Merge tag 'trace-v4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "This is mostly clean ups and small fixes.  Some of the more visible
  changes are:

   - The function pid code uses the event pid filtering logic
   - [ku]probe events have access to current->comm
   - trace_printk now has sample code
   - PCI devices now trace physical addresses
   - stack tracing has less unnessary functions traced"

* tag 'trace-v4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
  printk, tracing: Avoiding unneeded blank lines
  tracing: Use __get_str() when manipulating strings
  tracing, RAS: Cleanup on __get_str() usage
  tracing: Use outer () on __get_str() definition
  ftrace: Reduce size of function graph entries
  tracing: Have HIST_TRIGGERS select TRACING
  tracing: Using for_each_set_bit() to simplify trace_pid_write()
  ftrace: Move toplevel init out of ftrace_init_tracefs()
  tracing/function_graph: Fix filters for function_graph threshold
  tracing: Skip more functions when doing stack tracing of events
  tracing: Expose CPU physical addresses (resource values) for PCI devices
  tracing: Show the preempt count of when the event was called
  tracing: Add trace_printk sample code
  tracing: Choose static tp_printk buffer by explicit nesting count
  tracing: expose current->comm to [ku]probe events
  ftrace: Have set_ftrace_pid use the bitmap like events do
  tracing: Move pid_list write processing into its own function
  tracing: Move the pid_list seq_file functions to be global
  tracing: Move filtered_pid helper functions into trace.c
  tracing: Make the pid filtering helper functions global

Documentation/trace/kprobetrace.txt

@@ -40,6 +40,7 @@ Synopsis of kprobe_events
   $stackN	: Fetch Nth entry of stack (N >= 0)
   $stack	: Fetch stack address.
   $retval	: Fetch return value.(*)
+  $comm		: Fetch current task comm.
   +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**)
   NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
   FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
@@ -62,6 +63,8 @@ offset, and container-size (usually 32). The syntax is;
 
  b<bit-width>@<bit-offset>/<container-size>
 
+For $comm, the default type is "string"; any other type is invalid.
+
 
 Per-Probe Event Filtering
 -------------------------

Documentation/trace/uprobetracer.txt

@@ -36,6 +36,7 @@ Synopsis of uprobe_tracer
    $stackN	: Fetch Nth entry of stack (N >= 0)
    $stack	: Fetch stack address.
    $retval	: Fetch return value.(*)
+   $comm	: Fetch current task comm.
    +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**)
    NAME=FETCHARG     : Set NAME as the argument name of FETCHARG.
    FETCHARG:TYPE     : Set TYPE as the type of FETCHARG. Currently, basic types
@@ -57,6 +58,8 @@ offset, and container-size (usually 32). The syntax is;
 
  b<bit-width>@<bit-offset>/<container-size>
 
+For $comm, the default type is "string"; any other type is invalid.
+
 
 Event Profiling
 ---------------

fs/nfs/nfs4trace.h

@@ -1235,8 +1235,8 @@ DECLARE_EVENT_CLASS(nfs4_idmap_event,
 				len = 0;
 			__entry->error = error < 0 ? error : 0;
 			__entry->id = id;
-			memcpy(__get_dynamic_array(name), name, len);
-			((char *)__get_dynamic_array(name))[len] = 0;
+			memcpy(__get_str(name), name, len);
+			__get_str(name)[len] = 0;
 		),
 
 		TP_printk(

fs/nfs/nfstrace.h

@@ -707,9 +707,9 @@ TRACE_EVENT(nfs_sillyrename_unlink,
 			__entry->dev = dir->i_sb->s_dev;
 			__entry->dir = NFS_FILEID(dir);
 			__entry->error = error;
-			memcpy(__get_dynamic_array(name),
+			memcpy(__get_str(name),
 				data->args.name.name, len);
-			((char *)__get_dynamic_array(name))[len] = 0;
+			__get_str(name)[len] = 0;
 		),
 
 		TP_printk(

include/linux/ftrace.h

@@ -754,23 +754,27 @@ static inline void ftrace_init(void) { }
 
 /*
  * Structure that defines an entry function trace.
+ * It's already packed but the attribute "packed" is needed
+ * to remove extra padding at the end.
  */
 struct ftrace_graph_ent {
 	unsigned long func; /* Current function */
 	int depth;
-};
+} __packed;
 
 /*
  * Structure that defines a return function trace.
+ * It's already packed but the attribute "packed" is needed
+ * to remove extra padding at the end.
  */
 struct ftrace_graph_ret {
 	unsigned long func; /* Current function */
-	unsigned long long calltime;
-	unsigned long long rettime;
 	/* Number of functions that overran the depth limit for current task */
 	unsigned long overrun;
+	unsigned long long calltime;
+	unsigned long long rettime;
 	int depth;
-};
+} __packed;
 
 /* Type of the callback handlers for tracing function graph*/
 typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *); /* return */

include/ras/ras_event.h

@@ -147,7 +147,7 @@ TRACE_EVENT(mc_event,
 		  __entry->error_count,
 		  mc_event_error_type(__entry->error_type),
 		  __entry->error_count > 1 ? "s" : "",
-		  ((char *)__get_str(msg))[0] ? " " : "",
+		  __get_str(msg)[0] ? " " : "",
 		  __get_str(msg),
 		  __get_str(label),
 		  __entry->mc_index,
@@ -157,7 +157,7 @@ TRACE_EVENT(mc_event,
 		  __entry->address,
 		  1 << __entry->grain_bits,
 		  __entry->syndrome,
-		  ((char *)__get_str(driver_detail))[0] ? " " : "",
+		  __get_str(driver_detail)[0] ? " " : "",
 		  __get_str(driver_detail))
 );
 

include/trace/events/printk.h

@@ -16,8 +16,16 @@ TRACE_EVENT(console,
 	),
 
 	TP_fast_assign(
-		memcpy(__get_dynamic_array(msg), text, len);
-		((char *)__get_dynamic_array(msg))[len] = 0;
+		/*
+		 * Each trace entry is printed in a new line.
+		 * If the msg finishes with '\n', cut it off
+		 * to avoid blank lines in the trace.
+		 */
+		if ((len > 0) && (text[len-1] == '\n'))
+			len -= 1;
+
+		memcpy(__get_str(msg), text, len);
+		__get_str(msg)[len] = 0;
 	),
 
 	TP_printk("%s", __get_str(msg))

include/trace/perf.h

@@ -15,7 +15,7 @@
 		((__entry->__data_loc_##field >> 16) & 0xffff)
 
 #undef __get_str
-#define __get_str(field) (char *)__get_dynamic_array(field)
+#define __get_str(field) ((char *)__get_dynamic_array(field))
 
 #undef __get_bitmask
 #define __get_bitmask(field) (char *)__get_dynamic_array(field)

include/trace/trace_events.h

@@ -256,7 +256,7 @@ TRACE_MAKE_SYSTEM_STR();
 		((__entry->__data_loc_##field >> 16) & 0xffff)
 
 #undef __get_str
-#define __get_str(field) (char *)__get_dynamic_array(field)
+#define __get_str(field) ((char *)__get_dynamic_array(field))
 
 #undef __get_bitmask
 #define __get_bitmask(field)						\

kernel/trace/Kconfig

@@ -542,6 +542,7 @@ config HIST_TRIGGERS
 	bool "Histogram triggers"
 	depends on ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select TRACING_MAP
+	select TRACING
 	default n
 	help
 	  Hist triggers allow one or more arbitrary trace event fields

kernel/trace/ftrace.c

@@ -89,16 +89,16 @@ struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end;
 /* What to set function_trace_op to */
 static struct ftrace_ops *set_function_trace_op;
 
