x86, mce: add basic error injection infrastructure

Allow user programs to write mce records into /dev/mcelog. When they do
that a fake machine check is triggered to test the machine check code.

This uses the MCE MSR wrappers added earlier.

The implementation is straight forward. There is a struct mce record
per CPU and the MCE MSR accesses get data from there if there is valid
data injected there. This allows to test the machine check code
relatively realistically because only the lowest layer of hardware
access is intercepted.

The test suite and injector are available at
git://git.kernel.org/pub/scm/utils/cpu/mce/mce-test.git
git://git.kernel.org/pub/scm/utils/cpu/mce/mce-inject.git

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

3 files changed, 165 insertions, 1 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/Makefile b/arch/x86/kernel/cpu/mcheck/Makefile
index 5f8b09425d3..60ee182c6c5 100644
--- a/arch/x86/kernel/cpu/mcheck/Makefile
+++ b/arch/x86/kernel/cpu/mcheck/Makefile
@@ -7,3 +7,4 @@ obj-$(CONFIG_X86_MCE_INTEL)	+= mce_intel_64.o mce_intel.o
 obj-$(CONFIG_X86_MCE_AMD)	+= mce_amd_64.o
 obj-$(CONFIG_X86_MCE_NONFATAL)	+= non-fatal.o
 obj-$(CONFIG_X86_MCE_THRESHOLD) += threshold.o
+obj-$(CONFIG_X86_MCE_INJECT)	+= mce-inject.o
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
new file mode 100644
index 00000000000..58afac4b5df
--- /dev/null
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -0,0 +1,126 @@
+/*
+ * Machine check injection support.
+ * Copyright 2008 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ *
+ * Authors:
+ * Andi Kleen
+ * Ying Huang
+ */
+#include <linux/module.h>
+#include <linux/timer.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/fs.h>
+#include <linux/smp.h>
+#include <asm/uaccess.h>
+#include <asm/mce.h>
+
+/* Update fake mce registers on current CPU. */
+static void inject_mce(struct mce *m)
+{
+	struct mce *i = &per_cpu(injectm, m->cpu);
+
+	/* Make sure noone reads partially written injectm */
+	i->finished = 0;
+	mb();
+	m->finished = 0;
+	/* First set the fields after finished */
+	i->cpu = m->cpu;
+	mb();
+	/* Now write record in order, finished last (except above) */
+	memcpy(i, m, sizeof(struct mce));
+	/* Finally activate it */
+	mb();
+	i->finished = 1;
+}
+
+struct delayed_mce {
+	struct timer_list timer;
+	struct mce m;
+};
+
+/* Inject mce on current CPU */
+static void raise_mce(unsigned long data)
+{
+	struct delayed_mce *dm = (struct delayed_mce *)data;
+	struct mce *m = &dm->m;
+	int cpu = m->cpu;
+
+	inject_mce(m);
+	if (m->status & MCI_STATUS_UC) {
+		struct pt_regs regs;
+		memset(&regs, 0, sizeof(struct pt_regs));
+		regs.ip = m->ip;
+		regs.cs = m->cs;
+		printk(KERN_INFO "Triggering MCE exception on CPU %d\n", cpu);
+		do_machine_check(&regs, 0);
+		printk(KERN_INFO "MCE exception done on CPU %d\n", cpu);
+	} else {
+		mce_banks_t b;
+		memset(&b, 0xff, sizeof(mce_banks_t));
+		printk(KERN_INFO "Starting machine check poll CPU %d\n", cpu);
+		machine_check_poll(0, &b);
+		mce_notify_user();
+		printk(KERN_INFO "Finished machine check poll on CPU %d\n",
+		       cpu);
+	}
+	kfree(dm);
+}
+
+/* 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))
+		return -EPERM;
+	/*
+	 * There are some cases where real MSR reads could slip
+	 * through.
+	 */
+	if (!boot_cpu_has(X86_FEATURE_MCE) || !boot_cpu_has(X86_FEATURE_MCA))
+		return -EIO;
+
+	if ((unsigned long)usize > sizeof(struct mce))
+		usize = sizeof(struct mce);
+	if (copy_from_user(&m, ubuf, usize))
+		return -EFAULT;
+
+	if (m.cpu >= NR_CPUS || !cpu_online(m.cpu))
+		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.cpu);
+	return usize;
+}
+
+static int inject_init(void)
+{
+	printk(KERN_INFO "Machine check injector initialized\n");
+	mce_chrdev_ops.write = mce_write;
+	return 0;
+}
+
+module_init(inject_init);
+/* Cannot tolerate unloading currently because we cannot
+ * guarantee all openers of mce_chrdev will get a reference to us.
+ */
+MODULE_LICENSE("GPL");
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index e755c95674d..fe216bd10f4 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -98,6 +98,9 @@ void mce_setup(struct mce *m)
 	rdtscll(m->tsc);
 }
 
+DEFINE_PER_CPU(struct mce, injectm);
+EXPORT_PER_CPU_SYMBOL_GPL(injectm);
+
 /*
  * Lockless MCE logging infrastructure.
  * This avoids deadlocks on printk locks without having to break locks. Also
@@ -194,16 +197,46 @@ static void mce_panic(char *msg, struct mce *backup, u64 start)
 	panic(msg);
 }
 
+/* Support code for software error injection */
+
+static int msr_to_offset(u32 msr)
+{
+	unsigned bank = __get_cpu_var(injectm.bank);
+	if (msr == rip_msr)
+		return offsetof(struct mce, ip);
+	if (msr == MSR_IA32_MC0_STATUS + bank*4)
+		return offsetof(struct mce, status);
+	if (msr == MSR_IA32_MC0_ADDR + bank*4)
+		return offsetof(struct mce, addr);
+	if (msr == MSR_IA32_MC0_MISC + bank*4)
+		return offsetof(struct mce, misc);
+	if (msr == MSR_IA32_MCG_STATUS)
+		return offsetof(struct mce, mcgstatus);
+	return -1;
+}
+
 /* MSR access wrappers used for error injection */
 static u64 mce_rdmsrl(u32 msr)
 {
 	u64 v;
+	if (__get_cpu_var(injectm).finished) {
+		int offset = msr_to_offset(msr);
+		if (offset < 0)
+			return 0;
+		return *(u64 *)((char *)&__get_cpu_var(injectm) + offset);
+	}
 	rdmsrl(msr, v);
 	return v;
 }
 
 static void mce_wrmsrl(u32 msr, u64 v)
 {
+	if (__get_cpu_var(injectm).finished) {
+		int offset = msr_to_offset(msr);
+		if (offset >= 0)
+			*(u64 *)((char *)&__get_cpu_var(injectm) + offset) = v;
+		return;
+	}
 	wrmsrl(msr, v);
 }
 
@@ -296,6 +329,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 	 * exceptions.
 	 */
 }
+EXPORT_SYMBOL_GPL(machine_check_poll);
 
 /*
  * The actual machine check handler. This only handles real
@@ -468,6 +502,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
  out2:
 	atomic_dec(&mce_entry);
 }
+EXPORT_SYMBOL_GPL(do_machine_check);
 
 #ifdef CONFIG_X86_MCE_INTEL
 /***
@@ -568,6 +603,7 @@ int mce_notify_user(void)
 	}
 	return 0;
 }
+EXPORT_SYMBOL_GPL(mce_notify_user);
 
 /*
  * Initialize Machine Checks for a CPU.
@@ -904,13 +940,14 @@ static long mce_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 	}
 }
 
-static const struct file_operations mce_chrdev_ops = {
+struct file_operations mce_chrdev_ops = {
 	.open			= mce_open,
 	.release		= mce_release,
 	.read			= mce_read,
 	.poll			= mce_poll,
 	.unlocked_ioctl		= mce_ioctl,
 };
+EXPORT_SYMBOL_GPL(mce_chrdev_ops);
 
 static struct miscdevice mce_log_device = {
 	MISC_MCELOG_MINOR,