@@ -10,7 +10,11 @@
struct cgroup_subsys_bpf {
/* Head of the list of BPF rstat flushers attached to this subsystem */
struct list_head rstat_flushers;
- spinlock_t flushers_lock;
+ /*
+ * A list that runs through subsystems that have at least one rstat
+ * flusher.
+ */
+ struct list_head rstat_subsys_node;
};
struct bpf_subsys_rstat_flusher {
@@ -26,5 +30,6 @@ struct bpf_cgroup_subsys_link {
int cgroup_subsys_bpf_link_attach(const union bpf_attr *attr,
struct bpf_prog *prog);
+void bpf_run_rstat_flushers(struct cgroup *cgrp, int cpu);
#endif // _BPF_CGROUP_SUBSYS_H_
@@ -97,6 +97,8 @@ extern struct css_set init_css_set;
bool css_has_online_children(struct cgroup_subsys_state *css);
struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss);
+struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
+ struct cgroup_subsys *ss);
struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgroup,
struct cgroup_subsys *ss);
struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup,
@@ -6,10 +6,46 @@
*/
#include <linux/bpf-cgroup-subsys.h>
+#include <linux/cgroup.h>
#include <linux/filter.h>
#include "../cgroup/cgroup-internal.h"
+/* List of subsystems that have rstat flushers attached */
+static LIST_HEAD(bpf_rstat_subsys_list);
+/* Protects the above list, and the lists of rstat flushers in each subsys */
+static DEFINE_SPINLOCK(bpf_rstat_subsys_lock);
+
+
+void bpf_run_rstat_flushers(struct cgroup *cgrp, int cpu)
+{
+ struct cgroup_subsys_bpf *ss_bpf;
+ struct cgroup *parent = cgroup_parent(cgrp);
+ struct bpf_rstat_ctx ctx = {
+ .cgroup_id = cgroup_id(cgrp),
+ .parent_cgroup_id = parent ? cgroup_id(parent) : 0,
+ .cpu = cpu,
+ };
+
+ rcu_read_lock();
+ migrate_disable();
+ spin_lock(&bpf_rstat_subsys_lock);
+ list_for_each_entry(ss_bpf, &bpf_rstat_subsys_list, rstat_subsys_node) {
+ struct bpf_subsys_rstat_flusher *rstat_flusher;
+ struct cgroup_subsys *ss = container_of(ss_bpf,
+ struct cgroup_subsys,
+ bpf);
+
+ /* Subsystem ss is not enabled for cgrp */
+ if (!cgroup_css(cgrp, ss))
+ continue;
+ list_for_each_entry(rstat_flusher, &ss_bpf->rstat_flushers, list)
+ (void) bpf_prog_run(rstat_flusher->prog, &ctx);
+ }
+ spin_unlock(&bpf_rstat_subsys_lock);
+ migrate_enable();
+ rcu_read_unlock();
+}
static int cgroup_subsys_bpf_attach(struct cgroup_subsys *ss, struct bpf_prog *prog)
{
@@ -20,28 +56,38 @@ static int cgroup_subsys_bpf_attach(struct cgroup_subsys *ss, struct bpf_prog *p
return -ENOMEM;
rstat_flusher->prog = prog;
- spin_lock(&ss->bpf.flushers_lock);
+ spin_lock(&bpf_rstat_subsys_lock);
+ /* Add ss to bpf_rstat_subsys_list when we attach the first flusher */
+ if (list_empty(&ss->bpf.rstat_flushers))
+ list_add(&ss->bpf.rstat_subsys_node, &bpf_rstat_subsys_list);
list_add(&rstat_flusher->list, &ss->bpf.rstat_flushers);
- spin_unlock(&ss->bpf.flushers_lock);
+ spin_unlock(&bpf_rstat_subsys_lock);
return 0;
}
static void cgroup_subsys_bpf_detach(struct cgroup_subsys *ss, struct bpf_prog *prog)
{
- struct bpf_subsys_rstat_flusher *rstat_flusher = NULL;
+ struct bpf_subsys_rstat_flusher *iter, *rstat_flusher = NULL;
- spin_lock(&ss->bpf.flushers_lock);
- list_for_each_entry(rstat_flusher, &ss->bpf.rstat_flushers, list)
- if (rstat_flusher->prog == prog)
+ spin_lock(&bpf_rstat_subsys_lock);
+ list_for_each_entry(iter, &ss->bpf.rstat_flushers, list)
+ if (iter->prog == prog) {
+ rstat_flusher = iter;
break;
+ }
if (rstat_flusher) {
list_del(&rstat_flusher->list);
bpf_prog_put(rstat_flusher->prog);
kfree(rstat_flusher);
}
- spin_unlock(&ss->bpf.flushers_lock);
+ /*
+ * Remove ss from bpf_rstat_subsys_list when we detach the last flusher
+ */
+ if (list_empty(&ss->bpf.rstat_flushers))
+ list_del(&ss->bpf.rstat_subsys_node);
+ spin_unlock(&bpf_rstat_subsys_lock);
}
static void bpf_cgroup_subsys_link_release(struct bpf_link *link)
@@ -478,8 +478,8 @@ static u16 cgroup_ss_mask(struct cgroup *cgrp)
* keep accessing it outside the said locks. This function may return
* %NULL if @cgrp doesn't have @subsys_id enabled.
