[tip:x86/asm] x86/vdso: Use ->fault() instead of remap_pfn_range( ) for the vvar mapping

From: tip-bot for Andy Lutomirski
Date: Tue Jan 12 2016 - 07:05:20 EST


Commit-ID: a48a7042613eb1524d18b7b1ed7d3a6b611fd21f
Gitweb: http://git.kernel.org/tip/a48a7042613eb1524d18b7b1ed7d3a6b611fd21f
Author: Andy Lutomirski <luto@xxxxxxxxxx>
AuthorDate: Tue, 29 Dec 2015 20:12:23 -0800
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Tue, 12 Jan 2016 11:59:35 +0100

x86/vdso: Use ->fault() instead of remap_pfn_range() for the vvar mapping

This is IMO much less ugly, and it also opens the door to
disallowing unprivileged userspace HPET access on systems with
usable TSCs.

Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
Reviewed-by: Kees Cook <keescook@xxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Fenghua Yu <fenghua.yu@xxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Oleg Nesterov <oleg@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Quentin Casasnovas <quentin.casasnovas@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Link: http://lkml.kernel.org/r/c19c2909e5ee3c3d8742f916586676bb7c40345f.1451446564.git.luto@xxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
arch/x86/entry/vdso/vma.c | 97 ++++++++++++++++++++++++++++-------------------
1 file changed, 57 insertions(+), 40 deletions(-)

diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index eb50d7c..4b5461b 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -102,18 +102,69 @@ static const struct vm_special_mapping text_mapping = {
.fault = vdso_fault,
};

+static int vvar_fault(const struct vm_special_mapping *sm,
+ struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ const struct vdso_image *image = vma->vm_mm->context.vdso_image;
+ long sym_offset;
+ int ret = -EFAULT;
+
+ if (!image)
+ return VM_FAULT_SIGBUS;
+
+ sym_offset = (long)(vmf->pgoff << PAGE_SHIFT) +
+ image->sym_vvar_start;
+
+ /*
+ * Sanity check: a symbol offset of zero means that the page
+ * does not exist for this vdso image, not that the page is at
+ * offset zero relative to the text mapping. This should be
+ * impossible here, because sym_offset should only be zero for
+ * the page past the end of the vvar mapping.
+ */
+ if (sym_offset == 0)
+ return VM_FAULT_SIGBUS;
+
+ if (sym_offset == image->sym_vvar_page) {
+ ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address,
+ __pa_symbol(&__vvar_page) >> PAGE_SHIFT);
+ } else if (sym_offset == image->sym_hpet_page) {
+#ifdef CONFIG_HPET_TIMER
+ if (hpet_address) {
+ ret = vm_insert_pfn_prot(
+ vma,
+ (unsigned long)vmf->virtual_address,
+ hpet_address >> PAGE_SHIFT,
+ pgprot_noncached(PAGE_READONLY));
+ }
+#endif
+ } else if (sym_offset == image->sym_pvclock_page) {
+ struct pvclock_vsyscall_time_info *pvti =
+ pvclock_pvti_cpu0_va();
+ if (pvti) {
+ ret = vm_insert_pfn(
+ vma,
+ (unsigned long)vmf->virtual_address,
+ __pa(pvti) >> PAGE_SHIFT);
+ }
+ }
+
+ if (ret == 0 || ret == -EBUSY)
+ return VM_FAULT_NOPAGE;
+
+ return VM_FAULT_SIGBUS;
+}
+
static int map_vdso(const struct vdso_image *image, bool calculate_addr)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
unsigned long addr, text_start;
int ret = 0;
- static struct page *no_pages[] = {NULL};
- static struct vm_special_mapping vvar_mapping = {
+ static const struct vm_special_mapping vvar_mapping = {
.name = "[vvar]",
- .pages = no_pages,
+ .fault = vvar_fault,
};
- struct pvclock_vsyscall_time_info *pvti;

if (calculate_addr) {
addr = vdso_addr(current->mm->start_stack,
@@ -153,7 +204,8 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
vma = _install_special_mapping(mm,
addr,
-image->sym_vvar_start,
- VM_READ|VM_MAYREAD,
+ VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP|
+ VM_PFNMAP,
&vvar_mapping);

if (IS_ERR(vma)) {
@@ -161,41 +213,6 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
goto up_fail;
}

- if (image->sym_vvar_page)
- ret = remap_pfn_range(vma,
- text_start + image->sym_vvar_page,
- __pa_symbol(&__vvar_page) >> PAGE_SHIFT,
- PAGE_SIZE,
- PAGE_READONLY);
-
- if (ret)
- goto up_fail;
-
-#ifdef CONFIG_HPET_TIMER
- if (hpet_address && image->sym_hpet_page) {
- ret = io_remap_pfn_range(vma,
- text_start + image->sym_hpet_page,
- hpet_address >> PAGE_SHIFT,
- PAGE_SIZE,
- pgprot_noncached(PAGE_READONLY));
-
- if (ret)
- goto up_fail;
- }
-#endif
-
- pvti = pvclock_pvti_cpu0_va();
- if (pvti && image->sym_pvclock_page) {
- ret = remap_pfn_range(vma,
- text_start + image->sym_pvclock_page,
- __pa(pvti) >> PAGE_SHIFT,
- PAGE_SIZE,
- PAGE_READONLY);
-
- if (ret)
- goto up_fail;
- }
-
up_fail:
if (ret)
current->mm->context.vdso = NULL;