[PATCH] x86_64: Handle empty PXMs that only contain hotplug memory
The node setup code would try to allocate the node metadata in the node
itself, but that fails if there is no memory in there.
This can happen with memory hotplug when the hotplug area defines an so
far empty node.
Now use bootmem to try to allocate the mem_map in other nodes.
And if it fails don't panic, but just ignore the node.
To make this work I added a new __alloc_bootmem_nopanic function that
does what its name implies.
TBD should try to use nearby nodes here. Currently we just use any.
It's hard to do it better because bootmem doesn't have proper fallback
lists yet.
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c
index 779132a..cc02573 100644
--- a/arch/x86_64/mm/numa.c
+++ b/arch/x86_64/mm/numa.c
@@ -100,11 +100,30 @@
}
#endif
+static void * __init
+early_node_mem(int nodeid, unsigned long start, unsigned long end,
+ unsigned long size)
+{
+ unsigned long mem = find_e820_area(start, end, size);
+ void *ptr;
+ if (mem != -1L)
+ return __va(mem);
+ ptr = __alloc_bootmem_nopanic(size,
+ SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS));
+ if (ptr == 0) {
+ printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
+ size, nodeid);
+ return NULL;
+ }
+ return ptr;
+}
+
/* Initialize bootmem allocator for a node */
void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
{
unsigned long start_pfn, end_pfn, bootmap_pages, bootmap_size, bootmap_start;
unsigned long nodedata_phys;
+ void *bootmap;
const int pgdat_size = round_up(sizeof(pg_data_t), PAGE_SIZE);
start = round_up(start, ZONE_ALIGN);
@@ -114,13 +133,11 @@
start_pfn = start >> PAGE_SHIFT;
end_pfn = end >> PAGE_SHIFT;
- nodedata_phys = find_e820_area(start, end, pgdat_size);
- if (nodedata_phys == -1L)
- panic("Cannot find memory pgdat in node %d\n", nodeid);
+ node_data[nodeid] = early_node_mem(nodeid, start, end, pgdat_size);
+ if (node_data[nodeid] == NULL)
+ return;
+ nodedata_phys = __pa(node_data[nodeid]);
- Dprintk("nodedata_phys %lx\n", nodedata_phys);
-
- node_data[nodeid] = phys_to_virt(nodedata_phys);
memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t));
NODE_DATA(nodeid)->bdata = &plat_node_bdata[nodeid];
NODE_DATA(nodeid)->node_start_pfn = start_pfn;
@@ -129,9 +146,15 @@
/* Find a place for the bootmem map */
bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
bootmap_start = round_up(nodedata_phys + pgdat_size, PAGE_SIZE);
- bootmap_start = find_e820_area(bootmap_start, end, bootmap_pages<<PAGE_SHIFT);
- if (bootmap_start == -1L)
- panic("Not enough continuous space for bootmap on node %d", nodeid);
+ bootmap = early_node_mem(nodeid, bootmap_start, end,
+ bootmap_pages<<PAGE_SHIFT);
+ if (bootmap == NULL) {
+ if (nodedata_phys < start || nodedata_phys >= end)
+ free_bootmem((unsigned long)node_data[nodeid],pgdat_size);
+ node_data[nodeid] = NULL;
+ return;
+ }
+ bootmap_start = __pa(bootmap);
Dprintk("bootmap start %lu pages %lu\n", bootmap_start, bootmap_pages);
bootmap_size = init_bootmem_node(NODE_DATA(nodeid),
diff --git a/arch/x86_64/mm/srat.c b/arch/x86_64/mm/srat.c
index 443875e..15ae9fc 100644
--- a/arch/x86_64/mm/srat.c
+++ b/arch/x86_64/mm/srat.c
@@ -415,6 +415,12 @@
/* Finally register nodes */
for_each_node_mask(i, nodes_parsed)
setup_node_bootmem(i, nodes[i].start, nodes[i].end);
+ /* Try again in case setup_node_bootmem missed one due
+ to missing bootmem */
+ for_each_node_mask(i, nodes_parsed)
+ if (!node_online(i))
+ setup_node_bootmem(i, nodes[i].start, nodes[i].end);
+
for (i = 0; i < NR_CPUS; i++) {
if (cpu_to_node[i] == NUMA_NO_NODE)
continue;
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index de3eb8d..da2d107 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -45,6 +45,7 @@
extern unsigned long __init init_bootmem (unsigned long addr, unsigned long memend);
extern void __init free_bootmem (unsigned long addr, unsigned long size);
extern void * __init __alloc_bootmem (unsigned long size, unsigned long align, unsigned long goal);
+extern void * __init __alloc_bootmem_nopanic (unsigned long size, unsigned long align, unsigned long goal);
extern void * __init __alloc_bootmem_low(unsigned long size,
unsigned long align,
unsigned long goal);
diff --git a/mm/bootmem.c b/mm/bootmem.c
index d3e3bd2..d213fed 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -401,7 +401,7 @@
return(free_all_bootmem_core(NODE_DATA(0)));
}
-void * __init __alloc_bootmem(unsigned long size, unsigned long align, unsigned long goal)
+void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align, unsigned long goal)
{
bootmem_data_t *bdata;
void *ptr;
@@ -409,7 +409,14 @@
list_for_each_entry(bdata, &bdata_list, list)
if ((ptr = __alloc_bootmem_core(bdata, size, align, goal, 0)))
return(ptr);
+ return NULL;
+}
+void * __init __alloc_bootmem(unsigned long size, unsigned long align, unsigned long goal)
+{
+ void *mem = __alloc_bootmem_nopanic(size,align,goal);
+ if (mem)
+ return mem;
/*
* Whoops, we cannot satisfy the allocation request.
*/