eventfs: Remove eventfs_file and just use eventfs_inode

Instead of having a descriptor for every file represented in the eventfs
directory, only have the directory itself represented. Change the API to
send in a list of entries that represent all the files in the directory
(but not other directories). The entry list contains a name and a callback
function that will be used to create the files when they are accessed.

struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry *parent,
						const struct eventfs_entry *entries,
						int size, void *data);

is used for the top level eventfs directory, and returns an eventfs_inode
that will be used by:

struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode *parent,
					 const struct eventfs_entry *entries,
					 int size, void *data);

where both of the above take an array of struct eventfs_entry entries for
every file that is in the directory.

The entries are defined by:

typedef int (*eventfs_callback)(const char *name, umode_t *mode, void **data,
				const struct file_operations **fops);

struct eventfs_entry {
	const char			*name;
	eventfs_callback		callback;
};

Where the name is the name of the file and the callback gets called when
the file is being created. The callback passes in the name (in case the
same callback is used for multiple files), a pointer to the mode, data and
fops. The data will be pointing to the data that was passed in
eventfs_create_dir() or eventfs_create_events_dir() but may be overridden
to point to something else, as it will be used to point to the
inode->i_private that is created. The information passed back from the
callback is used to create the dentry/inode.

If the callback fills the data and the file should be created, it must
return a positive number. On zero or negative, the file is ignored.

This logic may also be used as a prototype to convert entire pseudo file
systems into just-in-time allocation.

The "show_events_dentry" file has been updated to show the directories,
and any files they have.

With just the eventfs_file allocations:

 Before after deltas for meminfo (in kB):

   MemFree:		-14360
   MemAvailable:	-14260
   Buffers:		40
   Cached:		24
   Active:		44
   Inactive:		48
   Inactive(anon):	28
   Active(file):	44
   Inactive(file):	20
   Dirty:		-4
   AnonPages:		28
   Mapped:		4
   KReclaimable:	132
   Slab:		1604
   SReclaimable:	132
   SUnreclaim:		1472
   Committed_AS:	12

 Before after deltas for slabinfo:

   <slab>:		<objects>	[ * <size> = <total>]

   ext4_inode_cache	27		[* 1184 = 31968 ]
   extent_status	102		[*   40 = 4080 ]
   tracefs_inode_cache	144		[*  656 = 94464 ]
   buffer_head		39		[*  104 = 4056 ]
   shmem_inode_cache	49		[*  800 = 39200 ]
   filp			-53		[*  256 = -13568 ]
   dentry		251		[*  192 = 48192 ]
   lsm_file_cache	277		[*   32 = 8864 ]
   vm_area_struct	-14		[*  184 = -2576 ]
   trace_event_file	1748		[*   88 = 153824 ]
   kmalloc-1k		35		[* 1024 = 35840 ]
   kmalloc-256		49		[*  256 = 12544 ]
   kmalloc-192		-28		[*  192 = -5376 ]
   kmalloc-128		-30		[*  128 = -3840 ]
   kmalloc-96		10581		[*   96 = 1015776 ]
   kmalloc-64		3056		[*   64 = 195584 ]
   kmalloc-32		1291		[*   32 = 41312 ]
   kmalloc-16		2310		[*   16 = 36960 ]
   kmalloc-8		9216		[*    8 = 73728 ]

 Free memory dropped by 14,360 kB
 Available memory dropped by 14,260 kB
 Total slab additions in size: 1,771,032 bytes

With this change:

 Before after deltas for meminfo (in kB):

   MemFree:		-12084
   MemAvailable:	-11976
   Buffers:		32
   Cached:		32
   Active:		72
   Inactive:		168
   Inactive(anon):	176
   Active(file):	72
   Inactive(file):	-8
   Dirty:		24
   AnonPages:		196
   Mapped:		8
   KReclaimable:	148
   Slab:		836
   SReclaimable:	148
   SUnreclaim:		688
   Committed_AS:	324

 Before after deltas for slabinfo:

   <slab>:		<objects>	[ * <size> = <total>]

   tracefs_inode_cache	144		[* 656 = 94464 ]
   shmem_inode_cache	-23		[* 800 = -18400 ]
   filp			-92		[* 256 = -23552 ]
   dentry		179		[* 192 = 34368 ]
   lsm_file_cache	-3		[* 32 = -96 ]
   vm_area_struct	-13		[* 184 = -2392 ]
   trace_event_file	1748		[* 88 = 153824 ]
   kmalloc-1k		-49		[* 1024 = -50176 ]
   kmalloc-256		-27		[* 256 = -6912 ]
   kmalloc-128		1864		[* 128 = 238592 ]
   kmalloc-64		4685		[* 64 = 299840 ]
   kmalloc-32		-72		[* 32 = -2304 ]
   kmalloc-16		256		[* 16 = 4096 ]
   total = 721352

 Free memory dropped by 12,084 kB
 Available memory dropped by 11,976 kB
 Total slab additions in size:  721,352 bytes

That's over 2 MB in savings per instance for free and available memory,
and over 1 MB in savings per instance of slab memory.

Link: https://lore.kernel.org/linux-trace-kernel/20231003184059.4924468e@gandalf.local.home
Link: https://lore.kernel.org/linux-trace-kernel/20231004165007.43d79161@gandalf.local.home

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Ajay Kaher <akaher@vmware.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

3 files changed, 221 insertions, 103 deletions

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index dd6395692ff9..4383be8fa1b0 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9764,7 +9764,6 @@ static __init void create_trace_instances(struct dentry *d_tracer)
 static void
 init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 {
-	struct trace_event_file *file;
 	int cpu;
 
 	trace_create_file("available_tracers", TRACE_MODE_READ, d_tracer,
@@ -9797,11 +9796,7 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 	trace_create_file("trace_marker", 0220, d_tracer,
 			  tr, &tracing_mark_fops);
 
-	file = __find_event_file(tr, "ftrace", "print");
-	if (file && file->ef)
-		eventfs_add_file("trigger", TRACE_MODE_WRITE, file->ef,
-				  file, &event_trigger_fops);
-	tr->trace_marker_file = file;
+	tr->trace_marker_file = __find_event_file(tr, "ftrace", "print");
 
 	trace_create_file("trace_marker_raw", 0220, d_tracer,
 			  tr, &tracing_mark_raw_fops);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index e92cb9c1292f..0e1405abf4f7 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -381,7 +381,7 @@ struct trace_array {
 	struct dentry		*dir;
 	struct dentry		*options;
 	struct dentry		*percpu_dir;
-	struct dentry		*event_dir;
+	struct eventfs_inode	*event_dir;
 	struct trace_options	*topts;
 	struct list_head	systems;
 	struct list_head	events;
@@ -1349,7 +1349,7 @@ struct trace_subsystem_dir {
 	struct list_head		list;
 	struct event_subsystem		*subsystem;
 	struct trace_array		*tr;
-	struct eventfs_file             *ef;
+	struct eventfs_inode		*ei;
 	int				ref_count;
 	int				nr_events;
 };
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 099b9b6bbdc4..a3b9d9423824 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -984,7 +984,7 @@ static void remove_subsystem(struct trace_subsystem_dir *dir)
 		return;
 
 	if (!--dir->nr_events) {
-		eventfs_remove(dir->ef);
+		eventfs_remove_dir(dir->ei);
 		list_del(&dir->list);
 		__put_system_dir(dir);
 	}
@@ -992,7 +992,7 @@ static void remove_subsystem(struct trace_subsystem_dir *dir)
 
 static void remove_event_file_dir(struct trace_event_file *file)
 {
-	eventfs_remove(file->ef);
+	eventfs_remove_dir(file->ei);
 	list_del(&file->list);
 	remove_subsystem(file->system);
 	free_event_filter(file->filter);
@@ -2282,14 +2282,40 @@ create_new_subsystem(const char *name)
 	return NULL;
 }
 
-static struct eventfs_file *
+int system_callback(const char *name, umode_t *mode, void **data,
+		    const struct file_operations **fops)
+{
+	if (strcmp(name, "filter") == 0)
+		*fops = &ftrace_subsystem_filter_fops;
+
+	else if (strcmp(name, "enable") == 0)
+		*fops = &ftrace_system_enable_fops;
+
+	else
+		return 0;
+
+	*mode = TRACE_MODE_WRITE;
+	return 1;
+}
+
+static struct eventfs_inode *
 event_subsystem_dir(struct trace_array *tr, const char *name,
-		    struct trace_event_file *file, struct dentry *parent)
+		    struct trace_event_file *file, struct eventfs_inode *parent)
 {
 	struct event_subsystem *system, *iter;
 	struct trace_subsystem_dir *dir;
-	struct eventfs_file *ef;
-	int res;
+	struct eventfs_inode *ei;
+	int nr_entries;
+	static struct eventfs_entry system_entries[] = {
+		{
+			.name		= "filter",
+			.callback	= system_callback,
+		},
+		{
+			.name		= "enable",
+			.callback	= system_callback,
+		}
+	};
 
 	/* First see if we did not already create this dir */
 	list_for_each_entry(dir, &tr->systems, list) {
@@ -2297,7 +2323,7 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
 		if (strcmp(system->name, name) == 0) {
 			dir->nr_events++;
 			file->system = dir;
-			return dir->ef;
+			return dir->ei;
 		}
 	}
 
@@ -2321,39 +2347,29 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
 	} else
 		__get_system(system);
 
-	ef = eventfs_add_subsystem_dir(name, parent);
-	if (IS_ERR(ef)) {
+	/* ftrace only has directories no files */
+	if (strcmp(name, "ftrace") == 0)
+		nr_entries = 0;
+	else
+		nr_entries = ARRAY_SIZE(system_entries);
+
+	ei = eventfs_create_dir(name, parent, system_entries, nr_entries, dir);
+	if (!ei) {
 		pr_warn("Failed to create system directory %s\n", name);
 		__put_system(system);
 		goto out_free;
 	}
 
-	dir->ef = ef;
+	dir->ei = ei;
 	dir->tr = tr;
 	dir->ref_count = 1;
 	dir->nr_events = 1;
 	dir->subsystem = system;
 	file->system = dir;
 
-	/* the ftrace system is special, do not create enable or filter files */
-	if (strcmp(name, "ftrace") != 0) {
-
-		res = eventfs_add_file("filter", TRACE_MODE_WRITE,
-					    dir->ef, dir,
-					    &ftrace_subsystem_filter_fops);
-		if (res) {
-			kfree(system->filter);
-			system->filter = NULL;
-			pr_warn("Could not create tracefs '%s/filter' entry\n", name);
-		}
-
-		eventfs_add_file("enable", TRACE_MODE_WRITE, dir->ef, dir,
-				  &ftrace_system_enable_fops);
-	}
-
 	list_add(&dir->list, &tr->systems);
 
-	return dir->ef;
+	return dir->ei;
 
  out_free:
 	kfree(dir);
@@ -2402,15 +2418,134 @@ event_define_fields(struct trace_event_call *call)
 	return ret;
 }
 
+static int event_callback(const char *name, umode_t *mode, void **data,
+			  const struct file_operations **fops)
+{
+	struct trace_event_file *file = *data;
+	struct trace_event_call *call = file->event_call;
+
+	if (strcmp(name, "format") == 0) {
+		*mode = TRACE_MODE_READ;
+		*fops = &ftrace_event_format_fops;
+		*data = call;
+		return 1;
+	}
+
+	/*
+	 * Only event directories that can be enabled should have
+	 * triggers or filters, with the exception of the "print"
+	 * event that can have a "trigger" file.
+	 */
+	if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) {
+		if (call->class->reg && strcmp(name, "enable") == 0) {
+			*mode = TRACE_MODE_WRITE;
+			*fops = &ftrace_enable_fops;
+			return 1;
+		}
+
+		if (strcmp(name, "filter") == 0) {
+			*mode = TRACE_MODE_WRITE;
+			*fops = &ftrace_event_filter_fops;
+			return 1;
+		}
+	}
+
+	if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) ||
+	    strcmp(trace_event_name(call), "print") == 0) {
+		if (strcmp(name, "trigger") == 0) {
+			*mode = TRACE_MODE_WRITE;
+			*fops = &event_trigger_fops;
+			return 1;
+		}
+	}
+
+#ifdef CONFIG_PERF_EVENTS
+	if (call->event.type && call->class->reg &&
+	    strcmp(name, "id") == 0) {
+		*mode = TRACE_MODE_READ;
+		*data = (void *)(long)call->event.type;
+		*fops = &ftrace_event_id_fops;
+		return 1;
+	}
+#endif
+
+#ifdef CONFIG_HIST_TRIGGERS
+	if (strcmp(name, "hist") == 0) {
+		*mode = TRACE_MODE_READ;
+		*fops = &event_hist_fops;
+		return 1;
+	}
+#endif
+#ifdef CONFIG_HIST_TRIGGERS_DEBUG
+	if (strcmp(name, "hist_debug") == 0) {
+		*mode = TRACE_MODE_READ;
+		*fops = &event_hist_debug_fops;
+		return 1;
+	}
+#endif
+#ifdef CONFIG_TRACE_EVENT_INJECT
+	if (call->event.type && call->class->reg &&
+	    strcmp(name, "inject") == 0) {
+		*mode = 0200;
+		*fops = &event_inject_fops;
+		return 1;
+	}
+#endif
+	return 0;
+}
+
 static int
-event_create_dir(struct dentry *parent, struct trace_event_file *file)
+event_create_dir(struct eventfs_inode *parent, struct trace_event_file *file)
 {
 	struct trace_event_call *call = file->event_call;
-	struct eventfs_file *ef_subsystem = NULL;
 	struct trace_array *tr = file->tr;
-	struct eventfs_file *ef;
+	struct eventfs_inode *e_events;
+	struct eventfs_inode *ei;
 	const char *name;
+	int nr_entries;
 	int ret;
+	static struct eventfs_entry event_entries[] = {
+		{
+			.name		= "enable",
+			.callback	= event_callback,
+		},
+		{
+			.name		= "filter",
+			.callback	= event_callback,
+		},
+		{
+			.name		= "trigger",
+			.callback	= event_callback,
+		},
+		{
+			.name		= "format",
+			.callback	= event_callback,
+		},
+#ifdef CONFIG_PERF_EVENTS
+		{
+			.name		= "id",
+			.callback	= event_callback,
+		},
+#endif
+#ifdef CONFIG_HIST_TRIGGERS
+		{
+			.name		= "hist",
+			.callback	= event_callback,
+		},
+#endif
+#ifdef CONFIG_HIST_TRIGGERS_DEBUG
+		{
+			.name		= "hist_debug",
+			.callback	= event_callback,
+		},
+#endif
+#ifdef CONFIG_TRACE_EVENT_INJECT
+		{
+			.name		= "inject",
+			.callback	= event_callback,
+		},
+#endif
+	};
 
 	/*
 	 * If the trace point header did not define TRACE_SYSTEM
@@ -2420,29 +2555,20 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file)
 	if (WARN_ON_ONCE(strcmp(call->class->system, TRACE_SYSTEM) == 0))
 		return -ENODEV;
 
-	ef_subsystem = event_subsystem_dir(tr, call->class->system, file, parent);
-	if (!ef_subsystem)
+	e_events = event_subsystem_dir(tr, call->class->system, file, parent);
+	if (!e_events)
 		return -ENOMEM;
 
+	nr_entries = ARRAY_SIZE(event_entries);
+
 	name = trace_event_name(call);
-	ef = eventfs_add_dir(name, ef_subsystem);
-	if (IS_ERR(ef)) {
+	ei = eventfs_create_dir(name, e_events, event_entries, nr_entries, file);
+	if (IS_ERR(ei)) {
 		pr_warn("Could not create tracefs '%s' directory\n", name);
 		return -1;
 	}
 
-	file->ef = ef;
-
-	if (call->class->reg && !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
-		eventfs_add_file("enable", TRACE_MODE_WRITE, file->ef, file,
-				  &ftrace_enable_fops);
-
-#ifdef CONFIG_PERF_EVENTS
-	if (call->event.type && call->class->reg)
-		eventfs_add_file("id", TRACE_MODE_READ, file->ef,
-				  (void *)(long)call->event.type,
-				  &ftrace_event_id_fops);
-#endif
+	file->ei = ei;
 
 	ret = event_define_fields(call);
 	if (ret < 0) {
@@ -2450,35 +2576,6 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file)
 		return ret;
 	}
 
