[for-next][PATCH 0/9] tracing: More updates for 5.15

[for-next][PATCH 0/9] tracing: More updates for 5.15

[Steven Rostedt]

  git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace.git
for-next

Head SHA1: 8e242060c6a4947e8ae7d29794af6a581db08841


Masami Hiramatsu (1):
      tracing/probes: Reject events which have the same name of existing one

Sebastian Andrzej Siewior (1):
      tracing: Replace deprecated CPU-hotplug functions.

Steven Rostedt (VMware) (7):
      tracing: Add DYNAMIC flag for dynamic events
      tracing: Have dynamic events have a ref counter
      tracing/probe: Have traceprobe_parse_probe_arg() take a const arg
      tracing/probes: Allow for dot delimiter as well as slash for system names
      tracing/probes: Use struct_size() instead of defining custom macros
      tracing/probe: Change traceprobe_set_print_fmt() to take a type
      tracing/probes: Have process_fetch_insn() take a void * instead of pt_regs

----
 include/linux/trace_events.h        | 48 ++++++++++++++++++-
 kernel/trace/ring_buffer.c          |  8 ++--
 kernel/trace/trace.c                |  4 +-
 kernel/trace/trace_dynevent.c       | 38 +++++++++++++++
 kernel/trace/trace_dynevent.h       |  4 +-
 kernel/trace/trace_event_perf.c     |  6 +--
 kernel/trace/trace_events.c         | 22 +++++----
 kernel/trace/trace_events_synth.c   | 21 +++++----
 kernel/trace/trace_events_trigger.c |  6 +--
 kernel/trace/trace_hwlat.c          | 28 +++++------
 kernel/trace/trace_kprobe.c         | 41 ++++++++--------
 kernel/trace/trace_osnoise.c        | 16 +++----
 kernel/trace/trace_probe.c          | 93 +++++++++++++++++++++++++++----------
 kernel/trace/trace_probe.h          | 10 +++-
 kernel/trace/trace_probe_tmpl.h     |  6 +--
 kernel/trace/trace_uprobe.c         | 40 ++++++++--------
 16 files changed, 271 insertions(+), 120 deletions(-)

[for-next][PATCH 1/9] tracing: Replace deprecated CPU-hotplug functions.

[Steven Rostedt]

From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

The functions get_online_cpus() and put_online_cpus() have been
deprecated during the CPU hotplug rework. They map directly to
cpus_read_lock() and cpus_read_unlock().

Replace deprecated CPU-hotplug functions with the official version.
The behavior remains unchanged.

Link: https://lkml.kernel.org/r/20210803141621.780504-37-bigeasy@linutronix.de

Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Acked-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c   |  8 ++++----
 kernel/trace/trace_hwlat.c   | 28 ++++++++++++++--------------
 kernel/trace/trace_osnoise.c | 16 ++++++++--------
 3 files changed, 26 insertions(+), 26 deletions(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index e592d1df6f88..c5a3fbf19617 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2111,7 +2111,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 			}
 		}
 
-		get_online_cpus();
+		cpus_read_lock();
 		/*
 		 * Fire off all the required work handlers
 		 * We can't schedule on offline CPUs, but it's not necessary
@@ -2143,7 +2143,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 			cpu_buffer->nr_pages_to_update = 0;
 		}
 
-		put_online_cpus();
+		cpus_read_unlock();
 	} else {
 		cpu_buffer = buffer->buffers[cpu_id];
 
@@ -2171,7 +2171,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 			goto out_err;
 		}
 
-		get_online_cpus();
+		cpus_read_lock();
 
 		/* Can't run something on an offline CPU. */
 		if (!cpu_online(cpu_id))
@@ -2183,7 +2183,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 		}
 
 		cpu_buffer->nr_pages_to_update = 0;
-		put_online_cpus();
+		cpus_read_unlock();
 	}
 
  out:
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index 14f46aae1981..1b83d75eb103 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -325,10 +325,10 @@ static void move_to_next_cpu(void)
 	if (!cpumask_equal(current_mask, current->cpus_ptr))
 		goto change_mode;
 
-	get_online_cpus();
+	cpus_read_lock();
 	cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask);
 	next_cpu = cpumask_next(raw_smp_processor_id(), current_mask);
-	put_online_cpus();
+	cpus_read_unlock();
 
 	if (next_cpu >= nr_cpu_ids)
 		next_cpu = cpumask_first(current_mask);
@@ -398,7 +398,7 @@ static void stop_single_kthread(void)
 	struct hwlat_kthread_data *kdata = get_cpu_data();
 	struct task_struct *kthread;
 
-	get_online_cpus();
+	cpus_read_lock();
 	kthread = kdata->kthread;
 
 	if (!kthread)
@@ -408,7 +408,7 @@ static void stop_single_kthread(void)
 	kdata->kthread = NULL;
 
 out_put_cpus:
-	put_online_cpus();
+	cpus_read_unlock();
 }
 
 
@@ -425,14 +425,14 @@ static int start_single_kthread(struct trace_array *tr)
 	struct task_struct *kthread;
 	int next_cpu;
 
-	get_online_cpus();
+	cpus_read_lock();
 	if (kdata->kthread)
 		goto out_put_cpus;
 
 	kthread = kthread_create(kthread_fn, NULL, "hwlatd");
 	if (IS_ERR(kthread)) {
 		pr_err(BANNER "could not start sampling thread\n");
-		put_online_cpus();
+		cpus_read_unlock();
 		return -ENOMEM;
 	}
 
@@ -452,7 +452,7 @@ static int start_single_kthread(struct trace_array *tr)
 	wake_up_process(kthread);
 
 out_put_cpus:
-	put_online_cpus();
+	cpus_read_unlock();
 	return 0;
 }
 
@@ -479,10 +479,10 @@ static void stop_per_cpu_kthreads(void)
 {
 	unsigned int cpu;
 
-	get_online_cpus();
+	cpus_read_lock();
 	for_each_online_cpu(cpu)
 		stop_cpu_kthread(cpu);
-	put_online_cpus();
+	cpus_read_unlock();
 }
 
 /*
@@ -515,7 +515,7 @@ static void hwlat_hotplug_workfn(struct work_struct *dummy)
 
 	mutex_lock(&trace_types_lock);
 	mutex_lock(&hwlat_data.lock);
-	get_online_cpus();
+	cpus_read_lock();
 
 	if (!hwlat_busy || hwlat_data.thread_mode != MODE_PER_CPU)
 		goto out_unlock;
@@ -526,7 +526,7 @@ static void hwlat_hotplug_workfn(struct work_struct *dummy)
 	start_cpu_kthread(cpu);
 
 out_unlock:
-	put_online_cpus();
+	cpus_read_unlock();
 	mutex_unlock(&hwlat_data.lock);
 	mutex_unlock(&trace_types_lock);
 }
@@ -582,7 +582,7 @@ static int start_per_cpu_kthreads(struct trace_array *tr)
 	unsigned int cpu;
 	int retval;
 
-	get_online_cpus();
+	cpus_read_lock();
 	/*
 	 * Run only on CPUs in which hwlat is allowed to run.
 	 */
@@ -596,12 +596,12 @@ static int start_per_cpu_kthreads(struct trace_array *tr)
 		if (retval)
 			goto out_error;
 	}
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return 0;
 
 out_error:
-	put_online_cpus();
+	cpus_read_unlock();
 	stop_per_cpu_kthreads();
 	return retval;
 }
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index b61eefe5ccf5..65b08b8e5bf8 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -1498,12 +1498,12 @@ static void stop_per_cpu_kthreads(void)
 {
 	int cpu;
 
-	get_online_cpus();
+	cpus_read_lock();
 
 	for_each_online_cpu(cpu)
 		stop_kthread(cpu);
 
-	put_online_cpus();
+	cpus_read_unlock();
 }
 
 /*
@@ -1551,7 +1551,7 @@ static int start_per_cpu_kthreads(struct trace_array *tr)
 	int retval;
 	int cpu;
 
-	get_online_cpus();
+	cpus_read_lock();
 	/*
 	 * Run only on CPUs in which trace and osnoise are allowed to run.
 	 */
@@ -1572,7 +1572,7 @@ static int start_per_cpu_kthreads(struct trace_array *tr)
 		}
 	}
 
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return 0;
 }
@@ -1590,7 +1590,7 @@ static void osnoise_hotplug_workfn(struct work_struct *dummy)
 		goto out_unlock_trace;
 
 	mutex_lock(&interface_lock);
-	get_online_cpus();
+	cpus_read_lock();
 
 	if (!cpumask_test_cpu(cpu, &osnoise_cpumask))
 		goto out_unlock;
@@ -1601,7 +1601,7 @@ static void osnoise_hotplug_workfn(struct work_struct *dummy)
 	start_kthread(cpu);
 
 out_unlock:
-	put_online_cpus();
+	cpus_read_unlock();
 	mutex_unlock(&interface_lock);
 out_unlock_trace:
 	mutex_unlock(&trace_types_lock);
@@ -1743,11 +1743,11 @@ osnoise_cpus_write(struct file *filp, const char __user *ubuf, size_t count,
 	/*
 	 * osnoise_cpumask is read by CPU hotplug operations.
 	 */
-	get_online_cpus();
+	cpus_read_lock();
 
 	cpumask_copy(&osnoise_cpumask, osnoise_cpumask_new);
 
-	put_online_cpus();
+	cpus_read_unlock();
 	mutex_unlock(&interface_lock);
 
 	if (running)
-- 
2.30.2

[for-next][PATCH 2/9] tracing: Add DYNAMIC flag for dynamic events

[Steven Rostedt]

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

To differentiate between static and dynamic events, add a new flag
DYNAMIC to the event flags that all dynamic events have set. This will
allow to differentiate when attaching to a dynamic event from a static
event.

Static events have a mod pointer that references the module they were
created in (or NULL for core kernel). This can be incremented when the
event has something attached to it. But there exists no such mechanism for
dynamic events. This is dangerous as the dynamic events may now disappear
without the "attachment" knowing that it no longer exists.

To enforce the dynamic flag, change dyn_event_add() to pass the event that
is being created such that it can set the DYNAMIC flag of the event. This
helps make sure that no location that creates a dynamic event misses
setting this flag.

Link: https://lore.kernel.org/linux-trace-devel/20210813004448.51c7de69ce432d338f4d226b@kernel.org/
Link: https://lkml.kernel.org/r/20210817035026.936958254@goodmis.org

Suggested-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/trace_events.h      | 3 +++
 kernel/trace/trace_dynevent.h     | 4 +++-
 kernel/trace/trace_events_synth.c | 2 +-
 kernel/trace/trace_kprobe.c       | 4 ++--
 kernel/trace/trace_uprobe.c       | 4 ++--
 5 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index ad413b382a3c..53c9dffd87fd 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -310,6 +310,7 @@ enum {
 	TRACE_EVENT_FL_NO_SET_FILTER_BIT,
 	TRACE_EVENT_FL_IGNORE_ENABLE_BIT,
 	TRACE_EVENT_FL_TRACEPOINT_BIT,
+	TRACE_EVENT_FL_DYNAMIC_BIT,
 	TRACE_EVENT_FL_KPROBE_BIT,
 	TRACE_EVENT_FL_UPROBE_BIT,
 };
@@ -321,6 +322,7 @@ enum {
  *  NO_SET_FILTER - Set when filter has error and is to be ignored
  *  IGNORE_ENABLE - For trace internal events, do not enable with debugfs file
  *  TRACEPOINT    - Event is a tracepoint
+ *  DYNAMIC       - Event is a dynamic event (created at run time)
  *  KPROBE        - Event is a kprobe
  *  UPROBE        - Event is a uprobe
  */
@@ -330,6 +332,7 @@ enum {
 	TRACE_EVENT_FL_NO_SET_FILTER	= (1 << TRACE_EVENT_FL_NO_SET_FILTER_BIT),
 	TRACE_EVENT_FL_IGNORE_ENABLE	= (1 << TRACE_EVENT_FL_IGNORE_ENABLE_BIT),
 	TRACE_EVENT_FL_TRACEPOINT	= (1 << TRACE_EVENT_FL_TRACEPOINT_BIT),
+	TRACE_EVENT_FL_DYNAMIC		= (1 << TRACE_EVENT_FL_DYNAMIC_BIT),
 	TRACE_EVENT_FL_KPROBE		= (1 << TRACE_EVENT_FL_KPROBE_BIT),
 	TRACE_EVENT_FL_UPROBE		= (1 << TRACE_EVENT_FL_UPROBE_BIT),
 };
diff --git a/kernel/trace/trace_dynevent.h b/kernel/trace/trace_dynevent.h
index 7754936b57ee..936477a111d3 100644
--- a/kernel/trace/trace_dynevent.h
+++ b/kernel/trace/trace_dynevent.h
@@ -76,13 +76,15 @@ int dyn_event_init(struct dyn_event *ev, struct dyn_event_operations *ops)
 	return 0;
 }
 
-static inline int dyn_event_add(struct dyn_event *ev)
+static inline int dyn_event_add(struct dyn_event *ev,
+				struct trace_event_call *call)
 {
 	lockdep_assert_held(&event_mutex);
 
 	if (!ev || !ev->ops)
 		return -EINVAL;
 
+	call->flags |= TRACE_EVENT_FL_DYNAMIC;
 	list_add_tail(&ev->list, &dyn_event_list);
 	return 0;
 }
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 9315fc03e303..f4f5489e1e28 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -1298,7 +1298,7 @@ static int __create_synth_event(const char *name, const char *raw_fields)
 	}
 	ret = register_synth_event(event);
 	if (!ret)
-		dyn_event_add(&event->devent);
+		dyn_event_add(&event->devent, &event->call);
 	else
 		free_synth_event(event);
  out:
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index ea6178cb5e33..bfef43bfce37 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -618,7 +618,7 @@ static int append_trace_kprobe(struct trace_kprobe *tk, struct trace_kprobe *to)
 	if (ret)
 		trace_probe_unlink(&tk->tp);
 	else
-		dyn_event_add(&tk->devent);
+		dyn_event_add(&tk->devent, trace_probe_event_call(&tk->tp));
 
 	return ret;
 }
@@ -661,7 +661,7 @@ static int register_trace_kprobe(struct trace_kprobe *tk)
 	if (ret < 0)
 		unregister_kprobe_event(tk);
 	else
-		dyn_event_add(&tk->devent);
+		dyn_event_add(&tk->devent, trace_probe_event_call(&tk->tp));
 
 end:
 	mutex_unlock(&event_mutex);
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 9b50869a5ddb..50eca53b8d22 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -455,7 +455,7 @@ static int append_trace_uprobe(struct trace_uprobe *tu, struct trace_uprobe *to)
 	/* Append to existing event */
 	ret = trace_probe_append(&tu->tp, &to->tp);
 	if (!ret)
-		dyn_event_add(&tu->devent);
+		dyn_event_add(&tu->devent, trace_probe_event_call(&tu->tp));
 
 	return ret;
 }
@@ -518,7 +518,7 @@ static int register_trace_uprobe(struct trace_uprobe *tu)
 		goto end;
 	}
 
-	dyn_event_add(&tu->devent);
+	dyn_event_add(&tu->devent, trace_probe_event_call(&tu->tp));
 
 end:
 	mutex_unlock(&event_mutex);
-- 
2.30.2

[for-next][PATCH 3/9] tracing: Have dynamic events have a ref counter

[Steven Rostedt]

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

As dynamic events are not created by modules, if something is attached to
one, calling "try_module_get()" on its "mod" field, is not going to keep
the dynamic event from going away.

Since dynamic events do not need the "mod" pointer of the event structure,
make a union out of it in order to save memory (there's one structure for
each of the thousand+ events in the kernel), and have any event with the
DYNAMIC flag set to use a ref counter instead.

Link: https://lore.kernel.org/linux-trace-devel/20210813004448.51c7de69ce432d338f4d226b@kernel.org/
Link: https://lkml.kernel.org/r/20210817035027.174869074@goodmis.org

Suggested-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/trace_events.h        | 45 ++++++++++++++++++++++++++++-
 kernel/trace/trace.c                |  4 +--
 kernel/trace/trace_dynevent.c       | 38 ++++++++++++++++++++++++
 kernel/trace/trace_event_perf.c     |  6 ++--
 kernel/trace/trace_events.c         | 22 +++++++++-----
 kernel/trace/trace_events_synth.c   | 19 +++++++-----
 kernel/trace/trace_events_trigger.c |  6 ++--
 kernel/trace/trace_kprobe.c         |  4 +++
 kernel/trace/trace_uprobe.c         |  4 +++
 9 files changed, 124 insertions(+), 24 deletions(-)

diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 53c9dffd87fd..9564c4d9a3b6 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -350,7 +350,14 @@ struct trace_event_call {
 	struct trace_event	event;
 	char			*print_fmt;
 	struct event_filter	*filter;
-	void			*mod;
+	/*
+	 * Static events can disappear with modules,
+	 * where as dynamic ones need their own ref count.
+	 */
+	union {
+		void				*module;
+		atomic_t			refcnt;
+	};
 	void			*data;
 
 	/* See the TRACE_EVENT_FL_* flags above */
@@ -366,6 +373,42 @@ struct trace_event_call {
 #endif
 };
 
+#ifdef CONFIG_DYNAMIC_EVENTS
+bool trace_event_dyn_try_get_ref(struct trace_event_call *call);
+void trace_event_dyn_put_ref(struct trace_event_call *call);
+bool trace_event_dyn_busy(struct trace_event_call *call);
+#else
+static inline bool trace_event_dyn_try_get_ref(struct trace_event_call *call)
+{
+	/* Without DYNAMIC_EVENTS configured, nothing should be calling this */
+	return false;
+}
+static inline void trace_event_dyn_put_ref(struct trace_event_call *call)
+{
+}
+static inline bool trace_event_dyn_busy(struct trace_event_call *call)
+{
+	/* Nothing should call this without DYNAIMIC_EVENTS configured. */
+	return true;
+}
+#endif
+
+static inline bool trace_event_try_get_ref(struct trace_event_call *call)
+{
+	if (call->flags & TRACE_EVENT_FL_DYNAMIC)
+		return trace_event_dyn_try_get_ref(call);
+	else
+		return try_module_get(call->module);
+}
+
+static inline void trace_event_put_ref(struct trace_event_call *call)
+{
+	if (call->flags & TRACE_EVENT_FL_DYNAMIC)
+		trace_event_dyn_put_ref(call);
+	else
+		module_put(call->module);
+}
+
 #ifdef CONFIG_PERF_EVENTS
 static inline bool bpf_prog_array_valid(struct trace_event_call *call)
 {
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index be0169594de5..8425c3d70895 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3697,11 +3697,11 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str)
 		return false;
 
 	event = container_of(trace_event, struct trace_event_call, event);
-	if (!event->mod)
+	if ((event->flags & TRACE_EVENT_FL_DYNAMIC) || !event->module)
 		return false;
 
 	/* Would rather have rodata, but this will suffice */
-	if (within_module_core(addr, event->mod))
+	if (within_module_core(addr, event->module))
 		return true;
 
 	return false;
diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index e57cc0870892..1110112e55bd 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -13,11 +13,49 @@
 #include <linux/tracefs.h>
 
 #include "trace.h"
+#include "trace_output.h"	/* for trace_event_sem */
 #include "trace_dynevent.h"
 
 static DEFINE_MUTEX(dyn_event_ops_mutex);
 static LIST_HEAD(dyn_event_ops_list);
 
+bool trace_event_dyn_try_get_ref(struct trace_event_call *dyn_call)
+{
+	struct trace_event_call *call;
+	bool ret = false;
+
+	if (WARN_ON_ONCE(!(dyn_call->flags & TRACE_EVENT_FL_DYNAMIC)))
+		return false;
+
+	down_read(&trace_event_sem);
+	list_for_each_entry(call, &ftrace_events, list) {
+		if (call == dyn_call) {
+			atomic_inc(&dyn_call->refcnt);
+			ret = true;
+		}
+	}
+	up_read(&trace_event_sem);
+	return ret;
+}
+
+void trace_event_dyn_put_ref(struct trace_event_call *call)
+{
+	if (WARN_ON_ONCE(!(call->flags & TRACE_EVENT_FL_DYNAMIC)))
+		return;
+
+	if (WARN_ON_ONCE(atomic_read(&call->refcnt) <= 0)) {
+		atomic_set(&call->refcnt, 0);
+		return;
+	}
+
+	atomic_dec(&call->refcnt);
+}
+
+bool trace_event_dyn_busy(struct trace_event_call *call)
+{
+	return atomic_read(&call->refcnt) != 0;
+}
+
 int dyn_event_register(struct dyn_event_operations *ops)
 {
 	if (!ops || !ops->create || !ops->show || !ops->is_busy ||
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 03be4435d103..6aed10e2f7ce 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -177,7 +177,7 @@ static void perf_trace_event_unreg(struct perf_event *p_event)
 		}
 	}
 out:
-	module_put(tp_event->mod);
+	trace_event_put_ref(tp_event);
 }
 
