Merge tag 'powerpc-5.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Enable KFENCE for 32-bit.

 - Implement EBPF for 32-bit.

 - Convert 32-bit to do interrupt entry/exit in C.

 - Convert 64-bit BookE to do interrupt entry/exit in C.

 - Changes to our signal handling code to use user_access_begin/end()
   more extensively.

 - Add support for time namespaces (CONFIG_TIME_NS)

 - A series of fixes that allow us to reenable STRICT_KERNEL_RWX.

 - Other smaller features, fixes & cleanups.

Thanks to Alexey Kardashevskiy, Andreas Schwab, Andrew Donnellan, Aneesh
Kumar K.V, Athira Rajeev, Bhaskar Chowdhury, Bixuan Cui, Cédric Le
Goater, Chen Huang, Chris Packham, Christophe Leroy, Christopher M.
Riedl, Colin Ian King, Dan Carpenter, Daniel Axtens, Daniel Henrique
Barboza, David Gibson, Davidlohr Bueso, Denis Efremov, dingsenjie,
Dmitry Safonov, Dominic DeMarco, Fabiano Rosas, Ganesh Goudar, Geert
Uytterhoeven, Geetika Moolchandani, Greg Kurz, Guenter Roeck, Haren
Myneni, He Ying, Jiapeng Chong, Jordan Niethe, Laurent Dufour, Lee
Jones, Leonardo Bras, Li Huafei, Madhavan Srinivasan, Mahesh Salgaonkar,
Masahiro Yamada, Nathan Chancellor, Nathan Lynch, Nicholas Piggin,
Oliver O'Halloran, Paul Menzel, Pu Lehui, Randy Dunlap, Ravi Bangoria,
Rosen Penev, Russell Currey, Santosh Sivaraj, Sebastian Andrzej Siewior,
Segher Boessenkool, Shivaprasad G Bhat, Srikar Dronamraju, Stephen
Rothwell, Thadeu Lima de Souza Cascardo, Thomas Gleixner, Tony Ambardar,
Tyrel Datwyler, Vaibhav Jain, Vincenzo Frascino, Xiongwei Song, Yang Li,
Yu Kuai, and Zhang Yunkai.

* tag 'powerpc-5.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (302 commits)
  powerpc/signal32: Fix erroneous SIGSEGV on RT signal return
  powerpc: Avoid clang uninitialized warning in __get_user_size_allowed
  powerpc/papr_scm: Mark nvdimm as unarmed if needed during probe
  powerpc/kvm: Fix build error when PPC_MEM_KEYS/PPC_PSERIES=n
  powerpc/kasan: Fix shadow start address with modules
  powerpc/kernel/iommu: Use largepool as a last resort when !largealloc
  powerpc/kernel/iommu: Align size for IOMMU_PAGE_SIZE() to save TCEs
  powerpc/44x: fix spelling mistake in Kconfig "varients" -> "variants"
  powerpc/iommu: Annotate nested lock for lockdep
  powerpc/iommu: Do not immediately panic when failed IOMMU table allocation
  powerpc/iommu: Allocate it_map by vmalloc
  selftests/powerpc: remove unneeded semicolon
  powerpc/64s: remove unneeded semicolon
  powerpc/eeh: remove unneeded semicolon
  powerpc/selftests: Add selftest to test concurrent perf/ptrace events
  powerpc/selftests/perf-hwbreak: Add testcases for 2nd DAWR
  powerpc/selftests/perf-hwbreak: Coalesce event creation code
  powerpc/selftests/ptrace-hwbreak: Add testcases for 2nd DAWR
  powerpc/configs: Add IBMVNIC to some 64-bit configs
  selftests/powerpc: Add uaccess flush test
  ...

