Merge tag 'liveupdate-v7.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/liveupdate/linux

Pull liveupdate updates from Mike Rapoport:
 "Kexec Handover (KHO):

   - make memory preservation compatible with deferred initialization
     of the memory map

  Live Update Orchestrator (LUO):

   - add LIVEUPDATE_SESSION_GET_NAME ioctl and parameter verification
     for LIVEUPDATE_IOCTL_CREATE_SESSION ioctl

   - documentation updates for liveupdate=on command line option,
     systemd support and the current compatibility status

   - remove the fixed limits on the number of files that can be
     preserved within a single session, and the total number of
     sessions managed by the LUO

  Misc fixes:

   - reference count incoming File-Lifecycle-Bound (FLB) data so
     it cannot be freed while a subsystem is still using it

   - fixes for a TOCTOU race in luo_session_retrieve(), a use-
     after-free in the file finish and unpreserve paths, concurrent
     session mutations during reboot and serialization on
     preserve_context kexec

   - make sure ioctls for incoming LUO sessions are blocked for
     outgoing sessions and vice versa

   - make sure KHO scratch size is always aligned by
     CMA_MIN_ALIGNMENT_BYTES

   - fix memblock tests build issue introduced by KHO changes"

* tag 'liveupdate-v7.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/liveupdate/linux: (36 commits)
  liveupdate: Document that retrieve failure is permanent
  docs: memfd_preservation: fix rendering of ABI documentation
  selftests/liveupdate: Add stress-files kexec test
  selftests/liveupdate: Add stress-sessions kexec test
  selftests/liveupdate: Test session and file limit removal
  liveupdate: Remove limit on the number of files per session
  liveupdate: Remove limit on the number of sessions
  liveupdate: defer session block allocation and physical address setting
  kho: add support for linked-block serialization
  liveupdate: Extract luo_session_deserialize_one helper
  liveupdate: Extract luo_file_deserialize_one helper
  liveupdate: register luo_ser as KHO subtree
  liveupdate: centralize state management into struct luo_ser
  liveupdate: avoid mixing cleanup guards with goto in luo_session_retrieve_fd
  liveupdate: change file_set->count type to u64 for type safety
  liveupdate: Remove unused ser field from struct luo_session
  liveupdate: fix u-a-f in luo_file_unpreserve_files() and luo_file_finish()
  liveupdate: block session mutations during reboot
  liveupdate: fix TOCTOU race in luo_session_retrieve()
  liveupdate: skip serialization for context-preserving kexec
  ...

2 files changed, 39 insertions, 47 deletions

diff --git a/mm/memblock.c b/mm/memblock.c
index ccd43f3abb82..6349c48154f4 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1028,40 +1028,6 @@ 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
@@ -2535,6 +2501,28 @@ 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 65623f95bec3..0f64909e8d20 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -706,9 +706,11 @@ 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
@@ -941,7 +943,8 @@ 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;
@@ -954,8 +957,7 @@ 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);
@@ -971,6 +973,8 @@ 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;
@@ -979,7 +983,7 @@ static void __init memmap_init(void)
 				continue;
 
 			memmap_init_zone_range(zone, start_pfn, end_pfn,
-					       &hole_pfn);
+					       &hole_pfn, mt);
 			zone_id = j;
 		}
 	}
@@ -1969,7 +1973,7 @@ 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;
@@ -1982,8 +1986,7 @@ 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;
 	}
@@ -1993,8 +1996,7 @@ 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);
 	}
 }
@@ -2052,6 +2054,8 @@ 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;
@@ -2064,7 +2068,7 @@ 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;