Re: [Xen-devel] [PATCH for-4.5] xen: vnuma: expose vnode_to_pnode to guest

2014-11-10 Thread Jan Beulich
On 10.11.14 at 11:51, dario.faggi...@citrix.com wrote: I'm 100% ok to re-start that discussion here and now... however, how stable should this interface be? Can't we deal with this when actually implementing NUMA aware ballooning and add stuff at than point, if necessary? Wei's desire to

Re: [Xen-devel] [v7][RFC][PATCH 06/13] hvmloader/ram: check if guest memory is out of reserved device memory maps

2014-11-12 Thread Jan Beulich
On 12.11.14 at 04:05, tiejun.c...@intel.com wrote: I don't see any feedback to this point, so I think you still prefer we should do all check in the callback function. As a draft this looks reasonable, but there are various bugs to be dealt with along with cosmetic issues (I'll point out the

Re: [Xen-devel] RFC: vNUMA project

2014-11-12 Thread Jan Beulich
On 11.11.14 at 19:03, david.vra...@citrix.com wrote: On 11/11/14 17:36, Wei Liu wrote: Option #1 requires less modification to guest, because guest won't need to switch to new hypercall. It's unclear at this point if a guest asks to populate a gpfn that doesn't belong to any vnode, what Xen

Re: [Xen-devel] [TestDay] VMX test report for Xen 4.5.0-rc1

2014-11-12 Thread Jan Beulich
On 12.11.14 at 07:58, robert...@intel.com wrote: 2. Failed to hotplug a VT-d device with XEN4.5-RC1 http://bugzilla-archived.xenproject.org/bugzilla/show_bug.cgi?id=1894 First of all I'm not sure it is really useful to use the old, discontinued bugzilla to report bugs. I think it would be

Re: [Xen-devel] [v7][RFC][PATCH 06/13] hvmloader/ram: check if guest memory is out of reserved device memory maps

2014-11-12 Thread Jan Beulich
On 12.11.14 at 10:13, tiejun.c...@intel.com wrote: On 2014/11/12 17:02, Jan Beulich wrote: On 12.11.14 at 09:45, tiejun.c...@intel.com wrote: #2 flags field in each specific device of new domctl would control whether this device need to check/reserve its own RMRR range. But its not dependent

Re: [Xen-devel] PCI passthrough (pci-attach) to HVM guests bug (BAR64 addresses are bogus)

2014-11-12 Thread Jan Beulich
On 12.11.14 at 11:01, malcolm.cross...@citrix.com wrote: As for the CRS regions: These typically describe the BIOS set limits in hardware configuration for the MMIO hole itself. On single socket systems anything which isn't RAM or another predefined region decodes to MMIO. This is probably

Re: [Xen-devel] [PATCH] Adjust number of domains in cpupools when destroying domain

2014-11-12 Thread Jan Beulich
On 12.11.14 at 11:46, andrew.coop...@citrix.com wrote: On 12/11/14 10:40, Juergen Gross wrote: --- a/xen/common/cpupool.c +++ b/xen/common/cpupool.c @@ -225,6 +225,35 @@ static int cpupool_destroy(struct cpupool *c) } /* + * Move domain to another cpupool + */ +static int

Re: [Xen-devel] [TestDay] VMX test report for Xen 4.5.0-rc1

2014-11-12 Thread Jan Beulich
On 12.11.14 at 11:53, robert...@intel.com wrote: From: Jan Beulich [mailto:jbeul...@suse.com] On 12.11.14 at 07:58, robert...@intel.com wrote: 4. Not all PFs are available if assign multi VT-d devices to Wndows guest VM http://bugzilla-archived.xenproject.org/bugzilla/show_bug.cgi?id

Re: [Xen-devel] RFC: vNUMA project

2014-11-12 Thread Jan Beulich
On 12.11.14 at 14:45, wei.l...@citrix.com wrote: On Wed, Nov 12, 2014 at 09:35:01AM +, Jan Beulich wrote: On 11.11.14 at 19:03, david.vra...@citrix.com wrote: On 11/11/14 17:36, Wei Liu wrote: Option #1 requires less modification to guest, because guest won't need to switch to new

Re: [Xen-devel] RFC: vNUMA project

2014-11-12 Thread Jan Beulich
On 12.11.14 at 15:40, wei.l...@citrix.com wrote: So what's the usual technique in Linux to make sure if a specific Xen feature is present? Jan, is it suitable to use a XENFEAT_* bit for this? Yes, that would be the canonical way. Jan ___

Re: [Xen-devel] [PATCH 3/3] x86/xen: use the maximum MFN to calculate the required DMA mask

2014-11-12 Thread Jan Beulich
On 12.11.14 at 16:25, david.vra...@citrix.com wrote: +u64 +xen_swiotlb_get_required_mask(struct device *dev) +{ + u64 max_mfn; + + max_mfn = HYPERVISOR_memory_op(XENMEM_maximum_ram_page, NULL); + + return DMA_BIT_MASK(fls64(max_mfn PAGE_SHIFT) + 1); +} The value the

Re: [Xen-devel] [PATCH 3/3] x86/xen: use the maximum MFN to calculate the required DMA mask

2014-11-12 Thread Jan Beulich
On 12.11.14 at 17:59, david.vra...@citrix.com wrote: On 12/11/14 15:55, Jan Beulich wrote: On 12.11.14 at 16:25, david.vra...@citrix.com wrote: +u64 +xen_swiotlb_get_required_mask(struct device *dev) +{ + u64 max_mfn; + + max_mfn = HYPERVISOR_memory_op(XENMEM_maximum_ram_page, NULL

Re: [Xen-devel] PCI passthrough (pci-attach) to HVM guests bug (BAR64 addresses are bogus)

2014-11-12 Thread Jan Beulich
On 12.11.14 at 16:14, konrad.w...@oracle.com wrote: On Wed, Nov 12, 2014 at 10:01:28AM +, Malcolm Crossley wrote: I agree with Jan. By using xl pci-attach you are effectively hotplugging a PCI device (in the bare metal case). The only way this will work reliably is if you reserve some

