linux-kernel - [PATCH v4 3/6] cgroup/pids: Make event counters hierarchical

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date: Tue, 16 Apr 2024 16:20:11 +0200
From: Michal Koutný <mkoutny@...e.com>
To: cgroups@...r.kernel.org,
	linux-doc@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	linux-kselftest@...r.kernel.org
Cc: Tejun Heo <tj@...nel.org>,
	Zefan Li <lizefan.x@...edance.com>,
	Johannes Weiner <hannes@...xchg.org>,
	Jonathan Corbet <corbet@....net>,
	Shuah Khan <shuah@...nel.org>,
	Muhammad Usama Anjum <usama.anjum@...labora.com>
Subject: [PATCH v4 3/6] cgroup/pids: Make event counters hierarchical

The pids.events file should honor the hierarchy, so make the events
propagate from their origin up to the root on the unified hierarchy. The
legacy behavior remains non-hierarchical.

Signed-off-by: Michal Koutný <mkoutny@...e.com>
---
 Documentation/admin-guide/cgroup-v2.rst |  2 +-
 kernel/cgroup/pids.c                    | 46 ++++++++++++++++---------
 2 files changed, 31 insertions(+), 17 deletions(-)

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 108b03dfb26a..aa97e9f91c51 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -241,7 +241,7 @@ cgroup v2 currently supports the following mount options.
 
   pid_localevents
         Represent fork failures inside cgroup's pids.events:max (not its limit
-        being hit).
+        being hit) and exclude subtree events from pids.events.
 
 
 Organizing Processes and Threads
diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c
index ea1fc6b37c0d..4ad28109c1c8 100644
--- a/kernel/cgroup/pids.c
+++ b/kernel/cgroup/pids.c
@@ -238,6 +238,34 @@ static void pids_cancel_attach(struct cgroup_taskset *tset)
 	}
 }
 
+static void pids_event(struct pids_cgroup *pids_forking,
+		       struct pids_cgroup *pids_over_limit)
+{
+	struct pids_cgroup *p = pids_forking;
+	bool limit = false;
+
+	for (; parent_pids(p); p = parent_pids(p)) {
+		/* Only log the first time limit is hit. */
+		if (atomic64_inc_return(&p->events[PIDCG_FORKFAIL]) == 1) {
+			pr_info("cgroup: fork rejected by pids controller in ");
+			pr_cont_cgroup_path(p->css.cgroup);
+			pr_cont("\n");
+		}
+		cgroup_file_notify(&p->events_file);
+
+		if (!cgroup_subsys_on_dfl(pids_cgrp_subsys) ||
+		    cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS)
+			break;
+
+		if (p == pids_over_limit)
+			limit = true;
+		if (limit)
+			atomic64_inc(&p->events[PIDCG_MAX]);
+
+		cgroup_file_notify(&p->events_file);
+	}
+}
+
 /*
  * task_css_check(true) in pids_can_fork() and pids_cancel_fork() relies
  * on cgroup_threadgroup_change_begin() held by the copy_process().
@@ -254,23 +282,9 @@ static int pids_can_fork(struct task_struct *task, struct css_set *cset)
 		css = task_css_check(current, pids_cgrp_id, true);
 	pids = css_pids(css);
 	err = pids_try_charge(pids, 1, &pids_over_limit);
-	if (err) {
-		/* compatibility on v1 where events were notified in leaves. */
-		if (!cgroup_subsys_on_dfl(pids_cgrp_subsys))
-			pids_over_limit = pids;
-
-		/* Only log the first time limit is hit. */
-		if (atomic64_inc_return(&pids->events[PIDCG_FORKFAIL]) == 1) {
-			pr_info("cgroup: fork rejected by pids controller in ");
-			pr_cont_cgroup_path(pids->css.cgroup);
-			pr_cont("\n");
-		}
-		atomic64_inc(&pids_over_limit->events[PIDCG_MAX]);
+	if (err)
+		pids_event(pids, pids_over_limit);
 
-		cgroup_file_notify(&pids->events_file);
-		if (pids_over_limit != pids)
-			cgroup_file_notify(&pids_over_limit->events_file);
-	}
 	return err;
 }
 
-- 
2.44.0