KVM: Protect vCPU's "last run PID" with rwlock, not RCU

To avoid jitter on KVM_RUN due to synchronize_rcu(), use a rwlock instead
of RCU to protect vcpu->pid, a.k.a. the pid of the task last used to a
vCPU.  When userspace is doing M:N scheduling of tasks to vCPUs, e.g. to
run SEV migration helper vCPUs during post-copy, the synchronize_rcu()
needed to change the PID associated with the vCPU can stall for hundreds
of milliseconds, which is problematic for latency sensitive post-copy
operations.

In the directed yield path, do not acquire the lock if it's contended,
i.e. if the associated PID is changing, as that means the vCPU's task is
already running.

Reported-by: Steve Rutherford <srutherford@google.com>
Reviewed-by: Steve Rutherford <srutherford@google.com>
Acked-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20240802200136.329973-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

1 files changed, 25 insertions, 14 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 17048d9575e3..c1876b9ed213 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -447,6 +447,7 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 	vcpu->kvm = kvm;
 	vcpu->vcpu_id = id;
 	vcpu->pid = NULL;
+	rwlock_init(&vcpu->pid_lock);
 #ifndef __KVM_HAVE_ARCH_WQP
 	rcuwait_init(&vcpu->wait);
 #endif
@@ -474,7 +475,7 @@ static void kvm_vcpu_destroy(struct kvm_vcpu *vcpu)
 	 * the vcpu->pid pointer, and at destruction time all file descriptors
 	 * are already gone.
 	 */
-	put_pid(rcu_dereference_protected(vcpu->pid, 1));
+	put_pid(vcpu->pid);
 
 	free_page((unsigned long)vcpu->run);
 	kmem_cache_free(kvm_vcpu_cache, vcpu);
@@ -3770,15 +3771,17 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_kick);
 
 int kvm_vcpu_yield_to(struct kvm_vcpu *target)
 {
-	struct pid *pid;
 	struct task_struct *task = NULL;
 	int ret;
 
-	rcu_read_lock();
-	pid = rcu_dereference(target->pid);
-	if (pid)
-		task = get_pid_task(pid, PIDTYPE_PID);
-	rcu_read_unlock();
+	if (!read_trylock(&target->pid_lock))
+		return 0;
+
+	if (target->pid)
+		task = get_pid_task(target->pid, PIDTYPE_PID);
+
+	read_unlock(&target->pid_lock);
+
 	if (!task)
 		return 0;
 	ret = yield_to(task, 1);
@@ -4030,9 +4033,9 @@ static int vcpu_get_pid(void *data, u64 *val)
 {
 	struct kvm_vcpu *vcpu = data;
 
-	rcu_read_lock();
-	*val = pid_nr(rcu_dereference(vcpu->pid));
-	rcu_read_unlock();
+	read_lock(&vcpu->pid_lock);
+	*val = pid_nr(vcpu->pid);
+	read_unlock(&vcpu->pid_lock);
 	return 0;
 }
 
@@ -4318,7 +4321,14 @@ static long kvm_vcpu_ioctl(struct file *filp,
 		r = -EINVAL;
 		if (arg)
 			goto out;
-		oldpid = rcu_access_pointer(vcpu->pid);
+
+		/*
+		 * Note, vcpu->pid is primarily protected by vcpu->mutex. The
+		 * dedicated r/w lock allows other tasks, e.g. other vCPUs, to
+		 * read vcpu->pid while this vCPU is in KVM_RUN, e.g. to yield
+		 * directly to this vCPU
+		 */
+		oldpid = vcpu->pid;
 		if (unlikely(oldpid != task_pid(current))) {
 			/* The thread running this VCPU changed. */
 			struct pid *newpid;
@@ -4328,9 +4338,10 @@ static long kvm_vcpu_ioctl(struct file *filp,
 				break;
 
 			newpid = get_task_pid(current, PIDTYPE_PID);
-			rcu_assign_pointer(vcpu->pid, newpid);
-			if (oldpid)
-				synchronize_rcu();
+			write_lock(&vcpu->pid_lock);
+			vcpu->pid = newpid;
+			write_unlock(&vcpu->pid_lock);
+
 			put_pid(oldpid);
 		}
 		vcpu->wants_to_run = !READ_ONCE(vcpu->run->immediate_exit__unsafe);