[PATCH] vdso: randomize the i386 vDSO by moving it into a vma

Move the i386 VDSO down into a vma and thus randomize it.

Besides the security implications, this feature also helps debuggers, which
can COW a vma-backed VDSO just like a normal DSO and can thus do
single-stepping and other debugging features.

It's good for hypervisors (Xen, VMWare) too, which typically live in the same
high-mapped address space as the VDSO, hence whenever the VDSO is used, they
get lots of guest pagefaults and have to fix such guest accesses up - which
slows things down instead of speeding things up (the primary purpose of the
VDSO).

There's a new CONFIG_COMPAT_VDSO (default=y) option, which provides support
for older glibcs that still rely on a prelinked high-mapped VDSO.  Newer
distributions (using glibc 2.3.3 or later) can turn this option off.  Turning
it off is also recommended for security reasons: attackers cannot use the
predictable high-mapped VDSO page as syscall trampoline anymore.

There is a new vdso=[0|1] boot option as well, and a runtime
/proc/sys/vm/vdso_enabled sysctl switch, that allows the VDSO to be turned
on/off.

(This version of the VDSO-randomization patch also has working ELF
coredumping, the previous patch crashed in the coredumping code.)

This code is a combined work of the exec-shield VDSO randomization
code and Gerd Hoffmann's hypervisor-centric VDSO patch. Rusty Russell
started this patch and i completed it.

[akpm@osdl.org: cleanups]
[akpm@osdl.org: compile fix]
[akpm@osdl.org: compile fix 2]
[akpm@osdl.org: compile fix 3]
[akpm@osdl.org: revernt MAXMEM change]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjan@infradead.org>
Cc: Gerd Hoffmann <kraxel@suse.de>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Zachary Amsden <zach@vmware.com>
Cc: Andi Kleen <ak@muc.de>
Cc: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 124 insertions, 4 deletions

diff --git a/arch/i386/kernel/sysenter.c b/arch/i386/kernel/sysenter.c
index 0bada18..c60419de 100644
--- a/arch/i386/kernel/sysenter.c
+++ b/arch/i386/kernel/sysenter.c
@@ -2,6 +2,8 @@
  * linux/arch/i386/kernel/sysenter.c
  *
  * (C) Copyright 2002 Linus Torvalds
+ * Portions based on the vdso-randomization code from exec-shield:
+ * Copyright(C) 2005-2006, Red Hat, Inc., Ingo Molnar
  *
  * This file contains the needed initializations to support sysenter.
  */
@@ -13,12 +15,31 @@
 #include <linux/gfp.h>
 #include <linux/string.h>
 #include <linux/elf.h>
+#include <linux/mm.h>
+#include <linux/module.h>
 
 #include <asm/cpufeature.h>
 #include <asm/msr.h>
 #include <asm/pgtable.h>
 #include <asm/unistd.h>
 
+/*
+ * Should the kernel map a VDSO page into processes and pass its
+ * address down to glibc upon exec()?
+ */
+unsigned int __read_mostly vdso_enabled = 1;
+
+EXPORT_SYMBOL_GPL(vdso_enabled);
+
+static int __init vdso_setup(char *s)
+{
+	vdso_enabled = simple_strtoul(s, NULL, 0);
+
+	return 1;
+}
+
+__setup("vdso=", vdso_setup);
+
 extern asmlinkage void sysenter_entry(void);
 
 void enable_sep_cpu(void)
@@ -45,23 +66,122 @@ void enable_sep_cpu(void)
  */
 extern const char vsyscall_int80_start, vsyscall_int80_end;
 extern const char vsyscall_sysenter_start, vsyscall_sysenter_end;
+static void *syscall_page;
 
 int __init sysenter_setup(void)
 {
-	void *page = (void *)get_zeroed_page(GFP_ATOMIC);
+	syscall_page = (void *)get_zeroed_page(GFP_ATOMIC);
 
-	__set_fixmap(FIX_VSYSCALL, __pa(page), PAGE_READONLY_EXEC);
+#ifdef CONFIG_COMPAT_VDSO
+	__set_fixmap(FIX_VDSO, __pa(syscall_page), PAGE_READONLY);
+	printk("Compat vDSO mapped to %08lx.\n", __fix_to_virt(FIX_VDSO));
+#else
+	/*
+	 * In the non-compat case the ELF coredumping code needs the fixmap:
+	 */
+	__set_fixmap(FIX_VDSO, __pa(syscall_page), PAGE_KERNEL_RO);
+#endif
 
 	if (!boot_cpu_has(X86_FEATURE_SEP)) {
-		memcpy(page,
+		memcpy(syscall_page,
 		       &vsyscall_int80_start,
 		       &vsyscall_int80_end - &vsyscall_int80_start);
 		return 0;
 	}
 
-	memcpy(page,
+	memcpy(syscall_page,
 	       &vsyscall_sysenter_start,
 	       &vsyscall_sysenter_end - &vsyscall_sysenter_start);
 
 	return 0;
 }
+
+static struct page *syscall_nopage(struct vm_area_struct *vma,
+				unsigned long adr, int *type)
+{
+	struct page *p = virt_to_page(adr - vma->vm_start + syscall_page);
+	get_page(p);
+	return p;
+}
+
+/* Prevent VMA merging */
+static void syscall_vma_close(struct vm_area_struct *vma)
+{
+}
+
+static struct vm_operations_struct syscall_vm_ops = {
+	.close = syscall_vma_close,
+	.nopage = syscall_nopage,
+};
+
+/* Defined in vsyscall-sysenter.S */
+extern void SYSENTER_RETURN;
+
+/* Setup a VMA at program startup for the vsyscall page */
+int arch_setup_additional_pages(struct linux_binprm *bprm, int exstack)
+{
+	struct vm_area_struct *vma;
+	struct mm_struct *mm = current->mm;
+	unsigned long addr;
+	int ret;
+
+	down_write(&mm->mmap_sem);
+	addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
+	if (IS_ERR_VALUE(addr)) {
+		ret = addr;
+		goto up_fail;
+	}
+
+	vma = kmem_cache_zalloc(vm_area_cachep, SLAB_KERNEL);
+	if (!vma) {
+		ret = -ENOMEM;
+		goto up_fail;
+	}
+
+	vma->vm_start = addr;
+	vma->vm_end = addr + PAGE_SIZE;
+	/* MAYWRITE to allow gdb to COW and set breakpoints */
+	vma->vm_flags = VM_READ|VM_EXEC|VM_MAYREAD|VM_MAYEXEC|VM_MAYWRITE;
+	vma->vm_flags |= mm->def_flags;
+	vma->vm_page_prot = protection_map[vma->vm_flags & 7];
+	vma->vm_ops = &syscall_vm_ops;
+	vma->vm_mm = mm;
+
+	ret = insert_vm_struct(mm, vma);
+	if (ret)
+		goto free_vma;
+
+	current->mm->context.vdso = (void *)addr;
+	current_thread_info()->sysenter_return =
+				    (void *)VDSO_SYM(&SYSENTER_RETURN);
+	mm->total_vm++;
+up_fail:
+	up_write(&mm->mmap_sem);
+	return ret;
+
+free_vma:
+	kmem_cache_free(vm_area_cachep, vma);
+	return ret;
+}
+
+const char *arch_vma_name(struct vm_area_struct *vma)
+{
+	if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso)
+		return "[vdso]";
+	return NULL;
+}
+
+struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
+{
+	return NULL;
+}
+
+int in_gate_area(struct task_struct *task, unsigned long addr)
+{
+	return 0;
+}
+
+int in_gate_area_no_task(unsigned long addr)
+{
+	return 0;
+}