From 42378a9ca55347102bbf86708776061d8fe3ece2 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 28 Oct 2022 19:54:30 -0700 Subject: [PATCH 1/8] bpf, verifier: Fix memory leak in array reallocation for stack state If an error (NULL) is returned by krealloc(), callers of realloc_array() were setting their allocation pointers to NULL, but on error krealloc() does not touch the original allocation. This would result in a memory resource leak. Instead, free the old allocation on the error handling path. The memory leak information is as follows as also reported by Zhengchao: unreferenced object 0xffff888019801800 (size 256): comm "bpf_repo", pid 6490, jiffies 4294959200 (age 17.170s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000b211474b>] __kmalloc_node_track_caller+0x45/0xc0 [<0000000086712a0b>] krealloc+0x83/0xd0 [<00000000139aab02>] realloc_array+0x82/0xe2 [<00000000b1ca41d1>] grow_stack_state+0xfb/0x186 [<00000000cd6f36d2>] check_mem_access.cold+0x141/0x1341 [<0000000081780455>] do_check_common+0x5358/0xb350 [<0000000015f6b091>] bpf_check.cold+0xc3/0x29d [<000000002973c690>] bpf_prog_load+0x13db/0x2240 [<00000000028d1644>] __sys_bpf+0x1605/0x4ce0 [<00000000053f29bd>] __x64_sys_bpf+0x75/0xb0 [<0000000056fedaf5>] do_syscall_64+0x35/0x80 [<000000002bd58261>] entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: c69431aab67a ("bpf: verifier: Improve function state reallocation") Reported-by: Zhengchao Shao Reported-by: Kees Cook Signed-off-by: Kees Cook Signed-off-by: Daniel Borkmann Reviewed-by: Bill Wendling Cc: Lorenz Bauer Link: https://lore.kernel.org/bpf/20221029025433.2533810-1-keescook@chromium.org --- 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 7f0a9f6cb889..dd9019c8b0db 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1027,12 +1027,17 @@ out: */ static void *realloc_array(void *arr, size_t old_n, size_t new_n, size_t size) { + void *new_arr; + if (!new_n || old_n == new_n) goto out; - arr = krealloc_array(arr, new_n, size, GFP_KERNEL); - if (!arr) + new_arr = krealloc_array(arr, new_n, size, GFP_KERNEL); + if (!new_arr) { + kfree(arr); return NULL; + } + arr = new_arr; if (new_n > old_n) memset(arr + old_n * size, 0, (new_n - old_n) * size); From 8ec95b94716a1e4d126edc3fb2bc426a717e2dba Mon Sep 17 00:00:00 2001 From: Wang Yufen Date: Tue, 1 Nov 2022 09:31:36 +0800 Subject: [PATCH 2/8] bpf, sockmap: Fix the sk->sk_forward_alloc warning of sk_stream_kill_queues When running `test_sockmap` selftests, the following warning appears: WARNING: CPU: 2 PID: 197 at net/core/stream.c:205 sk_stream_kill_queues+0xd3/0xf0 Call Trace: inet_csk_destroy_sock+0x55/0x110 tcp_rcv_state_process+0xd28/0x1380 ? tcp_v4_do_rcv+0x77/0x2c0 tcp_v4_do_rcv+0x77/0x2c0 __release_sock+0x106/0x130 __tcp_close+0x1a7/0x4e0 tcp_close+0x20/0x70 inet_release+0x3c/0x80 __sock_release+0x3a/0xb0 sock_close+0x14/0x20 __fput+0xa3/0x260 task_work_run+0x59/0xb0 exit_to_user_mode_prepare+0x1b3/0x1c0 syscall_exit_to_user_mode+0x19/0x50 do_syscall_64+0x48/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae The root case is in commit 84472b436e76 ("bpf, sockmap: Fix more uncharged while msg has more_data"), where I used msg->sg.size to replace the tosend, causing breakage: if (msg->apply_bytes && msg->apply_bytes < tosend) tosend = psock->apply_bytes; Fixes: 84472b436e76 ("bpf, sockmap: Fix more uncharged while msg has more_data") Reported-by: Jakub Sitnicki Signed-off-by: Wang Yufen Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Acked-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/1667266296-8794-1-git-send-email-wangyufen@huawei.com --- net/ipv4/tcp_bpf.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index c501c329b1db..cf9c3e8f7ccb 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -278,7 +278,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, { bool cork = false, enospc = sk_msg_full(msg); struct sock *sk_redir; - u32 tosend, delta = 0; + u32 tosend, origsize, sent, delta = 0; u32 eval = __SK_NONE; int ret; @@ -333,10 +333,12 @@ more_data: cork = true; psock->cork = NULL; } - sk_msg_return(sk, msg, msg->sg.size); + sk_msg_return(sk, msg, tosend); release_sock(sk); + origsize = msg->sg.size; ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags); + sent = origsize - msg->sg.size; if (eval == __SK_REDIRECT) sock_put(sk_redir); @@ -375,7 +377,7 @@ more_data: msg->sg.data[msg->sg.start].page_link && msg->sg.data[msg->sg.start].length) { if (eval == __SK_REDIRECT) - sk_mem_charge(sk, msg->sg.size); + sk_mem_charge(sk, tosend - sent); goto more_data; } } From 34de8e6e0e1f66e431abf4123934a2581cb5f133 Mon Sep 17 00:00:00 2001 From: Pu Lehui Date: Wed, 2 Nov 2022 16:40:34 +0800 Subject: [PATCH 3/8] bpftool: Fix NULL pointer dereference when pin {PROG, MAP, LINK} without FILE When using bpftool to pin {PROG, MAP, LINK} without FILE, segmentation fault will occur. The reson is that the lack of FILE will cause strlen to trigger NULL pointer dereference. The corresponding stacktrace is shown below: do_pin do_pin_any do_pin_fd mount_bpffs_for_pin strlen(name) <- NULL pointer dereference Fix it by adding validation to the common process. Fixes: 75a1e792c335 ("tools: bpftool: Allow all prog/map handles for pinning objects") Signed-off-by: Pu Lehui Signed-off-by: Daniel Borkmann Reviewed-by: Quentin Monnet Link: https://lore.kernel.org/bpf/20221102084034.3342995-1-pulehui@huaweicloud.com --- tools/bpf/bpftool/common.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 8727765add88..0cdb4f711510 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -300,6 +300,9 @@ int do_pin_any(int argc, char **argv, int (*get_fd)(int *, char ***)) int err; int fd; + if (!REQ_ARGS(3)) + return -EINVAL; + fd = get_fd(&argc, &argv); if (fd < 0) return fd; From aec1dc972d27c837d1406310dab5170189eb01e5 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 2 Nov 2022 11:25:16 -0700 Subject: [PATCH 4/8] net/ipv4: Fix linux/in.h header dependencies __DECLARE_FLEX_ARRAY is defined in include/uapi/linux/stddef.h but doesn't seem to be explicitly included from include/uapi/linux/in.h, which breaks BPF selftests builds (once we sync linux/stddef.h into tools/include directory in the next patch). Fix this by explicitly including linux/stddef.h. Given this affects BPF CI and bpf tree, targeting this for bpf tree. Fixes: 5854a09b4957 ("net/ipv4: Use __DECLARE_FLEX_ARRAY() helper") Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Cc: Gustavo A. R. Silva Cc: Jakub Kicinski Link: https://lore.kernel.org/bpf/20221102182517.2675301-1-andrii@kernel.org --- include/uapi/linux/in.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index f243ce665f74..07a4cb149305 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -20,6 +20,7 @@ #define _UAPI_LINUX_IN_H #include +#include #include #include From a778f5d46b6287ebe26e24b48f3e8079c2db8ed2 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 2 Nov 2022 11:25:17 -0700 Subject: [PATCH 5/8] tools/headers: Pull in stddef.h to uapi to fix BPF selftests build in CI With recent sync of linux/in.h tools/include headers are now relying on __DECLARE_FLEX_ARRAY macro, which isn't itself defined inside tools/include headers anywhere and is instead assumed to be present in system-wide UAPI header. This breaks isolated environments that don't have kernel UAPI headers installed system-wide, like BPF CI ([0]). To fix this, bring in include/uapi/linux/stddef.h into tools/include. We can't just copy/paste it, though, it has to be processed with scripts/headers_install.sh, which has a dependency on scripts/unifdef. So the full command to (re-)generate stddef.h for inclusion into tools/include directory is: $ make scripts_unifdef && \ cp $KBUILD_OUTPUT/scripts/unifdef scripts/ && \ scripts/headers_install.sh include/uapi/linux/stddef.h tools/include/uapi/linux/stddef.h This assumes KBUILD_OUTPUT envvar is set and used for out-of-tree builds. [0] https://github.com/kernel-patches/bpf/actions/runs/3379432493/jobs/5610982609 Fixes: 036b8f5b8970 ("tools headers uapi: Update linux/in.h copy") Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Cc: Jakub Kicinski Cc: Arnaldo Carvalho de Melo Link: https://lore.kernel.org/bpf/20221102182517.2675301-2-andrii@kernel.org --- tools/include/uapi/linux/in.h | 1 + tools/include/uapi/linux/stddef.h | 47 +++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+) create mode 100644 tools/include/uapi/linux/stddef.h diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index f243ce665f74..07a4cb149305 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -20,6 +20,7 @@ #define _UAPI_LINUX_IN_H #include +#include #include #include diff --git a/tools/include/uapi/linux/stddef.h b/tools/include/uapi/linux/stddef.h new file mode 100644 index 000000000000..bb6ea517efb5 --- /dev/null +++ b/tools/include/uapi/linux/stddef.