Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1947082AbdDYM1E (ORCPT ); Tue, 25 Apr 2017 08:27:04 -0400 Received: from mail-wm0-f66.google.com ([74.125.82.66]:34173 "EHLO mail-wm0-f66.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1947460AbdDYMYc (ORCPT ); Tue, 25 Apr 2017 08:24:32 -0400 From: Djalal Harouni To: Linux Kernel Mailing List , Andy Lutomirski , Kees Cook , Andrew Morton , linux-fsdevel@vger.kernel.org, kernel-hardening@lists.openwall.com, linux-security-module@vger.kernel.org Cc: Linux API , Dongsu Park , Casey Schaufler , James Morris , , Jeff Layton , , Alexander Viro , Alexey Dobriyan , Ingo Molnar , , Oleg Nesterov , Michal Hocko , Jonathan Corbet , Djalal Harouni Subject: [PATCH RFC v2 6/6] proc: flush task dcache entries from all procfs instances Date: Tue, 25 Apr 2017 14:23:58 +0200 Message-Id: <1493123038-30590-7-git-send-email-tixxdz@gmail.com> X-Mailer: git-send-email 2.5.5 In-Reply-To: <1493123038-30590-1-git-send-email-tixxdz@gmail.com> References: <1493123038-30590-1-git-send-email-tixxdz@gmail.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 6160 Lines: 204 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 --- fs/proc/base.c | 27 ++++++++++++++++++++++----- fs/proc/inode.c | 9 ++++++++- fs/proc/root.c | 10 ++++++++++ include/linux/pid_namespace.h | 42 ++++++++++++++++++++++++++++++++++++++++++ include/linux/proc_fs.h | 2 ++ 5 files changed, 84 insertions(+), 6 deletions(-) diff --git a/fs/proc/base.c b/fs/proc/base.c index a663284..3c35126 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -3030,7 +3030,8 @@ 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[PROC_NUMBUF]; @@ -3039,7 +3040,7 @@ static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid) name.name = buf; name.len = snprintf(buf, sizeof(buf), "%d", 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); @@ -3050,7 +3051,7 @@ static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid) name.name = buf; name.len = snprintf(buf, sizeof(buf), "%d", tgid); - leader = d_hash_and_lookup(mnt->mnt_root, &name); + leader = d_hash_and_lookup(mnt_root, &name); if (!leader) goto out; @@ -3105,14 +3106,30 @@ void proc_flush_task(struct task_struct *task) int i; struct pid *pid, *tgid; struct upid *upid; + struct proc_fs_info *fs_info_entry; + struct pid_namespace *pid_ns; + struct dentry *mnt_root; 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_entry, &pid_ns->procfs_mounts, + pidns_entry) { + if (proc_fs_newinstance(fs_info_entry)) { + mnt_root = fs_info_entry->sb->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/inode.c b/fs/proc/inode.c index b4ee4a1..f374dac 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -479,10 +479,17 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) int proc_fill_super(struct super_block *s, void *data, int silent) { struct proc_fs_info *fs_info = proc_sb(s); + struct pid_namespace *ns = get_pid_ns(fs_info->pid_ns); struct inode *root_inode; int ret; - get_pid_ns(fs_info->pid_ns); + fs_info->sb = s; + + if (proc_fs_newinstance(fs_info)) { + pidns_proc_lock(ns); + list_add_tail(&fs_info->pidns_entry, &ns->procfs_mounts); + pidns_proc_unlock(ns); + } if (!proc_parse_options(data, fs_info)) return -EINVAL; diff --git a/fs/proc/root.c b/fs/proc/root.c index f398c14..3f04584 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -248,6 +248,13 @@ 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); + + if (proc_fs_newinstance(fs_info)) { + pidns_proc_lock(ns); + list_del(&fs_info->pidns_entry); + pidns_proc_unlock(ns); + } + kill_anon_super(sb); put_pid_ns(ns); kfree(fs_info); @@ -363,6 +370,9 @@ int pid_ns_prepare_proc(struct pid_namespace *ns) return PTR_ERR(mnt); ns->proc_mnt = mnt; + init_rwsem(&ns->rw_procfs_mnts); + INIT_LIST_HEAD(&ns->procfs_mounts); + return 0; } diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 306bdc6..377b751 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -39,6 +39,8 @@ 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_procfs_mnts; + struct list_head procfs_mounts; /* list of separated procfs mounts */ #endif #ifdef CONFIG_BSD_PROCESS_ACCT struct fs_pin *bacct; @@ -105,4 +107,44 @@ extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk); void pidhash_init(void); void pidmap_init(void); +#ifdef CONFIG_PROC_FS +static inline void pidns_proc_lock(struct pid_namespace *pid_ns) +{ + down_write(&pid_ns->rw_procfs_mnts); +} + +static inline void pidns_proc_unlock(struct pid_namespace *pid_ns) +{ + up_write(&pid_ns->rw_procfs_mnts); +} + +static inline void pidns_proc_lock_shared(struct pid_namespace *pid_ns) +{ + down_read(&pid_ns->rw_procfs_mnts); +} + +static inline void pidns_proc_unlock_shared(struct pid_namespace *pid_ns) +{ + up_read(&pid_ns->rw_procfs_mnts); +} +#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 0fddb84..1af01c2 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -18,7 +18,9 @@ enum { /* definitions for proc mount option limit_pids */ }; struct proc_fs_info { + struct super_block *sb; struct pid_namespace *pid_ns; + struct list_head pidns_entry; /* Node in procfs_mounts of a pidns */ struct dentry *proc_self; /* For /proc/self */ struct dentry *proc_thread_self; /* For /proc/thread-self/ */ bool newinstance; /* Private flag for new separated instances */ -- 2.10.2