
Minchan Kim reported setting the following warning on a 32-bit system although it can affect 64-bit systems. WARNING: CPU: 4 PID: 1322 at mm/memcontrol.c:998 mem_cgroup_update_lru_size+0x103/0x110 mem_cgroup_update_lru_size(f44b4000, 1, -7): zid 1 lru_size 1 but empty Modules linked in: CPU: 4 PID: 1322 Comm: cp Not tainted 4.7.0-rc4-mm1+ #143 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: dump_stack+0x76/0xaf __warn+0xea/0x110 ? mem_cgroup_update_lru_size+0x103/0x110 warn_slowpath_fmt+0x3b/0x40 mem_cgroup_update_lru_size+0x103/0x110 isolate_lru_pages.isra.61+0x2e2/0x360 shrink_active_list+0xac/0x2a0 ? __delay+0xe/0x10 shrink_node_memcg+0x53c/0x7a0 shrink_node+0xab/0x2a0 do_try_to_free_pages+0xc6/0x390 try_to_free_pages+0x245/0x590 LRU list contents and counts are updated separately. Counts are updated before pages are added to the LRU and updated after pages are removed. The warning above is from a check in mem_cgroup_update_lru_size that ensures that list sizes of zero are empty. The problem is that node-lru needs to account for highmem pages if CONFIG_HIGHMEM is set. One impact of the implementation is that the sizes are updated in multiple passes when pages from multiple zones were isolated. This happens whether HIGHMEM is set or not. When multiple zones are isolated, it's possible for a debugging check in memcg to be tripped. This patch forces all the zone counts to be updated before the memcg function is called. Link: http://lkml.kernel.org/r/1468588165-12461-6-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Tested-by: Minchan Kim <minchan@kernel.org> Reported-by: Minchan Kim <minchan@kernel.org> Acked-by: Minchan Kim <minchan@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
138 lines
3.5 KiB
C
138 lines
3.5 KiB
C
#ifndef LINUX_MM_INLINE_H
|
|
#define LINUX_MM_INLINE_H
|
|
|
|
#include <linux/huge_mm.h>
|
|
#include <linux/swap.h>
|
|
|
|
#ifdef CONFIG_HIGHMEM
|
|
extern atomic_t highmem_file_pages;
|
|
|
|
static inline void acct_highmem_file_pages(int zid, enum lru_list lru,
|
|
int nr_pages)
|
|
{
|
|
if (is_highmem_idx(zid) && is_file_lru(lru))
|
|
atomic_add(nr_pages, &highmem_file_pages);
|
|
}
|
|
#else
|
|
static inline void acct_highmem_file_pages(int zid, enum lru_list lru,
|
|
int nr_pages)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
/**
|
|
* page_is_file_cache - should the page be on a file LRU or anon LRU?
|
|
* @page: the page to test
|
|
*
|
|
* Returns 1 if @page is page cache page backed by a regular filesystem,
|
|
* or 0 if @page is anonymous, tmpfs or otherwise ram or swap backed.
|
|
* Used by functions that manipulate the LRU lists, to sort a page
|
|
* onto the right LRU list.
|
|
*
|
|
* We would like to get this info without a page flag, but the state
|
|
* needs to survive until the page is last deleted from the LRU, which
|
|
* could be as far down as __page_cache_release.
|
|
*/
|
|
static inline int page_is_file_cache(struct page *page)
|
|
{
|
|
return !PageSwapBacked(page);
|
|
}
|
|
|
|
static __always_inline void __update_lru_size(struct lruvec *lruvec,
|
|
enum lru_list lru, enum zone_type zid,
|
|
int nr_pages)
|
|
{
|
|
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
|
|
|
|
__mod_node_page_state(pgdat, NR_LRU_BASE + lru, nr_pages);
|
|
acct_highmem_file_pages(zid, lru, nr_pages);
|
|
}
|
|
|
|
static __always_inline void update_lru_size(struct lruvec *lruvec,
|
|
enum lru_list lru, enum zone_type zid,
|
|
int nr_pages)
|
|
{
|
|
__update_lru_size(lruvec, lru, zid, nr_pages);
|
|
#ifdef CONFIG_MEMCG
|
|
mem_cgroup_update_lru_size(lruvec, lru, nr_pages);
|
|
#endif
|
|
}
|
|
|
|
static __always_inline void add_page_to_lru_list(struct page *page,
|
|
struct lruvec *lruvec, enum lru_list lru)
|
|
{
|
|
update_lru_size(lruvec, lru, page_zonenum(page), hpage_nr_pages(page));
|
|
list_add(&page->lru, &lruvec->lists[lru]);
|
|
}
|
|
|
|
static __always_inline void del_page_from_lru_list(struct page *page,
|
|
struct lruvec *lruvec, enum lru_list lru)
|
|
{
|
|
list_del(&page->lru);
|
|
update_lru_size(lruvec, lru, page_zonenum(page), -hpage_nr_pages(page));
|
|
}
|
|
|
|
/**
|
|
* page_lru_base_type - which LRU list type should a page be on?
|
|
* @page: the page to test
|
|
*
|
|
* Used for LRU list index arithmetic.
|
|
*
|
|
* Returns the base LRU type - file or anon - @page should be on.
|
|
*/
|
|
static inline enum lru_list page_lru_base_type(struct page *page)
|
|
{
|
|
if (page_is_file_cache(page))
|
|
return LRU_INACTIVE_FILE;
|
|
return LRU_INACTIVE_ANON;
|
|
}
|
|
|
|
/**
|
|
* page_off_lru - which LRU list was page on? clearing its lru flags.
|
|
* @page: the page to test
|
|
*
|
|
* Returns the LRU list a page was on, as an index into the array of LRU
|
|
* lists; and clears its Unevictable or Active flags, ready for freeing.
|
|
*/
|
|
static __always_inline enum lru_list page_off_lru(struct page *page)
|
|
{
|
|
enum lru_list lru;
|
|
|
|
if (PageUnevictable(page)) {
|
|
__ClearPageUnevictable(page);
|
|
lru = LRU_UNEVICTABLE;
|
|
} else {
|
|
lru = page_lru_base_type(page);
|
|
if (PageActive(page)) {
|
|
__ClearPageActive(page);
|
|
lru += LRU_ACTIVE;
|
|
}
|
|
}
|
|
return lru;
|
|
}
|
|
|
|
/**
|
|
* page_lru - which LRU list should a page be on?
|
|
* @page: the page to test
|
|
*
|
|
* Returns the LRU list a page should be on, as an index
|
|
* into the array of LRU lists.
|
|
*/
|
|
static __always_inline enum lru_list page_lru(struct page *page)
|
|
{
|
|
enum lru_list lru;
|
|
|
|
if (PageUnevictable(page))
|
|
lru = LRU_UNEVICTABLE;
|
|
else {
|
|
lru = page_lru_base_type(page);
|
|
if (PageActive(page))
|
|
lru += LRU_ACTIVE;
|
|
}
|
|
return lru;
|
|
}
|
|
|
|
#define lru_to_page(head) (list_entry((head)->prev, struct page, lru))
|
|
|
|
#endif
|