Re: [PATCH v3 21/21] arm64/fpsimd: Allocate kernel mode FP/SIMD buffers on the stack

[Eric Biggers <ebiggers@kernel.org>]

On Wed, Oct 08, 2025 at 05:45:55PM +0200, Ard Biesheuvel wrote:
> diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
> index 61d62bfd5a7b..226e635c53d9 100644
> --- a/arch/arm64/include/asm/processor.h
> +++ b/arch/arm64/include/asm/processor.h
> @@ -172,7 +172,7 @@ struct thread_struct {
>  	unsigned long		fault_code;	/* ESR_EL1 value */
>  	struct debug_info	debug;		/* debugging */
>  
> -	struct user_fpsimd_state	kernel_fpsimd_state;
> +	struct user_fpsimd_state	*kernel_fpsimd_state;

Perhaps this field deserves a comment?

> @@ -1834,7 +1837,7 @@ void fpsimd_save_and_flush_cpu_state(void)
>   * The caller may freely use the FPSIMD registers until kernel_neon_end() is
>   * called.
>   */
> -void kernel_neon_begin(void)
> +void kernel_neon_begin(struct user_fpsimd_state *state)

Similarly, the 'state' parameter to kernel_neon_begin() and
kernel_neon_end() could use documentation.

> -		if (IS_ENABLED(CONFIG_PREEMPT_RT) || !in_serving_softirq())
> +		if (IS_ENABLED(CONFIG_PREEMPT_RT) || !in_serving_softirq()) {
> +			/*
> +			 * Record the caller provided buffer as the kernel mode
> +			 * FP/SIMD buffer for this task, so that the state can
> +			 * be preserved and restored on a context switch.
> +			 */
> +			WARN_ON(current->thread.kernel_fpsimd_state != NULL);
> +			current->thread.kernel_fpsimd_state = state;
>  			set_thread_flag(TIF_KERNEL_FPSTATE);
> +		}

'state' can be NULL here, right?  So in that case we do set
TIF_KERNEL_FPSTATE, but we assume context switching cannot happen?

- Eric