From 4baf6e33251b37f111e21289f8ee71fe4cce236e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 1 Apr 2012 12:09:55 -0700 Subject: cgroup: convert all non-memcg controllers to the new cftype interface Convert debug, freezer, cpuset, cpu_cgroup, cpuacct, net_prio, blkio, net_cls and device controllers to use the new cftype based interface. Termination entry is added to cftype arrays and populate callbacks are replaced with cgroup_subsys->base_cftypes initializations. This is functionally identical transformation. There shouldn't be any visible behavior change. memcg is rather special and will be converted separately. Signed-off-by: Tejun Heo Acked-by: Li Zefan Cc: Paul Menage Cc: Ingo Molnar Cc: Peter Zijlstra Cc: "David S. Miller" Cc: Vivek Goyal --- security/device_cgroup.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) (limited to 'security') diff --git a/security/device_cgroup.c b/security/device_cgroup.c index c43a3323feea..442204cc22d9 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -447,22 +447,16 @@ static struct cftype dev_cgroup_files[] = { .read_seq_string = devcgroup_seq_read, .private = DEVCG_LIST, }, + { } /* terminate */ }; -static int devcgroup_populate(struct cgroup_subsys *ss, - struct cgroup *cgroup) -{ - return cgroup_add_files(cgroup, ss, dev_cgroup_files, - ARRAY_SIZE(dev_cgroup_files)); -} - struct cgroup_subsys devices_subsys = { .name = "devices", .can_attach = devcgroup_can_attach, .create = devcgroup_create, .destroy = devcgroup_destroy, - .populate = devcgroup_populate, .subsys_id = devices_subsys_id, + .base_cftypes = dev_cgroup_files, }; int __devcgroup_inode_permission(struct inode *inode, int mask) -- cgit v1.2.3-58-ga151 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(-) (limited to 'security') 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 v1.2.3-58-ga151 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(-) (limited to 'security') 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 v1.2.3-58-ga151 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(-) (limited to 'security') 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 v1.2.3-58-ga151 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(-) (limited to 'security') 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 v1.2.3-58-ga151 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(-) (limited to 'security') 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 v1.2.3-58-ga151 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(-) (limited to 'security') 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 v1.2.3-58-ga151 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(-) (limited to 'security') 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 v1.2.3-58-ga151 From d16cf20e2f2f13411eece7f7fb72c17d141c4a84 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 8 May 2012 19:45:28 +0200 Subject: netfilter: remove ip_queue support This patch removes ip_queue support which was marked as obsolete years ago. The nfnetlink_queue modules provides more advanced user-space packet queueing mechanism. This patch also removes capability code included in SELinux that refers to ip_queue. Otherwise, we break compilation. Several warning has been sent regarding this to the mailing list in the past month without anyone rising the hand to stop this with some strong argument. Signed-off-by: Pablo Neira Ayuso --- Documentation/ABI/removed/ip_queue | 9 + include/linux/netfilter_ipv4/Kbuild | 1 - include/linux/netfilter_ipv4/ip_queue.h | 72 ---- include/linux/netlink.h | 2 +- net/ipv4/netfilter/Makefile | 3 - net/ipv4/netfilter/ip_queue.c | 639 ------------------------------- net/ipv6/netfilter/Kconfig | 22 -- net/ipv6/netfilter/Makefile | 1 - net/ipv6/netfilter/ip6_queue.c | 641 -------------------------------- security/selinux/nlmsgtab.c | 13 - 10 files changed, 10 insertions(+), 1393 deletions(-) create mode 100644 Documentation/ABI/removed/ip_queue delete mode 100644 include/linux/netfilter_ipv4/ip_queue.h delete mode 100644 net/ipv4/netfilter/ip_queue.c delete mode 100644 net/ipv6/netfilter/ip6_queue.c (limited to 'security') diff --git a/Documentation/ABI/removed/ip_queue b/Documentation/ABI/removed/ip_queue new file mode 100644 index 000000000000..3243613bc2d2 --- /dev/null +++ b/Documentation/ABI/removed/ip_queue @@ -0,0 +1,9 @@ +What: ip_queue +Date: finally removed in kernel v3.5.0 +Contact: Pablo Neira Ayuso +Description: + ip_queue has been replaced by nfnetlink_queue which provides + more advanced queueing mechanism to user-space. The ip_queue + module was already announced to become obsolete years ago. + +Users: diff --git a/include/linux/netfilter_ipv4/Kbuild b/include/linux/netfilter_ipv4/Kbuild index 31f8bec95650..c61b8fb1a9ef 100644 --- a/include/linux/netfilter_ipv4/Kbuild +++ b/include/linux/netfilter_ipv4/Kbuild @@ -1,4 +1,3 @@ -header-y += ip_queue.h header-y += ip_tables.h header-y += ipt_CLUSTERIP.h header-y += ipt_ECN.h diff --git a/include/linux/netfilter_ipv4/ip_queue.h b/include/linux/netfilter_ipv4/ip_queue.h deleted file mode 100644 index a03507f465f8..000000000000 --- a/include/linux/netfilter_ipv4/ip_queue.h +++ /dev/null @@ -1,72 +0,0 @@ -/* - * This is a module which is used for queueing IPv4 packets and - * communicating with userspace via netlink. - * - * (C) 2000 James Morris, this code is GPL. - */ -#ifndef _IP_QUEUE_H -#define _IP_QUEUE_H - -#ifdef __KERNEL__ -#ifdef DEBUG_IPQ -#define QDEBUG(x...) printk(KERN_DEBUG ## x) -#else -#define QDEBUG(x...) -#endif /* DEBUG_IPQ */ -#else -#include -#endif /* ! __KERNEL__ */ - -/* Messages sent from kernel */ -typedef struct ipq_packet_msg { - unsigned long packet_id; /* ID of queued packet */ - unsigned long mark; /* Netfilter mark value */ - long timestamp_sec; /* Packet arrival time (seconds) */ - long timestamp_usec; /* Packet arrvial time (+useconds) */ - unsigned int hook; /* Netfilter hook we rode in on */ - char indev_name[IFNAMSIZ]; /* Name of incoming interface */ - char outdev_name[IFNAMSIZ]; /* Name of outgoing interface */ - __be16 hw_protocol; /* Hardware protocol (network order) */ - unsigned short hw_type; /* Hardware type */ - unsigned char hw_addrlen; /* Hardware address length */ - unsigned char hw_addr[8]; /* Hardware address */ - size_t data_len; /* Length of packet data */ - unsigned char payload[0]; /* Optional packet data */ -} ipq_packet_msg_t; - -/* Messages sent from userspace */ -typedef struct ipq_mode_msg { - unsigned char value; /* Requested mode */ - size_t range; /* Optional range of packet requested */ -} ipq_mode_msg_t; - -typedef struct ipq_verdict_msg { - unsigned int value; /* Verdict to hand to netfilter */ - unsigned long id; /* Packet ID for this verdict */ - size_t data_len; /* Length of replacement data */ - unsigned char payload[0]; /* Optional replacement packet */ -} ipq_verdict_msg_t; - -typedef struct ipq_peer_msg { - union { - ipq_verdict_msg_t verdict; - ipq_mode_msg_t mode; - } msg; -} ipq_peer_msg_t; - -/* Packet delivery modes */ -enum { - IPQ_COPY_NONE, /* Initial mode, packets are dropped */ - IPQ_COPY_META, /* Copy metadata */ - IPQ_COPY_PACKET /* Copy metadata + packet (range) */ -}; -#define IPQ_COPY_MAX IPQ_COPY_PACKET - -/* Types of messages */ -#define IPQM_BASE 0x10 /* standard netlink messages below this */ -#define IPQM_MODE (IPQM_BASE + 1) /* Mode request from peer */ -#define IPQM_VERDICT (IPQM_BASE + 2) /* Verdict from peer */ -#define IPQM_PACKET (IPQM_BASE + 3) /* Packet from kernel */ -#define IPQM_MAX (IPQM_BASE + 4) - -#endif /*_IP_QUEUE_H*/ diff --git a/include/linux/netlink.h b/include/linux/netlink.h index a2092f582a78..0f628ffa420c 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -7,7 +7,7 @@ #define NETLINK_ROUTE 0 /* Routing/device hook */ #define NETLINK_UNUSED 1 /* Unused number */ #define NETLINK_USERSOCK 2 /* Reserved for user mode socket protocols */ -#define NETLINK_FIREWALL 3 /* Firewalling hook */ +#define NETLINK_FIREWALL 3 /* Unused number, formerly ip_queue */ #define NETLINK_SOCK_DIAG 4 /* socket monitoring */ #define NETLINK_NFLOG 5 /* netfilter/iptables ULOG */ #define NETLINK_XFRM 6 /* ipsec */ diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 240b68469a7a..c20674dc9452 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -66,6 +66,3 @@ obj-$(CONFIG_IP_NF_ARP_MANGLE) += arpt_mangle.o # just filtering instance of ARP tables for now obj-$(CONFIG_IP_NF_ARPFILTER) += arptable_filter.o - -obj-$(CONFIG_IP_NF_QUEUE) += ip_queue.o - diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c deleted file mode 100644 index 09775a1e1348..000000000000 --- a/net/ipv4/netfilter/ip_queue.c +++ /dev/null @@ -1,639 +0,0 @@ -/* - * This is a module which is used for queueing IPv4 packets and - * communicating with userspace via netlink. - * - * (C) 2000-2002 James Morris - * (C) 2003-2005 Netfilter Core Team - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define IPQ_QMAX_DEFAULT 1024 -#define IPQ_PROC_FS_NAME "ip_queue" -#define NET_IPQ_QMAX 2088 -#define NET_IPQ_QMAX_NAME "ip_queue_maxlen" - -typedef int (*ipq_cmpfn)(struct nf_queue_entry *, unsigned long); - -static unsigned char copy_mode __read_mostly = IPQ_COPY_NONE; -static unsigned int queue_maxlen __read_mostly = IPQ_QMAX_DEFAULT; -static DEFINE_SPINLOCK(queue_lock); -static int peer_pid __read_mostly; -static unsigned int copy_range __read_mostly; -static unsigned int queue_total; -static unsigned int queue_dropped = 0; -static unsigned int queue_user_dropped = 0; -static struct sock *ipqnl __read_mostly; -static LIST_HEAD(queue_list); -static DEFINE_MUTEX(ipqnl_mutex); - -static inline void -__ipq_enqueue_entry(struct nf_queue_entry *entry) -{ - list_add_tail(&entry->list, &queue_list); - queue_total++; -} - -static inline int -__ipq_set_mode(unsigned char mode, unsigned int range) -{ - int status = 0; - - switch(mode) { - case IPQ_COPY_NONE: - case IPQ_COPY_META: - copy_mode = mode; - copy_range = 0; - break; - - case IPQ_COPY_PACKET: - if (range > 0xFFFF) - range = 0xFFFF; - copy_range = range; - copy_mode = mode; - break; - - default: - status = -EINVAL; - - } - return status; -} - -static void __ipq_flush(ipq_cmpfn cmpfn, unsigned long data); - -static inline void -__ipq_reset(void) -{ - peer_pid = 0; - net_disable_timestamp(); - __ipq_set_mode(IPQ_COPY_NONE, 0); - __ipq_flush(NULL, 0); -} - -static struct nf_queue_entry * -ipq_find_dequeue_entry(unsigned long id) -{ - struct nf_queue_entry *entry = NULL, *i; - - spin_lock_bh(&queue_lock); - - list_for_each_entry(i, &queue_list, list) { - if ((unsigned long)i == id) { - entry = i; - break; - } - } - - if (entry) { - list_del(&entry->list); - queue_total--; - } - - spin_unlock_bh(&queue_lock); - return entry; -} - -static void -__ipq_flush(ipq_cmpfn cmpfn, unsigned long data) -{ - struct nf_queue_entry *entry, *next; - - list_for_each_entry_safe(entry, next, &queue_list, list) { - if (!cmpfn || cmpfn(entry, data)) { - list_del(&entry->list); - queue_total--; - nf_reinject(entry, NF_DROP); - } - } -} - -static void -ipq_flush(ipq_cmpfn cmpfn, unsigned long data) -{ - spin_lock_bh(&queue_lock); - __ipq_flush(cmpfn, data); - spin_unlock_bh(&queue_lock); -} - -static struct sk_buff * -ipq_build_packet_message(struct nf_queue_entry *entry, int *errp) -{ - sk_buff_data_t old_tail; - size_t size = 0; - size_t data_len = 0; - struct sk_buff *skb; - struct ipq_packet_msg *pmsg; - struct nlmsghdr *nlh; - struct timeval tv; - - switch (ACCESS_ONCE(copy_mode)) { - case IPQ_COPY_META: - case IPQ_COPY_NONE: - size = NLMSG_SPACE(sizeof(*pmsg)); - break; - - case IPQ_COPY_PACKET: - if (entry->skb->ip_summed == CHECKSUM_PARTIAL && - (*errp = skb_checksum_help(entry->skb))) - return NULL; - - data_len = ACCESS_ONCE(copy_range); - if (data_len == 0 || data_len > entry->skb->len) - data_len = entry->skb->len; - - size = NLMSG_SPACE(sizeof(*pmsg) + data_len); - break; - - default: - *errp = -EINVAL; - return NULL; - } - - skb = alloc_skb(size, GFP_ATOMIC); - if (!skb) - goto nlmsg_failure; - - old_tail = skb->tail; - nlh = NLMSG_PUT(skb, 0, 0, IPQM_PACKET, size - sizeof(*nlh)); - pmsg = NLMSG_DATA(nlh); - memset(pmsg, 0, sizeof(*pmsg)); - - pmsg->packet_id = (unsigned long )entry; - pmsg->data_len = data_len; - tv = ktime_to_timeval(entry->skb->tstamp); - pmsg->timestamp_sec = tv.tv_sec; - pmsg->timestamp_usec = tv.tv_usec; - pmsg->mark = entry->skb->mark; - pmsg->hook = entry->hook; - pmsg->hw_protocol = entry->skb->protocol; - - if (entry->indev) - strcpy(pmsg->indev_name, entry->indev->name); - else - pmsg->indev_name[0] = '\0'; - - if (entry->outdev) - strcpy(pmsg->outdev_name, entry->outdev->name); - else - pmsg->outdev_name[0] = '\0'; - - if (entry->indev && entry->skb->dev && - entry->skb->mac_header != entry->skb->network_header) { - pmsg->hw_type = entry->skb->dev->type; - pmsg->hw_addrlen = dev_parse_header(entry->skb, - pmsg->hw_addr); - } - - if (data_len) - if (skb_copy_bits(entry->skb, 0, pmsg->payload, data_len)) - BUG(); - - nlh->nlmsg_len = skb->tail - old_tail; - return skb; - -nlmsg_failure: - kfree_skb(skb); - *errp = -EINVAL; - printk(KERN_ERR "ip_queue: error creating packet message\n"); - return NULL; -} - -static int -ipq_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) -{ - int status = -EINVAL; - struct sk_buff *nskb; - - if (copy_mode == IPQ_COPY_NONE) - return -EAGAIN; - - nskb = ipq_build_packet_message(entry, &status); - if (nskb == NULL) - return status; - - spin_lock_bh(&queue_lock); - - if (!peer_pid) - goto err_out_free_nskb; - - if (queue_total >= queue_maxlen) { - queue_dropped++; - status = -ENOSPC; - if (net_ratelimit()) - printk (KERN_WARNING "ip_queue: full at %d entries, " - "dropping packets(s). Dropped: %d\n", queue_total, - queue_dropped); - goto err_out_free_nskb; - } - - /* netlink_unicast will either free the nskb or attach it to a socket */ - status = netlink_unicast(ipqnl, nskb, peer_pid, MSG_DONTWAIT); - if (status < 0) { - queue_user_dropped++; - goto err_out_unlock; - } - - __ipq_enqueue_entry(entry); - - spin_unlock_bh(&queue_lock); - return status; - -err_out_free_nskb: - kfree_skb(nskb); - -err_out_unlock: - spin_unlock_bh(&queue_lock); - return status; -} - -static int -ipq_mangle_ipv4(ipq_verdict_msg_t *v, struct nf_queue_entry *e) -{ - int diff; - struct iphdr *user_iph = (struct iphdr *)v->payload; - struct sk_buff *nskb; - - if (v->data_len < sizeof(*user_iph)) - return 0; - diff = v->data_len - e->skb->len; - if (diff < 0) { - if (pskb_trim(e->skb, v->data_len)) - return -ENOMEM; - } else if (diff > 0) { - if (v->data_len > 0xFFFF) - return -EINVAL; - if (diff > skb_tailroom(e->skb)) { - nskb = skb_copy_expand(e->skb, skb_headroom(e->skb), - diff, GFP_ATOMIC); - if (!nskb) { - printk(KERN_WARNING "ip_queue: error " - "in mangle, dropping packet\n"); - return -ENOMEM; - } - kfree_skb(e->skb); - e->skb = nskb; - } - skb_put(e->skb, diff); - } - if (!skb_make_writable(e->skb, v->data_len)) - return -ENOMEM; - skb_copy_to_linear_data(e->skb, v->payload, v->data_len); - e->skb->ip_summed = CHECKSUM_NONE; - - return 0; -} - -static int -ipq_set_verdict(struct ipq_verdict_msg *vmsg, unsigned int len) -{ - struct nf_queue_entry *entry; - - if (vmsg->value > NF_MAX_VERDICT || vmsg->value == NF_STOLEN) - return -EINVAL; - - entry = ipq_find_dequeue_entry(vmsg->id); - if (entry == NULL) - return -ENOENT; - else { - int verdict = vmsg->value; - - if (vmsg->data_len && vmsg->data_len == len) - if (ipq_mangle_ipv4(vmsg, entry) < 0) - verdict = NF_DROP; - - nf_reinject(entry, verdict); - return 0; - } -} - -static int -ipq_set_mode(unsigned char mode, unsigned int range) -{ - int status; - - spin_lock_bh(&queue_lock); - status = __ipq_set_mode(mode, range); - spin_unlock_bh(&queue_lock); - return status; -} - -static int -ipq_receive_peer(struct ipq_peer_msg *pmsg, - unsigned char type, unsigned int len) -{ - int status = 0; - - if (len < sizeof(*pmsg)) - return -EINVAL; - - switch (type) { - case IPQM_MODE: - status = ipq_set_mode(pmsg->msg.mode.value, - pmsg->msg.mode.range); - break; - - case IPQM_VERDICT: - status = ipq_set_verdict(&pmsg->msg.verdict, - len - sizeof(*pmsg)); - break; - default: - status = -EINVAL; - } - return status; -} - -static int -dev_cmp(struct nf_queue_entry *entry, unsigned long ifindex) -{ - if (entry->indev) - if (entry->indev->ifindex == ifindex) - return 1; - if (entry->outdev) - if (entry->outdev->ifindex == ifindex) - return 1; -#ifdef CONFIG_BRIDGE_NETFILTER - if (entry->skb->nf_bridge) { - if (entry->skb->nf_bridge->physindev && - entry->skb->nf_bridge->physindev->ifindex == ifindex) - return 1; - if (entry->skb->nf_bridge->physoutdev && - entry->skb->nf_bridge->physoutdev->ifindex == ifindex) - return 1; - } -#endif - return 0; -} - -static void -ipq_dev_drop(int ifindex) -{ - ipq_flush(dev_cmp, ifindex); -} - -#define RCV_SKB_FAIL(err) do { netlink_ack(skb, nlh, (err)); return; } while (0) - -static inline void -__ipq_rcv_skb(struct sk_buff *skb) -{ - int status, type, pid, flags; - unsigned int nlmsglen, skblen; - struct nlmsghdr *nlh; - bool enable_timestamp = false; - - skblen = skb->len; - if (skblen < sizeof(*nlh)) - return; - - nlh = nlmsg_hdr(skb); - nlmsglen = nlh->nlmsg_len; - if (nlmsglen < sizeof(*nlh) || skblen < nlmsglen) - return; - - pid = nlh->nlmsg_pid; - flags = nlh->nlmsg_flags; - - if(pid <= 0 || !(flags & NLM_F_REQUEST) || flags & NLM_F_MULTI) - RCV_SKB_FAIL(-EINVAL); - - if (flags & MSG_TRUNC) - RCV_SKB_FAIL(-ECOMM); - - type = nlh->nlmsg_type; - if (type < NLMSG_NOOP || type >= IPQM_MAX) - RCV_SKB_FAIL(-EINVAL); - - if (type <= IPQM_BASE) - return; - - if (!capable(CAP_NET_ADMIN)) - RCV_SKB_FAIL(-EPERM); - - spin_lock_bh(&queue_lock); - - if (peer_pid) { - if (peer_pid != pid) { - spin_unlock_bh(&queue_lock); - RCV_SKB_FAIL(-EBUSY); - } - } else { - enable_timestamp = true; - peer_pid = pid; - } - - spin_unlock_bh(&queue_lock); - if (enable_timestamp) - net_enable_timestamp(); - status = ipq_receive_peer(NLMSG_DATA(nlh), type, - nlmsglen - NLMSG_LENGTH(0)); - if (status < 0) - RCV_SKB_FAIL(status); - - if (flags & NLM_F_ACK) - netlink_ack(skb, nlh, 0); -} - -static void -ipq_rcv_skb(struct sk_buff *skb) -{ - mutex_lock(&ipqnl_mutex); - __ipq_rcv_skb(skb); - mutex_unlock(&ipqnl_mutex); -} - -static int -ipq_rcv_dev_event(struct notifier_block *this, - unsigned long event, void *ptr) -{ - struct net_device *dev = ptr; - - if (!net_eq(dev_net(dev), &init_net)) - return NOTIFY_DONE; - - /* Drop any packets associated with the downed device */ - if (event == NETDEV_DOWN) - ipq_dev_drop(dev->ifindex); - return NOTIFY_DONE; -} - -static struct notifier_block ipq_dev_notifier = { - .notifier_call = ipq_rcv_dev_event, -}; - -static int -ipq_rcv_nl_event(struct notifier_block *this, - unsigned long event, void *ptr) -{ - struct netlink_notify *n = ptr; - - if (event == NETLINK_URELEASE && n->protocol == NETLINK_FIREWALL) { - spin_lock_bh(&queue_lock); - if ((net_eq(n->net, &init_net)) && (n->pid == peer_pid)) - __ipq_reset(); - spin_unlock_bh(&queue_lock); - } - return NOTIFY_DONE; -} - -static struct notifier_block ipq_nl_notifier = { - .notifier_call = ipq_rcv_nl_event, -}; - -#ifdef CONFIG_SYSCTL -static struct ctl_table_header *ipq_sysctl_header; - -static ctl_table ipq_table[] = { - { - .procname = NET_IPQ_QMAX_NAME, - .data = &queue_maxlen, - .maxlen = sizeof(queue_maxlen), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { } -}; -#endif - -#ifdef CONFIG_PROC_FS -static int ip_queue_show(struct seq_file *m, void *v) -{ - spin_lock_bh(&queue_lock); - - seq_printf(m, - "Peer PID : %d\n" - "Copy mode : %hu\n" - "Copy range : %u\n" - "Queue length : %u\n" - "Queue max. length : %u\n" - "Queue dropped : %u\n" - "Netlink dropped : %u\n", - peer_pid, - copy_mode, - copy_range, - queue_total, - queue_maxlen, - queue_dropped, - queue_user_dropped); - - spin_unlock_bh(&queue_lock); - return 0; -} - -static int ip_queue_open(struct inode *inode, struct file *file) -{ - return single_open(file, ip_queue_show, NULL); -} - -static const struct file_operations ip_queue_proc_fops = { - .open = ip_queue_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .owner = THIS_MODULE, -}; -#endif - -static const struct nf_queue_handler nfqh = { - .name = "ip_queue", - .outfn = &ipq_enqueue_packet, -}; - -static int __init ip_queue_init(void) -{ - int status = -ENOMEM; - struct proc_dir_entry *proc __maybe_unused; - - netlink_register_notifier(&ipq_nl_notifier); - ipqnl = netlink_kernel_create(&init_net, NETLINK_FIREWALL, 0, - ipq_rcv_skb, NULL, THIS_MODULE); - if (ipqnl == NULL) { - printk(KERN_ERR "ip_queue: failed to create netlink socket\n"); - goto cleanup_netlink_notifier; - } - -#ifdef CONFIG_PROC_FS - proc = proc_create(IPQ_PROC_FS_NAME, 0, init_net.proc_net, - &ip_queue_proc_fops); - if (!proc) { - printk(KERN_ERR "ip_queue: failed to create proc entry\n"); - goto cleanup_ipqnl; - } -#endif - register_netdevice_notifier(&ipq_dev_notifier); -#ifdef CONFIG_SYSCTL - ipq_sysctl_header = register_net_sysctl(&init_net, "net/ipv4", ipq_table); -#endif - status = nf_register_queue_handler(NFPROTO_IPV4, &nfqh); - if (status < 0) { - printk(KERN_ERR "ip_queue: failed to register queue handler\n"); - goto cleanup_sysctl; - } - return status; - -cleanup_sysctl: -#ifdef CONFIG_SYSCTL - unregister_net_sysctl_table(ipq_sysctl_header); -#endif - unregister_netdevice_notifier(&ipq_dev_notifier); - proc_net_remove(&init_net, IPQ_PROC_FS_NAME); -cleanup_ipqnl: __maybe_unused - netlink_kernel_release(ipqnl); - mutex_lock(&ipqnl_mutex); - mutex_unlock(&ipqnl_mutex); - -cleanup_netlink_notifier: - netlink_unregister_notifier(&ipq_nl_notifier); - return status; -} - -static void __exit ip_queue_fini(void) -{ - nf_unregister_queue_handlers(&nfqh); - - ipq_flush(NULL, 0); - -#ifdef CONFIG_SYSCTL - unregister_net_sysctl_table(ipq_sysctl_header); -#endif - unregister_netdevice_notifier(&ipq_dev_notifier); - proc_net_remove(&init_net, IPQ_PROC_FS_NAME); - - netlink_kernel_release(ipqnl); - mutex_lock(&ipqnl_mutex); - mutex_unlock(&ipqnl_mutex); - - netlink_unregister_notifier(&ipq_nl_notifier); -} - -MODULE_DESCRIPTION("IPv4 packet queue handler"); -MODULE_AUTHOR("James Morris "); -MODULE_LICENSE("GPL"); -MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_FIREWALL); - -module_init(ip_queue_init); -module_exit(ip_queue_fini); diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index d33cddd16fbb..10135342799e 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -25,28 +25,6 @@ config NF_CONNTRACK_IPV6 To compile it as a module, choose M here. If unsure, say N. -config IP6_NF_QUEUE - tristate "IP6 Userspace queueing via NETLINK (OBSOLETE)" - depends on INET && IPV6 && NETFILTER - depends on NETFILTER_ADVANCED - ---help--- - - This option adds a queue handler to the kernel for IPv6 - packets which enables users to receive the filtered packets - with QUEUE target using libipq. - - This option enables the old IPv6-only "ip6_queue" implementation - which has been obsoleted by the new "nfnetlink_queue" code (see - CONFIG_NETFILTER_NETLINK_QUEUE). - - (C) Fernando Anton 2001 - IPv64 Project - Work based in IPv64 draft by Arturo Azcorra. - Universidad Carlos III de Madrid - Universidad Politecnica de Alcala de Henares - email: . - - To compile it as a module, choose M here. If unsure, say N. - config IP6_NF_IPTABLES tristate "IP6 tables support (required for filtering)" depends on INET && IPV6 diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index d4dfd0a21097..534d3f216f7b 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -6,7 +6,6 @@ obj-$(CONFIG_IP6_NF_IPTABLES) += ip6_tables.o obj-$(CONFIG_IP6_NF_FILTER) += ip6table_filter.o obj-$(CONFIG_IP6_NF_MANGLE) += ip6table_mangle.o -obj-$(CONFIG_IP6_NF_QUEUE) += ip6_queue.o obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o obj-$(CONFIG_IP6_NF_SECURITY) += ip6table_security.o diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c deleted file mode 100644 index 3ca9303b3a19..000000000000 --- a/net/ipv6/netfilter/ip6_queue.c +++ /dev/null @@ -1,641 +0,0 @@ -/* - * This is a module which is used for queueing IPv6 packets and - * communicating with userspace via netlink. - * - * (C) 2001 Fernando Anton, this code is GPL. - * IPv64 Project - Work based in IPv64 draft by Arturo Azcorra. - * Universidad Carlos III de Madrid - Leganes (Madrid) - Spain - * Universidad Politecnica de Alcala de Henares - Alcala de H. (Madrid) - Spain - * email: fanton@it.uc3m.es - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define IPQ_QMAX_DEFAULT 1024 -#define IPQ_PROC_FS_NAME "ip6_queue" -#define NET_IPQ_QMAX_NAME "ip6_queue_maxlen" - -typedef int (*ipq_cmpfn)(struct nf_queue_entry *, unsigned long); - -static unsigned char copy_mode __read_mostly = IPQ_COPY_NONE; -static unsigned int queue_maxlen __read_mostly = IPQ_QMAX_DEFAULT; -static DEFINE_SPINLOCK(queue_lock); -static int peer_pid __read_mostly; -static unsigned int copy_range __read_mostly; -static unsigned int queue_total; -static unsigned int queue_dropped = 0; -static unsigned int queue_user_dropped = 0; -static struct sock *ipqnl __read_mostly; -static LIST_HEAD(queue_list); -static DEFINE_MUTEX(ipqnl_mutex); - -static inline void -__ipq_enqueue_entry(struct nf_queue_entry *entry) -{ - list_add_tail(&entry->list, &queue_list); - queue_total++; -} - -static inline int -__ipq_set_mode(unsigned char mode, unsigned int range) -{ - int status = 0; - - switch(mode) { - case IPQ_COPY_NONE: - case IPQ_COPY_META: - copy_mode = mode; - copy_range = 0; - break; - - case IPQ_COPY_PACKET: - if (range > 0xFFFF) - range = 0xFFFF; - copy_range = range; - copy_mode = mode; - break; - - default: - status = -EINVAL; - - } - return status; -} - -static void __ipq_flush(ipq_cmpfn cmpfn, unsigned long data); - -static inline void -__ipq_reset(void) -{ - peer_pid = 0; - net_disable_timestamp(); - __ipq_set_mode(IPQ_COPY_NONE, 0); - __ipq_flush(NULL, 0); -} - -static struct nf_queue_entry * -ipq_find_dequeue_entry(unsigned long id) -{ - struct nf_queue_entry *entry = NULL, *i; - - spin_lock_bh(&queue_lock); - - list_for_each_entry(i, &queue_list, list) { - if ((unsigned long)i == id) { - entry = i; - break; - } - } - - if (entry) { - list_del(&entry->list); - queue_total--; - } - - spin_unlock_bh(&queue_lock); - return entry; -} - -static void -__ipq_flush(ipq_cmpfn cmpfn, unsigned long data) -{ - struct nf_queue_entry *entry, *next; - - list_for_each_entry_safe(entry, next, &queue_list, list) { - if (!cmpfn || cmpfn(entry, data)) { - list_del(&entry->list); - queue_total--; - nf_reinject(entry, NF_DROP); - } - } -} - -static void -ipq_flush(ipq_cmpfn cmpfn, unsigned long data) -{ - spin_lock_bh(&queue_lock); - __ipq_flush(cmpfn, data); - spin_unlock_bh(&queue_lock); -} - -static struct sk_buff * -ipq_build_packet_message(struct nf_queue_entry *entry, int *errp) -{ - sk_buff_data_t old_tail; - size_t size = 0; - size_t data_len = 0; - struct sk_buff *skb; - struct ipq_packet_msg *pmsg; - struct nlmsghdr *nlh; - struct timeval tv; - - switch (ACCESS_ONCE(copy_mode)) { - case IPQ_COPY_META: - case IPQ_COPY_NONE: - size = NLMSG_SPACE(sizeof(*pmsg)); - break; - - case IPQ_COPY_PACKET: - if (entry->skb->ip_summed == CHECKSUM_PARTIAL && - (*errp = skb_checksum_help(entry->skb))) - return NULL; - - data_len = ACCESS_ONCE(copy_range); - if (data_len == 0 || data_len > entry->skb->len) - data_len = entry->skb->len; - - size = NLMSG_SPACE(sizeof(*pmsg) + data_len); - break; - - default: - *errp = -EINVAL; - return NULL; - } - - skb = alloc_skb(size, GFP_ATOMIC); - if (!skb) - goto nlmsg_failure; - - old_tail = skb->tail; - nlh = NLMSG_PUT(skb, 0, 0, IPQM_PACKET, size - sizeof(*nlh)); - pmsg = NLMSG_DATA(nlh); - memset(pmsg, 0, sizeof(*pmsg)); - - pmsg->packet_id = (unsigned long )entry; - pmsg->data_len = data_len; - tv = ktime_to_timeval(entry->skb->tstamp); - pmsg->timestamp_sec = tv.tv_sec; - pmsg->timestamp_usec = tv.tv_usec; - pmsg->mark = entry->skb->mark; - pmsg->hook = entry->hook; - pmsg->hw_protocol = entry->skb->protocol; - - if (entry->indev) - strcpy(pmsg->indev_name, entry->indev->name); - else - pmsg->indev_name[0] = '\0'; - - if (entry->outdev) - strcpy(pmsg->outdev_name, entry->outdev->name); - else - pmsg->outdev_name[0] = '\0'; - - if (entry->indev && entry->skb->dev && - entry->skb->mac_header != entry->skb->network_header) { - pmsg->hw_type = entry->skb->dev->type; - pmsg->hw_addrlen = dev_parse_header(entry->skb, pmsg->hw_addr); - } - - if (data_len) - if (skb_copy_bits(entry->skb, 0, pmsg->payload, data_len)) - BUG(); - - nlh->nlmsg_len = skb->tail - old_tail; - return skb; - -nlmsg_failure: - kfree_skb(skb); - *errp = -EINVAL; - printk(KERN_ERR "ip6_queue: error creating packet message\n"); - return NULL; -} - -static int -ipq_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) -{ - int status = -EINVAL; - struct sk_buff *nskb; - - if (copy_mode == IPQ_COPY_NONE) - return -EAGAIN; - - nskb = ipq_build_packet_message(entry, &status); - if (nskb == NULL) - return status; - - spin_lock_bh(&queue_lock); - - if (!peer_pid) - goto err_out_free_nskb; - - if (queue_total >= queue_maxlen) { - queue_dropped++; - status = -ENOSPC; - if (net_ratelimit()) - printk (KERN_WARNING "ip6_queue: fill at %d entries, " - "dropping packet(s). Dropped: %d\n", queue_total, - queue_dropped); - goto err_out_free_nskb; - } - - /* netlink_unicast will either free the nskb or attach it to a socket */ - status = netlink_unicast(ipqnl, nskb, peer_pid, MSG_DONTWAIT); - if (status < 0) { - queue_user_dropped++; - goto err_out_unlock; - } - - __ipq_enqueue_entry(entry); - - spin_unlock_bh(&queue_lock); - return status; - -err_out_free_nskb: - kfree_skb(nskb); - -err_out_unlock: - spin_unlock_bh(&queue_lock); - return status; -} - -static int -ipq_mangle_ipv6(ipq_verdict_msg_t *v, struct nf_queue_entry *e) -{ - int diff; - struct ipv6hdr *user_iph = (struct ipv6hdr *)v->payload; - struct sk_buff *nskb; - - if (v->data_len < sizeof(*user_iph)) - return 0; - diff = v->data_len - e->skb->len; - if (diff < 0) { - if (pskb_trim(e->skb, v->data_len)) - return -ENOMEM; - } else if (diff > 0) { - if (v->data_len > 0xFFFF) - return -EINVAL; - if (diff > skb_tailroom(e->skb)) { - nskb = skb_copy_expand(e->skb, skb_headroom(e->skb), - diff, GFP_ATOMIC); - if (!nskb) { - printk(KERN_WARNING "ip6_queue: OOM " - "in mangle, dropping packet\n"); - return -ENOMEM; - } - kfree_skb(e->skb); - e->skb = nskb; - } - skb_put(e->skb, diff); - } - if (!skb_make_writable(e->skb, v->data_len)) - return -ENOMEM; - skb_copy_to_linear_data(e->skb, v->payload, v->data_len); - e->skb->ip_summed = CHECKSUM_NONE; - - return 0; -} - -static int -ipq_set_verdict(struct ipq_verdict_msg *vmsg, unsigned int len) -{ - struct nf_queue_entry *entry; - - if (vmsg->value > NF_MAX_VERDICT || vmsg->value == NF_STOLEN) - return -EINVAL; - - entry = ipq_find_dequeue_entry(vmsg->id); - if (entry == NULL) - return -ENOENT; - else { - int verdict = vmsg->value; - - if (vmsg->data_len && vmsg->data_len == len) - if (ipq_mangle_ipv6(vmsg, entry) < 0) - verdict = NF_DROP; - - nf_reinject(entry, verdict); - return 0; - } -} - -static int -ipq_set_mode(unsigned char mode, unsigned int range) -{ - int status; - - spin_lock_bh(&queue_lock); - status = __ipq_set_mode(mode, range); - spin_unlock_bh(&queue_lock); - return status; -} - -static int -ipq_receive_peer(struct ipq_peer_msg *pmsg, - unsigned char type, unsigned int len) -{ - int status = 0; - - if (len < sizeof(*pmsg)) - return -EINVAL; - - switch (type) { - case IPQM_MODE: - status = ipq_set_mode(pmsg->msg.mode.value, - pmsg->msg.mode.range); - break; - - case IPQM_VERDICT: - status = ipq_set_verdict(&pmsg->msg.verdict, - len - sizeof(*pmsg)); - break; - default: - status = -EINVAL; - } - return status; -} - -static int -dev_cmp(struct nf_queue_entry *entry, unsigned long ifindex) -{ - if (entry->indev) - if (entry->indev->ifindex == ifindex) - return 1; - - if (entry->outdev) - if (entry->outdev->ifindex == ifindex) - return 1; -#ifdef CONFIG_BRIDGE_NETFILTER - if (entry->skb->nf_bridge) { - if (entry->skb->nf_bridge->physindev && - entry->skb->nf_bridge->physindev->ifindex == ifindex) - return 1; - if (entry->skb->nf_bridge->physoutdev && - entry->skb->nf_bridge->physoutdev->ifindex == ifindex) - return 1; - } -#endif - return 0; -} - -static void -ipq_dev_drop(int ifindex) -{ - ipq_flush(dev_cmp, ifindex); -} - -#define RCV_SKB_FAIL(err) do { netlink_ack(skb, nlh, (err)); return; } while (0) - -static inline void -__ipq_rcv_skb(struct sk_buff *skb) -{ - int status, type, pid, flags; - unsigned int nlmsglen, skblen; - struct nlmsghdr *nlh; - bool enable_timestamp = false; - - skblen = skb->len; - if (skblen < sizeof(*nlh)) - return; - - nlh = nlmsg_hdr(skb); - nlmsglen = nlh->nlmsg_len; - if (nlmsglen < sizeof(*nlh) || skblen < nlmsglen) - return; - - pid = nlh->nlmsg_pid; - flags = nlh->nlmsg_flags; - - if(pid <= 0 || !