Merge tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 fixes from Will Deacon:
 "I'd been collecting these whilst we debugged a CPU hotplug failure,
  but we ended up diagnosing that one to tglx, who has taken a fix via
  the -tip tree separately.

  We're seeing some NFS issues that we haven't gotten to the bottom of
  yet, and we've uncovered some issues with our backtracing too so there
  might be another fixes pull before we're done.

  Summary:

   - Ensure we have a guard page after the kernel image in vmalloc

   - Fix incorrect prefetch stride in copy_page

   - Ensure irqs are disabled in die()

   - Fix for event group validation in QCOM L2 PMU driver

   - Fix requesting of PMU IRQs on AMD Seattle

   - Minor cleanups and fixes"

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: mmu: Place guard page after mapping of kernel image
  drivers/perf: arm_pmu: Request PMU SPIs with IRQF_PER_CPU
  arm64: sysreg: Fix unprotected macro argmuent in write_sysreg
  perf: qcom_l2: fix column exclusion check
  arm64/lib: copy_page: use consistent prefetch stride
  arm64/numa: Drop duplicate message
  perf: Convert to using %pOF instead of full_name
  arm64: Convert to using %pOF instead of full_name
  arm64: traps: disable irq in die()
  arm64: atomics: Remove '&' from '+&' asm constraint in lse atomics
  arm64: uaccess: Remove redundant __force from addr cast in __range_ok

15 files changed, 84 insertions, 61 deletions

diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c
index 28083ef72819..71a34e8c345a 100644
--- a/arch/arm/mach-ux500/cpu-db8500.c
+++ b/arch/arm/mach-ux500/cpu-db8500.c
@@ -133,6 +133,7 @@ static irqreturn_t db8500_pmu_handler(int irq, void *dev, irq_handler_t handler)
 
 static struct arm_pmu_platdata db8500_pmu_platdata = {
 	.handle_irq		= db8500_pmu_handler,
+	.irq_flags		= IRQF_NOBALANCING | IRQF_NO_THREAD,
 };
 
 static struct of_dev_auxdata u8500_auxdata_lookup[] __initdata = {
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index 99fa69c9c3cf..9ef0797380cb 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -435,7 +435,7 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 	"	sub	x30, x30, %[ret]\n"
 	"	cbnz	x30, 1b\n"
 	"2:")
-	: [ret] "+&r" (x0), [v] "+Q" (v->counter)
+	: [ret] "+r" (x0), [v] "+Q" (v->counter)
 	:
 	: __LL_SC_CLOBBERS, "cc", "memory");
 
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 16e44fa9b3b6..248339e4aaf5 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -492,7 +492,7 @@ asm(
  * the "%x0" template means XZR.
  */
 #define write_sysreg(v, r) do {					\
-	u64 __val = (u64)v;					\
+	u64 __val = (u64)(v);					\
 	asm volatile("msr " __stringify(r) ", %x0"		\
 		     : : "rZ" (__val));				\
 } while (0)
@@ -508,7 +508,7 @@ asm(
 })
 
 #define write_sysreg_s(v, r) do {					\
-	u64 __val = (u64)v;						\
+	u64 __val = (u64)(v);						\
 	asm volatile("msr_s " __stringify(r) ", %x0" : : "rZ" (__val));	\
 } while (0)
 