Re: [Xen-devel] [PATCH] libxc: Turn on the pdpe1gb cpuid flag by default

2014-11-13 Thread Jan Beulich
On 13.11.14 at 06:31, liang.z...@intel.com wrote: Apart from the subject being kind of wrong (you're not turning it on by default, but only expose it if the hardware supports it), ... --- a/tools/libxc/xc_cpuid_x86.c +++ b/tools/libxc/xc_cpuid_x86.c @@ -192,6 +192,7 @@ static void

Re: [Xen-devel] [TestDay]Xen-4.5-RC1: Dom0 failed to resume from S3 power state with operations on '/sys/power/state'

2014-11-13 Thread Jan Beulich
On 13.11.14 at 03:32, robert...@intel.com wrote: Hi, This is a separated report for bug http://bugzilla-archived.xenproject.org/bugzilla/show_bug.cgi?id=1897 Environment: Service Arch (ia32/ia32e/IA64): ia32e Guest Arch (ia32/ia32e/IA64): Guest OS Type (Linux/Windows):

Re: [Xen-devel] About sharing pages between Xen and guest kernel

2014-11-13 Thread Jan Beulich
On 13.11.14 at 00:52, am...@gatech.edu wrote: Hello, I am trying to set up a shared page between the hypervisor and a Linux guest kernel. In Xen I am doing: void *ptr = alloc_xenheap_page(); share_xen_page_with_guest(virt_to_page(ptr), current-domain, XENSHARE_writable); unsigned int

[Xen-devel] delaying 4.4.2 and 4.3.4

2014-11-13 Thread Jan Beulich
All, while the 3 month period since the previous stable releases would expire at the beginning of December, looking at the number of changes in the stable trees I don't think starting preparations right now would make much sense. Unless I hear severe objections to this plan, and unless 4.5 gets

Re: [Xen-devel] [PATCH 2/3] x86: allow dma_get_required_mask() to be overridden

2014-11-13 Thread Jan Beulich
On 13.11.14 at 11:25, jbeul...@suse.com wrote: On 12.11.14 at 16:25, david.vra...@citrix.com wrote: --- a/arch/x86/include/asm/device.h +++ b/arch/x86/include/asm/device.h @@ -13,4 +13,6 @@ struct dev_archdata { struct pdev_archdata { }; +#define ARCH_HAS_DMA_GET_REQUIRED_MASK Is

Re: [Xen-devel] Problems accessing passthrough PCI device

2014-11-13 Thread Jan Beulich
On 13.11.14 at 16:07, furryfutt...@gmail.com wrote: Thanks Jan, Thursday, November 13, 2014, 11:08:33 AM, you wrote: On 13.11.14 at 14:29, furryfutt...@gmail.com wrote: I am having 2 major problems at the moment. 1.- Access to the PCI device from the PV will fail the second time I

Re: [Xen-devel] [PATCH RFC 1/2] xen/pvh: take the p2m lock when doing logdirty ops from HVM domains

2014-11-13 Thread Jan Beulich
On 13.11.14 at 16:46, t...@xen.org wrote: That leaves paging_log_dirty_op(). The inner loops of that function are already set up to be preempted for softirqs, c. I wonder could we arrange for it to map the first N pages of bitmap before taking any locks, and then drop the locks after that

Re: [Xen-devel] [PATCH v2] xen: remove Xencomm

2014-11-13 Thread Jan Beulich
-by: Jan Beulich jbeul...@suse.com ___ Xen-devel mailing list Xen-devel@lists.xen.org http://lists.xen.org/xen-devel

[Xen-devel] [PATCH RFC] EFI: allow retry of ExitBootServices() call

2014-11-14 Thread Jan Beulich
as the 1st one deleted them all, - a chosen node should be found as it got added in the 1st pass, - the various linux,uefi-* nodes all got added during the 1st pass and hence only their contents may get updated. Signed-off-by: Jan Beulich jbeul...@suse.com --- a/xen/arch/x86/efi/efi-boot.h +++ b

Re: [Xen-devel] Xen-unstable: xen panic RIP: dpci_softirq

2014-11-14 Thread Jan Beulich
On 14.11.14 at 14:11, li...@eikelenboom.it wrote: (XEN) [2014-11-14 13:00:06.810] [ Xen-4.5.0-rc x86_64 debug=y Not tainted ] (XEN) [2014-11-14 13:00:06.810] CPU:3 (XEN) [2014-11-14 13:00:06.810] RIP:e008:[82d080148f14] dpci_softirq+0x9c/0x231 (XEN) [2014-11-14

[Xen-devel] [PATCH] x86: (allow to) override LIST_POISON*

2014-11-14 Thread Jan Beulich
...@citrix.com Signed-off-by: Jan Beulich jbeul...@suse.com --- The security aspect of this makes Andrew and me think this should be considered for 4.5 despite it not fixing an actual bug. --- a/xen/include/asm-x86/config.h +++ b/xen/include/asm-x86/config.h @@ -106,6 +106,10 @@ /* Return value

Re: [Xen-devel] Xen-unstable: xen panic RIP: dpci_softirq

2014-11-14 Thread Jan Beulich
On 14.11.14 at 15:34, li...@eikelenboom.it wrote: # addr2line -e ./xen-syms 82d080148f14 /usr/src/new/xen-unstable/xen/include/xen/list.h:175 Which turns out to be this assert: /** * list_del - deletes entry from list. * @entry: the element to delete from the list. * Note:

Re: [Xen-devel] [PATCH v10 for-xen-4.5 2/2] dpci: Replace tasklet with an softirq

2014-11-14 Thread Jan Beulich
On 12.11.14 at 03:23, konrad.w...@oracle.com wrote: +static void pt_pirq_softirq_reset(struct hvm_pirq_dpci *pirq_dpci) +{ +struct domain *d = pirq_dpci-dom; + +ASSERT(spin_is_locked(d-event_lock)); + +switch ( cmpxchg(pirq_dpci-state, 1 STATE_SCHED, 0) ) +{ +case (1

Re: [Xen-devel] Xen-unstable: xen panic RIP: dpci_softirq

2014-11-14 Thread Jan Beulich
On 14.11.14 at 16:20, li...@eikelenboom.it wrote: If it still helps i could try Andrews suggestion and try out with only commit aeeea485 .. Yes, even if it's pretty certain it's the second of the commits, verifying this would be helpful (or if the assumption is wrong, the pattern it's dying

Re: [Xen-devel] [PATCH RFC] EFI: allow retry of ExitBootServices() call

2014-11-14 Thread Jan Beulich
On 14.11.14 at 16:32, konrad.w...@oracle.com wrote: On Fri, Nov 14, 2014 at 12:37:30PM +, Jan Beulich wrote: @@ -1051,17 +1051,23 @@ efi_start(EFI_HANDLE ImageHandle, EFI_SY if ( !efi_memmap ) blexit(LUnable to allocate memory for EFI memory map); -status = efi_bs

Re: [Xen-devel] [PATCH v10 for-xen-4.5 2/2] dpci: Replace tasklet with an softirq

2014-11-14 Thread Jan Beulich
On 14.11.14 at 17:11, konrad.w...@oracle.com wrote: On Fri, Nov 14, 2014 at 03:13:42PM +, Jan Beulich wrote: On 12.11.14 at 03:23, konrad.w...@oracle.com wrote: +static void pt_pirq_softirq_reset(struct hvm_pirq_dpci *pirq_dpci) +{ +struct domain *d = pirq_dpci-dom

Re: [Xen-devel] [v7][RFC][PATCH 06/13] hvmloader/ram: check if guest memory is out of reserved device memory maps

2014-11-17 Thread Jan Beulich
On 17.11.14 at 08:57, tiejun.c...@intel.com wrote: --- a/xen/common/memory.c +++ b/xen/common/memory.c @@ -698,10 +698,13 @@ struct get_reserved_device_memory { unsigned int used_entries; }; -static int get_reserved_device_memory(xen_pfn_t start, -

Re: [Xen-devel] [v7][RFC][PATCH 06/13] hvmloader/ram: check if guest memory is out of reserved device memory maps

2014-11-17 Thread Jan Beulich
On 17.11.14 at 12:08, tiejun.c...@intel.com wrote: On 2014/11/17 18:05, Jan Beulich wrote: On 17.11.14 at 08:57, tiejun.c...@intel.com wrote: --- a/xen/common/memory.c +++ b/xen/common/memory.c @@ -698,10 +698,13 @@ struct get_reserved_device_memory { unsigned int used_entries

Re: [Xen-devel] [PATCH RFC] EFI: allow retry of ExitBootServices() call

2014-11-17 Thread Jan Beulich
On 14.11.14 at 16:32, konrad.w...@oracle.com wrote: On Fri, Nov 14, 2014 at 12:37:30PM +, Jan Beulich wrote: The specification is kind of vague under what conditions ExitBootServices() may legitimately fail, requiring the OS loader to retry: If MapKey value is incorrect

Re: [Xen-devel] [PATCH V2] Decouple SnadyBridge quirk form VTd timeout

2014-11-17 Thread Jan Beulich
On 17.11.14 at 14:32, donald.d.dug...@intel.com wrote: Hmm, good ideas. How about I change the `snb_igd_quirk' parameter to be: snb_igd_quirk = current behavior, enable quirk with 1 sec timeout snb_igd_quirk=default = enable quirk with

Re: [Xen-devel] [PATCH V2] Decouple SnadyBridge quirk form VTd timeout

2014-11-17 Thread Jan Beulich
On 17.11.14 at 15:27, donald.d.dug...@intel.com wrote: I'm a big believer in backward compatibility, especially in not doing things that change current defined behavior. The current `snb_igd_quirk' flag enables the quirk code with a 1sec timeout. Even though that value is excessive

Re: [Xen-devel] [PATCH V2] Decouple SnadyBridge quirk form VTd timeout

2014-11-17 Thread Jan Beulich
On 17.11.14 at 15:51, donald.d.dug...@intel.com wrote: My primary goal is to decouple the IGD quirk code from the VTd timeout value, the two are unrelated and shouldn't be using the same define. In the process we can clean up the IGD code so that, if a user wants, the user can specify a

Re: [Xen-devel] [PATCH] libxc: Expose the pdpe1gb cpuid flag to guest

2014-11-17 Thread Jan Beulich
On 17.11.14 at 16:39, ian.jack...@eu.citrix.com wrote: Liang Li writes ([PATCH] libxc: Expose the pdpe1gb cpuid flag to guest): If hardware support the pdpe1gb flag, expose it to guest by default. Users don't have to use a 'cpuid= ' option in config file to turn it on. I don't understand

Re: [Xen-devel] [PATCH RFC 0/7] xen: Clean-up of mem_event subsystem

2014-11-17 Thread Jan Beulich
On 17.11.14 at 17:43, rcojoc...@bitdefender.com wrote: On 11/17/2014 06:37 PM, Jan Beulich wrote: On 12.11.14 at 16:48, andrew.coop...@citrix.com wrote: On 12/11/14 15:31, Tamas K Lengyel wrote: xen/include/public/domctl.h | 44 +-- xen/include/public/hvm/params.h | 2

Re: [Xen-devel] [PATCH RFC 0/7] xen: Clean-up of mem_event subsystem

2014-11-17 Thread Jan Beulich
On 17.11.14 at 18:06, tamas.leng...@zentific.com wrote: On Mon, Nov 17, 2014 at 5:37 PM, Jan Beulich jbeul...@suse.com wrote: On 12.11.14 at 16:48, andrew.coop...@citrix.com wrote: On 12/11/14 15:31, Tamas K Lengyel wrote: xen/include/public/domctl.h | 44 +-- xen/include

Re: [Xen-devel] Xen-unstable: xen panic RIP: dpci_softirq

2014-11-18 Thread Jan Beulich
On 17.11.14 at 23:40, li...@eikelenboom.it wrote: OK, i still don't get why the output of debug-key 'i' reports +47 as pirq here instead of the guest value (g_gsi of for this legacy interrupt which is 40 ?), like it does when it's a MSI with the PIRQ ? No - as you said yourself, it's a

Re: [Xen-devel] Xen-unstable: xen panic RIP: dpci_softirq

2014-11-18 Thread Jan Beulich
On 17.11.14 at 19:01, li...@eikelenboom.it wrote: (XEN) [2014-11-17 17:54:18.695] CPU00: (XEN) [2014-11-17 17:54:18.705] CPU01: (XEN) [2014-11-17 17:54:18.716] d16 OK-softirq 62msec ago, state:1, 2628 count, [prev:83054ef57e70, next:83054ef57e70] 83051b904428NULL MAPPED_SHIFT

Re: [Xen-devel] [v7][RFC][PATCH 06/13] hvmloader/ram: check if guest memory is out of reserved device memory maps

2014-11-18 Thread Jan Beulich
On 18.11.14 at 09:16, tiejun.c...@intel.com wrote: On 2014/11/18 16:01, Jan Beulich wrote: On 18.11.14 at 04:08, tiejun.c...@intel.com wrote: Here I tried to implement what you want. Note just pick two key fragments since others have no big deal. #1: @@ -898,14 +898,25 @@ int

Re: [Xen-devel] [PATCH for Xen 4.5] xen/arm: Add support for GICv3 for domU

2014-11-18 Thread Jan Beulich
On 18.11.14 at 16:00, julien.gr...@linaro.org wrote: On 10/31/2014 09:02 AM, Jan Beulich wrote: On 30.10.14 at 19:51, julien.gr...@linaro.org wrote: The naming suggests that the #if really should be around just the gic_version field (with a dummy field in the #else case to be C89 compatible

Re: [Xen-devel] [PATCH] Ignore non-zero data in unused xsave area.

2014-11-18 Thread Jan Beulich
On 18.11.14 at 16:26, dk...@verizon.com wrote: If we restore an xsave area from an older xen that has a larger size than the xcr0 bit call for, it is possible to have non-zero data in the unused area if an xsave has ever been done that used that area (e.g. during a context switch). Since the

Re: [Xen-devel] Problems accessing passthrough PCI device

2014-11-18 Thread Jan Beulich
On 18.11.14 at 17:24, furryfutt...@gmail.com wrote: Hello Jan, Friday, November 14, 2014, 5:27:36 AM, you wrote: I implied your earlier statement to mean that. But - did you also verify that the three flags actually end up set (ideally from both DomU and Dom0 perspective)? The PCI

Re: [Xen-devel] Xen-unstable: xen panic RIP: dpci_softirq

2014-11-18 Thread Jan Beulich
On 18.11.14 at 18:03, li...@eikelenboom.it wrote: Tuesday, November 18, 2014, 5:16:50 PM, you wrote: 1) test_and_[set|clear]_bit sometimes return unexpected values. [But this might be invalid as the addition of the 8303faaf25a8 might be correct - as the second dpci the softirq

Re: [Xen-devel] [v7][RFC][PATCH 06/13] hvmloader/ram: check if guest memory is out of reserved device memory maps

2014-11-19 Thread Jan Beulich
On 19.11.14 at 02:26, tiejun.c...@intel.com wrote: So without lookuping devices[i], how can we call func() for each sbdf as you mentioned? You've got both rmrr and bdf in the body of for_each_rmrr_device(). After all - as I said - you just open-coded it. Yeah, so change this again,

Re: [Xen-devel] Regression, host crash with 4.5rc1

2014-11-20 Thread Jan Beulich
On 20.11.14 at 02:23, sfl...@ihonk.com wrote: On 11/17/2014 23:54, Jan Beulich wrote: Another thing - now that serial logging appears to be working for you, did you try whether the host, once hung, still reacts to serial input (perhaps force input to go to Xen right at boot via the conswitch

Re: [Xen-devel] [PATCH v10 for-xen-4.5 2/2] dpci: Replace tasklet with an softirq

2014-11-20 Thread Jan Beulich
On 19.11.14 at 17:44, konrad.w...@oracle.com wrote: On Fri, Nov 14, 2014 at 11:11:46AM -0500, Konrad Rzeszutek Wilk wrote: On Fri, Nov 14, 2014 at 03:13:42PM +, Jan Beulich wrote: On 12.11.14 at 03:23, konrad.w...@oracle.com wrote: +static void pt_pirq_softirq_reset(struct

Re: [Xen-devel] Problems accessing passthrough PCI device

2014-11-20 Thread Jan Beulich
On 19.11.14 at 16:12, furryfutt...@gmail.com wrote: This is getting more interesting. It seems that something is overwriting the pci-back configuration data. Starting from a fresh reboot I checked the Dom0 pci configuration and got this: root@smartin-xen:~# lspci -s 00:19.0 -x

Re: [Xen-devel] [v7][RFC][PATCH 06/13] hvmloader/ram: check if guest memory is out of reserved device memory maps

2014-11-20 Thread Jan Beulich
On 20.11.14 at 09:12, tiejun.c...@intel.com wrote: On 2014/11/20 15:31, Jan Beulich wrote: On 19.11.14 at 02:26, tiejun.c...@intel.com wrote: int intel_iommu_get_reserved_device_memory(iommu_grdm_t *func, void *ctxt) { struct acpi_rmrr_unit *rmrr; int rc = 0; unsigned int

[Xen-devel] [PATCH 0/3] x86: XSA-109/110 follow-up (to be considered for 4.5)

2014-11-20 Thread Jan Beulich
the chances of them getting abused. Not unduly crashing the guest (as done in the third one) may avoid future security issues of guest user mode affecting the guest kernel. Signed-off-by: Jan Beulich jbeul...@suse.com ___ Xen-devel mailing list Xen-devel

[Xen-devel] [PATCH 1/3] x86: tighten page table owner checking in do_mmu_update()

2014-11-20 Thread Jan Beulich
MMU_MACHPHYS_UPDATE, not manipulating page tables, shouldn't ignore a bad page table domain being specified. Also pt_owner can't be NULL when reaching the out label, so the respective check can be dropped. Signed-off-by: Jan Beulich jbeul...@suse.com Acked-by: Tim Deegan t...@xen.org --- a/xen

[Xen-devel] [PATCH 2/3] x86: don't ignore foreigndom input on various MMUEXT ops

2014-11-20 Thread Jan Beulich
the respective logic is being adjusted at once, together with a little other related cleanup. Signed-off-by: Jan Beulich jbeul...@suse.com --- a/xen/arch/x86/mm.c +++ b/xen/arch/x86/mm.c @@ -3062,23 +3062,23 @@ long do_mmuext_op( } case MMUEXT_NEW_BASEPTR

[Xen-devel] [PATCH 3/3] x86/HVM: don't crash guest upon problems occurring in user mode

2014-11-20 Thread Jan Beulich
This extends commit 5283b310 (x86/HVM: only kill guest when unknown VM exit occurred in guest kernel mode) to further cases, including the failed VM entry one that XSA-110 was needed to be issued for. Signed-off-by: Jan Beulich jbeul...@suse.com --- a/xen/arch/x86/hvm/svm/svm.c +++ b/xen/arch

Re: [Xen-devel] [for-xen-4.5 PATCH v2 1/2] dpci: Fix list corruption if INTx device is used and an IRQ timeout is invoked.

2014-11-20 Thread Jan Beulich
On 19.11.14 at 23:21, konrad.w...@oracle.com wrote: @@ -97,13 +97,15 @@ bool_t pt_pirq_softirq_active(struct hvm_pirq_dpci *pirq_dpci) } /* - * Reset the pirq_dpci-dom parameter to NULL. + * Cancels an outstanding pirq_dpci (if scheduled). Also if clear is set, + * reset

Re: [Xen-devel] [for-xen-4.5 PATCH v2 2/2] dpci: Add ZOMBIE state to allow the softirq to finish with the dpci_pirq.

2014-11-20 Thread Jan Beulich
On 19.11.14 at 23:21, konrad.w...@oracle.com wrote: Leaving aside the question of whether this is the right approach, in case it is a couple of comments: @@ -85,7 +91,7 @@ static void raise_softirq_for(struct hvm_pirq_dpci *pirq_dpci) */ bool_t pt_pirq_softirq_active(struct

Re: [Xen-devel] [PATCH 3/3] x86/HVM: don't crash guest upon problems occurring in user mode

2014-11-20 Thread Jan Beulich
On 20.11.14 at 12:06, andrew.coop...@citrix.com wrote: On 20/11/14 10:13, Jan Beulich wrote: --- a/xen/arch/x86/hvm/svm/svm.c +++ b/xen/arch/x86/hvm/svm/svm.c @@ -90,6 +90,15 @@ static bool_t amd_erratum383_found __rea static uint64_t osvw_length, osvw_status; static DEFINE_SPINLOCK

Re: [Xen-devel] [PATCH] xen: use more fixed strings to build the hypervisor

2014-11-20 Thread Jan Beulich
On 19.11.14 at 08:35, o...@aepfle.de wrote: On Tue, Nov 18, Ian Jackson wrote: How about It should be possible to repeatedly build identical sources and get identical binaries, even on different hosts at different build times. This fails [etc. etc. ...] Provide variables

Re: [Xen-devel] [PATCH 4/4] x86/xen: use the maximum MFN to calculate the required DMA mask

2014-11-20 Thread Jan Beulich
that uses the maximum MFN to calculate the DMA mask. Signed-off-by: David Vrabel david.vra...@citrix.com Reviewed-by: Jan Beulich jbeul...@suse.com ___ Xen-devel mailing list Xen-devel@lists.xen.org http://lists.xen.org/xen-devel

Re: [Xen-devel] [PATCH V3] Decouple SnadyBridge quirk form VTd timeout

2014-11-20 Thread Jan Beulich
On 19.11.14 at 20:46, donald.d.dug...@intel.com wrote: @@ -237,6 +248,42 @@ } } +static void __init parse_snb_timeout(const char *s) +{ + int not; + + switch (*s) { + + case '\0': + snb_igd_timeout = SNB_IGD_TIMEOUT_LEGACY; + break; + +

Re: [Xen-devel] [PATCH 3/3] x86/HVM: don't crash guest upon problems occurring in user mode

2014-11-20 Thread Jan Beulich
On 20.11.14 at 12:34, t...@xen.org wrote: At 11:13 +0100 on 20 Nov (1416478386), Jan Beulich wrote: This extends commit 5283b310 (x86/HVM: only kill guest when unknown VM exit occurred in guest kernel mode) to further cases, including the failed VM entry one that XSA-110 was needed

[Xen-devel] DRAFT: XSA-113: Guest effectable page reference leak in MMU_MACHPHYS_UPDATE handling

2014-11-20 Thread Jan Beulich
-pointless MEM_LOG(). This brings the check in line with similar checks in the vicinity. Discovered while reviewing the XSA-109/110 followup series. This is XSA-113. Signed-off-by: Andrew Cooper andrew.coop...@citrix.com Reviewed-by: Jan Beulich jbeul...@suse.com Reviewed-by: Tim Deegan t

Re: [Xen-devel] [RFC for 4.6] xen: Extend DOMCTL createdomain to support arch configuration

2014-11-20 Thread Jan Beulich
On 18.11.14 at 20:20, julien.gr...@linaro.org wrote: --- a/xen/arch/x86/setup.c +++ b/xen/arch/x86/setup.c @@ -540,6 +540,7 @@ void __init noreturn __start_xen(unsigned long mbi_p) int i, j, e820_warn = 0, bytes = 0; bool_t acpi_boot_table_init_done = 0; struct domain *dom0;

Re: [Xen-devel] [v7][RFC][PATCH 06/13] hvmloader/ram: check if guest memory is out of reserved device memory maps

2014-11-20 Thread Jan Beulich
On 20.11.14 at 15:40, kevin.t...@intel.com wrote: From: Tian, Kevin Sent: Thursday, November 20, 2014 4:51 PM From: Jan Beulich [mailto:jbeul...@suse.com] Sent: Thursday, November 20, 2014 4:04 PM On 20.11.14 at 08:45, kevin.t...@intel.com wrote: Current option sounds a reasonable

Re: [Xen-devel] [for-xen-4.5 PATCH v2 2/2] dpci: Add ZOMBIE state to allow the softirq to finish with the dpci_pirq.

2014-11-20 Thread Jan Beulich
On 20.11.14 at 20:51, konrad.w...@oracle.com wrote: @@ -669,7 +670,7 @@ static void hvm_dirq_assist(struct domain *d, struct hvm_pirq_dpci *pirq_dpci) ASSERT(d-arch.hvm_domain.irq.dpci); spin_lock(d-event_lock); -if ( pirq_dpci-state ) +if (

Re: [Xen-devel] [v7][RFC][PATCH 04/13] hvmloader/util: get reserved device memory maps

2014-11-20 Thread Jan Beulich
On 21.11.14 at 08:43, kevin.t...@intel.com wrote: From: Chen, Tiejun Sent: Friday, November 21, 2014 2:26 PM On 2014/11/3 18:02, Jan Beulich wrote: On 03.11.14 at 10:55, tiejun.c...@intel.com wrote: On 2014/11/3 17:45, Jan Beulich wrote: On 03.11.14 at 10:32, tiejun.c...@intel.com

Re: [Xen-devel] Regression, host crash with 4.5rc1

2014-11-21 Thread Jan Beulich
On 20.11.14 at 21:07, sfl...@ihonk.com wrote: Running with mwait-idle=0 solves (hides?) the problem. Next step is to fiddle with the C states? For that I'd first of all like to know how much use of C states the system still makes with that option in place. For that I'd need the output of

Re: [Xen-devel] Regression, host crash with 4.5rc1

2014-11-21 Thread Jan Beulich
On 20.11.14 at 21:07, sfl...@ihonk.com wrote: Running with mwait-idle=0 solves (hides?) the problem. Next step is to fiddle with the C states? So this also prompted me to go over the list of errata. Just to confirm - your CPU is family 6 model 44? What stepping? And what nominal frequency?

Re: [Xen-devel] [v7][RFC][PATCH 04/13] hvmloader/util: get reserved device memory maps

2014-11-21 Thread Jan Beulich
On 21.11.14 at 09:54, tiejun.c...@intel.com wrote: On 2014/11/21 15:54, Jan Beulich wrote: On 21.11.14 at 08:43, kevin.t...@intel.com wrote: it's natural to get reserved information once, and then saved for either one-time or multiple-time references. Not really natural, but possible. Yet

Re: [Xen-devel] Buggy interaction of live migration and p2m updates

2014-11-21 Thread Jan Beulich
On 20.11.14 at 19:28, andrew.coop...@citrix.com wrote: Should the guest change the p2m structure during live migration, the toolstack ends up with a stale p2m with a non-p2m frame in the middle, resulting in bogus cross-referencing. Should the guest change an entry in the p2m, the p2m frame

Re: [Xen-devel] [PATCH 1/4] expand x86 arch_shared_info to support linear p2m list

2014-11-21 Thread Jan Beulich
On 21.11.14 at 14:37, jgr...@suse.com wrote: On 11/21/2014 02:26 PM, Andrew Cooper wrote: On 21/11/14 12:57, Juergen Gross wrote: On 11/21/2014 01:23 PM, Jan Beulich wrote: On 14.11.14 at 10:37, jgr...@suse.com.non-mime.internet wrote: --- a/xen/include/public/arch-x86/xen.h +++ b/xen

Re: [Xen-devel] PCI-passthrough for 32 bit guests and high MMIO addresses

2014-11-21 Thread Jan Beulich
On 21.11.14 at 15:39, jgr...@suse.com wrote: Trying to do PCI-passthrough with a 32-bit pv-domain I passed the wrong device to the domain. The MMIO address was too large for a MFN of a 32-bit system (it was 38000320-3800036f). Instead of rejecting the operation Xen tried to perform

Re: [Xen-devel] PCI-passthrough for 32 bit guests and high MMIO addresses

2014-11-21 Thread Jan Beulich
On 21.11.14 at 16:01, andrew.coop...@citrix.com wrote: On 21/11/14 14:54, Jan Beulich wrote: On 21.11.14 at 15:39, jgr...@suse.com wrote: Trying to do PCI-passthrough with a 32-bit pv-domain I passed the wrong device to the domain. The MMIO address was too large for a MFN of a 32-bit system

Re: [Xen-devel] PCI-passthrough for 32 bit guests and high MMIO addresses

2014-11-21 Thread Jan Beulich
On 21.11.14 at 16:17, jgr...@suse.com wrote: On 11/21/2014 03:54 PM, Jan Beulich wrote: On 21.11.14 at 15:39, jgr...@suse.com wrote: Trying to do PCI-passthrough with a 32-bit pv-domain I passed the wrong device to the domain. The MMIO address was too large for a MFN of a 32-bit system

Re: [Xen-devel] [for-xen-4.5 PATCH v2 2/2] dpci: Add ZOMBIE state to allow the softirq to finish with the dpci_pirq.

