From: Li Zhong <zhong@linux.vnet.ibm.com>
Date: Mon, 10 Sep 2012 15:37:43 +0000 (+0000)
Subject: powerpc/trace: Fix interrupt tracepoints vs. RCU
X-Git-Tag: v3.12-rc1~2238^2~29
X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=e72bbbab278a2e6d506bd2cf380ba9bef68e8ec1;p=kernel%2Fkernel-generic.git

powerpc/trace: Fix interrupt tracepoints vs. RCU

There are a few tracepoints in the interrupt code path, which is before
irq_enter(), or after irq_exit(), like
trace_irq_entry()/trace_irq_exit() in do_IRQ(),
trace_timer_interrupt_entry()/trace_timer_interrupt_exit() in
timer_interrupt().

If the interrupt is from idle(), and because tracepoint contains RCU
read-side critical section, we could see following suspicious RCU usage
reported:

[  145.127743] ===============================
[  145.127747] [ INFO: suspicious RCU usage. ]
[  145.127752] 3.6.0-rc3+ #1 Not tainted
[  145.127755] -------------------------------
[  145.127759] /root/.workdir/linux/arch/powerpc/include/asm/trace.h:33
suspicious rcu_dereference_check() usage!
[  145.127765]
[  145.127765] other info that might help us debug this:
[  145.127765]
[  145.127771]
[  145.127771] RCU used illegally from idle CPU!
[  145.127771] rcu_scheduler_active = 1, debug_locks = 0
[  145.127777] RCU used illegally from extended quiescent state!
[  145.127781] no locks held by swapper/0/0.
[  145.127785]
[  145.127785] stack backtrace:
[  145.127789] Call Trace:
[  145.127796] [c00000000108b530] [c000000000013c40] .show_stack
+0x70/0x1c0 (unreliable)
[  145.127806] [c00000000108b5e0]
[c0000000000f59d8] .lockdep_rcu_suspicious+0x118/0x150
[  145.127813] [c00000000108b680] [c00000000000fc58] .do_IRQ+0x498/0x500
[  145.127820] [c00000000108b750] [c000000000003950]
hardware_interrupt_common+0x150/0x180
[  145.127828] --- Exception: 501 at .plpar_hcall_norets+0x84/0xd4
[  145.127828]     LR = .check_and_cede_processor+0x38/0x70
[  145.127836] [c00000000108bab0] [c0000000000665dc] .shared_cede_loop
+0x5c/0x100
[  145.127844] [c00000000108bb70] [c000000000588ab0] .cpuidle_enter
+0x30/0x50
[  145.127850] [c00000000108bbe0]
[c000000000588b0c] .cpuidle_enter_state+0x3c/0xb0
[  145.127857] [c00000000108bc60] [c000000000589730] .cpuidle_idle_call
+0x150/0x6c0
[  145.127863] [c00000000108bd30] [c000000000058440] .pSeries_idle
+0x10/0x40
[  145.127870] [c00000000108bda0] [c00000000001683c] .cpu_idle
+0x18c/0x2d0
[  145.127876] [c00000000108be60] [c00000000000b434] .rest_init
+0x124/0x1b0
[  145.127884] [c00000000108bef0] [c0000000009d0d28] .start_kernel
+0x568/0x588
[  145.127890] [c00000000108bf90] [c000000000009660] .start_here_common
+0x20/0x40

This is because the RCU usage in interrupt context should be used in
area marked by rcu_irq_enter()/rcu_irq_exit(), called in
irq_enter()/irq_exit() respectively.

Move them into the irq_enter()/irq_exit() area to avoid the reporting.

Signed-off-by: Li Zhong <zhong@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---

diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 1f017bb..71413f4 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -489,10 +489,10 @@ void do_IRQ(struct pt_regs *regs)
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	unsigned int irq;
 
-	trace_irq_entry(regs);
-
 	irq_enter();
 
+	trace_irq_entry(regs);
+
 	check_stack_overflow();
 
 	/*
@@ -511,10 +511,10 @@ void do_IRQ(struct pt_regs *regs)
 	else
 		__get_cpu_var(irq_stat).spurious_irqs++;
 
+	trace_irq_exit(regs);
+
 	irq_exit();
 	set_irq_regs(old_regs);
-
-	trace_irq_exit(regs);
 }
 
 void __init init_IRQ(void)
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index e49e931..bd693a1 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -493,8 +493,6 @@ void timer_interrupt(struct pt_regs * regs)
 	 */
 	may_hard_irq_enable();
 
-	trace_timer_interrupt_entry(regs);
-
 	__get_cpu_var(irq_stat).timer_irqs++;
 
 #if defined(CONFIG_PPC32) && defined(CONFIG_PMAC)
@@ -505,6 +503,8 @@ void timer_interrupt(struct pt_regs * regs)
 	old_regs = set_irq_regs(regs);
 	irq_enter();
 
+	trace_timer_interrupt_entry(regs);
+
 	if (test_irq_work_pending()) {
 		clear_irq_work_pending();
 		irq_work_run();
@@ -529,10 +529,10 @@ void timer_interrupt(struct pt_regs * regs)
 	}
 #endif
 
+	trace_timer_interrupt_exit(regs);
+
 	irq_exit();
 	set_irq_regs(old_regs);
-
-	trace_timer_interrupt_exit(regs);
 }
 
 /*