From: "Steven Rostedt (Google)" rostedt@goodmis.org

The creation of the trace event directory requires that a TRACE_SYSTEM is defined that the trace event directory is added within the system it was defined in.

The code handled the case where a TRACE_SYSTEM was not added, and would then add the event at the events directory. But nothing should be doing this. This code also prevents the implementation of creating dynamic dentrys for the eventfs system.

As this path has never been hit on correct code, remove it. If it does get hit, issues a WARN_ON_ONCE() and return ENODEV.

Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Ajay Kaher akaher@vmware.com --- kernel/trace/trace_events.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 5d6ae4eae510..a284171d5c74 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2426,14 +2426,15 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file)

/* * 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; + + d_events = event_subsystem_dir(tr, call->class->system, file, parent); + if (!d_events) + return -ENOMEM;

name = trace_event_name(call); file->dir = tracefs_create_dir(name, d_events);

Add eventfs_file structure which will hold the properties of the eventfs files and directories.

Add following functions to create the directories in eventfs:

eventfs_create_events_dir() will create the top level "events" directory within the tracefs file system.

eventfs_add_subsystem_dir() creates an eventfs_file descriptor with the given name of the subsystem.

eventfs_add_dir() creates an eventfs_file descriptor with the given name of the directory and attached to a eventfs_file of a subsystem.

Add tracefs_inode structure to hold the inodes, flags and pointers to private data used by eventfs.

Signed-off-by: Ajay Kaher akaher@vmware.com Co-developed-by: Steven Rostedt (VMware) rostedt@goodmis.org Signed-off-by: Steven Rostedt (VMware) rostedt@goodmis.org Tested-by: Ching-lin Yu chinglinyu@google.com Reported-by: kernel test robot lkp@intel.com Closes: https://lore.kernel.org/oe-lkp/202305051619.9a469a9a-yujie.liu@intel.com --- fs/tracefs/Makefile | 1 + fs/tracefs/event_inode.c | 211 +++++++++++++++++++++++++++++++++++++++ include/linux/tracefs.h | 11 ++ 3 files changed, 223 insertions(+) create mode 100644 fs/tracefs/event_inode.c

diff --git a/fs/tracefs/Makefile b/fs/tracefs/Makefile index 7c35a282b484..73c56da8e284 100644 --- a/fs/tracefs/Makefile +++ b/fs/tracefs/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only tracefs-objs := inode.o +tracefs-objs += event_inode.o

