From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:60591)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <quintela@redhat.com>) id 1VMHN2-0004Kh-PB
	for qemu-devel@nongnu.org; Wed, 18 Sep 2013 09:00:45 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <quintela@redhat.com>) id 1VMHMx-0003Qk-IF
	for qemu-devel@nongnu.org; Wed, 18 Sep 2013 09:00:40 -0400
Received: from mx1.redhat.com ([209.132.183.28]:30643)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <quintela@redhat.com>) id 1VMHMx-0003Qd-5U
	for qemu-devel@nongnu.org; Wed, 18 Sep 2013 09:00:35 -0400
From: Juan Quintela <quintela@redhat.com>
In-Reply-To: <9683795de456be26be098f36807d1d4da3027cd0.1378261891.git.yamahata@private.email.ne.jp>
	(Isaku Yamahata's message of "Wed, 4 Sep 2013 11:32:20 +0900")
References: <5d53d839653bf4fd24d5cb56f6d24d3dc3f8f8a5.1378261891.git.yamahata@private.email.ne.jp>
	<5d53d839653bf4fd24d5cb56f6d24d3dc3f8f8a5.1378261891.git.yamahata@private.email.ne.jp>
	<9683795de456be26be098f36807d1d4da3027cd0.1378261891.git.yamahata@private.email.ne.jp>
Date: Wed, 18 Sep 2013 15:00:24 +0200
Message-ID: <87vc1yuvx3.fsf@elfo.elfo>
MIME-Version: 1.0
Content-Type: text/plain
Subject: Re: [Qemu-devel] [PATCH 2/2] rdma: simplify
	qemu_rdma_register_and_get_keys()
Reply-To: quintela@redhat.com
List-Id: <qemu-devel.nongnu.org>
List-Unsubscribe: <https://lists.nongnu.org/mailman/options/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.nongnu.org/archive/html/qemu-devel>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <https://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: Isaku Yamahata <yamahata@private.email.ne.jp>
Cc: owasserm@redhat.com, mrhines@us.ibm.com, qemu-devel@nongnu.org, pbonzini@redhat.com

Isaku Yamahata <yamahata@private.email.ne.jp> wrote:
> Signed-off-by: Isaku Yamahata <yamahata@private.email.ne.jp>

I don't understand this bit:

> +        uint8_t *chunk_start = ram_chunk_start(block, chunk);
> +        uint8_t *chunk_end = ram_chunk_end(block, chunk);

Here we are getting just the length of a chunk


>      sge.length = length;
>  
>      chunk = ram_chunk_index(block->local_host_addr, (uint8_t *) sge.addr);
> -    chunk_start = ram_chunk_start(block, chunk);
>  
>      if (block->is_ram_block) {
>          chunks = length / (1UL << RDMA_REG_CHUNK_SHIFT);
> @@ -1884,8 +1883,6 @@ retry:
>      DDPRINTF("Writing %" PRIu64 " chunks, (%" PRIu64 " MB)\n",
>          chunks + 1, (chunks + 1) * (1UL << RDMA_REG_CHUNK_SHIFT) / 1024 / 1024);
>  
> -    chunk_end = ram_chunk_end(block, chunk + chunks);
> -

But here chuck_end was the length of a list of chucks.


> @@ -3076,11 +3069,9 @@ static int qemu_rdma_registration_handle(QEMUFile *f, void *opaque,
>                      host_addr = block->local_host_addr +
>                          (reg->key.chunk * (1UL << RDMA_REG_CHUNK_SHIFT));
>                  }
> -                chunk_start = ram_chunk_start(block, chunk);
> -                chunk_end = ram_chunk_end(block, chunk + reg->chunks);
>                  if (qemu_rdma_register_and_get_keys(rdma, block,
>                              (uint8_t *)host_addr, NULL, &reg_result->rkey,
> -                            chunk, chunk_start, chunk_end)) {
> +                            chunk)) {

Same here.


I am missing something obvious?

PD.  No, I don't claim to understand RDMA.