Merge branch 'for-3.16' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup
Pull cgroup updates from Tejun Heo:
"A lot of activities on cgroup side. Heavy restructuring including
locking simplification took place to improve the code base and enable
implementation of the unified hierarchy, which currently exists behind
a __DEVEL__ mount option. The core support is mostly complete but
individual controllers need further work. To explain the design and
rationales of the the unified hierarchy
Documentation/cgroups/unified-hierarchy.txt
is added.
Another notable change is css (cgroup_subsys_state - what each
controller uses to identify and interact with a cgroup) iteration
update. This is part of continuing updates on css object lifetime and
visibility. cgroup started with reference count draining on removal
way back and is now reaching a point where csses behave and are
iterated like normal refcnted objects albeit with some complexities to
allow distinguishing the state where they're being deleted. The css
iteration update isn't taken advantage of yet but is planned to be
used to simplify memcg significantly"
* 'for-3.16' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (77 commits)
cgroup: disallow disabled controllers on the default hierarchy
cgroup: don't destroy the default root
cgroup: disallow debug controller on the default hierarchy
cgroup: clean up MAINTAINERS entries
cgroup: implement css_tryget()
device_cgroup: use css_has_online_children() instead of has_children()
cgroup: convert cgroup_has_live_children() into css_has_online_children()
cgroup: use CSS_ONLINE instead of CGRP_DEAD
cgroup: iterate cgroup_subsys_states directly
cgroup: introduce CSS_RELEASED and reduce css iteration fallback window
cgroup: move cgroup->serial_nr into cgroup_subsys_state
cgroup: link all cgroup_subsys_states in their sibling lists
cgroup: move cgroup->sibling and ->children into cgroup_subsys_state
cgroup: remove cgroup->parent
device_cgroup: remove direct access to cgroup->children
memcg: update memcg_has_children() to use css_next_child()
memcg: remove tasks/children test from mem_cgroup_force_empty()
cgroup: remove css_parent()
cgroup: skip refcnting on normal root csses and cgrp_dfl_root self css
cgroup: use cgroup->self.refcnt for cgroup refcnting
...
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a9559b9..a2c7bcb 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -526,18 +526,14 @@
static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
{
- /*
- * The ID of the root cgroup is 0, but memcg treat 0 as an
- * invalid ID, so we return (cgroup_id + 1).
- */
- return memcg->css.cgroup->id + 1;
+ return memcg->css.id;
}
static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
{
struct cgroup_subsys_state *css;
- css = css_from_id(id - 1, &memory_cgrp_subsys);
+ css = css_from_id(id, &memory_cgrp_subsys);
return mem_cgroup_from_css(css);
}
@@ -570,7 +566,8 @@
memcg = mem_cgroup_from_task(current);
cg_proto = sk->sk_prot->proto_cgroup(memcg);
if (!mem_cgroup_is_root(memcg) &&
- memcg_proto_active(cg_proto) && css_tryget(&memcg->css)) {
+ memcg_proto_active(cg_proto) &&
+ css_tryget_online(&memcg->css)) {
sk->sk_cgrp = cg_proto;
}
rcu_read_unlock();
@@ -831,7 +828,7 @@
*/
__mem_cgroup_remove_exceeded(mz, mctz);
if (!res_counter_soft_limit_excess(&mz->memcg->res) ||
- !css_tryget(&mz->memcg->css))
+ !css_tryget_online(&mz->memcg->css))
goto retry;
done:
return mz;
@@ -1073,7 +1070,7 @@
if (unlikely(!memcg))
memcg = root_mem_cgroup;
}
- } while (!css_tryget(&memcg->css));
+ } while (!css_tryget_online(&memcg->css));
rcu_read_unlock();
return memcg;
}
@@ -1110,7 +1107,8 @@
*/
if (next_css) {
if ((next_css == &root->css) ||
- ((next_css->flags & CSS_ONLINE) && css_tryget(next_css)))
+ ((next_css->flags & CSS_ONLINE) &&
+ css_tryget_online(next_css)))
return mem_cgroup_from_css(next_css);
prev_css = next_css;
@@ -1156,7 +1154,7 @@
* would be returned all the time.
*/
if (position && position != root &&
- !css_tryget(&position->css))
+ !css_tryget_online(&position->css))
position = NULL;
}
return position;
@@ -1533,7 +1531,7 @@
int mem_cgroup_swappiness(struct mem_cgroup *memcg)
{
/* root ? */
- if (mem_cgroup_disabled() || !css_parent(&memcg->css))
+ if (mem_cgroup_disabled() || !memcg->css.parent)
return vm_swappiness;
return memcg->swappiness;
@@ -2769,9 +2767,9 @@
/*
* A helper function to get mem_cgroup from ID. must be called under
- * rcu_read_lock(). The caller is responsible for calling css_tryget if
- * the mem_cgroup is used for charging. (dropping refcnt from swap can be
- * called against removed memcg.)
+ * rcu_read_lock(). The caller is responsible for calling
+ * css_tryget_online() if the mem_cgroup is used for charging. (dropping
+ * refcnt from swap can be called against removed memcg.)
*/
static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
{
@@ -2794,14 +2792,14 @@
lock_page_cgroup(pc);
if (PageCgroupUsed(pc)) {
memcg = pc->mem_cgroup;
- if (memcg && !css_tryget(&memcg->css))
+ if (memcg && !css_tryget_online(&memcg->css))
memcg = NULL;
} else if (PageSwapCache(page)) {
ent.val = page_private(page);
id = lookup_swap_cgroup_id(ent);
rcu_read_lock();
memcg = mem_cgroup_lookup(id);
- if (memcg && !css_tryget(&memcg->css))
+ if (memcg && !css_tryget_online(&memcg->css))
memcg = NULL;
rcu_read_unlock();
}
@@ -3365,7 +3363,7 @@
}
/* The corresponding put will be done in the workqueue. */
- if (!css_tryget(&memcg->css))
+ if (!css_tryget_online(&memcg->css))
goto out;
rcu_read_unlock();
@@ -4125,8 +4123,8 @@
memcg = mem_cgroup_lookup(id);
if (memcg) {
/*
- * We uncharge this because swap is freed.
- * This memcg can be obsolete one. We avoid calling css_tryget
+ * We uncharge this because swap is freed. This memcg can
+ * be obsolete one. We avoid calling css_tryget_online().
*/
if (!mem_cgroup_is_root(memcg))
res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
@@ -4711,18 +4709,28 @@
} while (usage > 0);
}
+/*
+ * Test whether @memcg has children, dead or alive. Note that this
+ * function doesn't care whether @memcg has use_hierarchy enabled and
+ * returns %true if there are child csses according to the cgroup
+ * hierarchy. Testing use_hierarchy is the caller's responsiblity.
+ */
static inline bool memcg_has_children(struct mem_cgroup *memcg)
{
- lockdep_assert_held(&memcg_create_mutex);
+ bool ret;
+
/*
- * The lock does not prevent addition or deletion to the list
- * of children, but it prevents a new child from being
- * initialized based on this parent in css_online(), so it's
- * enough to decide whether hierarchically inherited
- * attributes can still be changed or not.
+ * The lock does not prevent addition or deletion of children, but
+ * it prevents a new child from being initialized based on this
+ * parent in css_online(), so it's enough to decide whether
+ * hierarchically inherited attributes can still be changed or not.
*/
- return memcg->use_hierarchy &&
- !list_empty(&memcg->css.cgroup->children);
+ lockdep_assert_held(&memcg_create_mutex);
+
+ rcu_read_lock();
+ ret = css_next_child(NULL, &memcg->css);
+ rcu_read_unlock();
+ return ret;
}
/*
@@ -4734,11 +4742,6 @@
static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
{
int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
- struct cgroup *cgrp = memcg->css.cgroup;
-
- /* returns EBUSY if there is a task or if we come here twice. */
- if (cgroup_has_tasks(cgrp) || !list_empty(&cgrp->children))
- return -EBUSY;
/* we call try-to-free pages for make this cgroup empty */
lru_add_drain_all();
@@ -4758,20 +4761,19 @@
}
}
- lru_add_drain();
- mem_cgroup_reparent_charges(memcg);
return 0;
}
-static int mem_cgroup_force_empty_write(struct cgroup_subsys_state *css,
- unsigned int event)
+static ssize_t mem_cgroup_force_empty_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes,
+ loff_t off)
{
- struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
if (mem_cgroup_is_root(memcg))
return -EINVAL;
- return mem_cgroup_force_empty(memcg);
+ return mem_cgroup_force_empty(memcg) ?: nbytes;
}
static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css,
@@ -4785,7 +4787,7 @@
{
int retval = 0;
struct mem_cgroup *memcg = mem_cgroup_from_css(css);
- struct mem_cgroup *parent_memcg = mem_cgroup_from_css(css_parent(&memcg->css));
+ struct mem_cgroup *parent_memcg = mem_cgroup_from_css(memcg->css.parent);
mutex_lock(&memcg_create_mutex);
@@ -4802,7 +4804,7 @@
*/
if ((!parent_memcg || !parent_memcg->use_hierarchy) &&
(val == 1 || val == 0)) {
- if (list_empty(&memcg->css.cgroup->children))
+ if (!memcg_has_children(memcg))
memcg->use_hierarchy = val;
else
retval = -EBUSY;
@@ -4919,7 +4921,8 @@
* of course permitted.
*/
mutex_lock(&memcg_create_mutex);
- if (cgroup_has_tasks(memcg->css.cgroup) || memcg_has_children(memcg))
+ if (cgroup_has_tasks(memcg->css.cgroup) ||
+ (memcg->use_hierarchy && memcg_has_children(memcg)))
err = -EBUSY;
mutex_unlock(&memcg_create_mutex);
if (err)
@@ -5021,17 +5024,18 @@
* The user of this function is...
* RES_LIMIT.
*/
-static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft,
- char *buffer)
+static ssize_t mem_cgroup_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes, loff_t off)
{
- struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
enum res_type type;
int name;
unsigned long long val;
int ret;
- type = MEMFILE_TYPE(cft->private);
- name = MEMFILE_ATTR(cft->private);
+ buf = strstrip(buf);
+ type = MEMFILE_TYPE(of_cft(of)->private);
+ name = MEMFILE_ATTR(of_cft(of)->private);
switch (name) {
case RES_LIMIT:
@@ -5040,7 +5044,7 @@
break;
}
/* This function does all necessary parse...reuse it */
- ret = res_counter_memparse_write_strategy(buffer, &val);
+ ret = res_counter_memparse_write_strategy(buf, &val);
if (ret)
break;
if (type == _MEM)
@@ -5053,7 +5057,7 @@
return -EINVAL;
break;
case RES_SOFT_LIMIT:
- ret = res_counter_memparse_write_strategy(buffer, &val);
+ ret = res_counter_memparse_write_strategy(buf, &val);
if (ret)
break;
/*
@@ -5070,7 +5074,7 @@
ret = -EINVAL; /* should be BUG() ? */
break;
}
- return ret;
+ return ret ?: nbytes;
}
static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg,
@@ -5083,8 +5087,8 @@
if (!memcg->use_hierarchy)
goto out;
- while (css_parent(&memcg->css)) {
- memcg = mem_cgroup_from_css(css_parent(&memcg->css));
+ while (memcg->css.parent) {
+ memcg = mem_cgroup_from_css(memcg->css.parent);
if (!memcg->use_hierarchy)
break;
tmp = res_counter_read_u64(&memcg->res, RES_LIMIT);
@@ -5097,14 +5101,15 @@
*memsw_limit = min_memsw_limit;
}
-static int mem_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event)
+static ssize_t mem_cgroup_reset(struct kernfs_open_file *of, char *buf,
+ size_t nbytes, loff_t off)
{
- struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
int name;
enum res_type type;
- type = MEMFILE_TYPE(event);
- name = MEMFILE_ATTR(event);
+ type = MEMFILE_TYPE(of_cft(of)->private);
+ name = MEMFILE_ATTR(of_cft(of)->private);
switch (name) {
case RES_MAX_USAGE:
@@ -5129,7 +5134,7 @@
break;
}
- return 0;
+ return nbytes;
}
static u64 mem_cgroup_move_charge_read(struct cgroup_subsys_state *css,
@@ -5322,7 +5327,7 @@
if (val > 100)
return -EINVAL;
- if (css_parent(css))
+ if (css->parent)
memcg->swappiness = val;
else
vm_swappiness = val;
@@ -5659,7 +5664,7 @@
struct mem_cgroup *memcg = mem_cgroup_from_css(css);
/* cannot set to root cgroup and only 0 and 1 are allowed */
- if (!css_parent(css) || !((val == 0) || (val == 1)))
+ if (!css->parent || !((val == 0) || (val == 1)))
return -EINVAL;
memcg->oom_kill_disable = val;
@@ -5705,10 +5710,10 @@
* which is then paired with css_put during uncharge resp. here.
*
* Although this might sound strange as this path is called from
- * css_offline() when the referencemight have dropped down to 0
- * and shouldn't be incremented anymore (css_tryget would fail)
- * we do not have other options because of the kmem allocations
- * lifetime.
+ * css_offline() when the referencemight have dropped down to 0 and
+ * shouldn't be incremented anymore (css_tryget_online() would
+ * fail) we do not have other options because of the kmem
+ * allocations lifetime.
*/
css_get(&memcg->css);
@@ -5827,9 +5832,10 @@
* Input must be in format '<event_fd> <control_fd> <args>'.
* Interpretation of args is defined by control file implementation.
*/
-static int memcg_write_event_control(struct cgroup_subsys_state *css,
- struct cftype *cft, char *buffer)
+static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
+ char *buf, size_t nbytes, loff_t off)
{
+ struct cgroup_subsys_state *css = of_css(of);
struct mem_cgroup *memcg = mem_cgroup_from_css(css);
struct mem_cgroup_event *event;
struct cgroup_subsys_state *cfile_css;
@@ -5840,15 +5846,17 @@
char *endp;
int ret;
- efd = simple_strtoul(buffer, &endp, 10);
+ buf = strstrip(buf);
+
+ efd = simple_strtoul(buf, &endp, 10);
if (*endp != ' ')
return -EINVAL;
- buffer = endp + 1;
+ buf = endp + 1;
- cfd = simple_strtoul(buffer, &endp, 10);
+ cfd = simple_strtoul(buf, &endp, 10);
if ((*endp != ' ') && (*endp != '\0'))
return -EINVAL;
- buffer = endp + 1;
+ buf = endp + 1;
event = kzalloc(sizeof(*event), GFP_KERNEL);
if (!event)
@@ -5916,8 +5924,8 @@
* automatically removed on cgroup destruction but the removal is
* asynchronous, so take an extra ref on @css.
*/
- cfile_css = css_tryget_from_dir(cfile.file->f_dentry->d_parent,
- &memory_cgrp_subsys);
+ cfile_css = css_tryget_online_from_dir(cfile.file->f_dentry->d_parent,
+ &memory_cgrp_subsys);
ret = -EINVAL;
if (IS_ERR(cfile_css))
goto out_put_cfile;
@@ -5926,7 +5934,7 @@
goto out_put_cfile;
}
- ret = event->register_event(memcg, event->eventfd, buffer);
+ ret = event->register_event(memcg, event->eventfd, buf);
if (ret)
goto out_put_css;
@@ -5939,7 +5947,7 @@
fdput(cfile);
fdput(efile);
- return 0;
+ return nbytes;
out_put_css:
css_put(css);
@@ -5964,25 +5972,25 @@
{
.name = "max_usage_in_bytes",
.private = MEMFILE_PRIVATE(_MEM, RES_MAX_USAGE),
- .trigger = mem_cgroup_reset,
+ .write = mem_cgroup_reset,
.read_u64 = mem_cgroup_read_u64,
},
{
.name = "limit_in_bytes",
.private = MEMFILE_PRIVATE(_MEM, RES_LIMIT),
- .write_string = mem_cgroup_write,
+ .write = mem_cgroup_write,
.read_u64 = mem_cgroup_read_u64,
},
{
.name = "soft_limit_in_bytes",
.private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT),
- .write_string = mem_cgroup_write,
+ .write = mem_cgroup_write,
.read_u64 = mem_cgroup_read_u64,
},
{
.name = "failcnt",
.private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT),
- .trigger = mem_cgroup_reset,
+ .write = mem_cgroup_reset,
.read_u64 = mem_cgroup_read_u64,
},
{
@@ -5991,7 +5999,7 @@
},
{
.name = "force_empty",
- .trigger = mem_cgroup_force_empty_write,
+ .write = mem_cgroup_force_empty_write,
},
{
.name = "use_hierarchy",
@@ -6001,7 +6009,7 @@
},
{
.name = "cgroup.event_control", /* XXX: for compat */
- .write_string = memcg_write_event_control,
+ .write = memcg_write_event_control,
.flags = CFTYPE_NO_PREFIX,
.mode = S_IWUGO,
},
@@ -6034,7 +6042,7 @@
{
.name = "kmem.limit_in_bytes",
.private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT),
- .write_string = mem_cgroup_write,
+ .write = mem_cgroup_write,
.read_u64 = mem_cgroup_read_u64,
},
{
@@ -6045,13 +6053,13 @@
{
.name = "kmem.failcnt",
.private = MEMFILE_PRIVATE(_KMEM, RES_FAILCNT),
- .trigger = mem_cgroup_reset,
+ .write = mem_cgroup_reset,
.read_u64 = mem_cgroup_read_u64,
},
{
.name = "kmem.max_usage_in_bytes",
.private = MEMFILE_PRIVATE(_KMEM, RES_MAX_USAGE),
- .trigger = mem_cgroup_reset,
+ .write = mem_cgroup_reset,
.read_u64 = mem_cgroup_read_u64,
},
#ifdef CONFIG_SLABINFO
@@ -6074,19 +6082,19 @@
{
.name = "memsw.max_usage_in_bytes",
.private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE),
- .trigger = mem_cgroup_reset,
+ .write = mem_cgroup_reset,
.read_u64 = mem_cgroup_read_u64,
},
{
.name = "memsw.limit_in_bytes",
.private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT),
- .write_string = mem_cgroup_write,
+ .write = mem_cgroup_write,
.read_u64 = mem_cgroup_read_u64,
},
{
.name = "memsw.failcnt",
.private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT),
- .trigger = mem_cgroup_reset,
+ .write = mem_cgroup_reset,
.read_u64 = mem_cgroup_read_u64,
},
{ }, /* terminate */
@@ -6264,9 +6272,9 @@
mem_cgroup_css_online(struct cgroup_subsys_state *css)
{
struct mem_cgroup *memcg = mem_cgroup_from_css(css);
- struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(css));
+ struct mem_cgroup *parent = mem_cgroup_from_css(css->parent);
- if (css->cgroup->id > MEM_CGROUP_ID_MAX)
+ if (css->id > MEM_CGROUP_ID_MAX)
return -ENOSPC;
if (!parent)
@@ -6361,7 +6369,7 @@
/*
* XXX: css_offline() would be where we should reparent all
* memory to prepare the cgroup for destruction. However,
- * memcg does not do css_tryget() and res_counter charging
+ * memcg does not do css_tryget_online() and res_counter charging
* under the same RCU lock region, which means that charging
* could race with offlining. Offlining only happens to
* cgroups with no tasks in them but charges can show up
@@ -6375,9 +6383,9 @@
* lookup_swap_cgroup_id()
* rcu_read_lock()
* mem_cgroup_lookup()
- * css_tryget()
+ * css_tryget_online()
* rcu_read_unlock()
- * disable css_tryget()
+ * disable css_tryget_online()
* call_rcu()
* offline_css()
* reparent_charges()