diff options
| author | Oleg Nesterov <oleg@redhat.com> | 2010-11-30 20:55:34 +0100 |
|---|---|---|
| committer | Willy Tarreau <w@1wt.eu> | 2011-04-30 16:53:36 +0200 |
| commit | bb4659e0d68667f5eac7ef551a95762564e484a3 (patch) | |
| tree | d30262be5da55e8c3a34a8415193abdfe73294ac | |
| parent | 8ece1d67112e1a03cf7cad1c5a5771bdaa8966e8 (diff) | |
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.
Reported-by: Brad Spengler <spender@grsecurity.net>
Reviewed-and-discussed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Moritz Muehlenhoff <jmm@debian.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
| -rw-r--r-- | fs/exec.c | 26 | ||||
| -rw-r--r-- | include/linux/binfmts.h | 1 |
2 files changed, 26 insertions, 1 deletions
diff --git a/fs/exec.c b/fs/exec.c index 12e7ad2491b2..f08ebee3bb4a 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -168,6 +168,21 @@ exit: #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) { @@ -190,6 +205,8 @@ 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 @@ -291,6 +308,10 @@ 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) { @@ -995,6 +1016,7 @@ 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; @@ -1378,8 +1400,10 @@ out: security_bprm_free(bprm); out_mm: - if (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 12413a1e2784..a2e0013900ef 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -28,6 +28,7 @@ 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]; |