obj-$(CONFIG_TRACING) += tracefs.o

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c new file mode 100644 index 000000000000..8f334b122e46 --- /dev/null +++ b/fs/tracefs/event_inode.c @@ -0,0 +1,211 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * event_inode.c - part of tracefs, a pseudo file system for activating tracing + * + * Copyright (C) 2020-23 VMware Inc, author: Steven Rostedt (VMware) rostedt@goodmis.org + * Copyright (C) 2020-23 VMware Inc, author: Ajay Kaher akaher@vmware.com + * + * eventfs is used to dynamically create inodes and dentries based on the + * meta data provided by the tracing system. + * + * eventfs stores the meta-data of files/dirs and holds off on creating + * inodes/dentries of the files. When accessed, the eventfs will create the + * inodes/dentries in a just-in-time (JIT) manner. The eventfs will clean up + * and delete the inodes/dentries when they are no longer referenced. + */ +#include <linux/fsnotify.h> +#include <linux/fs.h> +#include <linux/namei.h> +#include <linux/workqueue.h> +#include <linux/security.h> +#include <linux/tracefs.h> +#include <linux/kref.h> +#include <linux/delay.h> +#include "internal.h" + +struct eventfs_inode { + struct list_head e_top_files; +}; + +/** + * struct eventfs_file - hold the properties of the eventfs files and + * directories. + * @name: the name of the file or directory to create + * @list: file or directory to be added to parent directory + * @ei: list of files and directories within directory + * @fop: file_operations for file or directory + * @iop: inode_operations for file or directory + * @data: something that the caller will want to get to later on + * @mode: the permission that the file or directory should have + */ +struct eventfs_file { + const char *name; + struct list_head list; + struct eventfs_inode *ei; + const struct file_operations *fop; + const struct inode_operations *iop; + void *data; + umode_t mode; +}; + +static DEFINE_MUTEX(eventfs_mutex); + +static const struct inode_operations eventfs_root_dir_inode_operations = { +}; + +static const struct file_operations eventfs_file_operations = { +}; + +/** + * eventfs_prepare_ef - helper function to prepare eventfs_file + * @name: the name of the file/directory to create. + * @mode: the permission that the file should have. + * @fop: struct file_operations that should be used for this file/directory. + * @iop: struct inode_operations that should be used for this file/directory. + * @data: something that the caller will want to get to later on. The + * inode.i_private pointer will point to this value on the open() call. + * + * This function allocates and fills the eventfs_file structure. + */ +static struct eventfs_file *eventfs_prepare_ef(const char *name, umode_t mode, + const struct file_operations *fop, + const struct inode_operations *iop, + void *data) +{ + struct eventfs_file *ef; + + ef = kzalloc(sizeof(*ef), GFP_KERNEL); + if (!ef) + return ERR_PTR(-ENOMEM); + + ef->name = kstrdup(name, GFP_KERNEL); + if (!ef->name) { + kfree(ef); + return ERR_PTR(-ENOMEM); + } + + if (S_ISDIR(mode)) { + ef->ei = kzalloc(sizeof(*ef->ei), GFP_KERNEL); + if (!ef->ei) { + kfree(ef->name); + kfree(ef); + return ERR_PTR(-ENOMEM); + } + INIT_LIST_HEAD(&ef->ei->e_top_files); + } else { + ef->ei = NULL; + } + + ef->iop = iop; + ef->fop = fop; + ef->mode = mode; + ef->data = data; + return ef; +} + +/** + * eventfs_create_events_dir - create the trace event structure + * @name: the name of the directory to create. + * @parent: parent dentry for this file. This should be a directory dentry + * if set. If this parameter is NULL, then the directory will be + * created in the root of the tracefs filesystem. + * + * This function creates the top of the trace event directory. + */ +struct dentry *eventfs_create_events_dir(const char *name, + struct dentry *parent) +{ + struct dentry *dentry = tracefs_start_creating(name, parent); + struct eventfs_inode *ei; + struct tracefs_inode *ti; + struct inode *inode; + + if (IS_ERR(dentry)) + return dentry; + + ei = kzalloc(sizeof(*ei), GFP_KERNEL); + if (!ei) + return ERR_PTR(-ENOMEM); + inode = tracefs_get_inode(dentry->d_sb); + if (unlikely(!inode)) { + kfree(ei); + tracefs_failed_creating(dentry); + return ERR_PTR(-ENOMEM); + } + + INIT_LIST_HEAD(&ei->e_top_files); + + ti = get_tracefs(inode); + ti->flags |= TRACEFS_EVENT_INODE; + ti->private = ei; + + inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; + inode->i_op = &eventfs_root_dir_inode_operations; + inode->i_fop = &eventfs_file_operations; + + /* directory inodes start off with i_nlink == 2 (for "." entry) */ + inc_nlink(inode); + d_instantiate(dentry, inode); + inc_nlink(dentry->d_parent->d_inode); + fsnotify_mkdir(dentry->d_parent->d_inode, dentry); + return tracefs_end_creating(dentry); +} + +/** + * eventfs_add_subsystem_dir - add eventfs subsystem_dir to list to create later + * @name: the name of the file to create. + * @parent: parent dentry for this dir. + * + * This function adds eventfs subsystem dir to list. + * And all these dirs are created on the fly when they are looked up, + * and the dentry and inodes will be removed when they are done. + */ +struct eventfs_file *eventfs_add_subsystem_dir(const char *name, + struct dentry *parent) +{ + struct tracefs_inode *ti_parent; + struct eventfs_inode *ei_parent; + struct eventfs_file *ef; + + if (!parent) + return ERR_PTR(-EINVAL); + + ti_parent = get_tracefs(parent->d_inode); + ei_parent = ti_parent->private; + + ef = eventfs_prepare_ef(name, S_IFDIR, NULL, NULL, NULL); + if (IS_ERR(ef)) + return ef; + + mutex_lock(&eventfs_mutex); + list_add_tail(&ef->list, &ei_parent->e_top_files); + mutex_unlock(&eventfs_mutex); + return ef; +} + +/** + * eventfs_add_dir - add eventfs dir to list to create later + * @name: the name of the file to create. + * @ef_parent: parent eventfs_file for this dir. + * + * This function adds eventfs dir to list. + * And all these dirs are created on the fly when they are looked up, + * and the dentry and inodes will be removed when they are done. + */ +struct eventfs_file *eventfs_add_dir(const char *name, + struct eventfs_file *ef_parent) +{ + struct eventfs_file *ef; + + if (!ef_parent) + return ERR_PTR(-EINVAL); + + ef = eventfs_prepare_ef(name, S_IFDIR, NULL, NULL, NULL); + if (IS_ERR(ef)) + return ef; + + mutex_lock(&eventfs_mutex); + list_add_tail(&ef->list, &ef_parent->ei->e_top_files); + mutex_unlock(&eventfs_mutex); + return ef; +} diff --git a/include/linux/tracefs.h b/include/linux/tracefs.h index 99912445974c..432e5e6f7901 100644 --- a/include/linux/tracefs.h +++ b/include/linux/tracefs.h @@ -21,6 +21,17 @@ 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); + struct dentry *tracefs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops);

