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

Pull arm64 updates from Catalin Marinas:

 - VMAP_STACK support, allowing the kernel stacks to be allocated in the
   vmalloc space with a guard page for trapping stack overflows. One of
   the patches introduces THREAD_ALIGN and changes the generic
   alloc_thread_stack_node() to use this instead of THREAD_SIZE (no
   functional change for other architectures)

 - Contiguous PTE hugetlb support re-enabled (after being reverted a
   couple of times). We now have the semantics agreed in the generic mm
   layer together with API improvements so that the architecture code
   can detect between contiguous and non-contiguous huge PTEs

 - Initial support for persistent memory on ARM: DC CVAP instruction
   exposed to user space (HWCAP) and the in-kernel pmem API implemented

 - raid6 improvements for arm64: faster algorithm for the delta syndrome
   and implementation of the recovery routines using Neon

 - FP/SIMD refactoring and removal of support for Neon in interrupt
   context. This is in preparation for full SVE support

 - PTE accessors converted from inline asm to cmpxchg so that we can use
   LSE atomics if available (ARMv8.1)

 - Perf support for Cortex-A35 and A73

 - Non-urgent fixes and cleanups

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (75 commits)
  arm64: cleanup {COMPAT_,}SET_PERSONALITY() macro
  arm64: introduce separated bits for mm_context_t flags
  arm64: hugetlb: Cleanup setup_hugepagesz
  arm64: Re-enable support for contiguous hugepages
  arm64: hugetlb: Override set_huge_swap_pte_at() to support contiguous hugepages
  arm64: hugetlb: Override huge_pte_clear() to support contiguous hugepages
  arm64: hugetlb: Handle swap entries in huge_pte_offset() for contiguous hugepages
  arm64: hugetlb: Add break-before-make logic for contiguous entries
  arm64: hugetlb: Spring clean huge pte accessors
  arm64: hugetlb: Introduce pte_pgprot helper
  arm64: hugetlb: set_huge_pte_at Add WARN_ON on !pte_present
  arm64: kexec: have own crash_smp_send_stop() for crash dump for nonpanic cores
  arm64: dma-mapping: Mark atomic_pool as __ro_after_init
  arm64: dma-mapping: Do not pass data to gen_pool_set_algo()
  arm64: Remove the !CONFIG_ARM64_HW_AFDBM alternative code paths
  arm64: Ignore hardware dirty bit updates in ptep_set_wrprotect()
  arm64: Move PTE_RDONLY bit handling out of set_pte_at()
  kvm: arm64: Convert kvm_set_s2pte_readonly() from inline asm to cmpxchg()
  arm64: Convert pte handling from inline asm to using (cmp)xchg
  arm64: neon/efi: Make EFI fpsimd save/restore variables static
  ...

4 files changed, 119 insertions, 107 deletions

diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index a3215ee671c1..736783c67ea0 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -588,7 +588,8 @@ void acpi_configure_pmsi_domain(struct device *dev)
 		dev_set_msi_domain(dev, msi_domain);
 }
 
-static int __get_pci_rid(struct pci_dev *pdev, u16 alias, void *data)
+static int __maybe_unused __get_pci_rid(struct pci_dev *pdev, u16 alias,
+					void *data)
 {
 	u32 *rid = data;
 
@@ -633,8 +634,7 @@ int iort_add_device_replay(const struct iommu_ops *ops, struct device *dev)
 {
 	int err = 0;
 
-	if (!IS_ERR_OR_NULL(ops) && ops->add_device && dev->bus &&
-	    !dev->iommu_group)
+	if (ops->add_device && dev->bus && !dev->iommu_group)
 		err = ops->add_device(dev);
 
 	return err;
@@ -648,36 +648,49 @@ int iort_add_device_replay(const struct iommu_ops *ops, struct device *dev)
 { return 0; }
 #endif
 
