* [RFC PATCH v2 4/4] virtio-mmio: wire up noirq system sleep PM callbacks
From: Sungho Bae @ 2026-04-17 13:34 UTC (permalink / raw)
To: mst, jasowang
Cc: xuanzhuo, eperezma, virtualization, linux-kernel, Sungho Bae
In-Reply-To: <20260417133430.507-1-baver.bae@gmail.com>
From: Sungho Bae <baver.bae@lge.com>
Implement the transport side of noirq system-sleep PM for virtio-mmio:
- vm_reset_vqs(): iterate all virtqueues, call virtqueue_reinit_vring()
to reset the vring state in place, then reprogram the MMIO queue
registers (QUEUE_SEL, QUEUE_NUM, descriptor/avail/used addresses,
QUEUE_READY) so the device can use the same rings immediately after
restore. No memory is allocated or freed.
- virtio_mmio_freeze_noirq() / virtio_mmio_restore_noirq(): thin
wrappers that forward to the virtio core noirq helpers. The
restore_noirq path also writes GUEST_PAGE_SIZE for legacy (v1)
devices, matching the existing restore callback.
- Wire vm_reset_vqs into virtio_mmio_config_ops and register the
noirq callbacks via SET_NOIRQ_SYSTEM_SLEEP_PM_OPS().
With this in place, a virtio-mmio driver can implement freeze_noirq /
restore_noirq to participate in the noirq PM phase, enabling use cases
such as virtio-clock or virtio-regulator that must be operational
before other devices are restored.
Signed-off-by: Sungho Bae <baver.bae@lge.com>
---
drivers/virtio/virtio_mmio.c | 131 ++++++++++++++++++++++++-----------
1 file changed, 92 insertions(+), 39 deletions(-)
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index 595c2274fbb5..7cde042e15ac 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -336,6 +336,75 @@ static void vm_del_vqs(struct virtio_device *vdev)
free_irq(platform_get_irq(vm_dev->pdev, 0), vm_dev);
}
+static int vm_active_vq(struct virtio_device *vdev, struct virtqueue *vq)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+ int q_num = virtqueue_get_vring_size(vq);
+
+ writel(q_num, vm_dev->base + VIRTIO_MMIO_QUEUE_NUM);
+ if (vm_dev->version == 1) {
+ u64 q_pfn = virtqueue_get_desc_addr(vq) >> PAGE_SHIFT;
+
+ /*
+ * virtio-mmio v1 uses a 32bit QUEUE PFN. If we have something
+ * that doesn't fit in 32bit, fail the setup rather than
+ * pretending to be successful.
+ */
+ if (q_pfn >> 32) {
+ dev_err(&vdev->dev,
+ "platform bug: legacy virtio-mmio must not be used with RAM above 0x%llxGB\n",
+ 0x1ULL << (32 + PAGE_SHIFT - 30));
+ return -E2BIG;
+ }
+
+ writel(PAGE_SIZE, vm_dev->base + VIRTIO_MMIO_QUEUE_ALIGN);
+ writel(q_pfn, vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
+ } else {
+ u64 addr;
+
+ addr = virtqueue_get_desc_addr(vq);
+ writel((u32)addr, vm_dev->base + VIRTIO_MMIO_QUEUE_DESC_LOW);
+ writel((u32)(addr >> 32),
+ vm_dev->base + VIRTIO_MMIO_QUEUE_DESC_HIGH);
+
+ addr = virtqueue_get_avail_addr(vq);
+ writel((u32)addr, vm_dev->base + VIRTIO_MMIO_QUEUE_AVAIL_LOW);
+ writel((u32)(addr >> 32),
+ vm_dev->base + VIRTIO_MMIO_QUEUE_AVAIL_HIGH);
+
+ addr = virtqueue_get_used_addr(vq);
+ writel((u32)addr, vm_dev->base + VIRTIO_MMIO_QUEUE_USED_LOW);
+ writel((u32)(addr >> 32),
+ vm_dev->base + VIRTIO_MMIO_QUEUE_USED_HIGH);
+
+ writel(1, vm_dev->base + VIRTIO_MMIO_QUEUE_READY);
+ }
+
+ return 0;
+}
+
+static int vm_reset_vqs(struct virtio_device *vdev)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+ struct virtqueue *vq;
+ int err;
+
+ virtio_device_for_each_vq(vdev, vq) {
+ /* Re-init vring */
+ virtqueue_reinit_vring(vq);
+
+ /* Select the queue we're interested in */
+ writel(vq->index, vm_dev->base + VIRTIO_MMIO_QUEUE_SEL);
+
+ /* Activate the queue */
+ err = vm_active_vq(vdev, vq);
+ if (err < 0)
+ return err;
+ }
+
+ return 0;
+}
+
static void vm_synchronize_cbs(struct virtio_device *vdev)
{
struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
@@ -388,45 +457,9 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned int in
vq->num_max = num;
/* Activate the queue */
- writel(virtqueue_get_vring_size(vq), vm_dev->base + VIRTIO_MMIO_QUEUE_NUM);
- if (vm_dev->version == 1) {
- u64 q_pfn = virtqueue_get_desc_addr(vq) >> PAGE_SHIFT;
-
- /*
- * virtio-mmio v1 uses a 32bit QUEUE PFN. If we have something
- * that doesn't fit in 32bit, fail the setup rather than
- * pretending to be successful.
- */
- if (q_pfn >> 32) {
- dev_err(&vdev->dev,
- "platform bug: legacy virtio-mmio must not be used with RAM above 0x%llxGB\n",
- 0x1ULL << (32 + PAGE_SHIFT - 30));
- err = -E2BIG;
- goto error_bad_pfn;
- }
-
- writel(PAGE_SIZE, vm_dev->base + VIRTIO_MMIO_QUEUE_ALIGN);
- writel(q_pfn, vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
- } else {
- u64 addr;
-
- addr = virtqueue_get_desc_addr(vq);
- writel((u32)addr, vm_dev->base + VIRTIO_MMIO_QUEUE_DESC_LOW);
- writel((u32)(addr >> 32),
- vm_dev->base + VIRTIO_MMIO_QUEUE_DESC_HIGH);
-
- addr = virtqueue_get_avail_addr(vq);
- writel((u32)addr, vm_dev->base + VIRTIO_MMIO_QUEUE_AVAIL_LOW);
- writel((u32)(addr >> 32),
- vm_dev->base + VIRTIO_MMIO_QUEUE_AVAIL_HIGH);
-
- addr = virtqueue_get_used_addr(vq);
- writel((u32)addr, vm_dev->base + VIRTIO_MMIO_QUEUE_USED_LOW);
- writel((u32)(addr >> 32),
- vm_dev->base + VIRTIO_MMIO_QUEUE_USED_HIGH);
-
- writel(1, vm_dev->base + VIRTIO_MMIO_QUEUE_READY);
- }
+ err = vm_active_vq(vdev, vq);
+ if (err < 0)
+ goto error_bad_pfn;
return vq;
@@ -528,6 +561,7 @@ static const struct virtio_config_ops virtio_mmio_config_ops = {
.reset = vm_reset,
.find_vqs = vm_find_vqs,
.del_vqs = vm_del_vqs,
+ .reset_vqs = vm_reset_vqs,
.get_features = vm_get_features,
.finalize_features = vm_finalize_features,
.bus_name = vm_bus_name,
@@ -553,8 +587,27 @@ static int virtio_mmio_restore(struct device *dev)
return virtio_device_restore(&vm_dev->vdev);
}
+static int virtio_mmio_freeze_noirq(struct device *dev)
+{
+ struct virtio_mmio_device *vm_dev = dev_get_drvdata(dev);
+
+ return virtio_device_freeze_noirq(&vm_dev->vdev);
+}
+
+static int virtio_mmio_restore_noirq(struct device *dev)
+{
+ struct virtio_mmio_device *vm_dev = dev_get_drvdata(dev);
+
+ if (vm_dev->version == 1)
+ writel(PAGE_SIZE, vm_dev->base + VIRTIO_MMIO_GUEST_PAGE_SIZE);
+
+ return virtio_device_restore_noirq(&vm_dev->vdev);
+}
+
static const struct dev_pm_ops virtio_mmio_pm_ops = {
SET_SYSTEM_SLEEP_PM_OPS(virtio_mmio_freeze, virtio_mmio_restore)
+ SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(virtio_mmio_freeze_noirq,
+ virtio_mmio_restore_noirq)
};
#endif
--
2.43.0
^ permalink raw reply related
* [RFC PATCH v2 3/4] virtio: add noirq system sleep PM infrastructure
From: Sungho Bae @ 2026-04-17 13:34 UTC (permalink / raw)
To: mst, jasowang
Cc: xuanzhuo, eperezma, virtualization, linux-kernel, Sungho Bae
In-Reply-To: <20260417133430.507-1-baver.bae@gmail.com>
From: Sungho Bae <baver.bae@lge.com>
Some virtio-mmio devices, such as virtio-clock or virtio-regulator,
must become operational before the regular PM restore callback runs
because other devices may depend on them.
Add the core infrastructure needed to support noirq system-sleep PM
callbacks for virtio transports:
- virtio_add_status_noirq(): status helper without might_sleep().
- virtio_features_ok_noirq(): feature negotiation without might_sleep().
- virtio_reset_device_noirq(): device reset that skips
virtio_synchronize_cbs() (IRQ handlers are already quiesced in the
noirq phase).
- virtio_device_reinit_noirq(): full noirq bring-up sequence using the
above helpers.
- virtio_config_core_enable_noirq(): config enable with irqsave
locking.
- virtio_device_ready_noirq(): marks DRIVER_OK without
virtio_synchronize_cbs().
Add freeze_noirq/restore_noirq callbacks to struct virtio_driver and
provide matching helper wrappers in the virtio core:
- virtio_device_freeze_noirq(): forwards to drv->freeze_noirq().
- virtio_device_restore_noirq(): runs the noirq bring-up sequence,
resets existing vrings via the new config_ops->reset_vqs() hook,
then calls drv->restore_noirq().
Modify virtio_device_restore() so that when a driver provides
restore_noirq, the normal-phase restore skips the re-initialization
that was already done in the noirq phase.
Signed-off-by: Sungho Bae <baver.bae@lge.com>
---
drivers/virtio/virtio.c | 172 +++++++++++++++++++++++++++++++++-
include/linux/virtio.h | 8 ++
include/linux/virtio_config.h | 29 ++++++
3 files changed, 206 insertions(+), 3 deletions(-)
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index b0668434ac21..4fcb6b8c797f 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -193,6 +193,17 @@ static void virtio_config_core_enable(struct virtio_device *dev)
spin_unlock_irq(&dev->config_lock);
}
+static void virtio_config_core_enable_noirq(struct virtio_device *dev)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&dev->config_lock, flags);
+ dev->config_core_enabled = true;
+ if (dev->config_change_pending)
+ __virtio_config_changed(dev);
+ spin_unlock_irqrestore(&dev->config_lock, flags);
+}
+
void virtio_add_status(struct virtio_device *dev, unsigned int status)
{
might_sleep();
@@ -200,6 +211,20 @@ void virtio_add_status(struct virtio_device *dev, unsigned int status)
}
EXPORT_SYMBOL_GPL(virtio_add_status);
+/*
+ * Same as virtio_add_status() but without the might_sleep() assertion,
+ * so it is safe to call from noirq context.
+ *
+ * This assumes that the device's get_status and set_status operations are
+ * also noirq-safe. Therefore, the device must garantee that get_status and
+ * set_status can be called from noirq context.
+ */
+void virtio_add_status_noirq(struct virtio_device *dev, unsigned int status)
+{
+ dev->config->set_status(dev, dev->config->get_status(dev) | status);
+}
+EXPORT_SYMBOL_GPL(virtio_add_status_noirq);
+
/* Do some validation, then set FEATURES_OK */
static int virtio_features_ok(struct virtio_device *dev)
{
@@ -234,6 +259,38 @@ static int virtio_features_ok(struct virtio_device *dev)
return 0;
}
+/* noirq-safe variant: no might_sleep(), uses virtio_add_status_noirq() */
+static int virtio_features_ok_noirq(struct virtio_device *dev)
+{
+ unsigned int status;
+
+ if (virtio_check_mem_acc_cb(dev)) {
+ if (!virtio_has_feature(dev, VIRTIO_F_VERSION_1)) {
+ dev_warn(&dev->dev,
+ "device must provide VIRTIO_F_VERSION_1\n");
+ return -ENODEV;
+ }
+
+ if (!virtio_has_feature(dev, VIRTIO_F_ACCESS_PLATFORM)) {
+ dev_warn(&dev->dev,
+ "device must provide VIRTIO_F_ACCESS_PLATFORM\n");
+ return -ENODEV;
+ }
+ }
+
+ if (!virtio_has_feature(dev, VIRTIO_F_VERSION_1))
+ return 0;
+
+ virtio_add_status_noirq(dev, VIRTIO_CONFIG_S_FEATURES_OK);
+ status = dev->config->get_status(dev);
+ if (!(status & VIRTIO_CONFIG_S_FEATURES_OK)) {
+ dev_err(&dev->dev, "virtio: device refuses features: %x\n",
+ status);
+ return -ENODEV;
+ }
+ return 0;
+}
+
/**
* virtio_reset_device - quiesce device for removal
* @dev: the device to reset
@@ -267,6 +324,24 @@ void virtio_reset_device(struct virtio_device *dev)
}
EXPORT_SYMBOL_GPL(virtio_reset_device);
+/**
+ * virtio_reset_device_noirq - noirq-safe variant of virtio_reset_device()
+ * @dev: the device to reset
+ */
+void virtio_reset_device_noirq(struct virtio_device *dev)
+{
+#ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION
+ /*
+ * The noirq stage runs with device IRQ handlers disabled, so
+ * virtio_synchronize_cbs() must not be called here.
+ */
+ virtio_break_device(dev);
+#endif
+
+ dev->config->reset(dev);
+}
+EXPORT_SYMBOL_GPL(virtio_reset_device_noirq);
+
static int virtio_dev_probe(struct device *_d)
{
int err, i;
@@ -618,6 +693,41 @@ static int virtio_device_reinit(struct virtio_device *dev)
return virtio_features_ok(dev);
}
+/* noirq-safe variant of virtio_device_reinit() */
+static int virtio_device_reinit_noirq(struct virtio_device *dev)
+{
+ struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+ int ret;
+
+ /*
+ * We always start by resetting the device, in case a previous
+ * driver messed it up.
+ */
+ virtio_reset_device_noirq(dev);
+
+ /* Acknowledge that we've seen the device. */
+ virtio_add_status_noirq(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
+
+ /*
+ * Maybe driver failed before freeze.
+ * Restore the failed status, for debugging.
+ */
+ if (dev->failed)
+ virtio_add_status_noirq(dev, VIRTIO_CONFIG_S_FAILED);
+
+ if (!drv)
+ return 0;
+
+ /* We have a driver! */
+ virtio_add_status_noirq(dev, VIRTIO_CONFIG_S_DRIVER);
+
+ ret = dev->config->finalize_features(dev);
+ if (ret)
+ return ret;
+
+ return virtio_features_ok_noirq(dev);
+}
+
#ifdef CONFIG_PM_SLEEP
int virtio_device_freeze(struct virtio_device *dev)
{
@@ -645,9 +755,15 @@ int virtio_device_restore(struct virtio_device *dev)
struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
int ret;
- ret = virtio_device_reinit(dev);
- if (ret)
- goto err;
+ /*
+ * If this device was already brought up in the noirq phase,
+ * skip the re-initialization here.
+ */
+ if (!drv || !drv->restore_noirq) {
+ ret = virtio_device_reinit(dev);
+ if (ret)
+ goto err;
+ }
if (drv && drv->restore) {
ret = drv->restore(dev);
@@ -668,6 +784,56 @@ int virtio_device_restore(struct virtio_device *dev)
return ret;
}
EXPORT_SYMBOL_GPL(virtio_device_restore);
+
+int virtio_device_freeze_noirq(struct virtio_device *dev)
+{
+ struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+
+ if (drv && drv->freeze_noirq)
+ return drv->freeze_noirq(dev);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_device_freeze_noirq);
+
+int virtio_device_restore_noirq(struct virtio_device *dev)
+{
+ struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+ int ret;
+
+ if (!drv || !drv->restore_noirq)
+ return 0;
+
+ ret = virtio_device_reinit_noirq(dev);
+ if (ret)
+ goto err;
+
+ if (!list_empty(&dev->vqs)) {
+ if (!dev->config->reset_vqs) {
+ ret = -EOPNOTSUPP;
+ goto err;
+ }
+
+ ret = dev->config->reset_vqs(dev);
+ if (ret)
+ goto err;
+ }
+
+ ret = drv->restore_noirq(dev);
+ if (ret)
+ goto err;
+
+ /* If restore_noirq set DRIVER_OK, enable config now. */
+ if (dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK)
+ virtio_config_core_enable_noirq(dev);
+
+ return 0;
+
+err:
+ virtio_add_status_noirq(dev, VIRTIO_CONFIG_S_FAILED);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(virtio_device_restore_noirq);
#endif
int virtio_device_reset_prepare(struct virtio_device *dev)
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 3bbc4cb6a672..31267334e4de 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -209,8 +209,12 @@ void virtio_config_driver_enable(struct virtio_device *dev);
#ifdef CONFIG_PM_SLEEP
int virtio_device_freeze(struct virtio_device *dev);
int virtio_device_restore(struct virtio_device *dev);
+int virtio_device_freeze_noirq(struct virtio_device *dev);
+int virtio_device_restore_noirq(struct virtio_device *dev);
#endif
void virtio_reset_device(struct virtio_device *dev);
+void virtio_reset_device_noirq(struct virtio_device *dev);
+void virtio_add_status_noirq(struct virtio_device *dev, unsigned int status);
int virtio_device_reset_prepare(struct virtio_device *dev);
int virtio_device_reset_done(struct virtio_device *dev);
@@ -237,6 +241,8 @@ size_t virtio_max_dma_size(const struct virtio_device *vdev);
* changes; may be called in interrupt context.
* @freeze: optional function to call during suspend/hibernation.
* @restore: optional function to call on resume.
+ * @freeze_noirq: optional function to call during noirq suspend/hibernation.
+ * @restore_noirq: optional function to call on noirq resume.
* @reset_prepare: optional function to call when a transport specific reset
* occurs.
* @reset_done: optional function to call after transport specific reset
@@ -258,6 +264,8 @@ struct virtio_driver {
void (*config_changed)(struct virtio_device *dev);
int (*freeze)(struct virtio_device *dev);
int (*restore)(struct virtio_device *dev);
+ int (*freeze_noirq)(struct virtio_device *dev);
+ int (*restore_noirq)(struct virtio_device *dev);
int (*reset_prepare)(struct virtio_device *dev);
int (*reset_done)(struct virtio_device *dev);
void (*shutdown)(struct virtio_device *dev);
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 69f84ea85d71..496897bc417e 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -70,6 +70,9 @@ struct virtqueue_info {
* vqs_info: array of virtqueue info structures
* Returns 0 on success or error status
* @del_vqs: free virtqueues found by find_vqs().
+ * @reset_vqs: reinitialize existing virtqueues without allocating or
+ * freeing them (optional). Used during noirq restore.
+ * Returns 0 on success or error status.
* @synchronize_cbs: synchronize with the virtqueue callbacks (optional)
* The function guarantees that all memory operations on the
* queue before it are visible to the vring_interrupt() that is
@@ -123,6 +126,7 @@ struct virtio_config_ops {
struct virtqueue_info vqs_info[],
struct irq_affinity *desc);
void (*del_vqs)(struct virtio_device *);
+ int (*reset_vqs)(struct virtio_device *vdev);
void (*synchronize_cbs)(struct virtio_device *);
u64 (*get_features)(struct virtio_device *vdev);
void (*get_extended_features)(struct virtio_device *vdev,
@@ -371,6 +375,31 @@ void virtio_device_ready(struct virtio_device *dev)
dev->config->set_status(dev, status | VIRTIO_CONFIG_S_DRIVER_OK);
}
+/**
+ * virtio_device_ready_noirq - noirq-safe variant of virtio_device_ready()
+ * @dev: the virtio device
+ *
+ * This assumes that the device's get_status and set_status operations are
+ * noirq-safe.
+ */
+static inline
+void virtio_device_ready_noirq(struct virtio_device *dev)
+{
+ unsigned int status = dev->config->get_status(dev);
+
+ WARN_ON(status & VIRTIO_CONFIG_S_DRIVER_OK);
+
+#ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION
+ /*
+ * The noirq stage runs with device IRQ handlers disabled, so
+ * virtio_synchronize_cbs() must not be called here.
+ */
+ __virtio_unbreak_device(dev);
+#endif
+
+ dev->config->set_status(dev, status | VIRTIO_CONFIG_S_DRIVER_OK);
+}
+
static inline
const char *virtio_bus_name(struct virtio_device *vdev)
{
--
2.43.0
^ permalink raw reply related
* [RFC PATCH v2 2/4] virtio_ring: export virtqueue_reinit_vring() for noirq restore
From: Sungho Bae @ 2026-04-17 13:34 UTC (permalink / raw)
To: mst, jasowang
Cc: xuanzhuo, eperezma, virtualization, linux-kernel, Sungho Bae
In-Reply-To: <20260417133430.507-1-baver.bae@gmail.com>
From: Sungho Bae <baver.bae@lge.com>
After a device reset in noirq context the existing vrings must be
re-initialized without any memory allocation, because GFP_KERNEL is
not available.
The internal helpers virtqueue_reset_split() and
virtqueue_reset_packed() already reset vring indices and descriptor
state in place. Add a thin exported wrapper, virtqueue_reinit_vring(),
that dispatches to the appropriate helper based on the ring layout.
This will be used by a subsequent patch that adds noirq system-sleep
PM callbacks for virtio-mmio.
Signed-off-by: Sungho Bae <baver.bae@lge.com>
---
drivers/virtio/virtio_ring.c | 19 +++++++++++++++++++
include/linux/virtio_ring.h | 3 +++
2 files changed, 22 insertions(+)
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index fbca7ce1c6bf..a57c625b5936 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -3936,5 +3936,24 @@ void virtqueue_map_sync_single_range_for_device(const struct virtqueue *_vq,
}
EXPORT_SYMBOL_GPL(virtqueue_map_sync_single_range_for_device);
+/**
+ * virtqueue_reinit_vring - reinitialize vring state without reallocation
+ * @_vq: the virtqueue
+ *
+ * Reset the avail/used indices and descriptor state of an existing
+ * virtqueue so it can be reused after a device reset. No memory is
+ * allocated or freed, making this safe for use in noirq context.
+ */
+void virtqueue_reinit_vring(struct virtqueue *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+
+ if (virtqueue_is_packed(vq))
+ virtqueue_reset_packed(vq);
+ else
+ virtqueue_reset_split(vq);
+}
+EXPORT_SYMBOL_GPL(virtqueue_reinit_vring);
+
MODULE_DESCRIPTION("Virtio ring implementation");
MODULE_LICENSE("GPL");
diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h
index c97a12c1cda3..26c7c9d0a151 100644
--- a/include/linux/virtio_ring.h
+++ b/include/linux/virtio_ring.h
@@ -118,6 +118,9 @@ void vring_del_virtqueue(struct virtqueue *vq);
/* Filter out transport-specific feature bits. */
void vring_transport_features(struct virtio_device *vdev);
+/* Reinitialize a virtqueue without reallocation (safe in noirq context) */
+void virtqueue_reinit_vring(struct virtqueue *_vq);
+
irqreturn_t vring_interrupt(int irq, void *_vq);
u32 vring_notification_data(struct virtqueue *_vq);
--
2.43.0
^ permalink raw reply related
* [RFC PATCH v2 1/4] virtio: separate PM restore and reset_done paths
From: Sungho Bae @ 2026-04-17 13:34 UTC (permalink / raw)
To: mst, jasowang
Cc: xuanzhuo, eperezma, virtualization, linux-kernel, Sungho Bae
In-Reply-To: <20260417133430.507-1-baver.bae@gmail.com>
From: Sungho Bae <baver.bae@lge.com>
Refactor virtio_device_restore_priv() by extracting the common device
re-initialization sequence into virtio_device_reinit(). This helper
performs the full bring-up sequence: reset, status acknowledgment,
feature finalization, and feature negotiation.
virtio_device_restore() and virtio_device_reset_done() now each call
virtio_device_reinit() directly instead of going through a boolean-
dispatched wrapper. This makes each path independently readable and
extensible without further complicating the dispatch logic.
A follow-up series will add noirq PM callbacks that only affect the
restore path; having the two paths separated avoids adding more
conditionals to a shared function.
No functional change.
Signed-off-by: Sungho Bae <baver.bae@lge.com>
---
drivers/virtio/virtio.c | 78 +++++++++++++++++++++++++----------------
1 file changed, 47 insertions(+), 31 deletions(-)
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 5bdc6b82b30b..b0668434ac21 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -588,7 +588,7 @@ void unregister_virtio_device(struct virtio_device *dev)
}
EXPORT_SYMBOL_GPL(unregister_virtio_device);
-static int virtio_device_restore_priv(struct virtio_device *dev, bool restore)
+static int virtio_device_reinit(struct virtio_device *dev)
{
struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
int ret;
@@ -613,35 +613,9 @@ static int virtio_device_restore_priv(struct virtio_device *dev, bool restore)
ret = dev->config->finalize_features(dev);
if (ret)
- goto err;
-
- ret = virtio_features_ok(dev);
- if (ret)
- goto err;
-
- if (restore) {
- if (drv->restore) {
- ret = drv->restore(dev);
- if (ret)
- goto err;
- }
- } else {
- ret = drv->reset_done(dev);
- if (ret)
- goto err;
- }
-
- /* If restore didn't do it, mark device DRIVER_OK ourselves. */
- if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK))
- virtio_device_ready(dev);
-
- virtio_config_core_enable(dev);
-
- return 0;
+ return ret;
-err:
- virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
- return ret;
+ return virtio_features_ok(dev);
}
#ifdef CONFIG_PM_SLEEP
@@ -668,7 +642,30 @@ EXPORT_SYMBOL_GPL(virtio_device_freeze);
int virtio_device_restore(struct virtio_device *dev)
{
- return virtio_device_restore_priv(dev, true);
+ struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+ int ret;
+
+ ret = virtio_device_reinit(dev);
+ if (ret)
+ goto err;
+
+ if (drv && drv->restore) {
+ ret = drv->restore(dev);
+ if (ret)
+ goto err;
+ }
+
+ /* If restore didn't do it, mark device DRIVER_OK ourselves. */
+ if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK))
+ virtio_device_ready(dev);
+
+ virtio_config_core_enable(dev);
+
+ return 0;
+
+err:
+ virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
+ return ret;
}
EXPORT_SYMBOL_GPL(virtio_device_restore);
#endif
@@ -698,11 +695,30 @@ EXPORT_SYMBOL_GPL(virtio_device_reset_prepare);
int virtio_device_reset_done(struct virtio_device *dev)
{
struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+ int ret;
if (!drv || !drv->reset_done)
return -EOPNOTSUPP;
- return virtio_device_restore_priv(dev, false);
+ ret = virtio_device_reinit(dev);
+ if (ret)
+ goto err;
+
+ ret = drv->reset_done(dev);
+ if (ret)
+ goto err;
+
+ /* If reset_done didn't do it, mark device DRIVER_OK ourselves. */
+ if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK))
+ virtio_device_ready(dev);
+
+ virtio_config_core_enable(dev);
+
+ return 0;
+
+err:
+ virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
+ return ret;
}
EXPORT_SYMBOL_GPL(virtio_device_reset_done);
--
2.43.0
^ permalink raw reply related
* [RFC PATCH v2 0/4] virtio: add noirq system sleep PM callbacks for virtio-mmio
From: Sungho Bae @ 2026-04-17 13:34 UTC (permalink / raw)
To: mst, jasowang
Cc: xuanzhuo, eperezma, virtualization, linux-kernel, Sungho Bae
From: Sungho Bae <baver.bae@lge.com>
Hi all,
Some virtio-mmio based devices, such as virtio-clock or virtio-regulator,
must become operational before other devices have their regular PM restore
callbacks invoked, because those other devices depend on them.
Generally, PM framework provides the three phases (freeze, freeze_late,
freeze_noirq) for the system sleep sequence, and the corresponding resume
phases. But, virtio core only supports the normal freeze/restore phase,
so virtio drivers have no way to participate in the noirq phase, which runs
with IRQs disabled and is guaranteed to run before any normal-phase restore
callbacks.
This series adds the infrastructure and the virtio-mmio transport
wiring so that virtio drivers can implement freeze_noirq/restore_noirq
callbacks.
Design overview
===============
The noirq phase runs with device IRQ handlers disabled and must avoid
sleepable operations. The main constraints addressed are:
- might_sleep() in virtio_add_status() and virtio_features_ok().
- virtio_synchronize_cbs() in virtio_reset_device() (IRQs are already
quiesced).
- spin_lock_irq() in virtio_config_core_enable() (not safe to call
with interrupts already disabled).
