From patchwork Sat Jan 25 13:05:37 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Alexey Gladkov X-Patchwork-Id: 11351589 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 771B51395 for ; Sat, 25 Jan 2020 13:07:28 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 55F172071E for ; Sat, 25 Jan 2020 13:07:28 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729623AbgAYNHT (ORCPT ); Sat, 25 Jan 2020 08:07:19 -0500 Received: from monster.unsafe.ru ([5.9.28.80]:41520 "EHLO mail.unsafe.ru" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1729262AbgAYNGv (ORCPT ); Sat, 25 Jan 2020 08:06:51 -0500 Received: from localhost.localdomain (ip-89-102-33-211.net.upcbroadband.cz [89.102.33.211]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by mail.unsafe.ru (Postfix) with ESMTPSA id 68C91C61B43; Sat, 25 Jan 2020 13:06:48 +0000 (UTC) From: Alexey Gladkov To: LKML , Kernel Hardening , Linux API , Linux FS Devel , Linux Security Module Cc: Akinobu Mita , Alexander Viro , Alexey Dobriyan , Alexey Gladkov , Andrew Morton , Andy Lutomirski , Daniel Micay , Djalal Harouni , "Dmitry V . Levin" , "Eric W . Biederman" , Greg Kroah-Hartman , Ingo Molnar , "J . Bruce Fields" , Jeff Layton , Jonathan Corbet , Kees Cook , Linus Torvalds , Oleg Nesterov , Solar Designer , Stephen Rothwell Subject: [PATCH v7 07/11] proc: flush task dcache entries from all procfs instances Date: Sat, 25 Jan 2020 14:05:37 +0100 Message-Id: <20200125130541.450409-8-gladkov.alexey@gmail.com> X-Mailer: git-send-email 2.24.1 In-Reply-To: <20200125130541.450409-1-gladkov.alexey@gmail.com> References: <20200125130541.450409-1-gladkov.alexey@gmail.com> MIME-Version: 1.0 Sender: linux-fsdevel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org This allows to flush dcache entries of a task on multiple procfs mounts per pid namespace. Cc: Kees Cook Cc: Andy Lutomirski Signed-off-by: Djalal Harouni Signed-off-by: Alexey Gladkov --- fs/proc/base.c | 23 ++++++++++++++----- fs/proc/root.c | 14 ++++++++++++ include/linux/pid_namespace.h | 42 +++++++++++++++++++++++++++++++++++ include/linux/proc_fs.h | 2 ++ 4 files changed, 76 insertions(+), 5 deletions(-) diff --git a/fs/proc/base.c b/fs/proc/base.c index 4ccb280a3e79..f4f1bcb28603 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -3133,7 +3133,7 @@ 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[10 + 1]; @@ -3142,7 +3142,7 @@ static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid) name.name = buf; name.len = snprintf(buf, sizeof(buf), "%u", 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); @@ -3153,7 +3153,7 @@ static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid) name.name = buf; name.len = snprintf(buf, sizeof(buf), "%u", tgid); - leader = d_hash_and_lookup(mnt->mnt_root, &name); + leader = d_hash_and_lookup(mnt_root, &name); if (!leader) goto out; @@ -3208,14 +3208,27 @@ void proc_flush_task(struct task_struct *task) int i; struct pid *pid, *tgid; struct upid *upid; + struct pid_namespace *pid_ns; + struct dentry *mnt_root; + struct proc_fs_info *fs_info; 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, &pid_ns->proc_mounts, pidns_entry) { + mnt_root = fs_info->m_super->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); } } diff --git a/fs/proc/root.c b/fs/proc/root.c index 5d5cba4c899b..3bb8df360cf7 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -112,6 +112,12 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc) proc_apply_options(ctx->fs_info, fc, pid_ns, current_user_ns()); + ctx->fs_info->m_super = s; + + pidns_proc_lock(pid_ns); + list_add_tail(&ctx->fs_info->pidns_entry, &pid_ns->proc_mounts); + pidns_proc_unlock(pid_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; @@ -215,6 +221,11 @@ 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); + + pidns_proc_lock(fs_info->pid_ns); + list_del(&fs_info->pidns_entry); + pidns_proc_unlock(fs_info->pid_ns); + kill_anon_super(sb); put_pid_ns(fs_info->pid_ns); kfree(fs_info); @@ -336,6 +347,9 @@ int pid_ns_prepare_proc(struct pid_namespace *ns) ctx->fs_info->pid_ns = ns; } + init_rwsem(&ns->rw_proc_mounts); + INIT_LIST_HEAD(&ns->proc_mounts); + mnt = fc_mount(fc); put_fs_context(fc); if (IS_ERR(mnt)) diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 66f47f1afe0d..297b39604312 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -26,6 +26,8 @@ struct pid_namespace { struct pid_namespace *parent; #ifdef CONFIG_PROC_FS struct vfsmount *proc_mnt; /* Internal proc mounted during each new pidns */ + struct rw_semaphore rw_proc_mounts; + struct list_head proc_mounts; /* list of separated procfs mounts */ #endif #ifdef CONFIG_BSD_PROCESS_ACCT struct fs_pin *bacct; @@ -90,4 +92,44 @@ 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_proc_mounts); +} + +static inline void pidns_proc_unlock(struct pid_namespace *pid_ns) +{ + up_write(&pid_ns->rw_proc_mounts); +} + +static inline void pidns_proc_lock_shared(struct pid_namespace *pid_ns) +{ + down_read(&pid_ns->rw_proc_mounts); +} + +static inline void pidns_proc_unlock_shared(struct pid_namespace *pid_ns) +{ + up_read(&pid_ns->rw_proc_mounts); +} +#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 */ diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 5f0b1b7e4271..f307940f8311 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -20,6 +20,8 @@ enum { }; struct proc_fs_info { + struct list_head pidns_entry; /* Node in procfs_mounts of a pidns */ + struct super_block *m_super; struct pid_namespace *pid_ns; struct dentry *proc_self; /* For /proc/self */ struct dentry *proc_thread_self; /* For /proc/thread-self */