Patchwork [07/35] KVM: PPC: Preload magic page when in kernel mode

login
register
mail settings
Submitter Alexander Graf
Date Aug. 31, 2010, 2:31 a.m.
Message ID <1283221937-21006-8-git-send-email-agraf@suse.de>
Download mbox | patch
Permalink /patch/63175/
State Not Applicable
Headers show

Comments

Alexander Graf - Aug. 31, 2010, 2:31 a.m.
When the guest jumps into kernel mode and has the magic page mapped, theres a
very high chance that it will also use it. So let's detect that scenario and
map the segment accordingly.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s.c |   10 ++++++++++
 1 files changed, 10 insertions(+), 0 deletions(-)

Patch

diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 37db61d..54ca578 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -145,6 +145,16 @@  void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
 		   (old_msr & (MSR_PR|MSR_IR|MSR_DR))) {
 		kvmppc_mmu_flush_segments(vcpu);
 		kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
+
+		/* Preload magic page segment when in kernel mode */
+		if (!(msr & MSR_PR) && vcpu->arch.magic_page_pa) {
+			struct kvm_vcpu_arch *a = &vcpu->arch;
+
+			if (msr & MSR_DR)
+				kvmppc_mmu_map_segment(vcpu, a->magic_page_ea);
+			else
+				kvmppc_mmu_map_segment(vcpu, a->magic_page_pa);
+		}
 	}
 
 	/* Preload FPU if it's enabled */