* [PATCH v9 1/3] kho: fix deferred initialization of scratch areas
2026-04-23 12:25 [PATCH v9 0/3] kho: add support for deferred struct page init Michal Clapinski
@ 2026-04-23 12:25 ` Michal Clapinski
2026-04-23 16:43 ` Pratyush Yadav
2026-04-23 17:42 ` Pasha Tatashin
2026-04-23 12:25 ` [PATCH v9 2/3] kho: make preserved pages compatible with deferred struct page init Michal Clapinski
2026-04-23 12:25 ` [PATCH v9 3/3] selftests: kho: test " Michal Clapinski
2 siblings, 2 replies; 8+ messages in thread
From: Michal Clapinski @ 2026-04-23 12:25 UTC (permalink / raw)
To: Evangelos Petrongonas, Pasha Tatashin, Mike Rapoport,
Pratyush Yadav, Alexander Graf, Samiullah Khawaja, kexec,
linux-mm
Cc: linux-kernel, Andrew Morton, Vlastimil Babka, Suren Baghdasaryan,
Michal Hocko, Brendan Jackman, Johannes Weiner, Zi Yan,
Michal Clapinski
Currently, if CONFIG_DEFERRED_STRUCT_PAGE_INIT is enabled,
kho_release_scratch() will initialize the struct pages and set migratetype
of KHO scratch. Unless the whole scratch fits below first_deferred_pfn,
some of that will be overwritten either by deferred_init_pages() or
memmap_init_reserved_range().
To fix it, make memmap_init_range(), deferred_init_memmap_chunk() and
__init_page_from_nid() recognize KHO scratch regions and set
migratetype of pageblocks in those regions to MIGRATE_CMA.
Co-developed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Michal Clapinski <mclapinski@google.com>
---
include/linux/memblock.h | 21 +++++++++--
kernel/liveupdate/kexec_handover.c | 25 -------------
mm/memblock.c | 56 ++++++++++++------------------
mm/mm_init.c | 30 +++++++++-------
4 files changed, 58 insertions(+), 74 deletions(-)
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index b0f750d22a7b..5afcd99aa8c1 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -613,11 +613,28 @@ static inline void memtest_report_meminfo(struct seq_file *m) { }
#ifdef CONFIG_MEMBLOCK_KHO_SCRATCH
void memblock_set_kho_scratch_only(void);
void memblock_clear_kho_scratch_only(void);
-void memmap_init_kho_scratch_pages(void);
+bool memblock_is_kho_scratch_memory(phys_addr_t addr);
+
+static inline enum migratetype kho_scratch_migratetype(unsigned long pfn,
+ enum migratetype mt)
+{
+ if (memblock_is_kho_scratch_memory(PFN_PHYS(pfn)))
+ return MIGRATE_CMA;
+ return mt;
+}
#else
static inline void memblock_set_kho_scratch_only(void) { }
static inline void memblock_clear_kho_scratch_only(void) { }
-static inline void memmap_init_kho_scratch_pages(void) {}
+static inline bool memblock_is_kho_scratch_memory(phys_addr_t addr)
+{
+ return false;
+}
+
+static inline enum migratetype kho_scratch_migratetype(unsigned long pfn,
+ enum migratetype mt)
+{
+ return mt;
+}
#endif
#endif /* _LINUX_MEMBLOCK_H */
diff --git a/kernel/liveupdate/kexec_handover.c b/kernel/liveupdate/kexec_handover.c
index 18509d8082ea..a507366a2cf9 100644
--- a/kernel/liveupdate/kexec_handover.c
+++ b/kernel/liveupdate/kexec_handover.c
@@ -1576,35 +1576,10 @@ static __init int kho_init(void)
}
fs_initcall(kho_init);
-static void __init kho_release_scratch(void)
-{
- phys_addr_t start, end;
- u64 i;
-
- memmap_init_kho_scratch_pages();
-
- /*
- * Mark scratch mem as CMA before we return it. That way we
- * ensure that no kernel allocations happen on it. That means
- * we can reuse it as scratch memory again later.
- */
- __for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,
- MEMBLOCK_KHO_SCRATCH, &start, &end, NULL) {
- ulong start_pfn = pageblock_start_pfn(PFN_DOWN(start));
- ulong end_pfn = pageblock_align(PFN_UP(end));
- ulong pfn;
-
- for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages)
- init_pageblock_migratetype(pfn_to_page(pfn),
- MIGRATE_CMA, false);
- }
-}
-
void __init kho_memory_init(void)
{
if (kho_in.scratch_phys) {
kho_scratch = phys_to_virt(kho_in.scratch_phys);
- kho_release_scratch();
if (kho_mem_retrieve(kho_get_fdt()))
kho_in.fdt_phys = 0;
diff --git a/mm/memblock.c b/mm/memblock.c
index a6a1c91e276d..01a962681726 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1026,40 +1026,6 @@ int __init_memblock memblock_physmem_add(phys_addr_t base, phys_addr_t size)
}
#endif
-#ifdef CONFIG_MEMBLOCK_KHO_SCRATCH
-__init void memblock_set_kho_scratch_only(void)
-{
- kho_scratch_only = true;
-}
-
-__init void memblock_clear_kho_scratch_only(void)
-{
- kho_scratch_only = false;
-}
-
-__init void memmap_init_kho_scratch_pages(void)
-{
- phys_addr_t start, end;
- unsigned long pfn;
- int nid;
- u64 i;
-
- if (!IS_ENABLED(CONFIG_DEFERRED_STRUCT_PAGE_INIT))
- return;
-
- /*
- * Initialize struct pages for free scratch memory.
- * The struct pages for reserved scratch memory will be set up in
- * memmap_init_reserved_pages()
- */
- __for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,
- MEMBLOCK_KHO_SCRATCH, &start, &end, &nid) {
- for (pfn = PFN_UP(start); pfn < PFN_DOWN(end); pfn++)
- init_deferred_page(pfn, nid);
- }
-}
-#endif
-
/**
* memblock_setclr_flag - set or clear flag for a memory region
* @type: memblock type to set/clear flag for
@@ -2533,6 +2499,28 @@ int reserve_mem_release_by_name(const char *name)
return 1;
}
+#ifdef CONFIG_MEMBLOCK_KHO_SCRATCH
+__init void memblock_set_kho_scratch_only(void)
+{
+ kho_scratch_only = true;
+}
+
+__init void memblock_clear_kho_scratch_only(void)
+{
+ kho_scratch_only = false;
+}
+
+bool __init_memblock memblock_is_kho_scratch_memory(phys_addr_t addr)
+{
+ int i = memblock_search(&memblock.memory, addr);
+
+ if (i == -1)
+ return false;
+
+ return memblock_is_kho_scratch(&memblock.memory.regions[i]);
+}
+#endif
+
#ifdef CONFIG_KEXEC_HANDOVER
static int __init reserved_mem_preserve(void)
diff --git a/mm/mm_init.c b/mm/mm_init.c
index f9f8e1af921c..eddc0f03a779 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -692,9 +692,11 @@ void __meminit __init_page_from_nid(unsigned long pfn, int nid)
}
__init_single_page(pfn_to_page(pfn), pfn, zid, nid);
- if (pageblock_aligned(pfn))
- init_pageblock_migratetype(pfn_to_page(pfn), MIGRATE_MOVABLE,
- false);
+ if (pageblock_aligned(pfn)) {
+ enum migratetype mt =
+ kho_scratch_migratetype(pfn, MIGRATE_MOVABLE);
+ init_pageblock_migratetype(pfn_to_page(pfn), mt, false);
+ }
}
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
@@ -927,7 +929,8 @@ void __meminit memmap_init_range(unsigned long size, int nid, unsigned long zone
static void __init memmap_init_zone_range(struct zone *zone,
unsigned long start_pfn,
unsigned long end_pfn,
- unsigned long *hole_pfn)
+ unsigned long *hole_pfn,
+ enum migratetype mt)
{
unsigned long zone_start_pfn = zone->zone_start_pfn;
unsigned long zone_end_pfn = zone_start_pfn + zone->spanned_pages;
@@ -940,8 +943,7 @@ static void __init memmap_init_zone_range(struct zone *zone,
return;
memmap_init_range(end_pfn - start_pfn, nid, zone_id, start_pfn,
- zone_end_pfn, MEMINIT_EARLY, NULL, MIGRATE_MOVABLE,
- false);
+ zone_end_pfn, MEMINIT_EARLY, NULL, mt, false);
if (*hole_pfn < start_pfn)
init_unavailable_range(*hole_pfn, start_pfn, zone_id, nid);
@@ -957,6 +959,8 @@ static void __init memmap_init(void)
for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
struct pglist_data *node = NODE_DATA(nid);
+ enum migratetype mt =
+ kho_scratch_migratetype(start_pfn, MIGRATE_MOVABLE);
for (j = 0; j < MAX_NR_ZONES; j++) {
struct zone *zone = node->node_zones + j;
@@ -965,7 +969,7 @@ static void __init memmap_init(void)
continue;
memmap_init_zone_range(zone, start_pfn, end_pfn,
- &hole_pfn);
+ &hole_pfn, mt);
zone_id = j;
}
}
@@ -1970,7 +1974,7 @@ unsigned long __init node_map_pfn_alignment(void)
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
static void __init deferred_free_pages(unsigned long pfn,
- unsigned long nr_pages)
+ unsigned long nr_pages, enum migratetype mt)
{
struct page *page;
unsigned long i;
@@ -1983,8 +1987,7 @@ static void __init deferred_free_pages(unsigned long pfn,
/* Free a large naturally-aligned chunk if possible */
if (nr_pages == MAX_ORDER_NR_PAGES && IS_MAX_ORDER_ALIGNED(pfn)) {
for (i = 0; i < nr_pages; i += pageblock_nr_pages)
- init_pageblock_migratetype(page + i, MIGRATE_MOVABLE,
- false);
+ init_pageblock_migratetype(page + i, mt, false);
__free_pages_core(page, MAX_PAGE_ORDER, MEMINIT_EARLY);
return;
}
@@ -1994,8 +1997,7 @@ static void __init deferred_free_pages(unsigned long pfn,
for (i = 0; i < nr_pages; i++, page++, pfn++) {
if (pageblock_aligned(pfn))
- init_pageblock_migratetype(page, MIGRATE_MOVABLE,
- false);
+ init_pageblock_migratetype(page, mt, false);
__free_pages_core(page, 0, MEMINIT_EARLY);
}
}
@@ -2053,6 +2055,8 @@ deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn,
for_each_free_mem_range(i, nid, 0, &start, &end, NULL) {
unsigned long spfn = PFN_UP(start);
unsigned long epfn = PFN_DOWN(end);
+ enum migratetype mt =
+ kho_scratch_migratetype(spfn, MIGRATE_MOVABLE);
if (spfn >= end_pfn)
break;
@@ -2065,7 +2069,7 @@ deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn,
unsigned long chunk_end = min(mo_pfn, epfn);
nr_pages += deferred_init_pages(zone, spfn, chunk_end);
- deferred_free_pages(spfn, chunk_end - spfn);
+ deferred_free_pages(spfn, chunk_end - spfn, mt);
spfn = chunk_end;
--
2.54.0.rc2.533.g4f5dca5207-goog
^ permalink raw reply related [flat|nested] 8+ messages in thread* [PATCH v9 2/3] kho: make preserved pages compatible with deferred struct page init
2026-04-23 12:25 [PATCH v9 0/3] kho: add support for deferred struct page init Michal Clapinski
2026-04-23 12:25 ` [PATCH v9 1/3] kho: fix deferred initialization of scratch areas Michal Clapinski
@ 2026-04-23 12:25 ` Michal Clapinski
2026-04-23 12:25 ` [PATCH v9 3/3] selftests: kho: test " Michal Clapinski
2 siblings, 0 replies; 8+ messages in thread
From: Michal Clapinski @ 2026-04-23 12:25 UTC (permalink / raw)
To: Evangelos Petrongonas, Pasha Tatashin, Mike Rapoport,
Pratyush Yadav, Alexander Graf, Samiullah Khawaja, kexec,
linux-mm
Cc: linux-kernel, Andrew Morton, Vlastimil Babka, Suren Baghdasaryan,
Michal Hocko, Brendan Jackman, Johannes Weiner, Zi Yan,
Michal Clapinski
From: Evangelos Petrongonas <epetron@amazon.de>
When CONFIG_DEFERRED_STRUCT_PAGE_INIT is enabled, struct page
initialization is deferred to parallel kthreads that run later
in the boot process.
During KHO restoration, kho_preserved_memory_reserve() writes metadata
for each preserved memory region. However, if the struct page has not
been initialized, this write targets uninitialized memory, potentially
leading to errors like:
BUG: unable to handle page fault for address: ...
Fix this by introducing kho_get_preserved_page(), which ensures
all struct pages in a preserved region are initialized by calling
init_deferred_page() which is a no-op when the struct page is already
initialized.
Signed-off-by: Evangelos Petrongonas <epetron@amazon.de>
Co-developed-by: Michal Clapinski <mclapinski@google.com>
Signed-off-by: Michal Clapinski <mclapinski@google.com>
Reviewed-by: Pratyush Yadav (Google) <pratyush@kernel.org>
Reviewed-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
---
kernel/liveupdate/Kconfig | 2 --
kernel/liveupdate/kexec_handover.c | 27 ++++++++++++++++++++++++++-
2 files changed, 26 insertions(+), 3 deletions(-)
diff --git a/kernel/liveupdate/Kconfig b/kernel/liveupdate/Kconfig
index 1a8513f16ef7..c13af38ba23a 100644
--- a/kernel/liveupdate/Kconfig
+++ b/kernel/liveupdate/Kconfig
@@ -1,12 +1,10 @@
# SPDX-License-Identifier: GPL-2.0-only
menu "Live Update and Kexec HandOver"
- depends on !DEFERRED_STRUCT_PAGE_INIT
config KEXEC_HANDOVER
bool "kexec handover"
depends on ARCH_SUPPORTS_KEXEC_HANDOVER && ARCH_SUPPORTS_KEXEC_FILE
- depends on !DEFERRED_STRUCT_PAGE_INIT
select MEMBLOCK_KHO_SCRATCH
select KEXEC_FILE
select LIBFDT
diff --git a/kernel/liveupdate/kexec_handover.c b/kernel/liveupdate/kexec_handover.c
index a507366a2cf9..d5718bef6d4d 100644
--- a/kernel/liveupdate/kexec_handover.c
+++ b/kernel/liveupdate/kexec_handover.c
@@ -473,6 +473,31 @@ struct page *kho_restore_pages(phys_addr_t phys, unsigned long nr_pages)
}
EXPORT_SYMBOL_GPL(kho_restore_pages);
+/*
+ * With CONFIG_DEFERRED_STRUCT_PAGE_INIT, struct pages in higher memory regions
+ * may not be initialized yet at the time KHO deserializes preserved memory.
+ * KHO uses the struct page to store metadata and a later initialization would
+ * overwrite it.
+ * Ensure all the struct pages in the preservation are
+ * initialized. kho_preserved_memory_reserve() marks the reservation as noinit
+ * to make sure they don't get re-initialized later.
+ */
+static struct page *__init kho_get_preserved_page(phys_addr_t phys,
+ unsigned int order)
+{
+ unsigned long pfn = PHYS_PFN(phys);
+ int nid;
+
+ if (!IS_ENABLED(CONFIG_DEFERRED_STRUCT_PAGE_INIT))
+ return pfn_to_page(pfn);
+
+ nid = early_pfn_to_nid(pfn);
+ for (unsigned long i = 0; i < (1UL << order); i++)
+ init_deferred_page(pfn + i, nid);
+
+ return pfn_to_page(pfn);
+}
+
static int __init kho_preserved_memory_reserve(phys_addr_t phys,
unsigned int order)
{
@@ -481,7 +506,7 @@ static int __init kho_preserved_memory_reserve(phys_addr_t phys,
u64 sz;
sz = 1 << (order + PAGE_SHIFT);
- page = phys_to_page(phys);
+ page = kho_get_preserved_page(phys, order);
/* Reserve the memory preserved in KHO in memblock */
memblock_reserve(phys, sz);
--
2.54.0.rc2.533.g4f5dca5207-goog
^ permalink raw reply related [flat|nested] 8+ messages in thread