[PATCH] x86: avoid wasting IRQs for PCI devices

I have submitted the patch for x86_64, this is submission for i386.

The patch changes the way IRQs are handed out to PCI devices.  Currently,
each I/O APIC pin gets associated with an IRQ, no matter if the pin is used
or not.  This imposes severe limitation on systems that have designs that
employ many I/O APICs, only utilizing couple lines of each, such as P64H2
chipset.  It is used in ES7000, and currently, there is no way to boot the
system with more that 9 I/O APICs.

The simple change below allows to boot a system with say 64 (or more) I/O
APICs, each providing 1 slot, which otherwise impossible because of the IRQ
gaps created for unused lines on each I/O APIC.  It does not resolve the
problem with number of devices that exceeds number of possible IRQs, but
eases up a tension for IRQs on any large system with potentually large
number of devices.

Signed-off-by: Natalie Protasevich <Natalie.Protasevich@unisys.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/arch/i386/kernel/mpparse.c b/arch/i386/kernel/mpparse.c
index 0a061056b8280ff38c7ca6359ef5aae56dfe5a6b..383a11600d2c35d4e940d5a3e8bb647accb45f6a 100644 (file)
--- a/arch/i386/kernel/mpparse.c
+++ b/arch/i386/kernel/mpparse.c
@@ -1058,11 +1058,20 @@ void __init mp_config_acpi_legacy_irqs (void)
        }
 }
 
+#define MAX_GSI_NUM    4096
+
 int mp_register_gsi (u32 gsi, int edge_level, int active_high_low)
 {
        int                     ioapic = -1;
        int                     ioapic_pin = 0;
        int                     idx, bit = 0;
+       static int              pci_irq = 16;
+       /*
+        * Mapping between Global System Interrups, which
+        * represent all possible interrupts, and IRQs
+        * assigned to actual devices.
+        */
+       static int              gsi_to_irq[MAX_GSI_NUM];
 
 #ifdef CONFIG_ACPI_BUS
        /* Don't set up the ACPI SCI because it's already set up */
@@ -1097,11 +1106,26 @@ int mp_register_gsi (u32 gsi, int edge_level, int active_high_low)
        if ((1<<bit) & mp_ioapic_routing[ioapic].pin_programmed[idx]) {
                Dprintk(KERN_DEBUG "Pin %d-%d already programmed\n",
                        mp_ioapic_routing[ioapic].apic_id, ioapic_pin);
-               return gsi;
+               return gsi_to_irq[gsi];
        }
 
        mp_ioapic_routing[ioapic].pin_programmed[idx] |= (1<<bit);
 
+       if (edge_level) {
+               /*
+                * For PCI devices assign IRQs in order, avoiding gaps
+                * due to unused I/O APIC pins.
+                */
+               int irq = gsi;
+               if (gsi < MAX_GSI_NUM) {
+                       gsi = pci_irq++;
+                       gsi_to_irq[irq] = gsi;
+               } else {
+                       printk(KERN_ERR "GSI %u is too high\n", gsi);
+                       return gsi;
+               }
+       }
+
        io_apic_set_pci_routing(ioapic, ioapic_pin, gsi,
                    edge_level == ACPI_EDGE_SENSITIVE ? 0 : 1,
                    active_high_low == ACPI_ACTIVE_HIGH ? 0 : 1);