[PATCH 2/5] PCI: Support two-pass shutdown

[Jeremy Allison]

From: Tanjore Suresh <tansuresh at google.com>

Enhance the base PCI driver to add support for two-pass shutdown. Add
shutdown_wait() method.

Assume a device takes n secs to shutdown. If a machine has been populated
with M such devices, the total time spent in shutting down all the devices
will be M * n secs if the shutdown is done synchronously. For example, if
NVMe PCI Controllers take 5 secs to shutdown and if there are 16 such NVMe
controllers in a system, system will spend a total of 80 secs to shutdown
all NVMe devices in that system.

In order to speed up the shutdown time, a two-pass interface to shutdown
has been implemented. The caller calls the shutdown method for each device
in turn to allow a shutdown request to be sent, then the caller walks the
list of devices and calls shutdown_wait() to synchronously wait for the
shutdown to complete.

In the NVMe case above, all 16 devices will process the shutdown in
parallel taking the total time to shutdown down to the time for one NVMe
PCI Controller to shut down.

This will significantly reduce the machine reboot time.

Signed-off-by: Tanjore Suresh <tansuresh at google.com>
Signed-off-by: Jeremy Allison <jallison at ciq.com>
---
 drivers/pci/pci-driver.c | 9 +++++++++
 include/linux/pci.h      | 2 ++
 2 files changed, 11 insertions(+)

diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 51ec9e7e784f..257bbb04c806 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -547,6 +547,14 @@ static int pci_restore_standard_config(struct pci_dev *pci_dev)
 }
 #endif /* CONFIG_PM_SLEEP */
 
+static void pci_device_shutdown_wait(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct pci_driver *drv = pci_dev->driver;
+
+	if (drv && drv->shutdown_wait)
+		drv->shutdown_wait(pci_dev);
+}
 #ifdef CONFIG_PM
 
 /* Auxiliary functions used for system resume and run-time resume */
@@ -1682,6 +1690,7 @@ struct bus_type pci_bus_type = {
 	.probe		= pci_device_probe,
 	.remove		= pci_device_remove,
 	.shutdown	= pci_device_shutdown,
+	.shutdown_wait	= pci_device_shutdown_wait,
 	.dev_groups	= pci_dev_groups,
 	.bus_groups	= pci_bus_groups,
 	.drv_groups	= pci_drv_groups,
diff --git a/include/linux/pci.h b/include/linux/pci.h
index add9368e6314..5ef014ac84f2 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -917,6 +917,7 @@ struct module;
  *		Useful for enabling wake-on-lan (NIC) or changing
  *		the power state of a device before reboot.
  *		e.g. drivers/net/e100.c.
+ * @shutdown_wait: Optional driver callback to allow two-pass shutdown.
  * @sriov_configure: Optional driver callback to allow configuration of
  *		number of VFs to enable via sysfs "sriov_numvfs" file.
  * @sriov_set_msix_vec_count: PF Driver callback to change number of MSI-X
@@ -947,6 +948,7 @@ struct pci_driver {
 	int  (*suspend)(struct pci_dev *dev, pm_message_t state);	/* Device suspended */
 	int  (*resume)(struct pci_dev *dev);	/* Device woken up */
 	void (*shutdown)(struct pci_dev *dev);
+	void (*shutdown_wait)(struct pci_dev *dev);
 	int  (*sriov_configure)(struct pci_dev *dev, int num_vfs); /* On PF */
 	int  (*sriov_set_msix_vec_count)(struct pci_dev *vf, int msix_vec_count); /* On PF */
 	u32  (*sriov_get_vf_total_msix)(struct pci_dev *pf);
-- 
2.39.3