similar to: [PATCH] VT-d: flush iotlb of selective iommu when a domain''s VT-d table is changed

On map: only flush when old PTE was valid or invalid PTE may be cached. On unmap: always flush old entry, but skip flush for unaffected IOMMUs. Signed-off-by: Espen Skoglund <espen.skoglund@netronome.com> -- iommu.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) -- diff -r 8187fd8113f9 xen/drivers/passthrough/vtd/iommu.c ---

This a step forward to fix the security hole introduced by dom0''s 1:1 mapping VT-d table: remove the critical code and data from it. The more flexible solution is to update dom0''s VT-d table on demand as what will be done for other PV domains. However, there could bring a performance issue even with software optimization. Iotlb flush of some hardware is time-consuming.

According to vt-d specs, the addr in IOTLB invalidation descriptor should be 4K page aligned. Signed-off-by: Yang Zhang <yang.z.zhang@Intel.com> diff -r 0455d8317631 xen/drivers/passthrough/vtd/qinval.c --- a/xen/drivers/passthrough/vtd/qinval.c Thu Jun 28 18:43:28 2012 +0100 +++ b/xen/drivers/passthrough/vtd/qinval.c Wed Jul 11 08:43:24 2012 +0800 @@ -140,7 +140,7 @@ static int

Keir: This is to to make the IDE device model multithreading so that the VMX domain IO access completion (triggering DMA operation) can be asynchronize with the completion of DMA operation. With this patch we get 8%--14% performance gain for kernel build. Thanks, eddie Yang, Xiaowei wrote: > Originally in qemu when a IDE dma transfer is started which is > triggered by access to 0xc000

Hi, I''ve added some preliminary support for VT-d for paravirtualized guests. This must be enabled using an ''iommu_pv'' boot parameter (disabled by default). I''ve added some python bindigs to allow xend to assign PCI devices to IOMMU for PV guests. For HVM guests this is handled in ioemu. Not sure if it makes sense to handle both cases in one place. The

Keir, The patch moves ACPI timer to HV, which is the last platform timer in Qemu. We found Vista polls ACPI timer very frequently (about 15 times averagely) when handling timer (RTC @ 64HZ) interrupt routine. Though the exact reason is known, it should be related to system time adjustment. When it''s in Qemu, the overhead is big. After moving, Vista''s idle overhead decreases

Keir, This patch fixes cirrus and rt8139 co-exist issue in new qemu-dm. The root cause is that if two MMIO spaces are continuous, qemu may misuse last MMIO space''s read/write to handle current request. Thanks, Xiaowei Signed-off-by: Yang Xiaowei <xiaowei.yang@intel.com> diff -r ecb8ff1fcf1f tools/ioemu/target-i386-dm/exec-dm.c --- a/tools/ioemu/target-i386-dm/exec-dm.c Fri

Hello, Are you going to fix https://bugs.debian.org/730254 or what is the status? I would like to close old issues in case these are not going to get fixed. --- Henri Salo -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 198 bytes Desc: Digital signature URL:

Package: xen Version: 4.0.1-5.11 Severity: important Tags: security, patch, fixed-upstream http://www.openwall.com/lists/oss-security/2013/11/21/2 Description: An inverted boolean parameter resulted in TLB flushes not happening upon clearing of a present translation table entry. Retaining stale TLB entries could allow guests access to memory that ought to have been revoked, or grant greater

This patch fixes MOVS handling memory spanning multiple pages. Signed-off-by: Eddie Dong <eddie.dong@intel.com> Signed-off-by: Xiaowei Yang <xiaowei.yang@intel.com> Signed-off-by: Xin Li <xin.b.li@intel.com> Thanks, Xiaowei _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel

The original code only sets EN bit of IA32_PERFEVTSEL0 when profiling is started. Signed-off-by: Xiaowei Yang <xiaowei.yang@intel.com> Regards, Xiaowei _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel

See below... ---------- Forwarded Message ---------- Subject: RE: [Xen-devel] xenoprof passive profiling and "mode" setting Date: Wednesday 05 July 2006 21:53 From: "Yang, Xiaowei" <xiaowei.yang@intel.com> To: "Keir Fraser" <Keir.Fraser@cl.cam.ac.uk>, "Ray Bryant" <raybry@mpdtxmail.amd.com> Cc: xen-devel@lists.xensource.com

This patch (attached) fixes a small problem in xentrace_format. Signed-off-by: Yang Xiaowei <xiaowei.yang@intel.com> Zhou Ting <ting.g.zhou@intel.com> --- diff -r 0df3bf8aac1e tools/xentrace/formats --- a/tools/xentrace/formats Mon Jun 16 16:35:17 2008 +0100 +++ b/tools/xentrace/formats Thu Aug 21 17:36:03 2008 +0800 @@ -23,8 +23,8 @@ 0x00081001 CPU%(cpu)d

On 2016/1/4 14:22, Jason Wang wrote: > > > On 01/04/2016 09:39 AM, Yang Zhang wrote: >> On 2015/12/31 15:13, Jason Wang wrote: >>> This patch tries to implement an device IOTLB for vhost. This could be >>> used with for co-operation with userspace(qemu) implementation of >>> iommu for a secure DMA environment in guest. >>> >>> The idea is

On 2016/1/4 14:22, Jason Wang wrote: > > > On 01/04/2016 09:39 AM, Yang Zhang wrote: >> On 2015/12/31 15:13, Jason Wang wrote: >>> This patch tries to implement an device IOTLB for vhost. This could be >>> used with for co-operation with userspace(qemu) implementation of >>> iommu for a secure DMA environment in guest. >>> >>> The idea is

From: Joerg Roedel <jroedel at suse.de> The Intel VT-d driver already has a matching function to determine the default domain type for a device. Wire it up in intel_iommu_ops. Signed-off-by: Joerg Roedel <jroedel at suse.de> --- drivers/iommu/intel-iommu.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index

an obvious fix to PIC IO intercept. In PIC IO, address from send_pio_req is physical address already. Signed-off-by: Xiaohui Xin <xiaohui.xin@intel.com> Signed-off-by: Xiaowei Yang <xiaowei.yang@intel.com> Signed-off-by: Xin Li <xin.b.li@intel.com> _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com

From: Joerg Roedel <jroedel at suse.de> Convert the Intel IOMMU driver to use the probe_device() and release_device() call-backs of iommu_ops, so that the iommu core code does the group and sysfs setup. Signed-off-by: Joerg Roedel <jroedel at suse.de> --- drivers/iommu/intel-iommu.c | 67 ++++--------------------------------- 1 file changed, 6 insertions(+), 61 deletions(-) diff

diff -r e6266fc76d08 -r 6feac926cf80 xen/drivers/passthrough/vtd/iommu.c --- a/xen/drivers/passthrough/vtd/iommu.c Fri Jul 27 12:22:13 2012 +0200 +++ b/xen/drivers/passthrough/vtd/iommu.c Mon Jul 30 15:35:16 2012 -0700 @@ -2137,6 +2137,15 @@ int __init intel_vtd_setup(void) { iommu = drhd->iommu; + printk("Intel VT-d supported page sizes: 4kB"); + if

On 2015/12/31 15:13, Jason Wang wrote: > This patch tries to implement an device IOTLB for vhost. This could be > used with for co-operation with userspace(qemu) implementation of > iommu for a secure DMA environment in guest. > > The idea is simple. When vhost meets an IOTLB miss, it will request > the assistance of userspace to do the translation, this is done > through: