From 27e23836ce22a3e5d89712ef832ab72e47ce9f43 Mon Sep 17 00:00:00 2001 From: Daniel Müller Date: Wed, 10 Aug 2022 20:07:10 +0000 Subject: selftests/bpf: Add lru_bug to s390x deny list The lru_bug BPF selftest is failing execution on s390x machines. The failure is due to program attachment failing in turn, similar to a bunch of other tests. Those other tests have already been deny-listed and with this change we do the same for the lru_bug test, adding it to the corresponding file. Fixes: de7b9927105b ("selftests/bpf: Add test for prealloc_lru_pop bug") Signed-off-by: Daniel Müller Acked-by: Mykola Lysenko Link: https://lore.kernel.org/r/20220810200710.1300299-1-deso@posteo.net Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/DENYLIST.s390x | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x index e33cab34d22f..db9810611788 100644 --- a/tools/testing/selftests/bpf/DENYLIST.s390x +++ b/tools/testing/selftests/bpf/DENYLIST.s390x @@ -65,3 +65,4 @@ send_signal # intermittently fails to receive signa select_reuseport # intermittently fails on new s390x setup xdp_synproxy # JIT does not support calling kernel function (kfunc) unpriv_bpf_disabled # fentry +lru_bug # prog 'printk': failed to auto-attach: -524 -- cgit v1.2.3 From 58ca14ed98c87cfe0d1408cc65a9745d9e9b7a56 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 12 Aug 2022 13:32:59 +0200 Subject: xsk: Fix corrupted packets for XDP_SHARED_UMEM Fix an issue in XDP_SHARED_UMEM mode together with aligned mode where packets are corrupted for the second and any further sockets bound to the same umem. In other words, this does not affect the first socket bound to the umem. The culprit for this bug is that the initialization of the DMA addresses for the pre-populated xsk buffer pool entries was not performed for any socket but the first one bound to the umem. Only the linear array of DMA addresses was populated. Fix this by populating the DMA addresses in the xsk buffer pool for every socket bound to the same umem. Fixes: 94033cd8e73b8 ("xsk: Optimize for aligned case") Reported-by: Alasdair McWilliam Reported-by: Intrusion Shield Team Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Tested-by: Alasdair McWilliam Acked-by: Maciej Fijalkowski Link: https://lore.kernel.org/xdp-newbies/6205E10C-292E-4995-9D10-409649354226@outlook.com/ Link: https://lore.kernel.org/bpf/20220812113259.531-1-magnus.karlsson@gmail.com --- net/xdp/xsk_buff_pool.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index f70112176b7c..a71a8c6edf55 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -379,6 +379,16 @@ static void xp_check_dma_contiguity(struct xsk_dma_map *dma_map) static int xp_init_dma_info(struct xsk_buff_pool *pool, struct xsk_dma_map *dma_map) { + if (!pool->unaligned) { + u32 i; + + for (i = 0; i < pool->heads_cnt; i++) { + struct xdp_buff_xsk *xskb = &pool->heads[i]; + + xp_init_xskb_dma(xskb, pool, dma_map->dma_pages, xskb->orig_addr); + } + } + pool->dma_pages = kvcalloc(dma_map->dma_pages_cnt, sizeof(*pool->dma_pages), GFP_KERNEL); if (!pool->dma_pages) return -ENOMEM; @@ -428,12 +438,6 @@ int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, if (pool->unaligned) xp_check_dma_contiguity(dma_map); - else - for (i = 0; i < pool->heads_cnt; i++) { - struct xdp_buff_xsk *xskb = &pool->heads[i]; - - xp_init_xskb_dma(xskb, pool, dma_map->dma_pages, xskb->orig_addr); - } err = xp_init_dma_info(pool, dma_map); if (err) { -- cgit v1.2.3 From 583585e48d965338e73e1eb383768d16e0922d73 Mon Sep 17 00:00:00 2001 From: Liu Jian Date: Tue, 9 Aug 2022 17:49:15 +0800 Subject: skmsg: Fix wrong last sg check in sk_msg_recvmsg() Fix one kernel NULL pointer dereference as below: [ 224.462334] Call Trace: [ 224.462394] __tcp_bpf_recvmsg+0xd3/0x380 [ 224.462441] ? sock_has_perm+0x78/0xa0 [ 224.462463] tcp_bpf_recvmsg+0x12e/0x220 [ 224.462494] inet_recvmsg+0x5b/0xd0 [ 224.462534] __sys_recvfrom+0xc8/0x130 [ 224.462574] ? syscall_trace_enter+0x1df/0x2e0 [ 224.462606] ? __do_page_fault+0x2de/0x500 [ 224.462635] __x64_sys_recvfrom+0x24/0x30 [ 224.462660] do_syscall_64+0x5d/0x1d0 [ 224.462709] entry_SYSCALL_64_after_hwframe+0x65/0xca In commit 9974d37ea75f ("skmsg: Fix invalid last sg check in sk_msg_recvmsg()"), we change last sg check to sg_is_last(), but in sockmap redirection case (without stream_parser/stream_verdict/ skb_verdict), we did not mark the end of the scatterlist. Check the sk_msg_alloc, sk_msg_page_add, and bpf_msg_push_data functions, they all do not mark the end of sg. They are expected to use sg.end for end judgment. So the judgment of '(i != msg_rx->sg.end)' is added back here. Fixes: 9974d37ea75f ("skmsg: Fix invalid last sg check in sk_msg_recvmsg()") Signed-off-by: Liu Jian Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Acked-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20220809094915.150391-1-liujian56@huawei.com --- net/core/skmsg.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index f47338d89d5d..5be4485ff07d 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -461,7 +461,7 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, if (copied == len) break; - } while (!sg_is_last(sge)); + } while ((i != msg_rx->sg.end) && !sg_is_last(sge)); if (unlikely(peek)) { msg_rx = sk_psock_next_msg(psock, msg_rx); @@ -471,7 +471,7 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, } msg_rx->sg.start = i; - if (!sge->length && sg_is_last(sge)) { + if (!sge->length && (i == msg_rx->sg.end || sg_is_last(sge))) { msg_rx = sk_psock_dequeue_msg(psock); kfree_sk_msg(msg_rx); } -- cgit v1.2.3 From 3024d95a4c521c278a7504ee9e80c57c3a9750e0 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 17 Aug 2022 23:32:09 +0200 Subject: bpf: Partially revert flexible-array member replacement Partially revert 94dfc73e7cf4 ("treewide: uapi: Replace zero-length arrays with flexible-array members") given it breaks BPF UAPI. For example, BPF CI run reveals build breakage under LLVM: [...] CLNG-BPF [test_maps] map_ptr_kern.o CLNG-BPF [test_maps] btf__core_reloc_arrays___diff_arr_val_sz.o CLNG-BPF [test_maps] test_bpf_cookie.o progs/map_ptr_kern.c:314:26: error: field 'trie_key' with variable sized type 'struct bpf_lpm_trie_key' not at the end of a struct or class is a GNU extension [-Werror,-Wgnu-variable-sized-type-not-at-end] struct bpf_lpm_trie_key trie_key; ^ CLNG-BPF [test_maps] btf__core_reloc_type_based___diff.o 1 error generated. make: *** [Makefile:521: /tmp/runner/work/bpf/bpf/tools/testing/selftests/bpf/map_ptr_kern.o] Error 1 make: *** Waiting for unfinished jobs.... [...] Typical usage of the bpf_lpm_trie_key is that the struct gets embedded into a user defined key for the LPM BPF map, from the selftest example: struct bpf_lpm_trie_key { <-- UAPI exported struct __u32 prefixlen; __u8 data[]; }; struct lpm_key { <-- BPF program defined struct struct bpf_lpm_trie_key trie_key; __u32 data; }; Undo this for BPF until a different solution can be found. It's the only flexible- array member case in the UAPI header. This was discovered in BPF CI after Dave reported that the include/uapi/linux/bpf.h header was out of sync with tools/include/uapi/linux/bpf.h after 94dfc73e7cf4. And the subsequent sync attempt failed CI. Fixes: 94dfc73e7cf4 ("treewide: uapi: Replace zero-length arrays with flexible-array members") Reported-by: Dave Marchevsky Signed-off-by: Daniel Borkmann Cc: Gustavo A. R. Silva Link: https://lore.kernel.org/bpf/22aebc88-da67-f086-e620-dd4a16e2bc69@iogearbox.net --- include/uapi/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7bf9ba1329be..59a217ca2dfd 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -79,7 +79,7 @@ struct bpf_insn { /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */ struct bpf_lpm_trie_key { __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */ - __u8 data[]; /* Arbitrary size */ + __u8 data[0]; /* Arbitrary size */ }; struct bpf_cgroup_storage_key { -- cgit v1.2.3 From 14b20b784f59bdd95f6f1cfb112c9818bcec4d84 Mon Sep 17 00:00:00 2001 From: YiFei Zhu Date: Tue, 16 Aug 2022 20:55:16 +0000 Subject: bpf: Restrict bpf_sys_bpf to CAP_PERFMON The verifier cannot perform sufficient validation of any pointers passed into bpf_attr and treats them as integers rather than pointers. The helper will then read from arbitrary pointers passed into it. Restrict the helper to CAP_PERFMON since the security model in BPF of arbitrary kernel read is CAP_BPF + CAP_PERFMON. Fixes: af2ac3e13e45 ("bpf: Prepare bpf syscall to be used from kernel and user space.") Signed-off-by: YiFei Zhu Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220816205517.682470-1-zhuyifei@google.com --- kernel/bpf/syscall.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a4d40d98428a..27760627370d 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -5197,7 +5197,7 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_sys_bpf: - return &bpf_sys_bpf_proto; + return !perfmon_capable() ? NULL : &bpf_sys_bpf_proto; case BPF_FUNC_btf_find_by_name_kind: return &bpf_btf_find_by_name_kind_proto; case BPF_FUNC_sys_close: -- cgit v1.2.3 From 7ec9fce4b31604f8415136a4c07f7dc8ad431aec Mon Sep 17 00:00:00 2001 From: Eyal Birger Date: Thu, 18 Aug 2022 10:41:18 +0300 Subject: ip_tunnel: Respect tunnel key's "flow_flags" in IP tunnels Commit 451ef36bd229 ("ip_tunnels: Add new flow flags field to ip_tunnel_key") added a "flow_flags" member to struct ip_tunnel_key which was later used by the commit in the fixes tag to avoid dropping packets with sources that aren't locally configured when set in bpf_set_tunnel_key(). VXLAN and GENEVE were made to respect this flag, ip tunnels like IPIP and GRE were not. This commit fixes this omission by making ip_tunnel_init_flow() receive the flow flags from the tunnel key in the relevant collect_md paths. Fixes: b8fff748521c ("bpf: Set flow flag to allow any source IP in bpf_tunnel_key") Signed-off-by: Eyal Birger Signed-off-by: Daniel Borkmann Reviewed-by: Paul Chaignon Link: https://lore.kernel.org/bpf/20220818074118.726639-1-eyal.birger@gmail.com --- drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c | 3 ++- include/net/ip_tunnels.h | 4 +++- net/ipv4/ip_gre.c | 2 +- net/ipv4/ip_tunnel.c | 7 ++++--- 4 files changed, 10 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index 39904dacf4f0..b3472fb94617 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -423,7 +423,8 @@ mlxsw_sp_span_gretap4_route(const struct net_device *to_dev, parms = mlxsw_sp_ipip_netdev_parms4(to_dev); ip_tunnel_init_flow(&fl4, parms.iph.protocol, *daddrp, *saddrp, - 0, 0, dev_net(to_dev), parms.link, tun->fwmark, 0); + 0, 0, dev_net(to_dev), parms.link, tun->fwmark, 0, + 0); rt = ip_route_output_key(tun->net, &fl4); if (IS_ERR(rt)) diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 63fac94f9ace..ced80e2f8b58 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -246,7 +246,8 @@ static inline void ip_tunnel_init_flow(struct