mm, shmem: add internal shmem resident memory accounting

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.

The internal accounting currently counts shmem pages together with
regular files.  As a preparation to extend the userspace interfaces,
this patch adds MM_SHMEMPAGES counter to mm_rss_stat to account for
shmem pages separately from MM_FILEPAGES.  The next patch will expose it
to userspace - this patch doesn't change the exported values yet, by
adding up MM_SHMEMPAGES to MM_FILEPAGES at places where MM_FILEPAGES was
used before.  The only user-visible change after this patch is the OOM
killer message that separates the reported "shmem-rss" from "file-rss".

[vbabka@suse.cz: forward-porting, tweak changelog]
Signed-off-by: Jerome Marchand <jmarchan@redhat.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 63b039899a5ed1d70c56445b28f18b6d5389df28..aa34af0a0b263a13940b5de0f26cb4aef3ef966c 100644 (file)
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -603,10 +603,7 @@ 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 8a03759bda3848c636f8e771cd27c9993b25b505..45eb24145978c661ef8214481c8376be6d13186d 100644 (file)
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -83,7 +83,8 @@ 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 00bad7793788b2fb3342bda26335fc0713f0e909..a8ab1fc0e9bcfd3dc488a917ffa91e534e20b42d 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1361,10 +1361,26 @@ 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)
+{
+       if (PageSwapBacked(page))
+               return MM_SHMEMPAGES;
+       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(mm, MM_ANONPAGES);
+               get_mm_counter(mm, MM_ANONPAGES) +
+               get_mm_counter(mm, MM_SHMEMPAGES);
 }
 
 static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index f8d1492a114f4447d0d7f4dfd8136e854a4a7581..207890be93c8c7e6eadd59ab21815f1059465c87 100644 (file)
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -369,9 +369,10 @@ 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 */
+       MM_SHMEMPAGES,  /* Resident shared memory pages */
        NR_MM_COUNTERS
 };
 

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 7dad84913abfb06df2495fae555e7f8bcac2b104..bb0669169716e4847d67f651896531d7bca7bc40 100644 (file)
--- 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 c387430f06c319d52794152b7e100a66a10c9f68..f7026c0359406bb631d099af750c57b58b763684 100644 (file)
--- 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 @@ again:
                        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 @@ again:
                                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 @@ again:
                        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 c12680993ff334560dbfc84ffcee4e0bd0487650..dc490c06941b2a6be5170c0d9ca73418b7fe8619 100644 (file)
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -585,10 +585,11 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p,
         */
        do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true);
        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(victim->mm, MM_SHMEMPAGES)));
        task_unlock(victim);
 
        /*

diff --git a/mm/rmap.c b/mm/rmap.c
index 3c3f1d21f07585e1fd49b2e5003f65051c89a921..622756c16ac84ccc905355d3d6b59a9b9dca35e4 100644 (file)
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1364,10 +1364,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
                if (PageHuge(page)) {
                        hugetlb_count_sub(1 << compound_order(page), mm);
                } else {
-                       if (PageAnon(page))
-                               dec_mm_counter(mm, MM_ANONPAGES);
-                       else
-                               dec_mm_counter(mm, MM_FILEPAGES);
+                       dec_mm_counter(mm, mm_counter(page));
                }
                set_pte_at(mm, address, pte,
                           swp_entry_to_pte(make_hwpoison_entry(page)));
@@ -1377,10 +1374,7 @@ 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 (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION)) {
                swp_entry_t entry;
                pte_t swp_pte;
@@ -1420,7 +1414,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
                        swp_pte = pte_swp_mksoft_dirty(swp_pte);
                set_pte_at(mm, address, pte, swp_pte);
        } else
-               dec_mm_counter(mm, MM_FILEPAGES);
+               dec_mm_counter(mm, mm_counter_file(page));
 
        page_remove_rmap(page);
        page_cache_release(page);