similar to: No subject

Please can you do an ''lspci -nv'' to find out the exact version of your controller. I''m wandering whether it features in pci/quirks.c and whether the fixup code is borked on Xen. Also, have you tried fiddling around with any of the BIOS IDE legacy mode settings? There really is no good explanation for a) why the MMIO region is so low on native, and b) why it is

On 2014-06-12 04:27, Rusty Russell wrote: > Henning Schild <henning.schild at siemens.com> writes: >> Hi, >> >> i am working on the jailhouse[1] project and am currently looking at >> inter-VM communication. We want to connect guests directly with virtual >> consoles based on shared memory. The code complexity in the hypervisor >> should be minimal, it

On 2014-06-12 04:27, Rusty Russell wrote: > Henning Schild <henning.schild at siemens.com> writes: >> Hi, >> >> i am working on the jailhouse[1] project and am currently looking at >> inter-VM communication. We want to connect guests directly with virtual >> consoles based on shared memory. The code complexity in the hypervisor >> should be minimal, it

Rusty Russell <rusty at rustcorp.com.au> writes: > Anthony Liguori <aliguori at us.ibm.com> writes: >> "Michael S. Tsirkin" <mst at redhat.com> writes: >>> + case offsetof(struct virtio_pci_common_cfg, device_feature_select): >>> + return proxy->device_feature_select; >> >> Oh dear no... Please use defines like the

On 2014-06-13 02:47, Rusty Russell wrote: > Jan Kiszka <jan.kiszka at siemens.com> writes: >> On 2014-06-12 04:27, Rusty Russell wrote: >>> Henning Schild <henning.schild at siemens.com> writes: >>> It was also never implemented, and remains a thought experiment. >>> However, implementing it in lguest should be fairly easy. >> >> The

On 2014-06-13 02:47, Rusty Russell wrote: > Jan Kiszka <jan.kiszka at siemens.com> writes: >> On 2014-06-12 04:27, Rusty Russell wrote: >>> Henning Schild <henning.schild at siemens.com> writes: >>> It was also never implemented, and remains a thought experiment. >>> However, implementing it in lguest should be fairly easy. >> >> The

P_STREAM can get more than 4GMb/s for the receive side, and more than 5GMb/= s for the send side. Is it the result from the raw socket or through tap? I want to duplicate such performance with vhost on my side. I can only get = more than 1GMb/s with following conditions: 1) disabled the GRO feature in the host 10G NIC driver 2) vi->big_packet in guest is false 3) MTU is 1500. 4) raw socket, not

P_STREAM can get more than 4GMb/s for the receive side, and more than 5GMb/= s for the send side. Is it the result from the raw socket or through tap? I want to duplicate such performance with vhost on my side. I can only get = more than 1GMb/s with following conditions: 1) disabled the GRO feature in the host 10G NIC driver 2) vi->big_packet in guest is false 3) MTU is 1500. 4) raw socket, not

Since we know vq->vring.num is a power of 2, modulus is lazy (it's asserted in vring_new_virtqueue()). Signed-off-by: Rusty Russell <rusty at rustcorp.com.au> --- drivers/virtio/virtio_ring.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@

Since we know vq->vring.num is a power of 2, modulus is lazy (it's asserted in vring_new_virtqueue()). Signed-off-by: Rusty Russell <rusty at rustcorp.com.au> --- drivers/virtio/virtio_ring.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@

Hi [1.] One line summary of the problem: rsync segfaulting and the kernel oops'ing while synchronizing two smbfs's [2.] Full description of the problem/report: I am implementing file synchronization between two Windows NT 4 machines through two smbfs mounts. Rsync runs for about half an hour; then the kernel gives an oops and rsync segfaults. Hereafter the smbfs file system is

We force notification when the ring is full, even if the host has indicated it doesn't want to know. This seemed like a good idea at the time: if we fill the transmit ring, we should tell the host immediately. Unfortunately this logic also applies to the receiving ring, which is refilled constantly. We should introduce real notification thesholds to replace this logic. Meanwhile, removing

We force notification when the ring is full, even if the host has indicated it doesn't want to know. This seemed like a good idea at the time: if we fill the transmit ring, we should tell the host immediately. Unfortunately this logic also applies to the receiving ring, which is refilled constantly. We should introduce real notification thesholds to replace this logic. Meanwhile, removing

Henning Schild <henning.schild at siemens.com> writes: > Hi, > > i am working on the jailhouse[1] project and am currently looking at > inter-VM communication. We want to connect guests directly with virtual > consoles based on shared memory. The code complexity in the hypervisor > should be minimal, it should just make the shared memory discoverable > and provide a

Hi all.. I have found some problems on smbfs module in 2.4.18 kernel. I compiled it by myself (not the very first kernel compilation in my life ;-)) and then I have got it. Looks like it touch smbfs module as when I recompile 2.4.18 modules with smbfs sources changed to sources of smbfs from 2.4.17 problem disappears!! My mainboard is Abit BE6 with Pentium III 450 MHz. I am using SuSE 7.3 with

Hi All, When tried to pass through 2 mpt2sas HBA to hvm guest, hvmloader paused with below: MPT BIOS Fault 09h encountered at adapter PCI(00h,04h,00h) Press any key to continue... Checked related codes and mostly like it caused by rombios did not loaded MPT BIOS properly, and lead MPT BIOS failed to bootup. config-file of the guest as below: ---------------------------------- # cat vm.cfg

cb wrote: > Dear Segher, Hi, Why do you ask me? Why not try the vorbis-dev@xiph.org list? (Or the Tremor list). > I am a portable audio player firmware engineer. I try to add vorbis support to our ARM7 base board. Because the total SRAM of our board is only 48kB and only about 32KB can be used by decoder, I try to save all huffman table in flash ROM then don't need to extract the

If qxl_device_init fails on creating resources and does not report it, then qxl module will catch null pointer exception on remove, or on probe's error path. The patch adds error path with resources release into qxl_device_init. Found by Linux Driver Verification project (linuxtesting.org). Signed-off-by: Anton Vasilyev <vasilyev at ispras.ru> --- drivers/gpu/drm/qxl/qxl_kms.c | 80

Anthony Liguori <aliguori at us.ibm.com> writes: > Rusty Russell <rusty at rustcorp.com.au> writes: > >> Anthony Liguori <aliguori at us.ibm.com> writes: >>> "Michael S. Tsirkin" <mst at redhat.com> writes: >>>> + case offsetof(struct virtio_pci_common_cfg, device_feature_select): >>>> + return

Anthony Liguori <aliguori at us.ibm.com> writes: > Rusty Russell <rusty at rustcorp.com.au> writes: > >> Anthony Liguori <aliguori at us.ibm.com> writes: >>> "Michael S. Tsirkin" <mst at redhat.com> writes: >>>> + case offsetof(struct virtio_pci_common_cfg, device_feature_select): >>>> + return