[PATCH] 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>
[chrisw: trivial backport]
Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c
index ec31534eb104875649847948c32f816c6951d5a8..6fd126a464f5c2f96048f5fac8a05a20e32fc376 100644 (file)
--- a/arch/x86_64/mm/init.c
+++ b/arch/x86_64/mm/init.c
@@ -776,3 +776,9 @@ 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 81c07cd18643a81aabc4b5b9968edea9102844e3..9543a5578652fdf7e42ca98cbc64b4c709e01bc8 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 ac26eb0d73cddeaf53b20fb7a7d31f954b8bc117..faa08e20e10ce24fafd177e23c59a855172616f1 100644 (file)
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -209,6 +209,12 @@ static int 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 *sparse_early_mem_map_alloc(unsigned long pnum)
 {
        struct page *map;
@@ -219,6 +225,11 @@ static struct page *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)