1 files changed, 252 insertions, 1 deletions

diff --git a/mm/vmstat.c b/mm/vmstat.c
index fa12ea3051fb..7759941d4e77 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -16,6 +16,7 @@
 #include <linux/cpu.h>
 #include <linux/vmstat.h>
 #include <linux/sched.h>
+#include <linux/math64.h>
 
 #ifdef CONFIG_VM_EVENT_COUNTERS
 DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}};
@@ -379,7 +380,86 @@ void zone_statistics(struct zone *preferred_zone, struct zone *z)
 }
 #endif
 
-#ifdef CONFIG_PROC_FS
+#ifdef CONFIG_COMPACTION
+struct contig_page_info {
+        unsigned long free_pages;
+        unsigned long free_blocks_total;
+        unsigned long free_blocks_suitable;
+};
+
+/*
+ * Calculate the number of free pages in a zone, how many contiguous
+ * pages are free and how many are large enough to satisfy an allocation of
+ * the target size. Note that this function makes no attempt to estimate
+ * how many suitable free blocks there *might* be if MOVABLE pages were
+ * migrated. Calculating that is possible, but expensive and can be
+ * figured out from userspace
+ */
+static void fill_contig_page_info(struct zone *zone,
+                                unsigned int suitable_order,
+                                struct contig_page_info *info)
+{
+        unsigned int order;
+
+        info->free_pages = 0;
+        info->free_blocks_total = 0;
+        info->free_blocks_suitable = 0;
+
+        for (order = 0; order < MAX_ORDER; order++) {
+                unsigned long blocks;
+
+                /* Count number of free blocks */
+                blocks = zone->free_area[order].nr_free;
+                info->free_blocks_total += blocks;
+
+                /* Count free base pages */
+                info->free_pages += blocks << order;
+
+                /* Count the suitable free blocks */
+                if (order >= suitable_order)
+                        info->free_blocks_suitable += blocks <<
+                                                (order - suitable_order);
+        }
+}
+
+/*
+ * A fragmentation index only makes sense if an allocation of a requested
+ * size would fail. If that is true, the fragmentation index indicates
+ * whether external fragmentation or a lack of memory was the problem.
+ * The value can be used to determine if page reclaim or compaction
+ * should be used
+ */
+static int __fragmentation_index(unsigned int order, struct contig_page_info *info)
+{
+        unsigned long requested = 1UL << order;
+
+        if (!info->free_blocks_total)
+                return 0;
+
+        /* Fragmentation index only makes sense when a request would fail */
+        if (info->free_blocks_suitable)
+                return -1000;
+
+        /*
+         * Index is between 0 and 1 so return within 3 decimal places
+         *
+         * 0 => allocation would fail due to lack of memory
+         * 1 => allocation would fail due to fragmentation
+         */
+        return 1000 - div_u64( (1000+(div_u64(info->free_pages * 1000ULL, requested))), info->free_blocks_total);
+}
+
+/* Same as __fragmentation index but allocs contig_page_info on stack */
+int fragmentation_index(struct zone *zone, unsigned int order)
+{
+        struct contig_page_info info;
+
+        fill_contig_page_info(zone, order, &info);
+        return __fragmentation_index(order, &info);
+}
+#endif
+
+#if defined(CONFIG_PROC_FS) || defined(CONFIG_COMPACTION)
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 
@@ -432,7 +512,9 @@ static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat,
                 spin_unlock_irqrestore(&zone->lock, flags);
         }
 }
+#endif
 
+#ifdef CONFIG_PROC_FS
 static void frag_show_print(struct seq_file *m, pg_data_t *pgdat,
                                                 struct zone *zone)
 {
@@ -693,6 +775,16 @@ static const char * const vmstat_text[] = {
         "allocstall",
 
         "pgrotated",
+
+#ifdef CONFIG_COMPACTION
+        "compact_blocks_moved",
+        "compact_pages_moved",
+        "compact_pagemigrate_failed",
+        "compact_stall",
+        "compact_fail",
+        "compact_success",
+#endif
+
 #ifdef CONFIG_HUGETLB_PAGE
         "htlb_buddy_alloc_success",
         "htlb_buddy_alloc_fail",
@@ -954,3 +1046,162 @@ static int __init setup_vmstat(void)
         return 0;
 }
 module_init(setup_vmstat)
+
+#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION)
+#include <linux/debugfs.h>
+
+static struct dentry *extfrag_debug_root;
+
+/*
+ * Return an index indicating how much of the available free memory is
+ * unusable for an allocation of the requested size.
+ */
+static int unusable_free_index(unsigned int order,
+                                struct contig_page_info *info)
+{
+        /* No free memory is interpreted as all free memory is unusable */
+        if (info->free_pages == 0)
+                return 1000;
+
+        /*
+         * Index should be a value between 0 and 1. Return a value to 3
+         * decimal places.
+         *
+         * 0 => no fragmentation
+         * 1 => high fragmentation
+         */
+        return div_u64((info->free_pages - (info->free_blocks_suitable << order)) * 1000ULL, info->free_pages);
+
+}
+
+static void unusable_show_print(struct seq_file *m,
+                                        pg_data_t *pgdat, struct zone *zone)
+{
+        unsigned int order;
+        int index;
+        struct contig_page_info info;
+
+        seq_printf(m, "Node %d, zone %8s ",
+                                pgdat->node_id,
+                                zone->name);
+        for (order = 0; order < MAX_ORDER; ++order) {
+                fill_contig_page_info(zone, order, &info);
+                index = unusable_free_index(order, &info);
+                seq_printf(m, "%d.%03d ", index / 1000, index % 1000);
+        }
+
+        seq_putc(m, '\n');
+}
+
+/*
+ * Display unusable free space index
+ *
+ * The unusable free space index measures how much of the available free
+ * memory cannot be used to satisfy an allocation of a given size and is a
+ * value between 0 and 1. The higher the value, the more of free memory is
+ * unusable and by implication, the worse the external fragmentation is. This
+ * can be expressed as a percentage by multiplying by 100.
+ */
+static int unusable_show(struct seq_file *m, void *arg)
+{
+        pg_data_t *pgdat = (pg_data_t *)arg;
+
+        /* check memoryless node */
+        if (!node_state(pgdat->node_id, N_HIGH_MEMORY))
+                return 0;
+
+        walk_zones_in_node(m, pgdat, unusable_show_print);
+
+        return 0;
+}
+
+static const struct seq_operations unusable_op = {
+        .start  = frag_start,
+        .next   = frag_next,
+        .stop   = frag_stop,
+        .show   = unusable_show,
+};
+
+static int unusable_open(struct inode *inode, struct file *file)
+{
+        return seq_open(file, &unusable_op);
+}
+
+static const struct file_operations unusable_file_ops = {
+        .open           = unusable_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = seq_release,
+};
+
+static void extfrag_show_print(struct seq_file *m,
+                                        pg_data_t *pgdat, struct zone *zone)
+{
+        unsigned int order;
+        int index;
+
+        /* Alloc on stack as interrupts are disabled for zone walk */
+        struct contig_page_info info;
+
+        seq_printf(m, "Node %d, zone %8s ",
+                                pgdat->node_id,
+                                zone->name);
+        for (order = 0; order < MAX_ORDER; ++order) {
+                fill_contig_page_info(zone, order, &info);
+                index = __fragmentation_index(order, &info);
+                seq_printf(m, "%d.%03d ", index / 1000, index % 1000);
+        }
+
+        seq_putc(m, '\n');
+}
+
+/*
+ * Display fragmentation index for orders that allocations would fail for
+ */
+static int extfrag_show(struct seq_file *m, void *arg)
+{
+        pg_data_t *pgdat = (pg_data_t *)arg;
+
+        walk_zones_in_node(m, pgdat, extfrag_show_print);
+
+        return 0;
+}
+
+static const struct seq_operations extfrag_op = {
+        .start  = frag_start,
+        .next   = frag_next,
+        .stop   = frag_stop,
+        .show   = extfrag_show,
+};
+
+static int extfrag_open(struct inode *inode, struct file *file)
+{
+        return seq_open(file, &extfrag_op);
+}
+
+static const struct file_operations extfrag_file_ops = {
+        .open           = extfrag_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = seq_release,
+};
+
+static int __init extfrag_debug_init(void)
+{
+        extfrag_debug_root = debugfs_create_dir("extfrag", NULL);
+        if (!extfrag_debug_root)
+                return -ENOMEM;
+
+        if (!debugfs_create_file("unusable_index", 0444,
+                        extfrag_debug_root, NULL, &unusable_file_ops))
+                return -ENOMEM;
+
+        if (!debugfs_create_file("extfrag_index", 0444,
+                        extfrag_debug_root, NULL, &extfrag_file_ops))
+                return -ENOMEM;
+
+        return 0;
+}
+
+module_init(extfrag_debug_init);
+#endif