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

unintentionally and incorrectly clears the cpuset.mems cgroup attribute on
an i386 kvm guest, meaning that cpuset.mems can not be used.

Fix this 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>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@elte.hu>,
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index c4378f4fd4a5e240125cfa60d2f1430a0bb35145..b177652251a43312c49be5dff4801351be8cff55 100644 (file)
--- a/arch/x86/mm/init_64.c
+++ b/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);
 }
 

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5d714f8fb30333f6de336e555f944658bfa1dc16..e0f2cdf9d8b1f2a351e409a1699cd3e06dcdc200 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4032,6 +4032,8 @@ static void __init find_zone_movable_pfns_for_nodes(unsigned long *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]);
 
@@ -4059,7 +4061,7 @@ static void __init find_zone_movable_pfns_for_nodes(unsigned long *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();
@@ -4158,6 +4160,10 @@ 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 ? */
@@ -4242,11 +4248,6 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
                                                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();