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_STDDEF_H +#define _LINUX_STDDEF_H + + + +#ifndef __always_inline +#define __always_inline __inline__ +#endif + +/** + * __struct_group() - Create a mirrored named and anonyomous struct + * + * @TAG: The tag name for the named sub-struct (usually empty) + * @NAME: The identifier name of the mirrored sub-struct + * @ATTRS: Any struct attributes (usually empty) + * @MEMBERS: The member declarations for the mirrored structs + * + * Used to create an anonymous union of two structs with identical layout + * and size: one anonymous and one named. The former's members can be used + * normally without sub-struct naming, and the latter can be used to + * reason about the start, end, and size of the group of struct members. + * The named struct can also be explicitly tagged for layer reuse, as well + * as both having struct attributes appended. + */ +#define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \ + union { \ + struct { MEMBERS } ATTRS; \ + struct TAG { MEMBERS } ATTRS NAME; \ + } + +/** + * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union + * + * @TYPE: The type of each flexible array element + * @NAME: The name of the flexible array member + * + * In order to have a flexible array member in a union or alone in a + * struct, it needs to be wrapped in an anonymous struct with at least 1 + * named member, but that member can be empty. + */ +#define __DECLARE_FLEX_ARRAY(TYPE, NAME) \ + struct { \ + struct { } __empty_ ## NAME; \ + TYPE NAME[]; \ + } +#endif From 8bbabb3fddcd0f858be69ed5abc9b470a239d6f2 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 1 Nov 2022 21:34:17 -0700 Subject: [PATCH 6/8] bpf, sock_map: Move cancel_work_sync() out of sock lock Stanislav reported a lockdep warning, which is caused by the cancel_work_sync() called inside sock_map_close(), as analyzed below by Jakub: psock->work.func = sk_psock_backlog() ACQUIRE psock->work_mutex sk_psock_handle_skb() skb_send_sock() __skb_send_sock() sendpage_unlocked() kernel_sendpage() sock->ops->sendpage = inet_sendpage() sk->sk_prot->sendpage = tcp_sendpage() ACQUIRE sk->sk_lock tcp_sendpage_locked() RELEASE sk->sk_lock RELEASE psock->work_mutex sock_map_close() ACQUIRE sk->sk_lock sk_psock_stop() sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED) cancel_work_sync() __cancel_work_timer() __flush_work() // wait for psock->work to finish RELEASE sk->sk_lock We can move the cancel_work_sync() out of the sock lock protection, but still before saved_close() was called. Fixes: 799aa7f98d53 ("skmsg: Avoid lock_sock() in sk_psock_backlog()") Reported-by: Stanislav Fomichev Signed-off-by: Cong Wang Signed-off-by: Daniel Borkmann Tested-by: Jakub Sitnicki Acked-by: John Fastabend Acked-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20221102043417.279409-1-xiyou.wangcong@gmail.com --- include/linux/skmsg.h | 2 +- net/core/skmsg.c | 7 ++----- net/core/sock_map.c | 7 ++++--- 3 files changed, 7 insertions(+), 9 deletions(-) diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 48f4b645193b..70d6cb94e580 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -376,7 +376,7 @@ static inline void sk_psock_report_error(struct sk_psock *psock, int err) } struct sk_psock *sk_psock_init(struct sock *sk, int node); -void sk_psock_stop(struct sk_psock *psock, bool wait); +void sk_psock_stop(struct sk_psock *psock); #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 1efdc47a999b..e6b9ced3eda8 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -803,16 +803,13 @@ static void sk_psock_link_destroy(struct sk_psock *psock) } } -void sk_psock_stop(struct sk_psock *psock, bool wait) +void sk_psock_stop(struct sk_psock *psock) { spin_lock_bh(&psock->ingress_lock); sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); sk_psock_cork_free(psock); __sk_psock_zap_ingress(psock); spin_unlock_bh(&psock->ingress_lock); - - if (wait) - cancel_work_sync(&psock->work); } static void sk_psock_done_strp(struct sk_psock *psock); @@ -850,7 +847,7 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock) sk_psock_stop_verdict(sk, psock); write_unlock_bh(&sk->sk_callback_lock); - sk_psock_stop(psock, false); + sk_psock_stop(psock); INIT_RCU_WORK(&psock->rwork, sk_psock_destroy); queue_rcu_work(system_wq, &psock->rwork); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index a660baedd9e7..81beb16ab1eb 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -1596,7 +1596,7 @@ void sock_map_destroy(struct sock *sk) saved_destroy = psock->saved_destroy; sock_map_remove_links(sk, psock); rcu_read_unlock(); - sk_psock_stop(psock, false); + sk_psock_stop(psock); sk_psock_put(sk, psock); saved_destroy(sk); } @@ -1619,9 +1619,10 @@ void sock_map_close(struct sock *sk, long timeout) saved_close = psock->saved_close; sock_map_remove_links(sk, psock); rcu_read_unlock(); - sk_psock_stop(psock, true); - sk_psock_put(sk, psock); + sk_psock_stop(psock); release_sock(sk); + cancel_work_sync(&psock->work); + sk_psock_put(sk, psock); saved_close(sk, timeout); } EXPORT_SYMBOL_GPL(sock_map_close); From f1db20814af532f85e091231223e5e4818e8464b Mon Sep 17 00:00:00 2001 From: Youlin Li Date: Thu, 3 Nov 2022 17:34:39 +0800 Subject: [PATCH 7/8] bpf: Fix wrong reg type conversion in release_reference() Some helper functions will allocate memory. To avoid memory leaks, the verifier requires the eBPF program to release these memories by calling the corresponding helper functions. When a resource is released, all pointer registers corresponding to the resource should be invalidated. The verifier use release_references() to do this job, by apply __mark_reg_unknown() to each relevant register. It will give these registers the type of SCALAR_VALUE. A register that will contain a pointer value at runtime, but of type SCALAR_VALUE, which may allow the unprivileged user to get a kernel pointer by storing this register into a map. Using __mark_reg_not_init() while NOT allow_ptr_leaks can mitigate this problem. Fixes: fd978bf7fd31 ("bpf: Add reference tracking to verifier") Signed-off-by: Youlin Li Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20221103093440.3161-1-liulin063@gmail.com --- kernel/bpf/verifier.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index dd9019c8b0db..225666307bba 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6623,8 +6623,12 @@ static int release_reference(struct bpf_verifier_env *env, return err; bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ - if (reg->ref_obj_id == ref_obj_id) - __mark_reg_unknown(env, reg); + if (reg->ref_obj_id == ref_obj_id) { + if (!env->allow_ptr_leaks) + __mark_reg_not_init(env, reg); + else + __mark_reg_unknown(env, reg); + } })); return 0; From 475244f5e06beeda7b557d9dde46a5f439bf3379 Mon Sep 17 00:00:00 2001 From: Youlin Li Date: Thu, 3 Nov 2022 17:34:40 +0800 Subject: [PATCH 8/8] selftests/bpf: Add verifier test for release_reference() Add a test case to ensure that released pointer registers will not be leaked into the map. Before fix: ./test_verifier 984 984/u reference tracking: try to leak released ptr reg FAIL Unexpected success to load! verification time 67 usec stack depth 4 processed 23 insns (limit 1000000) max_states_per_insn 0 total_states 2 peak_states 2 mark_read 1 984/p reference tracking: try to leak released ptr reg OK Summary: 1 PASSED, 0 SKIPPED, 1 FAILED After fix: ./test_verifier 984 984/u reference tracking: try to leak released ptr reg OK 984/p reference tracking: try to leak released ptr reg OK Summary: 2 PASSED, 0 SKIPPED, 0 FAILED Signed-off-by: Youlin Li Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20221103093440.3161-2-liulin063@gmail.com --- .../selftests/bpf/verifier/ref_tracking.c | 36 +++++++++++++++++++ 1 file changed, 36 insertions(+) diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c index f18ce867271f..fd683a32a276 100644 --- a/tools/testing/selftests/bpf/verifier/ref_tracking.c +++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c @@ -1044,3 +1044,39 @@ .result_unpriv = REJECT, .errstr_unpriv = "unknown func", }, +{ + "reference tracking: try to leak released ptr reg", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_9, BPF_REG_0), + + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_2, 8), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_ringbuf_reserve), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_8, BPF_REG_0), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_8), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_EMIT_CALL(BPF_FUNC_ringbuf_discard), + BPF_MOV64_IMM(BPF_REG_0, 0), + + BPF_STX_MEM(BPF_DW, BPF_REG_9, BPF_REG_8, 0), + BPF_EXIT_INSN() + }, + .fixup_map_array_48b = { 4 }, + .fixup_map_ringbuf = { 11 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R8 !read_ok" +},