Merge tag 'devicetree-for-4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux

Pull devicetree updates from Rob Herring:

 - Rewrite of the unflattening code to avoid recursion and lessen the
   stack usage.

 - Rewrite of the phandle args parsing code to get rid of the fixed args
   size.  This is needed for IOMMU code.

 - Sync to latest dtc which adds more dts style checking.  These
   warnings are enabled with "W=1" compiles.

 - Tegra documentation updates related to the above warnings.

 - A bunch of spelling and other doc fixes.

 - Various vendor prefix additions.

* tag 'devicetree-for-4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux: (52 commits)
  devicetree: Add Creative Technology vendor id
  gpio: dt-bindings: add ibm,ppc4xx-gpio binding
  of/unittest: Remove unnecessary module.h header inclusion
  drivers/of: Fix build warning in populate_node()
  drivers/of: Fix depth when unflattening devicetree
  of: dynamic: changeset prop-update revert fix
  drivers/of: Export of_detach_node()
  drivers/of: Return allocated memory from of_fdt_unflatten_tree()
  drivers/of: Specify parent node in of_fdt_unflatten_tree()
  drivers/of: Rename unflatten_dt_node()
  drivers/of: Avoid recursively calling unflatten_dt_node()
  drivers/of: Split unflatten_dt_node()
  of: include errno.h in of_graph.h
  of: document refcount incrementation of of_get_cpu_node()
  Documentation: dt: soc: fix spelling mistakes
  Documentation: dt: power: fix spelling mistake
  Documentation: dt: pinctrl: fix spelling mistake
  Documentation: dt: opp: fix spelling mistake
  Documentation: dt: net: fix spelling mistakes
  Documentation: dt: mtd: fix spelling mistake
  ...

6 files changed, 411 insertions, 229 deletions

diff --git a/drivers/gpu/drm/tilcdc/tilcdc_slave_compat.c b/drivers/gpu/drm/tilcdc/tilcdc_slave_compat.c
index 106679bca6cb..f9c79dabce20 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_slave_compat.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_slave_compat.c
@@ -157,7 +157,7 @@ struct device_node * __init tilcdc_get_overlay(struct kfree_table *kft)
 	if (!overlay_data || kfree_table_add(kft, overlay_data))
 		return NULL;
 
-	of_fdt_unflatten_tree(overlay_data, &overlay);
+	of_fdt_unflatten_tree(overlay_data, NULL, &overlay);
 	if (!overlay) {
 		pr_warn("%s: Unfattening overlay tree failed\n", __func__);
 		return NULL;
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 0360919a5737..e206ce7a4e4b 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -50,7 +50,7 @@
 #include "io-pgtable.h"
 
 /* Maximum number of stream IDs assigned to a single device */
-#define MAX_MASTER_STREAMIDS		MAX_PHANDLE_ARGS
+#define MAX_MASTER_STREAMIDS		128
 
 /* Maximum number of context banks per SMMU */
 #define ARM_SMMU_MAX_CBS		128
@@ -397,6 +397,12 @@ struct arm_smmu_domain {
 	struct iommu_domain		domain;
 };
 
+struct arm_smmu_phandle_args {
+	struct device_node *np;
+	int args_count;
+	uint32_t args[MAX_MASTER_STREAMIDS];
+};
+
 static DEFINE_SPINLOCK(arm_smmu_devices_lock);
 static LIST_HEAD(arm_smmu_devices);
 
@@ -506,7 +512,7 @@ static int insert_smmu_master(struct arm_smmu_device *smmu,
 
 static int register_smmu_master(struct arm_smmu_device *smmu,
 				struct device *dev,
-				struct of_phandle_args *masterspec)
+				struct arm_smmu_phandle_args *masterspec)
 {
 	int i;
 	struct arm_smmu_master *master;
@@ -1875,7 +1881,8 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 	struct arm_smmu_device *smmu;
 	struct device *dev = &pdev->dev;
 	struct rb_node *node;
-	struct of_phandle_args masterspec;
+	struct of_phandle_iterator it;
+	struct arm_smmu_phandle_args *masterspec;
 	int num_irqs, i, err;
 
