Le Mardi 13 Juin 2006 22:11, Magenheimer, Dan (HP Labs Fort Collins) a écrit :
After reading some Xen/ia64 source, I think we'd better not
to use vpsr.ic for
fast hypercall: it has some interractions with vpsr.ic flag!
I'd vote for creating a new paravirtualized register: xen_break (or
Le Mardi 13 Juin 2006 21:49, Magenheimer, Dan (HP Labs Fort Collins) a écrit :
The reason that there are two groups of privileged registers,
one in privregs (directly accessible by the guest) and one
in arch_vcpu (not directly accesible) is that arch_vcpu is
for registers that are not
Le Mercredi 14 Juin 2006 05:02, Isaku Yamahata a écrit :
On Tue, Jun 13, 2006 at 01:11:04PM -0700, Magenheimer, Dan (HP Labs Fort
Collins) wrote:
There are two purposes of paravirtualization: one is correctness
and the other is performance. If fully virtualized vDSO
works properly and
Hi,
This patch fixes the following warnings in mm.c.
mm.c:38: warning: implicit declaration of function `alloc_domain'
mm.c:38: warning: assignment makes pointer from integer without a cast
mm.c:46: warning: assignment makes pointer from integer without a cast
Kouya
Signed-off-by: Kouya
Le Mercredi 14 Juin 2006 07:58, Isaku Yamahata a écrit :
Hello.
[...]
- races between global tlb purge and tlb insert
This is a race between reading/writing vcpu-arch.{d, i}tlb or VHPT
entry. When a vcpu is about to insert tlb, another vcpu may purge tlb
cache globally. Inserting tlb
Le Mercredi 14 Juin 2006 10:30, Tristan Gingold a écrit :
Le Mercredi 14 Juin 2006 07:58, Isaku Yamahata a écrit :
Hello.
[...]
- races between global tlb purge and tlb insert
This is a race between reading/writing vcpu-arch.{d, i}tlb or VHPT
entry. When a vcpu is about to insert
Le Mercredi 14 Juin 2006 10:57, Isaku Yamahata a écrit :
On Wed, Jun 14, 2006 at 10:33:10AM +0200, Tristan Gingold wrote:
Le Mercredi 14 Juin 2006 10:30, Tristan Gingold a écrit :
Le Mercredi 14 Juin 2006 07:58, Isaku Yamahata a écrit :
- races between global tlb purge and tlb insert
Hi,
this patch fixes a few issue, so that make debug=y works (in Xen).
I think it is expected by Fedora.
Tested by booting dom0 (debug=y).
Tested by compiling without debug=y.
Tristan.
# HG changeset patch
# User [EMAIL PROTECTED]
# Node ID 9b33be2499b6b81729021b7162f294e5cc59d877
# Parent
Previously, on SMP VTI-domain, Guest OS was responsible for syncing itc by
calling
Ia64_sync_itc, but the round trip may be very large on VTI domain, that may
cause guest itcs are not synced well and cause guest wall clock is not accurate.
This patch intends to fix this issue, when guest wants
Hi,
because the guest may modify interrupt_mask_addr and Xen runs at PL0, Xen
should not use this pointer.
This patch fixes a security issue and is a step toward shared_info remapping.
Tested by booting dom0+domU.
Tristan.
# HG changeset patch
# User [EMAIL PROTECTED]
# Node ID
Hi
previously vpsr.pp was in tmp[8]. This creates a new field in struct
mapped_regs (without changing the layout).
Tested by booting dom0.
Tristan.
# HG changeset patch
# User [EMAIL PROTECTED]
# Node ID 0a081a42e2b71fee6dbcde871adf6fa3b6928396
# Parent
If the guest could randomly (maliciously or accidentally)
change iva, Xen should re-validate it before using it (e.g.
to ensure that it is not in Xen address space, to ensure
it is not an I/O address etc.)
As you noticed, these checks are not performed.
Xen address space is protected
I have a question on priv_handle_op().
I changed the function so that xen/ia64 reflects itlb miss
to a domain
when xen/ia64 fails to read a bundle.
Xen/ia64 reflected dtlb miss before my change.
Is it correct to reflect dtlb miss?
No this was just a hack that worked. It does need
I am currently running change-set 10240, the first one that I succeeded to
configure networking. I am experiencing some instability, with an average
up-time of 2 or 3 days --- failures are intermittent, sometimes the SCSI
complains about losing connection with the disks, sometimes it don´t, but in
Hi, Alex
Thank you for your comments.
There's quite a bit changed in this patch that doesn't seem to be
covered by #ifdef XEN. Could you look into adding those in? Thanks,
I'm sorry.
I forgot adding #ifdef XEN when we change linx-xen/ for XEN.
I'll add #ifdef XEN.
Best Regards,
Akio
On Thu, 2006-06-15 at 06:36 +0900, Akio Takebe wrote:
Hi, Alex
I forgot README.origin update, I'm sorry.
The first I made a small patch with cutpaste without ifdef.
But I remade a big patch with ifdef, because I think we may leverage the
original mac code. I don't know this leverage,
Isaku-san,
Would you object to the attached patch to clean up some of the
assign domain page ... already mapped! printks in mm.c? At
this stage, these don't seem necessary anymore, but I wanted to
make sure I wasn't stepping on something you had planned. If
you think these are okay, I'll ask
Hi Al.
On Wed, Jun 14, 2006 at 05:15:29PM -0600, Al Stone wrote:
Would you object to the attached patch to clean up some of the
assign domain page ... already mapped! printks in mm.c? At
this stage, these don't seem necessary anymore, but I wanted to
make sure I wasn't stepping on something
1 / 7
# HG changeset patch
# User [EMAIL PROTECTED]
# Node ID ad418fdb1981be2108d84bafbd294a9db9899396
# Parent d33add81096b057f98fa740ab88d6c17426f8d68
mpt_table is accessed concurrently by cpus, so it needs volatile qualifier
PATCHNAME: volatile_mpt_table
Signed-off-by: Isaku Yamahata
3 / 7
# HG changeset patch
# User [EMAIL PROTECTED]
# Node ID 30f4090206f0b135880319edb71d50ee023f33d0
# Parent 03b29286001dea87284cc401492a799e7e654a0f
guest_physmap_remove_page() should check mfn.
PATCHNAME: guest_physmap_remove_page_check_mfn
Signed-off-by: Isaku Yamahata [EMAIL PROTECTED]
2 / 7
# HG changeset patch
# User [EMAIL PROTECTED]
# Node ID 03b29286001dea87284cc401492a799e7e654a0f
# Parent ad418fdb1981be2108d84bafbd294a9db9899396
add volatile pte entry of the p2m table.
Since p2m table are shared by cpu. volatile is needed.
fix the races in pte access of
5 / 7
# HG changeset patch
# User [EMAIL PROTECTED]
# Node ID 4837d282c2c82370944307b0989c03f6bfa2df78
# Parent e5dd90005dd074a3d317d18499f32a35b477b793
get_page() when access a page of domain.
pages can be removed from domain and freed by another cpu.
To prevent accessing freeing page, use
6 / 7
# HG changeset patch
# User [EMAIL PROTECTED]
# Node ID 658419c4e60f399bf0a97f9c81b9e3bd6494040e
# Parent 4837d282c2c82370944307b0989c03f6bfa2df78
remove vtlb_lock.
As Tristan pointed out, vtlb_lock is unnecesary.
PATCHNAME: remove_vtlb_lock
Signed-off-by: Isaku Yamahata [EMAIL
23 matches
Mail list logo