From 02fd7f68f5342bc7e8054cb05ea4a07f26d41d12 Mon Sep 17 00:00:00 2001
From: Jeremy Linton <jeremy.linton@arm.com>
Date: Wed, 31 May 2017 16:56:42 -0500
Subject: trace: rename kernel enum section to eval

The kernel and its modules have sections containing the enum
string to value conversions. Rename this section because we
intend to store more than enums in it.

Link: http://lkml.kernel.org/r/20170531215653.3240-2-jeremy.linton@arm.com

Signed-off-by: Jeremy Linton <jeremy.linton@arm.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/asm-generic/vmlinux.lds.h | 6 +++---
 include/trace/trace_events.h      | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 314a0b9219c6..800f9f9677a6 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -125,9 +125,9 @@
 			VMLINUX_SYMBOL(__start_ftrace_events) = .;	\
 			KEEP(*(_ftrace_events))				\
 			VMLINUX_SYMBOL(__stop_ftrace_events) = .;	\
-			VMLINUX_SYMBOL(__start_ftrace_enum_maps) = .;	\
-			KEEP(*(_ftrace_enum_map))			\
-			VMLINUX_SYMBOL(__stop_ftrace_enum_maps) = .;
+			VMLINUX_SYMBOL(__start_ftrace_eval_maps) = .;	\
+			KEEP(*(_ftrace_eval_map))			\
+			VMLINUX_SYMBOL(__stop_ftrace_eval_maps) = .;
 #else
 #define FTRACE_EVENTS()
 #endif
diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h
index 00f643164ca2..4bdd84023f5b 100644
--- a/include/trace/trace_events.h
+++ b/include/trace/trace_events.h
@@ -43,7 +43,7 @@ TRACE_MAKE_SYSTEM_STR();
 		.enum_value = a				\
 	};						\
 	static struct trace_enum_map __used		\
-	__attribute__((section("_ftrace_enum_map")))	\
+	__attribute__((section("_ftrace_eval_map")))	\
 	*TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a
 
 /*
-- 
cgit v1.2.3


From 00f4b652b6f1dbfd4e1d5419d7f1cc23b1374da8 Mon Sep 17 00:00:00 2001
From: Jeremy Linton <jeremy.linton@arm.com>
Date: Wed, 31 May 2017 16:56:43 -0500
Subject: trace: rename trace_enum_map to trace_eval_map

Each enum is loaded into the trace_enum_map, as we
are now using this for more than enums rename it.

Link: http://lkml.kernel.org/r/20170531215653.3240-3-jeremy.linton@arm.com

Signed-off-by: Jeremy Linton <jeremy.linton@arm.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/module.h       |  2 +-
 include/linux/tracepoint.h   |  6 +++---
 include/trace/trace_events.h |  8 ++++----
 kernel/trace/trace.c         | 24 ++++++++++++------------
 kernel/trace/trace.h         |  4 ++--
 kernel/trace/trace_events.c  | 14 +++++++-------
 6 files changed, 29 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/include/linux/module.h b/include/linux/module.h
index 21f56393602f..46b48043d741 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -442,7 +442,7 @@ struct module {
 #ifdef CONFIG_EVENT_TRACING
 	struct trace_event_call **trace_events;
 	unsigned int num_trace_events;
-	struct trace_enum_map **trace_enums;
+	struct trace_eval_map **trace_enums;
 	unsigned int num_trace_enums;
 #endif
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index cc48cb2ce209..f7b0f5525e46 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -25,10 +25,10 @@ struct module;
 struct tracepoint;
 struct notifier_block;
 
-struct trace_enum_map {
+struct trace_eval_map {
 	const char		*system;
-	const char		*enum_string;
-	unsigned long		enum_value;
+	const char		*eval_string;
+	unsigned long		eval_value;
 };
 
 #define TRACEPOINT_DEFAULT_PRIO	10
diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h
index 4bdd84023f5b..49cce5fb54ee 100644
--- a/include/trace/trace_events.h
+++ b/include/trace/trace_events.h
@@ -35,14 +35,14 @@ TRACE_MAKE_SYSTEM_STR();
 
 #undef TRACE_DEFINE_ENUM
 #define TRACE_DEFINE_ENUM(a)				\
-	static struct trace_enum_map __used __initdata	\
+	static struct trace_eval_map __used __initdata	\
 	__##TRACE_SYSTEM##_##a =			\
 	{						\
 		.system = TRACE_SYSTEM_STRING,		\
-		.enum_string = #a,			\
-		.enum_value = a				\
+		.eval_string = #a,			\
+		.eval_value = a				\
 	};						\
-	static struct trace_enum_map __used		\
+	static struct trace_eval_map __used		\
 	__attribute__((section("_ftrace_eval_map")))	\
 	*TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index acd3eb4d56a0..46fac3f63af1 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -132,7 +132,7 @@ union trace_enum_map_item;
 struct trace_enum_map_tail {
 	/*
 	 * "end" is first and points to NULL as it must be different
-	 * than "mod" or "enum_string"
+	 * than "mod" or "eval_string"
 	 */
 	union trace_enum_map_item	*next;
 	const char			*end;	/* points to NULL */
@@ -148,7 +148,7 @@ static DEFINE_MUTEX(trace_enum_mutex);
  * pointer to the next array of saved enum_map items.
  */
 union trace_enum_map_item {
-	struct trace_enum_map		map;
+	struct trace_eval_map		map;
 	struct trace_enum_map_head	head;
 	struct trace_enum_map_tail	tail;
 };
@@ -4748,7 +4748,7 @@ static const struct file_operations tracing_saved_cmdlines_size_fops = {
 static union trace_enum_map_item *
 update_enum_map(union trace_enum_map_item *ptr)
 {
-	if (!ptr->map.enum_string) {
+	if (!ptr->map.eval_string) {
 		if (ptr->tail.next) {
 			ptr = ptr->tail.next;
 			/* Set ptr to the next real item (skip head) */
@@ -4808,7 +4808,7 @@ static int enum_map_show(struct seq_file *m, void *v)
 	union trace_enum_map_item *ptr = v;
 
 	seq_printf(m, "%s %ld (%s)\n",
-		   ptr->map.enum_string, ptr->map.enum_value,
+		   ptr->map.eval_string, ptr->map.eval_value,
 		   ptr->map.system);
 
 	return 0;
@@ -4844,11 +4844,11 @@ trace_enum_jmp_to_tail(union trace_enum_map_item *ptr)
 }
 
 static void
-trace_insert_enum_map_file(struct module *mod, struct trace_enum_map **start,
+trace_insert_enum_map_file(struct module *mod, struct trace_eval_map **start,
 			   int len)
 {
-	struct trace_enum_map **stop;
-	struct trace_enum_map **map;
+	struct trace_eval_map **stop;
+	struct trace_eval_map **map;
 	union trace_enum_map_item *map_array;
 	union trace_enum_map_item *ptr;
 
