[PATCH] Allow an arch to expand node boundaries

Arch-independent zone-sizing determines the size of a node
(pgdat->node_spanned_pages) based on the physical memory that was
registered by the architecture.  However, when
CONFIG_MEMORY_HOTPLUG_RESERVE is set, the architecture expects that the
spanned_pages will be much larger and that mem_map will be allocated that
is used lated on memory hot-add.

This patch allows an architecture that sets CONFIG_MEMORY_HOTPLUG_RESERVE
to call push_node_boundaries() which will set the node beginning and end to
at *least* the requested boundary.

Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: Andy Whitcroft <apw@shadowen.org>
Cc: Andi Kleen <ak@muc.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "Keith Mannthey" <kmannth@gmail.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 71 insertions, 0 deletions

diff --git a/arch/x86_64/mm/srat.c b/arch/x86_64/mm/srat.c
index db1b2e11cf8..f8c04d6935c 100644
--- a/arch/x86_64/mm/srat.c
+++ b/arch/x86_64/mm/srat.c
@@ -324,6 +324,8 @@ acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma)
 	       nd->start, nd->end);
 	e820_register_active_regions(node, nd->start >> PAGE_SHIFT,
 						nd->end >> PAGE_SHIFT);
+	push_node_boundaries(node, nd->start >> PAGE_SHIFT,
+						nd->end >> PAGE_SHIFT);
 
 #ifdef RESERVE_HOTADD
  	if (ma->flags.hot_pluggable && reserve_hotadd(node, start, end) < 0) {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 22936e1fcdf..9d046db31e7 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -970,6 +970,8 @@ extern void add_active_range(unsigned int nid, unsigned long start_pfn,
 					unsigned long end_pfn);
 extern void shrink_active_range(unsigned int nid, unsigned long old_end_pfn,
 						unsigned long new_end_pfn);
+extern void push_node_boundaries(unsigned int nid, unsigned long start_pfn,
+					unsigned long end_pfn);
 extern void remove_all_active_ranges(void);
 extern unsigned long absent_pages_in_range(unsigned long start_pfn,
 						unsigned long end_pfn);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 75133e1dc4b..acbf58f8a1b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -131,6 +131,10 @@ static unsigned long __initdata dma_reserve;
   int __initdata nr_nodemap_entries;
   unsigned long __initdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES];
   unsigned long __initdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
+#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
+  unsigned long __initdata node_boundary_start_pfn[MAX_NUMNODES];
+  unsigned long __initdata node_boundary_end_pfn[MAX_NUMNODES];
+#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */
 #endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
 
 #ifdef CONFIG_DEBUG_VM
@@ -2095,6 +2099,62 @@ void __init sparse_memory_present_with_active_regions(int nid)
 }
 
 /**
+ * push_node_boundaries - Push node boundaries to at least the requested boundary
+ * @nid: The nid of the node to push the boundary for
+ * @start_pfn: The start pfn of the node
+ * @end_pfn: The end pfn of the node
+ *
+ * In reserve-based hot-add, mem_map is allocated that is unused until hotadd
+ * time. Specifically, on x86_64, SRAT will report ranges that can potentially
+ * be hotplugged even though no physical memory exists. This function allows
+ * an arch to push out the node boundaries so mem_map is allocated that can
+ * be used later.
+ */
+#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
+void __init push_node_boundaries(unsigned int nid,
+		unsigned long start_pfn, unsigned long end_pfn)
+{
+	printk(KERN_DEBUG "Entering push_node_boundaries(%u, %lu, %lu)\n",
+			nid, start_pfn, end_pfn);
+
+	/* Initialise the boundary for this node if necessary */
+	if (node_boundary_end_pfn[nid] == 0)
+		node_boundary_start_pfn[nid] = -1UL;
+
+	/* Update the boundaries */
+	if (node_boundary_start_pfn[nid] > start_pfn)
+		node_boundary_start_pfn[nid] = start_pfn;
+	if (node_boundary_end_pfn[nid] < end_pfn)
+		node_boundary_end_pfn[nid] = end_pfn;
+}
+
+/* If necessary, push the node boundary out for reserve hotadd */
+static void __init account_node_boundary(unsigned int nid,
+		unsigned long *start_pfn, unsigned long *end_pfn)
+{
+	printk(KERN_DEBUG "Entering account_node_boundary(%u, %lu, %lu)\n",
+			nid, *start_pfn, *end_pfn);
+
+	/* Return if boundary information has not been provided */
+	if (node_boundary_end_pfn[nid] == 0)
+		return;
+
+	/* Check the boundaries and update if necessary */
+	if (node_boundary_start_pfn[nid] < *start_pfn)
+		*start_pfn = node_boundary_start_pfn[nid];
+	if (node_boundary_end_pfn[nid] > *end_pfn)
+		*end_pfn = node_boundary_end_pfn[nid];
+}
+#else
+void __init push_node_boundaries(unsigned int nid,
+		unsigned long start_pfn, unsigned long end_pfn) {}
+
+static void __init account_node_boundary(unsigned int nid,
+		unsigned long *start_pfn, unsigned long *end_pfn) {}
+#endif
+
+
+/**
  * get_pfn_range_for_nid - Return the start and end page frames for a node
  * @nid: The nid to return the range for. If MAX_NUMNODES, the min and max PFN are returned
  * @start_pfn: Passed by reference. On return, it will have the node start_pfn
@@ -2121,6 +2181,9 @@ void __init get_pfn_range_for_nid(unsigned int nid,
 		printk(KERN_WARNING "Node %u active with no memory\n", nid);
 		*start_pfn = 0;
 	}
+
+	/* Push the node boundaries out if requested */
+	account_node_boundary(nid, start_pfn, end_pfn);
 }
 
 /*
@@ -2527,6 +2590,10 @@ void __init remove_all_active_ranges()
 {
 	memset(early_node_map, 0, sizeof(early_node_map));
 	nr_nodemap_entries = 0;
+#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
+	memset(node_boundary_start_pfn, 0, sizeof(node_boundary_start_pfn));
+	memset(node_boundary_end_pfn, 0, sizeof(node_boundary_end_pfn));
+#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */
 }
 
 /* Compare two active node_active_regions */