All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH] fix bootmem allocator on machines with holes in memory
@ 2003-07-16 19:46 Anton Blanchard
  0 siblings, 0 replies; only message in thread
From: Anton Blanchard @ 2003-07-16 19:46 UTC (permalink / raw)
  To: torvalds; +Cc: akpm, linux-kernel


Hi,

If the memory we are trying to allocate is too large to fit in the
current region, we should skip to the end. We currently search the
available bitmap, find the area is too small, increment the start by
incr and try again. This resulted in an apparent lockup on a 64GB
machine that had a 3GB IO hole starting at 1GB (and the mem_map array
would not fit in the first region).

Also use ALIGN macro instead of an open coded version.

Anton

===== mm/bootmem.c 1.18 vs edited =====
--- 1.18/mm/bootmem.c	Sat Jul  5 16:52:55 2003
+++ edited/mm/bootmem.c	Thu Jul 17 05:00:42 2003
@@ -183,7 +183,7 @@
 	for (i = preferred; i < eidx; i += incr) {
 		unsigned long j;
 		i = find_next_zero_bit(bdata->node_bootmem_map, eidx, i);
-		i = (i + incr - 1) & -incr;
+		i = ALIGN(i, incr);
 		if (test_bit(i, bdata->node_bootmem_map))
 			continue;
 		for (j = i + 1; j < i + areasize; ++j) {
@@ -195,7 +195,7 @@
 		start = i;
 		goto found;
 	fail_block:
-		;
+		i = ALIGN(j, incr);
 	}
 
 	if (preferred > offset) {

^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2003-07-16 19:34 UTC | newest]

Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2003-07-16 19:46 [PATCH] fix bootmem allocator on machines with holes in memory Anton Blanchard

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.