flowi4 *fl4, __be32 daddr, __be32 saddr, __be32 key, __u8 tos, struct net *net, int oif, - __u32 mark, __u32 tun_inner_hash) + __u32 mark, __u32 tun_inner_hash, + __u8 flow_flags) { memset(fl4, 0, sizeof(*fl4)); @@ -263,6 +264,7 @@ static inline void ip_tunnel_init_flow(struct flowi4 *fl4, fl4->fl4_gre_key = key; fl4->flowi4_mark = mark; fl4->flowi4_multipath_hash = tun_inner_hash; + fl4->flowi4_flags = flow_flags; } int ip_tunnel_init(struct net_device *dev); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 5c58e21f724e..f866d6282b2b 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -609,7 +609,7 @@ static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) ip_tunnel_init_flow(&fl4, IPPROTO_GRE, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), key->tos & ~INET_ECN_MASK, dev_net(dev), 0, - skb->mark, skb_get_hash(skb)); + skb->mark, skb_get_hash(skb), key->flow_flags); rt = ip_route_output_key(dev_net(dev), &fl4); if (IS_ERR(rt)) return PTR_ERR(rt); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index e65e948cab9f..019f3b0839c5 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -295,7 +295,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev) ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr, iph->saddr, tunnel->parms.o_key, RT_TOS(iph->tos), dev_net(dev), - tunnel->parms.link, tunnel->fwmark, 0); + tunnel->parms.link, tunnel->fwmark, 0, 0); rt = ip_route_output_key(tunnel->net, &fl4); if (!IS_ERR(rt)) { @@ -570,7 +570,8 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), RT_TOS(tos), - dev_net(dev), 0, skb->mark, skb_get_hash(skb)); + dev_net(dev), 0, skb->mark, skb_get_hash(skb), + key->flow_flags); if (tunnel->encap.type != TUNNEL_ENCAP_NONE) goto tx_error; @@ -729,7 +730,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, tunnel->parms.o_key, RT_TOS(tos), dev_net(dev), tunnel->parms.link, - tunnel->fwmark, skb_get_hash(skb)); + tunnel->fwmark, skb_get_hash(skb), 0); if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) goto tx_error; -- cgit v1.2.3 From 7d6620f107bae6ed687ff07668e8e8f855487aa9 Mon Sep 17 00:00:00 2001 From: Pu Lehui Date: Sat, 13 Aug 2022 21:40:30 +0800 Subject: bpf, cgroup: Fix kernel BUG in purge_effective_progs Syzkaller reported a triggered kernel BUG as follows: ------------[ cut here ]------------ kernel BUG at kernel/bpf/cgroup.c:925! invalid opcode: 0000 [#1] PREEMPT SMP NOPTI CPU: 1 PID: 194 Comm: detach Not tainted 5.19.0-14184-g69dac8e431af #8 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 RIP: 0010:__cgroup_bpf_detach+0x1f2/0x2a0 Code: 00 e8 92 60 30 00 84 c0 75 d8 4c 89 e0 31 f6 85 f6 74 19 42 f6 84 28 48 05 00 00 02 75 0e 48 8b 80 c0 00 00 00 48 85 c0 75 e5 <0f> 0b 48 8b 0c5 RSP: 0018:ffffc9000055bdb0 EFLAGS: 00000246 RAX: 0000000000000000 RBX: ffff888100ec0800 RCX: ffffc900000f1000 RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff888100ec4578 RBP: 0000000000000000 R08: ffff888100ec0800 R09: 0000000000000040 R10: 0000000000000000 R11: 0000000000000000 R12: ffff888100ec4000 R13: 000000000000000d R14: ffffc90000199000 R15: ffff888100effb00 FS: 00007f68213d2b80(0000) GS:ffff88813bc80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055f74a0e5850 CR3: 0000000102836000 CR4: 00000000000006e0 Call Trace: cgroup_bpf_prog_detach+0xcc/0x100 __sys_bpf+0x2273/0x2a00 __x64_sys_bpf+0x17/0x20 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f68214dbcb9 Code: 08 44 89 e0 5b 41 5c c3 66 0f 1f 84 00 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff8 RSP: 002b:00007ffeb487db68 EFLAGS: 00000246 ORIG_RAX: 0000000000000141 RAX: ffffffffffffffda RBX: 000000000000000b RCX: 00007f68214dbcb9 RDX: 0000000000000090 RSI: 00007ffeb487db70 RDI: 0000000000000009 RBP: 0000000000000003 R08: 0000000000000012 R09: 0000000b00000003 R10: 00007ffeb487db70 R11: 0000000000000246 R12: 00007ffeb487dc20 R13: 0000000000000004 R14: 0000000000000001 R15: 000055f74a1011b0 Modules linked in: ---[ end trace 0000000000000000 ]--- Repetition steps: For the following cgroup tree, root | cg1 | cg2 1. attach prog2 to cg2, and then attach prog1 to cg1, both bpf progs attach type is NONE or OVERRIDE. 