Add the inode_operations, file_operations, and helper functions to eventfs: dcache_dir_open_wrapper() eventfs_root_lookup() eventfs_release() eventfs_set_ef_status_free() eventfs_post_create_dir()

The inode_operations and file_operations functions will be called from the VFS layer.

Signed-off-by: Ajay Kaher akaher@vmware.com Co-developed-by: Steven Rostedt (VMware) rostedt@goodmis.org Signed-off-by: Steven Rostedt (VMware) rostedt@goodmis.org Tested-by: Ching-lin Yu chinglinyu@google.com --- fs/tracefs/event_inode.c | 312 +++++++++++++++++++++++++++++++++++++++ fs/tracefs/internal.h | 2 + 2 files changed, 314 insertions(+)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 9e4843be9dc9..a3c1b8bf7192 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -31,6 +31,8 @@ struct eventfs_inode { * struct eventfs_file - hold the properties of the eventfs files and * directories. * @name: the name of the file or directory to create + * @d_parent: holds parent's dentry + * @dentry: once accessed holds dentry * @list: file or directory to be added to parent directory * @ei: list of files and directories within directory * @fop: file_operations for file or directory @@ -40,22 +42,328 @@ struct eventfs_inode { */ struct eventfs_file { const char *name; + struct dentry *d_parent; + struct dentry *dentry; struct list_head list; struct eventfs_inode *ei; const struct file_operations *fop; const struct inode_operations *iop; + union { + struct list_head del_list; /* list of eventfs_file to delete */ + struct rcu_head rcu; /* eventfs_file to delete */ + unsigned long is_freed; /* Freed if one of the above is set */ + }; void *data; umode_t mode; };

static DEFINE_MUTEX(eventfs_mutex); +DEFINE_STATIC_SRCU(eventfs_srcu); + +static struct dentry *eventfs_root_lookup(struct inode *dir, + struct dentry *dentry, + unsigned int flags); +static int dcache_dir_open_wrapper(struct inode *inode, struct file *file); +static int eventfs_release(struct inode *inode, struct file *file);

static const struct inode_operations eventfs_root_dir_inode_operations = { + .lookup = eventfs_root_lookup, };

static const struct file_operations eventfs_file_operations = { + .open = dcache_dir_open_wrapper, + .read = generic_read_dir, + .iterate_shared = dcache_readdir, + .llseek = generic_file_llseek, + .release = eventfs_release, +}; + +/** + * create_file - create a file in the tracefs filesystem + * @name: the name of the file to create. + * @mode: the permission that the file should have. + * @parent: parent dentry for this file. + * @data: something that the caller will want to get to later on. + * @fop: struct file_operations that should be used for this file. + * + * This is the basic "create a file" function for tracefs. It allows for a + * wide range of flexibility in creating a file. + * + * This function will return a pointer to a dentry if it succeeds. This + * pointer must be passed to the tracefs_remove() function when the file is + * to be removed (no automatic cleanup happens if your module is unloaded, + * you are responsible here.) If an error occurs, %NULL will be returned. + * + * If tracefs is not enabled in the kernel, the value -%ENODEV will be + * returned. + */ +static struct dentry *create_file(const char *name, umode_t mode, + struct dentry *parent, void *data, + const struct file_operations *fop) +{ + return NULL; };

