1 files changed, 136 insertions, 16 deletions

diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 4ddf497ca65..79836d01f78 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -141,47 +141,167 @@ static inline int save_add_info(void) {return 1;}
 static inline int save_add_info(void) {return 0;}
 #endif
 
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+static void __init
+handle_movablemem(int node, u64 start, u64 end, u32 hotpluggable)
+{
+	int overlap, i;
+	unsigned long start_pfn, end_pfn;
+
+	start_pfn = PFN_DOWN(start);
+	end_pfn = PFN_UP(end);
+
+	/*
+	 * For movablemem_map=acpi:
+	 *
+	 * SRAT:		|_____| |_____| |_________| |_________| ......
+	 * node id:                0       1         1           2
+	 * hotpluggable:	   n       y         y           n
+	 * movablemem_map:	        |_____| |_________|
+	 *
+	 * Using movablemem_map, we can prevent memblock from allocating memory
+	 * on ZONE_MOVABLE at boot time.
+	 *
+	 * Before parsing SRAT, memblock has already reserve some memory ranges
+	 * for other purposes, such as for kernel image. We cannot prevent
+	 * kernel from using these memory, so we need to exclude these memory
+	 * even if it is hotpluggable.
+	 * Furthermore, to ensure the kernel has enough memory to boot, we make
+	 * all the memory on the node which the kernel resides in
+	 * un-hotpluggable.
+	 */
+	if (hotpluggable && movablemem_map.acpi) {
+		/* Exclude ranges reserved by memblock. */
+		struct memblock_type *rgn = &memblock.reserved;
+
+		for (i = 0; i < rgn->cnt; i++) {
+			if (end <= rgn->regions[i].base ||
+			    start >= rgn->regions[i].base +
+			    rgn->regions[i].size)
+				continue;
+
+			/*
+			 * If the memory range overlaps the memory reserved by
+			 * memblock, then the kernel resides in this node.
+			 */
+			node_set(node, movablemem_map.numa_nodes_kernel);
+
+			goto out;
+		}
+
+		/*
+		 * If the kernel resides in this node, then the whole node
+		 * should not be hotpluggable.
+		 */
+		if (node_isset(node, movablemem_map.numa_nodes_kernel))
+			goto out;
+
+		insert_movablemem_map(start_pfn, end_pfn);
+
+		/*
+		 * numa_nodes_hotplug nodemask represents which nodes are put
+		 * into movablemem_map.map[].
+		 */
+		node_set(node, movablemem_map.numa_nodes_hotplug);
+		goto out;
+	}
+
+	/*
+	 * For movablemem_map=nn[KMG]@ss[KMG]:
+	 *
+	 * SRAT:		|_____| |_____| |_________| |_________| ......
+	 * node id:		   0       1         1           2
+	 * user specified:	          |__|                 |___|
+	 * movablemem_map:		  |___| |_________|    |______| ......
+	 *
+	 * Using movablemem_map, we can prevent memblock from allocating memory
+	 * on ZONE_MOVABLE at boot time.
+	 *
+	 * NOTE: In this case, SRAT info will be ingored.
+	 */
+	overlap = movablemem_map_overlap(start_pfn, end_pfn);
+	if (overlap >= 0) {
+		/*
+		 * If part of this range is in movablemem_map, we need to
+		 * add the range after it to extend the range to the end
+		 * of the node, because from the min address specified to
+		 * the end of the node will be ZONE_MOVABLE.
+		 */
+		start_pfn = max(start_pfn,
+			    movablemem_map.map[overlap].start_pfn);
+		insert_movablemem_map(start_pfn, end_pfn);
+
+		/*
+		 * Set the nodemask, so that if the address range on one node
+		 * is not continuse, we can add the subsequent ranges on the
+		 * same node into movablemem_map.
+		 */
+		node_set(node, movablemem_map.numa_nodes_hotplug);
+	} else {
+		if (node_isset(node, movablemem_map.numa_nodes_hotplug))
+			/*
+			 * Insert the range if we already have movable ranges
+			 * on the same node.
+			 */
+			insert_movablemem_map(start_pfn, end_pfn);
+	}
+out:
+	return;
+}
+#else		/* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
+static inline void
+handle_movablemem(int node, u64 start, u64 end, u32 hotpluggable)
+{
+}
+#endif		/* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
+
 /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */
 int __init
 acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 {
 	u64 start, end;
+	u32 hotpluggable;
 	int node, pxm;
 
 	if (srat_disabled())
-		return -1;
-	if (ma->header.length != sizeof(struct acpi_srat_mem_affinity)) {
-		bad_srat();
-		return -1;
-	}
+		goto out_err;
+	if (ma->header.length != sizeof(struct acpi_srat_mem_affinity))
+		goto out_err_bad_srat;
 	if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0)
-		return -1;
+		goto out_err;
+	hotpluggable = ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE;
+	if (hotpluggable && !save_add_info())
+		goto out_err;
 
-	if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && !save_add_info())
-		return -1;
 	start = ma->base_address;
 	end = start + ma->length;
 	pxm = ma->proximity_domain;
 	if (acpi_srat_revision <= 1)
 		pxm &= 0xff;
+
 	node = setup_node(pxm);
 	if (node < 0) {
 		printk(KERN_ERR "SRAT: Too many proximity domains.\n");
-		bad_srat();
-		return -1;
+		goto out_err_bad_srat;
 	}
 
-	if (numa_add_memblk(node, start, end) < 0) {
-		bad_srat();
-		return -1;
-	}
+	if (numa_add_memblk(node, start, end) < 0)
+		goto out_err_bad_srat;
 
 	node_set(node, numa_nodes_parsed);
 
-	printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n",
+	printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx] %s\n",
 	       node, pxm,
-	       (unsigned long long) start, (unsigned long long) end - 1);
+	       (unsigned long long) start, (unsigned long long) end - 1,
+	       hotpluggable ? "Hot Pluggable": "");
+
+	handle_movablemem(node, start, end, hotpluggable);
+
 	return 0;
+out_err_bad_srat:
+	bad_srat();
+out_err:
+	return -1;
 }
 
 void __init acpi_numa_arch_fixup(void) {}