[PATCH 4.8 41/85] mm: Add a user_ns owner to mm_struct and fix ptrace permission checks

[Greg Kroah-Hartman <gregkh@linuxfoundation.org>]

4.8-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Eric W. Biederman <ebiederm@xmission.com>

commit bfedb589252c01fa505ac9f6f2a3d5d68d707ef4 upstream.

During exec dumpable is cleared if the file that is being executed is
not readable by the user executing the file.  A bug in
ptrace_may_access allows reading the file if the executable happens to
enter into a subordinate user namespace (aka clone(CLONE_NEWUSER),
unshare(CLONE_NEWUSER), or setns(fd, CLONE_NEWUSER).

This problem is fixed with only necessary userspace breakage by adding
a user namespace owner to mm_struct, captured at the time of exec, so
it is clear in which user namespace CAP_SYS_PTRACE must be present in
to be able to safely give read permission to the executable.

The function ptrace_may_access is modified to verify that the ptracer
has CAP_SYS_ADMIN in task->mm->user_ns instead of task->cred->user_ns.
This ensures that if the task changes it's cred into a subordinate
user namespace it does not become ptraceable.

The function ptrace_attach is modified to only set PT_PTRACE_CAP when
CAP_SYS_PTRACE is held over task->mm->user_ns.  The intent of
PT_PTRACE_CAP is to be a flag to note that whatever permission changes
the task might go through the tracer has sufficient permissions for
it not to be an issue.  task->cred->user_ns is always the same
as or descendent of mm->user_ns.  Which guarantees that having
CAP_SYS_PTRACE over mm->user_ns is the worst case for the tasks
credentials.

To prevent regressions mm->dumpable and mm->user_ns are not considered
when a task has no mm.  As simply failing ptrace_may_attach causes
regressions in privileged applications attempting to read things
such as /proc/<pid>/stat

Acked-by: Kees Cook <keescook@chromium.org>
Tested-by: Cyrill Gorcunov <gorcunov@openvz.org>
Fixes: 8409cca70561 ("userns: allow ptrace from non-init user namespaces")
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 include/linux/mm_types.h |    1 +
 kernel/fork.c            |    9 ++++++---
 kernel/ptrace.c          |   26 +++++++++++---------------
 mm/init-mm.c             |    2 ++
 4 files changed, 20 insertions(+), 18 deletions(-)

--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -473,6 +473,7 @@ struct mm_struct {
 	 */
 	struct task_struct __rcu *owner;
 #endif
+	struct user_namespace *user_ns;
 
 	/* store ref to file /proc/<pid>/exe symlink points to */
 	struct file __rcu *exe_file;
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -598,7 +598,8 @@ static void mm_init_owner(struct mm_stru
 #endif
 }
 
-static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
+static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
+	struct user_namespace *user_ns)
 {
 	mm->mmap = NULL;
 	mm->mm_rb = RB_ROOT;
@@ -638,6 +639,7 @@ static struct mm_struct *mm_init(struct
 	if (init_new_context(p, mm))
 		goto fail_nocontext;
 
+	mm->user_ns = get_user_ns(user_ns);
 	return mm;
 
 fail_nocontext:
@@ -683,7 +685,7 @@ struct mm_struct *mm_alloc(void)
 		return NULL;
 
 	memset(mm, 0, sizeof(*mm));
-	return mm_init(mm, current);
+	return mm_init(mm, current, current_user_ns());
 }
 
 /*
@@ -698,6 +700,7 @@ void __mmdrop(struct mm_struct *mm)
 	destroy_context(mm);
 	mmu_notifier_mm_destroy(mm);
 	check_mm(mm);
+	put_user_ns(mm->user_ns);
 	free_mm(mm);
 }
 EXPORT_SYMBOL_GPL(__mmdrop);
@@ -977,7 +980,7 @@ static struct mm_struct *dup_mm(struct t
 
 	memcpy(mm, oldmm, sizeof(*mm));
 
-	if (!mm_init(mm, tsk))
+	if (!mm_init(mm, tsk, mm->user_ns))
 		goto fail_nomem;
 
 	err = dup_mmap(mm, oldmm);
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -218,7 +218,7 @@ static int ptrace_has_cap(struct user_na
 static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 {
 	const struct cred *cred = current_cred(), *tcred;
-	int dumpable = 0;
+	struct mm_struct *mm;
 	kuid_t caller_uid;
 	kgid_t caller_gid;
 
@@ -269,16 +269,11 @@ static int __ptrace_may_access(struct ta
 	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);
 }
@@ -329,6 +324,11 @@ static int ptrace_attach(struct task_str
 
 	task_lock(task);
 	retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS);
+	if (!retval) {
+		struct mm_struct *mm = task->mm;
+		if (mm && ns_capable(mm->user_ns, CAP_SYS_PTRACE))
+			flags |= PT_PTRACE_CAP;
+	}
 	task_unlock(task);
 	if (retval)
 		goto unlock_creds;
@@ -342,10 +342,6 @@ static int ptrace_attach(struct task_str
 
 	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);
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -6,6 +6,7 @@
 #include <linux/cpumask.h>
 
 #include <linux/atomic.h>
+#include <linux/user_namespace.h>
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
 
@@ -21,5 +22,6 @@ struct mm_struct init_mm = {
 	.mmap_sem	= __RWSEM_INITIALIZER(init_mm.mmap_sem),
 	.page_table_lock =  __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
 	.mmlist		= LIST_HEAD_INIT(init_mm.mmlist),
+	.user_ns	= &init_user_ns,
 	INIT_MM_CONTEXT(init_mm)
 };