Merge branch 'tip/perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into perf/core

26 files changed, 1663 insertions, 1003 deletions

diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt
index c83bd6b4e6e..d0d0bb9e3e2 100644
--- a/Documentation/trace/kprobetrace.txt
+++ b/Documentation/trace/kprobetrace.txt
@@ -22,14 +22,15 @@ current_tracer. Instead of that, add probe points via
 
 Synopsis of kprobe_events
 -------------------------
-  p[:[GRP/]EVENT] SYMBOL[+offs]|MEMADDR [FETCHARGS]	: Set a probe
-  r[:[GRP/]EVENT] SYMBOL[+0] [FETCHARGS]		: Set a return probe
+  p[:[GRP/]EVENT] [MOD:]SYM[+offs]|MEMADDR [FETCHARGS]	: Set a probe
+  r[:[GRP/]EVENT] [MOD:]SYM[+0] [FETCHARGS]		: Set a return probe
   -:[GRP/]EVENT						: Clear a probe
 
  GRP		: Group name. If omitted, use "kprobes" for it.
  EVENT		: Event name. If omitted, the event name is generated
-		  based on SYMBOL+offs or MEMADDR.
- SYMBOL[+offs]	: Symbol+offset where the probe is inserted.
+		  based on SYM+offs or MEMADDR.
+ MOD		: Module name which has given SYM.
+ SYM[+offs]	: Symbol+offset where the probe is inserted.
  MEMADDR	: Address where the probe is inserted.
 
  FETCHARGS	: Arguments. Each probe can have up to 128 args.
diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index 56fd9e3abbd..4d86c86178f 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -102,6 +102,14 @@
 #define P4_CONFIG_HT			(1ULL << P4_CONFIG_HT_SHIFT)
 
 /*
+ * If an event has alias it should be marked
+ * with a special bit. (Don't forget to check
+ * P4_PEBS_CONFIG_MASK and related bits on
+ * modification.)
+ */
+#define P4_CONFIG_ALIASABLE		(1 << 9)
+
+/*
  * The bits we allow to pass for RAW events
  */
 #define P4_CONFIG_MASK_ESCR		\
@@ -123,6 +131,31 @@
 	(p4_config_pack_escr(P4_CONFIG_MASK_ESCR))	| \
 	(p4_config_pack_cccr(P4_CONFIG_MASK_CCCR))
 
+/*
+ * In case of event aliasing we need to preserve some
+ * caller bits otherwise the mapping won't be complete.
+ */
+#define P4_CONFIG_EVENT_ALIAS_MASK			  \
+	(p4_config_pack_escr(P4_CONFIG_MASK_ESCR)	| \
+	 p4_config_pack_cccr(P4_CCCR_EDGE		| \
+			     P4_CCCR_THRESHOLD_MASK	| \
+			     P4_CCCR_COMPLEMENT		| \
+			     P4_CCCR_COMPARE))
+
+#define  P4_CONFIG_EVENT_ALIAS_IMMUTABLE_BITS		  \
+	((P4_CONFIG_HT)					| \
+	 p4_config_pack_escr(P4_ESCR_T0_OS		| \
+			     P4_ESCR_T0_USR		| \
+			     P4_ESCR_T1_OS		| \
+			     P4_ESCR_T1_USR)		| \
+	 p4_config_pack_cccr(P4_CCCR_OVF		| \
+			     P4_CCCR_CASCADE		| \
+			     P4_CCCR_FORCE_OVF		| \
+			     P4_CCCR_THREAD_ANY		| \
+			     P4_CCCR_OVF_PMI_T0		| \
+			     P4_CCCR_OVF_PMI_T1		| \
+			     P4_CONFIG_ALIASABLE))
+
 static inline bool p4_is_event_cascaded(u64 config)
 {
 	u32 cccr = p4_config_unpack_cccr(config);
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index c53d433c3dd..b7a010fce8c 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -274,7 +274,6 @@ struct x86_pmu {
 	void		(*enable_all)(int added);
 	void		(*enable)(struct perf_event *);
 	void		(*disable)(struct perf_event *);
-	void		(*hw_watchdog_set_attr)(struct perf_event_attr *attr);
 	int		(*hw_config)(struct perf_event *event);
 	int		(*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
 	unsigned	eventsel;
@@ -360,12 +359,6 @@ static u64 __read_mostly hw_cache_extra_regs
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX];
 
-void hw_nmi_watchdog_set_attr(struct perf_event_attr *wd_attr)
-{
-	if (x86_pmu.hw_watchdog_set_attr)
-		x86_pmu.hw_watchdog_set_attr(wd_attr);
-}
-
 /*
  * Propagate event elapsed time into the generic event.
  * Can only be executed on the CPU where the event is active.
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index fb901c5080f..8b7a0c30678 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -570,11 +570,92 @@ static __initconst const u64 p4_hw_cache_event_ids
  },
 };
 
+/*
+ * Because of Netburst being quite restricted in now
+ * many same events can run simultaneously, we use
+ * event aliases, ie different events which have the
+ * same functionallity but use non-intersected resources
+ * (ESCR/CCCR/couter registers). This allow us to run
+ * two or more semi-same events together. It is done
+ * transparently to a user space.
+ *
+ * Never set any cusom internal bits such as P4_CONFIG_HT,
+ * P4_CONFIG_ALIASABLE or bits for P4_PEBS_METRIC, they are
+ * either up-to-dated automatically either not appliable
+ * at all.
+ *
+ * And be really carefull choosing aliases!
+ */
+struct p4_event_alias {
+	u64 orig;
+	u64 alter;
+} p4_event_aliases[] = {
+	{
+		/*
+		 * Non-halted cycles can be substituted with
+		 * non-sleeping cycles (see Intel SDM Vol3b for
+		 * details).
+		 */
+	.orig	=
+		p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_GLOBAL_POWER_EVENTS)		|
+				    P4_ESCR_EMASK_BIT(P4_EVENT_GLOBAL_POWER_EVENTS, RUNNING)),
+	.alter	=
+		p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_EXECUTION_EVENT)		|
+				    P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS0)|
+				    P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS1)|
+				    P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS2)|
+				    P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS3)|
+				    P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS0)	|
+				    P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS1)	|
+				    P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS2)	|
+				    P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS3))|
+		p4_config_pack_cccr(P4_CCCR_THRESHOLD(15) | P4_CCCR_COMPLEMENT		|
+				    P4_CCCR_COMPARE),
+	},
+};
+
+static u64 p4_get_alias_event(u64 config)
+{
+	u64 config_match;
+	int i;
+
+	/*
+	 * Probably we're lucky and don't have to do
+	 * matching over all config bits.
+	 */
+	if (!(config & P4_CONFIG_ALIASABLE))
+		return 0;
+
+	config_match = config & P4_CONFIG_EVENT_ALIAS_MASK;
+
+	/*
+	 * If an event was previously swapped to the alter config
+	 * we should swap it back otherwise contnention on registers
+	 * will return back.
+	 */
+	for (i = 0; i < ARRAY_SIZE(p4_event_aliases); i++) {
+		if (config_match == p4_event_aliases[i].orig) {
+			config_match = p4_event_aliases[i].alter;
+			break;
+		} else if (config_match == p4_event_aliases[i].alter) {
+			config_match = p4_event_aliases[i].orig;
+			break;
+		}
+	}
+
+	if (i >= ARRAY_SIZE(p4_event_aliases))
+		return 0;
+
+	return config_match |
+		(config & P4_CONFIG_EVENT_ALIAS_IMMUTABLE_BITS);
+}
+
 static u64 p4_general_events[PERF_COUNT_HW_MAX] = {
   /* non-halted CPU clocks */
   [PERF_COUNT_HW_CPU_CYCLES] =
 	p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_GLOBAL_POWER_EVENTS)		|
-		P4_ESCR_EMASK_BIT(P4_EVENT_GLOBAL_POWER_EVENTS, RUNNING)),
+		P4_ESCR_EMASK_BIT(P4_EVENT_GLOBAL_POWER_EVENTS, RUNNING))	|
+		P4_CONFIG_ALIASABLE,
 
   /*
    * retired instructions
@@ -719,31 +800,6 @@ static int p4_validate_raw_event(struct perf_event *event)
 	return 0;
 }
 
-static void p4_hw_watchdog_set_attr(struct perf_event_attr *wd_attr)
-{
-	/*
-	 * Watchdog ticks are special on Netburst, we use
-	 * that named "non-sleeping" ticks as recommended
-	 * by Intel SDM Vol3b.
-	 */
-	WARN_ON_ONCE(wd_attr->type	!= PERF_TYPE_HARDWARE ||
-		     wd_attr->config	!= PERF_COUNT_HW_CPU_CYCLES);
-
-	wd_attr->type	= PERF_TYPE_RAW;
-	wd_attr->config	=
-		p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_EXECUTION_EVENT)		|
-			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS0)		|
-			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS1)		|
-			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS2)		|
-			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS3)		|
-			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS0)		|
-			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS1)		|
-			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS2)		|
-			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS3))		|
-		p4_config_pack_cccr(P4_CCCR_THRESHOLD(15) | P4_CCCR_COMPLEMENT		|
-			P4_CCCR_COMPARE);
-}
-
 static int p4_hw_config(struct perf_event *event)
 {
 	int cpu = get_cpu();
@@ -1159,6 +1215,8 @@ static int p4_pmu_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign
 	struct p4_event_bind *bind;
 	unsigned int i, thread, num;
 	int cntr_idx, escr_idx;
+	u64 config_alias;
+	int pass;
 
 	bitmap_zero(used_mask, X86_PMC_IDX_MAX);
 	bitmap_zero(escr_mask, P4_ESCR_MSR_TABLE_SIZE);
@@ -1167,6 +1225,17 @@ static int p4_pmu_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign
 
 		hwc = &cpuc->event_list[i]->hw;
 		thread = p4_ht_thread(cpu);
+		pass = 0;
+
+again:
+		/*
+		 * Aliases are swappable so we may hit circular
+		 * lock if both original config and alias need
+		 * resources (MSR registers) which already busy.
+		 */
+		if (pass > 2)
+			goto done;
+
 		bind = p4_config_get_bind(hwc->config);
 		escr_idx = p4_get_escr_idx(bind->escr_msr[thread]);
 		if (unlikely(escr_idx == -1))
@@ -1180,8 +1249,17 @@ static int p4_pmu_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign
 		}
 
 		cntr_idx = p4_next_cntr(thread, used_mask, bind);
-		if (cntr_idx == -1 || test_bit(escr_idx, escr_mask))
-			goto done;
+		if (cntr_idx == -1 || test_bit(escr_idx, escr_mask)) {
+			/*
+			 * Probably an event alias is still available.
+			 */
+			config_alias = p4_get_alias_event(hwc->config);
+			if (!config_alias)
+				goto done;
+			hwc->config = config_alias;
+			pass++;
+			goto again;
+		}
 
 		p4_pmu_swap_config_ts(hwc, cpu);
 		if (assign)
@@ -1218,7 +1296,6 @@ static __initconst const struct x86_pmu p4_pmu = {
 	.cntval_bits		= ARCH_P4_CNTRVAL_BITS,
 	.cntval_mask		= ARCH_P4_CNTRVAL_MASK,
 	.max_period		= (1ULL << (ARCH_P4_CNTRVAL_BITS - 1)) - 1,
-	.hw_watchdog_set_attr	= p4_hw_watchdog_set_attr,
 	.hw_config		= p4_hw_config,
 	.schedule_events	= p4_pmu_schedule_events,
 	/*
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index b1e69eefc20..96efa6794ea 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -76,6 +76,7 @@ struct trace_iterator {
 	struct trace_entry	*ent;
 	unsigned long		lost_events;
 	int			leftover;
+	int			ent_size;
 	int			cpu;
 	u64			ts;
 
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 77981813a1e..b30fd54eb98 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1255,19 +1255,29 @@ static int __kprobes in_kprobes_functions(unsigned long addr)
 /*
  * If we have a symbol_name argument, look it up and add the offset field
  * to it. This way, we can specify a relative address to a symbol.
+ * This returns encoded errors if it fails to look up symbol or invalid
+ * combination of parameters.
  */
 static kprobe_opcode_t __kprobes *kprobe_addr(struct kprobe *p)
 {
 	kprobe_opcode_t *addr = p->addr;
+
+	if ((p->symbol_name && p->addr) ||
+	    (!p->symbol_name && !p->addr))
+		goto invalid;
+
 	if (p->symbol_name) {
-		if (addr)
-			return NULL;
 		kprobe_lookup_name(p->symbol_name, addr);
+		if (!addr)
+			return ERR_PTR(-ENOENT);
 	}
 
-	if (!addr)
-		return NULL;
-	return (kprobe_opcode_t *)(((char *)addr) + p->offset);
+	addr = (kprobe_opcode_t *)(((char *)addr) + p->offset);
+	if (addr)
+		return addr;
+
+invalid:
+	return ERR_PTR(-EINVAL);
 }
 
 /* Check passed kprobe is valid and return kprobe in kprobe_table. */
@@ -1311,8 +1321,8 @@ int __kprobes register_kprobe(struct kprobe *p)
 	kprobe_opcode_t *addr;
 
 	addr = kprobe_addr(p);
-	if (!addr)
-		return -EINVAL;
+	if (IS_ERR(addr))
+		return PTR_ERR(addr);
 	p->addr = addr;
 
 	ret = check_kprobe_rereg(p);
@@ -1335,6 +1345,8 @@ int __kprobes register_kprobe(struct kprobe *p)
 	 */
 	probed_mod = __module_text_address((unsigned long) p->addr);
 	if (probed_mod) {
+		/* Return -ENOENT if fail. */
+		ret = -ENOENT;
 		/*
 		 * We must hold a refcount of the probed module while updating
 		 * its code to prohibit unexpected unloading.
@@ -1351,6 +1363,7 @@ int __kprobes register_kprobe(struct kprobe *p)
 			module_put(probed_mod);
 			goto fail_with_jump_label;
 		}
+		/* ret will be updated by following code */
 	}
 	preempt_enable();
 	jump_label_unlock();
@@ -1399,7 +1412,7 @@ out:
 fail_with_jump_label:
 	preempt_enable();
 	jump_label_unlock();
-	return -EINVAL;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(register_kprobe);
 
@@ -1686,8 +1699,8 @@ int __kprobes register_kretprobe(struct kretprobe *rp)
 
 	if (kretprobe_blacklist_size) {
 		addr = kprobe_addr(&rp->kp);
-		if (!addr)
-			return -EINVAL;
+		if (IS_ERR(addr))
+			return PTR_ERR(addr);
 
 		for (i = 0; kretprobe_blacklist[i].name != NULL; i++) {
 			if (kretprobe_blacklist[i].addr == addr)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index a0e246e2cee..c3e4575e782 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -88,6 +88,7 @@ static struct ftrace_ops ftrace_list_end __read_mostly = {
 static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end;
 static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end;
 ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
+static ftrace_func_t __ftrace_trace_function_delay __read_mostly = ftrace_stub;
 ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
 ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
 static struct ftrace_ops global_ops;
@@ -146,9 +147,11 @@ void clear_ftrace_function(void)
 {
 	ftrace_trace_function = ftrace_stub;
 	__ftrace_trace_function = ftrace_stub;
+	__ftrace_trace_function_delay = ftrace_stub;
 	ftrace_pid_function = ftrace_stub;
 }
 
+#undef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 #ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 /*
  * For those archs that do not test ftrace_trace_stop in their
@@ -208,7 +211,12 @@ static void update_ftrace_function(void)
 #ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	ftrace_trace_function = func;
 #else
+#ifdef CONFIG_DYNAMIC_FTRACE
+	/* do not update till all functions have been modified */
+	__ftrace_trace_function_delay = func;
+#else
 	__ftrace_trace_function = func;
+#endif
 	ftrace_trace_function = ftrace_test_stop_func;
 #endif
 }
@@ -1170,8 +1178,14 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash)
 	return NULL;
 }
 
+static void
+ftrace_hash_rec_disable(struct ftrace_ops *ops, int filter_hash);
+static void
+ftrace_hash_rec_enable(struct ftrace_ops *ops, int filter_hash);
+
 static int
-ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src)
+ftrace_hash_move(struct ftrace_ops *ops, int enable,
+		 struct ftrace_hash **dst, struct ftrace_hash *src)
 {
 	struct ftrace_func_entry *entry;
 	struct hlist_node *tp, *tn;
@@ -1181,9 +1195,16 @@ ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src)
 	unsigned long key;
 	int size = src->count;
 	int bits = 0;
+	int ret;
 	int i;
 
 	/*
+	 * Remove the current set, update the hash and add
+	 * them back.
+	 */
+	ftrace_hash_rec_disable(ops, enable);
+
+	/*
 	 * If the new source is empty, just free dst and assign it
 	 * the empty_hash.
 	 */
@@ -1203,9 +1224,10 @@ ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src)
 	if (bits > FTRACE_HASH_MAX_BITS)
 		bits = FTRACE_HASH_MAX_BITS;
 
+	ret = -ENOMEM;
 	new_hash = alloc_ftrace_hash(bits);
 	if (!new_hash)
-		return -ENOMEM;
+		goto out;
 
 	size = 1 << src->size_bits;
 	for (i = 0; i < size; i++) {
@@ -1224,7 +1246,16 @@ ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src)
 	rcu_assign_pointer(*dst, new_hash);
 	free_ftrace_hash_rcu(old_hash);
 
-	return 0;
+	ret = 0;
+ out:
+	/*
+	 * Enable regardless of ret:
+	 *  On success, we enable the new hash.
+	 *  On failure, we re-enable the original hash.
+	 */
+	ftrace_hash_rec_enable(ops, enable);
+
+	return ret;
 }
 
 /*
@@ -1584,6 +1615,12 @@ static int __ftrace_modify_code(void *data)
 {
 	int *command = data;
 
+	/*
+	 * Do not call function tracer while we update the code.
+	 * We are in stop machine, no worrying about races.
+	 */
+	function_trace_stop++;
+
 	if (*command & FTRACE_ENABLE_CALLS)
 		ftrace_replace_code(1);
 	else if (*command & FTRACE_DISABLE_CALLS)
@@ -1597,6 +1634,18 @@ static int __ftrace_modify_code(void *data)
 	else if (*command & FTRACE_STOP_FUNC_RET)
 		ftrace_disable_ftrace_graph_caller();
 
+#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+	/*
+	 * For archs that call ftrace_test_stop_func(), we must
+	 * wait till after we update all the function callers
+	 * before we update the callback. This keeps different
+	 * ops that record different functions from corrupting
+	 * each other.
+	 */
+	__ftrace_trace_function = __ftrace_trace_function_delay;
+#endif
+	function_trace_stop--;
+
 	return 0;
 }
 
