Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758482Ab0D3VgR (ORCPT ); Fri, 30 Apr 2010 17:36:17 -0400 Received: from mga11.intel.com ([192.55.52.93]:37354 "EHLO mga11.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754480Ab0D3VgP (ORCPT ); Fri, 30 Apr 2010 17:36:15 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.52,305,1270450800"; d="scan'208";a="563130431" From: Peter P Waskiewicz Jr Subject: [PATCH linux-next v4 1/2] irq: Add CPU mask affinity hint To: tglx@linutronix.de, davem@davemloft.net, arjan@linux.jf.intel.com, bhutchings@solarflare.com Cc: netdev@vger.kernel.org, linux-kernel@vger.kernel.org Date: Fri, 30 Apr 2010 14:44:50 -0700 Message-ID: <20100430214445.3992.41647.stgit@ppwaskie-hc2.jf.intel.com> User-Agent: StGIT/0.14.3 MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5620 Lines: 172 This patch adds a cpumask affinity hint to the irq_desc structure, along with a registration function and a read-only proc entry for each interrupt. This affinity_hint handle for each interrupt can be used by underlying drivers that need a better mechanism to control interrupt affinity. The underlying driver can register a cpumask for the interrupt, which will allow the driver to provide the CPU mask for the interrupt to anything that requests it. The intent is to extend the userspace daemon, irqbalance, to help hint to it a preferred CPU mask to balance the interrupt into. Signed-off-by: Peter P Waskiewicz Jr --- include/linux/interrupt.h | 6 ++++++ include/linux/irq.h | 1 + kernel/irq/manage.c | 19 +++++++++++++++++++ kernel/irq/proc.c | 39 +++++++++++++++++++++++++++++++++++++++ 4 files changed, 65 insertions(+), 0 deletions(-) diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 75f3f00..4ae3b2d 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -209,6 +209,7 @@ extern int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask); extern int irq_can_set_affinity(unsigned int irq); extern int irq_select_affinity(unsigned int irq); +extern int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m); #else /* CONFIG_SMP */ static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m) @@ -223,6 +224,11 @@ static inline int irq_can_set_affinity(unsigned int irq) static inline int irq_select_affinity(unsigned int irq) { return 0; } +static inline int irq_set_affinity_hint(unsigned int irq, + const struct cpumask *m) +{ + return -EINVAL; +} #endif /* CONFIG_SMP && CONFIG_GENERIC_HARDIRQS */ #ifdef CONFIG_GENERIC_HARDIRQS diff --git a/include/linux/irq.h b/include/linux/irq.h index 707ab12..83b16d7 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -206,6 +206,7 @@ struct irq_desc { struct proc_dir_entry *dir; #endif const char *name; + struct cpumask *affinity_hint; } ____cacheline_internodealigned_in_smp; extern void arch_init_copy_chip_data(struct irq_desc *old_desc, diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 704e488..1451c38 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -138,6 +138,22 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask) return 0; } +int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) +{ + struct irq_desc *desc = irq_to_desc(irq); + unsigned long flags; + + if (!desc) + return -EINVAL; + + raw_spin_lock_irqsave(&desc->lock, flags); + desc->affinity_hint = m; + raw_spin_unlock_irqrestore(&desc->lock, flags); + + return 0; +} +EXPORT_SYMBOL_GPL(irq_set_affinity_hint); + #ifndef CONFIG_AUTO_IRQ_AFFINITY /* * Generic version of the affinity autoselector. @@ -916,6 +932,9 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) desc->chip->disable(irq); } + /* make sure affinity_hint is cleaned up */ + desc->affinity_hint = NULL; + raw_spin_unlock_irqrestore(&desc->lock, flags); unregister_handler_proc(irq, action); diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 7a6eb04..e1e7408 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -32,6 +32,29 @@ static int irq_affinity_proc_show(struct seq_file *m, void *v) return 0; } +static int irq_affinity_hint_proc_show(struct seq_file *m, void *v) +{ + struct irq_desc *desc = irq_to_desc((long)m->private); + unsigned long flags; + cpumask_var_t mask; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + raw_spin_lock_irqsave(&desc->lock, flags); + if (desc->affinity_hint) + cpumask_copy(mask, desc->affinity_hint); + else + cpumask_setall(mask); + raw_spin_unlock_irqrestore(&desc->lock, flags); + + seq_cpumask(m, mask); + seq_putc(m, '\n'); + free_cpumask_var(mask); + + return 0; +} + #ifndef is_affinity_mask_valid #define is_affinity_mask_valid(val) 1 #endif @@ -84,6 +107,11 @@ static int irq_affinity_proc_open(struct inode *inode, struct file *file) return single_open(file, irq_affinity_proc_show, PDE(inode)->data); } +static int irq_affinity_hint_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, irq_affinity_hint_proc_show, PDE(inode)->data); +} + static const struct file_operations irq_affinity_proc_fops = { .open = irq_affinity_proc_open, .read = seq_read, @@ -92,6 +120,13 @@ static const struct file_operations irq_affinity_proc_fops = { .write = irq_affinity_proc_write, }; +static const struct file_operations irq_affinity_hint_proc_fops = { + .open = irq_affinity_hint_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + static int default_affinity_show(struct seq_file *m, void *v) { seq_cpumask(m, irq_default_affinity); @@ -231,6 +266,10 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc) /* create /proc/irq//smp_affinity */ proc_create_data("smp_affinity", 0600, desc->dir, &irq_affinity_proc_fops, (void *)(long)irq); + + /* create /proc/irq//affinity_hint */ + proc_create_data("affinity_hint", 0400, desc->dir, + &irq_affinity_hint_proc_fops, (void *)(long)irq); #endif proc_create_data("spurious", 0444, desc->dir, -- 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/