qemu/hw/vfio
Alex Williamson 95239e1625 vfio/pci: Lazy PBA emulation
The PCI spec recommends devices use additional alignment for MSI-X
data structures to allow software to map them to separate processor
pages.  One advantage of doing this is that we can emulate those data
structures without a significant performance impact to the operation
of the device.  Some devices fail to implement that suggestion and
assigned device performance suffers.

One such case of this is a Mellanox MT27500 series, ConnectX-3 VF,
where the MSI-X vector table and PBA are aligned on separate 4K
pages.  If PBA emulation is enabled, performance suffers.  It's not
clear how much value we get from PBA emulation, but the solution here
is to only lazily enable the emulated PBA when a masked MSI-X vector
fires.  We then attempt to more aggresively disable the PBA memory
region any time a vector is unmasked.  The expectation is then that
a typical VM will run entirely with PBA emulation disabled, and only
when used is that emulation re-enabled.

Reported-by: Shyam Kaushik <shyam.kaushik@gmail.com>
Tested-by: Shyam Kaushik <shyam.kaushik@gmail.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2016-01-19 11:33:42 -07:00
..
calxeda-xgmac.c hw/vfio/platform: calxeda xgmac device 2015-06-09 08:17:17 -06:00
common.c vfio: Allow hotplug of containers onto existing guest IOMMU mappings 2015-10-05 12:39:47 -06:00
Makefile.objs vfio/pci: Split quirks to a separate file 2015-09-23 13:04:45 -06:00
pci-quirks.c vfio/pci-quirks: Only quirk to size of PCI config space 2016-01-19 11:33:41 -07:00
pci.c vfio/pci: Lazy PBA emulation 2016-01-19 11:33:42 -07:00
pci.h vfio/pci: Lazy PBA emulation 2016-01-19 11:33:42 -07:00
platform.c vfio: Use g_new() & friends where that makes obvious sense 2015-11-10 12:11:08 -07:00