Setting TIF_IA32 in load_aout_binary() used to be enough; these days
TASK_SIZE is controlled by TIF_ADDR32 and that one doesn't get set
there.  Switch to use of set_personality_ia32()...
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This continues the theme started with vm_brk() and vm_munmap():
vm_mmap() does the same thing as do_mmap(), but additionally does the
required VM locking.

This uninlines (and rewrites it to be clearer) do_mmap(), which sadly
duplicates it in mm/mmap.c and mm/nommu.c.  But that way we don't have
to export our internal do_mmap_pgoff() function.

Some day we hopefully don't have to export do_mmap() either, if all
modular users can become the simpler vm_mmap() instead.  We're actually
very close to that already, with the notable exception of the (broken)
use in i810, and a couple of stragglers in binfmt_elf.
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

It does the same thing as "do_brk()", except it handles the VM locking
too.

It turns out that all external callers want that anyway, so we can make
do_brk() static to just mm/mmap.c while at it.
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Disintegrate asm/system.h for X86.
Signed-off-by: NDavid Howells <dhowells@redhat.com>
Acked-by: NH. Peter Anvin <hpa@zytor.com>
cc: x86@kernel.org

Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Just don't pass NULL to it - nobody does, anyway.
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This patch simply follows the same practice as for setting the TIF_IA32 flag.
In particular, an mm is marked as holding 32-bit tasks when a 32-bit binary is
exec'ed.  Both ELF and a.out formats are updated.
Signed-off-by: NStephen Wilson <wilsons@start.ca>
Reviewed-by: NMichel Lespinasse <walken@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

akiphie points out that a.out core-dumps have that odd task struct
dumping that was never used and was never really a good idea (it goes
back into the mists of history, probably the original core-dumping
code).  Just remove it.

Also do the access_ok() check on dump_write().  It probably doesn't
matter (since normal filesystems all seem to do it anyway), but he
points out that it's normally done by the VFS layer, so ...

[ I suspect that we should possibly do "vfs_write()" instead of
  calling ->write directly.  That also does the whole fsnotify and write
  statistics thing, which may or may not be a good idea. ]

And just to be anal, do this all for the x86-64 32-bit a.out emulation
code too, even though it's not enabled (and won't currently even
compile)
Reported-by: Nakiphie <akiphie@lavabit.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h

percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files.  percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.

percpu.h -> slab.h dependency is about to be removed.  Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability.  As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.

  http://userweb.kernel.org/~tj/misc/slabh-sweep.py

The script does the followings.

* Scan files for gfp and slab usages and update includes such that
  only the necessary includes are there.  ie. if only gfp is used,
  gfp.h, if slab is used, slab.h.

* When the script inserts a new include, it looks at the include
  blocks and try to put the new include such that its order conforms
  to its surrounding.  It's put in the include block which contains
  core kernel includes, in the same order that the rest are ordered -
  alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
  doesn't seem to be any matching order.

* If the script can't find a place to put a new include (mostly
  because the file doesn't have fitting include block), it prints out
  an error message indicating which .h file needs to be added to the
  file.

The conversion was done in the following steps.

1. The initial automatic conversion of all .c files updated slightly
   over 4000 files, deleting around 700 includes and adding ~480 gfp.h
   and ~3000 slab.h inclusions.  The script emitted errors for ~400
   files.

2. Each error was manually checked.  Some didn't need the inclusion,
   some needed manual addition while adding it to implementation .h or
   embedding .c file was more appropriate for others.  This step added
   inclusions to around 150 files.

3. The script was run again and the output was compared to the edits
   from #2 to make sure no file was left behind.

4. Several build tests were done and a couple of problems were fixed.
   e.g. lib/decompress_*.c used malloc/free() wrappers around slab
   APIs requiring slab.h to be added manually.

5. The script was run on all .h files but without automatically
   editing them as sprinkling gfp.h and slab.h inclusions around .h
   files could easily lead to inclusion dependency hell.  Most gfp.h
   inclusion directives were ignored as stuff from gfp.h was usually
   wildly available and often used in preprocessor macros.  Each
   slab.h inclusion directive was examined and added manually as
   necessary.

6. percpu.h was updated not to include slab.h.

7. Build test were done on the following configurations and failures
   were fixed.  CONFIG_GCOV_KERNEL was turned off for all tests (as my
   distributed build env didn't work with gcov compiles) and a few
   more options had to be turned off depending on archs to make things
   build (like ipr on powerpc/64 which failed due to missing writeq).

   * x86 and x86_64 UP and SMP allmodconfig and a custom test config.
   * powerpc and powerpc64 SMP allmodconfig
   * sparc and sparc64 SMP allmodconfig
   * ia64 SMP allmodconfig
   * s390 SMP allmodconfig
   * alpha SMP allmodconfig
   * um on x86_64 SMP allmodconfig

8. percpu.h modifications were reverted so that it could be applied as
   a separate patch and serve as bisection point.

Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: NTejun Heo <tj@kernel.org>
Guess-its-ok-by: NChristoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>

Do not set current->mm->mmap to NULL in 32-bit emulation on 64-bit
load_aout_binary after flush_old_exec as it would destroy already
set brpm mapping with arguments.

Introduced by b6a2fea3
mm: variable length argument support
where the argument mapping in bprm was added.

[ hpa: this is a regression from 2.6.22... time to kill a.out? ]
Signed-off-by: NJiri Slaby <jslaby@suse.cz>
LKML-Reference: <1265831716-7668-1-git-send-email-jslaby@suse.cz>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ollie Wild <aaw@google.com>
Cc: x86@kernel.org
Cc: <stable@kernel.org>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

Now that the previous commit made it possible to do the personality
setting at the point of no return, we do just that for ELF binaries.
And suddenly all the reasons for that insane TIF_ABI_PENDING bit go
away, and we can just make SET_PERSONALITY() just do the obvious thing
for a 32-bit compat process.

Everything becomes much more straightforward this way.
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>
Cc: stable@kernel.org
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

'flush_old_exec()' is the point of no return when doing an execve(), and
it is pretty badly misnamed.  It doesn't just flush the old executable
environment, it also starts up the new one.

Which is very inconvenient for things like setting up the new
personality, because we want the new personality to affect the starting
of the new environment, but at the same time we do _not_ want the new
personality to take effect if flushing the old one fails.

As a result, the x86-64 '32-bit' personality is actually done using this
insane "I'm going to change the ABI, but I haven't done it yet" bit
(TIF_ABI_PENDING), with SET_PERSONALITY() not actually setting the
personality, but just the "pending" bit, so that "flush_thread()" can do
the actual personality magic.

This patch in no way changes any of that insanity, but it does split the
'flush_old_exec()' function up into a preparatory part that can fail
(still called flush_old_exec()), and a new part that will actually set
up the new exec environment (setup_new_exec()).  All callers are changed
to trivially comply with the new world order.
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>
Cc: stable@kernel.org
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Make sure compiler won't do weird things with limits.  Fetching them
twice may return 2 different values after writable limits are
implemented.

We can either use rlimit helpers added in
3e10e716 or ACCESS_ONCE if not
applicable; this patch uses the helpers.
Signed-off-by: NJiri Slaby <jslaby@suse.cz>
LKML-Reference: <1264609942-24621-1-git-send-email-jslaby@suse.cz>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

Make execve() take advantage of copy-on-write credentials, allowing it to set
up the credentials in advance, and then commit the whole lot after the point
of no return.

This patch and the preceding patches have been tested with the LTP SELinux
testsuite.

This patch makes several logical sets of alteration:

 (1) execve().

     The credential bits from struct linux_binprm are, for the most part,
     replaced with a single credentials pointer (bprm->cred).  This means that
     all the creds can be calculated in advance and then applied at the point
     of no return with no possibility of failure.

     I would like to replace bprm->cap_effective with:

	cap_isclear(bprm->cap_effective)

     but this seems impossible due to special behaviour for processes of pid 1
     (they always retain their parent's capability masks where normally they'd
     be changed - see cap_bprm_set_creds()).

     The following sequence of events now happens:

     (a) At the start of do_execve, the current task's cred_exec_mutex is
     	 locked to prevent PTRACE_ATTACH from obsoleting the calculation of
     	 creds that we make.

     (a) prepare_exec_creds() is then called to make a copy of the current
     	 task's credentials and prepare it.  This copy is then assigned to
     	 bprm->cred.

  	 This renders security_bprm_alloc() and security_bprm_free()
     	 unnecessary, and so they've been removed.

     (b) The determination of unsafe execution is now performed immediately
     	 after (a) rather than later on in the code.  The result is stored in
     	 bprm->unsafe for future reference.

     (c) prepare_binprm() is called, possibly multiple times.

     	 (i) This applies the result of set[ug]id binaries to the new creds
     	     attached to bprm->cred.  Personality bit clearance is recorded,
     	     but now deferred on the basis that the exec procedure may yet
     	     fail.

         (ii) This then calls the new security_bprm_set_creds().  This should
	     calculate the new LSM and capability credentials into *bprm->cred.

	     This folds together security_bprm_set() and parts of
	     security_bprm_apply_creds() (these two have been removed).
	     Anything that might fail must be done at this point.

         (iii) bprm->cred_prepared is set to 1.

	     bprm->cred_prepared is 0 on the first pass of the security
	     calculations, and 1 on all subsequent passes.  This allows SELinux
	     in (ii) to base its calculations only on the initial script and
	     not on the interpreter.

     (d) flush_old_exec() is called to commit the task to execution.  This
     	 performs the following steps with regard to credentials:

	 (i) Clear pdeath_signal and set dumpable on certain circumstances that
	     may not be covered by commit_creds().

         (ii) Clear any bits in current->personality that were deferred from
             (c.i).

     (e) install_exec_creds() [compute_creds() as was] is called to install the
     	 new credentials.  This performs the following steps with regard to
     	 credentials:

         (i) Calls security_bprm_committing_creds() to apply any security
             requirements, such as flushing unauthorised files in SELinux, that
             must be done before the credentials are changed.

	     This is made up of bits of security_bprm_apply_creds() and
	     security_bprm_post_apply_creds(), both of which have been removed.
	     This function is not allowed to fail; anything that might fail
	     must have been done in (c.ii).

         (ii) Calls commit_creds() to apply the new credentials in a single
             assignment (more or less).  Possibly pdeath_signal and dumpable
             should be part of struct creds.

	 (iii) Unlocks the task's cred_replace_mutex, thus allowing
	     PTRACE_ATTACH to take place.

         (iv) Clears The bprm->cred pointer as the credentials it was holding
             are now immutable.

         (v) Calls security_bprm_committed_creds() to apply any security
             alterations that must be done after the creds have been changed.
             SELinux uses this to flush signals and signal handlers.

     (f) If an error occurs before (d.i), bprm_free() will call abort_creds()
     	 to destroy the proposed new credentials and will then unlock
     	 cred_replace_mutex.  No changes to the credentials will have been
     	 made.

 (2) LSM interface.

     A number of functions have been changed, added or removed:

     (*) security_bprm_alloc(), ->bprm_alloc_security()
     (*) security_bprm_free(), ->bprm_free_security()

     	 Removed in favour of preparing new credentials and modifying those.

     (*) security_bprm_apply_creds(), ->bprm_apply_creds()
     (*) security_bprm_post_apply_creds(), ->bprm_post_apply_creds()

     	 Removed; split between security_bprm_set_creds(),
     	 security_bprm_committing_creds() and security_bprm_committed_creds().

     (*) security_bprm_set(), ->bprm_set_security()

     	 Removed; folded into security_bprm_set_creds().

     (*) security_bprm_set_creds(), ->bprm_set_creds()

     	 New.  The new credentials in bprm->creds should be checked and set up
     	 as appropriate.  bprm->cred_prepared is 0 on the first call, 1 on the
     	 second and subsequent calls.

     (*) security_bprm_committing_creds(), ->bprm_committing_creds()
     (*) security_bprm_committed_creds(), ->bprm_committed_creds()

     	 New.  Apply the security effects of the new credentials.  This
     	 includes closing unauthorised files in SELinux.  This function may not
     	 fail.  When the former is called, the creds haven't yet been applied
     	 to the process; when the latter is called, they have.

 	 The former may access bprm->cred, the latter may not.

 (3) SELinux.

     SELinux has a number of changes, in addition to those to support the LSM
     interface changes mentioned above:

     (a) The bprm_security_struct struct has been removed in favour of using
     	 the credentials-under-construction approach.

     (c) flush_unauthorized_files() now takes a cred pointer and passes it on
     	 to inode_has_perm(), file_has_perm() and dentry_open().
Signed-off-by: NDavid Howells <dhowells@redhat.com>
Acked-by: NJames Morris <jmorris@namei.org>
Acked-by: NSerge Hallyn <serue@us.ibm.com>
Signed-off-by: NJames Morris <jmorris@namei.org>

Use savesegment and loadsegment consistently in ia32 compat code.
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

This moves all the ptrace hooks related to exec into tracehook.h inlines.

This also lifts the calls for tracing out of the binfmt load_binary hooks
into search_binary_handler() after it calls into the binfmt module.  This
change has no effect, since all the binfmt modules' load_binary functions
did the call at the end on success, and now search_binary_handler() does
it immediately after return if successful.  We consolidate the repeated
code, and binfmt modules no longer need to import ptrace_notify().
Signed-off-by: NRoland McGrath <roland@redhat.com>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Reviewed-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

struct user.u_ar0 is defined to contain a pointer offset on all
architectures in which it is defined (all architectures which define an
a.out format except SPARC.) However, it has a pointer type in the headers,
which is pointless -- <asm/user.h> is not exported to userspace, and it
just makes the code messy.

Redefine the field as "unsigned long" (which is the same size as a pointer
on all Linux architectures) and change the setting code to user offsetof()
instead of hand-coded arithmetic.

Cc: Linux Arch Mailing List <linux-arch@vger.kernel.org>
Cc: Bryan Wu <bryan.wu@analog.com>
Cc: Roman Zippel <zippel@linux-m68k.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Lennert Buytenhek <kernel@wantstofly.org>
Cc: Håvard Skinnemoen <hskinnemoen@atmel.com>
Cc: Mikael Starvik <starvik@axis.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Hirokazu Takata <takata@linux-m32r.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The functions time_before, time_before_eq, time_after, and time_after_eq
are more robust for comparing jiffies against other values.

A simplified version of the semantic patch making this change is as follows:
(http://www.emn.fr/x-info/coccinelle/)

// <smpl>
@ change_compare_np @
expression E;
@@

(
- jiffies <= E
+ time_before_eq(jiffies,E)
|
- jiffies >= E
+ time_after_eq(jiffies,E)
|
- jiffies < E
+ time_before(jiffies,E)
|
- jiffies > E
+ time_after(jiffies,E)
)

@ include depends on change_compare_np @
@@

#include <linux/jiffies.h>

@ no_include depends on !include && change_compare_np @
@@

  #include <linux/...>
+ #include <linux/jiffies.h>
// </smpl>

[ mingo@elte.hu: merge to x86.git ]
Signed-off-by: NJulia Lawall <julia@diku.dk>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

We have a lot of code which differs only by the naming of specific
members of structures that contain registers.  In order to enable
additional unifications, this patch drops the e- or r- size prefix
from the register names in struct pt_regs, and drops the x- prefixes
for segment registers on the 32-bit side.

This patch also performs the equivalent renames in some additional
places that might be candidates for unification in the future.
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

White space and coding style clenaup.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Previously the data from before the exec was kept in there. Zero
them instead.

[ tglx: arch/x86 adaptation ]
Signed-off-by: NAndi Kleen <ak@suse.de>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

For some time /proc/sys/kernel/core_pattern has been able to set its output
destination as a pipe, allowing a user space helper to receive and
intellegently process a core.  This infrastructure however has some
shortcommings which can be enhanced.  Specifically:

1) The coredump code in the kernel should ignore RLIMIT_CORE limitation
   when core_pattern is a pipe, since file system resources are not being
   consumed in this case, unless the user application wishes to save the core,
   at which point the app is restricted by usual file system limits and
   restrictions.

2) The core_pattern code should be able to parse and pass options to the
   user space helper as an argv array.  The real core limit of the uid of the
   crashing proces should also be passable to the user space helper (since it
   is overridden to zero when called).

3) Some miscellaneous bugs need to be cleaned up (specifically the
   recognition of a recursive core dump, should the user mode helper itself
   crash.  Also, the core dump code in the kernel should not wait for the user
   mode helper to exit, since the same context is responsible for writing to
   the pipe, and a read of the pipe by the user mode helper will result in a
   deadlock.

This patch:

Remove the check of RLIMIT_CORE if core_pattern is a pipe.  In the event that
core_pattern is a pipe, the entire core will be fed to the user mode helper.
Signed-off-by: NNeil Horman <nhorman@tuxdriver.com>
Cc: <martin.pitt@ubuntu.com>
Cc: <wwoods@redhat.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Remove the arg+env limit of MAX_ARG_PAGES by copying the strings directly from
the old mm into the new mm.

We create the new mm before the binfmt code runs, and place the new stack at
the very top of the address space.  Once the binfmt code runs and figures out
where the stack should be, we move it downwards.

It is a bit peculiar in that we have one task with two mm's, one of which is
inactive.

[a.p.zijlstra@chello.nl: limit stack size]
Signed-off-by: NOllie Wild <aaw@google.com>
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: <linux-arch@vger.kernel.org>
Cc: Hugh Dickins <hugh@veritas.com>
[bunk@stusta.de: unexport bprm_mm_init]
Signed-off-by: NAdrian Bunk <bunk@stusta.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Fix

linux/arch/x86_64/ia32/ia32_aout.c: In function ‘create_aout_tables’:
linux/arch/x86_64/ia32/ia32_aout.c:244: warning: cast from pointer to integer of different size
linux/arch/x86_64/ia32/ia32_aout.c:253: warning: cast from pointer to integer of different size

with gcc 4.3
Signed-off-by: NAndi Kleen <ak@suse.de>

Change all the uses of f_{dentry,vfsmnt} to f_path.{dentry,mnt} in the x86_64
arch code.
Signed-off-by: NJosef "Jeff" Sipek <jsipek@cs.sunysb.edu>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Signed-off-by: NAndi Kleen <ak@suse.de>

Signed-off-by: NAndi Kleen <ak@suse.de>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

How is anon_rss initialized?  In dup_mmap, and by mm_alloc's memset; but
that's not so good if an mm_counter_t is a special type.  And how is rss
initialized?  By set_mm_counter, all over the place.  Come on, we just need to
initialize them both at once by set_mm_counter in mm_init (which follows the
memcpy when forking).
Signed-off-by: NHugh Dickins <hugh@veritas.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

turn many #if $undefined_string into #ifdef $undefined_string to fix some
warnings after -Wno-def was added to global CFLAGS
Signed-off-by: NOlaf Hering <olh@suse.de>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Ingo recently introduced a great speedup for allocating new mmaps using the
free_area_cache pointer which boosts the specweb SSL benchmark by 4-5% and
causes huge performance increases in thread creation.

The downside of this patch is that it does lead to fragmentation in the
mmap-ed areas (visible via /proc/self/maps), such that some applications
that work fine under 2.4 kernels quickly run out of memory on any 2.6
kernel.

The problem is twofold:

  1) the free_area_cache is used to continue a search for memory where
     the last search ended.  Before the change new areas were always
     searched from the base address on.

     So now new small areas are cluttering holes of all sizes
     throughout the whole mmap-able region whereas before small holes
     tended to close holes near the base leaving holes far from the base
     large and available for larger requests.

  2) the free_area_cache also is set to the location of the last
     munmap-ed area so in scenarios where we allocate e.g.  five regions of
     1K each, then free regions 4 2 3 in this order the next request for 1K
     will be placed in the position of the old region 3, whereas before we
     appended it to the still active region 1, placing it at the location
     of the old region 2.  Before we had 1 free region of 2K, now we only
     get two free regions of 1K -> fragmentation.

The patch addresses thes issues by introducing yet another cache descriptor
cached_hole_size that contains the largest known hole size below the
current free_area_cache.  If a new request comes in the size is compared
against the cached_hole_size and if the request can be filled with a hole
below free_area_cache the search is started from the base instead.

The results look promising: Whereas 2.6.12-rc4 fragments quickly and my
(earlier posted) leakme.c test program terminates after 50000+ iterations
with 96 distinct and fragmented maps in /proc/self/maps it performs nicely
(as expected) with thread creation, Ingo's test_str02 with 20000 threads
requires 0.7s system time.

Taking out Ingo's patch (un-patch available per request) by basically
deleting all mentions of free_area_cache from the kernel and starting the
search for new memory always at the respective bases we observe: leakme
terminates successfully with 11 distinctive hardly fragmented areas in
/proc/self/maps but thread creating is gringdingly slow: 30+s(!) system
time for Ingo's test_str02 with 20000 threads.

Now - drumroll ;-) the appended patch works fine with leakme: it ends with
only 7 distinct areas in /proc/self/maps and also thread creation seems
sufficiently fast with 0.71s for 20000 threads.
Signed-off-by: NWolfgang Wander <wwc@rentec.com>
Credit-to: "Richard Purdie" <rpurdie@rpsys.net>
Signed-off-by: NKen Chen <kenneth.w.chen@intel.com>
Acked-by: Ingo Molnar <mingo@elte.hu> (partly)
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.

Let it rip!