diff options
author | David S. Miller <davem@davemloft.net> | 2020-03-30 19:52:37 -0700 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2020-03-30 19:52:37 -0700 |
commit | ed52f2c608c9451fa2bad298b2ab927416105d65 (patch) | |
tree | d624be01447b5d578aa79b02b37f0023a867bb42 | |
parent | f87238d30c0d550553a37585d0e27a8052952bb4 (diff) | |
parent | 8596a75f6c830a693ec86e6467a58b225713a7f1 (diff) | |
download | linux-stable-ed52f2c608c9451fa2bad298b2ab927416105d65.tar.gz linux-stable-ed52f2c608c9451fa2bad298b2ab927416105d65.tar.bz2 linux-stable-ed52f2c608c9451fa2bad298b2ab927416105d65.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Signed-off-by: David S. Miller <davem@davemloft.net>
107 files changed, 6086 insertions, 1728 deletions
diff --git a/Documentation/bpf/bpf_lsm.rst b/Documentation/bpf/bpf_lsm.rst new file mode 100644 index 000000000000..1c0a75a51d79 --- /dev/null +++ b/Documentation/bpf/bpf_lsm.rst @@ -0,0 +1,142 @@ +.. SPDX-License-Identifier: GPL-2.0+ +.. Copyright (C) 2020 Google LLC. + +================ +LSM BPF Programs +================ + +These BPF programs allow runtime instrumentation of the LSM hooks by privileged +users to implement system-wide MAC (Mandatory Access Control) and Audit +policies using eBPF. + +Structure +--------- + +The example shows an eBPF program that can be attached to the ``file_mprotect`` +LSM hook: + +.. c:function:: int file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot); + +Other LSM hooks which can be instrumented can be found in +``include/linux/lsm_hooks.h``. + +eBPF programs that use :doc:`/bpf/btf` do not need to include kernel headers +for accessing information from the attached eBPF program's context. They can +simply declare the structures in the eBPF program and only specify the fields +that need to be accessed. + +.. code-block:: c + + struct mm_struct { + unsigned long start_brk, brk, start_stack; + } __attribute__((preserve_access_index)); + + struct vm_area_struct { + unsigned long start_brk, brk, start_stack; + unsigned long vm_start, vm_end; + struct mm_struct *vm_mm; + } __attribute__((preserve_access_index)); + + +.. note:: The order of the fields is irrelevant. + +This can be further simplified (if one has access to the BTF information at +build time) by generating the ``vmlinux.h`` with: + +.. code-block:: console + + # bpftool btf dump file <path-to-btf-vmlinux> format c > vmlinux.h + +.. note:: ``path-to-btf-vmlinux`` can be ``/sys/kernel/btf/vmlinux`` if the + build environment matches the environment the BPF programs are + deployed in. + +The ``vmlinux.h`` can then simply be included in the BPF programs without +requiring the definition of the types. + +The eBPF programs can be declared using the``BPF_PROG`` +macros defined in `tools/lib/bpf/bpf_tracing.h`_. In this +example: + + * ``"lsm/file_mprotect"`` indicates the LSM hook that the program must + be attached to + * ``mprotect_audit`` is the name of the eBPF program + +.. code-block:: c + + SEC("lsm/file_mprotect") + int BPF_PROG(mprotect_audit, struct vm_area_struct *vma, + unsigned long reqprot, unsigned long prot, int ret) + { + /* ret is the return value from the previous BPF program + * or 0 if it's the first hook. + */ + if (ret != 0) + return ret; + + int is_heap; + + is_heap = (vma->vm_start >= vma->vm_mm->start_brk && + vma->vm_end <= vma->vm_mm->brk); + + /* Return an -EPERM or write information to the perf events buffer + * for auditing + */ + if (is_heap) + return -EPERM; + } + +The ``__attribute__((preserve_access_index))`` is a clang feature that allows +the BPF verifier to update the offsets for the access at runtime using the +:doc:`/bpf/btf` information. Since the BPF verifier is aware of the types, it +also validates all the accesses made to the various types in the eBPF program. + +Loading +------- + +eBPF programs can be loaded with the :manpage:`bpf(2)` syscall's +``BPF_PROG_LOAD`` operation: + +.. code-block:: c + + struct bpf_object *obj; + + obj = bpf_object__open("./my_prog.o"); + bpf_object__load(obj); + +This can be simplified by using a skeleton header generated by ``bpftool``: + +.. code-block:: console + + # bpftool gen skeleton my_prog.o > my_prog.skel.h + +and the program can be loaded by including ``my_prog.skel.h`` and using +the generated helper, ``my_prog__open_and_load``. + +Attachment to LSM Hooks +----------------------- + +The LSM allows attachment of eBPF programs as LSM hooks using :manpage:`bpf(2)` +syscall's ``BPF_RAW_TRACEPOINT_OPEN`` operation or more simply by +using the libbpf helper ``bpf_program__attach_lsm``. + +The program can be detached from the LSM hook by *destroying* the ``link`` +link returned by ``bpf_program__attach_lsm`` using ``bpf_link__destroy``. + +One can also use the helpers generated in ``my_prog.skel.h`` i.e. +``my_prog__attach`` for attachment and ``my_prog__destroy`` for cleaning up. + +Examples +-------- + +An example eBPF program can be found in +`tools/testing/selftests/bpf/progs/lsm.c`_ and the corresponding +userspace code in `tools/testing/selftests/bpf/prog_tests/test_lsm.c`_ + +.. Links +.. _tools/lib/bpf/bpf_tracing.h: + https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/tree/tools/lib/bpf/bpf_tracing.h +.. _tools/testing/selftests/bpf/progs/lsm.c: + https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/tree/tools/testing/selftests/bpf/progs/lsm.c +.. _tools/testing/selftests/bpf/prog_tests/test_lsm.c: + https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/tree/tools/testing/selftests/bpf/prog_tests/test_lsm.c diff --git a/Documentation/bpf/drgn.rst b/Documentation/bpf/drgn.rst new file mode 100644 index 000000000000..41f223c3161e --- /dev/null +++ b/Documentation/bpf/drgn.rst @@ -0,0 +1,213 @@ +.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +============== +BPF drgn tools +============== + +drgn scripts is a convenient and easy to use mechanism to retrieve arbitrary +kernel data structures. drgn is not relying on kernel UAPI to read the data. +Instead it's reading directly from ``/proc/kcore`` or vmcore and pretty prints +the data based on DWARF debug information from vmlinux. + +This document describes BPF related drgn tools. + +See `drgn/tools`_ for all tools available at the moment and `drgn/doc`_ for +more details on drgn itself. + +bpf_inspect.py +-------------- + +Description +=========== + +`bpf_inspect.py`_ is a tool intended to inspect BPF programs and maps. It can +iterate over all programs and maps in the system and print basic information +about these objects, including id, type and name. + +The main use-case `bpf_inspect.py`_ covers is to show BPF programs of types +``BPF_PROG_TYPE_EXT`` and ``BPF_PROG_TYPE_TRACING`` attached to other BPF +programs via ``freplace``/``fentry``/``fexit`` mechanisms, since there is no +user-space API to get this information. + +Getting started +=============== + +List BPF programs (full names are obtained from BTF):: + + % sudo bpf_inspect.py prog + 27: BPF_PROG_TYPE_TRACEPOINT tracepoint__tcp__tcp_send_reset + 4632: BPF_PROG_TYPE_CGROUP_SOCK_ADDR tw_ipt_bind + 49464: BPF_PROG_TYPE_RAW_TRACEPOINT raw_tracepoint__sched_process_exit + +List BPF maps:: + + % sudo bpf_inspect.py map + 2577: BPF_MAP_TYPE_HASH tw_ipt_vips + 4050: BPF_MAP_TYPE_STACK_TRACE stack_traces + 4069: BPF_MAP_TYPE_PERCPU_ARRAY ned_dctcp_cntr + +Find BPF programs attached to BPF program ``test_pkt_access``:: + + % sudo bpf_inspect.py p | grep test_pkt_access + 650: BPF_PROG_TYPE_SCHED_CLS test_pkt_access + 654: BPF_PROG_TYPE_TRACING test_main linked:[650->25: BPF_TRAMP_FEXIT test_pkt_access->test_pkt_access()] + 655: BPF_PROG_TYPE_TRACING test_subprog1 linked:[650->29: BPF_TRAMP_FEXIT test_pkt_access->test_pkt_access_subprog1()] + 656: BPF_PROG_TYPE_TRACING test_subprog2 linked:[650->31: BPF_TRAMP_FEXIT test_pkt_access->test_pkt_access_subprog2()] + 657: BPF_PROG_TYPE_TRACING test_subprog3 linked:[650->21: BPF_TRAMP_FEXIT test_pkt_access->test_pkt_access_subprog3()] + 658: BPF_PROG_TYPE_EXT new_get_skb_len linked:[650->16: BPF_TRAMP_REPLACE test_pkt_access->get_skb_len()] + 659: BPF_PROG_TYPE_EXT new_get_skb_ifindex linked:[650->23: BPF_TRAMP_REPLACE test_pkt_access->get_skb_ifindex()] + 660: BPF_PROG_TYPE_EXT new_get_constant linked:[650->19: BPF_TRAMP_REPLACE test_pkt_access->get_constant()] + +It can be seen that there is a program ``test_pkt_access``, id 650 and there +are multiple other tracing and ext programs attached to functions in +``test_pkt_access``. + +For example the line:: + + 658: BPF_PROG_TYPE_EXT new_get_skb_len linked:[650->16: BPF_TRAMP_REPLACE test_pkt_access->get_skb_len()] + +, means that BPF program id 658, type ``BPF_PROG_TYPE_EXT``, name +``new_get_skb_len`` replaces (``BPF_TRAMP_REPLACE``) function ``get_skb_len()`` +that has BTF id 16 in BPF program id 650, name ``test_pkt_access``. + +Getting help: + +.. code-block:: none + + % sudo bpf_inspect.py + usage: bpf_inspect.py [-h] {prog,p,map,m} ... + + drgn script to list BPF programs or maps and their properties + unavailable via kernel API. + + See https://github.com/osandov/drgn/ for more details on drgn. + + optional arguments: + -h, --help show this help message and exit + + subcommands: + {prog,p,map,m} + prog (p) list BPF programs + map (m) list BPF maps + +Customization +============= + +The script is intended to be customized by developers to print relevant +information about BPF programs, maps and other objects. + +For example, to print ``struct bpf_prog_aux`` for BPF program id 53077: + +.. code-block:: none + + % git diff + diff --git a/tools/bpf_inspect.py b/tools/bpf_inspect.py + index 650e228..aea2357 100755 + --- a/tools/bpf_inspect.py + +++ b/tools/bpf_inspect.py + @@ -112,7 +112,9 @@ def list_bpf_progs(args): + if linked: + linked = f" linked:[{linked}]" + + - print(f"{id_:>6}: {type_:32} {name:32} {linked}") + + if id_ == 53077: + + print(f"{id_:>6}: {type_:32} {name:32}") + + print(f"{bpf_prog.aux}") + + + def list_bpf_maps(args): + +It produces the output:: + + % sudo bpf_inspect.py p + 53077: BPF_PROG_TYPE_XDP tw_xdp_policer + *(struct bpf_prog_aux *)0xffff8893fad4b400 = { + .refcnt = (atomic64_t){ + .counter = (long)58, + }, + .used_map_cnt = (u32)1, + .max_ctx_offset = (u32)8, + .max_pkt_offset = (u32)15, + .max_tp_access = (u32)0, + .stack_depth = (u32)8, + .id = (u32)53077, + .func_cnt = (u32)0, + .func_idx = (u32)0, + .attach_btf_id = (u32)0, + .linked_prog = (struct bpf_prog *)0x0, + .verifier_zext = (bool)0, + .offload_requested = (bool)0, + .attach_btf_trace = (bool)0, + .func_proto_unreliable = (bool)0, + .trampoline_prog_type = (enum bpf_tramp_prog_type)BPF_TRAMP_FENTRY, + .trampoline = (struct bpf_trampoline *)0x0, + .tramp_hlist = (struct hlist_node){ + .next = (struct hlist_node *)0x0, + .pprev = (struct hlist_node **)0x0, + }, + .attach_func_proto = (const struct btf_type *)0x0, + .attach_func_name = (const char *)0x0, + .func = (struct bpf_prog **)0x0, + .jit_data = (void *)0x0, + .poke_tab = (struct bpf_jit_poke_descriptor *)0x0, + .size_poke_tab = (u32)0, + .ksym_tnode = (struct latch_tree_node){ + .node = (struct rb_node [2]){ + { + .__rb_parent_color = (unsigned long)18446612956263126665, + .rb_right = (struct rb_node *)0x0, + .rb_left = (struct rb_node *)0xffff88a0be3d0088, + }, + { + .__rb_parent_color = (unsigned long)18446612956263126689, + .rb_right = (struct rb_node *)0x0, + .rb_left = (struct rb_node *)0xffff88a0be3d00a0, + }, + }, + }, + .ksym_lnode = (struct list_head){ + .next = (struct list_head *)0xffff88bf481830b8, + .prev = (struct list_head *)0xffff888309f536b8, + }, + .ops = (const struct bpf_prog_ops *)xdp_prog_ops+0x0 = 0xffffffff820fa350, + .used_maps = (struct bpf_map **)0xffff889ff795de98, + .prog = (struct bpf_prog *)0xffffc9000cf2d000, + .user = (struct user_struct *)root_user+0x0 = 0xffffffff82444820, + .load_time = (u64)2408348759285319, + .cgroup_storage = (struct bpf_map *[2]){}, + .name = (char [16])"tw_xdp_policer", + .security = (void *)0xffff889ff795d548, + .offload = (struct bpf_prog_offload *)0x0, + .btf = (struct btf *)0xffff8890ce6d0580, + .func_info = (struct bpf_func_info *)0xffff889ff795d240, + .func_info_aux = (struct bpf_func_info_aux *)0xffff889ff795de20, + .linfo = (struct bpf_line_info *)0xffff888a707afc00, + .jited_linfo = (void **)0xffff8893fad48600, + .func_info_cnt = (u32)1, + .nr_linfo = (u32)37, + .linfo_idx = (u32)0, + .num_exentries = (u32)0, + .extable = (struct exception_table_entry *)0xffffffffa032d950, + .stats = (struct bpf_prog_stats *)0x603fe3a1f6d0, + .work = (struct work_struct){ + .data = (atomic_long_t){ + .counter = (long)0, + }, + .entry = (struct list_head){ + .next = (struct list_head *)0x0, + .prev = (struct list_head *)0x0, + }, + .func = (work_func_t)0x0, + }, + .rcu = (struct callback_head){ + .next = (struct callback_head *)0x0, + .func = (void (*)(struct callback_head *))0x0, + }, + } + + +.. Links +.. _drgn/doc: https://drgn.readthedocs.io/en/latest/ +.. _drgn/tools: https://github.com/osandov/drgn/tree/master/tools +.. _bpf_inspect.py: + https://github.com/osandov/drgn/blob/master/tools/bpf_inspect.py diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst index 4f5410b61441..f99677f3572f 100644 --- a/Documentation/bpf/index.rst +++ b/Documentation/bpf/index.rst @@ -45,14 +45,16 @@ Program types prog_cgroup_sockopt prog_cgroup_sysctl prog_flow_dissector + bpf_lsm -Testing BPF -=========== +Testing and debugging BPF +========================= .. toctree:: :maxdepth: 1 + drgn s390 diff --git a/MAINTAINERS b/MAINTAINERS index 9fa5b2f69212..e3e2db696ae9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3147,6 +3147,8 @@ R: Martin KaFai Lau <kafai@fb.com> R: Song Liu <songliubraving@fb.com> R: Yonghong Song <yhs@fb.com> R: Andrii Nakryiko <andriin@fb.com> +R: John Fastabend <john.fastabend@gmail.com> +R: KP Singh <kpsingh@chromium.org> L: netdev@vger.kernel.org L: bpf@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index a32d478a7f41..b4c89a1acebb 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -303,12 +303,6 @@ SECTIONS *(.branch_lt) } -#ifdef CONFIG_DEBUG_INFO_BTF - .BTF : AT(ADDR(.BTF) - LOAD_OFFSET) { - *(.BTF) - } -#endif - .opd : AT(ADDR(.opd) - LOAD_OFFSET) { __start_opd = .; KEEP(*(.opd)) diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index e00f41aa8ec4..39da8d8b561d 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -535,6 +535,7 @@ \ RO_EXCEPTION_TABLE \ NOTES \ + BTF \ \ . = ALIGN((align)); \ __end_rodata = .; @@ -622,6 +623,20 @@ } /* + * .BTF + */ +#ifdef CONFIG_DEBUG_INFO_BTF +#define BTF \ + .BTF : AT(ADDR(.BTF) - LOAD_OFFSET) { \ + __start_BTF = .; \ + *(.BTF) \ + __stop_BTF = .; \ + } +#else +#define BTF +#endif + +/* * Init task */ #define INIT_TASK_DATA_SECTION(align) \ diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index a7cd5c7a2509..c11b413d5b1a 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -51,9 +51,18 @@ struct bpf_cgroup_storage { struct rcu_head rcu; }; +struct bpf_cgroup_link { + struct bpf_link link; + struct cgroup *cgroup; + enum bpf_attach_type type; +}; + +extern const struct bpf_link_ops bpf_cgroup_link_lops; + struct bpf_prog_list { struct list_head node; struct bpf_prog *prog; + struct bpf_cgroup_link *link; struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]; }; @@ -84,20 +93,27 @@ struct cgroup_bpf { int cgroup_bpf_inherit(struct cgroup *cgrp); void cgroup_bpf_offline(struct cgroup *cgrp); -int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, - struct bpf_prog *replace_prog, +int __cgroup_bpf_attach(struct cgroup *cgrp, + struct bpf_prog *prog, struct bpf_prog *replace_prog, + struct bpf_cgroup_link *link, enum bpf_attach_type type, u32 flags); int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + struct bpf_cgroup_link *link, enum bpf_attach_type type); +int __cgroup_bpf_replace(struct cgroup *cgrp, struct bpf_cgroup_link *link, + struct bpf_prog *new_prog); int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, union bpf_attr __user *uattr); /* Wrapper for __cgroup_bpf_*() protected by cgroup_mutex */ -int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, - struct bpf_prog *replace_prog, enum bpf_attach_type type, +int cgroup_bpf_attach(struct cgroup *cgrp, + struct bpf_prog *prog, struct bpf_prog *replace_prog, + struct bpf_cgroup_link *link, enum bpf_attach_type type, u32 flags); int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type, u32 flags); + enum bpf_attach_type type); +int cgroup_bpf_replace(struct bpf_link *link, struct bpf_prog *old_prog, + struct bpf_prog *new_prog); int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, union bpf_attr __user *uattr); @@ -332,11 +348,13 @@ int cgroup_bpf_prog_attach(const union bpf_attr *attr, enum bpf_prog_type ptype, struct bpf_prog *prog); int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); +int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int cgroup_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); #else struct bpf_prog; +struct bpf_link; struct cgroup_bpf {}; static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } static inline void cgroup_bpf_offline(struct cgroup *cgrp) {} @@ -354,6 +372,19 @@ static inline int cgroup_bpf_prog_detach(const union bpf_attr *attr, return -EINVAL; } +static inline int cgroup_bpf_link_attach(const union bpf_attr *attr, + struct bpf_prog *prog) +{ + return -EINVAL; +} + +static inline int cgroup_bpf_replace(struct bpf_link *link, + struct bpf_prog *old_prog, + struct bpf_prog *new_prog) +{ + return -EINVAL; +} + static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 62e1c4120ff2..fd2b2322412d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -234,6 +234,7 @@ enum bpf_arg_type { ARG_CONST_SIZE_OR_ZERO, /* number of bytes accessed from memory or 0 */ ARG_PTR_TO_CTX, /* pointer to context */ + ARG_PTR_TO_CTX_OR_NULL, /* pointer to context or NULL */ ARG_ANYTHING, /* any (initialized) argument is ok */ ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */ ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */ @@ -1082,15 +1083,23 @@ extern int sysctl_unprivileged_bpf_disabled; int bpf_map_new_fd(struct bpf_map *map, int flags); int bpf_prog_new_fd(struct bpf_prog *prog); -struct bpf_link; +struct bpf_link { + atomic64_t refcnt; + const struct bpf_link_ops *ops; + struct bpf_prog *prog; + struct work_struct work; +}; struct bpf_link_ops { void (*release)(struct bpf_link *link); void (*dealloc)(struct bpf_link *link); + }; void bpf_link_init(struct bpf_link *link, const struct bpf_link_ops *ops, struct bpf_prog *prog); +void bpf_link_cleanup(struct bpf_link *link, struct file *link_file, + int link_fd); void bpf_link_inc(struct bpf_link *link); void bpf_link_put(struct bpf_link *link); int bpf_link_new_fd(struct bpf_link *link); @@ -1501,6 +1510,7 @@ extern const struct bpf_func_proto bpf_get_stack_proto; extern const struct bpf_func_proto bpf_sock_map_update_proto; extern const struct bpf_func_proto bpf_sock_hash_update_proto; extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto; +extern const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto; extern const struct bpf_func_proto bpf_msg_redirect_hash_proto; extern const struct bpf_func_proto bpf_msg_redirect_map_proto; extern const struct bpf_func_proto bpf_sk_redirect_hash_proto; @@ -1514,6 +1524,9 @@ extern const struct bpf_func_proto bpf_tcp_sock_proto; extern const struct bpf_func_proto bpf_jiffies64_proto; extern const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto; +const struct bpf_func_proto *bpf_tracing_func_proto( + enum bpf_func_id func_id, const struct bpf_prog *prog); + /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); diff --git a/include/linux/bpf_lsm.h b/include/linux/bpf_lsm.h new file mode 100644 index 000000000000..af74712af585 --- /dev/null +++ b/include/linux/bpf_lsm.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Copyright (C) 2020 Google LLC. + */ + +#ifndef _LINUX_BPF_LSM_H +#define _LINUX_BPF_LSM_H + +#include <linux/bpf.h> +#include <linux/lsm_hooks.h> + +#ifdef CONFIG_BPF_LSM + +#define LSM_HOOK(RET, DEFAULT, NAME, ...) \ + RET bpf_lsm_##NAME(__VA_ARGS__); +#include <linux/lsm_hook_defs.h> +#undef LSM_HOOK + +int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, + const struct bpf_prog *prog); + +#else /* !CONFIG_BPF_LSM */ + +static inline int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, + const struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} + +#endif /* CONFIG_BPF_LSM */ + +#endif /* _LINUX_BPF_LSM_H */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index c81d4ece79a4..ba0c2d56f8a3 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -70,6 +70,10 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_STRUCT_OPS, bpf_struct_ops, void *, void *) BPF_PROG_TYPE(BPF_PROG_TYPE_EXT, bpf_extension, void *, void *) +#ifdef CONFIG_BPF_LSM +BPF_PROG_TYPE(BPF_PROG_TYPE_LSM, lsm, + void *, void *) +#endif /* CONFIG_BPF_LSM */ #endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 5406e6e96585..6abd5a778fcd 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -123,6 +123,10 @@ struct bpf_reg_state { s64 smax_value; /* maximum possible (s64)value */ u64 umin_value; /* minimum possible (u64)value */ u64 umax_value; /* maximum possible (u64)value */ + s32 s32_min_value; /* minimum possible (s32)value */ + s32 s32_max_value; /* maximum possible (s32)value */ + u32 u32_min_value; /* minimum possible (u32)value */ + u32 u32_max_value; /* maximum possible (u32)value */ /* parentage chain for liveness checking */ struct bpf_reg_state *parent; /* Inside the callee two registers can be both PTR_TO_STACK like diff --git a/include/linux/limits.h b/include/linux/limits.h index 76afcd24ff8c..0d3de82dd354 100644 --- a/include/linux/limits.h +++ b/include/linux/limits.h @@ -27,6 +27,7 @@ #define S16_MAX ((s16)(U16_MAX >> 1)) #define S16_MIN ((s16)(-S16_MAX - 1)) #define U32_MAX ((u32)~0U) +#define U32_MIN ((u32)0) #define S32_MAX ((s32)(U32_MAX >> 1)) #define S32_MIN ((s32)(-S32_MAX - 1)) #define U64_MAX ((u64)~0ULL) diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h new file mode 100644 index 000000000000..9cd4455528e5 --- /dev/null +++ b/include/linux/lsm_hook_defs.h @@ -0,0 +1,381 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Linux Security Module Hook declarations. + * + * Copyright (C) 2001 WireX Communications, Inc <chris@wirex.com> + * Copyright (C) 2001 Greg Kroah-Hartman <greg@kroah.com> + * Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.com> + * Copyright (C) 2001 James Morris <jmorris@intercode.com.au> + * Copyright (C) 2001 Silicon Graphics, Inc. (Trust Technology Group) + * Copyright (C) 2015 Intel Corporation. + * Copyright (C) 2015 Casey Schaufler <casey@schaufler-ca.com> + * Copyright (C) 2016 Mellanox Techonologies + * Copyright (C) 2020 Google LLC. + */ + +/* + * The macro LSM_HOOK is used to define the data structures required by the + * the LSM framework using the pattern: + * + * LSM_HOOK(<return_type>, <default_value>, <hook_name>, args...) + * + * struct security_hook_heads { + * #define LSM_HOOK(RET, DEFAULT, NAME, ...) struct hlist_head NAME; + * #include <linux/lsm_hook_defs.h> + * #undef LSM_HOOK + * }; + */ +LSM_HOOK(int, 0, binder_set_context_mgr, struct task_struct *mgr) +LSM_HOOK(int, 0, binder_transaction, struct task_struct *from, + struct task_struct *to) +LSM_HOOK(int, 0, binder_transfer_binder, struct task_struct *from, + struct task_struct *to) +LSM_HOOK(int, 0, binder_transfer_file, struct task_struct *from, + struct task_struct *to, struct file *file) +LSM_HOOK(int, 0, ptrace_access_check, struct task_struct *child, + unsigned int mode) +LSM_HOOK(int, 0, ptrace_traceme, struct task_struct *parent) +LSM_HOOK(int, 0, capget, struct task_struct *target, kernel_cap_t *effective, + kernel_cap_t *inheritable, kernel_cap_t *permitted) +LSM_HOOK(int, 0, capset, struct cred *new, const struct cred *old, + const kernel_cap_t *effective, const kernel_cap_t *inheritable, + const kernel_cap_t *permitted) +LSM_HOOK(int, 0, capable, const struct cred *cred, struct user_namespace *ns, + int cap, unsigned int opts) +LSM_HOOK(int, 0, quotactl, int cmds, int type, int id, struct super_block *sb) +LSM_HOOK(int, 0, quota_on, struct dentry *dentry) +LSM_HOOK(int, 0, syslog, int type) +LSM_HOOK(int, 0, settime, const struct timespec64 *ts, + const struct timezone *tz) +LSM_HOOK(int, 0, vm_enough_memory, struct mm_struct *mm, long pages) +LSM_HOOK(int, 0, bprm_set_creds, struct linux_binprm *bprm) +LSM_HOOK(int, 0, bprm_check_security, struct linux_binprm *bprm) +LSM_HOOK(void, LSM_RET_VOID, bprm_committing_creds, struct linux_binprm *bprm) +LSM_HOOK(void, LSM_RET_VOID, bprm_committed_creds, struct linux_binprm *bprm) +LSM_HOOK(int, 0, fs_context_dup, struct fs_context *fc, + struct fs_context *src_sc) +LSM_HOOK(int, 0, fs_context_parse_param, struct fs_context *fc, + struct fs_parameter *param) +LSM_HOOK(int, 0, sb_alloc_security, struct super_block *sb) +LSM_HOOK(void, LSM_RET_VOID, sb_free_security, struct super_block *sb) +LSM_HOOK(void, LSM_RET_VOID, sb_free_mnt_opts, void *mnt_opts) +LSM_HOOK(int, 0, sb_eat_lsm_opts, char *orig, void **mnt_opts) +LSM_HOOK(int, 0, sb_remount, struct super_block *sb, void *mnt_opts) +LSM_HOOK(int, 0, sb_kern_mount, struct super_block *sb) +LSM_HOOK(int, 0, sb_show_options, struct seq_file *m, struct super_block *sb) +LSM_HOOK(int, 0, sb_statfs, struct dentry *dentry) +LSM_HOOK(int, 0, sb_mount, const char *dev_name, const struct path *path, + const char *type, unsigned long flags, void *data) +LSM_HOOK(int, 0, sb_umount, struct vfsmount *mnt, int flags) +LSM_HOOK(int, 0, sb_pivotroot, const struct path *old_path, + const struct path *new_path) +LSM_HOOK(int, 0, sb_set_mnt_opts, struct super_block *sb, void *mnt_opts, + unsigned long kern_flags, unsigned long *set_kern_flags) +LSM_HOOK(int, 0, sb_clone_mnt_opts, const struct super_block *oldsb, + struct super_block *newsb, unsigned long kern_flags, + unsigned long *set_kern_flags) +LSM_HOOK(int, 0, sb_add_mnt_opt, const char *option, const char *val, + int len, void **mnt_opts) +LSM_HOOK(int, 0, move_mount, const struct path *from_path, + const struct path *to_path) +LSM_HOOK(int, 0, dentry_init_security, struct dentry *dentry, + int mode, const struct qstr *name, void **ctx, u32 *ctxlen) +LSM_HOOK(int, 0, dentry_create_files_as, struct dentry *dentry, int mode, + struct qstr *name, const struct cred *old, struct cred *new) + +#ifdef CONFIG_SECURITY_PATH +LSM_HOOK(int, 0, path_unlink, const struct path *dir, struct dentry *dentry) +LSM_HOOK(int, 0, path_mkdir, const struct path *dir, struct dentry *dentry, + umode_t mode) +LSM_HOOK(int, 0, path_rmdir, const struct path *dir, struct dentry *dentry) +LSM_HOOK(int, 0, path_mknod, const struct path *dir, struct dentry *dentry, + umode_t mode, unsigned int dev) +LSM_HOOK(int, 0, path_truncate, const struct path *path) +LSM_HOOK(int, 0, path_symlink, const struct path *dir, struct dentry *dentry, + const char *old_name) +LSM_HOOK(int, 0, path_link, struct dentry *old_dentry, + const struct path *new_dir, struct dentry *new_dentry) +LSM_HOOK(int, 0, path_rename, const struct path *old_dir, + struct dentry *old_dentry, const struct path *new_dir, + struct dentry *new_dentry) +LSM_HOOK(int, 0, path_chmod, const struct path *path, umode_t mode) +LSM_HOOK(int, 0, path_chown, const struct path *path, kuid_t uid, kgid_t gid) +LSM_HOOK(int, 0, path_chroot, const struct path *path) +#endif /* CONFIG_SECURITY_PATH */ + +/* Needed for inode based security check */ +LSM_HOOK(int, 0, path_notify, const struct path *path, u64 mask, + unsigned int obj_type) +LSM_HOOK(int, 0, inode_alloc_security, struct inode *inode) +LSM_HOOK(void, LSM_RET_VOID, inode_free_security, struct inode *inode) +LSM_HOOK(int, 0, inode_init_security, struct inode *inode, + struct inode *dir, const struct qstr *qstr, const char **name, + void **value, size_t *len) +LSM_HOOK(int, 0, inode_create, struct inode *dir, struct dentry *dentry, + umode_t mode) +LSM_HOOK(int, 0, inode_link, struct dentry *old_dentry, struct inode *dir, + struct dentry *new_dentry) +LSM_HOOK(int, 0, inode_unlink, struct inode *dir, struct dentry *dentry) +LSM_HOOK(int, 0, inode_symlink, struct inode *dir, struct dentry *dentry, + const char *old_name) +LSM_HOOK(int, 0, inode_mkdir, struct inode *dir, struct dentry *dentry, + umode_t mode) +LSM_HOOK(int, 0, inode_rmdir, struct inode *dir, struct dentry *dentry) +LSM_HOOK(int, 0, inode_mknod, struct inode *dir, struct dentry *dentry, + umode_t mode, dev_t dev) +LSM_HOOK(int, 0, inode_rename, struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry) +LSM_HOOK(int, 0, inode_readlink, struct dentry *dentry) +LSM_HOOK(int, 0, inode_follow_link, struct dentry *dentry, struct inode *inode, + bool rcu) +LSM_HOOK(int, 0, inode_permission, struct inode *inode, int mask) +LSM_HOOK(int, 0, inode_setattr, struct dentry *dentry, struct iattr *attr) +LSM_HOOK(int, 0, inode_getattr, const struct path *path) +LSM_HOOK(int, 0, inode_setxattr, struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) +LSM_HOOK(void, LSM_RET_VOID, inode_post_setxattr, struct dentry *dentry, + const char *name, const void *value, size_t size, int flags) +LSM_HOOK(int, 0, inode_getxattr, struct dentry *dentry, const char *name) +LSM_HOOK(int, 0, inode_listxattr, struct dentry *dentry) +LSM_HOOK(int, 0, inode_removexattr, struct dentry *dentry, const char *name) +LSM_HOOK(int, 0, inode_need_killpriv, struct dentry *dentry) +LSM_HOOK(int, 0, inode_killpriv, struct dentry *dentry) +LSM_HOOK(int, -EOPNOTSUPP, inode_getsecurity, struct inode *inode, + const char *name, void **buffer, bool alloc) +LSM_HOOK(int, -EOPNOTSUPP, inode_setsecurity, struct inode *inode, + const char *name, const void *value, size_t size, int flags) +LSM_HOOK(int, 0, inode_listsecurity, struct inode *inode, char *buffer, + size_t buffer_size) +LSM_HOOK(void, LSM_RET_VOID, inode_getsecid, struct inode *inode, u32 *secid) +LSM_HOOK(int, 0, inode_copy_up, struct dentry *src, struct cred **new) +LSM_HOOK(int, 0, inode_copy_up_xattr, const char *name) +LSM_HOOK(int, 0, kernfs_init_security, struct kernfs_node *kn_dir, + struct kernfs_node *kn) +LSM_HOOK(int, 0, file_permission, struct file *file, int mask) +LSM_HOOK(int, 0, file_alloc_security, struct file *file) +LSM_HOOK(void, LSM_RET_VOID, file_free_security, struct file *file) +LSM_HOOK(int, 0, file_ioctl, struct file *file, unsigned int cmd, + unsigned long arg) +LSM_HOOK(int, 0, mmap_addr, unsigned long addr) +LSM_HOOK(int, 0, mmap_file, struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags) +LSM_HOOK(int, 0, file_mprotect, struct vm_area_struct *vma, + unsigned long reqprot, unsigned long prot) +LSM_HOOK(int, 0, file_lock, struct file *file, unsigned int cmd) +LSM_HOOK(int, 0, file_fcntl, struct file *file, unsigned int cmd, + unsigned long arg) +LSM_HOOK(void, LSM_RET_VOID, file_set_fowner, struct file *file) +LSM_HOOK(int, 0, file_send_sigiotask, struct task_struct *tsk, + struct fown_struct *fown, int sig) +LSM_HOOK(int, 0, file_receive, struct file *file) +LSM_HOOK(int, 0, file_open, struct file *file) +LSM_HOOK(int, 0, task_alloc, struct task_struct *task, + unsigned long clone_flags) +LSM_HOOK(void, LSM_RET_VOID, task_free, struct task_struct *task) +LSM_HOOK(int, 0, cred_alloc_blank, struct cred *cred, gfp_t gfp) +LSM_HOOK(void, LSM_RET_VOID, cred_free, struct cred *cred) +LSM_HOOK(int, 0, cred_prepare, struct cred *new, const struct cred *old, + gfp_t gfp) +LSM_HOOK(void, LSM_RET_VOID, cred_transfer, struct cred *new, + const struct cred *old) +LSM_HOOK(void, LSM_RET_VOID, cred_getsecid, const struct cred *c, u32 *secid) +LSM_HOOK(int, 0, kernel_act_as, struct cred *new, u32 secid) +LSM_HOOK(int, 0, kernel_create_files_as, struct cred *new, struct inode *inode) +LSM_HOOK(int, 0, kernel_module_request, char *kmod_name) +LSM_HOOK(int, 0, kernel_load_data, enum kernel_load_data_id id) +LSM_HOOK(int, 0, kernel_read_file, struct file *file, + enum kernel_read_file_id id) +LSM_HOOK(int, 0, kernel_post_read_file, struct file *file, char *buf, + loff_t size, enum kernel_read_file_id id) +LSM_HOOK(int, 0, task_fix_setuid, struct cred *new, const struct cred *old, + int flags) +LSM_HOOK(int, 0, task_setpgid, struct task_struct *p, pid_t pgid) +LSM_HOOK(int, 0, task_getpgid, struct task_struct *p) +LSM_HOOK(int, 0, task_getsid, struct task_struct *p) +LSM_HOOK(void, LSM_RET_VOID, task_getsecid, struct task_struct *p, u32 *secid) +LSM_HOOK(int, 0, task_setnice, struct task_struct *p, int nice) +LSM_HOOK(int, 0, task_setioprio, struct task_struct *p, int ioprio) +LSM_HOOK(int, 0, task_getioprio, struct task_struct *p) +LSM_HOOK(int, 0, task_prlimit, const struct cred *cred, + const struct cred *tcred, unsigned int flags) +LSM_HOOK(int, 0, task_setrlimit, struct task_struct *p, unsigned int resource, + struct rlimit *new_rlim) +LSM_HOOK(int, 0, task_setscheduler, struct task_struct *p) +LSM_HOOK(int, 0, task_getscheduler, struct task_struct *p) +LSM_HOOK(int, 0, task_movememory, struct task_struct *p) +LSM_HOOK(int, 0, task_kill, struct task_struct *p, struct kernel_siginfo *info, + int sig, const struct cred *cred) +LSM_HOOK(int, -ENOSYS, task_prctl, int option, unsigned long arg2, + unsigned long arg3, unsigned long arg4, unsigned long arg5) +LSM_HOOK(void, LSM_RET_VOID, task_to_inode, struct task_struct *p, + struct inode *inode) +LSM_HOOK(int, 0, ipc_permission, struct kern_ipc_perm *ipcp, short flag) +LSM_HOOK(void, LSM_RET_VOID, ipc_getsecid, struct kern_ipc_perm *ipcp, + u32 *secid) +LSM_HOOK(int, 0, msg_msg_alloc_security, struct msg_msg *msg) +LSM_HOOK(void, LSM_RET_VOID, msg_msg_free_security, struct msg_msg *msg) +LSM_HOOK(int, 0, msg_queue_alloc_security, struct kern_ipc_perm *perm) +LSM_HOOK(void, LSM_RET_VOID, msg_queue_free_security, + struct kern_ipc_perm *perm) +LSM_HOOK(int, 0, msg_queue_associate, struct kern_ipc_perm *perm, int msqflg) +LSM_HOOK(int, 0, msg_queue_msgctl, struct kern_ipc_perm *perm, int cmd) +LSM_HOOK(int, 0, msg_queue_msgsnd, struct kern_ipc_perm *perm, + struct msg_msg *msg, int msqflg) +LSM_HOOK(int, 0, msg_queue_msgrcv, struct kern_ipc_perm *perm, + struct msg_msg *msg, struct task_struct *target, long type, int mode) +LSM_HOOK(int, 0, shm_alloc_security, struct kern_ipc_perm *perm) +LSM_HOOK(void, LSM_RET_VOID, shm_free_security, struct kern_ipc_perm *perm) +LSM_HOOK(int, 0, shm_associate, struct kern_ipc_perm *perm, int shmflg) +LSM_HOOK(int, 0, shm_shmctl, struct kern_ipc_perm *perm, int cmd) +LSM_HOOK(int, 0, shm_shmat, struct kern_ipc_perm *perm, char __user *shmaddr, + int shmflg) +LSM_HOOK(int, 0, sem_alloc_security, struct kern_ipc_perm *perm) +LSM_HOOK(void, LSM_RET_VOID, sem_free_security, struct kern_ipc_perm *perm) +LSM_HOOK(int, 0, sem_associate, struct kern_ipc_perm *perm, int semflg) +LSM_HOOK(int, 0, sem_semctl, struct kern_ipc_perm *perm, int cmd) +LSM_HOOK(int, 0, sem_semop, struct kern_ipc_perm *perm, struct sembuf *sops, + unsigned nsops, int alter) +LSM_HOOK(int, 0, netlink_send, struct sock *sk, struct sk_buff *skb) +LSM_HOOK(void, LSM_RET_VOID, d_instantiate, struct dentry *dentry, + struct inode *inode) +LSM_HOOK(int, -EINVAL, getprocattr, struct task_struct *p, char *name, + char **value) +LSM_HOOK(int, -EINVAL, setprocattr, const char *name, void *value, size_t size) +LSM_HOOK(int, 0, ismaclabel, const char *name) +LSM_HOOK(int, 0, secid_to_secctx, u32 secid, char **secdata, + u32 *seclen) +LSM_HOOK(int, 0, secctx_to_secid, const char *secdata, u32 seclen, u32 *secid) +LSM_HOOK(void, LSM_RET_VOID, release_secctx, char *secdata, u32 seclen) +LSM_HOOK(void, LSM_RET_VOID, inode_invalidate_secctx, struct inode *inode) +LSM_HOOK(int, 0, inode_notifysecctx, struct inode *inode, void *ctx, u32 ctxlen) +LSM_HOOK(int, 0, inode_setsecctx, struct dentry *dentry, void *ctx, u32 ctxlen) +LSM_HOOK(int, 0, inode_getsecctx, struct inode *inode, void **ctx, + u32 *ctxlen) + +#ifdef CONFIG_SECURITY_NETWORK +LSM_HOOK(int, 0, unix_stream_connect, struct sock *sock, struct sock *other, + struct sock *newsk) +LSM_HOOK(int, 0, unix_may_send, struct socket *sock, struct socket *other) +LSM_HOOK(int, 0, socket_create, int family, int type, int protocol, int kern) +LSM_HOOK(int, 0, socket_post_create, struct socket *sock, int family, int type, + int protocol, int kern) +LSM_HOOK(int, 0, socket_socketpair, struct socket *socka, struct socket *sockb) +LSM_HOOK(int, 0, socket_bind, struct socket *sock, struct sockaddr *address, + int addrlen) +LSM_HOOK(int, 0, socket_connect, struct socket *sock, struct sockaddr *address, + int addrlen) +LSM_HOOK(int, 0, socket_listen, struct socket *sock, int backlog) +LSM_HOOK(int, 0, socket_accept, struct socket *sock, struct socket *newsock) +LSM_HOOK(int, 0, socket_sendmsg, struct socket *sock, struct msghdr *msg, + int size) +LSM_HOOK(int, 0, socket_recvmsg, struct socket *sock, struct msghdr *msg, + int size, int flags) +LSM_HOOK(int, 0, socket_getsockname, struct socket *sock) +LSM_HOOK(int, 0, socket_getpeername, struct socket *sock) +LSM_HOOK(int, 0, socket_getsockopt, struct socket *sock, int level, int optname) +LSM_HOOK(int, 0, socket_setsockopt, struct socket *sock, int level, int optname) +LSM_HOOK(int, 0, socket_shutdown, struct socket *sock, int how) +LSM_HOOK(int, 0, socket_sock_rcv_skb, struct sock *sk, struct sk_buff *skb) +LSM_HOOK(int, 0, socket_getpeersec_stream, struct socket *sock, + char __user *optval, int __user *optlen, unsigned len) +LSM_HOOK(int, 0, socket_getpeersec_dgram, struct socket *sock, + struct sk_buff *skb, u32 *secid) +LSM_HOOK(int, 0, sk_alloc_security, struct sock *sk, int family, gfp_t priority) +LSM_HOOK(void, LSM_RET_VOID, sk_free_security, struct sock *sk) +LSM_HOOK(void, LSM_RET_VOID, sk_clone_security, const struct sock *sk, + struct sock *newsk) +LSM_HOOK(void, LSM_RET_VOID, sk_getsecid, struct sock *sk, u32 *secid) +LSM_HOOK(void, LSM_RET_VOID, sock_graft, struct sock *sk, struct socket *parent) +LSM_HOOK(int, 0, inet_conn_request, struct sock *sk, struct sk_buff *skb, + struct request_sock *req) +LSM_HOOK(void, LSM_RET_VOID, inet_csk_clone, struct sock *newsk, + const struct request_sock *req) +LSM_HOOK(void, LSM_RET_VOID, inet_conn_established, struct sock *sk, + struct sk_buff *skb) +LSM_HOOK(int, 0, secmark_relabel_packet, u32 secid) +LSM_HOOK(void, LSM_RET_VOID, secmark_refcount_inc, void) +LSM_HOOK(void, LSM_RET_VOID, secmark_refcount_dec, void) +LSM_HOOK(void, LSM_RET_VOID, req_classify_flow, const struct request_sock *req, + struct flowi *fl) +LSM_HOOK(int, 0, tun_dev_alloc_security, void **security) +LSM_HOOK(void, LSM_RET_VOID, tun_dev_free_security, void *security) +LSM_HOOK(int, 0, tun_dev_create, void) +LSM_HOOK(int, 0, tun_dev_attach_queue, void *security) +LSM_HOOK(int, 0, tun_dev_attach, struct sock *sk, void *security) +LSM_HOOK(int, 0, tun_dev_open, void *security) +LSM_HOOK(int, 0, sctp_assoc_request, struct sctp_endpoint *ep, + struct sk_buff *skb) +LSM_HOOK(int, 0, sctp_bind_connect, struct sock *sk, int optname, + struct sockaddr *address, int addrlen) +LSM_HOOK(void, LSM_RET_VOID, sctp_sk_clone, struct sctp_endpoint *ep, + struct sock *sk, struct sock *newsk) +#endif /* CONFIG_SECURITY_NETWORK */ + +#ifdef CONFIG_SECURITY_INFINIBAND +LSM_HOOK(int, 0, ib_pkey_access, void *sec, u64 subnet_prefix, u16 pkey) +LSM_HOOK(int, 0, ib_endport_manage_subnet, void *sec, const char *dev_name, + u8 port_num) +LSM_HOOK(int, 0, ib_alloc_security, void **sec) +LSM_HOOK(void, LSM_RET_VOID, ib_free_security, void *sec) +#endif /* CONFIG_SECURITY_INFINIBAND */ + +#ifdef CONFIG_SECURITY_NETWORK_XFRM +LSM_HOOK(int, 0, xfrm_policy_alloc_security, struct xfrm_sec_ctx **ctxp, + struct xfrm_user_sec_ctx *sec_ctx, gfp_t gfp) +LSM_HOOK(int, 0, xfrm_policy_clone_security, struct xfrm_sec_ctx *old_ctx, + struct xfrm_sec_ctx **new_ctx) +LSM_HOOK(void, LSM_RET_VOID, xfrm_policy_free_security, + struct xfrm_sec_ctx *ctx) +LSM_HOOK(int, 0, xfrm_policy_delete_security, struct xfrm_sec_ctx *ctx) +LSM_HOOK(int, 0, xfrm_state_alloc, struct xfrm_state *x, + struct xfrm_user_sec_ctx *sec_ctx) +LSM_HOOK(int, 0, xfrm_state_alloc_acquire, struct xfrm_state *x, + struct xfrm_sec_ctx *polsec, u32 secid) +LSM_HOOK(void, LSM_RET_VOID, xfrm_state_free_security, struct xfrm_state *x) +LSM_HOOK(int, 0, xfrm_state_delete_security, struct xfrm_state *x) +LSM_HOOK(int, 0, xfrm_policy_lookup, struct xfrm_sec_ctx *ctx, u32 fl_secid, + u8 dir) +LSM_HOOK(int, 1, xfrm_state_pol_flow_match, struct xfrm_state *x, + struct xfrm_policy *xp, const struct flowi *fl) +LSM_HOOK(int, 0, xfrm_decode_session, struct sk_buff *skb, u32 *secid, + int ckall) +#endif /* CONFIG_SECURITY_NETWORK_XFRM */ + +/* key management security hooks */ +#ifdef CONFIG_KEYS +LSM_HOOK(int, 0, key_alloc, struct key *key, const struct cred *cred, + unsigned long flags) +LSM_HOOK(void, LSM_RET_VOID, key_free, struct key *key) +LSM_HOOK(int, 0, key_permission, key_ref_t key_ref, const struct cred *cred, + unsigned perm) +LSM_HOOK(int, 0, key_getsecurity, struct key *key, char **_buffer) +#endif /* CONFIG_KEYS */ + +#ifdef CONFIG_AUDIT +LSM_HOOK(int, 0, audit_rule_init, u32 field, u32 op, char *rulestr, + void **lsmrule) +LSM_HOOK(int, 0, audit_rule_known, struct audit_krule *krule) +LSM_HOOK(int, 0, audit_rule_match, u32 secid, u32 field, u32 op, void *lsmrule) +LSM_HOOK(void, LSM_RET_VOID, audit_rule_free, void *lsmrule) +#endif /* CONFIG_AUDIT */ + +#ifdef CONFIG_BPF_SYSCALL +LSM_HOOK(int, 0, bpf, int cmd, union bpf_attr *attr, unsigned int size) +LSM_HOOK(int, 0, bpf_map, struct bpf_map *map, fmode_t fmode) +LSM_HOOK(int, 0, bpf_prog, struct bpf_prog *prog) +LSM_HOOK(int, 0, bpf_map_alloc_security, struct bpf_map *map) +LSM_HOOK(void, LSM_RET_VOID, bpf_map_free_security, struct bpf_map *map) +LSM_HOOK(int, 0, bpf_prog_alloc_security, struct bpf_prog_aux *aux) +LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free_security, struct bpf_prog_aux *aux) +#endif /* CONFIG_BPF_SYSCALL */ + +LSM_HOOK(int, 0, locked_down, enum lockdown_reason what) + +#ifdef CONFIG_PERF_EVENTS +LSM_HOOK(int, 0, perf_event_open, struct perf_event_attr *attr, int type) +LSM_HOOK(int, 0, perf_event_alloc, struct perf_event *event) +LSM_HOOK(void, LSM_RET_VOID, perf_event_free, struct perf_event *event) +LSM_HOOK(int, 0, perf_event_read, struct perf_event *event) +LSM_HOOK(int, 0, perf_event_write, struct perf_event *event) +#endif /* CONFIG_PERF_EVENTS */ diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 20d8cf194fb7..c09623b32489 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1456,625 +1456,15 @@ * @what: kernel feature being accessed */ union security_list_options { - int (*binder_set_context_mgr)(struct task_struct *mgr); - int (*binder_transaction)(struct task_struct *from, - struct task_struct *to); - int (*binder_transfer_binder)(struct task_struct *from, - struct task_struct *to); - int (*binder_transfer_file)(struct task_struct *from, - struct task_struct *to, - struct file *file); - - int (*ptrace_access_check)(struct task_struct *child, - unsigned int mode); - int (*ptrace_traceme)(struct task_struct *parent); - int (*capget)(struct task_struct *target, kernel_cap_t *effective, - kernel_cap_t *inheritable, kernel_cap_t *permitted); - int (*capset)(struct cred *new, const struct cred *old, - const kernel_cap_t *effective, - const kernel_cap_t *inheritable, - const kernel_cap_t *permitted); - int (*capable)(const struct cred *cred, - struct user_namespace *ns, - int cap, - unsigned int opts); - int (*quotactl)(int cmds, int type, int id, struct super_block *sb); - int (*quota_on)(struct dentry *dentry); - int (*syslog)(int type); - int (*settime)(const struct timespec64 *ts, const struct timezone *tz); - int (*vm_enough_memory)(struct mm_struct *mm, long pages); - - int (*bprm_set_creds)(struct linux_binprm *bprm); - int (*bprm_check_security)(struct linux_binprm *bprm); - void (*bprm_committing_creds)(struct linux_binprm *bprm); - void (*bprm_committed_creds)(struct linux_binprm *bprm); - - int (*fs_context_dup)(struct fs_context *fc, struct fs_context *src_sc); - int (*fs_context_parse_param)(struct fs_context *fc, struct fs_parameter *param); - - int (*sb_alloc_security)(struct super_block *sb); - void (*sb_free_security)(struct super_block *sb); - void (*sb_free_mnt_opts)(void *mnt_opts); - int (*sb_eat_lsm_opts)(char *orig, void **mnt_opts); - int (*sb_remount)(struct super_block *sb, void *mnt_opts); - int (*sb_kern_mount)(struct super_block *sb); - int (*sb_show_options)(struct seq_file *m, struct super_block *sb); - int (*sb_statfs)(struct dentry *dentry); - int (*sb_mount)(const char *dev_name, const struct path *path, - const char *type, unsigned long flags, void *data); - int (*sb_umount)(struct vfsmount *mnt, int flags); - int (*sb_pivotroot)(const struct path *old_path, const struct path *new_path); - int (*sb_set_mnt_opts)(struct super_block *sb, - void *mnt_opts, - unsigned long kern_flags, - unsigned long *set_kern_flags); - int (*sb_clone_mnt_opts)(const struct super_block *oldsb, - struct super_block *newsb, - unsigned long kern_flags, - unsigned long *set_kern_flags); - int (*sb_add_mnt_opt)(const char *option, const char *val, int len, - void **mnt_opts); - int (*move_mount)(const struct path *from_path, const struct path *to_path); - int (*dentry_init_security)(struct dentry *dentry, int mode, - const struct qstr *name, void **ctx, - u32 *ctxlen); - int (*dentry_create_files_as)(struct dentry *dentry, int mode, - struct qstr *name, - const struct cred *old, - struct cred *new); - - -#ifdef CONFIG_SECURITY_PATH - int (*path_unlink)(const struct path *dir, struct dentry *dentry); - int (*path_mkdir)(const struct path *dir, struct dentry *dentry, - umode_t mode); - int (*path_rmdir)(const struct path *dir, struct dentry *dentry); - int (*path_mknod)(const struct path *dir, struct dentry *dentry, - umode_t mode, unsigned int dev); - int (*path_truncate)(const struct path *path); - int (*path_symlink)(const struct path *dir, struct dentry *dentry, - const char *old_name); - int (*path_link)(struct dentry *old_dentry, const struct path *new_dir, - struct dentry *new_dentry); - int (*path_rename)(const struct path *old_dir, struct dentry *old_dentry, - const struct path *new_dir, - struct dentry *new_dentry); - int (*path_chmod)(const struct path *path, umode_t mode); - int (*path_chown)(const struct path *path, kuid_t uid, kgid_t gid); - int (*path_chroot)(const struct path *path); -#endif - /* Needed for inode based security check */ - int (*path_notify)(const struct path *path, u64 mask, - unsigned int obj_type); - int (*inode_alloc_security)(struct inode *inode); - void (*inode_free_security)(struct inode *inode); - int (*inode_init_security)(struct inode *inode, struct inode *dir, - const struct qstr *qstr, - const char **name, void **value, - size_t *len); - int (*inode_create)(struct inode *dir, struct dentry *dentry, - umode_t mode); - int (*inode_link)(struct dentry *old_dentry, struct inode *dir, - struct dentry *new_dentry); - int (*inode_unlink)(struct inode *dir, struct dentry *dentry); - int (*inode_symlink)(struct inode *dir, struct dentry *dentry, - const char *old_name); - int (*inode_mkdir)(struct inode *dir, struct dentry *dentry, - umode_t mode); - int (*inode_rmdir)(struct inode *dir, struct dentry *dentry); - int (*inode_mknod)(struct inode *dir, struct dentry *dentry, - umode_t mode, dev_t dev); - int (*inode_rename)(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, - struct dentry *new_dentry); - int (*inode_readlink)(struct dentry *dentry); - int (*inode_follow_link)(struct dentry *dentry, struct inode *inode, - bool rcu); - int (*inode_permission)(struct inode *inode, int mask); - int (*inode_setattr)(struct dentry *dentry, struct iattr *attr); - int (*inode_getattr)(const struct path *path); - int (*inode_setxattr)(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags); - void (*inode_post_setxattr)(struct dentry *dentry, const char *name, - const void *value, size_t size, - int flags); - int (*inode_getxattr)(struct dentry *dentry, const char *name); - int (*inode_listxattr)(struct dentry *dentry); - int (*inode_removexattr)(struct dentry *dentry, const char *name); - int (*inode_need_killpriv)(struct dentry *dentry); - int (*inode_killpriv)(struct dentry *dentry); - int (*inode_getsecurity)(struct inode *inode, const char *name, - void **buffer, bool alloc); - int (*inode_setsecurity)(struct inode *inode, const char *name, - const void *value, size_t size, - int flags); - int (*inode_listsecurity)(struct inode *inode, char *buffer, - size_t buffer_size); - void (*inode_getsecid)(struct inode *inode, u32 *secid); - int (*inode_copy_up)(struct dentry *src, struct cred **new); - int (*inode_copy_up_xattr)(const char *name); - - int (*kernfs_init_security)(struct kernfs_node *kn_dir, - struct kernfs_node *kn); - - int (*file_permission)(struct file *file, int mask); - int (*file_alloc_security)(struct file *file); - void (*file_free_security)(struct file *file); - int (*file_ioctl)(struct file *file, unsigned int cmd, - unsigned long arg); - int (*mmap_addr)(unsigned long addr); - int (*mmap_file)(struct file *file, unsigned long reqprot, - unsigned long prot, unsigned long flags); - int (*file_mprotect)(struct vm_area_struct *vma, unsigned long reqprot, - unsigned long prot); - int (*file_lock)(struct file *file, unsigned int cmd); - int (*file_fcntl)(struct file *file, unsigned int cmd, - unsigned long arg); - void (*file_set_fowner)(struct file *file); - int (*file_send_sigiotask)(struct task_struct *tsk, - struct fown_struct *fown, int sig); - int (*file_receive)(struct file *file); - int (*file_open)(struct file *file); - - int (*task_alloc)(struct task_struct *task, unsigned long clone_flags); - void (*task_free)(struct task_struct *task); - int (*cred_alloc_blank)(struct cred *cred, gfp_t gfp); - void (*cred_free)(struct cred *cred); - int (*cred_prepare)(struct cred *new, const struct cred *old, - gfp_t gfp); - void (*cred_transfer)(struct cred *new, const struct cred *old); - void (*cred_getsecid)(const struct cred *c, u32 *secid); - int (*kernel_act_as)(struct cred *new, u32 secid); - int (*kernel_create_files_as)(struct cred *new, struct inode *inode); - int (*kernel_module_request)(char *kmod_name); - int (*kernel_load_data)(enum kernel_load_data_id id); - int (*kernel_read_file)(struct file *file, enum kernel_read_file_id id); - int (*kernel_post_read_file)(struct file *file, char *buf, loff_t size, - enum kernel_read_file_id id); - int (*task_fix_setuid)(struct cred *new, const struct cred *old, - int flags); - int (*task_setpgid)(struct task_struct *p, pid_t pgid); - int (*task_getpgid)(struct task_struct *p); - int (*task_getsid)(struct task_struct *p); - void (*task_getsecid)(struct task_struct *p, u32 *secid); - int (*task_setnice)(struct task_struct *p, int nice); - int (*task_setioprio)(struct task_struct *p, int ioprio); - int (*task_getioprio)(struct task_struct *p); - int (*task_prlimit)(const struct cred *cred, const struct cred *tcred, - unsigned int flags); - int (*task_setrlimit)(struct task_struct *p, unsigned int resource, - struct rlimit *new_rlim); - int (*task_setscheduler)(struct task_struct *p); - int (*task_getscheduler)(struct task_struct *p); - int (*task_movememory)(struct task_struct *p); - int (*task_kill)(struct task_struct *p, struct kernel_siginfo *info, - int sig, const struct cred *cred); - int (*task_prctl)(int option, unsigned long arg2, unsigned long arg3, - unsigned long arg4, unsigned long arg5); - void (*task_to_inode)(struct task_struct *p, struct inode *inode); - - int (*ipc_permission)(struct kern_ipc_perm *ipcp, short flag); - void (*ipc_getsecid)(struct kern_ipc_perm *ipcp, u32 *secid); - - int (*msg_msg_alloc_security)(struct msg_msg *msg); - void (*msg_msg_free_security)(struct msg_msg *msg); - - int (*msg_queue_alloc_security)(struct kern_ipc_perm *perm); - void (*msg_queue_free_security)(struct kern_ipc_perm *perm); - int (*msg_queue_associate)(struct kern_ipc_perm *perm, int msqflg); - int (*msg_queue_msgctl)(struct kern_ipc_perm *perm, int cmd); - int (*msg_queue_msgsnd)(struct kern_ipc_perm *perm, struct msg_msg *msg, - int msqflg); - int (*msg_queue_msgrcv)(struct kern_ipc_perm *perm, struct msg_msg *msg, - struct task_struct *target, long type, - int mode); - - int (*shm_alloc_security)(struct kern_ipc_perm *perm); - void (*shm_free_security)(struct kern_ipc_perm *perm); - int (*shm_associate)(struct kern_ipc_perm *perm, int shmflg); - int (*shm_shmctl)(struct kern_ipc_perm *perm, int cmd); - int (*shm_shmat)(struct kern_ipc_perm *perm, char __user *shmaddr, - int shmflg); - - int (*sem_alloc_security)(struct kern_ipc_perm *perm); - void (*sem_free_security)(struct kern_ipc_perm *perm); - int (*sem_associate)(struct kern_ipc_perm *perm, int semflg); - int (*sem_semctl)(struct kern_ipc_perm *perm, int cmd); - int (*sem_semop)(struct kern_ipc_perm *perm, struct sembuf *sops, - unsigned nsops, int alter); - - int (*netlink_send)(struct sock *sk, struct sk_buff *skb); - - void (*d_instantiate)(struct dentry *dentry, struct inode *inode); - - int (*getprocattr)(struct task_struct *p, char *name, char **value); - int (*setprocattr)(const char *name, void *value, size_t size); - int (*ismaclabel)(const char *name); - int (*secid_to_secctx)(u32 secid, char **secdata, u32 *seclen); - int (*secctx_to_secid)(const char *secdata, u32 seclen, u32 *secid); - void (*release_secctx)(char *secdata, u32 seclen); - - void (*inode_invalidate_secctx)(struct inode *inode); - int (*inode_notifysecctx)(struct inode *inode, void *ctx, u32 ctxlen); - int (*inode_setsecctx)(struct dentry *dentry, void *ctx, u32 ctxlen); - int (*inode_getsecctx)(struct inode *inode, void **ctx, u32 *ctxlen); - -#ifdef CONFIG_SECURITY_NETWORK - int (*unix_stream_connect)(struct sock *sock, struct sock *other, - struct sock *newsk); - int (*unix_may_send)(struct socket *sock, struct socket *other); - - int (*socket_create)(int family, int type, int protocol, int kern); - int (*socket_post_create)(struct socket *sock, int family, int type, - int protocol, int kern); - int (*socket_socketpair)(struct socket *socka, struct socket *sockb); - int (*socket_bind)(struct socket *sock, struct sockaddr *address, - int addrlen); - int (*socket_connect)(struct socket *sock, struct sockaddr *address, - int addrlen); - int (*socket_listen)(struct socket *sock, int backlog); - int (*socket_accept)(struct socket *sock, struct socket *newsock); - int (*socket_sendmsg)(struct socket *sock, struct msghdr *msg, - int size); - int (*socket_recvmsg)(struct socket *sock, struct msghdr *msg, - int size, int flags); - int (*socket_getsockname)(struct socket *sock); - int (*socket_getpeername)(struct socket *sock); - int (*socket_getsockopt)(struct socket *sock, int level, int optname); - int (*socket_setsockopt)(struct socket *sock, int level, int optname); - int (*socket_shutdown)(struct socket *sock, int how); - int (*socket_sock_rcv_skb)(struct sock *sk, struct sk_buff *skb); - int (*socket_getpeersec_stream)(struct socket *sock, - char __user *optval, - int __user *optlen, unsigned len); - int (*socket_getpeersec_dgram)(struct socket *sock, - struct sk_buff *skb, u32 *secid); - int (*sk_alloc_security)(struct sock *sk, int family, gfp_t priority); - void (*sk_free_security)(struct sock *sk); - void (*sk_clone_security)(const struct sock *sk, struct sock *newsk); - void (*sk_getsecid)(struct sock *sk, u32 *secid); - void (*sock_graft)(struct sock *sk, struct socket *parent); - int (*inet_conn_request)(struct sock *sk, struct sk_buff *skb, - struct request_sock *req); - void (*inet_csk_clone)(struct sock *newsk, - const struct request_sock *req); - void (*inet_conn_established)(struct sock *sk, struct sk_buff *skb); - int (*secmark_relabel_packet)(u32 secid); - void (*secmark_refcount_inc)(void); - void (*secmark_refcount_dec)(void); - void (*req_classify_flow)(const struct request_sock *req, - struct flowi *fl); - int (*tun_dev_alloc_security)(void **security); - void (*tun_dev_free_security)(void *security); - int (*tun_dev_create)(void); - int (*tun_dev_attach_queue)(void *security); - int (*tun_dev_attach)(struct sock *sk, void *security); - int (*tun_dev_open)(void *security); - int (*sctp_assoc_request)(struct sctp_endpoint *ep, - struct sk_buff *skb); - int (*sctp_bind_connect)(struct sock *sk, int optname, - struct sockaddr *address, int addrlen); - void (*sctp_sk_clone)(struct sctp_endpoint *ep, struct sock *sk, - struct sock *newsk); -#endif /* CONFIG_SECURITY_NETWORK */ - -#ifdef CONFIG_SECURITY_INFINIBAND - int (*ib_pkey_access)(void *sec, u64 subnet_prefix, u16 pkey); - int (*ib_endport_manage_subnet)(void *sec, const char *dev_name, - u8 port_num); - int (*ib_alloc_security)(void **sec); - void (*ib_free_security)(void *sec); -#endif /* CONFIG_SECURITY_INFINIBAND */ - -#ifdef CONFIG_SECURITY_NETWORK_XFRM - int (*xfrm_policy_alloc_security)(struct xfrm_sec_ctx **ctxp, - struct xfrm_user_sec_ctx *sec_ctx, - gfp_t gfp); - int (*xfrm_policy_clone_security)(struct xfrm_sec_ctx *old_ctx, - struct xfrm_sec_ctx **new_ctx); - void (*xfrm_policy_free_security)(struct xfrm_sec_ctx *ctx); - int (*xfrm_policy_delete_security)(struct xfrm_sec_ctx *ctx); - int (*xfrm_state_alloc)(struct xfrm_state *x, - struct xfrm_user_sec_ctx *sec_ctx); - int (*xfrm_state_alloc_acquire)(struct xfrm_state *x, - struct xfrm_sec_ctx *polsec, - u32 secid); - void (*xfrm_state_free_security)(struct xfrm_state *x); - int (*xfrm_state_delete_security)(struct xfrm_state *x); - int (*xfrm_policy_lookup)(struct xfrm_sec_ctx *ctx, u32 fl_secid, - u8 dir); - int (*xfrm_state_pol_flow_match)(struct xfrm_state *x, - struct xfrm_policy *xp, - const struct flowi *fl); - int (*xfrm_decode_session)(struct sk_buff *skb, u32 *secid, int ckall); -#endif /* CONFIG_SECURITY_NETWORK_XFRM */ - - /* key management security hooks */ -#ifdef CONFIG_KEYS - int (*key_alloc)(struct key *key, const struct cred *cred, - unsigned long flags); - void (*key_free)(struct key *key); - int (*key_permission)(key_ref_t key_ref, const struct cred *cred, - unsigned perm); - int (*key_getsecurity)(struct key *key, char **_buffer); -#endif /* CONFIG_KEYS */ - -#ifdef CONFIG_AUDIT - int (*audit_rule_init)(u32 field, u32 op, char *rulestr, - void **lsmrule); - int (*audit_rule_known)(struct audit_krule *krule); - int (*audit_rule_match)(u32 secid, u32 field, u32 op, void *lsmrule); - void (*audit_rule_free)(void *lsmrule); -#endif /* CONFIG_AUDIT */ - -#ifdef CONFIG_BPF_SYSCALL - int (*bpf)(int cmd, union bpf_attr *attr, - unsigned int size); - int (*bpf_map)(struct bpf_map *map, fmode_t fmode); - int (*bpf_prog)(struct bpf_prog *prog); - int (*bpf_map_alloc_security)(struct bpf_map *map); - void (*bpf_map_free_security)(struct bpf_map *map); - int (*bpf_prog_alloc_security)(struct bpf_prog_aux *aux); - void (*bpf_prog_free_security)(struct bpf_prog_aux *aux); -#endif /* CONFIG_BPF_SYSCALL */ - int (*locked_down)(enum lockdown_reason what); -#ifdef CONFIG_PERF_EVENTS - int (*perf_event_open)(struct perf_event_attr *attr, int type); - int (*perf_event_alloc)(struct perf_event *event); - void (*perf_event_free)(struct perf_event *event); - int (*perf_event_read)(struct perf_event *event); - int (*perf_event_write)(struct perf_event *event); - -#endif + #define LSM_HOOK(RET, DEFAULT, NAME, ...) RET (*NAME)(__VA_ARGS__); + #include "lsm_hook_defs.h" + #undef LSM_HOOK }; struct security_hook_heads { - struct hlist_head binder_set_context_mgr; - struct hlist_head binder_transaction; - struct hlist_head binder_transfer_binder; - struct hlist_head binder_transfer_file; - struct hlist_head ptrace_access_check; - struct hlist_head ptrace_traceme; - struct hlist_head capget; - struct hlist_head capset; - struct hlist_head capable; - struct hlist_head quotactl; - struct hlist_head quota_on; - struct hlist_head syslog; - struct hlist_head settime; - struct hlist_head vm_enough_memory; - struct hlist_head bprm_set_creds; - struct hlist_head bprm_check_security; - struct hlist_head bprm_committing_creds; - struct hlist_head bprm_committed_creds; - struct hlist_head fs_context_dup; - struct hlist_head fs_context_parse_param; - struct hlist_head sb_alloc_security; - struct hlist_head sb_free_security; - struct hlist_head sb_free_mnt_opts; - struct hlist_head sb_eat_lsm_opts; - struct hlist_head sb_remount; - struct hlist_head sb_kern_mount; - struct hlist_head sb_show_options; - struct hlist_head sb_statfs; - struct hlist_head sb_mount; - struct hlist_head sb_umount; - struct hlist_head sb_pivotroot; - struct hlist_head sb_set_mnt_opts; - struct hlist_head sb_clone_mnt_opts; - struct hlist_head sb_add_mnt_opt; - struct hlist_head move_mount; - struct hlist_head dentry_init_security; - struct hlist_head dentry_create_files_as; -#ifdef CONFIG_SECURITY_PATH - struct hlist_head path_unlink; - struct hlist_head path_mkdir; - struct hlist_head path_rmdir; - struct hlist_head path_mknod; - struct hlist_head path_truncate; - struct hlist_head path_symlink; - struct hlist_head path_link; - struct hlist_head path_rename; - struct hlist_head path_chmod; - struct hlist_head path_chown; - struct hlist_head path_chroot; -#endif - /* Needed for inode based modules as well */ - struct hlist_head path_notify; - struct hlist_head inode_alloc_security; - struct hlist_head inode_free_security; - struct hlist_head inode_init_security; - struct hlist_head inode_create; - struct hlist_head inode_link; - struct hlist_head inode_unlink; - struct hlist_head inode_symlink; - struct hlist_head inode_mkdir; - struct hlist_head inode_rmdir; - struct hlist_head inode_mknod; - struct hlist_head inode_rename; - struct hlist_head inode_readlink; - struct hlist_head inode_follow_link; - struct hlist_head inode_permission; - struct hlist_head inode_setattr; - struct hlist_head inode_getattr; - struct hlist_head inode_setxattr; - struct hlist_head inode_post_setxattr; - struct hlist_head inode_getxattr; - struct hlist_head inode_listxattr; - struct hlist_head inode_removexattr; - struct hlist_head inode_need_killpriv; - struct hlist_head inode_killpriv; - struct hlist_head inode_getsecurity; - struct hlist_head inode_setsecurity; - struct hlist_head inode_listsecurity; - struct hlist_head inode_getsecid; - struct hlist_head inode_copy_up; - struct hlist_head inode_copy_up_xattr; - struct hlist_head kernfs_init_security; - struct hlist_head file_permission; - struct hlist_head file_alloc_security; - struct hlist_head file_free_security; - struct hlist_head file_ioctl; - struct hlist_head mmap_addr; - struct hlist_head mmap_file; - struct hlist_head file_mprotect; - struct hlist_head file_lock; - struct hlist_head file_fcntl; - struct hlist_head file_set_fowner; - struct hlist_head file_send_sigiotask; - struct hlist_head file_receive; - struct hlist_head file_open; - struct hlist_head task_alloc; - struct hlist_head task_free; - struct hlist_head cred_alloc_blank; - struct hlist_head cred_free; - struct hlist_head cred_prepare; - struct hlist_head cred_transfer; - struct hlist_head cred_getsecid; - struct hlist_head kernel_act_as; - struct hlist_head kernel_create_files_as; - struct hlist_head kernel_load_data; - struct hlist_head kernel_read_file; - struct hlist_head kernel_post_read_file; - struct hlist_head kernel_module_request; - struct hlist_head task_fix_setuid; - struct hlist_head task_setpgid; - struct hlist_head task_getpgid; - struct hlist_head task_getsid; - struct hlist_head task_getsecid; - struct hlist_head task_setnice; - struct hlist_head task_setioprio; - struct hlist_head task_getioprio; - struct hlist_head task_prlimit; - struct hlist_head task_setrlimit; - struct hlist_head task_setscheduler; - struct hlist_head task_getscheduler; - struct hlist_head task_movememory; - struct hlist_head task_kill; - struct hlist_head task_prctl; - struct hlist_head task_to_inode; - struct hlist_head ipc_permission; - struct hlist_head ipc_getsecid; - struct hlist_head msg_msg_alloc_security; - struct hlist_head msg_msg_free_security; - struct hlist_head msg_queue_alloc_security; - struct hlist_head msg_queue_free_security; - struct hlist_head msg_queue_associate; - struct hlist_head msg_queue_msgctl; - struct hlist_head msg_queue_msgsnd; - struct hlist_head msg_queue_msgrcv; - struct hlist_head shm_alloc_security; - struct hlist_head shm_free_security; - struct hlist_head shm_associate; - struct hlist_head shm_shmctl; - struct hlist_head shm_shmat; - struct hlist_head sem_alloc_security; - struct hlist_head sem_free_security; - struct hlist_head sem_associate; - struct hlist_head sem_semctl; - struct hlist_head sem_semop; - struct hlist_head netlink_send; - struct hlist_head d_instantiate; - struct hlist_head getprocattr; - struct hlist_head setprocattr; - struct hlist_head ismaclabel; - struct hlist_head secid_to_secctx; - struct hlist_head secctx_to_secid; - struct hlist_head release_secctx; - struct hlist_head inode_invalidate_secctx; - struct hlist_head inode_notifysecctx; - struct hlist_head inode_setsecctx; - struct hlist_head inode_getsecctx; -#ifdef CONFIG_SECURITY_NETWORK - struct hlist_head unix_stream_connect; - struct hlist_head unix_may_send; - struct hlist_head socket_create; - struct hlist_head socket_post_create; - struct hlist_head socket_socketpair; - struct hlist_head socket_bind; - struct hlist_head socket_connect; - struct hlist_head socket_listen; - struct hlist_head socket_accept; - struct hlist_head socket_sendmsg; - struct hlist_head socket_recvmsg; - struct hlist_head socket_getsockname; - struct hlist_head socket_getpeername; - struct hlist_head socket_getsockopt; - struct hlist_head socket_setsockopt; - struct hlist_head socket_shutdown; - struct hlist_head socket_sock_rcv_skb; - struct hlist_head socket_getpeersec_stream; - struct hlist_head socket_getpeersec_dgram; - struct hlist_head sk_alloc_security; - struct hlist_head sk_free_security; - struct hlist_head sk_clone_security; - struct hlist_head sk_getsecid; - struct hlist_head sock_graft; - struct hlist_head inet_conn_request; - struct hlist_head inet_csk_clone; - struct hlist_head inet_conn_established; - struct hlist_head secmark_relabel_packet; - struct hlist_head secmark_refcount_inc; - struct hlist_head secmark_refcount_dec; - struct hlist_head req_classify_flow; - struct hlist_head tun_dev_alloc_security; - struct hlist_head tun_dev_free_security; - struct hlist_head tun_dev_create; - struct hlist_head tun_dev_attach_queue; - struct hlist_head tun_dev_attach; - struct hlist_head tun_dev_open; - struct hlist_head sctp_assoc_request; - struct hlist_head sctp_bind_connect; - struct hlist_head sctp_sk_clone; -#endif /* CONFIG_SECURITY_NETWORK */ -#ifdef CONFIG_SECURITY_INFINIBAND - struct hlist_head ib_pkey_access; - struct hlist_head ib_endport_manage_subnet; - struct hlist_head ib_alloc_security; - struct hlist_head ib_free_security; -#endif /* CONFIG_SECURITY_INFINIBAND */ -#ifdef CONFIG_SECURITY_NETWORK_XFRM - struct hlist_head xfrm_policy_alloc_security; - struct hlist_head xfrm_policy_clone_security; - struct hlist_head xfrm_policy_free_security; - struct hlist_head xfrm_policy_delete_security; - struct hlist_head xfrm_state_alloc; - struct hlist_head xfrm_state_alloc_acquire; - struct hlist_head xfrm_state_free_security; - struct hlist_head xfrm_state_delete_security; - struct hlist_head xfrm_policy_lookup; - struct hlist_head xfrm_state_pol_flow_match; - struct hlist_head xfrm_decode_session; -#endif /* CONFIG_SECURITY_NETWORK_XFRM */ -#ifdef CONFIG_KEYS - struct hlist_head key_alloc; - struct hlist_head key_free; - struct hlist_head key_permission; - struct hlist_head key_getsecurity; -#endif /* CONFIG_KEYS */ -#ifdef CONFIG_AUDIT - struct hlist_head audit_rule_init; - struct hlist_head audit_rule_known; - struct hlist_head audit_rule_match; - struct hlist_head audit_rule_free; -#endif /* CONFIG_AUDIT */ -#ifdef CONFIG_BPF_SYSCALL - struct hlist_head bpf; - struct hlist_head bpf_map; - struct hlist_head bpf_prog; - struct hlist_head bpf_map_alloc_security; - struct hlist_head bpf_map_free_security; - struct hlist_head bpf_prog_alloc_security; - struct hlist_head bpf_prog_free_security; -#endif /* CONFIG_BPF_SYSCALL */ - struct hlist_head locked_down; -#ifdef CONFIG_PERF_EVENTS - struct hlist_head perf_event_open; - struct hlist_head perf_event_alloc; - struct hlist_head perf_event_free; - struct hlist_head perf_event_read; - struct hlist_head perf_event_write; -#endif + #define LSM_HOOK(RET, DEFAULT, NAME, ...) struct hlist_head NAME; + #include "lsm_hook_defs.h" + #undef LSM_HOOK } __randomize_layout; /* @@ -2101,6 +1491,12 @@ struct lsm_blob_sizes { }; /* + * LSM_RET_VOID is used as the default value in LSM_HOOK definitions for void + * LSM hooks (in include/linux/lsm_hook_defs.h). + */ +#define LSM_RET_VOID ((void) 0) + +/* * Initializing a security_hook_list structure takes * up a lot of space in a source file. This macro takes * care of the common case and reduces the amount of diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b521500b244d..130a668049ab 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3777,7 +3777,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf); int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, - int fd, u32 flags); + int fd, int expected_fd, u32 flags); u32 __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op, enum bpf_netdev_command cmd); int xdp_umem_query(struct net_device *dev, u16 queue_id); diff --git a/include/linux/tnum.h b/include/linux/tnum.h index ea627d1ab7e3..498dbcedb451 100644 --- a/include/linux/tnum.h +++ b/include/linux/tnum.h @@ -86,4 +86,16 @@ int tnum_strn(char *str, size_t size, struct tnum a); /* Format a tnum as tristate binary expansion */ int tnum_sbin(char *str, size_t size, struct tnum a); +/* Returns the 32-bit subreg */ +struct tnum tnum_subreg(struct tnum a); +/* Returns the tnum with the lower 32-bit subreg cleared */ +struct tnum tnum_clear_subreg(struct tnum a); +/* Returns the tnum with the lower 32-bit subreg set to value */ +struct tnum tnum_const_subreg(struct tnum a, u32 value); +/* Returns true if 32-bit subreg @a is a known constant*/ +static inline bool tnum_subreg_is_const(struct tnum a) +{ + return !(tnum_subreg(a)).mask; +} + #endif /* _LINUX_TNUM_H */ diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h index 4295de3e6a4b..7e78e7d6f015 100644 --- a/include/net/cls_cgroup.h +++ b/include/net/cls_cgroup.h @@ -45,9 +45,14 @@ static inline void sock_update_classid(struct sock_cgroup_data *skcd) sock_cgroup_set_classid(skcd, classid); } +static inline u32 __task_get_classid(struct task_struct *task) +{ + return task_cls_state(task)->classid; +} + static inline u32 task_get_classid(const struct sk_buff *skb) { - u32 classid = task_cls_state(current)->classid; + u32 classid = __task_get_classid(current); /* Due to the nature of the classifier it is required to ignore all * packets originating from softirq context as accessing `current' diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index fe96bf247aac..81b965953036 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -85,9 +85,8 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, int iif, int sdif, bool *refcounted) { - struct sock *sk = skb_steal_sock(skb); + struct sock *sk = skb_steal_sock(skb, refcounted); - *refcounted = true; if (sk) return sk; diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index d0019d3395cf..ad64ba6a057f 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -379,10 +379,9 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, const int sdif, bool *refcounted) { - struct sock *sk = skb_steal_sock(skb); + struct sock *sk = skb_steal_sock(skb, refcounted); const struct iphdr *iph = ip_hdr(skb); - *refcounted = true; if (sk) return sk; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 854d39ef1ca3..ab96fb59131c 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -168,6 +168,9 @@ struct net { #ifdef CONFIG_XFRM struct netns_xfrm xfrm; #endif + + atomic64_t net_cookie; /* written once */ + #if IS_ENABLED(CONFIG_IP_VS) struct netns_ipvs *ipvs; #endif @@ -225,6 +228,8 @@ extern struct list_head net_namespace_list; struct net *get_net_ns_by_pid(pid_t pid); struct net *get_net_ns_by_fd(int fd); +u64 net_gen_cookie(struct net *net); + #ifdef CONFIG_SYSCTL void ipx_register_sysctl(void); void ipx_unregister_sysctl(void); diff --git a/include/net/sock.h b/include/net/sock.h index b5cca7bae69b..6d84784d33fa 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1659,6 +1659,7 @@ void sock_rfree(struct sk_buff *skb); void sock_efree(struct sk_buff *skb); #ifdef CONFIG_INET void sock_edemux(struct sk_buff *skb); +void sock_pfree(struct sk_buff *skb); #else #define sock_edemux sock_efree #endif @@ -2526,16 +2527,14 @@ void sock_net_set(struct sock *sk, struct net *net) write_pnet(&sk->sk_net, net); } -static inline struct sock *skb_steal_sock(struct sk_buff *skb) +static inline bool +skb_sk_is_prefetched(struct sk_buff *skb) { - if (skb->sk) { - struct sock *sk = skb->sk; - - skb->destructor = NULL; - skb->sk = NULL; - return sk; - } - return NULL; +#ifdef CONFIG_INET + return skb->destructor == sock_pfree; +#else + return false; +#endif /* CONFIG_INET */ } /* This helper checks if a socket is a full socket, @@ -2546,6 +2545,35 @@ static inline bool sk_fullsock(const struct sock *sk) return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV); } +static inline bool +sk_is_refcounted(struct sock *sk) +{ + /* Only full sockets have sk->sk_flags. */ + return !sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE); +} + +/** + * skb_steal_sock + * @skb to steal the socket from + * @refcounted is set to true if the socket is reference-counted + */ +static inline struct sock * +skb_steal_sock(struct sk_buff *skb, bool *refcounted) +{ + if (skb->sk) { + struct sock *sk = skb->sk; + + *refcounted = true; + if (skb_sk_is_prefetched(skb)) + *refcounted = sk_is_refcounted(sk); + skb->destructor = NULL; + skb->sk = NULL; + return sk; + } + *refcounted = false; + return NULL; +} + /* Checks if this SKB belongs to an HW offloaded socket * and whether any SW fallbacks are required based on dev. * Check decrypted mark in case skb_orphan() cleared socket. diff --git a/include/net/tcp.h b/include/net/tcp.h index 43fa07a36fa6..5fa9eacd965a 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2207,8 +2207,6 @@ static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) #ifdef CONFIG_NET_SOCK_MSG int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, u32 bytes, int flags); -int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, - int nonblock, int flags, int *addr_len); int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); #endif /* CONFIG_NET_SOCK_MSG */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 5d01c5c7e598..2e29a671d67e 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -111,6 +111,8 @@ enum bpf_cmd { BPF_MAP_LOOKUP_AND_DELETE_BATCH, BPF_MAP_UPDATE_BATCH, BPF_MAP_DELETE_BATCH, + BPF_LINK_CREATE, + BPF_LINK_UPDATE, }; enum bpf_map_type { @@ -181,6 +183,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_TRACING, BPF_PROG_TYPE_STRUCT_OPS, BPF_PROG_TYPE_EXT, + BPF_PROG_TYPE_LSM, }; enum bpf_attach_type { @@ -211,6 +214,7 @@ enum bpf_attach_type { BPF_TRACE_FENTRY, BPF_TRACE_FEXIT, BPF_MODIFY_RETURN, + BPF_LSM_MAC, __MAX_BPF_ATTACH_TYPE }; @@ -539,7 +543,7 @@ union bpf_attr { __u32 prog_cnt; } query; - struct { + struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */ __u64 name; __u32 prog_fd; } raw_tracepoint; @@ -567,6 +571,24 @@ union bpf_attr { __u64 probe_offset; /* output: probe_offset */ __u64 probe_addr; /* output: probe_addr */ } task_fd_query; + + struct { /* struct used by BPF_LINK_CREATE command */ + __u32 prog_fd; /* eBPF program to attach */ + __u32 target_fd; /* object to attach to */ + __u32 attach_type; /* attach type */ + __u32 flags; /* extra flags */ + } link_create; + + struct { /* struct used by BPF_LINK_UPDATE command */ + __u32 link_fd; /* link fd */ + /* new program fd to update link with */ + __u32 new_prog_fd; + __u32 flags; /* extra flags */ + /* expected link's program fd; is specified only if + * BPF_F_REPLACE flag is set in flags */ + __u32 old_prog_fd; + } link_update; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF @@ -2950,6 +2972,59 @@ union bpf_attr { * restricted to raw_tracepoint bpf programs. * Return * 0 on success, or a negative error in case of failure. + * + * u64 bpf_get_netns_cookie(void *ctx) + * Description + * Retrieve the cookie (generated by the kernel) of the network + * namespace the input *ctx* is associated with. The network + * namespace cookie remains stable for its lifetime and provides + * a global identifier that can be assumed unique. If *ctx* is + * NULL, then the helper returns the cookie for the initial + * network namespace. The cookie itself is very similar to that + * of bpf_get_socket_cookie() helper, but for network namespaces + * instead of sockets. + * Return + * A 8-byte long opaque number. + * + * u64 bpf_get_current_ancestor_cgroup_id(int ancestor_level) + * Description + * Return id of cgroup v2 that is ancestor of the cgroup associated + * with the current task at the *ancestor_level*. The root cgroup + * is at *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with the current task, then return value will be the + * same as that of **bpf_get_current_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with the current task. + * + * The format of returned id and helper limitations are same as in + * **bpf_get_current_cgroup_id**\ (). + * Return + * The id is returned or 0 in case the id could not be retrieved. + * + * int bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags) + * Description + * Assign the *sk* to the *skb*. When combined with appropriate + * routing configuration to receive the packet towards the socket, + * will cause *skb* to be delivered to the specified socket. + * Subsequent redirection of *skb* via **bpf_redirect**\ (), + * **bpf_clone_redirect**\ () or other methods outside of BPF may + * interfere with successful delivery to the socket. + * + * This operation is only valid from TC ingress path. + * + * The *flags* argument must be zero. + * Return + * 0 on success, or a negative errno in case of failure. + * + * * **-EINVAL** Unsupported flags specified. + * * **-ENOENT** Socket is unavailable for assignment. + * * **-ENETUNREACH** Socket is unreachable (wrong netns). + * * **-EOPNOTSUPP** Unsupported operation, for example a + * call from outside of TC ingress. + * * **-ESOCKTNOSUPPORT** Socket type not supported (reuseport). */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3073,7 +3148,10 @@ union bpf_attr { FN(jiffies64), \ FN(read_branch_records), \ FN(get_ns_current_pid_tgid), \ - FN(xdp_output), + FN(xdp_output), \ + FN(get_netns_cookie), \ + FN(get_current_ancestor_cgroup_id), \ + FN(sk_assign), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index e204c3e4dce1..127c704eeba9 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -974,11 +974,12 @@ enum { #define XDP_FLAGS_SKB_MODE (1U << 1) #define XDP_FLAGS_DRV_MODE (1U << 2) #define XDP_FLAGS_HW_MODE (1U << 3) +#define XDP_FLAGS_REPLACE (1U << 4) #define XDP_FLAGS_MODES (XDP_FLAGS_SKB_MODE | \ XDP_FLAGS_DRV_MODE | \ XDP_FLAGS_HW_MODE) #define XDP_FLAGS_MASK (XDP_FLAGS_UPDATE_IF_NOEXIST | \ - XDP_FLAGS_MODES) + XDP_FLAGS_MODES | XDP_FLAGS_REPLACE) /* These are stored into IFLA_XDP_ATTACHED on dump. */ enum { @@ -998,6 +999,7 @@ enum { IFLA_XDP_DRV_PROG_ID, IFLA_XDP_SKB_PROG_ID, IFLA_XDP_HW_PROG_ID, + IFLA_XDP_EXPECTED_FD, __IFLA_XDP_MAX, }; diff --git a/init/Kconfig b/init/Kconfig index 4f717bfdbfe2..680dbb7dd64f 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1615,6 +1615,19 @@ config KALLSYMS_BASE_RELATIVE # end of the "standard kernel features (expert users)" menu # syscall, maps, verifier + +config BPF_LSM + bool "LSM Instrumentation with BPF" + depends on BPF_EVENTS + depends on BPF_SYSCALL + depends on SECURITY + depends on BPF_JIT + help + Enables instrumentation of the security hooks with eBPF programs for + implementing dynamic MAC and Audit Policies. + + If you are unsure how to answer this question, answer N. + config BPF_SYSCALL bool "Enable bpf() system call" select BPF diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 046ce5d98033..f2d7be596966 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -29,4 +29,5 @@ obj-$(CONFIG_DEBUG_INFO_BTF) += sysfs_btf.o endif ifeq ($(CONFIG_BPF_JIT),y) obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o +obj-${CONFIG_BPF_LSM} += bpf_lsm.o endif diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c new file mode 100644 index 000000000000..19636703b24e --- /dev/null +++ b/kernel/bpf/bpf_lsm.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (C) 2020 Google LLC. + */ + +#include <linux/filter.h> +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/lsm_hooks.h> +#include <linux/bpf_lsm.h> +#include <linux/kallsyms.h> +#include <linux/bpf_verifier.h> + +/* For every LSM hook that allows attachment of BPF programs, declare a nop + * function where a BPF program can be attached. + */ +#define LSM_HOOK(RET, DEFAULT, NAME, ...) \ +noinline RET bpf_lsm_##NAME(__VA_ARGS__) \ +{ \ + return DEFAULT; \ +} + +#include <linux/lsm_hook_defs.h> +#undef LSM_HOOK + +#define BPF_LSM_SYM_PREFX "bpf_lsm_" + +int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, + const struct bpf_prog *prog) +{ + if (!prog->gpl_compatible) { + bpf_log(vlog, + "LSM programs must have a GPL compatible license\n"); + return -EINVAL; + } + + if (strncmp(BPF_LSM_SYM_PREFX, prog->aux->attach_func_name, + sizeof(BPF_LSM_SYM_PREFX) - 1)) { + bpf_log(vlog, "attach_btf_id %u points to wrong type name %s\n", + prog->aux->attach_btf_id, prog->aux->attach_func_name); + return -EINVAL; + } + + return 0; +} + +const struct bpf_prog_ops lsm_prog_ops = { +}; + +const struct bpf_verifier_ops lsm_verifier_ops = { + .get_func_proto = bpf_tracing_func_proto, + .is_valid_access = btf_ctx_access, +}; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 50f3c8c7bb2c..d65c6912bdaf 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3477,8 +3477,8 @@ errout: return ERR_PTR(err); } -extern char __weak _binary__btf_vmlinux_bin_start[]; -extern char __weak _binary__btf_vmlinux_bin_end[]; +extern char __weak __start_BTF[]; +extern char __weak __stop_BTF[]; extern struct btf *btf_vmlinux; #define BPF_MAP_TYPE(_id, _ops) @@ -3605,9 +3605,8 @@ struct btf *btf_parse_vmlinux(void) } env->btf = btf; - btf->data = _binary__btf_vmlinux_bin_start; - btf->data_size = _binary__btf_vmlinux_bin_end - - _binary__btf_vmlinux_bin_start; + btf->data = __start_BTF; + btf->data_size = __stop_BTF - __start_BTF; err = btf_parse_hdr(env); if (err) @@ -3710,12 +3709,34 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, nr_args--; } + if (arg > nr_args) { + bpf_log(log, "func '%s' doesn't have %d-th argument\n", + tname, arg + 1); + return false; + } + if (arg == nr_args) { - if (prog->expected_attach_type == BPF_TRACE_FEXIT) { + switch (prog->expected_attach_type) { + case BPF_LSM_MAC: + case BPF_TRACE_FEXIT: + /* When LSM programs are attached to void LSM hooks + * they use FEXIT trampolines and when attached to + * int LSM hooks, they use MODIFY_RETURN trampolines. + * + * While the LSM programs are BPF_MODIFY_RETURN-like + * the check: + * + * if (ret_type != 'int') + * return -EINVAL; + * + * is _not_ done here. This is still safe as LSM hooks + * have only void and int return types. + */ if (!t) return true; t = btf_type_by_id(btf, t->type); - } else if (prog->expected_attach_type == BPF_MODIFY_RETURN) { + break; + case BPF_MODIFY_RETURN: /* For now the BPF_MODIFY_RETURN can only be attached to * functions that return an int. */ @@ -3729,17 +3750,19 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, btf_kind_str[BTF_INFO_KIND(t->info)]); return false; } + break; + default: + bpf_log(log, "func '%s' doesn't have %d-th argument\n", + tname, arg + 1); + return false; } - } else if (arg >= nr_args) { - bpf_log(log, "func '%s' doesn't have %d-th argument\n", - tname, arg + 1); - return false; } else { if (!t) /* Default prog with 5 args */ return true; t = btf_type_by_id(btf, args[arg].type); } + /* skip modifiers */ while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 4f1472409ef8..cb305e71e7de 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -28,6 +28,69 @@ void cgroup_bpf_offline(struct cgroup *cgrp) percpu_ref_kill(&cgrp->bpf.refcnt); } +static void bpf_cgroup_storages_free(struct bpf_cgroup_storage *storages[]) +{ + enum bpf_cgroup_storage_type stype; + + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_free(storages[stype]); +} + +static int bpf_cgroup_storages_alloc(struct bpf_cgroup_storage *storages[], + struct bpf_prog *prog) +{ + enum bpf_cgroup_storage_type stype; + + for_each_cgroup_storage_type(stype) { + storages[stype] = bpf_cgroup_storage_alloc(prog, stype); + if (IS_ERR(storages[stype])) { + storages[stype] = NULL; + bpf_cgroup_storages_free(storages); + return -ENOMEM; + } + } + + return 0; +} + +static void bpf_cgroup_storages_assign(struct bpf_cgroup_storage *dst[], + struct bpf_cgroup_storage *src[]) +{ + enum bpf_cgroup_storage_type stype; + + for_each_cgroup_storage_type(stype) + dst[stype] = src[stype]; +} + +static void bpf_cgroup_storages_link(struct bpf_cgroup_storage *storages[], + struct cgroup* cgrp, + enum bpf_attach_type attach_type) +{ + enum bpf_cgroup_storage_type stype; + + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_link(storages[stype], cgrp, attach_type); +} + +static void bpf_cgroup_storages_unlink(struct bpf_cgroup_storage *storages[]) +{ + enum bpf_cgroup_storage_type stype; + + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_unlink(storages[stype]); +} + +/* Called when bpf_cgroup_link is auto-detached from dying cgroup. + * It drops cgroup and bpf_prog refcounts, and marks bpf_link as defunct. It + * doesn't free link memory, which will eventually be done by bpf_link's + * release() callback, when its last FD is closed. + */ +static void bpf_cgroup_link_auto_detach(struct bpf_cgroup_link *link) +{ + cgroup_put(link->cgroup); + link->cgroup = NULL; +} + /** * cgroup_bpf_release() - put references of all bpf programs and * release all cgroup bpf data @@ -37,7 +100,6 @@ static void cgroup_bpf_release(struct work_struct *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; @@ -49,11 +111,12 @@ static void cgroup_bpf_release(struct work_struct *work) list_for_each_entry_safe(pl, tmp, progs, node) { list_del(&pl->node); - bpf_prog_put(pl->prog); - for_each_cgroup_storage_type(stype) { - bpf_cgroup_storage_unlink(pl->storage[stype]); - bpf_cgroup_storage_free(pl->storage[stype]); - } + if (pl->prog) + bpf_prog_put(pl->prog); + if (pl->link) + bpf_cgroup_link_auto_detach(pl->link); + bpf_cgroup_storages_unlink(pl->storage); + bpf_cgroup_storages_free(pl->storage); kfree(pl); static_branch_dec(&cgroup_bpf_enabled_key); } @@ -85,6 +148,18 @@ static void cgroup_bpf_release_fn(struct percpu_ref *ref) queue_work(system_wq, &cgrp->bpf.release_work); } +/* Get underlying bpf_prog of bpf_prog_list entry, regardless if it's through + * link or direct prog. + */ +static struct bpf_prog *prog_list_prog(struct bpf_prog_list *pl) +{ + if (pl->prog) + return pl->prog; + if (pl->link) + return pl->link->link.prog; + return NULL; +} + /* count number of elements in the list. * it's slow but the list cannot be long */ @@ -94,7 +169,7 @@ static u32 prog_list_length(struct list_head *head) u32 cnt = 0; list_for_each_entry(pl, head, node) { - if (!pl->prog) + if (!prog_list_prog(pl)) continue; cnt++; } @@ -138,7 +213,7 @@ static int compute_effective_progs(struct cgroup *cgrp, enum bpf_attach_type type, struct bpf_prog_array **array) { - enum bpf_cgroup_storage_type stype; + struct bpf_prog_array_item *item; struct bpf_prog_array *progs; struct bpf_prog_list *pl; struct cgroup *p = cgrp; @@ -163,13 +238,13 @@ static int compute_effective_progs(struct cgroup *cgrp, continue; list_for_each_entry(pl, &p->bpf.progs[type], node) { - if (!pl->prog) + if (!prog_list_prog(pl)) continue; - progs->items[cnt].prog = pl->prog; - for_each_cgroup_storage_type(stype) - progs->items[cnt].cgroup_storage[stype] = - pl->storage[stype]; + item = &progs->items[cnt]; + item->prog = prog_list_prog(pl); + bpf_cgroup_storages_assign(item->cgroup_storage, + pl->storage); cnt++; } } while ((p = cgroup_parent(p))); @@ -287,19 +362,60 @@ cleanup: #define BPF_CGROUP_MAX_PROGS 64 +static struct bpf_prog_list *find_attach_entry(struct list_head *progs, + struct bpf_prog *prog, + struct bpf_cgroup_link *link, + struct bpf_prog *replace_prog, + bool allow_multi) +{ + struct bpf_prog_list *pl; + + /* single-attach case */ + if (!allow_multi) { + if (list_empty(progs)) + return NULL; + return list_first_entry(progs, typeof(*pl), node); + } + + list_for_each_entry(pl, progs, node) { + if (prog && pl->prog == prog) + /* disallow attaching the same prog twice */ + return ERR_PTR(-EINVAL); + if (link && pl->link == link) + /* disallow attaching the same link twice */ + return ERR_PTR(-EINVAL); + } + + /* direct prog multi-attach w/ replacement case */ + if (replace_prog) { + list_for_each_entry(pl, progs, node) { + if (pl->prog == replace_prog) + /* a match found */ + return pl; + } + /* prog to replace not found for cgroup */ + return ERR_PTR(-ENOENT); + } + + return NULL; +} + /** - * __cgroup_bpf_attach() - Attach the program to a cgroup, and + * __cgroup_bpf_attach() - Attach the program or the link to a cgroup, and * propagate the change to descendants * @cgrp: The cgroup which descendants to traverse * @prog: A program to attach + * @link: A link to attach * @replace_prog: Previously attached program to replace if BPF_F_REPLACE is set * @type: Type of attach operation * @flags: Option flags * + * Exactly one of @prog or @link can be non-null. * Must be called with cgroup_mutex held. */ -int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, - struct bpf_prog *replace_prog, +int __cgroup_bpf_attach(struct cgroup *cgrp, + struct bpf_prog *prog, struct bpf_prog *replace_prog, + struct bpf_cgroup_link *link, enum bpf_attach_type type, u32 flags) { u32 saved_flags = (flags & (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)); @@ -307,14 +423,19 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, struct bpf_prog *old_prog = NULL; struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {}; struct bpf_cgroup_storage *old_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {}; - struct bpf_prog_list *pl, *replace_pl = NULL; - enum bpf_cgroup_storage_type stype; + struct bpf_prog_list *pl; int err; if (((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI)) || ((flags & BPF_F_REPLACE) && !(flags & BPF_F_ALLOW_MULTI))) /* invalid combination */ return -EINVAL; + if (link && (prog || replace_prog)) + /* only either link or prog/replace_prog can be specified */ + return -EINVAL; + if (!!replace_prog != !!(flags & BPF_F_REPLACE)) + /* replace_prog implies BPF_F_REPLACE, and vice versa */ + return -EINVAL; if (!hierarchy_allows_attach(cgrp, type)) return -EPERM; @@ -329,140 +450,203 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS) return -E2BIG; - if (flags & BPF_F_ALLOW_MULTI) { - list_for_each_entry(pl, progs, node) { - if (pl->prog == prog) - /* disallow attaching the same prog twice */ - return -EINVAL; - if (pl->prog == replace_prog) - replace_pl = pl; - } - if ((flags & BPF_F_REPLACE) && !replace_pl) - /* prog to replace not found for cgroup */ - return -ENOENT; - } else if (!list_empty(progs)) { - replace_pl = list_first_entry(progs, typeof(*pl), node); - } + pl = find_attach_entry(progs, prog, link, replace_prog, + flags & BPF_F_ALLOW_MULTI); + if (IS_ERR(pl)) + return PTR_ERR(pl); - for_each_cgroup_storage_type(stype) { - storage[stype] = bpf_cgroup_storage_alloc(prog, stype); - if (IS_ERR(storage[stype])) { - storage[stype] = NULL; - for_each_cgroup_storage_type(stype) - bpf_cgroup_storage_free(storage[stype]); - return -ENOMEM; - } - } + if (bpf_cgroup_storages_alloc(storage, prog ? : link->link.prog)) + return -ENOMEM; - if (replace_pl) { - pl = replace_pl; + if (pl) { old_prog = pl->prog; - for_each_cgroup_storage_type(stype) { - old_storage[stype] = pl->storage[stype]; - bpf_cgroup_storage_unlink(old_storage[stype]); - } + bpf_cgroup_storages_unlink(pl->storage); + bpf_cgroup_storages_assign(old_storage, pl->storage); } else { pl = kmalloc(sizeof(*pl), GFP_KERNEL); if (!pl) { - for_each_cgroup_storage_type(stype) - bpf_cgroup_storage_free(storage[stype]); + bpf_cgroup_storages_free(storage); return -ENOMEM; } list_add_tail(&pl->node, progs); } pl->prog = prog; - for_each_cgroup_storage_type(stype) - pl->storage[stype] = storage[stype]; - + pl->link = link; + bpf_cgroup_storages_assign(pl->storage, storage); cgrp->bpf.flags[type] = saved_flags; err = update_effective_progs(cgrp, type); if (err) goto cleanup; - static_branch_inc(&cgroup_bpf_enabled_key); - for_each_cgroup_storage_type(stype) { - if (!old_storage[stype]) - continue; - bpf_cgroup_storage_free(old_storage[stype]); - } - if (old_prog) { + bpf_cgroup_storages_free(old_storage); + if (old_prog) bpf_prog_put(old_prog); - static_branch_dec(&cgroup_bpf_enabled_key); - } - for_each_cgroup_storage_type(stype) - bpf_cgroup_storage_link(storage[stype], cgrp, type); + else + static_branch_inc(&cgroup_bpf_enabled_key); + bpf_cgroup_storages_link(pl->storage, cgrp, type); return 0; cleanup: - /* and cleanup the prog list */ - pl->prog = old_prog; - for_each_cgroup_storage_type(stype) { - bpf_cgroup_storage_free(pl->storage[stype]); - pl->storage[stype] = old_storage[stype]; - bpf_cgroup_storage_link(old_storage[stype], cgrp, type); + if (old_prog) { + pl->prog = old_prog; + pl->link = NULL; } - if (!replace_pl) { + bpf_cgroup_storages_free(pl->storage); + bpf_cgroup_storages_assign(pl->storage, old_storage); + bpf_cgroup_storages_link(pl->storage, cgrp, type); + if (!old_prog) { list_del(&pl->node); kfree(pl); } return err; } +/* Swap updated BPF program for given link in effective program arrays across + * all descendant cgroups. This function is guaranteed to succeed. + */ +static void replace_effective_prog(struct cgroup *cgrp, + enum bpf_attach_type type, + struct bpf_cgroup_link *link) +{ + struct bpf_prog_array_item *item; + struct cgroup_subsys_state *css; + struct bpf_prog_array *progs; + struct bpf_prog_list *pl; + struct list_head *head; + struct cgroup *cg; + int pos; + + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + + if (percpu_ref_is_zero(&desc->bpf.refcnt)) + continue; + + /* find position of link in effective progs array */ + for (pos = 0, cg = desc; cg; cg = cgroup_parent(cg)) { + if (pos && !(cg->bpf.flags[type] & BPF_F_ALLOW_MULTI)) + continue; + + head = &cg->bpf.progs[type]; + list_for_each_entry(pl, head, node) { + if (!prog_list_prog(pl)) + continue; + if (pl->link == link) + goto found; + pos++; + } + } +found: + BUG_ON(!cg); + progs = rcu_dereference_protected( + desc->bpf.effective[type], + lockdep_is_held(&cgroup_mutex)); + item = &progs->items[pos]; + WRITE_ONCE(item->prog, link->link.prog); + } +} + /** - * __cgroup_bpf_detach() - Detach the program from a cgroup, and + * __cgroup_bpf_replace() - Replace link's program and propagate the change + * to descendants + * @cgrp: The cgroup which descendants to traverse + * @link: A link for which to replace BPF program + * @type: Type of attach operation + * + * Must be called with cgroup_mutex held. + */ +int __cgroup_bpf_replace(struct cgroup *cgrp, struct bpf_cgroup_link *link, + struct bpf_prog *new_prog) +{ + struct list_head *progs = &cgrp->bpf.progs[link->type]; + struct bpf_prog *old_prog; + struct bpf_prog_list *pl; + bool found = false; + + if (link->link.prog->type != new_prog->type) + return -EINVAL; + + list_for_each_entry(pl, progs, node) { + if (pl->link == link) { + found = true; + break; + } + } + if (!found) + return -ENOENT; + + old_prog = xchg(&link->link.prog, new_prog); + replace_effective_prog(cgrp, link->type, link); + bpf_prog_put(old_prog); + return 0; +} + +static struct bpf_prog_list *find_detach_entry(struct list_head *progs, + struct bpf_prog *prog, + struct bpf_cgroup_link *link, + bool allow_multi) +{ + struct bpf_prog_list *pl; + + if (!allow_multi) { + if (list_empty(progs)) + /* report error when trying to detach and nothing is attached */ + return ERR_PTR(-ENOENT); + + /* to maintain backward compatibility NONE and OVERRIDE cgroups + * allow detaching with invalid FD (prog==NULL) in legacy mode + */ + return list_first_entry(progs, typeof(*pl), node); + } + + if (!prog && !link) + /* to detach MULTI prog the user has to specify valid FD + * of the program or link to be detached + */ + return ERR_PTR(-EINVAL); + + /* find the prog or link and detach it */ + list_for_each_entry(pl, progs, node) { + if (pl->prog == prog && pl->link == link) + return pl; + } + return ERR_PTR(-ENOENT); +} + +/** + * __cgroup_bpf_detach() - Detach the program or link from a cgroup, and * propagate the change to descendants * @cgrp: The cgroup which descendants to traverse * @prog: A program to detach or NULL + * @prog: A link to detach or NULL * @type: Type of detach operation * + * At most one of @prog or @link can be non-NULL. * Must be called with cgroup_mutex held. */ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type) + struct bpf_cgroup_link *link, enum bpf_attach_type type) { struct list_head *progs = &cgrp->bpf.progs[type]; - enum bpf_cgroup_storage_type stype; u32 flags = cgrp->bpf.flags[type]; - struct bpf_prog *old_prog = NULL; struct bpf_prog_list *pl; + struct bpf_prog *old_prog; int err; - if (flags & BPF_F_ALLOW_MULTI) { - if (!prog) - /* to detach MULTI prog the user has to specify valid FD - * of the program to be detached - */ - return -EINVAL; - } else { - if (list_empty(progs)) - /* report error when trying to detach and nothing is attached */ - return -ENOENT; - } + if (prog && link) + /* only one of prog or link can be specified */ + return -EINVAL; - if (flags & BPF_F_ALLOW_MULTI) { - /* find the prog and detach it */ - list_for_each_entry(pl, progs, node) { - if (pl->prog != prog) - continue; - old_prog = prog; - /* mark it deleted, so it's ignored while - * recomputing effective - */ - pl->prog = NULL; - break; - } - if (!old_prog) - return -ENOENT; - } else { - /* to maintain backward compatibility NONE and OVERRIDE cgroups - * allow detaching with invalid FD (prog==NULL) - */ - pl = list_first_entry(progs, typeof(*pl), node); - old_prog = pl->prog; - pl->prog = NULL; - } + pl = find_detach_entry(progs, prog, link, flags & BPF_F_ALLOW_MULTI); + if (IS_ERR(pl)) + return PTR_ERR(pl); + + /* mark it deleted, so it's ignored while recomputing effective */ + old_prog = pl->prog; + pl->prog = NULL; + pl->link = NULL; err = update_effective_progs(cgrp, type); if (err) @@ -470,22 +654,21 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, /* now can actually delete it from this cgroup list */ list_del(&pl->node); - for_each_cgroup_storage_type(stype) { - bpf_cgroup_storage_unlink(pl->storage[stype]); - bpf_cgroup_storage_free(pl->storage[stype]); - } + bpf_cgroup_storages_unlink(pl->storage); + bpf_cgroup_storages_free(pl->storage); kfree(pl); if (list_empty(progs)) /* last program was detached, reset flags to zero */ cgrp->bpf.flags[type] = 0; - - bpf_prog_put(old_prog); + if (old_prog) + bpf_prog_put(old_prog); static_branch_dec(&cgroup_bpf_enabled_key); return 0; cleanup: - /* and restore back old_prog */ + /* restore back prog or link */ pl->prog = old_prog; + pl->link = link; return err; } @@ -498,6 +681,7 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, struct list_head *progs = &cgrp->bpf.progs[type]; u32 flags = cgrp->bpf.flags[type]; struct bpf_prog_array *effective; + struct bpf_prog *prog; int cnt, ret = 0, i; effective = rcu_dereference_protected(cgrp->bpf.effective[type], @@ -528,7 +712,8 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, i = 0; list_for_each_entry(pl, progs, node) { - id = pl->prog->aux->id; + prog = prog_list_prog(pl); + id = prog->aux->id; if (copy_to_user(prog_ids + i, &id, sizeof(id))) return -EFAULT; if (++i == cnt) @@ -558,8 +743,8 @@ int cgroup_bpf_prog_attach(const union bpf_attr *attr, } } - ret = cgroup_bpf_attach(cgrp, prog, replace_prog, attr->attach_type, - attr->attach_flags); + ret = cgroup_bpf_attach(cgrp, prog, replace_prog, NULL, + attr->attach_type, attr->attach_flags); if (replace_prog) bpf_prog_put(replace_prog); @@ -581,7 +766,7 @@ int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) if (IS_ERR(prog)) prog = NULL; - ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0); + ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type); if (prog) bpf_prog_put(prog); @@ -589,6 +774,90 @@ int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) return ret; } +static void bpf_cgroup_link_release(struct bpf_link *link) +{ + struct bpf_cgroup_link *cg_link = + container_of(link, struct bpf_cgroup_link, link); + + /* link might have been auto-detached by dying cgroup already, + * in that case our work is done here + */ + if (!cg_link->cgroup) + return; + + mutex_lock(&cgroup_mutex); + + /* re-check cgroup under lock again */ + if (!cg_link->cgroup) { + mutex_unlock(&cgroup_mutex); + return; + } + + WARN_ON(__cgroup_bpf_detach(cg_link->cgroup, NULL, cg_link, + cg_link->type)); + + mutex_unlock(&cgroup_mutex); + cgroup_put(cg_link->cgroup); +} + +static void bpf_cgroup_link_dealloc(struct bpf_link *link) +{ + struct bpf_cgroup_link *cg_link = + container_of(link, struct bpf_cgroup_link, link); + + kfree(cg_link); +} + +const struct bpf_link_ops bpf_cgroup_link_lops = { + .release = bpf_cgroup_link_release, + .dealloc = bpf_cgroup_link_dealloc, +}; + +int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_cgroup_link *link; + struct file *link_file; + struct cgroup *cgrp; + int err, link_fd; + + if (attr->link_create.flags) + return -EINVAL; + + cgrp = cgroup_get_from_fd(attr->link_create.target_fd); + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); + + link = kzalloc(sizeof(*link), GFP_USER); + if (!link) { + err = -ENOMEM; + goto out_put_cgroup; + } + bpf_link_init(&link->link, &bpf_cgroup_link_lops, prog); + link->cgroup = cgrp; + link->type = attr->link_create.attach_type; + + link_file = bpf_link_new_file(&link->link, &link_fd); + if (IS_ERR(link_file)) { + kfree(link); + err = PTR_ERR(link_file); + goto out_put_cgroup; + } + + err = cgroup_bpf_attach(cgrp, NULL, NULL, link, link->type, + BPF_F_ALLOW_MULTI); + if (err) { + bpf_link_cleanup(&link->link, link_file, link_fd); + goto out_put_cgroup; + } + + fd_install(link_fd, link_file); + return link_fd; + +out_put_cgroup: + cgroup_put(cgrp); + return err; +} + int cgroup_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 914f3463aa41..916f5132a984 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2156,6 +2156,7 @@ const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; const struct bpf_func_proto bpf_get_current_comm_proto __weak; const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak; +const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto __weak; const struct bpf_func_proto bpf_get_local_storage_proto __weak; const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto __weak; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 01878db15eaf..bafc53ddd350 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -340,6 +340,24 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { .ret_type = RET_INTEGER, }; +BPF_CALL_1(bpf_get_current_ancestor_cgroup_id, int, ancestor_level) +{ + struct cgroup *cgrp = task_dfl_cgroup(current); + struct cgroup *ancestor; + + ancestor = cgroup_ancestor(cgrp, ancestor_level); + if (!ancestor) + return 0; + return cgroup_id(ancestor); +} + +const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto = { + .func = bpf_get_current_ancestor_cgroup_id, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, +}; + #ifdef CONFIG_CGROUP_BPF DECLARE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index f00c00b942df..64783da34202 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -25,6 +25,7 @@ #include <linux/nospec.h> #include <linux/audit.h> #include <uapi/linux/btf.h> +#include <linux/bpf_lsm.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ @@ -1942,6 +1943,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, switch (prog_type) { case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_STRUCT_OPS: case BPF_PROG_TYPE_EXT: break; @@ -2181,13 +2183,6 @@ static int bpf_obj_get(const union bpf_attr *attr) attr->file_flags); } -struct bpf_link { - atomic64_t refcnt; - const struct bpf_link_ops *ops; - struct bpf_prog *prog; - struct work_struct work; -}; - void bpf_link_init(struct bpf_link *link, const struct bpf_link_ops *ops, struct bpf_prog *prog) { @@ -2201,8 +2196,8 @@ void bpf_link_init(struct bpf_link *link, const struct bpf_link_ops *ops, * anon_inode's release() call. This helper manages marking bpf_link as * defunct, releases anon_inode file and puts reserved FD. */ -static void bpf_link_cleanup(struct bpf_link *link, struct file *link_file, - int link_fd) +void bpf_link_cleanup(struct bpf_link *link, struct file *link_file, + int link_fd) { link->prog = NULL; fput(link_file); @@ -2260,7 +2255,6 @@ static int bpf_link_release(struct inode *inode, struct file *filp) #ifdef CONFIG_PROC_FS static const struct bpf_link_ops bpf_raw_tp_lops; static const struct bpf_link_ops bpf_tracing_link_lops; -static const struct bpf_link_ops bpf_xdp_link_lops; static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp) { @@ -2273,6 +2267,10 @@ static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp) link_type = "raw_tracepoint"; else if (link->ops == &bpf_tracing_link_lops) link_type = "tracing"; +#ifdef CONFIG_CGROUP_BPF + else if (link->ops == &bpf_cgroup_link_lops) + link_type = "cgroup"; +#endif else link_type = "unknown"; @@ -2375,10 +2373,28 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog) struct file *link_file; int link_fd, err; - if (prog->expected_attach_type != BPF_TRACE_FENTRY && - prog->expected_attach_type != BPF_TRACE_FEXIT && - prog->expected_attach_type != BPF_MODIFY_RETURN && - prog->type != BPF_PROG_TYPE_EXT) { + switch (prog->type) { + case BPF_PROG_TYPE_TRACING: + if (prog->expected_attach_type != BPF_TRACE_FENTRY && + prog->expected_attach_type != BPF_TRACE_FEXIT && + prog->expected_attach_type != BPF_MODIFY_RETURN) { + err = -EINVAL; + goto out_put_prog; + } + break; + case BPF_PROG_TYPE_EXT: + if (prog->expected_attach_type != 0) { + err = -EINVAL; + goto out_put_prog; + } + break; + case BPF_PROG_TYPE_LSM: + if (prog->expected_attach_type != BPF_LSM_MAC) { + err = -EINVAL; + goto out_put_prog; + } + break; + default: err = -EINVAL; goto out_put_prog; } @@ -2457,16 +2473,10 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) if (IS_ERR(prog)) return PTR_ERR(prog); - if (prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT && - prog->type != BPF_PROG_TYPE_TRACING && - prog->type != BPF_PROG_TYPE_EXT && - prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE) { - err = -EINVAL; - goto out_put_prog; - } - - if (prog->type == BPF_PROG_TYPE_TRACING || - prog->type == BPF_PROG_TYPE_EXT) { + switch (prog->type) { + case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_EXT: + case BPF_PROG_TYPE_LSM: if (attr->raw_tracepoint.name) { /* The attach point for this category of programs * should be specified via btf_id during program load. @@ -2474,11 +2484,14 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) err = -EINVAL; goto out_put_prog; } - if (prog->expected_attach_type == BPF_TRACE_RAW_TP) + if (prog->type == BPF_PROG_TYPE_TRACING && + prog->expected_attach_type == BPF_TRACE_RAW_TP) { tp_name = prog->aux->attach_func_name; - else - return bpf_tracing_prog_attach(prog); - } else { + break; + } + return bpf_tracing_prog_attach(prog); + case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: if (strncpy_from_user(buf, u64_to_user_ptr(attr->raw_tracepoint.name), sizeof(buf) - 1) < 0) { @@ -2487,6 +2500,10 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) } buf[sizeof(buf) - 1] = 0; tp_name = buf; + break; + default: + err = -EINVAL; + goto out_put_prog; } btp = bpf_get_raw_tracepoint(tp_name); @@ -2543,36 +2560,18 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, } } -#define BPF_PROG_ATTACH_LAST_FIELD replace_bpf_fd - -#define BPF_F_ATTACH_MASK \ - (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI | BPF_F_REPLACE) - -static int bpf_prog_attach(const union bpf_attr *attr) +static enum bpf_prog_type +attach_type_to_prog_type(enum bpf_attach_type attach_type) { - enum bpf_prog_type ptype; - struct bpf_prog *prog; - int ret; - - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - - if (CHECK_ATTR(BPF_PROG_ATTACH)) - return -EINVAL; - - if (attr->attach_flags & ~BPF_F_ATTACH_MASK) - return -EINVAL; - - switch (attr->attach_type) { + switch (attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: - ptype = BPF_PROG_TYPE_CGROUP_SKB; + return BPF_PROG_TYPE_CGROUP_SKB; break; case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: - ptype = BPF_PROG_TYPE_CGROUP_SOCK; - break; + return BPF_PROG_TYPE_CGROUP_SOCK; case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: @@ -2581,37 +2580,53 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: - ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; - break; + return BPF_PROG_TYPE_CGROUP_SOCK_ADDR; case BPF_CGROUP_SOCK_OPS: - ptype = BPF_PROG_TYPE_SOCK_OPS; - break; + return BPF_PROG_TYPE_SOCK_OPS; case BPF_CGROUP_DEVICE: - ptype = BPF_PROG_TYPE_CGROUP_DEVICE; - break; + return BPF_PROG_TYPE_CGROUP_DEVICE; case BPF_SK_MSG_VERDICT: - ptype = BPF_PROG_TYPE_SK_MSG; - break; + return BPF_PROG_TYPE_SK_MSG; case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: - ptype = BPF_PROG_TYPE_SK_SKB; - break; + return BPF_PROG_TYPE_SK_SKB; case BPF_LIRC_MODE2: - ptype = BPF_PROG_TYPE_LIRC_MODE2; - break; + return BPF_PROG_TYPE_LIRC_MODE2; case BPF_FLOW_DISSECTOR: - ptype = BPF_PROG_TYPE_FLOW_DISSECTOR; - break; + return BPF_PROG_TYPE_FLOW_DISSECTOR; case BPF_CGROUP_SYSCTL: - ptype = BPF_PROG_TYPE_CGROUP_SYSCTL; - break; + return BPF_PROG_TYPE_CGROUP_SYSCTL; case BPF_CGROUP_GETSOCKOPT: case BPF_CGROUP_SETSOCKOPT: - ptype = BPF_PROG_TYPE_CGROUP_SOCKOPT; - break; + return BPF_PROG_TYPE_CGROUP_SOCKOPT; default: - return -EINVAL; + return BPF_PROG_TYPE_UNSPEC; } +} + +#define BPF_PROG_ATTACH_LAST_FIELD replace_bpf_fd + +#define BPF_F_ATTACH_MASK \ + (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI | BPF_F_REPLACE) + +static int bpf_prog_attach(const union bpf_attr *attr) +{ + enum bpf_prog_type ptype; + struct bpf_prog *prog; + int ret; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (CHECK_ATTR(BPF_PROG_ATTACH)) + return -EINVAL; + + if (attr->attach_flags & ~BPF_F_ATTACH_MASK) + return -EINVAL; + + ptype = attach_type_to_prog_type(attr->attach_type); + if (ptype == BPF_PROG_TYPE_UNSPEC) + return -EINVAL; prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); if (IS_ERR(prog)) @@ -2633,8 +2648,17 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_PROG_TYPE_FLOW_DISSECTOR: ret = skb_flow_dissector_bpf_prog_attach(attr, prog); break; - default: + case BPF_PROG_TYPE_CGROUP_DEVICE: + case BPF_PROG_TYPE_CGROUP_SKB: + case BPF_PROG_TYPE_CGROUP_SOCK: + case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: + case BPF_PROG_TYPE_CGROUP_SOCKOPT: + case BPF_PROG_TYPE_CGROUP_SYSCTL: + case BPF_PROG_TYPE_SOCK_OPS: ret = cgroup_bpf_prog_attach(attr, ptype, prog); + break; + default: + ret = -EINVAL; } if (ret) @@ -2654,53 +2678,27 @@ static int bpf_prog_detach(const union bpf_attr *attr) if (CHECK_ATTR(BPF_PROG_DETACH)) return -EINVAL; - switch (attr->attach_type) { - case BPF_CGROUP_INET_INGRESS: - case BPF_CGROUP_INET_EGRESS: - ptype = BPF_PROG_TYPE_CGROUP_SKB; - break; - case BPF_CGROUP_INET_SOCK_CREATE: - case BPF_CGROUP_INET4_POST_BIND: - case BPF_CGROUP_INET6_POST_BIND: - ptype = BPF_PROG_TYPE_CGROUP_SOCK; - break; - case BPF_CGROUP_INET4_BIND: - case BPF_CGROUP_INET6_BIND: - case BPF_CGROUP_INET4_CONNECT: - case BPF_CGROUP_INET6_CONNECT: - case BPF_CGROUP_UDP4_SENDMSG: - case BPF_CGROUP_UDP6_SENDMSG: - case BPF_CGROUP_UDP4_RECVMSG: - case BPF_CGROUP_UDP6_RECVMSG: - ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; - break; - case BPF_CGROUP_SOCK_OPS: - ptype = BPF_PROG_TYPE_SOCK_OPS; - break; - case BPF_CGROUP_DEVICE: - ptype = BPF_PROG_TYPE_CGROUP_DEVICE; - break; - case BPF_SK_MSG_VERDICT: - return sock_map_get_from_fd(attr, NULL); - case BPF_SK_SKB_STREAM_PARSER: - case BPF_SK_SKB_STREAM_VERDICT: + ptype = attach_type_to_prog_type(attr->attach_type); + + switch (ptype) { + case BPF_PROG_TYPE_SK_MSG: + case BPF_PROG_TYPE_SK_SKB: return sock_map_get_from_fd(attr, NULL); - case BPF_LIRC_MODE2: + case BPF_PROG_TYPE_LIRC_MODE2: return lirc_prog_detach(attr); - case BPF_FLOW_DISSECTOR: + case BPF_PROG_TYPE_FLOW_DISSECTOR: return skb_flow_dissector_bpf_prog_detach(attr); - case BPF_CGROUP_SYSCTL: - ptype = BPF_PROG_TYPE_CGROUP_SYSCTL; - break; - case BPF_CGROUP_GETSOCKOPT: - case BPF_CGROUP_SETSOCKOPT: - ptype = BPF_PROG_TYPE_CGROUP_SOCKOPT; - break; + case BPF_PROG_TYPE_CGROUP_DEVICE: + case BPF_PROG_TYPE_CGROUP_SKB: + case BPF_PROG_TYPE_CGROUP_SOCK: + case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: + case BPF_PROG_TYPE_CGROUP_SOCKOPT: + case BPF_PROG_TYPE_CGROUP_SYSCTL: + case BPF_PROG_TYPE_SOCK_OPS: + return cgroup_bpf_prog_detach(attr, ptype); default: return -EINVAL; } - - return cgroup_bpf_prog_detach(attr, ptype); } #define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt @@ -2734,7 +2732,7 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_CGROUP_SYSCTL: case BPF_CGROUP_GETSOCKOPT: case BPF_CGROUP_SETSOCKOPT: - break; + return cgroup_bpf_prog_query(attr, uattr); case BPF_LIRC_MODE2: return lirc_prog_query(attr, uattr); case BPF_FLOW_DISSECTOR: @@ -2742,8 +2740,6 @@ static int bpf_prog_query(const union bpf_attr *attr, default: return -EINVAL; } - - return cgroup_bpf_prog_query(attr, uattr); } #define BPF_PROG_TEST_RUN_LAST_FIELD test.ctx_out @@ -3564,6 +3560,104 @@ err_put: return err; } +#define BPF_LINK_CREATE_LAST_FIELD link_create.flags +static int link_create(union bpf_attr *attr) +{ + enum bpf_prog_type ptype; + struct bpf_prog *prog; + int ret; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (CHECK_ATTR(BPF_LINK_CREATE)) + return -EINVAL; + + ptype = attach_type_to_prog_type(attr->link_create.attach_type); + if (ptype == BPF_PROG_TYPE_UNSPEC) + return -EINVAL; + + prog = bpf_prog_get_type(attr->link_create.prog_fd, ptype); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + ret = bpf_prog_attach_check_attach_type(prog, + attr->link_create.attach_type); + if (ret) + goto err_out; + + switch (ptype) { + case BPF_PROG_TYPE_CGROUP_SKB: + case BPF_PROG_TYPE_CGROUP_SOCK: + case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: + case BPF_PROG_TYPE_SOCK_OPS: + case BPF_PROG_TYPE_CGROUP_DEVICE: + case BPF_PROG_TYPE_CGROUP_SYSCTL: + case BPF_PROG_TYPE_CGROUP_SOCKOPT: + ret = cgroup_bpf_link_attach(attr, prog); + break; + default: + ret = -EINVAL; + } + +err_out: + if (ret < 0) + bpf_prog_put(prog); + return ret; +} + +#define BPF_LINK_UPDATE_LAST_FIELD link_update.old_prog_fd + +static int link_update(union bpf_attr *attr) +{ + struct bpf_prog *old_prog = NULL, *new_prog; + struct bpf_link *link; + u32 flags; + int ret; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (CHECK_ATTR(BPF_LINK_UPDATE)) + return -EINVAL; + + flags = attr->link_update.flags; + if (flags & ~BPF_F_REPLACE) + return -EINVAL; + + link = bpf_link_get_from_fd(attr->link_update.link_fd); + if (IS_ERR(link)) + return PTR_ERR(link); + + new_prog = bpf_prog_get(attr->link_update.new_prog_fd); + if (IS_ERR(new_prog)) + return PTR_ERR(new_prog); + + if (flags & BPF_F_REPLACE) { + old_prog = bpf_prog_get(attr->link_update.old_prog_fd); + if (IS_ERR(old_prog)) { + ret = PTR_ERR(old_prog); + old_prog = NULL; + goto out_put_progs; + } + } + +#ifdef CONFIG_CGROUP_BPF + if (link->ops == &bpf_cgroup_link_lops) { + ret = cgroup_bpf_replace(link, old_prog, new_prog); + goto out_put_progs; + } +#endif + ret = -EINVAL; + +out_put_progs: + if (old_prog) + bpf_prog_put(old_prog); + if (ret) + bpf_prog_put(new_prog); + return ret; +} + SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { union bpf_attr attr; @@ -3675,6 +3769,12 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_MAP_DELETE_BATCH: err = bpf_map_do_batch(&attr, uattr, BPF_MAP_DELETE_BATCH); break; + case BPF_LINK_CREATE: + err = link_create(&attr); + break; + case BPF_LINK_UPDATE: + err = link_update(&attr); + break; default: err = -EINVAL; break; diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c index 7ae5dddd1fe6..3b495773de5a 100644 --- a/kernel/bpf/sysfs_btf.c +++ b/kernel/bpf/sysfs_btf.c @@ -9,15 +9,15 @@ #include <linux/sysfs.h> /* See scripts/link-vmlinux.sh, gen_btf() func for details */ -extern char __weak _binary__btf_vmlinux_bin_start[]; -extern char __weak _binary__btf_vmlinux_bin_end[]; +extern char __weak __start_BTF[]; +extern char __weak __stop_BTF[]; static ssize_t btf_vmlinux_read(struct file *file, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len) { - memcpy(buf, _binary__btf_vmlinux_bin_start + off, len); + memcpy(buf, __start_BTF + off, len); return len; } @@ -30,15 +30,14 @@ static struct kobject *btf_kobj; static int __init btf_vmlinux_init(void) { - if (!_binary__btf_vmlinux_bin_start) + if (!__start_BTF) return 0; btf_kobj = kobject_create_and_add("btf", kernel_kobj); if (!btf_kobj) return -ENOMEM; - bin_attr_btf_vmlinux.size = _binary__btf_vmlinux_bin_end - - _binary__btf_vmlinux_bin_start; + bin_attr_btf_vmlinux.size = __stop_BTF - __start_BTF; return sysfs_create_bin_file(btf_kobj, &bin_attr_btf_vmlinux); } diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c index d4f335a9a899..ceac5281bd31 100644 --- a/kernel/bpf/tnum.c +++ b/kernel/bpf/tnum.c @@ -194,3 +194,18 @@ int tnum_sbin(char *str, size_t size, struct tnum a) str[min(size - 1, (size_t)64)] = 0; return 64; } + +struct tnum tnum_subreg(struct tnum a) +{ + return tnum_cast(a, 4); +} + +struct tnum tnum_clear_subreg(struct tnum a) +{ + return tnum_lshift(tnum_rshift(a, 32), 32); +} + +struct tnum tnum_const_subreg(struct tnum a, u32 value) +{ + return tnum_or(tnum_clear_subreg(a), tnum_const(value)); +} diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index f30bca2a4d01..9be85aa4ec5f 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -6,6 +6,7 @@ #include <linux/ftrace.h> #include <linux/rbtree_latch.h> #include <linux/perf_event.h> +#include <linux/btf.h> /* dummy _ops. The verifier will operate on target program's ops. */ const struct bpf_verifier_ops bpf_extension_verifier_ops = { @@ -233,15 +234,23 @@ out: return err; } -static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(enum bpf_attach_type t) +static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog) { - switch (t) { + switch (prog->expected_attach_type) { case BPF_TRACE_FENTRY: return BPF_TRAMP_FENTRY; case BPF_MODIFY_RETURN: return BPF_TRAMP_MODIFY_RETURN; case BPF_TRACE_FEXIT: return BPF_TRAMP_FEXIT; + case BPF_LSM_MAC: + if (!prog->aux->attach_func_proto->type) + /* The function returns void, we cannot modify its + * return value. + */ + return BPF_TRAMP_FEXIT; + else + return BPF_TRAMP_MODIFY_RETURN; default: return BPF_TRAMP_REPLACE; } @@ -255,7 +264,7 @@ int bpf_trampoline_link_prog(struct bpf_prog *prog) int cnt; tr = prog->aux->trampoline; - kind = bpf_attach_type_to_tramp(prog->expected_attach_type); + kind = bpf_attach_type_to_tramp(prog); mutex_lock(&tr->mutex); if (tr->extension_prog) { /* cannot attach fentry/fexit if extension prog is attached. @@ -305,7 +314,7 @@ int bpf_trampoline_unlink_prog(struct bpf_prog *prog) int err; tr = prog->aux->trampoline; - kind = bpf_attach_type_to_tramp(prog->expected_attach_type); + kind = bpf_attach_type_to_tramp(prog); mutex_lock(&tr->mutex); if (kind == BPF_TRAMP_REPLACE) { WARN_ON_ONCE(!tr->extension_prog); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 745f3cfdf3b2..04c6630cc18f 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -20,6 +20,7 @@ #include <linux/perf_event.h> #include <linux/ctype.h> #include <linux/error-injection.h> +#include <linux/bpf_lsm.h> #include "disasm.h" @@ -228,8 +229,7 @@ struct bpf_call_arg_meta { bool pkt_access; int regno; int access_size; - s64 msize_smax_value; - u64 msize_umax_value; + u64 msize_max_value; int ref_obj_id; int func_id; u32 btf_id; @@ -550,6 +550,22 @@ static void print_verifier_state(struct bpf_verifier_env *env, tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, ",var_off=%s", tn_buf); } + if (reg->s32_min_value != reg->smin_value && + reg->s32_min_value != S32_MIN) + verbose(env, ",s32_min_value=%d", + (int)(reg->s32_min_value)); + if (reg->s32_max_value != reg->smax_value && + reg->s32_max_value != S32_MAX) + verbose(env, ",s32_max_value=%d", + (int)(reg->s32_max_value)); + if (reg->u32_min_value != reg->umin_value && + reg->u32_min_value != U32_MIN) + verbose(env, ",u32_min_value=%d", + (int)(reg->u32_min_value)); + if (reg->u32_max_value != reg->umax_value && + reg->u32_max_value != U32_MAX) + verbose(env, ",u32_max_value=%d", + (int)(reg->u32_max_value)); } verbose(env, ")"); } @@ -924,6 +940,20 @@ static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm) reg->smax_value = (s64)imm; reg->umin_value = imm; reg->umax_value = imm; + + reg->s32_min_value = (s32)imm; + reg->s32_max_value = (s32)imm; + reg->u32_min_value = (u32)imm; + reg->u32_max_value = (u32)imm; +} + +static void __mark_reg32_known(struct bpf_reg_state *reg, u64 imm) +{ + reg->var_off = tnum_const_subreg(reg->var_off, imm); + reg->s32_min_value = (s32)imm; + reg->s32_max_value = (s32)imm; + reg->u32_min_value = (u32)imm; + reg->u32_max_value = (u32)imm; } /* Mark the 'variable offset' part of a register as zero. This should be @@ -978,8 +1008,52 @@ static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg, tnum_equals_const(reg->var_off, 0); } -/* Attempts to improve min/max values based on var_off information */ -static void __update_reg_bounds(struct bpf_reg_state *reg) +/* Reset the min/max bounds of a register */ +static void __mark_reg_unbounded(struct bpf_reg_state *reg) +{ + reg->smin_value = S64_MIN; + reg->smax_value = S64_MAX; + reg->umin_value = 0; + reg->umax_value = U64_MAX; + + reg->s32_min_value = S32_MIN; + reg->s32_max_value = S32_MAX; + reg->u32_min_value = 0; + reg->u32_max_value = U32_MAX; +} + +static void __mark_reg64_unbounded(struct bpf_reg_state *reg) +{ + reg->smin_value = S64_MIN; + reg->smax_value = S64_MAX; + reg->umin_value = 0; + reg->umax_value = U64_MAX; +} + +static void __mark_reg32_unbounded(struct bpf_reg_state *reg) +{ + reg->s32_min_value = S32_MIN; + reg->s32_max_value = S32_MAX; + reg->u32_min_value = 0; + reg->u32_max_value = U32_MAX; +} + +static void __update_reg32_bounds(struct bpf_reg_state *reg) +{ + struct tnum var32_off = tnum_subreg(reg->var_off); + + /* min signed is max(sign bit) | min(other bits) */ + reg->s32_min_value = max_t(s32, reg->s32_min_value, + var32_off.value | (var32_off.mask & S32_MIN)); + /* max signed is min(sign bit) | max(other bits) */ + reg->s32_max_value = min_t(s32, reg->s32_max_value, + var32_off.value | (var32_off.mask & S32_MAX)); + reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)var32_off.value); + reg->u32_max_value = min(reg->u32_max_value, + (u32)(var32_off.value | var32_off.mask)); +} + +static void __update_reg64_bounds(struct bpf_reg_state *reg) { /* min signed is max(sign bit) | min(other bits) */ reg->smin_value = max_t(s64, reg->smin_value, @@ -992,8 +1066,48 @@ static void __update_reg_bounds(struct bpf_reg_state *reg) reg->var_off.value | reg->var_off.mask); } +static void __update_reg_bounds(struct bpf_reg_state *reg) +{ + __update_reg32_bounds(reg); + __update_reg64_bounds(reg); +} + /* Uses signed min/max values to inform unsigned, and vice-versa */ -static void __reg_deduce_bounds(struct bpf_reg_state *reg) +static void __reg32_deduce_bounds(struct bpf_reg_state *reg) +{ + /* Learn sign from signed bounds. + * If we cannot cross the sign boundary, then signed and unsigned bounds + * are the same, so combine. This works even in the negative case, e.g. + * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff. + */ + if (reg->s32_min_value >= 0 || reg->s32_max_value < 0) { + reg->s32_min_value = reg->u32_min_value = + max_t(u32, reg->s32_min_value, reg->u32_min_value); + reg->s32_max_value = reg->u32_max_value = + min_t(u32, reg->s32_max_value, reg->u32_max_value); + return; + } + /* Learn sign from unsigned bounds. Signed bounds cross the sign + * boundary, so we must be careful. + */ + if ((s32)reg->u32_max_value >= 0) { + /* Positive. We can't learn anything from the smin, but smax + * is positive, hence safe. + */ + reg->s32_min_value = reg->u32_min_value; + reg->s32_max_value = reg->u32_max_value = + min_t(u32, reg->s32_max_value, reg->u32_max_value); + } else if ((s32)reg->u32_min_value < 0) { + /* Negative. We can't learn anything from the smax, but smin + * is negative, hence safe. + */ + reg->s32_min_value = reg->u32_min_value = + max_t(u32, reg->s32_min_value, reg->u32_min_value); + reg->s32_max_value = reg->u32_max_value; + } +} + +static void __reg64_deduce_bounds(struct bpf_reg_state *reg) { /* Learn sign from signed bounds. * If we cannot cross the sign boundary, then signed and unsigned bounds @@ -1027,32 +1141,106 @@ static void __reg_deduce_bounds(struct bpf_reg_state *reg) } } +static void __reg_deduce_bounds(struct bpf_reg_state *reg) +{ + __reg32_deduce_bounds(reg); + __reg64_deduce_bounds(reg); +} + /* Attempts to improve var_off based on unsigned min/max information */ static void __reg_bound_offset(struct bpf_reg_state *reg) { - reg->var_off = tnum_intersect(reg->var_off, - tnum_range(reg->umin_value, - reg->umax_value)); + struct tnum var64_off = tnum_intersect(reg->var_off, + tnum_range(reg->umin_value, + reg->umax_value)); + struct tnum var32_off = tnum_intersect(tnum_subreg(reg->var_off), + tnum_range(reg->u32_min_value, + reg->u32_max_value)); + + reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off); +} + +static void __reg_assign_32_into_64(struct bpf_reg_state *reg) +{ + reg->umin_value = reg->u32_min_value; + reg->umax_value = reg->u32_max_value; + /* Attempt to pull 32-bit signed bounds into 64-bit bounds + * but must be positive otherwise set to worse case bounds + * and refine later from tnum. + */ + if (reg->s32_min_value > 0) + reg->smin_value = reg->s32_min_value; + else + reg->smin_value = 0; + if (reg->s32_max_value > 0) + reg->smax_value = reg->s32_max_value; + else + reg->smax_value = U32_MAX; +} + +static void __reg_combine_32_into_64(struct bpf_reg_state *reg) +{ + /* special case when 64-bit register has upper 32-bit register + * zeroed. Typically happens after zext or <<32, >>32 sequence + * allowing us to use 32-bit bounds directly, + */ + if (tnum_equals_const(tnum_clear_subreg(reg->var_off), 0)) { + __reg_assign_32_into_64(reg); + } else { + /* Otherwise the best we can do is push lower 32bit known and + * unknown bits into register (var_off set from jmp logic) + * then learn as much as possible from the 64-bit tnum + * known and unknown bits. The previous smin/smax bounds are + * invalid here because of jmp32 compare so mark them unknown + * so they do not impact tnum bounds calculation. + */ + __mark_reg64_unbounded(reg); + __update_reg_bounds(reg); + } + + /* Intersecting with the old var_off might have improved our bounds + * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), + * then new var_off is (0; 0x7f...fc) which improves our umax. + */ + __reg_deduce_bounds(reg); + __reg_bound_offset(reg); + __update_reg_bounds(reg); } -static void __reg_bound_offset32(struct bpf_reg_state *reg) +static bool __reg64_bound_s32(s64 a) { - u64 mask = 0xffffFFFF; - struct tnum range = tnum_range(reg->umin_value & mask, - reg->umax_value & mask); - struct tnum lo32 = tnum_cast(reg->var_off, 4); - struct tnum hi32 = tnum_lshift(tnum_rshift(reg->var_off, 32), 32); + if (a > S32_MIN && a < S32_MAX) + return true; + return false; +} - reg->var_off = tnum_or(hi32, tnum_intersect(lo32, range)); +static bool __reg64_bound_u32(u64 a) +{ + if (a > U32_MIN && a < U32_MAX) + return true; + return false; } -/* Reset the min/max bounds of a register */ -static void __mark_reg_unbounded(struct bpf_reg_state *reg) +static void __reg_combine_64_into_32(struct bpf_reg_state *reg) { - reg->smin_value = S64_MIN; - reg->smax_value = S64_MAX; - reg->umin_value = 0; - reg->umax_value = U64_MAX; + __mark_reg32_unbounded(reg); + + if (__reg64_bound_s32(reg->smin_value)) + reg->s32_min_value = (s32)reg->smin_value; + if (__reg64_bound_s32(reg->smax_value)) + reg->s32_max_value = (s32)reg->smax_value; + if (__reg64_bound_u32(reg->umin_value)) + reg->u32_min_value = (u32)reg->umin_value; + if (__reg64_bound_u32(reg->umax_value)) + reg->u32_max_value = (u32)reg->umax_value; + + /* Intersecting with the old var_off might have improved our bounds + * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), + * then new var_off is (0; 0x7f...fc) which improves our umax. + */ + __reg_deduce_bounds(reg); + __reg_bound_offset(reg); + __update_reg_bounds(reg); } /* Mark a register as having a completely unknown (scalar) value. */ @@ -2785,6 +2973,12 @@ static int check_tp_buffer_access(struct bpf_verifier_env *env, return 0; } +/* BPF architecture zero extends alu32 ops into 64-bit registesr */ +static void zext_32_to_64(struct bpf_reg_state *reg) +{ + reg->var_off = tnum_subreg(reg->var_off); + __reg_assign_32_into_64(reg); +} /* truncate register to smaller size (in bytes) * must be called with size < BPF_REG_SIZE @@ -2807,6 +3001,14 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) } reg->smin_value = reg->umin_value; reg->smax_value = reg->umax_value; + + /* If size is smaller than 32bit register the 32bit register + * values are also truncated so we push 64-bit bounds into + * 32-bit bounds. Above were truncated < 32-bits already. + */ + if (size >= 4) + return; + __reg_combine_64_into_32(reg); } static bool bpf_map_is_rdonly(const struct bpf_map *map) @@ -3461,13 +3663,17 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, expected_type = CONST_PTR_TO_MAP; if (type != expected_type) goto err_type; - } else if (arg_type == ARG_PTR_TO_CTX) { + } else if (arg_type == ARG_PTR_TO_CTX || + arg_type == ARG_PTR_TO_CTX_OR_NULL) { expected_type = PTR_TO_CTX; - if (type != expected_type) - goto err_type; - err = check_ctx_reg(env, reg, regno); - if (err < 0) - return err; + if (!(register_is_null(reg) && + arg_type == ARG_PTR_TO_CTX_OR_NULL)) { + if (type != expected_type) + goto err_type; + err = check_ctx_reg(env, reg, regno); + if (err < 0) + return err; + } } else if (arg_type == ARG_PTR_TO_SOCK_COMMON) { expected_type = PTR_TO_SOCK_COMMON; /* Any sk pointer can be ARG_PTR_TO_SOCK_COMMON */ @@ -3577,11 +3783,15 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, } else if (arg_type_is_mem_size(arg_type)) { bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO); - /* remember the mem_size which may be used later - * to refine return values. + /* This is used to refine r0 return value bounds for helpers + * that enforce this value as an upper bound on return values. + * See do_refine_retval_range() for helpers that can refine + * the return value. C type of helper is u32 so we pull register + * bound from umax_value however, if negative verifier errors + * out. Only upper bounds can be learned because retval is an + * int type and negative retvals are allowed. */ - meta->msize_smax_value = reg->smax_value; - meta->msize_umax_value = reg->umax_value; + meta->msize_max_value = reg->umax_value; /* The register is SCALAR_VALUE; the access check * happens using its boundaries. @@ -4124,10 +4334,11 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type, func_id != BPF_FUNC_probe_read_str)) return; - ret_reg->smax_value = meta->msize_smax_value; - ret_reg->umax_value = meta->msize_umax_value; + ret_reg->smax_value = meta->msize_max_value; + ret_reg->s32_max_value = meta->msize_max_value; __reg_deduce_bounds(ret_reg); __reg_bound_offset(ret_reg); + __update_reg_bounds(ret_reg); } static int @@ -4434,7 +4645,17 @@ static bool signed_add_overflows(s64 a, s64 b) return res < a; } -static bool signed_sub_overflows(s64 a, s64 b) +static bool signed_add32_overflows(s64 a, s64 b) +{ + /* Do the add in u32, where overflow is well-defined */ + s32 res = (s32)((u32)a + (u32)b); + + if (b < 0) + return res > a; + return res < a; +} + +static bool signed_sub_overflows(s32 a, s32 b) { /* Do the sub in u64, where overflow is well-defined */ s64 res = (s64)((u64)a - (u64)b); @@ -4444,6 +4665,16 @@ static bool signed_sub_overflows(s64 a, s64 b) return res > a; } +static bool signed_sub32_overflows(s32 a, s32 b) +{ + /* Do the sub in u64, where overflow is well-defined */ + s32 res = (s32)((u32)a - (u32)b); + + if (b < 0) + return res < a; + return res > a; +} + static bool check_reg_sane_offset(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, enum bpf_reg_type type) @@ -4680,6 +4911,9 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, !check_reg_sane_offset(env, ptr_reg, ptr_reg->type)) return -EINVAL; + /* pointer types do not carry 32-bit bounds at the moment. */ + __mark_reg32_unbounded(dst_reg); + switch (opcode) { case BPF_ADD: ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0); @@ -4843,6 +5077,518 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, return 0; } +static void scalar32_min_max_add(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + s32 smin_val = src_reg->s32_min_value; + s32 smax_val = src_reg->s32_max_value; + u32 umin_val = src_reg->u32_min_value; + u32 umax_val = src_reg->u32_max_value; + + if (signed_add32_overflows(dst_reg->s32_min_value, smin_val) || + signed_add32_overflows(dst_reg->s32_max_value, smax_val)) { + dst_reg->s32_min_value = S32_MIN; + dst_reg->s32_max_value = S32_MAX; + } else { + dst_reg->s32_min_value += smin_val; + dst_reg->s32_max_value += smax_val; + } + if (dst_reg->u32_min_value + umin_val < umin_val || + dst_reg->u32_max_value + umax_val < umax_val) { + dst_reg->u32_min_value = 0; + dst_reg->u32_max_value = U32_MAX; + } else { + dst_reg->u32_min_value += umin_val; + dst_reg->u32_max_value += umax_val; + } +} + +static void scalar_min_max_add(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + s64 smin_val = src_reg->smin_value; + s64 smax_val = src_reg->smax_value; + u64 umin_val = src_reg->umin_value; + u64 umax_val = src_reg->umax_value; + + if (signed_add_overflows(dst_reg->smin_value, smin_val) || + signed_add_overflows(dst_reg->smax_value, smax_val)) { + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; + } else { + dst_reg->smin_value += smin_val; + dst_reg->smax_value += smax_val; + } + if (dst_reg->umin_value + umin_val < umin_val || + dst_reg->umax_value + umax_val < umax_val) { + dst_reg->umin_value = 0; + dst_reg->umax_value = U64_MAX; + } else { + dst_reg->umin_value += umin_val; + dst_reg->umax_value += umax_val; + } +} + +static void scalar32_min_max_sub(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + s32 smin_val = src_reg->s32_min_value; + s32 smax_val = src_reg->s32_max_value; + u32 umin_val = src_reg->u32_min_value; + u32 umax_val = src_reg->u32_max_value; + + if (signed_sub32_overflows(dst_reg->s32_min_value, smax_val) || + signed_sub32_overflows(dst_reg->s32_max_value, smin_val)) { + /* Overflow possible, we know nothing */ + dst_reg->s32_min_value = S32_MIN; + dst_reg->s32_max_value = S32_MAX; + } else { + dst_reg->s32_min_value -= smax_val; + dst_reg->s32_max_value -= smin_val; + } + if (dst_reg->u32_min_value < umax_val) { + /* Overflow possible, we know nothing */ + dst_reg->u32_min_value = 0; + dst_reg->u32_max_value = U32_MAX; + } else { + /* Cannot overflow (as long as bounds are consistent) */ + dst_reg->u32_min_value -= umax_val; + dst_reg->u32_max_value -= umin_val; + } +} + +static void scalar_min_max_sub(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + s64 smin_val = src_reg->smin_value; + s64 smax_val = src_reg->smax_value; + u64 umin_val = src_reg->umin_value; + u64 umax_val = src_reg->umax_value; + + if (signed_sub_overflows(dst_reg->smin_value, smax_val) || + signed_sub_overflows(dst_reg->smax_value, smin_val)) { + /* Overflow possible, we know nothing */ + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; + } else { + dst_reg->smin_value -= smax_val; + dst_reg->smax_value -= smin_val; + } + if (dst_reg->umin_value < umax_val) { + /* Overflow possible, we know nothing */ + dst_reg->umin_value = 0; + dst_reg->umax_value = U64_MAX; + } else { + /* Cannot overflow (as long as bounds are consistent) */ + dst_reg->umin_value -= umax_val; + dst_reg->umax_value -= umin_val; + } +} + +static void scalar32_min_max_mul(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + s32 smin_val = src_reg->s32_min_value; + u32 umin_val = src_reg->u32_min_value; + u32 umax_val = src_reg->u32_max_value; + + if (smin_val < 0 || dst_reg->s32_min_value < 0) { + /* Ain't nobody got time to multiply that sign */ + __mark_reg32_unbounded(dst_reg); + return; + } + /* Both values are positive, so we can work with unsigned and + * copy the result to signed (unless it exceeds S32_MAX). + */ + if (umax_val > U16_MAX || dst_reg->u32_max_value > U16_MAX) { + /* Potential overflow, we know nothing */ + __mark_reg32_unbounded(dst_reg); + return; + } + dst_reg->u32_min_value *= umin_val; + dst_reg->u32_max_value *= umax_val; + if (dst_reg->u32_max_value > S32_MAX) { + /* Overflow possible, we know nothing */ + dst_reg->s32_min_value = S32_MIN; + dst_reg->s32_max_value = S32_MAX; + } else { + dst_reg->s32_min_value = dst_reg->u32_min_value; + dst_reg->s32_max_value = dst_reg->u32_max_value; + } +} + +static void scalar_min_max_mul(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + s64 smin_val = src_reg->smin_value; + u64 umin_val = src_reg->umin_value; + u64 umax_val = src_reg->umax_value; + + if (smin_val < 0 || dst_reg->smin_value < 0) { + /* Ain't nobody got time to multiply that sign */ + __mark_reg64_unbounded(dst_reg); + return; + } + /* Both values are positive, so we can work with unsigned and + * copy the result to signed (unless it exceeds S64_MAX). + */ + if (umax_val > U32_MAX || dst_reg->umax_value > U32_MAX) { + /* Potential overflow, we know nothing */ + __mark_reg64_unbounded(dst_reg); + return; + } + dst_reg->umin_value *= umin_val; + dst_reg->umax_value *= umax_val; + if (dst_reg->umax_value > S64_MAX) { + /* Overflow possible, we know nothing */ + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; + } else { + dst_reg->smin_value = dst_reg->umin_value; + dst_reg->smax_value = dst_reg->umax_value; + } +} + +static void scalar32_min_max_and(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + bool src_known = tnum_subreg_is_const(src_reg->var_off); + bool dst_known = tnum_subreg_is_const(dst_reg->var_off); + struct tnum var32_off = tnum_subreg(dst_reg->var_off); + s32 smin_val = src_reg->s32_min_value; + u32 umax_val = src_reg->u32_max_value; + + /* Assuming scalar64_min_max_and will be called so its safe + * to skip updating register for known 32-bit case. + */ + if (src_known && dst_known) + return; + + /* We get our minimum from the var_off, since that's inherently + * bitwise. Our maximum is the minimum of the operands' maxima. + */ + dst_reg->u32_min_value = var32_off.value; + dst_reg->u32_max_value = min(dst_reg->u32_max_value, umax_val); + if (dst_reg->s32_min_value < 0 || smin_val < 0) { + /* Lose signed bounds when ANDing negative numbers, + * ain't nobody got time for that. + */ + dst_reg->s32_min_value = S32_MIN; + dst_reg->s32_max_value = S32_MAX; + } else { + /* ANDing two positives gives a positive, so safe to + * cast result into s64. + */ + dst_reg->s32_min_value = dst_reg->u32_min_value; + dst_reg->s32_max_value = dst_reg->u32_max_value; + } + +} + +static void scalar_min_max_and(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + bool src_known = tnum_is_const(src_reg->var_off); + bool dst_known = tnum_is_const(dst_reg->var_off); + s64 smin_val = src_reg->smin_value; + u64 umax_val = src_reg->umax_value; + + if (src_known && dst_known) { + __mark_reg_known(dst_reg, dst_reg->var_off.value & + src_reg->var_off.value); + return; + } + + /* We get our minimum from the var_off, since that's inherently + * bitwise. Our maximum is the minimum of the operands' maxima. + */ + dst_reg->umin_value = dst_reg->var_off.value; + dst_reg->umax_value = min(dst_reg->umax_value, umax_val); + if (dst_reg->smin_value < 0 || smin_val < 0) { + /* Lose signed bounds when ANDing negative numbers, + * ain't nobody got time for that. + */ + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; + } else { + /* ANDing two positives gives a positive, so safe to + * cast result into s64. + */ + dst_reg->smin_value = dst_reg->umin_value; + dst_reg->smax_value = dst_reg->umax_value; + } + /* We may learn something more from the var_off */ + __update_reg_bounds(dst_reg); +} + +static void scalar32_min_max_or(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + bool src_known = tnum_subreg_is_const(src_reg->var_off); + bool dst_known = tnum_subreg_is_const(dst_reg->var_off); + struct tnum var32_off = tnum_subreg(dst_reg->var_off); + s32 smin_val = src_reg->smin_value; + u32 umin_val = src_reg->umin_value; + + /* Assuming scalar64_min_max_or will be called so it is safe + * to skip updating register for known case. + */ + if (src_known && dst_known) + return; + + /* We get our maximum from the var_off, and our minimum is the + * maximum of the operands' minima + */ + dst_reg->u32_min_value = max(dst_reg->u32_min_value, umin_val); + dst_reg->u32_max_value = var32_off.value | var32_off.mask; + if (dst_reg->s32_min_value < 0 || smin_val < 0) { + /* Lose signed bounds when ORing negative numbers, + * ain't nobody got time for that. + */ + dst_reg->s32_min_value = S32_MIN; + dst_reg->s32_max_value = S32_MAX; + } else { + /* ORing two positives gives a positive, so safe to + * cast result into s64. + */ + dst_reg->s32_min_value = dst_reg->umin_value; + dst_reg->s32_max_value = dst_reg->umax_value; + } +} + +static void scalar_min_max_or(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + bool src_known = tnum_is_const(src_reg->var_off); + bool dst_known = tnum_is_const(dst_reg->var_off); + s64 smin_val = src_reg->smin_value; + u64 umin_val = src_reg->umin_value; + + if (src_known && dst_known) { + __mark_reg_known(dst_reg, dst_reg->var_off.value | + src_reg->var_off.value); + return; + } + + /* We get our maximum from the var_off, and our minimum is the + * maximum of the operands' minima + */ + dst_reg->umin_value = max(dst_reg->umin_value, umin_val); + dst_reg->umax_value = dst_reg->var_off.value | dst_reg->var_off.mask; + if (dst_reg->smin_value < 0 || smin_val < 0) { + /* Lose signed bounds when ORing negative numbers, + * ain't nobody got time for that. + */ + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; + } else { + /* ORing two positives gives a positive, so safe to + * cast result into s64. + */ + dst_reg->smin_value = dst_reg->umin_value; + dst_reg->smax_value = dst_reg->umax_value; + } + /* We may learn something more from the var_off */ + __update_reg_bounds(dst_reg); +} + +static void __scalar32_min_max_lsh(struct bpf_reg_state *dst_reg, + u64 umin_val, u64 umax_val) +{ + /* We lose all sign bit information (except what we can pick + * up from var_off) + */ + dst_reg->s32_min_value = S32_MIN; + dst_reg->s32_max_value = S32_MAX; + /* If we might shift our top bit out, then we know nothing */ + if (umax_val > 31 || dst_reg->u32_max_value > 1ULL << (31 - umax_val)) { + dst_reg->u32_min_value = 0; + dst_reg->u32_max_value = U32_MAX; + } else { + dst_reg->u32_min_value <<= umin_val; + dst_reg->u32_max_value <<= umax_val; + } +} + +static void scalar32_min_max_lsh(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + u32 umax_val = src_reg->u32_max_value; + u32 umin_val = src_reg->u32_min_value; + /* u32 alu operation will zext upper bits */ + struct tnum subreg = tnum_subreg(dst_reg->var_off); + + __scalar32_min_max_lsh(dst_reg, umin_val, umax_val); + dst_reg->var_off = tnum_subreg(tnum_lshift(subreg, umin_val)); + /* Not required but being careful mark reg64 bounds as unknown so + * that we are forced to pick them up from tnum and zext later and + * if some path skips this step we are still safe. + */ + __mark_reg64_unbounded(dst_reg); + __update_reg32_bounds(dst_reg); +} + +static void __scalar64_min_max_lsh(struct bpf_reg_state *dst_reg, + u64 umin_val, u64 umax_val) +{ + /* Special case <<32 because it is a common compiler pattern to sign + * extend subreg by doing <<32 s>>32. In this case if 32bit bounds are + * positive we know this shift will also be positive so we can track + * bounds correctly. Otherwise we lose all sign bit information except + * what we can pick up from var_off. Perhaps we can generalize this + * later to shifts of any length. + */ + if (umin_val == 32 && umax_val == 32 && dst_reg->s32_max_value >= 0) + dst_reg->smax_value = (s64)dst_reg->s32_max_value << 32; + else + dst_reg->smax_value = S64_MAX; + + if (umin_val == 32 && umax_val == 32 && dst_reg->s32_min_value >= 0) + dst_reg->smin_value = (s64)dst_reg->s32_min_value << 32; + else + dst_reg->smin_value = S64_MIN; + + /* If we might shift our top bit out, then we know nothing */ + if (dst_reg->umax_value > 1ULL << (63 - umax_val)) { + dst_reg->umin_value = 0; + dst_reg->umax_value = U64_MAX; + } else { + dst_reg->umin_value <<= umin_val; + dst_reg->umax_value <<= umax_val; + } +} + +static void scalar_min_max_lsh(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + u64 umax_val = src_reg->umax_value; + u64 umin_val = src_reg->umin_value; + + /* scalar64 calc uses 32bit unshifted bounds so must be called first */ + __scalar64_min_max_lsh(dst_reg, umin_val, umax_val); + __scalar32_min_max_lsh(dst_reg, umin_val, umax_val); + + dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val); + /* We may learn something more from the var_off */ + __update_reg_bounds(dst_reg); +} + +static void scalar32_min_max_rsh(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + struct tnum subreg = tnum_subreg(dst_reg->var_off); + u32 umax_val = src_reg->u32_max_value; + u32 umin_val = src_reg->u32_min_value; + + /* BPF_RSH is an unsigned shift. If the value in dst_reg might + * be negative, then either: + * 1) src_reg might be zero, so the sign bit of the result is + * unknown, so we lose our signed bounds + * 2) it's known negative, thus the unsigned bounds capture the + * signed bounds + * 3) the signed bounds cross zero, so they tell us nothing + * about the result + * If the value in dst_reg is known nonnegative, then again the + * unsigned bounts capture the signed bounds. + * Thus, in all cases it suffices to blow away our signed bounds + * and rely on inferring new ones from the unsigned bounds and + * var_off of the result. + */ + dst_reg->s32_min_value = S32_MIN; + dst_reg->s32_max_value = S32_MAX; + + dst_reg->var_off = tnum_rshift(subreg, umin_val); + dst_reg->u32_min_value >>= umax_val; + dst_reg->u32_max_value >>= umin_val; + + __mark_reg64_unbounded(dst_reg); + __update_reg32_bounds(dst_reg); +} + +static void scalar_min_max_rsh(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + u64 umax_val = src_reg->umax_value; + u64 umin_val = src_reg->umin_value; + + /* BPF_RSH is an unsigned shift. If the value in dst_reg might + * be negative, then either: + * 1) src_reg might be zero, so the sign bit of the result is + * unknown, so we lose our signed bounds + * 2) it's known negative, thus the unsigned bounds capture the + * signed bounds + * 3) the signed bounds cross zero, so they tell us nothing + * about the result + * If the value in dst_reg is known nonnegative, then again the + * unsigned bounts capture the signed bounds. + * Thus, in all cases it suffices to blow away our signed bounds + * and rely on inferring new ones from the unsigned bounds and + * var_off of the result. + */ + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; + dst_reg->var_off = tnum_rshift(dst_reg->var_off, umin_val); + dst_reg->umin_value >>= umax_val; + dst_reg->umax_value >>= umin_val; + + /* Its not easy to operate on alu32 bounds here because it depends + * on bits being shifted in. Take easy way out and mark unbounded + * so we can recalculate later from tnum. + */ + __mark_reg32_unbounded(dst_reg); + __update_reg_bounds(dst_reg); +} + +static void scalar32_min_max_arsh(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + u64 umin_val = src_reg->u32_min_value; + + /* Upon reaching here, src_known is true and + * umax_val is equal to umin_val. + */ + dst_reg->s32_min_value = (u32)(((s32)dst_reg->s32_min_value) >> umin_val); + dst_reg->s32_max_value = (u32)(((s32)dst_reg->s32_max_value) >> umin_val); + + dst_reg->var_off = tnum_arshift(tnum_subreg(dst_reg->var_off), umin_val, 32); + + /* blow away the dst_reg umin_value/umax_value and rely on + * dst_reg var_off to refine the result. + */ + dst_reg->u32_min_value = 0; + dst_reg->u32_max_value = U32_MAX; + + __mark_reg64_unbounded(dst_reg); + __update_reg32_bounds(dst_reg); +} + +static void scalar_min_max_arsh(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + u64 umin_val = src_reg->umin_value; + + /* Upon reaching here, src_known is true and umax_val is equal + * to umin_val. + */ + dst_reg->smin_value >>= umin_val; + dst_reg->smax_value >>= umin_val; + + dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val, 64); + + /* blow away the dst_reg umin_value/umax_value and rely on + * dst_reg var_off to refine the result. + */ + dst_reg->umin_value = 0; + dst_reg->umax_value = U64_MAX; + + /* Its not easy to operate on alu32 bounds here because it depends + * on bits being shifted in from upper 32-bits. Take easy way out + * and mark unbounded so we can recalculate later from tnum. + */ + __mark_reg32_unbounded(dst_reg); + __update_reg_bounds(dst_reg); +} + /* WARNING: This function does calculations on 64-bit values, but the actual * execution may occur on 32-bit values. Therefore, things like bitshifts * need extra checks in the 32-bit case. @@ -4857,33 +5603,47 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, bool src_known, dst_known; s64 smin_val, smax_val; u64 umin_val, umax_val; + s32 s32_min_val, s32_max_val; + u32 u32_min_val, u32_max_val; u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32; u32 dst = insn->dst_reg; int ret; - - if (insn_bitness == 32) { - /* Relevant for 32-bit RSH: Information can propagate towards - * LSB, so it isn't sufficient to only truncate the output to - * 32 bits. - */ - coerce_reg_to_size(dst_reg, 4); - coerce_reg_to_size(&src_reg, 4); - } + bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64); smin_val = src_reg.smin_value; smax_val = src_reg.smax_value; umin_val = src_reg.umin_value; umax_val = src_reg.umax_value; - src_known = tnum_is_const(src_reg.var_off); - dst_known = tnum_is_const(dst_reg->var_off); - if ((src_known && (smin_val != smax_val || umin_val != umax_val)) || - smin_val > smax_val || umin_val > umax_val) { - /* Taint dst register if offset had invalid bounds derived from - * e.g. dead branches. - */ - __mark_reg_unknown(env, dst_reg); - return 0; + s32_min_val = src_reg.s32_min_value; + s32_max_val = src_reg.s32_max_value; + u32_min_val = src_reg.u32_min_value; + u32_max_val = src_reg.u32_max_value; + + if (alu32) { + src_known = tnum_subreg_is_const(src_reg.var_off); + dst_known = tnum_subreg_is_const(dst_reg->var_off); + if ((src_known && + (s32_min_val != s32_max_val || u32_min_val != u32_max_val)) || + s32_min_val > s32_max_val || u32_min_val > u32_max_val) { + /* Taint dst register if offset had invalid bounds + * derived from e.g. dead branches. + */ + __mark_reg_unknown(env, dst_reg); + return 0; + } + } else { + src_known = tnum_is_const(src_reg.var_off); + dst_known = tnum_is_const(dst_reg->var_off); + if ((src_known && + (smin_val != smax_val || umin_val != umax_val)) || + smin_val > smax_val || umin_val > umax_val) { + /* Taint dst register if offset had invalid bounds + * derived from e.g. dead branches. + */ + __mark_reg_unknown(env, dst_reg); + return 0; + } } if (!src_known && @@ -4892,6 +5652,20 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, return 0; } + /* Calculate sign/unsigned bounds and tnum for alu32 and alu64 bit ops. + * There are two classes of instructions: The first class we track both + * alu32 and alu64 sign/unsigned bounds independently this provides the + * greatest amount of precision when alu operations are mixed with jmp32 + * operations. These operations are BPF_ADD, BPF_SUB, BPF_MUL, BPF_ADD, + * and BPF_OR. This is possible because these ops have fairly easy to + * understand and calculate behavior in both 32-bit and 64-bit alu ops. + * See alu32 verifier tests for examples. The second class of + * operations, BPF_LSH, BPF_RSH, and BPF_ARSH, however are not so easy + * with regards to tracking sign/unsigned bounds because the bits may + * cross subreg boundaries in the alu64 case. When this happens we mark + * the reg unbounded in the subreg bound space and use the resulting + * tnum to calculate an approximation of the sign/unsigned bounds. + */ switch (opcode) { case BPF_ADD: ret = sanitize_val_alu(env, insn); @@ -4899,22 +5673,8 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, verbose(env, "R%d tried to add from different pointers or scalars\n", dst); return ret; } - if (signed_add_overflows(dst_reg->smin_value, smin_val) || - signed_add_overflows(dst_reg->smax_value, smax_val)) { - dst_reg->smin_value = S64_MIN; - dst_reg->smax_value = S64_MAX; - } else { - dst_reg->smin_value += smin_val; - dst_reg->smax_value += smax_val; - } - if (dst_reg->umin_value + umin_val < umin_val || - dst_reg->umax_value + umax_val < umax_val) { - dst_reg->umin_value = 0; - dst_reg->umax_value = U64_MAX; - } else { - dst_reg->umin_value += umin_val; - dst_reg->umax_value += umax_val; - } + scalar32_min_max_add(dst_reg, &src_reg); + scalar_min_max_add(dst_reg, &src_reg); dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off); break; case BPF_SUB: @@ -4923,111 +5683,24 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, verbose(env, "R%d tried to sub from different pointers or scalars\n", dst); return ret; } - if (signed_sub_overflows(dst_reg->smin_value, smax_val) || - signed_sub_overflows(dst_reg->smax_value, smin_val)) { - /* Overflow possible, we know nothing */ - dst_reg->smin_value = S64_MIN; - dst_reg->smax_value = S64_MAX; - } else { - dst_reg->smin_value -= smax_val; - dst_reg->smax_value -= smin_val; - } - if (dst_reg->umin_value < umax_val) { - /* Overflow possible, we know nothing */ - dst_reg->umin_value = 0; - dst_reg->umax_value = U64_MAX; - } else { - /* Cannot overflow (as long as bounds are consistent) */ - dst_reg->umin_value -= umax_val; - dst_reg->umax_value -= umin_val; - } + scalar32_min_max_sub(dst_reg, &src_reg); + scalar_min_max_sub(dst_reg, &src_reg); dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off); break; case BPF_MUL: dst_reg->var_off = tnum_mul(dst_reg->var_off, src_reg.var_off); - if (smin_val < 0 || dst_reg->smin_value < 0) { - /* Ain't nobody got time to multiply that sign */ - __mark_reg_unbounded(dst_reg); - __update_reg_bounds(dst_reg); - break; - } - /* Both values are positive, so we can work with unsigned and - * copy the result to signed (unless it exceeds S64_MAX). - */ - if (umax_val > U32_MAX || dst_reg->umax_value > U32_MAX) { - /* Potential overflow, we know nothing */ - __mark_reg_unbounded(dst_reg); - /* (except what we can learn from the var_off) */ - __update_reg_bounds(dst_reg); - break; - } - dst_reg->umin_value *= umin_val; - dst_reg->umax_value *= umax_val; - if (dst_reg->umax_value > S64_MAX) { - /* Overflow possible, we know nothing */ - dst_reg->smin_value = S64_MIN; - dst_reg->smax_value = S64_MAX; - } else { - dst_reg->smin_value = dst_reg->umin_value; - dst_reg->smax_value = dst_reg->umax_value; - } + scalar32_min_max_mul(dst_reg, &src_reg); + scalar_min_max_mul(dst_reg, &src_reg); break; case BPF_AND: - if (src_known && dst_known) { - __mark_reg_known(dst_reg, dst_reg->var_off.value & - src_reg.var_off.value); - break; - } - /* We get our minimum from the var_off, since that's inherently - * bitwise. Our maximum is the minimum of the operands' maxima. - */ dst_reg->var_off = tnum_and(dst_reg->var_off, src_reg.var_off); - dst_reg->umin_value = dst_reg->var_off.value; - dst_reg->umax_value = min(dst_reg->umax_value, umax_val); - if (dst_reg->smin_value < 0 || smin_val < 0) { - /* Lose signed bounds when ANDing negative numbers, - * ain't nobody got time for that. - */ - dst_reg->smin_value = S64_MIN; - dst_reg->smax_value = S64_MAX; - } else { - /* ANDing two positives gives a positive, so safe to - * cast result into s64. - */ - dst_reg->smin_value = dst_reg->umin_value; - dst_reg->smax_value = dst_reg->umax_value; - } - /* We may learn something more from the var_off */ - __update_reg_bounds(dst_reg); + scalar32_min_max_and(dst_reg, &src_reg); + scalar_min_max_and(dst_reg, &src_reg); break; case BPF_OR: - if (src_known && dst_known) { - __mark_reg_known(dst_reg, dst_reg->var_off.value | - src_reg.var_off.value); - break; - } - /* We get our maximum from the var_off, and our minimum is the - * maximum of the operands' minima - */ dst_reg->var_off = tnum_or(dst_reg->var_off, src_reg.var_off); - dst_reg->umin_value = max(dst_reg->umin_value, umin_val); - dst_reg->umax_value = dst_reg->var_off.value | - dst_reg->var_off.mask; - if (dst_reg->smin_value < 0 || smin_val < 0) { - /* Lose signed bounds when ORing negative numbers, - * ain't nobody got time for that. - */ - dst_reg->smin_value = S64_MIN; - dst_reg->smax_value = S64_MAX; - } else { - /* ORing two positives gives a positive, so safe to - * cast result into s64. - */ - dst_reg->smin_value = dst_reg->umin_value; - dst_reg->smax_value = dst_reg->umax_value; - } - /* We may learn something more from the var_off */ - __update_reg_bounds(dst_reg); + scalar32_min_max_or(dst_reg, &src_reg); + scalar_min_max_or(dst_reg, &src_reg); break; case BPF_LSH: if (umax_val >= insn_bitness) { @@ -5037,22 +5710,10 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, mark_reg_unknown(env, regs, insn->dst_reg); break; } - /* We lose all sign bit information (except what we can pick - * up from var_off) - */ - dst_reg->smin_value = S64_MIN; - dst_reg->smax_value = S64_MAX; - /* If we might shift our top bit out, then we know nothing */ - if (dst_reg->umax_value > 1ULL << (63 - umax_val)) { - dst_reg->umin_value = 0; - dst_reg->umax_value = U64_MAX; - } else { - dst_reg->umin_value <<= umin_val; - dst_reg->umax_value <<= umax_val; - } - dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val); - /* We may learn something more from the var_off */ - __update_reg_bounds(dst_reg); + if (alu32) + scalar32_min_max_lsh(dst_reg, &src_reg); + else + scalar_min_max_lsh(dst_reg, &src_reg); break; case BPF_RSH: if (umax_val >= insn_bitness) { @@ -5062,27 +5723,10 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, mark_reg_unknown(env, regs, insn->dst_reg); break; } - /* BPF_RSH is an unsigned shift. If the value in dst_reg might - * be negative, then either: - * 1) src_reg might be zero, so the sign bit of the result is - * unknown, so we lose our signed bounds - * 2) it's known negative, thus the unsigned bounds capture the - * signed bounds - * 3) the signed bounds cross zero, so they tell us nothing - * about the result - * If the value in dst_reg is known nonnegative, then again the - * unsigned bounts capture the signed bounds. - * Thus, in all cases it suffices to blow away our signed bounds - * and rely on inferring new ones from the unsigned bounds and - * var_off of the result. - */ - dst_reg->smin_value = S64_MIN; - dst_reg->smax_value = S64_MAX; - dst_reg->var_off = tnum_rshift(dst_reg->var_off, umin_val); - dst_reg->umin_value >>= umax_val; - dst_reg->umax_value >>= umin_val; - /* We may learn something more from the var_off */ - __update_reg_bounds(dst_reg); + if (alu32) + scalar32_min_max_rsh(dst_reg, &src_reg); + else + scalar_min_max_rsh(dst_reg, &src_reg); break; case BPF_ARSH: if (umax_val >= insn_bitness) { @@ -5092,38 +5736,21 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, mark_reg_unknown(env, regs, insn->dst_reg); break; } - - /* Upon reaching here, src_known is true and - * umax_val is equal to umin_val. - */ - if (insn_bitness == 32) { - dst_reg->smin_value = (u32)(((s32)dst_reg->smin_value) >> umin_val); - dst_reg->smax_value = (u32)(((s32)dst_reg->smax_value) >> umin_val); - } else { - dst_reg->smin_value >>= umin_val; - dst_reg->smax_value >>= umin_val; - } - - dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val, - insn_bitness); - - /* blow away the dst_reg umin_value/umax_value and rely on - * dst_reg var_off to refine the result. - */ - dst_reg->umin_value = 0; - dst_reg->umax_value = U64_MAX; - __update_reg_bounds(dst_reg); + if (alu32) + scalar32_min_max_arsh(dst_reg, &src_reg); + else + scalar_min_max_arsh(dst_reg, &src_reg); break; default: mark_reg_unknown(env, regs, insn->dst_reg); break; } - if (BPF_CLASS(insn->code) != BPF_ALU64) { - /* 32-bit ALU ops are (32,32)->32 */ - coerce_reg_to_size(dst_reg, 4); - } + /* ALU32 ops are zero extended into 64bit register */ + if (alu32) + zext_32_to_64(dst_reg); + __update_reg_bounds(dst_reg); __reg_deduce_bounds(dst_reg); __reg_bound_offset(dst_reg); return 0; @@ -5297,7 +5924,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) mark_reg_unknown(env, regs, insn->dst_reg); } - coerce_reg_to_size(dst_reg, 4); + zext_32_to_64(dst_reg); } } else { /* case: R = imm @@ -5467,55 +6094,83 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, new_range); } -/* compute branch direction of the expression "if (reg opcode val) goto target;" - * and return: - * 1 - branch will be taken and "goto target" will be executed - * 0 - branch will not be taken and fall-through to next insn - * -1 - unknown. Example: "if (reg < 5)" is unknown when register value range [0,10] - */ -static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode, - bool is_jmp32) +static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode) { - struct bpf_reg_state reg_lo; - s64 sval; + struct tnum subreg = tnum_subreg(reg->var_off); + s32 sval = (s32)val; - if (__is_pointer_value(false, reg)) - return -1; + switch (opcode) { + case BPF_JEQ: + if (tnum_is_const(subreg)) + return !!tnum_equals_const(subreg, val); + break; + case BPF_JNE: + if (tnum_is_const(subreg)) + return !tnum_equals_const(subreg, val); + break; + case BPF_JSET: + if ((~subreg.mask & subreg.value) & val) + return 1; + if (!((subreg.mask | subreg.value) & val)) + return 0; + break; + case BPF_JGT: + if (reg->u32_min_value > val) + return 1; + else if (reg->u32_max_value <= val) + return 0; + break; + case BPF_JSGT: + if (reg->s32_min_value > sval) + return 1; + else if (reg->s32_max_value < sval) + return 0; + break; + case BPF_JLT: + if (reg->u32_max_value < val) + return 1; + else if (reg->u32_min_value >= val) + return 0; + break; + case BPF_JSLT: + if (reg->s32_max_value < sval) + return 1; + else if (reg->s32_min_value >= sval) + return 0; + break; + case BPF_JGE: + if (reg->u32_min_value >= val) + return 1; + else if (reg->u32_max_value < val) + return 0; + break; + case BPF_JSGE: + if (reg->s32_min_value >= sval) + return 1; + else if (reg->s32_max_value < sval) + return 0; + break; + case BPF_JLE: + if (reg->u32_max_value <= val) + return 1; + else if (reg->u32_min_value > val) + return 0; + break; + case BPF_JSLE: + if (reg->s32_max_value <= sval) + return 1; + else if (reg->s32_min_value > sval) + return 0; + break; + } - if (is_jmp32) { - reg_lo = *reg; - reg = ®_lo; - /* For JMP32, only low 32 bits are compared, coerce_reg_to_size - * could truncate high bits and update umin/umax according to - * information of low bits. - */ - coerce_reg_to_size(reg, 4); - /* smin/smax need special handling. For example, after coerce, - * if smin_value is 0x00000000ffffffffLL, the value is -1 when - * used as operand to JMP32. It is a negative number from s32's - * point of view, while it is a positive number when seen as - * s64. The smin/smax are kept as s64, therefore, when used with - * JMP32, they need to be transformed into s32, then sign - * extended back to s64. - * - * Also, smin/smax were copied from umin/umax. If umin/umax has - * different sign bit, then min/max relationship doesn't - * maintain after casting into s32, for this case, set smin/smax - * to safest range. - */ - if ((reg->umax_value ^ reg->umin_value) & - (1ULL << 31)) { - reg->smin_value = S32_MIN; - reg->smax_value = S32_MAX; - } - reg->smin_value = (s64)(s32)reg->smin_value; - reg->smax_value = (s64)(s32)reg->smax_value; + return -1; +} - val = (u32)val; - sval = (s64)(s32)val; - } else { - sval = (s64)val; - } + +static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode) +{ + s64 sval = (s64)val; switch (opcode) { case BPF_JEQ: @@ -5585,27 +6240,22 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode, return -1; } -/* Generate min value of the high 32-bit from TNUM info. */ -static u64 gen_hi_min(struct tnum var) -{ - return var.value & ~0xffffffffULL; -} - -/* Generate max value of the high 32-bit from TNUM info. */ -static u64 gen_hi_max(struct tnum var) -{ - return (var.value | var.mask) & ~0xffffffffULL; -} - -/* Return true if VAL is compared with a s64 sign extended from s32, and they - * are with the same signedness. +/* compute branch direction of the expression "if (reg opcode val) goto target;" + * and return: + * 1 - branch will be taken and "goto target" will be executed + * 0 - branch will not be taken and fall-through to next insn + * -1 - unknown. Example: "if (reg < 5)" is unknown when register value + * range [0,10] */ -static bool cmp_val_with_extended_s64(s64 sval, struct bpf_reg_state *reg) +static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode, + bool is_jmp32) { - return ((s32)sval >= 0 && - reg->smin_value >= 0 && reg->smax_value <= S32_MAX) || - ((s32)sval < 0 && - reg->smax_value <= 0 && reg->smin_value >= S32_MIN); + if (__is_pointer_value(false, reg)) + return -1; + + if (is_jmp32) + return is_branch32_taken(reg, val, opcode); + return is_branch64_taken(reg, val, opcode); } /* Adjusts the register min/max values in the case that the dst_reg is the @@ -5614,10 +6264,16 @@ static bool cmp_val_with_extended_s64(s64 sval, struct bpf_reg_state *reg) * In JEQ/JNE cases we also adjust the var_off values. */ static void reg_set_min_max(struct bpf_reg_state *true_reg, - struct bpf_reg_state *false_reg, u64 val, + struct bpf_reg_state *false_reg, + u64 val, u32 val32, u8 opcode, bool is_jmp32) { - s64 sval; + struct tnum false_32off = tnum_subreg(false_reg->var_off); + struct tnum false_64off = false_reg->var_off; + struct tnum true_32off = tnum_subreg(true_reg->var_off); + struct tnum true_64off = true_reg->var_off; + s64 sval = (s64)val; + s32 sval32 = (s32)val32; /* If the dst_reg is a pointer, we can't learn anything about its * variable offset from the compare (unless src_reg were a pointer into @@ -5628,9 +6284,6 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg, if (__is_pointer_value(false, false_reg)) return; - val = is_jmp32 ? (u32)val : val; - sval = is_jmp32 ? (s64)(s32)val : (s64)val; - switch (opcode) { case BPF_JEQ: case BPF_JNE: @@ -5642,211 +6295,150 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg, * if it is true we know the value for sure. Likewise for * BPF_JNE. */ - if (is_jmp32) { - u64 old_v = reg->var_off.value; - u64 hi_mask = ~0xffffffffULL; - - reg->var_off.value = (old_v & hi_mask) | val; - reg->var_off.mask &= hi_mask; - } else { + if (is_jmp32) + __mark_reg32_known(reg, val32); + else __mark_reg_known(reg, val); - } break; } case BPF_JSET: - false_reg->var_off = tnum_and(false_reg->var_off, - tnum_const(~val)); - if (is_power_of_2(val)) - true_reg->var_off = tnum_or(true_reg->var_off, - tnum_const(val)); + if (is_jmp32) { + false_32off = tnum_and(false_32off, tnum_const(~val32)); + if (is_power_of_2(val32)) + true_32off = tnum_or(true_32off, + tnum_const(val32)); + } else { + false_64off = tnum_and(false_64off, tnum_const(~val)); + if (is_power_of_2(val)) + true_64off = tnum_or(true_64off, + tnum_const(val)); + } break; case BPF_JGE: case BPF_JGT: { - u64 false_umax = opcode == BPF_JGT ? val : val - 1; - u64 true_umin = opcode == BPF_JGT ? val + 1 : val; - if (is_jmp32) { - false_umax += gen_hi_max(false_reg->var_off); - true_umin += gen_hi_min(true_reg->var_off); + u32 false_umax = opcode == BPF_JGT ? val32 : val32 - 1; + u32 true_umin = opcode == BPF_JGT ? val32 + 1 : val32; + + false_reg->u32_max_value = min(false_reg->u32_max_value, + false_umax); + true_reg->u32_min_value = max(true_reg->u32_min_value, + true_umin); + } else { + u64 false_umax = opcode == BPF_JGT ? val : val - 1; + u64 true_umin = opcode == BPF_JGT ? val + 1 : val; + + false_reg->umax_value = min(false_reg->umax_value, false_umax); + true_reg->umin_value = max(true_reg->umin_value, true_umin); } - false_reg->umax_value = min(false_reg->umax_value, false_umax); - true_reg->umin_value = max(true_reg->umin_value, true_umin); break; } case BPF_JSGE: case BPF_JSGT: { - s64 false_smax = opcode == BPF_JSGT ? sval : sval - 1; - s64 true_smin = opcode == BPF_JSGT ? sval + 1 : sval; + if (is_jmp32) { + s32 false_smax = opcode == BPF_JSGT ? sval32 : sval32 - 1; + s32 true_smin = opcode == BPF_JSGT ? sval32 + 1 : sval32; - /* If the full s64 was not sign-extended from s32 then don't - * deduct further info. - */ - if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg)) - break; - false_reg->smax_value = min(false_reg->smax_value, false_smax); - true_reg->smin_value = max(true_reg->smin_value, true_smin); + false_reg->s32_max_value = min(false_reg->s32_max_value, false_smax); + true_reg->s32_min_value = max(true_reg->s32_min_value, true_smin); + } else { + s64 false_smax = opcode == BPF_JSGT ? sval : sval - 1; + s64 true_smin = opcode == BPF_JSGT ? sval + 1 : sval; + + false_reg->smax_value = min(false_reg->smax_value, false_smax); + true_reg->smin_value = max(true_reg->smin_value, true_smin); + } break; } case BPF_JLE: case BPF_JLT: { - u64 false_umin = opcode == BPF_JLT ? val : val + 1; - u64 true_umax = opcode == BPF_JLT ? val - 1 : val; - if (is_jmp32) { - false_umin += gen_hi_min(false_reg->var_off); - true_umax += gen_hi_max(true_reg->var_off); + u32 false_umin = opcode == BPF_JLT ? val32 : val32 + 1; + u32 true_umax = opcode == BPF_JLT ? val32 - 1 : val32; + + false_reg->u32_min_value = max(false_reg->u32_min_value, + false_umin); + true_reg->u32_max_value = min(true_reg->u32_max_value, + true_umax); + } else { + u64 false_umin = opcode == BPF_JLT ? val : val + 1; + u64 true_umax = opcode == BPF_JLT ? val - 1 : val; + + false_reg->umin_value = max(false_reg->umin_value, false_umin); + true_reg->umax_value = min(true_reg->umax_value, true_umax); } - false_reg->umin_value = max(false_reg->umin_value, false_umin); - true_reg->umax_value = min(true_reg->umax_value, true_umax); break; } case BPF_JSLE: case BPF_JSLT: { - s64 false_smin = opcode == BPF_JSLT ? sval : sval + 1; - s64 true_smax = opcode == BPF_JSLT ? sval - 1 : sval; + if (is_jmp32) { + s32 false_smin = opcode == BPF_JSLT ? sval32 : sval32 + 1; + s32 true_smax = opcode == BPF_JSLT ? sval32 - 1 : sval32; - if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg)) - break; - false_reg->smin_value = max(false_reg->smin_value, false_smin); - true_reg->smax_value = min(true_reg->smax_value, true_smax); + false_reg->s32_min_value = max(false_reg->s32_min_value, false_smin); + true_reg->s32_max_value = min(true_reg->s32_max_value, true_smax); + } else { + s64 false_smin = opcode == BPF_JSLT ? sval : sval + 1; + s64 true_smax = opcode == BPF_JSLT ? sval - 1 : sval; + + false_reg->smin_value = max(false_reg->smin_value, false_smin); + true_reg->smax_value = min(true_reg->smax_value, true_smax); + } break; } default: - break; + return; } - __reg_deduce_bounds(false_reg); - __reg_deduce_bounds(true_reg); - /* We might have learned some bits from the bounds. */ - __reg_bound_offset(false_reg); - __reg_bound_offset(true_reg); if (is_jmp32) { - __reg_bound_offset32(false_reg); - __reg_bound_offset32(true_reg); + false_reg->var_off = tnum_or(tnum_clear_subreg(false_64off), + tnum_subreg(false_32off)); + true_reg->var_off = tnum_or(tnum_clear_subreg(true_64off), + tnum_subreg(true_32off)); + __reg_combine_32_into_64(false_reg); + __reg_combine_32_into_64(true_reg); + } else { + false_reg->var_off = false_64off; + true_reg->var_off = true_64off; + __reg_combine_64_into_32(false_reg); + __reg_combine_64_into_32(true_reg); } - /* Intersecting with the old var_off might have improved our bounds - * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), - * then new var_off is (0; 0x7f...fc) which improves our umax. - */ - __update_reg_bounds(false_reg); - __update_reg_bounds(true_reg); } /* Same as above, but for the case that dst_reg holds a constant and src_reg is * the variable reg. */ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg, - struct bpf_reg_state *false_reg, u64 val, + struct bpf_reg_state *false_reg, + u64 val, u32 val32, u8 opcode, bool is_jmp32) { - s64 sval; - - if (__is_pointer_value(false, false_reg)) - return; - - val = is_jmp32 ? (u32)val : val; - sval = is_jmp32 ? (s64)(s32)val : (s64)val; - - switch (opcode) { - case BPF_JEQ: - case BPF_JNE: - { - struct bpf_reg_state *reg = - opcode == BPF_JEQ ? true_reg : false_reg; - - if (is_jmp32) { - u64 old_v = reg->var_off.value; - u64 hi_mask = ~0xffffffffULL; - - reg->var_off.value = (old_v & hi_mask) | val; - reg->var_off.mask &= hi_mask; - } else { - __mark_reg_known(reg, val); - } - break; - } - case BPF_JSET: - false_reg->var_off = tnum_and(false_reg->var_off, - tnum_const(~val)); - if (is_power_of_2(val)) - true_reg->var_off = tnum_or(true_reg->var_off, - tnum_const(val)); - break; - case BPF_JGE: - case BPF_JGT: - { - u64 false_umin = opcode == BPF_JGT ? val : val + 1; - u64 true_umax = opcode == BPF_JGT ? val - 1 : val; - - if (is_jmp32) { - false_umin += gen_hi_min(false_reg->var_off); - true_umax += gen_hi_max(true_reg->var_off); - } - false_reg->umin_value = max(false_reg->umin_value, false_umin); - true_reg->umax_value = min(true_reg->umax_value, true_umax); - break; - } - case BPF_JSGE: - case BPF_JSGT: - { - s64 false_smin = opcode == BPF_JSGT ? sval : sval + 1; - s64 true_smax = opcode == BPF_JSGT ? sval - 1 : sval; - - if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg)) - break; - false_reg->smin_value = max(false_reg->smin_value, false_smin); - true_reg->smax_value = min(true_reg->smax_value, true_smax); - break; - } - case BPF_JLE: - case BPF_JLT: - { - u64 false_umax = opcode == BPF_JLT ? val : val - 1; - u64 true_umin = opcode == BPF_JLT ? val + 1 : val; - - if (is_jmp32) { - false_umax += gen_hi_max(false_reg->var_off); - true_umin += gen_hi_min(true_reg->var_off); - } - false_reg->umax_value = min(false_reg->umax_value, false_umax); - true_reg->umin_value = max(true_reg->umin_value, true_umin); - break; - } - case BPF_JSLE: - case BPF_JSLT: - { - s64 false_smax = opcode == BPF_JSLT ? sval : sval - 1; - s64 true_smin = opcode == BPF_JSLT ? sval + 1 : sval; - - if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg)) - break; - false_reg->smax_value = min(false_reg->smax_value, false_smax); - true_reg->smin_value = max(true_reg->smin_value, true_smin); - break; - } - default: - break; - } - - __reg_deduce_bounds(false_reg); - __reg_deduce_bounds(true_reg); - /* We might have learned some bits from the bounds. */ - __reg_bound_offset(false_reg); - __reg_bound_offset(true_reg); - if (is_jmp32) { - __reg_bound_offset32(false_reg); - __reg_bound_offset32(true_reg); - } - /* Intersecting with the old var_off might have improved our bounds - * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), - * then new var_off is (0; 0x7f...fc) which improves our umax. + /* How can we transform "a <op> b" into "b <op> a"? */ + static const u8 opcode_flip[16] = { + /* these stay the same */ + [BPF_JEQ >> 4] = BPF_JEQ, + [BPF_JNE >> 4] = BPF_JNE, + [BPF_JSET >> 4] = BPF_JSET, + /* these swap "lesser" and "greater" (L and G in the opcodes) */ + [BPF_JGE >> 4] = BPF_JLE, + [BPF_JGT >> 4] = BPF_JLT, + [BPF_JLE >> 4] = BPF_JGE, + [BPF_JLT >> 4] = BPF_JGT, + [BPF_JSGE >> 4] = BPF_JSLE, + [BPF_JSGT >> 4] = BPF_JSLT, + [BPF_JSLE >> 4] = BPF_JSGE, + [BPF_JSLT >> 4] = BPF_JSGT + }; + opcode = opcode_flip[opcode >> 4]; + /* This uses zero as "not present in table"; luckily the zero opcode, + * BPF_JA, can't get here. */ - __update_reg_bounds(false_reg); - __update_reg_bounds(true_reg); + if (opcode) + reg_set_min_max(true_reg, false_reg, val, val32, opcode, is_jmp32); } /* Regs are known to be equal, so intersect their min/max/var_off */ @@ -6135,13 +6727,22 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, dst_reg = ®s[insn->dst_reg]; is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32; - if (BPF_SRC(insn->code) == BPF_K) - pred = is_branch_taken(dst_reg, insn->imm, - opcode, is_jmp32); - else if (src_reg->type == SCALAR_VALUE && - tnum_is_const(src_reg->var_off)) - pred = is_branch_taken(dst_reg, src_reg->var_off.value, - opcode, is_jmp32); + if (BPF_SRC(insn->code) == BPF_K) { + pred = is_branch_taken(dst_reg, insn->imm, opcode, is_jmp32); + } else if (src_reg->type == SCALAR_VALUE && + is_jmp32 && tnum_is_const(tnum_subreg(src_reg->var_off))) { + pred = is_branch_taken(dst_reg, + tnum_subreg(src_reg->var_off).value, + opcode, + is_jmp32); + } else if (src_reg->type == SCALAR_VALUE && + !is_jmp32 && tnum_is_const(src_reg->var_off)) { + pred = is_branch_taken(dst_reg, + src_reg->var_off.value, + opcode, + is_jmp32); + } + if (pred >= 0) { err = mark_chain_precision(env, insn->dst_reg); if (BPF_SRC(insn->code) == BPF_X && !err) @@ -6175,32 +6776,24 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, */ if (BPF_SRC(insn->code) == BPF_X) { struct bpf_reg_state *src_reg = ®s[insn->src_reg]; - struct bpf_reg_state lo_reg0 = *dst_reg; - struct bpf_reg_state lo_reg1 = *src_reg; - struct bpf_reg_state *src_lo, *dst_lo; - - dst_lo = &lo_reg0; - src_lo = &lo_reg1; - coerce_reg_to_size(dst_lo, 4); - coerce_reg_to_size(src_lo, 4); if (dst_reg->type == SCALAR_VALUE && src_reg->type == SCALAR_VALUE) { if (tnum_is_const(src_reg->var_off) || - (is_jmp32 && tnum_is_const(src_lo->var_off))) + (is_jmp32 && + tnum_is_const(tnum_subreg(src_reg->var_off)))) reg_set_min_max(&other_branch_regs[insn->dst_reg], dst_reg, - is_jmp32 - ? src_lo->var_off.value - : src_reg->var_off.value, + src_reg->var_off.value, + tnum_subreg(src_reg->var_off).value, opcode, is_jmp32); else if (tnum_is_const(dst_reg->var_off) || - (is_jmp32 && tnum_is_const(dst_lo->var_off))) + (is_jmp32 && + tnum_is_const(tnum_subreg(dst_reg->var_off)))) reg_set_min_max_inv(&other_branch_regs[insn->src_reg], src_reg, - is_jmp32 - ? dst_lo->var_off.value - : dst_reg->var_off.value, + dst_reg->var_off.value, + tnum_subreg(dst_reg->var_off).value, opcode, is_jmp32); else if (!is_jmp32 && (opcode == BPF_JEQ || opcode == BPF_JNE)) @@ -6211,7 +6804,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, } } else if (dst_reg->type == SCALAR_VALUE) { reg_set_min_max(&other_branch_regs[insn->dst_reg], - dst_reg, insn->imm, opcode, is_jmp32); + dst_reg, insn->imm, (u32)insn->imm, + opcode, is_jmp32); } /* detect if R == 0 where R is returned from bpf_map_lookup_elem(). @@ -6412,8 +7006,9 @@ static int check_return_code(struct bpf_verifier_env *env) struct tnum range = tnum_range(0, 1); int err; - /* The struct_ops func-ptr's return type could be "void" */ - if (env->prog->type == BPF_PROG_TYPE_STRUCT_OPS && + /* LSM and struct_ops func-ptr's return type could be "void" */ + if ((env->prog->type == BPF_PROG_TYPE_STRUCT_OPS || + env->prog->type == BPF_PROG_TYPE_LSM) && !prog->aux->attach_func_proto->type) return 0; @@ -9843,7 +10438,9 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) return check_struct_ops_btf_id(env); - if (prog->type != BPF_PROG_TYPE_TRACING && !prog_extension) + if (prog->type != BPF_PROG_TYPE_TRACING && + prog->type != BPF_PROG_TYPE_LSM && + !prog_extension) return 0; if (!btf_id) { @@ -9974,8 +10571,16 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) return -EINVAL; /* fallthrough */ case BPF_MODIFY_RETURN: + case BPF_LSM_MAC: case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: + prog->aux->attach_func_name = tname; + if (prog->type == BPF_PROG_TYPE_LSM) { + ret = bpf_lsm_verify_prog(&env->log, prog); + if (ret < 0) + return ret; + } + if (!btf_type_is_func(t)) { verbose(env, "attach_btf_id %u is not a function\n", btf_id); @@ -9990,7 +10595,6 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) tr = bpf_trampoline_lookup(key); if (!tr) return -ENOMEM; - prog->aux->attach_func_name = tname; /* t is either vmlinux type or another program's type */ prog->aux->attach_func_proto = t; mutex_lock(&tr->mutex); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 3dead0416b91..915dda3f7f19 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6303,27 +6303,58 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd) #endif /* CONFIG_SOCK_CGROUP_DATA */ #ifdef CONFIG_CGROUP_BPF -int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, - struct bpf_prog *replace_prog, enum bpf_attach_type type, +int cgroup_bpf_attach(struct cgroup *cgrp, + struct bpf_prog *prog, struct bpf_prog *replace_prog, + struct bpf_cgroup_link *link, + enum bpf_attach_type type, u32 flags) { int ret; mutex_lock(&cgroup_mutex); - ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, type, flags); + ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, link, type, flags); mutex_unlock(&cgroup_mutex); return ret; } + +int cgroup_bpf_replace(struct bpf_link *link, struct bpf_prog *old_prog, + struct bpf_prog *new_prog) +{ + struct bpf_cgroup_link *cg_link; + int ret; + + if (link->ops != &bpf_cgroup_link_lops) + return -EINVAL; + + cg_link = container_of(link, struct bpf_cgroup_link, link); + + mutex_lock(&cgroup_mutex); + /* link might have been auto-released by dying cgroup, so fail */ + if (!cg_link->cgroup) { + ret = -EINVAL; + goto out_unlock; + } + if (old_prog && link->prog != old_prog) { + ret = -EPERM; + goto out_unlock; + } + ret = __cgroup_bpf_replace(cg_link->cgroup, cg_link, new_prog); +out_unlock: + mutex_unlock(&cgroup_mutex); + return ret; +} + int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type, u32 flags) + enum bpf_attach_type type) { int ret; mutex_lock(&cgroup_mutex); - ret = __cgroup_bpf_detach(cgrp, prog, type); + ret = __cgroup_bpf_detach(cgrp, prog, NULL, type); mutex_unlock(&cgroup_mutex); return ret; } + int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, union bpf_attr __user *uattr) { diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 5d8d2365a373..ca1796747a77 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -779,8 +779,8 @@ static const struct bpf_func_proto bpf_send_signal_thread_proto = { .arg1_type = ARG_ANYTHING, }; -static const struct bpf_func_proto * -tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +const struct bpf_func_proto * +bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_map_lookup_elem: @@ -865,7 +865,7 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_override_return_proto; #endif default: - return tracing_func_proto(func_id, prog); + return bpf_tracing_func_proto(func_id, prog); } } @@ -975,7 +975,7 @@ tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_get_stack: return &bpf_get_stack_proto_tp; default: - return tracing_func_proto(func_id, prog); + return bpf_tracing_func_proto(func_id, prog); } } @@ -1082,7 +1082,7 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_read_branch_records: return &bpf_read_branch_records_proto; default: - return tracing_func_proto(func_id, prog); + return bpf_tracing_func_proto(func_id, prog); } } @@ -1210,7 +1210,7 @@ raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_get_stack: return &bpf_get_stack_proto_raw_tp; default: - return tracing_func_proto(func_id, prog); + return bpf_tracing_func_proto(func_id, prog); } } diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 4c921f5154e0..29dbdd4c29f6 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -114,6 +114,9 @@ out: * architecture dependent calling conventions. 7+ can be supported in the * future. */ +__diag_push(); +__diag_ignore(GCC, 8, "-Wmissing-prototypes", + "Global functions as their definitions will be in vmlinux BTF"); int noinline bpf_fentry_test1(int a) { return a + 1; @@ -149,6 +152,7 @@ int noinline bpf_modify_return_test(int a, int *b) *b += 1; return a + *b; } +__diag_pop(); ALLOW_ERROR_INJECTION(bpf_modify_return_test, ERRNO); diff --git a/net/core/dev.c b/net/core/dev.c index dee392f21466..9c9e763bfe0e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8655,15 +8655,17 @@ static void dev_xdp_uninstall(struct net_device *dev) * @dev: device * @extack: netlink extended ack * @fd: new program fd or negative value to clear + * @expected_fd: old program fd that userspace expects to replace or clear * @flags: xdp-related flags * * Set or clear a bpf program for a device */ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, - int fd, u32 flags) + int fd, int expected_fd, u32 flags) { const struct net_device_ops *ops = dev->netdev_ops; enum bpf_netdev_command query; + u32 prog_id, expected_id = 0; struct bpf_prog *prog = NULL; bpf_op_t bpf_op, bpf_chk; bool offload; @@ -8684,15 +8686,29 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, if (bpf_op == bpf_chk) bpf_chk = generic_xdp_install; - if (fd >= 0) { - u32 prog_id; + prog_id = __dev_xdp_query(dev, bpf_op, query); + if (flags & XDP_FLAGS_REPLACE) { + if (expected_fd >= 0) { + prog = bpf_prog_get_type_dev(expected_fd, + BPF_PROG_TYPE_XDP, + bpf_op == ops->ndo_bpf); + if (IS_ERR(prog)) + return PTR_ERR(prog); + expected_id = prog->aux->id; + bpf_prog_put(prog); + } + if (prog_id != expected_id) { + NL_SET_ERR_MSG(extack, "Active program does not match expected"); + return -EEXIST; + } + } + if (fd >= 0) { if (!offload && __dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG)) { NL_SET_ERR_MSG(extack, "native and generic XDP can't be active at the same time"); return -EEXIST; } - prog_id = __dev_xdp_query(dev, bpf_op, query); if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && prog_id) { NL_SET_ERR_MSG(extack, "XDP program already attached"); return -EBUSY; @@ -8715,7 +8731,7 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, return 0; } } else { - if (!__dev_xdp_query(dev, bpf_op, query)) + if (!prog_id) return 0; } diff --git a/net/core/filter.c b/net/core/filter.c index 96350a743539..7628b947dbc3 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2642,6 +2642,19 @@ static const struct bpf_func_proto bpf_msg_pop_data_proto = { .arg4_type = ARG_ANYTHING, }; +#ifdef CONFIG_CGROUP_NET_CLASSID +BPF_CALL_0(bpf_get_cgroup_classid_curr) +{ + return __task_get_classid(current); +} + +static const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto = { + .func = bpf_get_cgroup_classid_curr, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; +#endif + BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb) { return task_get_classid(skb); @@ -4117,6 +4130,18 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = { .arg1_type = ARG_PTR_TO_CTX, }; +BPF_CALL_1(bpf_get_socket_cookie_sock, struct sock *, ctx) +{ + return sock_gen_cookie(ctx); +} + +static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = { + .func = bpf_get_socket_cookie_sock, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + BPF_CALL_1(bpf_get_socket_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx) { return sock_gen_cookie(ctx->sk); @@ -4129,6 +4154,39 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = { .arg1_type = ARG_PTR_TO_CTX, }; +static u64 __bpf_get_netns_cookie(struct sock *sk) +{ +#ifdef CONFIG_NET_NS + return net_gen_cookie(sk ? sk->sk_net.net : &init_net); +#else + return 0; +#endif +} + +BPF_CALL_1(bpf_get_netns_cookie_sock, struct sock *, ctx) +{ + return __bpf_get_netns_cookie(ctx); +} + +static const struct bpf_func_proto bpf_get_netns_cookie_sock_proto = { + .func = bpf_get_netns_cookie_sock, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX_OR_NULL, +}; + +BPF_CALL_1(bpf_get_netns_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx) +{ + return __bpf_get_netns_cookie(ctx ? ctx->sk : NULL); +} + +static const struct bpf_func_proto bpf_get_netns_cookie_sock_addr_proto = { + .func = bpf_get_netns_cookie_sock_addr, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX_OR_NULL, +}; + BPF_CALL_1(bpf_get_socket_uid, struct sk_buff *, skb) { struct sock *sk = sk_to_full_sk(skb->sk); @@ -4147,8 +4205,8 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = { .arg1_type = ARG_PTR_TO_CTX, }; -BPF_CALL_5(bpf_sockopt_event_output, struct bpf_sock_ops_kern *, bpf_sock, - struct bpf_map *, map, u64, flags, void *, data, u64, size) +BPF_CALL_5(bpf_event_output_data, void *, ctx, struct bpf_map *, map, u64, flags, + void *, data, u64, size) { if (unlikely(flags & ~(BPF_F_INDEX_MASK))) return -EINVAL; @@ -4156,8 +4214,8 @@ BPF_CALL_5(bpf_sockopt_event_output, struct bpf_sock_ops_kern *, bpf_sock, return bpf_event_output(map, flags, data, size, NULL, 0, NULL); } -static const struct bpf_func_proto bpf_sockopt_event_output_proto = { - .func = bpf_sockopt_event_output, +static const struct bpf_func_proto bpf_event_output_data_proto = { + .func = bpf_event_output_data, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, @@ -5343,8 +5401,7 @@ static const struct bpf_func_proto bpf_sk_lookup_udp_proto = { BPF_CALL_1(bpf_sk_release, struct sock *, sk) { - /* Only full sockets have sk->sk_flags. */ - if (!sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE)) + if (sk_is_refcounted(sk)) sock_gen_put(sk); return 0; } @@ -5860,6 +5917,36 @@ static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = { .arg5_type = ARG_CONST_SIZE, }; +BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags) +{ + if (flags != 0) + return -EINVAL; + if (!skb_at_tc_ingress(skb)) + return -EOPNOTSUPP; + if (unlikely(dev_net(skb->dev) != sock_net(sk))) + return -ENETUNREACH; + if (unlikely(sk->sk_reuseport)) + return -ESOCKTNOSUPPORT; + if (sk_is_refcounted(sk) && + unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) + return -ENOENT; + + skb_orphan(skb); + skb->sk = sk; + skb->destructor = sock_pfree; + + return 0; +} + +static const struct bpf_func_proto bpf_sk_assign_proto = { + .func = bpf_sk_assign, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_SOCK_COMMON, + .arg3_type = ARG_ANYTHING, +}; + #endif /* CONFIG_INET */ bool bpf_helper_changes_pkt_data(void *func) @@ -5954,6 +6041,26 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_current_uid_gid_proto; case BPF_FUNC_get_local_storage: return &bpf_get_local_storage_proto; + case BPF_FUNC_get_socket_cookie: + return &bpf_get_socket_cookie_sock_proto; + case BPF_FUNC_get_netns_cookie: + return &bpf_get_netns_cookie_sock_proto; + case BPF_FUNC_perf_event_output: + return &bpf_event_output_data_proto; + case BPF_FUNC_get_current_pid_tgid: + return &bpf_get_current_pid_tgid_proto; + case BPF_FUNC_get_current_comm: + return &bpf_get_current_comm_proto; +#ifdef CONFIG_CGROUPS + case BPF_FUNC_get_current_cgroup_id: + return &bpf_get_current_cgroup_id_proto; + case BPF_FUNC_get_current_ancestor_cgroup_id: + return &bpf_get_current_ancestor_cgroup_id_proto; +#endif +#ifdef CONFIG_CGROUP_NET_CLASSID + case BPF_FUNC_get_cgroup_classid: + return &bpf_get_cgroup_classid_curr_proto; +#endif default: return bpf_base_func_proto(func_id); } @@ -5978,8 +6085,26 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) } case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_sock_addr_proto; + case BPF_FUNC_get_netns_cookie: + return &bpf_get_netns_cookie_sock_addr_proto; case BPF_FUNC_get_local_storage: return &bpf_get_local_storage_proto; + case BPF_FUNC_perf_event_output: + return &bpf_event_output_data_proto; + case BPF_FUNC_get_current_pid_tgid: + return &bpf_get_current_pid_tgid_proto; + case BPF_FUNC_get_current_comm: + return &bpf_get_current_comm_proto; +#ifdef CONFIG_CGROUPS + case BPF_FUNC_get_current_cgroup_id: + return &bpf_get_current_cgroup_id_proto; + case BPF_FUNC_get_current_ancestor_cgroup_id: + return &bpf_get_current_ancestor_cgroup_id_proto; +#endif +#ifdef CONFIG_CGROUP_NET_CLASSID + case BPF_FUNC_get_cgroup_classid: + return &bpf_get_cgroup_classid_curr_proto; +#endif #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_sock_addr_sk_lookup_tcp_proto; @@ -6153,6 +6278,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skb_ecn_set_ce_proto; case BPF_FUNC_tcp_gen_syncookie: return &bpf_tcp_gen_syncookie_proto; + case BPF_FUNC_sk_assign: + return &bpf_sk_assign_proto; #endif default: return bpf_base_func_proto(func_id); @@ -6222,7 +6349,7 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_get_local_storage: return &bpf_get_local_storage_proto; case BPF_FUNC_perf_event_output: - return &bpf_sockopt_event_output_proto; + return &bpf_event_output_data_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 757cc1d084e7..190ca66a383b 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -69,6 +69,20 @@ EXPORT_SYMBOL_GPL(pernet_ops_rwsem); static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS; +static atomic64_t cookie_gen; + +u64 net_gen_cookie(struct net *net) +{ + while (1) { + u64 res = atomic64_read(&net->net_cookie); + + if (res) + return res; + res = atomic64_inc_return(&cookie_gen); + atomic64_cmpxchg(&net->net_cookie, 0, res); + } +} + static struct net_generic *net_alloc_generic(void) { struct net_generic *ng; @@ -1087,6 +1101,7 @@ static int __init net_ns_init(void) panic("Could not allocate generic netns"); rcu_assign_pointer(init_net.gen, ng); + net_gen_cookie(&init_net); down_write(&pernet_ops_rwsem); if (setup_net(&init_net, &init_user_ns)) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 14e6ea21c378..709ebbf8ab5b 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1872,7 +1872,9 @@ static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { }; static const struct nla_policy ifla_xdp_policy[IFLA_XDP_MAX + 1] = { + [IFLA_XDP_UNSPEC] = { .strict_start_type = IFLA_XDP_EXPECTED_FD }, [IFLA_XDP_FD] = { .type = NLA_S32 }, + [IFLA_XDP_EXPECTED_FD] = { .type = NLA_S32 }, [IFLA_XDP_ATTACHED] = { .type = NLA_U8 }, [IFLA_XDP_FLAGS] = { .type = NLA_U32 }, [IFLA_XDP_PROG_ID] = { .type = NLA_U32 }, @@ -2799,8 +2801,20 @@ static int do_setlink(const struct sk_buff *skb, } if (xdp[IFLA_XDP_FD]) { + int expected_fd = -1; + + if (xdp_flags & XDP_FLAGS_REPLACE) { + if (!xdp[IFLA_XDP_EXPECTED_FD]) { + err = -EINVAL; + goto errout; + } + expected_fd = + nla_get_s32(xdp[IFLA_XDP_EXPECTED_FD]); + } + err = dev_change_xdp_fd(dev, extack, nla_get_s32(xdp[IFLA_XDP_FD]), + expected_fd, xdp_flags); if (err) goto errout; diff --git a/net/core/sock.c b/net/core/sock.c index 0fc8937a7ff4..da32d9b6d09f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2071,6 +2071,18 @@ void sock_efree(struct sk_buff *skb) } EXPORT_SYMBOL(sock_efree); +/* Buffer destructor for prefetch/receive path where reference count may + * not be held, e.g. for listen sockets. + */ +#ifdef CONFIG_INET +void sock_pfree(struct sk_buff *skb) +{ + if (sk_is_refcounted(skb->sk)) + sock_gen_put(skb->sk); +} +EXPORT_SYMBOL(sock_pfree); +#endif /* CONFIG_INET */ + kuid_t sock_i_uid(struct sock *sk) { kuid_t uid; diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 2bf3abeb1456..e3939f76b024 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -7,6 +7,7 @@ #include <linux/btf.h> #include <linux/filter.h> #include <net/tcp.h> +#include <net/bpf_sk_storage.h> static u32 optional_ops[] = { offsetof(struct tcp_congestion_ops, init), @@ -27,6 +28,27 @@ static u32 unsupported_ops[] = { static const struct btf_type *tcp_sock_type; static u32 tcp_sock_id, sock_id; +static int btf_sk_storage_get_ids[5]; +static struct bpf_func_proto btf_sk_storage_get_proto __read_mostly; + +static int btf_sk_storage_delete_ids[5]; +static struct bpf_func_proto btf_sk_storage_delete_proto __read_mostly; + +static void convert_sk_func_proto(struct bpf_func_proto *to, int *to_btf_ids, + const struct bpf_func_proto *from) +{ + int i; + + *to = *from; + to->btf_id = to_btf_ids; + for (i = 0; i < ARRAY_SIZE(to->arg_type); i++) { + if (to->arg_type[i] == ARG_PTR_TO_SOCKET) { + to->arg_type[i] = ARG_PTR_TO_BTF_ID; + to->btf_id[i] = tcp_sock_id; + } + } +} + static int bpf_tcp_ca_init(struct btf *btf) { s32 type_id; @@ -42,6 +64,13 @@ static int bpf_tcp_ca_init(struct btf *btf) tcp_sock_id = type_id; tcp_sock_type = btf_type_by_id(btf, tcp_sock_id); + convert_sk_func_proto(&btf_sk_storage_get_proto, + btf_sk_storage_get_ids, + &bpf_sk_storage_get_proto); + convert_sk_func_proto(&btf_sk_storage_delete_proto, + btf_sk_storage_delete_ids, + &bpf_sk_storage_delete_proto); + return 0; } @@ -167,6 +196,10 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, switch (func_id) { case BPF_FUNC_tcp_send_ack: return &bpf_tcp_send_ack_proto; + case BPF_FUNC_sk_storage_get: + return &btf_sk_storage_get_proto; + case BPF_FUNC_sk_storage_delete: + return &btf_sk_storage_delete_proto; default: return bpf_base_func_proto(func_id); } diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index aa438c6758a7..b0c244af1e4d 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -509,7 +509,8 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net) IPCB(skb)->iif = skb->skb_iif; /* Must drop socket now because of tproxy. */ - skb_orphan(skb); + if (!skb_sk_is_prefetched(skb)) + skb_orphan(skb); return skb; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index fe7b4fbc31c1..5a05327f97c1 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -10,38 +10,6 @@ #include <net/inet_common.h> #include <net/tls.h> -static bool tcp_bpf_stream_read(const struct sock *sk) -{ - struct sk_psock *psock; - bool empty = true; - - rcu_read_lock(); - psock = sk_psock(sk); - if (likely(psock)) - empty = list_empty(&psock->ingress_msg); - rcu_read_unlock(); - return !empty; -} - -static int tcp_bpf_wait_data(struct sock *sk, struct sk_psock *psock, - int flags, long timeo, int *err) -{ - DEFINE_WAIT_FUNC(wait, woken_wake_function); - int ret = 0; - - if (!timeo) - return ret; - - add_wait_queue(sk_sleep(sk), &wait); - sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); - ret = sk_wait_event(sk, &timeo, - !list_empty(&psock->ingress_msg) || - !skb_queue_empty(&sk->sk_receive_queue), &wait); - sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); - remove_wait_queue(sk_sleep(sk), &wait); - return ret; -} - int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags) { @@ -115,49 +83,6 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, } EXPORT_SYMBOL_GPL(__tcp_bpf_recvmsg); -int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, - int nonblock, int flags, int *addr_len) -{ - struct sk_psock *psock; - int copied, ret; - - psock = sk_psock_get(sk); - if (unlikely(!psock)) - return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); - if (unlikely(flags & MSG_ERRQUEUE)) - return inet_recv_error(sk, msg, len, addr_len); - if (!skb_queue_empty(&sk->sk_receive_queue) && - sk_psock_queue_empty(psock)) - return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); - lock_sock(sk); -msg_bytes_ready: - copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags); - if (!copied) { - int data, err = 0; - long timeo; - - timeo = sock_rcvtimeo(sk, nonblock); - data = tcp_bpf_wait_data(sk, psock, flags, timeo, &err); - if (data) { - if (!sk_psock_queue_empty(psock)) - goto msg_bytes_ready; - release_sock(sk); - sk_psock_put(sk, psock); - return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); - } - if (err) { - ret = err; - goto out; - } - copied = -EAGAIN; - } - ret = copied; -out: - release_sock(sk); - sk_psock_put(sk, psock); - return ret; -} - static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg, u32 apply_bytes, int flags) { @@ -298,6 +223,82 @@ int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, } EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir); +#ifdef CONFIG_BPF_STREAM_PARSER +static bool tcp_bpf_stream_read(const struct sock *sk) +{ + struct sk_psock *psock; + bool empty = true; + + rcu_read_lock(); + psock = sk_psock(sk); + if (likely(psock)) + empty = list_empty(&psock->ingress_msg); + rcu_read_unlock(); + return !empty; +} + +static int tcp_bpf_wait_data(struct sock *sk, struct sk_psock *psock, + int flags, long timeo, int *err) +{ + DEFINE_WAIT_FUNC(wait, woken_wake_function); + int ret = 0; + + if (!timeo) + return ret; + + add_wait_queue(sk_sleep(sk), &wait); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); + ret = sk_wait_event(sk, &timeo, + !list_empty(&psock->ingress_msg) || + !skb_queue_empty(&sk->sk_receive_queue), &wait); + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); + remove_wait_queue(sk_sleep(sk), &wait); + return ret; +} + +static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int nonblock, int flags, int *addr_len) +{ + struct sk_psock *psock; + int copied, ret; + + psock = sk_psock_get(sk); + if (unlikely(!psock)) + return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); + if (unlikely(flags & MSG_ERRQUEUE)) + return inet_recv_error(sk, msg, len, addr_len); + if (!skb_queue_empty(&sk->sk_receive_queue) && + sk_psock_queue_empty(psock)) + return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); + lock_sock(sk); +msg_bytes_ready: + copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags); + if (!copied) { + int data, err = 0; + long timeo; + + timeo = sock_rcvtimeo(sk, nonblock); + data = tcp_bpf_wait_data(sk, psock, flags, timeo, &err); + if (data) { + if (!sk_psock_queue_empty(psock)) + goto msg_bytes_ready; + release_sock(sk); + sk_psock_put(sk, psock); + return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); + } + if (err) { + ret = err; + goto out; + } + copied = -EAGAIN; + } + ret = copied; +out: + release_sock(sk); + sk_psock_put(sk, psock); + return ret; +} + static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg, int *copied, int flags) { @@ -528,7 +529,6 @@ out_err: return copied ? copied : err; } -#ifdef CONFIG_BPF_STREAM_PARSER enum { TCP_BPF_IPV4, TCP_BPF_IPV6, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 7ea90eb4a1ba..32564b350823 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2288,6 +2288,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, struct rtable *rt = skb_rtable(skb); __be32 saddr, daddr; struct net *net = dev_net(skb->dev); + bool refcounted; /* * Validate the packet. @@ -2313,7 +2314,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (udp4_csum_init(skb, uh, proto)) goto csum_error; - sk = skb_steal_sock(skb); + sk = skb_steal_sock(skb, &refcounted); if (sk) { struct dst_entry *dst = skb_dst(skb); int ret; @@ -2322,7 +2323,8 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, udp_sk_rx_dst_set(sk, dst); ret = udp_unicast_rcv_skb(sk, skb, uh); - sock_put(sk); + if (refcounted) + sock_put(sk); return ret; } diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 7b089d0ac8cd..e96304d8a4a7 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -285,7 +285,8 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev, rcu_read_unlock(); /* Must drop socket now because of tproxy. */ - skb_orphan(skb); + if (!skb_sk_is_prefetched(skb)) + skb_orphan(skb); return skb; err: diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 5dc439a391fe..7d4151747340 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -843,6 +843,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, struct net *net = dev_net(skb->dev); struct udphdr *uh; struct sock *sk; + bool refcounted; u32 ulen = 0; if (!pskb_may_pull(skb, sizeof(struct udphdr))) @@ -879,7 +880,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, goto csum_error; /* Check if the socket is already available, e.g. due to early demux */ - sk = skb_steal_sock(skb); + sk = skb_steal_sock(skb, &refcounted); if (sk) { struct dst_entry *dst = skb_dst(skb); int ret; @@ -888,12 +889,14 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, udp6_sk_rx_dst_set(sk, dst); if (!uh->check && !udp_sk(sk)->no_check6_rx) { - sock_put(sk); + if (refcounted) + sock_put(sk); goto report_csum_error; } ret = udp6_unicast_rcv_skb(sk, skb, uh); - sock_put(sk); + if (refcounted) + sock_put(sk); return ret; } diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 46f47e58b3be..54d5652cfe6c 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -12,6 +12,7 @@ #include <linux/bpf.h> #include <net/netlink.h> +#include <net/sock.