-/* List for set_ftrace_pid's pids. */
-LIST_HEAD(ftrace_pids);
-struct ftrace_pid {
-	struct list_head list;
-	struct pid *pid;
-};
-
-static bool ftrace_pids_enabled(void)
+static bool ftrace_pids_enabled(struct ftrace_ops *ops)
 {
-	return !list_empty(&ftrace_pids);
+	struct trace_array *tr;
+
+	if (!(ops->flags & FTRACE_OPS_FL_PID) || !ops->private)
+		return false;
+
+	tr = ops->private;
+
+	return tr->function_pids != NULL;
 }
 
 static void ftrace_update_trampoline(struct ftrace_ops *ops);
@@ -179,7 +179,9 @@ int ftrace_nr_registered_ops(void)
 static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
 			    struct ftrace_ops *op, struct pt_regs *regs)
 {
-	if (!test_tsk_trace_trace(current))
+	struct trace_array *tr = op->private;
+
+	if (tr && this_cpu_read(tr->trace_buffer.data->ftrace_ignore_pid))
 		return;
 
 	op->saved_func(ip, parent_ip, op, regs);
@@ -417,7 +419,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
 	/* Always save the function, and reset at unregistering */
 	ops->saved_func = ops->func;
 
-	if (ops->flags & FTRACE_OPS_FL_PID && ftrace_pids_enabled())
+	if (ftrace_pids_enabled(ops))
 		ops->func = ftrace_pid_func;
 
 	ftrace_update_trampoline(ops);
@@ -450,7 +452,6 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 
 static void ftrace_update_pid_func(void)
 {
-	bool enabled = ftrace_pids_enabled();
 	struct ftrace_ops *op;
 
 	/* Only do something if we are tracing something */
@@ -459,8 +460,8 @@ static void ftrace_update_pid_func(void)
 
 	do_for_each_ftrace_op(op, ftrace_ops_list) {
 		if (op->flags & FTRACE_OPS_FL_PID) {
-			op->func = enabled ? ftrace_pid_func :
-				op->saved_func;
+			op->func = ftrace_pids_enabled(op) ?
+				ftrace_pid_func : op->saved_func;
 			ftrace_update_trampoline(op);
 		}
 	} while_for_each_ftrace_op(op);
@@ -5324,179 +5325,99 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops)
 	return ops->func;
 }
 
-static void clear_ftrace_swapper(void)
+static void
+ftrace_filter_pid_sched_switch_probe(void *data, bool preempt,
+		    struct task_struct *prev, struct task_struct *next)
 {
-	struct task_struct *p;
-	int cpu;
+	struct trace_array *tr = data;
+	struct trace_pid_list *pid_list;
 
-	get_online_cpus();
-	for_each_online_cpu(cpu) {
-		p = idle_task(cpu);
-		clear_tsk_trace_trace(p);
-	}
-	put_online_cpus();
-}
-
-static void set_ftrace_swapper(void)
-{
-	struct task_struct *p;
-	int cpu;
+	pid_list = rcu_dereference_sched(tr->function_pids);
 
-	get_online_cpus();
-	for_each_online_cpu(cpu) {
-		p = idle_task(cpu);
-		set_tsk_trace_trace(p);
-	}
-	put_online_cpus();
+	this_cpu_write(tr->trace_buffer.data->ftrace_ignore_pid,
+		       trace_ignore_this_task(pid_list, next));
 }
 
-static void clear_ftrace_pid(struct pid *pid)
+static void clear_ftrace_pids(struct trace_array *tr)
 {
-	struct task_struct *p;
+	struct trace_pid_list *pid_list;
+	int cpu;
 
-	rcu_read_lock();
-	do_each_pid_task(pid, PIDTYPE_PID, p) {
-		clear_tsk_trace_trace(p);
-	} while_each_pid_task(pid, PIDTYPE_PID, p);
-	rcu_read_unlock();
+	pid_list = rcu_dereference_protected(tr->function_pids,
+					     lockdep_is_held(&ftrace_lock));
+	if (!pid_list)
+		return;
 
-	put_pid(pid);
-}
+	unregister_trace_sched_switch(ftrace_filter_pid_sched_switch_probe, tr);
 
-static void set_ftrace_pid(struct pid *pid)
-{
-	struct task_struct *p;
+	for_each_possible_cpu(cpu)
+		per_cpu_ptr(tr->trace_buffer.data, cpu)->ftrace_ignore_pid = false;
 
-	rcu_read_lock();
-	do_each_pid_task(pid, PIDTYPE_PID, p) {
-		set_tsk_trace_trace(p);
-	} while_each_pid_task(pid, PIDTYPE_PID, p);
-	rcu_read_unlock();
-}
+	rcu_assign_pointer(tr->function_pids, NULL);
 
-static void clear_ftrace_pid_task(struct pid *pid)
-{
-	if (pid == ftrace_swapper_pid)
-		clear_ftrace_swapper();
-	else
-		clear_ftrace_pid(pid);
-}
+	/* Wait till all users are no longer using pid filtering */
+	synchronize_sched();
 
-static void set_ftrace_pid_task(struct pid *pid)
-{
-	if (pid == ftrace_swapper_pid)
-		set_ftrace_swapper();
-	else
-		set_ftrace_pid(pid);
+	trace_free_pid_list(pid_list);
 }
 
-static int ftrace_pid_add(int p)
+static void ftrace_pid_reset(struct trace_array *tr)
 {
-	struct pid *pid;
-	struct ftrace_pid *fpid;
-	int ret = -EINVAL;
-
 	mutex_lock(&ftrace_lock);
-
-	if (!p)
-		pid = ftrace_swapper_pid;
-	else
-		pid = find_get_pid(p);
-
-	if (!pid)
-		goto out;
-
-	ret = 0;
-
-	list_for_each_entry(fpid, &ftrace_pids, list)
-		if (fpid->pid == pid)
-			goto out_put;
-
-	ret = -ENOMEM;
-
-	fpid = kmalloc(sizeof(*fpid), GFP_KERNEL);
-	if (!fpid)
-		goto out_put;
-
-	list_add(&fpid->list, &ftrace_pids);
-	fpid->pid = pid;
-
-	set_ftrace_pid_task(pid);
+	clear_ftrace_pids(tr);
 
 	ftrace_update_pid_func();
-
 	ftrace_startup_all(0);
 
 	mutex_unlock(&ftrace_lock);
-	return 0;
-
-out_put:
-	if (pid != ftrace_swapper_pid)
-		put_pid(pid);
-
-out:
-	mutex_unlock(&ftrace_lock);
-	return ret;
 }
 
-static void ftrace_pid_reset(void)
-{
-	struct ftrace_pid *fpid, *safe;
-
-	mutex_lock(&ftrace_lock);
-	list_for_each_entry_safe(fpid, safe, &ftrace_pids, list) {
-		struct pid *pid = fpid->pid;
-
-		clear_ftrace_pid_task(pid);
-
-		list_del(&fpid->list);
-		kfree(fpid);
-	}
-
-	ftrace_update_pid_func();
-	ftrace_startup_all(0);
-
-	mutex_unlock(&ftrace_lock);
-}
+/* Greater than any max PID */
+#define FTRACE_NO_PIDS		(void *)(PID_MAX_LIMIT + 1)
 
 static void *fpid_start(struct seq_file *m, loff_t *pos)
+	__acquires(RCU)
 {
+	struct trace_pid_list *pid_list;
+	struct trace_array *tr = m->private;
+
 	mutex_lock(&ftrace_lock);
+	rcu_read_lock_sched();
 
-	if (!ftrace_pids_enabled() && (!*pos))
-		return (void *) 1;
+	pid_list = rcu_dereference_sched(tr->function_pids);
 
-	return seq_list_start(&ftrace_pids, *pos);
+	if (!pid_list)
+		return !(*pos) ? FTRACE_NO_PIDS : NULL;
+
+	return trace_pid_start(pid_list, pos);
 }
 
 static void *fpid_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	if (v == (void *)1)
+	struct trace_array *tr = m->private;
+	struct trace_pid_list *pid_list = rcu_dereference_sched(tr->function_pids);
+
+	if (v == FTRACE_NO_PIDS)
 		return NULL;
 
-	return seq_list_next(v, &ftrace_pids, pos);
+	return trace_pid_next(pid_list, v, pos);
 }
 
 static void fpid_stop(struct seq_file *m, void *p)
+	__releases(RCU)
 {
+	rcu_read_unlock_sched();
 	mutex_unlock(&ftrace_lock);
 }
 
 static int fpid_show(struct seq_file *m, void *v)
 {
-	const struct ftrace_pid *fpid = list_entry(v, struct ftrace_pid, list);
-
-	if (v == (void *)1) {
+	if (v == FTRACE_NO_PIDS) {
 		seq_puts(m, "no pid\n");
 		return 0;
 	}
 
-	if (fpid->pid == ftrace_swapper_pid)
-		seq_puts(m, "swapper tasks\n");
-	else
-		seq_printf(m, "%u\n", pid_vnr(fpid->pid));
-
-	return 0;
+	return trace_pid_show(m, v);
 }
 
 static const struct seq_operations ftrace_pid_sops = {
@@ -5509,58 +5430,103 @@ static const struct seq_operations ftrace_pid_sops = {
 static int
 ftrace_pid_open(struct inode *inode, struct file *file)
 {
+	struct trace_array *tr = inode->i_private;
+	struct seq_file *m;
 	int ret = 0;
 
+	if (trace_array_get(tr) < 0)
+		return -ENODEV;
+
 	if ((file->f_mode & FMODE_WRITE) &&
 	    (file->f_flags & O_TRUNC))
-		ftrace_pid_reset();
+		ftrace_pid_reset(tr);
 
-	if (file->f_mode & FMODE_READ)
-		ret = seq_open(file, &ftrace_pid_sops);
+	ret = seq_open(file, &ftrace_pid_sops);
+	if (ret < 0) {
+		trace_array_put(tr);
+	} else {
+		m = file->private_data;
+		/* copy tr over to seq ops */
+		m->private = tr;
+	}
 
 	return ret;
 }
 
+static void ignore_task_cpu(void *data)
+{
+	struct trace_array *tr = data;
+	struct trace_pid_list *pid_list;
+
+	/*
+	 * This function is called by on_each_cpu() while the
+	 * event_mutex is held.
+	 */
+	pid_list = rcu_dereference_protected(tr->function_pids,
+					     mutex_is_locked(&ftrace_lock));
+
+	this_cpu_write(tr->trace_buffer.data->ftrace_ignore_pid,
+		       trace_ignore_this_task(pid_list, current));
+}
+
 static ssize_t
 ftrace_pid_write(struct file *filp, const char __user *ubuf,
 		   size_t cnt, loff_t *ppos)
 {
-	char buf[64], *tmp;
-	long val;
-	int ret;
+	struct seq_file *m = filp->private_data;
+	struct trace_array *tr = m->private;
+	struct trace_pid_list *filtered_pids = NULL;
+	struct trace_pid_list *pid_list;
+	ssize_t ret;
 
-	if (cnt >= sizeof(buf))
-		return -EINVAL;
+	if (!cnt)
+		return 0;
+
+	mutex_lock(&ftrace_lock);
+
+	filtered_pids = rcu_dereference_protected(tr->function_pids,
+					     lockdep_is_held(&ftrace_lock));
+
+	ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt);
+	if (ret < 0)
+		goto out;
 
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
+	rcu_assign_pointer(tr->function_pids, pid_list);
 
-	buf[cnt] = 0;
+	if (filtered_pids) {
+		synchronize_sched();
+		trace_free_pid_list(filtered_pids);
+	} else if (pid_list) {
+		/* Register a probe to set whether to ignore the tracing of a task */
+		register_trace_sched_switch(ftrace_filter_pid_sched_switch_probe, tr);
+	}
 
 	/*
-	 * Allow "echo > set_ftrace_pid" or "echo -n '' > set_ftrace_pid"
-	 * to clean the filter quietly.
+	 * Ignoring of pids is done at task switch. But we have to
+	 * check for those tasks that are currently running.
+	 * Always do this in case a pid was appended or removed.
 	 */
-	tmp = strstrip(buf);
-	if (strlen(tmp) == 0)
-		return 1;
+	on_each_cpu(ignore_task_cpu, tr, 1);
 
-	ret = kstrtol(tmp, 10, &val);
-	if (ret < 0)
-		return ret;
+	ftrace_update_pid_func();
+	ftrace_startup_all(0);
+ out:
+	mutex_unlock(&ftrace_lock);
 
-	ret = ftrace_pid_add(val);
+	if (ret > 0)
+		*ppos += ret;
 
-	return ret ? ret : cnt;
+	return ret;
 }
 
 static int
 ftrace_pid_release(struct inode *inode, struct file *file)
 {
-	if (file->f_mode & FMODE_READ)
-		seq_release(inode, file);
+	struct trace_array *tr = inode->i_private;
 
-	return 0;
+	trace_array_put(tr);
+
+	return seq_release(inode, file);
 }
 
 static const struct file_operations ftrace_pid_fops = {
@@ -5571,24 +5537,21 @@ static const struct file_operations ftrace_pid_fops = {
 	.release	= ftrace_pid_release,
 };
 
-static __init int ftrace_init_tracefs(void)
+void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 {
-	struct dentry *d_tracer;
+	trace_create_file("set_ftrace_pid", 0644, d_tracer,
+			    tr, &ftrace_pid_fops);
+}
 
-	d_tracer = tracing_init_dentry();
-	if (IS_ERR(d_tracer))
-		return 0;
+void __init ftrace_init_tracefs_toplevel(struct trace_array *tr,
+					 struct dentry *d_tracer)
+{
+	/* Only the top level directory has the dyn_tracefs and profile */
+	WARN_ON(!(tr->flags & TRACE_ARRAY_FL_GLOBAL));
 
 	ftrace_init_dyn_tracefs(d_tracer);
-
-	trace_create_file("set_ftrace_pid", 0644, d_tracer,
-			    NULL, &ftrace_pid_fops);
-
 	ftrace_profile_tracefs(d_tracer);
-
-	return 0;
 }
-fs_initcall(ftrace_init_tracefs);
 
 /**
  * ftrace_kill - kill ftrace

kernel/trace/trace.c

@@ -25,7 +25,7 @@
 #include <linux/hardirq.h>
 #include <linux/linkage.h>
 #include <linux/uaccess.h>
-#include <linux/kprobes.h>
+#include <linux/vmalloc.h>
 #include <linux/ftrace.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
@@ -319,6 +319,258 @@ int call_filter_check_discard(struct trace_event_call *call, void *rec,
 	return 0;
 }
 
