On Wed 05-08-15 15:01:24, Vlastimil Babka wrote:
> From: Jerome Marchand <jmarc...@redhat.com>
>
> Currently looking at /proc/<pid>/status or statm, there is no way to
> distinguish shmem pages from pages mapped to a regular file (shmem
> pages are mapped to /dev/zero), even though their implication in
> actual memory use is quite different.
> This patch adds MM_SHMEMPAGES counter to mm_rss_stat to account for
> shmem pages instead of MM_FILEPAGES.
Conflating SHMEM and FILEPAGES was imho unfortunate. Some of that is
even unfortunate and people had to learn to subtract shmem from cache...
> Signed-off-by: Jerome Marchand <jmarc...@redhat.com>
> Signed-off-by: Vlastimil Babka <vba...@suse.cz>
I am not sure that making MM_SHMEMPAGES conditional is really worth
the complications. We already have MM_SWAPENTS unconditional. If we
really care about the additional 64b then let's make both conditional
but this can be done in a separate patch IMO.
Btw. task_statm got it wrong and it uses the counter directly. So either
this one has to be fixed or just make it unconditional.
Other than that:
Acked-by: Michal Hocko <mho...@suse.com>
> ---
> arch/s390/mm/pgtable.c | 5 +----
> fs/proc/task_mmu.c | 3 ++-
> include/linux/mm.h | 28 ++++++++++++++++++++++++++++
> include/linux/mm_types.h | 9 ++++++---
> kernel/events/uprobes.c | 2 +-
> mm/memory.c | 30 ++++++++++--------------------
> mm/oom_kill.c | 5 +++--
> mm/rmap.c | 15 ++++-----------
> 8 files changed, 55 insertions(+), 42 deletions(-)
>
> diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
> index b33f661..276e3dd 100644
> --- a/arch/s390/mm/pgtable.c
> +++ b/arch/s390/mm/pgtable.c
> @@ -610,10 +610,7 @@ static void gmap_zap_swap_entry(swp_entry_t entry,
> struct mm_struct *mm)
> else if (is_migration_entry(entry)) {
> struct page *page = migration_entry_to_page(entry);
>
> - if (PageAnon(page))
> - dec_mm_counter(mm, MM_ANONPAGES);
> - else
> - dec_mm_counter(mm, MM_FILEPAGES);
> + dec_mm_counter(mm, mm_counter(page));
> }
> free_swap_and_cache(entry);
> }
> diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
> index f94f8f3..99b0efe 100644
> --- a/fs/proc/task_mmu.c
> +++ b/fs/proc/task_mmu.c
> @@ -81,7 +81,8 @@ unsigned long task_statm(struct mm_struct *mm,
> unsigned long *shared, unsigned long *text,
> unsigned long *data, unsigned long *resident)
> {
> - *shared = get_mm_counter(mm, MM_FILEPAGES);
> + *shared = get_mm_counter(mm, MM_FILEPAGES) +
> + get_mm_counter(mm, MM_SHMEMPAGES);
> *text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
> >> PAGE_SHIFT;
> *data = mm->total_vm - mm->shared_vm;
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 5e08787..b814ac2 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -1235,6 +1235,16 @@ static inline unsigned long get_mm_counter(struct
> mm_struct *mm, int member)
> return (unsigned long)val;
> }
>
> +/* A wrapper for the CONFIG_SHMEM dependent counter */
> +static inline unsigned long get_mm_counter_shmem(struct mm_struct *mm)
> +{
> +#ifdef CONFIG_SHMEM
> + return get_mm_counter(mm, MM_SHMEMPAGES);
> +#else
> + return 0;
> +#endif
> +}
> +
> static inline void add_mm_counter(struct mm_struct *mm, int member, long
> value)
> {
> atomic_long_add(value, &mm->rss_stat.count[member]);
> @@ -1250,9 +1260,27 @@ static inline void dec_mm_counter(struct mm_struct
> *mm, int member)
> atomic_long_dec(&mm->rss_stat.count[member]);
> }
>
> +/* Optimized variant when page is already known not to be PageAnon */
> +static inline int mm_counter_file(struct page *page)
> +{
> +#ifdef CONFIG_SHMEM
> + if (PageSwapBacked(page))
> + return MM_SHMEMPAGES;
> +#endif
> + return MM_FILEPAGES;
> +}
> +
> +static inline int mm_counter(struct page *page)
> +{
> + if (PageAnon(page))
> + return MM_ANONPAGES;
> + return mm_counter_file(page);
> +}
> +
> static inline unsigned long get_mm_rss(struct mm_struct *mm)
> {
> return get_mm_counter(mm, MM_FILEPAGES) +
> + get_mm_counter_shmem(mm) +
> get_mm_counter(mm, MM_ANONPAGES);
> }
>
> diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
> index 4957bd3..e02a855 100644
> --- a/include/linux/mm_types.h
> +++ b/include/linux/mm_types.h
> @@ -356,9 +356,12 @@ struct core_state {
> };
>
> enum {
> - MM_FILEPAGES,
> - MM_ANONPAGES,
> - MM_SWAPENTS,
> + MM_FILEPAGES, /* Resident file mapping pages */
> + MM_ANONPAGES, /* Resident anonymous pages */
> + MM_SWAPENTS, /* Anonymous swap entries */
> +#ifdef CONFIG_SHMEM
> + MM_SHMEMPAGES, /* Resident shared memory pages */
> +#endif
> NR_MM_COUNTERS
> };
>
> diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
> index 4e5e979..6288606 100644
> --- a/kernel/events/uprobes.c
> +++ b/kernel/events/uprobes.c
> @@ -180,7 +180,7 @@ static int __replace_page(struct vm_area_struct *vma,
> unsigned long addr,
> lru_cache_add_active_or_unevictable(kpage, vma);
>
> if (!PageAnon(page)) {
> - dec_mm_counter(mm, MM_FILEPAGES);
> + dec_mm_counter(mm, mm_counter_file(page));
> inc_mm_counter(mm, MM_ANONPAGES);
> }
>
> diff --git a/mm/memory.c b/mm/memory.c
> index fe1e6de..00030e8 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -832,10 +832,7 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct
> *src_mm,
> } else if (is_migration_entry(entry)) {
> page = migration_entry_to_page(entry);
>
> - if (PageAnon(page))
> - rss[MM_ANONPAGES]++;
> - else
> - rss[MM_FILEPAGES]++;
> + rss[mm_counter(page)]++;
>
> if (is_write_migration_entry(entry) &&
> is_cow_mapping(vm_flags)) {
> @@ -874,10 +871,7 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct
> *src_mm,
> if (page) {
> get_page(page);
> page_dup_rmap(page);
> - if (PageAnon(page))
> - rss[MM_ANONPAGES]++;
> - else
> - rss[MM_FILEPAGES]++;
> + rss[mm_counter(page)]++;
> }
>
> out_set_pte:
> @@ -1113,9 +1107,8 @@ static unsigned long zap_pte_range(struct mmu_gather
> *tlb,
> tlb_remove_tlb_entry(tlb, pte, addr);
> if (unlikely(!page))
> continue;
> - if (PageAnon(page))
> - rss[MM_ANONPAGES]--;
> - else {
> +
> + if (!PageAnon(page)) {
> if (pte_dirty(ptent)) {
> force_flush = 1;
> set_page_dirty(page);
> @@ -1123,8 +1116,8 @@ static unsigned long zap_pte_range(struct mmu_gather
> *tlb,
> if (pte_young(ptent) &&
> likely(!(vma->vm_flags & VM_SEQ_READ)))
> mark_page_accessed(page);
> - rss[MM_FILEPAGES]--;
> }
> + rss[mm_counter(page)]--;
> page_remove_rmap(page);
> if (unlikely(page_mapcount(page) < 0))
> print_bad_pte(vma, addr, ptent, page);
> @@ -1146,11 +1139,7 @@ static unsigned long zap_pte_range(struct mmu_gather
> *tlb,
> struct page *page;
>
> page = migration_entry_to_page(entry);
> -
> - if (PageAnon(page))
> - rss[MM_ANONPAGES]--;
> - else
> - rss[MM_FILEPAGES]--;
> + rss[mm_counter(page)]--;
> }
> if (unlikely(!free_swap_and_cache(entry)))
> print_bad_pte(vma, addr, ptent, NULL);
> @@ -1460,7 +1449,7 @@ static int insert_page(struct vm_area_struct *vma,
> unsigned long addr,
>
> /* Ok, finally just insert the thing.. */
> get_page(page);
> - inc_mm_counter_fast(mm, MM_FILEPAGES);
> + inc_mm_counter_fast(mm, mm_counter_file(page));
> page_add_file_rmap(page);
> set_pte_at(mm, addr, pte, mk_pte(page, prot));
>
> @@ -2097,7 +2086,8 @@ static int wp_page_copy(struct mm_struct *mm, struct
> vm_area_struct *vma,
> if (likely(pte_same(*page_table, orig_pte))) {
> if (old_page) {
> if (!PageAnon(old_page)) {
> - dec_mm_counter_fast(mm, MM_FILEPAGES);
> + dec_mm_counter_fast(mm,
> + mm_counter_file(old_page));
> inc_mm_counter_fast(mm, MM_ANONPAGES);
> }
> } else {
> @@ -2820,7 +2810,7 @@ void do_set_pte(struct vm_area_struct *vma, unsigned
> long address,
> inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
> page_add_new_anon_rmap(page, vma, address);
> } else {
> - inc_mm_counter_fast(vma->vm_mm, MM_FILEPAGES);
> + inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page));
> page_add_file_rmap(page);
> }
> set_pte_at(vma->vm_mm, address, pte, entry);
> diff --git a/mm/oom_kill.c b/mm/oom_kill.c
> index 1ecc0bc..230edc4 100644
> --- a/mm/oom_kill.c
> +++ b/mm/oom_kill.c
> @@ -555,10 +555,11 @@ void oom_kill_process(struct oom_control *oc, struct
> task_struct *p,
> /* mm cannot safely be dereferenced after task_unlock(victim) */
> mm = victim->mm;
> mark_oom_victim(victim);
> - pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB,
> file-rss:%lukB\n",
> + pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB,
> file-rss:%lukB, shmem-rss:%lukB\n",
> task_pid_nr(victim), victim->comm, K(victim->mm->total_vm),
> K(get_mm_counter(victim->mm, MM_ANONPAGES)),
> - K(get_mm_counter(victim->mm, MM_FILEPAGES)));
> + K(get_mm_counter(victim->mm, MM_FILEPAGES)),
> + K(get_mm_counter_shmem(victim->mm)));
> task_unlock(victim);
>
> /*
> diff --git a/mm/rmap.c b/mm/rmap.c
> index b6db6a6..e38a134 100644
> --- a/mm/rmap.c
> +++ b/mm/rmap.c
> @@ -1381,12 +1381,8 @@ static int try_to_unmap_one(struct page *page, struct
> vm_area_struct *vma,
> update_hiwater_rss(mm);
>
> if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) {
> - if (!PageHuge(page)) {
> - if (PageAnon(page))
> - dec_mm_counter(mm, MM_ANONPAGES);
> - else
> - dec_mm_counter(mm, MM_FILEPAGES);
> - }
> + if (!PageHuge(page))
> + dec_mm_counter(mm, mm_counter(page));
> set_pte_at(mm, address, pte,
> swp_entry_to_pte(make_hwpoison_entry(page)));
> } else if (pte_unused(pteval)) {
> @@ -1395,10 +1391,7 @@ static int try_to_unmap_one(struct page *page, struct
> vm_area_struct *vma,
> * interest anymore. Simply discard the pte, vmscan
> * will take care of the rest.
> */
> - if (PageAnon(page))
> - dec_mm_counter(mm, MM_ANONPAGES);
> - else
> - dec_mm_counter(mm, MM_FILEPAGES);
> + dec_mm_counter(mm, mm_counter(page));
> } else if (PageAnon(page)) {
> swp_entry_t entry = { .val = page_private(page) };
> pte_t swp_pte;
> @@ -1454,7 +1447,7 @@ static int try_to_unmap_one(struct page *page, struct
> vm_area_struct *vma,
> entry = make_migration_entry(page, pte_write(pteval));
> set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
> } else
> - dec_mm_counter(mm, MM_FILEPAGES);
> + dec_mm_counter(mm, mm_counter_file(page));
>
> discard:
> page_remove_rmap(page);
> --
> 2.4.6
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majord...@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
--
Michal Hocko
SUSE Labs
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
