linux-kernel-test/arch/x86_64/kernel/i8259.c
Eric W. Biederman 550f2299ac [PATCH] genirq: x86_64 irq: make vector_irq per cpu
This refactors the irq handling code to make the vectors a per cpu resource so
the same vector number can be simultaneously used on multiple cpus for
different irqs.

This should make systems that were hitting limits on the total number of irqs
much more livable.

[akpm@osdl.org: build fix]
[akpm@osdl.org: __target_IO_APIC_irq is unneeded on UP]
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Rajesh Shah <rajesh.shah@intel.com>
Cc: Andi Kleen <ak@muc.de>
Cc: "Protasevich, Natalie" <Natalie.Protasevich@UNISYS.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-04 07:55:29 -07:00

563 lines
14 KiB
C

#include <linux/linkage.h>
#include <linux/errno.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/ioport.h>
#include <linux/interrupt.h>
#include <linux/timex.h>
#include <linux/slab.h>
#include <linux/random.h>
#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/kernel_stat.h>
#include <linux/sysdev.h>
#include <linux/bitops.h>
#include <asm/acpi.h>
#include <asm/atomic.h>
#include <asm/system.h>
#include <asm/io.h>
#include <asm/hw_irq.h>
#include <asm/pgtable.h>
#include <asm/delay.h>
#include <asm/desc.h>
#include <asm/apic.h>
/*
* Common place to define all x86 IRQ vectors
*
* This builds up the IRQ handler stubs using some ugly macros in irq.h
*
* These macros create the low-level assembly IRQ routines that save
* register context and call do_IRQ(). do_IRQ() then does all the
* operations that are needed to keep the AT (or SMP IOAPIC)
* interrupt-controller happy.
*/
#define BI(x,y) \
BUILD_IRQ(x##y)
#define BUILD_16_IRQS(x) \
BI(x,0) BI(x,1) BI(x,2) BI(x,3) \
BI(x,4) BI(x,5) BI(x,6) BI(x,7) \
BI(x,8) BI(x,9) BI(x,a) BI(x,b) \
BI(x,c) BI(x,d) BI(x,e) BI(x,f)
/*
* ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
* (these are usually mapped to vectors 0x20-0x2f)
*/
/*
* The IO-APIC gives us many more interrupt sources. Most of these
* are unused but an SMP system is supposed to have enough memory ...
* sometimes (mostly wrt. hw bugs) we get corrupted vectors all
* across the spectrum, so we really want to be prepared to get all
* of these. Plus, more powerful systems might have more than 64
* IO-APIC registers.
*
* (these are usually mapped into the 0x30-0xff vector range)
*/
BUILD_16_IRQS(0x2) BUILD_16_IRQS(0x3)
BUILD_16_IRQS(0x4) BUILD_16_IRQS(0x5) BUILD_16_IRQS(0x6) BUILD_16_IRQS(0x7)
BUILD_16_IRQS(0x8) BUILD_16_IRQS(0x9) BUILD_16_IRQS(0xa) BUILD_16_IRQS(0xb)
BUILD_16_IRQS(0xc) BUILD_16_IRQS(0xd) BUILD_16_IRQS(0xe) BUILD_16_IRQS(0xf)
#undef BUILD_16_IRQS
#undef BI
#define IRQ(x,y) \
IRQ##x##y##_interrupt
#define IRQLIST_16(x) \
IRQ(x,0), IRQ(x,1), IRQ(x,2), IRQ(x,3), \
IRQ(x,4), IRQ(x,5), IRQ(x,6), IRQ(x,7), \
IRQ(x,8), IRQ(x,9), IRQ(x,a), IRQ(x,b), \
IRQ(x,c), IRQ(x,d), IRQ(x,e), IRQ(x,f)
void (*interrupt[NR_IRQS])(void) = {
IRQLIST_16(0x2), IRQLIST_16(0x3),
IRQLIST_16(0x4), IRQLIST_16(0x5), IRQLIST_16(0x6), IRQLIST_16(0x7),
IRQLIST_16(0x8), IRQLIST_16(0x9), IRQLIST_16(0xa), IRQLIST_16(0xb),
IRQLIST_16(0xc), IRQLIST_16(0xd), IRQLIST_16(0xe), IRQLIST_16(0xf)
};
#undef IRQ
#undef IRQLIST_16
/*
* This is the 'legacy' 8259A Programmable Interrupt Controller,
* present in the majority of PC/AT boxes.
* plus some generic x86 specific things if generic specifics makes
* any sense at all.
* this file should become arch/i386/kernel/irq.c when the old irq.c
* moves to arch independent land
*/
static int i8259A_auto_eoi;
DEFINE_SPINLOCK(i8259A_lock);
static void mask_and_ack_8259A(unsigned int);
static struct irq_chip i8259A_chip = {
.name = "XT-PIC",
.mask = disable_8259A_irq,
.unmask = enable_8259A_irq,
.mask_ack = mask_and_ack_8259A,
};
/*
* 8259A PIC functions to handle ISA devices:
*/
/*
* This contains the irq mask for both 8259A irq controllers,
*/
static unsigned int cached_irq_mask = 0xffff;
#define __byte(x,y) (((unsigned char *)&(y))[x])
#define cached_21 (__byte(0,cached_irq_mask))
#define cached_A1 (__byte(1,cached_irq_mask))
/*
* Not all IRQs can be routed through the IO-APIC, eg. on certain (older)
* boards the timer interrupt is not really connected to any IO-APIC pin,
* it's fed to the master 8259A's IR0 line only.
*
* Any '1' bit in this mask means the IRQ is routed through the IO-APIC.
* this 'mixed mode' IRQ handling costs nothing because it's only used
* at IRQ setup time.
*/
unsigned long io_apic_irqs;
void disable_8259A_irq(unsigned int irq)
{
unsigned int mask = 1 << irq;
unsigned long flags;
spin_lock_irqsave(&i8259A_lock, flags);
cached_irq_mask |= mask;
if (irq & 8)
outb(cached_A1,0xA1);
else
outb(cached_21,0x21);
spin_unlock_irqrestore(&i8259A_lock, flags);
}
void enable_8259A_irq(unsigned int irq)
{
unsigned int mask = ~(1 << irq);
unsigned long flags;
spin_lock_irqsave(&i8259A_lock, flags);
cached_irq_mask &= mask;
if (irq & 8)
outb(cached_A1,0xA1);
else
outb(cached_21,0x21);
spin_unlock_irqrestore(&i8259A_lock, flags);
}
int i8259A_irq_pending(unsigned int irq)
{
unsigned int mask = 1<<irq;
unsigned long flags;
int ret;
spin_lock_irqsave(&i8259A_lock, flags);
if (irq < 8)
ret = inb(0x20) & mask;
else
ret = inb(0xA0) & (mask >> 8);
spin_unlock_irqrestore(&i8259A_lock, flags);
return ret;
}
void make_8259A_irq(unsigned int irq)
{
disable_irq_nosync(irq);
io_apic_irqs &= ~(1<<irq);
set_irq_chip_and_handler(irq, &i8259A_chip, handle_level_irq);
enable_irq(irq);
}
/*
* This function assumes to be called rarely. Switching between
* 8259A registers is slow.
* This has to be protected by the irq controller spinlock
* before being called.
*/
static inline int i8259A_irq_real(unsigned int irq)
{
int value;
int irqmask = 1<<irq;
if (irq < 8) {
outb(0x0B,0x20); /* ISR register */
value = inb(0x20) & irqmask;
outb(0x0A,0x20); /* back to the IRR register */
return value;
}
outb(0x0B,0xA0); /* ISR register */
value = inb(0xA0) & (irqmask >> 8);
outb(0x0A,0xA0); /* back to the IRR register */
return value;
}
/*
* Careful! The 8259A is a fragile beast, it pretty
* much _has_ to be done exactly like this (mask it
* first, _then_ send the EOI, and the order of EOI
* to the two 8259s is important!
*/
static void mask_and_ack_8259A(unsigned int irq)
{
unsigned int irqmask = 1 << irq;
unsigned long flags;
spin_lock_irqsave(&i8259A_lock, flags);
/*
* Lightweight spurious IRQ detection. We do not want
* to overdo spurious IRQ handling - it's usually a sign
* of hardware problems, so we only do the checks we can
* do without slowing down good hardware unnecessarily.
*
* Note that IRQ7 and IRQ15 (the two spurious IRQs
* usually resulting from the 8259A-1|2 PICs) occur
* even if the IRQ is masked in the 8259A. Thus we
* can check spurious 8259A IRQs without doing the
* quite slow i8259A_irq_real() call for every IRQ.
* This does not cover 100% of spurious interrupts,
* but should be enough to warn the user that there
* is something bad going on ...
*/
if (cached_irq_mask & irqmask)
goto spurious_8259A_irq;
cached_irq_mask |= irqmask;
handle_real_irq:
if (irq & 8) {
inb(0xA1); /* DUMMY - (do we need this?) */
outb(cached_A1,0xA1);
outb(0x60+(irq&7),0xA0);/* 'Specific EOI' to slave */
outb(0x62,0x20); /* 'Specific EOI' to master-IRQ2 */
} else {
inb(0x21); /* DUMMY - (do we need this?) */
outb(cached_21,0x21);
outb(0x60+irq,0x20); /* 'Specific EOI' to master */
}
spin_unlock_irqrestore(&i8259A_lock, flags);
return;
spurious_8259A_irq:
/*
* this is the slow path - should happen rarely.
*/
if (i8259A_irq_real(irq))
/*
* oops, the IRQ _is_ in service according to the
* 8259A - not spurious, go handle it.
*/
goto handle_real_irq;
{
static int spurious_irq_mask;
/*
* At this point we can be sure the IRQ is spurious,
* lets ACK and report it. [once per IRQ]
*/
if (!(spurious_irq_mask & irqmask)) {
printk(KERN_DEBUG "spurious 8259A interrupt: IRQ%d.\n", irq);
spurious_irq_mask |= irqmask;
}
atomic_inc(&irq_err_count);
/*
* Theoretically we do not have to handle this IRQ,
* but in Linux this does not cause problems and is
* simpler for us.
*/
goto handle_real_irq;
}
}
void init_8259A(int auto_eoi)
{
unsigned long flags;
i8259A_auto_eoi = auto_eoi;
spin_lock_irqsave(&i8259A_lock, flags);
outb(0xff, 0x21); /* mask all of 8259A-1 */
outb(0xff, 0xA1); /* mask all of 8259A-2 */
/*
* outb_p - this has to work on a wide range of PC hardware.
*/
outb_p(0x11, 0x20); /* ICW1: select 8259A-1 init */
outb_p(0x20 + 0, 0x21); /* ICW2: 8259A-1 IR0-7 mapped to 0x20-0x27 */
outb_p(0x04, 0x21); /* 8259A-1 (the master) has a slave on IR2 */
if (auto_eoi)
outb_p(0x03, 0x21); /* master does Auto EOI */
else
outb_p(0x01, 0x21); /* master expects normal EOI */
outb_p(0x11, 0xA0); /* ICW1: select 8259A-2 init */
outb_p(0x20 + 8, 0xA1); /* ICW2: 8259A-2 IR0-7 mapped to 0x28-0x2f */
outb_p(0x02, 0xA1); /* 8259A-2 is a slave on master's IR2 */
outb_p(0x01, 0xA1); /* (slave's support for AEOI in flat mode
is to be investigated) */
if (auto_eoi)
/*
* in AEOI mode we just have to mask the interrupt
* when acking.
*/
i8259A_chip.mask_ack = disable_8259A_irq;
else
i8259A_chip.mask_ack = mask_and_ack_8259A;
udelay(100); /* wait for 8259A to initialize */
outb(cached_21, 0x21); /* restore master IRQ mask */
outb(cached_A1, 0xA1); /* restore slave IRQ mask */
spin_unlock_irqrestore(&i8259A_lock, flags);
}
static char irq_trigger[2];
/**
* ELCR registers (0x4d0, 0x4d1) control edge/level of IRQ
*/
static void restore_ELCR(char *trigger)
{
outb(trigger[0], 0x4d0);
outb(trigger[1], 0x4d1);
}
static void save_ELCR(char *trigger)
{
/* IRQ 0,1,2,8,13 are marked as reserved */
trigger[0] = inb(0x4d0) & 0xF8;
trigger[1] = inb(0x4d1) & 0xDE;
}
static int i8259A_resume(struct sys_device *dev)
{
init_8259A(i8259A_auto_eoi);
restore_ELCR(irq_trigger);
return 0;
}
static int i8259A_suspend(struct sys_device *dev, pm_message_t state)
{
save_ELCR(irq_trigger);
return 0;
}
static int i8259A_shutdown(struct sys_device *dev)
{
/* Put the i8259A into a quiescent state that
* the kernel initialization code can get it
* out of.
*/
outb(0xff, 0x21); /* mask all of 8259A-1 */
outb(0xff, 0xA1); /* mask all of 8259A-1 */
return 0;
}
static struct sysdev_class i8259_sysdev_class = {
set_kset_name("i8259"),
.suspend = i8259A_suspend,
.resume = i8259A_resume,
.shutdown = i8259A_shutdown,
};
static struct sys_device device_i8259A = {
.id = 0,
.cls = &i8259_sysdev_class,
};
static int __init i8259A_init_sysfs(void)
{
int error = sysdev_class_register(&i8259_sysdev_class);
if (!error)
error = sysdev_register(&device_i8259A);
return error;
}
device_initcall(i8259A_init_sysfs);
/*
* IRQ2 is cascade interrupt to second interrupt controller
*/
static struct irqaction irq2 = { no_action, 0, CPU_MASK_NONE, "cascade", NULL, NULL};
DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
[0 ... FIRST_EXTERNAL_VECTOR - 1] = -1,
[FIRST_EXTERNAL_VECTOR + 0] = 0,
[FIRST_EXTERNAL_VECTOR + 1] = 1,
[FIRST_EXTERNAL_VECTOR + 2] = 2,
[FIRST_EXTERNAL_VECTOR + 3] = 3,
[FIRST_EXTERNAL_VECTOR + 4] = 4,
[FIRST_EXTERNAL_VECTOR + 5] = 5,
[FIRST_EXTERNAL_VECTOR + 6] = 6,
[FIRST_EXTERNAL_VECTOR + 7] = 7,
[FIRST_EXTERNAL_VECTOR + 8] = 8,
[FIRST_EXTERNAL_VECTOR + 9] = 9,
[FIRST_EXTERNAL_VECTOR + 10] = 10,
[FIRST_EXTERNAL_VECTOR + 11] = 11,
[FIRST_EXTERNAL_VECTOR + 12] = 12,
[FIRST_EXTERNAL_VECTOR + 13] = 13,
[FIRST_EXTERNAL_VECTOR + 14] = 14,
[FIRST_EXTERNAL_VECTOR + 15] = 15,
[FIRST_EXTERNAL_VECTOR + 16 ... NR_VECTORS - 1] = -1
};
void __init init_ISA_irqs (void)
{
int i;
init_bsp_APIC();
init_8259A(0);
for (i = 0; i < NR_IRQS; i++) {
irq_desc[i].status = IRQ_DISABLED;
irq_desc[i].action = NULL;
irq_desc[i].depth = 1;
if (i < 16) {
/*
* 16 old-style INTA-cycle interrupts:
*/
set_irq_chip_and_handler(i, &i8259A_chip,
handle_level_irq);
} else {
/*
* 'high' PCI IRQs filled in on demand
*/
irq_desc[i].chip = &no_irq_chip;
}
}
}
void apic_timer_interrupt(void);
void spurious_interrupt(void);
void error_interrupt(void);
void reschedule_interrupt(void);
void call_function_interrupt(void);
void invalidate_interrupt0(void);
void invalidate_interrupt1(void);
void invalidate_interrupt2(void);
void invalidate_interrupt3(void);
void invalidate_interrupt4(void);
void invalidate_interrupt5(void);
void invalidate_interrupt6(void);
void invalidate_interrupt7(void);
void thermal_interrupt(void);
void threshold_interrupt(void);
void i8254_timer_resume(void);
static void setup_timer_hardware(void)
{
outb_p(0x34,0x43); /* binary, mode 2, LSB/MSB, ch 0 */
udelay(10);
outb_p(LATCH & 0xff , 0x40); /* LSB */
udelay(10);
outb(LATCH >> 8 , 0x40); /* MSB */
}
static int timer_resume(struct sys_device *dev)
{
setup_timer_hardware();
return 0;
}
void i8254_timer_resume(void)
{
setup_timer_hardware();
}
static struct sysdev_class timer_sysclass = {
set_kset_name("timer_pit"),
.resume = timer_resume,
};
static struct sys_device device_timer = {
.id = 0,
.cls = &timer_sysclass,
};
static int __init init_timer_sysfs(void)
{
int error = sysdev_class_register(&timer_sysclass);
if (!error)
error = sysdev_register(&device_timer);
return error;
}
device_initcall(init_timer_sysfs);
void __init init_IRQ(void)
{
int i;
init_ISA_irqs();
/*
* Cover the whole vector space, no vector can escape
* us. (some of these will be overridden and become
* 'special' SMP interrupts)
*/
for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) {
int vector = FIRST_EXTERNAL_VECTOR + i;
if (vector != IA32_SYSCALL_VECTOR)
set_intr_gate(vector, interrupt[i]);
}
#ifdef CONFIG_SMP
/*
* IRQ0 must be given a fixed assignment and initialized,
* because it's used before the IO-APIC is set up.
*/
__get_cpu_var(vector_irq)[FIRST_DEVICE_VECTOR] = 0;
/*
* The reschedule interrupt is a CPU-to-CPU reschedule-helper
* IPI, driven by wakeup.
*/
set_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
/* IPIs for invalidation */
set_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0);
set_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1);
set_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2);
set_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3);
set_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4);
set_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5);
set_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6);
set_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7);
/* IPI for generic function call */
set_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
#endif
set_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
set_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
/* self generated IPI for local APIC timer */
set_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
/* IPI vectors for APIC spurious and error interrupts */
set_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
set_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
/*
* Set the clock to HZ Hz, we already have a valid
* vector now:
*/
setup_timer_hardware();
if (!acpi_ioapic)
setup_irq(2, &irq2);
}