linux.git/ipc/namespace.c, branch v4.14-rc4

ipc: optimize semget/shmget/msgget for lots of keys

2017-09-09T01:26:51+00:00

ipc_findkey() used to scan all objects to look for the wanted key.  This
is slow when using a high number of keys.  This change adds an rhashtable
of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n).

This change gives a 865% improvement of benchmark reaim.jobs_per_min on a
56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1]

Other (more micro) benchmark results, by the author: On an i5 laptop, the
following loop executed right after a reboot took, without and with this
change:

    for (int i = 0, k=0x424242; i < KEYS; ++i)
        semget(k++, 1, IPC_CREAT | 0600);

                 total       total          max single  max single
   KEYS        without        with        call without   call with

      1            3.5         4.9   Âµs            3.5         4.9
     10            7.6         8.6   Âµs            3.7         4.7
     32           16.2        15.9   Âµs            4.3         5.3
    100           72.9        41.8   Âµs            3.7         4.7
   1000        5,630.0       502.0   Âµs             *           *
  10000    1,340,000.0     7,240.0   Âµs             *           *
  31900   17,600,000.0    22,200.0   Âµs             *           *

 *: unreliable measure: high variance

The duration for a lookup-only usage was obtained by the same loop once
the keys are present:

                 total       total          max single  max single
   KEYS        without        with        call without   call with

      1            2.1         2.5   Âµs            2.1         2.5
     10            4.5         4.8   Âµs            2.2         2.3
     32           13.0        10.8   Âµs            2.3         2.8
    100           82.9        25.1   Âµs             *          2.3
   1000        5,780.0       217.0   Âµs             *           *
  10000    1,470,000.0     2,520.0   Âµs             *           *
  31900   17,400,000.0     7,810.0   Âµs             *           *

Finally, executing each semget() in a new process gave, when still
summing only the durations of these syscalls:

creation:
                 total       total
   KEYS        without        with

      1            3.7         5.0   Âµs
     10           32.9        36.7   Âµs
     32          125.0       109.0   Âµs
    100          523.0       353.0   Âµs
   1000       20,300.0     3,280.0   Âµs
  10000    2,470,000.0    46,700.0   Âµs
  31900   27,800,000.0   219,000.0   Âµs

lookup-only:
                 total       total
   KEYS        without        with

      1            2.5         2.7   Âµs
     10           25.4        24.4   Âµs
     32          106.0        72.6   Âµs
    100          591.0       352.0   Âµs
   1000       22,400.0     2,250.0   Âµs
  10000    2,510,000.0    25,700.0   Âµs
  31900   28,200,000.0   115,000.0   Âµs

[1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop

Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix
Signed-off-by: Guillaume Knispel 
Reviewed-by: Marc Pardo 
Cc: Davidlohr Bueso 
Cc: Kees Cook 
Cc: Manfred Spraul 
Cc: Alexey Dobriyan 
Cc: "Eric W. Biederman" 
Cc: "Peter Zijlstra (Intel)" 
Cc: Ingo Molnar 
Cc: Sebastian Andrzej Siewior 
Cc: Serge Hallyn 
Cc: Andrey Vagin 
Cc: Guillaume Knispel 
Cc: Marc Pardo 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

ipc: convert ipc_namespace.count from atomic_t to refcount_t

2017-09-09T01:26:51+00:00

refcount_t type and corresponding API should be used instead of atomic_t
when the variable is used as a reference counter.  This allows to avoid
accidental refcounter overflows that might lead to use-after-free
situations.

Link: http://lkml.kernel.org/r/1499417992-3238-2-git-send-email-elena.reshetova@intel.com
Signed-off-by: Elena Reshetova 
Signed-off-by: Hans Liljestrand 
Signed-off-by: Kees Cook 
Signed-off-by: David Windsor 
Cc: Peter Zijlstra 
Cc: Greg Kroah-Hartman 
Cc: "Eric W. Biederman" 
Cc: Ingo Molnar 
Cc: Alexey Dobriyan 
Cc: Serge Hallyn 
Cc: 
Cc: Davidlohr Bueso 
Cc: Manfred Spraul 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

sched/headers: Prepare to move the task_lock()/unlock() APIs to

2017-03-02T07:42:38+00:00

But first update the code that uses these facilities with the
new header.

Acked-by: Linus Torvalds 
Cc: Mike Galbraith 
Cc: Peter Zijlstra 
Cc: Thomas Gleixner 
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar

sched/headers: Prepare to remove inclusion from

2017-03-02T07:42:31+00:00

Add #include  dependencies to all .c files rely on sched.h
doing that for them.

Note that even if the count where we need to add extra headers seems high,
it's still a net win, because  is included in over
2,200 files ...

Acked-by: Linus Torvalds 
Cc: Mike Galbraith 
Cc: Peter Zijlstra 
Cc: Thomas Gleixner 
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar

Merge branch 'nsfs-ioctls' into HEAD

2016-09-23T01:00:36+00:00

From: Andrey Vagin 

Each namespace has an owning user namespace and now there is not way
to discover these relationships.

Pid and user namepaces are hierarchical. There is no way to discover
parent-child relationships too.

Why we may want to know relationships between namespaces?

One use would be visualization, in order to understand the running
system.  Another would be to answer the question: what capability does
process X have to perform operations on a resource governed by namespace
Y?

One more use-case (which usually called abnormal) is checkpoint/restart.
In CRIU we are going to dump and restore nested namespaces.

There [1] was a discussion about which interface to choose to determing
relationships between namespaces.

Eric suggested to add two ioctl-s [2]:
> Grumble, Grumble.  I think this may actually a case for creating ioctls
> for these two cases.  Now that random nsfs file descriptors are bind
> mountable the original reason for using proc files is not as pressing.
>
> One ioctl for the user namespace that owns a file descriptor.
> One ioctl for the parent namespace of a namespace file descriptor.

Here is an implementaions of these ioctl-s.

$ man man7/namespaces.7
...
Since  Linux  4.X,  the  following  ioctl(2)  calls are supported for
namespace file descriptors.  The correct syntax is:

      fd = ioctl(ns_fd, ioctl_type);

where ioctl_type is one of the following:

NS_GET_USERNS
      Returns a file descriptor that refers to an owning user names‐
      pace.

NS_GET_PARENT
      Returns  a  file descriptor that refers to a parent namespace.
      This ioctl(2) can be used for pid  and  user  namespaces.  For
      user namespaces, NS_GET_PARENT and NS_GET_USERNS have the same
      meaning.

In addition to generic ioctl(2) errors, the following  specific  ones
can occur:

EINVAL NS_GET_PARENT was called for a nonhierarchical namespace.

EPERM  The  requested  namespace  is outside of the current namespace
      scope.

[1] https://lkml.org/lkml/2016/7/6/158
[2] https://lkml.org/lkml/2016/7/9/101

Changes for v2:
* don't return ENOENT for init_user_ns and init_pid_ns. There is nothing
  outside of the init namespace, so we can return EPERM in this case too.
  > The fewer special cases the easier the code is to get
  > correct, and the easier it is to read. // Eric

Changes for v3:
* rename ns->get_owner() to ns->owner(). get_* usually means that it
  grabs a reference.

Cc: "Eric W. Biederman" 
Cc: James Bottomley 
Cc: "Michael Kerrisk (man-pages)" 
Cc: "W. Trevor King" 
Cc: Alexander Viro 
Cc: Serge Hallyn

kernel: add a helper to get an owning user namespace for a namespace

2016-09-23T00:59:39+00:00

Return -EPERM if an owning user namespace is outside of a process
current user namespace.

v2: In a first version ns_get_owner returned ENOENT for init_user_ns.
    This special cases was removed from this version. There is nothing
    outside of init_user_ns, so we can return EPERM.
v3: rename ns->get_owner() to ns->owner(). get_* usually means that it
grabs a reference.

Acked-by: Serge Hallyn 
Signed-off-by: Andrei Vagin 
Signed-off-by: Eric W. Biederman

userns: When the per user per user namespace limit is reached return ENOSPC

2016-09-22T18:25:56+00:00

The current error codes returned when a the per user per user
namespace limit are hit (EINVAL, EUSERS, and ENFILE) are wrong.  I
asked for advice on linux-api and it we made clear that those were
the wrong error code, but a correct effor code was not suggested.

The best general error code I have found for hitting a resource limit
is ENOSPC.  It is not perfect but as it is unambiguous it will serve
until someone comes up with a better error code.

Signed-off-by: "Eric W. Biederman"

ipcns: Add a limit on the number of ipc namespaces

2016-08-08T19:42:03+00:00

Acked-by: Kees Cook 
Signed-off-by: "Eric W. Biederman"

ipc: delete "nr_ipc_ns"

2016-08-02T23:35:44+00:00

Write-only variable.

Link: http://lkml.kernel.org/r/20160708214356.GA6785@p183.telecom.by
Signed-off-by: Alexey Dobriyan 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

ipc: Initialize ipc_namespace->user_ns early.

2016-06-23T20:41:53+00:00

Allow the ipc namespace initialization code to depend on ns->user_ns
being set during initialization.

In particular this allows mq_init_ns to use ns->user_ns for permission
checks and initializating s_user_ns while the the mq filesystem is
being mounted.

Acked-by: Seth Forshee 
Suggested-by: Seth Forshee 
Signed-off-by: "Eric W. Biederman"