From: Klaus Birkelund <its@irrelevant.dk>
To: Beata Michalska <beata.michalska@linaro.org>
Cc: Kevin Wolf <kwolf@redhat.com>,
qemu-block@nongnu.org, qemu-devel@nongnu.org,
Max Reitz <mreitz@redhat.com>,
Paul Durrant <Paul.Durrant@citrix.com>,
Keith Busch <kbusch@kernel.org>
Subject: Re: [PATCH v2 14/20] nvme: allow multiple aios per command
Date: Thu, 21 Nov 2019 12:57:51 +0100 [thread overview]
Message-ID: <20191121115751.GB1211716@apples.localdomain> (raw)
In-Reply-To: <CADSWDzvEdK1MXXNeF6bFiyC0UDY-wTp7_ZdeV-i_Ys5YdGoyqg@mail.gmail.com>
On Tue, Nov 12, 2019 at 03:25:06PM +0000, Beata Michalska wrote:
> Hi Klaus,
>
> On Tue, 15 Oct 2019 at 11:55, Klaus Jensen <its@irrelevant.dk> wrote:
> > @@ -341,19 +344,18 @@ static uint16_t nvme_dma_write_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
> Any reason why the nvme_dma_write_prp is missing the changes applied
> to nvme_dma_read_prp ?
>
This was adressed by proxy through changes to the previous patch
(by combining the read/write functions).
> > + case NVME_AIO_OPC_WRITE_ZEROES:
> > + block_acct_start(stats, acct, aio->iov.size, BLOCK_ACCT_WRITE);
> > + aio->aiocb = blk_aio_pwrite_zeroes(aio->blk, aio->offset,
> > + aio->iov.size, BDRV_REQ_MAY_UNMAP, nvme_aio_cb, aio);
> Minor: aio->blk => blk
>
Thanks. Fixed this in a couple of other places as well.
> > @@ -621,8 +880,11 @@ static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeCmd *cmd)
> > sq = n->sq[qid];
> > while (!QTAILQ_EMPTY(&sq->out_req_list)) {
> > req = QTAILQ_FIRST(&sq->out_req_list);
> > - assert(req->aiocb);
> > - blk_aio_cancel(req->aiocb);
> > + while (!QTAILQ_EMPTY(&req->aio_tailq)) {
> > + aio = QTAILQ_FIRST(&req->aio_tailq);
> > + assert(aio->aiocb);
> > + blk_aio_cancel(aio->aiocb);
> What about releasing memory associated with given aio ?
I believe the callback is still called when cancelled? That should take
care of it. Or have I misunderstood that? At least for the DMAAIOCBs it
is.
> > +struct NvmeAIO {
> > + NvmeRequest *req;
> > +
> > + NvmeAIOOp opc;
> > + int64_t offset;
> > + BlockBackend *blk;
> > + BlockAIOCB *aiocb;
> > + BlockAcctCookie acct;
> > +
> > + NvmeAIOCompletionFunc *cb;
> > + void *cb_arg;
> > +
> > + QEMUSGList *qsg;
> > + QEMUIOVector iov;
>
> There is a bit of inconsistency on the ownership of IOVs and SGLs.
> SGLs now seem to be owned by request whereas IOVs by the aio.
> WOuld be good to have that unified or documented at least.
>
Fixed this. The NvmeAIO only holds pointers now.
> > +#define NVME_REQ_TRANSFER_DMA 0x1
> This one does not seem to be used ....
>
I have dropped the flags and reverted to a simple req->is_cmb as that is
all that is really needed.
next prev parent reply other threads:[~2019-11-21 12:00 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 01/20] nvme: remove superfluous breaks Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 02/20] nvme: move device parameters to separate struct Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 03/20] nvme: add missing fields in the identify controller data structure Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 04/20] nvme: populate the mandatory subnqn and ver fields Klaus Jensen
2019-11-12 15:04 ` Beata Michalska
2019-11-13 6:16 ` Klaus Birkelund
2019-10-15 10:38 ` [PATCH v2 05/20] nvme: allow completion queues in the cmb Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 06/20] nvme: add support for the abort command Klaus Jensen
2019-11-12 15:04 ` Beata Michalska
2019-11-13 6:12 ` Klaus Birkelund
2019-11-15 11:56 ` Beata Michalska
2019-11-18 8:49 ` Klaus Birkelund
2019-10-15 10:38 ` [PATCH v2 07/20] nvme: refactor device realization Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 08/20] nvme: add support for the get log page command Klaus Jensen
2019-11-12 15:04 ` Beata Michalska
2019-11-19 20:01 ` Klaus Birkelund
2019-10-15 10:38 ` [PATCH v2 09/20] nvme: add support for the asynchronous event request command Klaus Jensen
2019-11-12 15:04 ` Beata Michalska
2019-11-19 19:51 ` Klaus Birkelund
2019-11-25 12:44 ` Beata Michalska
2019-10-15 10:38 ` [PATCH v2 10/20] nvme: add logging to error information log page Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 11/20] nvme: add missing mandatory features Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 12/20] nvme: bump supported specification version to 1.3 Klaus Jensen
2019-11-12 15:05 ` Beata Michalska
2019-11-18 9:48 ` Klaus Birkelund
2019-11-25 12:13 ` Beata Michalska
2019-11-26 8:40 ` Klaus Birkelund
2019-10-15 10:38 ` [PATCH v2 13/20] nvme: refactor prp mapping Klaus Jensen
2019-11-12 15:23 ` Beata Michalska
2019-11-20 9:39 ` Klaus Birkelund
2019-11-25 13:15 ` Beata Michalska
2019-10-15 10:38 ` [PATCH v2 14/20] nvme: allow multiple aios per command Klaus Jensen
2019-11-12 15:25 ` Beata Michalska
2019-11-21 11:57 ` Klaus Birkelund [this message]
2019-11-25 13:59 ` Beata Michalska
2019-10-15 10:38 ` [PATCH v2 15/20] nvme: add support for scatter gather lists Klaus Jensen
2019-11-12 15:25 ` Beata Michalska
2019-11-25 6:21 ` Klaus Birkelund
2019-11-25 14:10 ` Beata Michalska
2019-11-26 8:34 ` Klaus Birkelund
2019-10-15 10:38 ` [PATCH v2 16/20] nvme: support multiple namespaces Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 17/20] nvme: bump controller pci device id Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 18/20] nvme: remove redundant NvmeCmd pointer parameter Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 19/20] nvme: make lba data size configurable Klaus Jensen
2019-11-12 15:24 ` Beata Michalska
2019-11-13 7:13 ` Klaus Birkelund
2019-10-15 10:39 ` [PATCH v2 20/20] nvme: handle dma errors Klaus Jensen
2019-10-15 17:19 ` [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces no-reply
2019-10-15 17:26 ` no-reply
2019-10-16 6:29 ` Fam Zheng
2019-10-28 6:09 ` Klaus Birkelund
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20191121115751.GB1211716@apples.localdomain \
--to=its@irrelevant.dk \
--cc=Paul.Durrant@citrix.com \
--cc=beata.michalska@linaro.org \
--cc=kbusch@kernel.org \
--cc=kwolf@redhat.com \
--cc=mreitz@redhat.com \
--cc=qemu-block@nongnu.org \
--cc=qemu-devel@nongnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).