X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;ds=sidebyside;f=kernel%2Fcpuset.c;h=9fceb97e989c25c82e438010437804774b892025;hb=3a57a788757738b8f80a82d4f5101fefb8fd7a58;hp=fe5407ca2f1ebd90cde99a2620c2d9d5b68fde1e;hpb=addf2c739d9015d3e9c0500b58a3af051cd58ea7;p=linux-2.6

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index fe5407ca2f..9fceb97e98 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -127,6 +127,7 @@ struct cpuset_hotplug_scanner {
 typedef enum {
 	CS_CPU_EXCLUSIVE,
 	CS_MEM_EXCLUSIVE,
+	CS_MEM_HARDWALL,
 	CS_MEMORY_MIGRATE,
 	CS_SCHED_LOAD_BALANCE,
 	CS_SPREAD_PAGE,
@@ -144,6 +145,11 @@ static inline int is_mem_exclusive(const struct cpuset *cs)
 	return test_bit(CS_MEM_EXCLUSIVE, &cs->flags);
 }
 
+static inline int is_mem_hardwall(const struct cpuset *cs)
+{
+	return test_bit(CS_MEM_HARDWALL, &cs->flags);
+}
+
 static inline int is_sched_load_balance(const struct cpuset *cs)
 {
 	return test_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
@@ -791,8 +797,10 @@ static int update_cpumask(struct cpuset *cs, char *buf)
 		retval = cpulist_parse(buf, trialcs.cpus_allowed);
 		if (retval < 0)
 			return retval;
+
+		if (!cpus_subset(trialcs.cpus_allowed, cpu_online_map))
+			return -EINVAL;
 	}
-	cpus_and(trialcs.cpus_allowed, trialcs.cpus_allowed, cpu_online_map);
 	retval = validate_change(cs, &trialcs);
 	if (retval < 0)
 		return retval;
@@ -926,9 +934,11 @@ static int update_nodemask(struct cpuset *cs, char *buf)
 		retval = nodelist_parse(buf, trialcs.mems_allowed);
 		if (retval < 0)
 			goto done;
+
+		if (!nodes_subset(trialcs.mems_allowed,
+				node_states[N_HIGH_MEMORY]))
+			return -EINVAL;
 	}
-	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 */
@@ -1025,12 +1035,10 @@ int current_cpuset_is_being_rebound(void)
 	return task_cs(current) == cpuset_being_rebound;
 }
 
-static int update_relax_domain_level(struct cpuset *cs, char *buf)
+static int update_relax_domain_level(struct cpuset *cs, s64 val)
 {
-	int val = simple_strtol(buf, NULL, 10);
-
-	if (val < 0)
-		val = -1;
+	if (val < -1 || val >= SD_LV_MAX)
+		return -EINVAL;
 
 	if (val != cs->relax_domain_level) {
 		cs->relax_domain_level = val;
@@ -1042,12 +1050,9 @@ static int update_relax_domain_level(struct cpuset *cs, char *buf)
 
 /*
  * update_flag - read a 0 or a 1 in a file and update associated flag
- * bit:	the bit to update (CS_CPU_EXCLUSIVE, CS_MEM_EXCLUSIVE,
- *				CS_SCHED_LOAD_BALANCE,
- *				CS_NOTIFY_ON_RELEASE, CS_MEMORY_MIGRATE,
- *				CS_SPREAD_PAGE, CS_SPREAD_SLAB)
- * cs:	the cpuset to update
- * buf:	the buffer where we read the 0 or 1
+ * bit:		the bit to update (see cpuset_flagbits_t)
+ * cs:		the cpuset to update
+ * turning_on: 	whether the flag is being set or cleared
  *
  * Call with cgroup_mutex held.
  */
@@ -1228,6 +1233,7 @@ typedef enum {
 	FILE_MEMLIST,
 	FILE_CPU_EXCLUSIVE,
 	FILE_MEM_EXCLUSIVE,
+	FILE_MEM_HARDWALL,
 	FILE_SCHED_LOAD_BALANCE,
 	FILE_SCHED_RELAX_DOMAIN_LEVEL,
 	FILE_MEMORY_PRESSURE_ENABLED,
@@ -1276,9 +1282,6 @@ static ssize_t cpuset_common_file_write(struct cgroup *cont,
 	case FILE_MEMLIST:
 		retval = update_nodemask(cs, buffer);
 		break;
-	case FILE_SCHED_RELAX_DOMAIN_LEVEL:
-		retval = update_relax_domain_level(cs, buffer);
-		break;
 	default:
 		retval = -EINVAL;
 		goto out2;
@@ -1313,6 +1316,9 @@ static int cpuset_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
 	case FILE_MEM_EXCLUSIVE:
 		retval = update_flag(CS_MEM_EXCLUSIVE, cs, val);
 		break;
+	case FILE_MEM_HARDWALL:
+		retval = update_flag(CS_MEM_HARDWALL, cs, val);
+		break;
 	case FILE_SCHED_LOAD_BALANCE:
 		retval = update_flag(CS_SCHED_LOAD_BALANCE, cs, val);
 		break;
@@ -1341,6 +1347,30 @@ static int cpuset_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
 	return retval;
 }
 
+static int cpuset_write_s64(struct cgroup *cgrp, struct cftype *cft, s64 val)
+{
+	int retval = 0;
+	struct cpuset *cs = cgroup_cs(cgrp);
+	cpuset_filetype_t type = cft->private;
+
+	cgroup_lock();
+
+	if (cgroup_is_removed(cgrp)) {
+		cgroup_unlock();
+		return -ENODEV;
+	}
+	switch (type) {
+	case FILE_SCHED_RELAX_DOMAIN_LEVEL:
+		retval = update_relax_domain_level(cs, val);
+		break;
+	default:
+		retval = -EINVAL;
+		break;
+	}
+	cgroup_unlock();
+	return retval;
+}
+
 /*
  * These ascii lists should be read in a single call, by using a user
  * buffer large enough to hold the entire map.  If read in smaller
@@ -1399,9 +1429,6 @@ static ssize_t cpuset_common_file_read(struct cgroup *cont,
 	case FILE_MEMLIST:
 		s += cpuset_sprintf_memlist(s, cs);
 		break;
-	case FILE_SCHED_RELAX_DOMAIN_LEVEL:
-		s += sprintf(s, "%d", cs->relax_domain_level);
-		break;
 	default:
 		retval = -EINVAL;
 		goto out;
@@ -1423,6 +1450,8 @@ static u64 cpuset_read_u64(struct cgroup *cont, struct cftype *cft)
 		return is_cpu_exclusive(cs);
 	case FILE_MEM_EXCLUSIVE:
 		return is_mem_exclusive(cs);
+	case FILE_MEM_HARDWALL:
+		return is_mem_hardwall(cs);
 	case FILE_SCHED_LOAD_BALANCE:
 		return is_sched_load_balance(cs);
 	case FILE_MEMORY_MIGRATE:
@@ -1440,6 +1469,18 @@ static u64 cpuset_read_u64(struct cgroup *cont, struct cftype *cft)
 	}
 }
 
+static s64 cpuset_read_s64(struct cgroup *cont, struct cftype *cft)
+{
+	struct cpuset *cs = cgroup_cs(cont);
+	cpuset_filetype_t type = cft->private;
+	switch (type) {
+	case FILE_SCHED_RELAX_DOMAIN_LEVEL:
+		return cs->relax_domain_level;
+	default:
+		BUG();
+	}
+}
+
 
 /*
  * for the common functions, 'private' gives the type of file
@@ -1474,6 +1515,13 @@ static struct cftype files[] = {
 		.private = FILE_MEM_EXCLUSIVE,
 	},
 
+	{
+		.name = "mem_hardwall",
+		.read_u64 = cpuset_read_u64,
+		.write_u64 = cpuset_write_u64,
+		.private = FILE_MEM_HARDWALL,
+	},
+
 	{
 		.name = "sched_load_balance",
 		.read_u64 = cpuset_read_u64,
@@ -1483,8 +1531,8 @@ static struct cftype files[] = {
 
