linux/mm/mmzone.c

117 lines
2.4 KiB
C
Raw Normal View History

/*
* linux/mm/mmzone.c
*
* management codes for pgdats, zones and page flags
*/
#include <linux/stddef.h>
[ARM] Double check memmap is actually valid with a memmap has unexpected holes V2 pfn_valid() is meant to be able to tell if a given PFN has valid memmap associated with it or not. In FLATMEM, it is expected that holes always have valid memmap as long as there is valid PFNs either side of the hole. In SPARSEMEM, it is assumed that a valid section has a memmap for the entire section. However, ARM and maybe other embedded architectures in the future free memmap backing holes to save memory on the assumption the memmap is never used. The page_zone linkages are then broken even though pfn_valid() returns true. A walker of the full memmap must then do this additional check to ensure the memmap they are looking at is sane by making sure the zone and PFN linkages are still valid. This is expensive, but walkers of the full memmap are extremely rare. This was caught before for FLATMEM and hacked around but it hits again for SPARSEMEM because the page_zone linkages can look ok where the PFN linkages are totally screwed. This looks like a hatchet job but the reality is that any clean solution would end up consumning all the memory saved by punching these unexpected holes in the memmap. For example, we tried marking the memmap within the section invalid but the section size exceeds the size of the hole in most cases so pfn_valid() starts returning false where valid memmap exists. Shrinking the size of the section would increase memory consumption offsetting the gains. This patch identifies when an architecture is punching unexpected holes in the memmap that the memory model cannot automatically detect and sets ARCH_HAS_HOLES_MEMORYMODEL. At the moment, this is restricted to EP93xx which is the model sub-architecture this has been reported on but may expand later. When set, walkers of the full memmap must call memmap_valid_within() for each PFN and passing in what it expects the page and zone to be for that PFN. If it finds the linkages to be broken, it assumes the memmap is invalid for that PFN. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2009-05-13 18:34:48 +02:00
#include <linux/mm.h>
#include <linux/mmzone.h>
struct pglist_data *first_online_pgdat(void)
{
return NODE_DATA(first_online_node);
}
struct pglist_data *next_online_pgdat(struct pglist_data *pgdat)
{
int nid = next_online_node(pgdat->node_id);
if (nid == MAX_NUMNODES)
return NULL;
return NODE_DATA(nid);
}
/*
* next_zone - helper magic for for_each_zone()
*/
struct zone *next_zone(struct zone *zone)
{
pg_data_t *pgdat = zone->zone_pgdat;
if (zone < pgdat->node_zones + MAX_NR_ZONES - 1)
zone++;
else {
pgdat = next_online_pgdat(pgdat);
if (pgdat)
zone = pgdat->node_zones;
else
zone = NULL;
}
return zone;
}
static inline int zref_in_nodemask(struct zoneref *zref, nodemask_t *nodes)
{
#ifdef CONFIG_NUMA
return node_isset(zonelist_node_idx(zref), *nodes);
#else
return 1;
#endif /* CONFIG_NUMA */
}
/* Returns the next zone at or below highest_zoneidx in a zonelist */
struct zoneref *next_zones_zonelist(struct zoneref *z,
enum zone_type highest_zoneidx,
nodemask_t *nodes,
struct zone **zone)
{
/*
* Find the next suitable zone to use for the allocation.
* Only filter based on nodemask if it's set
*/
if (likely(nodes == NULL))
while (zonelist_zone_idx(z) > highest_zoneidx)
z++;
else
while (zonelist_zone_idx(z) > highest_zoneidx ||
(z->zone && !zref_in_nodemask(z, nodes)))
z++;
*zone = zonelist_zone(z);
return z;
}
[ARM] Double check memmap is actually valid with a memmap has unexpected holes V2 pfn_valid() is meant to be able to tell if a given PFN has valid memmap associated with it or not. In FLATMEM, it is expected that holes always have valid memmap as long as there is valid PFNs either side of the hole. In SPARSEMEM, it is assumed that a valid section has a memmap for the entire section. However, ARM and maybe other embedded architectures in the future free memmap backing holes to save memory on the assumption the memmap is never used. The page_zone linkages are then broken even though pfn_valid() returns true. A walker of the full memmap must then do this additional check to ensure the memmap they are looking at is sane by making sure the zone and PFN linkages are still valid. This is expensive, but walkers of the full memmap are extremely rare. This was caught before for FLATMEM and hacked around but it hits again for SPARSEMEM because the page_zone linkages can look ok where the PFN linkages are totally screwed. This looks like a hatchet job but the reality is that any clean solution would end up consumning all the memory saved by punching these unexpected holes in the memmap. For example, we tried marking the memmap within the section invalid but the section size exceeds the size of the hole in most cases so pfn_valid() starts returning false where valid memmap exists. Shrinking the size of the section would increase memory consumption offsetting the gains. This patch identifies when an architecture is punching unexpected holes in the memmap that the memory model cannot automatically detect and sets ARCH_HAS_HOLES_MEMORYMODEL. At the moment, this is restricted to EP93xx which is the model sub-architecture this has been reported on but may expand later. When set, walkers of the full memmap must call memmap_valid_within() for each PFN and passing in what it expects the page and zone to be for that PFN. If it finds the linkages to be broken, it assumes the memmap is invalid for that PFN. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2009-05-13 18:34:48 +02:00
#ifdef CONFIG_ARCH_HAS_HOLES_MEMORYMODEL
int memmap_valid_within(unsigned long pfn,
struct page *page, struct zone *zone)
{
if (page_to_pfn(page) != pfn)
return 0;
if (page_zone(page) != zone)
return 0;
return 1;
}
#endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */
memcg: fix hotplugged memory zone oops When MEMCG is configured on (even when it's disabled by boot option), when adding or removing a page to/from its lru list, the zone pointer used for stats updates is nowadays taken from the struct lruvec. (On many configurations, calculating zone from page is slower.) But we have no code to update all the lruvecs (per zone, per memcg) when a memory node is hotadded. Here's an extract from the oops which results when running numactl to bind a program to a newly onlined node: BUG: unable to handle kernel NULL pointer dereference at 0000000000000f60 IP: __mod_zone_page_state+0x9/0x60 Pid: 1219, comm: numactl Not tainted 3.6.0-rc5+ #180 Bochs Bochs Process numactl (pid: 1219, threadinfo ffff880039abc000, task ffff8800383c4ce0) Call Trace: __pagevec_lru_add_fn+0xdf/0x140 pagevec_lru_move_fn+0xb1/0x100 __pagevec_lru_add+0x1c/0x30 lru_add_drain_cpu+0xa3/0x130 lru_add_drain+0x2f/0x40 ... The natural solution might be to use a memcg callback whenever memory is hotadded; but that solution has not been scoped out, and it happens that we do have an easy location at which to update lruvec->zone. The lruvec pointer is discovered either by mem_cgroup_zone_lruvec() or by mem_cgroup_page_lruvec(), and both of those do know the right zone. So check and set lruvec->zone in those; and remove the inadequate attempt to set lruvec->zone from lruvec_init(), which is called before NODE_DATA(node) has been allocated in such cases. Ah, there was one exceptionr. For no particularly good reason, mem_cgroup_force_empty_list() has its own code for deciding lruvec. Change it to use the standard mem_cgroup_zone_lruvec() and mem_cgroup_get_lru_size() too. In fact it was already safe against such an oops (the lru lists in danger could only be empty), but we're better proofed against future changes this way. I've marked this for stable (3.6) since we introduced the problem in 3.5 (now closed to stable); but I have no idea if this is the only fix needed to get memory hotadd working with memcg in 3.6, and received no answer when I enquired twice before. Reported-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-11-16 23:14:54 +01:00
void lruvec_init(struct lruvec *lruvec)
{
enum lru_list lru;
memset(lruvec, 0, sizeof(struct lruvec));
for_each_lru(lru)
INIT_LIST_HEAD(&lruvec->lists[lru]);
}
#if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_NID_NOT_IN_PAGE_FLAGS)
int page_nid_xchg_last(struct page *page, int nid)
{
unsigned long old_flags, flags;
int last_nid;
do {
old_flags = flags = page->flags;
last_nid = page_nid_last(page);
flags &= ~(LAST_NID_MASK << LAST_NID_PGSHIFT);
flags |= (nid & LAST_NID_MASK) << LAST_NID_PGSHIFT;
} while (unlikely(cmpxchg(&page->flags, old_flags, flags) != old_flags));
return last_nid;
}
#endif