@@ -4902,13 +4902,13 @@ static void trace_create_enum_file(struct dentry *d_tracer)
 #else /* CONFIG_TRACE_ENUM_MAP_FILE */
 static inline void trace_create_enum_file(struct dentry *d_tracer) { }
 static inline void trace_insert_enum_map_file(struct module *mod,
-			      struct trace_enum_map **start, int len) { }
+			      struct trace_eval_map **start, int len) { }
 #endif /* !CONFIG_TRACE_ENUM_MAP_FILE */
 
 static void trace_insert_enum_map(struct module *mod,
-				  struct trace_enum_map **start, int len)
+				  struct trace_eval_map **start, int len)
 {
-	struct trace_enum_map **map;
+	struct trace_eval_map **map;
 
 	if (len <= 0)
 		return;
@@ -7732,8 +7732,8 @@ struct dentry *tracing_init_dentry(void)
 	return NULL;
 }
 
-extern struct trace_enum_map *__start_ftrace_eval_maps[];
-extern struct trace_enum_map *__stop_ftrace_eval_maps[];
+extern struct trace_eval_map *__start_ftrace_eval_maps[];
+extern struct trace_eval_map *__stop_ftrace_eval_maps[];
 
 static void __init trace_enum_init(void)
 {
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 39fd77330aab..a9667297ae49 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1773,10 +1773,10 @@ static inline const char *get_syscall_name(int syscall)
 
 #ifdef CONFIG_EVENT_TRACING
 void trace_event_init(void);
-void trace_event_enum_update(struct trace_enum_map **map, int len);
+void trace_event_enum_update(struct trace_eval_map **map, int len);
 #else
 static inline void __init trace_event_init(void) { }
-static inline void trace_event_enum_update(struct trace_enum_map **map, int len) { }
+static inline void trace_event_enum_update(struct trace_eval_map **map, int len) { }
 #endif
 
 extern struct trace_iterator *tracepoint_print_iter;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index e7973e10398c..cf5b9aa4d732 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2067,18 +2067,18 @@ __register_event(struct trace_event_call *call, struct module *mod)
 	return 0;
 }
 
-static char *enum_replace(char *ptr, struct trace_enum_map *map, int len)
+static char *enum_replace(char *ptr, struct trace_eval_map *map, int len)
 {
 	int rlen;
 	int elen;
 
 	/* Find the length of the enum value as a string */
-	elen = snprintf(ptr, 0, "%ld", map->enum_value);
+	elen = snprintf(ptr, 0, "%ld", map->eval_value);
 	/* Make sure there's enough room to replace the string with the value */
 	if (len < elen)
 		return NULL;
 
-	snprintf(ptr, elen + 1, "%ld", map->enum_value);
+	snprintf(ptr, elen + 1, "%ld", map->eval_value);
 
 	/* Get the rest of the string of ptr */
 	rlen = strlen(ptr + len);
@@ -2090,11 +2090,11 @@ static char *enum_replace(char *ptr, struct trace_enum_map *map, int len)
 }
 
 static void update_event_printk(struct trace_event_call *call,
-				struct trace_enum_map *map)
+				struct trace_eval_map *map)
 {
 	char *ptr;
 	int quote = 0;
-	int len = strlen(map->enum_string);
+	int len = strlen(map->eval_string);
 
 	for (ptr = call->print_fmt; *ptr; ptr++) {
 		if (*ptr == '\\') {
@@ -2125,7 +2125,7 @@ static void update_event_printk(struct trace_event_call *call,
 			continue;
 		}
 		if (isalpha(*ptr) || *ptr == '_') {
-			if (strncmp(map->enum_string, ptr, len) == 0 &&
+			if (strncmp(map->eval_string, ptr, len) == 0 &&
 			    !isalnum(ptr[len]) && ptr[len] != '_') {
 				ptr = enum_replace(ptr, map, len);
 				/* Hmm, enum string smaller than value */
@@ -2165,7 +2165,7 @@ static void update_event_printk(struct trace_event_call *call,
 	}
 }
 
-void trace_event_enum_update(struct trace_enum_map **map, int len)
+void trace_event_enum_update(struct trace_eval_map **map, int len)
 {
 	struct trace_event_call *call, *p;
 	const char *last_system = NULL;
-- 
cgit v1.2.3


From 99be647c5841d570a23b5dfa65bfecada8b6e6b5 Mon Sep 17 00:00:00 2001
From: Jeremy Linton <jeremy.linton@arm.com>
Date: Wed, 31 May 2017 16:56:44 -0500
Subject: trace: rename struct module entry for trace enums

Each module has a list of enum's its contributing to the
enum map, rename that entry to reflect its use by more than
enums.

Link: http://lkml.kernel.org/r/20170531215653.3240-4-jeremy.linton@arm.com

Signed-off-by: Jeremy Linton <jeremy.linton@arm.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/module.h | 4 ++--
 kernel/module.c        | 6 +++---
 kernel/trace/trace.c   | 6 +++---
 3 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/module.h b/include/linux/module.h
index 46b48043d741..8eb9a1e693e5 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -442,8 +442,8 @@ struct module {
 #ifdef CONFIG_EVENT_TRACING
 	struct trace_event_call **trace_events;
 	unsigned int num_trace_events;
-	struct trace_eval_map **trace_enums;
-	unsigned int num_trace_enums;
+	struct trace_eval_map **trace_evals;
+	unsigned int num_trace_evals;
 #endif
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 	unsigned int num_ftrace_callsites;
diff --git a/kernel/module.c b/kernel/module.c
index 9ec4713c5eee..df1c4a9e7abb 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3077,9 +3077,9 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 	mod->trace_events = section_objs(info, "_ftrace_events",
 					 sizeof(*mod->trace_events),
 					 &mod->num_trace_events);
-	mod->trace_enums = section_objs(info, "_ftrace_eval_map",
-					sizeof(*mod->trace_enums),
-					&mod->num_trace_enums);
+	mod->trace_evals = section_objs(info, "_ftrace_eval_map",
+					sizeof(*mod->trace_evals),
+					&mod->num_trace_evals);
 #endif
 #ifdef CONFIG_TRACING
 	mod->trace_bprintk_fmt_start = section_objs(info, "__trace_printk_fmt",
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 46fac3f63af1..061abd8ba101 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -7746,7 +7746,7 @@ static void __init trace_enum_init(void)
 #ifdef CONFIG_MODULES
 static void trace_module_add_enums(struct module *mod)
 {
-	if (!mod->num_trace_enums)
+	if (!mod->num_trace_evals)
 		return;
 
 	/*
@@ -7756,7 +7756,7 @@ static void trace_module_add_enums(struct module *mod)
 	if (trace_module_has_bad_taint(mod))
 		return;
 
-	trace_insert_enum_map(mod, mod->trace_enums, mod->num_trace_enums);
+	trace_insert_enum_map(mod, mod->trace_evals, mod->num_trace_evals);
 }
 
 #ifdef CONFIG_TRACE_ENUM_MAP_FILE
@@ -7765,7 +7765,7 @@ static void trace_module_remove_enums(struct module *mod)
 	union trace_enum_map_item *map;
 	union trace_enum_map_item **last = &trace_enum_maps;
 
-	if (!mod->num_trace_enums)
+	if (!mod->num_trace_evals)
 		return;
 
 	mutex_lock(&trace_enum_mutex);
-- 
cgit v1.2.3


From 4f0dfd76e9cc9296d74d6d5f579a5c7ca3bed869 Mon Sep 17 00:00:00 2001
From: Jeremy Linton <jeremy.linton@arm.com>
Date: Wed, 31 May 2017 16:56:50 -0500
Subject: tracing: define TRACE_DEFINE_SIZEOF() macro to map sizeof's to their
 values

Perf has a problem that if sizeof() macros are used within TRACE_EVENT()
macro's they end up in userspace as "sizeof(kernel structure)" which
cannot properly be parsed. Add a macro which can forward this data
through the eval_map for userspace utilization.

Link: http://lkml.kernel.org/r/20170531215653.3240-10-jeremy.linton@arm.com

Signed-off-by: Jeremy Linton <jeremy.linton@arm.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/tracepoint.h   |  1 +
 include/trace/trace_events.h | 16 ++++++++++++++++
 2 files changed, 17 insertions(+)

(limited to 'include')

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index f7b0f5525e46..a26ffbe09e71 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -88,6 +88,7 @@ extern void syscall_unregfunc(void);
 #define PARAMS(args...) args
 
 #define TRACE_DEFINE_ENUM(x)
+#define TRACE_DEFINE_SIZEOF(x)
 
 #endif /* _LINUX_TRACEPOINT_H */
 
diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h
index 49cce5fb54ee..3976fa1f6e42 100644
--- a/include/trace/trace_events.h
+++ b/include/trace/trace_events.h
@@ -46,6 +46,19 @@ TRACE_MAKE_SYSTEM_STR();
 	__attribute__((section("_ftrace_eval_map")))	\
 	*TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a
 
+#undef TRACE_DEFINE_SIZEOF
+#define TRACE_DEFINE_SIZEOF(a)				\
+	static struct trace_eval_map __used __initdata	\
+	__##TRACE_SYSTEM##_##a =			\
+	{						\
+		.system = TRACE_SYSTEM_STRING,		\
+		.eval_string = "sizeof(" #a ")",	\
+		.eval_value = sizeof(a)			\
+	};						\
+	static struct trace_eval_map __used		\
+	__attribute__((section("_ftrace_eval_map")))	\
+	*TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a
+
 /*
  * DECLARE_EVENT_CLASS can be used to add a generic function
  * handlers for events. That is, if all events have the same
@@ -158,6 +171,9 @@ TRACE_MAKE_SYSTEM_STR();
 #undef TRACE_DEFINE_ENUM
 #define TRACE_DEFINE_ENUM(a)
 
+#undef TRACE_DEFINE_SIZEOF
+#define TRACE_DEFINE_SIZEOF(a)
+
 #undef __field
 #define __field(type, item)
 
-- 
cgit v1.2.3


From ff910cfdc6e928c31344245cca70e391634ba560 Mon Sep 17 00:00:00 2001
From: Jeremy Linton <jeremy.linton@arm.com>
Date: Wed, 31 May 2017 16:56:52 -0500
Subject: tracing: Add TRACE_DEFINE_SIZEOF() macros

There are a few places in the kernel where sizeof() is already
being used. Update those locations with TRACE_DEFINE_SIZEOF.

Link: http://lkml.kernel.org/r/20170531215653.3240-12-jeremy.linton@arm.com

Signed-off-by: Jeremy Linton <jeremy.linton@arm.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 arch/arm64/kvm/trace.h     |  2 ++
 include/trace/events/xen.h | 13 +++++++++++--
 2 files changed, 13 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/kvm/trace.h b/arch/arm64/kvm/trace.h
index 7fb0008c4fa3..5188c7007169 100644
--- a/arch/arm64/kvm/trace.h
+++ b/arch/arm64/kvm/trace.h
@@ -93,6 +93,8 @@ TRACE_EVENT(kvm_arm_set_dreg32,
 	TP_printk("%s: 0x%08x", __entry->name, __entry->value)
 );
 
+TRACE_DEFINE_SIZEOF(__u64);
+
 TRACE_EVENT(kvm_arm_set_regset,
 	TP_PROTO(const char *type, int len, __u64 *control, __u64 *value),
 	TP_ARGS(type, len, control, value),
diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h
index 31acce9019a6..b70a38b7fa84 100644
--- a/include/trace/events/xen.h
+++ b/include/trace/events/xen.h
@@ -30,6 +30,8 @@ DECLARE_EVENT_CLASS(xen_mc__batch,
 DEFINE_XEN_MC_BATCH(xen_mc_batch);
 DEFINE_XEN_MC_BATCH(xen_mc_issue);
 
+TRACE_DEFINE_SIZEOF(ulong);
+
 TRACE_EVENT(xen_mc_entry,
 	    TP_PROTO(struct multicall_entry *mc, unsigned nargs),
 	    TP_ARGS(mc, nargs),
@@ -40,8 +42,8 @@ TRACE_EVENT(xen_mc_entry,
 		    ),
 	    TP_fast_assign(__entry->op = mc->op;
 			   __entry->nargs = nargs;
-			   memcpy(__entry->args, mc->args, sizeof(unsigned long) * nargs);
-			   memset(__entry->args + nargs, 0, sizeof(unsigned long) * (6 - nargs));
+			   memcpy(__entry->args, mc->args, sizeof(ulong) * nargs);
+			   memset(__entry->args + nargs, 0, sizeof(ulong) * (6 - nargs));
 		    ),
 	    TP_printk("op %u%s args [%lx, %lx, %lx, %lx, %lx, %lx]",
 		      __entry->op, xen_hypercall_name(__entry->op),
@@ -122,6 +124,7 @@ TRACE_EVENT(xen_mc_extend_args,
 		      __entry->res == XEN_MC_XE_NO_SPACE ? "NO_SPACE" : "???")
 	);
 
+TRACE_DEFINE_SIZEOF(pteval_t);
 /* mmu */
 DECLARE_EVENT_CLASS(xen_mmu__set_pte,
 	    TP_PROTO(pte_t *ptep, pte_t pteval),
@@ -199,6 +202,8 @@ TRACE_EVENT(xen_mmu_pte_clear,
 		      __entry->mm, __entry->addr, __entry->ptep)
 	);
 
+TRACE_DEFINE_SIZEOF(pmdval_t);
+
 TRACE_EVENT(xen_mmu_set_pmd,
 	    TP_PROTO(pmd_t *pmdp, pmd_t pmdval),
 	    TP_ARGS(pmdp, pmdval),
@@ -226,6 +231,8 @@ TRACE_EVENT(xen_mmu_pmd_clear,
 
 #if CONFIG_PGTABLE_LEVELS >= 4
 
+TRACE_DEFINE_SIZEOF(pudval_t);
+
 TRACE_EVENT(xen_mmu_set_pud,
 	    TP_PROTO(pud_t *pudp, pud_t pudval),
 	    TP_ARGS(pudp, pudval),
@@ -241,6 +248,8 @@ TRACE_EVENT(xen_mmu_set_pud,
 		      (int)sizeof(pudval_t) * 2, (unsigned long long)__entry->pudval)
 	);
 
+TRACE_DEFINE_SIZEOF(p4dval_t);
+
 TRACE_EVENT(xen_mmu_set_p4d,
 	    TP_PROTO(p4d_t *p4dp, p4d_t *user_p4dp, p4d_t p4dval),
 	    TP_ARGS(p4dp, user_p4dp, p4dval),
-- 
cgit v1.2.3


From d0ba52f1d7649a3f088e410e860559cf36d479d0 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Wed, 21 Jun 2017 13:39:13 -0400
Subject: ftrace: Add missing comment for FTRACE_OPS_FL_RCU

All the enum flags for FTRACE_OPS has a comment except for the RCU one. Add
the comment for that.

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/ftrace.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 473f088aabea..1b6992e994e6 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -119,6 +119,7 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
  *            for any of the functions that this ops will be registered for, then
  *            this ops will fail to register or set_filter_ip.
  * PID     - Is affected by set_ftrace_pid (allows filtering on those pids)
+ * RCU     - Set when the ops can only be called when RCU is watching.
  */
 enum {
 	FTRACE_OPS_FL_ENABLED			= 1 << 0,
-- 
cgit v1.2.3


From 5985ea8bd5d1b820b909af49fbc2767a990080a6 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Fri, 23 Jun 2017 16:05:11 -0400
Subject: ftrace: Have the cached module list show in set_ftrace_filter

When writing in a module filter into set_ftrace_filter for a module that is
not yet loaded, it it cached, and will be executed when the module is loaded
(although that is not implemented yet at this commit). Display the list of
cached modules to be traced.

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/ftrace.h |   3 +-
 kernel/trace/ftrace.c  | 112 +++++++++++++++++++++++++++++++++++++++++++------
 2 files changed, 102 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 1b6992e994e6..9fb9a67dc9d4 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -446,7 +446,8 @@ enum {
 	FTRACE_ITER_PRINTALL	= (1 << 2),
 	FTRACE_ITER_DO_PROBES	= (1 << 3),
 	FTRACE_ITER_PROBE	= (1 << 4),
-	FTRACE_ITER_ENABLED	= (1 << 5),
+	FTRACE_ITER_MOD		= (1 << 5),
+	FTRACE_ITER_ENABLED	= (1 << 6),
 };
 
 void arch_ftrace_update_code(int command);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 1867edec6269..bfdbce78064b 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3112,6 +3112,7 @@ ftrace_allocate_pages(unsigned long num_to_init)
 struct ftrace_iterator {
 	loff_t				pos;
 	loff_t				func_pos;
+	loff_t				mod_pos;
 	struct ftrace_page		*pg;
 	struct dyn_ftrace		*func;
 	struct ftrace_func_probe	*probe;
@@ -3119,6 +3120,8 @@ struct ftrace_iterator {
 	struct trace_parser		parser;
 	struct ftrace_hash		*hash;
 	struct ftrace_ops		*ops;
+	struct trace_array		*tr;
+	struct list_head		*mod_list;
 	int				pidx;
 	int				idx;
 	unsigned			flags;
@@ -3203,13 +3206,13 @@ static void *t_probe_start(struct seq_file *m, loff_t *pos)
 	if (!(iter->flags & FTRACE_ITER_DO_PROBES))
 		return NULL;
 
-	if (iter->func_pos > *pos)
+	if (iter->mod_pos > *pos)
 		return NULL;
 
 	iter->probe = NULL;
 	iter->probe_entry = NULL;
 	iter->pidx = 0;
-	for (l = 0; l <= (*pos - iter->func_pos); ) {
+	for (l = 0; l <= (*pos - iter->mod_pos); ) {
 		p = t_probe_next(m, &l);
 		if (!p)
 			break;
@@ -3247,6 +3250,82 @@ t_probe_show(struct seq_file *m, struct ftrace_iterator *iter)
 	return 0;
 }
 
+static void *
+t_mod_next(struct seq_file *m, loff_t *pos)
+{
+	struct ftrace_iterator *iter = m->private;
+	struct trace_array *tr = iter->tr;
+
+	(*pos)++;
+	iter->pos = *pos;
+
+	iter->mod_list = iter->mod_list->next;
+
+	if (iter->mod_list == &tr->mod_trace ||
+	    iter->mod_list == &tr->mod_notrace) {
+		iter->flags &= ~FTRACE_ITER_MOD;
+		return NULL;
+	}
+
+	iter->mod_pos = *pos;
+
+	return iter;
+}
+
+static void *t_mod_start(struct seq_file *m, loff_t *pos)
+{
+	struct ftrace_iterator *iter = m->private;
+	void *p = NULL;
+	loff_t l;
+
+	if (iter->func_pos > *pos)
+		return NULL;
+
+	iter->mod_pos = iter->func_pos;
+
+	/* probes are only available if tr is set */
+	if (!iter->tr)
+		return NULL;
+
+	for (l = 0; l <= (*pos - iter->func_pos); ) {
+		p = t_mod_next(m, &l);
+		if (!p)
+			break;
+	}
+	if (!p) {
+		iter->flags &= ~FTRACE_ITER_MOD;
+		return t_probe_start(m, pos);
+	}
+
+	/* Only set this if we have an item */
+	iter->flags |= FTRACE_ITER_MOD;
+
+	return iter;
+}
+
+static int
+t_mod_show(struct seq_file *m, struct ftrace_iterator *iter)
+{
+	struct ftrace_mod_load *ftrace_mod;
+	struct trace_array *tr = iter->tr;
+
+	if (WARN_ON_ONCE(!iter->mod_list) ||
+			 iter->mod_list == &tr->mod_trace ||
+			 iter->mod_list == &tr->mod_notrace)
+		return -EIO;
+
+	ftrace_mod = list_entry(iter->mod_list, struct ftrace_mod_load, list);
+
+	if (ftrace_mod->func)
+		seq_printf(m, "%s", ftrace_mod->func);
+	else
+		seq_putc(m, '*');
+
+	seq_printf(m, ":mod:%s\n", ftrace_mod->module);
+
+	return 0;
+}
+
 static void *
 t_func_next(struct seq_file *m, loff_t *pos)
 {
@@ -3288,7 +3367,7 @@ static void *
 t_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct ftrace_iterator *iter = m->private;
-	loff_t l = *pos; /* t_hash_start() must use original pos */
+	loff_t l = *pos; /* t_probe_start() must use original pos */
 	void *ret;
 
 	if (unlikely(ftrace_disabled))
@@ -3297,16 +3376,19 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 	if (iter->flags & FTRACE_ITER_PROBE)
 		return t_probe_next(m, pos);
 
+	if (iter->flags & FTRACE_ITER_MOD)
+		return t_mod_next(m, pos);
+
 	if (iter->flags & FTRACE_ITER_PRINTALL) {
 		/* next must increment pos, and t_probe_start does not */
 		(*pos)++;
-		return t_probe_start(m, &l);
+		return t_mod_start(m, &l);
 	}
 
 	ret = t_func_next(m, pos);
 
 	if (!ret)
-		return t_probe_start(m, &l);
+		return t_mod_start(m, &l);
 
 	return ret;
 }
@@ -3315,7 +3397,7 @@ static void reset_iter_read(struct ftrace_iterator *iter)
 {
 	iter->pos = 0;
 	iter->func_pos = 0;
-	iter->flags &= ~(FTRACE_ITER_PRINTALL | FTRACE_ITER_PROBE);
+	iter->flags &= ~(FTRACE_ITER_PRINTALL | FTRACE_ITER_PROBE | FTRACE_ITER_MOD);
 }
 
 static void *t_start(struct seq_file *m, loff_t *pos)
@@ -3344,15 +3426,15 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 	    ftrace_hash_empty(iter->hash)) {
 		iter->func_pos = 1; /* Account for the message */
 		if (*pos > 0)
-			return t_probe_start(m, pos);
+			return t_mod_start(m, pos);
 		iter->flags |= FTRACE_ITER_PRINTALL;
 		/* reset in case of seek/pread */
 		iter->flags &= ~FTRACE_ITER_PROBE;
 		return iter;
 	}
 
-	if (iter->flags & FTRACE_ITER_PROBE)
-		return t_probe_start(m, pos);
+	if (iter->flags & FTRACE_ITER_MOD)
+		return t_mod_start(m, pos);
 
 	/*
 	 * Unfortunately, we need to restart at ftrace_pages_start
@@ -3368,7 +3450,7 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 	}
 
 	if (!p)
-		return t_probe_start(m, pos);
+		return t_mod_start(m, pos);
 
 	return iter;
 }
@@ -3402,6 +3484,9 @@ static int t_show(struct seq_file *m, void *v)
 	if (iter->flags & FTRACE_ITER_PROBE)
 		return t_probe_show(m, iter);
 
+	if (iter->flags & FTRACE_ITER_MOD)
+		return t_mod_show(m, iter);
+
 	if (iter->flags & FTRACE_ITER_PRINTALL) {
 		if (iter->flags & FTRACE_ITER_NOTRACE)
 			seq_puts(m, "#### no functions disabled ####\n");
@@ -3528,17 +3613,20 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
 
 	iter->ops = ops;
 	iter->flags = flag;
+	iter->tr = tr;
 
 	mutex_lock(&ops->func_hash->regex_lock);
 
 	if (flag & FTRACE_ITER_NOTRACE) {
 		hash = ops->func_hash->notrace_hash;
-		mod_head = tr ? &tr->mod_trace : NULL;
+		mod_head = tr ? &tr->mod_notrace : NULL;
 	} else {
 		hash = ops->func_hash->filter_hash;
-		mod_head = tr ? &tr->mod_notrace : NULL;
+		mod_head = tr ? &tr->mod_trace : NULL;
 	}
 
+	iter->mod_list = mod_head;
+
 	if (file->f_mode & FMODE_WRITE) {
 		const int size_bits = FTRACE_HASH_DEFAULT_BITS;
 
-- 
cgit v1.2.3


From 8c08f0d5c6fb10ff93ffb1cbf416f4f1c3a52a80 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Mon, 26 Jun 2017 11:47:31 -0400
Subject: ftrace: Have cached module filters be an active filter

When a module filter is added to set_ftrace_filter, if the module is not
loaded, it is cached. This should be considered an active filter, and
function tracing should be filtered by this. That is, if a cached module
filter is the only filter set, then no function tracing should be happening,
as all the functions available will be filtered out.

This makes sense, as the reason to add a cached module filter, is to trace
the module when you load it. There shouldn't be any other tracing happening
until then.

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/ftrace.h |  2 ++
 kernel/trace/ftrace.c  | 20 +++++++++++++++-----
 kernel/trace/trace.h   |  7 ++++++-
 3 files changed, 23 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 9fb9a67dc9d4..5857390ac35a 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -120,6 +120,7 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
  *            this ops will fail to register or set_filter_ip.
  * PID     - Is affected by set_ftrace_pid (allows filtering on those pids)
  * RCU     - Set when the ops can only be called when RCU is watching.
+ * TRACE_ARRAY - The ops->private points to a trace_array descriptor.
  */
 enum {
 	FTRACE_OPS_FL_ENABLED			= 1 << 0,
@@ -138,6 +139,7 @@ enum {
 	FTRACE_OPS_FL_IPMODIFY			= 1 << 13,
 	FTRACE_OPS_FL_PID			= 1 << 14,
 	FTRACE_OPS_FL_RCU			= 1 << 15,
+	FTRACE_OPS_FL_TRACE_ARRAY		= 1 << 16,
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f1ccf8be9df7..914539e3e301 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1410,6 +1410,9 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash)
 	if (!new_hash)
 		return NULL;
 
+	if (hash)
+		new_hash->flags = hash->flags;
+
 	/* Empty hash? */
 	if (ftrace_hash_empty(hash))
 		return new_hash;
@@ -1454,7 +1457,7 @@ __ftrace_hash_move(struct ftrace_hash *src)
 	/*
 	 * If the new source is empty, just return the empty_hash.
 	 */
-	if (!src->count)
+	if (ftrace_hash_empty(src))
 		return EMPTY_HASH;
 
 	/*
@@ -1471,6 +1474,8 @@ __ftrace_hash_move(struct ftrace_hash *src)
 	if (!new_hash)
 		return NULL;
 
+	new_hash->flags = src->flags;
+
 	size = 1 << src->size_bits;
 	for (i = 0; i < size; i++) {
 		hhd = &src->buckets[i];
@@ -1701,7 +1706,7 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
 	struct dyn_ftrace *rec;
 	bool update = false;
 	int count = 0;
-	int all = 0;
+	int all = false;
 
 	/* Only update if the ops has been registered */
 	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
@@ -1722,7 +1727,7 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
 		hash = ops->func_hash->filter_hash;
 		other_hash = ops->func_hash->notrace_hash;
 		if (ftrace_hash_empty(hash))
-			all = 1;
+			all = true;
 	} else {
 		inc = !inc;
 		hash = ops->func_hash->notrace_hash;
@@ -4028,6 +4033,9 @@ static void process_mod_list(struct list_head *head, struct ftrace_ops *ops,
 		free_ftrace_mod(ftrace_mod);
 	}
 
+	if (enable && list_empty(head))
+		new_hash->flags &= ~FTRACE_HASH_FL_MOD;
+
 	mutex_lock(&ftrace_lock);
 
 	ret = ftrace_hash_move_and_update_ops(ops, orig_hash,
@@ -5035,9 +5043,11 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
 	if (file->f_mode & FMODE_WRITE) {
 		filter_hash = !!(iter->flags & FTRACE_ITER_FILTER);
 
-		if (filter_hash)
+		if (filter_hash) {
 			orig_hash = &iter->ops->func_hash->filter_hash;
-		else
+			if (!list_empty(&iter->tr->mod_trace))
+				iter->hash->flags |= FTRACE_HASH_FL_MOD;
+		} else
 			orig_hash = &iter->ops->func_hash->notrace_hash;
 
 		mutex_lock(&ftrace_lock);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index d63550cdbdfa..13823951e42b 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -773,10 +773,15 @@ struct ftrace_mod_load {
 	int			 enable;
 };
 
+enum {
+	FTRACE_HASH_FL_MOD	= (1 << 0),
+};
+
 struct ftrace_hash {
 	unsigned long		size_bits;
 	struct hlist_head	*buckets;
 	unsigned long		count;
+	unsigned long		flags;
 	struct rcu_head		rcu;
 };
 
@@ -785,7 +790,7 @@ ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip);
 
 static __always_inline bool ftrace_hash_empty(struct ftrace_hash *hash)
 {
-	return !hash || !hash->count;
+	return !hash || !(hash->count || (hash->flags & FTRACE_HASH_FL_MOD));
 }
 
 /* Standard output formatting function used for function return traces */
-- 
cgit v1.2.3


From d914ba37d7145acb9fd3bb23075c2d56e5a44eb6 Mon Sep 17 00:00:00 2001
From: Joel Fernandes <joelaf@google.com>
Date: Mon, 26 Jun 2017 19:01:55 -0700
Subject: tracing: Add support for recording tgid of tasks

Inorder to support recording of tgid, the following changes are made:

* Introduce a new API (tracing_record_taskinfo) to additionally record the tgid
  along with the task's comm at the same time. This has has the benefit of not
  setting trace_cmdline_save before all the information for a task is saved.
* Add a new API tracing_record_taskinfo_sched_switch to record task information
  for 2 tasks at a time (previous and next) and use it from sched_switch probe.
* Preserve the old API (tracing_record_cmdline) and create it as a wrapper
  around the new one so that existing callers aren't affected.
* Reuse the existing sched_switch and sched_wakeup probes to record tgid
  information and add a new option 'record-tgid' to enable recording of tgid

When record-tgid option isn't enabled to being with, we take care to make sure
that there's isn't memory or runtime overhead.

Link: http://lkml.kernel.org/r/20170627020155.5139-1-joelaf@google.com

Cc: kernel-team@android.com
Cc: Ingo Molnar <mingo@redhat.com>
Tested-by: Michael Sartain <mikesart@gmail.com>
Signed-off-by: Joel Fernandes <joelaf@google.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/trace_events.h      |  13 ++++-
 kernel/trace/trace.c              | 105 ++++++++++++++++++++++++++++++++++----
 kernel/trace/trace.h              |   7 +++
 kernel/trace/trace_events.c       |  42 ++++++++++++++-
 kernel/trace/trace_sched_switch.c |  72 +++++++++++++++++++++-----
 5 files changed, 213 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index a556805eff8a..f73cedfa2e0b 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -151,7 +151,15 @@ trace_event_buffer_lock_reserve(struct ring_buffer **current_buffer,
 				int type, unsigned long len,
 				unsigned long flags, int pc);
 
-void tracing_record_cmdline(struct task_struct *tsk);
+#define TRACE_RECORD_CMDLINE	BIT(0)
+#define TRACE_RECORD_TGID	BIT(1)
+
+void tracing_record_taskinfo(struct task_struct *task, int flags);
+void tracing_record_taskinfo_sched_switch(struct task_struct *prev,
+					  struct task_struct *next, int flags);
+
+void tracing_record_cmdline(struct task_struct *task);
+void tracing_record_tgid(struct task_struct *task);
 
 int trace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...);
 
@@ -290,6 +298,7 @@ struct trace_subsystem_dir;
 enum {
 	EVENT_FILE_FL_ENABLED_BIT,
 	EVENT_FILE_FL_RECORDED_CMD_BIT,
+	EVENT_FILE_FL_RECORDED_TGID_BIT,
 	EVENT_FILE_FL_FILTERED_BIT,
 	EVENT_FILE_FL_NO_SET_FILTER_BIT,
 	EVENT_FILE_FL_SOFT_MODE_BIT,
@@ -303,6 +312,7 @@ enum {
  * Event file flags:
  *  ENABLED	  - The event is enabled
  *  RECORDED_CMD  - The comms should be recorded at sched_switch
+ *  RECORDED_TGID - The tgids should be recorded at sched_switch
  *  FILTERED	  - The event has a filter attached
  *  NO_SET_FILTER - Set when filter has error and is to be ignored
  *  SOFT_MODE     - The event is enabled/disabled by SOFT_DISABLED
@@ -315,6 +325,7 @@ enum {
 enum {
 	EVENT_FILE_FL_ENABLED		= (1 << EVENT_FILE_FL_ENABLED_BIT),
 	EVENT_FILE_FL_RECORDED_CMD	= (1 << EVENT_FILE_FL_RECORDED_CMD_BIT),
+	EVENT_FILE_FL_RECORDED_TGID	= (1 << EVENT_FILE_FL_RECORDED_TGID_BIT),
 	EVENT_FILE_FL_FILTERED		= (1 << EVENT_FILE_FL_FILTERED_BIT),
 	EVENT_FILE_FL_NO_SET_FILTER	= (1 << EVENT_FILE_FL_NO_SET_FILTER_BIT),
 	EVENT_FILE_FL_SOFT_MODE		= (1 << EVENT_FILE_FL_SOFT_MODE_BIT),
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 14318ce92b13..ab9db750dd29 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -87,7 +87,7 @@ dummy_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
  * tracing is active, only save the comm when a trace event
  * occurred.
  */
-static DEFINE_PER_CPU(bool, trace_cmdline_save);
+static DEFINE_PER_CPU(bool, trace_taskinfo_save);
 
 /*
  * Kill all tracing for good (never come back).
@@ -790,7 +790,7 @@ EXPORT_SYMBOL_GPL(tracing_on);
 static __always_inline void
 __buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event)
 {
-	__this_cpu_write(trace_cmdline_save, true);
+	__this_cpu_write(trace_taskinfo_save, true);
 
 	/* If this is the temp buffer, we need to commit fully */
 	if (this_cpu_read(trace_buffered_event) == event) {
@@ -1709,6 +1709,8 @@ void tracing_reset_all_online_cpus(void)
 	}
 }
 
+static int *tgid_map;
+
 #define SAVED_CMDLINES_DEFAULT 128
 #define NO_CMDLINE_MAP UINT_MAX
 static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
@@ -1722,7 +1724,7 @@ struct saved_cmdlines_buffer {
 static struct saved_cmdlines_buffer *savedcmd;
 
 /* temporary disable recording */
-static atomic_t trace_record_cmdline_disabled __read_mostly;
+static atomic_t trace_record_taskinfo_disabled __read_mostly;
 
 static inline char *get_saved_cmdlines(int idx)
 {
@@ -1990,16 +1992,87 @@ void trace_find_cmdline(int pid, char comm[])
 	preempt_enable();
 }
 
-void tracing_record_cmdline(struct task_struct *tsk)
+int trace_find_tgid(int pid)
+{
+	if (unlikely(!tgid_map || !pid || pid > PID_MAX_DEFAULT))
+		return 0;
+
+	return tgid_map[pid];
+}
+
+static int trace_save_tgid(struct task_struct *tsk)
 {
-	if (atomic_read(&trace_record_cmdline_disabled) || !tracing_is_on())
+	if (unlikely(!tgid_map || !tsk->pid || tsk->pid > PID_MAX_DEFAULT))
+		return 0;
+
+	tgid_map[tsk->pid] = tsk->tgid;
+	return 1;
+}
+
+static bool tracing_record_taskinfo_skip(int flags)
+{
+	if (unlikely(!(flags & (TRACE_RECORD_CMDLINE | TRACE_RECORD_TGID))))
+		return true;
+	if (atomic_read(&trace_record_taskinfo_disabled) || !tracing_is_on())
+		return true;
+	if (!__this_cpu_read(trace_taskinfo_save))
+		return true;
+	return false;
+}
+
+/**
+ * tracing_record_taskinfo - record the task info of a task
+ *
+ * @task  - task to record
+ * @flags - TRACE_RECORD_CMDLINE for recording comm
+ *        - TRACE_RECORD_TGID for recording tgid
+ */
+void tracing_record_taskinfo(struct task_struct *task, int flags)
+{
+	if (tracing_record_taskinfo_skip(flags))
+		return;
+	if ((flags & TRACE_RECORD_CMDLINE) && !trace_save_cmdline(task))
+		return;
+	if ((flags & TRACE_RECORD_TGID) && !trace_save_tgid(task))
 		return;
 
-	if (!__this_cpu_read(trace_cmdline_save))
+	__this_cpu_write(trace_taskinfo_save, false);
+}
+
+/**
+ * tracing_record_taskinfo_sched_switch - record task info for sched_switch
+ *
+ * @prev - previous task during sched_switch
+ * @next - next task during sched_switch
+ * @flags - TRACE_RECORD_CMDLINE for recording comm
+ *          TRACE_RECORD_TGID for recording tgid
+ */
+void tracing_record_taskinfo_sched_switch(struct task_struct *prev,
+					  struct task_struct *next, int flags)
+{
+	if (tracing_record_taskinfo_skip(flags))
 		return;
 
-	if (trace_save_cmdline(tsk))
-		__this_cpu_write(trace_cmdline_save, false);
+	if ((flags & TRACE_RECORD_CMDLINE) &&
+	    (!trace_save_cmdline(prev) || !trace_save_cmdline(next)))
+		return;
+
+	if ((flags & TRACE_RECORD_TGID) &&
+	    (!trace_save_tgid(prev) || !trace_save_tgid(next)))
+		return;
+
+	__this_cpu_write(trace_taskinfo_save, false);
+}
+
+/* Helpers to record a specific task information */
+void tracing_record_cmdline(struct task_struct *task)
+{
+	tracing_record_taskinfo(task, TRACE_RECORD_CMDLINE);
+}
+
+void tracing_record_tgid(struct task_struct *task)
+{
+	tracing_record_taskinfo(task, TRACE_RECORD_TGID);
 }
 
 /*
@@ -3144,7 +3217,7 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 #endif
 
 	if (!iter->snapshot)
-		atomic_inc(&trace_record_cmdline_disabled);
+		atomic_inc(&trace_record_taskinfo_disabled);
 
 	if (*pos != iter->pos) {
 		iter->ent = NULL;
@@ -3189,7 +3262,7 @@ static void s_stop(struct seq_file *m, void *p)
 #endif
 
 	if (!iter->snapshot)
-		atomic_dec(&trace_record_cmdline_disabled);
+		atomic_dec(&trace_record_taskinfo_disabled);
 
 	trace_access_unlock(iter->cpu_file);
 	trace_event_read_unlock();
@@ -4236,6 +4309,18 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
 	if (mask == TRACE_ITER_RECORD_CMD)
 		trace_event_enable_cmd_record(enabled);
 
+	if (mask == TRACE_ITER_RECORD_TGID) {
+		if (!tgid_map)
+			tgid_map = kzalloc((PID_MAX_DEFAULT + 1) * sizeof(*tgid_map),
+					   GFP_KERNEL);
+		if (!tgid_map) {
+			tr->trace_flags &= ~TRACE_ITER_RECORD_TGID;
+			return -ENOMEM;
+		}
+
+		trace_event_enable_tgid_record(enabled);
+	}
+
 	if (mask == TRACE_ITER_EVENT_FORK)
 		trace_event_follow_fork(tr, enabled);
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 13823951e42b..6ade1c55cc3a 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -640,6 +640,9 @@ void set_graph_array(struct trace_array *tr);
 
 void tracing_start_cmdline_record(void);
 void tracing_stop_cmdline_record(void);
+void tracing_start_tgid_record(void);
+void tracing_stop_tgid_record(void);
+
 int register_tracer(struct tracer *type);
 int is_tracing_stopped(void);
 
@@ -700,6 +703,7 @@ static inline void __trace_stack(struct trace_array *tr, unsigned long flags,
 extern u64 ftrace_now(int cpu);
 
 extern void trace_find_cmdline(int pid, char comm[]);
+extern int trace_find_tgid(int pid);
 extern void trace_event_follow_fork(struct trace_array *tr, bool enable);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -1124,6 +1128,7 @@ extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 		C(CONTEXT_INFO,		"context-info"),   /* Print pid/cpu/time */ \
 		C(LATENCY_FMT,		"latency-format"),	\
 		C(RECORD_CMD,		"record-cmd"),		\
+		C(RECORD_TGID,		"record-tgid"),		\
 		C(OVERWRITE,		"overwrite"),		\
 		C(STOP_ON_FREE,		"disable_on_free"),	\
 		C(IRQ_INFO,		"irq-info"),		\
@@ -1440,6 +1445,8 @@ struct ftrace_event_field *
 trace_find_event_field(struct trace_event_call *call, char *name);
 
 extern void trace_event_enable_cmd_record(bool enable);
+extern void trace_event_enable_tgid_record(bool enable);
+
 extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr);
 extern int event_trace_del_tracer(struct trace_array *tr);
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 83dfd0dbbbfe..36132f9280e6 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -343,6 +343,28 @@ void trace_event_enable_cmd_record(bool enable)
 	mutex_unlock(&event_mutex);
 }
 
+void trace_event_enable_tgid_record(bool enable)
+{
+	struct trace_event_file *file;
+	struct trace_array *tr;
+
+	mutex_lock(&event_mutex);
+	do_for_each_event_file(tr, file) {
+		if (!(file->flags & EVENT_FILE_FL_ENABLED))
+			continue;
+
+		if (enable) {
+			tracing_start_tgid_record();
+			set_bit(EVENT_FILE_FL_RECORDED_TGID_BIT, &file->flags);
+		} else {
+			tracing_stop_tgid_record();
+			clear_bit(EVENT_FILE_FL_RECORDED_TGID_BIT,
+				  &file->flags);
+		}
+	} while_for_each_event_file();
+	mutex_unlock(&event_mutex);
+}
+
 static int __ftrace_event_enable_disable(struct trace_event_file *file,
 					 int enable, int soft_disable)
 {
@@ -381,6 +403,12 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
 				tracing_stop_cmdline_record();
 				clear_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags);
 			}
+
+			if (file->flags & EVENT_FILE_FL_RECORDED_TGID) {
+				tracing_stop_tgid_record();
+				clear_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags);
+			}
+
 			call->class->reg(call, TRACE_REG_UNREGISTER, file);
 		}
 		/* If in SOFT_MODE, just set the SOFT_DISABLE_BIT, else clear it */
@@ -407,18 +435,30 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
 		}
 
 		if (!(file->flags & EVENT_FILE_FL_ENABLED)) {
+			bool cmd = false, tgid = false;
 
 			/* Keep the event disabled, when going to SOFT_MODE. */
 			if (soft_disable)
 				set_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags);
 
 			if (tr->trace_flags & TRACE_ITER_RECORD_CMD) {
+				cmd = true;
 				tracing_start_cmdline_record();
 				set_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags);
 			}
+
+			if (tr->trace_flags & TRACE_ITER_RECORD_TGID) {
+				tgid = true;
+				tracing_start_tgid_record();
+				set_bit(EVENT_FILE_FL_RECORDED_TGID_BIT, &file->flags);
+			}
+
 			ret = call->class->reg(call, TRACE_REG_REGISTER, file);
 			if (ret) {
-				tracing_stop_cmdline_record();
+				if (cmd)
+					tracing_stop_cmdline_record();
+				if (tgid)
+					tracing_stop_tgid_record();
 				pr_info("event trace: Could not enable event "
 					"%s\n", trace_event_name(call));
 				break;
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 4c896a0101bd..b341c02730be 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -12,27 +12,38 @@
 
 #include "trace.h"
 
-static int			sched_ref;
+#define RECORD_CMDLINE	1
+#define RECORD_TGID	2
+
+static int		sched_cmdline_ref;
+static int		sched_tgid_ref;
 static DEFINE_MUTEX(sched_register_mutex);
 
 static void
 probe_sched_switch(void *ignore, bool preempt,
 		   struct task_struct *prev, struct task_struct *next)
 {
-	if (unlikely(!sched_ref))
-		return;
+	int flags;
+
+	flags = (RECORD_TGID * !!sched_tgid_ref) +
+		(RECORD_CMDLINE * !!sched_cmdline_ref);
 
-	tracing_record_cmdline(prev);
-	tracing_record_cmdline(next);
+	if (!flags)
+		return;
+	tracing_record_taskinfo_sched_switch(prev, next, flags);
 }
 
 static void
 probe_sched_wakeup(void *ignore, struct task_struct *wakee)
 {
-	if (unlikely(!sched_ref))
-		return;
+	int flags;
+
+	flags = (RECORD_TGID * !!sched_tgid_ref) +
+		(RECORD_CMDLINE * !!sched_cmdline_ref);
 
-	tracing_record_cmdline(current);
+	if (!flags)
+		return;
+	tracing_record_taskinfo(current, flags);
 }
 
 static int tracing_sched_register(void)
@@ -75,28 +86,61 @@ static void tracing_sched_unregister(void)
 	unregister_trace_sched_wakeup(probe_sched_wakeup, NULL);
 }
 
-static void tracing_start_sched_switch(void)
+static void tracing_start_sched_switch(int ops)
 {
+	bool sched_register = (!sched_cmdline_ref && !sched_tgid_ref);
 	mutex_lock(&sched_register_mutex);
-	if (!(sched_ref++))
+
+	switch (ops) {
+	case RECORD_CMDLINE:
+		sched_cmdline_ref++;
+		break;
+
+	case RECORD_TGID:
+		sched_tgid_ref++;
+		break;
+	}
+
+	if (sched_register && (sched_cmdline_ref || sched_tgid_ref))
 		tracing_sched_register();
 	mutex_unlock(&sched_register_mutex);
 }
 
-static void tracing_stop_sched_switch(void)
+static void tracing_stop_sched_switch(int ops)
 {
 	mutex_lock(&sched_register_mutex);
-	if (!(--sched_ref))
+
+	switch (ops) {
+	case RECORD_CMDLINE:
+		sched_cmdline_ref--;
+		break;
+
+	case RECORD_TGID:
+		sched_tgid_ref--;
+		break;
+	}
+
+	if (!sched_cmdline_ref && !sched_tgid_ref)
 		tracing_sched_unregister();
 	mutex_unlock(&sched_register_mutex);
 }
 
 void tracing_start_cmdline_record(void)
 {
-	tracing_start_sched_switch();
+	tracing_start_sched_switch(RECORD_CMDLINE);
 }
 
 void tracing_stop_cmdline_record(void)
 {
-	tracing_stop_sched_switch();
+	tracing_stop_sched_switch(RECORD_CMDLINE);
+}
+
+void tracing_start_tgid_record(void)
+{
+	tracing_start_sched_switch(RECORD_TGID);
+}
+
+void tracing_stop_tgid_record(void)
+{
+	tracing_stop_sched_switch(RECORD_TGID);
 }
-- 
cgit v1.2.3