 	smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL);
@@ -1938,20 +1945,35 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 
 	i = 0;
 	smmu->masters = RB_ROOT;
-	while (!of_parse_phandle_with_args(dev->of_node, "mmu-masters",
-					   "#stream-id-cells", i,
-					   &masterspec)) {
-		err = register_smmu_master(smmu, dev, &masterspec);
+
+	err = -ENOMEM;
+	/* No need to zero the memory for masterspec */
+	masterspec = kmalloc(sizeof(*masterspec), GFP_KERNEL);
+	if (!masterspec)
+		goto out_put_masters;
+
+	of_for_each_phandle(&it, err, dev->of_node,
+			    "mmu-masters", "#stream-id-cells", 0) {
+		int count = of_phandle_iterator_args(&it, masterspec->args,
+						     MAX_MASTER_STREAMIDS);
+		masterspec->np		= of_node_get(it.node);
+		masterspec->args_count	= count;
+
+		err = register_smmu_master(smmu, dev, masterspec);
 		if (err) {
 			dev_err(dev, "failed to add master %s\n",
-				masterspec.np->name);
+				masterspec->np->name);
+			kfree(masterspec);
 			goto out_put_masters;
 		}
 
 		i++;
 	}
+
 	dev_notice(dev, "registered %d master devices\n", i);
 
+	kfree(masterspec);
+
 	parse_driver_options(smmu);
 
 	if (smmu->version == ARM_SMMU_V2 &&
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 64018ebcc861..ebf84e3b56d5 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -394,7 +394,8 @@ bool __weak arch_find_n_match_cpu_physical_id(struct device_node *cpun,
  * before booting secondary cores. This function uses arch_match_cpu_phys_id
  * which can be overridden by architecture specific implementation.
  *
- * Returns a node pointer for the logical cpu if found, else NULL.
+ * Returns a node pointer for the logical cpu with refcount incremented, use
+ * of_node_put() on it when done. Returns NULL if not found.
  */
 struct device_node *of_get_cpu_node(int cpu, unsigned int *thread)
 {
@@ -1440,106 +1441,155 @@ void of_print_phandle_args(const char *msg, const struct of_phandle_args *args)
 	printk("\n");
 }
 
-static int __of_parse_phandle_with_args(const struct device_node *np,
-					const char *list_name,
-					const char *cells_name,
-					int cell_count, int index,
-					struct of_phandle_args *out_args)
+int of_phandle_iterator_init(struct of_phandle_iterator *it,
+		const struct device_node *np,
+		const char *list_name,
+		const char *cells_name,
+		int cell_count)
 {
-	const __be32 *list, *list_end;
-	int rc = 0, size, cur_index = 0;
-	uint32_t count = 0;
-	struct device_node *node = NULL;
-	phandle phandle;
+	const __be32 *list;
+	int size;
+
+	memset(it, 0, sizeof(*it));
 
-	/* Retrieve the phandle list property */
 	list = of_get_property(np, list_name, &size);
 	if (!list)
 		return -ENOENT;
-	list_end = list + size / sizeof(*list);
 
-	/* Loop over the phandles until all the requested entry is found */
-	while (list < list_end) {
-		rc = -EINVAL;
-		count = 0;
+	it->cells_name = cells_name;
+	it->cell_count = cell_count;
+	it->parent = np;
+	it->list_end = list + size / sizeof(*list);
+	it->phandle_end = list;
+	it->cur = list;
+
+	return 0;
+}
+
+int of_phandle_iterator_next(struct of_phandle_iterator *it)
+{
+	uint32_t count = 0;
+
+	if (it->node) {
+		of_node_put(it->node);
+		it->node = NULL;
+	}
+
+	if (!it->cur || it->phandle_end >= it->list_end)
+		return -ENOENT;
+
+	it->cur = it->phandle_end;
+
+	/* If phandle is 0, then it is an empty entry with no arguments. */
+	it->phandle = be32_to_cpup(it->cur++);
+
+	if (it->phandle) {
 
 		/*
-		 * If phandle is 0, then it is an empty entry with no
-		 * arguments.  Skip forward to the next entry.
+		 * Find the provider node and parse the #*-cells property to
+		 * determine the argument length.
 		 */
-		phandle = be32_to_cpup(list++);
-		if (phandle) {
-			/*
-			 * Find the provider node and parse the #*-cells
-			 * property to determine the argument length.
-			 *
-			 * This is not needed if the cell count is hard-coded
-			 * (i.e. cells_name not set, but cell_count is set),
-			 * except when we're going to return the found node
-			 * below.
-			 */
-			if (cells_name || cur_index == index) {
-				node = of_find_node_by_phandle(phandle);
-				if (!node) {
-					pr_err("%s: could not find phandle\n",
-						np->full_name);
-					goto err;
-				}
-			}
+		it->node = of_find_node_by_phandle(it->phandle);
 
-			if (cells_name) {
-				if (of_property_read_u32(node, cells_name,
-							 &count)) {
-					pr_err("%s: could not get %s for %s\n",
-						np->full_name, cells_name,
-						node->full_name);
-					goto err;
-				}
-			} else {
-				count = cell_count;
+		if (it->cells_name) {
+			if (!it->node) {
+				pr_err("%s: could not find phandle\n",
+				       it->parent->full_name);
+				goto err;
 			}
 
-			/*
-			 * Make sure that the arguments actually fit in the
-			 * remaining property data length
-			 */
-			if (list + count > list_end) {
-				pr_err("%s: arguments longer than property\n",
-					 np->full_name);
+			if (of_property_read_u32(it->node, it->cells_name,
+						 &count)) {
+				pr_err("%s: could not get %s for %s\n",
+				       it->parent->full_name,
+				       it->cells_name,
+				       it->node->full_name);
 				goto err;
 			}
+		} else {
+			count = it->cell_count;
 		}
 
 		/*
-		 * All of the error cases above bail out of the loop, so at
+		 * Make sure that the arguments actually fit in the remaining
+		 * property data length
+		 */
+		if (it->cur + count > it->list_end) {
+			pr_err("%s: arguments longer than property\n",
+			       it->parent->full_name);
+			goto err;
+		}
+	}
+
+	it->phandle_end = it->cur + count;
+	it->cur_count = count;
+
+	return 0;
+
+err:
+	if (it->node) {
+		of_node_put(it->node);
+		it->node = NULL;
+	}
+
+	return -EINVAL;
+}
+
+int of_phandle_iterator_args(struct of_phandle_iterator *it,
+			     uint32_t *args,
+			     int size)
+{
+	int i, count;
+
+	count = it->cur_count;
+
+	if (WARN_ON(size < count))
+		count = size;
+
+	for (i = 0; i < count; i++)
+		args[i] = be32_to_cpup(it->cur++);
+
+	return count;
+}
+
+static int __of_parse_phandle_with_args(const struct device_node *np,
+					const char *list_name,
+					const char *cells_name,
+					int cell_count, int index,
+					struct of_phandle_args *out_args)
+{
+	struct of_phandle_iterator it;
+	int rc, cur_index = 0;
+
+	/* Loop over the phandles until all the requested entry is found */
+	of_for_each_phandle(&it, rc, np, list_name, cells_name, cell_count) {
+		/*
+		 * All of the error cases bail out of the loop, so at
 		 * this point, the parsing is successful. If the requested
 		 * index matches, then fill the out_args structure and return,
 		 * or return -ENOENT for an empty entry.
 		 */
 		rc = -ENOENT;
 		if (cur_index == index) {
-			if (!phandle)
+			if (!it.phandle)
 				goto err;
 
 			if (out_args) {
-				int i;
-				if (WARN_ON(count > MAX_PHANDLE_ARGS))
-					count = MAX_PHANDLE_ARGS;
-				out_args->np = node;
-				out_args->args_count = count;
-				for (i = 0; i < count; i++)
-					out_args->args[i] = be32_to_cpup(list++);
+				int c;
+
+				c = of_phandle_iterator_args(&it,
+							     out_args->args,
+							     MAX_PHANDLE_ARGS);
+				out_args->np = it.node;
+				out_args->args_count = c;
 			} else {
-				of_node_put(node);
+				of_node_put(it.node);
 			}
 
 			/* Found it! return success */
 			return 0;
 		}
 
-		of_node_put(node);
-		node = NULL;
-		list += count;
 		cur_index++;
 	}
 
@@ -1547,12 +1597,11 @@ static int __of_parse_phandle_with_args(const struct device_node *np,
 	 * Unlock node before returning result; will be one of:
 	 * -ENOENT : index is for empty phandle
 	 * -EINVAL : parsing error on data
-	 * [1..n]  : Number of phandle (count mode; when index = -1)
 	 */
-	rc = index < 0 ? cur_index : -ENOENT;
+
  err:
-	if (node)
-		of_node_put(node);
+	if (it.node)
+		of_node_put(it.node);
 	return rc;
 }
 
@@ -1684,8 +1733,20 @@ EXPORT_SYMBOL(of_parse_phandle_with_fixed_args);
 int of_count_phandle_with_args(const struct device_node *np, const char *list_name,
 				const char *cells_name)
 {
-	return __of_parse_phandle_with_args(np, list_name, cells_name, 0, -1,
-					    NULL);
+	struct of_phandle_iterator it;
+	int rc, cur_index = 0;
+
+	rc = of_phandle_iterator_init(&it, np, list_name, cells_name, 0);
+	if (rc)
+		return rc;
+
+	while ((rc = of_phandle_iterator_next(&it)) == 0)
+		cur_index += 1;
+
+	if (rc != -ENOENT)
+		return rc;
+
+	return cur_index;
 }
 EXPORT_SYMBOL(of_count_phandle_with_args);
 
diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c
index c647bd1b6903..3033fa3250dc 100644
--- a/drivers/of/dynamic.c
+++ b/drivers/of/dynamic.c
@@ -311,6 +311,7 @@ int of_detach_node(struct device_node *np)
 
 	return rc;
 }
+EXPORT_SYMBOL_GPL(of_detach_node);
 
 /**
  * of_node_release() - release a dynamically allocated node
@@ -497,6 +498,11 @@ static void __of_changeset_entry_invert(struct of_changeset_entry *ce,
 	case OF_RECONFIG_UPDATE_PROPERTY:
 		rce->old_prop = ce->prop;
 		rce->prop = ce->old_prop;
+		/* update was used but original property did not exist */
+		if (!rce->prop) {
+			rce->action = OF_RECONFIG_REMOVE_PROPERTY;
+			rce->prop = ce->prop;
+		}
 		break;
 	}
 }
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 3349d2aa6634..14f2f8c7c260 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -161,39 +161,127 @@ static void *unflatten_dt_alloc(void **mem, unsigned long size,
 	return res;
 }
 
