[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20250728-luo-pci-v1-21-955b078dd653@kernel.org>
Date: Mon, 28 Jul 2025 01:24:51 -0700
From: chrisl@...nel.org
To: Bjorn Helgaas <bhelgaas@...gle.com>,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
"Rafael J. Wysocki" <rafael@...nel.org>, Danilo Krummrich <dakr@...nel.org>,
Len Brown <lenb@...nel.org>
Cc: linux-kernel@...r.kernel.org, linux-pci@...r.kernel.org,
linux-acpi@...r.kernel.org, David Matlack <dmatlack@...gle.com>,
Pasha Tatashin <tatashin@...gle.com>, Jason Miu <jasonmiu@...gle.com>,
Vipin Sharma <vipinsh@...gle.com>, Saeed Mahameed <saeedm@...dia.com>,
Adithya Jayachandran <ajayachandra@...dia.com>,
Parav Pandit <parav@...dia.com>, William Tu <witu@...dia.com>,
Mike Rapoport <rppt@...nel.org>, Chris Li <chrisl@...nel.org>,
Jason Gunthorpe <jgg@...pe.ca>, Leon Romanovsky <leon@...nel.org>
Subject: [PATCH RFC 21/25] PCI/LUO: Save and restore the PCI resource
From: Jason Miu <jasonmiu@...gle.com>
Preserve the resource array in pci_dev, in pci_dev_ser with an array
of `struct pci_resource_ser`. This array save all resource regions
claimed by a PCI device in the LUO prepare phase.
When a PCI device is setting up after a liveupdate reboot, normally it
read/write the PCI BARs for probing the available resource regions,
with pci_read_bases() function. We check if liveupdate is enabled and
the preserved resource is preserved. If it does, we restore the
resource data structure instead of accessing the hardware.
Tested:
- QEMU VM boot test. Save and restore a pf-test driver.
Signed-off-by: Chris Li <chrisl@...nel.org>
---
drivers/pci/liveupdate.c | 52 +++++++++++++++++++++++++++++++++++++++++++++++-
drivers/pci/pci.h | 17 ++++++++++++++++
drivers/pci/probe.c | 18 ++++++++++++++---
3 files changed, 83 insertions(+), 4 deletions(-)
diff --git a/drivers/pci/liveupdate.c b/drivers/pci/liveupdate.c
index bc2c166ef494fd0b38cc05500bf0817c0f50fd95..7fda7e4d409adce6bf92ef7af1167f7bda302c7e 100644
--- a/drivers/pci/liveupdate.c
+++ b/drivers/pci/liveupdate.c
@@ -166,10 +166,12 @@ static int pci_save_device_state(struct device *dev, struct pci_dev_ser *s)
{
struct pci_dev *pdev = to_pci_dev(dev);
const char *name = dev->driver->name;
+ int i;
if (!name)
return -ENXIO;
- if (strlen(name) > sizeof(s->driver_name) - 1)
+ if ((strlen(name) > sizeof(s->driver_name) - 1) ||
+ (strlen(name) > sizeof(s->resource[0].name) - 1))
return -ENOSPC;
strscpy(s->driver_name, name, sizeof(s->driver_name));
s->path = pci_get_device_path(pdev);
@@ -190,6 +192,28 @@ static int pci_save_device_state(struct device *dev, struct pci_dev_ser *s)
s->pref_window = pdev->pref_window;
s->pref_64_window = pdev->pref_64_window;
+ /*
+ * Per PCIe r4.0, sec 9.3.4.1.11, the VF BARs are all RO Zero,
+ * no need to preserve the resource.
