4 Configuring procfs
4.1 Mount options
+ 5 Filesystem behavior
+
Preface
=======
========= ========================================================
hidepid= Set /proc/<pid>/ access mode.
gid= Set the group authorized to learn processes information.
+ subset= Show only the specified subset of procfs.
========= ========================================================
-hidepid=0 means classic mode - everybody may access all /proc/<pid>/ directories
-(default).
-
-hidepid=1 means users may not access any /proc/<pid>/ directories but their
-own. Sensitive files like cmdline, sched*, status are now protected against
-other users. This makes it impossible to learn whether any user runs
-specific program (given the program doesn't reveal itself by its behaviour).
-As an additional bonus, as /proc/<pid>/cmdline is unaccessible for other users,
-poorly written programs passing sensitive information via program arguments are
-now protected against local eavesdroppers.
-
-hidepid=2 means hidepid=1 plus all /proc/<pid>/ will be fully invisible to other
-users. It doesn't mean that it hides a fact whether a process with a specific
-pid value exists (it can be learned by other means, e.g. by "kill -0 $PID"),
-but it hides process' uid and gid, which may be learned by stat()'ing
-/proc/<pid>/ otherwise. It greatly complicates an intruder's task of gathering
-information about running processes, whether some daemon runs with elevated
-privileges, whether other user runs some sensitive program, whether other users
-run any program at all, etc.
+hidepid=off or hidepid=0 means classic mode - everybody may access all
+/proc/<pid>/ directories (default).
+
+hidepid=noaccess or hidepid=1 means users may not access any /proc/<pid>/
+directories but their own. Sensitive files like cmdline, sched*, status are now
+protected against other users. This makes it impossible to learn whether any
+user runs specific program (given the program doesn't reveal itself by its
+behaviour). As an additional bonus, as /proc/<pid>/cmdline is unaccessible for
+other users, poorly written programs passing sensitive information via program
+arguments are now protected against local eavesdroppers.
+
+hidepid=invisible or hidepid=2 means hidepid=1 plus all /proc/<pid>/ will be
+fully invisible to other users. It doesn't mean that it hides a fact whether a
+process with a specific pid value exists (it can be learned by other means, e.g.
+by "kill -0 $PID"), but it hides process' uid and gid, which may be learned by
+stat()'ing /proc/<pid>/ otherwise. It greatly complicates an intruder's task of
+gathering information about running processes, whether some daemon runs with
+elevated privileges, whether other user runs some sensitive program, whether
+other users run any program at all, etc.
+
+hidepid=ptraceable or hidepid=4 means that procfs should only contain
+/proc/<pid>/ directories that the caller can ptrace.
gid= defines a group authorized to learn processes information otherwise
prohibited by hidepid=. If you use some daemon like identd which needs to learn
information about processes information, just add identd to this group.
+
+subset=pid hides all top level files and directories in the procfs that
+are not related to tasks.
+
+5 Filesystem behavior
+----------------------------
+
+Originally, before the advent of pid namepsace, procfs was a global file
+system. It means that there was only one procfs instance in the system.
+
+When pid namespace was added, a separate procfs instance was mounted in
+each pid namespace. So, procfs mount options are global among all
+mountpoints within the same namespace.
+
+::
+
+# grep ^proc /proc/mounts
+proc /proc proc rw,relatime,hidepid=2 0 0
+
+# strace -e mount mount -o hidepid=1 -t proc proc /tmp/proc
+mount("proc", "/tmp/proc", "proc", 0, "hidepid=1") = 0
++++ exited with 0 +++
+
+# grep ^proc /proc/mounts
+proc /proc proc rw,relatime,hidepid=2 0 0
+proc /tmp/proc proc rw,relatime,hidepid=2 0 0
+
+and only after remounting procfs mount options will change at all
+mountpoints.
+
+# mount -o remount,hidepid=1 -t proc proc /tmp/proc
+
+# grep ^proc /proc/mounts
+proc /proc proc rw,relatime,hidepid=1 0 0
+proc /tmp/proc proc rw,relatime,hidepid=1 0 0
+
+This behavior is different from the behavior of other filesystems.
+
+The new procfs behavior is more like other filesystems. Each procfs mount
+creates a new procfs instance. Mount options affect own procfs instance.
+It means that it became possible to have several procfs instances
+displaying tasks with different filtering options in one pid namespace.
+
+# mount -o hidepid=invisible -t proc proc /proc
+# mount -o hidepid=noaccess -t proc proc /tmp/proc
+# grep ^proc /proc/mounts
+proc /proc proc rw,relatime,hidepid=invisible 0 0
+proc /tmp/proc proc rw,relatime,hidepid=noaccess 0 0
tsk->start_boottime = leader->start_boottime;
BUG_ON(!same_thread_group(leader, tsk));
- BUG_ON(has_group_leader_pid(tsk));
/*
* An exec() starts a new thread group with the
* TGID of the previous thread group. Rehash the
/* Become a process group leader with the old leader's pid.
* The old leader becomes a thread of the this thread group.
- * Note: The old leader also uses this pid until release_task
- * is called. Odd but simple and correct.
*/
- tsk->pid = leader->pid;
- change_pid(tsk, PIDTYPE_PID, task_pid(leader));
+ exchange_tids(tsk, leader);
transfer_pid(leader, tsk, PIDTYPE_TGID);
transfer_pid(leader, tsk, PIDTYPE_PGID);
transfer_pid(leader, tsk, PIDTYPE_SID);
{
struct inode *inode = NULL;
unsigned int fl_pid;
- struct pid_namespace *proc_pidns = file_inode(f->file)->i_sb->s_fs_info;
+ struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb);
fl_pid = locks_translate_pid(fl, proc_pidns);
/*
{
struct locks_iterator *iter = f->private;
struct file_lock *fl, *bfl;
- struct pid_namespace *proc_pidns = file_inode(f->file)->i_sb->s_fs_info;
+ struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb);
fl = hlist_entry(v, struct file_lock, fl_link);
{
struct inode *inode = file_inode(seq->file);
- seq_printf(seq, "%d ", pid_nr_ns(v, proc_pid_ns(inode)));
+ seq_printf(seq, "%d ", pid_nr_ns(v, proc_pid_ns(inode->i_sb)));
return 0;
}
* May current process learn task's sched/cmdline info (for hide_pid_min=1)
* or euid/egid (for hide_pid_min=2)?
*/
-static bool has_pid_permissions(struct pid_namespace *pid,
+static bool has_pid_permissions(struct proc_fs_info *fs_info,
struct task_struct *task,
- int hide_pid_min)
+ enum proc_hidepid hide_pid_min)
{
- if (pid->hide_pid < hide_pid_min)
+ /*
+ * If 'hidpid' mount option is set force a ptrace check,
+ * we indicate that we are using a filesystem syscall
+ * by passing PTRACE_MODE_READ_FSCREDS
+ */
+ if (fs_info->hide_pid == HIDEPID_NOT_PTRACEABLE)
+ return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
+
+ if (fs_info->hide_pid < hide_pid_min)
return true;
- if (in_group_p(pid->pid_gid))
+ if (in_group_p(fs_info->pid_gid))
return true;
return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
}
static int proc_pid_permission(struct inode *inode, int mask)
{
- struct pid_namespace *pid = proc_pid_ns(inode);
+ struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb);
struct task_struct *task;
bool has_perms;
task = get_proc_task(inode);
if (!task)
return -ESRCH;
- has_perms = has_pid_permissions(pid, task, HIDEPID_NO_ACCESS);
+ has_perms = has_pid_permissions(fs_info, task, HIDEPID_NO_ACCESS);
put_task_struct(task);
if (!has_perms) {
- if (pid->hide_pid == HIDEPID_INVISIBLE) {
+ if (fs_info->hide_pid == HIDEPID_INVISIBLE) {
/*
* Let's make getdents(), stat(), and open()
* consistent with each other. If a process
static int proc_single_show(struct seq_file *m, void *v)
{
struct inode *inode = m->private;
- struct pid_namespace *ns = proc_pid_ns(inode);
+ struct pid_namespace *ns = proc_pid_ns(inode->i_sb);
struct pid *pid = proc_pid(inode);
struct task_struct *task;
int ret;
static int sched_show(struct seq_file *m, void *v)
{
struct inode *inode = m->private;
- struct pid_namespace *ns = proc_pid_ns(inode);
+ struct pid_namespace *ns = proc_pid_ns(inode->i_sb);
struct task_struct *p;
p = get_proc_task(inode);
u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
- struct pid_namespace *pid = proc_pid_ns(inode);
+ struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb);
struct task_struct *task;
generic_fillattr(inode, stat);
rcu_read_lock();
task = pid_task(proc_pid(inode), PIDTYPE_PID);
if (task) {
- if (!has_pid_permissions(pid, task, HIDEPID_INVISIBLE)) {
+ if (!has_pid_permissions(fs_info, task, HIDEPID_INVISIBLE)) {
rcu_read_unlock();
/*
* This doesn't prevent learning whether PID exists,
return -ENOMEM;
tp->pid = proc_pid(inode);
- tp->ns = proc_pid_ns(inode);
+ tp->ns = proc_pid_ns(inode->i_sb);
return 0;
}
{
struct task_struct *task;
unsigned tgid;
+ struct proc_fs_info *fs_info;
struct pid_namespace *ns;
struct dentry *result = ERR_PTR(-ENOENT);
if (tgid == ~0U)
goto out;
- ns = dentry->d_sb->s_fs_info;
+ fs_info = proc_sb_info(dentry->d_sb);
+ ns = fs_info->pid_ns;
rcu_read_lock();
task = find_task_by_pid_ns(tgid, ns);
if (task)
if (!task)
goto out;
+ /* Limit procfs to only ptraceable tasks */
+ if (fs_info->hide_pid == HIDEPID_NOT_PTRACEABLE) {
+ if (!has_pid_permissions(fs_info, task, HIDEPID_NO_ACCESS))
+ goto out_put_task;
+ }
+
result = proc_pid_instantiate(dentry, task, NULL);
+out_put_task:
put_task_struct(task);
out:
return result;
pid = find_ge_pid(iter.tgid, ns);
if (pid) {
iter.tgid = pid_nr_ns(pid, ns);
- iter.task = pid_task(pid, PIDTYPE_PID);
- /* What we to know is if the pid we have find is the
- * pid of a thread_group_leader. Testing for task
- * being a thread_group_leader is the obvious thing
- * todo but there is a window when it fails, due to
- * the pid transfer logic in de_thread.
