kernel/security/apparmor/policy.c, branch linux-4.16.y

apparmor: fix possible recursive lock warning in __aa_create_ns

2017-11-21T10:17:16Z

Use mutex_lock_nested to provide lockdep the parent child lock ordering of the tree. This fixes the lockdep Warning [ 305.275177] ============================================ [ 305.275178] WARNING: possible recursive locking detected [ 305.275179] 4.14.0-rc7+ #320 Not tainted [ 305.275180] -------------------------------------------- [ 305.275181] apparmor_parser/1339 is trying to acquire lock: [ 305.275182] (&ns->lock){+.+.}, at: [] __aa_create_ns+0x6d/0x1e0 [ 305.275187] but task is already holding lock: [ 305.275187] (&ns->lock){+.+.}, at: [] aa_prepare_ns+0x3d/0xd0 [ 305.275190] other info that might help us debug this: [ 305.275191] Possible unsafe locking scenario: [ 305.275192] CPU0 [ 305.275193] ---- [ 305.275193] lock(&ns->lock); [ 305.275194] lock(&ns->lock); [ 305.275195] *** DEADLOCK *** [ 305.275196] May be due to missing lock nesting notation [ 305.275198] 2 locks held by apparmor_parser/1339: [ 305.275198] #0: (sb_writers#10){.+.+}, at: [] vfs_write+0x1a7/0x1d0 [ 305.275202] #1: (&ns->lock){+.+.}, at: [] aa_prepare_ns+0x3d/0xd0 [ 305.275205] stack backtrace: [ 305.275207] CPU: 1 PID: 1339 Comm: apparmor_parser Not tainted 4.14.0-rc7+ #320 [ 305.275208] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.1-1ubuntu1 04/01/2014 [ 305.275209] Call Trace: [ 305.275212] dump_stack+0x85/0xcb [ 305.275214] __lock_acquire+0x141c/0x1460 [ 305.275216] ? __aa_create_ns+0x6d/0x1e0 [ 305.275218] ? ___slab_alloc+0x183/0x540 [ 305.275219] ? ___slab_alloc+0x183/0x540 [ 305.275221] lock_acquire+0xed/0x1e0 [ 305.275223] ? lock_acquire+0xed/0x1e0 [ 305.275224] ? __aa_create_ns+0x6d/0x1e0 [ 305.275227] __mutex_lock+0x89/0x920 [ 305.275228] ? __aa_create_ns+0x6d/0x1e0 [ 305.275230] ? trace_hardirqs_on_caller+0x11f/0x190 [ 305.275231] ? __aa_create_ns+0x6d/0x1e0 [ 305.275233] ? __lockdep_init_map+0x57/0x1d0 [ 305.275234] ? lockdep_init_map+0x9/0x10 [ 305.275236] ? __rwlock_init+0x32/0x60 [ 305.275238] mutex_lock_nested+0x1b/0x20 [ 305.275240] ? mutex_lock_nested+0x1b/0x20 [ 305.275241] __aa_create_ns+0x6d/0x1e0 [ 305.275243] aa_prepare_ns+0xc2/0xd0 [ 305.275245] aa_replace_profiles+0x168/0xf30 [ 305.275247] ? __might_fault+0x85/0x90 [ 305.275250] policy_update+0xb9/0x380 [ 305.275252] profile_load+0x7e/0x90 [ 305.275254] __vfs_write+0x28/0x150 [ 305.275256] ? rcu_read_lock_sched_held+0x72/0x80 [ 305.275257] ? rcu_sync_lockdep_assert+0x2f/0x60 [ 305.275259] ? __sb_start_write+0xdc/0x1c0 [ 305.275261] ? vfs_write+0x1a7/0x1d0 [ 305.275262] vfs_write+0xca/0x1d0 [ 305.275264] ? trace_hardirqs_on_caller+0x11f/0x190 [ 305.275266] SyS_write+0x49/0xa0 [ 305.275268] entry_SYSCALL_64_fastpath+0x23/0xc2 [ 305.275271] RIP: 0033:0x7fa6b22e8c74 [ 305.275272] RSP: 002b:00007ffeaaee6288 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 305.275273] RAX: ffffffffffffffda RBX: 00007ffeaaee62a4 RCX: 00007fa6b22e8c74 [ 305.275274] RDX: 0000000000000a51 RSI: 00005566a8198c10 RDI: 0000000000000004 [ 305.275275] RBP: 0000000000000a39 R08: 0000000000000a51 R09: 0000000000000000 [ 305.275276] R10: 0000000000000000 R11: 0000000000000246 R12: 00005566a8198c10 [ 305.275277] R13: 0000000000000004 R14: 00005566a72ecb88 R15: 00005566a72ec3a8 Fixes: 73688d1ed0b8 ("apparmor: refactor prepare_ns() and make usable from different views") Signed-off-by: John Johansen

apparmor: fix leak of null profile name if profile allocation fails

2017-11-21T10:17:13Z

Fixes: d07881d2edb0 ("apparmor: move new_null_profile to after profile lookup fns()") Reported-by: Seth Arnold Signed-off-by: John Johansen

apparmor: fix race condition in null profile creation

2017-09-22T20:00:58Z

There is a race when null- profile is being created between the initial lookup/creation of the profile and lock/addition of the profile. This could result in multiple version of a profile being added to the list which need to be removed/replaced. Since these are learning profile their is no affect on mediation. Signed-off-by: John Johansen

apparmor: move new_null_profile to after profile lookup fns()

2017-09-22T20:00:58Z

new_null_profile will need to use some of the profile lookup fns() so move instead of doing forward fn declarations. Signed-off-by: John Johansen

apparmor: switch from profiles to using labels on contexts

2017-06-11T00:11:38Z

Begin the actual switch to using domain labels by storing them on the context and converting the label to a singular profile where possible. Signed-off-by: John Johansen

apparmor: cleanup remove unused and not fully implemented profile rename

2017-06-11T00:11:36Z

Remove the partially implemented code, until this can be properly implemented. Signed-off-by: John Johansen

apparmor: refactor updating profiles to the newest parent

2017-06-11T00:11:35Z

Signed-off-by: John Johansen

apparmor: share profile name on replacement

2017-06-11T00:11:35Z

The profile names are the same, leverage this. Signed-off-by: John Johansen

apparmor: fix policy load/remove semantics

2017-06-11T00:11:32Z

The namespace being passed into the replace/remove profiles fns() is not the view, but the namespace specified by the inode from the file hook (if present) or the loading tasks ns, if accessing the top level virtualized load/replace file interface. Signed-off-by: John Johansen

apparmor: add namespace lookup fns()

2017-06-11T00:11:32Z

Currently lookups are restricted to a single ns component in the path. However when namespaces are allowed to have separate views, and scopes this will not be sufficient, as it will be possible to have a multiple component ns path in scope. Add some ns lookup fns() to allow this and use them. Signed-off-by: John Johansen