2. write 1 to /proc/thread-self/fail-nth for failslab. 3. detach prog1 for cg1, and then kernel BUG occur. Failslab injection will cause kmalloc fail and fall back to purge_effective_progs. The problem is that cg2 have attached another prog, so when go through cg2 layer, iteration will add pos to 1, and subsequent operations will be skipped by the following condition, and cg will meet NULL in the end. `if (pos && !(cg->bpf.flags[atype] & BPF_F_ALLOW_MULTI))` The NULL cg means no link or prog match, this is as expected, and it's not a bug. So here just skip the no match situation. Fixes: 4c46091ee985 ("bpf: Fix KASAN use-after-free Read in compute_effective_progs") Signed-off-by: Pu Lehui Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220813134030.1972696-1-pulehui@huawei.com --- kernel/bpf/cgroup.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 59b7eb60d5b4..4a400cd63731 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -921,8 +921,10 @@ static void purge_effective_progs(struct cgroup *cgrp, struct bpf_prog *prog, pos++; } } + + /* no link or prog match, skip the cgroup of this layer */ + continue; found: - BUG_ON(!cg); progs = rcu_dereference_protected( desc->bpf.effective[atype], lockdep_is_held(&cgroup_mutex)); -- cgit v1.2.3 From 0947ae1121083d363d522ff7518ee72b55bd8d29 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Tue, 23 Aug 2022 14:58:04 -0700 Subject: bpf: Fix a data-race around bpf_jit_limit. While reading bpf_jit_limit, it can be changed concurrently via sysctl, WRITE_ONCE() in __do_proc_doulongvec_minmax(). The size of bpf_jit_limit is long, so we need to add a paired READ_ONCE() to avoid load-tearing. Fixes: ede95a63b5e8 ("bpf: add bpf_jit_limit knob to restrict unpriv allocations") Signed-off-by: Kuniyuki Iwashima Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20220823215804.2177-1-kuniyu@amazon.com --- kernel/bpf/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index c1e10d088dbb..3d9eb3ae334c 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -971,7 +971,7 @@ pure_initcall(bpf_jit_charge_init); int bpf_jit_charge_modmem(u32 size) { - if (atomic_long_add_return(size, &bpf_jit_current) > bpf_jit_limit) { + if (atomic_long_add_return(size, &bpf_jit_current) > READ_ONCE(bpf_jit_limit)) { if (!bpf_capable()) { atomic_long_sub(size, &bpf_jit_current); return -EPERM; -- cgit v1.2.3 From 2fc31465c5373b5ca4edf2e5238558cb62902311 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Tue, 23 Aug 2022 20:52:59 +0200 Subject: bpf: Do mark_chain_precision for ARG_CONST_ALLOC_SIZE_OR_ZERO Precision markers need to be propagated whenever we have an ARG_CONST_* style argument, as the verifier cannot consider imprecise scalars to be equivalent for the purposes of states_equal check when such arguments refine the return value (in this case, set mem_size for PTR_TO_MEM). The resultant mem_size for the R0 is derived from the constant value, and if the verifier incorrectly prunes states considering them equivalent where such arguments exist (by seeing that both registers have reg->precise as false in regsafe), we can end up with invalid programs passing the