+/** + * create_dir - create a dir in the tracefs filesystem + * @name: the name of the file to create. + * @parent: parent dentry for this file. + * @data: something that the caller will want to get to later on. + * + * This is the basic "create a dir" function for eventfs. It allows for a + * wide range of flexibility in creating a dir. + * + * This function will return a pointer to a dentry if it succeeds. This + * pointer must be passed to the tracefs_remove() function when the file is + * to be removed (no automatic cleanup happens if your module is unloaded, + * you are responsible here.) If an error occurs, %NULL will be returned. + * + * If tracefs is not enabled in the kernel, the value -%ENODEV will be + * returned. + */ +static struct dentry *create_dir(const char *name, struct dentry *parent, void *data) +{ + return NULL; +} + +/** + * eventfs_set_ef_status_free - set the ef->status to free + * @dentry: dentry who's status to be freed + * + * eventfs_set_ef_status_free will be called if no more + * references remain + */ +void eventfs_set_ef_status_free(struct dentry *dentry) +{ + struct tracefs_inode *ti_parent; + struct eventfs_file *ef; + + mutex_lock(&eventfs_mutex); + ti_parent = get_tracefs(dentry->d_parent->d_inode); + if (!ti_parent || !(ti_parent->flags & TRACEFS_EVENT_INODE)) + goto out; + + ef = dentry->d_fsdata; + if (!ef) + goto out; + + /* + * If ef was freed, then the LSB bit is set for d_fsdata. + * But this should not happen, as it should still have a + * ref count that prevents it. Warn in case it does. + */ + if (WARN_ON_ONCE((unsigned long)ef & 1)) + goto out; + + dentry->d_fsdata = NULL; + ef->dentry = NULL; +out: + mutex_unlock(&eventfs_mutex); +} + +/** + * eventfs_post_create_dir - post create dir routine + * @ef: eventfs_file of recently created dir + * + * Map the meta-data of files within an eventfs dir to their parent dentry + */ +static void eventfs_post_create_dir(struct eventfs_file *ef) +{ + struct eventfs_file *ef_child; + struct tracefs_inode *ti; + + /* srcu lock already held */ + /* fill parent-child relation */ + list_for_each_entry_srcu(ef_child, &ef->ei->e_top_files, list, + srcu_read_lock_held(&eventfs_srcu)) { + ef_child->d_parent = ef->dentry; + } + + ti = get_tracefs(ef->dentry->d_inode); + ti->private = ef->ei; +} + +/** + * create_dentry - helper function to create dentry + * @ef: eventfs_file of file or directory to create + * @parent: parent dentry + * @lookup: true if called from lookup routine + * + * Used to create a dentry for file/dir, executes post dentry creation routine + */ +static struct dentry * +create_dentry(struct eventfs_file *ef, struct dentry *parent, bool lookup) +{ + bool invalidate = false; + struct dentry *dentry; + + mutex_lock(&eventfs_mutex); + if (ef->is_freed) { + mutex_unlock(&eventfs_mutex); + return NULL; + } + if (ef->dentry) { + dentry = ef->dentry; + /* On dir open, up the ref count */ + if (!lookup) + dget(dentry); + mutex_unlock(&eventfs_mutex); + return dentry; + } + mutex_unlock(&eventfs_mutex); + + if (!lookup) + inode_lock(parent->d_inode); + + if (ef->ei) + dentry = create_dir(ef->name, parent, ef->data); + else + dentry = create_file(ef->name, ef->mode, parent, + ef->data, ef->fop); + + if (!lookup) + inode_unlock(parent->d_inode); + + mutex_lock(&eventfs_mutex); + if (IS_ERR_OR_NULL(dentry)) { + /* If the ef was already updated get it */ + dentry = ef->dentry; + if (dentry && !lookup) + dget(dentry); + mutex_unlock(&eventfs_mutex); + return dentry; + } + + if (!ef->dentry && !ef->is_freed) { + ef->dentry = dentry; + if (ef->ei) + eventfs_post_create_dir(ef); + dentry->d_fsdata = ef; + } else { + /* A race here, should try again (unless freed) */ + invalidate = true; + } + mutex_unlock(&eventfs_mutex); + if (invalidate) + d_invalidate(dentry); + + if (lookup || invalidate) + dput(dentry); + + return invalidate ? NULL : dentry; +} + +static bool match_event_file(struct eventfs_file *ef, const char *name) +{ + bool ret; + + mutex_lock(&eventfs_mutex); + ret = !ef->is_freed && strcmp(ef->name, name) == 0; + mutex_unlock(&eventfs_mutex); + + return ret; +} + +/** + * eventfs_root_lookup - lookup routine to create file/dir + * @dir: in which a lookup is being done + * @dentry: file/dir dentry + * @flags: to pass as flags parameter to simple lookup + * + * Used to create a dynamic file/dir within @dir. Use the eventfs_inode + * list of meta data to find the information needed to create the file/dir. + */ +static struct dentry *eventfs_root_lookup(struct inode *dir, + struct dentry *dentry, + unsigned int flags) +{ + struct tracefs_inode *ti; + struct eventfs_inode *ei; + struct eventfs_file *ef; + struct dentry *ret = NULL; + int idx; + + ti = get_tracefs(dir); + if (!(ti->flags & TRACEFS_EVENT_INODE)) + return NULL; + + ei = ti->private; + idx = srcu_read_lock(&eventfs_srcu); + list_for_each_entry_srcu(ef, &ei->e_top_files, list, + srcu_read_lock_held(&eventfs_srcu)) { + if (!match_event_file(ef, dentry->d_name.name)) + continue; + ret = simple_lookup(dir, dentry, flags); + create_dentry(ef, ef->d_parent, true); + break; + } + srcu_read_unlock(&eventfs_srcu, idx); + return ret; +} + +/** + * eventfs_release - called to release eventfs file/dir + * @inode: inode to be released + * @file: file to be released (not used) + */ +static int eventfs_release(struct inode *inode, struct file *file) +{ + struct tracefs_inode *ti; + struct eventfs_inode *ei; + struct eventfs_file *ef; + struct dentry *dentry; + int idx; + + ti = get_tracefs(inode); + if (!(ti->flags & TRACEFS_EVENT_INODE)) + return -EINVAL; + + ei = ti->private; + idx = srcu_read_lock(&eventfs_srcu); + list_for_each_entry_srcu(ef, &ei->e_top_files, list, + srcu_read_lock_held(&eventfs_srcu)) { + mutex_lock(&eventfs_mutex); + dentry = ef->dentry; + mutex_unlock(&eventfs_mutex); + if (dentry) + dput(dentry); + } + srcu_read_unlock(&eventfs_srcu, idx); + return dcache_dir_close(inode, file); +} + +/** + * dcache_dir_open_wrapper - eventfs open wrapper + * @inode: not used + * @file: dir to be opened (to create its child) + * + * Used to dynamically create the file/dir within @file. @file is really a + * directory and all the files/dirs of the children within @file will be + * created. If any of the files/dirs have already been created, their + * reference count will be incremented. + */ +static int dcache_dir_open_wrapper(struct inode *inode, struct file *file) +{ + struct tracefs_inode *ti; + struct eventfs_inode *ei; + struct eventfs_file *ef; + struct dentry *dentry = file_dentry(file); + struct inode *f_inode = file_inode(file); + int idx; + + ti = get_tracefs(f_inode); + if (!(ti->flags & TRACEFS_EVENT_INODE)) + return -EINVAL; + + ei = ti->private; + idx = srcu_read_lock(&eventfs_srcu); + list_for_each_entry_rcu(ef, &ei->e_top_files, list) { + create_dentry(ef, dentry, false); + } + srcu_read_unlock(&eventfs_srcu, idx); + return dcache_dir_open(inode, file); +} + /** * eventfs_prepare_ef - helper function to prepare eventfs_file * @name: the name of the file/directory to create. @@ -179,6 +487,7 @@ struct eventfs_file *eventfs_add_subsystem_dir(const char *name,