 static int perf_trace_event_open(struct perf_event *p_event)
@@ -224,10 +224,10 @@ int perf_trace_init(struct perf_event *p_event)
 	list_for_each_entry(tp_event, &ftrace_events, list) {
 		if (tp_event->event.type == event_id &&
 		    tp_event->class && tp_event->class->reg &&
-		    try_module_get(tp_event->mod)) {
+		    trace_event_try_get_ref(tp_event)) {
 			ret = perf_trace_event_init(tp_event, p_event);
 			if (ret)
-				module_put(tp_event->mod);
+				trace_event_put_ref(tp_event);
 			break;
 		}
 	}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 80e96989770e..1349b6de5eeb 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2525,7 +2525,10 @@ __register_event(struct trace_event_call *call, struct module *mod)
 		return ret;
 
 	list_add(&call->list, &ftrace_events);
-	call->mod = mod;
+	if (call->flags & TRACE_EVENT_FL_DYNAMIC)
+		atomic_set(&call->refcnt, 0);
+	else
+		call->module = mod;
 
 	return 0;
 }
@@ -2839,7 +2842,9 @@ static void trace_module_remove_events(struct module *mod)
 
 	down_write(&trace_event_sem);
 	list_for_each_entry_safe(call, p, &ftrace_events, list) {
-		if (call->mod == mod)
+		if ((call->flags & TRACE_EVENT_FL_DYNAMIC) || !call->module)
+			continue;
+		if (call->module == mod)
 			__trace_remove_event_call(call);
 	}
 	up_write(&trace_event_sem);
@@ -2982,7 +2987,7 @@ struct trace_event_file *trace_get_event_file(const char *instance,
 	}
 
 	/* Don't let event modules unload while in use */
-	ret = try_module_get(file->event_call->mod);
+	ret = trace_event_try_get_ref(file->event_call);
 	if (!ret) {
 		trace_array_put(tr);
 		ret = -EBUSY;
@@ -3012,7 +3017,7 @@ EXPORT_SYMBOL_GPL(trace_get_event_file);
 void trace_put_event_file(struct trace_event_file *file)
 {
 	mutex_lock(&event_mutex);
-	module_put(file->event_call->mod);
+	trace_event_put_ref(file->event_call);
 	mutex_unlock(&event_mutex);
 
 	trace_array_put(file->tr);
@@ -3147,7 +3152,7 @@ static int free_probe_data(void *data)
 	if (!edata->ref) {
 		/* Remove the SOFT_MODE flag */
 		__ftrace_event_enable_disable(edata->file, 0, 1);
-		module_put(edata->file->event_call->mod);
+		trace_event_put_ref(edata->file->event_call);
 		kfree(edata);
 	}
 	return 0;
@@ -3280,7 +3285,7 @@ event_enable_func(struct trace_array *tr, struct ftrace_hash *hash,
 
  out_reg:
 	/* Don't let event modules unload while probe registered */
-	ret = try_module_get(file->event_call->mod);
+	ret = trace_event_try_get_ref(file->event_call);
 	if (!ret) {
 		ret = -EBUSY;
 		goto out_free;
@@ -3310,7 +3315,7 @@ event_enable_func(struct trace_array *tr, struct ftrace_hash *hash,
  out_disable:
 	__ftrace_event_enable_disable(file, 0, 1);
  out_put:
-	module_put(file->event_call->mod);
+	trace_event_put_ref(file->event_call);
  out_free:
 	kfree(data);
 	goto out;
@@ -3376,7 +3381,8 @@ void __trace_early_add_events(struct trace_array *tr)
 
 	list_for_each_entry(call, &ftrace_events, list) {
 		/* Early boot up should not have any modules loaded */
-		if (WARN_ON_ONCE(call->mod))
+		if (!(call->flags & TRACE_EVENT_FL_DYNAMIC) &&
+		    WARN_ON_ONCE(call->module))
 			continue;
 
 		ret = __trace_early_add_new_event(call, tr);
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index f4f5489e1e28..d54094b7a9d7 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -1369,13 +1369,15 @@ static int destroy_synth_event(struct synth_event *se)
 	int ret;
 
 	if (se->ref)
-		ret = -EBUSY;
-	else {
-		ret = unregister_synth_event(se);
-		if (!ret) {
-			dyn_event_remove(&se->devent);
-			free_synth_event(se);
-		}
+		return -EBUSY;
+
+	if (trace_event_dyn_busy(&se->call))
+		return -EBUSY;
+
+	ret = unregister_synth_event(se);
+	if (!ret) {
+		dyn_event_remove(&se->devent);
+		free_synth_event(se);
 	}
 
 	return ret;
@@ -2102,6 +2104,9 @@ static int synth_event_release(struct dyn_event *ev)
 	if (event->ref)
 		return -EBUSY;
 
+	if (trace_event_dyn_busy(&event->call))
+		return -EBUSY;
+
 	ret = unregister_synth_event(event);
 	if (ret)
 		return ret;
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index cf84d0f6583a..6b11e335a62e 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -1334,7 +1334,7 @@ void event_enable_trigger_free(struct event_trigger_ops *ops,
 	if (!data->ref) {
 		/* Remove the SOFT_MODE flag */
 		trace_event_enable_disable(enable_data->file, 0, 1);
-		module_put(enable_data->file->event_call->mod);
+		trace_event_put_ref(enable_data->file->event_call);
 		trigger_data_free(data);
 		kfree(enable_data);
 	}
@@ -1481,7 +1481,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
 
  out_reg:
 	/* Don't let event modules unload while probe registered */
-	ret = try_module_get(event_enable_file->event_call->mod);
+	ret = trace_event_try_get_ref(event_enable_file->event_call);
 	if (!ret) {
 		ret = -EBUSY;
 		goto out_free;
@@ -1510,7 +1510,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
  out_disable:
 	trace_event_enable_disable(event_enable_file, 0, 1);
  out_put:
-	module_put(event_enable_file->event_call->mod);
+	trace_event_put_ref(event_enable_file->event_call);
  out_free:
 	if (cmd_ops->set_filter)
 		cmd_ops->set_filter(NULL, trigger_data, NULL);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index bfef43bfce37..82c3b86013b2 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -543,6 +543,10 @@ static int unregister_trace_kprobe(struct trace_kprobe *tk)
 	if (trace_probe_is_enabled(&tk->tp))
 		return -EBUSY;
 
+	/* If there's a reference to the dynamic event */
+	if (trace_event_dyn_busy(trace_probe_event_call(&tk->tp)))
+		return -EBUSY;
+
 	/* Will fail if probe is being used by ftrace or perf */
 	if (unregister_kprobe_event(tk))
 		return -EBUSY;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 50eca53b8d22..1e2a92e7607d 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -393,6 +393,10 @@ static int unregister_trace_uprobe(struct trace_uprobe *tu)
 	if (trace_probe_has_sibling(&tu->tp))
 		goto unreg;
 
+	/* If there's a reference to the dynamic event */
+	if (trace_event_dyn_busy(trace_probe_event_call(&tu->tp)))
+		return -EBUSY;
+
 	ret = unregister_uprobe_event(tu);
 	if (ret)
 		return ret;
-- 
2.30.2

[for-next][PATCH 4/9] tracing/probe: Have traceprobe_parse_probe_arg() take a const arg

[Steven Rostedt]

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

The two places that call traceprobe_parse_probe_arg() allocate a temporary
buffer to copy the argv[i] into, because argv[i] is constant and the
traceprobe_parse_probe_arg() will modify it to do the parsing. These two
places allocate this buffer and then free it right after calling this
function, leaving the onus of this allocation to the caller.

