HWPOISON: Add PR_MCE_KILL prctl to control early kill behaviour per process

This allows processes to override their early/late kill behaviour on hardware memory errors. Typically applications which are memory error aware is better of with early kill (see the error as soon as possible), all others with late kill (only see the error when the error is really impacting execution) There's a global sysctl, but this way an application can set its specific policy. We're using two bits, one to signify that the process stated its intention and that I also made the prctl future proof by enforcing the unused arguments are 0. The state is inherited to children. Note this makes us officially run out of process flags on 32bit, but the next patch can easily add another field. Manpage patch will be supplied separately.

Andi Kleen committed 17 years ago

Commit 4db96cf1 parent 6746aff3 files · +26 −0Browse files

Unified · Split

3 files

include/linux/prctl.h +2 −0
include/linux/sched.h +2 −0
kernel/sys.c +22 −0

include/linux/prctl.h+2−0

@@ -88,4 +88,6 @@ · 87 unmodified lines
88	#define PR_TASK_PERF_COUNTERS_DISABLE 31	88	#define PR_TASK_PERF_COUNTERS_DISABLE 31
89	#define PR_TASK_PERF_COUNTERS_ENABLE 32	89	#define PR_TASK_PERF_COUNTERS_ENABLE 32
90		90
		91	#define PR_MCE_KILL 33
		92
91	#endif /* _LINUX_PRCTL_H */	93	#endif /* _LINUX_PRCTL_H */

include/linux/sched.h+2−0

 #define PF_EXITPIDONE	0x00000008	/* pi exit done on shut down */
 #define PF_VCPU		0x00000010	/* I'm a virtual CPU */
 #define PF_FORKNOEXEC	0x00000040	/* forked but didn't exec */
+#define PF_MCE_PROCESS  0x00000080      /* process policy on mce errors */
 #define PF_SUPERPRIV	0x00000100	/* used super-user privileges */
 #define PF_DUMPCORE	0x00000200	/* dumped core */
 #define PF_SIGNALED	0x00000400	/* killed by a signal */
 #define PF_SPREAD_PAGE	0x01000000	/* Spread page cache over cpuset */
 #define PF_SPREAD_SLAB	0x02000000	/* Spread some slab caches over cpuset */
 #define PF_THREAD_BOUND	0x04000000	/* Thread bound to specific cpu */
+#define PF_MCE_EARLY    0x08000000      /* Early kill for mce process policy */
 #define PF_MEMPOLICY	0x10000000	/* Non-default NUMA mempolicy */
 #define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */
 #define PF_FREEZER_SKIP	0x40000000	/* Freezer should not count it as freezeable */

kernel/sys.c+22−0

@@ -1528,6 +1528,28 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, · 1527 unmodified lines
1528	current->timer_slack_ns = arg2;	1528	current->timer_slack_ns = arg2;
1529	error = 0;	1529	error = 0;
1530	break;	1530	break;
		1531	case PR_MCE_KILL:
		1532	if (arg4 \| arg5)
		1533	return -EINVAL;
		1534	switch (arg2) {
		1535	case 0:
		1536	if (arg3 != 0)
		1537	return -EINVAL;
		1538	current->flags &= ~PF_MCE_PROCESS;
		1539	break;
		1540	case 1:
		1541	current->flags \|= PF_MCE_PROCESS;
		1542	if (arg3 != 0)
		1543	current->flags \|= PF_MCE_EARLY;
		1544	else
		1545	current->flags &= ~PF_MCE_EARLY;
		1546	break;
		1547	default:
		1548	return -EINVAL;
		1549	}
		1550	error = 0;
		1551	break;
		1552
1531	default:	1553	default:
1532	error = -EINVAL;	1554	error = -EINVAL;
1533	break;	1555	break;