KAISER: Kernel Address Isolation

This patch introduces our implementation of KAISER (Kernel Address Isolation to
have Side-channels Efficiently Removed), a kernel isolation technique to close
hardware side channels on kernel address information.

More information about the patch can be found on:

        https://github.com/IAIK/KAISER

From: Richard Fellner <richard.fellner@student.tugraz.at>
From: Daniel Gruss <daniel.gruss@iaik.tugraz.at>
Subject: [RFC, PATCH] x86_64: KAISER - do not map kernel in user mode
Date: Thu, 4 May 2017 14:26:50 +0200
Link: http://marc.info/?l=linux-kernel&m=149390087310405&w=2
Kaiser-4.10-SHA1: c4b1831d44c6144d3762ccc72f0c4e71a0c713e5

To: <linux-kernel@vger.kernel.org>
To: <kernel-hardening@lists.openwall.com>
Cc: <clementine.maurice@iaik.tugraz.at>
Cc: <moritz.lipp@iaik.tugraz.at>
Cc: Michael Schwarz <michael.schwarz@iaik.tugraz.at>
Cc: Richard Fellner <richard.fellner@student.tugraz.at>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: <kirill.shutemov@linux.intel.com>
Cc: <anders.fogh@gdata-adan.de>

After several recent works [1,2,3] KASLR on x86_64 was basically
considered dead by many researchers. We have been working on an
efficient but effective fix for this problem and found that not mapping
the kernel space when running in user mode is the solution to this
problem [4] (the corresponding paper [5] will be presented at ESSoS17).

With this RFC patch we allow anybody to configure their kernel with the
flag CONFIG_KAISER to add our defense mechanism.

If there are any questions we would love to answer them.
We also appreciate any comments!

Cheers,
Daniel (+ the KAISER team from Graz University of Technology)

[1] http://www.ieee-security.org/TC/SP2013/papers/4977a191.pdf
[2] https://www.blackhat.com/docs/us-16/materials/us-16-Fogh-Using-Undocumented-CPU-Behaviour-To-See-Into-Kernel-Mode-And-Break-KASLR-In-The-Process.pdf
[3] https://www.blackhat.com/docs/us-16/materials/us-16-Jang-Breaking-Kernel-Address-Space-Layout-Randomization-KASLR-With-Intel-TSX.pdf
[4] https://github.com/IAIK/KAISER
[5] https://gruss.cc/files/kaiser.pdf

(cherry picked from Change-Id: I0eb000c33290af01fc4454ca0c701d00f1d30b1d)

Conflicts:
arch/x86/entry/entry_64.S (not in this tree)
arch/x86/kernel/entry_64.S (patched instead of that)
arch/x86/entry/entry_64_compat.S (not in this tree)
arch/x86/ia32/ia32entry.S (patched instead of that)
arch/x86/include/asm/hw_irq.h
arch/x86/include/asm/pgtable_types.h
arch/x86/include/asm/processor.h
arch/x86/kernel/irqinit.c
arch/x86/kernel/process.c
arch/x86/mm/Makefile
arch/x86/mm/pgtable.c
init/main.c

Signed-off-by: Hugh Dickins <hughd@google.com>
[bwh: Folded in the follow-up patches from Hugh:
 - kaiser: merged update
 - kaiser: do not set _PAGE_NX on pgd_none
 - kaiser: stack map PAGE_SIZE at THREAD_SIZE-PAGE_SIZE
 - kaiser: fix build and FIXME in alloc_ldt_struct()
 - kaiser: KAISER depends on SMP
 - kaiser: fix regs to do_nmi() ifndef CONFIG_KAISER
 - kaiser: fix perf crashes
 - kaiser: ENOMEM if kaiser_pagetable_walk() NULL
 - kaiser: tidied up asm/kaiser.h somewhat
 - kaiser: tidied up kaiser_add/remove_mapping slightly
 - kaiser: kaiser_remove_mapping() move along the pgd
 - kaiser: align addition to x86/mm/Makefile
 - kaiser: cleanups while trying for gold link
 - kaiser: name that 0x1000 KAISER_SHADOW_PGD_OFFSET
 - kaiser: delete KAISER_REAL_SWITCH option
 - kaiser: vmstat show NR_KAISERTABLE as nr_overhead
 - kaiser: enhanced by kernel and user PCIDs
 - kaiser: load_new_mm_cr3() let SWITCH_USER_CR3 flush user
 - kaiser: PCID 0 for kernel and 128 for user
 - kaiser: x86_cr3_pcid_noflush and x86_cr3_pcid_user
 - kaiser: paranoid_entry pass cr3 need to paranoid_exit
 - kaiser: _pgd_alloc() without __GFP_REPEAT to avoid stalls
 - kaiser: fix unlikely error in alloc_ldt_struct()
 - kaiser: drop is_atomic arg to kaiser_pagetable_walk()
 Backported to 3.16:
 - Add missing #include in arch/x86/mm/kaiser.c
 - Use variable PEBS buffer size since we have "perf/x86/intel: Use PAGE_SIZE
   for PEBS buffer size on Core2"
 - Renumber X86_FEATURE_INVPCID_SINGLE to avoid collision
 - Adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>

4 files changed, 92 insertions, 2 deletions

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index c1c0b0cf39b4..4191efe77e36 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -689,7 +689,14 @@
  */
 #define PERCPU_INPUT(cacheline)						\
 	VMLINUX_SYMBOL(__per_cpu_start) = .;				\
+	VMLINUX_SYMBOL(__per_cpu_user_mapped_start) = .;		\
 	*(.data..percpu..first)						\
+	. = ALIGN(cacheline);						\
+	*(.data..percpu..user_mapped)					\
+	*(.data..percpu..user_mapped..shared_aligned)			\
+	. = ALIGN(PAGE_SIZE);						\
+	*(.data..percpu..user_mapped..page_aligned)			\
+	VMLINUX_SYMBOL(__per_cpu_user_mapped_end) = .;			\
 	. = ALIGN(PAGE_SIZE);						\
 	*(.data..percpu..page_aligned)					\
 	. = ALIGN(cacheline);						\
diff --git a/include/linux/kaiser.h b/include/linux/kaiser.h
new file mode 100644
index 000000000000..4a4d6d911a14
--- /dev/null
+++ b/include/linux/kaiser.h
@@ -0,0 +1,52 @@
+#ifndef _LINUX_KAISER_H
+#define _LINUX_KAISER_H
+
+#ifdef CONFIG_KAISER
+#include <asm/kaiser.h>
+
+static inline int kaiser_map_thread_stack(void *stack)
+{
+	/*
+	 * Map that page of kernel stack on which we enter from user context.
+	 */
+	return kaiser_add_mapping((unsigned long)stack +
+			THREAD_SIZE - PAGE_SIZE, PAGE_SIZE, __PAGE_KERNEL);
+}
+
+static inline void kaiser_unmap_thread_stack(void *stack)
+{
+	/*
+	 * Note: may be called even when kaiser_map_thread_stack() failed.
+	 */
+	kaiser_remove_mapping((unsigned long)stack +
+			THREAD_SIZE - PAGE_SIZE, PAGE_SIZE);
+}
+#else
+
+/*
+ * These stubs are used whenever CONFIG_KAISER is off, which
+ * includes architectures that support KAISER, but have it disabled.
+ */
+
+static inline void kaiser_init(void)
+{
+}
+static inline int kaiser_add_mapping(unsigned long addr,
+				     unsigned long size, unsigned long flags)
+{
+	return 0;
+}
+static inline void kaiser_remove_mapping(unsigned long start,
+					 unsigned long size)
+{
+}
+static inline int kaiser_map_thread_stack(void *stack)
+{
+	return 0;
+}
+static inline void kaiser_unmap_thread_stack(void *stack)
+{
+}
+
+#endif /* !CONFIG_KAISER */
+#endif /* _LINUX_KAISER_H */
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index c7eb42235fbe..9fe9377821a5 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -131,8 +131,9 @@ enum zone_stat_item {
 	NR_SLAB_RECLAIMABLE,
 	NR_SLAB_UNRECLAIMABLE,
 	NR_PAGETABLE,		/* used for pagetables */
-	NR_KERNEL_STACK,
 	/* Second 128 byte cacheline */
+	NR_KERNEL_STACK,
+	NR_KAISERTABLE,
 	NR_UNSTABLE_NFS,	/* NFS unstable pages */
 	NR_BOUNCE,
 	NR_VMSCAN_WRITE,
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index dec01d6c3f80..4eb4f90d211b 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -1,6 +1,12 @@
 #ifndef _LINUX_PERCPU_DEFS_H
 #define _LINUX_PERCPU_DEFS_H
 
+#ifdef CONFIG_KAISER
+#define USER_MAPPED_SECTION "..user_mapped"
+#else
+#define USER_MAPPED_SECTION ""
+#endif
+
 /*
  * Base implementations of per-CPU variable declarations and definitions, where
  * the section in which the variable is to be placed is provided by the
@@ -94,6 +100,12 @@
 #define DEFINE_PER_CPU(type, name)					\
 	DEFINE_PER_CPU_SECTION(type, name, "")
 
+#define DECLARE_PER_CPU_USER_MAPPED(type, name)				\
+	DECLARE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION)
+
+#define DEFINE_PER_CPU_USER_MAPPED(type, name)				\
+	DEFINE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION)
+
 /*
  * Declaration/definition used for per-CPU variables that must come first in
  * the set of variables.
@@ -123,6 +135,14 @@
 	DEFINE_PER_CPU_SECTION(type, name, PER_CPU_SHARED_ALIGNED_SECTION) \
 	____cacheline_aligned_in_smp
 
+#define DECLARE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(type, name)		\
+	DECLARE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION PER_CPU_SHARED_ALIGNED_SECTION) \
+	____cacheline_aligned_in_smp
+
+#define DEFINE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(type, name)		\
+	DEFINE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION PER_CPU_SHARED_ALIGNED_SECTION) \
+	____cacheline_aligned_in_smp
+
 #define DECLARE_PER_CPU_ALIGNED(type, name)				\
 	DECLARE_PER_CPU_SECTION(type, name, PER_CPU_ALIGNED_SECTION)	\
 	____cacheline_aligned
@@ -141,11 +161,21 @@
 #define DEFINE_PER_CPU_PAGE_ALIGNED(type, name)				\
 	DEFINE_PER_CPU_SECTION(type, name, "..page_aligned")		\
 	__aligned(PAGE_SIZE)
+/*
+ * Declaration/definition used for per-CPU variables that must be page aligned and need to be mapped in user mode.
+ */
+#define DECLARE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(type, name)		\
+	DECLARE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION"..page_aligned") \
+	__aligned(PAGE_SIZE)
+
+#define DEFINE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(type, name)		\
+	DEFINE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION"..page_aligned") \
+	__aligned(PAGE_SIZE)
 
 /*
  * Declaration/definition used for per-CPU variables that must be read mostly.
  */
-#define DECLARE_PER_CPU_READ_MOSTLY(type, name)			\
+#define DECLARE_PER_CPU_READ_MOSTLY(type, name)				\
 	DECLARE_PER_CPU_SECTION(type, name, "..read_mostly")
 
 #define DEFINE_PER_CPU_READ_MOSTLY(type, name)				\