@@ -2865,7 +2914,11 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
 		ftrace_match_records(hash, buf, len);
 
 	mutex_lock(&ftrace_lock);
-	ret = ftrace_hash_move(orig_hash, hash);
+	ret = ftrace_hash_move(ops, enable, orig_hash, hash);
+	if (!ret && ops->flags & FTRACE_OPS_FL_ENABLED
+	    && ftrace_enabled)
+		ftrace_run_update_code(FTRACE_ENABLE_CALLS);
+
 	mutex_unlock(&ftrace_lock);
 
 	mutex_unlock(&ftrace_regex_lock);
@@ -3048,18 +3101,12 @@ ftrace_regex_release(struct inode *inode, struct file *file)
 			orig_hash = &iter->ops->notrace_hash;
 
 		mutex_lock(&ftrace_lock);
-		/*
-		 * Remove the current set, update the hash and add
-		 * them back.
-		 */
-		ftrace_hash_rec_disable(iter->ops, filter_hash);
-		ret = ftrace_hash_move(orig_hash, iter->hash);
-		if (!ret) {
-			ftrace_hash_rec_enable(iter->ops, filter_hash);
-			if (iter->ops->flags & FTRACE_OPS_FL_ENABLED
-			    && ftrace_enabled)
-				ftrace_run_update_code(FTRACE_ENABLE_CALLS);
-		}
+		ret = ftrace_hash_move(iter->ops, filter_hash,
+				       orig_hash, iter->hash);
+		if (!ret && (iter->ops->flags & FTRACE_OPS_FL_ENABLED)
+		    && ftrace_enabled)
+			ftrace_run_update_code(FTRACE_ENABLE_CALLS);
+
 		mutex_unlock(&ftrace_lock);
 	}
 	free_ftrace_hash(iter->hash);
@@ -3338,7 +3385,7 @@ static int ftrace_process_locs(struct module *mod,
 {
 	unsigned long *p;
 	unsigned long addr;
-	unsigned long flags;
+	unsigned long flags = 0; /* Shut up gcc */
 
 	mutex_lock(&ftrace_lock);
 	p = start;
@@ -3356,12 +3403,18 @@ static int ftrace_process_locs(struct module *mod,
 	}
 
 	/*
-	 * Disable interrupts to prevent interrupts from executing
-	 * code that is being modified.
+	 * We only need to disable interrupts on start up
+	 * because we are modifying code that an interrupt
+	 * may execute, and the modification is not atomic.
+	 * But for modules, nothing runs the code we modify
+	 * until we are finished with it, and there's no
+	 * reason to cause large interrupt latencies while we do it.
 	 */
-	local_irq_save(flags);
+	if (!mod)
+		local_irq_save(flags);
 	ftrace_update_code(mod);
-	local_irq_restore(flags);
+	if (!mod)
+		local_irq_restore(flags);
 	mutex_unlock(&ftrace_lock);
 
 	return 0;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index d9c16123f6e..e5df02c69b1 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1248,6 +1248,15 @@ ftrace(struct trace_array *tr, struct trace_array_cpu *data,
 }
 
 #ifdef CONFIG_STACKTRACE
+
+#define FTRACE_STACK_MAX_ENTRIES (PAGE_SIZE / sizeof(unsigned long))
+struct ftrace_stack {
+	unsigned long		calls[FTRACE_STACK_MAX_ENTRIES];
+};
+
+static DEFINE_PER_CPU(struct ftrace_stack, ftrace_stack);
+static DEFINE_PER_CPU(int, ftrace_stack_reserve);
+
 static void __ftrace_trace_stack(struct ring_buffer *buffer,
 				 unsigned long flags,
 				 int skip, int pc, struct pt_regs *regs)
@@ -1256,25 +1265,77 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
 	struct ring_buffer_event *event;
 	struct stack_entry *entry;
 	struct stack_trace trace;
+	int use_stack;
+	int size = FTRACE_STACK_ENTRIES;
+
+	trace.nr_entries	= 0;
+	trace.skip		= skip;
+
+	/*
+	 * Since events can happen in NMIs there's no safe way to
+	 * use the per cpu ftrace_stacks. We reserve it and if an interrupt
+	 * or NMI comes in, it will just have to use the default
+	 * FTRACE_STACK_SIZE.
+	 */
+	preempt_disable_notrace();
+
+	use_stack = ++__get_cpu_var(ftrace_stack_reserve);
+	/*
+	 * We don't need any atomic variables, just a barrier.
+	 * If an interrupt comes in, we don't care, because it would
+	 * have exited and put the counter back to what we want.
+	 * We just need a barrier to keep gcc from moving things
+	 * around.
+	 */
+	barrier();
+	if (use_stack == 1) {
+		trace.entries		= &__get_cpu_var(ftrace_stack).calls[0];
+		trace.max_entries	= FTRACE_STACK_MAX_ENTRIES;
+
+		if (regs)
+			save_stack_trace_regs(regs, &trace);
+		else
+			save_stack_trace(&trace);
+
+		if (trace.nr_entries > size)
+			size = trace.nr_entries;
+	} else
+		/* From now on, use_stack is a boolean */
+		use_stack = 0;
+
+	size *= sizeof(unsigned long);
 
