From patchwork Fri Nov 6 15:15:10 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Alexey Gladkov X-Patchwork-Id: 11887273 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 7226616C1 for ; Fri, 6 Nov 2020 15:21:33 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 5D85522228 for ; Fri, 6 Nov 2020 15:21:33 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727497AbgKFPVc (ORCPT ); Fri, 6 Nov 2020 10:21:32 -0500 Received: from raptor.unsafe.ru ([5.9.43.93]:49014 "EHLO raptor.unsafe.ru" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727020AbgKFPVc (ORCPT ); Fri, 6 Nov 2020 10:21:32 -0500 Received: from comp-core-i7-2640m-0182e6.redhat.com (ip-89-103-122-167.net.upcbroadband.cz [89.103.122.167]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)) (No client certificate requested) by raptor.unsafe.ru (Postfix) with ESMTPSA id 41BAB20A04; Fri, 6 Nov 2020 15:15:23 +0000 (UTC) From: Alexey Gladkov To: LKML , Linux FS Devel , "Eric W . Biederman" Cc: Alexey Gladkov , Alexander Viro , Kees Cook Subject: [PATCH v4 1/3] proc: Relax check of mount visibility Date: Fri, 6 Nov 2020 16:15:10 +0100 Message-Id: <6ab3588965e4451cc01a80da7ae4c82f9701465d.1604675649.git.gladkov.alexey@gmail.com> X-Mailer: git-send-email 2.25.4 In-Reply-To: References: MIME-Version: 1.0 X-Greylist: Sender succeeded SMTP AUTH, not delayed by milter-greylist-4.6.1 (raptor.unsafe.ru [5.9.43.93]); Fri, 06 Nov 2020 15:15:23 +0000 (UTC) Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Allow to mount of procfs with subset=pid option even if the entire procfs is not fully accessible to the user. Signed-off-by: Alexey Gladkov --- fs/namespace.c | 27 ++++++++++++++++----------- fs/proc/root.c | 17 ++++++++++------- include/linux/fs.h | 1 + 3 files changed, 27 insertions(+), 18 deletions(-) diff --git a/fs/namespace.c b/fs/namespace.c index 4a0f600a3328..ab9d607921da 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -3949,18 +3949,23 @@ static bool mnt_already_visible(struct mnt_namespace *ns, ((mnt_flags & MNT_ATIME_MASK) != (new_flags & MNT_ATIME_MASK))) continue; - /* This mount is not fully visible if there are any - * locked child mounts that cover anything except for - * empty directories. + /* If this filesystem is completely dynamic, then it + * makes no sense to check for any child mounts. */ - list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { - struct inode *inode = child->mnt_mountpoint->d_inode; - /* Only worry about locked mounts */ - if (!(child->mnt.mnt_flags & MNT_LOCKED)) - continue; - /* Is the directory permanetly empty? */ - if (!is_empty_dir_inode(inode)) - goto next; + if (!(sb->s_iflags & SB_I_DYNAMIC)) { + /* This mount is not fully visible if there are any + * locked child mounts that cover anything except for + * empty directories. + */ + list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { + struct inode *inode = child->mnt_mountpoint->d_inode; + /* Only worry about locked mounts */ + if (!(child->mnt.mnt_flags & MNT_LOCKED)) + continue; + /* Is the directory permanetly empty? */ + if (!is_empty_dir_inode(inode)) + goto next; + } } /* Preserve the locked attributes */ *new_mnt_flags |= mnt_flags & (MNT_LOCK_READONLY | \ diff --git a/fs/proc/root.c b/fs/proc/root.c index 5e444d4f9717..051ffe5e67ce 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -145,18 +145,22 @@ 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 void proc_apply_options(struct super_block *s, struct fs_context *fc, struct user_namespace *user_ns) { struct proc_fs_context *ctx = fc->fs_private; + struct proc_fs_info *fs_info = proc_sb_info(s); if (ctx->mask & (1 << Opt_gid)) fs_info->pid_gid = make_kgid(user_ns, ctx->gid); if (ctx->mask & (1 << Opt_hidepid)) fs_info->hide_pid = ctx->hidepid; - if (ctx->mask & (1 << Opt_subset)) + if (ctx->mask & (1 << Opt_subset)) { + if (ctx->pidonly == PROC_PIDONLY_ON) + s->s_iflags |= SB_I_DYNAMIC; fs_info->pidonly = ctx->pidonly; + } } static int proc_fill_super(struct super_block *s, struct fs_context *fc) @@ -170,9 +174,6 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc) 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_flags |= SB_NODIRATIME | SB_NOSUID | SB_NOEXEC; @@ -183,6 +184,9 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc) s->s_time_gran = 1; s->s_fs_info = fs_info; + fs_info->pid_ns = get_pid_ns(ctx->pid_ns); + proc_apply_options(s, fc, current_user_ns()); + /* * procfs isn't actually a stacking filesystem; however, there is * too much magic going on inside it to permit stacking things on @@ -216,11 +220,10 @@ 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 proc_fs_info *fs_info = proc_sb_info(sb); sync_filesystem(sb); - proc_apply_options(fs_info, fc, current_user_ns()); + proc_apply_options(sb, fc, current_user_ns()); return 0; } diff --git a/include/linux/fs.h b/include/linux/fs.h index f5abba86107d..aff5ed9e8f82 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1413,6 +1413,7 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ #define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 #define SB_I_UNTRUSTED_MOUNTER 0x00000040 +#define SB_I_DYNAMIC 0x00000080 #define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ From patchwork Fri Nov 6 15:15:11 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Alexey Gladkov X-Patchwork-Id: 11887267 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 300EC14C0 for ; Fri, 6 Nov 2020 15:21:32 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 13DF1208C7 for ; Fri, 6 Nov 2020 15:21:31 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727395AbgKFPVb (ORCPT ); Fri, 6 Nov 2020 10:21:31 -0500 Received: from raptor.unsafe.ru ([5.9.43.93]:49018 "EHLO raptor.unsafe.ru" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726813AbgKFPVa (ORCPT ); Fri, 6 Nov 2020 10:21:30 -0500 Received: from comp-core-i7-2640m-0182e6.redhat.com (ip-89-103-122-167.net.upcbroadband.cz [89.103.122.167]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)) (No client certificate requested) by raptor.unsafe.ru (Postfix) with ESMTPSA id 8542620A0A; Fri, 6 Nov 2020 15:15:23 +0000 (UTC) From: Alexey Gladkov To: LKML , Linux FS Devel , "Eric W . Biederman" Cc: Alexey Gladkov , Alexander Viro , Kees Cook Subject: [PATCH v4 2/3] proc: Show /proc/self/net only for CAP_NET_ADMIN Date: Fri, 6 Nov 2020 16:15:11 +0100 Message-Id: <8b31b58cd5331f86e6f5a927168ce3b8e97ca760.1604675649.git.gladkov.alexey@gmail.com> X-Mailer: git-send-email 2.25.4 In-Reply-To: References: MIME-Version: 1.0 X-Greylist: Sender succeeded SMTP AUTH, not delayed by milter-greylist-4.6.1 (raptor.unsafe.ru [5.9.43.93]); Fri, 06 Nov 2020 15:15:23 +0000 (UTC) Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Cache the mounters credentials and make access to the net directories contingent of the permissions of the mounter of proc. Show /proc/self/net only if mounter has CAP_NET_ADMIN and if proc is mounted with subset=pid option. Signed-off-by: Alexey Gladkov --- fs/proc/proc_net.c | 8 ++++++++ fs/proc/root.c | 7 +++++++ include/linux/proc_fs.h | 1 + 3 files changed, 16 insertions(+) diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index dba63b2429f0..c43fc5c907db 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -26,6 +26,7 @@ #include #include #include +#include #include "internal.h" @@ -275,6 +276,7 @@ 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); @@ -287,6 +289,12 @@ 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 051ffe5e67ce..0ab90e24d9ae 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -185,6 +185,8 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc) s->s_fs_info = fs_info; fs_info->pid_ns = get_pid_ns(ctx->pid_ns); + fs_info->mounter_cred = get_cred(fc->cred); + proc_apply_options(s, fc, current_user_ns()); /* @@ -220,9 +222,13 @@ 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 proc_fs_info *fs_info = proc_sb_info(sb); sync_filesystem(sb); + put_cred(fs_info->mounter_cred); + fs_info->mounter_cred = get_cred(fc->cred); + proc_apply_options(sb, fc, current_user_ns()); return 0; } @@ -277,6 +283,7 @@ static void proc_kill_sb(struct super_block *sb) kill_anon_super(sb); put_pid_ns(fs_info->pid_ns); + put_cred(fs_info->mounter_cred); kfree(fs_info); } diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index d1eed1b43651..ce00560789f6 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -63,6 +63,7 @@ struct proc_fs_info { kgid_t pid_gid; enum proc_hidepid hide_pid; enum proc_pidonly pidonly; + const struct cred *mounter_cred; }; static inline struct proc_fs_info *proc_sb_info(struct super_block *sb) From patchwork Fri Nov 6 15:15:12 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Alexey Gladkov X-Patchwork-Id: 11887271 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 21D761130 for ; Fri, 6 Nov 2020 15:21:33 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 0C632206E3 for ; Fri, 6 Nov 2020 15:21:32 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727494AbgKFPVb (ORCPT ); Fri, 6 Nov 2020 10:21:31 -0500 Received: from raptor.unsafe.ru ([5.9.43.93]:49016 "EHLO raptor.unsafe.ru" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726812AbgKFPVb (ORCPT ); Fri, 6 Nov 2020 10:21:31 -0500 X-Greylist: delayed 366 seconds by postgrey-1.27 at vger.kernel.org; Fri, 06 Nov 2020 10:21:30 EST Received: from comp-core-i7-2640m-0182e6.redhat.com (ip-89-103-122-167.net.upcbroadband.cz [89.103.122.167]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)) (No client certificate requested) by raptor.unsafe.ru (Postfix) with ESMTPSA id E60C220A0C; Fri, 6 Nov 2020 15:15:23 +0000 (UTC) From: Alexey Gladkov To: LKML , Linux FS Devel , "Eric W . Biederman" Cc: Alexey Gladkov , Alexander Viro , Kees Cook Subject: [PATCH v4 3/3] proc: Disable cancellation of subset=pid option Date: Fri, 6 Nov 2020 16:15:12 +0100 Message-Id: <2ef0e59e5c51859997e990b9cfbeb28e1f1a5787.1604675649.git.gladkov.alexey@gmail.com> X-Mailer: git-send-email 2.25.4 In-Reply-To: References: MIME-Version: 1.0 X-Greylist: Sender succeeded SMTP AUTH, not delayed by milter-greylist-4.6.1 (raptor.unsafe.ru [5.9.43.93]); Fri, 06 Nov 2020 15:15:24 +0000 (UTC) Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org There is no way to remount procfs mountpoint with subset=pid option without it. This is done in order not to make visible what was hidden since some checks occur during mount. This patch makes this limitation explicit and demonstrates the error. Signed-off-by: Alexey Gladkov --- fs/proc/root.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/fs/proc/root.c b/fs/proc/root.c index 0ab90e24d9ae..d4a91f48c430 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -145,7 +145,7 @@ static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param) return 0; } -static void proc_apply_options(struct super_block *s, +static int proc_apply_options(struct super_block *s, struct fs_context *fc, struct user_namespace *user_ns) { @@ -159,8 +159,11 @@ static void proc_apply_options(struct super_block *s, if (ctx->mask & (1 << Opt_subset)) { if (ctx->pidonly == PROC_PIDONLY_ON) s->s_iflags |= SB_I_DYNAMIC; + else if (fs_info->pidonly == PROC_PIDONLY_ON) + return invalf(fc, "proc: subset=pid cannot be unset\n"); fs_info->pidonly = ctx->pidonly; } + return 0; } static int proc_fill_super(struct super_block *s, struct fs_context *fc) @@ -187,7 +190,10 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc) fs_info->pid_ns = get_pid_ns(ctx->pid_ns); fs_info->mounter_cred = get_cred(fc->cred); - proc_apply_options(s, fc, current_user_ns()); + ret = proc_apply_options(s, fc, current_user_ns()); + if (ret) { + return ret; + } /* * procfs isn't actually a stacking filesystem; however, there is @@ -229,8 +235,7 @@ static int proc_reconfigure(struct fs_context *fc) put_cred(fs_info->mounter_cred); fs_info->mounter_cred = get_cred(fc->cred); - proc_apply_options(sb, fc, current_user_ns()); - return 0; + return proc_apply_options(sb, fc, current_user_ns()); } static int proc_get_tree(struct fs_context *fc)