x86/irq: round-robin distribution of irqs to cpus w/in node
SGI has encountered situations where particular CPUs run out of interrupt vectors on systems with many (several hundred or more) CPUs. This happens because some drivers (particularly the mlx4_core driver) select the number of interrupts they allocate based on the number of CPUs, and because of how the default irq affinity is used.
Do psuedo round-robin distribution of irqs to CPUs within a node to avoid (or at least delay) running out of vectors on any particular CPU.
Signed-off-by Arthur Kepner <[email protected]>
---
arch/x86/kernel/apic/io_apic.c | 28 ++++++++++++++++++++++++++-- 1 file changed, 26 insertions(+), 2 deletions(-)
arch/x86/kernel/apic/io_apic.c +26 -2
@@ -3254,6 +3254,8 @@ unsigned int create_irq_nr(unsigned int irq_want, int node)raw_spin_lock_irqsave (&vector_lock, flags);for (new = irq_want; new < nr_irqs; new++) { +cpumask_var_t tmp_mask; + desc_new =irq_to_desc_alloc_node (new, node);if (!desc_new) {printk (KERN_INFO "can not get irq_desc for %d\n" , new);
@@ -3267,8 +3269,30 @@ unsigned int create_irq_nr(unsigned int irq_want, int node) desc_new =move_irq_desc (desc_new, node); cfg_new = desc_new->chip_data; -if (__assign_irq_vector (new, cfg_new, apic->target_cpus ()) ==0 ) - irq = new; +if ((node !=-1 ) &&alloc_cpumask_var (&tmp_mask,GFP_ATOMIC )) { + +static int cpu; + +/* try to place irq on a cpu in the node in psuedo- +* round robin order*/ + + cpu =__next_cpu_nr (cpu,cpumask_of_node (node)); +if (cpu >= nr_cpu_ids) + cpu =0 ; + +cpumask_set_cpu (cpu, tmp_mask); + +if (cpumask_test_cpu (cpu, apic->target_cpus ()) && +__assign_irq_vector (new, cfg_new, tmp_mask) ==0 ) + irq = new; + +free_cpumask_var (tmp_mask); + } + +if (irq ==0 ) +if (__assign_irq_vector (new, cfg_new, + apic->target_cpus ()) ==0 ) + irq = new;break ; }raw_spin_unlock_irqrestore (&vector_lock, flags);