Sir ,i am still puzzled by the windows and freebsd arch similar. 1 the window TPS say that windwo allocate the resource window in default size of 1M or 2M,so there may be hole ,does that happen in freebsd 5 or 6? 2 in my view i believe that freebsd us the "just enough "tactics,so the nexus level of resource view is ===continuous====with NO hole in a boot up system, IF hot remove do not happen .am i right? 3 IF i do a PCI hotplug under a bridge, and the bridge 's MEM Window is full ,i have to do reballacne (including use the device_pause method:)), and if i can not declaim the resource from other bridge because "nexus level of resource view is ===continuous====with NO hole ", can i extend the physical address space beyond the boot time locate range to PCI host bridge ?
On 11/6/05, John Baldwin <[EMAIL PROTECTED]> wrote: > On Sunday 06 November 2005 06:14 am, kylin wrote: > > On 11/6/05, M. Warner Losh <[EMAIL PROTECTED]> wrote: > > > In message: <[EMAIL PROTECTED]> > > > > > > kylin <[EMAIL PROTECTED]> writes: > > > : /////////////// > > > : pci bridge dynamic resize > > > : ///////////// > > > : it seems that the device arch of freebsd is similar to what is revealed > > > : in window OS. i have read the pcie hotplug tps of windows longhorn ,it > > > : is said that with some hardware mechanisms the pci bridge driver can do > > > : global pci resource window reconfiguration.so good to the hotplugin pci > > > : device for it avoid prelocating resource for the device . > > > : i wonder ,if the mem /io/irq reconfiguration possible under freebsd .:) > > > : 1 > > > > > > Yes. Cardbus does it all the time. However, there's no pcie hot-plug > > > support yet, so the process for kicking off configuration of the new > > > device doesn't happen. > > > > > > Warner > > > > sorry for my poor grammar ,i think i confused the public:) i will make > > myself clear with the words below about the PCI Multi-level Rebalance > > > > PCI Multi-level Rebalance in Windows Longhorn > > Updated: November 25, 2003 > > No, FreeBSD doesn't currently do what this decribes yet. It would be possible > to do it by adding a new device_pause() method that drivers would be required > to implement while the resources were shuffled around though and possibly a > device_unpause() method so that they could update their state if their > resources were changed while the device was paused. > > -- > John Baldwin <[EMAIL PROTECTED]> <>< http://www.FreeBSD.org/~jhb/ > "Power Users Use the Power to Serve" = http://www.FreeBSD.org > -- we who r about to die,salute u! _______________________________________________ freebsd-hackers@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-hackers To unsubscribe, send any mail to "[EMAIL PROTECTED]"
