---

yaml
---
r: 288651
b: refs/heads/master
c: 73323f5
h: refs/heads/master
i:
  288649: 7627cce
  288647: 4c3f44a
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: f8d98f1095210da708a59f3a0b6fd267ad8f3f03
+refs/heads/master: 73323f541fe5f55a3b8a5c3d565bfc1efd64abf6

trunk/Documentation/nmi_watchdog.txt

@@ -0,0 +1,83 @@
+
+[NMI watchdog is available for x86 and x86-64 architectures]
+
+Is your system locking up unpredictably? No keyboard activity, just
+a frustrating complete hard lockup? Do you want to help us debugging
+such lockups? If all yes then this document is definitely for you.
+
+On many x86/x86-64 type hardware there is a feature that enables
+us to generate 'watchdog NMI interrupts'.  (NMI: Non Maskable Interrupt
+which get executed even if the system is otherwise locked up hard).
+This can be used to debug hard kernel lockups.  By executing periodic
+NMI interrupts, the kernel can monitor whether any CPU has locked up,
+and print out debugging messages if so.
+
+In order to use the NMI watchdog, you need to have APIC support in your
+kernel. For SMP kernels, APIC support gets compiled in automatically. For
+UP, enable either CONFIG_X86_UP_APIC (Processor type and features -> Local
+APIC support on uniprocessors) or CONFIG_X86_UP_IOAPIC (Processor type and
+features -> IO-APIC support on uniprocessors) in your kernel config.
+CONFIG_X86_UP_APIC is for uniprocessor machines without an IO-APIC.
+CONFIG_X86_UP_IOAPIC is for uniprocessor with an IO-APIC. [Note: certain
+kernel debugging options, such as Kernel Stack Meter or Kernel Tracer,
+may implicitly disable the NMI watchdog.]
+
+For x86-64, the needed APIC is always compiled in.
+
+Using local APIC (nmi_watchdog=2) needs the first performance register, so
+you can't use it for other purposes (such as high precision performance
+profiling.) However, at least oprofile and the perfctr driver disable the
+local APIC NMI watchdog automatically.
+
+To actually enable the NMI watchdog, use the 'nmi_watchdog=N' boot
+parameter.  Eg. the relevant lilo.conf entry:
+
+        append="nmi_watchdog=1"
+
+For SMP machines and UP machines with an IO-APIC use nmi_watchdog=1.
+For UP machines without an IO-APIC use nmi_watchdog=2, this only works
+for some processor types.  If in doubt, boot with nmi_watchdog=1 and
+check the NMI count in /proc/interrupts; if the count is zero then
+reboot with nmi_watchdog=2 and check the NMI count.  If it is still
+zero then log a problem, you probably have a processor that needs to be
+added to the nmi code.
+
+A 'lockup' is the following scenario: if any CPU in the system does not
+execute the period local timer interrupt for more than 5 seconds, then
+the NMI handler generates an oops and kills the process. This
+'controlled crash' (and the resulting kernel messages) can be used to
+debug the lockup. Thus whenever the lockup happens, wait 5 seconds and
+the oops will show up automatically. If the kernel produces no messages
+then the system has crashed so hard (eg. hardware-wise) that either it
+cannot even accept NMI interrupts, or the crash has made the kernel
+unable to print messages.
+
+Be aware that when using local APIC, the frequency of NMI interrupts
+it generates, depends on the system load. The local APIC NMI watchdog,
+lacking a better source, uses the "cycles unhalted" event. As you may
+guess it doesn't tick when the CPU is in the halted state (which happens
+when the system is idle), but if your system locks up on anything but the
+"hlt" processor instruction, the watchdog will trigger very soon as the
+"cycles unhalted" event will happen every clock tick. If it locks up on
+"hlt", then you are out of luck -- the event will not happen at all and the
+watchdog won't trigger. This is a shortcoming of the local APIC watchdog
+-- unfortunately there is no "clock ticks" event that would work all the
+time. The I/O APIC watchdog is driven externally and has no such shortcoming.
+But its NMI frequency is much higher, resulting in a more significant hit
+to the overall system performance.
+
+On x86 nmi_watchdog is disabled by default so you have to enable it with
+a boot time parameter.
+
+It's possible to disable the NMI watchdog in run-time by writing "0" to
+/proc/sys/kernel/nmi_watchdog. Writing "1" to the same file will re-enable
+the NMI watchdog. Notice that you still need to use "nmi_watchdog=" parameter
+at boot time.
+
+NOTE: In kernels prior to 2.4.2-ac18 the NMI-oopser is enabled unconditionally
+on x86 SMP boxes.
+
+[ feel free to send bug reports, suggestions and patches to
+  Ingo Molnar <mingo@redhat.com> or the Linux SMP mailing
+  list at <linux-smp@vger.kernel.org> ]
+

