[PATCH] mm/x86: AMD Bulldozer ASLR fix

[Hector Marco-Gisbert <hecmargi@upv.es>]

A bug in Linux ASLR implementation which affects some AMD processors has been
found. The issue affects to all Linux process even if they are not using
shared libraries (statically compiled).

The problem appears because some mmapped objects (VDSO, libraries, etc.)
are poorly randomized in an attempt to avoid cache aliasing penalties for
AMD Bulldozer (Family 15h) processors.

Affected systems have reduced the mmapped files entropy by eight.

The following output is the run on an AMD Opteron 62xx class CPU processor
under x86_64 Linux 4.0.0:

for i in `seq 1 10`; do cat /proc/self/maps | grep "r-xp.*libc" ; done
b7588000-b7736000 r-xp 00000000 00:01 4924       /lib/i386-linux-gnu/libc.so.6
b7570000-b771e000 r-xp 00000000 00:01 4924       /lib/i386-linux-gnu/libc.so.6
b75d0000-b777e000 r-xp 00000000 00:01 4924       /lib/i386-linux-gnu/libc.so.6
b75b0000-b775e000 r-xp 00000000 00:01 4924       /lib/i386-linux-gnu/libc.so.6
b7578000-b7726000 r-xp 00000000 00:01 4924       /lib/i386-linux-gnu/libc.so.6

As shown in the previous output, the bits 12, 13 and 14 are always 0. The address
always ends in 0x8000 or 0x0000.

The bug is caused by a hack to improve performance by avoiding cache aliasing
penalties in the Family 15h of AMD Bulldozer processors (commit: dfb09f9b).

32-bit systems are specially sensitive to this issue because the entropy for
libraries is reduced from 2^8 to 2^5, which means that libraries only have 32
different places where they can be loaded.

This patch randomizes per boot the three affected bits, rather than setting
them to zero. Since all the shared pages have the same value at the bits
[12..14], there is no cache aliasing problems (which is supposed to be the
cause of performance loss). On the other hand, since the value is not
known by a potential remote attacker, the ASLR preserves its effectiveness.

More details at:

http://hmarco.org/bugs/AMD-Bulldozer-linux-ASLR-weakness-reducing-mmaped-files-by-eight.html


Signed-off-by: Hector Marco-Gisbert <hecmargi@upv.es>
Signed-off-by: Ismael Ripoll <iripoll@disca.upv.es>
---
 arch/x86/include/asm/elf.h   |  1 +
 arch/x86/kernel/cpu/amd.c    |  3 +++
 arch/x86/kernel/sys_x86_64.c | 20 +++++++++++++++++---
 3 files changed, 21 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index ca3347a..bd292ce 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -365,6 +365,7 @@ enum align_flags {
 struct va_alignment {
 	int flags;
 	unsigned long mask;
+	unsigned long bits;
 } ____cacheline_aligned;
 
 extern struct va_alignment va_align;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 15c5df9..45a41be 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -5,6 +5,7 @@
 
 #include <linux/io.h>
 #include <linux/sched.h>
+#include <linux/random.h>
 #include <asm/processor.h>
 #include <asm/apic.h>
 #include <asm/cpu.h>
@@ -488,6 +489,8 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 
 		va_align.mask	  = (upperbit - 1) & PAGE_MASK;
 		va_align.flags    = ALIGN_VA_32 | ALIGN_VA_64;
+		/* A random value per boot for bits 12,13 and 14 */
+		va_align.bits = get_random_int() & va_align.mask;
 	}
 }
 
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index 30277e2..d38905d 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -34,10 +34,16 @@ static unsigned long get_align_mask(void)
 	return va_align.mask;
 }
 
+static unsigned long get_align_bits(void){
+
+	return va_align.bits & get_align_mask();
+}
+
 unsigned long align_vdso_addr(unsigned long addr)
 {
 	unsigned long align_mask = get_align_mask();
-	return (addr + align_mask) & ~align_mask;
+	addr = (addr + align_mask) & ~align_mask;
+	return addr | get_align_bits();
 }
 
 static int __init control_va_addr_alignment(char *str)
@@ -135,8 +141,12 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	info.length = len;
 	info.low_limit = begin;
 	info.high_limit = end;
-	info.align_mask = filp ? get_align_mask() : 0;
+	info.align_mask = 0;
 	info.align_offset = pgoff << PAGE_SHIFT;
+	if(filp){
+		info.align_mask = get_align_mask();
+		info.align_offset += get_align_bits();
+	}
 	return vm_unmapped_area(&info);
 }
 
@@ -174,8 +184,12 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	info.length = len;
 	info.low_limit = PAGE_SIZE;
 	info.high_limit = mm->mmap_base;
-	info.align_mask = filp ? get_align_mask() : 0;
+	info.align_mask = 0;
 	info.align_offset = pgoff << PAGE_SHIFT;
+	if(filp){
+		info.align_mask = get_align_mask();
+		info.align_offset += get_align_bits();
+	}
 	addr = vm_unmapped_area(&info);
 	if (!(addr & ~PAGE_MASK))
 		return addr;
-- 
1.9.1