summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorNishanth Aravamudan <nacc@linux.vnet.ibm.com>2012-03-22 00:34:07 +0100
committerLinus Torvalds <torvalds@linux-foundation.org>2012-03-22 01:54:58 +0100
commitf5bf18fa22f8c41a13eb8762c7373eb3a93a7333 (patch)
tree3da24eb0edae3563c1937088b72a413e7026fdec
parentmm: drain percpu lru add/rotate page-vectors on cpu hot-unplug (diff)
downloadlinux-f5bf18fa22f8c41a13eb8762c7373eb3a93a7333.tar.xz
linux-f5bf18fa22f8c41a13eb8762c7373eb3a93a7333.zip
bootmem/sparsemem: remove limit constraint in alloc_bootmem_section
While testing AMS (Active Memory Sharing) / CMO (Cooperative Memory Overcommit) on powerpc, we tripped the following: kernel BUG at mm/bootmem.c:483! cpu 0x0: Vector: 700 (Program Check) at [c000000000c03940] pc: c000000000a62bd8: .alloc_bootmem_core+0x90/0x39c lr: c000000000a64bcc: .sparse_early_usemaps_alloc_node+0x84/0x29c sp: c000000000c03bc0 msr: 8000000000021032 current = 0xc000000000b0cce0 paca = 0xc000000001d80000 pid = 0, comm = swapper kernel BUG at mm/bootmem.c:483! enter ? for help [c000000000c03c80] c000000000a64bcc .sparse_early_usemaps_alloc_node+0x84/0x29c [c000000000c03d50] c000000000a64f10 .sparse_init+0x12c/0x28c [c000000000c03e20] c000000000a474f4 .setup_arch+0x20c/0x294 [c000000000c03ee0] c000000000a4079c .start_kernel+0xb4/0x460 [c000000000c03f90] c000000000009670 .start_here_common+0x1c/0x2c This is BUG_ON(limit && goal + size > limit); and after some debugging, it seems that goal = 0x7ffff000000 limit = 0x80000000000 and sparse_early_usemaps_alloc_node -> sparse_early_usemaps_alloc_pgdat_section calls return alloc_bootmem_section(usemap_size() * count, section_nr); This is on a system with 8TB available via the AMS pool, and as a quirk of AMS in firmware, all of that memory shows up in node 0. So, we end up with an allocation that will fail the goal/limit constraints. In theory, we could "fall-back" to alloc_bootmem_node() in sparse_early_usemaps_alloc_node(), but since we actually have HOTREMOVE defined, we'll BUG_ON() instead. A simple solution appears to be to unconditionally remove the limit condition in alloc_bootmem_section, meaning allocations are allowed to cross section boundaries (necessary for systems of this size). Johannes Weiner pointed out that if alloc_bootmem_section() no longer guarantees section-locality, we need check_usemap_section_nr() to print possible cross-dependencies between node descriptors and the usemaps allocated through it. That makes the two loops in sparse_early_usemaps_alloc_node() identical, so re-factor the code a bit. [akpm@linux-foundation.org: code simplification] Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: Anton Blanchard <anton@au1.ibm.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Ben Herrenschmidt <benh@kernel.crashing.org> Cc: Robert Jennings <rcj@linux.vnet.ibm.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: <stable@vger.kernel.org> [3.3.1] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--mm/bootmem.c5
-rw-r--r--mm/sparse.c30
2 files changed, 13 insertions, 22 deletions
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 668e94df8cf2..0131170c9d54 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -766,14 +766,13 @@ void * __init alloc_bootmem_section(unsigned long size,
unsigned long section_nr)
{
bootmem_data_t *bdata;
- unsigned long pfn, goal, limit;
+ unsigned long pfn, goal;
pfn = section_nr_to_pfn(section_nr);
goal = pfn << PAGE_SHIFT;
- limit = section_nr_to_pfn(section_nr + 1) << PAGE_SHIFT;
bdata = &bootmem_node_data[early_pfn_to_nid(pfn)];
- return alloc_bootmem_core(bdata, size, SMP_CACHE_BYTES, goal, limit);
+ return alloc_bootmem_core(bdata, size, SMP_CACHE_BYTES, goal, 0);
}
#endif
diff --git a/mm/sparse.c b/mm/sparse.c
index 61d7cde23111..a8bc7d364deb 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -353,29 +353,21 @@ static void __init sparse_early_usemaps_alloc_node(unsigned long**usemap_map,
usemap = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nodeid),
usemap_count);
- if (usemap) {
- for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
- if (!present_section_nr(pnum))
- continue;
- usemap_map[pnum] = usemap;
- usemap += size;
+ if (!usemap) {
+ usemap = alloc_bootmem_node(NODE_DATA(nodeid), size * usemap_count);
+ if (!usemap) {
+ printk(KERN_WARNING "%s: allocation failed\n", __func__);
+ return;
}
- return;
}
- usemap = alloc_bootmem_node(NODE_DATA(nodeid), size * usemap_count);
- if (usemap) {
- for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
- if (!present_section_nr(pnum))
- continue;
- usemap_map[pnum] = usemap;
- usemap += size;
- check_usemap_section_nr(nodeid, usemap_map[pnum]);
- }
- return;
+ for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+ if (!present_section_nr(pnum))
+ continue;
+ usemap_map[pnum] = usemap;
+ usemap += size;
+ check_usemap_section_nr(nodeid, usemap_map[pnum]);
}
-
- printk(KERN_WARNING "%s: allocation failed\n", __func__);
}
#ifndef CONFIG_SPARSEMEM_VMEMMAP