1 files changed, 271 insertions, 365 deletions

diff --git a/fs/exec.c b/fs/exec.c
index ab913243a367..9d5ebc9d15b0 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -65,6 +65,9 @@
 #include <linux/syscall_user_dispatch.h>
 #include <linux/coredump.h>
 #include <linux/time_namespace.h>
+#include <linux/user_events.h>
+#include <linux/rseq.h>
+#include <linux/ksm.h>
 
 #include <linux/uaccess.h>
 #include <asm/mmu_context.h>
@@ -75,6 +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;
@@ -108,74 +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 | __FMODE_EXEC,
-		.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;
-
-	/*
-	 * may_open() has already checked for this, so it should be
-	 * impossible to trip now. But we need to be extra cautious
-	 * and check again at the very end too.
-	 */
-	error = -EACCES;
-	if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode) ||
-			 path_noexec(&file->f_path)))
-		goto exit;
-
-	fsnotify_open(file);
-
-	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
@@ -199,33 +144,31 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 		int write)
 {
 	struct page *page;
+	struct vm_area_struct *vma = bprm->vma;
+	struct mm_struct *mm = bprm->mm;
 	int ret;
-	unsigned int gup_flags = 0;
-
-#ifdef CONFIG_STACK_GROWSUP
-	if (write) {
-		ret = expand_downwards(bprm->vma, pos);
-		if (ret < 0)
-			return NULL;
-	}
-#endif
 
-	if (write)
-		gup_flags |= FOLL_WRITE;
+	/*
+	 * Avoid relying on expanding the stack down in GUP (which
+	 * does not work for STACK_GROWSUP anyway), and just do it
+	 * ahead of time.
+	 */
+	if (!mmap_read_lock_maybe_expand(mm, vma, pos, write))
+		return NULL;
 
 	/*
 	 * We are doing an exec().  'current' is the process
-	 * doing the exec and bprm->mm is the new process's mm.
+	 * doing the exec and 'mm' is the new process's mm.
 	 */
-	mmap_read_lock(bprm->mm);
-	ret = get_user_pages_remote(bprm->mm, pos, 1, gup_flags,
-			&page, NULL, NULL);
-	mmap_read_unlock(bprm->mm);
+	ret = get_user_pages_remote(mm, pos, 1,
+			write ? FOLL_WRITE : 0,
+			&page, NULL);
+	mmap_read_unlock(mm);
 	if (ret <= 0)
 		return NULL;
 
 	if (write)
-		acct_arg_size(bprm, vma_pages(bprm->vma));
+		acct_arg_size(bprm, vma_pages(vma));
 
 	return page;
 }
@@ -245,50 +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;
-	}
-
-	/*
-	 * 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;
-	vma->vm_flags = 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:
-	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;
@@ -341,12 +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;
@@ -375,9 +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;
 
@@ -469,6 +366,35 @@ static int count_strings_kernel(const char *const *argv)
 	return i;
 }
 
+static inline int bprm_set_stack_limit(struct linux_binprm *bprm,
+				       unsigned long limit)
+{
+#ifdef CONFIG_MMU
+	/* Avoid a pathological bprm->p. */
+	if (bprm->p < limit)
+		return -E2BIG;
+	bprm->argmin = bprm->p - limit;
+#endif
+	return 0;
+}
+static inline bool bprm_hit_stack_limit(struct linux_binprm *bprm)
+{
+#ifdef CONFIG_MMU
+	return bprm->p < bprm->argmin;
+#else
+	return false;
+#endif
+}
+
+/*
+ * Calculate bprm->argmin from:
+ * - _STK_LIM
+ * - ARG_MAX
+ * - bprm->rlim_stack.rlim_cur
+ * - bprm->argc
+ * - bprm->envc
+ * - bprm->p
+ */
 static int bprm_stack_limits(struct linux_binprm *bprm)
 {
 	unsigned long limit, ptr_size;
@@ -488,6 +414,9 @@ static int bprm_stack_limits(struct linux_binprm *bprm)
 	 * of argument strings even with small stacks
 	 */
 	limit = max_t(unsigned long, limit, ARG_MAX);
+	/* Reject totally pathological counts. */
+	if (bprm->argc < 0 || bprm->envc < 0)
+		return -E2BIG;
 	/*
 	 * We must account for the size of all the argv and envp pointers to
 	 * the argv and envp strings, since they will also take up space in
@@ -501,13 +430,14 @@ static int bprm_stack_limits(struct linux_binprm *bprm)
 	 * argc can never be 0, to keep them from walking envp by accident.
 	 * See do_execveat_common().
 	 */
-	ptr_size = (max(bprm->argc, 1) + bprm->envc) * sizeof(void *);
+	if (check_add_overflow(max(bprm->argc, 1), bprm->envc, &ptr_size) ||
+	    check_mul_overflow(ptr_size, sizeof(void *), &ptr_size))
+		return -E2BIG;
 	if (limit <= ptr_size)
 		return -E2BIG;
 	limit -= ptr_size;
 
-	bprm->argmin = bprm->p - limit;
-	return 0;
+	return bprm_set_stack_limit(bprm, limit);
 }
 
 /*
@@ -545,10 +475,8 @@ static int copy_strings(int argc, struct user_arg_ptr argv,
 		pos = bprm->p;
 		str += len;
 		bprm->p -= len;
-#ifdef CONFIG_MMU
-		if (bprm->p < bprm->argmin)
+		if (bprm_hit_stack_limit(bprm))
 			goto out;
-#endif
 
 		while (len > 0) {
 			int offset, bytes_to_copy;
@@ -623,7 +551,7 @@ int copy_string_kernel(const char *arg, struct linux_binprm *bprm)
 	/* We're going to work our way backwards. */
 	arg += len;
 	bprm->p -= len;
-	if (IS_ENABLED(CONFIG_MMU) && bprm->p < bprm->argmin)
+	if (bprm_hit_stack_limit(bprm))
 		return -E2BIG;
 
 	while (len > 0) {
@@ -664,82 +592,6 @@ static int copy_strings_kernel(int argc, const char *const *argv,
 #ifdef CONFIG_MMU
 
 /*
- * During bprm_mm_init(), we create a temporary stack at STACK_TOP_MAX.  Once
- * the binfmt code determines where the new stack should reside, we shift it to
- * its final location.  The process proceeds as follows:
- *
- * 1) Use shift to calculate the new vma endpoints.
- * 2) Extend vma to cover both the old and new ranges.  This ensures the
- *    arguments passed to subsequent functions are consistent.
- * 3) Move vma's page tables to the new range.
- * 4) Free up any cleared pgd range.
- * 5) Shrink the vma to cover only the new range.
- */
-static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
-{
-	struct mm_struct *mm = vma->vm_mm;
-	unsigned long old_start = vma->vm_start;
-	unsigned long old_end = vma->vm_end;
-	unsigned long length = old_end - old_start;
-	unsigned long new_start = old_start - shift;
-	unsigned long new_end = old_end - shift;
-	VMA_ITERATOR(vmi, mm, new_start);
-	struct vm_area_struct *next;
-	struct mmu_gather tlb;
-
-	BUG_ON(new_start > new_end);
-
-	/*
-	 * ensure there are no vmas between where we want to go
-	 * and where we are
-	 */
-	if (vma != vma_next(&vmi))
-		return -EFAULT;
-
-	/*
-	 * cover the whole range: [new_start, old_end)
-	 */
-	if (vma_adjust(vma, new_start, old_end, vma->vm_pgoff, NULL))
-		return -ENOMEM;
-
-	/*
-	 * move the page tables downwards, on failure we rely on
-	 * process cleanup to remove whatever mess we made.
-	 */
-	if (length != move_page_tables(vma, old_start,
-				       vma, new_start, length, false))
-		return -ENOMEM;
-
-	lru_add_drain();
-	tlb_gather_mmu(&tlb, mm);
-	next = vma_next(&vmi);
-	if (new_end > old_start) {
-		/*
-		 * when the old and new regions overlap clear from new_end.
-		 */
-		free_pgd_range(&tlb, new_end, old_end, new_end,
-			next ? next->vm_start : USER_PGTABLES_CEILING);
-	} else {
-		/*
-		 * otherwise, clean from old_start; this is done to not touch
-		 * the address space in [new_end, old_start) some architectures
-		 * have constraints on va-space that make this illegal (IA64) -
-		 * for the others its just a little faster.
-		 */
-		free_pgd_range(&tlb, old_start, old_end, new_end,
-			next ? next->vm_start : USER_PGTABLES_CEILING);
-	}
-	tlb_finish_mmu(&tlb);
-
-	/*
-	 * Shrink the vma to just the new range.  Always succeeds.
-	 */
-	vma_adjust(vma, new_start, new_end, vma->vm_pgoff, NULL);
-
-	return 0;
-}
-
-/*
  * Finalizes the stack vm_area_struct. The flags and permissions are updated,
  * the stack is optionally relocated, and some extra space is added.
  */
@@ -747,17 +599,18 @@ int setup_arg_pages(struct linux_binprm *bprm,
 		    unsigned long stack_top,
 		    int executable_stack)
 {
-	unsigned long ret;
+	int ret;
 	unsigned long stack_shift;
 	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;
 	unsigned long rlim_stack;
 	struct mmu_gather tlb;
+	struct vma_iterator vmi;
 
