similar to: [PATCH][VTD] pci mmcfg patch for x86-64 - version 2

Hi, First of all, thanks for your help. I have made some test with this results debian testing with xen 4.4 can run if we add mmcfg=0 as boot options to kernel boot parameters !!! Remember that with xen kernel <=4.0 works perfect without to add mmcfg=0 I have tried to install citrix xenserver 5.6 and works perfect (remember that this is xen 3 branch) Also we have tried to install xenserver

On Fri, 2014-09-05 at 13:39 +0200, trenta wrote: > Additional information: > http://lists.xen.org/archives/html/xen-devel/2013-09/msg00584.html This thread suggests that mmconfig might be the issue, in which case does adding "mmcfg=0" to your hypervisor command line help? I'd recommend continuing to pursue this upstream, there are far more experts on the low level aspect of

Forcibly enabling the MMCFG space on AMD Fam10 CPUs cannot be expected to work since with the firmware not being aware of the address range used it cannot possibly reserve the space in E820 or ACPI resources. Hence we need to manually insert the range into the E820 table, and enable the range only when the insertion actually works without conflict. Further, the actual enabling of the space is

Signed-off-by: Jan Beulich <jbeulich@suse.com> --- a/xen/arch/x86/x86_64/mmconfig_64.c +++ b/xen/arch/x86/x86_64/mmconfig_64.c @@ -23,7 +23,7 @@ struct mmcfg_virt { char __iomem *virt; }; static struct mmcfg_virt *pci_mmcfg_virt; -static int __initdata mmcfg_pci_segment_shift; +static unsigned int mmcfg_pci_segment_shift; static char __iomem *get_virt(unsigned int seg, unsigned

Hi Allen, Hi All, I''m looking into SR-IOV on Xen and in particular getting the VFs of the Intel 82756 initialised in dom0. One problem that I am coming up against is that the SRIOV extended PCIe capability does not show up for the PF (physical PCI function). Actually, the extended PCIe capability space doesn''t show up at all for any device. This seems to be related to a

Package: xen-hypervisor-4.4-amd64 Version: 4.4.0-4 Severity: normal -- System Information: Debian Release: jessie/sid APT prefers testing-updates APT policy: (500, 'testing-updates'), (500, 'testing') Architecture: amd64 (x86_64) Kernel: Linux 3.14-2-amd64 (SMP w/4 CPU cores) Locale: LANG=C, LC_CTYPE=C (charmap=ANSI_X3.4-1968) Shell: /bin/sh linked to /bin/dash

There are BIOSes that want to map the IO-APIC MMIO region from some ACPI method(s), and there is at least one BIOS flavor that wants to use this mapping to clear an RTE''s mask bit. While we can''t allow the latter, we can permit reads and simply drop write attempts, leveraging the already existing infrastructure introduced for dealing with AMD IOMMUs'' representation as

# HG changeset patch # User Ian Campbell <ian.campbell@citrix.com> # Date 1332754018 -3600 # Node ID b3fc067f938da14fd8b0dce7b00c4876bbf99e8b # Parent d8e15dc99bf307bd0ae0b042f1d50409b9f26386 docs: wrap misc/xen-command-line.markdown to 80 columns Makes it more readable as a text document. Signed-off-by: Ian Campbell <ian.campbell@citrix.com> diff -r d8e15dc99bf3 -r b3fc067f938d