* + kho-drop-notifiers.patch added to mm-nonmm-unstable branch
@ 2025-10-09 2:15 Andrew Morton
0 siblings, 0 replies; 3+ messages in thread
From: Andrew Morton @ 2025-10-09 2:15 UTC (permalink / raw)
To: mm-commits, tj, rdunlap, pratyush, pasha.tatashin, ojeda,
masahiroy, jgg, jgg, graf, corbet, brauner, rppt, akpm
The patch titled
Subject: kho: drop notifiers
has been added to the -mm mm-nonmm-unstable branch. Its filename is
kho-drop-notifiers.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/kho-drop-notifiers.patch
This patch will later appear in the mm-nonmm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Subject: kho: drop notifiers
Date: Tue, 7 Oct 2025 03:30:56 +0000
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/20251007033100.836886-4-pasha.tatashin@soleen.com
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Alexander Graf <graf@amazon.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: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/kexec_handover.h | 28 ----
kernel/kexec_handover.c | 164 ++++++++++++++++-------------
kernel/kexec_handover_debug.c | 15 +-
kernel/kexec_handover_internal.h | 5
lib/test_kho.c | 30 -----
mm/memblock.c | 60 +---------
6 files changed, 124 insertions(+), 178 deletions(-)
--- a/include/linux/kexec_handover.h~kho-drop-notifiers
+++ a/include/linux/kexec_handover.h
@@ -10,14 +10,7 @@ struct kho_scratch {
phys_addr_t size;
};
-/* KHO Notifier index */
-enum kho_event {
- KEXEC_KHO_FINALIZE = 0,
- KEXEC_KHO_ABORT = 1,
-};
-
struct folio;
-struct notifier_block;
struct page;
#define DECLARE_KHOSER_PTR(name, type) \
@@ -37,8 +30,6 @@ struct page;
(typeof((s).ptr))((s).phys ? phys_to_virt((s).phys) : NULL); \
})
-struct kho_serialization;
-
struct kho_vmalloc_chunk;
struct kho_vmalloc {
DECLARE_KHOSER_PTR(first, struct kho_vmalloc_chunk *);
@@ -57,12 +48,10 @@ int kho_preserve_vmalloc(void *ptr, stru
struct folio *kho_restore_folio(phys_addr_t phys);
struct page *kho_restore_pages(phys_addr_t phys, unsigned int nr_pages);
void *kho_restore_vmalloc(const struct kho_vmalloc *preservation);
-int kho_add_subtree(struct kho_serialization *ser, const char *name, void *fdt);
+int kho_add_subtree(const char *name, void *fdt);
+void kho_remove_subtree(void *fdt);
int kho_retrieve_subtree(const char *name, phys_addr_t *phys);
-int register_kho_notifier(struct notifier_block *nb);
-int unregister_kho_notifier(struct notifier_block *nb);
-
void kho_memory_init(void);
void kho_populate(phys_addr_t fdt_phys, u64 fdt_len, phys_addr_t scratch_phys,
@@ -114,23 +103,16 @@ static inline void *kho_restore_vmalloc(
return NULL;
}
-static inline int kho_add_subtree(struct kho_serialization *ser,
- const char *name, void *fdt)
+static inline int kho_add_subtree(const char *name, void *fdt)
{
return -EOPNOTSUPP;
}
-static inline int kho_retrieve_subtree(const char *name, phys_addr_t *phys)
+static inline void kho_remove_subtree(void *fdt)
{
- return -EOPNOTSUPP;
}
-static inline int register_kho_notifier(struct notifier_block *nb)
-{
- return -EOPNOTSUPP;
-}
-
-static inline int unregister_kho_notifier(struct notifier_block *nb)
+static inline int kho_retrieve_subtree(const char *name, phys_addr_t *phys)
{
return -EOPNOTSUPP;
}
--- a/kernel/kexec_handover.c~kho-drop-notifiers
+++ a/kernel/kexec_handover.c
@@ -15,7 +15,6 @@
#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>
@@ -99,29 +98,34 @@ 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,
};
@@ -362,14 +366,14 @@ static void kho_mem_ser_free(struct khos
}
}
-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;
struct kho_mem_phys *physxa;
unsigned long order;
- 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;
@@ -397,7 +401,7 @@ static int kho_mem_serialize(struct kho_
}
}
- ser->preserved_mem_map = first_chunk;
+ kho_out->preserved_mem_map = first_chunk;
return 0;
@@ -658,7 +662,6 @@ 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.
*
@@ -672,34 +675,45 @@ 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;
+ int err;
- 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;
+
+ mutex_lock(&kho_out.fdts_lock);
+ list_add_tail(&sub_fdt->l, &kho_out.sub_fdts);
+ err = kho_debugfs_fdt_add(&kho_out.dbg, name, fdt, false);
+ mutex_unlock(&kho_out.fdts_lock);
- return kho_debugfs_fdt_add(&kho_out.dbg, name, fdt, false);
+ return err;
}
EXPORT_SYMBOL_GPL(kho_add_subtree);
-int register_kho_notifier(struct notifier_block *nb)
+void kho_remove_subtree(void *fdt)
{
- return blocking_notifier_chain_register(&kho_out.chain_head, nb);
-}
-EXPORT_SYMBOL_GPL(register_kho_notifier);
+ struct kho_sub_fdt *sub_fdt;
+
+ mutex_lock(&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;
+ }
+ }
+ mutex_unlock(&kho_out.fdts_lock);
-int unregister_kho_notifier(struct notifier_block *nb)
-{
- return blocking_notifier_chain_unregister(&kho_out.chain_head, nb);
}
-EXPORT_SYMBOL_GPL(unregister_kho_notifier);
+EXPORT_SYMBOL_GPL(kho_remove_subtree);
/**
* kho_preserve_folio - preserve a folio across kexec.
@@ -714,7 +728,7 @@ int kho_preserve_folio(struct folio *fol
{
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;
return __kho_preserve_order(track, pfn, order);
}
@@ -732,7 +746,7 @@ 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;
@@ -828,7 +842,7 @@ err_free:
static void kho_vmalloc_unpreserve_chunk(struct kho_vmalloc_chunk *chunk)
{
- 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);
@@ -1010,11 +1024,11 @@ 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;
@@ -1024,17 +1038,13 @@ 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);
@@ -1057,7 +1067,8 @@ 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;
}
@@ -1066,41 +1077,46 @@ 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);
- *preserved_mem_map = (u64)virt_to_phys(kho_out.ser.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);
+
+ 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) {
@@ -1129,7 +1145,7 @@ 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);
+ kho_out.fdt, true);
}
bool kho_finalized(void)
@@ -1212,15 +1228,17 @@ 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)
@@ -1248,8 +1266,8 @@ 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);
@@ -1260,7 +1278,7 @@ err_free_scratch:
kho_enable = false;
return err;
}
-late_initcall(kho_init);
+fs_initcall(kho_init);
static void __init kho_release_scratch(void)
{
@@ -1396,7 +1414,7 @@ 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){
--- a/kernel/kexec_handover_debug.c~kho-drop-notifiers
+++ a/kernel/kexec_handover_debug.c
@@ -61,14 +61,17 @@ int kho_debugfs_fdt_add(struct kho_debug
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;
+ struct fdt_debugfs *ff;
- list_for_each_entry_safe(ff, tmp, &dbg->fdt_list, list) {
- debugfs_remove(ff->file);
- list_del(&ff->list);
- kfree(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;
+ }
}
}
--- a/kernel/kexec_handover_internal.h~kho-drop-notifiers
+++ a/kernel/kexec_handover_internal.h
@@ -30,7 +30,7 @@ void kho_in_debugfs_init(struct kho_debu
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,
@@ -38,7 +38,8 @@ static inline void kho_in_debugfs_init(s
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 */
#endif /* LINUX_KEXEC_HANDOVER_INTERNAL_H */
--- a/lib/test_kho.c~kho-drop-notifiers
+++ a/lib/test_kho.c
@@ -39,33 +39,17 @@ struct kho_test_state {
static struct kho_test_state kho_test_state;
-static int kho_test_notifier(struct notifier_block *self, unsigned long cmd,
- void *v)
+static int kho_test(void)
{
struct kho_test_state *state = &kho_test_state;
- struct kho_serialization *ser = v;
int err = 0;
- switch (cmd) {
- case KEXEC_KHO_ABORT:
- return NOTIFY_DONE;
- case KEXEC_KHO_FINALIZE:
- /* Handled below */
- break;
- default:
- return NOTIFY_BAD;
- }
-
err |= kho_preserve_folio(state->fdt);
- err |= kho_add_subtree(ser, KHO_TEST_FDT, folio_address(state->fdt));
+ err |= kho_add_subtree(KHO_TEST_FDT, folio_address(state->fdt));
return err ? NOTIFY_BAD : NOTIFY_DONE;
}
-static struct notifier_block kho_test_nb = {
- .notifier_call = kho_test_notifier,
-};
-
static int kho_test_save_data(struct kho_test_state *state, void *fdt)
{
phys_addr_t *folios_info __free(kvfree) = NULL;
@@ -102,6 +86,9 @@ static int kho_test_save_data(struct kho
if (!err)
state->folios_info = no_free_ptr(folios_info);
+ if (!err)
+ err = kho_test();
+
return err;
}
@@ -203,14 +190,8 @@ static int kho_test_save(void)
if (err)
goto err_free_folios;
- err = register_kho_notifier(&kho_test_nb);
- if (err)
- goto err_free_fdt;
-
return 0;
-err_free_fdt:
- folio_put(state->fdt);
err_free_folios:
kvfree(folios);
return err;
@@ -326,7 +307,6 @@ static void kho_test_cleanup(void)
static void __exit kho_test_exit(void)
{
- unregister_kho_notifier(&kho_test_nb);
kho_test_cleanup();
}
module_exit(kho_test_exit);
--- a/mm/memblock.c~kho-drop-notifiers
+++ a/mm/memblock.c
@@ -2444,53 +2444,18 @@ int reserve_mem_release_by_name(const ch
#define MEMBLOCK_KHO_FDT "memblock"
#define MEMBLOCK_KHO_NODE_COMPATIBLE "memblock-v1"
#define RESERVE_MEM_KHO_NODE_COMPATIBLE "reserve-mem-v1"
-static struct page *kho_fdt;
-
-static int reserve_mem_kho_finalize(struct kho_serialization *ser)
-{
- int err = 0, i;
-
- for (i = 0; i < reserved_mem_count; i++) {
- struct reserve_mem_table *map = &reserved_mem_table[i];
- struct page *page = phys_to_page(map->start);
- unsigned int nr_pages = map->size >> PAGE_SHIFT;
-
- err |= kho_preserve_pages(page, nr_pages);
- }
-
- err |= kho_preserve_folio(page_folio(kho_fdt));
- err |= kho_add_subtree(ser, MEMBLOCK_KHO_FDT, page_to_virt(kho_fdt));
-
- return notifier_from_errno(err);
-}
-
-static int reserve_mem_kho_notifier(struct notifier_block *self,
- unsigned long cmd, void *v)
-{
- switch (cmd) {
- case KEXEC_KHO_FINALIZE:
- return reserve_mem_kho_finalize((struct kho_serialization *)v);
- case KEXEC_KHO_ABORT:
- return NOTIFY_DONE;
- default:
- return NOTIFY_BAD;
- }
-}
-
-static struct notifier_block reserve_mem_kho_nb = {
- .notifier_call = reserve_mem_kho_notifier,
-};
static int __init prepare_kho_fdt(void)
{
int err = 0, i;
+ struct page *fdt_page;
void *fdt;
- kho_fdt = alloc_page(GFP_KERNEL);
- if (!kho_fdt)
+ fdt_page = alloc_page(GFP_KERNEL);
+ if (!fdt_page)
return -ENOMEM;
- fdt = page_to_virt(kho_fdt);
+ fdt = page_to_virt(fdt_page);
err |= fdt_create(fdt, PAGE_SIZE);
err |= fdt_finish_reservemap(fdt);
@@ -2499,7 +2464,10 @@ static int __init prepare_kho_fdt(void)
err |= fdt_property_string(fdt, "compatible", MEMBLOCK_KHO_NODE_COMPATIBLE);
for (i = 0; i < reserved_mem_count; i++) {
struct reserve_mem_table *map = &reserved_mem_table[i];
+ struct page *page = phys_to_page(map->start);
+ unsigned int nr_pages = map->size >> PAGE_SHIFT;
+ err |= kho_preserve_pages(page, nr_pages);
err |= fdt_begin_node(fdt, map->name);
err |= fdt_property_string(fdt, "compatible", RESERVE_MEM_KHO_NODE_COMPATIBLE);
err |= fdt_property(fdt, "start", &map->start, sizeof(map->start));
@@ -2507,13 +2475,14 @@ static int __init prepare_kho_fdt(void)
err |= fdt_end_node(fdt);
}
err |= fdt_end_node(fdt);
-
err |= fdt_finish(fdt);
+ err |= kho_preserve_folio(page_folio(fdt_page));
+ err |= kho_add_subtree(MEMBLOCK_KHO_FDT, fdt);
+
if (err) {
pr_err("failed to prepare memblock FDT for KHO: %d\n", err);
- put_page(kho_fdt);
- kho_fdt = NULL;
+ put_page(fdt_page);
}
return err;
@@ -2529,13 +2498,6 @@ static int __init reserve_mem_init(void)
err = prepare_kho_fdt();
if (err)
return err;
-
- err = register_kho_notifier(&reserve_mem_kho_nb);
- if (err) {
- put_page(kho_fdt);
- kho_fdt = NULL;
- }
-
return err;
}
late_initcall(reserve_mem_init);
_
Patches currently in -mm which might be from rppt@kernel.org are
kho-drop-notifiers.patch
^ permalink raw reply [flat|nested] 3+ messages in thread
* + kho-drop-notifiers.patch added to mm-nonmm-unstable branch
@ 2025-10-26 4:06 Andrew Morton
0 siblings, 0 replies; 3+ messages in thread
From: Andrew Morton @ 2025-10-26 4:06 UTC (permalink / raw)
To: mm-commits, tj, rdunlap, pratyush, pasha.tatashin, ojeda,
masahiroy, jgg, jgg, graf, corbet, brauner, rppt, akpm
The patch titled
Subject: kho: drop notifiers
has been added to the -mm mm-nonmm-unstable branch. Its filename is
kho-drop-notifiers.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/kho-drop-notifiers.patch
This patch will later appear in the mm-nonmm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Subject: kho: drop notifiers
Date: Fri, 24 Oct 2025 12:09:57 -0400
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/20251024161002.747372-4-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>
Reviewed-by: Pratyush Yadav <pratyush@kernel.org>
Cc: Alexander Graf <graf@amazon.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: Randy Dunlap <rdunlap@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/kexec_handover.h | 28 ----
kernel/kexec_handover.c | 164 +++++++++++++++--------------
kernel/kexec_handover_debugfs.c | 15 +-
kernel/kexec_handover_internal.h | 5
lib/test_kho.c | 33 -----
mm/memblock.c | 62 ++--------
6 files changed, 124 insertions(+), 183 deletions(-)
--- a/include/linux/kexec_handover.h~kho-drop-notifiers
+++ a/include/linux/kexec_handover.h
@@ -10,14 +10,7 @@ struct kho_scratch {
phys_addr_t size;
};
-/* KHO Notifier index */
-enum kho_event {
- KEXEC_KHO_FINALIZE = 0,
- KEXEC_KHO_ABORT = 1,
-};
-
struct folio;
-struct notifier_block;
struct page;
#define DECLARE_KHOSER_PTR(name, type) \
@@ -37,8 +30,6 @@ struct page;
(typeof((s).ptr))((s).phys ? phys_to_virt((s).phys) : NULL); \
})
-struct kho_serialization;
-
struct kho_vmalloc_chunk;
struct kho_vmalloc {
DECLARE_KHOSER_PTR(first, struct kho_vmalloc_chunk *);
@@ -57,12 +48,10 @@ int kho_preserve_vmalloc(void *ptr, stru
struct folio *kho_restore_folio(phys_addr_t phys);
struct page *kho_restore_pages(phys_addr_t phys, unsigned int nr_pages);
void *kho_restore_vmalloc(const struct kho_vmalloc *preservation);
-int kho_add_subtree(struct kho_serialization *ser, const char *name, void *fdt);
+int kho_add_subtree(const char *name, void *fdt);
+void kho_remove_subtree(void *fdt);
int kho_retrieve_subtree(const char *name, phys_addr_t *phys);
-int register_kho_notifier(struct notifier_block *nb);
-int unregister_kho_notifier(struct notifier_block *nb);
-
void kho_memory_init(void);
void kho_populate(phys_addr_t fdt_phys, u64 fdt_len, phys_addr_t scratch_phys,
@@ -114,23 +103,16 @@ static inline void *kho_restore_vmalloc(
return NULL;
}
-static inline int kho_add_subtree(struct kho_serialization *ser,
- const char *name, void *fdt)
+static inline int kho_add_subtree(const char *name, void *fdt)
{
return -EOPNOTSUPP;
}
-static inline int kho_retrieve_subtree(const char *name, phys_addr_t *phys)
+static inline void kho_remove_subtree(void *fdt)
{
- return -EOPNOTSUPP;
}
-static inline int register_kho_notifier(struct notifier_block *nb)
-{
- return -EOPNOTSUPP;
-}
-
-static inline int unregister_kho_notifier(struct notifier_block *nb)
+static inline int kho_retrieve_subtree(const char *name, phys_addr_t *phys)
{
return -EOPNOTSUPP;
}
--- a/kernel/kexec_handover.c~kho-drop-notifiers
+++ a/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 khos
}
}
-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_
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_
}
}
- 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;
+
+ 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));
- return kho_debugfs_fdt_add(&kho_out.dbg, name, fdt, false);
+ return 0;
}
EXPORT_SYMBOL_GPL(kho_add_subtree);
-int register_kho_notifier(struct notifier_block *nb)
+void kho_remove_subtree(void *fdt)
{
- return blocking_notifier_chain_register(&kho_out.chain_head, nb);
-}
-EXPORT_SYMBOL_GPL(register_kho_notifier);
+ struct kho_sub_fdt *sub_fdt;
-int unregister_kho_notifier(struct notifier_block *nb)
-{
- return blocking_notifier_chain_unregister(&kho_out.chain_head, nb);
+ 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 *fol
{
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;
@@ -848,7 +858,7 @@ err_free:
