Merge branch 'x86-mce-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-mce-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (21 commits)
  x86, mce: Fix compilation with !CONFIG_DEBUG_FS in mce-severity.c
  x86, mce: CE in last bank prevents panic by unknown MCE
  x86, mce: Fake panic support for MCE testing
  x86, mce: Move debugfs mce dir creating to mce.c
  x86, mce: Support specifying raise mode for software MCE injection
  x86, mce: Support specifying context for software mce injection
  x86, mce: fix reporting of Thermal Monitoring mechanism enabled
  x86, mce: remove never executed code
  x86, mce: add missing __cpuinit tags
  x86, mce: fix "mce" boot option handling for CONFIG_X86_NEW_MCE
  x86, mce: don't log boot MCEs on Pentium M (model == 13) CPUs
  x86: mce: Lower maximum number of banks to architecture limit
  x86: mce: macros to compute banks MSRs
  x86: mce: Move per bank data in a single datastructure
  x86: mce: Move code in mce.c
  x86: mce: Rename CONFIG_X86_NEW_MCE to CONFIG_X86_MCE
  x86: mce: Remove old i386 machine check code
  x86: mce: Update X86_MCE description in x86/Kconfig
  x86: mce: Make CONFIG_X86_ANCIENT_MCE dependent on CONFIG_X86_MCE
  x86, mce: use atomic_inc_return() instead of add by 1
  ...

Manually fixed up trivial conflicts:
	Documentation/feature-removal-schedule.txt
	arch/x86/kernel/cpu/mcheck/mce.c

1 files changed, 127 insertions, 31 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index a3a235a53f0..7029f0e2aca 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -18,7 +18,12 @@
 #include <linux/string.h>
 #include <linux/fs.h>
 #include <linux/smp.h>
+#include <linux/notifier.h>
+#include <linux/kdebug.h>
+#include <linux/cpu.h>
+#include <linux/sched.h>
 #include <asm/mce.h>
+#include <asm/apic.h>
 
 /* Update fake mce registers on current CPU. */
 static void inject_mce(struct mce *m)
@@ -39,44 +44,141 @@ static void inject_mce(struct mce *m)
 	i->finished = 1;
 }
 
-struct delayed_mce {
-	struct timer_list timer;
-	struct mce m;
-};
+static void raise_poll(struct mce *m)
+{
+	unsigned long flags;
+	mce_banks_t b;
 
-/* Inject mce on current CPU */
-static void raise_mce(unsigned long data)
+	memset(&b, 0xff, sizeof(mce_banks_t));
+	local_irq_save(flags);
+	machine_check_poll(0, &b);
+	local_irq_restore(flags);
+	m->finished = 0;
+}
+
+static void raise_exception(struct mce *m, struct pt_regs *pregs)
 {
-	struct delayed_mce *dm = (struct delayed_mce *)data;
-	struct mce *m = &dm->m;
-	int cpu = m->extcpu;
+	struct pt_regs regs;
+	unsigned long flags;
 
-	inject_mce(m);
-	if (m->status & MCI_STATUS_UC) {
-		struct pt_regs regs;
+	if (!pregs) {
 		memset(&regs, 0, sizeof(struct pt_regs));
 		regs.ip = m->ip;
 		regs.cs = m->cs;
+		pregs = &regs;
+	}
+	/* in mcheck exeception handler, irq will be disabled */
+	local_irq_save(flags);
+	do_machine_check(pregs, 0);
+	local_irq_restore(flags);
+	m->finished = 0;
+}
+
+static cpumask_t mce_inject_cpumask;
+
+static int mce_raise_notify(struct notifier_block *self,
+			    unsigned long val, void *data)
+{
+	struct die_args *args = (struct die_args *)data;
+	int cpu = smp_processor_id();
+	struct mce *m = &__get_cpu_var(injectm);
+	if (val != DIE_NMI_IPI || !cpu_isset(cpu, mce_inject_cpumask))
+		return NOTIFY_DONE;
+	cpu_clear(cpu, mce_inject_cpumask);
+	if (m->inject_flags & MCJ_EXCEPTION)
+		raise_exception(m, args->regs);
+	else if (m->status)
+		raise_poll(m);
+	return NOTIFY_STOP;
+}
+
+static struct notifier_block mce_raise_nb = {
+	.notifier_call = mce_raise_notify,
+	.priority = 1000,
+};
+
+/* Inject mce on current CPU */
+static int raise_local(struct mce *m)
+{
+	int context = MCJ_CTX(m->inject_flags);
+	int ret = 0;
+	int cpu = m->extcpu;
+
+	if (m->inject_flags & MCJ_EXCEPTION) {
 		printk(KERN_INFO "Triggering MCE exception on CPU %d\n", cpu);
-		do_machine_check(&regs, 0);
+		switch (context) {
+		case MCJ_CTX_IRQ:
+			/*
+			 * Could do more to fake interrupts like
+			 * calling irq_enter, but the necessary
+			 * machinery isn't exported currently.
+			 */
+			/*FALL THROUGH*/
+		case MCJ_CTX_PROCESS:
+			raise_exception(m, NULL);
+			break;
+		default:
+			printk(KERN_INFO "Invalid MCE context\n");
+			ret = -EINVAL;
+		}
 		printk(KERN_INFO "MCE exception done on CPU %d\n", cpu);
-	} else {
-		mce_banks_t b;
-		memset(&b, 0xff, sizeof(mce_banks_t));
+	} else if (m->status) {
 		printk(KERN_INFO "Starting machine check poll CPU %d\n", cpu);
-		machine_check_poll(0, &b);
+		raise_poll(m);
 		mce_notify_irq();
-		printk(KERN_INFO "Finished machine check poll on CPU %d\n",
-		       cpu);
-	}
-	kfree(dm);
+		printk(KERN_INFO "Machine check poll done on CPU %d\n", cpu);
+	} else
+		m->finished = 0;
+
+	return ret;
+}
+
+static void raise_mce(struct mce *m)
+{
+	int context = MCJ_CTX(m->inject_flags);
+
+	inject_mce(m);
+
+	if (context == MCJ_CTX_RANDOM)
+		return;
+
+#ifdef CONFIG_X86_LOCAL_APIC
+	if (m->inject_flags & MCJ_NMI_BROADCAST) {
+		unsigned long start;
+		int cpu;
+		get_online_cpus();
+		mce_inject_cpumask = cpu_online_map;
+		cpu_clear(get_cpu(), mce_inject_cpumask);
+		for_each_online_cpu(cpu) {
+			struct mce *mcpu = &per_cpu(injectm, cpu);
+			if (!mcpu->finished ||
+			    MCJ_CTX(mcpu->inject_flags) != MCJ_CTX_RANDOM)
+				cpu_clear(cpu, mce_inject_cpumask);
+		}
+		if (!cpus_empty(mce_inject_cpumask))
+			apic->send_IPI_mask(&mce_inject_cpumask, NMI_VECTOR);
+		start = jiffies;
+		while (!cpus_empty(mce_inject_cpumask)) {
+			if (!time_before(jiffies, start + 2*HZ)) {
+				printk(KERN_ERR
+				"Timeout waiting for mce inject NMI %lx\n",
+					*cpus_addr(mce_inject_cpumask));
+				break;
+			}
+			cpu_relax();
+		}
+		raise_local(m);
+		put_cpu();
+		put_online_cpus();
+	} else
+#endif
+		raise_local(m);
 }
 
 /* Error injection interface */
 static ssize_t mce_write(struct file *filp, const char __user *ubuf,
 			 size_t usize, loff_t *off)
 {
-	struct delayed_mce *dm;
 	struct mce m;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -96,19 +198,12 @@ static ssize_t mce_write(struct file *filp, const char __user *ubuf,
 	if (m.extcpu >= num_possible_cpus() || !cpu_online(m.extcpu))
 		return -EINVAL;
 
-	dm = kmalloc(sizeof(struct delayed_mce), GFP_KERNEL);
-	if (!dm)
-		return -ENOMEM;
-
 	/*
 	 * Need to give user space some time to set everything up,
 	 * so do it a jiffie or two later everywhere.
-	 * Should we use a hrtimer here for better synchronization?
 	 */
-	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.extcpu);
+	schedule_timeout(2);
+	raise_mce(&m);
 	return usize;
 }
 
@@ -116,6 +211,7 @@ static int inject_init(void)
 {
 	printk(KERN_INFO "Machine check injector initialized\n");
 	mce_chrdev_ops.write = mce_write;
+	register_die_notifier(&mce_raise_nb);
 	return 0;
 }