Merge branch 'x86/for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86/for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (821 commits)
  x86: make 64bit hpet_set_mapping to use ioremap too, v2
  x86: get x86_phys_bits early
  x86: max_low_pfn_mapped fix #4
  x86: change _node_to_cpumask_ptr to return const ptr
  x86: I/O APIC: remove an IRQ2-mask hack
  x86: fix numaq_tsc_disable calling
  x86, e820: remove end_user_pfn
  x86: max_low_pfn_mapped fix, #3
  x86: max_low_pfn_mapped fix, #2
  x86: max_low_pfn_mapped fix, #1
  x86_64: fix delayed signals
  x86: remove conflicting nx6325 and nx6125 quirks
  x86: Recover timer_ack lost in the merge of the NMI watchdog
  x86: I/O APIC: Never configure IRQ2
  x86: L-APIC: Always fully configure IRQ0
  x86: L-APIC: Set IRQ0 as edge-triggered
  x86: merge dwarf2 headers
  x86: use AS_CFI instead of UNWIND_INFO
  x86: use ignore macro instead of hash comment
  x86: use matching CFI_ENDPROC
  ...

2 files changed, 80 insertions, 24 deletions

diff --git a/mm/mprotect.c b/mm/mprotect.c
index a5bf31c..acfe7c8 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -47,19 +47,17 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
 		if (pte_present(oldpte)) {
 			pte_t ptent;
 
-			/* Avoid an SMP race with hardware updated dirty/clean
-			 * bits by wiping the pte and then setting the new pte
-			 * into place.
-			 */
-			ptent = ptep_get_and_clear(mm, addr, pte);
+			ptent = ptep_modify_prot_start(mm, addr, pte);
 			ptent = pte_modify(ptent, newprot);
+
 			/*
 			 * Avoid taking write faults for pages we know to be
 			 * dirty.
 			 */
 			if (dirty_accountable && pte_dirty(ptent))
 				ptent = pte_mkwrite(ptent);
-			set_pte_at(mm, addr, pte, ptent);
+
+			ptep_modify_prot_commit(mm, addr, pte, ptent);
 #ifdef CONFIG_MIGRATION
 		} else if (!pte_file(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f32fae3..f024b9b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2929,6 +2929,18 @@ void __init free_bootmem_with_active_regions(int nid,
 	}
 }
 
+void __init work_with_active_regions(int nid, work_fn_t work_fn, void *data)
+{
+	int i;
+	int ret;
+
+	for_each_active_range_index_in_nid(i, nid) {
+		ret = work_fn(early_node_map[i].start_pfn,
+			      early_node_map[i].end_pfn, data);
+		if (ret)
+			break;
+	}
+}
 /**
  * sparse_memory_present_with_active_regions - Call memory_present for each active range
  * @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used.
@@ -3461,6 +3473,11 @@ void __paginginit free_area_init_node(int nid, struct pglist_data *pgdat,
 	calculate_node_totalpages(pgdat, zones_size, zholes_size);
 
 	alloc_node_mem_map(pgdat);
+#ifdef CONFIG_FLAT_NODE_MEM_MAP
+	printk(KERN_DEBUG "free_area_init_node: node %d, pgdat %08lx, node_mem_map %08lx\n",
+		nid, (unsigned long)pgdat,
+		(unsigned long)pgdat->node_mem_map);
+#endif
 
 	free_area_init_core(pgdat, zones_size, zholes_size);
 }
@@ -3503,7 +3520,7 @@ void __init add_active_range(unsigned int nid, unsigned long start_pfn,
 {
 	int i;
 
-	printk(KERN_DEBUG "Entering add_active_range(%d, %lu, %lu) "
+	printk(KERN_DEBUG "Entering add_active_range(%d, %#lx, %#lx) "
 			  "%d entries of %d used\n",
 			  nid, start_pfn, end_pfn,
 			  nr_nodemap_entries, MAX_ACTIVE_REGIONS);
@@ -3547,27 +3564,68 @@ void __init add_active_range(unsigned int nid, unsigned long start_pfn,
 }
 
 /**
- * shrink_active_range - Shrink an existing registered range of PFNs
+ * remove_active_range - Shrink an existing registered range of PFNs
  * @nid: The node id the range is on that should be shrunk
- * @old_end_pfn: The old end PFN of the range
- * @new_end_pfn: The new PFN of the range
+ * @start_pfn: The new PFN of the range
+ * @end_pfn: The new PFN of the range
  *
  * i386 with NUMA use alloc_remap() to store a node_mem_map on a local node.
- * The map is kept at the end physical page range that has already been
- * registered with add_active_range(). This function allows an arch to shrink
- * an existing registered range.
+ * The map is kept near the end physical page range that has already been
+ * registered. This function allows an arch to shrink an existing registered
+ * range.
  */
-void __init shrink_active_range(unsigned int nid, unsigned long old_end_pfn,
-						unsigned long new_end_pfn)
+void __init remove_active_range(unsigned int nid, unsigned long start_pfn,
+				unsigned long end_pfn)
 {
-	int i;
+	int i, j;
+	int removed = 0;
+
+	printk(KERN_DEBUG "remove_active_range (%d, %lu, %lu)\n",
+			  nid, start_pfn, end_pfn);
 
 	/* Find the old active region end and shrink */
-	for_each_active_range_index_in_nid(i, nid)
-		if (early_node_map[i].end_pfn == old_end_pfn) {
-			early_node_map[i].end_pfn = new_end_pfn;
-			break;
+	for_each_active_range_index_in_nid(i, nid) {
+		if (early_node_map[i].start_pfn >= start_pfn &&
+		    early_node_map[i].end_pfn <= end_pfn) {
+			/* clear it */
+			early_node_map[i].start_pfn = 0;
+			early_node_map[i].end_pfn = 0;
+			removed = 1;
+			continue;
+		}
+		if (early_node_map[i].start_pfn < start_pfn &&
+		    early_node_map[i].end_pfn > start_pfn) {
+			unsigned long temp_end_pfn = early_node_map[i].end_pfn;
+			early_node_map[i].end_pfn = start_pfn;
+			if (temp_end_pfn > end_pfn)
+				add_active_range(nid, end_pfn, temp_end_pfn);
+			continue;
 		}
+		if (early_node_map[i].start_pfn >= start_pfn &&
+		    early_node_map[i].end_pfn > end_pfn &&
+		    early_node_map[i].start_pfn < end_pfn) {
+			early_node_map[i].start_pfn = end_pfn;
+			continue;
+		}
+	}
+
+	if (!removed)
+		return;
+
+	/* remove the blank ones */
+	for (i = nr_nodemap_entries - 1; i > 0; i--) {
+		if (early_node_map[i].nid != nid)
+			continue;
+		if (early_node_map[i].end_pfn)
+			continue;
+		/* we found it, get rid of it */
+		for (j = i; j < nr_nodemap_entries - 1; j++)
+			memcpy(&early_node_map[j], &early_node_map[j+1],
+				sizeof(early_node_map[j]));
+		j = nr_nodemap_entries - 1;
+		memset(&early_node_map[j], 0, sizeof(early_node_map[j]));
+		nr_nodemap_entries--;
+	}
 }
 
 /**
@@ -3611,7 +3669,7 @@ static void __init sort_node_map(void)
 }
 
 /* Find the lowest pfn for a node */
-unsigned long __init find_min_pfn_for_node(unsigned long nid)
+unsigned long __init find_min_pfn_for_node(int nid)
 {
 	int i;
 	unsigned long min_pfn = ULONG_MAX;
@@ -3622,7 +3680,7 @@ unsigned long __init find_min_pfn_for_node(unsigned long nid)
 
 	if (min_pfn == ULONG_MAX) {
 		printk(KERN_WARNING
-			"Could not find start_pfn for node %lu\n", nid);
+			"Could not find start_pfn for node %d\n", nid);
 		return 0;
 	}
 
@@ -3878,7 +3936,7 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 	for (i = 0; i < MAX_NR_ZONES; i++) {
 		if (i == ZONE_MOVABLE)
 			continue;
-		printk("  %-8s %8lu -> %8lu\n",
+		printk("  %-8s %0#10lx -> %0#10lx\n",
 				zone_names[i],
 				arch_zone_lowest_possible_pfn[i],
 				arch_zone_highest_possible_pfn[i]);
@@ -3894,7 +3952,7 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 	/* Print out the early_node_map[] */
 	printk("early_node_map[%d] active PFN ranges\n", nr_nodemap_entries);
 	for (i = 0; i < nr_nodemap_entries; i++)
-		printk("  %3d: %8lu -> %8lu\n", early_node_map[i].nid,
+		printk("  %3d: %0#10lx -> %0#10lx\n", early_node_map[i].nid,
 						early_node_map[i].start_pfn,
 						early_node_map[i].end_pfn);