x86-64, NUMA: Kill mem_nodes_parsed

With all memory configuration information now carried in numa_meminfo,
there's no need to keep mem_nodes_parsed separate.  Drop it and use
numa_nodes_parsed for CPU / memory-less nodes.

A new helper numa_nodemask_from_meminfo() is added to calculate
memnode mask on the fly which is currently used to set
node_possible_map.

This simplifies NUMA init methods a bit and removes a source of
possible inconsistencies.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Shaohui Zheng <shaohui.zheng@intel.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/include/asm/numa_64.h b/arch/x86/include/asm/numa_64.h
index 6e94469..f42710b 100644 (file)
--- a/arch/x86/include/asm/numa_64.h
+++ b/arch/x86/include/asm/numa_64.h
@@ -25,7 +25,6 @@ extern void setup_node_bootmem(int nodeid, unsigned long start,
 #define NODE_MIN_SIZE (4*1024*1024)
 
 extern nodemask_t numa_nodes_parsed __initdata;
-extern nodemask_t mem_nodes_parsed __initdata;
 
 extern int __cpuinit numa_cpu_node(int cpu);
 extern int __init numa_add_memblk(int nodeid, u64 start, u64 end);

diff --git a/arch/x86/mm/amdtopology_64.c b/arch/x86/mm/amdtopology_64.c
index e76bffa..fd7b609 100644 (file)
--- a/arch/x86/mm/amdtopology_64.c
+++ b/arch/x86/mm/amdtopology_64.c
@@ -122,7 +122,7 @@ int __init amd_numa_init(void)
                               nodeid, (base >> 8) & 3, (limit >> 8) & 3);
                        return -EINVAL;
                }
-               if (node_isset(nodeid, mem_nodes_parsed)) {
+               if (node_isset(nodeid, numa_nodes_parsed)) {
                        pr_info("Node %d already present, skipping\n",
                                nodeid);
                        continue;
@@ -167,11 +167,10 @@ int __init amd_numa_init(void)
 
                prevbase = base;
                numa_add_memblk(nodeid, base, limit);
-               node_set(nodeid, mem_nodes_parsed);
                node_set(nodeid, numa_nodes_parsed);
        }
 
-       if (!nodes_weight(mem_nodes_parsed))
+       if (!nodes_weight(numa_nodes_parsed))
                return -ENOENT;
 
        /*

diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 6e4fbd7..8b1f178 100644 (file)
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -37,7 +37,6 @@ struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
 
 nodemask_t numa_nodes_parsed __initdata;
-nodemask_t mem_nodes_parsed __initdata;
 
 struct memnode memnode;
 
@@ -344,6 +343,20 @@ static int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
 }
 
 /*
+ * Set nodes, which have memory in @mi, in *@nodemask.
+ */
+static void __init numa_nodemask_from_meminfo(nodemask_t *nodemask,
+                                             const struct numa_meminfo *mi)
+{
+       int i;
+
+       for (i = 0; i < ARRAY_SIZE(mi->blk); i++)
+               if (mi->blk[i].start != mi->blk[i].end &&
+                   mi->blk[i].nid != NUMA_NO_NODE)
+                       node_set(mi->blk[i].nid, *nodemask);
+}
+
+/*
  * Sanity check to catch more bad NUMA configurations (they are amazingly
  * common).  Make sure the nodes cover all memory.
  */
@@ -379,7 +392,8 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
        int i, j, nid;
 
        /* Account for nodes with cpus and no memory */
-       nodes_or(node_possible_map, mem_nodes_parsed, numa_nodes_parsed);
+       node_possible_map = numa_nodes_parsed;
+       numa_nodemask_from_meminfo(&node_possible_map, mi);
        if (WARN_ON(nodes_empty(node_possible_map)))
                return -EINVAL;
 
@@ -824,7 +838,6 @@ static int dummy_numa_init(void)
               0LU, max_pfn << PAGE_SHIFT);
 
        node_set(0, numa_nodes_parsed);
-       node_set(0, mem_nodes_parsed);
        numa_add_memblk(0, 0, (u64)max_pfn << PAGE_SHIFT);
 
        return 0;
@@ -852,7 +865,6 @@ void __init initmem_init(void)
                        set_apicid_to_node(j, NUMA_NO_NODE);
 
                nodes_clear(numa_nodes_parsed);
-               nodes_clear(mem_nodes_parsed);
                nodes_clear(node_possible_map);
                nodes_clear(node_online_map);
                memset(&numa_meminfo, 0, sizeof(numa_meminfo));

diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 8185189..4f8e6cd 100644 (file)
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -238,9 +238,7 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
        printk(KERN_INFO "SRAT: Node %u PXM %u %lx-%lx\n", node, pxm,
               start, end);
 
-       if (!(ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE))
-               node_set(node, mem_nodes_parsed);
-       else
+       if (ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE)
                update_nodes_add(node, start, end);
 }
 
@@ -310,10 +308,9 @@ void __init acpi_fake_nodes(const struct bootnode *fake_nodes, int num_nodes)
                __acpi_map_pxm_to_node(fake_node_to_pxm_map[i], i);
        memcpy(__apicid_to_node, fake_apicid_to_node, sizeof(__apicid_to_node));
 
-       nodes_clear(mem_nodes_parsed);
        for (i = 0; i < num_nodes; i++)
                if (fake_nodes[i].start != fake_nodes[i].end)
-                       node_set(i, mem_nodes_parsed);
+                       node_set(i, numa_nodes_parsed);
 }
 
 static int null_slit_node_compare(int a, int b)