From patchwork Thu Jun 30 14:57:41 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Daniel Thompson X-Patchwork-Id: 71253 Delivered-To: patches@linaro.org Received: by 10.140.28.4 with SMTP id 4csp438033qgy; Thu, 30 Jun 2016 07:58:02 -0700 (PDT) X-Received: by 10.28.224.5 with SMTP id x5mr26418569wmg.11.1467298682601; Thu, 30 Jun 2016 07:58:02 -0700 (PDT) Return-Path: Received: from mail-wm0-x22b.google.com (mail-wm0-x22b.google.com. [2a00:1450:400c:c09::22b]) by mx.google.com with ESMTPS id uq9si4339836wjb.114.2016.06.30.07.58.02 for (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Thu, 30 Jun 2016 07:58:02 -0700 (PDT) Received-SPF: pass (google.com: domain of daniel.thompson@linaro.org designates 2a00:1450:400c:c09::22b as permitted sender) client-ip=2a00:1450:400c:c09::22b; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org; spf=pass (google.com: domain of daniel.thompson@linaro.org designates 2a00:1450:400c:c09::22b as permitted sender) smtp.mailfrom=daniel.thompson@linaro.org; dmarc=pass (p=NONE dis=NONE) header.from=linaro.org Received: by mail-wm0-x22b.google.com with SMTP id r201so122736009wme.1 for ; Thu, 30 Jun 2016 07:58:02 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=from:to:cc:subject:date:message-id:in-reply-to:references; bh=VPy875oXcmpLCIr5Fuy3ZdV/mT0T7IxtB+keIVcleO8=; b=Le3c5elCqnc+xYoT9UWB4X+ImeMTsiuQn1aCGad8LER9ke09Y+waeaayTH9kRrKTfK f1xHcE10Gb4m1wNULTb+ajzNdzXgXi0+sYDU0p6g+r/ARiWsnfA/AxWuqyzCJqa/dI9h mQaiGoaOlolqxEitwKZTO904fkQXf/GntWaLs= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references; bh=VPy875oXcmpLCIr5Fuy3ZdV/mT0T7IxtB+keIVcleO8=; b=YfCkmEWVW2l83NeKzqHuHHlzDBlJ52SHpFYPrFm1CrUe9EBeOBuKEmEAwcJCG6nYjU 7FzEakGqzVENvdIcgwUxTa43YlyZvH4bDWwAjqY3i8+frMJO5lJYtW9OcI/ofrFjvNHI To3kbU+6GZtYT9zkHksDyxPVid3fZ8V14/GrA4wuDR2iBruBSmARYKb2zdGagc5ZTzhS y/951iSjdxHjr1dgAEuxJpUVE1AwTDqwB9MFTfTGZJLzJYyarMbUUGmKP0Y7CRujfEa4 WLGurOOUmb1GaF0CN/PkVHCFy8t+l3aES1lkITAbS1oxa1bDBZ6lxNXJLT8H9gJMqXi1 sWVA== X-Gm-Message-State: ALyK8tIACYqkCgdGtthrScI4Bxh0h8neGuKTST8sPsFXtFDmm/Y7Uv83xyTfRSluK83bBZ6NMsY= X-Received: by 10.28.189.9 with SMTP id n9mr14241900wmf.79.1467298682345; Thu, 30 Jun 2016 07:58:02 -0700 (PDT) Return-Path: Received: from wychelm.lan (cpc4-aztw19-0-0-cust71.18-1.cable.virginm.net. [82.33.25.72]) by smtp.gmail.com with ESMTPSA id r130sm4222874wmf.20.2016.06.30.07.58.00 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Thu, 30 Jun 2016 07:58:01 -0700 (PDT) From: Daniel Thompson To: Thomas Gleixner , Jason Cooper , Russell King , Marc Zyngier Cc: Daniel Thompson , Will Deacon , Catalin Marinas , Stephen Boyd , John Stultz , Steven Rostedt , linux-kernel@vger.kernel.org, linux-arm-kernel@lists.infradead.org, patches@linaro.org, linaro-kernel@lists.linaro.org, Sumit Semwal , Dirk Behme , Daniel Drake , Dmitry Pervushin , Tim Sander , Petr Mladek , Lucas Stach Subject: [PATCH 4.7-rc3 v23 1/4] irqchip: gic: Optimize locking in gic_raise_softirq Date: Thu, 30 Jun 2016 15:57:41 +0100 Message-Id: <1467298664-24039-2-git-send-email-daniel.thompson@linaro.org> X-Mailer: git-send-email 2.5.5 In-Reply-To: <1467298664-24039-1-git-send-email-daniel.thompson@linaro.org> References: <1436188438-9478-1-git-send-email-daniel.thompson@linaro.org> <1467298664-24039-1-git-send-email-daniel.thompson@linaro.org> Currently