6 files changed, 59 insertions, 49 deletions

diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 286d289b039..37b8b0fe832 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -81,6 +81,11 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
 		end, pgt_buf_start << PAGE_SHIFT, pgt_buf_top << PAGE_SHIFT);
 }
 
+void __init native_pagetable_reserve(u64 start, u64 end)
+{
+	memblock_x86_reserve_range(start, end, "PGTABLE");
+}
+
 struct map_range {
 	unsigned long start;
 	unsigned long end;
@@ -272,9 +277,24 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 
 	__flush_tlb_all();
 
+	/*
+	 * Reserve the kernel pagetable pages we used (pgt_buf_start -
+	 * pgt_buf_end) and free the other ones (pgt_buf_end - pgt_buf_top)
+	 * so that they can be reused for other purposes.
+	 *
+	 * On native it just means calling memblock_x86_reserve_range, on Xen it
+	 * also means marking RW the pagetable pages that we allocated before
+	 * but that haven't been used.
+	 *
+	 * In fact on xen we mark RO the whole range pgt_buf_start -
+	 * pgt_buf_top, because we have to make sure that when
+	 * init_memory_mapping reaches the pagetable pages area, it maps
+	 * RO all the pagetable pages, including the ones that are beyond
+	 * pgt_buf_end at that time.
+	 */
 	if (!after_bootmem && pgt_buf_end > pgt_buf_start)
-		memblock_x86_reserve_range(pgt_buf_start << PAGE_SHIFT,
-				 pgt_buf_end << PAGE_SHIFT, "PGTABLE");
+		x86_init.mapping.pagetable_reserve(PFN_PHYS(pgt_buf_start),
+				PFN_PHYS(pgt_buf_end));
 
 	if (!after_bootmem)
 		early_memtest(start, end);
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 0aa34669ed3..79423358728 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -52,6 +52,7 @@
 #include <asm/cacheflush.h>
 #include <asm/init.h>
 #include <asm/uv/uv.h>
+#include <asm/setup.h>
 
 static int __init parse_direct_gbpages_off(char *arg)
 {
@@ -294,18 +295,18 @@ void __init init_extra_mapping_uc(unsigned long phys, unsigned long size)
  * to the compile time generated pmds. This results in invalid pmds up
  * to the point where we hit the physaddr 0 mapping.
  *
- * We limit the mappings to the region from _text to _end.  _end is
- * rounded up to the 2MB boundary. This catches the invalid pmds as
+ * We limit the mappings to the region from _text to _brk_end.  _brk_end
+ * is rounded up to the 2MB boundary. This catches the invalid pmds as
  * well, as they are located before _text:
  */
 void __init cleanup_highmap(void)
 {
 	unsigned long vaddr = __START_KERNEL_map;
-	unsigned long end = roundup((unsigned long)_end, PMD_SIZE) - 1;
+	unsigned long vaddr_end = __START_KERNEL_map + (max_pfn_mapped << PAGE_SHIFT);
+	unsigned long end = roundup((unsigned long)_brk_end, PMD_SIZE) - 1;
 	pmd_t *pmd = level2_kernel_pgt;
-	pmd_t *last_pmd = pmd + PTRS_PER_PMD;
 
-	for (; pmd < last_pmd; pmd++, vaddr += PMD_SIZE) {
+	for (; vaddr + PMD_SIZE - 1 < vaddr_end; pmd++, vaddr += PMD_SIZE) {
 		if (pmd_none(*pmd))
 			continue;
 		if (vaddr < (unsigned long) _text || vaddr > end)
@@ -861,18 +862,18 @@ static struct vm_area_struct gate_vma = {
 	.vm_flags	= VM_READ | VM_EXEC
 };
 
-struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
 {
 #ifdef CONFIG_IA32_EMULATION
-	if (test_tsk_thread_flag(tsk, TIF_IA32))
+	if (!mm || mm->context.ia32_compat)
 		return NULL;
 #endif
 	return &gate_vma;
 }
 
-int in_gate_area(struct task_struct *task, unsigned long addr)
+int in_gate_area(struct mm_struct *mm, unsigned long addr)
 {
-	struct vm_area_struct *vma = get_gate_vma(task);
+	struct vm_area_struct *vma = get_gate_vma(mm);
 
 	if (!vma)
 		return 0;
@@ -881,11 +882,11 @@ int in_gate_area(struct task_struct *task, unsigned long addr)
 }
 
 /*
- * Use this when you have no reliable task/vma, typically from interrupt
- * context. It is less reliable than using the task's vma and may give
- * false positives:
+ * Use this when you have no reliable mm, typically from interrupt
+ * context. It is less reliable than using a task's mm and may give
+ * false positives.
  */
-int in_gate_area_no_task(unsigned long addr)
+int in_gate_area_no_mm(unsigned long addr)
 {
 	return (addr >= VSYSCALL_START) && (addr < VSYSCALL_END);
 }
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 9559d360fde..745258dfc4d 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -213,53 +213,48 @@ int early_cpu_to_node(int cpu)
 	return per_cpu(x86_cpu_to_node_map, cpu);
 }
 
-struct cpumask __cpuinit *debug_cpumask_set_cpu(int cpu, int enable)
+void debug_cpumask_set_cpu(int cpu, int node, bool enable)
 {
-	int node = early_cpu_to_node(cpu);
 	struct cpumask *mask;
 	char buf[64];
 
 	if (node == NUMA_NO_NODE) {
 		/* early_cpu_to_node() already emits a warning and trace */
-		return NULL;
+		return;
 	}
 	mask = node_to_cpumask_map[node];
 	if (!mask) {
 		pr_err("node_to_cpumask_map[%i] NULL\n", node);
 		dump_stack();
-		return NULL;
+		return;
 	}
 
+	if (enable)
+		cpumask_set_cpu(cpu, mask);
+	else
+		cpumask_clear_cpu(cpu, mask);
+
 	cpulist_scnprintf(buf, sizeof(buf), mask);
 	printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
 		enable ? "numa_add_cpu" : "numa_remove_cpu",
 		cpu, node, buf);
-	return mask;
+	return;
 }
 
 # ifndef CONFIG_NUMA_EMU
-static void __cpuinit numa_set_cpumask(int cpu, int enable)
+static void __cpuinit numa_set_cpumask(int cpu, bool enable)
 {
-	struct cpumask *mask;
-
-	mask = debug_cpumask_set_cpu(cpu, enable);
-	if (!mask)
-		return;
-
-	if (enable)
-		cpumask_set_cpu(cpu, mask);
-	else
-		cpumask_clear_cpu(cpu, mask);
+	debug_cpumask_set_cpu(cpu, early_cpu_to_node(cpu), enable);
 }
 
 void __cpuinit numa_add_cpu(int cpu)
 {
-	numa_set_cpumask(cpu, 1);
+	numa_set_cpumask(cpu, true);
 }
 
 void __cpuinit numa_remove_cpu(int cpu)
 {
-	numa_set_cpumask(cpu, 0);
+	numa_set_cpumask(cpu, false);
 }
 # endif	/* !CONFIG_NUMA_EMU */
 
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index e8c00cc7203..85b52fc0308 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -306,7 +306,7 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
 		bi->end = min(bi->end, high);
 
 		/* and there's no empty block */
-		if (bi->start == bi->end) {
+		if (bi->start >= bi->end) {
 			numa_remove_memblk_from(i--, mi);
 			continue;
 		}
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index ad091e4cff1..de84cc14037 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -454,10 +454,9 @@ void __cpuinit numa_remove_cpu(int cpu)
 		cpumask_clear_cpu(cpu, node_to_cpumask_map[i]);
 }
 #else	/* !CONFIG_DEBUG_PER_CPU_MAPS */
-static void __cpuinit numa_set_cpumask(int cpu, int enable)
+static void __cpuinit numa_set_cpumask(int cpu, bool enable)
 {
-	struct cpumask *mask;
-	int nid, physnid, i;
+	int nid, physnid;
 
 	nid = early_cpu_to_node(cpu);
 	if (nid == NUMA_NO_NODE) {
@@ -467,28 +466,21 @@ static void __cpuinit numa_set_cpumask(int cpu, int enable)
 
 	physnid = emu_nid_to_phys[nid];
 
-	for_each_online_node(i) {
+	for_each_online_node(nid) {
 		if (emu_nid_to_phys[nid] != physnid)
 			continue;
 
-		mask = debug_cpumask_set_cpu(cpu, enable);
-		if (!mask)
-			return;
-
-		if (enable)
-			cpumask_set_cpu(cpu, mask);
-		else
-			cpumask_clear_cpu(cpu, mask);
+		debug_cpumask_set_cpu(cpu, nid, enable);
 	}
 }
 
 void __cpuinit numa_add_cpu(int cpu)
 {
-	numa_set_cpumask(cpu, 1);
+	numa_set_cpumask(cpu, true);
 }
 
 void __cpuinit numa_remove_cpu(int cpu)
 {
-	numa_set_cpumask(cpu, 0);
+	numa_set_cpumask(cpu, false);
 }
 #endif	/* !CONFIG_DEBUG_PER_CPU_MAPS */
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index 48651c6f657..364f36bdfad 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -211,10 +211,12 @@ int __init get_memcfg_from_srat(void)
 {
 	int i, j, nid;
 
-
 	if (srat_disabled())
 		goto out_fail;
 
+	if (acpi_numa_init() < 0)
+		goto out_fail;
+
 	if (num_memory_chunks == 0) {
 		printk(KERN_DEBUG
 			 "could not find any ACPI SRAT memory areas.\n");