linux-nvme.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: John Garry <john.g.garry@oracle.com>
To: Ming Lei <ming.lei@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>, Christoph Hellwig <hch@lst.de>,
	linux-nvme@lists.infradead.org,
	"Martin K . Petersen" <martin.petersen@oracle.com>,
	linux-scsi@vger.kernel.org, linux-block@vger.kernel.org,
	Wen Xiong <wenxiong@linux.ibm.com>,
	Keith Busch <kbusch@kernel.org>,
	Xiang Chen <chenxiang66@hisilicon.com>
Subject: Re: [PATCH V2 5/9] scsi: hisi: take blk_mq_max_nr_hw_queues() into account for calculating io vectors
Date: Thu, 27 Jul 2023 08:35:06 +0100	[thread overview]
Message-ID: <44b1bd30-426d-db85-4b52-4f079948e52a@oracle.com> (raw)
In-Reply-To: <ZMHFQm2BpuGjjlTm@ovpn-8-16.pek2.redhat.com>

On 27/07/2023 02:15, Ming Lei wrote:
>>> hisi_sas_v3_hw.c
>>> +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
>>> @@ -2550,6 +2550,9 @@ static int interrupt_preinit_v3_hw(struct hisi_hba *hisi_hba)
>>>    	hisi_hba->cq_nvecs = vectors - BASE_VECTORS_V3_HW - hisi_hba->iopoll_q_cnt;
>>> +	if (hisi_hba->cq_nvecs > scsi_max_nr_hw_queues())
>>> +		hisi_hba->cq_nvecs = scsi_max_nr_hw_queues();
>>> +
>>>    	shost->nr_hw_queues = hisi_hba->cq_nvecs + hisi_hba->iopoll_q_cnt;
>> For other drivers you limit the max MSI vectors which we try to allocate
>> according to scsi_max_nr_hw_queues(), but here you continue to alloc the
>> same max vectors but then limit the driver's completion queue count. Why not
>> limit the max MSI vectors also here?

Ah, checking again, I think that this driver always allocates maximum 
possible MSI due to arm interrupt controller driver bug - see comment at 
top of function interrupt_preinit_v3_hw(). IIRC, there was a problem if 
we remove and re-insert the device driver that the GIC ITS fails to 
allocate MSI unless all MSI were previously allocated.

Xiang Chen can confirm.

> Good catch!
> 
> I guess it is because of the following line:
> 
>     	hisi_hba->cq_nvecs = vectors - BASE_VECTORS_V3_HW - hisi_hba->iopoll_q_cnt;
> 
> I am a bit confused why hisi_sas_v3 takes ->iopoll_q_cnt into account
> allocated msi vectors?  ->iopoll_q_cnt supposes to not consume msi
> vectors, so I think we need the following fix first:
> 
> diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
> index 20e1607c6282..032c13ce8373 100644
> --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
> +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
> @@ -2549,7 +2549,7 @@ static int interrupt_preinit_v3_hw(struct hisi_hba *hisi_hba)
>                  return -ENOENT;
> 
> 
> -       hisi_hba->cq_nvecs = vectors - BASE_VECTORS_V3_HW - hisi_hba->iopoll_q_cnt;
> +       hisi_hba->cq_nvecs = vectors - BASE_VECTORS_V3_HW;
>          shost->nr_hw_queues = hisi_hba->cq_nvecs + hisi_hba->iopoll_q_cnt;

Thanks,
John


  reply	other threads:[~2023-07-27  7:35 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-07-26  9:40 [PATCH V2 0/9] blk-mq: fix wrong queue mapping for kdump kernel Ming Lei
2023-07-26  9:40 ` [PATCH V2 1/9] blk-mq: add blk_mq_max_nr_hw_queues() Ming Lei
2023-07-26 16:36   ` John Garry
2023-07-27  1:06     ` Ming Lei
2023-07-26  9:40 ` [PATCH V2 2/9] nvme-pci: use blk_mq_max_nr_hw_queues() to calculate io queues Ming Lei
2023-07-26  9:40 ` [PATCH V2 3/9] scsi: core: add helper of scsi_max_nr_hw_queues() Ming Lei
2023-07-26  9:40 ` [PATCH V2 4/9] scsi: lpfc: use blk_mq_max_nr_hw_queues() to calculate io vectors Ming Lei
2023-07-26 22:12   ` Justin Tee
2023-07-27  1:19     ` Ming Lei
2023-07-27 16:56       ` Justin Tee
2023-07-26  9:40 ` [PATCH V2 5/9] scsi: hisi: take blk_mq_max_nr_hw_queues() into account for calculating " Ming Lei
2023-07-26 15:42   ` John Garry
2023-07-27  1:15     ` Ming Lei
2023-07-27  7:35       ` John Garry [this message]
2023-07-27  9:42         ` Ming Lei
2023-07-27 10:28           ` John Garry
2023-07-27 10:56             ` Ming Lei
2023-07-27 11:30               ` John Garry
2023-07-27 12:01                 ` Ming Lei
2023-07-27 12:36                   ` John Garry
2023-07-26  9:40 ` [PATCH V2 6/9] scsi: mpi3mr: " Ming Lei
2023-07-26  9:40 ` [PATCH V2 7/9] scsi: megaraid: " Ming Lei
2023-07-26  9:40 ` [PATCH V2 8/9] scsi: mpt3sas: " Ming Lei
2023-07-26  9:40 ` [PATCH V2 9/9] scsi: pm8001: " Ming Lei
2023-07-31  7:14 ` [PATCH V2 0/9] blk-mq: fix wrong queue mapping for kdump kernel Christoph Hellwig

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=44b1bd30-426d-db85-4b52-4f079948e52a@oracle.com \
    --to=john.g.garry@oracle.com \
    --cc=axboe@kernel.dk \
    --cc=chenxiang66@hisilicon.com \
    --cc=hch@lst.de \
    --cc=kbusch@kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=martin.petersen@oracle.com \
    --cc=ming.lei@redhat.com \
    --cc=wenxiong@linux.ibm.com \
    /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).