As there's about to be a third user of this function that will have to do
the same thing, instead of having the caller allocate the temporary
buffer, simply move that allocation into the traceprobe_parse_probe_arg()
itself, which will simplify the code of the callers.

Link: https://lkml.kernel.org/r/20210817035027.385422828@goodmis.org

Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_kprobe.c |  9 +------
 kernel/trace/trace_probe.c  | 47 ++++++++++++++++++++++---------------
 kernel/trace/trace_probe.h  |  2 +-
 kernel/trace/trace_uprobe.c |  9 +------
 4 files changed, 31 insertions(+), 36 deletions(-)

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 82c3b86013b2..ed1e3c2087ab 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -873,15 +873,8 @@ static int __trace_kprobe_create(int argc, const char *argv[])
 
 	/* parse arguments */
 	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
-		tmp = kstrdup(argv[i], GFP_KERNEL);
-		if (!tmp) {
-			ret = -ENOMEM;
-			goto error;
-		}
-
 		trace_probe_log_set_index(i + 2);
-		ret = traceprobe_parse_probe_arg(&tk->tp, i, tmp, flags);
-		kfree(tmp);
+		ret = traceprobe_parse_probe_arg(&tk->tp, i, argv[i], flags);
 		if (ret)
 			goto error;	/* This can be -ENOMEM */
 	}
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 15413ad7cef2..ef717b373443 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -540,26 +540,34 @@ static int __parse_bitfield_probe_arg(const char *bf,
 }
 
 /* String length checking wrapper */
-static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
+static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
 		struct probe_arg *parg, unsigned int flags, int offset)
 {
 	struct fetch_insn *code, *scode, *tmp = NULL;
 	char *t, *t2, *t3;
+	char *arg;
 	int ret, len;
 
+	arg = kstrdup(argv, GFP_KERNEL);
+	if (!arg)
+		return -ENOMEM;
+
+	ret = -EINVAL;
 	len = strlen(arg);
 	if (len > MAX_ARGSTR_LEN) {
 		trace_probe_log_err(offset, ARG_TOO_LONG);
-		return -EINVAL;
+		goto out;
 	} else if (len == 0) {
 		trace_probe_log_err(offset, NO_ARG_BODY);
-		return -EINVAL;
+		goto out;
 	}
 
+	ret = -ENOMEM;
 	parg->comm = kstrdup(arg, GFP_KERNEL);
 	if (!parg->comm)
-		return -ENOMEM;
+		goto out;
 
+	ret = -EINVAL;
 	t = strchr(arg, ':');
 	if (t) {
 		*t = '\0';
@@ -571,22 +579,22 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 				offset += t2 + strlen(t2) - arg;
 				trace_probe_log_err(offset,
 						    ARRAY_NO_CLOSE);
-				return -EINVAL;
+				goto out;
 			} else if (t3[1] != '\0') {
 				trace_probe_log_err(offset + t3 + 1 - arg,
 						    BAD_ARRAY_SUFFIX);
-				return -EINVAL;
+				goto out;
 			}
 			*t3 = '\0';
 			if (kstrtouint(t2, 0, &parg->count) || !parg->count) {
 				trace_probe_log_err(offset + t2 - arg,
 						    BAD_ARRAY_NUM);
-				return -EINVAL;
+				goto out;
 			}
 			if (parg->count > MAX_ARRAY_LEN) {
 				trace_probe_log_err(offset + t2 - arg,
 						    ARRAY_TOO_BIG);
-				return -EINVAL;
+				goto out;
 			}
 		}
 	}
@@ -598,29 +606,30 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 	if (strcmp(arg, "$comm") == 0 || strncmp(arg, "\\\"", 2) == 0) {
 		/* The type of $comm must be "string", and not an array. */
 		if (parg->count || (t && strcmp(t, "string")))
-			return -EINVAL;
+			goto out;
 		parg->type = find_fetch_type("string");
 	} else
 		parg->type = find_fetch_type(t);
 	if (!parg->type) {
 		trace_probe_log_err(offset + (t ? (t - arg) : 0), BAD_TYPE);
-		return -EINVAL;
+		goto out;
 	}
 	parg->offset = *size;
 	*size += parg->type->size * (parg->count ?: 1);
 
+	ret = -ENOMEM;
 	if (parg->count) {
 		len = strlen(parg->type->fmttype) + 6;
 		parg->fmt = kmalloc(len, GFP_KERNEL);
 		if (!parg->fmt)
-			return -ENOMEM;
+			goto out;
 		snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype,
 			 parg->count);
 	}
 
 	code = tmp = kcalloc(FETCH_INSN_MAX, sizeof(*code), GFP_KERNEL);
 	if (!code)
-		return -ENOMEM;
+		goto out;
 	code[FETCH_INSN_MAX - 1].op = FETCH_OP_END;
 
 	ret = parse_probe_arg(arg, parg->type, &code, &code[FETCH_INSN_MAX - 1],
@@ -628,6 +637,7 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 	if (ret)
 		goto fail;
 
+	ret = -EINVAL;
 	/* Store operation */
 	if (!strcmp(parg->type->name, "string") ||
 	    !strcmp(parg->type->name, "ustring")) {
@@ -636,7 +646,6 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 		    code->op != FETCH_OP_DATA) {
 			trace_probe_log_err(offset + (t ? (t - arg) : 0),
 					    BAD_STRING);
-			ret = -EINVAL;
 			goto fail;
 		}
 		if ((code->op == FETCH_OP_IMM || code->op == FETCH_OP_COMM ||
@@ -650,7 +659,6 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 			code++;
 			if (code->op != FETCH_OP_NOP) {
 				trace_probe_log_err(offset, TOO_MANY_OPS);
-				ret = -EINVAL;
 				goto fail;
 			}
 		}
@@ -672,7 +680,6 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 		code++;
 		if (code->op != FETCH_OP_NOP) {
 			trace_probe_log_err(offset, TOO_MANY_OPS);
-			ret = -EINVAL;
 			goto fail;
 		}
 		code->op = FETCH_OP_ST_RAW;
@@ -687,6 +694,7 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 			goto fail;
 		}
 	}
+	ret = -EINVAL;
 	/* Loop(Array) operation */
 	if (parg->count) {
 		if (scode->op != FETCH_OP_ST_MEM &&
@@ -694,13 +702,11 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 		    scode->op != FETCH_OP_ST_USTRING) {
 			trace_probe_log_err(offset + (t ? (t - arg) : 0),
 					    BAD_STRING);
-			ret = -EINVAL;
 			goto fail;
 		}
 		code++;
 		if (code->op != FETCH_OP_NOP) {
 			trace_probe_log_err(offset, TOO_MANY_OPS);
-			ret = -EINVAL;
 			goto fail;
 		}
 		code->op = FETCH_OP_LP_ARRAY;
@@ -709,6 +715,7 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 	code++;
 	code->op = FETCH_OP_END;
 
