Create the ZONE_MOVABLE zone

The following 8 patches against 2.6.20-mm2 create a zone called ZONE_MOVABLE
that is only usable by allocations that specify both __GFP_HIGHMEM and
__GFP_MOVABLE.  This has the effect of keeping all non-movable pages within a
single memory partition while allowing movable allocations to be satisfied
from either partition.  The patches may be applied with the list-based
anti-fragmentation patches that groups pages together based on mobility.

The size of the zone is determined by a kernelcore= parameter specified at
boot-time.  This specifies how much memory is usable by non-movable
allocations and the remainder is used for ZONE_MOVABLE.  Any range of pages
within ZONE_MOVABLE can be released by migrating the pages or by reclaiming.

When selecting a zone to take pages from for ZONE_MOVABLE, there are two
things to consider.  First, only memory from the highest populated zone is
used for ZONE_MOVABLE.  On the x86, this is probably going to be ZONE_HIGHMEM
but it would be ZONE_DMA on ppc64 or possibly ZONE_DMA32 on x86_64.  Second,
the amount of memory usable by the kernel will be spread evenly throughout
NUMA nodes where possible.  If the nodes are not of equal size, the amount of
memory usable by the kernel on some nodes may be greater than others.

By default, the zone is not as useful for hugetlb allocations because they are
pinned and non-migratable (currently at least).  A sysctl is provided that
allows huge pages to be allocated from that zone.  This means that the huge
page pool can be resized to the size of ZONE_MOVABLE during the lifetime of
the system assuming that pages are not mlocked.  Despite huge pages being
non-movable, we do not introduce additional external fragmentation of note as
huge pages are always the largest contiguous block we care about.

Credit goes to Andy Whitcroft for catching a large variety of problems during
review of the patches.

This patch creates an additional zone, ZONE_MOVABLE.  This zone is only usable
by allocations which specify both __GFP_HIGHMEM and __GFP_MOVABLE.  Hot-added
memory continues to be placed in their existing destination as there is no
mechanism to redirect them to a specific zone.

[y-goto@jp.fujitsu.com: Fix section mismatch of memory hotplug related code]
[akpm@linux-foundation.org: various fixes]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Cc: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: William Lee Irwin III <wli@holomorphy.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 235 insertions, 6 deletions

diff --git a/mm/highmem.c b/mm/highmem.c
index be8f8d3..7a967bc 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -46,9 +46,14 @@ unsigned int nr_free_highpages (void)
 	pg_data_t *pgdat;
 	unsigned int pages = 0;
 
-	for_each_online_pgdat(pgdat)
+	for_each_online_pgdat(pgdat) {
 		pages += zone_page_state(&pgdat->node_zones[ZONE_HIGHMEM],
 			NR_FREE_PAGES);
+		if (zone_movable_is_highmem())
+			pages += zone_page_state(
+					&pgdat->node_zones[ZONE_MOVABLE],
+					NR_FREE_PAGES);
+	}
 
 	return pages;
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f9e4e64..c3f6f85 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -80,8 +80,9 @@ int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = {
 	 256,
 #endif
 #ifdef CONFIG_HIGHMEM
-	 32
+	 32,
 #endif
+	 32,
 };
 
 EXPORT_SYMBOL(totalram_pages);
@@ -95,8 +96,9 @@ static char * const zone_names[MAX_NR_ZONES] = {
 #endif
 	 "Normal",
 #ifdef CONFIG_HIGHMEM
-	 "HighMem"
+	 "HighMem",
 #endif
+	 "Movable",
 };
 
 int min_free_kbytes = 1024;
@@ -134,6 +136,12 @@ static unsigned long __meminitdata dma_reserve;
   static unsigned long __meminitdata node_boundary_start_pfn[MAX_NUMNODES];
   static unsigned long __meminitdata node_boundary_end_pfn[MAX_NUMNODES];
 #endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */
+  unsigned long __initdata required_kernelcore;
+  unsigned long __initdata zone_movable_pfn[MAX_NUMNODES];
+
+  /* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */
+  int movable_zone;
+  EXPORT_SYMBOL(movable_zone);
 #endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
 
 #if MAX_NUMNODES > 1
@@ -1480,7 +1488,7 @@ unsigned int nr_free_buffer_pages(void)
  */
 unsigned int nr_free_pagecache_pages(void)
 {
-	return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER));
+	return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER_MOVABLE));
 }
 
 static inline void show_node(struct zone *zone)
@@ -2667,6 +2675,63 @@ void __meminit get_pfn_range_for_nid(unsigned int nid,
 }
 
 /*
+ * This finds a zone that can be used for ZONE_MOVABLE pages. The
+ * assumption is made that zones within a node are ordered in monotonic
+ * increasing memory addresses so that the "highest" populated zone is used
+ */
+void __init find_usable_zone_for_movable(void)
+{
+	int zone_index;
+	for (zone_index = MAX_NR_ZONES - 1; zone_index >= 0; zone_index--) {
+		if (zone_index == ZONE_MOVABLE)
+			continue;
+
+		if (arch_zone_highest_possible_pfn[zone_index] >
+				arch_zone_lowest_possible_pfn[zone_index])
+			break;
+	}
+
+	VM_BUG_ON(zone_index == -1);
+	movable_zone = zone_index;
+}
+
+/*
+ * The zone ranges provided by the architecture do not include ZONE_MOVABLE
+ * because it is sized independant of architecture. Unlike the other zones,
+ * the starting point for ZONE_MOVABLE is not fixed. It may be different
+ * in each node depending on the size of each node and how evenly kernelcore
+ * is distributed. This helper function adjusts the zone ranges
+ * provided by the architecture for a given node by using the end of the
+ * highest usable zone for ZONE_MOVABLE. This preserves the assumption that
+ * zones within a node are in order of monotonic increases memory addresses
+ */
+void __meminit adjust_zone_range_for_zone_movable(int nid,
+					unsigned long zone_type,
+					unsigned long node_start_pfn,
+					unsigned long node_end_pfn,
+					unsigned long *zone_start_pfn,
+					unsigned long *zone_end_pfn)
+{
+	/* Only adjust if ZONE_MOVABLE is on this node */
+	if (zone_movable_pfn[nid]) {
+		/* Size ZONE_MOVABLE */
+		if (zone_type == ZONE_MOVABLE) {
+			*zone_start_pfn = zone_movable_pfn[nid];
+			*zone_end_pfn = min(node_end_pfn,
+				arch_zone_highest_possible_pfn[movable_zone]);
+
+		/* Adjust for ZONE_MOVABLE starting within this range */
+		} else if (*zone_start_pfn < zone_movable_pfn[nid] &&
+				*zone_end_pfn > zone_movable_pfn[nid]) {
+			*zone_end_pfn = zone_movable_pfn[nid];
+
+		/* Check if this whole range is within ZONE_MOVABLE */
+		} else if (*zone_start_pfn >= zone_movable_pfn[nid])
+			*zone_start_pfn = *zone_end_pfn;
+	}
+}
+
+/*
  * Return the number of pages a zone spans in a node, including holes
  * present_pages = zone_spanned_pages_in_node() - zone_absent_pages_in_node()
  */
@@ -2681,6 +2746,9 @@ static unsigned long __meminit zone_spanned_pages_in_node(int nid,
 	get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn);
 	zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type];
 	zone_end_pfn = arch_zone_highest_possible_pfn[zone_type];
+	adjust_zone_range_for_zone_movable(nid, zone_type,
+				node_start_pfn, node_end_pfn,
+				&zone_start_pfn, &zone_end_pfn);
 
 	/* Check that this node has pages within the zone's required range */
 	if (zone_end_pfn < node_start_pfn || zone_start_pfn > node_end_pfn)
@@ -2771,6 +2839,9 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid,
 	zone_end_pfn = min(arch_zone_highest_possible_pfn[zone_type],
 							node_end_pfn);
 
+	adjust_zone_range_for_zone_movable(nid, zone_type,
+			node_start_pfn, node_end_pfn,
+			&zone_start_pfn, &zone_end_pfn);
 	return __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn);
 }
 
@@ -3148,6 +3219,122 @@ unsigned long __init find_max_pfn_with_active_regions(void)
 	return max_pfn;
 }
 
+/*
+ * Find the PFN the Movable zone begins in each node. Kernel memory
+ * is spread evenly between nodes as long as the nodes have enough
+ * memory. When they don't, some nodes will have more kernelcore than
+ * others
+ */
+void __init find_zone_movable_pfns_for_nodes(unsigned long *movable_pfn)
+{
+	int i, nid;
+	unsigned long usable_startpfn;
+	unsigned long kernelcore_node, kernelcore_remaining;
+	int usable_nodes = num_online_nodes();
+
+	/* If kernelcore was not specified, there is no ZONE_MOVABLE */
+	if (!required_kernelcore)
+		return;
+
+	/* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */
+	find_usable_zone_for_movable();
+	usable_startpfn = arch_zone_lowest_possible_pfn[movable_zone];
+
+restart:
+	/* Spread kernelcore memory as evenly as possible throughout nodes */
+	kernelcore_node = required_kernelcore / usable_nodes;
+	for_each_online_node(nid) {
+		/*
+		 * Recalculate kernelcore_node if the division per node
+		 * now exceeds what is necessary to satisfy the requested
+		 * amount of memory for the kernel
+		 */
+		if (required_kernelcore < kernelcore_node)
+			kernelcore_node = required_kernelcore / usable_nodes;
+
+		/*
+		 * As the map is walked, we track how much memory is usable
+		 * by the kernel using kernelcore_remaining. When it is
+		 * 0, the rest of the node is usable by ZONE_MOVABLE
+		 */
+		kernelcore_remaining = kernelcore_node;
+
+		/* Go through each range of PFNs within this node */
+		for_each_active_range_index_in_nid(i, nid) {
+			unsigned long start_pfn, end_pfn;
+			unsigned long size_pages;
+
+			start_pfn = max(early_node_map[i].start_pfn,
+						zone_movable_pfn[nid]);
+			end_pfn = early_node_map[i].end_pfn;
+			if (start_pfn >= end_pfn)
+				continue;
+
+			/* Account for what is only usable for kernelcore */
+			if (start_pfn < usable_startpfn) {
+				unsigned long kernel_pages;
+				kernel_pages = min(end_pfn, usable_startpfn)
+								- start_pfn;
+
+				kernelcore_remaining -= min(kernel_pages,
+							kernelcore_remaining);
+				required_kernelcore -= min(kernel_pages,
+							required_kernelcore);
+
+				/* Continue if range is now fully accounted */
+				if (end_pfn <= usable_startpfn) {
+
+					/*
+					 * Push zone_movable_pfn to the end so
+					 * that if we have to rebalance
+					 * kernelcore across nodes, we will
+					 * not double account here
+					 */
+					zone_movable_pfn[nid] = end_pfn;
+					continue;
+				}
+				start_pfn = usable_startpfn;
+			}
+
+			/*
+			 * The usable PFN range for ZONE_MOVABLE is from
+			 * start_pfn->end_pfn. Calculate size_pages as the
+			 * number of pages used as kernelcore
+			 */
+			size_pages = end_pfn - start_pfn;
+			if (size_pages > kernelcore_remaining)
+				size_pages = kernelcore_remaining;
+			zone_movable_pfn[nid] = start_pfn + size_pages;
+
+			/*
+			 * Some kernelcore has been met, update counts and
+			 * break if the kernelcore for this node has been
+			 * satisified
+			 */
+			required_kernelcore -= min(required_kernelcore,
+								size_pages);
+			kernelcore_remaining -= size_pages;
+			if (!kernelcore_remaining)
+				break;
+		}
+	}
+
+	/*
+	 * If there is still required_kernelcore, we do another pass with one
+	 * less node in the count. This will push zone_movable_pfn[nid] further
+	 * along on the nodes that still have memory until kernelcore is
+	 * satisified
+	 */
+	usable_nodes--;
+	if (usable_nodes && required_kernelcore > usable_nodes)
+		goto restart;
+
+	/* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */
+	for (nid = 0; nid < MAX_NUMNODES; nid++)
+		zone_movable_pfn[nid] =
+			roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES);
+}
+
 /**
  * free_area_init_nodes - Initialise all pg_data_t and zone data
  * @max_zone_pfn: an array of max PFNs for each zone
@@ -3177,19 +3364,37 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 	arch_zone_lowest_possible_pfn[0] = find_min_pfn_with_active_regions();
 	arch_zone_highest_possible_pfn[0] = max_zone_pfn[0];
 	for (i = 1; i < MAX_NR_ZONES; i++) {
+		if (i == ZONE_MOVABLE)
+			continue;
 		arch_zone_lowest_possible_pfn[i] =
 			arch_zone_highest_possible_pfn[i-1];
 		arch_zone_highest_possible_pfn[i] =
 			max(max_zone_pfn[i], arch_zone_lowest_possible_pfn[i]);
 	}
+	arch_zone_lowest_possible_pfn[ZONE_MOVABLE] = 0;
+	arch_zone_highest_possible_pfn[ZONE_MOVABLE] = 0;
+
+	/* Find the PFNs that ZONE_MOVABLE begins at in each node */
+	memset(zone_movable_pfn, 0, sizeof(zone_movable_pfn));
+	find_zone_movable_pfns_for_nodes(zone_movable_pfn);
 
 	/* Print out the zone ranges */
 	printk("Zone PFN ranges:\n");
-	for (i = 0; i < MAX_NR_ZONES; i++)
+	for (i = 0; i < MAX_NR_ZONES; i++) {
+		if (i == ZONE_MOVABLE)
+			continue;
 		printk("  %-8s %8lu -> %8lu\n",
 				zone_names[i],
 				arch_zone_lowest_possible_pfn[i],
 				arch_zone_highest_possible_pfn[i]);
+	}
+
+	/* Print out the PFNs ZONE_MOVABLE begins at in each node */
+	printk("Movable zone start PFN for each node\n");
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		if (zone_movable_pfn[i])
+			printk("  Node %d: %lu\n", i, zone_movable_pfn[i]);
+	}
 
 	/* Print out the early_node_map[] */
 	printk("early_node_map[%d] active PFN ranges\n", nr_nodemap_entries);
@@ -3206,6 +3411,25 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 				find_min_pfn_for_node(nid), NULL);
 	}
 }
+
+/*
+ * kernelcore=size sets the amount of memory for use for allocations that
+ * cannot be reclaimed or migrated.
+ */
+int __init cmdline_parse_kernelcore(char *p)
+{
+	unsigned long long coremem;
+	if (!p)
+		return -EINVAL;
+
+	coremem = memparse(p, &p);
+	required_kernelcore = coremem >> PAGE_SHIFT;
+
+	/* Paranoid check that UL is enough for required_kernelcore */
+	WARN_ON((coremem >> PAGE_SHIFT) > ULONG_MAX);
+
+	return 0;
+}
 #endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
 
 /**
diff --git a/mm/vmstat.c b/mm/vmstat.c
index eceaf49..fadf791 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -472,7 +472,7 @@ const struct seq_operations fragmentation_op = {
 #endif
 
 #define TEXTS_FOR_ZONES(xx) TEXT_FOR_DMA(xx) TEXT_FOR_DMA32(xx) xx "_normal", \
-					TEXT_FOR_HIGHMEM(xx)
+					TEXT_FOR_HIGHMEM(xx) xx "_movable",
 
 static const char * const vmstat_text[] = {
 	/* Zoned VM counters */