[RFC,2/3] Linux/Guest cooperative unmapped page cache control

Commit Message

Balbir Singh Oct. 28, 2010, 10:40 p.m. UTC

None

Patch

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 0f1da45..70f97ea 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -99,12 +99,24 @@  static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq)
 
 static void fill_balloon(struct virtio_balloon *vb, size_t num)
 {
+	u32 reclaim_cache_first;
+	int err;
+	gfp_t mask = GFP_HIGHUSER | __GFP_NORETRY | __GFP_NOMEMALLOC |
+			__GFP_NOWARN;
+
+	err = virtio_config_val(vb->vdev, VIRTIO_BALLOON_F_BALLOON_HINT,
+				offsetof(struct virtio_balloon_config,
+						reclaim_cache_first),
+				&reclaim_cache_first);
+
+	if (!err && reclaim_cache_first)
+		mask |= __GFP_FREE_CACHE;
+
 	/* We can only do one array worth at a time. */
 	num = min(num, ARRAY_SIZE(vb->pfns));
 
 	for (vb->num_pfns = 0; vb->num_pfns < num; vb->num_pfns++) {
-		struct page *page = alloc_page(GFP_HIGHUSER | __GFP_NORETRY |
-					__GFP_NOMEMALLOC | __GFP_NOWARN);
+		struct page *page = alloc_page(mask);
 		if (!page) {
 			if (printk_ratelimit())
 				dev_printk(KERN_INFO, &vb->vdev->dev,
@@ -358,6 +370,7 @@  static void __devexit virtballoon_remove(struct virtio_device *vdev)
 static unsigned int features[] = {
 	VIRTIO_BALLOON_F_MUST_TELL_HOST,
 	VIRTIO_BALLOON_F_STATS_VQ,
+	VIRTIO_BALLOON_F_BALLOON_HINT,
 };
 
 static struct virtio_driver virtio_balloon_driver = {
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 975609c..9048259 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -61,12 +61,18 @@  struct vm_area_struct;
 #endif
 
 /*
+ * While allocating pages, try to free cache pages first. Note the
+ * heavy dependency on zone_reclaim_mode logic
+ */
+#define __GFP_FREE_CACHE ((__force gfp_t)0x400000u) /* Free cache first */
+
+/*
  * This may seem redundant, but it's a way of annotating false positives vs.
  * allocations that simply cannot be supported (e.g. page tables).
  */
 #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK)
 
-#define __GFP_BITS_SHIFT 22	/* Room for 22 __GFP_FOO bits */
+#define __GFP_BITS_SHIFT 23	/* Room for 22 __GFP_FOO bits */
 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
 
 /* This equals 0, but use constants in case they ever change */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 5d29097..e77db75 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -254,16 +254,13 @@  extern long vm_total_pages;
 extern bool should_balance_unmapped_pages(struct zone *zone);
 
 extern int sysctl_min_unmapped_ratio;
-#ifdef CONFIG_NUMA
-extern int zone_reclaim_mode;
 extern int sysctl_min_slab_ratio;
 extern int zone_reclaim(struct zone *, gfp_t, unsigned int);
+
+#ifdef CONFIG_NUMA
+extern int zone_reclaim_mode;
 #else
 #define zone_reclaim_mode 0
-static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order)
-{
-	return 0;
-}
 #endif
 
 extern int page_evictable(struct page *page, struct vm_area_struct *vma);
diff --git a/include/linux/virtio_balloon.h b/include/linux/virtio_balloon.h
index a50ecd1..6e405b4 100644
--- a/include/linux/virtio_balloon.h
+++ b/include/linux/virtio_balloon.h
@@ -8,6 +8,7 @@ 
 /* The feature bitmap for virtio balloon */
 #define VIRTIO_BALLOON_F_MUST_TELL_HOST	0 /* Tell before reclaiming pages */
 #define VIRTIO_BALLOON_F_STATS_VQ	1 /* Memory Stats virtqueue */
+#define VIRTIO_BALLOON_F_BALLOON_HINT	2 /* Reclaim hint */
 
 /* Size of a PFN in the balloon interface. */
 #define VIRTIO_BALLOON_PFN_SHIFT 12
@@ -18,6 +19,8 @@  struct virtio_balloon_config
 	__le32 num_pages;
 	/* Number of pages we've actually got in balloon. */
 	__le32 actual;
+	/* Hint, should we reclaim cached pages first? */
+	__le32 reclaim_cache_first;
 };
 
 #define VIRTIO_BALLOON_S_SWAP_IN  0   /* Amount of memory swapped in */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d8fe29f..2cdf4a9 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1650,7 +1650,8 @@  zonelist_scan:
 				    classzone_idx, alloc_flags))
 				goto try_this_zone;
 
-			if (zone_reclaim_mode == 0)
+			if (zone_reclaim_mode == 0 &&
+				!(gfp_mask & __GFP_FREE_CACHE))
 				goto this_zone_full;
 
 			ret = zone_reclaim(zone, gfp_mask, order);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 02346ad..9a11e5a 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2705,6 +2705,7 @@  module_init(kswapd_init)
  * the watermarks.
  */
 int zone_reclaim_mode __read_mostly;
+#endif
 
 /*
  * If the number of slab pages in a zone grows beyond this percentage then
@@ -2870,7 +2871,6 @@  int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 
 	return ret;
 }
-#endif
 
 /*
  * page_evictable - test whether a page is evictable