(flags & NLM_F_REQUEST) || flags & NLM_F_MULTI) - RCV_SKB_FAIL(-EINVAL); - - if (flags & MSG_TRUNC) - RCV_SKB_FAIL(-ECOMM); - - type = nlh->nlmsg_type; - if (type < NLMSG_NOOP || type >= IPQM_MAX) - RCV_SKB_FAIL(-EINVAL); - - if (type <= IPQM_BASE) - return; - - if (!capable(CAP_NET_ADMIN)) - RCV_SKB_FAIL(-EPERM); - - spin_lock_bh(&queue_lock); - - if (peer_pid) { - if (peer_pid != pid) { - spin_unlock_bh(&queue_lock); - RCV_SKB_FAIL(-EBUSY); - } - } else { - enable_timestamp = true; - peer_pid = pid; - } - - spin_unlock_bh(&queue_lock); - if (enable_timestamp) - net_enable_timestamp(); - - status = ipq_receive_peer(NLMSG_DATA(nlh), type, - nlmsglen - NLMSG_LENGTH(0)); - if (status < 0) - RCV_SKB_FAIL(status); - - if (flags & NLM_F_ACK) - netlink_ack(skb, nlh, 0); -} - -static void -ipq_rcv_skb(struct sk_buff *skb) -{ - mutex_lock(&ipqnl_mutex); - __ipq_rcv_skb(skb); - mutex_unlock(&ipqnl_mutex); -} - -static int -ipq_rcv_dev_event(struct notifier_block *this, - unsigned long event, void *ptr) -{ - struct net_device *dev = ptr; - - if (!net_eq(dev_net(dev), &init_net)) - return NOTIFY_DONE; - - /* Drop any packets associated with the downed device */ - if (event == NETDEV_DOWN) - ipq_dev_drop(dev->ifindex); - return NOTIFY_DONE; -} - -static struct notifier_block ipq_dev_notifier = { - .notifier_call = ipq_rcv_dev_event, -}; - -static int -ipq_rcv_nl_event(struct notifier_block *this, - unsigned long event, void *ptr) -{ - struct netlink_notify *n = ptr; - - if (event == NETLINK_URELEASE && n->protocol == NETLINK_IP6_FW) { - spin_lock_bh(&queue_lock); - if ((net_eq(n->net, &init_net)) && (n->pid == peer_pid)) - __ipq_reset(); - spin_unlock_bh(&queue_lock); - } - return NOTIFY_DONE; -} - -static struct notifier_block ipq_nl_notifier = { - .notifier_call = ipq_rcv_nl_event, -}; - -#ifdef CONFIG_SYSCTL -static struct ctl_table_header *ipq_sysctl_header; - -static ctl_table ipq_table[] = { - { - .procname = NET_IPQ_QMAX_NAME, - .data = &queue_maxlen, - .maxlen = sizeof(queue_maxlen), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { } -}; -#endif - -#ifdef CONFIG_PROC_FS -static int ip6_queue_show(struct seq_file *m, void *v) -{ - spin_lock_bh(&queue_lock); - - seq_printf(m, - "Peer PID : %d\n" - "Copy mode : %hu\n" - "Copy range : %u\n" - "Queue length : %u\n" - "Queue max. length : %u\n" - "Queue dropped : %u\n" - "Netfilter dropped : %u\n", - peer_pid, - copy_mode, - copy_range, - queue_total, - queue_maxlen, - queue_dropped, - queue_user_dropped); - - spin_unlock_bh(&queue_lock); - return 0; -} - -static int ip6_queue_open(struct inode *inode, struct file *file) -{ - return single_open(file, ip6_queue_show, NULL); -} - -static const struct file_operations ip6_queue_proc_fops = { - .open = ip6_queue_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .owner = THIS_MODULE, -}; -#endif - -static const struct nf_queue_handler nfqh = { - .name = "ip6_queue", - .outfn = &ipq_enqueue_packet, -}; - -static int __init ip6_queue_init(void) -{ - int status = -ENOMEM; - struct proc_dir_entry *proc __maybe_unused; - - netlink_register_notifier(&ipq_nl_notifier); - ipqnl = netlink_kernel_create(&init_net, NETLINK_IP6_FW, 0, - ipq_rcv_skb, NULL, THIS_MODULE); - if (ipqnl == NULL) { - printk(KERN_ERR "ip6_queue: failed to create netlink socket\n"); - goto cleanup_netlink_notifier; - } - -#ifdef CONFIG_PROC_FS - proc = proc_create(IPQ_PROC_FS_NAME, 0, init_net.proc_net, - &ip6_queue_proc_fops); - if (!proc) { - printk(KERN_ERR "ip6_queue: failed to create proc entry\n"); - goto cleanup_ipqnl; - } -#endif - register_netdevice_notifier(&ipq_dev_notifier); -#ifdef CONFIG_SYSCTL - ipq_sysctl_header = register_net_sysctl(&init_net, "net/ipv6", ipq_table); -#endif - status = nf_register_queue_handler(NFPROTO_IPV6, &nfqh); - if (status < 0) { - printk(KERN_ERR "ip6_queue: failed to register queue handler\n"); - goto cleanup_sysctl; - } - return status; - -cleanup_sysctl: -#ifdef CONFIG_SYSCTL - unregister_net_sysctl_table(ipq_sysctl_header); -#endif - unregister_netdevice_notifier(&ipq_dev_notifier); - proc_net_remove(&init_net, IPQ_PROC_FS_NAME); - -cleanup_ipqnl: __maybe_unused - netlink_kernel_release(ipqnl); - mutex_lock(&ipqnl_mutex); - mutex_unlock(&ipqnl_mutex); - -cleanup_netlink_notifier: - netlink_unregister_notifier(&ipq_nl_notifier); - return status; -} - -static void __exit ip6_queue_fini(void) -{ - nf_unregister_queue_handlers(&nfqh); - - ipq_flush(NULL, 0); - -#ifdef CONFIG_SYSCTL - unregister_net_sysctl_table(ipq_sysctl_header); -#endif - unregister_netdevice_notifier(&ipq_dev_notifier); - proc_net_remove(&init_net, IPQ_PROC_FS_NAME); - - netlink_kernel_release(ipqnl); - mutex_lock(&ipqnl_mutex); - mutex_unlock(&ipqnl_mutex); - - netlink_unregister_notifier(&ipq_nl_notifier); -} - -MODULE_DESCRIPTION("IPv6 packet queue handler"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_IP6_FW); - -module_init(ip6_queue_init); -module_exit(ip6_queue_fini); diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c index 0920ea3bf599..d309e7f472d8 100644 --- a/security/selinux/nlmsgtab.c +++ b/security/selinux/nlmsgtab.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include @@ -70,12 +69,6 @@ static struct nlmsg_perm nlmsg_route_perms[] = { RTM_SETDCB, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, }; -static struct nlmsg_perm nlmsg_firewall_perms[] = -{ - { IPQM_MODE, NETLINK_FIREWALL_SOCKET__NLMSG_WRITE }, - { IPQM_VERDICT, NETLINK_FIREWALL_SOCKET__NLMSG_WRITE }, -}; - static struct nlmsg_perm nlmsg_tcpdiag_perms[] = { { TCPDIAG_GETSOCK, NETLINK_TCPDIAG_SOCKET__NLMSG_READ }, @@ -145,12 +138,6 @@ int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm) sizeof(nlmsg_route_perms)); break; - case SECCLASS_NETLINK_FIREWALL_SOCKET: - case SECCLASS_NETLINK_IP6FW_SOCKET: - err = nlmsg_perm(nlmsg_type, perm, nlmsg_firewall_perms, - sizeof(nlmsg_firewall_perms)); - break; - case SECCLASS_NETLINK_TCPDIAG_SOCKET: err = nlmsg_perm(nlmsg_type, perm, nlmsg_tcpdiag_perms, sizeof(nlmsg_tcpdiag_perms)); -- cgit v1.2.3-58-ga151 From 1227dd773d8d4e3983b4b751f9ffa0f41402fb7c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 24 Apr 2012 02:44:49 -0400 Subject: TIF_NOTIFY_RESUME is defined on all targets now Signed-off-by: Al Viro --- include/linux/tracehook.h | 2 -- security/keys/keyctl.c | 10 ---------- 2 files changed, 12 deletions(-) (limited to 'security') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 51bd91d911c3..8a2a3fc9bd05 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -153,7 +153,6 @@ static inline void tracehook_signal_handler(int sig, siginfo_t *info, ptrace_notify(SIGTRAP); } -#ifdef TIF_NOTIFY_RESUME /** * set_notify_resume - cause tracehook_notify_resume() to be called * @task: task that will call tracehook_notify_resume() @@ -185,6 +184,5 @@ static inline void set_notify_resume(struct task_struct *task) static inline void tracehook_notify_resume(struct pt_regs *regs) { } -#endif /* TIF_NOTIFY_RESUME */ #endif /* */ diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index ddb3e05bc5fc..534a634283a4 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -1454,7 +1454,6 @@ long keyctl_get_security(key_serial_t keyid, */ long keyctl_session_to_parent(void) { -#ifdef TIF_NOTIFY_RESUME struct task_struct *me, *parent; const struct cred *mycred, *pcred; struct cred *cred, *oldcred; @@ -1542,15 +1541,6 @@ not_permitted: error_keyring: key_ref_put(keyring_r); return ret; - -#else /* !TIF_NOTIFY_RESUME */ - /* - * To be removed when TIF_NOTIFY_RESUME has been implemented on - * m68k/xtensa - */ -#warning TIF_NOTIFY_RESUME not implemented - return -EOPNOTSUPP; -#endif /* !TIF_NOTIFY_RESUME */ } /* -- cgit v1.2.3-58-ga151 From 413cd3d9abeaef590e5ce00564f7a443165db238 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 11 May 2012 10:59:08 +1000 Subject: keys: change keyctl_session_to_parent() to use task_work_add() Change keyctl_session_to_parent() to use task_work_add() and move key_replace_session_keyring() logic into task_work->func(). Note that we do task_work_cancel() before task_work_add() to ensure that only one work can be pending at any time. This is important, we must not allow user-space to abuse the parent's ->task_works list. The callback, replace_session_keyring(), checks PF_EXITING. I guess this is not really needed but looks better. As a side effect, this fixes the (unlikely) race. The callers of key_replace_session_keyring() and keyctl_session_to_parent() lack the necessary barriers, the parent can miss the request. Now we can remove task_struct->replacement_session_keyring and related code. Signed-off-by: Oleg Nesterov Acked-by: David Howells Cc: Thomas Gleixner Cc: Richard Kuo Cc: Linus Torvalds Cc: Alexander Gordeev Cc: Chris Zankel Cc: David Smith Cc: "Frank Ch. Eigler" Cc: Geert Uytterhoeven Cc: Larry Woodman Cc: Peter Zijlstra Cc: Tejun Heo Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/key.h | 6 ++--- security/keys/internal.h | 2 ++ security/keys/keyctl.c | 63 ++++++++++++++++++++++++-------------------- security/keys/process_keys.c | 20 +++++--------- 4 files changed, 46 insertions(+), 45 deletions(-) (limited to 'security') diff --git a/include/linux/key.h b/include/linux/key.h index 5231800770e1..2a0ee11584e9 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -33,6 +33,8 @@ typedef uint32_t key_perm_t; struct key; +#define key_replace_session_keyring() do { } while (0) + #ifdef CONFIG_KEYS #undef KEY_DEBUGGING @@ -308,9 +310,6 @@ static inline bool key_is_instantiated(const struct key *key) #ifdef CONFIG_SYSCTL extern ctl_table key_sysctls[]; #endif - -extern void key_replace_session_keyring(void); - /* * the userspace interface */ @@ -334,7 +333,6 @@ extern void key_init(void); #define key_fsuid_changed(t) do { } while(0) #define key_fsgid_changed(t) do { } while(0) #define key_init() do { } while(0) -#define key_replace_session_keyring() do { } while(0) #endif /* CONFIG_KEYS */ #endif /* __KERNEL__ */ diff --git a/security/keys/internal.h b/security/keys/internal.h index f711b094ed41..3dcbf86b0d31 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -14,6 +14,7 @@ #include #include +#include #ifdef __KDEBUG #define kenter(FMT, ...) \ @@ -148,6 +149,7 @@ extern key_ref_t lookup_user_key(key_serial_t id, unsigned long flags, #define KEY_LOOKUP_FOR_UNLINK 0x04 extern long join_session_keyring(const char *name); +extern void key_change_session_keyring(struct task_work *twork); extern struct work_struct key_gc_work; extern unsigned key_gc_delay; diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index 534a634283a4..2f28126215a2 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -1456,47 +1456,55 @@ long keyctl_session_to_parent(void) { struct task_struct *me, *parent; const struct cred *mycred, *pcred; - struct cred *cred, *oldcred; + struct task_work *newwork, *oldwork; key_ref_t keyring_r; + struct cred *cred; int ret; keyring_r = lookup_user_key(KEY_SPEC_SESSION_KEYRING, 0, KEY_LINK); if (IS_ERR(keyring_r)) return PTR_ERR(keyring_r); + ret = -ENOMEM; + newwork = kmalloc(sizeof(struct task_work), GFP_KERNEL); + if (!newwork) + goto error_keyring; + /* our parent is going to need a new cred struct, a new tgcred struct * and new security data, so we allocate them here to prevent ENOMEM in * our parent */ - ret = -ENOMEM; cred = cred_alloc_blank(); if (!cred) - goto error_keyring; + goto error_newwork; cred->tgcred->session_keyring = key_ref_to_ptr(keyring_r); - keyring_r = NULL; + init_task_work(newwork, key_change_session_keyring, cred); me = current; rcu_read_lock(); write_lock_irq(&tasklist_lock); - parent = me->real_parent; ret = -EPERM; + oldwork = NULL; + parent = me->real_parent; /* the parent mustn't be init and mustn't be a kernel thread */ if (parent->pid <= 1 || !parent->mm) - goto not_permitted; + goto unlock; /* the parent must be single threaded */ if (!thread_group_empty(parent)) - goto not_permitted; + goto unlock; /* the parent and the child must have different session keyrings or * there's no point */ mycred = current_cred(); pcred = __task_cred(parent); if (mycred == pcred || - mycred->tgcred->session_keyring == pcred->tgcred->session_keyring) - goto already_same; + mycred->tgcred->session_keyring == pcred->tgcred->session_keyring) { + ret = 0; + goto unlock; + } /* the parent must have the same effective ownership and mustn't be * SUID/SGID */ @@ -1506,38 +1514,37 @@ long keyctl_session_to_parent(void) pcred->gid != mycred->egid || pcred->egid != mycred->egid || pcred->sgid != mycred->egid) - goto not_permitted; + goto unlock; /* the keyrings must have the same UID */ if ((pcred->tgcred->session_keyring && pcred->tgcred->session_keyring->uid != mycred->euid) || mycred->tgcred->session_keyring->uid != mycred->euid) - goto not_permitted; + goto unlock; - /* if there's an already pending keyring replacement, then we replace - * that */ - oldcred = parent->replacement_session_keyring; + /* cancel an already pending keyring replacement */ + oldwork = task_work_cancel(parent, key_change_session_keyring); /* the replacement session keyring is applied just prior to userspace * restarting */ - parent->replacement_session_keyring = cred; - cred = NULL; - set_ti_thread_flag(task_thread_info(parent), TIF_NOTIFY_RESUME); - - write_unlock_irq(&tasklist_lock); - rcu_read_unlock(); - if (oldcred) - put_cred(oldcred); - return 0; - -already_same: - ret = 0; -not_permitted: + ret = task_work_add(parent, newwork, true); + if (!ret) + newwork = NULL; +unlock: write_unlock_irq(&tasklist_lock); rcu_read_unlock(); - put_cred(cred); + if (oldwork) { + put_cred(oldwork->data); + kfree(oldwork); + } + if (newwork) { + put_cred(newwork->data); + kfree(newwork); + } return ret; +error_newwork: + kfree(newwork); error_keyring: key_ref_put(keyring_r); return ret; diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c index d71056db7b67..4ad54eea1ea4 100644 --- a/security/keys/process_keys.c +++ b/security/keys/process_keys.c @@ -834,23 +834,17 @@ error: * Replace a process's session keyring on behalf of one of its children when * the target process is about to resume userspace execution. */ -void key_replace_session_keyring(void) +void key_change_session_keyring(struct task_work *twork) { - const struct cred *old; - struct cred *new; - - if (!current->replacement_session_keyring) - return; + const struct cred *old = current_cred(); + struct cred *new = twork->data; - write_lock_irq(&tasklist_lock); - new = current->replacement_session_keyring; - current->replacement_session_keyring = NULL; - write_unlock_irq(&tasklist_lock); - - if (!new) + kfree(twork); + if (unlikely(current->flags & PF_EXITING)) { + put_cred(new); return; + } - old = current_cred(); new-> uid = old-> uid; new-> euid = old-> euid; new-> suid = old-> suid; -- cgit v1.2.3-58-ga151 From cc1dad7183e4cb7f5d313b6942f2059fc0eabab6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 2 Apr 2012 19:40:47 -0400 Subject: selinuxfs snprintf() misuses a) %d does _not_ produce a page worth of output b) snprintf() doesn't return negatives - it used to in old glibc, but that's the kernel... Signed-off-by: Al Viro --- security/selinux/selinuxfs.c | 36 +++++++----------------------------- 1 file changed, 7 insertions(+), 29 deletions(-) (limited to 'security') diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 4e93f9ef970b..3ad290251288 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -1259,12 +1259,8 @@ static int sel_make_bools(void) if (!inode) goto out; - ret = -EINVAL; - len = snprintf(page, PAGE_SIZE, "/%s/%s", BOOL_DIR_NAME, names[i]); - if (len < 0) - goto out; - ret = -ENAMETOOLONG; + len = snprintf(page, PAGE_SIZE, "/%s/%s", BOOL_DIR_NAME, names[i]); if (len >= PAGE_SIZE) goto out; @@ -1557,19 +1553,10 @@ static inline u32 sel_ino_to_perm(unsigned long ino) static ssize_t sel_read_class(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - ssize_t rc, len; - char *page; unsigned long ino = file->f_path.dentry->d_inode->i_ino; - - page = (char *)__get_free_page(GFP_KERNEL); - if (!page) - return -ENOMEM; - - len = snprintf(page, PAGE_SIZE, "%d", sel_ino_to_class(ino)); - rc = simple_read_from_buffer(buf, count, ppos, page, len); - free_page((unsigned long)page); - - return rc; + char res[TMPBUFLEN]; + ssize_t len = snprintf(res, sizeof(res), "%d", sel_ino_to_class(ino)); + return simple_read_from_buffer(buf, count, ppos, res, len); } static const struct file_operations sel_class_ops = { @@ -1580,19 +1567,10 @@ static const struct file_operations sel_class_ops = { static ssize_t sel_read_perm(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - ssize_t rc, len; - char *page; unsigned long ino = file->f_path.dentry->d_inode->i_ino; - - page = (char *)__get_free_page(GFP_KERNEL); - if (!page) - return -ENOMEM; - - len = snprintf(page, PAGE_SIZE, "%d", sel_ino_to_perm(ino)); - rc = simple_read_from_buffer(buf, count, ppos, page, len); - free_page((unsigned long)page); - - return rc; + char res[TMPBUFLEN]; + ssize_t len = snprintf(res, sizeof(res), "%d", sel_ino_to_perm(ino)); + return simple_read_from_buffer(buf, count, ppos, res, len); } static const struct file_operations sel_perm_ops = { -- cgit v1.2.3-58-ga151 From d007794a182bc072a7b7479909dbd0d67ba341be Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 30 May 2012 13:11:37 -0400 Subject: split cap_mmap_addr() out of cap_file_mmap() ... switch callers. Signed-off-by: Al Viro --- include/linux/security.h | 3 ++- security/apparmor/lsm.c | 2 +- security/commoncap.c | 32 +++++++++++++++++++++++--------- security/selinux/hooks.c | 2 +- security/smack/smack_lsm.c | 2 +- 5 files changed, 28 insertions(+), 13 deletions(-) (limited to 'security') diff --git a/include/linux/security.h b/include/linux/security.h index ab0e091ce5fa..4ad59c9fa731 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -86,6 +86,7 @@ extern int cap_inode_setxattr(struct dentry *dentry, const char *name, extern int cap_inode_removexattr(struct dentry *dentry, const char *name); extern int cap_inode_need_killpriv(struct dentry *dentry); extern int cap_inode_killpriv(struct dentry *dentry); +extern int cap_mmap_addr(unsigned long addr); extern int cap_file_mmap(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags, unsigned long addr, unsigned long addr_only); @@ -2187,7 +2188,7 @@ static inline int security_file_mmap(struct file *file, unsigned long reqprot, unsigned long addr, unsigned long addr_only) { - return cap_file_mmap(file, reqprot, prot, flags, addr, addr_only); + return cap_mmap_addr(addr); } static inline int security_file_mprotect(struct vm_area_struct *vma, diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 032daab449b0..8430d8937afb 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -497,7 +497,7 @@ static int apparmor_file_mmap(struct file *file, unsigned long reqprot, int rc = 0; /* do DAC check */ - rc = cap_file_mmap(file, reqprot, prot, flags, addr, addr_only); + rc = cap_mmap_addr(addr); if (rc || addr_only) return rc; diff --git a/security/commoncap.c b/security/commoncap.c index e771cb1b2d79..ebac3618896e 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -958,22 +958,15 @@ int cap_vm_enough_memory(struct mm_struct *mm, long pages) } /* - * cap_file_mmap - check if able to map given addr - * @file: unused - * @reqprot: unused - * @prot: unused - * @flags: unused + * cap_mmap_addr - check if able to map given addr * @addr: address attempting to be mapped - * @addr_only: unused * * If the process is attempting to map memory below dac_mmap_min_addr they need * CAP_SYS_RAWIO. The other parameters to this function are unused by the * capability security module. Returns 0 if this mapping should be allowed * -EPERM if not. */ -int cap_file_mmap(struct file *file, unsigned long reqprot, - unsigned long prot, unsigned long flags, - unsigned long addr, unsigned long addr_only) +int cap_mmap_addr(unsigned long addr) { int ret = 0; @@ -986,3 +979,24 @@ int cap_file_mmap(struct file *file, unsigned long reqprot, } return ret; } + +/* + * cap_file_mmap - check if able to map given addr + * @file: unused + * @reqprot: unused + * @prot: unused + * @flags: unused + * @addr: address attempting to be mapped + * @addr_only: unused + * + * If the process is attempting to map memory below dac_mmap_min_addr they need + * CAP_SYS_RAWIO. The other parameters to this function are unused by the + * capability security module. Returns 0 if this mapping should be allowed + * -EPERM if not. + */ +int cap_file_mmap(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags, + unsigned long addr, unsigned long addr_only) +{ + return cap_mmap_addr(addr); +} diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index fa2341b68331..25c125eaa3d8 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3104,7 +3104,7 @@ static int selinux_file_mmap(struct file *file, unsigned long reqprot, } /* do DAC check on address space usage */ - rc = cap_file_mmap(file, reqprot, prot, flags, addr, addr_only); + rc = cap_mmap_addr(addr); if (rc || addr_only) return rc; diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index d583c0545808..a62197718768 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -1199,7 +1199,7 @@ static int smack_file_mmap(struct file *file, int rc; /* do DAC check on address space usage */ - rc = cap_file_mmap(file, reqprot, prot, flags, addr, addr_only); + rc = cap_mmap_addr(addr); if (rc || addr_only) return rc; -- cgit v1.2.3-58-ga151 From e5467859f7f79b69fc49004403009dfdba3bec53 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 30 May 2012 13:30:51 -0400 Subject: split ->file_mmap() into ->mmap_addr()/->mmap_file() ... i.e. file-dependent and address-dependent checks. Signed-off-by: Al Viro --- fs/exec.c | 4 ---- include/linux/security.h | 36 ++++++++++++++++++++---------------- mm/mmap.c | 12 ++++++++---- mm/mremap.c | 4 ++-- mm/nommu.c | 5 ++++- security/apparmor/lsm.c | 15 ++++----------- security/capability.c | 3 ++- security/commoncap.c | 21 +++------------------ security/security.c | 12 ++++++++---- security/selinux/hooks.c | 15 ++++++++------- security/smack/smack_lsm.c | 15 +++++---------- 11 files changed, 64 insertions(+), 78 deletions(-) (limited to 'security') diff --git a/fs/exec.c b/fs/exec.c index 52c9e2ff6e6b..a79786a8d2c8 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -280,10 +280,6 @@ static int __bprm_mm_init(struct linux_binprm *bprm) vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); INIT_LIST_HEAD(&vma->anon_vma_chain); - err = security_file_mmap(NULL, 0, 0, 0, vma->vm_start, 1); - if (err) - goto err; - err = insert_vm_struct(mm, vma); if (err) goto err; diff --git a/include/linux/security.h b/include/linux/security.h index 4ad59c9fa731..f1bae0963ddc 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -87,9 +87,8 @@ extern int cap_inode_removexattr(struct dentry *dentry, const char *name); extern int cap_inode_need_killpriv(struct dentry *dentry); extern int cap_inode_killpriv(struct dentry *dentry); extern int cap_mmap_addr(unsigned long addr); -extern int cap_file_mmap(struct file *file, unsigned long reqprot, - unsigned long prot, unsigned long flags, - unsigned long addr, unsigned long addr_only); +extern int cap_mmap_file(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags); extern int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags); extern int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5); @@ -587,15 +586,17 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * simple integer value. When @arg represents a user space pointer, it * should never be used by the security module. * Return 0 if permission is granted. - * @file_mmap : + * @mmap_addr : + * Check permissions for a mmap operation at @addr. + * @addr contains virtual address that will be used for the operation. + * Return 0 if permission is granted. + * @mmap_file : * Check permissions for a mmap operation. The @file may be NULL, e.g. * if mapping anonymous memory. * @file contains the file structure for file to map (may be NULL). * @reqprot contains the protection requested by the application. * @prot contains the protection that will be applied by the kernel. * @flags contains the operational flags. - * @addr contains virtual address that will be used for the operation. - * @addr_only contains a boolean: 0 if file-backed VMA, otherwise 1. * Return 0 if permission is granted. * @file_mprotect: * Check permissions before changing memory access permissions. @@ -1482,10 +1483,10 @@ struct security_operations { void (*file_free_security) (struct file *file); int (*file_ioctl) (struct file *file, unsigned int cmd, unsigned long arg); - int (*file_mmap) (struct file *file, + int (*mmap_addr) (unsigned long addr); + int (*mmap_file) (struct file *file, unsigned long reqprot, unsigned long prot, - unsigned long flags, unsigned long addr, - unsigned long addr_only); + unsigned long flags); int (*file_mprotect) (struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot); @@ -1744,9 +1745,9 @@ int security_file_permission(struct file *file, int mask); int security_file_alloc(struct file *file); void security_file_free(struct file *file); int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg); -int security_file_mmap(struct file *file, unsigned long reqprot, - unsigned long prot, unsigned long flags, - unsigned long addr, unsigned long addr_only); +int security_mmap_file(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags); +int security_mmap_addr(unsigned long addr); int security_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot); int security_file_lock(struct file *file, unsigned int cmd); @@ -2182,11 +2183,14 @@ static inline int security_file_ioctl(struct file *file, unsigned int cmd, return 0; } -static inline int security_file_mmap(struct file *file, unsigned long reqprot, +static inline int security_mmap_file(struct file *file, unsigned long reqprot, unsigned long prot, - unsigned long flags, - unsigned long addr, - unsigned long addr_only) + unsigned long flags) +{ + return 0; +} + +static inline int security_mmap_addr(unsigned long addr) { return cap_mmap_addr(addr); } diff --git a/mm/mmap.c b/mm/mmap.c index 83c56624f1f6..49283da9a2ae 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1101,7 +1101,11 @@ static unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, } } - error = security_file_mmap(file, reqprot, prot, flags, addr, 0); + error = security_mmap_addr(addr); + if (error) + return error; + + error = security_mmap_file(file, reqprot, prot, flags); if (error) return error; @@ -1817,7 +1821,7 @@ int expand_downwards(struct vm_area_struct *vma, return -ENOMEM; address &= PAGE_MASK; - error = security_file_mmap(NULL, 0, 0, 0, address, 1); + error = security_mmap_addr(address); if (error) return error; @@ -2205,7 +2209,7 @@ static unsigned long do_brk(unsigned long addr, unsigned long len) if (!len) return addr; - error = security_file_mmap(NULL, 0, 0, 0, addr, 1); + error = security_mmap_addr(addr); if (error) return error; @@ -2561,7 +2565,7 @@ int install_special_mapping(struct mm_struct *mm, vma->vm_ops = &special_mapping_vmops; vma->vm_private_data = pages; - ret = security_file_mmap(NULL, 0, 0, 0, vma->vm_start, 1); + ret = security_mmap_addr(vma->vm_start); if (ret) goto out; diff --git a/mm/mremap.c b/mm/mremap.c index 169c53b87749..ebf10892b63d 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -371,7 +371,7 @@ static unsigned long mremap_to(unsigned long addr, if ((addr <= new_addr) && (addr+old_len) > new_addr) goto out; - ret = security_file_mmap(NULL, 0, 0, 0, new_addr, 1); + ret = security_mmap_addr(new_addr); if (ret) goto out; @@ -532,7 +532,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, goto out; } - ret = security_file_mmap(NULL, 0, 0, 0, new_addr, 1); + ret = security_mmap_addr(new_addr); if (ret) goto out; ret = move_vma(vma, addr, old_len, new_len, new_addr); diff --git a/mm/nommu.c b/mm/nommu.c index de6084e3a046..acfe419785db 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1047,7 +1047,10 @@ static int validate_mmap_request(struct file *file, } /* allow the security API to have its say */ - ret = security_file_mmap(file, reqprot, prot, flags, addr, 0); + ret = security_mmap_addr(addr); + if (ret < 0) + return ret; + ret = security_mmap_file(file, reqprot, prot, flags); if (ret < 0) return ret; diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 8430d8937afb..8ea39aabe948 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -490,17 +490,9 @@ static int common_mmap(int op, struct file *file, unsigned long prot, return common_file_perm(op, file, mask); } -static int apparmor_file_mmap(struct file *file, unsigned long reqprot, - unsigned long prot, unsigned long flags, - unsigned long addr, unsigned long addr_only) +static int apparmor_mmap_file(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags) { - int rc = 0; - - /* do DAC check */ - rc = cap_mmap_addr(addr); - if (rc || addr_only) - return rc; - return common_mmap(OP_FMMAP, file, prot, flags); } @@ -646,7 +638,8 @@ static struct security_operations apparmor_ops = { .file_permission = apparmor_file_permission, .file_alloc_security = apparmor_file_alloc_security, .file_free_security = apparmor_file_free_security, - .file_mmap = apparmor_file_mmap, + .mmap_file = apparmor_mmap_file, + .mmap_addr = cap_mmap_addr, .file_mprotect = apparmor_file_mprotect, .file_lock = apparmor_file_lock, diff --git a/security/capability.c b/security/capability.c index fca889676c5e..61095df8b89a 100644 --- a/security/capability.c +++ b/security/capability.c @@ -949,7 +949,8 @@ void __init security_fixup_ops(struct security_operations *ops) set_to_cap_if_null(ops, file_alloc_security); set_to_cap_if_null(ops, file_free_security); set_to_cap_if_null(ops, file_ioctl); - set_to_cap_if_null(ops, file_mmap); + set_to_cap_if_null(ops, mmap_addr); + set_to_cap_if_null(ops, mmap_file); set_to_cap_if_null(ops, file_mprotect); set_to_cap_if_null(ops, file_lock); set_to_cap_if_null(ops, file_fcntl); diff --git a/security/commoncap.c b/security/commoncap.c index ebac3618896e..6dbae4650abe 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -980,23 +980,8 @@ int cap_mmap_addr(unsigned long addr) return ret; } -/* - * cap_file_mmap - check if able to map given addr - * @file: unused - * @reqprot: unused - * @prot: unused - * @flags: unused - * @addr: address attempting to be mapped - * @addr_only: unused - * - * If the process is attempting to map memory below dac_mmap_min_addr they need - * CAP_SYS_RAWIO. The other parameters to this function are unused by the - * capability security module. Returns 0 if this mapping should be allowed - * -EPERM if not. - */ -int cap_file_mmap(struct file *file, unsigned long reqprot, - unsigned long prot, unsigned long flags, - unsigned long addr, unsigned long addr_only) +int cap_mmap_file(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags) { - return cap_mmap_addr(addr); + return 0; } diff --git a/security/security.c b/security/security.c index 5497a57fba01..d91c66d3956b 100644 --- a/security/security.c +++ b/security/security.c @@ -657,18 +657,22 @@ int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return security_ops->file_ioctl(file, cmd, arg); } -int security_file_mmap(struct file *file, unsigned long reqprot, - unsigned long prot, unsigned long flags, - unsigned long addr, unsigned long addr_only) +int security_mmap_file(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags) { int ret; - ret = security_ops->file_mmap(file, reqprot, prot, flags, addr, addr_only); + ret = security_ops->mmap_file(file, reqprot, prot, flags); if (ret) return ret; return ima_file_mmap(file, prot); } +int security_mmap_addr(unsigned long addr) +{ + return security_ops->mmap_addr(addr); +} + int security_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) { diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 25c125eaa3d8..372ec6502aa8 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3083,9 +3083,7 @@ error: return rc; } -static int selinux_file_mmap(struct file *file, unsigned long reqprot, - unsigned long prot, unsigned long flags, - unsigned long addr, unsigned long addr_only) +static int