x86/mce: Add mechanism to safely save information in MCE handler

[platform/adaptation/renesas_rcar/renesas_kernel.git] / arch / x86 / kernel / cpu / mcheck / mce.c

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 362056a..e1579c5 100644 (file)
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -492,6 +492,27 @@ static void mce_report_event(struct pt_regs *regs)
        irq_work_queue(&__get_cpu_var(mce_irq_work));
 }
 
+/*
+ * Read ADDR and MISC registers.
+ */
+static void mce_read_aux(struct mce *m, int i)
+{
+       if (m->status & MCI_STATUS_MISCV)
+               m->misc = mce_rdmsrl(MSR_IA32_MCx_MISC(i));
+       if (m->status & MCI_STATUS_ADDRV) {
+               m->addr = mce_rdmsrl(MSR_IA32_MCx_ADDR(i));
+
+               /*
+                * Mask the reported address by the reported granularity.
+                */
+               if (mce_ser && (m->status & MCI_STATUS_MISCV)) {
+                       u8 shift = MCI_MISC_ADDR_LSB(m->misc);
+                       m->addr >>= shift;
+                       m->addr <<= shift;
+               }
+       }
+}
+
 DEFINE_PER_CPU(unsigned, mce_poll_count);
 
 /*
@@ -542,10 +563,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
                    (m.status & (mce_ser ? MCI_STATUS_S : MCI_STATUS_UC)))
                        continue;
 
-               if (m.status & MCI_STATUS_MISCV)
-                       m.misc = mce_rdmsrl(MSR_IA32_MCx_MISC(i));
-               if (m.status & MCI_STATUS_ADDRV)
-                       m.addr = mce_rdmsrl(MSR_IA32_MCx_ADDR(i));
+               mce_read_aux(&m, i);
 
                if (!(flags & MCP_TIMESTAMP))
                        m.tsc = 0;
@@ -869,6 +887,49 @@ static void mce_clear_state(unsigned long *toclear)
 }
 
 /*
+ * Need to save faulting physical address associated with a process
+ * in the machine check handler some place where we can grab it back
+ * later in mce_notify_process()
+ */
+#define        MCE_INFO_MAX    16
+
+struct mce_info {
+       atomic_t                inuse;
+       struct task_struct      *t;
+       __u64                   paddr;
+} mce_info[MCE_INFO_MAX];
+
+static void mce_save_info(__u64 addr)
+{
+       struct mce_info *mi;
+
+       for (mi = mce_info; mi < &mce_info[MCE_INFO_MAX]; mi++) {
+               if (atomic_cmpxchg(&mi->inuse, 0, 1) == 0) {
+                       mi->t = current;
+                       mi->paddr = addr;
+                       return;
+               }
+       }
+
+       mce_panic("Too many concurrent recoverable errors", NULL, NULL);
+}
+
+static struct mce_info *mce_find_info(void)
+{
+       struct mce_info *mi;
+
+       for (mi = mce_info; mi < &mce_info[MCE_INFO_MAX]; mi++)
+               if (atomic_read(&mi->inuse) && mi->t == current)
+                       return mi;
+       return NULL;
+}
+
+static void mce_clear_info(struct mce_info *mi)
+{
+       atomic_set(&mi->inuse, 0);
+}
+
+/*
  * The actual machine check handler. This only handles real
  * exceptions when something got corrupted coming in through int 18.
  *
@@ -981,10 +1042,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
                if (severity == MCE_AR_SEVERITY)
                        kill_it = 1;
 
-               if (m.status & MCI_STATUS_MISCV)
-                       m.misc = mce_rdmsrl(MSR_IA32_MCx_MISC(i));
-               if (m.status & MCI_STATUS_ADDRV)
-                       m.addr = mce_rdmsrl(MSR_IA32_MCx_ADDR(i));
+               mce_read_aux(&m, i);
 
                /*
                 * Action optional error. Queue address for later processing.
@@ -1046,11 +1104,15 @@ out:
 }
 EXPORT_SYMBOL_GPL(do_machine_check);
 
-/* dummy to break dependency. actual code is in mm/memory-failure.c */
-void __attribute__((weak)) memory_failure(unsigned long pfn, int vector)
+#ifndef CONFIG_MEMORY_FAILURE
+int memory_failure(unsigned long pfn, int vector, int flags)
 {
-       printk(KERN_ERR "Action optional memory failure at %lx ignored\n", pfn);
+       printk(KERN_ERR "Uncorrected memory error in page 0x%lx ignored\n"
+               "Rebuild kernel with CONFIG_MEMORY_FAILURE=y for smarter handling\n", pfn);
+
+       return 0;
 }
+#endif
 
 /*
  * Called after mce notification in process context. This code
@@ -1068,7 +1130,7 @@ void mce_notify_process(void)
        unsigned long pfn;
        mce_notify_irq();
        while (mce_ring_get(&pfn))
-               memory_failure(pfn, MCE_VECTOR);
+               memory_failure(pfn, MCE_VECTOR, 0);
 }
 
 static void mce_process_work(struct work_struct *dummy)
@@ -1634,16 +1696,35 @@ static long mce_chrdev_ioctl(struct file *f, unsigned int cmd,
        }
 }
 
-/* Modified in mce-inject.c, so not static or const */
-struct file_operations mce_chrdev_ops = {
+static ssize_t (*mce_write)(struct file *filp, const char __user *ubuf,
+                           size_t usize, loff_t *off);
+
+void register_mce_write_callback(ssize_t (*fn)(struct file *filp,
+                            const char __user *ubuf,
+                            size_t usize, loff_t *off))
+{
+       mce_write = fn;
+}
+EXPORT_SYMBOL_GPL(register_mce_write_callback);
+
+ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
+                        size_t usize, loff_t *off)
+{
+       if (mce_write)
+               return mce_write(filp, ubuf, usize, off);
+       else
+               return -EINVAL;
+}
+
+static const struct file_operations mce_chrdev_ops = {
        .open                   = mce_chrdev_open,
        .release                = mce_chrdev_release,
        .read                   = mce_chrdev_read,
+       .write                  = mce_chrdev_write,
        .poll                   = mce_chrdev_poll,
        .unlocked_ioctl         = mce_chrdev_ioctl,
        .llseek                 = no_llseek,
 };
-EXPORT_SYMBOL_GPL(mce_chrdev_ops);
 
 static struct miscdevice mce_chrdev_device = {
        MISC_MCELOG_MINOR,