Re: [PATCH v7 24/39] arm64/signal: Set up and restore the GCS context for signal handlers

[Thiago Jung Bauermann <thiago.bauermann@linaro.org>]

Mark Brown <broonie@kernel.org> writes:

> +static bool gcs_signal_cap_valid(u64 addr, u64 val)
> +{
> +	/*
> +	 * The top bit should be set, this is an invalid address for
> +	 * EL0 and will only be set for caps created by signals.
> +	 */
> +	if (!(val & GCS_SIGNAL_CAP_FLAG))
> +		return false;
> +
> +	/* The rest should be a standard architectural cap token. */
> +	val &= ~GCS_SIGNAL_CAP_FLAG;
> +
> +	/* The cap must have the low bits set to a token value */
> +	if (GCS_CAP_TOKEN(val) != 0)
> +		return false;

I found the comment above a little confusing, since the if condition
actually checks that low bits aren't set at all. Perhaps reword to
something like "The token value of a signal cap must be 0"?

> +
> +	/* The cap must store the VA the cap was stored at */
> +	if (GCS_CAP_ADDR(addr) != GCS_CAP_ADDR(val))
> +		return false;
> +
> +	return true;
> +}
> +#endif
> +
>  /*
>   * Do a signal return; undo the signal stack. These are aligned to 128-bit.
>   */
> @@ -815,6 +847,45 @@ static int restore_sigframe(struct pt_regs *regs,
>  	return err;
>  }
>  
> +#ifdef CONFIG_ARM64_GCS
> +static int gcs_restore_signal(void)
> +{
> +	u64 gcspr_el0, cap;
> +	int ret;
> +
> +	if (!system_supports_gcs())
> +		return 0;
> +
> +	if (!(current->thread.gcs_el0_mode & PR_SHADOW_STACK_ENABLE))
> +		return 0;
> +
> +	gcspr_el0 = read_sysreg_s(SYS_GCSPR_EL0);
> +
> +	/*
> +	 * GCSPR_EL0 should be pointing at a capped GCS, read the cap...
> +	 */
> +	gcsb_dsync();
> +	ret = copy_from_user(&cap, (__user void*)gcspr_el0, sizeof(cap));
> +	if (ret)
> +		return -EFAULT;
> +
> +	/*
> +	 * ...then check that the cap is the actual GCS before
> +	 * restoring it.
> +	 */
> +	if (!gcs_signal_cap_valid(gcspr_el0, cap))
> +		return -EINVAL;
> +
> +	current->thread.gcspr_el0 = gcspr_el0 + sizeof(cap);
> +	write_sysreg_s(current->thread.gcspr_el0, SYS_GCSPR_EL0);

At this point, there's an inactive but valid cap just below the GCS.
Over time, as different signals are received when the GCSPR is pointing
at different locations of the stack, there could be a number of valid
inactive caps available for misuse.

I'm still not proficient enough in GCS to know how exactly this could be
abused (e.g., somehow writing the desired return location right above
one of these inactive caps and arranging for GCSPR to point to the cap
before returning from a signal) but to be safe or paranoid, perhaps zero
the location of the cap before returning?

> +
> +	return 0;
> +}
> +
> +#else
> +static int gcs_restore_signal(void) { return 0; }
> +#endif
> +
>  SYSCALL_DEFINE0(rt_sigreturn)
>  {
>  	struct pt_regs *regs = current_pt_regs();
> @@ -841,6 +912,9 @@ SYSCALL_DEFINE0(rt_sigreturn)
>  	if (restore_altstack(&frame->uc.uc_stack))
>  		goto badframe;
>  
> +	if (gcs_restore_signal())
> +		goto badframe;
> +
>  	return regs->regs[0];
>  
>  badframe:
> @@ -1071,7 +1145,50 @@ static int get_sigframe(struct rt_sigframe_user_layout *user,
>  	return 0;
>  }
>  
> -static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
> +#ifdef CONFIG_ARM64_GCS
> +
> +static int gcs_signal_entry(__sigrestore_t sigtramp, struct ksignal *ksig)

The ksig argument is unused, so it can be removed.

> +{
> +	unsigned long __user *gcspr_el0;
> +	int ret = 0;
> +
> +	if (!system_supports_gcs())
> +		return 0;
> +
> +	if (!task_gcs_el0_enabled(current))
> +		return 0;
> +
> +	/*
> +	 * We are entering a signal handler, current register state is
> +	 * active.
> +	 */
> +	gcspr_el0 = (unsigned long __user *)read_sysreg_s(SYS_GCSPR_EL0);
> +
> +	/*
> +	 * Push a cap and the GCS entry for the trampoline onto the GCS.
> +	 */
> +	put_user_gcs((unsigned long)sigtramp, gcspr_el0 - 2, &ret);
> +	put_user_gcs(GCS_SIGNAL_CAP(gcspr_el0 - 1), gcspr_el0 - 1, &ret);
> +	if (ret != 0)
> +		return ret;
> +
> +	gcsb_dsync();
> +
> +	gcspr_el0 -= 2;
> +	write_sysreg_s((unsigned long)gcspr_el0, SYS_GCSPR_EL0);
> +
> +	return 0;
> +}
> +#else
> +
> +static int gcs_signal_entry(__sigrestore_t sigtramp, struct ksignal *ksig)
> +{
> +	return 0;
> +}
> +
> +#endif
> +
> +static int setup_return(struct pt_regs *regs, struct ksignal *ksig,
>  			 struct rt_sigframe_user_layout *user, int usig)

Since the ksig argument isn't used by gcs_signal_entry(), setup_return()
can keep the ka argument and the changes below from ka to ksic->ka are
unnecessary.

>  {
>  	__sigrestore_t sigtramp;
> @@ -1079,7 +1196,7 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
>  	regs->regs[0] = usig;
>  	regs->sp = (unsigned long)user->sigframe;
>  	regs->regs[29] = (unsigned long)&user->next_frame->fp;
> -	regs->pc = (unsigned long)ka->sa.sa_handler;
> +	regs->pc = (unsigned long)ksig->ka.sa.sa_handler;
>  
>  	/*
>  	 * Signal delivery is a (wacky) indirect function call in
> @@ -1119,12 +1236,14 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
>  		sme_smstop();
>  	}
>  
> -	if (ka->sa.sa_flags & SA_RESTORER)
> -		sigtramp = ka->sa.sa_restorer;
> +	if (ksig->ka.sa.sa_flags & SA_RESTORER)
> +		sigtramp = ksig->ka.sa.sa_restorer;
>  	else
>  		sigtramp = VDSO_SYMBOL(current->mm->context.vdso, sigtramp);
>  
>  	regs->regs[30] = (unsigned long)sigtramp;
> +
> +	return gcs_signal_entry(sigtramp, ksig);
>  }
>  
>  static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
> @@ -1147,7 +1266,7 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
>  	err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
>  	err |= setup_sigframe(&user, regs, set);
>  	if (err == 0) {
> -		setup_return(regs, &ksig->ka, &user, usig);
> +		err = setup_return(regs, ksig, &user, usig);
>  		if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
>  			err |= copy_siginfo_to_user(&frame->info, &ksig->info);
>  			regs->regs[1] = (unsigned long)&frame->info;
> diff --git a/arch/arm64/mm/gcs.c b/arch/arm64/mm/gcs.c
> index 02f8f6046c10..6f51429c5a46 100644
> --- a/arch/arm64/mm/gcs.c
> +++ b/arch/arm64/mm/gcs.c
> @@ -6,6 +6,7 @@
>  #include <linux/types.h>
>  
>  #include <asm/cpufeature.h>
> +#include <asm/gcs.h>
>  #include <asm/page.h>

This is #include isn't needed by this patch. Probably better as part of
another one.

-- 
Thiago