The patch titled Subject: huge tmpfs: mem_cgroup shmem_pmdmapped accounting has been added to the -mm tree. Its filename is huge-tmpfs-mem_cgroup-shmem_pmdmapped-accounting.patch This patch should soon appear at http://ozlabs.org/~akpm/mmots/broken-out/huge-tmpfs-mem_cgroup-shmem_pmdmapped-accounting.patch and later at http://ozlabs.org/~akpm/mmotm/broken-out/huge-tmpfs-mem_cgroup-shmem_pmdmapped-accounting.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ From: Andres Lagar-Cavilla <andreslc@xxxxxxxxxx> Subject: huge tmpfs: mem_cgroup shmem_pmdmapped accounting Grep now for shmem_pmdmapped in memory.stat (and also for "total_..." in a hierarchical setting). This metric allows for easy checking on a per-cgroup basis of the amount of page team memory hugely mapped (at least once) out there. The metric is counted towards the cgroup owning the page (unlike in an event such as THP split) because the team page may be mapped hugely for the first time via a shared map in some other process. Moved up mem_group_move_account()'s PageWriteback block: that movement is irrelevant to this patch, but lets us concentrate better on the PageTeam locking issues which follow in the next patch. Signed-off-by: Andres Lagar-Cavilla <andreslc@xxxxxxxxxx> Signed-off-by: Hugh Dickins <hughd@xxxxxxxxxx> Cc: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx> Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx> Cc: Yang Shi <yang.shi@xxxxxxxxxx> Cc: Ning Qu <quning@xxxxxxxxx> Cc: David Rientjes <rientjes@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/memcontrol.h | 2 ++ include/linux/pageteam.h | 16 ++++++++++++++++ mm/huge_memory.c | 4 ++++ mm/memcontrol.c | 35 ++++++++++++++++++++++++++--------- 4 files changed, 48 insertions(+), 9 deletions(-) diff -puN include/linux/memcontrol.h~huge-tmpfs-mem_cgroup-shmem_pmdmapped-accounting include/linux/memcontrol.h --- a/include/linux/memcontrol.h~huge-tmpfs-mem_cgroup-shmem_pmdmapped-accounting +++ a/include/linux/memcontrol.h @@ -50,6 +50,8 @@ enum mem_cgroup_stat_index { MEM_CGROUP_STAT_DIRTY, /* # of dirty pages in page cache */ MEM_CGROUP_STAT_WRITEBACK, /* # of pages under writeback */ MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */ + /* # of pages charged as hugely mapped teams */ + MEM_CGROUP_STAT_SHMEM_PMDMAPPED, MEM_CGROUP_STAT_NSTATS, /* default hierarchy stats */ MEMCG_KERNEL_STACK = MEM_CGROUP_STAT_NSTATS, diff -puN include/linux/pageteam.h~huge-tmpfs-mem_cgroup-shmem_pmdmapped-accounting include/linux/pageteam.h --- a/include/linux/pageteam.h~huge-tmpfs-mem_cgroup-shmem_pmdmapped-accounting +++ a/include/linux/pageteam.h @@ -135,6 +135,22 @@ static inline bool dec_team_pmd_mapped(s } /* + * Supplies those values which mem_cgroup_move_account() + * needs to maintain memcg's huge tmpfs stats correctly. + */ +static inline void count_team_pmd_mapped(struct page *head, int *file_mapped, + bool *pmd_mapped) +{ + long team_usage; + + *file_mapped = 1; + team_usage = atomic_long_read(&head->team_usage); + *pmd_mapped = team_usage >= TEAM_PMD_MAPPED; + if (*pmd_mapped) + *file_mapped = HPAGE_PMD_NR - team_pte_count(team_usage); +} + +/* * Returns true if this pte mapping is of a non-team page, or of a team page not * covered by an existing huge pmd mapping: whereupon stats need to be updated. * Only called when mapcount goes up from 0 to 1 i.e. _mapcount from -1 to 0. diff -puN mm/huge_memory.c~huge-tmpfs-mem_cgroup-shmem_pmdmapped-accounting mm/huge_memory.c --- a/mm/huge_memory.c~huge-tmpfs-mem_cgroup-shmem_pmdmapped-accounting +++ a/mm/huge_memory.c @@ -3512,6 +3512,8 @@ static void page_add_team_rmap(struct pa __mod_zone_page_state(zone, NR_FILE_MAPPED, nr_pages); mem_cgroup_update_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED, nr_pages); + mem_cgroup_update_page_stat(page, + MEM_CGROUP_STAT_SHMEM_PMDMAPPED, HPAGE_PMD_NR); } unlock_page_memcg(page); } @@ -3531,6 +3533,8 @@ static void page_remove_team_rmap(struct __mod_zone_page_state(zone, NR_FILE_MAPPED, -nr_pages); mem_cgroup_update_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED, -nr_pages); + mem_cgroup_update_page_stat(page, + MEM_CGROUP_STAT_SHMEM_PMDMAPPED, -HPAGE_PMD_NR); } unlock_page_memcg(page); } diff -puN mm/memcontrol.c~huge-tmpfs-mem_cgroup-shmem_pmdmapped-accounting mm/memcontrol.c --- a/mm/memcontrol.c~huge-tmpfs-mem_cgroup-shmem_pmdmapped-accounting +++ a/mm/memcontrol.c @@ -37,6 +37,7 @@ #include <linux/mm.h> #include <linux/hugetlb.h> #include <linux/pagemap.h> +#include <linux/pageteam.h> #include <linux/smp.h> #include <linux/page-flags.h> #include <linux/backing-dev.h> @@ -106,6 +107,7 @@ static const char * const mem_cgroup_sta "dirty", "writeback", "swap", + "shmem_pmdmapped", }; static const char * const mem_cgroup_events_names[] = { @@ -4444,7 +4446,8 @@ static int mem_cgroup_move_account(struc struct mem_cgroup *to) { unsigned long flags; - unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; + int nr_pages = compound ? hpage_nr_pages(page) : 1; + int file_mapped = 1; int ret; bool anon; @@ -4468,10 +4471,10 @@ static int mem_cgroup_move_account(struc spin_lock_irqsave(&from->move_lock, flags); - if (!anon && page_mapped(page)) { - __this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED], + if (PageWriteback(page)) { + __this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_WRITEBACK], nr_pages); - __this_cpu_add(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED], + __this_cpu_add(to->stat->count[MEM_CGROUP_STAT_WRITEBACK], nr_pages); } @@ -4491,11 +4494,25 @@ static int mem_cgroup_move_account(struc } } - if (PageWriteback(page)) { - __this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_WRITEBACK], - nr_pages); - __this_cpu_add(to->stat->count[MEM_CGROUP_STAT_WRITEBACK], - nr_pages); + if (!anon && PageTeam(page)) { + if (page == team_head(page)) { + bool pmd_mapped; + + count_team_pmd_mapped(page, &file_mapped, &pmd_mapped); + if (pmd_mapped) { + __this_cpu_sub(from->stat->count[ + MEM_CGROUP_STAT_SHMEM_PMDMAPPED], HPAGE_PMD_NR); + __this_cpu_add(to->stat->count[ + MEM_CGROUP_STAT_SHMEM_PMDMAPPED], HPAGE_PMD_NR); + } + } + } + + if (!anon && page_mapped(page)) { + __this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED], + file_mapped); + __this_cpu_add(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED], + file_mapped); } /* _ Patches currently in -mm which might be from andreslc@xxxxxxxxxx are tmpfs-mem_cgroup-charge-fault-to-vm_mm-not-current-mm.patch kvm-plumb-return-of-hva-when-resolving-page-fault.patch kvm-teach-kvm-to-map-page-teams-as-huge-pages.patch huge-tmpfs-mem_cgroup-shmem_pmdmapped-accounting.patch huge-tmpfs-mem_cgroup-shmem_hugepages-accounting.patch huge-tmpfs-show-page-team-flag-in-pageflags.patch huge-tmpfs-no-kswapd-by-default-on-sync-allocations.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html