[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-merge] io_apic.c, part 1




--On Monday, August 08, 2005 17:53:28 +0200 Andi Kleen <ak@xxxxxxx> wrote:

> On Mon, Aug 08, 2005 at 08:43:38AM -0700, Martin J. Bligh wrote:
>> This just shoves some ifdef wrappers around whole functions to
>> either not define them, or provide a no-op function instead.
>> The alternative to this is to split the file, but I tried that,
>> and it made an unholy mess. Plus it's much nicer for maintainance
>> to keep the alternative definitions right next to each other, if
>> it's this trivial.
> 
> I would prefer to just replace apic.c/io_apic.c completely with new
> files in the Xen case and perhaps factor the still needed functions out.
> That's much better than ifdef mess and apic/io_apic needed some
> cleanup anyways.

OK, this is roughly what happens if you do this, without pissing around
with all the makefiles and include headers for func declarations etc.
Yes, there's a lot less ifdefs. Not sure I like it any better personally,
and it's going to be a pig to maintain out of tree. Opinions?

diff -purN -X /home/mbligh/.diff.exclude virgin/arch/i386/kernel/apic.c 
io_apic_split/arch/i386/kernel/apic.c
--- virgin/arch/i386/kernel/apic.c      2005-06-17 12:48:29.000000000 -0700
+++ io_apic_split/arch/i386/kernel/apic.c       2005-08-08 16:00:34.869760704 
-0700
@@ -205,22 +205,6 @@ void __init connect_bsp_APIC(void)
        enable_apic_mode();
 }
 
-void disconnect_bsp_APIC(void)
-{
-       if (pic_mode) {
-               /*
-                * Put the board back into PIC mode (has an effect
-                * only on certain older boards).  Note that APIC
-                * interrupts, including IPIs, won't work beyond
-                * this point!  The only exception are INIT IPIs.
-                */
-               apic_printk(APIC_VERBOSE, "disabling APIC mode, "
-                               "entering PIC mode.\n");
-               outb(0x70, 0x22);
-               outb(0x00, 0x23);
-       }
-}
-
 void disable_local_APIC(void)
 {
        unsigned long value;
@@ -298,22 +282,6 @@ int __init verify_local_APIC(void)
        return 1;
 }
 
-void __init sync_Arb_IDs(void)
-{
-       /* Unsupported on P4 - see Intel Dev. Manual Vol. 3, Ch. 8.6.1 */
-       unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
-       if (ver >= 0x14)        /* P4 or higher */
-               return;
-       /*
-        * Wait for idle.
-        */
-       apic_wait_icr_idle();
-
-       apic_printk(APIC_DEBUG, "Synchronizing Arb IDs.\n");
-       apic_write_around(APIC_ICR, APIC_DEST_ALLINC | APIC_INT_LEVELTRIG
-                               | APIC_DM_INIT);
-}
-
 extern void __error_in_apic_c (void);
 
 /*
diff -purN -X /home/mbligh/.diff.exclude virgin/arch/i386/kernel/io_apic.c 
io_apic_split/arch/i386/kernel/io_apic.c
--- virgin/arch/i386/kernel/io_apic.c   2005-06-17 12:48:29.000000000 -0700
+++ io_apic_split/arch/i386/kernel/io_apic.c    2005-08-08 16:11:35.786286120 
-0700
@@ -107,143 +107,6 @@ static void add_pin_to_irq(unsigned int 
        entry->pin = pin;
 }
 
-/*
- * Reroute an IRQ to a different pin.
- */
-static void __init replace_pin_at_irq(unsigned int irq,
-                                     int oldapic, int oldpin,
-                                     int newapic, int newpin)
-{
-       struct irq_pin_list *entry = irq_2_pin + irq;
-
-       while (1) {
-               if (entry->apic == oldapic && entry->pin == oldpin) {
-                       entry->apic = newapic;
-                       entry->pin = newpin;
-               }
-               if (!entry->next)
-                       break;
-               entry = irq_2_pin + entry->next;
-       }
-}
-
-static void __modify_IO_APIC_irq (unsigned int irq, unsigned long enable, 
unsigned long disable)
-{
-       struct irq_pin_list *entry = irq_2_pin + irq;
-       unsigned int pin, reg;
-
-       for (;;) {
-               pin = entry->pin;
-               if (pin == -1)
-                       break;
-               reg = io_apic_read(entry->apic, 0x10 + pin*2);
-               reg &= ~disable;
-               reg |= enable;
-               io_apic_modify(entry->apic, 0x10 + pin*2, reg);
-               if (!entry->next)
-                       break;
-               entry = irq_2_pin + entry->next;
-       }
-}
-
-/* mask = 1 */
-static void __mask_IO_APIC_irq (unsigned int irq)
-{
-       __modify_IO_APIC_irq(irq, 0x00010000, 0);
-}
-
-/* mask = 0 */
-static void __unmask_IO_APIC_irq (unsigned int irq)
-{
-       __modify_IO_APIC_irq(irq, 0, 0x00010000);
-}
-
-/* mask = 1, trigger = 0 */
-static void __mask_and_edge_IO_APIC_irq (unsigned int irq)
-{
-       __modify_IO_APIC_irq(irq, 0x00010000, 0x00008000);
-}
-
-/* mask = 0, trigger = 1 */
-static void __unmask_and_level_IO_APIC_irq (unsigned int irq)
-{
-       __modify_IO_APIC_irq(irq, 0x00008000, 0x00010000);
-}
-
-static void mask_IO_APIC_irq (unsigned int irq)
-{
-       unsigned long flags;
-
-       spin_lock_irqsave(&ioapic_lock, flags);
-       __mask_IO_APIC_irq(irq);
-       spin_unlock_irqrestore(&ioapic_lock, flags);
-}
-
-static void unmask_IO_APIC_irq (unsigned int irq)
-{
-       unsigned long flags;
-
-       spin_lock_irqsave(&ioapic_lock, flags);
-       __unmask_IO_APIC_irq(irq);
-       spin_unlock_irqrestore(&ioapic_lock, flags);
-}
-
-static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
-{
-       struct IO_APIC_route_entry entry;
-       unsigned long flags;
-       
-       /* Check delivery_mode to be sure we're not clearing an SMI pin */
-       spin_lock_irqsave(&ioapic_lock, flags);
-       *(((int*)&entry) + 0) = io_apic_read(apic, 0x10 + 2 * pin);
-       *(((int*)&entry) + 1) = io_apic_read(apic, 0x11 + 2 * pin);
-       spin_unlock_irqrestore(&ioapic_lock, flags);
-       if (entry.delivery_mode == dest_SMI)
-               return;
-
-       /*
-        * Disable it in the IO-APIC irq-routing table:
-        */
-       memset(&entry, 0, sizeof(entry));
-       entry.mask = 1;
-       spin_lock_irqsave(&ioapic_lock, flags);
-       io_apic_write(apic, 0x10 + 2 * pin, *(((int *)&entry) + 0));
-       io_apic_write(apic, 0x11 + 2 * pin, *(((int *)&entry) + 1));
-       spin_unlock_irqrestore(&ioapic_lock, flags);
-}
-
-static void clear_IO_APIC (void)
-{
-       int apic, pin;
-
-       for (apic = 0; apic < nr_ioapics; apic++)
-               for (pin = 0; pin < nr_ioapic_registers[apic]; pin++)
-                       clear_IO_APIC_pin(apic, pin);
-}
-
-static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask)
-{
-       unsigned long flags;
-       int pin;
-       struct irq_pin_list *entry = irq_2_pin + irq;
-       unsigned int apicid_value;
-       
-       apicid_value = cpu_mask_to_apicid(cpumask);
-       /* Prepare to do the io_apic_write */
-       apicid_value = apicid_value << 24;
-       spin_lock_irqsave(&ioapic_lock, flags);
-       for (;;) {
-               pin = entry->pin;
-               if (pin == -1)
-                       break;
-               io_apic_write(entry->apic, 0x10 + 1 + pin*2, apicid_value);
-               if (!entry->next)
-                       break;
-               entry = irq_2_pin + entry->next;
-       }
-       spin_unlock_irqrestore(&ioapic_lock, flags);
-}
-
 #if defined(CONFIG_IRQBALANCE)
 # include <asm/processor.h>    /* kernel_thread() */
 # include <linux/kernel_stat.h>        /* kstat */
@@ -661,24 +524,6 @@ late_initcall(balanced_irq_init);
 static inline void move_irq(int irq) { }
 #endif /* CONFIG_IRQBALANCE */
 
-#ifndef CONFIG_SMP
-void fastcall send_IPI_self(int vector)
-{
-       unsigned int cfg;
-
-       /*
-        * Wait for idle.
-        */
-       apic_wait_icr_idle();
-       cfg = APIC_DM_FIXED | APIC_DEST_SELF | vector | APIC_DEST_LOGICAL;
-       /*
-        * Send the IPI. The write to APIC_ICR fires this off.
-        */
-       apic_write_around(APIC_ICR, cfg);
-}
-#endif /* !CONFIG_SMP */
-
-
 /*
  * support for broken MP BIOSs, enables hand-redirection of PIRQ0-7 to
  * specific CPU-side IRQs.
@@ -745,29 +590,6 @@ static int find_irq_entry(int apic, int 
 }
 
 /*
- * Find the pin to which IRQ[irq] (ISA) is connected
- */
-static int find_isa_irq_pin(int irq, int type)
-{
-       int i;
-
-       for (i = 0; i < mp_irq_entries; i++) {
-               int lbus = mp_irqs[i].mpc_srcbus;
-
-               if ((mp_bus_id_to_type[lbus] == MP_BUS_ISA ||
-                    mp_bus_id_to_type[lbus] == MP_BUS_EISA ||
-                    mp_bus_id_to_type[lbus] == MP_BUS_MCA ||
-                    mp_bus_id_to_type[lbus] == MP_BUS_NEC98
-                   ) &&
-                   (mp_irqs[i].mpc_irqtype == type) &&
-                   (mp_irqs[i].mpc_srcbusirq == irq))
-
-                       return mp_irqs[i].mpc_dstirq;
-       }
-       return -1;
-}
-
-/*
  * Find a specific PCI IRQ entry.
  * Not an __init, possibly needed by modules
  */
@@ -814,30 +636,6 @@ int IO_APIC_get_PCI_irq_vector(int bus, 
 }
 
 /*
- * This function currently is only a helper for the i386 smp boot process 
where 
- * we need to reprogram the ioredtbls to cater for the cpus which have come 
online
- * so mask in all cases should simply be TARGET_CPUS
- */
-void __init setup_ioapic_dest(void)
-{
-       int pin, ioapic, irq, irq_entry;
-
-       if (skip_ioapic_setup == 1)
-               return;
-
-       for (ioapic = 0; ioapic < nr_ioapics; ioapic++) {
-               for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) {
-                       irq_entry = find_irq_entry(ioapic, pin, mp_INT);
-                       if (irq_entry == -1)
-                               continue;
-                       irq = pin_2_irq(irq_entry, ioapic, pin);
-                       set_ioapic_affinity_irq(irq, TARGET_CPUS);
-               }
-
-       }
-}
-
-/*
  * EISA Edge/Level control register, ELCR
  */
 static int EISA_ELCR(unsigned int irq)
@@ -1153,32 +951,6 @@ next:
        return current_vector;
 }
 
-static struct hw_interrupt_type ioapic_level_type;
-static struct hw_interrupt_type ioapic_edge_type;
-
-#define IOAPIC_AUTO    -1
-#define IOAPIC_EDGE    0
-#define IOAPIC_LEVEL   1
-
-static inline void ioapic_register_intr(int irq, int vector, unsigned long 
trigger)
-{
-       if (use_pci_vector() && !platform_legacy_irq(irq)) {
-               if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
-                               trigger == IOAPIC_LEVEL)
-                       irq_desc[vector].handler = &ioapic_level_type;
-               else
-                       irq_desc[vector].handler = &ioapic_edge_type;
-               set_intr_gate(vector, interrupt[vector]);
-       } else  {
-               if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
-                               trigger == IOAPIC_LEVEL)
-                       irq_desc[irq].handler = &ioapic_level_type;
-               else
-                       irq_desc[irq].handler = &ioapic_edge_type;
-               set_intr_gate(vector, interrupt[irq]);
-       }
-}
-
 static void __init setup_IO_APIC_irqs(void)
 {
        struct IO_APIC_route_entry entry;
@@ -1255,203 +1027,6 @@ static void __init setup_IO_APIC_irqs(vo
                apic_printk(APIC_VERBOSE, " not connected.\n");
 }
 
-/*
- * Set up the 8259A-master output pin:
- */
-static void __init setup_ExtINT_IRQ0_pin(unsigned int pin, int vector)
-{
-       struct IO_APIC_route_entry entry;
-       unsigned long flags;
-
-       memset(&entry,0,sizeof(entry));
-
-       disable_8259A_irq(0);
-
-       /* mask LVT0 */
-       apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
-
-       /*
-        * We use logical delivery to get the timer IRQ
-        * to the first CPU.
-        */
-       entry.dest_mode = INT_DEST_MODE;
-       entry.mask = 0;                                 /* unmask IRQ now */
-       entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS);
-       entry.delivery_mode = INT_DELIVERY_MODE;
-       entry.polarity = 0;
-       entry.trigger = 0;
-       entry.vector = vector;
-
-       /*
-        * The timer IRQ doesn't have to know that behind the
-        * scene we have a 8259A-master in AEOI mode ...
-        */
-       irq_desc[0].handler = &ioapic_edge_type;
-
-       /*
-        * Add it to the IO-APIC irq-routing table:
-        */
-       spin_lock_irqsave(&ioapic_lock, flags);
-       io_apic_write(0, 0x11+2*pin, *(((int *)&entry)+1));
-       io_apic_write(0, 0x10+2*pin, *(((int *)&entry)+0));
-       spin_unlock_irqrestore(&ioapic_lock, flags);
-
-       enable_8259A_irq(0);
-}
-
-static inline void UNEXPECTED_IO_APIC(void)
-{
-}
-
-void __init print_IO_APIC(void)
-{
-       int apic, i;
-       union IO_APIC_reg_00 reg_00;
-       union IO_APIC_reg_01 reg_01;
-       union IO_APIC_reg_02 reg_02;
-       union IO_APIC_reg_03 reg_03;
-       unsigned long flags;
-
-       if (apic_verbosity == APIC_QUIET)
-               return;
-
-       printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
-       for (i = 0; i < nr_ioapics; i++)
-               printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n",
-                      mp_ioapics[i].mpc_apicid, nr_ioapic_registers[i]);
-
-       /*
-        * We are a bit conservative about what we expect.  We have to
-        * know about every hardware change ASAP.
-        */
-       printk(KERN_INFO "testing the IO APIC.......................\n");
-
-       for (apic = 0; apic < nr_ioapics; apic++) {
-
-       spin_lock_irqsave(&ioapic_lock, flags);
-       reg_00.raw = io_apic_read(apic, 0);
-       reg_01.raw = io_apic_read(apic, 1);
-       if (reg_01.bits.version >= 0x10)
-               reg_02.raw = io_apic_read(apic, 2);
-       if (reg_01.bits.version >= 0x20)
-               reg_03.raw = io_apic_read(apic, 3);
-       spin_unlock_irqrestore(&ioapic_lock, flags);
-
-       printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mpc_apicid);
-       printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw);
-       printk(KERN_DEBUG ".......    : physical APIC id: %02X\n", 
reg_00.bits.ID);
-       printk(KERN_DEBUG ".......    : Delivery Type: %X\n", 
reg_00.bits.delivery_type);
-       printk(KERN_DEBUG ".......    : LTS          : %X\n", reg_00.bits.LTS);
-       if (reg_00.bits.ID >= get_physical_broadcast())
-               UNEXPECTED_IO_APIC();
-       if (reg_00.bits.__reserved_1 || reg_00.bits.__reserved_2)
-               UNEXPECTED_IO_APIC();
-
-       printk(KERN_DEBUG ".... register #01: %08X\n", reg_01.raw);
-       printk(KERN_DEBUG ".......     : max redirection entries: %04X\n", 
reg_01.bits.entries);
-       if (    (reg_01.bits.entries != 0x0f) && /* older (Neptune) boards */
-               (reg_01.bits.entries != 0x17) && /* typical ISA+PCI boards */
-               (reg_01.bits.entries != 0x1b) && /* Compaq Proliant boards */
-               (reg_01.bits.entries != 0x1f) && /* dual Xeon boards */
-               (reg_01.bits.entries != 0x22) && /* bigger Xeon boards */
-               (reg_01.bits.entries != 0x2E) &&
-               (reg_01.bits.entries != 0x3F)
-       )
-               UNEXPECTED_IO_APIC();
-
-       printk(KERN_DEBUG ".......     : PRQ implemented: %X\n", 
reg_01.bits.PRQ);
-       printk(KERN_DEBUG ".......     : IO APIC version: %04X\n", 
reg_01.bits.version);
-       if (    (reg_01.bits.version != 0x01) && /* 82489DX IO-APICs */
-               (reg_01.bits.version != 0x10) && /* oldest IO-APICs */
-               (reg_01.bits.version != 0x11) && /* Pentium/Pro IO-APICs */
-               (reg_01.bits.version != 0x13) && /* Xeon IO-APICs */
-               (reg_01.bits.version != 0x20)    /* Intel P64H (82806 AA) */
-       )
-               UNEXPECTED_IO_APIC();
-       if (reg_01.bits.__reserved_1 || reg_01.bits.__reserved_2)
-               UNEXPECTED_IO_APIC();
-
-       /*
-        * Some Intel chipsets with IO APIC VERSION of 0x1? don't have reg_02,
-        * but the value of reg_02 is read as the previous read register
-        * value, so ignore it if reg_02 == reg_01.
-        */
-       if (reg_01.bits.version >= 0x10 && reg_02.raw != reg_01.raw) {
-               printk(KERN_DEBUG ".... register #02: %08X\n", reg_02.raw);
-               printk(KERN_DEBUG ".......     : arbitration: %02X\n", 
reg_02.bits.arbitration);
-               if (reg_02.bits.__reserved_1 || reg_02.bits.__reserved_2)
-                       UNEXPECTED_IO_APIC();
-       }
-
-       /*
-        * Some Intel chipsets with IO APIC VERSION of 0x2? don't have reg_02
-        * or reg_03, but the value of reg_0[23] is read as the previous read
-        * register value, so ignore it if reg_03 == reg_0[12].
-        */
-       if (reg_01.bits.version >= 0x20 && reg_03.raw != reg_02.raw &&
-           reg_03.raw != reg_01.raw) {
-               printk(KERN_DEBUG ".... register #03: %08X\n", reg_03.raw);
-               printk(KERN_DEBUG ".......     : Boot DT    : %X\n", 
reg_03.bits.boot_DT);
-               if (reg_03.bits.__reserved_1)
-                       UNEXPECTED_IO_APIC();
-       }
-
-       printk(KERN_DEBUG ".... IRQ redirection table:\n");
-
-       printk(KERN_DEBUG " NR Log Phy Mask Trig IRR Pol"
-                         " Stat Dest Deli Vect:   \n");
-
-       for (i = 0; i <= reg_01.bits.entries; i++) {
-               struct IO_APIC_route_entry entry;
-
-               spin_lock_irqsave(&ioapic_lock, flags);
-               *(((int *)&entry)+0) = io_apic_read(apic, 0x10+i*2);
-               *(((int *)&entry)+1) = io_apic_read(apic, 0x11+i*2);
-               spin_unlock_irqrestore(&ioapic_lock, flags);
-
-               printk(KERN_DEBUG " %02x %03X %02X  ",
-                       i,
-                       entry.dest.logical.logical_dest,
-                       entry.dest.physical.physical_dest
-               );
-
-               printk("%1d    %1d    %1d   %1d   %1d    %1d    %1d    %02X\n",
-                       entry.mask,
-                       entry.trigger,
-                       entry.irr,
-                       entry.polarity,
-                       entry.delivery_status,
-                       entry.dest_mode,
-                       entry.delivery_mode,
-                       entry.vector
-               );
-       }
-       }
-       if (use_pci_vector())
-               printk(KERN_INFO "Using vector-based indexing\n");
-       printk(KERN_DEBUG "IRQ to pin mappings:\n");
-       for (i = 0; i < NR_IRQS; i++) {
-               struct irq_pin_list *entry = irq_2_pin + i;
-               if (entry->pin < 0)
-                       continue;
-               if (use_pci_vector() && !platform_legacy_irq(i))
-                       printk(KERN_DEBUG "IRQ%d ", IO_APIC_VECTOR(i));
-               else
-                       printk(KERN_DEBUG "IRQ%d ", i);
-               for (;;) {
-                       printk("-> %d:%d", entry->apic, entry->pin);
-                       if (!entry->next)
-                               break;
-                       entry = irq_2_pin + entry->next;
-               }
-               printk("\n");
-       }
-
-       printk(KERN_INFO ".................................... done.\n");
-
-       return;
-}
-
 #if 0
 
 static void print_APIC_bitfield (int base)
@@ -1641,345 +1216,6 @@ void disable_IO_APIC(void)
        disconnect_bsp_APIC();
 }
 
-/*
- * function to set the IO-APIC physical IDs based on the
- * values stored in the MPC table.
- *
- * by Matt Domsch <Matt_Domsch@xxxxxxxx>  Tue Dec 21 12:25:05 CST 1999
- */
-
-#ifndef CONFIG_X86_NUMAQ
-static void __init setup_ioapic_ids_from_mpc(void)
-{
-       union IO_APIC_reg_00 reg_00;
-       physid_mask_t phys_id_present_map;
-       int apic;
-       int i;
-       unsigned char old_id;
-       unsigned long flags;
-
-       /*
-        * This is broken; anything with a real cpu count has to
-        * circumvent this idiocy regardless.
-        */
-       phys_id_present_map = ioapic_phys_id_map(phys_cpu_present_map);
-
-       /*
-        * Set the IOAPIC ID to the value stored in the MPC table.
-        */
-       for (apic = 0; apic < nr_ioapics; apic++) {
-
-               /* Read the register 0 value */
-               spin_lock_irqsave(&ioapic_lock, flags);
-               reg_00.raw = io_apic_read(apic, 0);
-               spin_unlock_irqrestore(&ioapic_lock, flags);
-               
-               old_id = mp_ioapics[apic].mpc_apicid;
-
-               if (mp_ioapics[apic].mpc_apicid >= get_physical_broadcast()) {
-                       printk(KERN_ERR "BIOS bug, IO-APIC#%d ID is %d in the 
MPC table!...\n",
-                               apic, mp_ioapics[apic].mpc_apicid);
-                       printk(KERN_ERR "... fixing up to %d. (tell your hw 
vendor)\n",
-                               reg_00.bits.ID);
-                       mp_ioapics[apic].mpc_apicid = reg_00.bits.ID;
-               }
-
-               /* Don't check I/O APIC IDs for some xAPIC systems.  They have
-                * no meaning without the serial APIC bus. */
-               if (NO_IOAPIC_CHECK)
-                       continue;
-               /*
-                * Sanity check, is the ID really free? Every APIC in a
-                * system must have a unique ID or we get lots of nice
-                * 'stuck on smp_invalidate_needed IPI wait' messages.
-                */
-               if (check_apicid_used(phys_id_present_map,
-                                       mp_ioapics[apic].mpc_apicid)) {
-                       printk(KERN_ERR "BIOS bug, IO-APIC#%d ID %d is already 
used!...\n",
-                               apic, mp_ioapics[apic].mpc_apicid);
-                       for (i = 0; i < get_physical_broadcast(); i++)
-                               if (!physid_isset(i, phys_id_present_map))
-                                       break;
-                       if (i >= get_physical_broadcast())
-                               panic("Max APIC ID exceeded!\n");
-                       printk(KERN_ERR "... fixing up to %d. (tell your hw 
vendor)\n",
-                               i);
-                       physid_set(i, phys_id_present_map);
-                       mp_ioapics[apic].mpc_apicid = i;
-               } else {
-                       physid_mask_t tmp;
-                       tmp = 
apicid_to_cpu_present(mp_ioapics[apic].mpc_apicid);
-                       apic_printk(APIC_VERBOSE, "Setting %d in the "
-                                       "phys_id_present_map\n",
-                                       mp_ioapics[apic].mpc_apicid);
-                       physids_or(phys_id_present_map, phys_id_present_map, 
tmp);
-               }
-
-
-               /*
-                * We need to adjust the IRQ routing table
-                * if the ID changed.
-                */
-               if (old_id != mp_ioapics[apic].mpc_apicid)
-                       for (i = 0; i < mp_irq_entries; i++)
-                               if (mp_irqs[i].mpc_dstapic == old_id)
-                                       mp_irqs[i].mpc_dstapic
-                                               = mp_ioapics[apic].mpc_apicid;
-
-               /*
-                * Read the right value from the MPC table and
-                * write it into the ID register.
-                */
-               apic_printk(APIC_VERBOSE, KERN_INFO
-                       "...changing IO-APIC physical APIC ID to %d ...",
-                       mp_ioapics[apic].mpc_apicid);
-
-               reg_00.bits.ID = mp_ioapics[apic].mpc_apicid;
-               spin_lock_irqsave(&ioapic_lock, flags);
-               io_apic_write(apic, 0, reg_00.raw);
-               spin_unlock_irqrestore(&ioapic_lock, flags);
-
-               /*
-                * Sanity check
-                */
-               spin_lock_irqsave(&ioapic_lock, flags);
-               reg_00.raw = io_apic_read(apic, 0);
-               spin_unlock_irqrestore(&ioapic_lock, flags);
-               if (reg_00.bits.ID != mp_ioapics[apic].mpc_apicid)
-                       printk("could not set ID!\n");
-               else
-                       apic_printk(APIC_VERBOSE, " ok.\n");
-       }
-}
-#else
-static void __init setup_ioapic_ids_from_mpc(void) { }
-#endif
-
-/*
- * There is a nasty bug in some older SMP boards, their mptable lies
- * about the timer IRQ. We do the following to work around the situation:
- *
- *     - timer IRQ defaults to IO-APIC IRQ
- *     - if this function detects that timer IRQs are defunct, then we fall
- *       back to ISA timer IRQs
- */
-static int __init timer_irq_works(void)
-{
-       unsigned long t1 = jiffies;
-
-       local_irq_enable();
-       /* Let ten ticks pass... */
-       mdelay((10 * 1000) / HZ);
-
-       /*
-        * Expect a few ticks at least, to be sure some possible
-        * glue logic does not lock up after one or two first
-        * ticks in a non-ExtINT mode.  Also the local APIC
-        * might have cached one ExtINT interrupt.  Finally, at
-        * least one tick may be lost due to delays.
-        */
-       if (jiffies - t1 > 4)
-               return 1;
-
-       return 0;
-}
-
-/*
- * In the SMP+IOAPIC case it might happen that there are an unspecified
- * number of pending IRQ events unhandled. These cases are very rare,
- * so we 'resend' these IRQs via IPIs, to the same CPU. It's much
- * better to do it this way as thus we do not have to be aware of
- * 'pending' interrupts in the IRQ path, except at this point.
- */
-/*
- * Edge triggered needs to resend any interrupt
- * that was delayed but this is now handled in the device
- * independent code.
- */
-
-/*
- * Starting up a edge-triggered IO-APIC interrupt is
- * nasty - we need to make sure that we get the edge.
- * If it is already asserted for some reason, we need
- * return 1 to indicate that is was pending.
- *
- * This is not complete - we should be able to fake
- * an edge even if it isn't on the 8259A...
- */
-static unsigned int startup_edge_ioapic_irq(unsigned int irq)
-{
-       int was_pending = 0;
-       unsigned long flags;
-
-       spin_lock_irqsave(&ioapic_lock, flags);
-       if (irq < 16) {
-               disable_8259A_irq(irq);
-               if (i8259A_irq_pending(irq))
-                       was_pending = 1;
-       }
-       __unmask_IO_APIC_irq(irq);
-       spin_unlock_irqrestore(&ioapic_lock, flags);
-
-       return was_pending;
-}
-
-/*
- * Once we have recorded IRQ_PENDING already, we can mask the
- * interrupt for real. This prevents IRQ storms from unhandled
- * devices.
- */
-static void ack_edge_ioapic_irq(unsigned int irq)
-{
-       move_irq(irq);
-       if ((irq_desc[irq].status & (IRQ_PENDING | IRQ_DISABLED))
-                                       == (IRQ_PENDING | IRQ_DISABLED))
-               mask_IO_APIC_irq(irq);
-       ack_APIC_irq();
-}
-
-/*
- * Level triggered interrupts can just be masked,
- * and shutting down and starting up the interrupt
- * is the same as enabling and disabling them -- except
- * with a startup need to return a "was pending" value.
- *
- * Level triggered interrupts are special because we
- * do not touch any IO-APIC register while handling
- * them. We ack the APIC in the end-IRQ handler, not
- * in the start-IRQ-handler. Protection against reentrance
- * from the same interrupt is still provided, both by the
- * generic IRQ layer and by the fact that an unacked local
- * APIC does not accept IRQs.
- */
-static unsigned int startup_level_ioapic_irq (unsigned int irq)
-{
-       unmask_IO_APIC_irq(irq);
-
-       return 0; /* don't check for pending */
-}
-
-static void end_level_ioapic_irq (unsigned int irq)
-{
-       unsigned long v;
-       int i;
-
-       move_irq(irq);
-/*
- * It appears there is an erratum which affects at least version 0x11
- * of I/O APIC (that's the 82093AA and cores integrated into various
- * chipsets).  Under certain conditions a level-triggered interrupt is
- * erroneously delivered as edge-triggered one but the respective IRR
- * bit gets set nevertheless.  As a result the I/O unit expects an EOI
- * message but it will never arrive and further interrupts are blocked
- * from the source.  The exact reason is so far unknown, but the
- * phenomenon was observed when two consecutive interrupt requests
- * from a given source get delivered to the same CPU and the source is
- * temporarily disabled in between.
- *
- * A workaround is to simulate an EOI message manually.  We achieve it
- * by setting the trigger mode to edge and then to level when the edge
- * trigger mode gets detected in the TMR of a local APIC for a
- * level-triggered interrupt.  We mask the source for the time of the
- * operation to prevent an edge-triggered interrupt escaping meanwhile.
- * The idea is from Manfred Spraul.  --macro
- */
-       i = IO_APIC_VECTOR(irq);
-
-       v = apic_read(APIC_TMR + ((i & ~0x1f) >> 1));
-
-       ack_APIC_irq();
-
-       if (!(v & (1 << (i & 0x1f)))) {
-               atomic_inc(&irq_mis_count);
-               spin_lock(&ioapic_lock);
-               __mask_and_edge_IO_APIC_irq(irq);
-               __unmask_and_level_IO_APIC_irq(irq);
-               spin_unlock(&ioapic_lock);
-       }
-}
-
-#ifdef CONFIG_PCI_MSI
-static unsigned int startup_edge_ioapic_vector(unsigned int vector)
-{
-       int irq = vector_to_irq(vector);
-
-       return startup_edge_ioapic_irq(irq);
-}
-
-static void ack_edge_ioapic_vector(unsigned int vector)
-{
-       int irq = vector_to_irq(vector);
-
-       ack_edge_ioapic_irq(irq);
-}
-
-static unsigned int startup_level_ioapic_vector (unsigned int vector)
-{
-       int irq = vector_to_irq(vector);
-
-       return startup_level_ioapic_irq (irq);
-}
-
-static void end_level_ioapic_vector (unsigned int vector)
-{
-       int irq = vector_to_irq(vector);
-
-       end_level_ioapic_irq(irq);
-}
-
-static void mask_IO_APIC_vector (unsigned int vector)
-{
-       int irq = vector_to_irq(vector);
-
-       mask_IO_APIC_irq(irq);
-}
-
-static void unmask_IO_APIC_vector (unsigned int vector)
-{
-       int irq = vector_to_irq(vector);
-
-       unmask_IO_APIC_irq(irq);
-}
-
-static void set_ioapic_affinity_vector (unsigned int vector,
-                                       cpumask_t cpu_mask)
-{
-       int irq = vector_to_irq(vector);
-
-       set_ioapic_affinity_irq(irq, cpu_mask);
-}
-#endif
-
-/*
- * Level and edge triggered IO-APIC interrupts need different handling,
- * so we use two separate IRQ descriptors. Edge triggered IRQs can be
- * handled with the level-triggered descriptor, but that one has slightly
- * more overhead. Level-triggered interrupts cannot be handled with the
- * edge-triggered handler, without risking IRQ storms and other ugly
- * races.
- */
-static struct hw_interrupt_type ioapic_edge_type = {
-       .typename       = "IO-APIC-edge",
-       .startup        = startup_edge_ioapic,
-       .shutdown       = shutdown_edge_ioapic,
-       .enable         = enable_edge_ioapic,
-       .disable        = disable_edge_ioapic,
-       .ack            = ack_edge_ioapic,
-       .end            = end_edge_ioapic,
-       .set_affinity   = set_ioapic_affinity,
-};
-
-static struct hw_interrupt_type ioapic_level_type = {
-       .typename       = "IO-APIC-level",
-       .startup        = startup_level_ioapic,
-       .shutdown       = shutdown_level_ioapic,
-       .enable         = enable_level_ioapic,
-       .disable        = disable_level_ioapic,
-       .ack            = mask_and_ack_level_ioapic,
-       .end            = end_level_ioapic,
-       .set_affinity   = set_ioapic_affinity,
-};
-
 static inline void init_IO_APIC_traps(void)
 {
        int irq;
@@ -2017,233 +1253,6 @@ static inline void init_IO_APIC_traps(vo
        }
 }
 
