> -----Original Message-----
> From: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>
> Sent: Monday, August 25, 2025 6:13 PM
> To: Sridhar, Kanchana P <kanchana.p.sridhar@xxxxxxxxx>
> Cc: Nhat Pham <nphamcs@xxxxxxxxx>; linux-kernel@xxxxxxxxxxxxxxx; linux-
> mm@xxxxxxxxx; hannes@xxxxxxxxxxx; yosry.ahmed@xxxxxxxxx;
> chengming.zhou@xxxxxxxxx; usamaarif642@xxxxxxxxx;
> ryan.roberts@xxxxxxx; 21cnbao@xxxxxxxxx;
> ying.huang@xxxxxxxxxxxxxxxxx; akpm@xxxxxxxxxxxxxxxxxxxx;
> senozhatsky@xxxxxxxxxxxx; linux-crypto@xxxxxxxxxxxxxxx;
> davem@xxxxxxxxxxxxx; clabbe@xxxxxxxxxxxx; ardb@xxxxxxxxxx;
> ebiggers@xxxxxxxxxx; surenb@xxxxxxxxxx; Accardi, Kristen C
> <kristen.c.accardi@xxxxxxxxx>; Gomes, Vinicius <vinicius.gomes@xxxxxxxxx>;
> Feghali, Wajdi K <wajdi.k.feghali@xxxxxxxxx>; Gopal, Vinodh
> <vinodh.gopal@xxxxxxxxx>
> Subject: Re: [PATCH v11 00/24] zswap compression batching with optimized
> iaa_crypto driver
>
> On Mon, Aug 25, 2025 at 06:12:19PM +0000, Sridhar, Kanchana P wrote:
> >
> > Thanks Herbert, for reviewing the approach. IIUC, we should follow
> > these constraints:
> >
> > 1) The folio should be submitted as the source.
> >
> > 2) For the destination, construct an SG list for them and pass that in.
> > The rule should be that the SG list must contain a sufficient number
> > of pages for the compression output based on the given unit size
> > (PAGE_SIZE for zswap).
> >
> > For PMD folios, there would be 512 compression outputs. In this case,
> > would we need to pass in an SG list that can contain 512 compression
> > outputs after calling the acompress API once?
>
> Eventually yes :)
>
> But for now we're just replicating your current patch-set, so
> the folio should come with an offset and a length restriction,
> and correspondingly the destination SG list should contain the
> same number of pages as there are in your current patch-set.
Thanks Herbert. Just want to make sure I understand this. Are you
referring to replacing sg_set_page() for the input with sg_set_folio()?
We have to pass in a scatterlist for the acomp_req->src..
This is how the converged zswap_compress() code would look for
batch compression of "nr_pages" in "folio", starting at index "start".
The input SG list will contain "nr_comps" pages: nr_comps is
1 for software and 8 for IAA.
The destination SG list will contain an equivalent number of
buffers (each is PAGE_SIZE * 2).
Based on your suggestions, I was able to come up with a unified
implementation for software and hardware compressors: the SG list
for the input is a key aspect of this (lines 24-25 from the start of the
procedure):
static bool zswap_compress(struct folio *folio, long start, unsigned int nr_pages,
struct zswap_entry *entries[], struct zswap_pool *pool,
int node_id)
{
unsigned int nr_comps = min(nr_pages, pool->compr_batch_size);
unsigned int dlens[ZSWAP_MAX_BATCH_SIZE];
struct crypto_acomp_ctx *acomp_ctx;
struct zpool *zpool = pool->zpool;
struct scatterlist *sg;
unsigned int i, j, k;
gfp_t gfp;
int err;
gfp = GFP_NOWAIT | __GFP_NORETRY | __GFP_HIGHMEM | __GFP_MOVABLE;
acomp_ctx = raw_cpu_ptr(pool->acomp_ctx);
mutex_lock(&acomp_ctx->mutex);
prefetchw(acomp_ctx->sg_inputs->sgl);
prefetchw(acomp_ctx->sg_outputs->sgl);
/*
* Note:
* [i] refers to the incoming batch space and is used to
* index into the folio pages and @entries.
*
* [k] refers to the @acomp_ctx space, as determined by
* @pool->compr_batch_size, and is used to index into
* @acomp_ctx->buffers and @dlens.
*/
for (i = 0; i < nr_pages; i += nr_comps) {
for_each_sg(acomp_ctx->sg_inputs->sgl, sg, nr_comps, k)
sg_set_folio(sg, folio, PAGE_SIZE, (start + k + i) * PAGE_SIZE);
/*
* We need PAGE_SIZE * 2 here since there maybe over-compression case,
* and hardware-accelerators may won't check the dst buffer size, so
* giving the dst buffer with enough length to avoid buffer overflow.
*/
for_each_sg(acomp_ctx->sg_outputs->sgl, sg, nr_comps, k)
sg_set_buf(sg, acomp_ctx->buffers[k], PAGE_SIZE * 2);
acomp_request_set_params(acomp_ctx->req,
acomp_ctx->sg_inputs->sgl,
acomp_ctx->sg_outputs->sgl,
nr_comps * PAGE_SIZE,
nr_comps * PAGE_SIZE);
err = crypto_wait_req(crypto_acomp_compress(acomp_ctx->req),
&acomp_ctx->wait);
if (unlikely(err)) {
if (nr_comps == 1)
dlens[0] = err;
goto compress_error;
}
if (nr_comps == 1)
dlens[0] = acomp_ctx->req->dlen;
else
for_each_sg(acomp_ctx->sg_outputs->sgl, sg, nr_comps, k)
dlens[k] = sg->length;
[ store each compressed page in zpool]
I quickly tested this with usemem 30 processes. Switching from sg_set_page()
to sg_set_folio() does cause a 15% throughput regression for IAA and 2%
regression for zstd:
usemem30/64K folios/deflate-iaa/Avg throughput (KB/s):
sg_set_page(): 357,141
sg_set_folio(): 304,696
usemem30/64K folios/zstd/Avg throughput (KB/s):
sg_set_page(): 230,760
sg_set_folio(): 226,246
In my experience, zswap_compress() is highly performance critical code
and the smallest compute additions can cause significant impact on workload
performance and sys time.
Given the code simplification and unification that your SG list suggestions
have enabled, may I understand better why sg_set_folio() is preferred?
Again, my apologies if I have misunderstood your suggestion, but I think
it is worth getting this clarified so we are all in agreement.
Thanks and best regards,
Kanchana
>
> Cheers,
> --
> Email: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>
> Home Page: http://gondor.apana.org.au/~herbert/
> PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
