From e10360f815ca6367357b2c2cfef17fc663e50f7b Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 27 Dec 2019 13:50:34 -0800 Subject: [PATCH 1/2] bpf: cgroup: prevent out-of-order release of cgroup bpf 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 --- kernel/bpf/cgroup.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 4fb20ab179fe..9e43b72eb619 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -35,8 +35,8 @@ void cgroup_bpf_offline(struct cgroup *cgrp) */ static void cgroup_bpf_release(struct work_struct *work) { - struct cgroup *cgrp = container_of(work, struct cgroup, - bpf.release_work); + struct cgroup *p, *cgrp = container_of(work, struct cgroup, + bpf.release_work); enum bpf_cgroup_storage_type stype; struct bpf_prog_array *old_array; unsigned int type; @@ -65,6 +65,9 @@ static void cgroup_bpf_release(struct work_struct *work) mutex_unlock(&cgroup_mutex); + for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p)) + cgroup_bpf_put(p); + percpu_ref_exit(&cgrp->bpf.refcnt); cgroup_put(cgrp); } @@ -199,6 +202,7 @@ int cgroup_bpf_inherit(struct cgroup *cgrp) */ #define NR ARRAY_SIZE(cgrp->bpf.effective) struct bpf_prog_array *arrays[NR] = {}; + struct cgroup *p; int ret, i; ret = percpu_ref_init(&cgrp->bpf.refcnt, cgroup_bpf_release_fn, 0, @@ -206,6 +210,9 @@ int cgroup_bpf_inherit(struct cgroup *cgrp) if (ret) return ret; + for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p)) + cgroup_bpf_get(p); + for (i = 0; i < NR; i++) INIT_LIST_HEAD(&cgrp->bpf.progs[i]); From 6d4f151acf9a4f6fab09b615f246c717ddedcf0c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 6 Jan 2020 22:51:57 +0100 Subject: [PATCH 2/2] bpf: Fix passing modified ctx to ld/abs/ind instruction Anatoly has been fuzzing with kBdysch harness and reported a KASAN slab oob in one of the outcomes: [...] [ 77.359642] BUG: KASAN: slab-out-of-bounds in bpf_skb_load_helper_8_no_cache+0x71/0x130 [ 77.360463] Read of size 4 at addr ffff8880679bac68 by task bpf/406 [ 77.361119] [ 77.361289] CPU: 2 PID: 406 Comm: bpf Not tainted 5.5.0-rc2-xfstests-00157-g2187f215eba #1 [ 77.362134] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014 [ 77.362984] Call Trace: [ 77.363249] dump_stack+0x97/0xe0 [ 77.363603] print_address_description.constprop.0+0x1d/0x220 [ 77.364251] ? bpf_skb_load_helper_8_no_cache+0x71/0x130 [ 77.365030] ? bpf_skb_load_helper_8_no_cache+0x71/0x130 [ 77.365860] __kasan_report.cold+0x37/0x7b [ 77.366365] ? bpf_skb_load_helper_8_no_cache+0x71/0x130 [ 77.366940] kasan_report+0xe/0x20 [ 77.367295] bpf_skb_load_helper_8_no_cache+0x71/0x130 [ 77.367821] ? bpf_skb_load_helper_8+0xf0/0xf0 [ 77.368278] ? mark_lock+0xa3/0x9b0 [ 77.368641] ? kvm_sched_clock_read+0x14/0x30 [ 77.369096] ? sched_clock+0x5/0x10 [ 77.369460] ? sched_clock_cpu+0x18/0x110 [ 77.369876] ? bpf_skb_load_helper_8+0xf0/0xf0 [ 77.370330] ___bpf_prog_run+0x16c0/0x28f0 [ 77.370755] __bpf_prog_run32+0x83/0xc0 [ 77.371153] ? __bpf_prog_run64+0xc0/0xc0 [ 77.371568] ? match_held_lock+0x1b/0x230 [ 77.371984] ? rcu_read_lock_held+0xa1/0xb0 [ 77.372416] ? rcu_is_watching+0x34/0x50 [ 77.372826] sk_filter_trim_cap+0x17c/0x4d0 [ 77.373259] ? sock_kzfree_s+0x40/0x40 [ 77.373648] ? __get_filter+0x150/0x150 [ 77.374059] ? skb_copy_datagram_from_iter+0x80/0x280 [ 77.374581] ? do_raw_spin_unlock+0xa5/0x140 [ 77.375025] unix_dgram_sendmsg+0x33a/0xa70 [ 77.375459] ? do_raw_spin_lock+0x1d0/0x1d0 [ 77.375893] ? unix_peer_get+0xa0/0xa0 [ 77.376287] ? __fget_light+0xa4/0xf0 [ 77.376670] __sys_sendto+0x265/0x280 [ 77.377056] ? __ia32_sys_getpeername+0x50/0x50 [ 77.377523] ? lock_downgrade+0x350/0x350 [ 77.377940] ? __sys_setsockopt+0x2a6/0x2c0 [ 77.378374] ? sock_read_iter+0x240/0x240 [ 77.378789] ? __sys_socketpair+0x22a/0x300 [ 77.379221] ? __ia32_sys_socket+0x50/0x50 [ 77.379649] ? mark_held_locks+0x1d/0x90 [ 77.380059] ? trace_hardirqs_on_thunk+0x1a/0x1c [ 77.380536] __x64_sys_sendto+0x74/0x90 [ 77.380938] do_syscall_64+0x68/0x2a0 [ 77.381324] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 77.381878] RIP: 0033:0x44c070 [...] After further debugging, turns out while in case of other helper functions we disallow passing modified ctx, the special case of ld/abs/ind instruction which has similar semantics (except r6 being the ctx argument) is missing such check. Modified ctx is impossible here as bpf_skb_load_helper_8_no_cache() and others are expecting skb fields in original position, hence, add check_ctx_reg() to reject any modified ctx. Issue was first introduced back in f1174f77b50c ("bpf/verifier: rework value tracking"). Fixes: f1174f77b50c ("bpf/verifier: rework value tracking") Reported-by: Anatoly Trosinenko Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200106215157.3553-1-daniel@iogearbox.net --- kernel/bpf/verifier.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6f63ae7a370c..ce85e7041f0c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6264,6 +6264,7 @@ static bool may_access_skb(enum bpf_prog_type type) static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_reg_state *regs = cur_regs(env); + static const int ctx_reg = BPF_REG_6; u8 mode = BPF_MODE(insn->code); int i, err; @@ -6297,7 +6298,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) } /* check whether implicit source operand (register R6) is readable */ - err = check_reg_arg(env, BPF_REG_6, SRC_OP); + err = check_reg_arg(env, ctx_reg, SRC_OP); if (err) return err; @@ -6316,7 +6317,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } - if (regs[BPF_REG_6].type != PTR_TO_CTX) { + if (regs[ctx_reg].type != PTR_TO_CTX) { verbose(env, "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); return -EINVAL; @@ -6329,6 +6330,10 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; } + err = check_ctx_reg(env, ®s[ctx_reg], ctx_reg); + if (err < 0) + return err; + /* reset caller saved regs to unreadable */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]);