Merge tag 'vfs-7.2-rc1.procfs' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull procfs updates from Christian Brauner:

 - Revamp fs/filesystems.c

   The file was a mess with a hand-rolled linked list in desperate need
   of a cleanup. The filesystems list is now RCU-ified, /proc files can
   be marked permanent from outside fs/proc/, and the string emitted
   when reading /proc/filesystems is pre-generated and cached instead of
   pointer-chasing and printfing entry by entry on every read.

   The file is read frequently because libselinux reads it and is linked
   into numerous frequently used programs (even ones you would not
   suspect, like sed!). Scalability also improves since reference
   maintenance on open/close is bypassed.

    open+read+close cycle single-threaded (ops/s):
      before: 442732
      after:  1063462 (+140%)

    open+read+close cycle with 20 processes (ops/s):
      before: 606177
      after:  3300576 (+444%)

   A follow-up patch adds missing unlocks in some corner cases and
   tidies things up.

 - Relax the mount visibility check for subset=pid mounts

   When procfs is mounted with subset=pid, all static files become
   unavailable and only the dynamic pid information is accessible. In
   that case there is no point in imposing the full mount visibility
   restrictions on the mounter - everything that can be hidden in procfs
   is already inaccessible. These restrictions prevented procfs from
   being mounted inside rootless containers since almost all container
   implementations overmount parts of procfs to hide certain
   directories.

   As part of this /proc/self/net is only shown in subset=pid mounts for
   CAP_NET_ADMIN, reconfiguring subset=pid is rejected, the
   SB_I_USERNS_VISIBLE superblock flag is replaced with an
   FS_USERNS_MOUNT_RESTRICTED filesystem flag, fully visible mounts are
   recorded in a list, and the mount restrictions are finally
   documented.

 - Protect ptrace_may_access() with exec_update_lock in procfs

   Most uses of ptrace_may_access() in procfs should hold
   exec_update_lock to avoid TOCTOU issues with concurrent privileged
   execve() (like setuid binary execution).

   This fixes the easy cases - the owner and visibility checks and the
   FD link permission checks - with the gnarlier ones to follow later.

* tag 'vfs-7.2-rc1.procfs' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  fs: fix ups and tidy ups to /proc/filesystems caching
  proc: protect ptrace_may_access() with exec_update_lock (FD links)
  proc: protect ptrace_may_access() with exec_update_lock (part 1)
  docs: proc: add documentation about mount restrictions
  proc: handle subset=pid separately in userns visibility checks
  proc: prevent reconfiguring subset=pid
  proc: subset=pid: Show /proc/self/net only for CAP_NET_ADMIN
  fs: cache the string generated by reading /proc/filesystems
  sysfs: remove trivial sysfs_get_tree() wrapper
  fs: RCU-ify filesystems list
  fs: move SB_I_USERNS_VISIBLE to FS_USERNS_MOUNT_RESTRICTED
  proc: allow to mark /proc files permanent outside of fs/proc/
  namespace: record fully visible mounts in list

8 files changed, 137 insertions, 113 deletions

diff --git a/fs/proc/array.c b/fs/proc/array.c
index 90fb0c6b5f99..479ea8cb4ef4 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -482,6 +482,11 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	unsigned long flags;
 	int exit_code = task->exit_code;
 	struct signal_struct *sig = task->signal;
+	int ret;
+
+	ret = down_read_killable(&task->signal->exec_update_lock);
+	if (ret)
+		return ret;
 
 	state = *get_task_state(task);
 	vsize = eip = esp = 0;
@@ -657,6 +662,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 		seq_puts(m, " 0");
 
 	seq_putc(m, '\n');
+	up_read(&task->signal->exec_update_lock);
 	if (mm)
 		mmput(mm);
 	return 0;
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 126b98419adb..b67e8c3605fb 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -219,33 +219,24 @@ static int get_task_root(struct task_struct *task, struct path *root)
 	return result;
 }
 
-static int proc_cwd_link(struct dentry *dentry, struct path *path)
+static int proc_cwd_link(struct dentry *dentry, struct path *path,
+			 struct task_struct *task)
 {
-	struct task_struct *task = get_proc_task(d_inode(dentry));
 	int result = -ENOENT;
 
