static DEFINE_SPINLOCK(ioapic_lock);
static DEFINE_SPINLOCK(vector_lock);
-int timer_over_8254 __initdata = 1;
+int timer_through_8259 __initdata;
/*
* Is the SiS APIC rmw bug present ?
}
}
-static void __modify_IO_APIC_irq (unsigned int irq, unsigned long enable, unsigned long disable)
+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;
}
/* mask = 1 */
-static void __mask_IO_APIC_irq (unsigned int irq)
+static void __mask_IO_APIC_irq(unsigned int irq)
{
- __modify_IO_APIC_irq(irq, 0x00010000, 0);
+ __modify_IO_APIC_irq(irq, IO_APIC_REDIR_MASKED, 0);
}
/* mask = 0 */
-static void __unmask_IO_APIC_irq (unsigned int irq)
+static void __unmask_IO_APIC_irq(unsigned int irq)
{
- __modify_IO_APIC_irq(irq, 0, 0x00010000);
+ __modify_IO_APIC_irq(irq, 0, IO_APIC_REDIR_MASKED);
}
/* mask = 1, trigger = 0 */
-static void __mask_and_edge_IO_APIC_irq (unsigned int irq)
+static void __mask_and_edge_IO_APIC_irq(unsigned int irq)
{
- __modify_IO_APIC_irq(irq, 0x00010000, 0x00008000);
+ __modify_IO_APIC_irq(irq, IO_APIC_REDIR_MASKED,
+ IO_APIC_REDIR_LEVEL_TRIGGER);
}
/* mask = 0, trigger = 1 */
-static void __unmask_and_level_IO_APIC_irq (unsigned int irq)
+static void __unmask_and_level_IO_APIC_irq(unsigned int irq)
{
- __modify_IO_APIC_irq(irq, 0x00008000, 0x00010000);
+ __modify_IO_APIC_irq(irq, IO_APIC_REDIR_LEVEL_TRIGGER,
+ IO_APIC_REDIR_MASKED);
}
-static void mask_IO_APIC_irq (unsigned int irq)
+static void mask_IO_APIC_irq(unsigned int irq)
{
unsigned long flags;
spin_unlock_irqrestore(&ioapic_lock, flags);
}
-static void unmask_IO_APIC_irq (unsigned int irq)
+static void unmask_IO_APIC_irq(unsigned int irq)
{
unsigned long flags;
static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
{
struct IO_APIC_route_entry entry;
-
+
/* Check delivery_mode to be sure we're not clearing an SMI pin */
entry = ioapic_read_entry(apic, pin);
if (entry.delivery_mode == dest_SMI)
ioapic_mask_entry(apic, pin);
}
-static void clear_IO_APIC (void)
+static void clear_IO_APIC(void)
{
int apic, pin;
struct irq_pin_list *entry = irq_2_pin + irq;
unsigned int apicid_value;
cpumask_t tmp;
-
+
cpus_and(tmp, cpumask, cpu_online_map);
if (cpus_empty(tmp))
tmp = TARGET_CPUS;
# include <linux/kernel_stat.h> /* kstat */
# include <linux/slab.h> /* kmalloc() */
# include <linux/timer.h>
-
+
#define IRQBALANCE_CHECK_ARCH -999
#define MAX_BALANCED_IRQ_INTERVAL (5*HZ)
#define MIN_BALANCED_IRQ_INTERVAL (HZ/2)
static long balanced_irq_interval __read_mostly = MAX_BALANCED_IRQ_INTERVAL;
static struct irq_cpu_info {
- unsigned long * last_irq;
- unsigned long * irq_delta;
+ unsigned long *last_irq;
+ unsigned long *irq_delta;
unsigned long irq;
} irq_cpu_data[NR_CPUS];
#define CPU_IRQ(cpu) (irq_cpu_data[cpu].irq)
-#define LAST_CPU_IRQ(cpu,irq) (irq_cpu_data[cpu].last_irq[irq])
-#define IRQ_DELTA(cpu,irq) (irq_cpu_data[cpu].irq_delta[irq])
+#define LAST_CPU_IRQ(cpu, irq) (irq_cpu_data[cpu].last_irq[irq])
+#define IRQ_DELTA(cpu, irq) (irq_cpu_data[cpu].irq_delta[irq])
#define IDLE_ENOUGH(cpu,now) \
(idle_cpu(cpu) && ((now) - per_cpu(irq_stat, (cpu)).idle_timestamp > 1))
if (cpu == -1)
cpu = NR_CPUS-1;
}
- } while (!cpu_online(cpu) || !IRQ_ALLOWED(cpu,allowed_mask) ||
- (search_idle && !IDLE_ENOUGH(cpu,now)));
+ } while (!cpu_online(cpu) || !IRQ_ALLOWED(cpu, allowed_mask) ||
+ (search_idle && !IDLE_ENOUGH(cpu, now)));
return cpu;
}
unsigned long now = jiffies;
cpumask_t allowed_mask;
unsigned int new_cpu;
-
+
if (irqbalance_disabled)
- return;
+ return;
cpus_and(allowed_mask, cpu_online_map, balance_irq_affinity[irq]);
new_cpu = move(cpu, allowed_mask, now, 1);
- if (cpu != new_cpu) {
+ if (cpu != new_cpu)
set_pending_irq(irq, cpumask_of_cpu(new_cpu));
- }
}
static inline void rotate_irqs_among_cpus(unsigned long useful_load_threshold)
if (!irq_desc[j].action)
continue;
/* Is it a significant load ? */
- if (IRQ_DELTA(CPU_TO_PACKAGEINDEX(i),j) <
+ if (IRQ_DELTA(CPU_TO_PACKAGEINDEX(i), j) <
useful_load_threshold)
continue;
balance_irq(i, j);
}
}
balanced_irq_interval = max((long)MIN_BALANCED_IRQ_INTERVAL,
- balanced_irq_interval - BALANCED_IRQ_LESS_DELTA);
+ balanced_irq_interval - BALANCED_IRQ_LESS_DELTA);
return;
}
/* Is this an active IRQ or balancing disabled ? */
if (!irq_desc[j].action || irq_balancing_disabled(j))
continue;
- if ( package_index == i )
- IRQ_DELTA(package_index,j) = 0;
+ if (package_index == i)
+ IRQ_DELTA(package_index, j) = 0;
/* Determine the total count per processor per IRQ */
value_now = (unsigned long) kstat_cpu(i).irqs[j];
/* Determine the activity per processor per IRQ */
- delta = value_now - LAST_CPU_IRQ(i,j);
+ delta = value_now - LAST_CPU_IRQ(i, j);
/* Update last_cpu_irq[][] for the next time */
- LAST_CPU_IRQ(i,j) = value_now;
+ LAST_CPU_IRQ(i, j) = value_now;
/* Ignore IRQs whose rate is less than the clock */
if (delta < useful_load_threshold)
continue;
/* update the load for the processor or package total */
- IRQ_DELTA(package_index,j) += delta;
+ IRQ_DELTA(package_index, j) += delta;
/* Keep track of the higher numbered sibling as well */
if (i != package_index)
max_cpu_irq = ULONG_MAX;
tryanothercpu:
- /* Look for heaviest loaded processor.
