mm: introduce PageHuge() for testing huge/gigantic pages

A series of patches to enhance the /proc/pagemap interface and to add a
userspace executable which can be used to present the pagemap data.

Export 10 more flags to end users (and more for kernel developers):

        11. KPF_MMAP            (pseudo flag) memory mapped page
        12. KPF_ANON            (pseudo flag) memory mapped page (anonymous)
        13. KPF_SWAPCACHE       page is in swap cache
        14. KPF_SWAPBACKED      page is swap/RAM backed
        15. KPF_COMPOUND_HEAD   (*)
        16. KPF_COMPOUND_TAIL   (*)
        17. KPF_HUGE		hugeTLB pages
        18. KPF_UNEVICTABLE     page is in the unevictable LRU list
        19. KPF_HWPOISON        hardware detected corruption
        20. KPF_NOPAGE          (pseudo flag) no page frame at the address

        (*) For compound pages, exporting _both_ head/tail info enables
            users to tell where a compound page starts/ends, and its order.

a simple demo of the page-types tool

# ./page-types -h
page-types [options]
            -r|--raw                  Raw mode, for kernel developers
            -a|--addr    addr-spec    Walk a range of pages
            -b|--bits    bits-spec    Walk pages with specified bits
            -l|--list                 Show page details in ranges
            -L|--list-each            Show page details one by one
            -N|--no-summary           Don't show summay info
            -h|--help                 Show this usage message
addr-spec:
            N                         one page at offset N (unit: pages)
            N+M                       pages range from N to N+M-1
            N,M                       pages range from N to M-1
            N,                        pages range from N to end
            ,M                        pages range from 0 to M
bits-spec:
            bit1,bit2                 (flags & (bit1|bit2)) != 0
            bit1,bit2=bit1            (flags & (bit1|bit2)) == bit1
            bit1,~bit2                (flags & (bit1|bit2)) == bit1
            =bit1,bit2                flags == (bit1|bit2)
bit-names:
          locked              error         referenced           uptodate
           dirty                lru             active               slab
       writeback            reclaim              buddy               mmap
       anonymous          swapcache         swapbacked      compound_head
   compound_tail               huge        unevictable           hwpoison
          nopage           reserved(r)         mlocked(r)    mappedtodisk(r)
         private(r)       private_2(r)   owner_private(r)            arch(r)
        uncached(r)       readahead(o)       slob_free(o)     slub_frozen(o)
      slub_debug(o)
                                   (r) raw mode bits  (o) overloaded bits

# ./page-types
             flags      page-count       MB  symbolic-flags                     long-symbolic-flags
0x0000000000000000          487369     1903  _________________________________
0x0000000000000014               5        0  __R_D____________________________  referenced,dirty
0x0000000000000020               1        0  _____l___________________________  lru
0x0000000000000024              34        0  __R__l___________________________  referenced,lru
0x0000000000000028            3838       14  ___U_l___________________________  uptodate,lru
0x0001000000000028              48        0  ___U_l_______________________I___  uptodate,lru,readahead
0x000000000000002c            6478       25  __RU_l___________________________  referenced,uptodate,lru
0x000100000000002c              47        0  __RU_l_______________________I___  referenced,uptodate,lru,readahead
0x0000000000000040            8344       32  ______A__________________________  active
0x0000000000000060               1        0  _____lA__________________________  lru,active
0x0000000000000068             348        1  ___U_lA__________________________  uptodate,lru,active
0x0001000000000068              12        0  ___U_lA______________________I___  uptodate,lru,active,readahead
0x000000000000006c             988        3  __RU_lA__________________________  referenced,uptodate,lru,active
0x000100000000006c              48        0  __RU_lA______________________I___  referenced,uptodate,lru,active,readahead
0x0000000000004078               1        0  ___UDlA_______b__________________  uptodate,dirty,lru,active,swapbacked
0x000000000000407c              34        0  __RUDlA_______b__________________  referenced,uptodate,dirty,lru,active,swapbacked
0x0000000000000400             503        1  __________B______________________  buddy
0x0000000000000804               1        0  __R________M_____________________  referenced,mmap
0x0000000000000828            1029        4  ___U_l_____M_____________________  uptodate,lru,mmap
0x0001000000000828              43        0  ___U_l_____M_________________I___  uptodate,lru,mmap,readahead
0x000000000000082c             382        1  __RU_l_____M_____________________  referenced,uptodate,lru,mmap
0x000100000000082c              12        0  __RU_l_____M_________________I___  referenced,uptodate,lru,mmap,readahead
0x0000000000000868             192        0  ___U_lA____M_____________________  uptodate,lru,active,mmap
0x0001000000000868              12        0  ___U_lA____M_________________I___  uptodate,lru,active,mmap,readahead
0x000000000000086c             800        3  __RU_lA____M_____________________  referenced,uptodate,lru,active,mmap
0x000100000000086c              31        0  __RU_lA____M_________________I___  referenced,uptodate,lru,active,mmap,readahead
0x0000000000004878               2        0  ___UDlA____M__b__________________  uptodate,dirty,lru,active,mmap,swapbacked
0x0000000000001000             492        1  ____________a____________________  anonymous
0x0000000000005808               4        0  ___U_______Ma_b__________________  uptodate,mmap,anonymous,swapbacked
0x0000000000005868            2839       11  ___U_lA____Ma_b__________________  uptodate,lru,active,mmap,anonymous,swapbacked
0x000000000000586c              30        0  __RU_lA____Ma_b__________________  referenced,uptodate,lru,active,mmap,anonymous,swapbacked
             total          513968     2007

# ./page-types -r
             flags      page-count       MB  symbolic-flags                     long-symbolic-flags
0x0000000000000000          468002     1828  _________________________________
0x0000000100000000           19102       74  _____________________r___________  reserved
0x0000000000008000              41        0  _______________H_________________  compound_head
0x0000000000010000             188        0  ________________T________________  compound_tail
0x0000000000008014               1        0  __R_D__________H_________________  referenced,dirty,compound_head
0x0000000000010014               4        0  __R_D___________T________________  referenced,dirty,compound_tail
0x0000000000000020               1        0  _____l___________________________  lru
0x0000000800000024              34        0  __R__l__________________P________  referenced,lru,private
0x0000000000000028            3794       14  ___U_l___________________________  uptodate,lru
0x0001000000000028              46        0  ___U_l_______________________I___  uptodate,lru,readahead
0x0000000400000028              44        0  ___U_l_________________d_________  uptodate,lru,mappedtodisk
0x0001000400000028               2        0  ___U_l_________________d_____I___  uptodate,lru,mappedtodisk,readahead
0x000000000000002c            6434       25  __RU_l___________________________  referenced,uptodate,lru
0x000100000000002c              47        0  __RU_l_______________________I___  referenced,uptodate,lru,readahead
0x000000040000002c              14        0  __RU_l_________________d_________  referenced,uptodate,lru,mappedtodisk
0x000000080000002c              30        0  __RU_l__________________P________  referenced,uptodate,lru,private
0x0000000800000040            8124       31  ______A_________________P________  active,private
0x0000000000000040             219        0  ______A__________________________  active
0x0000000800000060               1        0  _____lA_________________P________  lru,active,private
0x0000000000000068             322        1  ___U_lA__________________________  uptodate,lru,active
0x0001000000000068              12        0  ___U_lA______________________I___  uptodate,lru,active,readahead
0x0000000400000068              13        0  ___U_lA________________d_________  uptodate,lru,active,mappedtodisk
0x0000000800000068              12        0  ___U_lA_________________P________  uptodate,lru,active,private
0x000000000000006c             977        3  __RU_lA__________________________  referenced,uptodate,lru,active
0x000100000000006c              48        0  __RU_lA______________________I___  referenced,uptodate,lru,active,readahead
0x000000040000006c               5        0  __RU_lA________________d_________  referenced,uptodate,lru,active,mappedtodisk
0x000000080000006c               3        0  __RU_lA_________________P________  referenced,uptodate,lru,active,private
0x0000000c0000006c               3        0  __RU_lA________________dP________  referenced,uptodate,lru,active,mappedtodisk,private
0x0000000c00000068               1        0  ___U_lA________________dP________  uptodate,lru,active,mappedtodisk,private
0x0000000000004078               1        0  ___UDlA_______b__________________  uptodate,dirty,lru,active,swapbacked
0x000000000000407c              34        0  __RUDlA_______b__________________  referenced,uptodate,dirty,lru,active,swapbacked
0x0000000000000400             538        2  __________B______________________  buddy
0x0000000000000804               1        0  __R________M_____________________  referenced,mmap
0x0000000000000828            1029        4  ___U_l_____M_____________________  uptodate,lru,mmap
0x0001000000000828              43        0  ___U_l_____M_________________I___  uptodate,lru,mmap,readahead
0x000000000000082c             382        1  __RU_l_____M_____________________  referenced,uptodate,lru,mmap
0x000100000000082c              12        0  __RU_l_____M_________________I___  referenced,uptodate,lru,mmap,readahead
0x0000000000000868             192        0  ___U_lA____M_____________________  uptodate,lru,active,mmap
0x0001000000000868              12        0  ___U_lA____M_________________I___  uptodate,lru,active,mmap,readahead
0x000000000000086c             800        3  __RU_lA____M_____________________  referenced,uptodate,lru,active,mmap
0x000100000000086c              31        0  __RU_lA____M_________________I___  referenced,uptodate,lru,active,mmap,readahead
0x0000000000004878               2        0  ___UDlA____M__b__________________  uptodate,dirty,lru,active,mmap,swapbacked
0x0000000000001000             492        1  ____________a____________________  anonymous
0x0000000000005008               2        0  ___U________a_b__________________  uptodate,anonymous,swapbacked
0x0000000000005808               4        0  ___U_______Ma_b__________________  uptodate,mmap,anonymous,swapbacked
0x000000000000580c               1        0  __RU_______Ma_b__________________  referenced,uptodate,mmap,anonymous,swapbacked
0x0000000000005868            2839       11  ___U_lA____Ma_b__________________  uptodate,lru,active,mmap,anonymous,swapbacked
0x000000000000586c              29        0  __RU_lA____Ma_b__________________  referenced,uptodate,lru,active,mmap,anonymous,swapbacked
             total          513968     2007

# ./page-types --raw --list --no-summary --bits reserved
offset  count   flags
0       15      _____________________r___________
31      4       _____________________r___________
159     97      _____________________r___________
4096    2067    _____________________r___________
6752    2390    _____________________r___________
9355    3       _____________________r___________
9728    14526   _____________________r___________

This patch:

Introduce PageHuge(), which identifies huge/gigantic pages by their
dedicated compound destructor functions.

Also move prep_compound_gigantic_page() to hugetlb.c and make
__free_pages_ok() non-static.

Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/proc/page.c b/fs/proc/page.c
index e998383..38dd88b 100644 (file)
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -6,6 +6,7 @@
 #include <linux/mmzone.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/hugetlb.h>
 #include <asm/uaccess.h>
 #include "internal.h"
 

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 03be7f2..a05a5ef 100644 (file)
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -11,6 +11,8 @@
 
 struct ctl_table;
 
+int PageHuge(struct page *page);
+
 static inline int is_vm_hugetlb_page(struct vm_area_struct *vma)
 {
        return vma->vm_flags & VM_HUGETLB;
@@ -61,6 +63,11 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
 
 #else /* !CONFIG_HUGETLB_PAGE */
 
+static inline int PageHuge(struct page *page)
+{
+       return 0;
+}
+
 static inline int is_vm_hugetlb_page(struct vm_area_struct *vma)
 {
        return 0;

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7b9b601..a56e6f3 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -578,41 +578,6 @@ static void free_huge_page(struct page *page)
                hugetlb_put_quota(mapping, 1);
 }
 
-/*
- * Increment or decrement surplus_huge_pages.  Keep node-specific counters
- * balanced by operating on them in a round-robin fashion.
- * Returns 1 if an adjustment was made.
- */
-static int adjust_pool_surplus(struct hstate *h, int delta)
-{
-       static int prev_nid;
-       int nid = prev_nid;
-       int ret = 0;
-
-       VM_BUG_ON(delta != -1 && delta != 1);
-       do {
-               nid = next_node(nid, node_online_map);
-               if (nid == MAX_NUMNODES)
-                       nid = first_node(node_online_map);
-
-               /* To shrink on this node, there must be a surplus page */
-               if (delta < 0 && !h->surplus_huge_pages_node[nid])
-                       continue;
-               /* Surplus cannot exceed the total number of pages */
-               if (delta > 0 && h->surplus_huge_pages_node[nid] >=
-                                               h->nr_huge_pages_node[nid])
-                       continue;
-
-               h->surplus_huge_pages += delta;
-               h->surplus_huge_pages_node[nid] += delta;
-               ret = 1;
-               break;
-       } while (nid != prev_nid);
-
-       prev_nid = nid;
-       return ret;
-}
-
 static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 {
        set_compound_page_dtor(page, free_huge_page);
@@ -623,6 +588,34 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
        put_page(page); /* free it into the hugepage allocator */
 }
 
+static void prep_compound_gigantic_page(struct page *page, unsigned long order)
+{
+       int i;
+       int nr_pages = 1 << order;
+       struct page *p = page + 1;
+
+       /* we rely on prep_new_huge_page to set the destructor */
+       set_compound_order(page, order);
+       __SetPageHead(page);
+       for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
+               __SetPageTail(p);
+               p->first_page = page;
+       }
+}
+
+int PageHuge(struct page *page)
+{
+       compound_page_dtor *dtor;
+
+       if (!PageCompound(page))
+               return 0;
+
+       page = compound_head(page);
+       dtor = get_compound_page_dtor(page);
+
+       return dtor == free_huge_page;
+}
+
 static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 {
        struct page *page;
@@ -1140,6 +1133,41 @@ static inline void try_to_free_low(struct hstate *h, unsigned long count)
 }
 #endif
 
+/*
+ * Increment or decrement surplus_huge_pages.  Keep node-specific counters
+ * balanced by operating on them in a round-robin fashion.
+ * Returns 1 if an adjustment was made.
+ */
+static int adjust_pool_surplus(struct hstate *h, int delta)
+{
+       static int prev_nid;
+       int nid = prev_nid;
+       int ret = 0;
+
+       VM_BUG_ON(delta != -1 && delta != 1);
+       do {
+               nid = next_node(nid, node_online_map);
+               if (nid == MAX_NUMNODES)
+                       nid = first_node(node_online_map);
+
+               /* To shrink on this node, there must be a surplus page */
+               if (delta < 0 && !h->surplus_huge_pages_node[nid])
+                       continue;
+               /* Surplus cannot exceed the total number of pages */
+               if (delta > 0 && h->surplus_huge_pages_node[nid] >=
+                                               h->nr_huge_pages_node[nid])
+                       continue;
+
+               h->surplus_huge_pages += delta;
+               h->surplus_huge_pages_node[nid] += delta;
+               ret = 1;
+               break;
+       } while (nid != prev_nid);
+
+       prev_nid = nid;
+       return ret;
+}
+
 #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
 static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count)
 {

diff --git a/mm/internal.h b/mm/internal.h
index 4b1672a..b4ac332 100644 (file)
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -16,9 +16,6 @@
 void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
                unsigned long floor, unsigned long ceiling);
 
-extern void prep_compound_page(struct page *page, unsigned long order);
-extern void prep_compound_gigantic_page(struct page *page, unsigned long order);
-
 static inline void set_page_count(struct page *page, int v)
 {
        atomic_set(&page->_count, v);
@@ -51,6 +48,8 @@ extern void putback_lru_page(struct page *page);
  */
 extern unsigned long highest_memmap_pfn;
 extern void __free_pages_bootmem(struct page *page, unsigned int order);
+extern void prep_compound_page(struct page *page, unsigned long order);
+
 
 /*
  * function for dealing with page's order in buddy system.

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8ca06d8..131655c 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -300,23 +300,6 @@ void prep_compound_page(struct page *page, unsigned long order)
        }
 }
 
-#ifdef CONFIG_HUGETLBFS
-void prep_compound_gigantic_page(struct page *page, unsigned long order)
-{
-       int i;
-       int nr_pages = 1 << order;
-       struct page *p = page + 1;
-
-       set_compound_page_dtor(page, free_compound_page);
-       set_compound_order(page, order);
-       __SetPageHead(page);
-       for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
-               __SetPageTail(p);
-               p->first_page = page;
-       }
-}
-#endif
-
 static int destroy_compound_page(struct page *page, unsigned long order)
 {
        int i;