memblock: introduce MEMBLOCK_RSRV_NOINIT flag

For reserved memory regions marked with this flag, reserve_bootmem_region
is not called during memmap_init_reserved_pages.  This can be used to
avoid struct page initialization for regions which won't need them, for
e.g.  hugepages with Hugepage Vmemmap Optimization enabled.

Link: https://lkml.kernel.org/r/20230913105401.519709-4-usama.arif@bytedance.comSigned-off-by: Usama Arif <usama.arif@bytedance.com>
Acked-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Fam Zheng <fam.zheng@bytedance.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Punit Agrawal <punit.agrawal@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

include/linux/memblock.h

@@ -40,6 +40,8 @@ extern unsigned long long max_possible_pfn;
  * via a driver, and never indicated in the firmware-provided memory map as
  * system RAM. This corresponds to IORESOURCE_SYSRAM_DRIVER_MANAGED in the
  * kernel resource tree.
+ * @MEMBLOCK_RSRV_NOINIT: memory region for which struct pages are
+ * not initialized (only for reserved regions).
  */
 enum memblock_flags {
 	MEMBLOCK_NONE		= 0x0,	/* No special request */
@@ -47,6 +49,7 @@ enum memblock_flags {
 	MEMBLOCK_MIRROR		= 0x2,	/* mirrored region */
 	MEMBLOCK_NOMAP		= 0x4,	/* don't add to kernel direct mapping */
 	MEMBLOCK_DRIVER_MANAGED = 0x8,	/* always detected via a driver */
+	MEMBLOCK_RSRV_NOINIT	= 0x10,	/* don't initialize struct pages */
 };
 
 /**
@@ -125,6 +128,7 @@ int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size);
 int memblock_mark_mirror(phys_addr_t base, phys_addr_t size);
 int memblock_mark_nomap(phys_addr_t base, phys_addr_t size);
 int memblock_clear_nomap(phys_addr_t base, phys_addr_t size);
+int memblock_reserved_mark_noinit(phys_addr_t base, phys_addr_t size);
 
 void memblock_free_all(void);
 void memblock_free(void *ptr, size_t size);
@@ -259,6 +263,11 @@ static inline bool memblock_is_nomap(struct memblock_region *m)
 	return m->flags & MEMBLOCK_NOMAP;
 }
 
+static inline bool memblock_is_reserved_noinit(struct memblock_region *m)
+{
+	return m->flags & MEMBLOCK_RSRV_NOINIT;
+}
+
 static inline bool memblock_is_driver_managed(struct memblock_region *m)
 {
 	return m->flags & MEMBLOCK_DRIVER_MANAGED;

mm/memblock.c

@@ -997,6 +997,24 @@ int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size)
 	return memblock_setclr_flag(&memblock.memory, base, size, 0, MEMBLOCK_NOMAP);
 }
 
+/**
+ * memblock_reserved_mark_noinit - Mark a reserved memory region with flag
+ * MEMBLOCK_RSRV_NOINIT which results in the struct pages not being initialized
+ * for this region.
+ * @base: the base phys addr of the region
+ * @size: the size of the region
+ *
+ * struct pages will not be initialized for reserved memory regions marked with
+ * %MEMBLOCK_RSRV_NOINIT.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int __init_memblock memblock_reserved_mark_noinit(phys_addr_t base, phys_addr_t size)
+{
+	return memblock_setclr_flag(&memblock.reserved, base, size, 1,
+				    MEMBLOCK_RSRV_NOINIT);
+}
+
 static bool should_skip_region(struct memblock_type *type,
 			       struct memblock_region *m,
 			       int nid, int flags)
@@ -2113,14 +2131,19 @@ static void __init memmap_init_reserved_pages(void)
 		memblock_set_node(start, end, &memblock.reserved, nid);
 	}
 
-	/* initialize struct pages for the reserved regions */
+	/*
+	 * initialize struct pages for reserved regions that don't have
+	 * the MEMBLOCK_RSRV_NOINIT flag set
+	 */
 	for_each_reserved_mem_region(region) {
+		if (!memblock_is_reserved_noinit(region)) {
 			nid = memblock_get_region_node(region);
 			start = region->base;
 			end = start + region->size;
 
 			reserve_bootmem_region(start, end, nid);
 		}
+	}
 }
 
 static unsigned long __init free_low_memory_core_early(void)