The existing arm64 stack randomization uses the kernel rng to acquire 5 bits of address space randomization. This is problematic because it creates non determinism in the syscall path when the rng needs to be generated or reseeded. This shows up as large tail latencies in some benchmarks and directly affects the minimum RT latencies as seen by cyclictest.
Other architectures are using timers/cycle counters for this function, which is sketchy from a randomization perspective because it should be possible to estimate this value from knowledge of the syscall return time, and from reading the current value of the timer/counters. So, a poor rng should be better than the cycle counter if it is hard to extract the stack offsets sufficiently to be able to detect the PRNG's period. Lets downgrade from get_random_u16() to prandom_u32_state() under the theory that the danger of someone guessing the 1 in 32 per call offset, is larger than that of being able to extract sufficient history to accurately predict future offsets. Further it should be safer to run with prandom_u32_state than disabling stack randomization for those subset of applications where the difference in latency is on the order of ~5X worse. Reported-by: James Yang <james.y...@arm.com> Reported-by: Shiyou Huang <shiyou.hu...@arm.com> Signed-off-by: Jeremy Linton <jeremy.lin...@arm.com> --- arch/arm64/kernel/syscall.c | 42 ++++++++++++++++++++++++++++++++++++- 1 file changed, 41 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 9a70d9746b66..33b3ea4adff8 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/prandom.h> #include <linux/randomize_kstack.h> #include <linux/syscalls.h> @@ -37,6 +38,45 @@ static long __invoke_syscall(struct pt_regs *regs, syscall_fn_t syscall_fn) return syscall_fn(regs); } +#ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET +DEFINE_PER_CPU(struct rnd_state, kstackrng); + +static u16 kstack_rng(void) +{ + u32 rng = prandom_u32_state(this_cpu_ptr(&kstackrng)); + + return rng & 0x1ff; +} + +/* Should we reseed? */ +static int kstack_rng_setup(unsigned int cpu) +{ + u32 rng_seed; + + /* zero should be avoided as a seed */ + do { + rng_seed = get_random_u32(); + } while (!rng_seed); + prandom_seed_state(this_cpu_ptr(&kstackrng), rng_seed); + return 0; +} + +static int kstack_init(void) +{ + int ret; + + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "arm64/cpuinfo:kstackrandomize", + kstack_rng_setup, NULL); + if (ret < 0) + pr_err("kstack: failed to register rng callbacks.\n"); + return 0; +} + +arch_initcall(kstack_init); +#else +static u16 kstack_rng(void) { return 0; } +#endif /* CONFIG_RANDOMIZE_KSTACK_OFFSET */ + static void invoke_syscall(struct pt_regs *regs, unsigned int scno, unsigned int sc_nr, const syscall_fn_t syscall_table[]) @@ -66,7 +106,7 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno, * * The resulting 5 bits of entropy is seen in SP[8:4]. */ - choose_random_kstack_offset(get_random_u16() & 0x1FF); + choose_random_kstack_offset(kstack_rng()); } static inline bool has_syscall_work(unsigned long flags) -- 2.43.0