x86/mm: Make PV linear pagetables optional

Allowing pagetables to point to other pagetables of the same level
(often called 'linear pagetables') has been included in Xen since its
inception; but recently it has been the source of a number of subtle
reference-counting bugs.

It is not used by Linux or MiniOS; but it is used by NetBSD and Novell
Netware.  There are significant numbers of people who are never going
to use the feature, along with significant numbers who need the
feature.

Add a Kconfig option for the feature (default to 'y').  Also add a
command-line option to control whether PV linear pagetables are
allowed (default to 'true').

NB that we leave linear_pt_count in the page struct.  It's in a union,
so its presence doesn't increase the size of the data struct.
Changing the layout of the other elements based on configuration
options is asking for trouble however; so we'll just leave it there
and ASSERT that it's zero.

Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: George Dunlap <george.dunlap@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Release-acked-by: Julien Grall <julien.grall@arm.com>

diff --git a/docs/misc/xen-command-line.markdown b/docs/misc/xen-command-line.markdown
index eb4995e68b8cd97a49bbf340831c90d336dd93c5..781110d4b2a54c38cad829ea2654888e362deeb0 100644 (file)
--- a/docs/misc/xen-command-line.markdown
+++ b/docs/misc/xen-command-line.markdown
@@ -1422,6 +1422,25 @@ The following resources are available:
     CDP, one COS will corespond two CBMs other than one with CAT, due to the
     sum of CBMs is fixed, that means actual `cos_max` in use will automatically
     reduce to half when CDP is enabled.
+       
+### pv-linear-pt
+> `= <boolean>`
+
+> Default: `true`
+
+Only available if Xen is compiled with CONFIG\_PV\_LINEAR\_PT support
+enabled.
+
+Allow PV guests to have pagetable entries pointing to other pagetables
+of the same level (i.e., allowing L2 PTEs to point to other L2 pages).
+This technique is often called "linear pagetables", and is sometimes
+used to allow operating systems a simple way to consistently map the
+current process's pagetables into its own virtual address space.
+
+Linux and MiniOS don't use this technique.  NetBSD and Novell Netware
+do; there may be other custom operating systems which do.  If you're
+certain you don't plan on having PV guests which use this feature,
+turning it off can reduce the attack surface.
 
 ### rcu-idle-timer-period-ms
 > `= <integer>`

diff --git a/xen/arch/x86/Kconfig b/xen/arch/x86/Kconfig
index 64955dc017987d96c1396aa079be164f1f02aa57..7c4582922f79d457d2b6309db33af94e30d907c5 100644 (file)
--- a/xen/arch/x86/Kconfig
+++ b/xen/arch/x86/Kconfig
@@ -37,6 +37,26 @@ source "arch/Kconfig"
 config PV
        def_bool y
 
+config PV_LINEAR_PT
+       bool "Support for PV linear pagetables"
+       depends on PV
+       default y
+       ---help---
+         Linear pagetables (also called "recursive pagetables") refers
+         to the practice of a guest operating system having pagetable
+         entries pointing to other pagetables of the same level (i.e.,
+         allowing L2 PTEs to point to other L2 pages).  Some operating
+         systems use it as a simple way to consistently map the current
+         process's pagetables into its own virtual address space.
+
+         Linux and MiniOS don't use this technique.  NetBSD and Novell
+         Netware do; there may be other custom operating systems which
+         do.  If you're certain you don't plan on having PV guests
+         which use this feature, turning it off can reduce the attack
+         surface.
+
+         If unsure, say Y.
+
 config HVM
        def_bool y
 

diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index 1ff4a9d629b9d32604055645d0c0663ef57e3f8e..a20fdcaea4fb4f81f260755da3ee25dae830628b 100644 (file)
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -626,6 +626,8 @@ static void put_data_page(
         put_page(page);
 }
 
+#ifdef CONFIG_PV_LINEAR_PT
+
 static bool inc_linear_entries(struct page_info *pg)
 {
     typeof(pg->linear_pt_count) nc = read_atomic(&pg->linear_pt_count), oc;
@@ -693,6 +695,9 @@ static void dec_linear_uses(struct page_info *pg)
  *     frame if it is mapped by a different root table. This is sufficient and
  *     also necessary to allow validation of a root table mapping itself.
  */
+static bool __read_mostly opt_pv_linear_pt = true;
+boolean_param("pv-linear-pt", opt_pv_linear_pt);
+
 #define define_get_linear_pagetable(level)                                  \
 static int                                                                  \
 get_##level##_linear_pagetable(                                             \
@@ -702,6 +707,13 @@ get_##level##_linear_pagetable(                                             \
     struct page_info *page;                                                 \
     unsigned long pfn;                                                      \
                                                                             \
+    if ( !opt_pv_linear_pt )                                                \
+    {                                                                       \
+        gdprintk(XENLOG_WARNING,                                            \
+                 "Attempt to create linear p.t. (feature disabled)\n");     \
+        return 0;                                                           \
+    }                                                                       \
+                                                                            \
     if ( (level##e_get_flags(pde) & _PAGE_RW) )                             \
     {                                                                       \
         gdprintk(XENLOG_WARNING,                                            \
@@ -759,6 +771,27 @@ get_##level##_linear_pagetable(                                             \
     return 1;                                                               \
 }
 
+#else /* CONFIG_PV_LINEAR_PT */
+
+#define define_get_linear_pagetable(level)                              \
+static int                                                              \
+get_##level##_linear_pagetable(                                         \
+        level##_pgentry_t pde, unsigned long pde_pfn, struct domain *d) \
+{                                                                       \
+        return 0;                                                       \
+}
+
+static void dec_linear_uses(struct page_info *pg)
+{
+    ASSERT(pg->linear_pt_count == 0);
+}
+
+static void dec_linear_entries(struct page_info *pg)
+{
+    ASSERT(pg->linear_pt_count == 0);
+}
+
+#endif /* CONFIG_PV_LINEAR_PT */
 
 bool is_iomem_page(mfn_t mfn)
 {
@@ -2444,6 +2477,7 @@ static int _put_page_type(struct page_info *page, bool preemptible,
                 break;
             }
 
+#ifdef CONFIG_PV_LINEAR_PT
             if ( ptpg && PGT_type_equal(x, ptpg->u.inuse.type_info) )
             {
                 /*
@@ -2458,6 +2492,9 @@ static int _put_page_type(struct page_info *page, bool preemptible,
                 ASSERT(ptpg->linear_pt_count > 0);
                 ptpg = NULL;
             }
+#else /* CONFIG_PV_LINEAR_PT */
+            BUG_ON(ptpg && PGT_type_equal(x, ptpg->u.inuse.type_info));
+#endif
 
             set_tlbflush_timestamp(page);
         }