From 975d6b3932d43b87a48d2107264ed0c9a7541d8d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 13 Nov 2011 12:16:43 -0800 Subject: vfs: Don't allow a user namespace root to make device nodes Safely making device nodes in a container is solvable but simply having the capability in a user namespace is not sufficient to make this work. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- fs/namei.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index 1898198abc3d..701954d68ac7 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2560,8 +2560,7 @@ int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) if (error) return error; - if ((S_ISCHR(mode) || S_ISBLK(mode)) && - !ns_capable(inode_userns(dir), CAP_MKNOD)) + if ((S_ISCHR(mode) || S_ISBLK(mode)) && !capable(CAP_MKNOD)) return -EPERM; if (!dir->i_op->mknod) -- cgit v1.2.3 From 57a39aa3e3ca00e371cec37be4f7c2e950eb1f1f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 16 Nov 2011 22:06:16 -0800 Subject: userns: Kill bogus declaration of function release_uids There is no release_uids function remove the declaration from sched.h Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 81a173c0897d..720ce8d98a7d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2184,7 +2184,6 @@ static inline struct user_struct *get_uid(struct user_struct *u) return u; } extern void free_uid(struct user_struct *); -extern void release_uids(struct user_namespace *ns); #include -- cgit v1.2.3 From 39fda8db80c9da028bc78ef444a51ea56f3cf0ad Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 3 Apr 2012 18:36:26 -0700 Subject: userns: Replace netlink uses of cap_raised with capable. In 2009 Philip Reiser notied that a few users of netlink connector interface needed a capability check and added the idiom cap_raised(nsp->eff_cap, CAP_SYS_ADMIN) to a few of them, on the premise that netlink was asynchronous. In 2011 Patrick McHardy noticed we were being silly because netlink is synchronous and removed eff_cap from the netlink_skb_params and changed the idiom to cap_raised(current_cap(), CAP_SYS_ADMIN). Looking at those spots with a fresh eye we should be calling capable(CAP_SYS_ADMIN). The only reason I can see for not calling capable is that it once appeared we were not in the same task as the caller which would have made calling capable() impossible. In the initial user_namespace the only difference between between cap_raised(current_cap(), CAP_SYS_ADMIN) and capable(CAP_SYS_ADMIN) are a few sanity checks and the fact that capable(CAP_SYS_ADMIN) sets PF_SUPERPRIV if we use the capability. Since we are going to be using root privilege setting PF_SUPERPRIV seems the right thing to do. The motivation for this that patch is that in a child user namespace cap_raised(current_cap(),...) tests your capabilities with respect to that child user namespace not capabilities in the initial user namespace and thus will allow processes that should be unprivielged to use the kernel services that are only protected with cap_raised(current_cap(),..). To fix possible user_namespace issues and to just clean up the code replace cap_raised(current_cap(), CAP_SYS_ADMIN) with capable(CAP_SYS_ADMIN). Acked-by: Serge E. Hallyn Reviewed-by: James Morris Acked-by: Andrew G. Morgan Cc: Patrick McHardy Cc: Philipp Reisner Cc: Serge E. Hallyn Cc: Vasiliy Kulikov Cc: David Howells Signed-off-by: Eric W. Biederman --- drivers/block/drbd/drbd_nl.c | 2 +- drivers/md/dm-log-userspace-transfer.c | 2 +- drivers/video/uvesafb.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index abfaacaaf346..946166e13953 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -2297,7 +2297,7 @@ static void drbd_connector_callback(struct cn_msg *req, struct netlink_skb_parms return; } - if (!cap_raised(current_cap(), CAP_SYS_ADMIN)) { + if (!capable(CAP_SYS_ADMIN)) { retcode = ERR_PERM; goto fail; } diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c index 1f23e048f077..08d9a207259a 100644 --- a/drivers/md/dm-log-userspace-transfer.c +++ b/drivers/md/dm-log-userspace-transfer.c @@ -134,7 +134,7 @@ static void cn_ulog_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp) { struct dm_ulog_request *tfr = (struct dm_ulog_request *)(msg + 1); - if (!cap_raised(current_cap(), CAP_SYS_ADMIN)) + if (!capable(CAP_SYS_ADMIN)) return; spin_lock(&receiving_list_lock); diff --git a/drivers/video/uvesafb.c b/drivers/video/uvesafb.c index 260cca7ddb41..9f7d27a6bdb1 100644 --- a/drivers/video/uvesafb.c +++ b/drivers/video/uvesafb.c @@ -73,7 +73,7 @@ static void uvesafb_cn_callback(struct cn_msg *msg, struct netlink_skb_parms *ns struct uvesafb_task *utask; struct uvesafb_ktask *task; - if (!cap_raised(current_cap(), CAP_SYS_ADMIN)) + if (!capable(CAP_SYS_ADMIN)) return; if (msg->seq >= UVESAFB_TASKS_MAX) -- cgit v1.2.3 From 74ba508f60c3650595297b33a4cdfd02e443194e Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 3 Mar 2012 18:58:11 -0800 Subject: userns: Remove unnecessary cast to struct user_struct when copying cred->user. In struct cred the user member is and has always been declared struct user_struct *user. At most a constant struct cred will have a constant pointer to non-constant user_struct so remove this unnecessary cast. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- kernel/sys.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/sys.c b/kernel/sys.c index e7006eb6c1e4..f7a43514ac65 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -209,7 +209,7 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); break; case PRIO_USER: - user = (struct user_struct *) cred->user; + user = cred->user; if (!who) who = cred->uid; else if ((who != cred->uid) && @@ -274,7 +274,7 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who) } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); break; case PRIO_USER: - user = (struct user_struct *) cred->user; + user = cred->user; if (!who) who = cred->uid; else if ((who != cred->uid) && -- cgit v1.2.3 From 7e6bd8fadd1216f50468f965d0308f45e5109ced Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 14 Nov 2011 19:29:17 -0800 Subject: cred: Add forward declaration of init_user_ns in all cases. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- include/linux/cred.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/cred.h b/include/linux/cred.h index adadf71a7327..d12c4e475c15 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -357,11 +357,11 @@ static inline void put_cred(const struct cred *_cred) #define current_user() (current_cred_xxx(user)) #define current_security() (current_cred_xxx(security)) +extern struct user_namespace init_user_ns; #ifdef CONFIG_USER_NS #define current_user_ns() (current_cred_xxx(user_ns)) #define task_user_ns(task) (task_cred_xxx((task), user_ns)) #else -extern struct user_namespace init_user_ns; #define current_user_ns() (&init_user_ns) #define task_user_ns(task) (&init_user_ns) #endif -- cgit v1.2.3 From c4a4d603796c727b9555867571f89483be9c565e Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 16 Nov 2011 23:15:31 -0800 Subject: userns: Use cred->user_ns instead of cred->user->user_ns Optimize performance and prepare for the removal of the user_ns reference from user_struct. Remove the slow long walk through cred->user->user_ns and instead go straight to cred->user_ns. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- fs/ecryptfs/messaging.c | 2 +- ipc/namespace.c | 2 +- kernel/ptrace.c | 4 ++-- kernel/sched/core.c | 2 +- kernel/signal.c | 4 ++-- kernel/sys.c | 8 ++++---- kernel/user_namespace.c | 4 ++-- kernel/utsname.c | 2 +- security/commoncap.c | 14 +++++++------- security/keys/key.c | 2 +- security/keys/permission.c | 2 +- security/keys/process_keys.c | 2 +- 12 files changed, 24 insertions(+), 24 deletions(-) diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c index ab2248090515..a750f957b145 100644 --- a/fs/ecryptfs/messaging.c +++ b/fs/ecryptfs/messaging.c @@ -303,7 +303,7 @@ int ecryptfs_process_response(struct ecryptfs_message *msg, uid_t euid, mutex_unlock(&ecryptfs_daemon_hash_mux); goto wake_up; } - tsk_user_ns = __task_cred(msg_ctx->task)->user->user_ns; + tsk_user_ns = __task_cred(msg_ctx->task)->user_ns; ctx_euid = task_euid(msg_ctx->task); rc = ecryptfs_find_daemon_by_euid(&daemon, ctx_euid, tsk_user_ns); rcu_read_unlock(); diff --git a/ipc/namespace.c b/ipc/namespace.c index ce0a647869b1..f362298c5ce4 100644 --- a/ipc/namespace.c +++ b/ipc/namespace.c @@ -46,7 +46,7 @@ static struct ipc_namespace *create_ipc_ns(struct task_struct *tsk, ipcns_notify(IPCNS_CREATED); register_ipcns_notifier(ns); - ns->user_ns = get_user_ns(task_cred_xxx(tsk, user)->user_ns); + ns->user_ns = get_user_ns(task_cred_xxx(tsk, user_ns)); return ns; } diff --git a/kernel/ptrace.c b/kernel/ptrace.c index ee8d49b9c309..24e0a5a94824 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -198,7 +198,7 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode) return 0; rcu_read_lock(); tcred = __task_cred(task); - if (cred->user->user_ns == tcred->user->user_ns && + if (cred->user_ns == tcred->user_ns && (cred->uid == tcred->euid && cred->uid == tcred->suid && cred->uid == tcred->uid && @@ -206,7 +206,7 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode) cred->gid == tcred->sgid && cred->gid == tcred->gid)) goto ok; - if (ptrace_has_cap(tcred->user->user_ns, mode)) + if (ptrace_has_cap(tcred->user_ns, mode)) goto ok; rcu_read_unlock(); return -EPERM; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 4603b9d8f30a..96bff855b866 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4042,7 +4042,7 @@ static bool check_same_owner(struct task_struct *p) rcu_read_lock(); pcred = __task_cred(p); - if (cred->user->user_ns == pcred->user->user_ns) + if (cred->user_ns == pcred->user_ns) match = (cred->euid == pcred->euid || cred->euid == pcred->uid); else diff --git a/kernel/signal.c b/kernel/signal.c index 17afcaf582d0..e2c5d84f2dac 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -767,14 +767,14 @@ static int kill_ok_by_cred(struct task_struct *t) const struct cred *cred = current_cred(); const struct cred *tcred = __task_cred(t); - if (cred->user->user_ns == tcred->user->user_ns && + if (cred->user_ns == tcred->user_ns && (cred->euid == tcred->suid || cred->euid == tcred->uid || cred->uid == tcred->suid || cred->uid == tcred->uid)) return 1; - if (ns_capable(tcred->user->user_ns, CAP_KILL)) + if (ns_capable(tcred->user_ns, CAP_KILL)) return 1; return 0; diff --git a/kernel/sys.c b/kernel/sys.c index f7a43514ac65..82d8714bbede 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -133,11 +133,11 @@ static bool set_one_prio_perm(struct task_struct *p) { const struct cred *cred = current_cred(), *pcred = __task_cred(p); - if (pcred->user->user_ns == cred->user->user_ns && + if (pcred->user_ns == cred->user_ns && (pcred->uid == cred->euid || pcred->euid == cred->euid)) return true; - if (ns_capable(pcred->user->user_ns, CAP_SYS_NICE)) + if (ns_capable(pcred->user_ns, CAP_SYS_NICE)) return true; return false; } @@ -1498,7 +1498,7 @@ static int check_prlimit_permission(struct task_struct *task) return 0; tcred = __task_cred(task); - if (cred->user->user_ns == tcred->user->user_ns && + if (cred->user_ns == tcred->user_ns && (cred->uid == tcred->euid && cred->uid == tcred->suid && cred->uid == tcred->uid && @@ -1506,7 +1506,7 @@ static int check_prlimit_permission(struct task_struct *task) cred->gid == tcred->sgid && cred->gid == tcred->gid)) return 0; - if (ns_capable(tcred->user->user_ns, CAP_SYS_RESOURCE)) + if (ns_capable(tcred->user_ns, CAP_SYS_RESOURCE)) return 0; return -EPERM; diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 3b906e98b1db..f084083a0fd3 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -90,7 +90,7 @@ uid_t user_ns_map_uid(struct user_namespace *to, const struct cred *cred, uid_t { struct user_namespace *tmp; - if (likely(to == cred->user->user_ns)) + if (likely(to == cred->user_ns)) return uid; @@ -112,7 +112,7 @@ gid_t user_ns_map_gid(struct user_namespace *to, const struct cred *cred, gid_t { struct user_namespace *tmp; - if (likely(to == cred->user->user_ns)) + if (likely(to == cred->user_ns)) return gid; /* Is cred->user the creator of the target user_ns diff --git a/kernel/utsname.c b/kernel/utsname.c index 405caf91aad5..679d97a5d3fd 100644 --- a/kernel/utsname.c +++ b/kernel/utsname.c @@ -43,7 +43,7 @@ static struct uts_namespace *clone_uts_ns(struct task_struct *tsk, down_read(&uts_sem); memcpy(&ns->name, &old_ns->name, sizeof(ns->name)); - ns->user_ns = get_user_ns(task_cred_xxx(tsk, user)->user_ns); + ns->user_ns = get_user_ns(task_cred_xxx(tsk, user_ns)); up_read(&uts_sem); return ns; } diff --git a/security/commoncap.c b/security/commoncap.c index 0cf4b53480a7..8b3e10e2eac7 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -81,7 +81,7 @@ int cap_capable(const struct cred *cred, struct user_namespace *targ_ns, return 0; /* Do we have the necessary capabilities? */ - if (targ_ns == cred->user->user_ns) + if (targ_ns == cred->user_ns) return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM; /* Have we tried all of the parent namespaces? */ @@ -136,10 +136,10 @@ int cap_ptrace_access_check(struct task_struct *child, unsigned int mode) rcu_read_lock(); cred = current_cred(); child_cred = __task_cred(child); - if (cred->user->user_ns == child_cred->user->user_ns && + if (cred->user_ns == child_cred->user_ns && cap_issubset(child_cred->cap_permitted, cred->cap_permitted)) goto out; - if (ns_capable(child_cred->user->user_ns, CAP_SYS_PTRACE)) + if (ns_capable(child_cred->user_ns, CAP_SYS_PTRACE)) goto out; ret = -EPERM; out: @@ -168,10 +168,10 @@ int cap_ptrace_traceme(struct task_struct *parent) rcu_read_lock(); cred = __task_cred(parent); child_cred = current_cred(); - if (cred->user->user_ns == child_cred->user->user_ns && + if (cred->user_ns == child_cred->user_ns && cap_issubset(child_cred->cap_permitted, cred->cap_permitted)) goto out; - if (has_ns_capability(parent, child_cred->user->user_ns, CAP_SYS_PTRACE)) + if (has_ns_capability(parent, child_cred->user_ns, CAP_SYS_PTRACE)) goto out; ret = -EPERM; out: @@ -214,7 +214,7 @@ static inline int cap_inh_is_capped(void) /* they are so limited unless the current task has the CAP_SETPCAP * capability */ - if (cap_capable(current_cred(), current_cred()->user->user_ns, + if (cap_capable(current_cred(), current_cred()->user_ns, CAP_SETPCAP, SECURITY_CAP_AUDIT) == 0) return 0; return 1; @@ -866,7 +866,7 @@ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, || ((new->securebits & SECURE_ALL_LOCKS & ~arg2)) /*[2]*/ || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS)) /*[3]*/ || (cap_capable(current_cred(), - current_cred()->user->user_ns, CAP_SETPCAP, + current_cred()->user_ns, CAP_SETPCAP, SECURITY_CAP_AUDIT) != 0) /*[4]*/ /* * [1] no changing of bits that are locked diff --git a/security/keys/key.c b/security/keys/key.c index 06783cffb3af..7e6034793af3 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -253,7 +253,7 @@ struct key *key_alloc(struct key_type *type, const char *desc, quotalen = desclen + type->def_datalen; /* get hold of the key tracking for this user */ - user = key_user_lookup(uid, cred->user->user_ns); + user = key_user_lookup(uid, cred->user_ns); if (!user) goto no_memory_1; diff --git a/security/keys/permission.c b/security/keys/permission.c index c35b5229e3cd..e146cbd714bd 100644 --- a/security/keys/permission.c +++ b/security/keys/permission.c @@ -36,7 +36,7 @@ int key_task_permission(const key_ref_t key_ref, const struct cred *cred, key = key_ref_to_ptr(key_ref); - if (key->user->user_ns != cred->user->user_ns) + if (key->user->user_ns != cred->user_ns) goto use_other_perms; /* use the second 8-bits of permissions for keys the caller owns */ diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c index be7ecb2018dd..70febff06da9 100644 --- a/security/keys/process_keys.c +++ b/security/keys/process_keys.c @@ -858,7 +858,7 @@ void key_replace_session_keyring(void) new-> sgid = old-> sgid; new->fsgid = old->fsgid; new->user = get_uid(old->user); - new->user_ns = new->user->user_ns; + new->user_ns = new->user_ns; new->group_info = get_group_info(old->group_info); new->securebits = old->securebits; -- cgit v1.2.3 From 0093ccb68f3753c0ba4d74c89d7e0f444b8d6123 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 16 Nov 2011 21:52:53 -0800 Subject: cred: Refcount the user_ns pointed to by the cred. struct user_struct will shortly loose it's user_ns reference so make the cred user_ns reference a proper reference complete with reference counting. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- include/linux/cred.h | 2 +- kernel/cred.c | 8 +++----- kernel/user_namespace.c | 8 +++++--- security/keys/process_keys.c | 2 +- 4 files changed, 10 insertions(+), 10 deletions(-) diff --git a/include/linux/cred.h b/include/linux/cred.h index d12c4e475c15..2c60ec802678 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -146,7 +146,7 @@ struct cred { void *security; /* subjective LSM security */ #endif struct user_struct *user; /* real user ID subscription */ - struct user_namespace *user_ns; /* cached user->user_ns */ + struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ struct group_info *group_info; /* supplementary groups for euid/fsgid */ struct rcu_head rcu; /* RCU deletion hook */ }; diff --git a/kernel/cred.c b/kernel/cred.c index 97b36eeca4c9..7a0d80669886 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -148,6 +148,7 @@ static void put_cred_rcu(struct rcu_head *rcu) if (cred->group_info) put_group_info(cred->group_info); free_uid(cred->user); + put_user_ns(cred->user_ns); kmem_cache_free(cred_jar, cred); } @@ -303,6 +304,7 @@ struct cred *prepare_creds(void) set_cred_subscribers(new, 0); get_group_info(new->group_info); get_uid(new->user); + get_user_ns(new->user_ns); #ifdef CONFIG_KEYS key_get(new->thread_keyring); @@ -412,11 +414,6 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) goto error_put; } - /* cache user_ns in cred. Doesn't need a refcount because it will - * stay pinned by cred->user - */ - new->user_ns = new->user->user_ns; - #ifdef CONFIG_KEYS /* new threads get their own thread keyrings if their parent already * had one */ @@ -676,6 +673,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) atomic_set(&new->usage, 1); set_cred_subscribers(new, 0); get_uid(new->user); + get_user_ns(new->user_ns); get_group_info(new->group_info); #ifdef CONFIG_KEYS diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index f084083a0fd3..58bb8781a778 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -24,7 +24,7 @@ static struct kmem_cache *user_ns_cachep __read_mostly; */ int create_user_ns(struct cred *new) { - struct user_namespace *ns; + struct user_namespace *ns, *parent_ns = new->user_ns; struct user_struct *root_user; int n; @@ -57,8 +57,10 @@ int create_user_ns(struct cred *new) #endif /* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */ - /* root_user holds a reference to ns, our reference can be dropped */ - put_user_ns(ns); + /* Leave the reference to our user_ns with the new cred */ + new->user_ns = ns; + + put_user_ns(parent_ns); return 0; } diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c index 70febff06da9..447fb7618ff3 100644 --- a/security/keys/process_keys.c +++ b/security/keys/process_keys.c @@ -858,7 +858,7 @@ void key_replace_session_keyring(void) new-> sgid = old-> sgid; new->fsgid = old->fsgid; new->user = get_uid(old->user); - new->user_ns = new->user_ns; + new->user_ns = get_user_ns(new->user_ns); new->group_info = get_group_info(old->group_info); new->securebits = old->securebits; -- cgit v1.2.3 From aeb3ae9da9b50a386b22af786d19b623e8d9f0fa Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 16 Nov 2011 21:59:43 -0800 Subject: userns: Add an explicit reference to the parent user namespace I am about to remove the struct user_namespace reference from struct user_struct. So keep an explicit track of the parent user namespace. Take advantage of this new reference and replace instances of user_ns->creator->user_ns with user_ns->parent. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- include/linux/user_namespace.h | 1 + kernel/user_namespace.c | 13 ++++++------- security/commoncap.c | 2 +- 3 files changed, 8 insertions(+), 8 deletions(-) diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index faf467944baf..dc2d85a76376 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -12,6 +12,7 @@ struct user_namespace { struct kref kref; struct hlist_head uidhash_table[UIDHASH_SZ]; + struct user_namespace *parent; struct user_struct *creator; struct work_struct destroyer; }; diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 58bb8781a778..c15e533d6bc5 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -45,6 +45,7 @@ int create_user_ns(struct cred *new) } /* set the new root user in the credentials under preparation */ + ns->parent = parent_ns; ns->creator = new->user; new->user = root_user; new->uid = new->euid = new->suid = new->fsuid = 0; @@ -60,8 +61,6 @@ int create_user_ns(struct cred *new) /* Leave the reference to our user_ns with the new cred */ new->user_ns = ns; - put_user_ns(parent_ns); - return 0; } @@ -72,10 +71,12 @@ int create_user_ns(struct cred *new) */ static void free_user_ns_work(struct work_struct *work) { - struct user_namespace *ns = + struct user_namespace *parent, *ns = container_of(work, struct user_namespace, destroyer); + parent = ns->parent; free_uid(ns->creator); kmem_cache_free(user_ns_cachep, ns); + put_user_ns(parent); } void free_user_ns(struct kref *kref) @@ -99,8 +100,7 @@ uid_t user_ns_map_uid(struct user_namespace *to, const struct cred *cred, uid_t /* Is cred->user the creator of the target user_ns * or the creator of one of it's parents? */ - for ( tmp = to; tmp != &init_user_ns; - tmp = tmp->creator->user_ns ) { + for ( tmp = to; tmp != &init_user_ns; tmp = tmp->parent ) { if (cred->user == tmp->creator) { return (uid_t)0; } @@ -120,8 +120,7 @@ gid_t user_ns_map_gid(struct user_namespace *to, const struct cred *cred, gid_t /* Is cred->user the creator of the target user_ns * or the creator of one of it's parents? */ - for ( tmp = to; tmp != &init_user_ns; - tmp = tmp->creator->user_ns ) { + for ( tmp = to; tmp != &init_user_ns; tmp = tmp->parent ) { if (cred->user == tmp->creator) { return (gid_t)0; } diff --git a/security/commoncap.c b/security/commoncap.c index 8b3e10e2eac7..435d074853f3 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -92,7 +92,7 @@ int cap_capable(const struct cred *cred, struct user_namespace *targ_ns, *If you have a capability in a parent user ns, then you have * it over all children user namespaces as well. */ - targ_ns = targ_ns->creator->user_ns; + targ_ns = targ_ns->parent; } /* We never get here */ -- cgit v1.2.3 From 6f9ac6d93a0916de09d11b0a247ade8f4347728b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 16 Nov 2011 22:57:55 -0800 Subject: mqueue: Explicitly capture the user namespace to send the notification to. Stop relying on user->user_ns which is going away and instead capture the user_namespace of the process we are supposed to notify. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- ipc/mqueue.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 28bd64ddeda3..b53cf3469d01 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -66,6 +66,7 @@ struct mqueue_inode_info { struct sigevent notify; struct pid* notify_owner; + struct user_namespace *notify_user_ns; struct user_struct *user; /* user who created, for accounting */ struct sock *notify_sock; struct sk_buff *notify_cookie; @@ -139,6 +140,7 @@ static struct inode *mqueue_get_inode(struct super_block *sb, INIT_LIST_HEAD(&info->e_wait_q[0].list); INIT_LIST_HEAD(&info->e_wait_q[1].list); info->notify_owner = NULL; + info->notify_user_ns = NULL; info->qsize = 0; info->user = NULL; /* set when all is ok */ memset(&info->attr, 0, sizeof(info->attr)); @@ -536,7 +538,7 @@ static void __do_notify(struct mqueue_inode_info *info) rcu_read_lock(); sig_i.si_pid = task_tgid_nr_ns(current, ns_of_pid(info->notify_owner)); - sig_i.si_uid = user_ns_map_uid(info->user->user_ns, + sig_i.si_uid = user_ns_map_uid(info->notify_user_ns, current_cred(), current_uid()); rcu_read_unlock(); @@ -550,7 +552,9 @@ static void __do_notify(struct mqueue_inode_info *info) } /* after notification unregisters process */ put_pid(info->notify_owner); + put_user_ns(info->notify_user_ns); info->notify_owner = NULL; + info->notify_user_ns = NULL; } wake_up(&info->wait_q); } @@ -575,7 +579,9 @@ static void remove_notification(struct mqueue_inode_info *info) netlink_sendskb(info->notify_sock, info->notify_cookie); } put_pid(info->notify_owner); + put_user_ns(info->notify_user_ns); info->notify_owner = NULL; + info->notify_user_ns = NULL; } static int mq_attr_ok(struct ipc_namespace *ipc_ns, struct mq_attr *attr) @@ -1140,6 +1146,7 @@ retry: } info->notify_owner = get_pid(task_tgid(current)); + info->notify_user_ns = get_user_ns(current_user_ns()); inode->i_atime = inode->i_ctime = CURRENT_TIME; } spin_unlock(&info->lock); -- cgit v1.2.3 From d0bd6594e286bd6145e04e19e8d3fa2e902cb800 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 16 Nov 2011 23:20:58 -0800 Subject: userns: Deprecate and rename the user_namespace reference in the user_struct With a user_ns reference in struct cred the only user of the user namespace reference in struct user_struct is to keep the uid hash table alive. The user_namespace reference in struct user_struct will be going away soon, and I have removed all of the references. Rename the field from user_ns to _user_ns so that the compiler can verify nothing follows the user struct to the user namespace anymore. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- include/linux/sched.h | 2 +- kernel/user.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 720ce8d98a7d..6867ae9bc8a0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -729,7 +729,7 @@ struct user_struct { /* Hash table maintenance information */ struct hlist_node uidhash_node; uid_t uid; - struct user_namespace *user_ns; + struct user_namespace *_user_ns; /* Don't use will be removed soon */ #ifdef CONFIG_PERF_EVENTS atomic_long_t locked_vm; diff --git a/kernel/user.c b/kernel/user.c index 71dd2363ab0f..d65fec0615a0 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -58,7 +58,7 @@ struct user_struct root_user = { .files = ATOMIC_INIT(0), .sigpending = ATOMIC_INIT(0), .locked_shm = 0, - .user_ns = &init_user_ns, + ._user_ns = &init_user_ns, }; /* @@ -72,7 +72,7 @@ static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent) static void uid_hash_remove(struct user_struct *up) { hlist_del_init(&up->uidhash_node); - put_user_ns(up->user_ns); + put_user_ns(up->_user_ns); /* It is safe to free the uid hash table now */ } static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent) @@ -153,7 +153,7 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid) new->uid = uid; atomic_set(&new->__count, 1); - new->user_ns = get_user_ns(ns); + new->_user_ns = get_user_ns(ns); /* * Before adding this, check whether we raced -- cgit v1.2.3 From 973c5914260d75292f71a4729753086b9e863d57 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 17 Nov 2011 01:59:07 -0800 Subject: userns: Start out with a full set of capabilities. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- kernel/user_namespace.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index c15e533d6bc5..e216e1e8ce84 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -11,6 +11,7 @@ #include #include #include +#include static struct kmem_cache *user_ns_cachep __read_mostly; @@ -52,6 +53,14 @@ int create_user_ns(struct cred *new) new->gid = new->egid = new->sgid = new->fsgid = 0; put_group_info(new->group_info); new->group_info = get_group_info(&init_groups); + /* Start with the same capabilities as init but useless for doing + * anything as the capabilities are bound to the new user namespace. + */ + new->securebits = SECUREBITS_DEFAULT; + new->cap_inheritable = CAP_EMPTY_SET; + new->cap_permitted = CAP_FULL_SET; + new->cap_effective = CAP_FULL_SET; + new->cap_bset = CAP_FULL_SET; #ifdef CONFIG_KEYS key_put(new->request_key_auth); new->request_key_auth = NULL; -- cgit v1.2.3 From 1a48e2ac034d47ed843081c4523b63c46b46888b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 14 Nov 2011 16:24:06 -0800 Subject: userns: Replace the hard to write inode_userns with inode_capable. This represents a change in strategy of how to handle user namespaces. Instead of tagging everything explicitly with a user namespace and bulking up all of the comparisons of uids and gids in the kernel, all uids and gids in use will have a mapping to a flat kuid and kgid spaces respectively. This allows much more of the existing logic to be preserved and in general allows for faster code. In this new and improved world we allow someone to utiliize capabilities over an inode if the inodes owner mapps into the capabilities holders user namespace and the user has capabilities in their user namespace. Which is simple and efficient. Moving the fs uid comparisons to be comparisons in a flat kuid space follows in later patches, something that is only significant if you are using user namespaces. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- fs/inode.c | 6 ++---- fs/namei.c | 18 +++++------------- include/linux/capability.h | 2 ++ include/linux/fs.h | 6 ------ kernel/capability.c | 19 +++++++++++++++++++ 5 files changed, 28 insertions(+), 23 deletions(-) diff --git a/fs/inode.c b/fs/inode.c index 9f4f5fecc096..f0c4ace408e4 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1732,11 +1732,9 @@ EXPORT_SYMBOL(inode_init_owner); */ bool inode_owner_or_capable(const struct inode *inode) { - struct user_namespace *ns = inode_userns(inode); - - if (current_user_ns() == ns && current_fsuid() == inode->i_uid) + if (current_fsuid() == inode->i_uid) return true; - if (ns_capable(ns, CAP_FOWNER)) + if (inode_capable(inode, CAP_FOWNER)) return true; return false; } diff --git a/fs/namei.c b/fs/namei.c index 701954d68ac7..941c4362e298 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -228,9 +228,6 @@ static int acl_permission_check(struct inode *inode, int mask) { unsigned int mode = inode->i_mode; - if (current_user_ns() != inode_userns(inode)) - goto other_perms; - if (likely(current_fsuid() == inode->i_uid)) mode >>= 6; else { @@ -244,7 +241,6 @@ static int acl_permission_check(struct inode *inode, int mask) mode >>= 3; } -other_perms: /* * If the DACs are ok we don't need any capability check. */ @@ -280,10 +276,10 @@ int generic_permission(struct inode *inode, int mask) if (S_ISDIR(inode->i_mode)) { /* DACs are overridable for directories */ - if (ns_capable(inode_userns(inode), CAP_DAC_OVERRIDE)) + if (inode_capable(inode, CAP_DAC_OVERRIDE)) return 0; if (!(mask & MAY_WRITE)) - if (ns_capable(inode_userns(inode), CAP_DAC_READ_SEARCH)) + if (inode_capable(inode, CAP_DAC_READ_SEARCH)) return 0; return -EACCES; } @@ -293,7 +289,7 @@ int generic_permission(struct inode *inode, int mask) * at least one exec bit set. */ if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO)) - if (ns_capable(inode_userns(inode), CAP_DAC_OVERRIDE)) + if (inode_capable(inode, CAP_DAC_OVERRIDE)) return 0; /* @@ -301,7 +297,7 @@ int generic_permission(struct inode *inode, int mask) */ mask &= MAY_READ | MAY_WRITE | MAY_EXEC; if (mask == MAY_READ) - if (ns_capable(inode_userns(inode), CAP_DAC_READ_SEARCH)) + if (inode_capable(inode, CAP_DAC_READ_SEARCH)) return 0; return -EACCES; @@ -1964,15 +1960,11 @@ static inline int check_sticky(struct inode *dir, struct inode *inode) if (!(dir->i_mode & S_ISVTX)) return 0; - if (current_user_ns() != inode_userns(inode)) - goto other_userns; if (inode->i_uid == fsuid) return 0; if (dir->i_uid == fsuid) return 0; - -other_userns: - return !ns_capable(inode_userns(inode), CAP_FOWNER); + return !inode_capable(inode, CAP_FOWNER); } /* diff --git a/include/linux/capability.h b/include/linux/capability.h index 12d52dedb229..a76eca907470 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -374,6 +374,7 @@ struct cpu_vfs_cap_data { #ifdef __KERNEL__ +struct inode; struct dentry; struct user_namespace; @@ -548,6 +549,7 @@ extern bool has_ns_capability_noaudit(struct task_struct *t, extern bool capable(int cap); extern bool ns_capable(struct user_namespace *ns, int cap); extern bool nsown_capable(int cap); +extern bool inode_capable(const struct inode *inode, int cap); /* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); diff --git a/include/linux/fs.h b/include/linux/fs.h index 135693e79f2b..a6c5efbee0d7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1522,12 +1522,6 @@ enum { #define vfs_check_frozen(sb, level) \ wait_event((sb)->s_wait_unfrozen, ((sb)->s_frozen < (level))) -/* - * until VFS tracks user namespaces for inodes, just make all files - * belong to init_user_ns - */ -extern struct user_namespace init_user_ns; -#define inode_userns(inode) (&init_user_ns) extern bool inode_owner_or_capable(const struct inode *inode); /* not quite ready to be deprecated, but... */ diff --git a/kernel/capability.c b/kernel/capability.c index 3f1adb6c6470..cc5f0718215d 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -419,3 +419,22 @@ bool nsown_capable(int cap) { return ns_capable(current_user_ns(), cap); } + +/** + * inode_capable - Check superior capability over inode + * @inode: The inode in question + * @cap: The capability in question + * + * Return true if the current task has the given superior capability + * targeted at it's own user namespace and that the given inode is owned + * by the current user namespace or a child namespace. + * + * Currently inodes can only be owned by the initial user namespace. + * + */ +bool inode_capable(const struct inode *inode, int cap) +{ + struct user_namespace *ns = current_user_ns(); + + return ns_capable(ns, cap) && (ns == &init_user_ns); +} -- cgit v1.2.3 From 7a4e7408c5cadb240e068a662251754a562355e3 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 14 Nov 2011 14:29:51 -0800 Subject: userns: Add kuid_t and kgid_t and associated infrastructure in uidgid.h Start distinguishing between internal kernel uids and gids and values that userspace can use. This is done by introducing two new types: kuid_t and kgid_t. These types and their associated functions are infrastructure are declared in the new header uidgid.h. Ultimately there will be a different implementation of the mapping functions for use with user namespaces. But to keep it simple we introduce the mapping functions first to separate the meat from the mechanical code conversions. Export overflowuid and overflowgid so we can use from_kuid_munged and from_kgid_munged in modular code. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- include/linux/uidgid.h | 176 +++++++++++++++++++++++++++++++++++++++++++++++++ kernel/sys.c | 2 - 2 files changed, 176 insertions(+), 2 deletions(-) create mode 100644 include/linux/uidgid.h diff --git a/include/linux/uidgid.h b/include/linux/uidgid.h new file mode 100644 index 000000000000..a0addb8e5889 --- /dev/null +++ b/include/linux/uidgid.h @@ -0,0 +1,176 @@ +#ifndef _LINUX_UIDGID_H +#define _LINUX_UIDGID_H + +/* + * A set of types for the internal kernel types representing uids and gids. + * + * The types defined in this header allow distinguishing which uids and gids in + * the kernel are values used by userspace and which uid and gid values are + * the internal kernel values. With the addition of user namespaces the values + * can be different. Using the type system makes it possible for the compiler + * to detect when we overlook these differences. + * + */ +#include +#include + +struct user_namespace; +extern struct user_namespace init_user_ns; + +#if defined(NOTYET) + +typedef struct { + uid_t val; +} kuid_t; + + +typedef struct { + gid_t val; +} kgid_t; + +#define KUIDT_INIT(value) (kuid_t){ value } +#define KGIDT_INIT(value) (kgid_t){ value } + +static inline uid_t __kuid_val(kuid_t uid) +{ + return uid.val; +} + +static inline gid_t __kgid_val(kgid_t gid) +{ + return gid.val; +} + +#else + +typedef uid_t kuid_t; +typedef gid_t kgid_t; + +static inline uid_t __kuid_val(kuid_t uid) +{ + return uid; +} + +static inline gid_t __kgid_val(kgid_t gid) +{ + return gid; +} + +#define KUIDT_INIT(value) ((kuid_t) value ) +#define KGIDT_INIT(value) ((kgid_t) value ) + +#endif + +#define GLOBAL_ROOT_UID KUIDT_INIT(0) +#define GLOBAL_ROOT_GID KGIDT_INIT(0) + +#define INVALID_UID KUIDT_INIT(-1) +#define INVALID_GID KGIDT_INIT(-1) + +static inline bool uid_eq(kuid_t left, kuid_t right) +{ + return __kuid_val(left) == __kuid_val(right); +} + +static inline bool gid_eq(kgid_t left, kgid_t right) +{ + return __kgid_val(left) == __kgid_val(right); +} + +static inline bool uid_gt(kuid_t left, kuid_t right) +{ + return __kuid_val(left) > __kuid_val(right); +} + +static inline bool gid_gt(kgid_t left, kgid_t right) +{ + return __kgid_val(left) > __kgid_val(right); +} + +static inline bool uid_gte(kuid_t left, kuid_t right) +{ + return __kuid_val(left) >= __kuid_val(right); +} + +static inline bool gid_gte(kgid_t left, kgid_t right) +{ + return __kgid_val(left) >= __kgid_val(right); +} + +static inline bool uid_lt(kuid_t left, kuid_t right) +{ + return __kuid_val(left) < __kuid_val(right); +} + +static inline bool gid_lt(kgid_t left, kgid_t right) +{ + return __kgid_val(left) < __kgid_val(right); +} + +static inline bool uid_lte(kuid_t left, kuid_t right) +{ + return __kuid_val(left) <= __kuid_val(right); +} + +static inline bool gid_lte(kgid_t left, kgid_t right) +{ + return __kgid_val(left) <= __kgid_val(right); +} + +static inline bool uid_valid(kuid_t uid) +{ + return !uid_eq(uid, INVALID_UID); +} + +static inline bool gid_valid(kgid_t gid) +{ + return !gid_eq(gid, INVALID_GID); +} + +static inline kuid_t make_kuid(struct user_namespace *from, uid_t uid) +{ + return KUIDT_INIT(uid); +} + +static inline kgid_t make_kgid(struct user_namespace *from, gid_t gid) +{ + return KGIDT_INIT(gid); +} + +static inline uid_t from_kuid(struct user_namespace *to, kuid_t kuid) +{ + return __kuid_val(kuid); +} + +static inline gid_t from_kgid(struct user_namespace *to, kgid_t kgid) +{ + return __kgid_val(kgid); +} + +static inline uid_t from_kuid_munged(struct user_namespace *to, kuid_t kuid) +{ + uid_t uid = from_kuid(to, kuid); + if (uid == (uid_t)-1) + uid = overflowuid; + return uid; +} + +static inline gid_t from_kgid_munged(struct user_namespace *to, kgid_t kgid) +{ + gid_t gid = from_kgid(to, kgid); + if (gid == (gid_t)-1) + gid = overflowgid; + return gid; +} + +static inline bool kuid_has_mapping(struct user_namespace *ns, kuid_t uid) +{ + return true; +} + +static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid) +{ + return true; +} + +#endif /* _LINUX_UIDGID_H */ diff --git a/kernel/sys.c b/kernel/sys.c index 82d8714bbede..71852417cfc8 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -93,10 +93,8 @@ int overflowuid = DEFAULT_OVERFLOWUID; int overflowgid = DEFAULT_OVERFLOWGID; -#ifdef CONFIG_UID16 EXPORT_SYMBOL(overflowuid); EXPORT_SYMBOL(overflowgid); -#endif /* * the same as above, but for filesystems which can only store a 16-bit -- cgit v1.2.3 From 5673a94c14574d7c6495c320c6b0e480673d54bd Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 17 Nov 2011 10:23:55 -0800 Subject: userns: Add a Kconfig option to enforce strict kuid and kgid type checks Make it possible to easily switch between strong mandatory type checks and relaxed type checks so that the code can easily be tested with the type checks and then built with the strong type checks disabled so the resulting code can be used. Require strong mandatory type checks when enabling the user namespace. It is very simple to make a typo and use the wrong type allowing conversions to/from userspace values to be bypassed by accident, the strong type checks prevent this. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- include/linux/uidgid.h | 2 +- init/Kconfig | 12 +++++++++++- 2 files changed, 12 insertions(+), 2 deletions(-) diff --git a/include/linux/uidgid.h b/include/linux/uidgid.h index a0addb8e5889..539856829caf 100644 --- a/include/linux/uidgid.h +++ b/include/linux/uidgid.h @@ -17,7 +17,7 @@ struct user_namespace; extern struct user_namespace init_user_ns; -#if defined(NOTYET) +#ifdef CONFIG_UIDGID_STRICT_TYPE_CHECKS typedef struct { uid_t val; diff --git a/init/Kconfig b/init/Kconfig index 72f33faca44f..86cf760893b3 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -828,7 +828,8 @@ config IPC_NS config USER_NS bool "User namespace (EXPERIMENTAL)" depends on EXPERIMENTAL - default y + select UIDGID_STRICT_TYPE_CHECKS + default n help This allows containers, i.e. vservers, to use user namespaces to provide different user info for different servers. @@ -852,6 +853,15 @@ config NET_NS endif # NAMESPACES +config UIDGID_STRICT_TYPE_CHECKS + bool "Require conversions between uid/gids and their internal representation" + default n + help + While the nececessary conversions are being added to all subsystems this option allows + the code to continue to build for unconverted subsystems. + + Say Y here if you want the strict type checking enabled + config SCHED_AUTOGROUP bool "Automatic process group scheduling" select EVENTFD -- cgit v1.2.3 From 7b44ab978b77a91b327058a0f4db7e6fcdb90b92 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 16 Nov 2011 23:20:58 -0800 Subject: userns: Disassociate user_struct from the user_namespace. Modify alloc_uid to take a kuid and make the user hash table global. Stop holding a reference to the user namespace in struct user_struct. This simplifies the code and makes the per user accounting not care about which user namespace a uid happens to appear in. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- fs/ioprio.c | 18 ++++++++++++++---- include/linux/sched.h | 8 ++++---- include/linux/user_namespace.h | 4 ---- kernel/sys.c | 34 +++++++++++++++++++++++----------- kernel/user.c | 28 +++++++++++++--------------- kernel/user_namespace.c | 6 +----- 6 files changed, 55 insertions(+), 43 deletions(-) diff --git a/fs/ioprio.c b/fs/ioprio.c index 0f1b9515213b..8e35e964d9ed 100644 --- a/fs/ioprio.c +++ b/fs/ioprio.c @@ -65,6 +65,7 @@ SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio) struct task_struct *p, *g; struct user_struct *user; struct pid *pgrp; + kuid_t uid; int ret; switch (class) { @@ -110,16 +111,21 @@ SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio) } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); break; case IOPRIO_WHO_USER: + uid = make_kuid(current_user_ns(), who); + if (!uid_valid(uid)) + break; if (!who) user = current_user(); else - user = find_user(who); + user = find_user(uid); if (!user) break; do_each_thread(g, p) { - if (__task_cred(p)->uid != who) + const struct cred *tcred = __task_cred(p); + kuid_t tcred_uid = make_kuid(tcred->user_ns, tcred->uid); + if (!uid_eq(tcred_uid, uid)) continue; ret = set_task_ioprio(p, ioprio); if (ret) @@ -174,6 +180,7 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who) struct task_struct *g, *p; struct user_struct *user; struct pid *pgrp; + kuid_t uid; int ret = -ESRCH; int tmpio; @@ -203,16 +210,19 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who) } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); break; case IOPRIO_WHO_USER: + uid = make_kuid(current_user_ns(), who); if (!who) user = current_user(); else - user = find_user(who); + user = find_user(uid); if (!user) break; do_each_thread(g, p) { - if (__task_cred(p)->uid != user->uid) + const struct cred *tcred = __task_cred(p); + kuid_t tcred_uid = make_kuid(tcred->user_ns, tcred->uid); + if (!uid_eq(tcred_uid, user->uid)) continue; tmpio = get_task_ioprio(p); if (tmpio < 0) diff --git a/include/linux/sched.h b/include/linux/sched.h index 6867ae9bc8a0..5fdc1ebbcbc4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -90,6 +90,7 @@ struct sched_param { #include #include #include +#include #include @@ -728,8 +729,7 @@ struct user_struct { /* Hash table maintenance information */ struct hlist_node uidhash_node; - uid_t uid; - struct user_namespace *_user_ns; /* Don't use will be removed soon */ + kuid_t uid; #ifdef CONFIG_PERF_EVENTS atomic_long_t locked_vm; @@ -738,7 +738,7 @@ struct user_struct { extern int uids_sysfs_init(void); -extern struct user_struct *find_user(uid_t); +extern struct user_struct *find_user(kuid_t); extern struct user_struct root_user; #define INIT_USER (&root_user) @@ -2177,7 +2177,7 @@ extern struct task_struct *find_task_by_pid_ns(pid_t nr, extern void __set_special_pids(struct pid *pid); /* per-UID process charging. */ -extern struct user_struct * alloc_uid(struct user_namespace *, uid_t); +extern struct user_struct * alloc_uid(kuid_t); static inline struct user_struct *get_uid(struct user_struct *u) { atomic_inc(&u->__count); diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index dc2d85a76376..d767508db4f9 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -6,12 +6,8 @@ #include #include -#define UIDHASH_BITS (CONFIG_BASE_SMALL ? 3 : 7) -#define UIDHASH_SZ (1 << UIDHASH_BITS) - struct user_namespace { struct kref kref; - struct hlist_head uidhash_table[UIDHASH_SZ]; struct user_namespace *parent; struct user_struct *creator; struct work_struct destroyer; diff --git a/kernel/sys.c b/kernel/sys.c index 71852417cfc8..f0c43b4b6657 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -175,6 +175,8 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) const struct cred *cred = current_cred(); int error = -EINVAL; struct pid *pgrp; + kuid_t cred_uid; + kuid_t uid; if (which > PRIO_USER || which < PRIO_PROCESS) goto out; @@ -207,18 +209,22 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); break; case PRIO_USER: + cred_uid = make_kuid(cred->user_ns, cred->uid); + uid = make_kuid(cred->user_ns, who); user = cred->user; if (!who) - who = cred->uid; - else if ((who != cred->uid) && - !(user = find_user(who))) + uid = cred_uid; + else if (!uid_eq(uid, cred_uid) && + !(user = find_user(uid))) goto out_unlock; /* No processes for this user */ do_each_thread(g, p) { - if (__task_cred(p)->uid == who) + const struct cred *tcred = __task_cred(p); + kuid_t tcred_uid = make_kuid(tcred->user_ns, tcred->uid); + if (uid_eq(tcred_uid, uid)) error = set_one_prio(p, niceval, error); } while_each_thread(g, p); - if (who != cred->uid) + if (!uid_eq(uid, cred_uid)) free_uid(user); /* For find_user() */ break; } @@ -242,6 +248,8 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who) const struct cred *cred = current_cred(); long niceval, retval = -ESRCH; struct pid *pgrp; + kuid_t cred_uid; + kuid_t uid; if (which > PRIO_USER || which < PRIO_PROCESS) return -EINVAL; @@ -272,21 +280,25 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who) } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); break; case PRIO_USER: + cred_uid = make_kuid(cred->user_ns, cred->uid); + uid = make_kuid(cred->user_ns, who); user = cred->user; if (!who) - who = cred->uid; - else if ((who != cred->uid) && - !(user = find_user(who))) + uid = cred_uid; + else if (!uid_eq(uid, cred_uid) && + !(user = find_user(uid))) goto out_unlock; /* No processes for this user */ do_each_thread(g, p) { - if (__task_cred(p)->uid == who) { + const struct cred *tcred = __task_cred(p); + kuid_t tcred_uid = make_kuid(tcred->user_ns, tcred->uid); + if (uid_eq(tcred_uid, uid)) { niceval = 20 - task_nice(p); if (niceval > retval) retval = niceval; } } while_each_thread(g, p); - if (who != cred->uid) + if (!uid_eq(uid, cred_uid)) free_uid(user); /* for find_user() */ break; } @@ -629,7 +641,7 @@ static int set_user(struct cred *new) { struct user_struct *new_user; - new_user = alloc_uid(current_user_ns(), new->uid); + new_user = alloc_uid(make_kuid(new->user_ns, new->uid)); if (!new_user) return -EAGAIN; diff --git a/kernel/user.c b/kernel/user.c index d65fec0615a0..025077e54a7c 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -34,11 +34,14 @@ EXPORT_SYMBOL_GPL(init_user_ns); * when changing user ID's (ie setuid() and friends). */ +#define UIDHASH_BITS (CONFIG_BASE_SMALL ? 3 : 7) +#define UIDHASH_SZ (1 << UIDHASH_BITS) #define UIDHASH_MASK (UIDHASH_SZ - 1) #define __uidhashfn(uid) (((uid >> UIDHASH_BITS) + uid) & UIDHASH_MASK) -#define uidhashentry(ns, uid) ((ns)->uidhash_table + __uidhashfn((uid))) +#define uidhashentry(uid) (uidhash_table + __uidhashfn((__kuid_val(uid)))) static struct kmem_cache *uid_cachep; +struct hlist_head uidhash_table[UIDHASH_SZ]; /* * The uidhash_lock is mostly taken from process context, but it is @@ -58,7 +61,7 @@ struct user_struct root_user = { .files = ATOMIC_INIT(0), .sigpending = ATOMIC_INIT(0), .locked_shm = 0, - ._user_ns = &init_user_ns, + .uid = GLOBAL_ROOT_UID, }; /* @@ -72,16 +75,15 @@ static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent) static void uid_hash_remove(struct user_struct *up) { hlist_del_init(&up->uidhash_node); - put_user_ns(up->_user_ns); /* It is safe to free the uid hash table now */ } -static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent) +static struct user_struct *uid_hash_find(kuid_t uid, struct hlist_head *hashent) { struct user_struct *user; struct hlist_node *h; hlist_for_each_entry(user, h, hashent, uidhash_node) { - if (user->uid == uid) { + if (uid_eq(user->uid, uid)) { atomic_inc(&user->__count); return user; } @@ -110,14 +112,13 @@ static void free_user(struct user_struct *up, unsigned long flags) * * If the user_struct could not be found, return NULL. */ -struct user_struct *find_user(uid_t uid) +struct user_struct *find_user(kuid_t uid) { struct user_struct *ret; unsigned long flags; - struct user_namespace *ns = current_user_ns(); spin_lock_irqsave(&uidhash_lock, flags); - ret = uid_hash_find(uid, uidhashentry(ns, uid)); + ret = uid_hash_find(uid, uidhashentry(uid)); spin_unlock_irqrestore(&uidhash_lock, flags); return ret; } @@ -136,9 +137,9 @@ void free_uid(struct user_struct *up) local_irq_restore(flags); } -struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid) +struct user_struct *alloc_uid(kuid_t uid) { - struct hlist_head *hashent = uidhashentry(ns, uid); + struct hlist_head *hashent = uidhashentry(uid); struct user_struct *up, *new; spin_lock_irq(&uidhash_lock); @@ -153,8 +154,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid) new->uid = uid; atomic_set(&new->__count, 1); - new->_user_ns = get_user_ns(ns); - /* * Before adding this, check whether we raced * on adding the same user already.. @@ -162,7 +161,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid) spin_lock_irq(&uidhash_lock); up = uid_hash_find(uid, hashent); if (up) { - put_user_ns(ns); key_put(new->uid_keyring); key_put(new->session_keyring); kmem_cache_free(uid_cachep, new); @@ -187,11 +185,11 @@ static int __init uid_cache_init(void) 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); for(n = 0; n < UIDHASH_SZ; ++n) - INIT_HLIST_HEAD(init_user_ns.uidhash_table + n); + INIT_HLIST_HEAD(uidhash_table + n); /* Insert the root user immediately (init already runs as root) */ spin_lock_irq(&uidhash_lock); - uid_hash_insert(&root_user, uidhashentry(&init_user_ns, 0)); + uid_hash_insert(&root_user, uidhashentry(GLOBAL_ROOT_UID)); spin_unlock_irq(&uidhash_lock); return 0; diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index e216e1e8ce84..898e973bd1e8 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -27,7 +27,6 @@ int create_user_ns(struct cred *new) { struct user_namespace *ns, *parent_ns = new->user_ns; struct user_struct *root_user; - int n; ns = kmem_cache_alloc(user_ns_cachep, GFP_KERNEL); if (!ns) @@ -35,11 +34,8 @@ int create_user_ns(struct cred *new) kref_init(&ns->kref); - for (n = 0; n < UIDHASH_SZ; ++n) - INIT_HLIST_HEAD(ns->uidhash_table + n); - /* Alloc new root user. */ - root_user = alloc_uid(ns, 0); + root_user = alloc_uid(make_kuid(ns, 0)); if (!root_user) { kmem_cache_free(user_ns_cachep, ns); return -ENOMEM; -- cgit v1.2.3 From 783291e6900292521a3895583785e0c04a56c5b3 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 17 Nov 2011 01:32:59 -0800 Subject: userns: Simplify the user_namespace by making userns->creator a kuid. - Transform userns->creator from a user_struct reference to a simple kuid_t, kgid_t pair. In cap_capable this allows the check to see if we are the creator of a namespace to become the classic suser style euid permission check. This allows us to remove the need for a struct cred in the mapping functions and still be able to dispaly the user namespace creators uid and gid as 0. - Remove the now unnecessary delayed_work in free_user_ns. All that is left for free_user_ns to do is to call kmem_cache_free and put_user_ns. Those functions can be called in any context so call them directly from free_user_ns removing the need for delayed work. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- include/linux/user_namespace.h | 4 ++-- kernel/user.c | 7 ++++--- kernel/user_namespace.c | 42 ++++++++++++++++++++---------------------- security/commoncap.c | 5 +++-- 4 files changed, 29 insertions(+), 29 deletions(-) diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index d767508db4f9..8a391bd53de2 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -9,8 +9,8 @@ struct user_namespace { struct kref kref; struct user_namespace *parent; - struct user_struct *creator; - struct work_struct destroyer; + kuid_t owner; + kgid_t group; }; extern struct user_namespace init_user_ns; diff --git a/kernel/user.c b/kernel/user.c index 025077e54a7c..cff385659175 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -25,7 +25,8 @@ struct user_namespace init_user_ns = { .kref = { .refcount = ATOMIC_INIT(3), }, - .creator = &root_user, + .owner = GLOBAL_ROOT_UID, + .group = GLOBAL_ROOT_GID, }; EXPORT_SYMBOL_GPL(init_user_ns); @@ -54,9 +55,9 @@ struct hlist_head uidhash_table[UIDHASH_SZ]; */ static DEFINE_SPINLOCK(uidhash_lock); -/* root_user.__count is 2, 1 for init task cred, 1 for init_user_ns->user_ns */ +/* root_user.__count is 1, for init task cred */ struct user_struct root_user = { - .__count = ATOMIC_INIT(2), + .__count = ATOMIC_INIT(1), .processes = ATOMIC_INIT(1), .files = ATOMIC_INIT(0), .sigpending = ATOMIC_INIT(0), diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 898e973bd1e8..ed08836558e0 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -27,6 +27,16 @@ int create_user_ns(struct cred *new) { struct user_namespace *ns, *parent_ns = new->user_ns; struct user_struct *root_user; + kuid_t owner = make_kuid(new->user_ns, new->euid); + kgid_t group = make_kgid(new->user_ns, new->egid); + + /* The creator needs a mapping in the parent user namespace + * or else we won't be able to reasonably tell userspace who + * created a user_namespace. + */ + if (!kuid_has_mapping(parent_ns, owner) || + !kgid_has_mapping(parent_ns, group)) + return -EPERM; ns = kmem_cache_alloc(user_ns_cachep, GFP_KERNEL); if (!ns) @@ -43,7 +53,9 @@ int create_user_ns(struct cred *new) /* set the new root user in the credentials under preparation */ ns->parent = parent_ns; - ns->creator = new->user; + ns->owner = owner; + ns->group = group; + free_uid(new->user); new->user = root_user; new->uid = new->euid = new->suid = new->fsuid = 0; new->gid = new->egid = new->sgid = new->fsgid = 0; @@ -63,35 +75,22 @@ int create_user_ns(struct cred *new) #endif /* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */ - /* Leave the reference to our user_ns with the new cred */ + /* Leave the new->user_ns reference with the new user namespace. */ + /* Leave the reference to our user_ns with the new cred. */ new->user_ns = ns; return 0; } -/* - * Deferred destructor for a user namespace. This is required because - * free_user_ns() may be called with uidhash_lock held, but we need to call - * back to free_uid() which will want to take the lock again. - */ -static void free_user_ns_work(struct work_struct *work) +void free_user_ns(struct kref *kref) { struct user_namespace *parent, *ns = - container_of(work, struct user_namespace, destroyer); + container_of(kref, struct user_namespace, kref); + parent = ns->parent; - free_uid(ns->creator); kmem_cache_free(user_ns_cachep, ns); put_user_ns(parent); } - -void free_user_ns(struct kref *kref) -{ - struct user_namespace *ns = - container_of(kref, struct user_namespace, kref); - - INIT_WORK(&ns->destroyer, free_user_ns_work); - schedule_work(&ns->destroyer); -} EXPORT_SYMBOL(free_user_ns); uid_t user_ns_map_uid(struct user_namespace *to, const struct cred *cred, uid_t uid) @@ -101,12 +100,11 @@ uid_t user_ns_map_uid(struct user_namespace *to, const struct cred *cred, uid_t if (likely(to == cred->user_ns)) return uid; - /* Is cred->user the creator of the target user_ns * or the creator of one of it's parents? */ for ( tmp = to; tmp != &init_user_ns; tmp = tmp->parent ) { - if (cred->user == tmp->creator) { + if (uid_eq(cred->user->uid, tmp->owner)) { return (uid_t)0; } } @@ -126,7 +124,7 @@ gid_t user_ns_map_gid(struct user_namespace *to, const struct cred *cred, gid_t * or the creator of one of it's parents? */ for ( tmp = to; tmp != &init_user_ns; tmp = tmp->parent ) { - if (cred->user == tmp->creator) { + if (uid_eq(cred->user->uid, tmp->owner)) { return (gid_t)0; } } diff --git a/security/commoncap.c b/security/commoncap.c index 435d074853f3..f2399d8afbe0 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -76,8 +76,9 @@ int cap_capable(const struct cred *cred, struct user_namespace *targ_ns, int cap, int audit) { for (;;) { - /* The creator of the user namespace has all caps. */ - if (targ_ns != &init_user_ns && targ_ns->creator == cred->user) + /* The owner of the user namespace has all caps. */ + if (targ_ns != &init_user_ns && uid_eq(targ_ns->owner, + make_kuid(cred->user_ns, cred->euid))) return 0; /* Do we have the necessary capabilities? */ -- cgit v1.2.3 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 ++++++ include/linux/uidgid.h | 24 ++ include/linux/user_namespace.h | 30 ++- kernel/user.c | 16 ++ kernel/user_namespace.c | 545 +++++++++++++++++++++++++++++++++++++---- 5 files changed, 644 insertions(+), 48 deletions(-) diff --git a/fs/proc/base.c b/fs/proc/base.c index 1c8b280146d7..2ee514c7e64a 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, diff --git a/include/linux/uidgid.h b/include/linux/uidgid.h index 539856829caf..8e522cbcef29 100644 --- a/include/linux/uidgid.h +++ b/include/linux/uidgid.h @@ -127,6 +127,28 @@ static inline bool gid_valid(kgid_t gid) return !gid_eq(gid, INVALID_GID); } +#ifdef CONFIG_USER_NS + +extern kuid_t make_kuid(struct user_namespace *from, uid_t uid); +extern kgid_t make_kgid(struct user_namespace *from, gid_t gid); + +extern uid_t from_kuid(struct user_namespace *to, kuid_t uid); +extern gid_t from_kgid(struct user_namespace *to, kgid_t gid); +extern uid_t from_kuid_munged(struct user_namespace *to, kuid_t uid); +extern gid_t from_kgid_munged(struct user_namespace *to, kgid_t gid); + +static inline bool kuid_has_mapping(struct user_namespace *ns, kuid_t uid) +{ + return from_kuid(ns, uid) != (uid_t) -1; +} + +static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid) +{ + return from_kgid(ns, gid) != (gid_t) -1; +} + +#else + static inline kuid_t make_kuid(struct user_namespace *from, uid_t uid) { return KUIDT_INIT(uid); @@ -173,4 +195,6 @@ static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid) return true; } +#endif /* CONFIG_USER_NS */ + #endif /* _LINUX_UIDGID_H */ diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 8a391bd53de2..4c9846d90741 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -6,7 +6,20 @@ #include #include +#define UID_GID_MAP_MAX_EXTENTS 5 + +struct uid_gid_map { /* 64 bytes -- 1 cache line */ + u32 nr_extents; + struct uid_gid_extent { + u32 first; + u32 lower_first; + u32 count; + } extent[UID_GID_MAP_MAX_EXTENTS]; +}; + struct user_namespace { + struct uid_gid_map uid_map; + struct uid_gid_map gid_map; struct kref kref; struct user_namespace *parent; kuid_t owner; @@ -33,9 +46,11 @@ static inline void put_user_ns(struct user_namespace *ns) kref_put(&ns->kref, free_user_ns); } -uid_t user_ns_map_uid(struct user_namespace *to, const struct cred *cred, uid_t uid); -gid_t user_ns_map_gid(struct user_namespace *to, const struct cred *cred, gid_t gid); - +struct seq_operations; +extern struct seq_operations proc_uid_seq_operations; +extern struct seq_operations proc_gid_seq_operations; +extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *); +extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *); #else static inline struct user_namespace *get_user_ns(struct user_namespace *ns) @@ -52,17 +67,18 @@ static inline void put_user_ns(struct user_namespace *ns) { } +#endif + static inline uid_t user_ns_map_uid(struct user_namespace *to, const struct cred *cred, uid_t uid) { - return uid; + return from_kuid_munged(to, make_kuid(cred->user_ns, uid)); } + static inline gid_t user_ns_map_gid(struct user_namespace *to, const struct cred *cred, gid_t gid) { - return gid; + return from_kgid_munged(to, make_kgid(cred->user_ns, gid)); } -#endif - #endif /* _LINUX_USER_H */ diff --git a/kernel/user.c b/kernel/user.c index cff385659175..f9e420e36699 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -22,6 +22,22 @@ * and 1 for... ? */ struct user_namespace init_user_ns = { + .uid_map = { + .nr_extents = 1, + .extent[0] = { + .first = 0, + .lower_first = 0, + .count = 4294967295, + }, + }, + .gid_map = { + .nr_extents = 1, + .extent[0] = { + .first = 0, + .lower_first = 0, + .count = 4294967295, + }, + }, .kref = { .refcount = ATOMIC_INIT(3), }, diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index ed08836558e0..7eff867bfac5 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -12,9 +12,19 @@ #include #include #include +#include +#include +#include +#include +#include +#include +#include static struct kmem_cache *user_ns_cachep __read_mostly; +static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid, + struct uid_gid_map *map); + /* * Create a new user namespace, deriving the creator from the user in the * passed credentials, and replacing that user with the new root user for the @@ -26,7 +36,6 @@ static struct kmem_cache *user_ns_cachep __read_mostly; int create_user_ns(struct cred *new) { struct user_namespace *ns, *parent_ns = new->user_ns; - struct user_struct *root_user; kuid_t owner = make_kuid(new->user_ns, new->euid); kgid_t group = make_kgid(new->user_ns, new->egid); @@ -38,29 +47,15 @@ int create_user_ns(struct cred *new) !kgid_has_mapping(parent_ns, group)) return -EPERM; - ns = kmem_cache_alloc(user_ns_cachep, GFP_KERNEL); + ns = kmem_cache_zalloc(user_ns_cachep, GFP_KERNEL); if (!ns) return -ENOMEM; kref_init(&ns->kref); - - /* Alloc new root user. */ - root_user = alloc_uid(make_kuid(ns, 0)); - if (!root_user) { - kmem_cache_free(user_ns_cachep, ns); - return -ENOMEM; - } - - /* set the new root user in the credentials under preparation */ ns->parent = parent_ns; ns->owner = owner; ns->group = group; - free_uid(new->user); - new->user = root_user; - new->uid = new->euid = new->suid = new->fsuid = 0; - new->gid = new->egid = new->sgid = new->fsgid = 0; - put_group_info(new->group_info); - new->group_info = get_group_info(&init_groups); + /* Start with the same capabilities as init but useless for doing * anything as the capabilities are bound to the new user namespace. */ @@ -93,44 +88,512 @@ void free_user_ns(struct kref *kref) } EXPORT_SYMBOL(free_user_ns); -uid_t user_ns_map_uid(struct user_namespace *to, const struct cred *cred, uid_t uid) +static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count) { - struct user_namespace *tmp; + unsigned idx, extents; + u32 first, last, id2; - if (likely(to == cred->user_ns)) - return uid; + id2 = id + count - 1; - /* Is cred->user the creator of the target user_ns - * or the creator of one of it's parents? - */ - for ( tmp = to; tmp != &init_user_ns; tmp = tmp->parent ) { - if (uid_eq(cred->user->uid, tmp->owner)) { - return (uid_t)0; - } + /* Find the matching extent */ + extents = map->nr_extents; + smp_read_barrier_depends(); + for (idx = 0; idx < extents; idx++) { + first = map->extent[idx].first; + last = first + map->extent[idx].count - 1; + if (id >= first && id <= last && + (id2 >= first && id2 <= last)) + break; + } + /* Map the id or note failure */ + if (idx < extents) + id = (id - first) + map->extent[idx].lower_first; + else + id = (u32) -1; + + return id; +} + +static u32 map_id_down(struct uid_gid_map *map, u32 id) +{ + unsigned idx, extents; + u32 first, last; + + /* Find the matching extent */ + extents = map->nr_extents; + smp_read_barrier_depends(); + for (idx = 0; idx < extents; idx++) { + first = map->extent[idx].first; + last = first + map->extent[idx].count - 1; + if (id >= first && id <= last) + break; + } + /* Map the id or note failure */ + if (idx < extents) + id = (id - first) + map->extent[idx].lower_first; + else + id = (u32) -1; + + return id; +} + +static u32 map_id_up(struct uid_gid_map *map, u32 id) +{ + unsigned idx, extents; + u32 first, last; + + /* Find the matching extent */ + extents = map->nr_extents; + smp_read_barrier_depends(); + for (idx = 0; idx < extents; idx++) { + first = map->extent[idx].lower_first; + last = first + map->extent[idx].count - 1; + if (id >= first && id <= last) + break; } + /* Map the id or note failure */ + if (idx < extents) + id = (id - first) + map->extent[idx].first; + else + id = (u32) -1; + + return id; +} + +/** + * make_kuid - Map a user-namespace uid pair into a kuid. + * @ns: User namespace that the uid is in + * @uid: User identifier + * + * Maps a user-namespace uid pair into a kernel internal kuid, + * and returns that kuid. + * + * When there is no mapping defined for the user-namespace uid + * pair INVALID_UID is returned. Callers are expected to test + * for and handle handle INVALID_UID being returned. INVALID_UID + * may be tested for using uid_valid(). + */ +kuid_t make_kuid(struct user_namespace *ns, uid_t uid) +{ + /* Map the uid to a global kernel uid */ + return KUIDT_INIT(map_id_down(&ns->uid_map, uid)); +} +EXPORT_SYMBOL(make_kuid); + +/** + * from_kuid - Create a uid from a kuid user-namespace pair. + * @targ: The user namespace we want a uid in. + * @kuid: The kernel internal uid to start with. + * + * Map @kuid into the user-namespace specified by @targ and + * return the resulting uid. + * + * There is always a mapping into the initial user_namespace. + * + * If @kuid has no mapping in @targ (uid_t)-1 is returned. + */ +uid_t from_kuid(struct user_namespace *targ, kuid_t kuid) +{ + /* Map the uid from a global kernel uid */ + return map_id_up(&targ->uid_map, __kuid_val(kuid)); +} +EXPORT_SYMBOL(from_kuid); + +/** + * from_kuid_munged - Create a uid from a kuid user-namespace pair. + * @targ: The user namespace we want a uid in. + * @kuid: The kernel internal uid to start with. + * + * Map @kuid into the user-namespace specified by @targ and + * return the resulting uid. + * + * There is always a mapping into the initial user_namespace. + * + * Unlike from_kuid from_kuid_munged never fails and always + * returns a valid uid. This makes from_kuid_munged appropriate + * for use in syscalls like stat and getuid where failing the + * system call and failing to provide a valid uid are not an + * options. + * + * If @kuid has no mapping in @targ overflowuid is returned. + */ +uid_t from_kuid_munged(struct user_namespace *targ, kuid_t kuid) +{ + uid_t uid; + uid = from_kuid(targ, kuid); + + if (uid == (uid_t) -1) + uid = overflowuid; + return uid; +} +EXPORT_SYMBOL(from_kuid_munged); + +/** + * make_kgid - Map a user-namespace gid pair into a kgid. + * @ns: User namespace that the gid is in + * @uid: group identifier + * + * Maps a user-namespace gid pair into a kernel internal kgid, + * and returns that kgid. + * + * When there is no mapping defined for the user-namespace gid + * pair INVALID_GID is returned. Callers are expected to test + * for and handle INVALID_GID being returned. INVALID_GID may be + * tested for using gid_valid(). + */ +kgid_t make_kgid(struct user_namespace *ns, gid_t gid) +{ + /* Map the gid to a global kernel gid */ + return KGIDT_INIT(map_id_down(&ns->gid_map, gid)); +} +EXPORT_SYMBOL(make_kgid); + +/** + * from_kgid - Create a gid from a kgid user-namespace pair. + * @targ: The user namespace we want a gid in. + * @kgid: The kernel internal gid to start with. + * + * Map @kgid into the user-namespace specified by @targ and + * return the resulting gid. + * + * There is always a mapping into the initial user_namespace. + * + * If @kgid has no mapping in @targ (gid_t)-1 is returned. + */ +gid_t from_kgid(struct user_namespace *targ, kgid_t kgid) +{ + /* Map the gid from a global kernel gid */ + return map_id_up(&targ->gid_map, __kgid_val(kgid)); +} +EXPORT_SYMBOL(from_kgid); + +/** + * from_kgid_munged - Create a gid from a kgid user-namespace pair. + * @targ: The user namespace we want a gid in. + * @kgid: The kernel internal gid to start with. + * + * Map @kgid into the user-namespace specified by @targ and + * return the resulting gid. + * + * There is always a mapping into the initial user_namespace. + * + * Unlike from_kgid from_kgid_munged never fails and always + * returns a valid gid. This makes from_kgid_munged appropriate + * for use in syscalls like stat and getgid where failing the + * system call and failing to provide a valid gid are not options. + * + * If @kgid has no mapping in @targ overflowgid is returned. + */ +gid_t from_kgid_munged(struct user_namespace *targ, kgid_t kgid) +{ + gid_t gid; + gid = from_kgid(targ, kgid); + + if (gid == (gid_t) -1) + gid = overflowgid; + return gid; +} +EXPORT_SYMBOL(from_kgid_munged); + +static int uid_m_show(struct seq_file *seq, void *v) +{ + struct user_namespace *ns = seq->private; + struct uid_gid_extent *extent = v; + struct user_namespace *lower_ns; + uid_t lower; - /* No useful relationship so no mapping */ - return overflowuid; + lower_ns = current_user_ns(); + if ((lower_ns == ns) && lower_ns->parent) + lower_ns = lower_ns->parent; + + lower = from_kuid(lower_ns, KUIDT_INIT(extent->lower_first)); + + seq_printf(seq, "%10u %10u %10u\n", + extent->first, + lower, + extent->count); + + return 0; } -gid_t user_ns_map_gid(struct user_namespace *to, const struct cred *cred, gid_t gid) +static int gid_m_show(struct seq_file *seq, void *v) { - struct user_namespace *tmp; + struct user_namespace *ns = seq->private; + struct uid_gid_extent *extent = v; + struct user_namespace *lower_ns; + gid_t lower; - if (likely(to == cred->user_ns)) - return gid; + lower_ns = current_user_ns(); + if ((lower_ns == ns) && lower_ns->parent) + lower_ns = lower_ns->parent; - /* Is cred->user the creator of the target user_ns - * or the creator of one of it's parents? + lower = from_kgid(lower_ns, KGIDT_INIT(extent->lower_first)); + + seq_printf(seq, "%10u %10u %10u\n", + extent->first, + lower, + extent->count); + + return 0; +} + +static void *m_start(struct seq_file *seq, loff_t *ppos, struct uid_gid_map *map) +{ + struct uid_gid_extent *extent = NULL; + loff_t pos = *ppos; + + if (pos < map->nr_extents) + extent = &map->extent[pos]; + + return extent; +} + +static void *uid_m_start(struct seq_file *seq, loff_t *ppos) +{ + struct user_namespace *ns = seq->private; + + return m_start(seq, ppos, &ns->uid_map); +} + +static void *gid_m_start(struct seq_file *seq, loff_t *ppos) +{ + struct user_namespace *ns = seq->private; + + return m_start(seq, ppos, &ns->gid_map); +} + +static void *m_next(struct seq_file *seq, void *v, loff_t *pos) +{ + (*pos)++; + return seq->op->start(seq, pos); +} + +static void m_stop(struct seq_file *seq, void *v) +{ + return; +} + +struct seq_operations proc_uid_seq_operations = { + .start = uid_m_start, + .stop = m_stop, + .next = m_next, + .show = uid_m_show, +}; + +struct seq_operations proc_gid_seq_operations = { + .start = gid_m_start, + .stop = m_stop, + .next = m_next, + .show = gid_m_show, +}; + +static DEFINE_MUTEX(id_map_mutex); + +static ssize_t map_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos, + int cap_setid, + struct uid_gid_map *map, + struct uid_gid_map *parent_map) +{ + struct seq_file *seq = file->private_data; + struct user_namespace *ns = seq->private; + struct uid_gid_map new_map; + unsigned idx; + struct uid_gid_extent *extent, *last = NULL; + unsigned long page = 0; + char *kbuf, *pos, *next_line; + ssize_t ret = -EINVAL; + + /* + * The id_map_mutex serializes all writes to any given map. + * + * Any map is only ever written once. + * + * An id map fits within 1 cache line on most architectures. + * + * On read nothing needs to be done unless you are on an + * architecture with a crazy cache coherency model like alpha. + * + * There is a one time data dependency between reading the + * count of the extents and the values of the extents. The + * desired behavior is to see the values of the extents that + * were written before the count of the extents. + * + * To achieve this smp_wmb() is used on guarantee the write + * order and smp_read_barrier_depends() is guaranteed that we + * don't have crazy architectures returning stale data. + * + */ + mutex_lock(&id_map_mutex); + + ret = -EPERM; + /* Only allow one successful write to the map */ + if (map->nr_extents != 0) + goto out; + + /* Require the appropriate privilege CAP_SETUID or CAP_SETGID + * over the user namespace in order to set the id mapping. */ - for ( tmp = to; tmp != &init_user_ns; tmp = tmp->parent ) { - if (uid_eq(cred->user->uid, tmp->owner)) { - return (gid_t)0; + if (!ns_capable(ns, cap_setid)) + goto out; + + /* Get a buffer */ + ret = -ENOMEM; + page = __get_free_page(GFP_TEMPORARY); + kbuf = (char *) page; + if (!page) + goto out; + + /* Only allow <= page size writes at the beginning of the file */ + ret = -EINVAL; + if ((*ppos != 0) || (count >= PAGE_SIZE)) + goto out; + + /* Slurp in the user data */ + ret = -EFAULT; + if (copy_from_user(kbuf, buf, count)) + goto out; + kbuf[count] = '\0'; + + /* Parse the user data */ + ret = -EINVAL; + pos = kbuf; + new_map.nr_extents = 0; + for (;pos; pos = next_line) { + extent = &new_map.extent[new_map.nr_extents]; + + /* Find the end of line and ensure I don't look past it */ + next_line = strchr(pos, '\n'); + if (next_line) { + *next_line = '\0'; + next_line++; + if (*next_line == '\0') + next_line = NULL; } + + pos = skip_spaces(pos); + extent->first = simple_strtoul(pos, &pos, 10); + if (!isspace(*pos)) + goto out; + + pos = skip_spaces(pos); + extent->lower_first = simple_strtoul(pos, &pos, 10); + if (!isspace(*pos)) + goto out; + + pos = skip_spaces(pos); + extent->count = simple_strtoul(pos, &pos, 10); + if (*pos && !isspace(*pos)) + goto out; + + /* Verify there is not trailing junk on the line */ + pos = skip_spaces(pos); + if (*pos != '\0') + goto out; + + /* Verify we have been given valid starting values */ + if ((extent->first == (u32) -1) || + (extent->lower_first == (u32) -1 )) + goto out; + + /* Verify count is not zero and does not cause the extent to wrap */ + if ((extent->first + extent->count) <= extent->first) + goto out; + if ((extent->lower_first + extent->count) <= extent->lower_first) + goto out; + + /* For now only accept extents that are strictly in order */ + if (last && + (((last->first + last->count) > extent->first) || + ((last->lower_first + last->count) > extent->lower_first))) + goto out; + + new_map.nr_extents++; + last = extent; + + /* Fail if the file contains too many extents */ + if ((new_map.nr_extents == UID_GID_MAP_MAX_EXTENTS) && + (next_line != NULL)) + goto out; } + /* Be very certaint the new map actually exists */ + if (new_map.nr_extents == 0) + goto out; + + ret = -EPERM; + /* Validate the user is allowed to use user id's mapped to. */ + if (!new_idmap_permitted(ns, cap_setid, &new_map)) + goto out; + + /* Map the lower ids from the parent user namespace to the + * kernel global id space. + */ + for (idx = 0; idx < new_map.nr_extents; idx++) { + u32 lower_first; + extent = &new_map.extent[idx]; + + lower_first = map_id_range_down(parent_map, + extent->lower_first, + extent->count); + + /* Fail if we can not map the specified extent to + * the kernel global id space. + */ + if (lower_first == (u32) -1) + goto out; + + extent->lower_first = lower_first; + } + + /* Install the map */ + memcpy(map->extent, new_map.extent, + new_map.nr_extents*sizeof(new_map.extent[0])); + smp_wmb(); + map->nr_extents = new_map.nr_extents; + + *ppos = count; + ret = count; +out: + mutex_unlock(&id_map_mutex); + if (page) + free_page(page); + return ret; +} + +ssize_t proc_uid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) +{ + struct seq_file *seq = file->private_data; + struct user_namespace *ns = seq->private; + + if (!ns->parent) + return -EPERM; + + return map_write(file, buf, size, ppos, CAP_SETUID, + &ns->uid_map, &ns->parent->uid_map); +} + +ssize_t proc_gid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) +{ + struct seq_file *seq = file->private_data; + struct user_namespace *ns = seq->private; + + if (!ns->parent) + return -EPERM; + + return map_write(file, buf, size, ppos, CAP_SETGID, + &ns->gid_map, &ns->parent->gid_map); +} + +static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid, + struct uid_gid_map *new_map) +{ + /* Allow the specified ids if we have the appropriate capability + * (CAP_SETUID or CAP_SETGID) over the parent user namespace. + */ + if (ns_capable(ns->parent, cap_setid)) + return true; - /* No useful relationship so no mapping */ - return overflowgid; + return false; } static __init int user_namespaces_init(void) -- cgit v1.2.3 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 --- arch/s390/kernel/compat_linux.c | 14 ++++++++++-- fs/nfsd/auth.c | 5 ++-- fs/proc/array.c | 5 +++- include/linux/cred.h | 9 ++++---- kernel/groups.c | 48 ++++++++++++++++++++------------------- kernel/uid16.c | 14 ++++++++++-- net/ipv4/ping.c | 11 ++++++--- net/sunrpc/auth_generic.c | 4 ++-- net/sunrpc/auth_gss/svcauth_gss.c | 7 +++++- net/sunrpc/auth_unix.c | 15 ++++++++---- net/sunrpc/svcauth_unix.c | 18 +++++++++++---- security/keys/permission.c | 3 ++- 12 files changed, 104 insertions(+), 49 deletions(-) diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index ab64bdbab2ae..f0273ed760ef 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -173,11 +173,14 @@ asmlinkage long sys32_setfsgid16(u16 gid) static int groups16_to_user(u16 __user *grouplist, struct group_info *group_info) { + struct user_namespace *user_ns = current_user_ns(); int i; u16 group; + kgid_t kgid; for (i = 0; i < group_info->ngroups; i++) { - group = (u16)GROUP_AT(group_info, i); + kgid = GROUP_AT(group_info, i); + group = (u16)from_kgid_munged(user_ns, kgid); if (put_user(group, grouplist+i)) return -EFAULT; } @@ -187,13 +190,20 @@ static int groups16_to_user(u16 __user *grouplist, struct group_info *group_info static int groups16_from_user(struct group_info *group_info, u16 __user *grouplist) { + struct user_namespace *user_ns = current_user_ns(); int i; u16 group; + kgid_t kgid; for (i = 0; i < group_info->ngroups; i++) { if (get_user(group, grouplist+i)) return -EFAULT; - GROUP_AT(group_info, i) = (gid_t)group; + + kgid = make_kgid(user_ns, (gid_t)group); + if (!gid_valid(kgid)) + return -EINVAL; + + GROUP_AT(group_info, i) = kgid; } return 0; diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index 79717a40daba..204438cc914e 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -1,6 +1,7 @@ /* Copyright (C) 1995, 1996 Olaf Kirch */ #include +#include #include "nfsd.h" #include "auth.h" @@ -56,8 +57,8 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) goto oom; for (i = 0; i < rqgi->ngroups; i++) { - if (!GROUP_AT(rqgi, i)) - GROUP_AT(gi, i) = exp->ex_anon_gid; + if (gid_eq(GLOBAL_ROOT_GID, GROUP_AT(rqgi, i))) + GROUP_AT(gi, i) = make_kgid(&init_user_ns, exp->ex_anon_gid); else GROUP_AT(gi, i) = GROUP_AT(rqgi, i); } diff --git a/fs/proc/array.c b/fs/proc/array.c index f9bd395b3473..36a0a9192ece 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'); diff --git a/include/linux/cred.h b/include/linux/cred.h index 2c60ec802678..0ab3cda4a774 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -17,6 +17,7 @@ #include #include #include +#include struct user_struct; struct cred; @@ -26,14 +27,14 @@ struct inode; * COW Supplementary groups list */ #define NGROUPS_SMALL 32 -#define NGROUPS_PER_BLOCK ((unsigned int)(PAGE_SIZE / sizeof(gid_t))) +#define NGROUPS_PER_BLOCK ((unsigned int)(PAGE_SIZE / sizeof(kgid_t))) struct group_info { atomic_t usage; int ngroups; int nblocks; - gid_t small_block[NGROUPS_SMALL]; - gid_t *blocks[0]; + kgid_t small_block[NGROUPS_SMALL]; + kgid_t *blocks[0]; }; /** @@ -66,7 +67,7 @@ extern struct group_info init_groups; extern void groups_free(struct group_info *); extern int set_current_groups(struct group_info *); extern int set_groups(struct cred *, struct group_info *); -extern int groups_search(const struct group_info *, gid_t); +extern int groups_search(const struct group_info *, kgid_t); /* access the groups "array" with this macro */ #define GROUP_AT(gi, i) \ diff --git a/kernel/groups.c b/kernel/groups.c index 99b53d1eb7ea..84156f2d4c8c 100644 --- a/kernel/groups.c +++ b/kernel/groups.c @@ -31,7 +31,7 @@ struct group_info *groups_alloc(int gidsetsize) group_info->blocks[0] = group_info->small_block; else { for (i = 0; i < nblocks; i++) { - gid_t *b; + kgid_t *b; b = (void *)__get_free_page(GFP_USER); if (!b) goto out_undo_partial_alloc; @@ -66,18 +66,15 @@ EXPORT_SYMBOL(groups_free); static int groups_to_user(gid_t __user *grouplist, const struct group_info *group_info) { + struct user_namespace *user_ns = current_user_ns(); int i; unsigned int count = group_info->ngroups; - for (i = 0; i < group_info->nblocks; i++) { - unsigned int cp_count = min(NGROUPS_PER_BLOCK, count); - unsigned int len = cp_count * sizeof(*grouplist); - - if (copy_to_user(grouplist, group_info->blocks[i], len)) + for (i = 0; i < count; i++) { + gid_t gid; + gid = from_kgid_munged(user_ns, GROUP_AT(group_info, i)); + if (put_user(gid, grouplist+i)) return -EFAULT; - - grouplist += NGROUPS_PER_BLOCK; - count -= cp_count; } return 0; } @@ -86,18 +83,21 @@ static int groups_to_user(gid_t __user *grouplist, static int groups_from_user(struct group_info *group_info, gid_t __user *grouplist) { + struct user_namespace *user_ns = current_user_ns(); int i; unsigned int count = group_info->ngroups; - for (i = 0; i < group_info->nblocks; i++) { - unsigned int cp_count = min(NGROUPS_PER_BLOCK, count); - unsigned int len = cp_count * sizeof(*grouplist); - - if (copy_from_user(group_info->blocks[i], grouplist, len)) + for (i = 0; i < count; i++) { + gid_t gid; + kgid_t kgid; + if (get_user(gid, grouplist+i)) return -EFAULT; - grouplist += NGROUPS_PER_BLOCK; - count -= cp_count; + kgid = make_kgid(user_ns, gid); + if (!gid_valid(kgid)) + return -EINVAL; + + GROUP_AT(group_info, i) = kgid; } return 0; } @@ -117,9 +117,9 @@ static void groups_sort(struct group_info *group_info) for (base = 0; base < max; base++) { int left = base; int right = left + stride; - gid_t tmp = GROUP_AT(group_info, right); + kgid_t tmp = GROUP_AT(group_info, right); - while (left >= 0 && GROUP_AT(group_info, left) > tmp) { + while (left >= 0 && gid_gt(GROUP_AT(group_info, left), tmp)) { GROUP_AT(group_info, right) = GROUP_AT(group_info, left); right = left; @@ -132,7 +132,7 @@ static void groups_sort(struct group_info *group_info) } /* a simple bsearch */ -int groups_search(const struct group_info *group_info, gid_t grp) +int groups_search(const struct group_info *group_info, kgid_t grp) { unsigned int left, right; @@ -143,9 +143,9 @@ int groups_search(const struct group_info *group_info, gid_t grp) right = group_info->ngroups; while (left < right) { unsigned int mid = (left+right)/2; - if (grp > GROUP_AT(group_info, mid)) + if (gid_gt(grp, GROUP_AT(group_info, mid))) left = mid + 1; - else if (grp < GROUP_AT(group_info, mid)) + else if (gid_lt(grp, GROUP_AT(group_info, mid))) right = mid; else return 1; @@ -262,7 +262,8 @@ int in_group_p(gid_t grp) int retval = 1; if (grp != cred->fsgid) - retval = groups_search(cred->group_info, grp); + retval = groups_search(cred->group_info, + make_kgid(cred->user_ns, grp)); return retval; } @@ -274,7 +275,8 @@ int in_egroup_p(gid_t grp) int retval = 1; if (grp != cred->egid) - retval = groups_search(cred->group_info, grp); + retval = groups_search(cred->group_info, + make_kgid(cred->user_ns, grp)); return retval; } diff --git a/kernel/uid16.c b/kernel/uid16.c index 51c6e89e8619..e530bc34c4cf 100644 --- a/kernel/uid16.c +++ b/kernel/uid16.c @@ -134,11 +134,14 @@ SYSCALL_DEFINE1(setfsgid16, old_gid_t, gid) static int groups16_to_user(old_gid_t __user *grouplist, struct group_info *group_info) { + struct user_namespace *user_ns = current_user_ns(); int i; old_gid_t group; + kgid_t kgid; for (i = 0; i < group_info->ngroups; i++) { - group = high2lowgid(GROUP_AT(group_info, i)); + kgid = GROUP_AT(group_info, i); + group = high2lowgid(from_kgid_munged(user_ns, kgid)); if (put_user(group, grouplist+i)) return -EFAULT; } @@ -149,13 +152,20 @@ static int groups16_to_user(old_gid_t __user *grouplist, static int groups16_from_user(struct group_info *group_info, old_gid_t __user *grouplist) { + struct user_namespace *user_ns = current_user_ns(); int i; old_gid_t group; + kgid_t kgid; for (i = 0; i < group_info->ngroups; i++) { if (get_user(group, grouplist+i)) return -EFAULT; - GROUP_AT(group_info, i) = low2highgid(group); + + kgid = make_kgid(user_ns, low2highgid(group)); + if (!gid_valid(kgid)) + return -EINVAL; + + GROUP_AT(group_info, i) = kgid; } return 0; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 50009c787bcd..9d3044ff45b9 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -205,17 +205,22 @@ static int ping_init_sock(struct sock *sk) gid_t range[2]; struct group_info *group_info = get_current_groups(); int i, j, count = group_info->ngroups; + kgid_t low, high; inet_get_ping_group_range_net(net, range, range+1); + low = make_kgid(&init_user_ns, range[0]); + high = make_kgid(&init_user_ns, range[1]); + if (!gid_valid(low) || !gid_valid(high) || gid_lt(high, low)) + return -EACCES; + if (range[0] <= group && group <= range[1]) return 0; for (i = 0; i < group_info->nblocks; i++) { int cp_count = min_t(int, NGROUPS_PER_BLOCK, count); - for (j = 0; j < cp_count; j++) { - group = group_info->blocks[i][j]; - if (range[0] <= group && group <= range[1]) + kgid_t gid = group_info->blocks[i][j]; + if (gid_lte(low, gid) && gid_lte(gid, high)) return 0; } diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c index 75762f346975..6ed6f201b022 100644 --- a/net/sunrpc/auth_generic.c +++ b/net/sunrpc/auth_generic.c @@ -160,8 +160,8 @@ generic_match(struct auth_cred *acred, struct rpc_cred *cred, int flags) if (gcred->acred.group_info->ngroups != acred->group_info->ngroups) goto out_nomatch; for (i = 0; i < gcred->acred.group_info->ngroups; i++) { - if (GROUP_AT(gcred->acred.group_info, i) != - GROUP_AT(acred->group_info, i)) + if (!gid_eq(GROUP_AT(gcred->acred.group_info, i), + GROUP_AT(acred->group_info, i))) goto out_nomatch; } out_match: diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 1600cfb1618c..28b62dbb6d1e 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include @@ -470,9 +471,13 @@ static int rsc_parse(struct cache_detail *cd, status = -EINVAL; for (i=0; i #include #include +#include #define NFS_NGROUPS 16 @@ -78,8 +79,11 @@ unx_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) groups = NFS_NGROUPS; cred->uc_gid = acred->gid; - for (i = 0; i < groups; i++) - cred->uc_gids[i] = GROUP_AT(acred->group_info, i); + for (i = 0; i < groups; i++) { + gid_t gid; + gid = from_kgid(&init_user_ns, GROUP_AT(acred->group_info, i)); + cred->uc_gids[i] = gid; + } if (i < NFS_NGROUPS) cred->uc_gids[i] = NOGROUP; @@ -126,9 +130,12 @@ unx_match(struct auth_cred *acred, struct rpc_cred *rcred, int flags) groups = acred->group_info->ngroups; if (groups > NFS_NGROUPS) groups = NFS_NGROUPS; - for (i = 0; i < groups ; i++) - if (cred->uc_gids[i] != GROUP_AT(acred->group_info, i)) + for (i = 0; i < groups ; i++) { + gid_t gid; + gid = from_kgid(&init_user_ns, GROUP_AT(acred->group_info, i)); + if (cred->uc_gids[i] != gid) return 0; + } if (groups < NFS_NGROUPS && cred->uc_gids[groups] != NOGROUP) return 0; diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 521d8f7dc833..71ec8530ec8c 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -14,6 +14,7 @@ #include #include #include +#include #define RPCDBG_FACILITY RPCDBG_AUTH #include @@ -530,11 +531,15 @@ static int unix_gid_parse(struct cache_detail *cd, for (i = 0 ; i < gids ; i++) { int gid; + kgid_t kgid; rv = get_int(&mesg, &gid); err = -EINVAL; if (rv) goto out; - GROUP_AT(ug.gi, i) = gid; + kgid = make_kgid(&init_user_ns, gid); + if (!gid_valid(kgid)) + goto out; + GROUP_AT(ug.gi, i) = kgid; } ugp = unix_gid_lookup(cd, uid); @@ -563,6 +568,7 @@ static int unix_gid_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h) { + struct user_namespace *user_ns = current_user_ns(); struct unix_gid *ug; int i; int glen; @@ -580,7 +586,7 @@ static int unix_gid_show(struct seq_file *m, seq_printf(m, "%u %d:", ug->uid, glen); for (i = 0; i < glen; i++) - seq_printf(m, " %d", GROUP_AT(ug->gi, i)); + seq_printf(m, " %d", from_kgid_munged(user_ns, GROUP_AT(ug->gi, i))); seq_printf(m, "\n"); return 0; } @@ -831,8 +837,12 @@ svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp) cred->cr_group_info = groups_alloc(slen); if (cred->cr_group_info == NULL) return SVC_CLOSE; - for (i = 0; i < slen; i++) - GROUP_AT(cred->cr_group_info, i) = svc_getnl(argv); + for (i = 0; i < slen; i++) { + kgid_t kgid = make_kgid(&init_user_ns, svc_getnl(argv)); + if (!gid_valid(kgid)) + goto badcred; + GROUP_AT(cred->cr_group_info, i) = kgid; + } if (svc_getu32(argv) != htonl(RPC_AUTH_NULL) || svc_getu32(argv) != 0) { *authp = rpc_autherr_badverf; return SVC_DENIED; diff --git a/security/keys/permission.c b/security/keys/permission.c index e146cbd714bd..5442900d2929 100644 --- a/security/keys/permission.c +++ b/security/keys/permission.c @@ -53,7 +53,8 @@ int key_task_permission(const key_ref_t key_ref, const struct cred *cred, goto use_these_perms; } - ret = groups_search(cred->group_info, key->gid); + ret = groups_search(cred->group_info, + make_kgid(current_user_ns(), key->gid)); if (ret) { kperm = key->perm >> 8; goto use_these_perms; -- cgit v1.2.3 From 078de5f706ece36afd73bb4b8283314132d2dfdf Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 8 Feb 2012 07:00:08 -0800 Subject: userns: Store uid and gid values in struct cred with kuid_t and kgid_t types cred.h and a few trivial users of struct cred are changed. The rest of the users of struct cred are left for other patches as there are too many changes to make in one go and leave the change reviewable. If the user namespace is disabled and CONFIG_UIDGID_STRICT_TYPE_CHECKS are disabled the code will contiue to compile and behave correctly. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- arch/x86/mm/fault.c | 2 +- fs/ioprio.c | 8 ++------ include/linux/cred.h | 16 ++++++++-------- include/linux/user_namespace.h | 8 ++++---- kernel/cred.c | 36 ++++++++++++++++++++++-------------- kernel/signal.c | 14 ++++++++------ kernel/sys.c | 26 +++++++++----------------- kernel/user_namespace.c | 4 ++-- mm/oom_kill.c | 4 ++-- security/commoncap.c | 3 +-- 10 files changed, 59 insertions(+), 62 deletions(-) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 3ecfd1aaf214..76dcd9d8e0bc 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -582,7 +582,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, pte_t *pte = lookup_address(address, &level); if (pte && pte_present(*pte) && !pte_exec(*pte)) - printk(nx_warning, current_uid()); + printk(nx_warning, from_kuid(&init_user_ns, current_uid())); } printk(KERN_ALERT "BUG: unable to handle kernel "); diff --git a/fs/ioprio.c b/fs/ioprio.c index 8e35e964d9ed..2072e41785d2 100644 --- a/fs/ioprio.c +++ b/fs/ioprio.c @@ -123,9 +123,7 @@ SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio) break; do_each_thread(g, p) { - const struct cred *tcred = __task_cred(p); - kuid_t tcred_uid = make_kuid(tcred->user_ns, tcred->uid); - if (!uid_eq(tcred_uid, uid)) + if (!uid_eq(task_uid(p), uid)) continue; ret = set_task_ioprio(p, ioprio); if (ret) @@ -220,9 +218,7 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who) break; do_each_thread(g, p) { - const struct cred *tcred = __task_cred(p); - kuid_t tcred_uid = make_kuid(tcred->user_ns, tcred->uid); - if (!uid_eq(tcred_uid, user->uid)) + if (!uid_eq(task_uid(p), user->uid)) continue; tmpio = get_task_ioprio(p); if (tmpio < 0) diff --git a/include/linux/cred.h b/include/linux/cred.h index 0ab3cda4a774..fac0579258fc 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -123,14 +123,14 @@ struct cred { #define CRED_MAGIC 0x43736564 #define CRED_MAGIC_DEAD 0x44656144 #endif - uid_t uid; /* real UID of the task */ - gid_t gid; /* real GID of the task */ - uid_t suid; /* saved UID of the task */ - gid_t sgid; /* saved GID of the task */ - uid_t euid; /* effective UID of the task */ - gid_t egid; /* effective GID of the task */ - uid_t fsuid; /* UID for VFS ops */ - gid_t fsgid; /* GID for VFS ops */ + kuid_t uid; /* real UID of the task */ + kgid_t gid; /* real GID of the task */ + kuid_t suid; /* saved UID of the task */ + kgid_t sgid; /* saved GID of the task */ + kuid_t euid; /* effective UID of the task */ + kgid_t egid; /* effective GID of the task */ + kuid_t fsuid; /* UID for VFS ops */ + kgid_t fsgid; /* GID for VFS ops */ unsigned securebits; /* SUID-less security management */ kernel_cap_t cap_inheritable; /* caps our children can inherit */ kernel_cap_t cap_permitted; /* caps we're permitted */ diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 4c9846d90741..a2c61457cba1 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -70,15 +70,15 @@ static inline void put_user_ns(struct user_namespace *ns) #endif static inline uid_t user_ns_map_uid(struct user_namespace *to, - const struct cred *cred, uid_t uid) + const struct cred *cred, kuid_t uid) { - return from_kuid_munged(to, make_kuid(cred->user_ns, uid)); + return from_kuid_munged(to, uid); } static inline gid_t user_ns_map_gid(struct user_namespace *to, - const struct cred *cred, gid_t gid) + const struct cred *cred, kgid_t gid) { - return from_kgid_munged(to, make_kgid(cred->user_ns, gid)); + return from_kgid_munged(to, gid); } #endif /* _LINUX_USER_H */ diff --git a/kernel/cred.c b/kernel/cred.c index 7a0d80669886..eddc5e2e9587 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -49,6 +49,14 @@ struct cred init_cred = { .subscribers = ATOMIC_INIT(2), .magic = CRED_MAGIC, #endif + .uid = GLOBAL_ROOT_UID, + .gid = GLOBAL_ROOT_GID, + .suid = GLOBAL_ROOT_UID, + .sgid = GLOBAL_ROOT_GID, + .euid = GLOBAL_ROOT_UID, + .egid = GLOBAL_ROOT_GID, + .fsuid = GLOBAL_ROOT_UID, + .fsgid = GLOBAL_ROOT_GID, .securebits = SECUREBITS_DEFAULT, .cap_inheritable = CAP_EMPTY_SET, .cap_permitted = CAP_FULL_SET, @@ -488,10 +496,10 @@ int commit_creds(struct cred *new) get_cred(new); /* we will require a ref for the subj creds too */ /* dumpability changes */ - if (old->euid != new->euid || - old->egid != new->egid || - old->fsuid != new->fsuid || - old->fsgid != new->fsgid || + if (!uid_eq(old->euid, new->euid) || + !gid_eq(old->egid, new->egid) || + !uid_eq(old->fsuid, new->fsuid) || + !gid_eq(old->fsgid, new->fsgid) || !cap_issubset(new->cap_permitted, old->cap_permitted)) { if (task->mm) set_dumpable(task->mm, suid_dumpable); @@ -500,9 +508,9 @@ int commit_creds(struct cred *new) } /* alter the thread keyring */ - if (new->fsuid != old->fsuid) + if (!uid_eq(new->fsuid, old->fsuid)) key_fsuid_changed(task); - if (new->fsgid != old->fsgid) + if (!gid_eq(new->fsgid, old->fsgid)) key_fsgid_changed(task); /* do it @@ -519,16 +527,16 @@ int commit_creds(struct cred *new) alter_cred_subscribers(old, -2); /* send notifications */ - if (new->uid != old->uid || - new->euid != old->euid || - new->suid != old->suid || - new->fsuid != old->fsuid) + if (!uid_eq(new->uid, old->uid) || + !uid_eq(new->euid, old->euid) || + !uid_eq(new->suid, old->suid) || + !uid_eq(new->fsuid, old->fsuid)) proc_id_connector(task, PROC_EVENT_UID); - if (new->gid != old->gid || - new->egid != old->egid || - new->sgid != old->sgid || - new->fsgid != old->fsgid) + if (!gid_eq(new->gid, old->gid) || + !gid_eq(new->egid, old->egid) || + !gid_eq(new->sgid, old->sgid) || + !gid_eq(new->fsgid, old->fsgid)) proc_id_connector(task, PROC_EVENT_GID); /* release the old obj and subj refs both */ diff --git a/kernel/signal.c b/kernel/signal.c index e2c5d84f2dac..2734dc965f69 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1038,8 +1038,10 @@ static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_str if (SI_FROMKERNEL(info)) return; - info->si_uid = user_ns_map_uid(task_cred_xxx(t, user_ns), - current_cred(), info->si_uid); + rcu_read_lock(); + info->si_uid = from_kuid_munged(task_cred_xxx(t, user_ns), + make_kuid(current_user_ns(), info->si_uid)); + rcu_read_unlock(); } #else static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_struct *t) @@ -1106,7 +1108,7 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t, q->info.si_code = SI_USER; q->info.si_pid = task_tgid_nr_ns(current, task_active_pid_ns(t)); - q->info.si_uid = current_uid(); + q->info.si_uid = from_kuid_munged(current_user_ns(), current_uid()); break; case (unsigned long) SEND_SIG_PRIV: q->info.si_signo = sig; @@ -1973,7 +1975,7 @@ static void ptrace_do_notify(int signr, int exit_code, int why) info.si_signo = signr; info.si_code = exit_code; info.si_pid = task_pid_vnr(current); - info.si_uid = current_uid(); + info.si_uid = from_kuid_munged(current_user_ns(), current_uid()); /* Let the debugger run. */ ptrace_stop(exit_code, why, 1, &info); @@ -2828,7 +2830,7 @@ SYSCALL_DEFINE2(kill, pid_t, pid, int, sig) info.si_errno = 0; info.si_code = SI_USER; info.si_pid = task_tgid_vnr(current); - info.si_uid = current_uid(); + info.si_uid = from_kuid_munged(current_user_ns(), current_uid()); return kill_something_info(sig, &info, pid); } @@ -2871,7 +2873,7 @@ static int do_tkill(pid_t tgid, pid_t pid, int sig) info.si_errno = 0; info.si_code = SI_TKILL; info.si_pid = task_tgid_vnr(current); - info.si_uid = current_uid(); + info.si_uid = from_kuid_munged(current_user_ns(), current_uid()); return do_send_specific(tgid, pid, sig, &info); } diff --git a/kernel/sys.c b/kernel/sys.c index f0c43b4b6657..39962818c008 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -175,7 +175,6 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) const struct cred *cred = current_cred(); int error = -EINVAL; struct pid *pgrp; - kuid_t cred_uid; kuid_t uid; if (which > PRIO_USER || which < PRIO_PROCESS) @@ -209,22 +208,19 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); break; case PRIO_USER: - cred_uid = make_kuid(cred->user_ns, cred->uid); uid = make_kuid(cred->user_ns, who); user = cred->user; if (!who) - uid = cred_uid; - else if (!uid_eq(uid, cred_uid) && + uid = cred->uid; + else if (!uid_eq(uid, cred->uid) && !(user = find_user(uid))) goto out_unlock; /* No processes for this user */ do_each_thread(g, p) { - const struct cred *tcred = __task_cred(p); - kuid_t tcred_uid = make_kuid(tcred->user_ns, tcred->uid); - if (uid_eq(tcred_uid, uid)) + if (uid_eq(task_uid(p), uid)) error = set_one_prio(p, niceval, error); } while_each_thread(g, p); - if (!uid_eq(uid, cred_uid)) + if (!uid_eq(uid, cred->uid)) free_uid(user); /* For find_user() */ break; } @@ -248,7 +244,6 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who) const struct cred *cred = current_cred(); long niceval, retval = -ESRCH; struct pid *pgrp; - kuid_t cred_uid; kuid_t uid; if (which > PRIO_USER || which < PRIO_PROCESS) @@ -280,25 +275,22 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who) } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); break; case PRIO_USER: - cred_uid = make_kuid(cred->user_ns, cred->uid); uid = make_kuid(cred->user_ns, who); user = cred->user; if (!who) - uid = cred_uid; - else if (!uid_eq(uid, cred_uid) && + uid = cred->uid; + else if (!uid_eq(uid, cred->uid) && !(user = find_user(uid))) goto out_unlock; /* No processes for this user */ do_each_thread(g, p) { - const struct cred *tcred = __task_cred(p); - kuid_t tcred_uid = make_kuid(tcred->user_ns, tcred->uid); - if (uid_eq(tcred_uid, uid)) { + if (uid_eq(task_uid(p), uid)) { niceval = 20 - task_nice(p); if (niceval > retval) retval = niceval; } } while_each_thread(g, p); - if (!uid_eq(uid, cred_uid)) + if (!uid_eq(uid, cred->uid)) free_uid(user); /* for find_user() */ break; } @@ -641,7 +633,7 @@ static int set_user(struct cred *new) { struct user_struct *new_user; - new_user = alloc_uid(make_kuid(new->user_ns, new->uid)); + new_user = alloc_uid(new->uid); if (!new_user) return -EAGAIN; diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 7eff867bfac5..86602316422d 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -36,8 +36,8 @@ static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid, int create_user_ns(struct cred *new) { struct user_namespace *ns, *parent_ns = new->user_ns; - kuid_t owner = make_kuid(new->user_ns, new->euid); - kgid_t group = make_kgid(new->user_ns, new->egid); + kuid_t owner = new->euid; + kgid_t group = new->egid; /* The creator needs a mapping in the parent user namespace * or else we won't be able to reasonably tell userspace who diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 46bf2ed5594c..9f09a1fde9f9 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -410,8 +410,8 @@ static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemas } pr_info("[%5d] %5d %5d %8lu %8lu %3u %3d %5d %s\n", - task->pid, task_uid(task), task->tgid, - task->mm->total_vm, get_mm_rss(task->mm), + task->pid, from_kuid(&init_user_ns, task_uid(task)), + task->tgid, task->mm->total_vm, get_mm_rss(task->mm), task_cpu(task), task->signal->oom_adj, task->signal->oom_score_adj, task->comm); task_unlock(task); diff --git a/security/commoncap.c b/security/commoncap.c index f2399d8afbe0..dbd465a59286 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -77,8 +77,7 @@ int cap_capable(const struct cred *cred, struct user_namespace *targ_ns, { for (;;) { /* The owner of the user namespace has all caps. */ - if (targ_ns != &init_user_ns && uid_eq(targ_ns->owner, - make_kuid(cred->user_ns, cred->euid))) + if (targ_ns != &init_user_ns && uid_eq(targ_ns->owner, cred->euid)) return 0; /* Do we have the necessary capabilities? */ -- cgit v1.2.3 From 76b6db010297d4928ab7b7e7c78dd982f413f0a4 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 14 Mar 2012 15:24:19 -0700 Subject: userns: Replace user_ns_map_uid and user_ns_map_gid with from_kuid and from_kgid These function are no longer needed replace them with their more useful equivalents. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- include/linux/user_namespace.h | 12 ------------ ipc/mqueue.c | 3 +-- kernel/signal.c | 2 +- net/core/sock.c | 4 ++-- 4 files changed, 4 insertions(+), 17 deletions(-) diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index a2c61457cba1..4e72922e5a75 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -69,16 +69,4 @@ static inline void put_user_ns(struct user_namespace *ns) #endif -static inline uid_t user_ns_map_uid(struct user_namespace *to, - const struct cred *cred, kuid_t uid) -{ - return from_kuid_munged(to, uid); -} - -static inline gid_t user_ns_map_gid(struct user_namespace *to, - const struct cred *cred, kgid_t gid) -{ - return from_kgid_munged(to, gid); -} - #endif /* _LINUX_USER_H */ diff --git a/ipc/mqueue.c b/ipc/mqueue.c index b53cf3469d01..b6a0d46fbad7 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -538,8 +538,7 @@ static void __do_notify(struct mqueue_inode_info *info) rcu_read_lock(); sig_i.si_pid = task_tgid_nr_ns(current, ns_of_pid(info->notify_owner)); - sig_i.si_uid = user_ns_map_uid(info->notify_user_ns, - current_cred(), current_uid()); + sig_i.si_uid = from_kuid_munged(info->notify_user_ns, current_uid()); rcu_read_unlock(); kill_pid_info(info->notify.sigev_signo, diff --git a/kernel/signal.c b/kernel/signal.c index 2734dc965f69..d6303277a640 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1026,7 +1026,7 @@ static inline int legacy_queue(struct sigpending *signals, int sig) static inline uid_t map_cred_ns(const struct cred *cred, struct user_namespace *ns) { - return user_ns_map_uid(ns, cred, cred->uid); + return from_kuid_munged(ns, cred->uid); } #ifdef CONFIG_USER_NS diff --git a/net/core/sock.c b/net/core/sock.c index b2e14c07d920..e1ec8ba1381c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -821,8 +821,8 @@ void cred_to_ucred(struct pid *pid, const struct cred *cred, if (cred) { struct user_namespace *current_ns = current_user_ns(); - ucred->uid = user_ns_map_uid(current_ns, cred, cred->euid); - ucred->gid = user_ns_map_gid(current_ns, cred, cred->egid); + ucred->uid = from_kuid(current_ns, cred->euid); + ucred->gid = from_kgid(current_ns, cred->egid); } } EXPORT_SYMBOL_GPL(cred_to_ucred); -- cgit v1.2.3 From 9c806aa06f8e121c6058db8e8073798aa5c4355b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 2 Feb 2012 18:54:02 -0800 Subject: userns: Convert sched_set_affinity and sched_set_scheduler's permission checks - Compare kuids with uid_eq - kuid are uniuqe across all user namespaces so there is no longer the need for a user_namespace comparison. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- kernel/sched/core.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 96bff855b866..b189fecaef90 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4042,11 +4042,8 @@ static bool check_same_owner(struct task_struct *p) rcu_read_lock(); pcred = __task_cred(p); - if (cred->user_ns == pcred->user_ns) - match = (cred->euid == pcred->euid || - cred->euid == pcred->uid); - else - match = false; + match = (uid_eq(cred->euid, pcred->euid) || + uid_eq(cred->euid, pcred->uid)); rcu_read_unlock(); return match; } -- cgit v1.2.3 From 18815a18085364d8514c0d0c4c986776cb74272c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 7 Feb 2012 16:45:47 -0800 Subject: userns: Convert capabilities related permsion checks - Use uid_eq when comparing kuids Use gid_eq when comparing kgids - Use make_kuid(user_ns, 0) to talk about the user_namespace root uid Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- fs/open.c | 3 ++- security/commoncap.c | 41 ++++++++++++++++++++++++++--------------- 2 files changed, 28 insertions(+), 16 deletions(-) diff --git a/fs/open.c b/fs/open.c index 5720854156db..92335f663545 100644 --- a/fs/open.c +++ b/fs/open.c @@ -316,7 +316,8 @@ SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode) if (!issecure(SECURE_NO_SETUID_FIXUP)) { /* Clear the capabilities if we switch to a non-root user */ - if (override_cred->uid) + kuid_t root_uid = make_kuid(override_cred->user_ns, 0); + if (!uid_eq(override_cred->uid, root_uid)) cap_clear(override_cred->cap_effective); else override_cred->cap_effective = diff --git a/security/commoncap.c b/security/commoncap.c index dbd465a59286..ff9b113bb07c 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -472,19 +472,22 @@ int cap_bprm_set_creds(struct linux_binprm *bprm) struct cred *new = bprm->cred; bool effective, has_cap = false; int ret; + kuid_t root_uid; effective = false; ret = get_file_caps(bprm, &effective, &has_cap); if (ret < 0) return ret; + root_uid = make_kuid(new->user_ns, 0); + if (!issecure(SECURE_NOROOT)) { /* * If the legacy file capability is set, then don't set privs * for a setuid root binary run by a non-root user. Do set it * for a root user just to cause least surprise to an admin. */ - if (has_cap && new->uid != 0 && new->euid == 0) { + if (has_cap && !uid_eq(new->uid, root_uid) && uid_eq(new->euid, root_uid)) { warn_setuid_and_fcaps_mixed(bprm->filename); goto skip; } @@ -495,12 +498,12 @@ int cap_bprm_set_creds(struct linux_binprm *bprm) * * If only the real uid is 0, we do not set the effective bit. */ - if (new->euid == 0 || new->uid == 0) { + if (uid_eq(new->euid, root_uid) || uid_eq(new->uid, root_uid)) { /* pP' = (cap_bset & ~0) | (pI & ~0) */ new->cap_permitted = cap_combine(old->cap_bset, old->cap_inheritable); } - if (new->euid == 0) + if (uid_eq(new->euid, root_uid)) effective = true; } skip: @@ -508,8 +511,8 @@ skip: /* Don't let someone trace a set[ug]id/setpcap binary with the revised * credentials unless they have the appropriate permit */ - if ((new->euid != old->uid || - new->egid != old->gid || + if ((!uid_eq(new->euid, old->uid) || + !gid_eq(new->egid, old->gid) || !cap_issubset(new->cap_permitted, old->cap_permitted)) && bprm->unsafe & ~LSM_UNSAFE_PTRACE_CAP) { /* downgrade; they get no more than they had, and maybe less */ @@ -544,7 +547,7 @@ skip: */ if (!cap_isclear(new->cap_effective)) { if (!cap_issubset(CAP_FULL_SET, new->cap_effective) || - new->euid != 0 || new->uid != 0 || + !uid_eq(new->euid, root_uid) || !uid_eq(new->uid, root_uid) || issecure(SECURE_NOROOT)) { ret = audit_log_bprm_fcaps(bprm, new, old); if (ret < 0) @@ -569,16 +572,17 @@ skip: int cap_bprm_secureexec(struct linux_binprm *bprm) { const struct cred *cred = current_cred(); + kuid_t root_uid = make_kuid(cred->user_ns, 0); - if (cred->uid != 0) { + if (!uid_eq(cred->uid, root_uid)) { if (bprm->cap_effective) return 1; if (!cap_isclear(cred->cap_permitted)) return 1; } - return (cred->euid != cred->uid || - cred->egid != cred->gid); + return (!uid_eq(cred->euid, cred->uid) || + !gid_eq(cred->egid, cred->gid)); } /** @@ -668,15 +672,21 @@ int cap_inode_removexattr(struct dentry *dentry, const char *name) */ static inline void cap_emulate_setxuid(struct cred *new, const struct cred *old) { - if ((old->uid == 0 || old->euid == 0 || old->suid == 0) && - (new->uid != 0 && new->euid != 0 && new->suid != 0) && + kuid_t root_uid = make_kuid(old->user_ns, 0); + + if ((uid_eq(old->uid, root_uid) || + uid_eq(old->euid, root_uid) || + uid_eq(old->suid, root_uid)) && + (!uid_eq(new->uid, root_uid) && + !uid_eq(new->euid, root_uid) && + !uid_eq(new->suid, root_uid)) && !issecure(SECURE_KEEP_CAPS)) { cap_clear(new->cap_permitted); cap_clear(new->cap_effective); } - if (old->euid == 0 && new->euid != 0) + if (uid_eq(old->euid, root_uid) && !uid_eq(new->euid, root_uid)) cap_clear(new->cap_effective); - if (old->euid != 0 && new->euid == 0) + if (!uid_eq(old->euid, root_uid) && uid_eq(new->euid, root_uid)) new->cap_effective = new->cap_permitted; } @@ -709,11 +719,12 @@ int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags) * if not, we might be a bit too harsh here. */ if (!issecure(SECURE_NO_SETUID_FIXUP)) { - if (old->fsuid == 0 && new->fsuid != 0) + kuid_t root_uid = make_kuid(old->user_ns, 0); + if (uid_eq(old->fsuid, root_uid) && !uid_eq(new->fsuid, root_uid)) new->cap_effective = cap_drop_fs_set(new->cap_effective); - if (old->fsuid != 0 && new->fsuid == 0) + if (!uid_eq(old->fsuid, root_uid) && uid_eq(new->fsuid, root_uid)) new->cap_effective = cap_raise_fs_set(new->cap_effective, new->cap_permitted); -- cgit v1.2.3 From a29c33f4e506e1dae7e0985b6328046535becbf8 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 7 Feb 2012 18:51:01 -0800 Subject: userns: Convert setting and getting uid and gid system calls to use kuid and kgid Convert setregid, setgid, setreuid, setuid, setresuid, getresuid, setresgid, getresgid, setfsuid, setfsgid, getuid, geteuid, getgid, getegid, waitpid, waitid, wait4. Convert userspace uids and gids into kuids and kgids before being placed on struct cred. Convert struct cred kuids and kgids into userspace uids and gids when returning them. Signed-off-by: Eric W. Biederman --- kernel/exit.c | 6 +- kernel/sys.c | 216 +++++++++++++++++++++++++++++++++++++++------------------ kernel/timer.c | 8 +-- kernel/uid16.c | 34 +++++---- 4 files changed, 178 insertions(+), 86 deletions(-) diff --git a/kernel/exit.c b/kernel/exit.c index d8bd3b425fa7..789e3c5777f7 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1214,7 +1214,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) unsigned long state; int retval, status, traced; pid_t pid = task_pid_vnr(p); - uid_t uid = __task_cred(p)->uid; + uid_t uid = from_kuid_munged(current_user_ns(), __task_cred(p)->uid); struct siginfo __user *infop; if (!likely(wo->wo_flags & WEXITED)) @@ -1427,7 +1427,7 @@ static int wait_task_stopped(struct wait_opts *wo, if (!unlikely(wo->wo_flags & WNOWAIT)) *p_code = 0; - uid = task_uid(p); + uid = from_kuid_munged(current_user_ns(), __task_cred(p)->uid); unlock_sig: spin_unlock_irq(&p->sighand->siglock); if (!exit_code) @@ -1500,7 +1500,7 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p) } if (!unlikely(wo->wo_flags & WNOWAIT)) p->signal->flags &= ~SIGNAL_STOP_CONTINUED; - uid = task_uid(p); + uid = from_kuid_munged(current_user_ns(), __task_cred(p)->uid); spin_unlock_irq(&p->sighand->siglock); pid = task_pid_vnr(p); diff --git a/kernel/sys.c b/kernel/sys.c index 39962818c008..aff09f208eb3 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -555,9 +555,19 @@ void ctrl_alt_del(void) */ SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid) { + struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; + kgid_t krgid, kegid; + + krgid = make_kgid(ns, rgid); + kegid = make_kgid(ns, egid); + + if ((rgid != (gid_t) -1) && !gid_valid(krgid)) + return -EINVAL; + if ((egid != (gid_t) -1) && !gid_valid(kegid)) + return -EINVAL; new = prepare_creds(); if (!new) @@ -566,25 +576,25 @@ SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid) retval = -EPERM; if (rgid != (gid_t) -1) { - if (old->gid == rgid || - old->egid == rgid || + if (gid_eq(old->gid, krgid) || + gid_eq(old->egid, krgid) || nsown_capable(CAP_SETGID)) - new->gid = rgid; + new->gid = krgid; else goto error; } if (egid != (gid_t) -1) { - if (old->gid == egid || - old->egid == egid || - old->sgid == egid || + if (gid_eq(old->gid, kegid) || + gid_eq(old->egid, kegid) || + gid_eq(old->sgid, kegid) || nsown_capable(CAP_SETGID)) - new->egid = egid; + new->egid = kegid; else goto error; } if (rgid != (gid_t) -1 || - (egid != (gid_t) -1 && egid != old->gid)) + (egid != (gid_t) -1 && !gid_eq(kegid, old->gid))) new->sgid = new->egid; new->fsgid = new->egid; @@ -602,9 +612,15 @@ error: */ SYSCALL_DEFINE1(setgid, gid_t, gid) { + struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; + kgid_t kgid; + + kgid = make_kgid(ns, gid); + if (!gid_valid(kgid)) + return -EINVAL; new = prepare_creds(); if (!new) @@ -613,9 +629,9 @@ SYSCALL_DEFINE1(setgid, gid_t, gid) retval = -EPERM; if (nsown_capable(CAP_SETGID)) - new->gid = new->egid = new->sgid = new->fsgid = gid; - else if (gid == old->gid || gid == old->sgid) - new->egid = new->fsgid = gid; + new->gid = new->egid = new->sgid = new->fsgid = kgid; + else if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->sgid)) + new->egid = new->fsgid = kgid; else goto error; @@ -672,9 +688,19 @@ static int set_user(struct cred *new) */ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid) { + struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; + kuid_t kruid, keuid; + + kruid = make_kuid(ns, ruid); + keuid = make_kuid(ns, euid); + + if ((ruid != (uid_t) -1) && !uid_valid(kruid)) + return -EINVAL; + if ((euid != (uid_t) -1) && !uid_valid(keuid)) + return -EINVAL; new = prepare_creds(); if (!new) @@ -683,29 +709,29 @@ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid) retval = -EPERM; if (ruid != (uid_t) -1) { - new->uid = ruid; - if (old->uid != ruid && - old->euid != ruid && + new->uid = kruid; + if (!uid_eq(old->uid, kruid) && + !uid_eq(old->euid, kruid) && !nsown_capable(CAP_SETUID)) goto error; } if (euid != (uid_t) -1) { - new->euid = euid; - if (old->uid != euid && - old->euid != euid && - old->suid != euid && + new->euid = keuid; + if (!uid_eq(old->uid, keuid) && + !uid_eq(old->euid, keuid) && + !uid_eq(old->suid, keuid) && !nsown_capable(CAP_SETUID)) goto error; } - if (new->uid != old->uid) { + if (!uid_eq(new->uid, old->uid)) { retval = set_user(new); if (retval < 0) goto error; } if (ruid != (uid_t) -1 || - (euid != (uid_t) -1 && euid != old->uid)) + (euid != (uid_t) -1 && !uid_eq(keuid, old->uid))) new->suid = new->euid; new->fsuid = new->euid; @@ -733,9 +759,15 @@ error: */ SYSCALL_DEFINE1(setuid, uid_t, uid) { + struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; + kuid_t kuid; + + kuid = make_kuid(ns, uid); + if (!uid_valid(kuid)) + return -EINVAL; new = prepare_creds(); if (!new) @@ -744,17 +776,17 @@ SYSCALL_DEFINE1(setuid, uid_t, uid) retval = -EPERM; if (nsown_capable(CAP_SETUID)) { - new->suid = new->uid = uid; - if (uid != old->uid) { + new->suid = new->uid = kuid; + if (!uid_eq(kuid, old->uid)) { retval = set_user(new); if (retval < 0) goto error; } - } else if (uid != old->uid && uid != new->suid) { + } else if (!uid_eq(kuid, old->uid) && !uid_eq(kuid, new->suid)) { goto error; } - new->fsuid = new->euid = uid; + new->fsuid = new->euid = kuid; retval = security_task_fix_setuid(new, old, LSM_SETID_ID); if (retval < 0) @@ -774,9 +806,24 @@ error: */ SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid) { + struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; + kuid_t kruid, keuid, ksuid; + + kruid = make_kuid(ns, ruid); + keuid = make_kuid(ns, euid); + ksuid = make_kuid(ns, suid); + + if ((ruid != (uid_t) -1) && !uid_valid(kruid)) + return -EINVAL; + + if ((euid != (uid_t) -1) && !uid_valid(keuid)) + return -EINVAL; + + if ((suid != (uid_t) -1) && !uid_valid(ksuid)) + return -EINVAL; new = prepare_creds(); if (!new) @@ -786,29 +833,29 @@ SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid) retval = -EPERM; if (!nsown_capable(CAP_SETUID)) { - if (ruid != (uid_t) -1 && ruid != old->uid && - ruid != old->euid && ruid != old->suid) + if (ruid != (uid_t) -1 && !uid_eq(kruid, old->uid) && + !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid)) goto error; - if (euid != (uid_t) -1 && euid != old->uid && - euid != old->euid && euid != old->suid) + if (euid != (uid_t) -1 && !uid_eq(keuid, old->uid) && + !uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid)) goto error; - if (suid != (uid_t) -1 && suid != old->uid && - suid != old->euid && suid != old->suid) + if (suid != (uid_t) -1 && !uid_eq(ksuid, old->uid) && + !uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid)) goto error; } if (ruid != (uid_t) -1) { - new->uid = ruid; - if (ruid != old->uid) { + new->uid = kruid; + if (!uid_eq(kruid, old->uid)) { retval = set_user(new); if (retval < 0) goto error; } } if (euid != (uid_t) -1) - new->euid = euid; + new->euid = keuid; if (suid != (uid_t) -1) - new->suid = suid; + new->suid = ksuid; new->fsuid = new->euid; retval = security_task_fix_setuid(new, old, LSM_SETID_RES); @@ -822,14 +869,19 @@ error: return retval; } -SYSCALL_DEFINE3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __user *, suid) +SYSCALL_DEFINE3(getresuid, uid_t __user *, ruidp, uid_t __user *, euidp, uid_t __user *, suidp) { const struct cred *cred = current_cred(); int retval; + uid_t ruid, euid, suid; + + ruid = from_kuid_munged(cred->user_ns, cred->uid); + euid = from_kuid_munged(cred->user_ns, cred->euid); + suid = from_kuid_munged(cred->user_ns, cred->suid); - if (!(retval = put_user(cred->uid, ruid)) && - !(retval = put_user(cred->euid, euid))) - retval = put_user(cred->suid, suid); + if (!(retval = put_user(ruid, ruidp)) && + !(retval = put_user(euid, euidp))) + retval = put_user(suid, suidp); return retval; } @@ -839,9 +891,22 @@ SYSCALL_DEFINE3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __u */ SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid) { + struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; + kgid_t krgid, kegid, ksgid; + + krgid = make_kgid(ns, rgid); + kegid = make_kgid(ns, egid); + ksgid = make_kgid(ns, sgid); + + if ((rgid != (gid_t) -1) && !gid_valid(krgid)) + return -EINVAL; + if ((egid != (gid_t) -1) && !gid_valid(kegid)) + return -EINVAL; + if ((sgid != (gid_t) -1) && !gid_valid(ksgid)) + return -EINVAL; new = prepare_creds(); if (!new) @@ -850,23 +915,23 @@ SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid) retval = -EPERM; if (!nsown_capable(CAP_SETGID)) { - if (rgid != (gid_t) -1 && rgid != old->gid && - rgid != old->egid && rgid != old->sgid) + if (rgid != (gid_t) -1 && !gid_eq(krgid, old->gid) && + !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid)) goto error; - if (egid != (gid_t) -1 && egid != old->gid && - egid != old->egid && egid != old->sgid) + if (egid != (gid_t) -1 && !gid_eq(kegid, old->gid) && + !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid)) goto error; - if (sgid != (gid_t) -1 && sgid != old->gid && - sgid != old->egid && sgid != old->sgid) + if (sgid != (gid_t) -1 && !gid_eq(ksgid, old->gid) && + !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid)) goto error; } if (rgid != (gid_t) -1) - new->gid = rgid; + new->gid = krgid; if (egid != (gid_t) -1) - new->egid = egid; + new->egid = kegid; if (sgid != (gid_t) -1) - new->sgid = sgid; + new->sgid = ksgid; new->fsgid = new->egid; return commit_creds(new); @@ -876,14 +941,19 @@ error: return retval; } -SYSCALL_DEFINE3(getresgid, gid_t __user *, rgid, gid_t __user *, egid, gid_t __user *, sgid) +SYSCALL_DEFINE3(getresgid, gid_t __user *, rgidp, gid_t __user *, egidp, gid_t __user *, sgidp) { const struct cred *cred = current_cred(); int retval; + gid_t rgid, egid, sgid; + + rgid = from_kgid_munged(cred->user_ns, cred->gid); + egid = from_kgid_munged(cred->user_ns, cred->egid); + sgid = from_kgid_munged(cred->user_ns, cred->sgid); - if (!(retval = put_user(cred->gid, rgid)) && - !(retval = put_user(cred->egid, egid))) - retval = put_user(cred->sgid, sgid); + if (!(retval = put_user(rgid, rgidp)) && + !(retval = put_user(egid, egidp))) + retval = put_user(sgid, sgidp); return retval; } @@ -900,18 +970,24 @@ SYSCALL_DEFINE1(setfsuid, uid_t, uid) const struct cred *old; struct cred *new; uid_t old_fsuid; + kuid_t kuid; + + old = current_cred(); + old_fsuid = from_kuid_munged(old->user_ns, old->fsuid); + + kuid = make_kuid(old->user_ns, uid); + if (!uid_valid(kuid)) + return old_fsuid; new = prepare_creds(); if (!new) - return current_fsuid(); - old = current_cred(); - old_fsuid = old->fsuid; + return old_fsuid; - if (uid == old->uid || uid == old->euid || - uid == old->suid || uid == old->fsuid || + if (uid_eq(kuid, old->uid) || uid_eq(kuid, old->euid) || + uid_eq(kuid, old->suid) || uid_eq(kuid, old->fsuid) || nsown_capable(CAP_SETUID)) { - if (uid != old_fsuid) { - new->fsuid = uid; + if (!uid_eq(kuid, old->fsuid)) { + new->fsuid = kuid; if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0) goto change_okay; } @@ -933,18 +1009,24 @@ SYSCALL_DEFINE1(setfsgid, gid_t, gid) const struct cred *old; struct cred *new; gid_t old_fsgid; + kgid_t kgid; + + old = current_cred(); + old_fsgid = from_kgid_munged(old->user_ns, old->fsgid); + + kgid = make_kgid(old->user_ns, gid); + if (!gid_valid(kgid)) + return old_fsgid; new = prepare_creds(); if (!new) - return current_fsgid(); - old = current_cred(); - old_fsgid = old->fsgid; + return old_fsgid; - if (gid == old->gid || gid == old->egid || - gid == old->sgid || gid == old->fsgid || + if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->egid) || + gid_eq(kgid, old->sgid) || gid_eq(kgid, old->fsgid) || nsown_capable(CAP_SETGID)) { - if (gid != old_fsgid) { - new->fsgid = gid; + if (!gid_eq(kgid, old->fsgid)) { + new->fsgid = kgid; goto change_okay; } } @@ -1503,10 +1585,10 @@ static int check_prlimit_permission(struct task_struct *task) if (cred->user_ns == tcred->user_ns && (cred->uid == tcred->euid && cred->uid == tcred->suid && - cred->uid == tcred->uid && + cred->uid == tcred->uid && cred->gid == tcred->egid && cred->gid == tcred->sgid && - cred->gid == tcred->gid)) + cred->gid == tcred->gid)) return 0; if (ns_capable(tcred->user_ns, CAP_SYS_RESOURCE)) return 0; diff --git a/kernel/timer.c b/kernel/timer.c index a297ffcf888e..67316cb6a777 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1427,25 +1427,25 @@ SYSCALL_DEFINE0(getppid) SYSCALL_DEFINE0(getuid) { /* Only we change this so SMP safe */ - return current_uid(); + return from_kuid_munged(current_user_ns(), current_uid()); } SYSCALL_DEFINE0(geteuid) { /* Only we change this so SMP safe */ - return current_euid(); + return from_kuid_munged(current_user_ns(), current_euid()); } SYSCALL_DEFINE0(getgid) { /* Only we change this so SMP safe */ - return current_gid(); + return from_kgid_munged(current_user_ns(), current_gid()); } SYSCALL_DEFINE0(getegid) { /* Only we change this so SMP safe */ - return current_egid(); + return from_kgid_munged(current_user_ns(), current_egid()); } #endif diff --git a/kernel/uid16.c b/kernel/uid16.c index e530bc34c4cf..d7948eb10225 100644 --- a/kernel/uid16.c +++ b/kernel/uid16.c @@ -81,14 +81,19 @@ SYSCALL_DEFINE3(setresuid16, old_uid_t, ruid, old_uid_t, euid, old_uid_t, suid) return ret; } -SYSCALL_DEFINE3(getresuid16, old_uid_t __user *, ruid, old_uid_t __user *, euid, old_uid_t __user *, suid) +SYSCALL_DEFINE3(getresuid16, old_uid_t __user *, ruidp, old_uid_t __user *, euidp, old_uid_t __user *, suidp) { const struct cred *cred = current_cred(); int retval; + old_uid_t ruid, euid, suid; - if (!(retval = put_user(high2lowuid(cred->uid), ruid)) && - !(retval = put_user(high2lowuid(cred->euid), euid))) - retval = put_user(high2lowuid(cred->suid), suid); + ruid = high2lowuid(from_kuid_munged(cred->user_ns, cred->uid)); + euid = high2lowuid(from_kuid_munged(cred->user_ns, cred->euid)); + suid = high2lowuid(from_kuid_munged(cred->user_ns, cred->suid)); + + if (!(retval = put_user(ruid, ruidp)) && + !(retval = put_user(euid, euidp))) + retval = put_user(suid, suidp); return retval; } @@ -103,14 +108,19 @@ SYSCALL_DEFINE3(setresgid16, old_gid_t, rgid, old_gid_t, egid, old_gid_t, sgid) } -SYSCALL_DEFINE3(getresgid16, old_gid_t __user *, rgid, old_gid_t __user *, egid, old_gid_t __user *, sgid) +SYSCALL_DEFINE3(getresgid16, old_gid_t __user *, rgidp, old_gid_t __user *, egidp, old_gid_t __user *, sgidp) { const struct cred *cred = current_cred(); int retval; + old_gid_t rgid, egid, sgid; + + rgid = high2lowgid(from_kgid_munged(cred->user_ns, cred->gid)); + egid = high2lowgid(from_kgid_munged(cred->user_ns, cred->egid)); + sgid = high2lowgid(from_kgid_munged(cred->user_ns, cred->sgid)); - if (!(retval = put_user(high2lowgid(cred->gid), rgid)) && - !(retval = put_user(high2lowgid(cred->egid), egid))) - retval = put_user(high2lowgid(cred->sgid), sgid); + if (!(retval = put_user(rgid, rgidp)) && + !(retval = put_user(egid, egidp))) + retval = put_user(sgid, sgidp); return retval; } @@ -221,20 +231,20 @@ SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist) SYSCALL_DEFINE0(getuid16) { - return high2lowuid(current_uid()); + return high2lowuid(from_kuid_munged(current_user_ns(), current_uid())); } SYSCALL_DEFINE0(geteuid16) { - return high2lowuid(current_euid()); + return high2lowuid(from_kuid_munged(current_user_ns(), current_euid())); } SYSCALL_DEFINE0(getgid16) { - return high2lowgid(current_gid()); + return high2lowgid(from_kgid_munged(current_user_ns(), current_gid())); } SYSCALL_DEFINE0(getegid16) { - return high2lowgid(current_egid()); + return high2lowgid(from_kgid_munged(current_user_ns(), current_egid())); } -- cgit v1.2.3 From 5af662030e5db1a5560fd917250d5d688a6be586 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 3 Mar 2012 20:21:47 -0800 Subject: userns: Convert ptrace, kill, set_priority permission checks to work with kuids and kgids Update the permission checks to use the new uid_eq and gid_eq helpers and remove the now unnecessary user_ns equality comparison. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- kernel/ptrace.c | 13 ++++++------- kernel/signal.c | 15 ++++++--------- kernel/sys.c | 18 ++++++++---------- 3 files changed, 20 insertions(+), 26 deletions(-) diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 24e0a5a94824..a232bb59d93f 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -198,13 +198,12 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode) return 0; rcu_read_lock(); tcred = __task_cred(task); - if (cred->user_ns == tcred->user_ns && - (cred->uid == tcred->euid && - cred->uid == tcred->suid && - cred->uid == tcred->uid && - cred->gid == tcred->egid && - cred->gid == tcred->sgid && - cred->gid == tcred->gid)) + if (uid_eq(cred->uid, tcred->euid) && + uid_eq(cred->uid, tcred->suid) && + uid_eq(cred->uid, tcred->uid) && + gid_eq(cred->gid, tcred->egid) && + gid_eq(cred->gid, tcred->sgid) && + gid_eq(cred->gid, tcred->gid)) goto ok; if (ptrace_has_cap(tcred->user_ns, mode)) goto ok; diff --git a/kernel/signal.c b/kernel/signal.c index d6303277a640..aef629c65c87 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -767,11 +767,10 @@ static int kill_ok_by_cred(struct task_struct *t) const struct cred *cred = current_cred(); const struct cred *tcred = __task_cred(t); - if (cred->user_ns == tcred->user_ns && - (cred->euid == tcred->suid || - cred->euid == tcred->uid || - cred->uid == tcred->suid || - cred->uid == tcred->uid)) + if (uid_eq(cred->euid, tcred->suid) || + uid_eq(cred->euid, tcred->uid) || + uid_eq(cred->uid, tcred->suid) || + uid_eq(cred->uid, tcred->uid)) return 1; if (ns_capable(tcred->user_ns, CAP_KILL)) @@ -1389,10 +1388,8 @@ static int kill_as_cred_perm(const struct cred *cred, struct task_struct *target) { const struct cred *pcred = __task_cred(target); - if (cred->user_ns != pcred->user_ns) - return 0; - if (cred->euid != pcred->suid && cred->euid != pcred->uid && - cred->uid != pcred->suid && cred->uid != pcred->uid) + if (!uid_eq(cred->euid, pcred->suid) && !uid_eq(cred->euid, pcred->uid) && + !uid_eq(cred->uid, pcred->suid) && !uid_eq(cred->uid, pcred->uid)) return 0; return 1; } diff --git a/kernel/sys.c b/kernel/sys.c index aff09f208eb3..f484077b6b14 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -131,9 +131,8 @@ static bool set_one_prio_perm(struct task_struct *p) { const struct cred *cred = current_cred(), *pcred = __task_cred(p); - if (pcred->user_ns == cred->user_ns && - (pcred->uid == cred->euid || - pcred->euid == cred->euid)) + if (uid_eq(pcred->uid, cred->euid) || + uid_eq(pcred->euid, cred->euid)) return true; if (ns_capable(pcred->user_ns, CAP_SYS_NICE)) return true; @@ -1582,13 +1581,12 @@ static int check_prlimit_permission(struct task_struct *task) return 0; tcred = __task_cred(task); - if (cred->user_ns == tcred->user_ns && - (cred->uid == tcred->euid && - cred->uid == tcred->suid && - cred->uid == tcred->uid && - cred->gid == tcred->egid && - cred->gid == tcred->sgid && - cred->gid == tcred->gid)) + if (uid_eq(cred->uid, tcred->euid) && + uid_eq(cred->uid, tcred->suid) && + uid_eq(cred->uid, tcred->uid) && + gid_eq(cred->gid, tcred->egid) && + gid_eq(cred->gid, tcred->sgid) && + gid_eq(cred->gid, tcred->gid)) return 0; if (ns_capable(tcred->user_ns, CAP_SYS_RESOURCE)) return 0; -- cgit v1.2.3 From 92361636e0153bd0cb22e7dfe3fc6287f6537c66 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 8 Feb 2012 07:07:50 -0800 Subject: userns: Store uid and gid types in vfs structures with kuid_t and kgid_t types The conversion of all of the users is not done yet there are too many to change in one go and leave the code reviewable. For now I change just the header and a few trivial users and rely on CONFIG_UIDGID_STRICT_TYPE_CHECKS not being set to ensure that the code will still compile during the transition. Helper functions i_uid_read, i_uid_write, i_gid_read, i_gid_write are added so that in most cases filesystems can avoid the complexities of multiple user namespaces and can concentrate on moving their raw numeric values into and out of the vfs data structures. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- fs/inode.c | 6 +++--- include/linux/fs.h | 36 +++++++++++++++++++++++++++++++----- 2 files changed, 34 insertions(+), 8 deletions(-) diff --git a/fs/inode.c b/fs/inode.c index f0c4ace408e4..deb72f6c2b4f 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -135,8 +135,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_fop = &empty_fops; inode->__i_nlink = 1; inode->i_opflags = 0; - inode->i_uid = 0; - inode->i_gid = 0; + i_uid_write(inode, 0); + i_gid_write(inode, 0); atomic_set(&inode->i_writecount, 0); inode->i_size = 0; inode->i_blocks = 0; @@ -1732,7 +1732,7 @@ EXPORT_SYMBOL(inode_init_owner); */ bool inode_owner_or_capable(const struct inode *inode) { - if (current_fsuid() == inode->i_uid) + if (uid_eq(current_fsuid(), inode->i_uid)) return true; if (inode_capable(inode, CAP_FOWNER)) return true; diff --git a/include/linux/fs.h b/include/linux/fs.h index a6c5efbee0d7..797eb262d9f1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -402,6 +402,7 @@ struct inodes_stat_t { #include #include #include +#include #include @@ -469,8 +470,8 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, struct iattr { unsigned int ia_valid; umode_t ia_mode; - uid_t ia_uid; - gid_t ia_gid; + kuid_t ia_uid; + kgid_t ia_gid; loff_t ia_size; struct timespec ia_atime; struct timespec ia_mtime; @@ -761,8 +762,8 @@ struct posix_acl; struct inode { umode_t i_mode; unsigned short i_opflags; - uid_t i_uid; - gid_t i_gid; + kuid_t i_uid; + kgid_t i_gid; unsigned int i_flags; #ifdef CONFIG_FS_POSIX_ACL @@ -927,6 +928,31 @@ static inline void i_size_write(struct inode *inode, loff_t i_size) #endif } +/* Helper functions so that in most cases filesystems will + * not need to deal directly with kuid_t and kgid_t and can + * instead deal with the raw numeric values that are stored + * in the filesystem. + */ +static inline uid_t i_uid_read(const struct inode *inode) +{ + return from_kuid(&init_user_ns, inode->i_uid); +} + +static inline gid_t i_gid_read(const struct inode *inode) +{ + return from_kgid(&init_user_ns, inode->i_gid); +} + +static inline void i_uid_write(struct inode *inode, uid_t uid) +{ + inode->i_uid = make_kuid(&init_user_ns, uid); +} + +static inline void i_gid_write(struct inode *inode, gid_t gid) +{ + inode->i_gid = make_kgid(&init_user_ns, gid); +} + static inline unsigned iminor(const struct inode *inode) { return MINOR(inode->i_rdev); @@ -943,7 +969,7 @@ struct fown_struct { rwlock_t lock; /* protects pid, uid, euid fields */ struct pid *pid; /* pid or -pgrp where SIGIO should be sent */ enum pid_type pid_type; /* Kind of process group SIGIO should be sent to */ - uid_t uid, euid; /* uid/euid of process setting the owner */ + kuid_t uid, euid; /* uid/euid of process setting the owner */ int signum; /* posix.1b rt signal to be delivered on IO */ }; -- cgit v1.2.3 From 72cda3d1ef24ab0a9a89c15e9776ca737b75f45a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 9 Feb 2012 09:09:39 -0800 Subject: userns: Convert in_group_p and in_egroup_p to use kgid_t Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- include/linux/cred.h | 4 ++-- kernel/groups.c | 14 ++++++-------- 2 files changed, 8 insertions(+), 10 deletions(-) diff --git a/include/linux/cred.h b/include/linux/cred.h index fac0579258fc..917dc5aeb1d4 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -73,8 +73,8 @@ extern int groups_search(const struct group_info *, kgid_t); #define GROUP_AT(gi, i) \ ((gi)->blocks[(i) / NGROUPS_PER_BLOCK][(i) % NGROUPS_PER_BLOCK]) -extern int in_group_p(gid_t); -extern int in_egroup_p(gid_t); +extern int in_group_p(kgid_t); +extern int in_egroup_p(kgid_t); /* * The common credentials for a thread group diff --git a/kernel/groups.c b/kernel/groups.c index 84156f2d4c8c..6b2588dd04ff 100644 --- a/kernel/groups.c +++ b/kernel/groups.c @@ -256,27 +256,25 @@ SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist) /* * Check whether we're fsgid/egid or in the supplemental group.. */ -int in_group_p(gid_t grp) +int in_group_p(kgid_t grp) { const struct cred *cred = current_cred(); int retval = 1; - if (grp != cred->fsgid) - retval = groups_search(cred->group_info, - make_kgid(cred->user_ns, grp)); + if (!gid_eq(grp, cred->fsgid)) + retval = groups_search(cred->group_info, grp); return retval; } EXPORT_SYMBOL(in_group_p); -int in_egroup_p(gid_t grp) +int in_egroup_p(kgid_t grp) { const struct cred *cred = current_cred(); int retval = 1; - if (grp != cred->egid) - retval = groups_search(cred->group_info, - make_kgid(cred->user_ns, grp)); + if (!gid_eq(grp, cred->egid)) + retval = groups_search(cred->group_info, grp); return retval; } -- cgit v1.2.3 From 8e96e3b7b8407be794ab1fd8e4b332818a358e78 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 3 Mar 2012 21:17:15 -0800 Subject: userns: Use uid_eq gid_eq helpers when comparing kuids and kgids in the vfs Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- fs/attr.c | 8 ++++---- fs/exec.c | 10 +++++----- fs/fcntl.c | 6 +++--- fs/ioprio.c | 4 ++-- fs/locks.c | 2 +- fs/namei.c | 8 ++++---- include/linux/quotaops.h | 4 ++-- 7 files changed, 21 insertions(+), 21 deletions(-) diff --git a/fs/attr.c b/fs/attr.c index 73f69a6ce9ed..584620e5dee5 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -47,14 +47,14 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr) /* Make sure a caller can chown. */ if ((ia_valid & ATTR_UID) && - (current_fsuid() != inode->i_uid || - attr->ia_uid != inode->i_uid) && !capable(CAP_CHOWN)) + (!uid_eq(current_fsuid(), inode->i_uid) || + !uid_eq(attr->ia_uid, inode->i_uid)) && !capable(CAP_CHOWN)) return -EPERM; /* Make sure caller can chgrp. */ if ((ia_valid & ATTR_GID) && - (current_fsuid() != inode->i_uid || - (!in_group_p(attr->ia_gid) && attr->ia_gid != inode->i_gid)) && + (!uid_eq(current_fsuid(), inode->i_uid) || + (!in_group_p(attr->ia_gid) && !gid_eq(attr->ia_gid, inode->i_gid))) && !capable(CAP_CHOWN)) return -EPERM; diff --git a/fs/exec.c b/fs/exec.c index 9a1d9f0a60ab..00ae2ef100d8 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1139,7 +1139,7 @@ void setup_new_exec(struct linux_binprm * bprm) /* This is the point of no return */ current->sas_ss_sp = current->sas_ss_size = 0; - if (current_euid() == current_uid() && current_egid() == current_gid()) + if (uid_eq(current_euid(), current_uid()) && gid_eq(current_egid(), current_gid())) set_dumpable(current->mm, 1); else set_dumpable(current->mm, suid_dumpable); @@ -1153,8 +1153,8 @@ void setup_new_exec(struct linux_binprm * bprm) current->mm->task_size = TASK_SIZE; /* install the new credentials */ - if (bprm->cred->uid != current_euid() || - bprm->cred->gid != current_egid()) { + if (!uid_eq(bprm->cred->uid, current_euid()) || + !gid_eq(bprm->cred->gid, current_egid())) { current->pdeath_signal = 0; } else { would_dump(bprm, bprm->file); @@ -2120,7 +2120,7 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs) if (__get_dumpable(cprm.mm_flags) == 2) { /* Setuid core dump mode */ flag = O_EXCL; /* Stop rewrite attacks */ - cred->fsuid = 0; /* Dump root private */ + cred->fsuid = GLOBAL_ROOT_UID; /* Dump root private */ } retval = coredump_wait(exit_code, &core_state); @@ -2221,7 +2221,7 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs) * Dont allow local users get cute and trick others to coredump * into their pre-created files. */ - if (inode->i_uid != current_fsuid()) + if (!uid_eq(inode->i_uid, current_fsuid())) goto close_fail; if (!cprm.file->f_op || !cprm.file->f_op->write) goto close_fail; diff --git a/fs/fcntl.c b/fs/fcntl.c index 75e7c1f3a080..d078b75572a7 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -532,9 +532,9 @@ static inline int sigio_perm(struct task_struct *p, rcu_read_lock(); cred = __task_cred(p); - ret = ((fown->euid == 0 || - fown->euid == cred->suid || fown->euid == cred->uid || - fown->uid == cred->suid || fown->uid == cred->uid) && + ret = ((uid_eq(fown->euid, GLOBAL_ROOT_UID) || + uid_eq(fown->euid, cred->suid) || uid_eq(fown->euid, cred->uid) || + uid_eq(fown->uid, cred->suid) || uid_eq(fown->uid, cred->uid)) && !security_file_send_sigiotask(p, fown, sig)); rcu_read_unlock(); return ret; diff --git a/fs/ioprio.c b/fs/ioprio.c index 2072e41785d2..5e6dbe8958fc 100644 --- a/fs/ioprio.c +++ b/fs/ioprio.c @@ -37,8 +37,8 @@ int set_task_ioprio(struct task_struct *task, int ioprio) rcu_read_lock(); tcred = __task_cred(task); - if (tcred->uid != cred->euid && - tcred->uid != cred->uid && !capable(CAP_SYS_NICE)) { + if (!uid_eq(tcred->uid, cred->euid) && + !uid_eq(tcred->uid, cred->uid) && !capable(CAP_SYS_NICE)) { rcu_read_unlock(); return -EPERM; } diff --git a/fs/locks.c b/fs/locks.c index 637694bf3a03..3e946cda98c6 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1445,7 +1445,7 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp) struct inode *inode = dentry->d_inode; int error; - if ((current_fsuid() != inode->i_uid) && !capable(CAP_LEASE)) + if ((!uid_eq(current_fsuid(), inode->i_uid)) && !capable(CAP_LEASE)) return -EACCES; if (!S_ISREG(inode->i_mode)) return -EINVAL; diff --git a/fs/namei.c b/fs/namei.c index 941c4362e298..86512b4d38fd 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -228,7 +228,7 @@ static int acl_permission_check(struct inode *inode, int mask) { unsigned int mode = inode->i_mode; - if (likely(current_fsuid() == inode->i_uid)) + if (likely(uid_eq(current_fsuid(), inode->i_uid))) mode >>= 6; else { if (IS_POSIXACL(inode) && (mode & S_IRWXG)) { @@ -1956,13 +1956,13 @@ static int user_path_parent(int dfd, const char __user *path, */ static inline int check_sticky(struct inode *dir, struct inode *inode) { - uid_t fsuid = current_fsuid(); + kuid_t fsuid = current_fsuid(); if (!(dir->i_mode & S_ISVTX)) return 0; - if (inode->i_uid == fsuid) + if (uid_eq(inode->i_uid, fsuid)) return 0; - if (dir->i_uid == fsuid) + if (uid_eq(dir->i_uid, fsuid)) return 0; return !inode_capable(inode, CAP_FOWNER); } diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index d93f95e6177c..17b977304a09 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -22,8 +22,8 @@ static inline struct quota_info *sb_dqopt(struct super_block *sb) static inline bool is_quota_modification(struct inode *inode, struct iattr *ia) { return (ia->ia_valid & ATTR_SIZE && ia->ia_size != inode->i_size) || - (ia->ia_valid & ATTR_UID && ia->ia_uid != inode->i_uid) || - (ia->ia_valid & ATTR_GID && ia->ia_gid != inode->i_gid); + (ia->ia_valid & ATTR_UID && !uid_eq(ia->ia_uid, inode->i_uid)) || + (ia->ia_valid & ATTR_GID && !gid_eq(ia->ia_gid, inode->i_gid)); } #if defined(CONFIG_QUOTA) -- cgit v1.2.3 From 52137abe1820196d956bfd51edebc571b3427deb Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 3 Mar 2012 19:52:01 -0800 Subject: userns: Convert user specfied uids and gids in chown into kuids and kgid Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- fs/open.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/fs/open.c b/fs/open.c index 92335f663545..e16680138323 100644 --- a/fs/open.c +++ b/fs/open.c @@ -506,15 +506,24 @@ static int chown_common(struct path *path, uid_t user, gid_t group) struct inode *inode = path->dentry->d_inode; int error; struct iattr newattrs; + kuid_t uid; + kgid_t gid; + + uid = make_kuid(current_user_ns(), user); + gid = make_kgid(current_user_ns(), group); newattrs.ia_valid = ATTR_CTIME; if (user != (uid_t) -1) { + if (!uid_valid(uid)) + return -EINVAL; newattrs.ia_valid |= ATTR_UID; - newattrs.ia_uid = user; + newattrs.ia_uid = uid; } if (group != (gid_t) -1) { + if (!gid_valid(gid)) + return -EINVAL; newattrs.ia_valid |= ATTR_GID; - newattrs.ia_gid = group; + newattrs.ia_gid = gid; } if (!S_ISDIR(inode->i_mode)) newattrs.ia_valid |= -- cgit v1.2.3 From a7c1938e22c02b008655524c766d185ae99d9d53 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 9 Feb 2012 09:10:30 -0800 Subject: userns: Convert stat to return values mapped from kuids and kgids - Store uids and gids with kuid_t and kgid_t in struct kstat - Convert uid and gids to userspace usable values with from_kuid and from_kgid Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- arch/arm/kernel/sys_oabi-compat.c | 4 ++-- arch/parisc/hpux/fs.c | 4 ++-- arch/s390/kernel/compat_linux.c | 4 ++-- arch/sparc/kernel/sys_sparc32.c | 4 ++-- arch/x86/ia32/sys_ia32.c | 4 ++-- fs/compat.c | 4 ++-- fs/stat.c | 12 ++++++------ include/linux/stat.h | 5 +++-- 8 files changed, 21 insertions(+), 20 deletions(-) diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c index af0aaebf4de6..3e94811690ce 100644 --- a/arch/arm/kernel/sys_oabi-compat.c +++ b/arch/arm/kernel/sys_oabi-compat.c @@ -124,8 +124,8 @@ static long cp_oldabi_stat64(struct kstat *stat, tmp.__st_ino = stat->ino; tmp.st_mode = stat->mode; tmp.st_nlink = stat->nlink; - tmp.st_uid = stat->uid; - tmp.st_gid = stat->gid; + tmp.st_uid = from_kuid_munged(current_user_ns(), stat->uid); + tmp.st_gid = from_kgid_munged(current_user_ns(), stat->gid); tmp.st_rdev = huge_encode_dev(stat->rdev); tmp.st_size = stat->size; tmp.st_blocks = stat->blocks; diff --git a/arch/parisc/hpux/fs.c b/arch/parisc/hpux/fs.c index 0dc8543acb4f..c71eb6c79897 100644 --- a/arch/parisc/hpux/fs.c +++ b/arch/parisc/hpux/fs.c @@ -159,8 +159,8 @@ static int cp_hpux_stat(struct kstat *stat, struct hpux_stat64 __user *statbuf) tmp.st_ino = stat->ino; tmp.st_mode = stat->mode; tmp.st_nlink = stat->nlink; - tmp.st_uid = stat->uid; - tmp.st_gid = stat->gid; + tmp.st_uid = from_kuid_munged(current_user_ns(), stat->uid); + tmp.st_gid = from_kgid_munged(current_user_ns(), stat->gid); tmp.st_rdev = new_encode_dev(stat->rdev); tmp.st_size = stat->size; tmp.st_atime = stat->atime.tv_sec; diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index f0273ed760ef..65426525d9f2 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -547,8 +547,8 @@ static int cp_stat64(struct stat64_emu31 __user *ubuf, struct kstat *stat) tmp.__st_ino = (u32)stat->ino; tmp.st_mode = stat->mode; tmp.st_nlink = (unsigned int)stat->nlink; - tmp.st_uid = stat->uid; - tmp.st_gid = stat->gid; + tmp.st_uid = from_kuid_munged(current_user_ns(), stat->uid); + tmp.st_gid = from_kgid_munged(current_user_ns(), stat->gid); tmp.st_rdev = huge_encode_dev(stat->rdev); tmp.st_size = stat->size; tmp.st_blksize = (u32)stat->blksize; diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c index 29c478ffed91..f7392336961f 100644 --- a/arch/sparc/kernel/sys_sparc32.c +++ b/arch/sparc/kernel/sys_sparc32.c @@ -139,8 +139,8 @@ static int cp_compat_stat64(struct kstat *stat, err |= put_user(stat->ino, &statbuf->st_ino); err |= put_user(stat->mode, &statbuf->st_mode); err |= put_user(stat->nlink, &statbuf->st_nlink); - err |= put_user(stat->uid, &statbuf->st_uid); - err |= put_user(stat->gid, &statbuf->st_gid); + err |= put_user(from_kuid_munged(current_user_ns(), stat->uid), &statbuf->st_uid); + err |= put_user(from_kgid_munged(current_user_ns(), stat->gid), &statbuf->st_gid); err |= put_user(huge_encode_dev(stat->rdev), &statbuf->st_rdev); err |= put_user(0, (unsigned long __user *) &statbuf->__pad3[0]); err |= put_user(stat->size, &statbuf->st_size); diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index aec2202a596c..d5c820a54590 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -71,8 +71,8 @@ static int cp_stat64(struct stat64 __user *ubuf, struct kstat *stat) { typeof(ubuf->st_uid) uid = 0; typeof(ubuf->st_gid) gid = 0; - SET_UID(uid, stat->uid); - SET_GID(gid, stat->gid); + SET_UID(uid, from_kuid_munged(current_user_ns(), stat->uid)); + SET_GID(gid, from_kgid_munged(current_user_ns(), stat->gid)); if (!access_ok(VERIFY_WRITE, ubuf, sizeof(struct stat64)) || __put_user(huge_encode_dev(stat->dev), &ubuf->st_dev) || __put_user(stat->ino, &ubuf->__st_ino) || diff --git a/fs/compat.c b/fs/compat.c index f2944ace7a7b..0781e619a62a 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -144,8 +144,8 @@ static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) tmp.st_nlink = stat->nlink; if (tmp.st_nlink != stat->nlink) return -EOVERFLOW; - SET_UID(tmp.st_uid, stat->uid); - SET_GID(tmp.st_gid, stat->gid); + SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); + SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); tmp.st_rdev = old_encode_dev(stat->rdev); if ((u64) stat->size > MAX_NON_LFS) return -EOVERFLOW; diff --git a/fs/stat.c b/fs/stat.c index c733dc5753ae..31acca5f5a0c 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -137,8 +137,8 @@ static int cp_old_stat(struct kstat *stat, struct __old_kernel_stat __user * sta tmp.st_nlink = stat->nlink; if (tmp.st_nlink != stat->nlink) return -EOVERFLOW; - SET_UID(tmp.st_uid, stat->uid); - SET_GID(tmp.st_gid, stat->gid); + SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); + SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); tmp.st_rdev = old_encode_dev(stat->rdev); #if BITS_PER_LONG == 32 if (stat->size > MAX_NON_LFS) @@ -215,8 +215,8 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) tmp.st_nlink = stat->nlink; if (tmp.st_nlink != stat->nlink) return -EOVERFLOW; - SET_UID(tmp.st_uid, stat->uid); - SET_GID(tmp.st_gid, stat->gid); + SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); + SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); #if BITS_PER_LONG == 32 tmp.st_rdev = old_encode_dev(stat->rdev); #else @@ -350,8 +350,8 @@ static long cp_new_stat64(struct kstat *stat, struct stat64 __user *statbuf) #endif tmp.st_mode = stat->mode; tmp.st_nlink = stat->nlink; - tmp.st_uid = stat->uid; - tmp.st_gid = stat->gid; + tmp.st_uid = from_kuid_munged(current_user_ns(), stat->uid); + tmp.st_gid = from_kgid_munged(current_user_ns(), stat->gid); tmp.st_atime = stat->atime.tv_sec; tmp.st_atime_nsec = stat->atime.tv_nsec; tmp.st_mtime = stat->mtime.tv_sec; diff --git a/include/linux/stat.h b/include/linux/stat.h index 611c398dab72..46132409a3f7 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -58,14 +58,15 @@ #include #include +#include struct kstat { u64 ino; dev_t dev; umode_t mode; unsigned int nlink; - uid_t uid; - gid_t gid; + kuid_t uid; + kgid_t gid; dev_t rdev; loff_t size; struct timespec atime; -- cgit v1.2.3 From 9e4a36ece652908276bc4abb4324ec56292453e1 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 16 Nov 2011 23:37:59 -0800 Subject: userns: Fail exec for suid and sgid binaries with ids outside our user namespace. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- fs/exec.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/exec.c b/fs/exec.c index 00ae2ef100d8..e001bdfac530 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1291,8 +1291,11 @@ int prepare_binprm(struct linux_binprm *bprm) if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)) { /* Set-uid? */ if (mode & S_ISUID) { + if (!kuid_has_mapping(bprm->cred->user_ns, inode->i_uid)) + return -EPERM; bprm->per_clear |= PER_CLEAR_ON_SETID; bprm->cred->euid = inode->i_uid; + } /* Set-gid? */ @@ -1302,6 +1305,8 @@ int prepare_binprm(struct linux_binprm *bprm) * executable. */ if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { + if (!kgid_has_mapping(bprm->cred->user_ns, inode->i_gid)) + return -EPERM; bprm->per_clear |= PER_CLEAR_ON_SETID; bprm->cred->egid = inode->i_gid; } -- cgit v1.2.3 From 65cc5a17ad3388f89ddc3d68226a09242656809b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 12 Mar 2012 13:08:45 -0700 Subject: userns: Teach inode_capable to understand inodes whose uids map to other namespaces. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- kernel/capability.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/kernel/capability.c b/kernel/capability.c index cc5f0718215d..493d97259484 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -429,12 +429,14 @@ bool nsown_capable(int cap) * targeted at it's own user namespace and that the given inode is owned * by the current user namespace or a child namespace. * - * Currently inodes can only be owned by the initial user namespace. + * Currently we check to see if an inode is owned by the current + * user namespace by seeing if the inode's owner maps into the + * current user namespace. * */ bool inode_capable(const struct inode *inode, int cap) { struct user_namespace *ns = current_user_ns(); - return ns_capable(ns, cap) && (ns == &init_user_ns); + return ns_capable(ns, cap) && kuid_has_mapping(ns, inode->i_uid); } -- cgit v1.2.3 From 54ba47edac90091d42e5f97516cad56953576a5a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 13 Mar 2012 16:04:35 -0700 Subject: userns: signal remove unnecessary map_cred_ns map_cred_ns is a light wrapper around from_kuid with the order of the arguments reversed. Replace map_cred_ns with from_kuid and remove map_cred_ns. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- kernel/signal.c | 20 +++++--------------- 1 file changed, 5 insertions(+), 15 deletions(-) diff --git a/kernel/signal.c b/kernel/signal.c index aef629c65c87..833ea5166855 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1019,15 +1019,6 @@ static inline int legacy_queue(struct sigpending *signals, int sig) return (sig < SIGRTMIN) && sigismember(&signals->signal, sig); } -/* - * map the uid in struct cred into user namespace *ns - */ -static inline uid_t map_cred_ns(const struct cred *cred, - struct user_namespace *ns) -{ - return from_kuid_munged(ns, cred->uid); -} - #ifdef CONFIG_USER_NS static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_struct *t) { @@ -1677,8 +1668,8 @@ bool do_notify_parent(struct task_struct *tsk, int sig) */ rcu_read_lock(); info.si_pid = task_pid_nr_ns(tsk, tsk->parent->nsproxy->pid_ns); - info.si_uid = map_cred_ns(__task_cred(tsk), - task_cred_xxx(tsk->parent, user_ns)); + info.si_uid = from_kuid_munged(task_cred_xxx(tsk->parent, user_ns), + task_uid(tsk)); rcu_read_unlock(); info.si_utime = cputime_to_clock_t(tsk->utime + tsk->signal->utime); @@ -1761,8 +1752,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, */ rcu_read_lock(); info.si_pid = task_pid_nr_ns(tsk, parent->nsproxy->pid_ns); - info.si_uid = map_cred_ns(__task_cred(tsk), - task_cred_xxx(parent, user_ns)); + info.si_uid = from_kuid_munged(task_cred_xxx(parent, user_ns), task_uid(tsk)); rcu_read_unlock(); info.si_utime = cputime_to_clock_t(tsk->utime); @@ -2180,8 +2170,8 @@ static int ptrace_signal(int signr, siginfo_t *info, info->si_code = SI_USER; rcu_read_lock(); info->si_pid = task_pid_vnr(current->parent); - info->si_uid = map_cred_ns(__task_cred(current->parent), - current_user_ns()); + info->si_uid = from_kuid_munged(current_user_ns(), + task_uid(current->parent)); rcu_read_unlock(); } -- cgit v1.2.3 From e1c972b681bf118fcedb9fe2ed7a73de983aa5ef Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 21 Apr 2012 04:09:01 -0700 Subject: userns: Add negative depends on entries to avoid building code that is userns unsafe Add a new internal Kconfig option UIDGID_CONVERTED that is true when the selected Kconfig options have been converted to be user namespace safe, and guard USER_NS and guard the UIDGID_STRICT_TYPE_CHECK options with it. This keeps innocent kernel users from having the choice to enable the user namespace in the cases where it is known not to work. Most of the rest of the conversions are simple and straight forward but their sheer number means it is good not to count on having them all done and reviwed before thinking of merging this code. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- init/Kconfig | 131 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 131 insertions(+) diff --git a/init/Kconfig b/init/Kconfig index 86cf760893b3..3349670149dc 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -828,7 +828,9 @@ config IPC_NS config USER_NS bool "User namespace (EXPERIMENTAL)" depends on EXPERIMENTAL + depends on UIDGID_CONVERTED select UIDGID_STRICT_TYPE_CHECKS + default n help This allows containers, i.e. vservers, to use user namespaces @@ -853,8 +855,137 @@ config NET_NS endif # NAMESPACES +config UIDGID_CONVERTED + # True if all of the selected software conmponents are known + # to have uid_t and gid_t converted to kuid_t and kgid_t + # where appropriate and are otherwise safe to use with + # the user namespace. + bool + default y + + # List of kernel pieces that need user namespace work + # Features + depends on BINFMT_ELF = n + depends on BINFMT_ELF_FDPIC = n + depends on UNIX98_PTYS = n + depends on CGROUPS = n + depends on MIGRATION = n + depends on NUMA = n + depends on SYSVIPC = n + depends on IMA = n + depends on EVM = n + depends on KEYS = n + depends on AUDIT = n + depends on AUDITSYSCALL = n + depends on TASKSTATS = n + depends on TRACING = n + depends on FS_POSIX_ACL = n + depends on QUOTA = n + depends on QUOTACTL = n + depends on DEBUG_CREDENTIALS = n + depends on BSD_PROCESS_ACCT = n + depends on DRM = n + depends on PROC_EVENTS = n + + # Networking + depends on NET = n + depends on NET_9P = n + depends on IPX = n + depends on PHONET = n + depends on NET_CLS_FLOW = n + depends on NETFILTER_XT_MATCH_OWNER = n + depends on NETFILTER_XT_MATCH_RECENT = n + depends on NETFILTER_XT_TARGET_LOG = n + depends on NETFILTER_NETLINK_LOG = n + depends on INET = n + depends on IPV6 = n + depends on IP_SCTP = n + depends on AF_RXRPC = n + depends on LLC2 = n + depends on NET_KEY = n + depends on INET_DIAG = n + depends on DNS_RESOLVER = n + depends on AX25 = n + depends on ATALK = n + + # Filesystems + depends on USB_DEVICEFS = n + depends on USB_GADGETFS = n + depends on USB_FUNCTIONFS = n + depends on DEVTMPFS = n + depends on XENFS = n + + depends on 9P_FS = n + depends on ADFS_FS = n + depends on AFFS_FS = n + depends on AFS_FS = n + depends on AUTOFS4_FS = n + depends on BEFS_FS = n + depends on BFS_FS = n + depends on BTRFS_FS = n + depends on CEPH_FS = n + depends on CIFS = n + depends on CODA_FS = n + depends on CONFIGFS_FS = n + depends on CRAMFS = n + depends on DEBUG_FS = n + depends on ECRYPT_FS = n + depends on EFS_FS = n + depends on EXOFS_FS = n + depends on EXT2_FS = n + depends on EXT3_FS = n + depends on EXT4_FS = n + depends on FAT_FS = n + depends on FUSE_FS = n + depends on GFS2_FS = n + depends on HFS_FS = n + depends on HFSPLUS_FS = n + depends on HPFS_FS = n + depends on HUGETLBFS = n + depends on ISO9660_FS = n + depends on JFFS2_FS = n + depends on JFS_FS = n + depends on LOGFS = n + depends on MINIX_FS = n + depends on NCP_FS = n + depends on NFSD = n + depends on NFS_FS = n + depends on NILFS2_FS = n + depends on NTFS_FS = n + depends on OCFS2_FS = n + depends on OMFS_FS = n + depends on PROC_FS = n + depends on PROC_SYSCTL = n + depends on QNX4FS_FS = n + depends on QNX6FS_FS = n + depends on REISERFS_FS = n + depends on SQUASHFS = n + depends on SYSFS = n + depends on SYSV_FS = n + depends on TMPFS = n + depends on UBIFS_FS = n + depends on UDF_FS = n + depends on UFS_FS = n + depends on VXFS_FS = n + depends on XFS_FS = n + + depends on !UML || HOSTFS = n + + # The rare drivers that won't build + depends on AIRO = n + depends on AIRO_CS = n + depends on TUN = n + depends on INFINIBAND_QIB = n + depends on BLK_DEV_LOOP = n + depends on ANDROID_BINDER_IPC = n + + # Security modules + depends on SECURITY_TOMOYO = n + depends on SECURITY_APPARMOR = n + config UIDGID_STRICT_TYPE_CHECKS bool "Require conversions between uid/gids and their internal representation" + depends on UIDGID_CONVERTED default n help While the nececessary conversions are being added to all subsystems this option allows -- cgit v1.2.3 From ebc887b278944fc478ab31a4be8ba0cae5fe4f48 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 7 Feb 2012 18:36:10 -0800 Subject: userns: Convert binary formats to use kuid/kgid where appropriate Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- fs/binfmt_elf.c | 12 ++++++------ fs/binfmt_elf_fdpic.c | 12 ++++++------ init/Kconfig | 2 -- 3 files changed, 12 insertions(+), 14 deletions(-) diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 48ffb3dc610a..efc673163ef5 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -228,10 +228,10 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec, NEW_AUX_ENT(AT_BASE, interp_load_addr); NEW_AUX_ENT(AT_FLAGS, 0); NEW_AUX_ENT(AT_ENTRY, exec->e_entry); - NEW_AUX_ENT(AT_UID, cred->uid); - NEW_AUX_ENT(AT_EUID, cred->euid); - NEW_AUX_ENT(AT_GID, cred->gid); - NEW_AUX_ENT(AT_EGID, cred->egid); + NEW_AUX_ENT(AT_UID, from_kuid_munged(cred->user_ns, cred->uid)); + NEW_AUX_ENT(AT_EUID, from_kuid_munged(cred->user_ns, cred->euid)); + NEW_AUX_ENT(AT_GID, from_kgid_munged(cred->user_ns, cred->gid)); + NEW_AUX_ENT(AT_EGID, from_kgid_munged(cred->user_ns, cred->egid)); NEW_AUX_ENT(AT_SECURE, security_bprm_secureexec(bprm)); NEW_AUX_ENT(AT_RANDOM, (elf_addr_t)(unsigned long)u_rand_bytes); NEW_AUX_ENT(AT_EXECFN, bprm->exec); @@ -1367,8 +1367,8 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p, psinfo->pr_flag = p->flags; rcu_read_lock(); cred = __task_cred(p); - SET_UID(psinfo->pr_uid, cred->uid); - SET_GID(psinfo->pr_gid, cred->gid); + SET_UID(psinfo->pr_uid, from_kuid_munged(cred->user_ns, cred->uid)); + SET_GID(psinfo->pr_gid, from_kgid_munged(cred->user_ns, cred->gid)); rcu_read_unlock(); strncpy(psinfo->pr_fname, p->comm, sizeof(psinfo->pr_fname)); diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 9bd5612a8224..82bf0ed0cd10 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -631,10 +631,10 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm, NEW_AUX_ENT(AT_BASE, interp_params->elfhdr_addr); NEW_AUX_ENT(AT_FLAGS, 0); NEW_AUX_ENT(AT_ENTRY, exec_params->entry_addr); - NEW_AUX_ENT(AT_UID, (elf_addr_t) cred->uid); - NEW_AUX_ENT(AT_EUID, (elf_addr_t) cred->euid); - NEW_AUX_ENT(AT_GID, (elf_addr_t) cred->gid); - NEW_AUX_ENT(AT_EGID, (elf_addr_t) cred->egid); + NEW_AUX_ENT(AT_UID, (elf_addr_t) from_kuid_munged(cred->user_ns, cred->uid)); + NEW_AUX_ENT(AT_EUID, (elf_addr_t) from_kuid_munged(cred->user_ns, cred->euid)); + NEW_AUX_ENT(AT_GID, (elf_addr_t) from_kgid_munged(cred->user_ns, cred->gid)); + NEW_AUX_ENT(AT_EGID, (elf_addr_t) from_kgid_munged(cred->user_ns, cred->egid)); NEW_AUX_ENT(AT_SECURE, security_bprm_secureexec(bprm)); NEW_AUX_ENT(AT_EXECFN, bprm->exec); @@ -1431,8 +1431,8 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p, psinfo->pr_flag = p->flags; rcu_read_lock(); cred = __task_cred(p); - SET_UID(psinfo->pr_uid, cred->uid); - SET_GID(psinfo->pr_gid, cred->gid); + SET_UID(psinfo->pr_uid, from_kuid_munged(cred->user_ns, cred->uid)); + SET_GID(psinfo->pr_gid, from_kgid_munged(cred->user_ns, cred->gid)); rcu_read_unlock(); strncpy(psinfo->pr_fname, p->comm, sizeof(psinfo->pr_fname)); diff --git a/init/Kconfig b/init/Kconfig index 3349670149dc..994a53ec1d8a 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -865,8 +865,6 @@ config UIDGID_CONVERTED # List of kernel pieces that need user namespace work # Features - depends on BINFMT_ELF = n - depends on BINFMT_ELF_FDPIC = n depends on UNIX98_PTYS = n depends on CGROUPS = n depends on MIGRATION = n -- cgit v1.2.3 From f04c6ce2cfaff4b982a6c8ad37e07c14379c111c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 7 Feb 2012 16:22:56 -0800 Subject: userns: Convert devpts to use kuid/kgid where appropriate Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- fs/devpts/inode.c | 24 ++++++++++++++++-------- init/Kconfig | 1 - 2 files changed, 16 insertions(+), 9 deletions(-) diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 10f5e0b484db..979c1e309c73 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -98,8 +98,8 @@ static struct vfsmount *devpts_mnt; struct pts_mount_opts { int setuid; int setgid; - uid_t uid; - gid_t gid; + kuid_t uid; + kgid_t gid; umode_t mode; umode_t ptmxmode; int newinstance; @@ -158,11 +158,13 @@ static inline struct super_block *pts_sb_from_inode(struct inode *inode) static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts) { char *p; + kuid_t uid; + kgid_t gid; opts->setuid = 0; opts->setgid = 0; - opts->uid = 0; - opts->gid = 0; + opts->uid = GLOBAL_ROOT_UID; + opts->gid = GLOBAL_ROOT_GID; opts->mode = DEVPTS_DEFAULT_MODE; opts->ptmxmode = DEVPTS_DEFAULT_PTMX_MODE; opts->max = NR_UNIX98_PTY_MAX; @@ -184,13 +186,19 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts) case Opt_uid: if (match_int(&args[0], &option)) return -EINVAL; - opts->uid = option; + uid = make_kuid(current_user_ns(), option); + if (!uid_valid(uid)) + return -EINVAL; + opts->uid = uid; opts->setuid = 1; break; case Opt_gid: if (match_int(&args[0], &option)) return -EINVAL; - opts->gid = option; + gid = make_kgid(current_user_ns(), option); + if (!gid_valid(gid)) + return -EINVAL; + opts->gid = gid; opts->setgid = 1; break; case Opt_mode: @@ -315,9 +323,9 @@ static int devpts_show_options(struct seq_file *seq, struct dentry *root) struct pts_mount_opts *opts = &fsi->mount_opts; if (opts->setuid) - seq_printf(seq, ",uid=%u", opts->uid); + seq_printf(seq, ",uid=%u", from_kuid_munged(&init_user_ns, opts->uid)); if (opts->setgid) - seq_printf(seq, ",gid=%u", opts->gid); + seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, opts->gid)); seq_printf(seq, ",mode=%03o", opts->mode); #ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES seq_printf(seq, ",ptmxmode=%03o", opts->ptmxmode); diff --git a/init/Kconfig b/init/Kconfig index 994a53ec1d8a..2738a7c47936 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -865,7 +865,6 @@ config UIDGID_CONVERTED # List of kernel pieces that need user namespace work # Features - depends on UNIX98_PTYS = n depends on CGROUPS = n depends on MIGRATION = n depends on NUMA = n -- cgit v1.2.3 From b8a9f9e183229d163d8ace855cbbb63c209fba3c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 7 Feb 2012 15:39:12 -0800 Subject: userns: Convert ext2 to use kuid/kgid where appropriate. Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- fs/ext2/balloc.c | 5 +++-- fs/ext2/ext2.h | 8 ++++---- fs/ext2/inode.c | 20 ++++++++++++-------- fs/ext2/super.c | 31 +++++++++++++++++++++++-------- init/Kconfig | 1 - 5 files changed, 42 insertions(+), 23 deletions(-) diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c index a8cbe1bc6ad4..030c6d277e14 100644 --- a/fs/ext2/balloc.c +++ b/fs/ext2/balloc.c @@ -1193,8 +1193,9 @@ static int ext2_has_free_blocks(struct ext2_sb_info *sbi) free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter); root_blocks = le32_to_cpu(sbi->s_es->s_r_blocks_count); if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) && - sbi->s_resuid != current_fsuid() && - (sbi->s_resgid == 0 || !in_group_p (sbi->s_resgid))) { + !uid_eq(sbi->s_resuid, current_fsuid()) && + (gid_eq(sbi->s_resgid, GLOBAL_ROOT_GID) || + !in_group_p (sbi->s_resgid))) { return 0; } return 1; diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 0b2b4db5bdcd..d9a17d0b124d 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -82,8 +82,8 @@ struct ext2_sb_info { struct buffer_head ** s_group_desc; unsigned long s_mount_opt; unsigned long s_sb_block; - uid_t s_resuid; - gid_t s_resgid; + kuid_t s_resuid; + kgid_t s_resgid; unsigned short s_mount_state; unsigned short s_pad; int s_addr_per_block_bits; @@ -637,8 +637,8 @@ static inline void verify_offsets(void) */ struct ext2_mount_options { unsigned long s_mount_opt; - uid_t s_resuid; - gid_t s_resgid; + kuid_t s_resuid; + kgid_t s_resgid; }; /* diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 740cad8dcd8d..f9fa95f8443d 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1293,6 +1293,8 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino) struct inode *inode; long ret = -EIO; int n; + uid_t i_uid; + gid_t i_gid; inode = iget_locked(sb, ino); if (!inode) @@ -1310,12 +1312,14 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino) } inode->i_mode = le16_to_cpu(raw_inode->i_mode); - inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); - inode->i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); + i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); + i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); if (!(test_opt (inode->i_sb, NO_UID32))) { - inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; - inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; + i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; + i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; } + i_uid_write(inode, i_uid); + i_gid_write(inode, i_gid); set_nlink(inode, le16_to_cpu(raw_inode->i_links_count)); inode->i_size = le32_to_cpu(raw_inode->i_size); inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime); @@ -1413,8 +1417,8 @@ static int __ext2_write_inode(struct inode *inode, int do_sync) struct ext2_inode_info *ei = EXT2_I(inode); struct super_block *sb = inode->i_sb; ino_t ino = inode->i_ino; - uid_t uid = inode->i_uid; - gid_t gid = inode->i_gid; + uid_t uid = i_uid_read(inode); + gid_t gid = i_gid_read(inode); struct buffer_head * bh; struct ext2_inode * raw_inode = ext2_get_inode(sb, ino, &bh); int n; @@ -1529,8 +1533,8 @@ int ext2_setattr(struct dentry *dentry, struct iattr *iattr) if (is_quota_modification(inode, iattr)) dquot_initialize(inode); - if ((iattr->ia_valid & ATTR_UID && iattr->ia_uid != inode->i_uid) || - (iattr->ia_valid & ATTR_GID && iattr->ia_gid != inode->i_gid)) { + if ((iattr->ia_valid & ATTR_UID && !uid_eq(iattr->ia_uid, inode->i_uid)) || + (iattr->ia_valid & ATTR_GID && !gid_eq(iattr->ia_gid, inode->i_gid))) { error = dquot_transfer(inode, iattr); if (error) return error; diff --git a/fs/ext2/super.c b/fs/ext2/super.c index e1025c7a437a..38f816071ddb 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -228,13 +228,15 @@ static int ext2_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",grpid"); if (!test_opt(sb, GRPID) && (def_mount_opts & EXT2_DEFM_BSDGROUPS)) seq_puts(seq, ",nogrpid"); - if (sbi->s_resuid != EXT2_DEF_RESUID || + if (!uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT2_DEF_RESUID)) || le16_to_cpu(es->s_def_resuid) != EXT2_DEF_RESUID) { - seq_printf(seq, ",resuid=%u", sbi->s_resuid); + seq_printf(seq, ",resuid=%u", + from_kuid_munged(&init_user_ns, sbi->s_resuid)); } - if (sbi->s_resgid != EXT2_DEF_RESGID || + if (!gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT2_DEF_RESGID)) || le16_to_cpu(es->s_def_resgid) != EXT2_DEF_RESGID) { - seq_printf(seq, ",resgid=%u", sbi->s_resgid); + seq_printf(seq, ",resgid=%u", + from_kgid_munged(&init_user_ns, sbi->s_resgid)); } if (test_opt(sb, ERRORS_RO)) { int def_errors = le16_to_cpu(es->s_errors); @@ -436,6 +438,8 @@ static int parse_options(char *options, struct super_block *sb) struct ext2_sb_info *sbi = EXT2_SB(sb); substring_t args[MAX_OPT_ARGS]; int option; + kuid_t uid; + kgid_t gid; if (!options) return 1; @@ -462,12 +466,23 @@ static int parse_options(char *options, struct super_block *sb) case Opt_resuid: if (match_int(&args[0], &option)) return 0; - sbi->s_resuid = option; + uid = make_kuid(current_user_ns(), option); + if (!uid_valid(uid)) { + ext2_msg(sb, KERN_ERR, "Invalid uid value %d", option); + return -1; + + } + sbi->s_resuid = uid; break; case Opt_resgid: if (match_int(&args[0], &option)) return 0; - sbi->s_resgid = option; + gid = make_kgid(current_user_ns(), option); + if (!gid_valid(gid)) { + ext2_msg(sb, KERN_ERR, "Invalid gid value %d", option); + return -1; + } + sbi->s_resgid = gid; break; case Opt_sb: /* handled by get_sb_block() instead of here */ @@ -841,8 +856,8 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) else set_opt(sbi->s_mount_opt, ERRORS_RO); - sbi->s_resuid = le16_to_cpu(es->s_def_resuid); - sbi->s_resgid = le16_to_cpu(es->s_def_resgid); + sbi->s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid)); + sbi->s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid)); set_opt(sbi->s_mount_opt, RESERVATION); diff --git a/init/Kconfig b/init/Kconfig index 2738a7c47936..769d9a471eec 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -929,7 +929,6 @@ config UIDGID_CONVERTED depends on ECRYPT_FS = n depends on EFS_FS = n depends on EXOFS_FS = n - depends on EXT2_FS = n depends on EXT3_FS = n depends on EXT4_FS = n depends on FAT_FS = n -- cgit v1.2.3 From 1523299d5817773e344d135d4b1c485f269400bc Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 7 Feb 2012 15:41:24 -0800 Subject: userns: Convert ext3 to use kuid/kgid where appropriate Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- fs/ext3/balloc.c | 5 +++-- fs/ext3/ext3.h | 8 ++++---- fs/ext3/inode.c | 32 ++++++++++++++++++++------------ fs/ext3/super.c | 35 +++++++++++++++++++++++++---------- include/trace/events/ext3.h | 4 ++-- init/Kconfig | 1 - 6 files changed, 54 insertions(+), 31 deletions(-) diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c index baac1b129fba..25cd60892116 100644 --- a/fs/ext3/balloc.c +++ b/fs/ext3/balloc.c @@ -1439,8 +1439,9 @@ static int ext3_has_free_blocks(struct ext3_sb_info *sbi, int use_reservation) free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter); root_blocks = le32_to_cpu(sbi->s_es->s_r_blocks_count); if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) && - !use_reservation && sbi->s_resuid != current_fsuid() && - (sbi->s_resgid == 0 || !in_group_p (sbi->s_resgid))) { + !use_reservation && !uid_eq(sbi->s_resuid, current_fsuid()) && + (gid_eq(sbi->s_resgid, GLOBAL_ROOT_GID) || + !in_group_p (sbi->s_resgid))) { return 0; } return 1; diff --git a/fs/ext3/ext3.h b/fs/ext3/ext3.h index b6515fd7e56c..7977973a24f0 100644 --- a/fs/ext3/ext3.h +++ b/fs/ext3/ext3.h @@ -243,8 +243,8 @@ struct ext3_new_group_data { */ struct ext3_mount_options { unsigned long s_mount_opt; - uid_t s_resuid; - gid_t s_resgid; + kuid_t s_resuid; + kgid_t s_resgid; unsigned long s_commit_interval; #ifdef CONFIG_QUOTA int s_jquota_fmt; @@ -637,8 +637,8 @@ struct ext3_sb_info { struct buffer_head ** s_group_desc; unsigned long s_mount_opt; ext3_fsblk_t s_sb_block; - uid_t s_resuid; - gid_t s_resgid; + kuid_t s_resuid; + kgid_t s_resgid; unsigned short s_mount_state; unsigned short s_pad; int s_addr_per_block_bits; diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 10d7812f6021..a09790a412b1 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -2891,6 +2891,8 @@ struct inode *ext3_iget(struct super_block *sb, unsigned long ino) transaction_t *transaction; long ret; int block; + uid_t i_uid; + gid_t i_gid; inode = iget_locked(sb, ino); if (!inode) @@ -2907,12 +2909,14 @@ struct inode *ext3_iget(struct super_block *sb, unsigned long ino) bh = iloc.bh; raw_inode = ext3_raw_inode(&iloc); inode->i_mode = le16_to_cpu(raw_inode->i_mode); - inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); - inode->i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); + i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); + i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); if(!(test_opt (inode->i_sb, NO_UID32))) { - inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; - inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; + i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; + i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; } + i_uid_write(inode, i_uid); + i_gid_write(inode, i_gid); set_nlink(inode, le16_to_cpu(raw_inode->i_links_count)); inode->i_size = le32_to_cpu(raw_inode->i_size); inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime); @@ -3068,6 +3072,8 @@ static int ext3_do_update_inode(handle_t *handle, struct ext3_inode_info *ei = EXT3_I(inode); struct buffer_head *bh = iloc->bh; int err = 0, rc, block; + uid_t i_uid; + gid_t i_gid; again: /* we can't allow multiple procs in here at once, its a bit racey */ @@ -3080,27 +3086,29 @@ again: ext3_get_inode_flags(ei); raw_inode->i_mode = cpu_to_le16(inode->i_mode); + i_uid = i_uid_read(inode); + i_gid = i_gid_read(inode); if(!(test_opt(inode->i_sb, NO_UID32))) { - raw_inode->i_uid_low = cpu_to_le16(low_16_bits(inode->i_uid)); - raw_inode->i_gid_low = cpu_to_le16(low_16_bits(inode->i_gid)); + raw_inode->i_uid_low = cpu_to_le16(low_16_bits(i_uid)); + raw_inode->i_gid_low = cpu_to_le16(low_16_bits(i_gid)); /* * Fix up interoperability with old kernels. Otherwise, old inodes get * re-used with the upper 16 bits of the uid/gid intact */ if(!ei->i_dtime) { raw_inode->i_uid_high = - cpu_to_le16(high_16_bits(inode->i_uid)); + cpu_to_le16(high_16_bits(i_uid)); raw_inode->i_gid_high = - cpu_to_le16(high_16_bits(inode->i_gid)); + cpu_to_le16(high_16_bits(i_gid)); } else { raw_inode->i_uid_high = 0; raw_inode->i_gid_high = 0; } } else { raw_inode->i_uid_low = - cpu_to_le16(fs_high2lowuid(inode->i_uid)); + cpu_to_le16(fs_high2lowuid(i_uid)); raw_inode->i_gid_low = - cpu_to_le16(fs_high2lowgid(inode->i_gid)); + cpu_to_le16(fs_high2lowgid(i_gid)); raw_inode->i_uid_high = 0; raw_inode->i_gid_high = 0; } @@ -3262,8 +3270,8 @@ int ext3_setattr(struct dentry *dentry, struct iattr *attr) if (is_quota_modification(inode, attr)) dquot_initialize(inode); - if ((ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) || - (ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid)) { + if ((ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) || + (ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) { handle_t *handle; /* (user+group)*(old+new) structure, inode write (sb, diff --git a/fs/ext3/super.c b/fs/ext3/super.c index cf0b5921cf0f..94ef7e616129 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -617,13 +617,15 @@ static int ext3_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",grpid"); if (!test_opt(sb, GRPID) && (def_mount_opts & EXT3_DEFM_BSDGROUPS)) seq_puts(seq, ",nogrpid"); - if (sbi->s_resuid != EXT3_DEF_RESUID || + if (!uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT3_DEF_RESUID)) || le16_to_cpu(es->s_def_resuid) != EXT3_DEF_RESUID) { - seq_printf(seq, ",resuid=%u", sbi->s_resuid); + seq_printf(seq, ",resuid=%u", + from_kuid_munged(&init_user_ns, sbi->s_resuid)); } - if (sbi->s_resgid != EXT3_DEF_RESGID || + if (!gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT3_DEF_RESGID)) || le16_to_cpu(es->s_def_resgid) != EXT3_DEF_RESGID) { - seq_printf(seq, ",resgid=%u", sbi->s_resgid); + seq_printf(seq, ",resgid=%u", + from_kgid_munged(&init_user_ns, sbi->s_resgid)); } if (test_opt(sb, ERRORS_RO)) { int def_errors = le16_to_cpu(es->s_errors); @@ -967,6 +969,8 @@ static int parse_options (char *options, struct super_block *sb, substring_t args[MAX_OPT_ARGS]; int data_opt = 0; int option; + kuid_t uid; + kgid_t gid; #ifdef CONFIG_QUOTA int qfmt; #endif @@ -1000,12 +1004,23 @@ static int parse_options (char *options, struct super_block *sb, case Opt_resuid: if (match_int(&args[0], &option)) return 0; - sbi->s_resuid = option; + uid = make_kuid(current_user_ns(), option); + if (!uid_valid(uid)) { + ext3_msg(sb, KERN_ERR, "Invalid uid value %d", option); + return -1; + + } + sbi->s_resuid = uid; break; case Opt_resgid: if (match_int(&args[0], &option)) return 0; - sbi->s_resgid = option; + gid = make_kgid(current_user_ns(), option); + if (!gid_valid(gid)) { + ext3_msg(sb, KERN_ERR, "Invalid gid value %d", option); + return -1; + } + sbi->s_resgid = gid; break; case Opt_sb: /* handled by get_sb_block() instead of here */ @@ -1651,8 +1666,8 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) } sb->s_fs_info = sbi; sbi->s_mount_opt = 0; - sbi->s_resuid = EXT3_DEF_RESUID; - sbi->s_resgid = EXT3_DEF_RESGID; + sbi->s_resuid = make_kuid(&init_user_ns, EXT3_DEF_RESUID); + sbi->s_resgid = make_kgid(&init_user_ns, EXT3_DEF_RESGID); sbi->s_sb_block = sb_block; blocksize = sb_min_blocksize(sb, EXT3_MIN_BLOCK_SIZE); @@ -1716,8 +1731,8 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) else set_opt(sbi->s_mount_opt, ERRORS_RO); - sbi->s_resuid = le16_to_cpu(es->s_def_resuid); - sbi->s_resgid = le16_to_cpu(es->s_def_resgid); + sbi->s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid)); + sbi->s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid)); /* enable barriers by default */ set_opt(sbi->s_mount_opt, BARRIER); diff --git a/include/trace/events/ext3.h b/include/trace/events/ext3.h index 7b53c0573dc9..15d11a39be47 100644 --- a/include/trace/events/ext3.h +++ b/include/trace/events/ext3.h @@ -24,8 +24,8 @@ TRACE_EVENT(ext3_free_inode, __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->mode = inode->i_mode; - __entry->uid = inode->i_uid; - __entry->gid = inode->i_gid; + __entry->uid = i_uid_read(inode); + __entry->gid = i_gid_read(inode); __entry->blocks = inode->i_blocks; ), diff --git a/init/Kconfig b/init/Kconfig index 769d9a471eec..669f991bb133 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -929,7 +929,6 @@ config UIDGID_CONVERTED depends on ECRYPT_FS = n depends on EFS_FS = n depends on EXOFS_FS = n - depends on EXT3_FS = n depends on EXT4_FS = n depends on FAT_FS = n depends on FUSE_FS = n -- cgit v1.2.3 From 08cefc7ab839cf3ece44b8033968a4732eac06d8 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 7 Feb 2012 15:41:49 -0800 Subject: userns: Convert ext4 to user kuid/kgid where appropriate Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- fs/ext4/balloc.c | 4 ++-- fs/ext4/ext4.h | 4 ++-- fs/ext4/ialloc.c | 4 ++-- fs/ext4/inode.c | 34 ++++++++++++++++++++-------------- fs/ext4/migrate.c | 4 ++-- fs/ext4/super.c | 38 ++++++++++++++++++++++++++------------ include/trace/events/ext4.h | 4 ++-- init/Kconfig | 1 - 8 files changed, 56 insertions(+), 37 deletions(-) diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 4bbd07a6fa18..c45c41129a35 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -461,8 +461,8 @@ static int ext4_has_free_clusters(struct ext4_sb_info *sbi, return 1; /* Hm, nope. Are (enough) root reserved clusters available? */ - if (sbi->s_resuid == current_fsuid() || - ((sbi->s_resgid != 0) && in_group_p(sbi->s_resgid)) || + if (uid_eq(sbi->s_resuid, current_fsuid()) || + (!gid_eq(sbi->s_resgid, GLOBAL_ROOT_GID) && in_group_p(sbi->s_resgid)) || capable(CAP_SYS_RESOURCE) || (flags & EXT4_MB_USE_ROOT_BLOCKS)) { diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index ab2594a30f86..0b4aeb24593c 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1153,8 +1153,8 @@ struct ext4_sb_info { unsigned int s_mount_flags; unsigned int s_def_mount_opt; ext4_fsblk_t s_sb_block; - uid_t s_resuid; - gid_t s_resgid; + kuid_t s_resuid; + kgid_t s_resgid; unsigned short s_mount_state; unsigned short s_pad; int s_addr_per_block_bits; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 409c2ee7750a..9f9acac6c43f 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -808,8 +808,8 @@ got: } if (owner) { inode->i_mode = mode; - inode->i_uid = owner[0]; - inode->i_gid = owner[1]; + i_uid_write(inode, owner[0]); + i_gid_write(inode, owner[1]); } else if (test_opt(sb, GRPID)) { inode->i_mode = mode; inode->i_uid = current_fsuid(); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index c77b0bd2c711..07eaf565fdcb 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3630,6 +3630,8 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) journal_t *journal = EXT4_SB(sb)->s_journal; long ret; int block; + uid_t i_uid; + gid_t i_gid; inode = iget_locked(sb, ino); if (!inode) @@ -3645,12 +3647,14 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) goto bad_inode; raw_inode = ext4_raw_inode(&iloc); inode->i_mode = le16_to_cpu(raw_inode->i_mode); - inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); - inode->i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); + i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); + i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); if (!(test_opt(inode->i_sb, NO_UID32))) { - inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; - inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; + i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; + i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; } + i_uid_write(inode, i_uid); + i_gid_write(inode, i_gid); set_nlink(inode, le16_to_cpu(raw_inode->i_links_count)); ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */ @@ -3870,6 +3874,8 @@ static int ext4_do_update_inode(handle_t *handle, struct ext4_inode_info *ei = EXT4_I(inode); struct buffer_head *bh = iloc->bh; int err = 0, rc, block; + uid_t i_uid; + gid_t i_gid; /* For fields not not tracking in the in-memory inode, * initialise them to zero for new inodes. */ @@ -3878,27 +3884,27 @@ static int ext4_do_update_inode(handle_t *handle, ext4_get_inode_flags(ei); raw_inode->i_mode = cpu_to_le16(inode->i_mode); + i_uid = i_uid_read(inode); + i_gid = i_gid_read(inode); if (!(test_opt(inode->i_sb, NO_UID32))) { - raw_inode->i_uid_low = cpu_to_le16(low_16_bits(inode->i_uid)); - raw_inode->i_gid_low = cpu_to_le16(low_16_bits(inode->i_gid)); + raw_inode->i_uid_low = cpu_to_le16(low_16_bits(i_uid)); + raw_inode->i_gid_low = cpu_to_le16(low_16_bits(i_gid)); /* * Fix up interoperability with old kernels. Otherwise, old inodes get * re-used with the upper 16 bits of the uid/gid intact */ if (!ei->i_dtime) { raw_inode->i_uid_high = - cpu_to_le16(high_16_bits(inode->i_uid)); + cpu_to_le16(high_16_bits(i_uid)); raw_inode->i_gid_high = - cpu_to_le16(high_16_bits(inode->i_gid)); + cpu_to_le16(high_16_bits(i_gid)); } else { raw_inode->i_uid_high = 0; raw_inode->i_gid_high = 0; } } else { - raw_inode->i_uid_low = - cpu_to_le16(fs_high2lowuid(inode->i_uid)); - raw_inode->i_gid_low = - cpu_to_le16(fs_high2lowgid(inode->i_gid)); + raw_inode->i_uid_low = cpu_to_le16(fs_high2lowuid(i_uid)); + raw_inode->i_gid_low = cpu_to_le16(fs_high2lowgid(i_gid)); raw_inode->i_uid_high = 0; raw_inode->i_gid_high = 0; } @@ -4084,8 +4090,8 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) if (is_quota_modification(inode, attr)) dquot_initialize(inode); - if ((ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) || - (ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid)) { + if ((ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) || + (ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) { handle_t *handle; /* (user+group)*(old+new) structure, inode write (sb, diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index f39f80f8f2c5..f1bb32ec0169 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -466,8 +466,8 @@ int ext4_ext_migrate(struct inode *inode) } goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) * EXT4_INODES_PER_GROUP(inode->i_sb)) + 1; - owner[0] = inode->i_uid; - owner[1] = inode->i_gid; + owner[0] = i_uid_read(inode); + owner[1] = i_gid_read(inode); tmp_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode, S_IFREG, NULL, goal, owner); if (IS_ERR(tmp_inode)) { diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ceebaf853beb..9d8eba0de27d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1448,6 +1448,8 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, { struct ext4_sb_info *sbi = EXT4_SB(sb); const struct mount_opts *m; + kuid_t uid; + kgid_t gid; int arg = 0; if (args->from && match_int(args, &arg)) @@ -1464,10 +1466,20 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, "Ignoring removed %s option", opt); return 1; case Opt_resuid: - sbi->s_resuid = arg; + uid = make_kuid(current_user_ns(), arg); + if (!uid_valid(uid)) { + ext4_msg(sb, KERN_ERR, "Invalid uid value %d", arg); + return -1; + } + sbi->s_resuid = uid; return 1; case Opt_resgid: - sbi->s_resgid = arg; + gid = make_kgid(current_user_ns(), arg); + if (!gid_valid(gid)) { + ext4_msg(sb, KERN_ERR, "Invalid gid value %d", arg); + return -1; + } + sbi->s_resgid = gid; return 1; case Opt_abort: sbi->s_mount_flags |= EXT4_MF_FS_ABORTED; @@ -1732,12 +1744,14 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, SEQ_OPTS_PRINT("%s", token2str(m->token)); } - if (nodefs || sbi->s_resuid != EXT4_DEF_RESUID || + if (nodefs || !uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT4_DEF_RESUID)) || le16_to_cpu(es->s_def_resuid) != EXT4_DEF_RESUID) - SEQ_OPTS_PRINT("resuid=%u", sbi->s_resuid); - if (nodefs || sbi->s_resgid != EXT4_DEF_RESGID || + SEQ_OPTS_PRINT("resuid=%u", + from_kuid_munged(&init_user_ns, sbi->s_resuid)); + if (nodefs || !gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT4_DEF_RESGID)) || le16_to_cpu(es->s_def_resgid) != EXT4_DEF_RESGID) - SEQ_OPTS_PRINT("resgid=%u", sbi->s_resgid); + SEQ_OPTS_PRINT("resgid=%u", + from_kgid_munged(&init_user_ns, sbi->s_resgid)); def_errors = nodefs ? -1 : le16_to_cpu(es->s_errors); if (test_opt(sb, ERRORS_RO) && def_errors != EXT4_ERRORS_RO) SEQ_OPTS_PUTS("errors=remount-ro"); @@ -2996,8 +3010,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } sb->s_fs_info = sbi; sbi->s_mount_opt = 0; - sbi->s_resuid = EXT4_DEF_RESUID; - sbi->s_resgid = EXT4_DEF_RESGID; + sbi->s_resuid = make_kuid(&init_user_ns, EXT4_DEF_RESUID); + sbi->s_resgid = make_kgid(&init_user_ns, EXT4_DEF_RESGID); sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS; sbi->s_sb_block = sb_block; if (sb->s_bdev->bd_part) @@ -3076,8 +3090,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (def_mount_opts & EXT4_DEFM_DISCARD) set_opt(sb, DISCARD); - sbi->s_resuid = le16_to_cpu(es->s_def_resuid); - sbi->s_resgid = le16_to_cpu(es->s_def_resgid); + sbi->s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid)); + sbi->s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid)); sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ; sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME; sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME; @@ -4229,8 +4243,8 @@ static int ext4_unfreeze(struct super_block *sb) struct ext4_mount_options { unsigned long s_mount_opt; unsigned long s_mount_opt2; - uid_t s_resuid; - gid_t s_resgid; + kuid_t s_resuid; + kgid_t s_resgid; unsigned long s_commit_interval; u32 s_min_batch_time, s_max_batch_time; #ifdef CONFIG_QUOTA diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 319538bf17d2..69d8a69ea831 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -36,8 +36,8 @@ TRACE_EVENT(ext4_free_inode, __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->mode = inode->i_mode; - __entry->uid = inode->i_uid; - __entry->gid = inode->i_gid; + __entry->uid = i_uid_read(inode); + __entry->gid = i_gid_read(inode); __entry->blocks = inode->i_blocks; ), diff --git a/init/Kconfig b/init/Kconfig index 669f991bb133..0e7d30ba8ebb 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -929,7 +929,6 @@ config UIDGID_CONVERTED depends on ECRYPT_FS = n depends on EFS_FS = n depends on EXOFS_FS = n - depends on EXT4_FS = n depends on FAT_FS = n depends on FUSE_FS = n depends on GFS2_FS = n -- cgit v1.2.3 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 +- include/linux/pid_namespace.h | 2 +- include/linux/proc_fs.h | 4 ++-- init/Kconfig | 1 - 7 files changed, 22 insertions(+), 17 deletions(-) diff --git a/fs/proc/array.c b/fs/proc/array.c index 36a0a9192ece..dc4c5a7b9ece 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 2ee514c7e64a..c47904994b78 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 205c92280838..554ecc54799f 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 46a15d8a29ca..df4e4561dbbf 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)) diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index b067bd8c49d0..00474b047145 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -31,7 +31,7 @@ struct pid_namespace { #ifdef CONFIG_BSD_PROCESS_ACCT struct bsd_acct_struct *bacct; #endif - gid_t pid_gid; + kgid_t pid_gid; int hide_pid; int reboot; /* group exit code if this pidns was rebooted */ }; diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 85c507306239..3fd2e871ff1b 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -52,8 +52,8 @@ struct proc_dir_entry { unsigned int low_ino; umode_t mode; nlink_t nlink; - uid_t uid; - gid_t gid; + kuid_t uid; + kgid_t gid; loff_t size; const struct inode_operations *proc_iops; /* diff --git a/init/Kconfig b/init/Kconfig index 0e7d30ba8ebb..7bebe91367c5 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -948,7 +948,6 @@ config UIDGID_CONVERTED depends on NTFS_FS = n depends on OCFS2_FS = n depends on OMFS_FS = n - depends on PROC_FS = n depends on PROC_SYSCTL = n depends on QNX4FS_FS = n depends on QNX6FS_FS = n -- cgit v1.2.3 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 ++-- init/Kconfig | 1 - 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 21d836f40292..3476bca8f7af 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; diff --git a/init/Kconfig b/init/Kconfig index 7bebe91367c5..be587651b952 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -948,7 +948,6 @@ config UIDGID_CONVERTED depends on NTFS_FS = n depends on OCFS2_FS = n depends on OMFS_FS = n - depends on PROC_SYSCTL = n depends on QNX4FS_FS = n depends on QNX6FS_FS = n depends on REISERFS_FS = n -- cgit v1.2.3 From ab27b91b9f1937ddb9e0eb0d0892728f852b48cf Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 7 Feb 2012 15:46:26 -0800 Subject: userns: Convert sysfs to use kgid/kuid where appropriate Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- fs/sysfs/inode.c | 4 ++-- init/Kconfig | 1 - 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c index feb2d69396cf..907c2b3af758 100644 --- a/fs/sysfs/inode.c +++ b/fs/sysfs/inode.c @@ -62,8 +62,8 @@ static struct sysfs_inode_attrs *sysfs_init_inode_attrs(struct sysfs_dirent *sd) /* assign default attributes */ iattrs->ia_mode = sd->s_mode; - iattrs->ia_uid = 0; - iattrs->ia_gid = 0; + iattrs->ia_uid = GLOBAL_ROOT_UID; + iattrs->ia_gid = GLOBAL_ROOT_GID; iattrs->ia_atime = iattrs->ia_mtime = iattrs->ia_ctime = CURRENT_TIME; return attrs; diff --git a/init/Kconfig b/init/Kconfig index be587651b952..908e61cd0b0e 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -952,7 +952,6 @@ config UIDGID_CONVERTED depends on QNX6FS_FS = n depends on REISERFS_FS = n depends on SQUASHFS = n - depends on SYSFS = n depends on SYSV_FS = n depends on TMPFS = n depends on UBIFS_FS = n -- cgit v1.2.3 From 8751e03958f2adbfba6a0f186f4c5797c950c22a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 7 Feb 2012 16:46:12 -0800 Subject: userns: Convert tmpfs to use kuid and kgid where appropriate Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- include/linux/shmem_fs.h | 4 ++-- init/Kconfig | 1 - mm/shmem.c | 22 ++++++++++++++++------ 3 files changed, 18 insertions(+), 9 deletions(-) diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 79ab2555b3b0..bef2cf00b3be 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -28,8 +28,8 @@ struct shmem_sb_info { unsigned long max_inodes; /* How many inodes are allowed */ unsigned long free_inodes; /* How many are left for allocation */ spinlock_t stat_lock; /* Serialize shmem_sb_info changes */ - uid_t uid; /* Mount uid for root directory */ - gid_t gid; /* Mount gid for root directory */ + kuid_t uid; /* Mount uid for root directory */ + kgid_t gid; /* Mount gid for root directory */ umode_t mode; /* Mount mode for root directory */ struct mempolicy *mpol; /* default memory policy for mappings */ }; diff --git a/init/Kconfig b/init/Kconfig index 908e61cd0b0e..7a5ccb2e9e0f 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -953,7 +953,6 @@ config UIDGID_CONVERTED depends on REISERFS_FS = n depends on SQUASHFS = n depends on SYSV_FS = n - depends on TMPFS = n depends on UBIFS_FS = n depends on UDF_FS = n depends on UFS_FS = n diff --git a/mm/shmem.c b/mm/shmem.c index f99ff3e50bd6..d7b433a1ef5e 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2075,6 +2075,8 @@ static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo, bool remount) { char *this_char, *value, *rest; + uid_t uid; + gid_t gid; while (options != NULL) { this_char = options; @@ -2134,15 +2136,21 @@ static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo, } else if (!strcmp(this_char,"uid")) { if (remount) continue; - sbinfo->uid = simple_strtoul(value, &rest, 0); + uid = simple_strtoul(value, &rest, 0); if (*rest) goto bad_val; + sbinfo->uid = make_kuid(current_user_ns(), uid); + if (!uid_valid(sbinfo->uid)) + goto bad_val; } else if (!strcmp(this_char,"gid")) { if (remount) continue; - sbinfo->gid = simple_strtoul(value, &rest, 0); + gid = simple_strtoul(value, &rest, 0); if (*rest) goto bad_val; + sbinfo->gid = make_kgid(current_user_ns(), gid); + if (!gid_valid(sbinfo->gid)) + goto bad_val; } else if (!strcmp(this_char,"mpol")) { if (mpol_parse_str(value, &sbinfo->mpol, 1)) goto bad_val; @@ -2210,10 +2218,12 @@ static int shmem_show_options(struct seq_file *seq, struct dentry *root) seq_printf(seq, ",nr_inodes=%lu", sbinfo->max_inodes); if (sbinfo->mode != (S_IRWXUGO | S_ISVTX)) seq_printf(seq, ",mode=%03ho", sbinfo->mode); - if (sbinfo->uid != 0) - seq_printf(seq, ",uid=%u", sbinfo->uid); - if (sbinfo->gid != 0) - seq_printf(seq, ",gid=%u", sbinfo->gid); + if (!uid_eq(sbinfo->uid, GLOBAL_ROOT_UID)) + seq_printf(seq, ",uid=%u", + from_kuid_munged(&init_user_ns, sbinfo->uid)); + if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID)) + seq_printf(seq, ",gid=%u", + from_kgid_munged(&init_user_ns, sbinfo->gid)); shmem_show_mpol(seq, sbinfo->mpol); return 0; } -- cgit v1.2.3 From 14a590c3f987977d7b09ec926481ee0238c08eee Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 12 Mar 2012 15:44:39 -0700 Subject: userns: Convert cgroup permission checks to use uid_eq Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- init/Kconfig | 1 - kernel/cgroup.c | 6 +++--- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/init/Kconfig b/init/Kconfig index 7a5ccb2e9e0f..d24cc75caf65 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -865,7 +865,6 @@ config UIDGID_CONVERTED # List of kernel pieces that need user namespace work # Features - depends on CGROUPS = n depends on MIGRATION = n depends on NUMA = n depends on SYSVIPC = n diff --git a/kernel/cgroup.c b/kernel/cgroup.c index ed64ccac67c9..c8329b0c2576 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2160,9 +2160,9 @@ retry_find_task: * only need to check permissions on one of them. */ tcred = __task_cred(tsk); - if (cred->euid && - cred->euid != tcred->uid && - cred->euid != tcred->suid) { + if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && + !uid_eq(cred->euid, tcred->uid) && + !uid_eq(cred->euid, tcred->suid)) { rcu_read_unlock(); ret = -EACCES; goto out_unlock_cgroup; -- cgit v1.2.3 From b38a86eb196d9402299919456fe3f28e490c76fa Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 12 Mar 2012 15:48:24 -0700 Subject: userns: Convert the move_pages, and migrate_pages permission checks to use uid_eq Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- init/Kconfig | 2 -- mm/mempolicy.c | 4 ++-- mm/migrate.c | 4 ++-- 3 files changed, 4 insertions(+), 6 deletions(-) diff --git a/init/Kconfig b/init/Kconfig index d24cc75caf65..b5dff4d1e1de 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -865,8 +865,6 @@ config UIDGID_CONVERTED # List of kernel pieces that need user namespace work # Features - depends on MIGRATION = n - depends on NUMA = n depends on SYSVIPC = n depends on IMA = n depends on EVM = n diff --git a/mm/mempolicy.c b/mm/mempolicy.c index cfb6c8678754..7b44fc8ec99c 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1334,8 +1334,8 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, * userid as the target process. */ tcred = __task_cred(task); - if (cred->euid != tcred->suid && cred->euid != tcred->uid && - cred->uid != tcred->suid && cred->uid != tcred->uid && + if (!uid_eq(cred->euid, tcred->suid) && !uid_eq(cred->euid, tcred->uid) && + !uid_eq(cred->uid, tcred->suid) && !uid_eq(cred->uid, tcred->uid) && !capable(CAP_SYS_NICE)) { rcu_read_unlock(); err = -EPERM; diff --git a/mm/migrate.c b/mm/migrate.c index 51c08a0c6f68..1cf5252c3b99 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1371,8 +1371,8 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages, * userid as the target process. */ tcred = __task_cred(task); - if (cred->euid != tcred->suid && cred->euid != tcred->uid && - cred->uid != tcred->suid && cred->uid != tcred->uid && + if (!uid_eq(cred->euid, tcred->suid) && !uid_eq(cred->euid, tcred->uid) && + !uid_eq(cred->uid, tcred->suid) && !uid_eq(cred->uid, tcred->uid) && !capable(CAP_SYS_NICE)) { rcu_read_unlock(); err = -EPERM; -- cgit v1.2.3 From 8ca937a668d4be0b0c89c4fc9a912a5885ac06fe Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Thu, 17 May 2012 23:31:39 +0200 Subject: cred: use correct cred accessor with regards to rcu read lock Commit "userns: Convert setting and getting uid and gid system calls to use kuid and kgid has modified the accessors in wait_task_continued() and wait_task_stopped() to use __task_cred() instead of task_uid(). __task_cred() assumes that we're inside a rcu read lock, which is untrue for these two functions. Modify it to use task_uid() instead. Signed-off-by: Sasha Levin Signed-off-by: Eric W. Biederman --- kernel/exit.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/exit.c b/kernel/exit.c index 789e3c5777f7..910a0716e17a 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1427,7 +1427,7 @@ static int wait_task_stopped(struct wait_opts *wo, if (!unlikely(wo->wo_flags & WNOWAIT)) *p_code = 0; - uid = from_kuid_munged(current_user_ns(), __task_cred(p)->uid); + uid = from_kuid_munged(current_user_ns(), task_uid(p)); unlock_sig: spin_unlock_irq(&p->sighand->siglock); if (!exit_code) @@ -1500,7 +1500,7 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p) } if (!unlikely(wo->wo_flags & WNOWAIT)) p->signal->flags &= ~SIGNAL_STOP_CONTINUED; - uid = from_kuid_munged(current_user_ns(), __task_cred(p)->uid); + uid = from_kuid_munged(current_user_ns(), task_uid(p)); spin_unlock_irq(&p->sighand->siglock); pid = task_pid_vnr(p); -- cgit v1.2.3 From 4b06a81f1daee668fbd6de85557bfb36dd36078f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 19 May 2012 15:44:06 -0600 Subject: userns: Silence silly gcc warning. On 32bit builds gcc says: kernel/user.c:30:4: warning: this decimal constant is unsigned only in ISO C90 [enabled by default] kernel/user.c:38:4: warning: this decimal constant is unsigned only in ISO C90 [enabled by default] Silence gcc by changing the constant 4294967295 to 4294967295U. Signed-off-by: Eric W. Biederman --- kernel/user.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/user.c b/kernel/user.c index f9e420e36699..b815fefbe76f 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -27,7 +27,7 @@ struct user_namespace init_user_ns = { .extent[0] = { .first = 0, .lower_first = 0, - .count = 4294967295, + .count = 4294967295U, }, }, .gid_map = { @@ -35,7 +35,7 @@ struct user_namespace init_user_ns = { .extent[0] = { .first = 0, .lower_first = 0, - .count = 4294967295, + .count = 4294967295U, }, }, .kref = { -- cgit v1.2.3