[PATCH][2.5] flush_tlb_all is not preempt safe.

From: Zwane Mwaikambo (zwane@holomorphy.com)
Date: Fri Feb 14 2003 - 06:06:16 EST

Hi,
        Considering that smp_call_function isn't allowed to hold a lock
reference and within smp_call_function we lock and unlock call_lock thus
triggering a preempt point. Therefore we can't guarantee that we'll be on
the same processor when we hit do_flush_tlb_all_local.

void flush_tlb_all(void)
{
        preempt_disable();
        smp_call_function (flush_tlb_all_ipi,0,1,1);

        do_flush_tlb_all_local();
        preempt_enable();
}

...

smp_call_function()
{
        spin_lock(call_lock);
        ...
        spin_unlock(call_lock);
        <preemption point>
}

...

do_flush_tlb_all_local() - possibly not executing on same processor
anymore.

This case is fixed in my smp_call_function_on_cpu patches by not allowing
smp_call_function to invoke preemption.

Index: linux-2.5.60-uml/arch/i386/kernel/smp.c
===================================================================
RCS file: /build/cvsroot/linux-2.5.60/arch/i386/kernel/smp.c,v
retrieving revision 1.1.1.1
diff -u -r1.1.1.1 smp.c
--- linux-2.5.60-uml/arch/i386/kernel/smp.c 10 Feb 2003 22:14:16 -0000 1.1.1.1
+++ linux-2.5.60-uml/arch/i386/kernel/smp.c 14 Feb 2003 10:59:19 -0000
@@ -452,9 +452,11 @@
 
 void flush_tlb_all(void)
 {
+ preempt_disable();
         smp_call_function (flush_tlb_all_ipi,0,1,1);
 
         do_flush_tlb_all_local();
+ preempt_enable();
 }
 
 /* 

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

This archive was generated by hypermail 2b29 : Sat Feb 15 2003 - 22:00:53 EST