Linux-Fsdevel Archive on lore.kernel.org
 help / color / Atom feed
From: Alexey Gladkov <gladkov.alexey@gmail.com>
To: LKML <linux-kernel@vger.kernel.org>,
	Kernel Hardening <kernel-hardening@lists.openwall.com>,
	Linux API <linux-api@vger.kernel.org>,
	Linux FS Devel <linux-fsdevel@vger.kernel.org>,
	Linux Security Module <linux-security-module@vger.kernel.org>
Cc: Akinobu Mita <akinobu.mita@gmail.com>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	Alexey Dobriyan <adobriyan@gmail.com>,
	Alexey Gladkov <gladkov.alexey@gmail.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Andy Lutomirski <luto@kernel.org>,
	Daniel Micay <danielmicay@gmail.com>,
	Djalal Harouni <tixxdz@gmail.com>,
	"Dmitry V . Levin" <ldv@altlinux.org>,
	"Eric W . Biederman" <ebiederm@xmission.com>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	Ingo Molnar <mingo@kernel.org>,
	"J . Bruce Fields" <bfields@fieldses.org>,
	Jeff Layton <jlayton@poochiereds.net>,
	Jonathan Corbet <corbet@lwn.net>,
	Kees Cook <keescook@chromium.org>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Oleg Nesterov <oleg@redhat.com>,
	Solar Designer <solar@openwall.com>
Subject: [PATCH v8 02/11] proc: add proc_fs_info struct to store proc information
Date: Mon, 10 Feb 2020 16:05:10 +0100
Message-ID: <20200210150519.538333-3-gladkov.alexey@gmail.com> (raw)
In-Reply-To: <20200210150519.538333-1-gladkov.alexey@gmail.com>

This is a preparation patch that adds proc_fs_info to be able to store
different procfs options and informations. Right now some mount options
are stored inside the pid namespace which makes it hard to change or
modernize procfs without affecting pid namespaces. Plus we do want to
treat proc as more of a real mount point and filesystem. procfs is part
of Linux API where it offers some features using filesystem syscalls and
in order to support some features where we are able to have multiple
instances of procfs, each one with its mount options inside the same pid
namespace, we have to separate these procfs instances.

This is the same feature that was also added to other Linux interfaces
like devpts in order to support containers, sandboxes, and to have
multiple instances of devpts filesystem [1].

[1] https://elixir.bootlin.com/linux/v3.4/source/Documentation/filesystems/devpts.txt

Cc: Kees Cook <keescook@chromium.org>
Suggested-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Djalal Harouni <tixxdz@gmail.com>
Signed-off-by: Alexey Gladkov <gladkov.alexey@gmail.com>
---
 fs/locks.c              |  6 +++--
 fs/proc/base.c          |  8 +++++--
 fs/proc/inode.c         |  4 ++--
 fs/proc/root.c          | 49 +++++++++++++++++++++++++++--------------
 include/linux/proc_fs.h | 11 ++++++++-
 5 files changed, 54 insertions(+), 24 deletions(-)

diff --git a/fs/locks.c b/fs/locks.c
index 6970f55daf54..21200e3005e4 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -2795,7 +2795,8 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
 {
 	struct inode *inode = NULL;
 	unsigned int fl_pid;
-	struct pid_namespace *proc_pidns = file_inode(f->file)->i_sb->s_fs_info;
+	struct proc_fs_info *fs_info = proc_sb_info(file_inode(f->file)->i_sb);
+	struct pid_namespace *proc_pidns = fs_info->pid_ns;
 
 	fl_pid = locks_translate_pid(fl, proc_pidns);
 	/*
@@ -2873,7 +2874,8 @@ static int locks_show(struct seq_file *f, void *v)
 {
 	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 proc_fs_info *fs_info = proc_sb_info(file_inode(f->file)->i_sb);
+	struct pid_namespace *proc_pidns = fs_info->pid_ns;
 
 	fl = hlist_entry(v, struct file_lock, fl_link);
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index ebea9501afb8..672e71c52dbd 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -3243,6 +3243,7 @@ struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags)
 {
 	struct task_struct *task;
 	unsigned tgid;
+	struct proc_fs_info *fs_info;
 	struct pid_namespace *ns;
 	struct dentry *result = ERR_PTR(-ENOENT);
 
@@ -3250,7 +3251,8 @@ struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags)
 	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)
@@ -3538,6 +3540,7 @@ static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry
 	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);
 
@@ -3548,7 +3551,8 @@ static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry
 	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)
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index dbe43a50caf2..b631608dfbcc 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -104,8 +104,8 @@ void __init proc_init_kmemcache(void)
 
 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);
+	struct pid_namespace *pid = fs_info->pid_ns;
 
 	if (!gid_eq(pid->pid_gid, GLOBAL_ROOT_GID))
 		seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, pid->pid_gid));
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 0b7c8dffc9ae..d449f095f0f7 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -30,7 +30,7 @@
 #include "internal.h"
 
 struct proc_fs_context {
-	struct pid_namespace	*pid_ns;
+	struct proc_fs_info	*fs_info;
 	unsigned int		mask;
 	int			hidepid;
 	int			gid;
@@ -97,7 +97,8 @@ static void proc_apply_options(struct super_block *s,
 
 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 pid_namespace *pid_ns = get_pid_ns(ctx->fs_info->pid_ns);
 	struct inode *root_inode;
 	int ret;
 
@@ -145,7 +146,8 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc)
 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);
+	struct pid_namespace *pid = fs_info->pid_ns;
 
 	sync_filesystem(sb);
 
@@ -157,14 +159,14 @@ 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_keyed(fc, proc_fill_super, ctx->fs_info);
 }
 
 static void proc_fs_context_free(struct fs_context *fc)
 {
 	struct proc_fs_context *ctx = fc->fs_private;
 
-	put_pid_ns(ctx->pid_ns);
+	put_pid_ns(ctx->fs_info->pid_ns);
 	kfree(ctx);
 }
 
@@ -178,14 +180,27 @@ static const struct fs_context_operations proc_fs_context_ops = {
 static int proc_init_fs_context(struct fs_context *fc)
 {
 	struct proc_fs_context *ctx;
+	struct pid_namespace *pid_ns;
 
 	ctx = kzalloc(sizeof(struct proc_fs_context), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
 
-	ctx->pid_ns = get_pid_ns(task_active_pid_ns(current));
+	pid_ns = get_pid_ns(task_active_pid_ns(current));
+
+	if (!pid_ns->proc_mnt) {
+		ctx->fs_info = kzalloc(sizeof(struct proc_fs_info), GFP_KERNEL);
+		if (!ctx->fs_info) {
+			kfree(ctx);
+			return -ENOMEM;
+		}
+		ctx->fs_info->pid_ns = pid_ns;
+	} else {
+		ctx->fs_info = proc_sb_info(pid_ns->proc_mnt->mnt_sb);
+	}
+
 	put_user_ns(fc->user_ns);
-	fc->user_ns = get_user_ns(ctx->pid_ns->user_ns);
+	fc->user_ns = get_user_ns(ctx->fs_info->pid_ns->user_ns);
 	fc->fs_private = ctx;
 	fc->ops = &proc_fs_context_ops;
 	return 0;
@@ -193,15 +208,15 @@ static int proc_init_fs_context(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);
+	if (fs_info->pid_ns->proc_self)
+		dput(fs_info->pid_ns->proc_self);
+	if (fs_info->pid_ns->proc_thread_self)
+		dput(fs_info->pid_ns->proc_thread_self);
 	kill_anon_super(sb);
-	put_pid_ns(ns);
+	put_pid_ns(fs_info->pid_ns);
+	kfree(fs_info);
 }
 
 static struct file_system_type proc_fs_type = {
@@ -314,10 +329,10 @@ int pid_ns_prepare_proc(struct pid_namespace *ns)
 	}
 
 	ctx = fc->fs_private;
-	if (ctx->pid_ns != ns) {
-		put_pid_ns(ctx->pid_ns);
+	if (ctx->fs_info->pid_ns != ns) {
+		put_pid_ns(ctx->fs_info->pid_ns);
 		get_pid_ns(ns);
-		ctx->pid_ns = ns;
+		ctx->fs_info->pid_ns = ns;
 	}
 
 	mnt = fc_mount(fc);
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index a705aa2d03f9..2d79489e55aa 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -12,6 +12,15 @@ struct proc_dir_entry;
 struct seq_file;
 struct seq_operations;
 
+struct proc_fs_info {
+	struct pid_namespace *pid_ns;
+};
+
+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);
@@ -146,7 +155,7 @@ int open_related_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)
 {
-	return inode->i_sb->s_fs_info;
+	return proc_sb_info(inode->i_sb)->pid_ns;
 }
 
