From mboxrd@z Thu Jan 1 00:00:00 1970 From: Roman Gushchin Subject: [PATCH v5 3/7] cgroup: protect cgroup->nr_(dying_)descendants by css_set_lock Date: Fri, 7 Dec 2018 12:15:27 -0800 Message-ID: <20181207201531.1665-4-guro@fb.com> References: <20181207201531.1665-1-guro@fb.com> Return-path: DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=from:to:cc:subject:date:message-id:in-reply-to:references; bh=AF6FjZ5bYHqrhn2j5NEFo6/8zOWEnmu3uN/KpDBNyX8=; b=Zab/XM4V325VwLDjQweH6/BjCmL72mI1hULkW0qXSRg8VLOY0XFTvNNtOPrJPZL50C eq1kPcbT++Kv9gQaRQassMfIIa4TjxnlWxGak0TIK7KWHKsTDevl5n1aPTBKIRaMtcH/ 365X7yjF6admMely003US2abDL4tEZEVQgPShcLtBSzu5G5XPFq+qeIcA4aakQh5koOR TORvjAVHpA3Qe53DyMmCvUk51knVyBPPacmJ+uHZyyIKVCbu5fVA1PIV8JJZS4UMqNcO 0Bs1g+Zfffl7P022i3lO54vLdB20PdVYUCzQuEUJ8pOZHdDatawPP6aoODY3S4xa5tGg Cbiw== In-Reply-To: <20181207201531.1665-1-guro@fb.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: Tejun Heo , Oleg Nesterov Cc: Dan Carpenter , Mike Rapoport , cgroups@vger.kernel.org, linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org, kernel-team@fb.com, Roman Gushchin The number of descendant cgroups and the number of dying descendant cgroups are currently synchronized using the cgroup_mutex. The number of descendant cgroups will be required by the cgroup v2 freezer, which will use it to determine if a cgroup is frozen (depending on total number of descendants and number of frozen descendants). It's not always acceptable to grab the cgroup_mutex, especially from quite hot paths (e.g. exit()). To avoid this, let's additionally synchronize these counters using the css_set_lock. So, it's safe to read these counters with either cgroup_mutex or css_set_lock locked, and for changing both locks should be acquired. Signed-off-by: Roman Gushchin Cc: Tejun Heo Cc: kernel-team@fb.com --- include/linux/cgroup-defs.h | 5 +++++ kernel/cgroup/cgroup.c | 6 ++++++ 2 files changed, 11 insertions(+) diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 8fcbae1b8db0..03355d7008ff 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -348,6 +348,11 @@ struct cgroup { * Dying cgroups are cgroups which were deleted by a user, * but are still existing because someone else is holding a reference. * max_descendants is a maximum allowed number of descent cgroups. + * + * nr_descendants and nr_dying_descendants are protected + * by cgroup_mutex and css_set_lock. It's fine to read them holding + * any of cgroup_mutex and css_set_lock; for writing both locks + * should be held. */ int nr_descendants; int nr_dying_descendants; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 7519a4307021..f89dde50f693 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4723,9 +4723,11 @@ static void css_release_work_fn(struct work_struct *work) if (cgroup_on_dfl(cgrp)) cgroup_rstat_flush(cgrp); + spin_lock_irq(&css_set_lock); for (tcgrp = cgroup_parent(cgrp); tcgrp; tcgrp = cgroup_parent(tcgrp)) tcgrp->nr_dying_descendants--; + spin_unlock_irq(&css_set_lock); cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id); cgrp->id = -1; @@ -4943,12 +4945,14 @@ static struct cgroup *cgroup_create(struct cgroup *parent) if (ret) goto out_psi_free; + spin_lock_irq(&css_set_lock); for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) { cgrp->ancestor_ids[tcgrp->level] = tcgrp->id; if (tcgrp != cgrp) tcgrp->nr_descendants++; } + spin_unlock_irq(&css_set_lock); if (notify_on_release(parent)) set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); @@ -5233,10 +5237,12 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) if (parent && cgroup_is_threaded(cgrp)) parent->nr_threaded_children--; + spin_lock_irq(&css_set_lock); for (tcgrp = cgroup_parent(cgrp); tcgrp; tcgrp = cgroup_parent(tcgrp)) { tcgrp->nr_descendants--; tcgrp->nr_dying_descendants++; } + spin_unlock_irq(&css_set_lock); cgroup1_check_for_release(parent); -- 2.17.2