1
0
Fork 0
alistair23-linux/arch/x86/kernel/nmi.c

337 lines
7.0 KiB
C
Raw Normal View History

/*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
* Copyright (C) 2011 Don Zickus Red Hat, Inc.
*
* Pentium III FXSR, SSE support
* Gareth Hughes <gareth@valinux.com>, May 2000
*/
/*
* Handle hardware traps and faults.
*/
#include <linux/spinlock.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/nmi.h>
x86, nmi: Create new NMI handler routines The NMI handlers used to rely on the notifier infrastructure. This worked great until we wanted to support handling multiple events better. One of the key ideas to the nmi handling is to process _all_ the handlers for each NMI. The reason behind this switch is because NMIs are edge triggered. If enough NMIs are triggered, then they could be lost because the cpu can only latch at most one NMI (besides the one currently being processed). In order to deal with this we have decided to process all the NMI handlers for each NMI. This allows the handlers to determine if they recieved an event or not (the ones that can not determine this will be left to fend for themselves on the unknown NMI list). As a result of this change it is now possible to have an extra NMI that was destined to be received for an already processed event. Because the event was processed in the previous NMI, this NMI gets dropped and becomes an 'unknown' NMI. This of course will cause printks that scare people. However, we prefer to have extra NMIs as opposed to losing NMIs and as such are have developed a basic mechanism to catch most of them. That will be a later patch. To accomplish this idea, I unhooked the nmi handlers from the notifier routines and created a new mechanism loosely based on doIRQ. The reason for this is the notifier routines have a couple of shortcomings. One we could't guarantee all future NMI handlers used NOTIFY_OK instead of NOTIFY_STOP. Second, we couldn't keep track of the number of events being handled in each routine (most only handle one, perf can handle more than one). Third, I wanted to eventually display which nmi handlers are registered in the system in /proc/interrupts to help see who is generating NMIs. The patch below just implements the new infrastructure but doesn't wire it up yet (that is the next patch). Its design is based on doIRQ structs and the atomic notifier routines. So the rcu stuff in the patch isn't entirely untested (as the notifier routines have soaked it) but it should be double checked in case I copied the code wrong. Signed-off-by: Don Zickus <dzickus@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1317409584-23662-3-git-send-email-dzickus@redhat.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-09-30 13:06:20 -06:00
#include <linux/delay.h>
#include <linux/hardirq.h>
#include <linux/slab.h>
#if defined(CONFIG_EDAC)
#include <linux/edac.h>
#endif
#include <linux/atomic.h>
#include <asm/traps.h>
#include <asm/mach_traps.h>
x86, nmi: Create new NMI handler routines The NMI handlers used to rely on the notifier infrastructure. This worked great until we wanted to support handling multiple events better. One of the key ideas to the nmi handling is to process _all_ the handlers for each NMI. The reason behind this switch is because NMIs are edge triggered. If enough NMIs are triggered, then they could be lost because the cpu can only latch at most one NMI (besides the one currently being processed). In order to deal with this we have decided to process all the NMI handlers for each NMI. This allows the handlers to determine if they recieved an event or not (the ones that can not determine this will be left to fend for themselves on the unknown NMI list). As a result of this change it is now possible to have an extra NMI that was destined to be received for an already processed event. Because the event was processed in the previous NMI, this NMI gets dropped and becomes an 'unknown' NMI. This of course will cause printks that scare people. However, we prefer to have extra NMIs as opposed to losing NMIs and as such are have developed a basic mechanism to catch most of them. That will be a later patch. To accomplish this idea, I unhooked the nmi handlers from the notifier routines and created a new mechanism loosely based on doIRQ. The reason for this is the notifier routines have a couple of shortcomings. One we could't guarantee all future NMI handlers used NOTIFY_OK instead of NOTIFY_STOP. Second, we couldn't keep track of the number of events being handled in each routine (most only handle one, perf can handle more than one). Third, I wanted to eventually display which nmi handlers are registered in the system in /proc/interrupts to help see who is generating NMIs. The patch below just implements the new infrastructure but doesn't wire it up yet (that is the next patch). Its design is based on doIRQ structs and the atomic notifier routines. So the rcu stuff in the patch isn't entirely untested (as the notifier routines have soaked it) but it should be double checked in case I copied the code wrong. Signed-off-by: Don Zickus <dzickus@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1317409584-23662-3-git-send-email-dzickus@redhat.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-09-30 13:06:20 -06:00
#include <asm/nmi.h>
#define NMI_MAX_NAMELEN 16
struct nmiaction {
struct list_head list;
nmi_handler_t handler;
unsigned int flags;
char *name;
};
struct nmi_desc {
spinlock_t lock;
struct list_head head;
};
static struct nmi_desc nmi_desc[NMI_MAX] =
{
{
.lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[0].lock),
.head = LIST_HEAD_INIT(nmi_desc[0].head),
},
{
.lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[1].lock),
.head = LIST_HEAD_INIT(nmi_desc[1].head),
},
};
static int ignore_nmis;
int unknown_nmi_panic;
/*
* Prevent NMI reason port (0x61) being accessed simultaneously, can
* only be used in NMI handler.
