x86, NMI: Add NMI symbol constants and rename memory parity to PCI SERR
Replace the NMI related magic numbers with symbol constants.
Memory parity error is only valid for IBM PC-AT, newer machine use
bit 7 (0x80) of 0x61 port for PCI SERR. While memory error is usually
reported via MCE. So corresponding function name and kernel log string
is changed.
But on some machines, PCI SERR line is still used to report memory
errors. This is used by EDAC, so corresponding EDAC call is reserved.
Signed-off-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: Don Zickus <dzickus@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1294348732-15030-2-git-send-email-dzickus@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index c76aaca..c7fd1ce 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -310,15 +310,15 @@
__setup("unknown_nmi_panic", setup_unknown_nmi_panic);
static notrace __kprobes void
-mem_parity_error(unsigned char reason, struct pt_regs *regs)
+pci_serr_error(unsigned char reason, struct pt_regs *regs)
{
- printk(KERN_EMERG
- "Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
- reason, smp_processor_id());
+ pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n",
+ reason, smp_processor_id());
- printk(KERN_EMERG
- "You have some hardware problem, likely on the PCI bus.\n");
-
+ /*
+ * 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();
@@ -329,11 +329,11 @@
if (panic_on_unrecovered_nmi)
panic("NMI: Not continuing");
- printk(KERN_EMERG "Dazed and confused, but trying to continue\n");
+ pr_emerg("Dazed and confused, but trying to continue\n");
- /* Clear and disable the memory parity error line. */
- reason = (reason & 0xf) | 4;
- outb(reason, 0x61);
+ /* 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
@@ -341,15 +341,17 @@
{
unsigned long i;
- printk(KERN_EMERG "NMI: IOCK error (debug interrupt?)\n");
+ 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 & 0xf) | 8;
- outb(reason, 0x61);
+ reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK;
+ outb(reason, NMI_REASON_PORT);
i = 20000;
while (--i) {
@@ -357,8 +359,8 @@
udelay(100);
}
- reason &= ~8;
- outb(reason, 0x61);
+ reason &= ~NMI_REASON_CLEAR_IOCHK;
+ outb(reason, NMI_REASON_PORT);
}
static notrace __kprobes void
@@ -377,15 +379,14 @@
return;
}
#endif
- printk(KERN_EMERG
- "Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
- reason, smp_processor_id());
+ pr_emerg("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
+ reason, smp_processor_id());
- printk(KERN_EMERG "Do you have a strange power saving mode enabled?\n");
+ pr_emerg("Do you have a strange power saving mode enabled?\n");
if (unknown_nmi_panic || panic_on_unrecovered_nmi)
panic("NMI: Not continuing");
- printk(KERN_EMERG "Dazed and confused, but trying to continue\n");
+ pr_emerg("Dazed and confused, but trying to continue\n");
}
static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
@@ -399,7 +400,7 @@
if (!cpu)
reason = get_nmi_reason();
- if (!(reason & 0xc0)) {
+ if (!(reason & NMI_REASON_MASK)) {
if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 2, SIGINT)
== NOTIFY_STOP)
return;
@@ -417,9 +418,9 @@
return;
/* AK: following checks seem to be broken on modern chipsets. FIXME */
- if (reason & 0x80)
- mem_parity_error(reason, regs);
- if (reason & 0x40)
+ if (reason & NMI_REASON_SERR)
+ pci_serr_error(reason, regs);
+ if (reason & NMI_REASON_IOCHK)
io_check_error(reason, regs);
#ifdef CONFIG_X86_32
/*