Re: [patch] fix hugepage unuseable issu on non-NUMA machine

[Yinghai Lu <yinghai@kernel.org>]

alex.shi wrote:
> 73d60b7f747176dbdff826c4127d22e1fd3f9f74 commit introduced a nodes_clear
> function for NUMA machine. But seems the commit omits non-NUMA machine.
> If find_zone_movable_pfns_for_nodes/early_calculate_totalpages has no
> chance to run. nodes_clear will block HUPEPAGE using in my specjbb2005
> testing. 
> 
> 
> So maybe we need to disable nodes_clear sometimes. With the following
> patch. specjbb2005 recovered. 

please check if following patch fixed your problem

[PATCH] x86: only clear node_states for 64bit

Nathan reported that
| commit 73d60b7f747176dbdff826c4127d22e1fd3f9f74
| Author: Yinghai Lu <yinghai@kernel.org>
| Date:   Tue Jun 16 15:33:00 2009 -0700
|
|    page-allocator: clear N_HIGH_MEMORY map before we set it again
|    
|    SRAT tables may contains nodes of very small size.  The arch code may
|    decide to not activate such a node.  However, currently the early boot
|    code sets N_HIGH_MEMORY for such nodes.  These nodes therefore seem to be
|    active although these nodes have no present pages.
|    
|    For 64bit N_HIGH_MEMORY == N_NORMAL_MEMORY, so that works for 64 bit too

broke the cpuset.mems cgroup attribute on an i386 kvm guest

fix it by only clearing node_states[N_NORMAL_MEMORY] for 64bit only.
and need to do save/restore for that in find_zone_movable_pfn

Reported-by: Nathan Lynch <ntl@pobox.com>
Tested-by: Nathan Lynch <ntl@pobox.com>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>

---
 arch/x86/mm/init_64.c |    2 ++
 mm/page_alloc.c       |   13 +++++++------
 2 files changed, 9 insertions(+), 6 deletions(-)

Index: linux-2.6/arch/x86/mm/init_64.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/init_64.c
+++ linux-2.6/arch/x86/mm/init_64.c
@@ -598,6 +598,8 @@ void __init paging_init(void)
 
 	sparse_memory_present_with_active_regions(MAX_NUMNODES);
 	sparse_init();
+	/* clear the default setting with node 0 */
+	nodes_clear(node_states[N_NORMAL_MEMORY]);
 	free_area_init_nodes(max_zone_pfns);
 }
 
Index: linux-2.6/mm/page_alloc.c
===================================================================
--- linux-2.6.orig/mm/page_alloc.c
+++ linux-2.6/mm/page_alloc.c
@@ -4037,6 +4037,8 @@ static void __init find_zone_movable_pfn
 	int i, nid;
 	unsigned long usable_startpfn;
 	unsigned long kernelcore_node, kernelcore_remaining;
+	/* save the state before borrow the nodemask */
+	nodemask_t saved_node_state = node_states[N_HIGH_MEMORY];
 	unsigned long totalpages = early_calculate_totalpages();
 	int usable_nodes = nodes_weight(node_states[N_HIGH_MEMORY]);
 
@@ -4064,7 +4066,7 @@ static void __init find_zone_movable_pfn
 
 	/* If kernelcore was not specified, there is no ZONE_MOVABLE */
 	if (!required_kernelcore)
-		return;
+		goto out;
 
 	/* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */
 	find_usable_zone_for_movable();
@@ -4163,6 +4165,10 @@ restart:
 	for (nid = 0; nid < MAX_NUMNODES; nid++)
 		zone_movable_pfn[nid] =
 			roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES);
+
+out:
+	/* restore the node_state */
+	node_states[N_HIGH_MEMORY] = saved_node_state;
 }
 
 /* Any regular memory on that node ? */
@@ -4247,11 +4253,6 @@ void __init free_area_init_nodes(unsigne
 						early_node_map[i].start_pfn,
 						early_node_map[i].end_pfn);
 
-	/*
-	 * find_zone_movable_pfns_for_nodes/early_calculate_totalpages init
-	 * that node_mask, clear it at first
-	 */
-	nodes_clear(node_states[N_HIGH_MEMORY]);
 	/* Initialise every node */
 	mminit_verify_pageflags_layout();
 	setup_nr_node_ids();