From c9b14e575935b3540e08f4467cf6588be2669710 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 14 Dec 2010 23:40:11 +0100 Subject: [PATCH] exec: make argv/envp memory visible to oom-killer commit 3c77f845722158206a7209c45ccddc264d19319c upstream. Brad Spengler published a local memory-allocation DoS that evades the OOM-killer (though not the virtual memory RLIMIT): http://www.grsecurity.net/~spender/64bit_dos.c execve()->copy_strings() can allocate a lot of memory, but this is not visible to oom-killer, nobody can see the nascent bprm->mm and take it into account. With this patch get_arg_page() increments current's MM_ANONPAGES counter every time we allocate the new page for argv/envp. When do_execve() succeds or fails, we change this counter back. Technically this is not 100% correct, we can't know if the new page is swapped out and turn MM_ANONPAGES into MM_SWAPENTS, but I don't think this really matters and everything becomes correct once exec changes ->mm or fails. Compared to upstream: before 2.6.36 kernel, oom-killer's badness() takes mm->total_vm into account and nothing else. So acct_arg_size() has to play with this counter too. Reported-by: Brad Spengler Signed-off-by: Andi Kleen Reviewed-and-discussed-by: KOSAKI Motohiro Signed-off-by: Oleg Nesterov Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- fs/exec.c | 28 ++++++++++++++++++++++++++-- include/linux/binfmts.h | 1 + 2 files changed, 27 insertions(+), 2 deletions(-) diff --git a/fs/exec.c b/fs/exec.c index 956bd37743c..53a5fc558bf 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -158,6 +158,21 @@ out: #ifdef CONFIG_MMU +static void acct_arg_size(struct linux_binprm *bprm, unsigned long pages) +{ + struct mm_struct *mm = current->mm; + long diff = (long)(pages - bprm->vma_pages); + + if (!mm || !diff) + return; + + bprm->vma_pages = pages; + + down_write(&mm->mmap_sem); + mm->total_vm += diff; + up_write(&mm->mmap_sem); +} + static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, int write) { @@ -180,6 +195,8 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start; struct rlimit *rlim; + acct_arg_size(bprm, size / PAGE_SIZE); + /* * We've historically supported up to 32 pages (ARG_MAX) * of argument strings even with small stacks @@ -270,6 +287,10 @@ static bool valid_arg_len(struct linux_binprm *bprm, long len) #else +static inline void acct_arg_size(struct linux_binprm *bprm, unsigned long pages) +{ +} + static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, int write) { @@ -991,6 +1012,7 @@ int flush_old_exec(struct linux_binprm * bprm) /* * Release all of the old mmap stuff */ + acct_arg_size(bprm, 0); retval = exec_mmap(bprm->mm); if (retval) goto out; @@ -1415,8 +1437,10 @@ int do_execve(char * filename, return retval; out: - if (bprm->mm) - mmput (bprm->mm); + if (bprm->mm) { + acct_arg_size(bprm, 0); + mmput(bprm->mm); + } out_file: if (bprm->file) { diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index c809e286d21..39798c65c23 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -29,6 +29,7 @@ struct linux_binprm{ char buf[BINPRM_BUF_SIZE]; #ifdef CONFIG_MMU struct vm_area_struct *vma; + unsigned long vma_pages; #else # define MAX_ARG_PAGES 32 struct page *page[MAX_ARG_PAGES]; -- 2.34.1