*/
-static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
- struct cgroup_subsys *ss)
+struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
+ struct cgroup_subsys *ss)
{
if (CGROUP_HAS_SUBSYS_CONFIG && ss)
return rcu_dereference_check(cgrp->subsys[ss->id],
@@ -5746,6 +5746,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early)
idr_init(&ss->css_idr);
INIT_LIST_HEAD(&ss->cfts);
INIT_LIST_HEAD(&ss->bpf.rstat_flushers);
+ INIT_LIST_HEAD(&ss->bpf.rstat_subsys_node);
/* Create the root cgroup state for this subsystem */
ss->root = &cgrp_dfl_root;
@@ -2,6 +2,7 @@
#include "cgroup-internal.h"
#include <linux/sched/cputime.h>
+#include <linux/bpf-cgroup-subsys.h>
static DEFINE_SPINLOCK(cgroup_rstat_lock);
static DEFINE_PER_CPU(raw_spinlock_t, cgroup_rstat_cpu_lock);
@@ -173,6 +174,16 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep)
list_for_each_entry_rcu(css, &pos->rstat_css_list,
rstat_css_node)
css->ss->css_rstat_flush(css, cpu);
+ /*
+ * We run bpf flushers in a separate loop in
+ * bpf_run_rstat_flushers() as the above
+ * loop only goes through subsystems that have rstat
+ * flushing registered in the kernel.
+ *
+ * This gives flexibility for BPF programs to utilize
+ * rstat to collect stats for any subsystem.
+ */
+ bpf_run_rstat_flushers(pos, cpu);
rcu_read_unlock();
}
raw_spin_unlock_irqrestore(cpu_lock, flags);
When a cgroup is popped from the rstat updated tree, subsystems rstat flushers are run through the css_rstat_flush() callback. Also run bpf flushers for all subsystems that have at least one bpf rstat flusher attached, and are enabled for this cgroup. A list of subsystems that have attached rstat flushers is maintained to avoid looping through all subsystems for all cpus for every cgroup that is being popped from the updated tree. Since we introduce a lock here to protect this list, also use it to protect rstat_flushers lists inside each subsystem (since they both need to locked together anyway), and get read of the locks in struct cgroup_subsys_bpf. rstat flushers are run for any enabled subsystem that has flushers attached, even if it does not subscribe to css flushing through css_rstat_flush(). This gives flexibility for bpf programs to collect stats for any subsystem, regardless of the implementation changes in the kernel. Signed-off-by: Yosry Ahmed <yosryahmed@google.com> --- include/linux/bpf-cgroup-subsys.h | 7 +++- include/linux/cgroup.h | 2 ++ kernel/bpf/cgroup_subsys.c | 60 +++++++++++++++++++++++++++---- kernel/cgroup/cgroup.c | 5 +-- kernel/cgroup/rstat.c | 11 ++++++ 5 files changed, 75 insertions(+), 10 deletions(-)