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> @@ -53,6 +54,8 @@ static int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act, bpf_compute_data_pointers(skb); filter_res = BPF_PROG_RUN(filter, skb); } + if (skb_sk_is_prefetched(skb) && filter_res != TC_ACT_OK) + skb_orphan(skb); rcu_read_unlock(); /* A BPF program may overwrite the default action opcode. diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 79b0fee6943b..424f6fe7ce38 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -64,11 +64,11 @@ fds_example-objs := fds_example.o sockex1-objs := sockex1_user.o sockex2-objs := sockex2_user.o sockex3-objs := bpf_load.o sockex3_user.o -tracex1-objs := bpf_load.o tracex1_user.o +tracex1-objs := bpf_load.o tracex1_user.o $(TRACE_HELPERS) tracex2-objs := bpf_load.o tracex2_user.o tracex3-objs := bpf_load.o tracex3_user.o tracex4-objs := bpf_load.o tracex4_user.o -tracex5-objs := bpf_load.o tracex5_user.o +tracex5-objs := bpf_load.o tracex5_user.o $(TRACE_HELPERS) tracex6-objs := bpf_load.o tracex6_user.o tracex7-objs := bpf_load.o tracex7_user.o test_probe_write_user-objs := bpf_load.o test_probe_write_user_user.o @@ -88,8 +88,8 @@ xdp2-objs := xdp1_user.o xdp_router_ipv4-objs := xdp_router_ipv4_user.o test_current_task_under_cgroup-objs := bpf_load.o $(CGROUP_HELPERS) \ test_current_task_under_cgroup_user.o -trace_event-objs := bpf_load.o trace_event_user.o $(TRACE_HELPERS) -sampleip-objs := bpf_load.o sampleip_user.o $(TRACE_HELPERS) +trace_event-objs := trace_event_user.o $(TRACE_HELPERS) +sampleip-objs := sampleip_user.o $(TRACE_HELPERS) tc_l2_redirect-objs := bpf_load.o tc_l2_redirect_user.o lwt_len_hist-objs := bpf_load.o lwt_len_hist_user.o xdp_tx_iptunnel-objs := xdp_tx_iptunnel_user.o diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c index 4574b1939e49..c5ad528f046e 100644 --- a/samples/bpf/bpf_load.c +++ b/samples/bpf/bpf_load.c @@ -665,23 +665,3 @@ int load_bpf_file_fixup_map(const char *path, fixup_map_cb fixup_map) { return do_load_bpf_file(path, fixup_map); } - -void read_trace_pipe(void) -{ - int trace_fd; - - trace_fd = open(DEBUGFS "trace_pipe", O_RDONLY, 0); - if (trace_fd < 0) - return; - - while (1) { - static char buf[4096]; - ssize_t sz; - - sz = read(trace_fd, buf, sizeof(buf) - 1); - if (sz > 0) { - buf[sz] = 0; - puts(buf); - } - } -} diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h index 814894a12974..4fcd258c616f 100644 --- a/samples/bpf/bpf_load.h +++ b/samples/bpf/bpf_load.h @@ -53,6 +53,5 @@ extern int map_data_count; int load_bpf_file(char *path); int load_bpf_file_fixup_map(const char *path, fixup_map_cb fixup_map); -void read_trace_pipe(void); int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); #endif diff --git a/samples/bpf/sampleip_user.c b/samples/bpf/sampleip_user.c index b0f115f938bc..4372d2da2f9e 100644 --- a/samples/bpf/sampleip_user.c +++ b/samples/bpf/sampleip_user.c @@ -10,21 +10,23 @@ #include <errno.h> #include <signal.h> #include <string.h> -#include <assert.h> #include <linux/perf_event.h> #include <linux/ptrace.h> #include <linux/bpf.h> -#include <sys/ioctl.h> +#include <bpf/bpf.h> #include <bpf/libbpf.h> -#include "bpf_load.h" #include "perf-sys.h" #include "trace_helpers.h" +#define __must_check +#include <linux/err.h> + #define DEFAULT_FREQ 99 #define DEFAULT_SECS 5 #define MAX_IPS 8192 #define PAGE_OFFSET 0xffff880000000000 +static int map_fd; static int nr_cpus; static void usage(void) @@ -34,9 +36,10 @@ static void usage(void) printf(" duration # sampling duration (seconds), default 5\n"); } -static int sampling_start(int *pmu_fd, int freq) +static int sampling_start(int freq, struct bpf_program *prog, + struct bpf_link *links[]) { - int i; + int i, pmu_fd; struct perf_event_attr pe_sample_attr = { .type = PERF_TYPE_SOFTWARE, @@ -47,26 +50,30 @@ static int sampling_start(int *pmu_fd, int freq) }; for (i = 0; i < nr_cpus; i++) { - pmu_fd[i] = sys_perf_event_open(&pe_sample_attr, -1 /* pid */, i, + pmu_fd = sys_perf_event_open(&pe_sample_attr, -1 /* pid */, i, -1 /* group_fd */, 0 /* flags */); - if (pmu_fd[i] < 0) { + if (pmu_fd < 0) { fprintf(stderr, "ERROR: Initializing perf sampling\n"); return 1; } - assert(ioctl(pmu_fd[i], PERF_EVENT_IOC_SET_BPF, - prog_fd[0]) == 0); - assert(ioctl(pmu_fd[i], PERF_EVENT_IOC_ENABLE, 0) == 0); + links[i] = bpf_program__attach_perf_event(prog, pmu_fd); + if (IS_ERR(links[i])) { + fprintf(stderr, "ERROR: Attach perf event\n"); + links[i] = NULL; + close(pmu_fd); + return 1; + } } return 0; } -static void sampling_end(int *pmu_fd) +static void sampling_end(struct bpf_link *links[]) { int i; for (i = 0; i < nr_cpus; i++) - close(pmu_fd[i]); + bpf_link__destroy(links[i]); } struct ipcount { @@ -128,14 +135,17 @@ static void print_ip_map(int fd) static void int_exit(int sig) { printf("\n"); - print_ip_map(map_fd[0]); + print_ip_map(map_fd); exit(0); } int main(int argc, char **argv) { + int opt, freq = DEFAULT_FREQ, secs = DEFAULT_SECS, error = 1; + struct bpf_object *obj = NULL; + struct bpf_program *prog; + struct bpf_link **links; char filename[256]; - int *pmu_fd, opt, freq = DEFAULT_FREQ, secs = DEFAULT_SECS; /* process arguments */ while ((opt = getopt(argc, argv, "F:h")) != -1) { @@ -163,38 +173,58 @@ int main(int argc, char **argv) } /* create perf FDs for each CPU */ - nr_cpus = sysconf(_SC_NPROCESSORS_CONF); - pmu_fd = malloc(nr_cpus * sizeof(int)); - if (pmu_fd == NULL) { - fprintf(stderr, "ERROR: malloc of pmu_fd\n"); - return 1; + nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); + links = calloc(nr_cpus, sizeof(struct bpf_link *)); + if (!links) { + fprintf(stderr, "ERROR: malloc of links\n"); + goto cleanup; } - /* load BPF program */ snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - if (load_bpf_file(filename)) { - fprintf(stderr, "ERROR: loading BPF program (errno %d):\n", - errno); - if (strcmp(bpf_log_buf, "") == 0) - fprintf(stderr, "Try: ulimit -l unlimited\n"); - else - fprintf(stderr, "%s", bpf_log_buf); - return 1; + obj = bpf_object__open_file(filename, NULL); + if (IS_ERR(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + obj = NULL; + goto cleanup; + } + + prog = bpf_object__find_program_by_name(obj, "do_sample"); + if (!prog) { + fprintf(stderr, "ERROR: finding a prog in obj file failed\n"); + goto cleanup; } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd = bpf_object__find_map_fd_by_name(obj, "ip_map"); + if (map_fd < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + signal(SIGINT, int_exit); signal(SIGTERM, int_exit); /* do sampling */ printf("Sampling at %d Hertz for %d seconds. Ctrl-C also ends.\n", freq, secs); - if (sampling_start(pmu_fd, freq) != 0) - return 1; + if (sampling_start(freq, prog, links) != 0) + goto cleanup; + sleep(secs); - sampling_end(pmu_fd); - free(pmu_fd); + error = 0; +cleanup: + sampling_end(links); /* output sample counts */ - print_ip_map(map_fd[0]); + if (!error) + print_ip_map(map_fd); - return 0; + free(links); + bpf_object__close(obj); + return error; } diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c index 356171bc392b..b6cd358d0418 100644 --- a/samples/bpf/trace_event_user.c +++ b/samples/bpf/trace_event_user.c @@ -6,22 +6,25 @@ #include <stdlib.h> #include <stdbool.h> #include <string.h> -#include <fcntl.h> -#include <poll.h> -#include <sys/ioctl.h> #include <linux/perf_event.h> #include <linux/bpf.h> #include <signal.h> -#include <assert.h> #include <errno.h> #include <sys/resource.h> +#include <bpf/bpf.h> #include <bpf/libbpf.h> -#include "bpf_load.h" #include "perf-sys.h" #include "trace_helpers.h" +#define __must_check +#include <linux/err.h> + #define SAMPLE_FREQ 50 +static int pid; +/* counts, stackmap */ +static int map_fd[2]; +struct bpf_program *prog; static bool sys_read_seen, sys_write_seen; static void print_ksym(__u64 addr) @@ -91,10 +94,10 @@ static void print_stack(struct key_t *key, __u64 count) } } -static void int_exit(int sig) +static void err_exit(int err) { - kill(0, SIGKILL); - exit(0); + kill(pid, SIGKILL); + exit(err); } static void print_stacks(void) @@ -102,7 +105,7 @@ static void print_stacks(void) struct key_t key = {}, next_key; __u64 value; __u32 stackid = 0, next_id; - int fd = map_fd[0], stack_map = map_fd[1]; + int error = 1, fd = map_fd[0], stack_map = map_fd[1]; sys_read_seen = sys_write_seen = false; while (bpf_map_get_next_key(fd, &key, &next_key) == 0) { @@ -114,7 +117,7 @@ static void print_stacks(void) printf("\n"); if (!sys_read_seen || !sys_write_seen) { printf("BUG kernel stack doesn't contain sys_read() and sys_write()\n"); - int_exit(0); + err_exit(error); } /* clear stack map */ @@ -136,43 +139,52 @@ static inline int generate_load(void) static void test_perf_event_all_cpu(struct perf_event_attr *attr) { - int nr_cpus = sysconf(_SC_NPROCESSORS_CONF); - int *pmu_fd = malloc(nr_cpus * sizeof(int)); - int i, error = 0; + int nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); + struct bpf_link **links = calloc(nr_cpus, sizeof(struct bpf_link *)); + int i, pmu_fd, error = 1; + + if (!links) { + printf("malloc of links failed\n"); + goto err; + } /* system wide perf event, no need to inherit */ attr->inherit = 0; /* open perf_event on all cpus */ for (i = 0; i < nr_cpus; i++) { - pmu_fd[i] = sys_perf_event_open(attr, -1, i, -1, 0); - if (pmu_fd[i] < 0) { + pmu_fd = sys_perf_event_open(attr, -1, i, -1, 0); + if (pmu_fd < 0) { printf("sys_perf_event_open failed\n"); - error = 1; goto all_cpu_err; } - assert(ioctl(pmu_fd[i], PERF_EVENT_IOC_SET_BPF, prog_fd[0]) == 0); - assert(ioctl(pmu_fd[i], PERF_EVENT_IOC_ENABLE) == 0); + links[i] = bpf_program__attach_perf_event(prog, pmu_fd); + if (IS_ERR(links[i])) { + printf("bpf_program__attach_perf_event failed\n"); + links[i] = NULL; + close(pmu_fd); + goto all_cpu_err; + } } - if (generate_load() < 0) { - error = 1; + if (generate_load() < 0) goto all_cpu_err; - } + print_stacks(); + error = 0; all_cpu_err: - for (i--; i >= 0; i--) { - ioctl(pmu_fd[i], PERF_EVENT_IOC_DISABLE); - close(pmu_fd[i]); - } - free(pmu_fd); + for (i--; i >= 0; i--) + bpf_link__destroy(links[i]); +err: + free(links); if (error) - int_exit(0); + err_exit(error); } static void test_perf_event_task(struct perf_event_attr *attr) { - int pmu_fd, error = 0; + struct bpf_link *link = NULL; + int pmu_fd, error = 1; /* per task perf event, enable inherit so the "dd ..." command can be traced properly. * Enabling inherit will cause bpf_perf_prog_read_time helper failure. @@ -183,21 +195,25 @@ static void test_perf_event_task(struct perf_event_attr *attr) pmu_fd = sys_perf_event_open(attr, 0, -1, -1, 0); if (pmu_fd < 0) { printf("sys_perf_event_open failed\n"); - int_exit(0); + goto err; } - assert(ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd[0]) == 0); - assert(ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE) == 0); - - if (generate_load() < 0) { - error = 1; + link = bpf_program__attach_perf_event(prog, pmu_fd); + if (IS_ERR(link)) { + printf("bpf_program__attach_perf_event failed\n"); + link = NULL; + close(pmu_fd); goto err; } + + if (generate_load() < 0) + goto err; + print_stacks(); + error = 0; err: - ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE); - close(pmu_fd); + bpf_link__destroy(link); if (error) - int_exit(0); + err_exit(error); } static void test_bpf_perf_event(void) @@ -282,29 +298,60 @@ static void test_bpf_perf_event(void) int main(int argc, char **argv) { struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_object *obj = NULL; char filename[256]; + int error = 1; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); setrlimit(RLIMIT_MEMLOCK, &r); - signal(SIGINT, int_exit); - signal(SIGTERM, int_exit); + signal(SIGINT, err_exit); + signal(SIGTERM, err_exit); if (load_kallsyms()) { printf("failed to process /proc/kallsyms\n"); - return 1; + goto cleanup; + } + + obj = bpf_object__open_file(filename, NULL); + if (IS_ERR(obj)) { + printf("opening BPF object file failed\n"); + obj = NULL; + goto cleanup; + } + + prog = bpf_object__find_program_by_name(obj, "bpf_prog1"); + if (!prog) { + printf("finding a prog in obj file failed\n"); + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + printf("loading BPF object file failed\n"); + goto cleanup; } - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 2; + map_fd[0] = bpf_object__find_map_fd_by_name(obj, "counts"); + map_fd[1] = bpf_object__find_map_fd_by_name(obj, "stackmap"); + if (map_fd[0] < 0 || map_fd[1] < 0) { + printf("finding a counts/stackmap map in obj file failed\n"); + goto cleanup; } - if (fork() == 0) { + pid = fork(); + if (pid == 0) { read_trace_pipe(); return 0; + } else if (pid == -1) { + printf("couldn't spawn process\n"); + goto cleanup; } + test_bpf_perf_event(); - int_exit(0); - return 0; + error = 0; + +cleanup: + bpf_object__close(obj); + err_exit(error); } diff --git a/samples/bpf/tracex1_user.c b/samples/bpf/tracex1_user.c index af8c20608ab5..55fddbd08702 100644 --- a/samples/bpf/tracex1_user.c +++ b/samples/bpf/tracex1_user.c @@ -4,6 +4,7 @@ #include <unistd.h> #include <bpf/bpf.h> #include "bpf_load.h" +#include "trace_helpers.h" int main(int ac, char **argv) { diff --git a/samples/bpf/tracex5_user.c b/samples/bpf/tracex5_user.c index c4ab91c89494..c2317b39e0d2 100644 --- a/samples/bpf/tracex5_user.c +++ b/samples/bpf/tracex5_user.c @@ -8,6 +8,7 @@ #include <bpf/bpf.h> #include "bpf_load.h" #include <sys/resource.h> +#include "trace_helpers.h" /* install fake seccomp program to enable seccomp code path inside the kernel, * so that our kprobe attached to seccomp_phase1() can be triggered diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index ac569e197bfa..d09ab4afbda4 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -113,9 +113,6 @@ vmlinux_link() gen_btf() { local pahole_ver - local bin_arch - local bin_format - local bin_file if ! [ -x "$(command -v ${PAHOLE})" ]; then echo >&2 "BTF: ${1}: pahole (${PAHOLE}) is not available" @@ -133,17 +130,16 @@ gen_btf() info "BTF" ${2} LLVM_OBJCOPY=${OBJCOPY} ${PAHOLE} -J ${1} - # dump .BTF section into raw binary file to link with final vmlinux - bin_arch=$(LANG=C ${OBJDUMP} -f ${1} | grep architecture | \ - cut -d, -f1 | cut -d' ' -f2) - bin_format=$(LANG=C ${OBJDUMP} -f ${1} | grep 'file format' | \ - awk '{print $4}') - bin_file=.btf.vmlinux.bin - ${OBJCOPY} --change-section-address .BTF=0 \ - --set-section-flags .BTF=alloc -O binary \ - --only-section=.BTF ${1} $bin_file - ${OBJCOPY} -I binary -O ${bin_format} -B ${bin_arch} \ - --rename-section .data=.BTF $bin_file ${2} + # Create ${2} which contains just .BTF section but no symbols. Add + # SHF_ALLOC because .BTF will be part of the vmlinux image. --strip-all + # deletes all symbols including __start_BTF and __stop_BTF, which will + # be redefined in the linker script. Add 2>/dev/null to suppress GNU + # objcopy warnings: "empty loadable segment detected at ..." + ${OBJCOPY} --only-section=.BTF --set-section-flags .BTF=alloc,readonly \ + --strip-all ${1} ${2} 2>/dev/null + # Change e_type to ET_REL so that it can be used to link final vmlinux. + # Unlike GNU ld, lld does not allow an ET_EXEC input. + printf '\1' | dd of=${2} conv=notrunc bs=1 seek=16 status=none } # Create ${2} .o file with all symbols from the ${1} object file diff --git a/security/Kconfig b/security/Kconfig index 2a1a2d396228..cd3cc7da3a55 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -277,11 +277,11 @@ endchoice config LSM string "Ordered list of enabled LSMs" - default "lockdown,yama,loadpin,safesetid,integrity,smack,selinux,tomoyo,apparmor" if DEFAULT_SECURITY_SMACK - default "lockdown,yama,loadpin,safesetid,integrity,apparmor,selinux,smack,tomoyo" if DEFAULT_SECURITY_APPARMOR - default "lockdown,yama,loadpin,safesetid,integrity,tomoyo" if DEFAULT_SECURITY_TOMOYO - default "lockdown,yama,loadpin,safesetid,integrity" if DEFAULT_SECURITY_DAC - default "lockdown,yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" + default "lockdown,yama,loadpin,safesetid,integrity,smack,selinux,tomoyo,apparmor,bpf" if DEFAULT_SECURITY_SMACK + default "lockdown,yama,loadpin,safesetid,integrity,apparmor,selinux,smack,tomoyo,bpf" if DEFAULT_SECURITY_APPARMOR + default "lockdown,yama,loadpin,safesetid,integrity,tomoyo,bpf" if DEFAULT_SECURITY_TOMOYO + default "lockdown,yama,loadpin,safesetid,integrity,bpf" if DEFAULT_SECURITY_DAC + default "lockdown,yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor,bpf" help A comma-separated list of LSMs, in initialization order. Any LSMs left off this list will be ignored. This can be diff --git a/security/Makefile b/security/Makefile index 746438499029..22e73a3482bd 100644 --- a/security/Makefile +++ b/security/Makefile @@ -12,6 +12,7 @@ subdir-$(CONFIG_SECURITY_YAMA) += yama subdir-$(CONFIG_SECURITY_LOADPIN) += loadpin subdir-$(CONFIG_SECURITY_SAFESETID) += safesetid subdir-$(CONFIG_SECURITY_LOCKDOWN_LSM) += lockdown +subdir-$(CONFIG_BPF_LSM) += bpf # always enable default capabilities obj-y += commoncap.o @@ -30,6 +31,7 @@ obj-$(CONFIG_SECURITY_LOADPIN) += loadpin/ obj-$(CONFIG_SECURITY_SAFESETID) += safesetid/ obj-$(CONFIG_SECURITY_LOCKDOWN_LSM) += lockdown/ obj-$(CONFIG_CGROUP_DEVICE) += device_cgroup.o +obj-$(CONFIG_BPF_LSM) += bpf/ # Object integrity file lists subdir-$(CONFIG_INTEGRITY) += integrity diff --git a/security/bpf/Makefile b/security/bpf/Makefile new file mode 100644 index 000000000000..c7a89a962084 --- /dev/null +++ b/security/bpf/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (C) 2020 Google LLC. + +obj-$(CONFIG_BPF_LSM) := hooks.o diff --git a/security/bpf/hooks.c b/security/bpf/hooks.c new file mode 100644 index 000000000000..32d32d485451 --- /dev/null +++ b/security/bpf/hooks.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (C) 2020 Google LLC. + */ +#include <linux/lsm_hooks.h> +#include <linux/bpf_lsm.h> + +static struct security_hook_list bpf_lsm_hooks[] __lsm_ro_after_init = { + #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ + LSM_HOOK_INIT(NAME, bpf_lsm_##NAME), + #include <linux/lsm_hook_defs.h> + #undef LSM_HOOK +}; + +static int __init bpf_lsm_init(void) +{ + security_add_hooks(bpf_lsm_hooks, ARRAY_SIZE(bpf_lsm_hooks), "bpf"); + pr_info("LSM support for eBPF active\n"); + return 0; +} + +DEFINE_LSM(bpf) = { + .name = "bpf", + .init = bpf_lsm_init, +}; diff --git a/security/security.c b/security/security.c index 565bc9b67276..7fed24b9d57e 100644 --- a/security/security.c +++ b/security/security.c @@ -669,6 +669,25 @@ static void __init lsm_early_task(struct task_struct *task) } /* + * The default value of the LSM hook is defined in linux/lsm_hook_defs.h and + * can be accessed with: + * + * LSM_RET_DEFAULT(<hook_name>) + * + * The macros below define static constants for the default value of each + * LSM hook. + */ +#define LSM_RET_DEFAULT(NAME) (NAME##_default) +#define DECLARE_LSM_RET_DEFAULT_void(DEFAULT, NAME) +#define DECLARE_LSM_RET_DEFAULT_int(DEFAULT, NAME) \ + static const int LSM_RET_DEFAULT(NAME) = (DEFAULT); +#define LSM_HOOK(RET, DEFAULT, NAME, ...) \ + DECLARE_LSM_RET_DEFAULT_##RET(DEFAULT, NAME) + +#include <linux/lsm_hook_defs.h> +#undef LSM_HOOK + +/* * Hook list operation macros. * * call_void_hook: @@ -1338,16 +1357,16 @@ int security_inode_getsecurity(struct inode *inode, const char *name, void **buf int rc; if (unlikely(IS_PRIVATE(inode))) - return -EOPNOTSUPP; + return LSM_RET_DEFAULT(inode_getsecurity); /* * Only one module will provide an attribute with a given name. */ hlist_for_each_entry(hp, &security_hook_heads.inode_getsecurity, list) { rc = hp->hook.inode_getsecurity(inode, name, buffer, alloc); - if (rc != -EOPNOTSUPP) + if (rc != LSM_RET_DEFAULT(inode_getsecurity)) return rc; } - return -EOPNOTSUPP; + return LSM_RET_DEFAULT(inode_getsecurity); } int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) @@ -1356,17 +1375,17 @@ int security_inode_setsecurity(struct inode *inode, const char *name, const void int rc; if (unlikely(IS_PRIVATE(inode))) - return -EOPNOTSUPP; + return LSM_RET_DEFAULT(inode_setsecurity); /* * Only one module will provide an attribute with a given name. */ hlist_for_each_entry(hp, &security_hook_heads.inode_setsecurity, list) { rc = hp->hook.inode_setsecurity(inode, name, value, size, flags); - if (rc != -EOPNOTSUPP) + if (rc != LSM_RET_DEFAULT(inode_setsecurity)) return rc; } - return -EOPNOTSUPP; + return LSM_RET_DEFAULT(inode_setsecurity); } int security_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size) @@ -1740,12 +1759,12 @@ int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { int thisrc; - int rc = -ENOSYS; + int rc = LSM_RET_DEFAULT(task_prctl); struct security_hook_list *hp; hlist_for_each_entry(hp, &security_hook_heads.task_prctl, list) { thisrc = hp->hook.task_prctl(option, arg2, arg3, arg4, arg5); - if (thisrc != -ENOSYS) { + if (thisrc != LSM_RET_DEFAULT(task_prctl)) { rc = thisrc; if (thisrc != 0) break; @@ -1917,7 +1936,7 @@ int security_getprocattr(struct task_struct *p, const char *lsm, char *name, continue; return hp->hook.getprocattr(p, name, value); } - return -EINVAL; + return LSM_RET_DEFAULT(getprocattr); } int security_setprocattr(const char *lsm, const char *name, void *value, @@ -1930,7 +1949,7 @@ int security_setprocattr(const char *lsm, const char *name, void *value, continue; return hp->hook.setprocattr(name, value, size); } - return -EINVAL; + return LSM_RET_DEFAULT(setprocattr); } int security_netlink_send(struct sock *sk, struct sk_buff *skb) @@ -2315,7 +2334,7 @@ int security_xfrm_state_pol_flow_match(struct xfrm_state *x, const struct flowi *fl) { struct security_hook_list *hp; - int rc = 1; + int rc = LSM_RET_DEFAULT(xfrm_state_pol_flow_match); /* * Since this function is expected to return 0 or 1, the judgment diff --git a/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst b/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst new file mode 100644 index 000000000000..f045cc89dd6d --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst @@ -0,0 +1,116 @@ +================== +bpftool-struct_ops +================== +------------------------------------------------------------------------------- +tool to register/unregister/introspect BPF struct_ops +------------------------------------------------------------------------------- + +:Manual section: 8 + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **struct_ops** *COMMAND* + + *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] } + + *COMMANDS* := + { **show** | **list** | **dump** | **register** | **unregister** | **help** } + +STRUCT_OPS COMMANDS +=================== + +| **bpftool** **struct_ops { show | list }** [*STRUCT_OPS_MAP*] +| **bpftool** **struct_ops dump** [*STRUCT_OPS_MAP*] +| **bpftool** **struct_ops register** *OBJ* +| **bpftool** **struct_ops unregister** *STRUCT_OPS_MAP* +| **bpftool** **struct_ops help** +| +| *STRUCT_OPS_MAP* := { **id** *STRUCT_OPS_MAP_ID* | **name** *STRUCT_OPS_MAP_NAME* } +| *OBJ* := /a/file/of/bpf_struct_ops.o + + +DESCRIPTION +=========== + **bpftool struct_ops { show | list }** [*STRUCT_OPS_MAP*] + Show brief information about the struct_ops in the system. + If *STRUCT_OPS_MAP* is specified, it shows information only + for the given struct_ops. Otherwise, it lists all struct_ops + currently existing in the system. + + Output will start with struct_ops map ID, followed by its map + name and its struct_ops's kernel type. + + **bpftool struct_ops dump** [*STRUCT_OPS_MAP*] + Dump details information about the struct_ops in the system. + If *STRUCT_OPS_MAP* is specified, it dumps information only + for the given struct_ops. Otherwise, it dumps all struct_ops + currently existing in the system. + + **bpftool struct_ops register** *OBJ* + Register bpf struct_ops from *OBJ*. All struct_ops under + the ELF section ".struct_ops" will be registered to + its kernel subsystem. + + **bpftool struct_ops unregister** *STRUCT_OPS_MAP* + Unregister the *STRUCT_OPS_MAP* from the kernel subsystem. + + **bpftool struct_ops help** + Print short help message. + +OPTIONS +======= + -h, --help + Print short generic help message (similar to **bpftool help**). + + -V, --version + Print version number (similar to **bpftool version**). + + -j, --json + Generate JSON output. For commands that cannot produce JSON, this + option has no effect. + + -p, --pretty + Generate human-readable JSON output. Implies **-j**. + + -d, --debug + Print all logs available, even debug-level information. This + includes logs from libbpf as well as from the verifier, when + attempting to load programs. + +EXAMPLES +======== +**# bpftool struct_ops show** + +:: + + 100: dctcp tcp_congestion_ops + 105: cubic tcp_congestion_ops + +**# bpftool struct_ops unregister id 105** + +:: + + Unregistered tcp_congestion_ops cubic id 105 + +**# bpftool struct_ops register bpf_cubic.o** + +:: + + Registered tcp_congestion_ops cubic id 110 + + +SEE ALSO +======== + **bpf**\ (2), + **bpf-helpers**\ (7), + **bpftool**\ (8), + **bpftool-prog**\ (8), + **bpftool-map**\ (8), + **bpftool-cgroup**\ (8), + **bpftool-feature**\ (8), + **bpftool-net**\ (8), + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) + **bpftool-gen**\ (8) + diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 9b0534f558f1..45ee99b159e2 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -576,6 +576,34 @@ _bpftool() ;; esac ;; + struct_ops) + local STRUCT_OPS_TYPE='id name' + case $command in + show|list|dump|unregister) + case $prev in + $command) + COMPREPLY=( $( compgen -W "$STRUCT_OPS_TYPE" -- "$cur" ) ) + ;; + id) + _bpftool_get_map_ids_for_type struct_ops + ;; + name) + _bpftool_get_map_names_for_type struct_ops + ;; + esac + return 0 + ;; + register) + _filedir + return 0 + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'register unregister show list dump help' \ + -- "$cur" ) ) + ;; + esac + ;; map) local MAP_TYPE='id pinned name' case $command in diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c index 01cc52b834fa..497807bec675 100644 --- a/tools/bpf/bpftool/btf_dumper.c +++ b/tools/bpf/bpftool/btf_dumper.c @@ -4,11 +4,13 @@ #include <ctype.h> #include <stdio.h> /* for (FILE *) used by json_writer */ #include <string.h> +#include <unistd.h> #include <asm/byteorder.h> #include <linux/bitops.h> #include <linux/btf.h> #include <linux/err.h> #include <bpf/btf.h> +#include <bpf/bpf.h> #include "json_writer.h" #include "main.h" @@ -22,13 +24,102 @@ static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id, __u8 bit_offset, const void *data); -static void btf_dumper_ptr(const void *data, json_writer_t *jw, - bool is_plain_text) +static int btf_dump_func(const struct btf *btf, char *func_sig, + const struct btf_type *func_proto, + const struct btf_type *func, int pos, int size); + +static int dump_prog_id_as_func_ptr(const struct btf_dumper *d, + const struct btf_type *func_proto, + __u32 prog_id) { - if (is_plain_text) - jsonw_printf(jw, "%p", *(void **)data); + struct bpf_prog_info_linear *prog_info = NULL; + const struct btf_type *func_type; + const char *prog_name = NULL; + struct bpf_func_info *finfo; + struct btf *prog_btf = NULL; + struct bpf_prog_info *info; + int prog_fd, func_sig_len; + char prog_str[1024]; + + /* Get the ptr's func_proto */ + func_sig_len = btf_dump_func(d->btf, prog_str, func_proto, NULL, 0, + sizeof(prog_str)); + if (func_sig_len == -1) + return -1; + + if (!prog_id) + goto print; + + /* Get the bpf_prog's name. Obtain from func_info. */ + prog_fd = bpf_prog_get_fd_by_id(prog_id); + if (prog_fd == -1) + goto print; + + prog_info = bpf_program__get_prog_info_linear(prog_fd, + 1UL << BPF_PROG_INFO_FUNC_INFO); + close(prog_fd); + if (IS_ERR(prog_info)) { + prog_info = NULL; + goto print; + } + info = &prog_info->info; + + if (!info->btf_id || !info->nr_func_info || + btf__get_from_id(info->btf_id, &prog_btf)) + goto print; + finfo = (struct bpf_func_info *)info->func_info; + func_type = btf__type_by_id(prog_btf, finfo->type_id); + if (!func_type || !btf_is_func(func_type)) + goto print; + + prog_name = btf__name_by_offset(prog_btf, func_type->name_off); + +print: + if (!prog_id) + snprintf(&prog_str[func_sig_len], + sizeof(prog_str) - func_sig_len, " 0"); + else if (prog_name) + snprintf(&prog_str[func_sig_len], + sizeof(prog_str) - func_sig_len, + " %s/prog_id:%u", prog_name, prog_id); else - jsonw_printf(jw, "%lu", *(unsigned long *)data); + snprintf(&prog_str[func_sig_len], + sizeof(prog_str) - func_sig_len, + " <unknown_prog_name>/prog_id:%u", prog_id); + + prog_str[sizeof(prog_str) - 1] = '\0'; + jsonw_string(d->jw, prog_str); + btf__free(prog_btf); + free(prog_info); + return 0; +} + +static void btf_dumper_ptr(const struct btf_dumper *d, + const struct btf_type *t, + const void *data) +{ + unsigned long value = *(unsigned long *)data; + const struct btf_type *ptr_type; + __s32 ptr_type_id; + + if (!d->prog_id_as_func_ptr || value > UINT32_MAX) + goto print_ptr_value; + + ptr_type_id = btf__resolve_type(d->btf, t->type); + if (ptr_type_id < 0) + goto print_ptr_value; + ptr_type = btf__type_by_id(d->btf, ptr_type_id); + if (!ptr_type || !btf_is_func_proto(ptr_type)) + goto print_ptr_value; + + if (!dump_prog_id_as_func_ptr(d, ptr_type, value)) + return; + +print_ptr_value: + if (d->is_plain_text) + jsonw_printf(d->jw, "%p", (void *)value); + else + jsonw_printf(d->jw, "%lu", value); } static int btf_dumper_modifier(const struct btf_dumper *d, __u32 type_id, @@ -43,9 +134,78 @@ static int btf_dumper_modifier(const struct btf_dumper *d, __u32 type_id, return btf_dumper_do_type(d, actual_type_id, bit_offset, data); } -static void btf_dumper_enum(const void *data, json_writer_t *jw) +static int btf_dumper_enum(const struct btf_dumper *d, + const struct btf_type *t, + const void *data) +{ + const struct btf_enum *enums = btf_enum(t); + __s64 value; + __u16 i; + + switch (t->size) { + case 8: + value = *(__s64 *)data; + break; + case 4: + value = *(__s32 *)data; + break; + case 2: + value = *(__s16 *)data; + break; + case 1: + value = *(__s8 *)data; + break; + default: + return -EINVAL; + } + + for (i = 0; i < btf_vlen(t); i++) { + if (value == enums[i].val) { + jsonw_string(d->jw, + btf__name_by_offset(d->btf, + enums[i].name_off)); + return 0; + } + } + + jsonw_int(d->jw, value); + return 0; +} + +static bool is_str_array(const struct btf *btf, const struct btf_array *arr, + const char *s) { - jsonw_printf(jw, "%d", *(int *)data); + const struct btf_type *elem_type; + const char *end_s; + + if (!arr->nelems) + return false; + + elem_type = btf__type_by_id(btf, arr->type); + /* Not skipping typedef. typedef to char does not count as + * a string now. + */ + while (elem_type && btf_is_mod(elem_type)) + elem_type = btf__type_by_id(btf, elem_type->type); + + if (!elem_type || !btf_is_int(elem_type) || elem_type->size != 1) + return false; + + if (btf_int_encoding(elem_type) != BTF_INT_CHAR && + strcmp("char", btf__name_by_offset(btf, elem_type->name_off))) + return false; + + end_s = s + arr->nelems; + while (s < end_s) { + if (!*s) + return true; + if (*s <= 0x1f || *s >= 0x7f) + return false; + s++; + } + + /* '\0' is not found */ + return false; } static int btf_dumper_array(const struct btf_dumper *d, __u32 type_id, @@ -57,6 +217,11 @@ static int btf_dumper_array(const struct btf_dumper *d, __u32 type_id, int ret = 0; __u32 i; + if (is_str_array(d->btf, arr, data)) { + jsonw_string(d->jw, data); + return 0; + } + elem_size = btf__resolve_size(d->btf, arr->type); if (elem_size < 0) return elem_size; @@ -366,10 +531,9 @@ static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id, case BTF_KIND_ARRAY: return btf_dumper_array(d, type_id, data); case BTF_KIND_ENUM: - btf_dumper_enum(data, d->jw); - return 0; + return btf_dumper_enum(d, t, data); case BTF_KIND_PTR: - btf_dumper_ptr(data, d->jw, d->is_plain_text); + btf_dumper_ptr(d, t, data); return 0; case BTF_KIND_UNKN: jsonw_printf(d->jw, "(unknown)"); @@ -414,10 +578,6 @@ int btf_dumper_type(const struct btf_dumper *d, __u32 type_id, return -1; \ } while (0) -static int btf_dump_func(const struct btf *btf, char *func_sig, - const struct btf_type *func_proto, - const struct btf_type *func, int pos, int size); - static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id, char *func_sig, int pos, int size) { @@ -526,8 +686,15 @@ static int btf_dump_func(const struct btf *btf, char *func_sig, BTF_PRINT_ARG(", "); if (arg->type) { BTF_PRINT_TYPE(arg->type); - BTF_PRINT_ARG("%s", - btf__name_by_offset(btf, arg->name_off)); + if (arg->name_off) + BTF_PRINT_ARG("%s", + btf__name_by_offset(btf, arg->name_off)); + else if (pos && func_sig[pos - 1] == ' ') + /* Remove unnecessary space for + * FUNC_PROTO that does not have + * arg->name_off + */ + func_sig[--pos] = '\0'; } else { BTF_PRINT_ARG("..."); } diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 06449e846e4b..466c269eabdd 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -58,7 +58,7 @@ static int do_help(int argc, char **argv) " %s batch file FILE\n" " %s version\n" "\n" - " OBJECT := { prog | map | cgroup | perf | net | feature | btf | gen }\n" + " OBJECT := { prog | map | cgroup | perf | net | feature | btf | gen | struct_ops }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, bin_name, bin_name); @@ -221,6 +221,7 @@ static const struct cmd cmds[] = { { "feature", do_feature }, { "btf", do_btf }, { "gen", do_gen }, + { "struct_ops", do_struct_ops }, { "version", do_version }, { 0 } }; diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 5f6dccd43622..86f14ce26fd7 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -161,6 +161,7 @@ int do_tracelog(int argc, char **arg); int do_feature(int argc, char **argv); int do_btf(int argc, char **argv); int do_gen(int argc, char **argv); +int do_struct_ops(int argc, char **argv); int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what); int prog_parse_fd(int *argc, char ***argv); @@ -205,6 +206,7 @@ struct btf_dumper { const struct btf *btf; json_writer_t *jw; bool is_plain_text; + bool prog_id_as_func_ptr; }; /* btf_dumper_type - print data along with type information diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c new file mode 100644 index 000000000000..2a7befbd11ad --- /dev/null +++ b/tools/bpf/bpftool/struct_ops.c @@ -0,0 +1,596 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2020 Facebook */ + +#include <errno.h> +#include <stdio.h> +#include <unistd.h> + +#include <linux/err.h> + +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/libbpf.h> + +#include "json_writer.h" +#include "main.h" + +#define STRUCT_OPS_VALUE_PREFIX "bpf_struct_ops_" + +static const struct btf_type *map_info_type; +static __u32 map_info_alloc_len; +static struct btf *btf_vmlinux; +static __s32 map_info_type_id; + +struct res { + unsigned int nr_maps; + unsigned int nr_errs; +}; + +static const struct btf *get_btf_vmlinux(void) +{ + if (btf_vmlinux) + return btf_vmlinux; + + btf_vmlinux = libbpf_find_kernel_btf(); + if (IS_ERR(btf_vmlinux)) + p_err("struct_ops requires kernel CONFIG_DEBUG_INFO_BTF=y"); + + return btf_vmlinux; +} + +static const char *get_kern_struct_ops_name(const struct bpf_map_info *info) +{ + const struct btf *kern_btf; + const struct btf_type *t; + const char *st_ops_name; + + kern_btf = get_btf_vmlinux(); + if (IS_ERR(kern_btf)) + return "<btf_vmlinux_not_found>"; + + t = btf__type_by_id(kern_btf, info->btf_vmlinux_value_type_id); + st_ops_name = btf__name_by_offset(kern_btf, t->name_off); + st_ops_name += strlen(STRUCT_OPS_VALUE_PREFIX); + + return st_ops_name; +} + +static __s32 get_map_info_type_id(void) +{ + const struct btf *kern_btf; + + if (map_info_type_id) + return map_info_type_id; + + kern_btf = get_btf_vmlinux(); + if (IS_ERR(kern_btf)) { + map_info_type_id = PTR_ERR(kern_btf); + return map_info_type_id; + } + + map_info_type_id = btf__find_by_name_kind(kern_btf, "bpf_map_info", + BTF_KIND_STRUCT); + if (map_info_type_id < 0) { + p_err("can't find bpf_map_info from btf_vmlinux"); + return map_info_type_id; + } + map_info_type = btf__type_by_id(kern_btf, map_info_type_id); + + /* Ensure map_info_alloc() has at least what the bpftool needs */ + map_info_alloc_len = map_info_type->size; + if (map_info_alloc_len < sizeof(struct bpf_map_info)) + map_info_alloc_len = sizeof(struct bpf_map_info); + + return map_info_type_id; +} + +/* If the subcmd needs to print out the bpf_map_info, + * it should always call map_info_alloc to allocate + * a bpf_map_info object instead of allocating it + * on the stack. + * + * map_info_alloc() will take the running kernel's btf + * into account. i.e. it will consider the + * sizeof(struct bpf_map_info) of the running kernel. + * + * It will enable the "struct_ops" cmd to print the latest + * "struct bpf_map_info". + * + * [ Recall that "struct_ops" requires the kernel's btf to + * be available ] + */ +static struct bpf_map_info *map_info_alloc(__u32 *alloc_len) +{ + struct bpf_map_info *info; + + if (get_map_info_type_id() < 0) + return NULL; + + info = calloc(1, map_info_alloc_len); + if (!info) + p_err("mem alloc failed"); + else + *alloc_len = map_info_alloc_len; + + return info; +} + +/* It iterates all struct_ops maps of the system. + * It returns the fd in "*res_fd" and map_info in "*info". + * In the very first iteration, info->id should be 0. + * An optional map "*name" filter can be specified. + * The filter can be made more flexible in the future. + * e.g. filter by kernel-struct-ops-name, regex-name, glob-name, ...etc. + * + * Return value: + * 1: A struct_ops map found. It is returned in "*res_fd" and "*info". + * The caller can continue to call get_next in the future. + * 0: No struct_ops map is returned. + * All struct_ops map has been found. + * -1: Error and the caller should abort the iteration. + */ +static int get_next_struct_ops_map(const char *name, int *res_fd, + struct bpf_map_info *info, __u32 info_len) +{ + __u32 id = info->id; + int err, fd; + + while (true) { + err = bpf_map_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) + return 0; + p_err("can't get next map: %s", strerror(errno)); + return -1; + } + + fd = bpf_map_get_fd_by_id(id); + if (fd < 0) { + if (errno == ENOENT) + continue; + p_err("can't get map by id (%u): %s", + id, strerror(errno)); + return -1; + } + + err = bpf_obj_get_info_by_fd(fd, info, &info_len); + if (err) { + p_err("can't get map info: %s", strerror(errno)); + close(fd); + return -1; + } + + if (info->type == BPF_MAP_TYPE_STRUCT_OPS && + (!name || !strcmp(name, info->name))) { + *res_fd = fd; + return 1; + } + close(fd); + } +} + +static int cmd_retval(const struct res *res, bool must_have_one_map) +{ + if (res->nr_errs || (!res->nr_maps && must_have_one_map)) + return -1; + + return 0; +} + +/* "data" is the work_func private storage */ +typedef int (*work_func)(int fd, const struct bpf_map_info *info, void *data, + struct json_writer *wtr); + +/* Find all struct_ops map in the system. + * Filter out by "name" (if specified). + * Then call "func(fd, info, data, wtr)" on each struct_ops map found. + */ +static struct res do_search(const char *name, work_func func, void *data, + struct json_writer *wtr) +{ + struct bpf_map_info *info; + struct res res = {}; + __u32 info_len; + int fd, err; + + info = map_info_alloc(&info_len); + if (!info) { + res.nr_errs++; + return res; + } + + if (wtr) + jsonw_start_array(wtr); + while ((err = get_next_struct_ops_map(name, &fd, info, info_len)) == 1) { + res.nr_maps++; + err = func(fd, info, data, wtr); + if (err) + res.nr_errs++; + close(fd); + } + if (wtr) + jsonw_end_array(wtr); + + if (err) + res.nr_errs++; + + if (!wtr && name && !res.nr_errs && !res.nr_maps) + /* It is not printing empty []. + * Thus, needs to specifically say nothing found + * for "name" here. + */ + p_err("no struct_ops found for %s", name); + else if (!wtr && json_output && !res.nr_errs) + /* The "func()" above is not writing any json (i.e. !wtr + * test here). + * + * However, "-j" is enabled and there is no errs here, + * so call json_null() as the current convention of + * other cmds. + */ + jsonw_null(json_wtr); + + free(info); + return res; +} + +static struct res do_one_id(const char *id_str, work_func func, void *data, + struct json_writer *wtr) +{ + struct bpf_map_info *info; + struct res res = {}; + unsigned long id; + __u32 info_len; + char *endptr; + int fd; + + id = strtoul(id_str, &endptr, 0); + if (*endptr || !id || id > UINT32_MAX) { + p_err("invalid id %s", id_str); + res.nr_errs++; + return res; + } + + fd = bpf_map_get_fd_by_id(id); + if (fd == -1) { + p_err("can't get map by id (%lu): %s", id, strerror(errno)); + res.nr_errs++; + return res; + } + + info = map_info_alloc(&info_len); + if (!info) { + res.nr_errs++; + goto done; + } + + if (bpf_obj_get_info_by_fd(fd, info, &info_len)) { + p_err("can't get map info: %s", strerror(errno)); + res.nr_errs++; + goto done; + } + + if (info->type != BPF_MAP_TYPE_STRUCT_OPS) { + p_err("%s id %u is not a struct_ops map", info->name, info->id); + res.nr_errs++; + goto done; + } + + res.nr_maps++; + + if (func(fd, info, data, wtr)) + res.nr_errs++; + else if (!wtr && json_output) + /* The "func()" above is not writing any json (i.e. !wtr + * test here). + * + * However, "-j" is enabled and there is no errs here, + * so call json_null() as the current convention of + * other cmds. + */ + jsonw_null(json_wtr); + +done: + free(info); + close(fd); + + return res; +} + +static struct res do_work_on_struct_ops(const char *search_type, + const char *search_term, + work_func func, void *data, + struct json_writer *wtr) +{ + if (search_type) { + if (is_prefix(search_type, "id")) + return do_one_id(search_term, func, data, wtr); + else if (!is_prefix(search_type, "name")) + usage(); + } + + return do_search(search_term, func, data, wtr); +} + +static int __do_show(int fd, const struct bpf_map_info *info, void *data, + struct json_writer *wtr) +{ + if (wtr) { + jsonw_start_object(wtr); + jsonw_uint_field(wtr, "id", info->id); + jsonw_string_field(wtr, "name", info->name); + jsonw_string_field(wtr, "kernel_struct_ops", + get_kern_struct_ops_name(info)); + jsonw_end_object(wtr); + } else { + printf("%u: %-15s %-32s\n", info->id, info->name, + get_kern_struct_ops_name(info)); + } + + return 0; +} + +static int do_show(int argc, char **argv) +{ + const char *search_type = NULL, *search_term = NULL; + struct res res; + + if (argc && argc != 2) + usage(); + + if (argc == 2) { + search_type = GET_ARG(); + search_term = GET_ARG(); + } + + res = do_work_on_struct_ops(search_type, search_term, __do_show, + NULL, json_wtr); + + return cmd_retval(&res, !!search_term); +} + +static int __do_dump(int fd, const struct bpf_map_info *info, void *data, + struct json_writer *wtr) +{ + struct btf_dumper *d = (struct btf_dumper *)data; + const struct btf_type *struct_ops_type; + const struct btf *kern_btf = d->btf; + const char *struct_ops_name; + int zero = 0; + void *value; + + /* note: d->jw == wtr */ + + kern_btf = d->btf; + + /* The kernel supporting BPF_MAP_TYPE_STRUCT_OPS must have + * btf_vmlinux_value_type_id. + */ + struct_ops_type = btf__type_by_id(kern_btf, + info->btf_vmlinux_value_type_id); + struct_ops_name = btf__name_by_offset(kern_btf, + struct_ops_type->name_off); + value = calloc(1, info->value_size); + if (!value) { + p_err("mem alloc failed"); + return -1; + } + + if (bpf_map_lookup_elem(fd, &zero, value)) { + p_err("can't lookup struct_ops map %s id %u", + info->name, info->id); + free(value); + return -1; + } + + jsonw_start_object(wtr); + jsonw_name(wtr, "bpf_map_info"); + btf_dumper_type(d, map_info_type_id, (void *)info); + jsonw_end_object(wtr); + + jsonw_start_object(wtr); + jsonw_name(wtr, struct_ops_name); + btf_dumper_type(d, info->btf_vmlinux_value_type_id, value); + jsonw_end_object(wtr); + + free(value); + + return 0; +} + +static int do_dump(int argc, char **argv) +{ + const char *search_type = NULL, *search_term = NULL; + json_writer_t *wtr = json_wtr; + const struct btf *kern_btf; + struct btf_dumper d = {}; + struct res res; + + if (argc && argc != 2) + usage(); + + if (argc == 2) { + search_type = GET_ARG(); + search_term = GET_ARG(); + } + + kern_btf = get_btf_vmlinux(); + if (IS_ERR(kern_btf)) + return -1; + + if (!json_output) { + wtr = jsonw_new(stdout); + if (!wtr) { + p_err("can't create json writer"); + return -1; + } + jsonw_pretty(wtr, true); + } + + d.btf = kern_btf; + d.jw = wtr; + d.is_plain_text = !json_output; + d.prog_id_as_func_ptr = true; + + res = do_work_on_struct_ops(search_type, search_term, __do_dump, &d, + wtr); + + if (!json_output) + jsonw_destroy(&wtr); + + return cmd_retval(&res, !!search_term); +} + +static int __do_unregister(int fd, const struct bpf_map_info *info, void *data, + struct json_writer *wtr) +{ + int zero = 0; + + if (bpf_map_delete_elem(fd, &zero)) { + p_err("can't unload %s %s id %u: %s", + get_kern_struct_ops_name(info), info->name, + info->id, strerror(errno)); + return -1; + } + + p_info("Unregistered %s %s id %u", + get_kern_struct_ops_name(info), info->name, + info->id); + + return 0; +} + +static int do_unregister(int argc, char **argv) +{ + const char *search_type, *search_term; + struct res res; + + if (argc != 2) + usage(); + + search_type = GET_ARG(); + search_term = GET_ARG(); + + res = do_work_on_struct_ops(search_type, search_term, + __do_unregister, NULL, NULL); + + return cmd_retval(&res, true); +} + +static int do_register(int argc, char **argv) +{ + const struct bpf_map_def *def; + struct bpf_map_info info = {}; + __u32 info_len = sizeof(info); + int nr_errs = 0, nr_maps = 0; + struct bpf_object *obj; + struct bpf_link *link; + struct bpf_map *map; + const char *file; + + if (argc != 1) + usage(); + + file = GET_ARG(); + + obj = bpf_object__open(file); + if (IS_ERR_OR_NULL(obj)) + return -1; + + set_max_rlimit(); + + if (bpf_object__load(obj)) { + bpf_object__close(obj); + return -1; + } + + bpf_object__for_each_map(map, obj) { + def = bpf_map__def(map); + if (def->type != BPF_MAP_TYPE_STRUCT_OPS) + continue; + + link = bpf_map__attach_struct_ops(map); + if (IS_ERR(link)) { + p_err("can't register struct_ops %s: %s", + bpf_map__name(map), + strerror(-PTR_ERR(link))); + nr_errs++; + continue; + } + nr_maps++; + + bpf_link__disconnect(link); + bpf_link__destroy(link); + + if (!bpf_obj_get_info_by_fd(bpf_map__fd(map), &info, + &info_len)) + p_info("Registered %s %s id %u", + get_kern_struct_ops_name(&info), + bpf_map__name(map), + info.id); + else + /* Not p_err. The struct_ops was attached + * successfully. + */ + p_info("Registered %s but can't find id: %s", + bpf_map__name(map), strerror(errno)); + } + + bpf_object__close(obj); + + if (nr_errs) + return -1; + + if (!nr_maps) { + p_err("no struct_ops found in %s", file); + return -1; + } + + if (json_output) + jsonw_null(json_wtr); + + return 0; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %s %s { show | list } [STRUCT_OPS_MAP]\n" + " %s %s dump [STRUCT_OPS_MAP]\n" + " %s %s register OBJ\n" + " %s %s unregister STRUCT_OPS_MAP\n" + " %s %s help\n" + "\n" + " OPTIONS := { {-j|--json} [{-p|--pretty}] }\n" + " STRUCT_OPS_MAP := [ id STRUCT_OPS_MAP_ID | name STRUCT_OPS_MAP_NAME ]\n", + bin_name, argv[-2], bin_name, argv[-2], + bin_name, argv[-2], bin_name, argv[-2], + bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "register", do_register }, + { "unregister", do_unregister }, + { "dump", do_dump }, + { "help", do_help }, + { 0 } +}; + +int do_struct_ops(int argc, char **argv) +{ + int err; + + err = cmd_select(cmds, argc, argv, do_help); + + btf__free(btf_vmlinux); + return err; +} diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 5d01c5c7e598..2e29a671d67e 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -111,6 +111,8 @@ enum bpf_cmd { BPF_MAP_LOOKUP_AND_DELETE_BATCH, BPF_MAP_UPDATE_BATCH, BPF_MAP_DELETE_BATCH, + BPF_LINK_CREATE, + BPF_LINK_UPDATE, }; enum bpf_map_type { @@ -181,6 +183,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_TRACING, BPF_PROG_TYPE_STRUCT_OPS, BPF_PROG_TYPE_EXT, + BPF_PROG_TYPE_LSM, }; enum bpf_attach_type { @@ -211,6 +214,7 @@ enum bpf_attach_type { BPF_TRACE_FENTRY, BPF_TRACE_FEXIT, BPF_MODIFY_RETURN, + BPF_LSM_MAC, __MAX_BPF_ATTACH_TYPE }; @@ -539,7 +543,7 @@ union bpf_attr { __u32 prog_cnt; } query; - struct { + struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */ __u64 name; __u32 prog_fd; } raw_tracepoint; @@ -567,6 +571,24 @@ union bpf_attr { __u64 probe_offset; /* output: probe_offset */ __u64 probe_addr; /* output: probe_addr */ } task_fd_query; + + struct { /* struct used by BPF_LINK_CREATE command */ + __u32 prog_fd; /* eBPF program to attach */ + __u32 target_fd; /* object to attach to */ + __u32 attach_type; /* attach type */ + __u32 flags; /* extra flags */ + } link_create; + + struct { /* struct used by BPF_LINK_UPDATE command */ + __u32 link_fd; /* link fd */ + /* new program fd to update link with */ + __u32 new_prog_fd; + __u32 flags; /* extra flags */ + /* expected link's program fd; is specified only if + * BPF_F_REPLACE flag is set in flags */ + __u32 old_prog_fd; + } link_update; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF @@ -2950,6 +2972,59 @@ union bpf_attr { * restricted to raw_tracepoint bpf programs. * Return * 0 on success, or a negative error in case of failure. + * + * u64 bpf_get_netns_cookie(void *ctx) + * Description + * Retrieve the cookie (generated by the kernel) of the network + * namespace the input *ctx* is associated with. The network + * namespace cookie remains stable for its lifetime and provides + * a global identifier that can be assumed unique. If *ctx* is + * NULL, then the helper returns the cookie for the initial + * network namespace. The cookie itself is very similar to that + * of bpf_get_socket_cookie() helper, but for network namespaces + * instead of sockets. + * Return + * A 8-byte long opaque number. + * + * u64 bpf_get_current_ancestor_cgroup_id(int ancestor_level) + * Description + * Return id of cgroup v2 that is ancestor of the cgroup associated + * with the current task at the *ancestor_level*. The root cgroup + * is at *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with the current task, then return value will be the + * same as that of **bpf_get_current_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with the current task. + * + * The format of returned id and helper limitations are same as in + * **bpf_get_current_cgroup_id**\ (). + * Return + * The id is returned or 0 in case the id could not be retrieved. + * + * int bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags) + * Description + * Assign the *sk* to the *skb*. When combined with appropriate + * routing configuration to receive the packet towards the socket, + * will cause *skb* to be delivered to the specified socket. + * Subsequent redirection of *skb* via **bpf_redirect**\ (), + * **bpf_clone_redirect**\ () or other methods outside of BPF may + * interfere with successful delivery to the socket. + * + * This operation is only valid from TC ingress path. + * + * The *flags* argument must be zero. + * Return + * 0 on success, or a negative errno in case of failure. + * + * * **-EINVAL** Unsupported flags specified. + * * **-ENOENT** Socket is unavailable for assignment. + * * **-ENETUNREACH** Socket is unreachable (wrong netns). + * * **-EOPNOTSUPP** Unsupported operation, for example a + * call from outside of TC ingress. + * * **-ESOCKTNOSUPPORT** Socket type not supported (reuseport). */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3073,7 +3148,10 @@ union bpf_attr { FN(jiffies64), \ FN(read_branch_records), \ FN(get_ns_current_pid_tgid), \ - FN(xdp_output), + FN(xdp_output), \ + FN(get_netns_cookie), \ + FN(get_current_ancestor_cgroup_id), \ + FN(sk_assign), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 24cf6fe075f7..ca6665ea758a 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -962,11 +962,12 @@ enum { #define XDP_FLAGS_SKB_MODE (1U << 1) #define XDP_FLAGS_DRV_MODE (1U << 2) #define XDP_FLAGS_HW_MODE (1U << 3) +#define XDP_FLAGS_REPLACE (1U << 4) #define XDP_FLAGS_MODES (XDP_FLAGS_SKB_MODE | \ XDP_FLAGS_DRV_MODE | \ XDP_FLAGS_HW_MODE) #define XDP_FLAGS_MASK (XDP_FLAGS_UPDATE_IF_NOEXIST | \ - XDP_FLAGS_MODES) + XDP_FLAGS_MODES | XDP_FLAGS_REPLACE) /* These are stored into IFLA_XDP_ATTACHED on dump. */ enum { @@ -986,6 +987,7 @@ enum { IFLA_XDP_DRV_PROG_ID, IFLA_XDP_SKB_PROG_ID, IFLA_XDP_HW_PROG_ID, + IFLA_XDP_EXPECTED_FD, __IFLA_XDP_MAX, }; diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index c6dafe563176..5cc1b0785d18 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -235,7 +235,8 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, memset(&attr, 0, sizeof(attr)); attr.prog_type = load_attr->prog_type; attr.expected_attach_type = load_attr->expected_attach_type; - if (attr.prog_type == BPF_PROG_TYPE_STRUCT_OPS) { + if (attr.prog_type == BPF_PROG_TYPE_STRUCT_OPS || + attr.prog_type == BPF_PROG_TYPE_LSM) { attr.attach_btf_id = load_attr->attach_btf_id; } else if (attr.prog_type == BPF_PROG_TYPE_TRACING || attr.prog_type == BPF_PROG_TYPE_EXT) { @@ -584,6 +585,40 @@ int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type) return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr)); } +int bpf_link_create(int prog_fd, int target_fd, + enum bpf_attach_type attach_type, + const struct bpf_link_create_opts *opts) +{ + union bpf_attr attr; + + if (!OPTS_VALID(opts, bpf_link_create_opts)) + return -EINVAL; + + memset(&attr, 0, sizeof(attr)); + attr.link_create.prog_fd = prog_fd; + attr.link_create.target_fd = target_fd; + attr.link_create.attach_type = attach_type; + + return sys_bpf(BPF_LINK_CREATE, &attr, sizeof(attr)); +} + +int bpf_link_update(int link_fd, int new_prog_fd, + const struct bpf_link_update_opts *opts) +{ + union bpf_attr attr; + + if (!OPTS_VALID(opts, bpf_link_update_opts)) + return -EINVAL; + + memset(&attr, 0, sizeof(attr)); + attr.link_update.link_fd = link_fd; + attr.link_update.new_prog_fd = new_prog_fd; + attr.link_update.flags = OPTS_GET(opts, flags, 0); + attr.link_update.old_prog_fd = OPTS_GET(opts, old_prog_fd, 0); + + return sys_bpf(BPF_LINK_UPDATE, &attr, sizeof(attr)); +} + int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt) { diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index b976e77316cc..46d47afdd887 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -168,6 +168,25 @@ LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type); LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd, enum bpf_attach_type type); +struct bpf_link_create_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ +}; +#define bpf_link_create_opts__last_field sz + +LIBBPF_API int bpf_link_create(int prog_fd, int target_fd, + enum bpf_attach_type attach_type, + const struct bpf_link_create_opts *opts); + +struct bpf_link_update_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + __u32 flags; /* extra flags */ + __u32 old_prog_fd; /* expected old program FD */ +}; +#define bpf_link_update_opts__last_field old_prog_fd + +LIBBPF_API int bpf_link_update(int link_fd, int new_prog_fd, + const struct bpf_link_update_opts *opts); + struct bpf_prog_test_run_attr { int prog_fd; int repeat; diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index b0c9ae5c73b5..f3f3c3fb98cb 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -390,7 +390,7 @@ ____##name(struct pt_regs *ctx, ##args) #define ___bpf_kretprobe_args0() ctx #define ___bpf_kretprobe_args1(x) \ - ___bpf_kretprobe_args0(), (void *)PT_REGS_RET(ctx) + ___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx) #define ___bpf_kretprobe_args(args...) \ ___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args) diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 3d1c25fc97ae..bfef3d606b54 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -657,22 +657,32 @@ int btf__finalize_data(struct bpf_object *obj, struct btf *btf) int btf__load(struct btf *btf) { - __u32 log_buf_size = BPF_LOG_BUF_SIZE; + __u32 log_buf_size = 0; char *log_buf = NULL; int err = 0; if (btf->fd >= 0) return -EEXIST; - log_buf = malloc(log_buf_size); - if (!log_buf) - return -ENOMEM; +retry_load: + if (log_buf_size) { + log_buf = malloc(log_buf_size); + if (!log_buf) + return -ENOMEM; - *log_buf = 0; + *log_buf = 0; + } btf->fd = bpf_load_btf(btf->data, btf->data_size, log_buf, log_buf_size, false); if (btf->fd < 0) { + if (!log_buf || errno == ENOSPC) { + log_buf_size = max((__u32)BPF_LOG_BUF_SIZE, + log_buf_size << 1); + free(log_buf); + goto retry_load; + } + err = -errno; pr_warn("Error loading BTF: %s(%d)\n", strerror(errno), errno); if (*log_buf) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 085e41f9b68e..ff9174282a8c 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -1845,7 +1845,6 @@ resolve_func_ptr(const struct btf *btf, __u32 id, __u32 *res_id) * type definition, while using only sizeof(void *) space in ELF data section. */ static bool get_map_field_int(const char *map_name, const struct btf *btf, - const struct btf_type *def, const struct btf_member *m, __u32 *res) { const struct btf_type *t = skip_mods_and_typedefs(btf, m->type, NULL); @@ -1972,19 +1971,19 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, return -EINVAL; } if (strcmp(name, "type") == 0) { - if (!get_map_field_int(map_name, obj->btf, def, m, + if (!get_map_field_int(map_name, obj->btf, m, &map->def.type)) return -EINVAL; pr_debug("map '%s': found type = %u.\n", map_name, map->def.type); } else if (strcmp(name, "max_entries") == 0) { - if (!get_map_field_int(map_name, obj->btf, def, m, + if (!get_map_field_int(map_name, obj->btf, m, &map->def.max_entries)) return -EINVAL; pr_debug("map '%s': found max_entries = %u.\n", map_name, map->def.max_entries); } else if (strcmp(name, "map_flags") == 0) { - if (!get_map_field_int(map_name, obj->btf, def, m, + if (!get_map_field_int(map_name, obj->btf, m, &map->def.map_flags)) return -EINVAL; pr_debug("map '%s': found map_flags = %u.\n", @@ -1992,8 +1991,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, } else if (strcmp(name, "key_size") == 0) { __u32 sz; - if (!get_map_field_int(map_name, obj->btf, def, m, - &sz)) + if (!get_map_field_int(map_name, obj->btf, m, &sz)) return -EINVAL; pr_debug("map '%s': found key_size = %u.\n", map_name, sz); @@ -2035,8 +2033,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, } else if (strcmp(name, "value_size") == 0) { __u32 sz; - if (!get_map_field_int(map_name, obj->btf, def, m, - &sz)) + if (!get_map_field_int(map_name, obj->btf, m, &sz)) return -EINVAL; pr_debug("map '%s': found value_size = %u.\n", map_name, sz); @@ -2079,8 +2076,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, __u32 val; int err; - if (!get_map_field_int(map_name, obj->btf, def, m, - &val)) + if (!get_map_field_int(map_name, obj->btf, m, &val)) return -EINVAL; pr_debug("map '%s': found pinning = %u.\n", map_name, val); @@ -2362,7 +2358,8 @@ static int bpf_object__finalize_btf(struct bpf_object *obj) static inline bool libbpf_prog_needs_vmlinux_btf(struct bpf_program *prog) { - if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) + if (prog->type == BPF_PROG_TYPE_STRUCT_OPS || + prog->type == BPF_PROG_TYPE_LSM) return true; /* BPF_PROG_TYPE_TRACING programs which do not attach to other programs @@ -4855,8 +4852,8 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, { struct bpf_load_program_attr load_attr; char *cp, errmsg[STRERR_BUFSIZE]; - int log_buf_size = BPF_LOG_BUF_SIZE; - char *log_buf; + size_t log_buf_size = 0; + char *log_buf = NULL; int btf_fd, ret; if (!insns || !insns_cnt) @@ -4870,7 +4867,8 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.insns = insns; load_attr.insns_cnt = insns_cnt; load_attr.license = license; - if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) { + if (prog->type == BPF_PROG_TYPE_STRUCT_OPS || + prog->type == BPF_PROG_TYPE_LSM) { load_attr.attach_btf_id = prog->attach_btf_id; } else if (prog->type == BPF_PROG_TYPE_TRACING || prog->type == BPF_PROG_TYPE_EXT) { @@ -4896,22 +4894,28 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.prog_flags = prog->prog_flags; retry_load: - log_buf = malloc(log_buf_size); - if (!log_buf) - pr_warn("Alloc log buffer for bpf loader error, continue without log\n"); + if (log_buf_size) { + log_buf = malloc(log_buf_size); + if (!log_buf) + return -ENOMEM; + + *log_buf = 0; + } ret = bpf_load_program_xattr(&load_attr, log_buf, log_buf_size); if (ret >= 0) { - if (load_attr.log_level) + if (log_buf && load_attr.log_level) pr_debug("verifier log:\n%s", log_buf); *pfd = ret; ret = 0; goto out; } - if (errno == ENOSPC) { - log_buf_size <<= 1; + if (!log_buf || errno == ENOSPC) { + log_buf_size = max((size_t)BPF_LOG_BUF_SIZE, + log_buf_size << 1); + free(log_buf); goto retry_load; } @@ -4955,6 +4959,7 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) int err = 0, fd, i, btf_id; if ((prog->type == BPF_PROG_TYPE_TRACING || + prog->type == BPF_PROG_TYPE_LSM || prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) { btf_id = libbpf_find_attach_btf_id(prog); if (btf_id <= 0) @@ -6194,6 +6199,7 @@ bool bpf_program__is_##NAME(const struct bpf_program *prog) \ } \ BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER); +BPF_PROG_TYPE_FNS(lsm, BPF_PROG_TYPE_LSM); BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE); BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS); BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT); @@ -6260,6 +6266,8 @@ static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec, struct bpf_program *prog); static struct bpf_link *attach_trace(const struct bpf_sec_def *sec, struct bpf_program *prog); +static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec, + struct bpf_program *prog); struct bpf_sec_def { const char *sec; @@ -6310,6 +6318,10 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("freplace/", EXT, .is_attach_btf = true, .attach_fn = attach_trace), + SEC_DEF("lsm/", LSM, + .is_attach_btf = true, + .expected_attach_type = BPF_LSM_MAC, + .attach_fn = attach_lsm), BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP), BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN), @@ -6572,6 +6584,7 @@ invalid_prog: } #define BTF_TRACE_PREFIX "btf_trace_" +#define BTF_LSM_PREFIX "bpf_lsm_" #define BTF_MAX_NAME_SIZE 128 static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix, @@ -6599,6 +6612,9 @@ static inline int __find_vmlinux_btf_id(struct btf *btf, const char *name, if (attach_type == BPF_TRACE_RAW_TP) err = find_btf_by_prefix_kind(btf, BTF_TRACE_PREFIX, name, BTF_KIND_TYPEDEF); + else if (attach_type == BPF_LSM_MAC) + err = find_btf_by_prefix_kind(btf, BTF_LSM_PREFIX, name, + BTF_KIND_FUNC); else err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC); @@ -6756,6 +6772,17 @@ void *bpf_map__priv(const struct bpf_map *map) return map ? map->priv : ERR_PTR(-EINVAL); } +int bpf_map__set_initial_value(struct bpf_map *map, + const void *data, size_t size) +{ + if (!map->mmaped || map->libbpf_type == LIBBPF_MAP_KCONFIG || + size != map->def.value_size || map->fd >= 0) + return -EINVAL; + + memcpy(map->mmaped, data, size); + return 0; +} + bool bpf_map__is_offload_neutral(const struct bpf_map *map) { return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY; @@ -6951,6 +6978,12 @@ struct bpf_link { bool disconnected; }; +/* Replace link's underlying BPF program with the new one */ +int bpf_link__update_program(struct bpf_link *link, struct bpf_program *prog) +{ + return bpf_link_update(bpf_link__fd(link), bpf_program__fd(prog), NULL); +} + /* Release "ownership" of underlying BPF resource (typically, BPF program * attached to some BPF hook, e.g., tracepoint, kprobe, etc). Disconnected * link, when destructed through bpf_link__destroy() call won't attempt to @@ -7452,7 +7485,8 @@ static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec, return bpf_program__attach_raw_tracepoint(prog, tp_name); } -struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog) +/* Common logic for all BPF program types that attach to a btf_id */ +static struct bpf_link *bpf_program__attach_btf_id(struct bpf_program *prog) { char errmsg[STRERR_BUFSIZE]; struct bpf_link *link; @@ -7474,7 +7508,7 @@ struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog) if (pfd < 0) { pfd = -errno; free(link); - pr_warn("program '%s': failed to attach to trace: %s\n", + pr_warn("program '%s': failed to attach: %s\n", bpf_program__title(prog, false), libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); return ERR_PTR(pfd); @@ -7483,12 +7517,68 @@ struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog) return (struct bpf_link *)link; } +struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog) +{ + return bpf_program__attach_btf_id(prog); +} + +struct bpf_link *bpf_program__attach_lsm(struct bpf_program *prog) +{ + return bpf_program__attach_btf_id(prog); +} + static struct bpf_link *attach_trace(const struct bpf_sec_def *sec, struct bpf_program *prog) { return bpf_program__attach_trace(prog); } +static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec, + struct bpf_program *prog) +{ + return bpf_program__attach_lsm(prog); +} + +struct bpf_link * +bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd) +{ + const struct bpf_sec_def *sec_def; + enum bpf_attach_type attach_type; + char errmsg[STRERR_BUFSIZE]; + struct bpf_link *link; + int prog_fd, link_fd; + + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warn("program '%s': can't attach before loaded\n", + bpf_program__title(prog, false)); + return ERR_PTR(-EINVAL); + } + + link = calloc(1, sizeof(*link)); + if (!link) + return ERR_PTR(-ENOMEM); + link->detach = &bpf_link__detach_fd; + + attach_type = bpf_program__get_expected_attach_type(prog); + if (!attach_type) { + sec_def = find_sec_def(bpf_program__title(prog, false)); + if (sec_def) + attach_type = sec_def->attach_type; + } + link_fd = bpf_link_create(prog_fd, cgroup_fd, attach_type, NULL); + if (link_fd < 0) { + link_fd = -errno; + free(link); + pr_warn("program '%s': failed to attach to cgroup: %s\n", + bpf_program__title(prog, false), + libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg))); + return ERR_PTR(link_fd); + } + link->fd = link_fd; + return link; +} + struct bpf_link *bpf_program__attach(struct bpf_program *prog) { const struct bpf_sec_def *sec_def; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index d38d7a629417..44df1d3e7287 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -224,6 +224,8 @@ LIBBPF_API int bpf_link__fd(const struct bpf_link *link); LIBBPF_API const char *bpf_link__pin_path(const struct bpf_link *link); LIBBPF_API int bpf_link__pin(struct bpf_link *link, const char *path); LIBBPF_API int bpf_link__unpin(struct bpf_link *link); +LIBBPF_API int bpf_link__update_program(struct bpf_link *link, + struct bpf_program *prog); LIBBPF_API void bpf_link__disconnect(struct bpf_link *link); LIBBPF_API int bpf_link__destroy(struct bpf_link *link); @@ -245,11 +247,17 @@ bpf_program__attach_tracepoint(struct bpf_program *prog, LIBBPF_API struct bpf_link * bpf_program__attach_raw_tracepoint(struct bpf_program *prog, const char *tp_name); - LIBBPF_API struct bpf_link * bpf_program__attach_trace(struct bpf_program *prog); +LIBBPF_API struct bpf_link * +bpf_program__attach_lsm(struct bpf_program *prog); +LIBBPF_API struct bpf_link * +bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd); + struct bpf_map; + LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map); + struct bpf_insn; /* @@ -321,6 +329,7 @@ LIBBPF_API int bpf_program__set_socket_filter(struct bpf_program *prog); LIBBPF_API int bpf_program__set_tracepoint(struct bpf_program *prog); LIBBPF_API int bpf_program__set_raw_tracepoint(struct bpf_program *prog); LIBBPF_API int bpf_program__set_kprobe(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_lsm(struct bpf_program *prog); LIBBPF_API int bpf_program__set_sched_cls(struct bpf_program *prog); LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog); LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog); @@ -347,6 +356,7 @@ LIBBPF_API bool bpf_program__is_socket_filter(const struct bpf_program *prog); LIBBPF_API bool bpf_program__is_tracepoint(const struct bpf_program *prog); LIBBPF_API bool bpf_program__is_raw_tracepoint(const struct bpf_program *prog); LIBBPF_API bool bpf_program__is_kprobe(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_lsm(const struct bpf_program *prog); LIBBPF_API bool bpf_program__is_sched_cls(const struct bpf_program *prog); LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog); LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog); @@ -407,6 +417,8 @@ typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv, bpf_map_clear_priv_t clear_priv); LIBBPF_API void *bpf_map__priv(const struct bpf_map *map); +LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map, + const void *data, size_t size); LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd); LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries); LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map); @@ -444,7 +456,15 @@ struct xdp_link_info { __u8 attach_mode; }; +struct bpf_xdp_set_link_opts { + size_t sz; + __u32 old_fd; +}; +#define bpf_xdp_set_link_opts__last_field old_fd + LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); +LIBBPF_API int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags, + const struct bpf_xdp_set_link_opts *opts); LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags); LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, size_t info_size, __u32 flags); diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 5129283c0284..bb8831605b25 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -243,5 +243,14 @@ LIBBPF_0.0.8 { bpf_link__pin; bpf_link__pin_path; bpf_link__unpin; + bpf_link__update_program; + bpf_link_create; + bpf_link_update; + bpf_map__set_initial_value; + bpf_program__attach_cgroup; + bpf_program__attach_lsm; + bpf_program__is_lsm; bpf_program__set_attach_target; + bpf_program__set_lsm; + bpf_set_link_xdp_fd_opts; } LIBBPF_0.0.7; diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index b782ebef6ac9..2c92059c0c90 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -108,6 +108,7 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_STRUCT_OPS: case BPF_PROG_TYPE_EXT: + case BPF_PROG_TYPE_LSM: default: break; } diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 431bd25c6cdb..18b5319025e1 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -132,7 +132,8 @@ done: return ret; } -int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags) +static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd, + __u32 flags) { int sock, seq = 0, ret; struct nlattr *nla, *nla_xdp; @@ -178,6 +179,14 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags) nla->nla_len += nla_xdp->nla_len; } + if (flags & XDP_FLAGS_REPLACE) { + nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); + nla_xdp->nla_type = IFLA_XDP_EXPECTED_FD; + nla_xdp->nla_len = NLA_HDRLEN + sizeof(old_fd); + memcpy((char *)nla_xdp + NLA_HDRLEN, &old_fd, sizeof(old_fd)); + nla->nla_len += nla_xdp->nla_len; + } + req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len); if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) { @@ -191,6 +200,29 @@ cleanup: return ret; } +int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags, + const struct bpf_xdp_set_link_opts *opts) +{ + int old_fd = -1; + + if (!OPTS_VALID(opts, bpf_xdp_set_link_opts)) + return -EINVAL; + + if (OPTS_HAS(opts, old_fd)) { + old_fd = OPTS_GET(opts, old_fd, -1); + flags |= XDP_FLAGS_REPLACE; + } + + return __bpf_set_link_xdp_fd_replace(ifindex, fd, + old_fd, + flags); +} + +int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags) +{ + return __bpf_set_link_xdp_fd_replace(ifindex, fd, 0, flags); +} + static int __dump_link_nlmsg(struct nlmsghdr *nlh, libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie) { diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 9807903f121e..f7f4efb70a4c 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -280,7 +280,11 @@ int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area, fill->consumer = map + off.fr.consumer; fill->flags = map + off.fr.flags; fill->ring = map + off.fr.desc; - fill->cached_cons = umem->config.fill_size; + fill->cached_prod = *fill->producer; + /* cached_cons is "size" bigger than the real consumer pointer + * See xsk_prod_nb_free + */ + fill->cached_cons = *fill->consumer + umem->config.fill_size; map = mmap(NULL, off.cr.desc + umem->config.comp_size * sizeof(__u64), PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, umem->fd, @@ -297,6 +301,8 @@ int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area, comp->consumer = map + off.cr.consumer; comp->flags = map + off.cr.flags; comp->ring = map + off.cr.desc; + comp->cached_prod = *comp->producer; + comp->cached_cons = *comp->consumer; *umem_ptr = umem; return 0; @@ -672,6 +678,8 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, rx->consumer = rx_map + off.rx.consumer; rx->flags = rx_map + off.rx.flags; rx->ring = rx_map + off.rx.desc; + rx->cached_prod = *rx->producer; + rx->cached_cons = *rx->consumer; } xsk->rx = rx; @@ -691,7 +699,11 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, tx->consumer = tx_map + off.tx.consumer; tx->flags = tx_map + off.tx.flags; tx->ring = tx_map + off.tx.desc; - tx->cached_cons = xsk->config.tx_size; + tx->cached_prod = *tx->producer; + /* cached_cons is r->size bigger than the real consumer pointer + * See xsk_prod_nb_free + */ + tx->cached_cons = *tx->consumer + xsk->config.tx_size; } xsk->tx = tx; diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 5dc109f4c097..60e3ae5d4e48 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -35,3 +35,5 @@ CONFIG_MPLS_ROUTING=m CONFIG_MPLS_IPTUNNEL=m CONFIG_IPV6_SIT=m CONFIG_BPF_JIT=y +CONFIG_BPF_LSM=y +CONFIG_SECURITY=y diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c index 8482bbc67eec..9a8f47fc0b91 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c @@ -11,6 +11,7 @@ static const unsigned int total_bytes = 10 * 1024 * 1024; static const struct timeval timeo_sec = { .tv_sec = 10 }; static const size_t timeo_optlen = sizeof(timeo_sec); +static int expected_stg = 0xeB9F; static int stop, duration; static int settimeo(int fd) @@ -88,7 +89,7 @@ done: return NULL; } -static void do_test(const char *tcp_ca) +static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map) { struct sockaddr_in6 sa6 = {}; ssize_t nr_recv = 0, bytes = 0; @@ -126,14 +127,34 @@ static void do_test(const char *tcp_ca) err = listen(lfd, 1); if (CHECK(err == -1, "listen", "errno:%d\n", errno)) goto done; - err = pthread_create(&srv_thread, NULL, server, (void *)(long)lfd); - if (CHECK(err != 0, "pthread_create", "err:%d\n", err)) - goto done; + + if (sk_stg_map) { + err = bpf_map_update_elem(bpf_map__fd(sk_stg_map), &fd, + &expected_stg, BPF_NOEXIST); + if (CHECK(err, "bpf_map_update_elem(sk_stg_map)", + "err:%d errno:%d\n", err, errno)) + goto done; + } /* connect to server */ err = connect(fd, (struct sockaddr *)&sa6, addrlen); if (CHECK(err == -1, "connect", "errno:%d\n", errno)) - goto wait_thread; + goto done; + + if (sk_stg_map) { + int tmp_stg; + + err = bpf_map_lookup_elem(bpf_map__fd(sk_stg_map), &fd, + &tmp_stg); + if (CHECK(!err || errno != ENOENT, + "bpf_map_lookup_elem(sk_stg_map)", + "err:%d errno:%d\n", err, errno)) + goto done; + } + + err = pthread_create(&srv_thread, NULL, server, (void *)(long)lfd); + if (CHECK(err != 0, "pthread_create", "err:%d errno:%d\n", err, errno)) + goto done; /* recv total_bytes */ while (bytes < total_bytes && !READ_ONCE(stop)) { @@ -149,7 +170,6 @@ static void do_test(const char *tcp_ca) CHECK(bytes != total_bytes, "recv", "%zd != %u nr_recv:%zd errno:%d\n", bytes, total_bytes, nr_recv, errno); -wait_thread: WRITE_ONCE(stop, 1); pthread_join(srv_thread, &thread_ret); CHECK(IS_ERR(thread_ret), "pthread_join", "thread_ret:%ld", @@ -175,7 +195,7 @@ static void test_cubic(void) return; } - do_test("bpf_cubic"); + do_test("bpf_cubic", NULL); bpf_link__destroy(link); bpf_cubic__destroy(cubic_skel); @@ -197,7 +217,10 @@ static void test_dctcp(void) return; } - do_test("bpf_dctcp"); + do_test("bpf_dctcp", dctcp_skel->maps.sk_stg_map); + CHECK(dctcp_skel->bss->stg_result != expected_stg, + "Unexpected stg_result", "stg_result (%x) != expected_stg (%x)\n", + dctcp_skel->bss->stg_result, expected_stg); bpf_link__destroy(link); bpf_dctcp__destroy(dctcp_skel); diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c index 7390d3061065..cb33a7ee4e04 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c @@ -125,6 +125,6 @@ void test_btf_dump() { if (!test__start_subtest(t->name)) continue; - test_btf_dump_case(i, &btf_dump_test_cases[i]); + test_btf_dump_case(i, &btf_dump_test_cases[i]); } } diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_link.c b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c new file mode 100644 index 000000000000..6e04f8d1d15b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c @@ -0,0 +1,244 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include "cgroup_helpers.h" +#include "test_cgroup_link.skel.h" + +static __u32 duration = 0; +#define PING_CMD "ping -q -c1 -w1 127.0.0.1 > /dev/null" + +static struct test_cgroup_link *skel = NULL; + +int ping_and_check(int exp_calls, int exp_alt_calls) +{ + skel->bss->calls = 0; + skel->bss->alt_calls = 0; + CHECK_FAIL(system(PING_CMD)); + if (CHECK(skel->bss->calls != exp_calls, "call_cnt", + "exp %d, got %d\n", exp_calls, skel->bss->calls)) + return -EINVAL; + if (CHECK(skel->bss->alt_calls != exp_alt_calls, "alt_call_cnt", + "exp %d, got %d\n", exp_alt_calls, skel->bss->alt_calls)) + return -EINVAL; + return 0; +} + +void test_cgroup_link(void) +{ + struct { + const char *path; + int fd; + } cgs[] = { + { "/cg1" }, + { "/cg1/cg2" }, + { "/cg1/cg2/cg3" }, + { "/cg1/cg2/cg3/cg4" }, + }; + int last_cg = ARRAY_SIZE(cgs) - 1, cg_nr = ARRAY_SIZE(cgs); + DECLARE_LIBBPF_OPTS(bpf_link_update_opts, link_upd_opts); + struct bpf_link *links[ARRAY_SIZE(cgs)] = {}, *tmp_link; + __u32 prog_ids[ARRAY_SIZE(cgs)], prog_cnt = 0, attach_flags; + int i = 0, err, prog_fd; + bool detach_legacy = false; + + skel = test_cgroup_link__open_and_load(); + if (CHECK(!skel, "skel_open_load", "failed to open/load skeleton\n")) + return; + prog_fd = bpf_program__fd(skel->progs.egress); + + err = setup_cgroup_environment(); + if (CHECK(err, "cg_init", "failed: %d\n", err)) + goto cleanup; + + for (i = 0; i < cg_nr; i++) { + cgs[i].fd = create_and_get_cgroup(cgs[i].path); + if (CHECK(cgs[i].fd < 0, "cg_create", "fail: %d\n", cgs[i].fd)) + goto cleanup; + } + + err = join_cgroup(cgs[last_cg].path); + if (CHECK(err, "cg_join", "fail: %d\n", err)) + goto cleanup; + + for (i = 0; i < cg_nr; i++) { + links[i] = bpf_program__attach_cgroup(skel->progs.egress, + cgs[i].fd); + if (CHECK(IS_ERR(links[i]), "cg_attach", "i: %d, err: %ld\n", + i, PTR_ERR(links[i]))) + goto cleanup; + } + + ping_and_check(cg_nr, 0); + + /* query the number of effective progs and attach flags in root cg */ + err = bpf_prog_query(cgs[0].fd, BPF_CGROUP_INET_EGRESS, + BPF_F_QUERY_EFFECTIVE, &attach_flags, NULL, + &prog_cnt); + CHECK_FAIL(err); + CHECK_FAIL(attach_flags != BPF_F_ALLOW_MULTI); + if (CHECK(prog_cnt != 1, "effect_cnt", "exp %d, got %d\n", 1, prog_cnt)) + goto cleanup; + + /* query the number of effective progs in last cg */ + err = bpf_prog_query(cgs[last_cg].fd, BPF_CGROUP_INET_EGRESS, + BPF_F_QUERY_EFFECTIVE, NULL, NULL, + &prog_cnt); + CHECK_FAIL(err); + CHECK_FAIL(attach_flags != BPF_F_ALLOW_MULTI); + if (CHECK(prog_cnt != cg_nr, "effect_cnt", "exp %d, got %d\n", + cg_nr, prog_cnt)) + goto cleanup; + + /* query the effective prog IDs in last cg */ + err = bpf_prog_query(cgs[last_cg].fd, BPF_CGROUP_INET_EGRESS, + BPF_F_QUERY_EFFECTIVE, &attach_flags, + prog_ids, &prog_cnt); + CHECK_FAIL(err); + CHECK_FAIL(attach_flags != BPF_F_ALLOW_MULTI); + if (CHECK(prog_cnt != cg_nr, "effect_cnt", "exp %d, got %d\n", + cg_nr, prog_cnt)) + goto cleanup; + for (i = 1; i < prog_cnt; i++) { + CHECK(prog_ids[i - 1] != prog_ids[i], "prog_id_check", + "idx %d, prev id %d, cur id %d\n", + i, prog_ids[i - 1], prog_ids[i]); + } + + /* detach bottom program and ping again */ + bpf_link__destroy(links[last_cg]); + links[last_cg] = NULL; + + ping_and_check(cg_nr - 1, 0); + + /* mix in with non link-based multi-attachments */ + err = bpf_prog_attach(prog_fd, cgs[last_cg].fd, + BPF_CGROUP_INET_EGRESS, BPF_F_ALLOW_MULTI); + if (CHECK(err, "cg_attach_legacy", "errno=%d\n", errno)) + goto cleanup; + detach_legacy = true; + + links[last_cg] = bpf_program__attach_cgroup(skel->progs.egress, + cgs[last_cg].fd); + if (CHECK(IS_ERR(links[last_cg]), "cg_attach", "err: %ld\n", + PTR_ERR(links[last_cg]))) + goto cleanup; + + ping_and_check(cg_nr + 1, 0); + + /* detach link */ + bpf_link__destroy(links[last_cg]); + links[last_cg] = NULL; + + /* detach legacy */ + err = bpf_prog_detach2(prog_fd, cgs[last_cg].fd, BPF_CGROUP_INET_EGRESS); + if (CHECK(err, "cg_detach_legacy", "errno=%d\n", errno)) + goto cleanup; + detach_legacy = false; + + /* attach legacy exclusive prog attachment */ + err = bpf_prog_attach(prog_fd, cgs[last_cg].fd, + BPF_CGROUP_INET_EGRESS, 0); + if (CHECK(err, "cg_attach_exclusive", "errno=%d\n", errno)) + goto cleanup; + detach_legacy = true; + + /* attempt to mix in with multi-attach bpf_link */ + tmp_link = bpf_program__attach_cgroup(skel->progs.egress, + cgs[last_cg].fd); + if (CHECK(!IS_ERR(tmp_link), "cg_attach_fail", "unexpected success!