- Memory allocation during vq setup (virtqueue_reinit_vring() reuses
existing buffers instead).
The series provides noirq-safe variants for each of these, plus a new
config_ops->reset_vqs() callback that lets the transport reprogram
queue registers without freeing/reallocating vring memory.
When a driver implements restore_noirq, the device bring-up (reset ->
ACKNOWLEDGE -> DRIVER -> finalize_features -> FEATURES_OK) happens in
the noirq phase. The subsequent normal-phase virtio_device_restore()
detects this and skips the redundant re-initialization.
Patch breakdown
===============
Patch 1 is a preparatory refactoring with no functional change.
Patches 2-3 add the core infrastructure. Patch 4 wires it up for
virtio-mmio.
1. virtio: separate PM restore and reset_done paths
Splits virtio_device_restore_priv() into independent
virtio_device_restore() and virtio_device_reset_done() paths,
using a shared virtio_device_reinit() helper. This is a pure
refactoring to make the restore path independently extensible
without complicating the boolean dispatch.
2. virtio_ring: export virtqueue_reinit_vring() for noirq restore
Adds a thin exported wrapper around the existing static
virtqueue_reset_split()/virtqueue_reset_packed() helpers, which
reset vring indices and descriptor state in place without any
memory allocation. This makes them usable from the transport's
reset_vqs() callback in noirq context.
3. virtio: add noirq system sleep PM infrastructure
Adds noirq-safe helpers (virtio_add_status_noirq,
virtio_features_ok_noirq, virtio_reset_device_noirq,
virtio_config_core_enable_noirq, virtio_device_ready_noirq) and
the freeze_noirq/restore_noirq driver callbacks plus the
config_ops->reset_vqs() transport hook. Modifies
virtio_device_restore() to skip bring-up when restore_noirq
already ran.
4. virtio-mmio: wire up noirq system sleep PM callbacks
Implements vm_reset_vqs() which iterates existing virtqueues,
reinitializes the vring state via virtqueue_reinit_vring(), and
reprograms the MMIO queue registers. Adds
virtio_mmio_freeze_noirq/virtio_mmio_restore_noirq and registers
them via SET_NOIRQ_SYSTEM_SLEEP_PM_OPS().
Testing
=======
Build-tested with arm64 cross-compilation.
(make ARCH=arm64 M=drivers/virtio)
Runtime-tested on an internal virtio-mmio platform with virtio-clock,
confirming that the clock device works well before other devices' normal
restore() callbacks run.
Questions for reviewers
=======================
- virtio_config_core_enable_noirq() is currently a separate helper
that duplicates the spin_lock logic, but it only differs from
virtio_config_core_enable() by the locking context.
Would it be better to merge them into a single function with irqsafe
locking, or is the current separate-helper approach acceptable?
- Should reset_vqs be a mandatory callback when restore_noirq is
used, or should the core silently skip vq re-initialization when
the vq list is empty (current behavior)?
- Some functions, such as get_status() and set_status(), are also used
in the noirq restore path. Therefore, it is assumed that drivers using
noirq callbacks have implemented these functions usable in the noirq
context.
Is the current implementation acceptable? Or is it necessary to create a
flag to indicate the driver supports them in the noirq context, or
have a separate noirq callback?
Changes
=======
v2:
virtio-mmio: wire up noirq system sleep PM callbacks
- The code that was duplicated in vm_setup_vq() and vm_reset_vqs() has
been moved to vm_active_vq() function.
Sungho Bae (4):
virtio: separate PM restore and reset_done paths
virtio_ring: export virtqueue_reinit_vring() for noirq restore
virtio: add noirq system sleep PM infrastructure
virtio-mmio: wire up noirq system sleep PM callbacks
drivers/virtio/virtio.c | 234 ++++++++++++++++++++++++++++++----
drivers/virtio/virtio_mmio.c | 131 +++++++++++++------
drivers/virtio/virtio_ring.c | 19 +++
include/linux/virtio.h | 8 ++
include/linux/virtio_config.h | 29 +++++
include/linux/virtio_ring.h | 3 +
6 files changed, 359 insertions(+), 65 deletions(-)
--
2.43.0
^ permalink raw reply
* Re: [PATCH] drm/virtgpu: Add PM support for suspend/resume
From: Morris Pan (潘泰為) @ 2026-04-17 9:40 UTC (permalink / raw)
To: airlied@redhat.com, kraxel@redhat.com,
dmitry.osipenko@collabora.com
Cc: virtualization@lists.linux.dev, srv_heupstream@mediatek.com,
simona@ffwll.ch, gurchetansingh@chromium.org, tzimmermann@suse.de,
olvaffe@gmail.com, dri-devel@lists.freedesktop.org,
maarten.lankhorst@linux.intel.com, mripard@kernel.org
In-Reply-To: <2175a05a-d83f-4252-bbf8-581ae652a6b8@collabora.com>
On Wed, 2026-04-08 at 15:59 +0300, Dmitry Osipenko wrote:
> Hi,
>
> On 4/1/26 09:10, Morris Pan wrote:
> > diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c
> > b/drivers/gpu/drm/virtio/virtgpu_drv.c
> > index a5ce96fb8a1d..fbca0a82958c 100644
> > --- a/drivers/gpu/drm/virtio/virtgpu_drv.c
> > +++ b/drivers/gpu/drm/virtio/virtgpu_drv.c
> > @@ -145,6 +145,40 @@ static void virtio_gpu_config_changed(struct
> > virtio_device *vdev)
> > schedule_work(&vgdev->config_changed_work);
> > }
> >
> > +#ifdef CONFIG_PM_SLEEP
> > +static int virtgpu_freeze(struct virtio_device *vdev)
> > +{
> > + vdev->config->del_vqs(vdev);
> > + virtio_reset_device(vdev);
> > +
> > + return 0;
> > +}
>
> VirtIO-GPU shouldn't be reset freely. See [1] and follow previous
> hibernation-support discussions on the ML.
>
> [1[
> https://lore.kernel.org/dri-devel/20260107182745.229481-1-dongwon.kim@intel.com/
>
>
Hi Dmitry,
Thank you for the guidance and for pointing me to that thread.
I have looked into the series you mentioned, specifically "PATCH v7
1/3: drm/virtio: Freeze and restore hooks to support suspend and
resume" (link).
I have verified that this change resolves the issue I was experiencing
in my envirronment.
I will keep an eye on that series and follow its progress. Thank you
for your time and help.
Best regards,
Morris Pan
^ permalink raw reply
* Re: [PATCH net v2] hv_sock: Report EOF instead of -EIO for FIN
From: Stefano Garzarella @ 2026-04-17 8:11 UTC (permalink / raw)
To: Dexuan Cui
Cc: kys, haiyangz, wei.liu, longli, davem, edumazet, kuba, pabeni,
horms, niuxuewei.nxw, linux-hyperv, virtualization, netdev,
linux-kernel, stable, Ben Hillis, Mitchell Levy
In-Reply-To: <20260416191433.840637-1-decui@microsoft.com>
On Thu, Apr 16, 2026 at 12:14:33PM -0700, Dexuan Cui wrote:
>Commit f0c5827d07cb unluckily causes a regression for the FIN packet,
>and the final read syscall gets an error rather than 0.
>
>Ideally, we would want to fix hvs_channel_readable_payload() so that it
>could return 0 in the FIN scenario, but it's not good for the hv_sock
>driver to use the VMBus ringbuffer's cached priv_read_index, which is
>internal data in the VMBus driver.
>
>Fix the regression in hv_sock by returning 0 rather than -EIO.
>
>Fixes: f0c5827d07cb ("hv_sock: Return the readable bytes in hvs_stream_has_data()")
>Cc: stable@vger.kernel.org
>Reported-by: Ben Hillis <Ben.Hillis@microsoft.com>
>Reported-by: Mitchell Levy <levymitchell0@gmail.com>
>Signed-off-by: Dexuan Cui <decui@microsoft.com>
>---
>
>Changes since v1:
> Removed the local variable 'need_refill' to make the code more
> readable. Stefano, thanks!
Thanks for the fix!
>
> No other change.
>
> net/vmw_vsock/hyperv_transport.c | 20 ++++++++++++++++----
> 1 file changed, 16 insertions(+), 4 deletions(-)
Acked-by: Stefano Garzarella <sgarzare@redhat.com>
^ permalink raw reply
* Re: [PATCH] ALSA: virtio: drop an extaneous kernel-doc comment
From: Takashi Iwai @ 2026-04-17 7:49 UTC (permalink / raw)
To: Randy Dunlap
Cc: linux-sound, Matias Ezequiel Vara Larsen, Michael S. Tsirkin,
virtualization, Jaroslav Kysela, Takashi Iwai
In-Reply-To: <75a01b73-f46a-47fd-91bb-4ce9d5c30866@infradead.org>
On Fri, 17 Apr 2026 00:00:17 +0200,
Randy Dunlap wrote:
>
> ping.
>
> On 2/15/26 9:59 PM, Randy Dunlap wrote:
> > Drop a kernel-doc struct comment since the struct member was removed.
> > This eliminates a kernel-doc warning when make W=1 is used.
> >
> > virtio_pcm.h:65: warning: Excess struct member 'msg_last_enqueued'
> > description in 'virtio_pcm_substream'
> >
> > Fixes: fe981e67568c ("ALSA: virtio: use ack callback")
> > Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
> > ---
> > Cc: Anton Yakovlev <anton.yakovlev@opensynergy.com>
> > Cc: Matias Ezequiel Vara Larsen <mvaralar@redhat.com>
> > Cc: "Michael S. Tsirkin" <mst@redhat.com>
> > Cc: virtualization@lists.linux.dev
> > Cc: Jaroslav Kysela <perex@perex.cz>
> > Cc: Takashi Iwai <tiwai@suse.com>
> > Cc: linux-sound@vger.kernel.org
> >
> > sound/virtio/virtio_pcm.h | 1 -
> > 1 file changed, 1 deletion(-)
> >
> > --- linux-next-20251210.orig/sound/virtio/virtio_pcm.h
> > +++ linux-next-20251210/sound/virtio/virtio_pcm.h
> > @@ -37,7 +37,6 @@ struct virtio_pcm_msg;
> > * the device side at resume.
> > * @msgs: Allocated I/O messages.
> > * @nmsgs: Number of allocated I/O messages.
> > - * @msg_last_enqueued: Index of the last I/O message added to the virtqueue.
> > * @msg_count: Number of pending I/O messages in the virtqueue.
> > * @msg_empty: Notify when msg_count is zero.
> > */
Sorry, it slipped from my inbox, maybe it hit on a bad day :-<
Applied now this and another one for vx. Thanks.
Takashi
^ permalink raw reply
* RE: [PATCH 1/2] vfio/pci: Set up VFIO barmap before creating a DMABUF
From: Tian, Kevin @ 2026-04-17 5:16 UTC (permalink / raw)
To: Alex Williamson, Matt Evans
Cc: Ankit Agrawal, Jason Gunthorpe, Yishai Hadas, Shameer Kolothum,
Alistair Popple, Leon Romanovsky, Kasireddy, Vivek, Kees Cook,
Zhi Wang, Peter Xu, Alexey Kardashevskiy, Eric Auger,
kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
virtualization@lists.linux.dev
In-Reply-To: <20260416164406.7fb3bb0b@shazbot.org>
> From: Alex Williamson <alex@shazbot.org>
> Sent: Friday, April 17, 2026 6:44 AM
>
> On Wed, 15 Apr 2026 11:14:22 -0700
> Matt Evans <mattev@meta.com> wrote:
>
> > A DMABUF exports access to BAR resources which need to be requested
> > before the DMABUF is handed out. Usually the resources are requested
> > when setting up the barmap when the VFIO device fd is mmap()ed, but
> > there's no guarantee that's done before a DMABUF is created.
> >
> > Set up the barmap (and so request resources) in the DMABUF-creation
> > path.
> >
> > Fixes: 5d74781ebc86c ("vfio/pci: Add dma-buf export support for MMIO
> regions")
> > Signed-off-by: Matt Evans <mattev@meta.com>
> > ---
> > drivers/vfio/pci/vfio_pci_dmabuf.c | 9 +++++++++
> > 1 file changed, 9 insertions(+)
> >
> > diff --git a/drivers/vfio/pci/vfio_pci_dmabuf.c
> b/drivers/vfio/pci/vfio_pci_dmabuf.c
> > index 4ccaf3531e02..fefe7cf4256b 100644
> > --- a/drivers/vfio/pci/vfio_pci_dmabuf.c
> > +++ b/drivers/vfio/pci/vfio_pci_dmabuf.c
> > @@ -272,6 +272,15 @@ int vfio_pci_core_feature_dma_buf(struct
> vfio_pci_core_device *vdev, u32 flags,
> > goto err_free_priv;
> > }
> >
> > + /*
> > + * See comment in vfio_pci_core_mmap(); ensure PCI regions
> > + * were requested before returning DMABUFs that reference
> > + * them. Barmap setup does this:
> > + */
> > + ret = vfio_pci_core_setup_barmap(vdev, get_dma_buf.region_index);
> > + if (ret)
> > + goto err_free_phys;
> > +
> > priv->vdev = vdev;
> > priv->nr_ranges = get_dma_buf.nr_ranges;
> > priv->size = length;
>
> Wouldn't this get a lot easier if we just setup all the barmaps in
> vfio_pci_core_enable(), conditional on pci_resource_len() just like we
> use to filter in REGION_INFO?
>
> I don't recall if there's some reason we've avoid this so far, maybe
> others can shout it out if they do.
I don't remember too. probably just because it's not a wide requirement
then was made in this on-demand approach...
>
> We already tear them all down in vfio_pci_core_disable(). It would be
> a small patch to add that, which we would mark as Fixes:, then a small
> follow-up on top of that that removes any then redundant or unnecessary
> callers (all of them). Thoughts? Thanks,
>
Agree. then the next patch fixing the racing conditions is also not required.
^ permalink raw reply
* Re: [PATCH net v4 0/3] vsock/virtio: fix MSG_PEEK calculation on bytes to copy
From: patchwork-bot+netdevbpf @ 2026-04-17 2:40 UTC (permalink / raw)
To: Luigi Leonardi
Cc: stefanha, sgarzare, mst, jasowang, xuanzhuo, eperezma, davem,
edumazet, kuba, pabeni, horms, avkrasnov, kvm, virtualization,
netdev, linux-kernel
In-Reply-To: <20260415-fix_peek-v4-0-8207e872759e@redhat.com>
Hello:
This series was applied to netdev/net.git (main)
by Jakub Kicinski <kuba@kernel.org>:
On Wed, 15 Apr 2026 17:09:27 +0200 you wrote:
> `virtio_transport_stream_do_peek`, when calculating the number of bytes to
> copy, didn't consider the `offset`, caused by partial reads that happened
> before.
