mm: fix alloc_bootmem_core to use fast searching for all nodes

Make the nodes other than node 0 use bdata->last_success for fast
search too.

We need to use __alloc_bootmem_core() for vmemmap allocation for other
nodes when numa and sparsemem/vmemmap are enabled.

Also, make fail_block path increase i with incr only after ALIGN
to avoid extra increase when size is larger than align.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 2ccea70..3c012fb 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -238,28 +238,32 @@
 	 * We try to allocate bootmem pages above 'goal'
 	 * first, then we try to allocate lower pages.
 	 */
-	if (goal && goal >= bdata->node_boot_start && PFN_DOWN(goal) < end_pfn) {
-		preferred = goal - bdata->node_boot_start;
+	preferred = 0;
+	if (goal && PFN_DOWN(goal) < end_pfn) {
+		if (goal > bdata->node_boot_start)
+			preferred = goal - bdata->node_boot_start;
 
 		if (bdata->last_success >= preferred)
 			if (!limit || (limit && limit > bdata->last_success))
 				preferred = bdata->last_success;
-	} else
-		preferred = 0;
+	}
 
 	preferred = PFN_DOWN(ALIGN(preferred, align)) + offset;
 	areasize = (size + PAGE_SIZE-1) / PAGE_SIZE;
 	incr = align >> PAGE_SHIFT ? : 1;
 
 restart_scan:
-	for (i = preferred; i < eidx; i += incr) {
+	for (i = preferred; i < eidx;) {
 		unsigned long j;
+
 		i = find_next_zero_bit(bdata->node_bootmem_map, eidx, i);
 		i = ALIGN(i, incr);
 		if (i >= eidx)
 			break;
-		if (test_bit(i, bdata->node_bootmem_map))
+		if (test_bit(i, bdata->node_bootmem_map)) {
+			i += incr;
 			continue;
+		}
 		for (j = i + 1; j < i + areasize; ++j) {
 			if (j >= eidx)
 				goto fail_block;
@@ -270,6 +274,8 @@
 		goto found;
 	fail_block:
 		i = ALIGN(j, incr);
+		if (i == j)
+			i += incr;
 	}
 
 	if (preferred > offset) {