mm: sparse: fix usemap allocation above node descriptor section

After commit f5bf18fa22f8 ("bootmem/sparsemem: remove limit constraint
in alloc_bootmem_section"), usemap allocations may easily be placed
outside the optimal section that holds the node descriptor, even if
there is space available in that section.  This results in unnecessary
hotplug dependencies that need to have the node unplugged before the
section holding the usemap.

The reason is that the bootmem allocator doesn't guarantee a linear
search starting from the passed allocation goal but may start out at a
much higher address absent an upper limit.

Fix this by trying the allocation with the limit at the section end,
then retry without if that fails.  This keeps the fix from f5bf18fa22f8
of not panicking if the allocation does not fit in the section, but
still makes sure to try to stay within the section at first.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: <stable@vger.kernel.org>	[3.3.x, 3.4.x]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 20 insertions, 7 deletions

diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index 324fe08ea3b1..6d6795d46a75 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -91,6 +91,11 @@ extern void *__alloc_bootmem_node_nopanic(pg_data_t *pgdat,
 				  unsigned long size,
 				  unsigned long align,
 				  unsigned long goal);
+void *___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
+				  unsigned long size,
+				  unsigned long align,
+				  unsigned long goal,
+				  unsigned long limit);
 extern void *__alloc_bootmem_low(unsigned long size,
 				 unsigned long align,
 				 unsigned long goal);
diff --git a/mm/bootmem.c b/mm/bootmem.c
index ec4fcb7a56c8..73096630cb35 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -698,7 +698,7 @@ void * __init __alloc_bootmem(unsigned long size, unsigned long align,
 	return ___alloc_bootmem(size, align, goal, limit);
 }
 
-static void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
+void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
 				unsigned long size, unsigned long align,
 				unsigned long goal, unsigned long limit)
 {
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index d23415c001bc..0900b3910cda 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -274,7 +274,7 @@ void * __init __alloc_bootmem(unsigned long size, unsigned long align,
 	return ___alloc_bootmem(size, align, goal, limit);
 }
 
-static void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
+void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
 						   unsigned long size,
 						   unsigned long align,
 						   unsigned long goal,
diff --git a/mm/sparse.c b/mm/sparse.c
index e861397016a9..c7bb952400c8 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -275,8 +275,9 @@ static unsigned long * __init
 sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
 					 unsigned long size)
 {
-	pg_data_t *host_pgdat;
-	unsigned long goal;
+	unsigned long goal, limit;
+	unsigned long *p;
+	int nid;
 	/*
 	 * A page may contain usemaps for other sections preventing the
 	 * page being freed and making a section unremovable while
@@ -288,9 +289,16 @@ sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
 	 * this problem.
 	 */
 	goal = __pa(pgdat) & (PAGE_SECTION_MASK << PAGE_SHIFT);
-	host_pgdat = NODE_DATA(early_pfn_to_nid(goal >> PAGE_SHIFT));
-	return __alloc_bootmem_node_nopanic(host_pgdat, size,
-					    SMP_CACHE_BYTES, goal);
+	limit = goal + (1UL << PA_SECTION_SHIFT);
+	nid = early_pfn_to_nid(goal >> PAGE_SHIFT);
+again:
+	p = ___alloc_bootmem_node_nopanic(NODE_DATA(nid), size,
+					  SMP_CACHE_BYTES, goal, limit);
+	if (!p && limit) {
+		limit = 0;
+		goto again;
+	}
+	return p;
 }
 
 static void __init check_usemap_section_nr(int nid, unsigned long *usemap)