Re: [PATCH v4 07/14] util/dsa: Implement DSA task asynchronous submission and wait for completion.

[Peter Xu <peterx@redhat.com>]

On Thu, Apr 25, 2024 at 02:21:10AM +0000, Hao Xiang wrote:
> +/**
> + * @brief Performs buffer zero comparison on a DSA batch task asynchronously.
> + *
> + * @param batch_task A pointer to the batch task.
> + * @param buf An array of memory buffers.
> + * @param count The number of buffers in the array.
> + * @param len The buffer length.
> + *
> + * @return Zero if successful, otherwise non-zero.
> + */
> +int
> +buffer_is_zero_dsa_batch_async(struct dsa_batch_task *batch_task,
> +                               const void **buf, size_t count, size_t len)

It says it's "async", but then..

> +{
> +    if (count <= 0 || count > batch_task->batch_size) {
> +        return -1;
> +    }
> +
> +    assert(batch_task != NULL);
> +    assert(len != 0);
> +    assert(buf != NULL);
> +
> +    if (count == 1) {
> +        /* DSA doesn't take batch operation with only 1 task. */
> +        buffer_zero_dsa_async(batch_task, buf[0], len);
> +    } else {
> +        buffer_zero_dsa_batch_async(batch_task, buf, count, len);
> +    }
> +
> +    buffer_zero_dsa_wait(batch_task);

... it waits always.

Wrong function name?

> +    buffer_zero_cpu_fallback(batch_task);

Is this introducing yet another path even if it internally still uses
buffer_is_zero()?

Can we allow buffer_is_zero_dsa_batch_async() (or when it's renamed) fail
directly with a hint that it should fallback?  Ultimately something like:


    if (dsa_is_running() && zero_page_detect_dsa(p)) {
        /* Succeeded */
        return;
    }

    /* Use cpu detection by default, or as fallback */
    zero_page_detect_cpu();

> +
> +    return 0;
> +}
> +
>  #endif
>  
> -- 
> 2.30.2
> 
> 

-- 
Peter Xu