-/**
- * unflatten_dt_node - Alloc and populate a device_node from the flat tree
- * @blob: The parent device tree blob
- * @mem: Memory chunk to use for allocating device nodes and properties
- * @poffset: pointer to node in flat tree
- * @dad: Parent struct device_node
- * @nodepp: The device_node tree created by the call
- * @fpsize: Size of the node path up at the current depth.
- * @dryrun: If true, do not allocate device nodes but still calculate needed
- * memory size
- */
-static void * unflatten_dt_node(const void *blob,
-				void *mem,
-				int *poffset,
-				struct device_node *dad,
-				struct device_node **nodepp,
-				unsigned long fpsize,
+static void populate_properties(const void *blob,
+				int offset,
+				void **mem,
+				struct device_node *np,
+				const char *nodename,
 				bool dryrun)
 {
-	const __be32 *p;
+	struct property *pp, **pprev = NULL;
+	int cur;
+	bool has_name = false;
+
+	pprev = &np->properties;
+	for (cur = fdt_first_property_offset(blob, offset);
+	     cur >= 0;
+	     cur = fdt_next_property_offset(blob, cur)) {
+		const __be32 *val;
+		const char *pname;
+		u32 sz;
+
+		val = fdt_getprop_by_offset(blob, cur, &pname, &sz);
+		if (!val) {
+			pr_warn("%s: Cannot locate property at 0x%x\n",
+				__func__, cur);
+			continue;
+		}
+
+		if (!pname) {
+			pr_warn("%s: Cannot find property name at 0x%x\n",
+				__func__, cur);
+			continue;
+		}
+
+		if (!strcmp(pname, "name"))
+			has_name = true;
+
+		pp = unflatten_dt_alloc(mem, sizeof(struct property),
+					__alignof__(struct property));
+		if (dryrun)
+			continue;
+
+		/* We accept flattened tree phandles either in
+		 * ePAPR-style "phandle" properties, or the
+		 * legacy "linux,phandle" properties.  If both
+		 * appear and have different values, things
+		 * will get weird. Don't do that.
+		 */
+		if (!strcmp(pname, "phandle") ||
+		    !strcmp(pname, "linux,phandle")) {
+			if (!np->phandle)
+				np->phandle = be32_to_cpup(val);
+		}
+
+		/* And we process the "ibm,phandle" property
+		 * used in pSeries dynamic device tree
+		 * stuff
+		 */
+		if (!strcmp(pname, "ibm,phandle"))
+			np->phandle = be32_to_cpup(val);
+
+		pp->name   = (char *)pname;
+		pp->length = sz;
+		pp->value  = (__be32 *)val;
+		*pprev     = pp;
+		pprev      = &pp->next;
+	}
+
+	/* With version 0x10 we may not have the name property,
+	 * recreate it here from the unit name if absent
+	 */
+	if (!has_name) {
+		const char *p = nodename, *ps = p, *pa = NULL;
+		int len;
+
+		while (*p) {
+			if ((*p) == '@')
+				pa = p;
+			else if ((*p) == '/')
+				ps = p + 1;
+			p++;
+		}
+
+		if (pa < ps)
+			pa = p;
+		len = (pa - ps) + 1;
+		pp = unflatten_dt_alloc(mem, sizeof(struct property) + len,
+					__alignof__(struct property));
+		if (!dryrun) {
+			pp->name   = "name";
+			pp->length = len;
+			pp->value  = pp + 1;
+			*pprev     = pp;
+			pprev      = &pp->next;
+			memcpy(pp->value, ps, len - 1);
+			((char *)pp->value)[len - 1] = 0;
+			pr_debug("fixed up name for %s -> %s\n",
+				 nodename, (char *)pp->value);
+		}
+	}
+
+	if (!dryrun)
+		*pprev = NULL;
+}
+
+static unsigned int populate_node(const void *blob,
+				  int offset,
+				  void **mem,
+				  struct device_node *dad,
+				  unsigned int fpsize,
+				  struct device_node **pnp,
+				  bool dryrun)
+{
 	struct device_node *np;
-	struct property *pp, **prev_pp = NULL;
 	const char *pathp;
 	unsigned int l, allocl;
-	static int depth;
-	int old_depth;
-	int offset;
-	int has_name = 0;
 	int new_format = 0;
 
-	pathp = fdt_get_name(blob, *poffset, &l);
-	if (!pathp)
-		return mem;
+	pathp = fdt_get_name(blob, offset, &l);
+	if (!pathp) {
+		*pnp = NULL;
+		return 0;
+	}
 
 	allocl = ++l;
 
@@ -223,7 +311,7 @@ static void * unflatten_dt_node(const void *blob,
 		}
 	}
 
-	np = unflatten_dt_alloc(&mem, sizeof(struct device_node) + allocl,
+	np = unflatten_dt_alloc(mem, sizeof(struct device_node) + allocl,
 				__alignof__(struct device_node));
 	if (!dryrun) {
 		char *fn;
@@ -246,89 +334,15 @@ static void * unflatten_dt_node(const void *blob,
 		}
 		memcpy(fn, pathp, l);
 
-		prev_pp = &np->properties;
 		if (dad != NULL) {
 			np->parent = dad;
 			np->sibling = dad->child;
 			dad->child = np;
 		}
 	}
-	/* process properties */
-	for (offset = fdt_first_property_offset(blob, *poffset);
-	     (offset >= 0);
-	     (offset = fdt_next_property_offset(blob, offset))) {
-		const char *pname;
-		u32 sz;
-
-		if (!(p = fdt_getprop_by_offset(blob, offset, &pname, &sz))) {
-			offset = -FDT_ERR_INTERNAL;
-			break;
-		}
 
-		if (pname == NULL) {
-			pr_info("Can't find property name in list !\n");
-			break;
-		}
-		if (strcmp(pname, "name") == 0)
-			has_name = 1;
-		pp = unflatten_dt_alloc(&mem, sizeof(struct property),
-					__alignof__(struct property));
-		if (!dryrun) {
-			/* We accept flattened tree phandles either in
-			 * ePAPR-style "phandle" properties, or the
-			 * legacy "linux,phandle" properties.  If both
-			 * appear and have different values, things
-			 * will get weird.  Don't do that. */
-			if ((strcmp(pname, "phandle") == 0) ||
-			    (strcmp(pname, "linux,phandle") == 0)) {
-				if (np->phandle == 0)
-					np->phandle = be32_to_cpup(p);
-			}
-			/* And we process the "ibm,phandle" property
-			 * used in pSeries dynamic device tree
-			 * stuff */
-			if (strcmp(pname, "ibm,phandle") == 0)
-				np->phandle = be32_to_cpup(p);
-			pp->name = (char *)pname;
-			pp->length = sz;
-			pp->value = (__be32 *)p;
-			*prev_pp = pp;
-			prev_pp = &pp->next;
-		}
-	}
-	/* with version 0x10 we may not have the name property, recreate
-	 * it here from the unit name if absent
-	 */
-	if (!has_name) {
-		const char *p1 = pathp, *ps = pathp, *pa = NULL;
-		int sz;
-
-		while (*p1) {
-			if ((*p1) == '@')
-				pa = p1;
-			if ((*p1) == '/')
-				ps = p1 + 1;
-			p1++;
-		}
-		if (pa < ps)
-			pa = p1;
-		sz = (pa - ps) + 1;
-		pp = unflatten_dt_alloc(&mem, sizeof(struct property) + sz,
-					__alignof__(struct property));
-		if (!dryrun) {
-			pp->name = "name";
-			pp->length = sz;
-			pp->value = pp + 1;
-			*prev_pp = pp;
-			prev_pp = &pp->next;
-			memcpy(pp->value, ps, sz - 1);
-			((char *)pp->value)[sz - 1] = 0;
-			pr_debug("fixed up name for %s -> %s\n", pathp,
-				(char *)pp->value);
-		}
-	}
+	populate_properties(blob, offset, mem, np, pathp, dryrun);
 	if (!dryrun) {
-		*prev_pp = NULL;
 		np->name = of_get_property(np, "name", NULL);
 		np->type = of_get_property(np, "device_type", NULL);
 
@@ -338,36 +352,94 @@ static void * unflatten_dt_node(const void *blob,
 			np->type = "<NULL>";
 	}
 
-	old_depth = depth;
-	*poffset = fdt_next_node(blob, *poffset, &depth);
-	if (depth < 0)
-		depth = 0;
-	while (*poffset > 0 && depth > old_depth)
-		mem = unflatten_dt_node(blob, mem, poffset, np, NULL,
-					fpsize, dryrun);
+	*pnp = np;
+	return fpsize;
+}
+
+static void reverse_nodes(struct device_node *parent)
+{
+	struct device_node *child, *next;
+
+	/* In-depth first */
+	child = parent->child;
+	while (child) {
+		reverse_nodes(child);
+
+		child = child->sibling;
+	}
+
+	/* Reverse the nodes in the child list */
+	child = parent->child;
+	parent->child = NULL;
+	while (child) {
+		next = child->sibling;
+
+		child->sibling = parent->child;
+		parent->child = child;
+		child = next;
+	}
+}
+
+/**
+ * unflatten_dt_nodes - Alloc and populate a device_node from the flat tree
+ * @blob: The parent device tree blob
+ * @mem: Memory chunk to use for allocating device nodes and properties
+ * @dad: Parent struct device_node
+ * @nodepp: The device_node tree created by the call
+ *
+ * It returns the size of unflattened device tree or error code
+ */
+static int unflatten_dt_nodes(const void *blob,
+			      void *mem,
+			      struct device_node *dad,
+			      struct device_node **nodepp)
+{
+	struct device_node *root;
+	int offset = 0, depth = 0;
+#define FDT_MAX_DEPTH	64
+	unsigned int fpsizes[FDT_MAX_DEPTH];
+	struct device_node *nps[FDT_MAX_DEPTH];
+	void *base = mem;
+	bool dryrun = !base;
 
