linux-kernel - [PATCH v3 17/29] arm_mpam: Extend reset logic to allow devices to be reset any time

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 for Android: free password hash cracker in your pocket

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

Message-Id: <20251017185645.26604-18-james.morse@arm.com>
Date: Fri, 17 Oct 2025 18:56:33 +0000
From: James Morse <james.morse@....com>
To: linux-kernel@...r.kernel.org,
	linux-arm-kernel@...ts.infradead.org,
	linux-acpi@...r.kernel.org
Cc: James Morse <james.morse@....com>,
	D Scott Phillips OS <scott@...amperecomputing.com>,
	carl@...amperecomputing.com,
	lcherian@...vell.com,
	bobo.shaobowang@...wei.com,
	tan.shaopeng@...itsu.com,
	baolin.wang@...ux.alibaba.com,
	Jamie Iles <quic_jiles@...cinc.com>,
	Xin Hao <xhao@...ux.alibaba.com>,
	peternewman@...gle.com,
	dfustini@...libre.com,
	amitsinght@...vell.com,
	David Hildenbrand <david@...hat.com>,
	Dave Martin <dave.martin@....com>,
	Koba Ko <kobak@...dia.com>,
	Shanker Donthineni <sdonthineni@...dia.com>,
	fenghuay@...dia.com,
	baisheng.gao@...soc.com,
	Jonathan Cameron <jonathan.cameron@...wei.com>,
	Rob Herring <robh@...nel.org>,
	Rohit Mathew <rohit.mathew@....com>,
	Rafael Wysocki <rafael@...nel.org>,
	Len Brown <lenb@...nel.org>,
	Lorenzo Pieralisi <lpieralisi@...nel.org>,
	Hanjun Guo <guohanjun@...wei.com>,
	Sudeep Holla <sudeep.holla@....com>,
	Catalin Marinas <catalin.marinas@....com>,
	Will Deacon <will@...nel.org>,
	Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
	Danilo Krummrich <dakr@...nel.org>,
	Jeremy Linton <jeremy.linton@....com>,
	Gavin Shan <gshan@...hat.com>,
	Ben Horgan <ben.horgan@....com>
Subject: [PATCH v3 17/29] arm_mpam: Extend reset logic to allow devices to be reset any time

cpuhp callbacks aren't the only time the MSC configuration may need to
be reset. Resctrl has an API call to reset a class.
If an MPAM error interrupt arrives it indicates the driver has
misprogrammed an MSC. The safest thing to do is reset all the MSCs
and disable MPAM.

Add a helper to reset RIS via their class. Call this from mpam_disable(),
which can be scheduled from the error interrupt handler.

Signed-off-by: James Morse <james.morse@....com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@...wei.com>
Reviewed-by: Ben Horgan <ben.horgan@....com>
Tested-by: Fenghua Yu <fenghuay@...dia.com>
---
Changes since v2:
 * Reduced the scop of arguments in mpam_reset_component_locked().

Changes since v1:
 * more complete use of _srcu helpers.
 * Use guard macro for srcu.
 * Dropped a might_sleep() - something else will bark.
---
 drivers/resctrl/mpam_devices.c | 58 ++++++++++++++++++++++++++++++++--
 1 file changed, 55 insertions(+), 3 deletions(-)

diff --git a/drivers/resctrl/mpam_devices.c b/drivers/resctrl/mpam_devices.c
index ec089593acad..545482e112b7 100644
--- a/drivers/resctrl/mpam_devices.c
+++ b/drivers/resctrl/mpam_devices.c
@@ -802,15 +802,13 @@ static void mpam_reset_ris_partid(struct mpam_msc_ris *ris, u16 partid)
 
 /*
  * Called via smp_call_on_cpu() to prevent migration, while still being
- * pre-emptible.
+ * pre-emptible. Caller must hold mpam_srcu.
  */
 static int mpam_reset_ris(void *arg)
 {
 	u16 partid, partid_max;
 	struct mpam_msc_ris *ris = arg;
 
-	WARN_ON_ONCE(!srcu_read_lock_held((&mpam_srcu)));
-
 	if (ris->in_reset_state)
 		return 0;
 
@@ -1328,8 +1326,56 @@ static void mpam_enable_once(void)
 	       mpam_partid_max + 1, mpam_pmg_max + 1);
 }
 
+static void mpam_reset_component_locked(struct mpam_component *comp)
+{
+
+	struct mpam_vmsc *vmsc;
+
+	lockdep_assert_cpus_held();
+
+	guard(srcu)(&mpam_srcu);
+	list_for_each_entry_srcu(vmsc, &comp->vmsc, comp_list,
+				 srcu_read_lock_held(&mpam_srcu)) {
+		struct mpam_msc *msc = vmsc->msc;
+		struct mpam_msc_ris *ris;
+
+		list_for_each_entry_srcu(ris, &vmsc->ris, vmsc_list,
+					 srcu_read_lock_held(&mpam_srcu)) {
+			if (!ris->in_reset_state)
+				mpam_touch_msc(msc, mpam_reset_ris, ris);
+			ris->in_reset_state = true;
+		}
+	}
+}
+
+static void mpam_reset_class_locked(struct mpam_class *class)
+{
+	struct mpam_component *comp;
+
+	lockdep_assert_cpus_held();
+
+	guard(srcu)(&mpam_srcu);
+	list_for_each_entry_srcu(comp, &class->components, class_list,
+				 srcu_read_lock_held(&mpam_srcu))
+		mpam_reset_component_locked(comp);
+}
+
+static void mpam_reset_class(struct mpam_class *class)
+{
+	cpus_read_lock();
+	mpam_reset_class_locked(class);
+	cpus_read_unlock();
+}
+
+/*
+ * Called in response to an error IRQ.
+ * All of MPAMs errors indicate a software bug, restore any modified
+ * controls to their reset values.
+ */
 void mpam_disable(struct work_struct *ignored)
 {
+	int idx;
+	struct mpam_class *class;
 	struct mpam_msc *msc, *tmp;
 
 	mutex_lock(&mpam_cpuhp_state_lock);
@@ -1339,6 +1385,12 @@ void mpam_disable(struct work_struct *ignored)
 	}
 	mutex_unlock(&mpam_cpuhp_state_lock);
 
+	idx = srcu_read_lock(&mpam_srcu);
+	list_for_each_entry_srcu(class, &mpam_classes, classes_list,
+				 srcu_read_lock_held(&mpam_srcu))
+		mpam_reset_class(class);
+	srcu_read_unlock(&mpam_srcu, idx);
+
 	mutex_lock(&mpam_list_lock);
 	list_for_each_entry_safe(msc, tmp, &mpam_all_msc, all_msc_list)
 		mpam_msc_destroy(msc);
-- 
2.39.5