Merge tag 'secureexec-v4.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux

Pull secureexec update from Kees Cook:
 "This series has the ultimate goal of providing a sane stack rlimit
  when running set*id processes.

  To do this, the bprm_secureexec LSM hook is collapsed into the
  bprm_set_creds hook so the secureexec-ness of an exec can be
  determined early enough to make decisions about rlimits and the
  resulting memory layouts. Other logic acting on the secureexec-ness of
  an exec is similarly consolidated. Capabilities needed some special
  handling, but the refactoring removed other special handling, so that
  was a wash"

* tag 'secureexec-v4.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux:
  exec: Consolidate pdeath_signal clearing
  exec: Use sane stack rlimit under secureexec
  exec: Consolidate dumpability logic
  smack: Remove redundant pdeath_signal clearing
  exec: Use secureexec for clearing pdeath_signal
  exec: Use secureexec for setting dumpability
  LSM: drop bprm_secureexec hook
  commoncap: Move cap_elevated calculation into bprm_set_creds
  commoncap: Refactor to remove bprm_secureexec hook
  smack: Refactor to remove bprm_secureexec hook
  selinux: Refactor to remove bprm_secureexec hook
  apparmor: Refactor to remove bprm_secureexec hook
  binfmt: Introduce secureexec flag
  exec: Correct comments about "point of no return"
  exec: Rename bprm->cred_prepared to called_set_creds

4 files changed, 44 insertions, 18 deletions

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 6466153f2bf0..ec45d24875b1 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -252,7 +252,7 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
 	NEW_AUX_ENT(AT_EUID, from_kuid_munged(cred->user_ns, cred->euid));
 	NEW_AUX_ENT(AT_GID, from_kgid_munged(cred->user_ns, cred->gid));
 	NEW_AUX_ENT(AT_EGID, from_kgid_munged(cred->user_ns, cred->egid));
- 	NEW_AUX_ENT(AT_SECURE, security_bprm_secureexec(bprm));
+	NEW_AUX_ENT(AT_SECURE, bprm->secureexec);
 	NEW_AUX_ENT(AT_RANDOM, (elf_addr_t)(unsigned long)u_rand_bytes);
 #ifdef ELF_HWCAP2
 	NEW_AUX_ENT(AT_HWCAP2, ELF_HWCAP2);
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index cf93a4fad012..5aa9199dfb13 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -650,7 +650,7 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
 	NEW_AUX_ENT(AT_EUID,	(elf_addr_t) from_kuid_munged(cred->user_ns, cred->euid));
 	NEW_AUX_ENT(AT_GID,	(elf_addr_t) from_kgid_munged(cred->user_ns, cred->gid));
 	NEW_AUX_ENT(AT_EGID,	(elf_addr_t) from_kgid_munged(cred->user_ns, cred->egid));
-	NEW_AUX_ENT(AT_SECURE,	security_bprm_secureexec(bprm));
+	NEW_AUX_ENT(AT_SECURE,	bprm->secureexec);
 	NEW_AUX_ENT(AT_EXECFN,	bprm->exec);
 
 #ifdef ARCH_DLINFO
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index a1e6860b6f46..604a176df0c2 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -890,7 +890,7 @@ static int load_flat_shared_library(int id, struct lib_info *libs)
 	 * as we're past the point of no return and are dealing with shared
 	 * libraries.
 	 */
-	bprm.cred_prepared = 1;
+	bprm.called_set_creds = 1;
 
 	res = prepare_binprm(&bprm);
 
diff --git a/fs/exec.c b/fs/exec.c
index 62175cbcc801..01a9fb9d8ac3 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1259,6 +1259,12 @@ void __set_task_comm(struct task_struct *tsk, const char *buf, bool exec)
 	perf_event_comm(tsk, exec);
 }
 
+/*
+ * Calling this is the point of no return. None of the failures will be
+ * seen by userspace since either the process is already taking a fatal
+ * signal (via de_thread() or coredump), or will have SEGV raised
+ * (after exec_mmap()) by search_binary_handlers (see below).
+ */
 int flush_old_exec(struct linux_binprm * bprm)
 {
 	int retval;
@@ -1286,7 +1292,13 @@ int flush_old_exec(struct linux_binprm * bprm)
 	if (retval)
 		goto out;
 
-	bprm->mm = NULL;		/* We're using it now */
+	/*
+	 * After clearing bprm->mm (to mark that current is using the
+	 * prepared mm now), we have nothing left of the original
+	 * process. If anything from here on returns an error, the check
+	 * in search_binary_handler() will SEGV current.
+	 */
+	bprm->mm = NULL;
 
 	set_fs(USER_DS);
 	current->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD |
@@ -1331,15 +1343,38 @@ EXPORT_SYMBOL(would_dump);
 
 void setup_new_exec(struct linux_binprm * bprm)
 {
+	/*
+	 * Once here, prepare_binrpm() will not be called any more, so
+	 * the final state of setuid/setgid/fscaps can be merged into the
+	 * secureexec flag.
+	 */
+	bprm->secureexec |= bprm->cap_elevated;
+
+	if (bprm->secureexec) {
+		/* Make sure parent cannot signal privileged process. */
+		current->pdeath_signal = 0;
+
+		/*
+		 * For secureexec, reset the stack limit to sane default to
+		 * avoid bad behavior from the prior rlimits. This has to
+		 * happen before arch_pick_mmap_layout(), which examines
+		 * RLIMIT_STACK, but after the point of no return to avoid
+		 * needing to clean up the change on failure.
+		 */
+		if (current->signal->rlim[RLIMIT_STACK].rlim_cur > _STK_LIM)
+			current->signal->rlim[RLIMIT_STACK].rlim_cur = _STK_LIM;
+	}
+
 	arch_pick_mmap_layout(current->mm);
 
-	/* This is the point of no return */
 	current->sas_ss_sp = current->sas_ss_size = 0;
 
-	if (uid_eq(current_euid(), current_uid()) && gid_eq(current_egid(), current_gid()))
-		set_dumpable(current->mm, SUID_DUMP_USER);
-	else
+	/* Figure out dumpability. */
+	if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP ||
+	    bprm->secureexec)
 		set_dumpable(current->mm, suid_dumpable);
+	else
+		set_dumpable(current->mm, SUID_DUMP_USER);
 
 	arch_setup_new_exec();
 	perf_event_exec();
@@ -1351,15 +1386,6 @@ void setup_new_exec(struct linux_binprm * bprm)
 	 */
 	current->mm->task_size = TASK_SIZE;
 
-	/* install the new credentials */
-	if (!uid_eq(bprm->cred->uid, current_euid()) ||
-	    !gid_eq(bprm->cred->gid, current_egid())) {
-		current->pdeath_signal = 0;
-	} else {
-		if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP)
-			set_dumpable(current->mm, suid_dumpable);
-	}
-
 	/* An exec changes our domain. We are no longer part of the thread
 	   group */
 	current->self_exec_id++;
@@ -1548,7 +1574,7 @@ int prepare_binprm(struct linux_binprm *bprm)
 	retval = security_bprm_set_creds(bprm);
 	if (retval)
 		return retval;
-	bprm->cred_prepared = 1;
+	bprm->called_set_creds = 1;
 
 	memset(bprm->buf, 0, BINPRM_BUF_SIZE);
 	return kernel_read(bprm->file, 0, bprm->buf, BINPRM_BUF_SIZE);