x86/xen: don't copy bogus duplicate entries into kernel page tables

When RANDOMIZE_BASE (KASLR) is enabled; or the sum of all loaded
modules exceeds 512 MiB, then loading modules fails with a warning
(and hence a vmalloc allocation failure) because the PTEs for the
newly-allocated vmalloc address space are not zero.

  WARNING: CPU: 0 PID: 494 at linux/mm/vmalloc.c:128
           vmap_page_range_noflush+0x2a1/0x360()

This is caused by xen_setup_kernel_pagetables() copying
level2_kernel_pgt into level2_fixmap_pgt, overwriting many non-present
entries.

Without KASLR, the normal kernel image size only covers the first half
of level2_kernel_pgt and module space starts after that.

L4[511]->level3_kernel_pgt[510]->level2_kernel_pgt[  0..255]->kernel
                                                  [256..511]->module
                          [511]->level2_fixmap_pgt[  0..505]->module

This allows 512 MiB of of module vmalloc space to be used before
having to use the corrupted level2_fixmap_pgt entries.

With KASLR enabled, the kernel image uses the full PUD range of 1G and
module space starts in the level2_fixmap_pgt. So basically:

L4[511]->level3_kernel_pgt[510]->level2_kernel_pgt[0..511]->kernel
                          [511]->level2_fixmap_pgt[0..505]->module

And now no module vmalloc space can be used without using the corrupt
level2_fixmap_pgt entries.

Fix this by properly converting the level2_fixmap_pgt entries to MFNs,
and setting level1_fixmap_pgt as read-only.

A number of comments were also using the the wrong L3 offset for
level2_kernel_pgt.  These have been corrected.

Signed-off-by: Stefan Bader <stefan.bader@canonical.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: stable@vger.kernel.org

2 files changed, 13 insertions, 15 deletions

diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 5be9063545d278..3874693c0e53ad 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -19,6 +19,7 @@ extern pud_t level3_ident_pgt[512];
 extern pmd_t level2_kernel_pgt[512];
 extern pmd_t level2_fixmap_pgt[512];
 extern pmd_t level2_ident_pgt[512];
+extern pte_t level1_fixmap_pgt[512];
 extern pgd_t init_level4_pgt[];
 
 #define swapper_pg_dir init_level4_pgt
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index e8a1201c3293bf..16fb0099b7f295 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1866,12 +1866,11 @@ static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end,
  *
  * We can construct this by grafting the Xen provided pagetable into
  * head_64.S's preconstructed pagetables.  We copy the Xen L2's into
- * level2_ident_pgt, level2_kernel_pgt and level2_fixmap_pgt.  This
- * means that only the kernel has a physical mapping to start with -
- * but that's enough to get __va working.  We need to fill in the rest
- * of the physical mapping once some sort of allocator has been set
- * up.
- * NOTE: for PVH, the page tables are native.
+ * level2_ident_pgt, and level2_kernel_pgt.  This means that only the
+ * kernel has a physical mapping to start with - but that's enough to
+ * get __va working.  We need to fill in the rest of the physical
+ * mapping once some sort of allocator has been set up.  NOTE: for
+ * PVH, the page tables are native.
  */
 void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 {
@@ -1902,8 +1901,11 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 		/* L3_i[0] -> level2_ident_pgt */
 		convert_pfn_mfn(level3_ident_pgt);
 		/* L3_k[510] -> level2_kernel_pgt
-		 * L3_i[511] -> level2_fixmap_pgt */
+		 * L3_k[511] -> level2_fixmap_pgt */
 		convert_pfn_mfn(level3_kernel_pgt);
+
+		/* L3_k[511][506] -> level1_fixmap_pgt */
+		convert_pfn_mfn(level2_fixmap_pgt);
 	}
 	/* We get [511][511] and have Xen's version of level2_kernel_pgt */
 	l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd);
@@ -1913,21 +1915,15 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	addr[1] = (unsigned long)l3;
 	addr[2] = (unsigned long)l2;
 	/* Graft it onto L4[272][0]. Note that we creating an aliasing problem:
-	 * Both L4[272][0] and L4[511][511] have entries that point to the same
+	 * Both L4[272][0] and L4[511][510] have entries that point to the same
 	 * L2 (PMD) tables. Meaning that if you modify it in __va space
 	 * it will be also modified in the __ka space! (But if you just
 	 * modify the PMD table to point to other PTE's or none, then you
 	 * are OK - which is what cleanup_highmap does) */
 	copy_page(level2_ident_pgt, l2);
-	/* Graft it onto L4[511][511] */
+	/* Graft it onto L4[511][510] */
 	copy_page(level2_kernel_pgt, l2);
 
-	/* Get [511][510] and graft that in level2_fixmap_pgt */
-	l3 = m2v(pgd[pgd_index(__START_KERNEL_map + PMD_SIZE)].pgd);
-	l2 = m2v(l3[pud_index(__START_KERNEL_map + PMD_SIZE)].pud);
-	copy_page(level2_fixmap_pgt, l2);
-	/* Note that we don't do anything with level1_fixmap_pgt which
-	 * we don't need. */
 	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
 		/* Make pagetable pieces RO */
 		set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
@@ -1937,6 +1933,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 		set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
 		set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
 		set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
+		set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO);
 
 		/* Pin down new L4 */
 		pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,