KVM: x86: switch hugepage recovery thread to vhost_task

kvm_vm_create_worker_thread() is meant to be used for kthreads that
can consume significant amounts of CPU time on behalf of a VM or in
response to how the VM behaves (for example how it accesses its memory).
Therefore it wants to charge the CPU time consumed by that work to
the VM's container.

However, because of these threads, cgroups which have kvm instances
inside never complete freezing.  This can be trivially reproduced:

  root@test ~# mkdir /sys/fs/cgroup/test
  root@test ~# echo $$ > /sys/fs/cgroup/test/cgroup.procs
  root@test ~# qemu-system-x86_64 -nographic -enable-kvm

and in another terminal:

  root@test ~# echo 1 > /sys/fs/cgroup/test/cgroup.freeze
  root@test ~# cat /sys/fs/cgroup/test/cgroup.events
  populated 1
  frozen 0

The cgroup freezing happens in the signal delivery path but
kvm_nx_huge_page_recovery_worker, while joining non-root cgroups, never
calls into the signal delivery path and thus never gets frozen. Because
the cgroup freezer determines whether a given cgroup is frozen by
comparing the number of frozen threads to the total number of threads
in the cgroup, the cgroup never becomes frozen and users waiting for
the state transition may hang indefinitely.

Since the worker kthread is tied to a user process, it's better if
it behaves similarly to user tasks as much as possible, including
being able to send SIGSTOP and SIGCONT.  In fact, vhost_task is all
that kvm_vm_create_worker_thread() wanted to be and more: not only it
inherits the userspace process's cgroups, it has other niceties like
being parented properly in the process tree.  Use it instead of the
homegrown alternative.

Incidentally, the new code is also better behaved when you flip recovery
back and forth to disabled and back to enabled.  If your recovery period
is 1 minute, it will run the next recovery after 1 minute independent
of how many times you flipped the parameter.

(Commit message based on emails from Tejun).

Reported-by: Tejun Heo <tj@kernel.org>
Reported-by: Luca Boccassi <bluca@debian.org>
Acked-by: Tejun Heo <tj@kernel.org>
Tested-by: Luca Boccassi <bluca@debian.org>
Cc: stable@vger.kernel.org
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

3 files changed, 35 insertions, 38 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3e8afc82ae2f..e159e44a6a1b 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -26,6 +26,7 @@
 #include <linux/irqbypass.h>
 #include <linux/hyperv.h>
 #include <linux/kfifo.h>
+#include <linux/sched/vhost_task.h>
 
 #include <asm/apic.h>
 #include <asm/pvclock-abi.h>
@@ -1442,7 +1443,8 @@ struct kvm_arch {
 	bool sgx_provisioning_allowed;
 
 	struct kvm_x86_pmu_event_filter __rcu *pmu_event_filter;
-	struct task_struct *nx_huge_page_recovery_thread;
+	struct vhost_task *nx_huge_page_recovery_thread;
+	u64 nx_huge_page_last;
 
 #ifdef CONFIG_X86_64
 	/* The number of TDP MMU pages across all roots. */
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 1ed1e4f5d51c..d93af5390341 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -30,6 +30,7 @@ config KVM_X86
 	select HAVE_KVM_IRQ_BYPASS
 	select HAVE_KVM_IRQ_ROUTING
 	select HAVE_KVM_READONLY_MEM
+	select VHOST_TASK
 	select KVM_ASYNC_PF
 	select USER_RETURN_NOTIFIER
 	select KVM_MMIO
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index d7b391fe2c23..22e7ad235123 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -7162,7 +7162,7 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
 			kvm_mmu_zap_all_fast(kvm);
 			mutex_unlock(&kvm->slots_lock);
 
-			wake_up_process(kvm->arch.nx_huge_page_recovery_thread);
+			vhost_task_wake(kvm->arch.nx_huge_page_recovery_thread);
 		}
 		mutex_unlock(&kvm_lock);
 	}
@@ -7291,7 +7291,7 @@ static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel
 		mutex_lock(&kvm_lock);
 
 		list_for_each_entry(kvm, &vm_list, vm_list)
-			wake_up_process(kvm->arch.nx_huge_page_recovery_thread);
+			vhost_task_wake(kvm->arch.nx_huge_page_recovery_thread);
 
 		mutex_unlock(&kvm_lock);
 	}
@@ -7394,62 +7394,56 @@ static void kvm_recover_nx_huge_pages(struct kvm *kvm)
 	srcu_read_unlock(&kvm->srcu, rcu_idx);
 }
 
-static long get_nx_huge_page_recovery_timeout(u64 start_time)
+static void kvm_nx_huge_page_recovery_worker_kill(void *data)
 {
-	bool enabled;
-	uint period;
-
-	enabled = calc_nx_huge_pages_recovery_period(&period);
-
-	return enabled ? start_time + msecs_to_jiffies(period) - get_jiffies_64()
-		       : MAX_SCHEDULE_TIMEOUT;
 }
 
-static int kvm_nx_huge_page_recovery_worker(struct kvm *kvm, uintptr_t data)
+static bool kvm_nx_huge_page_recovery_worker(void *data)
 {
-	u64 start_time;
+	struct kvm *kvm = data;
+	bool enabled;
+	uint period;
 	long remaining_time;
 
-	while (true) {
-		start_time = get_jiffies_64();
-		remaining_time = get_nx_huge_page_recovery_timeout(start_time);
-
-		set_current_state(TASK_INTERRUPTIBLE);
-		while (!kthread_should_stop() && remaining_time > 0) {
-			schedule_timeout(remaining_time);
-			remaining_time = get_nx_huge_page_recovery_timeout(start_time);
-			set_current_state(TASK_INTERRUPTIBLE);
-		}
-
-		set_current_state(TASK_RUNNING);
-
-		if (kthread_should_stop())
-			return 0;
+	enabled = calc_nx_huge_pages_recovery_period(&period);
+	if (!enabled)
+		return false;
 
-		kvm_recover_nx_huge_pages(kvm);
+	remaining_time = kvm->arch.nx_huge_page_last + msecs_to_jiffies(period)
+		- get_jiffies_64();
+	if (remaining_time > 0) {
+		schedule_timeout(remaining_time);
+		/* check for signals and come back */
+		return true;
 	}
+
+	__set_current_state(TASK_RUNNING);
+	kvm_recover_nx_huge_pages(kvm);
+	kvm->arch.nx_huge_page_last = get_jiffies_64();
+	return true;
 }
 
 int kvm_mmu_post_init_vm(struct kvm *kvm)
 {
-	int err;
-
 	if (nx_hugepage_mitigation_hard_disabled)
 		return 0;
 
-	err = kvm_vm_create_worker_thread(kvm, kvm_nx_huge_page_recovery_worker, 0,
-					  "kvm-nx-lpage-recovery",
-					  &kvm->arch.nx_huge_page_recovery_thread);
-	if (!err)
-		kthread_unpark(kvm->arch.nx_huge_page_recovery_thread);
+	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");
 
-	return err;
+	if (!kvm->arch.nx_huge_page_recovery_thread)
+		return -ENOMEM;
+
+	vhost_task_start(kvm->arch.nx_huge_page_recovery_thread);
+	return 0;
 }
 
 void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
 {
 	if (kvm->arch.nx_huge_page_recovery_thread)
-		kthread_stop(kvm->arch.nx_huge_page_recovery_thread);
+		vhost_task_stop(kvm->arch.nx_huge_page_recovery_thread);
 }
 
 #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES