};
+struct trace_event;
+
typedef enum print_line_t (*trace_print_func)(struct trace_iterator *iter,
- int flags);
-struct trace_event {
- struct hlist_node node;
- struct list_head list;
- int type;
+ int flags, struct trace_event *event);
+
+struct trace_event_functions {
trace_print_func trace;
trace_print_func raw;
trace_print_func hex;
trace_print_func binary;
};
+struct trace_event {
+ struct hlist_node node;
+ struct list_head list;
+ int type;
+ struct trace_event_functions *funcs;
+};
+
extern int register_ftrace_event(struct trace_event *event);
extern int unregister_ftrace_event(struct trace_event *event);
struct event_filter;
+enum trace_reg {
+ TRACE_REG_REGISTER,
+ TRACE_REG_UNREGISTER,
+ TRACE_REG_PERF_REGISTER,
+ TRACE_REG_PERF_UNREGISTER,
+};
+
+struct ftrace_event_call;
+
+struct ftrace_event_class {
+ char *system;
+ void *probe;
+#ifdef CONFIG_PERF_EVENTS
+ void *perf_probe;
+#endif
+ int (*reg)(struct ftrace_event_call *event,
+ enum trace_reg type);
+ int (*define_fields)(struct ftrace_event_call *);
+ struct list_head *(*get_fields)(struct ftrace_event_call *);
+ struct list_head fields;
+ int (*raw_init)(struct ftrace_event_call *);
+};
+
+enum {
+ TRACE_EVENT_FL_ENABLED_BIT,
+ TRACE_EVENT_FL_FILTERED_BIT,
+};
+
+enum {
+ TRACE_EVENT_FL_ENABLED = (1 << TRACE_EVENT_FL_ENABLED_BIT),
+ TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT),
+};
+
struct ftrace_event_call {
struct list_head list;
+ struct ftrace_event_class *class;
char *name;
- char *system;
struct dentry *dir;
- struct trace_event *event;
- int enabled;
- int (*regfunc)(struct ftrace_event_call *);
- void (*unregfunc)(struct ftrace_event_call *);
- int id;
+ struct trace_event event;
const char *print_fmt;
- int (*raw_init)(struct ftrace_event_call *);
- int (*define_fields)(struct ftrace_event_call *);
- struct list_head fields;
- int filter_active;
struct event_filter *filter;
void *mod;
void *data;
+ /*
+ * 32 bit flags:
+ * bit 1: enabled
+ * bit 2: filter_active
+ *
+ * Changes to flags must hold the event_mutex.
+ *
+ * Note: Reads of flags do not hold the event_mutex since
+ * they occur in critical sections. But the way flags
+ * is currently used, these changes do no affect the code
+ * except that when a change is made, it may have a slight
+ * delay in propagating the changes to other CPUs due to
+ * caching and such.
+ */
+ unsigned int flags;
+
++#ifdef CONFIG_PERF_EVENTS
int perf_refcount;
- int (*perf_event_enable)(struct ftrace_event_call *);
- void (*perf_event_disable)(struct ftrace_event_call *);
+ struct hlist_head *perf_events;
++#endif
};
#define PERF_MAX_TRACE_SIZE 2048
DECLARE_PER_CPU(struct pt_regs, perf_trace_regs);
- extern int perf_trace_enable(int event_id);
- extern void perf_trace_disable(int event_id);
- extern int ftrace_profile_set_filter(struct perf_event *event, int event_id,
+ extern int perf_trace_init(struct perf_event *event);
+ extern void perf_trace_destroy(struct perf_event *event);
+ extern int perf_trace_enable(struct perf_event *event);
+ extern void perf_trace_disable(struct perf_event *event);
+ extern int ftrace_profile_set_filter(struct perf_event *event, int event_id,
char *filter_str);
extern void ftrace_profile_free_filter(struct perf_event *event);
- extern void *
- perf_trace_buf_prepare(int size, unsigned short type, int *rctxp,
- unsigned long *irq_flags);
+ extern void *perf_trace_buf_prepare(int size, unsigned short type,
+ struct pt_regs *regs, int *rctxp);
static inline void
perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr,
- u64 count, unsigned long irq_flags, struct pt_regs *regs)
+ u64 count, struct pt_regs *regs, void *head)
{
- struct trace_entry *entry = raw_data;
-
- perf_tp_event(entry->type, addr, count, raw_data, size, regs);
+ perf_tp_event(addr, count, raw_data, size, regs, head);
perf_swevent_put_recursion_context(rctx);
- local_irq_restore(irq_flags);
}
#endif
struct trace_entry ent; \
tstruct \
char __data[0]; \
- };
+ }; \
+ \
+ static struct ftrace_event_class event_class_##name;
+
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, name, proto, args) \
static struct ftrace_event_call \
*
* entry = iter->ent;
*
- * if (entry->type != event_<call>.id) {
+ * if (entry->type != event_<call>->event.type) {
* WARN_ON_ONCE(1);
* return TRACE_TYPE_UNHANDLED;
* }
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
static notrace enum print_line_t \
-ftrace_raw_output_id_##call(int event_id, const char *name, \
- struct trace_iterator *iter, int flags) \
+ftrace_raw_output_##call(struct trace_iterator *iter, int flags, \
+ struct trace_event *trace_event) \
{ \
+ struct ftrace_event_call *event; \
struct trace_seq *s = &iter->seq; \
struct ftrace_raw_##call *field; \
struct trace_entry *entry; \
struct trace_seq *p; \
int ret; \
\
+ event = container_of(trace_event, struct ftrace_event_call, \
+ event); \
+ \
entry = iter->ent; \
\
- if (entry->type != event_id) { \
+ if (entry->type != event->event.type) { \
WARN_ON_ONCE(1); \
return TRACE_TYPE_UNHANDLED; \
} \
\
p = &get_cpu_var(ftrace_event_seq); \
trace_seq_init(p); \
- ret = trace_seq_printf(s, "%s: ", name); \
+ ret = trace_seq_printf(s, "%s: ", event->name); \
if (ret) \
ret = trace_seq_printf(s, print); \
put_cpu(); \
return TRACE_TYPE_PARTIAL_LINE; \
\
return TRACE_TYPE_HANDLED; \
-}
-
-#undef DEFINE_EVENT
-#define DEFINE_EVENT(template, name, proto, args) \
-static notrace enum print_line_t \
-ftrace_raw_output_##name(struct trace_iterator *iter, int flags) \
-{ \
- return ftrace_raw_output_id_##template(event_##name.id, \
- #name, iter, flags); \
-}
+} \
+static struct trace_event_functions ftrace_event_type_funcs_##call = { \
+ .trace = ftrace_raw_output_##call, \
+};
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, call, proto, args, print) \
static notrace enum print_line_t \
-ftrace_raw_output_##call(struct trace_iterator *iter, int flags) \
+ftrace_raw_output_##call(struct trace_iterator *iter, int flags, \
+ struct trace_event *event) \
{ \
struct trace_seq *s = &iter->seq; \
struct ftrace_raw_##template *field; \
\
entry = iter->ent; \
\
- if (entry->type != event_##call.id) { \
+ if (entry->type != event_##call.event.type) { \
WARN_ON_ONCE(1); \
return TRACE_TYPE_UNHANDLED; \
} \
return TRACE_TYPE_PARTIAL_LINE; \
\
return TRACE_TYPE_HANDLED; \
-}
+} \
+static struct trace_event_functions ftrace_event_type_funcs_##call = { \
+ .trace = ftrace_raw_output_##call, \
+};
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
-#ifdef CONFIG_PERF_EVENTS
-
-/*
- * Generate the functions needed for tracepoint perf_event support.
- *
- * NOTE: The insertion profile callback (ftrace_profile_<call>) is defined later
- *
- * static int ftrace_profile_enable_<call>(void)
- * {
- * return register_trace_<call>(ftrace_profile_<call>);
- * }
- *
- * static void ftrace_profile_disable_<call>(void)
- * {
- * unregister_trace_<call>(ftrace_profile_<call>);
- * }
- *
- */
-
-#undef DECLARE_EVENT_CLASS
-#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)
-
-#undef DEFINE_EVENT
-#define DEFINE_EVENT(template, name, proto, args) \
- \
-static void perf_trace_##name(proto); \
- \
-static notrace int \
-perf_trace_enable_##name(struct ftrace_event_call *unused) \
-{ \
- return register_trace_##name(perf_trace_##name); \
-} \
- \
-static notrace void \
-perf_trace_disable_##name(struct ftrace_event_call *unused) \
-{ \
- unregister_trace_##name(perf_trace_##name); \
-}
-
-#undef DEFINE_EVENT_PRINT
-#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
- DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
-
-#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
-
-#endif /* CONFIG_PERF_EVENTS */
-
/*
* Stage 4 of the trace events.
*
* Override the macros in <trace/trace_events.h> to include the following:
*
- * static void ftrace_event_<call>(proto)
- * {
- * event_trace_printk(_RET_IP_, "<call>: " <fmt>);
- * }
- *
- * static int ftrace_reg_event_<call>(struct ftrace_event_call *unused)
- * {
- * return register_trace_<call>(ftrace_event_<call>);
- * }
- *
- * static void ftrace_unreg_event_<call>(struct ftrace_event_call *unused)
- * {
- * unregister_trace_<call>(ftrace_event_<call>);
- * }
- *
- *
* For those macros defined with TRACE_EVENT:
*
* static struct ftrace_event_call event_<call>;
*
- * static void ftrace_raw_event_<call>(proto)
+ * static void ftrace_raw_event_<call>(void *__data, proto)
* {
+ * struct ftrace_event_call *event_call = __data;
* struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
* struct ring_buffer_event *event;
* struct ftrace_raw_<call> *entry; <-- defined in stage 1
* __data_size = ftrace_get_offsets_<call>(&__data_offsets, args);
*
* event = trace_current_buffer_lock_reserve(&buffer,
- * event_<call>.id,
+ * event_<call>->event.type,
* sizeof(*entry) + __data_size,
* irq_flags, pc);
* if (!event)
* event, irq_flags, pc);
* }
*
- * static int ftrace_raw_reg_event_<call>(struct ftrace_event_call *unused)
- * {
- * return register_trace_<call>(ftrace_raw_event_<call>);
- * }
- *
- * static void ftrace_unreg_event_<call>(struct ftrace_event_call *unused)
- * {
- * unregister_trace_<call>(ftrace_raw_event_<call>);
- * }
- *
* static struct trace_event ftrace_event_type_<call> = {
* .trace = ftrace_raw_output_<call>, <-- stage 2
* };
*
* static const char print_fmt_<call>[] = <TP_printk>;
*
+ * static struct ftrace_event_class __used event_class_<template> = {
+ * .system = "<system>",
+ * .define_fields = ftrace_define_fields_<call>,
+ * .fields = LIST_HEAD_INIT(event_class_##call.fields),
+ * .raw_init = trace_event_raw_init,
+ * .probe = ftrace_raw_event_##call,
+ * };
+ *
* static struct ftrace_event_call __used
* __attribute__((__aligned__(4)))
* __attribute__((section("_ftrace_events"))) event_<call> = {
* .name = "<call>",
- * .system = "<system>",
- * .raw_init = trace_event_raw_init,
- * .regfunc = ftrace_reg_event_<call>,
- * .unregfunc = ftrace_unreg_event_<call>,
+ * .class = event_class_<template>,
+ * .event = &ftrace_event_type_<call>,
* .print_fmt = print_fmt_<call>,
- * .define_fields = ftrace_define_fields_<call>,
- * }
+ * };
*
*/
#ifdef CONFIG_PERF_EVENTS
+#define _TRACE_PERF_PROTO(call, proto) \
+ static notrace void \
+ perf_trace_##call(void *__data, proto);
+
#define _TRACE_PERF_INIT(call) \
- .perf_event_enable = perf_trace_enable_##call, \
- .perf_event_disable = perf_trace_disable_##call,
+ .perf_probe = perf_trace_##call,
#else
+#define _TRACE_PERF_PROTO(call, proto)
#define _TRACE_PERF_INIT(call)
#endif /* CONFIG_PERF_EVENTS */
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
\
static notrace void \
-ftrace_raw_event_id_##call(struct ftrace_event_call *event_call, \
- proto) \
+ftrace_raw_event_##call(void *__data, proto) \
{ \
+ struct ftrace_event_call *event_call = __data; \
struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
struct ring_buffer_event *event; \
struct ftrace_raw_##call *entry; \
__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
\
event = trace_current_buffer_lock_reserve(&buffer, \
- event_call->id, \
+ event_call->event.type, \
sizeof(*entry) + __data_size, \
irq_flags, pc); \
if (!event) \
trace_nowake_buffer_unlock_commit(buffer, \
event, irq_flags, pc); \
}
+/*
+ * The ftrace_test_probe is compiled out, it is only here as a build time check
+ * to make sure that if the tracepoint handling changes, the ftrace probe will
+ * fail to compile unless it too is updated.
+ */
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, call, proto, args) \
- \
-static notrace void ftrace_raw_event_##call(proto) \
-{ \
- ftrace_raw_event_id_##template(&event_##call, args); \
-} \
- \
-static notrace int \
-ftrace_raw_reg_event_##call(struct ftrace_event_call *unused) \
-{ \
- return register_trace_##call(ftrace_raw_event_##call); \
-} \
- \
-static notrace void \
-ftrace_raw_unreg_event_##call(struct ftrace_event_call *unused) \
+static inline void ftrace_test_probe_##call(void) \
{ \
- unregister_trace_##call(ftrace_raw_event_##call); \
-} \
- \
-static struct trace_event ftrace_event_type_##call = { \
- .trace = ftrace_raw_output_##call, \
-};
+ check_trace_callback_type_##call(ftrace_raw_event_##template); \
+}
#undef DEFINE_EVENT_PRINT
-#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
- DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print)
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
-static const char print_fmt_##call[] = print;
+_TRACE_PERF_PROTO(call, PARAMS(proto)); \
+static const char print_fmt_##call[] = print; \
+static struct ftrace_event_class __used event_class_##call = { \
+ .system = __stringify(TRACE_SYSTEM), \
+ .define_fields = ftrace_define_fields_##call, \
+ .fields = LIST_HEAD_INIT(event_class_##call.fields),\
+ .raw_init = trace_event_raw_init, \
+ .probe = ftrace_raw_event_##call, \
+ _TRACE_PERF_INIT(call) \
+};
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, call, proto, args) \
__attribute__((__aligned__(4))) \
__attribute__((section("_ftrace_events"))) event_##call = { \
.name = #call, \
- .system = __stringify(TRACE_SYSTEM), \
- .event = &ftrace_event_type_##call, \
- .raw_init = trace_event_raw_init, \
- .regfunc = ftrace_raw_reg_event_##call, \
- .unregfunc = ftrace_raw_unreg_event_##call, \
+ .class = &event_class_##template, \
+ .event.funcs = &ftrace_event_type_funcs_##template, \
.print_fmt = print_fmt_##template, \
- .define_fields = ftrace_define_fields_##template, \
- _TRACE_PERF_INIT(call) \
-}
+};
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, call, proto, args, print) \
__attribute__((__aligned__(4))) \
__attribute__((section("_ftrace_events"))) event_##call = { \
.name = #call, \
- .system = __stringify(TRACE_SYSTEM), \
- .event = &ftrace_event_type_##call, \
- .raw_init = trace_event_raw_init, \
- .regfunc = ftrace_raw_reg_event_##call, \
- .unregfunc = ftrace_raw_unreg_event_##call, \
+ .class = &event_class_##template, \
+ .event.funcs = &ftrace_event_type_funcs_##call, \
.print_fmt = print_fmt_##call, \
- .define_fields = ftrace_define_fields_##template, \
- _TRACE_PERF_INIT(call) \
}
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
static notrace void \
-perf_trace_templ_##call(struct ftrace_event_call *event_call, \
- struct pt_regs *__regs, proto) \
+perf_trace_##call(void *__data, proto) \
{ \
+ struct ftrace_event_call *event_call = __data; \
struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
struct ftrace_raw_##call *entry; \
- struct pt_regs *__regs = &get_cpu_var(perf_trace_regs); \
++ struct pt_regs __regs; \
u64 __addr = 0, __count = 1; \
- unsigned long irq_flags; \
+ struct hlist_head *head; \
int __entry_size; \
int __data_size; \
int rctx; \
\
- perf_fetch_caller_regs(__regs, 1); \
++ perf_fetch_caller_regs(&__regs, 1); \
+ \
__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
sizeof(u64)); \
\
if (WARN_ONCE(__entry_size > PERF_MAX_TRACE_SIZE, \
"profile buffer not large enough")) \
- goto out; \
+ return; \
+ \
entry = (struct ftrace_raw_##call *)perf_trace_buf_prepare( \
- __entry_size, event_call->event.type, &rctx, &irq_flags); \
- __entry_size, event_call->id, __regs, &rctx); \
++ __entry_size, event_call->event.type, &__regs, &rctx); \
if (!entry) \
- goto out; \
+ return; \
+ \
tstruct \
\
{ assign; } \
\
+ head = per_cpu_ptr(event_call->perf_events, smp_processor_id());\
perf_trace_buf_submit(entry, __entry_size, rctx, __addr, \
- __count, irq_flags, __regs); \
- out: \
- put_cpu_var(perf_trace_regs); \
- __count, __regs, head); \
++ __count, &__regs, head); \
}
+/*
+ * This part is compiled out, it is only here as a build time check
+ * to make sure that if the tracepoint handling changes, the
+ * perf probe will fail to compile unless it too is updated.
+ */
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, call, proto, args) \
-static notrace void perf_trace_##call(proto) \
+static inline void perf_test_probe_##call(void) \
{ \
- struct ftrace_event_call *event_call = &event_##call; \
- struct pt_regs __regs; \
- \
- perf_fetch_caller_regs(&__regs, 1); \
- perf_trace_templ_##template(event_call, &__regs, args); \
+ check_trace_callback_type_##call(perf_trace_##template); \
- \
}
+
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
#include <linux/kprobes.h>
#include "trace.h"
- DEFINE_PER_CPU(struct pt_regs, perf_trace_regs);
- EXPORT_PER_CPU_SYMBOL_GPL(perf_trace_regs);
-
EXPORT_SYMBOL_GPL(perf_arch_fetch_caller_regs);
- static char *perf_trace_buf;
- static char *perf_trace_buf_nmi;
+ static char *perf_trace_buf[4];
/*
* Force it to be aligned to unsigned long to avoid misaligned accesses
/* Count the events in use (per event id, not per instance) */
static int total_ref_count;
- static int perf_trace_event_enable(struct ftrace_event_call *event)
+ static int perf_trace_event_init(struct ftrace_event_call *tp_event,
+ struct perf_event *p_event)
{
- char *buf;
+ struct hlist_head *list;
int ret = -ENOMEM;
+ int cpu;
- if (event->perf_refcount++ > 0)
+ p_event->tp_event = tp_event;
+ if (tp_event->perf_refcount++ > 0)
return 0;
- if (!total_ref_count) {
- buf = (char *)alloc_percpu(perf_trace_t);
- if (!buf)
- goto fail_buf;
+ list = alloc_percpu(struct hlist_head);
+ if (!list)
+ goto fail;
+
+ for_each_possible_cpu(cpu)
+ INIT_HLIST_HEAD(per_cpu_ptr(list, cpu));
- rcu_assign_pointer(perf_trace_buf, buf);
+ tp_event->perf_events = list;
+
+ if (!total_ref_count) {
+ char *buf;
+ int i;
- buf = (char *)alloc_percpu(perf_trace_t);
- if (!buf)
- goto fail_buf_nmi;
+ for (i = 0; i < 4; i++) {
+ buf = (char *)alloc_percpu(perf_trace_t);
+ if (!buf)
+ goto fail;
- rcu_assign_pointer(perf_trace_buf_nmi, buf);
+ perf_trace_buf[i] = buf;
+ }
}
- if (event->class->reg)
- ret = event->class->reg(event, TRACE_REG_PERF_REGISTER);
- ret = tp_event->perf_event_enable(tp_event);
++ if (tp_event->class->reg)
++ ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER);
+ else
- ret = tracepoint_probe_register(event->name,
- event->class->perf_probe,
- event);
- if (!ret) {
- total_ref_count++;
- return 0;
- }
++ ret = tracepoint_probe_register(tp_event->name,
++ tp_event->class->perf_probe,
++ tp_event);
++
+ if (ret)
+ goto fail;
- fail_buf_nmi:
+ total_ref_count++;
+ return 0;
+
+ fail:
if (!total_ref_count) {
- free_percpu(perf_trace_buf_nmi);
- free_percpu(perf_trace_buf);
- perf_trace_buf_nmi = NULL;
- perf_trace_buf = NULL;
+ int i;
+
+ for (i = 0; i < 4; i++) {
+ free_percpu(perf_trace_buf[i]);
+ perf_trace_buf[i] = NULL;
+ }
+ }
+
+ if (!--tp_event->perf_refcount) {
+ free_percpu(tp_event->perf_events);
+ tp_event->perf_events = NULL;
}
- fail_buf:
- event->perf_refcount--;
return ret;
}
- int perf_trace_enable(int event_id)
+ int perf_trace_init(struct perf_event *p_event)
{
- struct ftrace_event_call *event;
+ struct ftrace_event_call *tp_event;
+ int event_id = p_event->attr.config;
int ret = -EINVAL;
mutex_lock(&event_mutex);
- list_for_each_entry(event, &ftrace_events, list) {
- if (event->event.type == event_id &&
- event->class && event->class->perf_probe &&
- try_module_get(event->mod)) {
- ret = perf_trace_event_enable(event);
+ list_for_each_entry(tp_event, &ftrace_events, list) {
- if (tp_event->id == event_id && tp_event->perf_event_enable &&
++ if (tp_event->event.type == event_id &&
++ tp_event->class && tp_event->class->perf_probe &&
+ try_module_get(tp_event->mod)) {
+ ret = perf_trace_event_init(tp_event, p_event);
break;
}
}
return ret;
}
- static void perf_trace_event_disable(struct ftrace_event_call *event)
+ int perf_trace_enable(struct perf_event *p_event)
{
- char *buf, *nmi_buf;
-
- if (--event->perf_refcount > 0)
- return;
-
- if (event->class->reg)
- event->class->reg(event, TRACE_REG_PERF_UNREGISTER);
- else
- tracepoint_probe_unregister(event->name, event->class->perf_probe, event);
+ struct ftrace_event_call *tp_event = p_event->tp_event;
+ struct hlist_head *list;
- if (!--total_ref_count) {
- buf = perf_trace_buf;
- rcu_assign_pointer(perf_trace_buf, NULL);
+ list = tp_event->perf_events;
+ if (WARN_ON_ONCE(!list))
+ return -EINVAL;
- nmi_buf = perf_trace_buf_nmi;
- rcu_assign_pointer(perf_trace_buf_nmi, NULL);
+ list = per_cpu_ptr(list, smp_processor_id());
+ hlist_add_head_rcu(&p_event->hlist_entry, list);
- /*
- * Ensure every events in profiling have finished before
- * releasing the buffers
- */
- synchronize_sched();
+ return 0;
+ }
- free_percpu(buf);
- free_percpu(nmi_buf);
- }
+ void perf_trace_disable(struct perf_event *p_event)
+ {
+ hlist_del_rcu(&p_event->hlist_entry);
}
- void perf_trace_disable(int event_id)
+ void perf_trace_destroy(struct perf_event *p_event)
{
- struct ftrace_event_call *event;
+ struct ftrace_event_call *tp_event = p_event->tp_event;
+ int i;
- mutex_lock(&event_mutex);
- list_for_each_entry(event, &ftrace_events, list) {
- if (event->event.type == event_id) {
- perf_trace_event_disable(event);
- module_put(event->mod);
- break;
+ if (--tp_event->perf_refcount > 0)
+ return;
+
- tp_event->perf_event_disable(tp_event);
++ if (tp_event->class->reg)
++ tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER);
++ else
++ tracepoint_probe_unregister(tp_event->name,
++ tp_event->class->perf_probe,
++ tp_event);
+
+ free_percpu(tp_event->perf_events);
+ tp_event->perf_events = NULL;
+
+ if (!--total_ref_count) {
+ for (i = 0; i < 4; i++) {
+ free_percpu(perf_trace_buf[i]);
+ perf_trace_buf[i] = NULL;
}
}
- mutex_unlock(&event_mutex);
}
__kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
- int *rctxp, unsigned long *irq_flags)
+ struct pt_regs *regs, int *rctxp)
{
struct trace_entry *entry;
- char *trace_buf, *raw_data;
- int pc, cpu;
+ char *raw_data;
+ int pc;
BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long));
pc = preempt_count();
- /* Protect the per cpu buffer, begin the rcu read side */
- local_irq_save(*irq_flags);
-
*rctxp = perf_swevent_get_recursion_context();
if (*rctxp < 0)
- goto err_recursion;
-
- cpu = smp_processor_id();
-
- if (in_nmi())
- trace_buf = rcu_dereference_sched(perf_trace_buf_nmi);
- else
- trace_buf = rcu_dereference_sched(perf_trace_buf);
-
- if (!trace_buf)
- goto err;
+ return NULL;
- raw_data = per_cpu_ptr(trace_buf, cpu);
+ raw_data = per_cpu_ptr(perf_trace_buf[*rctxp], smp_processor_id());
/* zero the dead bytes from align to not leak stack to user */
memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64));
entry = (struct trace_entry *)raw_data;
- tracing_generic_entry_update(entry, *irq_flags, pc);
+ tracing_generic_entry_update(entry, regs->flags, pc);
entry->type = type;
return raw_data;
- err:
- perf_swevent_put_recursion_context(*rctxp);
- err_recursion:
- local_irq_restore(*irq_flags);
- return NULL;
}
EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
unsigned long nhit;
unsigned int flags; /* For TP_FLAG_* */
const char *symbol; /* symbol name */
+ struct ftrace_event_class class;
struct ftrace_event_call call;
- struct trace_event event;
ssize_t size; /* trace entry size */
unsigned int nr_args;
struct probe_arg args[];
goto error;
}
+ tp->call.class = &tp->class;
tp->call.name = kstrdup(event, GFP_KERNEL);
if (!tp->call.name)
goto error;
goto error;
}
- tp->call.system = kstrdup(group, GFP_KERNEL);
- if (!tp->call.system)
+ tp->class.system = kstrdup(group, GFP_KERNEL);
+ if (!tp->class.system)
goto error;
INIT_LIST_HEAD(&tp->list);
for (i = 0; i < tp->nr_args; i++)
free_probe_arg(&tp->args[i]);
- kfree(tp->call.system);
+ kfree(tp->call.class->system);
kfree(tp->call.name);
kfree(tp->symbol);
kfree(tp);
list_for_each_entry(tp, &probe_list, list)
if (strcmp(tp->call.name, event) == 0 &&
- strcmp(tp->call.system, group) == 0)
+ strcmp(tp->call.class->system, group) == 0)
return tp;
return NULL;
}
mutex_lock(&probe_lock);
/* register as an event */
- old_tp = find_probe_event(tp->call.name, tp->call.system);
+ old_tp = find_probe_event(tp->call.name, tp->call.class->system);
if (old_tp) {
/* delete old event */
unregister_trace_probe(old_tp);
int i;
seq_printf(m, "%c", probe_is_return(tp) ? 'r' : 'p');
- seq_printf(m, ":%s/%s", tp->call.system, tp->call.name);
+ seq_printf(m, ":%s/%s", tp->call.class->system, tp->call.name);
if (!tp->symbol)
seq_printf(m, " 0x%p", tp->rp.kp.addr);
size = sizeof(*entry) + tp->size;
- event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
- irq_flags, pc);
+ event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
+ size, irq_flags, pc);
if (!event)
return;
size = sizeof(*entry) + tp->size;
- event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
- irq_flags, pc);
+ event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
+ size, irq_flags, pc);
if (!event)
return;
/* Event entry printers */
enum print_line_t
-print_kprobe_event(struct trace_iterator *iter, int flags)
+print_kprobe_event(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct kprobe_trace_entry_head *field;
struct trace_seq *s = &iter->seq;
- struct trace_event *event;
struct trace_probe *tp;
u8 *data;
int i;
field = (struct kprobe_trace_entry_head *)iter->ent;
- event = ftrace_find_event(field->ent.type);
- tp = container_of(event, struct trace_probe, event);
+ tp = container_of(event, struct trace_probe, call.event);
if (!trace_seq_printf(s, "%s: (", tp->call.name))
goto partial;
}
enum print_line_t
-print_kretprobe_event(struct trace_iterator *iter, int flags)
+print_kretprobe_event(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct kretprobe_trace_entry_head *field;
struct trace_seq *s = &iter->seq;
- struct trace_event *event;
struct trace_probe *tp;
u8 *data;
int i;
field = (struct kretprobe_trace_entry_head *)iter->ent;
- event = ftrace_find_event(field->ent.type);
- tp = container_of(event, struct trace_probe, event);
+ tp = container_of(event, struct trace_probe, call.event);
if (!trace_seq_printf(s, "%s: (", tp->call.name))
goto partial;
static int probe_event_raw_init(struct ftrace_event_call *event_call)
{
- INIT_LIST_HEAD(&event_call->fields);
-
return 0;
}
struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
struct ftrace_event_call *call = &tp->call;
struct kprobe_trace_entry_head *entry;
+ struct hlist_head *head;
u8 *data;
int size, __size, i;
- unsigned long irq_flags;
int rctx;
__size = sizeof(*entry) + tp->size;
"profile buffer not large enough"))
return;
- entry = perf_trace_buf_prepare(size, call->event.type,
- &rctx, &irq_flags);
- entry = perf_trace_buf_prepare(size, call->id, regs, &rctx);
++ entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
if (!entry)
return;
for (i = 0; i < tp->nr_args; i++)
call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
- perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, irq_flags, regs);
+ head = per_cpu_ptr(call->perf_events, smp_processor_id());
+ perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head);
}
/* Kretprobe profile handler */
struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
struct ftrace_event_call *call = &tp->call;
struct kretprobe_trace_entry_head *entry;
+ struct hlist_head *head;
u8 *data;
int size, __size, i;
- unsigned long irq_flags;
int rctx;
__size = sizeof(*entry) + tp->size;
"profile buffer not large enough"))
return;
- entry = perf_trace_buf_prepare(size, call->event.type,
- &rctx, &irq_flags);
- entry = perf_trace_buf_prepare(size, call->id, regs, &rctx);
++ entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
if (!entry)
return;
for (i = 0; i < tp->nr_args; i++)
call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
- perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1,
- irq_flags, regs);
+ head = per_cpu_ptr(call->perf_events, smp_processor_id());
+ perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1, regs, head);
}
static int probe_perf_enable(struct ftrace_event_call *call)
}
#endif /* CONFIG_PERF_EVENTS */
+static __kprobes
+int kprobe_register(struct ftrace_event_call *event, enum trace_reg type)
+{
+ switch (type) {
+ case TRACE_REG_REGISTER:
+ return probe_event_enable(event);
+ case TRACE_REG_UNREGISTER:
+ probe_event_disable(event);
+ return 0;
+
+#ifdef CONFIG_PERF_EVENTS
+ case TRACE_REG_PERF_REGISTER:
+ return probe_perf_enable(event);
+ case TRACE_REG_PERF_UNREGISTER:
+ probe_perf_disable(event);
+ return 0;
+#endif
+ }
+ return 0;
+}
static __kprobes
int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
return 0; /* We don't tweek kernel, so just return 0 */
}
+static struct trace_event_functions kretprobe_funcs = {
+ .trace = print_kretprobe_event
+};
+
+static struct trace_event_functions kprobe_funcs = {
+ .trace = print_kprobe_event
+};
+
static int register_probe_event(struct trace_probe *tp)
{
struct ftrace_event_call *call = &tp->call;
/* Initialize ftrace_event_call */
if (probe_is_return(tp)) {
- tp->event.trace = print_kretprobe_event;
- call->raw_init = probe_event_raw_init;
- call->define_fields = kretprobe_event_define_fields;
+ INIT_LIST_HEAD(&call->class->fields);
+ call->event.funcs = &kretprobe_funcs;
+ call->class->raw_init = probe_event_raw_init;
+ call->class->define_fields = kretprobe_event_define_fields;
} else {
- tp->event.trace = print_kprobe_event;
- call->raw_init = probe_event_raw_init;
- call->define_fields = kprobe_event_define_fields;
+ INIT_LIST_HEAD(&call->class->fields);
+ call->event.funcs = &kprobe_funcs;
+ call->class->raw_init = probe_event_raw_init;
+ call->class->define_fields = kprobe_event_define_fields;
}
if (set_print_fmt(tp) < 0)
return -ENOMEM;
- call->event = &tp->event;
- call->id = register_ftrace_event(&tp->event);
- if (!call->id) {
+ ret = register_ftrace_event(&call->event);
+ if (!ret) {
kfree(call->print_fmt);
return -ENODEV;
}
- call->enabled = 0;
- call->regfunc = probe_event_enable;
- call->unregfunc = probe_event_disable;
-
-#ifdef CONFIG_PERF_EVENTS
- call->perf_event_enable = probe_perf_enable;
- call->perf_event_disable = probe_perf_disable;
-#endif
+ call->flags = 0;
+ call->class->reg = kprobe_register;
call->data = tp;
ret = trace_add_event_call(call);
if (ret) {
pr_info("Failed to register kprobe event: %s\n", call->name);
kfree(call->print_fmt);
- unregister_ftrace_event(&tp->event);
+ unregister_ftrace_event(&call->event);
}
return ret;
}
static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
+static int syscall_enter_register(struct ftrace_event_call *event,
+ enum trace_reg type);
+static int syscall_exit_register(struct ftrace_event_call *event,
+ enum trace_reg type);
+
+static int syscall_enter_define_fields(struct ftrace_event_call *call);
+static int syscall_exit_define_fields(struct ftrace_event_call *call);
+
+static struct list_head *
+syscall_get_enter_fields(struct ftrace_event_call *call)
+{
+ struct syscall_metadata *entry = call->data;
+
+ return &entry->enter_fields;
+}
+
+static struct list_head *
+syscall_get_exit_fields(struct ftrace_event_call *call)
+{
+ struct syscall_metadata *entry = call->data;
+
+ return &entry->exit_fields;
+}
+
+struct trace_event_functions enter_syscall_print_funcs = {
+ .trace = print_syscall_enter,
+};
+
+struct trace_event_functions exit_syscall_print_funcs = {
+ .trace = print_syscall_exit,
+};
+
+struct ftrace_event_class event_class_syscall_enter = {
+ .system = "syscalls",
+ .reg = syscall_enter_register,
+ .define_fields = syscall_enter_define_fields,
+ .get_fields = syscall_get_enter_fields,
+ .raw_init = init_syscall_trace,
+};
+
+struct ftrace_event_class event_class_syscall_exit = {
+ .system = "syscalls",
+ .reg = syscall_exit_register,
+ .define_fields = syscall_exit_define_fields,
+ .get_fields = syscall_get_exit_fields,
+ .raw_init = init_syscall_trace,
+};
+
extern unsigned long __start_syscalls_metadata[];
extern unsigned long __stop_syscalls_metadata[];
}
enum print_line_t
-print_syscall_enter(struct trace_iterator *iter, int flags)
+print_syscall_enter(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct trace_seq *s = &iter->seq;
struct trace_entry *ent = iter->ent;
if (!entry)
goto end;
- if (entry->enter_event->id != ent->type) {
+ if (entry->enter_event->event.type != ent->type) {
WARN_ON_ONCE(1);
goto end;
}
}
enum print_line_t
-print_syscall_exit(struct trace_iterator *iter, int flags)
+print_syscall_exit(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct trace_seq *s = &iter->seq;
struct trace_entry *ent = iter->ent;
return TRACE_TYPE_HANDLED;
}
- if (entry->exit_event->id != ent->type) {
+ if (entry->exit_event->event.type != ent->type) {
WARN_ON_ONCE(1);
return TRACE_TYPE_UNHANDLED;
}
kfree(call->print_fmt);
}
-int syscall_enter_define_fields(struct ftrace_event_call *call)
+static int syscall_enter_define_fields(struct ftrace_event_call *call)
{
struct syscall_trace_enter trace;
struct syscall_metadata *meta = call->data;
return ret;
}
-int syscall_exit_define_fields(struct ftrace_event_call *call)
+static int syscall_exit_define_fields(struct ftrace_event_call *call)
{
struct syscall_trace_exit trace;
int ret;
return ret;
}
-void ftrace_syscall_enter(struct pt_regs *regs, long id)
+void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
{
struct syscall_trace_enter *entry;
struct syscall_metadata *sys_data;
size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
event = trace_current_buffer_lock_reserve(&buffer,
- sys_data->enter_event->id, size, 0, 0);
+ sys_data->enter_event->event.type, size, 0, 0);
if (!event)
return;
trace_current_buffer_unlock_commit(buffer, event, 0, 0);
}
-void ftrace_syscall_exit(struct pt_regs *regs, long ret)
+void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
{
struct syscall_trace_exit *entry;
struct syscall_metadata *sys_data;
return;
event = trace_current_buffer_lock_reserve(&buffer,
- sys_data->exit_event->id, sizeof(*entry), 0, 0);
+ sys_data->exit_event->event.type, sizeof(*entry), 0, 0);
if (!event)
return;
return -ENOSYS;
mutex_lock(&syscall_trace_lock);
if (!sys_refcount_enter)
- ret = register_trace_sys_enter(ftrace_syscall_enter);
+ ret = register_trace_sys_enter(ftrace_syscall_enter, NULL);
if (!ret) {
set_bit(num, enabled_enter_syscalls);
sys_refcount_enter++;
sys_refcount_enter--;
clear_bit(num, enabled_enter_syscalls);
if (!sys_refcount_enter)
- unregister_trace_sys_enter(ftrace_syscall_enter);
+ unregister_trace_sys_enter(ftrace_syscall_enter, NULL);
mutex_unlock(&syscall_trace_lock);
}
return -ENOSYS;
mutex_lock(&syscall_trace_lock);
if (!sys_refcount_exit)
- ret = register_trace_sys_exit(ftrace_syscall_exit);
+ ret = register_trace_sys_exit(ftrace_syscall_exit, NULL);
if (!ret) {
set_bit(num, enabled_exit_syscalls);
sys_refcount_exit++;
sys_refcount_exit--;
clear_bit(num, enabled_exit_syscalls);
if (!sys_refcount_exit)
- unregister_trace_sys_exit(ftrace_syscall_exit);
+ unregister_trace_sys_exit(ftrace_syscall_exit, NULL);
mutex_unlock(&syscall_trace_lock);
}
static int sys_perf_refcount_enter;
static int sys_perf_refcount_exit;
-static void perf_syscall_enter(struct pt_regs *regs, long id)
+static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
{
struct syscall_metadata *sys_data;
struct syscall_trace_enter *rec;
- unsigned long flags;
+ struct hlist_head *head;
int syscall_nr;
int rctx;
int size;
return;
rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size,
- sys_data->enter_event->event.type,
- &rctx, &flags);
- sys_data->enter_event->id, regs, &rctx);
++ sys_data->enter_event->event.type, regs, &rctx);
if (!rec)
return;
rec->nr = syscall_nr;
syscall_get_arguments(current, regs, 0, sys_data->nb_args,
(unsigned long *)&rec->args);
- perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs);
+
+ head = per_cpu_ptr(sys_data->enter_event->perf_events, smp_processor_id());
+ perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head);
}
int perf_sysenter_enable(struct ftrace_event_call *call)
mutex_lock(&syscall_trace_lock);
if (!sys_perf_refcount_enter)
- ret = register_trace_sys_enter(perf_syscall_enter);
+ ret = register_trace_sys_enter(perf_syscall_enter, NULL);
if (ret) {
pr_info("event trace: Could not activate"
"syscall entry trace point");
sys_perf_refcount_enter--;
clear_bit(num, enabled_perf_enter_syscalls);
if (!sys_perf_refcount_enter)
- unregister_trace_sys_enter(perf_syscall_enter);
+ unregister_trace_sys_enter(perf_syscall_enter, NULL);
mutex_unlock(&syscall_trace_lock);
}
-static void perf_syscall_exit(struct pt_regs *regs, long ret)
+static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
{
struct syscall_metadata *sys_data;
struct syscall_trace_exit *rec;
- unsigned long flags;
+ struct hlist_head *head;
int syscall_nr;
int rctx;
int size;
return;
rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size,
- sys_data->exit_event->event.type,
- &rctx, &flags);
- sys_data->exit_event->id, regs, &rctx);
++ sys_data->exit_event->event.type, regs, &rctx);
if (!rec)
return;
rec->nr = syscall_nr;
rec->ret = syscall_get_return_value(current, regs);
- perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs);
+ head = per_cpu_ptr(sys_data->exit_event->perf_events, smp_processor_id());
+ perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head);
}
int perf_sysexit_enable(struct ftrace_event_call *call)
mutex_lock(&syscall_trace_lock);
if (!sys_perf_refcount_exit)
- ret = register_trace_sys_exit(perf_syscall_exit);
+ ret = register_trace_sys_exit(perf_syscall_exit, NULL);
if (ret) {
pr_info("event trace: Could not activate"
"syscall exit trace point");
sys_perf_refcount_exit--;
clear_bit(num, enabled_perf_exit_syscalls);
if (!sys_perf_refcount_exit)
- unregister_trace_sys_exit(perf_syscall_exit);
+ unregister_trace_sys_exit(perf_syscall_exit, NULL);
mutex_unlock(&syscall_trace_lock);
}
#endif /* CONFIG_PERF_EVENTS */
+static int syscall_enter_register(struct ftrace_event_call *event,
+ enum trace_reg type)
+{
+ switch (type) {
+ case TRACE_REG_REGISTER:
+ return reg_event_syscall_enter(event);
+ case TRACE_REG_UNREGISTER:
+ unreg_event_syscall_enter(event);
+ return 0;
+
+#ifdef CONFIG_PERF_EVENTS
+ case TRACE_REG_PERF_REGISTER:
+ return perf_sysenter_enable(event);
+ case TRACE_REG_PERF_UNREGISTER:
+ perf_sysenter_disable(event);
+ return 0;
+#endif
+ }
+ return 0;
+}
+
+static int syscall_exit_register(struct ftrace_event_call *event,
+ enum trace_reg type)
+{
+ switch (type) {
+ case TRACE_REG_REGISTER:
+ return reg_event_syscall_exit(event);
+ case TRACE_REG_UNREGISTER:
+ unreg_event_syscall_exit(event);
+ return 0;
+
+#ifdef CONFIG_PERF_EVENTS
+ case TRACE_REG_PERF_REGISTER:
+ return perf_sysexit_enable(event);
+ case TRACE_REG_PERF_UNREGISTER:
+ perf_sysexit_disable(event);
+ return 0;
+#endif
+ }
+ return 0;
+}
projects / karo-tx-linux.git / commitdiff