trunk/arch/x86/include/asm/inat.h

@@ -97,12 +97,11 @@
 
 /* Attribute search APIs */
 extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode);
-extern int inat_get_last_prefix_id(insn_byte_t last_pfx);
 extern insn_attr_t inat_get_escape_attribute(insn_byte_t opcode,
-					     int lpfx_id,
+					     insn_byte_t last_pfx,
 					     insn_attr_t esc_attr);
 extern insn_attr_t inat_get_group_attribute(insn_byte_t modrm,
-					    int lpfx_id,
+					    insn_byte_t last_pfx,
 					    insn_attr_t esc_attr);
 extern insn_attr_t inat_get_avx_attribute(insn_byte_t opcode,
 					  insn_byte_t vex_m,

trunk/arch/x86/include/asm/insn.h

@@ -96,6 +96,12 @@ struct insn {
 #define X86_VEX_P(vex)	((vex) & 0x03)		/* VEX3 Byte2, VEX2 Byte1 */
 #define X86_VEX_M_MAX	0x1f			/* VEX3.M Maximum value */
 
+/* The last prefix is needed for two-byte and three-byte opcodes */
+static inline insn_byte_t insn_last_prefix(struct insn *insn)
+{
+	return insn->prefixes.bytes[3];
+}
+
 extern void insn_init(struct insn *insn, const void *kaddr, int x86_64);
 extern void insn_get_prefixes(struct insn *insn);
 extern void insn_get_opcode(struct insn *insn);
@@ -154,18 +160,6 @@ static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
 		return X86_VEX_P(insn->vex_prefix.bytes[2]);
 }
 
-/* Get the last prefix id from last prefix or VEX prefix */
-static inline int insn_last_prefix_id(struct insn *insn)
-{
-	if (insn_is_avx(insn))
-		return insn_vex_p_bits(insn);	/* VEX_p is a SIMD prefix id */
-
-	if (insn->prefixes.bytes[3])
-		return inat_get_last_prefix_id(insn->prefixes.bytes[3]);
-
-	return 0;
-}
-
 /* Offset of each field from kaddr */
 static inline int insn_offset_rex_prefix(struct insn *insn)
 {

trunk/arch/x86/lib/inat.c

@@ -29,46 +29,46 @@ insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode)
 	return inat_primary_table[opcode];
 }
 
-int inat_get_last_prefix_id(insn_byte_t last_pfx)
-{
-	insn_attr_t lpfx_attr;
-
-	lpfx_attr = inat_get_opcode_attribute(last_pfx);
-	return inat_last_prefix_id(lpfx_attr);
-}
-
-insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, int lpfx_id,
+insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, insn_byte_t last_pfx,
 				      insn_attr_t esc_attr)
 {
 	const insn_attr_t *table;
-	int n;
+	insn_attr_t lpfx_attr;
+	int n, m = 0;
 
 	n = inat_escape_id(esc_attr);
-
+	if (last_pfx) {
+		lpfx_attr = inat_get_opcode_attribute(last_pfx);
+		m = inat_last_prefix_id(lpfx_attr);
+	}
 	table = inat_escape_tables[n][0];
 	if (!table)
 		return 0;
-	if (inat_has_variant(table[opcode]) && lpfx_id) {
-		table = inat_escape_tables[n][lpfx_id];
+	if (inat_has_variant(table[opcode]) && m) {
+		table = inat_escape_tables[n][m];
 		if (!table)
 			return 0;
 	}
 	return table[opcode];
 }
 