- *
- * So we perform the straight forward test of seeing
- * if the pid we have found is the pid of a thread
- * group leader, and don't worry if the task we have
- * found doesn't happen to be a thread group leader.
- * As we don't care in the case of readdir.
- */
- if (!iter.task || !has_group_leader_pid(iter.task)) {
+ iter.task = pid_task(pid, PIDTYPE_TGID);
+ if (!iter.task) {
iter.tgid += 1;
goto retry;
}
int proc_pid_readdir(struct file *file, struct dir_context *ctx)
{
struct tgid_iter iter;
- struct pid_namespace *ns = proc_pid_ns(file_inode(file));
+ struct proc_fs_info *fs_info = proc_sb_info(file_inode(file)->i_sb);
+ struct pid_namespace *ns = proc_pid_ns(file_inode(file)->i_sb);
loff_t pos = ctx->pos;
if (pos >= PID_MAX_LIMIT + TGID_OFFSET)
return 0;
if (pos == TGID_OFFSET - 2) {
- struct inode *inode = d_inode(ns->proc_self);
+ struct inode *inode = d_inode(fs_info->proc_self);
if (!dir_emit(ctx, "self", 4, inode->i_ino, DT_LNK))
return 0;
ctx->pos = pos = pos + 1;
}
if (pos == TGID_OFFSET - 1) {
- struct inode *inode = d_inode(ns->proc_thread_self);
+ struct inode *inode = d_inode(fs_info->proc_thread_self);
if (!dir_emit(ctx, "thread-self", 11, inode->i_ino, DT_LNK))
return 0;
ctx->pos = pos = pos + 1;
unsigned int len;
cond_resched();
- if (!has_pid_permissions(ns, iter.task, HIDEPID_INVISIBLE))
+ if (!has_pid_permissions(fs_info, iter.task, HIDEPID_INVISIBLE))
continue;
len = snprintf(name, sizeof(name), "%u", iter.tgid);
struct task_struct *task;
struct task_struct *leader = get_proc_task(dir);
unsigned tid;
+ struct proc_fs_info *fs_info;
struct pid_namespace *ns;
struct dentry *result = ERR_PTR(-ENOENT);
if (tid == ~0U)
goto out;
- ns = dentry->d_sb->s_fs_info;
+ fs_info = proc_sb_info(dentry->d_sb);
+ ns = fs_info->pid_ns;
rcu_read_lock();
task = find_task_by_pid_ns(tid, ns);
if (task)
/* f_version caches the tgid value that the last readdir call couldn't
* return. lseek aka telldir automagically resets f_version to 0.
*/
- ns = proc_pid_ns(inode);
+ ns = proc_pid_ns(inode->i_sb);
tid = (int)file->f_version;
file->f_version = 0;
for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns);
struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
+ struct proc_fs_info *fs_info = proc_sb_info(dir->i_sb);
+
+ if (fs_info->pidonly == PROC_PIDONLY_ON)
+ return ERR_PTR(-ENOENT);
+
return proc_lookup_de(dir, dentry, PDE(dir));
}
int proc_readdir(struct file *file, struct dir_context *ctx)
{
struct inode *inode = file_inode(file);
+ struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb);
+
+ if (fs_info->pidonly == PROC_PIDONLY_ON)
+ return 1;
return proc_readdir_de(file, ctx, PDE(inode));
}
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/mount.h>
+#include <linux/bug.h>
#include <linux/uaccess.h>
deactivate_super(old_sb);
}
+static inline const char *hidepid2str(enum proc_hidepid v)
+{
+ switch (v) {
+ case HIDEPID_OFF: return "off";
+ case HIDEPID_NO_ACCESS: return "noaccess";
+ case HIDEPID_INVISIBLE: return "invisible";
+ case HIDEPID_NOT_PTRACEABLE: return "ptraceable";
+ }
+ WARN_ONCE(1, "bad hide_pid value: %d\n", v);
+ return "unknown";
+}
+
static int proc_show_options(struct seq_file *seq, struct dentry *root)
{
- struct super_block *sb = root->d_sb;
- struct pid_namespace *pid = sb->s_fs_info;
+ struct proc_fs_info *fs_info = proc_sb_info(root->d_sb);
- if (!gid_eq(pid->pid_gid, GLOBAL_ROOT_GID))
- seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, pid->pid_gid));
- if (pid->hide_pid != HIDEPID_OFF)
- seq_printf(seq, ",hidepid=%u", pid->hide_pid);
+ if (!gid_eq(fs_info->pid_gid, GLOBAL_ROOT_GID))
+ seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, fs_info->pid_gid));
+ if (fs_info->hide_pid != HIDEPID_OFF)
+ seq_printf(seq, ",hidepid=%s", hidepid2str(fs_info->hide_pid));
+ if (fs_info->pidonly != PROC_PIDONLY_OFF)
+ seq_printf(seq, ",subset=pid");
return 0;
}
static int proc_reg_open(struct inode *inode, struct file *file)
