From 8a43ddfb93a0c6ae1a6e1f5c25705ec5d1843c40 Mon Sep 17 00:00:00 2001 From: Richard Fellner Date: Thu, 4 May 2017 14:26:50 +0200 Subject: 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 From: Daniel Gruss X-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: To: Cc: Cc: Cc: Michael Schwarz Cc: Richard Fellner Cc: Ingo Molnar Cc: Cc: 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 [patch based also on https://raw.githubusercontent.com/IAIK/KAISER/master/KAISER/0001-KAISER-Kernel-Address-Isolation.patch] Signed-off-by: Richard Fellner Signed-off-by: Moritz Lipp Signed-off-by: Daniel Gruss Signed-off-by: Michael Schwarz Acked-by: Jiri Kosina Signed-off-by: Hugh Dickins Signed-off-by: Greg Kroah-Hartman --- include/linux/percpu-defs.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 8f16299ca068..8ea945f63a05 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -35,6 +35,12 @@ #endif +#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 @@ -115,6 +121,12 @@ #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. @@ -144,6 +156,14 @@ 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 @@ -162,6 +182,16 @@ #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. -- cgit v1.2.3 From bed9bb7f3e6d4045013d2bb9e4004896de57f02b Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Wed, 30 Aug 2017 16:23:00 -0700 Subject: kaiser: merged update Merged fixes and cleanups, rebased to 4.4.89 tree (no 5-level paging). Signed-off-by: Dave Hansen Signed-off-by: Hugh Dickins Acked-by: Jiri Kosina Signed-off-by: Greg Kroah-Hartman --- include/linux/kaiser.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) create mode 100644 include/linux/kaiser.h (limited to 'include/linux') diff --git a/include/linux/kaiser.h b/include/linux/kaiser.h new file mode 100644 index 000000000000..9db5433c2284 --- /dev/null +++ b/include/linux/kaiser.h @@ -0,0 +1,26 @@ +#ifndef _INCLUDE_KAISER_H +#define _INCLUDE_KAISER_H + +#ifdef CONFIG_KAISER +#include +#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 void kaiser_remove_mapping(unsigned long start, unsigned long size) +{ +} +static inline int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags) +{ + return 0; +} + +#endif /* !CONFIG_KAISER */ +#endif /* _INCLUDE_KAISER_H */ -- cgit v1.2.3 From 003e476716906afa135faf605ae0a5c3598c0293 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sun, 3 Sep 2017 18:57:03 -0700 Subject: kaiser: stack map PAGE_SIZE at THREAD_SIZE-PAGE_SIZE Kaiser only needs to map one page of the stack; and kernel/fork.c did not build on powerpc (no __PAGE_KERNEL). It's all cleaner if linux/kaiser.h provides kaiser_map_thread_stack() and kaiser_unmap_thread_stack() wrappers around asm/kaiser.h's kaiser_add_mapping() and kaiser_remove_mapping(). And use linux/kaiser.h in init/main.c to avoid the #ifdefs there. Signed-off-by: Hugh Dickins Acked-by: Jiri Kosina Signed-off-by: Greg Kroah-Hartman --- include/linux/kaiser.h | 40 +++++++++++++++++++++++++++++++++------- 1 file changed, 33 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kaiser.h b/include/linux/kaiser.h index 9db5433c2284..4a4d6d911a14 100644 --- a/include/linux/kaiser.h +++ b/include/linux/kaiser.h @@ -1,26 +1,52 @@ -#ifndef _INCLUDE_KAISER_H -#define _INCLUDE_KAISER_H +#ifndef _LINUX_KAISER_H +#define _LINUX_KAISER_H #ifdef CONFIG_KAISER #include + +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. + * includes architectures that support KAISER, but have it disabled. */ static inline void kaiser_init(void) { } -static inline void kaiser_remove_mapping(unsigned long start, unsigned long size) +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_add_mapping(unsigned long addr, unsigned long size, unsigned long flags) +static inline int kaiser_map_thread_stack(void *stack) { return 0; } +static inline void kaiser_unmap_thread_stack(void *stack) +{ +} #endif /* !CONFIG_KAISER */ -#endif /* _INCLUDE_KAISER_H */ +#endif /* _LINUX_KAISER_H */ -- cgit v1.2.3 From c52e55a2a82d3a44189810d35717d81cb4cf61d4 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 21 Aug 2017 20:11:43 -0700 Subject: kaiser: cleanups while trying for gold link While trying to get our gold link to work, four cleanups: matched the gdt_page declaration to its definition; in fiddling unsuccessfully with PERCPU_INPUT(), lined up backslashes; lined up the backslashes according to convention in percpu-defs.h; deleted the unused irq_stack_pointer addition to irq_stack_union. Sad to report that aligning backslashes does not appear to help gold align to 8192: but while these did not help, they are worth keeping. Signed-off-by: Hugh Dickins Acked-by: Jiri Kosina Signed-off-by: Greg Kroah-Hartman --- include/linux/percpu-defs.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 8ea945f63a05..cfe13cb4ec63 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -121,10 +121,10 @@ #define DEFINE_PER_CPU(type, name) \ DEFINE_PER_CPU_SECTION(type, name, "") -#define DECLARE_PER_CPU_USER_MAPPED(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 DEFINE_PER_CPU_USER_MAPPED(type, name) \ DEFINE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION) /* @@ -156,11 +156,11 @@ 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) \ +#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 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 @@ -185,18 +185,18 @@ /* * 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 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) +#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) \ -- cgit v1.2.3 From 3e3d38fd9832e82a8cb1a5b1154acfa43ac08d15 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sat, 9 Sep 2017 21:27:32 -0700 Subject: kaiser: vmstat show NR_KAISERTABLE as nr_overhead The kaiser update made an interesting choice, never to free any shadow page tables. Contention on global spinlock was worrying, particularly with it held across page table scans when freeing. Something had to be done: I was going to add refcounting; but simply never to free them is an appealing choice, minimizing contention without complicating the code (the more a page table is found already, the less the spinlock is used). But leaking pages in this way is also a worry: can we get away with it? At the very least, we need a count to show how bad it actually gets: in principle, one might end up wasting about 1/256 of memory that way (1/512 for when direct-mapped pages have to be user-mapped, plus 1/512 for when they are user-mapped from the vmalloc area on another occasion (but we don't have vmalloc'ed stacks, so only large ldts are vmalloc'ed). Add per-cpu stat NR_KAISERTABLE: including 256 at startup for the shared pgd entries, and 1 for each intermediate page table added thereafter for user-mapping - but leave out the 1 per mm, for its shadow pgd, because that distracts from the monotonic increase. Shown in /proc/vmstat as nr_overhead (0 if kaiser not enabled). In practice, it doesn't look so bad so far: more like 1/12000 after nine hours of gtests below; and movable pageblock segregation should tend to cluster the kaiser tables into a subset of the address space (if not, they will be bad for compaction too). But production may tell a different story: keep an eye on this number, and bring back lighter freeing if it gets out of control (maybe a shrinker). Signed-off-by: Hugh Dickins Acked-by: Jiri Kosina Signed-off-by: Greg Kroah-Hartman --- include/linux/mmzone.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ff88d6189411..b93b578cfa42 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, -- cgit v1.2.3 From 3e1457d6bf26d9ec300781f84cd0057e44deb45d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 3 Jan 2018 10:43:15 -0800 Subject: KPTI: Rename to PAGE_TABLE_ISOLATION This renames CONFIG_KAISER to CONFIG_PAGE_TABLE_ISOLATION. Signed-off-by: Kees Cook Signed-off-by: Greg Kroah-Hartman --- include/linux/kaiser.h | 6 +++--- include/linux/percpu-defs.h | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kaiser.h b/include/linux/kaiser.h index 4a4d6d911a14..58c55b1589d0 100644 --- a/include/linux/kaiser.h +++ b/include/linux/kaiser.h @@ -1,7 +1,7 @@ #ifndef _LINUX_KAISER_H #define _LINUX_KAISER_H -#ifdef CONFIG_KAISER +#ifdef CONFIG_PAGE_TABLE_ISOLATION #include static inline int kaiser_map_thread_stack(void *stack) @@ -24,7 +24,7 @@ static inline void kaiser_unmap_thread_stack(void *stack) #else /* - * These stubs are used whenever CONFIG_KAISER is off, which + * These stubs are used whenever CONFIG_PAGE_TABLE_ISOLATION is off, which * includes architectures that support KAISER, but have it disabled. */ @@ -48,5 +48,5 @@ static inline void kaiser_unmap_thread_stack(void *stack) { } -#endif /* !CONFIG_KAISER */ +#endif /* !CONFIG_PAGE_TABLE_ISOLATION */ #endif /* _LINUX_KAISER_H */ diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index cfe13cb4ec63..8902f23bb770 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -35,7 +35,7 @@ #endif -#ifdef CONFIG_KAISER +#ifdef CONFIG_PAGE_TABLE_ISOLATION #define USER_MAPPED_SECTION "..user_mapped" #else #define USER_MAPPED_SECTION "" -- cgit v1.2.3