Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758628AbYFBIgD (ORCPT ); Mon, 2 Jun 2008 04:36:03 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753893AbYFBIf0 (ORCPT ); Mon, 2 Jun 2008 04:35:26 -0400 Received: from cn.fujitsu.com ([222.73.24.84]:62631 "EHLO song.cn.fujitsu.com" rhost-flags-OK-FAIL-OK-OK) by vger.kernel.org with ESMTP id S1752130AbYFBIfX (ORCPT ); Mon, 2 Jun 2008 04:35:23 -0400 Message-ID: <4843AFC9.7000100@cn.fujitsu.com> Date: Mon, 02 Jun 2008 16:31:05 +0800 From: Miao Xie Reply-To: miaox@cn.fujitsu.com User-Agent: Thunderbird 2.0.0.6 (Windows/20070728) MIME-Version: 1.0 To: Andrew Morton , Linux-Kernel CC: Paul Jackson , Paul Menage Subject: [PATCH 1/2] cpusets: restructure the function update_cpumask() and update_nodemask() 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: 8005 Lines: 269 extract two functions from update_cpumask() and update_nodemask().They will be used later for updating tasks' cpus_allowed and mems_allowed after CPU/NODE offline/online. Signed-off-by: Miao Xie Acked-by: Paul Jackson --- kernel/cpuset.c | 179 +++++++++++++++++++++++++++++++++---------------------- 1 files changed, 108 insertions(+), 71 deletions(-) diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 86ea9e3..dc16f71 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -766,6 +766,37 @@ static void cpuset_change_cpumask(struct task_struct *tsk, } /** + * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset. + * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed + * + * Called with cgroup_mutex held + * + * The cgroup_scan_tasks() function will scan all the tasks in a cgroup, + * calling callback functions for each. + * + * Return 0 if successful, -errno if not. + */ +static int update_tasks_cpumask(struct cpuset *cs) +{ + struct cgroup_scanner scan; + struct ptr_heap heap; + int retval; + + retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, &started_after); + if (retval) + return retval; + + scan.cg = cs->css.cgroup; + scan.test_task = cpuset_test_cpumask; + scan.process_task = cpuset_change_cpumask; + scan.heap = &heap; + retval = cgroup_scan_tasks(&scan); + + heap_free(&heap); + return retval; +} + +/** * update_cpumask - update the cpus_allowed mask of a cpuset and all tasks in it * @cs: the cpuset to consider * @buf: buffer of cpu numbers written to this cpuset @@ -773,8 +804,6 @@ static void cpuset_change_cpumask(struct task_struct *tsk, static int update_cpumask(struct cpuset *cs, char *buf) { struct cpuset trialcs; - struct cgroup_scanner scan; - struct ptr_heap heap; int retval; int is_load_balanced; @@ -807,10 +836,6 @@ static int update_cpumask(struct cpuset *cs, char *buf) if (cpus_equal(cs->cpus_allowed, trialcs.cpus_allowed)) return 0; - retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, &started_after); - if (retval) - return retval; - is_load_balanced = is_sched_load_balance(&trialcs); mutex_lock(&callback_mutex); @@ -821,12 +846,9 @@ static int update_cpumask(struct cpuset *cs, char *buf) * Scan tasks in the cpuset, and update the cpumasks of any * that need an update. */ - scan.cg = cs->css.cgroup; - scan.test_task = cpuset_test_cpumask; - scan.process_task = cpuset_change_cpumask; - scan.heap = &heap; - cgroup_scan_tasks(&scan); - heap_free(&heap); + retval = update_tasks_cpumask(cs); + if (retval < 0) + return retval; if (is_load_balanced) rebuild_sched_domains(); @@ -882,72 +904,25 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, mutex_unlock(&callback_mutex); } -/* - * Handle user request to change the 'mems' memory placement - * of a cpuset. Needs to validate the request, update the - * cpusets mems_allowed and mems_generation, and for each - * task in the cpuset, rebind any vma mempolicies and if - * the cpuset is marked 'memory_migrate', migrate the tasks - * pages to the new memory. - * - * Call with cgroup_mutex held. May take callback_mutex during call. - * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, - * lock each such tasks mm->mmap_sem, scan its vma's and rebind - * their mempolicies to the cpusets new mems_allowed. - */ - static void *cpuset_being_rebound; -static int update_nodemask(struct cpuset *cs, char *buf) +/** + * update_tasks_nodemask - Update the nodemasks of tasks in the cpuset. + * @cs: the cpuset in which each task's mems_allowed mask needs to be changed + * @oldmem: old mems_allowed of cpuset cs + * + * Called with cgroup_mutex held + * Return 0 if successful, -errno if not. + */ +static int update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem) { - struct cpuset trialcs; - nodemask_t oldmem; struct task_struct *p; struct mm_struct **mmarray; int i, n, ntasks; int migrate; int fudge; - int retval; struct cgroup_iter it; - - /* - * top_cpuset.mems_allowed tracks node_stats[N_HIGH_MEMORY]; - * it's read-only - */ - if (cs == &top_cpuset) - return -EACCES; - - trialcs = *cs; - - /* - * An empty mems_allowed is ok iff there are no tasks in the cpuset. - * Since nodelist_parse() fails on an empty mask, we special case - * that parsing. The validate_change() call ensures that cpusets - * with tasks have memory. - */ - buf = strstrip(buf); - if (!*buf) { - nodes_clear(trialcs.mems_allowed); - } else { - retval = nodelist_parse(buf, trialcs.mems_allowed); - if (retval < 0) - goto done; - } - nodes_and(trialcs.mems_allowed, trialcs.mems_allowed, - node_states[N_HIGH_MEMORY]); - oldmem = cs->mems_allowed; - if (nodes_equal(oldmem, trialcs.mems_allowed)) { - retval = 0; /* Too easy - nothing to do */ - goto done; - } - retval = validate_change(cs, &trialcs); - if (retval < 0) - goto done; - - mutex_lock(&callback_mutex); - cs->mems_allowed = trialcs.mems_allowed; - cs->mems_generation = cpuset_mems_generation++; - mutex_unlock(&callback_mutex); + int retval; cpuset_being_rebound = cs; /* causes mpol_dup() rebind */ @@ -1014,7 +989,7 @@ static int update_nodemask(struct cpuset *cs, char *buf) mpol_rebind_mm(mm, &cs->mems_allowed); if (migrate) - cpuset_migrate_mm(mm, &oldmem, &cs->mems_allowed); + cpuset_migrate_mm(mm, oldmem, &cs->mems_allowed); mmput(mm); } @@ -1026,6 +1001,69 @@ done: return retval; } +/* + * Handle user request to change the 'mems' memory placement + * of a cpuset. Needs to validate the request, update the + * cpusets mems_allowed and mems_generation, and for each + * task in the cpuset, rebind any vma mempolicies and if + * the cpuset is marked 'memory_migrate', migrate the tasks + * pages to the new memory. + * + * Call with cgroup_mutex held. May take callback_mutex during call. + * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, + * lock each such tasks mm->mmap_sem, scan its vma's and rebind + * their mempolicies to the cpusets new mems_allowed. + */ +static int update_nodemask(struct cpuset *cs, char *buf) +{ + struct cpuset trialcs; + nodemask_t oldmem; + int retval; + + /* + * top_cpuset.mems_allowed tracks node_stats[N_HIGH_MEMORY]; + * it's read-only + */ + if (cs == &top_cpuset) + return -EACCES; + + trialcs = *cs; + + /* + * An empty mems_allowed is ok iff there are no tasks in the cpuset. + * Since nodelist_parse() fails on an empty mask, we special case + * that parsing. The validate_change() call ensures that cpusets + * with tasks have memory. + */ + buf = strstrip(buf); + if (!*buf) { + nodes_clear(trialcs.mems_allowed); + } else { + retval = nodelist_parse(buf, trialcs.mems_allowed); + if (retval < 0) + goto done; + } + nodes_and(trialcs.mems_allowed, trialcs.mems_allowed, + node_states[N_HIGH_MEMORY]); + oldmem = cs->mems_allowed; + if (nodes_equal(oldmem, trialcs.mems_allowed)) { + retval = 0; /* Too easy - nothing to do */ + goto done; + } + retval = validate_change(cs, &trialcs); + if (retval < 0) + goto done; + + mutex_lock(&callback_mutex); + cs->mems_allowed = trialcs.mems_allowed; + cs->mems_generation = cpuset_mems_generation++; + mutex_unlock(&callback_mutex); + + retval = update_tasks_nodemask(cs, &oldmem); +done: + return retval; +} + int current_cpuset_is_being_rebound(void) { return task_cs(current) == cpuset_being_rebound; @@ -1938,7 +1976,6 @@ void __init cpuset_init_smp(void) } /** - * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset. * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed. * @pmask: pointer to cpumask_t variable to receive cpus_allowed set. -- 1.5.4.rc3 -- 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/