1 files changed, 29 insertions, 133 deletions

diff --git a/fs/exec.c b/fs/exec.c
index f45859ad13ac..2a1e5e4042a1 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -78,6 +78,9 @@
 
 #include <trace/events/sched.h>
 
+/* For vma exec functions. */
+#include "../mm/internal.h"
+
 static int bprm_creds_from_file(struct linux_binprm *bprm);
 
 int suid_dumpable = 0;
@@ -111,70 +114,13 @@ static inline void put_binfmt(struct linux_binfmt * fmt)
 
 bool path_noexec(const struct path *path)
 {
+	/* If it's an anonymous inode make sure that we catch any shenanigans. */
+	VFS_WARN_ON_ONCE(IS_ANON_FILE(d_inode(path->dentry)) &&
+			 !(path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC));
 	return (path->mnt->mnt_flags & MNT_NOEXEC) ||
 	       (path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC);
 }
 
-#ifdef CONFIG_USELIB
-/*
- * Note that a shared library must be both readable and executable due to
- * security reasons.
- *
- * Also note that we take the address to load from the file itself.
- */
-SYSCALL_DEFINE1(uselib, const char __user *, library)
-{
-	struct linux_binfmt *fmt;
-	struct file *file;
-	struct filename *tmp = getname(library);
-	int error = PTR_ERR(tmp);
-	static const struct open_flags uselib_flags = {
-		.open_flag = O_LARGEFILE | O_RDONLY,
-		.acc_mode = MAY_READ | MAY_EXEC,
-		.intent = LOOKUP_OPEN,
-		.lookup_flags = LOOKUP_FOLLOW,
-	};
-
-	if (IS_ERR(tmp))
-		goto out;
-
-	file = do_filp_open(AT_FDCWD, tmp, &uselib_flags);
-	putname(tmp);
-	error = PTR_ERR(file);
-	if (IS_ERR(file))
-		goto out;
-
-	/*
-	 * Check do_open_execat() for an explanation.
-	 */
-	error = -EACCES;
-	if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)) ||
-	    path_noexec(&file->f_path))
-		goto exit;
-
-	error = -ENOEXEC;
-
-	read_lock(&binfmt_lock);
-	list_for_each_entry(fmt, &formats, lh) {
-		if (!fmt->load_shlib)
-			continue;
-		if (!try_module_get(fmt->module))
-			continue;
-		read_unlock(&binfmt_lock);
-		error = fmt->load_shlib(file);
-		read_lock(&binfmt_lock);
-		put_binfmt(fmt);
-		if (error != -ENOEXEC)
-			break;
-	}
-	read_unlock(&binfmt_lock);
-exit:
-	fput(file);
-out:
-	return error;
-}
-#endif /* #ifdef CONFIG_USELIB */
-
 #ifdef CONFIG_MMU
 /*
  * The nascent bprm->mm is not visible until exec_mmap() but it can
@@ -242,60 +188,6 @@ static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos,
 	flush_cache_page(bprm->vma, pos, page_to_pfn(page));
 }
 
-static int __bprm_mm_init(struct linux_binprm *bprm)
-{
-	int err;
-	struct vm_area_struct *vma = NULL;
-	struct mm_struct *mm = bprm->mm;
-
-	bprm->vma = vma = vm_area_alloc(mm);
-	if (!vma)
-		return -ENOMEM;
-	vma_set_anonymous(vma);
-
-	if (mmap_write_lock_killable(mm)) {
-		err = -EINTR;
-		goto err_free;
-	}
-
-	/*
-	 * Need to be called with mmap write lock
-	 * held, to avoid race with ksmd.
-	 */
-	err = ksm_execve(mm);
-	if (err)
-		goto err_ksm;
-
-	/*
-	 * Place the stack at the largest stack address the architecture
-	 * supports. Later, we'll move this to an appropriate place. We don't
-	 * use STACK_TOP because that can depend on attributes which aren't
-	 * configured yet.
-	 */
-	BUILD_BUG_ON(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP);
-	vma->vm_end = STACK_TOP_MAX;
-	vma->vm_start = vma->vm_end - PAGE_SIZE;
-	vm_flags_init(vma, VM_SOFTDIRTY | VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP);
-	vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
-
-	err = insert_vm_struct(mm, vma);
-	if (err)
-		goto err;
-
-	mm->stack_vm = mm->total_vm = 1;
-	mmap_write_unlock(mm);
-	bprm->p = vma->vm_end - sizeof(void *);
-	return 0;
-err:
-	ksm_exit(mm);
-err_ksm:
-	mmap_write_unlock(mm);
-err_free:
-	bprm->vma = NULL;
-	vm_area_free(vma);
-	return err;
-}
-
 static bool valid_arg_len(struct linux_binprm *bprm, long len)
 {
 	return len <= MAX_ARG_STRLEN;
@@ -348,12 +240,6 @@ static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos,
 {
 }
 
-static int __bprm_mm_init(struct linux_binprm *bprm)
-{
-	bprm->p = PAGE_SIZE * MAX_ARG_PAGES - sizeof(void *);
-	return 0;
-}
-
 static bool valid_arg_len(struct linux_binprm *bprm, long len)
 {
 	return len <= bprm->p;
@@ -382,9 +268,13 @@ static int bprm_mm_init(struct linux_binprm *bprm)
 	bprm->rlim_stack = current->signal->rlim[RLIMIT_STACK];
 	task_unlock(current->group_leader);
 
-	err = __bprm_mm_init(bprm);
+#ifndef CONFIG_MMU
+	bprm->p = PAGE_SIZE * MAX_ARG_PAGES - sizeof(void *);
+#else
+	err = create_init_stack_vma(bprm->mm, &bprm->vma, &bprm->p);
 	if (err)
 		goto err;
+#endif
 
 	return 0;
 
@@ -714,7 +604,7 @@ int setup_arg_pages(struct linux_binprm *bprm,
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma = bprm->vma;
 	struct vm_area_struct *prev = NULL;
-	unsigned long vm_flags;
+	vm_flags_t vm_flags;
 	unsigned long stack_base;
 	unsigned long stack_size;
 	unsigned long stack_expand;
@@ -894,13 +784,15 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags)
 	if (IS_ERR(file))
 		return file;
 
+	if (path_noexec(&file->f_path))
+		return ERR_PTR(-EACCES);
+
 	/*
 	 * In the past the regular type check was here. It moved to may_open() in
 	 * 633fb6ac3980 ("exec: move S_ISREG() check earlier"). Since then it is
 	 * an invariant that all non-regular files error out before we get here.
 	 */
-	if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)) ||
-	    path_noexec(&file->f_path))
+	if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)))
 		return ERR_PTR(-EACCES);
 
 	err = exe_file_deny_write_access(file);
@@ -1227,13 +1119,12 @@ int begin_new_exec(struct linux_binprm * bprm)
 	 */
 	bprm->point_of_no_return = true;
 
-	/*
-	 * Make this the only thread in the thread group.
-	 */
+	/* Make this the only thread in the thread group */
 	retval = de_thread(me);
 	if (retval)
 		goto out;
-
+	/* see the comment in check_unsafe_exec() */
+	current->fs->in_exec = 0;
 	/*
 	 * Cancel any io_uring activity across execve
 	 */
@@ -1495,6 +1386,8 @@ static void free_bprm(struct linux_binprm *bprm)
 	}
 	free_arg_pages(bprm);
 	if (bprm->cred) {
+		/* in case exec fails before de_thread() succeeds */
+		current->fs->in_exec = 0;
 		mutex_unlock(&current->signal->cred_guard_mutex);
 		abort_creds(bprm->cred);
 	}
@@ -1616,9 +1509,13 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
 	 * suid exec because the differently privileged task
 	 * will be able to manipulate the current directory, etc.
 	 * It would be nice to force an unshare instead...
+	 *
+	 * Otherwise we set fs->in_exec = 1 to deny clone(CLONE_FS)
+	 * from another sub-thread until de_thread() succeeds, this
+	 * state is protected by cred_guard_mutex we hold.
 	 */
 	n_fs = 1;
-	spin_lock(&p->fs->lock);
+	read_seqlock_excl(&p->fs->seq);
 	rcu_read_lock();
 	for_other_threads(p, t) {
 		if (t->fs == p->fs)
@@ -1631,7 +1528,7 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
 		bprm->unsafe |= LSM_UNSAFE_SHARE;
 	else
 		p->fs->in_exec = 1;
-	spin_unlock(&p->fs->lock);
+	read_sequnlock_excl(&p->fs->seq);
 }
 
 static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file)
@@ -1859,10 +1756,9 @@ static int bprm_execve(struct linux_binprm *bprm)
 		goto out;
 
 	sched_mm_cid_after_execve(current);
+	rseq_execve(current);
 	/* execve succeeded */
-	current->fs->in_exec = 0;
 	current->in_execve = 0;
-	rseq_execve(current);
 	user_events_execve(current);
 	acct_update_integrals(current);
 	task_numa_free(current, false);
@@ -1879,7 +1775,7 @@ out:
 		force_fatal_sig(SIGSEGV);
 
 	sched_mm_cid_after_execve(current);
-	current->fs->in_exec = 0;
+	rseq_set_notify_resume(current);
 	current->in_execve = 0;
 
 	return retval;