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]
Message-ID: <20230308131452.383914-4-peternewman@google.com>
Date:   Wed,  8 Mar 2023 14:14:52 +0100
From:   Peter Newman <peternewman@...gle.com>
To:     reinette.chatre@...el.com, fenghua.yu@...el.com
Cc:     Babu.Moger@....com, bp@...en8.de, dave.hansen@...ux.intel.com,
        eranian@...gle.com, gupasani@...gle.com, hpa@...or.com,
        james.morse@....com, linux-kernel@...r.kernel.org,
        mingo@...hat.com, skodak@...gle.com, tglx@...utronix.de,
        tony.luck@...el.com, x86@...nel.org,
        Peter Newman <peternewman@...gle.com>
Subject: [PATCH v4 3/3] x86/resctrl: Implement rename op for mon groups

To change the class of service for a large group of tasks, such as an
application container, a container manager must write all of the tasks'
IDs into the tasks file interface of the new control group.

If a container manager is tracking containers' bandwidth usage by
placing tasks from each into their own monitoring group, it must first
move the tasks to the default monitoring group of the new control group
before it can move the tasks into their new monitoring groups. This is
undesirable because it makes bandwidth usage during the move
unattributable to the correct tasks and resets monitoring event counters
and cache usage information for the group.

To address this, implement the rename operation for resctrlfs mon groups
to effect a change in CLOSID for a MON group while otherwise leaving the
monitoring group intact.

Signed-off-by: Peter Newman <peternewman@...gle.com>
---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 127 +++++++++++++++++++++++++
 1 file changed, 127 insertions(+)

diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 84af23a29612..6d576013fc16 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -3256,6 +3256,132 @@ static int rdtgroup_rmdir(struct kernfs_node *kn)
 	return ret;
 }
 
+static bool mongrp_reparent_match(struct task_struct *t, struct rdtgroup *from)
+{
+	WARN_ON(from->type != RDTMON_GROUP);
+
+	/* RMID match implies CLOSID match. */
+	return is_rmid_match(t, from);
+}
+
+/**
+ * mongrp_reparent() - replace parent CTRL_MON group of a MON group
+ * @rdtgrp:		the MON group whose parent should be replaced
+ * @new_prdtgrp:	replacement parent CTRL_MON group for @rdtgrp
+ * @cpus:		cpumask provided by the caller for use during this call
+ *
+ * Replaces the parent CTRL_MON group for a MON group, resulting in all member
+ * tasks' CLOSID immediately changing to that of the new parent group.
+ * Monitoring data for the group is unaffected by this operation.
+ */
+static void mongrp_reparent(struct rdtgroup *rdtgrp,
+			    struct rdtgroup *new_prdtgrp,
+			    cpumask_var_t cpus)
+{
+	struct rdtgroup *prdtgrp = rdtgrp->mon.parent;
+
+	WARN_ON(rdtgrp->type != RDTMON_GROUP);
+	WARN_ON(new_prdtgrp->type != RDTCTRL_GROUP);
+
+	/* Nothing to do when simply renaming a MON group. */
+	if (prdtgrp == new_prdtgrp)
+		return;
+
+	WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list));
+	list_del(&rdtgrp->mon.crdtgrp_list);
+
+	list_add_tail(&rdtgrp->mon.crdtgrp_list,
+		      &new_prdtgrp->mon.crdtgrp_list);
+	rdtgrp->mon.parent = new_prdtgrp;
+	rdtgrp->closid = new_prdtgrp->closid;
+
+	/* Propagate updated closid to all tasks in this group. */
+	rdt_move_group_tasks(rdtgrp, rdtgrp, cpus, mongrp_reparent_match);
+
+	update_closid_rmid(cpus, NULL);
+}
+
+static int rdtgroup_rename(struct kernfs_node *kn,
+			   struct kernfs_node *new_parent, const char *new_name)
+{
+	struct rdtgroup *new_prdtgrp;
+	struct rdtgroup *rdtgrp;
+	cpumask_var_t tmpmask;
+	int ret;
+
+	/*
+	 * Don't allow kernfs_to_rdtgroup() to return a parent rdtgroup if
+	 * either kernfs_node is a file.
+	 */
+	if (kernfs_type(kn) != KERNFS_DIR ||
+	    kernfs_type(new_parent) != KERNFS_DIR)
+		return -EPERM;
+
+	rdtgrp = kernfs_to_rdtgroup(kn);
+	new_prdtgrp = kernfs_to_rdtgroup(new_parent);
+	if (!rdtgrp || !new_prdtgrp)
+		return -EPERM;
+
+	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
+		return -ENOMEM;
+
+	/* Release both kernfs active_refs before obtaining rdtgroup mutex. */
+	rdtgroup_kn_get(rdtgrp, kn);
+	rdtgroup_kn_get(new_prdtgrp, new_parent);
+
+	mutex_lock(&rdtgroup_mutex);
+
+	rdt_last_cmd_clear();
+
+	if ((rdtgrp->flags & RDT_DELETED) || (new_prdtgrp->flags & RDT_DELETED)) {
+		ret = -ESRCH;
+		goto out;
+	}
+
+	if (rdtgrp->type != RDTMON_GROUP || !kn->parent ||
+	    !is_mon_groups(kn->parent, kn->name)) {
+		rdt_last_cmd_puts("source must be a MON group\n");
+		ret = -EPERM;
+		goto out;
+	}
+
+	if (!is_mon_groups(new_parent, new_name)) {
+		rdt_last_cmd_puts("destination must be a mon_groups subdirectory\n");
+		ret = -EPERM;
+		goto out;
+	}
+
+	/*
+	 * If the MON group is monitoring CPUs, they must be assigned to the
+	 * current parent CTRL_MON group and therefore cannot be assigned to
+	 * the new parent, making the move illegal.
+	 */
+	if (!cpumask_empty(&rdtgrp->cpu_mask) &&
+	    (rdtgrp->mon.parent != new_prdtgrp)) {
+		rdt_last_cmd_puts("cannot move a MON group that monitors CPUs\n");
+		ret = -EPERM;
+		goto out;
+	}
+
+	/*
+	 * Perform all input validation needed to ensure mongrp_reparent() will
+	 * succeed before calling kernfs_rename(), otherwise it would be
+	 * necessary to revert this call if mongrp_reparent() failed.
+	 */
+	ret = kernfs_rename(kn, new_parent, new_name);
+	if (ret)
+		goto out;
+
+	mongrp_reparent(rdtgrp, new_prdtgrp, tmpmask);
+
+out:
+	mutex_unlock(&rdtgroup_mutex);
+	rdtgroup_kn_put(rdtgrp, kn);
+	rdtgroup_kn_put(new_prdtgrp, new_parent);
+	free_cpumask_var(tmpmask);
+	return ret;
+}
+
 static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf)
 {
 	if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3))
@@ -3273,6 +3399,7 @@ static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf)
 static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = {
 	.mkdir		= rdtgroup_mkdir,
 	.rmdir		= rdtgroup_rmdir,
+	.rename		= rdtgroup_rename,
 	.show_options	= rdtgroup_show_options,
 };
 
-- 
2.40.0.rc0.216.gc4246ad0f0-goog

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