linux-kernel - [PATCH 20/33] 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: Windows password security audit tool. GUI, reports in PDF.

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

Message-ID: <20251107123450.664001-21-ben.horgan@arm.com>
Date: Fri,  7 Nov 2025 12:34:37 +0000
From: Ben Horgan <ben.horgan@....com>
To: james.morse@....com
Cc: amitsinght@...vell.com,
	baisheng.gao@...soc.com,
	baolin.wang@...ux.alibaba.com,
	bobo.shaobowang@...wei.com,
	carl@...amperecomputing.com,
	catalin.marinas@....com,
	dakr@...nel.org,
	dave.martin@....com,
	david@...hat.com,
	dfustini@...libre.com,
	fenghuay@...dia.com,
	gregkh@...uxfoundation.org,
	gshan@...hat.com,
	guohanjun@...wei.com,
	jeremy.linton@....com,
	jonathan.cameron@...wei.com,
	kobak@...dia.com,
	lcherian@...vell.com,
	lenb@...nel.org,
	linux-acpi@...r.kernel.org,
	linux-arm-kernel@...ts.infradead.org,
	linux-kernel@...r.kernel.org,
	lpieralisi@...nel.org,
	peternewman@...gle.com,
	quic_jiles@...cinc.com,
	rafael@...nel.org,
	robh@...nel.org,
	rohit.mathew@....com,
	scott@...amperecomputing.com,
	sdonthineni@...dia.com,
	sudeep.holla@....com,
	tan.shaopeng@...itsu.com,
	will@...nel.org,
	xhao@...ux.alibaba.com,
	Ben Horgan <ben.horgan@....com>,
	Shaopeng Tan <tan.shaopeng@...fujitsu.com>
Subject: [PATCH 20/33] arm_mpam: Extend reset logic to allow devices to be reset any time

From: James Morse <james.morse@....com>

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>
Tested-by: Shaopeng Tan <tan.shaopeng@...fujitsu.com>
Tested-by: Peter Newman <peternewman@...gle.com>
Signed-off-by: Ben Horgan <ben.horgan@....com>
---
 drivers/resctrl/mpam_devices.c | 57 ++++++++++++++++++++++++++++++++--
 1 file changed, 54 insertions(+), 3 deletions(-)

diff --git a/drivers/resctrl/mpam_devices.c b/drivers/resctrl/mpam_devices.c
index bcdf4fbc3941..a8efd3e02c62 100644
--- a/drivers/resctrl/mpam_devices.c
+++ b/drivers/resctrl/mpam_devices.c
@@ -809,15 +809,13 @@ 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;
 
@@ -1341,8 +1339,55 @@ 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);
@@ -1352,6 +1397,12 @@ 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);
-- 
2.43.0