From 728c2edfcf14b3b61bd0ff82894f03455ca0e7d7 Mon Sep 17 00:00:00 2001 From: Jason Andryuk Date: Mon, 29 Aug 2022 11:15:36 -0400 Subject: [PATCH] xen-pcifront: Handle missed Connected state An HVM guest with linux stubdomain and 2 PCI devices failed to start as libxl timed out waiting for the PCI devices to be added. It happens intermittently but with some regularity. libxl wrote the two xenstore entries for the devices, but then timed out waiting for backend state 4 (Connected) - the state stayed at 7 (Reconfiguring). (PCI passthrough to an HVM with stubdomain is PV passthrough to the stubdomain and then HVM passthrough with the QEMU inside the stubdomain.) The stubdomain kernel never printed "pcifront pci-0: Installing PCI frontend", so it seems to have missed state 4 which would have called pcifront_try_connect() -> pcifront_connect_and_init_dma() Have pcifront_detach_devices() special-case state Initialised and call pcifront_connect_and_init_dma(). Don't use pcifront_try_connect() because that sets the xenbus state which may throw off the backend. After connecting, skip the remainder of detach_devices since none have been initialized yet. When the backend switches to Reconfigured, pcifront_attach_devices() will pick them up again. Signed-off-by: Jason Andryuk Reviewed-by: Juergen Gross Link: https://lore.kernel.org/r/20220829151536.8578-1-jandryuk@gmail.com Signed-off-by: Juergen Gross --- drivers/pci/xen-pcifront.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c index 689271c..77e61b4 100644 --- a/drivers/pci/xen-pcifront.c +++ b/drivers/pci/xen-pcifront.c @@ -981,13 +981,26 @@ static int pcifront_detach_devices(struct pcifront_device *pdev) { int err = 0; int i, num_devs; + enum xenbus_state state; unsigned int domain, bus, slot, func; struct pci_dev *pci_dev; char str[64]; - if (xenbus_read_driver_state(pdev->xdev->nodename) != - XenbusStateConnected) + state = xenbus_read_driver_state(pdev->xdev->nodename); + if (state == XenbusStateInitialised) { + dev_dbg(&pdev->xdev->dev, "Handle skipped connect.\n"); + /* We missed Connected and need to initialize. */ + err = pcifront_connect_and_init_dma(pdev); + if (err && err != -EEXIST) { + xenbus_dev_fatal(pdev->xdev, err, + "Error setting up PCI Frontend"); + goto out; + } + + goto out_switch_state; + } else if (state != XenbusStateConnected) { goto out; + } err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, "num_devs", "%d", &num_devs); @@ -1048,6 +1061,7 @@ static int pcifront_detach_devices(struct pcifront_device *pdev) domain, bus, slot, func); } + out_switch_state: err = xenbus_switch_state(pdev->xdev, XenbusStateReconfiguring); out: -- 2.7.4