summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/bpf/map_sockmap.rst498
-rw-r--r--arch/x86/net/bpf_jit_comp.c70
-rw-r--r--include/linux/bpf.h16
-rw-r--r--include/linux/bpf_verifier.h40
-rw-r--r--include/uapi/linux/bpf.h4
-rw-r--r--kernel/bpf/bpf_local_storage.c4
-rw-r--r--kernel/bpf/btf.c21
-rw-r--r--kernel/bpf/helpers.c71
-rw-r--r--kernel/bpf/syscall.c1
-rw-r--r--kernel/bpf/verifier.c153
-rw-r--r--kernel/trace/bpf_trace.c56
-rw-r--r--net/core/filter.c5
-rw-r--r--samples/bpf/Makefile10
-rw-r--r--samples/bpf/gnu/stubs.h1
-rw-r--r--samples/bpf/map_perf_test.bpf.c (renamed from samples/bpf/map_perf_test_kern.c)48
-rw-r--r--samples/bpf/map_perf_test_user.c2
-rw-r--r--samples/bpf/test_current_task_under_cgroup.bpf.c (renamed from samples/bpf/test_current_task_under_cgroup_kern.c)11
-rw-r--r--samples/bpf/test_current_task_under_cgroup_user.c8
-rw-r--r--samples/bpf/test_lru_dist.c5
-rw-r--r--samples/bpf/test_map_in_map_kern.c1
-rw-r--r--samples/bpf/test_probe_write_user.bpf.c (renamed from samples/bpf/test_probe_write_user_kern.c)20
-rw-r--r--samples/bpf/test_probe_write_user_user.c2
-rw-r--r--samples/bpf/trace_common.h13
-rw-r--r--samples/bpf/trace_output.bpf.c (renamed from samples/bpf/trace_output_kern.c)6
-rw-r--r--samples/bpf/trace_output_user.c2
-rw-r--r--samples/bpf/tracex2.bpf.c (renamed from samples/bpf/tracex2_kern.c)13
-rw-r--r--samples/bpf/tracex2_user.c2
-rw-r--r--samples/bpf/tracex4_user.c4
-rw-r--r--tools/bpf/bpftool/Makefile3
-rw-r--r--tools/bpf/resolve_btfids/Makefile8
-rw-r--r--tools/include/uapi/linux/bpf.h4
-rw-r--r--tools/lib/bpf/bpf_tracing.h25
-rw-r--r--tools/lib/bpf/btf.c16
-rw-r--r--tools/lib/bpf/btf_dump.c199
-rw-r--r--tools/lib/bpf/libbpf.c2
-rw-r--r--tools/lib/bpf/libbpf.h29
-rw-r--r--tools/lib/bpf/libbpf.map3
-rw-r--r--tools/lib/bpf/libbpf_errno.c16
-rw-r--r--tools/lib/bpf/libbpf_internal.h1
-rw-r--r--tools/lib/bpf/libbpf_version.h2
-rw-r--r--tools/testing/selftests/bpf/DENYLIST.s390x1
-rw-r--r--tools/testing/selftests/bpf/Makefile3
-rw-r--r--tools/testing/selftests/bpf/prog_tests/jit_probe_mem.c28
-rw-r--r--tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c2
-rw-r--r--tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c80
-rw-r--r--tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c162
-rw-r--r--tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c36
-rw-r--r--tools/testing/selftests/bpf/progs/jit_probe_mem.c61
-rw-r--r--tools/testing/selftests/bpf/progs/test_tunnel_kern.c21
-rwxr-xr-xtools/testing/selftests/bpf/test_tunnel.sh40
50 files changed, 1454 insertions, 375 deletions
diff --git a/Documentation/bpf/map_sockmap.rst b/Documentation/bpf/map_sockmap.rst
new file mode 100644
index 000000000000..cc92047c6630
--- /dev/null
+++ b/Documentation/bpf/map_sockmap.rst
@@ -0,0 +1,498 @@
+.. SPDX-License-Identifier: GPL-2.0-only
+.. Copyright Red Hat
+
+==============================================
+BPF_MAP_TYPE_SOCKMAP and BPF_MAP_TYPE_SOCKHASH
+==============================================
+
+.. note::
+ - ``BPF_MAP_TYPE_SOCKMAP`` was introduced in kernel version 4.14
+ - ``BPF_MAP_TYPE_SOCKHASH`` was introduced in kernel version 4.18
+
+``BPF_MAP_TYPE_SOCKMAP`` and ``BPF_MAP_TYPE_SOCKHASH`` maps can be used to
+redirect skbs between sockets or to apply policy at the socket level based on
+the result of a BPF (verdict) program with the help of the BPF helpers
+``bpf_sk_redirect_map()``, ``bpf_sk_redirect_hash()``,
+``bpf_msg_redirect_map()`` and ``bpf_msg_redirect_hash()``.
+
+``BPF_MAP_TYPE_SOCKMAP`` is backed by an array that uses an integer key as the
+index to look up a reference to a ``struct sock``. The map values are socket
+descriptors. Similarly, ``BPF_MAP_TYPE_SOCKHASH`` is a hash backed BPF map that
+holds references to sockets via their socket descriptors.
+
+.. note::
+ The value type is either __u32 or __u64; the latter (__u64) is to support
+ returning socket cookies to userspace. Returning the ``struct sock *`` that
+ the map holds to user-space is neither safe nor useful.
+
+These maps may have BPF programs attached to them, specifically a parser program
+and a verdict program. The parser program determines how much data has been
+parsed and therefore how much data needs to be queued to come to a verdict. The
+verdict program is essentially the redirect program and can return a verdict
+of ``__SK_DROP``, ``__SK_PASS``, or ``__SK_REDIRECT``.
+
+When a socket is inserted into one of these maps, its socket callbacks are
+replaced and a ``struct sk_psock`` is attached to it. Additionally, this
+``sk_psock`` inherits the programs that are attached to the map.
+
+A sock object may be in multiple maps, but can only inherit a single
+parse or verdict program. If adding a sock object to a map would result
+in having multiple parser programs the update will return an EBUSY error.
+
+The supported programs to attach to these maps are:
+
+.. code-block:: c
+
+ struct sk_psock_progs {
+ struct bpf_prog *msg_parser;
+ struct bpf_prog *stream_parser;
+ struct bpf_prog *stream_verdict;
+ struct bpf_prog *skb_verdict;
+ };
+
+.. note::
+ Users are not allowed to attach ``stream_verdict`` and ``skb_verdict``
+ programs to the same map.
+
+The attach types for the map programs are:
+
+- ``msg_parser`` program - ``BPF_SK_MSG_VERDICT``.
+- ``stream_parser`` program - ``BPF_SK_SKB_STREAM_PARSER``.
+- ``stream_verdict`` program - ``BPF_SK_SKB_STREAM_VERDICT``.
+- ``skb_verdict`` program - ``BPF_SK_SKB_VERDICT``.
+
+There are additional helpers available to use with the parser and verdict
+programs: ``bpf_msg_apply_bytes()`` and ``bpf_msg_cork_bytes()``. With
+``bpf_msg_apply_bytes()`` BPF programs can tell the infrastructure how many
+bytes the given verdict should apply to. The helper ``bpf_msg_cork_bytes()``
+handles a different case where a BPF program cannot reach a verdict on a msg
+until it receives more bytes AND the program doesn't want to forward the packet
+until it is known to be good.
+
+Finally, the helpers ``bpf_msg_pull_data()`` and ``bpf_msg_push_data()`` are
+available to ``BPF_PROG_TYPE_SK_MSG`` BPF programs to pull in data and set the
+start and end pointers to given values or to add metadata to the ``struct
+sk_msg_buff *msg``.
+
+All these helpers will be described in more detail below.
+
+Usage
+=====
+Kernel BPF
+----------
+bpf_msg_redirect_map()
+^^^^^^^^^^^^^^^^^^^^^^
+.. code-block:: c
+
+ long bpf_msg_redirect_map(struct sk_msg_buff *msg, struct bpf_map *map, u32 key, u64 flags)
+
+This helper is used in programs implementing policies at the socket level. If
+the message ``msg`` is allowed to pass (i.e., if the verdict BPF program
+returns ``SK_PASS``), redirect it to the socket referenced by ``map`` (of type
+``BPF_MAP_TYPE_SOCKMAP``) at index ``key``. Both ingress and egress interfaces
+can be used for redirection. The ``BPF_F_INGRESS`` value in ``flags`` is used
+to select the ingress path otherwise the egress path is selected. This is the
+only flag supported for now.
+
+Returns ``SK_PASS`` on success, or ``SK_DROP`` on error.
+
+bpf_sk_redirect_map()
+^^^^^^^^^^^^^^^^^^^^^
+.. code-block:: c
+
+ long bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key u64 flags)
+
+Redirect the packet to the socket referenced by ``map`` (of type
+``BPF_MAP_TYPE_SOCKMAP``) at index ``key``. Both ingress and egress interfaces
+can be used for redirection. The ``BPF_F_INGRESS`` value in ``flags`` is used
+to select the ingress path otherwise the egress path is selected. This is the
+only flag supported for now.
+
+Returns ``SK_PASS`` on success, or ``SK_DROP`` on error.
+
+bpf_map_lookup_elem()
+^^^^^^^^^^^^^^^^^^^^^
+.. code-block:: c
+
+ void *bpf_map_lookup_elem(struct bpf_map *map, const void *key)
+
+socket entries of type ``struct sock *`` can be retrieved using the
+``bpf_map_lookup_elem()`` helper.
+
+bpf_sock_map_update()
+^^^^^^^^^^^^^^^^^^^^^
+.. code-block:: c
+
+ long bpf_sock_map_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
+
+Add an entry to, or update a ``map`` referencing sockets. The ``skops`` is used
+as a new value for the entry associated to ``key``. The ``flags`` argument can
+be one of the following:
+
+- ``BPF_ANY``: Create a new element or update an existing element.
+- ``BPF_NOEXIST``: Create a new element only if it did not exist.
+- ``BPF_EXIST``: Update an existing element.
+
+If the ``map`` has BPF programs (parser and verdict), those will be inherited
+by the socket being added. If the socket is already attached to BPF programs,
+this results in an error.
+
+Returns 0 on success, or a negative error in case of failure.
+
+bpf_sock_hash_update()
+^^^^^^^^^^^^^^^^^^^^^^
+.. code-block:: c
+
+ long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
+
+Add an entry to, or update a sockhash ``map`` referencing sockets. The ``skops``
+is used as a new value for the entry associated to ``key``.
+
+The ``flags`` argument can be one of the following:
+
+- ``BPF_ANY``: Create a new element or update an existing element.
+- ``BPF_NOEXIST``: Create a new element only if it did not exist.
+- ``BPF_EXIST``: Update an existing element.
+
+If the ``map`` has BPF programs (parser and verdict), those will be inherited
+by the socket being added. If the socket is already attached to BPF programs,
+this results in an error.
+
+Returns 0 on success, or a negative error in case of failure.
+
+bpf_msg_redirect_hash()
+^^^^^^^^^^^^^^^^^^^^^^^
+.. code-block:: c
+
+ long bpf_msg_redirect_hash(struct sk_msg_buff *msg, struct bpf_map *map, void *key, u64 flags)
+
+This helper is used in programs implementing policies at the socket level. If
+the message ``msg`` is allowed to pass (i.e., if the verdict BPF program returns
+``SK_PASS``), redirect it to the socket referenced by ``map`` (of type
+``BPF_MAP_TYPE_SOCKHASH``) using hash ``key``. Both ingress and egress
+interfaces can be used for redirection. The ``BPF_F_INGRESS`` value in
+``flags`` is used to select the ingress path otherwise the egress path is
+selected. This is the only flag supported for now.
+
+Returns ``SK_PASS`` on success, or ``SK_DROP`` on error.
+
+bpf_sk_redirect_hash()
+^^^^^^^^^^^^^^^^^^^^^^
+.. code-block:: c
+
+ long bpf_sk_redirect_hash(struct sk_buff *skb, struct bpf_map *map, void *key, u64 flags)
+
+This helper is used in programs implementing policies at the skb socket level.
+If the sk_buff ``skb`` is allowed to pass (i.e., if the verdict BPF program
+returns ``SK_PASS``), redirect it to the socket referenced by ``map`` (of type
+``BPF_MAP_TYPE_SOCKHASH``) using hash ``key``. Both ingress and egress
+interfaces can be used for redirection. The ``BPF_F_INGRESS`` value in
+``flags`` is used to select the ingress path otherwise the egress path is
+selected. This is the only flag supported for now.
+
+Returns ``SK_PASS`` on success, or ``SK_DROP`` on error.
+
+bpf_msg_apply_bytes()
+^^^^^^^^^^^^^^^^^^^^^^
+.. code-block:: c
+
+ long bpf_msg_apply_bytes(struct sk_msg_buff *msg, u32 bytes)
+
+For socket policies, apply the verdict of the BPF program to the next (number
+of ``bytes``) of message ``msg``. For example, this helper can be used in the
+following cases:
+
+- A single ``sendmsg()`` or ``sendfile()`` system call contains multiple
+ logical messages that the BPF program is supposed to read and for which it
+ should apply a verdict.
+- A BPF program only cares to read the first ``bytes`` of a ``msg``. If the
+ message has a large payload, then setting up and calling the BPF program
+ repeatedly for all bytes, even though the verdict is already known, would
+ create unnecessary overhead.
+
+Returns 0
+
+bpf_msg_cork_bytes()
+^^^^^^^^^^^^^^^^^^^^^^
+.. code-block:: c
+
+ long bpf_msg_cork_bytes(struct sk_msg_buff *msg, u32 bytes)
+
+For socket policies, prevent the execution of the verdict BPF program for
+message ``msg`` until the number of ``bytes`` have been accumulated.
+
+This can be used when one needs a specific number of bytes before a verdict can
+be assigned, even if the data spans multiple ``sendmsg()`` or ``sendfile()``
+calls.
