x86/mm/numa: Drop dead code and rename setup_node_data() to setup_alloc_data()

The setup_node_data() function allocates a pg_data_t object,
inserts it into the node_data[] array and initializes the
following fields: node_id, node_start_pfn and
node_spanned_pages.

However, a few function calls later during the kernel boot,
free_area_init_node() re-initializes those fields, possibly with
setup_node_data() is not used.

This causes a small glitch when running Linux as a hyperv numa
guest:

  SRAT: PXM 0 -> APIC 0x00 -> Node 0
  SRAT: PXM 0 -> APIC 0x01 -> Node 0
  SRAT: PXM 1 -> APIC 0x02 -> Node 1
  SRAT: PXM 1 -> APIC 0x03 -> Node 1
  SRAT: Node 0 PXM 0 [mem 0x00000000-0x7fffffff]
  SRAT: Node 1 PXM 1 [mem 0x80200000-0xf7ffffff]
  SRAT: Node 1 PXM 1 [mem 0x100000000-0x1081fffff]
  NUMA: Node 1 [mem 0x80200000-0xf7ffffff] + [mem 0x100000000-0x1081fffff] -> [mem 0x80200000-0x1081fffff]
  Initmem setup node 0 [mem 0x00000000-0x7fffffff]
    NODE_DATA [mem 0x7ffdc000-0x7ffeffff]
  Initmem setup node 1 [mem 0x80800000-0x1081fffff]
    NODE_DATA [mem 0x1081ea000-0x1081fdfff]
  crashkernel: memory value expected
   [ffffea0000000000-ffffea0001ffffff] PMD -> [ffff88007de00000-ffff88007fdfffff] on node 0
   [ffffea0002000000-ffffea00043fffff] PMD -> [ffff880105600000-ffff8801077fffff] on node 1
  Zone ranges:
    DMA      [mem 0x00001000-0x00ffffff]
    DMA32    [mem 0x01000000-0xffffffff]
    Normal   [mem 0x100000000-0x1081fffff]
  Movable zone start for each node
  Early memory node ranges
    node   0: [mem 0x00001000-0x0009efff]
    node   0: [mem 0x00100000-0x7ffeffff]
    node   1: [mem 0x80200000-0xf7ffffff]
    node   1: [mem 0x100000000-0x1081fffff]
  On node 0 totalpages: 524174
    DMA zone: 64 pages used for memmap
    DMA zone: 21 pages reserved
    DMA zone: 3998 pages, LIFO batch:0
    DMA32 zone: 8128 pages used for memmap
    DMA32 zone: 520176 pages, LIFO batch:31
  On node 1 totalpages: 524288
    DMA32 zone: 7672 pages used for memmap
    DMA32 zone: 491008 pages, LIFO batch:31
    Normal zone: 520 pages used for memmap
    Normal zone: 33280 pages, LIFO batch:7

In this dmesg, the SRAT table reports that the memory range for
node 1 starts at 0x80200000.  However, the line starting with
"Initmem" reports that node 1 memory range starts at 0x80800000.
 The "Initmem" line is reported by setup_node_data() and is
wrong, because the kernel ends up using the range as reported in
the SRAT table.

This commit drops all that dead code from setup_node_data(),
renames it to alloc_node_data() and adds a printk() to
free_area_init_node() so that we report a node's memory range
accurately.

Here's the same dmesg section with this patch applied:

   SRAT: PXM 0 -> APIC 0x00 -> Node 0
   SRAT: PXM 0 -> APIC 0x01 -> Node 0
   SRAT: PXM 1 -> APIC 0x02 -> Node 1
   SRAT: PXM 1 -> APIC 0x03 -> Node 1
   SRAT: Node 0 PXM 0 [mem 0x00000000-0x7fffffff]
   SRAT: Node 1 PXM 1 [mem 0x80200000-0xf7ffffff]
   SRAT: Node 1 PXM 1 [mem 0x100000000-0x1081fffff]
   NUMA: Node 1 [mem 0x80200000-0xf7ffffff] + [mem 0x100000000-0x1081fffff] -> [mem 0x80200000-0x1081fffff]
   NODE_DATA(0) allocated [mem 0x7ffdc000-0x7ffeffff]
   NODE_DATA(1) allocated [mem 0x1081ea000-0x1081fdfff]
   crashkernel: memory value expected
    [ffffea0000000000-ffffea0001ffffff] PMD -> [ffff88007de00000-ffff88007fdfffff] on node 0
    [ffffea0002000000-ffffea00043fffff] PMD -> [ffff880105600000-ffff8801077fffff] on node 1
   Zone ranges:
     DMA      [mem 0x00001000-0x00ffffff]
     DMA32    [mem 0x01000000-0xffffffff]
     Normal   [mem 0x100000000-0x1081fffff]
   Movable zone start for each node
   Early memory node ranges
     node   0: [mem 0x00001000-0x0009efff]
     node   0: [mem 0x00100000-0x7ffeffff]
     node   1: [mem 0x80200000-0xf7ffffff]
     node   1: [mem 0x100000000-0x1081fffff]
   Initmem setup node 0 [mem 0x00001000-0x7ffeffff]
   On node 0 totalpages: 524174
     DMA zone: 64 pages used for memmap
     DMA zone: 21 pages reserved
     DMA zone: 3998 pages, LIFO batch:0
     DMA32 zone: 8128 pages used for memmap
     DMA32 zone: 520176 pages, LIFO batch:31
   Initmem setup node 1 [mem 0x80200000-0x1081fffff]
   On node 1 totalpages: 524288
     DMA32 zone: 7672 pages used for memmap
     DMA32 zone: 491008 pages, LIFO batch:31
     Normal zone: 520 pages used for memmap
     Normal zone: 33280 pages, LIFO batch:7

This commit was tested on a two node bare-metal NUMA machine and
Linux as a numa guest on hyperv and qemu/kvm.

PS: The wrong memory range reported by setup_node_data() seems to be
    harmless in the current kernel because it's just not used.  However,
    that bad range is used in kernel 2.6.32 to initialize the old boot
    memory allocator, which causes a crash during boot.

Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/numa.h

@@ -9,7 +9,6 @@
 #ifdef CONFIG_NUMA
 
 #define NR_NODE_MEMBLKS		(MAX_NUMNODES*2)
-#define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT))
 
 /*
  * Too small node sizes may confuse the VM badly. Usually they

arch/x86/mm/numa.c

@@ -185,26 +185,14 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
 	return numa_add_memblk_to(nid, start, end, &numa_meminfo);
 }
 
-/* Initialize NODE_DATA for a node on the local memory */
-static void __init setup_node_data(int nid, u64 start, u64 end)
+/* Allocate NODE_DATA for a node on the local memory */
+static void __init alloc_node_data(int nid)
 {
 	const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
 	u64 nd_pa;
 	void *nd;
 	int tnid;
 
-	/*
-	 * Don't confuse VM with a node that doesn't have the
-	 * minimum amount of memory:
-	 */
-	if (end && (end - start) < NODE_MIN_SIZE)
-		return;
-
-	start = roundup(start, ZONE_ALIGN);
-
-	printk(KERN_INFO "Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
-	       nid, start, end - 1);
-
 	/*
 	 * Allocate node data.  Try node-local memory and then any node.
 	 * Never allocate in DMA zone.
@@ -222,7 +210,7 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
 	nd = __va(nd_pa);
 
 	/* report and initialize */
-	printk(KERN_INFO "  NODE_DATA [mem %#010Lx-%#010Lx]\n",
+	printk(KERN_INFO "NODE_DATA(%d) allocated [mem %#010Lx-%#010Lx]\n", nid,
 	       nd_pa, nd_pa + nd_size - 1);
 	tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
 	if (tnid != nid)
@@ -230,9 +218,6 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
 
 	node_data[nid] = nd;
 	memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
-	NODE_DATA(nid)->node_id = nid;
-	NODE_DATA(nid)->node_start_pfn = start >> PAGE_SHIFT;
-	NODE_DATA(nid)->node_spanned_pages = (end - start) >> PAGE_SHIFT;
 
 	node_set_online(nid);
 }
@@ -523,8 +508,17 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
 			end = max(mi->blk[i].end, end);
 		}
 
-		if (start < end)
-			setup_node_data(nid, start, end);
+		if (start >= end)
+			continue;
+
+		/*
+		 * Don't confuse VM with a node that doesn't have the
+		 * minimum amount of memory:
+		 */
+		if (end && (end - start) < NODE_MIN_SIZE)
+			continue;
+
+		alloc_node_data(nid);
 	}
 
 	/* Dump memblock with node info and return. */

mm/page_alloc.c

@@ -4976,6 +4976,8 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 	pgdat->node_start_pfn = node_start_pfn;
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 	get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
+	printk(KERN_INFO "Initmem setup node %d [mem %#010Lx-%#010Lx]\n", nid,
+			(u64) start_pfn << PAGE_SHIFT, (u64) (end_pfn << PAGE_SHIFT) - 1);
 #endif
 	calculate_node_totalpages(pgdat, start_pfn, end_pfn,
 				  zones_size, zholes_size);