mm/sparse: allow for alternate vmemmap section init at boot

Add functions that are called just before the per-section memmap is
initialized and just before the memmap page structures are initialized. 
They are called sparse_vmemmap_init_nid_early and
sparse_vmemmap_init_nid_late, respectively.

This allows for mm subsystems to add calls to initialize memmap and page
structures in a specific way, if using SPARSEMEM_VMEMMAP.  Specifically,
hugetlb can pre-HVO bootmem allocated pages that way, so that no time and
resources are wasted on allocating vmemmap pages, only to free them later
(and possibly unnecessarily running the system out of memory in the
process).

Refactor some code and export a few convenience functions for external
use.

In sparse_init_nid, skip any sections that are already initialized, e.g. 
they have been initialized by sparse_vmemmap_init_nid_early already.

The hugetlb code to use these functions will be added in a later commit.

Export section_map_size, as any alternate memmap init code will want to
use it.

The internal config option to enable this is SPARSEMEM_VMEMMAP_PREINIT,
which is selected if an architecture-specific option,
ARCH_WANT_HUGETLB_VMEMMAP_PREINIT, is set.  In the future, if other
subsystems want to do preinit too, they can do it in a similar fashion.

The internal config option is there because a section flag is used, and
the number of flags available is architecture-dependent (see mmzone.h). 
Architecures can decide if there is room for the flag when enabling
options that select SPARSEMEM_VMEMMAP_PREINIT.

Fortunately, as of right now, all sparse vmemmap using architectures do
have room.

Link: https://lkml.kernel.org/r/20250228182928.2645936-11-fvdl@google.com
Signed-off-by: Frank van der Linden <fvdl@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Dan Carpenter <dan.carpenter@linaro.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin (Cruise) <roman.gushchin@linux.dev>
Cc: Usama Arif <usamaarif642@gmail.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 36 insertions, 0 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index e90ab0bdcc8c..03e4807bd911 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3928,6 +3928,7 @@ static inline void print_vma_addr(char *prefix, unsigned long rip)
 #endif
 
 void *sparse_buffer_alloc(unsigned long size);
+unsigned long section_map_size(void);
 struct page * __populate_section_memmap(unsigned long pfn,
 		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
 		struct dev_pagemap *pgmap);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 9540b41894da..44ecb2f90db4 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1934,6 +1934,9 @@ enum {
 #ifdef CONFIG_ZONE_DEVICE
 	SECTION_TAINT_ZONE_DEVICE_BIT,
 #endif
+#ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT
+	SECTION_IS_VMEMMAP_PREINIT_BIT,
+#endif
 	SECTION_MAP_LAST_BIT,
 };
 
@@ -1944,6 +1947,9 @@ enum {
 #ifdef CONFIG_ZONE_DEVICE
 #define SECTION_TAINT_ZONE_DEVICE	BIT(SECTION_TAINT_ZONE_DEVICE_BIT)
 #endif
+#ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT
+#define SECTION_IS_VMEMMAP_PREINIT	BIT(SECTION_IS_VMEMMAP_PREINIT_BIT)
+#endif
 #define SECTION_MAP_MASK		(~(BIT(SECTION_MAP_LAST_BIT) - 1))
 #define SECTION_NID_SHIFT		SECTION_MAP_LAST_BIT
 
@@ -1998,6 +2004,30 @@ static inline int online_device_section(struct mem_section *section)
 }
 #endif
 
+#ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT
+static inline int preinited_vmemmap_section(struct mem_section *section)
+{
+	return (section &&
+		(section->section_mem_map & SECTION_IS_VMEMMAP_PREINIT));
+}
+
+void sparse_vmemmap_init_nid_early(int nid);
+void sparse_vmemmap_init_nid_late(int nid);
+
+#else
+static inline int preinited_vmemmap_section(struct mem_section *section)
+{
+	return 0;
+}
+static inline void sparse_vmemmap_init_nid_early(int nid)
+{
+}
+
+static inline void sparse_vmemmap_init_nid_late(int nid)
+{
+}
+#endif
+
 static inline int online_section_nr(unsigned long nr)
 {
 	return online_section(__nr_to_section(nr));
@@ -2035,6 +2065,9 @@ static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
 }
 #endif
 
+void sparse_init_early_section(int nid, struct page *map, unsigned long pnum,
+			       unsigned long flags);
+
 #ifndef CONFIG_HAVE_ARCH_PFN_VALID
 /**
  * pfn_valid - check if there is a valid memory map entry for a PFN
@@ -2116,6 +2149,8 @@ void sparse_init(void);
 #else
 #define sparse_init()	do {} while (0)
 #define sparse_index_init(_sec, _nid)  do {} while (0)
+#define sparse_vmemmap_init_nid_early(_nid, _use) do {} while (0)
+#define sparse_vmemmap_init_nid_late(_nid) do {} while (0)
 #define pfn_in_present_section pfn_valid
 #define subsection_map_init(_pfn, _nr_pages) do {} while (0)
 #endif /* CONFIG_SPARSEMEM */