[PATCH 13/16] irq: add support for allocating (and affinitizing) sets of IRQs

[Jens Axboe]

A driver may have a need to allocate multiple sets of MSI/MSI-X
interrupts, and have them appropriately affinitized. Add support for
defining a number of sets in the irq_affinity structure, of varying
sizes, and get each set affinitized correctly across the machine.

Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: linux-kernel@xxxxxxxxxxxxxxx
Reviewed-by: Hannes Reinecke <hare@xxxxxxxx>
Reviewed-by: Ming Lei <ming.lei@xxxxxxxxxx>
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
---
 drivers/pci/msi.c         | 14 ++++++++++++++
 include/linux/interrupt.h |  4 ++++
 kernel/irq/affinity.c     | 40 ++++++++++++++++++++++++++++++---------
 3 files changed, 49 insertions(+), 9 deletions(-)

diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index af24ed50a245..e6c6e10b9ceb 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1036,6 +1036,13 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec,
 	if (maxvec < minvec)
 		return -ERANGE;
 
+	/*
+	 * If the caller is passing in sets, we can't support a range of
+	 * vectors. The caller needs to handle that.
+	 */
+	if (affd->nr_sets && minvec != maxvec)
+		return -EINVAL;
+
 	if (WARN_ON_ONCE(dev->msi_enabled))
 		return -EINVAL;
 
@@ -1087,6 +1094,13 @@ static int __pci_enable_msix_range(struct pci_dev *dev,
 	if (maxvec < minvec)
 		return -ERANGE;
 
+	/*
+	 * If the caller is passing in sets, we can't support a range of
+	 * supported vectors. The caller needs to handle that.
+	 */
+	if (affd->nr_sets && minvec != maxvec)
+		return -EINVAL;
+
 	if (WARN_ON_ONCE(dev->msix_enabled))
 		return -EINVAL;
 
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 1d6711c28271..ca397ff40836 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -247,10 +247,14 @@ struct irq_affinity_notify {
  *			the MSI(-X) vector space
  * @post_vectors:	Don't apply affinity to @post_vectors at end of
  *			the MSI(-X) vector space
+ * @nr_sets:		Length of passed in *sets array
+ * @sets:		Number of affinitized sets
  */
 struct irq_affinity {
 	int	pre_vectors;
 	int	post_vectors;
+	int	nr_sets;
+	int	*sets;
 };
 
 #if defined(CONFIG_SMP)
diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
index f4f29b9d90ee..2046a0f0f0f1 100644
--- a/kernel/irq/affinity.c
+++ b/kernel/irq/affinity.c
@@ -180,6 +180,7 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
 	int curvec, usedvecs;
 	cpumask_var_t nmsk, npresmsk, *node_to_cpumask;
 	struct cpumask *masks = NULL;
+	int i, nr_sets;
 
 	/*
 	 * If there aren't any vectors left after applying the pre/post
@@ -210,10 +211,23 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
 	get_online_cpus();
 	build_node_to_cpumask(node_to_cpumask);
 
-	/* Spread on present CPUs starting from affd->pre_vectors */
-	usedvecs = irq_build_affinity_masks(affd, curvec, affvecs,
-					    node_to_cpumask, cpu_present_mask,
-					    nmsk, masks);
+	/*
+	 * Spread on present CPUs starting from affd->pre_vectors. If we
+	 * have multiple sets, build each sets affinity mask separately.
+	 */
+	nr_sets = affd->nr_sets;
+	if (!nr_sets)
+		nr_sets = 1;
+
+	for (i = 0, usedvecs = 0; i < nr_sets; i++) {
+		int this_vecs = affd->sets ? affd->sets[i] : affvecs;
+		int nr;
+
+		nr = irq_build_affinity_masks(affd, curvec, this_vecs,
+					      node_to_cpumask, cpu_present_mask,
+					      nmsk, masks + usedvecs);
+		usedvecs += nr;
+	}
 
 	/*
 	 * Spread on non present CPUs starting from the next vector to be
@@ -258,13 +272,21 @@ int irq_calc_affinity_vectors(int minvec, int maxvec, const struct irq_affinity
 {
 	int resv = affd->pre_vectors + affd->post_vectors;
 	int vecs = maxvec - resv;
-	int ret;
+	int set_vecs;
 
 	if (resv > minvec)
 		return 0;
 
-	get_online_cpus();
-	ret = min_t(int, cpumask_weight(cpu_possible_mask), vecs) + resv;
-	put_online_cpus();
-	return ret;
+	if (affd->nr_sets) {
+		int i;
+
+		for (i = 0, set_vecs = 0;  i < affd->nr_sets; i++)
+			set_vecs += affd->sets[i];
+	} else {
+		get_online_cpus();
+		set_vecs = cpumask_weight(cpu_possible_mask);
+		put_online_cpus();
+	}
+
+	return resv + min(set_vecs, vecs);
 }
-- 
2.17.1