[PATCH v4 02/11] PCI: liveupdate: Track outgoing preserved PCI devices

[Samiullah Khawaja]

On Thu, Apr 23, 2026 at 09:23:06PM +0000, David Matlack wrote:
>Add APIs to allow drivers to notify the PCI core of which devices are
>being preserved across a Live Update for the next kernel, i.e.
>"outgoing" devices.
>
>Drivers must notify the PCI core when devices are preserved so that the
>PCI core can update its FLB data (struct pci_ser) and track the list of
>outgoing devices. pci_liveupdate_preserve() notifies the PCI core that a
>device must be preserved across Live Update. pci_liveupdate_unpreserve()
>reverses this (cancels the preservation of the device).
>
>This tracking ensures the PCI core is fully aware of which devices may
>need special handling during shutdown and kexec, and so that it can be
>handed off to the next kernel.
>
>Signed-off-by: David Matlack <dmatlack at google.com>
>---
> drivers/pci/liveupdate.c    | 101 ++++++++++++++++++++++++++++++++++++
> include/linux/kho/abi/pci.h |   7 +--
> include/linux/pci.h         |  26 ++++++++++
> 3 files changed, 131 insertions(+), 3 deletions(-)
>
>diff --git a/drivers/pci/liveupdate.c b/drivers/pci/liveupdate.c
>index d4fa61625d56..2dd8daa2f17c 100644
>--- a/drivers/pci/liveupdate.c
>+++ b/drivers/pci/liveupdate.c
>@@ -43,6 +43,26 @@
>  *
>  *  * ``pci_liveupdate_register_flb(driver_file_handler)``
>  *  * ``pci_liveupdate_unregister_flb(driver_file_handler)``
>+ *
>+ * Device Tracking
>+ * ===============
>+ *
>+ * Drivers must notify the PCI core when specific devices are preserved or
>+ * unpreserved with the following APIs:
>+ *
>+ *  * ``pci_liveupdate_preserve(pci_dev)``
>+ *  * ``pci_liveupdate_unpreserve(pci_dev)``
>+ *
>+ * This allows the PCI core to keep it's FLB data (struct pci_ser) up to date
>+ * with the list of **outgoing** preserved devices for the next kernel.
>+ *
>+ * Restrictions
>+ * ============
>+ *
>+ * The PCI core enforces the following restrictions on which devices can be
>+ * preserved. These may be relaxed in the future:
>+ *
>+ *  * The device cannot be a Virtual Function (VF).
>  */
>
> #define pr_fmt(fmt) "PCI: liveupdate: " fmt
>@@ -57,6 +77,8 @@
> #include <linux/pci.h>
> #include <linux/sort.h>
>
>+static DEFINE_MUTEX(pci_flb_outgoing_lock);
>+
> static int pci_flb_preserve(struct liveupdate_flb_op_args *args)
> {
> 	struct pci_dev *dev = NULL;
>@@ -124,6 +146,85 @@ static struct liveupdate_flb pci_liveupdate_flb = {
> 	.compatible = PCI_LUO_FLB_COMPATIBLE,
> };
>
>+int pci_liveupdate_preserve(struct pci_dev *dev)
>+{
>+	struct pci_ser *ser;
>+	int i, ret;
>+
>+	guard(mutex)(&pci_flb_outgoing_lock);
>+
>+	ret = liveupdate_flb_get_outgoing(&pci_liveupdate_flb, (void **)&ser);
>+	if (ret)
>+		return ret;
>+
>+	if (!ser)
>+		return -ENOENT;
>+
>+	if (dev->is_virtfn)
>+		return -EINVAL;
>+
>+	if (dev->liveupdate_outgoing)
>+		return -EBUSY;
>+
>+	if (ser->nr_devices == ser->max_nr_devices)
>+		return -ENOSPC;
>+
>+	for (i = 0; i < ser->max_nr_devices; i++) {
>+		/*
>+		 * Start searching at index ser->nr_devices. This should result
>+		 * in a constant time search under expected conditions (devices
>+		 * are not getting unpreserved).
>+		 */
>+		int index = (ser->nr_devices + i) % ser->max_nr_devices;
>+		struct pci_dev_ser *dev_ser = &ser->devices[index];

nit: Maybe we can move this logic in a separate function as down the road
when we expand this to add VFs and Hotpluggable devices, this might
change significantly? It's good if it is self-contained.
>+
>+		if (dev_ser->refcount)
>+			continue;
>+
>+		pci_info(dev, "Device will be preserved across next Live Update\n");
>+		ser->nr_devices++;
>+
>+		dev_ser->domain = pci_domain_nr(dev->bus);
>+		dev_ser->bdf = pci_dev_id(dev);
>+		dev_ser->refcount = 1;
>+
>+		dev->liveupdate_outgoing = dev_ser;
>+		return 0;
>+	}
>+
>+	return -ENOSPC;
>+}
>+EXPORT_SYMBOL_GPL(pci_liveupdate_preserve);
>+
>+void pci_liveupdate_unpreserve(struct pci_dev *dev)
>+{
>+	struct pci_dev_ser *dev_ser;
>+	struct pci_ser *ser = NULL;
>+	int ret;
>+
>+	guard(mutex)(&pci_flb_outgoing_lock);
>+
>+	ret = liveupdate_flb_get_outgoing(&pci_liveupdate_flb, (void **)&ser);
>+
>+	if (ret || !ser) {
>+		pci_warn(dev, "Cannot unpreserve device without outgoing Live Update state\n");
>+		return;
>+
>+	}
>+
>+	dev_ser = dev->liveupdate_outgoing;
>+	if (!dev_ser) {
>+		pci_warn(dev, "Cannot unpreserve device that is not preserved\n");
>+		return;
>+	}
>+
>+	pci_info(dev, "Device will no longer be preserved across next Live Update\n");
>+	ser->nr_devices--;
>+	memset(dev_ser, 0, sizeof(*dev_ser));
>+	dev->liveupdate_outgoing = NULL;
>+}
>+EXPORT_SYMBOL_GPL(pci_liveupdate_unpreserve);
>+
> int pci_liveupdate_register_flb(struct liveupdate_file_handler *fh)
> {
> 	pr_debug("Registering file handler \"%s\"\n", fh->compatible);
>diff --git a/include/linux/kho/abi/pci.h b/include/linux/kho/abi/pci.h
>index 5c0e92588c00..5b4c8d9e462c 100644
>--- a/include/linux/kho/abi/pci.h
>+++ b/include/linux/kho/abi/pci.h
>@@ -23,19 +23,20 @@
>  * incrementing the version number in the PCI_LUO_FLB_COMPATIBLE string.
>  */
>
>-#define PCI_LUO_FLB_COMPATIBLE "pci-v1"
>+#define PCI_LUO_FLB_COMPATIBLE "pci-v2"
>
> /**
>  * struct pci_dev_ser - Serialized state about a single PCI device.
>  *
>  * @domain: The device's PCI domain number (segment).
>  * @bdf: The device's PCI bus, device, and function number.
>- * @reserved: Reserved (to naturally align struct pci_dev_ser).
>+ * @refcount: Reference count used by the PCI core to keep track of whether it
>+ *            is done using a device's struct pci_dev_ser.
>  */
> struct pci_dev_ser {
> 	u32 domain;
> 	u16 bdf;
>-	u16 reserved;
>+	u16 refcount;
> } __packed;
>
> /**
>diff --git a/include/linux/pci.h b/include/linux/pci.h
>index d70080babd52..eb94cbd8ab9d 100644
>--- a/include/linux/pci.h
>+++ b/include/linux/pci.h
>@@ -41,6 +41,7 @@
> #include <linux/msi_api.h>
> #include <uapi/linux/pci.h>
> #include <linux/liveupdate.h>
>+#include <linux/kho/abi/pci.h>
>
> #include <linux/pci_ids.h>
>
>@@ -594,6 +595,9 @@ struct pci_dev {
> 	u8		tph_mode;	/* TPH mode */
> 	u8		tph_req_type;	/* TPH requester type */
> #endif
>+#ifdef CONFIG_PCI_LIVEUPDATE
>+	struct pci_dev_ser *liveupdate_outgoing; /* State preserved for next kernel */
>+#endif
> };
>
> static inline struct pci_dev *pci_physfn(struct pci_dev *dev)
>@@ -2880,6 +2884,14 @@ void pci_uevent_ers(struct pci_dev *pdev, enum  pci_ers_result err_type);
> #ifdef CONFIG_PCI_LIVEUPDATE
> int pci_liveupdate_register_flb(struct liveupdate_file_handler *fh);
> void pci_liveupdate_unregister_flb(struct liveupdate_file_handler *fh);
>+
>+int pci_liveupdate_preserve(struct pci_dev *dev);
>+void pci_liveupdate_unpreserve(struct pci_dev *dev);
>+
>+static inline struct pci_dev_ser *pci_liveupdate_outgoing(struct pci_dev *dev)
>+{
>+	return dev->liveupdate_outgoing;
>+}

Is this expected to be called under the outgoing lock?
> #else
> static inline int pci_liveupdate_register_flb(struct liveupdate_file_handler *fh)
> {
>@@ -2889,6 +2901,20 @@ static inline int pci_liveupdate_register_flb(struct liveupdate_file_handler *fh
> static inline void pci_liveupdate_unregister_flb(struct liveupdate_file_handler *fh)
> {
> }
>+
>+static inline int pci_liveupdate_preserve(struct pci_dev *dev)
>+{
>+	return -EOPNOTSUPP;
>+}
>+
>+static inline void pci_liveupdate_unpreserve(struct pci_dev *dev)
>+{
>+}
>+
>+static inline struct pci_dev_ser *pci_liveupdate_outgoing(struct pci_dev *dev)
>+{
>+	return NULL;
>+}
> #endif
>
> #endif /* LINUX_PCI_H */
>-- 
>2.54.0.rc2.544.gc7ae2d5bb8-goog
>