X-Git-Url: https://git.karo-electronics.de/?a=blobdiff_plain;f=kernel%2Fcpuset.c;h=c02d677c541c68067f76f0053864ed176ba39ccc;hb=be179ea691b396cc044c5e0cf640896cb97ed416;hp=fdf1759bdca5725c952187d28d2e083b42a59cea;hpb=ed8c2241c1ae1b64e4a783ae7a2c685c93142a8d;p=karo-tx-linux.git

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index fdf1759bdca5..c02d677c541c 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -474,7 +474,8 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 
 	/* On legacy hiearchy, we must be a subset of our parent cpuset. */
 	ret = -EACCES;
-	if (!cgroup_on_dfl(cur->css.cgroup) && !is_cpuset_subset(trial, par))
+	if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
+	    !is_cpuset_subset(trial, par))
 		goto out;
 
 	/*
@@ -498,7 +499,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 	 * be changed to have empty cpus_allowed or mems_allowed.
 	 */
 	ret = -ENOSPC;
-	if ((cgroup_has_tasks(cur->css.cgroup) || cur->attach_in_progress)) {
+	if ((cgroup_is_populated(cur->css.cgroup) || cur->attach_in_progress)) {
 		if (!cpumask_empty(cur->cpus_allowed) &&
 		    cpumask_empty(trial->cpus_allowed))
 			goto out;
@@ -549,9 +550,6 @@ static void update_domain_attr_tree(struct sched_domain_attr *dattr,
 
 	rcu_read_lock();
 	cpuset_for_each_descendant_pre(cp, pos_css, root_cs) {
-		if (cp == root_cs)
-			continue;
-
 		/* skip the whole subtree if @cp doesn't have any CPU */
 		if (cpumask_empty(cp->cpus_allowed)) {
 			pos_css = css_rightmost_descendant(pos_css);
@@ -626,6 +624,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
 	int csn;		/* how many cpuset ptrs in csa so far */
 	int i, j, k;		/* indices for partition finding loops */
 	cpumask_var_t *doms;	/* resulting partition; i.e. sched domains */
+	cpumask_var_t non_isolated_cpus;  /* load balanced CPUs */
 	struct sched_domain_attr *dattr;  /* attributes for custom domains */
 	int ndoms = 0;		/* number of sched domains in result */
 	int nslot;		/* next empty doms[] struct cpumask slot */
@@ -635,6 +634,10 @@ static int generate_sched_domains(cpumask_var_t **domains,
 	dattr = NULL;
 	csa = NULL;
 
+	if (!alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL))
+		goto done;
+	cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
+
 	/* Special case for the 99% of systems with one, full, sched domain */
 	if (is_sched_load_balance(&top_cpuset)) {
 		ndoms = 1;
@@ -647,7 +650,8 @@ static int generate_sched_domains(cpumask_var_t **domains,
 			*dattr = SD_ATTR_INIT;
 			update_domain_attr_tree(dattr, &top_cpuset);
 		}
-		cpumask_copy(doms[0], top_cpuset.effective_cpus);
+		cpumask_and(doms[0], top_cpuset.effective_cpus,
+				     non_isolated_cpus);
 
 		goto done;
 	}
@@ -670,7 +674,8 @@ static int generate_sched_domains(cpumask_var_t **domains,
 		 * the corresponding sched domain.
 		 */
 		if (!cpumask_empty(cp->cpus_allowed) &&
-		    !is_sched_load_balance(cp))
+		    !(is_sched_load_balance(cp) &&
+		      cpumask_intersects(cp->cpus_allowed, non_isolated_cpus)))
 			continue;
 
 		if (is_sched_load_balance(cp))
@@ -752,6 +757,7 @@ restart:
 
 			if (apn == b->pn) {
 				cpumask_or(dp, dp, b->effective_cpus);
+				cpumask_and(dp, dp, non_isolated_cpus);
 				if (dattr)
 					update_domain_attr_tree(dattr + nslot, b);
 
@@ -764,6 +770,7 @@ restart:
 	BUG_ON(nslot != ndoms);
 
 done:
+	free_cpumask_var(non_isolated_cpus);
 	kfree(csa);
 
 	/*
@@ -874,7 +881,8 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
 		 * If it becomes empty, inherit the effective mask of the
 		 * parent, which is guaranteed to have some CPUs.
 		 */
-		if (cpumask_empty(new_cpus))
+		if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
+		    cpumask_empty(new_cpus))
 			cpumask_copy(new_cpus, parent->effective_cpus);
 
 		/* Skip the whole subtree if the cpumask remains the same. */
@@ -891,7 +899,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
 		cpumask_copy(cp->effective_cpus, new_cpus);
 		spin_unlock_irq(&callback_lock);
 
-		WARN_ON(!cgroup_on_dfl(cp->css.cgroup) &&
+		WARN_ON(!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
 			!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
 
 		update_tasks_cpumask(cp);
@@ -1130,7 +1138,8 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
 		 * If it becomes empty, inherit the effective mask of the
 		 * parent, which is guaranteed to have some MEMs.
 		 */
-		if (nodes_empty(*new_mems))
+		if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
+		    nodes_empty(*new_mems))
 			*new_mems = parent->effective_mems;
 
 		/* Skip the whole subtree if the nodemask remains the same. */
@@ -1147,7 +1156,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
 		cp->effective_mems = *new_mems;
 		spin_unlock_irq(&callback_lock);
 
-		WARN_ON(!cgroup_on_dfl(cp->css.cgroup) &&
+		WARN_ON(!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
 			!nodes_equal(cp->mems_allowed, cp->effective_mems));
 
 		update_tasks_nodemask(cp);
@@ -1218,7 +1227,7 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
 	spin_unlock_irq(&callback_lock);
 
 	/* use trialcs->mems_allowed as a temp variable */
-	update_nodemasks_hier(cs, &cs->mems_allowed);
+	update_nodemasks_hier(cs, &trialcs->mems_allowed);
 done:
 	return retval;
 }
@@ -1438,7 +1447,7 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css,
 
 	/* allow moving tasks into an empty cpuset if on default hierarchy */
 	ret = -ENOSPC;
-	if (!cgroup_on_dfl(css->cgroup) &&
+	if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
 	    (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)))
 		goto out_unlock;
 
@@ -1482,9 +1491,8 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
 {
 	/* static buf protected by cpuset_mutex */
 	static nodemask_t cpuset_attach_nodemask_to;
-	struct mm_struct *mm;
 	struct task_struct *task;
-	struct task_struct *leader = cgroup_taskset_first(tset);
+	struct task_struct *leader;
 	struct cpuset *cs = css_cs(css);
 	struct cpuset *oldcs = cpuset_attach_old_cs;
 
@@ -1510,26 +1518,30 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
 	}
 
 	/*
-	 * Change mm, possibly for multiple threads in a threadgroup. This is
-	 * expensive and may sleep.
+	 * Change mm for all threadgroup leaders. This is expensive and may
+	 * sleep and should be moved outside migration path proper.
 	 */
 	cpuset_attach_nodemask_to = cs->effective_mems;
-	mm = get_task_mm(leader);
-	if (mm) {
-		mpol_rebind_mm(mm, &cpuset_attach_nodemask_to);
-
-		/*
-		 * old_mems_allowed is the same with mems_allowed here, except
-		 * if this task is being moved automatically due to hotplug.
-		 * In that case @mems_allowed has been updated and is empty,
-		 * so @old_mems_allowed is the right nodesets that we migrate
-		 * mm from.
-		 */
-		if (is_memory_migrate(cs)) {
-			cpuset_migrate_mm(mm, &oldcs->old_mems_allowed,
-					  &cpuset_attach_nodemask_to);
+	cgroup_taskset_for_each_leader(leader, tset) {
+		struct mm_struct *mm = get_task_mm(leader);
+
+		if (mm) {
+			mpol_rebind_mm(mm, &cpuset_attach_nodemask_to);
+
+			/*
+			 * old_mems_allowed is the same with mems_allowed
+			 * here, except if this task is being moved
+			 * automatically due to hotplug.  In that case
+			 * @mems_allowed has been updated and is empty, so
+			 * @old_mems_allowed is the right nodesets that we
+			 * migrate mm from.
+			 */
+			if (is_memory_migrate(cs)) {
+				cpuset_migrate_mm(mm, &oldcs->old_mems_allowed,
+						  &cpuset_attach_nodemask_to);
+			}
+			mmput(mm);
 		}
-		mmput(mm);
 	}
 
 	cs->old_mems_allowed = cpuset_attach_nodemask_to;
@@ -1592,9 +1604,6 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
 	case FILE_MEMORY_PRESSURE_ENABLED:
 		cpuset_memory_pressure_enabled = !!val;
 		break;
-	case FILE_MEMORY_PRESSURE:
-		retval = -EACCES;
-		break;
 	case FILE_SPREAD_PAGE:
 		retval = update_flag(CS_SPREAD_PAGE, cs, val);
 		break;
@@ -1711,40 +1720,27 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
 {
 	struct cpuset *cs = css_cs(seq_css(sf));
 	cpuset_filetype_t type = seq_cft(sf)->private;
-	ssize_t count;
-	char *buf, *s;
 	int ret = 0;
 
-	count = seq_get_buf(sf, &buf);
-	s = buf;
-
 	spin_lock_irq(&callback_lock);
 
 	switch (type) {
 	case FILE_CPULIST:
-		s += cpulist_scnprintf(s, count, cs->cpus_allowed);
+		seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->cpus_allowed));
 		break;
 	case FILE_MEMLIST:
-		s += nodelist_scnprintf(s, count, cs->mems_allowed);
+		seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->mems_allowed));
 		break;
 	case FILE_EFFECTIVE_CPULIST:
-		s += cpulist_scnprintf(s, count, cs->effective_cpus);
+		seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->effective_cpus));
 		break;
 	case FILE_EFFECTIVE_MEMLIST:
-		s += nodelist_scnprintf(s, count, cs->effective_mems);
+		seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->effective_mems));
 		break;
 	default:
 		ret = -EINVAL;
-		goto out_unlock;
 	}
 
-	if (s < buf + count - 1) {
-		*s++ = '\n';
-		seq_commit(sf, s - buf);
-	} else {
-		seq_commit(sf, -1);
-	}
-out_unlock:
 	spin_unlock_irq(&callback_lock);
 	return ret;
 }
@@ -1874,9 +1870,6 @@ static struct cftype files[] = {
 	{
 		.name = "memory_pressure",
 		.read_u64 = cpuset_read_u64,
-		.write_u64 = cpuset_write_u64,
-		.private = FILE_MEMORY_PRESSURE,
-		.mode = S_IRUGO,
 	},
 
 	{
@@ -1963,7 +1956,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 	cpuset_inc();
 
 	spin_lock_irq(&callback_lock);
-	if (cgroup_on_dfl(cs->css.cgroup)) {
+	if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) {
 		cpumask_copy(cs->effective_cpus, parent->effective_cpus);
 		cs->effective_mems = parent->effective_mems;
 	}
@@ -1996,7 +1989,9 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 
 	spin_lock_irq(&callback_lock);
 	cs->mems_allowed = parent->mems_allowed;
+	cs->effective_mems = parent->mems_allowed;
 	cpumask_copy(cs->cpus_allowed, parent->cpus_allowed);
+	cpumask_copy(cs->effective_cpus, parent->cpus_allowed);
 	spin_unlock_irq(&callback_lock);
 out_unlock:
 	mutex_unlock(&cpuset_mutex);
@@ -2038,7 +2033,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css)
 	mutex_lock(&cpuset_mutex);
 	spin_lock_irq(&callback_lock);
 
-	if (cgroup_on_dfl(root_css->cgroup)) {
+	if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) {
 		cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask);
 		top_cpuset.mems_allowed = node_possible_map;
 	} else {
@@ -2219,7 +2214,7 @@ retry:
 	cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus);
 	mems_updated = !nodes_equal(new_mems, cs->effective_mems);
 
-	if (cgroup_on_dfl(cs->css.cgroup))
+	if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys))
 		hotplug_update_tasks(cs, &new_cpus, &new_mems,
 				     cpus_updated, mems_updated);
 	else
@@ -2250,7 +2245,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 	static cpumask_t new_cpus;
 	static nodemask_t new_mems;
 	bool cpus_updated, mems_updated;
-	bool on_dfl = cgroup_on_dfl(top_cpuset.css.cgroup);
+	bool on_dfl = cgroup_subsys_on_dfl(cpuset_cgrp_subsys);
 
 	mutex_lock(&cpuset_mutex);
 
@@ -2404,7 +2399,7 @@ void cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 	 */
 }
 
-void cpuset_init_current_mems_allowed(void)
+void __init cpuset_init_current_mems_allowed(void)
 {
 	nodes_setall(current->mems_allowed);
 }
@@ -2462,20 +2457,12 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs)
  * @node: is this an allowed node?
  * @gfp_mask: memory allocation flags
  *
- * If we're in interrupt, yes, we can always allocate.  If __GFP_THISNODE is
- * set, yes, we can always allocate.  If node is in our task's mems_allowed,
- * yes.  If it's not a __GFP_HARDWALL request and this node is in the nearest
- * hardwalled cpuset ancestor to this task's cpuset, yes.  If the task has been
- * OOM killed and has access to memory reserves as specified by the TIF_MEMDIE
- * flag, yes.
+ * If we're in interrupt, yes, we can always allocate.  If @node is set in
+ * current's mems_allowed, yes.  If it's not a __GFP_HARDWALL request and this
+ * node is set in the nearest hardwalled cpuset ancestor to current's cpuset,
+ * yes.  If current has access to memory reserves due to TIF_MEMDIE, yes.
  * Otherwise, no.
  *
- * The __GFP_THISNODE placement logic is really handled elsewhere,
- * by forcibly using a zonelist starting at a specified node, and by
- * (in get_page_from_freelist()) refusing to consider the zones for
- * any node on the zonelist except the first.  By the time any such
- * calls get to this routine, we should just shut up and say 'yes'.
- *
  * GFP_USER allocations are marked with the __GFP_HARDWALL bit,
  * and do not allow allocations outside the current tasks cpuset
  * unless the task has been OOM killed as is marked TIF_MEMDIE.
@@ -2511,7 +2498,7 @@ int __cpuset_node_allowed(int node, gfp_t gfp_mask)
 	int allowed;			/* is allocation in zone z allowed? */
 	unsigned long flags;
 
-	if (in_interrupt() || (gfp_mask & __GFP_THISNODE))
+	if (in_interrupt())
 		return 1;
 	if (node_isset(node, current->mems_allowed))
 		return 1;
@@ -2614,8 +2601,6 @@ int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
 	return nodes_intersects(tsk1->mems_allowed, tsk2->mems_allowed);
 }
 
-#define CPUSET_NODELIST_LEN	(256)
-
 /**
  * cpuset_print_task_mems_allowed - prints task's cpuset and mems_allowed
  * @tsk: pointer to task_struct of some task.
@@ -2625,23 +2610,16 @@ int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
  */
 void cpuset_print_task_mems_allowed(struct task_struct *tsk)
 {
-	 /* Statically allocated to prevent using excess stack. */
-	static char cpuset_nodelist[CPUSET_NODELIST_LEN];
-	static DEFINE_SPINLOCK(cpuset_buffer_lock);
 	struct cgroup *cgrp;
 
-	spin_lock(&cpuset_buffer_lock);
 	rcu_read_lock();
 
 	cgrp = task_cs(tsk)->css.cgroup;
-	nodelist_scnprintf(cpuset_nodelist, CPUSET_NODELIST_LEN,
-			   tsk->mems_allowed);
 	pr_info("%s cpuset=", tsk->comm);
 	pr_cont_cgroup_name(cgrp);
-	pr_cont(" mems_allowed=%s\n", cpuset_nodelist);
+	pr_cont(" mems_allowed=%*pbl\n", nodemask_pr_args(&tsk->mems_allowed));
 
 	rcu_read_unlock();
-	spin_unlock(&cpuset_buffer_lock);
 }
 
 /*
@@ -2719,10 +2697,8 @@ out:
 /* Display task mems_allowed in /proc/<pid>/status file. */
 void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task)
 {
-	seq_puts(m, "Mems_allowed:\t");
-	seq_nodemask(m, &task->mems_allowed);
-	seq_puts(m, "\n");
-	seq_puts(m, "Mems_allowed_list:\t");
-	seq_nodemask_list(m, &task->mems_allowed);
-	seq_puts(m, "\n");
+	seq_printf(m, "Mems_allowed:\t%*pb\n",
+		   nodemask_pr_args(&task->mems_allowed));
+	seq_printf(m, "Mems_allowed_list:\t%*pbl\n",
+		   nodemask_pr_args(&task->mems_allowed));
 }