[PATCH 01/24] x86/mm/kaiser: Disable global pages by default with KAISER

[Ingo Molnar]

From: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>

Global pages stay in the TLB across context switches.  Since all contexts
share the same kernel mapping, these mappings are marked as global pages
so kernel entries in the TLB are not flushed out on a context switch.

But, even having these entries in the TLB opens up something that an
attacker can use, such as the double-page-fault attack:

   http://www.ieee-security.org/TC/SP2013/papers/4977a191.pdf

That means that even when KAISER switches page tables on return to user
space the global pages would stay in the TLB cache.

Disable global pages so that kernel TLB entries can be flushed before
returning to user space. This way, all accesses to kernel addresses from
userspace result in a TLB miss independent of the existence of a kernel
mapping.

Replace _PAGE_GLOBAL by __PAGE_KERNEL_GLOBAL and keep _PAGE_GLOBAL
available so that it can still be used for a few selected kernel mappings
which must be visible to userspace, when KAISER is enabled, like the
entry/exit code and data.

Signed-off-by: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Reviewed-by: Borislav Petkov <bp@xxxxxxx>
Reviewed-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Reviewed-by: Rik van Riel <riel@xxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Brian Gerst <brgerst@xxxxxxxxx>
Cc: Denys Vlasenko <dvlasenk@xxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: daniel.gruss@xxxxxxxxxxxxxx
Cc: hughd@xxxxxxxxxx
Cc: keescook@xxxxxxxxxx
Cc: linux-mm@xxxxxxxxx
Cc: michael.schwarz@xxxxxxxxxxxxxx
Cc: moritz.lipp@xxxxxxxxxxxxxx
Cc: richard.fellner@xxxxxxxxxxxxxxxxx
Link: https://lkml.kernel.org/r/20171123003441.63DDFC6F@xxxxxxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 arch/x86/include/asm/pgtable_types.h | 17 ++++++++++++++++-
 arch/x86/mm/pageattr.c               | 16 ++++++++--------
 2 files changed, 24 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 9e9b05fc4860..84fb12404618 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -180,8 +180,23 @@ enum page_cache_mode {
 #define PAGE_READONLY_EXEC	__pgprot(_PAGE_PRESENT | _PAGE_USER |	\
 					 _PAGE_ACCESSED)
 
+/*
+ * Disable global pages for anything using the default
+ * __PAGE_KERNEL* macros.
+ *
+ * PGE will still be enabled and _PAGE_GLOBAL may still be used carefully
+ * for a few selected kernel mappings which must be visible to userspace,
+ * when KAISER is enabled, like the entry/exit code and data.
+ */
+#ifdef CONFIG_KAISER
+#define __PAGE_KERNEL_GLOBAL	0
+#else
+#define __PAGE_KERNEL_GLOBAL	_PAGE_GLOBAL
+#endif
+
 #define __PAGE_KERNEL_EXEC						\
-	(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_GLOBAL)
+	(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED |	\
+	 __PAGE_KERNEL_GLOBAL)
 #define __PAGE_KERNEL		(__PAGE_KERNEL_EXEC | _PAGE_NX)
 
 #define __PAGE_KERNEL_RO		(__PAGE_KERNEL & ~_PAGE_RW)
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 3fe68483463c..ffe584fa1f5e 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -585,9 +585,9 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 	 * for the ancient hardware that doesn't support it.
 	 */
 	if (pgprot_val(req_prot) & _PAGE_PRESENT)
-		pgprot_val(req_prot) |= _PAGE_PSE | _PAGE_GLOBAL;
+		pgprot_val(req_prot) |= _PAGE_PSE | __PAGE_KERNEL_GLOBAL;
 	else
-		pgprot_val(req_prot) &= ~(_PAGE_PSE | _PAGE_GLOBAL);
+		pgprot_val(req_prot) &= ~(_PAGE_PSE | __PAGE_KERNEL_GLOBAL);
 
 	req_prot = canon_pgprot(req_prot);
 
@@ -705,9 +705,9 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
 	 * for the ancient hardware that doesn't support it.
 	 */
 	if (pgprot_val(ref_prot) & _PAGE_PRESENT)
-		pgprot_val(ref_prot) |= _PAGE_GLOBAL;
+		pgprot_val(ref_prot) |= __PAGE_KERNEL_GLOBAL;
 	else
-		pgprot_val(ref_prot) &= ~_PAGE_GLOBAL;
+		pgprot_val(ref_prot) &= ~__PAGE_KERNEL_GLOBAL;
 
 	/*
 	 * Get the target pfn from the original entry:
@@ -938,9 +938,9 @@ static void populate_pte(struct cpa_data *cpa,
 	 * support it.
 	 */
 	if (pgprot_val(pgprot) & _PAGE_PRESENT)
-		pgprot_val(pgprot) |= _PAGE_GLOBAL;
+		pgprot_val(pgprot) |= __PAGE_KERNEL_GLOBAL;
 	else
-		pgprot_val(pgprot) &= ~_PAGE_GLOBAL;
+		pgprot_val(pgprot) &= ~__PAGE_KERNEL_GLOBAL;
 
 	pgprot = canon_pgprot(pgprot);
 
@@ -1242,9 +1242,9 @@ static int __change_page_attr(struct cpa_data *cpa, int primary)
 		 * support it.
 		 */
 		if (pgprot_val(new_prot) & _PAGE_PRESENT)
-			pgprot_val(new_prot) |= _PAGE_GLOBAL;
+			pgprot_val(new_prot) |= __PAGE_KERNEL_GLOBAL;
 		else
-			pgprot_val(new_prot) &= ~_PAGE_GLOBAL;
+			pgprot_val(new_prot) &= ~__PAGE_KERNEL_GLOBAL;
 
 		/*
 		 * We need to keep the pfn from the existing PTE,
-- 
2.14.1