mm: pass nid to reserve_bootmem_region()
early_pfn_to_nid() is called frequently in init_reserved_page(), it
returns the node id of the PFN. These PFN are probably from the same
memory region, they have the same node id. It's not necessary to call
early_pfn_to_nid() for each PFN.
Pass nid to reserve_bootmem_region() and drop the call to
early_pfn_to_nid() in init_reserved_page(). Also, set nid on all reserved
pages before doing this, as some reserved memory regions may not be set
nid.
The most beneficial function is memmap_init_reserved_pages() if
CONFIG_DEFERRED_STRUCT_PAGE_INIT is enabled.
The following data was tested on an x86 machine with 190GB of RAM.
before:
memmap_init_reserved_pages() 67ms
after:
memmap_init_reserved_pages() 20ms
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Yajun Deng <[email protected]>
Reviewed-by: Mike Rapoport (IBM) <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 122e9bf..7ffa609 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -646,10 +646,8 @@ static inline void pgdat_set_deferred_range(pg_data_t *pgdat)
}
/* Returns true if the struct page for the pfn is initialised */
-static inline bool __meminit early_page_initialised(unsigned long pfn)
+static inline bool __meminit early_page_initialised(unsigned long pfn, int nid)
{
- int nid = early_pfn_to_nid(pfn);
-
if (node_online(nid) && pfn >= NODE_DATA(nid)->first_deferred_pfn)
return false;
@@ -695,15 +693,14 @@ defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
return false;
}
-static void __meminit init_reserved_page(unsigned long pfn)
+static void __meminit init_reserved_page(unsigned long pfn, int nid)
{
pg_data_t *pgdat;
- int nid, zid;
+ int zid;
- if (early_page_initialised(pfn))
+ if (early_page_initialised(pfn, nid))
return;
- nid = early_pfn_to_nid(pfn);
pgdat = NODE_DATA(nid);
for (zid = 0; zid < MAX_NR_ZONES; zid++) {
@@ -717,7 +714,7 @@ static void __meminit init_reserved_page(unsigned long pfn)
#else
static inline void pgdat_set_deferred_range(pg_data_t *pgdat) {}
-static inline bool early_page_initialised(unsigned long pfn)
+static inline bool early_page_initialised(unsigned long pfn, int nid)
{
return true;
}
@@ -727,7 +724,7 @@ static inline bool defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
return false;
}
-static inline void init_reserved_page(unsigned long pfn)
+static inline void init_reserved_page(unsigned long pfn, int nid)
{
}
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
@@ -738,7 +735,8 @@ static inline void init_reserved_page(unsigned long pfn)
* marks the pages PageReserved. The remaining valid pages are later
* sent to the buddy page allocator.
*/
-void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end)
+void __meminit reserve_bootmem_region(phys_addr_t start,
+ phys_addr_t end, int nid)
{
unsigned long start_pfn = PFN_DOWN(start);
unsigned long end_pfn = PFN_UP(end);
@@ -747,7 +745,7 @@ void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end)
if (pfn_valid(start_pfn)) {
struct page *page = pfn_to_page(start_pfn);
- init_reserved_page(start_pfn);
+ init_reserved_page(start_pfn, nid);
/* Avoid false-positive PageTail() */
INIT_LIST_HEAD(&page->lru);
@@ -2572,8 +2570,14 @@ void __init set_dma_reserve(unsigned long new_dma_reserve)
void __init memblock_free_pages(struct page *page, unsigned long pfn,
unsigned int order)
{
- if (!early_page_initialised(pfn))
- return;
+
+ if (IS_ENABLED(CONFIG_DEFERRED_STRUCT_PAGE_INIT)) {
+ int nid = early_pfn_to_nid(pfn);
+
+ if (!early_page_initialised(pfn, nid))
+ return;
+ }
+
if (!kmsan_memblock_free_pages(page, order)) {
/* KMSAN will take care of these pages. */
return;