Resguardo inicial

linux-7.2.3/kernel/liveupdate/Kconfig

@@ -0,0 +1,89 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+menu "Live Update and Kexec HandOver"
+
+config KEXEC_HANDOVER
+	bool "kexec handover"
+	depends on ARCH_SUPPORTS_KEXEC_HANDOVER && ARCH_SUPPORTS_KEXEC_FILE
+	select MEMBLOCK_KHO_SCRATCH
+	select KEXEC_FILE
+	select LIBFDT
+	select CMA
+	help
+	  Allow kexec to hand over state across kernels by generating and
+	  passing additional metadata to the target kernel. This is useful
+	  to keep data or state alive across the kexec. For this to work,
+	  both source and target kernels need to have this option enabled.
+
+config KEXEC_HANDOVER_DEBUG
+	bool "Enable Kexec Handover debug checks"
+	depends on KEXEC_HANDOVER
+	help
+	  This option enables extra sanity checks for the Kexec Handover
+	  subsystem. Since, KHO performance is crucial in live update
+	  scenarios and the extra code might be adding overhead it is
+	  only optionally enabled.
+
+config KEXEC_HANDOVER_DEBUGFS
+	bool "kexec handover debugfs interface"
+	default KEXEC_HANDOVER
+	depends on KEXEC_HANDOVER
+	select DEBUG_FS
+	help
+	  Allow to control kexec handover device tree via debugfs
+	  interface, i.e. finalize the state or aborting the finalization.
+	  Also, enables inspecting the KHO fdt trees with the debugfs binary
+	  blobs.
+
+config KEXEC_HANDOVER_ENABLE_DEFAULT
+	bool "Enable kexec handover by default"
+	depends on KEXEC_HANDOVER
+	help
+	  Enable Kexec Handover by default. This avoids the need to
+	  explicitly pass 'kho=on' on the kernel command line.
+
+	  This is useful for systems where KHO is a prerequisite for other
+	  features, such as Live Update, ensuring the mechanism is always
+	  active.
+
+	  The default behavior can still be overridden at boot time by
+	  passing 'kho=off'.
+
+config LIVEUPDATE
+	bool "Live Update Orchestrator"
+	depends on KEXEC_HANDOVER
+	help
+	  Enable the Live Update Orchestrator. Live Update is a mechanism,
+	  typically based on kexec, that allows the kernel to be updated
+	  while keeping selected devices operational across the transition.
+	  These devices are intended to be reclaimed by the new kernel and
+	  re-attached to their original workload without requiring a device
+	  reset.
+
+	  Ability to handover a device from current to the next kernel depends
+	  on specific support within device drivers and related kernel
+	  subsystems.
+
+	  This feature primarily targets virtual machine hosts to quickly update
+	  the kernel hypervisor with minimal disruption to the running virtual
+	  machines.
+
+	  If unsure, say N.
+
+config LIVEUPDATE_MEMFD
+	bool "Live update support for memfd"
+	depends on LIVEUPDATE
+	depends on MEMFD_CREATE
+	depends on SHMEM
+	default LIVEUPDATE
+	help
+	  Enable live update support for memfd regions. This allows preserving
+	  memfd-backed memory across kernel live updates.
+
+	  This can be used to back VM memory with memfds, allowing the guest
+	  memory to persist, or for other user workloads needing to preserve
+	  pages.
+
+	  If unsure, say N.
+
+endmenu

linux-7.2.3/kernel/liveupdate/Makefile

@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0
+
+luo-y :=								\
+		kho_block.o						\
+		luo_core.o						\
+		luo_file.o						\
+		luo_flb.o						\
+		luo_session.o
+
+obj-$(CONFIG_KEXEC_HANDOVER)		+= kexec_handover.o
+obj-$(CONFIG_KEXEC_HANDOVER_DEBUG)	+= kexec_handover_debug.o
+obj-$(CONFIG_KEXEC_HANDOVER_DEBUGFS)	+= kexec_handover_debugfs.o
+
+obj-$(CONFIG_LIVEUPDATE)		+= luo.o

linux-7.2.3/kernel/liveupdate/kexec_handover_debug.c

@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * kexec_handover_debug.c - kexec handover optional debug functionality
+ * Copyright (C) 2025 Google LLC, Pasha Tatashin <pasha.tatashin@soleen.com>
+ */
+
+#define pr_fmt(fmt) "KHO: " fmt
+
+#include "kexec_handover_internal.h"
+
+bool kho_scratch_overlap(phys_addr_t phys, size_t size)
+{
+	phys_addr_t scratch_start, scratch_end;
+	unsigned int i;
+
+	for (i = 0; i < kho_scratch_cnt; i++) {
+		scratch_start = kho_scratch[i].addr;
+		scratch_end = kho_scratch[i].addr + kho_scratch[i].size;
+
+		if (phys < scratch_end && (phys + size) > scratch_start)
+			return true;
+	}
+
+	return false;
+}

linux-7.2.3/kernel/liveupdate/kexec_handover_debugfs.c

@@ -0,0 +1,214 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * kexec_handover_debugfs.c - kexec handover debugfs interfaces
+ * Copyright (C) 2023 Alexander Graf <graf@amazon.com>
+ * Copyright (C) 2025 Microsoft Corporation, Mike Rapoport <rppt@kernel.org>
+ * Copyright (C) 2025 Google LLC, Changyuan Lyu <changyuanl@google.com>
+ * Copyright (C) 2025 Google LLC, Pasha Tatashin <pasha.tatashin@soleen.com>
+ */
+
+#define pr_fmt(fmt) "KHO: " fmt
+
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/libfdt.h>
+#include <linux/mm.h>
+#include <linux/kho/abi/kexec_handover.h>
+#include "kexec_handover_internal.h"
+
+static struct dentry *debugfs_root;
+
+struct fdt_debugfs {
+	struct list_head list;
+	struct debugfs_blob_wrapper wrapper;
+	struct dentry *file;
+};
+
+static int __kho_debugfs_blob_add(struct list_head *list, struct dentry *dir,
+				  const char *name, const void *blob,
+				  size_t size)
+{
+	struct fdt_debugfs *f;
+	struct dentry *file;
+
+	f = kmalloc_obj(*f);
+	if (!f)
+		return -ENOMEM;
+
+	f->wrapper.data = (void *)blob;
+	f->wrapper.size = size;
+
+	file = debugfs_create_blob(name, 0400, dir, &f->wrapper);
+	if (IS_ERR(file)) {
+		kfree(f);
+		return PTR_ERR(file);
+	}
+
+	f->file = file;
+	list_add(&f->list, list);
+
+	return 0;
+}
+
+int kho_debugfs_blob_add(struct kho_debugfs *dbg, const char *name,
+			 const void *blob, size_t size, bool root)
+{
+	struct dentry *dir;
+
+	if (root)
+		dir = dbg->dir;
+	else
+		dir = dbg->sub_fdt_dir;
+
+	return __kho_debugfs_blob_add(&dbg->fdt_list, dir, name, blob, size);
+}
+
+void kho_debugfs_blob_remove(struct kho_debugfs *dbg, void *blob)
+{
+	struct fdt_debugfs *ff;
+
+	list_for_each_entry(ff, &dbg->fdt_list, list) {
+		if (ff->wrapper.data == blob) {
+			debugfs_remove(ff->file);
+			list_del(&ff->list);
+			kfree(ff);
+			break;
+		}
+	}
+}
+
+static int scratch_phys_show(struct seq_file *m, void *v)
+{
+	for (int i = 0; i < kho_scratch_cnt; i++)
+		seq_printf(m, "0x%llx\n", kho_scratch[i].addr);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(scratch_phys);
+
+static int scratch_len_show(struct seq_file *m, void *v)
+{
+	for (int i = 0; i < kho_scratch_cnt; i++)
+		seq_printf(m, "0x%llx\n", kho_scratch[i].size);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(scratch_len);
+
+__init void kho_in_debugfs_init(struct kho_debugfs *dbg, const void *fdt)
+{
+	struct dentry *dir, *sub_fdt_dir;
+	int err, child;
+
+	INIT_LIST_HEAD(&dbg->fdt_list);
+
+	dir = debugfs_create_dir("in", debugfs_root);
+	if (IS_ERR(dir)) {
+		err = PTR_ERR(dir);
+		goto err_out;
+	}
+
+	sub_fdt_dir = debugfs_create_dir("sub_fdts", dir);
+	if (IS_ERR(sub_fdt_dir)) {
+		err = PTR_ERR(sub_fdt_dir);
+		goto err_rmdir;
+	}
+
+	err = __kho_debugfs_blob_add(&dbg->fdt_list, dir, "fdt", fdt,
+				     fdt_totalsize(fdt));
+	if (err)
+		goto err_rmdir;
+
+	fdt_for_each_subnode(child, fdt, 0) {
+		int len = 0;
+		const char *name = fdt_get_name(fdt, child, NULL);
+		const u64 *blob_phys;
+		const u64 *blob_size;
+		void *blob;
+
+		blob_phys = fdt_getprop(fdt, child,
+					KHO_SUB_TREE_PROP_NAME, &len);
+		if (!blob_phys)
+			continue;
+		if (len != sizeof(*blob_phys)) {
+			pr_warn("node %s prop %s has invalid length: %d\n",
+				name, KHO_SUB_TREE_PROP_NAME, len);
+			continue;
+		}
+
+		blob_size = fdt_getprop(fdt, child,
+					KHO_SUB_TREE_SIZE_PROP_NAME, &len);
+		if (!blob_size || len != sizeof(*blob_size)) {
+			pr_warn("node %s missing or invalid %s property\n",
+				name, KHO_SUB_TREE_SIZE_PROP_NAME);
+			continue;
+		}
+
+		blob = phys_to_virt(*blob_phys);
+		err = __kho_debugfs_blob_add(&dbg->fdt_list, sub_fdt_dir, name,
+					     blob, *blob_size);
+		if (err) {
+			pr_warn("failed to add blob %s to debugfs: %pe\n",
+				name, ERR_PTR(err));
+			continue;
+		}
+	}
+
+	dbg->dir = dir;
+	dbg->sub_fdt_dir = sub_fdt_dir;
+
+	return;
+err_rmdir:
+	debugfs_remove_recursive(dir);
+err_out:
+	/*
+	 * Failure to create /sys/kernel/debug/kho/in does not prevent
+	 * reviving state from KHO and setting up KHO for the next
+	 * kexec.
+	 */
+	if (err) {
+		pr_err("failed exposing handover FDT in debugfs: %pe\n",
+		       ERR_PTR(err));
+	}
+}
+
+__init int kho_out_debugfs_init(struct kho_debugfs *dbg)
+{
+	struct dentry *dir, *f, *sub_fdt_dir;
+
+	INIT_LIST_HEAD(&dbg->fdt_list);
+
+	dir = debugfs_create_dir("out", debugfs_root);
+	if (IS_ERR(dir))
+		return -ENOMEM;
+
+	sub_fdt_dir = debugfs_create_dir("sub_fdts", dir);
+	if (IS_ERR(sub_fdt_dir))
+		goto err_rmdir;
+
+	f = debugfs_create_file("scratch_phys", 0400, dir, NULL,
+				&scratch_phys_fops);
+	if (IS_ERR(f))
+		goto err_rmdir;
+
+	f = debugfs_create_file("scratch_len", 0400, dir, NULL,
+				&scratch_len_fops);
+	if (IS_ERR(f))
+		goto err_rmdir;
+
+	dbg->dir = dir;
+	dbg->sub_fdt_dir = sub_fdt_dir;
+	return 0;
+
+err_rmdir:
+	debugfs_remove_recursive(dir);
+	return -ENOENT;
+}
+
+__init int kho_debugfs_init(void)
+{
+	debugfs_root = debugfs_create_dir("kho", NULL);
+	if (IS_ERR(debugfs_root))
+		return -ENOENT;
+	return 0;
+}

linux-7.2.3/kernel/liveupdate/kexec_handover_internal.h

@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef LINUX_KEXEC_HANDOVER_INTERNAL_H
+#define LINUX_KEXEC_HANDOVER_INTERNAL_H
+
+#include <linux/kexec_handover.h>
+#include <linux/list.h>
+#include <linux/types.h>
+
+#ifdef CONFIG_KEXEC_HANDOVER_DEBUGFS
+#include <linux/debugfs.h>
+
+struct kho_debugfs {
+	struct dentry *dir;
+	struct dentry *sub_fdt_dir;
+	struct list_head fdt_list;
+};
+
+#else
+struct kho_debugfs {};
+#endif
+
+extern struct kho_scratch *kho_scratch;
+extern unsigned int kho_scratch_cnt;
+
+#ifdef CONFIG_KEXEC_HANDOVER_DEBUGFS
+int kho_debugfs_init(void);
+void kho_in_debugfs_init(struct kho_debugfs *dbg, const void *fdt);
+int kho_out_debugfs_init(struct kho_debugfs *dbg);
+int kho_debugfs_blob_add(struct kho_debugfs *dbg, const char *name,
+			 const void *blob, size_t size, bool root);
+void kho_debugfs_blob_remove(struct kho_debugfs *dbg, void *blob);
+#else
+static inline int kho_debugfs_init(void) { return 0; }
+static inline void kho_in_debugfs_init(struct kho_debugfs *dbg,
+				       const void *fdt) { }
+static inline int kho_out_debugfs_init(struct kho_debugfs *dbg) { return 0; }
+static inline int kho_debugfs_blob_add(struct kho_debugfs *dbg,
+				       const char *name, const void *blob,
+				       size_t size, bool root) { return 0; }
+static inline void kho_debugfs_blob_remove(struct kho_debugfs *dbg,
+					   void *blob) { }
+#endif /* CONFIG_KEXEC_HANDOVER_DEBUGFS */
+
+#ifdef CONFIG_KEXEC_HANDOVER_DEBUG
+bool kho_scratch_overlap(phys_addr_t phys, size_t size);
+#else
+static inline bool kho_scratch_overlap(phys_addr_t phys, size_t size)
+{
+	return false;
+}
+#endif /* CONFIG_KEXEC_HANDOVER_DEBUG */
+
+#endif /* LINUX_KEXEC_HANDOVER_INTERNAL_H */

linux-7.2.3/kernel/liveupdate/kho_block.c

@@ -0,0 +1,416 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (c) 2026, Google LLC.
+ * Pasha Tatashin <pasha.tatashin@soleen.com>
+ */
+
+/**
+ * DOC: KHO Serialization Blocks
+ *
+ * KHO provides a mechanism to preserve stateful data across a kexec handover
+ * by serializing it into memory blocks, and provides the common
+ * infrastructure for managing these blocks.
+ *
+ * Each block consists of a header (struct kho_block_header_ser) followed by an
+ * array of serialized entries. Multiple blocks are linked together via a
+ * physical pointer in the header, forming a linked list that can be easily
+ * traversed in both the current and the next kernel.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/io.h>
+#include <linux/kexec_handover.h>
+#include <linux/kho/abi/block.h>
+#include <linux/kho_block.h>
+#include <linux/slab.h>
+
+/*
+ * Safeguard limit for the number of serialization blocks. This is used to
+ * prevent infinite loops and excessive memory allocation in case of memory
+ * corruption in the preserved state.
+ *
+ * With a 4KB page size, 10k blocks is about 40MB. For 32-byte entries
+ * (e.g. 4 u64s), each block holds up to 127 entries (accounting for the
+ * 16-byte header), allowing the block set to hold up to 1.27M entries.
+ */
+#define KHO_MAX_BLOCKS 10000
+
+/**
+ * kho_block_set_init - Initialize a block set.
+ * @bs:         The block set to initialize.
+ * @entry_size: The size of each entry in the blocks.
+ */
+void kho_block_set_init(struct kho_block_set *bs, size_t entry_size)
+{
+	*bs = (struct kho_block_set)KHO_BLOCK_SET_INIT(*bs, entry_size);
+	WARN_ON_ONCE(!bs->count_per_block);
+}
+
+/* Serialized entries start immediately after the block header */
+static void *kho_block_entries(struct kho_block *block)
+{
+	return (void *)(block->ser + 1);
+}
+
+/* Get the address of the serialized entry at the specified index */
+static void *kho_block_entry(struct kho_block_set_it *it, u64 index)
+{
+	return kho_block_entries(it->block) + (index * it->bs->entry_size);
+}
+
+/* Free serialized data */
+static void kho_block_free_ser(struct kho_block_set *bs,
+			       struct kho_block_header_ser *ser)
+{
+	if (bs->incoming)
+		kho_restore_free(ser);
+	else
+		kho_unpreserve_free(ser);
+}
+
+static struct kho_block_header_ser *kho_block_alloc_ser(struct kho_block_set *bs)
+{
+	WARN_ON_ONCE(bs->incoming);
+	return kho_alloc_preserve(KHO_BLOCK_SIZE);
+}
+
+static int kho_block_add(struct kho_block_set *bs,
+			 struct kho_block_header_ser *ser)
+{
+	struct kho_block *block, *last;
+
+	if (bs->nblocks >= KHO_MAX_BLOCKS)
+		return -ENOSPC;
+
+	block = kzalloc_obj(*block);
+	if (!block)
+		return -ENOMEM;
+
+	block->ser = ser;
+	last = list_last_entry_or_null(&bs->blocks, struct kho_block, list);
+	list_add_tail(&block->list, &bs->blocks);
+	bs->nblocks++;
+
+	if (last)
+		last->ser->next = virt_to_phys(ser);
+	else
+		bs->head_pa = virt_to_phys(ser);
+
+	return 0;
+}
+
+static int kho_block_set_grow_one(struct kho_block_set *bs)
+{
+	struct kho_block_header_ser *ser;
+	int err;
+
+	ser = kho_block_alloc_ser(bs);
+	if (IS_ERR(ser))
+		return PTR_ERR(ser);
+
+	err = kho_block_add(bs, ser);
+	if (err) {
+		kho_block_free_ser(bs, ser);
+		return err;
+	}
+
+	return 0;
+}
+
+static void kho_block_set_shrink_one(struct kho_block_set *bs)
+{
+	struct kho_block *last, *new_last;
+
+	if (list_empty(&bs->blocks))
+		return;
+
+	last = list_last_entry(&bs->blocks, struct kho_block, list);
+	list_del(&last->list);
+	bs->nblocks--;
+	kho_block_free_ser(bs, last->ser);
+	kfree(last);
+
+	new_last = list_last_entry_or_null(&bs->blocks, struct kho_block, list);
+	if (new_last)
+		new_last->ser->next = 0;
+	else
+		bs->head_pa = 0;
+}
+
+/**
+ * kho_block_set_grow - Expand the block set to accommodate the target count.
+ * @bs:    The block set.
+ * @count: The target number of valid entries to accommodate.
+ *
+ * Dynamically preallocates and links preserved memory blocks if the target
+ * entry count exceeds the current total capacity of the set, ensuring they
+ * are available during serialization/deserialization.
+ *
+ * Context: Caller must hold a lock protecting the block set.
+ * Return: 0 on success, or a negative errno on failure.
+ */
+int kho_block_set_grow(struct kho_block_set *bs, u64 count)
+{
+	long orig_nblocks = bs->nblocks;
+	int err;
+
+	if (WARN_ON_ONCE(bs->incoming))
+		return -EINVAL;
+
+	while (count > bs->nblocks * bs->count_per_block) {
+		err = kho_block_set_grow_one(bs);
+		if (err)
+			goto err_shrink;
+	}
+
+	return 0;
+
+err_shrink:
+	while (bs->nblocks > orig_nblocks)
+		kho_block_set_shrink_one(bs);
+	return err;
+}
+
+/**
+ * kho_block_set_shrink - Shrink the block set to accommodate the target count.
+ * @bs:              The block set.
+ * @count:           The target number of valid entries to accommodate.
+ *
+ * Releases and unallocates redundant preserved memory blocks. Checks if the
+ * last block in the set can be removed because the remaining entry count is
+ * fully accommodated by the preceding blocks.
+ *
+ * Note: It is the caller's responsibility to ensure that entries are removed
+ * in the reverse order of their insertion. Because shrinking destroys the last
+ * block in the set, removing entries in any other order would corrupt active
+ * data.
+ *
+ * Context: Caller must hold a lock protecting the block set.
+ */
+void kho_block_set_shrink(struct kho_block_set *bs, u64 count)
+{
+	while (bs->nblocks > 0 && count <= (bs->nblocks - 1) * bs->count_per_block)
+		kho_block_set_shrink_one(bs);
+}
+
+/*
+ * kho_block_set_is_cyclic - Check for cycles in a linked list of blocks.
+ * Uses Floyd's cycle-finding algorithm to ensure sanity of the incoming list.
+ *
+ * Return: true if a cycle or corruption is detected, false otherwise.
+ */
+static bool kho_block_set_is_cyclic(struct kho_block_set *bs)
+{
+	struct kho_block_header_ser *fast;
+	struct kho_block_header_ser *slow;
+	int count = 0;
+
+	fast = phys_to_virt(bs->head_pa);
+	slow = fast;
+
+	while (fast) {
+		if (count++ >= KHO_MAX_BLOCKS) {
+			pr_err("Block set is corrupted\n");
+			return true;
+		}
+
+		if (!fast->next)
+			break;
+
+		fast = phys_to_virt(fast->next);
+		if (!fast->next)
+			break;
+
+		fast = phys_to_virt(fast->next);
+		slow = phys_to_virt(slow->next);
+
+		if (slow == fast) {
+			pr_err("Block set is corrupted\n");
+			return true;
+		}
+	}
+
+	return false;
+}
+
+/**
+ * kho_block_set_restore - Restore a block set from a physical address.
+ * @bs:      The block set to restore.
+ * @head_pa: Physical address of the first block header.
+ *
+ * Restores a serialized block set from a given physical address. The caller is
+ * responsible for ensuring that the block set @bs has been allocated and
+ * initialized prior to calling this function.
+ *
+ * Return: 0 on success, or a negative errno on failure.
+ */
+int kho_block_set_restore(struct kho_block_set *bs, u64 head_pa)
+{
+	struct kho_block_header_ser *ser;
+	u64 next_pa = head_pa;
+	int err;
+
+	/* Restored block sets use size from the previous kernel */
+	bs->incoming = true;
+	if (!head_pa)
+		return 0;
+
+	bs->head_pa = head_pa;
+	if (kho_block_set_is_cyclic(bs)) {
+		bs->head_pa = 0;
+		return -EINVAL;
+	}
+
+	while (next_pa) {
+		ser = phys_to_virt(next_pa);
+		if (!ser->count || ser->count > bs->count_per_block) {
+			pr_warn("Block contains invalid entry count: %llu\n",
+				ser->count);
+			err = -EINVAL;
+			goto err_destroy;
+		}
+		err = kho_block_add(bs, ser);
+		if (err)
+			goto err_destroy;
+		next_pa = ser->next;
+	}
+
+	return 0;
+
+err_destroy:
+	kho_block_set_destroy(bs);
+
+	/* Free the remaining un-restored blocks in the physical chain */
+	while (next_pa) {
+		struct kho_block_header_ser *next_ser = phys_to_virt(next_pa);
+
+		next_pa = next_ser->next;
+		kho_block_free_ser(bs, next_ser);
+	}
+	return err;
+}
+
+/**
+ * kho_block_set_destroy - Destroy all blocks in a block set.
+ * @bs:          The block set.
+ */
+void kho_block_set_destroy(struct kho_block_set *bs)
+{
+	struct kho_block *block, *tmp;
+
+	list_for_each_entry_safe(block, tmp, &bs->blocks, list) {
+		list_del(&block->list);
+		kho_block_free_ser(bs, block->ser);
+		kfree(block);
+	}
+	bs->nblocks = 0;
+	bs->head_pa = 0;
+}
+
+/**
+ * kho_block_set_clear - Clear all serialized data in a block set.
+ * @bs: The block set to clear.
+ */
+void kho_block_set_clear(struct kho_block_set *bs)
+{
+	struct kho_block *block;
+
+	list_for_each_entry(block, &bs->blocks, list) {
+		block->ser->count = 0;
+		memset(block->ser + 1, 0, KHO_BLOCK_SIZE - sizeof(*block->ser));
+	}
+}
+
+/**
+ * kho_block_set_it_init - Initialize a block set iterator.
+ * @it:         The iterator to initialize.
+ * @bs:         The block set to iterate over.
+ */
+void kho_block_set_it_init(struct kho_block_set_it *it, struct kho_block_set *bs)
+{
+	it->bs = bs;
+	it->block = list_first_entry_or_null(&bs->blocks, struct kho_block, list);
+	it->i = 0;
+}
+
+/**
+ * kho_block_set_it_reserve_entry - Reserve and return the next available slot for writing.
+ * @it: The block iterator.
+ *
+ * Reserves a slot in the current block during state serialization to add a new
+ * entry, advancing the internal index. If the current block is full, it
+ * automatically moves to the next block in the set.
+ *
+ * Return: A pointer to the reserved entry slot, or NULL if the block set's
+ * capacity is fully exhausted.
+ */
+void *kho_block_set_it_reserve_entry(struct kho_block_set_it *it)
+{
+	void *entry;
+
+	if (!it->block)
+		return NULL;
+
+	if (it->i == it->bs->count_per_block) {
+		if (list_is_last(&it->block->list, &it->bs->blocks))
+			return NULL;
+		it->block = list_next_entry(it->block, list);
+		it->i = 0;
+	}
+
+	entry = kho_block_entry(it, it->i++);
+	it->block->ser->count = it->i;
+	return entry;
+}
+
+/**
+ * kho_block_set_it_read_entry - Read the next serialized entry from the block set.
+ * @it: The block iterator.
+ *
+ * Iterates through previously written entries during state deserialization,
+ * respecting the actual count stored in each block's header.
+ *
+ * Return: A pointer to the next serialized entry, or NULL if all serialized
+ * entries have been read.
+ */
+void *kho_block_set_it_read_entry(struct kho_block_set_it *it)
+{
+	if (!it->block)
+		return NULL;
+
+	if (it->i == it->block->ser->count) {
+		if (list_is_last(&it->block->list, &it->bs->blocks))
+			return NULL;
+		it->block = list_next_entry(it->block, list);
+		it->i = 0;
+	}
+
+	return kho_block_entry(it, it->i++);
+}
+
+/**
+ * kho_block_set_it_prev - Return the previous entry slot in the block set.
+ * @it: The block iterator.
+ *
+ * If the current index is at the start of a block, it automatically moves to
+ * the end of the previous block.
+ *
+ * Return: A pointer to the previous entry slot, or NULL if at the very
+ * beginning of the block set.
+ */
+void *kho_block_set_it_prev(struct kho_block_set_it *it)
+{
+	if (!it->block)
+		return NULL;
+
+	if (it->i == 0) {
+		if (list_is_first(&it->block->list, &it->bs->blocks))
+			return NULL;
+		it->block = list_prev_entry(it->block, list);
+		it->i = it->bs->count_per_block;
+	}
+
+	return kho_block_entry(it, --it->i);
+}

linux-7.2.3/kernel/liveupdate/luo_core.c

@@ -0,0 +1,442 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (c) 2025, Google LLC.
+ * Pasha Tatashin <pasha.tatashin@soleen.com>
+ */
+
+/**
+ * DOC: Live Update Orchestrator (LUO)
+ *
+ * Live Update is a specialized, kexec-based reboot process that allows a
+ * running kernel to be updated from one version to another while preserving
+ * the state of selected resources and keeping designated hardware devices
+ * operational. For these devices, DMA activity may continue throughout the
+ * kernel transition.
+ *
+ * While the primary use case driving this work is supporting live updates of
+ * the Linux kernel when it is used as a hypervisor in cloud environments, the
+ * LUO framework itself is designed to be workload-agnostic. Live Update
+ * facilitates a full kernel version upgrade for any type of system.
+ *
+ * For example, a non-hypervisor system running an in-memory cache like
+ * memcached with many gigabytes of data can use LUO. The userspace service
+ * can place its cache into a memfd, have its state preserved by LUO, and
+ * restore it immediately after the kernel kexec.
+ *
+ * Whether the system is running virtual machines, containers, a
+ * high-performance database, or networking services, LUO's primary goal is to
+ * enable a full kernel update by preserving critical userspace state and
+ * keeping essential devices operational.
+ *
+ * The core of LUO is a mechanism that tracks the progress of a live update,
+ * along with a callback API that allows other kernel subsystems to participate
+ * in the process. Example subsystems that can hook into LUO include: kvm,
+ * iommu, interrupts, vfio, participating filesystems, and memory management.
+ *
+ * LUO uses Kexec Handover to transfer memory state from the current kernel to
+ * the next kernel. For more details see Documentation/core-api/kho/index.rst.
+ *
+ * .. note::
+ *     To enable LUO, boot the kernel with the ``liveupdate=on`` command line
+ *     parameter.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/atomic.h>
+#include <linux/errno.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/kexec_handover.h>
+#include <linux/kho/abi/luo.h>
+#include <linux/kobject.h>
+#include <linux/liveupdate.h>
+#include <linux/miscdevice.h>
+#include <linux/mm.h>
+#include <linux/rwsem.h>
+#include <linux/sizes.h>
+#include <linux/string.h>
+
+#include "kexec_handover_internal.h"
+#include "luo_internal.h"
+
+static struct {
+	bool enabled;
+	struct luo_ser *luo_ser_out;
+	u64 liveupdate_num;
+} luo_global;
+
+/*
+ * luo_register_rwlock - Protects registration of file handlers and FLBs.
+ */
+DECLARE_RWSEM(luo_register_rwlock);
+
+static int __init early_liveupdate_param(char *buf)
+{
+	return kstrtobool(buf, &luo_global.enabled);
+}
+early_param("liveupdate", early_liveupdate_param);
+
+static int __init luo_early_startup(void)
+{
+	phys_addr_t luo_ser_phys;
+	struct luo_ser *luo_ser;
+	size_t len;
+	int err;
+
+	if (!kho_is_enabled()) {
+		if (liveupdate_enabled())
+			pr_warn("Disabling liveupdate because KHO is disabled\n");
+		luo_global.enabled = false;
+		return 0;
+	}
+
+	/* Retrieve LUO state from KHO. */
+	err = kho_retrieve_subtree(LUO_KHO_ENTRY_NAME, &luo_ser_phys, &len);
+	if (err) {
+		if (err != -ENOENT) {
+			pr_err("failed to retrieve LUO state '%s' from KHO: %pe\n",
+			       LUO_KHO_ENTRY_NAME, ERR_PTR(err));
+			return err;
+		}
+
+		return 0;
+	}
+
+	if (len < sizeof(*luo_ser)) {
+		pr_err("LUO state is too small (%zu < %zu)\n", len, sizeof(*luo_ser));
+		return -EINVAL;
+	}
+
+	luo_ser = phys_to_virt(luo_ser_phys);
+	if (strncmp(luo_ser->compatible, LUO_ABI_COMPATIBLE, LUO_ABI_COMPAT_LEN)) {
+		pr_err("LUO state is incompatible with '%s'\n", LUO_ABI_COMPATIBLE);
+		return -EINVAL;
+	}
+
+	luo_global.liveupdate_num = luo_ser->liveupdate_num;
+	pr_info("Retrieved live update data, liveupdate number: %lld\n",
+		luo_global.liveupdate_num);
+
+	err = luo_session_setup_incoming(luo_ser->sessions_pa);
+	if (err)
+		goto out_free_ser;
+
+	luo_flb_setup_incoming(luo_ser->flbs_pa);
+
+	err = 0;
+
+out_free_ser:
+	kho_restore_free(luo_ser);
+	return err;
+}
+
+static int __init liveupdate_early_init(void)
+{
+	int err;
+
+	err = luo_early_startup();
+	if (err) {
+		luo_global.enabled = false;
+		luo_restore_fail("The incoming tree failed to initialize properly [%pe], disabling live update\n",
+				 ERR_PTR(err));
+	}
+
+	return err;
+}
+early_initcall(liveupdate_early_init);
+
+/* Called during boot to create outgoing LUO state */
+static int __init luo_state_setup(void)
+{
+	struct luo_ser *luo_ser;
+	int err;
+
+	luo_ser = kho_alloc_preserve(sizeof(*luo_ser));
+	if (IS_ERR(luo_ser)) {
+		pr_err("failed to allocate/preserve LUO state memory\n");
+		return PTR_ERR(luo_ser);
+	}
+
+	strscpy(luo_ser->compatible, LUO_ABI_COMPATIBLE, sizeof(luo_ser->compatible));
+	luo_ser->liveupdate_num = luo_global.liveupdate_num + 1;
+
+	luo_session_setup_outgoing(&luo_ser->sessions_pa);
+
+	err = luo_flb_setup_outgoing(&luo_ser->flbs_pa);
+	if (err)
+		goto exit_free_luo_ser;
+
+	err = kho_add_subtree(LUO_KHO_ENTRY_NAME, luo_ser, sizeof(*luo_ser));
+	if (err)
+		goto exit_free_luo_ser;
+
+	luo_global.luo_ser_out = luo_ser;
+
+	return 0;
+
+exit_free_luo_ser:
+	kho_unpreserve_free(luo_ser);
+	pr_err("failed to prepare LUO state: %d\n", err);
+
+	return err;
+}
+
+/*
+ * late initcall because it initializes the outgoing tree that is needed only
+ * once userspace starts using /dev/liveupdate.
+ */
+static int __init luo_late_startup(void)
+{
+	int err;
+
+	if (!liveupdate_enabled())
+		return 0;
+
+	err = luo_state_setup();
+	if (err)
+		luo_global.enabled = false;
+
+	return err;
+}
+late_initcall(luo_late_startup);
+
+/* Public Functions */
+
+/**
+ * liveupdate_reboot() - Kernel reboot notifier for live update final
+ * serialization.
+ *
+ * This function is invoked directly from the reboot() syscall pathway
+ * if kexec is in progress.
+ *
+ * If any callback fails, this function aborts KHO, undoes the freeze()
+ * callbacks, and returns an error.
+ */
+int liveupdate_reboot(void)
+{
+	int err;
+
+	if (!liveupdate_enabled())
+		return 0;
+
+	err = luo_session_serialize();
+	if (err)
+		return err;
+
+	luo_flb_serialize();
+
+	return 0;
+}
+
+/**
+ * liveupdate_enabled - Check if the live update feature is enabled.
+ *
+ * This function returns the state of the live update feature flag, which
+ * can be controlled via the ``liveupdate`` kernel command-line parameter.
+ *
+ * @return true if live update is enabled, false otherwise.
+ */
+bool liveupdate_enabled(void)
+{
+	return luo_global.enabled;
+}
+
+/**
+ * DOC: LUO ioctl Interface
+ *
+ * The IOCTL user-space control interface for the LUO subsystem.
+ * It registers a character device, typically found at ``/dev/liveupdate``,
+ * which allows a userspace agent to manage the LUO state machine and its
+ * associated resources, such as preservable file descriptors.
+ *
+ * To ensure that the state machine is controlled by a single entity, access
+ * to this device is exclusive: only one process is permitted to have
+ * ``/dev/liveupdate`` open at any given time. Subsequent open attempts will
+ * fail with -EBUSY until the first process closes its file descriptor.
+ * This singleton model simplifies state management by preventing conflicting
+ * commands from multiple userspace agents.
+ */
+
+struct luo_device_state {
+	struct miscdevice miscdev;
+	atomic_t in_use;
+};
+
+static int luo_ioctl_create_session(struct luo_ucmd *ucmd)
+{
+	struct liveupdate_ioctl_create_session *argp = ucmd->cmd;
+	struct file *file;
+	int err;
+
+	argp->fd = get_unused_fd_flags(O_CLOEXEC);
+	if (argp->fd < 0)
+		return argp->fd;
+
+	err = luo_session_create(argp->name, &file);
+	if (err)
+		goto err_put_fd;
+
+	err = luo_ucmd_respond(ucmd, sizeof(*argp));
+	if (err)
+		goto err_put_file;
+
+	fd_install(argp->fd, file);
+
+	return 0;
+
+err_put_file:
+	fput(file);
+err_put_fd:
+	put_unused_fd(argp->fd);
+
+	return err;
+}
+
+static int luo_ioctl_retrieve_session(struct luo_ucmd *ucmd)
+{
+	struct liveupdate_ioctl_retrieve_session *argp = ucmd->cmd;
+	struct file *file;
+	int err;
+
+	argp->fd = get_unused_fd_flags(O_CLOEXEC);
+	if (argp->fd < 0)
+		return argp->fd;
+
+	err = luo_session_retrieve(argp->name, &file);
+	if (err < 0)
+		goto err_put_fd;
+
+	err = luo_ucmd_respond(ucmd, sizeof(*argp));
+	if (err)
+		goto err_put_file;
+
+	fd_install(argp->fd, file);
+
+	return 0;
+
+err_put_file:
+	fput(file);
+err_put_fd:
+	put_unused_fd(argp->fd);
+
+	return err;
+}
+
+static int luo_open(struct inode *inodep, struct file *filep)
+{
+	struct luo_device_state *ldev = container_of(filep->private_data,
+						     struct luo_device_state,
+						     miscdev);
+
+	if (atomic_cmpxchg(&ldev->in_use, 0, 1))
+		return -EBUSY;
+
+	/* Always return -EIO to user if deserialization fail */
+	if (luo_session_deserialize()) {
+		atomic_set(&ldev->in_use, 0);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int luo_release(struct inode *inodep, struct file *filep)
+{
+	struct luo_device_state *ldev = container_of(filep->private_data,
+						     struct luo_device_state,
+						     miscdev);
+	atomic_set(&ldev->in_use, 0);
+
+	return 0;
+}
+
+union ucmd_buffer {
+	struct liveupdate_ioctl_create_session create;
+	struct liveupdate_ioctl_retrieve_session retrieve;
+};
+
+struct luo_ioctl_op {
+	unsigned int size;
+	unsigned int min_size;
+	unsigned int ioctl_num;
+	int (*execute)(struct luo_ucmd *ucmd);
+};
+
+#define IOCTL_OP(_ioctl, _fn, _struct, _last)                                  \
+	[_IOC_NR(_ioctl) - LIVEUPDATE_CMD_BASE] = {                            \
+		.size = sizeof(_struct) +                                      \
+			BUILD_BUG_ON_ZERO(sizeof(union ucmd_buffer) <          \
+					  sizeof(_struct)),                    \
+		.min_size = offsetofend(_struct, _last),                       \
+		.ioctl_num = _ioctl,                                           \
+		.execute = _fn,                                                \
+	}
+
+static const struct luo_ioctl_op luo_ioctl_ops[] = {
+	IOCTL_OP(LIVEUPDATE_IOCTL_CREATE_SESSION, luo_ioctl_create_session,
+		 struct liveupdate_ioctl_create_session, name),
+	IOCTL_OP(LIVEUPDATE_IOCTL_RETRIEVE_SESSION, luo_ioctl_retrieve_session,
+		 struct liveupdate_ioctl_retrieve_session, name),
+};
+
+static long luo_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
+{
+	const struct luo_ioctl_op *op;
+	struct luo_ucmd ucmd = {};
+	union ucmd_buffer buf;
+	unsigned int nr;
+	int err;
+
+	nr = _IOC_NR(cmd);
+	if (nr - LIVEUPDATE_CMD_BASE >= ARRAY_SIZE(luo_ioctl_ops))
+		return -EINVAL;
+
+	ucmd.ubuffer = (void __user *)arg;
+	err = get_user(ucmd.user_size, (u32 __user *)ucmd.ubuffer);
+	if (err)
+		return err;
+
+	op = &luo_ioctl_ops[nr - LIVEUPDATE_CMD_BASE];
+	if (op->ioctl_num != cmd)
+		return -ENOIOCTLCMD;
+	if (ucmd.user_size < op->min_size)
+		return -EINVAL;
+
+	ucmd.cmd = &buf;
+	err = copy_struct_from_user(ucmd.cmd, op->size, ucmd.ubuffer,
+				    ucmd.user_size);
+	if (err)
+		return err;
+
+	return op->execute(&ucmd);
+}
+
+static const struct file_operations luo_fops = {
+	.owner		= THIS_MODULE,
+	.open		= luo_open,
+	.release	= luo_release,
+	.unlocked_ioctl	= luo_ioctl,
+};
+
+static struct luo_device_state luo_dev = {
+	.miscdev = {
+		.minor = MISC_DYNAMIC_MINOR,
+		.name  = "liveupdate",
+		.fops  = &luo_fops,
+	},
+	.in_use = ATOMIC_INIT(0),
+};
+
+static int __init liveupdate_ioctl_init(void)
+{
+	if (!liveupdate_enabled())
+		return 0;
+
+	return misc_register(&luo_dev.miscdev);
+}
+late_initcall(liveupdate_ioctl_init);

linux-7.2.3/kernel/liveupdate/luo_file.c

@@ -0,0 +1,928 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (c) 2025, Google LLC.
+ * Pasha Tatashin <pasha.tatashin@soleen.com>
+ */
+
+/**
+ * DOC: LUO File Descriptors
+ *
+ * LUO provides the infrastructure to preserve specific, stateful file
+ * descriptors across a kexec-based live update. The primary goal is to allow
+ * workloads, such as virtual machines using vfio, memfd, or iommufd, to
+ * retain access to their essential resources without interruption.
+ *
+ * The framework is built around a callback-based handler model and a well-
+ * defined lifecycle for each preserved file.
+ *
+ * Handler Registration:
+ * Kernel modules responsible for a specific file type (e.g., memfd, vfio)
+ * register a &struct liveupdate_file_handler. This handler provides a set of
+ * callbacks that LUO invokes at different stages of the update process, most
+ * notably:
+ *
+ *   - can_preserve(): A lightweight check to determine if the handler is
+ *     compatible with a given 'struct file'.
+ *   - preserve(): The heavyweight operation that saves the file's state and
+ *     returns an opaque u64 handle. This is typically performed while the
+ *     workload is still active to minimize the downtime during the
+ *     actual reboot transition.
+ *   - unpreserve(): Cleans up any resources allocated by .preserve(), called
+ *     if the preservation process is aborted before the reboot (i.e. session is
+ *     closed).
+ *   - freeze(): A final pre-reboot opportunity to prepare the state for kexec.
+ *     We are already in reboot syscall, and therefore userspace cannot mutate
+ *     the file anymore.
+ *   - unfreeze(): Undoes the actions of .freeze(), called if the live update
+ *     is aborted after the freeze phase.
+ *   - retrieve(): Reconstructs the file in the new kernel from the preserved
+ *     handle.
+ *   - finish(): Performs final check and cleanup in the new kernel. After
+ *     succesul finish call, LUO gives up ownership to this file.
+ *
+ * File Preservation Lifecycle happy path:
+ *
+ * 1. Preserve (Normal Operation): A userspace agent preserves files one by one
+ *    via an ioctl. For each file, luo_preserve_file() finds a compatible
+ *    handler, calls its .preserve() operation, and creates an internal &struct
+ *    luo_file to track the live state.
+ *
+ * 2. Freeze (Pre-Reboot): Just before the kexec, luo_file_freeze() is called.
+ *    It iterates through all preserved files, calls their respective .freeze()
+ *    operation, and serializes their final metadata (compatible string, token,
+ *    and data handle) into a contiguous memory block for KHO.
+ *
+ * 3. Deserialize: After kexec, luo_file_deserialize() runs when session gets
+ *    deserialized (which is when /dev/liveupdate is first opened). It reads the
+ *    serialized data from the KHO memory region and reconstructs the in-memory
+ *    list of &struct luo_file instances for the new kernel, linking them to
+ *    their corresponding handlers.
+ *
+ * 4. Retrieve (New Kernel - Userspace Ready): The userspace agent can now
+ *    restore file descriptors by providing a token. luo_retrieve_file()
+ *    searches for the matching token, calls the handler's .retrieve() op to
+ *    re-create the 'struct file', and returns a new FD. Files can be
+ *    retrieved in ANY order.
+ *
+ * 5. Finish (New Kernel - Cleanup): Once a session retrival is complete,
+ *    luo_file_finish() is called. It iterates through all files, invokes their
+ *    .finish() operations for final cleanup, and releases all associated kernel
+ *    resources.
+ *
+ * File Preservation Lifecycle unhappy paths:
+ *
+ * 1. Abort Before Reboot: If the userspace agent aborts the live update
+ *    process before calling reboot (e.g., by closing the session file
+ *    descriptor), the session's release handler calls
+ *    luo_file_unpreserve_files(). This invokes the .unpreserve() callback on
+ *    all preserved files, ensuring all allocated resources are cleaned up and
+ *    returning the system to a clean state.
+ *
+ * 2. Freeze Failure: During the reboot() syscall, if any handler's .freeze()
+ *    op fails, the .unfreeze() op is invoked on all previously *successful*
+ *    freezes to roll back their state. The reboot() syscall then returns an
+ *    error to userspace, canceling the live update.
+ *
+ * 3. Finish Failure: In the new kernel, if a handler's .finish() op fails,
+ *    the luo_file_finish() operation is aborted. LUO retains ownership of
+ *    all files within that session, including those that were not yet
+ *    processed. The userspace agent can attempt to call the finish operation
+ *    again later. If the issue cannot be resolved, these resources will be held
+ *    by LUO until the next live update cycle, at which point they will be
+ *    discarded.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/cleanup.h>
+#include <linux/compiler.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/io.h>
+#include <linux/kexec_handover.h>
+#include <linux/kho/abi/luo.h>
+#include <linux/list_private.h>
+#include <linux/liveupdate.h>
+#include <linux/module.h>
+#include <linux/sizes.h>
+#include <linux/xarray.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include "luo_internal.h"
+
+static LIST_HEAD(luo_file_handler_list);
+
+/* Keep track of files being preserved by LUO */
+static DEFINE_XARRAY(luo_preserved_files);
+
+/**
+ * struct luo_file - Represents a single preserved file instance.
+ * @fh:            Pointer to the &struct liveupdate_file_handler that manages
+ *                 this type of file.
+ * @file:          Pointer to the kernel's &struct file that is being preserved.
+ *                 This is NULL in the new kernel until the file is successfully
+ *                 retrieved.
+ * @serialized_data: The opaque u64 handle to the serialized state of the file.
+ *                 This handle is passed back to the handler's .freeze(),
+ *                 .retrieve(), and .finish() callbacks, allowing it to track
+ *                 and update its serialized state across phases.
+ * @private_data:  Pointer to the private data for the file used to hold runtime
+ *                 state that is not preserved. Set by the handler's .preserve()
+ *                 callback, and must be freed in the handler's .unpreserve()
+ *                 callback.
+ * @retrieve_status: Status code indicating whether a user/kernel in the new kernel has
+ *                 successfully called retrieve() on this file. This prevents
+ *                 multiple retrieval attempts. A value of 0 means a retrieve()
+ *                 has not been attempted, a positive value means the retrieve()
+ *                 was successful, and a negative value means the retrieve()
+ *                 failed, and the value is the error code of the call.
+ * @mutex:         A mutex that protects the fields of this specific instance
+ *                 (e.g., @retrieved, @file), ensuring that operations like
+ *                 retrieving or finishing a file are atomic.
+ * @list:          The list_head linking this instance into its parent
+ *                 file_set's list of preserved files.
+ * @token:         The user-provided unique token used to identify this file.
+ *
+ * This structure is the core in-kernel representation of a single file being
+ * managed through a live update. An instance is created by luo_preserve_file()
+ * to link a 'struct file' to its corresponding handler, a user-provided token,
+ * and the serialized state handle returned by the handler's .preserve()
+ * operation.
+ *
+ * These instances are tracked in a per-file_set list. The @serialized_data
+ * field, which holds a handle to the file's serialized state, may be updated
+ * during the .freeze() callback before being serialized for the next kernel.
+ * After reboot, these structures are recreated by luo_file_deserialize() and
+ * are finally cleaned up by luo_file_finish().
+ */
+struct luo_file {
+	struct liveupdate_file_handler *fh;
+	struct file *file;
+	u64 serialized_data;
+	void *private_data;
+	int retrieve_status;
+	struct mutex mutex;
+	struct list_head list;
+	u64 token;
+};
+
+static unsigned long luo_get_id(struct liveupdate_file_handler *fh,
+				struct file *file)
+{
+	return fh->ops->get_id ? fh->ops->get_id(file) : (unsigned long)file;
+}
+
+static bool luo_token_is_used(struct luo_file_set *file_set, u64 token)
+{
+	struct luo_file *iter;
+
+	list_for_each_entry(iter, &file_set->files_list, list) {
+		if (iter->token == token)
+			return true;
+	}
+
+	return false;
+}
+
+/**
+ * luo_preserve_file - Initiate the preservation of a file descriptor.
+ * @file_set: The file_set to which the preserved file will be added.
+ * @token:    A unique, user-provided identifier for the file.
+ * @fd:       The file descriptor to be preserved.
+ *
+ * This function orchestrates the first phase of preserving a file. Upon entry,
+ * it takes a reference to the 'struct file' via fget(), effectively making LUO
+ * a co-owner of the file. This reference is held until the file is either
+ * unpreserved or successfully finished in the next kernel, preventing the file
+ * from being prematurely destroyed.
+ *
+ * This function orchestrates the first phase of preserving a file. It performs
+ * the following steps:
+ *
+ * 1. Validates that the @token is not already in use within the file_set.
+ * 2. Ensures the file_set's memory for files serialization is allocated
+ *    (allocates if needed).
+ * 3. Iterates through registered handlers, calling can_preserve() to find one
+ *    compatible with the given @fd.
+ * 4. Calls the handler's .preserve() operation, which saves the file's state
+ *    and returns an opaque private data handle.
+ * 5. Adds the new instance to the file_set's internal list.
+ *
+ * On success, LUO takes a reference to the 'struct file' and considers it
+ * under its management until it is unpreserved or finished.
+ *
+ * In case of any failure, all intermediate allocations (file reference, memory
+ * for the 'luo_file' struct, etc.) are cleaned up before returning an error.
+ *
+ * Context: Can be called from an ioctl handler during normal system operation.
+ * Return: 0 on success. Returns a negative errno on failure:
+ *         -EEXIST if the token is already used.
+ *         -EBUSY if the file descriptor is already preserved by another session.
+ *         -EBADF if the file descriptor is invalid.
+ *         -ENOSPC if the file_set is full.
+ *         -ENOENT if no compatible handler is found.
+ *         -ENOMEM on memory allocation failure.
+ *         Other erros might be returned by .preserve().
+ */
+int luo_preserve_file(struct luo_file_set *file_set, u64 token, int fd)
+{
+	struct liveupdate_file_op_args args = {0};
+	struct liveupdate_file_handler *fh;
+	struct luo_file *luo_file;
+	struct file *file;
+	int err;
+
+	if (luo_token_is_used(file_set, token))
+		return -EEXIST;
+
+	err = kho_block_set_grow(&file_set->block_set, file_set->count + 1);
+	if (err)
+		return err;
+
+	file = fget(fd);
+	if (!file) {
+		err = -EBADF;
+		goto err_shrink;
+	}
+
+	err = -ENOENT;
+	down_read(&luo_register_rwlock);
+	list_private_for_each_entry(fh, &luo_file_handler_list, list) {
+		if (fh->ops->can_preserve(fh, file)) {
+			if (try_module_get(fh->ops->owner))
+				err = 0;
+			break;
+		}
+	}
+	up_read(&luo_register_rwlock);
+
+	/* err is still -ENOENT if no handler was found */
+	if (err)
+		goto err_fput;
+
+	err = xa_insert(&luo_preserved_files, luo_get_id(fh, file),
+			file, GFP_KERNEL);
+	if (err)
+		goto err_module_put;
+
+	err = luo_flb_file_preserve(fh);
+	if (err)
+		goto err_erase_xa;
+
+	luo_file = kzalloc_obj(*luo_file);
+	if (!luo_file) {
+		err = -ENOMEM;
+		goto err_flb_unpreserve;
+	}
+
+	luo_file->file = file;
+	luo_file->fh = fh;
+	luo_file->token = token;
+	mutex_init(&luo_file->mutex);
+
+	args.handler = fh;
+	args.file = file;
+	err = fh->ops->preserve(&args);
+	if (err)
+		goto err_kfree;
+
+	luo_file->serialized_data = args.serialized_data;
+	luo_file->private_data = args.private_data;
+	list_add_tail(&luo_file->list, &file_set->files_list);
+	file_set->count++;
+
+	return 0;
+
+err_kfree:
+	kfree(luo_file);
+err_flb_unpreserve:
+	luo_flb_file_unpreserve(fh);
+err_erase_xa:
+	xa_erase(&luo_preserved_files, luo_get_id(fh, file));
+err_module_put:
+	module_put(fh->ops->owner);
+err_fput:
+	fput(file);
+err_shrink:
+	kho_block_set_shrink(&file_set->block_set, file_set->count);
+
+	return err;
+}
+
+/**
+ * luo_file_unpreserve_files - Unpreserves all files from a file_set.
+ * @file_set: The files to be cleaned up.
+ *
+ * This function serves as the primary cleanup path for a file_set. It is
+ * invoked when the userspace agent closes the file_set's file descriptor.
+ *
+ * For each file, it performs the following cleanup actions:
+ *   1. Calls the handler's .unpreserve() callback to allow the handler to
+ *      release any resources it allocated.
+ *   2. Removes the file from the file_set's internal tracking list.
+ *   3. Releases the reference to the 'struct file' that was taken by
+ *      luo_preserve_file() via fput(), returning ownership.
+ *   4. Frees the memory associated with the internal 'struct luo_file'.
+ *
+ * After all individual files are unpreserved, it frees the contiguous memory
+ * block that was allocated to hold their serialization data.
+ */
+void luo_file_unpreserve_files(struct luo_file_set *file_set)
+{
+	struct luo_file *luo_file;
+
+	while (!list_empty(&file_set->files_list)) {
+		struct liveupdate_file_op_args args = {0};
+
+		luo_file = list_last_entry(&file_set->files_list,
+					   struct luo_file, list);
+
+		args.handler = luo_file->fh;
+		args.file = luo_file->file;
+		args.serialized_data = luo_file->serialized_data;
+		args.private_data = luo_file->private_data;
+		luo_file->fh->ops->unpreserve(&args);
+		luo_flb_file_unpreserve(luo_file->fh);
+
+		xa_erase(&luo_preserved_files,
+			 luo_get_id(luo_file->fh, luo_file->file));
+		module_put(luo_file->fh->ops->owner);
+
+		list_del(&luo_file->list);
+		file_set->count--;
+		kho_block_set_shrink(&file_set->block_set, file_set->count);
+
+		fput(luo_file->file);
+		mutex_destroy(&luo_file->mutex);
+		kfree(luo_file);
+	}
+
+	kho_block_set_destroy(&file_set->block_set);
+}
+
+static int luo_file_freeze_one(struct luo_file_set *file_set,
+			       struct luo_file *luo_file)
+{
+	int err = 0;
+
+	guard(mutex)(&luo_file->mutex);
+
+	if (luo_file->fh->ops->freeze) {
+		struct liveupdate_file_op_args args = {0};
+
+		args.handler = luo_file->fh;
+		args.file = luo_file->file;
+		args.serialized_data = luo_file->serialized_data;
+		args.private_data = luo_file->private_data;
+
+		err = luo_file->fh->ops->freeze(&args);
+		if (!err)
+			luo_file->serialized_data = args.serialized_data;
+	}
+
+	return err;
+}
+
+static void luo_file_unfreeze_one(struct luo_file_set *file_set,
+				  struct luo_file *luo_file)
+{
+	guard(mutex)(&luo_file->mutex);
+
+	if (luo_file->fh->ops->unfreeze) {
+		struct liveupdate_file_op_args args = {0};
+
+		args.handler = luo_file->fh;
+		args.file = luo_file->file;
+		args.serialized_data = luo_file->serialized_data;
+		args.private_data = luo_file->private_data;
+
+		luo_file->fh->ops->unfreeze(&args);
+	}
+}
+
+static void __luo_file_unfreeze(struct luo_file_set *file_set,
+				struct luo_file *failed_entry)
+{
+	struct list_head *files_list = &file_set->files_list;
+	struct luo_file *luo_file;
+
+	list_for_each_entry(luo_file, files_list, list) {
+		if (luo_file == failed_entry)
+			break;
+
+		luo_file_unfreeze_one(file_set, luo_file);
+	}
+
+	kho_block_set_clear(&file_set->block_set);
+}
+
+/**
+ * luo_file_freeze - Freezes all preserved files and serializes their metadata.
+ * @file_set:     The file_set whose files are to be frozen.
+ * @file_set_ser: Where to put the serialized file_set.
+ *
+ * This function is called from the reboot() syscall path, just before the
+ * kernel transitions to the new image via kexec. Its purpose is to perform the
+ * final preparation and serialization of all preserved files in the file_set.
+ *
+ * It iterates through each preserved file in FIFO order (the order of
+ * preservation) and performs two main actions:
+ *
+ * 1. Freezes the File: It calls the handler's .freeze() callback for each
+ *    file. This gives the handler a final opportunity to quiesce the device or
+ *    prepare its state for the upcoming reboot. The handler may update its
+ *    private data handle during this step.
+ *
+ * 2. Serializes Metadata: After a successful freeze, it copies the final file
+ *    metadata—the handler's compatible string, the user token, and the final
+ *    private data handle—into the pre-allocated contiguous memory buffer
+ *    (file_set->files) that will be handed over to the next kernel via KHO.
+ *
+ * Error Handling (Rollback):
+ * This function is atomic. If any handler's .freeze() operation fails, the
+ * entire live update is aborted. The __luo_file_unfreeze() helper is
+ * immediately called to invoke the .unfreeze() op on all files that were
+ * successfully frozen before the point of failure, rolling them back to a
+ * running state. The function then returns an error, causing the reboot()
+ * syscall to fail.
+ *
+ * Context: Called only from the liveupdate_reboot() path.
+ * Return: 0 on success, or a negative errno on failure.
+ */
+int luo_file_freeze(struct luo_file_set *file_set,
+		    struct luo_file_set_ser *file_set_ser)
+{
+	struct luo_file *luo_file;
+	struct kho_block_set_it it;
+	int err;
+
+	if (!file_set->count)
+		return 0;
+
+	kho_block_set_it_init(&it, &file_set->block_set);
+
+	list_for_each_entry(luo_file, &file_set->files_list, list) {
+		struct luo_file_ser *file_ser = kho_block_set_it_reserve_entry(&it);
+
+		/* This should not fail normally as blocks were pre-allocated */
+		if (WARN_ON_ONCE(!file_ser)) {
+			err = -ENOSPC;
+			goto err_unfreeze;
+		}
+
+		err = luo_file_freeze_one(file_set, luo_file);
+		if (err < 0) {
+			pr_warn("Freeze failed for token[%#0llx] handler[%s] err[%pe]\n",
+				luo_file->token, luo_file->fh->compatible,
+				ERR_PTR(err));
+			goto err_unfreeze;
+		}
+
+		strscpy(file_ser->compatible, luo_file->fh->compatible,
+			sizeof(file_ser->compatible));
+		file_ser->data = luo_file->serialized_data;
+		file_ser->token = luo_file->token;
+	}
+
+	file_set_ser->count = file_set->count;
+	file_set_ser->files = kho_block_set_head_pa(&file_set->block_set);
+
+	return 0;
+
+err_unfreeze:
+	__luo_file_unfreeze(file_set, luo_file);
+
+	return err;
+}
+
+/**
+ * luo_file_unfreeze - Unfreezes all files in a file_set and clear serialization
+ * @file_set:     The file_set whose files are to be unfrozen.
+ * @file_set_ser: Serialized file_set.
+ *
+ * This function rolls back the state of all files in a file_set after the
+ * freeze phase has begun but must be aborted. It is the counterpart to
+ * luo_file_freeze().
+ *
+ * It invokes the __luo_file_unfreeze() helper with a NULL argument, which
+ * signals the helper to iterate through all files in the file_set and call
+ * their respective .unfreeze() handler callbacks.
+ *
+ * Context: This is called when the live update is aborted during
+ *          the reboot() syscall, after luo_file_freeze() has been called.
+ */
+void luo_file_unfreeze(struct luo_file_set *file_set,
+		       struct luo_file_set_ser *file_set_ser)
+{
+	if (!file_set->count)
+		return;
+
+	__luo_file_unfreeze(file_set, NULL);
+	memset(file_set_ser, 0, sizeof(*file_set_ser));
+}
+
+/**
+ * luo_retrieve_file - Restores a preserved file from a file_set by its token.
+ * @file_set: The file_set from which to retrieve the file.
+ * @token:    The unique token identifying the file to be restored.
+ * @filep:    Output parameter; on success, this is populated with a pointer
+ *            to the newly retrieved 'struct file'.
+ *
+ * This function is the primary mechanism for recreating a file in the new
+ * kernel after a live update. It searches the file_set's list of deserialized
+ * files for an entry matching the provided @token.
+ *
+ * The operation is idempotent: if a file has already been successfully
+ * retrieved, this function will simply return a pointer to the existing
+ * 'struct file' and report success without re-executing the retrieve
+ * operation. This is handled by checking the 'retrieved' flag under a lock.
+ *
+ * File retrieval can happen in any order; it is not bound by the order of
+ * preservation.
+ *
+ * Context: Can be called from an ioctl or other in-kernel code in the new
+ *          kernel.
+ * Return: 0 on success. Returns a negative errno on failure:
+ *         -ENOENT if no file with the matching token is found.
+ *         Any error code returned by the handler's .retrieve() op.
+ */
+int luo_retrieve_file(struct luo_file_set *file_set, u64 token,
+		      struct file **filep)
+{
+	struct liveupdate_file_op_args args = {0};
+	struct luo_file *luo_file;
+	bool found = false;
+	int err;
+
+	if (list_empty(&file_set->files_list))
+		return -ENOENT;
+
+	list_for_each_entry(luo_file, &file_set->files_list, list) {
+		if (luo_file->token == token) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found)
+		return -ENOENT;
+
+	guard(mutex)(&luo_file->mutex);
+	if (luo_file->retrieve_status < 0) {
+		/* Retrieve was attempted and it failed. Return the error code. */
+		return luo_file->retrieve_status;
+	}
+
+	if (luo_file->retrieve_status > 0) {
+		/*
+		 * Someone is asking for this file again, so get a reference
+		 * for them.
+		 */
+		get_file(luo_file->file);
+		*filep = luo_file->file;
+		return 0;
+	}
+
+	args.handler = luo_file->fh;
+	args.serialized_data = luo_file->serialized_data;
+	err = luo_file->fh->ops->retrieve(&args);
+	if (err) {
+		/* Keep the error code for later use. */
+		luo_file->retrieve_status = err;
+		return err;
+	}
+
+	luo_file->file = args.file;
+	/* Get reference so we can keep this file in LUO until finish */
+	get_file(luo_file->file);
+
+	WARN_ON(xa_insert(&luo_preserved_files,
+			  luo_get_id(luo_file->fh, luo_file->file),
+			  luo_file->file, GFP_KERNEL));
+
+	*filep = luo_file->file;
+	luo_file->retrieve_status = 1;
+
+	return 0;
+}
+
+static int luo_file_can_finish_one(struct luo_file_set *file_set,
+				   struct luo_file *luo_file)
+{
+	bool can_finish = true;
+
+	guard(mutex)(&luo_file->mutex);
+
+	if (luo_file->fh->ops->can_finish) {
+		struct liveupdate_file_op_args args = {0};
+
+		args.handler = luo_file->fh;
+		args.file = luo_file->file;
+		args.serialized_data = luo_file->serialized_data;
+		args.retrieve_status = luo_file->retrieve_status;
+		can_finish = luo_file->fh->ops->can_finish(&args);
+	}
+
+	return can_finish ? 0 : -EBUSY;
+}
+
+static void luo_file_finish_one(struct luo_file_set *file_set,
+				struct luo_file *luo_file)
+{
+	struct liveupdate_file_op_args args = {0};
+
+	guard(mutex)(&luo_file->mutex);
+
+	args.handler = luo_file->fh;
+	args.file = luo_file->file;
+	args.serialized_data = luo_file->serialized_data;
+	args.retrieve_status = luo_file->retrieve_status;
+
+	luo_file->fh->ops->finish(&args);
+	luo_flb_file_finish(luo_file->fh);
+}
+
+/**
+ * luo_file_finish - Completes the lifecycle for all files in a file_set.
+ * @file_set: The file_set to be finalized.
+ *
+ * This function orchestrates the final teardown of a live update file_set in
+ * the new kernel. It should be called after all necessary files have been
+ * retrieved and the userspace agent is ready to release the preserved state.
+ *
+ * The function iterates through all tracked files. For each file, it performs
+ * the following sequence of cleanup actions:
+ *
+ * 1. If file is not yet retrieved, retrieves it, and calls can_finish() on
+ *    every file in the file_set. If all can_finish return true, continue to
+ *    finish.
+ * 2. Calls the handler's .finish() callback (via luo_file_finish_one) to
+ *    allow for final resource cleanup within the handler.
+ * 3. Releases LUO's ownership reference on the 'struct file' via fput(). This
+ *    is the counterpart to the get_file() call in luo_retrieve_file().
+ * 4. Removes the 'struct luo_file' from the file_set's internal list.
+ * 5. Frees the memory for the 'struct luo_file' instance itself.
+ *
+ * After successfully finishing all individual files, it frees the
+ * contiguous memory block that was used to transfer the serialized metadata
+ * from the previous kernel.
+ *
+ * Error Handling (Atomic Failure):
+ * This operation is atomic. If any handler's .can_finish() op fails, the entire
+ * function aborts immediately and returns an error.
+ *
+ * Context: Can be called from an ioctl handler in the new kernel.
+ * Return: 0 on success, or a negative errno on failure.
+ */
+int luo_file_finish(struct luo_file_set *file_set)
+{
+	struct list_head *files_list = &file_set->files_list;
+	struct luo_file *luo_file;
+	int err;
+
+	if (!file_set->count)
+		return 0;
+
+	list_for_each_entry(luo_file, files_list, list) {
+		err = luo_file_can_finish_one(file_set, luo_file);
+		if (err)
+			return err;
+	}
+
+	while (!list_empty(&file_set->files_list)) {
+		luo_file = list_last_entry(&file_set->files_list,
+					   struct luo_file, list);
+
+		luo_file_finish_one(file_set, luo_file);
+
+		if (luo_file->file) {
+			xa_erase(&luo_preserved_files,
+				 luo_get_id(luo_file->fh, luo_file->file));
+			fput(luo_file->file);
+		}
+		module_put(luo_file->fh->ops->owner);
+		list_del(&luo_file->list);
+		file_set->count--;
+		kho_block_set_shrink(&file_set->block_set, file_set->count);
+		mutex_destroy(&luo_file->mutex);
+		kfree(luo_file);
+	}
+
+	kho_block_set_destroy(&file_set->block_set);
+
+	return 0;
+}
+
+static int luo_file_deserialize_one(struct luo_file_set *file_set,
+				    struct luo_file_ser *ser)
+{
+	struct liveupdate_file_handler *fh;
+	bool handler_found = false;
+	struct luo_file *luo_file;
+
+	down_read(&luo_register_rwlock);
+	list_private_for_each_entry(fh, &luo_file_handler_list, list) {
+		if (!strcmp(fh->compatible, ser->compatible)) {
+			if (try_module_get(fh->ops->owner))
+				handler_found = true;
+			break;
+		}
+	}
+	up_read(&luo_register_rwlock);
+
+	if (!handler_found) {
+		pr_warn("No registered handler for compatible '%.*s'\n",
+			(int)sizeof(ser->compatible),
+			ser->compatible);
+		return -ENOENT;
+	}
+
+	luo_file = kzalloc_obj(*luo_file);
+	if (!luo_file) {
+		module_put(fh->ops->owner);
+		return -ENOMEM;
+	}
+
+	luo_file->fh = fh;
+	luo_file->file = NULL;
+	luo_file->serialized_data = ser->data;
+	luo_file->token = ser->token;
+	mutex_init(&luo_file->mutex);
+	list_add_tail(&luo_file->list, &file_set->files_list);
+
+	return 0;
+}
+
+/**
+ * luo_file_deserialize - Reconstructs the list of preserved files in the new kernel.
+ * @file_set:     The incoming file_set to fill with deserialized data.
+ * @file_set_ser: Serialized KHO file_set data from the previous kernel.
+ *
+ * This function is called during the early boot process of the new kernel. It
+ * takes the raw, contiguous memory block of 'struct luo_file_ser' entries,
+ * provided by the previous kernel, and transforms it back into a live,
+ * in-memory linked list of 'struct luo_file' instances.
+ *
+ * For each serialized entry, it performs the following steps:
+ *   1. Reads the 'compatible' string.
+ *   2. Searches the global list of registered file handlers for one that
+ *      matches the compatible string.
+ *   3. Allocates a new 'struct luo_file'.
+ *   4. Populates the new structure with the deserialized data (token, private
+ *      data handle) and links it to the found handler. The 'file' pointer is
+ *      initialized to NULL, as the file has not been retrieved yet.
+ *   5. Adds the new 'struct luo_file' to the file_set's files_list.
+ *
+ * This prepares the file_set for userspace, which can later call
+ * luo_retrieve_file() to restore the actual file descriptors.
+ *
+ * Context: Called from session deserialization.
+ */
+int luo_file_deserialize(struct luo_file_set *file_set,
+			 struct luo_file_set_ser *file_set_ser)
+{
+	struct luo_file_ser *file_ser;
+	struct kho_block_set_it it;
+	int err;
+
+	if (!file_set_ser->files) {
+		WARN_ON(file_set_ser->count);
+		return 0;
+	}
+
+	file_set->count = 0;
+	err = kho_block_set_restore(&file_set->block_set, file_set_ser->files);
+	if (err)
+		return err;
+
+	/*
+	 * Note on error handling:
+	 *
+	 * If deserialization fails (e.g., allocation failure or corrupt data),
+	 * we intentionally skip cleanup of files that were already restored.
+	 *
+	 * A partial failure leaves the preserved state inconsistent.
+	 * Implementing a safe "undo" to unwind complex dependencies (sessions,
+	 * files, hardware state) is error-prone and provides little value, as
+	 * the system is effectively in a broken state.
+	 *
+	 * We treat these resources as leaked. The expected recovery path is for
+	 * userspace to detect the failure and trigger a reboot, which will
+	 * reliably reset devices and reclaim memory.
+	 */
+	kho_block_set_it_init(&it, &file_set->block_set);
+	while ((file_ser = kho_block_set_it_read_entry(&it))) {
+		err = luo_file_deserialize_one(file_set, file_ser);
+		if (err)
+			goto err_destroy_blocks;
+		file_set->count++;
+	}
+
+	if (file_set->count != file_set_ser->count) {
+		pr_warn("File count mismatch: expected %llu, found %llu\n",
+			file_set_ser->count, file_set->count);
+		err = -EINVAL;
+		goto err_destroy_blocks;
+	}
+
+	return 0;
+
+err_destroy_blocks:
+	while (!list_empty(&file_set->files_list)) {
+		struct luo_file *luo_file;
+
+		luo_file = list_first_entry(&file_set->files_list,
+					    struct luo_file, list);
+		list_del(&luo_file->list);
+		module_put(luo_file->fh->ops->owner);
+		mutex_destroy(&luo_file->mutex);
+		kfree(luo_file);
+	}
+	file_set->count = 0;
+	kho_block_set_destroy(&file_set->block_set);
+	return err;
+}
+
+void luo_file_set_init(struct luo_file_set *file_set)
+{
+	INIT_LIST_HEAD(&file_set->files_list);
+	kho_block_set_init(&file_set->block_set, sizeof(struct luo_file_ser));
+}
+
+void luo_file_set_destroy(struct luo_file_set *file_set)
+{
+	WARN_ON(file_set->count);
+	WARN_ON(!list_empty(&file_set->files_list));
+	WARN_ON(!kho_block_set_is_empty(&file_set->block_set));
+}
+
+/**
+ * liveupdate_register_file_handler - Register a file handler with LUO.
+ * @fh: Pointer to a caller-allocated &struct liveupdate_file_handler.
+ * The caller must initialize this structure, including a unique
+ * 'compatible' string and a valid 'fh' callbacks. This function adds the
+ * handler to the global list of supported file handlers.
+ *
+ * Context: Typically called during module initialization for file types that
+ * support live update preservation.
+ *
+ * Return: 0 on success. Negative errno on failure.
+ */
+int liveupdate_register_file_handler(struct liveupdate_file_handler *fh)
+{
+	struct liveupdate_file_handler *fh_iter;
+	int err;
+
+	if (!liveupdate_enabled())
+		return -EOPNOTSUPP;
+
+	/* Sanity check that all required callbacks are set */
+	if (!fh->ops->preserve || !fh->ops->unpreserve || !fh->ops->retrieve ||
+	    !fh->ops->finish || !fh->ops->can_preserve) {
+		return -EINVAL;
+	}
+
+	down_write(&luo_register_rwlock);
+	/* Check for duplicate compatible strings */
+	list_private_for_each_entry(fh_iter, &luo_file_handler_list, list) {
+		if (!strcmp(fh_iter->compatible, fh->compatible)) {
+			pr_err("File handler registration failed: Compatible string '%s' already registered.\n",
+			       fh->compatible);
+			err = -EEXIST;
+			goto err_unlock;
+		}
+	}
+
+	INIT_LIST_HEAD(&ACCESS_PRIVATE(fh, flb_list));
+	INIT_LIST_HEAD(&ACCESS_PRIVATE(fh, list));
+	list_add_tail(&ACCESS_PRIVATE(fh, list), &luo_file_handler_list);
+	up_write(&luo_register_rwlock);
+
+	liveupdate_test_register(fh);
+
+	return 0;
+
+err_unlock:
+	up_write(&luo_register_rwlock);
+	return err;
+}
+
+/**
+ * liveupdate_unregister_file_handler - Unregister a liveupdate file handler
+ * @fh: The file handler to unregister
+ *
+ * Unregisters the file handler from the liveupdate core. This function
+ * reverses the operations of liveupdate_register_file_handler().
+ */
+void liveupdate_unregister_file_handler(struct liveupdate_file_handler *fh)
+{
+	if (!liveupdate_enabled())
+		return;
+
+	guard(rwsem_write)(&luo_register_rwlock);
+	luo_flb_unregister_all(fh);
+	list_del(&ACCESS_PRIVATE(fh, list));
+}

linux-7.2.3/kernel/liveupdate/luo_flb.c

@@ -0,0 +1,618 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (c) 2025, Google LLC.
+ * Pasha Tatashin <pasha.tatashin@soleen.com>
+ */
+
+/**
+ * DOC: LUO File Lifecycle Bound Global Data
+ *
+ * File-Lifecycle-Bound (FLB) objects provide a mechanism for managing global
+ * state that is shared across multiple live-updatable files. The lifecycle of
+ * this shared state is tied to the preservation of the files that depend on it.
+ *
+ * An FLB represents a global resource, such as the IOMMU core state, that is
+ * required by multiple file descriptors (e.g., all VFIO fds).
+ *
+ * The preservation of the FLB's state is triggered when the *first* file
+ * depending on it is preserved. The cleanup of this state (unpreserve or
+ * finish) is triggered when the *last* file depending on it is unpreserved or
+ * finished.
+ *
+ * Handler Dependency: A file handler declares its dependency on one or more
+ * FLBs by registering them via liveupdate_register_flb().
+ *
+ * Callback Model: Each FLB is defined by a set of operations
+ * (&struct liveupdate_flb_ops) that LUO invokes at key points:
+ *
+ *     - .preserve(): Called for the first file. Saves global state.
+ *     - .unpreserve(): Called for the last file (if aborted pre-reboot).
+ *     - .retrieve(): Called on-demand in the new kernel to restore the state.
+ *     - .finish(): Called for the last file in the new kernel for cleanup.
+ *
+ * This reference-counted approach ensures that shared state is saved exactly
+ * once and restored exactly once, regardless of how many files depend on it,
+ * and that its lifecycle is correctly managed across the kexec transition.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/cleanup.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/io.h>
+#include <linux/kexec_handover.h>
+#include <linux/kho/abi/luo.h>
+#include <linux/list_private.h>
+#include <linux/liveupdate.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include "luo_internal.h"
+
+#define LUO_FLB_PGCNT		1ul
+#define LUO_FLB_MAX		(((LUO_FLB_PGCNT << PAGE_SHIFT) -	\
+		sizeof(struct luo_flb_header_ser)) / sizeof(struct luo_flb_ser))
+
+struct luo_flb_header {
+	struct luo_flb_header_ser *header_ser;
+	struct luo_flb_ser *ser;
+	bool active;
+};
+
+struct luo_flb_global {
+	struct luo_flb_header incoming;
+	struct luo_flb_header outgoing;
+	struct list_head list;
+	long count;
+};
+
+static struct luo_flb_global luo_flb_global = {
+	.list = LIST_HEAD_INIT(luo_flb_global.list),
+};
+
+/*
+ * struct luo_flb_link - Links an FLB definition to a file handler's internal
+ * list of dependencies.
+ * @flb:  A pointer to the registered &struct liveupdate_flb definition.
+ * @list: The list_head for linking.
+ */
+struct luo_flb_link {
+	struct liveupdate_flb *flb;
+	struct list_head list;
+};
+
+/* luo_flb_get_private - Access private field, and if needed initialize it. */
+static struct luo_flb_private *luo_flb_get_private(struct liveupdate_flb *flb)
+{
+	struct luo_flb_private *private = &ACCESS_PRIVATE(flb, private);
+	static DEFINE_SPINLOCK(luo_flb_init_lock);
+
+	if (smp_load_acquire(&private->initialized))
+		return private;
+
+	guard(spinlock)(&luo_flb_init_lock);
+	if (!private->initialized) {
+		mutex_init(&private->incoming.lock);
+		mutex_init(&private->outgoing.lock);
+		INIT_LIST_HEAD(&private->list);
+		private->users = 0;
+		smp_store_release(&private->initialized, true);
+	}
+
+	return private;
+}
+
+static int luo_flb_file_preserve_one(struct liveupdate_flb *flb)
+{
+	struct luo_flb_private *private = luo_flb_get_private(flb);
+
+	scoped_guard(mutex, &private->outgoing.lock) {
+		if (!refcount_read(&private->outgoing.count)) {
+			struct liveupdate_flb_op_args args = {0};
+			int err;
+
+			if (!try_module_get(flb->ops->owner))
+				return -ENODEV;
+
+			args.flb = flb;
+			err = flb->ops->preserve(&args);
+			if (err) {
+				module_put(flb->ops->owner);
+				return err;
+			}
+			private->outgoing.data = args.data;
+			private->outgoing.obj = args.obj;
+			refcount_set(&private->outgoing.count, 1);
+		} else {
+			refcount_inc(&private->outgoing.count);
+		}
+	}
+
+	return 0;
+}
+
+static void luo_flb_file_unpreserve_one(struct liveupdate_flb *flb)
+{
+	struct luo_flb_private *private = luo_flb_get_private(flb);
+
+	scoped_guard(mutex, &private->outgoing.lock) {
+		if (refcount_dec_and_test(&private->outgoing.count)) {
+			struct liveupdate_flb_op_args args = {0};
+
+			args.flb = flb;
+			args.data = private->outgoing.data;
+			args.obj = private->outgoing.obj;
+
+			if (flb->ops->unpreserve)
+				flb->ops->unpreserve(&args);
+
+			private->outgoing.data = 0;
+			private->outgoing.obj = NULL;
+			module_put(flb->ops->owner);
+		}
+	}
+}
+
+static int luo_flb_retrieve_one(struct liveupdate_flb *flb)
+{
+	struct luo_flb_private *private = luo_flb_get_private(flb);
+	struct luo_flb_header *fh = &luo_flb_global.incoming;
+	struct liveupdate_flb_op_args args = {0};
+	bool found = false;
+	int err;
+
+	lockdep_assert_held(&private->incoming.lock);
+
+	if (private->incoming.finished)
+		return -ENODATA;
+
+	if (private->incoming.retrieved)
+		return 0;
+
+	if (!fh->active)
+		return -ENODATA;
+
+	for (int i = 0; i < fh->header_ser->count; i++) {
+		if (!strcmp(fh->ser[i].name, flb->compatible)) {
+			private->incoming.data = fh->ser[i].data;
+			refcount_set(&private->incoming.count, fh->ser[i].count);
+			found = true;
+			break;
+		}
+	}
+
+	if (!found)
+		return -ENOENT;
+
+	if (!try_module_get(flb->ops->owner))
+		return -ENODEV;
+
+	args.flb = flb;
+	args.data = private->incoming.data;
+
+	err = flb->ops->retrieve(&args);
+	if (err) {
+		module_put(flb->ops->owner);
+		return err;
+	}
+
+	private->incoming.obj = args.obj;
+	private->incoming.retrieved = true;
+
+	return 0;
+}
+
+void liveupdate_flb_put_incoming(struct liveupdate_flb *flb)
+{
+	struct luo_flb_private *private = luo_flb_get_private(flb);
+	struct liveupdate_flb_op_args args = {0};
+
+	scoped_guard(mutex, &private->incoming.lock) {
+		if (!refcount_dec_and_test(&private->incoming.count))
+			return;
+
+		if (!private->incoming.retrieved) {
+			int err = luo_flb_retrieve_one(flb);
+
+			if (WARN_ON(err))
+				return;
+		}
+
+		args.flb = flb;
+		args.obj = private->incoming.obj;
+		flb->ops->finish(&args);
+
+		private->incoming.data = 0;
+		private->incoming.obj = NULL;
+		private->incoming.finished = true;
+		module_put(flb->ops->owner);
+	}
+}
+
+/**
+ * luo_flb_file_preserve - Notifies FLBs that a file is about to be preserved.
+ * @fh: The file handler for the preserved file.
+ *
+ * This function iterates through all FLBs associated with the given file
+ * handler. It increments the reference count for each FLB. If the count becomes
+ * 1, it triggers the FLB's .preserve() callback to save the global state.
+ *
+ * This operation is atomic. If any FLB's .preserve() op fails, it will roll
+ * back by calling .unpreserve() on any FLBs that were successfully preserved
+ * during this call.
+ *
+ * Context: Called from luo_preserve_file()
+ * Return: 0 on success, or a negative errno on failure.
+ */
+int luo_flb_file_preserve(struct liveupdate_file_handler *fh)
+{
+	struct list_head *flb_list = &ACCESS_PRIVATE(fh, flb_list);
+	struct luo_flb_link *iter;
+	int err = 0;
+
+	down_read(&luo_register_rwlock);
+	list_for_each_entry(iter, flb_list, list) {
+		err = luo_flb_file_preserve_one(iter->flb);
+		if (err)
+			goto exit_err;
+	}
+	up_read(&luo_register_rwlock);
+
+	return 0;
+
+exit_err:
+	list_for_each_entry_continue_reverse(iter, flb_list, list)
+		luo_flb_file_unpreserve_one(iter->flb);
+	up_read(&luo_register_rwlock);
+
+	return err;
+}
+
+/**
+ * luo_flb_file_unpreserve - Notifies FLBs that a dependent file was unpreserved.
+ * @fh: The file handler for the unpreserved file.
+ *
+ * This function iterates through all FLBs associated with the given file
+ * handler, in reverse order of registration. It decrements the reference count
+ * for each FLB. If the count becomes 0, it triggers the FLB's .unpreserve()
+ * callback to clean up the global state.
+ *
+ * Context: Called when a preserved file is being cleaned up before reboot
+ *          (e.g., from luo_file_unpreserve_files()).
+ */
+void luo_flb_file_unpreserve(struct liveupdate_file_handler *fh)
+{
+	struct list_head *flb_list = &ACCESS_PRIVATE(fh, flb_list);
+	struct luo_flb_link *iter;
+
+	guard(rwsem_read)(&luo_register_rwlock);
+	list_for_each_entry_reverse(iter, flb_list, list)
+		luo_flb_file_unpreserve_one(iter->flb);
+}
+
+/**
+ * luo_flb_file_finish - Notifies FLBs that a dependent file has been finished.
+ * @fh: The file handler for the finished file.
+ *
+ * This function iterates through all FLBs associated with the given file
+ * handler, in reverse order of registration. It decrements the incoming
+ * reference count for each FLB. If the count becomes 0, it triggers the FLB's
+ * .finish() callback for final cleanup in the new kernel.
+ *
+ * Context: Called from luo_file_finish() for each file being finished.
+ */
+void luo_flb_file_finish(struct liveupdate_file_handler *fh)
+{
+	struct list_head *flb_list = &ACCESS_PRIVATE(fh, flb_list);
+	struct luo_flb_link *iter;
+
+	guard(rwsem_read)(&luo_register_rwlock);
+	list_for_each_entry_reverse(iter, flb_list, list)
+		liveupdate_flb_put_incoming(iter->flb);
+}
+
+static void luo_flb_unregister_one(struct liveupdate_file_handler *fh,
+				   struct liveupdate_flb *flb)
+{
+	struct luo_flb_private *private = luo_flb_get_private(flb);
+	struct list_head *flb_list = &ACCESS_PRIVATE(fh, flb_list);
+	struct luo_flb_link *iter;
+	bool found = false;
+
+	/* Find and remove the link from the file handler's list */
+	list_for_each_entry(iter, flb_list, list) {
+		if (iter->flb == flb) {
+			list_del(&iter->list);
+			kfree(iter);
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		pr_warn("Failed to unregister FLB '%s': not found in file handler '%s'\n",
+			flb->compatible, fh->compatible);
+		return;
+	}
+
+	private->users--;
+
+	/*
+	 * If this is the last file-handler with which we are registred, remove
+	 * from the global list.
+	 */
+	if (!private->users) {
+		list_del_init(&private->list);
+		luo_flb_global.count--;
+	}
+}
+
+/**
+ * luo_flb_unregister_all - Unregister all FLBs associated with a file handler.
+ * @fh: The file handler whose FLBs should be unregistered.
+ *
+ * This function iterates through the list of FLBs associated with the given
+ * file handler and unregisters them all one by one.
+ */
+void luo_flb_unregister_all(struct liveupdate_file_handler *fh)
+{
+	struct list_head *flb_list = &ACCESS_PRIVATE(fh, flb_list);
+	struct luo_flb_link *iter, *tmp;
+
+	if (!liveupdate_enabled())
+		return;
+
+	lockdep_assert_held_write(&luo_register_rwlock);
+	list_for_each_entry_safe(iter, tmp, flb_list, list)
+		luo_flb_unregister_one(fh, iter->flb);
+}
+
+/**
+ * liveupdate_register_flb - Associate an FLB with a file handler and register it globally.
+ * @fh:   The file handler that will now depend on the FLB.
+ * @flb:  The File-Lifecycle-Bound object to associate.
+ *
+ * Establishes a dependency, informing the LUO core that whenever a file of
+ * type @fh is preserved, the state of @flb must also be managed.
+ *
+ * On the first registration of a given @flb object, it is added to a global
+ * registry. This function checks for duplicate registrations, both for a
+ * specific handler and globally, and ensures the total number of unique
+ * FLBs does not exceed the system limit.
+ *
+ * Context: Typically called from a subsystem's module init function after
+ *          both the handler and the FLB have been defined and initialized.
+ * Return: 0 on success. Returns a negative errno on failure:
+ *         -EINVAL if arguments are NULL or not initialized.
+ *         -ENOMEM on memory allocation failure.
+ *         -EEXIST if this FLB is already registered with this handler.
+ *         -ENOSPC if the maximum number of global FLBs has been reached.
+ *         -EOPNOTSUPP if live update is disabled or not configured.
+ */
+int liveupdate_register_flb(struct liveupdate_file_handler *fh,
+			    struct liveupdate_flb *flb)
+{
+	struct luo_flb_private *private = luo_flb_get_private(flb);
+	struct list_head *flb_list = &ACCESS_PRIVATE(fh, flb_list);
+	struct luo_flb_link *link __free(kfree) = NULL;
+	struct liveupdate_flb *gflb;
+	struct luo_flb_link *iter;
+
+	if (!liveupdate_enabled())
+		return -EOPNOTSUPP;
+
+	if (WARN_ON(!flb->ops->preserve || !flb->ops->unpreserve ||
+		    !flb->ops->retrieve || !flb->ops->finish)) {
+		return -EINVAL;
+	}
+
+	/*
+	 * File handler must already be registered, as it initializes the
+	 * flb_list
+	 */
+	if (WARN_ON(list_empty(&ACCESS_PRIVATE(fh, list))))
+		return -EINVAL;
+
+	link = kzalloc_obj(*link);
+	if (!link)
+		return -ENOMEM;
+
+	guard(rwsem_write)(&luo_register_rwlock);
+
+	/* Check that this FLB is not already linked to this file handler */
+	list_for_each_entry(iter, flb_list, list) {
+		if (iter->flb == flb)
+			return -EEXIST;
+	}
+
+	/*
+	 * If this FLB is not linked to global list it's the first time the FLB
+	 * is registered
+	 */
+	if (!private->users) {
+		if (WARN_ON(!list_empty(&private->list)))
+			return -EINVAL;
+
+		if (luo_flb_global.count == LUO_FLB_MAX)
+			return -ENOSPC;
+
+		/* Check that compatible string is unique in global list */
+		list_private_for_each_entry(gflb, &luo_flb_global.list, private.list) {
+			if (!strcmp(gflb->compatible, flb->compatible))
+				return -EEXIST;
+		}
+
+		list_add_tail(&private->list, &luo_flb_global.list);
+		luo_flb_global.count++;
+	}
+
+	/* Finally, link the FLB to the file handler */
+	private->users++;
+	link->flb = flb;
+	list_add_tail(&no_free_ptr(link)->list, flb_list);
+
+	return 0;
+}
+
+/**
+ * liveupdate_unregister_flb - Remove an FLB dependency from a file handler.
+ * @fh:   The file handler that is currently depending on the FLB.
+ * @flb:  The File-Lifecycle-Bound object to remove.
+ *
+ * Removes the association between the specified file handler and the FLB
+ * previously established by liveupdate_register_flb().
+ *
+ * This function manages the global lifecycle of the FLB. It decrements the
+ * FLB's usage count. If this was the last file handler referencing this FLB,
+ * the FLB is removed from the global registry and the reference to its
+ * owner module (acquired during registration) is released.
+ *
+ * Context: It is typically called from a subsystem's module exit function.
+ */
+void liveupdate_unregister_flb(struct liveupdate_file_handler *fh,
+			       struct liveupdate_flb *flb)
+{
+	if (!liveupdate_enabled())
+		return;
+
+	guard(rwsem_write)(&luo_register_rwlock);
+
+	luo_flb_unregister_one(fh, flb);
+}
+
+/**
+ * liveupdate_flb_get_incoming - Retrieve the incoming FLB object.
+ * @flb:  The FLB definition.
+ * @objp: Output parameter; will be populated with the live shared object.
+ *
+ * Returns a pointer to its shared live object for the incoming (post-reboot)
+ * path.
+ *
+ * If this is the first time the object is requested in the new kernel, this
+ * function will trigger the FLB's .retrieve() callback to reconstruct the
+ * object from its preserved state. Subsequent calls will return the same
+ * cached object.
+ *
+ * Return: 0 on success, or a negative errno on failure. -ENODATA means no
+ * incoming FLB data, -ENOENT means specific flb not found in the incoming
+ * data, -ENODEV if the FLB's module is unloading, and -EOPNOTSUPP when
+ * live update is disabled or not configured.
+ */
+int liveupdate_flb_get_incoming(struct liveupdate_flb *flb, void **objp)
+{
+	struct luo_flb_private *private = luo_flb_get_private(flb);
+
+	if (!liveupdate_enabled())
+		return -EOPNOTSUPP;
+
+	guard(mutex)(&private->incoming.lock);
+
+	if (!private->incoming.obj) {
+		int err = luo_flb_retrieve_one(flb);
+
+		if (err)
+			return err;
+	}
+
+	refcount_inc(&private->incoming.count);
+	*objp = private->incoming.obj;
+
+	return 0;
+}
+
+/**
+ * liveupdate_flb_get_outgoing - Retrieve the outgoing FLB object.
+ * @flb:  The FLB definition.
+ * @objp: Output parameter; will be populated with the live shared object.
+ *
+ * Returns a pointer to its shared live object for the outgoing (pre-reboot)
+ * path.
+ *
+ * This function assumes the object has already been created by the FLB's
+ * .preserve() callback, which is triggered when the first dependent file
+ * is preserved.
+ *
+ * Return: 0 on success, or a negative errno on failure.
+ */
+int liveupdate_flb_get_outgoing(struct liveupdate_flb *flb, void **objp)
+{
+	struct luo_flb_private *private = luo_flb_get_private(flb);
+
+	if (!liveupdate_enabled())
+		return -EOPNOTSUPP;
+
+	guard(mutex)(&private->outgoing.lock);
+	*objp = private->outgoing.obj;
+
+	return 0;
+}
+
+int __init luo_flb_setup_outgoing(u64 *flbs_pa)
+{
+	struct luo_flb_header_ser *header_ser;
+
+	header_ser = kho_alloc_preserve(LUO_FLB_PGCNT << PAGE_SHIFT);
+	if (IS_ERR(header_ser))
+		return PTR_ERR(header_ser);
+
+	*flbs_pa = virt_to_phys(header_ser);
+
+	header_ser->pgcnt = LUO_FLB_PGCNT;
+	luo_flb_global.outgoing.header_ser = header_ser;
+	luo_flb_global.outgoing.ser = (void *)(header_ser + 1);
+	luo_flb_global.outgoing.active = true;
+
+	return 0;
+}
+
+void __init luo_flb_setup_incoming(u64 flbs_pa)
+{
+	struct luo_flb_header_ser *header_ser;
+
+	if (!flbs_pa)
+		return;
+
+	header_ser = phys_to_virt(flbs_pa);
+	luo_flb_global.incoming.header_ser = header_ser;
+	luo_flb_global.incoming.ser = (void *)(header_ser + 1);
+	luo_flb_global.incoming.active = true;
+}
+
+/**
+ * luo_flb_serialize - Serializes all active FLB objects for KHO.
+ *
+ * This function is called from the reboot path. It iterates through all
+ * registered File-Lifecycle-Bound (FLB) objects. For each FLB that has been
+ * preserved (i.e., its reference count is greater than zero), it writes its
+ * metadata into the memory region designated for Kexec Handover.
+ *
+ * The serialized data includes the FLB's compatibility string, its opaque
+ * data handle, and the final reference count. This allows the new kernel to
+ * find the appropriate handler and reconstruct the FLB's state.
+ *
+ * Context: Called from liveupdate_reboot() just before kho_finalize().
+ */
+void luo_flb_serialize(void)
+{
+	struct luo_flb_header *fh = &luo_flb_global.outgoing;
+	struct liveupdate_flb *gflb;
+	int i = 0;
+
+	guard(rwsem_read)(&luo_register_rwlock);
+	list_private_for_each_entry(gflb, &luo_flb_global.list, private.list) {
+		struct luo_flb_private *private = luo_flb_get_private(gflb);
+		long count = refcount_read(&private->outgoing.count);
+
+		if (count > 0) {
+			strscpy(fh->ser[i].name, gflb->compatible,
+				sizeof(fh->ser[i].name));
+			fh->ser[i].data = private->outgoing.data;
+			fh->ser[i].count = count;
+			i++;
+		}
+	}
+
+	fh->header_ser->count = i;
+}

linux-7.2.3/kernel/liveupdate/luo_internal.h

@@ -0,0 +1,115 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Copyright (c) 2025, Google LLC.
+ * Pasha Tatashin <pasha.tatashin@soleen.com>
+ */
+
+#ifndef _LINUX_LUO_INTERNAL_H
+#define _LINUX_LUO_INTERNAL_H
+
+#include <linux/liveupdate.h>
+#include <linux/uaccess.h>
+#include <linux/kho_block.h>
+
+struct luo_ucmd {
+	void __user *ubuffer;
+	u32 user_size;
+	void *cmd;
+};
+
+static inline int luo_ucmd_respond(struct luo_ucmd *ucmd,
+				   size_t kernel_cmd_size)
+{
+	/*
+	 * Copy the minimum of what the user provided and what we actually
+	 * have.
+	 */
+	if (copy_to_user(ucmd->ubuffer, ucmd->cmd,
+			 min_t(size_t, ucmd->user_size, kernel_cmd_size))) {
+		return -EFAULT;
+	}
+	return 0;
+}
+
+/*
+ * Handles a deserialization failure: devices and memory is in unpredictable
+ * state.
+ *
+ * Continuing the boot process after a failure is dangerous because it could
+ * lead to leaks of private data.
+ */
+#define luo_restore_fail(__fmt, ...) panic(__fmt, ##__VA_ARGS__)
+
+/**
+ * struct luo_file_set - A set of files that belong to the same sessions.
+ * @files_list: An ordered list of files associated with this session, it is
+ *              ordered by preservation time.
+ * @block_set:  The set of serialization blocks.
+ * @count:      A counter tracking the number of files currently stored in the
+ *              @files_list for this session.
+ */
+struct luo_file_set {
+	struct list_head files_list;
+	struct kho_block_set block_set;
+	u64 count;
+};
+
+/**
+ * struct luo_session - Represents an active or incoming Live Update session.
+ * @name:       A unique name for this session, used for identification and
+ *              retrieval.
+ * @list:       A list_head member used to link this session into a global list
+ *              of either outgoing (to be preserved) or incoming (restored from
+ *              previous kernel) sessions.
+ * @retrieved:  A boolean flag indicating whether this session has been
+ *              retrieved by a consumer in the new kernel.
+ * @file_set:   A set of files that belong to this session.
+ * @mutex:      protects fields in the luo_session.
+ */
+struct luo_session {
+	char name[LIVEUPDATE_SESSION_NAME_LENGTH];
+	struct list_head list;
+	bool retrieved;
+	struct luo_file_set file_set;
+	struct mutex mutex;
+};
+
+extern struct rw_semaphore luo_register_rwlock;
+
+int luo_session_create(const char *name, struct file **filep);
+int luo_session_retrieve(const char *name, struct file **filep);
+void __init luo_session_setup_outgoing(u64 *sessions_pa);
+int __init luo_session_setup_incoming(u64 sessions_pa);
+int luo_session_serialize(void);
+int luo_session_deserialize(void);
+
+int luo_preserve_file(struct luo_file_set *file_set, u64 token, int fd);
+void luo_file_unpreserve_files(struct luo_file_set *file_set);
+int luo_file_freeze(struct luo_file_set *file_set,
+		    struct luo_file_set_ser *file_set_ser);
+void luo_file_unfreeze(struct luo_file_set *file_set,
+		       struct luo_file_set_ser *file_set_ser);
+int luo_retrieve_file(struct luo_file_set *file_set, u64 token,
+		      struct file **filep);
+int luo_file_finish(struct luo_file_set *file_set);
+int luo_file_deserialize(struct luo_file_set *file_set,
+			 struct luo_file_set_ser *file_set_ser);
+void luo_file_set_init(struct luo_file_set *file_set);
+void luo_file_set_destroy(struct luo_file_set *file_set);
+
+int luo_flb_file_preserve(struct liveupdate_file_handler *fh);
+void luo_flb_file_unpreserve(struct liveupdate_file_handler *fh);
+void luo_flb_file_finish(struct liveupdate_file_handler *fh);
+void luo_flb_unregister_all(struct liveupdate_file_handler *fh);
+int __init luo_flb_setup_outgoing(u64 *flbs_pa);
+void __init luo_flb_setup_incoming(u64 flbs_pa);
+void luo_flb_serialize(void);
+
+#ifdef CONFIG_LIVEUPDATE_TEST
+void liveupdate_test_register(struct liveupdate_file_handler *fh);
+#else
+static inline void liveupdate_test_register(struct liveupdate_file_handler *fh) { }
+#endif
+
+#endif /* _LINUX_LUO_INTERNAL_H */

linux-7.2.3/kernel/liveupdate/luo_session.c

@@ -0,0 +1,682 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (c) 2025, Google LLC.
+ * Pasha Tatashin <pasha.tatashin@soleen.com>
+ */
+
+/**
+ * DOC: LUO Sessions
+ *
+ * LUO Sessions provide the core mechanism for grouping and managing `struct
+ * file *` instances that need to be preserved across a kexec-based live
+ * update. Each session acts as a named container for a set of file objects,
+ * allowing a userspace agent to manage the lifecycle of resources critical to a
+ * workload.
+ *
+ * Core Concepts:
+ *
+ * - Named Containers: Sessions are identified by a unique, user-provided name,
+ *   which is used for both creation in the current kernel and retrieval in the
+ *   next kernel.
+ *
+ * - Userspace Interface: Session management is driven from userspace via
+ *   ioctls on /dev/liveupdate.
+ *
+ * - Serialization: Session metadata is preserved using the KHO framework. When
+ *   a live update is triggered via kexec, session metadata is serialized into
+ *   a chain of linked-blocks and placed in a preserved memory region. The
+ *   physical address of the first block header is stored in the centralized
+ *   `struct luo_ser` structure.
+ *
+ * Session Lifecycle:
+ *
+ * 1.  Creation: A userspace agent calls `luo_session_create()` to create a
+ *     new, empty session and receives a file descriptor for it.
+ *
+ * 2.  Serialization: When the `reboot(LINUX_REBOOT_CMD_KEXEC)` syscall is
+ *     made, `luo_session_serialize()` is called. It iterates through all
+ *     active sessions and writes their metadata into a memory area preserved
+ *     by KHO.
+ *
+ * 3.  Deserialization (in new kernel): After kexec, `luo_session_deserialize()`
+ *     runs, reading the serialized data and creating a list of `struct
+ *     luo_session` objects representing the preserved sessions.
+ *
+ * 4.  Retrieval: A userspace agent in the new kernel can then call
+ *     `luo_session_retrieve()` with a session name to get a new file
+ *     descriptor and access the preserved state.
+ *
+ * Locking:
+ *
+ * The LUO session subsystem uses a three-tier locking hierarchy to ensure thread
+ * safety and prevent deadlocks during concurrent session mutations and kexec
+ * serialization:
+ *
+ * 1. `luo_session_serialize_rwsem` (global rwsem):
+ *    Protects session mutations (creation, retrieval, release, and ioctls)
+ *    against the serialization process during reboot.
+ *
+ *    - Readers: Taken by any path modifying or accessing session state (e.g.,
+ *      `luo_session_create()`, `luo_session_retrieve()`, `luo_session_release()`,
+ *      and `luo_session_ioctl()`).
+ *    - Writer: Taken by the serialization process (`luo_session_serialize()`)
+ *      during reboot. On success, the write lock is held indefinitely to freeze
+ *      the subsystem. On failure, it is released to allow recovery.
+ *
+ * 2. `luo_session_header->rwsem` (per-list rwsem):
+ *    Synchronizes list-level operations for the incoming and outgoing session headers.
+ *
+ *    - Writer: Taken during list mutation operations (inserting or removing a
+ *      session from the list).
+ *    - Reader: Taken when traversing the list (e.g., retrieving a session by name).
+ *
+ * 3. `luo_session->mutex` (per-session mutex):
+ *    Protects the internal state and file sets of an individual session. It is
+ *    acquired during per-session operations such as preserving, retrieving,
+ *    or freezing files.
+ *
+ * Lock Hierarchy:
+ *   `luo_session_serialize_rwsem` -> `luo_session_header->rwsem` -> `luo_session->mutex`
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/anon_inodes.h>
+#include <linux/cleanup.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/io.h>
+#include <linux/kexec_handover.h>
+#include <linux/kho_block.h>
+#include <linux/kho/abi/luo.h>
+#include <linux/list.h>
+#include <linux/liveupdate.h>
+#include <linux/mutex.h>
+#include <linux/rwsem.h>
+#include <linux/slab.h>
+#include <uapi/linux/liveupdate.h>
+#include "luo_internal.h"
+
+static DECLARE_RWSEM(luo_session_serialize_rwsem);
+/**
+ * struct luo_session_header - Header struct for managing LUO sessions.
+ * @count:       The number of sessions currently tracked in the @list.
+ * @list:        The head of the linked list of `struct luo_session` instances.
+ * @rwsem:       A read-write semaphore providing synchronized access to the
+ *               session list and other fields in this structure.
+ * @block_set:   The set of serialization blocks.
+ * @sessions_pa: Points to the location of sessions_pa within struct luo_ser.
+ * @active:      Set to true when first initialized. If previous kernel did not
+ *               send session data, active stays false for incoming.
+ */
+struct luo_session_header {
+	long count;
+	struct list_head list;
+	struct rw_semaphore rwsem;
+	struct kho_block_set block_set;
+	u64 *sessions_pa;
+	bool active;
+};
+
+/**
+ * struct luo_session_global - Global container for managing LUO sessions.
+ * @incoming:     The sessions passed from the previous kernel.
+ * @outgoing:     The sessions that are going to be passed to the next kernel.
+ */
+struct luo_session_global {
+	struct luo_session_header incoming;
+	struct luo_session_header outgoing;
+};
+
+static struct luo_session_global luo_session_global = {
+	.incoming = {
+		.list = LIST_HEAD_INIT(luo_session_global.incoming.list),
+		.rwsem = __RWSEM_INITIALIZER(luo_session_global.incoming.rwsem),
+		.block_set = KHO_BLOCK_SET_INIT(luo_session_global.incoming.block_set,
+						sizeof(struct luo_session_ser)),
+	},
+	.outgoing = {
+		.list = LIST_HEAD_INIT(luo_session_global.outgoing.list),
+		.rwsem = __RWSEM_INITIALIZER(luo_session_global.outgoing.rwsem),
+		.block_set = KHO_BLOCK_SET_INIT(luo_session_global.outgoing.block_set,
+						sizeof(struct luo_session_ser)),
+	},
+};
+
+static struct luo_session *luo_session_alloc(const char *name)
+{
+	struct luo_session *session = kzalloc_obj(*session);
+
+	if (!session)
+		return ERR_PTR(-ENOMEM);
+
+	strscpy(session->name, name, sizeof(session->name));
+	INIT_LIST_HEAD(&session->file_set.files_list);
+	luo_file_set_init(&session->file_set);
+	INIT_LIST_HEAD(&session->list);
+	mutex_init(&session->mutex);
+
+	return session;
+}
+
+static void luo_session_free(struct luo_session *session)
+{
+	luo_file_set_destroy(&session->file_set);
+	mutex_destroy(&session->mutex);
+	kfree(session);
+}
+
+static int luo_session_insert(struct luo_session_header *sh,
+			      struct luo_session *session)
+{
+	struct luo_session *it;
+	int err;
+
+	guard(rwsem_write)(&sh->rwsem);
+
+	/*
+	 * For outgoing we should make sure there is room in serialization array
+	 * for new session.
+	 */
+	if (sh == &luo_session_global.outgoing) {
+		err = kho_block_set_grow(&sh->block_set, sh->count + 1);
+		if (err)
+			return err;
+	}
+
+	/*
+	 * For small number of sessions this loop won't hurt performance
+	 * but if we ever start using a lot of sessions, this might
+	 * become a bottle neck during deserialization time, as it would
+	 * cause O(n*n) complexity.
+	 */
+	list_for_each_entry(it, &sh->list, list) {
+		if (!strncmp(it->name, session->name, sizeof(it->name)))
+			return -EEXIST;
+	}
+	list_add_tail(&session->list, &sh->list);
+	sh->count++;
+
+	return 0;
+}
+
+static void luo_session_remove(struct luo_session_header *sh,
+			       struct luo_session *session)
+{
+	guard(rwsem_write)(&sh->rwsem);
+	list_del(&session->list);
+	sh->count--;
+	if (sh == &luo_session_global.outgoing)
+		kho_block_set_shrink(&sh->block_set, sh->count);
+}
+
+static int luo_session_finish_one(struct luo_session *session)
+{
+	guard(mutex)(&session->mutex);
+	return luo_file_finish(&session->file_set);
+}
+
+static void luo_session_unfreeze_one(struct luo_session *session,
+				     struct luo_session_ser *ser)
+{
+	guard(mutex)(&session->mutex);
+	luo_file_unfreeze(&session->file_set, &ser->file_set_ser);
+}
+
+static int luo_session_freeze_one(struct luo_session *session,
+				  struct luo_session_ser *ser)
+{
+	guard(mutex)(&session->mutex);
+	return luo_file_freeze(&session->file_set, &ser->file_set_ser);
+}
+
+static int luo_session_release(struct inode *inodep, struct file *filep)
+{
+	struct luo_session *session = filep->private_data;
+	struct luo_session_header *sh;
+
+	guard(rwsem_read)(&luo_session_serialize_rwsem);
+	/* If retrieved is set, it means this session is from incoming list */
+	if (session->retrieved) {
+		int err = luo_session_finish_one(session);
+
+		if (err) {
+			pr_warn("Unable to finish session [%s] on release\n",
+				session->name);
+			return err;
+		}
+		sh = &luo_session_global.incoming;
+	} else {
+		scoped_guard(mutex, &session->mutex)
+			luo_file_unpreserve_files(&session->file_set);
+		sh = &luo_session_global.outgoing;
+	}
+
+	luo_session_remove(sh, session);
+	luo_session_free(session);
+
+	return 0;
+}
+
+static int luo_session_preserve_fd(struct luo_session *session,
+				   struct luo_ucmd *ucmd)
+{
+	struct liveupdate_session_preserve_fd *argp = ucmd->cmd;
+	int err;
+
+	guard(mutex)(&session->mutex);
+	err = luo_preserve_file(&session->file_set, argp->token, argp->fd);
+	if (err)
+		return err;
+
+	err = luo_ucmd_respond(ucmd, sizeof(*argp));
+	if (err)
+		pr_warn("The file was successfully preserved, but response to user failed\n");
+
+	return err;
+}
+
+static int luo_session_retrieve_fd(struct luo_session *session,
+				   struct luo_ucmd *ucmd)
+{
+	struct liveupdate_session_retrieve_fd *argp = ucmd->cmd;
+	struct file *file;
+	int err;
+
+	argp->fd = get_unused_fd_flags(O_CLOEXEC);
+	if (argp->fd < 0)
+		return argp->fd;
+
+	mutex_lock(&session->mutex);
+	err = luo_retrieve_file(&session->file_set, argp->token, &file);
+	mutex_unlock(&session->mutex);
+	if (err < 0)
+		goto err_put_fd;
+
+	err = luo_ucmd_respond(ucmd, sizeof(*argp));
+	if (err)
+		goto err_put_file;
+
+	fd_install(argp->fd, file);
+
+	return 0;
+
+err_put_file:
+	fput(file);
+err_put_fd:
+	put_unused_fd(argp->fd);
+
+	return err;
+}
+
+static int luo_session_finish(struct luo_session *session,
+			      struct luo_ucmd *ucmd)
+{
+	struct liveupdate_session_finish *argp = ucmd->cmd;
+	int err = luo_session_finish_one(session);
+
+	if (err)
+		return err;
+
+	return luo_ucmd_respond(ucmd, sizeof(*argp));
+}
+
+static int luo_session_get_name(struct luo_session *session,
+				struct luo_ucmd *ucmd)
+{
+	struct liveupdate_session_get_name *argp = ucmd->cmd;
+
+	if (argp->reserved != 0)
+		return -EINVAL;
+
+	strscpy((char *)argp->name, session->name, sizeof(argp->name));
+
+	return luo_ucmd_respond(ucmd, sizeof(*argp));
+}
+
+union ucmd_buffer {
+	struct liveupdate_session_finish finish;
+	struct liveupdate_session_preserve_fd preserve;
+	struct liveupdate_session_retrieve_fd retrieve;
+	struct liveupdate_session_get_name get_name;
+};
+
+/* Type of sessions the ioctl applies to. */
+enum luo_ioctl_type {
+	LUO_IOCTL_INCOMING,
+	LUO_IOCTL_OUTGOING,
+	LUO_IOCTL_ALL,
+};
+
+struct luo_ioctl_op {
+	unsigned int size;
+	unsigned int min_size;
+	unsigned int ioctl_num;
+	enum luo_ioctl_type type;
+	int (*execute)(struct luo_session *session, struct luo_ucmd *ucmd);
+};
+
+#define IOCTL_OP(_ioctl, _fn, _struct, _last, _type)                           \
+	[_IOC_NR(_ioctl) - LIVEUPDATE_CMD_SESSION_BASE] = {                    \
+		.size = sizeof(_struct) +                                      \
+			BUILD_BUG_ON_ZERO(sizeof(union ucmd_buffer) <          \
+					  sizeof(_struct)),                    \
+		.min_size = offsetofend(_struct, _last),                       \
+		.ioctl_num = _ioctl,                                           \
+		.type = _type,                                                 \
+		.execute = _fn,                                                \
+	}
+
+static const struct luo_ioctl_op luo_session_ioctl_ops[] = {
+	IOCTL_OP(LIVEUPDATE_SESSION_FINISH, luo_session_finish,
+		 struct liveupdate_session_finish, reserved, LUO_IOCTL_INCOMING),
+	IOCTL_OP(LIVEUPDATE_SESSION_PRESERVE_FD, luo_session_preserve_fd,
+		 struct liveupdate_session_preserve_fd, token, LUO_IOCTL_OUTGOING),
+	IOCTL_OP(LIVEUPDATE_SESSION_RETRIEVE_FD, luo_session_retrieve_fd,
+		 struct liveupdate_session_retrieve_fd, token, LUO_IOCTL_INCOMING),
+	IOCTL_OP(LIVEUPDATE_SESSION_GET_NAME, luo_session_get_name,
+		 struct liveupdate_session_get_name, name, LUO_IOCTL_ALL),
+};
+
+static bool luo_ioctl_type_valid(struct luo_session *session,
+				 const struct luo_ioctl_op *op)
+{
+	switch (op->type) {
+	case LUO_IOCTL_INCOMING:
+		/* Retrieved is only set on incoming sessions */
+		return session->retrieved;
+	case LUO_IOCTL_OUTGOING:
+		return !session->retrieved;
+	case LUO_IOCTL_ALL:
+		return true;
+	}
+
+	/* Catch-all. */
+	return false;
+}
+
+static long luo_session_ioctl(struct file *filep, unsigned int cmd,
+			      unsigned long arg)
+{
+	struct luo_session *session = filep->private_data;
+	const struct luo_ioctl_op *op;
+	struct luo_ucmd ucmd = {};
+	union ucmd_buffer buf;
+	unsigned int nr;
+	int ret;
+
+	nr = _IOC_NR(cmd);
+	if (nr < LIVEUPDATE_CMD_SESSION_BASE || (nr - LIVEUPDATE_CMD_SESSION_BASE) >=
+	    ARRAY_SIZE(luo_session_ioctl_ops)) {
+		return -EINVAL;
+	}
+
+	ucmd.ubuffer = (void __user *)arg;
+	ret = get_user(ucmd.user_size, (u32 __user *)ucmd.ubuffer);
+	if (ret)
+		return ret;
+
+	op = &luo_session_ioctl_ops[nr - LIVEUPDATE_CMD_SESSION_BASE];
+	if (op->ioctl_num != cmd)
+		return -ENOIOCTLCMD;
+	if (!luo_ioctl_type_valid(session, op))
+		return -EINVAL;
+	if (ucmd.user_size < op->min_size)
+		return -EINVAL;
+
+	ucmd.cmd = &buf;
+	ret = copy_struct_from_user(ucmd.cmd, op->size, ucmd.ubuffer,
+				    ucmd.user_size);
+	if (ret)
+		return ret;
+
+	guard(rwsem_read)(&luo_session_serialize_rwsem);
+	return op->execute(session, &ucmd);
+}
+
+static const struct file_operations luo_session_fops = {
+	.owner = THIS_MODULE,
+	.release = luo_session_release,
+	.unlocked_ioctl = luo_session_ioctl,
+};
+
+/* Create a "struct file" for session */
+static int luo_session_getfile(struct luo_session *session, struct file **filep)
+{
+	char name_buf[128];
+	struct file *file;
+
+	lockdep_assert_held(&session->mutex);
+	snprintf(name_buf, sizeof(name_buf), "[luo_session] %s", session->name);
+	file = anon_inode_getfile(name_buf, &luo_session_fops, session, O_RDWR);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	*filep = file;
+
+	return 0;
+}
+
+int luo_session_create(const char *name, struct file **filep)
+{
+	size_t len = strnlen(name, LIVEUPDATE_SESSION_NAME_LENGTH);
+	struct luo_session *session;
+	int err;
+
+	if (len == 0 || len > LIVEUPDATE_SESSION_NAME_LENGTH - 1)
+		return -EINVAL;
+
+	session = luo_session_alloc(name);
+	if (IS_ERR(session))
+		return PTR_ERR(session);
+
+	down_read(&luo_session_serialize_rwsem);
+	err = luo_session_insert(&luo_session_global.outgoing, session);
+	if (err)
+		goto err_free;
+
+	mutex_lock(&session->mutex);
+	err = luo_session_getfile(session, filep);
+	mutex_unlock(&session->mutex);
+	if (err)
+		goto err_remove;
+	up_read(&luo_session_serialize_rwsem);
+
+	return 0;
+
+err_remove:
+	luo_session_remove(&luo_session_global.outgoing, session);
+err_free:
+	luo_session_free(session);
+	up_read(&luo_session_serialize_rwsem);
+
+	return err;
+}
+
+int luo_session_retrieve(const char *name, struct file **filep)
+{
+	struct luo_session_header *sh = &luo_session_global.incoming;
+	struct luo_session *session = NULL;
+	struct luo_session *it;
+	int err;
+
+	guard(rwsem_read)(&luo_session_serialize_rwsem);
+	guard(rwsem_read)(&sh->rwsem);
+	list_for_each_entry(it, &sh->list, list) {
+		if (!strncmp(it->name, name, sizeof(it->name))) {
+			session = it;
+			break;
+		}
+	}
+
+	if (!session)
+		return -ENOENT;
+
+	guard(mutex)(&session->mutex);
+	if (session->retrieved)
+		return -EINVAL;
+
+	err = luo_session_getfile(session, filep);
+	if (!err)
+		session->retrieved = true;
+
+	return err;
+}
+
+void __init luo_session_setup_outgoing(u64 *sessions_pa)
+{
+	luo_session_global.outgoing.sessions_pa = sessions_pa;
+	luo_session_global.outgoing.active = true;
+}
+
+int __init luo_session_setup_incoming(u64 sessions_pa)
+{
+	struct luo_session_header *sh = &luo_session_global.incoming;
+	int err;
+
+	if (!sessions_pa)
+		return 0;
+
+	err = kho_block_set_restore(&sh->block_set, sessions_pa);
+	if (err)
+		return err;
+
+	sh->active = true;
+	return 0;
+}
+
+static int luo_session_deserialize_one(struct luo_session_header *sh,
+				       struct luo_session_ser *ser)
+{
+	struct luo_session *session;
+	int err;
+
+	session = luo_session_alloc(ser->name);
+	if (IS_ERR(session)) {
+		pr_warn("Failed to allocate session [%.*s] during deserialization %pe\n",
+			(int)sizeof(ser->name), ser->name, session);
+		return PTR_ERR(session);
+	}
+
+	err = luo_session_insert(sh, session);
+	if (err) {
+		pr_warn("Failed to insert session [%s] %pe\n",
+			session->name, ERR_PTR(err));
+		luo_session_free(session);
+		return err;
+	}
+
+	scoped_guard(mutex, &session->mutex) {
+		err = luo_file_deserialize(&session->file_set,
+					   &ser->file_set_ser);
+	}
+	if (err) {
+		pr_warn("Failed to deserialize files for session [%s] %pe\n",
+			session->name, ERR_PTR(err));
+		return err;
+	}
+
+	return 0;
+}
+
+int luo_session_deserialize(void)
+{
+	struct luo_session_header *sh = &luo_session_global.incoming;
+	static bool is_deserialized;
+	struct luo_session_ser *ser;
+	struct kho_block_set_it it;
+	static int saved_err;
+	int err;
+
+	/* If has been deserialized, always return the same error code */
+	if (is_deserialized)
+		return saved_err;
+
+	is_deserialized = true;
+	if (!sh->active)
+		return 0;
+
+	/*
+	 * Note on error handling:
+	 *
+	 * If deserialization fails (e.g., allocation failure or corrupt data),
+	 * we intentionally skip cleanup of sessions that were already restored.
+	 *
+	 * A partial failure leaves the preserved state inconsistent.
+	 * Implementing a safe "undo" to unwind complex dependencies (sessions,
+	 * files, hardware state) is error-prone and provides little value, as
+	 * the system is effectively in a broken state.
+	 *
+	 * We treat these resources as leaked. The expected recovery path is for
+	 * userspace to detect the failure and trigger a reboot, which will
+	 * reliably reset devices and reclaim memory.
+	 */
+	kho_block_set_it_init(&it, &sh->block_set);
+	while ((ser = kho_block_set_it_read_entry(&it))) {
+		err = luo_session_deserialize_one(sh, ser);
+		if (err)
+			goto save_err;
+	}
+
+	kho_block_set_destroy(&sh->block_set);
+
+	return 0;
+
+save_err:
+	kho_block_set_destroy(&sh->block_set);
+	saved_err = err;
+	return err;
+}
+
+int luo_session_serialize(void)
+{
+	struct luo_session_header *sh = &luo_session_global.outgoing;
+	struct luo_session *session;
+	struct kho_block_set_it it;
+	int err;
+
+	down_write(&luo_session_serialize_rwsem);
+	down_write(&sh->rwsem);
+	*sh->sessions_pa = 0;
+
+	kho_block_set_it_init(&it, &sh->block_set);
+
+	list_for_each_entry(session, &sh->list, list) {
+		struct luo_session_ser *ser = kho_block_set_it_reserve_entry(&it);
+
+		/* This should not fail normally as blocks were pre-allocated */
+		if (WARN_ON_ONCE(!ser)) {
+			err = -ENOSPC;
+			goto err_undo;
+		}
+
+		err = luo_session_freeze_one(session, ser);
+		if (err) {
+			kho_block_set_it_prev(&it);
+			goto err_undo;
+		}
+
+		strscpy(ser->name, session->name, sizeof(ser->name));
+	}
+
+	if (sh->count > 0)
+		*sh->sessions_pa = kho_block_set_head_pa(&sh->block_set);
+	up_write(&sh->rwsem);
+
+	return 0;
+
+err_undo:
+	list_for_each_entry_continue_reverse(session, &sh->list, list) {
+		struct luo_session_ser *ser = kho_block_set_it_prev(&it);
+
+		luo_session_unfreeze_one(session, ser);
+		memset(ser->name, 0, sizeof(ser->name));
+	}
+	up_write(&sh->rwsem);
+	up_write(&luo_session_serialize_rwsem);
+
+	return err;
+}