search for: intremap

So I want to turn iommu support on in a guest ( <type arch='x86_64' machine='pc-q35-4.1'>hvm</type>). Per [1] I tried to add to devices either <devices> <iommu model='intel'> <driver intremap='on'/> </iommu> </devices> or just a simpler <devices> <iommu model='intel /'> </devices> However, when I try to boot it, it crashes with the following error message (stolen from /var/log/libvirt/qemu/testkvm.log): 2020-02-11T05:13:27.278707Z...

Wei, Quick question: Am I reading the code correctly, that even with per-device interrupt remap tables, that GSIs are accounted to the intremap table of the corresponding IOAPIC, presumably because the IOMMU sees interrupts generated as GSIs as coming from the IOAPIC? In that case, then we need all devices sharing the same IOAPIC must not have any vector collisions. Is that correct? -George ____________________________________________...

...gn in most cases (as the value isn''t being used anywhere), it can be confusing (and misguiding) when printing the value read or when comparing it to the one previously passed into the inverse function. Signed-off-by: Jan Beulich <jbeulich@suse.com> --- a/xen/drivers/passthrough/vtd/intremap.c +++ b/xen/drivers/passthrough/vtd/intremap.c @@ -504,7 +504,11 @@ static int remap_entry_to_msi_msg( MSI_ADDR_REDIRECTION_CPU: MSI_ADDR_REDIRECTION_LOWPRI); if ( x2apic_enabled ) + { msg->dest32 = iremap_entry->lo.dst; + msg->address_lo |...

.../vtd/quirks.c --- a/xen/drivers/passthrough/vtd/quirks.c +++ b/xen/drivers/passthrough/vtd/quirks.c @@ -244,6 +244,29 @@ void vtd_ops_postamble_quirk(struct iomm } } +/* 5500/5520/X58 Chipset Interrupt remapping errata, for stepping B-3. + * Fixed in stepping C-2. */ +void __init tylersburg_intremap_quirk(void) +{ + uint32_t bus, device; + uint8_t rev; + + for ( bus = 0; bus < 0x100; bus++ ) + { + /* Match on System Management Registers on Device 20 Function 0 */ + device = pci_conf_read32(0, bus, 20, 0, PCI_VENDOR_ID); + rev = pci_conf_read8(0, bus, 20, 0,...

Dear mailinglist, I own a Gigabyte motherboard GA 970A UD3 with IOMMU support. Since the update XSA-36 (also part of the latest debian wheezy pkg), the IO-Virtualisation does not work any more as discussed on this mailinglist [0] and [1]. I like to ask, if there is an "official" solution in sight. I''m not sure about my alternatives. How "dangerous" is the

...is vulnerability. MITIGATION ========== This issue can be avoided by not assigning PCI devices to untrusted guests. In Xen versions 4.1.3 and above the sharing of the interrupt remapping table (and hence the more severe part of this problem) can be avoided by passing "iommu=amd-iommu-perdev-intremap" as a command line option to the hypervisor. This option is not fully functional on earlier hypervisors. RESOLUTION ========== Applying the appropriate attached patch resolves this issue. Note that on certain systems (SP5100 chipsets with erratum 28 present, or such with broken IVRS ACPI t...

...s this by keeping the iommu disabled until iommu_setup() is entered. Originally-by: Ronny Hegewald <ronny.hegewald@online.de> In order for iommu_enable to be off initially, iommu_supports_eim() must not depend on it anymore, nor must acpi_parse_dmar(). The former in turn requires that iommu_intremap gets uncoupled from iommu_enabled (in particular, failure during IOMMU setup should no longer result in iommu_intremap getting cleared by generic code; IOMMU specific code can still do so provided in can live with the consequences). This could have the nice side effect of allowing to use "iom...

...e what is happening as the machine boots. Also there is nothing on the screen when I reboot. My /etc/default/grub is GRUB_DISTRIBUTOR="$(sed 's, release .*$,,g' /etc/system-release)" GRUB_DEFAULT=saved GRUB_DISABLE_SUBMENU=true GRUB_CMDLINE_LINUX="crashkernel=auto rhgb intremap=no_x2apic_optout" GRUB_CMDLINE_XEN_DEFAULT="dom0_mem=13312M,max:14336M dom0_max_vcpus=6 dom0_vcpus_pin" GRUB_GFXMODE=1024x768 GRUB_GFXPAYLOAD_LINUX=keep GRUB_CMDLINE_LINUX_XEN_REPLACE_DEFAULT="console=hvc0 earlyprintk=xen nomodeset" I have tried setting (for a 1024x76...

...ricio Tavares wrote: > So I want to turn iommu support on in a guest ( <type arch='x86_64' > machine='pc-q35-4.1'>hvm</type>). Per [1] I tried to add to devices > either > > <devices> > <iommu model='intel'> > <driver intremap='on'/> > </iommu> > </devices> > > or just a simpler > > <devices> > <iommu model='intel /'> > </devices> > > However, when I try to boot it, it crashes with the following error > message (stolen from /var/log/...

...t;>>>This patch was tested with QEMU and a patch applied [1] to fix a >>>>simple issue: >>>>??? $ qemu -M q35,accel=kvm,kernel-irqchip=split \ >>>>?????????? -drive file=fedora.qcow2,format=qcow2,if=virtio \ >>>>?????????? -device intel-iommu,intremap=on \ >>>>?????????? -device vhost-vsock-pci,guest-cid=3,iommu_platform=on >>> >>> >>>Patch looks good, but a question: >>> >>>It looks to me you don't enable ATS which means vhost won't get >>>any invalidation request or did...

...m for generating a bootable grub2 stanza for hypervisors. As the /etc/grub.d/* files rely on defaults in /etc/default/grub, I added the following Xen specific variable: GRUB_CMDLINE_XEN_DEFAULT="console=com1 115200,8n1 dom0_mem=512M dom0_max_vcpus=1 dom0_vcpus_pin=true iommu=1,passthrough,no-intremap loglvl=all loglvl_guest=all loglevl=10 debug acpi=force apic=on apic_verbosity=verbose numa=on" The script itself is a hacked version of the10-linux that comes with grub2. This is 09-xen so it places it''s boot entries ahead of the non-xen entries. The resulting grub.cfg entry looks l...

...Also there is nothing on the > screen when I reboot. > > My /etc/default/grub is > > GRUB_DISTRIBUTOR="$(sed 's, release .*$,,g' /etc/system-release)" > GRUB_DEFAULT=saved > GRUB_DISABLE_SUBMENU=true > GRUB_CMDLINE_LINUX="crashkernel=auto rhgb intremap=no_x2apic_optout" > GRUB_CMDLINE_XEN_DEFAULT="dom0_mem=13312M,max:14336M dom0_max_vcpus=6 > dom0_vcpus_pin" > GRUB_GFXMODE=1024x768 > GRUB_GFXPAYLOAD_LINUX=keep > GRUB_CMDLINE_LINUX_XEN_REPLACE_DEFAULT="console=hvc0 earlyprintk=xen > nomodeset" >...

...boots. Also there is nothing on the screen when I reboot. > > My /etc/default/grub is > > GRUB_DISTRIBUTOR="$(sed 's, release .*$,,g' /etc/system-release)" > GRUB_DEFAULT=saved > GRUB_DISABLE_SUBMENU=true > GRUB_CMDLINE_LINUX="crashkernel=auto rhgb intremap=no_x2apic_optout" > GRUB_CMDLINE_XEN_DEFAULT="dom0_mem=13312M,max:14336M dom0_max_vcpus=6 dom0_vcpus_pin" > GRUB_GFXMODE=1024x768 > GRUB_GFXPAYLOAD_LINUX=keep > GRUB_CMDLINE_LINUX_XEN_REPLACE_DEFAULT="console=hvc0 earlyprintk=xen nomodeset" > > I hav...

...eeds allocating the memory for Address Translation Structure from NUMA node which guest domain runs. This patch is useful for a system which has many IOMMUs. Thanks, -- Yuji Shimada Signed-off-by: Yuji Shimada <shimada-yxb@necst.nec.co.jp> diff -r 5fd51e1e9c79 xen/drivers/passthrough/vtd/intremap.c --- a/xen/drivers/passthrough/vtd/intremap.c Wed Nov 05 10:57:21 2008 +0000 +++ b/xen/drivers/passthrough/vtd/intremap.c Tue Nov 18 17:37:31 2008 +0900 @@ -473,7 +473,7 @@ ir_ctrl = iommu_ir_ctrl(iommu); if ( ir_ctrl->iremap_maddr == 0 ) { - ir_ctrl->iremap_maddr = all...

...sc *desc = irq_to_desc(irq); diff -r 84e4d183fa8b -r 6671fc79717a xen/drivers/passthrough/amd/pci_amd_iommu.c --- a/xen/drivers/passthrough/amd/pci_amd_iommu.c +++ b/xen/drivers/passthrough/amd/pci_amd_iommu.c @@ -238,6 +238,21 @@ int __init amd_iov_detect(void) } if ( !amd_iommu_perdev_intremap ) printk(XENLOG_WARNING "AMD-Vi: Using global interrupt remap table is not recommended (see XSA-36)!\n"); + + /* Per-device vector map logic is broken for devices with multiple MSI-X + * interrupts (and would also be for multiple MSI, if Xen supported it). + * + *...

Hi! From other people posting to this list, I know that there has been a bug related to the issue described in Xen Security Advisory 36 that disables iommu for some AMD users like me. However, even when passing "iommu=no-amd-iommu-perdev-intremap" it still disables i/o virtualisatoin. Related Xen dmesg output: (XEN) IVHD Error: Invalid IO-APIC 0 (XEN) AMD-Vi: Error initialization (XEN) I/O virtualisation disabled Is there _any_ way I can fix this to make IOMMU work again? Updating my BIOS had no effect. I''m using Xen 4.4 un...

...s patch fixes this by keeping the iommu disabled until iommu_setup() is entered. Signed-off-by: Ronny Hegewald@online.de --- xen/drivers/passthrough/iommu.c.org 2012-10-05 03:38:33.000000000 +0000 +++ xen/drivers/passthrough/iommu.c 2012-10-17 22:58:07.000000000 +0000 @@ -38,7 +38,7 @@ * no-intremap Disable VT-d Interrupt Remapping */ custom_param("iommu", parse_iommu_param); -bool_t __read_mostly iommu_enabled = 1; +bool_t __read_mostly iommu_enabled = 0; bool_t __read_mostly force_iommu; bool_t __initdata iommu_dom0_strict; bool_t __read_mostly iommu_verbose; @...

1: IOMMU: properly check whether interrupt remapping is enabled 2: AMD IOMMU: only disable when certain IVRS consistency checks fail 3: VT-d: deal with 5500/5520/X58 errata Patch 1 and 2 are version 2 of a previously submitted, then withdrawn patch following up after XSA-36. Patch 3 is version 3 of a patch previously sent by Malcolm and Andrew. Signed-off-by: Jan Beulich

Further to my messages back in May I have at last got round to trying to get my DomU to recognise USB devices. I am using Xen 4.6 with CentOS kernel 3.18.34-20.el7.x86_64. I have to manually make the port available before creating the DomU by issuing the command: xl pci-assignable-add 00:1a.0 otherwise nothing shows in: xl pci-assignable-list I have added this to my .cfg file as per the

The patch moves the struct IO_APIC_route_entry to a common place. This allows us to share the struct with iosapic. Thanks, -- Dexuan _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel