Merge "Enabling kvmfornfv daily job test cases"

[kvmfornfv.git] / kernel / kernel / ptrace.c

diff --git a/kernel/kernel/ptrace.c b/kernel/kernel/ptrace.c
index b8d001b..6947f76 100644 (file)
--- a/kernel/kernel/ptrace.c
+++ b/kernel/kernel/ptrace.c
@@ -39,6 +39,9 @@ void __ptrace_link(struct task_struct *child, struct task_struct *new_parent)
        BUG_ON(!list_empty(&child->ptrace_entry));
        list_add(&child->ptrace_entry, &new_parent->ptraced);
        child->parent = new_parent;
+       rcu_read_lock();
+       child->ptracer_cred = get_cred(__task_cred(new_parent));
+       rcu_read_unlock();
 }
 
 /**
@@ -71,11 +74,15 @@ void __ptrace_link(struct task_struct *child, struct task_struct *new_parent)
  */
 void __ptrace_unlink(struct task_struct *child)
 {
+       const struct cred *old_cred;
        BUG_ON(!child->ptrace);
 
        child->ptrace = 0;
        child->parent = child->real_parent;
        list_del_init(&child->ptrace_entry);
+       old_cred = child->ptracer_cred;
+       child->ptracer_cred = NULL;
+       put_cred(old_cred);
 
        spin_lock(&child->sighand->siglock);
 
@@ -129,12 +136,14 @@ static bool ptrace_freeze_traced(struct task_struct *task)
 
        spin_lock_irq(&task->sighand->siglock);
        if (task_is_traced(task) && !__fatal_signal_pending(task)) {
-               raw_spin_lock_irq(&task->pi_lock);
+               unsigned long flags;
+
+               raw_spin_lock_irqsave(&task->pi_lock, flags);
                if (task->state & __TASK_TRACED)
                        task->state = __TASK_TRACED;
                else
                        task->saved_state = __TASK_TRACED;
-               raw_spin_unlock_irq(&task->pi_lock);
+               raw_spin_unlock_irqrestore(&task->pi_lock, flags);
                ret = true;
        }
        spin_unlock_irq(&task->sighand->siglock);
@@ -224,6 +233,14 @@ static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode)
 static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 {
        const struct cred *cred = current_cred(), *tcred;
+       struct mm_struct *mm;
+       kuid_t caller_uid;
+       kgid_t caller_gid;
+
+       if (!(mode & PTRACE_MODE_FSCREDS) == !(mode & PTRACE_MODE_REALCREDS)) {
+               WARN(1, "denying ptrace access check without PTRACE_MODE_*CREDS\n");
+               return -EPERM;
+       }
 
        /* May we inspect the given task?
         * This check is used both for attaching with ptrace
@@ -233,18 +250,33 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
         * because setting up the necessary parent/child relationship
         * or halting the specified task is impossible.
         */
-       int dumpable = 0;
+
        /* Don't let security modules deny introspection */
        if (same_thread_group(task, current))
                return 0;
        rcu_read_lock();
+       if (mode & PTRACE_MODE_FSCREDS) {
+               caller_uid = cred->fsuid;
+               caller_gid = cred->fsgid;
+       } else {
+               /*
+                * Using the euid would make more sense here, but something
+                * in userland might rely on the old behavior, and this
+                * shouldn't be a security problem since
+                * PTRACE_MODE_REALCREDS implies that the caller explicitly
+                * used a syscall that requests access to another process
+                * (and not a filesystem syscall to procfs).
+                */
+               caller_uid = cred->uid;
+               caller_gid = cred->gid;
+       }
        tcred = __task_cred(task);
-       if (uid_eq(cred->uid, tcred->euid) &&
-           uid_eq(cred->uid, tcred->suid) &&
-           uid_eq(cred->uid, tcred->uid)  &&
-           gid_eq(cred->gid, tcred->egid) &&
-           gid_eq(cred->gid, tcred->sgid) &&
-           gid_eq(cred->gid, tcred->gid))
+       if (uid_eq(caller_uid, tcred->euid) &&
+           uid_eq(caller_uid, tcred->suid) &&
+           uid_eq(caller_uid, tcred->uid)  &&
+           gid_eq(caller_gid, tcred->egid) &&
+           gid_eq(caller_gid, tcred->sgid) &&
+           gid_eq(caller_gid, tcred->gid))
                goto ok;
        if (ptrace_has_cap(tcred->user_ns, mode))
                goto ok;
@@ -252,16 +284,11 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
        return -EPERM;
 ok:
        rcu_read_unlock();
-       smp_rmb();
-       if (task->mm)
-               dumpable = get_dumpable(task->mm);
-       rcu_read_lock();
-       if (dumpable != SUID_DUMP_USER &&
-           !ptrace_has_cap(__task_cred(task)->user_ns, mode)) {
-               rcu_read_unlock();
-               return -EPERM;
-       }
-       rcu_read_unlock();
+       mm = task->mm;
+       if (mm &&
+           ((get_dumpable(mm) != SUID_DUMP_USER) &&
+            !ptrace_has_cap(mm->user_ns, mode)))
+           return -EPERM;
 
        return security_ptrace_access_check(task, mode);
 }
@@ -311,7 +338,7 @@ static int ptrace_attach(struct task_struct *task, long request,
                goto out;
 
        task_lock(task);
-       retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH);
+       retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS);
        task_unlock(task);
        if (retval)
                goto unlock_creds;
@@ -325,10 +352,6 @@ static int ptrace_attach(struct task_struct *task, long request,
 
        if (seize)
                flags |= PT_SEIZED;
-       rcu_read_lock();
-       if (ns_capable(__task_cred(task)->user_ns, CAP_SYS_PTRACE))
-               flags |= PT_PTRACE_CAP;
-       rcu_read_unlock();
        task->ptrace = flags;
 
        __ptrace_link(task, current);
@@ -561,6 +584,19 @@ static int ptrace_setoptions(struct task_struct *child, unsigned long data)
        if (data & ~(unsigned long)PTRACE_O_MASK)
                return -EINVAL;
 
+       if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) {
+               if (!config_enabled(CONFIG_CHECKPOINT_RESTORE) ||
+                   !config_enabled(CONFIG_SECCOMP))
+                       return -EINVAL;
+
+               if (!capable(CAP_SYS_ADMIN))
+                       return -EPERM;
+
+               if (seccomp_mode(&current->seccomp) != SECCOMP_MODE_DISABLED ||
+                   current->ptrace & PT_SUSPEND_SECCOMP)
+                       return -EPERM;
+       }
+
        /* Avoid intermediate state when all opts are cleared */
        flags = child->ptrace;
        flags &= ~(PTRACE_O_MASK << PT_OPT_FLAG_SHIFT);
@@ -1008,6 +1044,11 @@ int ptrace_request(struct task_struct *child, long request,
                break;
        }
 #endif
+
+       case PTRACE_SECCOMP_GET_FILTER:
+               ret = seccomp_get_filter(child, addr, datavp);
+               break;
+
        default:
                break;
        }