memblock: free allocated memblock_reserved_regions later

memblock_free_reserved_regions() calls memblock_free(), but
memblock_free() would double reserved.regions too, so we could free the
old range for reserved.regions.

Also tj said there is another bug which could be related to this.

| I don't think we're saving any noticeable
| amount by doing this "free - give it to page allocator - reserve
| again" dancing.  We should just allocate regions aligned to page
| boundaries and free them later when memblock is no longer in use.

in that case, when DEBUG_PAGEALLOC, will get panic:

     memblock_free: [0x0000102febc080-0x0000102febf080] memblock_free_reserved_regions+0x37/0x39
  BUG: unable to handle kernel paging request at ffff88102febd948
  IP: [<ffffffff836a5774>] __next_free_mem_range+0x9b/0x155
  PGD 4826063 PUD cf67a067 PMD cf7fa067 PTE 800000102febd160
  Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
  CPU 0
  Pid: 0, comm: swapper Not tainted 3.5.0-rc2-next-20120614-sasha #447
  RIP: 0010:[<ffffffff836a5774>]  [<ffffffff836a5774>] __next_free_mem_range+0x9b/0x155

See the discussion at https://lkml.org/lkml/2012/6/13/469

So try to allocate with PAGE_SIZE alignment and free it later.

Reported-by: Sasha Levin <levinsasha928@gmail.com>
Acked-by: Tejun Heo <tj@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 23 insertions, 15 deletions

diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index 0900b3910cda..405573010f99 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -105,27 +105,35 @@ static void __init __free_pages_memory(unsigned long start, unsigned long end)
                 __free_pages_bootmem(pfn_to_page(i), 0);
 }
 
+static unsigned long __init __free_memory_core(phys_addr_t start,
+                                 phys_addr_t end)
+{
+        unsigned long start_pfn = PFN_UP(start);
+        unsigned long end_pfn = min_t(unsigned long,
+                                      PFN_DOWN(end), max_low_pfn);
+
+        if (start_pfn > end_pfn)
+                return 0;
+
+        __free_pages_memory(start_pfn, end_pfn);
+
+        return end_pfn - start_pfn;
+}
+
 unsigned long __init free_low_memory_core_early(int nodeid)
 {
         unsigned long count = 0;
-        phys_addr_t start, end;
+        phys_addr_t start, end, size;
         u64 i;
 
-        /* free reserved array temporarily so that it's treated as free area */
-        memblock_free_reserved_regions();
-
-        for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) {
-                unsigned long start_pfn = PFN_UP(start);
-                unsigned long end_pfn = min_t(unsigned long,
-                                              PFN_DOWN(end), max_low_pfn);
-                if (start_pfn < end_pfn) {
-                        __free_pages_memory(start_pfn, end_pfn);
-                        count += end_pfn - start_pfn;
-                }
-        }
+        for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL)
+                count += __free_memory_core(start, end);
+
+        /* free range that is used for reserved array if we allocate it */
+        size = get_allocated_memblock_reserved_regions_info(&start);
+        if (size)
+                count += __free_memory_core(start, start + size);
 
-        /* put region array back? */
-        memblock_reserve_reserved_regions();
         return count;
 }