-	if (*poffset < 0 && *poffset != -FDT_ERR_NOTFOUND)
-		pr_err("unflatten: error %d processing FDT\n", *poffset);
+	if (nodepp)
+		*nodepp = NULL;
+
+	root = dad;
+	fpsizes[depth] = dad ? strlen(of_node_full_name(dad)) : 0;
+	nps[depth] = dad;
+	for (offset = 0;
+	     offset >= 0 && depth >= 0;
+	     offset = fdt_next_node(blob, offset, &depth)) {
+		if (WARN_ON_ONCE(depth >= FDT_MAX_DEPTH))
+			continue;
+
+		fpsizes[depth+1] = populate_node(blob, offset, &mem,
+						 nps[depth],
+						 fpsizes[depth],
+						 &nps[depth+1], dryrun);
+		if (!fpsizes[depth+1])
+			return mem - base;
+
+		if (!dryrun && nodepp && !*nodepp)
+			*nodepp = nps[depth+1];
+		if (!dryrun && !root)
+			root = nps[depth+1];
+	}
+
+	if (offset < 0 && offset != -FDT_ERR_NOTFOUND) {
+		pr_err("%s: Error %d processing FDT\n", __func__, offset);
+		return -EINVAL;
+	}
 
 	/*
 	 * Reverse the child list. Some drivers assumes node order matches .dts
 	 * node order
 	 */
-	if (!dryrun && np->child) {
-		struct device_node *child = np->child;
-		np->child = NULL;
-		while (child) {
-			struct device_node *next = child->sibling;
-			child->sibling = np->child;
-			np->child = child;
-			child = next;
-		}
-	}
-
-	if (nodepp)
-		*nodepp = np;
+	if (!dryrun)
+		reverse_nodes(root);
 
-	return mem;
+	return mem - base;
 }
 
 /**
@@ -378,23 +450,27 @@ static void * unflatten_dt_node(const void *blob,
  * pointers of the nodes so the normal device-tree walking functions
  * can be used.
  * @blob: The blob to expand
+ * @dad: Parent device node
  * @mynodes: The device_node tree created by the call
  * @dt_alloc: An allocator that provides a virtual address to memory
  * for the resulting tree
+ *
+ * Returns NULL on failure or the memory chunk containing the unflattened
+ * device tree on success.
  */
-static void __unflatten_device_tree(const void *blob,
-			     struct device_node **mynodes,
-			     void * (*dt_alloc)(u64 size, u64 align))
+static void *__unflatten_device_tree(const void *blob,
+				     struct device_node *dad,
+				     struct device_node **mynodes,
+				     void *(*dt_alloc)(u64 size, u64 align))
 {
-	unsigned long size;
-	int start;
+	int size;
 	void *mem;
 
 	pr_debug(" -> unflatten_device_tree()\n");
 
 	if (!blob) {
 		pr_debug("No device tree pointer\n");
-		return;
+		return NULL;
 	}
 
 	pr_debug("Unflattening device tree:\n");
@@ -404,15 +480,16 @@ static void __unflatten_device_tree(const void *blob,
 
 	if (fdt_check_header(blob)) {
 		pr_err("Invalid device tree blob header\n");
-		return;
+		return NULL;
 	}
 
 	/* First pass, scan for size */
-	start = 0;
-	size = (unsigned long)unflatten_dt_node(blob, NULL, &start, NULL, NULL, 0, true);
-	size = ALIGN(size, 4);
+	size = unflatten_dt_nodes(blob, NULL, dad, NULL);
+	if (size < 0)
+		return NULL;
 
-	pr_debug("  size is %lx, allocating...\n", size);
+	size = ALIGN(size, 4);
+	pr_debug("  size is %d, allocating...\n", size);
 
 	/* Allocate memory for the expanded device tree */
 	mem = dt_alloc(size + 4, __alignof__(struct device_node));
@@ -423,13 +500,13 @@ static void __unflatten_device_tree(const void *blob,
 	pr_debug("  unflattening %p...\n", mem);
 
 	/* Second pass, do actual unflattening */
-	start = 0;
-	unflatten_dt_node(blob, mem, &start, NULL, mynodes, 0, false);
+	unflatten_dt_nodes(blob, mem, dad, mynodes);
 	if (be32_to_cpup(mem + size) != 0xdeadbeef)
 		pr_warning("End of tree marker overwritten: %08x\n",
 			   be32_to_cpup(mem + size));
 
 	pr_debug(" <- unflatten_device_tree()\n");
+	return mem;
 }
 
 static void *kernel_tree_alloc(u64 size, u64 align)
@@ -441,18 +518,29 @@ static DEFINE_MUTEX(of_fdt_unflatten_mutex);
 
 /**
  * of_fdt_unflatten_tree - create tree of device_nodes from flat blob
+ * @blob: Flat device tree blob
+ * @dad: Parent device node
+ * @mynodes: The device tree created by the call
  *
  * unflattens the device-tree passed by the firmware, creating the
  * tree of struct device_node. It also fills the "name" and "type"
  * pointers of the nodes so the normal device-tree walking functions
  * can be used.
+ *
+ * Returns NULL on failure or the memory chunk containing the unflattened
+ * device tree on success.
  */
-void of_fdt_unflatten_tree(const unsigned long *blob,
-			struct device_node **mynodes)
+void *of_fdt_unflatten_tree(const unsigned long *blob,
+			    struct device_node *dad,
+			    struct device_node **mynodes)
 {
+	void *mem;
+
 	mutex_lock(&of_fdt_unflatten_mutex);
-	__unflatten_device_tree(blob, mynodes, &kernel_tree_alloc);
+	mem = __unflatten_device_tree(blob, dad, mynodes, &kernel_tree_alloc);
 	mutex_unlock(&of_fdt_unflatten_mutex);
+
+	return mem;
 }
 EXPORT_SYMBOL_GPL(of_fdt_unflatten_tree);
 
@@ -969,10 +1057,16 @@ int __init early_init_dt_scan_chosen(unsigned long node, const char *uname,
 	 * is set in which case we override whatever was found earlier.
 	 */
 #ifdef CONFIG_CMDLINE
-#ifndef CONFIG_CMDLINE_FORCE
+#if defined(CONFIG_CMDLINE_EXTEND)
+	strlcat(data, " ", COMMAND_LINE_SIZE);
+	strlcat(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
+#elif defined(CONFIG_CMDLINE_FORCE)
+	strlcpy(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
+#else
+	/* No arguments from boot loader, use kernel's  cmdl*/
 	if (!((char *)data)[0])
-#endif
 		strlcpy(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
+#endif
 #endif /* CONFIG_CMDLINE */
 
 	pr_debug("Command line is: %s\n", (char*)data);
@@ -1118,7 +1212,7 @@ bool __init early_init_dt_scan(void *params)
  */
 void __init unflatten_device_tree(void)
 {
-	__unflatten_device_tree(initial_boot_params, &of_root,
+	__unflatten_device_tree(initial_boot_params, NULL, &of_root,
 				early_init_dt_alloc_memory_arch);
 
 	/* Get pointer to "/chosen" and "/aliases" nodes for use everywhere */
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index c1ebbfb79453..f34ed9310323 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -8,7 +8,6 @@
 #include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/hashtable.h>
-#include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <linux/of_irq.h>
@@ -921,7 +920,7 @@ static int __init unittest_data_add(void)
 			"not running tests\n", __func__);
 		return -ENOMEM;
 	}
-	of_fdt_unflatten_tree(unittest_data, &unittest_data_node);
+	of_fdt_unflatten_tree(unittest_data, NULL, &unittest_data_node);
 	if (!unittest_data_node) {
 		pr_warn("%s: No tree to attach; not running tests\n", __func__);
 		return -ENODATA;