[PATCH] kvm: defer huge page recovery vhost task to later

[Keith Busch <kbusch@meta.com>]

From: Keith Busch <kbusch@kernel.org>

Some libraries ensure they are single threaded before forking. This
assumption breaks after making kvm hugepage recovery thread a vhost task
of the user process. 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 child processes and should be
safe to start the vhost task.

Link: https://lore.kernel.org/kvm/Z2RYyagu3phDFIac@kbusch-mbp.dhcp.thefacebook.com/
Fixes: d96c77bd4eeba46 ("KVM: x86: switch hugepage recovery thread to vhost_task")
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 arch/x86/kvm/mmu/mmu.c   |  2 ++
 arch/x86/kvm/x86.c       |  9 ++++-----
 include/linux/kvm_host.h |  1 -
 virt/kvm/kvm_main.c      | 15 ---------------
 4 files changed, 6 insertions(+), 21 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 2401606db2604..422b6b06de4fe 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -7415,6 +7415,8 @@ int kvm_mmu_post_init_vm(struct kvm *kvm)
 {
 	if (nx_hugepage_mitigation_hard_disabled)
 		return 0;
+	if (kvm->arch.nx_huge_page_recovery_thread)
+		return 0;
 
 	kvm->arch.nx_huge_page_last = get_jiffies_64();
 	kvm->arch.nx_huge_page_recovery_thread = vhost_task_create(
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c79a8cc57ba42..263363c46626b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -11463,6 +11463,10 @@ 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;
@@ -12740,11 +12744,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	return ret;
 }
 
-int kvm_arch_post_init_vm(struct kvm *kvm)
-{
-	return kvm_mmu_post_init_vm(kvm);
-}
-
 static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
 {
 	vcpu_load(vcpu);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 401439bb21e3e..a219bd2d8aec8 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1596,7 +1596,6 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);
 bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu);
 bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu);
 bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu);
-int kvm_arch_post_init_vm(struct kvm *kvm);
 void kvm_arch_pre_destroy_vm(struct kvm *kvm);
 void kvm_arch_create_vm_debugfs(struct kvm *kvm);
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index de2c11dae2316..adacc6eaa7d9d 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1065,15 +1065,6 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, const char *fdname)
 	return ret;
 }
 
-/*
- * Called after the VM is otherwise initialized, but just before adding it to
- * the vm_list.
- */
-int __weak kvm_arch_post_init_vm(struct kvm *kvm)
-{
-	return 0;
-}
-
 /*
  * Called just after removing the VM from the vm_list, but before doing any
  * other destruction.
@@ -1194,10 +1185,6 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	if (r)
 		goto out_err_no_debugfs;
 
-	r = kvm_arch_post_init_vm(kvm);
-	if (r)
-		goto out_err;
-
 	mutex_lock(&kvm_lock);
 	list_add(&kvm->vm_list, &vm_list);
 	mutex_unlock(&kvm_lock);
@@ -1207,8 +1194,6 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 
 	return kvm;
 
-out_err:
-	kvm_destroy_vm_debugfs(kvm);
 out_err_no_debugfs:
 	kvm_coalesced_mmio_free(kvm);
 out_no_coalesced_mmio:
-- 
2.43.5