Create a kmem cache of tracefs_inodes. To be more efficient, as there are lots of tracefs inodes, create its own cache. This also allows to see how many tracefs inodes have been created.

Add helper functions: tracefs_alloc_inode() tracefs_free_inode() get_tracefs()

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 | 39 +++++++++++++++++++++++++++++++++++++++ fs/tracefs/internal.h | 15 +++++++++++++++ 2 files changed, 54 insertions(+) create mode 100644 fs/tracefs/internal.h

diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 57ac8aa4a724..2508944cc4d8 100644 --- a/fs/tracefs/inode.c +++ b/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) { @@ -346,6 +366,9 @@ 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, @@ -628,10 +651,26 @@ 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; diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h new file mode 100644 index 000000000000..954ea005632b --- /dev/null +++ b/fs/tracefs/internal.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _TRACEFS_INTERNAL_H +#define _TRACEFS_INTERNAL_H + +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); +} +#endif /* _TRACEFS_INTERNAL_H */

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 +++++++++++++++++++++++++++++++++++++++ fs/tracefs/internal.h | 4 + include/linux/tracefs.h | 11 ++ 4 files changed, 227 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/fs/tracefs/internal.h b/fs/tracefs/internal.h index 7dfb7ebc1c3f..f0fd565d59ec 100644 --- a/fs/tracefs/internal.h +++ b/fs/tracefs/internal.h @@ -2,6 +2,10 @@ #ifndef _TRACEFS_INTERNAL_H #define _TRACEFS_INTERNAL_H

+enum { + TRACEFS_EVENT_INODE = BIT(1), +}; + struct tracefs_inode { unsigned long flags; void *private; 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.

create_file() and create_dir() are added as stub functions and will be filled in later.

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 | 304 +++++++++++++++++++++++++++++++++++++++ fs/tracefs/internal.h | 2 + 2 files changed, 306 insertions(+)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 9e4843be9dc9..24d645c61029 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 +42,320 @@ 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; + + 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 +479,7 @@ 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 +507,7 @@ 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 +556,7 @@ 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 +595,7 @@ 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 */

When events are removed from tracefs, the eventfs must be aware of this. The eventfs_remove() removes the meta data from eventfs so that it will no longer create the files associated with that event.

When an instance is removed from tracefs, eventfs_remove_events_dir() will remove and clean up the entire "events" directory.

The helper function eventfs_remove_rec() is used to clean up and free the associated data from eventfs for both of the added functions. SRCU is used to protect the lists of meta data stored in the eventfs. The eventfs_mutex is used to protect the content of the items in the list.

As lookups may be happening as deletions of events are made, the freeing of dentry/inodes and relative information is done after the SRCU grace period has passed.

