aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--block/blk-cgroup.c49
-rw-r--r--block/blk-cgroup.h38
-rw-r--r--block/blk-throttle.c43
-rw-r--r--block/cfq-iosched.c90
-rw-r--r--fs/bio.c2
-rw-r--r--include/linux/cgroup.h303
-rw-r--r--include/linux/memcontrol.h2
-rw-r--r--include/linux/vmpressure.h6
-rw-r--r--include/net/cls_cgroup.h4
-rw-r--r--include/net/netprio_cgroup.h8
-rw-r--r--kernel/cgroup.c1643
-rw-r--r--kernel/cgroup_freezer.c155
-rw-r--r--kernel/cpuset.c317
-rw-r--r--kernel/events/core.c27
-rw-r--r--kernel/sched/core.c113
-rw-r--r--kernel/sched/cpuacct.c51
-rw-r--r--kernel/sched/sched.h6
-rw-r--r--mm/hugetlb_cgroup.c69
-rw-r--r--mm/memcontrol.c223
-rw-r--r--mm/vmpressure.c25
-rw-r--r--net/core/netprio_cgroup.c72
-rw-r--r--net/ipv4/tcp_memcontrol.c12
-rw-r--r--net/sched/cls_cgroup.c39
-rw-r--r--security/device_cgroup.c65
24 files changed, 1751 insertions, 1611 deletions
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 290792a13e3..e90c7c164c8 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -437,10 +437,10 @@ struct request_list *__blk_queue_next_rl(struct request_list *rl,
return &blkg->rl;
}
-static int blkcg_reset_stats(struct cgroup *cgroup, struct cftype *cftype,
- u64 val)
+static int blkcg_reset_stats(struct cgroup_subsys_state *css,
+ struct cftype *cftype, u64 val)
{
- struct blkcg *blkcg = cgroup_to_blkcg(cgroup);
+ struct blkcg *blkcg = css_to_blkcg(css);
struct blkcg_gq *blkg;
int i;
@@ -614,15 +614,13 @@ u64 blkg_stat_recursive_sum(struct blkg_policy_data *pd, int off)
{
struct blkcg_policy *pol = blkcg_policy[pd->plid];
struct blkcg_gq *pos_blkg;
- struct cgroup *pos_cgrp;
- u64 sum;
+ struct cgroup_subsys_state *pos_css;
+ u64 sum = 0;
lockdep_assert_held(pd->blkg->q->queue_lock);
- sum = blkg_stat_read((void *)pd + off);
-
rcu_read_lock();
- blkg_for_each_descendant_pre(pos_blkg, pos_cgrp, pd_to_blkg(pd)) {
+ blkg_for_each_descendant_pre(pos_blkg, pos_css, pd_to_blkg(pd)) {
struct blkg_policy_data *pos_pd = blkg_to_pd(pos_blkg, pol);
struct blkg_stat *stat = (void *)pos_pd + off;
@@ -649,16 +647,14 @@ struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkg_policy_data *pd,
{
struct blkcg_policy *pol = blkcg_policy[pd->plid];
struct blkcg_gq *pos_blkg;
- struct cgroup *pos_cgrp;
- struct blkg_rwstat sum;
+ struct cgroup_subsys_state *pos_css;
+ struct blkg_rwstat sum = { };
int i;
lockdep_assert_held(pd->blkg->q->queue_lock);
- sum = blkg_rwstat_read((void *)pd + off);
-
rcu_read_lock();
- blkg_for_each_descendant_pre(pos_blkg, pos_cgrp, pd_to_blkg(pd)) {
+ blkg_for_each_descendant_pre(pos_blkg, pos_css, pd_to_blkg(pd)) {
struct blkg_policy_data *pos_pd = blkg_to_pd(pos_blkg, pol);
struct blkg_rwstat *rwstat = (void *)pos_pd + off;
struct blkg_rwstat tmp;
@@ -765,18 +761,18 @@ struct cftype blkcg_files[] = {
/**
* blkcg_css_offline - cgroup css_offline callback
- * @cgroup: cgroup of interest
+ * @css: css of interest
*
- * This function is called when @cgroup is about to go away and responsible
- * for shooting down all blkgs associated with @cgroup. blkgs should be
+ * This function is called when @css is about to go away and responsible
+ * for shooting down all blkgs associated with @css. blkgs should be
* removed while holding both q and blkcg locks. As blkcg lock is nested
* inside q lock, this function performs reverse double lock dancing.
*
* This is the blkcg counterpart of ioc_release_fn().
