x86_64: allocate sparsemem memmap above 4G

On systems with huge amount of physical memory, VFS cache and memory memmap
may eat all available system memory under 4G, then the system may fail to
allocate swiotlb bounce buffer.

There was a fix for this issue in arch/x86_64/mm/numa.c, but that fix dose
not cover sparsemem model.

This patch add fix to sparsemem model by first try to allocate memmap above
4G.

Signed-off-by: Zou Nan hai <nanhai.zou@intel.com>
Acked-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Andi Kleen <ak@suse.de>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c
index 1336da8bdee125f5b0ba227360d89c4709264323..1ad5111aec381d7042648c0a871f2707181f3400 100644 (file)
--- a/arch/x86_64/mm/init.c
+++ b/arch/x86_64/mm/init.c
@@ -761,3 +761,9 @@ int in_gate_area_no_task(unsigned long addr)
 {
        return (addr >= VSYSCALL_START) && (addr < VSYSCALL_END);
 }
+
+void *alloc_bootmem_high_node(pg_data_t *pgdat, unsigned long size)
+{
+       return __alloc_bootmem_core(pgdat->bdata, size,
+                       SMP_CACHE_BYTES, (4UL*1024*1024*1024), 0);
+}

diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index 0365ec9fc0c9248422801fe71b232d1188a12972..c83534ee1e796c46b2cc47c129ad3924cedbeb20 100644 (file)
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -59,6 +59,7 @@ extern void *__alloc_bootmem_core(struct bootmem_data *bdata,
                                  unsigned long align,
                                  unsigned long goal,
                                  unsigned long limit);
+extern void *alloc_bootmem_high_node(pg_data_t *pgdat, unsigned long size);
 
 #ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE
 extern void reserve_bootmem(unsigned long addr, unsigned long size);

diff --git a/mm/sparse.c b/mm/sparse.c
index 1302f8348d51c8dbc10d104c333eeea3e01a6f1a..545e4d3afcdff14877204b270bf6e671c33d5509 100644 (file)
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -209,6 +209,12 @@ static int __meminit sparse_init_one_section(struct mem_section *ms,
        return 1;
 }
 
+__attribute__((weak))
+void *alloc_bootmem_high_node(pg_data_t *pgdat, unsigned long size)
+{
+       return NULL;
+}
+
 static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
 {
        struct page *map;
@@ -219,6 +225,11 @@ static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
        if (map)
                return map;
 
+       map = alloc_bootmem_high_node(NODE_DATA(nid),
+                       sizeof(struct page) * PAGES_PER_SECTION);
+       if (map)
+               return map;
+
        map = alloc_bootmem_node(NODE_DATA(nid),
                        sizeof(struct page) * PAGES_PER_SECTION);
        if (map)