 #ifdef CONFIG_STACK_GROWSUP
 	/* Limit stack size */
@@ -766,7 +619,8 @@ int setup_arg_pages(struct linux_binprm *bprm,
 	stack_base = calc_max_stack_size(stack_base);
 
 	/* Add space for stack randomization. */
-	stack_base += (STACK_RND_MASK << PAGE_SHIFT);
+	if (current->flags & PF_RANDOMIZE)
+		stack_base += (STACK_RND_MASK << PAGE_SHIFT);
 
 	/* Make sure we didn't let the argument array grow too large. */
 	if (vma->vm_end - vma->vm_start > stack_base)
@@ -791,8 +645,6 @@ int setup_arg_pages(struct linux_binprm *bprm,
 	mm->arg_start = bprm->p;
 #endif
 
-	if (bprm->loader)
-		bprm->loader -= stack_shift;
 	bprm->exec -= stack_shift;
 
 	if (mmap_write_lock_killable(mm))
@@ -812,8 +664,10 @@ int setup_arg_pages(struct linux_binprm *bprm,
 	vm_flags |= mm->def_flags;
 	vm_flags |= VM_STACK_INCOMPLETE_SETUP;
 
+	vma_iter_init(&vmi, mm, vma->vm_start);
+
 	tlb_gather_mmu(&tlb, mm);
-	ret = mprotect_fixup(&tlb, vma, &prev, vma->vm_start, vma->vm_end,
+	ret = mprotect_fixup(&vmi, &tlb, vma, &prev, vma->vm_start, vma->vm_end,
 			vm_flags);
 	tlb_finish_mmu(&tlb);
 
@@ -828,13 +682,18 @@ int setup_arg_pages(struct linux_binprm *bprm,
 
 	/* Move stack pages down in memory. */
 	if (stack_shift) {
-		ret = shift_arg_pages(vma, stack_shift);
+		/*
+		 * During bprm_mm_init(), we create a temporary stack at STACK_TOP_MAX.  Once
+		 * the binfmt code determines where the new stack should reside, we shift it to
+		 * its final location.
+		 */
+		ret = relocate_vma_down(vma, stack_shift);
 		if (ret)
 			goto out_unlock;
 	}
 
 	/* mprotect_fixup is overkill to remove the temporary stack flags */
-	vma->vm_flags &= ~VM_STACK_INCOMPLETE_SETUP;
+	vm_flags_clear(vma, VM_STACK_INCOMPLETE_SETUP);
 
 	stack_expand = 131072UL; /* randomly 32*4k (or 2*64k) pages */
 	stack_size = vma->vm_end - vma->vm_start;
@@ -852,7 +711,7 @@ int setup_arg_pages(struct linux_binprm *bprm,
 	stack_base = vma->vm_end - stack_expand;
 #endif
 	current->mm->start_stack = bprm->p;
-	ret = expand_stack(vma, stack_base);
+	ret = expand_stack_locked(vma, stack_base);
 	if (ret)
 		ret = -EFAULT;
 
@@ -888,6 +747,7 @@ int transfer_args_to_stack(struct linux_binprm *bprm,
 			goto out;
 	}
 
+	bprm->exec += *sp_location - MAX_ARG_PAGES * PAGE_SIZE;
 	*sp_location = sp;
 
 out:
@@ -897,10 +757,14 @@ EXPORT_SYMBOL(transfer_args_to_stack);
 
 #endif /* CONFIG_MMU */
 
+/*
+ * On success, caller must call do_close_execat() on the returned
+ * struct file to close it.
+ */
 static struct file *do_open_execat(int fd, struct filename *name, int flags)
 {
-	struct file *file;
 	int err;
+	struct file *file __free(fput) = NULL;
 	struct open_flags open_exec_flags = {
 		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
 		.acc_mode = MAY_EXEC,
@@ -908,7 +772,8 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags)
 		.lookup_flags = LOOKUP_FOLLOW,
 	};
 
-	if ((flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
+	if ((flags &
+	     ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH | AT_EXECVE_CHECK)) != 0)
 		return ERR_PTR(-EINVAL);
 	if (flags & AT_SYMLINK_NOFOLLOW)
 		open_exec_flags.lookup_flags &= ~LOOKUP_FOLLOW;
@@ -917,33 +782,37 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags)
 
 	file = do_filp_open(fd, name, &open_exec_flags);
 	if (IS_ERR(file))
-		goto out;
+		return file;
+
+	if (path_noexec(&file->f_path))
+		return ERR_PTR(-EACCES);
 
 	/*
-	 * may_open() has already checked for this, so it should be
-	 * impossible to trip now. But we need to be extra cautious
-	 * and check again at the very end too.
+	 * 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.
 	 */
-	err = -EACCES;
-	if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode) ||
-			 path_noexec(&file->f_path)))
-		goto exit;
+	if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)))
+		return ERR_PTR(-EACCES);
 
-	err = deny_write_access(file);
+	err = exe_file_deny_write_access(file);
 	if (err)
-		goto exit;
-
-	if (name->name[0] != '\0')
-		fsnotify_open(file);
-
-out:
-	return file;
+		return ERR_PTR(err);
 
-exit:
-	fput(file);
-	return ERR_PTR(err);
+	return no_free_ptr(file);
 }
 
+/**
+ * open_exec - Open a path name for execution
+ *
+ * @name: path name to open with the intent of executing it.
+ *
+ * Returns ERR_PTR on failure or allocated struct file on success.
+ *
+ * As this is a wrapper for the internal do_open_execat(), callers
+ * must call exe_file_allow_write_access() before fput() on release. Also see
+ * do_close_execat().
+ */
 struct file *open_exec(const char *name)
 {
 	struct filename *filename = getname_kernel(name);
@@ -983,8 +852,6 @@ 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 = down_write_killable(&tsk->signal->exec_update_lock);
 	if (ret)
@@ -1010,6 +877,7 @@ static int exec_mmap(struct mm_struct *mm)
 	active_mm = tsk->active_mm;
 	tsk->active_mm = mm;
 	tsk->mm = mm;
+	mm_init_cid(mm, tsk);
 	/*
 	 * This prevents preemption while active_mm is being loaded and
 	 * it and mm are being updated, which could cause problems for
@@ -1033,7 +901,7 @@ static int exec_mmap(struct mm_struct *mm)
 		mmput(old_mm);
 		return 0;
 	}
-	mmdrop(active_mm);
+	mmdrop_lazy_tlb(active_mm);
 	return 0;
 }
 
@@ -1140,7 +1008,6 @@ static int de_thread(struct task_struct *tsk)
 
 		BUG_ON(leader->exit_state != EXIT_ZOMBIE);
 		leader->exit_state = EXIT_DEAD;
-
 		/*
 		 * We are going to release_task()->ptrace_unlink() silently,
 		 * the tracer can sleep in do_wait(). EXIT_DEAD guarantees
@@ -1209,27 +1076,17 @@ static int unshare_sighand(struct task_struct *me)
 	return 0;
 }
 
-char *__get_task_comm(char *buf, size_t buf_size, struct task_struct *tsk)
-{
-	task_lock(tsk);
-	/* Always NUL terminated and zero-padded */
-	strscpy_pad(buf, tsk->comm, buf_size);
-	task_unlock(tsk);
-	return buf;
-}
-EXPORT_SYMBOL_GPL(__get_task_comm);
-
 /*
- * These functions flushes out all traces of the currently running executable
- * so that a new one can be started
+ * This is unlocked -- the string will always be NUL-terminated, but
+ * may show overlapping contents if racing concurrent reads.
  */
-
 void __set_task_comm(struct task_struct *tsk, const char *buf, bool exec)
 {
-	task_lock(tsk);
+	size_t len = min(strlen(buf), sizeof(tsk->comm) - 1);
+
 	trace_task_rename(tsk, buf);
-	strscpy_pad(tsk->comm, buf, sizeof(tsk->comm));
-	task_unlock(tsk);
+	memcpy(tsk->comm, buf, len);
+	memset(&tsk->comm[len], 0, sizeof(tsk->comm) - len);
 	perf_event_comm(tsk, exec);
 }
 
@@ -1250,17 +1107,24 @@ int begin_new_exec(struct linux_binprm * bprm)
 		return retval;
 
 	/*
-	 * Ensure all future errors are fatal.
+	 * This tracepoint marks the point before flushing the old exec where
+	 * the current task is still unchanged, but errors are fatal (point of
+	 * no return). The later "sched_process_exec" tracepoint is called after
+	 * the current task has successfully switched to the new exec.
 	 */
-	bprm->point_of_no_return = true;
+	trace_sched_prepare_exec(current, bprm);
 
 	/*
-	 * Make this the only thread in the thread group.
+	 * Ensure all future errors are fatal.
 	 */
+	bprm->point_of_no_return = true;
+
+	/* 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
 	 */
@@ -1273,8 +1137,8 @@ int begin_new_exec(struct linux_binprm * bprm)
 
 	/*
 	 * Must be called _before_ exec_mmap() as bprm->mm is
-	 * not visible until then. This also enables the update
-	 * to be lockless.
+	 * not visible until then. Doing it here also ensures
+	 * we don't race against replace_mm_exe_file().
 	 */
 	retval = set_mm_exe_file(bprm->mm, bprm->file);
 	if (retval)
@@ -1359,7 +1223,28 @@ int begin_new_exec(struct linux_binprm * bprm)
 		set_dumpable(current->mm, SUID_DUMP_USER);
 
 	perf_event_exec();
-	__set_task_comm(me, kbasename(bprm->filename), true);
+
+	/*
+	 * If the original filename was empty, alloc_bprm() made up a path
+	 * that will probably not be useful to admins running ps or similar.
+	 * Let's fix it up to be something reasonable.
+	 */
+	if (bprm->comm_from_dentry) {
+		/*
+		 * Hold RCU lock to keep the name from being freed behind our back.
+		 * Use acquire semantics to make sure the terminating NUL from
+		 * __d_alloc() is seen.
+		 *
+		 * Note, we're deliberately sloppy here. We don't need to care about
+		 * detecting a concurrent rename and just want a terminated name.
+		 */
+		rcu_read_lock();
+		__set_task_comm(me, smp_load_acquire(&bprm->file->f_path.dentry->d_name.name),
+				true);
+		rcu_read_unlock();
+	} else {
+		__set_task_comm(me, kbasename(bprm->filename), true);
+	}
 
 	/* An exec changes our domain. We are no longer part of the thread
 	   group */
@@ -1395,10 +1280,9 @@ int begin_new_exec(struct linux_binprm * bprm)
 
 	/* Pass the opened binary to the interpreter. */
 	if (bprm->have_execfd) {
-		retval = get_unused_fd_flags(0);
+		retval = FD_ADD(0, bprm->executable);
 		if (retval < 0)
 			goto out_unlock;
-		fd_install(retval, bprm->executable);
 		bprm->executable = NULL;
 		bprm->execfd = retval;
 	}
@@ -1406,6 +1290,9 @@ int begin_new_exec(struct linux_binprm * bprm)
 
 out_unlock:
 	up_write(&me->signal->exec_update_lock);
+	if (!bprm->cred)
+		mutex_unlock(&me->signal->cred_guard_mutex);
+
 out:
 	return retval;
 }
@@ -1414,15 +1301,15 @@ EXPORT_SYMBOL(begin_new_exec);
 void would_dump(struct linux_binprm *bprm, struct file *file)
 {
 	struct inode *inode = file_inode(file);
-	struct user_namespace *mnt_userns = file_mnt_user_ns(file);
-	if (inode_permission(mnt_userns, inode, MAY_READ) < 0) {
+	struct mnt_idmap *idmap = file_mnt_idmap(file);
+	if (inode_permission(idmap, inode, MAY_READ) < 0) {
 		struct user_namespace *old, *user_ns;
 		bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP;
 
 		/* Ensure mm->user_ns contains the executable */
 		user_ns = old = bprm->mm->user_ns;
 		while ((user_ns != &init_user_ns) &&
-		       !privileged_wrt_inode_uidgid(user_ns, mnt_userns, inode))
+		       !privileged_wrt_inode_uidgid(user_ns, idmap, inode))
 			user_ns = user_ns->parent;
 
 		if (old != user_ns) {
@@ -1481,6 +1368,15 @@ static int prepare_bprm_creds(struct linux_binprm *bprm)
 	return -ENOMEM;
 }
 
+/* Matches do_open_execat() */
+static void do_close_execat(struct file *file)
+{
+	if (!file)
+		return;
+	exe_file_allow_write_access(file);
+	fput(file);
+}
+
 static void free_bprm(struct linux_binprm *bprm)
 {
 	if (bprm->mm) {
@@ -1489,13 +1385,12 @@ 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);
 	}
-	if (bprm->file) {
-		allow_write_access(bprm->file);
-		fput(bprm->file);
-	}
+	do_close_execat(bprm->file);
 	if (bprm->executable)
 		fput(bprm->executable);
 	/* If a binfmt changed the interp, free it. */
@@ -1505,36 +1400,74 @@ static void free_bprm(struct linux_binprm *bprm)
 	kfree(bprm);
 }
 
-static struct linux_binprm *alloc_bprm(int fd, struct filename *filename)
+static struct linux_binprm *alloc_bprm(int fd, struct filename *filename, int flags)
 {
-	struct linux_binprm *bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
+	struct linux_binprm *bprm;
+	struct file *file;
 	int retval = -ENOMEM;
-	if (!bprm)
-		goto out;
+
+	file = do_open_execat(fd, filename, flags);
+	if (IS_ERR(file))
+		return ERR_CAST(file);
+
+	bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
+	if (!bprm) {
+		do_close_execat(file);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	bprm->file = file;
 
 	if (fd == AT_FDCWD || filename->name[0] == '/') {
 		bprm->filename = filename->name;
 	} else {
-		if (filename->name[0] == '\0')
+		if (filename->name[0] == '\0') {
 			bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d", fd);
-		else
+			bprm->comm_from_dentry = 1;
+		} else {
 			bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d/%s",
 						  fd, filename->name);
+		}
 		if (!bprm->fdpath)
 			goto out_free;
 
+		/*
+		 * Record that a name derived from an O_CLOEXEC fd will be
+		 * inaccessible after exec.  This allows the code in exec to
+		 * choose to fail when the executable is not mmaped into the
+		 * interpreter and an open file descriptor is not passed to
+		 * the interpreter.  This makes for a better user experience
+		 * than having the interpreter start and then immediately fail
+		 * when it finds the executable is inaccessible.
+		 */
+		if (get_close_on_exec(fd))
+			bprm->interp_flags |= BINPRM_FLAGS_PATH_INACCESSIBLE;
+
 		bprm->filename = bprm->fdpath;
 	}
 	bprm->interp = bprm->filename;
 
+	/*
+	 * At this point, security_file_open() has already been called (with
+	 * __FMODE_EXEC) and access control checks for AT_EXECVE_CHECK will
+	 * stop just after the security_bprm_creds_for_exec() call in
+	 * bprm_execve().  Indeed, the kernel should not try to parse the
+	 * content of the file with exec_binprm() nor change the calling
+	 * thread, which means that the following security functions will not
+	 * be called:
+	 * - security_bprm_check()
+	 * - security_bprm_creds_from_file()
+	 * - security_bprm_committing_creds()
+	 * - security_bprm_committed_creds()
+	 */
+	bprm->is_check = !!(flags & AT_EXECVE_CHECK);
+
 	retval = bprm_mm_init(bprm);
-	if (retval)
-		goto out_free;
-	return bprm;
+	if (!retval)
+		return bprm;
 
 out_free:
 	free_bprm(bprm);
-out:
 	return ERR_PTR(retval);
 }
 
@@ -1575,32 +1508,37 @@ 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.
 	 */
-	t = p;
 	n_fs = 1;
-	spin_lock(&p->fs->lock);
+	read_seqlock_excl(&p->fs->seq);
 	rcu_read_lock();
-	while_each_thread(p, t) {
+	for_other_threads(p, t) {
 		if (t->fs == p->fs)
 			n_fs++;
 	}
 	rcu_read_unlock();
 
+	/* "users" and "in_exec" locked for copy_fs() */
 	if (p->fs->users > n_fs)
 		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)
 {
 	/* Handle suid and sgid on files */
-	struct user_namespace *mnt_userns;
+	struct mnt_idmap *idmap;
 	struct inode *inode = file_inode(file);
 	unsigned int mode;
 	vfsuid_t vfsuid;
 	vfsgid_t vfsgid;
+	int err;
 
 	if (!mnt_may_suid(file->f_path.mnt))
 		return;
@@ -1612,17 +1550,22 @@ static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file)
 	if (!(mode & (S_ISUID|S_ISGID)))
 		return;
 
-	mnt_userns = file_mnt_user_ns(file);
+	idmap = file_mnt_idmap(file);
 
 	/* Be careful if suid/sgid is set */
 	inode_lock(inode);
 
-	/* reload atomically mode/uid/gid now that lock held */
+	/* Atomically reload and check mode/uid/gid now that lock held. */
 	mode = inode->i_mode;
-	vfsuid = i_uid_into_vfsuid(mnt_userns, inode);
-	vfsgid = i_gid_into_vfsgid(mnt_userns, inode);
+	vfsuid = i_uid_into_vfsuid(idmap, inode);
+	vfsgid = i_gid_into_vfsgid(idmap, inode);
+	err = inode_permission(idmap, inode, MAY_EXEC);
 	inode_unlock(inode);
 
+	/* Did the exec bit vanish out from under us? Give up. */
+	if (err)
+		return;
+
 	/* We ignore suid/sgid if there are no mappings for them in the ns */
 	if (!vfsuid_has_mapping(bprm->cred->user_ns, vfsuid) ||
 	    !vfsgid_has_mapping(bprm->cred->user_ns, vfsgid))
@@ -1672,7 +1615,6 @@ static int prepare_binprm(struct linux_binprm *bprm)
  */
 int remove_arg_zero(struct linux_binprm *bprm)
 {
-	int ret = 0;
 	unsigned long offset;
 	char *kaddr;
 	struct page *page;
@@ -1683,10 +1625,8 @@ int remove_arg_zero(struct linux_binprm *bprm)
 	do {
 		offset = bprm->p & ~PAGE_MASK;
 		page = get_arg_page(bprm, bprm->p, 0);
-		if (!page) {
-			ret = -EFAULT;
-			goto out;
-		}
+		if (!page)
+			return -EFAULT;
 		kaddr = kmap_local_page(page);
 
 		for (; offset < PAGE_SIZE && kaddr[offset];
@@ -1699,20 +1639,16 @@ int remove_arg_zero(struct linux_binprm *bprm)
 
 	bprm->p++;
 	bprm->argc--;
-	ret = 0;
 
-out:
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(remove_arg_zero);
 
-#define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e))
 /*
  * cycle the list of binary formats handler, until one recognizes the image
  */
 static int search_binary_handler(struct linux_binprm *bprm)
 {
-	bool need_retry = IS_ENABLED(CONFIG_MODULES);
 	struct linux_binfmt *fmt;
 	int retval;
 
@@ -1724,8 +1660,6 @@ static int search_binary_handler(struct linux_binprm *bprm)
 	if (retval)
 		return retval;
 
-	retval = -ENOENT;
- retry:
 	read_lock(&binfmt_lock);
 	list_for_each_entry(fmt, &formats, lh) {
 		if (!try_module_get(fmt->module))
@@ -1743,17 +1677,7 @@ static int search_binary_handler(struct linux_binprm *bprm)
 	}
 	read_unlock(&binfmt_lock);
 
-	if (need_retry) {
-		if (printable(bprm->buf[0]) && printable(bprm->buf[1]) &&
-		    printable(bprm->buf[2]) && printable(bprm->buf[3]))
-			return retval;
-		if (request_module("binfmt-%04x", *(ushort *)(bprm->buf + 2)) < 0)
-			return retval;
-		need_retry = false;
-		goto retry;
-	}
-
-	return retval;
+	return -ENOEXEC;
 }
 
 /* binfmt handlers will call back into begin_new_exec() on success. */
@@ -1784,7 +1708,7 @@ static int exec_binprm(struct linux_binprm *bprm)
 		bprm->file = bprm->interpreter;
 		bprm->interpreter = NULL;
 
-		allow_write_access(exec);
+		exe_file_allow_write_access(exec);
 		if (unlikely(bprm->have_execfd)) {
 			if (bprm->executable) {
 				fput(exec);
@@ -1802,13 +1726,8 @@ static int exec_binprm(struct linux_binprm *bprm)
 	return 0;
 }
 
-/*
- * sys_execve() executes a new program.
- */
-static int bprm_execve(struct linux_binprm *bprm,
-		       int fd, struct filename *filename, int flags)
+static int bprm_execve(struct linux_binprm *bprm)
 {
-	struct file *file;
 	int retval;
 
 	retval = prepare_bprm_creds(bprm);
@@ -1822,40 +1741,24 @@ static int bprm_execve(struct linux_binprm *bprm,
 	 */
 	check_unsafe_exec(bprm);
 	current->in_execve = 1;
-
-	file = do_open_execat(fd, filename, flags);
-	retval = PTR_ERR(file);
-	if (IS_ERR(file))
-		goto out_unmark;
+	sched_mm_cid_before_execve(current);
 
 	sched_exec();
 