+	ret = 0;
 	/* Shrink down the code buffer */
 	parg->code = kcalloc(code - tmp + 1, sizeof(*code), GFP_KERNEL);
 	if (!parg->code)
@@ -724,6 +731,8 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 				kfree(code->data);
 	}
 	kfree(tmp);
+out:
+	kfree(arg);
 
 	return ret;
 }
@@ -745,11 +754,11 @@ static int traceprobe_conflict_field_name(const char *name,
 	return 0;
 }
 
-int traceprobe_parse_probe_arg(struct trace_probe *tp, int i, char *arg,
+int traceprobe_parse_probe_arg(struct trace_probe *tp, int i, const char *arg,
 				unsigned int flags)
 {
 	struct probe_arg *parg = &tp->args[i];
-	char *body;
+	const char *body;
 
 	/* Increment count for freeing args in error case */
 	tp->nr_args++;
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 227d518e5ba5..42aa084902fa 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -354,7 +354,7 @@ int trace_probe_create(const char *raw_command, int (*createfn)(int, const char
 #define TPARG_FL_MASK	GENMASK(2, 0)
 
 extern int traceprobe_parse_probe_arg(struct trace_probe *tp, int i,
-				char *arg, unsigned int flags);
+				const char *argv, unsigned int flags);
 
 extern int traceprobe_update_arg(struct probe_arg *arg);
 extern void traceprobe_free_probe_arg(struct probe_arg *arg);
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 1e2a92e7607d..93ff96541971 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -684,16 +684,9 @@ static int __trace_uprobe_create(int argc, const char **argv)
 
 	/* parse arguments */
 	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
-		tmp = kstrdup(argv[i], GFP_KERNEL);
-		if (!tmp) {
-			ret = -ENOMEM;
-			goto error;
-		}
-
 		trace_probe_log_set_index(i + 2);
-		ret = traceprobe_parse_probe_arg(&tu->tp, i, tmp,
+		ret = traceprobe_parse_probe_arg(&tu->tp, i, argv[i],
 					is_return ? TPARG_FL_RETURN : 0);
-		kfree(tmp);
 		if (ret)
 			goto error;
 	}
-- 
2.30.2

[for-next][PATCH 5/9] tracing/probes: Allow for dot delimiter as well as slash for system names

[Steven Rostedt]

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

Kprobe and uprobe events can add a "system" to the events that are created
via the kprobe_events and uprobe_events files respectively. If they do not
include a "system" in the name, then the default "kprobes" or "uprobes" is
used. The current notation to specify a system for one of these probe
events is to add a '/' delimiter in the name, where the content before the
'/' will be the system to use, and the content after will be the event
name.

 echo 'p:my_system/my_event' > kprobe_events

But this is inconsistent with the way histogram triggers separate their
system / event names. The histogram triggers use a '.' delimiter, which
can be confusing.

To allow this to be more consistent, as well as keep backward
compatibility, allow the kprobe and uprobe events to denote a system name
with either a '/' or a '.'.

That is:

  echo 'p:my_system/my_event' > kprobe_events

is equivalent to:

  echo 'p:my_system.my_event' > kprobe_events

Link: https://lore.kernel.org/linux-trace-devel/20210813004448.51c7de69ce432d338f4d226b@kernel.org/
Link: https://lkml.kernel.org/r/20210817035027.580493202@goodmis.org

Suggested-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_probe.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index ef717b373443..0916a9964719 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -233,6 +233,9 @@ int traceprobe_parse_event_name(const char **pevent, const char **pgroup,
 	int len;
 
 	slash = strchr(event, '/');
+	if (!slash)
+		slash = strchr(event, '.');
+
 	if (slash) {
 		if (slash == event) {
 			trace_probe_log_err(offset, NO_GROUP_NAME);
-- 
2.30.2

[for-next][PATCH 6/9] tracing/probes: Use struct_size() instead of defining custom macros

[Steven Rostedt]

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

Remove SIZEOF_TRACE_KPROBE() and SIZEOF_TRACE_UPROBE() and use
struct_size() as that's what it is made for. No need to have custom
macros. Especially since struct_size() has some extra memory checks for
correctness.

Link: https://lkml.kernel.org/r/20210817035027.795000217@goodmis.org

Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_kprobe.c | 6 +-----
 kernel/trace/trace_uprobe.c | 6 +-----
 2 files changed, 2 insertions(+), 10 deletions(-)

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index ed1e3c2087ab..ca726c9d0859 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -80,10 +80,6 @@ static struct trace_kprobe *to_trace_kprobe(struct dyn_event *ev)
 	for_each_dyn_event(dpos)		\
 		if (is_trace_kprobe(dpos) && (pos = to_trace_kprobe(dpos)))
 
-#define SIZEOF_TRACE_KPROBE(n)				\
-	(offsetof(struct trace_kprobe, tp.args) +	\
-	(sizeof(struct probe_arg) * (n)))
-
 static nokprobe_inline bool trace_kprobe_is_return(struct trace_kprobe *tk)
 {
 	return tk->rp.handler != NULL;
@@ -265,7 +261,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group,
 	struct trace_kprobe *tk;
 	int ret = -ENOMEM;
 
-	tk = kzalloc(SIZEOF_TRACE_KPROBE(nargs), GFP_KERNEL);
+	tk = kzalloc(struct_size(tk, tp.args, nargs), GFP_KERNEL);
 	if (!tk)
 		return ERR_PTR(ret);
 
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 93ff96541971..590bb9a02f8d 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -83,10 +83,6 @@ static struct trace_uprobe *to_trace_uprobe(struct dyn_event *ev)
 	for_each_dyn_event(dpos)		\
 		if (is_trace_uprobe(dpos) && (pos = to_trace_uprobe(dpos)))
 
-#define SIZEOF_TRACE_UPROBE(n)				\
-	(offsetof(struct trace_uprobe, tp.args) +	\
-	(sizeof(struct probe_arg) * (n)))
-
 static int register_uprobe_event(struct trace_uprobe *tu);
 static int unregister_uprobe_event(struct trace_uprobe *tu);
 
@@ -340,7 +336,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
 	struct trace_uprobe *tu;
 	int ret;
 
-	tu = kzalloc(SIZEOF_TRACE_UPROBE(nargs), GFP_KERNEL);
+	tu = kzalloc(struct_size(tu, tp.args, nargs), GFP_KERNEL);
 	if (!tu)
 		return ERR_PTR(-ENOMEM);
 
-- 
2.30.2

[for-next][PATCH 7/9] tracing/probe: Change traceprobe_set_print_fmt() to take a type

[Steven Rostedt]

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

Instead of a boolean "is_return" have traceprobe_set_print_fmt() take a
type (currently just PROBE_PRINT_NORMAL and PROBE_PRINT_RETURN). This will
simplify adding different types. For example, the development of the
event_probe, will need its own type as it prints an event, and not an IP.

