From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Sat, 28 Feb 2015 19:38:59 +0000 (-0800)
Subject: Drivers: hv: hv_balloon: report offline pages as being used
X-Git-Tag: firefly_0821_release~176^2~1906^2~103
X-Git-Url: http://demsky.eecs.uci.edu/git/?a=commitdiff_plain;h=549fd280b145e2154db5a7d06981d041f8bbf597;p=firefly-linux-kernel-4.4.55.git

Drivers: hv: hv_balloon: report offline pages as being used

When hot-added memory pages are not brought online or when some memory blocks
are sent offline the subsequent ballooning process kills the guest with OOM
killer. This happens as we don't report these pages as neither used nor free
and apparently host algorithm considers them as being unused. Keep track of
all online/offline operations and report all currently offline pages as being
used so host won't try to balloon them out.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---

diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index ea3d33cdf99c..53932b3e1973 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -503,6 +503,8 @@ struct hv_dynmem_device {
 	 * Number of pages we have currently ballooned out.
 	 */
 	unsigned int num_pages_ballooned;
+	unsigned int num_pages_onlined;
+	unsigned int num_pages_added;
 
 	/*
 	 * State to manage the ballooning (up) operation.
@@ -556,12 +558,15 @@ static void post_status(struct hv_dynmem_device *dm);
 static int hv_memory_notifier(struct notifier_block *nb, unsigned long val,
 			      void *v)
 {
+	struct memory_notify *mem = (struct memory_notify *)v;
+
 	switch (val) {
 	case MEM_GOING_ONLINE:
 		mutex_lock(&dm_device.ha_region_mutex);
 		break;
 
 	case MEM_ONLINE:
+		dm_device.num_pages_onlined += mem->nr_pages;
 	case MEM_CANCEL_ONLINE:
 		mutex_unlock(&dm_device.ha_region_mutex);
 		if (dm_device.ha_waiting) {
@@ -570,8 +575,12 @@ static int hv_memory_notifier(struct notifier_block *nb, unsigned long val,
 		}
 		break;
 
-	case MEM_GOING_OFFLINE:
 	case MEM_OFFLINE:
+		mutex_lock(&dm_device.ha_region_mutex);
+		dm_device.num_pages_onlined -= mem->nr_pages;
+		mutex_unlock(&dm_device.ha_region_mutex);
+		break;
+	case MEM_GOING_OFFLINE:
 	case MEM_CANCEL_OFFLINE:
 		break;
 	}
@@ -896,6 +905,8 @@ static void hot_add_req(struct work_struct *dummy)
 	if (do_hot_add)
 		resp.page_count = process_hot_add(pg_start, pfn_cnt,
 						rg_start, rg_sz);
+
+	dm->num_pages_added += resp.page_count;
 	mutex_unlock(&dm_device.ha_region_mutex);
 #endif
 	/*
@@ -1009,17 +1020,21 @@ static void post_status(struct hv_dynmem_device *dm)
 	status.hdr.trans_id = atomic_inc_return(&trans_id);
 
 	/*
-	 * The host expects the guest to report free memory.
-	 * Further, the host expects the pressure information to
-	 * include the ballooned out pages.
-	 * For a given amount of memory that we are managing, we
-	 * need to compute a floor below which we should not balloon.
-	 * Compute this and add it to the pressure report.
+	 * The host expects the guest to report free and committed memory.
+	 * Furthermore, the host expects the pressure information to include
+	 * the ballooned out pages. For a given amount of memory that we are
+	 * managing we need to compute a floor below which we should not
+	 * balloon. Compute this and add it to the pressure report.
+	 * We also need to report all offline pages (num_pages_added -
+	 * num_pages_onlined) as committed to the host, otherwise it can try
+	 * asking us to balloon them out.
 	 */
 	status.num_avail = val.freeram;
 	status.num_committed = vm_memory_committed() +
-				dm->num_pages_ballooned +
-				compute_balloon_floor();
+		dm->num_pages_ballooned +
+		(dm->num_pages_added > dm->num_pages_onlined ?
+		 dm->num_pages_added - dm->num_pages_onlined : 0) +
+		compute_balloon_floor();
 
 	/*
 	 * If our transaction ID is no longer current, just don't