Merge branch 'tip/perf/core' of git://git.kernel.org/pub/scm/linux/ke…

…rnel/git/rostedt/linux-2.6-trace into perf/core

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.

arch/x86/include/asm/perf_event_p4.h

@@ -101,6 +101,14 @@
 #define P4_CONFIG_HT_SHIFT		63
 #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
  */
@@ -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);

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.

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,
 	/*

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;
 

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 @@ int __kprobes register_kprobe(struct kprobe *p)
 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)