Merge tag 'x86-entry-2021-04-26' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull entry code update from Thomas Gleixner:
 "Provide support for randomized stack offsets per syscall to make
  stack-based attacks harder which rely on the deterministic stack
  layout.

  The feature is based on the original idea of PaX's RANDSTACK feature,
  but uses a significantly different implementation.

  The offset does not affect the pt_regs location on the task stack as
  this was agreed on to be of dubious value. The offset is applied
  before the actual syscall is invoked.

  The offset is stored per cpu and the randomization happens at the end
  of the syscall which is less predictable than on syscall entry.

  The mechanism to apply the offset is via alloca(), i.e. abusing the
  dispised VLAs. This comes with the drawback that
  stack-clash-protection has to be disabled for the affected compilation
  units and there is also a negative interaction with stack-protector.

  Those downsides are traded with the advantage that this approach does
  not require any intrusive changes to the low level assembly entry
  code, does not affect the unwinder and the correct stack alignment is
  handled automatically by the compiler.

  The feature is guarded with a static branch which avoids the overhead
  when disabled.

  Currently this is supported for X86 and ARM64"

* tag 'x86-entry-2021-04-26' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  arm64: entry: Enable random_kstack_offset support
  lkdtm: Add REPORT_STACK for checking stack offsets
  x86/entry: Enable random_kstack_offset support
  stack: Optionally randomize kernel stack offset each syscall
  init_on_alloc: Optimize static branches
  jump_label: Provide CONFIG-driven build state defaults

7 files changed, 65 insertions, 0 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index ecfd3520b676..6b11c825fc36 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1054,6 +1054,29 @@ config VMAP_STACK
 	  backing virtual mappings with real shadow memory, and KASAN_VMALLOC
 	  must be enabled.
 
+config HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
+	def_bool n
+	help
+	  An arch should select this symbol if it can support kernel stack
+	  offset randomization with calls to add_random_kstack_offset()
+	  during syscall entry and choose_random_kstack_offset() during
+	  syscall exit. Careful removal of -fstack-protector-strong and
+	  -fstack-protector should also be applied to the entry code and
+	  closely examined, as the artificial stack bump looks like an array
+	  to the compiler, so it will attempt to add canary checks regardless
+	  of the static branch state.
+
+config RANDOMIZE_KSTACK_OFFSET_DEFAULT
+	bool "Randomize kernel stack offset on syscall entry"
+	depends on HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
+	help
+	  The kernel stack offset can be randomized (after pt_regs) by
+	  roughly 5 bits of entropy, frustrating memory corruption
+	  attacks that depend on stack address determinism or
+	  cross-syscall address exposures. This feature is controlled
+	  by kernel boot param "randomize_kstack_offset=on/off", and this
+	  config chooses the default boot state.
+
 config ARCH_OPTIONAL_KERNEL_RWX
 	def_bool n
 
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index dfdc3e0af5e1..f1a032ed2274 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -146,6 +146,7 @@ config ARM64
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
 	select HAVE_ARCH_PFN_VALID
 	select HAVE_ARCH_PREL32_RELOCATIONS
+	select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_STACKLEAK
 	select HAVE_ARCH_THREAD_STRUCT_WHITELIST
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index ed65576ce710..6cc97730790e 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -9,6 +9,11 @@ CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_insn.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE)
 
+# Remove stack protector to avoid triggering unneeded stack canary
+# checks due to randomize_kstack_offset.
+CFLAGS_REMOVE_syscall.o	 = -fstack-protector -fstack-protector-strong
+CFLAGS_syscall.o	+= -fno-stack-protector
+
 # Object file lists.
 obj-y			:= debug-monitors.o entry.o irq.o fpsimd.o		\
 			   entry-common.o entry-fpsimd.o process.o ptrace.o	\
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index b9cf12b271d7..263d6c1a525f 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -5,6 +5,7 @@
 #include <linux/errno.h>
 #include <linux/nospec.h>
 #include <linux/ptrace.h>
+#include <linux/randomize_kstack.h>
 #include <linux/syscalls.h>
 
 #include <asm/daifflags.h>
@@ -43,6 +44,8 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno,
 {
 	long ret;
 
+	add_random_kstack_offset();
+
 	if (scno < sc_nr) {
 		syscall_fn_t syscall_fn;
 		syscall_fn = syscall_table[array_index_nospec(scno, sc_nr)];
@@ -55,6 +58,19 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno,
 		ret = lower_32_bits(ret);
 
 	regs->regs[0] = ret;
+
+	/*
+	 * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(),
+	 * but not enough for arm64 stack utilization comfort. To keep
+	 * reasonable stack head room, reduce the maximum offset to 9 bits.
+	 *
+	 * The actual entropy will be further reduced by the compiler when
+	 * applying stack alignment constraints: the AAPCS mandates a
+	 * 16-byte (i.e. 4-bit) aligned SP at function boundaries.
+	 *
+	 * The resulting 5 bits of entropy is seen in SP[8:4].
+	 */
+	choose_random_kstack_offset(get_random_int() & 0x1FF);
 }
 
 static inline bool has_syscall_work(unsigned long flags)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6e0b08310949..f3db131be563 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -165,6 +165,7 @@ config X86
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64
 	select HAVE_ARCH_USERFAULTFD_WP         if X86_64 && USERFAULTFD
 	select HAVE_ARCH_VMAP_STACK		if X86_64
+	select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
 	select HAVE_ARCH_WITHIN_STACK_FRAMES
 	select HAVE_ASM_MODVERSIONS
 	select HAVE_CMPXCHG_DOUBLE
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 4efd39aacb9f..7b2542b13ebd 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -38,6 +38,7 @@
 #ifdef CONFIG_X86_64
 __visible noinstr void do_syscall_64(unsigned long nr, struct pt_regs *regs)
 {
+	add_random_kstack_offset();
 	nr = syscall_enter_from_user_mode(regs, nr);
 
 	instrumentation_begin();
@@ -83,6 +84,7 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
 {
 	unsigned int nr = syscall_32_enter(regs);
 
+	add_random_kstack_offset();
 	/*
 	 * Subtlety here: if ptrace pokes something larger than 2^32-1 into
 	 * orig_ax, the unsigned int return value truncates it.  This may
@@ -102,6 +104,7 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
 	unsigned int nr = syscall_32_enter(regs);
 	int res;
 
+	add_random_kstack_offset();
 	/*
 	 * This cannot use syscall_enter_from_user_mode() as it has to
 	 * fetch EBP before invoking any of the syscall entry work
diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h
index 2b87b191b3b8..14ebd2196569 100644
--- a/arch/x86/include/asm/entry-common.h
+++ b/arch/x86/include/asm/entry-common.h
@@ -2,6 +2,7 @@
 #ifndef _ASM_X86_ENTRY_COMMON_H
 #define _ASM_X86_ENTRY_COMMON_H
 
+#include <linux/randomize_kstack.h>
 #include <linux/user-return-notifier.h>
 
 #include <asm/nospec-branch.h>
@@ -70,6 +71,21 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 	 */
 	current_thread_info()->status &= ~(TS_COMPAT | TS_I386_REGS_POKED);
 #endif
+
+	/*
+	 * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(),
+	 * but not enough for x86 stack utilization comfort. To keep
+	 * reasonable stack head room, reduce the maximum offset to 8 bits.
+	 *
+	 * The actual entropy will be further reduced by the compiler when
+	 * applying stack alignment constraints (see cc_stack_align4/8 in
+	 * arch/x86/Makefile), which will remove the 3 (x86_64) or 2 (ia32)
+	 * low bits from any entropy chosen here.
+	 *
+	 * Therefore, final stack offset entropy will be 5 (x86_64) or
+	 * 6 (ia32) bits.
+	 */
+	choose_random_kstack_offset(rdtsc() & 0xFF);
 }
 #define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare