Re: [PATCH] Fix OOPS in mmap_region() when merging adjacent VM_LOCKED file segments

[Lee Schermerhorn <Lee.Schermerhorn@hp.com>]

On Sat, 2009-01-31 at 12:35 +0000, Hugh Dickins wrote:
<snip>
> I have by now recalled why I chose to play those VM_ACCOUNT games:
> 	/* We set VM_ACCOUNT in a shared mapping's vm_flags, to inform
> 	 * shmem_zero_setup (perhaps called through /dev/zero's ->mmap)
> 	 * that memory reservation must be checked; but that reservation
> 	 * belongs to shared memory object, not to vma: so now clear it.
> We need a way to communicate not-MAP_NORESERVE to shmem.c, and we don't
> just need it in the explicit shmem_zero_setup() case, we also need it
> for the (probably rare nowadays) case when mmap() is working on file
          ^^^^^^^^^^^^^^^^^^^^^^^^
> /dev/zero (drivers/char/mem.c mmap_zero()), rather than using MAP_ANON.


This reminded me of something I'd seen recently looking
at /proc/<pid>/[numa]_maps for <a large commercial database> on
Linux/x86_64: 

2adadf247000-2adadf2b2000 rwxp 2adadf247000 00:00 0
2adadf2b2000-2adadf2b3000 rwxs 00000000 68:31 55362966                   <some file != /dev/zero>
2adadf2b9000-2adadf2c0000 rwxp 00000000 00:0e 4072                       /dev/zero
2adadf2c0000-2adadf2d0000 rwxp 00000000 00:0e 4072                       /dev/zero
2adadf2d0000-2adadf2e0000 rwxp 00000000 00:0e 4072                       /dev/zero
2adadf2e0000-2adadf2f0000 rwxp 00000000 00:0e 4072                       /dev/zero
2adadf2f0000-2adadf300000 rwxp 00000000 00:0e 4072                       /dev/zero
2adadf300000-2adadf310000 rwxp 00000000 00:0e 4072                       /dev/zero
2adadf310000-2adadf320000 rwxp 00000000 00:0e 4072                       /dev/zero
2adadf320000-2adadf330000 rwxp 00000000 00:0e 4072                       /dev/zero
2adadf330000-2adadf339000 rwxp 00077000 00:0e 4072                       /dev/zero
2adadf353000-2adadf35a000 r-xp 00000000 69:02 1228822                    /lib64/libnss_compat-2.4.so
2adadf35a000-2adadf459000 ---p 00007000 69:02 1228822                    /lib64/libnss_compat-2.4.so
2adadf459000-2adadf45b000 rwxp 00006000 69:02 1228822                    /lib64/libnss_compat-2.4.so
2adadf45b000-2adadf464000 r-xp 00000000 69:02 1228830                    /lib64/libnss_nis-2.4.so
2adadf464000-2adadf564000 ---p 00009000 69:02 1228830                    /lib64/libnss_nis-2.4.so
2adadf564000-2adadf566000 rwxp 00009000 69:02 1228830                    /lib64/libnss_nis-2.4.so
2adadf566000-2adadf570000 r-xp 00000000 69:02 1228826                    /lib64/libnss_files-2.4.so
2adadf570000-2adadf66f000 ---p 0000a000 69:02 1228826                    /lib64/libnss_files-2.4.so
2adadf66f000-2adadf671000 rwxp 00009000 69:02 1228826                    /lib64/libnss_files-2.4.so
2adadf671000-2adadf681000 rwxp 00000000 00:0e 4072                       /dev/zero
2adadf681000-2adadf6a1000 rwxp 00000000 00:0e 4072                       /dev/zero
2adadf6a1000-2adadf6b1000 rwxp 00000000 00:0e 4072                       /dev/zero
2adadf6b1000-2adadf6c1000 rwxp 00000000 00:0e 4072                       /dev/zero
2adadf6c1000-2adadf6d1000 rwxp 00000000 00:0e 4072                       /dev/zero
2adadf6d1000-2adadf6e1000 rwxp 00000000 00:0e 4072                       /dev/zero
2adadf6e1000-2adadf6f1000 rwxp 00000000 00:0e 4072                       /dev/zero
2adadf6f1000-2adadf701000 rwxp 00000000 00:0e 4072                       /dev/zero
2adadf701000-2adadf711000 rwxp 00000000 00:0e 4072                       /dev/zero
2adadf711000-2adadf721000 rwxp 00000000 00:0e 4072                       /dev/zero
2adadf721000-2adadf731000 rwxp 00000000 00:0e 4072                       /dev/zero
2adadf731000-2adadf741000 rwxp 00000000 00:0e 4072                       /dev/zero

<and so on, for another 90 lines until>

7fffcdd36000-7fffcdd4e000 rwxp 7fffcdd36000 00:00 0                      [stack]
ffffffffff600000-ffffffffffe00000 ---p 00000000 00:00 0                  [vdso]

For portability between Linux and various Unix-like systems that don't
support MAP_ANON*, perhaps?

Anyway, from the addresses and permissions, these all look potentially
mergeable.  The offset is preventing merging, right?  I guess that's one
of the downsides of mapping /dev/zero rather than using MAP_ANONYMOUS?

Makes one wonder whether it would be worthwhile [not to mention
possible] to rework mmap_zero() to mimic MAP_ANONYMOUS...

Lee