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 8f0a1de11e4a..fab46a0ea223 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -69,7 +69,7 @@ static inline void set_fs(mm_segment_t fs)
  */
 #define __range_ok(addr, size)						\
 ({									\
-	unsigned long __addr = (unsigned long __force)(addr);		\
+	unsigned long __addr = (unsigned long)(addr);			\
 	unsigned long flag, roksum;					\
 	__chk_user_ptr(addr);						\
 	asm("adds %1, %1, %3; ccmp %1, %4, #2, cc; cset %0, ls"		\
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
index e137ceaf5016..d16978213c5b 100644
--- a/arch/arm64/kernel/cpu_ops.c
+++ b/arch/arm64/kernel/cpu_ops.c
@@ -82,8 +82,8 @@ static const char *__init cpu_read_enable_method(int cpu)
 			 * Don't warn spuriously.
 			 */
 			if (cpu != 0)
-				pr_err("%s: missing enable-method property\n",
-					dn->full_name);
+				pr_err("%pOF: missing enable-method property\n",
+					dn);
 		}
 	} else {
 		enable_method = acpi_get_enable_method(cpu);
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 321119881abf..dc66e6ec3a99 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -469,7 +469,7 @@ static u64 __init of_get_cpu_mpidr(struct device_node *dn)
 	 */
 	cell = of_get_property(dn, "reg", NULL);
 	if (!cell) {
-		pr_err("%s: missing reg property\n", dn->full_name);
+		pr_err("%pOF: missing reg property\n", dn);
 		return INVALID_HWID;
 	}
 
@@ -478,7 +478,7 @@ static u64 __init of_get_cpu_mpidr(struct device_node *dn)
 	 * Non affinity bits must be set to 0 in the DT
 	 */
 	if (hwid & ~MPIDR_HWID_BITMASK) {
-		pr_err("%s: invalid reg property\n", dn->full_name);
+		pr_err("%pOF: invalid reg property\n", dn);
 		return INVALID_HWID;
 	}
 	return hwid;
@@ -627,8 +627,8 @@ static void __init of_parse_and_init_cpus(void)
 			goto next;
 
 		if (is_mpidr_duplicate(cpu_count, hwid)) {
-			pr_err("%s: duplicate cpu reg properties in the DT\n",
-				dn->full_name);
+			pr_err("%pOF: duplicate cpu reg properties in the DT\n",
+				dn);
 			goto next;
 		}
 
@@ -640,8 +640,8 @@ static void __init of_parse_and_init_cpus(void)
 		 */
 		if (hwid == cpu_logical_map(0)) {
 			if (bootcpu_valid) {
-				pr_err("%s: duplicate boot cpu reg property in DT\n",
-					dn->full_name);
+				pr_err("%pOF: duplicate boot cpu reg property in DT\n",
+					dn);
 				goto next;
 			}
 
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 79244c75eaec..8d48b233e6ce 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -45,7 +45,7 @@ static int __init get_cpu_for_node(struct device_node *node)
 		}
 	}
 
-	pr_crit("Unable to find CPU node for %s\n", cpu_node->full_name);
+	pr_crit("Unable to find CPU node for %pOF\n", cpu_node);
 
 	of_node_put(cpu_node);
 	return -1;
@@ -71,8 +71,8 @@ static int __init parse_core(struct device_node *core, int cluster_id,
 				cpu_topology[cpu].core_id = core_id;
 				cpu_topology[cpu].thread_id = i;
 			} else {
-				pr_err("%s: Can't get CPU for thread\n",
-				       t->full_name);
+				pr_err("%pOF: Can't get CPU for thread\n",
+				       t);
 				of_node_put(t);
 				return -EINVAL;
 			}
@@ -84,15 +84,15 @@ static int __init parse_core(struct device_node *core, int cluster_id,
 	cpu = get_cpu_for_node(core);
 	if (cpu >= 0) {
 		if (!leaf) {
-			pr_err("%s: Core has both threads and CPU\n",
-			       core->full_name);
+			pr_err("%pOF: Core has both threads and CPU\n",
+			       core);
 			return -EINVAL;
 		}
 
 		cpu_topology[cpu].cluster_id = cluster_id;
 		cpu_topology[cpu].core_id = core_id;
 	} else if (leaf) {
-		pr_err("%s: Can't get CPU for leaf core\n", core->full_name);
+		pr_err("%pOF: Can't get CPU for leaf core\n", core);
 		return -EINVAL;
 	}
 
@@ -137,8 +137,8 @@ static int __init parse_cluster(struct device_node *cluster, int depth)
 			has_cores = true;
 
 			if (depth == 0) {
-				pr_err("%s: cpu-map children should be clusters\n",
-				       c->full_name);
+				pr_err("%pOF: cpu-map children should be clusters\n",
+				       c);
 				of_node_put(c);
 				return -EINVAL;
 			}
@@ -146,8 +146,8 @@ static int __init parse_cluster(struct device_node *cluster, int depth)
 			if (leaf) {
 				ret = parse_core(c, cluster_id, core_id++);
 			} else {
-				pr_err("%s: Non-leaf cluster with core %s\n",
-				       cluster->full_name, name);
+				pr_err("%pOF: Non-leaf cluster with core %s\n",
+				       cluster, name);
 				ret = -EINVAL;
 			}
 
@@ -159,7 +159,7 @@ static int __init parse_cluster(struct device_node *cluster, int depth)
 	} while (c);
 
 	if (leaf && !has_cores)
-		pr_warn("%s: empty cluster\n", cluster->full_name);
+		pr_warn("%pOF: empty cluster\n", cluster);
 
 	if (leaf)
 		cluster_id++;
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index c7c7088097be..d48f47080213 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -274,10 +274,12 @@ static DEFINE_RAW_SPINLOCK(die_lock);
 void die(const char *str, struct pt_regs *regs, int err)
 {
 	int ret;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&die_lock, flags);
 
 	oops_enter();
 
-	raw_spin_lock_irq(&die_lock);
 	console_verbose();
 	bust_spinlocks(1);
 	ret = __die(str, err, regs);
@@ -287,13 +289,15 @@ void die(const char *str, struct pt_regs *regs, int err)
 
 	bust_spinlocks(0);
 	add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
-	raw_spin_unlock_irq(&die_lock);
 	oops_exit();
 
 	if (in_interrupt())
 		panic("Fatal exception in interrupt");
 	if (panic_on_oops)
 		panic("Fatal exception");
+
+	raw_spin_unlock_irqrestore(&die_lock, flags);
+
 	if (ret != NOTIFY_STOP)
 		do_exit(SIGSEGV);
 }
diff --git a/arch/arm64/lib/copy_page.S b/arch/arm64/lib/copy_page.S
index c3cd65e31814..076c43715e64 100644
--- a/arch/arm64/lib/copy_page.S
+++ b/arch/arm64/lib/copy_page.S
@@ -30,9 +30,10 @@
  */
 ENTRY(copy_page)
 alternative_if ARM64_HAS_NO_HW_PREFETCH
-	# Prefetch two cache lines ahead.
-	prfm    pldl1strm, [x1, #128]
-	prfm    pldl1strm, [x1, #256]
+	// Prefetch three cache lines ahead.
+	prfm	pldl1strm, [x1, #128]
+	prfm	pldl1strm, [x1, #256]
+	prfm	pldl1strm, [x1, #384]
 alternative_else_nop_endif
 
 	ldp	x2, x3, [x1]
@@ -50,7 +51,7 @@ alternative_else_nop_endif
 	subs	x18, x18, #128
 
 alternative_if ARM64_HAS_NO_HW_PREFETCH
-	prfm    pldl1strm, [x1, #384]
+	prfm	pldl1strm, [x1, #384]
 alternative_else_nop_endif
 
 	stnp	x2, x3, [x0]
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 23c2d89a362e..f1eb15e0e864 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -496,7 +496,7 @@ void mark_rodata_ro(void)
 
 static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
 				      pgprot_t prot, struct vm_struct *vma,
-				      int flags)
+				      int flags, unsigned long vm_flags)
 {
 	phys_addr_t pa_start = __pa_symbol(va_start);
 	unsigned long size = va_end - va_start;
@@ -507,10 +507,13 @@ static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
 	__create_pgd_mapping(pgd, pa_start, (unsigned long)va_start, size, prot,
 			     early_pgtable_alloc, flags);
 
+	if (!(vm_flags & VM_NO_GUARD))
+		size += PAGE_SIZE;
+
 	vma->addr	= va_start;
 	vma->phys_addr	= pa_start;
 	vma->size	= size;
-	vma->flags	= VM_MAP;
+	vma->flags	= VM_MAP | vm_flags;
 	vma->caller	= __builtin_return_address(0);
 
 	vm_area_add_early(vma);
@@ -541,14 +544,15 @@ static void __init map_kernel(pgd_t *pgd)
 	 * Only rodata will be remapped with different permissions later on,
 	 * all other segments are allowed to use contiguous mappings.
 	 */
-	map_kernel_segment(pgd, _text, _etext, text_prot, &vmlinux_text, 0);
+	map_kernel_segment(pgd, _text, _etext, text_prot, &vmlinux_text, 0,
+			   VM_NO_GUARD);
 	map_kernel_segment(pgd, __start_rodata, __inittext_begin, PAGE_KERNEL,
-			   &vmlinux_rodata, NO_CONT_MAPPINGS);
+			   &vmlinux_rodata, NO_CONT_MAPPINGS, VM_NO_GUARD);
 	map_kernel_segment(pgd, __inittext_begin, __inittext_end, text_prot,
-			   &vmlinux_inittext, 0);
+			   &vmlinux_inittext, 0, VM_NO_GUARD);
 	map_kernel_segment(pgd, __initdata_begin, __initdata_end, PAGE_KERNEL,
-			   &vmlinux_initdata, 0);
-	map_kernel_segment(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data, 0);
+			   &vmlinux_initdata, 0, VM_NO_GUARD);
+	map_kernel_segment(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data, 0, 0);
 
 	if (!pgd_val(*pgd_offset_raw(pgd, FIXADDR_START))) {
 		/*
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index b388a99fea7b..dad128ba98bf 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -208,8 +208,6 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
 	}
 
 	node_set(nid, numa_nodes_parsed);
-	pr_info("Adding memblock [0x%llx - 0x%llx] on node %d\n",
-			start, (end - 1), nid);
 	return ret;
 }
 
@@ -223,10 +221,7 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
 	void *nd;
 	int tnid;
 
-	if (start_pfn < end_pfn)
-		pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n", nid,
-			start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);
-	else
+	if (start_pfn >= end_pfn)
 		pr_info("Initmem setup node %d [<memory-less node>]\n", nid);
 
 	nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index dc459eb1246b..1c5e0f333779 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -569,22 +569,41 @@ int armpmu_request_irq(struct arm_pmu *armpmu, int cpu)
 		if (irq != other_irq) {
 			pr_warn("mismatched PPIs detected.\n");
 			err = -EINVAL;
+			goto err_out;
 		}
 	} else {
-		err = request_irq(irq, handler,
-				  IRQF_NOBALANCING | IRQF_NO_THREAD, "arm-pmu",
+		struct arm_pmu_platdata *platdata = armpmu_get_platdata(armpmu);
+		unsigned long irq_flags;
+
+		err = irq_force_affinity(irq, cpumask_of(cpu));
+
+		if (err && num_possible_cpus() > 1) {
+			pr_warn("unable to set irq affinity (irq=%d, cpu=%u)\n",
+				irq, cpu);
+			goto err_out;
+		}
+
+		if (platdata && platdata->irq_flags) {
+			irq_flags = platdata->irq_flags;
+		} else {
+			irq_flags = IRQF_PERCPU |
+				    IRQF_NOBALANCING |
+				    IRQF_NO_THREAD;
+		}
+
+		err = request_irq(irq, handler, irq_flags, "arm-pmu",
 				  per_cpu_ptr(&hw_events->percpu_pmu, cpu));
 	}
 
-	if (err) {
-		pr_err("unable to request IRQ%d for ARM PMU counters\n",
-			irq);
-		return err;
-	}
+	if (err)
+		goto err_out;
 
 	cpumask_set_cpu(cpu, &armpmu->active_irqs);
-
 	return 0;
+
+err_out:
+	pr_err("unable to request IRQ%d for ARM PMU counters\n", irq);
+	return err;
 }
 
 int armpmu_request_irqs(struct arm_pmu *armpmu)
@@ -628,12 +647,6 @@ static int arm_perf_starting_cpu(unsigned int cpu, struct hlist_node *node)
 			enable_percpu_irq(irq, IRQ_TYPE_NONE);
 			return 0;
 		}
-
-		if (irq_force_affinity(irq, cpumask_of(cpu)) &&
-		    num_possible_cpus() > 1) {
-			pr_warn("unable to set irq affinity (irq=%d, cpu=%u)\n",
-				irq, cpu);
-		}
 	}
 
 	return 0;
diff --git a/drivers/perf/arm_pmu_platform.c b/drivers/perf/arm_pmu_platform.c
index 69255f53057a..4eafa7a42e52 100644
--- a/drivers/perf/arm_pmu_platform.c
+++ b/drivers/perf/arm_pmu_platform.c
@@ -131,8 +131,8 @@ static int pmu_parse_irqs(struct arm_pmu *pmu)
 	}
 
 	if (!pmu_has_irq_affinity(pdev->dev.of_node)) {
-		pr_warn("no interrupt-affinity property for %s, guessing.\n",
-			of_node_full_name(pdev->dev.of_node));
+		pr_warn("no interrupt-affinity property for %pOF, guessing.\n",
+			pdev->dev.of_node);
 	}
 
 	/*
@@ -211,7 +211,7 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 	}
 
 	if (ret) {
-		pr_info("%s: failed to probe PMU!\n", of_node_full_name(node));
+		pr_info("%pOF: failed to probe PMU!\n", node);
 		goto out_free;
 	}
 
@@ -228,8 +228,7 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 out_free_irqs:
 	armpmu_free_irqs(pmu);
 out_free:
-	pr_info("%s: failed to register PMU devices!\n",
-		of_node_full_name(node));
+	pr_info("%pOF: failed to register PMU devices!\n", node);
 	armpmu_free(pmu);
 	return ret;
 }
diff --git a/drivers/perf/qcom_l2_pmu.c b/drivers/perf/qcom_l2_pmu.c
index c259848228b4..b242cce10468 100644
--- a/drivers/perf/qcom_l2_pmu.c
+++ b/drivers/perf/qcom_l2_pmu.c
@@ -546,6 +546,7 @@ static int l2_cache_event_init(struct perf_event *event)
 	}
 
 	if ((event != event->group_leader) &&
+	    !is_software_event(event->group_leader) &&
 	    (L2_EVT_GROUP(event->group_leader->attr.config) ==
 	     L2_EVT_GROUP(event->attr.config))) {
 		dev_dbg_ratelimited(&l2cache_pmu->pdev->dev,
@@ -558,6 +559,7 @@ static int l2_cache_event_init(struct perf_event *event)
 	list_for_each_entry(sibling, &event->group_leader->sibling_list,
 			    group_entry) {
 		if ((sibling != event) &&
+		    !is_software_event(sibling) &&
 		    (L2_EVT_GROUP(sibling->attr.config) ==
 		     L2_EVT_GROUP(event->attr.config))) {
 			dev_dbg_ratelimited(&l2cache_pmu->pdev->dev,
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 1360dd6d5e61..af0f44effd44 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -24,10 +24,14 @@
  *	interrupt and passed the address of the low level handler,
  *	and can be used to implement any platform specific handling
  *	before or after calling it.
+ *
+ * @irq_flags: if non-zero, these flags will be passed to request_irq
+ *             when requesting interrupts for this PMU device.
  */
 struct arm_pmu_platdata {
 	irqreturn_t (*handle_irq)(int irq, void *dev,
 				  irq_handler_t pmu_handler);
+	unsigned long irq_flags;
 };
 
 #ifdef CONFIG_ARM_PMU