8 files changed, 383 insertions, 113 deletions

diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c
index 0a725e46d017..53816dfab645 100644
--- a/drivers/acpi/numa/srat.c
+++ b/drivers/acpi/numa/srat.c
@@ -14,6 +14,7 @@
 #include <linux/errno.h>
 #include <linux/acpi.h>
 #include <linux/memblock.h>
+#include <linux/memory.h>
 #include <linux/numa.h>
 #include <linux/nodemask.h>
 #include <linux/topology.h>
@@ -429,13 +430,23 @@ static int __init acpi_parse_cfmws(union acpi_subtable_headers *header,
 {
 	struct acpi_cedt_cfmws *cfmws;
 	int *fake_pxm = arg;
-	u64 start, end;
+	u64 start, end, align;
 	int node;
+	int err;
 
 	cfmws = (struct acpi_cedt_cfmws *)header;
 	start = cfmws->base_hpa;
 	end = cfmws->base_hpa + cfmws->window_size;
 
+	/* Align memblock size to CFMW regions if possible */
+	align = 1UL << __ffs(start | end);
+	if (align >= SZ_256M) {
+		err = memory_block_advise_max_size(align);
+		if (err)
+			pr_warn("CFMWS: memblock size advise failed (%d)\n", err);
+	} else
+		pr_err("CFMWS: [BIOS BUG] base/size alignment violates spec\n");
+
 	/*
 	 * The SRAT may have already described NUMA details for all,
 	 * or a portion of, this CFMWS HPA range. Extend the memblks
@@ -453,7 +464,7 @@ static int __init acpi_parse_cfmws(union acpi_subtable_headers *header,
 		return -EINVAL;
 	}
 
-	if (numa_add_memblk(node, start, end) < 0) {
+	if (numa_add_reserved_memblk(node, start, end) < 0) {
 		/* CXL driver must handle the NUMA_NO_NODE case */
 		pr_warn("ACPI NUMA: Failed to add memblk for CFMWS node %d [mem %#llx-%#llx]\n",
 			node, start, end);
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 19469e7f88c2..ed3e69dc785c 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -110,6 +110,57 @@ static void memory_block_release(struct device *dev)
 	kfree(mem);
 }
 
+
+/* Max block size to be set by memory_block_advise_max_size */
+static unsigned long memory_block_advised_size;
+static bool memory_block_advised_size_queried;
+
+/**
+ * memory_block_advise_max_size() - advise memory hotplug on the max suggested
+ *				    block size, usually for alignment.
+ * @size: suggestion for maximum block size. must be aligned on power of 2.
+ *
+ * Early boot software (pre-allocator init) may advise archs on the max block
+ * size. This value can only decrease after initialization, as the intent is
+ * to identify the largest supported alignment for all sources.
+ *
+ * Use of this value is arch-defined, as is min/max block size.
+ *
+ * Return: 0 on success
+ *	   -EINVAL if size is 0 or not pow2 aligned
+ *	   -EBUSY if value has already been probed
+ */
+int __init memory_block_advise_max_size(unsigned long size)
+{
+	if (!size || !is_power_of_2(size))
+		return -EINVAL;
+
+	if (memory_block_advised_size_queried)
+		return -EBUSY;
+
+	if (memory_block_advised_size)
+		memory_block_advised_size = min(memory_block_advised_size, size);
+	else
+		memory_block_advised_size = size;
+
+	return 0;
+}
+
+/**
+ * memory_block_advised_max_size() - query advised max hotplug block size.
+ *
+ * After the first call, the value can never change. Callers looking for the
+ * actual block size should use memory_block_size_bytes. This interface is
+ * intended for use by arch-init when initializing the hotplug block size.
+ *
+ * Return: advised size in bytes, or 0 if never set.
+ */
+unsigned long memory_block_advised_max_size(void)
+{
+	memory_block_advised_size_queried = true;
+	return memory_block_advised_size;
+}
+
 unsigned long __weak memory_block_size_bytes(void)
 {
 	return MIN_MEMORY_BLOCK_SIZE;
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 618712071a1e..c19094481630 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -7,6 +7,7 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/memory.h>
+#include <linux/mempolicy.h>
 #include <linux/vmstat.h>
 #include <linux/notifier.h>
 #include <linux/node.h>
@@ -214,6 +215,14 @@ void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord,
 			break;
 		}
 	}
+
+	/* When setting CPU access coordinates, update mempolicy */
+	if (access == ACCESS_COORDINATE_CPU) {
+		if (mempolicy_set_node_perf(nid, coord)) {
+			pr_info("failed to set mempolicy attrs for node %d\n",
+				nid);
+		}
+	}
 }
 EXPORT_SYMBOL_GPL(node_set_perf_attrs);
 
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index fda7d8624889..94e6e9b80bf0 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -734,114 +734,19 @@ static void read_from_bdev_async(struct zram *zram, struct page *page,
 	submit_bio(bio);
 }
 
-#define PAGE_WB_SIG "page_index="
-
-#define PAGE_WRITEBACK			0
-#define HUGE_WRITEBACK			(1<<0)
-#define IDLE_WRITEBACK			(1<<1)
-#define INCOMPRESSIBLE_WRITEBACK	(1<<2)
-
-static int scan_slots_for_writeback(struct zram *zram, u32 mode,
-				    unsigned long nr_pages,
-				    unsigned long index,
-				    struct zram_pp_ctl *ctl)
+static int zram_writeback_slots(struct zram *zram, struct zram_pp_ctl *ctl)
 {
-	for (; nr_pages != 0; index++, nr_pages--) {
-		bool ok = true;
-
-		zram_slot_lock(zram, index);
-		if (!zram_allocated(zram, index))
-			goto next;
-
-		if (zram_test_flag(zram, index, ZRAM_WB) ||
-		    zram_test_flag(zram, index, ZRAM_SAME))
-			goto next;
-
-		if (mode & IDLE_WRITEBACK &&
-		    !zram_test_flag(zram, index, ZRAM_IDLE))
-			goto next;
-		if (mode & HUGE_WRITEBACK &&
-		    !zram_test_flag(zram, index, ZRAM_HUGE))
-			goto next;
-		if (mode & INCOMPRESSIBLE_WRITEBACK &&
-		    !zram_test_flag(zram, index, ZRAM_INCOMPRESSIBLE))
-			goto next;
-
-		ok = place_pp_slot(zram, ctl, index);
-next:
-		zram_slot_unlock(zram, index);
-		if (!ok)
-			break;
-	}
-
-	return 0;
-}
-
-static ssize_t writeback_store(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t len)
-{
-	struct zram *zram = dev_to_zram(dev);
-	unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
-	struct zram_pp_ctl *ctl = NULL;
+	unsigned long blk_idx = 0;
+	struct page *page = NULL;
 	struct zram_pp_slot *pps;
-	unsigned long index = 0;
-	struct bio bio;
 	struct bio_vec bio_vec;
-	struct page *page = NULL;
-	ssize_t ret = len;
-	int mode, err;
-	unsigned long blk_idx = 0;
-
-	if (sysfs_streq(buf, "idle"))
-		mode = IDLE_WRITEBACK;
-	else if (sysfs_streq(buf, "huge"))
-		mode = HUGE_WRITEBACK;
-	else if (sysfs_streq(buf, "huge_idle"))
-		mode = IDLE_WRITEBACK | HUGE_WRITEBACK;
-	else if (sysfs_streq(buf, "incompressible"))
-		mode = INCOMPRESSIBLE_WRITEBACK;
-	else {
-		if (strncmp(buf, PAGE_WB_SIG, sizeof(PAGE_WB_SIG) - 1))
-			return -EINVAL;
-
-		if (kstrtol(buf + sizeof(PAGE_WB_SIG) - 1, 10, &index) ||
-				index >= nr_pages)
-			return -EINVAL;
-
-		nr_pages = 1;
-		mode = PAGE_WRITEBACK;
-	}
-
-	down_read(&zram->init_lock);
-	if (!init_done(zram)) {
-		ret = -EINVAL;
-		goto release_init_lock;
-	}
-
-	/* Do not permit concurrent post-processing actions. */
-	if (atomic_xchg(&zram->pp_in_progress, 1)) {
-		up_read(&zram->init_lock);
-		return -EAGAIN;
-	}
-
-	if (!zram->backing_dev) {
-		ret = -ENODEV;
-		goto release_init_lock;
-	}
+	struct bio bio;
+	int ret = 0, err;
+	u32 index;
 
