Merge branch 'fixes' into topic/ppc-kvm

Merge our fixes branch. In parciular this brings in the KVM TCE handling
fix, which is a prerequisite for a subsequent patch.

arch/powerpc/kernel/time.c

@@ -615,23 +615,22 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
 		return;
 	}
 
-	/* Conditionally hard-enable interrupts. */
-	if (should_hard_irq_enable()) {
-		/*
-		 * Ensure a positive value is written to the decrementer, or
-		 * else some CPUs will continue to take decrementer exceptions.
-		 * When the PPC_WATCHDOG (decrementer based) is configured,
-		 * keep this at most 31 bits, which is about 4 seconds on most
-		 * systems, which gives the watchdog a chance of catching timer
-		 * interrupt hard lockups.
-		 */
-		if (IS_ENABLED(CONFIG_PPC_WATCHDOG))
-			set_dec(0x7fffffff);
-		else
-			set_dec(decrementer_max);
+	/*
+	 * Ensure a positive value is written to the decrementer, or
+	 * else some CPUs will continue to take decrementer exceptions.
+	 * When the PPC_WATCHDOG (decrementer based) is configured,
+	 * keep this at most 31 bits, which is about 4 seconds on most
+	 * systems, which gives the watchdog a chance of catching timer
+	 * interrupt hard lockups.
+	 */
+	if (IS_ENABLED(CONFIG_PPC_WATCHDOG))
+		set_dec(0x7fffffff);
+	else
+		set_dec(decrementer_max);
 
+	/* Conditionally hard-enable interrupts. */
+	if (should_hard_irq_enable())
 		do_hard_irq_enable();
-	}
 
 #if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC)
 	if (atomic_read(&ppc_n_lost_interrupts) != 0)

arch/powerpc/kernel/vdso/gettimeofday.S

@@ -22,12 +22,15 @@
 .macro cvdso_call funct call_time=0
   .cfi_startproc
 	PPC_STLU	r1, -PPC_MIN_STKFRM(r1)
+  .cfi_adjust_cfa_offset PPC_MIN_STKFRM
 	mflr		r0
-  .cfi_register lr, r0
 	PPC_STLU	r1, -PPC_MIN_STKFRM(r1)
+  .cfi_adjust_cfa_offset PPC_MIN_STKFRM
 	PPC_STL		r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
+  .cfi_rel_offset lr, PPC_MIN_STKFRM + PPC_LR_STKOFF
 #ifdef __powerpc64__
 	PPC_STL		r2, PPC_MIN_STKFRM + STK_GOT(r1)
+  .cfi_rel_offset r2, PPC_MIN_STKFRM + STK_GOT
 #endif
 	get_datapage	r5
 	.ifeq	\call_time
@@ -39,13 +42,15 @@
 	PPC_LL		r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
 #ifdef __powerpc64__
 	PPC_LL		r2, PPC_MIN_STKFRM + STK_GOT(r1)
+  .cfi_restore r2
 #endif
 	.ifeq	\call_time
 	cmpwi		r3, 0
 	.endif
 	mtlr		r0
-  .cfi_restore lr
 	addi		r1, r1, 2 * PPC_MIN_STKFRM
+  .cfi_restore lr
+  .cfi_def_cfa_offset 0
 	crclr		so
 	.ifeq	\call_time
 	beqlr+

arch/powerpc/kvm/book3s_32_sr.S

@@ -122,11 +122,27 @@
 
 	/* 0x0 - 0xb */
 
-	/* 'current->mm' needs to be in r4 */
-	tophys(r4, r2)
-	lwz	r4, MM(r4)
-	tophys(r4, r4)
-	/* This only clobbers r0, r3, r4 and r5 */
+	/* switch_mmu_context() needs paging, let's enable it */
+	mfmsr   r9
+	ori     r11, r9, MSR_DR
+	mtmsr   r11
+	sync
+
+	/* switch_mmu_context() clobbers r12, rescue it */
+	SAVE_GPR(12, r1)
+
+	/* Calling switch_mmu_context(<inv>, current->mm, <inv>); */
+	lwz	r4, MM(r2)
 	bl	switch_mmu_context
 
