mm: allow reserve_bootmem() cross nodes

split reserve_bootmem_core() into two functions, one which checks
conflicts, and one which sets the bits.

and make reserve_bootmem to loop bdata_list to cross the nodes.

user could be crashkernel and ramdisk..., in case the range provided
by those externalities crosses the nodes.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

mm/bootmem.c

@@ -111,44 +111,74 @@ static unsigned long __init init_bootmem_core(pg_data_t *pgdat,
  * might be used for boot-time allocations - or it might get added
  * to the free page pool later on.
  */
-static int __init reserve_bootmem_core(bootmem_data_t *bdata,
+static int __init can_reserve_bootmem_core(bootmem_data_t *bdata,
 			unsigned long addr, unsigned long size, int flags)
 {
 	unsigned long sidx, eidx;
 	unsigned long i;
-	int ret;
+
+	BUG_ON(!size);
+
+	/* out of range, don't hold other */
+	if (addr + size < bdata->node_boot_start ||
+		PFN_DOWN(addr) > bdata->node_low_pfn)
+		return 0;
 
 	/*
-	 * round up, partially reserved pages are considered
-	 * fully reserved.
+	 * Round up to index to the range.
 	 */
-	BUG_ON(!size);
-	BUG_ON(PFN_DOWN(addr) >= bdata->node_low_pfn);
-	BUG_ON(PFN_UP(addr + size) > bdata->node_low_pfn);
-	BUG_ON(addr < bdata->node_boot_start);
+	if (addr > bdata->node_boot_start)
+		sidx= PFN_DOWN(addr - bdata->node_boot_start);
+	else
+		sidx = 0;
 
-	sidx = PFN_DOWN(addr - bdata->node_boot_start);
 	eidx = PFN_UP(addr + size - bdata->node_boot_start);
+	if (eidx > bdata->node_low_pfn - PFN_DOWN(bdata->node_boot_start))
+		eidx = bdata->node_low_pfn - PFN_DOWN(bdata->node_boot_start);
 
-	for (i = sidx; i < eidx; i++)
+	for (i = sidx; i < eidx; i++) {
+		if (test_bit(i, bdata->node_bootmem_map)) {
+			if (flags & BOOTMEM_EXCLUSIVE)
+				return -EBUSY;
+		}
+	}
+
+	return 0;
+
+}
+
+static void __init reserve_bootmem_core(bootmem_data_t *bdata,
+			unsigned long addr, unsigned long size, int flags)
+{
+	unsigned long sidx, eidx;
+	unsigned long i;
+
+	BUG_ON(!size);
+
+	/* out of range */
+	if (addr + size < bdata->node_boot_start ||
+		PFN_DOWN(addr) > bdata->node_low_pfn)
+		return;
+
+	/*
+	 * Round up to index to the range.
+	 */
+	if (addr > bdata->node_boot_start)
+		sidx= PFN_DOWN(addr - bdata->node_boot_start);
+	else
+		sidx = 0;
+
+	eidx = PFN_UP(addr + size - bdata->node_boot_start);
+	if (eidx > bdata->node_low_pfn - PFN_DOWN(bdata->node_boot_start))
+		eidx = bdata->node_low_pfn - PFN_DOWN(bdata->node_boot_start);
+
+	for (i = sidx; i < eidx; i++) {
 		if (test_and_set_bit(i, bdata->node_bootmem_map)) {
 #ifdef CONFIG_DEBUG_BOOTMEM
 			printk("hm, page %08lx reserved twice.\n", i*PAGE_SIZE);
 #endif
-			if (flags & BOOTMEM_EXCLUSIVE) {
-				ret = -EBUSY;
-				goto err;
-			}
 		}
-
-	return 0;
-
-err:
-	/* unreserve memory we accidentally reserved */
-	for (i--; i >= sidx; i--)
-		clear_bit(i, bdata->node_bootmem_map);
-
-	return ret;
+	}
 }
 
 static void __init free_bootmem_core(bootmem_data_t *bdata, unsigned long addr,
@@ -415,6 +445,11 @@ unsigned long __init init_bootmem_node(pg_data_t *pgdat, unsigned long freepfn,
 void __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 				 unsigned long size, int flags)
 {
+	int ret;
+
+	ret = can_reserve_bootmem_core(pgdat->bdata, physaddr, size, flags);
+	if (ret < 0)
+		return;
 	reserve_bootmem_core(pgdat->bdata, physaddr, size, flags);
 }
 
@@ -440,7 +475,18 @@ unsigned long __init init_bootmem(unsigned long start, unsigned long pages)
 int __init reserve_bootmem(unsigned long addr, unsigned long size,
 			    int flags)
 {
-	return reserve_bootmem_core(NODE_DATA(0)->bdata, addr, size, flags);
+	bootmem_data_t *bdata;
+	int ret;
+
+	list_for_each_entry(bdata, &bdata_list, list) {
+		ret = can_reserve_bootmem_core(bdata, addr, size, flags);
+		if (ret < 0)
+			return ret;
+	}
+	list_for_each_entry(bdata, &bdata_list, list)
+		reserve_bootmem_core(bdata, addr, size, flags);
+
+	return 0;
 }
 #endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */