On 25/10/17 11:30, Andrew Cooper wrote:
On 25/10/17 00:30, Boris Ostrovsky wrote:
This call was left during PVHv1 removal (commit 33e5c32559e1 ("x86:
remove PVHv1 code")):
- if ( is_pvh_vcpu(sampling) &&
- !(vpmu_mode & XENPMU_MODE_ALL) &&
+ if ( !(vpmu_mode & XENPMU_MODE_ALL) &&
!vpmu->arch_vpmu_ops->do_interrupt(regs) )
return;
As result of this extra call VPMU no longer works for PV guests on Intel
because we effectively lose value of MSR_CORE_PERF_GLOBAL_STATUS.
Signed-off-by: Boris Ostrovsky <boris.ostrov...@oracle.com>
Reviewed-by: Andrew Cooper <andrew.coop...@citrix.com>
---
This should also go into 4.9
Agreed, and therefore makes it a 4.10 candidate at this point.
Release-acked-by: Julien Grall <julien.gr...@linaro.org>
Cheers,
~Andrew
xen/arch/x86/cpu/vpmu.c | 4 ----
1 file changed, 4 deletions(-)
diff --git a/xen/arch/x86/cpu/vpmu.c b/xen/arch/x86/cpu/vpmu.c
index fd2fcac..7baf461 100644
--- a/xen/arch/x86/cpu/vpmu.c
+++ b/xen/arch/x86/cpu/vpmu.c
@@ -227,10 +227,6 @@ void vpmu_do_interrupt(struct cpu_user_regs *regs)
if ( !vpmu->xenpmu_data )
return;
- if ( !(vpmu_mode & XENPMU_MODE_ALL) &&
- !vpmu->arch_vpmu_ops->do_interrupt(regs) )
- return;
-
if ( vpmu_is_set(vpmu, VPMU_CACHED) )
return;
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
--
Julien Grall
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel