[PATCH v3] powerpc: kvm: optimize "sc 1" as fast return

[Liu Ping Fan <kernelfans@gmail.com>]

In some scene, e.g openstack CI, PR guest can trigger "sc 1" frequently,
this patch optimizes the path by directly delivering BOOK3S_INTERRUPT_SYSCALL
to HV guest, so powernv can return to HV guest without heavy exit, i.e,
no need to swap TLB, HTAB,.. etc

Signed-off-by: Liu Ping Fan <pingfank@linux.vnet.ibm.com>
---
v3: add some document
---
 arch/powerpc/kvm/book3s_hv.c            | 10 ++++------
 arch/powerpc/kvm/book3s_hv_rmhandlers.S | 19 ++++++++++++++++++-
 2 files changed, 22 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 62a2b5a..1addb1a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -628,12 +628,10 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		/* hcall - punt to userspace */
 		int i;
 
-		if (vcpu->arch.shregs.msr & MSR_PR) {
-			/* sc 1 from userspace - reflect to guest syscall */
-			kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_SYSCALL);
-			r = RESUME_GUEST;
-			break;
-		}
+		/* hypercall with MSR_PR has already been handled in rmode,
+		 * and never reaches here.
+		 */
+
 		run->papr_hcall.nr = kvmppc_get_gpr(vcpu, 3);
 		for (i = 0; i < 9; ++i)
 			run->papr_hcall.args[i] = kvmppc_get_gpr(vcpu, 4 + i);
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index c71103b..eea7ca7 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -534,6 +534,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 5:	mtspr	SPRN_SRR0, r6
 	mtspr	SPRN_SRR1, r7
 
+/*
+ * Required state:
+ * R4 = vcpu
+ * R10: value for HSRR0
+ * R11: value for HSRR1
+ * R13 = PACA
+ */
 fast_guest_return:
 	li	r0,0
 	stb	r0,VCPU_CEDED(r4)	/* cancel cede */
@@ -1388,7 +1395,8 @@ kvmppc_hisi:
 hcall_try_real_mode:
 	ld	r3,VCPU_GPR(R3)(r9)
 	andi.	r0,r11,MSR_PR
-	bne	guest_exit_cont
+	/* sc 1 from userspace - reflect to guest syscall */
+	bne	sc_1_fast_return
 	clrrdi	r3,r3,2
 	cmpldi	r3,hcall_real_table_end - hcall_real_table
 	bge	guest_exit_cont
@@ -1409,6 +1417,15 @@ hcall_try_real_mode:
 	ld	r11,VCPU_MSR(r4)
 	b	fast_guest_return
 
+sc_1_fast_return:
+	mtspr	SPRN_SRR0,r10
+	mtspr	SPRN_SRR1,r11
+	li	r10, BOOK3S_INTERRUPT_SYSCALL
+	li	r11, (MSR_ME << 1) | 1  /* synthesize MSR_SF | MSR_ME */
+	rotldi	r11, r11, 63
+	mr	r4,r9
+	b	fast_guest_return
+
 	/* We've attempted a real mode hcall, but it's punted it back
 	 * to userspace.  We need to restore some clobbered volatiles
 	 * before resuming the pass-it-to-qemu path */
-- 
1.8.1.4