From 22098763a10d9c1340827fcf6edab66f153b27f0 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 13 Sep 2026 12:27:00 -0700 Subject: Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Don't destroy user event fields when removal fails User event fields are destroyed before the event is removed from visibility. But that can fail leaving the still visible event with no fields. Move the destroying of the fields to after the event is successfully removed from visibility. - Initialize function graph state is fork before calling copy_exec_state() For non-CLONE_VM forks, copy_exec_state() allocates a new task_exec_state. If that allocation fails, ftrace_graph_exit_task() will free the tasks ret_stack pointer. Since that pointer is still using the parent's ret_stack, it mistakenly frees the parent's pointer too. Call ftrace_graph_init() on the task first which will NULL out the new tasks's ret_stack and if the copy fails, it will not free anything. - Remove FGRAPH_MAX_INDEX The macro FGRAPH_MAX_INDEX was added but never used. Remove it. - Save ent_size in function graph printing of nested functions The function graph tracer needs to look at the next event to see if the next event is the return of the current function entry. If it is, it prints a single line: ktime_get(); Otherwise it prints it like a nested function: tick_nohz_irq_exit() { ktime_get(); kcpustat_irq_exit(); } In order to look at the next event, it must save the current event so that it has the information to print from it. It saves the event in the iterator descriptor called "ent". What it doesn't save is the ent_size of the event which is now used to know if the function graph arguments are to be printed. The peek doesn't save the size so the size used happens to be that of the size of the last event that was seen. Save the entry event size in the iterator descriptor so that the correct size is used. - Fix several errors with freeing data in the histogram code The histogram code had a lot of leaked or or incorrect accounting when failures happen. Correct them. - Fix histogram regression of .percent and .graph modifiers Up until 6.3 histogram values could have "percent" or "graph" modifiers that changed how they were printed. But a change that added restricting histograms values from being strings, stack traces and other modifiers inadvertently prevented them from using the percent and graph modifiers, which were legal use cases for values. Put back the percent and graph modifiers. - Fix various typos in the comments - Set the trace_clock before initializing a histogram with clock argument The histogram API allows the user to specific which trace clock to use via a "clock=" string. The histogram is set up first before the clock is checked. If the passed in clock is not valid, it exits without fully fixing up the histogram leaving it on the list and a use-after-free can trigger. Update the clock argument first and if it fails then exit gracefully before the histogram trigger is placed on any lists. - Restore :mod: trailer after parsing in ftrace_set_clr_event The function ftrace_set_clr_event() modifies the parse string and needs to put it back to what was passed in. It searches for ":mod:" via a strsep() but fails to put back the first ':' in the string. Add back the ':' in the passed in string. - Take trace_array reference when opening a tracer options file The options files are dynamically created and some tracers add their own options. When a tracer adds their own list of options, the trace_array holding them has an array to hold the list of options for each tracer. This array increases in size via a krealloc(), and the new entry gets a newly allocated array to hold the options of the new tracer being added. The element in each entry of the tracer's option array holds a pointer back to the trace_array, a pointer to the tracer it is associated to, a pointer to the flags of the option. The issue is that these arrays are freed when the trace_array is freed when its instance it represents is removed from the instances directory. There's a race that an open of one of these options files can happen when the instance is being removed. Add a new helper function to be called by the open function of the options file to iterate all existing trace_arrays under a lock and find the one that has the given option element in one of it's tracer arrays. If found, then update the associated trace_array's reference counter to keep it from being freed. If not found, have the open call return -ENODEV. - Disable interrupts when acquiring the lock in rb_wake_up_waiters() The function rb_wake_up_waiters() assumes it will be called in interrupt context and does not disable irqs when taking cpu_buffer->reader_lock, which can be called in hard interrupt context. The issue is in PREEMPT_RT, this function is called in thread context leaving this lock open to a deadlock. Take the lock with interrupts disabled. - Use rcu_assign_pointer() for tmp_ops filter hash The tmp_ops used in update_ftrace_direct_mod() assigns its filter_hash field directly, but that field is annotated as __rcu and sparse complains. Assign it with rcu_assign_pointer() - Fix use-after-free in enable_trigger_private_data_free() The trace_event_call is accessed through the event_trigger_data's trace_event_file pointer to put the trace_event_call on freeing. The issue is that the trace_event_file data may have been freed already causing a use-after-free. Add a field to the event_trigger_data that points directly to the trace_event_call so that it can decrement its reference directly without needing to go through the trace_event_file. - Fix accounting of buffer data remote headers trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount the number of pages is needed for the asked for size as it doesn't take into account the meta data on each page. Add a helper function to do the calculation properly and use that in these functions. - Catch nr_page_va overflow in ring_buffer_desc sizing The number of pages per remote ring buffer is capped by ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to overflow that field would silently allocate a descriptor smaller than what was asked for. - Do not resize the subbuf order if any per_cpu buffer is disabled The mmapping of ring buffers disables resizing the subbuffers, but it is done per-cpu whereas the subbuf size change is done for all the per_cpu buffers under the buffer->mutex. It could change the size of some while the mapping is happening on others. Have the resize of the subbuf order check all the per_cpu buffers under the lock to see if any of them is disabled before starting and causing an inconsistency between buffers that are being mapped. * tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits) ring-buffer: Check resize_disabled before publishing the new subbuf order tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing tracing/remotes: Account for ring buffer page header in size calculation tracing: Don't dereference trace_event_file in deferred trigger free ftrace: Use rcu_assign_pointer() for tmp_ops filter hash ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters() tracing: Take trace_array reference when opening a tracer options file tracing: Fix ring_buffer_read_page_size() kernel-doc tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event() tracing: Fix memory corruption from a "STACKTRACE" histogram key tracing: Fix memory corruption from the histogram stacktrace modifier tracing: Undo the registration when enabling the histogram trigger fails tracing: Take the reference before publishing the named histogram trigger tracing: Set the trace clock before registering the histogram trigger tracing: Fix typo "preceeded" in comment tracing: Fix typo "availabe" in comment tracing: Let histogram values keep the percent and graph modifiers tracing: Keep the entry count when the histogram stats allocation fails tracing: Free histogram the field rejected for a bad modifier tracing: Free histogram the var ref when its initialization fails ... --- fs/debugfs/inode.c | 932 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 932 insertions(+) create mode 100644 fs/debugfs/inode.c (limited to 'fs/debugfs/inode.c') diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c new file mode 100644 index 000000000..e054e6291 --- /dev/null +++ b/fs/debugfs/inode.c @@ -0,0 +1,932 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * inode.c - part of debugfs, a tiny little debug file system + * + * Copyright (C) 2004,2019 Greg Kroah-Hartman + * Copyright (C) 2004 IBM Inc. + * Copyright (C) 2019 Linux Foundation + * + * debugfs is for people to use instead of /proc or /sys. + * See ./Documentation/core-api/kernel-api.rst for more details. + */ + +#define pr_fmt(fmt) "debugfs: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "internal.h" + +#define DEBUGFS_DEFAULT_MODE 0700 + +static struct vfsmount *debugfs_mount; +static int debugfs_mount_count; +static bool debugfs_registered; +static bool debugfs_enabled __ro_after_init = IS_ENABLED(CONFIG_DEBUG_FS_ALLOW_ALL); + +/* + * Don't allow access attributes to be changed whilst the kernel is locked down + * so that we can use the file mode as part of a heuristic to determine whether + * to lock down individual files. + */ +static int debugfs_setattr(struct mnt_idmap *idmap, + struct dentry *dentry, struct iattr *ia) +{ + int ret; + + if (ia->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) { + ret = security_locked_down(LOCKDOWN_DEBUGFS); + if (ret) + return ret; + } + return simple_setattr(&nop_mnt_idmap, dentry, ia); +} + +static const struct inode_operations debugfs_file_inode_operations = { + .setattr = debugfs_setattr, +}; +static const struct inode_operations debugfs_dir_inode_operations = { + .lookup = simple_lookup, + .setattr = debugfs_setattr, +}; +static const struct inode_operations debugfs_symlink_inode_operations = { + .get_link = simple_get_link, + .setattr = debugfs_setattr, +}; + +static struct inode *debugfs_get_inode(struct super_block *sb) +{ + struct inode *inode = new_inode(sb); + if (inode) { + inode->i_ino = get_next_ino(); + simple_inode_init_ts(inode); + } + return inode; +} + +struct debugfs_fs_info { + kuid_t uid; + kgid_t gid; + umode_t mode; + /* Opt_* bitfield. */ + unsigned int opts; +}; + +enum { + Opt_uid, + Opt_gid, + Opt_mode, + Opt_source, +}; + +static const struct fs_parameter_spec debugfs_param_specs[] = { + fsparam_gid ("gid", Opt_gid), + fsparam_u32oct ("mode", Opt_mode), + fsparam_uid ("uid", Opt_uid), + fsparam_string ("source", Opt_source), + {} +}; + +static int debugfs_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + struct debugfs_fs_info *opts = fc->s_fs_info; + struct fs_parse_result result; + int opt; + + opt = fs_parse(fc, debugfs_param_specs, param, &result); + if (opt < 0) { + /* + * We might like to report bad mount options here; but + * traditionally debugfs has ignored all mount options + */ + if (opt == -ENOPARAM) + return 0; + + return opt; + } + + switch (opt) { + case Opt_uid: + opts->uid = result.uid; + break; + case Opt_gid: + opts->gid = result.gid; + break; + case Opt_mode: + opts->mode = result.uint_32 & S_IALLUGO; + break; + case Opt_source: + if (fc->source) + return invalfc(fc, "Multiple sources specified"); + fc->source = param->string; + param->string = NULL; + break; + /* + * We might like to report bad mount options here; + * but traditionally debugfs has ignored all mount options + */ + } + + opts->opts |= BIT(opt); + + return 0; +} + +static void _debugfs_apply_options(struct super_block *sb, bool remount) +{ + struct debugfs_fs_info *fsi = sb->s_fs_info; + struct inode *inode = d_inode(sb->s_root); + + /* + * On remount, only reset mode/uid/gid if they were provided as mount + * options. + */ + + if (!remount || fsi->opts & BIT(Opt_mode)) { + inode->i_mode &= ~S_IALLUGO; + inode->i_mode |= fsi->mode; + } + + if (!remount || fsi->opts & BIT(Opt_uid)) + inode->i_uid = fsi->uid; + + if (!remount || fsi->opts & BIT(Opt_gid)) + inode->i_gid = fsi->gid; +} + +static void debugfs_apply_options(struct super_block *sb) +{ + _debugfs_apply_options(sb, false); +} + +static void debugfs_apply_options_remount(struct super_block *sb) +{ + _debugfs_apply_options(sb, true); +} + +static int debugfs_reconfigure(struct fs_context *fc) +{ + struct super_block *sb = fc->root->d_sb; + struct debugfs_fs_info *sb_opts = sb->s_fs_info; + struct debugfs_fs_info *new_opts = fc->s_fs_info; + + if (!new_opts) + return 0; + + sync_filesystem(sb); + + /* structure copy of new mount options to sb */ + *sb_opts = *new_opts; + debugfs_apply_options_remount(sb); + + return 0; +} + +static int debugfs_show_options(struct seq_file *m, struct dentry *root) +{ + struct debugfs_fs_info *fsi = root->d_sb->s_fs_info; + + if (!uid_eq(fsi->uid, GLOBAL_ROOT_UID)) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, fsi->uid)); + if (!gid_eq(fsi->gid, GLOBAL_ROOT_GID)) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, fsi->gid)); + if (fsi->mode != DEBUGFS_DEFAULT_MODE) + seq_printf(m, ",mode=%o", fsi->mode); + + return 0; +} + +static struct kmem_cache *debugfs_inode_cachep __ro_after_init; + +static void init_once(void *foo) +{ + struct debugfs_inode_info *info = foo; + inode_init_once(&info->vfs_inode); +} + +static struct inode *debugfs_alloc_inode(struct super_block *sb) +{ + struct debugfs_inode_info *info; + info = alloc_inode_sb(sb, debugfs_inode_cachep, GFP_KERNEL); + if (!info) + return NULL; + return &info->vfs_inode; +} + +static void debugfs_free_inode(struct inode *inode) +{ + if (S_ISLNK(inode->i_mode)) + kfree(inode->i_link); + kmem_cache_free(debugfs_inode_cachep, DEBUGFS_I(inode)); +} + +static const struct super_operations debugfs_super_operations = { + .statfs = simple_statfs, + .show_options = debugfs_show_options, + .alloc_inode = debugfs_alloc_inode, + .free_inode = debugfs_free_inode, +}; + +static void debugfs_release_dentry(struct dentry *dentry) +{ + struct debugfs_fsdata *fsd = dentry->d_fsdata; + + if (fsd) { + WARN_ON(!list_empty(&fsd->cancellations)); + mutex_destroy(&fsd->cancellations_mtx); + } + kfree(fsd); +} + +static struct vfsmount *debugfs_automount(struct path *path) +{ + struct inode *inode = path->dentry->d_inode; + + return DEBUGFS_I(inode)->automount(path->dentry, inode->i_private); +} + +static const struct dentry_operations debugfs_dops = { + .d_release = debugfs_release_dentry, + .d_automount = debugfs_automount, +}; + +static int debugfs_fill_super(struct super_block *sb, struct fs_context *fc) +{ + static const struct tree_descr debug_files[] = {{""}}; + int err; + + err = simple_fill_super(sb, DEBUGFS_MAGIC, debug_files); + if (err) + return err; + + sb->s_op = &debugfs_super_operations; + set_default_d_op(sb, &debugfs_dops); + sb->s_d_flags |= DCACHE_DONTCACHE; + + debugfs_apply_options(sb); + + return 0; +} + +static int debugfs_get_tree(struct fs_context *fc) +{ + int err; + + err = get_tree_single(fc, debugfs_fill_super); + if (err) + return err; + + return debugfs_reconfigure(fc); +} + +static void debugfs_free_fc(struct fs_context *fc) +{ + kfree(fc->s_fs_info); +} + +static const struct fs_context_operations debugfs_context_ops = { + .free = debugfs_free_fc, + .parse_param = debugfs_parse_param, + .get_tree = debugfs_get_tree, + .reconfigure = debugfs_reconfigure, +}; + +static int debugfs_init_fs_context(struct fs_context *fc) +{ + struct debugfs_fs_info *fsi; + + fsi = kzalloc_obj(struct debugfs_fs_info); + if (!fsi) + return -ENOMEM; + + fsi->mode = DEBUGFS_DEFAULT_MODE; + + fc->s_fs_info = fsi; + fc->ops = &debugfs_context_ops; + return 0; +} + +static struct file_system_type debug_fs_type = { + .owner = THIS_MODULE, + .name = "debugfs", + .init_fs_context = debugfs_init_fs_context, + .parameters = debugfs_param_specs, + .kill_sb = kill_anon_super, +}; +MODULE_ALIAS_FS("debugfs"); + +/** + * debugfs_lookup() - look up an existing debugfs file + * @name: a pointer to a string containing the name of the file to look up. + * @parent: a pointer to the parent dentry of the file. + * + * This function will return a pointer to a dentry if it succeeds. If the file + * doesn't exist or an error occurs, %NULL will be returned. The returned + * dentry must be passed to dput() when it is no longer needed. + * + * If debugfs is not enabled in the kernel, the value -%ENODEV will be + * returned. + */ +struct dentry *debugfs_lookup(const char *name, struct dentry *parent) +{ + struct dentry *dentry; + + if (!debugfs_initialized() || IS_ERR_OR_NULL(name) || IS_ERR(parent)) + return NULL; + + if (!parent) + parent = debugfs_mount->mnt_root; + + dentry = lookup_noperm_positive_unlocked(&QSTR(name), parent); + if (IS_ERR(dentry)) + return NULL; + return dentry; +} +EXPORT_SYMBOL_GPL(debugfs_lookup); + +static struct dentry *debugfs_start_creating(const char *name, + struct dentry *parent) +{ + struct dentry *dentry; + int error; + + if (!debugfs_enabled) + return ERR_PTR(-EPERM); + + if (!debugfs_initialized()) { + pr_err("Unable to create file '%s', debugfs is not initialized yet\n", + name); + return ERR_PTR(-ENOENT); + } + + pr_debug("creating file '%s'\n", name); + + if (IS_ERR(parent)) + return parent; + + error = simple_pin_fs(&debug_fs_type, &debugfs_mount, + &debugfs_mount_count); + if (error) { + pr_err("Unable to pin filesystem for file '%s'\n", name); + 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 = debugfs_mount->mnt_root; + + dentry = simple_start_creating(parent, name); + if (IS_ERR(dentry)) { + if (dentry == ERR_PTR(-EEXIST)) + pr_err("'%s' already exists in '%pd'\n", name, parent); + simple_release_fs(&debugfs_mount, &debugfs_mount_count); + } + return dentry; +} + +static struct dentry *debugfs_failed_creating(struct dentry *dentry) +{ + simple_done_creating(dentry); + simple_release_fs(&debugfs_mount, &debugfs_mount_count); + return ERR_PTR(-ENOMEM); +} + +static struct dentry *debugfs_end_creating(struct dentry *dentry) +{ + simple_done_creating(dentry); + return dentry; // borrowed +} + +static struct dentry *__debugfs_create_file(const char *name, umode_t mode, + struct dentry *parent, void *data, + const void *aux, + const struct file_operations *proxy_fops, + const void *real_fops) +{ + struct dentry *dentry; + struct inode *inode; + + if (!(mode & S_IFMT)) + mode |= S_IFREG; + BUG_ON(!S_ISREG(mode)); + dentry = debugfs_start_creating(name, parent); + + if (IS_ERR(dentry)) + return dentry; + + inode = debugfs_get_inode(dentry->d_sb); + if (unlikely(!inode)) { + pr_err("out of free dentries, can not create file '%s'\n", + name); + return debugfs_failed_creating(dentry); + } + + inode->i_mode = mode; + inode->i_private = data; + + inode->i_op = &debugfs_file_inode_operations; + if (!real_fops) + proxy_fops = &debugfs_noop_file_operations; + inode->i_fop = proxy_fops; + DEBUGFS_I(inode)->raw = real_fops; + DEBUGFS_I(inode)->aux = (void *)aux; + + d_make_persistent(dentry, inode); + fsnotify_create(d_inode(dentry->d_parent), dentry); + return debugfs_end_creating(dentry); +} + +struct dentry *debugfs_create_file_full(const char *name, umode_t mode, + struct dentry *parent, void *data, + const void *aux, + const struct file_operations *fops) +{ + return __debugfs_create_file(name, mode, parent, data, aux, + &debugfs_full_proxy_file_operations, + fops); +} +EXPORT_SYMBOL_GPL(debugfs_create_file_full); + +struct dentry *debugfs_create_file_short(const char *name, umode_t mode, + struct dentry *parent, void *data, + const void *aux, + const struct debugfs_short_fops *fops) +{ + return __debugfs_create_file(name, mode, parent, data, aux, + &debugfs_full_short_proxy_file_operations, + fops); +} +EXPORT_SYMBOL_GPL(debugfs_create_file_short); + +/** + * debugfs_create_file_unsafe - create a file in the debugfs filesystem + * @name: a pointer to a string containing the name of the file to create. + * @mode: the permission that the file should have. + * @parent: a pointer to the parent dentry for this file. This should be a + * directory dentry if set. If this parameter is NULL, then the + * file will be created in the root of the debugfs filesystem. + * @data: a pointer to 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. + * @fops: a pointer to a struct file_operations that should be used for + * this file. + * + * debugfs_create_file_unsafe() is completely analogous to + * debugfs_create_file(), the only difference being that the fops + * handed it will not get protected against file removals by the + * debugfs core. + * + * It is your responsibility to protect your struct file_operation + * methods against file removals by means of debugfs_file_get() + * and debugfs_file_put(). ->open() is still protected by + * debugfs though. + * + * Any struct file_operations defined by means of + * DEFINE_DEBUGFS_ATTRIBUTE() is protected against file removals and + * thus, may be used here. + */ +struct dentry *debugfs_create_file_unsafe(const char *name, umode_t mode, + struct dentry *parent, void *data, + const struct file_operations *fops) +{ + + return __debugfs_create_file(name, mode, parent, data, NULL, + &debugfs_open_proxy_file_operations, + fops); +} +EXPORT_SYMBOL_GPL(debugfs_create_file_unsafe); + +/** + * debugfs_create_file_size - create a file in the debugfs filesystem + * @name: a pointer to a string containing the name of the file to create. + * @mode: the permission that the file should have. + * @parent: a pointer to the parent dentry for this file. This should be a + * directory dentry if set. If this parameter is NULL, then the + * file will