[PATCH] x86/x86_64: deferred handling of writes to /proc/irqxx/smp_affinity

When handling writes to /proc/irq, current code is re-programming rte
entries directly. This is not recommended and could potentially cause
chipset's to lockup, or cause missing interrupts.

CONFIG_IRQ_BALANCE does this correctly, where it re-programs only when the
interrupt is pending. The same needs to be done for /proc/irq handling as well.
Otherwise user space irq balancers are really not doing the right thing.

- Changed pending_irq_balance_cpumask to pending_irq_migrate_cpumask for
  lack of a generic name.
- added move_irq out of IRQ_BALANCE, and added this same to X86_64
- Added new proc handler for write, so we can do deferred write at irq
  handling time.
- Display of /proc/irq/XX/smp_affinity used to display CPU_MASKALL, instead
  it now shows only active cpu masks, or exactly what was set.
- Provided a common move_irq implementation, instead of duplicating
  when using generic irq framework.

Tested on i386/x86_64 and ia64 with CONFIG_PCI_MSI turned on and off.
Tested UP builds as well.

MSI testing: tbd: I have cards, need to look for a x-over cable, although I
did test an earlier version of this patch.  Will test in a couple days.

Signed-off-by: Ashok Raj <ashok.raj@intel.com>
Acked-by: Zwane Mwaikambo <zwane@holomorphy.com>
Grudgingly-acked-by: Andi Kleen <ak@muc.de>
Signed-off-by: Coywolf Qi Hunt <coywolf@lovecn.org>
Signed-off-by: Ashok Raj <ashok.raj@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 6 insertions, 38 deletions

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 3deced637f0..17b5dbf8c31 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -434,6 +434,11 @@ config GENERIC_IRQ_PROBE
         bool
         default y
 
+config GENERIC_PENDING_IRQ
+        bool
+        depends on GENERIC_HARDIRQS && SMP
+        default y
+
 source "arch/ia64/hp/sim/Kconfig"
 
 source "arch/ia64/oprofile/Kconfig"
diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c
index 28f2aadc38d..205d9802826 100644
--- a/arch/ia64/kernel/irq.c
+++ b/arch/ia64/kernel/irq.c
@@ -91,23 +91,8 @@ skip:
 }
 
 #ifdef CONFIG_SMP
-/*
- * This is updated when the user sets irq affinity via /proc
- */
-static cpumask_t __cacheline_aligned pending_irq_cpumask[NR_IRQS];
-static unsigned long pending_irq_redir[BITS_TO_LONGS(NR_IRQS)];
-
 static char irq_redir [NR_IRQS]; // = { [0 ... NR_IRQS-1] = 1 };
 
-/*
- * Arch specific routine for deferred write to iosapic rte to reprogram
- * intr destination.
- */
-void proc_set_irq_affinity(unsigned int irq, cpumask_t mask_val)
-{
-        pending_irq_cpumask[irq] = mask_val;
-}
-
 void set_irq_affinity_info (unsigned int irq, int hwid, int redir)
 {
         cpumask_t mask = CPU_MASK_NONE;
@@ -116,32 +101,10 @@ void set_irq_affinity_info (unsigned int irq, int hwid, int redir)
 
         if (irq < NR_IRQS) {
                 irq_affinity[irq] = mask;
+                set_irq_info(irq, mask);
                 irq_redir[irq] = (char) (redir & 0xff);
         }
 }
-
-
-void move_irq(int irq)
-{
-        /* note - we hold desc->lock */
-        cpumask_t tmp;
-        irq_desc_t *desc = irq_descp(irq);
-        int redir = test_bit(irq, pending_irq_redir);
-
-        if (unlikely(!desc->handler->set_affinity))
-                return;
-
-        if (!cpus_empty(pending_irq_cpumask[irq])) {
-                cpus_and(tmp, pending_irq_cpumask[irq], cpu_online_map);
-                if (unlikely(!cpus_empty(tmp))) {
-                        desc->handler->set_affinity(irq | (redir ? IA64_IRQ_REDIRECTED : 0),
-                                                    pending_irq_cpumask[irq]);
-                }
-                cpus_clear(pending_irq_cpumask[irq]);
-        }
-}
-
-
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_HOTPLUG_CPU