Merge tag 'trace-v4.13' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "The new features of this release:

   - Added TRACE_DEFINE_SIZEOF() which allows trace events that use
     sizeof() it the TP_printk() to be converted to the actual size such
     that trace-cmd and perf can parse them correctly.

   - Some rework of the TRACE_DEFINE_ENUM() such that the above
     TRACE_DEFINE_SIZEOF() could reuse the same code.

   - Recording of tgid (Thread Group ID). This is similar to how task
     COMMs are recorded (cached at sched_switch), where it is in a table
     and used on output of the trace and trace_pipe files.

   - Have ":mod:<module>" be cached when written into set_ftrace_filter.
     Then the functions of the module will be traced at module load.

   - Some random clean ups and small fixes"

* tag 'trace-v4.13' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (26 commits)
  ftrace: Test for NULL iter->tr in regex for stack_trace_filter changes
  ftrace: Decrement count for dyn_ftrace_total_info for init functions
  ftrace: Unlock hash mutex on failed allocation in process_mod_list()
  tracing: Add support for display of tgid in trace output
  tracing: Add support for recording tgid of tasks
  ftrace: Decrement count for dyn_ftrace_total_info file
  ftrace: Remove unused function ftrace_arch_read_dyn_info()
  sh/ftrace: Remove only user of ftrace_arch_read_dyn_info()
  ftrace: Have cached module filters be an active filter
  ftrace: Implement cached modules tracing on module load
  ftrace: Have the cached module list show in set_ftrace_filter
  ftrace: Add :mod: caching infrastructure to trace_array
  tracing: Show address when function names are not found
  ftrace: Add missing comment for FTRACE_OPS_FL_RCU
  tracing: Rename update the enum_map file
  tracing: Add TRACE_DEFINE_SIZEOF() macros
  tracing: define TRACE_DEFINE_SIZEOF() macro to map sizeof's to their values
  tracing: Rename enum_replace to eval_replace
  trace: rename enum_map functions
  trace: rename trace.c enum functions
  ...

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),

arch/sh/kernel/ftrace.c

@@ -96,19 +96,6 @@ static int mod_code_status;		/* holds return value of text write */
 static void *mod_code_ip;		/* holds the IP to write to */
 static void *mod_code_newcode;		/* holds the text to write to the IP */
 
-static unsigned nmi_wait_count;
-static atomic_t nmi_update_count = ATOMIC_INIT(0);
-
-int ftrace_arch_read_dyn_info(char *buf, int size)
-{
-	int r;
-
-	r = snprintf(buf, size, "%u %u",
-		     nmi_wait_count,
-		     atomic_read(&nmi_update_count));
-	return r;
-}
-
 static void clear_mod_flag(void)
 {
 	int old = atomic_read(&nmi_running);
@@ -144,7 +131,6 @@ void arch_ftrace_nmi_enter(void)
 	if (atomic_inc_return(&nmi_running) & MOD_CODE_WRITE_FLAG) {
 		smp_rmb();
 		ftrace_mod_code();
-		atomic_inc(&nmi_update_count);
 	}
 	/* Must have previous changes seen before executions */
 	smp_mb();
@@ -165,8 +151,6 @@ static void wait_for_nmi_and_set_mod_flag(void)
 	do {
 		cpu_relax();
 	} while (atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG));
-
-	nmi_wait_count++;
 }
 
 static void wait_for_nmi(void)
@@ -177,8 +161,6 @@ static void wait_for_nmi(void)
 	do {
 		cpu_relax();
 	} while (atomic_read(&nmi_running));
-
-	nmi_wait_count++;
 }
 
 static int

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

include/linux/ftrace.h

@@ -119,6 +119,8 @@ 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.
+ * TRACE_ARRAY - The ops->private points to a trace_array descriptor.
  */
 enum {
 	FTRACE_OPS_FL_ENABLED			= 1 << 0,
@@ -137,6 +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
@@ -445,7 +448,8 @@ 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);

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_enum_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;

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),

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
@@ -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 */
 

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),

include/trace/trace_events.h

@@ -35,15 +35,28 @@ 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		\
-	__attribute__((section("_ftrace_enum_map")))	\
+	static struct trace_eval_map __used		\
+	__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
 
 /*
@@ -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)
 

kernel/module.c

@@ -3074,9 +3074,9 @@ 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_enum_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",

kernel/trace/Kconfig

@@ -667,30 +667,30 @@ config RING_BUFFER_STARTUP_TEST
 
 	 If unsure, say N
 
-config TRACE_ENUM_MAP_FILE
-       bool "Show enum mappings for trace events"
+config TRACE_EVAL_MAP_FILE
+       bool "Show eval mappings for trace events"
        depends on TRACING
        help
-        The "print fmt" of the trace events will show the enum names instead
-	of their values. This can cause problems for user space tools that
-	use this string to parse the raw data as user space does not know
+	The "print fmt" of the trace events will show the enum/sizeof names
+	instead	of their values. This can cause problems for user space tools
+	that use this string to parse the raw data as user space does not know
 	how to convert the string to its value.
 
 	To fix this, there's a special macro in the kernel that can be used
-	to convert the enum into its value. If this macro is used, then the
-	print fmt strings will have the enums converted to their values.
+	to convert an enum/sizeof into its value. If this macro is used, then
+	the print fmt strings will be converted to their values.
 
 	If something does not get converted properly, this option can be
-	used to show what enums the kernel tried to convert.
+	used to show what enums/sizeof the kernel tried to convert.
 
-	This option is for debugging the enum conversions. A file is created
-	in the tracing directory called "enum_map" that will show the enum
+	This option is for debugging the conversions. A file is created
+	in the tracing directory called "eval_map" that will show the
 	names matched with their values and what trace event system they
 	belong too.
 
 	Normally, the mapping of the strings to values will be freed after
 	boot up or module load. With this option, they will not be freed, as
-	they are needed for the "enum_map" file. Enabling this option will
+	they are needed for the "eval_map" file. Enabling this option will
 	increase the memory footprint of the running kernel.
 
 	If unsure, say N

kernel/trace/ftrace.c

@@ -1293,6 +1293,28 @@ static void ftrace_hash_clear(struct ftrace_hash *hash)
 	FTRACE_WARN_ON(hash->count);
 }
 
+static void free_ftrace_mod(struct ftrace_mod_load *ftrace_mod)
+{
+	list_del(&ftrace_mod->list);
+	kfree(ftrace_mod->module);
+	kfree(ftrace_mod->func);
+	kfree(ftrace_mod);
+}
+
+static void clear_ftrace_mod_list(struct list_head *head)
+{
+	struct ftrace_mod_load *p, *n;
+
+	/* stack tracer isn't supported yet */
+	if (!head)
+		return;
+
+	mutex_lock(&ftrace_lock);
+	list_for_each_entry_safe(p, n, head, list)
+		free_ftrace_mod(p);
+	mutex_unlock(&ftrace_lock);
+}
+
 static void free_ftrace_hash(struct ftrace_hash *hash)
 {
 	if (!hash || hash == EMPTY_HASH)
@@ -1346,6 +1368,35 @@ static struct ftrace_hash *alloc_ftrace_hash(int size_bits)
 	return hash;
 }
 
+
+static int ftrace_add_mod(struct trace_array *tr,
+			  const char *func, const char *module,
+			  int enable)
+{
+	struct ftrace_mod_load *ftrace_mod;
+	struct list_head *mod_head = enable ? &tr->mod_trace : &tr->mod_notrace;
+
+	ftrace_mod = kzalloc(sizeof(*ftrace_mod), GFP_KERNEL);
+	if (!ftrace_mod)
+		return -ENOMEM;
+
+	ftrace_mod->func = kstrdup(func, GFP_KERNEL);
+	ftrace_mod->module = kstrdup(module, GFP_KERNEL);
+	ftrace_mod->enable = enable;
+
+	if (!ftrace_mod->func || !ftrace_mod->module)
+		goto out_free;
+
+	list_add(&ftrace_mod->list, mod_head);
+
+	return 0;
+
+ out_free:
+	free_ftrace_mod(ftrace_mod);
+
+	return -ENOMEM;
+}
+
 static struct ftrace_hash *
 alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash)
 {
@@ -1359,6 +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;
@@ -1403,7 +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;
 
