Re: [PATCH v1 07/16] vfio/ccw: remove unnecessary malloc alignment

[Matthew Rosato <mjrosato@linux.ibm.com>]

On 11/21/22 4:40 PM, Eric Farman wrote:
> Everything about this allocation is harder than necessary,
> since the memory allocation is already aligned to our needs.
> Break them apart for readability, instead of doing the
> funky artithmetic.
> 
> Of the structures that are involved, only ch_ccw needs the
> GFP_DMA flag, so the others can be allocated without it.
> 
> Signed-off-by: Eric Farman <farman@linux.ibm.com>
> ---
>  drivers/s390/cio/vfio_ccw_cp.c | 39 ++++++++++++++++++----------------
>  1 file changed, 21 insertions(+), 18 deletions(-)
> 
> diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
> index d41d94cecdf8..4b6b5f9dc92d 100644
> --- a/drivers/s390/cio/vfio_ccw_cp.c
> +++ b/drivers/s390/cio/vfio_ccw_cp.c
> @@ -311,40 +311,41 @@ static inline int is_tic_within_range(struct ccw1 *ccw, u32 head, int len)
>  static struct ccwchain *ccwchain_alloc(struct channel_program *cp, int len)
>  {
>  	struct ccwchain *chain;
> -	void *data;
> -	size_t size;
> -
> -	/* Make ccw address aligned to 8. */
> -	size = ((sizeof(*chain) + 7L) & -8L) +
> -		sizeof(*chain->ch_ccw) * len +
> -		sizeof(*chain->ch_pa) * len;
> -	chain = kzalloc(size, GFP_DMA | GFP_KERNEL);
> +
> +	chain = kzalloc(sizeof(*chain), GFP_KERNEL);

I suppose you could consider a WARN_ONCE here if one of these kzalloc'd addresses has something in the low-order 3 bits; would probably make it more obvious if for some reason the alignment guarantee was broken vs some status after-the-fact in the IRB.  But as per our discussion off-list I think that can only happen if ARCH_KMALLOC_MINALIGN were to change.

>  	if (!chain)
>  		return NULL;
>  
> -	data = (u8 *)chain + ((sizeof(*chain) + 7L) & -8L);
> -	chain->ch_ccw = (struct ccw1 *)data;
> -
> -	data = (u8 *)(chain->ch_ccw) + sizeof(*chain->ch_ccw) * len;
> -	chain->ch_pa = (struct page_array *)data;
> +	chain->ch_ccw = kcalloc(len, sizeof(*chain->ch_ccw), GFP_DMA | GFP_KERNEL);
> +	if (!chain->ch_ccw)
> +		goto out_err;
>  
> -	chain->ch_len = len;
> +	chain->ch_pa = kcalloc(len, sizeof(*chain->ch_pa), GFP_KERNEL);
> +	if (!chain->ch_pa)
> +		goto out_err;
>  
>  	list_add_tail(&chain->next, &cp->ccwchain_list);
>  
>  	return chain;
> +
> +out_err:
> +	kfree(chain->ch_ccw);
> +	kfree(chain);
> +	return NULL;
>  }
>  
>  static void ccwchain_free(struct ccwchain *chain)
>  {
>  	list_del(&chain->next);
> +	kfree(chain->ch_pa);
> +	kfree(chain->ch_ccw);
>  	kfree(chain);
>  }
>  
>  /* Free resource for a ccw that allocated memory for its cda. */
>  static void ccwchain_cda_free(struct ccwchain *chain, int idx)
>  {
> -	struct ccw1 *ccw = chain->ch_ccw + idx;
> +	struct ccw1 *ccw = &chain->ch_ccw[idx];
>  
>  	if (ccw_is_tic(ccw))
>  		return;
> @@ -443,6 +444,8 @@ static int ccwchain_handle_ccw(u32 cda, struct channel_program *cp)
>  	chain = ccwchain_alloc(cp, len);
>  	if (!chain)
>  		return -ENOMEM;
> +
> +	chain->ch_len = len;
>  	chain->ch_iova = cda;
>  
>  	/* Copy the actual CCWs into the new chain */
> @@ -464,7 +467,7 @@ static int ccwchain_loop_tic(struct ccwchain *chain, struct channel_program *cp)
>  	int i, ret;
>  
>  	for (i = 0; i < chain->ch_len; i++) {
> -		tic = chain->ch_ccw + i;
> +		tic = &chain->ch_ccw[i];

These don't seem equivalent...  Before at each iteration you'd offset tic by i bytes, now you're treating i as an index of 8B ccw1 structs, so it seems like this went from tic = x + i to tic = x + (8 * i)?  Was the old code broken or am I missing something? 

>  
>  		if (!ccw_is_tic(tic))
>  			continue;
> @@ -739,8 +742,8 @@ int cp_prefetch(struct channel_program *cp)
>  	list_for_each_entry(chain, &cp->ccwchain_list, next) {
>  		len = chain->ch_len;
>  		for (idx = 0; idx < len; idx++) {
> -			ccw = chain->ch_ccw + idx;
> -			pa = chain->ch_pa + idx;
> +			ccw = &chain->ch_ccw[idx];
> +			pa = &chain->ch_pa[idx];

Same sort of question re: ch_pa

>  
>  			ret = ccwchain_fetch_one(ccw, pa, cp);
>  			if (ret)