-static const struct iommu_ops *iort_iommu_xlate(struct device *dev,
-					struct acpi_iort_node *node,
-					u32 streamid)
+static int iort_iommu_xlate(struct device *dev, struct acpi_iort_node *node,
+			    u32 streamid)
 {
-	const struct iommu_ops *ops = NULL;
-	int ret = -ENODEV;
+	const struct iommu_ops *ops;
 	struct fwnode_handle *iort_fwnode;
 
-	if (node) {
-		iort_fwnode = iort_get_fwnode(node);
-		if (!iort_fwnode)
-			return NULL;
+	if (!node)
+		return -ENODEV;
 
-		ops = iommu_ops_from_fwnode(iort_fwnode);
-		/*
-		 * If the ops look-up fails, this means that either
-		 * the SMMU drivers have not been probed yet or that
-		 * the SMMU drivers are not built in the kernel;
-		 * Depending on whether the SMMU drivers are built-in
-		 * in the kernel or not, defer the IOMMU configuration
-		 * or just abort it.
-		 */
-		if (!ops)
-			return iort_iommu_driver_enabled(node->type) ?
-			       ERR_PTR(-EPROBE_DEFER) : NULL;
+	iort_fwnode = iort_get_fwnode(node);
+	if (!iort_fwnode)
+		return -ENODEV;
 
-		ret = arm_smmu_iort_xlate(dev, streamid, iort_fwnode, ops);
-	}
+	/*
+	 * If the ops look-up fails, this means that either
+	 * the SMMU drivers have not been probed yet or that
+	 * the SMMU drivers are not built in the kernel;
+	 * Depending on whether the SMMU drivers are built-in
+	 * in the kernel or not, defer the IOMMU configuration
+	 * or just abort it.
+	 */
+	ops = iommu_ops_from_fwnode(iort_fwnode);
+	if (!ops)
+		return iort_iommu_driver_enabled(node->type) ?
+		       -EPROBE_DEFER : -ENODEV;
 
-	return ret ? NULL : ops;
+	return arm_smmu_iort_xlate(dev, streamid, iort_fwnode, ops);
+}
+
+struct iort_pci_alias_info {
+	struct device *dev;
+	struct acpi_iort_node *node;
+};
+
+static int iort_pci_iommu_init(struct pci_dev *pdev, u16 alias, void *data)
+{
+	struct iort_pci_alias_info *info = data;
+	struct acpi_iort_node *parent;
+	u32 streamid;
+
+	parent = iort_node_map_id(info->node, alias, &streamid,
+				  IORT_IOMMU_TYPE);
+	return iort_iommu_xlate(info->dev, parent, streamid);
 }
 
 /**
@@ -713,9 +726,9 @@ void iort_set_dma_mask(struct device *dev)
 const struct iommu_ops *iort_iommu_configure(struct device *dev)
 {
 	struct acpi_iort_node *node, *parent;
-	const struct iommu_ops *ops = NULL;
+	const struct iommu_ops *ops;
 	u32 streamid = 0;
-	int err;
+	int err = -ENODEV;
 
 	/*
 	 * If we already translated the fwspec there
@@ -727,21 +740,16 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev)
 
 	if (dev_is_pci(dev)) {
 		struct pci_bus *bus = to_pci_dev(dev)->bus;
-		u32 rid;
-
-		pci_for_each_dma_alias(to_pci_dev(dev), __get_pci_rid,
-				       &rid);
+		struct iort_pci_alias_info info = { .dev = dev };
 
 		node = iort_scan_node(ACPI_IORT_NODE_PCI_ROOT_COMPLEX,
 				      iort_match_node_callback, &bus->dev);
 		if (!node)
 			return NULL;
 
-		parent = iort_node_map_id(node, rid, &streamid,
-					  IORT_IOMMU_TYPE);
-
-		ops = iort_iommu_xlate(dev, parent, streamid);
-
+		info.node = node;
+		err = pci_for_each_dma_alias(to_pci_dev(dev),
+					     iort_pci_iommu_init, &info);
 	} else {
 		int i = 0;
 
@@ -750,31 +758,30 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev)
 		if (!node)
 			return NULL;
 
-		parent = iort_node_map_platform_id(node, &streamid,
-						   IORT_IOMMU_TYPE, i++);
-
-		while (parent) {
-			ops = iort_iommu_xlate(dev, parent, streamid);
-			if (IS_ERR_OR_NULL(ops))
-				return ops;
-
+		do {
 			parent = iort_node_map_platform_id(node, &streamid,
 							   IORT_IOMMU_TYPE,
 							   i++);
-		}
+
+			if (parent)
+				err = iort_iommu_xlate(dev, parent, streamid);
+		} while (parent && !err);
 	}
 
 	/*
 	 * If we have reason to believe the IOMMU driver missed the initial
 	 * add_device callback for dev, replay it to get things in order.
 	 */
-	err = iort_add_device_replay(ops, dev);
-	if (err)
-		ops = ERR_PTR(err);
+	if (!err) {
+		ops = iort_fwspec_iommu_ops(dev->iommu_fwspec);
+		err = iort_add_device_replay(ops, dev);
+	}
 
 	/* Ignore all other errors apart from EPROBE_DEFER */
-	if (IS_ERR(ops) && (PTR_ERR(ops) != -EPROBE_DEFER)) {
-		dev_dbg(dev, "Adding to IOMMU failed: %ld\n", PTR_ERR(ops));
+	if (err == -EPROBE_DEFER) {
+		ops = ERR_PTR(err);
+	} else if (err) {
+		dev_dbg(dev, "Adding to IOMMU failed: %d\n", err);
 		ops = NULL;
 	}
 
@@ -908,6 +915,27 @@ static bool __init arm_smmu_v3_is_coherent(struct acpi_iort_node *node)
 	return smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE;
 }
 
+#if defined(CONFIG_ACPI_NUMA) && defined(ACPI_IORT_SMMU_V3_PXM_VALID)
+/*
+ * set numa proximity domain for smmuv3 device
+ */
+static void  __init arm_smmu_v3_set_proximity(struct device *dev,
+					      struct acpi_iort_node *node)
+{
+	struct acpi_iort_smmu_v3 *smmu;
+
+	smmu = (struct acpi_iort_smmu_v3 *)node->node_data;
+	if (smmu->flags & ACPI_IORT_SMMU_V3_PXM_VALID) {
+		set_dev_node(dev, acpi_map_pxm_to_node(smmu->pxm));
+		pr_info("SMMU-v3[%llx] Mapped to Proximity domain %d\n",
+			smmu->base_address,
+			smmu->pxm);
+	}
+}
+#else
+#define arm_smmu_v3_set_proximity NULL
+#endif
+
 static int __init arm_smmu_count_resources(struct acpi_iort_node *node)
 {
 	struct acpi_iort_smmu *smmu;
@@ -977,13 +1005,16 @@ struct iort_iommu_config {
 	int (*iommu_count_resources)(struct acpi_iort_node *node);
 	void (*iommu_init_resources)(struct resource *res,
 				     struct acpi_iort_node *node);
+	void (*iommu_set_proximity)(struct device *dev,
+				    struct acpi_iort_node *node);
 };
 
 static const struct iort_iommu_config iort_arm_smmu_v3_cfg __initconst = {
 	.name = "arm-smmu-v3",
 	.iommu_is_coherent = arm_smmu_v3_is_coherent,
 	.iommu_count_resources = arm_smmu_v3_count_resources,
-	.iommu_init_resources = arm_smmu_v3_init_resources
+	.iommu_init_resources = arm_smmu_v3_init_resources,
+	.iommu_set_proximity = arm_smmu_v3_set_proximity,
 };
 
 static const struct iort_iommu_config iort_arm_smmu_cfg __initconst = {
@@ -1028,6 +1059,9 @@ static int __init iort_add_smmu_platform_device(struct acpi_iort_node *node)
 	if (!pdev)
 		return -ENOMEM;
 
+	if (ops->iommu_set_proximity)
+		ops->iommu_set_proximity(&pdev->dev, node);
+
 	count = ops->iommu_count_resources(node);
 
 	r = kcalloc(count, sizeof(*r), GFP_KERNEL);
diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c
index b4c2589d7c91..af6ae95a5e34 100644
--- a/drivers/firmware/efi/libstub/arm64-stub.c
+++ b/drivers/firmware/efi/libstub/arm64-stub.c
@@ -11,6 +11,7 @@
  */
 #include <linux/efi.h>
 #include <asm/efi.h>
+#include <asm/memory.h>
 #include <asm/sections.h>
 #include <asm/sysreg.h>
 
@@ -81,9 +82,10 @@ efi_status_t handle_kernel_image(efi_system_table_t *sys_table_arg,
 		/*
 		 * If CONFIG_DEBUG_ALIGN_RODATA is not set, produce a
 		 * displacement in the interval [0, MIN_KIMG_ALIGN) that
-		 * is a multiple of the minimal segment alignment (SZ_64K)
+		 * doesn't violate this kernel's de-facto alignment
+		 * constraints.
 		 */
-		u32 mask = (MIN_KIMG_ALIGN - 1) & ~(SZ_64K - 1);
+		u32 mask = (MIN_KIMG_ALIGN - 1) & ~(EFI_KIMG_ALIGN - 1);
 		u32 offset = !IS_ENABLED(CONFIG_DEBUG_ALIGN_RODATA) ?
 			     (phys_seed >> 32) & mask : TEXT_OFFSET;
 
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 1c5e0f333779..d14fc2e67f93 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -47,6 +47,9 @@ armpmu_map_cache_event(const unsigned (*cache_map)
 	if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
 		return -EINVAL;
 
+	if (!cache_map)
+		return -ENOENT;
+
 	ret = (int)(*cache_map)[cache_type][cache_op][cache_result];
 
 	if (ret == CACHE_OP_UNSUPPORTED)
@@ -63,6 +66,9 @@ armpmu_map_hw_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
 	if (config >= PERF_COUNT_HW_MAX)
 		return -EINVAL;
 
+	if (!event_map)
+		return -ENOENT;
+
 	mapping = (*event_map)[config];
 	return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
 }
diff --git a/drivers/perf/xgene_pmu.c b/drivers/perf/xgene_pmu.c
index e841282d690c..eb23311bc70c 100644
--- a/drivers/perf/xgene_pmu.c
+++ b/drivers/perf/xgene_pmu.c
@@ -1147,7 +1147,6 @@ xgene_pmu_dev_add(struct xgene_pmu *xgene_pmu, struct xgene_pmu_dev_ctx *ctx)
 {
 	struct device *dev = xgene_pmu->dev;
 	struct xgene_pmu_dev *pmu;
-	int rc;
 
 	pmu = devm_kzalloc(dev, sizeof(*pmu), GFP_KERNEL);
 	if (!pmu)
@@ -1159,7 +1158,7 @@ xgene_pmu_dev_add(struct xgene_pmu *xgene_pmu, struct xgene_pmu_dev_ctx *ctx)
 	switch (pmu->inf->type) {
 	case PMU_TYPE_L3C:
 		if (!(xgene_pmu->l3c_active_mask & pmu->inf->enable_mask))
-			goto dev_err;
+			return -ENODEV;
 		if (xgene_pmu->version == PCP_PMU_V3)
 			pmu->attr_groups = l3c_pmu_v3_attr_groups;
 		else
@@ -1177,7 +1176,7 @@ xgene_pmu_dev_add(struct xgene_pmu *xgene_pmu, struct xgene_pmu_dev_ctx *ctx)
 		break;
 	case PMU_TYPE_MCB:
 		if (!(xgene_pmu->mcb_active_mask & pmu->inf->enable_mask))
-			goto dev_err;
+			return -ENODEV;
 		if (xgene_pmu->version == PCP_PMU_V3)
 			pmu->attr_groups = mcb_pmu_v3_attr_groups;
 		else
@@ -1185,7 +1184,7 @@ xgene_pmu_dev_add(struct xgene_pmu *xgene_pmu, struct xgene_pmu_dev_ctx *ctx)
 		break;
 	case PMU_TYPE_MC:
 		if (!(xgene_pmu->mc_active_mask & pmu->inf->enable_mask))
-			goto dev_err;
+			return -ENODEV;
 		if (xgene_pmu->version == PCP_PMU_V3)
 			pmu->attr_groups = mc_pmu_v3_attr_groups;
 		else
@@ -1195,19 +1194,14 @@ xgene_pmu_dev_add(struct xgene_pmu *xgene_pmu, struct xgene_pmu_dev_ctx *ctx)
 		return -EINVAL;
 	}
 
-	rc = xgene_init_perf(pmu, ctx->name);
-	if (rc) {
+	if (xgene_init_perf(pmu, ctx->name)) {
 		dev_err(dev, "%s PMU: Failed to init perf driver\n", ctx->name);
-		goto dev_err;
+		return -ENODEV;
 	}
 
 	dev_info(dev, "%s PMU registered\n", ctx->name);
 
-	return rc;
-
-dev_err:
-	devm_kfree(dev, pmu);
-	return -ENODEV;
+	return 0;
 }
 
 static void _xgene_pmu_isr(int irq, struct xgene_pmu_dev *pmu_dev)
@@ -1515,13 +1509,13 @@ xgene_pmu_dev_ctx *acpi_get_pmu_hw_inf(struct xgene_pmu *xgene_pmu,
 	acpi_dev_free_resource_list(&resource_list);
 	if (rc < 0) {
 		dev_err(dev, "PMU type %d: No resource address found\n", type);
-		goto err;
+		return NULL;
 	}
 
 	dev_csr = devm_ioremap_resource(dev, &res);
 	if (IS_ERR(dev_csr)) {
 		dev_err(dev, "PMU type %d: Fail to map resource\n", type);
-		goto err;
+		return NULL;
 	}
 
 	/* A PMU device node without enable-bit-index is always enabled */
@@ -1535,7 +1529,7 @@ xgene_pmu_dev_ctx *acpi_get_pmu_hw_inf(struct xgene_pmu *xgene_pmu,
 	ctx->name = xgene_pmu_dev_name(dev, type, enable_bit);
 	if (!ctx->name) {
 		dev_err(dev, "PMU type %d: Fail to get device name\n", type);
-		goto err;
+		return NULL;
 	}
 	inf = &ctx->inf;
 	inf->type = type;
@@ -1543,9 +1537,6 @@ xgene_pmu_dev_ctx *acpi_get_pmu_hw_inf(struct xgene_pmu *xgene_pmu,
 	inf->enable_mask = 1 << enable_bit;
 
 	return ctx;
-err:
-	devm_kfree(dev, ctx);
-	return NULL;
 }
 
 static const struct acpi_device_id xgene_pmu_acpi_type_match[] = {
@@ -1663,20 +1654,20 @@ xgene_pmu_dev_ctx *fdt_get_pmu_hw_inf(struct xgene_pmu *xgene_pmu,
 	void __iomem *dev_csr;
 	struct resource res;
 	int enable_bit;
-	int rc;
 
 	ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return NULL;
-	rc = of_address_to_resource(np, 0, &res);
-	if (rc < 0) {
+
+	if (of_address_to_resource(np, 0, &res) < 0) {
 		dev_err(dev, "PMU type %d: No resource address found\n", type);
-		goto err;
+		return NULL;
 	}
+
 	dev_csr = devm_ioremap_resource(dev, &res);
 	if (IS_ERR(dev_csr)) {
 		dev_err(dev, "PMU type %d: Fail to map resource\n", type);
-		goto err;
+		return NULL;
 	}
 
