We need to have numa info ready before init_mem_mapping, so we
can call init_mem_mapping per nodes also can trim node mem range to
big alignment.
Current numa parsing need to allocate some buffer and need to be
called after init_mem_mapping.
So try to split parsing numa info to two stages, and early one will be
before init_mem_mapping, and it should not need allocate buffers.
At last we will have early_initmem_init() and initmem_init().
This one is first one for separation.
setup_node_data() and numa_init_array() are only called for successful
path, so we can move calling to x86_numa_init(). That will also make
numa_init() small and readable.
-v2: remove online_node_map clear in numa_init(), as it is only
set in setup_node_data() at last in successful path.
Signed-off-by: Yinghai Lu <ying...@kernel.org>
---
arch/x86/mm/numa.c | 69 +++++++++++++++++++++++++++++-----------------------
1 file changed, 39 insertions(+), 30 deletions(-)
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 72fe01e..d545638 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -480,7 +480,7 @@ static bool __init numa_meminfo_cover_memory(const struct
numa_meminfo *mi)
static int __init numa_register_memblks(struct numa_meminfo *mi)
{
unsigned long uninitialized_var(pfn_align);
- int i, nid;
+ int i;
/* Account for nodes with cpus and no memory */
node_possible_map = numa_nodes_parsed;
@@ -509,24 +509,6 @@ static int __init numa_register_memblks(struct
numa_meminfo *mi)
if (!numa_meminfo_cover_memory(mi))
return -EINVAL;
- /* Finally register nodes. */
- for_each_node_mask(nid, node_possible_map) {
- u64 start = PFN_PHYS(max_pfn);
- u64 end = 0;
-
- for (i = 0; i < mi->nr_blks; i++) {
- if (nid != mi->blk[i].nid)
- continue;
- start = min(mi->blk[i].start, start);
- end = max(mi->blk[i].end, end);
- }
-
- if (start < end)
- setup_node_data(nid, start, end);
- }
-
- /* Dump memblock with node info and return. */
- memblock_dump_all();
return 0;
}
@@ -562,7 +544,6 @@ static int __init numa_init(int (*init_func)(void))
nodes_clear(numa_nodes_parsed);
nodes_clear(node_possible_map);
- nodes_clear(node_online_map);
memset(&numa_meminfo, 0, sizeof(numa_meminfo));
WARN_ON(memblock_set_node(0, ULLONG_MAX, MAX_NUMNODES));
numa_reset_distance();
@@ -580,15 +561,6 @@ static int __init numa_init(int (*init_func)(void))
if (ret < 0)
return ret;
- for (i = 0; i < nr_cpu_ids; i++) {
- int nid = early_cpu_to_node(i);
-
- if (nid == NUMA_NO_NODE)
- continue;
- if (!node_online(nid))
- numa_clear_node(i);
- }
- numa_init_array();
return 0;
}
@@ -621,7 +593,7 @@ static int __init dummy_numa_init(void)
* last fallback is dummy single node config encomapssing whole memory and
* never fails.
*/
-void __init x86_numa_init(void)
+static void __init early_x86_numa_init(void)
{
if (!numa_off) {
#ifdef CONFIG_X86_NUMAQ
@@ -641,6 +613,43 @@ void __init x86_numa_init(void)
numa_init(dummy_numa_init);
}
+void __init x86_numa_init(void)
+{
+ int i, nid;
+ struct numa_meminfo *mi = &numa_meminfo;
+
+ early_x86_numa_init();
+
+ /* Finally register nodes. */
+ for_each_node_mask(nid, node_possible_map) {
+ u64 start = PFN_PHYS(max_pfn);
+ u64 end = 0;
+
+ for (i = 0; i < mi->nr_blks; i++) {
+ if (nid != mi->blk[i].nid)
+ continue;
+ start = min(mi->blk[i].start, start);
+ end = max(mi->blk[i].end, end);
+ }
+
+ if (start < end)
+ setup_node_data(nid, start, end); /* online is set */
+ }
+
+ /* Dump memblock with node info */
+ memblock_dump_all();
+
+ for (i = 0; i < nr_cpu_ids; i++) {
+ int nid = early_cpu_to_node(i);
+
+ if (nid == NUMA_NO_NODE)
+ continue;
+ if (!node_online(nid))
+ numa_clear_node(i);
+ }
+ numa_init_array();
+}
+
static __init int find_near_online_node(int node)
{
int n, val;
--
1.7.10.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
