Merge tag 'powerpc-6.0-4' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:

 - Fix handling of PCI domains in /proc on 32-bit systems using the
   recently added support for numbering buses from zero for each domain.

 - A fix and a revert for some changes to use READ/WRITE_ONCE() which
   caused problems with KASAN enabled due to sanitisation calls being
   introduced in low-level paths that can't cope with it.

 - Fix build errors on 32-bit caused by the syscall table being
   misaligned sometimes.

 - Two fixes to get IBM Cell native machines booting again, which had
   bit-rotted while my QS22 was temporarily out of action.

 - Fix the papr_scm driver to not assume the order of events returned by
   the hypervisor is stable, and a related compile fix.

Thanks to Aneesh Kumar K.V, Christophe Leroy, Jordan Niethe, Kajol Jain,
Masahiro Yamada, Nathan Chancellor, Pali Rohár, Vaibhav Jain, and Zhouyi
Zhou.

* tag 'powerpc-6.0-4' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc/papr_scm: Ensure rc is always initialized in papr_scm_pmu_register()
  Revert "powerpc/irq: Don't open code irq_soft_mask helpers"
  powerpc: Fix hard_irq_disable() with sanitizer
  powerpc/rtas: Fix RTAS MSR[HV] handling for Cell
  Revert "powerpc: Remove unused FW_FEATURE_NATIVE references"
  powerpc: align syscall table for ppc32
  powerpc/pci: Enable PCI domains in /proc when PCI bus numbers are not unique
  powerpc/papr_scm: Fix nvdimm event mappings

arch/powerpc/include/asm/firmware.h

@@ -83,6 +83,8 @@ enum {
 	FW_FEATURE_POWERNV_ALWAYS = 0,
 	FW_FEATURE_PS3_POSSIBLE = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1,
 	FW_FEATURE_PS3_ALWAYS = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1,
+	FW_FEATURE_NATIVE_POSSIBLE = 0,
+	FW_FEATURE_NATIVE_ALWAYS = 0,
 	FW_FEATURE_POSSIBLE =
 #ifdef CONFIG_PPC_PSERIES
 		FW_FEATURE_PSERIES_POSSIBLE |
@@ -92,6 +94,9 @@ enum {
 #endif
 #ifdef CONFIG_PPC_PS3
 		FW_FEATURE_PS3_POSSIBLE |
+#endif
+#ifdef CONFIG_PPC_HASH_MMU_NATIVE
+		FW_FEATURE_NATIVE_ALWAYS |
 #endif
 		0,
 	FW_FEATURE_ALWAYS =
@@ -103,6 +108,9 @@ enum {
 #endif
 #ifdef CONFIG_PPC_PS3
 		FW_FEATURE_PS3_ALWAYS &
+#endif
+#ifdef CONFIG_PPC_HASH_MMU_NATIVE
+		FW_FEATURE_NATIVE_ALWAYS &
 #endif
 		FW_FEATURE_POSSIBLE,
 

arch/powerpc/include/asm/hw_irq.h

@@ -113,7 +113,14 @@ static inline void __hard_RI_enable(void)
 
 static inline notrace unsigned long irq_soft_mask_return(void)
 {
-	return READ_ONCE(local_paca->irq_soft_mask);
+	unsigned long flags;
+
+	asm volatile(
+		"lbz %0,%1(13)"
+		: "=r" (flags)
+		: "i" (offsetof(struct paca_struct, irq_soft_mask)));
+
+	return flags;
 }
 
 /*
@@ -140,24 +147,46 @@ static inline notrace void irq_soft_mask_set(unsigned long mask)
 	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
 		WARN_ON(mask && !(mask & IRQS_DISABLED));
 
-	WRITE_ONCE(local_paca->irq_soft_mask, mask);
-	barrier();
+	asm volatile(
+		"stb %0,%1(13)"
+		:
+		: "r" (mask),
+		  "i" (offsetof(struct paca_struct, irq_soft_mask))
+		: "memory");
 }
 
 static inline notrace unsigned long irq_soft_mask_set_return(unsigned long mask)
 {
-	unsigned long flags = irq_soft_mask_return();
+	unsigned long flags;
 
-	irq_soft_mask_set(mask);
+#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
+	WARN_ON(mask && !(mask & IRQS_DISABLED));
+#endif
+
+	asm volatile(
+		"lbz %0,%1(13); stb %2,%1(13)"
+		: "=&r" (flags)
+		: "i" (offsetof(struct paca_struct, irq_soft_mask)),
+		  "r" (mask)
+		: "memory");
 
 	return flags;
 }
 
 static inline notrace unsigned long irq_soft_mask_or_return(unsigned long mask)
 {
-	unsigned long flags = irq_soft_mask_return();
+	unsigned long flags, tmp;
+
+	asm volatile(
+		"lbz %0,%2(13); or %1,%0,%3; stb %1,%2(13)"
+		: "=&r" (flags), "=r" (tmp)
+		: "i" (offsetof(struct paca_struct, irq_soft_mask)),
+		  "r" (mask)
+		: "memory");
 
-	irq_soft_mask_set(flags | mask);
+#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
+	WARN_ON((mask | flags) && !((mask | flags) & IRQS_DISABLED));
+#endif
 
 	return flags;
 }
@@ -282,7 +311,8 @@ static inline bool pmi_irq_pending(void)
 	flags = irq_soft_mask_set_return(IRQS_ALL_DISABLED);		\
 	local_paca->irq_happened |= PACA_IRQ_HARD_DIS;			\
 	if (!arch_irqs_disabled_flags(flags)) {				\
-		WRITE_ONCE(local_paca->saved_r1, current_stack_pointer);\
+		asm volatile("std%X0 %1,%0" : "=m" (local_paca->saved_r1) \
+					    : "r" (current_stack_pointer)); \
 		trace_hardirqs_off();					\
 	}								\
 } while(0)

arch/powerpc/kernel/pci_32.c

@@ -245,6 +245,15 @@ static int __init pcibios_init(void)
 
 	printk(KERN_INFO "PCI: Probing PCI hardware\n");
 
+#ifdef CONFIG_PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT
+	/*
+	 * Enable PCI domains in /proc when PCI bus numbers are not unique
+	 * across all PCI domains to prevent conflicts. And keep PCI domain 0
+	 * backward compatible in /proc for video cards.
+	 */
+	pci_add_flags(PCI_ENABLE_PROC_DOMAINS | PCI_COMPAT_DOMAIN_0);
+#endif
+
 	if (pci_has_flag(PCI_REASSIGN_ALL_BUS))
 		pci_assign_all_buses = 1;
 

arch/powerpc/kernel/rtas_entry.S

@@ -109,8 +109,12 @@ __enter_rtas:
 	 * its critical regions (as specified in PAPR+ section 7.2.1). MSR[S]
 	 * is not impacted by RFI_TO_KERNEL (only urfid can unset it). So if
 	 * MSR[S] is set, it will remain when entering RTAS.
+	 * If we're in HV mode, RTAS must also run in HV mode, so extract MSR_HV
+	 * from the saved MSR value and insert into the value RTAS will use.
 	 */
+	extrdi	r0, r6, 1, 63 - MSR_HV_LG
 	LOAD_REG_IMMEDIATE(r6, MSR_ME | MSR_RI)
+	insrdi	r6, r0, 1, 63 - MSR_HV_LG
 
 	li      r0,0
 	mtmsrd  r0,1                    /* disable RI before using SRR0/1 */

arch/powerpc/kernel/systbl.S

@@ -18,6 +18,7 @@
 	.p2align	3
 #define __SYSCALL(nr, entry)	.8byte entry
 #else
+	.p2align	2
 #define __SYSCALL(nr, entry)	.long entry
 #endif
 

arch/powerpc/platforms/pseries/papr_scm.c

@@ -124,9 +124,6 @@ struct papr_scm_priv {
 
 	/* The bits which needs to be overridden */
 	u64 health_bitmap_inject_mask;
-
-	/* array to have event_code and stat_id mappings */
-	u8 *nvdimm_events_map;
 };
 
 static int papr_scm_pmem_flush(struct nd_region *nd_region,
@@ -350,6 +347,25 @@ static ssize_t drc_pmem_query_stats(struct papr_scm_priv *p,
 #ifdef CONFIG_PERF_EVENTS
 #define to_nvdimm_pmu(_pmu)	container_of(_pmu, struct nvdimm_pmu, pmu)
 
+static const char * const nvdimm_events_map[] = {
+	[1] = "CtlResCt",
+	[2] = "CtlResTm",
+	[3] = "PonSecs ",
+	[4] = "MemLife ",
+	[5] = "CritRscU",
+	[6] = "HostLCnt",
+	[7] = "HostSCnt",
+	[8] = "HostSDur",
+	[9] = "HostLDur",
+	[10] = "MedRCnt ",
+	[11] = "MedWCnt ",
+	[12] = "MedRDur ",
+	[13] = "MedWDur ",
+	[14] = "CchRHCnt",
+	[15] = "CchWHCnt",
+	[16] = "FastWCnt",
+};
+
 static int papr_scm_pmu_get_value(struct perf_event *event, struct device *dev, u64 *count)
 {
 	struct papr_scm_perf_stat *stat;
@@ -357,11 +373,15 @@ static int papr_scm_pmu_get_value(struct perf_event *event, struct device *dev,
 	struct papr_scm_priv *p = dev_get_drvdata(dev);
 	int rc, size;
 
+	/* Invalid eventcode */
+	if (event->attr.config == 0 || event->attr.config >= ARRAY_SIZE(nvdimm_events_map))
+		return -EINVAL;
+
 	/* Allocate request buffer enough to hold single performance stat */
 	size = sizeof(struct papr_scm_perf_stats) +
 		sizeof(struct papr_scm_perf_stat);
 
-	if (!p || !p->nvdimm_events_map)
+	if (!p)
 		return -EINVAL;
 
 	stats = kzalloc(size, GFP_KERNEL);
@@ -370,7 +390,7 @@ static int papr_scm_pmu_get_value(struct perf_event *event, struct device *dev,
 
 	stat = &stats->scm_statistic[0];
 	memcpy(&stat->stat_id,
-	       &p->nvdimm_events_map[event->attr.config * sizeof(stat->stat_id)],
+	       nvdimm_events_map[event->attr.config],
 		sizeof(stat->stat_id));
 	stat->stat_val = 0;
 
@@ -458,56 +478,6 @@ static void papr_scm_pmu_del(struct perf_event *event, int flags)
 	papr_scm_pmu_read(event);
 }
 
-static int papr_scm_pmu_check_events(struct papr_scm_priv *p, struct nvdimm_pmu *nd_pmu)
-{
-	struct papr_scm_perf_stat *stat;
-	struct papr_scm_perf_stats *stats;
-	u32 available_events;
-	int index, rc = 0;
-
-	if (!p->stat_buffer_len)
-		return -ENOENT;
-
-	available_events = (p->stat_buffer_len  - sizeof(struct papr_scm_perf_stats))
-			/ sizeof(struct papr_scm_perf_stat);
-	if (available_events == 0)
-		return -EOPNOTSUPP;
-
-	/* Allocate the buffer for phyp where stats are written */
-	stats = kzalloc(p->stat_buffer_len, GFP_KERNEL);
-	if (!stats) {
-		rc = -ENOMEM;
-		return rc;
-	}
-
-	/* Called to get list of events supported */
-	rc = drc_pmem_query_stats(p, stats, 0);
-	if (rc)
-		goto out;
-
-	/*
-	 * Allocate memory and populate nvdimm_event_map.
-	 * Allocate an extra element for NULL entry
-	 */
-	p->nvdimm_events_map = kcalloc(available_events + 1,
-				       sizeof(stat->stat_id),
-				       GFP_KERNEL);
-	if (!p->nvdimm_events_map) {
-		rc = -ENOMEM;
-		goto out;
-	}
-
-	/* Copy all stat_ids to event map */
-	for (index = 0, stat = stats->scm_statistic;
-	     index < available_events; index++, ++stat) {
-		memcpy(&p->nvdimm_events_map[index * sizeof(stat->stat_id)],
-		       &stat->stat_id, sizeof(stat->stat_id));
-	}
-out:
-	kfree(stats);
-	return rc;
-}
-
 static void papr_scm_pmu_register(struct papr_scm_priv *p)
 {
 	struct nvdimm_pmu *nd_pmu;
@@ -519,9 +489,10 @@ static void papr_scm_pmu_register(struct papr_scm_priv *p)
 		goto pmu_err_print;
 	}
 
-	rc = papr_scm_pmu_check_events(p, nd_pmu);
-	if (rc)
+	if (!p->stat_buffer_len) {
+		rc = -ENOENT;
 		goto pmu_check_events_err;
+	}
 
 	nd_pmu->pmu.task_ctx_nr = perf_invalid_context;
 	nd_pmu->pmu.name = nvdimm_name(p->nvdimm);
@@ -539,7 +510,7 @@ static void papr_scm_pmu_register(struct papr_scm_priv *p)
 
 	rc = register_nvdimm_pmu(nd_pmu, p->pdev);
 	if (rc)
-		goto pmu_register_err;
+		goto pmu_check_events_err;
 
 	/*
 	 * Set archdata.priv value to nvdimm_pmu structure, to handle the
@@ -548,8 +519,6 @@ static void papr_scm_pmu_register(struct papr_scm_priv *p)
 	p->pdev->archdata.priv = nd_pmu;
 	return;
 
-pmu_register_err:
-	kfree(p->nvdimm_events_map);
 pmu_check_events_err:
 	kfree(nd_pmu);
 pmu_err_print:
@@ -1560,7 +1529,6 @@ static int papr_scm_remove(struct platform_device *pdev)
 		unregister_nvdimm_pmu(pdev->archdata.priv);
 
 	pdev->archdata.priv = NULL;
-	kfree(p->nvdimm_events_map);
 	kfree(p->bus_desc.provider_name);
 	kfree(p);