mm/page_alloc.c: calculate 'available' memory in a separate function

Add a new field, VIRTIO_BALLOON_S_AVAIL, to virtio_balloon memory
statistics protocol, corresponding to 'Available' in /proc/meminfo.

It indicates to the hypervisor how big the balloon can be inflated
without pushing the guest system to swap.  This metric would be very
useful in VM orchestration software to improve memory management of
different VMs under overcommit.

This patch (of 2):

Factor out calculation of the available memory counter into a separate
exportable function, in order to be able to use it in other parts of the
kernel.

In particular, it appears a relevant metric to report to the hypervisor
via virtio-balloon statistics interface (in a followup patch).

Signed-off-by: Igor Redko <redkoi@virtuozzo.com>
Signed-off-by: Denis V. Lunev <den@openvz.org>
Reviewed-by: Roman Kagan <rkagan@virtuozzo.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 43 insertions, 0 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 25a75da53c27..941b802e11ec 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3713,6 +3713,49 @@ static inline void show_node(struct zone *zone)
                 printk("Node %d ", zone_to_nid(zone));
 }
 
+long si_mem_available(void)
+{
+        long available;
+        unsigned long pagecache;
+        unsigned long wmark_low = 0;
+        unsigned long pages[NR_LRU_LISTS];
+        struct zone *zone;
+        int lru;
+
+        for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
+                pages[lru] = global_page_state(NR_LRU_BASE + lru);
+
+        for_each_zone(zone)
+                wmark_low += zone->watermark[WMARK_LOW];
+
+        /*
+         * Estimate the amount of memory available for userspace allocations,
+         * without causing swapping.
+         */
+        available = global_page_state(NR_FREE_PAGES) - totalreserve_pages;
+
+        /*
+         * Not all the page cache can be freed, otherwise the system will
+         * start swapping. Assume at least half of the page cache, or the
+         * low watermark worth of cache, needs to stay.
+         */
+        pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE];
+        pagecache -= min(pagecache / 2, wmark_low);
+        available += pagecache;
+
+        /*
+         * Part of the reclaimable slab consists of items that are in use,
+         * and cannot be freed. Cap this estimate at the low watermark.
+         */
+        available += global_page_state(NR_SLAB_RECLAIMABLE) -
+                     min(global_page_state(NR_SLAB_RECLAIMABLE) / 2, wmark_low);
+
+        if (available < 0)
+                available = 0;
+        return available;
+}
+EXPORT_SYMBOL_GPL(si_mem_available);
+
 void si_meminfo(struct sysinfo *val)
 {
         val->totalram = totalram_pages;