-static void enable_lapic_irq (unsigned int irq)
-{
-       unsigned long v;
-
-       v = apic_read(APIC_LVT0);
-       apic_write_around(APIC_LVT0, v & ~APIC_LVT_MASKED);
-}
-
-static void disable_lapic_irq (unsigned int irq)
-{
-       unsigned long v;
-
-       v = apic_read(APIC_LVT0);
-       apic_write_around(APIC_LVT0, v | APIC_LVT_MASKED);
-}
-
-static void ack_lapic_irq (unsigned int irq)
-{
-       ack_APIC_irq();
-}
-
-static void end_lapic_irq (unsigned int i) { /* nothing */ }
-
-static struct hw_interrupt_type lapic_irq_type = {
-       .typename       = "local-APIC-edge",
-       .startup        = NULL, /* startup_irq() not used for IRQ0 */
-       .shutdown       = NULL, /* shutdown_irq() not used for IRQ0 */
-       .enable         = enable_lapic_irq,
-       .disable        = disable_lapic_irq,
-       .ack            = ack_lapic_irq,
-       .end            = end_lapic_irq
-};
-
-static void setup_nmi (void)
-{
-       /*
-        * Dirty trick to enable the NMI watchdog ...
-        * We put the 8259A master into AEOI mode and
-        * unmask on all local APICs LVT0 as NMI.
-        *
-        * The idea to use the 8259A in AEOI mode ('8259A Virtual Wire')
-        * is from Maciej W. Rozycki - so we do not have to EOI from
-        * the NMI handler or the timer interrupt.
-        */ 
-       apic_printk(APIC_VERBOSE, KERN_INFO "activating NMI Watchdog ...");
-
-       on_each_cpu(enable_NMI_through_LVT0, NULL, 1, 1);
-
-       apic_printk(APIC_VERBOSE, " done.\n");
-}
-
-/*
- * This looks a bit hackish but it's about the only one way of sending
- * a few INTA cycles to 8259As and any associated glue logic.  ICR does
- * not support the ExtINT mode, unfortunately.  We need to send these
- * cycles as some i82489DX-based boards have glue logic that keeps the
- * 8259A interrupt line asserted until INTA.  --macro
- */
-static inline void unlock_ExtINT_logic(void)
-{
-       int pin, i;
-       struct IO_APIC_route_entry entry0, entry1;
-       unsigned char save_control, save_freq_select;
-       unsigned long flags;
-
-       pin = find_isa_irq_pin(8, mp_INT);
-       if (pin == -1)
-               return;
-
-       spin_lock_irqsave(&ioapic_lock, flags);
-       *(((int *)&entry0) + 1) = io_apic_read(0, 0x11 + 2 * pin);
-       *(((int *)&entry0) + 0) = io_apic_read(0, 0x10 + 2 * pin);
-       spin_unlock_irqrestore(&ioapic_lock, flags);
-       clear_IO_APIC_pin(0, pin);
-
-       memset(&entry1, 0, sizeof(entry1));
-
-       entry1.dest_mode = 0;                   /* physical delivery */
-       entry1.mask = 0;                        /* unmask IRQ now */
-       entry1.dest.physical.physical_dest = hard_smp_processor_id();
-       entry1.delivery_mode = dest_ExtINT;
-       entry1.polarity = entry0.polarity;
-       entry1.trigger = 0;
-       entry1.vector = 0;
-
-       spin_lock_irqsave(&ioapic_lock, flags);
-       io_apic_write(0, 0x11 + 2 * pin, *(((int *)&entry1) + 1));
-       io_apic_write(0, 0x10 + 2 * pin, *(((int *)&entry1) + 0));
-       spin_unlock_irqrestore(&ioapic_lock, flags);
-
-       save_control = CMOS_READ(RTC_CONTROL);
-       save_freq_select = CMOS_READ(RTC_FREQ_SELECT);
-       CMOS_WRITE((save_freq_select & ~RTC_RATE_SELECT) | 0x6,
-                  RTC_FREQ_SELECT);
-       CMOS_WRITE(save_control | RTC_PIE, RTC_CONTROL);
-
-       i = 100;
-       while (i-- > 0) {
-               mdelay(10);
-               if ((CMOS_READ(RTC_INTR_FLAGS) & RTC_PF) == RTC_PF)
-                       i -= 10;
-       }
-
-       CMOS_WRITE(save_control, RTC_CONTROL);
-       CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
-       clear_IO_APIC_pin(0, pin);
-
-       spin_lock_irqsave(&ioapic_lock, flags);
-       io_apic_write(0, 0x11 + 2 * pin, *(((int *)&entry0) + 1));
-       io_apic_write(0, 0x10 + 2 * pin, *(((int *)&entry0) + 0));
-       spin_unlock_irqrestore(&ioapic_lock, flags);
-}
-
-/*
- * This code may look a bit paranoid, but it's supposed to cooperate with
- * a wide range of boards and BIOS bugs.  Fortunately only the timer IRQ
- * is so screwy.  Thanks to Brian Perkins for testing/hacking this beast
- * fanatically on his truly buggy board.
- */
-static inline void check_timer(void)
-{
-       int pin1, pin2;
-       int vector;
-
-       /*
-        * get/set the timer IRQ vector:
-        */
-       disable_8259A_irq(0);
-       vector = assign_irq_vector(0);
-       set_intr_gate(vector, interrupt[0]);
-
-       /*
-        * Subtle, code in do_timer_interrupt() expects an AEOI
-        * mode for the 8259A whenever interrupts are routed
-        * through I/O APICs.  Also IRQ0 has to be enabled in
-        * the 8259A which implies the virtual wire has to be
-        * disabled in the local APIC.
-        */
-       apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
-       init_8259A(1);
-       timer_ack = 1;
-       enable_8259A_irq(0);
-
-       pin1 = find_isa_irq_pin(0, mp_INT);
-       pin2 = find_isa_irq_pin(0, mp_ExtINT);
-
-       printk(KERN_INFO "..TIMER: vector=0x%02X pin1=%d pin2=%d\n", vector, 
pin1, pin2);
-
-       if (pin1 != -1) {
-               /*
-                * Ok, does IRQ0 through the IOAPIC work?
-                */
-               unmask_IO_APIC_irq(0);
-               if (timer_irq_works()) {
-                       if (nmi_watchdog == NMI_IO_APIC) {
-                               disable_8259A_irq(0);
-                               setup_nmi();
-                               enable_8259A_irq(0);
-                       }
-                       return;
-               }
-               clear_IO_APIC_pin(0, pin1);
-               printk(KERN_ERR "..MP-BIOS bug: 8254 timer not connected to 
IO-APIC\n");
-       }
-
-       printk(KERN_INFO "...trying to set up timer (IRQ0) through the 8259A 
... ");
-       if (pin2 != -1) {
-               printk("\n..... (found pin %d) ...", pin2);
-               /*
-                * legacy devices should be connected to IO APIC #0
-                */
-               setup_ExtINT_IRQ0_pin(pin2, vector);
-               if (timer_irq_works()) {
-                       printk("works.\n");
-                       if (pin1 != -1)
-                               replace_pin_at_irq(0, 0, pin1, 0, pin2);
-                       else
-                               add_pin_to_irq(0, 0, pin2);
-                       if (nmi_watchdog == NMI_IO_APIC) {
-                               setup_nmi();
-                       }
-                       return;
-               }
-               /*
-                * Cleanup, just in case ...
-                */
-               clear_IO_APIC_pin(0, pin2);
-       }
-       printk(" failed.\n");
-
-       if (nmi_watchdog == NMI_IO_APIC) {
-               printk(KERN_WARNING "timer doesn't work through the IO-APIC - 
disabling NMI Watchdog!\n");
-               nmi_watchdog = 0;
-       }
-
-       printk(KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
-
-       disable_8259A_irq(0);
-       irq_desc[0].handler = &lapic_irq_type;
-       apic_write_around(APIC_LVT0, APIC_DM_FIXED | vector);   /* Fixed mode */
-       enable_8259A_irq(0);
-
-       if (timer_irq_works()) {
-               printk(" works.\n");
-               return;
-       }
-       apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | vector);
-       printk(" failed.\n");
-
-       printk(KERN_INFO "...trying to set up timer as ExtINT IRQ...");
-
-       timer_ack = 0;
-       init_8259A(0);
-       make_8259A_irq(0);
-       apic_write_around(APIC_LVT0, APIC_DM_EXTINT);
-
-       unlock_ExtINT_logic();
-
-       if (timer_irq_works()) {
-               printk(" works.\n");
-               return;
-       }
-       printk(" failed :(.\n");
-       panic("IO-APIC + timer doesn't work!  Boot with apic=debug and send a "
-               "report.  Then try booting with the 'noapic' option");
-}
-
 /*
  *
  * IRQ's that are handled by the PIC in the MPS IOAPIC case.
@@ -2389,79 +1398,6 @@ device_initcall(ioapic_init_sysfs);
 
 #ifdef CONFIG_ACPI_BOOT
 
-int __init io_apic_get_unique_id (int ioapic, int apic_id)
-{
-       union IO_APIC_reg_00 reg_00;
-       static physid_mask_t apic_id_map = PHYSID_MASK_NONE;
-       physid_mask_t tmp;
-       unsigned long flags;
-       int i = 0;
-
-       /*
-        * The P4 platform supports up to 256 APIC IDs on two separate APIC 
-        * buses (one for LAPICs, one for IOAPICs), where predecessors only 
-        * supports up to 16 on one shared APIC bus.
-        * 
-        * TBD: Expand LAPIC/IOAPIC support on P4-class systems to take full
-        *      advantage of new APIC bus architecture.
-        */
-
-       if (physids_empty(apic_id_map))
-               apic_id_map = ioapic_phys_id_map(phys_cpu_present_map);
-
-       spin_lock_irqsave(&ioapic_lock, flags);
-       reg_00.raw = io_apic_read(ioapic, 0);
-       spin_unlock_irqrestore(&ioapic_lock, flags);
-
-       if (apic_id >= get_physical_broadcast()) {
-               printk(KERN_WARNING "IOAPIC[%d]: Invalid apic_id %d, trying "
-                       "%d\n", ioapic, apic_id, reg_00.bits.ID);
-               apic_id = reg_00.bits.ID;
-       }
-
-       /*
-        * Every APIC in a system must have a unique ID or we get lots of nice 
-        * 'stuck on smp_invalidate_needed IPI wait' messages.
-        */
-       if (check_apicid_used(apic_id_map, apic_id)) {
-
-               for (i = 0; i < get_physical_broadcast(); i++) {
-                       if (!check_apicid_used(apic_id_map, i))
-                               break;
-               }
-
-               if (i == get_physical_broadcast())
-                       panic("Max apic_id exceeded!\n");
-
-               printk(KERN_WARNING "IOAPIC[%d]: apic_id %d already used, "
-                       "trying %d\n", ioapic, apic_id, i);
-
-               apic_id = i;
-       } 
-
-       tmp = apicid_to_cpu_present(apic_id);
-       physids_or(apic_id_map, apic_id_map, tmp);
-
-       if (reg_00.bits.ID != apic_id) {
-               reg_00.bits.ID = apic_id;
-
-               spin_lock_irqsave(&ioapic_lock, flags);
-               io_apic_write(ioapic, 0, reg_00.raw);
-               reg_00.raw = io_apic_read(ioapic, 0);
-               spin_unlock_irqrestore(&ioapic_lock, flags);
-
-               /* Sanity check */
-               if (reg_00.bits.ID != apic_id)
-                       panic("IOAPIC[%d]: Unable change apic_id!\n", ioapic);
-       }
-
-       apic_printk(APIC_VERBOSE, KERN_INFO
-                       "IOAPIC[%d]: Assigned apic_id %d\n", ioapic, apic_id);
-
-       return apic_id;
-}
-
-
 int __init io_apic_get_version (int ioapic)
 {
        union IO_APIC_reg_01    reg_01;
diff -purN -X /home/mbligh/.diff.exclude virgin/arch/i386/mach-default/apic.c 
io_apic_split/arch/i386/mach-default/apic.c
--- virgin/arch/i386/mach-default/apic.c        1969-12-31 16:00:00.000000000 
-0800
+++ io_apic_split/arch/i386/mach-default/apic.c 2005-08-08 16:02:55.803335544 
-0700
@@ -0,0 +1,57 @@
+#include <linux/config.h>
+#include <linux/init.h>
+
+#include <linux/mm.h>
+#include <linux/irq.h>
+#include <linux/delay.h>
+#include <linux/bootmem.h>
+#include <linux/smp_lock.h>
+#include <linux/interrupt.h>
+#include <linux/mc146818rtc.h>
+#include <linux/kernel_stat.h>
+#include <linux/sysdev.h>
+
+#include <asm/atomic.h>
+#include <asm/smp.h>
+#include <asm/mtrr.h>
+#include <asm/mpspec.h>
+#include <asm/desc.h>
+#include <asm/arch_hooks.h>
+#include <asm/hpet.h>
+
+#include <mach_apic.h>
+
+#include "io_ports.h"
+
+void disconnect_bsp_APIC(void)
+{
+       if (pic_mode) {
+               /*
+                * Put the board back into PIC mode (has an effect
+                * only on certain older boards).  Note that APIC
+                * interrupts, including IPIs, won't work beyond
+                * this point!  The only exception are INIT IPIs.
+                */
+               apic_printk(APIC_VERBOSE, "disabling APIC mode, "
+                               "entering PIC mode.\n");
+               outb(0x70, 0x22);
+               outb(0x00, 0x23);
+       }
+}
+
+void __init sync_Arb_IDs(void)
+{
+       /* Unsupported on P4 - see Intel Dev. Manual Vol. 3, Ch. 8.6.1 */
+       unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
+       if (ver >= 0x14)        /* P4 or higher */
+               return;
+       /*
+        * Wait for idle.
+        */
+       apic_wait_icr_idle();
+
+       apic_printk(APIC_DEBUG, "Synchronizing Arb IDs.\n");
+       apic_write_around(APIC_ICR, APIC_DEST_ALLINC | APIC_INT_LEVELTRIG
+                               | APIC_DM_INIT);
+}
+
diff -purN -X /home/mbligh/.diff.exclude 
virgin/arch/i386/mach-default/io_apic.c 
io_apic_split/arch/i386/mach-default/io_apic.c
--- virgin/arch/i386/mach-default/io_apic.c     1969-12-31 16:00:00.000000000 
-0800
+++ io_apic_split/arch/i386/mach-default/io_apic.c      2005-08-08 
16:23:20.275187528 -0700
@@ -0,0 +1,1106 @@
+/*
+ *     Intel IO-APIC support for multi-Pentium hosts.
+ *
+ *     Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar, Hajnalka Szabo
+ *
+ *     Many thanks to Stig Venaas for trying out countless experimental
+ *     patches and reporting/debugging problems patiently!
+ *
+ *     (c) 1999, Multiple IO-APIC support, developed by
+ *     Ken-ichi Yaku <yaku@xxxxxxxxxxxxxxxxxxxx> and
+ *      Hidemi Kishimoto <kisimoto@xxxxxxxxxxxxxxxxxxxx>,
+ *     further tested and cleaned up by Zach Brown <zab@xxxxxxxxxx>
+ *     and Ingo Molnar <mingo@xxxxxxxxxx>
+ *
+ *     Fixes
+ *     Maciej W. Rozycki       :       Bits for genuine 82489DX APICs;
+ *                                     thanks to Eric Gilmore
+ *                                     and Rolf G. Tews
+ *                                     for testing these extensively
+ *     Paul Diefenbaugh        :       Added full ACPI support
+ */
+
+#include <linux/mm.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/sched.h>
+#include <linux/config.h>
+#include <linux/smp_lock.h>
+#include <linux/mc146818rtc.h>
+#include <linux/compiler.h>
+#include <linux/acpi.h>
+
+#include <linux/sysdev.h>
+#include <asm/io.h>
+#include <asm/smp.h>
+#include <asm/desc.h>
+#include <asm/timer.h>
+
+#include <mach_apic.h>
+
+#include "io_ports.h"
+
+/*
+ * Reroute an IRQ to a different pin.
+ */
+static void __init replace_pin_at_irq(unsigned int irq,
+                                     int oldapic, int oldpin,
+                                     int newapic, int newpin)
+{
+       struct irq_pin_list *entry = irq_2_pin + irq;
+
+       while (1) {
+               if (entry->apic == oldapic && entry->pin == oldpin) {
+                       entry->apic = newapic;
+                       entry->pin = newpin;
+               }
+               if (!entry->next)
+                       break;
+               entry = irq_2_pin + entry->next;
+       }
+}
+
+static void __modify_IO_APIC_irq (unsigned int irq, unsigned long enable, 
unsigned long disable)
+{
+       struct irq_pin_list *entry = irq_2_pin + irq;
+       unsigned int pin, reg;
+
+       for (;;) {
+               pin = entry->pin;
+               if (pin == -1)
+                       break;
+               reg = io_apic_read(entry->apic, 0x10 + pin*2);
+               reg &= ~disable;
+               reg |= enable;
+               io_apic_modify(entry->apic, 0x10 + pin*2, reg);
+               if (!entry->next)
+                       break;
+               entry = irq_2_pin + entry->next;
+       }
+}
+
+/* mask = 1 */
+static void __mask_IO_APIC_irq (unsigned int irq)
+{
+       __modify_IO_APIC_irq(irq, 0x00010000, 0);
+}
+
+/* mask = 0 */
+static void __unmask_IO_APIC_irq (unsigned int irq)
+{
+       __modify_IO_APIC_irq(irq, 0, 0x00010000);
+}
+
+/* mask = 1, trigger = 0 */
+static void __mask_and_edge_IO_APIC_irq (unsigned int irq)
+{
+       __modify_IO_APIC_irq(irq, 0x00010000, 0x00008000);
+}
+
+/* mask = 0, trigger = 1 */
+static void __unmask_and_level_IO_APIC_irq (unsigned int irq)
+{
+       __modify_IO_APIC_irq(irq, 0x00008000, 0x00010000);
+}
+
+static void mask_IO_APIC_irq (unsigned int irq)
+{
+       unsigned long flags;
+
+       spin_lock_irqsave(&ioapic_lock, flags);
+       __mask_IO_APIC_irq(irq);
+       spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+static void unmask_IO_APIC_irq (unsigned int irq)
+{
+       unsigned long flags;
+
+       spin_lock_irqsave(&ioapic_lock, flags);
+       __unmask_IO_APIC_irq(irq);
+       spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
+{
+       struct IO_APIC_route_entry entry;
+       unsigned long flags;
+       
+       /* Check delivery_mode to be sure we're not clearing an SMI pin */
+       spin_lock_irqsave(&ioapic_lock, flags);
+       *(((int*)&entry) + 0) = io_apic_read(apic, 0x10 + 2 * pin);
+       *(((int*)&entry) + 1) = io_apic_read(apic, 0x11 + 2 * pin);
+       spin_unlock_irqrestore(&ioapic_lock, flags);
+       if (entry.delivery_mode == dest_SMI)
+               return;
+
+       /*
+        * Disable it in the IO-APIC irq-routing table:
+        */
+       memset(&entry, 0, sizeof(entry));
+       entry.mask = 1;
+       spin_lock_irqsave(&ioapic_lock, flags);
+       io_apic_write(apic, 0x10 + 2 * pin, *(((int *)&entry) + 0));
+       io_apic_write(apic, 0x11 + 2 * pin, *(((int *)&entry) + 1));
+       spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+static void clear_IO_APIC (void)
+{
+       int apic, pin;
+
+       for (apic = 0; apic < nr_ioapics; apic++)
+               for (pin = 0; pin < nr_ioapic_registers[apic]; pin++)
+                       clear_IO_APIC_pin(apic, pin);
+}
+
+static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask)
+{
+       unsigned long flags;
+       int pin;
+       struct irq_pin_list *entry = irq_2_pin + irq;
+       unsigned int apicid_value;
+       
+       apicid_value = cpu_mask_to_apicid(cpumask);
+       /* Prepare to do the io_apic_write */
+       apicid_value = apicid_value << 24;
+       spin_lock_irqsave(&ioapic_lock, flags);
+       for (;;) {
+               pin = entry->pin;
+               if (pin == -1)
+                       break;
+               io_apic_write(entry->apic, 0x10 + 1 + pin*2, apicid_value);
+               if (!entry->next)
+                       break;
+               entry = irq_2_pin + entry->next;
+       }
+       spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+#ifndef CONFIG_SMP
+void fastcall send_IPI_self(int vector)
+{
+       unsigned int cfg;
+
+       /*
+        * Wait for idle.
+        */
+       apic_wait_icr_idle();
+       cfg = APIC_DM_FIXED | APIC_DEST_SELF | vector | APIC_DEST_LOGICAL;
+       /*
+        * Send the IPI. The write to APIC_ICR fires this off.
+        */
+       apic_write_around(APIC_ICR, cfg);
+}
+#endif /* !CONFIG_SMP */
+
+/*
+ * Find the pin to which IRQ[irq] (ISA) is connected
+ */
+static int find_isa_irq_pin(int irq, int type)
+{
+       int i;
+
+       for (i = 0; i < mp_irq_entries; i++) {
+               int lbus = mp_irqs[i].mpc_srcbus;
+
+               if ((mp_bus_id_to_type[lbus] == MP_BUS_ISA ||
+                    mp_bus_id_to_type[lbus] == MP_BUS_EISA ||
+                    mp_bus_id_to_type[lbus] == MP_BUS_MCA ||
+                    mp_bus_id_to_type[lbus] == MP_BUS_NEC98
+                   ) &&
+                   (mp_irqs[i].mpc_irqtype == type) &&
+                   (mp_irqs[i].mpc_srcbusirq == irq))
+
+                       return mp_irqs[i].mpc_dstirq;
+       }
+       return -1;
+}
+
+/*
+ * This function currently is only a helper for the i386 smp boot process 
where 
+ * we need to reprogram the ioredtbls to cater for the cpus which have come 
online
+ * so mask in all cases should simply be TARGET_CPUS
+ */
+void __init setup_ioapic_dest(void)
+{
+       int pin, ioapic, irq, irq_entry;
+
+       if (skip_ioapic_setup == 1)
+               return;
+
+       for (ioapic = 0; ioapic < nr_ioapics; ioapic++) {
+               for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) {
+                       irq_entry = find_irq_entry(ioapic, pin, mp_INT);
+                       if (irq_entry == -1)
+                               continue;
+                       irq = pin_2_irq(irq_entry, ioapic, pin);
+                       set_ioapic_affinity_irq(irq, TARGET_CPUS);
+               }
+
+       }
+}
+
+static struct hw_interrupt_type ioapic_level_type;
+static struct hw_interrupt_type ioapic_edge_type;
+
+#define IOAPIC_AUTO    -1
+#define IOAPIC_EDGE    0
+#define IOAPIC_LEVEL   1
+
+static inline void ioapic_register_intr(int irq, int vector, unsigned long 
trigger)
+{
+       if (use_pci_vector() && !platform_legacy_irq(irq)) {
+               if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
+                               trigger == IOAPIC_LEVEL)
+                       irq_desc[vector].handler = &ioapic_level_type;
+               else
+                       irq_desc[vector].handler = &ioapic_edge_type;
+               set_intr_gate(vector, interrupt[vector]);
+       } else  {
+               if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
+                               trigger == IOAPIC_LEVEL)
+                       irq_desc[irq].handler = &ioapic_level_type;
+               else
+                       irq_desc[irq].handler = &ioapic_edge_type;
+               set_intr_gate(vector, interrupt[irq]);
+       }
+}
+
+/*
+ * Set up the 8259A-master output pin:
+ */
+static void __init setup_ExtINT_IRQ0_pin(unsigned int pin, int vector)
+{
+       struct IO_APIC_route_entry entry;
+       unsigned long flags;
+
+       memset(&entry,0,sizeof(entry));
+
+       disable_8259A_irq(0);
+
+       /* mask LVT0 */
+       apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
+
+       /*
+        * We use logical delivery to get the timer IRQ
+        * to the first CPU.
+        */
+       entry.dest_mode = INT_DEST_MODE;
+       entry.mask = 0;                                 /* unmask IRQ now */
+       entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS);
+       entry.delivery_mode = INT_DELIVERY_MODE;
+       entry.polarity = 0;
+       entry.trigger = 0;
+       entry.vector = vector;
+
+       /*
+        * The timer IRQ doesn't have to know that behind the
+        * scene we have a 8259A-master in AEOI mode ...
+        */
+       irq_desc[0].handler = &ioapic_edge_type;
+
+       /*
+        * Add it to the IO-APIC irq-routing table:
+        */
+       spin_lock_irqsave(&ioapic_lock, flags);
+       io_apic_write(0, 0x11+2*pin, *(((int *)&entry)+1));
+       io_apic_write(0, 0x10+2*pin, *(((int *)&entry)+0));
+       spin_unlock_irqrestore(&ioapic_lock, flags);
+
+       enable_8259A_irq(0);
+}
+
+static inline void UNEXPECTED_IO_APIC(void)
+{
+}
+
+void __init print_IO_APIC(void)
+{
+       int apic, i;
+       union IO_APIC_reg_00 reg_00;
+       union IO_APIC_reg_01 reg_01;
+       union IO_APIC_reg_02 reg_02;
+       union IO_APIC_reg_03 reg_03;
+       unsigned long flags;
+
+       if (apic_verbosity == APIC_QUIET)
+               return;
+
+       printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
+       for (i = 0; i < nr_ioapics; i++)
+               printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n",
+                      mp_ioapics[i].mpc_apicid, nr_ioapic_registers[i]);
+
+       /*
+        * We are a bit conservative about what we expect.  We have to
+        * know about every hardware change ASAP.
+        */
+       printk(KERN_INFO "testing the IO APIC.......................\n");
+
+       for (apic = 0; apic < nr_ioapics; apic++) {
+
+       spin_lock_irqsave(&ioapic_lock, flags);
+       reg_00.raw = io_apic_read(apic, 0);
+       reg_01.raw = io_apic_read(apic, 1);
+       if (reg_01.bits.version >= 0x10)
+               reg_02.raw = io_apic_read(apic, 2);
+       if (reg_01.bits.version >= 0x20)
+               reg_03.raw = io_apic_read(apic, 3);
+       spin_unlock_irqrestore(&ioapic_lock, flags);
+
+       printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mpc_apicid);
+       printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw);
+       printk(KERN_DEBUG ".......    : physical APIC id: %02X\n", 
reg_00.bits.ID);
+       printk(KERN_DEBUG ".......    : Delivery Type: %X\n", 
reg_00.bits.delivery_type);
+       printk(KERN_DEBUG ".......    : LTS          : %X\n", reg_00.bits.LTS);
+       if (reg_00.bits.ID >= get_physical_broadcast())
+               UNEXPECTED_IO_APIC();
+       if (reg_00.bits.__reserved_1 || reg_00.bits.__reserved_2)
+               UNEXPECTED_IO_APIC();
+
+       printk(KERN_DEBUG ".... register #01: %08X\n", reg_01.raw);
+       printk(KERN_DEBUG ".......     : max redirection entries: %04X\n", 
reg_01.bits.entries);
+       if (    (reg_01.bits.entries != 0x0f) && /* older (Neptune) boards */
+               (reg_01.bits.entries != 0x17) && /* typical ISA+PCI boards */
+               (reg_01.bits.entries != 0x1b) && /* Compaq Proliant boards */
+               (reg_01.bits.entries != 0x1f) && /* dual Xeon boards */
+               (reg_01.bits.entries != 0x22) && /* bigger Xeon boards */
+               (reg_01.bits.entries != 0x2E) &&
+               (reg_01.bits.entries != 0x3F)
+       )
+               UNEXPECTED_IO_APIC();
+
+       printk(KERN_DEBUG ".......     : PRQ implemented: %X\n", 
reg_01.bits.PRQ);
+       printk(KERN_DEBUG ".......     : IO APIC version: %04X\n", 
reg_01.bits.version);
+       if (    (reg_01.bits.version != 0x01) && /* 82489DX IO-APICs */
+               (reg_01.bits.version != 0x10) && /* oldest IO-APICs */
+               (reg_01.bits.version != 0x11) && /* Pentium/Pro IO-APICs */
+               (reg_01.bits.version != 0x13) && /* Xeon IO-APICs */
+               (reg_01.bits.version != 0x20)    /* Intel P64H (82806 AA) */
+       )
+               UNEXPECTED_IO_APIC();
+       if (reg_01.bits.__reserved_1 || reg_01.bits.__reserved_2)
+               UNEXPECTED_IO_APIC();
+
+       /*
+        * Some Intel chipsets with IO APIC VERSION of 0x1? don't have reg_02,
+        * but the value of reg_02 is read as the previous read register
+        * value, so ignore it if reg_02 == reg_01.
+        */
+       if (reg_01.bits.version >= 0x10 && reg_02.raw != reg_01.raw) {
+               printk(KERN_DEBUG ".... register #02: %08X\n", reg_02.raw);
+               printk(KERN_DEBUG ".......     : arbitration: %02X\n", 
reg_02.bits.arbitration);
+               if (reg_02.bits.__reserved_1 || reg_02.bits.__reserved_2)
+                       UNEXPECTED_IO_APIC();
+       }
+
+       /*
+        * Some Intel chipsets with IO APIC VERSION of 0x2? don't have reg_02
+        * or reg_03, but the value of reg_0[23] is read as the previous read
+        * register value, so ignore it if reg_03 == reg_0[12].
+        */
+       if (reg_01.bits.version >= 0x20 && reg_03.raw != reg_02.raw &&
+           reg_03.raw != reg_01.raw) {
+               printk(KERN_DEBUG ".... register #03: %08X\n", reg_03.raw);
+               printk(KERN_DEBUG ".......     : Boot DT    : %X\n", 
reg_03.bits.boot_DT);
+               if (reg_03.bits.__reserved_1)
+                       UNEXPECTED_IO_APIC();
+       }
+
+       printk(KERN_DEBUG ".... IRQ redirection table:\n");
+
+       printk(KERN_DEBUG " NR Log Phy Mask Trig IRR Pol"
+                         " Stat Dest Deli Vect:   \n");
+
+       for (i = 0; i <= reg_01.bits.entries; i++) {
+               struct IO_APIC_route_entry entry;
+
+               spin_lock_irqsave(&ioapic_lock, flags);
+               *(((int *)&entry)+0) = io_apic_read(apic, 0x10+i*2);
+               *(((int *)&entry)+1) = io_apic_read(apic, 0x11+i*2);
+               spin_unlock_irqrestore(&ioapic_lock, flags);
+
+               printk(KERN_DEBUG " %02x %03X %02X  ",
+                       i,
+                       entry.dest.logical.logical_dest,
+                       entry.dest.physical.physical_dest
+               );
+
+               printk("%1d    %1d    %1d   %1d   %1d    %1d    %1d    %02X\n",
+                       entry.mask,
+                       entry.trigger,
+                       entry.irr,
+                       entry.polarity,
+                       entry.delivery_status,
+                       entry.dest_mode,
+                       entry.delivery_mode,
+                       entry.vector
+               );
+       }
+       }
+       if (use_pci_vector())
+               printk(KERN_INFO "Using vector-based indexing\n");
+       printk(KERN_DEBUG "IRQ to pin mappings:\n");
+       for (i = 0; i < NR_IRQS; i++) {
+               struct irq_pin_list *entry = irq_2_pin + i;
+               if (entry->pin < 0)
+                       continue;
+               if (use_pci_vector() && !platform_legacy_irq(i))
+                       printk(KERN_DEBUG "IRQ%d ", IO_APIC_VECTOR(i));
+               else
+                       printk(KERN_DEBUG "IRQ%d ", i);
+               for (;;) {
+                       printk("-> %d:%d", entry->apic, entry->pin);
+                       if (!entry->next)
+                               break;
+                       entry = irq_2_pin + entry->next;
+               }
+               printk("\n");
+       }
+
+       printk(KERN_INFO ".................................... done.\n");
+
+       return;
+}
+
+/*
+ * function to set the IO-APIC physical IDs based on the
+ * values stored in the MPC table.
+ *
+ * by Matt Domsch <Matt_Domsch@xxxxxxxx>  Tue Dec 21 12:25:05 CST 1999
+ */
+
+#ifdef CONFIG_X86_NUMAQ
+static void __init setup_ioapic_ids_from_mpc(void) { }
+#else
+static void __init setup_ioapic_ids_from_mpc(void)
+{
+       union IO_APIC_reg_00 reg_00;
+       physid_mask_t phys_id_present_map;
+       int apic;
+       int i;
+       unsigned char old_id;
+       unsigned long flags;
+
+       /*
+        * This is broken; anything with a real cpu count has to
+        * circumvent this idiocy regardless.
+        */
+       phys_id_present_map = ioapic_phys_id_map(phys_cpu_present_map);
+
+       /*
+        * Set the IOAPIC ID to the value stored in the MPC table.
+        */
+       for (apic = 0; apic < nr_ioapics; apic++) {
+
+               /* Read the register 0 value */
+               spin_lock_irqsave(&ioapic_lock, flags);
+               reg_00.raw = io_apic_read(apic, 0);
+               spin_unlock_irqrestore(&ioapic_lock, flags);
+               
+               old_id = mp_ioapics[apic].mpc_apicid;
+
+               if (mp_ioapics[apic].mpc_apicid >= get_physical_broadcast()) {
+                       printk(KERN_ERR "BIOS bug, IO-APIC#%d ID is %d in the 
MPC table!...\n",
+                               apic, mp_ioapics[apic].mpc_apicid);
+                       printk(KERN_ERR "... fixing up to %d. (tell your hw 
vendor)\n",
+                               reg_00.bits.ID);
+                       mp_ioapics[apic].mpc_apicid = reg_00.bits.ID;
+               }
+
+               /* Don't check I/O APIC IDs for some xAPIC systems.  They have
+                * no meaning without the serial APIC bus. */
+               if (NO_IOAPIC_CHECK)
+                       continue;
+               /*
+                * Sanity check, is the ID really free? Every APIC in a
+                * system must have a unique ID or we get lots of nice
+                * 'stuck on smp_invalidate_needed IPI wait' messages.
+                */
+               if (check_apicid_used(phys_id_present_map,
+                                       mp_ioapics[apic].mpc_apicid)) {
+                       printk(KERN_ERR "BIOS bug, IO-APIC#%d ID %d is already 
used!...\n",
+                               apic, mp_ioapics[apic].mpc_apicid);
+                       for (i = 0; i < get_physical_broadcast(); i++)
+                               if (!physid_isset(i, phys_id_present_map))
+                                       break;
+                       if (i >= get_physical_broadcast())
+                               panic("Max APIC ID exceeded!\n");
+                       printk(KERN_ERR "... fixing up to %d. (tell your hw 
vendor)\n",
+                               i);
+                       physid_set(i, phys_id_present_map);
+                       mp_ioapics[apic].mpc_apicid = i;
+               } else {
+                       physid_mask_t tmp;
+                       tmp = 
apicid_to_cpu_present(mp_ioapics[apic].mpc_apicid);
+                       apic_printk(APIC_VERBOSE, "Setting %d in the "
+                                       "phys_id_present_map\n",
+                                       mp_ioapics[apic].mpc_apicid);
+                       physids_or(phys_id_present_map, phys_id_present_map, 
tmp);
+               }
+
+
+               /*
+                * We need to adjust the IRQ routing table
+                * if the ID changed.
+                */
+               if (old_id != mp_ioapics[apic].mpc_apicid)
+                       for (i = 0; i < mp_irq_entries; i++)
+                               if (mp_irqs[i].mpc_dstapic == old_id)
+                                       mp_irqs[i].mpc_dstapic
+                                               = mp_ioapics[apic].mpc_apicid;
+
+               /*
+                * Read the right value from the MPC table and
+                * write it into the ID register.
+                */
+               apic_printk(APIC_VERBOSE, KERN_INFO
+                       "...changing IO-APIC physical APIC ID to %d ...",
+                       mp_ioapics[apic].mpc_apicid);
+
+               reg_00.bits.ID = mp_ioapics[apic].mpc_apicid;
+               spin_lock_irqsave(&ioapic_lock, flags);
+               io_apic_write(apic, 0, reg_00.raw);
+               spin_unlock_irqrestore(&ioapic_lock, flags);
+
+               /*
+                * Sanity check
+                */
+               spin_lock_irqsave(&ioapic_lock, flags);
+               reg_00.raw = io_apic_read(apic, 0);
+               spin_unlock_irqrestore(&ioapic_lock, flags);
+               if (reg_00.bits.ID != mp_ioapics[apic].mpc_apicid)
+                       printk("could not set ID!\n");
+               else
+                       apic_printk(APIC_VERBOSE, " ok.\n");
+       }
+}
+#endif /* !CONFIG_NUMAQ */
+
+/*
+ * There is a nasty bug in some older SMP boards, their mptable lies
+ * about the timer IRQ. We do the following to work around the situation:
+ *
+ *     - timer IRQ defaults to IO-APIC IRQ
+ *     - if this function detects that timer IRQs are defunct, then we fall
+ *       back to ISA timer IRQs
+ */
+static int __init timer_irq_works(void)
+{
+       unsigned long t1 = jiffies;
+
+       local_irq_enable();
+       /* Let ten ticks pass... */
+       mdelay((10 * 1000) / HZ);
+
+       /*
+        * Expect a few ticks at least, to be sure some possible
+        * glue logic does not lock up after one or two first
+        * ticks in a non-ExtINT mode.  Also the local APIC
+        * might have cached one ExtINT interrupt.  Finally, at
+        * least one tick may be lost due to delays.
+        */
+       if (jiffies - t1 > 4)
+               return 1;
+
+       return 0;
+}
+
+/*
+ * In the SMP+IOAPIC case it might happen that there are an unspecified
+ * number of pending IRQ events unhandled. These cases are very rare,
+ * so we 'resend' these IRQs via IPIs, to the same CPU. It's much
+ * better to do it this way as thus we do not have to be aware of
+ * 'pending' interrupts in the IRQ path, except at this point.
+ */
+/*
+ * Edge triggered needs to resend any interrupt
+ * that was delayed but this is now handled in the device
+ * independent code.
+ */
+
+/*
+ * Starting up a edge-triggered IO-APIC interrupt is
+ * nasty - we need to make sure that we get the edge.
+ * If it is already asserted for some reason, we need
+ * return 1 to indicate that is was pending.
+ *
+ * This is not complete - we should be able to fake
+ * an edge even if it isn't on the 8259A...
+ */
+static unsigned int startup_edge_ioapic_irq(unsigned int irq)
+{
+       int was_pending = 0;
+       unsigned long flags;
+
+       spin_lock_irqsave(&ioapic_lock, flags);
+       if (irq < 16) {
+               disable_8259A_irq(irq);
+               if (i8259A_irq_pending(irq))
+                       was_pending = 1;
+       }
+       __unmask_IO_APIC_irq(irq);
+       spin_unlock_irqrestore(&ioapic_lock, flags);
+
+       return was_pending;
+}
+
+/*
+ * Once we have recorded IRQ_PENDING already, we can mask the
+ * interrupt for real. This prevents IRQ storms from unhandled
+ * devices.
+ */
+static void ack_edge_ioapic_irq(unsigned int irq)
+{
+       move_irq(irq);
+       if ((irq_desc[irq].status & (IRQ_PENDING | IRQ_DISABLED))
+                                       == (IRQ_PENDING | IRQ_DISABLED))
+               mask_IO_APIC_irq(irq);
+       ack_APIC_irq();
+}
+
+/*
+ * Level triggered interrupts can just be masked,
+ * and shutting down and starting up the interrupt
+ * is the same as enabling and disabling them -- except
+ * with a startup need to return a "was pending" value.
+ *
+ * Level triggered interrupts are special because we
+ * do not touch any IO-APIC register while handling
+ * them. We ack the APIC in the end-IRQ handler, not
+ * in the start-IRQ-handler. Protection against reentrance
+ * from the same interrupt is still provided, both by the
+ * generic IRQ layer and by the fact that an unacked local
+ * APIC does not accept IRQs.
+ */
+static unsigned int startup_level_ioapic_irq (unsigned int irq)
+{
+       unmask_IO_APIC_irq(irq);
+
+       return 0; /* don't check for pending */
+}
+
+static void end_level_ioapic_irq (unsigned int irq)
+{
+       unsigned long v;
+       int i;
+
+       move_irq(irq);
+/*
+ * It appears there is an erratum which affects at least version 0x11
+ * of I/O APIC (that's the 82093AA and cores integrated into various
+ * chipsets).  Under certain conditions a level-triggered interrupt is
+ * erroneously delivered as edge-triggered one but the respective IRR
+ * bit gets set nevertheless.  As a result the I/O unit expects an EOI
+ * message but it will never arrive and further interrupts are blocked
+ * from the source.  The exact reason is so far unknown, but the
+ * phenomenon was observed when two consecutive interrupt requests
+ * from a given source get delivered to the same CPU and the source is
+ * temporarily disabled in between.
+ *
+ * A workaround is to simulate an EOI message manually.  We achieve it
+ * by setting the trigger mode to edge and then to level when the edge
+ * trigger mode gets detected in the TMR of a local APIC for a
+ * level-triggered interrupt.  We mask the source for the time of the
+ * operation to prevent an edge-triggered interrupt escaping meanwhile.
+ * The idea is from Manfred Spraul.  --macro
+ */
+       i = IO_APIC_VECTOR(irq);
+
+       v = apic_read(APIC_TMR + ((i & ~0x1f) >> 1));
+
+       ack_APIC_irq();
+
+       if (!(v & (1 << (i & 0x1f)))) {
+               atomic_inc(&irq_mis_count);
+               spin_lock(&ioapic_lock);
+               __mask_and_edge_IO_APIC_irq(irq);
+               __unmask_and_level_IO_APIC_irq(irq);
+               spin_unlock(&ioapic_lock);
+       }
+}
+
+#ifdef CONFIG_PCI_MSI
+static unsigned int startup_edge_ioapic_vector(unsigned int vector)
+{
+       int irq = vector_to_irq(vector);
+
+       return startup_edge_ioapic_irq(irq);
+}
+
+static void ack_edge_ioapic_vector(unsigned int vector)
+{
+       int irq = vector_to_irq(vector);
+
+       ack_edge_ioapic_irq(irq);
+}
+
+static unsigned int startup_level_ioapic_vector (unsigned int vector)
+{
+       int irq = vector_to_irq(vector);
+
+       return startup_level_ioapic_irq (irq);
+}
+
+static void end_level_ioapic_vector (unsigned int vector)
+{
+       int irq = vector_to_irq(vector);
+
+       end_level_ioapic_irq(irq);
+}
+
+static void mask_IO_APIC_vector (unsigned int vector)
+{
+       int irq = vector_to_irq(vector);
+
+       mask_IO_APIC_irq(irq);
+}
+
+static void unmask_IO_APIC_vector (unsigned int vector)
+{
+       int irq = vector_to_irq(vector);
+
+       unmask_IO_APIC_irq(irq);
+}
+
+static void set_ioapic_affinity_vector (unsigned int vector,
+                                       cpumask_t cpu_mask)
+{
+       int irq = vector_to_irq(vector);
+
+       set_ioapic_affinity_irq(irq, cpu_mask);
+}
+#endif
+
+/*
+ * Level and edge triggered IO-APIC interrupts need different handling,
+ * so we use two separate IRQ descriptors. Edge triggered IRQs can be
+ * handled with the level-triggered descriptor, but that one has slightly
+ * more overhead. Level-triggered interrupts cannot be handled with the
+ * edge-triggered handler, without risking IRQ storms and other ugly
+ * races.
+ */
+static struct hw_interrupt_type ioapic_edge_type = {
+       .typename       = "IO-APIC-edge",
+       .startup        = startup_edge_ioapic,
+       .shutdown       = shutdown_edge_ioapic,
+       .enable         = enable_edge_ioapic,
+       .disable        = disable_edge_ioapic,
+       .ack            = ack_edge_ioapic,
+       .end            = end_edge_ioapic,
+       .set_affinity   = set_ioapic_affinity,
+};
+
+static struct hw_interrupt_type ioapic_level_type = {
+       .typename       = "IO-APIC-level",
+       .startup        = startup_level_ioapic,
+       .shutdown       = shutdown_level_ioapic,
+       .enable         = enable_level_ioapic,
+       .disable        = disable_level_ioapic,
+       .ack            = mask_and_ack_level_ioapic,
+       .end            = end_level_ioapic,
+       .set_affinity   = set_ioapic_affinity,
+};
+
+static void enable_lapic_irq (unsigned int irq)
+{
+       unsigned long v;
+
+       v = apic_read(APIC_LVT0);
+       apic_write_around(APIC_LVT0, v & ~APIC_LVT_MASKED);
+}
+
+static void disable_lapic_irq (unsigned int irq)
+{
+       unsigned long v;
+
+       v = apic_read(APIC_LVT0);
+       apic_write_around(APIC_LVT0, v | APIC_LVT_MASKED);
+}
+
+static void ack_lapic_irq (unsigned int irq)
+{
+       ack_APIC_irq();
+}
+
+static void end_lapic_irq (unsigned int i) { /* nothing */ }
+
+static struct hw_interrupt_type lapic_irq_type = {
+       .typename       = "local-APIC-edge",
+       .startup        = NULL, /* startup_irq() not used for IRQ0 */
+       .shutdown       = NULL, /* shutdown_irq() not used for IRQ0 */
+       .enable         = enable_lapic_irq,
+       .disable        = disable_lapic_irq,
+       .ack            = ack_lapic_irq,
+       .end            = end_lapic_irq
+};
+
+static void setup_nmi (void)
+{
+       /*
+        * Dirty trick to enable the NMI watchdog ...
+        * We put the 8259A master into AEOI mode and
+        * unmask on all local APICs LVT0 as NMI.
+        *
+        * The idea to use the 8259A in AEOI mode ('8259A Virtual Wire')
+        * is from Maciej W. Rozycki - so we do not have to EOI from
+        * the NMI handler or the timer interrupt.
+        */ 
+       apic_printk(APIC_VERBOSE, KERN_INFO "activating NMI Watchdog ...");
+
+       on_each_cpu(enable_NMI_through_LVT0, NULL, 1, 1);
+
+       apic_printk(APIC_VERBOSE, " done.\n");
+}
+
+/*
+ * This looks a bit hackish but it's about the only one way of sending
+ * a few INTA cycles to 8259As and any associated glue logic.  ICR does
+ * not support the ExtINT mode, unfortunately.  We need to send these
+ * cycles as some i82489DX-based boards have glue logic that keeps the
+ * 8259A interrupt line asserted until INTA.  --macro
+ */
+static inline void unlock_ExtINT_logic(void)
+{
+       int pin, i;
+       struct IO_APIC_route_entry entry0, entry1;
+       unsigned char save_control, save_freq_select;
+       unsigned long flags;
+
+       pin = find_isa_irq_pin(8, mp_INT);
+       if (pin == -1)
+               return;
+
