Adding upstream version 6.10.3.upstream/6.10.3

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

6 files changed, 650 insertions, 290 deletions

diff --git a/arch/powerpc/kexec/Makefile b/arch/powerpc/kexec/Makefile
index 8e469c4da3..470eb0453e 100644
--- a/arch/powerpc/kexec/Makefile
+++ b/arch/powerpc/kexec/Makefile
@@ -3,11 +3,11 @@
 # Makefile for the linux kernel.
 #
 
-obj-y				+= core.o core_$(BITS).o
+obj-y				+= core.o core_$(BITS).o ranges.o
 
 obj-$(CONFIG_PPC32)		+= relocate_32.o
 
-obj-$(CONFIG_KEXEC_FILE)	+= file_load.o ranges.o file_load_$(BITS).o elf_$(BITS).o
+obj-$(CONFIG_KEXEC_FILE)	+= file_load.o file_load_$(BITS).o elf_$(BITS).o
 obj-$(CONFIG_VMCORE_INFO)	+= vmcore_info.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash.o
 
diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c
index 27254624f6..222aa326da 100644
--- a/arch/powerpc/kexec/core_64.c
+++ b/arch/powerpc/kexec/core_64.c
@@ -17,6 +17,7 @@
 #include <linux/cpu.h>
 #include <linux/hardirq.h>
 #include <linux/of.h>
+#include <linux/libfdt.h>
 
 #include <asm/page.h>
 #include <asm/current.h>
@@ -31,6 +32,7 @@
 #include <asm/hw_breakpoint.h>
 #include <asm/svm.h>
 #include <asm/ultravisor.h>
+#include <asm/crashdump-ppc64.h>
 
 int machine_kexec_prepare(struct kimage *image)
 {
@@ -430,3 +432,113 @@ static int __init export_htab_values(void)
 }
 late_initcall(export_htab_values);
 #endif /* CONFIG_PPC_64S_HASH_MMU */
+
+#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP)
+/**
+ * add_node_props - Reads node properties from device node structure and add
+ *                  them to fdt.
+ * @fdt:            Flattened device tree of the kernel
+ * @node_offset:    offset of the node to add a property at
+ * @dn:             device node pointer
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+static int add_node_props(void *fdt, int node_offset, const struct device_node *dn)
+{
+	int ret = 0;
+	struct property *pp;
+
+	if (!dn)
+		return -EINVAL;
+
+	for_each_property_of_node(dn, pp) {
+		ret = fdt_setprop(fdt, node_offset, pp->name, pp->value, pp->length);
+		if (ret < 0) {
+			pr_err("Unable to add %s property: %s\n", pp->name, fdt_strerror(ret));
+			return ret;
+		}
+	}
+	return ret;
+}
+
+/**
+ * update_cpus_node - Update cpus node of flattened device tree using of_root
+ *                    device node.
+ * @fdt:              Flattened device tree of the kernel.
+ *
+ * Returns 0 on success, negative errno on error.
+ *
+ * Note: expecting no subnodes under /cpus/<node> with device_type == "cpu".
+ * If this changes, update this function to include them.
+ */
+int update_cpus_node(void *fdt)
+{
+	int prev_node_offset;
+	const char *device_type;
+	const struct fdt_property *prop;
+	struct device_node *cpus_node, *dn;
+	int cpus_offset, cpus_subnode_offset, ret = 0;
+
+	cpus_offset = fdt_path_offset(fdt, "/cpus");
+	if (cpus_offset < 0 && cpus_offset != -FDT_ERR_NOTFOUND) {
+		pr_err("Malformed device tree: error reading /cpus node: %s\n",
+		       fdt_strerror(cpus_offset));
+		return cpus_offset;
+	}
+
+	prev_node_offset = cpus_offset;
+	/* Delete sub-nodes of /cpus node with device_type == "cpu" */
+	for (cpus_subnode_offset = fdt_first_subnode(fdt, cpus_offset); cpus_subnode_offset >= 0;) {
+		/* Ignore nodes that do not have a device_type property or device_type != "cpu" */
+		prop = fdt_get_property(fdt, cpus_subnode_offset, "device_type", NULL);
+		if (!prop || strcmp(prop->data, "cpu")) {
+			prev_node_offset = cpus_subnode_offset;
+			goto next_node;
+		}
+
+		ret = fdt_del_node(fdt, cpus_subnode_offset);
+		if (ret < 0) {
+			pr_err("Failed to delete a cpus sub-node: %s\n", fdt_strerror(ret));
+			return ret;
+		}
+next_node:
+		if (prev_node_offset == cpus_offset)
+			cpus_subnode_offset = fdt_first_subnode(fdt, cpus_offset);
+		else
+			cpus_subnode_offset = fdt_next_subnode(fdt, prev_node_offset);
+	}
+
+	cpus_node = of_find_node_by_path("/cpus");
+	/* Fail here to avoid kexec/kdump kernel boot hung */
+	if (!cpus_node) {
+		pr_err("No /cpus node found\n");
+		return -EINVAL;
+	}
+
+	/* Add all /cpus sub-nodes of device_type == "cpu" to FDT */
+	for_each_child_of_node(cpus_node, dn) {
+		/* Ignore device nodes that do not have a device_type property
+		 * or device_type != "cpu".
+		 */
+		device_type = of_get_property(dn, "device_type", NULL);
+		if (!device_type || strcmp(device_type, "cpu"))
+			continue;
+
+		cpus_subnode_offset = fdt_add_subnode(fdt, cpus_offset, dn->full_name);
+		if (cpus_subnode_offset < 0) {
+			pr_err("Unable to add %s subnode: %s\n", dn->full_name,
+			       fdt_strerror(cpus_subnode_offset));
+			ret = cpus_subnode_offset;
+			goto out;
+		}
+
+		ret = add_node_props(fdt, cpus_subnode_offset, dn);
+		if (ret < 0)
+			goto out;
+	}
+out:
+	of_node_put(cpus_node);
+	of_node_put(dn);
+	return ret;
+}
+#endif /* CONFIG_KEXEC_FILE || CONFIG_CRASH_DUMP */
diff --git a/arch/powerpc/kexec/crash.c b/arch/powerpc/kexec/crash.c
index ef5c2d25ec..9ac3266e49 100644
--- a/arch/powerpc/kexec/crash.c
+++ b/arch/powerpc/kexec/crash.c
@@ -16,6 +16,8 @@
 #include <linux/delay.h>
 #include <linux/irq.h>
 #include <linux/types.h>
+#include <linux/libfdt.h>
+#include <linux/memory.h>
 
 #include <asm/processor.h>
 #include <asm/machdep.h>
@@ -24,6 +26,7 @@
 #include <asm/setjmp.h>
 #include <asm/debug.h>
 #include <asm/interrupt.h>
+#include <asm/kexec_ranges.h>
 
 /*
  * The primary CPU waits a while for all secondary CPUs to enter. This is to
@@ -392,3 +395,195 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
 	if (ppc_md.kexec_cpu_down)
 		ppc_md.kexec_cpu_down(1, 0);
 }
+
+#ifdef CONFIG_CRASH_HOTPLUG
+#undef pr_fmt
+#define pr_fmt(fmt) "crash hp: " fmt
+
+/*
+ * Advertise preferred elfcorehdr size to userspace via
+ * /sys/kernel/crash_elfcorehdr_size sysfs interface.
+ */
+unsigned int arch_crash_get_elfcorehdr_size(void)
+{
+	unsigned long phdr_cnt;
+
+	/* A program header for possible CPUs + vmcoreinfo */
+	phdr_cnt = num_possible_cpus() + 1;
+	if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG))
+		phdr_cnt += CONFIG_CRASH_MAX_MEMORY_RANGES;
+
+	return sizeof(struct elfhdr) + (phdr_cnt * sizeof(Elf64_Phdr));
+}
+
+/**
+ * update_crash_elfcorehdr() - Recreate the elfcorehdr and replace it with old
+ *			       elfcorehdr in the kexec segment array.
+ * @image: the active struct kimage
+ * @mn: struct memory_notify data handler
+ */
+static void update_crash_elfcorehdr(struct kimage *image, struct memory_notify *mn)
+{
+	int ret;
+	struct crash_mem *cmem = NULL;
+	struct kexec_segment *ksegment;
+	void *ptr, *mem, *elfbuf = NULL;
+	unsigned long elfsz, memsz, base_addr, size;
+
+	ksegment = &image->segment[image->elfcorehdr_index];
+	mem = (void *) ksegment->mem;
+	memsz = ksegment->memsz;
+
+	ret = get_crash_memory_ranges(&cmem);
+	if (ret) {
+		pr_err("Failed to get crash mem range\n");
+		return;
+	}
+
+	/*
+	 * The hot unplugged memory is part of crash memory ranges,
+	 * remove it here.
+	 */
+	if (image->hp_action == KEXEC_CRASH_HP_REMOVE_MEMORY) {
+		base_addr = PFN_PHYS(mn->start_pfn);
+		size = mn->nr_pages * PAGE_SIZE;
+		ret = remove_mem_range(&cmem, base_addr, size);
+		if (ret) {
+			pr_err("Failed to remove hot-unplugged memory from crash memory ranges\n");
+			goto out;
+		}
+	}
+
+	ret = crash_prepare_elf64_headers(cmem, false, &elfbuf, &elfsz);
+	if (ret) {
+		pr_err("Failed to prepare elf header\n");
+		goto out;
+	}
+
+	/*
+	 * It is unlikely that kernel hit this because elfcorehdr kexec
+	 * segment (memsz) is built with addition space to accommodate growing
+	 * number of crash memory ranges while loading the kdump kernel. It is
+	 * Just to avoid any unforeseen case.
+	 */
+	if (elfsz > memsz) {
+		pr_err("Updated crash elfcorehdr elfsz %lu > memsz %lu", elfsz, memsz);
+		goto out;
+	}
+
+	ptr = __va(mem);
+	if (ptr) {
+		/* Temporarily invalidate the crash image while it is replaced */
+		xchg(&kexec_crash_image, NULL);
+
+		/* Replace the old elfcorehdr with newly prepared elfcorehdr */
+		memcpy((void *)ptr, elfbuf, elfsz);
+
+		/* The crash image is now valid once again */
+		xchg(&kexec_crash_image, image);
+	}
+out:
+	kvfree(cmem);
+	kvfree(elfbuf);
+}
+
+/**
+ * get_fdt_index - Loop through the kexec segment array and find
+ *		   the index of the FDT segment.
+ * @image: a pointer to kexec_crash_image
+ *
+ * Returns the index of FDT segment in the kexec segment array
+ * if found; otherwise -1.
+ */
+static int get_fdt_index(struct kimage *image)
+{
+	void *ptr;
+	unsigned long mem;
+	int i, fdt_index = -1;
+
+	/* Find the FDT segment index in kexec segment array. */
+	for (i = 0; i < image->nr_segments; i++) {
+		mem = image->segment[i].mem;
+		ptr = __va(mem);
+
+		if (ptr && fdt_magic(ptr) == FDT_MAGIC) {
+			fdt_index = i;
+			break;
+		}
+	}
+
+	return fdt_index;
+}
+
+/**
+ * update_crash_fdt - updates the cpus node of the crash FDT.
+ *
+ * @image: a pointer to kexec_crash_image
+ */
+static void update_crash_fdt(struct kimage *image)
+{
+	void *fdt;
+	int fdt_index;
+
+	fdt_index = get_fdt_index(image);
+	if (fdt_index < 0) {
+		pr_err("Unable to locate FDT segment.\n");
+		return;
+	}
+
+	fdt = __va((void *)image->segment[fdt_index].mem);
+
+	/* Temporarily invalidate the crash image while it is replaced */
+	xchg(&kexec_crash_image, NULL);
+
+	/* update FDT to reflect changes in CPU resources */
+	if (update_cpus_node(fdt))
+		pr_err("Failed to update crash FDT");
+
+	/* The crash image is now valid once again */
+	xchg(&kexec_crash_image, image);
+}
+
+int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags)
+{
+#ifdef CONFIG_KEXEC_FILE
+	if (image->file_mode)
+		return 1;
+#endif
+	return kexec_flags & KEXEC_CRASH_HOTPLUG_SUPPORT;
+}
+
+/**
+ * arch_crash_handle_hotplug_event - Handle crash CPU/Memory hotplug events to update the
+ *				     necessary kexec segments based on the hotplug event.
+ * @image: a pointer to kexec_crash_image
+ * @arg: struct memory_notify handler for memory hotplug case and NULL for CPU hotplug case.
+ *
+ * Update the kdump image based on the type of hotplug event, represented by image->hp_action.
+ * CPU add: Update the FDT segment to include the newly added CPU.
+ * CPU remove: No action is needed, with the assumption that it's okay to have offline CPUs
+ *	       part of the FDT.
+ * Memory add/remove: No action is taken as this is not yet supported.
+ */
+void arch_crash_handle_hotplug_event(struct kimage *image, void *arg)
+{
+	struct memory_notify *mn;
+
+	switch (image->hp_action) {
+	case KEXEC_CRASH_HP_REMOVE_CPU:
+		return;
+
+	case KEXEC_CRASH_HP_ADD_CPU:
+		update_crash_fdt(image);
+		break;
+
+	case KEXEC_CRASH_HP_REMOVE_MEMORY:
+	case KEXEC_CRASH_HP_ADD_MEMORY:
+		mn = (struct memory_notify *)arg;
+		update_crash_elfcorehdr(image, mn);
+		return;
+	default:
+		pr_warn_once("Unknown hotplug action\n");
+	}
+}
+#endif /* CONFIG_CRASH_HOTPLUG */
diff --git a/arch/powerpc/kexec/elf_64.c b/arch/powerpc/kexec/elf_64.c
index 6d8951e8e9..214c071c58 100644
--- a/arch/powerpc/kexec/elf_64.c
+++ b/arch/powerpc/kexec/elf_64.c
@@ -116,7 +116,8 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
 	if (ret)
 		goto out_free_fdt;
 
-	fdt_pack(fdt);
+	if (!IS_ENABLED(CONFIG_CRASH_HOTPLUG) || image->type != KEXEC_TYPE_CRASH)
+		fdt_pack(fdt);
 
 	kbuf.buffer = fdt;
 	kbuf.bufsz = kbuf.memsz = fdt_totalsize(fdt);
diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c
index 1bc65de617..925a69ad24 100644
--- a/arch/powerpc/kexec/file_load_64.c
+++ b/arch/powerpc/kexec/file_load_64.c
@@ -30,6 +30,7 @@
 #include <asm/iommu.h>
 #include <asm/prom.h>
 #include <asm/plpks.h>
+#include <asm/cputhreads.h>
 
 struct umem_info {
 	__be64 *buf;		/* data buffer for usable-memory property */
@@ -48,83 +49,6 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
 };
 
 /**
- * get_exclude_memory_ranges - Get exclude memory ranges. This list includes
- *                             regions like opal/rtas, tce-table, initrd,
- *                             kernel, htab which should be avoided while
- *                             setting up kexec load segments.
- * @mem_ranges:                Range list to add the memory ranges to.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int get_exclude_memory_ranges(struct crash_mem **mem_ranges)
-{
-	int ret;
-
-	ret = add_tce_mem_ranges(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_initrd_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_htab_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_kernel_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_rtas_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_opal_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_reserved_mem_ranges(mem_ranges);
-	if (ret)
-		goto out;
-
-	/* exclude memory ranges should be sorted for easy lookup */
-	sort_memory_ranges(*mem_ranges, true);
-out:
-	if (ret)
-		pr_err("Failed to setup exclude memory ranges\n");
-	return ret;
-}
-
-/**
- * get_reserved_memory_ranges - Get reserve memory ranges. This list includes
- *                              memory regions that should be added to the
- *                              memory reserve map to ensure the region is
- *                              protected from any mischief.
- * @mem_ranges:                 Range list to add the memory ranges to.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int get_reserved_memory_ranges(struct crash_mem **mem_ranges)
-{
-	int ret;
-
-	ret = add_rtas_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_tce_mem_ranges(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_reserved_mem_ranges(mem_ranges);
-out:
-	if (ret)
-		pr_err("Failed to setup reserved memory ranges\n");
-	return ret;
-}
-
-/**
  * __locate_mem_hole_top_down - Looks top down for a large enough memory hole
  *                              in the memory regions between buf_min & buf_max
  *                              for the buffer. If found, sets kbuf->mem.
@@ -323,119 +247,6 @@ static int locate_mem_hole_bottom_up_ppc64(struct kexec_buf *kbuf,
 
 #ifdef CONFIG_CRASH_DUMP
 /**
- * get_usable_memory_ranges - Get usable memory ranges. This list includes
- *                            regions like crashkernel, opal/rtas & tce-table,
- *                            that kdump kernel could use.
- * @mem_ranges:               Range list to add the memory ranges to.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int get_usable_memory_ranges(struct crash_mem **mem_ranges)
-{
-	int ret;
-
-	/*
-	 * Early boot failure observed on guests when low memory (first memory
-	 * block?) is not added to usable memory. So, add [0, crashk_res.end]
-	 * instead of [crashk_res.start, crashk_res.end] to workaround it.
-	 * Also, crashed kernel's memory must be added to reserve map to
-	 * avoid kdump kernel from using it.
-	 */
-	ret = add_mem_range(mem_ranges, 0, crashk_res.end + 1);
-	if (ret)
-		goto out;
-
-	ret = add_rtas_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_opal_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_tce_mem_ranges(mem_ranges);
-out:
-	if (ret)
-		pr_err("Failed to setup usable memory ranges\n");
-	return ret;
-}
-
-/**
- * get_crash_memory_ranges - Get crash memory ranges. This list includes
- *                           first/crashing kernel's memory regions that
- *                           would be exported via an elfcore.
- * @mem_ranges:              Range list to add the memory ranges to.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int get_crash_memory_ranges(struct crash_mem **mem_ranges)
-{
-	phys_addr_t base, end;
-	struct crash_mem *tmem;
-	u64 i;
-	int ret;
-
-	for_each_mem_range(i, &base, &end) {
-		u64 size = end - base;
-
-		/* Skip backup memory region, which needs a separate entry */
-		if (base == BACKUP_SRC_START) {
-			if (size > BACKUP_SRC_SIZE) {
-				base = BACKUP_SRC_END + 1;
-				size -= BACKUP_SRC_SIZE;
-			} else
-				continue;
-		}
-
-		ret = add_mem_range(mem_ranges, base, size);
-		if (ret)
-			goto out;
-
-		/* Try merging adjacent ranges before reallocation attempt */
-		if ((*mem_ranges)->nr_ranges == (*mem_ranges)->max_nr_ranges)
-			sort_memory_ranges(*mem_ranges, true);
-	}
-
-	/* Reallocate memory ranges if there is no space to split ranges */
-	tmem = *mem_ranges;
-	if (tmem && (tmem->nr_ranges == tmem->max_nr_ranges)) {
-		tmem = realloc_mem_ranges(mem_ranges);
-		if (!tmem)
-			goto out;
-	}
-
-	/* Exclude crashkernel region */
-	ret = crash_exclude_mem_range(tmem, crashk_res.start, crashk_res.end);
-	if (ret)
-		goto out;
-
-	/*
-	 * FIXME: For now, stay in parity with kexec-tools but if RTAS/OPAL
-	 *        regions are exported to save their context at the time of
-	 *        crash, they should actually be backed up just like the
-	 *        first 64K bytes of memory.
-	 */
-	ret = add_rtas_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_opal_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	/* create a separate program header for the backup region */
-	ret = add_mem_range(mem_ranges, BACKUP_SRC_START, BACKUP_SRC_SIZE);
-	if (ret)
-		goto out;
-
-	sort_memory_ranges(*mem_ranges, false);
-out:
-	if (ret)
-		pr_err("Failed to setup crash memory ranges\n");
-	return ret;
-}
-
-/**
  * check_realloc_usable_mem - Reallocate buffer if it can't accommodate entries
  * @um_info:                  Usable memory buffer and ranges info.
  * @cnt:                      No. of entries to accommodate.
@@ -784,6 +595,23 @@ static void update_backup_region_phdr(struct kimage *image, Elf64_Ehdr *ehdr)
 	}
 }
 
+static unsigned int kdump_extra_elfcorehdr_size(struct crash_mem *cmem)
+{
+#if defined(CONFIG_CRASH_HOTPLUG) && defined(CONFIG_MEMORY_HOTPLUG)
+	unsigned int extra_sz = 0;
+
+	if (CONFIG_CRASH_MAX_MEMORY_RANGES > (unsigned int)PN_XNUM)
+		pr_warn("Number of Phdrs %u exceeds max\n", CONFIG_CRASH_MAX_MEMORY_RANGES);
+	else if (cmem->nr_ranges >= CONFIG_CRASH_MAX_MEMORY_RANGES)
+		pr_warn("Configured crash mem ranges may not be enough\n");
+	else
+		extra_sz = (CONFIG_CRASH_MAX_MEMORY_RANGES - cmem->nr_ranges) * sizeof(Elf64_Phdr);
+
+	return extra_sz;
+#endif
+	return 0;
+}
+
 /**
  * load_elfcorehdr_segment - Setup crash memory ranges and initialize elfcorehdr
  *                           segment needed to load kdump kernel.
@@ -815,7 +643,8 @@ static int load_elfcorehdr_segment(struct kimage *image, struct kexec_buf *kbuf)
 
 	kbuf->buffer = headers;
 	kbuf->mem = KEXEC_BUF_MEM_UNKNOWN;
-	kbuf->bufsz = kbuf->memsz = headers_sz;
+	kbuf->bufsz = headers_sz;
+	kbuf->memsz = headers_sz + kdump_extra_elfcorehdr_size(cmem);
 	kbuf->top_down = false;
 
 	ret = kexec_add_buffer(kbuf);
@@ -979,6 +808,9 @@ static unsigned int kdump_extra_fdt_size_ppc64(struct kimage *image)
 	unsigned int cpu_nodes, extra_size = 0;
 	struct device_node *dn;
 	u64 usm_entries;
+#ifdef CONFIG_CRASH_HOTPLUG
+	unsigned int possible_cpu_nodes;
+#endif
 
 	if (!IS_ENABLED(CONFIG_CRASH_DUMP) || image->type != KEXEC_TYPE_CRASH)
 		return 0;
@@ -1006,6 +838,19 @@ static unsigned int kdump_extra_fdt_size_ppc64(struct kimage *image)
 	if (cpu_nodes > boot_cpu_node_count)
 		extra_size += (cpu_nodes - boot_cpu_node_count) * cpu_node_size();
 
+#ifdef CONFIG_CRASH_HOTPLUG
+	/*
+	 * Make sure enough space is reserved to accommodate possible CPU nodes
+	 * in the crash FDT. This allows packing possible CPU nodes which are
+	 * not yet present in the system without regenerating the entire FDT.
+	 */
+	if (image->type == KEXEC_TYPE_CRASH) {
+		possible_cpu_nodes = num_possible_cpus() / threads_per_core;
+		if (possible_cpu_nodes > cpu_nodes)
+			extra_size += (possible_cpu_nodes - cpu_nodes) * cpu_node_size();
+	}
+#endif
+
 	return extra_size;
 }
 
@@ -1028,93 +873,6 @@ unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image)
 	return extra_size + kdump_extra_fdt_size_ppc64(image);
 }
 
-/**
- * add_node_props - Reads node properties from device node structure and add
- *                  them to fdt.
- * @fdt:            Flattened device tree of the kernel
- * @node_offset:    offset of the node to add a property at
- * @dn:             device node pointer
- *
- * Returns 0 on success, negative errno on error.
- */
-static int add_node_props(void *fdt, int node_offset, const struct device_node *dn)
-{
-	int ret = 0;
-	struct property *pp;
-
-	if (!dn)
-		return -EINVAL;
-
-	for_each_property_of_node(dn, pp) {
-		ret = fdt_setprop(fdt, node_offset, pp->name, pp->value, pp->length);
-		if (ret < 0) {
-			pr_err("Unable to add %s property: %s\n", pp->name, fdt_strerror(ret));
-			return ret;
-		}
-	}
-	return ret;
-}
-
-/**
- * update_cpus_node - Update cpus node of flattened device tree using of_root
- *                    device node.
- * @fdt:              Flattened device tree of the kernel.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int update_cpus_node(void *fdt)
-{
-	struct device_node *cpus_node, *dn;
-	int cpus_offset, cpus_subnode_offset, ret = 0;
-
-	cpus_offset = fdt_path_offset(fdt, "/cpus");
-	if (cpus_offset < 0 && cpus_offset != -FDT_ERR_NOTFOUND) {
-		pr_err("Malformed device tree: error reading /cpus node: %s\n",
-		       fdt_strerror(cpus_offset));
-		return cpus_offset;
-	}
-
-	if (cpus_offset > 0) {
-		ret = fdt_del_node(fdt, cpus_offset);
-		if (ret < 0) {
-			pr_err("Error deleting /cpus node: %s\n", fdt_strerror(ret));
-			return -EINVAL;
-		}
-	}
-
-	/* Add cpus node to fdt */
-	cpus_offset = fdt_add_subnode(fdt, fdt_path_offset(fdt, "/"), "cpus");
-	if (cpus_offset < 0) {
-		pr_err("Error creating /cpus node: %s\n", fdt_strerror(cpus_offset));
-		return -EINVAL;
-	}
-
-	/* Add cpus node properties */
-	cpus_node = of_find_node_by_path("/cpus");
-	ret = add_node_props(fdt, cpus_offset, cpus_node);
-	of_node_put(cpus_node);
-	if (ret < 0)
-		return ret;
-
-	/* Loop through all subnodes of cpus and add them to fdt */
-	for_each_node_by_type(dn, "cpu") {
-		cpus_subnode_offset = fdt_add_subnode(fdt, cpus_offset, dn->full_name);
-		if (cpus_subnode_offset < 0) {
-			pr_err("Unable to add %s subnode: %s\n", dn->full_name,
-			       fdt_strerror(cpus_subnode_offset));
-			ret = cpus_subnode_offset;
-			goto out;
-		}
-
-		ret = add_node_props(fdt, cpus_subnode_offset, dn);
-		if (ret < 0)
-			goto out;
-	}
-out:
-	of_node_put(dn);
-	return ret;
-}
-
 static int copy_property(void *fdt, int node_offset, const struct device_node *dn,
 			 const char *propname)
 {
diff --git a/arch/powerpc/kexec/ranges.c b/arch/powerpc/kexec/ranges.c
index 33b780049a..3702b0bdab 100644
--- a/arch/powerpc/kexec/ranges.c
+++ b/arch/powerpc/kexec/ranges.c
@@ -20,9 +20,13 @@
 #include <linux/kexec.h>
 #include <linux/of.h>
 #include <linux/slab.h>
+#include <linux/memblock.h>
+#include <linux/crash_core.h>
 #include <asm/sections.h>
 #include <asm/kexec_ranges.h>
+#include <asm/crashdump-ppc64.h>
 
+#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP)
 /**
  * get_max_nr_ranges - Get the max no. of ranges crash_mem structure
  *                     could hold, given the size allocated for it.
@@ -234,13 +238,16 @@ int add_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size)
 	return __add_mem_range(mem_ranges, base, size);
 }
 
+#endif /* CONFIG_KEXEC_FILE || CONFIG_CRASH_DUMP */
+
+#ifdef CONFIG_KEXEC_FILE
 /**
  * add_tce_mem_ranges - Adds tce-table range to the given memory ranges list.
  * @mem_ranges:         Range list to add the memory range(s) to.
  *
  * Returns 0 on success, negative errno on error.
  */
-int add_tce_mem_ranges(struct crash_mem **mem_ranges)
+static int add_tce_mem_ranges(struct crash_mem **mem_ranges)
 {
 	struct device_node *dn = NULL;
 	int ret = 0;
@@ -279,7 +286,7 @@ int add_tce_mem_ranges(struct crash_mem **mem_ranges)
  *
  * Returns 0 on success, negative errno on error.
  */
-int add_initrd_mem_range(struct crash_mem **mem_ranges)
+static int add_initrd_mem_range(struct crash_mem **mem_ranges)
 {
 	u64 base, end;
 	int ret;
@@ -296,7 +303,6 @@ int add_initrd_mem_range(struct crash_mem **mem_ranges)
 	return ret;
 }
 
-#ifdef CONFIG_PPC_64S_HASH_MMU
 /**
  * add_htab_mem_range - Adds htab range to the given memory ranges list,
  *                      if it exists
@@ -304,14 +310,18 @@ int add_initrd_mem_range(struct crash_mem **mem_ranges)
  *
  * Returns 0 on success, negative errno on error.
  */
-int add_htab_mem_range(struct crash_mem **mem_ranges)
+static int add_htab_mem_range(struct crash_mem **mem_ranges)
 {
+
+#ifdef CONFIG_PPC_64S_HASH_MMU
 	if (!htab_address)
 		return 0;
 
 	return add_mem_range(mem_ranges, __pa(htab_address), htab_size_bytes);
-}
+#else
+	return 0;
 #endif
+}
 
 /**
  * add_kernel_mem_range - Adds kernel text region to the given
@@ -320,18 +330,20 @@ int add_htab_mem_range(struct crash_mem **mem_ranges)
  *
  * Returns 0 on success, negative errno on error.
  */
-int add_kernel_mem_range(struct crash_mem **mem_ranges)
+static int add_kernel_mem_range(struct crash_mem **mem_ranges)
 {
 	return add_mem_range(mem_ranges, 0, __pa(_end));
 }
+#endif /* CONFIG_KEXEC_FILE */
 
+#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP)
 /**
  * add_rtas_mem_range - Adds RTAS region to the given memory ranges list.
  * @mem_ranges:         Range list to add the memory range to.
  *
  * Returns 0 on success, negative errno on error.
  */
-int add_rtas_mem_range(struct crash_mem **mem_ranges)
+static int add_rtas_mem_range(struct crash_mem **mem_ranges)
 {
 	struct device_node *dn;
 	u32 base, size;
@@ -356,7 +368,7 @@ int add_rtas_mem_range(struct crash_mem **mem_ranges)
  *
  * Returns 0 on success, negative errno on error.
  */
-int add_opal_mem_range(struct crash_mem **mem_ranges)
+static int add_opal_mem_range(struct crash_mem **mem_ranges)
 {
 	struct device_node *dn;
 	u64 base, size;
@@ -374,7 +386,9 @@ int add_opal_mem_range(struct crash_mem **mem_ranges)
 	of_node_put(dn);
 	return ret;
 }
+#endif /* CONFIG_KEXEC_FILE || CONFIG_CRASH_DUMP */
 
+#ifdef CONFIG_KEXEC_FILE
 /**
  * add_reserved_mem_ranges - Adds "/reserved-ranges" regions exported by f/w
  *                           to the given memory ranges list.
@@ -382,7 +396,7 @@ int add_opal_mem_range(struct crash_mem **mem_ranges)
  *
  * Returns 0 on success, negative errno on error.
  */
-int add_reserved_mem_ranges(struct crash_mem **mem_ranges)
+static int add_reserved_mem_ranges(struct crash_mem **mem_ranges)
 {
 	int n_mem_addr_cells, n_mem_size_cells, i, len, cells, ret = 0;
 	struct device_node *root = of_find_node_by_path("/");
@@ -412,3 +426,283 @@ int add_reserved_mem_ranges(struct crash_mem **mem_ranges)
 
 	return ret;
 }
+
+/**
+ * get_reserved_memory_ranges - Get reserve memory ranges. This list includes
+ *                              memory regions that should be added to the
+ *                              memory reserve map to ensure the region is
+ *                              protected from any mischief.
+ * @mem_ranges:                 Range list to add the memory ranges to.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+int get_reserved_memory_ranges(struct crash_mem **mem_ranges)
+{
+	int ret;
+
+	ret = add_rtas_mem_range(mem_ranges);
+	if (ret)
+		goto out;
+
+	ret = add_tce_mem_ranges(mem_ranges);
+	if (ret)
+		goto out;
+
+	ret = add_reserved_mem_ranges(mem_ranges);
+out:
+	if (ret)
+		pr_err("Failed to setup reserved memory ranges\n");
+	return ret;
+}
+
+/**
+ * get_exclude_memory_ranges - Get exclude memory ranges. This list includes
+ *                             regions like opal/rtas, tce-table, initrd,
+ *                             kernel, htab which should be avoided while
+ *                             setting up kexec load segments.
+ * @mem_ranges:                Range list to add the memory ranges to.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+int get_exclude_memory_ranges(struct crash_mem **mem_ranges)
+{
+	int ret;
+
+	ret = add_tce_mem_ranges(mem_ranges);
+	if (ret)
+		goto out;
+
+	ret = add_initrd_mem_range(mem_ranges);
+	if (ret)
+		goto out;
+
+	ret = add_htab_mem_range(mem_ranges);
+	if (ret)
+		goto out;
+
+	ret = add_kernel_mem_range(mem_ranges);
+	if (ret)
+		goto out;
+
+	ret = add_rtas_mem_range(mem_ranges);
+	if (ret)
+		goto out;
+
+	ret = add_opal_mem_range(mem_ranges);
+	if (ret)
+		goto out;
+
+	ret = add_reserved_mem_ranges(mem_ranges);
+	if (ret)
+		goto out;
+
+	/* exclude memory ranges should be sorted for easy lookup */
+	sort_memory_ranges(*mem_ranges, true);
+out:
+	if (ret)
+		pr_err("Failed to setup exclude memory ranges\n");
+	return ret;
+}
+
+#ifdef CONFIG_CRASH_DUMP
+/**
+ * get_usable_memory_ranges - Get usable memory ranges. This list includes
+ *                            regions like crashkernel, opal/rtas & tce-table,
+ *                            that kdump kernel could use.
+ * @mem_ranges:               Range list to add the memory ranges to.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+int get_usable_memory_ranges(struct crash_mem **mem_ranges)
+{
+	int ret;
+
+	/*
+	 * Early boot failure observed on guests when low memory (first memory
+	 * block?) is not added to usable memory. So, add [0, crashk_res.end]
+	 * instead of [crashk_res.start, crashk_res.end] to workaround it.
+	 * Also, crashed kernel's memory must be added to reserve map to
+	 * avoid kdump kernel from using it.
+	 */
+	ret = add_mem_range(mem_ranges, 0, crashk_res.end + 1);
+	if (ret)
+		goto out;
+
+	ret = add_rtas_mem_range(mem_ranges);
+	if (ret)
+		goto out;
+
+	ret = add_opal_mem_range(mem_ranges);
+	if (ret)
+		goto out;
+
+	ret = add_tce_mem_ranges(mem_ranges);
+out:
+	if (ret)
+		pr_err("Failed to setup usable memory ranges\n");
+	return ret;
+}
+#endif /* CONFIG_CRASH_DUMP */
+#endif /* CONFIG_KEXEC_FILE */
+
+#ifdef CONFIG_CRASH_DUMP
+/**
+ * get_crash_memory_ranges - Get crash memory ranges. This list includes
+ *                           first/crashing kernel's memory regions that
+ *                           would be exported via an elfcore.
+ * @mem_ranges:              Range list to add the memory ranges to.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+int get_crash_memory_ranges(struct crash_mem **mem_ranges)
+{
+	phys_addr_t base, end;
+	struct crash_mem *tmem;
+	u64 i;
+	int ret;
+
+	for_each_mem_range(i, &base, &end) {
+		u64 size = end - base;
+
+		/* Skip backup memory region, which needs a separate entry */
+		if (base == BACKUP_SRC_START) {