-insn_attr_t inat_get_group_attribute(insn_byte_t modrm, int lpfx_id,
+insn_attr_t inat_get_group_attribute(insn_byte_t modrm, insn_byte_t last_pfx,
 				     insn_attr_t grp_attr)
 {
 	const insn_attr_t *table;
-	int n;
+	insn_attr_t lpfx_attr;
+	int n, m = 0;
 
 	n = inat_group_id(grp_attr);
-
+	if (last_pfx) {
+		lpfx_attr = inat_get_opcode_attribute(last_pfx);
+		m = inat_last_prefix_id(lpfx_attr);
+	}
 	table = inat_group_tables[n][0];
 	if (!table)
 		return inat_group_common_attribute(grp_attr);
-	if (inat_has_variant(table[X86_MODRM_REG(modrm)]) && lpfx_id) {
-		table = inat_group_tables[n][lpfx_id];
+	if (inat_has_variant(table[X86_MODRM_REG(modrm)]) && m) {
+		table = inat_group_tables[n][m];
 		if (!table)
 			return inat_group_common_attribute(grp_attr);
 	}

trunk/arch/x86/lib/insn.c

@@ -185,8 +185,7 @@ void insn_get_prefixes(struct insn *insn)
 void insn_get_opcode(struct insn *insn)
 {
 	struct insn_field *opcode = &insn->opcode;
-	insn_byte_t op;
-	int pfx_id;
+	insn_byte_t op, pfx;
 	if (opcode->got)
 		return;
 	if (!insn->prefixes.got)
@@ -213,8 +212,8 @@ void insn_get_opcode(struct insn *insn)
 		/* Get escaped opcode */
 		op = get_next(insn_byte_t, insn);
 		opcode->bytes[opcode->nbytes++] = op;
-		pfx_id = insn_last_prefix_id(insn);
-		insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr);
+		pfx = insn_last_prefix(insn);
+		insn->attr = inat_get_escape_attribute(op, pfx, insn->attr);
 	}
 	if (inat_must_vex(insn->attr))
 		insn->attr = 0;	/* This instruction is bad */
@@ -236,7 +235,7 @@ void insn_get_opcode(struct insn *insn)
 void insn_get_modrm(struct insn *insn)
 {
 	struct insn_field *modrm = &insn->modrm;
-	insn_byte_t pfx_id, mod;
+	insn_byte_t pfx, mod;
 	if (modrm->got)
 		return;
 	if (!insn->opcode.got)
@@ -247,8 +246,8 @@ void insn_get_modrm(struct insn *insn)
 		modrm->value = mod;
 		modrm->nbytes = 1;
 		if (inat_is_group(insn->attr)) {
-			pfx_id = insn_last_prefix_id(insn);
-			insn->attr = inat_get_group_attribute(mod, pfx_id,
+			pfx = insn_last_prefix(insn);
+			insn->attr = inat_get_group_attribute(mod, pfx,
 							      insn->attr);
 			if (insn_is_avx(insn) && !inat_accept_vex(insn->attr))
 				insn->attr = 0;	/* This is bad */

trunk/kernel/watchdog.c

@@ -3,9 +3,12 @@
  *
  * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc.
  *
- * Note: Most of this code is borrowed heavily from the original softlockup
- * detector, so thanks to Ingo for the initial implementation.
- * Some chunks also taken from the old x86-specific nmi watchdog code, thanks
+ * this code detects hard lockups: incidents in where on a CPU
+ * the kernel does not respond to anything except NMI.
+ *
+ * Note: Most of this code is borrowed heavily from softlockup.c,
+ * so thanks to Ingo for the initial implementation.
+ * Some chunks also taken from arch/x86/kernel/apic/nmi.c, thanks
  * to those contributors as well.
  */
 
@@ -114,10 +117,9 @@ static unsigned long get_sample_period(void)
 {
 	/*
 	 * convert watchdog_thresh from seconds to ns
-	 * the divide by 5 is to give hrtimer several chances (two
-	 * or three with the current relation between the soft
-	 * and hard thresholds) to increment before the
-	 * hardlockup detector generates a warning
+	 * the divide by 5 is to give hrtimer 5 chances to
+	 * increment before the hardlockup detector generates
+	 * a warning
 	 */
 	return get_softlockup_thresh() * (NSEC_PER_SEC / 5);
 }
@@ -334,11 +336,9 @@ static int watchdog(void *unused)
 
 	set_current_state(TASK_INTERRUPTIBLE);
 	/*
-	 * Run briefly (kicked by the hrtimer callback function) once every
-	 * get_sample_period() seconds (4 seconds by default) to reset the
-	 * softlockup timestamp. If this gets delayed for more than
-	 * 2*watchdog_thresh seconds then the debug-printout triggers in
-	 * watchdog_timer_fn().
+	 * Run briefly once per second to reset the softlockup timestamp.
+	 * If this gets delayed for more than 60 seconds then the
+	 * debug-printout triggers in watchdog_timer_fn().
 	 */
 	while (!kthread_should_stop()) {
 		__touch_watchdog();

trunk/lib/Kconfig.debug

@@ -166,21 +166,18 @@ config LOCKUP_DETECTOR
 	  hard and soft lockups.
 
 	  Softlockups are bugs that cause the kernel to loop in kernel
-	  mode for more than 20 seconds, without giving other tasks a
+	  mode for more than 60 seconds, without giving other tasks a
 	  chance to run.  The current stack trace is displayed upon
 	  detection and the system will stay locked up.
 
 	  Hardlockups are bugs that cause the CPU to loop in kernel mode
-	  for more than 10 seconds, without letting other interrupts have a
+	  for more than 60 seconds, without letting other interrupts have a
 	  chance to run.  The current stack trace is displayed upon detection
 	  and the system will stay locked up.
 
 	  The overhead should be minimal.  A periodic hrtimer runs to
-	  generate interrupts and kick the watchdog task every 4 seconds.
-	  An NMI is generated every 10 seconds or so to check for hardlockups.
-
-	  The frequency of hrtimer and NMI events and the soft and hard lockup
-	  thresholds can be controlled through the sysctl watchdog_thresh.
+	  generate interrupts and kick the watchdog task every 10-12 seconds.
+	  An NMI is generated every 60 seconds or so to check for hardlockups.
 
 config HARDLOCKUP_DETECTOR
 	def_bool LOCKUP_DETECTOR && PERF_EVENTS && HAVE_PERF_EVENTS_NMI && \
@@ -192,8 +189,7 @@ config BOOTPARAM_HARDLOCKUP_PANIC
 	help
 	  Say Y here to enable the kernel to panic on "hard lockups",
 	  which are bugs that cause the kernel to loop in kernel
-	  mode with interrupts disabled for more than 10 seconds (configurable
-	  using the watchdog_thresh sysctl).
+	  mode with interrupts disabled for more than 60 seconds.
 
 	  Say N if unsure.
 
@@ -210,8 +206,8 @@ config BOOTPARAM_SOFTLOCKUP_PANIC
 	help
 	  Say Y here to enable the kernel to panic on "soft lockups",
 	  which are bugs that cause the kernel to loop in kernel
-	  mode for more than 20 seconds (configurable using the watchdog_thresh
-	  sysctl), without giving other tasks a chance to run.
+	  mode for more than 60 seconds, without giving other tasks a
+	  chance to run.
 
 	  The panic can be used in combination with panic_timeout,
 	  to cause the system to reboot automatically after a