*
+	 * When zapping private page, write lock is held. So no race
+	 * condition with other vcpu sept operation.  Race only with
+	 * TDH.VP.ENTER.
+	 */
+	err = tdh_mem_page_remove(kvm_tdx->tdr_pa, gpa, tdx_level, &entry,
+				  &level_state);
+	if ((err & TDX_OPERAND_BUSY)) {
+		/* After no vCPUs enter, the second retry is expected to succeed */
+		tdx_no_vcpus_enter_start(kvm);
 		err = tdh_mem_page_remove(kvm_tdx->tdr_pa, gpa, tdx_level, &entry,
 					  &level_state);
-	} while (unlikely(err == TDX_ERROR_SEPT_BUSY));
+		tdx_no_vcpus_enter_stop(kvm);
+	}
 
 	if (unlikely(kvm_tdx->state != TD_STATE_RUNNABLE &&
 		     err == (TDX_EPT_WALK_FAILED | TDX_OPERAND_ID_RCX))) {
@@ -1728,8 +1747,12 @@ static int tdx_sept_zap_private_spte(struct kvm *kvm, gfn_t gfn,
 	WARN_ON_ONCE(level != PG_LEVEL_4K);
 
 	err = tdh_mem_range_block(kvm_tdx->tdr_pa, gpa, tdx_level, &entry, &level_state);
-	if (unlikely(err == TDX_ERROR_SEPT_BUSY))
-		return -EAGAIN;
+	if (unlikely(err & TDX_OPERAND_BUSY)) {
+		/* After no vCPUs enter, the second retry is expected to succeed */
+		tdx_no_vcpus_enter_start(kvm);
+		err = tdh_mem_range_block(kvm_tdx->tdr_pa, gpa, tdx_level, &entry, &level_state);
+		tdx_no_vcpus_enter_stop(kvm);
+	}
 	if (KVM_BUG_ON(err, kvm)) {
 		pr_tdx_error_2(TDH_MEM_RANGE_BLOCK, err, entry, level_state);
 		return -EIO;
@@ -1772,9 +1795,13 @@ static void tdx_track(struct kvm *kvm)
 
 	lockdep_assert_held_write(&kvm->mmu_lock);
 
-	do {
+	err = tdh_mem_track(kvm_tdx->tdr_pa);
+	if ((err & TDX_SEAMCALL_STATUS_MASK) == TDX_OPERAND_BUSY) {
+		/* After no vCPUs enter, the second retry is expected to succeed */
+		tdx_no_vcpus_enter_start(kvm);
 		err = tdh_mem_track(kvm_tdx->tdr_pa);
-	} while (unlikely((err & TDX_SEAMCALL_STATUS_MASK) == TDX_OPERAND_BUSY));
+		tdx_no_vcpus_enter_stop(kvm);
+	}
 
 	if (KVM_BUG_ON(err, kvm))
 		pr_tdx_error(TDH_MEM_TRACK, err);
-- 
2.43.2