+ /*
+ * Look for heaviest loaded processor.
* We may come back to get the next heaviest loaded processor.
* Skip processors with trivial loads.
*/
for_each_online_cpu(i) {
if (i != CPU_TO_PACKAGEINDEX(i))
continue;
- if (max_cpu_irq <= CPU_IRQ(i))
+ if (max_cpu_irq <= CPU_IRQ(i))
continue;
if (tmp_cpu_irq < CPU_IRQ(i)) {
tmp_cpu_irq = CPU_IRQ(i);
}
if (tmp_loaded == -1) {
- /* In the case of small number of heavy interrupt sources,
- * loading some of the cpus too much. We use Ingo's original
+ /*
+ * In the case of small number of heavy interrupt sources,
+ * loading some of the cpus too much. We use Ingo's original
* approach to rotate them around.
*/
if (!first_attempt && imbalance >= useful_load_threshold) {
}
goto not_worth_the_effort;
}
-
+
first_attempt = 0; /* heaviest search */
max_cpu_irq = tmp_cpu_irq; /* load */
max_loaded = tmp_loaded; /* processor */
imbalance = (max_cpu_irq - min_cpu_irq) / 2;
-
- /* if imbalance is less than approx 10% of max load, then
+
+ /*
+ * if imbalance is less than approx 10% of max load, then
* observe diminishing returns action. - quit
*/
if (imbalance < (max_cpu_irq >> 3))
/* Is this an active IRQ? */
if (!irq_desc[j].action)
continue;
- if (imbalance <= IRQ_DELTA(max_loaded,j))
+ if (imbalance <= IRQ_DELTA(max_loaded, j))
continue;
/* Try to find the IRQ that is closest to the imbalance
* without going over.
*/
- if (move_this_load < IRQ_DELTA(max_loaded,j)) {
- move_this_load = IRQ_DELTA(max_loaded,j);
+ if (move_this_load < IRQ_DELTA(max_loaded, j)) {
+ move_this_load = IRQ_DELTA(max_loaded, j);
selected_irq = j;
}
}
- if (selected_irq == -1) {
+ if (selected_irq == -1)
goto tryanothercpu;
- }
imbalance = move_this_load;
-
+
/* For physical_balance case, we accumulated both load
* values in the one of the siblings cpu_irq[],
* to use the same code for physical and logical processors
- * as much as possible.
+ * as much as possible.
*
* NOTE: the cpu_irq[] array holds the sum of the load for
* sibling A and sibling B in the slot for the lowest numbered
/* mark for change destination */
set_pending_irq(selected_irq, cpumask_of_cpu(min_loaded));
- /* Since we made a change, come back sooner to
+ /* Since we made a change, come back sooner to
* check for more variation.
*/
balanced_irq_interval = max((long)MIN_BALANCED_IRQ_INTERVAL,
- balanced_irq_interval - BALANCED_IRQ_LESS_DELTA);
+ balanced_irq_interval - BALANCED_IRQ_LESS_DELTA);
return;
}
goto tryanotherirq;
* upward
*/
balanced_irq_interval = min((long)MAX_BALANCED_IRQ_INTERVAL,
- balanced_irq_interval + BALANCED_IRQ_MORE_DELTA);
+ balanced_irq_interval + BALANCED_IRQ_MORE_DELTA);
return;
}
cpumask_t tmp;
cpus_shift_right(tmp, cpu_online_map, 2);
- c = &boot_cpu_data;
+ c = &boot_cpu_data;
/* When not overwritten by the command line ask subarchitecture. */
if (irqbalance_disabled == IRQBALANCE_CHECK_ARCH)
irqbalance_disabled = NO_BALANCE_IRQ;
if (irqbalance_disabled)
return 0;
-
+
/* disable irqbalance completely if there is only one processor online */
if (num_online_cpus() < 2) {
irqbalance_disabled = 1;
physical_balance = 1;
for_each_online_cpu(i) {
- irq_cpu_data[i].irq_delta = kmalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
- irq_cpu_data[i].last_irq = kmalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
+ irq_cpu_data[i].irq_delta = kzalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
+ irq_cpu_data[i].last_irq = kzalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
if (irq_cpu_data[i].irq_delta == NULL || irq_cpu_data[i].last_irq == NULL) {
printk(KERN_ERR "balanced_irq_init: out of memory");
goto failed;
}
- memset(irq_cpu_data[i].irq_delta,0,sizeof(unsigned long) * NR_IRQS);
- memset(irq_cpu_data[i].last_irq,0,sizeof(unsigned long) * NR_IRQS);
}
-
+
printk(KERN_INFO "Starting balanced_irq\n");
if (!IS_ERR(kthread_run(balanced_irq, NULL, "kirqd")))
return 0;
}
if (i < mp_irq_entries) {
int apic;
- for(apic = 0; apic < nr_ioapics; apic++) {
+ for (apic = 0; apic < nr_ioapics; apic++) {
if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic)
return apic;
}
!mp_irqs[i].mpc_irqtype &&
(bus == lbus) &&
(slot == ((mp_irqs[i].mpc_srcbusirq >> 2) & 0x1f))) {
- int irq = pin_2_irq(i,apic,mp_irqs[i].mpc_dstirq);
+ int irq = pin_2_irq(i, apic, mp_irqs[i].mpc_dstirq);
if (!(apic || IO_APIC_IRQ(irq)))
continue;
EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
/*
- * This function currently is only a helper for the i386 smp boot process where
+ * 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
*/
/*
* Determine IRQ line polarity (high active or low active):
*/
- switch (mp_irqs[idx].mpc_irqflag & 3)
+ switch (mp_irqs[idx].mpc_irqflag & 3) {
+ case 0: /* conforms, ie. bus-type dependent polarity */
{
- case 0: /* conforms, ie. bus-type dependent polarity */
- {
- polarity = test_bit(bus, mp_bus_not_pci)?
