[PATCH] mm: rss = file_rss + anon_rss

I was lazy when we added anon_rss, and chose to change as few places as
possible.  So currently each anonymous page has to be counted twice, in rss
and in anon_rss.  Which won't be so good if those are atomic counts in some
configurations.

Change that around: keep file_rss and anon_rss separately, and add them
together (with get_mm_rss macro) when the total is needed - reading two
atomics is much cheaper than updating two atomics.  And update anon_rss
upfront, typically in memory.c, not tucked away in page_add_anon_rmap.

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/fs/exec.c b/fs/exec.c
index d2208f7c87db81c30d8bdd3ddf965e887f693e4a..cefadf5ab83b77472bafa23f337884de3eaf1dc1 100644 (file)
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -330,7 +330,7 @@ void install_arg_page(struct vm_area_struct *vma,
                pte_unmap(pte);
                goto out;
        }
-       inc_mm_counter(mm, rss);
+       inc_mm_counter(mm, anon_rss);
        lru_cache_add_active(page);
        set_pte_at(mm, address, pte, pte_mkdirty(pte_mkwrite(mk_pte(
                                        page, vma->vm_page_prot))));

diff --git a/fs/proc/array.c b/fs/proc/array.c
index d84eecacbeaff81b91cb4ed43d65c2b6e418c163..3e1239e4b303002b11b709a9d1e6016ebf7d47e9 100644 (file)
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -438,7 +438,7 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole)
                jiffies_to_clock_t(it_real_value),
                start_time,
                vsize,
-               mm ? get_mm_counter(mm, rss) : 0, /* you might want to shift this left 3 */
+               mm ? get_mm_rss(mm) : 0,
                rsslim,
                mm ? mm->start_code : 0,
                mm ? mm->end_code : 0,

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 994612bc72d00aad278cef60434fa4b74d300cb2..bccee7cf9ccd52e80ef5ac8dfd5d2f55d4e71755 100644 (file)
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -29,7 +29,7 @@ char *task_mem(struct mm_struct *mm, char *buffer)
                "VmPTE:\t%8lu kB\n",
                (mm->total_vm - mm->reserved_vm) << (PAGE_SHIFT-10),
                mm->locked_vm << (PAGE_SHIFT-10),
-               get_mm_counter(mm, rss) << (PAGE_SHIFT-10),
+               get_mm_rss(mm) << (PAGE_SHIFT-10),
                data << (PAGE_SHIFT-10),
                mm->stack_vm << (PAGE_SHIFT-10), text, lib,
                (PTRS_PER_PTE*sizeof(pte_t)*mm->nr_ptes) >> 10);
@@ -44,13 +44,11 @@ unsigned long task_vsize(struct mm_struct *mm)
 int task_statm(struct mm_struct *mm, int *shared, int *text,
               int *data, int *resident)
 {
-       int rss = get_mm_counter(mm, rss);
-
-       *shared = rss - get_mm_counter(mm, anon_rss);
+       *shared = get_mm_counter(mm, file_rss);
        *text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
                                                                >> PAGE_SHIFT;
        *data = mm->total_vm - mm->shared_vm;
-       *resident = rss;
+       *resident = *shared + get_mm_counter(mm, anon_rss);
        return mm->total_vm;
 }
 

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 27519df0f9876bfb1ced31d3998062ccd48c12e5..afcaac66cbd5bf1f997eb834b81f406cdba67043 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -254,6 +254,8 @@ extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
 #define add_mm_counter(mm, member, value) (mm)->_##member += (value)
 #define inc_mm_counter(mm, member) (mm)->_##member++
 #define dec_mm_counter(mm, member) (mm)->_##member--
+#define get_mm_rss(mm) ((mm)->_file_rss + (mm)->_anon_rss)
+
 typedef unsigned long mm_counter_t;
 
 struct mm_struct {
@@ -286,7 +288,7 @@ struct mm_struct {
        unsigned long exec_vm, stack_vm, reserved_vm, def_flags, nr_ptes;
 
        /* Special counters protected by the page_table_lock */
-       mm_counter_t _rss;
+       mm_counter_t _file_rss;
        mm_counter_t _anon_rss;
 
        unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */

diff --git a/kernel/acct.c b/kernel/acct.c
index b756f527497ea8c201d533df64ff053da0084d96..2e3f4a47e7d0578c6a7dc05f2296d1c6be8cc18d 100644 (file)
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -553,7 +553,7 @@ void acct_update_integrals(struct task_struct *tsk)
                if (delta == 0)
                        return;
                tsk->acct_stimexpd = tsk->stime;
-               tsk->acct_rss_mem1 += delta * get_mm_counter(tsk->mm, rss);
+               tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm);
                tsk->acct_vm_mem1 += delta * tsk->mm->total_vm;
        }
 }

diff --git a/kernel/fork.c b/kernel/fork.c
index 25caa02e2eac5729bab0952db88ef2dd2c6cc101..2048ed7b5872262f963c6bbb633769b7baaff4cb 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -321,7 +321,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm)
        INIT_LIST_HEAD(&mm->mmlist);
        mm->core_waiters = 0;
        mm->nr_ptes = 0;
-       set_mm_counter(mm, rss, 0);
+       set_mm_counter(mm, file_rss, 0);
        set_mm_counter(mm, anon_rss, 0);
        spin_lock_init(&mm->page_table_lock);
        rwlock_init(&mm->ioctx_list_lock);
@@ -499,7 +499,7 @@ static int copy_mm(unsigned long clone_flags, struct task_struct * tsk)
        if (retval)
                goto free_pt;
 