{
+ struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb);
struct proc_dir_entry *pde = PDE(inode);
int rv = 0;
typeof_member(struct proc_ops, proc_open) open;
return rv;
}
+ if (fs_info->pidonly == PROC_PIDONLY_ON)
+ return -ENOENT;
+
/*
* Ensure that
* 1) PDE's ->release hook will be called no matter what
struct proc_fs_context {
struct pid_namespace *pid_ns;
unsigned int mask;
- int hidepid;
+ enum proc_hidepid hidepid;
int gid;
+ enum proc_pidonly pidonly;
};
enum proc_param {
Opt_gid,
Opt_hidepid,
+ Opt_subset,
};
static const struct fs_parameter_spec proc_fs_parameters[] = {
fsparam_u32("gid", Opt_gid),
- fsparam_u32("hidepid", Opt_hidepid),
+ fsparam_string("hidepid", Opt_hidepid),
+ fsparam_string("subset", Opt_subset),
{}
};
+static inline int valid_hidepid(unsigned int value)
+{
+ return (value == HIDEPID_OFF ||
+ value == HIDEPID_NO_ACCESS ||
+ value == HIDEPID_INVISIBLE ||
+ value == HIDEPID_NOT_PTRACEABLE);
+}
+
+static int proc_parse_hidepid_param(struct fs_context *fc, struct fs_parameter *param)
+{
+ struct proc_fs_context *ctx = fc->fs_private;
+ struct fs_parameter_spec hidepid_u32_spec = fsparam_u32("hidepid", Opt_hidepid);
+ struct fs_parse_result result;
+ int base = (unsigned long)hidepid_u32_spec.data;
+
+ if (param->type != fs_value_is_string)
+ return invalf(fc, "proc: unexpected type of hidepid value\n");
+
+ if (!kstrtouint(param->string, base, &result.uint_32)) {
+ if (!valid_hidepid(result.uint_32))
+ return invalf(fc, "proc: unknown value of hidepid - %s\n", param->string);
+ ctx->hidepid = result.uint_32;
+ return 0;
+ }
+
+ if (!strcmp(param->string, "off"))
+ ctx->hidepid = HIDEPID_OFF;
+ else if (!strcmp(param->string, "noaccess"))
+ ctx->hidepid = HIDEPID_NO_ACCESS;
+ else if (!strcmp(param->string, "invisible"))
+ ctx->hidepid = HIDEPID_INVISIBLE;
+ else if (!strcmp(param->string, "ptraceable"))
+ ctx->hidepid = HIDEPID_NOT_PTRACEABLE;
+ else
+ return invalf(fc, "proc: unknown value of hidepid - %s\n", param->string);
+
+ return 0;
+}
+
+static int proc_parse_subset_param(struct fs_context *fc, char *value)
+{
+ struct proc_fs_context *ctx = fc->fs_private;
+
+ while (value) {
+ char *ptr = strchr(value, ',');
+
+ if (ptr != NULL)
+ *ptr++ = '\0';
+
+ if (*value != '\0') {
+ if (!strcmp(value, "pid")) {
+ ctx->pidonly = PROC_PIDONLY_ON;
+ } else {
+ return invalf(fc, "proc: unsupported subset option - %s\n", value);
+ }
+ }
+ value = ptr;
+ }
+
+ return 0;
+}
+
static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
struct proc_fs_context *ctx = fc->fs_private;
break;
case Opt_hidepid:
- ctx->hidepid = result.uint_32;
- if (ctx->hidepid < HIDEPID_OFF ||
- ctx->hidepid > HIDEPID_INVISIBLE)
- return invalfc(fc, "hidepid value must be between 0 and 2.\n");
+ if (proc_parse_hidepid_param(fc, param))
+ return -EINVAL;
+ break;
+
+ case Opt_subset:
+ if (proc_parse_subset_param(fc, param->string) < 0)
+ return -EINVAL;
break;
default:
return 0;
}
-static void proc_apply_options(struct super_block *s,
+static void proc_apply_options(struct proc_fs_info *fs_info,
struct fs_context *fc,
- struct pid_namespace *pid_ns,
struct user_namespace *user_ns)
{
struct proc_fs_context *ctx = fc->fs_private;
if (ctx->mask & (1 << Opt_gid))
- pid_ns->pid_gid = make_kgid(user_ns, ctx->gid);
+ fs_info->pid_gid = make_kgid(user_ns, ctx->gid);
if (ctx->mask & (1 << Opt_hidepid))
- pid_ns->hide_pid = ctx->hidepid;
+ fs_info->hide_pid = ctx->hidepid;
+ if (ctx->mask & (1 << Opt_subset))
+ fs_info->pidonly = ctx->pidonly;
}
static int proc_fill_super(struct super_block *s, struct fs_context *fc)
{
- struct pid_namespace *pid_ns = get_pid_ns(s->s_fs_info);
+ struct proc_fs_context *ctx = fc->fs_private;
struct inode *root_inode;
+ struct proc_fs_info *fs_info;
int ret;
- proc_apply_options(s, fc, pid_ns, current_user_ns());
+ fs_info = kzalloc(sizeof(*fs_info), GFP_KERNEL);
+ if (!fs_info)
+ return -ENOMEM;
+