+void trace_free_pid_list(struct trace_pid_list *pid_list)
+{
+	vfree(pid_list->pids);
+	kfree(pid_list);
+}
+
+/**
+ * trace_find_filtered_pid - check if a pid exists in a filtered_pid list
+ * @filtered_pids: The list of pids to check
+ * @search_pid: The PID to find in @filtered_pids
+ *
+ * Returns true if @search_pid is fonud in @filtered_pids, and false otherwis.
+ */
+bool
+trace_find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid)
+{
+	/*
+	 * If pid_max changed after filtered_pids was created, we
+	 * by default ignore all pids greater than the previous pid_max.
+	 */
+	if (search_pid >= filtered_pids->pid_max)
+		return false;
+
+	return test_bit(search_pid, filtered_pids->pids);
+}
+
+/**
+ * trace_ignore_this_task - should a task be ignored for tracing
+ * @filtered_pids: The list of pids to check
+ * @task: The task that should be ignored if not filtered
+ *
+ * Checks if @task should be traced or not from @filtered_pids.
+ * Returns true if @task should *NOT* be traced.
+ * Returns false if @task should be traced.
+ */
+bool
+trace_ignore_this_task(struct trace_pid_list *filtered_pids, struct task_struct *task)
+{
+	/*
+	 * Return false, because if filtered_pids does not exist,
+	 * all pids are good to trace.
+	 */
+	if (!filtered_pids)
+		return false;
+
+	return !trace_find_filtered_pid(filtered_pids, task->pid);
+}
+
+/**
+ * trace_pid_filter_add_remove - Add or remove a task from a pid_list
+ * @pid_list: The list to modify
+ * @self: The current task for fork or NULL for exit
+ * @task: The task to add or remove
+ *
+ * If adding a task, if @self is defined, the task is only added if @self
+ * is also included in @pid_list. This happens on fork and tasks should
+ * only be added when the parent is listed. If @self is NULL, then the
+ * @task pid will be removed from the list, which would happen on exit
+ * of a task.
+ */
+void trace_filter_add_remove_task(struct trace_pid_list *pid_list,
+				  struct task_struct *self,
+				  struct task_struct *task)
+{
+	if (!pid_list)
+		return;
+
+	/* For forks, we only add if the forking task is listed */
+	if (self) {
+		if (!trace_find_filtered_pid(pid_list, self->pid))
+			return;
+	}
+
+	/* Sorry, but we don't support pid_max changing after setting */
+	if (task->pid >= pid_list->pid_max)
+		return;
+
+	/* "self" is set for forks, and NULL for exits */
+	if (self)
+		set_bit(task->pid, pid_list->pids);
+	else
+		clear_bit(task->pid, pid_list->pids);
+}
+
+/**
+ * trace_pid_next - Used for seq_file to get to the next pid of a pid_list
+ * @pid_list: The pid list to show
+ * @v: The last pid that was shown (+1 the actual pid to let zero be displayed)
+ * @pos: The position of the file
+ *
+ * This is used by the seq_file "next" operation to iterate the pids
+ * listed in a trace_pid_list structure.
+ *
+ * Returns the pid+1 as we want to display pid of zero, but NULL would
+ * stop the iteration.
+ */
+void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos)
+{
+	unsigned long pid = (unsigned long)v;
+
+	(*pos)++;
+
+	/* pid already is +1 of the actual prevous bit */
+	pid = find_next_bit(pid_list->pids, pid_list->pid_max, pid);
+
+	/* Return pid + 1 to allow zero to be represented */
+	if (pid < pid_list->pid_max)
+		return (void *)(pid + 1);
+
+	return NULL;
+}
+
+/**
+ * trace_pid_start - Used for seq_file to start reading pid lists
+ * @pid_list: The pid list to show
+ * @pos: The position of the file
+ *
+ * This is used by seq_file "start" operation to start the iteration
+ * of listing pids.
+ *
+ * Returns the pid+1 as we want to display pid of zero, but NULL would
+ * stop the iteration.
+ */
+void *trace_pid_start(struct trace_pid_list *pid_list, loff_t *pos)
+{
+	unsigned long pid;
+	loff_t l = 0;
+
+	pid = find_first_bit(pid_list->pids, pid_list->pid_max);
+	if (pid >= pid_list->pid_max)
+		return NULL;
+
+	/* Return pid + 1 so that zero can be the exit value */
+	for (pid++; pid && l < *pos;
+	     pid = (unsigned long)trace_pid_next(pid_list, (void *)pid, &l))
+		;
+	return (void *)pid;
+}
+
+/**
+ * trace_pid_show - show the current pid in seq_file processing
+ * @m: The seq_file structure to write into
+ * @v: A void pointer of the pid (+1) value to display
+ *
+ * Can be directly used by seq_file operations to display the current
+ * pid value.
+ */
+int trace_pid_show(struct seq_file *m, void *v)
+{
+	unsigned long pid = (unsigned long)v - 1;
+
+	seq_printf(m, "%lu\n", pid);
+	return 0;
+}
+
+/* 128 should be much more than enough */
+#define PID_BUF_SIZE		127
+
+int trace_pid_write(struct trace_pid_list *filtered_pids,
+		    struct trace_pid_list **new_pid_list,
+		    const char __user *ubuf, size_t cnt)
+{
+	struct trace_pid_list *pid_list;
+	struct trace_parser parser;
+	unsigned long val;
+	int nr_pids = 0;
+	ssize_t read = 0;
+	ssize_t ret = 0;
+	loff_t pos;
+	pid_t pid;
+
+	if (trace_parser_get_init(&parser, PID_BUF_SIZE + 1))
+		return -ENOMEM;
+
+	/*
+	 * Always recreate a new array. The write is an all or nothing
+	 * operation. Always create a new array when adding new pids by
+	 * the user. If the operation fails, then the current list is
+	 * not modified.
+	 */
+	pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL);
+	if (!pid_list)
+		return -ENOMEM;
+
+	pid_list->pid_max = READ_ONCE(pid_max);
+
+	/* Only truncating will shrink pid_max */
+	if (filtered_pids && filtered_pids->pid_max > pid_list->pid_max)
+		pid_list->pid_max = filtered_pids->pid_max;
+
+	pid_list->pids = vzalloc((pid_list->pid_max + 7) >> 3);
+	if (!pid_list->pids) {
+		kfree(pid_list);
+		return -ENOMEM;
+	}
+
+	if (filtered_pids) {
+		/* copy the current bits to the new max */
+		for_each_set_bit(pid, filtered_pids->pids,
+				 filtered_pids->pid_max) {
+			set_bit(pid, pid_list->pids);
+			nr_pids++;
+		}
+	}
+
+	while (cnt > 0) {
+
+		pos = 0;
+
+		ret = trace_get_user(&parser, ubuf, cnt, &pos);
+		if (ret < 0 || !trace_parser_loaded(&parser))
+			break;
+
+		read += ret;
+		ubuf += ret;
+		cnt -= ret;
+
+		parser.buffer[parser.idx] = 0;
+
+		ret = -EINVAL;
+		if (kstrtoul(parser.buffer, 0, &val))
+			break;
+		if (val >= pid_list->pid_max)
+			break;
+
+		pid = (pid_t)val;
+
+		set_bit(pid, pid_list->pids);
+		nr_pids++;
+
+		trace_parser_clear(&parser);
+		ret = 0;
+	}
+	trace_parser_put(&parser);
+
+	if (ret < 0) {
+		trace_free_pid_list(pid_list);
+		return ret;
+	}
+
+	if (!nr_pids) {
+		/* Cleared the list of pids */
+		trace_free_pid_list(pid_list);
+		read = ret;
+		pid_list = NULL;
+	}
+
+	*new_pid_list = pid_list;
+
+	return read;
+}
+
 static cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu)
 {
 	u64 ts;
@@ -1862,7 +2114,17 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr,
 {
 	__buffer_unlock_commit(buffer, event);
 
-	ftrace_trace_stack(tr, buffer, flags, 0, pc, regs);
+	/*
+	 * If regs is not set, then skip the following callers:
+	 *   trace_buffer_unlock_commit_regs
+	 *   event_trigger_unlock_commit
+	 *   trace_event_buffer_commit
+	 *   trace_event_raw_event_sched_switch
+	 * Note, we can still get here via blktrace, wakeup tracer
+	 * and mmiotrace, but that's ok if they lose a function or
+	 * two. They are that meaningful.
+	 */
+	ftrace_trace_stack(tr, buffer, flags, regs ? 0 : 4, pc, regs);
 	ftrace_trace_userstack(buffer, flags, pc);
 }
 
@@ -1912,6 +2174,13 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
 	trace.nr_entries	= 0;
 	trace.skip		= skip;
 
+	/*
+	 * Add two, for this function and the call to save_stack_trace()
+	 * If regs is set, then these functions will not be in the way.
+	 */
+	if (!regs)
+		trace.skip += 2;
+
 	/*
 	 * Since events can happen in NMIs there's no safe way to
 	 * use the per cpu ftrace_stacks. We reserve it and if an interrupt
@@ -2083,83 +2352,41 @@ static void __trace_userstack(struct trace_array *tr, unsigned long flags)
 
 /* created for use with alloc_percpu */
 struct trace_buffer_struct {
-	char buffer[TRACE_BUF_SIZE];
+	int nesting;
+	char buffer[4][TRACE_BUF_SIZE];
 };
 
 static struct trace_buffer_struct *trace_percpu_buffer;
-static struct trace_buffer_struct *trace_percpu_sirq_buffer;
-static struct trace_buffer_struct *trace_percpu_irq_buffer;
-static struct trace_buffer_struct *trace_percpu_nmi_buffer;
 
