From: Christoph Hellwig <hch@lst.de>
To: tglx@linutronix.de, linux-block@vger.kernel.org,
linux-pci@vger.kernel.org
Cc: linux-nvme@lists.infradead.org, linux-kernel@vger.kernel.org
Subject: [PATCH 7/8] pci: spread interrupt vectors in pci_alloc_irq_vectors
Date: Fri, 15 Apr 2016 18:35:51 -0700 [thread overview]
Message-ID: <1460770552-31260-8-git-send-email-hch@lst.de> (raw)
In-Reply-To: <1460770552-31260-1-git-send-email-hch@lst.de>
Set the affinity_mask before allocating vectors. And for now we also
need a little hack after allocation, hopefully someone smarter than me
can move this into the core code.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/pci/irq.c | 16 +++++++++++++++-
1 file changed, 15 insertions(+), 1 deletion(-)
diff --git a/drivers/pci/irq.c b/drivers/pci/irq.c
index b683465..d26df69 100644
--- a/drivers/pci/irq.c
+++ b/drivers/pci/irq.c
@@ -55,9 +55,14 @@ int pci_alloc_irq_vectors(struct pci_dev *pdev, int nr_vecs)
nr_vecs = min(nr_vecs, pci_nr_irq_vectors(pdev));
+ ret = irq_create_affinity_mask(&pdev->dev.irq_affinity, nr_vecs);
+ if (ret)
+ return ret;
+
+ ret = -ENOMEM;
irqs = kcalloc(nr_vecs, sizeof(u32), GFP_KERNEL);
if (!irqs)
- return -ENOMEM;
+ goto out_free_affinity;
vecs = pci_enable_msix_range_wrapper(pdev, irqs, nr_vecs);
if (vecs <= 0) {
@@ -75,11 +80,20 @@ int pci_alloc_irq_vectors(struct pci_dev *pdev, int nr_vecs)
irqs[i] = pdev->irq + i;
}
+ /* XXX: this should really move into the core IRQ allocation code.. */
+ if (vecs > 1) {
+ for (i = 0; i < vecs; i++)
+ irq_program_affinity(irqs[i]);
+ }
+
pdev->irqs = irqs;
return vecs;
out_free_irqs:
kfree(irqs);
+out_free_affinity:
+ kfree(pdev->dev.irq_affinity);
+ pdev->dev.irq_affinity = NULL;
return ret;
}
EXPORT_SYMBOL(pci_alloc_irq_vectors);
--
2.1.4
next prev parent reply other threads:[~2016-04-16 1:35 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-04-16 1:35 RFC: automatic interrupt affinity for MSI/MSI-X capable devices Christoph Hellwig
2016-04-16 1:35 ` [PATCH 1/8] device: Add irq affinity hint cpumask pointer Christoph Hellwig
2016-04-16 1:35 ` [PATCH 2/8] genirq: Make use of dev->irq_affinity Christoph Hellwig
2016-04-16 1:35 ` [PATCH 3/8] genirq: add a helper spread an affinity mask for MSI/MSI-X vectors Christoph Hellwig
2016-04-16 1:35 ` [PATCH 4/8] genirq: add a helper to program the pre-set affinity mask into the controller Christoph Hellwig
2016-04-16 1:35 ` [PATCH 5/8] blk-mq: allow the driver to pass in an affinity mask Christoph Hellwig
2016-04-16 1:35 ` [PATCH 6/8] pci: provide sensible irq vector alloc/free routines Christoph Hellwig
2016-04-29 21:16 ` Bjorn Helgaas
2016-05-01 18:01 ` Christoph Hellwig
2016-05-02 13:11 ` Bjorn Helgaas
2016-05-02 14:42 ` Christoph Hellwig
2016-05-02 15:29 ` Bjorn Helgaas
2016-05-03 21:19 ` Christoph Hellwig
2016-05-03 21:37 ` Bjorn Helgaas
2016-04-16 1:35 ` Christoph Hellwig [this message]
2016-04-18 8:30 ` [PATCH 7/8] pci: spread interrupt vectors in pci_alloc_irq_vectors Thomas Gleixner
2016-04-16 1:35 ` [PATCH 8/8] nvme: switch to use pci_alloc_irq_vectors 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=1460770552-31260-8-git-send-email-hch@lst.de \
--to=hch@lst.de \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=linux-pci@vger.kernel.org \
--cc=tglx@linutronix.de \
/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).