linux-toradex.git/kernel/bpf/cgroup.c, branch v5.5

bpf: cgroup: prevent out-of-order release of cgroup bpf

2020-01-06T22:00:30+00:00

Before commit 4bfc0bb2c60e ("bpf: decouple the lifetime of cgroup_bpf from cgroup itself")
cgroup bpf structures were released with
corresponding cgroup structures. It guaranteed the hierarchical order
of destruction: children were always first. It preserved attached
programs from being released before their propagated copies.

But with cgroup auto-detachment there are no such guarantees anymore:
cgroup bpf is released as soon as the cgroup is offline and there are
no live associated sockets. It means that an attached program can be
detached and released, while its propagated copy is still living
in the cgroup subtree. This will obviously lead to an use-after-free
bug.

To reproduce the issue the following script can be used:

  #!/bin/bash

  CGROOT=/sys/fs/cgroup

  mkdir -p ${CGROOT}/A ${CGROOT}/B ${CGROOT}/A/C
  sleep 1

  ./test_cgrp2_attach ${CGROOT}/A egress &
  A_PID=$!
  ./test_cgrp2_attach ${CGROOT}/B egress &
  B_PID=$!

  echo $$ > ${CGROOT}/A/C/cgroup.procs
  iperf -s &
  S_PID=$!
  iperf -c localhost -t 100 &
  C_PID=$!

  sleep 1

  echo $$ > ${CGROOT}/B/cgroup.procs
  echo ${S_PID} > ${CGROOT}/B/cgroup.procs
  echo ${C_PID} > ${CGROOT}/B/cgroup.procs

  sleep 1

  rmdir ${CGROOT}/A/C
  rmdir ${CGROOT}/A

  sleep 1

  kill -9 ${S_PID} ${C_PID} ${A_PID} ${B_PID}

On the unpatched kernel the following stacktrace can be obtained:

[   33.619799] BUG: unable to handle page fault for address: ffffbdb4801ab002
[   33.620677] #PF: supervisor read access in kernel mode
[   33.621293] #PF: error_code(0x0000) - not-present page
[   33.622754] Oops: 0000 [#1] SMP NOPTI
[   33.623202] CPU: 0 PID: 601 Comm: iperf Not tainted 5.5.0-rc2+ #23
[   33.625545] RIP: 0010:__cgroup_bpf_run_filter_skb+0x29f/0x3d0
[   33.635809] Call Trace:
[   33.636118]  ? __cgroup_bpf_run_filter_skb+0x2bf/0x3d0
[   33.636728]  ? __switch_to_asm+0x40/0x70
[   33.637196]  ip_finish_output+0x68/0xa0
[   33.637654]  ip_output+0x76/0xf0
[   33.638046]  ? __ip_finish_output+0x1c0/0x1c0
[   33.638576]  __ip_queue_xmit+0x157/0x410
[   33.639049]  __tcp_transmit_skb+0x535/0xaf0
[   33.639557]  tcp_write_xmit+0x378/0x1190
[   33.640049]  ? _copy_from_iter_full+0x8d/0x260
[   33.640592]  tcp_sendmsg_locked+0x2a2/0xdc0
[   33.641098]  ? sock_has_perm+0x10/0xa0
[   33.641574]  tcp_sendmsg+0x28/0x40
[   33.641985]  sock_sendmsg+0x57/0x60
[   33.642411]  sock_write_iter+0x97/0x100
[   33.642876]  new_sync_write+0x1b6/0x1d0
[   33.643339]  vfs_write+0xb6/0x1a0
[   33.643752]  ksys_write+0xa7/0xe0
[   33.644156]  do_syscall_64+0x5b/0x1b0
[   33.644605]  entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fix this by grabbing a reference to the bpf structure of each ancestor
on the initialization of the cgroup bpf structure, and dropping the
reference at the end of releasing the cgroup bpf structure.

This will restore the hierarchical order of cgroup bpf releasing,
without adding any operations on hot paths.

Thanks to Josef Bacik for the debugging and the initial analysis of
the problem.

Fixes: 4bfc0bb2c60e ("bpf: decouple the lifetime of cgroup_bpf from cgroup itself")
Reported-by: Josef Bacik 
Signed-off-by: Roman Gushchin 
Acked-by: Song Liu 
Signed-off-by: Alexei Starovoitov

treewide: Use sizeof_field() macro

2019-12-09T18:36:44+00:00

Replace all the occurrences of FIELD_SIZEOF() with sizeof_field() except
at places where these are defined. Later patches will remove the unused
definition of FIELD_SIZEOF().

