On Fri, 2011-05-20 at 08:07 +0200, Daniel Hellstrom wrote:Yes, my patches implements IPI for sparc32.
Peter Zijlstra wrote:
On Thu, 2011-05-19 at 15:37 +0200, Daniel Hellstrom wrote:The above function is one of the IPI interrupt handlers.
diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.cThat doesn't look like an IPI, that looks like its calls the function on
index 41102c5..d5b3958 100644
@@ -156,11 +156,11 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask)
- * do nothing, since it all was about calling re-schedule
- * routine called by interrupt return code.
+ /* re-schedule routine called by interrupt return code. */
the local cpu, which is completely pointless.
The smp_send_reschedule() is called by the generic code, it is responsible for sending an IRQ to the target CPU, that CPU comes into smp_resched_interrupt above from the IRQ trap handler. So yes, the scheduler_ipi() is called on the local CPU, but on the CPU taking the IPI not the CPU sending the IPI.
Ah, clearly I cannot read well, I actually thought that was
smp_send_reschedule(). OK, if sparc32 is now actually sending IPIs and
the above is the handler, then you're completely right, sorry for the
Also, since sparc32 now grew this IPI, you can remove:
@@ -827,6 +827,11 @@ config SCHED_AUTOGROUP
desktop applications. Task group autogeneration is currently based
upon task session.
+ depends on !SPARC32
+ default y