1 files changed, 100 insertions, 21 deletions

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 4ea6f0dc2fc..9d850ae13b1 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -240,7 +240,7 @@ static struct super_block *cpuset_sb;
  * A cpuset can only be deleted if both its 'count' of using tasks
  * is zero, and its list of 'children' cpusets is empty.  Since all
  * tasks in the system use _some_ cpuset, and since there is always at
- * least one task in the system (init, pid == 1), therefore, top_cpuset
+ * least one task in the system (init), therefore, top_cpuset
  * always has either children cpusets and/or using tasks.  So we don't
  * need a special hack to ensure that top_cpuset cannot be deleted.
  *
@@ -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;
@@ -378,7 +377,7 @@ static int cpuset_fill_super(struct super_block *sb, void *unused_data,
 		inode->i_op = &simple_dir_inode_operations;
 		inode->i_fop = &simple_dir_operations;
 		/* directories start off with i_nlink == 2 (for "." entry) */
-		inode->i_nlink++;
+		inc_nlink(inode);
 	} else {
 		return -ENOMEM;
 	}
@@ -913,6 +912,10 @@ static int update_nodemask(struct cpuset *cs, char *buf)
 	int fudge;
 	int retval;
 
+	/* top_cpuset.mems_allowed tracks node_online_map; it's read-only */
+	if (cs == &top_cpuset)
+		return -EACCES;
+
 	trialcs = *cs;
 	retval = nodelist_parse(buf, trialcs.mems_allowed);
 	if (retval < 0)
@@ -1222,7 +1225,12 @@ static int attach_task(struct cpuset *cs, char *pidbuf, char **ppathbuf)
 
 	task_lock(tsk);
 	oldcs = tsk->cpuset;
-	if (!oldcs) {
+	/*
+	 * After getting 'oldcs' cpuset ptr, be sure still not exiting.
+	 * If 'oldcs' might be the top_cpuset due to the_top_cpuset_hack
+	 * then fail this attach_task(), to avoid breaking top_cpuset.count.
+	 */
+	if (tsk->flags & PF_EXITING) {
 		task_unlock(tsk);
 		mutex_unlock(&callback_mutex);
 		put_task_struct(tsk);
@@ -1557,7 +1565,7 @@ static int cpuset_create_file(struct dentry *dentry, int mode)
 		inode->i_fop = &simple_dir_operations;
 
 		/* start off with i_nlink == 2 (for "." entry) */
-		inode->i_nlink++;
+		inc_nlink(inode);
 	} else if (S_ISREG(mode)) {
 		inode->i_size = 0;
 		inode->i_fop = &cpuset_file_operations;
@@ -1590,7 +1598,7 @@ static int cpuset_create_dir(struct cpuset *cs, const char *name, int mode)
 	error = cpuset_create_file(dentry, S_IFDIR | mode);
 	if (!error) {
 		dentry->d_fsdata = cs;
-		parent->d_inode->i_nlink++;
+		inc_nlink(parent->d_inode);
 		cs->dentry = dentry;
 	}
 	dput(dentry);
@@ -2025,7 +2033,7 @@ int __init cpuset_init(void)
 	}
 	root = cpuset_mount->mnt_sb->s_root;
 	root->d_fsdata = &top_cpuset;
-	root->d_inode->i_nlink++;
+	inc_nlink(root->d_inode);
 	top_cpuset.dentry = root;
 	root->d_inode->i_op = &cpuset_dir_inode_operations;
 	number_of_cpusets = 1;
@@ -2037,33 +2045,104 @@ out:
 	return err;
 }
 
+#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_MEMORY_HOTPLUG)
 /*
- * 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.
+ * If common_cpu_mem_hotplug_unplug(), below, unplugs any CPUs
+ * or memory nodes, we need to walk over the cpuset hierarchy,
+ * removing that CPU or node from all cpusets.  If this removes the
+ * last CPU or node from a cpuset, then the guarantee_online_cpus()
+ * or guarantee_online_mems() code will use that emptied cpusets
+ * parent online CPUs or nodes.  Cpusets that were already empty of
+ * CPUs or nodes are left empty.
+ *
+ * This routine is intentionally inefficient in a couple of regards.
+ * It will check all cpusets in a subtree even if the top cpuset of
+ * the subtree has no offline CPUs or nodes.  It checks both CPUs and
+ * nodes, even though the caller could have been coded to know that
+ * only one of CPUs or nodes needed to be checked on a given call.
+ * This was done to minimize text size rather than cpu cycles.
+ *
+ * Call with both manage_mutex and callback_mutex held.
+ *
+ * Recursive, on depth of cpuset subtree.
  */
 
-#ifdef CONFIG_HOTPLUG_CPU
-static int cpuset_handle_cpuhp(struct notifier_block *nb,
-				unsigned long phase, void *cpu)
+static void guarantee_online_cpus_mems_in_subtree(const struct cpuset *cur)
+{
+	struct cpuset *c;
+
+	/* Each of our child cpusets mems must be online */
+	list_for_each_entry(c, &cur->children, sibling) {
+		guarantee_online_cpus_mems_in_subtree(c);
+		if (!cpus_empty(c->cpus_allowed))
+			guarantee_online_cpus(c, &c->cpus_allowed);
+		if (!nodes_empty(c->mems_allowed))
+			guarantee_online_mems(c, &c->mems_allowed);
+	}
+}
+
+/*
+ * The cpus_allowed and mems_allowed nodemasks in the top_cpuset track
+ * cpu_online_map and node_online_map.  Force the top cpuset to track
+ * whats online after any CPU or memory node hotplug or unplug event.
+ *
+ * To ensure that we don't remove a CPU or node from the top cpuset
+ * that is currently in use by a child cpuset (which would violate
+ * the rule that cpusets must be subsets of their parent), we first
+ * call the recursive routine guarantee_online_cpus_mems_in_subtree().
+ *
+ * Since there are two callers of this routine, one for CPU hotplug
+ * events and one for memory node hotplug events, we could have coded
+ * two separate routines here.  We code it as a single common routine
+ * in order to minimize text size.
+ */
+
+static void common_cpu_mem_hotplug_unplug(void)
 {
 	mutex_lock(&manage_mutex);
 	mutex_lock(&callback_mutex);
 
+	guarantee_online_cpus_mems_in_subtree(&top_cpuset);
 	top_cpuset.cpus_allowed = cpu_online_map;
+	top_cpuset.mems_allowed = node_online_map;
 
 	mutex_unlock(&callback_mutex);
 	mutex_unlock(&manage_mutex);
+}
+#endif
+
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * 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 routine ensures that top_cpuset.cpus_allowed tracks
+ * cpu_online_map on each CPU hotplug (cpuhp) event.
+ */
 
+static int cpuset_handle_cpuhp(struct notifier_block *nb,
+				unsigned long phase, void *cpu)
+{
+	common_cpu_mem_hotplug_unplug();
 	return 0;
 }
 #endif
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+/*
+ * Keep top_cpuset.mems_allowed tracking node_online_map.
+ * Call this routine anytime after you change node_online_map.
+ * See also the previous routine cpuset_handle_cpuhp().
+ */
+
+void cpuset_track_online_nodes()
+{
+	common_cpu_mem_hotplug_unplug();
+}
+#endif
+
 /**
  * cpuset_init_smp - initialize cpus_allowed
  *
@@ -2245,7 +2324,7 @@ 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;
@@ -2316,9 +2395,9 @@ 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;