+       spin_lock_irqsave(&ioapic_lock, flags);
+       *(((int *)&entry0) + 1) = io_apic_read(0, 0x11 + 2 * pin);
+       *(((int *)&entry0) + 0) = io_apic_read(0, 0x10 + 2 * pin);
+       spin_unlock_irqrestore(&ioapic_lock, flags);
+       clear_IO_APIC_pin(0, pin);
+
+       memset(&entry1, 0, sizeof(entry1));
+
+       entry1.dest_mode = 0;                   /* physical delivery */
+       entry1.mask = 0;                        /* unmask IRQ now */
+       entry1.dest.physical.physical_dest = hard_smp_processor_id();
+       entry1.delivery_mode = dest_ExtINT;
+       entry1.polarity = entry0.polarity;
+       entry1.trigger = 0;
+       entry1.vector = 0;
+
+       spin_lock_irqsave(&ioapic_lock, flags);
+       io_apic_write(0, 0x11 + 2 * pin, *(((int *)&entry1) + 1));
+       io_apic_write(0, 0x10 + 2 * pin, *(((int *)&entry1) + 0));
+       spin_unlock_irqrestore(&ioapic_lock, flags);
+
+       save_control = CMOS_READ(RTC_CONTROL);
+       save_freq_select = CMOS_READ(RTC_FREQ_SELECT);
+       CMOS_WRITE((save_freq_select & ~RTC_RATE_SELECT) | 0x6,
+                  RTC_FREQ_SELECT);
+       CMOS_WRITE(save_control | RTC_PIE, RTC_CONTROL);
+
+       i = 100;
+       while (i-- > 0) {
+               mdelay(10);
+               if ((CMOS_READ(RTC_INTR_FLAGS) & RTC_PF) == RTC_PF)
+                       i -= 10;
+       }
+
+       CMOS_WRITE(save_control, RTC_CONTROL);
+       CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
+       clear_IO_APIC_pin(0, pin);
+
+       spin_lock_irqsave(&ioapic_lock, flags);
+       io_apic_write(0, 0x11 + 2 * pin, *(((int *)&entry0) + 1));
+       io_apic_write(0, 0x10 + 2 * pin, *(((int *)&entry0) + 0));
+       spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+/*
+ * This code may look a bit paranoid, but it's supposed to cooperate with
+ * a wide range of boards and BIOS bugs.  Fortunately only the timer IRQ
+ * is so screwy.  Thanks to Brian Perkins for testing/hacking this beast
+ * fanatically on his truly buggy board.
+ */
+static inline void check_timer(void)
+{
+       int pin1, pin2;
+       int vector;
+
+       /*
+        * get/set the timer IRQ vector:
+        */
+       disable_8259A_irq(0);
+       vector = assign_irq_vector(0);
+       set_intr_gate(vector, interrupt[0]);
+
+       /*
+        * Subtle, code in do_timer_interrupt() expects an AEOI
+        * mode for the 8259A whenever interrupts are routed
+        * through I/O APICs.  Also IRQ0 has to be enabled in
+        * the 8259A which implies the virtual wire has to be
+        * disabled in the local APIC.
+        */
+       apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
+       init_8259A(1);
+       timer_ack = 1;
+       enable_8259A_irq(0);
+
+       pin1 = find_isa_irq_pin(0, mp_INT);
+       pin2 = find_isa_irq_pin(0, mp_ExtINT);
+
+       printk(KERN_INFO "..TIMER: vector=0x%02X pin1=%d pin2=%d\n", vector, 
pin1, pin2);
+
+       if (pin1 != -1) {
+               /*
+                * Ok, does IRQ0 through the IOAPIC work?
+                */
+               unmask_IO_APIC_irq(0);
+               if (timer_irq_works()) {
+                       if (nmi_watchdog == NMI_IO_APIC) {
+                               disable_8259A_irq(0);
+                               setup_nmi();
+                               enable_8259A_irq(0);
+                       }
+                       return;
+               }
+               clear_IO_APIC_pin(0, pin1);
+               printk(KERN_ERR "..MP-BIOS bug: 8254 timer not connected to 
IO-APIC\n");
+       }
+
+       printk(KERN_INFO "...trying to set up timer (IRQ0) through the 8259A 
... ");
+       if (pin2 != -1) {
+               printk("\n..... (found pin %d) ...", pin2);
+               /*
+                * legacy devices should be connected to IO APIC #0
+                */
+               setup_ExtINT_IRQ0_pin(pin2, vector);
+               if (timer_irq_works()) {
+                       printk("works.\n");
+                       if (pin1 != -1)
+                               replace_pin_at_irq(0, 0, pin1, 0, pin2);
+                       else
+                               add_pin_to_irq(0, 0, pin2);
+                       if (nmi_watchdog == NMI_IO_APIC) {
+                               setup_nmi();
+                       }
+                       return;
+               }
+               /*
+                * Cleanup, just in case ...
+                */
+               clear_IO_APIC_pin(0, pin2);
+       }
+       printk(" failed.\n");
+
+       if (nmi_watchdog == NMI_IO_APIC) {
+               printk(KERN_WARNING "timer doesn't work through the IO-APIC - 
disabling NMI Watchdog!\n");
+               nmi_watchdog = 0;
+       }
+
+       printk(KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
+
+       disable_8259A_irq(0);
+       irq_desc[0].handler = &lapic_irq_type;
+       apic_write_around(APIC_LVT0, APIC_DM_FIXED | vector);   /* Fixed mode */
+       enable_8259A_irq(0);
+
+       if (timer_irq_works()) {
+               printk(" works.\n");
+               return;
+       }
+       apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | vector);
+       printk(" failed.\n");
+
+       printk(KERN_INFO "...trying to set up timer as ExtINT IRQ...");
+
+       timer_ack = 0;
+       init_8259A(0);
+       make_8259A_irq(0);
+       apic_write_around(APIC_LVT0, APIC_DM_EXTINT);
+
+       unlock_ExtINT_logic();
+
+       if (timer_irq_works()) {
+               printk(" works.\n");
+               return;
+       }
+       printk(" failed :(.\n");
+       panic("IO-APIC + timer doesn't work!  Boot with apic=debug and send a "
+               "report.  Then try booting with the 'noapic' option");
+}
+
+int __init io_apic_get_unique_id (int ioapic, int apic_id)
+{
+       union IO_APIC_reg_00 reg_00;
+       static physid_mask_t apic_id_map = PHYSID_MASK_NONE;
+       physid_mask_t tmp;
+       unsigned long flags;
+       int i = 0;
+
+       /*
+        * The P4 platform supports up to 256 APIC IDs on two separate APIC 
+        * buses (one for LAPICs, one for IOAPICs), where predecessors only 
+        * supports up to 16 on one shared APIC bus.
+        * 
+        * TBD: Expand LAPIC/IOAPIC support on P4-class systems to take full
+        *      advantage of new APIC bus architecture.
+        */
+
+       if (physids_empty(apic_id_map))
+               apic_id_map = ioapic_phys_id_map(phys_cpu_present_map);
+
+       spin_lock_irqsave(&ioapic_lock, flags);
+       reg_00.raw = io_apic_read(ioapic, 0);
+       spin_unlock_irqrestore(&ioapic_lock, flags);
+
+       if (apic_id >= get_physical_broadcast()) {
+               printk(KERN_WARNING "IOAPIC[%d]: Invalid apic_id %d, trying "
+                       "%d\n", ioapic, apic_id, reg_00.bits.ID);
+               apic_id = reg_00.bits.ID;
+       }
+
+       /*
+        * Every APIC in a system must have a unique ID or we get lots of nice 
+        * 'stuck on smp_invalidate_needed IPI wait' messages.
+        */
+       if (check_apicid_used(apic_id_map, apic_id)) {
+
+               for (i = 0; i < get_physical_broadcast(); i++) {
+                       if (!check_apicid_used(apic_id_map, i))
+                               break;
+               }
+
+               if (i == get_physical_broadcast())
+                       panic("Max apic_id exceeded!\n");
+
+               printk(KERN_WARNING "IOAPIC[%d]: apic_id %d already used, "
+                       "trying %d\n", ioapic, apic_id, i);
+
+               apic_id = i;
+       } 
+
+       tmp = apicid_to_cpu_present(apic_id);
+       physids_or(apic_id_map, apic_id_map, tmp);
+
+       if (reg_00.bits.ID != apic_id) {
+               reg_00.bits.ID = apic_id;
+
+               spin_lock_irqsave(&ioapic_lock, flags);
+               io_apic_write(ioapic, 0, reg_00.raw);
+               reg_00.raw = io_apic_read(ioapic, 0);
+               spin_unlock_irqrestore(&ioapic_lock, flags);
+
+               /* Sanity check */
+               if (reg_00.bits.ID != apic_id)
+                       panic("IOAPIC[%d]: Unable change apic_id!\n", ioapic);
+       }
+
+       apic_printk(APIC_VERBOSE, KERN_INFO
+                       "IOAPIC[%d]: Assigned apic_id %d\n", ioapic, apic_id);
+
+       return apic_id;
+}
+
diff -purN -X /home/mbligh/.diff.exclude virgin/arch/i386/mach-xen/apic.c 
io_apic_split/arch/i386/mach-xen/apic.c
--- virgin/arch/i386/mach-xen/apic.c    1969-12-31 16:00:00.000000000 -0800
+++ io_apic_split/arch/i386/mach-xen/apic.c     2005-08-08 16:03:56.490109752 
-0700
@@ -0,0 +1,28 @@
+#include <linux/config.h>
+#include <linux/init.h>
+
+#include <linux/mm.h>
+#include <linux/irq.h>
+#include <linux/delay.h>
+#include <linux/bootmem.h>
+#include <linux/smp_lock.h>
+#include <linux/interrupt.h>
+#include <linux/mc146818rtc.h>
+#include <linux/kernel_stat.h>
+#include <linux/sysdev.h>
+
+#include <asm/atomic.h>
+#include <asm/smp.h>
+#include <asm/mtrr.h>
+#include <asm/mpspec.h>
+#include <asm/desc.h>
+#include <asm/arch_hooks.h>
+#include <asm/hpet.h>
+
+#include <mach_apic.h>
+
+#include "io_ports.h"
+
+void disconnect_bsp_APIC(void) {}
+
+void __init sync_Arb_IDs(void) {}
diff -purN -X /home/mbligh/.diff.exclude virgin/arch/i386/mach-xen/io_apic.c 
io_apic_split/arch/i386/mach-xen/io_apic.c
--- virgin/arch/i386/mach-xen/io_apic.c 1969-12-31 16:00:00.000000000 -0800
+++ io_apic_split/arch/i386/mach-xen/io_apic.c  2005-08-08 16:17:11.857195576 
-0700
@@ -0,0 +1,62 @@
+/*
+ *     Intel IO-APIC support for multi-Pentium hosts.
+ *
+ *     Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar, Hajnalka Szabo
+ *
+ *     Many thanks to Stig Venaas for trying out countless experimental
+ *     patches and reporting/debugging problems patiently!
+ *
+ *     (c) 1999, Multiple IO-APIC support, developed by
+ *     Ken-ichi Yaku <yaku@xxxxxxxxxxxxxxxxxxxx> and
+ *      Hidemi Kishimoto <kisimoto@xxxxxxxxxxxxxxxxxxxx>,
+ *     further tested and cleaned up by Zach Brown <zab@xxxxxxxxxx>
+ *     and Ingo Molnar <mingo@xxxxxxxxxx>
+ *
+ *     Fixes
+ *     Maciej W. Rozycki       :       Bits for genuine 82489DX APICs;
+ *                                     thanks to Eric Gilmore
+ *                                     and Rolf G. Tews
+ *                                     for testing these extensively
+ *     Paul Diefenbaugh        :       Added full ACPI support
+ */
+
+#include <linux/mm.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/sched.h>
+#include <linux/config.h>
+#include <linux/smp_lock.h>
+#include <linux/mc146818rtc.h>
+#include <linux/compiler.h>
+#include <linux/acpi.h>
+
+#include <linux/sysdev.h>
+#include <asm/io.h>
+#include <asm/smp.h>
+#include <asm/desc.h>
+#include <asm/timer.h>
+
+#include <mach_apic.h>
+
+#include "io_ports.h"
+
+#define clear_IO_APIC() ((void)0)
+
+static inline void ioapic_register_intr(int irq, int vector, unsigned long 
trigger)
+{
+}
+
+void __init print_IO_APIC(void) { }
+
+static void __init setup_ioapic_ids_from_mpc(void) { }
+
+#define check_timer() ((void)0)
+
+int __init io_apic_get_unique_id (int ioapic, int apic_id)
+{
+       return apic_id;
+}
+
+
diff -purN -X /home/mbligh/.diff.exclude virgin/include/asm-i386/hw_irq.h 
io_apic_split/include/asm-i386/hw_irq.h
--- virgin/include/asm-i386/hw_irq.h    2005-06-17 12:48:29.000000000 -0700
+++ io_apic_split/include/asm-i386/hw_irq.h     2005-08-08 15:57:25.821500408 
-0700
@@ -66,7 +66,7 @@ extern atomic_t irq_mis_count;
 
 #define IO_APIC_IRQ(x) (((x) >= 16) || ((1<<(x)) & io_apic_irqs))
 
-#if defined(CONFIG_X86_IO_APIC)
+#if defined(CONFIG_X86_IO_APIC) && !defined(CONFIG_XEN)
 static inline void hw_resend_irq(struct hw_interrupt_type *h, unsigned int i)
 {
        if (IO_APIC_IRQ(i))


_______________________________________________
Xen-merge mailing list
Xen-merge@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-merge


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.