 	event = trace_buffer_lock_reserve(buffer, TRACE_STACK,
-					  sizeof(*entry), flags, pc);
+					  sizeof(*entry) + size, flags, pc);
 	if (!event)
-		return;
-	entry	= ring_buffer_event_data(event);
-	memset(&entry->caller, 0, sizeof(entry->caller));
+		goto out;
+	entry = ring_buffer_event_data(event);
 
-	trace.nr_entries	= 0;
-	trace.max_entries	= FTRACE_STACK_ENTRIES;
-	trace.skip		= skip;
-	trace.entries		= entry->caller;
+	memset(&entry->caller, 0, size);
+
+	if (use_stack)
+		memcpy(&entry->caller, trace.entries,
+		       trace.nr_entries * sizeof(unsigned long));
+	else {
+		trace.max_entries	= FTRACE_STACK_ENTRIES;
+		trace.entries		= entry->caller;
+		if (regs)
+			save_stack_trace_regs(regs, &trace);
+		else
+			save_stack_trace(&trace);
+	}
+
+	entry->size = trace.nr_entries;
 
-	if (regs)
-		save_stack_trace_regs(regs, &trace);
-	else
-		save_stack_trace(&trace);
 	if (!filter_check_discard(call, entry, buffer, event))
 		ring_buffer_unlock_commit(buffer, event);
+
+ out:
+	/* Again, don't let gcc optimize things here */
+	barrier();
+	__get_cpu_var(ftrace_stack_reserve)--;
+	preempt_enable_notrace();
+
 }
 
 void ftrace_trace_stack_regs(struct ring_buffer *buffer, unsigned long flags,
@@ -1562,7 +1623,12 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
 
 	ftrace_enable_cpu();
 
-	return event ? ring_buffer_event_data(event) : NULL;
+	if (event) {
+		iter->ent_size = ring_buffer_event_length(event);
+		return ring_buffer_event_data(event);
+	}
+	iter->ent_size = 0;
+	return NULL;
 }
 
 static struct trace_entry *
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 30a94c26dcb..3f381d0b20a 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -278,6 +278,29 @@ struct tracer {
 };
 
 
+/* Only current can touch trace_recursion */
+#define trace_recursion_inc() do { (current)->trace_recursion++; } while (0)
+#define trace_recursion_dec() do { (current)->trace_recursion--; } while (0)
+
+/* Ring buffer has the 10 LSB bits to count */
+#define trace_recursion_buffer() ((current)->trace_recursion & 0x3ff)
+
+/* for function tracing recursion */
+#define TRACE_INTERNAL_BIT		(1<<11)
+#define TRACE_GLOBAL_BIT		(1<<12)
+/*
+ * Abuse of the trace_recursion.
+ * As we need a way to maintain state if we are tracing the function
+ * graph in irq because we want to trace a particular function that
+ * was called in irq context but we have irq tracing off. Since this
+ * can only be modified by current, we can reuse trace_recursion.
+ */
+#define TRACE_IRQ_BIT			(1<<13)
+
+#define trace_recursion_set(bit)	do { (current)->trace_recursion |= (bit); } while (0)
+#define trace_recursion_clear(bit)	do { (current)->trace_recursion &= ~(bit); } while (0)
+#define trace_recursion_test(bit)	((current)->trace_recursion & (bit))
+
 #define TRACE_PIPE_ALL_CPU	-1
 
