From 78ff640819496212feea29c62174f3eb3c837134 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 5 Mar 2024 17:09:30 -0600 Subject: vfs: Convert tracefs to use the new mount API Convert the tracefs filesystem to the new internal mount API as the old one will be obsoleted and removed. This allows greater flexibility in communication of mount parameters between userspace, the VFS and the filesystem. See Documentation/filesystems/mount_api.txt for more information. Signed-off-by: David Howells Co-developed-by: Eric Sandeen Signed-off-by: Eric Sandeen [sandeen: forward port to modern kernel, fix remounting] Link: https://lore.kernel.org/r/536e99d3-345c-448b-adee-a21389d7ab4b@redhat.com cc: Steven Rostedt cc: Greg Kroah-Hartman Signed-off-by: Christian Brauner --- fs/tracefs/inode.c | 196 +++++++++++++++++++++++++---------------------------- 1 file changed, 91 insertions(+), 105 deletions(-) (limited to 'fs/tracefs/inode.c') diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 5545e6bf7d26..abd0b477e287 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -11,14 +11,14 @@ #include #include -#include +#include +#include #include #include #include #include #include #include -#include #include #include #include "internal.h" @@ -231,7 +231,7 @@ struct inode *tracefs_get_inode(struct super_block *sb) return inode; } -struct tracefs_mount_opts { +struct tracefs_fs_info { kuid_t uid; kgid_t gid; umode_t mode; @@ -243,68 +243,51 @@ enum { Opt_uid, Opt_gid, Opt_mode, - Opt_err }; -static const match_table_t tokens = { - {Opt_uid, "uid=%u"}, - {Opt_gid, "gid=%u"}, - {Opt_mode, "mode=%o"}, - {Opt_err, NULL} +static const struct fs_parameter_spec tracefs_param_specs[] = { + fsparam_u32 ("gid", Opt_gid), + fsparam_u32oct ("mode", Opt_mode), + fsparam_u32 ("uid", Opt_uid), + {} }; -struct tracefs_fs_info { - struct tracefs_mount_opts mount_opts; -}; - -static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts) +static int tracefs_parse_param(struct fs_context *fc, struct fs_parameter *param) { - substring_t args[MAX_OPT_ARGS]; - int option; - int token; + struct tracefs_fs_info *opts = fc->s_fs_info; + struct fs_parse_result result; kuid_t uid; kgid_t gid; - char *p; - - opts->opts = 0; - opts->mode = TRACEFS_DEFAULT_MODE; - - while ((p = strsep(&data, ",")) != NULL) { - if (!*p) - continue; - - token = match_token(p, tokens, args); - switch (token) { - case Opt_uid: - if (match_int(&args[0], &option)) - return -EINVAL; - uid = make_kuid(current_user_ns(), option); - if (!uid_valid(uid)) - return -EINVAL; - opts->uid = uid; - break; - case Opt_gid: - if (match_int(&args[0], &option)) - return -EINVAL; - gid = make_kgid(current_user_ns(), option); - if (!gid_valid(gid)) - return -EINVAL; - opts->gid = gid; - break; - case Opt_mode: - if (match_octal(&args[0], &option)) - return -EINVAL; - opts->mode = option & S_IALLUGO; - break; - /* - * We might like to report bad mount options here; - * but traditionally tracefs has ignored all mount options - */ - } - - opts->opts |= BIT(token); + int opt; + + opt = fs_parse(fc, tracefs_param_specs, param, &result); + if (opt < 0) + return opt; + + switch (opt) { + case Opt_uid: + uid = make_kuid(current_user_ns(), result.uint_32); + if (!uid_valid(uid)) + return invalf(fc, "Unknown uid"); + opts->uid = uid; + break; + case Opt_gid: + gid = make_kgid(current_user_ns(), result.uint_32); + if (!gid_valid(gid)) + return invalf(fc, "Unknown gid"); + opts->gid = gid; + break; + case Opt_mode: + opts->mode = result.uint_32 & S_IALLUGO; + break; + /* + * We might like to report bad mount options here; + * but traditionally tracefs