summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>2010-03-05 13:41:39 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2010-03-06 11:26:23 -0800
commitd559db086ff5be9bcc259e5aa50bf3d881eaf1d1 (patch)
treeaa968c8a4093234e4623a34c0415bf9d8683671c
parent19b629f581320999ddb9f6597051b79cdb53459c (diff)
downloadlwn-d559db086ff5be9bcc259e5aa50bf3d881eaf1d1.tar.gz
lwn-d559db086ff5be9bcc259e5aa50bf3d881eaf1d1.zip
mm: clean up mm_counter
Presently, per-mm statistics counter is defined by macro in sched.h This patch modifies it to - defined in mm.h as inlinf functions - use array instead of macro's name creation. This patch is for reducing patch size in future patch to modify implementation of per-mm counter. Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--fs/proc/task_mmu.c4
-rw-r--r--include/linux/mm.h104
-rw-r--r--include/linux/mm_types.h33
-rw-r--r--include/linux/sched.h54
-rw-r--r--kernel/fork.c3
-rw-r--r--kernel/tsacct.c1
-rw-r--r--mm/filemap_xip.c2
-rw-r--r--mm/fremap.c2
-rw-r--r--mm/memory.c56
-rw-r--r--mm/oom_kill.c4
-rw-r--r--mm/rmap.c10
-rw-r--r--mm/swapfile.c2
12 files changed, 174 insertions, 101 deletions
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index f277c4a111cb..375581276011 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -65,11 +65,11 @@ unsigned long task_vsize(struct mm_struct *mm)
int task_statm(struct mm_struct *mm, int *shared, int *text,
int *data, int *resident)
{
- *shared = get_mm_counter(mm, file_rss);
+ *shared = get_mm_counter(mm, MM_FILEPAGES);
*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
>> PAGE_SHIFT;
*data = mm->total_vm - mm->shared_vm;
- *resident = *shared + get_mm_counter(mm, anon_rss);
+ *resident = *shared + get_mm_counter(mm, MM_ANONPAGES);
return mm->total_vm;
}
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 90957f14195c..2124cdb2d1d0 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -870,6 +870,110 @@ extern int mprotect_fixup(struct vm_area_struct *vma,
*/
int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
struct page **pages);
+/*
+ * per-process(per-mm_struct) statistics.
+ */
+#if USE_SPLIT_PTLOCKS
+/*
+ * The mm counters are not protected by its page_table_lock,
+ * so must be incremented atomically.
+ */
+static inline void set_mm_counter(struct mm_struct *mm, int member, long value)
+{
+ atomic_long_set(&mm->rss_stat.count[member], value);
+}
+
+static inline unsigned long get_mm_counter(struct mm_struct *mm, int member)
+{
+ return (unsigned long)atomic_long_read(&mm->rss_stat.count[member]);
+}
+
+static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
+{
+ atomic_long_add(value, &mm->rss_stat.count[member]);
+}
+
+static inline void inc_mm_counter(struct mm_struct *mm, int member)
+{
+ atomic_long_inc(&mm->rss_stat.count[member]);
+}
+
+static inline void dec_mm_counter(struct mm_struct *mm, int member)
+{
+ atomic_long_dec(&mm->rss_stat.count[member]);
+}
+
+#else /* !USE_SPLIT_PTLOCKS */
+/*
+ * The mm counters are protected by its page_table_lock,
+ * so can be incremented directly.
+ */
+static inline void set_mm_counter(struct mm_struct *mm, int member, long value)
+{
+ mm->rss_stat.count[member] = value;
+}
+
+static inline unsigned long get_mm_counter(struct mm_struct *mm, int member)
+{
+ return mm->rss_stat.count[member];
+}
+
+static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
+{
+ mm->rss_stat.count[member] += value;
+}
+
+static inline void inc_mm_counter(struct mm_struct *mm, int member)
+{
+ mm->rss_stat.count[member]++;
+}
+
+static inline void dec_mm_counter(struct mm_struct *mm, int member)
+{
+ mm->rss_stat.count[member]--;
+}
+
+#endif /* !USE_SPLIT_PTLOCKS */
+
+static inline unsigned long get_mm_rss(struct mm_struct *mm)
+{
+ return get_mm_counter(mm, MM_FILEPAGES) +
+ get_mm_counter(mm, MM_ANONPAGES);
+}
+
+static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm)
+{
+ return max(mm->hiwater_rss, get_mm_rss(mm));
+}
+
+static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm)
+{
+ return max(mm->hiwater_vm, mm->total_vm);
+}
+
+static inline void update_hiwater_rss(struct mm_struct *mm)
+{
+ unsigned long _rss = get_mm_rss(mm);
+
+ if ((mm)->hiwater_rss < _rss)
+ (mm)->hiwater_rss = _rss;
+}
+
+static inline void update_hiwater_vm(struct mm_struct *mm)
+{
+ if (mm->hiwater_vm < mm->total_vm)
+ mm->hiwater_vm = mm->total_vm;
+}
+
+static inline void setmax_mm_hiwater_rss(unsigned long *maxrss,
+ struct mm_struct *mm)
+{
+ unsigned long hiwater_rss = get_mm_hiwater_rss(mm);
+
+ if (*maxrss < hiwater_rss)
+ *maxrss = hiwater_rss;
+}
+
/*
* A callback you can register to apply pressure to ageable caches.
