operation automatically gets you a fresh page at the same
pseudo-physical address as Keir suggested.
Signed-off-by: Isaku Yamahata <yamahata@valinux.co.jp>
interface (the legacy hypercalls would break if subcommands with large
argument structures were added, as it would grow the size of the
union of all argument structures).
Also, based on a patch from Kevin Tian, add a new physdev op to
signal EOI for a particular irq.
Signed-off-by: Keir Fraser <keir@xensource.com>
any more. xen/ia64 dom0 vp model is a big change so that xen/ia64
with the old model (P=M) still remains as the compile option.
Hopefully the work around will be eliminated in the future completely.
Signed-off-by: Isaku Yamahata <yamahata@valinux.co.jp>
of the structures on the capability list. Specifically, this patch adds
support for reading data through the Vital Product Data capability
structure and for manipulating power management of a card. A driver
domain is not allowed to enable Power Management Events (the PME trace
may be shared across devices in many domains), but it can put a device
in its control to sleep or query it for power usage statistics. This
code could possibly be expanded in the future to add support for AGP,
PCI-X, and MSI/MSIX (all of which are controlled through structures on
the capability list).
This patch also corrects some formatting issues in the PCI backend and
adds some comments to the code regarding permissive mode.
Signed-off-by: Ryan Wilson <hap9@epoch.ncsc.mil>
linux default implementations of dma_declare_coheremnt_memory() and its
families which is defined in include/linux/dma-mapping.h.
So those in pci-dma-xen.c are unnecessary. #ifdef out them.
PATCHNAME: pci-dma-xen-common
Signed-off-by: Isaku Yamahata <yamahata@valinux.co.jp>
space handlers were making calls into ACPI code which uses semaphores.
Since semaphores can not be locked while atomic (because they could
sleep), I changed the way the PCI backend responds to requests from the
frontend. Previously, the virtual configuration space handlers ran in
the same context as the event channel interrupt handler (which was often
atomic if not always atomic). Now the interrupt handler schedules a
callback function (a bottom half) in the system work queue (keventd)
that will get called in process context at a slightly later time. This
allows the handlers in the virtual configuration space to run in process
context and to call any core PCI function regardless of whether it will
sleep or not.
Signed-off-by: Ryan Wilson <hap9@epoch.ncsc.mil>
checksums into already encrypted packets (esp4) in dom0. Obviously,
it is not possible to insert a checksum into an already encrypted
packet, so this patch inserts the checksum prior to encrypting
packets in net/ipv4/xfrm4_output.c.
To do this cleanly, the TCP/UDP header pointers need to be pointed to
the correct spot, so this functionality has been abstracted into a new
function.
This patch fixes bug 143 (verified by Jim Dykman). Earlier version
verified by Jon McCune.
Signed-off-by: James Dykman <dykman@us.ibm.com>
Signed-off-by: Jon Mason <jdmason@us.ibm.com>
This support is only active when supervisor_mode_kernel is enabled
in the Xen build (and when the hardware supports sysenter).
Signed-off-by: Ian Campbell <ian.campbell@xensource.com>
Add support to physdev ops, and thus give IOSAPIC RTEs
managed by Xen now. Dom0 now issues hypercall to r/w
RTE entry. Another change is the irq vector allocation
which is also owned by xen now.
After this change, the IOSAPIC is almost owned by xen
with only exception as IOSAPIC EOI which is still issued
by dom0 directly. But that's OK since currently dom0
owns all external physical devices. Later full event
channel mechanism will provide necessary support for
driver domain, and at that time, dom0 instead issues
physdev_op (PHYSDEVOP_IRQ_UNMASK_NOTIFY) naturally as
replace of IOSAPIC EOI.
Signed-off-by Kevin Tian <kevin.tian@intel.com>
of chipset IO-APICs to Xen. If REGSEL is bad (some old SiS
chipsets) then we have a slower read-modify-write routine.
Loosely based on an original patch from Jan Beulich.
Signed-off-by: Keir Fraser <keir@xensource.com>
issues needed to be resolved by executing certain code early/later
Restore the physical to machine array such that balloon-allocated
pages can be deallocated.
Signed-off-by: Stefan Berger <stefanb@us.ibm.com>
having the potential of missing synchronization there,
as I suspect exists in native Linux) is not needed with the hypercall
approach. In the hypervisor, the patch adds the
needed synchronization.
Signed-off-by: Jan Beulich <jbeulich@novell.com>
