Merge tag 'trace-v6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing updates from Steven Rostedt:
 "User visible changes:

   - Added a way to easier filter with cpumasks:

       # echo 'cpumask & CPUS{17-42}' > /sys/kernel/tracing/events/ipi_send_cpumask/filter

   - Show actual size of ring buffer after modifying the ring buffer
     size via buffer_size_kb.

     Currently it just returns what was written, but the actual size
     rounds up to the sub buffer size. Show that real size instead.

  Major changes:

   - Added "eventfs". This is the code that handles the inodes and
     dentries of tracefs/events directory. As there are thousands of
     events, and each event has several inodes and dentries that
     currently exist even when tracing is never used, they take up
     precious memory. Instead, eventfs will allocate the inodes and
     dentries in a JIT way (similar to what procfs does). There is now
     metadata that handles the events and subdirectories, and will
     create the inodes and dentries when they are used.

     Note, I also have patches that remove the subdirectory meta data,
     but will wait till the next merge window before applying them. It's
     a little more complex, and I want to make sure the dynamic code
     works properly before adding more complexity, making it easier to
     revert if need be.

  Minor changes:

   - Optimization to user event list traversal

   - Remove intermediate permission of tracefs files (note the
     intermediate permission removes all access to the files so it is
     not a security concern, but just a clean up)

   - Add the complex fix to FORTIFY_SOURCE to the kernel stack event
     logic

   - Other minor cleanups"

* tag 'trace-v6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (29 commits)
  tracefs: Remove kerneldoc from struct eventfs_file
  tracefs: Avoid changing i_mode to a temp value
  tracing/user_events: Optimize safe list traversals
  ftrace: Remove empty declaration ftrace_enable_daemon() and ftrace_disable_daemon()
  tracing: Remove unused function declarations
  tracing/filters: Document cpumask filtering
  tracing/filters: Further optimise scalar vs cpumask comparison
  tracing/filters: Optimise CPU vs cpumask filtering when the user mask is a single CPU
  tracing/filters: Optimise scalar vs cpumask filtering when the user mask is a single CPU
  tracing/filters: Optimise cpumask vs cpumask filtering when user mask is a single CPU
  tracing/filters: Enable filtering the CPU common field by a cpumask
  tracing/filters: Enable filtering a scalar field by a cpumask
  tracing/filters: Enable filtering a cpumask field by another cpumask
  tracing/filters: Dynamically allocate filter_pred.regex
  test: ftrace: Fix kprobe test for eventfs
  eventfs: Move tracing/events to eventfs
  eventfs: Implement removal of meta data from eventfs
  eventfs: Implement functions to create files and dirs when accessed
  eventfs: Implement eventfs lookup, read, open functions
  eventfs: Implement eventfs file add functions
  ...

Documentation/trace/events.rst

@@ -219,6 +219,20 @@ the function "security_prepare_creds" and less than the end of that function.
 The ".function" postfix can only be attached to values of size long, and can only
 be compared with "==" or "!=".
 
+Cpumask fields or scalar fields that encode a CPU number can be filtered using
+a user-provided cpumask in cpulist format. The format is as follows::
+
+  CPUS{$cpulist}
+
+Operators available to cpumask filtering are:
+
+& (intersection), ==, !=
+
+For example, this will filter events that have their .target_cpu field present
+in the given cpumask::
+
+  target_cpu & CPUS{17-42}
+
 5.2 Setting filters
 -------------------
 

fs/tracefs/Makefile

 # SPDX-License-Identifier: GPL-2.0-only
 tracefs-objs	:= inode.o
+tracefs-objs	+= event_inode.o
 
 obj-$(CONFIG_TRACING)	+= tracefs.o
 

fs/tracefs/inode.c

@@ -21,13 +21,33 @@
 #include <linux/parser.h>
 #include <linux/magic.h>
 #include <linux/slab.h>
+#include "internal.h"
 
 #define TRACEFS_DEFAULT_MODE	0700
+static struct kmem_cache *tracefs_inode_cachep __ro_after_init;
 
 static struct vfsmount *tracefs_mount;
 static int tracefs_mount_count;
 static bool tracefs_registered;
 
+static struct inode *tracefs_alloc_inode(struct super_block *sb)
+{
+	struct tracefs_inode *ti;
+
+	ti = kmem_cache_alloc(tracefs_inode_cachep, GFP_KERNEL);
+	if (!ti)
+		return NULL;
+
+	ti->flags = 0;
+
+	return &ti->vfs_inode;
+}
+
+static void tracefs_free_inode(struct inode *inode)
+{
+	kmem_cache_free(tracefs_inode_cachep, get_tracefs(inode));
+}
+
 static ssize_t default_read_file(struct file *file, char __user *buf,
 				 size_t count, loff_t *ppos)
 {
@@ -127,7 +147,7 @@ static const struct inode_operations tracefs_dir_inode_operations = {
 	.rmdir		= tracefs_syscall_rmdir,
 };
 
-static struct inode *tracefs_get_inode(struct super_block *sb)
+struct inode *tracefs_get_inode(struct super_block *sb)
 {
 	struct inode *inode = new_inode(sb);
 	if (inode) {
@@ -290,6 +310,7 @@ static int tracefs_apply_options(struct super_block *sb, bool remount)
 	struct tracefs_fs_info *fsi = sb->s_fs_info;
 	struct inode *inode = d_inode(sb->s_root);
 	struct tracefs_mount_opts *opts = &fsi->mount_opts;
+	umode_t tmp_mode;
 
 	/*
 	 * On remount, only reset mode/uid/gid if they were provided as mount
@@ -297,8 +318,9 @@ static int tracefs_apply_options(struct super_block *sb, bool remount)
 	 */
 
 	if (!remount || opts->opts & BIT(Opt_mode)) {
-		inode->i_mode &= ~S_IALLUGO;
-		inode->i_mode |= opts->mode;
+		tmp_mode = READ_ONCE(inode->i_mode) & ~S_IALLUGO;
+		tmp_mode |= opts->mode;
+		WRITE_ONCE(inode->i_mode, tmp_mode);
 	}
 
 	if (!remount || opts->opts & BIT(Opt_uid))
@@ -346,11 +368,31 @@ static int tracefs_show_options(struct seq_file *m, struct dentry *root)
 }
 
 static const struct super_operations tracefs_super_operations = {
+	.alloc_inode    = tracefs_alloc_inode,
+	.free_inode     = tracefs_free_inode,
+	.drop_inode     = generic_delete_inode,
 	.statfs		= simple_statfs,
 	.remount_fs	= tracefs_remount,
 	.show_options	= tracefs_show_options,
 };
 
+static void tracefs_dentry_iput(struct dentry *dentry, struct inode *inode)
+{
+	struct tracefs_inode *ti;
+
+	if (!dentry || !inode)
+		return;
+
+	ti = get_tracefs(inode);
+	if (ti && ti->flags & TRACEFS_EVENT_INODE)
+		eventfs_set_ef_status_free(dentry);
+	iput(inode);
+}
+
+static const struct dentry_operations tracefs_dentry_operations = {
+	.d_iput = tracefs_dentry_iput,
+};
+
 static int trace_fill_super(struct super_block *sb, void *data, int silent)
 {
 	static const struct tree_descr trace_files[] = {{""}};
@@ -373,6 +415,7 @@ static int trace_fill_super(struct super_block *sb, void *data, int silent)
 		goto fail;
 
 	sb->s_op = &tracefs_super_operations;
+	sb->s_d_op = &tracefs_dentry_operations;
 
 	tracefs_apply_options(sb, false);
 
@@ -399,7 +442,7 @@ static struct file_system_type trace_fs_type = {
 };
 MODULE_ALIAS_FS("tracefs");
 
-static struct dentry *start_creating(const char *name, struct dentry *parent)
+struct dentry *tracefs_start_creating(const char *name, struct dentry *parent)
 {
 	struct dentry *dentry;
 	int error;
@@ -437,7 +480,7 @@ static struct dentry *start_creating(const char *name, struct dentry *parent)
 	return dentry;
 }
 
-static struct dentry *failed_creating(struct dentry *dentry)
+struct dentry *tracefs_failed_creating(struct dentry *dentry)
 {
 	inode_unlock(d_inode(dentry->d_parent));
 	dput(dentry);
@@ -445,12 +488,86 @@ static struct dentry *failed_creating(struct dentry *dentry)
 	return NULL;
 }
 
-static struct dentry *end_creating(struct dentry *dentry)
+struct dentry *tracefs_end_creating(struct dentry *dentry)
 {
 	inode_unlock(d_inode(dentry->d_parent));
 	return dentry;
 }
 
+/**
+ * eventfs_start_creating - start the process of creating a dentry
+ * @name: Name of the file created for the dentry
+ * @parent: The parent dentry where this dentry will be created
+ *
+ * This is a simple helper function for the dynamically created eventfs
+ * files. When the directory of the eventfs files are accessed, their
+ * dentries are created on the fly. This function is used to start that
+ * process.
+ */
+struct dentry *eventfs_start_creating(const char *name, struct dentry *parent)
+{
+	struct dentry *dentry;
+	int error;
+
+	error = simple_pin_fs(&trace_fs_type, &tracefs_mount,
+			      &tracefs_mount_count);
+	if (error)
+		return ERR_PTR(error);
+
+	/*
+	 * If the parent is not specified, we create it in the root.
+	 * We need the root dentry to do this, which is in the super
+	 * block. A pointer to that is in the struct vfsmount that we
+	 * have around.
+	 */
+	if (!parent)
+		parent = tracefs_mount->mnt_root;
+
+	if (unlikely(IS_DEADDIR(parent->d_inode)))
+		dentry = ERR_PTR(-ENOENT);
+	else
+		dentry = lookup_one_len(name, parent, strlen(name));
+
+	if (!IS_ERR(dentry) && dentry->d_inode) {
+		dput(dentry);
+		dentry = ERR_PTR(-EEXIST);
+	}
+
+	if (IS_ERR(dentry))
+		simple_release_fs(&tracefs_mount, &tracefs_mount_count);
+
+	return dentry;
+}
+
+/**
+ * eventfs_failed_creating - clean up a failed eventfs dentry creation
+ * @dentry: The dentry to clean up
+ *
+ * If after calling eventfs_start_creating(), a failure is detected, the
+ * resources created by eventfs_start_creating() needs to be cleaned up. In
+ * that case, this function should be called to perform that clean up.
+ */
+struct dentry *eventfs_failed_creating(struct dentry *dentry)
+{
+	dput(dentry);
+	simple_release_fs(&tracefs_mount, &tracefs_mount_count);
+	return NULL;
+}
+
+/**
+ * eventfs_end_creating - Finish the process of creating a eventfs dentry
+ * @dentry: The dentry that has successfully been created.
+ *
+ * This function is currently just a place holder to match
+ * eventfs_start_creating(). In case any synchronization needs to be added,
+ * this function will be used to implement that without having to modify
+ * the callers of eventfs_start_creating().
+ */
+struct dentry *eventfs_end_creating(struct dentry *dentry)
+{
+	return dentry;
+}
+
 /**
  * tracefs_create_file - create a file in the tracefs filesystem
  * @name: a pointer to a string containing the name of the file to create.
@@ -490,14 +607,14 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode,
 	if (!(mode & S_IFMT))
 		mode |= S_IFREG;
 	BUG_ON(!S_ISREG(mode));
-	dentry = start_creating(name, parent);
+	dentry = tracefs_start_creating(name, parent);
 
 	if (IS_ERR(dentry))
 		return NULL;
 
 	inode = tracefs_get_inode(dentry->d_sb);
 	if (unlikely(!inode))
-		return failed_creating(dentry);
+		return tracefs_failed_creating(dentry);
 
 	inode->i_mode = mode;
 	inode->i_fop = fops ? fops : &tracefs_file_operations;
@@ -506,13 +623,13 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode,
 	inode->i_gid = d_inode(dentry->d_parent)->i_gid;
 	d_instantiate(dentry, inode);
 	fsnotify_create(d_inode(dentry->d_parent), dentry);
-	return end_creating(dentry);
+	return tracefs_end_creating(dentry);
 }
 
 static struct dentry *__create_dir(const char *name, struct dentry *parent,
 				   const struct inode_operations *ops)
 {
-	struct dentry *dentry = start_creating(name, parent);
+	struct dentry *dentry = tracefs_start_creating(name, parent);
 	struct inode *inode;
 
 	if (IS_ERR(dentry))
@@ -520,7 +637,7 @@ static struct dentry *__create_dir(const char *name, struct dentry *parent,
 
 	inode = tracefs_get_inode(dentry->d_sb);
 	if (unlikely(!inode))
-		return failed_creating(dentry);
+		return tracefs_failed_creating(dentry);
 
 	/* Do not set bits for OTH */
 	inode->i_mode = S_IFDIR | S_IRWXU | S_IRUSR| S_IRGRP | S_IXUSR | S_IXGRP;
@@ -534,7 +651,7 @@ static struct dentry *__create_dir(const char *name, struct dentry *parent,
 	d_instantiate(dentry, inode);
 	inc_nlink(d_inode(dentry->d_parent));
 	fsnotify_mkdir(d_inode(dentry->d_parent), dentry);
-	return end_creating(dentry);
+	return tracefs_end_creating(dentry);
 }
 
 /**
@@ -628,10 +745,26 @@ bool tracefs_initialized(void)
 	return tracefs_registered;
 }
 
+static void init_once(void *foo)
+{
+	struct tracefs_inode *ti = (struct tracefs_inode *) foo;
+
+	inode_init_once(&ti->vfs_inode);
+}
+
 static int __init tracefs_init(void)
 {
 	int retval;
 
+	tracefs_inode_cachep = kmem_cache_create("tracefs_inode_cache",
+						 sizeof(struct tracefs_inode),
+						 0, (SLAB_RECLAIM_ACCOUNT|
+						     SLAB_MEM_SPREAD|
+						     SLAB_ACCOUNT),
+						 init_once);
+	if (!tracefs_inode_cachep)
+		return -ENOMEM;
+
 	retval = sysfs_create_mount_point(kernel_kobj, "tracing");
 	if (retval)
 		return -EINVAL;

fs/tracefs/internal.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TRACEFS_INTERNAL_H
+#define _TRACEFS_INTERNAL_H
+
+enum {
+	TRACEFS_EVENT_INODE     = BIT(1),
+};
+
+struct tracefs_inode {
+	unsigned long           flags;
+	void                    *private;
+	struct inode            vfs_inode;
+};
+
+static inline struct tracefs_inode *get_tracefs(const struct inode *inode)
+{
+	return container_of(inode, struct tracefs_inode, vfs_inode);
+}
+
+struct dentry *tracefs_start_creating(const char *name, struct dentry *parent);
+struct dentry *tracefs_end_creating(struct dentry *dentry);
+struct dentry *tracefs_failed_creating(struct dentry *dentry);
+struct inode *tracefs_get_inode(struct super_block *sb);
+struct dentry *eventfs_start_creating(const char *name, struct dentry *parent);
+struct dentry *eventfs_failed_creating(struct dentry *dentry);
+struct dentry *eventfs_end_creating(struct dentry *dentry);
+void eventfs_set_ef_status_free(struct dentry *dentry);
+
+#endif /* _TRACEFS_INTERNAL_H */

include/linux/ftrace.h

@@ -862,13 +862,8 @@ extern int skip_trace(unsigned long ip);
 extern void ftrace_module_init(struct module *mod);
 extern void ftrace_module_enable(struct module *mod);
 extern void ftrace_release_mod(struct module *mod);
-
-extern void ftrace_disable_daemon(void);
-extern void ftrace_enable_daemon(void);
 #else /* CONFIG_DYNAMIC_FTRACE */
 static inline int skip_trace(unsigned long ip) { return 0; }
-static inline void ftrace_disable_daemon(void) { }
-static inline void ftrace_enable_daemon(void) { }
 static inline void ftrace_module_init(struct module *mod) { }
 static inline void ftrace_module_enable(struct module *mod) { }
 static inline void ftrace_release_mod(struct module *mod) { }

include/linux/trace_events.h

@@ -649,6 +649,7 @@ struct trace_event_file {
 	struct list_head		list;
 	struct trace_event_call		*event_call;
 	struct event_filter __rcu	*filter;
+	struct eventfs_file             *ef;
 	struct dentry			*dir;
 	struct trace_array		*tr;
 	struct trace_subsystem_dir	*system;
@@ -824,6 +825,7 @@ enum {
 	FILTER_RDYN_STRING,
 	FILTER_PTR_STRING,
 	FILTER_TRACE_FN,
+	FILTER_CPUMASK,
 	FILTER_COMM,
 	FILTER_CPU,
 	FILTER_STACKTRACE,

include/linux/tracefs.h

@@ -21,6 +21,29 @@ struct file_operations;
 
 #ifdef CONFIG_TRACING
 
+struct eventfs_file;
+
+struct dentry *eventfs_create_events_dir(const char *name,
+					 struct dentry *parent);
+
+struct eventfs_file *eventfs_add_subsystem_dir(const char *name,
+					       struct dentry *parent);
+
+struct eventfs_file *eventfs_add_dir(const char *name,
+				     struct eventfs_file *ef_parent);
+
+int eventfs_add_file(const char *name, umode_t mode,
+		     struct eventfs_file *ef_parent, void *data,
+		     const struct file_operations *fops);
+
+int eventfs_add_events_file(const char *name, umode_t mode,
+			 struct dentry *parent, void *data,
+			 const struct file_operations *fops);
+
+void eventfs_remove(struct eventfs_file *ef);
+
+void eventfs_remove_events_dir(struct dentry *dentry);
+
 struct dentry *tracefs_create_file(const char *name, umode_t mode,
 				   struct dentry *parent, void *data,
 				   const struct file_operations *fops);

kernel/trace/ring_buffer.c

@@ -692,10 +692,7 @@ static void rb_time_set(rb_time_t *t, u64 val)
 static inline bool
 rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set)
 {
-	unsigned long ret;
-
-	ret = local_cmpxchg(l, expect, set);
-	return ret == expect;
+	return local_try_cmpxchg(l, &expect, set);
 }
 
 static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
@@ -752,9 +749,7 @@ static void rb_time_set(rb_time_t *t, u64 val)
 
 static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
 {
-	u64 val;
-	val = local64_cmpxchg(&t->time, expect, set);
-	return val == expect;
+	return local64_try_cmpxchg(&t->time, &expect, set);
 }
 #endif
 
@@ -1494,14 +1489,11 @@ static bool rb_head_page_replace(struct buffer_page *old,
 {
 	unsigned long *ptr = (unsigned long *)&old->list.prev->next;
 	unsigned long val;
-	unsigned long ret;
 
 	val = *ptr & ~RB_FLAG_MASK;
 	val |= RB_PAGE_HEAD;
 
-	ret = cmpxchg(ptr, val, (unsigned long)&new->list);
-
-	return ret == val;
+	return try_cmpxchg(ptr, &val, (unsigned long)&new->list);
 }
 
 /*
@@ -3003,7 +2995,6 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 {
 	unsigned long new_index, old_index;
 	struct buffer_page *bpage;
-	unsigned long index;
 	unsigned long addr;
 	u64 write_stamp;
 	u64 delta;
@@ -3060,8 +3051,9 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 		 */
 		old_index += write_mask;
 		new_index += write_mask;
-		index = local_cmpxchg(&bpage->write, old_index, new_index);
-		if (index == old_index) {
+
+		/* caution: old_index gets updated on cmpxchg failure */
+		if (local_try_cmpxchg(&bpage->write, &old_index, new_index)) {
 			/* update counters */
 			local_sub(event_length, &cpu_buffer->entries_bytes);
 			return true;

kernel/trace/trace.c

@@ -3119,7 +3119,6 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer,
 	struct ftrace_stack *fstack;
 	struct stack_entry *entry;
 	int stackidx;
-	void *ptr;
 
 	/*
 	 * Add one, for this function and the call to save_stack_trace()
@@ -3157,32 +3156,16 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer,
 		nr_entries = stack_trace_save(fstack->calls, size, skip);
 	}
 
-	size = nr_entries * sizeof(unsigned long);
 	event = __trace_buffer_lock_reserve(buffer, TRACE_STACK,
-				    (sizeof(*entry) - sizeof(entry->caller)) + size,
+				    struct_size(entry, caller, nr_entries),
 				    trace_ctx);
 	if (!event)
 		goto out;
-	ptr = ring_buffer_event_data(event);
-	entry = ptr;
-
-	/*
-	 * For backward compatibility reasons, the entry->caller is an
-	 * array of 8 slots to store the stack. This is also exported
-	 * to user space. The amount allocated on the ring buffer actually
-	 * holds enough for the stack specified by nr_entries. This will
-	 * go into the location of entry->caller. Due to string fortifiers
-	 * checking the size of the destination of memcpy() it triggers
-	 * when it detects that size is greater than 8. To hide this from
-	 * the fortifiers, we use "ptr" and pointer arithmetic to assign caller.
-	 *
-	 * The below is really just:
-	 *   memcpy(&entry->caller, fstack->calls, size);
-	 */
-	ptr += offsetof(typeof(*entry), caller);
-	memcpy(ptr, fstack->calls, size);
+	entry = ring_buffer_event_data(event);
 
 	entry->size = nr_entries;
+	memcpy(&entry->caller, fstack->calls,
+	       flex_array_size(entry, caller, nr_entries));
 
 	if (!call_filter_check_discard(call, entry, buffer, event))
 		__buffer_unlock_commit(buffer, event);
@@ -4206,18 +4189,12 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 	loff_t l = 0;
 	int cpu;
 
-	/*
-	 * copy the tracer to avoid using a global lock all around.
-	 * iter->trace is a copy of current_trace, the pointer to the
-	 * name may be used instead of a strcmp(), as iter->trace->name
-	 * will point to the same string as current_trace->name.
-	 */
 	mutex_lock(&trace_types_lock);
-	if (unlikely(tr->current_trace && iter->trace->name != tr->current_trace->name)) {
+	if (unlikely(tr->current_trace != iter->trace)) {
 		/* Close iter->trace before switching to the new current tracer */
 		if (iter->trace->close)
 			iter->trace->close(iter);
-		*iter->trace = *tr->current_trace;
+		iter->trace = tr->current_trace;
 		/* Reopen the new current tracer */
 		if (iter->trace->open)
 			iter->trace->open(iter);
@@ -4829,6 +4806,25 @@ static const struct seq_operations tracer_seq_ops = {
 	.show		= s_show,
 };
 
+/*
+ * Note, as iter itself can be allocated and freed in different
+ * ways, this function is only used to free its content, and not
+ * the iterator itself. The only requirement to all the allocations
+ * is that it must zero all fields (kzalloc), as freeing works with
+ * ethier allocated content or NULL.
+ */
+static void free_trace_iter_content(struct trace_iterator *iter)
+{
+	/* The fmt is either NULL, allocated or points to static_fmt_buf */
+	if (iter->fmt != static_fmt_buf)
+		kfree(iter->fmt);
+
+	kfree(iter->temp);
+	kfree(iter->buffer_iter);
+	mutex_destroy(&iter->mutex);
+	free_cpumask_var(iter->started);
+}
+
 static struct trace_iterator *
 __tracing_open(struct inode *inode, struct file *file, bool snapshot)
 {
@@ -4870,16 +4866,8 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
 	iter->fmt = NULL;
 	iter->fmt_size = 0;
 
-	/*
-	 * We make a copy of the current tracer to avoid concurrent
-	 * changes on it while we are reading.
-	 */
 	mutex_lock(&trace_types_lock);
-	iter->trace = kzalloc(sizeof(*iter->trace), GFP_KERNEL);
-	if (!iter->trace)
-		goto fail;
-
-	*iter->trace = *tr->current_trace;
+	iter->trace = tr->current_trace;
 
 	if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL))
 		goto fail;
@@ -4944,9 +4932,7 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
 
  fail:
 	mutex_unlock(&trace_types_lock);
-	kfree(iter->trace);
-	kfree(iter->temp);
-	kfree(iter->buffer_iter);
+	free_trace_iter_content(iter);
 release:
 	seq_release_private(inode, file);
 	return ERR_PTR(-ENOMEM);
@@ -5025,12 +5011,7 @@ static int tracing_release(struct inode *inode, struct file *file)
 
 	mutex_unlock(&trace_types_lock);
 
-	mutex_destroy(&iter->mutex);
-	free_cpumask_var(iter->started);
-	kfree(iter->fmt);
-	kfree(iter->temp);
-	kfree(iter->trace);
-	kfree(iter->buffer_iter);
+	free_trace_iter_content(iter);
 	seq_release_private(inode, file);
 
 	return 0;
@@ -6318,6 +6299,15 @@ static void set_buffer_entries(struct array_buffer *buf, unsigned long val)
 		per_cpu_ptr(buf->data, cpu)->entries = val;
 }
 
+static void update_buffer_entries(struct array_buffer *buf, int cpu)
+{
+	if (cpu == RING_BUFFER_ALL_CPUS) {
+		set_buffer_entries(buf, ring_buffer_size(buf->buffer, 0));
+	} else {
+		per_cpu_ptr(buf->data, cpu)->entries = ring_buffer_size(buf->buffer, cpu);
+	}
+}
+
 #ifdef CONFIG_TRACER_MAX_TRACE
 /* resize @tr's buffer to the size of @size_tr's entries */
 static int resize_buffer_duplicate_size(struct array_buffer *trace_buf,
@@ -6396,18 +6386,12 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr,
 		return ret;
 	}
 
-	if (cpu == RING_BUFFER_ALL_CPUS)
-		set_buffer_entries(&tr->max_buffer, size);
-	else
-		per_cpu_ptr(tr->max_buffer.data, cpu)->entries = size;
+	update_buffer_entries(&tr->max_buffer, cpu);
 
  out:
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
-	if (cpu == RING_BUFFER_ALL_CPUS)
-		set_buffer_entries(&tr->array_buffer, size);
-	else
-		per_cpu_ptr(tr->array_buffer.data, cpu)->entries = size;
+	update_buffer_entries(&tr->array_buffer, cpu);
 
 	return ret;
 }
@@ -6825,10 +6809,7 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
 	close_pipe_on_cpu(tr, iter->cpu_file);
 	mutex_unlock(&trace_types_lock);
 
-	free_cpumask_var(iter->started);
-	kfree(iter->fmt);
-	kfree(iter->temp);
-	mutex_destroy(&iter->mutex);
+	free_trace_iter_content(iter);
 	kfree(iter);
 
 	trace_array_put(tr);

kernel/trace/trace.h

@@ -77,6 +77,16 @@ enum trace_type {
 #undef __array
 #define __array(type, item, size)	type	item[size];
 
+/*
+ * For backward compatibility, older user space expects to see the
+ * kernel_stack event with a fixed size caller field. But today the fix
+ * size is ignored by the kernel, and the real structure is dynamic.
+ * Expose to user space: "unsigned long caller[8];" but the real structure
+ * will be "unsigned long caller[] __counted_by(size)"
+ */
+#undef __stack_array
+#define __stack_array(type, item, size, field)		type item[] __counted_by(field);
+
 #undef __array_desc
 #define __array_desc(type, container, item, size)
 
@@ -596,7 +606,6 @@ trace_buffer_iter(struct trace_iterator *iter, int cpu)
 int tracer_init(struct tracer *t, struct trace_array *tr);
 int tracing_is_enabled(void);
 void tracing_reset_online_cpus(struct array_buffer *buf);
-void tracing_reset_current(int cpu);
 void tracing_reset_all_online_cpus(void);
 void tracing_reset_all_online_cpus_unlocked(void);
 int tracing_open_generic(struct inode *inode, struct file *filp);
@@ -697,7 +706,6 @@ void trace_filter_add_remove_task(struct trace_pid_list *pid_list,
 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);
@@ -1334,7 +1342,7 @@ struct trace_subsystem_dir {
 	struct list_head		list;
 	struct event_subsystem		*subsystem;
 	struct trace_array		*tr;
-	struct dentry			*entry;
+	struct eventfs_file             *ef;
 	int				ref_count;
 	int				nr_events;
 };

kernel/trace/trace_entries.h

@@ -190,7 +190,7 @@ FTRACE_ENTRY(kernel_stack, stack_entry,
 
 	F_STRUCT(
 		__field(	int,		size	)
-		__array(	unsigned long,	caller,	FTRACE_STACK_ENTRIES	)
+		__stack_array(	unsigned long,	caller,	FTRACE_STACK_ENTRIES, size)
 	),
 
 	F_printk("\t=> %ps\n\t=> %ps\n\t=> %ps\n"

kernel/trace/trace_events.c

@@ -984,7 +984,7 @@ static void remove_subsystem(struct trace_subsystem_dir *dir)
 		return;
 
 	if (!--dir->nr_events) {
-		tracefs_remove(dir->entry);
+		eventfs_remove(dir->ef);
 		list_del(&dir->list);
 		__put_system_dir(dir);
 	}
@@ -1005,7 +1005,7 @@ static void remove_event_file_dir(struct trace_event_file *file)
 
 		tracefs_remove(dir);
 	}
-
+	eventfs_remove(file->ef);
 	list_del(&file->list);
 	remove_subsystem(file->system);
 	free_event_filter(file->filter);
@@ -2291,13 +2291,13 @@ create_new_subsystem(const char *name)
 	return NULL;
 }
 
-static struct dentry *
+static struct eventfs_file *
 event_subsystem_dir(struct trace_array *tr, const char *name,
 		    struct trace_event_file *file, struct dentry *parent)
 {
 	struct event_subsystem *system, *iter;
 	struct trace_subsystem_dir *dir;
-	struct dentry *entry;
+	int res;
 
 	/* First see if we did not already create this dir */
 	list_for_each_entry(dir, &tr->systems, list) {
@@ -2305,7 +2305,7 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
 		if (strcmp(system->name, name) == 0) {
 			dir->nr_events++;
 			file->system = dir;
-			return dir->entry;
+			return dir->ef;
 		}
 	}
 
@@ -2329,8 +2329,8 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
 	} else
 		__get_system(system);
 
-	dir->entry = tracefs_create_dir(name, parent);
-	if (!dir->entry) {
+	dir->ef = eventfs_add_subsystem_dir(name, parent);
+	if (IS_ERR(dir->ef)) {
 		pr_warn("Failed to create system directory %s\n", name);
 		__put_system(system);
 		goto out_free;
@@ -2345,22 +2345,22 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
 	/* the ftrace system is special, do not create enable or filter files */
 	if (strcmp(name, "ftrace") != 0) {
 
-		entry = tracefs_create_file("filter", TRACE_MODE_WRITE,
-					    dir->entry, dir,
+		res = eventfs_add_file("filter", TRACE_MODE_WRITE,
+					    dir->ef, dir,
 					    &ftrace_subsystem_filter_fops);
-		if (!entry) {
+		if (res) {
 			kfree(system->filter);
 			system->filter = NULL;
 			pr_warn("Could not create tracefs '%s/filter' entry\n", name);
 		}
 
-		trace_create_file("enable", TRACE_MODE_WRITE, dir->entry, dir,
+		eventfs_add_file("enable", TRACE_MODE_WRITE, dir->ef, dir,
 				  &ftrace_system_enable_fops);
 	}
 
 	list_add(&dir->list, &tr->systems);
 
-	return dir->entry;
+	return dir->ef;
 
  out_free:
 	kfree(dir);
@@ -2413,36 +2413,37 @@ static int
 event_create_dir(struct dentry *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 dentry *d_events;
 	const char *name;
 	int ret;
 
 	/*
 	 * If the trace point header did not define TRACE_SYSTEM
-	 * then the system would be called "TRACE_SYSTEM".
+	 * then the system would be called "TRACE_SYSTEM". This should
+	 * never happen.
 	 */
-	if (strcmp(call->class->system, TRACE_SYSTEM) != 0) {
-		d_events = event_subsystem_dir(tr, call->class->system, file, parent);
-		if (!d_events)
-			return -ENOMEM;
-	} else
-		d_events = parent;
+	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)
+		return -ENOMEM;
 
 	name = trace_event_name(call);
-	file->dir = tracefs_create_dir(name, d_events);
-	if (!file->dir) {
+	file->ef = eventfs_add_dir(name, ef_subsystem);
+	if (IS_ERR(file->ef)) {
 		pr_warn("Could not create tracefs '%s' directory\n", name);
 		return -1;
 	}
 
 	if (call->class->reg && !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
-		trace_create_file("enable", TRACE_MODE_WRITE, file->dir, file,
+		eventfs_add_file("enable", TRACE_MODE_WRITE, file->ef, file,
 				  &ftrace_enable_fops);
 
 #ifdef CONFIG_PERF_EVENTS
 	if (call->event.type && call->class->reg)
-		trace_create_file("id", TRACE_MODE_READ, file->dir,
+		eventfs_add_file("id", TRACE_MODE_READ, file->ef,
 				  (void *)(long)call->event.type,
 				  &ftrace_event_id_fops);
 #endif
@@ -2458,27 +2459,27 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file)
 	 * triggers or filters.
 	 */
 	if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) {
-		trace_create_file("filter", TRACE_MODE_WRITE, file->dir,
+		eventfs_add_file("filter", TRACE_MODE_WRITE, file->ef,
 				  file, &ftrace_event_filter_fops);
 
-		trace_create_file("trigger", TRACE_MODE_WRITE, file->dir,
+		eventfs_add_file("trigger", TRACE_MODE_WRITE, file->ef,
 				  file, &event_trigger_fops);
 	}
 
 #ifdef CONFIG_HIST_TRIGGERS
-	trace_create_file("hist", TRACE_MODE_READ, file->dir, file,
+	eventfs_add_file("hist", TRACE_MODE_READ, file->ef, file,
 			  &event_hist_fops);
 #endif
 #ifdef CONFIG_HIST_TRIGGERS_DEBUG
-	trace_create_file("hist_debug", TRACE_MODE_READ, file->dir, file,
+	eventfs_add_file("hist_debug", TRACE_MODE_READ, file->ef, file,
 			  &event_hist_debug_fops);
 #endif
-	trace_create_file("format", TRACE_MODE_READ, file->dir, call,
+	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)
-		trace_create_file("inject", 0200, file->dir, file,
+		eventfs_add_file("inject", 0200, file->ef, file,
 				  &event_inject_fops);
 #endif
 
@@ -3631,21 +3632,22 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
 {
 	struct dentry *d_events;
 	struct dentry *entry;
+	int error = 0;
 
 	entry = trace_create_file("set_event", TRACE_MODE_WRITE, parent,
 				  tr, &ftrace_set_event_fops);
 	if (!entry)
 		return -ENOMEM;
 
-	d_events = tracefs_create_dir("events", parent);
-	if (!d_events) {
+	d_events = eventfs_create_events_dir("events", parent);
+	if (IS_ERR(d_events)) {
 		pr_warn("Could not create tracefs 'events' directory\n");
 		return -ENOMEM;
 	}
 
-	entry = trace_create_file("enable", TRACE_MODE_WRITE, d_events,
+	error = eventfs_add_events_file("enable", TRACE_MODE_WRITE, d_events,
 				  tr, &ftrace_tr_enable_fops);
-	if (!entry)
+	if (error)
 		return -ENOMEM;
 
 	/* There are not as crucial, just warn if they are not created */
@@ -3658,11 +3660,11 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
 			  &ftrace_set_event_notrace_pid_fops);
 
 	/* ring buffer internal formats */
-	trace_create_file("header_page", TRACE_MODE_READ, d_events,
+	eventfs_add_events_file("header_page", TRACE_MODE_READ, d_events,
 				  ring_buffer_print_page_header,
 				  &ftrace_show_header_fops);
 
-	trace_create_file("header_event", TRACE_MODE_READ, d_events,
+	eventfs_add_events_file("header_event", TRACE_MODE_READ, d_events,
 				  ring_buffer_print_entry_header,
 				  &ftrace_show_header_fops);
 
@@ -3750,7 +3752,7 @@ int event_trace_del_tracer(struct trace_array *tr)
 
 	down_write(&trace_event_sem);
 	__trace_remove_event_dirs(tr);
-	tracefs_remove(tr->event_dir);
+	eventfs_remove_events_dir(tr->event_dir);
 	up_write(&trace_event_sem);
 
 	tr->event_dir = NULL;

kernel/trace/trace_events_user.c

@@ -1328,14 +1328,14 @@ static int user_field_set_string(struct ftrace_event_field *field,
 
 static int user_event_set_print_fmt(struct user_event *user, char *buf, int len)
 {
-	struct ftrace_event_field *field, *next;
+	struct ftrace_event_field *field;
 	struct list_head *head = &user->fields;
 	int pos = 0, depth = 0;
 	const char *str_func;
 
 	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
 
-	list_for_each_entry_safe_reverse(field, next, head, link) {
+	list_for_each_entry_reverse(field, head, link) {
 		if (depth != 0)
 			pos += snprintf(buf + pos, LEN_OR_ZERO, " ");
 
@@ -1347,7 +1347,7 @@ static int user_event_set_print_fmt(struct user_event *user, char *buf, int len)
 
 	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
 
-	list_for_each_entry_safe_reverse(field, next, head, link) {
+	list_for_each_entry_reverse(field, head, link) {
 		if (user_field_is_dyn_string(field->type, &str_func))
 			pos += snprintf(buf + pos, LEN_OR_ZERO,
 					", %s(%s)", str_func, field->name);
@@ -1732,7 +1732,7 @@ static int user_event_create(const char *raw_command)
 static int user_event_show(struct seq_file *m, struct dyn_event *ev)
 {
 	struct user_event *user = container_of(ev, struct user_event, devent);
-	struct ftrace_event_field *field, *next;
+	struct ftrace_event_field *field;
 	struct list_head *head;
 	int depth = 0;
 
@@ -1740,7 +1740,7 @@ static int user_event_show(struct seq_file *m, struct dyn_event *ev)
 
 	head = trace_get_fields(&user->call);
 
-	list_for_each_entry_safe_reverse(field, next, head, link) {
+	list_for_each_entry_reverse(field, head, link) {
 		if (depth == 0)
 			seq_puts(m, " ");
 		else
@@ -1816,13 +1816,14 @@ static bool user_field_match(struct ftrace_event_field *field, int argc,
 static bool user_fields_match(struct user_event *user, int argc,
 			      const char **argv)
 {
-	struct ftrace_event_field *field, *next;
+	struct ftrace_event_field *field;
 	struct list_head *head = &user->fields;
 	int i = 0;
 
-	list_for_each_entry_safe_reverse(field, next, head, link)
+	list_for_each_entry_reverse(field, head, link) {
 		if (!user_field_match(field, argc, argv, &i))
 			return false;
+	}
 
 	if (i != argc)
 		return false;

kernel/trace/trace_export.c

@@ -51,6 +51,9 @@ static int ftrace_event_register(struct trace_event_call *call,
 #undef __array
 #define __array(type, item, size)			type item[size];
 
+#undef __stack_array
+#define __stack_array(type, item, size, field)		__array(type, item, size)
+
 #undef __array_desc
 #define __array_desc(type, container, item, size)	type item[size];
 
@@ -114,6 +117,9 @@ static void __always_unused ____ftrace_check_##name(void)		\
 	is_signed_type(_type), .filter_type = FILTER_OTHER,			\
 	.len = _len },
 
+#undef __stack_array
+#define __stack_array(_type, _item, _len, _field) __array(_type, _item, _len)
+
 #undef __array_desc
 #define __array_desc(_type, _container, _item, _len) __array(_type, _item, _len)
 
@@ -149,6 +155,9 @@ static struct trace_event_fields ftrace_event_fields_##name[] = {	\
 #undef __array
 #define __array(type, item, len)
 
+#undef __stack_array
+#define __stack_array(type, item, len, field)
+
 #undef __array_desc
 #define __array_desc(type, container, item, len)
 

tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_char.tc

@@ -34,14 +34,19 @@ mips*)
 esac
 
 : "Test get argument (1)"
-echo "p:testprobe tracefs_create_dir arg1=+0(${ARG1}):char" > kprobe_events
+if grep -q eventfs_add_dir available_filter_functions; then
+  DIR_NAME="eventfs_add_dir"
+else
+  DIR_NAME="tracefs_create_dir"
+fi
+echo "p:testprobe ${DIR_NAME} arg1=+0(${ARG1}):char" > kprobe_events
 echo 1 > events/kprobes/testprobe/enable
 echo "p:test $FUNCTION_FORK" >> kprobe_events
 grep -qe "testprobe.* arg1='t'" trace
 
 echo 0 > events/kprobes/testprobe/enable
 : "Test get argument (2)"
-echo "p:testprobe tracefs_create_dir arg1=+0(${ARG1}):char arg2=+0(${ARG1}):char[4]" > kprobe_events
+echo "p:testprobe ${DIR_NAME} arg1=+0(${ARG1}):char arg2=+0(${ARG1}):char[4]" > kprobe_events
 echo 1 > events/kprobes/testprobe/enable
 echo "p:test $FUNCTION_FORK" >> kprobe_events
 grep -qe "testprobe.* arg1='t' arg2={'t','e','s','t'}" trace

tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc

@@ -37,14 +37,19 @@ loongarch*)
 esac
 
 : "Test get argument (1)"
-echo "p:testprobe tracefs_create_dir arg1=+0(${ARG1}):string" > kprobe_events
+if grep -q eventfs_add_dir available_filter_functions; then
+  DIR_NAME="eventfs_add_dir"
+else
+  DIR_NAME="tracefs_create_dir"
+fi
+echo "p:testprobe ${DIR_NAME} arg1=+0(${ARG1}):string" > kprobe_events
 echo 1 > events/kprobes/testprobe/enable
 echo "p:test $FUNCTION_FORK" >> kprobe_events
 grep -qe "testprobe.* arg1=\"test\"" trace
 
 echo 0 > events/kprobes/testprobe/enable
 : "Test get argument (2)"
-echo "p:testprobe tracefs_create_dir arg1=+0(${ARG1}):string arg2=+0(${ARG1}):string" > kprobe_events
+echo "p:testprobe ${DIR_NAME} arg1=+0(${ARG1}):string arg2=+0(${ARG1}):string" > kprobe_events
 echo 1 > events/kprobes/testprobe/enable
 echo "p:test $FUNCTION_FORK" >> kprobe_events
 grep -qe "testprobe.* arg1=\"test\" arg2=\"test\"" trace