rseq, virt: Retrigger RSEQ after vcpu_run()

Hypervisors invoke resume_user_mode_work() before entering the guest, which
clears TIF_NOTIFY_RESUME. The @regs argument is NULL as there is no user
space context available to them, so the rseq notify handler skips
inspecting the critical section, but updates the CPU/MM CID values
unconditionally so that the eventual pending rseq event is not lost on the
way to user space.

This is a pointless exercise as the task might be rescheduled before
actually returning to user space and it creates unnecessary work in the
vcpu_run() loops.

It's way more efficient to ignore that invocation based on @regs == NULL
and let the hypervisors re-raise TIF_NOTIFY_RESUME after returning from the
vcpu_run() loop before returning from the ioctl().

This ensures that a pending RSEQ update is not lost and the IDs are updated
before returning to user space.

Once the RSEQ handling is decoupled from TIF_NOTIFY_RESUME, this turns into
a NOOP.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Sean Christopherson <seanjc@google.com>
Link: https://patch.msgid.link/20251027084306.399495855@linutronix.de

drivers/hv/mshv_root_main.c

@@ -29,6 +29,7 @@
 #include <linux/crash_dump.h>
 #include <linux/panic_notifier.h>
 #include <linux/vmalloc.h>
+#include <linux/rseq.h>
 
 #include "mshv_eventfd.h"
 #include "mshv.h"
@@ -560,6 +561,8 @@ static long mshv_run_vp_with_root_scheduler(struct mshv_vp *vp)
 		}
 	} while (!vp->run.flags.intercept_suspend);
 
+	rseq_virt_userspace_exit();
+
 	return ret;
 }
 

include/linux/rseq.h

@@ -37,6 +37,22 @@ static __always_inline void rseq_exit_to_user_mode(void)
 	}
 }
 
+/*
+ * KVM/HYPERV invoke resume_user_mode_work() before entering guest mode,
+ * which clears TIF_NOTIFY_RESUME. To avoid updating user space RSEQ in
+ * that case just to do it eventually again before returning to user space,
+ * the entry resume_user_mode_work() invocation is ignored as the register
+ * argument is NULL.
+ *
+ * After returning from guest mode, they have to invoke this function to
+ * re-raise TIF_NOTIFY_RESUME if necessary.
+ */
+static inline void rseq_virt_userspace_exit(void)
+{
+	if (current->rseq_event_pending)
+		set_tsk_thread_flag(current, TIF_NOTIFY_RESUME);
+}
+
 /*
  * If parent process has a registered restartable sequences area, the
  * child inherits. Unregister rseq for a clone with CLONE_VM set.
@@ -68,6 +84,7 @@ static inline void rseq_execve(struct task_struct *t)
 static inline void rseq_handle_notify_resume(struct pt_regs *regs) { }
 static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { }
 static inline void rseq_sched_switch_event(struct task_struct *t) { }
+static inline void rseq_virt_userspace_exit(void) { }
 static inline void rseq_fork(struct task_struct *t, u64 clone_flags) { }
 static inline void rseq_execve(struct task_struct *t) { }
 static inline void rseq_exit_to_user_mode(void) { }

kernel/rseq.c

@@ -422,50 +422,54 @@ void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs)
 {
 	struct task_struct *t = current;
 	int ret, sig;
+	bool event;
+
+	/*
+	 * If invoked from hypervisors before entering the guest via
+	 * resume_user_mode_work(), then @regs is a NULL pointer.
+	 *
+	 * resume_user_mode_work() clears TIF_NOTIFY_RESUME and re-raises
+	 * it before returning from the ioctl() to user space when
+	 * rseq_event.sched_switch is set.
+	 *
+	 * So it's safe to ignore here instead of pointlessly updating it
+	 * in the vcpu_run() loop.
+	 */
+	if (!regs)
+		return;
 
 	if (unlikely(t->flags & PF_EXITING))
 		return;
 
 	/*
-	 * If invoked from hypervisors or IO-URING, then @regs is a NULL
-	 * pointer, so fixup cannot be done. If the syscall which led to
-	 * this invocation was invoked inside a critical section, then it
-	 * will either end up in this code again or a possible violation of
-	 * a syscall inside a critical region can only be detected by the
-	 * debug code in rseq_syscall() in a debug enabled kernel.
+	 * Read and clear the event pending bit first. If the task
+	 * was not preempted or migrated or a signal is on the way,
+	 * there is no point in doing any of the heavy lifting here
+	 * on production kernels. In that case TIF_NOTIFY_RESUME
+	 * was raised by some other functionality.
+	 *
+	 * This is correct because the read/clear operation is
+	 * guarded against scheduler preemption, which makes it CPU
+	 * local atomic. If the task is preempted right after
+	 * re-enabling preemption then TIF_NOTIFY_RESUME is set
+	 * again and this function is invoked another time _before_
+	 * the task is able to return to user mode.
+	 *
+	 * On a debug kernel, invoke the fixup code unconditionally
+	 * with the result handed in to allow the detection of
+	 * inconsistencies.
 	 */
-	if (regs) {
-		/*
-		 * Read and clear the event pending bit first. If the task
-		 * was not preempted or migrated or a signal is on the way,
-		 * there is no point in doing any of the heavy lifting here
-		 * on production kernels. In that case TIF_NOTIFY_RESUME
-		 * was raised by some other functionality.
-		 *
-		 * This is correct because the read/clear operation is
-		 * guarded against scheduler preemption, which makes it CPU
-		 * local atomic. If the task is preempted right after
-		 * re-enabling preemption then TIF_NOTIFY_RESUME is set
-		 * again and this function is invoked another time _before_
-		 * the task is able to return to user mode.
-		 *
-		 * On a debug kernel, invoke the fixup code unconditionally
-		 * with the result handed in to allow the detection of
-		 * inconsistencies.
-		 */
-		bool event;
-
-		scoped_guard(RSEQ_EVENT_GUARD) {
-			event = t->rseq_event_pending;
-			t->rseq_event_pending = false;
-		}
-
-		if (IS_ENABLED(CONFIG_DEBUG_RSEQ) || event) {
-			ret = rseq_ip_fixup(regs, event);
-			if (unlikely(ret < 0))
-				goto error;
-		}
+	scoped_guard(RSEQ_EVENT_GUARD) {
+		event = t->rseq_event_pending;
+		t->rseq_event_pending = false;
 	}
+
+	if (IS_ENABLED(CONFIG_DEBUG_RSEQ) || event) {
+		ret = rseq_ip_fixup(regs, event);
+		if (unlikely(ret < 0))
+			goto error;
+	}
+
 	if (unlikely(rseq_update_cpu_node_id(t)))
 		goto error;
 	return;

virt/kvm/kvm_main.c

@@ -49,6 +49,7 @@
 #include <linux/lockdep.h>
 #include <linux/kthread.h>
 #include <linux/suspend.h>
+#include <linux/rseq.h>
 
 #include <asm/processor.h>
 #include <asm/ioctl.h>
@@ -4476,6 +4477,12 @@ static long kvm_vcpu_ioctl(struct file *filp,
 		r = kvm_arch_vcpu_ioctl_run(vcpu);
 		vcpu->wants_to_run = false;
 
+		/*
+		 * FIXME: Remove this hack once all KVM architectures
+		 * support the generic TIF bits, i.e. a dedicated TIF_RSEQ.
+		 */
+		rseq_virt_userspace_exit();
+
 		trace_kvm_userspace_exit(vcpu->run->exit_reason, r);
 		break;
 	}