+	/* restore r12 */
+	REST_GPR(12, r1)
+
+	/* Disable paging again */
+	mfmsr   r9
+	li      r6, MSR_DR
+	andc    r9, r9, r6
+	mtmsr	r9
+	sync
+
 .endm

arch/powerpc/kvm/book3s_64_vio.c

@@ -420,13 +420,19 @@ static void kvmppc_tce_put(struct kvmppc_spapr_tce_table *stt,
 	tbl[idx % TCES_PER_PAGE] = tce;
 }
 
-static void kvmppc_clear_tce(struct mm_struct *mm, struct iommu_table *tbl,
-		unsigned long entry)
+static void kvmppc_clear_tce(struct mm_struct *mm, struct kvmppc_spapr_tce_table *stt,
+		struct iommu_table *tbl, unsigned long entry)
 {
-	unsigned long hpa = 0;
-	enum dma_data_direction dir = DMA_NONE;
+	unsigned long i;
+	unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift);
+	unsigned long io_entry = entry << (stt->page_shift - tbl->it_page_shift);
+
+	for (i = 0; i < subpages; ++i) {
+		unsigned long hpa = 0;
+		enum dma_data_direction dir = DMA_NONE;
 
-	iommu_tce_xchg_no_kill(mm, tbl, entry, &hpa, &dir);
+		iommu_tce_xchg_no_kill(mm, tbl, io_entry + i, &hpa, &dir);
+	}
 }
 
 static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm,
@@ -485,6 +491,8 @@ static long kvmppc_tce_iommu_unmap(struct kvm *kvm,
 			break;
 	}
 
+	iommu_tce_kill(tbl, io_entry, subpages);
+
 	return ret;
 }
 
@@ -544,6 +552,8 @@ static long kvmppc_tce_iommu_map(struct kvm *kvm,
 			break;
 	}
 
+	iommu_tce_kill(tbl, io_entry, subpages);
+
 	return ret;
 }
 
@@ -590,10 +600,9 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 			ret = kvmppc_tce_iommu_map(vcpu->kvm, stt, stit->tbl,
 					entry, ua, dir);
 
-		iommu_tce_kill(stit->tbl, entry, 1);
 
 		if (ret != H_SUCCESS) {
-			kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, entry);
+			kvmppc_clear_tce(vcpu->kvm->mm, stt, stit->tbl, entry);
 			goto unlock_exit;
 		}
 	}
@@ -669,13 +678,13 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		 */
 		if (get_user(tce, tces + i)) {
 			ret = H_TOO_HARD;
-			goto invalidate_exit;
+			goto unlock_exit;
 		}
 		tce = be64_to_cpu(tce);
 
 		if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua)) {
 			ret = H_PARAMETER;
-			goto invalidate_exit;
+			goto unlock_exit;
 		}
 
 		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
@@ -684,19 +693,15 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 					iommu_tce_direction(tce));
 
 			if (ret != H_SUCCESS) {
-				kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl,
-						entry);
-				goto invalidate_exit;
+				kvmppc_clear_tce(vcpu->kvm->mm, stt, stit->tbl,
+						 entry + i);
+				goto unlock_exit;
 			}
 		}
 
 		kvmppc_tce_put(stt, entry + i, tce);
 	}
 
-invalidate_exit:
-	list_for_each_entry_lockless(stit, &stt->iommu_tables, next)
-		iommu_tce_kill(stit->tbl, entry, npages);
-
 unlock_exit:
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 
@@ -735,20 +740,16 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
 				continue;
 
 			if (ret == H_TOO_HARD)
-				goto invalidate_exit;
+				return ret;
 
 			WARN_ON_ONCE(1);
-			kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, entry);
+			kvmppc_clear_tce(vcpu->kvm->mm, stt, stit->tbl, entry + i);
 		}
 	}
 
 	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
 		kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
 
-invalidate_exit:
-	list_for_each_entry_lockless(stit, &stt->iommu_tables, next)
-		iommu_tce_kill(stit->tbl, ioba >> stt->page_shift, npages);
-
 	return ret;
 }
 EXPORT_SYMBOL_GPL(kvmppc_h_stuff_tce);

arch/powerpc/kvm/book3s_64_vio_hv.c

@@ -247,13 +247,19 @@ static void iommu_tce_kill_rm(struct iommu_table *tbl,
 		tbl->it_ops->tce_kill(tbl, entry, pages, true);
 }
 
-static void kvmppc_rm_clear_tce(struct kvm *kvm, struct iommu_table *tbl,
-		unsigned long entry)
+static void kvmppc_rm_clear_tce(struct kvm *kvm, struct kvmppc_spapr_tce_table *stt,
+		struct iommu_table *tbl, unsigned long entry)
 {
-	unsigned long hpa = 0;
-	enum dma_data_direction dir = DMA_NONE;
+	unsigned long i;
+	unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift);
+	unsigned long io_entry = entry << (stt->page_shift - tbl->it_page_shift);
+
+	for (i = 0; i < subpages; ++i) {
+		unsigned long hpa = 0;
+		enum dma_data_direction dir = DMA_NONE;
 
-	iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir);
+		iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, io_entry + i, &hpa, &dir);
+	}
 }
 
 static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm,
@@ -316,6 +322,8 @@ static long kvmppc_rm_tce_iommu_unmap(struct kvm *kvm,
 			break;
 	}
 
+	iommu_tce_kill_rm(tbl, io_entry, subpages);
+
 	return ret;
 }
 
@@ -379,6 +387,8 @@ static long kvmppc_rm_tce_iommu_map(struct kvm *kvm,
 			break;
 	}
 
+	iommu_tce_kill_rm(tbl, io_entry, subpages);
+
 	return ret;
 }
 
@@ -420,10 +430,8 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, stt,
 					stit->tbl, entry, ua, dir);
 
-		iommu_tce_kill_rm(stit->tbl, entry, 1);
-
 		if (ret != H_SUCCESS) {
-			kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry);
+			kvmppc_rm_clear_tce(vcpu->kvm, stt, stit->tbl, entry);
 			return ret;
 		}
 	}
@@ -561,7 +569,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		ua = 0;
 		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua)) {
 			ret = H_PARAMETER;
-			goto invalidate_exit;
+			goto unlock_exit;
 		}
 
 		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
@@ -570,19 +578,15 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 					iommu_tce_direction(tce));
 
 			if (ret != H_SUCCESS) {
-				kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl,
-						entry);
-				goto invalidate_exit;
+				kvmppc_rm_clear_tce(vcpu->kvm, stt, stit->tbl,
+						entry + i);
+				goto unlock_exit;
 			}
 		}
 
 		kvmppc_rm_tce_put(stt, entry + i, tce);
 	}
 
-invalidate_exit:
-	list_for_each_entry_lockless(stit, &stt->iommu_tables, next)
-		iommu_tce_kill_rm(stit->tbl, entry, npages);
-
 unlock_exit:
 	if (!prereg)
 		arch_spin_unlock(&kvm->mmu_lock.rlock.raw_lock);
@@ -620,20 +624,16 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 				continue;
 
 			if (ret == H_TOO_HARD)
-				goto invalidate_exit;
+				return ret;
 
 			WARN_ON_ONCE_RM(1);
-			kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry);
+			kvmppc_rm_clear_tce(vcpu->kvm, stt, stit->tbl, entry + i);
 		}
 	}
 
 	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
 		kvmppc_rm_tce_put(stt, ioba >> stt->page_shift, tce_value);
 
-invalidate_exit:
-	list_for_each_entry_lockless(stit, &stt->iommu_tables, next)
-		iommu_tce_kill_rm(stit->tbl, ioba >> stt->page_shift, npages);
-
 	return ret;
 }
 

arch/powerpc/perf/Makefile

@@ -3,11 +3,11 @@
 obj-y				+= callchain.o callchain_$(BITS).o perf_regs.o
 obj-$(CONFIG_COMPAT)		+= callchain_32.o
 
-obj-$(CONFIG_PPC_PERF_CTRS)	+= core-book3s.o bhrb.o
+obj-$(CONFIG_PPC_PERF_CTRS)	+= core-book3s.o
 obj64-$(CONFIG_PPC_PERF_CTRS)	+= ppc970-pmu.o power5-pmu.o \
 				   power5+-pmu.o power6-pmu.o power7-pmu.o \
 				   isa207-common.o power8-pmu.o power9-pmu.o \
-				   generic-compat-pmu.o power10-pmu.o
+				   generic-compat-pmu.o power10-pmu.o bhrb.o
 obj32-$(CONFIG_PPC_PERF_CTRS)	+= mpc7450-pmu.o
 
 obj-$(CONFIG_PPC_POWERNV)	+= imc-pmu.o

arch/powerpc/perf/power10-pmu.c

@@ -91,8 +91,8 @@ extern u64 PERF_REG_EXTENDED_MASK;
 
 /* Table of alternatives, sorted by column 0 */
 static const unsigned int power10_event_alternatives[][MAX_ALT] = {
-	{ PM_CYC_ALT,			PM_CYC },
 	{ PM_INST_CMPL_ALT,		PM_INST_CMPL },
+	{ PM_CYC_ALT,			PM_CYC },
 };
 
 static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[])

arch/powerpc/perf/power9-pmu.c

@@ -133,11 +133,11 @@ int p9_dd22_bl_ev[] = {
 
 /* Table of alternatives, sorted by column 0 */
 static const unsigned int power9_event_alternatives[][MAX_ALT] = {
-	{ PM_INST_DISP,			PM_INST_DISP_ALT },
-	{ PM_RUN_CYC_ALT,		PM_RUN_CYC },
-	{ PM_RUN_INST_CMPL_ALT,		PM_RUN_INST_CMPL },
-	{ PM_LD_MISS_L1,		PM_LD_MISS_L1_ALT },
 	{ PM_BR_2PATH,			PM_BR_2PATH_ALT },
+	{ PM_INST_DISP,			PM_INST_DISP_ALT },
+	{ PM_RUN_CYC_ALT,               PM_RUN_CYC },
+	{ PM_LD_MISS_L1,                PM_LD_MISS_L1_ALT },
+	{ PM_RUN_INST_CMPL_ALT,         PM_RUN_INST_CMPL },
 };
 
 static int power9_get_alternatives(u64 event, unsigned int flags, u64 alt[])

arch/powerpc/platforms/pseries/papr_scm.c

@@ -462,7 +462,6 @@ static int papr_scm_pmu_check_events(struct papr_scm_priv *p, struct nvdimm_pmu
 {
 	struct papr_scm_perf_stat *stat;
 	struct papr_scm_perf_stats *stats;
-	char *statid;
 	int index, rc, count;
 	u32 available_events;
 
@@ -493,14 +492,12 @@ static int papr_scm_pmu_check_events(struct papr_scm_priv *p, struct nvdimm_pmu
 
 	for (index = 0, stat = stats->scm_statistic, count = 0;
 		     index < available_events; index++, ++stat) {
-		statid = kzalloc(strlen(stat->stat_id) + 1, GFP_KERNEL);
-		if (!statid) {
+		p->nvdimm_events_map[count] = kmemdup_nul(stat->stat_id, 8, GFP_KERNEL);
+		if (!p->nvdimm_events_map[count]) {
 			rc = -ENOMEM;
 			goto out_nvdimm_events_map;
 		}
 
-		strcpy(statid, stat->stat_id);
-		p->nvdimm_events_map[count] = statid;
 		count++;
 	}
 	p->nvdimm_events_map[count] = NULL;

arch/powerpc/platforms/pseries/vas-sysfs.c

@@ -27,22 +27,31 @@ struct vas_caps_entry {
 
 /*
  * This function is used to get the notification from the drmgr when
- * QoS credits are changed. Though receiving the target total QoS
- * credits here, get the official QoS capabilities from the hypervisor.
+ * QoS credits are changed.
  */
-static ssize_t update_total_credits_trigger(struct vas_cop_feat_caps *caps,
+static ssize_t update_total_credits_store(struct vas_cop_feat_caps *caps,
 						const char *buf, size_t count)
 {
 	int err;
 	u16 creds;
 
