From 7064d865af804b9b841e7b9a3e9b653e40c3e5ca Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Mon, 17 Jan 2011 10:52:10 +0800 Subject: x86: Avoid tlbstate lock if not enough cpus This one isn't related to previous patch. If online cpus are below NUM_INVALIDATE_TLB_VECTORS, we don't need the lock. The comments in the code declares we don't need the check, but a hot lock still needs an atomic operation and expensive, so add the check here. Uses nr_cpu_ids here as suggested by Eric Dumazet. Signed-off-by: Shaohua Li Acked-by: Eric Dumazet Cc: Andi Kleen LKML-Reference: <1295232730.1949.710.camel@sli10-conroe> Signed-off-by: Ingo Molnar --- arch/x86/mm/tlb.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'arch/x86/mm/tlb.c') diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 6acc724d5d8f..55272d7c3b0b 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -179,12 +179,8 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask, sender = this_cpu_read(tlb_vector_offset); f = &flush_state[sender]; - /* - * Could avoid this lock when - * num_online_cpus() <= NUM_INVALIDATE_TLB_VECTORS, but it is - * probably not worth checking this for a cache-hot lock. - */ - raw_spin_lock(&f->tlbstate_lock); + if (nr_cpu_ids > NUM_INVALIDATE_TLB_VECTORS) + raw_spin_lock(&f->tlbstate_lock); f->flush_mm = mm; f->flush_va = va; @@ -202,7 +198,8 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask, f->flush_mm = NULL; f->flush_va = 0; - raw_spin_unlock(&f->tlbstate_lock); + if (nr_cpu_ids > NUM_INVALIDATE_TLB_VECTORS) + raw_spin_unlock(&f->tlbstate_lock); } void native_flush_tlb_others(const struct cpumask *cpumask, -- cgit v1.2.3 From 25542c646afbf14c43fa7d2b443055cadb73b07a Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Tue, 15 Mar 2011 09:57:37 +0800 Subject: x86, tlb, UV: Do small micro-optimization for native_flush_tlb_others() native_flush_tlb_others() is called from: flush_tlb_current_task() flush_tlb_mm() flush_tlb_page() All these functions disable preemption explicitly, so we can use smp_processor_id() instead of get_cpu() and put_cpu(). Signed-off-by: Xiao Guangrong Cc: Cliff Wickman LKML-Reference: <4D7EC791.4040003@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- arch/x86/mm/tlb.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'arch/x86/mm/tlb.c') diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 55272d7c3b0b..d6c0418c3e47 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -208,11 +208,10 @@ void native_flush_tlb_others(const struct cpumask *cpumask, if (is_uv_system()) { unsigned int cpu; - cpu = get_cpu(); + cpu = smp_processor_id(); cpumask = uv_flush_tlb_others(cpumask, mm, va, cpu); if (cpumask) flush_tlb_others_ipi(cpumask, mm, va); - put_cpu(); return; } flush_tlb_others_ipi(cpumask, mm, va); -- cgit v1.2.3