2014-11-21 Thread Jan Beulich
On 21.11.14 at 16:14, konrad.w...@oracle.com wrote: On Fri, Nov 21, 2014 at 01:03:43PM +0100, Jan Beulich wrote: On 21.11.14 at 12:50, konrad.w...@oracle.com wrote: On November 21, 2014 2:51:33 AM EST, Jan Beulich jbeul...@suse.com wrote: On 20.11.14 at 20:51, konrad.w...@oracle.com wrote

Re: [Xen-devel] PCI-passthrough for 32 bit guests and high MMIO addresses

2014-11-21 Thread Jan Beulich
On 21.11.14 at 16:48, david.vra...@citrix.com wrote: On 21/11/14 15:38, Jan Beulich wrote: On 21.11.14 at 16:01, andrew.coop...@citrix.com wrote: On 21/11/14 14:54, Jan Beulich wrote: On 21.11.14 at 15:39, jgr...@suse.com wrote: Trying to do PCI-passthrough with a 32-bit pv-domain I passed

Re: [Xen-devel] [PATCH 01/19] xen: dump vNUMA information with debug key u

2014-11-21 Thread Jan Beulich
On 21.11.14 at 16:06, wei.l...@citrix.com wrote: Signed-off-by: Elena Ufimsteva ufimts...@gmail.com Signed-off-by: Wei Liu wei.l...@citrix.com Cc: Jan Beulich jbeul...@suse.com --- xen/arch/x86/numa.c | 46 +- 1 file changed, 45 insertions

Re: [Xen-devel] [PATCH 00/19] Virtual NUMA for PV and HVM

2014-11-21 Thread Jan Beulich
On 21.11.14 at 17:35, wei.l...@citrix.com wrote: On Fri, Nov 21, 2014 at 04:25:34PM +, Jan Beulich wrote: On 21.11.14 at 16:06, wei.l...@citrix.com wrote: vnuma_vdistances = [10, 30] # optional Being optional, would the real distances be used instead? And what Default value of [10

Re: [Xen-devel] [PATCH 00/19] Virtual NUMA for PV and HVM

2014-11-21 Thread Jan Beulich
On 21.11.14 at 17:55, wei.l...@citrix.com wrote: Nonetheless I'm all for having a configuration option that would meet both present and future need. Do you have anything in mind? Are you suggesting we should allow specifying every element in SLIT in xl? I think that would be desirable. Jan

Re: [Xen-devel] [PATCH] xen-pciback: drop SR-IOV VFs when PF driver unloads

2014-11-23 Thread Jan Beulich
On 21.11.14 at 23:03, konrad.w...@oracle.com wrote: I rewrote it a bit to be more in the style of pciback: [...] [v2: Removed the switch statement, moved it about] What you don't mention here is that you also removed the outer loop, yet that breaks functionality afaict: There can (and I

Re: [Xen-devel] Regression, host crash with 4.5rc1

2014-11-24 Thread Jan Beulich
On 23.11.14 at 02:28, sfl...@ihonk.com wrote: With mwait-idle=0: (XEN) 'c' pressed - printing ACPI Cx structures (XEN) ==cpu0== (XEN) active state: C0 (XEN) max_cstate: C7 (XEN) states: (XEN) C1: type[C1] latency[001] usage[] method[ FFH]

Re: [Xen-devel] [for-xen-4.5 PATCH v2 2/2] dpci: Add ZOMBIE state to allow the softirq to finish with the dpci_pirq.

2014-11-24 Thread Jan Beulich
On 21.11.14 at 17:45, konrad.w...@oracle.com wrote: From 90d00db0949a8e796d7f812134753a54b2fe3d51 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk konrad.w...@oracle.com Date: Thu, 20 Nov 2014 14:28:11 -0500 Subject: [PATCH] dpci: Add 'masked' as an gate for hvm_dirq_assist to process.

Re: [Xen-devel] Regression, host crash with 4.5rc1

2014-11-24 Thread Jan Beulich
On 24.11.14 at 10:08, sfl...@ihonk.com wrote: On Nov 24, 2014, at 00:45, Jan Beulich jbeul...@suse.com wrote: On 23.11.14 at 02:28, sfl...@ihonk.com wrote: As promised, below is the apic-verbosity=debug log, with 'i'. Thanks! I'm sorry, I misspelled the option, it's really apic_verbosity

Re: [Xen-devel] [PATCH 14/19] hvmloader: disallow memory relocation when vNUMA is enabled

2014-11-24 Thread Jan Beulich
On 21.11.14 at 20:56, konrad.w...@oracle.com wrote: On Fri, Nov 21, 2014 at 03:06:56PM +, Wei Liu wrote: --- a/tools/firmware/hvmloader/pci.c +++ b/tools/firmware/hvmloader/pci.c @@ -88,6 +88,19 @@ void pci_setup(void) printf(Relocating guest memory for lowmem MMIO space %s\n,

Re: [Xen-devel] [PATCH 14/19] hvmloader: disallow memory relocation when vNUMA is enabled

2014-11-24 Thread Jan Beulich
On 21.11.14 at 16:06, wei.l...@citrix.com wrote: Signed-off-by: Wei Liu wei.l...@citrix.com So this is the fourth patch now without any description whatsoever. --- a/tools/firmware/hvmloader/pci.c +++ b/tools/firmware/hvmloader/pci.c @@ -88,6 +88,19 @@ void pci_setup(void)

Re: [Xen-devel] Hypervisor error messages after xl block-detach with linux 3.18-rc5

2014-11-24 Thread Jan Beulich
On 24.11.14 at 10:55, jgr...@suse.com wrote: - Sometimes I see only NMI watchdog messages, looking into hanging cpu state via xen debug keys I can see the cpu(s) in question are spinning in _raw_spin_lock(): __handle_mm_fault()-__pte_alloc()-pmd_lock()-_raw_spin_lock() The

Re: [Xen-devel] [PATCH 12/19] hvmloader: construct SRAT

2014-11-24 Thread Jan Beulich
On 24.11.14 at 11:13, wei.l...@citrix.com wrote: On Mon, Nov 24, 2014 at 10:08:42AM +, Jan Beulich wrote: On 21.11.14 at 16:06, wei.l...@citrix.com wrote: @@ -270,6 +331,13 @@ static int construct_secondary_tables(unsigned long *table_ptrs, table_ptrs[nr_tables

Re: [Xen-devel] Regression, host crash with 4.5rc1

2014-11-24 Thread Jan Beulich
On 24.11.14 at 10:08, sfl...@ihonk.com wrote: On Nov 24, 2014, at 00:45, Jan Beulich jbeul...@suse.com wrote: On 23.11.14 at 02:28, sfl...@ihonk.com wrote: With mwait-idle=0: (XEN) 'c' pressed - printing ACPI Cx structures (XEN) ==cpu0== (XEN) active state: C0 (XEN

Re: [Xen-devel] [PATCH 0/3] x86: XSA-109/110 follow-up (to be considered for 4.5)

2014-11-24 Thread Jan Beulich
checking (as done in the first two patches) reduces the chances of them getting abused. Not unduly crashing the guest (as done in the third one) may avoid future security issues of guest user mode affecting the guest kernel. Signed-off-by: Jan Beulich jbeul...@suse.com Hi Konrad - looks like I

Re: [Xen-devel] [PATCH 2/3] x86: don't ignore foreigndom input on various MMUEXT ops

2014-11-24 Thread Jan Beulich
On 24.11.14 at 13:43, dunl...@umich.edu wrote: On Thu, Nov 20, 2014 at 10:12 AM, Jan Beulich jbeul...@suse.com wrote: Instead properly fail requests that shouldn't be issued on foreign domains or - for MMUEXT_{CLEAR,COPY}_PAGE - extend the existing operation to work that way. I take

Re: [Xen-devel] Hypervisor error messages after xl block-detach with linux 3.18-rc5

2014-11-24 Thread Jan Beulich
On 24.11.14 at 18:27, jgr...@suse.com wrote: On 11/24/2014 04:09 PM, Juergen Gross wrote: Still seeing the issue, but less frequent. OTOH I just found in above thread in lkml that 3.17 is showing that issue, too. :-( I'll try to setup a pv-variant of Linus' patch and test it... First test

Re: [Xen-devel] Regression, host crash with 4.5rc1

2014-11-25 Thread Jan Beulich
On 24.11.14 at 23:17, sfl...@ihonk.com wrote: I'm combining this action with your patch, see below. Please let me know if this was incorrect. Thanks, that's perfectly fine. (XEN) 'c' pressed - printing ACPI Cx structures (XEN) ==cpu0== (XEN) active state:C0 (XEN) max_cstate:

Re: [Xen-devel] [PATCH for-xen-4.5] x86/pvh/vpmu: Disable VPMU for PVH guests

2014-11-25 Thread Jan Beulich
-by: Jan Beulich jbeul...@suse.com --- a/xen/arch/x86/hvm/hvm.c +++ b/xen/arch/x86/hvm/hvm.c @@ -2217,8 +2217,7 @@ int hvm_vcpu_initialise(struct vcpu *v) goto fail1; /* NB: vlapic_init must be called before hvm_funcs.vcpu_initialise */ -if ( is_hvm_vcpu(v) ) -rc = vlapic_init

Re: [Xen-devel] Failure on make clean

2014-11-25 Thread Jan Beulich
On 25.11.14 at 08:44, jgr...@suse.com wrote: Hi, make clean in xen-unstable is failing: make[2]: Entering directory '/home/gross/xen/tools' set -e; if test -d qemu-xen-traditional-dir/.; then \ make -C qemu-xen-traditional-dir clean; \ fi make[3]: Entering directory

Re: [Xen-devel] [PATCH for-4.5] x86/HVM: Partial revert of 28b4baacd5

2014-11-25 Thread Jan Beulich
On 25.11.14 at 11:08, andrew.coop...@citrix.com wrote: A failed vmentry is overwhelmingly likely to be caused by corrupt VMCS state. As a result, injecting a fault and retrying the the vmentry is likely to fail in the same way. That's not all that unlikely - remember that the change was

Re: [Xen-devel] Regression, host crash with 4.5rc1

2014-11-25 Thread Jan Beulich
On 25.11.14 at 10:38, sfl...@ihonk.com wrote: On 11/25/2014 12:16 AM, Jan Beulich wrote: Interesting, so other than for me (perhaps due to other patches I have in my tree) the change resulted in C states now being used again despite mwait-idle=0, which is good. Question now

Re: [Xen-devel] [PATCH for-4.5] x86/HVM: Partial revert of 28b4baacd5

2014-11-25 Thread Jan Beulich
On 25.11.14 at 11:46, andrew.coop...@citrix.com wrote: On 25/11/14 10:42, Jan Beulich wrote: On 25.11.14 at 11:08, andrew.coop...@citrix.com wrote: A failed vmentry is overwhelmingly likely to be caused by corrupt VMCS state. As a result, injecting a fault and retrying the the vmentry

Re: [Xen-devel] [PATCH for-4.5] x86/HVM: Partial revert of 28b4baacd5

2014-11-25 Thread Jan Beulich
On 25.11.14 at 11:58, andrew.coop...@citrix.com wrote: On 25/11/14 10:46, Andrew Cooper wrote: On 25/11/14 10:42, Jan Beulich wrote: On 25.11.14 at 11:08, andrew.coop...@citrix.com wrote: A failed vmentry is overwhelmingly likely to be caused by corrupt VMCS state. As a result, injecting

Re: [Xen-devel] [PATCH for-4.5] x86/HVM: Partial revert of 28b4baacd5

2014-11-25 Thread Jan Beulich
On 25.11.14 at 13:10, andrew.coop...@citrix.com wrote: On 25/11/14 11:31, Jan Beulich wrote: On 25.11.14 at 11:58, andrew.coop...@citrix.com wrote: On 25/11/14 10:46, Andrew Cooper wrote: On 25/11/14 10:42, Jan Beulich wrote: On 25.11.14 at 11:08, andrew.coop...@citrix.com wrote: A failed

[Xen-devel] [PATCH] vNUMA: rename interface structures

2014-11-25 Thread Jan Beulich
No-one (including me) paid attention during review that these structures don't adhere to the naming requirements of the public interface: Consistently use xen_ prefixes at least for all new additions. Signed-off-by: Jan Beulich jbeul...@suse.com --- a/tools/libxc/include/xenctrl.h +++ b/tools

  1   2   3   4   5   6   7   8   9   10   >