kho: drop notifiers

The KHO framework uses a notifier chain as the mechanism for clients to
participate in the finalization process.  While this works for a single,
central state machine, it is too restrictive for kernel-internal
components like pstore/reserve_mem or IMA.  These components need a
simpler, direct way to register their state for preservation (e.g., during
their initcall) without being part of a complex, shutdown-time notifier
sequence.  The notifier model forces all participants into a single
finalization flow and makes direct preservation from an arbitrary context
difficult.  This patch refactors the client participation model by
removing the notifier chain and introducing a direct API for managing FDT
subtrees.

The core kho_finalize() and kho_abort() state machine remains, but clients
now register their data with KHO beforehand.

Link: https://lkml.kernel.org/r/20251101142325.1326536-3-pasha.tatashin@soleen.com
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Co-developed-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Alexander Graf <graf@amazon.com>
Cc: Changyuan Lyu <changyuanl@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Pratyush Yadav <pratyush@kernel.org>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Simon Horman <horms@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Zhu Yanjun <yanjun.zhu@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

3 files changed, 104 insertions, 84 deletions

diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index befa6ceab574..3dd917bfedcc 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -16,7 +16,6 @@
 #include <linux/libfdt.h>
 #include <linux/list.h>
 #include <linux/memblock.h>
-#include <linux/notifier.h>
 #include <linux/page-isolation.h>
 #include <linux/vmalloc.h>
 
@@ -103,29 +102,34 @@ struct kho_mem_track {
 
 struct khoser_mem_chunk;
 
-struct kho_serialization {
-	struct page *fdt;
-	struct kho_mem_track track;
-	/* First chunk of serialized preserved memory map */
-	struct khoser_mem_chunk *preserved_mem_map;
+struct kho_sub_fdt {
+	struct list_head l;
+	const char *name;
+	void *fdt;
 };
 
 struct kho_out {
-	struct blocking_notifier_head chain_head;
-	struct mutex lock; /* protects KHO FDT finalization */
-	struct kho_serialization ser;
+	void *fdt;
 	bool finalized;
+	struct mutex lock; /* protects KHO FDT finalization */
+
+	struct list_head sub_fdts;
+	struct mutex fdts_lock;
+
+	struct kho_mem_track track;
+	/* First chunk of serialized preserved memory map */
+	struct khoser_mem_chunk *preserved_mem_map;
+
 	struct kho_debugfs dbg;
 };
 
 static struct kho_out kho_out = {
-	.chain_head = BLOCKING_NOTIFIER_INIT(kho_out.chain_head),
 	.lock = __MUTEX_INITIALIZER(kho_out.lock),
-	.ser = {
-		.track = {
-			.orders = XARRAY_INIT(kho_out.ser.track.orders, 0),
-		},
+	.track = {
+		.orders = XARRAY_INIT(kho_out.track.orders, 0),
 	},
+	.sub_fdts = LIST_HEAD_INIT(kho_out.sub_fdts),
+	.fdts_lock = __MUTEX_INITIALIZER(kho_out.fdts_lock),
 	.finalized = false,
 };
 
@@ -369,7 +373,7 @@ static void kho_mem_ser_free(struct khoser_mem_chunk *first_chunk)
 	}
 }
 
-static int kho_mem_serialize(struct kho_serialization *ser)
+static int kho_mem_serialize(struct kho_out *kho_out)
 {
 	struct khoser_mem_chunk *first_chunk = NULL;
 	struct khoser_mem_chunk *chunk = NULL;
@@ -377,7 +381,7 @@ static int kho_mem_serialize(struct kho_serialization *ser)
 	unsigned long order;
 	int err = -ENOMEM;
 
-	xa_for_each(&ser->track.orders, order, physxa) {
+	xa_for_each(&kho_out->track.orders, order, physxa) {
 		struct kho_mem_phys_bits *bits;
 		unsigned long phys;
 
@@ -409,7 +413,7 @@ static int kho_mem_serialize(struct kho_serialization *ser)
 		}
 	}
 
-	ser->preserved_mem_map = first_chunk;
+	kho_out->preserved_mem_map = first_chunk;
 
 	return 0;
 
@@ -670,7 +674,6 @@ err_disable_kho:
 
 /**
  * kho_add_subtree - record the physical address of a sub FDT in KHO root tree.
- * @ser: serialization control object passed by KHO notifiers.
  * @name: name of the sub tree.
  * @fdt: the sub tree blob.
  *
@@ -684,34 +687,41 @@ err_disable_kho:
  *
  * Return: 0 on success, error code on failure
  */
-int kho_add_subtree(struct kho_serialization *ser, const char *name, void *fdt)
+int kho_add_subtree(const char *name, void *fdt)
 {
-	int err = 0;
-	u64 phys = (u64)virt_to_phys(fdt);
-	void *root = page_to_virt(ser->fdt);
+	struct kho_sub_fdt *sub_fdt;
 
-	err |= fdt_begin_node(root, name);
-	err |= fdt_property(root, PROP_SUB_FDT, &phys, sizeof(phys));
-	err |= fdt_end_node(root);
+	sub_fdt = kmalloc(sizeof(*sub_fdt), GFP_KERNEL);
+	if (!sub_fdt)
+		return -ENOMEM;
 
-	if (err)
-		return err;
+	INIT_LIST_HEAD(&sub_fdt->l);
+	sub_fdt->name = name;
+	sub_fdt->fdt = fdt;
 
-	return kho_debugfs_fdt_add(&kho_out.dbg, name, fdt, false);
-}
-EXPORT_SYMBOL_GPL(kho_add_subtree);
+	guard(mutex)(&kho_out.fdts_lock);
+	list_add_tail(&sub_fdt->l, &kho_out.sub_fdts);
+	WARN_ON_ONCE(kho_debugfs_fdt_add(&kho_out.dbg, name, fdt, false));
 
-int register_kho_notifier(struct notifier_block *nb)
-{
-	return blocking_notifier_chain_register(&kho_out.chain_head, nb);
+	return 0;
 }
-EXPORT_SYMBOL_GPL(register_kho_notifier);
+EXPORT_SYMBOL_GPL(kho_add_subtree);
 
-int unregister_kho_notifier(struct notifier_block *nb)
+void kho_remove_subtree(void *fdt)
 {
-	return blocking_notifier_chain_unregister(&kho_out.chain_head, nb);
+	struct kho_sub_fdt *sub_fdt;
+
+	guard(mutex)(&kho_out.fdts_lock);
+	list_for_each_entry(sub_fdt, &kho_out.sub_fdts, l) {
+		if (sub_fdt->fdt == fdt) {
+			list_del(&sub_fdt->l);
+			kfree(sub_fdt);
+			kho_debugfs_fdt_remove(&kho_out.dbg, fdt);
+			break;
+		}
+	}
 }
-EXPORT_SYMBOL_GPL(unregister_kho_notifier);
+EXPORT_SYMBOL_GPL(kho_remove_subtree);
 
 /**
  * kho_preserve_folio - preserve a folio across kexec.
@@ -726,7 +736,7 @@ int kho_preserve_folio(struct folio *folio)
 {
 	const unsigned long pfn = folio_pfn(folio);
 	const unsigned int order = folio_order(folio);
-	struct kho_mem_track *track = &kho_out.ser.track;
+	struct kho_mem_track *track = &kho_out.track;
 
 	if (WARN_ON(kho_scratch_overlap(pfn << PAGE_SHIFT, PAGE_SIZE << order)))
 		return -EINVAL;
@@ -747,7 +757,7 @@ EXPORT_SYMBOL_GPL(kho_preserve_folio);
  */
 int kho_preserve_pages(struct page *page, unsigned int nr_pages)
 {
-	struct kho_mem_track *track = &kho_out.ser.track;
+	struct kho_mem_track *track = &kho_out.track;
 	const unsigned long start_pfn = page_to_pfn(page);
 	const unsigned long end_pfn = start_pfn + nr_pages;
 	unsigned long pfn = start_pfn;
@@ -849,7 +859,7 @@ err_free:
 static void kho_vmalloc_unpreserve_chunk(struct kho_vmalloc_chunk *chunk,
 					 unsigned short order)
 {
-	struct kho_mem_track *track = &kho_out.ser.track;
+	struct kho_mem_track *track = &kho_out.track;
 	unsigned long pfn = PHYS_PFN(virt_to_phys(chunk));
 
 	__kho_unpreserve(track, pfn, pfn + 1);
@@ -1031,11 +1041,11 @@ EXPORT_SYMBOL_GPL(kho_restore_vmalloc);
 
 static int __kho_abort(void)
 {
-	int err;
+	int err = 0;
 	unsigned long order;
 	struct kho_mem_phys *physxa;
 
-	xa_for_each(&kho_out.ser.track.orders, order, physxa) {
+	xa_for_each(&kho_out.track.orders, order, physxa) {
 		struct kho_mem_phys_bits *bits;
 		unsigned long phys;
 
@@ -1045,17 +1055,13 @@ static int __kho_abort(void)
 		xa_destroy(&physxa->phys_bits);
 		kfree(physxa);
 	}
-	xa_destroy(&kho_out.ser.track.orders);
+	xa_destroy(&kho_out.track.orders);
 
-	if (kho_out.ser.preserved_mem_map) {
-		kho_mem_ser_free(kho_out.ser.preserved_mem_map);
-		kho_out.ser.preserved_mem_map = NULL;
+	if (kho_out.preserved_mem_map) {
+		kho_mem_ser_free(kho_out.preserved_mem_map);
+		kho_out.preserved_mem_map = NULL;
 	}
 
-	err = blocking_notifier_call_chain(&kho_out.chain_head, KEXEC_KHO_ABORT,
-					   NULL);
-	err = notifier_to_errno(err);
-
 	if (err)
 		pr_err("Failed to abort KHO finalization: %d\n", err);
 
@@ -1078,7 +1084,8 @@ int kho_abort(void)
 		return ret;
 
 	kho_out.finalized = false;
-	kho_debugfs_cleanup(&kho_out.dbg);
+
+	kho_debugfs_fdt_remove(&kho_out.dbg, kho_out.fdt);
 
 	return 0;
 }
@@ -1087,41 +1094,46 @@ static int __kho_finalize(void)
 {
 	int err = 0;
 	u64 *preserved_mem_map;
-	void *fdt = page_to_virt(kho_out.ser.fdt);
+	void *root = kho_out.fdt;
+	struct kho_sub_fdt *fdt;
 
-	err |= fdt_create(fdt, PAGE_SIZE);
-	err |= fdt_finish_reservemap(fdt);
-	err |= fdt_begin_node(fdt, "");
-	err |= fdt_property_string(fdt, "compatible", KHO_FDT_COMPATIBLE);
+	err |= fdt_create(root, PAGE_SIZE);
+	err |= fdt_finish_reservemap(root);
+	err |= fdt_begin_node(root, "");
+	err |= fdt_property_string(root, "compatible", KHO_FDT_COMPATIBLE);
 	/**
 	 * Reserve the preserved-memory-map property in the root FDT, so
 	 * that all property definitions will precede subnodes created by
 	 * KHO callers.
 	 */
-	err |= fdt_property_placeholder(fdt, PROP_PRESERVED_MEMORY_MAP,
+	err |= fdt_property_placeholder(root, PROP_PRESERVED_MEMORY_MAP,
 					sizeof(*preserved_mem_map),
 					(void **)&preserved_mem_map);
 	if (err)
 		goto abort;
 
-	err = kho_preserve_folio(page_folio(kho_out.ser.fdt));
+	err = kho_preserve_folio(virt_to_folio(kho_out.fdt));
 	if (err)
 		goto abort;
 
-	err = blocking_notifier_call_chain(&kho_out.chain_head,
-					   KEXEC_KHO_FINALIZE, &kho_out.ser);
-	err = notifier_to_errno(err);
+	err = kho_mem_serialize(&kho_out);
 	if (err)
 		goto abort;
 
-	err = kho_mem_serialize(&kho_out.ser);
-	if (err)
-		goto abort;
+	*preserved_mem_map = (u64)virt_to_phys(kho_out.preserved_mem_map);
+
+	mutex_lock(&kho_out.fdts_lock);
+	list_for_each_entry(fdt, &kho_out.sub_fdts, l) {
+		phys_addr_t phys = virt_to_phys(fdt->fdt);
 
-	*preserved_mem_map = (u64)virt_to_phys(kho_out.ser.preserved_mem_map);
+		err |= fdt_begin_node(root, fdt->name);
+		err |= fdt_property(root, PROP_SUB_FDT, &phys, sizeof(phys));
+		err |= fdt_end_node(root);
+	}
+	mutex_unlock(&kho_out.fdts_lock);
 
-	err |= fdt_end_node(fdt);
-	err |= fdt_finish(fdt);
+	err |= fdt_end_node(root);
+	err |= fdt_finish(root);
 
 abort:
 	if (err) {
@@ -1149,8 +1161,10 @@ int kho_finalize(void)
 
 	kho_out.finalized = true;
 
-	return kho_debugfs_fdt_add(&kho_out.dbg, "fdt",
-				   page_to_virt(kho_out.ser.fdt), true);
+	WARN_ON_ONCE(kho_debugfs_fdt_add(&kho_out.dbg, "fdt",
+					 kho_out.fdt, true));
+
+	return 0;
 }
 
 bool kho_finalized(void)
@@ -1233,15 +1247,17 @@ static __init int kho_init(void)
 {
 	int err = 0;
 	const void *fdt = kho_get_fdt();
+	struct page *fdt_page;
 
 	if (!kho_enable)
 		return 0;
 
-	kho_out.ser.fdt = alloc_page(GFP_KERNEL);
-	if (!kho_out.ser.fdt) {
+	fdt_page = alloc_page(GFP_KERNEL);
+	if (!fdt_page) {
 		err = -ENOMEM;
 		goto err_free_scratch;
 	}
+	kho_out.fdt = page_to_virt(fdt_page);
 
 	err = kho_debugfs_init();
 	if (err)
@@ -1269,8 +1285,8 @@ static __init int kho_init(void)
 	return 0;
 
 err_free_fdt:
-	put_page(kho_out.ser.fdt);
-	kho_out.ser.fdt = NULL;
+	put_page(fdt_page);
+	kho_out.fdt = NULL;
 err_free_scratch:
 	for (int i = 0; i < kho_scratch_cnt; i++) {
 		void *start = __va(kho_scratch[i].addr);
@@ -1281,7 +1297,7 @@ err_free_scratch:
 	kho_enable = false;
 	return err;
 }
-late_initcall(kho_init);
+fs_initcall(kho_init);
 
 static void __init kho_release_scratch(void)
 {
@@ -1417,7 +1433,7 @@ int kho_fill_kimage(struct kimage *image)
 	if (!kho_out.finalized)
 		return 0;
 
-	image->kho.fdt = page_to_phys(kho_out.ser.fdt);
+	image->kho.fdt = virt_to_phys(kho_out.fdt);
 
 	scratch_size = sizeof(*kho_scratch) * kho_scratch_cnt;
 	scratch = (struct kexec_buf){
diff --git a/kernel/kexec_handover_debugfs.c b/kernel/kexec_handover_debugfs.c
index a91b279f1b23..46e9e6c0791f 100644
--- a/kernel/kexec_handover_debugfs.c
+++ b/kernel/kexec_handover_debugfs.c
@@ -61,14 +61,17 @@ int kho_debugfs_fdt_add(struct kho_debugfs *dbg, const char *name,
 	return __kho_debugfs_fdt_add(&dbg->fdt_list, dir, name, fdt);
 }
 
-void kho_debugfs_cleanup(struct kho_debugfs *dbg)
+void kho_debugfs_fdt_remove(struct kho_debugfs *dbg, void *fdt)
 {
-	struct fdt_debugfs *ff, *tmp;
-
-	list_for_each_entry_safe(ff, tmp, &dbg->fdt_list, list) {
-		debugfs_remove(ff->file);
-		list_del(&ff->list);
-		kfree(ff);
+	struct fdt_debugfs *ff;
+
+	list_for_each_entry(ff, &dbg->fdt_list, list) {
+		if (ff->wrapper.data == fdt) {
+			debugfs_remove(ff->file);
+			list_del(&ff->list);
+			kfree(ff);
+			break;
+		}
 	}
 }
 
diff --git a/kernel/kexec_handover_internal.h b/kernel/kexec_handover_internal.h
index 217b8b25a542..52ed73659fe6 100644
--- a/kernel/kexec_handover_internal.h
+++ b/kernel/kexec_handover_internal.h
@@ -32,7 +32,7 @@ void kho_in_debugfs_init(struct kho_debugfs *dbg, const void *fdt);
 int kho_out_debugfs_init(struct kho_debugfs *dbg);
 int kho_debugfs_fdt_add(struct kho_debugfs *dbg, const char *name,
 			const void *fdt, bool root);
-void kho_debugfs_cleanup(struct kho_debugfs *dbg);
+void kho_debugfs_fdt_remove(struct kho_debugfs *dbg, void *fdt);
 #else
 static inline int kho_debugfs_init(void) { return 0; }
 static inline void kho_in_debugfs_init(struct kho_debugfs *dbg,
@@ -40,7 +40,8 @@ static inline void kho_in_debugfs_init(struct kho_debugfs *dbg,
 static inline int kho_out_debugfs_init(struct kho_debugfs *dbg) { return 0; }
 static inline int kho_debugfs_fdt_add(struct kho_debugfs *dbg, const char *name,
 				      const void *fdt, bool root) { return 0; }
-static inline void kho_debugfs_cleanup(struct kho_debugfs *dbg) {}
+static inline void kho_debugfs_fdt_remove(struct kho_debugfs *dbg,
+					  void *fdt) { }
 #endif /* CONFIG_KEXEC_HANDOVER_DEBUGFS */
 
 #ifdef CONFIG_KEXEC_HANDOVER_DEBUG