From: "Yinghai Lu" In phys flat mode, when using set_xxx_irq_affinity to irq balance from one cpu to another, _assign_irq_vector will get to increase last used vector and get new vector. this will use up the vector if enough set_xxx_irq_affintiy are called. and end with using same vector in want to use same vector in different cpu for different irq when more than 0x240 irq needed). To keep it simple, the vector should be reused instead of getting new vector. Also according to Eric's review, make it more generic to be used with flat mode too. It also check if new domain and old domain is equal, to avoid extra operation. Cc: Eric W. Biederman Cc: Muli Ben-Yehuda Signed-off-by: Yinghai Lu Cc: Andi Kleen Signed-off-by: Andrew Morton --- arch/x86_64/kernel/io_apic.c | 72 +++++++++++++++++++++++---------- 1 files changed, 51 insertions(+), 21 deletions(-) diff -puN arch/x86_64/kernel/io_apic.c~x86_64-irq-reuse-vector-for-__assign_irq_vector arch/x86_64/kernel/io_apic.c --- a/arch/x86_64/kernel/io_apic.c~x86_64-irq-reuse-vector-for-__assign_irq_vector +++ a/arch/x86_64/kernel/io_apic.c @@ -613,8 +613,9 @@ static int __assign_irq_vector(int irq, * 0x80, because int 0x80 is hm, kind of importantish. ;) */ static int current_vector = FIRST_DEVICE_VECTOR, current_offset = 0; - int old_vector = -1; - int cpu; + int vector = -1, old_vector = -1; + cpumask_t domain, new_mask; + int cpu, new_cpu; BUG_ON((unsigned)irq >= NR_IRQ_VECTORS); @@ -624,15 +625,38 @@ static int __assign_irq_vector(int irq, if (irq_vector[irq] > 0) old_vector = irq_vector[irq]; if (old_vector > 0) { - cpus_and(*result, irq_domain[irq], mask); - if (!cpus_empty(*result)) - return old_vector; + /* try to reuse vector */ + for_each_cpu_mask(cpu, mask) { + int can_reuse = 1; + + domain = vector_allocation_domain(cpu); + cpus_and(new_mask, domain, cpu_online_map); + + if (cpus_equal(domain, irq_domain[irq])) { + cpus_and(*result, irq_domain[irq], mask); + if (!cpus_empty(*result)) + return old_vector; + } + + for_each_cpu_mask(new_cpu, new_mask) { + int old_irq; + old_irq = per_cpu(vector_irq, new_cpu)[old_vector]; + if ((old_irq != irq) && (old_irq != -1)) { + can_reuse = 0; + break; + } + } + + if(!can_reuse) + continue; + + vector = old_vector; + goto found_one; + } } for_each_cpu_mask(cpu, mask) { - cpumask_t domain, new_mask; - int new_cpu; - int vector, offset; + int offset; domain = vector_allocation_domain(cpu); cpus_and(new_mask, domain, cpu_online_map); @@ -656,21 +680,27 @@ next: /* Found one! */ current_vector = vector; current_offset = offset; - if (old_vector >= 0) { - cpumask_t old_mask; - int old_cpu; - cpus_and(old_mask, irq_domain[irq], cpu_online_map); - for_each_cpu_mask(old_cpu, old_mask) - per_cpu(vector_irq, old_cpu)[old_vector] = -1; - } - for_each_cpu_mask(new_cpu, new_mask) - per_cpu(vector_irq, new_cpu)[vector] = irq; - irq_vector[irq] = vector; - irq_domain[irq] = domain; - cpus_and(*result, domain, mask); - return vector; + + goto found_one; } + return -ENOSPC; + +found_one: + if (old_vector >= 0) { + cpumask_t old_mask; + int old_cpu; + cpus_and(old_mask, irq_domain[irq], cpu_online_map); + for_each_cpu_mask(old_cpu, old_mask) + per_cpu(vector_irq, old_cpu)[old_vector] = -1; + } + for_each_cpu_mask(new_cpu, new_mask) + per_cpu(vector_irq, new_cpu)[vector] = irq; + irq_vector[irq] = vector; + irq_domain[irq] = domain; + cpus_and(*result, domain, mask); + return vector; + } static int assign_irq_vector(int irq, cpumask_t mask, cpumask_t *result) _