mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Tony Luck <tony.luck@intel.com>
To: Fenghua Yu <fenghuay@nvidia.com>,
	Reinette Chatre <reinette.chatre@intel.com>,
	Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>,
	Peter Newman <peternewman@google.com>,
	James Morse <james.morse@arm.com>,
	Babu Moger <babu.moger@amd.com>,
	Drew Fustini <dfustini@baylibre.com>,
	Dave Martin <Dave.Martin@arm.com>, Chen Yu <yu.c.chen@intel.com>,
	David E Box <david.e.box@intel.com>,
	x86@kernel.org
Cc: Christoph Hellwig <hch@infradead.org>,
	linux-kernel@vger.kernel.org, patches@lists.linux.dev,
	Tony Luck <tony.luck@intel.com>, Ben Horgan <ben.horgan@arm.com>
Subject: [PATCH v8 01/16] fs/resctrl: Move functions to avoid forward references in subsequent fixes
Date: Mon, 15 Jun 2026 11:24:42 -0700	[thread overview]
Message-ID: <20260615182457.14725-2-tony.luck@intel.com> (raw)
In-Reply-To: <20260615182457.14725-1-tony.luck@intel.com>

rdt_get_tree() manages resctrl fs mount and rdt_kill_sb() manages resctrl
fs unmount.

There is significant overlap between error cleanup during resctrl mount
failure and cleanup on resctrl unmount yet the cleanup is not done
consistently in these two flows.

Pull some cleanup functions before rdt_get_tree() in preparation for
a new helper that can be shared between mount and unmount.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Ben Horgan <ben.horgan@arm.com>
---
 fs/resctrl/rdtgroup.c | 376 +++++++++++++++++++++---------------------
 1 file changed, 188 insertions(+), 188 deletions(-)

diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index 5dfdaa6f9d8f..a6376a3fc4c3 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -2782,6 +2782,194 @@ static void schemata_list_destroy(void)
 	}
 }
 
+/*
+ * Move tasks from one to the other group. If @from is NULL, then all tasks
+ * in the systems are moved unconditionally (used for teardown).
+ *
+ * If @mask is not NULL the cpus on which moved tasks are running are set
+ * in that mask so the update smp function call is restricted to affected
+ * cpus.
+ */
+static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
+				 struct cpumask *mask)
+{
+	struct task_struct *p, *t;
+
+	read_lock(&tasklist_lock);
+	for_each_process_thread(p, t) {
+		if (!from || is_closid_match(t, from) ||
+		    is_rmid_match(t, from)) {
+			resctrl_arch_set_closid_rmid(t, to->closid,
+						     to->mon.rmid);
+
+			/*
+			 * Order the closid/rmid stores above before the loads
+			 * in task_curr(). This pairs with the full barrier
+			 * between the rq->curr update and
+			 * resctrl_arch_sched_in() during context switch.
+			 */
+			smp_mb();
+
+			/*
+			 * If the task is on a CPU, set the CPU in the mask.
+			 * The detection is inaccurate as tasks might move or
+			 * schedule before the smp function call takes place.
+			 * In such a case the function call is pointless, but
+			 * there is no other side effect.
+			 */
+			if (IS_ENABLED(CONFIG_SMP) && mask && task_curr(t))
+				cpumask_set_cpu(task_cpu(t), mask);
+		}
+	}
+	read_unlock(&tasklist_lock);
+}
+
+static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp)
+{
+	struct rdtgroup *sentry, *stmp;
+	struct list_head *head;
+
+	head = &rdtgrp->mon.crdtgrp_list;
+	list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) {
+		rdtgroup_unassign_cntrs(sentry);
+		free_rmid(sentry->closid, sentry->mon.rmid);
+		list_del(&sentry->mon.crdtgrp_list);
+
+		if (atomic_read(&sentry->waitcount) != 0)
+			sentry->flags = RDT_DELETED;
+		else
+			rdtgroup_remove(sentry);
+	}
+}
+
+/*
+ * Forcibly remove all of subdirectories under root.
+ */
+static void rmdir_all_sub(void)
+{
+	struct rdtgroup *rdtgrp, *tmp;
+
+	/* Move all tasks to the default resource group */
+	rdt_move_group_tasks(NULL, &rdtgroup_default, NULL);
+
+	list_for_each_entry_safe(rdtgrp, tmp, &rdt_all_groups, rdtgroup_list) {
+		/* Free any child rmids */
+		free_all_child_rdtgrp(rdtgrp);
+
+		/* Remove each rdtgroup other than root */
+		if (rdtgrp == &rdtgroup_default)
+			continue;
+
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
+			rdtgroup_pseudo_lock_remove(rdtgrp);
+
+		/*
+		 * Give any CPUs back to the default group. We cannot copy
+		 * cpu_online_mask because a CPU might have executed the
+		 * offline callback already, but is still marked online.
+		 */
+		cpumask_or(&rdtgroup_default.cpu_mask,
+			   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
+
+		rdtgroup_unassign_cntrs(rdtgrp);
+
+		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
+
+		kernfs_remove(rdtgrp->kn);
+		list_del(&rdtgrp->rdtgroup_list);
+
+		if (atomic_read(&rdtgrp->waitcount) != 0)
+			rdtgrp->flags = RDT_DELETED;
+		else
+			rdtgroup_remove(rdtgrp);
+	}
+	/* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */
+	update_closid_rmid(cpu_online_mask, &rdtgroup_default);
+
+	kernfs_remove(kn_info);
+	kernfs_remove(kn_mongrp);
+	kernfs_remove(kn_mondata);
+}
+
+/**
+ * mon_get_kn_priv() - Get the mon_data priv data for this event.
+ *
+ * The same values are used across the mon_data directories of all control and
+ * monitor groups for the same event in the same domain. Keep a list of
+ * allocated structures and re-use an existing one with the same values for
+ * @rid, @domid, etc.
+ *
+ * @rid:    The resource id for the event file being created.
+ * @domid:  The domain id for the event file being created.
+ * @mevt:   The type of event file being created.
+ * @do_sum: Whether SNC summing monitors are being created. Only set
+ *	    when @rid == RDT_RESOURCE_L3.
+ *
+ * Return: Pointer to mon_data private data of the event, NULL on failure.
+ */
+static struct mon_data *mon_get_kn_priv(enum resctrl_res_level rid, int domid,
+					struct mon_evt *mevt,
+					bool do_sum)
+{
+	struct mon_data *priv;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	list_for_each_entry(priv, &mon_data_kn_priv_list, list) {
+		if (priv->rid == rid && priv->domid == domid &&
+		    priv->sum == do_sum && priv->evt == mevt)
+			return priv;
+	}
+
+	priv = kzalloc_obj(*priv);
+	if (!priv)
+		return NULL;
+
+	priv->rid = rid;
+	priv->domid = domid;
+	priv->sum = do_sum;
+	priv->evt = mevt;
+	list_add_tail(&priv->list, &mon_data_kn_priv_list);
+
+	return priv;
+}
+
+/**
+ * mon_put_kn_priv() - Free all allocated mon_data structures.
+ *
+ * Called when resctrl file system is unmounted.
+ */
+static void mon_put_kn_priv(void)
+{
+	struct mon_data *priv, *tmp;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	list_for_each_entry_safe(priv, tmp, &mon_data_kn_priv_list, list) {
+		list_del(&priv->list);
+		kfree(priv);
+	}
+}
+
+static void resctrl_fs_teardown(void)
+{
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	/* Cleared by rdtgroup_destroy_root() */
+	if (!rdtgroup_default.kn)
+		return;
+
+	rmdir_all_sub();
+	rdtgroup_unassign_cntrs(&rdtgroup_default);
+	mon_put_kn_priv();
+	rdt_pseudo_lock_release();
+	rdtgroup_default.mode = RDT_MODE_SHAREABLE;
+	closid_exit();
+	schemata_list_destroy();
+	rdtgroup_destroy_root();
+}
+
 static int rdt_get_tree(struct fs_context *fc)
 {
 	struct rdt_fs_context *ctx = rdt_fc2context(fc);
@@ -2981,194 +3169,6 @@ static int rdt_init_fs_context(struct fs_context *fc)
 	return 0;
 }
 
-/*
- * Move tasks from one to the other group. If @from is NULL, then all tasks
- * in the systems are moved unconditionally (used for teardown).
- *
- * If @mask is not NULL the cpus on which moved tasks are running are set
- * in that mask so the update smp function call is restricted to affected
- * cpus.
- */
-static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
-				 struct cpumask *mask)
-{
-	struct task_struct *p, *t;
-
-	read_lock(&tasklist_lock);
-	for_each_process_thread(p, t) {
-		if (!from || is_closid_match(t, from) ||
-		    is_rmid_match(t, from)) {
-			resctrl_arch_set_closid_rmid(t, to->closid,
-						     to->mon.rmid);
-
-			/*
-			 * Order the closid/rmid stores above before the loads
-			 * in task_curr(). This pairs with the full barrier
-			 * between the rq->curr update and
-			 * resctrl_arch_sched_in() during context switch.
-			 */
-			smp_mb();
-
-			/*
-			 * If the task is on a CPU, set the CPU in the mask.
-			 * The detection is inaccurate as tasks might move or
-			 * schedule before the smp function call takes place.
-			 * In such a case the function call is pointless, but
-			 * there is no other side effect.
-			 */
-			if (IS_ENABLED(CONFIG_SMP) && mask && task_curr(t))
-				cpumask_set_cpu(task_cpu(t), mask);
-		}
-	}
-	read_unlock(&tasklist_lock);
-}
-
-static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp)
-{
-	struct rdtgroup *sentry, *stmp;
-	struct list_head *head;
-
-	head = &rdtgrp->mon.crdtgrp_list;
-	list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) {
-		rdtgroup_unassign_cntrs(sentry);
-		free_rmid(sentry->closid, sentry->mon.rmid);
-		list_del(&sentry->mon.crdtgrp_list);
-
-		if (atomic_read(&sentry->waitcount) != 0)
-			sentry->flags = RDT_DELETED;
-		else
-			rdtgroup_remove(sentry);
-	}
-}
-
-/*
- * Forcibly remove all of subdirectories under root.
- */
-static void rmdir_all_sub(void)
-{
-	struct rdtgroup *rdtgrp, *tmp;
-
-	/* Move all tasks to the default resource group */
-	rdt_move_group_tasks(NULL, &rdtgroup_default, NULL);
-
-	list_for_each_entry_safe(rdtgrp, tmp, &rdt_all_groups, rdtgroup_list) {
-		/* Free any child rmids */
-		free_all_child_rdtgrp(rdtgrp);
-
-		/* Remove each rdtgroup other than root */
-		if (rdtgrp == &rdtgroup_default)
-			continue;
-
-		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
-		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
-			rdtgroup_pseudo_lock_remove(rdtgrp);
-
-		/*
-		 * Give any CPUs back to the default group. We cannot copy
-		 * cpu_online_mask because a CPU might have executed the
-		 * offline callback already, but is still marked online.
-		 */
-		cpumask_or(&rdtgroup_default.cpu_mask,
-			   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
-
-		rdtgroup_unassign_cntrs(rdtgrp);
-
-		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
-
-		kernfs_remove(rdtgrp->kn);
-		list_del(&rdtgrp->rdtgroup_list);
-
-		if (atomic_read(&rdtgrp->waitcount) != 0)
-			rdtgrp->flags = RDT_DELETED;
-		else
-			rdtgroup_remove(rdtgrp);
-	}
-	/* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */
-	update_closid_rmid(cpu_online_mask, &rdtgroup_default);
-
-	kernfs_remove(kn_info);
-	kernfs_remove(kn_mongrp);
-	kernfs_remove(kn_mondata);
-}
-
-/**
- * mon_get_kn_priv() - Get the mon_data priv data for this event.
- *
- * The same values are used across the mon_data directories of all control and
- * monitor groups for the same event in the same domain. Keep a list of
- * allocated structures and re-use an existing one with the same values for
- * @rid, @domid, etc.
- *
- * @rid:    The resource id for the event file being created.
- * @domid:  The domain id for the event file being created.
- * @mevt:   The type of event file being created.
- * @do_sum: Whether SNC summing monitors are being created. Only set
- *	    when @rid == RDT_RESOURCE_L3.
- *
- * Return: Pointer to mon_data private data of the event, NULL on failure.
- */
-static struct mon_data *mon_get_kn_priv(enum resctrl_res_level rid, int domid,
-					struct mon_evt *mevt,
-					bool do_sum)
-{
-	struct mon_data *priv;
-
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	list_for_each_entry(priv, &mon_data_kn_priv_list, list) {
-		if (priv->rid == rid && priv->domid == domid &&
-		    priv->sum == do_sum && priv->evt == mevt)
-			return priv;
-	}
-
-	priv = kzalloc_obj(*priv);
-	if (!priv)
-		return NULL;
-
-	priv->rid = rid;
-	priv->domid = domid;
-	priv->sum = do_sum;
-	priv->evt = mevt;
-	list_add_tail(&priv->list, &mon_data_kn_priv_list);
-
-	return priv;
-}
-
-/**
- * mon_put_kn_priv() - Free all allocated mon_data structures.
- *
- * Called when resctrl file system is unmounted.
- */
-static void mon_put_kn_priv(void)
-{
-	struct mon_data *priv, *tmp;
-
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	list_for_each_entry_safe(priv, tmp, &mon_data_kn_priv_list, list) {
-		list_del(&priv->list);
-		kfree(priv);
-	}
-}
-
-static void resctrl_fs_teardown(void)
-{
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	/* Cleared by rdtgroup_destroy_root() */
-	if (!rdtgroup_default.kn)
-		return;
-
-	rmdir_all_sub();
-	rdtgroup_unassign_cntrs(&rdtgroup_default);
-	mon_put_kn_priv();
-	rdt_pseudo_lock_release();
-	rdtgroup_default.mode = RDT_MODE_SHAREABLE;
-	closid_exit();
-	schemata_list_destroy();
-	rdtgroup_destroy_root();
-}
-
 static void rdt_kill_sb(struct super_block *sb)
 {
 	struct rdt_resource *r;
-- 
2.54.0


  reply	other threads:[~2026-06-15 18:25 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-06-15 18:24 [PATCH v8 00/16] Allow AET to use PMT as loadable module Tony Luck
2026-06-15 18:24 ` Tony Luck [this message]
2026-06-15 18:24 ` [PATCH v8 02/16] fs/resctrl: Free mon_data structures on rdt_get_tree() failure Tony Luck
2026-06-15 18:24 ` [PATCH v8 03/16] fs/resctrl: Fix use-after-free during unmount Tony Luck
2026-06-15 18:24 ` [PATCH v8 04/16] fs/resctrl: Fix deadlock on errors during mount Tony Luck
2026-06-15 18:24 ` [PATCH v8 05/16] platform/x86/intel/pmt: Prevent unbind of PMT telemetry driver Tony Luck
2026-06-15 18:24 ` [PATCH v8 06/16] fs/resctrl: Remove redundant calls to resctrl_arch_mon_capable() Tony Luck
2026-06-15 18:24 ` [PATCH v8 07/16] x86/resctrl: Honor rdt=perf option to force enable AET perf events Tony Luck
2026-06-15 18:24 ` [PATCH v8 08/16] fs/resctrl: Add interface to disable a monitor event Tony Luck
2026-06-15 18:24 ` [PATCH v8 09/16] x86/resctrl: Drop global 'rdt_mon_capable' flag Tony Luck
2026-06-15 18:24 ` [PATCH v8 10/16] arm,x86,fs/resctrl: Handle change in number of RMIDs on each mount Tony Luck
2026-06-15 18:24 ` [PATCH v8 11/16] x86/resctrl: Add PMT registration API for AET enumeration callbacks Tony Luck
2026-06-15 18:24 ` [PATCH v8 12/16] platform/x86/intel/pmt: Register enumeration functions with resctrl Tony Luck
2026-06-15 18:24 ` [PATCH v8 13/16] arm,x86/resctrl: Resolve INTEL_PMT_TELEMETRY symbols at runtime Tony Luck
2026-06-15 18:24 ` [PATCH v8 14/16] fs/resctrl: Call architecture hooks for every mount/unmount Tony Luck
2026-06-15 18:24 ` [PATCH v8 15/16] x86/resctrl: Simplify Kconfig options for resctrl Tony Luck
2026-06-15 18:24 ` [PATCH v8 16/16] Documentation/filesystems/resctrl: Add footnote for telemetry fstab mount caveat Tony Luck
2026-06-16 17:50 ` [PATCH v8 00/16] Allow AET to use PMT as loadable module Luck, Tony

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260615182457.14725-2-tony.luck@intel.com \
    --to=tony.luck@intel.com \
    --cc=Dave.Martin@arm.com \
    --cc=babu.moger@amd.com \
    --cc=ben.horgan@arm.com \
    --cc=david.e.box@intel.com \
    --cc=dfustini@baylibre.com \
    --cc=fenghuay@nvidia.com \
    --cc=hch@infradead.org \
    --cc=james.morse@arm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=maciej.wieczor-retman@intel.com \
    --cc=patches@lists.linux.dev \
    --cc=peternewman@google.com \
    --cc=reinette.chatre@intel.com \
    --cc=x86@kernel.org \
    --cc=yu.c.chen@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

Powered by JetHome