The patch titled
ia64: remove empty nodes at boot time
has been removed from the -mm tree. Its filename is
remove-empty-node-at-boot-time.patch
This patch was dropped because it had testing failures
------------------------------------------------------
Subject: ia64: remove empty nodes at boot time
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Remove empty nodes -- a node which containes no cpu, no memory (and no
I/O). for ia64.
This patch online nodes which has available resouces and avoid onlining
nodes which has only possible resouces.
SRAT describes possible resources, cpu and memory. It also shows proximity
domain, pxm. Each numa node is created according to pxm.
Current ia64 SRAT parser onlining node when new pxm is found. But
sometimes pxm just includes 'possible' resources, doesn't includes
available resources. Such pxms will create an empty node.
When an empty node is onlined, it allocates a pgdat for an empty node.
Now, fundamental codes for node-hot-plug are ready in -mm. We can add cpu
and memory dynamically to the created new node. (memory-less-node hotplug
is not ready. But I don't know whether there are demands for it now.)
Then, we can remove empty nodes, which just includes possible resource.
And, I'm now considering allocating new pgdat on-node. Empty nodes are
obstacles to do that.
TBD: I/O only node detections scheme should be fixed (if necessary).
Does anyone have a suggestion ?
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: "Luck, Tony" <tony.luck@xxxxxxxxx>
Cc: "Brown, Len" <len.brown@xxxxxxxxx>
Cc: "Yu, Luming" <luming.yu@xxxxxxxxx>
Cc: Bjorn Helgaas <bjorn.helgaas@xxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxx>
---
arch/ia64/kernel/acpi.c | 60 ++++++++++++++++++++++++++++++-------
arch/ia64/kernel/setup.c | 2 -
arch/ia64/mm/contig.c | 2 -
arch/ia64/mm/discontig.c | 2 -
4 files changed, 51 insertions(+), 15 deletions(-)
diff -puN arch/ia64/kernel/acpi.c~remove-empty-node-at-boot-time arch/ia64/kernel/acpi.c
--- a/arch/ia64/kernel/acpi.c~remove-empty-node-at-boot-time
+++ a/arch/ia64/kernel/acpi.c
@@ -514,6 +514,43 @@ acpi_numa_memory_affinity_init(struct ac
num_node_memblks++;
}
+/* online node if node has valid memory */
+static
+int find_valid_memory_range(unsigned long start, unsigned long end, void *arg)
+{
+ int i;
+ struct node_memblk_s *p;
+ start = __pa(start);
+ end = __pa(end);
+ for (i = 0; i < num_node_memblks; ++i) {
+ p = &node_memblk[i];
+ if (end < p->start_paddr)
+ continue;
+ if (p->start_paddr + p->size <= start)
+ continue;
+ node_set_online(p->nid);
+ }
+ return 0;
+}
+
+static void
+acpi_online_node_fixup(void)
+{
+ int i, cpu;
+ /* online node if a node has available cpus */
+ for (i = 0; i < srat_num_cpus; ++i)
+ for (cpu = 0; cpu < available_cpus; ++cpu)
+ if (smp_boot_data.cpu_phys_id[cpu] ==
+ node_cpuid[i].phys_id) {
+ node_set_online(node_cpuid[i].nid);
+ break;
+ }
+ /* memory */
+ efi_memmap_walk(find_valid_memory_range, NULL);
+
+ /* TBD: check I/O devices which have valid nid. and online it*/
+}
+
void __init acpi_numa_arch_fixup(void)
{
int i, j, node_from, node_to;
@@ -525,22 +562,28 @@ void __init acpi_numa_arch_fixup(void)
return;
}
- /*
- * MCD - This can probably be dropped now. No need for pxm ID to node ID
- * mapping with sparse node numbering iff MAX_PXM_DOMAINS <= MAX_NUMNODES.
- */
nodes_clear(node_online_map);
+ /* MAP pxm to nid */
for (i = 0; i < MAX_PXM_DOMAINS; i++) {
if (pxm_bit_test(i)) {
- int nid = acpi_map_pxm_to_node(i);
- node_set_online(nid);
+ /* this makes pxm <-> nid mapping */
+ acpi_map_pxm_to_node(i);
}
}
+ /* convert pxm information to nid information */
- /* set logical node id in memory chunk structure */
for (i = 0; i < num_node_memblks; i++)
node_memblk[i].nid = pxm_to_node(node_memblk[i].nid);
+ for (i = 0; i < srat_num_cpus; i++)
+ node_cpuid[i].nid = pxm_to_node(node_cpuid[i].nid);
+
+ /*
+ * confirm node is online or not.
+ * onlined node will have their own NODE_DATA
+ */
+ acpi_online_node_fixup();
+
/* assign memory bank numbers for each chunk on each node */
for_each_online_node(i) {
int bank;
@@ -551,9 +594,6 @@ void __init acpi_numa_arch_fixup(void)
node_memblk[j].bank = bank++;
}
- /* set logical node id in cpu structure */
- for (i = 0; i < srat_num_cpus; i++)
- node_cpuid[i].nid = pxm_to_node(node_cpuid[i].nid);
printk(KERN_INFO "Number of logical nodes in system = %d\n",
num_online_nodes());
diff -puN arch/ia64/kernel/setup.c~remove-empty-node-at-boot-time arch/ia64/kernel/setup.c
--- a/arch/ia64/kernel/setup.c~remove-empty-node-at-boot-time
+++ a/arch/ia64/kernel/setup.c
@@ -418,7 +418,7 @@ setup_arch (char **cmdline_p)
if (early_console_setup(*cmdline_p) == 0)
mark_bsp_online();
-
+ reserve_memory();
#ifdef CONFIG_ACPI
/* Initialize the ACPI boot-time table parser */
acpi_table_init();
diff -puN arch/ia64/mm/contig.c~remove-empty-node-at-boot-time arch/ia64/mm/contig.c
--- a/arch/ia64/mm/contig.c~remove-empty-node-at-boot-time
+++ a/arch/ia64/mm/contig.c
@@ -145,8 +145,6 @@ find_memory (void)
{
unsigned long bootmap_size;
- reserve_memory();
-
/* first find highest page frame number */
max_pfn = 0;
efi_memmap_walk(find_max_pfn, &max_pfn);
diff -puN arch/ia64/mm/discontig.c~remove-empty-node-at-boot-time arch/ia64/mm/discontig.c
--- a/arch/ia64/mm/discontig.c~remove-empty-node-at-boot-time
+++ a/arch/ia64/mm/discontig.c
@@ -453,8 +453,6 @@ void __init find_memory(void)
{
int node;
- reserve_memory();
-
if (num_online_nodes() == 0) {
printk(KERN_ERR "node info missing!\n");
node_set_online(0);
_
Patches currently in -mm which might be from kamezawa.hiroyu@xxxxxxxxxxxxxx are
remove-empty-node-at-boot-time.patch
namespaces-utsname-sysctl-hack.patch
reiser4-hardirq-include-fix.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
