vserver 2.0 rc7

[linux-2.6.git] / arch / x86_64 / kernel / mce.c

diff --git a/arch/x86_64/kernel/mce.c b/arch/x86_64/kernel/mce.c
index 86f9fd8..3a89d73 100644 (file)
--- a/arch/x86_64/kernel/mce.c
+++ b/arch/x86_64/kernel/mce.c
@@ -33,6 +33,7 @@ static int banks;
 static unsigned long bank[NR_BANKS] = { [0 ... NR_BANKS-1] = ~0UL };
 static unsigned long console_logged;
 static int notify_user;
+static int rip_msr;
 
 /*
  * Lockless MCE logging infrastructure.
@@ -124,6 +125,23 @@ static int mce_available(struct cpuinfo_x86 *c)
               test_bit(X86_FEATURE_MCA, &c->x86_capability);
 }
 
+static inline void mce_get_rip(struct mce *m, struct pt_regs *regs)
+{
+       if (regs && (m->mcgstatus & MCG_STATUS_RIPV)) {
+               m->rip = regs->rip;
+               m->cs = regs->cs;
+       } else {
+               m->rip = 0;
+               m->cs = 0;
+       }
+       if (rip_msr) {
+               /* Assume the RIP in the MSR is exact. Is this true? */
+               m->mcgstatus |= MCG_STATUS_EIPV;
+               rdmsrl(rip_msr, m->rip);
+               m->cs = 0;
+       }
+}
+
 /* 
  * The actual machine check handler
  */
@@ -176,14 +194,7 @@ void do_machine_check(struct pt_regs * regs, long error_code)
                if (m.status & MCI_STATUS_ADDRV)
                        rdmsrl(MSR_IA32_MC0_ADDR + i*4, m.addr);
 
-               if (regs && (m.mcgstatus & MCG_STATUS_RIPV)) {
-                       m.rip = regs->rip;
-                       m.cs = regs->cs;
-               } else {
-                       m.rip = 0;
-                       m.cs = 0;
-               }
-
+               mce_get_rip(&m, regs);
                if (error_code != -1)
                        rdtscll(m.tsc);
                wrmsrl(MSR_IA32_MC0_STATUS + i*4, 0);
@@ -296,6 +307,9 @@ static void mce_init(void *dummy)
                printk(KERN_INFO "MCE: warning: using only %d banks\n", banks);
                banks = NR_BANKS; 
        }
+       /* Use accurate RIP reporting if available. */
+       if ((cap & (1<<9)) && ((cap >> 16) & 0xff) >= 9)
+               rip_msr = MSR_IA32_MCG_EIP;
 
        /* Log the machine checks left over from the previous reset.
           This also clears all registers */
@@ -365,18 +379,23 @@ static void collect_tscs(void *data)
 
 static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize, loff_t *off)
 {
-       unsigned long cpu_tsc[NR_CPUS];
+       unsigned long *cpu_tsc;
        static DECLARE_MUTEX(mce_read_sem);
        unsigned next;
        char __user *buf = ubuf;
        int i, err;
 
+       cpu_tsc = kmalloc(NR_CPUS * sizeof(long), GFP_KERNEL);
+       if (!cpu_tsc)
+               return -ENOMEM;
+
        down(&mce_read_sem); 
        next = rcu_dereference(mcelog.next);
 
        /* Only supports full reads right now */
        if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) { 
                up(&mce_read_sem);
+               kfree(cpu_tsc);
                return -EINVAL;
        }
 
@@ -407,6 +426,7 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize, loff
                }
        }       
        up(&mce_read_sem);
+       kfree(cpu_tsc);
        return err ? -EFAULT : buf - ubuf; 
 }