> This might cause out-of-bounds read that lead to an EFAULT.
> More details in the commits.
>
> Commit 1 introduces the fix
> Commit 2 introduces some preliminary work for adding a test and fixes a
> problem in existing tests.
> Commit 3 introduces a test that checks for this bug to avoid future
> regressions.
>
> [...]
Here is the summary with links:
- [net,v4,1/3] vsock/virtio: fix MSG_PEEK ignoring skb offset when calculating bytes to copy
https://git.kernel.org/netdev/net/c/080f22f5d302
- [net,v4,2/3] vsock/test: fix MSG_PEEK handling in recv_buf()
https://git.kernel.org/netdev/net/c/a3f77afbf67d
- [net,v4,3/3] vsock/test: add MSG_PEEK after partial recv test
https://git.kernel.org/netdev/net/c/2a2675ef6190
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
^ permalink raw reply
* Re: [PATCH v5 6/7] locking: Factor out __queued_read_unlock()/__queued_write_unlock()
From: Paul E. McKenney @ 2026-04-16 23:55 UTC (permalink / raw)
To: Dmitry Ilvokhin
Cc: Peter Zijlstra, Ingo Molnar, Will Deacon, Boqun Feng, Waiman Long,
Thomas Bogendoerfer, Juergen Gross, Ajay Kaher, Alexey Makhalov,
Broadcom internal kernel review list, Thomas Gleixner,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Arnd Bergmann,
Dennis Zhou, Tejun Heo, Christoph Lameter, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, linux-kernel, linux-mips,
virtualization, linux-arch, linux-mm, linux-trace-kernel,
kernel-team
In-Reply-To: <eabc9de3347ca042eb0593c9b81c8e48254a4874.1776350944.git.d@ilvokhin.com>
On Thu, Apr 16, 2026 at 03:05:12PM +0000, Dmitry Ilvokhin wrote:
> This is a preparatory refactoring for the next commit, which adds
> contended_release tracepoint instrumentation and needs to call the
> unlock from both traced and non-traced paths.
>
> No functional change.
>
> Signed-off-by: Dmitry Ilvokhin <d@ilvokhin.com>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
> ---
> include/asm-generic/qrwlock.h | 20 +++++++++++++++-----
> 1 file changed, 15 insertions(+), 5 deletions(-)
>
> diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h
> index 75b8f4601b28..4b627bafba8b 100644
> --- a/include/asm-generic/qrwlock.h
> +++ b/include/asm-generic/qrwlock.h
> @@ -101,16 +101,26 @@ static inline void queued_write_lock(struct qrwlock *lock)
> queued_write_lock_slowpath(lock);
> }
>
> +static __always_inline void __queued_read_unlock(struct qrwlock *lock)
> +{
> + /*
> + * Atomically decrement the reader count
> + */
> + (void)atomic_sub_return_release(_QR_BIAS, &lock->cnts);
> +}
> +
> /**
> * queued_read_unlock - release read lock of a queued rwlock
> * @lock : Pointer to queued rwlock structure
> */
> static inline void queued_read_unlock(struct qrwlock *lock)
> {
> - /*
> - * Atomically decrement the reader count
> - */
> - (void)atomic_sub_return_release(_QR_BIAS, &lock->cnts);
> + __queued_read_unlock(lock);
> +}
> +
> +static __always_inline void __queued_write_unlock(struct qrwlock *lock)
> +{
> + smp_store_release(&lock->wlocked, 0);
> }
>
> /**
> @@ -119,7 +129,7 @@ static inline void queued_read_unlock(struct qrwlock *lock)
> */
> static inline void queued_write_unlock(struct qrwlock *lock)
> {
> - smp_store_release(&lock->wlocked, 0);
> + __queued_write_unlock(lock);
> }
>
> /**
> --
> 2.52.0
>
^ permalink raw reply
* Re: [PATCH v5 5/7] locking: Add contended_release tracepoint to qspinlock
From: Paul E. McKenney @ 2026-04-16 23:54 UTC (permalink / raw)
To: Dmitry Ilvokhin
Cc: Peter Zijlstra, Ingo Molnar, Will Deacon, Boqun Feng, Waiman Long,
Thomas Bogendoerfer, Juergen Gross, Ajay Kaher, Alexey Makhalov,
Broadcom internal kernel review list, Thomas Gleixner,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Arnd Bergmann,
Dennis Zhou, Tejun Heo, Christoph Lameter, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, linux-kernel, linux-mips,
virtualization, linux-arch, linux-mm, linux-trace-kernel,
kernel-team
In-Reply-To: <af285ffefa3fa2f73b73a39e9f06fb176009e047.1776350944.git.d@ilvokhin.com>
On Thu, Apr 16, 2026 at 03:05:11PM +0000, Dmitry Ilvokhin wrote:
> Use the arch-overridable queued_spin_release(), introduced in the
> previous commit, to ensure the tracepoint works correctly across all
> architectures, including those with custom unlock implementations (e.g.
> x86 paravirt).
>
> When the tracepoint is disabled, the only addition to the hot path is a
> single NOP instruction (the static branch). When enabled, the contention
> check, trace call, and unlock are combined in an out-of-line function to
> minimize hot path impact, avoiding the compiler needing to preserve the
> lock pointer in a callee-saved register across the trace call.
>
> Binary size impact (x86_64, defconfig):
> uninlined unlock (common case): +680 bytes (+0.00%)
> inlined unlock (worst case): +83659 bytes (+0.21%)
>
> The inlined unlock case could not be achieved through Kconfig options on
> x86_64 as PREEMPT_BUILD unconditionally selects UNINLINE_SPIN_UNLOCK on
> x86_64. The UNINLINE_SPIN_UNLOCK guards were manually inverted to force
> inline the unlock path and estimate the worst case binary size increase.
>
> In practice, configurations with UNINLINE_SPIN_UNLOCK=n have already
> opted against binary size optimization, so the inlined worst case is
> unlikely to be a concern.
>
> Architectures with fully custom qspinlock implementations (e.g.
> PowerPC) are not covered by this change.
>
> Signed-off-by: Dmitry Ilvokhin <d@ilvokhin.com>
Much nicer split out!
Acked-by: Paul E. McKenney <paulmck@kernel.org>
> ---
> include/asm-generic/qspinlock.h | 18 ++++++++++++++++++
> kernel/locking/qspinlock.c | 8 ++++++++
> 2 files changed, 26 insertions(+)
>
> diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
> index df76f34645a0..915a4c2777f6 100644
> --- a/include/asm-generic/qspinlock.h
> +++ b/include/asm-generic/qspinlock.h
> @@ -41,6 +41,7 @@
>
> #include <asm-generic/qspinlock_types.h>
> #include <linux/atomic.h>
> +#include <linux/tracepoint-defs.h>
>
> #ifndef queued_spin_is_locked
> /**
> @@ -129,12 +130,29 @@ static __always_inline void queued_spin_release(struct qspinlock *lock)
> }
> #endif
>
> +DECLARE_TRACEPOINT(contended_release);
> +
> +extern void queued_spin_release_traced(struct qspinlock *lock);
> +
> /**
> * queued_spin_unlock - unlock a queued spinlock
> * @lock : Pointer to queued spinlock structure
> + *
> + * Generic tracing wrapper around the arch-overridable
> + * queued_spin_release().
> */
> static __always_inline void queued_spin_unlock(struct qspinlock *lock)
> {
> + /*
> + * Trace and release are combined in queued_spin_release_traced() so
> + * the compiler does not need to preserve the lock pointer across the
> + * function call, avoiding callee-saved register save/restore on the
> + * hot path.
> + */
> + if (tracepoint_enabled(contended_release)) {
> + queued_spin_release_traced(lock);
> + return;
> + }
> queued_spin_release(lock);
> }
>
> diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
> index af8d122bb649..c72610980ec7 100644
> --- a/kernel/locking/qspinlock.c
> +++ b/kernel/locking/qspinlock.c
> @@ -104,6 +104,14 @@ static __always_inline u32 __pv_wait_head_or_lock(struct qspinlock *lock,
> #define queued_spin_lock_slowpath native_queued_spin_lock_slowpath
> #endif
>
> +void __lockfunc queued_spin_release_traced(struct qspinlock *lock)
> +{
> + if (queued_spin_is_contended(lock))
> + trace_contended_release(lock);
> + queued_spin_release(lock);
> +}
> +EXPORT_SYMBOL(queued_spin_release_traced);
> +
> #endif /* _GEN_PV_LOCK_SLOWPATH */
>
> /**
> --
> 2.52.0
>
^ permalink raw reply
* [PATCH] virtio: console: fix use-after-free after failed restore
From: physicalmtea @ 2026-04-16 23:37 UTC (permalink / raw)
To: amit; +Cc: arnd, gregkh, virtualization, linux-kernel, JiaJia
From: JiaJia <physicalmtea@gmail.com>
virtcons_freeze() tears down the virtqueues through remove_vqs(), but
remove_vqs() only deletes the virtqueues and frees portdev->in_vqs and
portdev->out_vqs. It leaves port->in_vq, port->out_vq, portdev->c_ivq,
and portdev->c_ovq pointing at the old queues.
Those stale pointers survive a failed restore:
virtcons_freeze()
-> remove_vqs()
-> del_vqs()
-> vring_del_virtqueue()
-> kfree(vq)
virtcons_restore()
-> init_vqs()
-> virtio_find_vqs()
If init_vqs() fails, virtcons_restore() returns without rebinding the
per-port queue pointers. Later get_chars(), __send_control_msg(),
control_work_handler(), get_inbuf(), reclaim_consumed_buffers(),
__send_to_port(), fill_readbuf(), and splice_write can still reach those
cached pointers and trigger a use-after-free or Oops.
A fault-injection-assisted hibernation run that forces init_vqs() to
fail reproduces this as a KASAN slab-use-after-free in
virtqueue_disable_cb() from virtcons_freeze() on the subsequent PM
path.
Clear the cached virtqueue pointers when queues are deleted, guard the
direct queue users that can still run after a failed restore, and make
queue-less open/write paths fail immediately instead of sleeping or
succeeding against a broken port state.
Signed-off-by: JiaJia <physicalmtea@gmail.com>
---
Runtime evidence from a fault-injection-assisted hibernation run that
forces init_vqs() to fail with -ENOMEM:
virtio_console virtio1: virtcons_restore: init_vqs failed: -12
virtio-pci 0000:00:02.0: PM: failed to thaw: error -12
KASAN report: slab-use-after-free in virtqueue_disable_cb+0x20/0xb0
Read of size 4 at addr fff000000417c848 by task virtio-console-/1
The buggy address belongs to the object at fff000000417c800
which belongs to the cache kmalloc-256 of size 256
The buggy address is located 72 bytes inside of
freed 256-byte region [fff000000417c800, fff000000417c900)
Call trace:
virtqueue_disable_cb+0x20/0xb0
virtcons_freeze+0x1f8/0x208
virtio_device_freeze+0x98/0xd0
virtio_pci_freeze+0x28/0x60
pci_pm_freeze+0x94/0x1a8
dpm_run_callback+0x118/0x4e0
device_suspend+0x210/0xa40
dpm_suspend+0x258/0x628
dpm_suspend_start+0x78/0x88
hibernation_restore+0x28/0x188
load_image_and_restore+0xd0/0x118
hibernate+0x2cc/0x430
drivers/char/virtio_console.c | 57 ++++++++++++++++++++++++++++-------
1 file changed, 46 insertions(+), 11 deletions(-)
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 9a33217c6..05887bdb5 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -464,6 +464,8 @@ static struct port_buffer *get_inbuf(struct port *port)
if (port->inbuf)
return port->inbuf;
+ if (!port->in_vq)
+ return NULL;
buf = virtqueue_get_buf(port->in_vq, &len);
if (buf) {
@@ -547,6 +549,8 @@ static ssize_t __send_control_msg(struct ports_device *portdev, u32 port_id,
return 0;
vq = portdev->c_ovq;
+ if (!vq)
+ return -ENODEV;
spin_lock(&portdev->c_ovq_lock);
@@ -583,8 +587,8 @@ static void reclaim_consumed_buffers(struct port *port)
struct port_buffer *buf;
unsigned int len;
- if (!port->portdev) {
- /* Device has been unplugged. vqs are already gone. */
+ if (!port->portdev || !port->out_vq) {
+ /* Device has been unplugged or the queues have been torn down. */
return;
}
while ((buf = virtqueue_get_buf(port->out_vq, &len))) {
@@ -603,6 +607,8 @@ static ssize_t __send_to_port(struct port *port, struct scatterlist *sg,
unsigned int len;
out_vq = port->out_vq;
+ if (!out_vq)
+ return -ENODEV;
spin_lock_irqsave(&port->outvq_lock, flags);
@@ -684,7 +690,9 @@ static ssize_t fill_readbuf(struct port *port, u8 __user *out_buf,
spin_lock_irqsave(&port->inbuf_lock, flags);
port->inbuf = NULL;
- if (add_inbuf(port->in_vq, buf) < 0)
+ if (!port->in_vq)
+ free_buf(buf, false);
+ else if (add_inbuf(port->in_vq, buf) < 0)
dev_warn(port->dev, "failed add_buf\n");
spin_unlock_irqrestore(&port->inbuf_lock, flags);
@@ -777,6 +785,9 @@ static int wait_port_writable(struct port *port, bool nonblock)
{
int ret;
+ if (!port->out_vq)
+ return -ENODEV;
+
if (will_write_block(port)) {
if (nonblock)
return -EAGAIN;
@@ -786,8 +797,8 @@ static int wait_port_writable(struct port *port, bool nonblock)
if (ret < 0)
return ret;
}
- /* Port got hot-unplugged. */
- if (!port->guest_connected)
+ /* Port got hot-unplugged or lost its queues. */
+ if (!port->guest_connected || !port->out_vq)
return -ENODEV;
return 0;
@@ -919,6 +930,8 @@ static ssize_t port_fops_splice_write(struct pipe_inode_info *pipe,
* regular pages to dma pages. And alloc_buf and free_buf must
* support allocating and freeing such a list of dma-buffers.
*/
+ if (!port->portdev || !port->out_vq)
+ return -ENODEV;
if (is_rproc_serial(port->out_vq->vdev))
return -EINVAL;
@@ -1039,7 +1052,6 @@ static int port_fops_open(struct inode *inode, struct file *filp)
ret = -ENXIO;
goto out;
}
-
/* Allow only one process to open a particular port at a time */
spin_lock_irq(&port->inbuf_lock);
if (port->guest_connected) {
@@ -1047,6 +1059,11 @@ static int port_fops_open(struct inode *inode, struct file *filp)
ret = -EBUSY;
goto out;
}
+ if (!port->in_vq || !port->out_vq) {
+ spin_unlock_irq(&port->inbuf_lock);
+ ret = -ENODEV;
+ goto out;
+ }
port->guest_connected = true;
spin_unlock_irq(&port->inbuf_lock);
@@ -1141,7 +1158,8 @@ static ssize_t get_chars(u32 vtermno, u8 *buf, size_t count)
return -EPIPE;
/* If we don't have an input queue yet, we can't get input. */
- BUG_ON(!port->in_vq);
+ if (!port->in_vq)
+ return -EPIPE;
return fill_readbuf(port, (__force u8 __user *)buf, count, false);
}
@@ -1666,6 +1684,8 @@ static void control_work_handler(struct work_struct *work)
portdev = container_of(work, struct ports_device, control_work);
vq = portdev->c_ivq;
+ if (!vq)
+ return;
spin_lock(&portdev->c_ivq_lock);
while ((buf = virtqueue_get_buf(vq, &len))) {
@@ -1869,7 +1889,11 @@ static int init_vqs(struct ports_device *portdev)
free:
kfree(portdev->out_vqs);
+ portdev->out_vqs = NULL;
kfree(portdev->in_vqs);
+ portdev->in_vqs = NULL;
+ portdev->c_ivq = NULL;
+ portdev->c_ovq = NULL;
kfree(vqs_info);
kfree(vqs);
@@ -1882,6 +1906,7 @@ static const struct file_operations portdev_fops = {
static void remove_vqs(struct ports_device *portdev)
{
+ struct port *port;
struct virtqueue *vq;
virtio_device_for_each_vq(portdev->vdev, vq) {
@@ -1892,9 +1917,17 @@ static void remove_vqs(struct ports_device *portdev)
free_buf(buf, true);
cond_resched();
}
+ list_for_each_entry(port, &portdev->ports, list) {
+ port->in_vq = NULL;
+ port->out_vq = NULL;
+ }
+ portdev->c_ivq = NULL;
+ portdev->c_ovq = NULL;
portdev->vdev->config->del_vqs(portdev->vdev);
kfree(portdev->in_vqs);
+ portdev->in_vqs = NULL;
kfree(portdev->out_vqs);
+ portdev->out_vqs = NULL;
}
static void virtcons_remove(struct virtio_device *vdev)
@@ -2094,7 +2127,7 @@ static int virtcons_freeze(struct virtio_device *vdev)
virtio_reset_device(vdev);
- if (use_multiport(portdev))
+ if (use_multiport(portdev) && portdev->c_ivq)
virtqueue_disable_cb(portdev->c_ivq);
cancel_work_sync(&portdev->control_work);
cancel_work_sync(&portdev->config_work);
@@ -2102,12 +2135,14 @@ static int virtcons_freeze(struct virtio_device *vdev)
* Once more: if control_work_handler() was running, it would
* enable the cb as the last step.
*/
- if (use_multiport(portdev))
+ if (use_multiport(portdev) && portdev->c_ivq)
virtqueue_disable_cb(portdev->c_ivq);
list_for_each_entry(port, &portdev->ports, list) {
- virtqueue_disable_cb(port->in_vq);
- virtqueue_disable_cb(port->out_vq);
+ if (port->in_vq)
+ virtqueue_disable_cb(port->in_vq);
+ if (port->out_vq)
+ virtqueue_disable_cb(port->out_vq);
/*
* We'll ask the host later if the new invocation has
* the port opened or closed.
--
2.34.1
^ permalink raw reply related
* Re: [PATCH 1/2] vfio/pci: Set up VFIO barmap before creating a DMABUF
From: Alex Williamson @ 2026-04-16 22:44 UTC (permalink / raw)
To: Matt Evans
Cc: Ankit Agrawal, Jason Gunthorpe, Yishai Hadas, Shameer Kolothum,
Kevin Tian, Alistair Popple, Leon Romanovsky, Vivek Kasireddy,
Kees Cook, Zhi Wang, Peter Xu, Alexey Kardashevskiy, Eric Auger,
kvm, linux-kernel, virtualization, alex
In-Reply-To: <20260415181423.1008458-1-mattev@meta.com>
On Wed, 15 Apr 2026 11:14:22 -0700
Matt Evans <mattev@meta.com> wrote:
> A DMABUF exports access to BAR resources which need to be requested
> before the DMABUF is handed out. Usually the resources are requested
> when setting up the barmap when the VFIO device fd is mmap()ed, but
> there's no guarantee that's done before a DMABUF is created.
>
> Set up the barmap (and so request resources) in the DMABUF-creation
> path.
>
> Fixes: 5d74781ebc86c ("vfio/pci: Add dma-buf export support for MMIO regions")
> Signed-off-by: Matt Evans <mattev@meta.com>
> ---
> drivers/vfio/pci/vfio_pci_dmabuf.c | 9 +++++++++
> 1 file changed, 9 insertions(+)
>
> diff --git a/drivers/vfio/pci/vfio_pci_dmabuf.c b/drivers/vfio/pci/vfio_pci_dmabuf.c
> index 4ccaf3531e02..fefe7cf4256b 100644
> --- a/drivers/vfio/pci/vfio_pci_dmabuf.c
> +++ b/drivers/vfio/pci/vfio_pci_dmabuf.c
> @@ -272,6 +272,15 @@ int vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device *vdev, u32 flags,
> goto err_free_priv;
> }
>
> + /*
> + * See comment in vfio_pci_core_mmap(); ensure PCI regions
> + * were requested before returning DMABUFs that reference
> + * them. Barmap setup does this:
> + */
> + ret = vfio_pci_core_setup_barmap(vdev, get_dma_buf.region_index);
> + if (ret)
> + goto err_free_phys;
> +
> priv->vdev = vdev;
> priv->nr_ranges = get_dma_buf.nr_ranges;
> priv->size = length;
Wouldn't this get a lot easier if we just setup all the barmaps in
vfio_pci_core_enable(), conditional on pci_resource_len() just like we
use to filter in REGION_INFO?
I don't recall if there's some reason we've avoid this so far, maybe
others can shout it out if they do.
We already tear them all down in vfio_pci_core_disable(). It would be
a small patch to add that, which we would mark as Fixes:, then a small
follow-up on top of that that removes any then redundant or unnecessary
callers (all of them). Thoughts? Thanks,
Alex
BTW, cover letters are appreciated for multi-part series.
^ permalink raw reply
* Re: [PATCH] ALSA: virtio: drop an extaneous kernel-doc comment
From: Randy Dunlap @ 2026-04-16 22:00 UTC (permalink / raw)
To: linux-sound
Cc: Matias Ezequiel Vara Larsen, Michael S. Tsirkin, virtualization,
Jaroslav Kysela, Takashi Iwai
In-Reply-To: <20260216055956.2784399-1-rdunlap@infradead.org>
ping.
On 2/15/26 9:59 PM, Randy Dunlap wrote:
> Drop a kernel-doc struct comment since the struct member was removed.
> This eliminates a kernel-doc warning when make W=1 is used.
>
> virtio_pcm.h:65: warning: Excess struct member 'msg_last_enqueued'
> description in 'virtio_pcm_substream'
>
> Fixes: fe981e67568c ("ALSA: virtio: use ack callback")
> Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
> ---
> Cc: Anton Yakovlev <anton.yakovlev@opensynergy.com>
> Cc: Matias Ezequiel Vara Larsen <mvaralar@redhat.com>
> Cc: "Michael S. Tsirkin" <mst@redhat.com>
> Cc: virtualization@lists.linux.dev
> Cc: Jaroslav Kysela <perex@perex.cz>
> Cc: Takashi Iwai <tiwai@suse.com>
> Cc: linux-sound@vger.kernel.org
>
> sound/virtio/virtio_pcm.h | 1 -
> 1 file changed, 1 deletion(-)
>
> --- linux-next-20251210.orig/sound/virtio/virtio_pcm.h
> +++ linux-next-20251210/sound/virtio/virtio_pcm.h
> @@ -37,7 +37,6 @@ struct virtio_pcm_msg;
> * the device side at resume.
> * @msgs: Allocated I/O messages.
> * @nmsgs: Number of allocated I/O messages.
> - * @msg_last_enqueued: Index of the last I/O message added to the virtqueue.
> * @msg_count: Number of pending I/O messages in the virtqueue.
> * @msg_empty: Notify when msg_count is zero.
> */
--
~Randy
^ permalink raw reply
* Re: [PATCH v11 00/13] blk: honor isolcpus configuration
From: Aaron Tomlin @ 2026-04-16 19:38 UTC (permalink / raw)
To: axboe, kbusch, hch, sagi, mst
Cc: aacraid, James.Bottomley, martin.petersen, liyihang9,
kashyap.desai, sumit.saxena, shivasharan.srikanteshwara,
chandrakanth.patil, sathya.prakash, sreekanth.reddy,
suganath-prabu.subramani, ranjan.kumar, jinpu.wang, tglx, mingo,
peterz, juri.lelli, vincent.guittot, akpm, maz, ruanjinjie,
bigeasy, yphbchou0911, wagi, frederic, longman, chenridong, hare,
kch, ming.lei, tom.leiming, steve, sean, chjohnst, neelx, mproche,
nick.lange, linux-block, linux-kernel, virtualization, linux-nvme,
linux-scsi, megaraidlinux.pdl, mpi3mr-linuxdrv.pdl,
MPT-FusionLinux.pdl
In-Reply-To: <20260416192942.1243421-1-atomlin@atomlin.com>
On Thu, Apr 16, 2026 at 03:29:29PM -0400, Aaron Tomlin wrote:
> Please let me know your thoughts.
My apologies, I neglected to include the changelog.
Changes in v11:
- Completely rewrote the isolcpus=io_queue documentation in
Documentation/admin-guide/kernel-parameters.txt to clarify its exclusive
application to managed IRQs, queue allocation limits, vector exhaustion
prevention, and hardware interrupt routing (Ming Lei)
- Fixed a stack frame bloat issue by avoiding the on-stack declaration of
struct cpumask (Waiman Long)
- Linked to v10: https://lore.kernel.org/linux-nvme/20260401222312.772334-1-atomlin@atomlin.com/
Changes in v10:
- Fixed a page fault regression encountered when initialising secondary
queue maps (e.g., NVMe poll queues). Restored the qmap->queue_offset to
the mq_map assignment to ensure CPUs are strictly mapped to absolute
hardware indices (Keith Busch)
- Corrected the active_hctx tracker to utilise relative queue indices,
preventing out-of-bounds mask assignments
- Fixed the blk_mq_validate() sanity check to properly evaluate absolute
queue indices against the offset-adjusted loop index
- Corrected typographical errors within block/blk-mq-cpumap.c
(Keith Busch)
- Clarified the commit message regarding the removal of the !SMP fallback
code, explicitly noting that the core scheduler now mandates SMP
unconditionally (Sebastian Andrzej Siewior)
- Added missing "Signed-off-by:" tags to properly record the patch series
chain of custody
- Linked to v9: https://lore.kernel.org/lkml/20260330221047.630206-1-atomlin@atomlin.com/
Changes in v9:
- Added "Reviewed-by:" tags
- Introduced irq_spread_hk_filter() to safely restrict managed IRQ
affinity to housekeeping CPUs (Thomas Gleixner)
- Removed the unsafe global static variable blk_hk_online_mask from
blk-mq-cpumap.c and blk-mq.c. blk_mq_online_queue_affinity() now returns
a stable pointer, delegating safe intersection to the callers to prevent
concurrent modification races (Thomas Gleixner, Hannes Reinecke)
- Resolved BUG: kernel NULL pointer dereference in __blk_mq_all_tag_iter
reported by the kernel test robot during cpuhotplug rcutorture stress
testing
- Linked to v8: https://lore.kernel.org/lkml/20250905-isolcpus-io-queues-v8-0-885984c5daca@kernel.org/
Changes in v8:
- Added commit 524f5eea4bbe ("lib/group_cpus: remove !SMP code")
- Merged the new mapping logic directly into the existing function to
avoid special casing
- Refined the group_mask_cpus_evenly() implementation with the following
updates:
- Corrected the function name typo (changed group_masks_cpus_evenly to
group_mask_cpus_evenly)
- Updated the documentation comment to accurately reflect the function's
behavior
- Renamed the cpu_mask argument to mask for consistency
- Added a new patch for aacraid to include the missing number of queues
calculation
- Restricted updates to only affect SCSI drivers that support
PCI_IRQ_AFFINITY and do not utilize nvme-fabrics
- Removed the __free cleanup attribute usage for cpumask_var_t allocations
due to compatibility issues
- Updated the documentation to explicitly highlight the limitations
surrounding CPU offlining
- Collected accumulated Reviewed-by and Acked-by tags
- Linked to v7: https://patch.msgid.link/20250702-isolcpus-io-queues-v7-0-557aa7eacce4@kernel.org
Changes in v7:
- Sent out the first part of the series independently:
https://lore.kernel.org/all/20250617-isolcpus-queue-counters-v1-0-13923686b54b@kernel.org/
- Added comprehensive kernel command-line documentation
- Added validation logic to ensure the resulting CPU-to-queue mapping is
fully operational
- Rewrote the isolcpus mapping code to properly account for active
hardware contexts (hctx)
- Introduced blk_mq_map_hk_irq_queues, which utilizes the mask retrieved
from irq_get_affinity()
- Refactored blk_mq_map_hk_queues to require the caller to explicitly test
for HK_TYPE_MANAGED_IRQ
- Linked to v6: https://patch.msgid.link/20250424-isolcpus-io-queues-v6-0-9a53a870ca1f@kernel.org
Changes in v6:
- Reintroduced the io_queue type for the isolcpus kernel parameter
- Prevented the offlining of a housekeeping CPU if an isolated CPU is
still present, upgrading this behavior from a simple warning to a hard
restriction
- Linked to v5: https://lore.kernel.org/r/20250110-isolcpus-io-queues-v5-0-0e4f118680b0@kernel.org
Changes in v5:
- Rebased the series onto the latest for-6.14/block branch.
- Updated the documentation regarding the managed_irq parameters
- Reworded the commit message for "blk-mq: issue warning when offlining
hctx with online isolcpus" for better clarity
- Split the input and output parameters in the patch "lib/group_cpus: let
group_cpu_evenly return number of groups"
- Dropped the patch "sched/isolation: document HK_TYPE housekeeping
option"
- Linked to v4: https://lore.kernel.org/r/20241217-isolcpus-io-queues-v4-0-5d355fbb1e14@kernel.org
Changes in v4:
- Added the patch "blk-mq: issue warning when offlining hctx with online
isolcpus"
- Fixed the check in group_cpus_evenly(); the condition now properly uses
housekeeping_enabled() instead of cpumask_weight(), as the latter always
returns a valid mask
- Dropped the Fixes: tag from "lib/group_cpus.c: honor housekeeping config
when grouping CPUs"
- Fixed an overlong line warning in the patch "scsi: use block layer
helpers to calculate num of queues"
- Dropped the patch "sched/isolation: Add io_queue housekeeping option" in
favor of simply documenting the housekeeping hk_type enum
- Added the patch "lib/group_cpus: let group_cpu_evenly return number of
groups"
- Collected accumulated Reviewed-by and Acked-by tags
- Split the patchset by moving foundational changes into a separate
preparation series:
https://lore.kernel.org/linux-nvme/20241202-refactor-blk-affinity-helpers-v6-0-27211e9c2cd5@kernel.org/
- Linked to v3: https://lore.kernel.org/r/20240806-isolcpus-io-queues-v3-0-da0eecfeaf8b@suse.de
Changes in v3:
- Integrated patches from Ming Lei
(https://lore.kernel.org/all/20210709081005.421340-1-ming.lei@redhat.com/):
"virtio: add APIs for retrieving vq affinity" and "blk-mq: introduce
blk_mq_dev_map_queues"
- Replaced all instances of blk_mq_pci_map_queues and
blk_mq_virtio_map_queues with the new unified blk_mq_dev_map_queues
- Updated and expanded the helper functions used for calculating the
number of queues
- Added the CPU-to-hctx mapping function specifically to support the
isolcpus=io_queue parameter
- Documented the hk_type enum and the newly introduced isolcpus=io_queue
parameter
- Added the patch "scsi: pm8001: do not overwrite PCI queue mapping"
- Linked to v2: https://lore.kernel.org/r/20240627-isolcpus-io-queues-v2-0-26a32e3c4f75@suse.de
Changes in v2:
- Updated the feature documentation for clarity and completeness
- Split the blk/nvme-pci patch into smaller, logical commits
- Dropped the HK_TYPE_IO_QUEUE macro in favor of reusing
HK_TYPE_MANAGED_IRQ
- Linked to v1: https://lore.kernel.org/r/20240621-isolcpus-io-queues-v1-0-8b169bf41083@suse.de
>
> Aaron Tomlin (1):
> genirq/affinity: Restrict managed IRQ affinity to housekeeping CPUs
>
> Daniel Wagner (12):
> scsi: aacraid: use block layer helpers to calculate num of queues
> lib/group_cpus: remove dead !SMP code
> lib/group_cpus: Add group_mask_cpus_evenly()
> genirq/affinity: Add cpumask to struct irq_affinity
> blk-mq: add blk_mq_{online|possible}_queue_affinity
> nvme-pci: use block layer helpers to constrain queue affinity
> scsi: Use block layer helpers to constrain queue affinity
> virtio: blk/scsi: use block layer helpers to constrain queue affinity
> isolation: Introduce io_queue isolcpus type
> blk-mq: use hk cpus only when isolcpus=io_queue is enabled
> blk-mq: prevent offlining hk CPUs with associated online isolated CPUs
> docs: add io_queue flag to isolcpus
>
> .../admin-guide/kernel-parameters.txt | 30 ++-
> block/blk-mq-cpumap.c | 192 ++++++++++++++++--
> block/blk-mq.c | 42 ++++
> drivers/block/virtio_blk.c | 4 +-
> drivers/nvme/host/pci.c | 1 +
> drivers/scsi/aacraid/comminit.c | 3 +-
> drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 1 +
> drivers/scsi/megaraid/megaraid_sas_base.c | 5 +-
> drivers/scsi/mpi3mr/mpi3mr_fw.c | 6 +-
> drivers/scsi/mpt3sas/mpt3sas_base.c | 5 +-
> drivers/scsi/pm8001/pm8001_init.c | 1 +
> drivers/scsi/virtio_scsi.c | 5 +-
> include/linux/blk-mq.h | 2 +
> include/linux/group_cpus.h | 3 +
> include/linux/interrupt.h | 16 +-
> include/linux/sched/isolation.h | 1 +
> kernel/irq/affinity.c | 38 +++-
> kernel/sched/isolation.c | 7 +
> lib/group_cpus.c | 65 ++++--
> 19 files changed, 379 insertions(+), 48 deletions(-)
>
>
> base-commit: 3cd8b194bf3428dfa53120fee47e827a7c495815
> --
> 2.51.0
>
--
Aaron Tomlin
^ permalink raw reply
* RE: [EXTERNAL] Re: [PATCH net] hv_sock: Report EOF instead of -EIO for FIN
From: Dexuan Cui @ 2026-04-16 19:30 UTC (permalink / raw)
To: Stefano Garzarella
Cc: KY Srinivasan, Haiyang Zhang, wei.liu@kernel.org, Long Li,
davem@davemloft.net, edumazet@google.com, kuba@kernel.org,
pabeni@redhat.com, horms@kernel.org, niuxuewei.nxw@antgroup.com,
linux-hyperv@vger.kernel.org, virtualization@lists.linux.dev,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
stable@vger.kernel.org, Ben Hillis, Mitchell Levy
In-Reply-To: <SA1PR21MB6921C57E27E17305E56BC0F9BF222@SA1PR21MB6921.namprd21.prod.outlook.com>
> From: Dexuan Cui
> Sent: Wednesday, April 15, 2026 9:56 AM
> To: 'Stefano Garzarella' <sgarzare@redhat.com>
> > ...
> > Can we drop `need_refill` entirly and just check `hvs->recv_desc` here?
>
> OK. Will post v2 later today.
>
> > Mainly because now the comment we are adding is confusing me about what
> > `need_refill` means.
> >
> > The rest LGTM.
> >
> > Thanks,
> > Stefano
Hi Stefano, I just posted v2 here:
https://lore.kernel.org/linux-hyperv/20260416191433.840637-1-decui@microsoft.com/T/#u
^ permalink raw reply
* [PATCH v11 13/13] docs: add io_queue flag to isolcpus
From: Aaron Tomlin @ 2026-04-16 19:29 UTC (permalink / raw)
To: axboe, kbusch, hch, sagi, mst
Cc: atomlin, aacraid, James.Bottomley, martin.petersen, liyihang9,
kashyap.desai, sumit.saxena, shivasharan.srikanteshwara,
chandrakanth.patil, sathya.prakash, sreekanth.reddy,
suganath-prabu.subramani, ranjan.kumar, jinpu.wang, tglx, mingo,
peterz, juri.lelli, vincent.guittot, akpm, maz, ruanjinjie,
bigeasy, yphbchou0911, wagi, frederic, longman, chenridong, hare,
kch, ming.lei, tom.leiming, steve, sean, chjohnst, neelx, mproche,
nick.lange, linux-block, linux-kernel, virtualization, linux-nvme,
linux-scsi, megaraidlinux.pdl, mpi3mr-linuxdrv.pdl,
MPT-FusionLinux.pdl
In-Reply-To: <20260416192942.1243421-1-atomlin@atomlin.com>
From: Daniel Wagner <wagi@kernel.org>
The io_queue flag informs multiqueue device drivers where to place
hardware queues. Document this new flag in the isolcpus
command-line argument description.
Signed-off-by: Daniel Wagner <wagi@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
[atomlin: Refined io_queue kernel parameter documentation]
Signed-off-by: Aaron Tomlin <atomlin@atomlin.com>
---
.../admin-guide/kernel-parameters.txt | 30 ++++++++++++++++++-
1 file changed, 29 insertions(+), 1 deletion(-)
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 4510b4b3c416..52ede95db56f 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2827,7 +2827,6 @@ Kernel parameters
"number of CPUs in system - 1".
managed_irq
-
Isolate from being targeted by managed interrupts
which have an interrupt mask containing isolated
CPUs. The affinity of managed interrupts is
@@ -2850,6 +2849,35 @@ Kernel parameters
housekeeping CPUs has no influence on those
queues.
+ io_queue
+ Applicable to managed IRQs only. Restrict
+ multiqueue hardware queue allocation to online
+ housekeeping CPUs. This guarantees that all
+ managed hardware completion interrupts are routed
+ exclusively to housekeeping cores, shielding
+ isolated CPUs from I/O interruptions even if they
+ initiated the request.
+
+ The io_queue configuration takes precedence over
+ managed_irq. When io_queue is used, managed_irq
+ placement constraints have no effect.
+
+ Note: Using io_queue restricts the number of
+ allocated hardware queues to match the number of
+ housekeeping CPUs. This prevents MSI-X vector
+ exhaustion and forces isolated CPUs to share
+ submission queues.
+
+ Note: Offlining housekeeping CPUs which serve
+ isolated CPUs will fail. The isolated CPUs must
+ be offlined before offlining the housekeeping
+ CPUs.
+
+ Note: When I/O is submitted by an application on
+ an isolated CPU, the hardware completion
+ interrupt is handled entirely by a housekeeping
+ CPU.
+
The format of <cpu-list> is described above.
iucv= [HW,NET]
--
2.51.0
^ permalink raw reply related
* [PATCH v11 12/13] genirq/affinity: Restrict managed IRQ affinity to housekeeping CPUs
From: Aaron Tomlin @ 2026-04-16 19:29 UTC (permalink / raw)
To: axboe, kbusch, hch, sagi, mst
Cc: atomlin, aacraid, James.Bottomley, martin.petersen, liyihang9,
kashyap.desai, sumit.saxena, shivasharan.srikanteshwara,
chandrakanth.patil, sathya.prakash, sreekanth.reddy,
suganath-prabu.subramani, ranjan.kumar, jinpu.wang, tglx, mingo,
peterz, juri.lelli, vincent.guittot, akpm, maz, ruanjinjie,
bigeasy, yphbchou0911, wagi, frederic, longman, chenridong, hare,
kch, ming.lei, tom.leiming, steve, sean, chjohnst, neelx, mproche,
nick.lange, linux-block, linux-kernel, virtualization, linux-nvme,
linux-scsi, megaraidlinux.pdl, mpi3mr-linuxdrv.pdl,
MPT-FusionLinux.pdl
In-Reply-To: <20260416192942.1243421-1-atomlin@atomlin.com>
At present, the managed interrupt spreading algorithm distributes vectors
across all available CPUs within a given node or system. On systems
employing CPU isolation (e.g., "isolcpus=io_queue"), this behaviour
defeats the primary purpose of isolation by routing hardware interrupts
(such as NVMe completion queues) directly to isolated cores.
Update irq_create_affinity_masks() to respect the housekeeping CPU mask.
Introduce irq_spread_hk_filter() to intersect the natively calculated
affinity mask with the HK_TYPE_IO_QUEUE mask, thereby keeping managed
interrupts off isolated CPUs.
To ensure strict isolation whilst guaranteeing a valid routing destination:
1. Fallback mechanism: Should the initial spreading logic assign a
vector exclusively to isolated CPUs (resulting in an empty
intersection), the filter safely falls back to the system's
online housekeeping CPUs.
2. Hotplug safety: The fallback utilises data_race(cpu_online_mask)
instead of allocating a local cpumask snapshot. This circumvents
CONFIG_CPUMASK_OFFSTACK stack bloat hazards on high-core-count
systems. Furthermore, it prevents deadlocks with concurrent CPU
hotplug operations (e.g., during storage driver error recovery)
by eliminating the need to hold the CPU hotplug read lock.
3. Fast-path optimisation: The filtering logic is conditionally
executed only if housekeeping is enabled, thereby ensuring zero
overhead for standard configurations.
Signed-off-by: Aaron Tomlin <atomlin@atomlin.com>
---
kernel/irq/affinity.c | 26 +++++++++++++++++++++++++-
1 file changed, 25 insertions(+), 1 deletion(-)
diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
index e0cf70a99339..03e914ffd720 100644
--- a/kernel/irq/affinity.c
+++ b/kernel/irq/affinity.c
@@ -8,6 +8,24 @@
#include <linux/slab.h>
#include <linux/cpu.h>
#include <linux/group_cpus.h>
+#include <linux/sched/isolation.h>
+
+/**
+ * irq_spread_hk_filter - Restrict an interrupt affinity mask to housekeeping CPUs
+ * @mask: The interrupt affinity mask to filter (in/out)
+ * @hk_mask: The system's housekeeping CPU mask
+ *
+ * Intersects @mask with @hk_mask to keep interrupts off isolated CPUs.
+ * If this intersection is empty (meaning all targeted CPUs were isolated),
+ * it falls back to the online housekeeping CPUs to guarantee a valid
+ * routing destination.
+ */
+static void irq_spread_hk_filter(struct cpumask *mask,
+ const struct cpumask *hk_mask)
+{
+ if (!cpumask_and(mask, mask, hk_mask))
+ cpumask_and(mask, hk_mask, data_race(cpu_online_mask));
+}
static void default_calc_sets(struct irq_affinity *affd, unsigned int affvecs)
{
@@ -27,6 +45,8 @@ irq_create_affinity_masks(unsigned int nvecs, struct irq_affinity *affd)
{
unsigned int affvecs, curvec, usedvecs, i;
struct irq_affinity_desc *masks = NULL;
+ const struct cpumask *hk_mask = housekeeping_cpumask(HK_TYPE_IO_QUEUE);
+ bool hk_enabled = housekeeping_enabled(HK_TYPE_IO_QUEUE);
/*
* Determine the number of vectors which need interrupt affinities
@@ -83,8 +103,12 @@ irq_create_affinity_masks(unsigned int nvecs, struct irq_affinity *affd)
return NULL;
}
- for (int j = 0; j < nr_masks; j++)
+ for (int j = 0; j < nr_masks; j++) {
cpumask_copy(&masks[curvec + j].mask, &result[j]);
+ if (hk_enabled)
+ irq_spread_hk_filter(&masks[curvec + j].mask,
+ hk_mask);
+ }
kfree(result);
curvec += nr_masks;
--
2.51.0
^ permalink raw reply related
* [PATCH v11 11/13] blk-mq: prevent offlining hk CPUs with associated online isolated CPUs
From: Aaron Tomlin @ 2026-04-16 19:29 UTC (permalink / raw)
To: axboe, kbusch, hch, sagi, mst
Cc: atomlin, aacraid, James.Bottomley, martin.petersen, liyihang9,
kashyap.desai, sumit.saxena, shivasharan.srikanteshwara,
chandrakanth.patil, sathya.prakash, sreekanth.reddy,
suganath-prabu.subramani, ranjan.kumar, jinpu.wang, tglx, mingo,
peterz, juri.lelli, vincent.guittot, akpm, maz, ruanjinjie,
bigeasy, yphbchou0911, wagi, frederic, longman, chenridong, hare,
kch, ming.lei, tom.leiming, steve, sean, chjohnst, neelx, mproche,
nick.lange, linux-block, linux-kernel, virtualization, linux-nvme,
linux-scsi, megaraidlinux.pdl, mpi3mr-linuxdrv.pdl,
MPT-FusionLinux.pdl
In-Reply-To: <20260416192942.1243421-1-atomlin@atomlin.com>
From: Daniel Wagner <wagi@kernel.org>
When isolcpus=io_queue is enabled, and the last housekeeping CPU for a
given hctx goes offline, there would be no CPU left to handle I/O. To
prevent I/O stalls, prevent offlining housekeeping CPUs that are still
serving isolated CPUs.
