1 files changed, 65 insertions, 30 deletions

diff --git a/kernel/sys.c b/kernel/sys.c
index 7f5a0cd296a9..e4128b278f23 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -37,12 +37,15 @@
 #include <linux/ptrace.h>
 #include <linux/fs_struct.h>
 #include <linux/gfp.h>
+#include <linux/syscore_ops.h>
 
 #include <linux/compat.h>
 #include <linux/syscalls.h>
 #include <linux/kprobes.h>
 #include <linux/user_namespace.h>
 
+#include <linux/kmsg_dump.h>
+
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <asm/unistd.h>
@@ -117,16 +120,33 @@ 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;
         }
@@ -285,6 +305,7 @@ out_unlock:
  */
 void emergency_restart(void)
 {
+        kmsg_dump(KMSG_DUMP_EMERG);
         machine_emergency_restart();
 }
 EXPORT_SYMBOL_GPL(emergency_restart);
@@ -293,8 +314,9 @@ void kernel_restart_prepare(char *cmd)
 {
         blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
         system_state = SYSTEM_RESTART;
+        usermodehelper_disable();
         device_shutdown();
-        sysdev_shutdown();
+        syscore_shutdown();
 }
 
 /**
@@ -312,6 +334,7 @@ void kernel_restart(char *cmd)
                 printk(KERN_EMERG "Restarting system.\n");
         else
                 printk(KERN_EMERG "Restarting system with command '%s'.\n", cmd);
+        kmsg_dump(KMSG_DUMP_RESTART);
         machine_restart(cmd);
 }
 EXPORT_SYMBOL_GPL(kernel_restart);
@@ -321,6 +344,7 @@ static void kernel_shutdown_prepare(enum system_states state)
         blocking_notifier_call_chain(&reboot_notifier_list,
                 (state == SYSTEM_HALT)?SYS_HALT:SYS_POWER_OFF, NULL);
         system_state = state;
+        usermodehelper_disable();
         device_shutdown();
 }
 /**
@@ -331,8 +355,9 @@ static void kernel_shutdown_prepare(enum system_states state)
 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();
 }
 
@@ -349,8 +374,9 @@ void kernel_power_off(void)
         if (pm_power_off_prepare)
                 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();
 }
 EXPORT_SYMBOL_GPL(kernel_power_off);
@@ -496,7 +522,7 @@ 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;
@@ -505,7 +531,7 @@ 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;
@@ -540,7 +566,7 @@ 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;
@@ -607,7 +633,7 @@ 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;
         }
 
@@ -616,7 +642,7 @@ 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;
         }
 
@@ -664,7 +690,7 @@ 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);
@@ -706,7 +732,7 @@ 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;
@@ -770,7 +796,7 @@ 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;
@@ -830,7 +856,7 @@ 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)
@@ -863,7 +889,7 @@ 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;
@@ -1080,8 +1106,10 @@ SYSCALL_DEFINE0(setsid)
         err = session;
 out:
         write_unlock_irq(&tasklist_lock);
-        if (err > 0)
+        if (err > 0) {
                 proc_sid_connector(group_leader);
+                sched_autogroup_create_attach(group_leader);
+        }
         return err;
 }
 
@@ -1169,8 +1197,9 @@ 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;
         down_write(&uts_sem);
@@ -1218,7 +1247,7 @@ 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;
@@ -1333,6 +1362,8 @@ 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;
@@ -1376,18 +1407,22 @@ static int check_prlimit_permission(struct task_struct *task)
 {
         const struct cred *cred = current_cred(), *tcred;
 
-        tcred = __task_cred(task);
-        if ((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,