2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
|
* Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar
|
|
|
|
|
*
|
|
|
|
|
* This file contains the lowest level x86_64-specific interrupt
|
|
|
|
|
* entry and irq statistics code. All the remaining irq logic is
|
|
|
|
|
* done by the generic kernel/irq/ code and in the
|
|
|
|
|
* x86_64-specific irq controller code. (e.g. i8259.c and
|
|
|
|
|
* io_apic.c.)
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#include <linux/kernel_stat.h>
|
|
|
|
|
#include <linux/interrupt.h>
|
|
|
|
|
#include <linux/seq_file.h>
|
|
|
|
|
#include <linux/module.h>
|
2005-06-25 21:55:00 +00:00
|
|
|
#include <linux/delay.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <asm/uaccess.h>
|
|
|
|
|
#include <asm/io_apic.h>
|
2006-01-11 21:44:36 +00:00
|
|
|
#include <asm/idle.h>
|
2007-02-13 12:26:25 +00:00
|
|
|
#include <asm/smp.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
|
atomic_t irq_err_count;
|
|
|
|
|
|
2008-01-30 12:30:19 +00:00
|
|
|
/*
|
|
|
|
|
* 'what should we do if we get a hw irq event on an illegal vector'.
|
|
|
|
|
* each architecture has to answer this themselves.
|
|
|
|
|
*/
|
|
|
|
|
void ack_bad_irq(unsigned int irq)
|
|
|
|
|
{
|
|
|
|
|
printk(KERN_WARNING "unexpected IRQ trap at vector %02x\n", irq);
|
|
|
|
|
/*
|
|
|
|
|
* Currently unexpected vectors happen only on SMP and APIC.
|
|
|
|
|
* We _must_ ack these because every local APIC has only N
|
|
|
|
|
* irq slots per priority level, and a 'hanging, unacked' IRQ
|
|
|
|
|
* holds up an irq slot - in excessive cases (when multiple
|
|
|
|
|
* unexpected vectors occur) that might lock up the APIC
|
|
|
|
|
* completely.
|
|
|
|
|
* But don't ack when the APIC is disabled. -AK
|
|
|
|
|
*/
|
|
|
|
|
if (!disable_apic)
|
|
|
|
|
ack_APIC_irq();
|
|
|
|
|
}
|
|
|
|
|
|
2006-06-26 12:00:05 +00:00
|
|
|
#ifdef CONFIG_DEBUG_STACKOVERFLOW
|
|
|
|
|
/*
|
|
|
|
|
* Probabilistic stack overflow check:
|
|
|
|
|
*
|
|
|
|
|
* Only check the stack in process context, because everything else
|
|
|
|
|
* runs on the big interrupt stacks. Checking reliably is too expensive,
|
|
|
|
|
* so we just check from interrupts.
|
|
|
|
|
*/
|
|
|
|
|
static inline void stack_overflow_check(struct pt_regs *regs)
|
|
|
|
|
{
|
2007-05-09 09:35:16 +00:00
|
|
|
u64 curbase = (u64)task_stack_page(current);
|
2006-06-26 12:00:05 +00:00
|
|
|
static unsigned long warned = -60*HZ;
|
|
|
|
|
|
2008-01-30 12:30:56 +00:00
|
|
|
if (regs->sp >= curbase && regs->sp <= curbase + THREAD_SIZE &&
|
|
|
|
|
regs->sp < curbase + sizeof(struct thread_info) + 128 &&
|
2006-06-26 12:00:05 +00:00
|
|
|
time_after(jiffies, warned + 60*HZ)) {
|
2008-01-30 12:30:56 +00:00
|
|
|
printk("do_IRQ: %s near stack overflow (cur:%Lx,sp:%lx)\n",
|
|
|
|
|
current->comm, curbase, regs->sp);
|
2006-06-26 12:00:05 +00:00
|
|
|
show_stack(NULL,NULL);
|
|
|
|
|
warned = jiffies;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
#endif
|
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
|
* Generic, controller-independent functions:
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
int show_interrupts(struct seq_file *p, void *v)
|
|
|
|
|
{
|
|
|
|
|
int i = *(loff_t *) v, j;
|
|
|
|
|
struct irqaction * action;
|
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
|
|
if (i == 0) {
|
|
|
|
|
seq_printf(p, " ");
|
2006-03-23 11:01:05 +00:00
|
|
|
for_each_online_cpu(j)
|
2006-06-26 11:59:23 +00:00
|
|
|
seq_printf(p, "CPU%-8d",j);
|
2005-04-16 22:20:36 +00:00
|
|
|
seq_putc(p, '\n');
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if (i < NR_IRQS) {
|
2007-10-17 16:04:40 +00:00
|
|
|
unsigned any_count = 0;
|
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
spin_lock_irqsave(&irq_desc[i].lock, flags);
|
2007-10-17 16:04:40 +00:00
|
|
|
#ifndef CONFIG_SMP
|
|
|
|
|
any_count = kstat_irqs(i);
|
|
|
|
|
#else
|
|
|
|
|
for_each_online_cpu(j)
|
|
|
|
|
any_count |= kstat_cpu(j).irqs[i];
|
|
|
|
|
#endif
|
2005-04-16 22:20:36 +00:00
|
|
|
action = irq_desc[i].action;
|
2007-10-17 16:04:40 +00:00
|
|
|
if (!action && !any_count)
|
2005-04-16 22:20:36 +00:00
|
|
|
goto skip;
|
|
|
|
|
seq_printf(p, "%3d: ",i);
|
|
|
|
|
#ifndef CONFIG_SMP
|
|
|
|
|
seq_printf(p, "%10u ", kstat_irqs(i));
|
|
|
|
|
#else
|
2006-03-23 11:01:05 +00:00
|
|
|
for_each_online_cpu(j)
|
|
|
|
|
seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
|
2005-04-16 22:20:36 +00:00
|
|
|
#endif
|
2006-10-04 09:16:25 +00:00
|
|
|
seq_printf(p, " %8s", irq_desc[i].chip->name);
|
2006-10-17 07:10:03 +00:00
|
|
|
seq_printf(p, "-%-8s", irq_desc[i].name);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2007-10-17 16:04:40 +00:00
|
|
|
if (action) {
|
|
|
|
|
seq_printf(p, " %s", action->name);
|
|
|
|
|
while ((action = action->next) != NULL)
|
|
|
|
|
seq_printf(p, ", %s", action->name);
|
|
|
|
|
}
|
2005-04-16 22:20:36 +00:00
|
|
|
seq_putc(p, '\n');
|
|
|
|
|
skip:
|
|
|
|
|
spin_unlock_irqrestore(&irq_desc[i].lock, flags);
|
|
|
|
|
} else if (i == NR_IRQS) {
|
|
|
|
|
seq_printf(p, "NMI: ");
|
2006-03-23 11:01:05 +00:00
|
|
|
for_each_online_cpu(j)
|
|
|
|
|
seq_printf(p, "%10u ", cpu_pda(j)->__nmi_count);
|
2007-10-17 16:04:40 +00:00
|
|
|
seq_printf(p, " Non-maskable interrupts\n");
|
2005-04-16 22:20:36 +00:00
|
|
|
seq_printf(p, "LOC: ");
|
2006-03-23 11:01:05 +00:00
|
|
|
for_each_online_cpu(j)
|
|
|
|
|
seq_printf(p, "%10u ", cpu_pda(j)->apic_timer_irqs);
|
2007-10-17 16:04:40 +00:00
|
|
|
seq_printf(p, " Local timer interrupts\n");
|
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
|
seq_printf(p, "RES: ");
|
|
|
|
|
for_each_online_cpu(j)
|
|
|
|
|
seq_printf(p, "%10u ", cpu_pda(j)->irq_resched_count);
|
|
|
|
|
seq_printf(p, " Rescheduling interrupts\n");
|
|
|
|
|
seq_printf(p, "CAL: ");
|
|
|
|
|
for_each_online_cpu(j)
|
|
|
|
|
seq_printf(p, "%10u ", cpu_pda(j)->irq_call_count);
|
|
|
|
|
seq_printf(p, " function call interrupts\n");
|
|
|
|
|
seq_printf(p, "TLB: ");
|
|
|
|
|
for_each_online_cpu(j)
|
|
|
|
|
seq_printf(p, "%10u ", cpu_pda(j)->irq_tlb_count);
|
|
|
|
|
seq_printf(p, " TLB shootdowns\n");
|
|
|
|
|
#endif
|
|
|
|
|
seq_printf(p, "TRM: ");
|
|
|
|
|
for_each_online_cpu(j)
|
|
|
|
|
seq_printf(p, "%10u ", cpu_pda(j)->irq_thermal_count);
|
|
|
|
|
seq_printf(p, " Thermal event interrupts\n");
|
|
|
|
|
seq_printf(p, "THR: ");
|
|
|
|
|
for_each_online_cpu(j)
|
|
|
|
|
seq_printf(p, "%10u ", cpu_pda(j)->irq_threshold_count);
|
|
|
|
|
seq_printf(p, " Threshold APIC interrupts\n");
|
|
|
|
|
seq_printf(p, "SPU: ");
|
|
|
|
|
for_each_online_cpu(j)
|
|
|
|
|
seq_printf(p, "%10u ", cpu_pda(j)->irq_spurious_count);
|
|
|
|
|
seq_printf(p, " Spurious interrupts\n");
|
2005-04-16 22:20:36 +00:00
|
|
|
seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
|
|
|
|
|
}
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* do_IRQ handles all normal device IRQ's (the special
|
|
|
|
|
* SMP cross-CPU interrupts have their own specific
|
|
|
|
|
* handlers).
