Change from v1:
Avoid changing the existing coding style in certain files.
Signed-off-by: Stuart Brady <stuart.brady@gmail.com>
git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@6120 c046a42c-6fe2-441c-8c8c-71466251a162
MMIO exits are more expensive in KVM or Xen than in QEMU because they
involve, at least, privilege transitions. However, MMIO write
operations can be effectively batched if those writes do not have side
effects.
Good examples of this include VGA pixel operations when in a planar
mode. As it turns out, we can get a nice boost in other areas too.
Laurent mentioned a 9.7% performance boost in iperf with the coalesced
MMIO changes for the e1000 when he originally posted this work for KVM.
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@5961 c046a42c-6fe2-441c-8c8c-71466251a162
We're currently ignoring the e1000 VLAN tagging, stripping and filtering
features in the e1000 emulation. This patch adds backing for the
relevant registers and provides a software implementation of the
acceleration, such that a guest can make use of VLANs.
This is mostly (only?) useful for a guest on a bridge (not user mode
networking). The only caveat beyond that is that you need to make sure
the host NIC isn't doing it's own tagging, stripping, or filtering.
This generally means the host NIC on the bridge should not be part of a
VLAN.
Signed-off-by: Alex Williamson <alex.williamson@hp.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@5766 c046a42c-6fe2-441c-8c8c-71466251a162
e1000_receive() has code to raise a receive overflow interrupt when the receive
buffer head and tail match. However, with the present implementation of
e1000_can_receive(), this code is unreachable -- and etherboot breaks as a
result.
Signed-off-by: Charles Duffy <charles_duffy@messageone.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@4987 c046a42c-6fe2-441c-8c8c-71466251a162
Previously, all data descriptors used TSE context descriptor by default,
It's not correct, per spec, data descriptor uses TSE bit to indicate
whether use TSE,
Legacy data descripter never use TSE.
This patch fixed this bug.
git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@4878 c046a42c-6fe2-441c-8c8c-71466251a162
This patch fixes endianness issues in the e1000 nic emulation, which
currently only works on little endian hosts with little endian targets.
Byte swapping does not depend on host endianness, so this patch remove
the use of cpu_to_le32 and le32_to_cpu functions. It depends on the path
from the CPU to the device, which is currently and *wrongly* implemented
in Qemu as a byteswap on big endian targets. This patch does the same
as in other devices emulation as all the currently implemented targets
work with this implementation.
git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@4046 c046a42c-6fe2-441c-8c8c-71466251a162
According to the Intel 82540EM manual, the mmio space is
128k size.
Copied from Xen list and noted by tina..yang@oracle.com
Signed-off-by: Dor Laor <dor.laor@qumranet.com>
git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@4032 c046a42c-6fe2-441c-8c8c-71466251a162
Applied %s/^\([^I ]*\)^I/\1 /g on e1000.c and added e1000 to help message.
git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@3949 c046a42c-6fe2-441c-8c8c-71466251a162
