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

Pull arm64 updates from Will Deacon:
 "It's a bit all over the place this time with no "killer feature" to
  speak of.  Support for mismatched cache line sizes should help people
  seeing whacky JIT failures on some SoCs, and the big.LITTLE perf
  updates have been a long time coming, but a lot of the changes here
  are cleanups.

  We stray outside arch/arm64 in a few areas: the arch/arm/ arch_timer
  workaround is acked by Russell, the DT/OF bits are acked by Rob, the
  arch_timer clocksource changes acked by Marc, CPU hotplug by tglx and
  jump_label by Peter (all CC'd).

  Summary:

   - Support for execute-only page permissions
   - Support for hibernate and DEBUG_PAGEALLOC
   - Support for heterogeneous systems with mismatches cache line sizes
   - Errata workarounds (A53 843419 update and QorIQ A-008585 timer bug)
   - arm64 PMU perf updates, including cpumasks for heterogeneous systems
   - Set UTS_MACHINE for building rpm packages
   - Yet another head.S tidy-up
   - Some cleanups and refactoring, particularly in the NUMA code
   - Lots of random, non-critical fixes across the board"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (100 commits)
  arm64: tlbflush.h: add __tlbi() macro
  arm64: Kconfig: remove SMP dependence for NUMA
  arm64: Kconfig: select OF/ACPI_NUMA under NUMA config
  arm64: fix dump_backtrace/unwind_frame with NULL tsk
  arm/arm64: arch_timer: Use archdata to indicate vdso suitability
  arm64: arch_timer: Work around QorIQ Erratum A-008585
  arm64: arch_timer: Add device tree binding for A-008585 erratum
  arm64: Correctly bounds check virt_addr_valid
  arm64: migrate exception table users off module.h and onto extable.h
  arm64: pmu: Hoist pmu platform device name
  arm64: pmu: Probe default hw/cache counters
  arm64: pmu: add fallback probe table
  MAINTAINERS: Update ARM PMU PROFILING AND DEBUGGING entry
  arm64: Improve kprobes test for atomic sequence
  arm64/kvm: use alternative auto-nop
  arm64: use alternative auto-nop
  arm64: alternative: add auto-nop infrastructure
  arm64: lse: convert lse alternatives NOP padding to use __nops
  arm64: barriers: introduce nops and __nops macros for NOP sequences
  arm64: sysreg: replace open-coded mrs_s/msr_s with {read,write}_sysreg_s
  ...

4 files changed, 169 insertions, 54 deletions

diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 567788664723..8a753fd5b79d 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -305,6 +305,16 @@ config ARM_ARCH_TIMER_EVTSTREAM
 	  This must be disabled for hardware validation purposes to detect any
 	  hardware anomalies of missing events.
 
+config FSL_ERRATUM_A008585
+	bool "Workaround for Freescale/NXP Erratum A-008585"
+	default y
+	depends on ARM_ARCH_TIMER && ARM64
+	help
+	  This option enables a workaround for Freescale/NXP Erratum
+	  A-008585 ("ARM generic timer may contain an erroneous
+	  value").  The workaround will only be active if the
+	  fsl,erratum-a008585 property is found in the timer node.
+
 config ARM_GLOBAL_TIMER
 	bool "Support for the ARM global timer" if COMPILE_TEST
 	select CLKSRC_OF if OF
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 57700541f951..73c487da6d2a 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -94,6 +94,43 @@ early_param("clocksource.arm_arch_timer.evtstrm", early_evtstrm_cfg);
  * Architected system timer support.
  */
 
+#ifdef CONFIG_FSL_ERRATUM_A008585
+DEFINE_STATIC_KEY_FALSE(arch_timer_read_ool_enabled);
+EXPORT_SYMBOL_GPL(arch_timer_read_ool_enabled);
+
+static int fsl_a008585_enable = -1;
+
+static int __init early_fsl_a008585_cfg(char *buf)
+{
+	int ret;
+	bool val;
+
+	ret = strtobool(buf, &val);
+	if (ret)
+		return ret;
+
+	fsl_a008585_enable = val;
+	return 0;
+}
+early_param("clocksource.arm_arch_timer.fsl-a008585", early_fsl_a008585_cfg);
+
+u32 __fsl_a008585_read_cntp_tval_el0(void)
+{
+	return __fsl_a008585_read_reg(cntp_tval_el0);
+}
+
+u32 __fsl_a008585_read_cntv_tval_el0(void)
+{
+	return __fsl_a008585_read_reg(cntv_tval_el0);
+}
+
+u64 __fsl_a008585_read_cntvct_el0(void)
+{
+	return __fsl_a008585_read_reg(cntvct_el0);
+}
+EXPORT_SYMBOL(__fsl_a008585_read_cntvct_el0);
+#endif /* CONFIG_FSL_ERRATUM_A008585 */
+
 static __always_inline
 void arch_timer_reg_write(int access, enum arch_timer_reg reg, u32 val,
 			  struct clock_event_device *clk)
@@ -243,6 +280,40 @@ static __always_inline void set_next_event(const int access, unsigned long evt,
 	arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
 }
 