-	/*
-	 * Only event directories that can be enabled should have
-	 * triggers or filters.
-	 */
-	if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) {
-		eventfs_add_file("filter", TRACE_MODE_WRITE, file->ef,
-				  file, &ftrace_event_filter_fops);
-
-		eventfs_add_file("trigger", TRACE_MODE_WRITE, file->ef,
-				  file, &event_trigger_fops);
-	}
-
-#ifdef CONFIG_HIST_TRIGGERS
-	eventfs_add_file("hist", TRACE_MODE_READ, file->ef, file,
-			  &event_hist_fops);
-#endif
-#ifdef CONFIG_HIST_TRIGGERS_DEBUG
-	eventfs_add_file("hist_debug", TRACE_MODE_READ, file->ef, file,
-			  &event_hist_debug_fops);
-#endif
-	eventfs_add_file("format", TRACE_MODE_READ, file->ef, call,
-			  &ftrace_event_format_fops);
-
-#ifdef CONFIG_TRACE_EVENT_INJECT
-	if (call->event.type && call->class->reg)
-		eventfs_add_file("inject", 0200, file->ef, file,
-				  &event_inject_fops);
-#endif
-
 	return 0;
 }
 
@@ -3623,30 +3720,65 @@ static __init int setup_trace_event(char *str)
 }
 __setup("trace_event=", setup_trace_event);
 
+static int events_callback(const char *name, umode_t *mode, void **data,
+			   const struct file_operations **fops)
+{
+	if (strcmp(name, "enable") == 0) {
+		*mode = TRACE_MODE_WRITE;
+		*fops = &ftrace_tr_enable_fops;
+		return 1;
+	}
+
+	if (strcmp(name, "header_page") == 0)
+		*data = ring_buffer_print_page_header;
+
+	else if (strcmp(name, "header_event") == 0)
+		*data = ring_buffer_print_entry_header;
+
+	else
+		return 0;
+
+	*mode = TRACE_MODE_READ;
+	*fops = &ftrace_show_header_fops;
+	return 1;
+}
+
 /* Expects to have event_mutex held when called */
 static int
 create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
 {
-	struct dentry *d_events;
+	struct eventfs_inode *e_events;
 	struct dentry *entry;
-	int error = 0;
+	int nr_entries;
+	static struct eventfs_entry events_entries[] = {
+		{
+			.name		= "enable",
+			.callback	= events_callback,
+		},
+		{
+			.name		= "header_page",
+			.callback	= events_callback,
+		},
+		{
+			.name		= "header_event",
+			.callback	= events_callback,
+		},
+	};
 
 	entry = trace_create_file("set_event", TRACE_MODE_WRITE, parent,
 				  tr, &ftrace_set_event_fops);
 	if (!entry)
 		return -ENOMEM;
 
-	d_events = eventfs_create_events_dir("events", parent);
-	if (IS_ERR(d_events)) {
+	nr_entries = ARRAY_SIZE(events_entries);
+
+	e_events = eventfs_create_events_dir("events", parent, events_entries,
+					     nr_entries, tr);
+	if (IS_ERR(e_events)) {
 		pr_warn("Could not create tracefs 'events' directory\n");
 		return -ENOMEM;
 	}
 
-	error = eventfs_add_events_file("enable", TRACE_MODE_WRITE, d_events,
-				  tr, &ftrace_tr_enable_fops);
-	if (error)
-		return -ENOMEM;
-
 	/* There are not as crucial, just warn if they are not created */
 
 	trace_create_file("set_event_pid", TRACE_MODE_WRITE, parent,
@@ -3656,16 +3788,7 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
 			  TRACE_MODE_WRITE, parent, tr,
 			  &ftrace_set_event_notrace_pid_fops);
 
-	/* ring buffer internal formats */
-	eventfs_add_events_file("header_page", TRACE_MODE_READ, d_events,
-				  ring_buffer_print_page_header,
-				  &ftrace_show_header_fops);
-
-	eventfs_add_events_file("header_event", TRACE_MODE_READ, d_events,
-				  ring_buffer_print_entry_header,
-				  &ftrace_show_header_fops);
-
-	tr->event_dir = d_events;
+	tr->event_dir = e_events;
 
 	return 0;
 }
@@ -3749,7 +3872,7 @@ int event_trace_del_tracer(struct trace_array *tr)
 
 	down_write(&trace_event_sem);
 	__trace_remove_event_dirs(tr);
-	eventfs_remove_events_dir(tr->event_dir);
+	eventfs_remove_dir(tr->event_dir);
 	up_write(&trace_event_sem);
 
 	tr->event_dir = NULL;