From: Wanpeng Li <wanpen...@tencent.com>

We should execute wbinvd on all dirty pCPUs when guest wbinvd exits 
to maintain datat consistency in order to deal with noncoherent DMA.
smp_call_function_many() does not execute the provided function on 
the local core, this patch replaces it by on_each_cpu_mask().

Reported-by: Nadav Amit <na...@vmware.com>
Cc: Nadav Amit <na...@vmware.com>
Signed-off-by: Wanpeng Li <wanpen...@tencent.com>
---
 arch/x86/kvm/x86.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 012d5df..aa6d667 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6638,7 +6638,7 @@ static int kvm_emulate_wbinvd_noskip(struct kvm_vcpu 
*vcpu)
                int cpu = get_cpu();
 
                cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask);
-               smp_call_function_many(vcpu->arch.wbinvd_dirty_mask,
+               on_each_cpu_mask(vcpu->arch.wbinvd_dirty_mask,
                                wbinvd_ipi, NULL, 1);
                put_cpu();
                cpumask_clear(vcpu->arch.wbinvd_dirty_mask);
-- 
2.7.4

Reply via email to