From: Ming Lei <ming.lei@redhat.com>
To: Christoph Hellwig <hch@lst.de>,
Bjorn Helgaas <helgaas@kernel.org>,
Thomas Gleixner <tglx@linutronix.de>
Cc: Jens Axboe <axboe@kernel.dk>,
linux-block@vger.kernel.org, Sagi Grimberg <sagi@grimberg.me>,
linux-nvme@lists.infradead.org, linux-kernel@vger.kernel.org,
linux-pci@vger.kernel.org, Ming Lei <ming.lei@redhat.com>
Subject: [PATCH 3/5] genirq/affinity: introduce irq_build_affinity()
Date: Fri, 25 Jan 2019 17:53:45 +0800 [thread overview]
Message-ID: <20190125095347.17950-4-ming.lei@redhat.com> (raw)
In-Reply-To: <20190125095347.17950-1-ming.lei@redhat.com>
Drivers may use this API to build customized irq affinity, one example
is NVMe, which needs to build multiple irq sets, on each of which all
CPUs are spread.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
include/linux/interrupt.h | 12 ++++++++++++
kernel/irq/affinity.c | 27 +++++++++++++++++++++++++++
2 files changed, 39 insertions(+)
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index f6cea778cf50..b820b07f3b55 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -323,6 +323,10 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify);
struct irq_affinity_desc *
irq_create_affinity_masks(int nvec, const struct irq_affinity *affd);
+int irq_build_affinity(const struct irq_affinity *affd, int startvec,
+ int numvecs, int firstvec,
+ struct irq_affinity_desc *masks, int nmasks);
+
int irq_calc_affinity_vectors(int minvec, int maxvec, const struct irq_affinity *affd);
#else /* CONFIG_SMP */
@@ -368,6 +372,14 @@ irq_calc_affinity_vectors(int minvec, int maxvec, const struct irq_affinity *aff
return maxvec;
}
+static inline int
+irq_build_affinity(const struct irq_affinity *affd, int startvec,
+ int numvecs, int firstvec,
+ struct irq_affinity_desc *masks, int nmasks)
+{
+ return 0;
+}
+
#endif /* CONFIG_SMP */
/*
diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
index 7b77cbdf739c..524fdcda9f85 100644
--- a/kernel/irq/affinity.c
+++ b/kernel/irq/affinity.c
@@ -232,6 +232,33 @@ static int irq_build_affinity_masks(const struct irq_affinity *affd,
}
/**
+ * irq_build_affinity - build affinity masks for multiqueue spreading
+ * @affd: Description of the affinity requirements
+ * @startvec: The start vector for building affinity masks
+ * @numvec: The number of vectors is needed for building affinity
+ * @firstvec: It is the IRQ vector which we jump to for continue spread
+ * after the last vector(@startvec + @numvec - 1) is built.
+ * @masks: The mask array for storing the affinity masks
+ * @nmasks: The total number of @masks
+ *
+ * Both @startvec and @firstvec are relative to the 1st irq vectorc
+ * allocated to the device.
+ *
+ * Returns 0 if affinty masks is built successfully.
+ */
+int irq_build_affinity(const struct irq_affinity *affd, int startvec,
+ int numvecs, int firstvec,
+ struct irq_affinity_desc *masks, int nmasks)
+{
+ if (startvec >= nmasks || firstvec >= nmasks || numvecs > nmasks)
+ return -EINVAL;
+
+ return irq_build_affinity_masks(affd, startvec, numvecs, firstvec,
+ masks);
+}
+EXPORT_SYMBOL_GPL(irq_build_affinity);
+
+/**
* irq_create_affinity_masks - Create affinity masks for multiqueue spreading
* @nvecs: The total number of vectors
* @affd: Description of the affinity requirements
--
2.9.5
next prev parent reply other threads:[~2019-01-25 9:54 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-01-25 9:53 [PATCH 0/5] genirq/affinity: introduce .setup_affinity to support allocating interrupt sets Ming Lei
2019-01-25 9:53 ` [PATCH 1/5] genirq/affinity: move allocation of 'node_to_cpumask' to irq_build_affinity_masks Ming Lei
2019-02-07 22:02 ` Bjorn Helgaas
2019-02-10 19:01 ` [tip:irq/core] genirq/affinity: Move allocation of 'node_to_cpumask' to irq_build_affinity_masks() tip-bot for Ming Lei
2019-01-25 9:53 ` [PATCH 2/5] genirq/affinity: allow driver to setup managed IRQ's affinity Ming Lei
2019-02-07 22:21 ` Bjorn Helgaas
2019-02-10 9:22 ` Ming Lei
2019-02-10 16:30 ` Thomas Gleixner
2019-02-11 3:54 ` Ming Lei
2019-02-11 14:39 ` Bjorn Helgaas
2019-02-11 22:38 ` Thomas Gleixner
2019-02-12 11:17 ` Ming Lei
2019-01-25 9:53 ` Ming Lei [this message]
2019-01-25 9:53 ` [PATCH 4/5] nvme-pci: simplify nvme_setup_irqs() via .setup_affinity callback Ming Lei
2019-02-10 16:39 ` Thomas Gleixner
2019-02-11 3:58 ` Ming Lei
2019-02-10 18:49 ` Thomas Gleixner
2019-02-11 4:09 ` Ming Lei
2019-01-25 9:53 ` [PATCH 5/5] genirq/affinity: remove support for allocating interrupt sets Ming Lei
2019-02-07 22:22 ` Bjorn Helgaas
2019-01-25 9:56 ` [PATCH 0/5] genirq/affinity: introduce .setup_affinity to support " Ming Lei
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=20190125095347.17950-4-ming.lei@redhat.com \
--to=ming.lei@redhat.com \
--cc=axboe@kernel.dk \
--cc=hch@lst.de \
--cc=helgaas@kernel.org \
--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=sagi@grimberg.me \
--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).