[PATCH OLK-6.6 0/4] Fix CVE-2026-68096
The following four patches are used to fix the CVE-2026-68096 vulnerability: Jeff Layton (1): audit: widen ino fields to u64 NeilBrown (1): VFS/audit: introduce kern_path_parent() for audit Ricardo Robaina (2): audit: use 'unsigned int' instead of 'unsigned' audit: fix recursive locking deadlock in audit_dupe_exe() fs/namei.c | 43 ++++++++++++++++++++++++++++++++++++++ include/linux/audit.h | 6 +++--- include/linux/audit_arch.h | 12 +++++------ include/linux/namei.h | 1 + kernel/audit.c | 2 +- kernel/audit.h | 32 ++++++++++++++++------------ kernel/audit_fsnotify.c | 39 +++++++++++++++++++++------------- kernel/audit_tree.c | 2 +- kernel/audit_watch.c | 42 ++++++++++++++++++++++++------------- kernel/auditfilter.c | 17 ++++++++------- kernel/auditsc.c | 6 +++--- lib/compat_audit.c | 12 +++++------ 12 files changed, 144 insertions(+), 70 deletions(-) -- 2.25.1
From: NeilBrown <neil@brown.name> stable inclusion from stable-v6.6.148 commit 3ff7d33398419c302450caf88cec7e2e22028ca0 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/16905 CVE: CVE-2026-68096 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=... -------------------------------- [ Upstream commit 76a53de6f7ff0641570364234fb4489f4d4fc8e9 ] audit_alloc_mark() and audit_get_nd() both need to perform a path lookup getting the parent dentry (which must exist) and the final target (following a LAST_NORM name) which sometimes doesn't need to exist. They don't need the parent to be locked, but use kern_path_locked() or kern_path_locked_negative() anyway. This is somewhat misleading to the casual reader. This patch introduces a more targeted function, kern_path_parent(), which returns not holding locks. On success the "path" will be set to the parent, which must be found, and the return value is the dentry of the target, which might be negative. This will clear the way to rename kern_path_locked() which is otherwise only used to prepare for removing something. It also allows us to remove kern_path_locked_negative(), which is transformed into the new kern_path_parent(). Signed-off-by: NeilBrown <neil@brown.name> Signed-off-by: Christian Brauner <brauner@kernel.org> Stable-dep-of: 81905b5acbe7 ("audit: fix recursive locking deadlock in audit_dupe_exe()") Signed-off-by: Sasha Levin <sashal@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Yi Yang <yiyang13@huawei.com> --- fs/namei.c | 43 +++++++++++++++++++++++++++++++++++++++++ include/linux/namei.h | 1 + kernel/audit.h | 4 ++-- kernel/audit_fsnotify.c | 9 +++------ kernel/audit_watch.c | 9 ++++++--- 5 files changed, 55 insertions(+), 11 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index afcc15b5ae2e..b66b00400bcf 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2605,6 +2605,49 @@ static struct dentry *__kern_path_locked(struct filename *name, struct path *pat return d; } +/** + * kern_path_parent: lookup path returning parent and target + * @name: path name + * @path: path to store parent in + * + * The path @name should end with a normal component, not "." or ".." or "/". + * A lookup is performed and if successful the parent information + * is store in @parent and the dentry is returned. + * + * The dentry maybe negative, the parent will be positive. + * + * Returns: dentry or error. + */ +struct dentry *kern_path_parent(const char *name, struct path *path) +{ + struct filename *filename = getname_kernel(name); + struct path parent_path; + struct dentry *d; + struct qstr last; + int type, error; + + error = filename_parentat(AT_FDCWD, filename, 0, &parent_path, &last, &type); + if (error) { + d = ERR_PTR(error); + goto out; + } + if (unlikely(type != LAST_NORM)) { + path_put(&parent_path); + d = ERR_PTR(-EINVAL); + goto out; + } + + d = lookup_one_len_unlocked(last.name, parent_path.dentry, last.len); + if (IS_ERR(d)) { + path_put(&parent_path); + goto out; + } + *path = parent_path; +out: + putname(filename); + return d; +} + struct dentry *kern_path_locked(const char *name, struct path *path) { struct filename *filename = getname_kernel(name); diff --git a/include/linux/namei.h b/include/linux/namei.h index 1463cbda4888..c1ff032607dd 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -61,6 +61,7 @@ struct dentry *lookup_one_qstr_excl(const struct qstr *name, struct dentry *base, unsigned int flags); extern int kern_path(const char *, unsigned, struct path *); +struct dentry *kern_path_parent(const char *name, struct path *parent); extern struct dentry *kern_path_create(int, const char *, struct path *, unsigned int); extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int); diff --git a/kernel/audit.h b/kernel/audit.h index 3938e25610bd..8186b14f0b36 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -283,8 +283,8 @@ extern struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, extern char *audit_mark_path(struct audit_fsnotify_mark *mark); extern void audit_remove_mark(struct audit_fsnotify_mark *audit_mark); extern void audit_remove_mark_rule(struct audit_krule *krule); -extern int audit_mark_compare(struct audit_fsnotify_mark *mark, - unsigned long ino, dev_t dev); +extern int audit_mark_compare(struct audit_fsnotify_mark *mark, u64 ino, + dev_t dev); extern int audit_dupe_exe(struct audit_krule *new, struct audit_krule *old); extern int audit_exe_compare(struct task_struct *tsk, struct audit_fsnotify_mark *mark); diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c index c565fbf66ac8..2b237895157d 100644 --- a/kernel/audit_fsnotify.c +++ b/kernel/audit_fsnotify.c @@ -57,7 +57,7 @@ char *audit_mark_path(struct audit_fsnotify_mark *mark) return mark->path; } -int audit_mark_compare(struct audit_fsnotify_mark *mark, unsigned long ino, dev_t dev) +int audit_mark_compare(struct audit_fsnotify_mark *mark, u64 ino, dev_t dev) { if (mark->ino == AUDIT_INO_UNSET) return 0; @@ -76,17 +76,14 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa struct audit_fsnotify_mark *audit_mark; struct path path; struct dentry *dentry; - struct inode *inode; int ret; if (pathname[0] != '/' || pathname[len-1] == '/') return ERR_PTR(-EINVAL); - dentry = kern_path_locked(pathname, &path); + dentry = kern_path_parent(pathname, &path); if (IS_ERR(dentry)) return ERR_CAST(dentry); /* returning an error */ - inode = path.dentry->d_inode; - inode_unlock(inode); audit_mark = kzalloc(sizeof(*audit_mark), GFP_KERNEL); if (unlikely(!audit_mark)) { @@ -100,7 +97,7 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa audit_update_mark(audit_mark, dentry->d_inode); audit_mark->rule = krule; - ret = fsnotify_add_inode_mark(&audit_mark->mark, inode, 0); + ret = fsnotify_add_inode_mark(&audit_mark->mark, path.dentry->d_inode, 0); if (ret < 0) { audit_mark->path = NULL; fsnotify_put_mark(&audit_mark->mark); diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 7a98cd176a12..60f5daebc5ef 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -244,7 +244,7 @@ static void audit_watch_log_rule_change(struct audit_krule *r, struct audit_watc /* Update inode info in audit rules based on filesystem event. */ static void audit_update_watch(struct audit_parent *parent, const struct qstr *dname, dev_t dev, - unsigned long ino, unsigned invalidating) + u64 ino, unsigned int invalidating) { struct audit_watch *owatch, *nwatch, *nextw; struct audit_krule *r, *nextr; @@ -347,15 +347,18 @@ static void audit_remove_parent_watches(struct audit_parent *parent) /* Get path information necessary for adding watches. */ static int audit_get_nd(struct audit_watch *watch, struct path *parent) { - struct dentry *d = kern_path_locked(watch->path, parent); + struct dentry *d; + + d = kern_path_parent(watch->path, parent); if (IS_ERR(d)) return PTR_ERR(d); + if (d_is_positive(d)) { /* update watch filter fields */ watch->dev = d->d_sb->s_dev; watch->ino = d_backing_inode(d)->i_ino; } - inode_unlock(d_backing_inode(parent->dentry)); + dput(d); return 0; } -- 2.25.1
From: Jeff Layton <jlayton@kernel.org> stable inclusion from stable-v6.6.148 commit 26f32cae6496ca4a3d0841e4eba7efcb2e94b18a category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/16905 CVE: CVE-2026-68096 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=... -------------------------------- [ Upstream commit 125dfa218134df7cc112667e92984de9d8cd0bf6 ] inode->i_ino is being widened from unsigned long to u64. The audit subsystem uses unsigned long ino in struct fields, function parameters, and local variables that store inode numbers from arbitrary filesystems. On 32-bit platforms this truncates inode numbers that exceed 32 bits, which will cause incorrect audit log entries and broken watch/mark comparisons. Widen all audit ino fields, parameters, and locals to u64, and update the inode format string from %lu to %llu to match. Signed-off-by: Jeff Layton <jlayton@kernel.org> Link: https://patch.msgid.link/20260304-iino-u64-v3-2-2257ad83d372@kernel.org Acked-by: Paul Moore <paul@paul-moore.com> Signed-off-by: Christian Brauner <brauner@kernel.org> Stable-dep-of: 81905b5acbe7 ("audit: fix recursive locking deadlock in audit_dupe_exe()") Signed-off-by: Sasha Levin <sashal@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Yi Yang <yiyang13@huawei.com> --- include/linux/audit.h | 2 +- kernel/audit.h | 9 ++++----- kernel/audit_fsnotify.c | 2 +- kernel/audit_watch.c | 10 +++++----- kernel/auditsc.c | 4 ++-- 5 files changed, 13 insertions(+), 14 deletions(-) diff --git a/include/linux/audit.h b/include/linux/audit.h index 625210306813..944841de21a5 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -16,7 +16,7 @@ #include <uapi/linux/netfilter/nf_tables.h> #include <uapi/linux/fanotify.h> -#define AUDIT_INO_UNSET ((unsigned long)-1) +#define AUDIT_INO_UNSET ((u64)-1) #define AUDIT_DEV_UNSET ((dev_t)-1) struct audit_sig_info { diff --git a/kernel/audit.h b/kernel/audit.h index 8186b14f0b36..0a2a51c85452 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -76,7 +76,7 @@ struct audit_names { int name_len; /* number of chars to log */ bool hidden; /* don't log this record */ - unsigned long ino; + u64 ino; dev_t dev; umode_t mode; kuid_t uid; @@ -223,9 +223,9 @@ extern int auditd_test_task(struct task_struct *task); #define AUDIT_INODE_BUCKETS 32 extern struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS]; -static inline int audit_hash_ino(u32 ino) +static inline int audit_hash_ino(u64 ino) { - return (ino & (AUDIT_INODE_BUCKETS-1)); + return ((u32)ino & (AUDIT_INODE_BUCKETS-1)); } /* Indicates that audit should log the full pathname. */ @@ -275,8 +275,7 @@ extern int audit_to_watch(struct audit_krule *krule, char *path, int len, extern int audit_add_watch(struct audit_krule *krule, struct list_head **list); extern void audit_remove_watch_rule(struct audit_krule *krule); extern char *audit_watch_path(struct audit_watch *watch); -extern int audit_watch_compare(struct audit_watch *watch, unsigned long ino, - dev_t dev); +extern int audit_watch_compare(struct audit_watch *watch, u64 ino, dev_t dev); extern struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pathname, int len); diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c index 2b237895157d..35753fb9029a 100644 --- a/kernel/audit_fsnotify.c +++ b/kernel/audit_fsnotify.c @@ -25,7 +25,7 @@ */ struct audit_fsnotify_mark { dev_t dev; /* associated superblock device */ - unsigned long ino; /* associated inode number */ + u64 ino; /* associated inode number */ char *path; /* insertion path */ struct fsnotify_mark mark; /* fsnotify mark on the inode */ struct audit_krule *rule; diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 60f5daebc5ef..c3a665fd635e 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -37,7 +37,7 @@ struct audit_watch { refcount_t count; /* reference count */ dev_t dev; /* associated superblock device */ char *path; /* insertion path */ - unsigned long ino; /* associated inode number */ + u64 ino; /* associated inode number */ struct audit_parent *parent; /* associated parent */ struct list_head wlist; /* entry in parent->watches list */ struct list_head rules; /* anchor for krule->rlist */ @@ -125,7 +125,7 @@ char *audit_watch_path(struct audit_watch *watch) return watch->path; } -int audit_watch_compare(struct audit_watch *watch, unsigned long ino, dev_t dev) +int audit_watch_compare(struct audit_watch *watch, u64 ino, dev_t dev) { return (watch->ino != AUDIT_INO_UNSET) && (watch->ino == ino) && @@ -285,7 +285,7 @@ static void audit_update_watch(struct audit_parent *parent, list_del(&oentry->rule.list); audit_panic("error updating watch, removing"); } else { - int h = audit_hash_ino((u32)ino); + int h = audit_hash_ino(ino); /* * nentry->rule.watch == oentry->rule.watch so @@ -439,7 +439,7 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list) audit_add_to_parent(krule, parent); - h = audit_hash_ino((u32)watch->ino); + h = audit_hash_ino(watch->ino); *list = &audit_inode_hash[h]; error: path_put(&parent_path); @@ -527,7 +527,7 @@ int audit_dupe_exe(struct audit_krule *new, struct audit_krule *old) int audit_exe_compare(struct task_struct *tsk, struct audit_fsnotify_mark *mark) { struct file *exe_file; - unsigned long ino; + u64 ino; dev_t dev; /* only do exe filtering if we are recording @current events/records */ diff --git a/kernel/auditsc.c b/kernel/auditsc.c index c3237f79e063..f48f91f380ff 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -884,7 +884,7 @@ static int audit_filter_inode_name(struct task_struct *tsk, struct audit_names *n, struct audit_context *ctx) { - int h = audit_hash_ino((u32)n->ino); + int h = audit_hash_ino(n->ino); struct list_head *list = &audit_inode_hash[h]; return __audit_filter_op(tsk, ctx, list, n, ctx->major); @@ -1549,7 +1549,7 @@ static void audit_log_name(struct audit_context *context, struct audit_names *n, audit_log_format(ab, " name=(null)"); if (n->ino != AUDIT_INO_UNSET) - audit_log_format(ab, " inode=%lu dev=%02x:%02x mode=%#ho ouid=%u ogid=%u rdev=%02x:%02x", + audit_log_format(ab, " inode=%llu dev=%02x:%02x mode=%#ho ouid=%u ogid=%u rdev=%02x:%02x", n->ino, MAJOR(n->dev), MINOR(n->dev), -- 2.25.1
From: Ricardo Robaina <rrobaina@redhat.com> stable inclusion from stable-v6.6.148 commit df550e88009a6c723b1567bd31b9ff50d0014a3d category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/16905 CVE: CVE-2026-68096 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=... -------------------------------- [ Upstream commit 8b226771014beab1292081151a99530886ce54b4 ] Address checkpatch.pl warning below, across the audit subsystem: WARNING: Prefer 'unsigned int' to bare use of 'unsigned' Minor cleanup, no functional changes. Signed-off-by: Ricardo Robaina <rrobaina@redhat.com> Signed-off-by: Paul Moore <paul@paul-moore.com> Stable-dep-of: 81905b5acbe7 ("audit: fix recursive locking deadlock in audit_dupe_exe()") Signed-off-by: Sasha Levin <sashal@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Yi Yang <yiyang13@huawei.com> --- include/linux/audit.h | 4 ++-- include/linux/audit_arch.h | 12 ++++++------ kernel/audit.c | 2 +- kernel/audit.h | 2 +- kernel/audit_tree.c | 2 +- kernel/auditfilter.c | 8 ++++---- kernel/auditsc.c | 2 +- lib/compat_audit.c | 12 ++++++------ 8 files changed, 22 insertions(+), 22 deletions(-) diff --git a/include/linux/audit.h b/include/linux/audit.h index 944841de21a5..2da263b48342 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -122,8 +122,8 @@ enum audit_nfcfgop { AUDIT_NFT_OP_INVALID, }; -extern int __init audit_register_class(int class, unsigned *list); -extern int audit_classify_syscall(int abi, unsigned syscall); +extern int __init audit_register_class(int class, unsigned int *list); +extern int audit_classify_syscall(int abi, unsigned int syscall); extern int audit_classify_arch(int arch); /* audit_names->type values */ diff --git a/include/linux/audit_arch.h b/include/linux/audit_arch.h index 2b8153791e6a..a35069a6c15d 100644 --- a/include/linux/audit_arch.h +++ b/include/linux/audit_arch.h @@ -21,13 +21,13 @@ enum auditsc_class_t { AUDITSC_NVALS /* count */ }; -extern int audit_classify_compat_syscall(int abi, unsigned syscall); +extern int audit_classify_compat_syscall(int abi, unsigned int syscall); /* only for compat system calls */ -extern unsigned compat_write_class[]; -extern unsigned compat_read_class[]; -extern unsigned compat_dir_class[]; -extern unsigned compat_chattr_class[]; -extern unsigned compat_signal_class[]; +extern unsigned int compat_write_class[]; +extern unsigned int compat_read_class[]; +extern unsigned int compat_dir_class[]; +extern unsigned int compat_chattr_class[]; +extern unsigned int compat_signal_class[]; #endif diff --git a/kernel/audit.c b/kernel/audit.c index 672bb4b30fa9..908fd188bf62 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1989,7 +1989,7 @@ static void audit_log_vformat(struct audit_buffer *ab, const char *fmt, * here and AUDIT_BUFSIZ is at least 1024, then we can * log everything that printk could have logged. */ avail = audit_expand(ab, - max_t(unsigned, AUDIT_BUFSIZ, 1+len-avail)); + max_t(unsigned int, AUDIT_BUFSIZ, 1+len-avail)); if (!avail) goto out_va_end; len = vsnprintf(skb_tail_pointer(skb), avail, fmt, args2); diff --git a/kernel/audit.h b/kernel/audit.h index 0a2a51c85452..a6ba490f1456 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -231,7 +231,7 @@ static inline int audit_hash_ino(u64 ino) /* Indicates that audit should log the full pathname. */ #define AUDIT_NAME_FULL -1 -extern int audit_match_class(int class, unsigned syscall); +extern int audit_match_class(int class, unsigned int syscall); extern int audit_comparator(const u32 left, const u32 op, const u32 right); extern int audit_uid_comparator(kuid_t left, u32 op, kuid_t right); extern int audit_gid_comparator(kgid_t left, u32 op, kgid_t right); diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index e867c17d3f84..17125ac3a573 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -33,7 +33,7 @@ struct audit_chunk { struct audit_node { struct list_head list; struct audit_tree *owner; - unsigned index; /* index; upper bit indicates 'will prune' */ + unsigned int index; /* index; upper bit indicates 'will prune' */ } owners[]; }; diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 93fcefbcc5d1..a2d5831acdea 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -165,13 +165,13 @@ static inline int audit_to_inode(struct audit_krule *krule, static __u32 *classes[AUDIT_SYSCALL_CLASSES]; -int __init audit_register_class(int class, unsigned *list) +int __init audit_register_class(int class, unsigned int *list) { __u32 *p = kcalloc(AUDIT_BITMASK_SIZE, sizeof(__u32), GFP_KERNEL); if (!p) return -ENOMEM; while (*list != ~0U) { - unsigned n = *list++; + unsigned int n = *list++; if (n >= AUDIT_BITMASK_SIZE * 32 - AUDIT_SYSCALL_CLASSES) { kfree(p); return -EINVAL; @@ -186,7 +186,7 @@ int __init audit_register_class(int class, unsigned *list) return 0; } -int audit_match_class(int class, unsigned syscall) +int audit_match_class(int class, unsigned int syscall) { if (unlikely(syscall >= AUDIT_BITMASK_SIZE * 32)) return 0; @@ -237,7 +237,7 @@ static int audit_match_signal(struct audit_entry *entry) /* Common user-space to kernel rule translation. */ static inline struct audit_entry *audit_to_entry_common(struct audit_rule_data *rule) { - unsigned listnr; + unsigned int listnr; struct audit_entry *entry; int i, err; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index f48f91f380ff..bbd64037498b 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -150,7 +150,7 @@ static const struct audit_nfcfgop_tab audit_nfcfgs[] = { static int audit_match_perm(struct audit_context *ctx, int mask) { - unsigned n; + unsigned int n; if (unlikely(!ctx)) return 0; diff --git a/lib/compat_audit.c b/lib/compat_audit.c index 3d6b8996f027..fee1dfccd116 100644 --- a/lib/compat_audit.c +++ b/lib/compat_audit.c @@ -4,32 +4,32 @@ #include <linux/audit_arch.h> #include <asm/unistd32.h> -unsigned compat_dir_class[] = { +unsigned int compat_dir_class[] = { #include <asm-generic/audit_dir_write.h> ~0U }; -unsigned compat_read_class[] = { +unsigned int compat_read_class[] = { #include <asm-generic/audit_read.h> ~0U }; -unsigned compat_write_class[] = { +unsigned int compat_write_class[] = { #include <asm-generic/audit_write.h> ~0U }; -unsigned compat_chattr_class[] = { +unsigned int compat_chattr_class[] = { #include <asm-generic/audit_change_attr.h> ~0U }; -unsigned compat_signal_class[] = { +unsigned int compat_signal_class[] = { #include <asm-generic/audit_signal.h> ~0U }; -int audit_classify_compat_syscall(int abi, unsigned syscall) +int audit_classify_compat_syscall(int abi, unsigned int syscall) { switch (syscall) { #ifdef __NR_open -- 2.25.1
From: Ricardo Robaina <rrobaina@redhat.com> stable inclusion from stable-v6.6.148 commit 36eb77f14b4e6f2dc1008c1fabe31236397be27a category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/16905 CVE: CVE-2026-68096 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=... -------------------------------- [ Upstream commit 81905b5acbe77284734438df3fbec1158e6429a3 ] A deadlock occurs in the audit subsystem when duplicating executable-related rules. When a file is moved (e.g., via do_renameat2()), the VFS layer locks the parent directory (I_MUTEX_PARENT), which synchronously triggers an fsnotify_move event. If an existing executable audit rule matches the file being moved, the audit subsystem catches this event and calls audit_dupe_exe() to duplicate the watch and update the rule. Then, audit_alloc_mark() would call kern_path_parent() to resolve the path, leading to a blind attempt to acquire the exact same I_MUTEX_PARENT lock already held by the task, resulting in the following recursive locking deadlock: ============================================ WARNING: possible recursive locking detected 6.12.0-55.27.1.el10_0.x86_64+debug #1 Not tainted -------------------------------------------- mv/5099 is trying to acquire lock: ffff888132845358 (&inode->i_sb->s_type->i_mutex_dir_key/1){+.+.}-{3:3}, at: __kern_path_locked+0x10a/0x2f0 but task is already holding lock: ffff888132846b58 (&inode->i_sb->s_type->i_mutex_dir_key/1){+.+.}-{3:3}, at: lock_two_directories+0x13f/0x2b0 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&inode->i_sb->s_type->i_mutex_dir_key/1); lock(&inode->i_sb->s_type->i_mutex_dir_key/1); *** DEADLOCK *** May be due to missing lock nesting notation 6 locks held by mv/5099: #0: ffff888112a9c440 (sb_writers#13) at: do_renameat2+0x34c/0xbc0 #1: ffff888112a9c790 (&type->s_vfs_rename_key#3) at: do_renameat2+0x415/0xbc0 #2: ffff888132846b58 (&inode->i_sb->s_type->i_mutex_dir_key/1) at: lock_two_directories+0x13f/0x2b0 #3: ffff888132845358 (&inode->i_sb->s_type->i_mutex_dir_key/5) at: lock_two_directories+0x175/0x2b0 #4: ffffffffb3a1fb10 (&fsnotify_mark_srcu) at: fsnotify+0x454/0x28a0 #5: ffffffffaf886230 (audit_filter_mutex) at: audit_update_watch+0x36/0x11e0 stack backtrace: Call Trace: <TASK> dump_stack_lvl+0x6f/0xb0 print_deadlock_bug.cold+0xbd/0xca validate_chain+0x83a/0xf00 __lock_acquire+0xcac/0x1d20 lock_acquire.part.0+0x11b/0x360 down_write_nested+0x9f/0x230 __kern_path_locked+0x10a/0x2f0 kern_path_locked+0x26/0x40 audit_alloc_mark+0xfb/0x4f0 audit_dupe_exe+0x6c/0xe0 audit_dupe_rule+0x6c2/0xc00 audit_update_watch+0x4cc/0x11e0 audit_watch_handle_event+0x12c/0x1b0 send_to_group+0x5d0/0x8b0 fsnotify+0x615/0x28a0 fsnotify_move+0x1d8/0x630 vfs_rename+0xdcd/0x1df0 do_renameat2+0x9d4/0xbc0 __x64_sys_renameat+0x192/0x260 do_syscall_64+0x92/0x180 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f0491fe8c4e Code: 0f 1f 40 00 48 8b 15 c1 e1 16 00 f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 f3 0f 1e fa 49 89 ca b8 08 01 00 00 0f 05 <48> 3d 00 f0 ff ff 77 0a c3 66 0f 1f 84 00 00 00 00 00 48 8b 15 89 RSP: 002b:00007ffc7210bf38 EFLAGS: 00000246 ORIG_RAX: 0000000000000108 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f0491fe8c4e RDX: 0000000000000003 RSI: 00007ffc7210e6c8 RDI: 00000000ffffff9c RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000001 R10: 00005575eb2dae2a R11: 0000000000000246 R12: 00005575eb2dae2a R13: 00007ffc7210e6c8 R14: 0000000000000003 R15: 00000000ffffff9c </TASK> The aforementioned deadlock can be consistently reproduced by running the script below: audit-dupe-exe-deadlock.sh -------------------------- #!/bin/bash auditctl -D mkdir -p /tmp/foo touch /tmp/file auditctl -a always,exit -F exe=/tmp/file -F path=/tmp/file -S all -k dr mv /tmp/file /tmp/foo/file rm -Rf /tmp/foo This patch fixes the issue by introducing struct audit_watch_ctx to pass the fsnotify event context down to audit_alloc_mark(). By utilizing the already-resolved directory inode provided by the event, we bypass the kern_path_parent() path resolution entirely, safely avoiding the recursive lock. Furthermore, it explicitly allows duplicate fsnotify marks (allow_dups = 1) during the rename update, allowing the new rule's mark to safely coexist with the old rule's mark until the old rule is freed. P.S.: This issue was identified and reproduced during a comprehensive code coverage analysis of the audit subsystem. The full report is available at the link below: https://people.redhat.com/rrobaina/audit-code-coverage-analysis.pdf P.P.S: With the permission of both Ricardo and Nathan, I've squashed a fixup patch from Nathan that addresses a compile time error when CONFIG_AUDITSYSCALL=n. Cc: stable@kernel.org Fixes: 34d99af52ad4 ("audit: implement audit by executable") Acked-by: Waiman Long <longman@redhat.com> Acked-by: Richard Guy Briggs <rgb@redhat.com> Signed-off-by: Nathan Chancellor <nathan@kernel.org> Signed-off-by: Ricardo Robaina <rrobaina@redhat.com> [PM: move link metadata into the msg, apply fix from NC] Signed-off-by: Paul Moore <paul@paul-moore.com> Signed-off-by: Sasha Levin <sashal@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Yi Yang <yiyang13@huawei.com> --- kernel/audit.h | 17 ++++++++++++----- kernel/audit_fsnotify.c | 32 +++++++++++++++++++++++--------- kernel/audit_watch.c | 25 +++++++++++++++++-------- kernel/auditfilter.c | 9 +++++---- 4 files changed, 57 insertions(+), 26 deletions(-) diff --git a/kernel/audit.h b/kernel/audit.h index a6ba490f1456..300bece310e0 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -254,8 +254,13 @@ extern int audit_del_rule(struct audit_entry *entry); extern void audit_free_rule_rcu(struct rcu_head *head); extern struct list_head audit_filter_list[]; -extern struct audit_entry *audit_dupe_rule(struct audit_krule *old); +struct audit_watch_ctx { + struct inode *dir; + struct inode *child; +}; +extern struct audit_entry *audit_dupe_rule(struct audit_krule *old, + struct audit_watch_ctx *ctx); extern void audit_log_d_path_exe(struct audit_buffer *ab, struct mm_struct *mm); @@ -278,13 +283,15 @@ extern char *audit_watch_path(struct audit_watch *watch); extern int audit_watch_compare(struct audit_watch *watch, u64 ino, dev_t dev); extern struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, - char *pathname, int len); + char *pathname, int len, + struct audit_watch_ctx *ctx); extern char *audit_mark_path(struct audit_fsnotify_mark *mark); extern void audit_remove_mark(struct audit_fsnotify_mark *audit_mark); extern void audit_remove_mark_rule(struct audit_krule *krule); extern int audit_mark_compare(struct audit_fsnotify_mark *mark, u64 ino, dev_t dev); -extern int audit_dupe_exe(struct audit_krule *new, struct audit_krule *old); +extern int audit_dupe_exe(struct audit_krule *new, struct audit_krule *old, + struct audit_watch_ctx *ctx); extern int audit_exe_compare(struct task_struct *tsk, struct audit_fsnotify_mark *mark); @@ -315,13 +322,13 @@ extern struct list_head *audit_killed_trees(void); #define audit_watch_path(w) "" #define audit_watch_compare(w, i, d) 0 -#define audit_alloc_mark(k, p, l) (ERR_PTR(-EINVAL)) +#define audit_alloc_mark(k, p, l, c) (ERR_PTR(-EINVAL)) #define audit_mark_path(m) "" #define audit_remove_mark(m) do { } while (0) #define audit_remove_mark_rule(k) do { } while (0) #define audit_mark_compare(m, i, d) 0 #define audit_exe_compare(t, m) (-EINVAL) -#define audit_dupe_exe(n, o) (-EINVAL) +#define audit_dupe_exe(n, o, c) (-EINVAL) #define audit_remove_tree_rule(rule) BUG() #define audit_add_tree_rule(rule) -EINVAL diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c index 35753fb9029a..e62066bf0b0a 100644 --- a/kernel/audit_fsnotify.c +++ b/kernel/audit_fsnotify.c @@ -71,19 +71,30 @@ static void audit_update_mark(struct audit_fsnotify_mark *audit_mark, audit_mark->ino = inode ? inode->i_ino : AUDIT_INO_UNSET; } -struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pathname, int len) +struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pathname, + int len, struct audit_watch_ctx *ctx) { struct audit_fsnotify_mark *audit_mark; struct path path; struct dentry *dentry; - int ret; + struct inode *dir, *child; + int ret, allow_dups; if (pathname[0] != '/' || pathname[len-1] == '/') return ERR_PTR(-EINVAL); - dentry = kern_path_parent(pathname, &path); - if (IS_ERR(dentry)) - return ERR_CAST(dentry); /* returning an error */ + if (!ctx) { + dentry = kern_path_parent(pathname, &path); + if (IS_ERR(dentry)) + return ERR_CAST(dentry); /* returning an error */ + dir = d_inode(path.dentry); + child = d_inode(dentry); + allow_dups = 0; + } else { + dir = ctx->dir; + child = ctx->child; + allow_dups = 1; + } audit_mark = kzalloc(sizeof(*audit_mark), GFP_KERNEL); if (unlikely(!audit_mark)) { @@ -94,18 +105,21 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa fsnotify_init_mark(&audit_mark->mark, audit_fsnotify_group); audit_mark->mark.mask = AUDIT_FS_EVENTS; audit_mark->path = pathname; - audit_update_mark(audit_mark, dentry->d_inode); audit_mark->rule = krule; - ret = fsnotify_add_inode_mark(&audit_mark->mark, path.dentry->d_inode, 0); + audit_update_mark(audit_mark, child); + ret = fsnotify_add_inode_mark(&audit_mark->mark, dir, allow_dups); + if (ret < 0) { audit_mark->path = NULL; fsnotify_put_mark(&audit_mark->mark); audit_mark = ERR_PTR(ret); } out: - dput(dentry); - path_put(&path); + if (!ctx) { + dput(dentry); + path_put(&path); + } return audit_mark; } diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index c3a665fd635e..4a7cbb891941 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -244,7 +244,8 @@ static void audit_watch_log_rule_change(struct audit_krule *r, struct audit_watc /* Update inode info in audit rules based on filesystem event. */ static void audit_update_watch(struct audit_parent *parent, const struct qstr *dname, dev_t dev, - u64 ino, unsigned int invalidating) + u64 ino, unsigned int invalidating, + struct audit_watch_ctx *ctx) { struct audit_watch *owatch, *nwatch, *nextw; struct audit_krule *r, *nextr; @@ -280,7 +281,7 @@ static void audit_update_watch(struct audit_parent *parent, list_del(&oentry->rule.rlist); list_del_rcu(&oentry->list); - nentry = audit_dupe_rule(&oentry->rule); + nentry = audit_dupe_rule(&oentry->rule, ctx); if (IS_ERR(nentry)) { list_del(&oentry->rule.list); audit_panic("error updating watch, removing"); @@ -479,10 +480,17 @@ static int audit_watch_handle_event(struct fsnotify_mark *inode_mark, u32 mask, if (WARN_ON_ONCE(inode_mark->group != audit_watch_group)) return 0; - if (mask & (FS_CREATE|FS_MOVED_TO) && inode) - audit_update_watch(parent, dname, inode->i_sb->s_dev, inode->i_ino, 0); - else if (mask & (FS_DELETE|FS_MOVED_FROM)) - audit_update_watch(parent, dname, AUDIT_DEV_UNSET, AUDIT_INO_UNSET, 1); + if (mask & (FS_CREATE|FS_MOVED_TO) && inode) { + struct audit_watch_ctx ctx = { .dir = dir, .child = inode }; + + audit_update_watch(parent, dname, inode->i_sb->s_dev, inode->i_ino, 0, + &ctx); + } else if (mask & (FS_DELETE|FS_MOVED_FROM)) { + struct audit_watch_ctx ctx = { .dir = dir, .child = NULL }; + + audit_update_watch(parent, dname, AUDIT_DEV_UNSET, AUDIT_INO_UNSET, 1, + &ctx); + } else if (mask & (FS_DELETE_SELF|FS_UNMOUNT|FS_MOVE_SELF)) audit_remove_parent_watches(parent); @@ -505,7 +513,8 @@ static int __init audit_watch_init(void) } device_initcall(audit_watch_init); -int audit_dupe_exe(struct audit_krule *new, struct audit_krule *old) +int audit_dupe_exe(struct audit_krule *new, struct audit_krule *old, + struct audit_watch_ctx *ctx) { struct audit_fsnotify_mark *audit_mark; char *pathname; @@ -514,7 +523,7 @@ int audit_dupe_exe(struct audit_krule *new, struct audit_krule *old) if (!pathname) return -ENOMEM; - audit_mark = audit_alloc_mark(new, pathname, strlen(pathname)); + audit_mark = audit_alloc_mark(new, pathname, strlen(pathname), ctx); if (IS_ERR(audit_mark)) { kfree(pathname); return PTR_ERR(audit_mark); diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index a2d5831acdea..538f5c640f7c 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -590,7 +590,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, err = PTR_ERR(str); goto exit_free; } - audit_mark = audit_alloc_mark(&entry->rule, str, f_val); + audit_mark = audit_alloc_mark(&entry->rule, str, f_val, NULL); if (IS_ERR(audit_mark)) { kfree(str); err = PTR_ERR(audit_mark); @@ -818,7 +818,8 @@ static inline int audit_dupe_lsm_field(struct audit_field *df, * rule with the new rule in the filterlist, then free the old rule. * The rlist element is undefined; list manipulations are handled apart from * the initial copy. */ -struct audit_entry *audit_dupe_rule(struct audit_krule *old) +struct audit_entry *audit_dupe_rule(struct audit_krule *old, + struct audit_watch_ctx *ctx) { u32 fcount = old->field_count; struct audit_entry *entry; @@ -877,7 +878,7 @@ struct audit_entry *audit_dupe_rule(struct audit_krule *old) new->filterkey = fk; break; case AUDIT_EXE: - err = audit_dupe_exe(new, old); + err = audit_dupe_exe(new, old, ctx); break; } if (err) { @@ -1410,7 +1411,7 @@ static int update_lsm_rule(struct audit_krule *r) if (!security_audit_rule_known(r)) return 0; - nentry = audit_dupe_rule(r); + nentry = audit_dupe_rule(r, NULL); if (entry->rule.exe) audit_remove_mark(entry->rule.exe); if (IS_ERR(nentry)) { -- 2.25.1
反馈： 您发送到kernel@openeuler.org的补丁/补丁集，已成功转换为PR！ PR链接地址： https://atomgit.com/openeuler/kernel/merge_requests/27291 邮件列表地址：https://mailweb.openeuler.org/archives/list/kernel@openeuler.org/message/V7O... FeedBack: The patch(es) which you have sent to kernel@openeuler.org mailing list has been converted to a pull request successfully! Pull request link: https://atomgit.com/openeuler/kernel/merge_requests/27291 Mailing list address: https://mailweb.openeuler.org/archives/list/kernel@openeuler.org/message/V7O...
participants (2)
-
patchwork bot -
Yi Yang