verifier which can do access beyond what should have been the correct mem_size in that explored state. To show a concrete example of the problem: 0000000000000000 : 0: r2 = *(u32 *)(r1 + 80) 1: r1 = *(u32 *)(r1 + 76) 2: r3 = r1 3: r3 += 4 4: if r3 > r2 goto +18 5: w2 = 0 6: *(u32 *)(r1 + 0) = r2 7: r1 = *(u32 *)(r1 + 0) 8: r2 = 1 9: if w1 == 0 goto +1 10: r2 = -1 0000000000000058 : 11: r1 = 0 ll 13: r3 = 0 14: call bpf_ringbuf_reserve 15: if r0 == 0 goto +7 16: r1 = r0 17: r1 += 16777215 18: w2 = 0 19: *(u8 *)(r1 + 0) = r2 20: r1 = r0 21: r2 = 0 22: call bpf_ringbuf_submit 00000000000000b8 : 23: w0 = 0 24: exit For the first case, the single line execution's exploration will prune the search at insn 14 for the branch insn 9's second leg as it will be verified first using r2 = -1 (UINT_MAX), while as w1 at insn 9 will always be 0 so at runtime we don't get error for being greater than UINT_MAX/4 from bpf_ringbuf_reserve. The verifier during regsafe just sees reg->precise as false for both r2 registers in both states, hence considers them equal for purposes of states_equal. If we propagated precise markers using the backtracking support, we would use the precise marking to then ensure that old r2 (UINT_MAX) was within the new r2 (1) and this would never be true, so the verification would rightfully fail. The end result is that the out of bounds access at instruction 19 would be permitted without this fix. Note that reg->precise is always set to true when user does not have CAP_BPF (or when subprog count is greater than 1 (i.e. use of any static or global functions)), hence this is only a problem when precision marks need to be explicitly propagated (i.e. privileged users with CAP_BPF). A simplified test case has been included in the next patch to prevent future regressions. Fixes: 457f44363a88 ("bpf: Implement BPF ring buffer and verifier support for it") Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220823185300.406-2-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 096fdac70165..30c6eebce146 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6066,6 +6066,9 @@ skip_type_check: return -EACCES; } meta->mem_size = reg->var_off.value; + err = mark_chain_precision(env, regno); + if (err) + return err; break; case ARG_PTR_TO_INT: case ARG_PTR_TO_LONG: -- cgit v1.2.3 From 1800b2ac96d8bc4ccdddc2ea9e83ecaffd54d3f2 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Tue, 23 Aug 2022 20:55:00 +0200 Subject: selftests/bpf: Add regression test for pruning fix Add a test to ensure we do mark_chain_precision for the argument type ARG_CONST_ALLOC_SIZE_OR_ZERO. For other argument types, this was already done, but propagation for missing for this case. Without the fix, this test case loads successfully. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220823185500.467-1-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/verifier/precise.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c index 9e754423fa8b..6c03a7d805f9 100644 --- a/tools/testing/selftests/bpf/verifier/precise.c +++ b/tools/testing/selftests/bpf/verifier/precise.c @@ -192,3 +192,28 @@ .result = VERBOSE_ACCEPT, .retval = -1, }, +{ + "precise: mark_chain_precision for ARG_CONST_ALLOC_SIZE_OR_ZERO", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, offsetof(struct xdp_md, ingress_ifindex)), + BPF_LD_MAP_FD(BPF_REG_6, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_2, 1), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 0, 1), + BPF_MOV64_IMM(BPF_REG_2, 0x1000), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 42), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_ringbuf = { 