When isolcpus=io_queue is enabled and the last housekeeping CPU
for a given hctx goes offline, no CPU would be left to handle I/O.
To prevent I/O stalls, disallow offlining housekeeping CPUs that are
still serving isolated CPUs.
Signed-off-by: Daniel Wagner <wagi@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Aaron Tomlin <atomlin@atomlin.com>
---
block/blk-mq.c | 42 ++++++++++++++++++++++++++++++++++++++++++
1 file changed, 42 insertions(+)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4c5c16cce4f8..4257d5b26641 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -3720,6 +3720,43 @@ static bool blk_mq_hctx_has_requests(struct blk_mq_hw_ctx *hctx)
return data.has_rq;
}
+static bool blk_mq_hctx_can_offline_hk_cpu(struct blk_mq_hw_ctx *hctx,
+ unsigned int this_cpu)
+{
+ const struct cpumask *hk_mask = housekeeping_cpumask(HK_TYPE_IO_QUEUE);
+
+ for (int i = 0; i < hctx->nr_ctx; i++) {
+ struct blk_mq_ctx *ctx = hctx->ctxs[i];
+
+ if (ctx->cpu == this_cpu)
+ continue;
+
+ /*
+ * Check if this context has at least one online
+ * housekeeping CPU; in this case the hardware context is
+ * usable.
+ */
+ if (cpumask_test_cpu(ctx->cpu, hk_mask) &&
+ cpu_online(ctx->cpu))
+ break;
+
+ /*
+ * The context doesn't have any online housekeeping CPUs,
+ * but there might be an online isolated CPU mapped to
+ * it.
+ */
+ if (cpu_is_offline(ctx->cpu))
+ continue;
+
+ pr_warn("%s: trying to offline hctx%d but there is still an online isolcpu CPU %d mapped to it\n",
+ hctx->queue->disk->disk_name,
+ hctx->queue_num, ctx->cpu);
+ return false;
+ }
+
+ return true;
+}
+
static bool blk_mq_hctx_has_online_cpu(struct blk_mq_hw_ctx *hctx,
unsigned int this_cpu)
{
@@ -3752,6 +3789,11 @@ static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node)
struct blk_mq_hw_ctx, cpuhp_online);
int ret = 0;
+ if (housekeeping_enabled(HK_TYPE_IO_QUEUE)) {
+ if (!blk_mq_hctx_can_offline_hk_cpu(hctx, cpu))
+ return -EINVAL;
+ }
+
if (!hctx->nr_ctx || blk_mq_hctx_has_online_cpu(hctx, cpu))
return 0;
--
2.51.0
^ permalink raw reply related
* [PATCH v11 10/13] blk-mq: use hk cpus only when isolcpus=io_queue is enabled
From: Aaron Tomlin @ 2026-04-16 19:29 UTC (permalink / raw)
To: axboe, kbusch, hch, sagi, mst
Cc: atomlin, aacraid, James.Bottomley, martin.petersen, liyihang9,
kashyap.desai, sumit.saxena, shivasharan.srikanteshwara,
chandrakanth.patil, sathya.prakash, sreekanth.reddy,
suganath-prabu.subramani, ranjan.kumar, jinpu.wang, tglx, mingo,
peterz, juri.lelli, vincent.guittot, akpm, maz, ruanjinjie,
bigeasy, yphbchou0911, wagi, frederic, longman, chenridong, hare,
kch, ming.lei, tom.leiming, steve, sean, chjohnst, neelx, mproche,
nick.lange, linux-block, linux-kernel, virtualization, linux-nvme,
linux-scsi, megaraidlinux.pdl, mpi3mr-linuxdrv.pdl,
MPT-FusionLinux.pdl
In-Reply-To: <20260416192942.1243421-1-atomlin@atomlin.com>
From: Daniel Wagner <wagi@kernel.org>
Extend the capabilities of the generic CPU to hardware queue (hctx)
mapping code, so it maps houskeeping CPUs and isolated CPUs to the
hardware queues evenly.
A hctx is only operational when there is at least one online
housekeeping CPU assigned (aka active_hctx). Thus, check the final
mapping that there is no hctx which has only offline housekeeing CPU and
online isolated CPUs.
Example mapping result:
16 online CPUs
isolcpus=io_queue,2-3,6-7,12-13
Queue mapping:
hctx0: default 0 2
hctx1: default 1 3
hctx2: default 4 6
hctx3: default 5 7
hctx4: default 8 12
hctx5: default 9 13
hctx6: default 10
hctx7: default 11
hctx8: default 14
hctx9: default 15
IRQ mapping:
irq 42 affinity 0 effective 0 nvme0q0
irq 43 affinity 0 effective 0 nvme0q1
irq 44 affinity 1 effective 1 nvme0q2
irq 45 affinity 4 effective 4 nvme0q3
irq 46 affinity 5 effective 5 nvme0q4
irq 47 affinity 8 effective 8 nvme0q5
irq 48 affinity 9 effective 9 nvme0q6
irq 49 affinity 10 effective 10 nvme0q7
irq 50 affinity 11 effective 11 nvme0q8
irq 51 affinity 14 effective 14 nvme0q9
irq 52 affinity 15 effective 15 nvme0q10
A corner case is when the number of online CPUs and present CPUs
differ and the driver asks for less queues than online CPUs, e.g.
8 online CPUs, 16 possible CPUs
isolcpus=io_queue,2-3,6-7,12-13
virtio_blk.num_request_queues=2
Queue mapping:
hctx0: default 0 1 2 3 4 5 6 7 8 12 13
hctx1: default 9 10 11 14 15
IRQ mapping
irq 27 affinity 0 effective 0 virtio0-config
irq 28 affinity 0-1,4-5,8 effective 5 virtio0-req.0
irq 29 affinity 9-11,14-15 effective 0 virtio0-req.1
Noteworthy is that for the normal/default configuration (!isoclpus) the
mapping will change for systems which have non hyperthreading CPUs. The
main assignment loop will completely rely that group_mask_cpus_evenly to
do the right thing. The old code would distribute the CPUs linearly over
the hardware context:
queue mapping for /dev/nvme0n1
hctx0: default 0 8
hctx1: default 1 9
hctx2: default 2 10
hctx3: default 3 11
hctx4: default 4 12
hctx5: default 5 13
hctx6: default 6 14
hctx7: default 7 15
The assign each hardware context the map generated by the
group_mask_cpus_evenly function:
queue mapping for /dev/nvme0n1
hctx0: default 0 1
hctx1: default 2 3
hctx2: default 4 5
hctx3: default 6 7
hctx4: default 8 9
hctx5: default 10 11
hctx6: default 12 13
hctx7: default 14 15
In case of hyperthreading CPUs, the resulting map stays the same.
Signed-off-by: Daniel Wagner <wagi@kernel.org>
[atomlin:
- Fixed absolute vs. relative hardware queue index mix-up in
blk_mq_map_queues and validation checks; fixed typographical
errors
- Reduced stack frame size of blk_mq_num_queues()]
Signed-off-by: Aaron Tomlin <atomlin@atomlin.com>
---
block/blk-mq-cpumap.c | 168 +++++++++++++++++++++++++++++++++++++-----
1 file changed, 150 insertions(+), 18 deletions(-)
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index 8244ecf87835..f7c5f52f3b35 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -22,7 +22,11 @@ static unsigned int blk_mq_num_queues(const struct cpumask *mask,
{
unsigned int num;
- num = cpumask_weight(mask);
+ if (housekeeping_enabled(HK_TYPE_IO_QUEUE))
+ num = cpumask_weight_and(mask, housekeeping_cpumask(HK_TYPE_IO_QUEUE));
+ else
+ num = cpumask_weight(mask);
+
return min_not_zero(num, max_queues);
}
@@ -31,9 +35,13 @@ static unsigned int blk_mq_num_queues(const struct cpumask *mask,
*
* Returns an affinity mask that represents the queue-to-CPU mapping
* requested by the block layer based on possible CPUs.
+ * This helper takes isolcpus settings into account.
*/
const struct cpumask *blk_mq_possible_queue_affinity(void)
{
+ if (housekeeping_enabled(HK_TYPE_IO_QUEUE))
+ return housekeeping_cpumask(HK_TYPE_IO_QUEUE);
+
return cpu_possible_mask;
}
EXPORT_SYMBOL_GPL(blk_mq_possible_queue_affinity);
@@ -46,6 +54,14 @@ EXPORT_SYMBOL_GPL(blk_mq_possible_queue_affinity);
*/
const struct cpumask *blk_mq_online_queue_affinity(void)
{
+ /*
+ * Return the stable housekeeping mask if enabled. Callers (e.g.,
+ * the IRQ affinity core) are responsible for safely intersecting
+ * this with a local snapshot of the online mask.
+ */
+ if (housekeeping_enabled(HK_TYPE_IO_QUEUE))
+ return housekeeping_cpumask(HK_TYPE_IO_QUEUE);
+
return cpu_online_mask;
}
EXPORT_SYMBOL_GPL(blk_mq_online_queue_affinity);
@@ -57,7 +73,8 @@ EXPORT_SYMBOL_GPL(blk_mq_online_queue_affinity);
* ignored.
*
* Calculates the number of queues to be used for a multiqueue
- * device based on the number of possible CPUs.
+ * device based on the number of possible CPUs. This helper
+ * takes isolcpus settings into account.
*/
unsigned int blk_mq_num_possible_queues(unsigned int max_queues)
{
@@ -72,7 +89,8 @@ EXPORT_SYMBOL_GPL(blk_mq_num_possible_queues);
* ignored.
*
* Calculates the number of queues to be used for a multiqueue
- * device based on the number of online CPUs.
+ * device based on the number of online CPUs. This helper
+ * takes isolcpus settings into account.
*/
unsigned int blk_mq_num_online_queues(unsigned int max_queues)
{
@@ -80,23 +98,104 @@ unsigned int blk_mq_num_online_queues(unsigned int max_queues)
}
EXPORT_SYMBOL_GPL(blk_mq_num_online_queues);
+static bool blk_mq_validate(struct blk_mq_queue_map *qmap,
+ const struct cpumask *active_hctx)
+{
+ /*
+ * Verify if the mapping is usable when housekeeping
+ * configuration is enabled
+ */
+
+ for (int queue = 0; queue < qmap->nr_queues; queue++) {
+ int cpu;
+
+ if (cpumask_test_cpu(queue, active_hctx)) {
+ /*
+ * This hctx has at least one online CPU thus it
+ * is able to serve any assigned isolated CPU.
+ */
+ continue;
+ }
+
+ /*
+ * There is no housekeeping online CPU for this hctx, all
+ * good as long as all non-housekeeping CPUs are also
+ * offline.
+ */
+ for_each_online_cpu(cpu) {
+ if (qmap->mq_map[cpu] != qmap->queue_offset + queue)
+ continue;
+
+ pr_warn("Unable to create a usable CPU-to-queue mapping with the given constraints\n");
+ return false;
+ }
+ }
+
+ return true;
+}
+
+static void blk_mq_map_fallback(struct blk_mq_queue_map *qmap)
+{
+ unsigned int cpu;
+
+ /*
+ * Map all CPUs to the first hctx to ensure at least one online
+ * CPU is serving it.
+ */
+ for_each_possible_cpu(cpu)
+ qmap->mq_map[cpu] = 0;
+}
+
void blk_mq_map_queues(struct blk_mq_queue_map *qmap)
{
- const struct cpumask *masks;
+ struct cpumask *masks __free(kfree) = NULL;
+ const struct cpumask *constraint;
unsigned int queue, cpu, nr_masks;
+ cpumask_var_t active_hctx;
- masks = group_cpus_evenly(qmap->nr_queues, &nr_masks);
- if (!masks) {
- for_each_possible_cpu(cpu)
- qmap->mq_map[cpu] = qmap->queue_offset;
- return;
- }
+ if (!zalloc_cpumask_var(&active_hctx, GFP_KERNEL))
+ goto fallback;
+
+ if (housekeeping_enabled(HK_TYPE_IO_QUEUE))
+ constraint = housekeeping_cpumask(HK_TYPE_IO_QUEUE);
+ else
+ constraint = cpu_possible_mask;
+
+ /* Map CPUs to the hardware contexts (hctx) */
+ masks = group_mask_cpus_evenly(qmap->nr_queues, constraint, &nr_masks);
+ if (!masks)
+ goto free_fallback;
for (queue = 0; queue < qmap->nr_queues; queue++) {
- for_each_cpu(cpu, &masks[queue % nr_masks])
+ unsigned int idx = (qmap->queue_offset + queue) % nr_masks;
+
+ for_each_cpu(cpu, &masks[idx]) {
qmap->mq_map[cpu] = qmap->queue_offset + queue;
+
+ if (cpu_online(cpu))
+ cpumask_set_cpu(queue, active_hctx);
+ }
}
- kfree(masks);
+
+ /* Map any unassigned CPU evenly to the hardware contexts (hctx) */
+ queue = cpumask_first(active_hctx);
+ for_each_cpu_andnot(cpu, cpu_possible_mask, constraint) {
+ qmap->mq_map[cpu] = qmap->queue_offset + queue;
+ queue = cpumask_next_wrap(queue, active_hctx);
+ }
+
+ if (!blk_mq_validate(qmap, active_hctx))
+ goto free_fallback;
+
+ free_cpumask_var(active_hctx);
+
+ return;
+
+free_fallback:
+ free_cpumask_var(active_hctx);
+
+fallback:
+ blk_mq_map_fallback(qmap);
}
EXPORT_SYMBOL_GPL(blk_mq_map_queues);
@@ -133,24 +232,57 @@ void blk_mq_map_hw_queues(struct blk_mq_queue_map *qmap,
struct device *dev, unsigned int offset)
{
- const struct cpumask *mask;
+ cpumask_var_t active_hctx, mask;
unsigned int queue, cpu;
if (!dev->bus->irq_get_affinity)
goto fallback;
+ if (!zalloc_cpumask_var(&active_hctx, GFP_KERNEL))
+ goto fallback;
+
+ if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) {
+ free_cpumask_var(active_hctx);
+ goto fallback;
+ }
+
+ /* Map CPUs to the hardware contexts (hctx) */
for (queue = 0; queue < qmap->nr_queues; queue++) {
- mask = dev->bus->irq_get_affinity(dev, queue + offset);
- if (!mask)
- goto fallback;
+ const struct cpumask *affinity_mask;
- for_each_cpu(cpu, mask)
+ affinity_mask = dev->bus->irq_get_affinity(dev, offset + queue);
+ if (!affinity_mask)
+ goto free_fallback;
+
+ for_each_cpu(cpu, affinity_mask) {
qmap->mq_map[cpu] = qmap->queue_offset + queue;
+
+ cpumask_set_cpu(cpu, mask);
+ if (cpu_online(cpu))
+ cpumask_set_cpu(queue, active_hctx);
+ }
}
+ /* Map any unassigned CPU evenly to the hardware contexts (hctx) */
+ queue = cpumask_first(active_hctx);
+ for_each_cpu_andnot(cpu, cpu_possible_mask, mask) {
+ qmap->mq_map[cpu] = qmap->queue_offset + queue;
+ queue = cpumask_next_wrap(queue, active_hctx);
+ }
+
+ if (!blk_mq_validate(qmap, active_hctx))
+ goto free_fallback;
+
+ free_cpumask_var(active_hctx);
+ free_cpumask_var(mask);
+
return;
+free_fallback:
+ free_cpumask_var(active_hctx);
+ free_cpumask_var(mask);
+
fallback:
- blk_mq_map_queues(qmap);
+ blk_mq_map_fallback(qmap);
}
EXPORT_SYMBOL_GPL(blk_mq_map_hw_queues);
--
2.51.0
^ permalink raw reply related
* [PATCH v11 09/13] isolation: Introduce io_queue isolcpus type
From: Aaron Tomlin @ 2026-04-16 19:29 UTC (permalink / raw)
To: axboe, kbusch, hch, sagi, mst
Cc: atomlin, aacraid, James.Bottomley, martin.petersen, liyihang9,
kashyap.desai, sumit.saxena, shivasharan.srikanteshwara,
chandrakanth.patil, sathya.prakash, sreekanth.reddy,
suganath-prabu.subramani, ranjan.kumar, jinpu.wang, tglx, mingo,
peterz, juri.lelli, vincent.guittot, akpm, maz, ruanjinjie,
bigeasy, yphbchou0911, wagi, frederic, longman, chenridong, hare,
kch, ming.lei, tom.leiming, steve, sean, chjohnst, neelx, mproche,
nick.lange, linux-block, linux-kernel, virtualization, linux-nvme,
linux-scsi, megaraidlinux.pdl, mpi3mr-linuxdrv.pdl,
MPT-FusionLinux.pdl
In-Reply-To: <20260416192942.1243421-1-atomlin@atomlin.com>
From: Daniel Wagner <wagi@kernel.org>
Multiqueue drivers spread I/O queues across all CPUs for optimal
performance. However, these drivers are not aware of CPU isolation
requirements and will distribute queues without considering the isolcpus
configuration.
Introduce a new isolcpus mask that allows users to define which CPUs
should have I/O queues assigned. This is similar to managed_irq, but
intended for drivers that do not use the managed IRQ infrastructure
Signed-off-by: Daniel Wagner <wagi@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Aaron Tomlin <atomlin@atomlin.com>
---
include/linux/sched/isolation.h | 1 +
kernel/sched/isolation.c | 7 +++++++
2 files changed, 8 insertions(+)
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index dc3975ff1b2e..7b266fc2a405 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -18,6 +18,7 @@ enum hk_type {
HK_TYPE_MANAGED_IRQ,
/* Inverse of boot-time nohz_full= or isolcpus=nohz arguments */
HK_TYPE_KERNEL_NOISE,
+ HK_TYPE_IO_QUEUE,
HK_TYPE_MAX,
/*
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index ef152d401fe2..3406e3024fd4 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -16,6 +16,7 @@ enum hk_flags {
HK_FLAG_DOMAIN = BIT(HK_TYPE_DOMAIN),
HK_FLAG_MANAGED_IRQ = BIT(HK_TYPE_MANAGED_IRQ),
HK_FLAG_KERNEL_NOISE = BIT(HK_TYPE_KERNEL_NOISE),
+ HK_FLAG_IO_QUEUE = BIT(HK_TYPE_IO_QUEUE),
};
DEFINE_STATIC_KEY_FALSE(housekeeping_overridden);
@@ -340,6 +341,12 @@ static int __init housekeeping_isolcpus_setup(char *str)
continue;
}
+ if (!strncmp(str, "io_queue,", 9)) {
+ str += 9;
+ flags |= HK_FLAG_IO_QUEUE;
+ continue;
+ }
+
/*
* Skip unknown sub-parameter and validate that it is not
* containing an invalid character.
--
2.51.0
^ permalink raw reply related
* [PATCH v11 08/13] virtio: blk/scsi: use block layer helpers to constrain queue affinity
From: Aaron Tomlin @ 2026-04-16 19:29 UTC (permalink / raw)
To: axboe, kbusch, hch, sagi, mst
Cc: atomlin, aacraid, James.Bottomley, martin.petersen, liyihang9,
kashyap.desai, sumit.saxena, shivasharan.srikanteshwara,
chandrakanth.patil, sathya.prakash, sreekanth.reddy,
suganath-prabu.subramani, ranjan.kumar, jinpu.wang, tglx, mingo,
peterz, juri.lelli, vincent.guittot, akpm, maz, ruanjinjie,
bigeasy, yphbchou0911, wagi, frederic, longman, chenridong, hare,
kch, ming.lei, tom.leiming, steve, sean, chjohnst, neelx, mproche,
nick.lange, linux-block, linux-kernel, virtualization, linux-nvme,
linux-scsi, megaraidlinux.pdl, mpi3mr-linuxdrv.pdl,
MPT-FusionLinux.pdl
In-Reply-To: <20260416192942.1243421-1-atomlin@atomlin.com>
From: Daniel Wagner <wagi@kernel.org>
Ensure that IRQ affinity setup also respects the queue-to-CPU mapping
constraints provided by the block layer. This allows the virtio drivers
to avoid assigning interrupts to CPUs that the block layer has excluded
(e.g., isolated CPUs).
Signed-off-by: Daniel Wagner <wagi@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Aaron Tomlin <atomlin@atomlin.com>
---
drivers/block/virtio_blk.c | 4 +++-
drivers/scsi/virtio_scsi.c | 5 ++++-
2 files changed, 7 insertions(+), 2 deletions(-)
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index b1c9a27fe00f..9d737510454b 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -964,7 +964,9 @@ static int init_vq(struct virtio_blk *vblk)
unsigned short num_vqs;
unsigned short num_poll_vqs;
struct virtio_device *vdev = vblk->vdev;
- struct irq_affinity desc = { 0, };
+ struct irq_affinity desc = {
+ .mask = blk_mq_possible_queue_affinity(),
+ };
err = virtio_cread_feature(vdev, VIRTIO_BLK_F_MQ,
struct virtio_blk_config, num_queues,
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 0ed8558dad72..520a7da5386e 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -849,7 +849,10 @@ static int virtscsi_init(struct virtio_device *vdev,
u32 num_vqs, num_poll_vqs, num_req_vqs;
struct virtqueue_info *vqs_info;
struct virtqueue **vqs;
- struct irq_affinity desc = { .pre_vectors = 2 };
+ struct irq_affinity desc = {
+ .pre_vectors = 2,
+ .mask = blk_mq_possible_queue_affinity(),
+ };
num_req_vqs = vscsi->num_queues;
num_vqs = num_req_vqs + VIRTIO_SCSI_VQ_BASE;
--
2.51.0
^ permalink raw reply related
* [PATCH v11 07/13] scsi: Use block layer helpers to constrain queue affinity
From: Aaron Tomlin @ 2026-04-16 19:29 UTC (permalink / raw)
To: axboe, kbusch, hch, sagi, mst
Cc: atomlin, aacraid, James.Bottomley, martin.petersen, liyihang9,
kashyap.desai, sumit.saxena, shivasharan.srikanteshwara,
chandrakanth.patil, sathya.prakash, sreekanth.reddy,
suganath-prabu.subramani, ranjan.kumar, jinpu.wang, tglx, mingo,
peterz, juri.lelli, vincent.guittot, akpm, maz, ruanjinjie,
bigeasy, yphbchou0911, wagi, frederic, longman, chenridong, hare,
kch, ming.lei, tom.leiming, steve, sean, chjohnst, neelx, mproche,
nick.lange, linux-block, linux-kernel, virtualization, linux-nvme,
linux-scsi, megaraidlinux.pdl, mpi3mr-linuxdrv.pdl,
MPT-FusionLinux.pdl
In-Reply-To: <20260416192942.1243421-1-atomlin@atomlin.com>
From: Daniel Wagner <wagi@kernel.org>
Ensure that IRQ affinity setup also respects the queue-to-CPU mapping
constraints provided by the block layer. This allows the SCSI drivers
to avoid assigning interrupts to CPUs that the block layer has excluded
(e.g., isolated CPUs).
Only convert drivers which are already using the
pci_alloc_irq_vectors_affinity with the PCI_IRQ_AFFINITY flag set.
Because these drivers are enabled to let the IRQ core code to
set the affinity. Also don't update qla2xxx because the nvme-fabrics
code is not ready yet.
Signed-off-by: Daniel Wagner <wagi@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Aaron Tomlin <atomlin@atomlin.com>
---
drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 1 +
drivers/scsi/megaraid/megaraid_sas_base.c | 5 ++++-
drivers/scsi/mpi3mr/mpi3mr_fw.c | 6 +++++-
drivers/scsi/mpt3sas/mpt3sas_base.c | 5 ++++-
drivers/scsi/pm8001/pm8001_init.c | 1 +
5 files changed, 15 insertions(+), 3 deletions(-)
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index f69efc6494b8..d1f689224e7b 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -2605,6 +2605,7 @@ static int interrupt_preinit_v3_hw(struct hisi_hba *hisi_hba)
struct pci_dev *pdev = hisi_hba->pci_dev;
struct irq_affinity desc = {
.pre_vectors = BASE_VECTORS_V3_HW,
+ .mask = blk_mq_online_queue_affinity(),
};
min_msi = MIN_AFFINE_VECTORS_V3_HW;
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index ac71ea4898b2..7e2a3c187ee0 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -5925,7 +5925,10 @@ static int
__megasas_alloc_irq_vectors(struct megasas_instance *instance)
{
int i, irq_flags;
- struct irq_affinity desc = { .pre_vectors = instance->low_latency_index_start };
+ struct irq_affinity desc = {
+ .pre_vectors = instance->low_latency_index_start,
+ .mask = blk_mq_online_queue_affinity(),
+ };
struct irq_affinity *descp = &desc;
irq_flags = PCI_IRQ_MSIX;
diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c
index c744210cc901..f9b8b3639c64 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_fw.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c
@@ -830,7 +830,11 @@ static int mpi3mr_setup_isr(struct mpi3mr_ioc *mrioc, u8 setup_one)
int max_vectors, min_vec;
int retval;
int i;
- struct irq_affinity desc = { .pre_vectors = 1, .post_vectors = 1 };
+ struct irq_affinity desc = {
+ .pre_vectors = 1,
+ .post_vectors = 1,
+ .mask = blk_mq_online_queue_affinity(),
+ };
if (mrioc->is_intr_info_set)
return 0;
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 79052f2accbd..91e1622b5b77 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -3370,7 +3370,10 @@ static int
_base_alloc_irq_vectors(struct MPT3SAS_ADAPTER *ioc)
{
int i, irq_flags = PCI_IRQ_MSIX;
- struct irq_affinity desc = { .pre_vectors = ioc->high_iops_queues };
+ struct irq_affinity desc = {
+ .pre_vectors = ioc->high_iops_queues,
+ .mask = blk_mq_online_queue_affinity(),
+ };
struct irq_affinity *descp = &desc;
/*
* Don't allocate msix vectors for poll_queues.
diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c
index e93ea76b565e..6360fa95bcf4 100644
--- a/drivers/scsi/pm8001/pm8001_init.c
+++ b/drivers/scsi/pm8001/pm8001_init.c
@@ -978,6 +978,7 @@ static u32 pm8001_setup_msix(struct pm8001_hba_info *pm8001_ha)
*/
struct irq_affinity desc = {
.pre_vectors = 1,
+ .mask = blk_mq_online_queue_affinity(),
};
rc = pci_alloc_irq_vectors_affinity(
pm8001_ha->pdev, 2, PM8001_MAX_MSIX_VEC,
--
2.51.0
^ permalink raw reply related
* [PATCH v11 06/13] nvme-pci: use block layer helpers to constrain queue affinity
From: Aaron Tomlin @ 2026-04-16 19:29 UTC (permalink / raw)
To: axboe, kbusch, hch, sagi, mst
Cc: atomlin, aacraid, James.Bottomley, martin.petersen, liyihang9,
kashyap.desai, sumit.saxena, shivasharan.srikanteshwara,
chandrakanth.patil, sathya.prakash, sreekanth.reddy,
suganath-prabu.subramani, ranjan.kumar, jinpu.wang, tglx, mingo,
peterz, juri.lelli, vincent.guittot, akpm, maz, ruanjinjie,
bigeasy, yphbchou0911, wagi, frederic, longman, chenridong, hare,
kch, ming.lei, tom.leiming, steve, sean, chjohnst, neelx, mproche,
nick.lange, linux-block, linux-kernel, virtualization, linux-nvme,
linux-scsi, megaraidlinux.pdl, mpi3mr-linuxdrv.pdl,
MPT-FusionLinux.pdl
In-Reply-To: <20260416192942.1243421-1-atomlin@atomlin.com>
From: Daniel Wagner <wagi@kernel.org>
Ensure that IRQ affinity setup also respects the queue-to-CPU mapping
constraints provided by the block layer. This allows the NVMe driver
to avoid assigning interrupts to CPUs that the block layer has excluded
(e.g., isolated CPUs).
Signed-off-by: Daniel Wagner <wagi@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Aaron Tomlin <atomlin@atomlin.com>
---
drivers/nvme/host/pci.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index db5fc9bf6627..daa041d15d3c 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2862,6 +2862,7 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
.pre_vectors = 1,
.calc_sets = nvme_calc_irq_sets,
.priv = dev,
+ .mask = blk_mq_possible_queue_affinity(),
};
unsigned int irq_queues, poll_queues;
unsigned int flags = PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY;
--
2.51.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox