diff mbox series

[V5,08/15] x86/entry: Move user return notifier out of loop

Message ID 20200722220520.159112003@linutronix.de (mailing list archive)
State New, archived
Headers show
Series entry, x86, kvm: Generic entry/exit functionality for host and guest | expand

Commit Message

Thomas Gleixner July 22, 2020, 10 p.m. UTC 
From: Thomas Gleixner <tglx@linutronix.de>

Guests and user space share certain MSRs. KVM sets these MSRs to guest
values once and does not set them back to user space values on every VM
exit to spare the costly MSR operations.

User return notifiers ensure that these MSRs are set back to the correct
values before returning to user space in exit_to_usermode_loop().

There is no reason to evaluate the TIF flag indicating that user return
notifiers need to be invoked in the loop. The important point is that they
are invoked before returning to user space.

Move the invocation out of the loop into the section which does the last
preperatory steps before returning to user space. That section is not
preemptible and runs with interrupts disabled until the actual return.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
V4: New patch
---
 arch/x86/entry/common.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

Comments

Sean Christopherson July 23, 2020, 11:41 p.m. UTC | #1 
On Thu, Jul 23, 2020 at 12:00:02AM +0200, Thomas Gleixner wrote:
> From: Thomas Gleixner <tglx@linutronix.de>
> 
> Guests and user space share certain MSRs. KVM sets these MSRs to guest
> values once and does not set them back to user space values on every VM
> exit to spare the costly MSR operations.
> 
> User return notifiers ensure that these MSRs are set back to the correct
> values before returning to user space in exit_to_usermode_loop().
> 
> There is no reason to evaluate the TIF flag indicating that user return
> notifiers need to be invoked in the loop. The important point is that they
> are invoked before returning to user space.
> 
> Move the invocation out of the loop into the section which does the last
> preperatory steps before returning to user space. That section is not
> preemptible and runs with interrupts disabled until the actual return.
> 
> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

Reviewed-and-tested-by: Sean Christopherson <sean.j.christopherson@intel.com>
diff mbox series

Patch

--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -208,7 +208,7 @@  static long syscall_trace_enter(struct p
 
 #define EXIT_TO_USERMODE_LOOP_FLAGS				\
 	(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE |	\
-	 _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY | _TIF_PATCH_PENDING)
+	 _TIF_NEED_RESCHED | _TIF_PATCH_PENDING)
 
 static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
 {
@@ -242,9 +242,6 @@  static void exit_to_usermode_loop(struct
 			rseq_handle_notify_resume(NULL, regs);
 		}
 
-		if (cached_flags & _TIF_USER_RETURN_NOTIFY)
-			fire_user_return_notifiers();
-
 		/* Disable IRQs and retry */
 		local_irq_disable();
 
@@ -273,6 +270,9 @@  static void __prepare_exit_to_usermode(s
 	/* Reload ti->flags; we may have rescheduled above. */
 	cached_flags = READ_ONCE(ti->flags);
 
+	if (cached_flags & _TIF_USER_RETURN_NOTIFY)
+		fire_user_return_notifiers();
+
 	if (unlikely(cached_flags & _TIF_IO_BITMAP))
 		tss_update_io_bitmap();