x86/mm: Fix guard hole handling

[ Upstream commit 16877a55 ]

There is a guard hole at the beginning of the kernel address space, also
used by hypervisors. It occupies 16 PGD entries.

This reserved range is not defined explicitely, it is calculated relative
to other entities: direct mapping and user space ranges.

The calculation got broken by recent changes of the kernel memory layout:
LDT remap range is now mapped before direct mapping and makes the
calculation invalid.

The breakage leads to crash on Xen dom0 boot[1].

Define the reserved range explicitely. It's part of kernel ABI (hypervisors
expect it to be stable) and must not depend on changes in the rest of
kernel memory layout.

[1] https://lists.xenproject.org/archives/html/xen-devel/2018-11/msg03313.html

Fixes: d52888aa ("x86/mm: Move LDT remap out of KASLR region on 5-level paging")
Reported-by: Hans van Kranenburg <hans.van.kranenburg@mendix.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Hans van Kranenburg <hans.van.kranenburg@mendix.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Cc: bp@alien8.de
Cc: hpa@zytor.com
Cc: dave.hansen@linux.intel.com
Cc: luto@kernel.org
Cc: peterz@infradead.org
Cc: boris.ostrovsky@oracle.com
Cc: bhe@redhat.com
Cc: linux-mm@kvack.org
Cc: xen-devel@lists.xenproject.org
Link: https://lkml.kernel.org/r/20181130202328.65359-2-kirill.shutemov@linux.intel.comSigned-off-by: Sasha Levin <sashal@kernel.org>

arch/x86/include/asm/pgtable_64_types.h

@@ -94,6 +94,11 @@ typedef struct { pteval_t pte; } pte_t;
 # define __VMEMMAP_BASE		_AC(0xffffea0000000000, UL)
 #endif
 
+#define GUARD_HOLE_PGD_ENTRY	-256UL
+#define GUARD_HOLE_SIZE		(16UL << PGDIR_SHIFT)
+#define GUARD_HOLE_BASE_ADDR	(GUARD_HOLE_PGD_ENTRY << PGDIR_SHIFT)
+#define GUARD_HOLE_END_ADDR	(GUARD_HOLE_BASE_ADDR + GUARD_HOLE_SIZE)
+
 #define LDT_PGD_ENTRY		-240UL
 #define LDT_BASE_ADDR		(LDT_PGD_ENTRY << PGDIR_SHIFT)
 

arch/x86/mm/dump_pagetables.c

@@ -465,11 +465,11 @@ static inline bool is_hypervisor_range(int idx)
 {
 #ifdef CONFIG_X86_64
 	/*
-	 * ffff800000000000 - ffff87ffffffffff is reserved for
-	 * the hypervisor.
+	 * A hole in the beginning of kernel address space reserved
+	 * for a hypervisor.
 	 */
-	return	(idx >= pgd_index(__PAGE_OFFSET) - 16) &&
-		(idx <  pgd_index(__PAGE_OFFSET));
+	return	(idx >= pgd_index(GUARD_HOLE_BASE_ADDR)) &&
+		(idx <  pgd_index(GUARD_HOLE_END_ADDR));
 #else
 	return false;
 #endif

arch/x86/xen/mmu_pv.c

@@ -614,19 +614,20 @@ static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd,
 			  unsigned long limit)
 {
 	int i, nr, flush = 0;
-	unsigned hole_low, hole_high;
+	unsigned hole_low = 0, hole_high = 0;
 
 	/* The limit is the last byte to be touched */
 	limit--;
 	BUG_ON(limit >= FIXADDR_TOP);
 
+#ifdef CONFIG_X86_64
 	/*
 	 * 64-bit has a great big hole in the middle of the address
-	 * space, which contains the Xen mappings.  On 32-bit these
-	 * will end up making a zero-sized hole and so is a no-op.
+	 * space, which contains the Xen mappings.
 	 */
-	hole_low = pgd_index(USER_LIMIT);
-	hole_high = pgd_index(PAGE_OFFSET);
+	hole_low = pgd_index(GUARD_HOLE_BASE_ADDR);
+	hole_high = pgd_index(GUARD_HOLE_END_ADDR);
+#endif
 
 	nr = pgd_index(limit) + 1;
 	for (i = 0; i < nr; i++) {