gic_raise_softirq() is locked using irq_controller_lock. This lock is primarily used to make register read-modify-write sequences atomic but gic_raise_softirq() uses it instead to ensure that the big.LITTLE migration logic can figure out when it is safe to migrate interrupts between physical cores. This is sub-optimal in closely related ways: 1. No locking at all is required on systems where the b.L switcher is not configured. 2. Finer grain locking can be used on systems where the b.L switcher is present. This patch resolves both of the above by introducing a separate finer grain lock and providing conditionally compiled inlines to lock/unlock it. Signed-off-by: Daniel Thompson Cc: Thomas Gleixner Cc: Jason Cooper Cc: Russell King Acked-by: Nicolas Pitre Acked-by: Marc Zyngier --- drivers/irqchip/irq-gic.c | 36 +++++++++++++++++++++++++++++++++--- 1 file changed, 33 insertions(+), 3 deletions(-) -- 2.5.5 diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index fbc4ae2afd29..2c14eb047359 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -94,6 +94,27 @@ struct gic_chip_data { static DEFINE_RAW_SPINLOCK(irq_controller_lock); /* + * This lock is used by the big.LITTLE migration code to ensure no IPIs + * can be pended on the old core after the map has been updated. + */ +#ifdef CONFIG_BL_SWITCHER +static DEFINE_RAW_SPINLOCK(cpu_map_migration_lock); + +static inline void gic_migration_lock(unsigned long *flags) +{ + raw_spin_lock_irqsave(&cpu_map_migration_lock, *flags); +} + +static inline void gic_migration_unlock(unsigned long flags) +{ + raw_spin_unlock_irqrestore(&cpu_map_migration_lock, flags); +} +#else +static inline void gic_migration_lock(unsigned long *flags) {} +static inline void gic_migration_unlock(unsigned long flags) {} +#endif + +/* * The GIC mapping of CPU interfaces does not necessarily match * the logical CPU numbering. Let's use a mapping as returned * by the GIC itself. @@ -769,7 +790,7 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq) int cpu; unsigned long flags, map = 0; - raw_spin_lock_irqsave(&irq_controller_lock, flags); + gic_migration_lock(&flags); /* Convert our logical CPU mask into a physical one. */ for_each_cpu(cpu, mask) @@ -784,7 +805,7 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq) /* this always happens on GIC0 */ writel_relaxed(map << 16 | irq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT); - raw_spin_unlock_irqrestore(&irq_controller_lock, flags); + gic_migration_unlock(flags); } #endif @@ -854,8 +875,17 @@ void gic_migrate_target(unsigned int new_cpu_id) raw_spin_lock(&irq_controller_lock); - /* Update the target interface for this logical CPU */ + /* + * Update the target interface for this logical CPU + * + * From the point we release the cpu_map_migration_lock any new + * SGIs will be pended on the new cpu which makes the set of SGIs + * pending on the old cpu static. That means we can defer the + * migration until after we have released the irq_controller_lock. + */ + raw_spin_lock(&cpu_map_migration_lock); gic_cpu_map[cpu] = 1 << new_cpu_id; + raw_spin_unlock(&cpu_map_migration_lock); /* * Find all the peripheral interrupts targetting the current