mm: variable length argument support

Remove the arg+env limit of MAX_ARG_PAGES by copying the strings directly from
the old mm into the new mm.

We create the new mm before the binfmt code runs, and place the new stack at
the very top of the address space.  Once the binfmt code runs and figures out
where the stack should be, we move it downwards.

It is a bit peculiar in that we have one task with two mm's, one of which is
inactive.

[a.p.zijlstra@chello.nl: limit stack size]
Signed-off-by: Ollie Wild <aaw@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: <linux-arch@vger.kernel.org>
Cc: Hugh Dickins <hugh@veritas.com>
[bunk@stusta.de: unexport bprm_mm_init]
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 21 insertions, 6 deletions

diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index a0b209cd5761..91c8c07fe8b7 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -6,11 +6,13 @@
 struct pt_regs;
 
 /*
- * MAX_ARG_PAGES defines the number of pages allocated for arguments
- * and envelope for the new program. 32 should suffice, this gives
- * a maximum env+arg of 128kB w/4KB pages!
+ * These are the maximum length and maximum number of strings passed to the
+ * execve() system call.  MAX_ARG_STRLEN is essentially random but serves to
+ * prevent the kernel from being unduly impacted by misaddressed pointers.
+ * MAX_ARG_STRINGS is chosen to fit in a signed 32-bit integer.
  */
-#define MAX_ARG_PAGES 32
+#define MAX_ARG_STRLEN (PAGE_SIZE * 32)
+#define MAX_ARG_STRINGS 0x7FFFFFFF
 
 /* sizeof(linux_binprm->buf) */
 #define BINPRM_BUF_SIZE 128
@@ -24,7 +26,12 @@ struct pt_regs;
  */
 struct linux_binprm{
         char buf[BINPRM_BUF_SIZE];
+#ifdef CONFIG_MMU
+        struct vm_area_struct *vma;
+#else
+# define MAX_ARG_PAGES  32
         struct page *page[MAX_ARG_PAGES];
+#endif
         struct mm_struct *mm;
         unsigned long p; /* current top of mem */
         int sh_bang;
@@ -69,7 +76,7 @@ extern int register_binfmt(struct linux_binfmt *);
 extern int unregister_binfmt(struct linux_binfmt *);
 
 extern int prepare_binprm(struct linux_binprm *);
-extern void remove_arg_zero(struct linux_binprm *);
+extern int __must_check remove_arg_zero(struct linux_binprm *);
 extern int search_binary_handler(struct linux_binprm *,struct pt_regs *);
 extern int flush_old_exec(struct linux_binprm * bprm);
 
@@ -86,6 +93,7 @@ extern int suid_dumpable;
 extern int setup_arg_pages(struct linux_binprm * bprm,
                            unsigned long stack_top,
                            int executable_stack);
+extern int bprm_mm_init(struct linux_binprm *bprm);
 extern int copy_strings_kernel(int argc,char ** argv,struct linux_binprm *bprm);
 extern void compute_creds(struct linux_binprm *binprm);
 extern int do_coredump(long signr, int exit_code, struct pt_regs * regs);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 50a0ed1d1806..c456c3a1c28e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -808,7 +808,6 @@ static inline int handle_mm_fault(struct mm_struct *mm,
 
 extern int make_pages_present(unsigned long addr, unsigned long end);
 extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write);
-void install_arg_page(struct vm_area_struct *, struct page *, unsigned long);
 
 int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start,
                 int len, int write, int force, struct page **pages, struct vm_area_struct **vmas);
@@ -825,9 +824,15 @@ int FASTCALL(set_page_dirty(struct page *page));
 int set_page_dirty_lock(struct page *page);
 int clear_page_dirty_for_io(struct page *page);
 
+extern unsigned long move_page_tables(struct vm_area_struct *vma,
+                unsigned long old_addr, struct vm_area_struct *new_vma,
+                unsigned long new_addr, unsigned long len);
 extern unsigned long do_mremap(unsigned long addr,
                                unsigned long old_len, unsigned long new_len,
                                unsigned long flags, unsigned long new_addr);
+extern int mprotect_fixup(struct vm_area_struct *vma,
+                          struct vm_area_struct **pprev, unsigned long start,
+                          unsigned long end, unsigned long newflags);
 
 /*
  * A callback you can register to apply pressure to ageable caches.
@@ -1159,6 +1164,8 @@ extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
 #ifdef CONFIG_IA64
 extern int expand_upwards(struct vm_area_struct *vma, unsigned long address);
 #endif
+extern int expand_stack_downwards(struct vm_area_struct *vma,
+                                  unsigned long address);
 
 /* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
 extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr);