arm64: entry: Enable random_kstack_offset support

Allow for a randomized stack offset on a per-syscall basis, with roughly
5 bits of entropy. (And include AAPCS rationale AAPCS thanks to Mark
Rutland.)

In order to avoid unconditional stack canaries on syscall entry (due to
the use of alloca()), also disable stack protector to avoid triggering
needless checks and slowing down the entry path. As there is no general
way to control stack protector coverage with a function attribute[1],
this must be disabled at the compilation unit level. This isn't a problem
here, though, since stack protector was not triggered before: examining
the resulting syscall.o, there are no changes in canary coverage (none
before, none now).

[1] a working __attribute__((no_stack_protector)) has been added to GCC
and Clang but has not been released in any version yet:
https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=346b302d09c1e6db56d9fe69048acb32fbb97845
https://reviews.llvm.org/rG4fbf84c1732fca596ad1d6e96015e19760eb8a9bSigned-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20210401232347.2791257-6-keescook@chromium.org

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

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	\

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)