From f0915781bd5edf78b1154e61efe962dc15872d09 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 11 Feb 2013 13:47:48 +0000 Subject: ARM: tlb: don't perform inner-shareable invalidation for local TLB ops Inner-shareable TLB invalidation is typically more expensive than local (non-shareable) invalidation, so performing the broadcasting for local_flush_tlb_* operations is a waste of cycles and needlessly clobbers entries in the TLBs of other CPUs. This patch introduces __flush_tlb_* versions for many of the TLB invalidation functions, which only respect inner-shareable variants of the invalidation instructions when presented with the TLB_V7_UIS_FULL flag. The local version is also inlined to prevent SMP_ON_UP kernels from missing flushes, where the __flush variant would be called with the UP flags. This gains us around 0.5% in hackbench scores for a dual-core A15, but I would expect this to improve as more cores (and clusters) are added to the equation. Reviewed-by: Catalin Marinas Reported-by: Albin Tonnerre Signed-off-by: Will Deacon --- arch/arm/kernel/smp_tlb.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'arch/arm/kernel/smp_tlb.c') diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c index c2edfff573c2..5883b8ae77c8 100644 --- a/arch/arm/kernel/smp_tlb.c +++ b/arch/arm/kernel/smp_tlb.c @@ -104,7 +104,7 @@ void flush_tlb_all(void) if (tlb_ops_need_broadcast()) on_each_cpu(ipi_flush_tlb_all, NULL, 1); else - local_flush_tlb_all(); + __flush_tlb_all(); broadcast_tlb_a15_erratum(); } @@ -113,7 +113,7 @@ void flush_tlb_mm(struct mm_struct *mm) if (tlb_ops_need_broadcast()) on_each_cpu_mask(mm_cpumask(mm), ipi_flush_tlb_mm, mm, 1); else - local_flush_tlb_mm(mm); + __flush_tlb_mm(mm); broadcast_tlb_mm_a15_erratum(mm); } @@ -126,7 +126,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_page, &ta, 1); } else - local_flush_tlb_page(vma, uaddr); + __flush_tlb_page(vma, uaddr); broadcast_tlb_mm_a15_erratum(vma->vm_mm); } @@ -137,7 +137,7 @@ void flush_tlb_kernel_page(unsigned long kaddr) ta.ta_start = kaddr; on_each_cpu(ipi_flush_tlb_kernel_page, &ta, 1); } else - local_flush_tlb_kernel_page(kaddr); + __flush_tlb_kernel_page(kaddr); broadcast_tlb_a15_erratum(); } -- cgit v1.2.1