 	page = alloc_page(GFP_KERNEL);
-	if (!page) {
-		ret = -ENOMEM;
-		goto release_init_lock;
-	}
-
-	ctl = init_pp_ctl();
-	if (!ctl) {
-		ret = -ENOMEM;
-		goto release_init_lock;
-	}
-
-	scan_slots_for_writeback(zram, mode, nr_pages, index, ctl);
+	if (!page)
+		return -ENOMEM;
 
 	while ((pps = select_pp_slot(ctl))) {
 		spin_lock(&zram->wb_limit_lock);
@@ -929,10 +834,215 @@ next:
 
 	if (blk_idx)
 		free_block_bdev(zram, blk_idx);
-
-release_init_lock:
 	if (page)
 		__free_page(page);
+
+	return ret;
+}
+
+#define PAGE_WRITEBACK			0
+#define HUGE_WRITEBACK			(1 << 0)
+#define IDLE_WRITEBACK			(1 << 1)
+#define INCOMPRESSIBLE_WRITEBACK	(1 << 2)
+
+static int parse_page_index(char *val, unsigned long nr_pages,
+			    unsigned long *lo, unsigned long *hi)
+{
+	int ret;
+
+	ret = kstrtoul(val, 10, lo);
+	if (ret)
+		return ret;
+	if (*lo >= nr_pages)
+		return -ERANGE;
+	*hi = *lo + 1;
+	return 0;
+}
+
+static int parse_page_indexes(char *val, unsigned long nr_pages,
+			      unsigned long *lo, unsigned long *hi)
+{
+	char *delim;
+	int ret;
+
+	delim = strchr(val, '-');
+	if (!delim)
+		return -EINVAL;
+
+	*delim = 0x00;
+	ret = kstrtoul(val, 10, lo);
+	if (ret)
+		return ret;
+	if (*lo >= nr_pages)
+		return -ERANGE;
+
+	ret = kstrtoul(delim + 1, 10, hi);
+	if (ret)
+		return ret;
+	if (*hi >= nr_pages || *lo > *hi)
+		return -ERANGE;
+	*hi += 1;
+	return 0;
+}
+
+static int parse_mode(char *val, u32 *mode)
+{
+	*mode = 0;
+
+	if (!strcmp(val, "idle"))
+		*mode = IDLE_WRITEBACK;
+	if (!strcmp(val, "huge"))
+		*mode = HUGE_WRITEBACK;
+	if (!strcmp(val, "huge_idle"))
+		*mode = IDLE_WRITEBACK | HUGE_WRITEBACK;
+	if (!strcmp(val, "incompressible"))
+		*mode = INCOMPRESSIBLE_WRITEBACK;
+
+	if (*mode == 0)
+		return -EINVAL;
+	return 0;
+}
+
+static int scan_slots_for_writeback(struct zram *zram, u32 mode,
+				    unsigned long lo, unsigned long hi,
+				    struct zram_pp_ctl *ctl)
+{
+	u32 index = lo;
+
+	while (index < hi) {
+		bool ok = true;
+
+		zram_slot_lock(zram, index);
+		if (!zram_allocated(zram, index))
+			goto next;
+
+		if (zram_test_flag(zram, index, ZRAM_WB) ||
+		    zram_test_flag(zram, index, ZRAM_SAME))
+			goto next;
+
+		if (mode & IDLE_WRITEBACK &&
+		    !zram_test_flag(zram, index, ZRAM_IDLE))
+			goto next;
+		if (mode & HUGE_WRITEBACK &&
+		    !zram_test_flag(zram, index, ZRAM_HUGE))
+			goto next;
+		if (mode & INCOMPRESSIBLE_WRITEBACK &&
+		    !zram_test_flag(zram, index, ZRAM_INCOMPRESSIBLE))
+			goto next;
+
+		ok = place_pp_slot(zram, ctl, index);
+next:
+		zram_slot_unlock(zram, index);
+		if (!ok)
+			break;
+		index++;
+	}
+
+	return 0;
+}
+
+static ssize_t writeback_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t len)
