Merge tag 'powerpc-6.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Rework kfence support for the HPT MMU to work on systems with >= 16TB
   of RAM.

 - Remove the powerpc "maple" platform, used by the "Yellow Dog
   Powerstation".

 - Add support for DYNAMIC_FTRACE_WITH_CALL_OPS,
   DYNAMIC_FTRACE_WITH_DIRECT_CALLS & BPF Trampolines.

 - Add support for running KVM nested guests on Power11.

 - Other small features, cleanups and fixes.

Thanks to Amit Machhiwal, Arnd Bergmann, Christophe Leroy, Costa
Shulyupin, David Hunter, David Wang, Disha Goel, Gautam Menghani, Geert
Uytterhoeven, Hari Bathini, Julia Lawall, Kajol Jain, Keith Packard,
Lukas Bulwahn, Madhavan Srinivasan, Markus Elfring, Michal Suchanek,
Ming Lei, Mukesh Kumar Chaurasiya, Nathan Chancellor, Naveen N Rao,
Nicholas Piggin, Nysal Jan K.A, Paulo Miguel Almeida, Pavithra Prakash,
Ritesh Harjani (IBM), Rob Herring (Arm), Sachin P Bappalige, Shen
Lichuan, Simon Horman, Sourabh Jain, Thomas Weißschuh, Thorsten Blum,
Thorsten Leemhuis, Venkat Rao Bagalkote, Zhang Zekun, and zhang jiao.

* tag 'powerpc-6.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (89 commits)
  EDAC/powerpc: Remove PPC_MAPLE drivers
  powerpc/perf: Add per-task/process monitoring to vpa_pmu driver
  powerpc/kvm: Add vpa latency counters to kvm_vcpu_arch
  docs: ABI: sysfs-bus-event_source-devices-vpa-pmu: Document sysfs event format entries for vpa_pmu
  powerpc/perf: Add perf interface to expose vpa counters
  MAINTAINERS: powerpc: Mark Maddy as "M"
  powerpc/Makefile: Allow overriding CPP
  powerpc-km82xx.c: replace of_node_put() with __free
  ps3: Correct some typos in comments
  powerpc/kexec: Fix return of uninitialized variable
  macintosh: Use common error handling code in via_pmu_led_init()
  powerpc/powermac: Use of_property_match_string() in pmac_has_backlight_type()
  powerpc: remove dead config options for MPC85xx platform support
  powerpc/xive: Use cpumask_intersects()
  selftests/powerpc: Remove the path after initialization.
  powerpc/xmon: symbol lookup length fixed
  powerpc/ep8248e: Use %pa to format resource_size_t
  powerpc/ps3: Reorganize kerneldoc parameter names
  KVM: PPC: Book3S HV: Fix kmv -> kvm typo
  powerpc/sstep: make emulate_vsx_load and emulate_vsx_store static
  ...

5 files changed, 102 insertions, 47 deletions

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index ad8dc4ccdaab..25429905ae90 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -400,7 +400,10 @@ static inline unsigned long map_pcr_to_cap(unsigned long pcr)
 		cap = H_GUEST_CAP_POWER9;
 		break;
 	case PCR_ARCH_31:
-		cap = H_GUEST_CAP_POWER10;
+		if (cpu_has_feature(CPU_FTR_P11_PVR))
+			cap = H_GUEST_CAP_POWER11;
+		else
+			cap = H_GUEST_CAP_POWER10;
 		break;
 	default:
 		break;
@@ -415,7 +418,7 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 
 	/* We can (emulate) our own architecture version and anything older */
-	if (cpu_has_feature(CPU_FTR_ARCH_31))
+	if (cpu_has_feature(CPU_FTR_P11_PVR) || cpu_has_feature(CPU_FTR_ARCH_31))
 		host_pcr_bit = PCR_ARCH_31;
 	else if (cpu_has_feature(CPU_FTR_ARCH_300))
 		host_pcr_bit = PCR_ARCH_300;
@@ -2060,36 +2063,9 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
 		fallthrough; /* go to facility unavailable handler */
 #endif
 
