x86: Call idle notifier after irq_enter()

Interrupts notify the idle exit state before calling irq_enter().
But the notifier code calls rcu_read_lock() and this is not
allowed while rcu is in an extended quiescent state. We need
to wait for irq_enter() -> rcu_idle_exit() to be called before
doing so otherwise this results in a grumpy RCU:

[    0.099991] WARNING: at include/linux/rcupdate.h:194 __atomic_notifier_call_chain+0xd2/0x110()
[    0.099991] Hardware name: AMD690VM-FMH
[    0.099991] Modules linked in:
[    0.099991] Pid: 0, comm: swapper Not tainted 3.0.0-rc6+ #255
[    0.099991] Call Trace:
[    0.099991]  <IRQ>  [<ffffffff81051c8a>] warn_slowpath_common+0x7a/0xb0
[    0.099991]  [<ffffffff81051cd5>] warn_slowpath_null+0x15/0x20
[    0.099991]  [<ffffffff817d6fa2>] __atomic_notifier_call_chain+0xd2/0x110
[    0.099991]  [<ffffffff817d6ff1>] atomic_notifier_call_chain+0x11/0x20
[    0.099991]  [<ffffffff81001873>] exit_idle+0x43/0x50
[    0.099991]  [<ffffffff81020439>] smp_apic_timer_interrupt+0x39/0xa0
[    0.099991]  [<ffffffff817da253>] apic_timer_interrupt+0x13/0x20
[    0.099991]  <EOI>  [<ffffffff8100ae67>] ? default_idle+0xa7/0x350
[    0.099991]  [<ffffffff8100ae65>] ? default_idle+0xa5/0x350
[    0.099991]  [<ffffffff8100b19b>] amd_e400_idle+0x8b/0x110
[    0.099991]  [<ffffffff810cb01f>] ? rcu_enter_nohz+0x8f/0x160
[    0.099991]  [<ffffffff810019a0>] cpu_idle+0xb0/0x110
[    0.099991]  [<ffffffff817a7505>] rest_init+0xe5/0x140
[    0.099991]  [<ffffffff817a7468>] ? rest_init+0x48/0x140
[    0.099991]  [<ffffffff81cc5ca3>] start_kernel+0x3d1/0x3dc
[    0.099991]  [<ffffffff81cc5321>] x86_64_start_reservations+0x131/0x135
[    0.099991]  [<ffffffff81cc5412>] x86_64_start_kernel+0xed/0xf4

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Andy Henroid <andrew.d.henroid@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index f98d84c..2cd2d93 100644 (file)
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -876,8 +876,8 @@ void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs)
         * Besides, if we don't timer interrupts ignore the global
         * interrupt lock, which is the WrongThing (tm) to do.
         */
-       exit_idle();
        irq_enter();
+       exit_idle();
        local_apic_timer_interrupt();
        irq_exit();
 
@@ -1809,8 +1809,8 @@ void smp_spurious_interrupt(struct pt_regs *regs)
 {
        u32 v;
 
-       exit_idle();
        irq_enter();
+       exit_idle();
        /*
         * Check if this really is a spurious interrupt and ACK it
         * if it is a vectored one.  Just in case...
@@ -1846,8 +1846,8 @@ void smp_error_interrupt(struct pt_regs *regs)
                "Illegal register address",     /* APIC Error Bit 7 */
        };
 
-       exit_idle();
        irq_enter();
+       exit_idle();
        /* First tickle the hardware, only then report what went on. -- REW */
        v0 = apic_read(APIC_ESR);
        apic_write(APIC_ESR, 0);

diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 6d939d7..8980555 100644 (file)
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2421,8 +2421,8 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void)
        unsigned vector, me;
 
        ack_APIC_irq();
-       exit_idle();
        irq_enter();
+       exit_idle();
 
        me = smp_processor_id();
        for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {

diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 787e06c..ce21561 100644 (file)
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -397,8 +397,8 @@ static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt;
 
 asmlinkage void smp_thermal_interrupt(struct pt_regs *regs)
 {
-       exit_idle();
        irq_enter();
+       exit_idle();
        inc_irq_stat(irq_thermal_count);
        smp_thermal_vector();
        irq_exit();

diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c
index d746df2..aa578ca 100644 (file)
--- a/arch/x86/kernel/cpu/mcheck/threshold.c
+++ b/arch/x86/kernel/cpu/mcheck/threshold.c
@@ -19,8 +19,8 @@ void (*mce_threshold_vector)(void) = default_threshold_interrupt;
 
 asmlinkage void smp_threshold_interrupt(void)
 {
-       exit_idle();
        irq_enter();
+       exit_idle();
        inc_irq_stat(irq_threshold_count);
        mce_threshold_vector();
        irq_exit();

diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 429e0c9..5d31e5b 100644 (file)
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -181,8 +181,8 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
        unsigned vector = ~regs->orig_ax;
        unsigned irq;
 
-       exit_idle();
        irq_enter();
+       exit_idle();
 
        irq = __this_cpu_read(vector_irq[vector]);
 
@@ -209,10 +209,10 @@ void smp_x86_platform_ipi(struct pt_regs *regs)
 
        ack_APIC_irq();
 
-       exit_idle();
-
        irq_enter();
 
+       exit_idle();
+
        inc_irq_stat(x86_platform_ipis);
 
        if (x86_platform_ipi_callback)