Merge branch 'exec-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull execve updates from Eric Biederman:
 "Last cycle for the Nth time I ran into bugs and quality of
  implementation issues related to exec that could not be easily be
  fixed because of the way exec is implemented. So I have been digging
  into exec and cleanup up what I can.

  I don't think I have exec sorted out enough to fix the issues I
  started with but I have made some headway this cycle with 4 sets of
  changes.

   - promised cleanups after introducing exec_update_mutex

   - trivial cleanups for exec

   - control flow simplifications

   - remove the recomputation of bprm->cred

  The net result is code that is a bit easier to understand and work
  with and a decrease in the number of lines of code (if you don't count
  the added tests)"

* 'exec-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (24 commits)
  exec: Compute file based creds only once
  exec: Add a per bprm->file version of per_clear
  binfmt_elf_fdpic: fix execfd build regression
  selftests/exec: Add binfmt_script regression test
  exec: Remove recursion from search_binary_handler
  exec: Generic execfd support
  exec/binfmt_script: Don't modify bprm->buf and then return -ENOEXEC
  exec: Move the call of prepare_binprm into search_binary_handler
  exec: Allow load_misc_binary to call prepare_binprm unconditionally
  exec: Convert security_bprm_set_creds into security_bprm_repopulate_creds
  exec: Factor security_bprm_creds_for_exec out of security_bprm_set_creds
  exec: Teach prepare_exec_creds how exec treats uids & gids
  exec: Set the point of no return sooner
  exec: Move handling of the point of no return to the top level
  exec: Run sync_mm_rss before taking exec_update_mutex
  exec: Fix spelling of search_binary_handler in a comment
  exec: Move the comment from above de_thread to above unshare_sighand
  exec: Rename flush_old_exec begin_new_exec
  exec: Move most of setup_new_exec into flush_old_exec
  exec: In setup_new_exec cache current in the local variable me
  ...

8 files changed, 229 insertions, 274 deletions

diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index 8e8346a81723..3e84e9bb9084 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -151,7 +151,7 @@ static int load_aout_binary(struct linux_binprm * bprm)
 		return -ENOMEM;
 
 	/* Flush all traces of the currently running executable */
-	retval = flush_old_exec(bprm);
+	retval = begin_new_exec(bprm);
 	if (retval)
 		return retval;
 
@@ -174,7 +174,6 @@ static int load_aout_binary(struct linux_binprm * bprm)
 	if (retval < 0)
 		return retval;
 
-	install_exec_creds(bprm);
 
 	if (N_MAGIC(ex) == OMAGIC) {
 		unsigned long text_addr, map_size;
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 8945671fe0e5..44813ceecc47 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -279,8 +279,8 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec,
 		NEW_AUX_ENT(AT_BASE_PLATFORM,
 			    (elf_addr_t)(unsigned long)u_base_platform);
 	}
-	if (bprm->interp_flags & BINPRM_FLAGS_EXECFD) {
-		NEW_AUX_ENT(AT_EXECFD, bprm->interp_data);
+	if (bprm->have_execfd) {
+		NEW_AUX_ENT(AT_EXECFD, bprm->execfd);
 	}
 #undef NEW_AUX_ENT
 	/* AT_NULL is zero; clear the rest too */
@@ -975,7 +975,7 @@ out_free_interp:
 		goto out_free_dentry;
 
 	/* Flush all traces of the currently running executable */
-	retval = flush_old_exec(bprm);
+	retval = begin_new_exec(bprm);
 	if (retval)
 		goto out_free_dentry;
 
@@ -989,7 +989,6 @@ out_free_interp:
 		current->flags |= PF_RANDOMIZE;
 
 	setup_new_exec(bprm);
-	install_exec_creds(bprm);
 
 	/* Do this so that we can load the interpreter, if need be.  We will
 	   change some of these later */
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index d9501a86cec9..aaf332d32326 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -338,7 +338,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 		interp_params.flags |= ELF_FDPIC_FLAG_CONSTDISP;
 
 	/* flush all traces of the currently running executable */
-	retval = flush_old_exec(bprm);
+	retval = begin_new_exec(bprm);
 	if (retval)
 		goto error;
 
@@ -434,7 +434,6 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 	current->mm->start_stack = current->mm->start_brk + stack_size;
 #endif
 