-	case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: {
-		u64 cause = vcpu->arch.hfscr >> 56;
-
-		/*
-		 * Only pass HFU interrupts to the L1 if the facility is
-		 * permitted but disabled by the L1's HFSCR, otherwise
-		 * the interrupt does not make sense to the L1 so turn
-		 * it into a HEAI.
-		 */
-		if (!(vcpu->arch.hfscr_permitted & (1UL << cause)) ||
-				(vcpu->arch.nested_hfscr & (1UL << cause))) {
-			ppc_inst_t pinst;
-			vcpu->arch.trap = BOOK3S_INTERRUPT_H_EMUL_ASSIST;
-
-			/*
-			 * If the fetch failed, return to guest and
-			 * try executing it again.
-			 */
-			r = kvmppc_get_last_inst(vcpu, INST_GENERIC, &pinst);
-			vcpu->arch.emul_inst = ppc_inst_val(pinst);
-			if (r != EMULATE_DONE)
-				r = RESUME_GUEST;
-			else
-				r = RESUME_HOST;
-		} else {
-			r = RESUME_HOST;
-		}
-
+	case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
+		r = RESUME_HOST;
 		break;
-	}
 
 	case BOOK3S_INTERRUPT_HV_RM_HARD:
 		vcpu->arch.trap = 0;
@@ -4153,8 +4129,9 @@ void kvmhv_set_l2_counters_status(int cpu, bool status)
 	else
 		lppaca_of(cpu).l2_counters_enable = 0;
 }
+EXPORT_SYMBOL(kvmhv_set_l2_counters_status);
 
-int kmvhv_counters_tracepoint_regfunc(void)
+int kvmhv_counters_tracepoint_regfunc(void)
 {
 	int cpu;
 
@@ -4164,7 +4141,7 @@ int kmvhv_counters_tracepoint_regfunc(void)
 	return 0;
 }
 
-void kmvhv_counters_tracepoint_unregfunc(void)
+void kvmhv_counters_tracepoint_unregfunc(void)
 {
 	int cpu;
 
@@ -4190,7 +4167,73 @@ static void do_trace_nested_cs_time(struct kvm_vcpu *vcpu)
 	*l1_to_l2_cs_ptr = l1_to_l2_ns;
 	*l2_to_l1_cs_ptr = l2_to_l1_ns;
 	*l2_runtime_agg_ptr = l2_runtime_ns;
+	vcpu->arch.l1_to_l2_cs = l1_to_l2_ns;
+	vcpu->arch.l2_to_l1_cs = l2_to_l1_ns;
+	vcpu->arch.l2_runtime_agg = l2_runtime_ns;
+}
+
+u64 kvmhv_get_l1_to_l2_cs_time(void)
+{
+	return tb_to_ns(be64_to_cpu(get_lppaca()->l1_to_l2_cs_tb));
+}
+EXPORT_SYMBOL(kvmhv_get_l1_to_l2_cs_time);
+
+u64 kvmhv_get_l2_to_l1_cs_time(void)
+{
+	return tb_to_ns(be64_to_cpu(get_lppaca()->l2_to_l1_cs_tb));
+}
+EXPORT_SYMBOL(kvmhv_get_l2_to_l1_cs_time);
+
+u64 kvmhv_get_l2_runtime_agg(void)
+{
+	return tb_to_ns(be64_to_cpu(get_lppaca()->l2_runtime_tb));
+}
+EXPORT_SYMBOL(kvmhv_get_l2_runtime_agg);
+
+u64 kvmhv_get_l1_to_l2_cs_time_vcpu(void)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vcpu_arch *arch;
+
+	vcpu = local_paca->kvm_hstate.kvm_vcpu;
+	if (vcpu) {
+		arch = &vcpu->arch;
+		return arch->l1_to_l2_cs;
+	} else {
+		return 0;
+	}
 }
+EXPORT_SYMBOL(kvmhv_get_l1_to_l2_cs_time_vcpu);
+
+u64 kvmhv_get_l2_to_l1_cs_time_vcpu(void)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vcpu_arch *arch;
+
+	vcpu = local_paca->kvm_hstate.kvm_vcpu;
+	if (vcpu) {
+		arch = &vcpu->arch;
+		return arch->l2_to_l1_cs;
+	} else {
+		return 0;
+	}
+}
+EXPORT_SYMBOL(kvmhv_get_l2_to_l1_cs_time_vcpu);
+
+u64 kvmhv_get_l2_runtime_agg_vcpu(void)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vcpu_arch *arch;
+
+	vcpu = local_paca->kvm_hstate.kvm_vcpu;
+	if (vcpu) {
+		arch = &vcpu->arch;
+		return arch->l2_runtime_agg;
+	} else {
+		return 0;
+	}
+}
+EXPORT_SYMBOL(kvmhv_get_l2_runtime_agg_vcpu);
 
 #else
 int kvmhv_get_l2_counters_status(void)
@@ -4310,6 +4353,15 @@ static int kvmhv_vcpu_entry_p9_nested(struct kvm_vcpu *vcpu, u64 time_limit, uns
 	hvregs.hdec_expiry = time_limit;
 
 	/*
+	 * hvregs has the doorbell status, so zero it here which
+	 * enables us to receive doorbells when H_ENTER_NESTED is
+	 * in progress for this vCPU
+	 */
+
+	if (vcpu->arch.doorbell_request)
+		vcpu->arch.doorbell_request = 0;
+
+	/*
 	 * When setting DEC, we must always deal with irq_work_raise
 	 * via NMI vs setting DEC. The problem occurs right as we
 	 * switch into guest mode if a NMI hits and sets pending work
@@ -4912,7 +4964,6 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 			lpcr &= ~LPCR_MER;
 		}
 	} else if (vcpu->arch.pending_exceptions ||
-		   vcpu->arch.doorbell_request ||
 		   xive_interrupt_pending(vcpu)) {
 		vcpu->arch.ret = RESUME_HOST;
 		goto out;
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 05f5220960c6..ef97f58d0d97 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -32,7 +32,7 @@ void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 
 	hr->pcr = vc->pcr | PCR_MASK;
-	hr->dpdes = vc->dpdes;
+	hr->dpdes = vcpu->arch.doorbell_request;
 	hr->hfscr = vcpu->arch.hfscr;
 	hr->tb_offset = vc->tb_offset;
 	hr->dawr0 = vcpu->arch.dawr0;
@@ -105,7 +105,7 @@ static void save_hv_return_state(struct kvm_vcpu *vcpu,
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 
-	hr->dpdes = vc->dpdes;
+	hr->dpdes = vcpu->arch.doorbell_request;
 	hr->purr = vcpu->arch.purr;
 	hr->spurr = vcpu->arch.spurr;
 	hr->ic = vcpu->arch.ic;
@@ -143,7 +143,7 @@ static void restore_hv_regs(struct kvm_vcpu *vcpu, const struct hv_guest_state *
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 
 	vc->pcr = hr->pcr | PCR_MASK;
-	vc->dpdes = hr->dpdes;
+	vcpu->arch.doorbell_request = hr->dpdes;
 	vcpu->arch.hfscr = hr->hfscr;
 	vcpu->arch.dawr0 = hr->dawr0;
 	vcpu->arch.dawrx0 = hr->dawrx0;
@@ -170,7 +170,13 @@ void kvmhv_restore_hv_return_state(struct kvm_vcpu *vcpu,
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 
-	vc->dpdes = hr->dpdes;
+	/*
+	 * This L2 vCPU might have received a doorbell while H_ENTER_NESTED was being handled.
+	 * Make sure we preserve the doorbell if it was either:
+	 *   a) Sent after H_ENTER_NESTED was called on this vCPU (arch.doorbell_request would be 1)
+	 *   b) Doorbell was not handled and L2 exited for some other reason (hr->dpdes would be 1)
+	 */
+	vcpu->arch.doorbell_request = vcpu->arch.doorbell_request | hr->dpdes;
 	vcpu->arch.hfscr = hr->hfscr;
 	vcpu->arch.purr = hr->purr;
 	vcpu->arch.spurr = hr->spurr;
@@ -445,6 +451,8 @@ long kvmhv_nested_init(void)
 	if (rc == H_SUCCESS) {
 		unsigned long capabilities = 0;
 
+		if (cpu_has_feature(CPU_FTR_P11_PVR))
+			capabilities |= H_GUEST_CAP_POWER11;
 		if (cpu_has_feature(CPU_FTR_ARCH_31))
 			capabilities |= H_GUEST_CAP_POWER10;
 		if (cpu_has_feature(CPU_FTR_ARCH_300))
diff --git a/arch/powerpc/kvm/book3s_hv_nestedv2.c b/arch/powerpc/kvm/book3s_hv_nestedv2.c
index eeecea8f202b..e5c7ce1fb761 100644
--- a/arch/powerpc/kvm/book3s_hv_nestedv2.c
+++ b/arch/powerpc/kvm/book3s_hv_nestedv2.c
@@ -370,7 +370,9 @@ static int gs_msg_ops_vcpu_fill_info(struct kvmppc_gs_buff *gsb,
 			 * default to L1's PVR.
 			 */
 			if (!vcpu->arch.vcore->arch_compat) {
-				if (cpu_has_feature(CPU_FTR_ARCH_31))
+				if (cpu_has_feature(CPU_FTR_P11_PVR))
+					arch_compat = PVR_ARCH_31_P11;
+				else if (cpu_has_feature(CPU_FTR_ARCH_31))
 					arch_compat = PVR_ARCH_31;
 				else if (cpu_has_feature(CPU_FTR_ARCH_300))
 					arch_compat = PVR_ARCH_300;
diff --git a/arch/powerpc/kvm/book3s_mmu_hpte.c b/arch/powerpc/kvm/book3s_mmu_hpte.c
index ce79ac33e8d3..d904e13e069b 100644
--- a/arch/powerpc/kvm/book3s_mmu_hpte.c
+++ b/arch/powerpc/kvm/book3s_mmu_hpte.c
@@ -92,12 +92,6 @@ void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 	spin_unlock(&vcpu3s->mmu_lock);
 }
 
-static void free_pte_rcu(struct rcu_head *head)
-{
-	struct hpte_cache *pte = container_of(head, struct hpte_cache, rcu_head);
-	kmem_cache_free(hpte_cache, pte);
-}
-
 static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 {
 	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
@@ -126,7 +120,7 @@ static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 
 	spin_unlock(&vcpu3s->mmu_lock);
 
-	call_rcu(&pte->rcu_head, free_pte_rcu);
+	kfree_rcu(pte, rcu_head);
 }
 
 static void kvmppc_mmu_pte_flush_all(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/trace_hv.h b/arch/powerpc/kvm/trace_hv.h
index 77ebc724e6cd..35fccaa575cc 100644
--- a/arch/powerpc/kvm/trace_hv.h
+++ b/arch/powerpc/kvm/trace_hv.h
@@ -538,7 +538,7 @@ TRACE_EVENT_FN_COND(kvmppc_vcpu_stats,
 	TP_printk("VCPU %d: l1_to_l2_cs_time=%llu ns l2_to_l1_cs_time=%llu ns l2_runtime=%llu ns",
 		__entry->vcpu_id,  __entry->l1_to_l2_cs,
 		__entry->l2_to_l1_cs, __entry->l2_runtime),
-	kmvhv_counters_tracepoint_regfunc, kmvhv_counters_tracepoint_unregfunc
+	kvmhv_counters_tracepoint_regfunc, kvmhv_counters_tracepoint_unregfunc
 );
 #endif
 #endif /* _TRACE_KVM_HV_H */