Quoting Xu, Anthony [EMAIL PROTECTED]:
Hi Tristan,
Yes the mf is necessary,
Hardware can speculatively load vhpt entries from VTHP page.
We had spent a lot of effort to identity this issue.
I don't fully understand your explanation. Memory ordering issues are only
SMP issues, not
VHPT speculative load happens in the same time when tlb_miss handler is
executing.
180 ld8 r25 = [r17]
181 ld8 r27 = [r18]
182 ld8 r29 = [r28]
183 dep r22 = -1,r24,63,1//set ti=1
184 ;;
185 st8 [r16] = r29, VLE_ITIR_OFFSET - VLE_TITAG_OFFSET
I get the wrong re-mapping from windbg(I didn't
see it from driver's debug output before). Your patch resolves
this issue. With it, windows map card's MMIO begin at
0xC400 and I don't see the graphic issue that you
mentioned.
Good good study,day day up ! ^_^
-Wing(zhang xin)
OTC,Intel
Hi,
I thik the following panic_domain in guest_write_eoi() is not necessary,
because ia64_eoi() in linux is called without checikng in-service.
515 void guest_write_eoi(VCPU *vcpu)
516 {
517 int vec;
518
519 vec = highest_inservice_irq(vcpu);
520 if ( vec == NULL_VECTOR )
On Tue, 2007-10-09 at 23:07 +0900, Akio Takebe wrote:
Hi,
I thik the following panic_domain in guest_write_eoi() is not necessary,
because ia64_eoi() in linux is called without checikng in-service.
515 void guest_write_eoi(VCPU *vcpu)
516 {
517 int vec;
518
519 vec =
On Tue, 2007-10-09 at 18:55 +0800, Zhang, Xing Z wrote:
I get the wrong re-mapping from windbg(I didn't
see it from driver's debug output before). Your patch resolves
this issue. With it, windows map card's MMIO begin at
0xC400 and I don't see the graphic issue that you
mentioned.
On Tue, Oct 09, 2007 at 04:23:20PM +0800, Xu, Anthony wrote:
VHPT speculative load happens in the same time when tlb_miss handler is
executing.
[...]
Mf is to make sure that before modifying vhpt entry, vhpt entry must be
disabled, otherwise VHPT walker hardware may see enabled half
Hi Tristan,
You are right, mf can be deleted.
Thanks
Anthony
From: Tristan Gingold [mailto:[EMAIL PROTECTED]
Sent: 2007年10月10日 9:09
To: Xu, Anthony
Cc: [EMAIL PROTECTED]; Xen-ia64-devel
Subject: Re: [Xen-ia64-devel] Question about vmx_ivt.S
On Tue, Oct 09, 2007 at 04:23:20PM +0800, Xu,