Merge branch 'nfs-rdma' of git://git.linux-nfs.org/projects/anna/nfs-rdma into linux-next

* 'nfs-rdma' of git://git.linux-nfs.org/projects/anna/nfs-rdma: (916 commits)
  xprtrdma: Handle additional connection events
  xprtrdma: Remove RPCRDMA_PERSISTENT_REGISTRATION macro
  xprtrdma: Make rpcrdma_ep_disconnect() return void
  xprtrdma: Schedule reply tasklet once per upcall
  xprtrdma: Allocate each struct rpcrdma_mw separately
  xprtrdma: Rename frmr_wr
  xprtrdma: Disable completions for LOCAL_INV Work Requests
  xprtrdma: Disable completions for FAST_REG_MR Work Requests
  xprtrdma: Don't post a LOCAL_INV in rpcrdma_register_frmr_external()
  xprtrdma: Reset FRMRs after a flushed LOCAL_INV Work Request
  xprtrdma: Reset FRMRs when FAST_REG_MR is flushed by a disconnect
  xprtrdma: Properly handle exhaustion of the rb_mws list
  xprtrdma: Chain together all MWs in same buffer pool
  xprtrdma: Back off rkey when FAST_REG_MR fails
  xprtrdma: Unclutter struct rpcrdma_mr_seg
  xprtrdma: Don't invalidate FRMRs if registration fails
  xprtrdma: On disconnect, don't ignore pending CQEs
  xprtrdma: Update rkeys after transport reconnect
  xprtrdma: Limit data payload size for ALLPHYSICAL
  xprtrdma: Protect ia->ri_id when unmapping/invalidating MRs
  ...

1 files changed, 42 insertions, 14 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4f59fa29eda8..0ea758b898fd 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -69,6 +69,7 @@
 
 /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
 static DEFINE_MUTEX(pcp_batch_high_lock);
+#define MIN_PERCPU_PAGELIST_FRACTION	(8)
 
 #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
 DEFINE_PER_CPU(int, numa_node);
@@ -815,9 +816,21 @@ void __init init_cma_reserved_pageblock(struct page *page)
 		set_page_count(p, 0);
 	} while (++p, --i);
 
-	set_page_refcounted(page);
 	set_pageblock_migratetype(page, MIGRATE_CMA);
-	__free_pages(page, pageblock_order);
+
+	if (pageblock_order >= MAX_ORDER) {
+		i = pageblock_nr_pages;
+		p = page;
+		do {
+			set_page_refcounted(p);
+			__free_pages(p, MAX_ORDER - 1);
+			p += MAX_ORDER_NR_PAGES;
+		} while (i -= MAX_ORDER_NR_PAGES);
+	} else {
+		set_page_refcounted(page);
+		__free_pages(page, pageblock_order);
+	}
+
 	adjust_managed_page_count(page, pageblock_nr_pages);
 }
 #endif
@@ -4145,7 +4158,7 @@ static void __meminit zone_init_free_lists(struct zone *zone)
 	memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY)
 #endif
 
-static int __meminit zone_batchsize(struct zone *zone)
+static int zone_batchsize(struct zone *zone)
 {
 #ifdef CONFIG_MMU
 	int batch;
@@ -4261,8 +4274,8 @@ static void pageset_set_high(struct per_cpu_pageset *p,
 	pageset_update(&p->pcp, high, batch);
 }
 
-static void __meminit pageset_set_high_and_batch(struct zone *zone,
-		struct per_cpu_pageset *pcp)
+static void pageset_set_high_and_batch(struct zone *zone,
+				       struct per_cpu_pageset *pcp)
 {
 	if (percpu_pagelist_fraction)
 		pageset_set_high(pcp,
@@ -5881,23 +5894,38 @@ int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *table, int write,
 	void __user *buffer, size_t *length, loff_t *ppos)
 {
 	struct zone *zone;
-	unsigned int cpu;
+	int old_percpu_pagelist_fraction;
 	int ret;
 
+	mutex_lock(&pcp_batch_high_lock);
+	old_percpu_pagelist_fraction = percpu_pagelist_fraction;
+
 	ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
-	if (!write || (ret < 0))
-		return ret;
+	if (!write || ret < 0)
+		goto out;
+
+	/* Sanity checking to avoid pcp imbalance */
+	if (percpu_pagelist_fraction &&
+	    percpu_pagelist_fraction < MIN_PERCPU_PAGELIST_FRACTION) {
+		percpu_pagelist_fraction = old_percpu_pagelist_fraction;
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* No change? */
+	if (percpu_pagelist_fraction == old_percpu_pagelist_fraction)
+		goto out;
 
-	mutex_lock(&pcp_batch_high_lock);
 	for_each_populated_zone(zone) {
-		unsigned long  high;
-		high = zone->managed_pages / percpu_pagelist_fraction;
+		unsigned int cpu;
+
 		for_each_possible_cpu(cpu)
-			pageset_set_high(per_cpu_ptr(zone->pageset, cpu),
-					 high);
+			pageset_set_high_and_batch(zone,
+					per_cpu_ptr(zone->pageset, cpu));
 	}
+out:
 	mutex_unlock(&pcp_batch_high_lock);
-	return 0;
+	return ret;
 }
 
 int hashdist = HASHDIST_DEFAULT;