From 22d917d80e842829d0ca0a561967d728eb1d6303 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 17 Nov 2011 00:11:58 -0800 Subject: userns: Rework the user_namespace adding uid/gid mapping support - Convert the old uid mapping functions into compatibility wrappers - Add a uid/gid mapping layer from user space uid and gids to kernel internal uids and gids that is extent based for simplicty and speed. * Working with number space after mapping uids/gids into their kernel internal version adds only mapping complexity over what we have today, leaving the kernel code easy to understand and test. - Add proc files /proc/self/uid_map /proc/self/gid_map These files display the mapping and allow a mapping to be added if a mapping does not exist. - Allow entering the user namespace without a uid or gid mapping. Since we are starting with an existing user our uids and gids still have global mappings so are still valid and useful they just don't have local mappings. The requirement for things to work are global uid and gid so it is odd but perfectly fine not to have a local uid and gid mapping. Not requiring global uid and gid mappings greatly simplifies the logic of setting up the uid and gid mappings by allowing the mappings to be set after the namespace is created which makes the slight weirdness worth it. - Make the mappings in the initial user namespace to the global uid/gid space explicit. Today it is an identity mapping but in the future we may want to twist this for debugging, similar to what we do with jiffies. - Document the memory ordering requirements of setting the uid and gid mappings. We only allow the mappings to be set once and there are no pointers involved so the requirments are trivial but a little atypical. Performance: In this scheme for the permission checks the performance is expected to stay the same as the actuall machine instructions should remain the same. The worst case I could think of is ls -l on a large directory where all of the stat results need to be translated with from kuids and kgids to uids and gids. So I benchmarked that case on my laptop with a dual core hyperthread Intel i5-2520M cpu with 3M of cpu cache. My benchmark consisted of going to single user mode where nothing else was running. On an ext4 filesystem opening 1,000,000 files and looping through all of the files 1000 times and calling fstat on the individuals files. This was to ensure I was benchmarking stat times where the inodes were in the kernels cache, but the inode values were not in the processors cache. My results: v3.4-rc1: ~= 156ns (unmodified v3.4-rc1 with user namespace support disabled) v3.4-rc1-userns-: ~= 155ns (v3.4-rc1 with my user namespace patches and user namespace support disabled) v3.4-rc1-userns+: ~= 164ns (v3.4-rc1 with my user namespace patches and user namespace support enabled) All of the configurations ran in roughly 120ns when I performed tests that ran in the cpu cache. So in summary the performance impact is: 1ns improvement in the worst case with user namespace support compiled out. 8ns aka 5% slowdown in the worst case with user namespace support compiled in. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- fs/proc/base.c | 77 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 77 insertions(+) (limited to 'fs/proc') diff --git a/fs/proc/base.c b/fs/proc/base.c index 1c8b280146d..2ee514c7e64 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -81,6 +81,7 @@ #include #include #include +#include #include #include #include @@ -2943,6 +2944,74 @@ static int proc_tgid_io_accounting(struct task_struct *task, char *buffer) } #endif /* CONFIG_TASK_IO_ACCOUNTING */ +#ifdef CONFIG_USER_NS +static int proc_id_map_open(struct inode *inode, struct file *file, + struct seq_operations *seq_ops) +{ + struct user_namespace *ns = NULL; + struct task_struct *task; + struct seq_file *seq; + int ret = -EINVAL; + + task = get_proc_task(inode); + if (task) { + rcu_read_lock(); + ns = get_user_ns(task_cred_xxx(task, user_ns)); + rcu_read_unlock(); + put_task_struct(task); + } + if (!ns) + goto err; + + ret = seq_open(file, seq_ops); + if (ret) + goto err_put_ns; + + seq = file->private_data; + seq->private = ns; + + return 0; +err_put_ns: + put_user_ns(ns); +err: + return ret; +} + +static int proc_id_map_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq = file->private_data; + struct user_namespace *ns = seq->private; + put_user_ns(ns); + return seq_release(inode, file); +} + +static int proc_uid_map_open(struct inode *inode, struct file *file) +{ + return proc_id_map_open(inode, file, &proc_uid_seq_operations); +} + +static int proc_gid_map_open(struct inode *inode, struct file *file) +{ + return proc_id_map_open(inode, file, &proc_gid_seq_operations); +} + +static const struct file_operations proc_uid_map_operations = { + .open = proc_uid_map_open, + .write = proc_uid_map_write, + .read = seq_read, + .llseek = seq_lseek, + .release = proc_id_map_release, +}; + +static const struct file_operations proc_gid_map_operations = { + .open = proc_gid_map_open, + .write = proc_gid_map_write, + .read = seq_read, + .llseek = seq_lseek, + .release = proc_id_map_release, +}; +#endif /* CONFIG_USER_NS */ + static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { @@ -3045,6 +3114,10 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_HARDWALL INF("hardwall", S_IRUGO, proc_pid_hardwall), #endif +#ifdef CONFIG_USER_NS + REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), + REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), +#endif }; static int proc_tgid_base_readdir(struct file * filp, @@ -3400,6 +3473,10 @@ static const struct pid_entry tid_base_stuff[] = { #ifdef CONFIG_HARDWALL INF("hardwall", S_IRUGO, proc_pid_hardwall), #endif +#ifdef CONFIG_USER_NS + REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), + REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), +#endif }; static int proc_tid_base_readdir(struct file * filp, -- cgit v1.2.3-18-g5258 From ae2975bc3476243b45a1e2344236d7920c268f38 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 14 Nov 2011 15:56:38 -0800 Subject: userns: Convert group_info values from gid_t to kgid_t. As a first step to converting struct cred to be all kuid_t and kgid_t values convert the group values stored in group_info to always be kgid_t values. Unless user namespaces are used this change should have no effect. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- fs/proc/array.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'fs/proc') diff --git a/fs/proc/array.c b/fs/proc/array.c index f9bd395b347..36a0a9192ec 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -81,6 +81,7 @@ #include #include #include +#include #include #include @@ -161,6 +162,7 @@ static inline const char *get_task_state(struct task_struct *tsk) static inline void task_state(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *p) { + struct user_namespace *user_ns = current_user_ns(); struct group_info *group_info; int g; struct fdtable *fdt = NULL; @@ -205,7 +207,8 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns, task_unlock(p); for (g = 0; g < min(group_info->ngroups, NGROUPS_SMALL); g++) - seq_printf(m, "%d ", GROUP_AT(group_info, g)); + seq_printf(m, "%d ", + from_kgid_munged(user_ns, GROUP_AT(group_info, g))); put_cred(cred); seq_putc(m, '\n'); -- cgit v1.2.3-18-g5258 From dcb0f22282e680ee5202ab7574ce78beb3803a9f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 9 Feb 2012 08:48:21 -0800 Subject: userns: Convert proc to use kuid/kgid where appropriate Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- fs/proc/array.c | 10 ++++++++-- fs/proc/base.c | 16 ++++++++-------- fs/proc/inode.c | 4 ++-- fs/proc/root.c | 2 +- 4 files changed, 19 insertions(+), 13 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/array.c b/fs/proc/array.c index 36a0a9192ec..dc4c5a7b9ec 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -191,8 +191,14 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns, task_tgid_nr_ns(p, ns), pid_nr_ns(pid, ns), ppid, tpid, - cred->uid, cred->euid, cred->suid, cred->fsuid, - cred->gid, cred->egid, cred->sgid, cred->fsgid); + from_kuid_munged(user_ns, cred->uid), + from_kuid_munged(user_ns, cred->euid), + from_kuid_munged(user_ns, cred->suid), + from_kuid_munged(user_ns, cred->fsuid), + from_kgid_munged(user_ns, cred->gid), + from_kgid_munged(user_ns, cred->egid), + from_kgid_munged(user_ns, cred->sgid), + from_kgid_munged(user_ns, cred->fsgid)); task_lock(p); if (p->files) diff --git a/fs/proc/base.c b/fs/proc/base.c index 2ee514c7e64..c47904994b7 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1562,8 +1562,8 @@ int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) generic_fillattr(inode, stat); rcu_read_lock(); - stat->uid = 0; - stat->gid = 0; + stat->uid = GLOBAL_ROOT_UID; + stat->gid = GLOBAL_ROOT_GID; task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) { if (!has_pid_permissions(pid, task, 2)) { @@ -1623,8 +1623,8 @@ int pid_revalidate(struct dentry *dentry, struct nameidata *nd) inode->i_gid = cred->egid; rcu_read_unlock(); } else { - inode->i_uid = 0; - inode->i_gid = 0; + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; } inode->i_mode &= ~(S_ISUID | S_ISGID); security_task_to_inode(task, inode); @@ -1811,8 +1811,8 @@ static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd) inode->i_gid = cred->egid; rcu_read_unlock(); } else { - inode->i_uid = 0; - inode->i_gid = 0; + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; } inode->i_mode &= ~(S_ISUID | S_ISGID); security_task_to_inode(task, inode); @@ -2061,8 +2061,8 @@ static int map_files_d_revalidate(struct dentry *dentry, struct nameidata *nd) inode->i_gid = cred->egid; rcu_read_unlock(); } else { - inode->i_uid = 0; - inode->i_gid = 0; + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; } security_task_to_inode(task, inode); status = 1; diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 205c9228083..554ecc54799 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -108,8 +108,8 @@ 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; - if (pid->pid_gid) - seq_printf(seq, ",gid=%lu", (unsigned long)pid->pid_gid); + if (!gid_eq(pid->pid_gid, GLOBAL_ROOT_GID)) + seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, pid->pid_gid)); if (pid->hide_pid != 0) seq_printf(seq, ",hidepid=%u", pid->hide_pid); diff --git a/fs/proc/root.c b/fs/proc/root.c index 46a15d8a29c..df4e4561dbb 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -67,7 +67,7 @@ static int proc_parse_options(char *options, struct pid_namespace *pid) case Opt_gid: if (match_int(&args[0], &option)) return 0; - pid->pid_gid = option; + pid->pid_gid = make_kgid(current_user_ns(), option); break; case Opt_hidepid: if (match_int(&args[0], &option)) -- cgit v1.2.3-18-g5258 From 091bd3ea4e7ff4da8509978b9be93dc9d8cf0680 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 13 Feb 2012 18:02:50 -0800 Subject: userns: Convert sysctl permission checks to use kuid and kgids. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- fs/proc/proc_sysctl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 21d836f4029..3476bca8f7a 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -371,9 +371,9 @@ void register_sysctl_root(struct ctl_table_root *root) static int test_perm(int mode, int op) { - if (!current_euid()) + if (uid_eq(current_euid(), GLOBAL_ROOT_UID)) mode >>= 6; - else if (in_egroup_p(0)) + else if (in_egroup_p(GLOBAL_ROOT_GID)) mode >>= 3; if ((op & ~mode & (MAY_READ|MAY_WRITE|MAY_EXEC)) == 0) return 0; -- cgit v1.2.3-18-g5258