Link: https://lkml.kernel.org/r/20210819041842.104626301@goodmis.org

Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_kprobe.c |  9 +++++++--
 kernel/trace/trace_probe.c  | 18 ++++++++++++------
 kernel/trace/trace_probe.h  |  7 ++++++-
 kernel/trace/trace_uprobe.c |  8 ++++++--
 4 files changed, 31 insertions(+), 11 deletions(-)

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index ca726c9d0859..c6fe7a6e3f35 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -742,6 +742,7 @@ static int __trace_kprobe_create(int argc, const char *argv[])
 	bool is_return = false;
 	char *symbol = NULL, *tmp = NULL;
 	const char *event = NULL, *group = KPROBE_EVENT_SYSTEM;
+	enum probe_print_type ptype;
 	int maxactive = 0;
 	long offset = 0;
 	void *addr = NULL;
@@ -875,7 +876,8 @@ static int __trace_kprobe_create(int argc, const char *argv[])
 			goto error;	/* This can be -ENOMEM */
 	}
 
-	ret = traceprobe_set_print_fmt(&tk->tp, is_return);
+	ptype = is_return ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL;
+	ret = traceprobe_set_print_fmt(&tk->tp, ptype);
 	if (ret < 0)
 		goto error;
 
@@ -1799,6 +1801,7 @@ struct trace_event_call *
 create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
 			  bool is_return)
 {
+	enum probe_print_type ptype;
 	struct trace_kprobe *tk;
 	int ret;
 	char *event;
@@ -1822,7 +1825,9 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
 
 	init_trace_event_call(tk);
 
-	if (traceprobe_set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0) {
+	ptype = trace_kprobe_is_return(tk) ?
+		PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL;
+	if (traceprobe_set_print_fmt(&tk->tp, ptype) < 0) {
 		ret = -ENOMEM;
 		goto error;
 	}
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 0916a9964719..9c9c83a063b2 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -851,19 +851,25 @@ int traceprobe_update_arg(struct probe_arg *arg)
 /* When len=0, we just calculate the needed length */
 #define LEN_OR_ZERO (len ? len - pos : 0)
 static int __set_print_fmt(struct trace_probe *tp, char *buf, int len,
-			   bool is_return)
+			   enum probe_print_type ptype)
 {
 	struct probe_arg *parg;
 	int i, j;
 	int pos = 0;
 	const char *fmt, *arg;
 
-	if (!is_return) {
+	switch (ptype) {
+	case PROBE_PRINT_NORMAL:
 		fmt = "(%lx)";
 		arg = "REC->" FIELD_STRING_IP;
-	} else {
+		break;
+	case PROBE_PRINT_RETURN:
 		fmt = "(%lx <- %lx)";
 		arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return 0;
 	}
 
 	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);
@@ -912,20 +918,20 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len,
 }
 #undef LEN_OR_ZERO
 
-int traceprobe_set_print_fmt(struct trace_probe *tp, bool is_return)
+int traceprobe_set_print_fmt(struct trace_probe *tp, enum probe_print_type ptype)
 {
 	struct trace_event_call *call = trace_probe_event_call(tp);
 	int len;
 	char *print_fmt;
 
 	/* First: called with 0 length to calculate the needed length */
-	len = __set_print_fmt(tp, NULL, 0, is_return);
+	len = __set_print_fmt(tp, NULL, 0, ptype);
 	print_fmt = kmalloc(len + 1, GFP_KERNEL);
 	if (!print_fmt)
 		return -ENOMEM;
 
 	/* Second: actually write the @print_fmt */
-	__set_print_fmt(tp, print_fmt, len + 1, is_return);
+	__set_print_fmt(tp, print_fmt, len + 1, ptype);
 	call->print_fmt = print_fmt;
 
 	return 0;
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 42aa084902fa..8adf5f3542a6 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -363,7 +363,12 @@ extern int traceprobe_split_symbol_offset(char *symbol, long *offset);
 int traceprobe_parse_event_name(const char **pevent, const char **pgroup,
 				char *buf, int offset);
 
-extern int traceprobe_set_print_fmt(struct trace_probe *tp, bool is_return);
+enum probe_print_type {
+	PROBE_PRINT_NORMAL,
+	PROBE_PRINT_RETURN,
+};
+
+extern int traceprobe_set_print_fmt(struct trace_probe *tp, enum probe_print_type ptype);
 
 #ifdef CONFIG_PERF_EVENTS
 extern struct trace_event_call *
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 590bb9a02f8d..09f8ca7f7ba0 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -536,6 +536,7 @@ static int __trace_uprobe_create(int argc, const char **argv)
 	const char *event = NULL, *group = UPROBE_EVENT_SYSTEM;
 	char *arg, *filename, *rctr, *rctr_end, *tmp;
 	char buf[MAX_EVENT_NAME_LEN];
+	enum probe_print_type ptype;
 	struct path path;
 	unsigned long offset, ref_ctr_offset;
 	bool is_return = false;
@@ -687,7 +688,8 @@ static int __trace_uprobe_create(int argc, const char **argv)
 			goto error;
 	}
 
-	ret = traceprobe_set_print_fmt(&tu->tp, is_ret_probe(tu));
+	ptype = is_ret_probe(tu) ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL;
+	ret = traceprobe_set_print_fmt(&tu->tp, ptype);
 	if (ret < 0)
 		goto error;
 
@@ -1578,6 +1580,7 @@ struct trace_event_call *
 create_local_trace_uprobe(char *name, unsigned long offs,
 			  unsigned long ref_ctr_offset, bool is_return)
 {
+	enum probe_print_type ptype;
 	struct trace_uprobe *tu;
 	struct path path;
 	int ret;
@@ -1612,7 +1615,8 @@ create_local_trace_uprobe(char *name, unsigned long offs,
 	tu->filename = kstrdup(name, GFP_KERNEL);
 	init_trace_event_call(tu);
 
-	if (traceprobe_set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0) {
+	ptype = is_ret_probe(tu) ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL;
+	if (traceprobe_set_print_fmt(&tu->tp, ptype) < 0) {
 		ret = -ENOMEM;
 		goto error;
 	}
-- 
2.30.2

[for-next][PATCH 8/9] tracing/probes: Have process_fetch_insn() take a void * instead of pt_regs

[Steven Rostedt]

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

In preparation to allow event probes to use the process_fetch_insn()
callback in trace_probe_tmpl.h, change the data passed to it from a
pointer to pt_regs, as the event probe will not be using regs, and make it
a void pointer instead.

