[PATCH 02/49] x86,mm: fix 32bit numa sparsemem

[Yinghai Lu]

Borislav Petkov <borislav.petkov@xxxxxxx> reported his 32bit numa has problem:

[    0.000000] Reserving total of 4c00 pages for numa KVA remap
[    0.000000] kva_start_pfn ~ 32800 max_low_pfn ~ 375fe
[    0.000000] max_pfn = 238000
[    0.000000] 8202MB HIGHMEM available.
[    0.000000] 885MB LOWMEM available.
[    0.000000]   mapped low ram: 0 - 375fe000
[    0.000000]   low ram: 0 - 375fe000
[    0.000000] alloc (nid=8 100000 - 7ee00000) (1000000 - ffffffff) 1000 1000 => 34e7000
[    0.000000] alloc (nid=8 100000 - 7ee00000) (1000000 - ffffffff) 200 40 => 34c9d80
[    0.000000] alloc (nid=0 100000 - 7ee00000) (1000000 - ffffffffffffffff) 180 40 => 34e6140
[    0.000000] alloc (nid=1 80000000 - c7e60000) (1000000 - ffffffffffffffff) 240 40 => 80000000
[    0.000000] BUG: unable to handle kernel paging request at 40000000
[    0.000000] IP: [<c2c8cff1>] __alloc_memory_core_early+0x147/0x1d6
[    0.000000] *pdpt = 0000000000000000 *pde = f000ff53f000ff00
...
[    0.000000] Call Trace:
[    0.000000]  [<c2c8b4f8>] ? __alloc_bootmem_node+0x216/0x22f
[    0.000000]  [<c2c90c9b>] ? sparse_early_usemaps_alloc_node+0x5a/0x10b
[    0.000000]  [<c2c9149e>] ? sparse_init+0x1dc/0x499
[    0.000000]  [<c2c79118>] ? paging_init+0x168/0x1df
[    0.000000]  [<c2c780ff>] ? native_pagetable_setup_start+0xef/0x1bb

looks like it allocate much high address for bootmem.

try to cut limit with get_max_mapped()

-v3: make alloc_bootmem_node could fallback to other node.
     just like old alloc_bootmem_node did

need this patch for 2.6.34 and 2.6.35

Reported-by: Borislav Petkov <borislav.petkov@xxxxxxx>
Signed-off-by: Yinghai Lu <yinghai@xxxxxxxxxx>
Cc: stable@xxxxxxxxxx
---
 mm/bootmem.c    |   24 ++++++++++++++++++++----
 mm/page_alloc.c |    3 +++
 2 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/mm/bootmem.c b/mm/bootmem.c
index 58c66cc..142c84a 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -833,15 +833,24 @@ static void * __init ___alloc_bootmem_node(bootmem_data_t *bdata,
 void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 				   unsigned long align, unsigned long goal)
 {
+	void *ptr;
+
 	if (WARN_ON_ONCE(slab_is_available()))
 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 
 #ifdef CONFIG_NO_BOOTMEM
-	return __alloc_memory_core_early(pgdat->node_id, size, align,
+	ptr = __alloc_memory_core_early(pgdat->node_id, size, align,
+					 goal, -1ULL);
+	if (ptr)
+		return ptr;
+
+	ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align,
 					 goal, -1ULL);
 #else
-	return ___alloc_bootmem_node(pgdat->bdata, size, align, goal, 0);
+	ptr = ___alloc_bootmem_node(pgdat->bdata, size, align, goal, 0);
 #endif
+
+	return ptr;
 }
 
 void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
@@ -977,14 +986,21 @@ void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
 void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
 				       unsigned long align, unsigned long goal)
 {
+	void *ptr;
+
 	if (WARN_ON_ONCE(slab_is_available()))
 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 
 #ifdef CONFIG_NO_BOOTMEM
-	return __alloc_memory_core_early(pgdat->node_id, size, align,
+	ptr = __alloc_memory_core_early(pgdat->node_id, size, align,
+				goal, ARCH_LOW_ADDRESS_LIMIT);
+	if (ptr)
+		return ptr;
+	ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align,
 				goal, ARCH_LOW_ADDRESS_LIMIT);
 #else
-	return ___alloc_bootmem_node(pgdat->bdata, size, align,
+	ptr = ___alloc_bootmem_node(pgdat->bdata, size, align,
 				goal, ARCH_LOW_ADDRESS_LIMIT);
 #endif
+	return ptr;
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 68319dd..9bd339e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3634,6 +3634,9 @@ void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
 	int i;
 	void *ptr;
 
+	if (limit > get_max_mapped())
+		limit = get_max_mapped();
+
 	/* need to go over early_node_map to find out good range for node */
 	for_each_active_range_index_in_nid(i, nid) {
 		u64 addr;
-- 
1.6.4.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/