Merge branch 'x86-mm' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/misc into x86/mm

5 files changed, 79 insertions, 101 deletions

diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index 97e6007e4edd..bce688d54c12 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -54,8 +54,6 @@ static inline phys_addr_t get_max_mapped(void)
 extern unsigned long init_memory_mapping(unsigned long start,
 					 unsigned long end);
 
-void init_memory_mapping_high(void);
-
 extern void initmem_init(void);
 extern void free_initmem(void);
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 46e684f85b36..c3a606c41ce0 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -963,6 +963,14 @@ void __init setup_arch(char **cmdline_p)
 	max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT);
 	max_pfn_mapped = max_low_pfn_mapped;
 
+#ifdef CONFIG_X86_64
+	if (max_pfn > max_low_pfn) {
+		max_pfn_mapped = init_memory_mapping(1UL<<32,
+						     max_pfn<<PAGE_SHIFT);
+		/* can we preseve max_low_pfn ?*/
+		max_low_pfn = max_pfn;
+	}
+#endif
 	memblock.current_limit = get_max_mapped();
 
 	/*
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 470cc4704a9a..c8813aa39740 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -606,63 +606,9 @@ kernel_physical_mapping_init(unsigned long start,
 void __init initmem_init(void)
 {
 	memblock_x86_register_active_regions(0, 0, max_pfn);
-	init_memory_mapping_high();
 }
 #endif
 
-struct mapping_work_data {
-	unsigned long start;
-	unsigned long end;
-	unsigned long pfn_mapped;
-};
-
-static int __init_refok
-mapping_work_fn(unsigned long start_pfn, unsigned long end_pfn, void *datax)
-{
-	struct mapping_work_data *data = datax;
-	unsigned long pfn_mapped;
-	unsigned long final_start, final_end;
-
-	final_start = max_t(unsigned long, start_pfn<<PAGE_SHIFT, data->start);
-	final_end = min_t(unsigned long, end_pfn<<PAGE_SHIFT, data->end);
-
-	if (final_end <= final_start)
-		return 0;
-
-	pfn_mapped = init_memory_mapping(final_start, final_end);
-
-	if (pfn_mapped > data->pfn_mapped)
-		data->pfn_mapped = pfn_mapped;
-
-	return 0;
-}
-
-static unsigned long __init_refok
-init_memory_mapping_active_regions(unsigned long start, unsigned long end)
-{
-	struct mapping_work_data data;
-
-	data.start = start;
-	data.end = end;
-	data.pfn_mapped = 0;
-
-	work_with_active_regions(MAX_NUMNODES, mapping_work_fn, &data);
-
-	return data.pfn_mapped;
-}
-
-void __init_refok init_memory_mapping_high(void)
-{
-	if (max_pfn > max_low_pfn) {
-		max_pfn_mapped = init_memory_mapping_active_regions(1UL<<32,
-							 max_pfn<<PAGE_SHIFT);
-		/* can we preserve max_low_pfn ? */
-		max_low_pfn = max_pfn;
-
-		memblock.current_limit = get_max_mapped();
-	}
-}
-
 void __init paging_init(void)
 {
 	unsigned long max_zone_pfns[MAX_NR_ZONES];
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 74064e8ae79f..9ec0f209a6a4 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -543,8 +543,6 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
 	if (!numa_meminfo_cover_memory(mi))
 		return -EINVAL;
 
-	init_memory_mapping_high();
-
 	/* Finally register nodes. */
 	for_each_node_mask(nid, node_possible_map) {
 		u64 start = (u64)max_pfn << PAGE_SHIFT;
@@ -564,6 +562,15 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
 	return 0;
 }
 
+/**
+ * dummy_numma_init - Fallback dummy NUMA init
+ *
+ * Used if there's no underlying NUMA architecture, NUMA initialization
+ * fails, or NUMA is disabled on the command line.
+ *
+ * Must online at least one node and add memory blocks that cover all
+ * allowed memory.  This function must not fail.
+ */
 static int __init dummy_numa_init(void)
 {
 	printk(KERN_INFO "%s\n",
@@ -577,57 +584,64 @@ static int __init dummy_numa_init(void)
 	return 0;
 }
 
-void __init initmem_init(void)
+static int __init numa_init(int (*init_func)(void))
 {
-	int (*numa_init[])(void) = { [2] = dummy_numa_init };
-	int i, j;
+	int i;
+	int ret;
 
-	if (!numa_off) {
-#ifdef CONFIG_ACPI_NUMA
-		numa_init[0] = x86_acpi_numa_init;
-#endif
-#ifdef CONFIG_AMD_NUMA
-		numa_init[1] = amd_numa_init;
-#endif
-	}
+	for (i = 0; i < MAX_LOCAL_APIC; i++)
+		set_apicid_to_node(i, NUMA_NO_NODE);
 
-	for (i = 0; i < ARRAY_SIZE(numa_init); i++) {
-		if (!numa_init[i])
-			continue;
+	nodes_clear(numa_nodes_parsed);
+	nodes_clear(node_possible_map);
+	nodes_clear(node_online_map);
+	memset(&numa_meminfo, 0, sizeof(numa_meminfo));
+	remove_all_active_ranges();
+	numa_reset_distance();
 
-		for (j = 0; j < MAX_LOCAL_APIC; j++)
-			set_apicid_to_node(j, NUMA_NO_NODE);
+	ret = init_func();
+	if (ret < 0)
+		return ret;
+	ret = numa_cleanup_meminfo(&numa_meminfo);
+	if (ret < 0)
+		return ret;
 
-		nodes_clear(numa_nodes_parsed);
-		nodes_clear(node_possible_map);
-		nodes_clear(node_online_map);
-		memset(&numa_meminfo, 0, sizeof(numa_meminfo));
-		remove_all_active_ranges();
-		numa_reset_distance();
+	numa_emulation(&numa_meminfo, numa_distance_cnt);
 
-		if (numa_init[i]() < 0)
-			continue;
+	ret = numa_register_memblks(&numa_meminfo);
+	if (ret < 0)
+		return ret;
 
-		if (numa_cleanup_meminfo(&numa_meminfo) < 0)
-			continue;
+	for (i = 0; i < nr_cpu_ids; i++) {
+		int nid = early_cpu_to_node(i);
 
-		numa_emulation(&numa_meminfo, numa_distance_cnt);
-
-		if (numa_register_memblks(&numa_meminfo) < 0)
+		if (nid == NUMA_NO_NODE)
 			continue;
+		if (!node_online(nid))
+			numa_clear_node(i);
+	}
+	numa_init_array();
+	return 0;
+}
 
-		for (j = 0; j < nr_cpu_ids; j++) {
-			int nid = early_cpu_to_node(j);
+void __init initmem_init(void)
+{
+	int ret;
 
-			if (nid == NUMA_NO_NODE)
-				continue;
-			if (!node_online(nid))
-				numa_clear_node(j);
-		}
-		numa_init_array();
-		return;
+	if (!numa_off) {
+#ifdef CONFIG_ACPI_NUMA
+		ret = numa_init(x86_acpi_numa_init);
+		if (!ret)
+			return;
+#endif
+#ifdef CONFIG_AMD_NUMA
+		ret = numa_init(amd_numa_init);
+		if (!ret)
+			return;
+#endif
 	}
-	BUG();
+
+	numa_init(dummy_numa_init);
 }
 
 unsigned long __init numa_free_all_bootmem(void)
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index aeecea93820f..3696be0c2204 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -301,6 +301,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 	const u64 max_addr = max_pfn << PAGE_SHIFT;
 	u8 *phys_dist = NULL;
 	size_t phys_size = numa_dist_cnt * numa_dist_cnt * sizeof(phys_dist[0]);
+	int dfl_phys_nid;
 	int i, j, ret;
 
 	if (!emu_cmdline)
@@ -357,6 +358,19 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 					node_distance(i, j);
 	}
 
+	/* determine the default phys nid to use for unmapped nodes */
+	dfl_phys_nid = NUMA_NO_NODE;
+	for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++) {
+		if (emu_nid_to_phys[i] != NUMA_NO_NODE) {
+			dfl_phys_nid = emu_nid_to_phys[i];
+			break;
+		}
+	}
+	if (dfl_phys_nid == NUMA_NO_NODE) {
+		pr_warning("NUMA: Warning: can't determine default physical node, disabling emulation\n");
+		goto no_emu;
+	}
+
 	/* commit */
 	*numa_meminfo = ei;
 
@@ -377,7 +391,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 	/* make sure all emulated nodes are mapped to a physical node */
 	for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++)
 		if (emu_nid_to_phys[i] == NUMA_NO_NODE)
-			emu_nid_to_phys[i] = 0;
+			emu_nid_to_phys[i] = dfl_phys_nid;
 
 	/*
 	 * Transform distance table.  numa_set_distance() ignores all
@@ -417,9 +431,7 @@ void __cpuinit numa_add_cpu(int cpu)
 {
 	int physnid, nid;
 
-	nid = numa_cpu_node(cpu);
-	if (nid == NUMA_NO_NODE)
-		nid = early_cpu_to_node(cpu);
+	nid = early_cpu_to_node(cpu);
 	BUG_ON(nid == NUMA_NO_NODE || !node_online(nid));
 
 	physnid = emu_nid_to_phys[nid];