has ignored all mount options + */ } + opts->opts |= BIT(opt); + return 0; } @@ -312,7 +295,6 @@ static int tracefs_apply_options(struct super_block *sb, bool remount) { struct tracefs_fs_info *fsi = sb->s_fs_info; struct inode *inode = d_inode(sb->s_root); - struct tracefs_mount_opts *opts = &fsi->mount_opts; umode_t tmp_mode; /* @@ -320,50 +302,46 @@ static int tracefs_apply_options(struct super_block *sb, bool remount) * options. */ - if (!remount || opts->opts & BIT(Opt_mode)) { + if (!remount || fsi->opts & BIT(Opt_mode)) { tmp_mode = READ_ONCE(inode->i_mode) & ~S_IALLUGO; - tmp_mode |= opts->mode; + tmp_mode |= fsi->mode; WRITE_ONCE(inode->i_mode, tmp_mode); } - if (!remount || opts->opts & BIT(Opt_uid)) - inode->i_uid = opts->uid; + if (!remount || fsi->opts & BIT(Opt_uid)) + inode->i_uid = fsi->uid; - if (!remount || opts->opts & BIT(Opt_gid)) - inode->i_gid = opts->gid; + if (!remount || fsi->opts & BIT(Opt_gid)) + inode->i_gid = fsi->gid; return 0; } -static int tracefs_remount(struct super_block *sb, int *flags, char *data) +static int tracefs_reconfigure(struct fs_context *fc) { - int err; - struct tracefs_fs_info *fsi = sb->s_fs_info; + struct super_block *sb = fc->root->d_sb; + struct tracefs_fs_info *sb_opts = sb->s_fs_info; + struct tracefs_fs_info *new_opts = fc->s_fs_info; sync_filesystem(sb); - err = tracefs_parse_options(data, &fsi->mount_opts); - if (err) - goto fail; + /* structure copy of new mount options to sb */ + *sb_opts = *new_opts; - tracefs_apply_options(sb, true); - -fail: - return err; + return tracefs_apply_options(sb, true); } static int tracefs_show_options(struct seq_file *m, struct dentry *root) { struct tracefs_fs_info *fsi = root->d_sb->s_fs_info; - struct tracefs_mount_opts *opts = &fsi->mount_opts; - if (!uid_eq(opts->uid, GLOBAL_ROOT_UID)) + if (!uid_eq(fsi->uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", - from_kuid_munged(&init_user_ns, opts->uid)); - if (!gid_eq(opts->gid, GLOBAL_ROOT_GID)) + 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, opts->gid)); - if (opts->mode != TRACEFS_DEFAULT_MODE) - seq_printf(m, ",mode=%o", opts->mode); + from_kgid_munged(&init_user_ns, fsi->gid)); + if (fsi->mode != TRACEFS_DEFAULT_MODE) + seq_printf(m, ",mode=%o", fsi->mode); return 0; } @@ -373,7 +351,6 @@ static const struct super_operations tracefs_super_operations = { .free_inode = tracefs_free_inode, .drop_inode = generic_delete_inode, .statfs = simple_statfs, - .remount_fs = tracefs_remount, .show_options = tracefs_show_options, }; @@ -403,26 +380,14 @@ static const struct dentry_operations tracefs_dentry_operations = { .d_release = tracefs_d_release, }; -static int trace_fill_super(struct super_block *sb, void *data, int silent) +static int tracefs_fill_super(struct super_block *sb, struct fs_context *fc) { static const struct tree_descr trace_files[] = {{""}}; - struct tracefs_fs_info *fsi; int err; - fsi = kzalloc(sizeof(struct tracefs_fs_info), GFP_KERNEL); - sb->s_fs_info = fsi; - if (!fsi) { - err = -ENOMEM; - goto fail; - } - - err = tracefs_parse_options(data, &fsi->mount_opts); - if (err) - goto fail; - - err = simple_fill_super(sb, TRACEFS_MAGIC, trace_files); + err = simple_fill_super(sb, TRACEFS_MAGIC, trace_files); if (err) - goto fail; + return err; sb->s_op = &tracefs_super_operations; sb->s_d_op = &tracefs_dentry_operations; @@ -430,24 +395,45 @@ static int trace_fill_super(struct super_block *sb, void *data, int silent) tracefs_apply_options(sb, false); return 0; +} -fail: - kfree(fsi); - sb->s_fs_info = NULL; - return err; +static int tracefs_get_tree(struct fs_context *fc) +{ + return get_tree_single(fc, tracefs_fill_super); } -static struct dentry *trace_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, - void *data) +static void tracefs_free_fc(struct fs_context *fc) { - return mount_single(fs_type, flags, data, trace_fill_super); + kfree(fc->s_fs_info); +} + +static const struct fs_context_operations tracefs_context_ops = { + .free = tracefs_free_fc, + .parse_param = tracefs_parse_param, + .get_tree = tracefs_get_tree, + .reconfigure = tracefs_reconfigure, +}; + +static int tracefs_init_fs_context(struct fs_context *fc) +{ + struct tracefs_fs_info *fsi; + + fsi = kzalloc(sizeof(struct tracefs_fs_info), GFP_KERNEL); + if (!fsi) + return -ENOMEM; + + fsi->mode = TRACEFS_DEFAULT_MODE; + + fc->s_fs_info = fsi; + fc->ops = &tracefs_context_ops; + return 0; } static struct file_system_type trace_fs_type = { .owner = THIS_MODULE, .name = "tracefs", - .mount = trace_mount, + .init_fs_context = tracefs_init_fs_context, + .parameters = tracefs_param_specs, .kill_sb = kill_litter_super, }; MODULE_ALIAS_FS("tracefs"); -- cgit v1.2.3-59-g8ed1b From baa23a8d4360d981a49913841a726edede5cdd54 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Thu, 2 May 2024 16:08:23 -0400 Subject: tracefs: Reset permissions on remount if permissions are options There's an inconsistency with the way permissions are handled in tracefs. Because the permissions are generated when accessed, they default to the root inode's permission if they were never set by the user. If the user sets the permissions, then a flag is set and the permissions are saved via the inode (for tracefs files) or an internal attribute field (for eventfs). But if a remount happens that specify the permissions, all the files that were not changed by the user gets updated, but the ones that were are not. If the user were to remount the file system with a given permission, then all files and directories within that file system should be updated. This can cause security issues if a file's permission was updated but the admin forgot about it. They could incorrectly think that remounting with permissions set would update all files, but miss some. For example: # cd /sys/kernel/tracing # chgrp 1002 current_tracer # ls -l [..] -rw-r----- 1 root root 0 May 1 21:25 buffer_size_kb -rw-r----- 1 root root 0 May 1 21:25 buffer_subbuf_size_kb -r--r----- 1 root root 0 May 1 21:25 buffer_total_size_kb -rw-r----- 1 root lkp 0 May 1 21:25 current_tracer -rw-r----- 1 root root 0 May 1 21:25 dynamic_events -r--r----- 1 root root 0 May 1 21:25 dyn_ftrace_total_info -r--r----- 1 root root 0 May 1 21:25 enabled_functions Where current_tracer now has group "lkp". # mount -o remount,gid=1001 . # ls -l -rw-r----- 1 root tracing 0 May 1 21:25 buffer_size_kb -rw-r----- 1 root tracing 0 May 1 21:25 buffer_subbuf_size_kb -r--r----- 1 root tracing 0 May 1 21:25 buffer_total_size_kb -rw-r----- 1 root lkp 0 May 1 21:25 current_tracer -rw-r----- 1 root tracing 0 May 1 21:25 dynamic_events -r--r----- 1 root tracing 0 May 1 21:25 dyn_ftrace_total_info -r--r----- 1 root tracing 0 May 1 21:25 enabled_functions Everything changed but the "current_tracer". Add a new link list that keeps track of all the tracefs_inodes which has the permission flags that tell if the file/dir should use the root inode's permission or not. Then on remount, clear all the flags so that the default behavior of using the root inode's permission is done for all files and directories. Link: https://lore.kernel.org/linux-trace-kernel/20240502200905.529542160@goodmis.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Fixes: 8186fff7ab649 ("tracefs/eventfs: Use root and instance inodes as default ownership") Signed-off-by: Steven Rostedt (Google) --- fs/tracefs/event_inode.c | 29 +++++++++++++++++++++ fs/tracefs/inode.c | 65 +++++++++++++++++++++++++++++++++++++++++++++++- fs/tracefs/internal.h | 7 +++++- 3 files changed, 99 insertions(+), 2 deletions(-) (limited to 'fs/tracefs/inode.c') diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index cc8b838bbe62..15a2a9c3c62b 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -308,6 +308,35 @@ static const struct file_operations eventfs_file_operations = { .llseek = generic_file_llseek, }; +/* + * On a remount of tracefs, if UID or GID options are set, then + * the mount point inode permissions should be used. + * Reset the saved permission flags appropriately. + */ +void eventfs_remount(struct tracefs_inode *ti, bool update_uid, bool update_gid) +{ + struct eventfs_inode *ei = ti->private; + + if (!ei) + return; + + if (update_uid) + ei->attr.mode &= ~EVENTFS_SAVE_UID; + + if (update_gid) + ei->attr.mode &= ~EVENTFS_SAVE_GID; + + if (!ei->entry_attrs) + return; + + for (int i = 0; i < ei->nr_entries; i++) { + if (update_uid) + ei->entry_attrs[i].mode &= ~EVENTFS_SAVE_UID; + if (update_gid) + ei->entry_attrs[i].mode &= ~EVENTFS_SAVE_GID; + } +} + /* Return the evenfs_inode of the "events" directory */ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry) { diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 5545e6bf7d26..52aa14bd2994 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -30,20 +30,47 @@ static struct vfsmount *tracefs_mount; static int tracefs_mount_count; static bool tracefs_registered; +/* + * Keep track of all tracefs_inodes in order to update their + * flags if necessary on a remount. + */ +static DEFINE_SPINLOCK(tracefs_inode_lock); +static LIST_HEAD(tracefs_inodes); + static struct inode *tracefs_alloc_inode(struct super_block *sb) { struct tracefs_inode *ti; + unsigned long flags; ti = kmem_cache_alloc(tracefs_inode_cachep, GFP_KERNEL); if (!ti) return NULL; + spin_lock_irqsave(&tracefs_inode_lock, flags); + list_add_rcu(&ti->list, &tracefs_inodes); + spin_unlock_irqrestore(&tracefs_inode_lock, flags); + return &ti->vfs_inode; } +static void tracefs_free_inode_rcu(struct rcu_head *rcu) +{ + struct tracefs_inode *ti; + + ti = container_of(rcu, struct tracefs_inode, rcu); + kmem_cache_free(tracefs_inode_cachep, ti); +} + static void tracefs_free_inode(struct inode *inode) { - kmem_cache_free(tracefs_inode_cachep, get_tracefs(inode)); + struct tracefs_inode *ti = get_tracefs(inode); + unsigned long flags; + + spin_lock_irqsave(&tracefs_inode_lock, flags); + list_del_rcu(&ti->list); + spin_unlock_irqrestore(&tracefs_inode_lock, flags); + + call_rcu(&ti->rcu, tracefs_free_inode_rcu); } static ssize_t default_read_file(struct file *file, char __user *buf, @@ -313,6 +340,8 @@ static int tracefs_apply_options(struct super_block *sb, bool remount) struct tracefs_fs_info *fsi = sb->s_fs_info; struct inode *inode = d_inode(sb->s_root); struct tracefs_mount_opts *opts = &fsi->mount_opts; + struct tracefs_inode *ti; + bool update_uid, update_gid; umode_t tmp_mode; /* @@ -332,6 +361,25 @@ static int tracefs_apply_options(struct super_block *sb, bool remount) if (!remount || opts->opts & BIT(Opt_gid)) inode->i_gid = opts->gid; + if (remount && (opts->opts & BIT(Opt_uid) || opts->opts & BIT(Opt_gid))) { + + update_uid = opts->opts & BIT(Opt_uid); + update_gid = opts->opts & BIT(Opt_gid); + + rcu_read_lock(); + list_for_each_entry_rcu(ti, &tracefs_inodes, list) { + if (update_uid) + ti->flags &= ~TRACEFS_UID_PERM_SET; + + if (update_gid) + ti->flags &= ~TRACEFS_GID_PERM_SET; + + if (ti->flags & TRACEFS_EVENT_INODE) + eventfs_remount(ti, update_uid, update_gid); + } + rcu_read_unlock(); + } + return 0; } @@ -398,7 +446,22 @@ static int tracefs_d_revalidate(struct dentry *dentry, unsigned int flags) return !(ei && ei->is_freed); } +static void tracefs_d_iput(struct dentry *dentry, struct inode *inode) +{ + struct tracefs_inode *ti = get_tracefs(inode); + + /* + * This inode is being freed and cannot be used for + * eventfs. Clear the flag so that it doesn't call into + * eventfs during the remount flag updates. The eventfs_inode + * gets freed after an RCU cycle, so the content will still + * be safe if the iteration is going on now. + */ + ti->flags &= ~TRACEFS_EVENT_INODE; +} + static const struct dentry_operations tracefs_dentry_operations = { + .d_iput = tracefs_d_iput, .d_revalidate = tracefs_d_revalidate, .d_release = tracefs_d_release, }; diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h index 15c26f9aaad4..29f0c999975b 100644 --- a/fs/tracefs/internal.h +++ b/fs/tracefs/internal.h @@ -11,8 +11,12 @@ enum { }; struct tracefs_inode { - struct inode vfs_inode; + union { + struct inode vfs_inode; + struct rcu_head rcu; + }; /* The below gets initialized with memset_after(ti, 0, vfs_inode) */ + struct list_head list; unsigned long flags; void *private; }; @@ -73,6 +77,7 @@ 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_remount(struct tracefs_inode *ti, bool update_uid, bool update_gid); void eventfs_d_release(struct dentry *dentry); #endif /* _TRACEFS_INTERNAL_H */ -- cgit v1.2.3-59-g8ed1b From 6599bd5517be66c8344f869f3ca3a91bc10f2b9e Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Thu, 2 May 2024 16:08:24 -0400 Subject: tracefs: Still use mount point as default permissions for instances If the instances directory's permissions were never change, then have it and its children use the mount point permissions as the default. Currently, the permissions of instance directories are determined by the instance directory's permissions itself. But if the tracefs file system is remounted and changes the permissions, the instance directory and its children should use the new permission. But because both the instance directory and its children use the instance directory's inode for permissions, it misses the update. To demonstrate this: # cd /sys/kernel/tracing/ # mkdir instances/foo # ls -ld instances/foo drwxr-x--- 5 root root 0 May 1 19:07 instances/foo # ls -ld instances drwxr-x--- 3 root root 0 May 1 18:57 instances # ls -ld current_tracer -rw-r----- 1 root root 0 May 1 18:57 current_tracer # mount -o remount,gid=1002 . # ls -ld instances drwxr-x--- 3 root root 0 May 1 18:57 instances # ls -ld instances/foo/ drwxr-x--- 5 root root 0 May 1 19:07 instances/foo/ # ls -ld current_tracer -rw-r----- 1 root lkp 0 May 1 18:57 current_tracer Notice that changing the group id to that of "lkp" did not affect the instances directory nor its children. It should have been: # ls -ld current_tracer -rw-r----- 1 root root 0 May 1 19:19 current_tracer # ls -ld instances/foo/ drwxr-x--- 5 root root 0 May 1 19:25 instances/foo/ # ls -ld instances drwxr-x--- 3 root root 0 May 1 19:19 instances # mount -o remount,gid=1002 . # ls -ld current_tracer -rw-r----- 1 root lkp 0 May 1 19:19 current_tracer # ls -ld instances drwxr-x--- 3 root lkp 0 May 1 19:19 instances # ls -ld instances/foo/ drwxr-x--- 5 root lkp 0 May 1 19:25 instances/foo/ Where all files were updated by the remount gid update. Link: https://lore.kernel.org/linux-trace-kernel/20240502200905.686838327@goodmis.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Fixes: 8186fff7ab649 ("tracefs/eventfs: Use root and instance inodes as default ownership") Signed-off-by: Steven Rostedt (Google) --- fs/tracefs/inode.c | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) (limited to 'fs/tracefs/inode.c') diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 52aa14bd2994..417c840e6403 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -180,16 +180,39 @@ static void set_tracefs_inode_owner(struct inode *inode) { struct tracefs_inode *ti = get_tracefs(inode); struct inode *root_inode = ti->private; + kuid_t uid; + kgid_t gid; + + uid = root_inode->i_uid; + gid = root_inode->i_gid; + + /* + * If the root is not the mount point, then check the root's + * permissions. If it was never set, then default to the + * mount point. + */ + if (root_inode != d_inode(root_inode->i_sb->s_root)) { + struct tracefs_inode *rti; + + rti = get_tracefs(root_inode); + root_inode = d_inode(root_inode->i_sb->s_root); + + if (!(rti->flags & TRACEFS_UID_PERM_SET)) + uid = root_inode->i_uid; + + if (!(rti->flags & TRACEFS_GID_PERM_SET)) + gid = root_inode->i_gid; + } /* * If this inode has never been referenced, then update * the permissions to the superblock. */ if (!(ti->flags & TRACEFS_UID_PERM_SET)) - inode->i_uid = root_inode->i_uid; + inode->i_uid = uid; if (!(ti->flags & TRACEFS_GID_PERM_SET)) - inode->i_gid = root_inode->i_gid; + inode->i_gid = gid; } static int tracefs_permission(struct mnt_idmap *idmap, -- cgit v1.2.3-59-g8ed1b From 27c046484382d78b4abb0a6e9905a20121af9b35 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Thu, 23 May 2024 01:14:27 -0400 Subject: tracefs: Update inode permissions on remount When a remount happens, if a gid or uid is specified update the inodes to have the same gid and uid. This will allow the simplification of the permissions logic for the dynamically created files and directories. Link: https://lore.kernel.org/linux-trace-kernel/20240523051539.592429986@goodmis.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Masahiro Yamada Fixes: baa23a8d4360d ("tracefs: Reset permissions on remount if permissions are options") Signed-off-by: Steven Rostedt (Google) --- fs/tracefs/event_inode.c | 17 +++++++++++++---- fs/tracefs/inode.c | 15 ++++++++++++--- 2 files changed, 25 insertions(+), 7 deletions(-) (limited to 'fs/tracefs/inode.c') diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 55a40a730b10..5dfb1ccd56ea 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -317,20 +317,29 @@ void eventfs_remount(struct tracefs_inode *ti, bool update_uid, bool update_gid) if (!ei) return; - if (update_uid) + if (update_uid) { ei->attr.mode &= ~EVENTFS_SAVE_UID; + ei->attr.uid = ti->vfs_inode.i_uid; + } + - if (update_gid) + if (update_gid) { ei->attr.mode &= ~EVENTFS_SAVE_GID; + ei->attr.gid = ti->vfs_inode.i_gid; + } if (!ei->entry_attrs) return; for (int i = 0; i < ei->nr_entries; i++) { - if (update_uid) + if (update_uid) { ei->entry_attrs[i].mode &= ~EVENTFS_SAVE_UID; - if (update_gid) + ei->entry_attrs[i].uid = ti->vfs_inode.i_uid; + } + if (update_gid) { ei->entry_attrs[i].mode &= ~EVENTFS_SAVE_GID; + ei->entry_attrs[i].gid = ti->vfs_inode.i_gid; + } } } diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index a827f6a716c4..9252e0d78ea2 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -373,12 +373,21 @@ static int tracefs_apply_options(struct super_block *sb, bool remount) rcu_read_lock(); list_for_each_entry_rcu(ti, &tracefs_inodes, list) { - if (update_uid) + if (update_uid) { ti->flags &= ~TRACEFS_UID_PERM_SET; + ti->vfs_inode.i_uid = fsi->uid; + } - if (update_gid) + if (update_gid) { ti->flags &= ~TRACEFS_GID_PERM_SET; - + ti->vfs_inode.i_gid = fsi->gid; + } + + /* + * Note, the above ti->vfs_inode updates are + * used in eventfs_remount() so they must come + * before calling it. + */ if (ti->flags & TRACEFS_EVENT_INODE) eventfs_remount(ti, update_uid, update_gid); } -- cgit v1.2.3-59-g8ed1b From 0bcfd9aa4dafa03b88d68bf66b694df2a3e76cf3 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Thu, 23 May 2024 01:14:29 -0400 Subject: tracefs: Clear EVENT_INODE flag in tracefs_drop_inode() When the inode is being dropped from the dentry, the TRACEFS_EVENT_INODE flag needs to be cleared to prevent a remount from calling eventfs_remount() on the tracefs_inode private data. There's a race between the inode is dropped (and the dentry freed) to where the inode is actually freed. If a remount happens between the two, the eventfs_inode could be accessed after it is freed (only the dentry keeps a ref count on it). Currently the TRACEFS_EVENT_INODE flag is cleared from the dentry iput() function. But this is incorrect, as it is possible that the inode has another reference to it. The flag should only be cleared when the inode is really being dropped and has no more references. That happens in the drop_inode callback of the inode, as that gets called when the last reference of the inode is released. Remove the tracefs_d_iput() function and move its logic to the more appropriate tracefs_drop_inode() callback function. Link: https://lore.kernel.org/linux-trace-kernel/20240523051539.908205106@goodmis.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Masahiro Yamada Fixes: baa23a8d4360d ("tracefs: Reset permissions on remount if permissions are options") Signed-off-by: Steven Rostedt (Google) --- fs/tracefs/inode.c | 33 +++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-) (limited to 'fs/tracefs/inode.c') diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 9252e0d78ea2..7c29f4afc23d 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -426,10 +426,26 @@ static int tracefs_show_options(struct seq_file *m, struct dentry *root) return 0; } +static int tracefs_drop_inode(struct inode *inode) +{ + struct tracefs_inode *ti = get_tracefs(inode); + + /* + * This inode is being freed and cannot be used for + * eventfs. Clear the flag so that it doesn't call into + * eventfs during the remount flag updates. The eventfs_inode + * gets freed after an RCU cycle, so the content will still + * be safe if the iteration is going on now. + */ + ti->flags &= ~TRACEFS_EVENT_INODE; + + return 1; +} + static const struct super_operations tracefs_super_operations = { .alloc_inode = tracefs_alloc_inode, .free_inode = tracefs_free_inode, - .drop_inode = generic_delete_inode, + .drop_inode = tracefs_drop_inode, .statfs = simple_statfs, .show_options = tracefs_show_options, }; @@ -455,22 +471,7 @@ static int tracefs_d_revalidate(struct dentry *dentry, unsigned int flags) return !(ei && ei->is_freed); } -static void tracefs_d_iput(struct dentry *dentry, struct inode *inode) -{ - struct tracefs_inode *ti = get_tracefs(inode); - - /* - * This inode is being freed and cannot be used for - * eventfs. Clear the flag so that it doesn't call into - * eventfs during the remount flag updates. The eventfs_inode - * gets freed after an RCU cycle, so the content will still - * be safe if the iteration is going on now. - */ - ti->flags &= ~TRACEFS_EVENT_INODE; -} - static const struct dentry_operations tracefs_dentry_operations = { - .d_iput = tracefs_d_iput, .d_revalidate = tracefs_d_revalidate, .d_release = tracefs_d_release, }; -- cgit v1.2.3-59-g8ed1b