[PATCH v4 0/5] kexec_file: Add buffer hand-over for the next kernel

@@ -383,6 +383,37 @@ static inline void *boot_phys_to_virt(unsigned long entry)
 	return phys_to_virt(boot_phys_to_phys(entry));
 }
 
+#ifdef CONFIG_KEXEC_FILE
+bool __weak kexec_can_hand_over_buffer(void);
+int __weak arch_kexec_add_handover_buffer(struct kimage *image,
+					  unsigned long load_addr,
+					  unsigned long size);
+int kexec_add_handover_buffer(struct kexec_buf *kbuf);
+int __weak kexec_get_handover_buffer(void **addr, unsigned long *size);
+int __weak kexec_free_handover_buffer(void);
+#else
+struct kexec_buf;
+
+static inline bool kexec_can_hand_over_buffer(void)
+{
+	return false;
+}
+
+static inline int kexec_add_handover_buffer(struct kexec_buf *kbuf)
+{
+	return -ENOTSUPP;
+}
+
+static inline int kexec_get_handover_buffer(void **addr, unsigned long *size)
+{
+	return -ENOTSUPP;
+}
+
+static inline int kexec_free_handover_buffer(void)
+{
+	return -ENOTSUPP;
+}
+#endif /* CONFIG_KEXEC_FILE */
 #else /* !CONFIG_KEXEC_CORE */
 struct pt_regs;
 struct task_struct;

@@ -113,6 +113,74 @@ void kimage_file_post_load_cleanup(struct kimage *image)
 	image->image_loader_data = NULL;
 }
 
+/**
+ * kexec_can_hand_over_buffer - can we pass data to the kexec'd kernel?
+ */
+bool __weak kexec_can_hand_over_buffer(void)
+{
+	return false;
+}
+
+/**
+ * arch_kexec_add_handover_buffer - do arch-specific steps to handover buffer
+ *
+ * Architectures should use this function to pass on the handover buffer
+ * information to the next kernel.
+ *
+ * Return: 0 on success, negative errno on error.
+ */
+int __weak arch_kexec_add_handover_buffer(struct kimage *image,
+					  unsigned long load_addr,
+					  unsigned long size)
+{
+	return -ENOTSUPP;
+}
+
+/**
+ * kexec_add_handover_buffer - add buffer to be used by the next kernel
+ * @kbuf:	Buffer contents and memory parameters.
+ *
+ * This function assumes that kexec_mutex is held.
+ * On successful return, @kbuf->mem will have the physical address of
+ * the buffer in the next kernel.
+ *
+ * Return: 0 on success, negative errno on error.
+ */
+int kexec_add_handover_buffer(struct kexec_buf *kbuf)
+{
+	int ret;
+
+	if (!kexec_can_hand_over_buffer())
+		return -ENOTSUPP;
+
+	ret = kexec_add_buffer(kbuf);
+	if (ret)
+		return ret;
+
+	return arch_kexec_add_handover_buffer(kbuf->image, kbuf->mem,
+					      kbuf->memsz);
+}
+
+/**
+ * kexec_get_handover_buffer - get the handover buffer from the previous kernel
+ * @addr:	On successful return, set to point to the buffer contents.
+ * @size:	On successful return, set to the buffer size.
+ *
+ * Return: 0 on success, negative errno on error.
+ */
+int __weak kexec_get_handover_buffer(void **addr, unsigned long *size)
+{
+	return -ENOTSUPP;
+}
+
+/**
+ * kexec_free_handover_buffer - free memory used by the handover buffer
+ */
+int __weak kexec_free_handover_buffer(void)
+{
+	return -ENOTSUPP;
+}
+
 /*
  * In file mode list of segments is prepared by kernel. Copy relevant
  * data from user space, do error checking, prepare segment list

@@ -100,6 +100,9 @@ struct kexec_segment {
 	size_t bufsz;
 	unsigned long mem;
 	size_t memsz;
+
+	/* Whether this segment is ignored in the checksum calculation. */
+	bool skip_checksum;
 };
 
 #ifdef CONFIG_COMPAT

@@ -151,15 +154,16 @@ struct kexec_file_ops {
 
 /**
  * struct kexec_buf - parameters for finding a place for a buffer in memory
- * @image:	kexec image in which memory to search.
- * @buffer:	Contents which will be copied to the allocated memory.
- * @bufsz:	Size of @buffer.
- * @mem:	On return will have address of the buffer in memory.
- * @memsz:	Size for the buffer in memory.
- * @buf_align:	Minimum alignment needed.
- * @buf_min:	The buffer can't be placed below this address.
- * @buf_max:	The buffer can't be placed above this address.
- * @top_down:	Allocate from top of memory.
+ * @image:		kexec image in which memory to search.
+ * @buffer:		Contents which will be copied to the allocated memory.
+ * @bufsz:		Size of @buffer.
+ * @mem:		On return will have address of the buffer in memory.
+ * @memsz:		Size for the buffer in memory.
+ * @buf_align:		Minimum alignment needed.
+ * @buf_min:		The buffer can't be placed below this address.
+ * @buf_max:		The buffer can't be placed above this address.
+ * @top_down:		Allocate from top of memory.
+ * @skip_checksum:	Don't verify checksum for this buffer in purgatory.
  */
 struct kexec_buf {
 	struct kimage *image;

@@ -171,6 +175,7 @@ struct kexec_buf {
 	unsigned long buf_min;
 	unsigned long buf_max;
 	bool top_down;
+	bool skip_checksum;
 };
 
 int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf,

@@ -584,6 +584,7 @@ int kexec_add_buffer(struct kexec_buf *kbuf)
 	ksegment->bufsz = kbuf->bufsz;
 	ksegment->mem = kbuf->mem;
 	ksegment->memsz = kbuf->memsz;
+	ksegment->skip_checksum = kbuf->skip_checksum;
 	kbuf->image->nr_segments++;
 	return 0;
 }

@@ -598,7 +599,6 @@ static int kexec_calculate_store_digests(struct kimage *image)
 	char *digest;
 	void *zero_buf;
 	struct kexec_sha_region *sha_regions;
-	struct purgatory_info *pi = &image->purgatory_info;
 
 	zero_buf = __va(page_to_pfn(ZERO_PAGE(0)) << PAGE_SHIFT);
 	zero_buf_sz = PAGE_SIZE;

@@ -638,11 +638,7 @@ static int kexec_calculate_store_digests(struct kimage *image)
 		struct kexec_segment *ksegment;
 
 		ksegment = &image->segment[i];
-		/*
-		 * Skip purgatory as it will be modified once we put digest
-		 * info in purgatory.
-		 */
-		if (ksegment->kbuf == pi->purgatory_buf)
+		if (ksegment->skip_checksum)
 			continue;
 
 		ret = crypto_shash_update(desc, ksegment->kbuf,

@@ -714,7 +710,7 @@ static int __kexec_load_purgatory(struct kimage *image, unsigned long min,
 	Elf_Shdr *sechdrs = NULL;
 	struct kexec_buf kbuf = { .image = image, .bufsz = 0, .buf_align = 1,
 				  .buf_min = min, .buf_max = max,
-				  .top_down = top_down };
+				  .top_down = top_down, .skip_checksum = true };
 
 	/*
 	 * sechdrs_c points to section headers in purgatory and are read

@@ -819,7 +815,10 @@ static int __kexec_load_purgatory(struct kimage *image, unsigned long min,
 	if (kbuf.buf_align < bss_align)
 		kbuf.buf_align = bss_align;
 
-	/* Add buffer to segment list */
+	/*
+	 * Add buffer to segment list. Don't checksum the segment as
+	 * it will be modified once we put digest info in purgatory.
+	 */
 	ret = kexec_add_buffer(&kbuf);
 	if (ret)
 		goto out;

