[PATCH] x86-64/i386: add mce tainting

This patch adds machine check tainting.  When a handled machine check
occurs the oops gets a new 'M' flag.  This is useful to ignore machines
with hardware problems in oops reports.

On i386 a thermal failure also sets this flag.

Done for x86-64 and i386 so far.
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

arch/i386/kernel/cpu/mcheck/k7.c

@@ -54,6 +54,7 @@ static asmlinkage void k7_machine_check(struct pt_regs * regs, long error_code)
 			wrmsr (MSR_IA32_MC0_STATUS+i*4, 0UL, 0UL);
 			/* Serialize */
 			wmb();
+			add_taint(TAINT_MACHINE_CHECK);
 		}
 	}
 

arch/i386/kernel/cpu/mcheck/non-fatal.c

@@ -48,6 +48,7 @@ static void mce_checkregs (void *info)
 
 			/* Serialize */
 			wmb();
+			add_taint(TAINT_MACHINE_CHECK);
 		}
 	}
 }

arch/i386/kernel/cpu/mcheck/p4.c

@@ -40,6 +40,7 @@ static void unexpected_thermal_interrupt(struct pt_regs *regs)
 {	
 	printk(KERN_ERR "CPU%d: Unexpected LVT TMR interrupt!\n",
 			smp_processor_id());
+	add_taint(TAINT_MACHINE_CHECK);
 }
 
 /* P4/Xeon Thermal transition interrupt handler */
@@ -60,6 +61,7 @@ static void intel_thermal_interrupt(struct pt_regs *regs)
 		printk(KERN_EMERG "CPU%d: Temperature above threshold\n", cpu);
 		printk(KERN_EMERG "CPU%d: Running in modulated clock mode\n",
 				cpu);
+		add_taint(TAINT_MACHINE_CHECK);
 	} else {
 		printk(KERN_INFO "CPU%d: Temperature/speed normal\n", cpu);
 	}
@@ -222,6 +224,7 @@ static asmlinkage void intel_machine_check(struct pt_regs * regs, long error_cod
 			wrmsr(msr, 0UL, 0UL);
 			/* Serialize */
 			wmb();
+			add_taint(TAINT_MACHINE_CHECK);
 		}
 	}
 	mcgstl &= ~(1<<2);

arch/i386/kernel/cpu/mcheck/p5.c

@@ -25,6 +25,7 @@ static asmlinkage void pentium_machine_check(struct pt_regs * regs, long error_c
 	printk(KERN_EMERG "CPU#%d: Machine Check Exception:  0x%8X (type 0x%8X).\n", smp_processor_id(), loaddr, lotype);
 	if(lotype&(1<<5))
 		printk(KERN_EMERG "CPU#%d: Possible thermal failure (CPU on fire ?).\n", smp_processor_id());
+	add_taint(TAINT_MACHINE_CHECK);
 }
 
 /* Set up machine check reporting for processors with Intel style MCE */

arch/i386/kernel/cpu/mcheck/p6.c

@@ -72,6 +72,7 @@ static asmlinkage void intel_machine_check(struct pt_regs * regs, long error_cod
 			wrmsr (msr, 0UL, 0UL);
 			/* Serialize */
 			wmb();
+			add_taint(TAINT_MACHINE_CHECK);
 		}
 	}
 	mcgstl &= ~(1<<2);

arch/i386/kernel/cpu/mcheck/winchip.c

@@ -19,6 +19,7 @@
 static asmlinkage void winchip_machine_check(struct pt_regs * regs, long error_code)
 {
 	printk(KERN_EMERG "CPU0: Machine Check Exception.\n");
+	add_taint(TAINT_MACHINE_CHECK);
 }
 
 /* Set up machine check reporting on the Winchip C6 series */

arch/x86_64/kernel/mce.c

@@ -191,6 +191,8 @@ void do_machine_check(struct pt_regs * regs, long error_code)
 			panicm = m;
 			panicm_found = 1;
 		}
+
+		tainted |= TAINT_MACHINE_CHECK;
 	}
 
 	/* Never do anything final in the polling timer */

include/linux/kernel.h

@@ -136,6 +136,7 @@ extern int oops_in_progress;		/* If set, an oops, panic(), BUG() or die() is in
 extern int panic_on_oops;
 extern int tainted;
 extern const char *print_tainted(void);
+extern void add_taint(unsigned);
 
 /* Values used for system_state */
 extern enum system_states {
@@ -150,6 +151,7 @@ extern enum system_states {
 #define TAINT_FORCED_MODULE		(1<<1)
 #define TAINT_UNSAFE_SMP		(1<<2)
 #define TAINT_FORCED_RMMOD		(1<<3)
+#define TAINT_MACHINE_CHECK		(1<<4)
 
 extern void dump_stack(void);
 

kernel/panic.c

@@ -110,6 +110,7 @@ EXPORT_SYMBOL(panic);
  *  'P' - Proprietary module has been loaded.
  *  'F' - Module has been forcibly loaded.
  *  'S' - SMP with CPUs not designed for SMP.
+ *  'M' - Machine had a machine check experience.
  *
  *	The string is overwritten by the next call to print_taint().
  */
@@ -118,12 +119,19 @@ const char *print_tainted(void)
 {
 	static char buf[20];
 	if (tainted) {
-		snprintf(buf, sizeof(buf), "Tainted: %c%c%c",
+		snprintf(buf, sizeof(buf), "Tainted: %c%c%c%c",
 			tainted & TAINT_PROPRIETARY_MODULE ? 'P' : 'G',
 			tainted & TAINT_FORCED_MODULE ? 'F' : ' ',
-			tainted & TAINT_UNSAFE_SMP ? 'S' : ' ');
+			tainted & TAINT_UNSAFE_SMP ? 'S' : ' ',
+ 			tainted & TAINT_MACHINE_CHECK ? 'M' : ' ');
 	}
 	else
 		snprintf(buf, sizeof(buf), "Not tainted");
 	return(buf);
 }
+
+void add_taint(unsigned flag)
+{
+	tainted |= flag;
+}
+EXPORT_SYMBOL(add_taint);