- default_ISA_polarity(idx):
- default_PCI_polarity(idx);
- break;
- }
- case 1: /* high active */
- {
- polarity = 0;
- break;
- }
- case 2: /* reserved */
- {
- printk(KERN_WARNING "broken BIOS!!\n");
- polarity = 1;
- break;
- }
- case 3: /* low active */
- {
- polarity = 1;
- break;
- }
- default: /* invalid */
- {
- printk(KERN_WARNING "broken BIOS!!\n");
- polarity = 1;
- break;
- }
+ polarity = test_bit(bus, mp_bus_not_pci)?
+ default_ISA_polarity(idx):
+ default_PCI_polarity(idx);
+ break;
+ }
+ case 1: /* high active */
+ {
+ polarity = 0;
+ break;
+ }
+ case 2: /* reserved */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ polarity = 1;
+ break;
+ }
+ case 3: /* low active */
+ {
+ polarity = 1;
+ break;
+ }
+ default: /* invalid */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ polarity = 1;
+ break;
+ }
}
return polarity;
}
/*
* Determine IRQ trigger mode (edge or level sensitive):
*/
- switch ((mp_irqs[idx].mpc_irqflag>>2) & 3)
+ switch ((mp_irqs[idx].mpc_irqflag>>2) & 3) {
+ case 0: /* conforms, ie. bus-type dependent */
{
- case 0: /* conforms, ie. bus-type dependent */
- {
- trigger = test_bit(bus, mp_bus_not_pci)?
- default_ISA_trigger(idx):
- default_PCI_trigger(idx);
+ trigger = test_bit(bus, mp_bus_not_pci)?
+ default_ISA_trigger(idx):
+ default_PCI_trigger(idx);
#if defined(CONFIG_EISA) || defined(CONFIG_MCA)
- switch (mp_bus_id_to_type[bus])
- {
- case MP_BUS_ISA: /* ISA pin */
- {
- /* set before the switch */
- break;
- }
- case MP_BUS_EISA: /* EISA pin */
- {
- trigger = default_EISA_trigger(idx);
- break;
- }
- case MP_BUS_PCI: /* PCI pin */
- {
- /* set before the switch */
- break;
- }
- case MP_BUS_MCA: /* MCA pin */
- {
- trigger = default_MCA_trigger(idx);
- break;
- }
- default:
- {
- printk(KERN_WARNING "broken BIOS!!\n");
- trigger = 1;
- break;
- }
- }
-#endif
+ switch (mp_bus_id_to_type[bus]) {
+ case MP_BUS_ISA: /* ISA pin */
+ {
+ /* set before the switch */
break;
}
- case 1: /* edge */
+ case MP_BUS_EISA: /* EISA pin */
{
- trigger = 0;
+ trigger = default_EISA_trigger(idx);
break;
}
- case 2: /* reserved */
+ case MP_BUS_PCI: /* PCI pin */
{
- printk(KERN_WARNING "broken BIOS!!\n");
- trigger = 1;
+ /* set before the switch */
break;
}
- case 3: /* level */
+ case MP_BUS_MCA: /* MCA pin */
{
- trigger = 1;
+ trigger = default_MCA_trigger(idx);
break;
}
- default: /* invalid */
+ default:
{
printk(KERN_WARNING "broken BIOS!!\n");
- trigger = 0;
+ trigger = 1;
break;
}
}
+#endif
+ break;
+ }
+ case 1: /* edge */
+ {
+ trigger = 0;
+ break;
+ }
+ case 2: /* reserved */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ trigger = 1;
+ break;
+ }
+ case 3: /* level */
+ {
+ trigger = 1;
+ break;
+ }
+ default: /* invalid */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ trigger = 0;
+ break;
+ }
+ }
return trigger;
}
for (apic = 0; apic < nr_ioapics; apic++) {
for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
- idx = find_irq_entry(apic,pin,mp_INT);
- if ((idx != -1) && (irq == pin_2_irq(idx,apic,pin)))
+ idx = find_irq_entry(apic, pin, mp_INT);
+ if ((idx != -1) && (irq == pin_2_irq(idx, apic, pin)))
return irq_trigger(idx);
}
}
static int __assign_irq_vector(int irq)
{
- static int current_vector = FIRST_DEVICE_VECTOR, current_offset = 0;
+ static int current_vector = FIRST_DEVICE_VECTOR, current_offset;
int vector, offset;
BUG_ON((unsigned)irq >= NR_IRQ_VECTORS);
offset = current_offset;
next:
vector += 8;
- if (vector >= FIRST_SYSTEM_VECTOR) {
+ if (vector >= first_system_vector) {
offset = (offset + 1) % 8;
vector = FIRST_DEVICE_VECTOR + offset;
}
/*
* add it to the IO-APIC irq-routing table:
*/
- memset(&entry,0,sizeof(entry));
+ memset(&entry, 0, sizeof(entry));
entry.delivery_mode = INT_DELIVERY_MODE;
entry.dest_mode = INT_DEST_MODE;
entry.mask = 0; /* enable IRQ */
- entry.dest.logical.logical_dest =
+ entry.dest.logical.logical_dest =
cpu_mask_to_apicid(TARGET_CPUS);
- idx = find_irq_entry(apic,pin,mp_INT);
+ idx = find_irq_entry(apic, pin, mp_INT);
if (idx == -1) {
if (first_notcon) {
apic_printk(APIC_VERBOSE, KERN_DEBUG
vector = assign_irq_vector(irq);
entry.vector = vector;
ioapic_register_intr(irq, vector, IOAPIC_AUTO);
-
+
if (!apic && (irq < 16))
disable_8259A_irq(irq);
}
}
/*
- * Set up the 8259A-master output pin:
+ * Set up the timer pin, possibly with the 8259A-master behind.
*/
-static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, int vector)
+static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
+ int vector)
{
struct IO_APIC_route_entry entry;
- memset(&entry,0,sizeof(entry));
-
- disable_8259A_irq(0);
-
- /* mask LVT0 */
- apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
+ memset(&entry, 0, sizeof(entry));
/*
* 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.mask = 1; /* mask IRQ now */
entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS);
entry.delivery_mode = INT_DELIVERY_MODE;
entry.polarity = 0;
/*
* The timer IRQ doesn't have to know that behind the
- * scene we have a 8259A-master in AEOI mode ...
+ * scene we may have a 8259A-master in AEOI mode ...
*/
- irq_desc[0].chip = &ioapic_chip;
- set_irq_handler(0, handle_edge_irq);
+ ioapic_register_intr(0, vector, IOAPIC_EDGE);
/*
* Add it to the IO-APIC irq-routing table:
*/
ioapic_write_entry(apic, pin, entry);
-
- enable_8259A_irq(0);
}
void __init print_IO_APIC(void)
if (apic_verbosity == APIC_QUIET)
return;
- printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
+ 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]);
#if 0
-static void print_APIC_bitfield (int base)
+static void print_APIC_bitfield(int base)
{
unsigned int v;
int i, j;
}
}
-void /*__init*/ print_local_APIC(void * dummy)
+void /*__init*/ print_local_APIC(void *dummy)
{
unsigned int v, ver, maxlvt;
printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
smp_processor_id(), hard_smp_processor_id());
+ v = apic_read(APIC_ID);
printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v,
GET_APIC_ID(read_apic_id()));
v = apic_read(APIC_LVR);
printk("\n");
}
-void print_all_local_APICs (void)
+void print_all_local_APICs(void)
{
on_each_cpu(print_local_APIC, NULL, 1, 1);
}
v = inb(0xa0) << 8 | inb(0x20);
printk(KERN_DEBUG "... PIC IRR: %04x\n", v);
- outb(0x0b,0xa0);
- outb(0x0b,0x20);
+ outb(0x0b, 0xa0);
+ outb(0x0b, 0x20);
v = inb(0xa0) << 8 | inb(0x20);
- outb(0x0a,0xa0);
- outb(0x0a,0x20);
+ outb(0x0a, 0xa0);
+ outb(0x0a, 0x20);
spin_unlock_irqrestore(&i8259A_lock, flags);
spin_unlock_irqrestore(&ioapic_lock, flags);
nr_ioapic_registers[apic] = reg_01.bits.entries+1;
}
- for(apic = 0; apic < nr_ioapics; apic++) {
+ for (apic = 0; apic < nr_ioapics; apic++) {
int pin;
/* See if any of the pins is in ExtINT mode */
for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
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()) {
/*
* 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);
ack_APIC_irq();
}
-static void mask_lapic_irq (unsigned int irq)
+static void mask_lapic_irq(unsigned int irq)
{
unsigned long v;
apic_write_around(APIC_LVT0, v | APIC_LVT_MASKED);
}
-static void unmask_lapic_irq (unsigned int irq)
+static void unmask_lapic_irq(unsigned int irq)
{
unsigned long v;
}
static struct irq_chip lapic_chip __read_mostly = {
- .name = "local-APIC-edge",
+ .name = "local-APIC",
.mask = mask_lapic_irq,
.unmask = unmask_lapic_irq,
.eoi = ack_apic,
static void __init setup_nmi(void)
{
/*
- * Dirty trick to enable the NMI watchdog ...
+ * 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 ...");
enable_NMI_through_LVT0();
static inline void __init check_timer(void)
{
int apic1, pin1, apic2, pin2;
+ int no_pin1 = 0;
int vector;
+ unsigned int ver;
unsigned long flags;
local_irq_save(flags);
+ ver = apic_read(APIC_LVR);
+ ver = GET_APIC_VERSION(ver);
+
/*
* get/set the timer IRQ vector:
*/
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.
+ * As IRQ0 is to be enabled in the 8259A, the virtual
+ * wire has to be disabled in the local APIC. Also
+ * timer interrupts need to be acknowledged manually in
+ * the 8259A for the i82489DX when using the NMI
+ * watchdog as that APIC treats NMIs as level-triggered.
+ * The AEOI mode will finish them in the 8259A
+ * automatically.
*/
apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
init_8259A(1);
- timer_ack = 1;
- if (timer_over_8254 > 0)
- enable_8259A_irq(0);
+ timer_ack = (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver));
pin1 = find_isa_irq_pin(0, mp_INT);
apic1 = find_isa_irq_apic(0, mp_INT);
printk(KERN_INFO "..TIMER: vector=0x%02X apic1=%d pin1=%d apic2=%d pin2=%d\n",
vector, apic1, pin1, apic2, pin2);
+ /*
+ * Some BIOS writers are clueless and report the ExtINTA
+ * I/O APIC input from the cascaded 8259A as the timer
+ * interrupt input. So just in case, if only one pin
+ * was found above, try it both directly and through the
+ * 8259A.
+ */
+ if (pin1 == -1) {
+ pin1 = pin2;
+ apic1 = apic2;
+ no_pin1 = 1;
+ } else if (pin2 == -1) {
+ pin2 = pin1;
+ apic2 = apic1;
+ }
+
if (pin1 != -1) {
/*
* Ok, does IRQ0 through the IOAPIC work?
*/
+ if (no_pin1) {
+ add_pin_to_irq(0, apic1, pin1);
+ setup_timer_IRQ0_pin(apic1, pin1, vector);
+ }
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);
}
goto out;
}
clear_IO_APIC_pin(apic1, pin1);
- printk(KERN_ERR "..MP-BIOS bug: 8254 timer not connected to "
- "IO-APIC\n");
- }
+ if (!no_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(KERN_INFO "...trying to set up timer (IRQ0) "
+ "through the 8259A ... ");
printk("\n..... (found pin %d) ...", pin2);
/*
* legacy devices should be connected to IO APIC #0
*/
- setup_ExtINT_IRQ0_pin(apic2, pin2, vector);
+ replace_pin_at_irq(0, apic1, pin1, apic2, pin2);
+ setup_timer_IRQ0_pin(apic2, pin2, vector);
+ unmask_IO_APIC_irq(0);
+ enable_8259A_irq(0);
if (timer_irq_works()) {
printk("works.\n");
- if (pin1 != -1)
- replace_pin_at_irq(0, apic1, pin1, apic2, pin2);
- else
- add_pin_to_irq(0, apic2, pin2);
+ timer_through_8259 = 1;
if (nmi_watchdog == NMI_IO_APIC) {
+ disable_8259A_irq(0);
setup_nmi();
+ enable_8259A_irq(0);
}
goto out;
}
/*
* Cleanup, just in case ...
*/
+ disable_8259A_irq(0);
clear_IO_APIC_pin(apic2, pin2);
+ printk(" failed.\n");
}
- 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;
+ nmi_watchdog = NMI_NONE;
}
+ timer_ack = 0;
printk(KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
- disable_8259A_irq(0);
set_irq_chip_and_handler_name(0, &lapic_chip, handle_fasteoi_irq,
"fasteoi");
apic_write_around(APIC_LVT0, APIC_DM_FIXED | vector); /* Fixed mode */
printk(" works.\n");
goto out;
}
+ disable_8259A_irq(0);
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);
int i;
/* Reserve all the system vectors. */
- for (i = FIRST_SYSTEM_VECTOR; i < NR_VECTORS; i++)
+ for (i = first_system_vector; i < NR_VECTORS; i++)
set_bit(i, used_vectors);
enable_IO_APIC();
print_IO_APIC();
}
-static int __init setup_disable_8254_timer(char *s)
-{
- timer_over_8254 = -1;
- return 1;
-}
-static int __init setup_enable_8254_timer(char *s)
-{
- timer_over_8254 = 2;
- return 1;
-}
-
-__setup("disable_8254_timer", setup_disable_8254_timer);
-__setup("enable_8254_timer", setup_enable_8254_timer);
-
/*
* Called after all the initialization is done. If we didnt find any
* APIC bugs then we can allow the modify fast path
*/
-
+
static int __init io_apic_bug_finalize(void)
{
- if(sis_apic_bug == -1)
+ if (sis_apic_bug == -1)
sis_apic_bug = 0;
return 0;
}
struct sys_device dev;
struct IO_APIC_route_entry entry[0];
};
-static struct sysfs_ioapic_data * mp_ioapic_data[MAX_IO_APICS];
+static struct sysfs_ioapic_data *mp_ioapic_data[MAX_IO_APICS];
static int ioapic_suspend(struct sys_device *dev, pm_message_t state)
{
struct IO_APIC_route_entry *entry;
struct sysfs_ioapic_data *data;
int i;
-
+
data = container_of(dev, struct sysfs_ioapic_data, dev);
entry = data->entry;
- for (i = 0; i < nr_ioapic_registers[dev->id]; i ++)
+ for (i = 0; i < nr_ioapic_registers[dev->id]; i++)
entry[i] = ioapic_read_entry(dev->id, i);
return 0;
unsigned long flags;
union IO_APIC_reg_00 reg_00;
int i;
-
+
data = container_of(dev, struct sysfs_ioapic_data, dev);
entry = data->entry;
io_apic_write(dev->id, 0, reg_00.raw);
}
spin_unlock_irqrestore(&ioapic_lock, flags);
- for (i = 0; i < nr_ioapic_registers[dev->id]; i ++)
+ for (i = 0; i < nr_ioapic_registers[dev->id]; i++)
ioapic_write_entry(dev->id, i, entry[i]);
return 0;
static int __init ioapic_init_sysfs(void)
{
- struct sys_device * dev;
+ struct sys_device *dev;
int i, size, error = 0;
error = sysdev_class_register(&ioapic_sysdev_class);
if (error)
return error;
- for (i = 0; i < nr_ioapics; i++ ) {
- size = sizeof(struct sys_device) + nr_ioapic_registers[i]
+ for (i = 0; i < nr_ioapics; i++) {
+ size = sizeof(struct sys_device) + nr_ioapic_registers[i]
* sizeof(struct IO_APIC_route_entry);
- mp_ioapic_data[i] = kmalloc(size, GFP_KERNEL);
+ mp_ioapic_data[i] = kzalloc(size, GFP_KERNEL);
if (!mp_ioapic_data[i]) {
printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
continue;
}
- memset(mp_ioapic_data[i], 0, size);
dev = &mp_ioapic_data[i]->dev;
- dev->id = i;
+ dev->id = i;
dev->cls = &ioapic_sysdev_class;
error = sysdev_register(dev);
if (error) {
msg->address_lo =
MSI_ADDR_BASE_LO |
((INT_DEST_MODE == 0) ?
- MSI_ADDR_DEST_MODE_PHYSICAL:
+MSI_ADDR_DEST_MODE_PHYSICAL:
MSI_ADDR_DEST_MODE_LOGICAL) |
((INT_DELIVERY_MODE != dest_LowestPrio) ?
MSI_ADDR_REDIRECTION_CPU:
MSI_DATA_TRIGGER_EDGE |
MSI_DATA_LEVEL_ASSERT |
((INT_DELIVERY_MODE != dest_LowestPrio) ?
- MSI_DATA_DELIVERY_FIXED:
+MSI_DATA_DELIVERY_FIXED:
MSI_DATA_DELIVERY_LOWPRI) |
MSI_DATA_VECTOR(vector);
}
#endif /* CONFIG_HT_IRQ */
/* --------------------------------------------------------------------------
- ACPI-based IOAPIC Configuration
+ ACPI-based IOAPIC Configuration
-------------------------------------------------------------------------- */
#ifdef CONFIG_ACPI
-int __init io_apic_get_unique_id (int ioapic, int apic_id)
+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;
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
+ * 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.
*/
}
/*
- * Every APIC in a system must have a unique ID or we get lots of nice
+ * 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)) {
"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);
}
-int __init io_apic_get_version (int ioapic)
+int __init io_apic_get_version(int ioapic)
{
union IO_APIC_reg_01 reg_01;
unsigned long flags;
}
-int __init io_apic_get_redir_entries (int ioapic)
+int __init io_apic_get_redir_entries(int ioapic)
{
union IO_APIC_reg_01 reg_01;
unsigned long flags;
}
-int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int active_high_low)
+int io_apic_set_pci_routing(int ioapic, int pin, int irq, int edge_level, int active_high_low)
{
struct IO_APIC_route_entry entry;
* corresponding device driver registers for this IRQ.
*/
- memset(&entry,0,sizeof(entry));
+ memset(&entry, 0, sizeof(entry));
entry.delivery_mode = INT_DELIVERY_MODE;
entry.dest_mode = INT_DEST_MODE;
};
/* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
-struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = {
+static struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = {
[0] = { .domain = CPU_MASK_ALL, .vector = IRQ0_VECTOR, },
[1] = { .domain = CPU_MASK_ALL, .vector = IRQ1_VECTOR, },
[2] = { .domain = CPU_MASK_ALL, .vector = IRQ2_VECTOR, },
static int assign_irq_vector(int irq, cpumask_t mask);
+ int first_system_vector = 0xfe;
+
+ char system_vectors[NR_VECTORS] = { [0 ... NR_VECTORS-1] = SYS_VECTOR_FREE};
+
#define __apicdebuginit __init
int sis_apic_bug; /* not actually supported, dummy for compile */
static int disable_timer_pin_1 __initdata;
-int timer_over_8254 __initdata = 1;
+int timer_through_8259 __initdata;
/* Where if anywhere is the i8259 connect in external int mode */
static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
break;
reg = io_apic_read(entry->apic, 0x10 + pin*2);
/* Is the remote IRR bit set? */
- if ((reg >> 14) & 1) {
+ if (reg & IO_APIC_REDIR_REMOTE_IRR) {
spin_unlock_irqrestore(&ioapic_lock, flags);
return true;
}
break;
io_apic_write(apic, 0x11 + pin*2, dest);
reg = io_apic_read(apic, 0x10 + pin*2);
- reg &= ~0x000000ff;
+ reg &= ~IO_APIC_REDIR_VECTOR_MASK;
reg |= vector;
io_apic_modify(apic, reg);
if (!entry->next)
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;
+ }
+}
+
#define DO_ACTION(name,R,ACTION, FINAL) \
\
static void name##_IO_APIC_irq (unsigned int irq) \
__DO_ACTION(R, ACTION, FINAL)
-DO_ACTION( __mask, 0, |= 0x00010000, io_apic_sync(entry->apic) )
- /* mask = 1 */
-DO_ACTION( __unmask, 0, &= 0xfffeffff, )
- /* mask = 0 */
+/* mask = 1 */
+DO_ACTION(__mask, 0, |= IO_APIC_REDIR_MASKED, io_apic_sync(entry->apic))
+
+/* mask = 0 */
+DO_ACTION(__unmask, 0, &= ~IO_APIC_REDIR_MASKED, )
static void mask_IO_APIC_irq (unsigned int irq)
{
}
__setup("disable_timer_pin_1", disable_timer_pin_setup);
-static int __init setup_disable_8254_timer(char *s)
-{
- timer_over_8254 = -1;
- return 1;
-}
-static int __init setup_enable_8254_timer(char *s)
-{
- timer_over_8254 = 2;
- return 1;
-}
-
-__setup("disable_8254_timer", setup_disable_8254_timer);
-__setup("enable_8254_timer", setup_enable_8254_timer);
-
/*
* Find the IRQ entry number of a certain pin.
offset = current_offset;
next:
vector += 8;
- if (vector >= FIRST_SYSTEM_VECTOR) {
+ if (vector >= first_system_vector) {
/* If we run out of vectors on large boxen, must share them. */
offset = (offset + 1) % 8;
vector = FIRST_DEVICE_VECTOR + offset;
}
/*
- * Set up the 8259A-master output pin as broadcast to all
- * CPUs.
+ * Set up the timer pin, possibly with the 8259A-master behind.
*/
-static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, int vector)
+static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
+ int vector)
{
struct IO_APIC_route_entry entry;
memset(&entry, 0, sizeof(entry));
- disable_8259A_irq(0);
-
- /* mask LVT0 */
- apic_write(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.mask = 1; /* mask IRQ now */
entry.dest = cpu_mask_to_apicid(TARGET_CPUS);
entry.delivery_mode = INT_DELIVERY_MODE;
entry.polarity = 0;
/*
* The timer IRQ doesn't have to know that behind the
- * scene we have a 8259A-master in AEOI mode ...
+ * scene we may have a 8259A-master in AEOI mode ...
*/
set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
* Add it to the IO-APIC irq-routing table:
*/
ioapic_write_entry(apic, pin, entry);
-
- enable_8259A_irq(0);
}
void __apicdebuginit print_IO_APIC(void)
printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
smp_processor_id(), hard_smp_processor_id());
+ v = apic_read(APIC_ID);
printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v, GET_APIC_ID(read_apic_id()));
v = apic_read(APIC_LVR);
printk(KERN_INFO "... APIC VERSION: %08x\n", v);
struct irq_cfg *cfg = irq_cfg + 0;
int apic1, pin1, apic2, pin2;
unsigned long flags;
+ int no_pin1 = 0;
local_irq_save(flags);
assign_irq_vector(0, TARGET_CPUS);
/*
- * 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.
+ * As IRQ0 is to be enabled in the 8259A, the virtual
+ * wire has to be disabled in the local APIC.
*/
apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
init_8259A(1);
- if (timer_over_8254 > 0)
- enable_8259A_irq(0);
pin1 = find_isa_irq_pin(0, mp_INT);
apic1 = find_isa_irq_apic(0, mp_INT);
apic_printk(APIC_VERBOSE,KERN_INFO "..TIMER: vector=0x%02X apic1=%d pin1=%d apic2=%d pin2=%d\n",
cfg->vector, apic1, pin1, apic2, pin2);
+ /*
+ * Some BIOS writers are clueless and report the ExtINTA
+ * I/O APIC input from the cascaded 8259A as the timer
+ * interrupt input. So just in case, if only one pin
+ * was found above, try it both directly and through the
+ * 8259A.
+ */
+ if (pin1 == -1) {
+ pin1 = pin2;
+ apic1 = apic2;
+ no_pin1 = 1;
+ } else if (pin2 == -1) {
+ pin2 = pin1;
+ apic2 = apic1;
+ }
+
+ replace_pin_at_irq(0, 0, 0, apic1, pin1);
+ apic1 = 0;
+ pin1 = 0;
+ setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
+
if (pin1 != -1) {
/*
* Ok, does IRQ0 through the IOAPIC work?
*/
+ if (no_pin1) {
+ add_pin_to_irq(0, apic1, pin1);
+ setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
+ }
unmask_IO_APIC_irq(0);
if (!no_timer_check && timer_irq_works()) {
nmi_watchdog_default();
if (nmi_watchdog == NMI_IO_APIC) {
- disable_8259A_irq(0);
setup_nmi();
enable_8259A_irq(0);
}
goto out;
}
clear_IO_APIC_pin(apic1, pin1);
- apic_printk(APIC_QUIET,KERN_ERR "..MP-BIOS bug: 8254 timer not "
- "connected to IO-APIC\n");
- }
+ if (!no_pin1)
+ apic_printk(APIC_QUIET,KERN_ERR "..MP-BIOS bug: "
+ "8254 timer not connected to IO-APIC\n");
- apic_printk(APIC_VERBOSE,KERN_INFO "...trying to set up timer (IRQ0) "
- "through the 8259A ... ");
- if (pin2 != -1) {
+ apic_printk(APIC_VERBOSE,KERN_INFO
+ "...trying to set up timer (IRQ0) "
+ "through the 8259A ... ");
apic_printk(APIC_VERBOSE,"\n..... (found apic %d pin %d) ...",
apic2, pin2);
/*
* legacy devices should be connected to IO APIC #0
*/
- setup_ExtINT_IRQ0_pin(apic2, pin2, cfg->vector);
+ replace_pin_at_irq(0, apic1, pin1, apic2, pin2);
+ setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
+ unmask_IO_APIC_irq(0);
+ enable_8259A_irq(0);
if (timer_irq_works()) {
apic_printk(APIC_VERBOSE," works.\n");
+ timer_through_8259 = 1;
nmi_watchdog_default();
if (nmi_watchdog == NMI_IO_APIC) {
+ disable_8259A_irq(0);
setup_nmi();
+ enable_8259A_irq(0);
}
goto out;
}
/*
* Cleanup, just in case ...
*/
+ disable_8259A_irq(0);
clear_IO_APIC_pin(apic2, pin2);
+ apic_printk(APIC_VERBOSE," failed.\n");
}
- apic_printk(APIC_VERBOSE," 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;
+ nmi_watchdog = NMI_NONE;
}
apic_printk(APIC_VERBOSE, KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
- disable_8259A_irq(0);
irq_desc[0].chip = &lapic_irq_type;
apic_write(APIC_LVT0, APIC_DM_FIXED | cfg->vector); /* Fixed mode */
enable_8259A_irq(0);
apic_printk(APIC_VERBOSE," works.\n");
goto out;
}
+ disable_8259A_irq(0);
apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | cfg->vector);
apic_printk(APIC_VERBOSE," failed.\n");
#endif
}
+ #ifdef CONFIG_DEBUG_STACKOVERFLOW
+ /* Debugging check for stack overflow: is there less than 1KB free? */
+ static int check_stack_overflow(void)
+ {
+ long sp;
+
+ __asm__ __volatile__("andl %%esp,%0" :
+ "=r" (sp) : "0" (THREAD_SIZE - 1));
+
+ return sp < (sizeof(struct thread_info) + STACK_WARN);
+ }
+
+ static void print_stack_overflow(void)
+ {
+ printk(KERN_WARNING "low stack detected by irq handler\n");
+ dump_stack();
+ }
+
+ #else
+ static inline int check_stack_overflow(void) { return 0; }
+ static inline void print_stack_overflow(void) { }
+ #endif
+
#ifdef CONFIG_4KSTACKS
/*
* per-CPU IRQ handling contexts (thread information and stack)
static union irq_ctx *hardirq_ctx[NR_CPUS] __read_mostly;
static union irq_ctx *softirq_ctx[NR_CPUS] __read_mostly;
- #endif
- /*
- * do_IRQ handles all normal device IRQ's (the special
- * SMP cross-CPU interrupts have their own specific
- * handlers).
- */
- unsigned int do_IRQ(struct pt_regs *regs)
- {
- struct pt_regs *old_regs;
- /* high bit used in ret_from_ code */
- int irq = ~regs->orig_ax;
- struct irq_desc *desc = irq_desc + irq;
- #ifdef CONFIG_4KSTACKS
- union irq_ctx *curctx, *irqctx;
- u32 *isp;
- #endif
+ static char softirq_stack[NR_CPUS * THREAD_SIZE]
+ __attribute__((__section__(".bss.page_aligned")));
- if (unlikely((unsigned)irq >= NR_IRQS)) {
- printk(KERN_EMERG "%s: cannot handle IRQ %d\n",
- __func__, irq);
- BUG();
- }
+ static char hardirq_stack[NR_CPUS * THREAD_SIZE]
+ __attribute__((__section__(".bss.page_aligned")));
- old_regs = set_irq_regs(regs);
- irq_enter();
- #ifdef CONFIG_DEBUG_STACKOVERFLOW
- /* Debugging check for stack overflow: is there less than 1KB free? */
- {
- long sp;
-
- __asm__ __volatile__("andl %%esp,%0" :
- "=r" (sp) : "0" (THREAD_SIZE - 1));
- if (unlikely(sp < (sizeof(struct thread_info) + STACK_WARN))) {
- printk("do_IRQ: stack overflow: %ld\n",
- sp - sizeof(struct thread_info));
- dump_stack();
- }
- }
- #endif
+ static void call_on_stack(void *func, void *stack)
+ {
+ asm volatile("xchgl %%ebx,%%esp \n"
+ "call *%%edi \n"
+ "movl %%ebx,%%esp \n"
+ : "=b" (stack)
+ : "0" (stack),
+ "D"(func)
+ : "memory", "cc", "edx", "ecx", "eax");
+ }
- #ifdef CONFIG_4KSTACKS
+ static inline int
+ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
+ {
+ union irq_ctx *curctx, *irqctx;
+ u32 *isp, arg1, arg2;
curctx = (union irq_ctx *) current_thread_info();
irqctx = hardirq_ctx[smp_processor_id()];
* handler) we can't do that and just have to keep using the
* current stack (which is the irq stack already after all)
*/
- if (curctx != irqctx) {
- int arg1, arg2, bx;
-
- /* build the stack frame on the IRQ stack */
- isp = (u32*) ((char*)irqctx + sizeof(*irqctx));
- irqctx->tinfo.task = curctx->tinfo.task;
- irqctx->tinfo.previous_esp = current_stack_pointer;
+ if (unlikely(curctx == irqctx))
+ return 0;
- /*
- * Copy the softirq bits in preempt_count so that the
- * softirq checks work in the hardirq context.
- */
- irqctx->tinfo.preempt_count =
- (irqctx->tinfo.preempt_count & ~SOFTIRQ_MASK) |
- (curctx->tinfo.preempt_count & SOFTIRQ_MASK);
-
- asm volatile(
- " xchgl %%ebx,%%esp \n"
- " call *%%edi \n"
- " movl %%ebx,%%esp \n"
- : "=a" (arg1), "=d" (arg2), "=b" (bx)
- : "0" (irq), "1" (desc), "2" (isp),
- "D" (desc->handle_irq)
- : "memory", "cc", "ecx"
- );
- } else
- #endif
- desc->handle_irq(irq, desc);
+ /* build the stack frame on the IRQ stack */
+ isp = (u32 *) ((char*)irqctx + sizeof(*irqctx));
+ irqctx->tinfo.task = curctx->tinfo.task;
+ irqctx->tinfo.previous_esp = current_stack_pointer;
- irq_exit();
- set_irq_regs(old_regs);
+ /*
+ * Copy the softirq bits in preempt_count so that the
+ * softirq checks work in the hardirq context.
+ */
+ irqctx->tinfo.preempt_count =
+ (irqctx->tinfo.preempt_count & ~SOFTIRQ_MASK) |
+ (curctx->tinfo.preempt_count & SOFTIRQ_MASK);
+
+ if (unlikely(overflow))
+ call_on_stack(print_stack_overflow, isp);
+
+ asm volatile("xchgl %%ebx,%%esp \n"
+ "call *%%edi \n"
+ "movl %%ebx,%%esp \n"
+ : "=a" (arg1), "=d" (arg2), "=b" (isp)
+ : "0" (irq), "1" (desc), "2" (isp),
+ "D" (desc->handle_irq)
+ : "memory", "cc", "ecx");
return 1;
}
- #ifdef CONFIG_4KSTACKS
-
- static char softirq_stack[NR_CPUS * THREAD_SIZE]
- __attribute__((__section__(".bss.page_aligned")));
-
- static char hardirq_stack[NR_CPUS * THREAD_SIZE]
- __attribute__((__section__(".bss.page_aligned")));
-
/*
* allocate per-cpu stacks for hardirq and for softirq processing
*/
- void irq_ctx_init(int cpu)
+ void __cpuinit irq_ctx_init(int cpu)
{
union irq_ctx *irqctx;
return;
irqctx = (union irq_ctx*) &hardirq_stack[cpu*THREAD_SIZE];
- irqctx->tinfo.task = NULL;
- irqctx->tinfo.exec_domain = NULL;
- irqctx->tinfo.cpu = cpu;
- irqctx->tinfo.preempt_count = HARDIRQ_OFFSET;
- irqctx->tinfo.addr_limit = MAKE_MM_SEG(0);
+ irqctx->tinfo.task = NULL;
+ irqctx->tinfo.exec_domain = NULL;
+ irqctx->tinfo.cpu = cpu;
+ irqctx->tinfo.preempt_count = HARDIRQ_OFFSET;
+ irqctx->tinfo.addr_limit = MAKE_MM_SEG(0);
hardirq_ctx[cpu] = irqctx;
irqctx = (union irq_ctx*) &softirq_stack[cpu*THREAD_SIZE];
- irqctx->tinfo.task = NULL;
- irqctx->tinfo.exec_domain = NULL;
- irqctx->tinfo.cpu = cpu;
- irqctx->tinfo.preempt_count = 0;
- irqctx->tinfo.addr_limit = MAKE_MM_SEG(0);
+ irqctx->tinfo.task = NULL;
+ irqctx->tinfo.exec_domain = NULL;
+ irqctx->tinfo.cpu = cpu;
+ irqctx->tinfo.preempt_count = 0;
+ irqctx->tinfo.addr_limit = MAKE_MM_SEG(0);
softirq_ctx[cpu] = irqctx;
- printk("CPU %u irqstacks, hard=%p soft=%p\n",
- cpu,hardirq_ctx[cpu],softirq_ctx[cpu]);
+ printk(KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n",
+ cpu,hardirq_ctx[cpu],softirq_ctx[cpu]);
}
void irq_ctx_exit(int cpu)
/* build the stack frame on the softirq stack */
isp = (u32*) ((char*)irqctx + sizeof(*irqctx));
- asm volatile(
- " xchgl %%ebx,%%esp \n"
- " call __do_softirq \n"
- " movl %%ebx,%%esp \n"
- : "=b"(isp)
- : "0"(isp)
- : "memory", "cc", "edx", "ecx", "eax"
- );
+ call_on_stack(__do_softirq, isp);
/*
* Shouldnt happen, we returned above if in_interrupt():
- */
+ */
WARN_ON_ONCE(softirq_count());
}
local_irq_restore(flags);
}
+
+ #else
+ static inline int
+ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) { return 0; }
#endif
+ /*
+ * do_IRQ handles all normal device IRQ's (the special
+ * SMP cross-CPU interrupts have their own specific
+ * handlers).
+ */
+ unsigned int do_IRQ(struct pt_regs *regs)
+ {
+ struct pt_regs *old_regs;
+ /* high bit used in ret_from_ code */
+ int overflow, irq = ~regs->orig_ax;
+ struct irq_desc *desc = irq_desc + irq;
+
+ if (unlikely((unsigned)irq >= NR_IRQS)) {
+ printk(KERN_EMERG "%s: cannot handle IRQ %d\n",
+ __func__, irq);
+ BUG();
+ }
+
+ old_regs = set_irq_regs(regs);
+ irq_enter();
+
+ overflow = check_stack_overflow();
+
+ if (!execute_on_irq_stack(overflow, desc, irq)) {
+ if (unlikely(overflow))
+ print_stack_overflow();
+ desc->handle_irq(irq, desc);
+ }
+
+ irq_exit();
+ set_irq_regs(old_regs);
+ return 1;
+ }
+
/*
* Interrupt statistics:
*/
per_cpu(irq_stat,j).irq_tlb_count);
seq_printf(p, " TLB shootdowns\n");
#endif
+#ifdef CONFIG_X86_MCE
seq_printf(p, "TRM: ");
for_each_online_cpu(j)
seq_printf(p, "%10u ",
per_cpu(irq_stat,j).irq_thermal_count);
seq_printf(p, " Thermal event interrupts\n");
+#endif
+#ifdef CONFIG_X86_LOCAL_APIC
seq_printf(p, "SPU: ");
for_each_online_cpu(j)
seq_printf(p, "%10u ",
per_cpu(irq_stat,j).irq_spurious_count);
seq_printf(p, " Spurious interrupts\n");
+#endif
seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
#if defined(CONFIG_X86_IO_APIC)
seq_printf(p, "MIS: %10u\n", atomic_read(&irq_mis_count));
return 0;
}
+/*
+ * /proc/stat helpers
+ */
+u64 arch_irq_stat_cpu(unsigned int cpu)
+{
+ u64 sum = nmi_count(cpu);
+
+#ifdef CONFIG_X86_LOCAL_APIC
+ sum += per_cpu(irq_stat, cpu).apic_timer_irqs;
+#endif
+#ifdef CONFIG_SMP
+ sum += per_cpu(irq_stat, cpu).irq_resched_count;
+ sum += per_cpu(irq_stat, cpu).irq_call_count;
+ sum += per_cpu(irq_stat, cpu).irq_tlb_count;
+#endif
+#ifdef CONFIG_X86_MCE
+ sum += per_cpu(irq_stat, cpu).irq_thermal_count;
+#endif
+#ifdef CONFIG_X86_LOCAL_APIC
+ sum += per_cpu(irq_stat, cpu).irq_spurious_count;
+#endif
+ return sum;
+}
+
+u64 arch_irq_stat(void)
+{
+ u64 sum = atomic_read(&irq_err_count);
+
+#ifdef CONFIG_X86_IO_APIC
+ sum += atomic_read(&irq_mis_count);
+#endif
+ return sum;
+}
+
#ifdef CONFIG_HOTPLUG_CPU
#include <mach_apic.h>