From 0550cfe8c2c6f8e7a4c348b6603a794576db12dd Mon Sep 17 00:00:00 2001 From: KP Singh Date: Wed, 20 May 2020 14:56:16 +0200 Subject: [PATCH 1/3] security: Fix hook iteration for secid_to_secctx secid_to_secctx is not stackable, and since the BPF LSM registers this hook by default, the call_int_hook logic is not suitable which "bails-on-fail" and casues issues when other LSMs register this hook and eventually breaks Audit. In order to fix this, directly iterate over the security hooks instead of using call_int_hook as suggested in: https: //lore.kernel.org/bpf/9d0eb6c6-803a-ff3a-5603-9ad6d9edfc00@schaufler-ca.com/#t Fixes: 98e828a0650f ("security: Refactor declaration of LSM hooks") Fixes: 625236ba3832 ("security: Fix the default value of secid_to_secctx hook") Reported-by: Alexei Starovoitov Signed-off-by: KP Singh Signed-off-by: Alexei Starovoitov Acked-by: James Morris Link: https://lore.kernel.org/bpf/20200520125616.193765-1-kpsingh@chromium.org --- security/security.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/security/security.c b/security/security.c index 7fed24b9d57e..51de970fbb1e 100644 --- a/security/security.c +++ b/security/security.c @@ -1965,8 +1965,20 @@ EXPORT_SYMBOL(security_ismaclabel); int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) { - return call_int_hook(secid_to_secctx, -EOPNOTSUPP, secid, secdata, - seclen); + struct security_hook_list *hp; + int rc; + + /* + * Currently, only one LSM can implement secid_to_secctx (i.e this + * LSM hook is not "stackable"). + */ + hlist_for_each_entry(hp, &security_hook_heads.secid_to_secctx, list) { + rc = hp->hook.secid_to_secctx(secid, secdata, seclen); + if (rc != LSM_RET_DEFAULT(secid_to_secctx)) + return rc; + } + + return LSM_RET_DEFAULT(secid_to_secctx); } EXPORT_SYMBOL(security_secid_to_secctx); From dfeb376dd4cb2c5004aeb625e2475f58a5ff2ea7 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 18 May 2020 22:38:24 -0700 Subject: [PATCH 2/3] bpf: Prevent mmap()'ing read-only maps as writable As discussed in [0], it's dangerous to allow mapping BPF map, that's meant to be frozen and is read-only on BPF program side, because that allows user-space to actually store a writable view to the page even after it is frozen. This is exacerbated by BPF verifier making a strong assumption that contents of such frozen map will remain unchanged. To prevent this, disallow mapping BPF_F_RDONLY_PROG mmap()'able BPF maps as writable, ever. [0] https://lore.kernel.org/bpf/CAEf4BzYGWYhXdp6BJ7_=9OQPJxQpgug080MMjdSB72i9R+5c6g@mail.gmail.com/ Fixes: fc9702273e2e ("bpf: Add mmap() support for BPF_MAP_TYPE_ARRAY") Suggested-by: Jann Horn Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Reviewed-by: Jann Horn Link: https://lore.kernel.org/bpf/20200519053824.1089415-1-andriin@fb.com --- kernel/bpf/syscall.c | 17 ++++++++++++++--- tools/testing/selftests/bpf/prog_tests/mmap.c | 13 ++++++++++++- tools/testing/selftests/bpf/progs/test_mmap.c | 8 ++++++++ 3 files changed, 34 insertions(+), 4 deletions(-) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 2843bbba9ca1..4e6dee19a668 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -623,9 +623,20 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) mutex_lock(&map->freeze_mutex); - if ((vma->vm_flags & VM_WRITE) && map->frozen) { - err = -EPERM; - goto out; + if (vma->vm_flags & VM_WRITE) { + if (map->frozen) { + err = -EPERM; + goto out; + } + /* map is meant to be read-only, so do not allow mapping as + * writable, because it's possible to leak a writable page + * reference and allows user-space to still modify it after + * freezing, while verifier will assume contents do not change + */ + if (map->map_flags & BPF_F_RDONLY_PROG) { + err = -EACCES; + goto out; + } } /* set default open/close callbacks */ diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c index 6b9dce431d41..43d0b5578f46 100644 --- a/tools/testing/selftests/bpf/prog_tests/mmap.c +++ b/tools/testing/selftests/bpf/prog_tests/mmap.c @@ -19,7 +19,7 @@ void test_mmap(void) const size_t map_sz = roundup_page(sizeof(struct map_data)); const int zero = 0, one = 1, two = 2, far = 1500; const long page_size = sysconf(_SC_PAGE_SIZE); - int err, duration = 0, i, data_map_fd, data_map_id, tmp_fd; + int err, duration = 0, i, data_map_fd, data_map_id, tmp_fd, rdmap_fd; struct bpf_map *data_map, *bss_map; void *bss_mmaped = NULL, *map_mmaped = NULL, *tmp1, *tmp2; struct test_mmap__bss *bss_data; @@ -37,6 +37,17 @@ void test_mmap(void) data_map = skel->maps.data_map; data_map_fd = bpf_map__fd(data_map); + rdmap_fd = bpf_map__fd(skel->maps.rdonly_map); + tmp1 = mmap(NULL, 4096, PROT_READ | PROT_WRITE, MAP_SHARED, rdmap_fd, 0); + if (CHECK(tmp1 != MAP_FAILED, "rdonly_write_mmap", "unexpected success\n")) { + munmap(tmp1, 4096); + goto cleanup; + } + /* now double-check if it's mmap()'able at all */ + tmp1 = mmap(NULL, 4096, PROT_READ, MAP_SHARED, rdmap_fd, 0); + if (CHECK(tmp1 == MAP_FAILED, "rdonly_read_mmap", "failed: %d\n", errno)) + goto cleanup; + /* get map's ID */ memset(&map_info, 0, map_info_sz); err = bpf_obj_get_info_by_fd(data_map_fd, &map_info, &map_info_sz); diff --git a/tools/testing/selftests/bpf/progs/test_mmap.c b/tools/testing/selftests/bpf/progs/test_mmap.c index 6239596cd14e..4eb42cff5fe9 100644 --- a/tools/testing/selftests/bpf/progs/test_mmap.c +++ b/tools/testing/selftests/bpf/progs/test_mmap.c @@ -7,6 +7,14 @@ char _license[] SEC("license") = "GPL"; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 4096); + __uint(map_flags, BPF_F_MMAPABLE | BPF_F_RDONLY_PROG); + __type(key, __u32); + __type(value, char); +} rdonly_map SEC(".maps"); + struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(max_entries, 512 * 4); /* at least 4 pages of data */ From 5cf65922bb15279402e1e19b5ee8c51d618fa51f Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Thu, 21 May 2020 10:34:35 +0200 Subject: [PATCH 3/3] flow_dissector: Drop BPF flow dissector prog ref on netns cleanup When attaching a flow dissector program to a network namespace with bpf(BPF_PROG_ATTACH, ...) we grab a reference to bpf_prog. If netns gets destroyed while a flow dissector is still attached, and there are no other references to the prog, we leak the reference and the program remains loaded. Leak can be reproduced by running flow dissector tests from selftests/bpf: # bpftool prog list # ./test_flow_dissector.sh ... selftests: test_flow_dissector [PASS] # bpftool prog list 4: flow_dissector name _dissect tag e314084d332a5338 gpl loaded_at 2020-05-20T18:50:53+0200 uid 0 xlated 552B jited 355B memlock 4096B map_ids 3,4 btf_id 4 # Fix it by detaching the flow dissector program when netns is going away. Fixes: d58e468b1112 ("flow_dissector: implements flow dissector BPF hook") Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Reviewed-by: Stanislav Fomichev Link: https://lore.kernel.org/bpf/20200521083435.560256-1-jakub@cloudflare.com --- net/core/flow_dissector.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 3eff84824c8b..5dceed467f64 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -160,12 +160,10 @@ out: return ret; } -int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) +static int flow_dissector_bpf_prog_detach(struct net *net) { struct bpf_prog *attached; - struct net *net; - net = current->nsproxy->net_ns; mutex_lock(&flow_dissector_mutex); attached = rcu_dereference_protected(net->flow_dissector_prog, lockdep_is_held(&flow_dissector_mutex)); @@ -179,6 +177,24 @@ int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) return 0; } +int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) +{ + return flow_dissector_bpf_prog_detach(current->nsproxy->net_ns); +} + +static void __net_exit flow_dissector_pernet_pre_exit(struct net *net) +{ + /* We're not racing with attach/detach because there are no + * references to netns left when pre_exit gets called. + */ + if (rcu_access_pointer(net->flow_dissector_prog)) + flow_dissector_bpf_prog_detach(net); +} + +static struct pernet_operations flow_dissector_pernet_ops __net_initdata = { + .pre_exit = flow_dissector_pernet_pre_exit, +}; + /** * __skb_flow_get_ports - extract the upper layer ports and return them * @skb: sk_buff to extract the ports from @@ -1836,7 +1852,7 @@ static int __init init_default_flow_dissectors(void) skb_flow_dissector_init(&flow_keys_basic_dissector, flow_keys_basic_dissector_keys, ARRAY_SIZE(flow_keys_basic_dissector_keys)); - return 0; -} + return register_pernet_subsys(&flow_dissector_pernet_ops); +} core_initcall(init_default_flow_dissectors);