[PATCH] xtime_lock vs update_process_times

From: Peter Zijlstra
Date: Wed Feb 13 2008 - 15:34:24 EST


This time with LKML CC'ed. Sorry for the duplication.

----
Subject: xtime_lock vs update_process_times
From: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>

( repost from: http://lkml.org/lkml/2008/1/28/101 )

Commit: d3d74453c34f8fd87674a8cf5b8a327c68f22e99
Subject: hrtimer: fixup the HRTIMER_CB_IRQSAFE_NO_SOFTIRQ fallback

Broke several archs, since only Russel bothered to merge the fix,
and Greg to ACK his arch, I'm sending this for merger.

I have confirmation that the Alpha bit results in a booting kernel.
That leaves: blackfin, frv, sh and sparc untested.

The deadlock in question was found by Russell:

IRQ handle
-> timer_tick() - xtime seqlock held for write
-> update_process_times()
-> run_local_timers()
-> hrtimer_run_queues()
-> hrtimer_get_softirq_time() - tries to get a read lock

Now, Thomas assures me the fix is trivial, only do_timer() needs to be
done under the xtime_lock, and update_process_times() can savely be removed
from under it.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Acked-by: Greg Ungerer <gerg@xxxxxxxxxxx>
CC: rth@xxxxxxxxxxx
CC: bryan.wu@xxxxxxxxxx
CC: dhowells@xxxxxxxxxx
CC: lethal@xxxxxxxxxxxx
CC: wli@xxxxxxxxxxxxxx
---
arch/alpha/kernel/time.c | 15 ++++++++-------
arch/blackfin/kernel/time.c | 8 +++++---
arch/frv/kernel/time.c | 6 ++++--
arch/m68knommu/kernel/time.c | 12 +++++++-----
arch/sh/kernel/timers/timer-cmt.c | 9 ---------
arch/sh/kernel/timers/timer-mtu2.c | 2 --
arch/sparc/kernel/pcic.c | 2 +-
arch/sparc/kernel/time.c | 7 +++----
8 files changed, 28 insertions(+), 33 deletions(-)

Index: linux-2.6/arch/alpha/kernel/time.c
===================================================================
--- linux-2.6.orig/arch/alpha/kernel/time.c
+++ linux-2.6/arch/alpha/kernel/time.c
@@ -119,13 +119,8 @@ irqreturn_t timer_interrupt(int irq, voi
state.partial_tick = delta & ((1UL << FIX_SHIFT) - 1);
nticks = delta >> FIX_SHIFT;

- while (nticks > 0) {
- do_timer(1);
-#ifndef CONFIG_SMP
- update_process_times(user_mode(get_irq_regs()));
-#endif
- nticks--;
- }
+ if (nticks)
+ do_timer(nticks);

/*
* If we have an externally synchronized Linux clock, then update
@@ -141,6 +136,12 @@ irqreturn_t timer_interrupt(int irq, voi
}

write_sequnlock(&xtime_lock);
+
+#ifndef CONFIG_SMP
+ while (nticks--)
+ update_process_times(user_mode(get_irq_regs()));
+#endif
+
return IRQ_HANDLED;
}

Index: linux-2.6/arch/blackfin/kernel/time.c
===================================================================
--- linux-2.6.orig/arch/blackfin/kernel/time.c
+++ linux-2.6/arch/blackfin/kernel/time.c
@@ -137,9 +137,6 @@ irqreturn_t timer_interrupt(int irq, voi

do_timer(1);

-#ifndef CONFIG_SMP
- update_process_times(user_mode(get_irq_regs()));
-#endif
profile_tick(CPU_PROFILING);

/*
@@ -161,6 +158,11 @@ irqreturn_t timer_interrupt(int irq, voi
last_rtc_update = xtime.tv_sec - 600;
}
write_sequnlock(&xtime_lock);
+
+#ifndef CONFIG_SMP
+ update_process_times(user_mode(get_irq_regs()));
+#endif
+
return IRQ_HANDLED;
}

Index: linux-2.6/arch/frv/kernel/time.c
===================================================================
--- linux-2.6.orig/arch/frv/kernel/time.c
+++ linux-2.6/arch/frv/kernel/time.c
@@ -63,6 +63,7 @@ static irqreturn_t timer_interrupt(int i
/* last time the cmos clock got updated */
static long last_rtc_update = 0;

+ profile_tick(CPU_PROFILING);
/*
* Here we are in the timer irq handler. We just have irqs locally
* disabled but we don't know if the timer_bh is running on the other
@@ -73,8 +74,6 @@ static irqreturn_t timer_interrupt(int i
write_seqlock(&xtime_lock);

do_timer(1);
- update_process_times(user_mode(get_irq_regs()));
- profile_tick(CPU_PROFILING);

