KVM: PPC: Book3S HV: Get rid of vcore nap_count and n_woken

We can tell when a secondary thread has finished running a guest by
the fact that it clears its kvm_hstate.kvm_vcpu pointer, so there
is no real need for the nap_count field in the kvmppc_vcore struct.
This changes kvmppc_wait_for_nap to poll the kvm_hstate.kvm_vcpu
pointers of the secondary threads rather than polling vc->nap_count.
Besides reducing the size of the kvmppc_vcore struct by 8 bytes,
this also means that we can tell which secondary threads have got
stuck and thus print a more informative error message.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

4 files changed, 34 insertions, 35 deletions

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 83c4425..1517faa 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -272,8 +272,6 @@ struct kvmppc_vcore {
 	int n_runnable;
 	int num_threads;
 	int entry_exit_count;
-	int n_woken;
-	int nap_count;
 	int napping_threads;
 	int first_vcpuid;
 	u16 pcpu;
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 92ec3fc..8aa8246 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -563,7 +563,6 @@ int main(void)
 	DEFINE(VCPU_WORT, offsetof(struct kvm_vcpu, arch.wort));
 	DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1));
 	DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count));
-	DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count));
 	DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
 	DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
 	DEFINE(VCORE_KVM, offsetof(struct kvmppc_vcore, kvm));
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index fb4f166..7c1335d 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1729,8 +1729,10 @@ static int kvmppc_grab_hwthread(int cpu)
 	tpaca = &paca[cpu];
 
 	/* Ensure the thread won't go into the kernel if it wakes */
-	tpaca->kvm_hstate.hwthread_req = 1;
 	tpaca->kvm_hstate.kvm_vcpu = NULL;
+	tpaca->kvm_hstate.napping = 0;
+	smp_wmb();
+	tpaca->kvm_hstate.hwthread_req = 1;
 
 	/*
 	 * If the thread is already executing in the kernel (e.g. handling
@@ -1773,35 +1775,43 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu)
 	}
 	cpu = vc->pcpu + vcpu->arch.ptid;
 	tpaca = &paca[cpu];
-	tpaca->kvm_hstate.kvm_vcpu = vcpu;
 	tpaca->kvm_hstate.kvm_vcore = vc;
 	tpaca->kvm_hstate.ptid = vcpu->arch.ptid;
 	vcpu->cpu = vc->pcpu;
+	/* Order stores to hstate.kvm_vcore etc. before store to kvm_vcpu */
 	smp_wmb();
+	tpaca->kvm_hstate.kvm_vcpu = vcpu;
 #if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
-	if (cpu != smp_processor_id()) {
+	if (cpu != smp_processor_id())
 		xics_wake_cpu(cpu);
-		if (vcpu->arch.ptid)
-			++vc->n_woken;
-	}
 #endif
 }
 
-static void kvmppc_wait_for_nap(struct kvmppc_vcore *vc)
+static void kvmppc_wait_for_nap(void)
 {
-	int i;
+	int cpu = smp_processor_id();
+	int i, loops;
 
-	HMT_low();
-	i = 0;
-	while (vc->nap_count < vc->n_woken) {
-		if (++i >= 1000000) {
-			pr_err("kvmppc_wait_for_nap timeout %d %d\n",
-			       vc->nap_count, vc->n_woken);
-			break;
+	for (loops = 0; loops < 1000000; ++loops) {
+		/*
+		 * Check if all threads are finished.
+		 * We set the vcpu pointer when starting a thread
+		 * and the thread clears it when finished, so we look
+		 * for any threads that still have a non-NULL vcpu ptr.
+		 */
+		for (i = 1; i < threads_per_subcore; ++i)
+			if (paca[cpu + i].kvm_hstate.kvm_vcpu)
+				break;
+		if (i == threads_per_subcore) {
+			HMT_medium();
+			return;
 		}
-		cpu_relax();
+		HMT_low();
 	}
 	HMT_medium();
+	for (i = 1; i < threads_per_subcore; ++i)
+		if (paca[cpu + i].kvm_hstate.kvm_vcpu)
+			pr_err("KVM: CPU %d seems to be stuck\n", cpu + i);
 }
 
 /*
@@ -1942,8 +1952,6 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 	/*
 	 * Initialize *vc.
 	 */
-	vc->n_woken = 0;
-	vc->nap_count = 0;
 	vc->entry_exit_count = 0;
 	vc->preempt_tb = TB_NIL;
 	vc->in_guest = 0;
@@ -2002,8 +2010,7 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
 		vcpu->cpu = -1;
 	/* wait for secondary threads to finish writing their state to memory */
-	if (vc->nap_count < vc->n_woken)
-		kvmppc_wait_for_nap(vc);
+	kvmppc_wait_for_nap();
 	for (i = 0; i < threads_per_subcore; ++i)
 		kvmppc_release_hwthread(vc->pcpu + i);
 	/* prevent other vcpu threads from doing kvmppc_start_thread() now */
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index f8267e5..6716db3 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -292,26 +292,21 @@ kvm_secondary_got_guest:
 	ld	r6, PACA_DSCR(r13)
 	std	r6, HSTATE_DSCR(r13)
 
+	/* Order load of vcore, ptid etc. after load of vcpu */
+	lwsync
 	bl	kvmppc_hv_entry
 
 	/* Back from the guest, go back to nap */
 	/* Clear our vcpu pointer so we don't come back in early */
 	li	r0, 0
-	std	r0, HSTATE_KVM_VCPU(r13)
 	/*
-	 * Make sure we clear HSTATE_KVM_VCPU(r13) before incrementing
-	 * the nap_count, because once the increment to nap_count is
-	 * visible we could be given another vcpu.
+	 * Once we clear HSTATE_KVM_VCPU(r13), the code in
+	 * kvmppc_run_core() is going to assume that all our vcpu
+	 * state is visible in memory.  This lwsync makes sure
+	 * that that is true.
 	 */
 	lwsync
-
-	/* increment the nap count and then go to nap mode */
-	ld	r4, HSTATE_KVM_VCORE(r13)
-	addi	r4, r4, VCORE_NAP_COUNT
-51:	lwarx	r3, 0, r4
-	addi	r3, r3, 1
-	stwcx.	r3, 0, r4
-	bne	51b
+	std	r0, HSTATE_KVM_VCPU(r13)
 
 /*
  * At this point we have finished executing in the guest.