selinux_mmap_addr(unsigned long addr) { int rc = 0; u32 sid = current_sid(); @@ -3104,10 +3102,12 @@ static int selinux_file_mmap(struct file *file, unsigned long reqprot, } /* do DAC check on address space usage */ - rc = cap_mmap_addr(addr); - if (rc || addr_only) - return rc; + return cap_mmap_addr(addr); +} +static int selinux_mmap_file(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags) +{ if (selinux_checkreqprot) prot = reqprot; @@ -5570,7 +5570,8 @@ static struct security_operations selinux_ops = { .file_alloc_security = selinux_file_alloc_security, .file_free_security = selinux_file_free_security, .file_ioctl = selinux_file_ioctl, - .file_mmap = selinux_file_mmap, + .mmap_file = selinux_mmap_file, + .mmap_addr = selinux_mmap_addr, .file_mprotect = selinux_file_mprotect, .file_lock = selinux_file_lock, .file_fcntl = selinux_file_fcntl, diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index a62197718768..ee0bb5735f35 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -1171,7 +1171,7 @@ static int smack_file_fcntl(struct file *file, unsigned int cmd, } /** - * smack_file_mmap : + * smack_mmap_file : * Check permissions for a mmap operation. The @file may be NULL, e.g. * if mapping anonymous memory. * @file contains the file structure for file to map (may be NULL). @@ -1180,10 +1180,9 @@ static int smack_file_fcntl(struct file *file, unsigned int cmd, * @flags contains the operational flags. * Return 0 if permission is granted. */ -static int smack_file_mmap(struct file *file, +static int smack_mmap_file(struct file *file, unsigned long reqprot, unsigned long prot, - unsigned long flags, unsigned long addr, - unsigned long addr_only) + unsigned long flags) { struct smack_known *skp; struct smack_rule *srp; @@ -1198,11 +1197,6 @@ static int smack_file_mmap(struct file *file, int tmay; int rc; - /* do DAC check on address space usage */ - rc = cap_mmap_addr(addr); - if (rc || addr_only) - return rc; - if (file == NULL || file->f_dentry == NULL) return 0; @@ -3482,7 +3476,8 @@ struct security_operations smack_ops = { .file_ioctl = smack_file_ioctl, .file_lock = smack_file_lock, .file_fcntl = smack_file_fcntl, - .file_mmap = smack_file_mmap, + .mmap_file = smack_mmap_file, + .mmap_addr = cap_mmap_addr, .file_set_fowner = smack_file_set_fowner, .file_send_sigiotask = smack_file_send_sigiotask, .file_receive = smack_file_receive, -- cgit v1.2.3-58-ga151 From 4f1c28d241d0882f25112d494885cd6084db225b Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 31 May 2012 16:26:02 -0700 Subject: security/keys/keyctl.c: suppress memory allocation failure warning This allocation may be large. The code is probing to see if it will succeed and if not, it falls back to vmalloc(). We should suppress any page-allocation failure messages when the fallback happens. Reported-by: Dave Jones Acked-by: David Howells Cc: James Morris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- security/keys/keyctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'security') diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index ddb3e05bc5fc..18f29de88fda 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -84,7 +84,7 @@ SYSCALL_DEFINE5(add_key, const char __user *, _type, vm = false; if (_payload) { ret = -ENOMEM; - payload = kmalloc(plen, GFP_KERNEL); + payload = kmalloc(plen, GFP_KERNEL | __GFP_NOWARN); if (!payload) { if (plen <= PAGE_SIZE) goto error2; -- cgit v1.2.3-58-ga151 From 81ab6e7b26b453a795d46f2616ed0e31d97f05b9 Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Thu, 31 May 2012 16:26:15 -0700 Subject: kmod: convert two call sites to call_usermodehelper_fns() Both kernel/sys.c && security/keys/request_key.c where inlining the exact same code as call_usermodehelper_fns(); So simply convert these sites to directly use call_usermodehelper_fns(). Signed-off-by: Boaz Harrosh Cc: Oleg Nesterov Cc: Tetsuo Handa Cc: Ingo Molnar Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sys.c | 19 ++++++++----------- security/keys/request_key.c | 13 +++---------- 2 files changed, 11 insertions(+), 21 deletions(-) (limited to 'security') diff --git a/kernel/sys.c b/kernel/sys.c index 8b71cef3bf1a..6e81aa7e4688 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2114,7 +2114,6 @@ int orderly_poweroff(bool force) NULL }; int ret = -ENOMEM; - struct subprocess_info *info; if (argv == NULL) { printk(KERN_WARNING "%s failed to allocate memory for \"%s\"\n", @@ -2122,18 +2121,16 @@ int orderly_poweroff(bool force) goto out; } - info = call_usermodehelper_setup(argv[0], argv, envp, GFP_ATOMIC); - if (info == NULL) { - argv_free(argv); - goto out; - } - - call_usermodehelper_setfns(info, NULL, argv_cleanup, NULL); + ret = call_usermodehelper_fns(argv[0], argv, envp, UMH_NO_WAIT, + NULL, argv_cleanup, NULL); +out: + if (likely(!ret)) + return 0; - ret = call_usermodehelper_exec(info, UMH_NO_WAIT); + if (ret == -ENOMEM) + argv_free(argv); - out: - if (ret && force) { + if (force) { printk(KERN_WARNING "Failed to start orderly shutdown: " "forcing the issue\n"); diff --git a/security/keys/request_key.c b/security/keys/request_key.c index cc3790315d2f..000e75017520 100644 --- a/security/keys/request_key.c +++ b/security/keys/request_key.c @@ -93,16 +93,9 @@ static void umh_keys_cleanup(struct subprocess_info *info) static int call_usermodehelper_keys(char *path, char **argv, char **envp, struct key *session_keyring, int wait) { - gfp_t gfp_mask = (wait == UMH_NO_WAIT) ? GFP_ATOMIC : GFP_KERNEL; - struct subprocess_info *info = - call_usermodehelper_setup(path, argv, envp, gfp_mask); - - if (!info) - return -ENOMEM; - - call_usermodehelper_setfns(info, umh_keys_init, umh_keys_cleanup, - key_get(session_keyring)); - return call_usermodehelper_exec(info, wait); + return call_usermodehelper_fns(path, argv, envp, wait, + umh_keys_init, umh_keys_cleanup, + key_get(session_keyring)); } /* -- cgit v1.2.3-58-ga151 From ac34ebb3a67e699edcb5ac72f19d31679369dfaa Mon Sep 17 00:00:00 2001 From: Christopher Yeoh Date: Thu, 31 May 2012 16:26:42 -0700 Subject: aio/vfs: cleanup of rw_copy_check_uvector() and compat_rw_copy_check_uvector() A cleanup of rw_copy_check_uvector and compat_rw_copy_check_uvector after changes made to support CMA in an earlier patch. Rather than having an additional check_access parameter to these functions, the first paramater type is overloaded to allow the caller to specify CHECK_IOVEC_ONLY which means check that the contents of the iovec are valid, but do not check the memory that they point to. This is used by process_vm_readv/writev where we need to validate that a iovec passed to the syscall is valid but do not want to check the memory that it points to at this point because it refers to an address space in another process. Signed-off-by: Chris Yeoh Reviewed-by: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/aio.c | 4 ++-- fs/compat.c | 6 +++--- fs/read_write.c | 7 +++---- include/linux/compat.h | 3 +-- include/linux/fs.h | 12 ++++++++++-- mm/process_vm_access.c | 16 ++++++++-------- security/keys/compat.c | 2 +- security/keys/keyctl.c | 2 +- 8 files changed, 29 insertions(+), 23 deletions(-) (limited to 'security') diff --git a/fs/aio.c b/fs/aio.c index e7f2fad7b4ce..8c7c8b805372 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1446,13 +1446,13 @@ static ssize_t aio_setup_vectored_rw(int type, struct kiocb *kiocb, bool compat) ret = compat_rw_copy_check_uvector(type, (struct compat_iovec __user *)kiocb->ki_buf, kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec, - &kiocb->ki_iovec, 1); + &kiocb->ki_iovec); else #endif ret = rw_copy_check_uvector(type, (struct iovec __user *)kiocb->ki_buf, kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec, - &kiocb->ki_iovec, 1); + &kiocb->ki_iovec); if (ret < 0) goto out; diff --git a/fs/compat.c b/fs/compat.c index 0781e619a62a..6556a9ce8a28 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -532,7 +532,7 @@ out: ssize_t compat_rw_copy_check_uvector(int type, const struct compat_iovec __user *uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_pointer, - struct iovec **ret_pointer, int check_access) + struct iovec **ret_pointer) { compat_ssize_t tot_len; struct iovec *iov = *ret_pointer = fast_pointer; @@ -579,7 +579,7 @@ ssize_t compat_rw_copy_check_uvector(int type, } if (len < 0) /* size_t not fitting in compat_ssize_t .. */ goto out; - if (check_access && + if (type >= 0 && !access_ok(vrfy_dir(type), compat_ptr(buf), len)) { ret = -EFAULT; goto out; @@ -1094,7 +1094,7 @@ static ssize_t compat_do_readv_writev(int type, struct file *file, goto out; tot_len = compat_rw_copy_check_uvector(type, uvector, nr_segs, - UIO_FASTIOV, iovstack, &iov, 1); + UIO_FASTIOV, iovstack, &iov); if (tot_len == 0) { ret = 0; goto out; diff --git a/fs/read_write.c b/fs/read_write.c index ffc99d22e0a3..c20614f86c01 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -633,8 +633,7 @@ ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov, ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_pointer, - struct iovec **ret_pointer, - int check_access) + struct iovec **ret_pointer) { unsigned long seg; ssize_t ret; @@ -690,7 +689,7 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, ret = -EINVAL; goto out; } - if (check_access + if (type >= 0 && unlikely(!access_ok(vrfy_dir(type), buf, len))) { ret = -EFAULT; goto out; @@ -723,7 +722,7 @@ static ssize_t do_readv_writev(int type, struct file *file, } ret = rw_copy_check_uvector(type, uvector, nr_segs, - ARRAY_SIZE(iovstack), iovstack, &iov, 1); + ARRAY_SIZE(iovstack), iovstack, &iov); if (ret <= 0) goto out; diff --git a/include/linux/compat.h b/include/linux/compat.h index 5d46217f84ad..4e890394ef99 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -577,8 +577,7 @@ extern ssize_t compat_rw_copy_check_uvector(int type, const struct compat_iovec __user *uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_pointer, - struct iovec **ret_pointer, - int check_access); + struct iovec **ret_pointer); extern void __user *compat_alloc_user_space(unsigned long len); diff --git a/include/linux/fs.h b/include/linux/fs.h index 038076b27ea4..cf2c5611b19b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -173,6 +173,15 @@ struct inodes_stat_t { #define WRITE_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA) #define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA) + +/* + * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector + * that indicates that they should check the contents of the iovec are + * valid, but not check the memory that the iovec elements + * points too. + */ +#define CHECK_IOVEC_ONLY -1 + #define SEL_IN 1 #define SEL_OUT 2 #define SEL_EX 4 @@ -1690,8 +1699,7 @@ struct seq_file; ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_pointer, - struct iovec **ret_pointer, - int check_access); + struct iovec **ret_pointer); extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index c20ff48994c2..926b46649749 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -371,15 +371,15 @@ static ssize_t process_vm_rw(pid_t pid, /* Check iovecs */ if (vm_write) rc = rw_copy_check_uvector(WRITE, lvec, liovcnt, UIO_FASTIOV, - iovstack_l, &iov_l, 1); + iovstack_l, &iov_l); else rc = rw_copy_check_uvector(READ, lvec, liovcnt, UIO_FASTIOV, - iovstack_l, &iov_l, 1); + iovstack_l, &iov_l); if (rc <= 0) goto free_iovecs; - rc = rw_copy_check_uvector(READ, rvec, riovcnt, UIO_FASTIOV, - iovstack_r, &iov_r, 0); + rc = rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV, + iovstack_r, &iov_r); if (rc <= 0) goto free_iovecs; @@ -438,16 +438,16 @@ compat_process_vm_rw(compat_pid_t pid, if (vm_write) rc = compat_rw_copy_check_uvector(WRITE, lvec, liovcnt, UIO_FASTIOV, iovstack_l, - &iov_l, 1); + &iov_l); else rc = compat_rw_copy_check_uvector(READ, lvec, liovcnt, UIO_FASTIOV, iovstack_l, - &iov_l, 1); + &iov_l); if (rc <= 0) goto free_iovecs; - rc = compat_rw_copy_check_uvector(READ, rvec, riovcnt, + rc = compat_rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV, iovstack_r, - &iov_r, 0); + &iov_r); if (rc <= 0) goto free_iovecs; diff --git a/security/keys/compat.c b/security/keys/compat.c index fab4f8dda6c6..c92d42b021aa 100644 --- a/security/keys/compat.c +++ b/security/keys/compat.c @@ -38,7 +38,7 @@ long compat_keyctl_instantiate_key_iov( ret = compat_rw_copy_check_uvector(WRITE, _payload_iov, ioc, ARRAY_SIZE(iovstack), - iovstack, &iov, 1); + iovstack, &iov); if (ret < 0) return ret; if (ret == 0) diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index 18f29de88fda..21907ea35b15 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -1110,7 +1110,7 @@ long keyctl_instantiate_key_iov(key_serial_t id, goto no_payload; ret = rw_copy_check_uvector(WRITE, _payload_iov, ioc, - ARRAY_SIZE(iovstack), iovstack, &iov, 1); + ARRAY_SIZE(iovstack), iovstack, &iov); if (ret < 0) return ret; if (ret == 0) -- cgit v1.2.3-58-ga151 From 8b3ec6814c83d76b85bd13badc48552836c24839 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 30 May 2012 17:11:23 -0400 Subject: take security_mmap_file() outside of ->mmap_sem Signed-off-by: Al Viro --- include/linux/security.h | 7 +++---- ipc/shm.c | 5 +++++ mm/mmap.c | 23 ++++++++++++----------- mm/nommu.c | 22 ++++++++++++---------- security/security.c | 33 ++++++++++++++++++++++++++++++--- 5 files changed, 62 insertions(+), 28 deletions(-) (limited to 'security') diff --git a/include/linux/security.h b/include/linux/security.h index f1bae0963ddc..4e5a73cdbbef 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1745,8 +1745,8 @@ int security_file_permission(struct file *file, int mask); int security_file_alloc(struct file *file); void security_file_free(struct file *file); int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg); -int security_mmap_file(struct file *file, unsigned long reqprot, - unsigned long prot, unsigned long flags); +int security_mmap_file(struct file *file, unsigned long prot, + unsigned long flags); int security_mmap_addr(unsigned long addr); int security_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot); @@ -2183,8 +2183,7 @@ static inline int security_file_ioctl(struct file *file, unsigned int cmd, return 0; } -static inline int security_mmap_file(struct file *file, unsigned long reqprot, - unsigned long prot, +static inline int security_mmap_file(struct file *file, unsigned long prot, unsigned long flags) { return 0; diff --git a/ipc/shm.c b/ipc/shm.c index 406c5b208193..e3a8063b1768 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -1036,6 +1036,10 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr) sfd->file = shp->shm_file; sfd->vm_ops = NULL; + err = security_mmap_file(file, prot, flags); + if (err) + goto out_fput; + down_write(¤t->mm->mmap_sem); if (addr && !(shmflg & SHM_REMAP)) { err = -EINVAL; @@ -1058,6 +1062,7 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr) invalid: up_write(¤t->mm->mmap_sem); +out_fput: fput(file); out_nattch: diff --git a/mm/mmap.c b/mm/mmap.c index 49283da9a2ae..34b280f4238d 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -979,7 +979,6 @@ static unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, struct inode *inode; vm_flags_t vm_flags; int error; - unsigned long reqprot = prot; /* * Does the application expect PROT_READ to imply PROT_EXEC? @@ -1105,10 +1104,6 @@ static unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, if (error) return error; - error = security_mmap_file(file, reqprot, prot, flags); - if (error) - return error; - return mmap_region(file, addr, len, flags, vm_flags, pgoff); } @@ -1130,9 +1125,12 @@ unsigned long vm_mmap(struct file *file, unsigned long addr, unsigned long ret; struct mm_struct *mm = current->mm; - down_write(&mm->mmap_sem); - ret = do_mmap(file, addr, len, prot, flag, offset); - up_write(&mm->mmap_sem); + ret = security_mmap_file(file, prot, flag); + if (!ret) { + down_write(&mm->mmap_sem); + ret = do_mmap(file, addr, len, prot, flag, offset); + up_write(&mm->mmap_sem); + } return ret; } EXPORT_SYMBOL(vm_mmap); @@ -1168,9 +1166,12 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); - down_write(¤t->mm->mmap_sem); - retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff); - up_write(¤t->mm->mmap_sem); + retval = security_mmap_file(file, prot, flags); + if (!retval) { + down_write(¤t->mm->mmap_sem); + retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff); + up_write(¤t->mm->mmap_sem); + } if (file) fput(file); diff --git a/mm/nommu.c b/mm/nommu.c index acfe419785db..8cbfd623b04a 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -889,7 +889,6 @@ static int validate_mmap_request(struct file *file, unsigned long *_capabilities) { unsigned long capabilities, rlen; - unsigned long reqprot = prot; int ret; /* do the simple checks first */ @@ -1048,9 +1047,6 @@ static int validate_mmap_request(struct file *file, /* allow the security API to have its say */ ret = security_mmap_addr(addr); - if (ret < 0) - return ret; - ret = security_mmap_file(file, reqprot, prot, flags); if (ret < 0) return ret; @@ -1492,9 +1488,12 @@ unsigned long vm_mmap(struct file *file, unsigned long addr, unsigned long ret; struct mm_struct *mm = current->mm; - down_write(&mm->mmap_sem); - ret = do_mmap(file, addr, len, prot, flag, offset); - up_write(&mm->mmap_sem); + ret = security_mmap_file(file, prot, flag); + if (!ret) { + down_write(&mm->mmap_sem); + ret = do_mmap(file, addr, len, prot, flag, offset); + up_write(&mm->mmap_sem); + } return ret; } EXPORT_SYMBOL(vm_mmap); @@ -1515,9 +1514,12 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); - down_write(¤t->mm->mmap_sem); - retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff); - up_write(¤t->mm->mmap_sem); + ret = security_mmap_file(file, prot, flags); + if (!ret) { + down_write(¤t->mm->mmap_sem); + retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff); + up_write(¤t->mm->mmap_sem); + } if (file) fput(file); diff --git a/security/security.c b/security/security.c index d91c66d3956b..3b11b3b72fe2 100644 --- a/security/security.c +++ b/security/security.c @@ -20,6 +20,9 @@ #include #include #include +#include +#include +#include #include #define MAX_LSM_EVM_XATTR 2 @@ -657,11 +660,35 @@ int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return security_ops->file_ioctl(file, cmd, arg); } -int security_mmap_file(struct file *file, unsigned long reqprot, - unsigned long prot, unsigned long flags) +int security_mmap_file(struct file *file, unsigned long prot, + unsigned long flags) { + unsigned long reqprot = prot; int ret; - + /* + * Does the application expect PROT_READ to imply PROT_EXEC? + * + * (the exception is when the underlying filesystem is noexec + * mounted, in which case we dont add PROT_EXEC.) + */ + if (!(reqprot & PROT_READ)) + goto out; + if (!(current->personality & READ_IMPLIES_EXEC)) + goto out; + if (!file) { + prot |= PROT_EXEC; + } else if (!(file->f_path.mnt->mnt_flags & MNT_NOEXEC)) { +#ifndef CONFIG_MMU + unsigned long caps = 0; + struct address_space *mapping = file->f_mapping; + if (mapping && mapping->backing_dev_info) + caps = mapping->backing_dev_info->capabilities; + if (!(caps & BDI_CAP_EXEC_MAP)) + goto out; +#endif + prot |= PROT_EXEC; + } +out: ret = security_ops->mmap_file(file, reqprot, prot, flags); if (ret) return ret; -- cgit v1.2.3-58-ga151 From 98de59bfe4b2ff6344d9ad8e5296f80de5dcc5b6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 30 May 2012 19:58:30 -0400 Subject: take calculation of final prot in security_mmap_file() into a helper Signed-off-by: Al Viro --- security/security.c | 46 ++++++++++++++++++++++++++++------------------ 1 file changed, 28 insertions(+), 18 deletions(-) (limited to 'security') diff --git a/security/security.c b/security/security.c index 3b11b3b72fe2..3efc9b12aef4 100644 --- a/security/security.c +++ b/security/security.c @@ -660,36 +660,46 @@ int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return security_ops->file_ioctl(file, cmd, arg); } -int security_mmap_file(struct file *file, unsigned long prot, - unsigned long flags) +static inline unsigned long mmap_prot(struct file *file, unsigned long prot) { - unsigned long reqprot = prot; - int ret; /* - * Does the application expect PROT_READ to imply PROT_EXEC? - * - * (the exception is when the underlying filesystem is noexec - * mounted, in which case we dont add PROT_EXEC.) + * Does we have PROT_READ and does the application expect + * it to imply PROT_EXEC? If not, nothing to talk about... */ - if (!(reqprot & PROT_READ)) - goto out; + if ((prot & (PROT_READ | PROT_EXEC)) != PROT_READ) + return prot; if (!(current->personality & READ_IMPLIES_EXEC)) - goto out; - if (!file) { - prot |= PROT_EXEC; - } else if (!(file->f_path.mnt->mnt_flags & MNT_NOEXEC)) { + return prot; + /* + * if that's an anonymous mapping, let it. + */ + if (!file) + return prot | PROT_EXEC; + /* + * ditto if it's not on noexec mount, except that on !MMU we need + * BDI_CAP_EXEC_MMAP (== VM_MAYEXEC) in this case + */ + if (!(file->f_path.mnt->mnt_flags & MNT_NOEXEC)) { #ifndef CONFIG_MMU unsigned long caps = 0; struct address_space *mapping = file->f_mapping; if (mapping && mapping->backing_dev_info) caps = mapping->backing_dev_info->capabilities; if (!(caps & BDI_CAP_EXEC_MAP)) - goto out; + return prot; #endif - prot |= PROT_EXEC; + return prot | PROT_EXEC; } -out: - ret = security_ops->mmap_file(file, reqprot, prot, flags); + /* anything on noexec mount won't get PROT_EXEC */ + return prot; +} + +int security_mmap_file(struct file *file, unsigned long prot, + unsigned long flags) +{ + int ret; + ret = security_ops->mmap_file(file, prot, + mmap_prot(file, prot), flags); if (ret) return ret; return ima_file_mmap(file, prot); -- cgit v1.2.3-58-ga151