 	/*
@@ -1420,6 +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];
@@ -1650,7 +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))
@@ -1671,7 +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;
@@ -3061,6 +3117,7 @@ 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;
@@ -3068,6 +3125,8 @@ 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;
@@ -3152,13 +3211,13 @@ 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;
@@ -3196,6 +3255,82 @@ 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)
 {
@@ -3237,7 +3372,7 @@ 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))
@@ -3246,16 +3381,19 @@ 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;
 }
@@ -3264,7 +3402,7 @@ 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)
@@ -3293,15 +3431,15 @@ 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
@@ -3317,7 +3455,7 @@ 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;
 }
@@ -3351,6 +3489,9 @@ 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");
@@ -3457,6 +3598,8 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
 {
 	struct ftrace_iterator *iter;
 	struct ftrace_hash *hash;
+	struct list_head *mod_head;
+	struct trace_array *tr = ops->private;
 	int ret = 0;
 
 	ftrace_ops_init(ops);
@@ -3475,21 +3618,29 @@ 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)
+	if (flag & FTRACE_ITER_NOTRACE) {
 		hash = ops->func_hash->notrace_hash;
-	else
+		mod_head = tr ? &tr->mod_notrace : NULL;
+	} else {
 		hash = ops->func_hash->filter_hash;
+		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;
 
-		if (file->f_flags & O_TRUNC)
+		if (file->f_flags & O_TRUNC) {
 			iter->hash = alloc_ftrace_hash(size_bits);
-		else
+			clear_ftrace_mod_list(mod_head);
+	        } else {
 			iter->hash = alloc_and_copy_ftrace_hash(size_bits, hash);
+		}
 
 		if (!iter->hash) {
 			trace_parser_put(&iter->parser);
@@ -3761,6 +3912,163 @@ static int ftrace_hash_move_and_update_ops(struct ftrace_ops *ops,
 	return ret;
 }
 
+static bool module_exists(const char *module)
+{
+	/* All modules have the symbol __this_module */
+	const char this_mod[] = "__this_module";
+	const int modname_size = MAX_PARAM_PREFIX_LEN + sizeof(this_mod) + 1;
+	char modname[modname_size + 1];
+	unsigned long val;
+	int n;
+
+	n = snprintf(modname, modname_size + 1, "%s:%s", module, this_mod);
+
+	if (n > modname_size)
+		return false;
+
+	val = module_kallsyms_lookup_name(modname);
+	return val != 0;
+}
+
+static int cache_mod(struct trace_array *tr,
+		     const char *func, char *module, int enable)
+{
+	struct ftrace_mod_load *ftrace_mod, *n;
+	struct list_head *head = enable ? &tr->mod_trace : &tr->mod_notrace;
+	int ret;
+
+	mutex_lock(&ftrace_lock);
+
+	/* We do not cache inverse filters */
+	if (func[0] == '!') {
+		func++;
+		ret = -EINVAL;
+
+		/* Look to remove this hash */
+		list_for_each_entry_safe(ftrace_mod, n, head, list) {
+			if (strcmp(ftrace_mod->module, module) != 0)
+				continue;
+
+			/* no func matches all */
+			if (!func || strcmp(func, "*") == 0 ||
+			    (ftrace_mod->func &&
+			     strcmp(ftrace_mod->func, func) == 0)) {
+				ret = 0;
+				free_ftrace_mod(ftrace_mod);
+				continue;
+			}
+		}
+		goto out;
+	}
+
+	ret = -EINVAL;
+	/* We only care about modules that have not been loaded yet */
+	if (module_exists(module))
+		goto out;
+
+	/* Save this string off, and execute it when the module is loaded */
+	ret = ftrace_add_mod(tr, func, module, enable);
+ out:
+	mutex_unlock(&ftrace_lock);
+
+	return ret;
+}
+
+static int
+ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
+		 int reset, int enable);
+
+static void process_mod_list(struct list_head *head, struct ftrace_ops *ops,
+			     char *mod, bool enable)
+{
+	struct ftrace_mod_load *ftrace_mod, *n;
+	struct ftrace_hash **orig_hash, *new_hash;
+	LIST_HEAD(process_mods);
+	char *func;
+	int ret;
+
+	mutex_lock(&ops->func_hash->regex_lock);
+
+	if (enable)
+		orig_hash = &ops->func_hash->filter_hash;
+	else
+		orig_hash = &ops->func_hash->notrace_hash;
+
+	new_hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS,
+					      *orig_hash);
+	if (!new_hash)
+		goto out; /* warn? */
+
+	mutex_lock(&ftrace_lock);
+
+	list_for_each_entry_safe(ftrace_mod, n, head, list) {
+
+		if (strcmp(ftrace_mod->module, mod) != 0)
+			continue;
+
+		if (ftrace_mod->func)
+			func = kstrdup(ftrace_mod->func, GFP_KERNEL);
+		else
+			func = kstrdup("*", GFP_KERNEL);
+
+		if (!func) /* warn? */
+			continue;
+
+		list_del(&ftrace_mod->list);
+		list_add(&ftrace_mod->list, &process_mods);
+
+		/* Use the newly allocated func, as it may be "*" */
+		kfree(ftrace_mod->func);
+		ftrace_mod->func = func;
+	}
+
+	mutex_unlock(&ftrace_lock);
+
+	list_for_each_entry_safe(ftrace_mod, n, &process_mods, list) {
+
+		func = ftrace_mod->func;
+
+		/* Grabs ftrace_lock, which is why we have this extra step */
+		match_records(new_hash, func, strlen(func), mod);
+		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,
+					      new_hash, enable);
+	mutex_unlock(&ftrace_lock);
+
+ out:
+	mutex_unlock(&ops->func_hash->regex_lock);
+
+	free_ftrace_hash(new_hash);
+}
+
+static void process_cached_mods(const char *mod_name)
+{
+	struct trace_array *tr;
+	char *mod;
+
+	mod = kstrdup(mod_name, GFP_KERNEL);
+	if (!mod)
+		return;
+
+	mutex_lock(&trace_types_lock);
+	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+		if (!list_empty(&tr->mod_trace))
+			process_mod_list(&tr->mod_trace, tr->ops, mod, true);
+		if (!list_empty(&tr->mod_notrace))
+			process_mod_list(&tr->mod_notrace, tr->ops, mod, false);
+	}
+	mutex_unlock(&trace_types_lock);
+
+	kfree(mod);
+}
+
 /*
  * We register the module command as a template to show others how
  * to register the a command as well.
@@ -3768,10 +4076,16 @@ static int ftrace_hash_move_and_update_ops(struct ftrace_ops *ops,
 
 static int
 ftrace_mod_callback(struct trace_array *tr, struct ftrace_hash *hash,
-		    char *func, char *cmd, char *module, int enable)
+		    char *func_orig, char *cmd, char *module, int enable)
 {
+	char *func;
 	int ret;
 
+	/* match_records() modifies func, and we need the original */
+	func = kstrdup(func_orig, GFP_KERNEL);
+	if (!func)
+		return -ENOMEM;
+
 	/*
 	 * cmd == 'mod' because we only registered this func
 	 * for the 'mod' ftrace_func_command.
@@ -3780,8 +4094,10 @@ ftrace_mod_callback(struct trace_array *tr, struct ftrace_hash *hash,
 	 * parameter.
 	 */
 	ret = match_records(hash, func, strlen(func), module);
+	kfree(func);
+
 	if (!ret)
-		return -EINVAL;
+		return cache_mod(tr, func_orig, module, enable);
 	if (ret < 0)
 		return ret;
 	return 0;
@@ -4725,9 +5041,11 @@ 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 (iter->tr && !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);
@@ -5385,6 +5703,7 @@ void ftrace_release_mod(struct module *mod)
 			if (pg == ftrace_pages)
 				ftrace_pages = next_to_ftrace_page(last_pg);
 
+			ftrace_update_tot_cnt -= pg->index;
 			*last_pg = pg->next;
 			order = get_count_order(pg->size / ENTRIES_PER_PAGE);
 			free_pages((unsigned long)pg->records, order);
@@ -5463,6 +5782,8 @@ void ftrace_module_enable(struct module *mod)
 
  out_unlock:
 	mutex_unlock(&ftrace_lock);
+
+	process_cached_mods(mod->name);
 }
 
 void ftrace_module_init(struct module *mod)
@@ -5501,6 +5822,7 @@ void __init ftrace_free_init_mem(void)
 		if (!rec)
 			continue;
 		pg->index--;
+		ftrace_update_tot_cnt--;
 		if (!pg->index) {
 			*last_pg = pg->next;
 			order = get_count_order(pg->size / ENTRIES_PER_PAGE);
@@ -5567,6 +5889,8 @@ static void ftrace_update_trampoline(struct ftrace_ops *ops)
 void ftrace_init_trace_array(struct trace_array *tr)
 {
 	INIT_LIST_HEAD(&tr->func_probes);
+	INIT_LIST_HEAD(&tr->mod_trace);
+	INIT_LIST_HEAD(&tr->mod_notrace);
 }
 #else
 

kernel/trace/trace.h

@@ -263,7 +263,10 @@ struct trace_array {
 	struct ftrace_ops	*ops;
 	struct trace_pid_list	__rcu *function_pids;
 #ifdef CONFIG_DYNAMIC_FTRACE
+	/* All of these are protected by the ftrace_lock */
 	struct list_head	func_probes;
+	struct list_head	mod_trace;
+	struct list_head	mod_notrace;
 #endif
 	/* function tracing enabled */
 	int			function_enabled;
@@ -637,6 +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);
 
@@ -697,6 +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
@@ -761,10 +768,24 @@ enum print_line_t print_trace_line(struct trace_iterator *iter);
 
 extern char trace_find_mark(unsigned long long duration);
 
+struct ftrace_hash;
+
+struct ftrace_mod_load {
+	struct list_head	list;
+	char			*func;
+	char			*module;
+	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;
 };
 
@@ -773,7 +794,7 @@ 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 */
@@ -1107,6 +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"),		\
@@ -1423,6 +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);
 
@@ -1773,10 +1797,10 @@ 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_eval_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_eval_update(struct trace_eval_map **map, int len) { }
 #endif
 
 extern struct trace_iterator *tracepoint_print_iter;

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;
@@ -2067,18 +2107,18 @@ __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 *eval_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);
+	/* Find the length of the eval value as a string */
+	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 +2130,11 @@ 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 == '\\') {
@@ -2125,16 +2165,16 @@ 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 */
+				ptr = eval_replace(ptr, map, len);
+				/* enum/sizeof string smaller than value */
 				if (WARN_ON_ONCE(!ptr))
 					return;
 				/*
-				 * No need to decrement here, as enum_replace()
+				 * No need to decrement here, as eval_replace()
 				 * returns the pointer to the character passed
-				 * the enum, and two enums can not be placed
+				 * the eval, and two evals can not be placed
 				 * back to back without something in between.
 				 * We can skip that something in between.
 				 */
@@ -2165,7 +2205,7 @@ 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_eval_update(struct trace_eval_map **map, int len)
 {
 	struct trace_event_call *call, *p;
 	const char *last_system = NULL;

kernel/trace/trace_output.c

@@ -340,31 +340,41 @@ static inline const char *kretprobed(const char *name)
 static void
 seq_print_sym_short(struct trace_seq *s, const char *fmt, unsigned long address)
 {
-#ifdef CONFIG_KALLSYMS
 	char str[KSYM_SYMBOL_LEN];
+#ifdef CONFIG_KALLSYMS
 	const char *name;
 
 	kallsyms_lookup(address, NULL, NULL, NULL, str);
 
 	name = kretprobed(str);
 
-	trace_seq_printf(s, fmt, name);
+	if (name && strlen(name)) {
+		trace_seq_printf(s, fmt, name);
+		return;
+	}
 #endif
+	snprintf(str, KSYM_SYMBOL_LEN, "0x%08lx", address);
+	trace_seq_printf(s, fmt, str);
 }
 
 static void
 seq_print_sym_offset(struct trace_seq *s, const char *fmt,
 		     unsigned long address)
 {
-#ifdef CONFIG_KALLSYMS
 	char str[KSYM_SYMBOL_LEN];
+#ifdef CONFIG_KALLSYMS
 	const char *name;
 
 	sprint_symbol(str, address);
 	name = kretprobed(str);
 
-	trace_seq_printf(s, fmt, name);
+	if (name && strlen(name)) {
+		trace_seq_printf(s, fmt, name);
+		return;
+	}
 #endif
+	snprintf(str, KSYM_SYMBOL_LEN, "0x%08lx", address);
+	trace_seq_printf(s, fmt, str);
 }
 
 #ifndef CONFIG_64BIT
@@ -587,6 +597,15 @@ int trace_print_context(struct trace_iterator *iter)
 	trace_seq_printf(s, "%16s-%-5d [%03d] ",
 			       comm, entry->pid, iter->cpu);
 
+	if (tr->trace_flags & TRACE_ITER_RECORD_TGID) {
+		unsigned int tgid = trace_find_tgid(entry->pid);
+
+		if (!tgid)
+			trace_seq_printf(s, "(-----) ");
+		else
+			trace_seq_printf(s, "(%5d) ", tgid);
+	}
+
 	if (tr->trace_flags & TRACE_ITER_IRQ_INFO)
 		trace_print_lat_fmt(s, entry);
 

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);
 }