+			if (size > BACKUP_SRC_SIZE) {
+				base = BACKUP_SRC_END + 1;
+				size -= BACKUP_SRC_SIZE;
+			} else
+				continue;
+		}
+
+		ret = add_mem_range(mem_ranges, base, size);
+		if (ret)
+			goto out;
+
+		/* Try merging adjacent ranges before reallocation attempt */
+		if ((*mem_ranges)->nr_ranges == (*mem_ranges)->max_nr_ranges)
+			sort_memory_ranges(*mem_ranges, true);
+	}
+
+	/* Reallocate memory ranges if there is no space to split ranges */
+	tmem = *mem_ranges;
+	if (tmem && (tmem->nr_ranges == tmem->max_nr_ranges)) {
+		tmem = realloc_mem_ranges(mem_ranges);
+		if (!tmem)
+			goto out;
+	}
+
+	/* Exclude crashkernel region */
+	ret = crash_exclude_mem_range(tmem, crashk_res.start, crashk_res.end);
+	if (ret)
+		goto out;
+
+	/*
+	 * FIXME: For now, stay in parity with kexec-tools but if RTAS/OPAL
+	 *        regions are exported to save their context at the time of
+	 *        crash, they should actually be backed up just like the
+	 *        first 64K bytes of memory.
+	 */
+	ret = add_rtas_mem_range(mem_ranges);
+	if (ret)
+		goto out;
+
+	ret = add_opal_mem_range(mem_ranges);
+	if (ret)
+		goto out;
+
+	/* create a separate program header for the backup region */
+	ret = add_mem_range(mem_ranges, BACKUP_SRC_START, BACKUP_SRC_SIZE);
+	if (ret)
+		goto out;
+
+	sort_memory_ranges(*mem_ranges, false);
+out:
+	if (ret)
+		pr_err("Failed to setup crash memory ranges\n");
+	return ret;
+}
+
+/**
+ * remove_mem_range - Removes the given memory range from the range list.
+ * @mem_ranges:    Range list to remove the memory range to.
+ * @base:          Base address of the range to remove.
+ * @size:          Size of the memory range to remove.
+ *
+ * (Re)allocates memory, if needed.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+int remove_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size)
+{
+	u64 end;
+	int ret = 0;
+	unsigned int i;
+	u64 mstart, mend;
+	struct crash_mem *mem_rngs = *mem_ranges;
+
+	if (!size)
+		return 0;
+
+	/*
+	 * Memory range are stored as start and end address, use
+	 * the same format to do remove operation.
+	 */
+	end = base + size - 1;
+
+	for (i = 0; i < mem_rngs->nr_ranges; i++) {
+		mstart = mem_rngs->ranges[i].start;
+		mend = mem_rngs->ranges[i].end;
+
+		/*
+		 * Memory range to remove is not part of this range entry
+		 * in the memory range list
+		 */
+		if (!(base >= mstart && end <= mend))
+			continue;
+
+		/*
+		 * Memory range to remove is equivalent to this entry in the
+		 * memory range list. Remove the range entry from the list.
+		 */
+		if (base == mstart && end == mend) {
+			for (; i < mem_rngs->nr_ranges - 1; i++) {
+				mem_rngs->ranges[i].start = mem_rngs->ranges[i+1].start;
+				mem_rngs->ranges[i].end = mem_rngs->ranges[i+1].end;
+			}
+			mem_rngs->nr_ranges--;
+			goto out;
+		}
+		/*
+		 * Start address of the memory range to remove and the
+		 * current memory range entry in the list is same. Just
+		 * move the start address of the current memory range
+		 * entry in the list to end + 1.
+		 */
+		else if (base == mstart) {
+			mem_rngs->ranges[i].start = end + 1;
+			goto out;
+		}
+		/*
+		 * End address of the memory range to remove and the
+		 * current memory range entry in the list is same.
+		 * Just move the end address of the current memory
+		 * range entry in the list to base - 1.
+		 */
+		else if (end == mend)  {
+			mem_rngs->ranges[i].end = base - 1;
+			goto out;
+		}
+		/*
+		 * Memory range to remove is not at the edge of current
+		 * memory range entry. Split the current memory entry into
+		 * two half.
+		 */
+		else {
+			mem_rngs->ranges[i].end = base - 1;
+			size = mem_rngs->ranges[i].end - end;
+			ret = add_mem_range(mem_ranges, end + 1, size);
+		}
+	}
+out:
+	return ret;
+}
+#endif /* CONFIG_CRASH_DUMP */