-	bprm->file = file;
-	/*
-	 * Record that a name derived from an O_CLOEXEC fd will be
-	 * inaccessible after exec.  This allows the code in exec to
-	 * choose to fail when the executable is not mmaped into the
-	 * interpreter and an open file descriptor is not passed to
-	 * the interpreter.  This makes for a better user experience
-	 * than having the interpreter start and then immediately fail
-	 * when it finds the executable is inaccessible.
-	 */
-	if (bprm->fdpath && get_close_on_exec(fd))
-		bprm->interp_flags |= BINPRM_FLAGS_PATH_INACCESSIBLE;
-
 	/* Set the unchanging part of bprm->cred */
 	retval = security_bprm_creds_for_exec(bprm);
-	if (retval)
+	if (retval || bprm->is_check)
 		goto out;
 
 	retval = exec_binprm(bprm);
 	if (retval < 0)
 		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);
 	return retval;
@@ -1870,8 +1773,8 @@ out:
 	if (bprm->point_of_no_return && !fatal_signal_pending(current))
 		force_fatal_sig(SIGSEGV);
 
-out_unmark:
-	current->fs->in_exec = 0;
+	sched_mm_cid_after_execve(current);
+	rseq_force_update();
 	current->in_execve = 0;
 
 	return retval;
@@ -1904,16 +1807,13 @@ static int do_execveat_common(int fd, struct filename *filename,
 	 * further execve() calls fail. */
 	current->flags &= ~PF_NPROC_EXCEEDED;
 
-	bprm = alloc_bprm(fd, filename);
+	bprm = alloc_bprm(fd, filename, flags);
 	if (IS_ERR(bprm)) {
 		retval = PTR_ERR(bprm);
 		goto out_ret;
 	}
 
 	retval = count(argv, MAX_ARG_STRINGS);
-	if (retval == 0)
-		pr_warn_once("process '%s' launched '%s' with NULL argv: empty string added\n",
-			     current->comm, bprm->filename);
 	if (retval < 0)
 		goto out_free;
 	bprm->argc = retval;
@@ -1951,9 +1851,12 @@ static int do_execveat_common(int fd, struct filename *filename,
 		if (retval < 0)
 			goto out_free;
 		bprm->argc = 1;
+
+		pr_warn_once("process '%s' launched '%s' with NULL argv: empty string added\n",
+			     current->comm, bprm->filename);
 	}
 
-	retval = bprm_execve(bprm, fd, filename, flags);
+	retval = bprm_execve(bprm);
 out_free:
 	free_bprm(bprm);
 
@@ -1978,7 +1881,7 @@ int kernel_execve(const char *kernel_filename,
 	if (IS_ERR(filename))
 		return PTR_ERR(filename);
 
-	bprm = alloc_bprm(fd, filename);
+	bprm = alloc_bprm(fd, filename, 0);
 	if (IS_ERR(bprm)) {
 		retval = PTR_ERR(bprm);
 		goto out_ret;
@@ -2013,7 +1916,7 @@ int kernel_execve(const char *kernel_filename,
 	if (retval < 0)
 		goto out_free;
 
-	retval = bprm_execve(bprm, fd, filename, 0);
+	retval = bprm_execve(bprm);
 out_free:
 	free_bprm(bprm);
 out_ret:
@@ -2095,7 +1998,7 @@ void set_dumpable(struct mm_struct *mm, int value)
 	if (WARN_ON((unsigned)value > SUID_DUMP_ROOT))
 		return;
 
-	set_mask_bits(&mm->flags, MMF_DUMPABLE_MASK, value);
+	__mm_flags_set_mask_dumpable(mm, value);
 }
 
 SYSCALL_DEFINE3(execve,
@@ -2139,17 +2042,17 @@ COMPAT_SYSCALL_DEFINE5(execveat, int, fd,
 
 #ifdef CONFIG_SYSCTL
 
-static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write,
+static int proc_dointvec_minmax_coredump(const struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 
-	if (!error)
+	if (!error && write)
 		validate_coredump_safety();
 	return error;
 }
 
-static struct ctl_table fs_exec_sysctls[] = {
+static const struct ctl_table fs_exec_sysctls[] = {
 	{
 		.procname	= "suid_dumpable",
 		.data		= &suid_dumpable,
@@ -2159,7 +2062,6 @@ static struct ctl_table fs_exec_sysctls[] = {
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_TWO,
 	},
-	{ }
 };
 
 static int __init init_fs_exec_sysctls(void)
@@ -2170,3 +2072,7 @@ static int __init init_fs_exec_sysctls(void)
 
 fs_initcall(init_fs_exec_sysctls);
 #endif /* CONFIG_SYSCTL */
+
+#ifdef CONFIG_EXEC_KUNIT_TEST
+#include "tests/exec_kunit.c"
+#endif