static void kho_vmalloc_unpreserve_chunk(struct kho_vmalloc_chunk *chunk)
{
- 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);
@@ -1030,11 +1040,11 @@ 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;
@@ -1044,17 +1054,13 @@ 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);
@@ -1077,7 +1083,8 @@ 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;
}
@@ -1086,41 +1093,46 @@ 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) {
@@ -1148,8 +1160,10 @@ 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)
@@ -1232,15 +1246,17 @@ 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)
@@ -1268,8 +1284,8 @@ 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);
@@ -1280,7 +1296,7 @@ err_free_scratch:
kho_enable = false;
return err;
}
-late_initcall(kho_init);
+fs_initcall(kho_init);
static void __init kho_release_scratch(void)
{
@@ -1416,7 +1432,7 @@ 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){
--- a/kernel/kexec_handover_debugfs.c~kho-drop-notifiers
+++ a/kernel/kexec_handover_debugfs.c
@@ -61,14 +61,17 @@ int kho_debugfs_fdt_add(struct kho_debug
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;
+ struct fdt_debugfs *ff;
- list_for_each_entry_safe(ff, tmp, &dbg->fdt_list, list) {
- debugfs_remove(ff->file);
- list_del(&ff->list);
- kfree(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;
+ }
}
}
--- a/kernel/kexec_handover_internal.h~kho-drop-notifiers
+++ a/kernel/kexec_handover_internal.h
@@ -30,7 +30,7 @@ void kho_in_debugfs_init(struct kho_debu
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,
@@ -38,7 +38,8 @@ static inline void kho_in_debugfs_init(s
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
--- a/lib/test_kho.c~kho-drop-notifiers
+++ a/lib/test_kho.c
@@ -39,33 +39,6 @@ struct kho_test_state {
static struct kho_test_state kho_test_state;
-static int kho_test_notifier(struct notifier_block *self, unsigned long cmd,
- void *v)
-{
- struct kho_test_state *state = &kho_test_state;
- struct kho_serialization *ser = v;
- int err = 0;
-
- switch (cmd) {
- case KEXEC_KHO_ABORT:
- return NOTIFY_DONE;
- case KEXEC_KHO_FINALIZE:
- /* Handled below */
- break;
- default:
- return NOTIFY_BAD;
- }
-
- err |= kho_preserve_folio(state->fdt);
- err |= kho_add_subtree(ser, KHO_TEST_FDT, folio_address(state->fdt));
-
- return err ? NOTIFY_BAD : NOTIFY_DONE;
-}
-
-static struct notifier_block kho_test_nb = {
- .notifier_call = kho_test_notifier,
-};
-
static int kho_test_save_data(struct kho_test_state *state, void *fdt)
{
phys_addr_t *folios_info __free(kvfree) = NULL;
@@ -120,6 +93,7 @@ static int kho_test_prepare_fdt(struct k
fdt = folio_address(state->fdt);
+ err |= kho_preserve_folio(state->fdt);
err |= fdt_create(fdt, fdt_size);
err |= fdt_finish_reservemap(fdt);
@@ -131,6 +105,7 @@ static int kho_test_prepare_fdt(struct k
err |= fdt_finish(fdt);
+ err = kho_add_subtree(KHO_TEST_FDT, folio_address(state->fdt));
if (err)
folio_put(state->fdt);
@@ -203,7 +178,7 @@ static int kho_test_save(void)
if (err)
goto err_free_folios;
- err = register_kho_notifier(&kho_test_nb);
+ err = kho_add_subtree(KHO_TEST_FDT, folio_address(state->fdt));
if (err)
goto err_free_fdt;
@@ -326,7 +301,7 @@ static void kho_test_cleanup(void)
static void __exit kho_test_exit(void)
{
- unregister_kho_notifier(&kho_test_nb);
+ kho_remove_subtree(folio_address(kho_test_state.fdt));
kho_test_cleanup();
}
module_exit(kho_test_exit);
--- a/mm/memblock.c~kho-drop-notifiers
+++ a/mm/memblock.c
@@ -2444,53 +2444,18 @@ int reserve_mem_release_by_name(const ch
#define MEMBLOCK_KHO_FDT "memblock"
#define MEMBLOCK_KHO_NODE_COMPATIBLE "memblock-v1"
#define RESERVE_MEM_KHO_NODE_COMPATIBLE "reserve-mem-v1"
-static struct page *kho_fdt;
-
-static int reserve_mem_kho_finalize(struct kho_serialization *ser)
-{
- int err = 0, i;
-
- for (i = 0; i < reserved_mem_count; i++) {
- struct reserve_mem_table *map = &reserved_mem_table[i];
- struct page *page = phys_to_page(map->start);
- unsigned int nr_pages = map->size >> PAGE_SHIFT;
-
- err |= kho_preserve_pages(page, nr_pages);
- }
-
- err |= kho_preserve_folio(page_folio(kho_fdt));
- err |= kho_add_subtree(ser, MEMBLOCK_KHO_FDT, page_to_virt(kho_fdt));
-
- return notifier_from_errno(err);
-}
-
-static int reserve_mem_kho_notifier(struct notifier_block *self,
- unsigned long cmd, void *v)
-{
- switch (cmd) {
- case KEXEC_KHO_FINALIZE:
- return reserve_mem_kho_finalize((struct kho_serialization *)v);
- case KEXEC_KHO_ABORT:
- return NOTIFY_DONE;
- default:
- return NOTIFY_BAD;
- }
-}
-
-static struct notifier_block reserve_mem_kho_nb = {
- .notifier_call = reserve_mem_kho_notifier,
-};
static int __init prepare_kho_fdt(void)
{
int err = 0, i;
+ struct page *fdt_page;
void *fdt;
- kho_fdt = alloc_page(GFP_KERNEL);
- if (!kho_fdt)
+ fdt_page = alloc_page(GFP_KERNEL);
+ if (!fdt_page)
return -ENOMEM;
- fdt = page_to_virt(kho_fdt);
+ fdt = page_to_virt(fdt_page);
err |= fdt_create(fdt, PAGE_SIZE);
err |= fdt_finish_reservemap(fdt);
@@ -2499,7 +2464,10 @@ static int __init prepare_kho_fdt(void)
err |= fdt_property_string(fdt, "compatible", MEMBLOCK_KHO_NODE_COMPATIBLE);
for (i = 0; i < reserved_mem_count; i++) {
struct reserve_mem_table *map = &reserved_mem_table[i];
+ struct page *page = phys_to_page(map->start);
+ unsigned int nr_pages = map->size >> PAGE_SHIFT;
+ err |= kho_preserve_pages(page, nr_pages);
err |= fdt_begin_node(fdt, map->name);
err |= fdt_property_string(fdt, "compatible", RESERVE_MEM_KHO_NODE_COMPATIBLE);
err |= fdt_property(fdt, "start", &map->start, sizeof(map->start));
@@ -2507,13 +2475,16 @@ static int __init prepare_kho_fdt(void)
err |= fdt_end_node(fdt);
}
err |= fdt_end_node(fdt);
-
err |= fdt_finish(fdt);
+ err |= kho_preserve_folio(page_folio(fdt_page));
+
+ if (!err)
+ err = kho_add_subtree(MEMBLOCK_KHO_FDT, fdt);
+
if (err) {
pr_err("failed to prepare memblock FDT for KHO: %d\n", err);
- put_page(kho_fdt);
- kho_fdt = NULL;
+ put_page(fdt_page);
}
return err;
@@ -2529,13 +2500,6 @@ static int __init reserve_mem_init(void)
err = prepare_kho_fdt();
if (err)
return err;
-
- err = register_kho_notifier(&reserve_mem_kho_nb);
- if (err) {
- put_page(kho_fdt);
- kho_fdt = NULL;
- }
-
return err;
}
late_initcall(reserve_mem_init);
_
Patches currently in -mm which might be from rppt@kernel.org are
kho-drop-notifiers.patch
^ permalink raw reply [flat|nested] 3+ messages in thread
* + kho-drop-notifiers.patch added to mm-nonmm-unstable branch
@ 2025-11-04 3:26 Andrew Morton
0 siblings, 0 replies; 3+ messages in thread
From: Andrew Morton @ 2025-11-04 3:26 UTC (permalink / raw)
To: mm-commits, yanjun.zhu, tj, rdunlap, pratyush, pasha.tatashin,
ojeda, masahiroy, jgg, jgg, horms, graf, corbet, changyuanl,
brauner, rppt, akpm
The patch titled
Subject: kho: drop notifiers
has been added to the -mm mm-nonmm-unstable branch. Its filename is
kho-drop-notifiers.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/kho-drop-notifiers.patch
This patch will later appear in the mm-nonmm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Subject: kho: drop notifiers
Date: Sat, 1 Nov 2025 10:23:18 -0400
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>
---
include/linux/kexec_handover.h | 28 ----
kernel/kexec_handover.c | 164 +++++++++++++++--------------
kernel/kexec_handover_debugfs.c | 15 +-
kernel/kexec_handover_internal.h | 5
lib/test_kho.c | 35 ------
mm/memblock.c | 62 ++--------
6 files changed, 123 insertions(+), 186 deletions(-)
--- a/include/linux/kexec_handover.h~kho-drop-notifiers
+++ a/include/linux/kexec_handover.h
@@ -10,14 +10,7 @@ struct kho_scratch {
phys_addr_t size;
};
-/* KHO Notifier index */
-enum kho_event {
- KEXEC_KHO_FINALIZE = 0,
- KEXEC_KHO_ABORT = 1,
-};
-
struct folio;
-struct notifier_block;
struct page;
#define DECLARE_KHOSER_PTR(name, type) \
@@ -37,8 +30,6 @@ struct page;
(typeof((s).ptr))((s).phys ? phys_to_virt((s).phys) : NULL); \
})
-struct kho_serialization;
-
struct kho_vmalloc_chunk;
struct kho_vmalloc {
DECLARE_KHOSER_PTR(first, struct kho_vmalloc_chunk *);
@@ -57,12 +48,10 @@ int kho_preserve_vmalloc(void *ptr, stru
struct folio *kho_restore_folio(phys_addr_t phys);
struct page *kho_restore_pages(phys_addr_t phys, unsigned int nr_pages);
void *kho_restore_vmalloc(const struct kho_vmalloc *preservation);
-int kho_add_subtree(struct kho_serialization *ser, const char *name, void *fdt);
+int kho_add_subtree(const char *name, void *fdt);
+void kho_remove_subtree(void *fdt);
int kho_retrieve_subtree(const char *name, phys_addr_t *phys);
-int register_kho_notifier(struct notifier_block *nb);
-int unregister_kho_notifier(struct notifier_block *nb);
-
void kho_memory_init(void);
void kho_populate(phys_addr_t fdt_phys, u64 fdt_len, phys_addr_t scratch_phys,
@@ -110,23 +99,16 @@ static inline void *kho_restore_vmalloc(
return NULL;
}
-static inline int kho_add_subtree(struct kho_serialization *ser,
- const char *name, void *fdt)
+static inline int kho_add_subtree(const char *name, void *fdt)
{
return -EOPNOTSUPP;
}
-static inline int kho_retrieve_subtree(const char *name, phys_addr_t *phys)
+static inline void kho_remove_subtree(void *fdt)
{
- return -EOPNOTSUPP;
}
-static inline int register_kho_notifier(struct notifier_block *nb)
-{
- return -EOPNOTSUPP;
-}
-
-static inline int unregister_kho_notifier(struct notifier_block *nb)
+static inline int kho_retrieve_subtree(const char *name, phys_addr_t *phys)
{
return -EOPNOTSUPP;
}
--- a/kernel/kexec_handover.c~kho-drop-notifiers
+++ a/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 khos
}
}
-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_
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_
}
}
- 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;
+
+ 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));
- return kho_debugfs_fdt_add(&kho_out.dbg, name, fdt, false);
+ return 0;
}
EXPORT_SYMBOL_GPL(kho_add_subtree);
-int register_kho_notifier(struct notifier_block *nb)
+void kho_remove_subtree(void *fdt)
{
- return blocking_notifier_chain_register(&kho_out.chain_head, nb);
-}
-EXPORT_SYMBOL_GPL(register_kho_notifier);
+ struct kho_sub_fdt *sub_fdt;
-int unregister_kho_notifier(struct notifier_block *nb)
-{
- return blocking_notifier_chain_unregister(&kho_out.chain_head, nb);
+ 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 *fol
{
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){
--- a/kernel/kexec_handover_debugfs.c~kho-drop-notifiers
+++ a/kernel/kexec_handover_debugfs.c
@@ -61,14 +61,17 @@ int kho_debugfs_fdt_add(struct kho_debug
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;
+ struct fdt_debugfs *ff;
- list_for_each_entry_safe(ff, tmp, &dbg->fdt_list, list) {
- debugfs_remove(ff->file);
- list_del(&ff->list);
- kfree(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;
+ }
}
}
--- a/kernel/kexec_handover_internal.h~kho-drop-notifiers
+++ a/kernel/kexec_handover_internal.h
@@ -32,7 +32,7 @@ void kho_in_debugfs_init(struct kho_debu
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(s
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
--- a/lib/test_kho.c~kho-drop-notifiers
+++ a/lib/test_kho.c
@@ -39,33 +39,6 @@ struct kho_test_state {
static struct kho_test_state kho_test_state;
-static int kho_test_notifier(struct notifier_block *self, unsigned long cmd,
- void *v)
-{
- struct kho_test_state *state = &kho_test_state;
- struct kho_serialization *ser = v;
- int err = 0;
-
- switch (cmd) {
- case KEXEC_KHO_ABORT:
- return NOTIFY_DONE;
- case KEXEC_KHO_FINALIZE:
- /* Handled below */
- break;
- default:
- return NOTIFY_BAD;
- }
-
- err |= kho_preserve_folio(state->fdt);
- err |= kho_add_subtree(ser, KHO_TEST_FDT, folio_address(state->fdt));
-
- return err ? NOTIFY_BAD : NOTIFY_DONE;
-}
-
-static struct notifier_block kho_test_nb = {
- .notifier_call = kho_test_notifier,
-};
-
static int kho_test_save_data(struct kho_test_state *state, void *fdt)
{
phys_addr_t *folios_info __free(kvfree) = NULL;
@@ -120,6 +93,7 @@ static int kho_test_prepare_fdt(struct k
fdt = folio_address(state->fdt);
+ err |= kho_preserve_folio(state->fdt);
err |= fdt_create(fdt, fdt_size);
err |= fdt_finish_reservemap(fdt);
@@ -131,6 +105,7 @@ static int kho_test_prepare_fdt(struct k
err |= fdt_finish(fdt);
+ err = kho_add_subtree(KHO_TEST_FDT, folio_address(state->fdt));
if (err)
folio_put(state->fdt);
@@ -203,10 +178,6 @@ static int kho_test_save(void)
if (err)
goto err_free_folios;
- err = register_kho_notifier(&kho_test_nb);
- if (err)
- goto err_free_fdt;
-
return 0;
err_free_fdt:
@@ -326,7 +297,7 @@ static void kho_test_cleanup(void)
static void __exit kho_test_exit(void)
{
- unregister_kho_notifier(&kho_test_nb);
+ kho_remove_subtree(folio_address(kho_test_state.fdt));
kho_test_cleanup();
}
module_exit(kho_test_exit);
--- a/mm/memblock.c~kho-drop-notifiers
+++ a/mm/memblock.c
@@ -2444,53 +2444,18 @@ int reserve_mem_release_by_name(const ch
#define MEMBLOCK_KHO_FDT "memblock"
#define MEMBLOCK_KHO_NODE_COMPATIBLE "memblock-v1"
#define RESERVE_MEM_KHO_NODE_COMPATIBLE "reserve-mem-v1"
-static struct page *kho_fdt;
-
-static int reserve_mem_kho_finalize(struct kho_serialization *ser)
-{
- int err = 0, i;
-
- for (i = 0; i < reserved_mem_count; i++) {
- struct reserve_mem_table *map = &reserved_mem_table[i];
- struct page *page = phys_to_page(map->start);
- unsigned int nr_pages = map->size >> PAGE_SHIFT;
-
- err |= kho_preserve_pages(page, nr_pages);
- }
-
- err |= kho_preserve_folio(page_folio(kho_fdt));
- err |= kho_add_subtree(ser, MEMBLOCK_KHO_FDT, page_to_virt(kho_fdt));
-
- return notifier_from_errno(err);
-}
-
-static int reserve_mem_kho_notifier(struct notifier_block *self,
- unsigned long cmd, void *v)
-{
- switch (cmd) {
- case KEXEC_KHO_FINALIZE:
- return reserve_mem_kho_finalize((struct kho_serialization *)v);
- case KEXEC_KHO_ABORT:
- return NOTIFY_DONE;
- default:
- return NOTIFY_BAD;
- }
-}
-
-static struct notifier_block reserve_mem_kho_nb = {
- .notifier_call = reserve_mem_kho_notifier,
-};
static int __init prepare_kho_fdt(void)
{
int err = 0, i;
+ struct page *fdt_page;
void *fdt;
- kho_fdt = alloc_page(GFP_KERNEL);
- if (!kho_fdt)
+ fdt_page = alloc_page(GFP_KERNEL);
+ if (!fdt_page)
return -ENOMEM;
- fdt = page_to_virt(kho_fdt);
+ fdt = page_to_virt(fdt_page);
err |= fdt_create(fdt, PAGE_SIZE);
err |= fdt_finish_reservemap(fdt);
@@ -2499,7 +2464,10 @@ static int __init prepare_kho_fdt(void)
err |= fdt_property_string(fdt, "compatible", MEMBLOCK_KHO_NODE_COMPATIBLE);
for (i = 0; i < reserved_mem_count; i++) {
struct reserve_mem_table *map = &reserved_mem_table[i];
+ struct page *page = phys_to_page(map->start);
+ unsigned int nr_pages = map->size >> PAGE_SHIFT;
+ err |= kho_preserve_pages(page, nr_pages);
err |= fdt_begin_node(fdt, map->name);
err |= fdt_property_string(fdt, "compatible", RESERVE_MEM_KHO_NODE_COMPATIBLE);
err |= fdt_property(fdt, "start", &map->start, sizeof(map->start));
@@ -2507,13 +2475,16 @@ static int __init prepare_kho_fdt(void)
err |= fdt_end_node(fdt);
}
err |= fdt_end_node(fdt);
-
err |= fdt_finish(fdt);
+ err |= kho_preserve_folio(page_folio(fdt_page));
+
+ if (!err)
+ err = kho_add_subtree(MEMBLOCK_KHO_FDT, fdt);
+
if (err) {
pr_err("failed to prepare memblock FDT for KHO: %d\n", err);
- put_page(kho_fdt);
- kho_fdt = NULL;
+ put_page(fdt_page);
}
return err;
@@ -2529,13 +2500,6 @@ static int __init reserve_mem_init(void)
err = prepare_kho_fdt();
if (err)
return err;
-
- err = register_kho_notifier(&reserve_mem_kho_nb);
- if (err) {
- put_page(kho_fdt);
- kho_fdt = NULL;
- }
-
return err;
}
late_initcall(reserve_mem_init);
_
Patches currently in -mm which might be from rppt@kernel.org are
liveupdate-kho-warn-and-fail-on-metadata-or-preserved-memory-in-scratch-area-fix.patch
kho-drop-notifiers.patch
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2025-11-04 3:26 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2025-10-26 4:06 + kho-drop-notifiers.patch added to mm-nonmm-unstable branch Andrew Morton
-- strict thread matches above, loose matches on Subject: below --
2025-11-04 3:26 Andrew Morton
2025-10-09 2:15 Andrew Morton
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.