-	install_exec_creds(bprm);
 	if (create_elf_fdpic_tables(bprm, current->mm,
 				    &exec_params, &interp_params) < 0)
 		goto error;
@@ -589,7 +588,7 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
 	nitems = 1 + DLINFO_ITEMS + (k_platform ? 1 : 0) +
 		(k_base_platform ? 1 : 0) + AT_VECTOR_SIZE_ARCH;
 
-	if (bprm->interp_flags & BINPRM_FLAGS_EXECFD)
+	if (bprm->have_execfd)
 		nitems++;
 
 	csp = sp;
@@ -629,10 +628,10 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
 			    (elf_addr_t) (unsigned long) u_base_platform);
 	}
 
-	if (bprm->interp_flags & BINPRM_FLAGS_EXECFD) {
+	if (bprm->have_execfd) {
 		nr = 0;
 		csp -= 2 * sizeof(unsigned long);
-		NEW_AUX_ENT(AT_EXECFD, bprm->interp_data);
+		NEW_AUX_ENT(AT_EXECFD, bprm->execfd);
 	}
 
 	nr = 0;
diff --git a/fs/binfmt_em86.c b/fs/binfmt_em86.c
index 466497860c62..995883693cb2 100644
--- a/fs/binfmt_em86.c
+++ b/fs/binfmt_em86.c
@@ -48,10 +48,6 @@ static int load_em86(struct linux_binprm *bprm)
 	if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
 		return -ENOENT;
 
-	allow_write_access(bprm->file);
-	fput(bprm->file);
-	bprm->file = NULL;
-
 	/* Unlike in the script case, we don't have to do any hairy
 	 * parsing to find our interpreter... it's hardcoded!
 	 */
@@ -89,13 +85,8 @@ static int load_em86(struct linux_binprm *bprm)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	bprm->file = file;
-
-	retval = prepare_binprm(bprm);
-	if (retval < 0)
-		return retval;
-
-	return search_binary_handler(bprm);
+	bprm->interpreter = file;
+	return 0;
 }
 
 static struct linux_binfmt em86_format = {
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index 831a2b25ba79..9b82bc111d0a 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -534,7 +534,7 @@ static int load_flat_file(struct linux_binprm *bprm,
 
 	/* Flush all traces of the currently running executable */
 	if (id == 0) {
-		ret = flush_old_exec(bprm);
+		ret = begin_new_exec(bprm);
 		if (ret)
 			goto err;
 
@@ -963,8 +963,6 @@ static int load_flat_binary(struct linux_binprm *bprm)
 		}
 	}
 
-	install_exec_creds(bprm);
-
 	set_binfmt(&flat_format);
 
 #ifdef CONFIG_MMU
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index cdb45829354d..bc5506619b7e 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -134,7 +134,6 @@ static int load_misc_binary(struct linux_binprm *bprm)
 	Node *fmt;
 	struct file *interp_file = NULL;
 	int retval;
-	int fd_binary = -1;
 
 	retval = -ENOEXEC;
 	if (!enabled)
@@ -160,51 +159,25 @@ static int load_misc_binary(struct linux_binprm *bprm)
 			goto ret;
 	}
 
-	if (fmt->flags & MISC_FMT_OPEN_BINARY) {
+	if (fmt->flags & MISC_FMT_OPEN_BINARY)
+		bprm->have_execfd = 1;
 
-		/* if the binary should be opened on behalf of the
-		 * interpreter than keep it open and assign descriptor
-		 * to it
-		 */
-		fd_binary = get_unused_fd_flags(0);
-		if (fd_binary < 0) {
-			retval = fd_binary;
-			goto ret;
-		}
-		fd_install(fd_binary, bprm->file);
-
-		/* if the binary is not readable than enforce mm->dumpable=0
-		   regardless of the interpreter's permissions */
-		would_dump(bprm, bprm->file);
-
-		allow_write_access(bprm->file);
-		bprm->file = NULL;
-
-		/* mark the bprm that fd should be passed to interp */
-		bprm->interp_flags |= BINPRM_FLAGS_EXECFD;
-		bprm->interp_data = fd_binary;
-
-	} else {
-		allow_write_access(bprm->file);
-		fput(bprm->file);
-		bprm->file = NULL;
-	}
 	/* make argv[1] be the path to the binary */
 	retval = copy_strings_kernel(1, &bprm->interp, bprm);
 	if (retval < 0)
-		goto error;
+		goto ret;
 	bprm->argc++;
 
 	/* add the interp as argv[0] */
 	retval = copy_strings_kernel(1, &fmt->interpreter, bprm);
 	if (retval < 0)
-		goto error;
+		goto ret;
 	bprm->argc++;
 
 	/* Update interp in case binfmt_script needs it. */
 	retval = bprm_change_interp(fmt->interpreter, bprm);
 	if (retval < 0)
-		goto error;
+		goto ret;
 
 	if (fmt->flags & MISC_FMT_OPEN_FILE) {
 		interp_file = file_clone_open(fmt->interp_file);
@@ -215,38 +188,16 @@ static int load_misc_binary(struct linux_binprm *bprm)
 	}
 	retval = PTR_ERR(interp_file);
 	if (IS_ERR(interp_file))
-		goto error;
-
-	bprm->file = interp_file;
-	if (fmt->flags & MISC_FMT_CREDENTIALS) {
-		loff_t pos = 0;
-
-		/*
-		 * No need to call prepare_binprm(), it's already been
-		 * done.  bprm->buf is stale, update from interp_file.
-		 */
-		memset(bprm->buf, 0, BINPRM_BUF_SIZE);
-		retval = kernel_read(bprm->file, bprm->buf, BINPRM_BUF_SIZE,
-				&pos);
-	} else
-		retval = prepare_binprm(bprm);
-
-	if (retval < 0)
-		goto error;
+		goto ret;
 
-	retval = search_binary_handler(bprm);
-	if (retval < 0)
-		goto error;
+	bprm->interpreter = interp_file;
+	if (fmt->flags & MISC_FMT_CREDENTIALS)
+		bprm->execfd_creds = 1;
 
+	retval = 0;
 ret:
 	dput(fmt->dentry);
 	return retval;
-error:
-	if (fd_binary > 0)
-		ksys_close(fd_binary);
-	bprm->interp_flags = 0;
-	bprm->interp_data = 0;
-	goto ret;
 }
 
 /* Command parsers */
diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c
index e9e6a6f4a35f..0e8b953d12cf 100644
--- a/fs/binfmt_script.c
+++ b/fs/binfmt_script.c
@@ -16,14 +16,14 @@
 #include <linux/fs.h>
 
 static inline bool spacetab(char c) { return c == ' ' || c == '\t'; }
-static inline char *next_non_spacetab(char *first, const char *last)
+static inline const char *next_non_spacetab(const char *first, const char *last)
 {
 	for (; first <= last; first++)
 		if (!spacetab(*first))
 			return first;
 	return NULL;
 }
-static inline char *next_terminator(char *first, const char *last)
+static inline const char *next_terminator(const char *first, const char *last)
 {
 	for (; first <= last; first++)
 		if (spacetab(*first) || !*first)
@@ -33,8 +33,7 @@ static inline char *next_terminator(char *first, const char *last)
 
 static int load_script(struct linux_binprm *bprm)
 {
-	const char *i_arg, *i_name;
-	char *cp, *buf_end;
+	const char *i_name, *i_sep, *i_arg, *i_end, *buf_end;
 	struct file *file;
 	int retval;
 
@@ -43,20 +42,6 @@ static int load_script(struct linux_binprm *bprm)
 		return -ENOEXEC;
 
 	/*
-	 * If the script filename will be inaccessible after exec, typically
-	 * because it is a "/dev/fd/<fd>/.." path against an O_CLOEXEC fd, give
-	 * up now (on the assumption that the interpreter will want to load
-	 * this file).
-	 */
-	if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
-		return -ENOENT;
-
-	/* Release since we are not mapping a binary into memory. */
-	allow_write_access(bprm->file);
-	fput(bprm->file);
-	bprm->file = NULL;
-
-	/*
 	 * This section handles parsing the #! line into separate
 	 * interpreter path and argument strings. We must be careful
 	 * because bprm->buf is not yet guaranteed to be NUL-terminated
@@ -71,39 +56,43 @@ static int load_script(struct linux_binprm *bprm)
 	 * parse them on its own.
 	 */
 	buf_end = bprm->buf + sizeof(bprm->buf) - 1;
-	cp = strnchr(bprm->buf, sizeof(bprm->buf), '\n');
-	if (!cp) {
-		cp = next_non_spacetab(bprm->buf + 2, buf_end);
-		if (!cp)
+	i_end = strnchr(bprm->buf, sizeof(bprm->buf), '\n');
+	if (!i_end) {
+		i_end = next_non_spacetab(bprm->buf + 2, buf_end);
+		if (!i_end)
 			return -ENOEXEC; /* Entire buf is spaces/tabs */
 		/*
 		 * If there is no later space/tab/NUL we must assume the
 		 * interpreter path is truncated.
 		 */
-		if (!next_terminator(cp, buf_end))
+		if (!next_terminator(i_end, buf_end))
 			return -ENOEXEC;
-		cp = buf_end;
+		i_end = buf_end;
 	}
-	/* NUL-terminate the buffer and any trailing spaces/tabs. */
-	*cp = '\0';
-	while (cp > bprm->buf) {
-		cp--;
-		if ((*cp == ' ') || (*cp == '\t'))
-			*cp = '\0';
-		else
-			break;
-	}
-	for (cp = bprm->buf+2; (*cp == ' ') || (*cp == '\t'); cp++);
-	if (*cp == '\0')
+	/* Trim any trailing spaces/tabs from i_end */
+	while (spacetab(i_end[-1]))
+		i_end--;
+
+	/* Skip over leading spaces/tabs */
+	i_name = next_non_spacetab(bprm->buf+2, i_end);
+	if (!i_name || (i_name == i_end))
 		return -ENOEXEC; /* No interpreter name found */
-	i_name = cp;
+
+	/* Is there an optional argument? */
 	i_arg = NULL;
-	for ( ; *cp && (*cp != ' ') && (*cp != '\t'); cp++)
-		/* nothing */ ;
-	while ((*cp == ' ') || (*cp == '\t'))
-		*cp++ = '\0';
-	if (*cp)
-		i_arg = cp;
+	i_sep = next_terminator(i_name, i_end);
+	if (i_sep && (*i_sep != '\0'))
+		i_arg = next_non_spacetab(i_sep, i_end);
+
+	/*
+	 * If the script filename will be inaccessible after exec, typically
+	 * because it is a "/dev/fd/<fd>/.." path against an O_CLOEXEC fd, give
+	 * up now (on the assumption that the interpreter will want to load
+	 * this file).
+	 */
+	if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
+		return -ENOENT;
+
 	/*
 	 * OK, we've parsed out the interpreter name and
 	 * (optional) argument.
@@ -121,7 +110,9 @@ static int load_script(struct linux_binprm *bprm)
 	if (retval < 0)
 		return retval;
 	bprm->argc++;
+	*((char *)i_end) = '\0';
 	if (i_arg) {
+		*((char *)i_sep) = '\0';
 		retval = copy_strings_kernel(1, &i_arg, bprm);
 		if (retval < 0)
 			return retval;
@@ -142,11 +133,8 @@ static int load_script(struct linux_binprm *bprm)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	bprm->file = file;
-	retval = prepare_binprm(bprm);
-	if (retval < 0)
-		return retval;
-	return search_binary_handler(bprm);
+	bprm->interpreter = file;
+	return 0;
 }
 
 static struct linux_binfmt script_format = {
diff --git a/fs/exec.c b/fs/exec.c
index 2f0a74582ac9..e850ee7dd636 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -72,6 +72,8 @@
 
 #include <trace/events/sched.h>
 
+static int bprm_creds_from_file(struct linux_binprm *bprm);
+
 int suid_dumpable = 0;
 
 static LIST_HEAD(formats);
@@ -1051,13 +1053,14 @@ static int exec_mmap(struct mm_struct *mm)
 	tsk = current;
 	old_mm = current->mm;
 	exec_mm_release(tsk, old_mm);
+	if (old_mm)
+		sync_mm_rss(old_mm);
 
 	ret = mutex_lock_killable(&tsk->signal->exec_update_mutex);
 	if (ret)
 		return ret;
 
 	if (old_mm) {
-		sync_mm_rss(old_mm);
 		/*
 		 * Make sure that if there is a core dump in progress
 		 * for the old mm, we get out and die instead of going
@@ -1093,12 +1096,6 @@ static int exec_mmap(struct mm_struct *mm)
 	return 0;
 }
 
-/*
- * This function makes sure the current process has its own signal table,
- * so that flush_signal_handlers can later reset the handlers without
- * disturbing other processes.  (Other processes might share the signal
- * table via the CLONE_SIGHAND option to clone().)
- */
 static int de_thread(struct task_struct *tsk)
 {
 	struct signal_struct *sig = tsk->signal;
@@ -1236,6 +1233,12 @@ killed:
 }
 
 
+/*
+ * This function makes sure the current process has its own signal table,
+ * so that flush_signal_handlers can later reset the handlers without
+ * disturbing other processes.  (Other processes might share the signal
+ * table via the CLONE_SIGHAND option to clone().)
+ */
 static int unshare_sighand(struct task_struct *me)
 {
 	struct sighand_struct *oldsighand = me->sighand;
@@ -1292,13 +1295,23 @@ void __set_task_comm(struct task_struct *tsk, const char *buf, bool 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).
+ * (after exec_mmap()) by search_binary_handler (see below).
  */
-int flush_old_exec(struct linux_binprm * bprm)
+int begin_new_exec(struct linux_binprm * bprm)
 {
 	struct task_struct *me = current;
 	int retval;
 
+	/* Once we are committed compute the creds */
+	retval = bprm_creds_from_file(bprm);
+	if (retval)
+		return retval;
+
+	/*
+	 * Ensure all future errors are fatal.
+	 */
+	bprm->point_of_no_return = true;
+
 	/*
 	 * Make this the only thread in the thread group.
 	 */
@@ -1313,7 +1326,10 @@ int flush_old_exec(struct linux_binprm * bprm)
 	 */
 	set_mm_exe_file(bprm->mm, bprm->file);
 
+	/* If the binary is not readable then enforce mm->dumpable=0 */
 	would_dump(bprm, bprm->file);
+	if (bprm->have_execfd)
+		would_dump(bprm, bprm->executable);
 
 	/*
 	 * Release all of the old mmap stuff
@@ -1323,13 +1339,6 @@ int flush_old_exec(struct linux_binprm * bprm)
 	if (retval)
 		goto out;
 
-	/*
-	 * After setting bprm->called_exec_mmap (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->called_exec_mmap = 1;
 	bprm->mm = NULL;
 
 #ifdef CONFIG_POSIX_TIMERS
@@ -1342,7 +1351,7 @@ int flush_old_exec(struct linux_binprm * bprm)
 	 */
 	retval = unshare_sighand(me);
 	if (retval)
-		goto out;
+		goto out_unlock;
 
 	set_fs(USER_DS);
 	me->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD |
@@ -1357,12 +1366,84 @@ int flush_old_exec(struct linux_binprm * bprm)
 	 * undergoing exec(2).
 	 */
 	do_close_on_exec(me->files);
+
+	if (bprm->secureexec) {
+		/* Make sure parent cannot signal privileged process. */
+		me->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 (bprm->rlim_stack.rlim_cur > _STK_LIM)
+			bprm->rlim_stack.rlim_cur = _STK_LIM;
+	}
+
+	me->sas_ss_sp = me->sas_ss_size = 0;
+
+	/*
+	 * Figure out dumpability. Note that this checking only of current
+	 * is wrong, but userspace depends on it. This should be testing
+	 * bprm->secureexec instead.
+	 */
+	if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP ||
+	    !(uid_eq(current_euid(), current_uid()) &&
+	      gid_eq(current_egid(), current_gid())))
+		set_dumpable(current->mm, suid_dumpable);
+	else
+		set_dumpable(current->mm, SUID_DUMP_USER);
+
+	perf_event_exec();
+	__set_task_comm(me, kbasename(bprm->filename), true);
+
+	/* An exec changes our domain. We are no longer part of the thread
+	   group */
+	WRITE_ONCE(me->self_exec_id, me->self_exec_id + 1);
+	flush_signal_handlers(me, 0);
+
+	/*
+	 * install the new credentials for this executable
+	 */
+	security_bprm_committing_creds(bprm);
+
+	commit_creds(bprm->cred);
+	bprm->cred = NULL;
+
+	/*
+	 * Disable monitoring for regular users
+	 * when executing setuid binaries. Must
+	 * wait until new credentials are committed
+	 * by commit_creds() above
+	 */
+	if (get_dumpable(me->mm) != SUID_DUMP_USER)
+		perf_event_exit_task(me);
+	/*
+	 * cred_guard_mutex must be held at least to this point to prevent
+	 * ptrace_attach() from altering our determination of the task's
+	 * credentials; any time after this it may be unlocked.
+	 */
+	security_bprm_committed_creds(bprm);
+
+	/* Pass the opened binary to the interpreter. */
+	if (bprm->have_execfd) {
+		retval = get_unused_fd_flags(0);
+		if (retval < 0)
+			goto out_unlock;
+		fd_install(retval, bprm->executable);
+		bprm->executable = NULL;
+		bprm->execfd = retval;
+	}
 	return 0;
 
+out_unlock:
+	mutex_unlock(&me->signal->exec_update_mutex);
 out:
 	return retval;
 }
-EXPORT_SYMBOL(flush_old_exec);
+EXPORT_SYMBOL(begin_new_exec);
 
 void would_dump(struct linux_binprm *bprm, struct file *file)
 {
@@ -1387,58 +1468,20 @@ 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 (bprm->rlim_stack.rlim_cur > _STK_LIM)
-			bprm->rlim_stack.rlim_cur = _STK_LIM;
-	}
-
-	arch_pick_mmap_layout(current->mm, &bprm->rlim_stack);
-
-	current->sas_ss_sp = current->sas_ss_size = 0;
+	/* Setup things that can depend upon the personality */
+	struct task_struct *me = current;
 
-	/*
-	 * Figure out dumpability. Note that this checking only of current
-	 * is wrong, but userspace depends on it. This should be testing
-	 * bprm->secureexec instead.
-	 */
-	if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP ||
-	    !(uid_eq(current_euid(), current_uid()) &&
-	      gid_eq(current_egid(), current_gid())))
-		set_dumpable(current->mm, suid_dumpable);
-	else
-		set_dumpable(current->mm, SUID_DUMP_USER);
+	arch_pick_mmap_layout(me->mm, &bprm->rlim_stack);
 
 	arch_setup_new_exec();
-	perf_event_exec();
-	__set_task_comm(current, kbasename(bprm->filename), true);
 
 	/* Set the new mm task size. We have to do that late because it may
 	 * depend on TIF_32BIT which is only updated in flush_thread() on
 	 * some architectures like powerpc
 	 */
-	current->mm->task_size = TASK_SIZE;
-
-	/* An exec changes our domain. We are no longer part of the thread
-	   group */
-	WRITE_ONCE(current->self_exec_id, current->self_exec_id + 1);
-	flush_signal_handlers(current, 0);
+	me->mm->task_size = TASK_SIZE;
+	mutex_unlock(&me->signal->exec_update_mutex);
+	mutex_unlock(&me->signal->cred_guard_mutex);
 }
 EXPORT_SYMBOL(setup_new_exec);
 
@@ -1454,7 +1497,7 @@ EXPORT_SYMBOL(finalize_exec);
 
 /*
  * Prepare credentials and lock ->cred_guard_mutex.
- * install_exec_creds() commits the new creds and drops the lock.
+ * setup_new_exec() commits the new creds and drops the lock.
  * Or, if exec fails before, free_bprm() should release ->cred and
  * and unlock.
  */
@@ -1475,8 +1518,6 @@ static void free_bprm(struct linux_binprm *bprm)
 {
 	free_arg_pages(bprm);
 	if (bprm->cred) {
-		if (bprm->called_exec_mmap)
-			mutex_unlock(&current->signal->exec_update_mutex);
 		mutex_unlock(&current->signal->cred_guard_mutex);
 		abort_creds(bprm->cred);
 	}
@@ -1484,6 +1525,8 @@ static void free_bprm(struct linux_binprm *bprm)
 		allow_write_access(bprm->file);
 		fput(bprm->file);
 	}
+	if (bprm->executable)
+		fput(bprm->executable);
 	/* If a binfmt changed the interp, free it. */
 	if (bprm->interp != bprm->filename)
 		kfree(bprm->interp);
@@ -1503,35 +1546,6 @@ int bprm_change_interp(const char *interp, struct linux_binprm *bprm)
 EXPORT_SYMBOL(bprm_change_interp);
 
 /*
- * install the new credentials for this executable
- */
-void install_exec_creds(struct linux_binprm *bprm)
-{
-	security_bprm_committing_creds(bprm);
-
-	commit_creds(bprm->cred);
-	bprm->cred = NULL;
-
-	/*
-	 * Disable monitoring for regular users
-	 * when executing setuid binaries. Must
-	 * wait until new credentials are committed
-	 * by commit_creds() above
-	 */
-	if (get_dumpable(current->mm) != SUID_DUMP_USER)
-		perf_event_exit_task(current);
-	/*
-	 * cred_guard_mutex must be held at least to this point to prevent
-	 * ptrace_attach() from altering our determination of the task's
-	 * credentials; any time after this it may be unlocked.
-	 */
-	security_bprm_committed_creds(bprm);
-	mutex_unlock(&current->signal->exec_update_mutex);
-	mutex_unlock(&current->signal->cred_guard_mutex);
-}
-EXPORT_SYMBOL(install_exec_creds);
-
-/*
  * determine how safe it is to execute the proposed program
  * - the caller must hold ->cred_guard_mutex to protect against
  *   PTRACE_ATTACH or seccomp thread-sync
@@ -1568,29 +1582,21 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
 	spin_unlock(&p->fs->lock);
 }
 
-static void bprm_fill_uid(struct linux_binprm *bprm)
+static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file)
 {
+	/* Handle suid and sgid on files */
 	struct inode *inode;
 	unsigned int mode;
 	kuid_t uid;
 	kgid_t gid;
 
-	/*
-	 * Since this can be called multiple times (via prepare_binprm),
-	 * we must clear any previous work done when setting set[ug]id
-	 * bits from any earlier bprm->file uses (for example when run
-	 * first for a setuid script then again for its interpreter).
-	 */
-	bprm->cred->euid = current_euid();
-	bprm->cred->egid = current_egid();
-
-	if (!mnt_may_suid(bprm->file->f_path.mnt))
+	if (!mnt_may_suid(file->f_path.mnt))
 		return;
 
 	if (task_no_new_privs(current))
 		return;
 
-	inode = bprm->file->f_path.dentry->d_inode;
+	inode = file->f_path.dentry->d_inode;
 	mode = READ_ONCE(inode->i_mode);
 	if (!(mode & (S_ISUID|S_ISGID)))
 		return;
@@ -1621,30 +1627,31 @@ static void bprm_fill_uid(struct linux_binprm *bprm)
 }
 
 /*
+ * Compute brpm->cred based upon the final binary.
+ */
+static int bprm_creds_from_file(struct linux_binprm *bprm)
+{
+	/* Compute creds based on which file? */
+	struct file *file = bprm->execfd_creds ? bprm->executable : bprm->file;
+
+	bprm_fill_uid(bprm, file);
+	return security_bprm_creds_from_file(bprm, file);
+}
+
+/*
  * Fill the binprm structure from the inode.
- * Check permissions, then read the first BINPRM_BUF_SIZE bytes
+ * Read the first BINPRM_BUF_SIZE bytes
  *
  * This may be called multiple times for binary chains (scripts for example).
  */
-int prepare_binprm(struct linux_binprm *bprm)
+static int prepare_binprm(struct linux_binprm *bprm)
 {
-	int retval;
 	loff_t pos = 0;
 
-	bprm_fill_uid(bprm);
-
-	/* fill in binprm security blob */
-	retval = security_bprm_set_creds(bprm);
-	if (retval)
-		return retval;
-	bprm->called_set_creds = 1;
-
 	memset(bprm->buf, 0, BINPRM_BUF_SIZE);
 	return kernel_read(bprm->file, bprm->buf, BINPRM_BUF_SIZE, &pos);
 }
 
-EXPORT_SYMBOL(prepare_binprm);
-
 /*
  * Arguments are '\0' separated strings found at the location bprm->p
  * points to; chop off the first by relocating brpm->p to right after
@@ -1690,15 +1697,15 @@ EXPORT_SYMBOL(remove_arg_zero);
 /*
  * cycle the list of binary formats handler, until one recognizes the image
  */
-int search_binary_handler(struct linux_binprm *bprm)
+static int search_binary_handler(struct linux_binprm *bprm)
 {
 	bool need_retry = IS_ENABLED(CONFIG_MODULES);
 	struct linux_binfmt *fmt;
 	int retval;
 