+{
+	struct zram *zram = dev_to_zram(dev);
+	u64 nr_pages = zram->disksize >> PAGE_SHIFT;
+	unsigned long lo = 0, hi = nr_pages;
+	struct zram_pp_ctl *ctl = NULL;
+	char *args, *param, *val;
+	ssize_t ret = len;
+	int err, mode = 0;
+
+	down_read(&zram->init_lock);
+	if (!init_done(zram)) {
+		up_read(&zram->init_lock);
+		return -EINVAL;
+	}
+
+	/* Do not permit concurrent post-processing actions. */
+	if (atomic_xchg(&zram->pp_in_progress, 1)) {
+		up_read(&zram->init_lock);
+		return -EAGAIN;
+	}
+
+	if (!zram->backing_dev) {
+		ret = -ENODEV;
+		goto release_init_lock;
+	}
+
+	ctl = init_pp_ctl();
+	if (!ctl) {
+		ret = -ENOMEM;
+		goto release_init_lock;
+	}
+
+	args = skip_spaces(buf);
+	while (*args) {
+		args = next_arg(args, &param, &val);
+
+		/*
+		 * Workaround to support the old writeback interface.
+		 *
+		 * The old writeback interface has a minor inconsistency and
+		 * requires key=value only for page_index parameter, while the
+		 * writeback mode is a valueless parameter.
+		 *
+		 * This is not the case anymore and now all parameters are
+		 * required to have values, however, we need to support the
+		 * legacy writeback interface format so we check if we can
+		 * recognize a valueless parameter as the (legacy) writeback
+		 * mode.
+		 */
+		if (!val || !*val) {
+			err = parse_mode(param, &mode);
+			if (err) {
+				ret = err;
+				goto release_init_lock;
+			}
+
+			scan_slots_for_writeback(zram, mode, lo, hi, ctl);
+			break;
+		}
+
+		if (!strcmp(param, "type")) {
+			err = parse_mode(val, &mode);
+			if (err) {
+				ret = err;
+				goto release_init_lock;
+			}
+
+			scan_slots_for_writeback(zram, mode, lo, hi, ctl);
+			break;
+		}
+
+		if (!strcmp(param, "page_index")) {
+			err = parse_page_index(val, nr_pages, &lo, &hi);
+			if (err) {
+				ret = err;
+				goto release_init_lock;
+			}
+
+			scan_slots_for_writeback(zram, mode, lo, hi, ctl);
+			continue;
+		}
+
+		if (!strcmp(param, "page_indexes")) {
+			err = parse_page_indexes(val, nr_pages, &lo, &hi);
+			if (err) {
+				ret = err;
+				goto release_init_lock;
+			}
+
+			scan_slots_for_writeback(zram, mode, lo, hi, ctl);
+			continue;
+		}
+	}
+
+	err = zram_writeback_slots(zram, ctl);
+	if (err)
+		ret = err;
+
+release_init_lock:
 	release_pp_ctl(zram, ctl);
 	atomic_set(&zram->pp_in_progress, 0);
 	up_read(&zram->init_lock);
@@ -1694,7 +1804,7 @@ static int write_incompressible_page(struct zram *zram, struct page *page,
 	 */
 	handle = zs_malloc(zram->mem_pool, PAGE_SIZE,
 			   GFP_NOIO | __GFP_NOWARN |
-			   __GFP_HIGHMEM | __GFP_MOVABLE);
+			   __GFP_HIGHMEM | __GFP_MOVABLE, page_to_nid(page));
 	if (IS_ERR_VALUE(handle))
 		return PTR_ERR((void *)handle);
 
@@ -1761,7 +1871,7 @@ static int zram_write_page(struct zram *zram, struct page *page, u32 index)
 
 	handle = zs_malloc(zram->mem_pool, comp_len,
 			   GFP_NOIO | __GFP_NOWARN |
-			   __GFP_HIGHMEM | __GFP_MOVABLE);
+			   __GFP_HIGHMEM | __GFP_MOVABLE, page_to_nid(page));
 	if (IS_ERR_VALUE(handle)) {
 		zcomp_stream_put(zstrm);
 		return PTR_ERR((void *)handle);
@@ -1981,10 +2091,15 @@ static int recompress_slot(struct zram *zram, u32 index, struct page *page,
 	 * We are holding per-CPU stream mutex and entry lock so better
 	 * avoid direct reclaim.  Allocation error is not fatal since
 	 * we still have the old object in the mem_pool.
+	 *
+	 * XXX: technically, the node we really want here is the node that holds
+	 * the original compressed data. But that would require us to modify
+	 * zsmalloc API to return this information. For now, we will make do with
+	 * the node of the page allocated for recompression.
 	 */
 	handle_new = zs_malloc(zram->mem_pool, comp_len_new,
 			       GFP_NOIO | __GFP_NOWARN |
-			       __GFP_HIGHMEM | __GFP_MOVABLE);
+			       __GFP_HIGHMEM | __GFP_MOVABLE, page_to_nid(page));
 	if (IS_ERR_VALUE(handle_new)) {
 		zcomp_stream_put(zstrm);
 		return PTR_ERR((void *)handle_new);
diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index e97d47f42ee2..584c70a34b52 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -13,6 +13,7 @@
 #include <linux/mman.h>
 #include <linux/memory-tiers.h>
 #include <linux/memory_hotplug.h>
+#include <linux/string_helpers.h>
 #include "dax-private.h"
 #include "bus.h"
 
@@ -68,7 +69,7 @@ static void kmem_put_memory_types(void)
 static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 {
 	struct device *dev = &dev_dax->dev;
-	unsigned long total_len = 0;
+	unsigned long total_len = 0, orig_len = 0;
 	struct dax_kmem_data *data;
 	struct memory_dev_type *mtype;
 	int i, rc, mapped = 0;
@@ -97,6 +98,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 	for (i = 0; i < dev_dax->nr_range; i++) {
 		struct range range;
 
+		orig_len += range_len(&dev_dax->ranges[i].range);
 		rc = dax_kmem_range(dev_dax, i, &range);
 		if (rc) {
 			dev_info(dev, "mapping%d: %#llx-%#llx too small after alignment\n",
@@ -109,6 +111,12 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 	if (!total_len) {
 		dev_warn(dev, "rejecting DAX region without any memory after alignment\n");
 		return -EINVAL;
+	} else if (total_len != orig_len) {
+		char buf[16];
+
+		string_get_size(orig_len - total_len, 1, STRING_UNITS_2,
+				buf, sizeof(buf));
+		dev_warn(dev, "DAX region truncated by %s due to alignment\n", buf);
 	}
 
 	init_node_memory_type(numa_node, mtype);
diff --git a/drivers/gpu/drm/i915/i915_mm.c b/drivers/gpu/drm/i915/i915_mm.c
index 76e2801619f0..c33bd3d83069 100644
--- a/drivers/gpu/drm/i915/i915_mm.c
+++ b/drivers/gpu/drm/i915/i915_mm.c
@@ -100,7 +100,7 @@ int remap_io_mapping(struct vm_area_struct *vma,
 
 	GEM_BUG_ON((vma->vm_flags & EXPECTED_FLAGS) != EXPECTED_FLAGS);
 
-	/* We rely on prevalidation of the io-mapping to skip track_pfn(). */
+	/* We rely on prevalidation of the io-mapping to skip pfnmap tracking. */
 	r.mm = vma->vm_mm;
 	r.pfn = pfn;
 	r.prot = __pgprot((pgprot_val(iomap->prot) & _PAGE_CACHE_MASK) |
@@ -140,7 +140,7 @@ int remap_io_sg(struct vm_area_struct *vma,
 	};
 	int err;
 
-	/* We rely on prevalidation of the io-mapping to skip track_pfn(). */
+	/* We rely on prevalidation of the io-mapping to skip pfnmap tracking. */
 	GEM_BUG_ON((vma->vm_flags & EXPECTED_FLAGS) != EXPECTED_FLAGS);
 
 	while (offset >= r.sgt.max >> PAGE_SHIFT) {
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index aedd0e2dcd89..0edd639898a6 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -25,6 +25,7 @@
 #include <linux/serial_core.h>
 #include <linux/sysfs.h>
 #include <linux/random.h>
+#include <linux/kexec_handover.h>
 
 #include <asm/setup.h>  /* for COMMAND_LINE_SIZE */
 #include <asm/page.h>
@@ -875,6 +876,36 @@ void __init early_init_dt_check_for_usable_mem_range(void)
 		memblock_add(rgn[i].base, rgn[i].size);
 }
 
+/**
+ * early_init_dt_check_kho - Decode info required for kexec handover from DT
+ */
+static void __init early_init_dt_check_kho(void)
+{
+	unsigned long node = chosen_node_offset;
+	u64 fdt_start, fdt_size, scratch_start, scratch_size;
+	const __be32 *p;
+	int l;
+
+	if (!IS_ENABLED(CONFIG_KEXEC_HANDOVER) || (long)node < 0)
+		return;
+
+	p = of_get_flat_dt_prop(node, "linux,kho-fdt", &l);
+	if (l != (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32))
+		return;
+
+	fdt_start = dt_mem_next_cell(dt_root_addr_cells, &p);
+	fdt_size = dt_mem_next_cell(dt_root_addr_cells, &p);
+
+	p = of_get_flat_dt_prop(node, "linux,kho-scratch", &l);
+	if (l != (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32))
+		return;
+
+	scratch_start = dt_mem_next_cell(dt_root_addr_cells, &p);
+	scratch_size = dt_mem_next_cell(dt_root_addr_cells, &p);
+
+	kho_populate(fdt_start, fdt_size, scratch_start, scratch_size);
+}
+
 #ifdef CONFIG_SERIAL_EARLYCON
 
 int __init early_init_dt_scan_chosen_stdout(void)
@@ -1169,6 +1200,9 @@ void __init early_init_dt_scan_nodes(void)
 
 	/* Handle linux,usable-memory-range property */
 	early_init_dt_check_for_usable_mem_range();
+
+	/* Handle kexec handover */
+	early_init_dt_check_kho();
 }
 
 bool __init early_init_dt_scan(void *dt_virt, phys_addr_t dt_phys)
diff --git a/drivers/of/kexec.c b/drivers/of/kexec.c
index 5b924597a4de..1ee2d31816ae 100644
--- a/drivers/of/kexec.c
+++ b/drivers/of/kexec.c
@@ -264,6 +264,43 @@ static inline int setup_ima_buffer(const struct kimage *image, void *fdt,
 }
 #endif /* CONFIG_IMA_KEXEC */
 
+static int kho_add_chosen(const struct kimage *image, void *fdt, int chosen_node)
+{
+	int ret = 0;
+#ifdef CONFIG_KEXEC_HANDOVER
+	phys_addr_t fdt_mem = 0;
+	phys_addr_t fdt_len = 0;
+	phys_addr_t scratch_mem = 0;
+	phys_addr_t scratch_len = 0;
+
+	ret = fdt_delprop(fdt, chosen_node, "linux,kho-fdt");
+	if (ret && ret != -FDT_ERR_NOTFOUND)
+		return ret;
+	ret = fdt_delprop(fdt, chosen_node, "linux,kho-scratch");
+	if (ret && ret != -FDT_ERR_NOTFOUND)
+		return ret;
+
+	if (!image->kho.fdt || !image->kho.scratch)
+		return 0;
+
+	fdt_mem = image->kho.fdt;
+	fdt_len = PAGE_SIZE;
+	scratch_mem = image->kho.scratch->mem;
+	scratch_len = image->kho.scratch->bufsz;
+
+	pr_debug("Adding kho metadata to DT");
+
+	ret = fdt_appendprop_addrrange(fdt, 0, chosen_node, "linux,kho-fdt",
+				       fdt_mem, fdt_len);
+	if (ret)
+		return ret;
+	ret = fdt_appendprop_addrrange(fdt, 0, chosen_node, "linux,kho-scratch",
+				       scratch_mem, scratch_len);
+
+#endif /* CONFIG_KEXEC_HANDOVER */
+	return ret;
+}
+
 /*
  * of_kexec_alloc_and_setup_fdt - Alloc and setup a new Flattened Device Tree
  *
@@ -414,6 +451,11 @@ void *of_kexec_alloc_and_setup_fdt(const struct kimage *image,
 #endif
 	}
 
+	/* Add kho metadata if this is a KHO image */
+	ret = kho_add_chosen(image, fdt, chosen_node);
+	if (ret)
+		goto out;
+
 	/* add bootargs */
 	if (cmdline) {
 		ret = fdt_setprop_string(fdt, chosen_node, "bootargs", cmdline);