+
+Returns 0
+
+bpf_msg_pull_data()
+^^^^^^^^^^^^^^^^^^^^^^
+.. code-block:: c
+
+ long bpf_msg_pull_data(struct sk_msg_buff *msg, u32 start, u32 end, u64 flags)
+
+For socket policies, pull in non-linear data from user space for ``msg`` and set
+pointers ``msg->data`` and ``msg->data_end`` to ``start`` and ``end`` bytes
+offsets into ``msg``, respectively.
+
+If a program of type ``BPF_PROG_TYPE_SK_MSG`` is run on a ``msg`` it can only
+parse data that the (``data``, ``data_end``) pointers have already consumed.
+For ``sendmsg()`` hooks this is likely the first scatterlist element. But for
+calls relying on the ``sendpage`` handler (e.g., ``sendfile()``) this will be
+the range (**0**, **0**) because the data is shared with user space and by
+default the objective is to avoid allowing user space to modify data while (or
+after) BPF verdict is being decided. This helper can be used to pull in data
+and to set the start and end pointers to given values. Data will be copied if
+necessary (i.e., if data was not linear and if start and end pointers do not
+point to the same chunk).
+
+A call to this helper is susceptible to change the underlying packet buffer.
+Therefore, at load time, all checks on pointers previously done by the verifier
+are invalidated and must be performed again, if the helper is used in
+combination with direct packet access.
+
+All values for ``flags`` are reserved for future usage, and must be left at
+zero.
+
+Returns 0 on success, or a negative error in case of failure.
+
+bpf_map_lookup_elem()
+^^^^^^^^^^^^^^^^^^^^^
+
+.. code-block:: c
+
+ void *bpf_map_lookup_elem(struct bpf_map *map, const void *key)
+
+Look up a socket entry in the sockmap or sockhash map.
+
+Returns the socket entry associated to ``key``, or NULL if no entry was found.
+
+bpf_map_update_elem()
+^^^^^^^^^^^^^^^^^^^^^
+.. code-block:: c
+
+ long bpf_map_update_elem(struct bpf_map *map, const void *key, const void *value, u64 flags)
+
+Add or update a socket entry in a sockmap or sockhash.
+
+The flags argument can be one of the following:
+
+- BPF_ANY: Create a new element or update an existing element.
+- BPF_NOEXIST: Create a new element only if it did not exist.
+- BPF_EXIST: Update an existing element.
+
+Returns 0 on success, or a negative error in case of failure.
+
+bpf_map_delete_elem()
+^^^^^^^^^^^^^^^^^^^^^^
+.. code-block:: c
+
+ long bpf_map_delete_elem(struct bpf_map *map, const void *key)
+
+Delete a socket entry from a sockmap or a sockhash.
+
+Returns 0 on success, or a negative error in case of failure.
+
+User space
+----------
+bpf_map_update_elem()
+^^^^^^^^^^^^^^^^^^^^^
+.. code-block:: c
+
+ int bpf_map_update_elem(int fd, const void *key, const void *value, __u64 flags)
+
+Sockmap entries can be added or updated using the ``bpf_map_update_elem()``
+function. The ``key`` parameter is the index value of the sockmap array. And the
+``value`` parameter is the FD value of that socket.
+
+Under the hood, the sockmap update function uses the socket FD value to
+retrieve the associated socket and its attached psock.
+
+The flags argument can be one of the following:
+
+- BPF_ANY: Create a new element or update an existing element.
+- BPF_NOEXIST: Create a new element only if it did not exist.
+- BPF_EXIST: Update an existing element.
+
+bpf_map_lookup_elem()
+^^^^^^^^^^^^^^^^^^^^^
+.. code-block:: c
+
+ int bpf_map_lookup_elem(int fd, const void *key, void *value)
+
+Sockmap entries can be retrieved using the ``bpf_map_lookup_elem()`` function.
+
+.. note::
+ The entry returned is a socket cookie rather than a socket itself.
+
+bpf_map_delete_elem()
+^^^^^^^^^^^^^^^^^^^^^
+.. code-block:: c
+
+ int bpf_map_delete_elem(int fd, const void *key)
+
+Sockmap entries can be deleted using the ``bpf_map_delete_elem()``
+function.
+
+Returns 0 on success, or negative error in case of failure.
+
+Examples
+========
+
+Kernel BPF
+----------
+Several examples of the use of sockmap APIs can be found in:
+
+- `tools/testing/selftests/bpf/progs/test_sockmap_kern.h`_
+- `tools/testing/selftests/bpf/progs/sockmap_parse_prog.c`_
+- `tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c`_
+- `tools/testing/selftests/bpf/progs/test_sockmap_listen.c`_
+- `tools/testing/selftests/bpf/progs/test_sockmap_update.c`_
+
+The following code snippet shows how to declare a sockmap.
+
+.. code-block:: c
+
+ struct {
+ __uint(type, BPF_MAP_TYPE_SOCKMAP);
+ __uint(max_entries, 1);
+ __type(key, __u32);
+ __type(value, __u64);
+ } sock_map_rx SEC(".maps");
+
+The following code snippet shows a sample parser program.
+
+.. code-block:: c
+
+ SEC("sk_skb/stream_parser")
+ int bpf_prog_parser(struct __sk_buff *skb)
+ {
+ return skb->len;
+ }
+
+The following code snippet shows a simple verdict program that interacts with a
+sockmap to redirect traffic to another socket based on the local port.
+
+.. code-block:: c
+
+ SEC("sk_skb/stream_verdict")
+ int bpf_prog_verdict(struct __sk_buff *skb)
+ {
+ __u32 lport = skb->local_port;
+ __u32 idx = 0;
+
+ if (lport == 10000)
+ return bpf_sk_redirect_map(skb, &sock_map_rx, idx, 0);
+
+ return SK_PASS;
+ }
+
+The following code snippet shows how to declare a sockhash map.
+
+.. code-block:: c
+
+ struct socket_key {
+ __u32 src_ip;
+ __u32 dst_ip;
+ __u32 src_port;
+ __u32 dst_port;
+ };
+
+ struct {
+ __uint(type, BPF_MAP_TYPE_SOCKHASH);
+ __uint(max_entries, 1);
+ __type(key, struct socket_key);
+ __type(value, __u64);
+ } sock_hash_rx SEC(".maps");
+
+The following code snippet shows a simple verdict program that interacts with a
+sockhash to redirect traffic to another socket based on a hash of some of the
+skb parameters.
+
+.. code-block:: c
+
+ static inline
+ void extract_socket_key(struct __sk_buff *skb, struct socket_key *key)
+ {
+ key->src_ip = skb->remote_ip4;
+ key->dst_ip = skb->local_ip4;
+ key->src_port = skb->remote_port >> 16;
+ key->dst_port = (bpf_htonl(skb->local_port)) >> 16;
+ }
+
+ SEC("sk_skb/stream_verdict")
+ int bpf_prog_verdict(struct __sk_buff *skb)
+ {
+ struct socket_key key;
+
+ extract_socket_key(skb, &key);
+
+ return bpf_sk_redirect_hash(skb, &sock_hash_rx, &key, 0);
+ }
+
+User space
+----------
+Several examples of the use of sockmap APIs can be found in:
+
+- `tools/testing/selftests/bpf/prog_tests/sockmap_basic.c`_
+- `tools/testing/selftests/bpf/test_sockmap.c`_
+- `tools/testing/selftests/bpf/test_maps.c`_
+
+The following code sample shows how to create a sockmap, attach a parser and
+verdict program, as well as add a socket entry.
+
+.. code-block:: c
+
+ int create_sample_sockmap(int sock, int parse_prog_fd, int verdict_prog_fd)
+ {
+ int index = 0;
+ int map, err;
+
+ map = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(int), sizeof(int), 1, NULL);
+ if (map < 0) {
+ fprintf(stderr, "Failed to create sockmap: %s\n", strerror(errno));
+ return -1;
+ }
+
+ err = bpf_prog_attach(parse_prog_fd, map, BPF_SK_SKB_STREAM_PARSER, 0);
+ if (err){
+ fprintf(stderr, "Failed to attach_parser_prog_to_map: %s\n", strerror(errno));
+ goto out;
+ }
+
+ err = bpf_prog_attach(verdict_prog_fd, map, BPF_SK_SKB_STREAM_VERDICT, 0);
+ if (err){
+ fprintf(stderr, "Failed to attach_verdict_prog_to_map: %s\n", strerror(errno));
+ goto out;
+ }
+
+ err = bpf_map_update_elem(map, &index, &sock, BPF_NOEXIST);
+ if (err) {
+ fprintf(stderr, "Failed to update sockmap: %s\n", strerror(errno));
+ goto out;
+ }
+
+ out:
+ close(map);
+ return err;
+ }
+
+References
+===========
+
+- https://github.com/jrfastab/linux-kernel-xdp/commit/c89fd73cb9d2d7f3c716c3e00836f07b1aeb261f
+- https://lwn.net/Articles/731133/
+- http://vger.kernel.org/lpc_net2018_talks/ktls_bpf_paper.pdf
+- https://lwn.net/Articles/748628/
+- https://lore.kernel.org/bpf/20200218171023.844439-7-jakub@cloudflare.com/
+
+.. _`tools/testing/selftests/bpf/progs/test_sockmap_kern.h`: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
+.. _`tools/testing/selftests/bpf/progs/sockmap_parse_prog.c`: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c
+.. _`tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c`: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
+.. _`tools/testing/selftests/bpf/prog_tests/sockmap_basic.c`: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+.. _`tools/testing/selftests/bpf/test_sockmap.c`: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/testing/selftests/bpf/test_sockmap.c
+.. _`tools/testing/selftests/bpf/test_maps.c`: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/testing/selftests/bpf/test_maps.c
+.. _`tools/testing/selftests/bpf/progs/test_sockmap_listen.c`: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
+.. _`tools/testing/selftests/bpf/progs/test_sockmap_update.c`: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/testing/selftests/bpf/progs/test_sockmap_update.c
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index b808be77635e..8db6077febdd 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1003,6 +1003,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
u8 b2 = 0, b3 = 0;
u8 *start_of_ldx;
s64 jmp_offset;
+ s16 insn_off;
u8 jmp_cond;
u8 *func;
int nops;
@@ -1369,57 +1370,52 @@ st: if (is_imm8(insn->off))
case BPF_LDX | BPF_PROBE_MEM | BPF_W:
case BPF_LDX | BPF_MEM | BPF_DW:
case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
+ insn_off = insn->off;
+
if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {
- /* Though the verifier prevents negative insn->off in BPF_PROBE_MEM
- * add abs(insn->off) to the limit to make sure that negative
- * offset won't be an issue.
- * insn->off is s16, so it won't affect valid pointers.
+ /* Conservatively check that src_reg + insn->off is a kernel address:
+ * src_reg + insn->off >= TASK_SIZE_MAX + PAGE_SIZE
+ * src_reg is used as scratch for src_reg += insn->off and restored
+ * after emit_ldx if necessary
*/
- u64 limit = TASK_SIZE_MAX + PAGE_SIZE + abs(insn->off);
- u8 *end_of_jmp1, *end_of_jmp2;
- /* Conservatively check that src_reg + insn->off is a kernel address:
- * 1. src_reg + insn->off >= limit
- * 2. src_reg + insn->off doesn't become small positive.
- * Cannot do src_reg + insn->off >= limit in one branch,
- * since it needs two spare registers, but JIT has only one.
+ u64 limit = TASK_SIZE_MAX + PAGE_SIZE;
+ u8 *end_of_jmp;
+
+ /* At end of these emitted checks, insn->off will have been added
+ * to src_reg, so no need to do relative load with insn->off offset
*/
+ insn_off = 0;
/* movabsq r11, limit */
EMIT2(add_1mod(0x48, AUX_REG), add_1reg(0xB8, AUX_REG));
EMIT((u32)limit, 4);
EMIT(limit >> 32, 4);
+
+ if (insn->off) {
+ /* add src_reg, insn->off */
+ maybe_emit_1mod(&prog, src_reg, true);
+ EMIT2_off32(0x81, add_1reg(0xC0, src_reg), insn->off);
+ }
+
/* cmp src_reg, r11 */
maybe_emit_mod(&prog, src_reg, AUX_REG, true);
EMIT2(0x39, add_2reg(0xC0, src_reg, AUX_REG));
- /* if unsigned '<' goto end_of_jmp2 */
- EMIT2(X86_JB, 0);
- end_of_jmp1 = prog;
-
- /* mov r11, src_reg */
- emit_mov_reg(&prog, true, AUX_REG, src_reg);
- /* add r11, insn->off */
- maybe_emit_1mod(&prog, AUX_REG, true);
- EMIT2_off32(0x81, add_1reg(0xC0, AUX_REG), insn->off);
- /* jmp if not carry to start_of_ldx
- * Otherwise ERR_PTR(-EINVAL) + 128 will be the user addr
- * that has to be rejected.
- */
- EMIT2(0x73 /* JNC */, 0);
- end_of_jmp2 = prog;
+
+ /* if unsigned '>=', goto load */
+ EMIT2(X86_JAE, 0);
+ end_of_jmp = prog;
/* xor dst_reg, dst_reg */
emit_mov_imm32(&prog, false, dst_reg, 0);
/* jmp byte_after_ldx */
EMIT2(0xEB, 0);
- /* populate jmp_offset for JB above to jump to xor dst_reg */
- end_of_jmp1[-1] = end_of_jmp2 - end_of_jmp1;
- /* populate jmp_offset for JNC above to jump to start_of_ldx */
+ /* populate jmp_offset for JAE above to jump to start_of_ldx */
start_of_ldx = prog;
- end_of_jmp2[-1] = start_of_ldx - end_of_jmp2;
+ end_of_jmp[-1] = start_of_ldx - end_of_jmp;
}
- emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off);
+ emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn_off);
if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {
struct exception_table_entry *ex;
u8 *_insn = image + proglen + (start_of_ldx - temp);
@@ -1428,6 +1424,18 @@ st: if (is_imm8(insn->off))
/* populate jmp_offset for JMP above */
start_of_ldx[-1] = prog - start_of_ldx;
+ if (insn->off && src_reg != dst_reg) {
+ /* sub src_reg, insn->off
+ * Restore src_reg after "add src_reg, insn->off" in prev
+ * if statement. But if src_reg == dst_reg, emit_ldx
+ * above already clobbered src_reg, so no need to restore.
+ * If add src_reg, insn->off was unnecessary, no need to
+ * restore either.
+ */
+ maybe_emit_1mod(&prog, src_reg, true);
+ EMIT2_off32(0x81, add_1reg(0xE8, src_reg), insn->off);
+ }
+
if (!bpf_prog->aux->extable)
break;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 3de24cfb7a3d..1697bd87fc06 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -189,7 +189,7 @@ struct btf_field_kptr {
u32 btf_id;
};
-struct btf_field_list_head {
+struct btf_field_graph_root {
struct btf *btf;
u32 value_btf_id;
u32 node_offset;
@@ -201,7 +201,7 @@ struct btf_field {
enum btf_field_type type;
union {
struct btf_field_kptr kptr;
- struct btf_field_list_head list_head;
+ struct btf_field_graph_root graph_root;
};
};
@@ -2795,10 +2795,18 @@ struct btf_id_set;
bool btf_id_set_contains(const struct btf_id_set *set, u32 id);
#define MAX_BPRINTF_VARARGS 12
+#define MAX_BPRINTF_BUF 1024
+
+struct bpf_bprintf_data {
+ u32 *bin_args;
+ char *buf;
+ bool get_bin_args;
+ bool get_buf;
+};
int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
- u32 **bin_buf, u32 num_args);
-void bpf_bprintf_cleanup(void);
+ u32 num_args, struct bpf_bprintf_data *data);
+void bpf_bprintf_cleanup(struct bpf_bprintf_data *data);
/* the implementation of the opaque uapi struct bpf_dynptr */
struct bpf_dynptr_kern {
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 53d175cbaa02..127058cfec47 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -92,6 +92,26 @@ struct bpf_reg_state {
u32 subprogno; /* for PTR_TO_FUNC */
};
+ /* For scalar types (SCALAR_VALUE), this represents our knowledge of
+ * the actual value.
+ * For pointer types, this represents the variable part of the offset
+ * from the pointed-to object, and is shared with all bpf_reg_states
+ * with the same id as us.
+ */
+ struct tnum var_off;
+ /* Used to determine if any memory access using this register will
+ * result in a bad access.
+ * These refer to the same value as var_off, not necessarily the actual
+ * contents of the register.
+ */
+ s64 smin_value; /* minimum possible (s64)value */
+ 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 */
/* For PTR_TO_PACKET, used to find other pointers with the same variable
* offset, so they can share range knowledge.
* For PTR_TO_MAP_VALUE_OR_NULL this is used to share which map value we
@@ -144,26 +164,6 @@ struct bpf_reg_state {
* allowed and has the same effect as bpf_sk_release(sk).
*/
u32 ref_obj_id;
- /* For scalar types (SCALAR_VALUE), this represents our knowledge of
- * the actual value.
- * For pointer types, this represents the variable part of the offset
- * from the pointed-to object, and is shared with all bpf_reg_states
- * with the same id as us.
- */
- struct tnum var_off;
- /* Used to determine if any memory access using this register will
- * result in a bad access.
- * These refer to the same value as var_off, not necessarily the actual
- * contents of the register.
- */
- s64 smin_value; /* minimum possible (s64)value */
- 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/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 464ca3f01fe7..bc1a3d232ae4 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2001,6 +2001,9 @@ union bpf_attr {
* sending the packet. This flag was added for GRE
* encapsulation, but might be used with other protocols
* as well in the future.
+ * **BPF_F_NO_TUNNEL_KEY**
+ * Add a flag to tunnel metadata indicating that no tunnel
+ * key should be set in the resulting tunnel header.
*
* Here is a typical usage on the transmit path:
*
@@ -5764,6 +5767,7 @@ enum {
BPF_F_ZERO_CSUM_TX = (1ULL << 1),
BPF_F_DONT_FRAGMENT = (1ULL << 2),
BPF_F_SEQ_NUMBER = (1ULL << 3),
+ BPF_F_NO_TUNNEL_KEY = (1ULL << 4),
};
/* BPF_FUNC_skb_get_tunnel_key flags. */
diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index b39a46e8fb08..373c3c2c75bc 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -580,8 +580,8 @@ static struct bpf_local_storage_map *__bpf_local_storage_map_alloc(union bpf_att
raw_spin_lock_init(&smap->buckets[i].lock);
}
- smap->elem_size =
- sizeof(struct bpf_local_storage_elem) + attr->value_size;
+ smap->elem_size = offsetof(struct bpf_local_storage_elem,
+ sdata.data[attr->value_size]);
return smap;
}
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index f7dd8af06413..578cee398550 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3228,7 +3228,7 @@ struct btf_field_info {
struct {
const char *node_name;
u32 value_btf_id;
- } list_head;
+ } graph_root;
};
};
@@ -3335,8 +3335,8 @@ static int btf_find_list_head(const struct btf *btf, const struct btf_type *pt,
return -EINVAL;
info->type = BPF_LIST_HEAD;
info->off = off;
- info->list_head.value_btf_id = id;
- info->list_head.node_name = list_node;
+ info->graph_root.value_btf_id = id;
+ info->graph_root.node_name = list_node;
return BTF_FIELD_FOUND;
}
@@ -3604,13 +3604,14 @@ static int btf_parse_list_head(const struct btf *btf, struct btf_field *field,
u32 offset;
int i;
- t = btf_type_by_id(btf, info->list_head.value_btf_id);
+ t = btf_type_by_id(btf, info->graph_root.value_btf_id);
/* We've already checked that value_btf_id is a struct type. We
* just need to figure out the offset of the list_node, and
* verify its type.
*/
for_each_member(i, t, member) {
- if (strcmp(info->list_head.node_name, __btf_name_by_offset(btf, member->name_off)))
+ if (strcmp(info->graph_root.node_name,
+ __btf_name_by_offset(btf, member->name_off)))
continue;
/* Invalid BTF, two members with same name */
if (n)
@@ -3627,9 +3628,9 @@ static int btf_parse_list_head(const struct btf *btf, struct btf_field *field,
if (offset % __alignof__(struct bpf_list_node))
return -EINVAL;
- field->list_head.btf = (struct btf *)btf;
- field->list_head.value_btf_id = info->list_head.value_btf_id;
- field->list_head.node_offset = offset;
+ field->graph_root.btf = (struct btf *)btf;
+ field->graph_root.value_btf_id = info->graph_root.value_btf_id;
+ field->graph_root.node_offset = offset;
}
if (!n)
return -ENOENT;
@@ -3736,11 +3737,11 @@ int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec)
if (!(rec->fields[i].type & BPF_LIST_HEAD))
continue;
- btf_id = rec->fields[i].list_head.value_btf_id;
+ btf_id = rec->fields[i].graph_root.value_btf_id;
meta = btf_find_struct_meta(btf, btf_id);
if (!meta)
return -EFAULT;
- rec->fields[i].list_head.value_rec = meta->record;
+ rec->fields[i].graph_root.value_rec = meta->record;
if (!(rec->field_mask & BPF_LIST_NODE))
continue;
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index af30c6cbd65d..458db2db2f81 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -756,19 +756,20 @@ static int bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype,
/* Per-cpu temp buffers used by printf-like helpers to store the bprintf binary
* arguments representation.
*/
-#define MAX_BPRINTF_BUF_LEN 512
+#define MAX_BPRINTF_BIN_ARGS 512
/* Support executing three nested bprintf helper calls on a given CPU */
#define MAX_BPRINTF_NEST_LEVEL 3
struct bpf_bprintf_buffers {
- char tmp_bufs[MAX_BPRINTF_NEST_LEVEL][MAX_BPRINTF_BUF_LEN];
+ char bin_args[MAX_BPRINTF_BIN_ARGS];
+ char buf[MAX_BPRINTF_BUF];
};
-static DEFINE_PER_CPU(struct bpf_bprintf_buffers, bpf_bprintf_bufs);
+
+static DEFINE_PER_CPU(struct bpf_bprintf_buffers[MAX_BPRINTF_NEST_LEVEL], bpf_bprintf_bufs);
static DEFINE_PER_CPU(int, bpf_bprintf_nest_level);
-static int try_get_fmt_tmp_buf(char **tmp_buf)
+static int try_get_buffers(struct bpf_bprintf_buffers **bufs)
{
- struct bpf_bprintf_buffers *bufs;
int nest_level;
preempt_disable();
@@ -778,18 +779,19 @@ static int try_get_fmt_tmp_buf(char **tmp_buf)
preempt_enable();
return -EBUSY;
}
- bufs = this_cpu_ptr(&bpf_bprintf_bufs);
- *tmp_buf = bufs->tmp_bufs[nest_level - 1];
+ *bufs = this_cpu_ptr(&bpf_bprintf_bufs[nest_level - 1]);
return 0;
}
-void bpf_bprintf_cleanup(void)
+void bpf_bprintf_cleanup(struct bpf_bprintf_data *data)
{
- if (this_cpu_read(bpf_bprintf_nest_level)) {
- this_cpu_dec(bpf_bprintf_nest_level);
- preempt_enable();
- }
+ if (!data->bin_args && !data->buf)
+ return;
+ if (WARN_ON_ONCE(this_cpu_read(bpf_bprintf_nest_level) == 0))
+ return;
+ this_cpu_dec(bpf_bprintf_nest_level);
+ preempt_enable();
}
/*
@@ -798,18 +800,20 @@ void bpf_bprintf_cleanup(void)
* Returns a negative value if fmt is an invalid format string or 0 otherwise.
*
* This can be used in two ways:
- * - Format string verification only: when bin_args is NULL
+ * - Format string verification only: when data->get_bin_args is false
* - Arguments preparation: in addition to the above verification, it writes in
- * bin_args a binary representation of arguments usable by bstr_printf where
- * pointers from BPF have been sanitized.
+ * data->bin_args a binary representation of arguments usable by bstr_printf
+ * where pointers from BPF have been sanitized.
*
* In argument preparation mode, if 0 is returned, safe temporary buffers are
* allocated and bpf_bprintf_cleanup should be called to free them after use.
*/
int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
- u32 **bin_args, u32 num_args)
+ u32 num_args, struct bpf_bprintf_data *data)
{
+ bool get_buffers = (data->get_bin_args && num_args) || data->get_buf;
char *unsafe_ptr = NULL, *tmp_buf = NULL, *tmp_buf_end, *fmt_end;
+ struct bpf_bprintf_buffers *buffers = NULL;
size_t sizeof_cur_arg, sizeof_cur_ip;
int err, i, num_spec = 0;
u64 cur_arg;
@@ -820,14 +824,19 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
return -EINVAL;
fmt_size = fmt_end - fmt;
- if (bin_args) {
- if (num_args && try_get_fmt_tmp_buf(&tmp_buf))
- return -EBUSY;
+ if (get_buffers && try_get_buffers(&buffers))
+ return -EBUSY;
- tmp_buf_end = tmp_buf + MAX_BPRINTF_BUF_LEN;
- *bin_args = (u32 *)tmp_buf;
+ if (data->get_bin_args) {
+ if (num_args)
+ tmp_buf = buffers->bin_args;
+ tmp_buf_end = tmp_buf + MAX_BPRINTF_BIN_ARGS;
+ data->bin_args = (u32 *)tmp_buf;
}
+ if (data->get_buf)
+ data->buf = buffers->buf;
+
for (i = 0; i < fmt_size; i++) {
if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) {
err = -EINVAL;
@@ -1021,31 +1030,33 @@ nocopy_fmt:
err = 0;
out:
if (err)
- bpf_bprintf_cleanup();
+ bpf_bprintf_cleanup(data);
return err;
}
BPF_CALL_5(bpf_snprintf, char *, str, u32, str_size, char *, fmt,
- const void *, data, u32, data_len)
+ const void *, args, u32, data_len)
{
+ struct bpf_bprintf_data data = {
+ .get_bin_args = true,
+ };
int err, num_args;
- u32 *bin_args;
if (data_len % 8 || data_len > MAX_BPRINTF_VARARGS * 8 ||
- (data_len && !data))
+ (data_len && !args))
return -EINVAL;
num_args = data_len / 8;
/* ARG_PTR_TO_CONST_STR guarantees that fmt is zero-terminated so we
* can safely give an unbounded size.
*/
- err = bpf_bprintf_prepare(fmt, UINT_MAX, data, &bin_args, num_args);
+ err = bpf_bprintf_prepare(fmt, UINT_MAX, args, num_args, &data);
if (err < 0)
return err;
- err = bstr_printf(str, str_size, fmt, bin_args);
+ err = bstr_printf(str, str_size, fmt, data.bin_args);
- bpf_bprintf_cleanup();
+ bpf_bprintf_cleanup(&data);
return err + 1;
}
@@ -1745,12 +1756,12 @@ unlock:
while (head != orig_head) {
void *obj = head;
- obj -= field->list_head.node_offset;
+ obj -= field->graph_root.node_offset;
head = head->next;
/* The contained type can also have resources, including a
* bpf_list_head which needs to be freed.
*/
- bpf_obj_free_fields(field->list_head.value_rec, obj);
+ bpf_obj_free_fields(field->graph_root.value_rec, obj);
/* bpf_mem_free requires migrate_disable(), since we can be
* called from map free path as well apart from BPF program (as
* part of map ops doing bpf_obj_free_fields).
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 64131f88c553..35ffd808f281 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -5319,7 +5319,6 @@ static struct ctl_table bpf_syscall_table[] = {
{
.procname = "bpf_stats_enabled",
.data = &bpf_stats_enabled_key.key,
- .maxlen = sizeof(bpf_stats_enabled_key),
.mode = 0644,
.proc_handler = bpf_stats_handler,
},
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a5255a0dcbb6..4a25375ebb0d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1402,9 +1402,11 @@ static void ___mark_reg_known(struct bpf_reg_state *reg, u64 imm)
*/
static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm)
{
- /* Clear id, off, and union(map_ptr, range) */
+ /* Clear off and union(map_ptr, range) */
memset(((u8 *)reg) + sizeof(reg->type), 0,
offsetof(struct bpf_reg_state, var_off) - sizeof(reg->type));
+ reg->id = 0;
+ reg->ref_obj_id = 0;
___mark_reg_known(reg, imm);
}
@@ -1750,11 +1752,13 @@ static void __mark_reg_unknown(const struct bpf_verifier_env *env,
struct bpf_reg_state *reg)
{
/*
- * Clear type, id, off, and union(map_ptr, range) and
+ * Clear type, off, and union(map_ptr, range) and
* padding between 'type' and union
*/
memset(reg, 0, offsetof(struct bpf_reg_state, var_off));
reg->type = SCALAR_VALUE;
+ reg->id = 0;
+ reg->ref_obj_id = 0;
reg->var_off = tnum_unknown;
reg->frameno = 0;
reg->precise = !env->bpf_capable;
@@ -7612,6 +7616,7 @@ static int check_bpf_snprintf_call(struct bpf_verifier_env *env,
struct bpf_reg_state *fmt_reg = &regs[BPF_REG_3];
struct bpf_reg_state *data_len_reg = &regs[BPF_REG_5];
struct bpf_map *fmt_map = fmt_reg->map_ptr;
+ struct bpf_bprintf_data data = {};
int err, fmt_map_off, num_args;
u64 fmt_addr;
char *fmt;
@@ -7636,7 +7641,7 @@ static int check_bpf_snprintf_call(struct bpf_verifier_env *env,
/* We are also guaranteed that fmt+fmt_map_off is NULL terminated, we
* can focus on validating the format specifiers.
*/
- err = bpf_bprintf_prepare(fmt, UINT_MAX, NULL, NULL, num_args);
+ err = bpf_bprintf_prepare(fmt, UINT_MAX, NULL, num_args, &data);
if (err < 0)
verbose(env, "Invalid format string\n");
@@ -8771,21 +8776,22 @@ static int process_kf_arg_ptr_to_list_node(struct bpf_verifier_env *env,
field = meta->arg_list_head.field;
- et = btf_type_by_id(field->list_head.btf, field->list_head.value_btf_id);
+ et = btf_type_by_id(field->graph_root.btf, field->graph_root.value_btf_id);
t = btf_type_by_id(reg->btf, reg->btf_id);
- if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, 0, field->list_head.btf,
- field->list_head.value_btf_id, true)) {
+ if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, 0, field->graph_root.btf,
+ field->graph_root.value_btf_id, true)) {
verbose(env, "operation on bpf_list_head expects arg#1 bpf_list_node at offset=%d "
"in struct %s, but arg is at offset=%d in struct %s\n",
- field->list_head.node_offset, btf_name_by_offset(field->list_head.btf, et->name_off),
+ field->graph_root.node_offset,
+ btf_name_by_offset(field->graph_root.btf, et->name_off),
list_node_off, btf_name_by_offset(reg->btf, t->name_off));
return -EINVAL;
}
- if (list_node_off != field->list_head.node_offset) {
+ if (list_node_off != field->graph_root.node_offset) {
verbose(env, "arg#1 offset=%d, but expected bpf_list_node at offset=%d in struct %s\n",
- list_node_off, field->list_head.node_offset,
- btf_name_by_offset(field->list_head.btf, et->name_off));
+ list_node_off, field->graph_root.node_offset,
+ btf_name_by_offset(field->graph_root.btf, et->name_off));
return -EINVAL;
}
/* Set arg#1 for expiration after unlock */
@@ -9227,9 +9233,9 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC;
- regs[BPF_REG_0].btf = field->list_head.btf;
- regs[BPF_REG_0].btf_id = field->list_head.value_btf_id;
- regs[BPF_REG_0].off = field->list_head.node_offset;
+ regs[BPF_REG_0].btf = field->graph_root.btf;
+ regs[BPF_REG_0].btf_id = field->graph_root.value_btf_id;
+ regs[BPF_REG_0].off = field->graph_root.node_offset;
} else if (meta.func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx]) {
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_TRUSTED;
@@ -12941,6 +12947,13 @@ static bool check_ids(u32 old_id, u32 cur_id, struct bpf_id_pair *idmap)
{
unsigned int i;
+ /* either both IDs should be set or both should be zero */
+ if (!!old_id != !!cur_id)
+ return false;
+
+ if (old_id == 0) /* cur_id == 0 as well */
+ return true;
+
for (i = 0; i < BPF_ID_MAP_SIZE; i++) {
if (!idmap[i].old) {
/* Reached an empty slot; haven't seen this id before */
@@ -13052,79 +13065,74 @@ next:
}
}
+static bool regs_exact(const struct bpf_reg_state *rold,
+ const struct bpf_reg_state *rcur,
+ struct bpf_id_pair *idmap)
+{
+ return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 &&
+ check_ids(rold->id, rcur->id, idmap) &&
+ check_ids(rold->ref_obj_id, rcur->ref_obj_id, idmap);
+}
+
/* Returns true if (rold safe implies rcur safe) */
static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
struct bpf_reg_state *rcur, struct bpf_id_pair *idmap)
{
- bool equal;
-
if (!(rold->live & REG_LIVE_READ))
/* explored state didn't use this */
return true;
-
- equal = memcmp(rold, rcur, offsetof(struct bpf_reg_state, parent)) == 0;
-
if (rold->type == NOT_INIT)
/* explored state can't have used this */
return true;
if (rcur->type == NOT_INIT)
return false;
+
+ /* Enforce that register types have to match exactly, including their
+ * modifiers (like PTR_MAYBE_NULL, MEM_RDONLY, etc), as a general
+ * rule.
+ *
+ * One can make a point that using a pointer register as unbounded
+ * SCALAR would be technically acceptable, but this could lead to
+ * pointer leaks because scalars are allowed to leak while pointers
+ * are not. We could make this safe in special cases if root is
+ * calling us, but it's probably not worth the hassle.
+ *
+ * Also, register types that are *not* MAYBE_NULL could technically be
+ * safe to use as their MAYBE_NULL variants (e.g., PTR_TO_MAP_VALUE
+ * is safe to be used as PTR_TO_MAP_VALUE_OR_NULL, provided both point
+ * to the same map).
+ * However, if the old MAYBE_NULL register then got NULL checked,
+ * doing so could have affected others with the same id, and we can't
+ * check for that because we lost the id when we converted to
+ * a non-MAYBE_NULL variant.
+ * So, as a general rule we don't allow mixing MAYBE_NULL and
+ * non-MAYBE_NULL registers as well.
+ */
+ if (rold->type != rcur->type)
+ return false;
+
switch (base_type(rold->type)) {
case SCALAR_VALUE:
- if (equal)
+ if (regs_exact(rold, rcur, idmap))
return true;
if (env->explore_alu_limits)
return false;
- if (rcur->type == SCALAR_VALUE) {
- if (!rold->precise)
- return true;
- /* new val must satisfy old val knowledge */
- return range_within(rold, rcur) &&
- tnum_in(rold->var_off, rcur->var_off);
- } else {
- /* We're trying to use a pointer in place of a scalar.
- * Even if the scalar was unbounded, this could lead to
- * pointer leaks because scalars are allowed to leak
- * while pointers are not. We could make this safe in
- * special cases if root is calling us, but it's
- * probably not worth the hassle.
- */
- return false;
- }
+ if (!rold->precise)
+ return true;
+ /* new val must satisfy old val knowledge */
+ return range_within(rold, rcur) &&
+ tnum_in(rold->var_off, rcur->var_off);
case PTR_TO_MAP_KEY:
case PTR_TO_MAP_VALUE:
- /* a PTR_TO_MAP_VALUE could be safe to use as a
- * PTR_TO_MAP_VALUE_OR_NULL into the same map.
- * However, if the old PTR_TO_MAP_VALUE_OR_NULL then got NULL-
- * checked, doing so could have affected others with the same
- * id, and we can't check for that because we lost the id when
- * we converted to a PTR_TO_MAP_VALUE.
- */
- if (type_may_be_null(rold->type)) {
- if (!type_may_be_null(rcur->type))
- return false;
- if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)))
- return false;
- /* Check our ids match any regs they're supposed to */
- return check_ids(rold->id, rcur->id, idmap);
- }
-
/* If the new min/max/var_off satisfy the old ones and
* everything else matches, we are OK.
- * 'id' is not compared, since it's only used for maps with
- * bpf_spin_lock inside map element and in such cases if
- * the rest of the prog is valid for one map element then
- * it's valid for all map elements regardless of the key
- * used in bpf_map_lookup()
*/
- return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 &&
+ return memcmp(rold, rcur, offsetof(struct bpf_reg_state, var_off)) == 0 &&
range_within(rold, rcur) &&
tnum_in(rold->var_off, rcur->var_off) &&
check_ids(rold->id, rcur->id, idmap);
case PTR_TO_PACKET_META:
case PTR_TO_PACKET:
- if (rcur->type != rold->type)
- return false;
/* We must have at least as much range as the old ptr
* did, so that any accesses which were safe before are
* still safe. This is true even if old range < old off,
@@ -13139,7 +13147,7 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
if (rold->off != rcur->off)
return false;
/* id relations must be preserved */
- if (rold->id && !check_ids(rold->id, rcur->id, idmap))
+ if (!check_ids(rold->id, rcur->id, idmap))
return false;
/* new val must satisfy old val knowledge */
return range_within(rold, rcur) &&
@@ -13148,15 +13156,10 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
/* two stack pointers are equal only if they're pointing to
* the same stack frame, since fp-8 in foo != fp-8 in bar
*/
- return equal && rold->frameno == rcur->frameno;
+ return regs_exact(rold, rcur, idmap) && rold->frameno == rcur->frameno;
default:
- /* Only valid matches are exact, which memcmp() */
- return equal;
+ return regs_exact(rold, rcur, idmap);
}
-
- /* Shouldn't get here; if we do, say it's not safe */
- WARN_ON_ONCE(1);
- return false;
}
static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
@@ -13222,12 +13225,20 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
return true;
}
-static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur)
+static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur,
+ struct bpf_id_pair *idmap)
{
+ int i;
+
if (old->acquired_refs != cur->acquired_refs)
return false;
- return !memcmp(old->refs, cur->refs,
- sizeof(*old->refs) * old->acquired_refs);
+
+ for (i = 0; i < old->acquired_refs; i++) {
+ if (!check_ids(old->refs[i].id, cur->refs[i].id, idmap))
+ return false;
+ }
+
+ return true;
}
/* compare two verifier states
@@ -13269,7 +13280,7 @@ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_stat
if (!stacksafe(env, old, cur, env->idmap_scratch))
return false;
- if (!refsafe(old, cur))
+ if (!refsafe(old, cur, env->idmap_scratch))
return false;
return true;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 3bbd3f0c810c..23ce498bca97 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -369,8 +369,6 @@ static const struct bpf_func_proto *bpf_get_probe_write_proto(void)
return &bpf_probe_write_user_proto;
}
-static DEFINE_RAW_SPINLOCK(trace_printk_lock);
-
#define MAX_TRACE_PRINTK_VARARGS 3
#define BPF_TRACE_PRINTK_SIZE 1024
@@ -378,23 +376,22 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
u64, arg2, u64, arg3)
{
u64 args[MAX_TRACE_PRINTK_VARARGS] = { arg1, arg2, arg3 };
- u32 *bin_args;
- static char buf[BPF_TRACE_PRINTK_SIZE];
- unsigned long flags;
+ struct bpf_bprintf_data data = {
+ .get_bin_args = true,
+ .get_buf = true,
+ };
int ret;
- ret = bpf_bprintf_prepare(fmt, fmt_size, args, &bin_args,
- MAX_TRACE_PRINTK_VARARGS);
+ ret = bpf_bprintf_prepare(fmt, fmt_size, args,
+ MAX_TRACE_PRINTK_VARARGS, &data);
if (ret < 0)
return ret;
- raw_spin_lock_irqsave(&trace_printk_lock, flags);
- ret = bstr_printf(buf, sizeof(buf), fmt, bin_args);
+ ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt, data.bin_args);
- trace_bpf_trace_printk(buf);
- raw_spin_unlock_irqrestore(&trace_printk_lock, flags);
+ trace_bpf_trace_printk(data.buf);
- bpf_bprintf_cleanup();
+ bpf_bprintf_cleanup(&data);
return ret;
}
@@ -427,30 +424,29 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
return &bpf_trace_printk_proto;
}
-BPF_CALL_4(bpf_trace_vprintk, char *, fmt, u32, fmt_size, const void *, data,
+BPF_CALL_4(bpf_trace_vprintk, char *, fmt, u32, fmt_size, const void *, args,
u32, data_len)
{
- static char buf[BPF_TRACE_PRINTK_SIZE];
- unsigned long flags;
+ struct bpf_bprintf_data data = {
+ .get_bin_args = true,
+ .get_buf = true,
+ };
int ret, num_args;
- u32 *bin_args;
if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 ||
- (data_len && !data))
+ (data_len && !args))
return -EINVAL;
num_args = data_len / 8;
- ret = bpf_bprintf_prepare(fmt, fmt_size, data, &bin_args, num_args);
+ ret = bpf_bprintf_prepare(fmt, fmt_size, args, num_args, &data);
if (ret < 0)
return ret;
- raw_spin_lock_irqsave(&trace_printk_lock, flags);
- ret = bstr_printf(buf, sizeof(buf), fmt, bin_args);
+ ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt, data.bin_args);
- trace_bpf_trace_printk(buf);
- raw_spin_unlock_irqrestore(&trace_printk_lock, flags);
+ trace_bpf_trace_printk(data.buf);
- bpf_bprintf_cleanup();
+ bpf_bprintf_cleanup(&data);
return ret;
}
@@ -472,23 +468,25 @@ const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void)
}
BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size,
- const void *, data, u32, data_len)
+ const void *, args, u32, data_len)
{
+ struct bpf_bprintf_data data = {
+ .get_bin_args = true,
+ };
int err, num_args;
- u32 *bin_args;
if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 ||
- (data_len && !data))
+ (data_len && !args))
return -EINVAL;
num_args = data_len / 8;
- err = bpf_bprintf_prepare(fmt, fmt_size, data, &bin_args, num_args);
+ err = bpf_bprintf_prepare(fmt, fmt_size, args, num_args, &data);
if (err < 0)
return err;
- seq_bprintf(m, fmt, bin_args);
+ seq_bprintf(m, fmt, data.bin_args);
- bpf_bprintf_cleanup();
+ bpf_bprintf_cleanup(&data);
return seq_has_overflowed(m) ? -EOVERFLOW : 0;
}
diff --git a/net/core/filter.c b/net/core/filter.c
index 929358677183..c746e4d77214 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4615,7 +4615,8 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb,
struct ip_tunnel_info *info;
if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX |
- BPF_F_DONT_FRAGMENT | BPF_F_SEQ_NUMBER)))
+ BPF_F_DONT_FRAGMENT | BPF_F_SEQ_NUMBER |
+ BPF_F_NO_TUNNEL_KEY)))
return -EINVAL;
if (unlikely(size != sizeof(struct bpf_tunnel_key))) {
switch (size) {
@@ -4653,6 +4654,8 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb,
info->key.tun_flags &= ~TUNNEL_CSUM;
if (flags & BPF_F_SEQ_NUMBER)
info->key.tun_flags |= TUNNEL_SEQ;
+ if (flags & BPF_F_NO_TUNNEL_KEY)
+ info->key.tun_flags &= ~TUNNEL_KEY;
info->key.tun_id = cpu_to_be64(from->tunnel_id);
info->key.tos = from->tunnel_tos;
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 727da3c5879b..22039a0a5b35 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -125,21 +125,21 @@ always-y += sockex1_kern.o
always-y += sockex2_kern.o
always-y += sockex3_kern.o
always-y += tracex1_kern.o
-always-y += tracex2_kern.o
+always-y += tracex2.bpf.o
always-y += tracex3_kern.o
always-y += tracex4_kern.o
always-y += tracex5_kern.o
always-y += tracex6_kern.o
always-y += tracex7_kern.o
always-y += sock_flags_kern.o
-always-y += test_probe_write_user_kern.o
-always-y += trace_output_kern.o
+always-y += test_probe_write_user.bpf.o
+always-y += trace_output.bpf.o
always-y += tcbpf1_kern.o
always-y += tc_l2_redirect_kern.o
always-y += lathist_kern.o
always-y += offwaketime_kern.o
always-y += spintest_kern.o
-always-y += map_perf_test_kern.o
+always-y += map_perf_test.bpf.o
always-y += test_overhead_tp_kern.o
always-y += test_overhead_raw_tp_kern.o
always-y += test_overhead_kprobe_kern.o
@@ -147,7 +147,7 @@ always-y += parse_varlen.o parse_simple.o parse_ldabs.o
always-y += test_cgrp2_tc_kern.o
always-y += xdp1_kern.o
always-y += xdp2_kern.o
-always-y += test_current_task_under_cgroup_kern.o
+always-y += test_current_task_under_cgroup.bpf.o
always-y += trace_event_kern.o
always-y += sampleip_kern.o
always-y += lwt_len_hist_kern.o
diff --git a/samples/bpf/gnu/stubs.h b/samples/bpf/gnu/stubs.h
new file mode 100644
index 000000000000..719225b16626
--- /dev/null
+++ b/samples/bpf/gnu/stubs.h
@@ -0,0 +1 @@
+/* dummy .h to trick /usr/include/features.h to work with 'clang -target bpf' */
diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test.bpf.c
index 7342c5b2f278..3cdeba2afe12 100644
--- a/samples/bpf/map_perf_test_kern.c
+++ b/samples/bpf/map_perf_test.bpf.c
@@ -4,14 +4,12 @@
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
-#include <linux/skbuff.h>
-#include <linux/netdevice.h>
+#include "vmlinux.h"
+#include <errno.h>
#include <linux/version.h>
-#include <uapi/linux/bpf.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
#include <bpf/bpf_core_read.h>
-#include "trace_common.h"
#define MAX_ENTRIES 1000
#define MAX_NR_CPUS 1024
@@ -102,8 +100,8 @@ struct {
__uint(max_entries, MAX_ENTRIES);
} lru_hash_lookup_map SEC(".maps");
-SEC("kprobe/" SYSCALL(sys_getuid))
-int stress_hmap(struct pt_regs *ctx)
+SEC("ksyscall/getuid")
+int BPF_KSYSCALL(stress_hmap)
{
u32 key = bpf_get_current_pid_tgid();
long init_val = 1;
@@ -120,8 +118,8 @@ int stress_hmap(struct pt_regs *ctx)
return 0;
}
-SEC("kprobe/" SYSCALL(sys_geteuid))
-int stress_percpu_hmap(struct pt_regs *ctx)
+SEC("ksyscall/geteuid")
+int BPF_KSYSCALL(stress_percpu_hmap)
{
u32 key = bpf_get_current_pid_tgid();
long init_val = 1;
@@ -137,8 +135,8 @@ int stress_percpu_hmap(struct pt_regs *ctx)
return 0;
}
-SEC("kprobe/" SYSCALL(sys_getgid))
-int stress_hmap_alloc(struct pt_regs *ctx)
+SEC("ksyscall/getgid")
+int BPF_KSYSCALL(stress_hmap_alloc)
{
u32 key = bpf_get_current_pid_tgid();
long init_val = 1;
@@ -154,8 +152,8 @@ int stress_hmap_alloc(struct pt_regs *ctx)
return 0;
}
-SEC("kprobe/" SYSCALL(sys_getegid))
-int stress_percpu_hmap_alloc(struct pt_regs *ctx)
+SEC("ksyscall/getegid")
+int BPF_KSYSCALL(stress_percpu_hmap_alloc)
{
u32 key = bpf_get_current_pid_tgid();
long init_val = 1;
@@ -170,11 +168,10 @@ int stress_percpu_hmap_alloc(struct pt_regs *ctx)
}
return 0;
}
-
-SEC("kprobe/" SYSCALL(sys_connect))
-int stress_lru_hmap_alloc(struct pt_regs *ctx)
+SEC("ksyscall/connect")
+int BPF_KSYSCALL(stress_lru_hmap_alloc, int fd, struct sockaddr_in *uservaddr,
+ int addrlen)
{
- struct pt_regs *real_regs = (struct pt_regs *)PT_REGS_PARM1_CORE(ctx);
char fmt[] = "Failed at stress_lru_hmap_alloc. ret:%dn";
union {
u16 dst6[8];
@@ -187,14 +184,11 @@ int stress_lru_hmap_alloc(struct pt_regs *ctx)
u32 key;
};
} test_params;
- struct sockaddr_in6 *in6;
+ struct sockaddr_in6 *in6 = (struct sockaddr_in6 *)uservaddr;
u16 test_case;
- int addrlen, ret;
long val = 1;
u32 key = 0;
-
- in6 = (struct sockaddr_in6 *)PT_REGS_PARM2_CORE(real_regs);
- addrlen = (int)PT_REGS_PARM3_CORE(real_regs);
+ int ret;
if (addrlen != sizeof(*in6))
return 0;
@@ -251,8 +245,8 @@ done:
return 0;
}
-SEC("kprobe/" SYSCALL(sys_gettid))
-int stress_lpm_trie_map_alloc(struct pt_regs *ctx)
+SEC("ksyscall/gettid")
+int BPF_KSYSCALL(stress_lpm_trie_map_alloc)
{
union {
u32 b32[2];
@@ -273,8 +267,8 @@ int stress_lpm_trie_map_alloc(struct pt_regs *ctx)
return 0;
}
-SEC("kprobe/" SYSCALL(sys_getpgid))
-int stress_hash_map_lookup(struct pt_regs *ctx)
+SEC("ksyscall/getpgid")
+int BPF_KSYSCALL(stress_hash_map_lookup)
{
u32 key = 1, i;
long *value;
@@ -286,8 +280,8 @@ int stress_hash_map_lookup(struct pt_regs *ctx)
return 0;
}
-SEC("kprobe/" SYSCALL(sys_getppid))
-int stress_array_map_lookup(struct pt_regs *ctx)
+SEC("ksyscall/getppid")
+int BPF_KSYSCALL(stress_array_map_lookup)
{
u32 key = 1, i;
long *value;
diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c
index 1bb53f4b29e1..d2fbcf963cdf 100644
--- a/samples/bpf/map_perf_test_user.c
+++ b/samples/bpf/map_perf_test_user.c
@@ -443,7 +443,7 @@ int main(int argc, char **argv)
if (argc > 4)
max_cnt = atoi(argv[4]);
- snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+ snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
obj = bpf_object__open_file(filename, NULL);
if (libbpf_get_error(obj)) {
fprintf(stderr, "ERROR: opening BPF object file failed\n");
diff --git a/samples/bpf/test_current_task_under_cgroup_kern.c b/samples/bpf/test_current_task_under_cgroup.bpf.c
index fbd43e2bb4d3..58b9cf7ed659 100644
--- a/samples/bpf/test_current_task_under_cgroup_kern.c
+++ b/samples/bpf/test_current_task_under_cgroup.bpf.c
@@ -5,12 +5,11 @@
* License as published by the Free Software Foundation.
*/
-#include <linux/ptrace.h>
-#include <uapi/linux/bpf.h>
+#include "vmlinux.h"
#include <linux/version.h>
#include <bpf/bpf_helpers.h>
-#include <uapi/linux/utsname.h>
-#include "trace_common.h"
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
struct {
__uint(type, BPF_MAP_TYPE_CGROUP_ARRAY);
@@ -27,8 +26,8 @@ struct {
} perf_map SEC(".maps");
/* Writes the last PID that called sync to a map at index 0 */
-SEC("kprobe/" SYSCALL(sys_sync))
-int bpf_prog1(struct pt_regs *ctx)
+SEC("ksyscall/sync")
+int BPF_KSYSCALL(bpf_prog1)
{
u64 pid = bpf_get_current_pid_tgid();
int idx = 0;
diff --git a/samples/bpf/test_current_task_under_cgroup_user.c b/samples/bpf/test_current_task_under_cgroup_user.c
index ac251a417f45..9726ed2a8a8b 100644
--- a/samples/bpf/test_current_task_under_cgroup_user.c
+++ b/samples/bpf/test_current_task_under_cgroup_user.c
@@ -14,14 +14,14 @@
int main(int argc, char **argv)
{
pid_t remote_pid, local_pid = getpid();
+ int cg2 = -1, idx = 0, rc = 1;
struct bpf_link *link = NULL;
struct bpf_program *prog;
- int cg2, idx = 0, rc = 1;
struct bpf_object *obj;
char filename[256];
int map_fd[2];
- snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+ snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
obj = bpf_object__open_file(filename, NULL);
if (libbpf_get_error(obj)) {
fprintf(stderr, "ERROR: opening BPF object file failed\n");
@@ -103,7 +103,9 @@ int main(int argc, char **argv)
rc = 0;
err:
- close(cg2);
+ if (cg2 != -1)
+ close(cg2);
+
cleanup_cgroup_environment();
cleanup:
diff --git a/samples/bpf/test_lru_dist.c b/samples/bpf/test_lru_dist.c
index 5efb91763d65..1c161276d57b 100644
--- a/samples/bpf/test_lru_dist.c
+++ b/samples/bpf/test_lru_dist.c
@@ -42,11 +42,6 @@ static inline void INIT_LIST_HEAD(struct list_head *list)
list->prev = list;
}
-static inline int list_empty(const struct list_head *head)
-{
- return head->next == head;
-}
-
static inline void __list_add(struct list_head *new,
struct list_head *prev,
struct list_head *next)
diff --git a/samples/bpf/test_map_in_map_kern.c b/samples/bpf/test_map_in_map_kern.c
index b0200c8eac09..0e17f9ade5c5 100644
--- a/samples/bpf/test_map_in_map_kern.c
+++ b/samples/bpf/test_map_in_map_kern.c
@@ -13,7 +13,6 @@
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
#include <bpf/bpf_core_read.h>
-#include "trace_common.h"
#define MAX_NR_PORTS 65536
diff --git a/samples/bpf/test_probe_write_user_kern.c b/samples/bpf/test_probe_write_user.bpf.c
index 220a96438d75..a4f3798b7fb0 100644
--- a/samples/bpf/test_probe_write_user_kern.c
+++ b/samples/bpf/test_probe_write_user.bpf.c
@@ -4,14 +4,12 @@
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
-#include <linux/skbuff.h>
-#include <linux/netdevice.h>
-#include <uapi/linux/bpf.h>
+#include "vmlinux.h"
+#include <string.h>
#include <linux/version.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
#include <bpf/bpf_core_read.h>
-#include "trace_common.h"
struct {
__uint(type, BPF_MAP_TYPE_HASH);
@@ -28,25 +26,23 @@ struct {
* This example sits on a syscall, and the syscall ABI is relatively stable
* of course, across platforms, and over time, the ABI may change.
*/
-SEC("kprobe/" SYSCALL(sys_connect))
-int bpf_prog1(struct pt_regs *ctx)
+SEC("ksyscall/connect")
+int BPF_KSYSCALL(bpf_prog1, int fd, struct sockaddr_in *uservaddr,
+ int addrlen)
{
- struct pt_regs *real_regs = (struct pt_regs *)PT_REGS_PARM1_CORE(ctx);
- void *sockaddr_arg = (void *)PT_REGS_PARM2_CORE(real_regs);
- int sockaddr_len = (int)PT_REGS_PARM3_CORE(real_regs);
struct sockaddr_in new_addr, orig_addr = {};
struct sockaddr_in *mapped_addr;
- if (sockaddr_len > sizeof(orig_addr))
+ if (addrlen > sizeof(orig_addr))
return 0;
- if (bpf_probe_read_user(&orig_addr, sizeof(orig_addr), sockaddr_arg) != 0)
+ if (bpf_probe_read_user(&orig_addr, sizeof(orig_addr), uservaddr) != 0)
return 0;
mapped_addr = bpf_map_lookup_elem(&dnat_map, &orig_addr);
if (mapped_addr != NULL) {
memcpy(&new_addr, mapped_addr, sizeof(new_addr));
- bpf_probe_write_user(sockaddr_arg, &new_addr,
+ bpf_probe_write_user(uservaddr, &new_addr,
sizeof(new_addr));
}
return 0;
diff --git a/samples/bpf/test_probe_write_user_user.c b/samples/bpf/test_probe_write_user_user.c
index 00ccfb834e45..2a539aec4116 100644
--- a/samples/bpf/test_probe_write_user_user.c
+++ b/samples/bpf/test_probe_write_user_user.c
@@ -24,7 +24,7 @@ int main(int ac, char **argv)
mapped_addr_in = (struct sockaddr_in *)&mapped_addr;
tmp_addr_in = (struct sockaddr_in *)&tmp_addr;
- snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+ snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
obj = bpf_object__open_file(filename, NULL);
if (libbpf_get_error(obj)) {
fprintf(stderr, "ERROR: opening BPF object file failed\n");
diff --git a/samples/bpf/trace_common.h b/samples/bpf/trace_common.h
deleted file mode 100644
index 8cb5400aed1f..000000000000
--- a/samples/bpf/trace_common.h
+++ /dev/null
@@ -1,13 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#ifndef __TRACE_COMMON_H
-#define __TRACE_COMMON_H
-
-#ifdef __x86_64__
-#define SYSCALL(SYS) "__x64_" __stringify(SYS)
-#elif defined(__s390x__)
-#define SYSCALL(SYS) "__s390x_" __stringify(SYS)
-#else
-#define SYSCALL(SYS) __stringify(SYS)
-#endif
-
-#endif
diff --git a/samples/bpf/trace_output_kern.c b/samples/bpf/trace_output.bpf.c
index b64815af0943..565a73b51b04 100644
--- a/samples/bpf/trace_output_kern.c
+++ b/samples/bpf/trace_output.bpf.c
@@ -1,8 +1,6 @@
-#include <linux/ptrace.h>
+#include "vmlinux.h"
#include <linux/version.h>
-#include <uapi/linux/bpf.h>
#include <bpf/bpf_helpers.h>
-#include "trace_common.h"
struct {
__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
@@ -11,7 +9,7 @@ struct {
__uint(max_entries, 2);
} my_map SEC(".maps");
-SEC("kprobe/" SYSCALL(sys_write))
+SEC("ksyscall/write")
int bpf_prog1(struct pt_regs *ctx)
{
struct S {
diff --git a/samples/bpf/trace_output_user.c b/samples/bpf/trace_output_user.c
index 371732f9cf8e..d316fd2c8e24 100644
--- a/samples/bpf/trace_output_user.c
+++ b/samples/bpf/trace_output_user.c
@@ -51,7 +51,7 @@ int main(int argc, char **argv)
char filename[256];
FILE *f;
- snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+ snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
obj = bpf_object__open_file(filename, NULL);
if (libbpf_get_error(obj)) {
fprintf(stderr, "ERROR: opening BPF object file failed\n");
diff --git a/samples/bpf/tracex2_kern.c b/samples/bpf/tracex2.bpf.c
index 93e0b7680b4f..0a5c75b367be 100644
--- a/samples/bpf/tracex2_kern.c
+++ b/samples/bpf/tracex2.bpf.c
@@ -4,13 +4,11 @@
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
-#include <linux/skbuff.h>
-#include <linux/netdevice.h>
+#include "vmlinux.h"
#include <linux/version.h>
-#include <uapi/linux/bpf.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
-#include "trace_common.h"
+#include <bpf/bpf_core_read.h>
struct {
__uint(type, BPF_MAP_TYPE_HASH);
@@ -78,15 +76,14 @@ struct {
__uint(max_entries, 1024);
} my_hist_map SEC(".maps");
-SEC("kprobe/" SYSCALL(sys_write))
-int bpf_prog3(struct pt_regs *ctx)
+SEC("ksyscall/write")
+int BPF_KSYSCALL(bpf_prog3, unsigned int fd, const char *buf, size_t count)
{
- long write_size = PT_REGS_PARM3(ctx);
long init_val = 1;
long *value;
struct hist_key key;
- key.index = log2l(write_size);
+ key.index = log2l(count);
key.pid_tgid = bpf_get_current_pid_tgid();
key.uid_gid = bpf_get_current_uid_gid();
bpf_get_current_comm(&key.comm, sizeof(key.comm));
diff --git a/samples/bpf/tracex2_user.c b/samples/bpf/tracex2_user.c
index 089e408abd7a..2131f1648cf1 100644
--- a/samples/bpf/tracex2_user.c
+++ b/samples/bpf/tracex2_user.c
@@ -123,7 +123,7 @@ int main(int ac, char **argv)
int i, j = 0;
FILE *f;
- snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+ snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
obj = bpf_object__open_file(filename, NULL);
if (libbpf_get_error(obj)) {
fprintf(stderr, "ERROR: opening BPF object file failed\n");
diff --git a/samples/bpf/tracex4_user.c b/samples/bpf/tracex4_user.c
index 227b05a0bc88..dee8f0a091ba 100644
--- a/samples/bpf/tracex4_user.c
+++ b/samples/bpf/tracex4_user.c
@@ -51,7 +51,7 @@ int main(int ac, char **argv)
struct bpf_program *prog;
struct bpf_object *obj;
char filename[256];
- int map_fd, i, j = 0;
+ int map_fd, j = 0;
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
obj = bpf_object__open_file(filename, NULL);
@@ -82,7 +82,7 @@ int main(int ac, char **argv)
j++;
}
- for (i = 0; ; i++) {
+ while (1) {
print_old_objects(map_fd);
sleep(1);
}
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 787b857d3fb5..313fd1b09189 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -289,3 +289,6 @@ FORCE:
.PHONY: all FORCE bootstrap clean install-bin install uninstall
.PHONY: doc doc-clean doc-install doc-uninstall
.DEFAULT_GOAL := all
+
+# Delete partially updated (corrupted) files on error
+.DELETE_ON_ERROR:
diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile
index 19a3112e271a..f7375a119f54 100644
--- a/tools/bpf/resolve_btfids/Makefile
+++ b/tools/bpf/resolve_btfids/Makefile
@@ -56,13 +56,17 @@ $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OU
DESTDIR=$(LIBBPF_DESTDIR) prefix= EXTRA_CFLAGS="$(CFLAGS)" \
$(abspath $@) install_headers
+LIBELF_FLAGS := $(shell $(HOSTPKG_CONFIG) libelf --cflags 2>/dev/null)
+LIBELF_LIBS := $(shell $(HOSTPKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf)
+
CFLAGS += -g \
-I$(srctree)/tools/include \
-I$(srctree)/tools/include/uapi \
-I$(LIBBPF_INCLUDE) \
- -I$(SUBCMD_SRC)
+ -I$(SUBCMD_SRC) \
+ $(LIBELF_FLAGS)
-LIBS = -lelf -lz
+LIBS = $(LIBELF_LIBS) -lz
export srctree OUTPUT CFLAGS Q
include $(srctree)/tools/build/Makefile.include
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 464ca3f01fe7..bc1a3d232ae4 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2001,6 +2001,9 @@ union bpf_attr {
* sending the packet. This flag was added for GRE
* encapsulation, but might be used with other protocols
* as well in the future.
+ * **BPF_F_NO_TUNNEL_KEY**
+ * Add a flag to tunnel metadata indicating that no tunnel
+ * key should be set in the resulting tunnel header.
*
* Here is a typical usage on the transmit path:
*
@@ -5764,6 +5767,7 @@ enum {
BPF_F_ZERO_CSUM_TX = (1ULL << 1),
BPF_F_DONT_FRAGMENT = (1ULL << 2),
BPF_F_SEQ_NUMBER = (1ULL << 3),
+ BPF_F_NO_TUNNEL_KEY = (1ULL << 4),
};
/* BPF_FUNC_skb_get_tunnel_key flags. */
diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index 2972dc25ff72..bdb0f6b5be84 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -32,6 +32,9 @@
#elif defined(__TARGET_ARCH_arc)
#define bpf_target_arc
#define bpf_target_defined
+#elif defined(__TARGET_ARCH_loongarch)
+ #define bpf_target_loongarch
+ #define bpf_target_defined
#else
/* Fall back to what the compiler says */
@@ -62,6 +65,9 @@
#elif defined(__arc__)
#define bpf_target_arc
#define bpf_target_defined
+#elif defined(__loongarch__)
+ #define bpf_target_loongarch
+ #define bpf_target_defined
#endif /* no compiler target */
#endif
@@ -137,7 +143,7 @@ struct pt_regs___s390 {
#define __PT_PARM3_REG gprs[4]
#define __PT_PARM4_REG gprs[5]
#define __PT_PARM5_REG gprs[6]
-#define __PT_RET_REG grps[14]
+#define __PT_RET_REG gprs[14]
#define __PT_FP_REG gprs[11] /* Works only with CONFIG_FRAME_POINTER */
#define __PT_RC_REG gprs[2]
#define __PT_SP_REG gprs[15]
@@ -258,6 +264,23 @@ struct pt_regs___arm64 {
/* arc does not select ARCH_HAS_SYSCALL_WRAPPER. */
#define PT_REGS_SYSCALL_REGS(ctx) ctx
+#elif defined(bpf_target_loongarch)
+
+/* https://loongson.github.io/LoongArch-Documentation/LoongArch-ELF-ABI-EN.html */
+
+#define __PT_PARM1_REG regs[4]
+#define __PT_PARM2_REG regs[5]
+#define __PT_PARM3_REG regs[6]
+#define __PT_PARM4_REG regs[7]
+#define __PT_PARM5_REG regs[8]
+#define __PT_RET_REG regs[1]
+#define __PT_FP_REG regs[22]
+#define __PT_RC_REG regs[4]
+#define __PT_SP_REG regs[3]
+#define __PT_IP_REG csr_era
+/* loongarch does not select ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ctx
+
#endif
#if defined(bpf_target_defined)
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 71e165b09ed5..64841117fbb2 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -688,8 +688,21 @@ int btf__align_of(const struct btf *btf, __u32 id)
if (align <= 0)
return libbpf_err(align);
max_align = max(max_align, align);
+
+ /* if field offset isn't aligned according to field
+ * type's alignment, then struct must be packed
+ */
+ if (btf_member_bitfield_size(t, i) == 0 &&
+ (m->offset % (8 * align)) != 0)
+ return 1;
}
+ /* if struct/union size isn't a multiple of its alignment,
+ * then struct must be packed
+ */
+ if ((t->size % max_align) != 0)
+ return 1;
+
return max_align;
}
default:
@@ -990,7 +1003,8 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
err = 0;
if (!btf_data) {
- err = -ENOENT;
+ pr_warn("failed to find '%s' ELF section in %s\n", BTF_ELF_SEC, path);
+ err = -ENODATA;
goto done;
}
btf = btf_new(btf_data->d_buf, btf_data->d_size, base_btf);
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index deb2bc9a0a7b..580985ee5545 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -13,6 +13,7 @@
#include <ctype.h>
#include <endian.h>
#include <errno.h>
+#include <limits.h>
#include <linux/err.h>
#include <linux/btf.h>
#include <linux/kernel.h>
@@ -833,14 +834,9 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id,
const struct btf_type *t)
{
const struct btf_member *m;
- int align, i, bit_sz;
+ int max_align = 1, align, i, bit_sz;
__u16 vlen;
- align = btf__align_of(btf, id);
- /* size of a non-packed struct has to be a multiple of its alignment*/
- if (align && t->size % align)
- return true;
-
m = btf_members(t);
vlen = btf_vlen(t);
/* all non-bitfield fields have to be naturally aligned */
@@ -849,8 +845,11 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id,
bit_sz = btf_member_bitfield_size(t, i);
if (align && bit_sz == 0 && m->offset % (8 * align) != 0)
return true;
+ max_align = max(align, max_align);
}
-
+ /* size of a non-packed struct has to be a multiple of its alignment */
+ if (t->size % max_align != 0)
+ return true;
/*
* if original struct was marked as packed, but its layout is
* naturally aligned, we'll detect that it's not packed
@@ -858,44 +857,97 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id,
return false;
}
-static int chip_away_bits(int total, int at_most)
-{
- return total % at_most ? : at_most;
-}
-
static void btf_dump_emit_bit_padding(const struct btf_dump *d,
- int cur_off, int m_off, int m_bit_sz,
- int align, int lvl)
+ int cur_off, int next_off, int next_align,
+ bool in_bitfield, int lvl)
{
- int off_diff = m_off - cur_off;
- int ptr_bits = d->ptr_sz * 8;
+ const struct {
+ const char *name;
+ int bits;
+ } pads[] = {
+ {"long", d->ptr_sz * 8}, {"int", 32}, {"short", 16}, {"char", 8}
+ };
+ int new_off, pad_bits, bits, i;
+ const char *pad_type;
+
+ if (cur_off >= next_off)
+ return; /* no gap */
+
+ /* For filling out padding we want to take advantage of
+ * natural alignment rules to minimize unnecessary explicit
+ * padding. First, we find the largest type (among long, int,
+ * short, or char) that can be used to force naturally aligned
+ * boundary. Once determined, we'll use such type to fill in
+ * the remaining padding gap. In some cases we can rely on
+ * compiler filling some gaps, but sometimes we need to force
+ * alignment to close natural alignment with markers like
+ * `long: 0` (this is always the case for bitfields). Note
+ * that even if struct itself has, let's say 4-byte alignment
+ * (i.e., it only uses up to int-aligned types), using `long:
+ * X;` explicit padding doesn't actually change struct's
+ * overall alignment requirements, but compiler does take into
+ * account that type's (long, in this example) natural
+ * alignment requirements when adding implicit padding. We use
+ * this fact heavily and don't worry about ruining correct
+ * struct alignment requirement.
+ */
+ for (i = 0; i < ARRAY_SIZE(pads); i++) {
+ pad_bits = pads[i].bits;
+ pad_type = pads[i].name;
- if (off_diff <= 0)
- /* no gap */
- return;
- if (m_bit_sz == 0 && off_diff < align * 8)
- /* natural padding will take care of a gap */
- return;
+ new_off = roundup(cur_off, pad_bits);
+ if (new_off <= next_off)
+ break;
+ }
- while (off_diff > 0) {
- const char *pad_type;
- int pad_bits;
-
- if (ptr_bits > 32 && off_diff > 32) {
- pad_type = "long";
- pad_bits = chip_away_bits(off_diff, ptr_bits);
- } else if (off_diff > 16) {
- pad_type = "int";
- pad_bits = chip_away_bits(off_diff, 32);
- } else if (off_diff > 8) {
- pad_type = "short";
- pad_bits = chip_away_bits(off_diff, 16);
- } else {
- pad_type = "char";
- pad_bits = chip_away_bits(off_diff, 8);
+ if (new_off > cur_off && new_off <= next_off) {
+ /* We need explicit `<type>: 0` aligning mark if next
+ * field is right on alignment offset and its
+ * alignment requirement is less strict than <type>'s
+ * alignment (so compiler won't naturally align to the
+ * offset we expect), or if subsequent `<type>: X`,
+ * will actually completely fit in the remaining hole,
+ * making compiler basically ignore `<type>: X`
+ * completely.
+ */
+ if (in_bitfield ||
+ (new_off == next_off && roundup(cur_off, next_align * 8) != new_off) ||
+ (new_off != next_off && next_off - new_off <= new_off - cur_off))
+ /* but for bitfields we'll emit explicit bit count */
+ btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type,
+ in_bitfield ? new_off - cur_off : 0);
+ cur_off = new_off;
+ }
+
+ /* Now we know we start at naturally aligned offset for a chosen
+ * padding type (long, int, short, or char), and so the rest is just
+ * a straightforward filling of remaining padding gap with full
+ * `<type>: sizeof(<type>);` markers, except for the last one, which
+ * might need smaller than sizeof(<type>) padding.
+ */
+ while (cur_off != next_off) {
+ bits = min(next_off - cur_off, pad_bits);
+ if (bits == pad_bits) {
+ btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, pad_bits);
+ cur_off += bits;
+ continue;
+ }
+ /* For the remainder padding that doesn't cover entire
+ * pad_type bit length, we pick the smallest necessary type.
+ * This is pure aesthetics, we could have just used `long`,
+ * but having smallest necessary one communicates better the
+ * scale of the padding gap.
+ */
+ for (i = ARRAY_SIZE(pads) - 1; i >= 0; i--) {
+ pad_type = pads[i].name;
+ pad_bits = pads[i].bits;
+ if (pad_bits < bits)
+ continue;
+
+ btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, bits);
+ cur_off += bits;
+ break;
}
- btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, pad_bits);
- off_diff -= pad_bits;
}
}
@@ -915,9 +967,11 @@ static void btf_dump_emit_struct_def(struct btf_dump *d,
{
const struct btf_member *m = btf_members(t);
bool is_struct = btf_is_struct(t);
- int align, i, packed, off = 0;
+ bool packed, prev_bitfield = false;
+ int align, i, off = 0;
__u16 vlen = btf_vlen(t);
+ align = btf__align_of(d->btf, id);
packed = is_struct ? btf_is_struct_packed(d->btf, id, t) : 0;
btf_dump_printf(d, "%s%s%s {",
@@ -927,41 +981,47 @@ static void btf_dump_emit_struct_def(struct btf_dump *d,
for (i = 0; i < vlen; i++, m++) {
const char *fname;
- int m_off, m_sz;
+ int m_off, m_sz, m_align;
+ bool in_bitfield;
fname = btf_name_of(d, m->name_off);
m_sz = btf_member_bitfield_size(t, i);
m_off = btf_member_bit_offset(t, i);
- align = packed ? 1 : btf__align_of(d->btf, m->type);
+ m_align = packed ? 1 : btf__align_of(d->btf, m->type);
+
+ in_bitfield = prev_bitfield && m_sz != 0;
- btf_dump_emit_bit_padding(d, off, m_off, m_sz, align, lvl + 1);
+ btf_dump_emit_bit_padding(d, off, m_off, m_align, in_bitfield, lvl + 1);
btf_dump_printf(d, "\n%s", pfx(lvl + 1));
btf_dump_emit_type_decl(d, m->type, fname, lvl + 1);
if (m_sz) {
btf_dump_printf(d, ": %d", m_sz);
off = m_off + m_sz;
+ prev_bitfield = true;
} else {
m_sz = max((__s64)0, btf__resolve_size(d->btf, m->type));
off = m_off + m_sz * 8;
+ prev_bitfield = false;
}
+
btf_dump_printf(d, ";");
}
/* pad at the end, if necessary */
- if (is_struct) {
- align = packed ? 1 : btf__align_of(d->btf, id);
- btf_dump_emit_bit_padding(d, off, t->size * 8, 0, align,
- lvl + 1);
- }
+ if (is_struct)
+ btf_dump_emit_bit_padding(d, off, t->size * 8, align, false, lvl + 1);
/*
* Keep `struct empty {}` on a single line,
* only print newline when there are regular or padding fields.
*/
- if (vlen || t->size)
+ if (vlen || t->size) {
btf_dump_printf(d, "\n");
- btf_dump_printf(d, "%s}", pfx(lvl));
+ btf_dump_printf(d, "%s}", pfx(lvl));
+ } else {
+ btf_dump_printf(d, "}");
+ }
if (packed)
btf_dump_printf(d, " __attribute__((packed))");
}
@@ -1073,6 +1133,43 @@ static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id,
else
btf_dump_emit_enum64_val(d, t, lvl, vlen);
btf_dump_printf(d, "\n%s}", pfx(lvl));
+
+ /* special case enums with special sizes */
+ if (t->size == 1) {
+ /* one-byte enums can be forced with mode(byte) attribute */
+ btf_dump_printf(d, " __attribute__((mode(byte)))");
+ } else if (t->size == 8 && d->ptr_sz == 8) {
+ /* enum can be 8-byte sized if one of the enumerator values
+ * doesn't fit in 32-bit integer, or by adding mode(word)
+ * attribute (but probably only on 64-bit architectures); do
+ * our best here to try to satisfy the contract without adding
+ * unnecessary attributes
+ */
+ bool needs_word_mode;
+
+ if (btf_is_enum(t)) {
+ /* enum can't represent 64-bit values, so we need word mode */
+ needs_word_mode = true;
+ } else {
+ /* enum64 needs mode(word) if none of its values has
+ * non-zero upper 32-bits (which means that all values
+ * fit in 32-bit integers and won't cause compiler to
+ * bump enum to be 64-bit naturally
+ */
+ int i;
+
+ needs_word_mode = true;
+ for (i = 0; i < vlen; i++) {
+ if (btf_enum64(t)[i].val_hi32 != 0) {
+ needs_word_mode = false;
+ break;
+ }
+ }
+ }
+ if (needs_word_mode)
+ btf_dump_printf(d, " __attribute__((mode(word)))");
+ }
+
}
static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id,
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 2a82f49ce16f..a5c67a3c93c5 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -9903,7 +9903,7 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name,
char errmsg[STRERR_BUFSIZE];
int type, pfd;
- if (ref_ctr_off >= (1ULL << PERF_UPROBE_REF_CTR_OFFSET_BITS))
+ if ((__u64)ref_ctr_off >= (1ULL << PERF_UPROBE_REF_CTR_OFFSET_BITS))
return -EINVAL;
memset(&attr, 0, attr_sz);
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index eee883f007f9..898db26e42e9 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -96,6 +96,12 @@ enum libbpf_print_level {
typedef int (*libbpf_print_fn_t)(enum libbpf_print_level level,
const char *, va_list ap);
+/**
+ * @brief **libbpf_set_print()** sets user-provided log callback function to
+ * be used for libbpf warnings and informational messages.
+ * @param fn The log print function. If NULL, libbpf won't print anything.
+ * @return Pointer to old print function.
+ */
LIBBPF_API libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn);
/* Hide internal to user */
@@ -174,6 +180,14 @@ struct bpf_object_open_opts {
};
#define bpf_object_open_opts__last_field kernel_log_level
+/**
+ * @brief **bpf_object__open()** creates a bpf_object by opening
+ * the BPF ELF object file pointed to by the passed path and loading it
+ * into memory.
+ * @param path BPF object file path.
+ * @return pointer to the new bpf_object; or NULL is returned on error,
+ * error code is stored in errno
+ */
LIBBPF_API struct bpf_object *bpf_object__open(const char *path);
/**
@@ -203,10 +217,21 @@ LIBBPF_API struct bpf_object *
bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz,
const struct bpf_object_open_opts *opts);
-/* Load/unload object into/from kernel */
+/**
+ * @brief **bpf_object__load()** loads BPF object into kernel.
+ * @param obj Pointer to a valid BPF object instance returned by
+ * **bpf_object__open*()** APIs
+ * @return 0, on success; negative error code, otherwise, error code is
+ * stored in errno
+ */
LIBBPF_API int bpf_object__load(struct bpf_object *obj);
-LIBBPF_API void bpf_object__close(struct bpf_object *object);
+/**
+ * @brief **bpf_object__close()** closes a BPF object and releases all
+ * resources.
+ * @param obj Pointer to a valid BPF object
+ */
+LIBBPF_API void bpf_object__close(struct bpf_object *obj);
/* pin_maps and unpin_maps can both be called with a NULL path, in which case
* they will use the pin_path attribute of each map (and ignore all maps that
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 71bf5691a689..11c36a3c1a9f 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -382,3 +382,6 @@ LIBBPF_1.1.0 {
user_ring_buffer__reserve_blocking;
user_ring_buffer__submit;
} LIBBPF_1.0.0;
+
+LIBBPF_1.2.0 {
+} LIBBPF_1.1.0;
diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c
index 96f67a772a1b..6b180172ec6b 100644
--- a/tools/lib/bpf/libbpf_errno.c
+++ b/tools/lib/bpf/libbpf_errno.c
@@ -39,14 +39,14 @@ static const char *libbpf_strerror_table[NR_ERRNO] = {
int libbpf_strerror(int err, char *buf, size_t size)
{
+ int ret;
+
if (!buf || !size)
return libbpf_err(-EINVAL);
err = err > 0 ? err : -err;
if (err < __LIBBPF_ERRNO__START) {
- int ret;
-
ret = strerror_r(err, buf, size);
buf[size - 1] = '\0';
return libbpf_err_errno(ret);
@@ -56,12 +56,20 @@ int libbpf_strerror(int err, char *buf, size_t size)
const char *msg;
msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
- snprintf(buf, size, "%s", msg);
+ ret = snprintf(buf, size, "%s", msg);
buf[size - 1] = '\0';
+ /* The length of the buf and msg is positive.
+ * A negative number may be returned only when the
+ * size exceeds INT_MAX. Not likely to appear.
+ */
+ if (ret >= size)
+ return libbpf_err(-ERANGE);
return 0;
}
- snprintf(buf, size, "Unknown libbpf error %d", err);
+ ret = snprintf(buf, size, "Unknown libbpf error %d", err);
buf[size - 1] = '\0';
+ if (ret >= size)
+ return libbpf_err(-ERANGE);
return libbpf_err(-ENOENT);
}
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 377642ff51fc..e4d05662a96c 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -543,6 +543,7 @@ static inline int ensure_good_fd(int fd)
fd = fcntl(fd, F_DUPFD_CLOEXEC, 3);
saved_errno = errno;
close(old_fd);
+ errno = saved_errno;
if (fd < 0) {
pr_warn("failed to dup FD %d to FD > 2: %d\n", old_fd, -saved_errno);
errno = saved_errno;
diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h
index e944f5bce728..1fd2eeac5cfc 100644
--- a/tools/lib/bpf/libbpf_version.h
+++ b/tools/lib/bpf/libbpf_version.h
@@ -4,6 +4,6 @@
#define __LIBBPF_VERSION_H
#define LIBBPF_MAJOR_VERSION 1
-#define LIBBPF_MINOR_VERSION 1
+#define LIBBPF_MINOR_VERSION 2
#endif /* __LIBBPF_VERSION_H */
diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x
index 585fcf73c731..3efe091255bf 100644
--- a/tools/testing/selftests/bpf/DENYLIST.s390x
+++ b/tools/testing/selftests/bpf/DENYLIST.s390x
@@ -26,6 +26,7 @@ get_func_args_test # trampoline
get_func_ip_test # get_func_ip_test__attach unexpected error: -524 (trampoline)
get_stack_raw_tp # user_stack corrupted user stack (no backchain userspace)
htab_update # failed to attach: ERROR: strerror_r(-524)=22 (trampoline)
+jit_probe_mem # jit_probe_mem__open_and_load unexpected error: -524 (kfunc)
kfree_skb # attach fentry unexpected error: -524 (trampoline)
kfunc_call # 'bpf_prog_active': not found in kernel BTF (?)
kfunc_dynptr_param # JIT does not support calling kernel function (kfunc)
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index c22c43bbee19..205e8c3c346a 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -626,3 +626,6 @@ EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) $(HOST_SCRATCH_DIR) \
liburandom_read.so)
.PHONY: docs docs-clean
+
+# Delete partially updated (corrupted) files on error
+.DELETE_ON_ERROR:
diff --git a/tools/testing/selftests/bpf/prog_tests/jit_probe_mem.c b/tools/testing/selftests/bpf/prog_tests/jit_probe_mem.c
new file mode 100644
index 000000000000..5639428607e6
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/jit_probe_mem.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <network_helpers.h>
+
+#include "jit_probe_mem.skel.h"
+
+void test_jit_probe_mem(void)
+{
+ LIBBPF_OPTS(bpf_test_run_opts, opts,
+ .data_in = &pkt_v4,
+ .data_size_in = sizeof(pkt_v4),
+ .repeat = 1,
+ );
+ struct jit_probe_mem *skel;
+ int ret;
+
+ skel = jit_probe_mem__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "jit_probe_mem__open_and_load"))
+ return;
+
+ ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_jit_probe_mem), &opts);
+ ASSERT_OK(ret, "jit_probe_mem ret");
+ ASSERT_OK(opts.retval, "jit_probe_mem opts.retval");
+ ASSERT_EQ(skel->data->total_sum, 192, "jit_probe_mem total_sum");
+
+ jit_probe_mem__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c
index e5560a656030..e01690618e1e 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c
@@ -53,7 +53,7 @@ struct bitfields_only_mixed_types {
*/
/* ------ END-EXPECTED-OUTPUT ------ */
struct bitfield_mixed_with_others {
- long: 4; /* char is enough as a backing field */
+ char: 4; /* char is enough as a backing field */
int a: 4;
/* 8-bit implicit padding */
short b; /* combined with previous bitfield */
diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c
index e304b6204bd9..7998f27df7dd 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c
@@ -58,7 +58,81 @@ union jump_code_union {
} __attribute__((packed));
};
-/*------ END-EXPECTED-OUTPUT ------ */
+/* ----- START-EXPECTED-OUTPUT ----- */
+/*
+ *struct nested_packed_but_aligned_struct {
+ * int x1;
+ * int x2;
+ *};
+ *
+ *struct outer_implicitly_packed_struct {
+ * char y1;
+ * struct nested_packed_but_aligned_struct y2;
+ *} __attribute__((packed));
+ *
+ */
+/* ------ END-EXPECTED-OUTPUT ------ */
+
+struct nested_packed_but_aligned_struct {
+ int x1;
+ int x2;
+} __attribute__((packed));
+
+struct outer_implicitly_packed_struct {
+ char y1;
+ struct nested_packed_but_aligned_struct y2;
+};
+/* ----- START-EXPECTED-OUTPUT ----- */
+/*
+ *struct usb_ss_ep_comp_descriptor {
+ * char: 8;
+ * char bDescriptorType;
+ * char bMaxBurst;
+ * short wBytesPerInterval;
+ *};
+ *
+ *struct usb_host_endpoint {
+ * long: 64;
+ * char: 8;
+ * struct usb_ss_ep_comp_descriptor ss_ep_comp;
+ * long: 0;
+ *} __attribute__((packed));
+ *
+ */
+/* ------ END-EXPECTED-OUTPUT ------ */
+
+struct usb_ss_ep_comp_descriptor {
+ char: 8;
+ char bDescriptorType;
+ char bMaxBurst;
+ int: 0;
+ short wBytesPerInterval;
+} __attribute__((packed));
+
+struct usb_host_endpoint {
+ long: 64;
+ char: 8;
+ struct usb_ss_ep_comp_descriptor ss_ep_comp;
+ long: 0;
+};
+
+/* ----- START-EXPECTED-OUTPUT ----- */
+struct nested_packed_struct {
+ int a;
+ char b;
+} __attribute__((packed));
+
+struct outer_nonpacked_struct {
+ short a;
+ struct nested_packed_struct b;
+};
+
+struct outer_packed_struct {
+ short a;
+ struct nested_packed_struct b;
+} __attribute__((packed));
+
+/* ------ END-EXPECTED-OUTPUT ------ */
int f(struct {
struct packed_trailing_space _1;
@@ -69,6 +143,10 @@ int f(struct {
union union_is_never_packed _6;
union union_does_not_need_packing _7;
union jump_code_union _8;
+ struct outer_implicitly_packed_struct _9;
+ struct usb_host_endpoint _10;
+ struct outer_nonpacked_struct _11;
+ struct outer_packed_struct _12;
} *_)
{
return 0;
diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c
index 7cb522d22a66..79276fbe454a 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c
@@ -19,7 +19,7 @@ struct padded_implicitly {
/*
*struct padded_explicitly {
* int a;
- * int: 32;
+ * long: 0;
* int b;
*};
*
@@ -28,41 +28,28 @@ struct padded_implicitly {
struct padded_explicitly {
int a;
- int: 1; /* algo will explicitly pad with full 32 bits here */
+ int: 1; /* algo will emit aligning `long: 0;` here */
int b;
};
/* ----- START-EXPECTED-OUTPUT ----- */
-/*
- *struct padded_a_lot {
- * int a;
- * long: 32;
- * long: 64;
- * long: 64;
- * int b;
- *};
- *
- */
-/* ------ END-EXPECTED-OUTPUT ------ */
-
struct padded_a_lot {
int a;
- /* 32 bit of implicit padding here, which algo will make explicit */
long: 64;
long: 64;
int b;
};
+/* ------ END-EXPECTED-OUTPUT ------ */
+
/* ----- START-EXPECTED-OUTPUT ----- */
/*
*struct padded_cache_line {
* int a;
- * long: 32;
* long: 64;
* long: 64;
* long: 64;
* int b;
- * long: 32;
* long: 64;
* long: 64;
* long: 64;
@@ -85,7 +72,7 @@ struct padded_cache_line {
*struct zone {
* int a;
* short b;
- * short: 16;
+ * long: 0;
* struct zone_padding __pad__;
*};
*
@@ -108,6 +95,131 @@ struct padding_wo_named_members {
long: 64;
};
+struct padding_weird_1 {
+ int a;
+ long: 64;
+ short: 16;
+ short b;
+};
+
+/* ------ END-EXPECTED-OUTPUT ------ */
+
+/* ----- START-EXPECTED-OUTPUT ----- */
+/*
+ *struct padding_weird_2 {
+ * long: 56;
+ * char a;
+ * long: 56;
+ * char b;
+ * char: 8;
+ *};
+ *
+ */
+/* ------ END-EXPECTED-OUTPUT ------ */
+struct padding_weird_2 {
+ int: 32; /* these paddings will be collapsed into `long: 56;` */
+ short: 16;
+ char: 8;
+ char a;
+ int: 32; /* these paddings will be collapsed into `long: 56;` */
+ short: 16;
+ char: 8;
+ char b;
+ char: 8;
+};
+
+/* ----- START-EXPECTED-OUTPUT ----- */
+struct exact_1byte {
+ char x;
+};
+
+struct padded_1byte {
+ char: 8;
+};
+
+struct exact_2bytes {
+ short x;
+};
+
+struct padded_2bytes {
+ short: 16;
+};
+
+struct exact_4bytes {
+ int x;
+};
+
+struct padded_4bytes {
+ int: 32;
+};
+
+struct exact_8bytes {
+ long x;
+};
+
+struct padded_8bytes {
+ long: 64;
+};
+
+struct ff_periodic_effect {
+ int: 32;
+ short magnitude;
+ long: 0;
+ short phase;
+ long: 0;
+ int: 32;
+ int custom_len;
+ short *custom_data;
+};
+
+struct ib_wc {
+ long: 64;
+ long: 64;
+ int: 32;
+ int byte_len;
+ void *qp;
+ union {} ex;
+ long: 64;
+ int slid;
+ int wc_flags;
+ long: 64;
+ char smac[6];
+ long: 0;
+ char network_hdr_type;
+};
+
+struct acpi_object_method {
+ long: 64;
+ char: 8;
+ char type;
+ short reference_count;
+ char flags;
+ short: 0;
+ char: 8;
+ char sync_level;
+ long: 64;
+ void *node;
+ void *aml_start;
+ union {} dispatch;
+ long: 64;
+ int aml_length;
+};
+
+struct nested_unpacked {
+ int x;
+};
+
+struct nested_packed {
+ struct nested_unpacked a;
+ char c;
+} __attribute__((packed));
+
+struct outer_mixed_but_unpacked {
+ struct nested_packed b1;
+ short a1;
+ struct nested_packed b2;
+};
+
/* ------ END-EXPECTED-OUTPUT ------ */
int f(struct {
@@ -117,6 +229,20 @@ int f(struct {
struct padded_cache_line _4;
struct zone _5;
struct padding_wo_named_members _6;
+ struct padding_weird_1 _7;
+ struct padding_weird_2 _8;
+ struct exact_1byte _100;
+ struct padded_1byte _101;
+ struct exact_2bytes _102;
+ struct padded_2bytes _103;
+ struct exact_4bytes _104;
+ struct padded_4bytes _105;
+ struct exact_8bytes _106;
+ struct padded_8bytes _107;
+ struct ff_periodic_effect _200;
+ struct ib_wc _201;
+ struct acpi_object_method _202;
+ struct outer_mixed_but_unpacked _203;
} *_)
{
return 0;
diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
index 4ee4748133fe..26fffb02ed10 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
@@ -25,6 +25,39 @@ typedef enum {
H = 2,
} e3_t;
+/* ----- START-EXPECTED-OUTPUT ----- */
+/*
+ *enum e_byte {
+ * EBYTE_1 = 0,
+ * EBYTE_2 = 1,
+ *} __attribute__((mode(byte)));
+ *
+ */
+/* ----- END-EXPECTED-OUTPUT ----- */
+enum e_byte {
+ EBYTE_1,
+ EBYTE_2,
+} __attribute__((mode(byte)));
+
+/* ----- START-EXPECTED-OUTPUT ----- */
+/*
+ *enum e_word {
+ * EWORD_1 = 0LL,
+ * EWORD_2 = 1LL,
+ *} __attribute__((mode(word)));
+ *
+ */
+/* ----- END-EXPECTED-OUTPUT ----- */
+enum e_word {
+ EWORD_1,
+ EWORD_2,
+} __attribute__((mode(word))); /* force to use 8-byte backing for this enum */
+
+/* ----- START-EXPECTED-OUTPUT ----- */
+enum e_big {
+ EBIG_1 = 1000000000000ULL,
+};
+
typedef int int_t;
typedef volatile const int * volatile const crazy_ptr_t;
@@ -224,6 +257,9 @@ struct root_struct {
enum e2 _2;
e2_t _2_1;
e3_t _2_2;
+ enum e_byte _100;
+ enum e_word _101;
+ enum e_big _102;
struct struct_w_typedefs _3;
anon_struct_t _7;
struct struct_fwd *_8;
diff --git a/tools/testing/selftests/bpf/progs/jit_probe_mem.c b/tools/testing/selftests/bpf/progs/jit_probe_mem.c
new file mode 100644
index 000000000000..2d2e61470794
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/jit_probe_mem.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+static struct prog_test_ref_kfunc __kptr_ref *v;
+long total_sum = -1;
+
+extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym;
+extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym;
+
+SEC("tc")
+int test_jit_probe_mem(struct __sk_buff *ctx)
+{
+ struct prog_test_ref_kfunc *p;
+ unsigned long zero = 0, sum;
+
+ p = bpf_kfunc_call_test_acquire(&zero);
+ if (!p)
+ return 1;
+
+ p = bpf_kptr_xchg(&v, p);
+ if (p)
+ goto release_out;
+
+ /* Direct map value access of kptr, should be PTR_UNTRUSTED */
+ p = v;
+ if (!p)
+ return 1;
+
+ asm volatile (
+ "r9 = %[p];"
+ "%[sum] = 0;"
+
+ /* r8 = p->a */
+ "r8 = *(u32 *)(r9 + 0);"
+ "%[sum] += r8;"
+
+ /* r8 = p->b */
+ "r8 = *(u32 *)(r9 + 4);"
+ "%[sum] += r8;"
+
+ "r9 += 8;"
+ /* r9 = p->a */
+ "r9 = *(u32 *)(r9 - 8);"
+ "%[sum] += r9;"
+
+ : [sum] "=r"(sum)
+ : [p] "r"(p)
+ : "r8", "r9"
+ );
+
+ total_sum = sum;
+ return 0;
+release_out:
+ bpf_kfunc_call_test_release(p);
+ return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
index 98af55f0bcd3..508da4a23c4f 100644
--- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
@@ -82,6 +82,27 @@ int gre_set_tunnel(struct __sk_buff *skb)
}
SEC("tc")
+int gre_set_tunnel_no_key(struct __sk_buff *skb)
+{
+ int ret;
+ struct bpf_tunnel_key key;
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
+ key.tunnel_ttl = 64;
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_ZERO_CSUM_TX | BPF_F_SEQ_NUMBER |
+ BPF_F_NO_TUNNEL_KEY);
+ if (ret < 0) {
+ log_err(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("tc")
int gre_get_tunnel(struct __sk_buff *skb)
{
int ret;
diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh
index 2eaedc1d9ed3..06857b689c11 100755
--- a/tools/testing/selftests/bpf/test_tunnel.sh
+++ b/tools/testing/selftests/bpf/test_tunnel.sh
@@ -66,15 +66,20 @@ config_device()
add_gre_tunnel()
{
+ tun_key=
+ if [ -n "$1" ]; then
+ tun_key="key $1"
+ fi
+
# at_ns0 namespace
ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE seq key 2 \
+ ip link add dev $DEV_NS type $TYPE seq $tun_key \
local 172.16.1.100 remote 172.16.1.200
ip netns exec at_ns0 ip link set dev $DEV_NS up
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
# root namespace
- ip link add dev $DEV type $TYPE key 2 external
+ ip link add dev $DEV type $TYPE $tun_key external
ip link set dev $DEV up
ip addr add dev $DEV 10.1.1.200/24
}
@@ -238,7 +243,7 @@ test_gre()
check $TYPE
config_device
- add_gre_tunnel
+ add_gre_tunnel 2
attach_bpf $DEV gre_set_tunnel gre_get_tunnel
ping $PING_ARG 10.1.1.100
check_err $?
@@ -253,6 +258,30 @@ test_gre()
echo -e ${GREEN}"PASS: $TYPE"${NC}
}
+test_gre_no_tunnel_key()
+{
+ TYPE=gre
+ DEV_NS=gre00
+ DEV=gre11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_gre_tunnel
+ attach_bpf $DEV gre_set_tunnel_no_key gre_get_tunnel
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
test_ip6gre()
{
TYPE=ip6gre
@@ -589,6 +618,7 @@ cleanup()
ip link del ipip6tnl11 2> /dev/null
ip link del ip6ip6tnl11 2> /dev/null
ip link del gretap11 2> /dev/null
+ ip link del gre11 2> /dev/null
ip link del ip6gre11 2> /dev/null
ip link del ip6gretap11 2> /dev/null
ip link del geneve11 2> /dev/null
@@ -641,6 +671,10 @@ bpf_tunnel_test()
test_gre
errors=$(( $errors + $? ))
+ echo "Testing GRE tunnel (without tunnel keys)..."
+ test_gre_no_tunnel_key
+ errors=$(( $errors + $? ))
+
echo "Testing IP6GRE tunnel..."
test_ip6gre
errors=$(( $errors + $? ))