-	if (task) {
-		task_lock(task);
-		if (task->fs) {
-			get_fs_pwd(task->fs, path);
-			result = 0;
-		}
-		task_unlock(task);
-		put_task_struct(task);
+	task_lock(task);
+	if (task->fs) {
+		get_fs_pwd(task->fs, path);
+		result = 0;
 	}
+	task_unlock(task);
 	return result;
 }
 
-static int proc_root_link(struct dentry *dentry, struct path *path)
+static int proc_root_link(struct dentry *dentry, struct path *path,
+			  struct task_struct *task)
 {
-	struct task_struct *task = get_proc_task(d_inode(dentry));
-	int result = -ENOENT;
-
-	if (task) {
-		result = get_task_root(task, path);
-		put_task_struct(task);
-	}
-	return result;
+	return get_task_root(task, path);
 }
 
 /*
@@ -424,18 +415,24 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns,
 {
 	unsigned long wchan;
 	char symname[KSYM_NAME_LEN];
+	int err;
 
+	err = down_read_killable(&task->signal->exec_update_lock);
+	if (err)
+		return err;
 	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
 		goto print0;
 
 	wchan = get_wchan(task);
 	if (wchan && !lookup_symbol_name(wchan, symname)) {
 		seq_puts(m, symname);
+		up_read(&task->signal->exec_update_lock);
 		return 0;
 	}
 
 print0:
 	seq_putc(m, '0');
+	up_read(&task->signal->exec_update_lock);
 	return 0;
 }
 #endif /* CONFIG_KALLSYMS */
@@ -705,23 +702,6 @@ static int proc_pid_syscall(struct seq_file *m, struct pid_namespace *ns,
 /*                       Here the fs part begins                        */
 /************************************************************************/
 
-/* permission checks */
-static bool proc_fd_access_allowed(struct inode *inode)
-{
-	struct task_struct *task;
-	bool allowed = false;
-	/* Allow access to a task's file descriptors if it is us or we
-	 * may use ptrace attach to the process and find out that
-	 * information.
-	 */
-	task = get_proc_task(inode);
-	if (task) {
-		allowed = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
-		put_task_struct(task);
-	}
-	return allowed;
-}
-
 int proc_nochmod_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		 struct iattr *attr)
 {
@@ -1778,16 +1758,12 @@ static const struct file_operations proc_pid_set_comm_operations = {
 	.release	= single_release,
 };
 
-static int proc_exe_link(struct dentry *dentry, struct path *exe_path)
+static int proc_exe_link(struct dentry *dentry, struct path *exe_path,
+			 struct task_struct *task)
 {
-	struct task_struct *task;
 	struct file *exe_file;
 
-	task = get_proc_task(d_inode(dentry));
-	if (!task)
-		return -ENOENT;
 	exe_file = get_task_exe_file(task);
-	put_task_struct(task);
 	if (exe_file) {
 		*exe_path = exe_file->f_path;
 		path_get(&exe_file->f_path);
@@ -1797,26 +1773,42 @@ static int proc_exe_link(struct dentry *dentry, struct path *exe_path)
 		return -ENOENT;
 }
 
+static int call_proc_get_link(struct dentry *dentry, struct inode *inode, struct path *path_out)
+{
+	struct task_struct *task;
+	int ret;
+
+	task = get_proc_task(inode);
+	if (!task)
+		return -ENOENT;
+	ret = down_read_killable(&task->signal->exec_update_lock);
+	if (ret)
+		goto out_put_task;
+	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
+		ret = -EACCES;
+		goto out;
+	}
+	ret = PROC_I(inode)->op.proc_get_link(dentry, path_out, task);
+
+out:
+	up_read(&task->signal->exec_update_lock);
+out_put_task:
+	put_task_struct(task);
+	return ret;
+}
+
 static const char *proc_pid_get_link(struct dentry *dentry,
 				     struct inode *inode,
 				     struct delayed_call *done)
 {
 	struct path path;
-	int error = -EACCES;
+	int error;
 
 	if (!dentry)
 		return ERR_PTR(-ECHILD);
-
-	/* Are we allowed to snoop on the tasks file descriptors? */
-	if (!proc_fd_access_allowed(inode))
-		goto out;
-
-	error = PROC_I(inode)->op.proc_get_link(dentry, &path);
-	if (error)
-		goto out;
-
-	error = nd_jump_link(&path);
-out:
+	error = call_proc_get_link(dentry, inode, &path);
+	if (!error)
+		error = nd_jump_link(&path);
 	return ERR_PTR(error);
 }
 
@@ -1850,17 +1842,11 @@ static int proc_pid_readlink(struct dentry * dentry, char __user * buffer, int b
 	struct inode *inode = d_inode(dentry);
 	struct path path;
 
-	/* Are we allowed to snoop on the tasks file descriptors? */
-	if (!proc_fd_access_allowed(inode))
-		goto out;
-
-	error = PROC_I(inode)->op.proc_get_link(dentry, &path);
-	if (error)
-		goto out;
-
-	error = do_proc_readlink(&path, buffer, buflen);
-	path_put(&path);
-out:
+	error = call_proc_get_link(dentry, inode, &path);
+	if (!error) {
+		error = do_proc_readlink(&path, buffer, buflen);
+		path_put(&path);
+	}
 	return error;
 }
 
@@ -2243,21 +2229,16 @@ static const struct dentry_operations tid_map_files_dentry_operations = {
 	.d_delete	= pid_delete_dentry,
 };
 
-static int map_files_get_link(struct dentry *dentry, struct path *path)
+static int map_files_get_link(struct dentry *dentry, struct path *path,
+			      struct task_struct *task)
 {
 	unsigned long vm_start, vm_end;
 	struct vm_area_struct *vma;
-	struct task_struct *task;
 	struct mm_struct *mm;
 	int rc;
 
 	rc = -ENOENT;
-	task = get_proc_task(d_inode(dentry));
-	if (!task)
-		goto out;
-
 	mm = get_task_mm(task);
-	put_task_struct(task);
 	if (!mm)
 		goto out;
 
@@ -2353,17 +2334,15 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
 	if (!task)
 		goto out;
 
-	result = ERR_PTR(-EACCES);
-	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
-		goto out_put_task;
-
 	result = ERR_PTR(-ENOENT);
 	if (dname_to_vma_addr(dentry, &vm_start, &vm_end))
 		goto out_put_task;
 
-	mm = get_task_mm(task);
-	if (!mm)
+	mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
+	if (IS_ERR(mm)) {
+		result = ERR_CAST(mm);
 		goto out_put_task;
+	}
 
 	result = ERR_PTR(-EINTR);
 	if (mmap_read_lock_killable(mm))
@@ -2413,23 +2392,22 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
 	if (!task)
 		goto out;
 
-	ret = -EACCES;
-	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
-		goto out_put_task;
-
 	ret = 0;
 	if (!dir_emit_dots(file, ctx))
 		goto out_put_task;
 
-	mm = get_task_mm(task);
-	if (!mm)
+	mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
+	if (IS_ERR(mm)) {
+		ret = PTR_ERR(mm);
+		/* if the task has no mm, the directory should just be empty */
+		if (ret == -ESRCH)
+			ret = 0;
 		goto out_put_task;
+	}
 
 	ret = mmap_read_lock_killable(mm);
-	if (ret) {
-		mmput(mm);
-		goto out_put_task;
-	}
+	if (ret)
+		goto out_put_mm;
 
 	nr_files = 0;
 
@@ -2455,8 +2433,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
 		if (!p) {
 			ret = -ENOMEM;
 			mmap_read_unlock(mm);
-			mmput(mm);
-			goto out_put_task;
+			goto out_put_mm;
 		}
 
 		p->start = vma->vm_start;
@@ -2464,7 +2441,6 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
 		p->mode = vma->vm_file->f_mode;
 	}
 	mmap_read_unlock(mm);
-	mmput(mm);
 
 	for (i = 0; i < nr_files; i++) {
 		char buf[4 * sizeof(long) + 2];	/* max: %lx-%lx\0 */
@@ -2481,6 +2457,8 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
 		ctx->pos++;
 	}
 
+out_put_mm:
+	mmput(mm);
 out_put_task:
 	put_task_struct(task);
 out:
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 05c7513e77c7..0f9a1556f2a3 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -171,24 +171,19 @@ static const struct dentry_operations tid_fd_dentry_operations = {
 	.d_delete	= pid_delete_dentry,
 };
 
