Remove memory and cpu parameters from DOM0_CREATEDOMAIN, and remove
DOM0_SETINITIALMEM. You can get the same effect via PINCPU,
SETMAXMEM, and do_mem_op(increase_reservation).
Signed-off-by: Keir Fraser <keir@xensource.com>
Now that the shadow code is squashing the global bit in PTEs,
it's OK to re-enable the PGE capability flag for vmx domains.
Signed-off-by: michael.fetterman@cl.cam.ac.uk
Patch to enable the destruction of domains which have shadow mode enabled.
Also fixes some shadow mode ref counting bugs, and one bug in check_pte()
recently introduced by the changes in page table accessor types/macros.
Signed-off-by: michael.fetterman@cl.cam.ac.uk
Enable the ProcFS part of grant table only when CONFIG_PROC_FS is defined.
This is also necessary for separate driver domains that contain block
device backend driver and operate in kernel-mode only (thus ProcFS turned off).
Signed-off-by: Bin Ren <bin.ren@cl.cam.ac.uk>
Truly round off the div result to get right PIT frequency for guest.
Otherwise, the guest's idea of time drifts away from that of the host.
Signed-off-by: Edwin Zhai <edwin.zhai@intel.com>
Signed-off-by: Arun Sharma <arun.sharma@intel.com>
Signed-off-by: ian@xensource.com
__vmxon() is called twice for the boot cpu, because identify_cpu() is called
twice. This patch ensures that identify_cpu() and hence __vmxon() is called
exactly once for the boot CPU on SMP.
Signed-off-by: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Signed-off-by: Arun Sharma <arun.sharma@intel.com>
Signed-off-by: ian@xensource.com
[PATCH] VMX world switch
The attached code implements a VMX world switch to vmxassist (a small assist
module residing in a VMX enabled partition where it is responsible for
emulating real mode) whever CR0.PE is disabled.
The patch temporarily disables the PGE feature flag in cpuid as it is
currently broken (try running an unmodified 2.6 kernel that sets PGE in
mm/init.c/paging_init()).
The patch adds consistency checks before setting the ARCH_VMX_IO_WAIT state
to detect race conditions on SMP systems.
Signed-Off-By: Leendert van Doorn <leendert@watson.ibm.com>
Signed-off-by: ian@xensource.com
grant-tables.txt:
fix to error check condition after map
blkback.c:
bug fix to grant table code in block backend
Kconfig:
amend config entry for XEN_BLKDEV_GRANT
Make the fallback memset/memcpy/memmove have a concrete in-place
implementation, or we end up with a recursive dependency when building
for x86/64.
Signed-off-by: Keir Fraser <keir@xensource.com>
Here is a patch to get Xen running on a 32-way Unisys ES7000 system.
Please note that this patch alone is not sufficient to do this. You will
also need the clustered APIC patch that I will be submitting soon. But
since this patch was to a general area in Xen I decided to submit it
separately. I think this patch will be required to get Xen running on
any system that has more than 16 CPUs.
Signed-off-by: Aravindh Puthiyaparambil <aravindh.puthiyaparambil@unisys.com>
Cleanup page table handling. Add macros to access page table
entries, fixup plenty of places in the code to use the page
table types instead of "unsigned long".
Signed-off-by: Gerd Knorr <kraxel@bytesex.org>
Signed-off-by: michael.fetterman@cl.cam.ac.uk
[PATCH] x86-64-enable-vmx.patch
Enable CONFIG_VMX for x86_64.
- Provides vmexit/entry handling code based on the x86_32 code
- Fix find_highest_vector for 64 bit (Benjamin Liu)
Signed-off-by: Arun Sharma <arun.sharma@intel.com>
[PATCH] [PATCH 2/2] x86_64 whitespace cleanup in Linux sparse
Eliminate extraneous whitespace changes in x86_64 portion of Linux
sparse patch.
Signed-off-by: Chris Wright <chrisw@osdl.org>
[PATCH] [PATCH 1/2] i386 whitespace cleanup in Linux sparse tree
Eliminate extraneous whitespace changes in i386 portion of Linux
sparse patch.
Signed-off-by: Chris Wright <chrisw@osdl.org>
Merge freefall.cl.cam.ac.uk:/auto/groups/xeno-xenod/BK/xen-unstable.bk
into freefall.cl.cam.ac.uk:/auto/groups/xeno/users/iap10/xeno-clone/xen-unstable.bk