 #endif /* _LINUX_PROC_FS_H */
-- 
2.24.1


  parent reply index

Thread overview: 85+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-10 15:05 [PATCH v8 00/11] proc: modernize proc to support multiple private instances Alexey Gladkov
2020-02-10 15:05 ` [PATCH v8 01/11] proc: Rename struct proc_fs_info to proc_fs_opts Alexey Gladkov
2020-02-10 15:05 ` Alexey Gladkov [this message]
2020-02-10 15:05 ` [PATCH v8 03/11] proc: move /proc/{self|thread-self} dentries to proc_fs_info Alexey Gladkov
2020-02-10 18:23   ` Andy Lutomirski
2020-02-12 15:00     ` Alexey Gladkov
2020-02-10 15:05 ` [PATCH v8 04/11] proc: move hide_pid, pid_gid from pid_namespace " Alexey Gladkov
2020-02-10 15:05 ` [PATCH v8 05/11] proc: add helpers to set and get proc hidepid and gid mount options Alexey Gladkov
2020-02-10 18:30   ` Andy Lutomirski
2020-02-12 14:57     ` Alexey Gladkov
2020-02-10 15:05 ` [PATCH v8 06/11] proc: support mounting procfs instances inside same pid namespace Alexey Gladkov
2020-02-10 15:05 ` [PATCH v8 07/11] proc: flush task dcache entries from all procfs instances Alexey Gladkov
2020-02-10 17:46   ` Linus Torvalds
2020-02-10 19:23     ` Al Viro
2020-02-11  1:36   ` Eric W. Biederman
2020-02-11  4:01     ` Eric W. Biederman
2020-02-12 14:49     ` Alexey Gladkov
2020-02-12 14:59       ` Eric W. Biederman
2020-02-12 17:08         ` Alexey Gladkov
2020-02-12 18:45         ` Linus Torvalds
2020-02-12 19:16           ` Eric W. Biederman
2020-02-12 19:49             ` Linus Torvalds
2020-02-12 20:03               ` Al Viro
2020-02-12 20:35                 ` Linus Torvalds
2020-02-12 20:38                   ` Al Viro
2020-02-12 20:41                     ` Al Viro
2020-02-12 21:02                       ` Linus Torvalds
2020-02-12 21:46                         ` Eric W. Biederman
2020-02-13  0:48                           ` Linus Torvalds
2020-02-13  4:37                             ` Eric W. Biederman
2020-02-13  5:55                               ` Al Viro
2020-02-13 21:30                                 ` Linus Torvalds
2020-02-13 22:23                                   ` Al Viro
2020-02-13 22:47                                     ` Linus Torvalds
2020-02-14 14:15                                       ` Eric W. Biederman
2020-02-14  3:48                                 ` Eric W. Biederman
2020-02-20 20:46                               ` [PATCH 0/7] proc: Dentry flushing without proc_mnt Eric W. Biederman
2020-02-20 20:47                                 ` [PATCH 1/7] proc: Rename in proc_inode rename sysctl_inodes sibling_inodes Eric W. Biederman
2020-02-20 20:48                                 ` [PATCH 2/7] proc: Generalize proc_sys_prune_dcache into proc_prune_siblings_dcache Eric W. Biederman
2020-02-20 20:49                                 ` [PATCH 3/7] proc: Mov rcu_read_(lock|unlock) in proc_prune_siblings_dcache Eric W. Biederman
2020-02-20 22:33                                   ` Linus Torvalds
2020-02-20 20:49                                 ` [PATCH 4/7] proc: Use d_invalidate " Eric W. Biederman
2020-02-20 22:43                                   ` Linus Torvalds
2020-02-20 22:54                                   ` Al Viro
2020-02-20 23:00                                     ` Linus Torvalds
2020-02-20 23:03                                     ` Al Viro
2020-02-20 23:39                                       ` Eric W. Biederman
2020-02-20 20:51                                 ` [PATCH 5/7] proc: Clear the pieces of proc_inode that proc_evict_inode cares about Eric W. Biederman
2020-02-20 20:52                                 ` [PATCH 6/7] proc: Use a list of inodes to flush from proc Eric W. Biederman
2020-02-20 20:52                                 ` [PATCH 7/7] proc: Ensure we see the exit of each process tid exactly once Eric W. Biederman
2020-02-21 16:50                                   ` Oleg Nesterov
2020-02-22 15:46                                     ` Eric W. Biederman
2020-02-20 23:02                                 ` [PATCH 0/7] proc: Dentry flushing without proc_mnt Linus Torvalds
2020-02-20 23:07                                   ` Al Viro
2020-02-20 23:37                                     ` Eric W. Biederman
