Merge tag 'powerpc-5.14-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - A big series refactoring parts of our KVM code, and converting some
   to C.

 - Support for ARCH_HAS_SET_MEMORY, and ARCH_HAS_STRICT_MODULE_RWX on
   some CPUs.

 - Support for the Microwatt soft-core.

 - Optimisations to our interrupt return path on 64-bit.

 - Support for userspace access to the NX GZIP accelerator on PowerVM on
   Power10.

 - Enable KUAP and KUEP by default on 32-bit Book3S CPUs.

 - Other smaller features, fixes & cleanups.

Thanks to: Andy Shevchenko, Aneesh Kumar K.V, Arnd Bergmann, Athira
Rajeev, Baokun Li, Benjamin Herrenschmidt, Bharata B Rao, Christophe
Leroy, Daniel Axtens, Daniel Henrique Barboza, Finn Thain, Geoff Levand,
Haren Myneni, Jason Wang, Jiapeng Chong, Joel Stanley, Jordan Niethe,
Kajol Jain, Nathan Chancellor, Nathan Lynch, Naveen N. Rao, Nicholas
Piggin, Nick Desaulniers, Paul Mackerras, Russell Currey, Sathvika
Vasireddy, Shaokun Zhang, Stephen Rothwell, Sudeep Holla, Suraj Jitindar
Singh, Tom Rix, Vaibhav Jain, YueHaibing, Zhang Jianhua, and Zhen Lei.

* tag 'powerpc-5.14-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (218 commits)
  powerpc: Only build restart_table.c for 64s
  powerpc/64s: move ret_from_fork etc above __end_soft_masked
  powerpc/64s/interrupt: clean up interrupt return labels
  powerpc/64/interrupt: add missing kprobe annotations on interrupt exit symbols
  powerpc/64: enable MSR[EE] in irq replay pt_regs
  powerpc/64s/interrupt: preserve regs->softe for NMI interrupts
  powerpc/64s: add a table of implicit soft-masked addresses
  powerpc/64e: remove implicit soft-masking and interrupt exit restart logic
  powerpc/64e: fix CONFIG_RELOCATABLE build warnings
  powerpc/64s: fix hash page fault interrupt handler
  powerpc/4xx: Fix setup_kuep() on SMP
  powerpc/32s: Fix setup_{kuap/kuep}() on SMP
  powerpc/interrupt: Use names in check_return_regs_valid()
  powerpc/interrupt: Also use exit_must_hard_disable() on PPC32
  powerpc/sysfs: Replace sizeof(arr)/sizeof(arr[0]) with ARRAY_SIZE
  powerpc/ptrace: Refactor regs_set_return_{msr/ip}
  powerpc/ptrace: Move set_return_regs_changed() before regs_set_return_{msr/ip}
  powerpc/stacktrace: Fix spurious "stale" traces in raise_backtrace_ipi()
  powerpc/pseries/vas: Include irqdomain.h
  powerpc: mark local variables around longjmp as volatile
  ...

6 files changed, 266 insertions, 3 deletions

diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 69af73765783..b8f76f3fd994 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -1072,7 +1072,7 @@ int fsl_pci_mcheck_exception(struct pt_regs *regs)
 			ret = get_kernel_nofault(inst, (void *)regs->nip);
 
 		if (!ret && mcheck_handle_load(regs, inst)) {
-			regs->nip += 4;
+			regs_add_return_ip(regs, 4);
 			return 1;
 		}
 	}
diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c
index 07c164f7f8cf..5a95b8ea23d8 100644
--- a/arch/powerpc/sysdev/fsl_rio.c
+++ b/arch/powerpc/sysdev/fsl_rio.c
@@ -108,8 +108,8 @@ int fsl_rio_mcheck_exception(struct pt_regs *regs)
 				 __func__);
 			out_be32((u32 *)(rio_regs_win + RIO_LTLEDCSR),
 				 0);
-			regs->msr |= MSR_RI;
-			regs->nip = extable_fixup(entry);
+			regs_set_return_msr(regs, regs->msr | MSR_RI);
+			regs_set_return_ip(regs, extable_fixup(entry));
 			return 1;
 		}
 	}
diff --git a/arch/powerpc/sysdev/xics/Kconfig b/arch/powerpc/sysdev/xics/Kconfig
index 304614c920aa..063d9195891f 100644
--- a/arch/powerpc/sysdev/xics/Kconfig
+++ b/arch/powerpc/sysdev/xics/Kconfig
@@ -12,3 +12,6 @@ config PPC_ICP_HV
 
 config PPC_ICS_RTAS
 	def_bool n
+
+config PPC_ICS_NATIVE
+	def_bool n
diff --git a/arch/powerpc/sysdev/xics/Makefile b/arch/powerpc/sysdev/xics/Makefile
index ba1e3117b1c0..747063927c6c 100644
--- a/arch/powerpc/sysdev/xics/Makefile
+++ b/arch/powerpc/sysdev/xics/Makefile
@@ -4,4 +4,5 @@ obj-y				+= xics-common.o
 obj-$(CONFIG_PPC_ICP_NATIVE)	+= icp-native.o
 obj-$(CONFIG_PPC_ICP_HV)	+= icp-hv.o
 obj-$(CONFIG_PPC_ICS_RTAS)	+= ics-rtas.o
+obj-$(CONFIG_PPC_ICS_NATIVE)	+= ics-native.o
 obj-$(CONFIG_PPC_POWERNV)	+= ics-opal.o icp-opal.o
diff --git a/arch/powerpc/sysdev/xics/ics-native.c b/arch/powerpc/sysdev/xics/ics-native.c
new file mode 100644
index 000000000000..d450502f4053
--- /dev/null
+++ b/arch/powerpc/sysdev/xics/ics-native.c
@@ -0,0 +1,257 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * ICS backend for OPAL managed interrupts.
+ *
+ * Copyright 2011 IBM Corp.
+ */
+
+//#define DEBUG
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/irq.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/cpu.h>
+#include <linux/of.h>
+#include <linux/spinlock.h>
+#include <linux/msi.h>
+#include <linux/list.h>
+
+#include <asm/prom.h>
+#include <asm/smp.h>
+#include <asm/machdep.h>
+#include <asm/irq.h>
+#include <asm/errno.h>
+#include <asm/xics.h>
+#include <asm/opal.h>
+#include <asm/firmware.h>
+
+struct ics_native {
+	struct ics		ics;
+	struct device_node	*node;
+	void __iomem    	*base;
+	u32             	ibase;
+	u32             	icount;
+};
+#define to_ics_native(_ics)     container_of(_ics, struct ics_native, ics)
+
+static void __iomem *ics_native_xive(struct ics_native *in, unsigned int vec)
+{
+	return in->base + 0x800 + ((vec - in->ibase) << 2);
+}
+
+static void ics_native_unmask_irq(struct irq_data *d)
+{
+	unsigned int vec = (unsigned int)irqd_to_hwirq(d);
+	struct ics *ics = irq_data_get_irq_chip_data(d);
+	struct ics_native *in = to_ics_native(ics);
+	unsigned int server;
+
+	pr_devel("ics-native: unmask virq %d [hw 0x%x]\n", d->irq, vec);
+
+	if (vec < in->ibase || vec >= (in->ibase + in->icount))
+		return;
+
+	server = xics_get_irq_server(d->irq, irq_data_get_affinity_mask(d), 0);
+	out_be32(ics_native_xive(in, vec), (server << 8) | DEFAULT_PRIORITY);
+}
+
+static unsigned int ics_native_startup(struct irq_data *d)
+{
+#ifdef CONFIG_PCI_MSI
+	/*
+	 * The generic MSI code returns with the interrupt disabled on the
+	 * card, using the MSI mask bits. Firmware doesn't appear to unmask
+	 * at that level, so we do it here by hand.
+	 */
+	if (irq_data_get_msi_desc(d))
+		pci_msi_unmask_irq(d);
+#endif
+
+	/* unmask it */
+	ics_native_unmask_irq(d);
+	return 0;
+}
+
+static void ics_native_do_mask(struct ics_native *in, unsigned int vec)
+{
+	out_be32(ics_native_xive(in, vec), 0xff);
+}
+
+static void ics_native_mask_irq(struct irq_data *d)
+{
+	unsigned int vec = (unsigned int)irqd_to_hwirq(d);
+	struct ics *ics = irq_data_get_irq_chip_data(d);
+	struct ics_native *in = to_ics_native(ics);
+
+	pr_devel("ics-native: mask virq %d [hw 0x%x]\n", d->irq, vec);
+
+	if (vec < in->ibase || vec >= (in->ibase + in->icount))
+		return;
+	ics_native_do_mask(in, vec);
+}
+
+static int ics_native_set_affinity(struct irq_data *d,
+				   const struct cpumask *cpumask,
+				   bool force)
+{
+	unsigned int vec = (unsigned int)irqd_to_hwirq(d);
+	struct ics *ics = irq_data_get_irq_chip_data(d);
+	struct ics_native *in = to_ics_native(ics);
+	int server;
+	u32 xive;
+
+	if (vec < in->ibase || vec >= (in->ibase + in->icount))
+		return -EINVAL;
+
+	server = xics_get_irq_server(d->irq, cpumask, 1);
+	if (server == -1) {
+		pr_warn("%s: No online cpus in the mask %*pb for irq %d\n",
+			__func__, cpumask_pr_args(cpumask), d->irq);
+		return -1;
+	}
+
+	xive = in_be32(ics_native_xive(in, vec));
+	xive = (xive & 0xff) | (server << 8);
