[PATCH 41/43] x86/mm/kaiser: Un-poison PGDs at runtime

[Ingo Molnar]

From: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>

With KAISER Kernel PGDs that map userspace are "poisoned" with
the NX bit.  This ensures that if a kernel->user CR3 switch is
missed, userspace crashes instead of running in an unhardened
state.

This code will be needed in a moment when KAISER is turned
on and off at runtime.

Note that an __ASSEMBLY__ #ifdef is now required since kaiser.h
is indirectly included into assembly.

Signed-off-by: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Brian Gerst <brgerst@xxxxxxxxx>
Cc: Daniel Gruss <daniel.gruss@xxxxxxxxxxxxxx>
Cc: Denys Vlasenko <dvlasenk@xxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
Cc: Kees Cook <keescook@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Michael Schwarz <michael.schwarz@xxxxxxxxxxxxxx>
Cc: Moritz Lipp <moritz.lipp@xxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Richard Fellner <richard.fellner@xxxxxxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: linux-mm@xxxxxxxxx
Link: http://lkml.kernel.org/r/20171123003521.A90AC3AF@xxxxxxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 arch/x86/include/asm/pgtable_64.h | 16 +++++++++++++++-
 arch/x86/mm/kaiser.c              | 38 ++++++++++++++++++++++++++++++++++++++
 include/linux/kaiser.h            |  3 ++-
 3 files changed, 55 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index c239839e92bd..89bde2091af1 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -3,6 +3,7 @@
 #define _ASM_X86_PGTABLE_64_H
 
 #include <linux/const.h>
+#include <linux/kaiser.h>
 #include <asm/pgtable_64_types.h>
 
 #ifndef __ASSEMBLY__
@@ -199,6 +200,18 @@ static inline bool pgd_userspace_access(pgd_t pgd)
 	return pgd.pgd & _PAGE_USER;
 }
 
+static inline void kaiser_poison_pgd(pgd_t *pgd)
+{
+	if (pgd->pgd & _PAGE_PRESENT)
+		pgd->pgd |= _PAGE_NX;
+}
+
+static inline void kaiser_unpoison_pgd(pgd_t *pgd)
+{
+	if (pgd->pgd & _PAGE_PRESENT)
+		pgd->pgd &= ~_PAGE_NX;
+}
+
 /*
  * Take a PGD location (pgdp) and a pgd value that needs
  * to be set there.  Populates the shadow and returns
@@ -222,7 +235,8 @@ static inline pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd)
 			 * wrong CR3 value, userspace will crash
 			 * instead of running.
 			 */
-			pgd.pgd |= _PAGE_NX;
+			if (kaiser_active())
+				kaiser_poison_pgd(&pgd);
 		}
 	} else if (pgd_userspace_access(*pgdp)) {
 		/*
diff --git a/arch/x86/mm/kaiser.c b/arch/x86/mm/kaiser.c
index 968d5b62d597..06966b111280 100644
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -501,6 +501,9 @@ static ssize_t kaiser_enabled_write_file(struct file *file,
 	if (enable > 1)
 		return -EINVAL;
 
+	if (kaiser_enabled == enable)
+		return count;
+
 	WRITE_ONCE(kaiser_enabled, enable);
 	return count;
 }
@@ -518,3 +521,38 @@ static int __init create_kaiser_enabled(void)
 	return 0;
 }
 late_initcall(create_kaiser_enabled);
+
+enum poison {
+	KAISER_POISON,
+	KAISER_UNPOISON
+};
+void kaiser_poison_pgd_page(pgd_t *pgd_page, enum poison do_poison)
+{
+	int i = 0;
+
+	for (i = 0; i < PTRS_PER_PGD; i++) {
+		pgd_t *pgd = &pgd_page[i];
+
+		/* Stop once we hit kernel addresses: */
+		if (!pgdp_maps_userspace(pgd))
+			break;
+
+		if (do_poison == KAISER_POISON)
+			kaiser_poison_pgd(pgd);
+		else
+			kaiser_unpoison_pgd(pgd);
+	}
+
+}
+
+void kaiser_poison_pgds(enum poison do_poison)
+{
+	struct page *page;
+
+	spin_lock(&pgd_lock);
+	list_for_each_entry(page, &pgd_list, lru) {
+		pgd_t *pgd = (pgd_t *)page_address(page);
+		kaiser_poison_pgd_page(pgd, do_poison);
+	}
+	spin_unlock(&pgd_lock);
+}
diff --git a/include/linux/kaiser.h b/include/linux/kaiser.h
index a3d28d00d555..83d465599646 100644
--- a/include/linux/kaiser.h
+++ b/include/linux/kaiser.h
@@ -4,7 +4,7 @@
 #ifdef CONFIG_KAISER
 #include <asm/kaiser.h>
 #else
-
+#ifndef __ASSEMBLY__
 /*
  * These stubs are used whenever CONFIG_KAISER is off, which
  * includes architectures that support KAISER, but have it
@@ -33,5 +33,6 @@ static inline bool kaiser_active(void)
 {
 	return 0;
 }
+#endif /* __ASSEMBLY__ */
 #endif /* !CONFIG_KAISER */
 #endif /* _INCLUDE_KAISER_H */
-- 
2.14.1