+ fs_info->pid_ns = get_pid_ns(ctx->pid_ns);
+ proc_apply_options(fs_info, fc, current_user_ns());
/* User space would break if executables or devices appear on proc */
s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NOEXEC | SB_I_NODEV;
s->s_magic = PROC_SUPER_MAGIC;
s->s_op = &proc_sops;
s->s_time_gran = 1;
+ s->s_fs_info = fs_info;
/*
* procfs isn't actually a stacking filesystem; however, there is
* top of it
*/
s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;
-
+
/* procfs dentries and inodes don't require IO to create */
s->s_shrink.seeks = 0;
static int proc_reconfigure(struct fs_context *fc)
{
struct super_block *sb = fc->root->d_sb;
- struct pid_namespace *pid = sb->s_fs_info;
+ struct proc_fs_info *fs_info = proc_sb_info(sb);
sync_filesystem(sb);
- proc_apply_options(sb, fc, pid, current_user_ns());
+ proc_apply_options(fs_info, fc, current_user_ns());
return 0;
}
static int proc_get_tree(struct fs_context *fc)
{
- struct proc_fs_context *ctx = fc->fs_private;
-
- return get_tree_keyed(fc, proc_fill_super, ctx->pid_ns);
+ return get_tree_nodev(fc, proc_fill_super);
}
static void proc_fs_context_free(struct fs_context *fc)
static void proc_kill_sb(struct super_block *sb)
{
- struct pid_namespace *ns;
+ struct proc_fs_info *fs_info = proc_sb_info(sb);
- ns = (struct pid_namespace *)sb->s_fs_info;
- if (ns->proc_self)
- dput(ns->proc_self);
- if (ns->proc_thread_self)
- dput(ns->proc_thread_self);
- kill_anon_super(sb);
+ if (fs_info->proc_self)
+ dput(fs_info->proc_self);
- /* Make the pid namespace safe for the next mount of proc */
- ns->proc_self = NULL;
- ns->proc_thread_self = NULL;
- ns->pid_gid = GLOBAL_ROOT_GID;
- ns->hide_pid = 0;
+ if (fs_info->proc_thread_self)
+ dput(fs_info->proc_thread_self);
- put_pid_ns(ns);
+ kill_anon_super(sb);
+ put_pid_ns(fs_info->pid_ns);
+ kfree(fs_info);
}
static struct file_system_type proc_fs_type = {
struct inode *inode,
struct delayed_call *done)
{
- struct pid_namespace *ns = proc_pid_ns(inode);
+ struct pid_namespace *ns = proc_pid_ns(inode->i_sb);
pid_t tgid = task_tgid_nr_ns(current, ns);
char *name;
int proc_setup_self(struct super_block *s)
{
struct inode *root_inode = d_inode(s->s_root);
- struct pid_namespace *ns = proc_pid_ns(root_inode);
+ struct proc_fs_info *fs_info = proc_sb_info(s);
struct dentry *self;
int ret = -ENOMEM;
-
+
inode_lock(root_inode);
self = d_alloc_name(s->s_root, "self");
if (self) {
if (ret)
pr_err("proc_fill_super: can't allocate /proc/self\n");
else
- ns->proc_self = self;
+ fs_info->proc_self = self;
return ret;
}
struct inode *inode,
struct delayed_call *done)
{
- struct pid_namespace *ns = proc_pid_ns(inode);
+ struct pid_namespace *ns = proc_pid_ns(inode->i_sb);
pid_t tgid = task_tgid_nr_ns(current, ns);
pid_t pid = task_pid_nr_ns(current, ns);
char *name;
int proc_setup_thread_self(struct super_block *s)
{
struct inode *root_inode = d_inode(s->s_root);
- struct pid_namespace *ns = proc_pid_ns(root_inode);
+ struct proc_fs_info *fs_info = proc_sb_info(s);
struct dentry *thread_self;
int ret = -ENOMEM;
inode_unlock(root_inode);
if (ret)
- pr_err("proc_fill_super: can't allocate /proc/thread_self\n");
+ pr_err("proc_fill_super: can't allocate /proc/thread-self\n");
else
- ns->proc_thread_self = thread_self;
+ fs_info->proc_thread_self = thread_self;
return ret;
}
return res;
}
-struct proc_fs_info {
+struct proc_fs_opts {
int flag;
const char *str;
};
static int show_sb_opts(struct seq_file *m, struct super_block *sb)
{
- static const struct proc_fs_info fs_info[] = {
+ static const struct proc_fs_opts fs_opts[] = {
{ SB_SYNCHRONOUS, ",sync" },
{ SB_DIRSYNC, ",dirsync" },
{ SB_MANDLOCK, ",mand" },
{ SB_LAZYTIME, ",lazytime" },
{ 0, NULL }
};
- const struct proc_fs_info *fs_infop;
+ const struct proc_fs_opts *fs_infop;
- for (fs_infop = fs_info; fs_infop->flag; fs_infop++) {
+ for (fs_infop = fs_opts; fs_infop->flag; fs_infop++) {
if (sb->s_flags & fs_infop->flag)
seq_puts(m, fs_infop->str);
}
static void show_mnt_opts(struct seq_file *m, struct vfsmount *mnt)
{
- static const struct proc_fs_info mnt_info[] = {
+ static const struct proc_fs_opts mnt_opts[] = {
{ MNT_NOSUID, ",nosuid" },
{ MNT_NODEV, ",nodev" },
{ MNT_NOEXEC, ",noexec" },
{ MNT_RELATIME, ",relatime" },
{ 0, NULL }
};
- const struct proc_fs_info *fs_infop;
+ const struct proc_fs_opts *fs_infop;
- for (fs_infop = mnt_info; fs_infop->flag; fs_infop++) {
+ for (fs_infop = mnt_opts; fs_infop->flag; fs_infop++) {
if (mnt->mnt_flags & fs_infop->flag)
seq_puts(m, fs_infop->str);
}
extern void detach_pid(struct task_struct *task, enum pid_type);
extern void change_pid(struct task_struct *task, enum pid_type,
struct pid *pid);
+extern void exchange_tids(struct task_struct *task, struct task_struct *old);
extern void transfer_pid(struct task_struct *old, struct task_struct *new,
enum pid_type);
struct fs_pin;
-enum { /* definitions for pid_namespace's hide_pid field */
- HIDEPID_OFF = 0,
- HIDEPID_NO_ACCESS = 1,
- HIDEPID_INVISIBLE = 2,
-};
-
struct pid_namespace {
struct kref kref;
struct idr idr;
struct kmem_cache *pid_cachep;
unsigned int level;
struct pid_namespace *parent;
-#ifdef CONFIG_PROC_FS
- struct dentry *proc_self;
- struct dentry *proc_thread_self;
-#endif
#ifdef CONFIG_BSD_PROCESS_ACCT
struct fs_pin *bacct;
#endif
struct user_namespace *user_ns;
struct ucounts *ucounts;
- kgid_t pid_gid;
- int hide_pid;
int reboot; /* group exit code if this pidns was rebooted */
struct ns_common ns;
} __randomize_layout;
unsigned long (*proc_get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
} __randomize_layout;
+/* definitions for hide_pid field */
+enum proc_hidepid {
+ HIDEPID_OFF = 0,
+ HIDEPID_NO_ACCESS = 1,
+ HIDEPID_INVISIBLE = 2,
+ HIDEPID_NOT_PTRACEABLE = 4, /* Limit pids to only ptraceable pids */
+};
+
+/* definitions for proc mount option pidonly */
+enum proc_pidonly {
+ PROC_PIDONLY_OFF = 0,
+ PROC_PIDONLY_ON = 1,
+};
+
+struct proc_fs_info {
+ struct pid_namespace *pid_ns;
+ struct dentry *proc_self; /* For /proc/self */
+ struct dentry *proc_thread_self; /* For /proc/thread-self */
+ kgid_t pid_gid;
+ enum proc_hidepid hide_pid;
+ enum proc_pidonly pidonly;
+};
+
+static inline struct proc_fs_info *proc_sb_info(struct super_block *sb)
+{
+ return sb->s_fs_info;
+}
+
#ifdef CONFIG_PROC_FS
typedef int (*proc_write_t)(struct file *, char *, size_t);
struct ns_common *(*get_ns)(struct ns_common *ns));
/* get the associated pid namespace for a file in procfs */
-static inline struct pid_namespace *proc_pid_ns(const struct inode *inode)
+static inline struct pid_namespace *proc_pid_ns(struct super_block *sb)
{
- return inode->i_sb->s_fs_info;
+ return proc_sb_info(sb)->pid_ns;
}
bool proc_ns_file(const struct file *file);
WRITE_ONCE(old->pprev, LIST_POISON2);
}
+/**
+ * hlists_swap_heads_rcu - swap the lists the hlist heads point to
+ * @left: The hlist head on the left
+ * @right: The hlist head on the right
+ *
+ * The lists start out as [@left ][node1 ... ] and
+ [@right ][node2 ... ]
+ * The lists end up as [@left ][node2 ... ]
+ * [@right ][node1 ... ]
+ */
+static inline void hlists_swap_heads_rcu(struct hlist_head *left, struct hlist_head *right)
+{
+ struct hlist_node *node1 = left->first;
+ struct hlist_node *node2 = right->first;
+
+ rcu_assign_pointer(left->first, node2);
+ rcu_assign_pointer(right->first, node1);
+ WRITE_ONCE(node2->pprev, &left->first);
+ WRITE_ONCE(node1->pprev, &right->first);
+}
+
/*
* return the first or the next element in an RCU protected hlist
*/
return p->exit_signal >= 0;
}
-/* Do to the insanities of de_thread it is possible for a process
- * to have the pid of the thread group leader without actually being
- * the thread group leader. For iteration through the pids in proc
- * all we care about is that we have a task with the appropriate
- * pid, we don't actually care if we have the right task.
- */
-static inline bool has_group_leader_pid(struct task_struct *p)
-{
- return task_pid(p) == task_tgid(p);
-}
-
static inline
bool same_thread_group(struct task_struct *p1, struct task_struct *p2)
{
pid_t nr = -1;
if (likely(pid_has_task(pid, PIDTYPE_PID))) {
- ns = proc_pid_ns(file_inode(m->file));
+ ns = proc_pid_ns(file_inode(m->file)->i_sb);
nr = pid_nr_ns(pid, ns);
}
attach_pid(task, type);
}
+void exchange_tids(struct task_struct *left, struct task_struct *right)
+{
+ struct pid *pid1 = left->thread_pid;
+ struct pid *pid2 = right->thread_pid;
+ struct hlist_head *head1 = &pid1->tasks[PIDTYPE_PID];
+ struct hlist_head *head2 = &pid2->tasks[PIDTYPE_PID];
+
+ /* Swap the single entry tid lists */
+ hlists_swap_heads_rcu(head1, head2);
+
+ /* Swap the per task_struct pid */
+ rcu_assign_pointer(left->thread_pid, pid2);
+ rcu_assign_pointer(right->thread_pid, pid1);
+
+ /* Swap the cached value */
+ WRITE_ONCE(left->pid, pid_nr(pid2));
+ WRITE_ONCE(right->pid, pid_nr(pid1));
+}
+
/* transfer_pid is an optimization of attach_pid(new), detach_pid(old) */
void transfer_pid(struct task_struct *old, struct task_struct *new,
enum pid_type type)
rcu_read_lock();
if (!ns)
ns = task_active_pid_ns(current);
- if (likely(pid_alive(task)))
- nr = pid_nr_ns(rcu_dereference(*task_pid_ptr(task, type)), ns);
+ nr = pid_nr_ns(rcu_dereference(*task_pid_ptr(task, type)), ns);
rcu_read_unlock();
return nr;
/*
* Functions for validating access to tasks.
*/
-static struct task_struct *lookup_task(const pid_t pid, bool thread,
- bool gettime)
+static struct pid *pid_for_clock(const clockid_t clock, bool gettime)
{
- struct task_struct *p;
+ const bool thread = !!CPUCLOCK_PERTHREAD(clock);
+ const pid_t upid = CPUCLOCK_PID(clock);
+ struct pid *pid;
+
+ if (CPUCLOCK_WHICH(clock) >= CPUCLOCK_MAX)
+ return NULL;
/*
* If the encoded PID is 0, then the timer is targeted at current
* or the process to which current belongs.
*/
- if (!pid)
- return thread ? current : current->group_leader;
+ if (upid == 0)
+ return thread ? task_pid(current) : task_tgid(current);
- p = find_task_by_vpid(pid);
- if (!p)
- return p;
-
- if (thread)
- return same_thread_group(p, current) ? p : NULL;
+ pid = find_vpid(upid);
+ if (!pid)
+ return NULL;
- if (gettime) {
- /*
- * For clock_gettime(PROCESS) the task does not need to be
- * the actual group leader. tsk->sighand gives
- * access to the group's clock.
- *
- * Timers need the group leader because they take a
- * reference on it and store the task pointer until the
- * timer is destroyed.
- */
- return (p == current || thread_group_leader(p)) ? p : NULL;
+ if (thread) {
+ struct task_struct *tsk = pid_task(pid, PIDTYPE_PID);
+ return (tsk && same_thread_group(tsk, current)) ? pid : NULL;
}
/*
- * For processes require that p is group leader.
+ * For clock_gettime(PROCESS) allow finding the process by
+ * with the pid of the current task. The code needs the tgid
+ * of the process so that pid_task(pid, PIDTYPE_TGID) can be
+ * used to find the process.
*/
- return has_group_leader_pid(p) ? p : NULL;
+ if (gettime && (pid == task_pid(current)))
+ return task_tgid(current);
+
+ /*
+ * For processes require that pid identifies a process.
+ */
+ return pid_has_task(pid, PIDTYPE_TGID) ? pid : NULL;
}
-static struct task_struct *__get_task_for_clock(const clockid_t clock,
- bool getref, bool gettime)
+static inline int validate_clock_permissions(const clockid_t clock)
{
- const bool thread = !!CPUCLOCK_PERTHREAD(clock);
- const pid_t pid = CPUCLOCK_PID(clock);
- struct task_struct *p;
-
- if (CPUCLOCK_WHICH(clock) >= CPUCLOCK_MAX)
- return NULL;
+ int ret;
rcu_read_lock();
- p = lookup_task(pid, thread, gettime);
- if (p && getref)
- get_task_struct(p);
+ ret = pid_for_clock(clock, false) ? 0 : -EINVAL;
rcu_read_unlock();
- return p;
-}
-
-static inline struct task_struct *get_task_for_clock(const clockid_t clock)
-{
- return __get_task_for_clock(clock, true, false);
-}
-static inline struct task_struct *get_task_for_clock_get(const clockid_t clock)
-{
- return __get_task_for_clock(clock, true, true);
-}
-
-static inline int validate_clock_permissions(const clockid_t clock)
-{
- return __get_task_for_clock(clock, false, false) ? 0 : -EINVAL;
+ return ret;
}
-static inline enum pid_type cpu_timer_pid_type(struct k_itimer *timer)
+static inline enum pid_type clock_pid_type(const clockid_t clock)
{
- return CPUCLOCK_PERTHREAD(timer->it_clock) ? PIDTYPE_PID : PIDTYPE_TGID;
+ return CPUCLOCK_PERTHREAD(clock) ? PIDTYPE_PID : PIDTYPE_TGID;
}
static inline struct task_struct *cpu_timer_task_rcu(struct k_itimer *timer)
{
- return pid_task(timer->it.cpu.pid, cpu_timer_pid_type(timer));
+ return pid_task(timer->it.cpu.pid, clock_pid_type(timer->it_clock));
}
/*
struct task_struct *tsk;
u64 t;
- tsk = get_task_for_clock_get(clock);
- if (!tsk)
+ rcu_read_lock();
+ tsk = pid_task(pid_for_clock(clock, true), clock_pid_type(clock));
+ if (!tsk) {
+ rcu_read_unlock();
return -EINVAL;
+ }
if (CPUCLOCK_PERTHREAD(clock))
t = cpu_clock_sample(clkid, tsk);
else
t = cpu_clock_sample_group(clkid, tsk, false);
- put_task_struct(tsk);
+ rcu_read_unlock();
*tp = ns_to_timespec64(t);
return 0;
*/
static int posix_cpu_timer_create(struct k_itimer *new_timer)
{
- struct task_struct *p = get_task_for_clock(new_timer->it_clock);
+ struct pid *pid;
- if (!p)
+ rcu_read_lock();
+ pid = pid_for_clock(new_timer->it_clock, false);
+ if (!pid) {
+ rcu_read_unlock();
return -EINVAL;
+ }
new_timer->kclock = &clock_posix_cpu;
timerqueue_init(&new_timer->it.cpu.node);
- new_timer->it.cpu.pid = get_task_pid(p, cpu_timer_pid_type(new_timer));
- /*
- * get_task_for_clock() took a reference on @p. Drop it as the timer
- * holds a reference on the pid of @p.
- */
- put_task_struct(p);
+ new_timer->it.cpu.pid = get_pid(pid);
+ rcu_read_unlock();
return 0;
}
{
struct ip6fl_iter_state *state = ip6fl_seq_private(seq);
- state->pid_ns = proc_pid_ns(file_inode(seq->file));
+ state->pid_ns = proc_pid_ns(file_inode(seq->file)->i_sb);
rcu_read_lock_bh();
return *pos ? ip6fl_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
#include "common.h"
#include <linux/magic.h>
+#include <linux/proc_fs.h>
/**
* tomoyo_encode2 - Encode binary string to ascii string.
if (sb->s_magic == PROC_SUPER_MAGIC && *pos == '/') {
char *ep;
const pid_t pid = (pid_t) simple_strtoul(pos + 1, &ep, 10);
+ struct pid_namespace *proc_pidns = proc_pid_ns(sb);
if (*ep == '/' && pid && pid ==
- task_tgid_nr_ns(current, sb->s_fs_info)) {
+ task_tgid_nr_ns(current, proc_pidns)) {
pos = ep - 5;
if (pos < buffer)
goto out;
/fd-001-lookup
/fd-002-posix-eq
/fd-003-kthread
+/proc-fsconfig-hidepid
/proc-loadavg-001
+/proc-multiple-procfs
/proc-pid-vm
/proc-self-map-files-001
/proc-self-map-files-002
TEST_GEN_PROGS += setns-dcache
TEST_GEN_PROGS += setns-sysvipc
TEST_GEN_PROGS += thread-self
+TEST_GEN_PROGS += proc-multiple-procfs
+TEST_GEN_PROGS += proc-fsconfig-hidepid
include ../lib.mk
--- /dev/null
+/*
+ * Copyright © 2020 Alexey Gladkov <gladkov.alexey@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+#include <assert.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <linux/mount.h>
+#include <linux/unistd.h>
+
+static inline int fsopen(const char *fsname, unsigned int flags)
+{
+ return syscall(__NR_fsopen, fsname, flags);
+}
+
+static inline int fsconfig(int fd, unsigned int cmd, const char *key, const void *val, int aux)
+{
+ return syscall(__NR_fsconfig, fd, cmd, key, val, aux);
+}
+
+int main(void)
+{
+ int fsfd, ret;
+ int hidepid = 2;
+
+ assert((fsfd = fsopen("proc", 0)) != -1);
+
+ ret = fsconfig(fsfd, FSCONFIG_SET_BINARY, "hidepid", &hidepid, 0);
+ assert(ret == -1);
+ assert(errno == EINVAL);
+
+ assert(!fsconfig(fsfd, FSCONFIG_SET_STRING, "hidepid", "2", 0));
+ assert(!fsconfig(fsfd, FSCONFIG_SET_STRING, "hidepid", "invisible", 0));
+
+ assert(!close(fsfd));
+
+ return 0;
+}
--- /dev/null
+/*
+ * Copyright © 2020 Alexey Gladkov <gladkov.alexey@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+#include <assert.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <sys/mount.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+int main(void)
+{
+ struct stat proc_st1, proc_st2;
+ char procbuff[] = "/tmp/proc.XXXXXX/meminfo";
+ char procdir1[] = "/tmp/proc.XXXXXX";
+ char procdir2[] = "/tmp/proc.XXXXXX";
+
+ assert(mkdtemp(procdir1) != NULL);
+ assert(mkdtemp(procdir2) != NULL);
+
+ assert(!mount("proc", procdir1, "proc", 0, "hidepid=1"));
+ assert(!mount("proc", procdir2, "proc", 0, "hidepid=2"));
+
+ snprintf(procbuff, sizeof(procbuff), "%s/meminfo", procdir1);
+ assert(!stat(procbuff, &proc_st1));
+
+ snprintf(procbuff, sizeof(procbuff), "%s/meminfo", procdir2);
+ assert(!stat(procbuff, &proc_st2));
+
+ umount(procdir1);
+ umount(procdir2);
+
+ assert(proc_st1.st_dev != proc_st2.st_dev);
+
+ return 0;
+}