 	/* A PMU device node without enable-bit-index is always enabled */
@@ -1686,17 +1677,15 @@ xgene_pmu_dev_ctx *fdt_get_pmu_hw_inf(struct xgene_pmu *xgene_pmu,
 	ctx->name = xgene_pmu_dev_name(dev, type, enable_bit);
 	if (!ctx->name) {
 		dev_err(dev, "PMU type %d: Fail to get device name\n", type);
-		goto err;
+		return NULL;
 	}
+
 	inf = &ctx->inf;
 	inf->type = type;
 	inf->csr = dev_csr;
 	inf->enable_mask = 1 << enable_bit;
 
 	return ctx;
-err:
-	devm_kfree(dev, ctx);
-	return NULL;
 }
 
 static int fdt_pmu_probe_pmu_dev(struct xgene_pmu *xgene_pmu,
@@ -1868,22 +1857,20 @@ static int xgene_pmu_probe(struct platform_device *pdev)
 	xgene_pmu->pcppmu_csr = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(xgene_pmu->pcppmu_csr)) {
 		dev_err(&pdev->dev, "ioremap failed for PCP PMU resource\n");
-		rc = PTR_ERR(xgene_pmu->pcppmu_csr);
-		goto err;
+		return PTR_ERR(xgene_pmu->pcppmu_csr);
 	}
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
 		dev_err(&pdev->dev, "No IRQ resource\n");
-		rc = -EINVAL;
-		goto err;
+		return -EINVAL;
 	}
 	rc = devm_request_irq(&pdev->dev, irq, xgene_pmu_isr,
 				IRQF_NOBALANCING | IRQF_NO_THREAD,
 				dev_name(&pdev->dev), xgene_pmu);
 	if (rc) {
 		dev_err(&pdev->dev, "Could not request IRQ %d\n", irq);
-		goto err;
+		return rc;
 	}
 
 	raw_spin_lock_init(&xgene_pmu->lock);
@@ -1903,42 +1890,29 @@ static int xgene_pmu_probe(struct platform_device *pdev)
 	rc = irq_set_affinity(irq, &xgene_pmu->cpu);
 	if (rc) {
 		dev_err(&pdev->dev, "Failed to set interrupt affinity!\n");
-		goto err;
+		return rc;
 	}
 
 	/* Walk through the tree for all PMU perf devices */
 	rc = xgene_pmu_probe_pmu_dev(xgene_pmu, pdev);
 	if (rc) {
 		dev_err(&pdev->dev, "No PMU perf devices found!\n");
-		goto err;
+		return rc;
 	}
 
 	/* Enable interrupt */
 	xgene_pmu->ops->unmask_int(xgene_pmu);
 
 	return 0;
-
-err:
-	if (xgene_pmu->pcppmu_csr)
-		devm_iounmap(&pdev->dev, xgene_pmu->pcppmu_csr);
-	devm_kfree(&pdev->dev, xgene_pmu);
-
-	return rc;
 }
 
 static void
 xgene_pmu_dev_cleanup(struct xgene_pmu *xgene_pmu, struct list_head *pmus)
 {
 	struct xgene_pmu_dev_ctx *ctx;
-	struct device *dev = xgene_pmu->dev;
-	struct xgene_pmu_dev *pmu_dev;
 
 	list_for_each_entry(ctx, pmus, next) {
-		pmu_dev = ctx->pmu_dev;
-		if (pmu_dev->inf->csr)
-			devm_iounmap(dev, pmu_dev->inf->csr);
-		devm_kfree(dev, ctx);
-		devm_kfree(dev, pmu_dev);
+		perf_pmu_unregister(&ctx->pmu_dev->pmu);
 	}
 }
 
@@ -1951,10 +1925,6 @@ static int xgene_pmu_remove(struct platform_device *pdev)
 	xgene_pmu_dev_cleanup(xgene_pmu, &xgene_pmu->mcbpmus);
 	xgene_pmu_dev_cleanup(xgene_pmu, &xgene_pmu->mcpmus);
 
-	if (xgene_pmu->pcppmu_csr)
-		devm_iounmap(&pdev->dev, xgene_pmu->pcppmu_csr);
-	devm_kfree(&pdev->dev, xgene_pmu);
-
 	return 0;
 }