mutex_lock(&eventfs_mutex); list_add_tail(&ef->list, &ei_parent->e_top_files); + ef->d_parent = parent; mutex_unlock(&eventfs_mutex); return ef; } @@ -206,6 +515,7 @@ struct eventfs_file *eventfs_add_dir(const char *name,

mutex_lock(&eventfs_mutex); list_add_tail(&ef->list, &ef_parent->ei->e_top_files); + ef->d_parent = ef_parent->dentry; mutex_unlock(&eventfs_mutex); return ef; } @@ -254,6 +564,7 @@ int eventfs_add_events_file(const char *name, umode_t mode,

mutex_lock(&eventfs_mutex); list_add_tail(&ef->list, &ei->e_top_files); + ef->d_parent = parent; mutex_unlock(&eventfs_mutex); return 0; } @@ -292,6 +603,7 @@ int eventfs_add_file(const char *name, umode_t mode,

mutex_lock(&eventfs_mutex); list_add_tail(&ef->list, &ef_parent->ei->e_top_files); + ef->d_parent = ef_parent->dentry; mutex_unlock(&eventfs_mutex); return 0; } diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h index f0fd565d59ec..9bfad9d95a4a 100644 --- a/fs/tracefs/internal.h +++ b/fs/tracefs/internal.h @@ -21,4 +21,6 @@ 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); +void eventfs_set_ef_status_free(struct dentry *dentry); + #endif /* _TRACEFS_INTERNAL_H */

Up until now, /sys/kernel/tracing/events was no different than any other part of tracefs. The files and directories within the events directory was created when the tracefs was mounted, and also created for the instances in /sys/kernel/tracing/instances/<instance>/events. Most of these files and directories will never be referenced. Since there are thousands of these files and directories they spend their time wasting precious memory resources.

Move the "events" directory to the new eventfs. The eventfs will take the meta data of the events that they represent and store that. When the files in the events directory are referenced, the dentry and inodes to represent them are then created. When the files are no longer referenced, they are freed. This saves the precious memory resources that were wasted on these seldom referenced dentries and inodes.

Signed-off-by: Ajay Kaher akaher@vmware.com Co-developed-by: Steven Rostedt (VMware) rostedt@goodmis.org Signed-off-by: Steven Rostedt (VMware) rostedt@goodmis.org Tested-by: Ching-lin Yu chinglinyu@google.com --- fs/tracefs/inode.c | 18 ++++++++++ include/linux/trace_events.h | 1 + kernel/trace/trace.h | 2 +- kernel/trace/trace_events.c | 65 ++++++++++++++++++------------------ 4 files changed, 53 insertions(+), 33 deletions(-)

diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index d9273066f25f..bb6de89eb446 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -374,6 +374,23 @@ static const struct super_operations tracefs_super_operations = { .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[] = {{""}}; @@ -396,6 +413,7 @@ 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);

diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 3930e676436c..c17623c78029 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -638,6 +638,7 @@ 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; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index e1edc2197fc8..956938357774 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1324,7 +1324,7 @@ 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; }; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index a284171d5c74..85f9a99bb506 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -990,7 +990,7 @@ 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); } @@ -1011,7 +1011,7 @@ 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); @@ -2297,13 +2297,13 @@ 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) { @@ -2311,7 +2311,7 @@ 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; } }

@@ -2335,8 +2335,8 @@ 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; @@ -2351,22 +2351,22 @@ 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); @@ -2419,8 +2419,8 @@ 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;

@@ -2432,24 +2432,24 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file) if (WARN_ON_ONCE(strcmp(call->class->system, TRACE_SYSTEM) == 0)) return -ENODEV;

- d_events = event_subsystem_dir(tr, call->class->system, file, parent); - if (!d_events) + 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 @@ -2465,27 +2465,27 @@ 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

@@ -3638,21 +3638,22 @@ 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 */ @@ -3665,11 +3666,11 @@ 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);

@@ -3757,7 +3758,7 @@ 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;