6 files changed, 149 insertions, 80 deletions

diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
index 6b4a34b36d98..1d33b7a5ea83 100644
--- a/arch/powerpc/sysdev/dart_iommu.c
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -344,7 +344,8 @@ static void iommu_table_dart_setup(void)
 	iommu_table_dart.it_index = 0;
 	iommu_table_dart.it_blocksize = 1;
 	iommu_table_dart.it_ops = &iommu_dart_ops;
-	iommu_init_table(&iommu_table_dart, -1, 0, 0);
+	if (!iommu_init_table(&iommu_table_dart, -1, 0, 0))
+		panic("Failed to initialize iommu table");
 
 	/* Reserve the last page of the DART to avoid possible prefetch
 	 * past the DART mapped area
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 040b9d01c079..69af73765783 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -455,7 +455,7 @@ static void setup_pci_atmu(struct pci_controller *hose)
 	}
 }
 
-static void __init setup_pci_cmd(struct pci_controller *hose)
+static void setup_pci_cmd(struct pci_controller *hose)
 {
 	u16 cmd;
 	int cap_x;
diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c
index 595310e056f4..50469700dec6 100644
--- a/arch/powerpc/sysdev/xive/common.c
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -63,8 +63,19 @@ static const struct xive_ops *xive_ops;
 static struct irq_domain *xive_irq_domain;
 
 #ifdef CONFIG_SMP
-/* The IPIs all use the same logical irq number */
-static u32 xive_ipi_irq;
+/* The IPIs use the same logical irq number when on the same chip */
+static struct xive_ipi_desc {
+	unsigned int irq;
+	char name[16];
+} *xive_ipis;
+
+/*
+ * Use early_cpu_to_node() for hot-plugged CPUs
+ */
+static unsigned int xive_ipi_cpu_to_irq(unsigned int cpu)
+{
+	return xive_ipis[early_cpu_to_node(cpu)].irq;
+}
 #endif
 
 /* Xive state for each CPU */
@@ -253,17 +264,20 @@ notrace void xmon_xive_do_dump(int cpu)
 	xmon_printf("\n");
 }
 
+static struct irq_data *xive_get_irq_data(u32 hw_irq)
+{
+	unsigned int irq = irq_find_mapping(xive_irq_domain, hw_irq);
+
+	return irq ? irq_get_irq_data(irq) : NULL;
+}
+
 int xmon_xive_get_irq_config(u32 hw_irq, struct irq_data *d)
 {
-	struct irq_chip *chip = irq_data_get_irq_chip(d);
 	int rc;
 	u32 target;
 	u8 prio;
 	u32 lirq;
 
-	if (!is_xive_irq(chip))
-		return -EINVAL;
-
 	rc = xive_ops->get_irq_config(hw_irq, &target, &prio, &lirq);
 	if (rc) {
 		xmon_printf("IRQ 0x%08x : no config rc=%d\n", hw_irq, rc);
@@ -273,6 +287,9 @@ int xmon_xive_get_irq_config(u32 hw_irq, struct irq_data *d)
 	xmon_printf("IRQ 0x%08x : target=0x%x prio=%02x lirq=0x%x ",
 		    hw_irq, target, prio, lirq);
 
+	if (!d)
+		d = xive_get_irq_data(hw_irq);
+
 	if (d) {
 		struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
 		u64 val = xive_esb_read(xd, XIVE_ESB_GET);
@@ -289,6 +306,20 @@ int xmon_xive_get_irq_config(u32 hw_irq, struct irq_data *d)
 	return 0;
 }
 
+void xmon_xive_get_irq_all(void)
+{
+	unsigned int i;
+	struct irq_desc *desc;
+
+	for_each_irq_desc(i, desc) {
+		struct irq_data *d = irq_desc_get_irq_data(desc);
+		unsigned int hwirq = (unsigned int)irqd_to_hwirq(d);
+
+		if (d->domain == xive_irq_domain)
+			xmon_xive_get_irq_config(hwirq, d);
+	}
+}
+
 #endif /* CONFIG_XMON */
 
 static unsigned int xive_get_irq(void)
@@ -1067,28 +1098,94 @@ static struct irq_chip xive_ipi_chip = {
 	.irq_unmask = xive_ipi_do_nothing,
 };
 
-static void __init xive_request_ipi(void)
+/*
+ * IPIs are marked per-cpu. We use separate HW interrupts under the
+ * hood but associated with the same "linux" interrupt
+ */
+struct xive_ipi_alloc_info {
+	irq_hw_number_t hwirq;
+};
+
+static int xive_ipi_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				     unsigned int nr_irqs, void *arg)
 {
-	unsigned int virq;
+	struct xive_ipi_alloc_info *info = arg;
+	int i;
 
-	/*
-	 * Initialization failed, move on, we might manage to
-	 * reach the point where we display our errors before
-	 * the system falls appart
-	 */
-	if (!xive_irq_domain)
-		return;
+	for (i = 0; i < nr_irqs; i++) {
+		irq_domain_set_info(domain, virq + i, info->hwirq + i, &xive_ipi_chip,
+				    domain->host_data, handle_percpu_irq,
+				    NULL, NULL);
+	}
+	return 0;
+}
 
-	/* Initialize it */
-	virq = irq_create_mapping(xive_irq_domain, XIVE_IPI_HW_IRQ);
-	xive_ipi_irq = virq;
+static const struct irq_domain_ops xive_ipi_irq_domain_ops = {
+	.alloc  = xive_ipi_irq_domain_alloc,
+};
 
-	WARN_ON(request_irq(virq, xive_muxed_ipi_action,
-			    IRQF_PERCPU | IRQF_NO_THREAD, "IPI", NULL));
+static int __init xive_request_ipi(void)
+{
+	struct fwnode_handle *fwnode;
+	struct irq_domain *ipi_domain;
+	unsigned int node;
+	int ret = -ENOMEM;
+
+	fwnode = irq_domain_alloc_named_fwnode("XIVE-IPI");
+	if (!fwnode)
+		goto out;
+
+	ipi_domain = irq_domain_create_linear(fwnode, nr_node_ids,
+					      &xive_ipi_irq_domain_ops, NULL);
+	if (!ipi_domain)
+		goto out_free_fwnode;
+
+	xive_ipis = kcalloc(nr_node_ids, sizeof(*xive_ipis), GFP_KERNEL | __GFP_NOFAIL);
+	if (!xive_ipis)
+		goto out_free_domain;
+
+	for_each_node(node) {
+		struct xive_ipi_desc *xid = &xive_ipis[node];
+		struct xive_ipi_alloc_info info = { node };
+
+		/* Skip nodes without CPUs */
+		if (cpumask_empty(cpumask_of_node(node)))
+			continue;
+
+		/*
+		 * Map one IPI interrupt per node for all cpus of that node.
+		 * Since the HW interrupt number doesn't have any meaning,
+		 * simply use the node number.
+		 */
+		xid->irq = irq_domain_alloc_irqs(ipi_domain, 1, node, &info);
+		if (xid->irq < 0) {
+			ret = xid->irq;
+			goto out_free_xive_ipis;
+		}
+
+		snprintf(xid->name, sizeof(xid->name), "IPI-%d", node);
+
+		ret = request_irq(xid->irq, xive_muxed_ipi_action,
+				  IRQF_PERCPU | IRQF_NO_THREAD, xid->name, NULL);
+
+		WARN(ret < 0, "Failed to request IPI %d: %d\n", xid->irq, ret);
+	}
+
+	return ret;
+
+out_free_xive_ipis:
+	kfree(xive_ipis);
+out_free_domain:
+	irq_domain_remove(ipi_domain);
+out_free_fwnode:
+	irq_domain_free_fwnode(fwnode);
+out:
+	return ret;
 }
 
 static int xive_setup_cpu_ipi(unsigned int cpu)
 {
+	unsigned int xive_ipi_irq = xive_ipi_cpu_to_irq(cpu);
 	struct xive_cpu *xc;
 	int rc;
 
@@ -1131,6 +1228,8 @@ static int xive_setup_cpu_ipi(unsigned int cpu)
 
 static void xive_cleanup_cpu_ipi(unsigned int cpu, struct xive_cpu *xc)
 {
+	unsigned int xive_ipi_irq = xive_ipi_cpu_to_irq(cpu);
+
 	/* Disable the IPI and free the IRQ data */
 
 	/* Already cleaned up ? */
@@ -1178,19 +1277,6 @@ static int xive_irq_domain_map(struct irq_domain *h, unsigned int virq,
 	 */
 	irq_clear_status_flags(virq, IRQ_LEVEL);
 
-#ifdef CONFIG_SMP
-	/* IPIs are special and come up with HW number 0 */
-	if (hw == XIVE_IPI_HW_IRQ) {
-		/*
-		 * IPIs are marked per-cpu. We use separate HW interrupts under
-		 * the hood but associated with the same "linux" interrupt
-		 */
-		irq_set_chip_and_handler(virq, &xive_ipi_chip,
-					 handle_percpu_irq);
-		return 0;
-	}
-#endif
-
 	rc = xive_irq_alloc_data(virq, hw);
 	if (rc)
 		return rc;
@@ -1202,15 +1288,7 @@ static int xive_irq_domain_map(struct irq_domain *h, unsigned int virq,
 
 static void xive_irq_domain_unmap(struct irq_domain *d, unsigned int virq)
 {
-	struct irq_data *data = irq_get_irq_data(virq);
-	unsigned int hw_irq;
-
-	/* XXX Assign BAD number */
-	if (!data)
-		return;
-	hw_irq = (unsigned int)irqd_to_hwirq(data);
-	if (hw_irq != XIVE_IPI_HW_IRQ)
-		xive_irq_free_data(virq);
+	xive_irq_free_data(virq);
 }
 
 static int xive_irq_domain_xlate(struct irq_domain *h, struct device_node *ct,
@@ -1335,17 +1413,14 @@ static int xive_prepare_cpu(unsigned int cpu)
 
 	xc = per_cpu(xive_cpu, cpu);
 	if (!xc) {
-		struct device_node *np;
-
 		xc = kzalloc_node(sizeof(struct xive_cpu),
 				  GFP_KERNEL, cpu_to_node(cpu));
 		if (!xc)
 			return -ENOMEM;
-		np = of_get_cpu_node(cpu, NULL);
-		if (np)
-			xc->chip_id = of_get_ibm_chip_id(np);
-		of_node_put(np);
 		xc->hw_ipi = XIVE_BAD_IRQ;
+		xc->chip_id = XIVE_INVALID_CHIP_ID;
+		if (xive_ops->prepare_cpu)
+			xive_ops->prepare_cpu(cpu, xc);
 
 		per_cpu(xive_cpu, cpu) = xc;
 	}
@@ -1408,13 +1483,12 @@ static void xive_flush_cpu_queue(unsigned int cpu, struct xive_cpu *xc)
 		struct irq_desc *desc = irq_to_desc(irq);
 		struct irq_data *d = irq_desc_get_irq_data(desc);
 		struct xive_irq_data *xd;
-		unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
 
 		/*
 		 * Ignore anything that isn't a XIVE irq and ignore
 		 * IPIs, so can just be dropped.
 		 */
-		if (d->domain != xive_irq_domain || hw_irq == XIVE_IPI_HW_IRQ)
+		if (d->domain != xive_irq_domain)
 			continue;
 
 		/*
@@ -1592,16 +1666,15 @@ static void xive_debug_show_cpu(struct seq_file *m, int cpu)
 	seq_puts(m, "\n");
 }
 
-static void xive_debug_show_irq(struct seq_file *m, u32 hw_irq, struct irq_data *d)
+static void xive_debug_show_irq(struct seq_file *m, struct irq_data *d)
 {
-	struct irq_chip *chip = irq_data_get_irq_chip(d);
+	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
 	int rc;
 	u32 target;
 	u8 prio;
 	u32 lirq;
-
-	if (!is_xive_irq(chip))
-		return;
+	struct xive_irq_data *xd;
+	u64 val;
 
 	rc = xive_ops->get_irq_config(hw_irq, &target, &prio, &lirq);
 	if (rc) {
@@ -1612,17 +1685,14 @@ static void xive_debug_show_irq(struct seq_file *m, u32 hw_irq, struct irq_data
 	seq_printf(m, "IRQ 0x%08x : target=0x%x prio=%02x lirq=0x%x ",
 		   hw_irq, target, prio, lirq);
 
-	if (d) {
-		struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
-		u64 val = xive_esb_read(xd, XIVE_ESB_GET);
-
-		seq_printf(m, "flags=%c%c%c PQ=%c%c",
-			   xd->flags & XIVE_IRQ_FLAG_STORE_EOI ? 'S' : ' ',
-			   xd->flags & XIVE_IRQ_FLAG_LSI ? 'L' : ' ',
-			   xd->flags & XIVE_IRQ_FLAG_H_INT_ESB ? 'H' : ' ',
-			   val & XIVE_ESB_VAL_P ? 'P' : '-',
-			   val & XIVE_ESB_VAL_Q ? 'Q' : '-');
-	}
+	xd = irq_data_get_irq_handler_data(d);
+	val = xive_esb_read(xd, XIVE_ESB_GET);
+	seq_printf(m, "flags=%c%c%c PQ=%c%c",
+		   xd->flags & XIVE_IRQ_FLAG_STORE_EOI ? 'S' : ' ',
+		   xd->flags & XIVE_IRQ_FLAG_LSI ? 'L' : ' ',
+		   xd->flags & XIVE_IRQ_FLAG_H_INT_ESB ? 'H' : ' ',
+		   val & XIVE_ESB_VAL_P ? 'P' : '-',
+		   val & XIVE_ESB_VAL_Q ? 'Q' : '-');
 	seq_puts(m, "\n");
 }
 
@@ -1640,16 +1710,9 @@ static int xive_core_debug_show(struct seq_file *m, void *private)
 
 	for_each_irq_desc(i, desc) {
 		struct irq_data *d = irq_desc_get_irq_data(desc);
-		unsigned int hw_irq;
-
-		if (!d)
-			continue;
-
-		hw_irq = (unsigned int)irqd_to_hwirq(d);
 
-		/* IPIs are special (HW number 0) */
-		if (hw_irq != XIVE_IPI_HW_IRQ)
-			xive_debug_show_irq(m, hw_irq, d);
+		if (d->domain == xive_irq_domain)
+			xive_debug_show_irq(m, d);
 	}
 	return 0;
 }
diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c
index 05a800a3104e..57e3f1540435 100644
--- a/arch/powerpc/sysdev/xive/native.c
+++ b/arch/powerpc/sysdev/xive/native.c
@@ -380,6 +380,11 @@ static void xive_native_update_pending(struct xive_cpu *xc)
 	}
 }
 
+static void xive_native_prepare_cpu(unsigned int cpu, struct xive_cpu *xc)
+{
+	xc->chip_id = cpu_to_chip_id(cpu);
+}
+
 static void xive_native_setup_cpu(unsigned int cpu, struct xive_cpu *xc)
 {
 	s64 rc;
@@ -462,6 +467,7 @@ static const struct xive_ops xive_native_ops = {
 	.match			= xive_native_match,
 	.shutdown		= xive_native_shutdown,
 	.update_pending		= xive_native_update_pending,
+	.prepare_cpu		= xive_native_prepare_cpu,
 	.setup_cpu		= xive_native_setup_cpu,
 	.teardown_cpu		= xive_native_teardown_cpu,
 	.sync_source		= xive_native_sync_source,
diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c
index 01ccc0786ada..f143b6f111ac 100644
--- a/arch/powerpc/sysdev/xive/spapr.c
+++ b/arch/powerpc/sysdev/xive/spapr.c
@@ -549,7 +549,7 @@ static void xive_spapr_cleanup_queue(unsigned int cpu, struct xive_cpu *xc,
 static bool xive_spapr_match(struct device_node *node)
 {
 	/* Ignore cascaded controllers for the moment */
-	return 1;
+	return true;
 }
 
 #ifdef CONFIG_SMP
diff --git a/arch/powerpc/sysdev/xive/xive-internal.h b/arch/powerpc/sysdev/xive/xive-internal.h
index 9cf57c722faa..504e7edce358 100644
--- a/arch/powerpc/sysdev/xive/xive-internal.h
+++ b/arch/powerpc/sysdev/xive/xive-internal.h
@@ -5,8 +5,6 @@
 #ifndef __XIVE_INTERNAL_H
 #define __XIVE_INTERNAL_H
 
-#define XIVE_IPI_HW_IRQ		0 /* interrupt source # for IPIs */
-
 /*
  * A "disabled" interrupt should never fire, to catch problems
  * we set its logical number to this
@@ -46,6 +44,7 @@ struct xive_ops {
 				  u32 *sw_irq);
 	int	(*setup_queue)(unsigned int cpu, struct xive_cpu *xc, u8 prio);
 	void	(*cleanup_queue)(unsigned int cpu, struct xive_cpu *xc, u8 prio);
+	void	(*prepare_cpu)(unsigned int cpu, struct xive_cpu *xc);
 	void	(*setup_cpu)(unsigned int cpu, struct xive_cpu *xc);
 	void	(*teardown_cpu)(unsigned int cpu, struct xive_cpu *xc);
 	bool	(*match)(struct device_node *np);