2020-02-24 16:25                                 ` [PATCH v2 0/6] " Eric W. Biederman
2020-02-24 16:26                                   ` [PATCH v2 1/6] proc: Rename in proc_inode rename sysctl_inodes sibling_inodes Eric W. Biederman
2020-02-24 16:27                                   ` [PATCH v2 2/6] proc: Generalize proc_sys_prune_dcache into proc_prune_siblings_dcache Eric W. Biederman
2020-02-24 16:27                                   ` [PATCH v2 3/6] proc: In proc_prune_siblings_dcache cache an aquired super block Eric W. Biederman
2020-02-24 16:28                                   ` [PATCH v2 4/6] proc: Use d_invalidate in proc_prune_siblings_dcache Eric W. Biederman
2020-02-24 16:28                                   ` [PATCH v2 5/6] proc: Clear the pieces of proc_inode that proc_evict_inode cares about Eric W. Biederman
2020-02-24 16:29                                   ` [PATCH v2 6/6] proc: Use a list of inodes to flush from proc Eric W. Biederman
2020-02-28 20:17                                   ` [PATCH 0/3] proc: Actually honor the mount options Eric W. Biederman
2020-02-28 20:18                                     ` [PATCH 1/3] uml: Don't consult current to find the proc_mnt in mconsole_proc Eric W. Biederman
2020-02-28 20:18                                     ` [PATCH 2/3] uml: Create a private mount of proc for mconsole Eric W. Biederman
2020-02-28 20:30                                       ` Christian Brauner
2020-02-28 21:28                                         ` Eric W. Biederman
2020-02-28 21:59                                           ` Christian Brauner
2020-02-28 20:19                                     ` [PATCH 3/3] proc: Remove the now unnecessary internal mount of proc Eric W. Biederman
2020-02-28 20:39                                       ` Christian Brauner
2020-02-28 21:40                                         ` Eric W. Biederman
2020-02-28 22:34                                     ` [PATCH 4/3] pid: Improve the comment about waiting in zap_pid_ns_processes Eric W. Biederman
2020-02-29  2:59                                       ` Christian Brauner
2020-02-14  3:49                     ` [PATCH v8 07/11] proc: flush task dcache entries from all procfs instances Eric W. Biederman
2020-02-12 19:47           ` Al Viro
2020-02-11 22:45   ` Al Viro
2020-02-12 14:26     ` Alexey Gladkov
2020-02-10 15:05 ` [PATCH v8 08/11] proc: instantiate only pids that we can ptrace on 'hidepid=4' mount option Alexey Gladkov
2020-02-10 16:29   ` Jordan Glover
2020-02-12 14:34     ` Alexey Gladkov
2020-02-10 15:05 ` [PATCH v8 09/11] proc: add option to mount only a pids subset Alexey Gladkov
2020-02-10 15:05 ` [PATCH v8 10/11] docs: proc: add documentation for "hidepid=4" and "subset=pidfs" options and new mount behavior Alexey Gladkov
2020-02-10 18:29   ` Andy Lutomirski
2020-02-12 16:03     ` Alexey Gladkov
2020-02-10 15:05 ` [PATCH v8 11/11] proc: Move hidepid values to uapi as they are user interface to mount Alexey Gladkov

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200210150519.538333-3-gladkov.alexey@gmail.com \
    --to=gladkov.alexey@gmail.com \
    --cc=adobriyan@gmail.com \
    --cc=akinobu.mita@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=bfields@fieldses.org \
    --cc=corbet@lwn.net \
    --cc=danielmicay@gmail.com \
    --cc=ebiederm@xmission.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=jlayton@poochiereds.net \
    --cc=keescook@chromium.org \
    --cc=kernel-hardening@lists.openwall.com \
    --cc=ldv@altlinux.org \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-security-module@vger.kernel.org \
    --cc=luto@kernel.org \
    --cc=mingo@kernel.org \
    --cc=oleg@redhat.com \
    --cc=solar@openwall.com \
    --cc=tixxdz@gmail.com \
    --cc=torvalds@linux-foundation.org \
    --cc=viro@zeniv.linux.org.uk \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-Fsdevel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-fsdevel/0 linux-fsdevel/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-fsdevel linux-fsdevel/ https://lore.kernel.org/linux-fsdevel \
		linux-fsdevel@vger.kernel.org
	public-inbox-index linux-fsdevel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-fsdevel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git