 	{
 		.name = "sched_relax_domain_level",
-		.read_u64 = cpuset_read_u64,
-		.write_u64 = cpuset_write_u64,
+		.read_s64 = cpuset_read_s64,
+		.write_s64 = cpuset_write_s64,
 		.private = FILE_SCHED_RELAX_DOMAIN_LEVEL,
 	},
 
@@ -1842,6 +1890,12 @@ static void common_cpu_mem_hotplug_unplug(void)
 	top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
 	scan_for_empty_cpusets(&top_cpuset);
 
+	/*
+	 * Scheduler destroys domains on hotplug events.
+	 * Rebuild them based on the current settings.
+	 */
+	rebuild_sched_domains();
+
 	cgroup_unlock();
 }
 
@@ -1963,14 +2017,14 @@ int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask)
 }
 
 /*
- * nearest_exclusive_ancestor() - Returns the nearest mem_exclusive
- * ancestor to the specified cpuset.  Call holding callback_mutex.
- * If no ancestor is mem_exclusive (an unusual configuration), then
- * returns the root cpuset.
+ * nearest_hardwall_ancestor() - Returns the nearest mem_exclusive or
+ * mem_hardwall ancestor to the specified cpuset.  Call holding
+ * callback_mutex.  If no ancestor is mem_exclusive or mem_hardwall
+ * (an unusual configuration), then returns the root cpuset.
  */
-static const struct cpuset *nearest_exclusive_ancestor(const struct cpuset *cs)
+static const struct cpuset *nearest_hardwall_ancestor(const struct cpuset *cs)
 {
-	while (!is_mem_exclusive(cs) && cs->parent)
+	while (!(is_mem_exclusive(cs) || is_mem_hardwall(cs)) && cs->parent)
 		cs = cs->parent;
 	return cs;
 }
@@ -1984,7 +2038,7 @@ static const struct cpuset *nearest_exclusive_ancestor(const struct cpuset *cs)
  * __GFP_THISNODE is set, yes, we can always allocate.  If zone
  * z's node is in our tasks mems_allowed, yes.  If it's not a
  * __GFP_HARDWALL request and this zone's nodes is in the nearest
- * mem_exclusive cpuset ancestor to this tasks cpuset, yes.
+ * hardwalled cpuset ancestor to this tasks cpuset, yes.
  * If the task has been OOM killed and has access to memory reserves
  * as specified by the TIF_MEMDIE flag, yes.
  * Otherwise, no.
@@ -2007,7 +2061,7 @@ static const struct cpuset *nearest_exclusive_ancestor(const struct cpuset *cs)
  * and do not allow allocations outside the current tasks cpuset
  * unless the task has been OOM killed as is marked TIF_MEMDIE.
  * GFP_KERNEL allocations are not so marked, so can escape to the
- * nearest enclosing mem_exclusive ancestor cpuset.
+ * nearest enclosing hardwalled ancestor cpuset.
  *
  * Scanning up parent cpusets requires callback_mutex.  The
  * __alloc_pages() routine only calls here with __GFP_HARDWALL bit
@@ -2030,7 +2084,7 @@ static const struct cpuset *nearest_exclusive_ancestor(const struct cpuset *cs)
  *	in_interrupt - any node ok (current task context irrelevant)
  *	GFP_ATOMIC   - any node ok
  *	TIF_MEMDIE   - any node ok
- *	GFP_KERNEL   - any node in enclosing mem_exclusive cpuset ok
+ *	GFP_KERNEL   - any node in enclosing hardwalled cpuset ok
  *	GFP_USER     - only nodes in current tasks mems allowed ok.
  *
  * Rule:
@@ -2067,7 +2121,7 @@ int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
 	mutex_lock(&callback_mutex);
 
 	task_lock(current);
-	cs = nearest_exclusive_ancestor(task_cs(current));
+	cs = nearest_hardwall_ancestor(task_cs(current));
 	task_unlock(current);
 
 	allowed = node_isset(node, cs->mems_allowed);