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 36f96271306c..e1ca64be6678 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -24,12 +24,6 @@ struct address_space;
#define USE_SPLIT_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS)
-#if USE_SPLIT_PTLOCKS
-typedef atomic_long_t mm_counter_t;
-#else /* !USE_SPLIT_PTLOCKS */
-typedef unsigned long mm_counter_t;
-#endif /* !USE_SPLIT_PTLOCKS */
-
/*
* Each physical page in the system has a struct page associated with
* it to keep track of whatever it is we are using the page for at the
@@ -201,6 +195,22 @@ struct core_state {
struct completion startup;
};
+enum {
+ MM_FILEPAGES,
+ MM_ANONPAGES,
+ NR_MM_COUNTERS
+};
+
+#if USE_SPLIT_PTLOCKS
+struct mm_rss_stat {
+ atomic_long_t count[NR_MM_COUNTERS];
+};
+#else /* !USE_SPLIT_PTLOCKS */
+struct mm_rss_stat {
+ unsigned long count[NR_MM_COUNTERS];
+};
+#endif /* !USE_SPLIT_PTLOCKS */
+
struct mm_struct {
struct vm_area_struct * mmap; /* list of VMAs */
struct rb_root mm_rb;
@@ -227,11 +237,6 @@ struct mm_struct {
* by mmlist_lock
*/
- /* Special counters, in some configurations protected by the
- * page_table_lock, in other configurations by being atomic.
- */
- mm_counter_t _file_rss;
- mm_counter_t _anon_rss;
unsigned long hiwater_rss; /* High-watermark of RSS usage */
unsigned long hiwater_vm; /* High-water virtual memory usage */
@@ -244,6 +249,12 @@ struct mm_struct {
unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */
+ /*
+ * Special counters, in some configurations protected by the
+ * page_table_lock, in other configurations by being atomic.
+ */
+ struct mm_rss_stat rss_stat;
+
struct linux_binfmt *binfmt;
cpumask_t cpu_vm_mask;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4b1753f7e48e..cbeafa49a53b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -396,60 +396,6 @@ extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
#endif
-#if USE_SPLIT_PTLOCKS
-/*
- * The mm counters are not protected by its page_table_lock,
- * so must be incremented atomically.
- */
-#define set_mm_counter(mm, member, value) atomic_long_set(&(mm)->_##member, value)
-#define get_mm_counter(mm, member) ((unsigned long)atomic_long_read(&(mm)->_##member))
-#define add_mm_counter(mm, member, value) atomic_long_add(value, &(mm)->_##member)
-#define inc_mm_counter(mm, member) atomic_long_inc(&(mm)->_##member)
-#define dec_mm_counter(mm, member) atomic_long_dec(&(mm)->_##member)
-
-#else /* !USE_SPLIT_PTLOCKS */
-/*
- * The mm counters are protected by its page_table_lock,
- * so can be incremented directly.
- */
-#define set_mm_counter(mm, member, value) (mm)->_##member = (value)
-#define get_mm_counter(mm, member) ((mm)->_##member)
-#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--
-
-#endif /* !USE_SPLIT_PTLOCKS */
-
-#define get_mm_rss(mm) \
- (get_mm_counter(mm, file_rss) + get_mm_counter(mm, anon_rss))
-#define update_hiwater_rss(mm) do { \
- unsigned long _rss = get_mm_rss(mm); \
- if ((mm)->hiwater_rss < _rss) \
- (mm)->hiwater_rss = _rss; \
-} while (0)
-#define update_hiwater_vm(mm) do { \
- if ((mm)->hiwater_vm < (mm)->total_vm) \
- (mm)->hiwater_vm = (mm)->total_vm; \
-} while (0)
-
-static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm)
-{
- return max(mm->hiwater_rss, get_mm_rss(mm));
-}
-
-static inline void setmax_mm_hiwater_rss(unsigned long *maxrss,
- struct mm_struct *mm)
-{
- unsigned long hiwater_rss = get_mm_hiwater_rss(mm);
-
- if (*maxrss < hiwater_rss)
- *maxrss = hiwater_rss;
-}
-
-static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm)
-{
- return max(mm->hiwater_vm, mm->total_vm);
-}
extern void set_dumpable(struct mm_struct *mm, int value);
extern int get_dumpable(struct mm_struct *mm);
diff --git a/kernel/fork.c b/kernel/fork.c
index 17bbf093356d..7616bcf107b9 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -455,8 +455,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
(current->mm->flags & MMF_INIT_MASK) : default_dump_filter;
mm->core_state = NULL;
mm->nr_ptes = 0;
- set_mm_counter(mm, file_rss, 0);
- set_mm_counter(mm, anon_rss, 0);
+ memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
spin_lock_init(&mm->page_table_lock);
mm->free_area_cache = TASK_UNMAPPED_BASE;
mm->cached_hole_size = ~0UL;
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 00d59d048edf..0a67e041edf8 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -21,6 +21,7 @@
#include <linux/tsacct_kern.h>
#include <linux/acct.h>
#include <linux/jiffies.h>
+#include <linux/mm.h>
/*
* fill in basic accounting fields
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index 1888b2d71bb8..78b94f0b6d5d 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -194,7 +194,7 @@ retry:
flush_cache_page(vma, address, pte_pfn(*pte));
pteval = ptep_clear_flush_notify(vma, address, pte);
page_remove_rmap(page);
- dec_mm_counter(mm, file_rss);
+ dec_mm_counter(mm, MM_FILEPAGES);
BUG_ON(pte_dirty(pteval));
pte_unmap_unlock(pte, ptl);
page_cache_release(page);
diff --git a/mm/fremap.c b/mm/fremap.c
index b6ec85abbb39..46f5dacf90a2 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -40,7 +40,7 @@ static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
page_remove_rmap(page);
page_cache_release(page);
update_hiwater_rss(mm);
- dec_mm_counter(mm, file_rss);
+ dec_mm_counter(mm, MM_FILEPAGES);
}
} else {
if (!pte_file(pte))
diff --git a/mm/memory.c b/mm/memory.c
index 72fb5f39bccc..c57678478801 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -121,6 +121,7 @@ static int __init init_zero_pfn(void)
}
core_initcall(init_zero_pfn);
+
/*
* If a p?d_bad entry is found while walking page tables, report
* the error, before resetting entry to p?d_none. Usually (but
@@ -376,12 +377,18 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address)
return 0;
}
-static inline void add_mm_rss(struct mm_struct *mm, int file_rss, int anon_rss)
+static inline void init_rss_vec(int *rss)
{
- if (file_rss)
- add_mm_counter(mm, file_rss, file_rss);
- if (anon_rss)
- add_mm_counter(mm, anon_rss, anon_rss);
+ memset(rss, 0, sizeof(int) * NR_MM_COUNTERS);
+}
+
+static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss)
+{
+ int i;
+
+ for (i = 0; i < NR_MM_COUNTERS; i++)
+ if (rss[i])
+ add_mm_counter(mm, i, rss[i]);
}
/*
@@ -632,7 +639,10 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
if (page) {
get_page(page);
page_dup_rmap(page);
- rss[PageAnon(page)]++;
+ if (PageAnon(page))
+ rss[MM_ANONPAGES]++;
+ else
+ rss[MM_FILEPAGES]++;
}
out_set_pte:
@@ -648,11 +658,12 @@ static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pte_t *src_pte, *dst_pte;
spinlock_t *src_ptl, *dst_ptl;
int progress = 0;
- int rss[2];
+ int rss[NR_MM_COUNTERS];
swp_entry_t entry = (swp_entry_t){0};
again:
- rss[1] = rss[0] = 0;
+ init_rss_vec(rss);
+
dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl);
if (!dst_pte)
return -ENOMEM;
@@ -688,7 +699,7 @@ again:
arch_leave_lazy_mmu_mode();
spin_unlock(src_ptl);
pte_unmap_nested(orig_src_pte);
- add_mm_rss(dst_mm, rss[0], rss[1]);
+ add_mm_rss_vec(dst_mm, rss);
pte_unmap_unlock(orig_dst_pte, dst_ptl);
cond_resched();
@@ -816,8 +827,9 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
struct mm_struct *mm = tlb->mm;
pte_t *pte;
spinlock_t *ptl;
- int file_rss = 0;
- int anon_rss = 0;
+ int rss[NR_MM_COUNTERS];
+
+ init_rss_vec(rss);
pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
arch_enter_lazy_mmu_mode();
@@ -863,14 +875,14 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
set_pte_at(mm, addr, pte,
pgoff_to_pte(page->index));
if (PageAnon(page))
- anon_rss--;
+ rss[MM_ANONPAGES]--;
else {
if (pte_dirty(ptent))
set_page_dirty(page);
if (pte_young(ptent) &&
likely(!VM_SequentialReadHint(vma)))
mark_page_accessed(page);
- file_rss--;
+ rss[MM_FILEPAGES]--;
}
page_remove_rmap(page);
if (unlikely(page_mapcount(page) < 0))
@@ -893,7 +905,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
} while (pte++, addr += PAGE_SIZE, (addr != end && *zap_work > 0));
- add_mm_rss(mm, file_rss, anon_rss);
+ add_mm_rss_vec(mm, rss);
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(pte - 1, ptl);
@@ -1527,7 +1539,7 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr,
/* Ok, finally just insert the thing.. */
get_page(page);
- inc_mm_counter(mm, file_rss);
+ inc_mm_counter(mm, MM_FILEPAGES);
page_add_file_rmap(page);
set_pte_at(mm, addr, pte, mk_pte(page, prot));
@@ -2163,11 +2175,11 @@ gotten:
if (likely(pte_same(*page_table, orig_pte))) {
if (old_page) {
if (!PageAnon(old_page)) {
- dec_mm_counter(mm, file_rss);
- inc_mm_counter(mm, anon_rss);
+ dec_mm_counter(mm, MM_FILEPAGES);
+ inc_mm_counter(mm, MM_ANONPAGES);
}
} else
- inc_mm_counter(mm, anon_rss);
+ inc_mm_counter(mm, MM_ANONPAGES);
flush_cache_page(vma, address, pte_pfn(orig_pte));
entry = mk_pte(new_page, vma->vm_page_prot);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
@@ -2604,7 +2616,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
* discarded at swap_free().
*/
- inc_mm_counter(mm, anon_rss);
+ inc_mm_counter(mm, MM_ANONPAGES);
pte = mk_pte(page, vma->vm_page_prot);
if ((flags & FAULT_FLAG_WRITE) && reuse_swap_page(page)) {
pte = maybe_mkwrite(pte_mkdirty(pte), vma);
@@ -2688,7 +2700,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
if (!pte_none(*page_table))
goto release;
- inc_mm_counter(mm, anon_rss);
+ inc_mm_counter(mm, MM_ANONPAGES);
page_add_new_anon_rmap(page, vma, address);
setpte:
set_pte_at(mm, address, page_table, entry);
@@ -2842,10 +2854,10 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
if (flags & FAULT_FLAG_WRITE)
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
if (anon) {
- inc_mm_counter(mm, anon_rss);
+ inc_mm_counter(mm, MM_ANONPAGES);
page_add_new_anon_rmap(page, vma, address);
} else {
- inc_mm_counter(mm, file_rss);
+ inc_mm_counter(mm, MM_FILEPAGES);
page_add_file_rmap(page);
if (flags & FAULT_FLAG_WRITE) {
dirty_page = page;
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 237050478f28..35755a4156d6 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -401,8 +401,8 @@ static void __oom_kill_task(struct task_struct *p, int verbose)
"vsz:%lukB, anon-rss:%lukB, file-rss:%lukB\n",
task_pid_nr(p), p->comm,
K(p->mm->total_vm),
- K(get_mm_counter(p->mm, anon_rss)),
- K(get_mm_counter(p->mm, file_rss)));
+ K(get_mm_counter(p->mm, MM_ANONPAGES)),
+ K(get_mm_counter(p->mm, MM_FILEPAGES)));
task_unlock(p);
/*
diff --git a/mm/rmap.c b/mm/rmap.c
index 278cd277bdec..73d0472884c2 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -815,9 +815,9 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) {
if (PageAnon(page))
- dec_mm_counter(mm, anon_rss);
+ dec_mm_counter(mm, MM_ANONPAGES);
else
- dec_mm_counter(mm, file_rss);
+ dec_mm_counter(mm, MM_FILEPAGES);
set_pte_at(mm, address, pte,
swp_entry_to_pte(make_hwpoison_entry(page)));
} else if (PageAnon(page)) {
@@ -839,7 +839,7 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
list_add(&mm->mmlist, &init_mm.mmlist);
spin_unlock(&mmlist_lock);
}
- dec_mm_counter(mm, anon_rss);
+ dec_mm_counter(mm, MM_ANONPAGES);
} else if (PAGE_MIGRATION) {
/*
* Store the pfn of the page in a special migration
@@ -857,7 +857,7 @@ 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, file_rss);
+ dec_mm_counter(mm, MM_FILEPAGES);
page_remove_rmap(page);
page_cache_release(page);
@@ -996,7 +996,7 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
page_remove_rmap(page);
page_cache_release(page);
- dec_mm_counter(mm, file_rss);
+ dec_mm_counter(mm, MM_FILEPAGES);
(*mapcount)--;
}
pte_unmap_unlock(pte - 1, ptl);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 6c0585b16418..893984946a2c 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -840,7 +840,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
goto out;
}
- inc_mm_counter(vma->vm_mm, anon_rss);
+ inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
get_page(page);
set_pte_at(vma->vm_mm, addr, pte,
pte_mkold(mk_pte(page, vma->vm_page_prot)));