1 }, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = BPF_F_TEST_STATE_FREQ, + .errstr = "invalid access to memory, mem_size=1 off=42 size=8", + .result = REJECT, +}, -- cgit v1.2.3 From a657182a5c5150cdfacb6640aad1d2712571a409 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 25 Aug 2022 23:26:47 +0200 Subject: bpf: Don't use tnum_range on array range checking for poke descriptors Hsin-Wei reported a KASAN splat triggered by their BPF runtime fuzzer which is based on a customized syzkaller: BUG: KASAN: slab-out-of-bounds in bpf_int_jit_compile+0x1257/0x13f0 Read of size 8 at addr ffff888004e90b58 by task syz-executor.0/1489 CPU: 1 PID: 1489 Comm: syz-executor.0 Not tainted 5.19.0 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 Call Trace: dump_stack_lvl+0x9c/0xc9 print_address_description.constprop.0+0x1f/0x1f0 ? bpf_int_jit_compile+0x1257/0x13f0 kasan_report.cold+0xeb/0x197 ? kvmalloc_node+0x170/0x200 ? bpf_int_jit_compile+0x1257/0x13f0 bpf_int_jit_compile+0x1257/0x13f0 ? arch_prepare_bpf_dispatcher+0xd0/0xd0 ? rcu_read_lock_sched_held+0x43/0x70 bpf_prog_select_runtime+0x3e8/0x640 ? bpf_obj_name_cpy+0x149/0x1b0 bpf_prog_load+0x102f/0x2220 ? __bpf_prog_put.constprop.0+0x220/0x220 ? find_held_lock+0x2c/0x110 ? __might_fault+0xd6/0x180 ? lock_downgrade+0x6e0/0x6e0 ? lock_is_held_type+0xa6/0x120 ? __might_fault+0x147/0x180 __sys_bpf+0x137b/0x6070 ? bpf_perf_link_attach+0x530/0x530 ? new_sync_read+0x600/0x600 ? __fget_files+0x255/0x450 ? lock_downgrade+0x6e0/0x6e0 ? fput+0x30/0x1a0 ? ksys_write+0x1a8/0x260 __x64_sys_bpf+0x7a/0xc0 ? syscall_enter_from_user_mode+0x21/0x70 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f917c4e2c2d The problem here is that a range of tnum_range(0, map->max_entries - 1) has limited ability to represent the concrete tight range with the tnum as the set of resulting states from value + mask can result in a superset of the actual intended range, and as such a tnum_in(range, reg->var_off) check may yield true when it shouldn't, for example tnum_range(0, 2) would result in 00XX -> v = 0000, m = 0011 such that the intended set of {0, 1, 2} is here represented by a less precise superset of {0, 1, 2, 3}. As the register is known const scalar, really just use the concrete reg->var_off.value for the upper index check. Fixes: d2e4c1e6c294 ("bpf: Constant map key tracking for prog array pokes") Reported-by: Hsin-Wei Hung Signed-off-by: Daniel Borkmann Cc: Shung-Hsi Yu Acked-by: John Fastabend Link: https://lore.kernel.org/r/984b37f9fdf7ac36831d2137415a4a915744c1b6.1661462653.git.daniel@iogearbox.net Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 30c6eebce146..3eadb14e090b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -7033,8 +7033,7 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; struct bpf_reg_state *regs = cur_regs(env), *reg; struct bpf_map *map = meta->map_ptr; - struct tnum range; - u64 val; + u64 val, max; int err; if (func_id != BPF_FUNC_tail_call) @@ -7044,10 +7043,11 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, return -EINVAL; } - range = tnum_range(0, map->max_entries - 1); reg = ®s[BPF_REG_3]; + val = reg->var_off.value; + max = map->max_entries; - if (!register_is_const(reg) || !tnum_in(range, reg->var_off)) { + if (!(register_is_const(reg) && val < max)) { bpf_map_key_store(aux, BPF_MAP_KEY_POISON); return 0; } @@ -7055,8 +7055,6 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, err = mark_chain_precision(env, BPF_REG_3); if (err) return err; - - val = reg->var_off.value; if (bpf_map_key_unseen(aux)) bpf_map_key_store(aux, val); else if (!bpf_map_key_poisoned(aux) && -- cgit v1.2.3