[PATCH 6/7] x86: Call idle notifier after irq_enter()

From: Frederic Weisbecker
Date: Mon Sep 26 2011 - 06:19:45 EST


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 rcu_irq_enter() 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@xxxxxxxxx>
Cc: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Andy Henroid <andrew.d.henroid@xxxxxxxxx>
---
arch/x86/kernel/apic/apic.c | 6 +++---
arch/x86/kernel/apic/io_apic.c | 2 +-
arch/x86/kernel/cpu/mcheck/mce.c | 2 +-
arch/x86/kernel/cpu/mcheck/therm_throt.c | 2 +-
arch/x86/kernel/cpu/mcheck/threshold.c | 2 +-
arch/x86/kernel/irq.c | 6 +++---
6 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index b9338b8..82af921 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -856,8 +856,8 @@ 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();

@@ -1790,8 +1790,8 @@ 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...
@@ -1827,8 +1827,8 @@ 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 e529339..e1b5eec 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2275,8 +2275,8 @@ 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/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index ff1ae9b..7ba9757 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -470,8 +470,8 @@ static inline void mce_get_rip(struct mce *m, struct pt_regs *regs)
asmlinkage void smp_mce_self_interrupt(struct pt_regs *regs)
{
ack_APIC_irq();
- exit_idle();
irq_enter();
+ exit_idle();
mce_notify_irq();
mce_schedule_work();
irq_exit();
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 27c6251..f6bbc64 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -396,8 +396,8 @@ 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
--- 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 6c0802e..73cf928 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -180,8 +180,8 @@ 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]);

@@ -208,10 +208,10 @@ 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)
--
1.7.5.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/