/*
* If we have an externally synchronized Linux clock, then update
@@ -99,6 +98,9 @@ static irqreturn_t timer_interrupt(int i
#endif /* CONFIG_HEARTBEAT */

write_sequnlock(&xtime_lock);
+
+ update_process_times(user_mode(get_irq_regs()));
+
return IRQ_HANDLED;
}

Index: linux-2.6/arch/m68knommu/kernel/time.c
===================================================================
--- linux-2.6.orig/arch/m68knommu/kernel/time.c
+++ linux-2.6/arch/m68knommu/kernel/time.c
@@ -42,14 +42,12 @@ irqreturn_t arch_timer_interrupt(int irq
/* last time the cmos clock got updated */
static long last_rtc_update=0;

+ if (current->pid)
+ profile_tick(CPU_PROFILING);
+
write_seqlock(&xtime_lock);

do_timer(1);
-#ifndef CONFIG_SMP
- update_process_times(user_mode(get_irq_regs()));
-#endif
- if (current->pid)
- profile_tick(CPU_PROFILING);

/*
* If we have an externally synchronized Linux clock, then update
@@ -67,6 +65,10 @@ irqreturn_t arch_timer_interrupt(int irq
}

write_sequnlock(&xtime_lock);
+
+#ifndef CONFIG_SMP
+ update_process_times(user_mode(get_irq_regs()));
+#endif
return(IRQ_HANDLED);
}

Index: linux-2.6/arch/sh/kernel/timers/timer-cmt.c
===================================================================
--- linux-2.6.orig/arch/sh/kernel/timers/timer-cmt.c
+++ linux-2.6/arch/sh/kernel/timers/timer-cmt.c
@@ -100,16 +100,7 @@ static irqreturn_t cmt_timer_interrupt(i
timer_status &= ~0x80;
ctrl_outw(timer_status, CMT_CMCSR_0);

- /*
- * Here we are in the timer irq handler. We just have irqs locally
- * disabled but we don't know if the timer_bh is running on the other
- * CPU. We need to avoid to SMP race with it. NOTE: we don' t need
- * the irq version of write_lock because as just said we have irq
- * locally disabled. -arca
- */
- write_seqlock(&xtime_lock);
handle_timer_tick();
- write_sequnlock(&xtime_lock);

return IRQ_HANDLED;
}
Index: linux-2.6/arch/sh/kernel/timers/timer-mtu2.c
===================================================================
--- linux-2.6.orig/arch/sh/kernel/timers/timer-mtu2.c
+++ linux-2.6/arch/sh/kernel/timers/timer-mtu2.c
@@ -100,9 +100,7 @@ static irqreturn_t mtu2_timer_interrupt(
ctrl_outb(timer_status, MTU2_TSR_1);

/* Do timer tick */
- write_seqlock(&xtime_lock);
handle_timer_tick();
- write_sequnlock(&xtime_lock);

return IRQ_HANDLED;
}
Index: linux-2.6/arch/sparc/kernel/pcic.c
===================================================================
--- linux-2.6.orig/arch/sparc/kernel/pcic.c
+++ linux-2.6/arch/sparc/kernel/pcic.c
@@ -713,10 +713,10 @@ static irqreturn_t pcic_timer_handler (i
write_seqlock(&xtime_lock); /* Dummy, to show that we remember */
pcic_clear_clock_irq();
do_timer(1);
+ write_sequnlock(&xtime_lock);
#ifndef CONFIG_SMP
update_process_times(user_mode(get_irq_regs()));
#endif
- write_sequnlock(&xtime_lock);
return IRQ_HANDLED;
}

Index: linux-2.6/arch/sparc/kernel/time.c
===================================================================
--- linux-2.6.orig/arch/sparc/kernel/time.c
+++ linux-2.6/arch/sparc/kernel/time.c
@@ -128,10 +128,6 @@ irqreturn_t timer_interrupt(int irq, voi
clear_clock_irq();

do_timer(1);
-#ifndef CONFIG_SMP
- update_process_times(user_mode(get_irq_regs()));
-#endif
-

/* Determine when to update the Mostek clock. */
if (ntp_synced() &&
@@ -145,6 +141,9 @@ irqreturn_t timer_interrupt(int irq, voi
}
write_sequnlock(&xtime_lock);

+#ifndef CONFIG_SMP
+ update_process_times(user_mode(get_irq_regs()));
+#endif
return IRQ_HANDLED;
}



--
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/