pagemap: add mmap-exclusive bit for marking pages mapped only here

This patch sets bit 56 in pagemap if this page is mapped only once.  It
allows to detect exclusively used pages without exposing PFN:

present file exclusive state
0       0    0         non-present
1       1    0         file page mapped somewhere else
1       1    1         file page mapped only here
1       0    0         anon non-CoWed page (shared with parent/child)
1       0    1         anon CoWed page (or never forked)

CoWed pages in (MAP_FILE | MAP_PRIVATE) areas are anon in this context.

MMap-exclusive bit doesn't reflect potential page-sharing via swapcache:
page could be mapped once but has several swap-ptes which point to it.
Application could detect that by swap bit in pagemap entry and touch that
pte via /proc/pid/mem to get real information.

See http://lkml.kernel.org/r/CAEVpBa+_RyACkhODZrRvQLs80iy0sqpdrd0AaP_-tgnX3Y9yNQ@mail.gmail.com

Requested by Mark Williamson.

[akpm@linux-foundation.org: fix spello]
Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Reviewed-by: Mark Williamson <mwilliamson@undo-software.com>
Tested-by:  Mark Williamson <mwilliamson@undo-software.com>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/Documentation/vm/pagemap.txt b/Documentation/vm/pagemap.txt
index 6bfbc172cdb96b437728a34eadf3e257ab456799..56faec0f73f7398fabc5e08f5756ba71ec033373 100644 (file)
--- a/Documentation/vm/pagemap.txt
+++ b/Documentation/vm/pagemap.txt
@@ -16,7 +16,8 @@ There are three components to pagemap:
     * Bits 0-4   swap type if swapped
     * Bits 5-54  swap offset if swapped
     * Bit  55    pte is soft-dirty (see Documentation/vm/soft-dirty.txt)
     * Bits 0-4   swap type if swapped
     * Bits 5-54  swap offset if swapped
     * Bit  55    pte is soft-dirty (see Documentation/vm/soft-dirty.txt)

-    * Bits 56-60 zero
+    * Bit  56    page exclusively mapped
+    * Bits 57-60 zero

     * Bit  61    page is file-page or shared-anon
     * Bit  62    page swapped
     * Bit  63    page present
     * Bit  61    page is file-page or shared-anon
     * Bit  62    page swapped
     * Bit  63    page present

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index bc651644b1b247c5c690236e2629492015ee4446..67c76468a7be4a057d42f1c2b1ca50ec851cb3d7 100644 (file)
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -949,6 +949,7 @@ struct pagemapread {
 #define PM_PFRAME_BITS         55
 #define PM_PFRAME_MASK         GENMASK_ULL(PM_PFRAME_BITS - 1, 0)
 #define PM_SOFT_DIRTY          BIT_ULL(55)
 #define PM_PFRAME_BITS         55
 #define PM_PFRAME_MASK         GENMASK_ULL(PM_PFRAME_BITS - 1, 0)
 #define PM_SOFT_DIRTY          BIT_ULL(55)

+#define PM_MMAP_EXCLUSIVE      BIT_ULL(56)

 #define PM_FILE                        BIT_ULL(61)
 #define PM_SWAP                        BIT_ULL(62)
 #define PM_PRESENT             BIT_ULL(63)
 #define PM_FILE                        BIT_ULL(61)
 #define PM_SWAP                        BIT_ULL(62)
 #define PM_PRESENT             BIT_ULL(63)


@@ -1036,6 +1037,8 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
 
        if (page && !PageAnon(page))
                flags |= PM_FILE;
 
        if (page && !PageAnon(page))
                flags |= PM_FILE;

+       if (page && page_mapcount(page) == 1)
+               flags |= PM_MMAP_EXCLUSIVE;

        if (vma->vm_flags & VM_SOFTDIRTY)
                flags |= PM_SOFT_DIRTY;
 
        if (vma->vm_flags & VM_SOFTDIRTY)
                flags |= PM_SOFT_DIRTY;
 


@@ -1066,6 +1069,11 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
                 * This if-check is just to prepare for future implementation.
                 */
                if (pmd_present(pmd)) {
                 * This if-check is just to prepare for future implementation.
                 */
                if (pmd_present(pmd)) {

+                       struct page *page = pmd_page(pmd);
+
+                       if (page_mapcount(page) == 1)
+                               flags |= PM_MMAP_EXCLUSIVE;
+

                        flags |= PM_PRESENT;
                        if (pm->show_pfn)
                                frame = pmd_pfn(pmd) +
                        flags |= PM_PRESENT;
                        if (pm->show_pfn)
                                frame = pmd_pfn(pmd) +


@@ -1131,6 +1139,9 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask,
                if (!PageAnon(page))
                        flags |= PM_FILE;
 
                if (!PageAnon(page))
                        flags |= PM_FILE;
 

+               if (page_mapcount(page) == 1)
+                       flags |= PM_MMAP_EXCLUSIVE;
+

                flags |= PM_PRESENT;
                if (pm->show_pfn)
                        frame = pte_pfn(pte) +
                flags |= PM_PRESENT;
                if (pm->show_pfn)
                        frame = pte_pfn(pte) +


@@ -1163,7 +1174,8 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask,
  * Bits 0-4   swap type if swapped
  * Bits 5-54  swap offset if swapped
  * Bit  55    pte is soft-dirty (see Documentation/vm/soft-dirty.txt)
  * Bits 0-4   swap type if swapped
  * Bits 5-54  swap offset if swapped
  * Bit  55    pte is soft-dirty (see Documentation/vm/soft-dirty.txt)

- * Bits 56-60 zero
+ * Bit  56    page exclusively mapped
+ * Bits 57-60 zero

  * Bit  61    page is file-page or shared-anon
  * Bit  62    page swapped
  * Bit  63    page present
  * Bit  61    page is file-page or shared-anon
  * Bit  62    page swapped
  * Bit  63    page present

diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
index 603ec916716b34561e974e6195421675daba7802..7f73fa32a590b5f5177affb4b2e6df93dc3e2f2f 100644 (file)
--- a/tools/vm/page-types.c
+++ b/tools/vm/page-types.c
@@ -62,6 +62,7 @@
 #define PM_PFRAME_MASK         ((1LL << PM_PFRAME_BITS) - 1)
 #define PM_PFRAME(x)           ((x) & PM_PFRAME_MASK)
 #define PM_SOFT_DIRTY          (1ULL << 55)
 #define PM_PFRAME_MASK         ((1LL << PM_PFRAME_BITS) - 1)
 #define PM_PFRAME(x)           ((x) & PM_PFRAME_MASK)
 #define PM_SOFT_DIRTY          (1ULL << 55)

+#define PM_MMAP_EXCLUSIVE      (1ULL << 56)

 #define PM_FILE                        (1ULL << 61)
 #define PM_SWAP                        (1ULL << 62)
 #define PM_PRESENT             (1ULL << 63)
 #define PM_FILE                        (1ULL << 61)
 #define PM_SWAP                        (1ULL << 62)
 #define PM_PRESENT             (1ULL << 63)


@@ -91,6 +92,8 @@
 #define KPF_SLOB_FREE          49
 #define KPF_SLUB_FROZEN                50
 #define KPF_SLUB_DEBUG         51
 #define KPF_SLOB_FREE          49
 #define KPF_SLUB_FROZEN                50
 #define KPF_SLUB_DEBUG         51

+#define KPF_FILE               62
+#define KPF_MMAP_EXCLUSIVE     63

 
 #define KPF_ALL_BITS           ((uint64_t)~0ULL)
 #define KPF_HACKERS_BITS       (0xffffULL << 32)
 
 #define KPF_ALL_BITS           ((uint64_t)~0ULL)
 #define KPF_HACKERS_BITS       (0xffffULL << 32)


@@ -140,6 +143,9 @@ static const char * const page_flag_names[] = {
        [KPF_SLOB_FREE]         = "P:slob_free",
        [KPF_SLUB_FROZEN]       = "A:slub_frozen",
        [KPF_SLUB_DEBUG]        = "E:slub_debug",
        [KPF_SLOB_FREE]         = "P:slob_free",
        [KPF_SLUB_FROZEN]       = "A:slub_frozen",
        [KPF_SLUB_DEBUG]        = "E:slub_debug",

+
+       [KPF_FILE]              = "F:file",
+       [KPF_MMAP_EXCLUSIVE]    = "1:mmap_exclusive",

 };
 
 
 };
 
 


@@ -443,6 +449,10 @@ static uint64_t expand_overloaded_flags(uint64_t flags, uint64_t pme)
 
        if (pme & PM_SOFT_DIRTY)
                flags |= BIT(SOFTDIRTY);
 
        if (pme & PM_SOFT_DIRTY)
                flags |= BIT(SOFTDIRTY);

+       if (pme & PM_FILE)
+               flags |= BIT(FILE);
+       if (pme & PM_MMAP_EXCLUSIVE)
+               flags |= BIT(MMAP_EXCLUSIVE);

 
        return flags;
 }
 
        return flags;
 }