diff options
| author | Zhang Yanmin <yanmin.zhang@intel.com> | 2006-06-23 02:04:22 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@g5.osdl.org> | 2006-06-23 07:42:57 -0700 |
| commit | 1b61b910e99059abdd54c93aa70e84e076e33d16 (patch) | |
| tree | fe2cd431dc39521a0f2d30e22c9bd3eb3e1bc317 /kernel/irq | |
| parent | afa024c3dbccf026e45121f4b9de54cda48edbea (diff) | |
| download | op-kernel-dev-1b61b910e99059abdd54c93aa70e84e076e33d16.zip op-kernel-dev-1b61b910e99059abdd54c93aa70e84e076e33d16.tar.gz | |
[PATCH] x86: kernel irq balance doesn't work
On i386, kernel irq balance doesn't work.
1) In function do_irq_balance, after kernel finds the min_loaded cpu but
before calling set_pending_irq to really pin the selected_irq to the
target cpu, kernel does a cpus_and with irq_affinity[selected_irq].
Later on, when the irq is acked, kernel would calls
move_native_irq=>desc->handler->set_affinity to change the irq affinity.
However, every function pointed by
hw_interrupt_type->set_affinity(unsigned int irq, cpumask_t cpumask)
always changes irq_affinity[irq] to cpumask. Next time when recalling
do_irq_balance, it has to do cpu_ands again with
irq_affinity[selected_irq], but irq_affinity[selected_irq] already
becomes one cpu selected by the first irq balance.
2) Function balance_irq in file arch/i386/kernel/io_apic.c has the same
issue.
[akpm@osdl.org: cleanups]
Signed-off-by: Zhang Yanmin <yanmin.zhang@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'kernel/irq')
| -rw-r--r-- | kernel/irq/proc.c | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index d03b5ee..afacd6f 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -24,6 +24,8 @@ static struct proc_dir_entry *smp_affinity_entry[NR_IRQS]; #ifdef CONFIG_GENERIC_PENDING_IRQ void proc_set_irq_affinity(unsigned int irq, cpumask_t mask_val) { + set_balance_irq_affinity(irq, mask_val); + /* * Save these away for later use. Re-progam when the * interrupt is pending @@ -33,6 +35,7 @@ void proc_set_irq_affinity(unsigned int irq, cpumask_t mask_val) #else void proc_set_irq_affinity(unsigned int irq, cpumask_t mask_val) { + set_balance_irq_affinity(irq, mask_val); irq_affinity[irq] = mask_val; irq_desc[irq].handler->set_affinity(irq, mask_val); } |
