x86/entry: Provide idtentry_entry/exit_cond_rcu()

After a lengthy discussion [1] it turned out that RCU does not need a full
rcu_irq_enter/exit() when RCU is already watching. All it needs if
NOHZ_FULL is active is to check whether the tick needs to be restarted.

This allows to avoid a separate variant for the pagefault handler which
cannot invoke rcu_irq_enter() on a kernel pagefault which might sleep.

The cond_rcu argument is only temporary and will be removed once the
existing users of idtentry_enter/exit() have been cleaned up. After that
the code can be significantly simplified.

[ mingo: Simplified the control flow ]

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: "Paul E. McKenney" <paulmck@kernel.org>
Acked-by: Andy Lutomirski <luto@kernel.org>
Link: [1] https://lkml.kernel.org/r/20200515235125.628629605@linutronix.de
Link: https://lore.kernel.org/r/20200521202117.181397835@linutronix.de

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 9ebe33485428f8d0852dcda0bc5b69d9ea5a68d7..a7f5846a4102c3c1e8955fcd393a25cccc3d9ba2 100644 (file)
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -512,8 +512,10 @@ SYSCALL_DEFINE0(ni_syscall)
 }
 
 /**
- * idtentry_enter - Handle state tracking on idtentry
+ * idtentry_enter_cond_rcu - Handle state tracking on idtentry with conditional
+ *                          RCU handling
  * @regs:      Pointer to pt_regs of interrupted context
+ * @cond_rcu:  Invoke rcu_irq_enter() only if RCU is not watching
  *
  * Invokes:
  *  - lockdep irqflag state tracking as low level ASM entry disabled
@@ -521,40 +523,84 @@ SYSCALL_DEFINE0(ni_syscall)
  *
  *  - Context tracking if the exception hit user mode.
  *
- *  - RCU notification if the exception hit kernel mode.
- *
  *  - The hardirq tracer to keep the state consistent as low level ASM
  *    entry disabled interrupts.
+ *
+ * For kernel mode entries RCU handling is done conditional. If RCU is
+ * watching then the only RCU requirement is to check whether the tick has
+ * to be restarted. If RCU is not watching then rcu_irq_enter() has to be
+ * invoked on entry and rcu_irq_exit() on exit.
+ *
+ * Avoiding the rcu_irq_enter/exit() calls is an optimization but also
+ * solves the problem of kernel mode pagefaults which can schedule, which
+ * is not possible after invoking rcu_irq_enter() without undoing it.
+ *
+ * For user mode entries enter_from_user_mode() must be invoked to
+ * establish the proper context for NOHZ_FULL. Otherwise scheduling on exit
+ * would not be possible.
+ *
+ * Returns: True if RCU has been adjusted on a kernel entry
+ *         False otherwise
+ *
+ * The return value must be fed into the rcu_exit argument of
+ * idtentry_exit_cond_rcu().
  */
-void noinstr idtentry_enter(struct pt_regs *regs)
+bool noinstr idtentry_enter_cond_rcu(struct pt_regs *regs, bool cond_rcu)
 {
        if (user_mode(regs)) {
                enter_from_user_mode();
-       } else {
+               return false;
+       }
+
+       if (!cond_rcu || !__rcu_is_watching()) {
+               /*
+                * If RCU is not watching then the same careful
+                * sequence vs. lockdep and tracing is required
+                * as in enter_from_user_mode().
+                *
+                * This only happens for IRQs that hit the idle
+                * loop, i.e. if idle is not using MWAIT.
+                */
                lockdep_hardirqs_off(CALLER_ADDR0);
                rcu_irq_enter();
                instrumentation_begin();
                trace_hardirqs_off_prepare();
                instrumentation_end();
+
+               return true;
        }
+
+       /*
+        * If RCU is watching then RCU only wants to check
+        * whether it needs to restart the tick in NOHZ
+        * mode.
+        */
+       instrumentation_begin();
+       rcu_irq_enter_check_tick();
+       /* Use the combo lockdep/tracing function */
+       trace_hardirqs_off();
+       instrumentation_end();
+
+       return false;
 }
 
 /**
- * idtentry_exit - Common code to handle return from exceptions
+ * idtentry_exit_cond_rcu - Handle return from exception with conditional RCU
+ *                         handling
  * @regs:      Pointer to pt_regs (exception entry regs)
+ * @rcu_exit:  Invoke rcu_irq_exit() if true
  *
  * Depending on the return target (kernel/user) this runs the necessary
- * preemption and work checks if possible and required and returns to
+ * preemption and work checks if possible and reguired and returns to
  * the caller with interrupts disabled and no further work pending.
  *
  * This is the last action before returning to the low level ASM code which
  * just needs to return to the appropriate context.
  *
- * Invoked by all exception/interrupt IDTENTRY handlers which are not
- * returning through the paranoid exit path (all except NMI, #DF and the IST
- * variants of #MC and #DB) and are therefore on the thread stack.
+ * Counterpart to idtentry_enter_cond_rcu(). The return value of the entry
+ * function must be fed into the @rcu_exit argument.
  */
-void noinstr idtentry_exit(struct pt_regs *regs)
+void noinstr idtentry_exit_cond_rcu(struct pt_regs *regs, bool rcu_exit)
 {
        lockdep_assert_irqs_disabled();
 
@@ -580,7 +626,8 @@ void noinstr idtentry_exit(struct pt_regs *regs)
                                if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
                                        WARN_ON_ONCE(!on_thread_stack());
                                instrumentation_begin();
-                               rcu_irq_exit_preempt();
+                               if (rcu_exit)
+                                       rcu_irq_exit_preempt();
                                if (need_resched())
                                        preempt_schedule_irq();
                                /* Covers both tracing and lockdep */
@@ -602,10 +649,12 @@ void noinstr idtentry_exit(struct pt_regs *regs)
                trace_hardirqs_on_prepare();
                lockdep_hardirqs_on_prepare(CALLER_ADDR0);
                instrumentation_end();
-               rcu_irq_exit();
+               if (rcu_exit)
+                       rcu_irq_exit();
                lockdep_hardirqs_on(CALLER_ADDR0);
        } else {
-               /* IRQ flags state is correct already. Just tell RCU */
-               rcu_irq_exit();
+               /* IRQ flags state is correct already. Just tell RCU. */
+               if (rcu_exit)
+                       rcu_irq_exit();
        }
 }

diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index ce97478ffc409d6e748aa88158de49958e3ec3dd..a116b80662d4c2d54ed86237e6fc52d6d5205504 100644 (file)
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -7,8 +7,18 @@
 
 #ifndef __ASSEMBLY__
 
-void idtentry_enter(struct pt_regs *regs);
-void idtentry_exit(struct pt_regs *regs);
+bool idtentry_enter_cond_rcu(struct pt_regs *regs, bool cond_rcu);
+void idtentry_exit_cond_rcu(struct pt_regs *regs, bool rcu_exit);
+
+static __always_inline void idtentry_enter(struct pt_regs *regs)
+{
+       idtentry_enter_cond_rcu(regs, false);
+}
+
+static __always_inline void idtentry_exit(struct pt_regs *regs)
+{
+       idtentry_exit_cond_rcu(regs, true);
+}
 
 /**
  * DECLARE_IDTENTRY - Declare functions for simple IDT entry points