[PATCH 3/4] [tip:x86/mm] NX protection for kernel data

* [PATCH 3/4] [tip:x86/mm] NX protection for kernel data
@ 2010-05-27 16:53 Siarhei Liakh
  0 siblings, 0 replies; 2+ messages in thread
From: Siarhei Liakh @ 2010-05-27 16:53 UTC (permalink / raw)
  To: linux-kernel, linux-security-module, linux-next
  Cc: Arjan van de Ven, James Morris, Andrew Morton, Andi Kleen,
	Thomas Gleixner, H. Peter Anvin, Ingo Molnar, Rusty Russell,
	Stephen Rothwell, Dave Jones

Note: this patch depends on "Correct improper large page preservation" patch

This patch expands functionality of CONFIG_DEBUG_RODATA to set main
(static) kernel data area as NX.
The following steps are taken to achieve this:
1. Linker script is adjusted so .text always starts and ends on a page boundary
2. Linker script is adjusted so .rodata and .data always start and
end on a page boundary
3. void mark_nxdata_nx(void) added to arch/x86/mm/init.c with actual
functionality: NX is set for all pages from _etext through _end.
4. mark_nxdata_nx() called from free_initmem() (after init has been released)
5. free_init_pages() sets released memory NX in arch/x86/mm/init.c

The results of patch application may be observed in the diff of kernel page
table dumps:
--- data_nx_pt_before.txt       2009-10-13 07:48:59.000000000 -0400
+++ data_nx_pt_after.txt        2009-10-13 07:26:46.000000000 -0400
@@ -2,8 +2,9 @@
 0x00000000-0xc0000000           3G                           pmd
 ---[ Kernel Mapping ]---
 0xc0000000-0xc0100000           1M     RW             GLB x  pte
-0xc0100000-0xc048d000        3636K     ro             GLB x  pte
-0xc048d000-0xc0600000        1484K     RW             GLB x  pte
+0xc0100000-0xc0381000        2564K     ro             GLB x  pte
+0xc0381000-0xc048d000        1072K     ro             GLB NX pte
+0xc048d000-0xc0600000        1484K     RW             GLB NX pte
 0xc0600000-0xf7800000         882M     RW         PSE GLB NX pmd
 0xf7800000-0xf79fe000        2040K     RW             GLB NX pte
 0xf79fe000-0xf7a00000           8K                           pte


The patch have been developed for Linux 2.6.34-rc2 x86 by Siarhei Liakh
<sliakh.lkml@gmail.com> and Xuxian Jiang <jiang@cs.ncsu.edu>.

V1:  initial patch for 2.6.30
V2:  patch for 2.6.31-rc7
V3:  moved all code into arch/x86, adjusted credits
V4:  fixed ifdef, removed credits from CREDITS
V5:  fixed an address calculation bug in mark_nxdata_nx()
V6:  added acked-by and PT dump diff to commit log
V7:  minor adjustments for -tip

Signed-off-by: Siarhei Liakh <sliakh.lkml@gmail.com>
Signed-off-by: Xuxian Jiang <jiang@cs.ncsu.edu>
Acked-by: Arjan van de Ven <arjan@linux.intel.com>
Reviewed-by: James Morris <jmorris@namei.org>
---

diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 2cc2497..7f82438 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -69,7 +69,7 @@ jiffies_64 = jiffies;

 PHDRS {
       text PT_LOAD FLAGS(5);          /* R_E */
-       data PT_LOAD FLAGS(7);          /* RWE */
+       data PT_LOAD FLAGS(6);          /* RW_ */
 #ifdef CONFIG_X86_64
       user PT_LOAD FLAGS(5);          /* R_E */
 #ifdef CONFIG_SMP
@@ -108,6 +108,8 @@ SECTIONS
               IRQENTRY_TEXT
               *(.fixup)
               *(.gnu.warning)
+               /* .text should occupy whole number of pages */
+               . = ALIGN(PAGE_SIZE);
               /* End of text section */
               _etext = .;
       } :text = 0x9090
@@ -121,6 +123,7 @@ SECTIONS
       X64_ALIGN_DEBUG_RODATA_END

       /* Data */
+       . = ALIGN(PAGE_SIZE);
       .data : AT(ADDR(.data) - LOAD_OFFSET) {
               /* Start of data section */
               _sdata = .;
@@ -143,6 +146,8 @@ SECTIONS
               /* rarely changed data like cpu maps */
               READ_MOSTLY_DATA(INTERNODE_CACHE_BYTES)

+               /* .data should occupy whole number of pages */
+               . = ALIGN(PAGE_SIZE);
               /* End of data section */
               _edata = .;
       } :data
@@ -307,7 +312,7 @@ SECTIONS
               __bss_start = .;
               *(.bss.page_aligned)
               *(.bss)
-               . = ALIGN(4);
+               . = ALIGN(PAGE_SIZE);
               __bss_stop = .;
       }

diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 452ee5b..240dcb0 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -361,8 +361,9 @@ void free_init_pages(char *what, unsigned long
begin, unsigned long end)
       /*
        * We just marked the kernel text read only above, now that
        * we are going to free part of that, we need to make that
-        * writeable first.
+        * writeable and non-executable first.
        */
+       set_memory_nx(begin, (end - begin) >> PAGE_SHIFT);
       set_memory_rw(begin, (end - begin) >> PAGE_SHIFT);

       printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
@@ -377,11 +378,29 @@ void free_init_pages(char *what, unsigned long
begin, unsigned long end)
 #endif
 }

+void mark_nxdata_nx(void)
+{
+#ifdef CONFIG_DEBUG_RODATA
+       /*
+        * When this called, init has already been executed and released,
+        * so everything past _etext sould be NX.
+        */
+       unsigned long start = PAGE_ALIGN((unsigned long)(&_etext));
+       unsigned long size = PAGE_ALIGN((unsigned long)(&_end)) - start;
+
+       printk(KERN_INFO "NX-protecting the kernel data: %lx, %lu pages\n",
+               start, size >> PAGE_SHIFT);
+       set_memory_nx(start, size >> PAGE_SHIFT);
+#endif
+}
+
 void free_initmem(void)
 {
       free_init_pages("unused kernel memory",
                       (unsigned long)(&__init_begin),
                       (unsigned long)(&__init_end));
+       /* Set kernel's data as NX */
+       mark_nxdata_nx();
 }

 #ifdef CONFIG_BLK_DEV_INITRD

^ permalink raw reply related	[flat|nested] 2+ messages in thread