@@ -256,6 +256,8 @@ extern int kexec_purgatory_get_set_symbol(struct kimage *image,
 					  unsigned int size, bool get_value);
 extern void *kexec_purgatory_get_symbol_addr(struct kimage *image,
 					     const char *name);
+int kexec_update_segment(const char *buffer, size_t bufsz,
+			 unsigned long load_addr, size_t memsz);
 extern void __crash_kexec(struct pt_regs *);
 extern void crash_kexec(struct pt_regs *);
 int kexec_should_crash(struct task_struct *);

@@ -721,6 +721,104 @@ static struct page *kimage_alloc_page(struct kimage *image,
 	return page;
 }
 
+/**
+ * kexec_update_segment - update the contents of a kimage segment
+ * @buffer:	New contents of the segment.
+ * @bufsz:	@buffer size.
+ * @load_addr:	Segment's physical address in the next kernel.
+ * @memsz:	Segment size.
+ *
+ * This function assumes kexec_mutex is held.
+ *
+ * Return: 0 on success, negative errno on error.
+ */
+int kexec_update_segment(const char *buffer, size_t bufsz,
+			 unsigned long load_addr, size_t memsz)
+{
+	int i;
+	unsigned long entry;
+	unsigned long *ptr = NULL;
+	void *dest = NULL;
+
+	if (kexec_image == NULL) {
+		pr_err("Can't update segment: no kexec image loaded.\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * kexec_add_buffer rounds up segment sizes to PAGE_SIZE, so
+	 * we have to do it here as well.
+	 */
+	memsz = ALIGN(memsz, PAGE_SIZE);
+
+	for (i = 0; i < kexec_image->nr_segments; i++)
+		/* We only support updating whole segments. */
+		if (load_addr == kexec_image->segment[i].mem &&
+		    memsz == kexec_image->segment[i].memsz) {
+			if (!kexec_image->segment[i].skip_checksum) {
+				pr_err("Trying to update non-modifiable segment.\n");
+				return -EINVAL;
+			}
+
+			break;
+		}
+	if (i == kexec_image->nr_segments) {
+		pr_err("Couldn't find segment to update: 0x%lx, size 0x%zx\n",
+		       load_addr, memsz);
+		return -EINVAL;
+	}
+
+	for (entry = kexec_image->head; !(entry & IND_DONE) && memsz;
+	     entry = *ptr++) {
+		void *addr = (void *) (entry & PAGE_MASK);
+
+		switch (entry & IND_FLAGS) {
+		case IND_DESTINATION:
+			dest = addr;
+			break;
+		case IND_INDIRECTION:
+			ptr = __va(entry & PAGE_MASK);
+			break;
+		case IND_SOURCE:
+			/* Shouldn't happen, but verify just to be safe. */
+			if (dest == NULL) {
+				pr_err("Invalid kexec entries list.");
+				return -EINVAL;
+			}
+
+			if (dest == (void *) load_addr) {
+				void *page_addr;
+				unsigned long offset;
+				size_t uchunk, mchunk;
+
+				page_addr = kmap_atomic(kmap_to_page(addr));
+
+				offset = load_addr & ~PAGE_MASK;
+				mchunk = min_t(size_t, memsz,
+					       PAGE_SIZE - offset);
+				uchunk = min(bufsz, mchunk);
+				memcpy(page_addr + offset, buffer, uchunk);
+
+				kunmap_atomic(page_addr);
+
+				bufsz -= uchunk;
+				load_addr += mchunk;
+				buffer += mchunk;
+				memsz -= mchunk;
+			}
+			dest += PAGE_SIZE;
+		}
+
+		/* Shouldn't happen, but verify just to be safe. */
+		if (ptr == NULL) {
+			pr_err("Invalid kexec entries list.");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 static int kimage_load_normal_segment(struct kimage *image,
 					 struct kexec_segment *segment)
 {

@@ -11,6 +11,7 @@
 #define _LINUX_IMA_H
 
 #include <linux/fs.h>
+#include <linux/kexec.h>
 struct linux_binprm;
 
 #ifdef CONFIG_IMA

@@ -23,6 +24,10 @@ extern int ima_post_read_file(struct file *file, void *buf, loff_t size,
 			      enum kernel_read_file_id id);
 extern void ima_post_path_mknod(struct dentry *dentry);
 