+	out_be32(ics_native_xive(in, vec), xive);
+
+	return IRQ_SET_MASK_OK;
+}
+
+static struct irq_chip ics_native_irq_chip = {
+	.name = "ICS",
+	.irq_startup		= ics_native_startup,
+	.irq_mask		= ics_native_mask_irq,
+	.irq_unmask		= ics_native_unmask_irq,
+	.irq_eoi		= NULL, /* Patched at init time */
+	.irq_set_affinity 	= ics_native_set_affinity,
+	.irq_set_type		= xics_set_irq_type,
+	.irq_retrigger		= xics_retrigger,
+};
+
+static int ics_native_map(struct ics *ics, unsigned int virq)
+{
+	unsigned int vec = (unsigned int)virq_to_hw(virq);
+	struct ics_native *in = to_ics_native(ics);
+
+	pr_devel("%s: vec=0x%x\n", __func__, vec);
+
+	if (vec < in->ibase || vec >= (in->ibase + in->icount))
+		return -EINVAL;
+
+	irq_set_chip_and_handler(virq, &ics_native_irq_chip, handle_fasteoi_irq);
+	irq_set_chip_data(virq, ics);
+
+	return 0;
+}
+
+static void ics_native_mask_unknown(struct ics *ics, unsigned long vec)
+{
+	struct ics_native *in = to_ics_native(ics);
+
+	if (vec < in->ibase || vec >= (in->ibase + in->icount))
+		return;
+
+	ics_native_do_mask(in, vec);
+}
+
+static long ics_native_get_server(struct ics *ics, unsigned long vec)
+{
+	struct ics_native *in = to_ics_native(ics);
+	u32 xive;
+
+	if (vec < in->ibase || vec >= (in->ibase + in->icount))
+		return -EINVAL;
+
+	xive = in_be32(ics_native_xive(in, vec));
+	return (xive >> 8) & 0xfff;
+}
+
+static int ics_native_host_match(struct ics *ics, struct device_node *node)
+{
+	struct ics_native *in = to_ics_native(ics);
+
+	return in->node == node;
+}
+
+static struct ics ics_native_template = {
+	.map		= ics_native_map,
+	.mask_unknown	= ics_native_mask_unknown,
+	.get_server	= ics_native_get_server,
+	.host_match	= ics_native_host_match,
+};
+
+static int __init ics_native_add_one(struct device_node *np)
+{
+	struct ics_native *ics;
+	u32 ranges[2];
+	int rc, count;
+
+	ics = kzalloc(sizeof(struct ics_native), GFP_KERNEL);
+	if (!ics)
+		return -ENOMEM;
+	ics->node = of_node_get(np);
+	memcpy(&ics->ics, &ics_native_template, sizeof(struct ics));
+
+	ics->base = of_iomap(np, 0);
+	if (!ics->base) {
+		pr_err("Failed to map %pOFP\n", np);
+		rc = -ENOMEM;
+		goto fail;
+	}
+
+	count = of_property_count_u32_elems(np, "interrupt-ranges");
+	if (count < 2 || count & 1) {
+		pr_err("Failed to read interrupt-ranges of %pOFP\n", np);
+		rc = -EINVAL;
+		goto fail;
+	}
+	if (count > 2) {
+		pr_warn("ICS %pOFP has %d ranges, only one supported\n",
+			np, count >> 1);
+	}
+	rc = of_property_read_u32_array(np, "interrupt-ranges",
+					ranges, 2);
+	if (rc) {
+		pr_err("Failed to read interrupt-ranges of %pOFP\n", np);
+		goto fail;
+	}
+	ics->ibase = ranges[0];
+	ics->icount = ranges[1];
+
+	pr_info("ICS native initialized for sources %d..%d\n",
+		ics->ibase, ics->ibase + ics->icount - 1);
+
+	/* Register ourselves */
+	xics_register_ics(&ics->ics);
+
+	return 0;
+fail:
+	of_node_put(ics->node);
+	kfree(ics);
+	return rc;
+}
+
+int __init ics_native_init(void)
+{
+	struct device_node *ics;
+	bool found_one = false;
+
+	/* We need to patch our irq chip's EOI to point to the
+	 * right ICP
+	 */
+	ics_native_irq_chip.irq_eoi = icp_ops->eoi;
+
+	/* Find native ICS in the device-tree */
+	for_each_compatible_node(ics, NULL, "openpower,xics-sources") {
+		if (ics_native_add_one(ics) == 0)
+			found_one = true;
+	}
+
+	if (found_one)
+		pr_info("ICS native backend registered\n");
+
+	return found_one ? 0 : -ENODEV;
+}
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index fdf8db4444b6..b14c502e56a8 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -477,6 +477,8 @@ void __init xics_init(void)
 	if (rc < 0)
 		rc = ics_opal_init();
 	if (rc < 0)
+		rc = ics_native_init();
+	if (rc < 0)
 		pr_warn("XICS: Cannot find a Source Controller !\n");
 
 	/* Initialize common bits */