|
|
|
|
|
*/
|
|
|
|
|
asmlinkage unsigned int do_IRQ(struct pt_regs *regs)
|
IRQ: Maintain regs pointer globally rather than passing to IRQ handlers
Maintain a per-CPU global "struct pt_regs *" variable which can be used instead
of passing regs around manually through all ~1800 interrupt handlers in the
Linux kernel.
The regs pointer is used in few places, but it potentially costs both stack
space and code to pass it around. On the FRV arch, removing the regs parameter
from all the genirq function results in a 20% speed up of the IRQ exit path
(ie: from leaving timer_interrupt() to leaving do_IRQ()).
Where appropriate, an arch may override the generic storage facility and do
something different with the variable. On FRV, for instance, the address is
maintained in GR28 at all times inside the kernel as part of general exception
handling.
Having looked over the code, it appears that the parameter may be handed down
through up to twenty or so layers of functions. Consider a USB character
device attached to a USB hub, attached to a USB controller that posts its
interrupts through a cascaded auxiliary interrupt controller. A character
device driver may want to pass regs to the sysrq handler through the input
layer which adds another few layers of parameter passing.
I've build this code with allyesconfig for x86_64 and i386. I've runtested the
main part of the code on FRV and i386, though I can't test most of the drivers.
I've also done partial conversion for powerpc and MIPS - these at least compile
with minimal configurations.
This will affect all archs. Mostly the changes should be relatively easy.
Take do_IRQ(), store the regs pointer at the beginning, saving the old one:
struct pt_regs *old_regs = set_irq_regs(regs);
And put the old one back at the end:
set_irq_regs(old_regs);
Don't pass regs through to generic_handle_irq() or __do_IRQ().
In timer_interrupt(), this sort of change will be necessary:
- update_process_times(user_mode(regs));
- profile_tick(CPU_PROFILING, regs);
+ update_process_times(user_mode(get_irq_regs()));
+ profile_tick(CPU_PROFILING);
I'd like to move update_process_times()'s use of get_irq_regs() into itself,
except that i386, alone of the archs, uses something other than user_mode().
Some notes on the interrupt handling in the drivers:
(*) input_dev() is now gone entirely. The regs pointer is no longer stored in
the input_dev struct.
(*) finish_unlinks() in drivers/usb/host/ohci-q.c needs checking. It does
something different depending on whether it's been supplied with a regs
pointer or not.
(*) Various IRQ handler function pointers have been moved to type
irq_handler_t.
Signed-Off-By: David Howells <dhowells@redhat.com>
(cherry picked from 1b16e7ac850969f38b375e511e3fa2f474a33867 commit)
2006-10-05 13:55:46 +00:00
|
|
|
{
|
|
|
|
|
struct pt_regs *old_regs = set_irq_regs(regs);
|
|
|
|
|
|
2006-06-27 09:53:44 +00:00
|
|
|
/* high bit used in ret_from_ code */
|
2008-01-30 12:30:56 +00:00
|
|
|
unsigned vector = ~regs->orig_ax;
|
2006-10-04 09:16:50 +00:00
|
|
|
unsigned irq;
|
|
|
|
|
|
|
|
|
|
exit_idle();
|
|
|
|
|
irq_enter();
|
2006-10-04 09:16:51 +00:00
|
|
|
irq = __get_cpu_var(vector_irq)[vector];
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2006-06-26 12:00:05 +00:00
|
|
|
#ifdef CONFIG_DEBUG_STACKOVERFLOW
|
|
|
|
|
stack_overflow_check(regs);
|
|
|
|
|
#endif
|
2006-10-09 05:41:59 +00:00
|
|
|
|
|
|
|
|
if (likely(irq < NR_IRQS))
|
|
|
|
|
generic_handle_irq(irq);
|
2007-02-13 12:26:25 +00:00
|
|
|
else {
|
|
|
|
|
if (!disable_apic)
|
|
|
|
|
ack_APIC_irq();
|
|
|
|
|
|
|
|
|
|
if (printk_ratelimit())
|
|
|
|
|
printk(KERN_EMERG "%s: %d.%d No irq handler for vector\n",
|
|
|
|
|
__func__, smp_processor_id(), vector);
|
|
|
|
|
}
|
2006-10-09 05:41:59 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
irq_exit();
|
|
|
|
|
|
IRQ: Maintain regs pointer globally rather than passing to IRQ handlers
Maintain a per-CPU global "struct pt_regs *" variable which can be used instead
of passing regs around manually through all ~1800 interrupt handlers in the
Linux kernel.
The regs pointer is used in few places, but it potentially costs both stack
space and code to pass it around. On the FRV arch, removing the regs parameter
from all the genirq function results in a 20% speed up of the IRQ exit path
(ie: from leaving timer_interrupt() to leaving do_IRQ()).
Where appropriate, an arch may override the generic storage facility and do
something different with the variable. On FRV, for instance, the address is
maintained in GR28 at all times inside the kernel as part of general exception
handling.
Having looked over the code, it appears that the parameter may be handed down
through up to twenty or so layers of functions. Consider a USB character
device attached to a USB hub, attached to a USB controller that posts its
interrupts through a cascaded auxiliary interrupt controller. A character
device driver may want to pass regs to the sysrq handler through the input
layer which adds another few layers of parameter passing.
I've build this code with allyesconfig for x86_64 and i386. I've runtested the
main part of the code on FRV and i386, though I can't test most of the drivers.
I've also done partial conversion for powerpc and MIPS - these at least compile
with minimal configurations.
This will affect all archs. Mostly the changes should be relatively easy.
Take do_IRQ(), store the regs pointer at the beginning, saving the old one:
struct pt_regs *old_regs = set_irq_regs(regs);
And put the old one back at the end:
set_irq_regs(old_regs);
Don't pass regs through to generic_handle_irq() or __do_IRQ().
In timer_interrupt(), this sort of change will be necessary:
- update_process_times(user_mode(regs));
- profile_tick(CPU_PROFILING, regs);
+ update_process_times(user_mode(get_irq_regs()));
+ profile_tick(CPU_PROFILING);
I'd like to move update_process_times()'s use of get_irq_regs() into itself,
except that i386, alone of the archs, uses something other than user_mode().
Some notes on the interrupt handling in the drivers:
(*) input_dev() is now gone entirely. The regs pointer is no longer stored in
the input_dev struct.
(*) finish_unlinks() in drivers/usb/host/ohci-q.c needs checking. It does
something different depending on whether it's been supplied with a regs
pointer or not.
(*) Various IRQ handler function pointers have been moved to type
irq_handler_t.
Signed-Off-By: David Howells <dhowells@redhat.com>
(cherry picked from 1b16e7ac850969f38b375e511e3fa2f474a33867 commit)
2006-10-05 13:55:46 +00:00
|
|
|
set_irq_regs(old_regs);
|
2005-04-16 22:20:36 +00:00
|
|
|
return 1;
|
|
|
|
|
}
|
|
|
|
|
|
2005-06-25 21:55:00 +00:00
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
|
|
|
void fixup_irqs(cpumask_t map)
|
|
|
|
|
{
|
|
|
|
|
unsigned int irq;
|
|
|
|
|
static int warned;
|
|
|
|
|
|
|
|
|
|
for (irq = 0; irq < NR_IRQS; irq++) {
|
|
|
|
|
cpumask_t mask;
|
2007-06-25 22:52:35 +00:00
|
|
|
int break_affinity = 0;
|
|
|
|
|
int set_affinity = 1;
|
|
|
|
|
|
2005-06-25 21:55:00 +00:00
|
|
|
if (irq == 2)
|
|
|
|
|
continue;
|
|
|
|
|
|
2007-06-25 22:52:35 +00:00
|
|
|
/* interrupt's are disabled at this point */
|
|
|
|
|
spin_lock(&irq_desc[irq].lock);
|
|
|
|
|
|
|
|
|
|
if (!irq_has_action(irq) ||
|
|
|
|
|
cpus_equal(irq_desc[irq].affinity, map)) {
|
|
|
|
|
spin_unlock(&irq_desc[irq].lock);
|
|
|
|
|
continue;
|
|
|
|
|
}
|
|
|
|
|
|
2006-06-29 09:24:38 +00:00
|
|
|
cpus_and(mask, irq_desc[irq].affinity, map);
|
2007-06-25 22:52:35 +00:00
|
|
|
if (cpus_empty(mask)) {
|
|
|
|
|
break_affinity = 1;
|
2005-06-25 21:55:00 +00:00
|
|
|
mask = map;
|
|
|
|
|
}
|
2007-06-25 22:52:35 +00:00
|
|
|
|
|
|
|
|
if (irq_desc[irq].chip->mask)
|
|
|
|
|
irq_desc[irq].chip->mask(irq);
|
|
|
|
|
|
[PATCH] genirq: rename desc->handler to desc->chip
This patch-queue improves the generic IRQ layer to be truly generic, by adding
various abstractions and features to it, without impacting existing
functionality.
While the queue can be best described as "fix and improve everything in the
generic IRQ layer that we could think of", and thus it consists of many
smaller features and lots of cleanups, the one feature that stands out most is
the new 'irq chip' abstraction.
The irq-chip abstraction is about describing and coding and IRQ controller
driver by mapping its raw hardware capabilities [and quirks, if needed] in a
straightforward way, without having to think about "IRQ flow"
(level/edge/etc.) type of details.
This stands in contrast with the current 'irq-type' model of genirq
architectures, which 'mixes' raw hardware capabilities with 'flow' details.
The patchset supports both types of irq controller designs at once, and
converts i386 and x86_64 to the new irq-chip design.
As a bonus side-effect of the irq-chip approach, chained interrupt controllers
(master/slave PIC constructs, etc.) are now supported by design as well.
The end result of this patchset intends to be simpler architecture-level code
and more consolidation between architectures.
We reused many bits of code and many concepts from Russell King's ARM IRQ
layer, the merging of which was one of the motivations for this patchset.
This patch:
rename desc->handler to desc->chip.
Originally i did not want to do this, because it's a big patch. But having
both "desc->handler", "desc->handle_irq" and "action->handler" caused a
large degree of confusion and made the code appear alot less clean than it
truly is.
I have also attempted a dual approach as well by introducing a
desc->chip alias - but that just wasnt robust enough and broke
frequently.
So lets get over with this quickly. The conversion was done automatically
via scripts and converts all the code in the kernel.
This renaming patch is the first one amongst the patches, so that the
remaining patches can stay flexible and can be merged and split up
without having some big monolithic patch act as a merge barrier.
[akpm@osdl.org: build fix]
[akpm@osdl.org: another build fix]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-29 09:24:36 +00:00
|
|
|
if (irq_desc[irq].chip->set_affinity)
|
|
|
|
|
irq_desc[irq].chip->set_affinity(irq, mask);
|
2007-06-25 22:52:35 +00:00
|
|
|
else if (!(warned++))
|
|
|
|
|
set_affinity = 0;
|
|
|
|
|
|
|
|
|
|
if (irq_desc[irq].chip->unmask)
|
|
|
|
|
irq_desc[irq].chip->unmask(irq);
|
|
|
|
|
|
|
|
|
|
spin_unlock(&irq_desc[irq].lock);
|
|
|
|
|
|
|
|
|
|
if (break_affinity && set_affinity)
|
|
|
|
|
printk("Broke affinity for irq %i\n", irq);
|
|
|
|
|
else if (!set_affinity)
|
2005-06-25 21:55:00 +00:00
|
|
|
printk("Cannot set affinity for irq %i\n", irq);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* That doesn't seem sufficient. Give it 1ms. */
|
|
|
|
|
local_irq_enable();
|
|
|
|
|
mdelay(1);
|
|
|
|
|
local_irq_disable();
|
|
|
|
|
}
|
|
|
|
|
#endif
|
2005-07-29 04:15:49 +00:00
|
|
|
|
|
|
|
|
extern void call_softirq(void);
|
|
|
|
|
|
|
|
|
|
asmlinkage void do_softirq(void)
|
|
|
|
|
{
|
|
|
|
|
__u32 pending;
|
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
|
|
if (in_interrupt())
|
|
|
|
|
return;
|
|
|
|
|
|
|
|
|
|
local_irq_save(flags);
|
|
|
|
|
pending = local_softirq_pending();
|
|
|
|
|
/* Switch to interrupt stack */
|
2006-07-03 07:24:45 +00:00
|
|
|
if (pending) {
|
2005-07-29 04:15:49 +00:00
|
|
|
call_softirq();
|
2006-07-03 07:24:45 +00:00
|
|
|
WARN_ON_ONCE(softirq_count());
|
|
|
|
|
}
|
2005-07-29 04:15:49 +00:00
|
|
|
local_irq_restore(flags);
|
|
|
|
|
}
|