+#ifdef CONFIG_FSL_ERRATUM_A008585
+static __always_inline void fsl_a008585_set_next_event(const int access,
+		unsigned long evt, struct clock_event_device *clk)
+{
+	unsigned long ctrl;
+	u64 cval = evt + arch_counter_get_cntvct();
+
+	ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk);
+	ctrl |= ARCH_TIMER_CTRL_ENABLE;
+	ctrl &= ~ARCH_TIMER_CTRL_IT_MASK;
+
+	if (access == ARCH_TIMER_PHYS_ACCESS)
+		write_sysreg(cval, cntp_cval_el0);
+	else if (access == ARCH_TIMER_VIRT_ACCESS)
+		write_sysreg(cval, cntv_cval_el0);
+
+	arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
+}
+
+static int fsl_a008585_set_next_event_virt(unsigned long evt,
+					   struct clock_event_device *clk)
+{
+	fsl_a008585_set_next_event(ARCH_TIMER_VIRT_ACCESS, evt, clk);
+	return 0;
+}
+
+static int fsl_a008585_set_next_event_phys(unsigned long evt,
+					   struct clock_event_device *clk)
+{
+	fsl_a008585_set_next_event(ARCH_TIMER_PHYS_ACCESS, evt, clk);
+	return 0;
+}
+#endif /* CONFIG_FSL_ERRATUM_A008585 */
+
 static int arch_timer_set_next_event_virt(unsigned long evt,
 					  struct clock_event_device *clk)
 {
@@ -271,6 +342,19 @@ static int arch_timer_set_next_event_phys_mem(unsigned long evt,
 	return 0;
 }
 
+static void fsl_a008585_set_sne(struct clock_event_device *clk)
+{
+#ifdef CONFIG_FSL_ERRATUM_A008585
+	if (!static_branch_unlikely(&arch_timer_read_ool_enabled))
+		return;
+
+	if (arch_timer_uses_ppi == VIRT_PPI)
+		clk->set_next_event = fsl_a008585_set_next_event_virt;
+	else
+		clk->set_next_event = fsl_a008585_set_next_event_phys;
+#endif
+}
+
 static void __arch_timer_setup(unsigned type,
 			       struct clock_event_device *clk)
 {
@@ -299,6 +383,8 @@ static void __arch_timer_setup(unsigned type,
 		default:
 			BUG();
 		}
+
+		fsl_a008585_set_sne(clk);
 	} else {
 		clk->features |= CLOCK_EVT_FEAT_DYNIRQ;
 		clk->name = "arch_mem_timer";
@@ -515,15 +601,19 @@ static void __init arch_counter_register(unsigned type)
 			arch_timer_read_counter = arch_counter_get_cntvct;
 		else
 			arch_timer_read_counter = arch_counter_get_cntpct;
-	} else {
-		arch_timer_read_counter = arch_counter_get_cntvct_mem;
 
-		/* If the clocksource name is "arch_sys_counter" the
-		 * VDSO will attempt to read the CP15-based counter.
-		 * Ensure this does not happen when CP15-based
-		 * counter is not available.
+		clocksource_counter.archdata.vdso_direct = true;
+
+#ifdef CONFIG_FSL_ERRATUM_A008585
+		/*
+		 * Don't use the vdso fastpath if errata require using
+		 * the out-of-line counter accessor.
 		 */
-		clocksource_counter.name = "arch_mem_counter";
+		if (static_branch_unlikely(&arch_timer_read_ool_enabled))
+			clocksource_counter.archdata.vdso_direct = false;
+#endif
+	} else {
+		arch_timer_read_counter = arch_counter_get_cntvct_mem;
 	}
 
 	start_count = arch_timer_read_counter();
@@ -800,6 +890,15 @@ static int __init arch_timer_of_init(struct device_node *np)
 
 	arch_timer_c3stop = !of_property_read_bool(np, "always-on");
 