-static int proc_fd_link(struct dentry *dentry, struct path *path)
+static int proc_fd_link(struct dentry *dentry, struct path *path,
+			struct task_struct *task)
 {
-	struct task_struct *task;
 	int ret = -ENOENT;
+	unsigned int fd = proc_fd(d_inode(dentry));
+	struct file *fd_file;
 
-	task = get_proc_task(d_inode(dentry));
-	if (task) {
-		unsigned int fd = proc_fd(d_inode(dentry));
-		struct file *fd_file;
-
-		fd_file = fget_task(task, fd);
-		if (fd_file) {
-			*path = fd_file->f_path;
-			path_get(&fd_file->f_path);
-			ret = 0;
-			fput(fd_file);
-		}
-		put_task_struct(task);
+	fd_file = fget_task(task, fd);
+	if (fd_file) {
+		*path = fd_file->f_path;
+		path_get(&fd_file->f_path);
+		ret = 0;
+		fput(fd_file);
 	}
 
 	return ret;
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 8bb81e58c9d8..c6ae076e1fa0 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -841,3 +841,13 @@ ssize_t proc_simple_write(struct file *f, const char __user *ubuf, size_t size,
 	kfree(buf);
 	return ret == 0 ? size : ret;
 }
+
+/*
+ * Not exported to modules:
+ * modules' /proc files aren't permanent because modules aren't permanent.
+ */
+void impl_proc_make_permanent(struct proc_dir_entry *pde)
+{
+	if (pde)
+		pde_make_permanent(pde);
+}
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 64dc44832808..b232e1098117 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -79,8 +79,11 @@ static inline bool pde_is_permanent(const struct proc_dir_entry *pde)
 	return pde->flags & PROC_ENTRY_PERMANENT;
 }
 
+/* This is for builtin code, not even for modules which are compiled in. */
 static inline void pde_make_permanent(struct proc_dir_entry *pde)
 {
+	/* Ensure magic flag does something. */
+	static_assert(PROC_ENTRY_PERMANENT != 0);
 	pde->flags |= PROC_ENTRY_PERMANENT;
 }
 
@@ -107,7 +110,7 @@ extern struct kmem_cache *proc_dir_entry_cache;
 void pde_free(struct proc_dir_entry *pde);
 
 union proc_op {
-	int (*proc_get_link)(struct dentry *, struct path *);
+	int (*proc_get_link)(struct dentry *, struct path *, struct task_struct *);
 	int (*proc_show)(struct seq_file *m,
 		struct pid_namespace *ns, struct pid *pid,
 		struct task_struct *task);
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 39f4169f669f..2f46f1396744 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -55,6 +55,10 @@ static const char *proc_ns_get_link(struct dentry *dentry,
 	if (!task)
 		return ERR_PTR(-EACCES);
 
+	error = down_read_killable(&task->signal->exec_update_lock);
+	if (error)
+		goto out_put_task;
+
 	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
 		goto out;
 
@@ -64,6 +68,8 @@ static const char *proc_ns_get_link(struct dentry *dentry,
 
 	error = nd_jump_link(&ns_path);
 out:
+	up_read(&task->signal->exec_update_lock);
+out_put_task:
 	put_task_struct(task);
 	return ERR_PTR(error);
 }
@@ -80,11 +86,17 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl
 	if (!task)
 		return res;
 
+	res = down_read_killable(&task->signal->exec_update_lock);
+	if (res)
+		goto out_put_task;
+
 	if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
 		res = ns_get_name(name, sizeof(name), task, ns_ops);
 		if (res >= 0)
 			res = readlink_copy(buffer, buflen, name, strlen(name));
 	}
+	up_read(&task->signal->exec_update_lock);
+out_put_task:
 	put_task_struct(task);
 	return res;
 }
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 184cddeb8215..00cc385bce21 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -23,6 +23,7 @@
 #include <linux/uidgid.h>
 #include <net/net_namespace.h>
 #include <linux/seq_file.h>
+#include <linux/security.h>
 
 #include "internal.h"
 
@@ -270,6 +271,7 @@ static struct net *get_proc_task_net(struct inode *dir)
 	struct task_struct *task;
 	struct nsproxy *ns;
 	struct net *net = NULL;
+	struct proc_fs_info *fs_info = proc_sb_info(dir->i_sb);
 
 	rcu_read_lock();
 	task = pid_task(proc_pid(dir), PIDTYPE_PID);
@@ -282,6 +284,12 @@ static struct net *get_proc_task_net(struct inode *dir)
 	}
 	rcu_read_unlock();
 
+	if (net && (fs_info->pidonly == PROC_PIDONLY_ON) &&
+	    security_capable(fs_info->mounter_cred, net->user_ns, CAP_NET_ADMIN, CAP_OPT_NONE) < 0) {
+		put_net(net);
+		net = NULL;
+	}
+
 	return net;
 }
 
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 0f9100559471..99adddfeb4a4 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -223,12 +223,17 @@ static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	return 0;
 }
 
-static void proc_apply_options(struct proc_fs_info *fs_info,
+static int proc_apply_options(struct proc_fs_info *fs_info,
 			       struct fs_context *fc,
 			       struct user_namespace *user_ns)
 {
 	struct proc_fs_context *ctx = fc->fs_private;
 
+	if ((ctx->mask & (1 << Opt_subset)) &&
+	    fc->purpose == FS_CONTEXT_FOR_RECONFIGURE &&
+	    ctx->pidonly != fs_info->pidonly)
+		return invalf(fc, "proc: subset=pid cannot be changed\n");
+
 	if (ctx->mask & (1 << Opt_gid))
 		fs_info->pid_gid = make_kgid(user_ns, ctx->gid);
 	if (ctx->mask & (1 << Opt_hidepid))
@@ -240,6 +245,7 @@ static void proc_apply_options(struct proc_fs_info *fs_info,
 		put_pid_ns(fs_info->pid_ns);
 		fs_info->pid_ns = get_pid_ns(ctx->pid_ns);
 	}
+	return 0;
 }
 
 static int proc_fill_super(struct super_block *s, struct fs_context *fc)
@@ -254,10 +260,13 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc)
 		return -ENOMEM;
 
 	fs_info->pid_ns = get_pid_ns(ctx->pid_ns);
-	proc_apply_options(fs_info, fc, current_user_ns());
+	fs_info->mounter_cred = get_cred(fc->cred);
+	ret = proc_apply_options(fs_info, fc, current_user_ns());
+	if (ret)
+		return ret;
 
 	/* 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_iflags |= SB_I_NOEXEC | SB_I_NODEV;
 	s->s_flags |= SB_NODIRATIME | SB_NOSUID | SB_NOEXEC;
 	s->s_blocksize = 1024;
 	s->s_blocksize_bits = 10;
@@ -266,6 +275,9 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc)
 	s->s_time_gran = 1;
 	s->s_fs_info = fs_info;
 
+	if (fs_info->pidonly == PROC_PIDONLY_ON)
+		s->s_iflags |= SB_I_RESTRICTED_VARIANT;
+
 	/*
 	 * procfs isn't actually a stacking filesystem; however, there is
 	 * too much magic going on inside it to permit stacking things on
@@ -303,8 +315,7 @@ static int proc_reconfigure(struct fs_context *fc)
 
 	sync_filesystem(sb);
 
-	proc_apply_options(fs_info, fc, current_user_ns());
-	return 0;
+	return proc_apply_options(fs_info, fc, current_user_ns());
 }
 
 static int proc_get_tree(struct fs_context *fc)
@@ -350,6 +361,7 @@ static void proc_kill_sb(struct super_block *sb)
 	kill_anon_super(sb);
 	if (fs_info) {
 		put_pid_ns(fs_info->pid_ns);
+		put_cred(fs_info->mounter_cred);
 		kfree_rcu(fs_info, rcu);
 	}
 }
@@ -359,7 +371,7 @@ static struct file_system_type proc_fs_type = {
 	.init_fs_context	= proc_init_fs_context,
 	.parameters		= proc_fs_parameters,
 	.kill_sb		= proc_kill_sb,
-	.fs_flags		= FS_USERNS_MOUNT | FS_DISALLOW_NOTIFY_PERM,
+	.fs_flags		= FS_USERNS_MOUNT | FS_USERNS_MOUNT_RESTRICTED | FS_DISALLOW_NOTIFY_PERM,
 };
 
 void __init proc_root_init(void)