[PATCH] KVM: MMU: Fix softlockup due to mmu_lock is held too long

[Wanpeng Li]

From: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>

watchdog: BUG: soft lockup - CPU#5 stuck for 22s! [warn_test:3089]
 irq event stamp: 20532
 hardirqs last  enabled at (20531): [<ffffffff8e9b6908>] restore_regs_and_iret+0x0/0x1d
 hardirqs last disabled at (20532): [<ffffffff8e9b7ae8>] apic_timer_interrupt+0x98/0xb0
 softirqs last  enabled at (8266): [<ffffffff8e9badc6>] __do_softirq+0x206/0x4c1
 softirqs last disabled at (8253): [<ffffffff8e083918>] irq_exit+0xf8/0x100
 CPU: 5 PID: 3089 Comm: warn_test Tainted: G           OE   4.13.0-rc3+ #8
 RIP: 0010:kvm_mmu_prepare_zap_page+0x72/0x4b0 [kvm]
 Call Trace:
  make_mmu_pages_available.isra.120+0x71/0xc0 [kvm]
  kvm_mmu_load+0x1cf/0x410 [kvm]
  kvm_arch_vcpu_ioctl_run+0x1316/0x1bf0 [kvm]
  kvm_vcpu_ioctl+0x340/0x700 [kvm]
  ? kvm_vcpu_ioctl+0x340/0x700 [kvm]
  ? __fget+0xfc/0x210
  do_vfs_ioctl+0xa4/0x6a0
  ? __fget+0x11d/0x210
  SyS_ioctl+0x79/0x90
  entry_SYSCALL_64_fastpath+0x23/0xc2
  ? __this_cpu_preempt_check+0x13/0x20

This can be reproduced readily by ept=N and running syzkaller tests since 
many syzkaller testcases don't setup any memory regions. However, if ept=Y
rmode identity map will be created, then kvm_mmu_calculate_mmu_pages() will 
extend the number of VM's mmu pages to at least KVM_MIN_ALLOC_MMU_PAGES 
which just hide the issue.

I saw the scenario kvm->arch.n_max_mmu_pages == 0 && kvm->arch.n_used_mmu_pages == 1,
so there is one active mmu page on the list, kvm_mmu_prepare_zap_page() fails 
to zap any pages, however prepare_zap_oldest_mmu_page() always returns true.
It incurs infinite loop in make_mmu_pages_available() which causes mmu->lock 
softlockup.

This patch fixes it by setting the return value of prepare_zap_oldest_mmu_page()
according to whether or not there is mmu page zapped. In addition, we bail out 
immediately if there is no available mmu page to alloc root page.

Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Radim KrÄmÃÅ <rkrcmar@xxxxxxxxxx>
Signed-off-by: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>
---
 arch/x86/kvm/mmu.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 9b1dd11..b9897e8 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2608,9 +2608,7 @@ static bool prepare_zap_oldest_mmu_page(struct kvm *kvm,
 
 	sp = list_last_entry(&kvm->arch.active_mmu_pages,
 			     struct kvm_mmu_page, link);
-	kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
-
-	return true;
+	return kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
 }
 
 /*
@@ -3379,6 +3377,10 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) {
 		spin_lock(&vcpu->kvm->mmu_lock);
 		make_mmu_pages_available(vcpu);
+		if (!kvm_mmu_available_pages(vcpu->kvm)) {
+			spin_unlock(&vcpu->kvm->mmu_lock);
+			return 1;
+		}
 		sp = kvm_mmu_get_page(vcpu, 0, 0, PT64_ROOT_LEVEL, 1, ACC_ALL);
 		++sp->root_count;
 		spin_unlock(&vcpu->kvm->mmu_lock);
@@ -3390,6 +3392,10 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
 			MMU_WARN_ON(VALID_PAGE(root));
 			spin_lock(&vcpu->kvm->mmu_lock);
 			make_mmu_pages_available(vcpu);
+			if (!kvm_mmu_available_pages(vcpu->kvm)) {
+				spin_unlock(&vcpu->kvm->mmu_lock);
+				return 1;
+			}
 			sp = kvm_mmu_get_page(vcpu, i << (30 - PAGE_SHIFT),
 					i << 30, PT32_ROOT_LEVEL, 1, ACC_ALL);
 			root = __pa(sp->spt);
@@ -3427,6 +3433,10 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 
 		spin_lock(&vcpu->kvm->mmu_lock);
 		make_mmu_pages_available(vcpu);
+		if (!kvm_mmu_available_pages(vcpu->kvm)) {
+			spin_unlock(&vcpu->kvm->mmu_lock);
+			return 1;
+		}
 		sp = kvm_mmu_get_page(vcpu, root_gfn, 0, PT64_ROOT_LEVEL,
 				      0, ACC_ALL);
 		root = __pa(sp->spt);
-- 
2.7.4