*/
static DEFINE_RAW_SPINLOCK(nmi_reason_lock);
static int __init setup_unknown_nmi_panic(char *str)
{
unknown_nmi_panic = 1;
return 1;
}
__setup("unknown_nmi_panic", setup_unknown_nmi_panic);
x86, nmi: Create new NMI handler routines The NMI handlers used to rely on the notifier infrastructure. This worked great until we wanted to support handling multiple events better. One of the key ideas to the nmi handling is to process _all_ the handlers for each NMI. The reason behind this switch is because NMIs are edge triggered. If enough NMIs are triggered, then they could be lost because the cpu can only latch at most one NMI (besides the one currently being processed). In order to deal with this we have decided to process all the NMI handlers for each NMI. This allows the handlers to determine if they recieved an event or not (the ones that can not determine this will be left to fend for themselves on the unknown NMI list). As a result of this change it is now possible to have an extra NMI that was destined to be received for an already processed event. Because the event was processed in the previous NMI, this NMI gets dropped and becomes an 'unknown' NMI. This of course will cause printks that scare people. However, we prefer to have extra NMIs as opposed to losing NMIs and as such are have developed a basic mechanism to catch most of them. That will be a later patch. To accomplish this idea, I unhooked the nmi handlers from the notifier routines and created a new mechanism loosely based on doIRQ. The reason for this is the notifier routines have a couple of shortcomings. One we could't guarantee all future NMI handlers used NOTIFY_OK instead of NOTIFY_STOP. Second, we couldn't keep track of the number of events being handled in each routine (most only handle one, perf can handle more than one). Third, I wanted to eventually display which nmi handlers are registered in the system in /proc/interrupts to help see who is generating NMIs. The patch below just implements the new infrastructure but doesn't wire it up yet (that is the next patch). Its design is based on doIRQ structs and the atomic notifier routines. So the rcu stuff in the patch isn't entirely untested (as the notifier routines have soaked it) but it should be double checked in case I copied the code wrong. Signed-off-by: Don Zickus <dzickus@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1317409584-23662-3-git-send-email-dzickus@redhat.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-09-30 13:06:20 -06:00
#define nmi_to_desc(type) (&nmi_desc[type])
static int notrace __kprobes nmi_handle(unsigned int type, struct pt_regs *regs)
{
struct nmi_desc *desc = nmi_to_desc(type);
struct nmiaction *a;
int handled=0;
rcu_read_lock();
/*
* NMIs are edge-triggered, which means if you have enough
* of them concurrently, you can lose some because only one
* can be latched at any given time. Walk the whole list
* to handle those situations.
*/
list_for_each_entry_rcu(a, &desc->head, list) {
handled += a->handler(type, regs);
}
rcu_read_unlock();
/* return total number of NMI events handled */
return handled;
}
static int __setup_nmi(unsigned int type, struct nmiaction *action)
{
struct nmi_desc *desc = nmi_to_desc(type);
unsigned long flags;
spin_lock_irqsave(&desc->lock, flags);
/*
* some handlers need to be executed first otherwise a fake
* event confuses some handlers (kdump uses this flag)
*/
if (action->flags & NMI_FLAG_FIRST)
list_add_rcu(&action->list, &desc->head);
else
list_add_tail_rcu(&action->list, &desc->head);
spin_unlock_irqrestore(&desc->lock, flags);
return 0;
}
static struct nmiaction *__free_nmi(unsigned int type, const char *name)
{
struct nmi_desc *desc = nmi_to_desc(type);
struct nmiaction *n;
unsigned long flags;
spin_lock_irqsave(&desc->lock, flags);
list_for_each_entry_rcu(n, &desc->head, list) {
/*
* the name passed in to describe the nmi handler
* is used as the lookup key
*/
if (!strcmp(n->name, name)) {
WARN(in_nmi(),
"Trying to free NMI (%s) from NMI context!\n", n->name);
list_del_rcu(&n->list);
break;
}
}
spin_unlock_irqrestore(&desc->lock, flags);
synchronize_rcu();
return (n);
}
int register_nmi_handler(unsigned int type, nmi_handler_t handler,
unsigned long nmiflags, const char *devname)
{
struct nmiaction *action;
int retval = -ENOMEM;
if (!handler)
return -EINVAL;
action = kzalloc(sizeof(struct nmiaction), GFP_KERNEL);
if (!action)
goto fail_action;
action->handler = handler;
action->flags = nmiflags;
action->name = kstrndup(devname, NMI_MAX_NAMELEN, GFP_KERNEL);
if (!action->name)
goto fail_action_name;
retval = __setup_nmi(type, action);
if (retval)
goto fail_setup_nmi;
return retval;
fail_setup_nmi:
kfree(action->name);
fail_action_name:
kfree(action);
fail_action:
return retval;
}
EXPORT_SYMBOL_GPL(register_nmi_handler);
void unregister_nmi_handler(unsigned int type, const char *name)
{
struct nmiaction *a;
a = __free_nmi(type, name);
if (a) {
kfree(a->name);
kfree(a);
}
}
EXPORT_SYMBOL_GPL(unregister_nmi_handler);
static notrace __kprobes void
pci_serr_error(unsigned char reason, struct pt_regs *regs)
{
pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n",
reason, smp_processor_id());
/*
* On some machines, PCI SERR line is used to report memory
* errors. EDAC makes use of it.
*/
#if defined(CONFIG_EDAC)
if (edac_handler_set()) {
edac_atomic_assert_error();
return;
}
#endif
if (panic_on_unrecovered_nmi)
panic("NMI: Not continuing");
pr_emerg("Dazed and confused, but trying to continue\n");
/* Clear and disable the PCI SERR error line. */
reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_SERR;
outb(reason, NMI_REASON_PORT);
}
static notrace __kprobes void
io_check_error(unsigned char reason, struct pt_regs *regs)
{
unsigned long i;
pr_emerg(
"NMI: IOCK error (debug interrupt?) for reason %02x on CPU %d.\n",
reason, smp_processor_id());
show_registers(regs);
if (panic_on_io_nmi)
panic("NMI IOCK error: Not continuing");
/* Re-enable the IOCK line, wait for a few seconds */
reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK;
outb(reason, NMI_REASON_PORT);
i = 20000;
while (--i) {
touch_nmi_watchdog();
udelay(100);
}
reason &= ~NMI_REASON_CLEAR_IOCHK;
outb(reason, NMI_REASON_PORT);
}
static notrace __kprobes void
unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
{
int handled;
handled = nmi_handle(NMI_UNKNOWN, regs);
if (handled)
return;
#ifdef CONFIG_MCA
/*
* Might actually be able to figure out what the guilty party
* is:
*/
if (MCA_bus) {
mca_handle_nmi();
return;
}
#endif
pr_emerg("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
reason, smp_processor_id());
pr_emerg("Do you have a strange power saving mode enabled?\n");
if (unknown_nmi_panic || panic_on_unrecovered_nmi)
panic("NMI: Not continuing");
pr_emerg("Dazed and confused, but trying to continue\n");
}
static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
{
unsigned char reason = 0;
int handled;
/*
* CPU-specific NMI must be processed before non-CPU-specific
* NMI, otherwise we may lose it, because the CPU-specific
* NMI can not be detected/processed on other CPUs.
*/
handled = nmi_handle(NMI_LOCAL, regs);
if (handled)
return;
/* Non-CPU-specific NMI: NMI sources can be processed on any CPU */
raw_spin_lock(&nmi_reason_lock);
reason = get_nmi_reason();
if (reason & NMI_REASON_MASK) {
if (reason & NMI_REASON_SERR)
pci_serr_error(reason, regs);
else if (reason & NMI_REASON_IOCHK)
io_check_error(reason, regs);
#ifdef CONFIG_X86_32
/*
* Reassert NMI in case it became active
* meanwhile as it's edge-triggered:
*/
reassert_nmi();
#endif
raw_spin_unlock(&nmi_reason_lock);
return;
}
raw_spin_unlock(&nmi_reason_lock);
unknown_nmi_error(reason, regs);
}
dotraplinkage notrace __kprobes void
do_nmi(struct pt_regs *regs, long error_code)
{
nmi_enter();
inc_irq_stat(__nmi_count);
if (!ignore_nmis)
default_do_nmi(regs);
nmi_exit();
}
void stop_nmi(void)
{
ignore_nmis++;
}
void restart_nmi(void)
{
ignore_nmis--;
}