-       mm->hiwater_rss = get_mm_counter(mm,rss);
+       mm->hiwater_rss = get_mm_rss(mm);
        mm->hiwater_vm = mm->total_vm;
 
 good_mm:

diff --git a/mm/fremap.c b/mm/fremap.c
index ab23a0673c351cc8ed263cfcea5f280c4736bbc9..fd7f2a17ff3e49bada9aa1d7c18febe56a9cda03 100644 (file)
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -39,7 +39,7 @@ static inline void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
                                        set_page_dirty(page);
                                page_remove_rmap(page);
                                page_cache_release(page);
-                               dec_mm_counter(mm, rss);
+                               dec_mm_counter(mm, file_rss);
                        }
                }
        } else {
@@ -95,7 +95,7 @@ int install_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
        zap_pte(mm, vma, addr, pte);
 
-       inc_mm_counter(mm,rss);
+       inc_mm_counter(mm, file_rss);
        flush_icache_page(vma, page);
        set_pte_at(mm, addr, pte, mk_pte(page, prot));
        page_add_file_rmap(page);

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 61d380678030312f453c44e86631c3f9c0e49028..094455bcbbf73c4476162336806acef804e7d449 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -286,7 +286,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
                        entry = *src_pte;
                        ptepage = pte_page(entry);
                        get_page(ptepage);
-                       add_mm_counter(dst, rss, HPAGE_SIZE / PAGE_SIZE);
+                       add_mm_counter(dst, file_rss, HPAGE_SIZE / PAGE_SIZE);
                        set_huge_pte_at(dst, addr, dst_pte, entry);
                }
                spin_unlock(&src->page_table_lock);
@@ -324,7 +324,7 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 
                page = pte_page(pte);
                put_page(page);
-               add_mm_counter(mm, rss,  - (HPAGE_SIZE / PAGE_SIZE));
+               add_mm_counter(mm, file_rss, (int) -(HPAGE_SIZE / PAGE_SIZE));
        }
        flush_tlb_range(vma, start, end);
 }
@@ -386,7 +386,7 @@ int hugetlb_prefault(struct address_space *mapping, struct vm_area_struct *vma)
                                goto out;
                        }
                }
-               add_mm_counter(mm, rss, HPAGE_SIZE / PAGE_SIZE);
+               add_mm_counter(mm, file_rss, HPAGE_SIZE / PAGE_SIZE);
                set_huge_pte_at(mm, addr, pte, make_huge_pte(vma, page));
        }
 out:

diff --git a/mm/memory.c b/mm/memory.c
index 51eb38574830408afad7fcd1a0841cb241312b80..59d42e50fa53683ce42b1ded64c96e4f0d98eb6c 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -397,9 +397,10 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
                pte = pte_mkclean(pte);
        pte = pte_mkold(pte);
        get_page(page);
-       inc_mm_counter(dst_mm, rss);
        if (PageAnon(page))
                inc_mm_counter(dst_mm, anon_rss);
+       else
+               inc_mm_counter(dst_mm, file_rss);
        set_pte_at(dst_mm, addr, dst_pte, pte);
        page_dup_rmap(page);
 }
@@ -581,8 +582,8 @@ static void zap_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
                                        set_page_dirty(page);
                                if (pte_young(ptent))
                                        mark_page_accessed(page);
+                               dec_mm_counter(tlb->mm, file_rss);
                        }
-                       dec_mm_counter(tlb->mm, rss);
                        page_remove_rmap(page);
                        tlb_remove_page(tlb, page);
                        continue;
@@ -1290,13 +1291,15 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
        spin_lock(&mm->page_table_lock);
        page_table = pte_offset_map(pmd, address);
        if (likely(pte_same(*page_table, orig_pte))) {
-               if (PageAnon(old_page))
-                       dec_mm_counter(mm, anon_rss);
                if (PageReserved(old_page))
-                       inc_mm_counter(mm, rss);
-               else
+                       inc_mm_counter(mm, anon_rss);
+               else {
                        page_remove_rmap(old_page);
-
+                       if (!PageAnon(old_page)) {
+                               inc_mm_counter(mm, anon_rss);
+                               dec_mm_counter(mm, file_rss);
+                       }
+               }
                flush_cache_page(vma, address, pfn);
                entry = mk_pte(new_page, vma->vm_page_prot);
                entry = maybe_mkwrite(pte_mkdirty(entry), vma);
@@ -1701,7 +1704,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
        /* The page isn't present yet, go ahead with the fault. */
 
-       inc_mm_counter(mm, rss);
+       inc_mm_counter(mm, anon_rss);
        pte = mk_pte(page, vma->vm_page_prot);
        if (write_access && can_share_swap_page(page)) {
                pte = maybe_mkwrite(pte_mkdirty(pte), vma);
@@ -1774,7 +1777,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
                        page_cache_release(page);
                        goto unlock;
                }
-               inc_mm_counter(mm, rss);
+               inc_mm_counter(mm, anon_rss);
                entry = mk_pte(page, vma->vm_page_prot);
                entry = maybe_mkwrite(pte_mkdirty(entry), vma);
                lru_cache_add_active(page);
@@ -1887,19 +1890,19 @@ retry:
         */
        /* Only go through if we didn't race with anybody else... */
        if (pte_none(*page_table)) {
-               if (!PageReserved(new_page))
-                       inc_mm_counter(mm, rss);
-
                flush_icache_page(vma, new_page);
                entry = mk_pte(new_page, vma->vm_page_prot);
                if (write_access)
                        entry = maybe_mkwrite(pte_mkdirty(entry), vma);
                set_pte_at(mm, address, page_table, entry);
                if (anon) {
+                       inc_mm_counter(mm, anon_rss);
                        lru_cache_add_active(new_page);
                        page_add_anon_rmap(new_page, vma, address);
-               } else
+               } else if (!PageReserved(new_page)) {
+                       inc_mm_counter(mm, file_rss);
                        page_add_file_rmap(new_page);
+               }
        } else {
                /* One of our sibling threads was faster, back out. */
                page_cache_release(new_page);
@@ -2192,7 +2195,7 @@ EXPORT_SYMBOL(vmalloc_to_pfn);
 void update_mem_hiwater(struct task_struct *tsk)
 {
        if (tsk->mm) {
-               unsigned long rss = get_mm_counter(tsk->mm, rss);
+               unsigned long rss = get_mm_rss(tsk->mm);
 
                if (tsk->mm->hiwater_rss < rss)
                        tsk->mm->hiwater_rss = rss;

diff --git a/mm/nommu.c b/mm/nommu.c
index 0ef241ae3763224372020f8e8ebe999db430ef8e..599924886eb56ff92d2371ced7cdbdbd3a388830 100644 (file)
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1083,7 +1083,7 @@ void update_mem_hiwater(struct task_struct *tsk)
        unsigned long rss;
 
        if (likely(tsk->mm)) {
-               rss = get_mm_counter(tsk->mm, rss);
+               rss = get_mm_rss(tsk->mm);
                if (tsk->mm->hiwater_rss < rss)
                        tsk->mm->hiwater_rss = rss;
                if (tsk->mm->hiwater_vm < tsk->mm->total_vm)

diff --git a/mm/rmap.c b/mm/rmap.c
index 1fc559e09ca8c75793ff1dc1b5d6f8ddb7ee2abe..504757624cce720f2cd424c13d6448111c86e6ca 100644 (file)
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -445,8 +445,6 @@ void page_add_anon_rmap(struct page *page,
 {
        BUG_ON(PageReserved(page));
 
-       inc_mm_counter(vma->vm_mm, anon_rss);
-
        if (atomic_inc_and_test(&page->_mapcount)) {
                struct anon_vma *anon_vma = vma->anon_vma;
 
@@ -561,9 +559,9 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma)
                set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
                BUG_ON(pte_file(*pte));
                dec_mm_counter(mm, anon_rss);
-       }
+       } else
+               dec_mm_counter(mm, file_rss);
 
-       dec_mm_counter(mm, rss);
        page_remove_rmap(page);
        page_cache_release(page);
 
@@ -667,7 +665,7 @@ static void try_to_unmap_cluster(unsigned long cursor,
 
                page_remove_rmap(page);
                page_cache_release(page);
-               dec_mm_counter(mm, rss);
+               dec_mm_counter(mm, file_rss);
                (*mapcount)--;
        }
 

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 05c85129124146a3e537f71a145a5fd9da3c4643..296e0bbf78360f673c4e95283ad72be118b88952 100644 (file)
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -407,7 +407,7 @@ void free_swap_and_cache(swp_entry_t entry)
 static void unuse_pte(struct vm_area_struct *vma, pte_t *pte,
                unsigned long addr, swp_entry_t entry, struct page *page)
 {
-       inc_mm_counter(vma->vm_mm, rss);
+       inc_mm_counter(vma->vm_mm, anon_rss);
        get_page(page);
        set_pte_at(vma->vm_mm, addr, pte,
                   pte_mkold(mk_pte(page, vma->vm_page_prot)));