From 40dc166cb5dddbd36aa4ad11c03915ea538f5a61 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 15 Mar 2011 00:43:46 +0100 Subject: PM / Core: Introduce struct syscore_ops for core subsystems PM Some subsystems need to carry out suspend/resume and shutdown operations with one CPU on-line and interrupts disabled. The only way to register such operations is to define a sysdev class and a sysdev specifically for this purpose which is cumbersome and inefficient. Moreover, the arguments taken by sysdev suspend, resume and shutdown callbacks are practically never necessary. For this reason, introduce a simpler interface allowing subsystems to register operations to be executed very late during system suspend and shutdown and very early during resume in the form of strcut syscore_ops objects. Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman --- kernel/sys.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel/sys.c') diff --git a/kernel/sys.c b/kernel/sys.c index 18da702ec81..1ad48b3b906 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include @@ -298,6 +299,7 @@ void kernel_restart_prepare(char *cmd) system_state = SYSTEM_RESTART; device_shutdown(); sysdev_shutdown(); + syscore_shutdown(); } /** @@ -336,6 +338,7 @@ void kernel_halt(void) { kernel_shutdown_prepare(SYSTEM_HALT); sysdev_shutdown(); + syscore_shutdown(); printk(KERN_EMERG "System halted.\n"); kmsg_dump(KMSG_DUMP_HALT); machine_halt(); @@ -355,6 +358,7 @@ void kernel_power_off(void) pm_power_off_prepare(); disable_nonboot_cpus(); sysdev_shutdown(); + syscore_shutdown(); printk(KERN_EMERG "Power down.\n"); kmsg_dump(KMSG_DUMP_POWEROFF); machine_power_off(); -- cgit v1.2.3-70-g09d2 From bb96a6f50be27390dc959ff67d9ea0ea0cfbe177 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Wed, 23 Mar 2011 16:43:18 -0700 Subject: userns: allow sethostname in a container Changelog: Feb 23: let clone_uts_ns() handle setting uts->user_ns To do so we need to pass in the task_struct who'll get the utsname, so we can get its user_ns. Feb 23: As per Oleg's coment, just pass in tsk, instead of two of its members. Signed-off-by: Serge E. Hallyn Acked-by: "Eric W. Biederman" Acked-by: Daniel Lezcano Acked-by: David Howells Cc: James Morris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/utsname.h | 6 +++--- kernel/nsproxy.c | 7 +------ kernel/sys.c | 2 +- kernel/utsname.c | 12 +++++++----- 4 files changed, 12 insertions(+), 15 deletions(-) (limited to 'kernel/sys.c') diff --git a/include/linux/utsname.h b/include/linux/utsname.h index 2c3c0f54370..4e5b0213fdc 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -54,7 +54,7 @@ static inline void get_uts_ns(struct uts_namespace *ns) } extern struct uts_namespace *copy_utsname(unsigned long flags, - struct uts_namespace *ns); + struct task_struct *tsk); extern void free_uts_ns(struct kref *kref); static inline void put_uts_ns(struct uts_namespace *ns) @@ -71,12 +71,12 @@ static inline void put_uts_ns(struct uts_namespace *ns) } static inline struct uts_namespace *copy_utsname(unsigned long flags, - struct uts_namespace *ns) + struct task_struct *tsk) { if (flags & CLONE_NEWUTS) return ERR_PTR(-EINVAL); - return ns; + return tsk->nsproxy->uts_ns; } #endif diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index 034dc2ed13a..b97fc9d04dd 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -69,16 +69,11 @@ static struct nsproxy *create_new_namespaces(unsigned long flags, goto out_ns; } - new_nsp->uts_ns = copy_utsname(flags, tsk->nsproxy->uts_ns); + new_nsp->uts_ns = copy_utsname(flags, tsk); if (IS_ERR(new_nsp->uts_ns)) { err = PTR_ERR(new_nsp->uts_ns); goto out_uts; } - if (new_nsp->uts_ns != tsk->nsproxy->uts_ns) { - put_user_ns(new_nsp->uts_ns->user_ns); - new_nsp->uts_ns->user_ns = task_cred_xxx(tsk, user)->user_ns; - get_user_ns(new_nsp->uts_ns->user_ns); - } new_nsp->ipc_ns = copy_ipcs(flags, tsk->nsproxy->ipc_ns); if (IS_ERR(new_nsp->ipc_ns)) { diff --git a/kernel/sys.c b/kernel/sys.c index 1ad48b3b906..5761c53e19e 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1181,7 +1181,7 @@ SYSCALL_DEFINE2(sethostname, char __user *, name, int, len) int errno; char tmp[__NEW_UTS_LEN]; - if (!capable(CAP_SYS_ADMIN)) + if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; if (len < 0 || len > __NEW_UTS_LEN) return -EINVAL; diff --git a/kernel/utsname.c b/kernel/utsname.c index a7b3a8d1ad2..44646179eab 100644 --- a/kernel/utsname.c +++ b/kernel/utsname.c @@ -31,7 +31,8 @@ static struct uts_namespace *create_uts_ns(void) * @old_ns: namespace to clone * Return NULL on error (failure to kmalloc), new ns otherwise */ -static struct uts_namespace *clone_uts_ns(struct uts_namespace *old_ns) +static struct uts_namespace *clone_uts_ns(struct task_struct *tsk, + struct uts_namespace *old_ns) { struct uts_namespace *ns; @@ -41,8 +42,7 @@ static struct uts_namespace *clone_uts_ns(struct uts_namespace *old_ns) down_read(&uts_sem); memcpy(&ns->name, &old_ns->name, sizeof(ns->name)); - ns->user_ns = old_ns->user_ns; - get_user_ns(ns->user_ns); + ns->user_ns = get_user_ns(task_cred_xxx(tsk, user)->user_ns); up_read(&uts_sem); return ns; } @@ -53,8 +53,10 @@ static struct uts_namespace *clone_uts_ns(struct uts_namespace *old_ns) * utsname of this process won't be seen by parent, and vice * versa. */ -struct uts_namespace *copy_utsname(unsigned long flags, struct uts_namespace *old_ns) +struct uts_namespace *copy_utsname(unsigned long flags, + struct task_struct *tsk) { + struct uts_namespace *old_ns = tsk->nsproxy->uts_ns; struct uts_namespace *new_ns; BUG_ON(!old_ns); @@ -63,7 +65,7 @@ struct uts_namespace *copy_utsname(unsigned long flags, struct uts_namespace *ol if (!(flags & CLONE_NEWUTS)) return old_ns; - new_ns = clone_uts_ns(old_ns); + new_ns = clone_uts_ns(tsk, old_ns); put_uts_ns(old_ns); return new_ns; -- cgit v1.2.3-70-g09d2 From fc832ad3645f0507f24d11752544525a50a83c71 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Wed, 23 Mar 2011 16:43:22 -0700 Subject: userns: user namespaces: convert all capable checks in kernel/sys.c This allows setuid/setgid in containers. It also fixes some corner cases where kernel logic foregoes capability checks when uids are equivalent. The latter will need to be done throughout the whole kernel. Changelog: Jan 11: Use nsown_capable() as suggested by Bastian Blank. Jan 11: Fix logic errors in uid checks pointed out by Bastian. Feb 15: allow prlimit to current (was regression in previous version) Feb 23: remove debugging printks, uninline set_one_prio_perm and make it bool, and document its return value. Signed-off-by: Serge E. Hallyn Acked-by: "Eric W. Biederman" Acked-by: Daniel Lezcano Acked-by: David Howells Cc: James Morris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sys.c | 75 +++++++++++++++++++++++++++++++++++++++--------------------- 1 file changed, 49 insertions(+), 26 deletions(-) (limited to 'kernel/sys.c') diff --git a/kernel/sys.c b/kernel/sys.c index 5761c53e19e..af468edf096 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -119,17 +119,34 @@ EXPORT_SYMBOL(cad_pid); void (*pm_power_off_prepare)(void); +/* + * Returns true if current's euid is same as p's uid or euid, + * or has CAP_SYS_NICE to p's user_ns. + * + * Called with rcu_read_lock, creds are safe + */ +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 && + (pcred->uid == cred->euid || + pcred->euid == cred->euid)) + return true; + if (ns_capable(pcred->user->user_ns, CAP_SYS_NICE)) + return true; + return false; +} + /* * set the priority of a task * - the caller must hold the RCU read lock */ static int set_one_prio(struct task_struct *p, int niceval, int error) { - const struct cred *cred = current_cred(), *pcred = __task_cred(p); int no_nice; - if (pcred->uid != cred->euid && - pcred->euid != cred->euid && !capable(CAP_SYS_NICE)) { + if (!set_one_prio_perm(p)) { error = -EPERM; goto out; } @@ -506,7 +523,7 @@ SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid) if (rgid != (gid_t) -1) { if (old->gid == rgid || old->egid == rgid || - capable(CAP_SETGID)) + nsown_capable(CAP_SETGID)) new->gid = rgid; else goto error; @@ -515,7 +532,7 @@ SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid) if (old->gid == egid || old->egid == egid || old->sgid == egid || - capable(CAP_SETGID)) + nsown_capable(CAP_SETGID)) new->egid = egid; else goto error; @@ -550,7 +567,7 @@ SYSCALL_DEFINE1(setgid, gid_t, gid) old = current_cred(); retval = -EPERM; - if (capable(CAP_SETGID)) + if (nsown_capable(CAP_SETGID)) new->gid = new->egid = new->sgid = new->fsgid = gid; else if (gid == old->gid || gid == old->sgid) new->egid = new->fsgid = gid; @@ -617,7 +634,7 @@ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid) new->uid = ruid; if (old->uid != ruid && old->euid != ruid && - !capable(CAP_SETUID)) + !nsown_capable(CAP_SETUID)) goto error; } @@ -626,7 +643,7 @@ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid) if (old->uid != euid && old->euid != euid && old->suid != euid && - !capable(CAP_SETUID)) + !nsown_capable(CAP_SETUID)) goto error; } @@ -674,7 +691,7 @@ SYSCALL_DEFINE1(setuid, uid_t, uid) old = current_cred(); retval = -EPERM; - if (capable(CAP_SETUID)) { + if (nsown_capable(CAP_SETUID)) { new->suid = new->uid = uid; if (uid != old->uid) { retval = set_user(new); @@ -716,7 +733,7 @@ SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid) old = current_cred(); retval = -EPERM; - if (!capable(CAP_SETUID)) { + if (!nsown_capable(CAP_SETUID)) { if (ruid != (uid_t) -1 && ruid != old->uid && ruid != old->euid && ruid != old->suid) goto error; @@ -780,7 +797,7 @@ SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid) old = current_cred(); retval = -EPERM; - if (!capable(CAP_SETGID)) { + if (!nsown_capable(CAP_SETGID)) { if (rgid != (gid_t) -1 && rgid != old->gid && rgid != old->egid && rgid != old->sgid) goto error; @@ -840,7 +857,7 @@ SYSCALL_DEFINE1(setfsuid, uid_t, uid) if (uid == old->uid || uid == old->euid || uid == old->suid || uid == old->fsuid || - capable(CAP_SETUID)) { + nsown_capable(CAP_SETUID)) { if (uid != old_fsuid) { new->fsuid = uid; if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0) @@ -873,7 +890,7 @@ SYSCALL_DEFINE1(setfsgid, gid_t, gid) if (gid == old->gid || gid == old->egid || gid == old->sgid || gid == old->fsgid || - capable(CAP_SETGID)) { + nsown_capable(CAP_SETGID)) { if (gid != old_fsgid) { new->fsgid = gid; goto change_okay; @@ -1183,6 +1200,7 @@ SYSCALL_DEFINE2(sethostname, char __user *, name, int, len) if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; + if (len < 0 || len > __NEW_UTS_LEN) return -EINVAL; down_write(&uts_sem); @@ -1230,7 +1248,7 @@ SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len) int errno; char tmp[__NEW_UTS_LEN]; - if (!capable(CAP_SYS_ADMIN)) + if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; if (len < 0 || len > __NEW_UTS_LEN) return -EINVAL; @@ -1345,6 +1363,8 @@ int do_prlimit(struct task_struct *tsk, unsigned int resource, rlim = tsk->signal->rlim + resource; task_lock(tsk->group_leader); if (new_rlim) { + /* Keep the capable check against init_user_ns until + cgroups can contain all limits */ if (new_rlim->rlim_max > rlim->rlim_max && !capable(CAP_SYS_RESOURCE)) retval = -EPERM; @@ -1388,19 +1408,22 @@ static int check_prlimit_permission(struct task_struct *task) { const struct cred *cred = current_cred(), *tcred; - tcred = __task_cred(task); - if (current != task && - (cred->uid != tcred->euid || - cred->uid != tcred->suid || - cred->uid != tcred->uid || - cred->gid != tcred->egid || - cred->gid != tcred->sgid || - cred->gid != tcred->gid) && - !capable(CAP_SYS_RESOURCE)) { - return -EPERM; - } + if (current == task) + return 0; - return 0; + tcred = __task_cred(task); + if (cred->user->user_ns == tcred->user->user_ns && + (cred->uid == tcred->euid && + cred->uid == tcred->suid && + cred->uid == tcred->uid && + cred->gid == tcred->egid && + cred->gid == tcred->sgid && + cred->gid == tcred->gid)) + return 0; + if (ns_capable(tcred->user->user_ns, CAP_SYS_RESOURCE)) + return 0; + + return -EPERM; } SYSCALL_DEFINE4(prlimit64, pid_t, pid, unsigned int, resource, -- cgit v1.2.3-70-g09d2