mm: fix boundary checking in free_bootmem_core

With numa enabled, some callers could have a range of memory on one node
but try to free that on other node.  This can cause some pages to be
freed wrongly.

For example: when we try to allocate 128g boot ram early for
gart/swiotlb, and free that range later so gart/swiotlb can get some
range afterwards.

With this patch, we don't need to care which node holds the range, just
loop to call free_bootmem_node for all online nodes.

This patch makes free_bootmem_core() more robust by trimming the sidx
and eidx according the ram range that the node has.

And make the free_bootmem_core handle this out of range case.  We could
use bdata_list to make sure the range can be freed for sure.  So next
time, we don't need to loop online nodes and could use free_bootmem
directly.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Cc: Andi Kleen <ak@suse.de>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Tested-by: Ingo Molnar <mingo@elte.hu>
Cc: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/bootmem.c b/mm/bootmem.c
index f6ff4337b4242e911ab4e4faadb160b76a445b50..2ccea700968f7ecaaa265023e79e52d540a82871 100644 (file)
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -125,6 +125,7 @@ static int __init reserve_bootmem_core(bootmem_data_t *bdata,
        BUG_ON(!size);
        BUG_ON(PFN_DOWN(addr) >= bdata->node_low_pfn);
        BUG_ON(PFN_UP(addr + size) > bdata->node_low_pfn);
+       BUG_ON(addr < bdata->node_boot_start);
 
        sidx = PFN_DOWN(addr - bdata->node_boot_start);
        eidx = PFN_UP(addr + size - bdata->node_boot_start);
@@ -156,21 +157,31 @@ static void __init free_bootmem_core(bootmem_data_t *bdata, unsigned long addr,
        unsigned long sidx, eidx;
        unsigned long i;
 
+       BUG_ON(!size);
+
+       /* out range */
+       if (addr + size < bdata->node_boot_start ||
+               PFN_DOWN(addr) > bdata->node_low_pfn)
+               return;
        /*
         * round down end of usable mem, partially free pages are
         * considered reserved.
         */
-       BUG_ON(!size);
-       BUG_ON(PFN_DOWN(addr + size) > bdata->node_low_pfn);
 
-       if (addr < bdata->last_success)
+       if (addr >= bdata->node_boot_start && addr < bdata->last_success)
                bdata->last_success = addr;
 
        /*
-        * Round up the beginning of the address.
+        * Round up to index to the range.
         */
-       sidx = PFN_UP(addr) - PFN_DOWN(bdata->node_boot_start);
+       if (PFN_UP(addr) > PFN_DOWN(bdata->node_boot_start))
+               sidx = PFN_UP(addr) - PFN_DOWN(bdata->node_boot_start);
+       else
+               sidx = 0;
+
        eidx = PFN_DOWN(addr + size - bdata->node_boot_start);
+       if (eidx > bdata->node_low_pfn - PFN_DOWN(bdata->node_boot_start))
+               eidx = bdata->node_low_pfn - PFN_DOWN(bdata->node_boot_start);
 
        for (i = sidx; i < eidx; i++) {
                if (unlikely(!test_and_clear_bit(i, bdata->node_bootmem_map)))
@@ -421,7 +432,9 @@ int __init reserve_bootmem(unsigned long addr, unsigned long size,
 
 void __init free_bootmem(unsigned long addr, unsigned long size)
 {
-       free_bootmem_core(NODE_DATA(0)->bdata, addr, size);
+       bootmem_data_t *bdata;
+       list_for_each_entry(bdata, &bdata_list, list)
+               free_bootmem_core(bdata, addr, size);
 }
 
 unsigned long __init free_all_bootmem(void)