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-kbuild-all/202305030611.Kas747Ev-lkp@intel.com/ --- fs/tracefs/event_inode.c | 143 +++++++++++++++++++++++++++++++++++++++ include/linux/tracefs.h | 4 ++ 2 files changed, 147 insertions(+)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 5240bd2c81e7..2db7f1028f75 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -198,6 +198,14 @@ void eventfs_set_ef_status_free(struct dentry *dentry) 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: @@ -656,3 +664,138 @@ int eventfs_add_file(const char *name, umode_t mode, mutex_unlock(&eventfs_mutex); return 0; } + +static void free_ef(struct rcu_head *head) +{ + struct eventfs_file *ef = container_of(head, struct eventfs_file, rcu); + + kfree(ef->name); + kfree(ef->ei); + kfree(ef); +} + +/** + * eventfs_remove_rec - remove eventfs dir or file from list + * @ef: eventfs_file to be removed. + * @head: to create list of eventfs_file to be deleted + * @level: to check recursion depth + * + * The helper function eventfs_remove_rec() is used to clean up and free the + * associated data from eventfs for both of the added functions. + */ +static void eventfs_remove_rec(struct eventfs_file *ef, struct list_head *head, int level) +{ + struct eventfs_file *ef_child; + + if (!ef) + return; + /* + * Check recursion depth. It should never be greater than 3: + * 0 - events/ + * 1 - events/group/ + * 2 - events/group/event/ + * 3 - events/group/event/file + */ + if (WARN_ON_ONCE(level > 3)) + return; + + if (ef->ei) { + /* search for nested folders or files */ + list_for_each_entry_srcu(ef_child, &ef->ei->e_top_files, list, + lockdep_is_held(&eventfs_mutex)) { + eventfs_remove_rec(ef_child, head, level + 1); + } + } + + list_del_rcu(&ef->list); + list_add_tail(&ef->del_list, head); +} + +/** + * eventfs_remove - remove eventfs dir or file from list + * @ef: eventfs_file to be removed. + * + * This function acquire the eventfs_mutex lock and call eventfs_remove_rec() + */ +void eventfs_remove(struct eventfs_file *ef) +{ + struct eventfs_file *tmp; + LIST_HEAD(ef_del_list); + struct dentry *dentry_list = NULL; + struct dentry *dentry; + + if (!ef) + return; + + mutex_lock(&eventfs_mutex); + eventfs_remove_rec(ef, &ef_del_list, 0); + list_for_each_entry_safe(ef, tmp, &ef_del_list, del_list) { + if (ef->dentry) { + unsigned long ptr = (unsigned long)dentry_list; + + /* Keep the dentry from being freed yet */ + dget(ef->dentry); + + /* + * Paranoid: The dget() above should prevent the dentry + * from being freed and calling eventfs_set_ef_status_free(). + * But just in case, set the link list LSB pointer to 1 + * and have eventfs_set_ef_status_free() check that to + * make sure that if it does happen, it will not think + * the d_fsdata is an event_file. + * + * For this to work, no event_file should be allocated + * on a odd space, as the ef should always be allocated + * to be at least word aligned. Check for that too. + */ + WARN_ON_ONCE(ptr & 1); + + ef->dentry->d_fsdata = (void *)(ptr | 1); + dentry_list = ef->dentry; + ef->dentry = NULL; + } + call_srcu(&eventfs_srcu, &ef->rcu, free_ef); + } + mutex_unlock(&eventfs_mutex); + + while (dentry_list) { + unsigned long ptr; + + dentry = dentry_list; + ptr = (unsigned long)dentry->d_fsdata & ~1UL; + dentry_list = (struct dentry *)ptr; + dentry->d_fsdata = NULL; + d_invalidate(dentry); + mutex_lock(&eventfs_mutex); + /* dentry should now have at least a single reference */ + WARN_ONCE((int)d_count(dentry) < 1, + "dentry %p less than one reference (%d) after invalidate\n", + dentry, d_count(dentry)); + mutex_unlock(&eventfs_mutex); + dput(dentry); + } +} + +/** + * eventfs_remove_events_dir - remove eventfs dir or file from list + * @dentry: events's dentry to be removed. + * + * This function remove events main directory + */ +void eventfs_remove_events_dir(struct dentry *dentry) +{ + struct tracefs_inode *ti; + struct eventfs_inode *ei; + + if (!dentry || !dentry->d_inode) + return; + + ti = get_tracefs(dentry->d_inode); + if (!ti || !(ti->flags & TRACEFS_EVENT_INODE)) + return; + + ei = ti->private; + d_invalidate(dentry); + dput(dentry); + kfree(ei); +} diff --git a/include/linux/tracefs.h b/include/linux/tracefs.h index 54c9cbd0389b..009072792fa3 100644 --- a/include/linux/tracefs.h +++ b/include/linux/tracefs.h @@ -40,6 +40,10 @@ 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);

kprobe_args_char.tc, kprobe_args_string.tc has validation check for tracefs_create_dir, for eventfs it should be eventfs_create_dir.

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 Acked-by: Masami Hiramatsu (Google) mhiramat@kernel.org --- .../selftests/ftrace/test.d/kprobe/kprobe_args_char.tc | 9 +++++++-- .../selftests/ftrace/test.d/kprobe/kprobe_args_string.tc | 9 +++++++-- 2 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_char.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_char.tc index 285b4770efad..ff7499eb98d6 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_char.tc +++ b/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 diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc index a4f8e7c53c1f..a202b2ea4baf 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc +++ b/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