 	err = kstrtou16(buf, 0, &creds);
+	/*
+	 * The user space interface from the management console
+	 * notifies OS with the new QoS credits and then the
+	 * hypervisor. So OS has to use this new credits value
+	 * and reconfigure VAS windows (close or reopen depends
+	 * on the credits available) instead of depending on VAS
+	 * QoS capabilities from the hypervisor.
+	 */
 	if (!err)
-		err = vas_reconfig_capabilties(caps->win_type);
+		err = vas_reconfig_capabilties(caps->win_type, creds);
 
 	if (err)
 		return -EINVAL;
 
+	pr_info("Set QoS total credits %u\n", creds);
+
 	return count;
 }
 
@@ -92,7 +101,7 @@ VAS_ATTR_RO(nr_total_credits);
 VAS_ATTR_RO(nr_used_credits);
 
 static struct vas_sysfs_entry update_total_credits_attribute =
-	__ATTR(update_total_credits, 0200, NULL, update_total_credits_trigger);
+	__ATTR(update_total_credits, 0200, NULL, update_total_credits_store);
 
 static struct attribute *vas_def_capab_attrs[] = {
 	&nr_total_credits_attribute.attr,

arch/powerpc/platforms/pseries/vas.c

@@ -779,10 +779,10 @@ static int reconfig_close_windows(struct vas_caps *vcap, int excess_creds,
  * changes. Reconfig window configurations based on the credits
  * availability from this new capabilities.
  */
-int vas_reconfig_capabilties(u8 type)
+int vas_reconfig_capabilties(u8 type, int new_nr_creds)
 {
 	struct vas_cop_feat_caps *caps;
-	int old_nr_creds, new_nr_creds;
+	int old_nr_creds;
 	struct vas_caps *vcaps;
 	int rc = 0, nr_active_wins;
 
@@ -795,12 +795,6 @@ int vas_reconfig_capabilties(u8 type)
 	caps = &vcaps->caps;
 
 	mutex_lock(&vas_pseries_mutex);
-	rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, vcaps->feat,
-				      (u64)virt_to_phys(&hv_cop_caps));
-	if (rc)
-		goto out;
-
-	new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds);
 
 	old_nr_creds = atomic_read(&caps->nr_total_credits);
 
@@ -832,7 +826,6 @@ int vas_reconfig_capabilties(u8 type)
 					false);
 	}
 
-out:
 	mutex_unlock(&vas_pseries_mutex);
 	return rc;
 }
@@ -850,7 +843,7 @@ static int pseries_vas_notifier(struct notifier_block *nb,
 	struct of_reconfig_data *rd = data;
 	struct device_node *dn = rd->dn;
 	const __be32 *intserv = NULL;
-	int len, rc = 0;
+	int new_nr_creds, len, rc = 0;
 
 	if ((action == OF_RECONFIG_ATTACH_NODE) ||
 		(action == OF_RECONFIG_DETACH_NODE))
@@ -862,7 +855,15 @@ static int pseries_vas_notifier(struct notifier_block *nb,
 	if (!intserv)
 		return NOTIFY_OK;
 
-	rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE);
+	rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES,
+					vascaps[VAS_GZIP_DEF_FEAT_TYPE].feat,
+					(u64)virt_to_phys(&hv_cop_caps));
+	if (!rc) {
+		new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds);
+		rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE,
+						new_nr_creds);
+	}
+
 	if (rc)
 		pr_err("Failed reconfig VAS capabilities with DLPAR\n");
 

arch/powerpc/platforms/pseries/vas.h

@@ -135,7 +135,7 @@ struct pseries_vas_window {
 };
 
 int sysfs_add_vas_caps(struct vas_cop_feat_caps *caps);
-int vas_reconfig_capabilties(u8 type);
+int vas_reconfig_capabilties(u8 type, int new_nr_creds);
 int __init sysfs_pseries_vas_init(struct vas_all_caps *vas_caps);
 
 #ifdef CONFIG_PPC_VAS