Linux-Block Archive on lore.kernel.org
 help / color / Atom feed
From: Ming Lei <tom.leiming@gmail.com>
To: Hannes Reinecke <hare@suse.de>
Cc: Ming Lei <ming.lei@redhat.com>, Jens Axboe <axboe@kernel.dk>,
	linux-block <linux-block@vger.kernel.org>,
	Linux SCSI List <linux-scsi@vger.kernel.org>,
	"Martin K . Petersen" <martin.petersen@oracle.com>,
	James Bottomley <James.Bottomley@hansenpartnership.com>,
	Bart Van Assche <bvanassche@acm.org>,
	Hannes Reinecke <hare@suse.com>,
	John Garry <john.garry@huawei.com>,
	Don Brace <don.brace@microsemi.com>,
	Kashyap Desai <kashyap.desai@broadcom.com>,
	Sathya Prakash <sathya.prakash@broadcom.com>,
	Christoph Hellwig <hch@lst.de>
Subject: Re: [PATCH 7/9] scsi: hisi_sas_v3: convert private reply queue to blk-mq hw queue
Date: Fri, 31 May 2019 14:34:36 +0800
Message-ID: <CACVXFVMG8gkw8E0pmWBJC0tBH9D-WVjY2FnL2gsxDja3ryfbng@mail.gmail.com> (raw)
In-Reply-To: <1afb4353-6703-a3f0-ca6c-d0b2bd754a56@suse.de>

On Fri, May 31, 2019 at 2:21 PM Hannes Reinecke <hare@suse.de> wrote:
>
> On 5/31/19 4:27 AM, Ming Lei wrote:
> > SCSI's reply qeueue is very similar with blk-mq's hw queue, both
> > assigned by IRQ vector, so map te private reply queue into blk-mq's hw
> > queue via .host_tagset.
> >
> > Then the private reply mapping can be removed.
> >
> > Another benefit is that the request/irq lost issue may be solved in
> > generic approach because managed IRQ may be shutdown during CPU
> > hotplug.
> >
> > Signed-off-by: Ming Lei <ming.lei@redhat.com>
> > ---
> >  drivers/scsi/hisi_sas/hisi_sas.h       |  2 +-
> >  drivers/scsi/hisi_sas/hisi_sas_main.c  | 36 ++++++++++----------
> >  drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 46 +++++++++-----------------
> >  3 files changed, 36 insertions(+), 48 deletions(-)
> >
> > diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
> > index fc87994b5d73..3d48848dbde7 100644
> > --- a/drivers/scsi/hisi_sas/hisi_sas.h
> > +++ b/drivers/scsi/hisi_sas/hisi_sas.h
> > @@ -26,6 +26,7 @@
> >  #include <linux/platform_device.h>
> >  #include <linux/property.h>
> >  #include <linux/regmap.h>
> > +#include <linux/blk-mq-pci.h>
> >  #include <scsi/sas_ata.h>
> >  #include <scsi/libsas.h>
> >
> > @@ -378,7 +379,6 @@ struct hisi_hba {
> >       u32 intr_coal_count;    /* Interrupt count to coalesce */
> >
> >       int cq_nvecs;
> > -     unsigned int *reply_map;
> >
> >       /* debugfs memories */
> >       u32 *debugfs_global_reg;
> > diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
> > index 8a7feb8ed8d6..a1c1f30b9fdb 100644
> > --- a/drivers/scsi/hisi_sas/hisi_sas_main.c
> > +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
> > @@ -441,6 +441,19 @@ static int hisi_sas_dif_dma_map(struct hisi_hba *hisi_hba,
> >       return rc;
> >  }
> >
> > +static struct scsi_cmnd *sas_task_to_scsi_cmd(struct sas_task *task)
> > +{
> > +     if (!task->uldd_task)
> > +             return NULL;
> > +
> > +     if (dev_is_sata(task->dev)) {
> > +             struct ata_queued_cmd *qc = task->uldd_task;
> > +             return qc->scsicmd;
> > +     } else {
> > +             return task->uldd_task;
> > +     }
> > +}
> > +
> >  static int hisi_sas_task_prep(struct sas_task *task,
> >                             struct hisi_sas_dq **dq_pointer,
> >                             bool is_tmf, struct hisi_sas_tmf_task *tmf,
> > @@ -459,6 +472,7 @@ static int hisi_sas_task_prep(struct sas_task *task,
> >       struct hisi_sas_dq *dq;
> >       unsigned long flags;
> >       int wr_q_index;
> > +     struct scsi_cmnd *scsi_cmnd;
> >
> >       if (DEV_IS_GONE(sas_dev)) {
> >               if (sas_dev)
> > @@ -471,9 +485,10 @@ static int hisi_sas_task_prep(struct sas_task *task,
> >               return -ECOMM;
> >       }
> >
> > -     if (hisi_hba->reply_map) {
> > -             int cpu = raw_smp_processor_id();
> > -             unsigned int dq_index = hisi_hba->reply_map[cpu];
> > +     scsi_cmnd = sas_task_to_scsi_cmd(task);
> > +     if (hisi_hba->shost->hostt->host_tagset) {
> > +             unsigned int dq_index = scsi_cmnd_hctx_index(
> > +                             hisi_hba->shost, scsi_cmnd);
> >
> >               *dq_pointer = dq = &hisi_hba->dq[dq_index];
> >       } else {
> > @@ -503,21 +518,8 @@ static int hisi_sas_task_prep(struct sas_task *task,
> >
> >       if (hisi_hba->hw->slot_index_alloc)
> >               rc = hisi_hba->hw->slot_index_alloc(hisi_hba, device);
> > -     else {
> > -             struct scsi_cmnd *scsi_cmnd = NULL;
> > -
> > -             if (task->uldd_task) {
> > -                     struct ata_queued_cmd *qc;
> > -
> > -                     if (dev_is_sata(device)) {
> > -                             qc = task->uldd_task;
> > -                             scsi_cmnd = qc->scsicmd;
> > -                     } else {
> > -                             scsi_cmnd = task->uldd_task;
> > -                     }
> > -             }
> > +     else
> >               rc  = hisi_sas_slot_index_alloc(hisi_hba, scsi_cmnd);
> > -     }
> >       if (rc < 0)
> >               goto err_out_dif_dma_unmap;
> >
> > diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