Update the process_fetch_insn() callers for kprobe and uprobe events to
have the regs defined in the function and just typecast the void pointer
parameter.

Link: https://lkml.kernel.org/r/20210819041842.291622924@goodmis.org

Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_kprobe.c     | 3 ++-
 kernel/trace/trace_probe_tmpl.h | 6 +++---
 kernel/trace/trace_uprobe.c     | 3 ++-
 3 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index c6fe7a6e3f35..4b013d24f5a9 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1325,9 +1325,10 @@ probe_mem_read(void *dest, void *src, size_t size)
 
 /* Note that we don't verify it, since the code does not come from user space */
 static int
-process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, void *dest,
+process_fetch_insn(struct fetch_insn *code, void *rec, void *dest,
 		   void *base)
 {
+	struct pt_regs *regs = rec;
 	unsigned long val;
 
 retry:
diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h
index f003c5d02a3a..b3bdb8ddb862 100644
--- a/kernel/trace/trace_probe_tmpl.h
+++ b/kernel/trace/trace_probe_tmpl.h
@@ -54,7 +54,7 @@ fetch_apply_bitfield(struct fetch_insn *code, void *buf)
  * If dest is NULL, don't store result and return required dynamic data size.
  */
 static int
-process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs,
+process_fetch_insn(struct fetch_insn *code, void *rec,
 		   void *dest, void *base);
 static nokprobe_inline int fetch_store_strlen(unsigned long addr);
 static nokprobe_inline int
@@ -188,7 +188,7 @@ __get_data_size(struct trace_probe *tp, struct pt_regs *regs)
 
 /* Store the value of each argument */
 static nokprobe_inline void
-store_trace_args(void *data, struct trace_probe *tp, struct pt_regs *regs,
+store_trace_args(void *data, struct trace_probe *tp, void *rec,
 		 int header_size, int maxlen)
 {
 	struct probe_arg *arg;
@@ -203,7 +203,7 @@ store_trace_args(void *data, struct trace_probe *tp, struct pt_regs *regs,
 		/* Point the dynamic data area if needed */
 		if (unlikely(arg->dynamic))
 			*dl = make_data_loc(maxlen, dyndata - base);
-		ret = process_fetch_insn(arg->code, regs, dl, base);
+		ret = process_fetch_insn(arg->code, rec, dl, base);
 		if (unlikely(ret < 0 && arg->dynamic)) {
 			*dl = make_data_loc(0, dyndata - base);
 		} else {
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 09f8ca7f7ba0..d219ba50efbd 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -213,9 +213,10 @@ static unsigned long translate_user_vaddr(unsigned long file_offset)
 
 /* Note that we don't verify it, since the code does not come from user space */
 static int
-process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, void *dest,
+process_fetch_insn(struct fetch_insn *code, void *rec, void *dest,
 		   void *base)
 {
+	struct pt_regs *regs = rec;
 	unsigned long val;
 
 	/* 1st stage: get value from context */
-- 
2.30.2

[for-next][PATCH 9/9] tracing/probes: Reject events which have the same name of existing one

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Since kprobe_events and uprobe_events only check whether the
other same-type probe event has the same name or not, if the
user gives the same name of the existing tracepoint event (or
the other type of probe events), it silently fails to create
the tracefs entry (but registered.) as below.

/sys/kernel/tracing # ls events/task/task_rename
enable   filter   format   hist     id       trigger
/sys/kernel/tracing # echo p:task/task_rename vfs_read >> kprobe_events
[  113.048508] Could not create tracefs 'task_rename' directory
/sys/kernel/tracing # cat kprobe_events
p:task/task_rename vfs_read

To fix this issue, check whether the existing events have the
same name or not in trace_probe_register_event_call(). If exists,
it rejects to register the new event.

Link: https://lkml.kernel.org/r/162936876189.187130.17558311387542061930.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_kprobe.c |  6 +++++-
 kernel/trace/trace_probe.c  | 25 +++++++++++++++++++++++++
 kernel/trace/trace_probe.h  |  1 +
 kernel/trace/trace_uprobe.c |  6 +++++-
 4 files changed, 36 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 4b013d24f5a9..882c27044029 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -647,7 +647,11 @@ static int register_trace_kprobe(struct trace_kprobe *tk)
 	/* Register new event */
 	ret = register_kprobe_event(tk);
 	if (ret) {
-		pr_warn("Failed to register probe event(%d)\n", ret);
+		if (ret == -EEXIST) {
+			trace_probe_log_set_index(0);
+			trace_probe_log_err(0, EVENT_EXIST);
+		} else
+			pr_warn("Failed to register probe event(%d)\n", ret);
 		goto end;
 	}
 
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 9c9c83a063b2..782c00eb6859 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -1047,11 +1047,36 @@ int trace_probe_init(struct trace_probe *tp, const char *event,
 	return ret;
 }
 
+static struct trace_event_call *
+find_trace_event_call(const char *system, const char *event_name)
+{
+	struct trace_event_call *tp_event;
+	const char *name;
+
+	list_for_each_entry(tp_event, &ftrace_events, list) {
+		if (!tp_event->class->system ||
+		    strcmp(system, tp_event->class->system))
+			continue;
+		name = trace_event_name(tp_event);
+		if (!name || strcmp(event_name, name))
+			continue;
+		return tp_event;
+	}
+
+	return NULL;
+}
+
 int trace_probe_register_event_call(struct trace_probe *tp)
 {
 	struct trace_event_call *call = trace_probe_event_call(tp);
 	int ret;
 
+	lockdep_assert_held(&event_mutex);
+
+	if (find_trace_event_call(trace_probe_group_name(tp),
+				  trace_probe_name(tp)))
+		return -EEXIST;
+
 	ret = register_trace_event(&call->event);
 	if (!ret)
 		return -ENODEV;
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 8adf5f3542a6..66701a92d186 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -404,6 +404,7 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
 	C(NO_EVENT_NAME,	"Event name is not specified"),		\
 	C(EVENT_TOO_LONG,	"Event name is too long"),		\
 	C(BAD_EVENT_NAME,	"Event name must follow the same rules as C identifiers"), \
+	C(EVENT_EXIST,		"Given group/event name is already used by another event"), \
 	C(RETVAL_ON_PROBE,	"$retval is not available on probe"),	\
 	C(BAD_STACK_NUM,	"Invalid stack number"),		\
 	C(BAD_ARG_NUM,		"Invalid argument number"),		\
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index d219ba50efbd..225ce569bf8f 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -515,7 +515,11 @@ static int register_trace_uprobe(struct trace_uprobe *tu)
 
 	ret = register_uprobe_event(tu);
 	if (ret) {
-		pr_warn("Failed to register probe event(%d)\n", ret);
+		if (ret == -EEXIST) {
+			trace_probe_log_set_index(0);
+			trace_probe_log_err(0, EVENT_EXIST);
+		} else
+			pr_warn("Failed to register probe event(%d)\n", ret);
 		goto end;
 	}
 
-- 
2.30.2