Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757428Ab2B2E46 (ORCPT ); Tue, 28 Feb 2012 23:56:58 -0500 Received: from mga03.intel.com ([143.182.124.21]:8275 "EHLO mga03.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756186Ab2B2E44 convert rfc822-to-8bit (ORCPT ); Tue, 28 Feb 2012 23:56:56 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.71,315,1320652800"; d="scan'208";a="71652283" From: "Liu, ShuoX" To: "linux-kernel@vger.kernel.org" CC: "Brown, Len" , "Yanmin_zhang@linux.intel.com" Subject: Subject: [PATCH] cpuidle: Add a sysfs entry to disable specific C state for debug purpose. Thread-Topic: Subject: [PATCH] cpuidle: Add a sysfs entry to disable specific C state for debug purpose. Thread-Index: Acz2nmNC30IlWH8hTJu9v281exLbng== Date: Wed, 29 Feb 2012 04:55:52 +0000 Message-ID: Accept-Language: zh-CN, en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [10.239.127.40] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 8BIT MIME-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5624 Lines: 156 From: ShuoX Liu Some C states of new CPU might be not good. One reason is BIOS might configure them incorrectly. To help developers root cause it quickly, the patch adds a new sysfs entry, so developers could disable specific C state manually. In addition, C state might have much impact on performance tuning, as it takes much time to enter/exit C states, which might delay interrupt processing. With the new debug option, developers could check if a deep C state could impact performance and how much impact it could cause. Signed-off-by: ShuoX Liu --- drivers/cpuidle/cpuidle.c | 1 + drivers/cpuidle/governors/menu.c | 5 ++++- drivers/cpuidle/sysfs.c | 34 ++++++++++++++++++++++++++++++++++ include/linux/cpuidle.h | 1 + 4 files changed, 40 insertions(+), 1 deletions(-) diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 59f4261..7d66d3e 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -197,6 +197,7 @@ static void poll_idle_init(struct cpuidle_driver *drv) state->power_usage = -1; state->flags = 0; state->enter = poll_idle; + state->disable = 0; } #else static void poll_idle_init(struct cpuidle_driver *drv) {} diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index ad09526..5c17ca1 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -280,7 +280,8 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) * We want to default to C1 (hlt), not to busy polling * unless the timer is happening really really soon. */ - if (data->expected_us > 5) + if (data->expected_us > 5 && + drv->states[CPUIDLE_DRIVER_STATE_START].disable == 0) data->last_state_idx = CPUIDLE_DRIVER_STATE_START; /* @@ -290,6 +291,8 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) { struct cpuidle_state *s = &drv->states[i]; + if (s->disable) + continue; if (s->target_residency > data->predicted_us) continue; if (s->exit_latency > latency_req) diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c index 3fe41fe..1eae29a 100644 --- a/drivers/cpuidle/sysfs.c +++ b/drivers/cpuidle/sysfs.c @@ -222,6 +222,9 @@ struct cpuidle_state_attr { #define define_one_state_ro(_name, show) \ static struct cpuidle_state_attr attr_##_name = __ATTR(_name, 0444, show, NULL) +#define define_one_state_rw(_name, show, store) \ +static struct cpuidle_state_attr attr_##_name = __ATTR(_name, 0644, show, store) + #define define_show_state_function(_name) \ static ssize_t show_state_##_name(struct cpuidle_state *state, \ struct cpuidle_state_usage *state_usage, char *buf) \ @@ -229,6 +232,19 @@ static ssize_t show_state_##_name(struct cpuidle_state *state, \ return sprintf(buf, "%u\n", state->_name);\ } +#define define_store_state_function(_name) \ +static ssize_t store_state_##_name(struct cpuidle_state *state, \ + const char *buf, size_t size) \ +{ \ + int value; \ + sscanf(buf, "%d", &value); \ + if (value) \ + state->disable = 1; \ + else \ + state->disable = 0; \ + return size; \ +} + #define define_show_state_ull_function(_name) \ static ssize_t show_state_##_name(struct cpuidle_state *state, \ struct cpuidle_state_usage *state_usage, char *buf) \ @@ -251,6 +267,8 @@ define_show_state_ull_function(usage) define_show_state_ull_function(time) define_show_state_str_function(name) define_show_state_str_function(desc) +define_show_state_function(disable) +define_store_state_function(disable) define_one_state_ro(name, show_state_name); define_one_state_ro(desc, show_state_desc); @@ -258,6 +276,7 @@ define_one_state_ro(latency, show_state_exit_latency); define_one_state_ro(power, show_state_power_usage); define_one_state_ro(usage, show_state_usage); define_one_state_ro(time, show_state_time); +define_one_state_rw(disable, show_state_disable, store_state_disable); static struct attribute *cpuidle_state_default_attrs[] = { &attr_name.attr, @@ -266,6 +285,7 @@ static struct attribute *cpuidle_state_default_attrs[] = { &attr_power.attr, &attr_usage.attr, &attr_time.attr, + &attr_disable.attr, NULL }; @@ -287,8 +307,22 @@ static ssize_t cpuidle_state_show(struct kobject * kobj, return ret; } +static ssize_t cpuidle_state_store(struct kobject *kobj, + struct attribute *attr, const char *buf, size_t size) +{ + int ret = -EIO; + struct cpuidle_state *state = kobj_to_state(kobj); + struct cpuidle_state_attr *cattr = attr_to_stateattr(attr); + + if (cattr->store) + ret = cattr->store(state, buf, size); + + return ret; +} + static const struct sysfs_ops cpuidle_state_sysfs_ops = { .show = cpuidle_state_show, + .store = cpuidle_state_store, }; static void cpuidle_state_sysfs_release(struct kobject *kobj) diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 712abcc..eb150a5 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -45,6 +45,7 @@ struct cpuidle_state { unsigned int exit_latency; /* in US */ unsigned int power_usage; /* in mW */ unsigned int target_residency; /* in US */ + unsigned int disable; int (*enter) (struct cpuidle_device *dev, struct cpuidle_driver *drv, -- 1.7.1 -- 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/