be created in the root of the debugfs filesystem. + * @data: a pointer to 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. + * @fops: a pointer to a struct file_operations that should be used for + * this file. + * @file_size: initial file size + * + * This is the basic "create a file" function for debugfs. It allows for a + * wide range of flexibility in creating a file, or a directory (if you want + * to create a directory, the debugfs_create_dir() function is + * recommended to be used instead.) + */ +void debugfs_create_file_size(const char *name, umode_t mode, + struct dentry *parent, void *data, + const struct file_operations *fops, + loff_t file_size) +{ + struct dentry *de = debugfs_create_file(name, mode, parent, data, fops); + + if (!IS_ERR(de)) + d_inode(de)->i_size = file_size; +} +EXPORT_SYMBOL_GPL(debugfs_create_file_size); + +/** + * debugfs_create_dir - create a directory in the debugfs filesystem + * @name: a pointer to a string containing the name of the directory to + * create. + * @parent: a pointer to the 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 debugfs filesystem. + * + * This function creates a directory in debugfs with the given name. + * + * This function will return a pointer to a dentry if it succeeds. This + * pointer must be passed to the debugfs_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, ERR_PTR(-ERROR) will be + * returned. + * + * If debugfs is not enabled in the kernel, the value -%ENODEV will be + * returned. + * + * NOTE: it's expected that most callers should _ignore_ the errors returned + * by this function. Other debugfs functions handle the fact that the "dentry" + * passed to them could be an error and they don't crash in that case. + * Drivers should generally work fine even if debugfs fails to init anyway. + */ +struct dentry *debugfs_create_dir(const char *name, struct dentry *parent) +{ + struct dentry *dentry = debugfs_start_creating(name, parent); + struct inode *inode; + + if (IS_ERR(dentry)) + return dentry; + + inode = debugfs_get_inode(dentry->d_sb); + if (unlikely(!inode)) { + pr_err("out of free dentries, can not create directory '%s'\n", + name); + return debugfs_failed_creating(dentry); + } + + inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; + inode->i_op = &debugfs_dir_inode_operations; + inode->i_fop = &simple_dir_operations; + + /* directory inodes start off with i_nlink == 2 (for "." entry) */ + inc_nlink(inode); + d_make_persistent(dentry, inode); + inc_nlink(d_inode(dentry->d_parent)); + fsnotify_mkdir(d_inode(dentry->d_parent), dentry); + return debugfs_end_creating(dentry); +} +EXPORT_SYMBOL_GPL(debugfs_create_dir); + +/** + * debugfs_create_automount - create automount point in the debugfs filesystem + * @name: a pointer to a string containing the name of the file to create. + * @parent: a pointer to the parent dentry for this file. This should be a + * directory dentry if set. If this parameter is NULL, then the + * file will be created in the root of the debugfs filesystem. + * @f: function to be called when pathname resolution steps on that one. + * @data: opaque argument to pass to f(). + * + * @f should return what ->d_automount() would. + */ +struct dentry *debugfs_create_automount(const char *name, + struct dentry *parent, + debugfs_automount_t f, + void *data) +{ + struct dentry *dentry = debugfs_start_creating(name, parent); + struct inode *inode; + + if (IS_ERR(dentry)) + return dentry; + + inode = debugfs_get_inode(dentry->d_sb); + if (unlikely(!inode)) { + pr_err("out of free dentries, can not create automount '%s'\n", + name); + return debugfs_failed_creating(dentry); + } + + make_empty_dir_inode(inode); + inode->i_flags |= S_AUTOMOUNT; + inode->i_private = data; + DEBUGFS_I(inode)->automount = f; + /* directory inodes start off with i_nlink == 2 (for "." entry) */ + inc_nlink(inode); + d_make_persistent(dentry, inode); + inc_nlink(d_inode(dentry->d_parent)); + fsnotify_mkdir(d_inode(dentry->d_parent), dentry); + return debugfs_end_creating(dentry); +} +EXPORT_SYMBOL(debugfs_create_automount); + +/** + * debugfs_create_symlink- create a symbolic link in the debugfs filesystem + * @name: a pointer to a string containing the name of the symbolic link to + * create. + * @parent: a pointer to the parent dentry for this symbolic link. This + * should be a directory dentry if set. If this parameter is NULL, + * then the symbolic link will be created in the root of the debugfs + * filesystem. + * @target: a pointer to a string containing the path to the target of the + * symbolic link. + * + * This function creates a symbolic link with the given name in debugfs that + * links to the given target path. + * + * This function will return a pointer to a dentry if it succeeds. This + * pointer must be passed to the debugfs_remove() function when the symbolic + * link is to be removed (no automatic cleanup happens if your module is + * unloaded, you are responsible here.) If an error occurs, ERR_PTR(-ERROR) + * will be returned. + * + * If debugfs is not enabled in the kernel, the value -%ENODEV will be + * returned. + */ +struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, + const char *target) +{ + struct dentry *dentry; + struct inode *inode; + char *link = kstrdup(target, GFP_KERNEL); + if (!link) + return ERR_PTR(-ENOMEM); + + dentry = debugfs_start_creating(name, parent); + if (IS_ERR(dentry)) { + kfree(link); + return dentry; + } + + inode = debugfs_get_inode(dentry->d_sb); + if (unlikely(!inode)) { + pr_err("out of free dentries, can not create symlink '%s'\n", + name); + kfree(link); + return debugfs_failed_creating(dentry); + } + inode->i_mode = S_IFLNK | S_IRWXUGO; + inode->i_op = &debugfs_symlink_inode_operations; + inode->i_link = link; + d_make_persistent(dentry, inode); + return debugfs_end_creating(dentry); +} +EXPORT_SYMBOL_GPL(debugfs_create_symlink); + +static void __debugfs_file_removed(struct dentry *dentry) +{ + struct debugfs_fsdata *fsd; + + /* + * Paired with the closing smp_mb() implied by a successful + * cmpxchg() in debugfs_file_get(): either + * debugfs_file_get() must see a dead dentry or we must see a + * debugfs_fsdata instance at ->d_fsdata here (or both). + */ + smp_mb(); + fsd = READ_ONCE(dentry->d_fsdata); + if (!fsd) + return; + + /* if this was the last reference, we're done */ + if (refcount_dec_and_test(&fsd->active_users)) + return; + + /* + * If there's still a reference, the code that obtained it can + * be in different states: + * - The common case of not using cancellations, or already + * after debugfs_leave_cancellation(), where we just need + * to wait for debugfs_file_put() which signals the completion; + * - inside a cancellation section, i.e. between + * debugfs_enter_cancellation() and debugfs_leave_cancellation(), + * in which case we need to trigger the ->cancel() function, + * and then wait for debugfs_file_put() just like in the + * previous case; + * - before debugfs_enter_cancellation() (but obviously after + * debugfs_file_get()), in which case we may not see the + * cancellation in the list on the first round of the loop, + * but debugfs_enter_cancellation() signals the completion + * after adding it, so this code gets woken up to call the + * ->cancel() function. + */ + while (refcount_read(&fsd->active_users)) { + struct debugfs_cancellation *c; + + /* + * Lock the cancellations. Note that the cancellations + * structs are meant to be on the stack, so we need to + * ensure we either use them here or don't touch them, + * and debugfs_leave_cancellation() will wait for this + * to be finished processing before exiting one. It may + * of course win and remove the cancellation, but then + * chances are we never even got into this bit, we only + * do if the refcount isn't zero already. + */ + mutex_lock(&fsd->cancellations_mtx); + while ((c = list_first_entry_or_null(&fsd->cancellations, + typeof(*c), list))) { + list_del_init(&c->list); + c->cancel(dentry, c->cancel_data); + } + mutex_unlock(&fsd->cancellations_mtx); + + wait_for_completion(&fsd->active_users_drained); + } +} + +static void remove_one(struct dentry *victim) +{ + if (d_is_reg(victim)) + __debugfs_file_removed(victim); + simple_release_fs(&debugfs_mount, &debugfs_mount_count); +} + +/** + * debugfs_remove - recursively removes a directory + * @dentry: a pointer to a the dentry of the directory to be removed. If this + * parameter is NULL or an error value, nothing will be done. + * + * This function recursively removes a directory tree in debugfs that + * was previously created with a call to another debugfs function + * (like debugfs_create_file() or variants thereof.) + * + * This function is required to be called in order for the file to be + * removed, no automatic cleanup of files will happen when a module is + * removed, you are responsible here. + */ +void debugfs_remove(struct dentry *dentry) +{ + if (IS_ERR_OR_NULL(dentry)) + return; + + simple_pin_fs(&debug_fs_type, &debugfs_mount, &debugfs_mount_count); + simple_recursive_removal(dentry, remove_one); + simple_release_fs(&debugfs_mount, &debugfs_mount_count); +} +EXPORT_SYMBOL_GPL(debugfs_remove); + +/** + * debugfs_lookup_and_remove - lookup a directory or file and recursively remove it + * @name: a pointer to a string containing the name of the item to look up. + * @parent: a pointer to the parent dentry of the item. + * + * This is the equlivant of doing something like + * debugfs_remove(debugfs_lookup(..)) but with the proper reference counting + * handled for the directory being looked up. + */ +void debugfs_lookup_and_remove(const char *name, struct dentry *parent) +{ + struct dentry *dentry; + + dentry = debugfs_lookup(name, parent); + if (!dentry) + return; + + debugfs_remove(dentry); + dput(dentry); +} +EXPORT_SYMBOL_GPL(debugfs_lookup_and_remove); + +/** + * debugfs_change_name - rename a file/directory in the debugfs filesystem + * @dentry: dentry of an object to be renamed. + * @fmt: format for new name + * + * This function renames a file/directory in debugfs. The target must not + * exist for rename to succeed. + * + * This function will return 0 on success and -E... on failure. + * + * If debugfs is not enabled in the kernel, the value -%ENODEV will be + * returned. + */ +int __printf(2, 3) debugfs_change_name(struct dentry *dentry, const char *fmt, ...) +{ + int error = 0; + const char *new_name; + struct name_snapshot old_name; + struct dentry *target; + struct renamedata rd = {}; + struct inode *dir; + va_list ap; + + if (IS_ERR_OR_NULL(dentry)) + return 0; + + va_start(ap, fmt); + new_name = kvasprintf_const(GFP_KERNEL, fmt, ap); + va_end(ap); + if (!new_name) + return -ENOMEM; + + rd.old_parent = dget_parent(dentry); + rd.new_parent = rd.old_parent; + rd.flags = RENAME_NOREPLACE; + target = lookup_noperm_unlocked(&QSTR(new_name), rd.new_parent); + if (IS_ERR(target)) { + error = PTR_ERR(target); + goto out_free; + } + + error = start_renaming_two_dentries(&rd, dentry, target); + if (error) { + if (error == -EEXIST && target == dentry) + /* it isn't an error to rename a thing to itself */ + error = 0; + goto out; + } + + dir = d_inode(rd.old_parent); + take_dentry_name_snapshot(&old_name, dentry); + simple_rename_timestamp(dir, dentry, dir, rd.new_dentry); + d_move(dentry, rd.new_dentry); + fsnotify_move(dir, dir, &old_name.name, d_is_dir(dentry), NULL, dentry); + release_dentry_name_snapshot(&old_name); + end_renaming(&rd); +out: + dput(rd.old_parent); + dput(target); +out_free: + kfree_const(new_name); + return error; +} +EXPORT_SYMBOL_GPL(debugfs_change_name); + +/** + * debugfs_initialized - Tells whether debugfs has been registered + */ +bool debugfs_initialized(void) +{ + return debugfs_registered; +} +EXPORT_SYMBOL_GPL(debugfs_initialized); + +static int __init debugfs_kernel(char *str) +{ + if (str) { + if (!strcmp(str, "on")) + debugfs_enabled = true; + else if (!strcmp(str, "off")) + debugfs_enabled = false; + else if (!strcmp(str, "no-mount")) { + pr_notice("debugfs=no-mount is a deprecated alias " + "for debugfs=off\n"); + debugfs_enabled = false; + } + } + + return 0; +} +early_param("debugfs", debugfs_kernel); + +static int __init debugfs_init(void) +{ + int retval; + + if (!debugfs_enabled) + return -EPERM; + + retval = sysfs_create_mount_point(kernel_kobj, "debug"); + if (retval) + return retval; + + debugfs_inode_cachep = kmem_cache_create("debugfs_inode_cache", + sizeof(struct debugfs_inode_info), 0, + SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT, + init_once); + if (debugfs_inode_cachep == NULL) { + sysfs_remove_mount_point(kernel_kobj, "debug"); + return -ENOMEM; + } + + retval = register_filesystem(&debug_fs_type); + if (retval) { // Really not going to happen + sysfs_remove_mount_point(kernel_kobj, "debug"); + kmem_cache_destroy(debugfs_inode_cachep); + return retval; + } + debugfs_registered = true; + return 0; +} +core_initcall(debugfs_init); -- cgit v1.3.1