+#ifdef CONFIG_KEXEC_FILE
+extern void ima_add_kexec_buffer(struct kimage *image);
+#endif
+
 #else
 static inline int ima_bprm_check(struct linux_binprm *bprm)
 {

@@ -60,6 +65,12 @@ static inline void ima_post_path_mknod(struct dentry *dentry)
 	return;
 }
 
+#ifdef CONFIG_KEXEC_FILE
+static inline void ima_add_kexec_buffer(struct kimage *image)
+{
+}
+#endif
+
 #endif /* CONFIG_IMA */
 
 #ifdef CONFIG_IMA_APPRAISE

@@ -19,6 +19,7 @@
 #include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/fs.h>
+#include <linux/ima.h>
 #include <crypto/hash.h>
 #include <crypto/sha.h>
 #include <linux/syscalls.h>

@@ -248,6 +249,9 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 		}
 	}
 
+	/* IMA needs to pass the measurement list to the next kernel. */
+	ima_add_kexec_buffer(image);
+
 	/* Call arch image load handlers */
 	ldata = arch_kexec_kernel_image_load(image);
 

@@ -102,6 +102,11 @@ struct ima_queue_entry {
 };
 extern struct list_head ima_measurements;	/* list of all measurements */
 
+#ifdef CONFIG_KEXEC_FILE
+extern void *kexec_buffer;
+extern size_t kexec_buffer_size;
+#endif
+
 /* Internal IMA function definitions */
 int ima_init(void);
 int ima_fs_init(void);

@@ -21,6 +21,7 @@
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 #include <linux/err.h>
+#include <linux/kexec.h>
 
 #include "ima.h"
 

@@ -104,6 +105,29 @@ void __init ima_load_x509(void)
 }
 #endif
 
+#ifdef CONFIG_KEXEC_FILE
+static void ima_load_kexec_buffer(void)
+{
+	int rc;
+
+	/* Fetch the buffer from the previous kernel, if any. */
+	rc = kexec_get_handover_buffer(&kexec_buffer, &kexec_buffer_size);
+	if (rc == 0) {
+		/* Demonstrate that buffer handover works. */
+		pr_err("kexec buffer contents: %s\n", (char *) kexec_buffer);
+		pr_err("kexec buffer contents after update: %s\n",
+		       (char *) kexec_buffer + 4 * PAGE_SIZE + 10);
+
+		kexec_free_handover_buffer();
+	} else if (rc == -ENOENT)
+		pr_debug("No kexec buffer from the previous kernel.\n");
+	else
+		pr_debug("Error restoring kexec buffer: %d\n", rc);
+}
+#else
+static void ima_load_kexec_buffer(void) { }
+#endif
+
 int __init ima_init(void)
 {
 	u8 pcr_i[TPM_DIGEST_SIZE];

@@ -134,5 +158,7 @@ int __init ima_init(void)
 
 	ima_init_policy();
 
+	ima_load_kexec_buffer();
+
 	return ima_fs_init();
 }

@@ -15,6 +15,8 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/kexec.h>
+#include <linux/reboot.h>
 #include "ima.h"
 #include "ima_template_lib.h"
 

@@ -182,6 +184,89 @@ static int template_desc_init_fields(const char *template_fmt,
 	return 0;
 }
 
+#ifdef CONFIG_KEXEC_FILE
+void *kexec_buffer;
+size_t kexec_buffer_size;
+
+/* Physical address of the measurement buffer in the next kernel. */
+unsigned long kexec_buffer_load_addr;
+
+/*
+ * Called during reboot. IMA can add here new events that were generated after
+ * the kexec image was loaded.
+ */
+static int ima_update_kexec_buffer(struct notifier_block *self,
+				   unsigned long action, void *data)
+{
+	int ret;
+
+	if (!kexec_in_progress)
+		return NOTIFY_OK;
+
+	/*
+	 * Add content deep in the buffer to show that we can update
+	 * all of it.
+	 */
+	strcpy(kexec_buffer + 4 * PAGE_SIZE + 10,
+	       "Updated kexec buffer contents.");
+
+	ret = kexec_update_segment(kexec_buffer, kexec_buffer_size,
+				   kexec_buffer_load_addr, kexec_buffer_size);
+	if (ret)
+		pr_err("Error updating kexec buffer: %d\n", ret);
+
+	return NOTIFY_OK;
+}
+
+struct notifier_block update_buffer_nb = {
+	.notifier_call = ima_update_kexec_buffer,
+};
+
+/*
+ * Called during kexec_file_load so that IMA can add a segment to the kexec
+ * image with the measurement event log for the next kernel.
+ */
+void ima_add_kexec_buffer(struct kimage *image)
+{
+	/* Ask not to checksum the segment, we may have to update it later. */
+	struct kexec_buf kbuf = { .image = image, .buf_align = PAGE_SIZE,
+				  .buf_min = 0, .buf_max = ULONG_MAX,
+				  .top_down = true, .skip_checksum = true };
+	bool first_kexec_load = kexec_buffer_load_addr == 0;
+	int ret;
+
+	if (!kexec_can_hand_over_buffer())
+		return;
+
+	if (!first_kexec_load)
+		kfree(kexec_buffer);
+
+	/* Create a relatively big buffer, for testing. */
+	kexec_buffer_size = kbuf.bufsz = kbuf.memsz = 5 * PAGE_SIZE;
+	kexec_buffer = kbuf.buffer = kzalloc(kexec_buffer_size, GFP_KERNEL);
+	if (!kexec_buffer) {
+		pr_err("Not enough memory for the kexec measurement buffer.\n");
+		return;
+	}
+
+	/* Add some content for demonstration purposes. */
+	strcpy(kexec_buffer, "Buffer contents at kexec load time.");
+
+	ret = kexec_add_handover_buffer(&kbuf);
+	if (ret) {
+		pr_err("Error passing over kexec measurement buffer.\n");
+		return;
+	}
+	kexec_buffer_load_addr = kbuf.mem;
+
+	if (first_kexec_load)
+		register_reboot_notifier(&update_buffer_nb);
+
+	pr_debug("kexec measurement buffer for the loaded kernel at 0x%lx.\n",
+		 kexec_buffer_load_addr);
+}
+#endif /* CONFIG_KEXEC_FILE */
+
 struct ima_template_desc *ima_template_desc_current(void)
 {
 	if (!ima_template)

@@ -92,12 +92,20 @@ static inline bool kdump_in_progress(void)
 }
 
 #ifdef CONFIG_KEXEC_FILE
+#define ARCH_HAS_KIMAGE_ARCH
+
+struct kimage_arch {
+	phys_addr_t handover_buffer_addr;
+	unsigned long handover_buffer_size;
+};
+
 int setup_purgatory(struct kimage *image, const void *slave_code,
 		    const void *fdt, unsigned long kernel_load_addr,
 		    unsigned long fdt_load_addr, unsigned long stack_top,
 		    int debug);
-int setup_new_fdt(void *fdt, unsigned long initrd_load_addr,
-		  unsigned long initrd_len, const char *cmdline);
+int setup_new_fdt(const struct kimage *image, void *fdt,
+		  unsigned long initrd_load_addr, unsigned long initrd_len,
+		  const char *cmdline);
 bool find_debug_console(const void *fdt);
 #endif /* CONFIG_KEXEC_FILE */
 

@@ -208,7 +208,7 @@ void *elf64_load(struct kimage *image, char *kernel_buf,
 		goto out;
 	}
 
-	ret = setup_new_fdt(fdt, initrd_load_addr, initrd_len, cmdline);
+	ret = setup_new_fdt(image, fdt, initrd_load_addr, initrd_len, cmdline);
 	if (ret)
 		goto out;
 

@@ -489,6 +489,77 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image)
 	return image->fops->cleanup(image->image_loader_data);
 }
 