 int tracer_init(struct tracer *t, struct trace_array *tr);
@@ -516,8 +539,18 @@ static inline int ftrace_graph_addr(unsigned long addr)
 		return 1;
 
 	for (i = 0; i < ftrace_graph_count; i++) {
-		if (addr == ftrace_graph_funcs[i])
+		if (addr == ftrace_graph_funcs[i]) {
+			/*
+			 * If no irqs are to be traced, but a set_graph_function
+			 * is set, and called by an interrupt handler, we still
+			 * want to trace it.
+			 */
+			if (in_irq())
+				trace_recursion_set(TRACE_IRQ_BIT);
+			else
+				trace_recursion_clear(TRACE_IRQ_BIT);
 			return 1;
+		}
 	}
 
 	return 0;
@@ -795,19 +828,4 @@ extern const char *__stop___trace_bprintk_fmt[];
 	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
 #include "trace_entries.h"
 
-/* Only current can touch trace_recursion */
-#define trace_recursion_inc() do { (current)->trace_recursion++; } while (0)
-#define trace_recursion_dec() do { (current)->trace_recursion--; } while (0)
-
-/* Ring buffer has the 10 LSB bits to count */
-#define trace_recursion_buffer() ((current)->trace_recursion & 0x3ff)
-
-/* for function tracing recursion */
-#define TRACE_INTERNAL_BIT		(1<<11)
-#define TRACE_GLOBAL_BIT		(1<<12)
-
-#define trace_recursion_set(bit)	do { (current)->trace_recursion |= (bit); } while (0)
-#define trace_recursion_clear(bit)	do { (current)->trace_recursion &= ~(bit); } while (0)
-#define trace_recursion_test(bit)	((current)->trace_recursion & (bit))
-
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index e32744c84d9..93365907f21 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -161,7 +161,8 @@ FTRACE_ENTRY(kernel_stack, stack_entry,
 	TRACE_STACK,
 
 	F_STRUCT(
-		__array(	unsigned long,	caller, FTRACE_STACK_ENTRIES	)
+		__field(	int,		size	)
+		__dynamic_array(unsigned long,	caller	)
 	),
 
 	F_printk("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n"
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index e8d6bb55d71..a7d2a4c653d 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -227,7 +227,7 @@ int __trace_graph_entry(struct trace_array *tr,
 
 static inline int ftrace_graph_ignore_irqs(void)
 {
-	if (!ftrace_graph_skip_irqs)
+	if (!ftrace_graph_skip_irqs || trace_recursion_test(TRACE_IRQ_BIT))
 		return 0;
 
 	return in_irq();
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 7db7b68c6c3..5fb3697bf0e 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -343,6 +343,14 @@ DEFINE_BASIC_FETCH_FUNCS(deref)
 DEFINE_FETCH_deref(string)
 DEFINE_FETCH_deref(string_size)
 
+static __kprobes void update_deref_fetch_param(struct deref_fetch_param *data)
+{
+	if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
+		update_deref_fetch_param(data->orig.data);
+	else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
+		update_symbol_cache(data->orig.data);
+}
+
 static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data)
 {
 	if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
@@ -377,6 +385,19 @@ DEFINE_BASIC_FETCH_FUNCS(bitfield)
 #define fetch_bitfield_string_size NULL
 
 static __kprobes void
+update_bitfield_fetch_param(struct bitfield_fetch_param *data)
+{
+	/*
+	 * Don't check the bitfield itself, because this must be the
+	 * last fetch function.
+	 */
+	if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
+		update_deref_fetch_param(data->orig.data);
+	else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
+		update_symbol_cache(data->orig.data);
+}
+
+static __kprobes void
 free_bitfield_fetch_param(struct bitfield_fetch_param *data)
 {
 	/*
@@ -389,6 +410,7 @@ free_bi