From: Zou Nan hai 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 Acked-by: Suresh Siddha Cc: Andi Kleen Cc: Signed-off-by: Andrew Morton --- arch/x86_64/mm/init.c | 6 ++++++ include/linux/bootmem.h | 1 + mm/sparse.c | 11 +++++++++++ 3 files changed, 18 insertions(+) diff -puN arch/x86_64/mm/init.c~x86_64-allocate-sparsemem-memmap-above-4g arch/x86_64/mm/init.c --- a/arch/x86_64/mm/init.c~x86_64-allocate-sparsemem-memmap-above-4g +++ a/arch/x86_64/mm/init.c @@ -770,3 +770,9 @@ const char *arch_vma_name(struct vm_area return "[vsyscall]"; return NULL; } + +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 -puN mm/sparse.c~x86_64-allocate-sparsemem-memmap-above-4g mm/sparse.c --- a/mm/sparse.c~x86_64-allocate-sparsemem-memmap-above-4g +++ a/mm/sparse.c @@ -209,6 +209,12 @@ static int __meminit sparse_init_one_sec 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_ 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) diff -puN include/linux/bootmem.h~x86_64-allocate-sparsemem-memmap-above-4g include/linux/bootmem.h --- a/include/linux/bootmem.h~x86_64-allocate-sparsemem-memmap-above-4g +++ a/include/linux/bootmem.h @@ -59,6 +59,7 @@ extern void *__alloc_bootmem_core(struct 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); _