@@ -3034,7 +3034,8 @@ static const struct inode_operations proc_tgid_base_inode_operations = {
.permission = proc_pid_permission,
};
-static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid)
+static void proc_flush_task_mnt_root(struct dentry *mnt_root,
+ pid_t pid, pid_t tgid)
{
struct dentry *dentry, *leader, *dir;
char buf[PROC_NUMBUF];
@@ -3043,7 +3044,7 @@ static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid)
name.name = buf;
name.len = snprintf(buf, sizeof(buf), "%d", pid);
/* no ->d_hash() rejects on procfs */
- dentry = d_hash_and_lookup(mnt->mnt_root, &name);
+ dentry = d_hash_and_lookup(mnt_root, &name);
if (dentry) {
d_invalidate(dentry);
dput(dentry);
@@ -3054,7 +3055,7 @@ static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid)
name.name = buf;
name.len = snprintf(buf, sizeof(buf), "%d", tgid);
- leader = d_hash_and_lookup(mnt->mnt_root, &name);
+ leader = d_hash_and_lookup(mnt_root, &name);
if (!leader)
goto out;
@@ -3109,14 +3110,30 @@ void proc_flush_task(struct task_struct *task)
int i;
struct pid *pid, *tgid;
struct upid *upid;
+ struct proc_fs_info *fs_info_entry;
+ struct pid_namespace *pid_ns;
+ struct dentry *mnt_root;
pid = task_pid(task);
tgid = task_tgid(task);
for (i = 0; i <= pid->level; i++) {
upid = &pid->numbers[i];
- proc_flush_task_mnt(upid->ns->proc_mnt, upid->nr,
- tgid->numbers[i].nr);
+ pid_ns = upid->ns;
+
+ pidns_proc_lock_shared(pid_ns);
+ list_for_each_entry(fs_info_entry, &pid_ns->procfs_mounts,
+ pidns_entry) {
+ if (proc_fs_newinstance(fs_info_entry)) {
+ mnt_root = fs_info_entry->sb->s_root;
+ proc_flush_task_mnt_root(mnt_root, upid->nr,
+ tgid->numbers[i].nr);
+ }
+ }
+ pidns_proc_unlock_shared(pid_ns);
+
+ mnt_root = pid_ns->proc_mnt->mnt_root;
+ proc_flush_task_mnt_root(mnt_root, upid->nr, tgid->numbers[i].nr);
}
}
@@ -484,10 +484,17 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
int proc_fill_super(struct super_block *s, void *data, int silent)
{
struct proc_fs_info *fs_info = proc_sb(s);
+ struct pid_namespace *ns = get_pid_ns(fs_info->pid_ns);
struct inode *root_inode;
int ret;
- get_pid_ns(fs_info->pid_ns);
+ fs_info->sb = s;
+
+ if (proc_fs_newinstance(fs_info)) {
+ pidns_proc_lock(ns);
+ list_add_tail(&fs_info->pidns_entry, &ns->procfs_mounts);
+ pidns_proc_unlock(ns);
+ }
if (!proc_parse_options(data, fs_info))
return -EINVAL;
@@ -259,6 +259,13 @@ static void proc_kill_sb(struct super_block *sb)
dput(fs_info->proc_self);
if (fs_info->proc_thread_self)
dput(fs_info->proc_thread_self);
+
+ if (proc_fs_newinstance(fs_info)) {
+ pidns_proc_lock(ns);
+ list_del(&fs_info->pidns_entry);
+ pidns_proc_unlock(ns);
+ }
+
kill_anon_super(sb);
put_pid_ns(ns);
kfree(fs_info);
@@ -374,6 +381,9 @@ int pid_ns_prepare_proc(struct pid_namespace *ns)
return PTR_ERR(mnt);
ns->proc_mnt = mnt;
+ init_rwsem(&ns->rw_procfs_mnts);
+ INIT_LIST_HEAD(&ns->procfs_mounts);
+
return 0;
}
@@ -26,6 +26,15 @@ struct pid_namespace {
struct pid_namespace *parent;
#ifdef CONFIG_PROC_FS
struct vfsmount *proc_mnt; /* Internal proc mounted during each new pidns */
+
+ /* Serialize separated procfs access from super block create/destory */
+ struct rw_semaphore rw_procfs_mnts;
+
+ /*
+ * List of separated procfs mounts, used to invalidate task dentry
+ * from all the related procfs mounts.
+ */
+ struct list_head procfs_mounts;
#endif
#ifdef CONFIG_BSD_PROCESS_ACCT
struct fs_pin *bacct;
@@ -90,4 +99,44 @@ extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk);
void pidhash_init(void);
void pid_idr_init(void);
+#ifdef CONFIG_PROC_FS
+static inline void pidns_proc_lock(struct pid_namespace *pid_ns)
+{
+ down_write(&pid_ns->rw_procfs_mnts);
+}
+
+static inline void pidns_proc_unlock(struct pid_namespace *pid_ns)
+{
+ up_write(&pid_ns->rw_procfs_mnts);
+}
+
+static inline void pidns_proc_lock_shared(struct pid_namespace *pid_ns)
+{
+ down_read(&pid_ns->rw_procfs_mnts);
+}
+
+static inline void pidns_proc_unlock_shared(struct pid_namespace *pid_ns)
+{
+ up_read(&pid_ns->rw_procfs_mnts);
+}
+#else /* !CONFIG_PROC_FS */
+
+static inline void pidns_proc_lock(struct pid_namespace *pid_ns)
+{
+}
+
+static inline void pidns_proc_unlock(struct pid_namespace *pid_ns)
+{
+}
+
+static inline void pidns_proc_lock_shared(struct pid_namespace *pid_ns)
+{
+}
+
+static inline void pidns_proc_unlock_shared(struct pid_namespace *pid_ns)
+{
+}
+
+#endif /* CONFIG_PROC_FS */
+
#endif /* _LINUX_PID_NS_H */
@@ -24,7 +24,9 @@ enum { /* definitions for 'pids' mount option */
};
struct proc_fs_info {
+ struct super_block *sb;
struct pid_namespace *pid_ns;
+ struct list_head pidns_entry; /* Node in procfs_mounts of pidns */
struct dentry *proc_self; /* For /proc/self/ */
struct dentry *proc_thread_self; /* For /proc/thread-self/ */
bool newinstance; /* Flag for new separated instances */
Flush dcache entries of a task when it terminates. The task may have showed up in multiple procfs mounts per pid namespace, and we need to walk the mounts and invalidate any left entires. Cc: Kees Cook <keescook@chromium.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Alexey Gladkov <gladkov.alexey@gmail.com> Signed-off-by: Djalal Harouni <tixxdz@gmail.com> --- fs/proc/base.c | 27 +++++++++++++++++++----- fs/proc/inode.c | 9 +++++++- fs/proc/root.c | 10 +++++++++ include/linux/pid_namespace.h | 49 +++++++++++++++++++++++++++++++++++++++++++ include/linux/proc_fs.h | 2 ++ 5 files changed, 91 insertions(+), 6 deletions(-)