X-Git-Url: http://pilppa.org/gitweb/gitweb.cgi?a=blobdiff_plain;f=kernel%2Fcpuset.c;h=1b32c2c04c153a056047134a28ed5f172eeb1f80;hb=6c5c934153513dc72e2d6464f39e8ef1f27c0a3e;hp=c232dc0774389378c9fc8130ac84fb4067835f43;hpb=0d10e47f9635ecafe5a9dc6e10cb056a87a4daa2;p=linux-2.6-omap-h63xx.git

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index c232dc07743..1b32c2c04c1 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -289,7 +289,6 @@ static struct inode *cpuset_new_inode(mode_t mode)
 		inode->i_mode = mode;
 		inode->i_uid = current->fsuid;
 		inode->i_gid = current->fsgid;
-		inode->i_blksize = PAGE_CACHE_SIZE;
 		inode->i_blocks = 0;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		inode->i_mapping->backing_dev_info = &cpuset_backing_dev_info;
@@ -762,6 +761,8 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial)
  *
  * Call with manage_mutex held.  May nest a call to the
  * lock_cpu_hotplug()/unlock_cpu_hotplug() pair.
+ * Must not be called holding callback_mutex, because we must
+ * not call lock_cpu_hotplug() while holding callback_mutex.
  */
 
 static void update_cpu_domains(struct cpuset *cur)
@@ -781,7 +782,7 @@ static void update_cpu_domains(struct cpuset *cur)
 		if (is_cpu_exclusive(c))
 			cpus_andnot(pspan, pspan, c->cpus_allowed);
 	}
-	if (is_removed(cur) || !is_cpu_exclusive(cur)) {
+	if (!is_cpu_exclusive(cur)) {
 		cpus_or(pspan, pspan, cur->cpus_allowed);
 		if (cpus_equal(pspan, cur->cpus_allowed))
 			return;
@@ -814,6 +815,10 @@ static int update_cpumask(struct cpuset *cs, char *buf)
 	struct cpuset trialcs;
 	int retval, cpus_unchanged;
 
+	/* top_cpuset.cpus_allowed tracks cpu_online_map; it's read-only */
+	if (cs == &top_cpuset)
+		return -EACCES;
+
 	trialcs = *cs;
 	retval = cpulist_parse(buf, trialcs.cpus_allowed);
 	if (retval < 0)
@@ -1917,6 +1922,17 @@ static int cpuset_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 	return cpuset_create(c_parent, dentry->d_name.name, mode | S_IFDIR);
 }
 
+/*
+ * Locking note on the strange update_flag() call below:
+ *
+ * If the cpuset being removed is marked cpu_exclusive, then simulate
+ * turning cpu_exclusive off, which will call update_cpu_domains().
+ * The lock_cpu_hotplug() call in update_cpu_domains() must not be
+ * made while holding callback_mutex.  Elsewhere the kernel nests
+ * callback_mutex inside lock_cpu_hotplug() calls.  So the reverse
+ * nesting would risk an ABBA deadlock.
+ */
+
 static int cpuset_rmdir(struct inode *unused_dir, struct dentry *dentry)
 {
 	struct cpuset *cs = dentry->d_fsdata;
@@ -1936,11 +1952,16 @@ static int cpuset_rmdir(struct inode *unused_dir, struct dentry *dentry)
 		mutex_unlock(&manage_mutex);
 		return -EBUSY;
 	}
+	if (is_cpu_exclusive(cs)) {
+		int retval = update_flag(CS_CPU_EXCLUSIVE, cs, "0");
+		if (retval < 0) {
+			mutex_unlock(&manage_mutex);
+			return retval;
+		}
+	}
 	parent = cs->parent;
 	mutex_lock(&callback_mutex);
 	set_bit(CS_REMOVED, &cs->flags);
-	if (is_cpu_exclusive(cs))
-		update_cpu_domains(cs);
 	list_del(&cs->sibling);	/* delete my sibling from parent->children */
 	spin_lock(&cs->dentry->d_lock);
 	d = dget(cs->dentry);
@@ -2015,6 +2036,33 @@ out:
 	return err;
 }
 
+/*
+ * The top_cpuset tracks what CPUs and Memory Nodes are online,
+ * period.  This is necessary in order to make cpusets transparent
+ * (of no affect) on systems that are actively using CPU hotplug
+ * but making no active use of cpusets.
+ *
+ * This handles CPU hotplug (cpuhp) events.  If someday Memory
+ * Nodes can be hotplugged (dynamically changing node_online_map)
+ * then we should handle that too, perhaps in a similar way.
+ */
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int cpuset_handle_cpuhp(struct notifier_block *nb,
+				unsigned long phase, void *cpu)
+{
+	mutex_lock(&manage_mutex);
+	mutex_lock(&callback_mutex);
+
+	top_cpuset.cpus_allowed = cpu_online_map;
+
+	mutex_unlock(&callback_mutex);
+	mutex_unlock(&manage_mutex);
+
+	return 0;
+}
+#endif
+
 /**
  * cpuset_init_smp - initialize cpus_allowed
  *
@@ -2025,6 +2073,8 @@ void __init cpuset_init_smp(void)
 {
 	top_cpuset.cpus_allowed = cpu_online_map;
 	top_cpuset.mems_allowed = node_online_map;
+
+	hotcpu_notifier(cpuset_handle_cpuhp, 0);
 }
 
 /**
@@ -2194,7 +2244,7 @@ int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl)
 	int i;
 
 	for (i = 0; zl->zones[i]; i++) {
-		int nid = zl->zones[i]->zone_pgdat->node_id;
+		int nid = zone_to_nid(zl->zones[i]);
 
 		if (node_isset(nid, current->mems_allowed))
 			return 1;
@@ -2265,9 +2315,9 @@ int __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
 	const struct cpuset *cs;	/* current cpuset ancestors */
 	int allowed;			/* is allocation in zone z allowed? */
 
-	if (in_interrupt())
+	if (in_interrupt() || (gfp_mask & __GFP_THISNODE))
 		return 1;
-	node = z->zone_pgdat->node_id;
+	node = zone_to_nid(z);
 	might_sleep_if(!(gfp_mask & __GFP_HARDWALL));
 	if (node_isset(node, current->mems_allowed))
 		return 1;
@@ -2369,7 +2419,7 @@ EXPORT_SYMBOL_GPL(cpuset_mem_spread_node);
 int cpuset_excl_nodes_overlap(const struct task_struct *p)
 {
 	const struct cpuset *cs1, *cs2;	/* my and p's cpuset ancestors */
-	int overlap = 0;		/* do cpusets overlap? */
+	int overlap = 1;		/* do cpusets overlap? */
 
 	task_lock(current);
 	if (current->flags & PF_EXITING) {