kvm: defer huge page recovery vhost task to later

Some libraries want to ensure they are single threaded before forking,
so making the kernel's kvm huge page recovery process a vhost task of
the user process breaks those. The minijail library used by crosvm is
one such affected application.

Defer the task to after the first VM_RUN call, which occurs after the
parent process has forked all its jailed processes. This needs to happen
only once for the kvm instance, so introduce some general-purpose
infrastructure for that, too.  It's similar in concept to pthread_once;
except it is actually usable, because the callback takes a parameter.

Cc: Sean Christopherson <seanjc@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Tested-by: Alyssa Ross <hi@alyssa.is>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Message-ID: <20250123153543.2769928-1-kbusch@meta.com>
[Move call_once API to include/linux. - Paolo]
Cc: stable@vger.kernel.org
Fixes: d96c77b ("KVM: x86: switch hugepage recovery thread to vhost_task")
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Author: keithbusch

arch/x86/include/asm/kvm_host.h

@@ -27,6 +27,7 @@
 #include <linux/hyperv.h>
 #include <linux/kfifo.h>
 #include <linux/sched/vhost_task.h>
+#include <linux/call_once.h>
 
 #include <asm/apic.h>
 #include <asm/pvclock-abi.h>
@@ -1466,6 +1467,7 @@ struct kvm_arch {
 	struct kvm_x86_pmu_event_filter __rcu *pmu_event_filter;
 	struct vhost_task *nx_huge_page_recovery_thread;
 	u64 nx_huge_page_last;
+	struct once nx_once;
 
 #ifdef CONFIG_X86_64
 	/* The number of TDP MMU pages across all roots. */

arch/x86/kvm/mmu/mmu.c

@@ -7447,20 +7447,28 @@ static bool kvm_nx_huge_page_recovery_worker(void *data)
 	return true;
 }
 
-int kvm_mmu_post_init_vm(struct kvm *kvm)
+static void kvm_mmu_start_lpage_recovery(struct once *once)
 {
-	if (nx_hugepage_mitigation_hard_disabled)
-		return 0;
+	struct kvm_arch *ka = container_of(once, struct kvm_arch, nx_once);
+	struct kvm *kvm = container_of(ka, struct kvm, arch);
 
 	kvm->arch.nx_huge_page_last = get_jiffies_64();
 	kvm->arch.nx_huge_page_recovery_thread = vhost_task_create(
 		kvm_nx_huge_page_recovery_worker, kvm_nx_huge_page_recovery_worker_kill,
 		kvm, "kvm-nx-lpage-recovery");
 
+	if (kvm->arch.nx_huge_page_recovery_thread)
+		vhost_task_start(kvm->arch.nx_huge_page_recovery_thread);
+}
+
+int kvm_mmu_post_init_vm(struct kvm *kvm)
+{
+	if (nx_hugepage_mitigation_hard_disabled)
+		return 0;
+
+	call_once(&kvm->arch.nx_once, kvm_mmu_start_lpage_recovery);
 	if (!kvm->arch.nx_huge_page_recovery_thread)
 		return -ENOMEM;
-
-	vhost_task_start(kvm->arch.nx_huge_page_recovery_thread);
 	return 0;
 }
 

arch/x86/kvm/x86.c

@@ -11471,6 +11471,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 	struct kvm_run *kvm_run = vcpu->run;
 	int r;
 
+	r = kvm_mmu_post_init_vm(vcpu->kvm);
+	if (r)
+		return r;
+
 	vcpu_load(vcpu);
 	kvm_sigset_activate(vcpu);
 	kvm_run->flags = 0;
@@ -12748,7 +12752,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 int kvm_arch_post_init_vm(struct kvm *kvm)
 {
-	return kvm_mmu_post_init_vm(kvm);
+	once_init(&kvm->arch.nx_once);
+	return 0;
 }
 
 static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)

include/linux/call_once.h

@@ -0,0 +1,45 @@
+#ifndef _LINUX_CALL_ONCE_H
+#define _LINUX_CALL_ONCE_H
+
+#include <linux/types.h>
+#include <linux/mutex.h>
+
+#define ONCE_NOT_STARTED 0
+#define ONCE_RUNNING     1
+#define ONCE_COMPLETED   2
+
+struct once {
+        atomic_t state;
+        struct mutex lock;
+};
+
+static inline void __once_init(struct once *once, const char *name,
+			       struct lock_class_key *key)
+{
+        atomic_set(&once->state, ONCE_NOT_STARTED);
+        __mutex_init(&once->lock, name, key);
+}
+
+#define once_init(once)							\
+do {									\
+	static struct lock_class_key __key;				\
+	__once_init((once), #once, &__key);				\
+} while (0)
+
+static inline void call_once(struct once *once, void (*cb)(struct once *))
+{
+        /* Pairs with atomic_set_release() below.  */
+        if (atomic_read_acquire(&once->state) == ONCE_COMPLETED)
+                return;
+
+        guard(mutex)(&once->lock);
+        WARN_ON(atomic_read(&once->state) == ONCE_RUNNING);
+        if (atomic_read(&once->state) != ONCE_NOT_STARTED)
+                return;
+
+        atomic_set(&once->state, ONCE_RUNNING);
+        cb(once);
+        atomic_set_release(&once->state, ONCE_COMPLETED);
+}
+
+#endif /* _LINUX_CALL_ONCE_H */