linux-kernel - [PATCH 6/6] genirq: soft_moderation: implement per-driver defaults (nvme and vfio)

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: <20251112192408.3646835-7-lrizzo@google.com>
Date: Wed, 12 Nov 2025 19:24:08 +0000
From: Luigi Rizzo <lrizzo@...gle.com>
To: Thomas Gleixner <tglx@...utronix.de>, Marc Zyngier <maz@...nel.org>, 
	Luigi Rizzo <rizzo.unipi@...il.com>, Paolo Abeni <pabeni@...hat.com>, 
	Andrew Morton <akpm@...ux-foundation.org>, Sean Christopherson <seanjc@...gle.com>, 
	Jacob Pan <jacob.jun.pan@...ux.intel.com>
Cc: linux-kernel@...r.kernel.org, linux-arch@...r.kernel.org, 
	Bjorn Helgaas <bhelgaas@...gle.com>, Willem de Bruijn <willemb@...gle.com>, 
	Luigi Rizzo <lrizzo@...gle.com>
Subject: [PATCH 6/6] genirq: soft_moderation: implement per-driver defaults
 (nvme and vfio)

Introduce helpers to implement per-driver module parameters to enable
moderation at boot/probe time.

As an example, use the helpers in nvme and vfio drivers.

To test, boot a kernel with

${driver}.soft_moderation=1 # enables moderation.

and verify with "cat /proc/irq/soft_moderation" that
the counters increase.

Change-Id: Iaad4110977deb96df845501895e0043bd93fc350
---
 drivers/nvme/host/pci.c           |  3 +++
 drivers/vfio/pci/vfio_pci_intrs.c |  3 +++
 include/linux/interrupt.h         | 13 +++++++++++++
 kernel/irq/irq_moderation.c       | 11 +++++++++++
 4 files changed, 30 insertions(+)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 72fb675a696f4..b9d7bce30061f 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -72,6 +72,8 @@
 static_assert(MAX_PRP_RANGE / NVME_CTRL_PAGE_SIZE <=
 	(1 /* prp1 */ + NVME_MAX_NR_DESCRIPTORS * PRPS_PER_PAGE));
 
+DEFINE_IRQ_MODERATION_MODE_PARAMETER;
+
 static int use_threaded_interrupts;
 module_param(use_threaded_interrupts, int, 0444);
 
@@ -1989,6 +1991,7 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled)
 		result = queue_request_irq(nvmeq);
 		if (result < 0)
 			goto release_sq;
+		IRQ_MODERATION_SET_DEFAULT_MODE(pci_irq_vector(to_pci_dev(dev->dev), vector));
 	}
 
 	set_bit(NVMEQ_ENABLED, &nvmeq->flags);
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index 30d3e921cb0de..e54d88cfe601d 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -22,6 +22,8 @@
 
 #include "vfio_pci_priv.h"
 
+DEFINE_IRQ_MODERATION_MODE_PARAMETER;
+
 struct vfio_pci_irq_ctx {
 	struct vfio_pci_core_device	*vdev;
 	struct eventfd_ctx		*trigger;
@@ -317,6 +319,7 @@ static int vfio_intx_enable(struct vfio_pci_core_device *vdev,
 		vfio_irq_ctx_free(vdev, ctx, 0);
 		return ret;
 	}
+	IRQ_MODERATION_SET_DEFAULT_MODE(pdev->irq);
 
 	return 0;
 }
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 007201c8db6dd..c7d68d8ec49d7 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -879,12 +879,25 @@ void irq_moderation_init_fields(struct irq_desc *desc);
 /* add/remove /proc/irq/NN/soft_moderation */
 void irq_moderation_procfs_entry(struct irq_desc *desc, umode_t umode);
 
+/* helpers for per-driver moderation mode settings */
+#define DEFINE_IRQ_MODERATION_MODE_PARAMETER		\
+	static bool soft_moderation;			\
+	module_param(soft_moderation, bool, 0644);	\
+	MODULE_PARM_DESC(soft_moderation, "0: off, 1: disable_irq")
+
+void irq_moderation_set_mode(int irq, bool mode);
+#define IRQ_MODERATION_SET_DEFAULT_MODE(_irq)		\
+	irq_moderation_set_mode(_irq, READ_ONCE(soft_moderation))
+
 #else   /* empty stubs to avoid conditional compilation */
 
 static inline void irq_moderation_percpu_init(void) {}
 static inline void irq_moderation_init_fields(struct irq_desc *desc) {}
 static inline void irq_moderation_procfs_entry(struct irq_desc *desc, umode_t umode) {};
 
+#define DEFINE_IRQ_MODERATION_MODE_PARAMETER
+#define IRQ_MODERATION_SET_DEFAULT_MODE(_irq)
+
 #endif
 
 /*
diff --git a/kernel/irq/irq_moderation.c b/kernel/irq/irq_moderation.c
index 672e161ecf29e..3b3962dae33d1 100644
--- a/kernel/irq/irq_moderation.c
+++ b/kernel/irq/irq_moderation.c
@@ -83,6 +83,10 @@ static bool enable_posted_msi;
  *
  *    echo "on" > /proc/irq/NN/soft_moderation # use "off" to disable
  *
+ * For selected drivers, the default can also be supplied via module parameters
+ *
+ *	${DRIVER}.soft_moderation=1
+ *
  * === MONITORING ===
  *
  * cat /proc/irq/soft_moderation shows per-CPU and global statistics.
@@ -302,6 +306,13 @@ static void set_moderation_mode(struct irq_desc *desc, bool mode)
 	}
 }
 
+/* irq_to_desc is not exported. Wrap it in this function for a specific use. */
+void irq_moderation_set_mode(int irq, bool mode)
+{
+	set_moderation_mode(irq_to_desc(irq), mode);
+}
+EXPORT_SYMBOL(irq_moderation_set_mode);
+
 #pragma clang diagnostic error "-Wformat"
 /* Print statistics */
 static int moderation_show(struct seq_file *p, void *v)
-- 
2.51.2.1041.gc1ab5b90ca-goog