similar to: [Patch] Fix cirrus and rt8139 co-exist issue

This function (introduced quite a long time ago in e7911109f4321e9ba0cc56a253b653600aa46bea - "disable qemu PCI devices in HVM domains") appears to be completely broken, causing the regression reported in http://bugzilla.xensource.com/bugzilla/show_bug.cgi?id=1805 (due to the newly added caller of it in 56d7747a3cf811910c4cf865e1ebcb8b82502005 - "qemu: clean up MSI-X table

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

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

From: "Xiaowei.Hu" <xiaowei.hu at oracle.com> ocfs2_block_group_alloc_discontig() disables chain relink by setting ac->ac_allow_chain_relink = 0 because it grabs clusters from multiple cluster groups. It doesn't keep the credits for all chain relink,but ocfs2_claim_suballoc_bits overrides this in this call trace:

Hi, I am using a freebsd 4.5-stable system. I am using the latest "rsync version 2.5.5 protocol version 26". I tried to rsync my home directory to another machine: rsync -Cavz /homes/yxw/ baggie.mit.edu:/disk1/ &> rsync.out& However, I ran into the error: www/wf-02.jpg www/wf-03.jpg www/www.c www/www.tar www/xiaowei.doc www/xiaowei_dadmom.jpg www/yxw-contact.txt wrote

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

Xiaowei, I''m puzzled by the following bit of code in p4_check_ctrs():        if (guest_kernel_mode(current, regs))                 mode = 1;         else if (ring_0(regs))                 mode = 2; If I look at the definition for guest_kernel_mode() it is: include/asm-x86/x86_64/regs.h: #define guest_kernel_mode(v, r)   \     (ring_3(r) && ((v)->arch.flags &

Hi Renato, This patch is to add Xenoprof passive domain support in SMP environment. Basically: - It allocates per vcpu buffers for passive domain and maps them into primary domain''s space. - When primary domain gets sampled and triggers virq, its kernel module will handle passive domain'' samples besides its owns. There is potential buffer overflow if passive is very busy while

Recently we had a try of stubdom, whose general status is good. One issue we found is with aio/sync blktap as backend, disk performance is obviously slower, and there are some IDE kernel error messages (like irq timeout) at boot time. Another issue (not stubdom specific) comes from blktap''s support for QCOW image which is based on a backing file. We never tried this configure

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 ---

[HVM] Pick up SMBIOS entry point in the ROMBIOS. Signed-off-by: Andrew D. Ball <aball@us.ibm.com> diff -r 1d817bfc5ed9 tools/firmware/rombios/rombios.c --- a/tools/firmware/rombios/rombios.c Fri Aug 11 14:22:54 2006 +0100 +++ b/tools/firmware/rombios/rombios.c Fri Aug 11 14:55:22 2006 -0400 @@ -9443,6 +9443,43 @@ rom_scan_increment: mov ds, ax ret +#ifdef HVMASSIST + +; Copy the

When a domain''s VT-d table is changed, only the iommus under which the domain has assigned devices need to be flushed. Signed-off-by: Yang, Xiaowei <xiaowei.yang@intel.com> Thanks, Xiaowei _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel

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.

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

While removing a non-empty directory, the kernel dumps a message: (rmdir,21743,1):ocfs2_unlink:953 ERROR: status = -39 Suppress the error message from being printed in the dmesg so users don't panic. Signed-off-by: Goldwyn Rodrigues <rgoldwyn at suse.com> --- diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 04ee1b5..33c7b91 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@

I''m looking into getting Xenoprof to tun in an HVM domain, since we will eventually need a profiler for HVM domains to track down areas of poor performance. (HVMs have poor performance? :) ) Being relatively new to OProfile, Xenoprof, and Xen internals, I would appreciate any pointers, tips, and comments on how to work the implementation. I see three basic areas of work. 1. Implement

Hi all, this is the long awaited patch series to add xen device model support in qemu; the main author is Anthony Perard. Developing this series we tried to come up with the cleanest possible solution from the qemu point of view, limiting the amount of changes to common code as much as possible. The end result still requires a couple of hooks in piix_pci but overall the impact should be very

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