Re: [RFC PATCH 23/28] algif: Remove hash_sendpage*()

From: David Howells <dhowells@redhat.com>
To: Herbert Xu <herbert@gondor.apana.org.au>
Cc: dhowells@redhat.com, willy@infradead.org, davem@davemloft.net,
	edumazet@google.com, kuba@kernel.org, pabeni@redhat.com,
	viro@zeniv.linux.org.uk, hch@infradead.org, axboe@kernel.dk,
	jlayton@kernel.org, brauner@kernel.org,
	torvalds@linux-foundation.org, netdev@vger.kernel.org,
	linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, linux-crypto@vger.kernel.org
Subject: Re: [RFC PATCH 23/28] algif: Remove hash_sendpage*()
Date: Fri, 24 Mar 2023 16:47:50 +0000	[thread overview]
Message-ID: <3763055.1679676470@warthog.procyon.org.uk> (raw)
In-Reply-To: <ZBPTC9WPYQGhFI30@gondor.apana.org.au>

Herbert Xu <herbert@gondor.apana.org.au> wrote:

> David Howells <dhowells@redhat.com> wrote:
> > Remove hash_sendpage*() and use hash_sendmsg() as the latter seems to just
> > use the source pages directly anyway.
> 
> ...
> 
> > -       if (!(flags & MSG_MORE)) {
> > -               if (ctx->more)
> > -                       err = crypto_ahash_finup(&ctx->req);
> > -               else
> > -                       err = crypto_ahash_digest(&ctx->req);
> 
> You've just removed the optimised path from user-space to
> finup/digest.  You need to add them back to sendmsg if you
> want to eliminate sendpage.

I must be missing something, I think.  What's particularly optimal about the
code in hash_sendpage() but not hash_sendmsg()?  Is it that the former uses
finup/digest, but the latter ony does update+final?

Also, looking at:

	if (!ctx->more) {
		if ((msg->msg_flags & MSG_MORE))
			hash_free_result(sk, ctx);

how is ctx->more meant to be interpreted?  I'm guessing it means that we're
continuing to the previous op.  But we do we need to free any old result if
MSG_MORE is set, but not if it isn't?

David