From: Keith Busch <keith.busch@intel.com>
To: Jens Axboe <axboe@kernel.dk>, Christoph Hellwig <hch@lst.de>,
Sagi Grimberg <sagi@grimberg.me>, Ming Lei <ming.lei@redhat.com>,
linux-nvme@lists.infradead.org,
Bjorn Helgaas <helgaas@kernel.org>,
linux-pci@vger.kernel.org
Cc: Keith Busch <keith.busch@intel.com>
Subject: [PATCH 4/4] nvme-pci: Use PCI to handle IRQ reduce and retry
Date: Thu, 3 Jan 2019 14:09:54 -0700 [thread overview]
Message-ID: <20190103210954.11129-4-keith.busch@intel.com> (raw)
In-Reply-To: <20190103210954.11129-1-keith.busch@intel.com>
Restore the previous error handling for vector allocation to the PCI core.
Signed-off-by: Keith Busch <keith.busch@intel.com>
---
drivers/nvme/host/pci.c | 77 ++++++++++++++-----------------------------------
1 file changed, 21 insertions(+), 56 deletions(-)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 1481bb6d9c42..f3ef09a8e8f9 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2059,37 +2059,43 @@ static int nvme_setup_host_mem(struct nvme_dev *dev)
return ret;
}
-static void nvme_calc_io_queues(struct nvme_dev *dev, unsigned int irq_queues)
+static void nvme_calc_io_queues(struct irq_affinity *affd, unsigned int nvecs)
{
+ struct nvme_dev *dev = affd->priv;
unsigned int this_w_queues = write_queues;
/*
* Setup read/write queue split
*/
- if (irq_queues == 1) {
+ if (nvecs == 1) {
dev->io_queues[HCTX_TYPE_DEFAULT] = 1;
dev->io_queues[HCTX_TYPE_READ] = 0;
- return;
+ goto set_sets;
}
/*
* If 'write_queues' is set, ensure it leaves room for at least
* one read queue
*/
- if (this_w_queues >= irq_queues)
- this_w_queues = irq_queues - 1;
+ if (this_w_queues >= nvecs - 1)
+ this_w_queues = nvecs - 1;
/*
* If 'write_queues' is set to zero, reads and writes will share
* a queue set.
*/
if (!this_w_queues) {
- dev->io_queues[HCTX_TYPE_DEFAULT] = irq_queues;
+ dev->io_queues[HCTX_TYPE_DEFAULT] = nvecs - 1;
dev->io_queues[HCTX_TYPE_READ] = 0;
} else {
dev->io_queues[HCTX_TYPE_DEFAULT] = this_w_queues;
- dev->io_queues[HCTX_TYPE_READ] = irq_queues - this_w_queues;
+ dev->io_queues[HCTX_TYPE_READ] = nvecs - this_w_queues - 1;
}
+set_sets:
+ affd->sets[0] = dev->io_queues[HCTX_TYPE_DEFAULT];
+ affd->sets[1] = dev->io_queues[HCTX_TYPE_READ];
+ if (!affd->sets[1])
+ affd->nr_sets = 1;
}
static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
@@ -2100,9 +2106,10 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
.pre_vectors = 1,
.nr_sets = ARRAY_SIZE(irq_sets),
.sets = irq_sets,
+ .recalc_sets = nvme_calc_io_queues,
+ .priv = dev,
};
- int result = 0;
- unsigned int irq_queues, this_p_queues;
+ unsigned int nvecs, this_p_queues;
/*
* Poll queues don't need interrupts, but we need at least one IO
@@ -2111,56 +2118,14 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
this_p_queues = poll_queues;
if (this_p_queues >= nr_io_queues) {
this_p_queues = nr_io_queues - 1;
- irq_queues = 1;
+ nvecs = 2;
} else {
- irq_queues = nr_io_queues - this_p_queues;
+ nvecs = nr_io_queues - this_p_queues + 1;
}
dev->io_queues[HCTX_TYPE_POLL] = this_p_queues;
-
- /*
- * For irq sets, we have to ask for minvec == maxvec. This passes
- * any reduction back to us, so we can adjust our queue counts and
- * IRQ vector needs.
- */
- do {
- nvme_calc_io_queues(dev, irq_queues);
- irq_sets[0] = dev->io_queues[HCTX_TYPE_DEFAULT];
- irq_sets[1] = dev->io_queues[HCTX_TYPE_READ];
- if (!irq_sets[1])
- affd.nr_sets = 1;
-
- /*
- * If we got a failure and we're down to asking for just
- * 1 + 1 queues, just ask for a single vector. We'll share
- * that between the single IO queue and the admin queue.
- */
- if (result >= 0 && irq_queues > 1)
- irq_queues = irq_sets[0] + irq_sets[1] + 1;
-
- result = pci_alloc_irq_vectors_affinity(pdev, irq_queues,
- irq_queues,
- PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd);
-
- /*
- * Need to reduce our vec counts. If we get ENOSPC, the
- * platform should support mulitple vecs, we just need
- * to decrease our ask. If we get EINVAL, the platform
- * likely does not. Back down to ask for just one vector.
- */
- if (result == -ENOSPC) {
- irq_queues--;
- if (!irq_queues)
- return result;
- continue;
- } else if (result == -EINVAL) {
- irq_queues = 1;
- continue;
- } else if (result <= 0)
- return -EIO;
- break;
- } while (1);
-
- return result;
+ nvme_calc_io_queues(&affd, nvecs);
+ return pci_alloc_irq_vectors_affinity(pdev, affd.pre_vectors, nvecs,
+ PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd);
}
static int nvme_setup_io_queues(struct nvme_dev *dev)
--
2.14.4
next prev parent reply other threads:[~2019-01-03 21:11 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-01-03 21:09 [PATCH 1/4] nvme-pci: Set tagset nr_maps just once Keith Busch
2019-01-03 21:09 ` [PATCH 2/4] nvme-pci: Distribute io queue types after creation Keith Busch
2019-01-03 21:09 ` [PATCH 3/4] pci/irq: Handle vector reduce and retry Keith Busch
2019-01-03 21:39 ` Bjorn Helgaas
2019-01-03 21:51 ` Keith Busch
2019-01-03 21:09 ` Keith Busch [this message]
2019-01-04 18:15 ` [PATCH 1/4] nvme-pci: Set tagset nr_maps just once Christoph Hellwig
2019-01-04 18:19 ` Keith Busch
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=20190103210954.11129-4-keith.busch@intel.com \
--to=keith.busch@intel.com \
--cc=axboe@kernel.dk \
--cc=hch@lst.de \
--cc=helgaas@kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=linux-pci@vger.kernel.org \
--cc=ming.lei@redhat.com \
--cc=sagi@grimberg.me \
/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).