irq/matrix: Spread managed interrupts on allocation

Linux spreads out the non managed interrupt across the possible target CPUs
to avoid vector space exhaustion.

Managed interrupts are treated differently, as for them the vectors are
reserved (with guarantee) when the interrupt descriptors are initialized.

When the interrupt is requested a real vector is assigned. The assignment
logic uses the first CPU in the affinity mask for assignment. If the
interrupt has more than one CPU in the affinity mask, which happens when a
multi queue device has less queues than CPUs, then doing the same search as
for non managed interrupts makes sense as it puts the interrupt on the
least interrupt plagued CPU. For single CPU affine vectors that's obviously
a NOOP.

Restructre the matrix allocation code so it does the 'best CPU' search, add
the sanity check for an empty affinity mask and adapt the call site in the
x86 vector management code.

[ tglx: Added the empty mask check to the core and improved change log ]

Signed-off-by: Dou Liyang <douly.fnst@cn.fujitsu.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/20180908175838.14450-2-dou_liyang@163.com

arch/x86/kernel/apic/vector.c

@@ -313,14 +313,13 @@ assign_managed_vector(struct irq_data *irqd, const struct cpumask *dest)
 	struct apic_chip_data *apicd = apic_chip_data(irqd);
 	int vector, cpu;
 
-	cpumask_and(vector_searchmask, vector_searchmask, affmsk);
-	cpu = cpumask_first(vector_searchmask);
-	if (cpu >= nr_cpu_ids)
-		return -EINVAL;
+	cpumask_and(vector_searchmask, dest, affmsk);
+
 	/* set_affinity might call here for nothing */
 	if (apicd->vector && cpumask_test_cpu(apicd->cpu, vector_searchmask))
 		return 0;
-	vector = irq_matrix_alloc_managed(vector_matrix, cpu);
+	vector = irq_matrix_alloc_managed(vector_matrix, vector_searchmask,
+					  &cpu);
 	trace_vector_alloc_managed(irqd->irq, vector, vector);
 	if (vector < 0)
 		return vector;

include/linux/irq.h

@@ -1151,7 +1151,8 @@ void irq_matrix_offline(struct irq_matrix *m);
 void irq_matrix_assign_system(struct irq_matrix *m, unsigned int bit, bool replace);
 int irq_matrix_reserve_managed(struct irq_matrix *m, const struct cpumask *msk);
 void irq_matrix_remove_managed(struct irq_matrix *m, const struct cpumask *msk);
-int irq_matrix_alloc_managed(struct irq_matrix *m, unsigned int cpu);
+int irq_matrix_alloc_managed(struct irq_matrix *m, const struct cpumask *msk,
+				unsigned int *mapped_cpu);
 void irq_matrix_reserve(struct irq_matrix *m);
 void irq_matrix_remove_reserved(struct irq_matrix *m);
 int irq_matrix_alloc(struct irq_matrix *m, const struct cpumask *msk,

kernel/irq/matrix.c

@@ -260,11 +260,21 @@ void irq_matrix_remove_managed(struct irq_matrix *m, const struct cpumask *msk)
  * @m:		Matrix pointer
  * @cpu:	On which CPU the interrupt should be allocated
  */
-int irq_matrix_alloc_managed(struct irq_matrix *m, unsigned int cpu)
+int irq_matrix_alloc_managed(struct irq_matrix *m, const struct cpumask *msk,
+			     unsigned int *mapped_cpu)
 {
-	struct cpumap *cm = per_cpu_ptr(m->maps, cpu);
-	unsigned int bit, end = m->alloc_end;
+	unsigned int bit, cpu, end = m->alloc_end;
+	struct cpumap *cm;
+
+	if (cpumask_empty(msk))
+		return -EINVAL;
 
+	cpu = matrix_find_best_cpu(m, msk);
+	if (cpu == UINT_MAX)
+		return -ENOSPC;
+
+	cm = per_cpu_ptr(m->maps, cpu);
+	end = m->alloc_end;
 	/* Get managed bit which are not allocated */
 	bitmap_andnot(m->scratch_map, cm->managed_map, cm->alloc_map, end);
 	bit = find_first_bit(m->scratch_map, end);
@@ -273,6 +283,7 @@ int irq_matrix_alloc_managed(struct irq_matrix *m, unsigned int cpu)
 	set_bit(bit, cm->alloc_map);
 	cm->allocated++;
 	m->total_allocated++;
+	*mapped_cpu = cpu;
 	trace_irq_matrix_alloc_managed(bit, cpu, m, cm);
 	return bit;
 }