+bool kexec_can_hand_over_buffer(void)
+{
+	return true;
+}
+
+int arch_kexec_add_handover_buffer(struct kimage *image,
+				   unsigned long load_addr, unsigned long size)
+{
+	image->arch.handover_buffer_addr = load_addr;
+	image->arch.handover_buffer_size = size;
+
+	return 0;
+}
+
+int kexec_get_handover_buffer(void **addr, unsigned long *size)
+{
+	int ret;
+	u64 start_addr, end_addr;
+
+	ret = of_property_read_u64(of_chosen,
+				   "linux,kexec-handover-buffer-start",
+				   &start_addr);
+	if (ret == -EINVAL)
+		return -ENOENT;
+	else if (ret)
+		return -EINVAL;
+
+	ret = of_property_read_u64(of_chosen, "linux,kexec-handover-buffer-end",
+				   &end_addr);
+	if (ret == -EINVAL)
+		return -ENOENT;
+	else if (ret)
+		return -EINVAL;
+
+	*addr =  __va(start_addr);
+	/* -end is the first address after the buffer. */
+	*size = end_addr - start_addr;
+
+	return 0;
+}
+
+int kexec_free_handover_buffer(void)
+{
+	int ret;
+	void *addr;
+	unsigned long size;
+	struct property *prop;
+
+	ret = kexec_get_handover_buffer(&addr, &size);
+	if (ret)
+		return ret;
+
+	ret = memblock_free(__pa(addr), size);
+	if (ret)
+		return ret;
+
+	prop = of_find_property(of_chosen, "linux,kexec-handover-buffer-start",
+				NULL);
+	ret = of_remove_property(of_chosen, prop);
+	if (ret)
+		return ret;
+
+	prop = of_find_property(of_chosen, "linux,kexec-handover-buffer-end",
+				NULL);
+	ret = of_remove_property(of_chosen, prop);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
 /**
  * arch_kexec_walk_mem() - call func(data) for each unreserved memory block
  * @kbuf:	Context info for the search. Also passed to @func.

@@ -686,26 +757,16 @@ int setup_purgatory(struct kimage *image, const void *slave_code,
 	return 0;
 }
 
-/*
- * setup_new_fdt() - modify /chosen and memory reservation for the next kernel
- * @fdt:
- * @initrd_load_addr:	Address where the next initrd will be loaded.
- * @initrd_len:		Size of the next initrd, or 0 if there will be none.
- * @cmdline:		Command line for the next kernel, or NULL if there will
- *			be none.
+/**
+ * delete_fdt_mem_rsv() - delete memory reservation with given address and size
  *
  * Return: 0 on success, or negative errno on error.
  */
-int setup_new_fdt(void *fdt, unsigned long initrd_load_addr,
-		  unsigned long initrd_len, const char *cmdline)
+static int delete_fdt_mem_rsv(void *fdt, uint64_t start, uint64_t size)
 {
-	uint64_t oldfdt_addr;
-	int i, ret, chosen_node;
-	const void *prop;
+	int i, ret, num_rsvs = fdt_num_mem_rsv(fdt);
 
-	/* Remove memory reservation for the current device tree. */
-	oldfdt_addr = __pa(initial_boot_params);
-	for (i = 0; i < fdt_num_mem_rsv(fdt); i++) {
+	for (i = 0; i < num_rsvs; i++) {
 		uint64_t rsv_start, rsv_size;
 
 		ret = fdt_get_mem_rsv(fdt, i, &rsv_start, &rsv_size);

@@ -714,19 +775,152 @@ int setup_new_fdt(void *fdt, unsigned long initrd_load_addr,
 			return -EINVAL;
 		}
 
-		if (rsv_start == oldfdt_addr &&
-		    rsv_size == fdt_totalsize(initial_boot_params)) {
+		if (rsv_start == start && rsv_size == size) {
 			ret = fdt_del_mem_rsv(fdt, i);
 			if (ret) {
-				pr_err("Error deleting fdt reservation.\n");
+				pr_err("Error deleting device tree reservation.\n");
 				return -EINVAL;
 			}
 
-			pr_debug("Removed old device tree reservation.\n");
-			break;
+			return 0;
 		}
 	}
 
+	return -ENOENT;
+}
+
+/**
+ * setup_handover_buffer() - add handover buffer information to the fdt
+ * @image:		kexec image being loaded.
+ * @fdt:		Flattened device tree for the next kernel.
+ * @chosen_node:	Offset to the chosen node.
+ *
+ * Return: 0 on success, or negative errno on error.
+ */
+static int setup_handover_buffer(const struct kimage *image, void *fdt,
+				 int chosen_node)
+{
+	int ret;
+	const void *prop;
+
+	/* Did we receive a buffer from the previous kernel? */
+	prop = fdt_getprop(fdt, chosen_node,
+			   "linux,kexec-handover-buffer-start", NULL);
+	if (prop) {
+		u64 orig_start, orig_end;
+		unsigned long size;
+		void *addr;
+
+		orig_start = fdt64_to_cpu(*((const fdt64_t *) prop));
+
+		prop = fdt_getprop(fdt, chosen_node,
+				   "linux,kexec-handover-buffer-end", NULL);
+		if (!prop) {
+			pr_err("Malformed device tree.\n");
+			return -EINVAL;
+		}
+		orig_end = fdt64_to_cpu(*((const fdt64_t *) prop));
+
+		/* Did we free the hand-over buffer from the previous kernel? */
+		ret = kexec_get_handover_buffer(&addr, &size);
+		if (ret == -ENOENT)
+			addr = NULL;
+		else if (ret)
+			return ret;
+
+		/*
+		 * If we received a buffer from the previous kernel but deleted
+		 * it from the live DT, or if we have a new buffer for the next
+		 * kernel then we should remove the memory reservation from
+		 * the FDT.
+		 */
+		if (addr == NULL || image->arch.handover_buffer_addr != 0) {
+			ret = delete_fdt_mem_rsv(fdt, orig_start,
+						 orig_end - orig_start);
+			if (ret == 0)
+				pr_debug("Removed old hand-over buffer reservation.\n");
+			else if (ret != -ENOENT)
+				return ret;
+		}
+
+		/*
+		 * If we received a buffer from the previous kernel but deleted
+		 * it from the live DT and we have no buffer for the next kernel
+		 * then we should remove the hand-over buffer properties from
+		 * the FDT.
+		 */
+		if (addr == NULL && image->arch.handover_buffer_addr == 0) {
+			ret = fdt_delprop(fdt, chosen_node,
+					  "linux,kexec-handover-buffer-start");
+			if (ret) {
+				pr_err("Error setting up the new device tree.\n");
+				return -EINVAL;
+			}
+
+			ret = fdt_delprop(fdt, chosen_node,
+					  "linux,kexec-handover-buffer-end");
+			if (ret) {
+				pr_err("Error setting up the new device tree.\n");
+				return -EINVAL;
+			}
+		}
+	}
+
+	if (image->arch.handover_buffer_addr == 0)
+		return 0;
+
+	ret = fdt_setprop_u64(fdt, chosen_node,
+			      "linux,kexec-handover-buffer-start",
+			      image->arch.handover_buffer_addr);
+	if (ret < 0)
+		return -EINVAL;
+
+	/* -end is the first address after the buffer. */
+	ret = fdt_setprop_u64(fdt, chosen_node,
+			      "linux,kexec-handover-buffer-end",
+			      image->arch.handover_buffer_addr +
+			      image->arch.handover_buffer_size);
+	if (ret < 0)
+		return -EINVAL;
+
+	ret = fdt_add_mem_rsv(fdt, image->arch.handover_buffer_addr,
+			      image->arch.handover_buffer_size);
+	if (ret)
+		return -EINVAL;
+
+	pr_debug("kexec handover buffer at 0x%llx, size = 0x%lx\n",
+		 image->arch.handover_buffer_addr,
+		 image->arch.handover_buffer_size);
+
+	return 0;
+}
+
+/**
+ * setup_new_fdt() - modify /chosen and memory reservations for the next kernel
+ * @image:		kexec image being loaded.
+ * @fdt:		Flattened device tree for the next kernel.
+ * @initrd_load_addr:	Address where the next initrd will be loaded.
+ * @initrd_len:		Size of the next initrd, or 0 if there will be none.
+ * @cmdline:		Command line for the next kernel, or NULL if there will
+ *			be none.
+ *
+ * Return: 0 on success, or negative errno on error.
+ */
+int setup_new_fdt(const struct kimage *image, void *fdt,
+		  unsigned long initrd_load_addr, unsigned long initrd_len,
+		  const char *cmdline)
+{
+	int ret, chosen_node;
+	const void *prop;
+
+	/* Remove memory reservation for the current device tree. */
+	ret = delete_fdt_mem_rsv(fdt, __pa(initial_boot_params),
+				 fdt_totalsize(initial_boot_params));
+	if (ret == 0)
+		pr_debug("Removed old device tree reservation.\n");
+	else if (ret != -ENOENT)
+		return ret;
+
 	chosen_node = fdt_path_offset(fdt, "/chosen");
 	if (chosen_node == -FDT_ERR_NOTFOUND) {
 		chosen_node = fdt_add_subnode(fdt, fdt_path_offset(fdt, "/"),

@@ -743,7 +937,7 @@ int setup_new_fdt(void *fdt, unsigned long initrd_load_addr,
 	/* Did we boot using an initrd? */
 	prop = fdt_getprop(fdt, chosen_node, "linux,initrd-start", NULL);
 	if (prop) {
-		uint64_t tmp_start, tmp_end, tmp_size, tmp_sizepg;
+		uint64_t tmp_start, tmp_end, tmp_size;
 
 		tmp_start = fdt64_to_cpu(*((const fdt64_t *) prop));
 

@@ -759,30 +953,14 @@ int setup_new_fdt(void *fdt, unsigned long initrd_load_addr,
 		 * reserve a multiple of PAGE_SIZE, so check for both.
 		 */
 		tmp_size = tmp_end - tmp_start;
-		tmp_sizepg = round_up(tmp_size, PAGE_SIZE);
-
-		/* Remove memory reservation for the current initrd. */
-		for (i = 0; i < fdt_num_mem_rsv(fdt); i++) {
-			uint64_t rsv_start, rsv_size;
-
-			ret = fdt_get_mem_rsv(fdt, i, &rsv_start, &rsv_size);
-			if (ret) {
-				pr_err("Malformed device tree.\n");
-				return -EINVAL;
-			}
-
-			if (rsv_start == tmp_start &&
-			    (rsv_size == tmp_size || rsv_size == tmp_sizepg)) {
-				ret = fdt_del_mem_rsv(fdt, i);
-				if (ret) {
-					pr_err("Error deleting fdt reservation.\n");
-					return -EINVAL;
-				}
-				pr_debug("Removed old initrd reservation.\n");
-
-				break;
-			}
-		}
+		ret = delete_fdt_mem_rsv(fdt, tmp_start, tmp_size);
+		if (ret == -ENOENT)
+			ret = delete_fdt_mem_rsv(fdt, tmp_start,
+						 round_up(tmp_size, PAGE_SIZE));
+		if (ret == 0)
+			pr_debug("Removed old initrd reservation.\n");
+		else if (ret != -ENOENT)
+			return ret;
 
 		/* If there's no new initrd, delete the old initrd's info. */
 		if (initrd_len == 0) {

@@ -840,6 +1018,12 @@ int setup_new_fdt(void *fdt, unsigned long initrd_load_addr,
 		}
 	}
 
+	ret = setup_handover_buffer(image, fdt, chosen_node);
+	if (ret) {
+		pr_err("Error setting up the new device tree.\n");
+		return ret;
+	}
+
 	ret = fdt_setprop(fdt, chosen_node, "linux,booted-from-kexec", NULL, 0);
 	if (ret) {
 		pr_err("Error setting up the new device tree.\n");