x86, mce: support more than 256 CPUs in struct mce

The old struct mce had a limitation to 256 CPUs. But x86 Linux supports
more than that now with x2apic. Add a new field extcpu to report the
extended number.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

arch/x86/include/asm/mce.h

@@ -40,9 +40,9 @@ struct mce {
 	__u64 res2;	/* dito. */
 	__u8  cs;		/* code segment */
 	__u8  bank;	/* machine check bank */
-	__u8  cpu;	/* cpu that raised the error */
+	__u8  cpu;	/* cpu number; obsolete; use extcpu now */
 	__u8  finished;   /* entry is valid */
-	__u32 pad;
+	__u32 extcpu;	/* linux cpu number that detected the error */
 };
 
 /*

arch/x86/kernel/cpu/mcheck/mce-inject.c

@@ -23,14 +23,14 @@
 /* Update fake mce registers on current CPU. */
 static void inject_mce(struct mce *m)
 {
-	struct mce *i = &per_cpu(injectm, m->cpu);
+	struct mce *i = &per_cpu(injectm, m->extcpu);
 
 	/* Make sure noone reads partially written injectm */
 	i->finished = 0;
 	mb();
 	m->finished = 0;
 	/* First set the fields after finished */
-	i->cpu = m->cpu;
+	i->extcpu = m->extcpu;
 	mb();
 	/* Now write record in order, finished last (except above) */
 	memcpy(i, m, sizeof(struct mce));
@@ -49,7 +49,7 @@ static void raise_mce(unsigned long data)
 {
 	struct delayed_mce *dm = (struct delayed_mce *)data;
 	struct mce *m = &dm->m;
-	int cpu = m->cpu;
+	int cpu = m->extcpu;
 
 	inject_mce(m);
 	if (m->status & MCI_STATUS_UC) {
@@ -93,7 +93,7 @@ static ssize_t mce_write(struct file *filp, const char __user *ubuf,
 	if (copy_from_user(&m, ubuf, usize))
 		return -EFAULT;
 
-	if (m.cpu >= num_possible_cpus() || !cpu_online(m.cpu))
+	if (m.extcpu >= num_possible_cpus() || !cpu_online(m.extcpu))
 		return -EINVAL;
 
 	dm = kmalloc(sizeof(struct delayed_mce), GFP_KERNEL);
@@ -108,7 +108,7 @@ static ssize_t mce_write(struct file *filp, const char __user *ubuf,
 	memcpy(&dm->m, &m, sizeof(struct mce));
 	setup_timer(&dm->timer, raise_mce, (unsigned long)dm);
 	dm->timer.expires = jiffies + 2;
-	add_timer_on(&dm->timer, m.cpu);
+	add_timer_on(&dm->timer, m.extcpu);
 	return usize;
 }
 

arch/x86/kernel/cpu/mcheck/mce.c

@@ -94,7 +94,7 @@ static inline int skip_bank_init(int i)
 void mce_setup(struct mce *m)
 {
 	memset(m, 0, sizeof(struct mce));
-	m->cpu = smp_processor_id();
+	m->cpu = m->extcpu = smp_processor_id();
 	rdtscll(m->tsc);
 }
 
@@ -158,7 +158,7 @@ static void print_mce(struct mce *m)
 	       KERN_EMERG "HARDWARE ERROR\n"
 	       KERN_EMERG
 	       "CPU %d: Machine Check Exception: %16Lx Bank %d: %016Lx\n",
-	       m->cpu, m->mcgstatus, m->bank, m->status);
+	       m->extcpu, m->mcgstatus, m->bank, m->status);
 	if (m->ip) {
 		printk(KERN_EMERG "RIP%s %02x:<%016Lx> ",
 		       !(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "",