--- zzzz-none-000/linux-3.10.107/arch/x86/mm/numa.c	2017-06-27 09:49:32.000000000 +0000
+++ scorpion-7490-727/linux-3.10.107/arch/x86/mm/numa.c	2021-02-04 17:41:59.000000000 +0000
@@ -60,7 +60,7 @@
 	[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
 };
 
-int __cpuinit numa_cpu_node(int cpu)
+int numa_cpu_node(int cpu)
 {
 	int apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
 
@@ -185,8 +185,8 @@
 	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;
@@ -194,31 +194,23 @@
 	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.
 	 */
 	nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
 	if (!nd_pa) {
-		pr_err("Cannot find %zu bytes in node %d\n",
-		       nd_size, nid);
-		return;
+		nd_pa = __memblock_alloc_base(nd_size, SMP_CACHE_BYTES,
+					      MEMBLOCK_ALLOC_ACCESSIBLE);
+		if (!nd_pa) {
+			pr_err("Cannot find %zu bytes in node %d\n",
+			       nd_size, nid);
+			return;
+		}
 	}
 	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)
@@ -226,9 +218,6 @@
 
 	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);
 }
@@ -257,8 +246,10 @@
 		bi->start = max(bi->start, low);
 		bi->end = min(bi->end, high);
 
-		/* and there's no empty block */
-		if (bi->start >= bi->end)
+		/* and there's no empty or non-exist block */
+		if (bi->start >= bi->end ||
+		    !memblock_overlaps_region(&memblock.memory,
+			bi->start, bi->end - bi->start))
 			numa_remove_memblk_from(i--, mi);
 	}
 
@@ -474,6 +465,49 @@
 	return true;
 }
 
+static void __init numa_clear_kernel_node_hotplug(void)
+{
+	int i, nid;
+	nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
+	unsigned long start, end;
+	struct memblock_region *r;
+
+	/*
+	 * At this time, all memory regions reserved by memblock are
+	 * used by the kernel. Set the nid in memblock.reserved will
+	 * mark out all the nodes the kernel resides in.
+	 */
+	for (i = 0; i < numa_meminfo.nr_blks; i++) {
+		struct numa_memblk *mb = &numa_meminfo.blk[i];
+
+		memblock_set_node(mb->start, mb->end - mb->start,
+				  &memblock.reserved, mb->nid);
+	}
+
+	/*
+	 * Mark all kernel nodes.
+	 *
+	 * When booting with mem=nn[kMG] or in a kdump kernel, numa_meminfo
+	 * may not include all the memblock.reserved memory ranges because
+	 * trim_snb_memory() reserves specific pages for Sandy Bridge graphics.
+	 */
+	for_each_memblock(reserved, r)
+		if (r->nid != MAX_NUMNODES)
+			node_set(r->nid, numa_kernel_nodes);
+
+	/* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */
+	for (i = 0; i < numa_meminfo.nr_blks; i++) {
+		nid = numa_meminfo.blk[i].nid;
+		if (!node_isset(nid, numa_kernel_nodes))
+			continue;
+
+		start = numa_meminfo.blk[i].start;
+		end = numa_meminfo.blk[i].end;
+
+		memblock_clear_hotplug(start, end - start);
+	}
+}
+
 static int __init numa_register_memblks(struct numa_meminfo *mi)
 {
 	unsigned long uninitialized_var(pfn_align);
@@ -487,10 +521,20 @@
 
 	for (i = 0; i < mi->nr_blks; i++) {
 		struct numa_memblk *mb = &mi->blk[i];
-		memblock_set_node(mb->start, mb->end - mb->start, mb->nid);
+		memblock_set_node(mb->start, mb->end - mb->start,
+				  &memblock.memory, mb->nid);
 	}
 
 	/*
+	 * At very early time, the kernel have to use some memory such as
+	 * loading the kernel image. We cannot prevent this anyway. So any
+	 * node the kernel resides in should be un-hotpluggable.
+	 *
+	 * And when we come here, alloc node data won't fail.
+	 */
+	numa_clear_kernel_node_hotplug();
+
+	/*
 	 * If sections array is gonna be used for pfn -> nid mapping, check
 	 * whether its granularity is fine enough.
 	 */
@@ -518,8 +562,17 @@
 			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. */
@@ -561,12 +614,28 @@
 	nodes_clear(node_possible_map);
 	nodes_clear(node_online_map);
 	memset(&numa_meminfo, 0, sizeof(numa_meminfo));
-	WARN_ON(memblock_set_node(0, ULLONG_MAX, MAX_NUMNODES));
+	WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.memory,
+				  MAX_NUMNODES));
+	WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.reserved,
+				  MAX_NUMNODES));
+	/* In case that parsing SRAT failed. */
+	WARN_ON(memblock_clear_hotplug(0, ULLONG_MAX));
 	numa_reset_distance();
 
 	ret = init_func();
 	if (ret < 0)
 		return ret;
+
+	/*
+	 * We reset memblock back to the top-down direction
+	 * here because if we configured ACPI_NUMA, we have
+	 * parsed SRAT in init_func(). It is ok to have the
+	 * reset here even if we did't configure ACPI_NUMA
+	 * or acpi numa init fails and fallbacks to dummy
+	 * numa init.
+	 */
+	memblock_set_bottom_up(false);
+
 	ret = numa_cleanup_meminfo(&numa_meminfo);
 	if (ret < 0)
 		return ret;
@@ -586,6 +655,7 @@
 			numa_clear_node(i);
 	}
 	numa_init_array();
+
 	return 0;
 }
 
@@ -621,10 +691,6 @@
 void __init x86_numa_init(void)
 {
 	if (!numa_off) {
-#ifdef CONFIG_X86_NUMAQ
-		if (!numa_init(numaq_numa_init))
-			return;
-#endif
 #ifdef CONFIG_ACPI_NUMA
 		if (!numa_init(x86_acpi_numa_init))
 			return;
@@ -691,12 +757,12 @@
 #ifndef CONFIG_DEBUG_PER_CPU_MAPS
 
 # ifndef CONFIG_NUMA_EMU
-void __cpuinit numa_add_cpu(int cpu)
+void numa_add_cpu(int cpu)
 {
 	cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
 }
 
-void __cpuinit numa_remove_cpu(int cpu)
+void numa_remove_cpu(int cpu)
 {
 	cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
 }
@@ -737,7 +803,6 @@
 void debug_cpumask_set_cpu(int cpu, int node, bool enable)
 {
 	struct cpumask *mask;
-	char buf[64];
 
 	if (node == NUMA_NO_NODE) {
 		/* early_cpu_to_node() already emits a warning and trace */
@@ -755,25 +820,24 @@
 	else
 		cpumask_clear_cpu(cpu, mask);
 
-	cpulist_scnprintf(buf, sizeof(buf), mask);
-	printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
+	printk(KERN_DEBUG "%s cpu %d node %d: mask now %*pbl\n",
 		enable ? "numa_add_cpu" : "numa_remove_cpu",
-		cpu, node, buf);
+		cpu, node, cpumask_pr_args(mask));
 	return;
 }
 
 # ifndef CONFIG_NUMA_EMU
-static void __cpuinit numa_set_cpumask(int cpu, bool enable)
+static void numa_set_cpumask(int cpu, bool enable)
 {
 	debug_cpumask_set_cpu(cpu, early_cpu_to_node(cpu), enable);
 }
 
-void __cpuinit numa_add_cpu(int cpu)
+void numa_add_cpu(int cpu)
 {
 	numa_set_cpumask(cpu, true);
 }
 
-void __cpuinit numa_remove_cpu(int cpu)
+void numa_remove_cpu(int cpu)
 {
 	numa_set_cpumask(cpu, false);
 }