From f313c51d26aa87e69633c9b46efb37a930faca71 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 19 Jun 2023 11:34:15 -0700 Subject: execve: expand new process stack manually ahead of time This is a small step towards a model where GUP itself would not expand the stack, and any user that needs GUP to not look up existing mappings, but actually expand on them, would have to do so manually before-hand, and with the mm lock held for writing. It turns out that execve() already did almost exactly that, except it didn't take the mm lock at all (it's single-threaded so no locking technically needed, but it could cause lockdep errors). And it only did it for the CONFIG_STACK_GROWSUP case, since in that case GUP has obviously never expanded the stack downwards. So just make that CONFIG_STACK_GROWSUP case do the right thing with locking, and enable it generally. This will eventually help GUP, and in the meantime avoids a special case and the lockdep issue. Signed-off-by: Linus Torvalds --- fs/exec.c | 37 +++++++++++++++++++++---------------- 1 file changed, 21 insertions(+), 16 deletions(-) (limited to 'fs/exec.c') diff --git a/fs/exec.c b/fs/exec.c index a61eb256e5e4..66e3e22ffb8a 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -200,34 +200,39 @@ 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) { - /* We claim to hold the lock - nobody to race with */ - ret = expand_downwards(bprm->vma, pos, true); - if (ret < 0) + /* + * Avoid relying on expanding the stack down in GUP (which + * does not work for STACK_GROWSUP anyway), and just do it + * by hand ahead of time. + */ + if (write && pos < vma->vm_start) { + mmap_write_lock(mm); + ret = expand_downwards(vma, pos, true); + if (unlikely(ret < 0)) { + mmap_write_unlock(mm); return NULL; - } -#endif - - if (write) - gup_flags |= FOLL_WRITE; + } + mmap_write_downgrade(mm); + } else + mmap_read_lock(mm); /* * 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, + ret = get_user_pages_remote(mm, pos, 1, + write ? FOLL_WRITE : 0, &page, NULL, NULL); - mmap_read_unlock(bprm->mm); + 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; } -- cgit v1.2.3-59-g8ed1b