-	/* This allows 4 levels of binfmt rewrites before failing hard. */
-	if (bprm->recursion_depth > 5)
-		return -ELOOP;
+	retval = prepare_binprm(bprm);
+	if (retval < 0)
+		return retval;
 
 	retval = security_bprm_check(bprm);
 	if (retval)
@@ -1712,19 +1719,11 @@ int search_binary_handler(struct linux_binprm *bprm)
 			continue;
 		read_unlock(&binfmt_lock);
 
-		bprm->recursion_depth++;
 		retval = fmt->load_binary(bprm);
-		bprm->recursion_depth--;
 
 		read_lock(&binfmt_lock);
 		put_binfmt(fmt);
-		if (retval < 0 && bprm->called_exec_mmap) {
-			/* we got to flush_old_exec() and failed after it */
-			read_unlock(&binfmt_lock);
-			force_sigsegv(SIGSEGV);
-			return retval;
-		}
-		if (retval != -ENOEXEC || !bprm->file) {
+		if (bprm->point_of_no_return || (retval != -ENOEXEC)) {
 			read_unlock(&binfmt_lock);
 			return retval;
 		}
@@ -1743,12 +1742,11 @@ int search_binary_handler(struct linux_binprm *bprm)
 
 	return retval;
 }
-EXPORT_SYMBOL(search_binary_handler);
 
 static int exec_binprm(struct linux_binprm *bprm)
 {
 	pid_t old_pid, old_vpid;
-	int ret;
+	int ret, depth;
 
 	/* Need to fetch pid before load_binary changes it */
 	old_pid = current->pid;
@@ -1756,15 +1754,38 @@ static int exec_binprm(struct linux_binprm *bprm)
 	old_vpid = task_pid_nr_ns(current, task_active_pid_ns(current->parent));
 	rcu_read_unlock();
 
-	ret = search_binary_handler(bprm);
-	if (ret >= 0) {
-		audit_bprm(bprm);
-		trace_sched_process_exec(current, old_pid, bprm);
-		ptrace_event(PTRACE_EVENT_EXEC, old_vpid);
-		proc_exec_connector(current);
+	/* This allows 4 levels of binfmt rewrites before failing hard. */
+	for (depth = 0;; depth++) {
+		struct file *exec;
+		if (depth > 5)
+			return -ELOOP;
+
+		ret = search_binary_handler(bprm);
+		if (ret < 0)
+			return ret;
+		if (!bprm->interpreter)
+			break;
+
+		exec = bprm->file;
+		bprm->file = bprm->interpreter;
+		bprm->interpreter = NULL;
+
+		allow_write_access(exec);
+		if (unlikely(bprm->have_execfd)) {
+			if (bprm->executable) {
+				fput(exec);
+				return -ENOEXEC;
+			}
+			bprm->executable = exec;
+		} else
+			fput(exec);
 	}
 
-	return ret;
+	audit_bprm(bprm);
+	trace_sched_process_exec(current, old_pid, bprm);
+	ptrace_event(PTRACE_EVENT_EXEC, old_vpid);
+	proc_exec_connector(current);
+	return 0;
 }
 
 /*
@@ -1857,8 +1878,9 @@ static int __do_execve_file(int fd, struct filename *filename,
 	if (retval < 0)
 		goto out;
 
-	retval = prepare_binprm(bprm);
-	if (retval < 0)
+	/* Set the unchanging part of bprm->cred */
+	retval = security_bprm_creds_for_exec(bprm);
+	if (retval)
 		goto out;
 
 	retval = copy_strings_kernel(1, &bprm->filename, bprm);
@@ -1893,6 +1915,14 @@ static int __do_execve_file(int fd, struct filename *filename,
 	return retval;
 
 out:
+	/*
+	 * If past the point of no return ensure the the code never
+	 * returns to the userspace process.  Use an existing fatal
+	 * signal if present otherwise terminate the process with
+	 * SIGSEGV.
+	 */
+	if (bprm->point_of_no_return && !fatal_signal_pending(current))
+		force_sigsegv(SIGSEGV);
 	if (bprm->mm) {
 		acct_arg_size(bprm, 0);
 		mmput(bprm->mm);