This patch is generated using following script:

EXCLUDE_FILES="include/linux/stddef.h|include/linux/kernel.h"

git grep -l -e "\bFIELD_SIZEOF\b" | while read file;
do

	if [[ "$file" =~ $EXCLUDE_FILES ]]; then
		continue
	fi
	sed -i  -e 's/\bFIELD_SIZEOF\b/sizeof_field/g' $file;
done

Signed-off-by: Pankaj Bharadiya 
Link: https://lore.kernel.org/r/20190924105839.110713-3-pankaj.laxminarayan.bharadiya@intel.com
Co-developed-by: Kees Cook 
Signed-off-by: Kees Cook 
Acked-by: David Miller  # for net

Merge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

2019-11-26T23:42:43+00:00

Pull RCU updates from Ingo Molnar:
 "The main changes in this cycle were:

   - Dynamic tick (nohz) updates, perhaps most notably changes to force
     the tick on when needed due to lengthy in-kernel execution on CPUs
     on which RCU is waiting.

   - Linux-kernel memory consistency model updates.

   - Replace rcu_swap_protected() with rcu_prepace_pointer().

   - Torture-test updates.

   - Documentation updates.

   - Miscellaneous fixes"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (51 commits)
  security/safesetid: Replace rcu_swap_protected() with rcu_replace_pointer()
  net/sched: Replace rcu_swap_protected() with rcu_replace_pointer()
  net/netfilter: Replace rcu_swap_protected() with rcu_replace_pointer()
  net/core: Replace rcu_swap_protected() with rcu_replace_pointer()
  bpf/cgroup: Replace rcu_swap_protected() with rcu_replace_pointer()
  fs/afs: Replace rcu_swap_protected() with rcu_replace_pointer()
  drivers/scsi: Replace rcu_swap_protected() with rcu_replace_pointer()
  drm/i915: Replace rcu_swap_protected() with rcu_replace_pointer()
  x86/kvm/pmu: Replace rcu_swap_protected() with rcu_replace_pointer()
  rcu: Upgrade rcu_swap_protected() to rcu_replace_pointer()
  rcu: Suppress levelspread uninitialized messages
  rcu: Fix uninitialized variable in nocb_gp_wait()
  rcu: Update descriptions for rcu_future_grace_period tracepoint
  rcu: Update descriptions for rcu_nocb_wake tracepoint
  rcu: Remove obsolete descriptions for rcu_barrier tracepoint
  rcu: Ensure that ->rcu_urgent_qs is set before resched IPI
  workqueue: Convert for_each_wq to use built-in list check
  rcu: Several rcu_segcblist functions can be static
  rcu: Remove unused function hlist_bl_del_init_rcu()
  Documentation: Rename rcu_node_context_switch() to rcu_note_context_switch()
  ...

bpf: Allow narrow loads of bpf_sysctl fields with offset > 0

2019-10-30T19:49:13+00:00

"ctx:file_pos sysctl:read read ok narrow" works on s390 by accident: it
reads the wrong byte, which happens to have the expected value of 0.
Improve the test by seeking to the 4th byte and expecting 4 instead of
0.

This makes the latent problem apparent: the test attempts to read the
first byte of bpf_sysctl.file_pos, assuming this is the least-significant
byte, which is not the case on big-endian machines: a non-zero offset is
needed.

The point of the test is to verify narrow loads, so we cannot cheat our
way out by simply using BPF_W. The existence of the test means that such
loads have to be supported, most likely because llvm can generate them.
Fix the test by adding a big-endian variant, which uses an offset to
access the least-significant byte of bpf_sysctl.file_pos.

This reveals the final problem: verifier rejects accesses to bpf_sysctl
fields with offset > 0. Such accesses are already allowed for a wide
range of structs: __sk_buff, bpf_sock_addr and sk_msg_md to name a few.
Extend this support to bpf_sysctl by using bpf_ctx_range instead of
offsetof when matching field offsets.

Fixes: 7b146cebe30c ("bpf: Sysctl hook")
Fixes: e1550bfe0de4 ("bpf: Add file_pos field to bpf_sysctl ctx")
Fixes: 9a1027e52535 ("selftests/bpf: Test file_pos field in bpf_sysctl ctx")
Signed-off-by: Ilya Leoshkevich 
Signed-off-by: Alexei Starovoitov 
Acked-by: Andrey Ignatov 
Acked-by: Andrii Nakryiko 
Link: https://lore.kernel.org/bpf/20191028122902.9763-1-iii@linux.ibm.com

bpf/cgroup: Replace rcu_swap_protected() with rcu_replace_pointer()

2019-10-30T15:45:14+00:00

This commit replaces the use of rcu_swap_protected() with the more
intuitively appealing rcu_replace_pointer() as a step towards removing
rcu_swap_protected().

Link: https://lore.kernel.org/lkml/CAHk-=wiAsJLw1egFEE=Z7-GGtM6wcvtyytXZA1+BHqta4gg6Hw@mail.gmail.com/
Reported-by: Linus Torvalds 
[ paulmck: From rcu_replace() to rcu_replace_pointer() per Ingo Molnar. ]
Signed-off-by: Paul E. McKenney 
Acked-by: Andrii Nakryiko 
Acked-by: Song Liu 
Cc: Alexei Starovoitov 
Cc: Daniel Borkmann 
Cc: Martin KaFai Lau 
Cc: Yonghong Song 
Cc: 
Cc:

bpf: fix accessing bpf_sysctl.file_pos on s390

2019-09-16T09:44:05+00:00

"ctx:file_pos sysctl:read write ok" fails on s390 with "Read value  !=
nux". This is because verifier rewrites a complete 32-bit
bpf_sysctl.file_pos update to a partial update of the first 32 bits of
64-bit *bpf_sysctl_kern.ppos, which is not correct on big-endian
systems.

Fix by using an offset on big-endian systems.

Ditto for bpf_sysctl.file_pos reads. Currently the test does not detect
a problem there, since it expects to see 0, which it gets with high
probability in error cases, so change it to seek to offset 3 and expect
3 in bpf_sysctl.file_pos.

Fixes: e1550bfe0de4 ("bpf: Add file_pos field to bpf_sysctl ctx")
Signed-off-by: Ilya Leoshkevich 
Acked-by: Yonghong Song 
Signed-off-by: Daniel Borkmann 
Link: https://lore.kernel.org/bpf/20190816105300.49035-1-iii@linux.ibm.com/

bpf: always allocate at least 16 bytes for setsockopt hook

2019-08-01T20:55:52+00:00

Since we always allocate memory, allocate just a little bit more
for the BPF program in case it need to override user input with
bigger value. The canonical example is TCP_CONGESTION where
input string might be too small to override (nv -> bbr or cubic).

16 bytes are chosen to match the size of TCP_CA_NAME_MAX and can
be extended in the future if needed.

Signed-off-by: Stanislav Fomichev 
Signed-off-by: Alexei Starovoitov

bpf: cgroup: Fix build error without CONFIG_NET

2019-07-08T15:17:00+00:00

If CONFIG_NET is not set and CONFIG_CGROUP_BPF=y,
gcc building fails:

kernel/bpf/cgroup.o: In function `cg_sockopt_func_proto':
cgroup.c:(.text+0x237e): undefined reference to `bpf_sk_storage_get_proto'
cgroup.c:(.text+0x2394): undefined reference to `bpf_sk_storage_delete_proto'
kernel/bpf/cgroup.o: In function `__cgroup_bpf_run_filter_getsockopt':
(.text+0x2a1f): undefined reference to `lock_sock_nested'
(.text+0x2ca2): undefined reference to `release_sock'
kernel/bpf/cgroup.o: In function `__cgroup_bpf_run_filter_setsockopt':
(.text+0x3006): undefined reference to `lock_sock_nested'
(.text+0x32bb): undefined reference to `release_sock'

Reported-by: Hulk Robot 
Suggested-by: Stanislav Fomichev 
Fixes: 0d01da6afc54 ("bpf: implement getsockopt and setsockopt hooks")
Signed-off-by: YueHaibing 
Acked-by: Yonghong Song 
Signed-off-by: Daniel Borkmann

bpf: implement getsockopt and setsockopt hooks

2019-06-27T22:25:16+00:00

Implement new BPF_PROG_TYPE_CGROUP_SOCKOPT program type and
BPF_CGROUP_{G,S}ETSOCKOPT cgroup hooks.

BPF_CGROUP_SETSOCKOPT can modify user setsockopt arguments before
passing them down to the kernel or bypass kernel completely.
BPF_CGROUP_GETSOCKOPT can can inspect/modify getsockopt arguments that
kernel returns.
Both hooks reuse existing PTR_TO_PACKET{,_END} infrastructure.

The buffer memory is pre-allocated (because I don't think there is
a precedent for working with __user memory from bpf). This might be
slow to do for each {s,g}etsockopt call, that's why I've added
__cgroup_bpf_prog_array_is_empty that exits early if there is nothing
attached to a cgroup. Note, however, that there is a race between
__cgroup_bpf_prog_array_is_empty and BPF_PROG_RUN_ARRAY where cgroup
program layout might have changed; this should not be a problem
because in general there is a race between multiple calls to
{s,g}etsocktop and user adding/removing bpf progs from a cgroup.

The return code of the BPF program is handled as follows:
* 0: EPERM
* 1: success, continue with next BPF program in the cgroup chain

v9:
* allow overwriting setsockopt arguments (Alexei Starovoitov):
  * use set_fs (same as kernel_setsockopt)
  * buffer is always kzalloc'd (no small on-stack buffer)

v8:
* use s32 for optlen (Andrii Nakryiko)

v7:
* return only 0 or 1 (Alexei Starovoitov)
* always run all progs (Alexei Starovoitov)
* use optval=0 as kernel bypass in setsockopt (Alexei Starovoitov)
  (decided to use optval=-1 instead, optval=0 might be a valid input)
* call getsockopt hook after kernel handlers (Alexei Starovoitov)

v6:
* rework cgroup chaining; stop as soon as bpf program returns
  0 or 2; see patch with the documentation for the details
* drop Andrii's and Martin's Acked-by (not sure they are comfortable
  with the new state of things)

v5:
* skip copy_to_user() and put_user() when ret == 0 (Martin Lau)

v4:
* don't export bpf_sk_fullsock helper (Martin Lau)
* size != sizeof(__u64) for uapi pointers (Martin Lau)
* offsetof instead of bpf_ctx_range when checking ctx access (Martin Lau)

v3:
* typos in BPF_PROG_CGROUP_SOCKOPT_RUN_ARRAY comments (Andrii Nakryiko)
* reverse christmas tree in BPF_PROG_CGROUP_SOCKOPT_RUN_ARRAY (Andrii
  Nakryiko)
* use __bpf_md_ptr instead of __u32 for optval{,_end} (Martin Lau)
* use BPF_FIELD_SIZEOF() for consistency (Martin Lau)
* new CG_SOCKOPT_ACCESS macro to wrap repeated parts

v2:
* moved bpf_sockopt_kern fields around to remove a hole (Martin Lau)
* aligned bpf_sockopt_kern->buf to 8 bytes (Martin Lau)
* bpf_prog_array_is_empty instead of bpf_prog_array_length (Martin Lau)
* added [0,2] return code check to verifier (Martin Lau)
* dropped unused buf[64] from the stack (Martin Lau)
* use PTR_TO_SOCKET for bpf_sockopt->sk (Martin Lau)
* dropped bpf_target_off from ctx rewrites (Martin Lau)
* use return code for kernel bypass (Martin Lau & Andrii Nakryiko)

Cc: Andrii Nakryiko 
Cc: Martin Lau 
Signed-off-by: Stanislav Fomichev 
Signed-off-by: Alexei Starovoitov

bpf: fix cgroup bpf release synchronization

2019-06-27T20:51:58+00:00

Since commit 4bfc0bb2c60e ("bpf: decouple the lifetime of cgroup_bpf
from cgroup itself"), cgroup_bpf release occurs asynchronously
(from a worker context), and before the release of the cgroup itself.

This introduced a previously non-existing race between the release
and update paths. E.g. if a leaf's cgroup_bpf is released and a new
bpf program is attached to the one of ancestor cgroups at the same
time. The race may result in double-free and other memory corruptions.

To fix the problem, let's protect the body of cgroup_bpf_release()
with cgroup_mutex, as it was effectively previously, when all this
code was called from the cgroup release path with cgroup mutex held.

Also let's skip cgroups, which have no chances to invoke a bpf
program, on the update path. If the cgroup bpf refcnt reached 0,
it means that the cgroup is offline (no attached processes), and
there are no associated sockets left. It means there is no point
in updating effective progs array! And it can lead to a leak,
if it happens after the release. So, let's skip such cgroups.

Big thanks for Tejun Heo for discovering and debugging of this problem!

Fixes: 4bfc0bb2c60e ("bpf: decouple the lifetime of cgroup_bpf from cgroup itself")
Reported-by: Tejun Heo 
Signed-off-by: Roman Gushchin 
Signed-off-by: Alexei Starovoitov 
Signed-off-by: Daniel Borkmann