[PATCH] x86_64: Try to allocate node memmap near the end of node

This fixes problems with very large nodes (over 128GB) filling up all of
the first 4GB with their mem_map and not leaving enough space for the
swiotlb.

Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 15 insertions, 2 deletions

diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c
index e4b62753a19a..07471a3eb190 100644
--- a/arch/x86_64/mm/numa.c
+++ b/arch/x86_64/mm/numa.c
@@ -149,7 +149,7 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long en
 /* Initialize final allocator for a zone */
 void __init setup_node_zones(int nodeid)
 { 
-        unsigned long start_pfn, end_pfn; 
+        unsigned long start_pfn, end_pfn, memmapsize, limit;
         unsigned long zones[MAX_NR_ZONES];
         unsigned long holes[MAX_NR_ZONES];
 
@@ -159,6 +159,16 @@ void __init setup_node_zones(int nodeid)
         Dprintk(KERN_INFO "Setting up node %d %lx-%lx\n",
                 nodeid, start_pfn, end_pfn);
 
+        /* Try to allocate mem_map at end to not fill up precious <4GB
+           memory. */
+        memmapsize = sizeof(struct page) * (end_pfn-start_pfn);
+        limit = end_pfn << PAGE_SHIFT;
+        NODE_DATA(nodeid)->node_mem_map = 
+                __alloc_bootmem_core(NODE_DATA(nodeid)->bdata, 
+                                memmapsize, SMP_CACHE_BYTES, 
+                                round_down(limit - memmapsize, PAGE_SIZE), 
+                                limit);
+
         size_zones(zones, holes, start_pfn, end_pfn);
         free_area_init_node(nodeid, NODE_DATA(nodeid), zones,
                             start_pfn, holes);
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index 993da8cc9706..7155452fb4a8 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -51,6 +51,9 @@ extern void * __init __alloc_bootmem_low_node(pg_data_t *pgdat,
                                               unsigned long size,
                                               unsigned long align,
                                               unsigned long goal);
+extern void * __init __alloc_bootmem_core(struct bootmem_data *bdata,
+                unsigned long size, unsigned long align, unsigned long goal,
+                unsigned long limit);
 #ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE
 extern void __init reserve_bootmem (unsigned long addr, unsigned long size);
 #define alloc_bootmem(x) \
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 35c32290f717..b55bd39fc5dd 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -152,7 +152,7 @@ static void __init free_bootmem_core(bootmem_data_t *bdata, unsigned long addr,
  *
  * NOTE:  This function is _not_ reentrant.
  */
-static void * __init
+void * __init
 __alloc_bootmem_core(struct bootmem_data *bdata, unsigned long size,
               unsigned long align, unsigned long goal, unsigned long limit)
 {