powerpc: do not make the entire heap executable

On 32-bit powerpc the ELF PLT sections of binaries (built with
--bss-plt, or with a toolchain which defaults to it) look like this:

  [17] .sbss             NOBITS          0002aff8 01aff8 000014 00  WA  0   0  4
  [18] .plt              NOBITS          0002b00c 01aff8 000084 00 WAX  0   0  4
  [19] .bss              NOBITS          0002b090 01aff8 0000a4 00  WA  0   0  4

Which results in an ELF load header:

  Type           Offset   VirtAddr   PhysAddr   FileSiz MemSiz  Flg Align
  LOAD           0x019c70 0x00029c70 0x00029c70 0x01388 0x014c4 RWE 0x10000

This is all correct, the load region containing the PLT is marked as
executable.  Note that the PLT starts at 0002b00c but the file mapping
ends at 0002aff8, so the PLT falls in the 0 fill section described by
the load header, and after a page boundary.

Unfortunately the generic ELF loader ignores the X bit in the load
headers when it creates the 0 filled non-file backed mappings.  It
assumes all of these mappings are RW BSS sections, which is not the case
for PPC.

gcc/ld has an option (--secure-plt) to not do this, this is said to
incur a small performance penalty.

Currently, to support 32-bit binaries with PLT in BSS kernel maps
*entire brk area* with executable rights for all binaries, even
--secure-plt ones.

Stop doing that.

Teach the ELF loader to check the X bit in the relevant load header and
create 0 filled anonymous mappings that are executable if the load
header requests that.

Test program showing the difference in /proc/$PID/maps:

int main() {
	char buf[16*1024];
	char *p = malloc(123); /* make "[heap]" mapping appear */
	int fd = open("/proc/self/maps", O_RDONLY);
	int len = read(fd, buf, sizeof(buf));
	write(1, buf, len);
	printf("%p\n", p);
	return 0;
}

Compiled using: gcc -mbss-plt -m32 -Os test.c -otest

Unpatched ppc64 kernel:
00100000-00120000 r-xp 00000000 00:00 0                                  [vdso]
0fe10000-0ffd0000 r-xp 00000000 fd:00 67898094                           /usr/lib/libc-2.17.so
0ffd0000-0ffe0000 r--p 001b0000 fd:00 67898094                           /usr/lib/libc-2.17.so
0ffe0000-0fff0000 rw-p 001c0000 fd:00 67898094                           /usr/lib/libc-2.17.so
10000000-10010000 r-xp 00000000 fd:00 100674505                          /home/user/test
10010000-10020000 r--p 00000000 fd:00 100674505                          /home/user/test
10020000-10030000 rw-p 00010000 fd:00 100674505                          /home/user/test
10690000-106c0000 rwxp 00000000 00:00 0                                  [heap]
f7f70000-f7fa0000 r-xp 00000000 fd:00 67898089                           /usr/lib/ld-2.17.so
f7fa0000-f7fb0000 r--p 00020000 fd:00 67898089                           /usr/lib/ld-2.17.so
f7fb0000-f7fc0000 rw-p 00030000 fd:00 67898089                           /usr/lib/ld-2.17.so
ffa90000-ffac0000 rw-p 00000000 00:00 0                                  [stack]
0x10690008

Patched ppc64 kernel:
00100000-00120000 r-xp 00000000 00:00 0                                  [vdso]
0fe10000-0ffd0000 r-xp 00000000 fd:00 67898094                           /usr/lib/libc-2.17.so
0ffd0000-0ffe0000 r--p 001b0000 fd:00 67898094                           /usr/lib/libc-2.17.so
0ffe0000-0fff0000 rw-p 001c0000 fd:00 67898094                           /usr/lib/libc-2.17.so
10000000-10010000 r-xp 00000000 fd:00 100674505                          /home/user/test
10010000-10020000 r--p 00000000 fd:00 100674505                          /home/user/test
10020000-10030000 rw-p 00010000 fd:00 100674505                          /home/user/test
10180000-101b0000 rw-p 00000000 00:00 0                                  [heap]
                  ^^^^ this has changed
f7c60000-f7c90000 r-xp 00000000 fd:00 67898089                           /usr/lib/ld-2.17.so
f7c90000-f7ca0000 r--p 00020000 fd:00 67898089                           /usr/lib/ld-2.17.so
f7ca0000-f7cb0000 rw-p 00030000 fd:00 67898089                           /usr/lib/ld-2.17.so
ff860000-ff890000 rw-p 00000000 00:00 0                                  [stack]
0x10180008

The patch was originally posted in 2012 by Jason Gunthorpe
and apparently ignored:

https://lkml.org/lkml/2012/9/30/138

Lightly run-tested.

Link: http://lkml.kernel.org/r/20161215131950.23054-1-dvlasenk@redhat.com
Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
Acked-by: Kees Cook <keescook@chromium.org>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Florian Weimer <fweimer@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 19 insertions, 5 deletions

diff --git a/mm/mmap.c b/mm/mmap.c
index dc4291dcc99b..b729084eea90 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2806,11 +2806,11 @@ static inline void verify_mm_writelocked(struct mm_struct *mm)
  *  anonymous maps.  eventually we may be able to do some
  *  brk-specific accounting here.
  */
-static int do_brk(unsigned long addr, unsigned long request)
+static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long flags)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma, *prev;
-	unsigned long flags, len;
+	unsigned long len;
 	struct rb_node **rb_link, *rb_parent;
 	pgoff_t pgoff = addr >> PAGE_SHIFT;
 	int error;
@@ -2821,7 +2821,10 @@ static int do_brk(unsigned long addr, unsigned long request)
 	if (!len)
 		return 0;
 
-	flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
+	/* Until we need other flags, refuse anything except VM_EXEC. */
+	if ((flags & (~VM_EXEC)) != 0)
+		return -EINVAL;
+	flags |= VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
 
 	error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED);
 	if (offset_in_page(error))
@@ -2889,7 +2892,12 @@ out:
 	return 0;
 }
 
-int vm_brk(unsigned long addr, unsigned long len)
+static int do_brk(unsigned long addr, unsigned long len)
+{
+	return do_brk_flags(addr, len, 0);
+}
+
+int vm_brk_flags(unsigned long addr, unsigned long len, unsigned long flags)
 {
 	struct mm_struct *mm = current->mm;
 	int ret;
@@ -2898,13 +2906,19 @@ int vm_brk(unsigned long addr, unsigned long len)
 	if (down_write_killable(&mm->mmap_sem))
 		return -EINTR;
 
-	ret = do_brk(addr, len);
+	ret = do_brk_flags(addr, len, flags);
 	populate = ((mm->def_flags & VM_LOCKED) != 0);
 	up_write(&mm->mmap_sem);
 	if (populate && !ret)
 		mm_populate(addr, len);
 	return ret;
 }
+EXPORT_SYMBOL(vm_brk_flags);
+
+int vm_brk(unsigned long addr, unsigned long len)
+{
+	return vm_brk_flags(addr, len, 0);
+}
 EXPORT_SYMBOL(vm_brk);
 
 /* Release all mmaps. */