+#ifdef CONFIG_FSL_ERRATUM_A008585
+	if (fsl_a008585_enable < 0)
+		fsl_a008585_enable = of_property_read_bool(np, "fsl,erratum-a008585");
+	if (fsl_a008585_enable) {
+		static_branch_enable(&arch_timer_read_ool_enabled);
+		pr_info("Enabling workaround for FSL erratum A-008585\n");
+	}
+#endif
+
 	/*
 	 * If we cannot rely on firmware initializing the timer registers then
 	 * we should use the physical timers instead.
diff --git a/drivers/of/of_numa.c b/drivers/of/of_numa.c
index ed5a097f0801..f63d4b0deff0 100644
--- a/drivers/of/of_numa.c
+++ b/drivers/of/of_numa.c
@@ -16,6 +16,8 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#define pr_fmt(fmt) "OF: NUMA: " fmt
+
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/nodemask.h>
@@ -49,10 +51,9 @@ static void __init of_numa_parse_cpu_nodes(void)
 		if (r)
 			continue;
 
-		pr_debug("NUMA: CPU on %u\n", nid);
+		pr_debug("CPU on %u\n", nid);
 		if (nid >= MAX_NUMNODES)
-			pr_warn("NUMA: Node id %u exceeds maximum value\n",
-				nid);
+			pr_warn("Node id %u exceeds maximum value\n", nid);
 		else
 			node_set(nid, numa_nodes_parsed);
 	}
@@ -63,13 +64,9 @@ static int __init of_numa_parse_memory_nodes(void)
 	struct device_node *np = NULL;
 	struct resource rsrc;
 	u32 nid;
-	int r = 0;
-
-	for (;;) {
-		np = of_find_node_by_type(np, "memory");
-		if (!np)
-			break;
+	int i, r;
 
+	for_each_node_by_type(np, "memory") {
 		r = of_property_read_u32(np, "numa-node-id", &nid);
 		if (r == -EINVAL)
 			/*
@@ -78,27 +75,23 @@ static int __init of_numa_parse_memory_nodes(void)
 			 * "numa-node-id" property
 			 */
 			continue;
-		else if (r)
-			/* some other error */
-			break;
 
-		r = of_address_to_resource(np, 0, &rsrc);
-		if (r) {
-			pr_err("NUMA: bad reg property in memory node\n");
-			break;
+		if (nid >= MAX_NUMNODES) {
+			pr_warn("Node id %u exceeds maximum value\n", nid);
+			r = -EINVAL;
 		}
 
-		pr_debug("NUMA:  base = %llx len = %llx, node = %u\n",
-			 rsrc.start, rsrc.end - rsrc.start + 1, nid);
-
+		for (i = 0; !r && !of_address_to_resource(np, i, &rsrc); i++)
+			r = numa_add_memblk(nid, rsrc.start, rsrc.end + 1);
 
-		r = numa_add_memblk(nid, rsrc.start, rsrc.end + 1);
-		if (r)
-			break;
+		if (!i || r) {
+			of_node_put(np);
+			pr_err("bad property in memory node\n");
+			return r ? : -EINVAL;
+		}
 	}
-	of_node_put(np);
 
-	return r;
+	return 0;
 }
 
 static int __init of_numa_parse_distance_map_v1(struct device_node *map)
@@ -107,17 +100,17 @@ static int __init of_numa_parse_distance_map_v1(struct device_node *map)
 	int entry_count;
 	int i;
 
-	pr_info("NUMA: parsing numa-distance-map-v1\n");
+	pr_info("parsing numa-distance-map-v1\n");
 
 	matrix = of_get_property(map, "distance-matrix", NULL);
 	if (!matrix) {
-		pr_err("NUMA: No distance-matrix property in distance-map\n");
+		pr_err("No distance-matrix property in distance-map\n");
 		return -EINVAL;
 	}
 
 	entry_count = of_property_count_u32_elems(map, "distance-matrix");
 	if (entry_count <= 0) {
-		pr_err("NUMA: Invalid distance-matrix\n");
+		pr_err("Invalid distance-matrix\n");
 		return -EINVAL;
 	}
 
@@ -132,7 +125,7 @@ static int __init of_numa_parse_distance_map_v1(struct device_node *map)
 		matrix++;
 
 		numa_set_distance(nodea, nodeb, distance);
-		pr_debug("NUMA:  distance[node%d -> node%d] = %d\n",
+		pr_debug("distance[node%d -> node%d] = %d\n",
 			 nodea, nodeb, distance);
 
 		/* Set default distance of node B->A same as A->B */
@@ -166,8 +159,6 @@ int of_node_to_nid(struct device_node *device)
 	np = of_node_get(device);
 
 	while (np) {
-		struct device_node *parent;
-
 		r = of_property_read_u32(np, "numa-node-id", &nid);
 		/*
 		 * -EINVAL indicates the property was not found, and
@@ -178,22 +169,15 @@ int of_node_to_nid(struct device_node *device)
 		if (r != -EINVAL)
 			break;
 
-		parent = of_get_parent(np);
-		of_node_put(np);
-		np = parent;
+		np = of_get_next_parent(np);
 	}
 	if (np && r)
-		pr_warn("NUMA: Invalid \"numa-node-id\" property in node %s\n",
+		pr_warn("Invalid \"numa-node-id\" property in node %s\n",
 			np->name);
 	of_node_put(np);
 
-	if (!r) {
-		if (nid >= MAX_NUMNODES)
-			pr_warn("NUMA: Node id %u exceeds maximum value\n",
-				nid);
-		else
-			return nid;
-	}
+	if (!r)
+		return nid;
 
 	return NUMA_NO_NODE;
 }
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index f5e1008a223d..30370817bf13 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -534,6 +534,24 @@ static int armpmu_filter_match(struct perf_event *event)
 	return cpumask_test_cpu(cpu, &armpmu->supported_cpus);
 }
 
+static ssize_t armpmu_cpumask_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct arm_pmu *armpmu = to_arm_pmu(dev_get_drvdata(dev));
+	return cpumap_print_to_pagebuf(true, buf, &armpmu->supported_cpus);
+}
+
+static DEVICE_ATTR(cpus, S_IRUGO, armpmu_cpumask_show, NULL);
+
+static struct attribute *armpmu_common_attrs[] = {
+	&dev_attr_cpus.attr,
+	NULL,
+};
+
+static struct attribute_group armpmu_common_attr_group = {
+	.attrs = armpmu_common_attrs,
+};
+
 static void armpmu_init(struct arm_pmu *armpmu)
 {
 	atomic_set(&armpmu->active_events, 0);
@@ -549,7 +567,10 @@ static void armpmu_init(struct arm_pmu *armpmu)
 		.stop		= armpmu_stop,
 		.read		= armpmu_read,
 		.filter_match	= armpmu_filter_match,
+		.attr_groups	= armpmu->attr_groups,
 	};
+	armpmu->attr_groups[ARMPMU_ATTR_GROUP_COMMON] =
+		&armpmu_common_attr_group;
 }
 
 /* Set at runtime when we know what CPU type we are. */
@@ -602,7 +623,7 @@ static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
 	irqs = min(pmu_device->num_resources, num_possible_cpus());
 
 	irq = platform_get_irq(pmu_device, 0);
-	if (irq >= 0 && irq_is_percpu(irq)) {
+	if (irq > 0 && irq_is_percpu(irq)) {
 		on_each_cpu_mask(&cpu_pmu->supported_cpus,
 				 cpu_pmu_disable_percpu_irq, &irq, 1);
 		free_percpu_irq(irq, &hw_events->percpu_pmu);
@@ -616,7 +637,7 @@ static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
 			if (!cpumask_test_and_clear_cpu(cpu, &cpu_pmu->active_irqs))
 				continue;
 			irq = platform_get_irq(pmu_device, i);
-			if (irq >= 0)
+			if (irq > 0)
 				free_irq(irq, per_cpu_ptr(&hw_events->percpu_pmu, cpu));
 		}
 	}
@@ -638,7 +659,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 	}
 
 	irq = platform_get_irq(pmu_device, 0);
-	if (irq >= 0 && irq_is_percpu(irq)) {
+	if (irq > 0 && irq_is_percpu(irq)) {
 		err = request_percpu_irq(irq, handler, "arm-pmu",
 					 &hw_events->percpu_pmu);
 		if (err) {
@@ -919,7 +940,7 @@ static int of_pmu_irq_cfg(struct arm_pmu *pmu)
 
 		/* Check the IRQ type and prohibit a mix of PPIs and SPIs */
 		irq = platform_get_irq(pdev, i);
-		if (irq >= 0) {
+		if (irq > 0) {
 			bool spi = !irq_is_percpu(irq);
 
 			if (i > 0 && spi != using_spi) {
@@ -970,7 +991,7 @@ static int of_pmu_irq_cfg(struct arm_pmu *pmu)
 	if (cpumask_weight(&pmu->supported_cpus) == 0) {
 		int irq = platform_get_irq(pdev, 0);
 
-		if (irq >= 0 && irq_is_percpu(irq)) {
+		if (irq > 0 && irq_is_percpu(irq)) {
 			/* If using PPIs, check the affinity of the partition */
 			int ret;
 
@@ -1029,7 +1050,7 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 		ret = of_pmu_irq_cfg(pmu);
 		if (!ret)
 			ret = init_fn(pmu);
-	} else {
+	} else if (probe_table) {
 		cpumask_setall(&pmu->supported_cpus);
 		ret = probe_current_pmu(pmu, probe_table);
 	}
@@ -1039,6 +1060,7 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 		goto out_free;
 	}
 
+
 	ret = cpu_pmu_init(pmu);
 	if (ret)
 		goto out_free;