linux-toradex.git/security/apparmor/policy.c, branch v3.14.4

apparmor: fix memleak of the profile hash

2013-10-16T00:53:59+00:00

BugLink: http://bugs.launchpad.net/bugs/1235523

This fixes the following kmemleak trace:
unreferenced object 0xffff8801e8c35680 (size 32):
  comm "apparmor_parser", pid 691, jiffies 4294895667 (age 13230.876s)
  hex dump (first 32 bytes):
    e0 d3 4e b5 ac 6d f4 ed 3f cb ee 48 1c fd 40 cf  ..N..m..?..H..@.
    5b cc e9 93 00 00 00 00 00 00 00 00 00 00 00 00  [...............
  backtrace:
    [] kmemleak_alloc+0x4e/0xb0
    [] __kmalloc+0x103/0x290
    [] aa_calc_profile_hash+0x6c/0x150
    [] aa_unpack+0x39d/0xd50
    [] aa_replace_profiles+0x3d/0xd80
    [] profile_replace+0x37/0x50
    [] vfs_write+0xbd/0x1e0
    [] SyS_write+0x4c/0xa0
    [] system_call_fastpath+0x1a/0x1f
    [] 0xffffffffffffffff

Signed-off-by: John Johansen 
Signed-off-by: James Morris

apparmor: fix suspicious RCU usage warning in policy.c/policy.h

2013-09-29T23:54:01+00:00

The recent 3.12 pull request for apparmor was missing a couple rcu _protected
access modifiers. Resulting in the follow suspicious RCU usage

 [   29.804534] [ INFO: suspicious RCU usage. ]
 [   29.804539] 3.11.0+ #5 Not tainted
 [   29.804541] -------------------------------
 [   29.804545] security/apparmor/include/policy.h:363 suspicious rcu_dereference_check() usage!
 [   29.804548]
 [   29.804548] other info that might help us debug this:
 [   29.804548]
 [   29.804553]
 [   29.804553] rcu_scheduler_active = 1, debug_locks = 1
 [   29.804558] 2 locks held by apparmor_parser/1268:
 [   29.804560]  #0:  (sb_writers#9){.+.+.+}, at: [] file_start_write+0x27/0x29
 [   29.804576]  #1:  (&ns->lock){+.+.+.}, at: [] aa_replace_profiles+0x166/0x57c
 [   29.804589]
 [   29.804589] stack backtrace:
 [   29.804595] CPU: 0 PID: 1268 Comm: apparmor_parser Not tainted 3.11.0+ #5
 [   29.804599] Hardware name: ASUSTeK Computer Inc.         UL50VT          /UL50VT    , BIOS 217     03/01/2010
 [   29.804602]  0000000000000000 ffff8800b95a1d90 ffffffff8144eb9b ffff8800b94db540
 [   29.804611]  ffff8800b95a1dc0 ffffffff81087439 ffff880138cc3a18 ffff880138cc3a18
 [   29.804619]  ffff8800b9464a90 ffff880138cc3a38 ffff8800b95a1df0 ffffffff811f5084
 [   29.804628] Call Trace:
 [   29.804636]  [] dump_stack+0x4e/0x82
 [   29.804642]  [] lockdep_rcu_suspicious+0xfc/0x105
 [   29.804649]  [] __aa_update_replacedby+0x53/0x7f
 [   29.804655]  [] __replace_profile+0x11f/0x1ed
 [   29.804661]  [] aa_replace_profiles+0x410/0x57c
 [   29.804668]  [] profile_replace+0x35/0x4c
 [   29.804674]  [] vfs_write+0xad/0x113
 [   29.804680]  [] SyS_write+0x44/0x7a
 [   29.804687]  [] system_call_fastpath+0x16/0x1b
 [   29.804691]
 [   29.804694] ===============================
 [   29.804697] [ INFO: suspicious RCU usage. ]
 [   29.804700] 3.11.0+ #5 Not tainted
 [   29.804703] -------------------------------
 [   29.804706] security/apparmor/policy.c:566 suspicious rcu_dereference_check() usage!
 [   29.804709]
 [   29.804709] other info that might help us debug this:
 [   29.804709]
 [   29.804714]
 [   29.804714] rcu_scheduler_active = 1, debug_locks = 1
 [   29.804718] 2 locks held by apparmor_parser/1268:
 [   29.804721]  #0:  (sb_writers#9){.+.+.+}, at: [] file_start_write+0x27/0x29
 [   29.804733]  #1:  (&ns->lock){+.+.+.}, at: [] aa_replace_profiles+0x166/0x57c
 [   29.804744]
 [   29.804744] stack backtrace:
 [   29.804750] CPU: 0 PID: 1268 Comm: apparmor_parser Not tainted 3.11.0+ #5
 [   29.804753] Hardware name: ASUSTeK Computer Inc.         UL50VT          /UL50VT    , BIOS 217     03/01/2010
 [   29.804756]  0000000000000000 ffff8800b95a1d80 ffffffff8144eb9b ffff8800b94db540
 [   29.804764]  ffff8800b95a1db0 ffffffff81087439 ffff8800b95b02b0 0000000000000000
 [   29.804772]  ffff8800b9efba08 ffff880138cc3a38 ffff8800b95a1dd0 ffffffff811f4f94
 [   29.804779] Call Trace:
 [   29.804786]  [] dump_stack+0x4e/0x82
 [   29.804791]  [] lockdep_rcu_suspicious+0xfc/0x105
 [   29.804798]  [] aa_free_replacedby_kref+0x4d/0x62
 [   29.804804]  [] ? aa_put_namespace+0x17/0x17
 [   29.804810]  [] kref_put+0x36/0x40
 [   29.804816]  [] __replace_profile+0x13a/0x1ed
 [   29.804822]  [] aa_replace_profiles+0x410/0x57c
 [   29.804829]  [] profile_replace+0x35/0x4c
 [   29.804835]  [] vfs_write+0xad/0x113
 [   29.804840]  [] SyS_write+0x44/0x7a
 [   29.804847]  [] system_call_fastpath+0x16/0x1b

Reported-by: miles.lane@gmail.com
CC: paulmck@linux.vnet.ibm.com
Signed-off-by: John Johansen 
Signed-off-by: James Morris

apparmor: add interface files for profiles and namespaces

2013-08-14T18:42:07+00:00

Add basic interface files to access namespace and profile information.
The interface files are created when a profile is loaded and removed
when the profile or namespace is removed.

Signed-off-by: John Johansen

apparmor: allow setting any profile into the unconfined state

2013-08-14T18:42:07+00:00

Allow emulating the default profile behavior from boot, by allowing
loading of a profile in the unconfined state into a new NS.

Signed-off-by: John Johansen 
Acked-by: Seth Arnold

apparmor: make free_profile available outside of policy.c

2013-08-14T18:42:06+00:00

Signed-off-by: John Johansen

apparmor: rework namespace free path

2013-08-14T18:42:06+00:00

namespaces now completely use the unconfined profile to track the
refcount and rcu freeing cycle. So rework the code to simplify (track
everything through the profile path right up to the end), and move the
rcu_head from policy base to profile as the namespace no longer needs
it.

Signed-off-by: John Johansen 
Acked-by: Seth Arnold

apparmor: update how unconfined is handled

2013-08-14T18:42:06+00:00

ns->unconfined is being used read side without locking, nor rcu but is
being updated when a namespace is removed. This works for the root ns
which is never removed but has a race window and can cause failures when
children namespaces are removed.

Also ns and ns->unconfined have a circular refcounting dependency that
is problematic and must be broken. Currently this is done incorrectly
when the namespace is destroyed.

Fix this by forward referencing unconfined via the replacedby infrastructure
instead of directly updating the ns->unconfined pointer.

Remove the circular refcount dependency by making the ns and its unconfined
profile share the same refcount.

Signed-off-by: John Johansen 
Acked-by: Seth Arnold

apparmor: change how profile replacement update is done

2013-08-14T18:42:06+00:00

remove the use of replaced by chaining and move to profile invalidation
and lookup to handle task replacement.

Replacement chaining can result in large chains of profiles being pinned
in memory when one profile in the chain is use. With implicit labeling
this will be even more of a problem, so move to a direct lookup method.

Signed-off-by: John Johansen

apparmor: convert profile lists to RCU based locking

2013-08-14T18:42:06+00:00

Signed-off-by: John Johansen

apparmor: provide base for multiple profiles to be replaced at once

2013-08-14T18:42:06+00:00

previously profiles had to be loaded one at a time, which could result
in cases where a replacement of a set would partially succeed, and then fail
resulting in inconsistent policy.

Allow multiple profiles to replaced "atomically" so that the replacement
either succeeds or fails for the entire set of profiles.

Signed-off-by: John Johansen