Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S965874Ab3GSFaJ (ORCPT ); Fri, 19 Jul 2013 01:30:09 -0400 Received: from mail.linuxfoundation.org ([140.211.169.12]:40040 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S965821Ab3GSF1R (ORCPT ); Fri, 19 Jul 2013 01:27:17 -0400 From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Will Deacon , Catalin Marinas , Marc Zyngier , Russell King Subject: [ 62/72] ARM: 7769/1: Cortex-A15: fix erratum 798181 implementation Date: Thu, 18 Jul 2013 22:26:19 -0700 Message-Id: <20130719052604.108594547@linuxfoundation.org> X-Mailer: git-send-email 1.8.3.2 In-Reply-To: <20130719052559.852627424@linuxfoundation.org> References: <20130719052559.852627424@linuxfoundation.org> User-Agent: quilt/0.60-1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4461 Lines: 133 3.10-stable review patch. If anyone has any objections, please let me know. ------------------ From: Marc Zyngier commit 0d0752bca1f9a91fb646647aa4abbb21156f316c upstream. Looking into the active_asids array is not enough, as we also need to look into the reserved_asids array (they both represent processes that are currently running). Also, not holding the ASID allocator lock is racy, as another CPU could schedule that process and trigger a rollover, making the erratum workaround miss an IPI. Exposing this outside of context.c is a little ugly on the side, so let's define a new entry point that the erratum workaround can call to obtain the cpumask. Acked-by: Will Deacon Acked-by: Catalin Marinas Signed-off-by: Marc Zyngier Signed-off-by: Russell King Signed-off-by: Greg Kroah-Hartman --- arch/arm/include/asm/mmu_context.h | 10 +++++++++- arch/arm/kernel/smp_tlb.c | 18 ++---------------- arch/arm/mm/context.c | 29 ++++++++++++++++++++++++++++- 3 files changed, 39 insertions(+), 18 deletions(-) --- a/arch/arm/include/asm/mmu_context.h +++ b/arch/arm/include/asm/mmu_context.h @@ -27,7 +27,15 @@ void __check_vmalloc_seq(struct mm_struc void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk); #define init_new_context(tsk,mm) ({ atomic64_set(&mm->context.id, 0); 0; }) -DECLARE_PER_CPU(atomic64_t, active_asids); +#ifdef CONFIG_ARM_ERRATA_798181 +void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm, + cpumask_t *mask); +#else /* !CONFIG_ARM_ERRATA_798181 */ +static inline void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm, + cpumask_t *mask) +{ +} +#endif /* CONFIG_ARM_ERRATA_798181 */ #else /* !CONFIG_CPU_HAS_ASID */ --- a/arch/arm/kernel/smp_tlb.c +++ b/arch/arm/kernel/smp_tlb.c @@ -103,7 +103,7 @@ static void broadcast_tlb_a15_erratum(vo static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm) { - int cpu, this_cpu; + int this_cpu; cpumask_t mask = { CPU_BITS_NONE }; if (!erratum_a15_798181()) @@ -111,21 +111,7 @@ static void broadcast_tlb_mm_a15_erratum dummy_flush_tlb_a15_erratum(); this_cpu = get_cpu(); - for_each_online_cpu(cpu) { - if (cpu == this_cpu) - continue; - /* - * We only need to send an IPI if the other CPUs are running - * the same ASID as the one being invalidated. There is no - * need for locking around the active_asids check since the - * switch_mm() function has at least one dmb() (as required by - * this workaround) in case a context switch happens on - * another CPU after the condition below. - */ - if (atomic64_read(&mm->context.id) == - atomic64_read(&per_cpu(active_asids, cpu))) - cpumask_set_cpu(cpu, &mask); - } + a15_erratum_get_cpumask(this_cpu, mm, &mask); smp_call_function_many(&mask, ipi_flush_tlb_a15_erratum, NULL, 1); put_cpu(); } --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -45,10 +45,37 @@ static DEFINE_RAW_SPINLOCK(cpu_asid_lock static atomic64_t asid_generation = ATOMIC64_INIT(ASID_FIRST_VERSION); static DECLARE_BITMAP(asid_map, NUM_USER_ASIDS); -DEFINE_PER_CPU(atomic64_t, active_asids); +static DEFINE_PER_CPU(atomic64_t, active_asids); static DEFINE_PER_CPU(u64, reserved_asids); static cpumask_t tlb_flush_pending; +#ifdef CONFIG_ARM_ERRATA_798181 +void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm, + cpumask_t *mask) +{ + int cpu; + unsigned long flags; + u64 context_id, asid; + + raw_spin_lock_irqsave(&cpu_asid_lock, flags); + context_id = mm->context.id.counter; + for_each_online_cpu(cpu) { + if (cpu == this_cpu) + continue; + /* + * We only need to send an IPI if the other CPUs are + * running the same ASID as the one being invalidated. + */ + asid = per_cpu(active_asids, cpu).counter; + if (asid == 0) + asid = per_cpu(reserved_asids, cpu); + if (context_id == asid) + cpumask_set_cpu(cpu, mask); + } + raw_spin_unlock_irqrestore(&cpu_asid_lock, flags); +} +#endif + #ifdef CONFIG_ARM_LPAE static void cpu_set_reserved_ttbr0(void) { -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/