 /*
- * The buffer used is dependent on the context. There is a per cpu
- * buffer for normal context, softirq contex, hard irq context and
- * for NMI context. Thise allows for lockless recording.
- *
- * Note, if the buffers failed to be allocated, then this returns NULL
+ * Thise allows for lockless recording.  If we're nested too deeply, then
+ * this returns NULL.
  */
 static char *get_trace_buf(void)
 {
-	struct trace_buffer_struct *percpu_buffer;
-
-	/*
-	 * If we have allocated per cpu buffers, then we do not
-	 * need to do any locking.
-	 */
-	if (in_nmi())
-		percpu_buffer = trace_percpu_nmi_buffer;
-	else if (in_irq())
-		percpu_buffer = trace_percpu_irq_buffer;
-	else if (in_softirq())
-		percpu_buffer = trace_percpu_sirq_buffer;
-	else
-		percpu_buffer = trace_percpu_buffer;
+	struct trace_buffer_struct *buffer = this_cpu_ptr(trace_percpu_buffer);
 
-	if (!percpu_buffer)
+	if (!buffer || buffer->nesting >= 4)
 		return NULL;
 
-	return this_cpu_ptr(&percpu_buffer->buffer[0]);
+	return &buffer->buffer[buffer->nesting++][0];
+}
+
+static void put_trace_buf(void)
+{
+	this_cpu_dec(trace_percpu_buffer->nesting);
 }
 
 static int alloc_percpu_trace_buffer(void)
 {
 	struct trace_buffer_struct *buffers;
-	struct trace_buffer_struct *sirq_buffers;
-	struct trace_buffer_struct *irq_buffers;
-	struct trace_buffer_struct *nmi_buffers;
 
 	buffers = alloc_percpu(struct trace_buffer_struct);
-	if (!buffers)
-		goto err_warn;
-
-	sirq_buffers = alloc_percpu(struct trace_buffer_struct);
-	if (!sirq_buffers)
-		goto err_sirq;
-
-	irq_buffers = alloc_percpu(struct trace_buffer_struct);
-	if (!irq_buffers)
-		goto err_irq;
-
-	nmi_buffers = alloc_percpu(struct trace_buffer_struct);
-	if (!nmi_buffers)
-		goto err_nmi;
+	if (WARN(!buffers, "Could not allocate percpu trace_printk buffer"))
+		return -ENOMEM;
 
 	trace_percpu_buffer = buffers;
-	trace_percpu_sirq_buffer = sirq_buffers;
-	trace_percpu_irq_buffer = irq_buffers;
-	trace_percpu_nmi_buffer = nmi_buffers;
-
 	return 0;
-
- err_nmi:
-	free_percpu(irq_buffers);
- err_irq:
-	free_percpu(sirq_buffers);
- err_sirq:
-	free_percpu(buffers);
- err_warn:
-	WARN(1, "Could not allocate percpu trace_printk buffer");
-	return -ENOMEM;
 }
 
 static int buffers_allocated;
@@ -2250,7 +2477,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 	tbuffer = get_trace_buf();
 	if (!tbuffer) {
 		len = 0;
-		goto out;
+		goto out_nobuffer;
 	}
 
 	len = vbin_printf((u32 *)tbuffer, TRACE_BUF_SIZE/sizeof(int), fmt, args);
@@ -2276,6 +2503,9 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 	}
 
 out:
+	put_trace_buf();
+
+out_nobuffer:
 	preempt_enable_notrace();
 	unpause_graph_tracing();
 
@@ -2307,7 +2537,7 @@ __trace_array_vprintk(struct ring_buffer *buffer,
 	tbuffer = get_trace_buf();
 	if (!tbuffer) {
 		len = 0;
-		goto out;
+		goto out_nobuffer;
 	}
 
 	len = vscnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args);
@@ -2326,7 +2556,11 @@ __trace_array_vprintk(struct ring_buffer *buffer,
 		__buffer_unlock_commit(buffer, event);
 		ftrace_trace_stack(&global_trace, buffer, flags, 6, pc, NULL);
 	}
- out:
+
+out:
+	put_trace_buf();
+
+out_nobuffer:
 	preempt_enable_notrace();
 	unpause_graph_tracing();
 
@@ -6977,6 +7211,7 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 	for_each_tracing_cpu(cpu)
 		tracing_init_tracefs_percpu(tr, cpu);
 
+	ftrace_init_tracefs(tr, d_tracer);
 }
 
 static struct vfsmount *trace_automount(void *ingore)
@@ -7130,6 +7365,7 @@ static __init int tracer_init_tracefs(void)
 		return 0;
 
 	init_tracer_tracefs(&global_trace, d_tracer);
+	ftrace_init_tracefs_toplevel(&global_trace, d_tracer);
 
 	trace_create_file("tracing_thresh", 0644, d_tracer,
 			&global_trace, &tracing_thresh_fops);

kernel/trace/trace.h

@@ -80,6 +80,12 @@ enum trace_type {
 	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
 		     filter)
 
+#undef FTRACE_ENTRY_PACKED
+#define FTRACE_ENTRY_PACKED(name, struct_name, id, tstruct, print,	\
+			    filter)					\
+	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
+		     filter) __packed
+
 #include "trace_entries.h"
 
 /*
@@ -156,6 +162,9 @@ struct trace_array_cpu {
 	char			comm[TASK_COMM_LEN];
 
 	bool			ignore_pid;
+#ifdef CONFIG_FUNCTION_TRACER
+	bool			ftrace_ignore_pid;
+#endif
 };
 
 struct tracer;
@@ -247,6 +256,7 @@ struct trace_array {
 	int			ref;
 #ifdef CONFIG_FUNCTION_TRACER
 	struct ftrace_ops	*ops;
+	struct trace_pid_list	__rcu *function_pids;
 	/* function tracing enabled */
 	int			function_enabled;
 #endif
@@ -628,6 +638,25 @@ extern unsigned long nsecs_to_usecs(unsigned long nsecs);
 
 extern unsigned long tracing_thresh;
 
+/* PID filtering */
+
+extern int pid_max;
+
+bool trace_find_filtered_pid(struct trace_pid_list *filtered_pids,
+			     pid_t search_pid);
+bool trace_ignore_this_task(struct trace_pid_list *filtered_pids,
+			    struct task_struct *task);
+void trace_filter_add_remove_task(struct trace_pid_list *pid_list,
+				  struct task_struct *self,
+				  struct task_struct *task);
+void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos);
+void *trace_pid_start(struct trace_pid_list *pid_list, loff_t *pos);
+int trace_pid_show(struct seq_file *m, void *v);
+void trace_free_pid_list(struct trace_pid_list *pid_list);
+int trace_pid_write(struct trace_pid_list *filtered_pids,
+		    struct trace_pid_list **new_pid_list,
+		    const char __user *ubuf, size_t cnt);
+
 #ifdef CONFIG_TRACER_MAX_TRACE
 void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu);
 void update_max_tr_single(struct trace_array *tr,
@@ -821,12 +850,9 @@ extern struct list_head ftrace_pids;
 
 #ifdef CONFIG_FUNCTION_TRACER
 extern bool ftrace_filter_param __initdata;
-static inline int ftrace_trace_task(struct task_struct *task)
+static inline int ftrace_trace_task(struct trace_array *tr)
 {
-	if (list_empty(&ftrace_pids))
-		return 1;
-
-	return test_tsk_trace_trace(task);
+	return !this_cpu_read(tr->trace_buffer.data->ftrace_ignore_pid);
 }
 extern int ftrace_is_dead(void);
 int ftrace_create_function_files(struct trace_array *tr,
@@ -836,8 +862,11 @@ void ftrace_init_global_array_ops(struct trace_array *tr);
 void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func);
 void ftrace_reset_array_ops(struct trace_array *tr);
 int using_ftrace_ops_list_func(void);
+void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer);
+void ftrace_init_tracefs_toplevel(struct trace_array *tr,
+				  struct dentry *d_tracer);
 #else
-static inline int ftrace_trace_task(struct task_struct *task)
+static inline int ftrace_trace_task(struct trace_array *tr)
 {
 	return 1;
 }
@@ -852,6 +881,8 @@ static inline void ftrace_destroy_function_files(struct trace_array *tr) { }
 static inline __init void
 ftrace_init_global_array_ops(struct trace_array *tr) { }
 static inline void ftrace_reset_array_ops(struct trace_array *tr) { }
+static inline void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d) { }
+static inline void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d) { }
 /* ftace_func_t type is not defined, use macro instead of static inline */
 #define ftrace_init_array_ops(tr, func) do { } while (0)
 #endif /* CONFIG_FUNCTION_TRACER */
@@ -1600,6 +1631,11 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled);
 #define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter)	\
 	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \
 		     filter)
+#undef FTRACE_ENTRY_PACKED
+#define FTRACE_ENTRY_PACKED(call, struct_name, id, tstruct, print, filter) \
+	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \
+		     filter)
+
 #include "trace_entries.h"
 
 #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_FUNCTION_TRACER)

kernel/trace/trace_entries.h

@@ -72,7 +72,7 @@ FTRACE_ENTRY_REG(function, ftrace_entry,
 );
 
 /* Function call entry */
-FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry,
+FTRACE_ENTRY_PACKED(funcgraph_entry, ftrace_graph_ent_entry,
 
 	TRACE_GRAPH_ENT,
 
@@ -88,7 +88,7 @@ FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry,
 );
 
 /* Function return entry */
-FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry,
+FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,
 
 	TRACE_GRAPH_RET,
 

kernel/trace/trace_events.c

@@ -15,7 +15,6 @@
 #include <linux/kthread.h>
 #include <linux/tracefs.h>
 #include <linux/uaccess.h>
-#include <linux/vmalloc.h>
 #include <linux/module.h>
 #include <linux/ctype.h>
 #include <linux/sort.h>
@@ -262,6 +261,14 @@ void *trace_event_buffer_reserve(struct trace_event_buffer *fbuffer,
 
 	local_save_flags(fbuffer->flags);
 	fbuffer->pc = preempt_count();
+	/*
+	 * If CONFIG_PREEMPT is enabled, then the tracepoint itself disables
+	 * preemption (adding one to the preempt_count). Since we are
+	 * interested in the preempt_count at the time the tracepoint was
+	 * hit, we need to subtract one to offset the increment.
+	 */
+	if (IS_ENABLED(CONFIG_PREEMPT))
+		fbuffer->pc--;
 	fbuffer->trace_file = trace_file;
 
 	fbuffer->event =
@@ -499,60 +506,6 @@ static void ftrace_clear_events(struct trace_array *tr)
 	mutex_unlock(&event_mutex);
 }
 
-/* Shouldn't this be in a header? */
-extern int pid_max;
-
-/* Returns true if found in filter */
-static bool
-find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid)
-{
-	/*
-	 * If pid_max changed after filtered_pids was created, we
-	 * by default ignore all pids greater than the previous pid_max.
-	 */
-	if (search_pid >= filtered_pids->pid_max)
-		return false;
-
-	return test_bit(search_pid, filtered_pids->pids);
-}
-
-static bool
-ignore_this_task(struct trace_pid_list *filtered_pids, struct task_struct *task)
-{
-	/*
-	 * Return false, because if filtered_pids does not exist,
-	 * all pids are good to trace.
-	 */
-	if (!filtered_pids)
-		return false;
-
-	return !find_filtered_pid(filtered_pids, task->pid);
-}
-
-static void filter_add_remove_task(struct trace_pid_list *pid_list,
-				   struct task_struct *self,
-				   struct task_struct *task)
-{
-	if (!pid_list)
-		return;
-
-	/* For forks, we only add if the forking task is listed */
-	if (self) {
-		if (!find_filtered_pid(pid_list, self->pid))
-			return;
-	}
-
-	/* Sorry, but we don't support pid_max changing after setting */
-	if (task->pid >= pid_list->pid_max)
-		return;
-
-	/* "self" is set for forks, and NULL for exits */
-	if (self)
-		set_bit(task->pid, pid_list->pids);
-	else
-		clear_bit(task->pid, pid_list->pids);
-}
-
 static void
 event_filter_pid_sched_process_exit(void *data, struct task_struct *task)
 {
@@ -560,7 +513,7 @@ event_filter_pid_sched_process_exit(void *data, struct task_struct *task)
 	struct trace_array *tr = data;
 
 	pid_list = rcu_dereference_sched(tr->filtered_pids);
-	filter_add_remove_task(pid_list, NULL, task);
+	trace_filter_add_remove_task(pid_list, NULL, task);
 }
 
 static void
@@ -572,7 +525,7 @@ event_filter_pid_sched_process_fork(void *data,
 	struct trace_array *tr = data;
 
 	pid_list = rcu_dereference_sched(tr->filtered_pids);
-	filter_add_remove_task(pid_list, self, task);
+	trace_filter_add_remove_task(pid_list, self, task);
 }
 
 void trace_event_follow_fork(struct trace_array *tr, bool enable)
@@ -600,8 +553,8 @@ event_filter_pid_sched_switch_probe_pre(void *data, bool preempt,
 	pid_list = rcu_dereference_sched(tr->filtered_pids);
 
 	this_cpu_write(tr->trace_buffer.data->ignore_pid,
-		       ignore_this_task(pid_list, prev) &&
-		       ignore_this_task(pid_list, next));
+		       trace_ignore_this_task(pid_list, prev) &&
+		       trace_ignore_this_task(pid_list, next));
 }
 
 static void
@@ -614,7 +567,7 @@ event_filter_pid_sched_switch_probe_post(void *data, bool preempt,
 	pid_list = rcu_dereference_sched(tr->filtered_pids);
 
 	this_cpu_write(tr->trace_buffer.data->ignore_pid,
-		       ignore_this_task(pid_list, next));
+		       trace_ignore_this_task(pid_list, next));
 }
 
 static void
@@ -630,7 +583,7 @@ event_filter_pid_sched_wakeup_probe_pre(void *data, struct task_struct *task)
 	pid_list = rcu_dereference_sched(tr->filtered_pids);
 
 	this_cpu_write(tr->trace_buffer.data->ignore_pid,
-		       ignore_this_task(pid_list, task));
+		       trace_ignore_this_task(pid_list, task));
 }
 
 static void
@@ -647,7 +600,7 @@ event_filter_pid_sched_wakeup_probe_post(void *data, struct task_struct *task)
 
 	/* Set tracing if current is enabled */
 	this_cpu_write(tr->trace_buffer.data->ignore_pid,
-		       ignore_this_task(pid_list, current));
+		       trace_ignore_this_task(pid_list, current));
 }
 
 static void __ftrace_clear_event_pids(struct trace_array *tr)
@@ -685,8 +638,7 @@ static void __ftrace_clear_event_pids(struct trace_array *tr)
 	/* Wait till all users are no longer using pid filtering */
 	synchronize_sched();
 
-	vfree(pid_list->pids);
-	kfree(pid_list);
+	trace_free_pid_list(pid_list);
 }
 
 static void ftrace_clear_event_pids(struct trace_array *tr)
@@ -1034,18 +986,8 @@ p_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct trace_array *tr = m->private;
 	struct trace_pid_list *pid_list = rcu_dereference_sched(tr->filtered_pids);
-	unsigned long pid = (unsigned long)v;
-
-	(*pos)++;
-
-	/* pid already is +1 of the actual prevous bit */
-	pid = find_next_bit(pid_list->pids, pid_list->pid_max, pid);
 
-	/* Return pid + 1 to allow zero to be represented */
-	if (pid < pid_list->pid_max)
-		return (void *)(pid + 1);
-
-	return NULL;
+	return trace_pid_next(pid_list, v, pos);
 }
 
 static void *p_start(struct seq_file *m, loff_t *pos)
@@ -1053,8 +995,6 @@ static void *p_start(struct seq_file *m, loff_t *pos)
 {
 	struct trace_pid_list *pid_list;
 	struct trace_array *tr = m->private;
-	unsigned long pid;
-	loff_t l = 0;
 
 	/*
 	 * Grab the mutex, to keep calls to p_next() having the same
@@ -1070,15 +1010,7 @@ static void *p_start(struct seq_file *m, loff_t *pos)
 	if (!pid_list)
 		return NULL;
 
-	pid = find_first_bit(pid_list->pids, pid_list->pid_max);
-	if (pid >= pid_list->pid_max)
-		return NULL;
-
-	/* Return pid + 1 so that zero can be the exit value */
-	for (pid++; pid && l < *pos;
-	     pid = (unsigned long)p_next(m, (void *)pid, &l))
-		;
-	return (void *)pid;
+	return trace_pid_start(pid_list, pos);
 }
 
 static void p_stop(struct seq_file *m, void *p)
@@ -1088,14 +1020,6 @@ static void p_stop(struct seq_file *m, void *p)
 	mutex_unlock(&event_mutex);
 }
 
-static int p_show(struct seq_file *m, void *v)
-{
-	unsigned long pid = (unsigned long)v - 1;
-
-	seq_printf(m, "%lu\n", pid);
-	return 0;
-}
-
 static ssize_t
 event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
 		  loff_t *ppos)
@@ -1654,7 +1578,7 @@ static void ignore_task_cpu(void *data)
 					     mutex_is_locked(&event_mutex));
 
 	this_cpu_write(tr->trace_buffer.data->ignore_pid,
-		       ignore_this_task(pid_list, current));
+		       trace_ignore_this_task(pid_list, current));
 }
 
 static ssize_t
@@ -1666,13 +1590,7 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
 	struct trace_pid_list *filtered_pids = NULL;
 	struct trace_pid_list *pid_list;
 	struct trace_event_file *file;
-	struct trace_parser parser;
-	unsigned long val;
-	loff_t this_pos;
-	ssize_t read = 0;
-	ssize_t ret = 0;
-	pid_t pid;
-	int nr_pids = 0;
+	ssize_t ret;
 
 	if (!cnt)
 		return 0;
@@ -1681,93 +1599,15 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
 	if (ret < 0)
 		return ret;
 
-	if (trace_parser_get_init(&parser, EVENT_BUF_SIZE + 1))
-		return -ENOMEM;
-
 	mutex_lock(&event_mutex);
+
 	filtered_pids = rcu_dereference_protected(tr->filtered_pids,
 					     lockdep_is_held(&event_mutex));
 
-	/*
-	 * Always recreate a new array. The write is an all or nothing
-	 * operation. Always create a new array when adding new pids by
-	 * the user. If the operation fails, then the current list is
-	 * not modified.
-	 */
-	pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL);
-	if (!pid_list) {
-		read = -ENOMEM;
-		goto out;
-	}
-	pid_list->pid_max = READ_ONCE(pid_max);
-	/* Only truncating will shrink pid_max */
-	if (filtered_pids && filtered_pids->pid_max > pid_list->pid_max)
-		pid_list->pid_max = filtered_pids->pid_max;
-	pid_list->pids = vzalloc((pid_list->pid_max + 7) >> 3);
-	if (!pid_list->pids) {
-		kfree(pid_list);
-		read = -ENOMEM;
-		goto out;
-	}
-	if (filtered_pids) {
-		/* copy the current bits to the new max */
-		pid = find_first_bit(filtered_pids->pids,
-				     filtered_pids->pid_max);
-		while (pid < filtered_pids->pid_max) {
-			set_bit(pid, pid_list->pids);
-			pid = find_next_bit(filtered_pids->pids,
-					    filtered_pids->pid_max,
-					    pid + 1);
-			nr_pids++;
-		}
-	}
-
-	while (cnt > 0) {
-
-		this_pos = 0;
-
-		ret = trace_get_user(&parser, ubuf, cnt, &this_pos);
-		if (ret < 0 || !trace_parser_loaded(&parser))
-			break;
-
-		read += ret;
-		ubuf += ret;
-		cnt -= ret;
-
-		parser.buffer[parser.idx] = 0;
-
-		ret = -EINVAL;
-		if (kstrtoul(parser.buffer, 0, &val))
-			break;
-		if (val >= pid_list->pid_max)
-			break;
-
-		pid = (pid_t)val;
-
-		set_bit(pid, pid_list->pids);
-		nr_pids++;
-
-		trace_parser_clear(&parser);
-		ret = 0;
-	}
-	trace_parser_put(&parser);
-
-	if (ret < 0) {
-		vfree(pid_list->pids);
-		kfree(pid_list);
-		read = ret;
+	ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt);
+	if (ret < 0)
 		goto out;
-	}
 
-	if (!nr_pids) {
-		/* Cleared the list of pids */
-		vfree(pid_list->pids);
-		kfree(pid_list);
-		read = ret;
-		if (!filtered_pids)
-			goto out;
-		pid_list = NULL;
-	}
 	rcu_assign_pointer(tr->filtered_pids, pid_list);
 
 	list_for_each_entry(file, &tr->events, list) {
@@ -1776,10 +1616,8 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
 
 	if (filtered_pids) {
 		synchronize_sched();
-
-		vfree(filtered_pids->pids);
-		kfree(filtered_pids);
-	} else {
+		trace_free_pid_list(filtered_pids);
+	} else if (pid_list) {
 		/*
 		 * Register a probe that is called before all other probes
 		 * to set ignore_pid if next or prev do not match.
@@ -1817,9 +1655,8 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
  out:
 	mutex_unlock(&event_mutex);
 
-	ret = read;
-	if (read > 0)
-		*ppos += read;
+	if (ret > 0)
+		*ppos += ret;
 
 	return ret;
 }
@@ -1846,7 +1683,7 @@ static const struct seq_operations show_set_event_seq_ops = {
 static const struct seq_operations show_set_pid_seq_ops = {
 	.start = p_start,
 	.next = p_next,
-	.show = p_show,
+	.show = trace_pid_show,
 	.stop = p_stop,
 };
 

kernel/trace/trace_functions.c

@@ -43,7 +43,7 @@ static int allocate_ftrace_ops(struct trace_array *tr)
 
 	/* Currently only the non stack verision is supported */
 	ops->func = function_trace_call;
-	ops->flags = FTRACE_OPS_FL_RECURSION_SAFE;
+	ops->flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_PID;
 
 	tr->ops = ops;
 	ops->private = tr;

kernel/trace/trace_functions_graph.c

@@ -319,7 +319,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
 	int cpu;
 	int pc;
 
-	if (!ftrace_trace_task(current))
+	if (!ftrace_trace_task(tr))
 		return 0;
 
 	/* trace it when it is-nested-in or is a function enabled. */
@@ -338,6 +338,13 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
 	if (ftrace_graph_notrace_addr(trace->func))
 		return 1;
 
+	/*
+	 * Stop here if tracing_threshold is set. We only write function return
+	 * events to the ring buffer.
+	 */
+	if (tracing_thresh)
+		return 1;
+
 	local_irq_save(flags);
 	cpu = raw_smp_processor_id();
 	data = per_cpu_ptr(tr->trace_buffer.data, cpu);
@@ -355,14 +362,6 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
 	return ret;
 }
 
-static int trace_graph_thresh_entry(struct ftrace_graph_ent *trace)
-{
-	if (tracing_thresh)
-		return 1;
-	else
-		return trace_graph_entry(trace);
-}
-
 static void
 __trace_graph_function(struct trace_array *tr,
 		unsigned long ip, unsigned long flags, int pc)
@@ -457,7 +456,7 @@ static int graph_trace_init(struct trace_array *tr)
 	set_graph_array(tr);
 	if (tracing_thresh)
 		ret = register_ftrace_graph(&trace_graph_thresh_return,
-					    &trace_graph_thresh_entry);
+					    &trace_graph_entry);
 	else
 		ret = register_ftrace_graph(&trace_graph_return,
 					    &trace_graph_entry);

kernel/trace/trace_kprobe.c

@@ -587,6 +587,7 @@ static int create_trace_kprobe(int argc, char **argv)
 	 *  $retval	: fetch return value
 	 *  $stack	: fetch stack address
 	 *  $stackN	: fetch Nth of stack (N:0-)
+	 *  $comm       : fetch current task comm
 	 *  @ADDR	: fetch memory at ADDR (ADDR should be in kernel)
 	 *  @SYM[+|-offs] : fetch memory at SYM +|- offs (SYM is a data symbol)
 	 *  %REG	: fetch register REG

kernel/trace/trace_mmiotrace.c

@@ -68,19 +68,15 @@ static void mmio_print_pcidev(struct trace_seq *s, const struct pci_dev *dev)
 	trace_seq_printf(s, "PCIDEV %02x%02x %04x%04x %x",
 			 dev->bus->number, dev->devfn,
 			 dev->vendor, dev->device, dev->irq);
-	/*
-	 * XXX: is pci_resource_to_user() appropriate, since we are
-	 * supposed to interpret the __ioremap() phys_addr argument based on
-	 * these printed values?
-	 */
 	for (i = 0; i < 7; i++) {
-		pci_resource_to_user(dev, i, &dev->resource[i], &start, &end);
+		start = dev->resource[i].start;
 		trace_seq_printf(s, " %llx",
 			(unsigned long long)(start |
 			(dev->resource[i].flags & PCI_REGION_FLAG_MASK)));
 	}
 	for (i = 0; i < 7; i++) {
-		pci_resource_to_user(dev, i, &dev->resource[i], &start, &end);
+		start = dev->resource[i].start;
+		end = dev->resource[i].end;
 		trace_seq_printf(s, " %llx",
 			dev->resource[i].start < dev->resource[i].end ?
 			(unsigned long long)(end - start) + 1 : 0);

kernel/trace/trace_probe.c

@@ -218,6 +218,28 @@ free_bitfield_fetch_param(struct bitfield_fetch_param *data)
 	kfree(data);
 }
 
+void FETCH_FUNC_NAME(comm, string)(struct pt_regs *regs,
+					  void *data, void *dest)
+{
+	int maxlen = get_rloc_len(*(u32 *)dest);
+	u8 *dst = get_rloc_data(dest);
+	long ret;
+
+	if (!maxlen)
+		return;
+
+	ret = strlcpy(dst, current->comm, maxlen);
+	*(u32 *)dest = make_data_rloc(ret, get_rloc_offs(*(u32 *)dest));
+}
+NOKPROBE_SYMBOL(FETCH_FUNC_NAME(comm, string));
+
+void FETCH_FUNC_NAME(comm, string_size)(struct pt_regs *regs,
+					       void *data, void *dest)
+{
+	*(u32 *)dest = strlen(current->comm) + 1;
+}
+NOKPROBE_SYMBOL(FETCH_FUNC_NAME(comm, string_size));
+
 static const struct fetch_type *find_fetch_type(const char *type,
 						const struct fetch_type *ftbl)
 {
@@ -348,6 +370,11 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
 			}
 		} else
 			ret = -EINVAL;
+	} else if (strcmp(arg, "comm") == 0) {
+		if (strcmp(t->name, "string") != 0 &&
+		    strcmp(t->name, "string_size") != 0)
+			return -EINVAL;
+		f->fn = t->fetch[FETCH_MTD_comm];
 	} else
 		ret = -EINVAL;
 
@@ -522,6 +549,12 @@ int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
 		arg[t - parg->comm] = '\0';
 		t++;
 	}
+	/*
+	 * The default type of $comm should be "string", and it can't be
+	 * dereferenced.
+	 */
+	if (!t && strcmp(arg, "$comm") == 0)
+		t = "string";
 	parg->type = find_fetch_type(t, ftbl);
 	if (!parg->type) {
 		pr_info("Unsupported type: %s\n", t);

kernel/trace/trace_probe.h

@@ -102,6 +102,7 @@ enum {
 	FETCH_MTD_reg = 0,
 	FETCH_MTD_stack,
 	FETCH_MTD_retval,
+	FETCH_MTD_comm,
 	FETCH_MTD_memory,
 	FETCH_MTD_symbol,
 	FETCH_MTD_deref,
@@ -183,6 +184,14 @@ DECLARE_BASIC_FETCH_FUNCS(bitfield);
 #define fetch_bitfield_string			NULL
 #define fetch_bitfield_string_size		NULL
 
+/* comm only makes sense as a string */
+#define fetch_comm_u8		NULL
+#define fetch_comm_u16		NULL
+#define fetch_comm_u32		NULL
+#define fetch_comm_u64		NULL
+DECLARE_FETCH_FUNC(comm, string);
+DECLARE_FETCH_FUNC(comm, string_size);
+
 /*
  * Define macro for basic types - we don't need to define s* types, because
  * we have to care only about bitwidth at recording time.
@@ -213,6 +222,7 @@ DEFINE_FETCH_##method(u64)
 ASSIGN_FETCH_FUNC(reg, ftype),				\
 ASSIGN_FETCH_FUNC(stack, ftype),			\
 ASSIGN_FETCH_FUNC(retval, ftype),			\
+ASSIGN_FETCH_FUNC(comm, ftype),				\
 ASSIGN_FETCH_FUNC(memory, ftype),			\
 ASSIGN_FETCH_FUNC(symbol, ftype),			\
 ASSIGN_FETCH_FUNC(deref, ftype),			\

samples/Kconfig

@@ -11,6 +11,13 @@ config SAMPLE_TRACE_EVENTS
 	help
 	  This build trace event example modules.
 
+config SAMPLE_TRACE_PRINTK
+        tristate "Build trace_printk module - tests various trace_printk formats"
+	depends on EVENT_TRACING && m
+	help
+	 This builds a module that calls trace_printk() and can be used to
+	 test various trace_printk() calls from a module.
+
 config SAMPLE_KOBJECT
 	tristate "Build kobject examples -- loadable modules only"
 	depends on m

samples/Makefile

@@ -2,4 +2,4 @@
 
 obj-$(CONFIG_SAMPLES)	+= kobject/ kprobes/ trace_events/ livepatch/ \
 			   hw_breakpoint/ kfifo/ kdb/ hidraw/ rpmsg/ seccomp/ \
-			   configfs/ connector/ v4l/
+			   configfs/ connector/ v4l/ trace_printk/

samples/trace_printk/Makefile

@@ -0,0 +1,6 @@
+# builds a module that calls various trace_printk routines
+# then to use one (as root):  insmod <module_name.ko>
+
+# This module can also be used to test the trace_printk code.
+
+obj-$(CONFIG_SAMPLE_TRACE_PRINTK) += trace-printk.o

samples/trace_printk/trace-printk.c

@@ -0,0 +1,56 @@
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/irq_work.h>
+
+/* Must not be static to force gcc to consider these non constant */
+char *trace_printk_test_global_str =
+	"This is a dynamic string that will use trace_puts\n";
+
+char *trace_printk_test_global_str_irq =
+	"(irq) This is a dynamic string that will use trace_puts\n";
+
+char *trace_printk_test_global_str_fmt =
+	"%sThis is a %s that will use trace_printk\n";
+
+static struct irq_work irqwork;
+
+static void trace_printk_irq_work(struct irq_work *work)
+{
+	trace_printk("(irq) This is a static string that will use trace_bputs\n");
+	trace_printk(trace_printk_test_global_str_irq);
+
+	trace_printk("(irq) This is a %s that will use trace_bprintk()\n",
+		     "static string");
+
+	trace_printk(trace_printk_test_global_str_fmt,
+		     "(irq) ", "dynamic string");
+}
+
+static int __init trace_printk_init(void)
+{
+	init_irq_work(&irqwork, trace_printk_irq_work);
+
+	trace_printk("This is a static string that will use trace_bputs\n");
+	trace_printk(trace_printk_test_global_str);
+
+	/* Kick off printing in irq context */
+	irq_work_queue(&irqwork);
+
+	trace_printk("This is a %s that will use trace_bprintk()\n",
+		     "static string");
+
+	trace_printk(trace_printk_test_global_str_fmt, "", "dynamic string");
+
+	return 0;
+}
+
+static void __exit trace_printk_exit(void)
+{
+}
+
+module_init(trace_printk_init);
+module_exit(trace_printk_exit);
+
+MODULE_AUTHOR("Steven Rostedt");
+MODULE_DESCRIPTION("trace-printk");
+MODULE_LICENSE("GPL");