\n")) { + bpf_link__destroy(tmp_link); + goto cleanup; + } + + ping_and_check(cg_nr, 0); + + /* detach */ + err = bpf_prog_detach2(prog_fd, cgs[last_cg].fd, BPF_CGROUP_INET_EGRESS); + if (CHECK(err, "cg_detach_legacy", "errno=%d\n", errno)) + goto cleanup; + detach_legacy = false; + + ping_and_check(cg_nr - 1, 0); + + /* attach back link-based one */ + links[last_cg] = bpf_program__attach_cgroup(skel->progs.egress, + cgs[last_cg].fd); + if (CHECK(IS_ERR(links[last_cg]), "cg_attach", "err: %ld\n", + PTR_ERR(links[last_cg]))) + goto cleanup; + + ping_and_check(cg_nr, 0); + + /* check legacy exclusive prog can't be attached */ + err = bpf_prog_attach(prog_fd, cgs[last_cg].fd, + BPF_CGROUP_INET_EGRESS, 0); + if (CHECK(!err, "cg_attach_exclusive", "unexpected success")) { + bpf_prog_detach2(prog_fd, cgs[last_cg].fd, BPF_CGROUP_INET_EGRESS); + goto cleanup; + } + + /* replace BPF programs inside their links for all but first link */ + for (i = 1; i < cg_nr; i++) { + err = bpf_link__update_program(links[i], skel->progs.egress_alt); + if (CHECK(err, "prog_upd", "link #%d\n", i)) + goto cleanup; + } + + ping_and_check(1, cg_nr - 1); + + /* Attempt program update with wrong expected BPF program */ + link_upd_opts.old_prog_fd = bpf_program__fd(skel->progs.egress_alt); + link_upd_opts.flags = BPF_F_REPLACE; + err = bpf_link_update(bpf_link__fd(links[0]), + bpf_program__fd(skel->progs.egress_alt), + &link_upd_opts); + if (CHECK(err == 0 || errno != EPERM, "prog_cmpxchg1", + "unexpectedly succeeded, err %d, errno %d\n", err, -errno)) + goto cleanup; + + /* Compare-exchange single link program from egress to egress_alt */ + link_upd_opts.old_prog_fd = bpf_program__fd(skel->progs.egress); + link_upd_opts.flags = BPF_F_REPLACE; + err = bpf_link_update(bpf_link__fd(links[0]), + bpf_program__fd(skel->progs.egress_alt), + &link_upd_opts); + if (CHECK(err, "prog_cmpxchg2", "errno %d\n", -errno)) + goto cleanup; + + /* ping */ + ping_and_check(0, cg_nr); + + /* close cgroup FDs before detaching links */ + for (i = 0; i < cg_nr; i++) { + if (cgs[i].fd > 0) { + close(cgs[i].fd); + cgs[i].fd = -1; + } + } + + /* BPF programs should still get called */ + ping_and_check(0, cg_nr); + + /* leave cgroup and remove them, don't detach programs */ + cleanup_cgroup_environment(); + + /* BPF programs should have been auto-detached */ + ping_and_check(0, 0); + +cleanup: + if (detach_legacy) + bpf_prog_detach2(prog_fd, cgs[last_cg].fd, + BPF_CGROUP_INET_EGRESS); + + for (i = 0; i < cg_nr; i++) { + if (!IS_ERR(links[i])) + bpf_link__destroy(links[i]); + } + test_cgroup_link__destroy(skel); + + for (i = 0; i < cg_nr; i++) { + if (cgs[i].fd > 0) + close(cgs[i].fd); + } + cleanup_cgroup_environment(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c index eba9a970703b..925722217edf 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c +++ b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c @@ -82,6 +82,7 @@ static void get_stack_print_output(void *ctx, int cpu, void *data, __u32 size) void test_get_stack_raw_tp(void) { const char *file = "./test_get_stack_rawtp.o"; + const char *file_err = "./test_get_stack_rawtp_err.o"; const char *prog_name = "raw_tracepoint/sys_enter"; int i, err, prog_fd, exp_cnt = MAX_CNT_RAWTP; struct perf_buffer_opts pb_opts = {}; @@ -93,6 +94,10 @@ void test_get_stack_raw_tp(void) struct bpf_map *map; cpu_set_t cpu_set; + err = bpf_prog_load(file_err, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd); + if (CHECK(err >= 0, "prog_load raw tp", "err %d errno %d\n", err, errno)) + return; + err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd); if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno)) return; diff --git a/tools/testing/selftests/bpf/prog_tests/global_data_init.c b/tools/testing/selftests/bpf/prog_tests/global_data_init.c new file mode 100644 index 000000000000..3bdaa5a40744 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/global_data_init.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> + +void test_global_data_init(void) +{ + const char *file = "./test_global_data.o"; + int err = -ENOMEM, map_fd, zero = 0; + __u8 *buff = NULL, *newval = NULL; + struct bpf_object *obj; + struct bpf_map *map; + __u32 duration = 0; + size_t sz; + + obj = bpf_object__open_file(file, NULL); + if (CHECK_FAIL(!obj)) + return; + + map = bpf_object__find_map_by_name(obj, "test_glo.rodata"); + if (CHECK_FAIL(!map || !bpf_map__is_internal(map))) + goto out; + + sz = bpf_map__def(map)->value_size; + newval = malloc(sz); + if (CHECK_FAIL(!newval)) + goto out; + + memset(newval, 0, sz); + /* wrong size, should fail */ + err = bpf_map__set_initial_value(map, newval, sz - 1); + if (CHECK(!err, "reject set initial value wrong size", "err %d\n", err)) + goto out; + + err = bpf_map__set_initial_value(map, newval, sz); + if (CHECK(err, "set initial value", "err %d\n", err)) + goto out; + + err = bpf_object__load(obj); + if (CHECK_FAIL(err)) + goto out; + + map_fd = bpf_map__fd(map); + if (CHECK_FAIL(map_fd < 0)) + goto out; + + buff = malloc(sz); + if (buff) + err = bpf_map_lookup_elem(map_fd, &zero, buff); + if (CHECK(!buff || err || memcmp(buff, newval, sz), + "compare .rodata map data override", + "err %d errno %d\n", err, errno)) + goto out; + + memset(newval, 1, sz); + /* object loaded - should fail */ + err = bpf_map__set_initial_value(map, newval, sz); + CHECK(!err, "reject set initial value after load", "err %d\n", err); +out: + free(buff); + free(newval); + bpf_object__close(obj); +} diff --git a/tools/testing/selftests/bpf/prog_tests/sk_assign.c b/tools/testing/selftests/bpf/prog_tests/sk_assign.c new file mode 100644 index 000000000000..d572e1a2c297 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sk_assign.c @@ -0,0 +1,309 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Facebook +// Copyright (c) 2019 Cloudflare +// Copyright (c) 2020 Isovalent, Inc. +/* + * Test that the socket assign program is able to redirect traffic towards a + * socket, regardless of whether the port or address destination of the traffic + * matches the port. + */ + +#define _GNU_SOURCE +#include <fcntl.h> +#include <signal.h> +#include <stdlib.h> +#include <unistd.h> + +#include "test_progs.h" + +#define BIND_PORT 1234 +#define CONNECT_PORT 4321 +#define TEST_DADDR (0xC0A80203) +#define NS_SELF "/proc/self/ns/net" + +static const struct timeval timeo_sec = { .tv_sec = 3 }; +static const size_t timeo_optlen = sizeof(timeo_sec); +static int stop, duration; + +static bool +configure_stack(void) +{ + char tc_cmd[BUFSIZ]; + + /* Move to a new networking namespace */ + if (CHECK_FAIL(unshare(CLONE_NEWNET))) + return false; + + /* Configure necessary links, routes */ + if (CHECK_FAIL(system("ip link set dev lo up"))) + return false; + if (CHECK_FAIL(system("ip route add local default dev lo"))) + return false; + if (CHECK_FAIL(system("ip -6 route add local default dev lo"))) + return false; + + /* Load qdisc, BPF program */ + if (CHECK_FAIL(system("tc qdisc add dev lo clsact"))) + return false; + sprintf(tc_cmd, "%s %s %s %s", "tc filter add dev lo ingress bpf", + "direct-action object-file ./test_sk_assign.o", + "section classifier/sk_assign_test", + (env.verbosity < VERBOSE_VERY) ? " 2>/dev/null" : ""); + if (CHECK(system(tc_cmd), "BPF load failed;", + "run with -vv for more info\n")) + return false; + + return true; +} + +static int +start_server(const struct sockaddr *addr, socklen_t len, int type) +{ + int fd; + + fd = socket(addr->sa_family, type, 0); + if (CHECK_FAIL(fd == -1)) + goto out; + if (CHECK_FAIL(setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &timeo_sec, + timeo_optlen))) + goto close_out; + if (CHECK_FAIL(bind(fd, addr, len) == -1)) + goto close_out; + if (type == SOCK_STREAM && CHECK_FAIL(listen(fd, 128) == -1)) + goto close_out; + + goto out; +close_out: + close(fd); + fd = -1; +out: + return fd; +} + +static int +connect_to_server(const struct sockaddr *addr, socklen_t len, int type) +{ + int fd = -1; + + fd = socket(addr->sa_family, type, 0); + if (CHECK_FAIL(fd == -1)) + goto out; + if (CHECK_FAIL(setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, &timeo_sec, + timeo_optlen))) + goto close_out; + if (CHECK_FAIL(connect(fd, addr, len))) + goto close_out; + + goto out; +close_out: + close(fd); + fd = -1; +out: + return fd; +} + +static in_port_t +get_port(int fd) +{ + struct sockaddr_storage ss; + socklen_t slen = sizeof(ss); + in_port_t port = 0; + + if (CHECK_FAIL(getsockname(fd, (struct sockaddr *)&ss, &slen))) + return port; + + switch (ss.ss_family) { + case AF_INET: + port = ((struct sockaddr_in *)&ss)->sin_port; + break; + case AF_INET6: + port = ((struct sockaddr_in6 *)&ss)->sin6_port; + break; + default: + CHECK(1, "Invalid address family", "%d\n", ss.ss_family); + } + return port; +} + +static ssize_t +rcv_msg(int srv_client, int type) +{ + struct sockaddr_storage ss; + char buf[BUFSIZ]; + socklen_t slen; + + if (type == SOCK_STREAM) + return read(srv_client, &buf, sizeof(buf)); + else + return recvfrom(srv_client, &buf, sizeof(buf), 0, + (struct sockaddr *)&ss, &slen); +} + +static int +run_test(int server_fd, const struct sockaddr *addr, socklen_t len, int type) +{ + int client = -1, srv_client = -1; + char buf[] = "testing"; + in_port_t port; + int ret = 1; + + client = connect_to_server(addr, len, type); + if (client == -1) { + perror("Cannot connect to server"); + goto out; + } + + if (type == SOCK_STREAM) { + srv_client = accept(server_fd, NULL, NULL); + if (CHECK_FAIL(srv_client == -1)) { + perror("Can't accept connection"); + goto out; + } + } else { + srv_client = server_fd; + } + if (CHECK_FAIL(write(client, buf, sizeof(buf)) != sizeof(buf))) { + perror("Can't write on client"); + goto out; + } + if (CHECK_FAIL(rcv_msg(srv_client, type) != sizeof(buf))) { + perror("Can't read on server"); + goto out; + } + + port = get_port(srv_client); + if (CHECK_FAIL(!port)) + goto out; + /* SOCK_STREAM is connected via accept(), so the server's local address + * will be the CONNECT_PORT rather than the BIND port that corresponds + * to the listen socket. SOCK_DGRAM on the other hand is connectionless + * so we can't really do the same check there; the server doesn't ever + * create a socket with CONNECT_PORT. + */ + if (type == SOCK_STREAM && + CHECK(port != htons(CONNECT_PORT), "Expected", "port %u but got %u", + CONNECT_PORT, ntohs(port))) + goto out; + else if (type == SOCK_DGRAM && + CHECK(port != htons(BIND_PORT), "Expected", + "port %u but got %u", BIND_PORT, ntohs(port))) + goto out; + + ret = 0; +out: + close(client); + if (srv_client != server_fd) + close(srv_client); + if (ret) + WRITE_ONCE(stop, 1); + return ret; +} + +static void +prepare_addr(struct sockaddr *addr, int family, __u16 port, bool rewrite_addr) +{ + struct sockaddr_in *addr4; + struct sockaddr_in6 *addr6; + + switch (family) { + case AF_INET: + addr4 = (struct sockaddr_in *)addr; + memset(addr4, 0, sizeof(*addr4)); + addr4->sin_family = family; + addr4->sin_port = htons(port); + if (rewrite_addr) + addr4->sin_addr.s_addr = htonl(TEST_DADDR); + else + addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); + break; + case AF_INET6: + addr6 = (struct sockaddr_in6 *)addr; + memset(addr6, 0, sizeof(*addr6)); + addr6->sin6_family = family; + addr6->sin6_port = htons(port); + addr6->sin6_addr = in6addr_loopback; + if (rewrite_addr) + addr6->sin6_addr.s6_addr32[3] = htonl(TEST_DADDR); + break; + default: + fprintf(stderr, "Invalid family %d", family); + } +} + +struct test_sk_cfg { + const char *name; + int family; + struct sockaddr *addr; + socklen_t len; + int type; + bool rewrite_addr; +}; + +#define TEST(NAME, FAMILY, TYPE, REWRITE) \ +{ \ + .name = NAME, \ + .family = FAMILY, \ + .addr = (FAMILY == AF_INET) ? (struct sockaddr *)&addr4 \ + : (struct sockaddr *)&addr6, \ + .len = (FAMILY == AF_INET) ? sizeof(addr4) : sizeof(addr6), \ + .type = TYPE, \ + .rewrite_addr = REWRITE, \ +} + +void test_sk_assign(void) +{ + struct sockaddr_in addr4; + struct sockaddr_in6 addr6; + struct test_sk_cfg tests[] = { + TEST("ipv4 tcp port redir", AF_INET, SOCK_STREAM, false), + TEST("ipv4 tcp addr redir", AF_INET, SOCK_STREAM, true), + TEST("ipv6 tcp port redir", AF_INET6, SOCK_STREAM, false), + TEST("ipv6 tcp addr redir", AF_INET6, SOCK_STREAM, true), + TEST("ipv4 udp port redir", AF_INET, SOCK_DGRAM, false), + TEST("ipv4 udp addr redir", AF_INET, SOCK_DGRAM, true), + TEST("ipv6 udp port redir", AF_INET6, SOCK_DGRAM, false), + TEST("ipv6 udp addr redir", AF_INET6, SOCK_DGRAM, true), + }; + int server = -1; + int self_net; + + self_net = open(NS_SELF, O_RDONLY); + if (CHECK_FAIL(self_net < 0)) { + perror("Unable to open "NS_SELF); + return; + } + + if (!configure_stack()) { + perror("configure_stack"); + goto cleanup; + } + + for (int i = 0; i < ARRAY_SIZE(tests) && !READ_ONCE(stop); i++) { + struct test_sk_cfg *test = &tests[i]; + const struct sockaddr *addr; + + if (!test__start_subtest(test->name)) + continue; + prepare_addr(test->addr, test->family, BIND_PORT, false); + addr = (const struct sockaddr *)test->addr; + server = start_server(addr, test->len, test->type); + if (server == -1) + goto cleanup; + + /* connect to unbound ports */ + prepare_addr(test->addr, test->family, CONNECT_PORT, + test->rewrite_addr); + if (run_test(server, addr, test->len, test->type)) + goto close; + + close(server); + server = -1; + } + +close: + close(server); +cleanup: + if (CHECK_FAIL(setns(self_net, CLONE_NEWNET))) + perror("Failed to setns("NS_SELF")"); + close(self_net); +} diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c index e08f6bb17700..e56b52ab41da 100644 --- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c +++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c @@ -226,7 +226,7 @@ static void *server_thread(void *arg) return ERR_PTR(err); } - while (!server_done) { + while (true) { client_fd = accept(fd, (struct sockaddr *)&addr, &len); if (client_fd == -1 && errno == EAGAIN) { usleep(50); @@ -272,7 +272,7 @@ void test_tcp_rtt(void) CHECK_FAIL(run_test(cgroup_fd, server_fd)); server_done = true; - pthread_join(tid, &server_res); + CHECK_FAIL(pthread_join(tid, &server_res)); CHECK_FAIL(IS_ERR(server_res)); close_server_fd: diff --git a/tools/testing/selftests/bpf/prog_tests/test_lsm.c b/tools/testing/selftests/bpf/prog_tests/test_lsm.c new file mode 100644 index 000000000000..1e4c258de09d --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_lsm.c @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (C) 2020 Google LLC. + */ + +#include <test_progs.h> +#include <sys/mman.h> +#include <sys/wait.h> +#include <unistd.h> +#include <malloc.h> +#include <stdlib.h> + +#include "lsm.skel.h" + +char *CMD_ARGS[] = {"true", NULL}; + +int heap_mprotect(void) +{ + void *buf; + long sz; + int ret; + + sz = sysconf(_SC_PAGESIZE); + if (sz < 0) + return sz; + + buf = memalign(sz, 2 * sz); + if (buf == NULL) + return -ENOMEM; + + ret = mprotect(buf, sz, PROT_READ | PROT_WRITE | PROT_EXEC); + free(buf); + return ret; +} + +int exec_cmd(int *monitored_pid) +{ + int child_pid, child_status; + + child_pid = fork(); + if (child_pid == 0) { + *monitored_pid = getpid(); + execvp(CMD_ARGS[0], CMD_ARGS); + return -EINVAL; + } else if (child_pid > 0) { + waitpid(child_pid, &child_status, 0); + return child_status; + } + + return -EINVAL; +} + +void test_test_lsm(void) +{ + struct lsm *skel = NULL; + int err, duration = 0; + + skel = lsm__open_and_load(); + if (CHECK(!skel, "skel_load", "lsm skeleton failed\n")) + goto close_prog; + + err = lsm__attach(skel); + if (CHECK(err, "attach", "lsm attach failed: %d\n", err)) + goto close_prog; + + err = exec_cmd(&skel->bss->monitored_pid); + if (CHECK(err < 0, "exec_cmd", "err %d errno %d\n", err, errno)) + goto close_prog; + + CHECK(skel->bss->bprm_count != 1, "bprm_count", "bprm_count = %d\n", + skel->bss->bprm_count); + + skel->bss->monitored_pid = getpid(); + + err = heap_mprotect(); + if (CHECK(errno != EPERM, "heap_mprotect", "want errno=EPERM, got %d\n", + errno)) + goto close_prog; + + CHECK(skel->bss->mprotect_count != 1, "mprotect_count", + "mprotect_count = %d\n", skel->bss->mprotect_count); + +close_prog: + lsm__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/vmlinux.c b/tools/testing/selftests/bpf/prog_tests/vmlinux.c index 04939eda1325..72310cfc6474 100644 --- a/tools/testing/selftests/bpf/prog_tests/vmlinux.c +++ b/tools/testing/selftests/bpf/prog_tests/vmlinux.c @@ -11,7 +11,7 @@ static void nsleep() { struct timespec ts = { .tv_nsec = MY_TV_NSEC }; - (void)nanosleep(&ts, NULL); + (void)syscall(__NR_nanosleep, &ts, NULL); } void test_vmlinux(void) diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c new file mode 100644 index 000000000000..05b294d6b923 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> + +#define IFINDEX_LO 1 +#define XDP_FLAGS_REPLACE (1U << 4) + +void test_xdp_attach(void) +{ + struct bpf_object *obj1, *obj2, *obj3; + const char *file = "./test_xdp.o"; + int err, fd1, fd2, fd3; + __u32 duration = 0; + DECLARE_LIBBPF_OPTS(bpf_xdp_set_link_opts, opts, + .old_fd = -1); + + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj1, &fd1); + if (CHECK_FAIL(err)) + return; + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj2, &fd2); + if (CHECK_FAIL(err)) + goto out_1; + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj3, &fd3); + if (CHECK_FAIL(err)) + goto out_2; + + err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd1, XDP_FLAGS_REPLACE, + &opts); + if (CHECK(err, "load_ok", "initial load failed")) + goto out_close; + + err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd2, XDP_FLAGS_REPLACE, + &opts); + if (CHECK(!err, "load_fail", "load with expected id didn't fail")) + goto out; + + opts.old_fd = fd1; + err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd2, 0, &opts); + if (CHECK(err, "replace_ok", "replace valid old_fd failed")) + goto out; + + err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd3, 0, &opts); + if (CHECK(!err, "replace_fail", "replace invalid old_fd didn't fail")) + goto out; + + err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, 0, &opts); + if (CHECK(!err, "remove_fail", "remove invalid old_fd didn't fail")) + goto out; + + opts.old_fd = fd2; + err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, 0, &opts); + if (CHECK(err, "remove_ok", "remove valid old_fd failed")) + goto out; + +out: + bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0); +out_close: + bpf_object__close(obj3); +out_2: + bpf_object__close(obj2); +out_1: + bpf_object__close(obj1); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c index 127ea762a062..3fb4260570b1 100644 --- a/tools/testing/selftests/bpf/progs/bpf_dctcp.c +++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c @@ -6,6 +6,7 @@ * the kernel BPF logic. */ +#include <stddef.h> #include <linux/bpf.h> #include <linux/types.h> #include <bpf/bpf_helpers.h> @@ -14,6 +15,15 @@ char _license[] SEC("license") = "GPL"; +int stg_result = 0; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, int); +} sk_stg_map SEC(".maps"); + #define DCTCP_MAX_ALPHA 1024U struct dctcp { @@ -43,12 +53,18 @@ void BPF_PROG(dctcp_init, struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); struct dctcp *ca = inet_csk_ca(sk); + int *stg; ca->prior_rcv_nxt = tp->rcv_nxt; ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA); ca->loss_cwnd = 0; ca->ce_state = 0; + stg = bpf_sk_storage_get(&sk_stg_map, (void *)tp, NULL, 0); + if (stg) { + stg_result = *stg; + bpf_sk_storage_delete(&sk_stg_map, (void *)tp); + } dctcp_reset(tp, ca); } diff --git a/tools/testing/selftests/bpf/progs/lsm.c b/tools/testing/selftests/bpf/progs/lsm.c new file mode 100644 index 000000000000..a4e3c223028d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/lsm.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright 2020 Google LLC. + */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <errno.h> + +char _license[] SEC("license") = "GPL"; + +int monitored_pid = 0; +int mprotect_count = 0; +int bprm_count = 0; + +SEC("lsm/file_mprotect") +int BPF_PROG(test_int_hook, struct vm_area_struct *vma, + unsigned long reqprot, unsigned long prot, int ret) +{ + if (ret != 0) + return ret; + + __u32 pid = bpf_get_current_pid_tgid() >> 32; + int is_heap = 0; + + is_heap = (vma->vm_start >= vma->vm_mm->start_brk && + vma->vm_end <= vma->vm_mm->brk); + + if (is_heap && monitored_pid == pid) { + mprotect_count++; + ret = -EPERM; + } + + return ret; +} + +SEC("lsm/bprm_committed_creds") +int BPF_PROG(test_void_hook, struct linux_binprm *bprm) +{ + __u32 pid = bpf_get_current_pid_tgid() >> 32; + + if (monitored_pid == pid) + bprm_count++; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c index a5c6d5903b22..ca283af80d4e 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c @@ -12,7 +12,6 @@ int bpf_prog1(struct __sk_buff *skb) __u32 lport = skb->local_port; __u32 rport = skb->remote_port; __u8 *d = data; - __u32 len = (__u32) data_end - (__u32) data; int err; if (data + 10 > data_end) { diff --git a/tools/testing/selftests/bpf/progs/test_cgroup_link.c b/tools/testing/selftests/bpf/progs/test_cgroup_link.c new file mode 100644 index 000000000000..77e47b9e4446 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_cgroup_link.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +int calls = 0; +int alt_calls = 0; + +SEC("cgroup_skb/egress1") +int egress(struct __sk_buff *skb) +{ + __sync_fetch_and_add(&calls, 1); + return 1; +} + +SEC("cgroup_skb/egress2") +int egress_alt(struct __sk_buff *skb) +{ + __sync_fetch_and_add(&alt_calls, 1); + return 1; +} + +char _license[] SEC("license") = "GPL"; + diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp_err.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp_err.c new file mode 100644 index 000000000000..8941a41c2a55 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp_err.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +#define MAX_STACK_RAWTP 10 + +SEC("raw_tracepoint/sys_enter") +int bpf_prog2(void *ctx) +{ + __u64 stack[MAX_STACK_RAWTP]; + int error; + + /* set all the flags which should return -EINVAL */ + error = bpf_get_stack(ctx, stack, 0, -1); + if (error < 0) + goto loop; + + return error; +loop: + while (1) { + error++; + } +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_global_data.c b/tools/testing/selftests/bpf/progs/test_global_data.c index dd7a4d3dbc0d..1319be1c54ba 100644 --- a/tools/testing/selftests/bpf/progs/test_global_data.c +++ b/tools/testing/selftests/bpf/progs/test_global_data.c @@ -68,7 +68,7 @@ static struct foo struct3 = { bpf_map_update_elem(&result_##map, &key, var, 0); \ } while (0) -SEC("static_data_load") +SEC("classifier/static_data_load") int load_static_data(struct __sk_buff *skb) { static const __u64 bar = ~0; diff --git a/tools/testing/selftests/bpf/progs/test_sk_assign.c b/tools/testing/selftests/bpf/progs/test_sk_assign.c new file mode 100644 index 000000000000..8f530843b4da --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sk_assign.c @@ -0,0 +1,204 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Cloudflare Ltd. +// Copyright (c) 2020 Isovalent, Inc. + +#include <stddef.h> +#include <stdbool.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/pkt_cls.h> +#include <linux/tcp.h> +#include <sys/socket.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +int _version SEC("version") = 1; +char _license[] SEC("license") = "GPL"; + +/* Fill 'tuple' with L3 info, and attempt to find L4. On fail, return NULL. */ +static inline struct bpf_sock_tuple * +get_tuple(struct __sk_buff *skb, bool *ipv4, bool *tcp) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + struct bpf_sock_tuple *result; + struct ethhdr *eth; + __u64 tuple_len; + __u8 proto = 0; + __u64 ihl_len; + + eth = (struct ethhdr *)(data); + if (eth + 1 > data_end) + return NULL; + + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = (struct iphdr *)(data + sizeof(*eth)); + + if (iph + 1 > data_end) + return NULL; + if (iph->ihl != 5) + /* Options are not supported */ + return NULL; + ihl_len = iph->ihl * 4; + proto = iph->protocol; + *ipv4 = true; + result = (struct bpf_sock_tuple *)&iph->saddr; + } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { + struct ipv6hdr *ip6h = (struct ipv6hdr *)(data + sizeof(*eth)); + + if (ip6h + 1 > data_end) + return NULL; + ihl_len = sizeof(*ip6h); + proto = ip6h->nexthdr; + *ipv4 = false; + result = (struct bpf_sock_tuple *)&ip6h->saddr; + } else { + return (struct bpf_sock_tuple *)data; + } + + if (proto != IPPROTO_TCP && proto != IPPROTO_UDP) + return NULL; + + *tcp = (proto == IPPROTO_TCP); + return result; +} + +static inline int +handle_udp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, bool ipv4) +{ + struct bpf_sock_tuple ln = {0}; + struct bpf_sock *sk; + size_t tuple_len; + int ret; + + tuple_len = ipv4 ? sizeof(tuple->ipv4) : sizeof(tuple->ipv6); + if ((void *)tuple + tuple_len > (void *)(long)skb->data_end) + return TC_ACT_SHOT; + + sk = bpf_sk_lookup_udp(skb, tuple, tuple_len, BPF_F_CURRENT_NETNS, 0); + if (sk) + goto assign; + + if (ipv4) { + if (tuple->ipv4.dport != bpf_htons(4321)) + return TC_ACT_OK; + + ln.ipv4.daddr = bpf_htonl(0x7f000001); + ln.ipv4.dport = bpf_htons(1234); + + sk = bpf_sk_lookup_udp(skb, &ln, sizeof(ln.ipv4), + BPF_F_CURRENT_NETNS, 0); + } else { + if (tuple->ipv6.dport != bpf_htons(4321)) + return TC_ACT_OK; + + /* Upper parts of daddr are already zero. */ + ln.ipv6.daddr[3] = bpf_htonl(0x1); + ln.ipv6.dport = bpf_htons(1234); + + sk = bpf_sk_lookup_udp(skb, &ln, sizeof(ln.ipv6), + BPF_F_CURRENT_NETNS, 0); + } + + /* workaround: We can't do a single socket lookup here, because then + * the compiler will likely spill tuple_len to the stack. This makes it + * lose all bounds information in the verifier, which then rejects the + * call as unsafe. + */ + if (!sk) + return TC_ACT_SHOT; + +assign: + ret = bpf_sk_assign(skb, sk, 0); + bpf_sk_release(sk); + return ret; +} + +static inline int +handle_tcp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, bool ipv4) +{ + struct bpf_sock_tuple ln = {0}; + struct bpf_sock *sk; + size_t tuple_len; + int ret; + + tuple_len = ipv4 ? sizeof(tuple->ipv4) : sizeof(tuple->ipv6); + if ((void *)tuple + tuple_len > (void *)(long)skb->data_end) + return TC_ACT_SHOT; + + sk = bpf_skc_lookup_tcp(skb, tuple, tuple_len, BPF_F_CURRENT_NETNS, 0); + if (sk) { + if (sk->state != BPF_TCP_LISTEN) + goto assign; + bpf_sk_release(sk); + } + + if (ipv4) { + if (tuple->ipv4.dport != bpf_htons(4321)) + return TC_ACT_OK; + + ln.ipv4.daddr = bpf_htonl(0x7f000001); + ln.ipv4.dport = bpf_htons(1234); + + sk = bpf_skc_lookup_tcp(skb, &ln, sizeof(ln.ipv4), + BPF_F_CURRENT_NETNS, 0); + } else { + if (tuple->ipv6.dport != bpf_htons(4321)) + return TC_ACT_OK; + + /* Upper parts of daddr are already zero. */ + ln.ipv6.daddr[3] = bpf_htonl(0x1); + ln.ipv6.dport = bpf_htons(1234); + + sk = bpf_skc_lookup_tcp(skb, &ln, sizeof(ln.ipv6), + BPF_F_CURRENT_NETNS, 0); + } + + /* workaround: We can't do a single socket lookup here, because then + * the compiler will likely spill tuple_len to the stack. This makes it + * lose all bounds information in the verifier, which then rejects the + * call as unsafe. + */ + if (!sk) + return TC_ACT_SHOT; + + if (sk->state != BPF_TCP_LISTEN) { + bpf_sk_release(sk); + return TC_ACT_SHOT; + } + +assign: + ret = bpf_sk_assign(skb, sk, 0); + bpf_sk_release(sk); + return ret; +} + +SEC("classifier/sk_assign_test") +int bpf_sk_assign_test(struct __sk_buff *skb) +{ + struct bpf_sock_tuple *tuple, ln = {0}; + bool ipv4 = false; + bool tcp = false; + int tuple_len; + int ret = 0; + + tuple = get_tuple(skb, &ipv4, &tcp); + if (!tuple) + return TC_ACT_SHOT; + + /* Note that the verifier socket return type for bpf_skc_lookup_tcp() + * differs from bpf_sk_lookup_udp(), so even though the C-level type is + * the same here, if we try to share the implementations they will + * fail to verify because we're crossing pointer types. + */ + if (tcp) + ret = handle_tcp(skb, tuple, ipv4); + else + ret = handle_udp(skb, tuple, ipv4); + + return ret == 0 ? TC_ACT_OK : TC_ACT_SHOT; +} diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index f85a06512541..b521e0a512b6 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -1,12 +1,15 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2017 Facebook */ +#define _GNU_SOURCE #include "test_progs.h" #include "cgroup_helpers.h" #include "bpf_rlimit.h" #include <argp.h> -#include <string.h> +#include <pthread.h> +#include <sched.h> #include <signal.h> +#include <string.h> #include <execinfo.h> /* backtrace */ /* defined in test_progs.h */ @@ -35,16 +38,12 @@ struct prog_test_def { */ int usleep(useconds_t usec) { - struct timespec ts; - - if (usec > 999999) { - ts.tv_sec = usec / 1000000; - ts.tv_nsec = usec % 1000000; - } else { - ts.tv_sec = 0; - ts.tv_nsec = usec; - } - return nanosleep(&ts, NULL); + struct timespec ts = { + .tv_sec = usec / 1000000, + .tv_nsec = (usec % 1000000) * 1000, + }; + + return syscall(__NR_nanosleep, &ts, NULL); } static bool should_run(struct test_selector *sel, int num, const char *name) @@ -94,6 +93,34 @@ static void skip_account(void) } } +static void stdio_restore(void); + +/* A bunch of tests set custom affinity per-thread and/or per-process. Reset + * it after each test/sub-test. + */ +static void reset_affinity() { + + cpu_set_t cpuset; + int i, err; + + CPU_ZERO(&cpuset); + for (i = 0; i < env.nr_cpus; i++) + CPU_SET(i, &cpuset); + + err = sched_setaffinity(0, sizeof(cpuset), &cpuset); + if (err < 0) { + stdio_restore(); + fprintf(stderr, "Failed to reset process affinity: %d!\n", err); + exit(-1); + } + err = pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset); + if (err < 0) { + stdio_restore(); + fprintf(stderr, "Failed to reset thread affinity: %d!\n", err); + exit(-1); + } +} + void test__end_subtest() { struct prog_test_def *test = env.test; @@ -111,6 +138,8 @@ void test__end_subtest() test->test_num, test->subtest_num, test->subtest_name, sub_error_cnt ? "FAIL" : "OK"); + reset_affinity(); + free(test->subtest_name); test->subtest_name = NULL; } @@ -428,7 +457,7 @@ err: int parse_num_list(const char *s, struct test_selector *sel) { - int i, set_len = 0, num, start = 0, end = -1; + int i, set_len = 0, new_len, num, start = 0, end = -1; bool *set = NULL, *tmp, parsing_end = false; char *next; @@ -463,18 +492,19 @@ int parse_num_list(const char *s, struct test_selector *sel) return -EINVAL; if (end + 1 > set_len) { - set_len = end + 1; - tmp = realloc(set, set_len); + new_len = end + 1; + tmp = realloc(set, new_len); if (!tmp) { free(set); return -ENOMEM; } + for (i = set_len; i < start; i++) + tmp[i] = false; set = tmp; + set_len = new_len; } - for (i = start; i <= end; i++) { + for (i = start; i <= end; i++) set[i] = true; - } - } if (!set) @@ -682,6 +712,12 @@ int main(int argc, char **argv) srand(time(NULL)); env.jit_enabled = is_jit_enabled(); + env.nr_cpus = libbpf_num_possible_cpus(); + if (env.nr_cpus < 0) { + fprintf(stderr, "Failed to get number of CPUs: %d!\n", + env.nr_cpus); + return -1; + } stdio_hijack(); for (i = 0; i < prog_test_cnt; i++) { @@ -712,6 +748,7 @@ int main(int argc, char **argv) test->test_num, test->test_name, test->error_cnt ? "FAIL" : "OK"); + reset_affinity(); if (test->need_cgroup_cleanup) cleanup_cgroup_environment(); } diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index fd85fa61dbf7..f4aff6b8284b 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -71,6 +71,7 @@ struct test_env { FILE *stderr; char *log_buf; size_t log_cnt; + int nr_cpus; int succ_cnt; /* successful tests */ int sub_succ_cnt; /* successful sub-tests */ diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index 7f989b3e4e22..4d0e913bbb22 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -4,12 +4,15 @@ #include <string.h> #include <assert.h> #include <errno.h> +#include <fcntl.h> #include <poll.h> #include <unistd.h> #include <linux/perf_event.h> #include <sys/mman.h> #include "trace_helpers.h" +#define DEBUGFS "/sys/kernel/debug/tracing/" + #define MAX_SYMS 300000 static struct ksym syms[MAX_SYMS]; static int sym_cnt; @@ -86,3 +89,23 @@ long ksym_get_addr(const char *name) return 0; } + +void read_trace_pipe(void) +{ + int trace_fd; + + trace_fd = open(DEBUGFS "trace_pipe", O_RDONLY, 0); + if (trace_fd < 0) + return; + + while (1) { + static char buf[4096]; + ssize_t sz; + + sz = read(trace_fd, buf, sizeof(buf) - 1); + if (sz > 0) { + buf[sz] = 0; + puts(buf); + } + } +} diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h index 0383c9b8adc1..25ef597dd03f 100644 --- a/tools/testing/selftests/bpf/trace_helpers.h +++ b/tools/testing/selftests/bpf/trace_helpers.h @@ -12,5 +12,6 @@ struct ksym { int load_kallsyms(void); struct ksym *ksym_search(long key); long ksym_get_addr(const char *name); +void read_trace_pipe(void); #endif diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c index d55f476f2237..4d0d09574bf4 100644 --- a/tools/testing/selftests/bpf/verifier/bounds.c +++ b/tools/testing/selftests/bpf/verifier/bounds.c @@ -257,17 +257,15 @@ * [0x00ff'ffff'ff00'0000, 0x00ff'ffff'ffff'ffff] */ BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8), - /* no-op or OOB pointer computation */ + /* error on OOB pointer computation */ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), - /* potentially OOB access */ - BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), /* exit */ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, .fixup_map_hash_8b = { 3 }, /* not actually fully unbounded, but the bound is very high */ - .errstr = "R0 unbounded memory access", + .errstr = "value 72057594021150720 makes map_value pointer be out of bounds", .result = REJECT }, { @@ -299,17 +297,15 @@ * [0x00ff'ffff'ff00'0000, 0x00ff'ffff'ffff'ffff] */ BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8), - /* no-op or OOB pointer computation */ + /* error on OOB pointer computation */ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), - /* potentially OOB access */ - BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), /* exit */ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, .fixup_map_hash_8b = { 3 }, /* not actually fully unbounded, but the bound is very high */ - .errstr = "R0 unbounded memory access", + .errstr = "value 72057594021150720 makes map_value pointer be out of bounds", .result = REJECT }, { @@ -411,16 +407,14 @@ BPF_ALU32_IMM(BPF_RSH, BPF_REG_1, 31), /* r1 = 0xffff'fffe (NOT 0!) */ BPF_ALU32_IMM(BPF_SUB, BPF_REG_1, 2), - /* computes OOB pointer */ + /* error on computing OOB pointer */ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), - /* OOB access */ - BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), /* exit */ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, .fixup_map_hash_8b = { 3 }, - .errstr = "R0 invalid mem access", + .errstr = "math between map_value pointer and 4294967294 is not allowed", .result = REJECT, }, { @@ -506,3 +500,42 @@ .errstr = "map_value pointer and 1000000000000", .result = REJECT }, +{ + "bounds check mixed 32bit and 64bit arithmatic. test1", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_1, -1), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 32), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1), + /* r1 = 0xffffFFFF00000001 */ + BPF_JMP32_IMM(BPF_JGT, BPF_REG_1, 1, 3), + /* check ALU64 op keeps 32bit bounds */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1), + BPF_JMP32_IMM(BPF_JGT, BPF_REG_1, 2, 1), + BPF_JMP_A(1), + /* invalid ldx if bounds are lost above */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, -1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT +}, +{ + "bounds check mixed 32bit and 64bit arithmatic. test2", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_1, -1), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 32), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1), + /* r1 = 0xffffFFFF00000001 */ + BPF_MOV64_IMM(BPF_REG_2, 3), + /* r1 = 0x2 */ + BPF_ALU32_IMM(BPF_ADD, BPF_REG_1, 1), + /* check ALU32 op zero extends 64bit bounds */ + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 1), + BPF_JMP_A(1), + /* invalid ldx if bounds are lost above */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, -1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT +}, diff --git a/tools/testing/selftests/bpf/verifier/bpf_get_stack.c b/tools/testing/selftests/bpf/verifier/bpf_get_stack.c index f24d50f09dbe..69b048cf46d9 100644 --- a/tools/testing/selftests/bpf/verifier/bpf_get_stack.c +++ b/tools/testing/selftests/bpf/verifier/bpf_get_stack.c @@ -9,17 +9,17 @@ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 28), BPF_MOV64_REG(BPF_REG_7, BPF_REG_0), - BPF_MOV64_IMM(BPF_REG_9, sizeof(struct test_val)), + BPF_MOV64_IMM(BPF_REG_9, sizeof(struct test_val)/2), BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), - BPF_MOV64_IMM(BPF_REG_3, sizeof(struct test_val)), + BPF_MOV64_IMM(BPF_REG_3, sizeof(struct test_val)/2), BPF_MOV64_IMM(BPF_REG_4, 256), BPF_EMIT_CALL(BPF_FUNC_get_stack), BPF_MOV64_IMM(BPF_REG_1, 0), BPF_MOV64_REG(BPF_REG_8, BPF_REG_0), BPF_ALU64_IMM(BPF_LSH, BPF_REG_8, 32), BPF_ALU64_IMM(BPF_ARSH, BPF_REG_8, 32), - BPF_JMP_REG(BPF_JSLT, BPF_REG_1, BPF_REG_8, 16), + BPF_JMP_REG(BPF_JSGT, BPF_REG_1, BPF_REG_8, 16), BPF_ALU64_REG(BPF_SUB, BPF_REG_9, BPF_REG_8), BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_8), @@ -29,7 +29,7 @@ BPF_MOV64_REG(BPF_REG_3, BPF_REG_2), BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_1), BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), - BPF_MOV64_IMM(BPF_REG_5, sizeof(struct test_val)), + BPF_MOV64_IMM(BPF_REG_5, sizeof(struct test_val)/2), BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_5), BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 4), BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), diff --git a/tools/testing/selftests/bpf/verifier/ctx.c b/tools/testing/selftests/bpf/verifier/ctx.c index 92762c08f5e3..93d6b1641481 100644 --- a/tools/testing/selftests/bpf/verifier/ctx.c +++ b/tools/testing/selftests/bpf/verifier/ctx.c @@ -91,3 +91,108 @@ .result = REJECT, .errstr = "variable ctx access var_off=(0x0; 0x4)", }, +{ + "pass ctx or null check, 1: ctx", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_netns_cookie), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, + .result = ACCEPT, +}, +{ + "pass ctx or null check, 2: null", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_netns_cookie), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, + .result = ACCEPT, +}, +{ + "pass ctx or null check, 3: 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 1), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_netns_cookie), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, + .result = REJECT, + .errstr = "R1 type=inv expected=ctx", +}, +{ + "pass ctx or null check, 4: ctx - const", + .insns = { + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -612), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_netns_cookie), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, + .result = REJECT, + .errstr = "dereference of modified ctx ptr", +}, +{ + "pass ctx or null check, 5: null (connect)", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_netns_cookie), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + .expected_attach_type = BPF_CGROUP_INET4_CONNECT, + .result = ACCEPT, +}, +{ + "pass ctx or null check, 6: null (bind)", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_netns_cookie), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, + .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, + .result = ACCEPT, +}, +{ + "pass ctx or null check, 7: ctx (bind)", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_socket_cookie), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, + .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, + .result = ACCEPT, +}, +{ + "pass ctx or null check, 8: null (bind)", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_socket_cookie), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, + .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, + .result = REJECT, + .errstr = "R1 type=inv expected=ctx", +}, |