xen: do not re-use pirq number cached in pci device msi msg data
Revert the main part of commit:af42b8d12f
("xen: fix MSI setup and teardown for PV on HVM guests") That commit introduced reading the pci device's msi message data to see if a pirq was previously configured for the device's msi/msix, and re-use that pirq. At the time, that was the correct behavior. However, a later change to Qemu caused it to call into the Xen hypervisor to unmap all pirqs for a pci device, when the pci device disables its MSI/MSIX vectors; specifically the Qemu commit: c976437c7dba9c7444fb41df45468968aaa326ad ("qemu-xen: free all the pirqs for msi/msix when driver unload") Once Qemu added this pirq unmapping, it was no longer correct for the kernel to re-use the pirq number cached in the pci device msi message data. All Qemu releases since 2.1.0 contain the patch that unmaps the pirqs when the pci device disables its MSI/MSIX vectors. This bug is causing failures to initialize multiple NVMe controllers under Xen, because the NVMe driver sets up a single MSIX vector for each controller (concurrently), and then after using that to talk to the controller for some configuration data, it disables the single MSIX vector and re-configures all the MSIX vectors it needs. So the MSIX setup code tries to re-use the cached pirq from the first vector for each controller, but the hypervisor has already given away that pirq to another controller, and its initialization fails. This is discussed in more detail at: https://lists.xen.org/archives/html/xen-devel/2017-01/msg00447.html Fixes:af42b8d12f
("xen: fix MSI setup and teardown for PV on HVM guests") Signed-off-by: Dan Streetman <dan.streetman@canonical.com> Reviewed-by: Stefano Stabellini <sstabellini@kernel.org> Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
This commit is contained in:
parent
4610d240d6
commit
c74fd80f2f
|
@ -234,23 +234,14 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
|
|||
return 1;
|
||||
|
||||
for_each_pci_msi_entry(msidesc, dev) {
|
||||
__pci_read_msi_msg(msidesc, &msg);
|
||||
pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) |
|
||||
((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff);
|
||||
if (msg.data != XEN_PIRQ_MSI_DATA ||
|
||||
xen_irq_from_pirq(pirq) < 0) {
|
||||
pirq = xen_allocate_pirq_msi(dev, msidesc);
|
||||
if (pirq < 0) {
|
||||
irq = -ENODEV;
|
||||
goto error;
|
||||
}
|
||||
xen_msi_compose_msg(dev, pirq, &msg);
|
||||
__pci_write_msi_msg(msidesc, &msg);
|
||||
dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq);
|
||||
} else {
|
||||
dev_dbg(&dev->dev,
|
||||
"xen: msi already bound to pirq=%d\n", pirq);
|
||||
pirq = xen_allocate_pirq_msi(dev, msidesc);
|
||||
if (pirq < 0) {
|
||||
irq = -ENODEV;
|
||||
goto error;
|
||||
}
|
||||
xen_msi_compose_msg(dev, pirq, &msg);
|
||||
__pci_write_msi_msg(msidesc, &msg);
|
||||
dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq);
|
||||
irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq,
|
||||
(type == PCI_CAP_ID_MSI) ? nvec : 1,
|
||||
(type == PCI_CAP_ID_MSIX) ?
|
||||
|
|
Loading…
Reference in New Issue