*/
-static void blkcg_css_offline(struct cgroup *cgroup)
+static void blkcg_css_offline(struct cgroup_subsys_state *css)
{
- struct blkcg *blkcg = cgroup_to_blkcg(cgroup);
+ struct blkcg *blkcg = css_to_blkcg(css);
spin_lock_irq(&blkcg->lock);
@@ -798,21 +794,21 @@ static void blkcg_css_offline(struct cgroup *cgroup)
spin_unlock_irq(&blkcg->lock);
}
-static void blkcg_css_free(struct cgroup *cgroup)
+static void blkcg_css_free(struct cgroup_subsys_state *css)
{
- struct blkcg *blkcg = cgroup_to_blkcg(cgroup);
+ struct blkcg *blkcg = css_to_blkcg(css);
if (blkcg != &blkcg_root)
kfree(blkcg);
}
-static struct cgroup_subsys_state *blkcg_css_alloc(struct cgroup *cgroup)
+static struct cgroup_subsys_state *
+blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
{
static atomic64_t id_seq = ATOMIC64_INIT(0);
struct blkcg *blkcg;
- struct cgroup *parent = cgroup->parent;
- if (!parent) {
+ if (!parent_css) {
blkcg = &blkcg_root;
goto done;
}
@@ -883,14 +879,15 @@ void blkcg_exit_queue(struct request_queue *q)
* of the main cic data structures. For now we allow a task to change
* its cgroup only if it's the only owner of its ioc.
*/
-static int blkcg_can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
+static int blkcg_can_attach(struct cgroup_subsys_state *css,
+ struct cgroup_taskset *tset)
{
struct task_struct *task;
struct io_context *ioc;
int ret = 0;
/* task_lock() is needed to avoid races with exit_io_context() */
- cgroup_taskset_for_each(task, cgrp, tset) {
+ cgroup_taskset_for_each(task, css, tset) {
task_lock(task);
ioc = task->io_context;
if (ioc && atomic_read(&ioc->nr_tasks) > 1)
@@ -1127,7 +1124,7 @@ void blkcg_policy_unregister(struct blkcg_policy *pol)
/* kill the intf files first */
if (pol->cftypes)
- cgroup_rm_cftypes(&blkio_subsys, pol->cftypes);
+ cgroup_rm_cftypes(pol->cftypes);
/* unregister and update blkgs */
blkcg_policy[pol->plid] = NULL;
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 8056c03a338..ae6969a7ffd 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -179,22 +179,20 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
void blkg_conf_finish(struct blkg_conf_ctx *ctx);
-static inline struct blkcg *cgroup_to_blkcg(struct cgroup *cgroup)
+static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css)
{
- return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id),
- struct blkcg, css);
+ return css ? container_of(css, struct blkcg, css) : NULL;
}
static inline struct blkcg *task_blkcg(struct task_struct *tsk)
{
- return container_of(task_subsys_state(tsk, blkio_subsys_id),
- struct blkcg, css);
+ return css_to_blkcg(task_css(tsk, blkio_subsys_id));
}
static inline struct blkcg *bio_blkcg(struct bio *bio)
{
if (bio && bio->bi_css)
- return container_of(bio->bi_css, struct blkcg, css);
+ return css_to_blkcg(bio->bi_css);
return task_blkcg(current);
}
@@ -206,9 +204,7 @@ static inline struct blkcg *bio_blkcg(struct bio *bio)
*/
static inline struct blkcg *blkcg_parent(struct blkcg *blkcg)
{
- struct cgroup *pcg = blkcg->css.cgroup->parent;
-
- return pcg ? cgroup_to_blkcg(pcg) : NULL;
+ return css_to_blkcg(css_parent(&blkcg->css));
}
/**
@@ -288,32 +284,33 @@ struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, struct request_queue *q,
/**
* blkg_for_each_descendant_pre - pre-order walk of a blkg's descendants
* @d_blkg: loop cursor pointing to the current descendant
- * @pos_cgrp: used for iteration
+ * @pos_css: used for iteration
* @p_blkg: target blkg to walk descendants of
*
* Walk @c_blkg through the descendants of @p_blkg. Must be used with RCU
* read locked. If called under either blkcg or queue lock, the iteration
* is guaranteed to include all and only online blkgs. The caller may
- * update @pos_cgrp by calling cgroup_rightmost_descendant() to skip
- * subtree.
+ * update @pos_css by calling css_rightmost_descendant() to skip subtree.
+ * @p_blkg is included in the iteration and the first node to be visited.
*/
-#define blkg_for_each_descendant_pre(d_blkg, pos_cgrp, p_blkg) \
- cgroup_for_each_descendant_pre((pos_cgrp), (p_blkg)->blkcg->css.cgroup) \
- if (((d_blkg) = __blkg_lookup(cgroup_to_blkcg(pos_cgrp), \
+#define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg) \
+ css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css) \
+ if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \
(p_blkg)->q, false)))
/**
* blkg_for_each_descendant_post - post-order walk of a blkg's descendants
* @d_blkg: loop cursor pointing to the current descendant
- * @pos_cgrp: used for iteration
+ * @pos_css: used for iteration
* @p_blkg: target blkg to walk descendants of
*
* Similar to blkg_for_each_descendant_pre() but performs post-order
- * traversal instead. Synchronization rules are the same.
+ * traversal instead. Synchronization rules are the same. @p_blkg is
+ * included in the iteration and the last node to be visited.
*/
-#define blkg_for_each_descendant_post(d_blkg, pos_cgrp, p_blkg) \
- cgroup_for_each_descendant_post((pos_cgrp), (p_blkg)->blkcg->css.cgroup) \
- if (((d_blkg) = __blkg_lookup(cgroup_to_blkcg(pos_cgrp), \
+#define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg) \
+ css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css) \
+ if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \
(p_blkg)->q, false)))
/**
@@ -576,7 +573,6 @@ static inline int blkcg_activate_policy(struct request_queue *q,
static inline void blkcg_deactivate_policy(struct request_queue *q,
const struct blkcg_policy *pol) { }
-static inline struct blkcg *cgroup_to_blkcg(struct cgroup *cgroup) { return NULL; }
static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; }
static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg,
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 08a32dfd384..8331aba9426 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -1293,10 +1293,10 @@ static u64 tg_prfill_cpu_rwstat(struct seq_file *sf,
return __blkg_prfill_rwstat(sf, pd, &rwstat);
}
-static int tg_print_cpu_rwstat(struct cgroup *cgrp, struct cftype *cft,
- struct seq_file *sf)
+static int tg_print_cpu_rwstat(struct cgroup_subsys_state *css,
+ struct cftype *cft, struct seq_file *sf)
{
- struct blkcg *blkcg = cgroup_to_blkcg(cgrp);
+ struct blkcg *blkcg = css_to_blkcg(css);
blkcg_print_blkgs(sf, blkcg, tg_prfill_cpu_rwstat, &blkcg_policy_throtl,
cft->private, true);
@@ -1325,31 +1325,31 @@ static u64 tg_prfill_conf_uint(struct seq_file *sf, struct blkg_policy_data *pd,
return __blkg_prfill_u64(sf, pd, v);
}
-static int tg_print_conf_u64(struct cgroup *cgrp, struct cftype *cft,
- struct seq_file *sf)
+static int tg_print_conf_u64(struct cgroup_subsys_state *css,
+ struct cftype *cft, struct seq_file *sf)
{
- blkcg_print_blkgs(sf, cgroup_to_blkcg(cgrp), tg_prfill_conf_u64,
+ blkcg_print_blkgs(sf, css_to_blkcg(css), tg_prfill_conf_u64,
&blkcg_policy_throtl, cft->private, false);
return 0;
}
-static int tg_print_conf_uint(struct cgroup *cgrp, struct cftype *cft,
- struct seq_file *sf)
+static int tg_print_conf_uint(struct cgroup_subsys_state *css,
+ struct cftype *cft, struct seq_file *sf)
{
- blkcg_print_blkgs(sf, cgroup_to_blkcg(cgrp), tg_prfill_conf_uint,
+ blkcg_print_blkgs(sf, css_to_blkcg(css), tg_prfill_conf_uint,
&blkcg_policy_throtl, cft->private, false);
return 0;
}
-static int tg_set_conf(struct cgroup *cgrp, struct cftype *cft, const char *buf,
- bool is_u64)
+static int tg_set_conf(struct cgroup_subsys_state *css, struct cftype *cft,
+ const char *buf, bool is_u64)
{
- struct blkcg *blkcg = cgroup_to_blkcg(cgrp);
+ struct blkcg *blkcg = css_to_blkcg(css);
struct blkg_conf_ctx ctx;
struct throtl_grp *tg;
struct throtl_service_queue *sq;
struct blkcg_gq *blkg;
- struct cgroup *pos_cgrp;
+ struct cgroup_subsys_state *pos_css;
int ret;
ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, buf, &ctx);
@@ -1379,8 +1379,7 @@ static int tg_set_conf(struct cgroup *cgrp, struct cftype *cft, const char *buf,
* restrictions in the whole hierarchy and allows them to bypass
* blk-throttle.
*/
- tg_update_has_rules(tg);
- blkg_for_each_descendant_pre(blkg, pos_cgrp, ctx.blkg)
+ blkg_for_each_descendant_pre(blkg, pos_css, ctx.blkg)
tg_update_has_rules(blkg_to_tg(blkg));
/*
@@ -1403,16 +1402,16 @@ static int tg_set_conf(struct cgroup *cgrp, struct cftype *cft, const char *buf,
return 0;
}
-static int tg_set_conf_u64(struct cgroup *cgrp, struct cftype *cft,
+static int tg_set_conf_u64(struct cgroup_subsys_state *css, struct cftype *cft,
const char *buf)
{
- return tg_set_conf(cgrp, cft, buf, true);
+ return tg_set_conf(css, cft, buf, true);
}
-static int tg_set_conf_uint(struct cgroup *cgrp, struct cftype *cft,
+static int tg_set_conf_uint(struct cgroup_subsys_state *css, struct cftype *cft,
const char *buf)
{
- return tg_set_conf(cgrp, cft, buf, false);
+ return tg_set_conf(css, cft, buf, false);
}
static struct cftype throtl_files[] = {
@@ -1623,7 +1622,7 @@ void blk_throtl_drain(struct request_queue *q)
{
struct throtl_data *td = q->td;
struct blkcg_gq *blkg;
- struct cgroup *pos_cgrp;
+ struct cgroup_subsys_state *pos_css;
struct bio *bio;
int rw;
@@ -1636,11 +1635,9 @@ void blk_throtl_drain(struct request_queue *q)
* better to walk service_queue tree directly but blkg walk is
* easier.
*/
- blkg_for_each_descendant_post(blkg, pos_cgrp, td->queue->root_blkg)
+ blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg)
tg_drain_bios(&blkg_to_tg(blkg)->service_queue);
- tg_drain_bios(&td_root_tg(td)->service_queue);
-
/* finally, transfer bios from top-level tg's into the td */
tg_drain_bios(&td->service_queue);
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index d5bbdcfd0da..dabb9d02cf9 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1607,12 +1607,11 @@ static u64 cfqg_prfill_weight_device(struct seq_file *sf,
return __blkg_prfill_u64(sf, pd, cfqg->dev_weight);
}
-static int cfqg_print_weight_device(struct cgroup *cgrp, struct cftype *cft,
- struct seq_file *sf)
+static int cfqg_print_weight_device(struct cgroup_subsys_state *css,
+ struct cftype *cft, struct seq_file *sf)
{
- blkcg_print_blkgs(sf, cgroup_to_blkcg(cgrp),
- cfqg_prfill_weight_device, &blkcg_policy_cfq, 0,
- false);
+ blkcg_print_blkgs(sf, css_to_blkcg(css), cfqg_prfill_weight_device,
+ &blkcg_policy_cfq, 0, false);
return 0;
}
@@ -1626,35 +1625,34 @@ static u64 cfqg_prfill_leaf_weight_device(struct seq_file *sf,
return __blkg_prfill_u64(sf, pd, cfqg->dev_leaf_weight);
}
-static int cfqg_print_leaf_weight_device(struct cgroup *cgrp,
+static int cfqg_print_leaf_weight_device(struct cgroup_subsys_state *css,
struct cftype *cft,
struct seq_file *sf)
{
- blkcg_print_blkgs(sf, cgroup_to_blkcg(cgrp),
- cfqg_prfill_leaf_weight_device, &blkcg_policy_cfq, 0,
- false);
+ blkcg_print_blkgs(sf, css_to_blkcg(css), cfqg_prfill_leaf_weight_device,
+ &blkcg_policy_cfq, 0, false);
return 0;
}
-static int cfq_print_weight(struct cgroup *cgrp, struct cftype *cft,
+static int cfq_print_weight(struct cgroup_subsys_state *css, struct cftype *cft,
struct seq_file *sf)
{
- seq_printf(sf, "%u\n", cgroup_to_blkcg(cgrp)->cfq_weight);
+ seq_printf(sf, "%u\n", css_to_blkcg(css)->cfq_weight);
return 0;
}
-static int cfq_print_leaf_weight(struct cgroup *cgrp, struct cftype *cft,
- struct seq_file *sf)
+static int cfq_print_leaf_weight(struct cgroup_subsys_state *css,
+ struct cftype *cft, struct seq_file *sf)
{
- seq_printf(sf, "%u\n",
- cgroup_to_blkcg(cgrp)->cfq_leaf_weight);
+ seq_printf(sf, "%u\n", css_to_blkcg(css)->cfq_leaf_weight);
return 0;
}
-static int __cfqg_set_weight_device(struct cgroup *cgrp, struct cftype *cft,
- const char *buf, bool is_leaf_weight)
+static int __cfqg_set_weight_device(struct cgroup_subsys_state *css,
+ struct cftype *cft, const char *buf,
+ bool is_leaf_weight)
{
- struct blkcg *blkcg = cgroup_to_blkcg(cgrp);
+ struct blkcg *blkcg = css_to_blkcg(css);
struct blkg_conf_ctx ctx;
struct cfq_group *cfqg;
int ret;
@@ -1680,22 +1678,22 @@ static int __cfqg_set_weight_device(struct cgroup *cgrp, struct cftype *cft,
return ret;
}
-static int cfqg_set_weight_device(struct cgroup *cgrp, struct cftype *cft,
- const char *buf)
+static int cfqg_set_weight_device(struct cgroup_subsys_state *css,
+ struct cftype *cft, const char *buf)
{
- return __cfqg_set_weight_device(cgrp, cft, buf, false);
+ return __cfqg_set_weight_device(css, cft, buf, false);
}
-static int cfqg_set_leaf_weight_device(struct cgroup *cgrp, struct cftype *cft,
- const char *buf)
+static int cfqg_set_leaf_weight_device(struct cgroup_subsys_state *css,
+ struct cftype *cft, const char *buf)
{
- return __cfqg_set_weight_device(cgrp, cft, buf, true);
+ return __cfqg_set_weight_device(css, cft, buf, true);
}
-static int __cfq_set_weight(struct cgroup *cgrp, struct cftype *cft, u64 val,
- bool is_leaf_weight)
+static int __cfq_set_weight(struct cgroup_subsys_state *css, struct cftype *cft,
+ u64 val, bool is_leaf_weight)
{
- struct blkcg *blkcg = cgroup_to_blkcg(cgrp);
+ struct blkcg *blkcg = css_to_blkcg(css);
struct blkcg_gq *blkg;
if (val < CFQ_WEIGHT_MIN || val > CFQ_WEIGHT_MAX)
@@ -1727,30 +1725,32 @@ static int __cfq_set_weight(struct cgroup *cgrp, struct cftype *cft, u64 val,
return 0;
}
-static int cfq_set_weight(struct cgroup *cgrp, struct cftype *cft, u64 val)
+static int cfq_set_weight(struct cgroup_subsys_state *css, struct cftype *cft,
+ u64 val)
{
- return __cfq_set_weight(cgrp, cft, val, false);
+ return __cfq_set_weight(css, cft, val, false);
}
-static int cfq_set_leaf_weight(struct cgroup *cgrp, struct cftype *cft, u64 val)
+static int cfq_set_leaf_weight(struct cgroup_subsys_state *css,
+ struct cftype *cft, u64 val)
{
- return __cfq_set_weight(cgrp, cft, val, true);
+ return __cfq_set_weight(css, cft, val, true);
}
-static int cfqg_print_stat(struct cgroup *cgrp, struct cftype *cft,
+static int cfqg_print_stat(struct cgroup_subsys_state *css, struct cftype *cft,
struct seq_file *sf)
{
- struct blkcg *blkcg = cgroup_to_blkcg(cgrp);
+ struct blkcg *blkcg = css_to_blkcg(css);
blkcg_print_blkgs(sf, blkcg, blkg_prfill_stat, &blkcg_policy_cfq,
cft->private, false);
return 0;
}
-static int cfqg_print_rwstat(struct cgroup *cgrp, struct cftype *cft,
- struct seq_file *sf)
+static int cfqg_print_rwstat(struct cgroup_subsys_state *css,
+ struct cftype *cft, struct seq_file *sf)
{
- struct blkcg *blkcg = cgroup_to_blkcg(cgrp);
+ struct blkcg *blkcg = css_to_blkcg(css);
blkcg_print_blkgs(sf, blkcg, blkg_prfill_rwstat, &blkcg_policy_cfq,
cft->private, true);
@@ -1773,20 +1773,20 @@ static u64 cfqg_prfill_rwstat_recursive(struct seq_file *sf,
return __blkg_prfill_rwstat(sf, pd, &sum);
}
-static int cfqg_print_stat_recursive(struct cgroup *cgrp, struct cftype *cft,
- struct seq_file *sf)
+static int cfqg_print_stat_recursive(struct cgroup_subsys_state *css,
+ struct cftype *cft, struct seq_file *sf)
{
- struct blkcg *blkcg = cgroup_to_blkcg(cgrp);
+ struct blkcg *blkcg = css_to_blkcg(css);
blkcg_print_blkgs(sf, blkcg, cfqg_prfill_stat_recursive,
&blkcg_policy_cfq, cft->private, false);
return 0;
}
-static int cfqg_print_rwstat_recursive(struct cgroup *cgrp, struct cftype *cft,
- struct seq_file *sf)
+static int cfqg_print_rwstat_recursive(struct cgroup_subsys_state *css,
+ struct cftype *cft, struct seq_file *sf)
{
- struct blkcg *blkcg = cgroup_to_blkcg(cgrp);
+ struct blkcg *blkcg = css_to_blkcg(css);
blkcg_print_blkgs(sf, blkcg, cfqg_prfill_rwstat_recursive,
&blkcg_policy_cfq, cft->private, true);
@@ -1810,10 +1810,10 @@ static u64 cfqg_prfill_avg_queue_size(struct seq_file *sf,
}
/* print avg_queue_size */
-static int cfqg_print_avg_queue_size(struct cgroup *cgrp, struct cftype *cft,
- struct seq_file *sf)
+static int cfqg_print_avg_queue_size(struct cgroup_subsys_state *css,
+ struct cftype *cft, struct seq_file *sf)
{
- struct blkcg *blkcg = cgroup_to_blkcg(cgrp);
+ struct blkcg *blkcg = css_to_blkcg(css);
blkcg_print_blkgs(sf, blkcg, cfqg_prfill_avg_queue_size,
&blkcg_policy_cfq, 0, false);
diff --git a/fs/bio.c b/fs/bio.c
index c5eae725149..b3b20ed9510 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -1956,7 +1956,7 @@ int bio_associate_current(struct bio *bio)
/* associate blkcg if exists */
rcu_read_lock();
- css = task_subsys_state(current, blkio_subsys_id);
+ css = task_css(current, blkio_subsys_id);
if (css && css_tryget(css))
bio->bi_css = css;
rcu_read_unlock();
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index e9ac882868c..3561d305b1e 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -66,22 +66,25 @@ enum cgroup_subsys_id {
/* Per-subsystem/per-cgroup state maintained by the system. */
struct cgroup_subsys_state {
- /*
- * The cgroup that this subsystem is attached to. Useful
- * for subsystems that want to know about the cgroup
- * hierarchy structure
- */
+ /* the cgroup that this css is attached to */
struct cgroup *cgroup;
+ /* the cgroup subsystem that this css is attached to */
+ struct cgroup_subsys *ss;
+
/* reference count - access via css_[try]get() and css_put() */
struct percpu_ref refcnt;
+ /* the parent css */
+ struct cgroup_subsys_state *parent;
+
unsigned long flags;
/* ID for this css, if possible */
struct css_id __rcu *id;
- /* Used to put @cgroup->dentry on the last css_put() */
- struct work_struct dput_work;
+ /* percpu_ref killing and RCU release */
+ struct rcu_head rcu_head;
+ struct work_struct destroy_work;
};
/* bits in struct cgroup_subsys_state flags field */
@@ -161,7 +164,16 @@ struct cgroup_name {
struct cgroup {
unsigned long flags; /* "unsigned long" so bitops work */
- int id; /* ida allocated in-hierarchy ID */
+ /*
+ * idr allocated in-hierarchy ID.
+ *
+ * The ID of the root cgroup is always 0, and a new cgroup
+ * will be assigned with a smallest available ID.
+ */
+ int id;
+
+ /* the number of attached css's */
+ int nr_css;
/*
* We link our 'sibling' struct into our parent's 'children'.
@@ -196,7 +208,7 @@ struct cgroup {
struct cgroup_name __rcu *name;
/* Private pointers for each registered subsystem */
- struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];
+ struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT];
struct cgroupfs_root *root;
@@ -220,10 +232,12 @@ struct cgroup {
struct list_head pidlists;
struct mutex pidlist_mutex;
+ /* dummy css with NULL ->ss, points back to this cgroup */
+ struct cgroup_subsys_state dummy_css;
+
/* For css percpu_ref killing and RCU-protected deletion */
struct rcu_head rcu_head;
struct work_struct destroy_work;
- atomic_t css_kill_cnt;
/* List of events which userspace want to receive */
struct list_head event_list;
@@ -322,7 +336,7 @@ struct cgroupfs_root {
unsigned long flags;
/* IDs for cgroups in this hierarchy */
- struct ida cgroup_ida;
+ struct idr cgroup_idr;
/* The path to use for release notifications. */
char release_agent_path[PATH_MAX];
@@ -394,9 +408,10 @@ struct cgroup_map_cb {
/* cftype->flags */
enum {
- CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cg */
- CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cg */
+ CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cgrp */
+ CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cgrp */
CFTYPE_INSANE = (1 << 2), /* don't create if sane_behavior */
+ CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */
};
#define MAX_CFTYPE_NAME 64
@@ -424,35 +439,41 @@ struct cftype {
/* CFTYPE_* flags */
unsigned int flags;
+ /*
+ * The subsys this file belongs to. Initialized automatically
+ * during registration. NULL for cgroup core files.
+ */
+ struct cgroup_subsys *ss;
+
int (*open)(struct inode *inode, struct file *file);
- ssize_t (*read)(struct cgroup *cgrp, struct cftype *cft,
+ ssize_t (*read)(struct cgroup_subsys_state *css, struct cftype *cft,
struct file *file,
char __user *buf, size_t nbytes, loff_t *ppos);
/*
* read_u64() is a shortcut for the common case of returning a
* single integer. Use it in place of read()
*/
- u64 (*read_u64)(struct cgroup *cgrp, struct cftype *cft);
+ u64 (*read_u64)(struct cgroup_subsys_state *css, struct cftype *cft);
/*
* read_s64() is a signed version of read_u64()
*/
- s64 (*read_s64)(struct cgroup *cgrp, struct cftype *cft);
+ s64 (*read_s64)(struct cgroup_subsys_state *css, struct cftype *cft);
/*
* read_map() is used for defining a map of key/value
* pairs. It should call cb->fill(cb, key, value) for each
* entry. The key/value pairs (and their ordering) should not
* change between reboots.
*/
- int (*read_map)(struct cgroup *cgrp, struct cftype *cft,
+ int (*read_map)(struct cgroup_subsys_state *css, struct cftype *cft,
struct cgroup_map_cb *cb);
/*
* read_seq_string() is used for outputting a simple sequence
* using seqfile.
*/
- int (*read_seq_string)(struct cgroup *cgrp, struct cftype *cft,
- struct seq_file *m);
+ int (*read_seq_string)(struct cgroup_subsys_state *css,
+ struct cftype *cft, struct seq_file *m);
- ssize_t (*write)(struct cgroup *cgrp, struct cftype *cft,
+ ssize_t (*write)(struct cgroup_subsys_state *css, struct cftype *cft,
struct file *file,
const char __user *buf, size_t nbytes, loff_t *ppos);
@@ -461,18 +482,20 @@ struct cftype {
* a single integer (as parsed by simple_strtoull) from
* userspace. Use in place of write(); return 0 or error.
*/
- int (*write_u64)(struct cgroup *cgrp, struct cftype *cft, u64 val);
+ int (*write_u64)(struct cgroup_subsys_state *css, struct cftype *cft,
+ u64 val);
/*
* write_s64() is a signed version of write_u64()
*/
- int (*write_s64)(struct cgroup *cgrp, struct cftype *cft, s64 val);
+ int (*write_s64)(struct cgroup_subsys_state *css, struct cftype *cft,
+ s64 val);
/*
* write_string() is passed a nul-terminated kernelspace
* buffer of maximum length determined by max_write_len.
* Returns 0 or -ve error code.
*/
- int (*write_string)(struct cgroup *cgrp, struct cftype *cft,
+ int (*write_string)(struct cgroup_subsys_state *css, struct cftype *cft,
const char *buffer);
/*
* trigger() callback can be used to get some kick from the
@@ -480,7 +503,7 @@ struct cftype {
* at all. The private field can be used to determine the
* kick type for multiplexing.
*/
- int (*trigger)(struct cgroup *cgrp, unsigned int event);
+ int (*trigger)(struct cgroup_subsys_state *css, unsigned int event);
int (*release)(struct inode *inode, struct file *file);
@@ -490,16 +513,18 @@ struct cftype {
* you want to provide this functionality. Use eventfd_signal()
* on eventfd to send notification to userspace.
*/
- int (*register_event)(struct cgroup *cgrp, struct cftype *cft,
- struct eventfd_ctx *eventfd, const char *args);
+ int (*register_event)(struct cgroup_subsys_state *css,
+ struct cftype *cft, struct eventfd_ctx *eventfd,
+ const char *args);
/*
* unregister_event() callback will be called when userspace
* closes the eventfd or on cgroup removing.
* This callback must be implemented, if you want provide
* notification functionality.
*/
- void (*unregister_event)(struct cgroup *cgrp, struct cftype *cft,
- struct eventfd_ctx *eventfd);
+ void (*unregister_event)(struct cgroup_subsys_state *css,
+ struct cftype *cft,
+ struct eventfd_ctx *eventfd);
};
/*
@@ -512,15 +537,6 @@ struct cftype_set {
struct cftype *cfts;
};
-struct cgroup_scanner {
- struct cgroup *cg;
- int (*test_task)(struct task_struct *p, struct cgroup_scanner *scan);
- void (*process_task)(struct task_struct *p,
- struct cgroup_scanner *scan);
- struct ptr_heap *heap;
- void *data;
-};
-
/*
* See the comment above CGRP_ROOT_SANE_BEHAVIOR for details. This
* function can be called as long as @cgrp is accessible.
@@ -537,7 +553,7 @@ static inline const char *cgroup_name(const struct cgroup *cgrp)
}
int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
-int cgroup_rm_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
+int cgroup_rm_cftypes(struct cftype *cfts);
bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor);
@@ -553,20 +569,22 @@ int cgroup_task_count(const struct cgroup *cgrp);
struct cgroup_taskset;
struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset);
struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset);
-struct cgroup *cgroup_taskset_cur_cgroup(struct cgroup_taskset *tset);
+struct cgroup_subsys_state *cgroup_taskset_cur_css(struct cgroup_taskset *tset,
+ int subsys_id);
int cgroup_taskset_size(struct cgroup_taskset *tset);
/**
* cgroup_taskset_for_each - iterate cgroup_taskset
* @task: the loop cursor
- * @skip_cgrp: skip if task's cgroup matches this, %NULL to iterate through all
+ * @skip_css: skip if task's css matches this, %NULL to iterate through all
* @tset: taskset to iterate
*/
-#define cgroup_taskset_for_each(task, skip_cgrp, tset) \
+#define cgroup_taskset_for_each(task, skip_css, tset) \
for ((task) = cgroup_taskset_first((tset)); (task); \
(task) = cgroup_taskset_next((tset))) \
- if (!(skip_cgrp) || \
- cgroup_taskset_cur_cgroup((tset)) != (skip_cgrp))
+ if (!(skip_css) || \
+ cgroup_taskset_cur_css((tset), \
+ (skip_css)->ss->subsys_id) != (skip_css))
/*
* Control Group subsystem type.
@@ -574,18 +592,22 @@ int cgroup_taskset_size(struct cgroup_taskset *tset);
*/
struct cgroup_subsys {
- struct cgroup_subsys_state *(*css_alloc)(struct cgroup *cgrp);
- int (*css_online)(struct cgroup *cgrp);
- void (*css_offline)(struct cgroup *cgrp);
- void (*css_free)(struct cgroup *cgrp);
-
- int (*can_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset);
- void (*cancel_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset);
- void (*attach)(struct cgroup *cgrp, struct cgroup_taskset *tset);
+ struct cgroup_subsys_state *(*css_alloc)(struct cgroup_subsys_state *parent_css);
+ int (*css_online)(struct cgroup_subsys_state *css);
+ void (*css_offline)(struct cgroup_subsys_state *css);
+ void (*css_free)(struct cgroup_subsys_state *css);
+
+ int (*can_attach)(struct cgroup_subsys_state *css,
+ struct cgroup_taskset *tset);
+ void (*cancel_attach)(struct cgroup_subsys_state *css,
+ struct cgroup_taskset *tset);
+ void (*attach)(struct cgroup_subsys_state *css,
+ struct cgroup_taskset *tset);
void (*fork)(struct task_struct *task);
- void (*exit)(struct cgroup *cgrp, struct cgroup *old_cgrp,
+ void (*exit)(struct cgroup_subsys_state *css,
+ struct cgroup_subsys_state *old_css,
struct task_struct *task);
- void (*bind)(struct cgroup *root);
+ void (*bind)(struct cgroup_subsys_state *root_css);
int subsys_id;
int disabled;
@@ -641,10 +663,17 @@ struct cgroup_subsys {
#undef IS_SUBSYS_ENABLED
#undef SUBSYS
-static inline struct cgroup_subsys_state *cgroup_subsys_state(
- struct cgroup *cgrp, int subsys_id)
+/**
+ * css_parent - find the parent css
+ * @css: the target cgroup_subsys_state
+ *
+ * Return the parent css of @css. This function is guaranteed to return
+ * non-NULL parent as long as @css isn't the root.
+ */
+static inline
+struct cgroup_subsys_state *css_parent(struct cgroup_subsys_state *css)
{
- return cgrp->subsys[subsys_id];
+ return css->parent;
}
/**
@@ -672,7 +701,7 @@ extern struct mutex cgroup_mutex;
#endif
/**
- * task_subsys_state_check - obtain css for (task, subsys) w/ extra access conds
+ * task_css_check - obtain css for (task, subsys) w/ extra access conds
* @task: the target task
* @subsys_id: the target subsystem ID
* @__c: extra condition expression to be passed to rcu_dereference_check()
@@ -680,7