> > index 49620c2411df..063e50e5b30c 100644
> > --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
> > +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
> > @@ -2344,30 +2344,6 @@ static irqreturn_t cq_interrupt_v3_hw(int irq_no, void *p)
> >       return IRQ_HANDLED;
> >  }
> >
> > -static void setup_reply_map_v3_hw(struct hisi_hba *hisi_hba, int nvecs)
> > -{
> > -     const struct cpumask *mask;
> > -     int queue, cpu;
> > -
> > -     for (queue = 0; queue < nvecs; queue++) {
> > -             struct hisi_sas_cq *cq = &hisi_hba->cq[queue];
> > -
> > -             mask = pci_irq_get_affinity(hisi_hba->pci_dev, queue +
> > -                                         BASE_VECTORS_V3_HW);
> > -             if (!mask)
> > -                     goto fallback;
> > -             cq->pci_irq_mask = mask;
> > -             for_each_cpu(cpu, mask)
> > -                     hisi_hba->reply_map[cpu] = queue;
> > -     }
> > -     return;
> > -
> > -fallback:
> > -     for_each_possible_cpu(cpu)
> > -             hisi_hba->reply_map[cpu] = cpu % hisi_hba->queue_count;
> > -     /* Don't clean all CQ masks */
> > -}
> > -
> >  static int interrupt_init_v3_hw(struct hisi_hba *hisi_hba)
> >  {
> >       struct device *dev = hisi_hba->dev;
> > @@ -2383,11 +2359,6 @@ static int interrupt_init_v3_hw(struct hisi_hba *hisi_hba)
> >
> >               min_msi = MIN_AFFINE_VECTORS_V3_HW;
> >
> > -             hisi_hba->reply_map = devm_kcalloc(dev, nr_cpu_ids,
> > -                                                sizeof(unsigned int),
> > -                                                GFP_KERNEL);
> > -             if (!hisi_hba->reply_map)
> > -                     return -ENOMEM;
> >               vectors = pci_alloc_irq_vectors_affinity(hisi_hba->pci_dev,
> >                                                        min_msi, max_msi,
> >                                                        PCI_IRQ_MSI |
> > @@ -2395,7 +2366,6 @@ static int interrupt_init_v3_hw(struct hisi_hba *hisi_hba)
> >                                                        &desc);
> >               if (vectors < 0)
> >                       return -ENOENT;
> > -             setup_reply_map_v3_hw(hisi_hba, vectors - BASE_VECTORS_V3_HW);
> >       } else {
> >               min_msi = max_msi;
> >               vectors = pci_alloc_irq_vectors(hisi_hba->pci_dev, min_msi,
> > @@ -2896,6 +2866,18 @@ static void debugfs_snapshot_restore_v3_hw(struct hisi_hba *hisi_hba)
> >       clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
> >  }
> >
> > +static int hisi_sas_map_queues(struct Scsi_Host *shost)
> > +{
> > +     struct hisi_hba *hisi_hba = shost_priv(shost);
> > +     struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT];
> > +
> > +     if (auto_affine_msi_experimental)
> > +             return blk_mq_pci_map_queues(qmap, hisi_hba->pci_dev,
> > +                             BASE_VECTORS_V3_HW);
> > +     else
> > +             return blk_mq_map_queues(qmap);
> > +}
> > +
> >  static struct scsi_host_template sht_v3_hw = {
> >       .name                   = DRV_NAME,
> >       .module                 = THIS_MODULE,
>
> As mentioned, we should be using a common function here.
>
> > @@ -2906,6 +2888,8 @@ static struct scsi_host_template sht_v3_hw = {
> >       .scan_start             = hisi_sas_scan_start,
> >       .change_queue_depth     = sas_change_queue_depth,
> >       .bios_param             = sas_bios_param,
> > +     .map_queues             = hisi_sas_map_queues,
> > +     .host_tagset            = 1,
> >       .this_id                = -1,
> >       .sg_tablesize           = HISI_SAS_SGE_PAGE_CNT,
> >       .sg_prot_tablesize      = HISI_SAS_SGE_PAGE_CNT,
> > @@ -3092,6 +3076,8 @@ hisi_sas_v3_probe(struct pci_dev *pdev, const struct pci_device_id *id)
> >       if (hisi_sas_debugfs_enable)
> >               hisi_sas_debugfs_init(hisi_hba);
> >
> > +     shost->nr_hw_queues = hisi_hba->cq_nvecs;
> > +
> >       rc = scsi_add_host(shost, dev);
> >       if (rc)
> >               goto err_out_ha;
> >
> Well, I'd rather see the v3 hardware converted to 'real' blk-mq first;
> the hardware itself is pretty much multiqueue already, so we should be
> better off converting it to blk-mq.

From John Garry's input, the tags is still hostwide, then not sure how to
partition the hostwide tags into each hw queue's tags. That can be quite
hard to do if the queue depth isn't big enough.

Thanks,
Ming Lei

  reply index

Thread overview: 48+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-05-31  2:27 [PATCH 0/9] blk-mq/scsi: convert private reply queue into blk_mq " Ming Lei
2019-05-31  2:27 ` [PATCH 1/9] blk-mq: allow hw queues to share hostwide tags Ming Lei
2019-05-31  6:07   ` Hannes Reinecke
2019-05-31 15:37   ` Bart Van Assche
2019-06-24  8:44     ` Ming Lei
2019-06-05 14:10   ` John Garry
2019-06-24  8:46     ` Ming Lei
2019-06-24 13:14       ` John Garry
2019-05-31  2:27 ` [PATCH 2/9] block: null_blk: introduce module parameter of 'g_host_tags' Ming Lei
2019-05-31  6:08   ` Hannes Reinecke
2019-05-31 15:39   ` Bart Van Assche
2019-06-24  8:43     ` Ming Lei
2019-06-02  1:56   ` Minwoo Im
2019-05-31  2:27 ` [PATCH 3/9] scsi: Add template flag 'host_tagset' Ming Lei
2019-05-31  6:08   ` Hannes Reinecke
2019-05-31  2:27 ` [PATCH 4/9] scsi_debug: support host tagset Ming Lei
2019-05-31  6:09   ` Hannes Reinecke
2019-06-02  2:03   ` Minwoo Im
2019-06-02 17:01   ` Douglas Gilbert
2019-05-31  2:27 ` [PATCH 5/9] scsi: introduce scsi_cmnd_hctx_index() Ming Lei
2019-05-31  6:10   ` Hannes Reinecke
2019-05-31  2:27 ` [PATCH 6/9] scsi: hpsa: convert private reply queue to blk-mq hw queue Ming Lei
2019-05-31  6:15   ` Hannes Reinecke
2019-05-31  6:30     ` Ming Lei
2019-05-31  6:40       ` Hannes Reinecke
2019-05-31  2:27 ` [PATCH 7/9] scsi: hisi_sas_v3: " Ming Lei
2019-05-31  6:20   ` Hannes Reinecke
2019-05-31  6:34     ` Ming Lei [this message]
2019-05-31  6:42       ` Hannes Reinecke
2019-05-31  7:14         ` Ming Lei
2019-05-31 11:38       ` John Garry
2019-06-03 11:00         ` Ming Lei
2019-06-03 13:00           ` John Garry
2019-06-04 13:37             ` Ming Lei
2019-05-31  2:28 ` [PATCH 8/9] scsi: megaraid: " Ming Lei
2019-05-31  6:22   ` Hannes Reinecke
2019-06-01 21:41   ` Kashyap Desai
2019-06-02  6:42     ` Ming Lei
2019-06-02  7:48       ` Ming Lei
2019-06-02 16:34         ` Kashyap Desai
2019-06-03  3:56           ` Ming Lei
2019-06-03 10:00             ` Kashyap Desai
2019-06-07  9:45             ` Kashyap Desai
2019-05-31  2:28 ` [PATCH 9/9] scsi: mp3sas: " Ming Lei
2019-05-31  6:23   ` Hannes Reinecke
2019-06-06 11:58   ` Sreekanth Reddy
2019-06-04  8:49 ` [PATCH 0/9] blk-mq/scsi: convert private reply queue into blk_mq " John Garry
2019-08-13  8:30   ` John Garry

Reply instructions:

You may reply publically 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=CACVXFVMG8gkw8E0pmWBJC0tBH9D-WVjY2FnL2gsxDja3ryfbng@mail.gmail.com \
    --to=tom.leiming@gmail.com \
    --cc=James.Bottomley@hansenpartnership.com \
    --cc=axboe@kernel.dk \
    --cc=bvanassche@acm.org \
    --cc=don.brace@microsemi.com \
    --cc=hare@suse.com \
    --cc=hare@suse.de \
    --cc=hch@lst.de \
    --cc=john.garry@huawei.com \
    --cc=kashyap.desai@broadcom.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=martin.petersen@oracle.com \
    --cc=ming.lei@redhat.com \
    --cc=sathya.prakash@broadcom.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

Linux-Block Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-block/0 linux-block/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-block linux-block/ https://lore.kernel.org/linux-block \
		linux-block@vger.kernel.org linux-block@archiver.kernel.org
	public-inbox-index linux-block


Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-block


AGPL code for this site: git clone https://public-inbox.org/ public-inbox