+ */
+ if (pdev->is_virtfn)
+ return 0;
+
+ for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
+ /* This resource region is not claimed by this device, skip. */
+ if ((pdev->resource[i].name == NULL) ||
+ (strlen(pdev->resource[i].name) == 0))
+ continue;
+
+ s->resource[i].start = pdev->resource[i].start;
+ s->resource[i].end = pdev->resource[i].end;
+ s->resource[i].flags = pdev->resource[i].flags;
+ s->resource[i].desc = pdev->resource[i].desc;
+
+ strscpy((char *)s->resource[i].name, pci_name(pdev),
+ sizeof(s->resource[i].name));
+ }
+
return 0;
}
@@ -502,6 +526,32 @@ void pci_liveupdate_override_driver(struct pci_dev *dev)
panic("PCI Liveupdate override driver failed: %s", s->driver_name);
}
+int pci_liveupdate_reclaim_resource(struct pci_dev *dev)
+{
+ const char *name = pci_name(dev);
+ int i;
+
+ if (!dev->dev.lu.dev_state)
+ return -EINVAL;
+
+ if (dev->is_virtfn)
+ return 0;
+
+ for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
+ /* This resource region was not claimed, skip. */
+ if (strncmp(PCI_SER_GET(dev, resource[i].name, ""), name,
+ strlen(name)) != 0)
+ continue;
+
+ dev->resource[i].start = PCI_SER_GET(dev, resource[i].start, 0);
+ dev->resource[i].end = PCI_SER_GET(dev, resource[i].end, 0);
+ dev->resource[i].name = pci_name(dev);
+ dev->resource[i].flags = PCI_SER_GET(dev, resource[i].flags, 0);
+ dev->resource[i].desc = PCI_SER_GET(dev, resource[i].desc, 0);
+ }
+
+ return 0;
+}
static int __init pci_liveupdate_init(void)
{
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index bd198227ae3cf687f4ddae76c2f53125681ca91d..7af32edb128faef9c5e2665ca5055374f7fd30ea 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -489,6 +489,19 @@ struct pci_sriov {
bool drivers_autoprobe; /* Auto probing of VFs by driver */
};
+#define PCI_RESOURCE_SER_NAME_SIZE 64
+struct pci_resource_ser {
+ u64 start;
+ u64 end;
+ const char name[PCI_RESOURCE_SER_NAME_SIZE];
+ u64 flags;
+ u64 desc;
+ /*
+ * The PCI resource is not nested. We do not need to preserve
+ * the parent, sibling, child pointers in the original struct resource.
+ */
+} __packed;
+
struct pci_dev_ser {
u32 path; /* domain + bus + slot + fn */
u8 requested;
@@ -509,6 +522,7 @@ struct pci_dev_ser {
u32 hotplug_user_indicators:1;
u32 pref_window:1;
u32 pref_64_window:1;
+ struct pci_resource_ser resource[DEVICE_COUNT_RESOURCE];
} __packed;
#ifdef CONFIG_PCI_DOE
@@ -1192,6 +1206,7 @@ static inline struct pci_dev_ser *pci_lu_adopt(struct pci_dev *dev)
{
return dev->dev.lu.requested ? dev->dev.lu.dev_state : NULL;
}
+int pci_liveupdate_reclaim_resource(struct pci_dev *dev);
#else
#define PCI_SER_GET(__dev, __var, __def) __def
@@ -1201,5 +1216,7 @@ static inline struct pci_dev_ser *pci_lu_adopt(struct pci_dev *dev)
{
return NULL;
}
+static inline int pci_liveupdate_reclaim_resource(
+ struct pci_dev *dev) { return -ENXIO; }
#endif
#endif /* DRIVERS_PCI_H */
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 5c30d1d52a96b17a92794756cab5db0972548267..a101a44956821e5e81c6b063e6aab7db49a4cf7f 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -2096,7 +2096,13 @@ int pci_setup_device(struct pci_dev *dev)
if (class == PCI_CLASS_BRIDGE_PCI)
goto bad;
pci_read_irq(dev);
- pci_read_bases(dev, PCI_STD_NUM_BARS, PCI_ROM_ADDRESS);
+
+ /*
+ * If we can reclaim the resource from liveupdate preserved data,
+ * do not access the hardware.
+ */
+ if (pci_liveupdate_reclaim_resource(dev) < 0)
+ pci_read_bases(dev, PCI_STD_NUM_BARS, PCI_ROM_ADDRESS);
pci_subsystem_ids(dev, &dev->subsystem_vendor, &dev->subsystem_device);
@@ -2152,7 +2158,10 @@ int pci_setup_device(struct pci_dev *dev)
*/
pci_read_irq(dev);
dev->transparent = ((dev->class & 0xff) == 1);
- pci_read_bases(dev, 2, PCI_ROM_ADDRESS1);
+
+ if (pci_liveupdate_reclaim_resource(dev) < 0)
+ pci_read_bases(dev, 2, PCI_ROM_ADDRESS1);
+
pci_read_bridge_windows(dev);
set_pcie_hotplug_bridge(dev);
pos = pci_find_capability(dev, PCI_CAP_ID_SSVID);
@@ -2166,7 +2175,10 @@ int pci_setup_device(struct pci_dev *dev)
if (class != PCI_CLASS_BRIDGE_CARDBUS)
goto bad;
pci_read_irq(dev);
- pci_read_bases(dev, 1, 0);
+
+ if (pci_liveupdate_reclaim_resource(dev) < 0)
+ pci_read_bases(dev, 1, 0);
+
pci_read_config_word(dev, PCI_CB_SUBSYSTEM_VENDOR_ID, &dev->subsystem_vendor);
pci_read_config_word(dev, PCI_CB_SUBSYSTEM_ID, &dev->subsystem_device);
break;
--
2.50.1.487.gc89ff58d15-goog
Powered by blists - more mailing lists