lkml.org 
[lkml]   [2009]   [May]   [14]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    Patch in this message
    /
    Date
    From
    Subject[PATCH 3/5] x86: fix node_possible_map logic -v2

    recently there are some changes to about meaning of node_possible_map

    and it is some strange:
    the node without memory would be set in node_possible_map
    but some node with less NODE_MIN_SIZE will be kicked out of node_possible_map.

    try to fix it by adding strict_setup_node_bootmem.
    also remove unparse_node.

    so result will be:
    1. cpu_to_node will return online node only (nearest one)
    2. apicid_to_node still return the node that could be not online but is set
    in node_possible_map.
    3. node_possible_map will include nodes that mem on it are less NODE_MIN_SIZE

    v2: after move_cpus_to_node change.

    [ Impact: get node_possible_map right ]

    Signed-off-by: Yinghai Lu <yinghai@kernel.org>
    Tested-by: Jack Steiner <steiner@sgi.com>

    ---
    arch/x86/include/asm/numa_64.h | 4 ++++
    arch/x86/mm/numa_64.c | 7 +++++++
    arch/x86/mm/srat_64.c | 29 ++---------------------------
    3 files changed, 13 insertions(+), 27 deletions(-)

    Index: linux-2.6/arch/x86/mm/srat_64.c
    ===================================================================
    --- linux-2.6.orig/arch/x86/mm/srat_64.c
    +++ linux-2.6/arch/x86/mm/srat_64.c
    @@ -36,10 +36,6 @@ static int num_node_memblks __initdata;
    static struct bootnode node_memblk_range[NR_NODE_MEMBLKS] __initdata;
    static int memblk_nodeid[NR_NODE_MEMBLKS] __initdata;

    -/* Too small nodes confuse the VM badly. Usually they result
    - from BIOS bugs. */
    -#define NODE_MIN_SIZE (4*1024*1024)
    -
    static __init int setup_node(int pxm)
    {
    return acpi_map_pxm_to_node(pxm);
    @@ -338,17 +334,6 @@ static int __init nodes_cover_memory(con
    return 1;
    }

    -static void __init unparse_node(int node)
    -{
    - int i;
    - node_clear(node, nodes_parsed);
    - node_clear(node, cpu_nodes_parsed);
    - for (i = 0; i < MAX_LOCAL_APIC; i++) {
    - if (apicid_to_node[i] == node)
    - apicid_to_node[i] = NUMA_NO_NODE;
    - }
    -}
    -
    void __init acpi_numa_arch_fixup(void) {}

    /* Use the information discovered above to actually set up the nodes. */
    @@ -360,18 +345,8 @@ int __init acpi_scan_nodes(unsigned long
    return -1;

    /* First clean up the node list */
    - for (i = 0; i < MAX_NUMNODES; i++) {
    + for (i = 0; i < MAX_NUMNODES; i++)
    cutoff_node(i, start, end);
    - /*
    - * don't confuse VM with a node that doesn't have the
    - * minimum memory.
    - */
    - if (nodes[i].end &&
    - (nodes[i].end - nodes[i].start) < NODE_MIN_SIZE) {
    - unparse_node(i);
    - node_set_offline(i);
    - }
    - }

    if (!nodes_cover_memory(nodes)) {
    bad_srat();
    @@ -404,7 +379,7 @@ int __init acpi_scan_nodes(unsigned long

    if (node == NUMA_NO_NODE)
    continue;
    - if (!node_isset(node, node_possible_map))
    + if (!node_online(node))
    numa_clear_node(i);
    }
    numa_init_array();
    Index: linux-2.6/arch/x86/mm/numa_64.c
    ===================================================================
    --- linux-2.6.orig/arch/x86/mm/numa_64.c
    +++ linux-2.6/arch/x86/mm/numa_64.c
    @@ -192,6 +192,13 @@ void __init setup_node_bootmem(int nodei
    if (!end)
    return;

    + /*
    + * don't confuse VM with a node that doesn't have the
    + * minimum memory.
    + */
    + if (end && (end - start) < NODE_MIN_SIZE)
    + return;
    +
    start = roundup(start, ZONE_ALIGN);

    printk(KERN_INFO "Bootmem setup node %d %016lx-%016lx\n", nodeid,
    Index: linux-2.6/arch/x86/include/asm/numa_64.h
    ===================================================================
    --- linux-2.6.orig/arch/x86/include/asm/numa_64.h
    +++ linux-2.6/arch/x86/include/asm/numa_64.h
    @@ -24,6 +24,10 @@ extern void setup_node_bootmem(int nodei
    unsigned long end);

    #ifdef CONFIG_NUMA
    +/* Too small nodes confuse the VM badly. Usually they result
    + from BIOS bugs. */
    +#define NODE_MIN_SIZE (4*1024*1024)
    +
    extern void __init init_cpu_to_node(void);
    extern void numa_set_node(int cpu, int node);
    extern void numa_clear_node(int cpu);

    \
     
     \ /
      Last update: 2009-05-14 18:45    [W:2.528 / U:0.060 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site