exec: make argv/envp memory visible to oom-killer

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>
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/exec.c b/fs/exec.c
index 99d33a1..4303b90 100644 (file)
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -164,6 +164,25 @@ 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;
+
+#ifdef SPLIT_RSS_COUNTING
+       add_mm_counter(mm, MM_ANONPAGES, diff);
+#else
+       spin_lock(&mm->page_table_lock);
+       add_mm_counter(mm, MM_ANONPAGES, diff);
+       spin_unlock(&mm->page_table_lock);
+#endif
+}
+
 static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
                int write)
 {
@@ -186,6 +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
@@ -276,6 +297,10 @@ 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)
 {
@@ -1003,6 +1028,7 @@ 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;
@@ -1426,8 +1452,10 @@ int do_execve(const 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 a065612..7c87796 100644 (file)
--- 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];